From f7005142dacea1769fba0152c493aaa61b33205c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 21 Dec 2020 17:29:34 +0200 Subject: spi: uapi: unify SPI modes into a single spi.h header This change moves all the SPI mode bits into a separate 'spi.h' header in uAPI. This is meant to re-use these definitions inside the kernel as well as export them to userspace (via uAPI). The SPI mode definitions have usually been duplicated between between 'include/linux/spi/spi.h' and 'include/uapi/linux/spi/spidev.h', so whenever adding a new entry, this would need to be put in both headers. They've been moved from 'include/linux/spi/spi.h', since that seems a bit more complete; the bits have descriptions and there is the SPI_MODE_X_MASK. This change also does a conversion of these bitfields to _BITUL() macro. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-1-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- include/uapi/linux/spi/spi.h | 31 +++++++++++++++++++++++++++++++ include/uapi/linux/spi/spidev.h | 30 +----------------------------- 2 files changed, 32 insertions(+), 29 deletions(-) create mode 100644 include/uapi/linux/spi/spi.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h new file mode 100644 index 000000000000..703b586f35df --- /dev/null +++ b/include/uapi/linux/spi/spi.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _UAPI_SPI_H +#define _UAPI_SPI_H + +#include + +#define SPI_CPHA _BITUL(0) /* clock phase */ +#define SPI_CPOL _BITUL(1) /* clock polarity */ + +#define SPI_MODE_0 (0|0) /* (original MicroWire) */ +#define SPI_MODE_1 (0|SPI_CPHA) +#define SPI_MODE_2 (SPI_CPOL|0) +#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) +#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) + +#define SPI_CS_HIGH _BITUL(2) /* chipselect active high? */ +#define SPI_LSB_FIRST _BITUL(3) /* per-word bits-on-wire */ +#define SPI_3WIRE _BITUL(4) /* SI/SO signals shared */ +#define SPI_LOOP _BITUL(5) /* loopback mode */ +#define SPI_NO_CS _BITUL(6) /* 1 dev/bus, no chipselect */ +#define SPI_READY _BITUL(7) /* slave pulls low to pause */ +#define SPI_TX_DUAL _BITUL(8) /* transmit with 2 wires */ +#define SPI_TX_QUAD _BITUL(9) /* transmit with 4 wires */ +#define SPI_RX_DUAL _BITUL(10) /* receive with 2 wires */ +#define SPI_RX_QUAD _BITUL(11) /* receive with 4 wires */ +#define SPI_CS_WORD _BITUL(12) /* toggle cs after each word */ +#define SPI_TX_OCTAL _BITUL(13) /* transmit with 8 wires */ +#define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ +#define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ + +#endif /* _UAPI_SPI_H */ diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index d56427c0b3e0..0c3da08f2aff 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -25,35 +25,7 @@ #include #include - -/* User space versions of kernel symbols for SPI clocking modes, - * matching - */ - -#define SPI_CPHA 0x01 -#define SPI_CPOL 0x02 - -#define SPI_MODE_0 (0|0) -#define SPI_MODE_1 (0|SPI_CPHA) -#define SPI_MODE_2 (SPI_CPOL|0) -#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) - -#define SPI_CS_HIGH 0x04 -#define SPI_LSB_FIRST 0x08 -#define SPI_3WIRE 0x10 -#define SPI_LOOP 0x20 -#define SPI_NO_CS 0x40 -#define SPI_READY 0x80 -#define SPI_TX_DUAL 0x100 -#define SPI_TX_QUAD 0x200 -#define SPI_RX_DUAL 0x400 -#define SPI_RX_QUAD 0x800 -#define SPI_CS_WORD 0x1000 -#define SPI_TX_OCTAL 0x2000 -#define SPI_RX_OCTAL 0x4000 -#define SPI_3WIRE_HIZ 0x8000 - -/*---------------------------------------------------------------------------*/ +#include /* IOCTL commands */ -- cgit v1.2.3 From d962608ce2188a1d46ec9d356d6fad5cd6fc0341 Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Mon, 21 Dec 2020 17:29:35 +0200 Subject: spi: Add SPI_NO_TX/RX support Transmit/receive only is a valid SPI mode. For example, the MOSI/TX line might be missing from an ADC while for a DAC the MISO/RX line may be optional. This patch adds these two new modes: SPI_NO_TX and SPI_NO_RX. This way, the drivers will be able to identify if any of these two lines is missing and to adjust the transfers accordingly. Signed-off-by: Dragos Bogdan Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-2-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 25 ++++++++++++++++++++----- include/linux/spi/spi.h | 17 +++++++++++++++++ include/uapi/linux/spi/spi.h | 10 ++++++++++ 3 files changed, 47 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 51d7c004fbab..ca75f4036eda 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1941,6 +1941,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, /* Device DUAL/QUAD mode */ if (!of_property_read_u32(nc, "spi-tx-bus-width", &value)) { switch (value) { + case 0: + spi->mode |= SPI_NO_TX; + break; case 1: break; case 2: @@ -1962,6 +1965,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, if (!of_property_read_u32(nc, "spi-rx-bus-width", &value)) { switch (value) { + case 0: + spi->mode |= SPI_NO_RX; + break; case 1: break; case 2: @@ -3329,12 +3335,16 @@ int spi_setup(struct spi_device *spi) unsigned bad_bits, ugly_bits; int status; - /* check mode to prevent that DUAL and QUAD set at the same time + /* + * check mode to prevent that any two of DUAL, QUAD and NO_MOSI/MISO + * are set at the same time */ - if (((spi->mode & SPI_TX_DUAL) && (spi->mode & SPI_TX_QUAD)) || - ((spi->mode & SPI_RX_DUAL) && (spi->mode & SPI_RX_QUAD))) { + if ((hweight_long(spi->mode & + (SPI_TX_DUAL | SPI_TX_QUAD | SPI_NO_TX)) > 1) || + (hweight_long(spi->mode & + (SPI_RX_DUAL | SPI_RX_QUAD | SPI_NO_RX)) > 1)) { dev_err(&spi->dev, - "setup: can not select dual and quad at the same time\n"); + "setup: can not select any two of dual, quad and no-rx/tx at the same time\n"); return -EINVAL; } /* if it is SPI_3WIRE mode, DUAL and QUAD should be forbidden @@ -3348,7 +3358,8 @@ int spi_setup(struct spi_device *spi) * SPI_CS_WORD has a fallback software implementation, * so it is ignored here. */ - bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD); + bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD | + SPI_NO_TX | SPI_NO_RX); /* nothing prevents from working with active-high CS in case if it * is driven by GPIO. */ @@ -3610,6 +3621,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) * 2. check tx/rx_nbits match the mode in spi_device */ if (xfer->tx_buf) { + if (spi->mode & SPI_NO_TX) + return -EINVAL; if (xfer->tx_nbits != SPI_NBITS_SINGLE && xfer->tx_nbits != SPI_NBITS_DUAL && xfer->tx_nbits != SPI_NBITS_QUAD) @@ -3623,6 +3636,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) } /* check transfer rx_nbits */ if (xfer->rx_buf) { + if (spi->mode & SPI_NO_RX) + return -EINVAL; if (xfer->rx_nbits != SPI_NBITS_SINGLE && xfer->rx_nbits != SPI_NBITS_DUAL && xfer->rx_nbits != SPI_NBITS_QUAD) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a08c3f37e202..9bfdfaf286eb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -6,6 +6,7 @@ #ifndef __LINUX_SPI_H #define __LINUX_SPI_H +#include #include #include #include @@ -166,6 +167,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; +#define SPI_NO_TX BIT(31) /* no transmit wire */ +#define SPI_NO_RX BIT(30) /* no receive wire */ + /* + * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. + * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, + * which is defined in 'include/uapi/linux/spi/spi.h'. + * The bits defined here are from bit 31 downwards, while in + * SPI_MODE_USER_MASK are from 0 upwards. + * These bits must not overlap. A static assert check should make sure of that. + * If adding extra bits, make sure to decrease the bit index below as well. + */ +#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) u32 mode; int irq; void *controller_state; @@ -189,6 +202,10 @@ struct spi_device { */ }; +/* Make sure that SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK don't overlap */ +static_assert((SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK) == 0, + "SPI_MODE_USER_MASK & SPI_MODE_KERNEL_MASK must not overlap"); + static inline struct spi_device *to_spi_device(struct device *dev) { return dev ? container_of(dev, struct spi_device, dev) : NULL; diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 703b586f35df..236a85f08ded 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -28,4 +28,14 @@ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ +/* + * All the bits defined above should be covered by SPI_MODE_USER_MASK. + * The SPI_MODE_USER_MASK has the SPI_MODE_KERNEL_MASK counterpart in + * 'include/linux/spi/spi.h'. The bits defined here are from bit 0 upwards + * while in SPI_MODE_KERNEL_MASK they are from the other end downwards. + * These bits must not overlap. A static assert check should make sure of that. + * If adding extra bits, make sure to increase the bit index below as well. + */ +#define SPI_MODE_USER_MASK (_BITUL(16) - 1) + #endif /* _UAPI_SPI_H */ -- cgit v1.2.3 From c9784e23c1020e63d6dba5e10ca8bf3d8b85c19c Mon Sep 17 00:00:00 2001 From: Dave Penkler Date: Tue, 15 Dec 2020 16:56:19 +0100 Subject: USB: usbtmc: Add USBTMC_IOCTL_GET_STB This new ioctl reads the status byte (STB) from the device and returns the STB unmodified to the application. The srq_asserted bit is not taken into account and not changed. This ioctl is useful to support non USBTMC-488 compliant devices. Tested-by: Jian-Wei Wu Reviewed-by: Guido Kiener Signed-off-by: Dave Penkler Link: https://lore.kernel.org/r/20201215155621.9592-3-dpenkler@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 6 ++++++ include/uapi/linux/usb/tmc.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 189f06dcb7d3..8918e2182eca 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -2149,6 +2149,12 @@ static long usbtmc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) file_data->auto_abort = !!tmp_byte; break; + case USBTMC_IOCTL_GET_STB: + retval = usbtmc_get_stb(file_data, &tmp_byte); + if (retval > 0) + retval = put_user(tmp_byte, (__u8 __user *)arg); + break; + case USBTMC_IOCTL_CANCEL_IO: retval = usbtmc_ioctl_cancel_io(file_data); break; diff --git a/include/uapi/linux/usb/tmc.h b/include/uapi/linux/usb/tmc.h index fdd4d88a7b95..1e7878fe591f 100644 --- a/include/uapi/linux/usb/tmc.h +++ b/include/uapi/linux/usb/tmc.h @@ -102,6 +102,8 @@ struct usbtmc_message { #define USBTMC_IOCTL_MSG_IN_ATTR _IOR(USBTMC_IOC_NR, 24, __u8) #define USBTMC_IOCTL_AUTO_ABORT _IOW(USBTMC_IOC_NR, 25, __u8) +#define USBTMC_IOCTL_GET_STB _IOR(USBTMC_IOC_NR, 26, __u8) + /* Cancel and cleanup asynchronous calls */ #define USBTMC_IOCTL_CANCEL_IO _IO(USBTMC_IOC_NR, 35) #define USBTMC_IOCTL_CLEANUP_IO _IO(USBTMC_IOC_NR, 36) -- cgit v1.2.3 From d1d9defdc6d582119d29f5d88f810b72bb1837fa Mon Sep 17 00:00:00 2001 From: Dave Penkler Date: Tue, 15 Dec 2020 16:56:20 +0100 Subject: USB: usbtmc: Add separate USBTMC_IOCTL_GET_SRQ_STB This new ioctl only returns the status byte (STB) that was originally sent by the device due to a service request (SRQ) condition. This ioctl checks the srq_asserted bit of the associated file descriptor. If set, the srq_asserted bit is reset and the cached STB with original SRQ information is returned. Otherwise the ioctl returns the error code ENOMSG. This ioctl is useful to support non USBTMC-488 compliant devices. Time sensitive applications can read the cached STB without incurring the cost of an urb transaction over the bus. Tested-by: Jian-Wei Wu Reviewed-by: Guido Kiener Signed-off-by: Dave Penkler Link: https://lore.kernel.org/r/20201215155621.9592-4-dpenkler@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 31 +++++++++++++++++++++++++++++++ include/uapi/linux/usb/tmc.h | 1 + 2 files changed, 32 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 8918e2182eca..d2fcc698c745 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -571,6 +571,32 @@ static int usbtmc488_ioctl_read_stb(struct usbtmc_file_data *file_data, } +static int usbtmc_ioctl_get_srq_stb(struct usbtmc_file_data *file_data, + void __user *arg) +{ + struct usbtmc_device_data *data = file_data->data; + struct device *dev = &data->intf->dev; + int srq_asserted = 0; + __u8 stb = 0; + int rv; + + spin_lock_irq(&data->dev_lock); + srq_asserted = atomic_xchg(&file_data->srq_asserted, srq_asserted); + + if (srq_asserted) { + stb = file_data->srq_byte; + spin_unlock_irq(&data->dev_lock); + rv = put_user(stb, (__u8 __user *)arg); + } else { + spin_unlock_irq(&data->dev_lock); + rv = -ENOMSG; + } + + dev_dbg(dev, "stb:0x%02x with srq received %d\n", (unsigned int)stb, rv); + + return rv; +} + static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, __u32 __user *arg) { @@ -2155,6 +2181,11 @@ static long usbtmc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) retval = put_user(tmp_byte, (__u8 __user *)arg); break; + case USBTMC_IOCTL_GET_SRQ_STB: + retval = usbtmc_ioctl_get_srq_stb(file_data, + (void __user *)arg); + break; + case USBTMC_IOCTL_CANCEL_IO: retval = usbtmc_ioctl_cancel_io(file_data); break; diff --git a/include/uapi/linux/usb/tmc.h b/include/uapi/linux/usb/tmc.h index 1e7878fe591f..d791cc58a7f0 100644 --- a/include/uapi/linux/usb/tmc.h +++ b/include/uapi/linux/usb/tmc.h @@ -103,6 +103,7 @@ struct usbtmc_message { #define USBTMC_IOCTL_AUTO_ABORT _IOW(USBTMC_IOC_NR, 25, __u8) #define USBTMC_IOCTL_GET_STB _IOR(USBTMC_IOC_NR, 26, __u8) +#define USBTMC_IOCTL_GET_SRQ_STB _IOR(USBTMC_IOC_NR, 27, __u8) /* Cancel and cleanup asynchronous calls */ #define USBTMC_IOCTL_CANCEL_IO _IO(USBTMC_IOC_NR, 35) -- cgit v1.2.3 From 99668f618062816ca7ba639b007eb145b9d3d41e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:10 -0700 Subject: fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED Now that we support non-blocking path resolution internally, expose it via openat2() in the struct open_how ->resolve flags. This allows applications using openat2() to limit path resolution to the extent that it is already cached. If the lookup cannot be satisfied in a non-blocking manner, openat2(2) will return -1/-EAGAIN. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro --- fs/open.c | 6 ++++++ include/linux/fcntl.h | 2 +- include/uapi/linux/openat2.h | 4 ++++ 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/open.c b/fs/open.c index 1e06e443a565..ca5444733acd 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1091,6 +1091,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 921e750843e6..766fcd973beb 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -19,7 +19,7 @@ /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ - RESOLVE_BENEATH | RESOLVE_IN_ROOT) + RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED) /* List of all open_how "versions". */ #define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index 58b1eb711360..a5feb7604948 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ -- cgit v1.2.3 From 178f6ab77e617c984d6520b92e747075a12676ff Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:58 +0100 Subject: platform/surface: Add Surface Aggregator user-space interface Add a misc-device providing user-space access to the Surface Aggregator EC, mainly intended for debugging, testing, and reverse-engineering. This interface gives user-space applications the ability to send requests to the EC and receive the corresponding responses. The device-file is managed by a pseudo platform-device and corresponding driver to avoid dependence on the dedicated bus, allowing it to be loaded in a minimal configuration. A python library and scripts to access this device can be found at [1]. [1]: https://github.com/linux-surface/surface-aggregator-module/tree/master/scripts/ssam Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20201221183959.1186143-9-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- .../driver-api/surface_aggregator/clients/cdev.rst | 87 ++++++ .../surface_aggregator/clients/index.rst | 12 +- Documentation/userspace-api/ioctl/ioctl-number.rst | 2 + MAINTAINERS | 2 + drivers/platform/surface/Kconfig | 17 ++ drivers/platform/surface/Makefile | 1 + drivers/platform/surface/surface_aggregator_cdev.c | 303 +++++++++++++++++++++ include/uapi/linux/surface_aggregator/cdev.h | 78 ++++++ 8 files changed, 501 insertions(+), 1 deletion(-) create mode 100644 Documentation/driver-api/surface_aggregator/clients/cdev.rst create mode 100644 drivers/platform/surface/surface_aggregator_cdev.c create mode 100644 include/uapi/linux/surface_aggregator/cdev.h (limited to 'include/uapi/linux') diff --git a/Documentation/driver-api/surface_aggregator/clients/cdev.rst b/Documentation/driver-api/surface_aggregator/clients/cdev.rst new file mode 100644 index 000000000000..248c1372d879 --- /dev/null +++ b/Documentation/driver-api/surface_aggregator/clients/cdev.rst @@ -0,0 +1,87 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +.. |u8| replace:: :c:type:`u8 ` +.. |u16| replace:: :c:type:`u16 ` +.. |ssam_cdev_request| replace:: :c:type:`struct ssam_cdev_request ` +.. |ssam_cdev_request_flags| replace:: :c:type:`enum ssam_cdev_request_flags ` + +============================== +User-Space EC Interface (cdev) +============================== + +The ``surface_aggregator_cdev`` module provides a misc-device for the SSAM +controller to allow for a (more or less) direct connection from user-space to +the SAM EC. It is intended to be used for development and debugging, and +therefore should not be used or relied upon in any other way. Note that this +module is not loaded automatically, but instead must be loaded manually. + +The provided interface is accessible through the ``/dev/surface/aggregator`` +device-file. All functionality of this interface is provided via IOCTLs. +These IOCTLs and their respective input/output parameter structs are defined in +``include/uapi/linux/surface_aggregator/cdev.h``. + +A small python library and scripts for accessing this interface can be found +at https://github.com/linux-surface/surface-aggregator-module/tree/master/scripts/ssam. + + +Controller IOCTLs +================= + +The following IOCTLs are provided: + +.. flat-table:: Controller IOCTLs + :widths: 1 1 1 1 4 + :header-rows: 1 + + * - Type + - Number + - Direction + - Name + - Description + + * - ``0xA5`` + - ``1`` + - ``WR`` + - ``REQUEST`` + - Perform synchronous SAM request. + + +``REQUEST`` +----------- + +Defined as ``_IOWR(0xA5, 1, struct ssam_cdev_request)``. + +Executes a synchronous SAM request. The request specification is passed in +as argument of type |ssam_cdev_request|, which is then written to/modified +by the IOCTL to return status and result of the request. + +Request payload data must be allocated separately and is passed in via the +``payload.data`` and ``payload.length`` members. If a response is required, +the response buffer must be allocated by the caller and passed in via the +``response.data`` member. The ``response.length`` member must be set to the +capacity of this buffer, or if no response is required, zero. Upon +completion of the request, the call will write the response to the response +buffer (if its capacity allows it) and overwrite the length field with the +actual size of the response, in bytes. + +Additionally, if the request has a response, this must be indicated via the +request flags, as is done with in-kernel requests. Request flags can be set +via the ``flags`` member and the values correspond to the values found in +|ssam_cdev_request_flags|. + +Finally, the status of the request itself is returned in the ``status`` +member (a negative errno value indicating failure). Note that failure +indication of the IOCTL is separated from failure indication of the request: +The IOCTL returns a negative status code if anything failed during setup of +the request (``-EFAULT``) or if the provided argument or any of its fields +are invalid (``-EINVAL``). In this case, the status value of the request +argument may be set, providing more detail on what went wrong (e.g. +``-ENOMEM`` for out-of-memory), but this value may also be zero. The IOCTL +will return with a zero status code in case the request has been set up, +submitted, and completed (i.e. handed back to user-space) successfully from +inside the IOCTL, but the request ``status`` member may still be negative in +case the actual execution of the request failed after it has been submitted. + +A full definition of the argument struct is provided below: + +.. kernel-doc:: include/uapi/linux/surface_aggregator/cdev.h diff --git a/Documentation/driver-api/surface_aggregator/clients/index.rst b/Documentation/driver-api/surface_aggregator/clients/index.rst index 31e026d96102..ab260ec82cfb 100644 --- a/Documentation/driver-api/surface_aggregator/clients/index.rst +++ b/Documentation/driver-api/surface_aggregator/clients/index.rst @@ -7,4 +7,14 @@ Client Driver Documentation This is the documentation for client drivers themselves. Refer to :doc:`../client` for documentation on how to write client drivers. -.. Place documentation for individual client drivers here. +.. toctree:: + :maxdepth: 1 + + cdev + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..b5231d7f9200 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -324,6 +324,8 @@ Code Seq# Include File Comments 0xA3 90-9F linux/dtlk.h 0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem 0xA4 00-1F uapi/asm/sgx.h +0xA5 01 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator + 0xAA 00-3F linux/uapi/linux/userfaultfd.h 0xAB 00-1F linux/nbd.h 0xAC 00-1F linux/raw.h diff --git a/MAINTAINERS b/MAINTAINERS index 41f082551942..9bd55c842898 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11820,7 +11820,9 @@ W: https://github.com/linux-surface/surface-aggregator-module C: irc://chat.freenode.net/##linux-surface F: Documentation/driver-api/surface_aggregator/ F: drivers/platform/surface/aggregator/ +F: drivers/platform/surface/surface_aggregator_cdev.c F: include/linux/surface_aggregator/ +F: include/uapi/linux/surface_aggregator/ MICROTEK X6 SCANNER M: Oliver Neukum diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 2916a47b130e..988b2de6b500 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -41,6 +41,23 @@ config SURFACE_3_POWER_OPREGION This driver provides support for ACPI operation region of the Surface 3 battery platform driver. +config SURFACE_AGGREGATOR_CDEV + tristate "Surface System Aggregator Module User-Space Interface" + depends on SURFACE_AGGREGATOR + help + Provides a misc-device interface to the Surface System Aggregator + Module (SSAM) controller. + + This option provides a module (called surface_aggregator_cdev), that, + when loaded, will add a client device (and its respective driver) to + the SSAM controller. Said client device manages a misc-device + interface (/dev/surface/aggregator), which can be used by user-space + tools to directly communicate with the SSAM EC by sending requests and + receiving the corresponding responses. + + The provided interface is intended for debugging and development only, + and should not be used otherwise. + config SURFACE_GPE tristate "Surface GPE/Lid Support Driver" depends on DMI diff --git a/drivers/platform/surface/Makefile b/drivers/platform/surface/Makefile index 034134fe0264..161f0ad05795 100644 --- a/drivers/platform/surface/Makefile +++ b/drivers/platform/surface/Makefile @@ -8,5 +8,6 @@ obj-$(CONFIG_SURFACE3_WMI) += surface3-wmi.o obj-$(CONFIG_SURFACE_3_BUTTON) += surface3_button.o obj-$(CONFIG_SURFACE_3_POWER_OPREGION) += surface3_power.o obj-$(CONFIG_SURFACE_AGGREGATOR) += aggregator/ +obj-$(CONFIG_SURFACE_AGGREGATOR_CDEV) += surface_aggregator_cdev.o obj-$(CONFIG_SURFACE_GPE) += surface_gpe.o obj-$(CONFIG_SURFACE_PRO3_BUTTON) += surfacepro3_button.o diff --git a/drivers/platform/surface/surface_aggregator_cdev.c b/drivers/platform/surface/surface_aggregator_cdev.c new file mode 100644 index 000000000000..340d15b148b9 --- /dev/null +++ b/drivers/platform/surface/surface_aggregator_cdev.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Provides user-space access to the SSAM EC via the /dev/surface/aggregator + * misc device. Intended for debugging and development. + * + * Copyright (C) 2020 Maximilian Luz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define SSAM_CDEV_DEVICE_NAME "surface_aggregator_cdev" + +struct ssam_cdev { + struct kref kref; + struct rw_semaphore lock; + struct ssam_controller *ctrl; + struct miscdevice mdev; +}; + +static void __ssam_cdev_release(struct kref *kref) +{ + kfree(container_of(kref, struct ssam_cdev, kref)); +} + +static struct ssam_cdev *ssam_cdev_get(struct ssam_cdev *cdev) +{ + if (cdev) + kref_get(&cdev->kref); + + return cdev; +} + +static void ssam_cdev_put(struct ssam_cdev *cdev) +{ + if (cdev) + kref_put(&cdev->kref, __ssam_cdev_release); +} + +static int ssam_cdev_device_open(struct inode *inode, struct file *filp) +{ + struct miscdevice *mdev = filp->private_data; + struct ssam_cdev *cdev = container_of(mdev, struct ssam_cdev, mdev); + + filp->private_data = ssam_cdev_get(cdev); + return stream_open(inode, filp); +} + +static int ssam_cdev_device_release(struct inode *inode, struct file *filp) +{ + ssam_cdev_put(filp->private_data); + return 0; +} + +static long ssam_cdev_request(struct ssam_cdev *cdev, unsigned long arg) +{ + struct ssam_cdev_request __user *r; + struct ssam_cdev_request rqst; + struct ssam_request spec; + struct ssam_response rsp; + const void __user *plddata; + void __user *rspdata; + int status = 0, ret = 0, tmp; + + r = (struct ssam_cdev_request __user *)arg; + ret = copy_struct_from_user(&rqst, sizeof(rqst), r, sizeof(*r)); + if (ret) + goto out; + + plddata = u64_to_user_ptr(rqst.payload.data); + rspdata = u64_to_user_ptr(rqst.response.data); + + /* Setup basic request fields. */ + spec.target_category = rqst.target_category; + spec.target_id = rqst.target_id; + spec.command_id = rqst.command_id; + spec.instance_id = rqst.instance_id; + spec.flags = 0; + spec.length = rqst.payload.length; + spec.payload = NULL; + + if (rqst.flags & SSAM_CDEV_REQUEST_HAS_RESPONSE) + spec.flags |= SSAM_REQUEST_HAS_RESPONSE; + + if (rqst.flags & SSAM_CDEV_REQUEST_UNSEQUENCED) + spec.flags |= SSAM_REQUEST_UNSEQUENCED; + + rsp.capacity = rqst.response.length; + rsp.length = 0; + rsp.pointer = NULL; + + /* Get request payload from user-space. */ + if (spec.length) { + if (!plddata) { + ret = -EINVAL; + goto out; + } + + spec.payload = kzalloc(spec.length, GFP_KERNEL); + if (!spec.payload) { + ret = -ENOMEM; + goto out; + } + + if (copy_from_user((void *)spec.payload, plddata, spec.length)) { + ret = -EFAULT; + goto out; + } + } + + /* Allocate response buffer. */ + if (rsp.capacity) { + if (!rspdata) { + ret = -EINVAL; + goto out; + } + + rsp.pointer = kzalloc(rsp.capacity, GFP_KERNEL); + if (!rsp.pointer) { + ret = -ENOMEM; + goto out; + } + } + + /* Perform request. */ + status = ssam_request_sync(cdev->ctrl, &spec, &rsp); + if (status) + goto out; + + /* Copy response to user-space. */ + if (rsp.length && copy_to_user(rspdata, rsp.pointer, rsp.length)) + ret = -EFAULT; + +out: + /* Always try to set response-length and status. */ + tmp = put_user(rsp.length, &r->response.length); + if (tmp) + ret = tmp; + + tmp = put_user(status, &r->status); + if (tmp) + ret = tmp; + + /* Cleanup. */ + kfree(spec.payload); + kfree(rsp.pointer); + + return ret; +} + +static long __ssam_cdev_device_ioctl(struct ssam_cdev *cdev, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case SSAM_CDEV_REQUEST: + return ssam_cdev_request(cdev, arg); + + default: + return -ENOTTY; + } +} + +static long ssam_cdev_device_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct ssam_cdev *cdev = file->private_data; + long status; + + /* Ensure that controller is valid for as long as we need it. */ + if (down_read_killable(&cdev->lock)) + return -ERESTARTSYS; + + if (!cdev->ctrl) { + up_read(&cdev->lock); + return -ENODEV; + } + + status = __ssam_cdev_device_ioctl(cdev, cmd, arg); + + up_read(&cdev->lock); + return status; +} + +static const struct file_operations ssam_controller_fops = { + .owner = THIS_MODULE, + .open = ssam_cdev_device_open, + .release = ssam_cdev_device_release, + .unlocked_ioctl = ssam_cdev_device_ioctl, + .compat_ioctl = ssam_cdev_device_ioctl, + .llseek = noop_llseek, +}; + +static int ssam_dbg_device_probe(struct platform_device *pdev) +{ + struct ssam_controller *ctrl; + struct ssam_cdev *cdev; + int status; + + ctrl = ssam_client_bind(&pdev->dev); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl) == -ENODEV ? -EPROBE_DEFER : PTR_ERR(ctrl); + + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + return -ENOMEM; + + kref_init(&cdev->kref); + init_rwsem(&cdev->lock); + cdev->ctrl = ctrl; + + cdev->mdev.parent = &pdev->dev; + cdev->mdev.minor = MISC_DYNAMIC_MINOR; + cdev->mdev.name = "surface_aggregator"; + cdev->mdev.nodename = "surface/aggregator"; + cdev->mdev.fops = &ssam_controller_fops; + + status = misc_register(&cdev->mdev); + if (status) { + kfree(cdev); + return status; + } + + platform_set_drvdata(pdev, cdev); + return 0; +} + +static int ssam_dbg_device_remove(struct platform_device *pdev) +{ + struct ssam_cdev *cdev = platform_get_drvdata(pdev); + + misc_deregister(&cdev->mdev); + + /* + * The controller is only guaranteed to be valid for as long as the + * driver is bound. Remove controller so that any lingering open files + * cannot access it any more after we're gone. + */ + down_write(&cdev->lock); + cdev->ctrl = NULL; + up_write(&cdev->lock); + + ssam_cdev_put(cdev); + return 0; +} + +static struct platform_device *ssam_cdev_device; + +static struct platform_driver ssam_cdev_driver = { + .probe = ssam_dbg_device_probe, + .remove = ssam_dbg_device_remove, + .driver = { + .name = SSAM_CDEV_DEVICE_NAME, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +static int __init ssam_debug_init(void) +{ + int status; + + ssam_cdev_device = platform_device_alloc(SSAM_CDEV_DEVICE_NAME, + PLATFORM_DEVID_NONE); + if (!ssam_cdev_device) + return -ENOMEM; + + status = platform_device_add(ssam_cdev_device); + if (status) + goto err_device; + + status = platform_driver_register(&ssam_cdev_driver); + if (status) + goto err_driver; + + return 0; + +err_driver: + platform_device_del(ssam_cdev_device); +err_device: + platform_device_put(ssam_cdev_device); + return status; +} +module_init(ssam_debug_init); + +static void __exit ssam_debug_exit(void) +{ + platform_driver_unregister(&ssam_cdev_driver); + platform_device_unregister(ssam_cdev_device); +} +module_exit(ssam_debug_exit); + +MODULE_AUTHOR("Maximilian Luz "); +MODULE_DESCRIPTION("User-space interface for Surface System Aggregator Module"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/surface_aggregator/cdev.h b/include/uapi/linux/surface_aggregator/cdev.h new file mode 100644 index 000000000000..fbcce04abfe9 --- /dev/null +++ b/include/uapi/linux/surface_aggregator/cdev.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Surface System Aggregator Module (SSAM) user-space EC interface. + * + * Definitions, structs, and IOCTLs for the /dev/surface/aggregator misc + * device. This device provides direct user-space access to the SSAM EC. + * Intended for debugging and development. + * + * Copyright (C) 2020 Maximilian Luz + */ + +#ifndef _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H +#define _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H + +#include +#include + +/** + * enum ssam_cdev_request_flags - Request flags for SSAM cdev request IOCTL. + * + * @SSAM_CDEV_REQUEST_HAS_RESPONSE: + * Specifies that the request expects a response. If not set, the request + * will be directly completed after its underlying packet has been + * transmitted. If set, the request transport system waits for a response + * of the request. + * + * @SSAM_CDEV_REQUEST_UNSEQUENCED: + * Specifies that the request should be transmitted via an unsequenced + * packet. If set, the request must not have a response, meaning that this + * flag and the %SSAM_CDEV_REQUEST_HAS_RESPONSE flag are mutually + * exclusive. + */ +enum ssam_cdev_request_flags { + SSAM_CDEV_REQUEST_HAS_RESPONSE = 0x01, + SSAM_CDEV_REQUEST_UNSEQUENCED = 0x02, +}; + +/** + * struct ssam_cdev_request - Controller request IOCTL argument. + * @target_category: Target category of the SAM request. + * @target_id: Target ID of the SAM request. + * @command_id: Command ID of the SAM request. + * @instance_id: Instance ID of the SAM request. + * @flags: Request flags (see &enum ssam_cdev_request_flags). + * @status: Request status (output). + * @payload: Request payload (input data). + * @payload.data: Pointer to request payload data. + * @payload.length: Length of request payload data (in bytes). + * @response: Request response (output data). + * @response.data: Pointer to response buffer. + * @response.length: On input: Capacity of response buffer (in bytes). + * On output: Length of request response (number of bytes + * in the buffer that are actually used). + */ +struct ssam_cdev_request { + __u8 target_category; + __u8 target_id; + __u8 command_id; + __u8 instance_id; + __u16 flags; + __s16 status; + + struct { + __u64 data; + __u16 length; + __u8 __pad[6]; + } payload; + + struct { + __u64 data; + __u16 length; + __u8 __pad[6]; + } response; +} __attribute__((__packed__)); + +#define SSAM_CDEV_REQUEST _IOWR(0xA5, 1, struct ssam_cdev_request) + +#endif /* _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H */ -- cgit v1.2.3 From c762a2b846b619c0f92f23e2e8e16f70d20df800 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:39 +0100 Subject: tty: drop termiox user definitions As was concluded in a follow-up discussion of commit e0efb3168d34 (tty: Remove dead termiox code) [1], termiox ioctls never worked, so there is barely anyone using this interface. We can safely remove the user definitions for this never adopted interface. [1] https://lore.kernel.org/lkml/c1c9fc04-02eb-2260-195b-44c357f057c0@kernel.org/t/#u Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-12-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/termios.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/termios.h b/include/uapi/linux/termios.h index 33961d4e4de0..e6da9d4433d1 100644 --- a/include/uapi/linux/termios.h +++ b/include/uapi/linux/termios.h @@ -5,19 +5,4 @@ #include #include -#define NFF 5 - -struct termiox -{ - __u16 x_hflag; - __u16 x_cflag; - __u16 x_rflag[NFF]; - __u16 x_sflag; -}; - -#define RTSXOFF 0x0001 /* RTS flow control on input */ -#define CTSXON 0x0002 /* CTS flow control on output */ -#define DTRXOFF 0x0004 /* DTR flow control on input */ -#define DSRXON 0x0008 /* DCD flow control on output */ - #endif -- cgit v1.2.3 From 0f9f696a502e1b01fbb137a08f56f157da9d95eb Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 8 Jan 2021 16:47:59 -0800 Subject: mptcp: add set_flags command in PM netlink This patch added a new command MPTCP_PM_CMD_SET_FLAGS in PM netlink: In mptcp_nl_cmd_set_flags, parse the input address, get the backup value according to whether the address's FLAG_BACKUP flag is set from the user-space. Then check whether this address had been added in the local address list. If it had been, then call mptcp_nl_addr_backup to deal with this address. In mptcp_nl_addr_backup, traverse all the existing msk sockets to find the relevant sockets, and call mptcp_pm_nl_mp_prio_send_ack to send out a MP_PRIO ACK packet. Finally in mptcp_nl_cmd_set_flags, set or clear the address's FLAG_BACKUP flag. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + net/mptcp/pm_netlink.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 9762660df741..3674a451a18c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -82,6 +82,7 @@ enum { MPTCP_PM_CMD_FLUSH_ADDRS, MPTCP_PM_CMD_SET_LIMITS, MPTCP_PM_CMD_GET_LIMITS, + MPTCP_PM_CMD_SET_FLAGS, __MPTCP_PM_CMD_AFTER_LAST }; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index bf0d13c85a68..8f80099f1657 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1164,6 +1164,66 @@ fail: return -EMSGSIZE; } +static int mptcp_nl_addr_backup(struct net *net, + struct mptcp_addr_info *addr, + u8 bkup) +{ + long s_slot = 0, s_num = 0; + struct mptcp_sock *msk; + int ret = -EINVAL; + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + + if (list_empty(&msk->conn_list)) + goto next; + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + +next: + sock_put(sk); + cond_resched(); + } + + return ret; +} + +static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct pm_nl_pernet *pernet = genl_info_pm_nl(info); + struct mptcp_pm_addr_entry addr, *entry; + struct net *net = sock_net(skb->sk); + u8 bkup = 0; + int ret; + + ret = mptcp_pm_parse_addr(attr, info, true, &addr); + if (ret < 0) + return ret; + + if (addr.addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; + + list_for_each_entry(entry, &pernet->local_addr_list, list) { + if (addresses_equal(&entry->addr, &addr.addr, true)) { + ret = mptcp_nl_addr_backup(net, &entry->addr, bkup); + if (ret) + return ret; + + if (bkup) + entry->addr.flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->addr.flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + } + } + + return 0; +} + static const struct genl_small_ops mptcp_pm_ops[] = { { .cmd = MPTCP_PM_CMD_ADD_ADDR, @@ -1194,6 +1254,11 @@ static const struct genl_small_ops mptcp_pm_ops[] = { .cmd = MPTCP_PM_CMD_GET_LIMITS, .doit = mptcp_nl_cmd_get_limits, }, + { + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .doit = mptcp_nl_cmd_set_flags, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family mptcp_genl_family __ro_after_init = { -- cgit v1.2.3 From ad0bfc233ae2e7ee3bcb9a6089e4aa54e2b44fa1 Mon Sep 17 00:00:00 2001 From: Danilo Carvalho Date: Fri, 8 Jan 2021 22:21:04 +0000 Subject: Fix whitespace in uapi/linux/tcp.h. List of things fixed: - Two of the socket options were idented with spaces instead of tabs. - Trailing whitespace in some lines. - Improper spacing around parenthesis caught by checkpatch.pl. - Mix of space and tabs in tcp_word_hdr union. Signed-off-by: Danilo Carvalho Link: https://lore.kernel.org/r/20210108222104.2079472-1-doak@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 13ceeb395eb8..768e93bd5b51 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -51,7 +51,7 @@ struct tcphdr { fin:1; #else #error "Adjust your defines" -#endif +#endif __be16 window; __sum16 check; __be16 urg_ptr; @@ -62,14 +62,14 @@ struct tcphdr { * (union is compatible to any of its members) * This means this part of the code is -fstrict-aliasing safe now. */ -union tcp_word_hdr { +union tcp_word_hdr { struct tcphdr hdr; - __be32 words[5]; -}; + __be32 words[5]; +}; -#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) +#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) -enum { +enum { TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), @@ -80,7 +80,7 @@ enum { TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) -}; +}; /* * TCP general constants @@ -103,8 +103,8 @@ enum { #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #define TCP_CONGESTION 13 /* Congestion control algorithm */ #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ -#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ -#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ #define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_QUEUE 20 -- cgit v1.2.3 From f7c7d6ccc503c0a5f4e5debb570b55bf2eb24c73 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 17 Dec 2020 19:27:08 +0100 Subject: media: uapi: Add an entity type for Image Signal Processors Add and document a media entity type for Image Signal Processor devices. Surprisingly we didn't have one, so add one now. More or less all ISP drivers should use this type instead of what they currently are using (or not using anything). Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/mediactl/media-types.rst | 7 +++++++ include/uapi/linux/media.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/mediactl/media-types.rst b/Documentation/userspace-api/media/mediactl/media-types.rst index 7b24a213cae7..e1e4043b3b1c 100644 --- a/Documentation/userspace-api/media/mediactl/media-types.rst +++ b/Documentation/userspace-api/media/mediactl/media-types.rst @@ -39,6 +39,7 @@ Types and flags used to represent the media graph elements .. _MEDIA-ENT-F-PROC-VIDEO-STATISTICS: .. _MEDIA-ENT-F-PROC-VIDEO-ENCODER: .. _MEDIA-ENT-F-PROC-VIDEO-DECODER: +.. _MEDIA-ENT-F-PROC-VIDEO-ISP: .. _MEDIA-ENT-F-VID-MUX: .. _MEDIA-ENT-F-VID-IF-BRIDGE: .. _MEDIA-ENT-F-DV-DECODER: @@ -201,6 +202,12 @@ Types and flags used to represent the media graph elements decompressing a compressed video stream into uncompressed video frames. Must have one sink pad and at least one source pad. + * - ``MEDIA_ENT_F_PROC_VIDEO_ISP`` + - An Image Signal Processor (ISP) device. ISPs generally are one of a + kind devices that have their specific control interfaces using a + combination of custom V4L2 controls and IOCTLs, and parameters + supplied in a metadata buffer. + * - ``MEDIA_ENT_F_VID_MUX`` - Video multiplexer. An entity capable of multiplexing must have at least two sink pads and one source pad, and must pass the video diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 383ac7b7d8f0..200fa8462b90 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -127,6 +127,7 @@ struct media_device_info { #define MEDIA_ENT_F_PROC_VIDEO_STATISTICS (MEDIA_ENT_F_BASE + 0x4006) #define MEDIA_ENT_F_PROC_VIDEO_ENCODER (MEDIA_ENT_F_BASE + 0x4007) #define MEDIA_ENT_F_PROC_VIDEO_DECODER (MEDIA_ENT_F_BASE + 0x4008) +#define MEDIA_ENT_F_PROC_VIDEO_ISP (MEDIA_ENT_F_BASE + 0x4009) /* * Switch and bridge entity functions -- cgit v1.2.3 From cd9f145dabafec8ad001756f2abe60c7c2ec3cc1 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 24 Sep 2020 21:44:13 +0200 Subject: media: v4l: uapi: Add user control base for CCS controls Add a control base for CCS controls, and reserve 128 controls. Luckily these numbers are cheap. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 823b214aac0c..9ead7a8386c8 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -204,6 +204,11 @@ enum v4l2_colorfx { * We reserve 16 controls for this driver. */ #define V4L2_CID_USER_CODA_BASE (V4L2_CID_USER_BASE + 0x10e0) +/* + * The base for MIPI CCS driver controls. + * We reserve 128 controls for this driver. + */ +#define V4L2_CID_USER_CCS_BASE (V4L2_CID_USER_BASE + 0x10f0) /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls -- cgit v1.2.3 From a8a2d75b0897fc359ada5fb9f8b62f985351882b Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 24 Sep 2020 00:21:32 +0200 Subject: media: v4l: uapi: ccs: Add controls for analogue gain constants Add V4L2 controls for analogue gain constants required to control analogue gain. The values are device specific and thus need to be obtained from the driver. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/drivers/ccs.rst | 25 +++++++++++++++++++++++ MAINTAINERS | 1 + include/uapi/linux/ccs.h | 14 +++++++++++++ 3 files changed, 40 insertions(+) create mode 100644 include/uapi/linux/ccs.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/drivers/ccs.rst b/Documentation/userspace-api/media/drivers/ccs.rst index 00bb3a6288f5..a95d7941533d 100644 --- a/Documentation/userspace-api/media/drivers/ccs.rst +++ b/Documentation/userspace-api/media/drivers/ccs.rst @@ -56,4 +56,29 @@ analogue data is never read from the pixel matrix that are outside the configured selection rectangle that designates crop. The difference has an effect in device timing and likely also in power consumption. +Private controls +---------------- + +The MIPI CCS driver implements a number of private controls under +``V4L2_CID_USER_BASE_CCS`` to control the MIPI CCS compliant camera sensors. + +Analogue gain model +~~~~~~~~~~~~~~~~~~~ + +The CCS defines an analogue gain model where the gain can be calculated using +the following formula: + + gain = m0 * x + c0 / (m1 * x + c1) + +Either m0 or c0 will be zero. The constants that are device specific, can be +obtained from the following controls: + + V4L2_CID_CCS_ANALOGUE_GAIN_M0 + V4L2_CID_CCS_ANALOGUE_GAIN_M1 + V4L2_CID_CCS_ANALOGUE_GAIN_C0 + V4L2_CID_CCS_ANALOGUE_GAIN_C1 + +The analogue gain (``x`` in the formula) is controlled through +``V4L2_CID_ANALOGUE_GAIN`` in this case. + **Copyright** |copy| 2020 Intel Corporation diff --git a/MAINTAINERS b/MAINTAINERS index 906ef1373285..7faa7ae50716 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11840,6 +11840,7 @@ F: Documentation/userspace-api/media/drivers/ccs.rst F: drivers/media/i2c/ccs-pll.c F: drivers/media/i2c/ccs-pll.h F: drivers/media/i2c/ccs/ +F: include/uapi/linux/ccs.h F: include/uapi/linux/smiapp.h MIPS diff --git a/include/uapi/linux/ccs.h b/include/uapi/linux/ccs.h new file mode 100644 index 000000000000..57515ed7aaab --- /dev/null +++ b/include/uapi/linux/ccs.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* Copyright (C) 2020 Intel Corporation */ + +#ifndef __UAPI_CCS_H__ +#define __UAPI_CCS_H__ + +#include + +#define V4L2_CID_CCS_ANALOGUE_GAIN_M0 (V4L2_CID_USER_CCS_BASE + 1) +#define V4L2_CID_CCS_ANALOGUE_GAIN_C0 (V4L2_CID_USER_CCS_BASE + 2) +#define V4L2_CID_CCS_ANALOGUE_GAIN_M1 (V4L2_CID_USER_CCS_BASE + 3) +#define V4L2_CID_CCS_ANALOGUE_GAIN_C1 (V4L2_CID_USER_CCS_BASE + 4) + +#endif -- cgit v1.2.3 From a75210a62b81ce8cfbe9e10e29880d870ce94b8d Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 24 Sep 2020 21:57:52 +0200 Subject: media: v4l: uapi: ccs: Add controls for CCS alternative analogue gain Add two new controls for alternative analogue gain some CCS compliant camera sensors support. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/drivers/ccs.rst | 13 +++++++++++++ include/uapi/linux/ccs.h | 2 ++ 2 files changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/drivers/ccs.rst b/Documentation/userspace-api/media/drivers/ccs.rst index a95d7941533d..ea09c8139c23 100644 --- a/Documentation/userspace-api/media/drivers/ccs.rst +++ b/Documentation/userspace-api/media/drivers/ccs.rst @@ -81,4 +81,17 @@ obtained from the following controls: The analogue gain (``x`` in the formula) is controlled through ``V4L2_CID_ANALOGUE_GAIN`` in this case. +Alternate analogue gain model +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The CCS defines another analogue gain model called alternate analogue gain. In +this case, the formula to calculate actual gain consists of linear and +exponential parts: + + gain = linear * 2 ^ exponent + +The ``linear`` and ``exponent`` factors can be set using the +``V4L2_CID_CCS_ANALOGUE_LINEAR_GAIN`` and +``V4L2_CID_CCS_ANALOGUE_EXPONENTIAL_GAIN`` controls, respectively + **Copyright** |copy| 2020 Intel Corporation diff --git a/include/uapi/linux/ccs.h b/include/uapi/linux/ccs.h index 57515ed7aaab..9ddec24c1401 100644 --- a/include/uapi/linux/ccs.h +++ b/include/uapi/linux/ccs.h @@ -10,5 +10,7 @@ #define V4L2_CID_CCS_ANALOGUE_GAIN_C0 (V4L2_CID_USER_CCS_BASE + 2) #define V4L2_CID_CCS_ANALOGUE_GAIN_M1 (V4L2_CID_USER_CCS_BASE + 3) #define V4L2_CID_CCS_ANALOGUE_GAIN_C1 (V4L2_CID_USER_CCS_BASE + 4) +#define V4L2_CID_CCS_ANALOGUE_LINEAR_GAIN (V4L2_CID_USER_CCS_BASE + 5) +#define V4L2_CID_CCS_ANALOGUE_EXPONENTIAL_GAIN (V4L2_CID_USER_CCS_BASE + 6) #endif -- cgit v1.2.3 From 7c0ed600f04d247cbb4c4030d87a8d36b12d44a4 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 25 Sep 2020 10:28:56 +0200 Subject: media: v4l: uapi: ccs: Add CCS controls for shading correction Add V4L2 controls for controlling CCS lens shading correction as well as conveying its capabilities. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/drivers/ccs.rst | 13 +++++++++++++ include/uapi/linux/ccs.h | 2 ++ 2 files changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/drivers/ccs.rst b/Documentation/userspace-api/media/drivers/ccs.rst index ea09c8139c23..161cb65f4d98 100644 --- a/Documentation/userspace-api/media/drivers/ccs.rst +++ b/Documentation/userspace-api/media/drivers/ccs.rst @@ -94,4 +94,17 @@ The ``linear`` and ``exponent`` factors can be set using the ``V4L2_CID_CCS_ANALOGUE_LINEAR_GAIN`` and ``V4L2_CID_CCS_ANALOGUE_EXPONENTIAL_GAIN`` controls, respectively +Shading correction +~~~~~~~~~~~~~~~~~~ + +The CCS standard supports lens shading correction. The feature can be controlled +using ``V4L2_CID_CCS_SHADING_CORRECTION``. Additionally, the luminance +correction level may be changed using +``V4L2_CID_CCS_LUMINANCE_CORRECTION_LEVEL``, where value 0 indicates no +correction and 128 indicates correcting the luminance in corners to 10 % less +than in the centre. + +Shading correction needs to be enabled for luminance correction level to have an +effect. + **Copyright** |copy| 2020 Intel Corporation diff --git a/include/uapi/linux/ccs.h b/include/uapi/linux/ccs.h index 9ddec24c1401..2896d3bfdb5e 100644 --- a/include/uapi/linux/ccs.h +++ b/include/uapi/linux/ccs.h @@ -12,5 +12,7 @@ #define V4L2_CID_CCS_ANALOGUE_GAIN_C1 (V4L2_CID_USER_CCS_BASE + 4) #define V4L2_CID_CCS_ANALOGUE_LINEAR_GAIN (V4L2_CID_USER_CCS_BASE + 5) #define V4L2_CID_CCS_ANALOGUE_EXPONENTIAL_GAIN (V4L2_CID_USER_CCS_BASE + 6) +#define V4L2_CID_CCS_SHADING_CORRECTION (V4L2_CID_USER_CCS_BASE + 8) +#define V4L2_CID_CCS_LUMINANCE_CORRECTION_LEVEL (V4L2_CID_USER_CCS_BASE + 9) #endif -- cgit v1.2.3 From c6458e72f6fd6ac7e390da0d9abe8446084886e5 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Tue, 12 Jan 2021 12:34:22 +0000 Subject: bpf: Clarify return value of probe str helpers When the buffer is too small to contain the input string, these helpers return the length of the buffer, not the length of the original string. This tries to make the docs totally clear about that, since "the length of the [copied ]string" could also refer to the length of the input. Signed-off-by: Brendan Jackman Signed-off-by: Daniel Borkmann Acked-by: KP Singh Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112123422.2011234-1-jackmanb@google.com --- include/uapi/linux/bpf.h | 10 +++++----- tools/include/uapi/linux/bpf.h | 10 +++++----- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77d7c1bb2923..a1ad32456f89 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2993,10 +2993,10 @@ union bpf_attr { * string length is larger than *size*, just *size*-1 bytes are * copied and the last byte is set to NUL. * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: * * :: * @@ -3024,7 +3024,7 @@ union bpf_attr { * **->mm->env_start**: using this helper and the return value, * one can quickly iterate at the right offset of the memory area. * Return - * On success, the strictly positive length of the string, + * On success, the strictly positive length of the output string, * including the trailing NUL character. On error, a negative * value. * diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 77d7c1bb2923..a1ad32456f89 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2993,10 +2993,10 @@ union bpf_attr { * string length is larger than *size*, just *size*-1 bytes are * copied and the last byte is set to NUL. * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: * * :: * @@ -3024,7 +3024,7 @@ union bpf_attr { * **->mm->env_start**: using this helper and the return value, * one can quickly iterate at the right offset of the memory area. * Return - * On success, the strictly positive length of the string, + * On success, the strictly positive length of the output string, * including the trailing NUL character. On error, a negative * value. * -- cgit v1.2.3 From 99d0cbe4be78ca33f06089521a8a0d76a20cdbb7 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Thu, 24 Dec 2020 12:25:33 +0100 Subject: media: v4l2-ctrl: Add frame-specific min/max qp controls for hevc - Adds min/max qp controls for B frame for h264. - Adds min/max qp controls for I/P/B frames for hevc similar to h264. - Update valid range of min/max qp for hevc to accommodate 10 bit. Signed-off-by: Dikshita Agarwal Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/ext-ctrls-codec.rst | 52 +++++++++++++++++++++- drivers/media/v4l2-core/v4l2-ctrls.c | 8 ++++ include/uapi/linux/v4l2-controls.h | 9 ++++ 3 files changed, 67 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 454ecd9a0f83..90c60add3fc0 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1182,6 +1182,18 @@ enum v4l2_mpeg_video_h264_entropy_mode - V4L2_CID_MPEG_VIDEO_H264_MAX_QP is also set, the quantization parameter should be chosen to meet both requirements. +``V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MIN_QP (integer)`` + Minimum quantization parameter for the H264 B frame to limit B frame + quality to a range. Valid range: from 0 to 51. If + V4L2_CID_MPEG_VIDEO_H264_MIN_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MAX_QP (integer)`` + Maximum quantization parameter for the H264 B frame to limit B frame + quality to a range. Valid range: from 0 to 51. If + V4L2_CID_MPEG_VIDEO_H264_MAX_QP is also set, the quantization parameter + should be chosen to meet both requirements. + ``V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (integer)`` Quantization parameter for an I frame for MPEG4. Valid range: from 1 to 31. @@ -2628,11 +2640,11 @@ HEVC/H.265 Control IDs ``V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP (integer)`` Minimum quantization parameter for HEVC. - Valid range: from 0 to 51. + Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. ``V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP (integer)`` Maximum quantization parameter for HEVC. - Valid range: from 0 to 51. + Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. ``V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP (integer)`` Quantization parameter for an I frame for HEVC. @@ -2649,6 +2661,42 @@ HEVC/H.265 Control IDs Valid range: [V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP, V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP]. +``V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MIN_QP (integer)`` + Minimum quantization parameter for the HEVC I frame to limit I frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MAX_QP (integer)`` + Maximum quantization parameter for the HEVC I frame to limit I frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MIN_QP (integer)`` + Minimum quantization parameter for the HEVC P frame to limit P frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MAX_QP (integer)`` + Maximum quantization parameter for the HEVC P frame to limit P frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MIN_QP (integer)`` + Minimum quantization parameter for the HEVC B frame to limit B frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP is also set, the quantization parameter + should be chosen to meet both requirements. + +``V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MAX_QP (integer)`` + Maximum quantization parameter for the HEVC B frame to limit B frame + quality to a range. Valid range: from 0 to 51 for 8 bit and from 0 to 63 for 10 bit. + If V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP is also set, the quantization parameter + should be chosen to meet both requirements. + ``V4L2_CID_MPEG_VIDEO_HEVC_HIER_QP (boolean)`` HIERARCHICAL_QP allows the host to specify the quantization parameter values for each temporal layer through HIERARCHICAL_QP_LAYER. This is diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 5cbe0ffbf501..410e54141c21 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -920,6 +920,8 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_MAX_QP: return "H264 I-Frame Maximum QP Value"; case V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MIN_QP: return "H264 P-Frame Minimum QP Value"; case V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MAX_QP: return "H264 P-Frame Maximum QP Value"; + case V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MIN_QP: return "H264 B-Frame Minimum QP Value"; + case V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MAX_QP: return "H264 B-Frame Maximum QP Value"; case V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL: return "MPEG2 Level"; case V4L2_CID_MPEG_VIDEO_MPEG2_PROFILE: return "MPEG2 Profile"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; @@ -969,6 +971,12 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_QP: return "HEVC B-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_HEVC_MIN_QP: return "HEVC Minimum QP Value"; case V4L2_CID_MPEG_VIDEO_HEVC_MAX_QP: return "HEVC Maximum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MIN_QP: return "HEVC I-Frame Minimum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MAX_QP: return "HEVC I-Frame Maximum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MIN_QP: return "HEVC P-Frame Minimum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MAX_QP: return "HEVC P-Frame Maximum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MIN_QP: return "HEVC B-Frame Minimum QP Value"; + case V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MAX_QP: return "HEVC B-Frame Maximum QP Value"; case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE: return "HEVC Profile"; case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL: return "HEVC Level"; case V4L2_CID_MPEG_VIDEO_HEVC_TIER: return "HEVC Tier"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 9ead7a8386c8..a7130f47199e 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -590,6 +590,8 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { #define V4L2_CID_MPEG_VIDEO_H264_I_FRAME_MAX_QP (V4L2_CID_CODEC_BASE+386) #define V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MIN_QP (V4L2_CID_CODEC_BASE+387) #define V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MAX_QP (V4L2_CID_CODEC_BASE+388) +#define V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MIN_QP (V4L2_CID_CODEC_BASE+389) +#define V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MAX_QP (V4L2_CID_CODEC_BASE+390) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_CODEC_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_CODEC_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_CODEC_BASE+402) @@ -780,6 +782,13 @@ enum v4l2_mpeg_video_frame_skip_mode { V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT = 2, }; +#define V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MIN_QP (V4L2_CID_CODEC_BASE + 647) +#define V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_MAX_QP (V4L2_CID_CODEC_BASE + 648) +#define V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MIN_QP (V4L2_CID_CODEC_BASE + 649) +#define V4L2_CID_MPEG_VIDEO_HEVC_P_FRAME_MAX_QP (V4L2_CID_CODEC_BASE + 650) +#define V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MIN_QP (V4L2_CID_CODEC_BASE + 651) +#define V4L2_CID_MPEG_VIDEO_HEVC_B_FRAME_MAX_QP (V4L2_CID_CODEC_BASE + 652) + /* MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */ #define V4L2_CID_CODEC_CX2341X_BASE (V4L2_CTRL_CLASS_CODEC | 0x1000) #define V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE (V4L2_CID_CODEC_CX2341X_BASE+0) -- cgit v1.2.3 From 4ca134ee98238c3aaf0bb51094716373d8ae8720 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Thu, 24 Dec 2020 12:25:34 +0100 Subject: media: v4l2-ctrl: Add layer wise bitrate controls for h264 Adds bitrate control for all coding layers for h264 same as hevc. Signed-off-by: Dikshita Agarwal Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/ext-ctrls-codec.rst | 20 ++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ctrls.c | 7 +++++++ include/uapi/linux/v4l2-controls.h | 7 +++++++ 3 files changed, 34 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 90c60add3fc0..400774ceffaa 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1513,6 +1513,26 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - * - Bit 16:32 - Layer number +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L0_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 0 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L1_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 1 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L2_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 2 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L3_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 3 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L4_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 4 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L5_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 5 for H264 encoder. + +``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L6_BR (integer)`` + Indicates bit rate (bps) for hierarchical coding layer 6 for H264 encoder. .. _v4l2-mpeg-mpeg2: diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 410e54141c21..16ab54f676e2 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -922,6 +922,13 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MAX_QP: return "H264 P-Frame Maximum QP Value"; case V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MIN_QP: return "H264 B-Frame Minimum QP Value"; case V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MAX_QP: return "H264 B-Frame Maximum QP Value"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L0_BR: return "H264 Hierarchical Lay 0 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L1_BR: return "H264 Hierarchical Lay 1 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L2_BR: return "H264 Hierarchical Lay 2 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L3_BR: return "H264 Hierarchical Lay 3 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L4_BR: return "H264 Hierarchical Lay 4 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L5_BR: return "H264 Hierarchical Lay 5 Bitrate"; + case V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L6_BR: return "H264 Hierarchical Lay 6 Bitrate"; case V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL: return "MPEG2 Level"; case V4L2_CID_MPEG_VIDEO_MPEG2_PROFILE: return "MPEG2 Profile"; case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP: return "MPEG4 I-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index a7130f47199e..0bd967543357 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -592,6 +592,13 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type { #define V4L2_CID_MPEG_VIDEO_H264_P_FRAME_MAX_QP (V4L2_CID_CODEC_BASE+388) #define V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MIN_QP (V4L2_CID_CODEC_BASE+389) #define V4L2_CID_MPEG_VIDEO_H264_B_FRAME_MAX_QP (V4L2_CID_CODEC_BASE+390) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L0_BR (V4L2_CID_CODEC_BASE+391) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L1_BR (V4L2_CID_CODEC_BASE+392) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L2_BR (V4L2_CID_CODEC_BASE+393) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L3_BR (V4L2_CID_CODEC_BASE+394) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L4_BR (V4L2_CID_CODEC_BASE+395) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L5_BR (V4L2_CID_CODEC_BASE+396) +#define V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L6_BR (V4L2_CID_CODEC_BASE+397) #define V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP (V4L2_CID_CODEC_BASE+400) #define V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP (V4L2_CID_CODEC_BASE+401) #define V4L2_CID_MPEG_VIDEO_MPEG4_B_FRAME_QP (V4L2_CID_CODEC_BASE+402) -- cgit v1.2.3 From 6bde70da98f6b5f5dbd61d2fa9c1e7efe83b0402 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Mon, 4 Jan 2021 06:41:53 +0100 Subject: media: v4l2-ctrl: Add base layer priority id control. This control indicates the priority id to be applied to base layer. [hverkuil: renumbered V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID] Signed-off-by: Dikshita Agarwal Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 9 +++++++++ drivers/media/v4l2-core/v4l2-ctrls.c | 1 + include/uapi/linux/v4l2-controls.h | 1 + 3 files changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index 400774ceffaa..00944e97d638 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -3637,3 +3637,12 @@ enum v4l2_mpeg_video_hevc_size_of_length_field - - Selecting this value specifies that HEVC slices are expected to be prefixed by Annex B start codes. According to :ref:`hevc` valid start codes can be 3-bytes 0x000001 or 4-bytes 0x00000001. + +``V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID (integer)`` + Specifies a priority identifier for the NAL unit, which will be applied to + the base layer. By default this value is set to 0 for the base layer, + and the next layer will have the priority ID assigned as 1, 2, 3 and so on. + The video encoder can't decide the priority id to be applied to a layer, + so this has to come from client. + This is applicable to H264 and valid Range is from 0 to 63. + Source Rec. ITU-T H.264 (06/2019); G.7.4.1.1, G.8.8.1. diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 16ab54f676e2..f7b310240af2 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -950,6 +950,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE: return "Vertical MV Search Range"; case V4L2_CID_MPEG_VIDEO_REPEAT_SEQ_HEADER: return "Repeat Sequence Header"; case V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME: return "Force Key Frame"; + case V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID: return "Base Layer Priority ID"; case V4L2_CID_MPEG_VIDEO_MPEG2_SLICE_PARAMS: return "MPEG-2 Slice Parameters"; case V4L2_CID_MPEG_VIDEO_MPEG2_QUANTIZATION: return "MPEG-2 Quantization Matrices"; case V4L2_CID_FWHT_I_FRAME_QP: return "FWHT I-Frame QP Value"; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 0bd967543357..039c0d7add1b 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -427,6 +427,7 @@ enum v4l2_mpeg_video_multi_slice_mode { #define V4L2_CID_MPEG_VIDEO_MV_H_SEARCH_RANGE (V4L2_CID_CODEC_BASE+227) #define V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE (V4L2_CID_CODEC_BASE+228) #define V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME (V4L2_CID_CODEC_BASE+229) +#define V4L2_CID_MPEG_VIDEO_BASELAYER_PRIORITY_ID (V4L2_CID_CODEC_BASE+230) /* CIDs for the MPEG-2 Part 2 (H.262) codec */ #define V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL (V4L2_CID_CODEC_BASE+270) -- cgit v1.2.3 From 91c960b0056672e74627776655c926388350fa30 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:44 +0000 Subject: bpf: Rename BPF_XADD and prepare to encode other atomics in .imm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A subsequent patch will add additional atomic operations. These new operations will use the same opcode field as the existing XADD, with the immediate discriminating different operations. In preparation, rename the instruction mode BPF_ATOMIC and start calling the zero immediate BPF_ADD. This is possible (doesn't break existing valid BPF progs) because the immediate field is currently reserved MBZ and BPF_ADD is zero. All uses are removed from the tree but the BPF_XADD definition is kept around to avoid breaking builds for people including kernel headers. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/20210114181751.768687-5-jackmanb@google.com --- Documentation/networking/filter.rst | 30 ++++++++------ arch/arm/net/bpf_jit_32.c | 7 ++-- arch/arm64/net/bpf_jit_comp.c | 16 ++++++-- arch/mips/net/ebpf_jit.c | 11 ++++-- arch/powerpc/net/bpf_jit_comp64.c | 25 +++++++++--- arch/riscv/net/bpf_jit_comp32.c | 20 ++++++++-- arch/riscv/net/bpf_jit_comp64.c | 16 ++++++-- arch/s390/net/bpf_jit_comp.c | 27 +++++++------ arch/sparc/net/bpf_jit_comp_64.c | 17 ++++++-- arch/x86/net/bpf_jit_comp.c | 46 ++++++++++++++++------ arch/x86/net/bpf_jit_comp32.c | 6 +-- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 14 +++++-- drivers/net/ethernet/netronome/nfp/bpf/main.h | 4 +- drivers/net/ethernet/netronome/nfp/bpf/verifier.c | 15 ++++--- include/linux/filter.h | 16 ++++++-- include/uapi/linux/bpf.h | 5 ++- kernel/bpf/core.c | 31 ++++++++++----- kernel/bpf/disasm.c | 6 ++- kernel/bpf/verifier.c | 24 ++++++----- lib/test_bpf.c | 14 +++---- samples/bpf/bpf_insn.h | 4 +- samples/bpf/cookie_uid_helper_example.c | 8 ++-- samples/bpf/sock_example.c | 2 +- samples/bpf/test_cgrp2_attach.c | 5 ++- tools/include/linux/filter.h | 15 +++++-- tools/include/uapi/linux/bpf.h | 5 ++- .../selftests/bpf/prog_tests/cgroup_attach_multi.c | 4 +- tools/testing/selftests/bpf/test_cgroup_storage.c | 2 +- tools/testing/selftests/bpf/verifier/ctx.c | 7 ++-- .../selftests/bpf/verifier/direct_packet_access.c | 4 +- tools/testing/selftests/bpf/verifier/leak_ptr.c | 10 ++--- tools/testing/selftests/bpf/verifier/meta_access.c | 4 +- tools/testing/selftests/bpf/verifier/unpriv.c | 3 +- .../selftests/bpf/verifier/value_illegal_alu.c | 2 +- tools/testing/selftests/bpf/verifier/xadd.c | 18 ++++----- 35 files changed, 291 insertions(+), 152 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index debb59e374de..1583d59d806d 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -1006,13 +1006,13 @@ Size modifier is one of ... Mode modifier is one of:: - BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */ - BPF_ABS 0x20 - BPF_IND 0x40 - BPF_MEM 0x60 - BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */ - BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */ - BPF_XADD 0xc0 /* eBPF only, exclusive add */ + BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */ + BPF_ABS 0x20 + BPF_IND 0x40 + BPF_MEM 0x60 + BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */ + BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */ + BPF_ATOMIC 0xc0 /* eBPF only, atomic operations */ eBPF has two non-generic instructions: (BPF_ABS | | BPF_LD) and (BPF_IND | | BPF_LD) which are used to access packet data. @@ -1044,11 +1044,19 @@ Unlike classic BPF instruction set, eBPF has generic load/store operations:: BPF_MEM | | BPF_STX: *(size *) (dst_reg + off) = src_reg BPF_MEM | | BPF_ST: *(size *) (dst_reg + off) = imm32 BPF_MEM | | BPF_LDX: dst_reg = *(size *) (src_reg + off) - BPF_XADD | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg - BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg -Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and -2 byte atomic increments are not supported. +Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. + +It also includes atomic operations, which use the immediate field for extra +encoding. + + .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg + .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg + +Note that 1 and 2 byte atomic operations are not supported. + +You may encounter BPF_XADD - this is a legacy name for BPF_ATOMIC, referring to +the exclusive-add operation encoded when the immediate field is zero. eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 0207b6ea6e8a..897634d0a67c 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1620,10 +1620,9 @@ exit: } emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code)); break; - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: - /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + /* Atomic ops */ + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: goto notyet; /* STX: *(size *)(dst + off) = src */ case BPF_STX | BPF_MEM | BPF_W: diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index ef9f1d5e989d..f7b194878a99 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -875,10 +875,18 @@ emit_cond_jmp: } break; - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: - /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm != BPF_ADD) { + pr_err_once("unknown atomic op code %02x\n", insn->imm); + return -EINVAL; + } + + /* STX XADD: lock *(u32 *)(dst + off) += src + * and + * STX XADD: lock *(u64 *)(dst + off) += src + */ + if (!off) { reg = dst; } else { diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 561154cbcc40..939dd06764bc 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1423,8 +1423,8 @@ jeq_common: case BPF_STX | BPF_H | BPF_MEM: case BPF_STX | BPF_W | BPF_MEM: case BPF_STX | BPF_DW | BPF_MEM: - case BPF_STX | BPF_W | BPF_XADD: - case BPF_STX | BPF_DW | BPF_XADD: + case BPF_STX | BPF_W | BPF_ATOMIC: + case BPF_STX | BPF_DW | BPF_ATOMIC: if (insn->dst_reg == BPF_REG_10) { ctx->flags |= EBPF_SEEN_FP; dst = MIPS_R_SP; @@ -1438,7 +1438,12 @@ jeq_common: src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); if (src < 0) return src; - if (BPF_MODE(insn->code) == BPF_XADD) { + if (BPF_MODE(insn->code) == BPF_ATOMIC) { + if (insn->imm != BPF_ADD) { + pr_err("ATOMIC OP %02x NOT HANDLED\n", insn->imm); + return -EINVAL; + } + /* * If mem_off does not fit within the 9 bit ll/sc * instruction immediate field, use a temp reg. diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 022103c6a201..aaf1a887f653 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -683,10 +683,18 @@ emit_clear: break; /* - * BPF_STX XADD (atomic_add) + * BPF_STX ATOMIC (atomic ops) */ - /* *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_W: + if (insn->imm != BPF_ADD) { + pr_err_ratelimited( + "eBPF filter atomic op code %02x (@%d) unsupported\n", + code, i); + return -ENOTSUPP; + } + + /* *(u32 *)(dst + off) += src */ + /* Get EA into TMP_REG_1 */ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); tmp_idx = ctx->idx * 4; @@ -699,8 +707,15 @@ emit_clear: /* we're done if this succeeded */ PPC_BCC_SHORT(COND_NE, tmp_idx); break; - /* *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm != BPF_ADD) { + pr_err_ratelimited( + "eBPF filter atomic op code %02x (@%d) unsupported\n", + code, i); + return -ENOTSUPP; + } + /* *(u64 *)(dst + off) += src */ + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); tmp_idx = ctx->idx * 4; EMIT(PPC_RAW_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0)); diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 579575f9cdae..81de865f4c7c 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -881,7 +881,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off, const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); const s8 *rs = bpf_get_reg64(src, tmp2, ctx); - if (mode == BPF_XADD && size != BPF_W) + if (mode == BPF_ATOMIC && size != BPF_W) return -1; emit_imm(RV_REG_T0, off, ctx); @@ -899,7 +899,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off, case BPF_MEM: emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); break; - case BPF_XADD: + case BPF_ATOMIC: /* Only BPF_ADD supported */ emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0), ctx); break; @@ -1260,7 +1260,6 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_STX | BPF_MEM | BPF_H: case BPF_STX | BPF_MEM | BPF_W: case BPF_STX | BPF_MEM | BPF_DW: - case BPF_STX | BPF_XADD | BPF_W: if (BPF_CLASS(code) == BPF_ST) { emit_imm32(tmp2, imm, ctx); src = tmp2; @@ -1271,8 +1270,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, return -1; break; + case BPF_STX | BPF_ATOMIC | BPF_W: + if (insn->imm != BPF_ADD) { + pr_info_once( + "bpf-jit: not supported: atomic operation %02x ***\n", + insn->imm); + return -EFAULT; + } + + if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code), + BPF_MODE(code))) + return -1; + break; + /* No hardware support for 8-byte atomics in RV32. */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_DW: /* Fallthrough. */ notsupported: diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 8a56b5293117..b44ff52f84a6 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1027,10 +1027,18 @@ out_be: emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); emit_sd(RV_REG_T1, 0, rs, ctx); break; - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: - /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm != BPF_ADD) { + pr_err("bpf-jit: not supported: atomic operation %02x ***\n", + insn->imm); + return -EINVAL; + } + + /* atomic_add: lock *(u32 *)(dst + off) += src + * atomic_add: lock *(u64 *)(dst + off) += src + */ + if (off) { if (is_12b_int(off)) { emit_addi(RV_REG_T1, rd, off, ctx); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 0a4182792876..f973e2ead197 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1205,18 +1205,23 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, jit->seen |= SEEN_MEM; break; /* - * BPF_STX XADD (atomic_add) + * BPF_ATOMIC */ - case BPF_STX | BPF_XADD | BPF_W: /* *(u32 *)(dst + off) += src */ - /* laal %w0,%src,off(%dst) */ - EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W0, src_reg, - dst_reg, off); - jit->seen |= SEEN_MEM; - break; - case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ - /* laalg %w0,%src,off(%dst) */ - EMIT6_DISP_LH(0xeb000000, 0x00ea, REG_W0, src_reg, - dst_reg, off); + case BPF_STX | BPF_ATOMIC | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_W: + if (insn->imm != BPF_ADD) { + pr_err("Unknown atomic operation %02x\n", insn->imm); + return -1; + } + + /* *(u32/u64 *)(dst + off) += src + * + * BFW_W: laal %w0,%src,off(%dst) + * BPF_DW: laalg %w0,%src,off(%dst) + */ + EMIT6_DISP_LH(0xeb000000, + BPF_SIZE(insn->code) == BPF_W ? 0x00fa : 0x00ea, + REG_W0, src_reg, dst_reg, off); jit->seen |= SEEN_MEM; break; /* diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 3364e2a00989..4b8d3c65d266 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1366,12 +1366,18 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; } - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: { + case BPF_STX | BPF_ATOMIC | BPF_W: { const u8 tmp = bpf2sparc[TMP_REG_1]; const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->imm != BPF_ADD) { + pr_err_once("unknown atomic op %02x\n", insn->imm); + return -EINVAL; + } + + /* lock *(u32 *)(dst + off) += src */ + if (insn->dst_reg == BPF_REG_FP) ctx->saw_frame_pointer = true; @@ -1390,11 +1396,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; } /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: { + case BPF_STX | BPF_ATOMIC | BPF_DW: { const u8 tmp = bpf2sparc[TMP_REG_1]; const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->imm != BPF_ADD) { + pr_err_once("unknown atomic op %02x\n", insn->imm); + return -EINVAL; + } + if (insn->dst_reg == BPF_REG_FP) ctx->saw_frame_pointer = true; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 93f32e0ba0ef..b1829a534da1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -795,6 +795,33 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +static int emit_atomic(u8 **pprog, u8 atomic_op, + u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) +{ + u8 *prog = *pprog; + int cnt = 0; + + EMIT1(0xF0); /* lock prefix */ + + maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW); + + /* emit opcode */ + switch (atomic_op) { + case BPF_ADD: + /* lock *(u32/u64*)(dst_reg + off) = src_reg */ + EMIT1(simple_alu_opcodes[atomic_op]); + break; + default: + pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); + return -EFAULT; + } + + emit_insn_suffix(&prog, dst_reg, src_reg, off); + + *pprog = prog; + return 0; +} + static bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) @@ -839,6 +866,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int i, cnt = 0, excnt = 0; int proglen = 0; u8 *prog = temp; + int err; detect_reg_usage(insn, insn_cnt, callee_regs_used, &tail_call_seen); @@ -1250,18 +1278,12 @@ st: if (is_imm8(insn->off)) } break; - /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ - case BPF_STX | BPF_XADD | BPF_W: - /* Emit 'lock add dword ptr [rax + off], eax' */ - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01); - else - EMIT2(0xF0, 0x01); - goto xadd; - case BPF_STX | BPF_XADD | BPF_DW: - EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01); -xadd: - emit_modrm_dstoff(&prog, dst_reg, src_reg, insn->off); + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, + insn->off, BPF_SIZE(insn->code)); + if (err) + return err; break; /* call */ diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 96fde03aa987..d17b67c69f89 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2243,10 +2243,8 @@ emit_jmp: return -EFAULT; } break; - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: - /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: goto notyet; case BPF_JMP | BPF_EXIT: if (seen_exit) { diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 0a721f6e8676..e31f8fbbc696 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -3109,13 +3109,19 @@ mem_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, bool is64) return 0; } -static int mem_xadd4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_atomic4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { + if (meta->insn.imm != BPF_ADD) + return -EOPNOTSUPP; + return mem_xadd(nfp_prog, meta, false); } -static int mem_xadd8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_atomic8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { + if (meta->insn.imm != BPF_ADD) + return -EOPNOTSUPP; + return mem_xadd(nfp_prog, meta, true); } @@ -3475,8 +3481,8 @@ static const instr_cb_t instr_cb[256] = { [BPF_STX | BPF_MEM | BPF_H] = mem_stx2, [BPF_STX | BPF_MEM | BPF_W] = mem_stx4, [BPF_STX | BPF_MEM | BPF_DW] = mem_stx8, - [BPF_STX | BPF_XADD | BPF_W] = mem_xadd4, - [BPF_STX | BPF_XADD | BPF_DW] = mem_xadd8, + [BPF_STX | BPF_ATOMIC | BPF_W] = mem_atomic4, + [BPF_STX | BPF_ATOMIC | BPF_DW] = mem_atomic8, [BPF_ST | BPF_MEM | BPF_B] = mem_st1, [BPF_ST | BPF_MEM | BPF_H] = mem_st2, [BPF_ST | BPF_MEM | BPF_W] = mem_st4, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index fac9c6f9e197..d0e17eebddd9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -428,9 +428,9 @@ static inline bool is_mbpf_classic_store_pkt(const struct nfp_insn_meta *meta) return is_mbpf_classic_store(meta) && meta->ptr.type == PTR_TO_PACKET; } -static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta) +static inline bool is_mbpf_atomic(const struct nfp_insn_meta *meta) { - return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD); + return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_ATOMIC); } static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index e92ee510fd52..9d235c0ce46a 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -479,7 +479,7 @@ nfp_bpf_check_ptr(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, pr_vlog(env, "map writes not supported\n"); return -EOPNOTSUPP; } - if (is_mbpf_xadd(meta)) { + if (is_mbpf_atomic(meta)) { err = nfp_bpf_map_mark_used(env, meta, reg, NFP_MAP_USE_ATOMIC_CNT); if (err) @@ -523,12 +523,17 @@ exit_check_ptr: } static int -nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, - struct bpf_verifier_env *env) +nfp_bpf_check_atomic(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + struct bpf_verifier_env *env) { const struct bpf_reg_state *sreg = cur_regs(env) + meta->insn.src_reg; const struct bpf_reg_state *dreg = cur_regs(env) + meta->insn.dst_reg; + if (meta->insn.imm != BPF_ADD) { + pr_vlog(env, "atomic op not implemented: %d\n", meta->insn.imm); + return -EOPNOTSUPP; + } + if (dreg->type != PTR_TO_MAP_VALUE) { pr_vlog(env, "atomic add not to a map value pointer: %d\n", dreg->type); @@ -655,8 +660,8 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, if (is_mbpf_store(meta)) return nfp_bpf_check_store(nfp_prog, meta, env); - if (is_mbpf_xadd(meta)) - return nfp_bpf_check_xadd(nfp_prog, meta, env); + if (is_mbpf_atomic(meta)) + return nfp_bpf_check_atomic(nfp_prog, meta, env); if (is_mbpf_alu(meta)) return nfp_bpf_check_alu(nfp_prog, meta, env); diff --git a/include/linux/filter.h b/include/linux/filter.h index 5edf2b660881..392e94b79668 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -259,15 +259,23 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1ad32456f89..6b3996343e63 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -19,7 +19,8 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ /* alu/jmp fields */ #define BPF_MOV 0xb0 /* mov reg to reg */ @@ -2448,7 +2449,7 @@ union bpf_attr { * running simultaneously. * * A user should care about the synchronization by himself. - * For example, by using the **BPF_STX_XADD** instruction to alter + * For example, by using the **BPF_ATOMIC** instructions to alter * the shared data. * Return * A pointer to the local storage area. diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 69c3c308de5e..4836ebf459cf 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1309,8 +1309,8 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ - INSN_3(STX, XADD, W), \ - INSN_3(STX, XADD, DW), \ + INSN_3(STX, ATOMIC, W), \ + INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ @@ -1618,13 +1618,25 @@ out: LDX_PROBE(DW, 8) #undef LDX_PROBE - STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ - atomic_add((u32) SRC, (atomic_t *)(unsigned long) - (DST + insn->off)); + STX_ATOMIC_W: + switch (IMM) { + case BPF_ADD: + /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ + atomic_add((u32) SRC, (atomic_t *)(unsigned long) + (DST + insn->off)); + default: + goto default_label; + } CONT; - STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ - atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) - (DST + insn->off)); + STX_ATOMIC_DW: + switch (IMM) { + case BPF_ADD: + /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ + atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) + (DST + insn->off)); + default: + goto default_label; + } CONT; default_label: @@ -1634,7 +1646,8 @@ out: * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ - pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code); + pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", + insn->code, insn->imm); BUG_ON(1); return 0; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index b44d8c447afd..37c8d6e9b4cc 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -153,14 +153,16 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_XADD) + else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_ADD) { verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); - else + } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); + } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ae2aee48cf82..cfc137b81ac6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3604,13 +3604,17 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; } -static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) +static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { int err; - if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || - insn->imm != 0) { - verbose(env, "BPF_XADD uses reserved fields\n"); + if (insn->imm != BPF_ADD) { + verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); + return -EINVAL; + } + + if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { + verbose(env, "invalid atomic operand size\n"); return -EINVAL; } @@ -3633,19 +3637,19 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || is_sk_reg(env, insn->dst_reg)) { - verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", + verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); return -EACCES; } - /* check whether atomic_add can read the memory */ + /* check whether we can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true); if (err) return err; - /* check whether atomic_add can write into the same memory */ + /* check whether we can write into the same memory */ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); } @@ -9524,8 +9528,8 @@ static int do_check(struct bpf_verifier_env *env) } else if (class == BPF_STX) { enum bpf_reg_type *prev_dst_type, dst_reg_type; - if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, env->insn_idx, insn); + if (BPF_MODE(insn->code) == BPF_ATOMIC) { + err = check_atomic(env, env->insn_idx, insn); if (err) return err; env->insn_idx++; @@ -10010,7 +10014,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) if (BPF_CLASS(insn->code) == BPF_STX && ((BPF_MODE(insn->code) != BPF_MEM && - BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { + BPF_MODE(insn->code) != BPF_ATOMIC) || insn->imm != 0)) { verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index ca7d635bccd9..49ec9e8d8aed 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -4295,13 +4295,13 @@ static struct bpf_test tests[] = { { { 0, 0xffffffff } }, .stack_depth = 40, }, - /* BPF_STX | BPF_XADD | BPF_W/DW */ + /* BPF_STX | BPF_ATOMIC | BPF_W/DW */ { "STX_XADD_W: Test: 0x12 + 0x10 = 0x22", .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_LDX_MEM(BPF_W, R0, R10, -40), BPF_EXIT_INSN(), }, @@ -4316,7 +4316,7 @@ static struct bpf_test tests[] = { BPF_ALU64_REG(BPF_MOV, R1, R10), BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_ALU64_REG(BPF_MOV, R0, R10), BPF_ALU64_REG(BPF_SUB, R0, R1), BPF_EXIT_INSN(), @@ -4331,7 +4331,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_EXIT_INSN(), }, INTERNAL, @@ -4352,7 +4352,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_LDX_MEM(BPF_DW, R0, R10, -40), BPF_EXIT_INSN(), }, @@ -4367,7 +4367,7 @@ static struct bpf_test tests[] = { BPF_ALU64_REG(BPF_MOV, R1, R10), BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_ALU64_REG(BPF_MOV, R0, R10), BPF_ALU64_REG(BPF_SUB, R0, R1), BPF_EXIT_INSN(), @@ -4382,7 +4382,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_EXIT_INSN(), }, INTERNAL, diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h index 544237980582..db67a2847395 100644 --- a/samples/bpf/bpf_insn.h +++ b/samples/bpf/bpf_insn.h @@ -138,11 +138,11 @@ struct bpf_insn; #define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = BPF_ADD }) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index deb0e3e0324d..c5ff7a13918c 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -147,12 +147,12 @@ static void prog_load(void) */ BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, - offsetof(struct stats, packets)), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, packets)), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), - BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, - offsetof(struct stats, bytes)), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, bytes)), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct __sk_buff, len)), BPF_EXIT_INSN(), diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index 00aae1d33fca..23d1930e1927 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -54,7 +54,7 @@ static int test_sock(void) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */ BPF_EXIT_INSN(), }; diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c index 20fbd1241db3..390ff38d2ac6 100644 --- a/samples/bpf/test_cgrp2_attach.c +++ b/samples/bpf/test_cgrp2_attach.c @@ -53,7 +53,7 @@ static int prog_load(int map_fd, int verdict) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), /* Count bytes */ BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */ @@ -64,7 +64,8 @@ static int prog_load(int map_fd, int verdict) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index ca28b6ab8db7..e870c9039f0d 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -169,15 +169,22 @@ .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + */ -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a1ad32456f89..6b3996343e63 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -19,7 +19,8 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ /* alu/jmp fields */ #define BPF_MOV 0xb0 /* mov reg to reg */ @@ -2448,7 +2449,7 @@ union bpf_attr { * running simultaneously. * * A user should care about the synchronization by himself. - * For example, by using the **BPF_STX_XADD** instruction to alter + * For example, by using the **BPF_ATOMIC** instructions to alter * the shared data. * Return * A pointer to the local storage area. diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index b549fcfacc0b..0a1fc9816cef 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -45,13 +45,13 @@ static int prog_load_cnt(int verdict, int val) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), BPF_MOV64_IMM(BPF_REG_1, val), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), BPF_MOV64_IMM(BPF_REG_2, 0), diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index d946252a25bb..0cda61da5d39 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -29,7 +29,7 @@ int main(int argc, char **argv) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1), BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c index 93d6b1641481..23080862aafd 100644 --- a/tools/testing/selftests/bpf/verifier/ctx.c +++ b/tools/testing/selftests/bpf/verifier/ctx.c @@ -10,14 +10,13 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "context stores via XADD", + "context stores via BPF_ATOMIC", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_1, - BPF_REG_0, offsetof(struct __sk_buff, mark), 0), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .errstr = "BPF_XADD stores into R1 ctx is not allowed", + .errstr = "BPF_ATOMIC stores into R1 ctx is not allowed", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index ae72536603fe..ac1e19d0f520 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -333,7 +333,7 @@ BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), - BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_4, BPF_REG_5, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -488,7 +488,7 @@ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 11), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8), BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), - BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_4, -8), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_4, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), diff --git a/tools/testing/selftests/bpf/verifier/leak_ptr.c b/tools/testing/selftests/bpf/verifier/leak_ptr.c index d6eec17f2cd2..73f0dea95546 100644 --- a/tools/testing/selftests/bpf/verifier/leak_ptr.c +++ b/tools/testing/selftests/bpf/verifier/leak_ptr.c @@ -5,7 +5,7 @@ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, cb[0])), BPF_LD_MAP_FD(BPF_REG_2, 0), - BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_2, + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_1, BPF_REG_2, offsetof(struct __sk_buff, cb[0])), BPF_EXIT_INSN(), }, @@ -13,7 +13,7 @@ .errstr_unpriv = "R2 leaks addr into mem", .result_unpriv = REJECT, .result = REJECT, - .errstr = "BPF_XADD stores into R1 ctx is not allowed", + .errstr = "BPF_ATOMIC stores into R1 ctx is not allowed", }, { "leak pointer into ctx 2", @@ -21,14 +21,14 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, cb[0])), - BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_10, + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_1, BPF_REG_10, offsetof(struct __sk_buff, cb[0])), BPF_EXIT_INSN(), }, .errstr_unpriv = "R10 leaks addr into mem", .result_unpriv = REJECT, .result = REJECT, - .errstr = "BPF_XADD stores into R1 ctx is not allowed", + .errstr = "BPF_ATOMIC stores into R1 ctx is not allowed", }, { "leak pointer into ctx 3", @@ -56,7 +56,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), - BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_6, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, diff --git a/tools/testing/selftests/bpf/verifier/meta_access.c b/tools/testing/selftests/bpf/verifier/meta_access.c index 205292b8dd65..b45e8af41420 100644 --- a/tools/testing/selftests/bpf/verifier/meta_access.c +++ b/tools/testing/selftests/bpf/verifier/meta_access.c @@ -171,7 +171,7 @@ BPF_MOV64_IMM(BPF_REG_5, 42), BPF_MOV64_IMM(BPF_REG_6, 24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), - BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_6, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5), @@ -196,7 +196,7 @@ BPF_MOV64_IMM(BPF_REG_5, 42), BPF_MOV64_IMM(BPF_REG_6, 24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), - BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_6, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5), diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index a3fe0fbaed41..ee298627abae 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -207,7 +207,8 @@ BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_10, BPF_REG_0, -8, 0), + BPF_RAW_INSN(BPF_STX | BPF_ATOMIC | BPF_DW, + BPF_REG_10, BPF_REG_0, -8, BPF_ADD), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_hash_recalc), BPF_EXIT_INSN(), diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c index ed1c2cea1dea..489062867218 100644 --- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c +++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c @@ -82,7 +82,7 @@ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), - BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_2, BPF_REG_3, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0), BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), BPF_EXIT_INSN(), diff --git a/tools/testing/selftests/bpf/verifier/xadd.c b/tools/testing/selftests/bpf/verifier/xadd.c index c5de2e62cc8b..b96ef3526815 100644 --- a/tools/testing/selftests/bpf/verifier/xadd.c +++ b/tools/testing/selftests/bpf/verifier/xadd.c @@ -3,7 +3,7 @@ .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -7), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), BPF_EXIT_INSN(), }, @@ -22,7 +22,7 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), BPF_EXIT_INSN(), BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 3), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3), BPF_EXIT_INSN(), }, @@ -45,13 +45,13 @@ BPF_MOV64_IMM(BPF_REG_0, 1), BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0), - BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1), - BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_2, BPF_REG_0, 1), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_2, BPF_REG_0, 2), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1), BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "BPF_XADD stores into R2 pkt is not allowed", + .errstr = "BPF_ATOMIC stores into R2 pkt is not allowed", .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -62,8 +62,8 @@ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_0, -8), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_0, -8), BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), @@ -82,8 +82,8 @@ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -8), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -8), BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), -- cgit v1.2.3 From 5ca419f2864a2c60940dcf4bbaeb69546200e36f Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:46 +0000 Subject: bpf: Add BPF_FETCH field / create atomic_fetch_add instruction The BPF_FETCH field can be set in bpf_insn.imm, for BPF_ATOMIC instructions, in order to have the previous value of the atomically-modified memory location loaded into the src register after an atomic op is carried out. Suggested-by: Yonghong Song Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210114181751.768687-7-jackmanb@google.com --- arch/x86/net/bpf_jit_comp.c | 4 ++++ include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 3 +++ kernel/bpf/core.c | 13 +++++++++++++ kernel/bpf/disasm.c | 7 +++++++ kernel/bpf/verifier.c | 33 ++++++++++++++++++++++++--------- tools/include/linux/filter.h | 1 + tools/include/uapi/linux/bpf.h | 3 +++ 8 files changed, 56 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b1829a534da1..eea7d8b0bb12 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -811,6 +811,10 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, /* lock *(u32/u64*)(dst_reg + off) = src_reg */ EMIT1(simple_alu_opcodes[atomic_op]); break; + case BPF_ADD | BPF_FETCH: + /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ + EMIT2(0x0F, 0xC1); + break; default: pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); return -EFAULT; diff --git a/include/linux/filter.h b/include/linux/filter.h index 392e94b79668..23fca41b8540 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -264,6 +264,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b3996343e63..ea262b009049 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -44,6 +44,9 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* fetch previous value into src reg */ + /* Register numbers */ enum { BPF_REG_0 = 0, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4836ebf459cf..28d6000463e4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1624,16 +1624,29 @@ out: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ atomic_add((u32) SRC, (atomic_t *)(unsigned long) (DST + insn->off)); + break; + case BPF_ADD | BPF_FETCH: + SRC = (u32) atomic_fetch_add( + (u32) SRC, + (atomic_t *)(unsigned long) (DST + insn->off)); + break; default: goto default_label; } CONT; + STX_ATOMIC_DW: switch (IMM) { case BPF_ADD: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); + break; + case BPF_ADD | BPF_FETCH: + SRC = (u64) atomic64_fetch_add( + (u64) SRC, + (atomic64_t *)(unsigned long) (DST + insn->off)); + break; default: goto default_label; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 37c8d6e9b4cc..d2e20f6d0516 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -160,6 +160,13 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == (BPF_ADD | BPF_FETCH)) { + verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_add((%s *)(r%d %+d), r%d)\n", + insn->code, insn->src_reg, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d8a85f4e5b95..6aa1fc919761 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3608,7 +3608,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i { int err; - if (insn->imm != BPF_ADD) { + switch (insn->imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + break; + default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); return -EINVAL; } @@ -3650,8 +3654,20 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i return err; /* check whether we can write into the same memory */ - return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1, true); + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, -1, true); + if (err) + return err; + + if (!(insn->imm & BPF_FETCH)) + return 0; + + /* check and record load of old value into src reg */ + err = check_reg_arg(env, insn->src_reg, DST_OP); + if (err) + return err; + + return 0; } static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno, @@ -9528,12 +9544,6 @@ static int do_check(struct bpf_verifier_env *env) } else if (class == BPF_STX) { enum bpf_reg_type *prev_dst_type, dst_reg_type; - if (((BPF_MODE(insn->code) != BPF_MEM && - BPF_MODE(insn->code) != BPF_ATOMIC) || insn->imm != 0)) { - verbose(env, "BPF_STX uses reserved fields\n"); - return -EINVAL; - } - if (BPF_MODE(insn->code) == BPF_ATOMIC) { err = check_atomic(env, env->insn_idx, insn); if (err) @@ -9542,6 +9552,11 @@ static int do_check(struct bpf_verifier_env *env) continue; } + if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { + verbose(env, "BPF_STX uses reserved fields\n"); + return -EINVAL; + } + /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index e870c9039f0d..7211ce9fba53 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -173,6 +173,7 @@ * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6b3996343e63..ea262b009049 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -44,6 +44,9 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* fetch previous value into src reg */ + /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From 5ffa25502b5ab3d639829a2d1e316cff7f59a41e Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:47 +0000 Subject: bpf: Add instructions for atomic_[cmp]xchg This adds two atomic opcodes, both of which include the BPF_FETCH flag. XCHG without the BPF_FETCH flag would naturally encode atomic_set. This is not supported because it would be of limited value to userspace (it doesn't imply any barriers). CMPXCHG without BPF_FETCH woulud be an atomic compare-and-write. We don't have such an operation in the kernel so it isn't provided to BPF either. There are two significant design decisions made for the CMPXCHG instruction: - To solve the issue that this operation fundamentally has 3 operands, but we only have two register fields. Therefore the operand we compare against (the kernel's API calls it 'old') is hard-coded to be R0. x86 has similar design (and A64 doesn't have this problem). A potential alternative might be to encode the other operand's register number in the immediate field. - The kernel's atomic_cmpxchg returns the old value, while the C11 userspace APIs return a boolean indicating the comparison result. Which should BPF do? A64 returns the old value. x86 returns the old value in the hard-coded register (and also sets a flag). That means return-old-value is easier to JIT, so that's what we use. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com --- arch/x86/net/bpf_jit_comp.c | 8 ++++++++ include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 4 +++- kernel/bpf/core.c | 20 ++++++++++++++++++++ kernel/bpf/disasm.c | 15 +++++++++++++++ kernel/bpf/verifier.c | 19 +++++++++++++++++-- tools/include/linux/filter.h | 2 ++ tools/include/uapi/linux/bpf.h | 4 +++- 8 files changed, 70 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index eea7d8b0bb12..308241187582 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -815,6 +815,14 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ EMIT2(0x0F, 0xC1); break; + case BPF_XCHG: + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + EMIT1(0x87); + break; + case BPF_CMPXCHG: + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + EMIT2(0x0F, 0xB1); + break; default: pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); return -EFAULT; diff --git a/include/linux/filter.h b/include/linux/filter.h index 23fca41b8540..d563820f197d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -265,6 +265,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ea262b009049..c001766adcbc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -45,7 +45,9 @@ #define BPF_EXIT 0x90 /* function return */ /* atomic op type fields (stored in immediate) */ -#define BPF_FETCH 0x01 /* fetch previous value into src reg */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ /* Register numbers */ enum { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 28d6000463e4..4df6daba43ef 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1630,6 +1630,16 @@ out: (u32) SRC, (atomic_t *)(unsigned long) (DST + insn->off)); break; + case BPF_XCHG: + SRC = (u32) atomic_xchg( + (atomic_t *)(unsigned long) (DST + insn->off), + (u32) SRC); + break; + case BPF_CMPXCHG: + BPF_R0 = (u32) atomic_cmpxchg( + (atomic_t *)(unsigned long) (DST + insn->off), + (u32) BPF_R0, (u32) SRC); + break; default: goto default_label; } @@ -1647,6 +1657,16 @@ out: (u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); break; + case BPF_XCHG: + SRC = (u64) atomic64_xchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) SRC); + break; + case BPF_CMPXCHG: + BPF_R0 = (u64) atomic64_cmpxchg( + (atomic64_t *)(unsigned long) (DST + insn->off), + (u64) BPF_R0, (u64) SRC); + break; default: goto default_label; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index d2e20f6d0516..ee8d1132767b 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -167,6 +167,21 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_CMPXCHG) { + verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)\n", + insn->code, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_XCHG) { + verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)\n", + insn->code, insn->src_reg, + BPF_SIZE(insn->code) == BPF_DW ? "64" : "", + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6aa1fc919761..89a4d154ab37 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3606,11 +3606,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { + int load_reg; int err; switch (insn->imm) { case BPF_ADD: case BPF_ADD | BPF_FETCH: + case BPF_XCHG: + case BPF_CMPXCHG: break; default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); @@ -3632,6 +3635,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (err) return err; + if (insn->imm == BPF_CMPXCHG) { + /* Check comparison of R0 with memory location */ + err = check_reg_arg(env, BPF_REG_0, SRC_OP); + if (err) + return err; + } + if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; @@ -3662,8 +3672,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (!(insn->imm & BPF_FETCH)) return 0; - /* check and record load of old value into src reg */ - err = check_reg_arg(env, insn->src_reg, DST_OP); + if (insn->imm == BPF_CMPXCHG) + load_reg = BPF_REG_0; + else + load_reg = insn->src_reg; + + /* check and record load of old value */ + err = check_reg_arg(env, load_reg, DST_OP); if (err) return err; diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 7211ce9fba53..d75998b0d5ac 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -174,6 +174,8 @@ * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ea262b009049..c001766adcbc 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -45,7 +45,9 @@ #define BPF_EXIT 0x90 /* function return */ /* atomic op type fields (stored in immediate) */ -#define BPF_FETCH 0x01 /* fetch previous value into src reg */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ /* Register numbers */ enum { -- cgit v1.2.3 From 88a16a1309333e43d328621ece3e9fa37027e8eb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:44 +0100 Subject: perf: Add build id data in mmap2 event Adding support to carry build id data in mmap2 event. The build id data replaces maj/min/ino/ino_generation fields, which are also used to identify map's binary, so it's ok to replace them with build id data: union { struct { u32 maj; u32 min; u64 ino; u64 ino_generation; }; struct { u8 build_id_size; u8 __reserved_1; u16 __reserved_2; u8 build_id[20]; }; }; Replaced maj/min/ino/ino_generation fields give us size of 24 bytes. We use 20 bytes for build id data, 1 byte for size and rest is unused. There's new misc bit for mmap2 to signal there's build id data in it: #define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210114134044.1418404-4-jolsa@kernel.org --- include/uapi/linux/perf_event.h | 42 ++++++++++++++++++++++++++++++++++++----- kernel/events/core.c | 32 +++++++++++++++++++++++++++---- 2 files changed, 65 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..cb6f84103560 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -386,7 +386,8 @@ struct perf_event_attr { aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - __reserved_1 : 30; + build_id : 1, /* use build id in mmap2 events */ + __reserved_1 : 29; union { __u32 wakeup_events; /* wakeup every n events */ @@ -659,6 +660,22 @@ struct perf_event_mmap_page { __u64 aux_size; }; +/* + * The current state of perf_event_header::misc bits usage: + * ('|' used bit, '-' unused bit) + * + * 012 CDEF + * |||---------|||| + * + * Where: + * 0-2 CPUMODE_MASK + * + * C PROC_MAP_PARSE_TIMEOUT + * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT + * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT + * F (reserved) + */ + #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) @@ -690,6 +707,7 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event * * * PERF_RECORD_MISC_EXACT_IP: @@ -699,9 +717,13 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: * Indicates that thread was preempted in TASK_RUNNING state. + * + * PERF_RECORD_MISC_MMAP_BUILD_ID: + * Indicates that mmap2 event carries build id data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) +#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ @@ -915,10 +937,20 @@ enum perf_event_type { * u64 addr; * u64 len; * u64 pgoff; - * u32 maj; - * u32 min; - * u64 ino; - * u64 ino_generation; + * union { + * struct { + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * }; + * struct { + * u8 build_id_size; + * u8 __reserved_1; + * u16 __reserved_2; + * u8 build_id[20]; + * }; + * }; * u32 prot, flags; * char filename[]; * struct sample_id sample_id; diff --git a/kernel/events/core.c b/kernel/events/core.c index 55d18791a72d..c37401e3e5f7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -53,6 +53,7 @@ #include #include #include +#include #include "internal.h" @@ -397,6 +398,7 @@ static atomic_t nr_ksymbol_events __read_mostly; static atomic_t nr_bpf_events __read_mostly; static atomic_t nr_cgroup_events __read_mostly; static atomic_t nr_text_poke_events __read_mostly; +static atomic_t nr_build_id_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -4673,6 +4675,8 @@ static void unaccount_event(struct perf_event *event) dec = true; if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); + if (event->attr.build_id) + atomic_dec(&nr_build_id_events); if (event->attr.comm) atomic_dec(&nr_comm_events); if (event->attr.namespaces) @@ -8046,6 +8050,8 @@ struct perf_mmap_event { u64 ino; u64 ino_generation; u32 prot, flags; + u8 build_id[BUILD_ID_SIZE_MAX]; + u32 build_id_size; struct { struct perf_event_header header; @@ -8077,6 +8083,7 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_sample_data sample; int size = mmap_event->event_id.header.size; u32 type = mmap_event->event_id.header.type; + bool use_build_id; int ret; if (!perf_event_mmap_match(event, data)) @@ -8101,13 +8108,25 @@ static void perf_event_mmap_output(struct perf_event *event, mmap_event->event_id.pid = perf_event_pid(event, current); mmap_event->event_id.tid = perf_event_tid(event, current); + use_build_id = event->attr.build_id && mmap_event->build_id_size; + + if (event->attr.mmap2 && use_build_id) + mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_BUILD_ID; + perf_output_put(&handle, mmap_event->event_id); if (event->attr.mmap2) { - perf_output_put(&handle, mmap_event->maj); - perf_output_put(&handle, mmap_event->min); - perf_output_put(&handle, mmap_event->ino); - perf_output_put(&handle, mmap_event->ino_generation); + if (use_build_id) { + u8 size[4] = { (u8) mmap_event->build_id_size, 0, 0, 0 }; + + __output_copy(&handle, size, 4); + __output_copy(&handle, mmap_event->build_id, BUILD_ID_SIZE_MAX); + } else { + perf_output_put(&handle, mmap_event->maj); + perf_output_put(&handle, mmap_event->min); + perf_output_put(&handle, mmap_event->ino); + perf_output_put(&handle, mmap_event->ino_generation); + } perf_output_put(&handle, mmap_event->prot); perf_output_put(&handle, mmap_event->flags); } @@ -8236,6 +8255,9 @@ got_name: mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; + if (atomic_read(&nr_build_id_events)) + build_id_parse(vma, mmap_event->build_id, &mmap_event->build_id_size); + perf_iterate_sb(perf_event_mmap_output, mmap_event, NULL); @@ -11172,6 +11194,8 @@ static void account_event(struct perf_event *event) inc = true; if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); + if (event->attr.build_id) + atomic_inc(&nr_build_id_events); if (event->attr.comm) atomic_inc(&nr_comm_events); if (event->attr.namespaces) -- cgit v1.2.3 From 429b29aef7f841086949c7359f9c3ccb051e7ea3 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 15 Jan 2021 16:51:29 +0100 Subject: tty: serial: Drop unused efm32 serial driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for this machine was just removed, so drop the now unused UART driver, too. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210115155130.185010-7-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 13 - drivers/tty/serial/Makefile | 1 - drivers/tty/serial/efm32-uart.c | 852 ------------------------------- include/linux/platform_data/efm32-uart.h | 19 - include/uapi/linux/serial_core.h | 3 - 5 files changed, 888 deletions(-) delete mode 100644 drivers/tty/serial/efm32-uart.c delete mode 100644 include/linux/platform_data/efm32-uart.h (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 34a2899e69c0..83f6ca4bf210 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1295,14 +1295,6 @@ config SERIAL_AR933X_NR_UARTS Set this to the number of serial ports you want the driver to support. -config SERIAL_EFM32_UART - tristate "EFM32 UART/USART port" - depends on ARM && (ARCH_EFM32 || COMPILE_TEST) - select SERIAL_CORE - help - This driver support the USART and UART ports on - Energy Micro's efm32 SoCs. - config SERIAL_MPS2_UART_CONSOLE bool "MPS2 UART console support" depends on SERIAL_MPS2_UART @@ -1316,11 +1308,6 @@ config SERIAL_MPS2_UART help This driver support the UART ports on ARM MPS2. -config SERIAL_EFM32_UART_CONSOLE - bool "EFM32 UART/USART console support" - depends on SERIAL_EFM32_UART=y - select SERIAL_CORE_CONSOLE - config SERIAL_ARC tristate "ARC UART driver support" select SERIAL_CORE diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index b85d53f9e9ff..ec2b74091f0c 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -73,7 +73,6 @@ obj-$(CONFIG_SERIAL_SIRFSOC) += sirfsoc_uart.o obj-$(CONFIG_SERIAL_TEGRA) += serial-tegra.o obj-$(CONFIG_SERIAL_TEGRA_TCU) += tegra-tcu.o obj-$(CONFIG_SERIAL_AR933X) += ar933x_uart.o -obj-$(CONFIG_SERIAL_EFM32_UART) += efm32-uart.o obj-$(CONFIG_SERIAL_ARC) += arc_uart.o obj-$(CONFIG_SERIAL_RP2) += rp2.o obj-$(CONFIG_SERIAL_FSL_LPUART) += fsl_lpuart.o diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c deleted file mode 100644 index f12f29cf4f31..000000000000 --- a/drivers/tty/serial/efm32-uart.c +++ /dev/null @@ -1,852 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#define DRIVER_NAME "efm32-uart" -#define DEV_NAME "ttyefm" - -#define UARTn_CTRL 0x00 -#define UARTn_CTRL_SYNC 0x0001 -#define UARTn_CTRL_TXBIL 0x1000 - -#define UARTn_FRAME 0x04 -#define UARTn_FRAME_DATABITS__MASK 0x000f -#define UARTn_FRAME_DATABITS(n) ((n) - 3) -#define UARTn_FRAME_PARITY__MASK 0x0300 -#define UARTn_FRAME_PARITY_NONE 0x0000 -#define UARTn_FRAME_PARITY_EVEN 0x0200 -#define UARTn_FRAME_PARITY_ODD 0x0300 -#define UARTn_FRAME_STOPBITS_HALF 0x0000 -#define UARTn_FRAME_STOPBITS_ONE 0x1000 -#define UARTn_FRAME_STOPBITS_TWO 0x3000 - -#define UARTn_CMD 0x0c -#define UARTn_CMD_RXEN 0x0001 -#define UARTn_CMD_RXDIS 0x0002 -#define UARTn_CMD_TXEN 0x0004 -#define UARTn_CMD_TXDIS 0x0008 - -#define UARTn_STATUS 0x10 -#define UARTn_STATUS_TXENS 0x0002 -#define UARTn_STATUS_TXC 0x0020 -#define UARTn_STATUS_TXBL 0x0040 -#define UARTn_STATUS_RXDATAV 0x0080 - -#define UARTn_CLKDIV 0x14 - -#define UARTn_RXDATAX 0x18 -#define UARTn_RXDATAX_RXDATA__MASK 0x01ff -#define UARTn_RXDATAX_PERR 0x4000 -#define UARTn_RXDATAX_FERR 0x8000 -/* - * This is a software only flag used for ignore_status_mask and - * read_status_mask! It's used for breaks that the hardware doesn't report - * explicitly. - */ -#define SW_UARTn_RXDATAX_BERR 0x2000 - -#define UARTn_TXDATA 0x34 - -#define UARTn_IF 0x40 -#define UARTn_IF_TXC 0x0001 -#define UARTn_IF_TXBL 0x0002 -#define UARTn_IF_RXDATAV 0x0004 -#define UARTn_IF_RXOF 0x0010 - -#define UARTn_IFS 0x44 -#define UARTn_IFC 0x48 -#define UARTn_IEN 0x4c - -#define UARTn_ROUTE 0x54 -#define UARTn_ROUTE_LOCATION__MASK 0x0700 -#define UARTn_ROUTE_LOCATION(n) (((n) << 8) & UARTn_ROUTE_LOCATION__MASK) -#define UARTn_ROUTE_RXPEN 0x0001 -#define UARTn_ROUTE_TXPEN 0x0002 - -struct efm32_uart_port { - struct uart_port port; - unsigned int txirq; - struct clk *clk; - struct efm32_uart_pdata pdata; -}; -#define to_efm_port(_port) container_of(_port, struct efm32_uart_port, port) -#define efm_debug(efm_port, format, arg...) \ - dev_dbg(efm_port->port.dev, format, ##arg) - -static void efm32_uart_write32(struct efm32_uart_port *efm_port, - u32 value, unsigned offset) -{ - writel_relaxed(value, efm_port->port.membase + offset); -} - -static u32 efm32_uart_read32(struct efm32_uart_port *efm_port, - unsigned offset) -{ - return readl_relaxed(efm_port->port.membase + offset); -} - -static unsigned int efm32_uart_tx_empty(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - u32 status = efm32_uart_read32(efm_port, UARTn_STATUS); - - if (status & UARTn_STATUS_TXC) - return TIOCSER_TEMT; - else - return 0; -} - -static void efm32_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) -{ - /* sorry, neither handshaking lines nor loop functionallity */ -} - -static unsigned int efm32_uart_get_mctrl(struct uart_port *port) -{ - /* sorry, no handshaking lines available */ - return TIOCM_CAR | TIOCM_CTS | TIOCM_DSR; -} - -static void efm32_uart_stop_tx(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - u32 ien = efm32_uart_read32(efm_port, UARTn_IEN); - - efm32_uart_write32(efm_port, UARTn_CMD_TXDIS, UARTn_CMD); - ien &= ~(UARTn_IF_TXC | UARTn_IF_TXBL); - efm32_uart_write32(efm_port, ien, UARTn_IEN); -} - -static void efm32_uart_tx_chars(struct efm32_uart_port *efm_port) -{ - struct uart_port *port = &efm_port->port; - struct circ_buf *xmit = &port->state->xmit; - - while (efm32_uart_read32(efm_port, UARTn_STATUS) & - UARTn_STATUS_TXBL) { - if (port->x_char) { - port->icount.tx++; - efm32_uart_write32(efm_port, port->x_char, - UARTn_TXDATA); - port->x_char = 0; - continue; - } - if (!uart_circ_empty(xmit) && !uart_tx_stopped(port)) { - port->icount.tx++; - efm32_uart_write32(efm_port, xmit->buf[xmit->tail], - UARTn_TXDATA); - xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); - } else - break; - } - - if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) - uart_write_wakeup(port); - - if (!port->x_char && uart_circ_empty(xmit) && - efm32_uart_read32(efm_port, UARTn_STATUS) & - UARTn_STATUS_TXC) - efm32_uart_stop_tx(port); -} - -static void efm32_uart_start_tx(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - u32 ien; - - efm32_uart_write32(efm_port, - UARTn_IF_TXBL | UARTn_IF_TXC, UARTn_IFC); - ien = efm32_uart_read32(efm_port, UARTn_IEN); - efm32_uart_write32(efm_port, - ien | UARTn_IF_TXBL | UARTn_IF_TXC, UARTn_IEN); - efm32_uart_write32(efm_port, UARTn_CMD_TXEN, UARTn_CMD); - - efm32_uart_tx_chars(efm_port); -} - -static void efm32_uart_stop_rx(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - - efm32_uart_write32(efm_port, UARTn_CMD_RXDIS, UARTn_CMD); -} - -static void efm32_uart_break_ctl(struct uart_port *port, int ctl) -{ - /* not possible without fiddling with gpios */ -} - -static void efm32_uart_rx_chars(struct efm32_uart_port *efm_port) -{ - struct uart_port *port = &efm_port->port; - - while (efm32_uart_read32(efm_port, UARTn_STATUS) & - UARTn_STATUS_RXDATAV) { - u32 rxdata = efm32_uart_read32(efm_port, UARTn_RXDATAX); - int flag = 0; - - /* - * This is a reserved bit and I only saw it read as 0. But to be - * sure not to be confused too much by new devices adhere to the - * warning in the reference manual that reserved bits might - * read as 1 in the future. - */ - rxdata &= ~SW_UARTn_RXDATAX_BERR; - - port->icount.rx++; - - if ((rxdata & UARTn_RXDATAX_FERR) && - !(rxdata & UARTn_RXDATAX_RXDATA__MASK)) { - rxdata |= SW_UARTn_RXDATAX_BERR; - port->icount.brk++; - if (uart_handle_break(port)) - continue; - } else if (rxdata & UARTn_RXDATAX_PERR) - port->icount.parity++; - else if (rxdata & UARTn_RXDATAX_FERR) - port->icount.frame++; - - rxdata &= port->read_status_mask; - - if (rxdata & SW_UARTn_RXDATAX_BERR) - flag = TTY_BREAK; - else if (rxdata & UARTn_RXDATAX_PERR) - flag = TTY_PARITY; - else if (rxdata & UARTn_RXDATAX_FERR) - flag = TTY_FRAME; - else if (uart_handle_sysrq_char(port, - rxdata & UARTn_RXDATAX_RXDATA__MASK)) - continue; - - if ((rxdata & port->ignore_status_mask) == 0) - tty_insert_flip_char(&port->state->port, - rxdata & UARTn_RXDATAX_RXDATA__MASK, flag); - } -} - -static irqreturn_t efm32_uart_rxirq(int irq, void *data) -{ - struct efm32_uart_port *efm_port = data; - u32 irqflag = efm32_uart_read32(efm_port, UARTn_IF); - int handled = IRQ_NONE; - struct uart_port *port = &efm_port->port; - struct tty_port *tport = &port->state->port; - - spin_lock(&port->lock); - - if (irqflag & UARTn_IF_RXDATAV) { - efm32_uart_write32(efm_port, UARTn_IF_RXDATAV, UARTn_IFC); - efm32_uart_rx_chars(efm_port); - - handled = IRQ_HANDLED; - } - - if (irqflag & UARTn_IF_RXOF) { - efm32_uart_write32(efm_port, UARTn_IF_RXOF, UARTn_IFC); - port->icount.overrun++; - tty_insert_flip_char(tport, 0, TTY_OVERRUN); - - handled = IRQ_HANDLED; - } - - spin_unlock(&port->lock); - - tty_flip_buffer_push(tport); - - return handled; -} - -static irqreturn_t efm32_uart_txirq(int irq, void *data) -{ - struct efm32_uart_port *efm_port = data; - u32 irqflag = efm32_uart_read32(efm_port, UARTn_IF); - - /* TXBL doesn't need to be cleared */ - if (irqflag & UARTn_IF_TXC) - efm32_uart_write32(efm_port, UARTn_IF_TXC, UARTn_IFC); - - if (irqflag & (UARTn_IF_TXC | UARTn_IF_TXBL)) { - efm32_uart_tx_chars(efm_port); - return IRQ_HANDLED; - } else - return IRQ_NONE; -} - -static int efm32_uart_startup(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - int ret; - - ret = clk_enable(efm_port->clk); - if (ret) { - efm_debug(efm_port, "failed to enable clk\n"); - goto err_clk_enable; - } - port->uartclk = clk_get_rate(efm_port->clk); - - /* Enable pins at configured location */ - efm32_uart_write32(efm_port, - UARTn_ROUTE_LOCATION(efm_port->pdata.location) | - UARTn_ROUTE_RXPEN | UARTn_ROUTE_TXPEN, - UARTn_ROUTE); - - ret = request_irq(port->irq, efm32_uart_rxirq, 0, - DRIVER_NAME, efm_port); - if (ret) { - efm_debug(efm_port, "failed to register rxirq\n"); - goto err_request_irq_rx; - } - - /* disable all irqs */ - efm32_uart_write32(efm_port, 0, UARTn_IEN); - - ret = request_irq(efm_port->txirq, efm32_uart_txirq, 0, - DRIVER_NAME, efm_port); - if (ret) { - efm_debug(efm_port, "failed to register txirq\n"); - free_irq(port->irq, efm_port); -err_request_irq_rx: - - clk_disable(efm_port->clk); - } else { - efm32_uart_write32(efm_port, - UARTn_IF_RXDATAV | UARTn_IF_RXOF, UARTn_IEN); - efm32_uart_write32(efm_port, UARTn_CMD_RXEN, UARTn_CMD); - } - -err_clk_enable: - return ret; -} - -static void efm32_uart_shutdown(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - - efm32_uart_write32(efm_port, 0, UARTn_IEN); - free_irq(port->irq, efm_port); - - clk_disable(efm_port->clk); -} - -static void efm32_uart_set_termios(struct uart_port *port, - struct ktermios *new, struct ktermios *old) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - unsigned long flags; - unsigned baud; - u32 clkdiv; - u32 frame = 0; - - /* no modem control lines */ - new->c_cflag &= ~(CRTSCTS | CMSPAR); - - baud = uart_get_baud_rate(port, new, old, - DIV_ROUND_CLOSEST(port->uartclk, 16 * 8192), - DIV_ROUND_CLOSEST(port->uartclk, 16)); - - switch (new->c_cflag & CSIZE) { - case CS5: - frame |= UARTn_FRAME_DATABITS(5); - break; - case CS6: - frame |= UARTn_FRAME_DATABITS(6); - break; - case CS7: - frame |= UARTn_FRAME_DATABITS(7); - break; - case CS8: - frame |= UARTn_FRAME_DATABITS(8); - break; - } - - if (new->c_cflag & CSTOPB) - /* the receiver only verifies the first stop bit */ - frame |= UARTn_FRAME_STOPBITS_TWO; - else - frame |= UARTn_FRAME_STOPBITS_ONE; - - if (new->c_cflag & PARENB) { - if (new->c_cflag & PARODD) - frame |= UARTn_FRAME_PARITY_ODD; - else - frame |= UARTn_FRAME_PARITY_EVEN; - } else - frame |= UARTn_FRAME_PARITY_NONE; - - /* - * the 6 lowest bits of CLKDIV are dc, bit 6 has value 0.25. - * port->uartclk <= 14e6, so 4 * port->uartclk doesn't overflow. - */ - clkdiv = (DIV_ROUND_CLOSEST(4 * port->uartclk, 16 * baud) - 4) << 6; - - spin_lock_irqsave(&port->lock, flags); - - efm32_uart_write32(efm_port, - UARTn_CMD_TXDIS | UARTn_CMD_RXDIS, UARTn_CMD); - - port->read_status_mask = UARTn_RXDATAX_RXDATA__MASK; - if (new->c_iflag & INPCK) - port->read_status_mask |= - UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR; - if (new->c_iflag & (IGNBRK | BRKINT | PARMRK)) - port->read_status_mask |= SW_UARTn_RXDATAX_BERR; - - port->ignore_status_mask = 0; - if (new->c_iflag & IGNPAR) - port->ignore_status_mask |= - UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR; - if (new->c_iflag & IGNBRK) - port->ignore_status_mask |= SW_UARTn_RXDATAX_BERR; - - uart_update_timeout(port, new->c_cflag, baud); - - efm32_uart_write32(efm_port, UARTn_CTRL_TXBIL, UARTn_CTRL); - efm32_uart_write32(efm_port, frame, UARTn_FRAME); - efm32_uart_write32(efm_port, clkdiv, UARTn_CLKDIV); - - efm32_uart_write32(efm_port, UARTn_CMD_TXEN | UARTn_CMD_RXEN, - UARTn_CMD); - - spin_unlock_irqrestore(&port->lock, flags); -} - -static const char *efm32_uart_type(struct uart_port *port) -{ - return port->type == PORT_EFMUART ? "efm32-uart" : NULL; -} - -static void efm32_uart_release_port(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - - clk_unprepare(efm_port->clk); - clk_put(efm_port->clk); - iounmap(port->membase); -} - -static int efm32_uart_request_port(struct uart_port *port) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - int ret; - - port->membase = ioremap(port->mapbase, 60); - if (!efm_port->port.membase) { - ret = -ENOMEM; - efm_debug(efm_port, "failed to remap\n"); - goto err_ioremap; - } - - efm_port->clk = clk_get(port->dev, NULL); - if (IS_ERR(efm_port->clk)) { - ret = PTR_ERR(efm_port->clk); - efm_debug(efm_port, "failed to get clock\n"); - goto err_clk_get; - } - - ret = clk_prepare(efm_port->clk); - if (ret) { - clk_put(efm_port->clk); -err_clk_get: - - iounmap(port->membase); -err_ioremap: - return ret; - } - return 0; -} - -static void efm32_uart_config_port(struct uart_port *port, int type) -{ - if (type & UART_CONFIG_TYPE && - !efm32_uart_request_port(port)) - port->type = PORT_EFMUART; -} - -static int efm32_uart_verify_port(struct uart_port *port, - struct serial_struct *serinfo) -{ - int ret = 0; - - if (serinfo->type != PORT_UNKNOWN && serinfo->type != PORT_EFMUART) - ret = -EINVAL; - - return ret; -} - -static const struct uart_ops efm32_uart_pops = { - .tx_empty = efm32_uart_tx_empty, - .set_mctrl = efm32_uart_set_mctrl, - .get_mctrl = efm32_uart_get_mctrl, - .stop_tx = efm32_uart_stop_tx, - .start_tx = efm32_uart_start_tx, - .stop_rx = efm32_uart_stop_rx, - .break_ctl = efm32_uart_break_ctl, - .startup = efm32_uart_startup, - .shutdown = efm32_uart_shutdown, - .set_termios = efm32_uart_set_termios, - .type = efm32_uart_type, - .release_port = efm32_uart_release_port, - .request_port = efm32_uart_request_port, - .config_port = efm32_uart_config_port, - .verify_port = efm32_uart_verify_port, -}; - -static struct efm32_uart_port *efm32_uart_ports[5]; - -#ifdef CONFIG_SERIAL_EFM32_UART_CONSOLE -static void efm32_uart_console_putchar(struct uart_port *port, int ch) -{ - struct efm32_uart_port *efm_port = to_efm_port(port); - unsigned int timeout = 0x400; - u32 status; - - while (1) { - status = efm32_uart_read32(efm_port, UARTn_STATUS); - - if (status & UARTn_STATUS_TXBL) - break; - if (!timeout--) - return; - } - efm32_uart_write32(efm_port, ch, UARTn_TXDATA); -} - -static void efm32_uart_console_write(struct console *co, const char *s, - unsigned int count) -{ - struct efm32_uart_port *efm_port = efm32_uart_ports[co->index]; - u32 status = efm32_uart_read32(efm_port, UARTn_STATUS); - unsigned int timeout = 0x400; - - if (!(status & UARTn_STATUS_TXENS)) - efm32_uart_write32(efm_port, UARTn_CMD_TXEN, UARTn_CMD); - - uart_console_write(&efm_port->port, s, count, - efm32_uart_console_putchar); - - /* Wait for the transmitter to become empty */ - while (1) { - u32 status = efm32_uart_read32(efm_port, UARTn_STATUS); - if (status & UARTn_STATUS_TXC) - break; - if (!timeout--) - break; - } - - if (!(status & UARTn_STATUS_TXENS)) - efm32_uart_write32(efm_port, UARTn_CMD_TXDIS, UARTn_CMD); -} - -static void efm32_uart_console_get_options(struct efm32_uart_port *efm_port, - int *baud, int *parity, int *bits) -{ - u32 ctrl = efm32_uart_read32(efm_port, UARTn_CTRL); - u32 route, clkdiv, frame; - - if (ctrl & UARTn_CTRL_SYNC) - /* not operating in async mode */ - return; - - route = efm32_uart_read32(efm_port, UARTn_ROUTE); - if (!(route & UARTn_ROUTE_TXPEN)) - /* tx pin not routed */ - return; - - clkdiv = efm32_uart_read32(efm_port, UARTn_CLKDIV); - - *baud = DIV_ROUND_CLOSEST(4 * efm_port->port.uartclk, - 16 * (4 + (clkdiv >> 6))); - - frame = efm32_uart_read32(efm_port, UARTn_FRAME); - switch (frame & UARTn_FRAME_PARITY__MASK) { - case UARTn_FRAME_PARITY_ODD: - *parity = 'o'; - break; - case UARTn_FRAME_PARITY_EVEN: - *parity = 'e'; - break; - default: - *parity = 'n'; - } - - *bits = (frame & UARTn_FRAME_DATABITS__MASK) - - UARTn_FRAME_DATABITS(4) + 4; - - efm_debug(efm_port, "get_opts: options=%d%c%d\n", - *baud, *parity, *bits); -} - -static int efm32_uart_console_setup(struct console *co, char *options) -{ - struct efm32_uart_port *efm_port; - int baud = 115200; - int bits = 8; - int parity = 'n'; - int flow = 'n'; - int ret; - - if (co->index < 0 || co->index >= ARRAY_SIZE(efm32_uart_ports)) { - unsigned i; - for (i = 0; i < ARRAY_SIZE(efm32_uart_ports); ++i) { - if (efm32_uart_ports[i]) { - pr_warn("efm32-console: fall back to console index %u (from %hhi)\n", - i, co->index); - co->index = i; - break; - } - } - } - - efm_port = efm32_uart_ports[co->index]; - if (!efm_port) { - pr_warn("efm32-console: No port at %d\n", co->index); - return -ENODEV; - } - - ret = clk_prepare(efm_port->clk); - if (ret) { - dev_warn(efm_port->port.dev, - "console: clk_prepare failed: %d\n", ret); - return ret; - } - - efm_port->port.uartclk = clk_get_rate(efm_port->clk); - - if (options) - uart_parse_options(options, &baud, &parity, &bits, &flow); - else - efm32_uart_console_get_options(efm_port, - &baud, &parity, &bits); - - return uart_set_options(&efm_port->port, co, baud, parity, bits, flow); -} - -static struct uart_driver efm32_uart_reg; - -static struct console efm32_uart_console = { - .name = DEV_NAME, - .write = efm32_uart_console_write, - .device = uart_console_device, - .setup = efm32_uart_console_setup, - .flags = CON_PRINTBUFFER, - .index = -1, - .data = &efm32_uart_reg, -}; - -#else -#define efm32_uart_console (*(struct console *)NULL) -#endif /* ifdef CONFIG_SERIAL_EFM32_UART_CONSOLE / else */ - -static struct uart_driver efm32_uart_reg = { - .owner = THIS_MODULE, - .driver_name = DRIVER_NAME, - .dev_name = DEV_NAME, - .nr = ARRAY_SIZE(efm32_uart_ports), - .cons = &efm32_uart_console, -}; - -static int efm32_uart_probe_dt(struct platform_device *pdev, - struct efm32_uart_port *efm_port) -{ - struct device_node *np = pdev->dev.of_node; - u32 location; - int ret; - - if (!np) - return 1; - - ret = of_property_read_u32(np, "energymicro,location", &location); - - if (ret) - /* fall back to wrongly namespaced property */ - ret = of_property_read_u32(np, "efm32,location", &location); - - if (ret) - /* fall back to old and (wrongly) generic property "location" */ - ret = of_property_read_u32(np, "location", &location); - - if (!ret) { - if (location > 5) { - dev_err(&pdev->dev, "invalid location\n"); - return -EINVAL; - } - efm_debug(efm_port, "using location %u\n", location); - efm_port->pdata.location = location; - } else { - efm_debug(efm_port, "fall back to location 0\n"); - } - - ret = of_alias_get_id(np, "serial"); - if (ret < 0) { - dev_err(&pdev->dev, "failed to get alias id: %d\n", ret); - return ret; - } else { - efm_port->port.line = ret; - return 0; - } - -} - -static int efm32_uart_probe(struct platform_device *pdev) -{ - struct efm32_uart_port *efm_port; - struct resource *res; - unsigned int line; - int ret; - - efm_port = kzalloc(sizeof(*efm_port), GFP_KERNEL); - if (!efm_port) { - dev_dbg(&pdev->dev, "failed to allocate private data\n"); - return -ENOMEM; - } - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - ret = -ENODEV; - dev_dbg(&pdev->dev, "failed to determine base address\n"); - goto err_get_base; - } - - if (resource_size(res) < 60) { - ret = -EINVAL; - dev_dbg(&pdev->dev, "memory resource too small\n"); - goto err_too_small; - } - - ret = platform_get_irq(pdev, 0); - if (ret <= 0) { - dev_dbg(&pdev->dev, "failed to get rx irq\n"); - goto err_get_rxirq; - } - - efm_port->port.irq = ret; - - ret = platform_get_irq(pdev, 1); - if (ret <= 0) - ret = efm_port->port.irq + 1; - - efm_port->txirq = ret; - - efm_port->port.dev = &pdev->dev; - efm_port->port.mapbase = res->start; - efm_port->port.type = PORT_EFMUART; - efm_port->port.iotype = UPIO_MEM32; - efm_port->port.fifosize = 2; - efm_port->port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_EFM32_UART_CONSOLE); - efm_port->port.ops = &efm32_uart_pops; - efm_port->port.flags = UPF_BOOT_AUTOCONF; - - ret = efm32_uart_probe_dt(pdev, efm_port); - if (ret > 0) { - /* not created by device tree */ - const struct efm32_uart_pdata *pdata = dev_get_platdata(&pdev->dev); - - efm_port->port.line = pdev->id; - - if (pdata) - efm_port->pdata = *pdata; - } else if (ret < 0) - goto err_probe_dt; - - line = efm_port->port.line; - - if (line >= 0 && line < ARRAY_SIZE(efm32_uart_ports)) - efm32_uart_ports[line] = efm_port; - - ret = uart_add_one_port(&efm32_uart_reg, &efm_port->port); - if (ret) { - dev_dbg(&pdev->dev, "failed to add port: %d\n", ret); - - if (line >= 0 && line < ARRAY_SIZE(efm32_uart_ports)) - efm32_uart_ports[line] = NULL; -err_probe_dt: -err_get_rxirq: -err_too_small: -err_get_base: - kfree(efm_port); - } else { - platform_set_drvdata(pdev, efm_port); - dev_dbg(&pdev->dev, "\\o/\n"); - } - - return ret; -} - -static int efm32_uart_remove(struct platform_device *pdev) -{ - struct efm32_uart_port *efm_port = platform_get_drvdata(pdev); - unsigned int line = efm_port->port.line; - - uart_remove_one_port(&efm32_uart_reg, &efm_port->port); - - if (line >= 0 && line < ARRAY_SIZE(efm32_uart_ports)) - efm32_uart_ports[line] = NULL; - - kfree(efm_port); - - return 0; -} - -static const struct of_device_id efm32_uart_dt_ids[] = { - { - .compatible = "energymicro,efm32-uart", - }, { - /* doesn't follow the "vendor,device" scheme, don't use */ - .compatible = "efm32,uart", - }, { - /* sentinel */ - } -}; -MODULE_DEVICE_TABLE(of, efm32_uart_dt_ids); - -static struct platform_driver efm32_uart_driver = { - .probe = efm32_uart_probe, - .remove = efm32_uart_remove, - - .driver = { - .name = DRIVER_NAME, - .of_match_table = efm32_uart_dt_ids, - }, -}; - -static int __init efm32_uart_init(void) -{ - int ret; - - ret = uart_register_driver(&efm32_uart_reg); - if (ret) - return ret; - - ret = platform_driver_register(&efm32_uart_driver); - if (ret) - uart_unregister_driver(&efm32_uart_reg); - - pr_info("EFM32 UART/USART driver\n"); - - return ret; -} -module_init(efm32_uart_init); - -static void __exit efm32_uart_exit(void) -{ - platform_driver_unregister(&efm32_uart_driver); - uart_unregister_driver(&efm32_uart_reg); -} -module_exit(efm32_uart_exit); - -MODULE_AUTHOR("Uwe Kleine-Koenig "); -MODULE_DESCRIPTION("EFM32 UART/USART driver"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/include/linux/platform_data/efm32-uart.h b/include/linux/platform_data/efm32-uart.h deleted file mode 100644 index ccbb8f11db75..000000000000 --- a/include/linux/platform_data/efm32-uart.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * - * - */ -#ifndef __LINUX_PLATFORM_DATA_EFM32_UART_H__ -#define __LINUX_PLATFORM_DATA_EFM32_UART_H__ - -#include - -/** - * struct efm32_uart_pdata - * @location: pinmux location for the I/O pins (to be written to the ROUTE - * register) - */ -struct efm32_uart_pdata { - u8 location; -}; -#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_UART_H__ */ diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 62c22045fe65..c4042dcfdc0c 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -208,9 +208,6 @@ /* Atheros AR933X SoC */ #define PORT_AR933X 99 -/* Energy Micro efm32 SoC */ -#define PORT_EFMUART 100 - /* ARC (Synopsys) on-chip UART */ #define PORT_ARC 101 -- cgit v1.2.3 From 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sat, 9 Jan 2021 23:00:21 -0800 Subject: GTP: add support for flow based tunneling API Following patch add support for flow based tunneling API to send and recv GTP tunnel packet over tunnel metadata API. This would allow this device integration with OVS or eBPF using flow based tunneling APIs. Signed-off-by: Pravin B Shelar Link: https://lore.kernel.org/r/20210110070021.26822-1-pbshelar@fb.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 527 +++++++++++++++++++++++++++---------- include/uapi/linux/gtp.h | 12 + include/uapi/linux/if_link.h | 1 + include/uapi/linux/if_tunnel.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 5 files changed, 398 insertions(+), 144 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 4c04e271f184..851364314ecc 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -21,6 +21,7 @@ #include #include +#include #include #include #include @@ -73,6 +74,9 @@ struct gtp_dev { unsigned int hash_size; struct hlist_head *tid_hash; struct hlist_head *addr_hash; + /* Used by LWT tunnel. */ + bool collect_md; + struct socket *collect_md_sock; }; static unsigned int gtp_net_id __read_mostly; @@ -179,33 +183,121 @@ static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx, return false; } -static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, - unsigned int hdrlen, unsigned int role) +static int gtp_set_tun_dst(struct gtp_dev *gtp, struct sk_buff *skb, + unsigned int hdrlen, u8 gtp_version, + __be64 tid, u8 flags) { - if (!gtp_check_ms(skb, pctx, hdrlen, role)) { - netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); - return 1; + struct metadata_dst *tun_dst; + int opts_len = 0; + + if (unlikely(flags & GTP1_F_MASK)) + opts_len = sizeof(struct gtpu_metadata); + + tun_dst = udp_tun_rx_dst(skb, gtp->sk1u->sk_family, TUNNEL_KEY, tid, opts_len); + if (!tun_dst) { + netdev_dbg(gtp->dev, "Failed to allocate tun_dst"); + goto err; } + netdev_dbg(gtp->dev, "attaching metadata_dst to skb, gtp ver %d hdrlen %d\n", + gtp_version, hdrlen); + if (unlikely(opts_len)) { + struct gtpu_metadata *opts; + struct gtp1_header *gtp1; + + opts = ip_tunnel_info_opts(&tun_dst->u.tun_info); + gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); + opts->ver = GTP_METADATA_V1; + opts->flags = gtp1->flags; + opts->type = gtp1->type; + netdev_dbg(gtp->dev, "recved control pkt: flag %x type: %d\n", + opts->flags, opts->type); + tun_dst->u.tun_info.key.tun_flags |= TUNNEL_GTPU_OPT; + tun_dst->u.tun_info.options_len = opts_len; + skb->protocol = htons(0xffff); /* Unknown */ + } /* Get rid of the GTP + UDP headers. */ if (iptunnel_pull_header(skb, hdrlen, skb->protocol, - !net_eq(sock_net(pctx->sk), dev_net(pctx->dev)))) - return -1; + !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)))) { + gtp->dev->stats.rx_length_errors++; + goto err; + } + + skb_dst_set(skb, &tun_dst->dst); + return 0; +err: + return -1; +} + +static int gtp_rx(struct gtp_dev *gtp, struct sk_buff *skb, + unsigned int hdrlen, u8 gtp_version, unsigned int role, + __be64 tid, u8 flags, u8 type) +{ + if (ip_tunnel_collect_metadata() || gtp->collect_md) { + int err; + + err = gtp_set_tun_dst(gtp, skb, hdrlen, gtp_version, tid, flags); + if (err) + goto err; + } else { + struct pdp_ctx *pctx; + + if (flags & GTP1_F_MASK) + hdrlen += 4; - netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); + if (type != GTP_TPDU) + return 1; + + if (gtp_version == GTP_V0) + pctx = gtp0_pdp_find(gtp, be64_to_cpu(tid)); + else + pctx = gtp1_pdp_find(gtp, be64_to_cpu(tid)); + if (!pctx) { + netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); + return 1; + } + + if (!gtp_check_ms(skb, pctx, hdrlen, role)) { + netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); + return 1; + } + /* Get rid of the GTP + UDP headers. */ + if (iptunnel_pull_header(skb, hdrlen, skb->protocol, + !net_eq(sock_net(pctx->sk), dev_net(gtp->dev)))) { + gtp->dev->stats.rx_length_errors++; + goto err; + } + } + netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n"); /* Now that the UDP and the GTP header have been removed, set up the * new network header. This is required by the upper layer to * calculate the transport header. */ skb_reset_network_header(skb); + if (pskb_may_pull(skb, sizeof(struct iphdr))) { + struct iphdr *iph; + + iph = ip_hdr(skb); + if (iph->version == 4) { + netdev_dbg(gtp->dev, "inner pkt: ipv4"); + skb->protocol = htons(ETH_P_IP); + } else if (iph->version == 6) { + netdev_dbg(gtp->dev, "inner pkt: ipv6"); + skb->protocol = htons(ETH_P_IPV6); + } else { + netdev_dbg(gtp->dev, "inner pkt error: Unknown type"); + } + } - skb->dev = pctx->dev; - - dev_sw_netstats_rx_add(pctx->dev, skb->len); - + skb->dev = gtp->dev; + dev_sw_netstats_rx_add(gtp->dev, skb->len); netif_rx(skb); return 0; + +err: + gtp->dev->stats.rx_dropped++; + return -1; } /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ @@ -214,7 +306,6 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp0_header); struct gtp0_header *gtp0; - struct pdp_ctx *pctx; if (!pskb_may_pull(skb, hdrlen)) return -1; @@ -224,16 +315,7 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if ((gtp0->flags >> 5) != GTP_V0) return 1; - if (gtp0->type != GTP_TPDU) - return 1; - - pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid)); - if (!pctx) { - netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); - return 1; - } - - return gtp_rx(pctx, skb, hdrlen, gtp->role); + return gtp_rx(gtp, skb, hdrlen, GTP_V0, gtp->role, gtp0->tid, gtp0->flags, gtp0->type); } static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) @@ -241,41 +323,30 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp1_header); struct gtp1_header *gtp1; - struct pdp_ctx *pctx; if (!pskb_may_pull(skb, hdrlen)) return -1; gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); + netdev_dbg(gtp->dev, "GTPv1 recv: flags %x\n", gtp1->flags); if ((gtp1->flags >> 5) != GTP_V1) return 1; - if (gtp1->type != GTP_TPDU) - return 1; - /* From 29.060: "This field shall be present if and only if any one or * more of the S, PN and E flags are set.". * * If any of the bit is set, then the remaining ones also have to be * set. */ - if (gtp1->flags & GTP1_F_MASK) - hdrlen += 4; - /* Make sure the header is larger enough, including extensions. */ if (!pskb_may_pull(skb, hdrlen)) return -1; gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); - pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid)); - if (!pctx) { - netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); - return 1; - } - - return gtp_rx(pctx, skb, hdrlen, gtp->role); + return gtp_rx(gtp, skb, hdrlen, GTP_V1, gtp->role, + key32_to_tunnel_id(gtp1->tid), gtp1->flags, gtp1->type); } static void __gtp_encap_destroy(struct sock *sk) @@ -315,6 +386,11 @@ static void gtp_encap_disable(struct gtp_dev *gtp) { gtp_encap_disable_sock(gtp->sk0); gtp_encap_disable_sock(gtp->sk1u); + if (gtp->collect_md_sock) { + udp_tunnel_sock_release(gtp->collect_md_sock); + gtp->collect_md_sock = NULL; + netdev_dbg(gtp->dev, "GTP socket released.\n"); + } } /* UDP encapsulation receive handler. See net/ipv4/udp.c. @@ -329,7 +405,8 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!gtp) return 1; - netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); + netdev_dbg(gtp->dev, "encap_recv sk=%p type %d\n", + sk, udp_sk(sk)->encap_type); switch (udp_sk(sk)->encap_type) { case UDP_ENCAP_GTP0: @@ -383,12 +460,13 @@ static void gtp_dev_uninit(struct net_device *dev) static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, const struct sock *sk, - __be32 daddr) + __be32 daddr, + __be32 saddr) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = sk->sk_bound_dev_if; fl4->daddr = daddr; - fl4->saddr = inet_sk(sk)->inet_saddr; + fl4->saddr = saddr; fl4->flowi4_tos = RT_CONN_FLAGS(sk); fl4->flowi4_proto = sk->sk_protocol; @@ -412,7 +490,7 @@ static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) gtp0->tid = cpu_to_be64(pctx->u.v0.tid); } -static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) +static inline void gtp1_push_header(struct sk_buff *skb, __be32 tid) { int payload_len = skb->len; struct gtp1_header *gtp1; @@ -428,46 +506,63 @@ static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) gtp1->flags = 0x30; /* v1, GTP-non-prime. */ gtp1->type = GTP_TPDU; gtp1->length = htons(payload_len); - gtp1->tid = htonl(pctx->u.v1.o_tei); + gtp1->tid = tid; /* TODO: Suppport for extension header, sequence number and N-PDU. * Update the length field if any of them is available. */ } -struct gtp_pktinfo { - struct sock *sk; - struct iphdr *iph; - struct flowi4 fl4; - struct rtable *rt; - struct pdp_ctx *pctx; - struct net_device *dev; - __be16 gtph_port; -}; - -static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo) +static inline int gtp1_push_control_header(struct sk_buff *skb, + __be32 tid, + struct gtpu_metadata *opts, + struct net_device *dev) { - switch (pktinfo->pctx->gtp_version) { - case GTP_V0: - pktinfo->gtph_port = htons(GTP0_PORT); - gtp0_push_header(skb, pktinfo->pctx); - break; - case GTP_V1: - pktinfo->gtph_port = htons(GTP1U_PORT); - gtp1_push_header(skb, pktinfo->pctx); - break; + struct gtp1_header *gtp1c; + int payload_len; + + if (opts->ver != GTP_METADATA_V1) + return -ENOENT; + + if (opts->type == 0xFE) { + /* for end marker ignore skb data. */ + netdev_dbg(dev, "xmit pkt with null data"); + pskb_trim(skb, 0); } + if (skb_cow_head(skb, sizeof(*gtp1c)) < 0) + return -ENOMEM; + + payload_len = skb->len; + + gtp1c = skb_push(skb, sizeof(*gtp1c)); + + gtp1c->flags = opts->flags; + gtp1c->type = opts->type; + gtp1c->length = htons(payload_len); + gtp1c->tid = tid; + netdev_dbg(dev, "xmit control pkt: ver %d flags %x type %x pkt len %d tid %x", + opts->ver, opts->flags, opts->type, skb->len, tid); + return 0; } +struct gtp_pktinfo { + struct sock *sk; + __u8 tos; + struct flowi4 fl4; + struct rtable *rt; + struct net_device *dev; + __be16 gtph_port; +}; + static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo, - struct sock *sk, struct iphdr *iph, - struct pdp_ctx *pctx, struct rtable *rt, + struct sock *sk, + __u8 tos, + struct rtable *rt, struct flowi4 *fl4, struct net_device *dev) { pktinfo->sk = sk; - pktinfo->iph = iph; - pktinfo->pctx = pctx; + pktinfo->tos = tos; pktinfo->rt = rt; pktinfo->fl4 = *fl4; pktinfo->dev = dev; @@ -477,40 +572,99 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo) { struct gtp_dev *gtp = netdev_priv(dev); + struct gtpu_metadata *opts = NULL; + struct sock *sk = NULL; struct pdp_ctx *pctx; struct rtable *rt; struct flowi4 fl4; - struct iphdr *iph; - __be16 df; + u8 gtp_version; + __be16 df = 0; + __be32 tun_id; + __be32 daddr; + __be32 saddr; + __u8 tos; int mtu; - /* Read the IP destination address and resolve the PDP context. - * Prepend PDP header with TEI/TID from PDP ctx. - */ - iph = ip_hdr(skb); - if (gtp->role == GTP_ROLE_SGSN) - pctx = ipv4_pdp_find(gtp, iph->saddr); - else - pctx = ipv4_pdp_find(gtp, iph->daddr); + if (gtp->collect_md) { + /* LWT GTP1U encap */ + struct ip_tunnel_info *info = NULL; - if (!pctx) { - netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n", - &iph->daddr); - return -ENOENT; + info = skb_tunnel_info(skb); + if (!info) { + netdev_dbg(dev, "missing tunnel info"); + return -ENOENT; + } + if (info->key.tp_dst && ntohs(info->key.tp_dst) != GTP1U_PORT) { + netdev_dbg(dev, "unexpected GTP dst port: %d", ntohs(info->key.tp_dst)); + return -EOPNOTSUPP; + } + pctx = NULL; + gtp_version = GTP_V1; + tun_id = tunnel_id_to_key32(info->key.tun_id); + daddr = info->key.u.ipv4.dst; + saddr = info->key.u.ipv4.src; + sk = gtp->sk1u; + if (!sk) { + netdev_dbg(dev, "missing tunnel sock"); + return -EOPNOTSUPP; + } + tos = info->key.tos; + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + + if (info->options_len != 0) { + if (info->key.tun_flags & TUNNEL_GTPU_OPT) { + opts = ip_tunnel_info_opts(info); + } else { + netdev_dbg(dev, "missing tunnel metadata for control pkt"); + return -EOPNOTSUPP; + } + } + netdev_dbg(dev, "flow-based GTP1U encap: tunnel id %d\n", + be32_to_cpu(tun_id)); + } else { + struct iphdr *iph; + + if (ntohs(skb->protocol) != ETH_P_IP) + return -EOPNOTSUPP; + + iph = ip_hdr(skb); + + /* Read the IP destination address and resolve the PDP context. + * Prepend PDP header with TEI/TID from PDP ctx. + */ + if (gtp->role == GTP_ROLE_SGSN) + pctx = ipv4_pdp_find(gtp, iph->saddr); + else + pctx = ipv4_pdp_find(gtp, iph->daddr); + + if (!pctx) { + netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n", + &iph->daddr); + return -ENOENT; + } + sk = pctx->sk; + netdev_dbg(dev, "found PDP context %p\n", pctx); + + gtp_version = pctx->gtp_version; + tun_id = htonl(pctx->u.v1.o_tei); + daddr = pctx->peer_addr_ip4.s_addr; + saddr = inet_sk(sk)->inet_saddr; + tos = iph->tos; + df = iph->frag_off; + netdev_dbg(dev, "gtp -> IP src: %pI4 dst: %pI4\n", + &iph->saddr, &iph->daddr); } - netdev_dbg(dev, "found PDP context %p\n", pctx); - rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr); + rt = ip4_route_output_gtp(&fl4, sk, daddr, saddr); if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to SSGN %pI4\n", - &pctx->peer_addr_ip4.s_addr); + netdev_dbg(dev, "no route to SSGN %pI4\n", &daddr); dev->stats.tx_carrier_errors++; goto err; } if (rt->dst.dev == dev) { - netdev_dbg(dev, "circular route to SSGN %pI4\n", - &pctx->peer_addr_ip4.s_addr); + netdev_dbg(dev, "circular route to SSGN %pI4\n", &daddr); dev->stats.collisions++; goto err_rt; } @@ -518,11 +672,10 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* This is similar to tnl_update_pmtu(). */ - df = iph->frag_off; if (df) { mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct iphdr) - sizeof(struct udphdr); - switch (pctx->gtp_version) { + switch (gtp_version) { case GTP_V0: mtu -= sizeof(struct gtp0_header); break; @@ -536,17 +689,38 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false); - if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && - mtu < ntohs(iph->tot_len)) { - netdev_dbg(dev, "packet too big, fragmentation needed\n"); + if (!skb_is_gso(skb) && (df & htons(IP_DF)) && mtu < skb->len) { + netdev_dbg(dev, "packet too big, fragmentation needed"); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; } - gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev); - gtp_push_header(skb, pktinfo); + gtp_set_pktinfo_ipv4(pktinfo, sk, tos, rt, &fl4, dev); + + if (unlikely(opts)) { + int err; + + pktinfo->gtph_port = htons(GTP1U_PORT); + err = gtp1_push_control_header(skb, tun_id, opts, dev); + if (err) { + netdev_info(dev, "cntr pkt error %d", err); + goto err_rt; + } + return 0; + } + + switch (gtp_version) { + case GTP_V0: + pktinfo->gtph_port = htons(GTP0_PORT); + gtp0_push_header(skb, pctx); + break; + case GTP_V1: + pktinfo->gtph_port = htons(GTP1U_PORT); + gtp1_push_header(skb, tun_id); + break; + } return 0; err_rt: @@ -557,7 +731,6 @@ err: static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) { - unsigned int proto = ntohs(skb->protocol); struct gtp_pktinfo pktinfo; int err; @@ -569,32 +742,22 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ rcu_read_lock(); - switch (proto) { - case ETH_P_IP: - err = gtp_build_skb_ip4(skb, dev, &pktinfo); - break; - default: - err = -EOPNOTSUPP; - break; - } + err = gtp_build_skb_ip4(skb, dev, &pktinfo); rcu_read_unlock(); if (err < 0) goto tx_err; - switch (proto) { - case ETH_P_IP: - netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n", - &pktinfo.iph->saddr, &pktinfo.iph->daddr); - udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb, - pktinfo.fl4.saddr, pktinfo.fl4.daddr, - pktinfo.iph->tos, - ip4_dst_hoplimit(&pktinfo.rt->dst), - 0, - pktinfo.gtph_port, pktinfo.gtph_port, - true, false); - break; - } + udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb, + pktinfo.fl4.saddr, + pktinfo.fl4.daddr, + pktinfo.tos, + ip4_dst_hoplimit(&pktinfo.rt->dst), + 0, + pktinfo.gtph_port, + pktinfo.gtph_port, + true, + false); return NETDEV_TX_OK; tx_err: @@ -610,6 +773,19 @@ static const struct net_device_ops gtp_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, }; +static struct gtp_dev *gtp_find_flow_based_dev(struct net *net) +{ + struct gtp_net *gn = net_generic(net, gtp_net_id); + struct gtp_dev *gtp; + + list_for_each_entry(gtp, &gn->gtp_dev_list, list) { + if (gtp->collect_md) + return gtp; + } + + return NULL; +} + static void gtp_link_setup(struct net_device *dev) { dev->netdev_ops = >p_netdev_ops; @@ -634,7 +810,7 @@ static void gtp_link_setup(struct net_device *dev) } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); -static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); +static int gtp_encap_enable(struct gtp_dev *gtp, struct net_device *dev, struct nlattr *data[]); static void gtp_destructor(struct net_device *dev) { @@ -652,11 +828,24 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, struct gtp_net *gn; int hashsize, err; - if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) + if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1] && + !data[IFLA_GTP_COLLECT_METADATA]) return -EINVAL; gtp = netdev_priv(dev); + if (data[IFLA_GTP_COLLECT_METADATA]) { + if (data[IFLA_GTP_FD0]) { + netdev_dbg(dev, "LWT device does not support setting v0 socket"); + return -EINVAL; + } + if (gtp_find_flow_based_dev(src_net)) { + netdev_dbg(dev, "LWT device already exist"); + return -EBUSY; + } + gtp->collect_md = true; + } + if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; } else { @@ -669,7 +858,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - err = gtp_encap_enable(gtp, data); + err = gtp_encap_enable(gtp, dev, data); if (err < 0) goto out_hashtable; @@ -683,7 +872,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, list_add_rcu(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; - netdev_dbg(dev, "registered new GTP interface\n"); + netdev_dbg(dev, "registered new GTP interface %s\n", dev->name); return 0; @@ -714,6 +903,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_FD1] = { .type = NLA_U32 }, [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 }, [IFLA_GTP_ROLE] = { .type = NLA_U32 }, + [IFLA_GTP_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], @@ -737,6 +927,9 @@ static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size)) goto nla_put_failure; + if (gtp->collect_md && nla_put_flag(skb, IFLA_GTP_COLLECT_METADATA)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -782,35 +975,24 @@ err1: return -ENOMEM; } -static struct sock *gtp_encap_enable_socket(int fd, int type, - struct gtp_dev *gtp) +static int __gtp_encap_enable_socket(struct socket *sock, int type, + struct gtp_dev *gtp) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; - struct socket *sock; struct sock *sk; - int err; - - pr_debug("enable gtp on %d, %d\n", fd, type); - - sock = sockfd_lookup(fd, &err); - if (!sock) { - pr_debug("gtp socket fd=%d not found\n", fd); - return NULL; - } sk = sock->sk; if (sk->sk_protocol != IPPROTO_UDP || sk->sk_type != SOCK_DGRAM || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { - pr_debug("socket fd=%d not UDP\n", fd); - sk = ERR_PTR(-EINVAL); - goto out_sock; + pr_debug("socket not UDP\n"); + return -EINVAL; } lock_sock(sk); if (sk->sk_user_data) { - sk = ERR_PTR(-EBUSY); - goto out_rel_sock; + release_sock(sock->sk); + return -EBUSY; } sock_hold(sk); @@ -821,15 +1003,58 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, tuncfg.encap_destroy = gtp_encap_destroy; setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); - -out_rel_sock: release_sock(sock->sk); -out_sock: + return 0; +} + +static struct sock *gtp_encap_enable_socket(int fd, int type, + struct gtp_dev *gtp) +{ + struct socket *sock; + int err; + + pr_debug("enable gtp on %d, %d\n", fd, type); + + sock = sockfd_lookup(fd, &err); + if (!sock) { + pr_debug("gtp socket fd=%d not found\n", fd); + return NULL; + } + err = __gtp_encap_enable_socket(sock, type, gtp); sockfd_put(sock); - return sk; + if (err) + return ERR_PTR(err); + + return sock->sk; } -static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) +static struct socket *gtp_create_gtp_socket(struct gtp_dev *gtp, struct net_device *dev) +{ + struct udp_port_cfg udp_conf; + struct socket *sock; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + udp_conf.local_udp_port = htons(GTP1U_PORT); + + err = udp_sock_create(dev_net(dev), &udp_conf, &sock); + if (err < 0) { + pr_debug("create gtp sock failed: %d\n", err); + return ERR_PTR(err); + } + err = __gtp_encap_enable_socket(sock, UDP_ENCAP_GTP1U, gtp); + if (err) { + pr_debug("enable gtp sock encap failed: %d\n", err); + udp_tunnel_sock_release(sock); + return ERR_PTR(err); + } + pr_debug("create gtp sock done\n"); + return sock; +} + +static int gtp_encap_enable(struct gtp_dev *gtp, struct net_device *dev, struct nlattr *data[]) { struct sock *sk1u = NULL; struct sock *sk0 = NULL; @@ -853,11 +1078,25 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) } } + if (data[IFLA_GTP_COLLECT_METADATA]) { + struct socket *sock; + + if (!sk1u) { + sock = gtp_create_gtp_socket(gtp, dev); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + gtp->collect_md_sock = sock; + sk1u = sock->sk; + } else { + gtp->collect_md_sock = NULL; + } + } + if (data[IFLA_GTP_ROLE]) { role = nla_get_u32(data[IFLA_GTP_ROLE]); if (role > GTP_ROLE_SGSN) { - gtp_encap_disable_sock(sk0); - gtp_encap_disable_sock(sk1u); + gtp_encap_disable(gtp); return -EINVAL; } } @@ -1416,7 +1655,7 @@ static int __init gtp_init(void) if (err < 0) goto unreg_genl_family; - pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", + pr_info("GTP module loaded (pdp ctx size %zd bytes) with tnl-md support\n", sizeof(struct pdp_ctx)); return 0; diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 79f9191bbb24..62aff78b7c56 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#include + #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -34,4 +36,14 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) +enum { + GTP_METADATA_V1 +}; + +struct gtpu_metadata { + __u8 ver; + __u8 flags; + __u8 type; +}; + #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 82708c6db432..2bd0d8bbcdb2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -809,6 +809,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 7d9105533c7b..802da679fab1 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,6 +176,7 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) +#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index d208b2af697f..28d649bda686 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -617,6 +617,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From 7ae41220ef5831674f446baef19bfe1b31358260 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 11 Jan 2021 00:17:36 +0100 Subject: rtc: introduce features bitfield Introduce a bitfield to allow the drivers to announce the available features for an RTC. The main use case would be to better handle alarms, that could be present or not or have a minute resolution or may need a correct week day to be set. Use the newly introduced RTC_FEATURE_ALARM bit to then test whether alarms are available instead of relying on the presence of ops->set_alarm. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210110231752.1418816-2-alexandre.belloni@bootlin.com --- drivers/rtc/class.c | 5 +++++ drivers/rtc/interface.c | 12 ++++++------ include/linux/rtc.h | 2 ++ include/uapi/linux/rtc.h | 5 +++++ 4 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 7e470fbd5e4d..03abd0aa229a 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -231,6 +231,8 @@ static struct rtc_device *rtc_allocate_device(void) rtc->pie_timer.function = rtc_pie_update_irq; rtc->pie_enabled = 0; + set_bit(RTC_FEATURE_ALARM, rtc->features); + return rtc; } @@ -386,6 +388,9 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) return -EINVAL; } + if (!rtc->ops->set_alarm) + clear_bit(RTC_FEATURE_ALARM, rtc->features); + rtc->owner = owner; rtc_device_get_offset(rtc); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 794a4f036b99..dcb34c73319e 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -186,7 +186,7 @@ static int rtc_read_alarm_internal(struct rtc_device *rtc, if (!rtc->ops) { err = -ENODEV; - } else if (!rtc->ops->read_alarm) { + } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->read_alarm) { err = -EINVAL; } else { alarm->enabled = 0; @@ -392,7 +392,7 @@ int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) return err; if (!rtc->ops) { err = -ENODEV; - } else if (!rtc->ops->read_alarm) { + } else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->read_alarm) { err = -EINVAL; } else { memset(alarm, 0, sizeof(struct rtc_wkalrm)); @@ -436,7 +436,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (!rtc->ops) err = -ENODEV; - else if (!rtc->ops->set_alarm) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) err = -EINVAL; else err = rtc->ops->set_alarm(rtc->dev.parent, alarm); @@ -451,7 +451,7 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (!rtc->ops) return -ENODEV; - else if (!rtc->ops->set_alarm) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -EINVAL; err = rtc_valid_tm(&alarm->time); @@ -531,7 +531,7 @@ int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) /* nothing */; else if (!rtc->ops) err = -ENODEV; - else if (!rtc->ops->alarm_irq_enable) + else if (!test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) err = -EINVAL; else err = rtc->ops->alarm_irq_enable(rtc->dev.parent, enabled); @@ -843,7 +843,7 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) static void rtc_alarm_disable(struct rtc_device *rtc) { - if (!rtc->ops || !rtc->ops->alarm_irq_enable) + if (!rtc->ops || !test_bit(RTC_FEATURE_ALARM, rtc->features) || !rtc->ops->alarm_irq_enable) return; rtc->ops->alarm_irq_enable(rtc->dev.parent, false); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 568909449c13..bd611e26291d 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -141,6 +141,8 @@ struct rtc_device { */ unsigned long set_offset_nsec; + unsigned long features[BITS_TO_LONGS(RTC_FEATURE_CNT)]; + time64_t range_min; timeu64_t range_max; time64_t start_secs; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index fa9aff91cbf2..f950bff75e97 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -110,6 +110,11 @@ struct rtc_pll_info { #define RTC_AF 0x20 /* Alarm interrupt */ #define RTC_UF 0x10 /* Update interrupt for 1Hz RTC */ +/* feature list */ +#define RTC_FEATURE_ALARM 0 +#define RTC_FEATURE_ALARM_RES_MINUTE 1 +#define RTC_FEATURE_NEED_WEEK_DAY 2 +#define RTC_FEATURE_CNT 3 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From f2fc9ff28d1c9bef7760516feadd38164044caae Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 13 Jan 2021 18:52:46 -0800 Subject: usb: ch9: Add USB 3.2 SSP attributes In preparation for USB 3.2 dual-lane support, add sublink speed attribute macros and enum usb_ssp_rate. A USB device that operates in SuperSpeed Plus may operate at different speed and lane count. These additional macros and enum values help specifying that. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/ae9293ebd63a29f2a2035054753534d9eb123d74.1610592135.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 9 +++++++++ include/uapi/linux/usb/ch9.h | 13 +++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 604c6c514a50..86c50907634e 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -36,6 +36,15 @@ #include #include +/* USB 3.2 SuperSpeed Plus phy signaling rate generation and lane count */ + +enum usb_ssp_rate { + USB_SSP_GEN_UNKNOWN = 0, + USB_SSP_GEN_2x1, + USB_SSP_GEN_1x2, + USB_SSP_GEN_2x2, +}; + /** * usb_ep_type_string() - Returns human readable-name of the endpoint type. * @ep_type: The endpoint type to return human-readable name for. If it's not diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 0f865ae4ba89..17ce56198c9a 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -968,9 +968,22 @@ struct usb_ssp_cap_descriptor { __le32 bmSublinkSpeedAttr[1]; /* list of sublink speed attrib entries */ #define USB_SSP_SUBLINK_SPEED_SSID (0xf) /* sublink speed ID */ #define USB_SSP_SUBLINK_SPEED_LSE (0x3 << 4) /* Lanespeed exponent */ +#define USB_SSP_SUBLINK_SPEED_LSE_BPS 0 +#define USB_SSP_SUBLINK_SPEED_LSE_KBPS 1 +#define USB_SSP_SUBLINK_SPEED_LSE_MBPS 2 +#define USB_SSP_SUBLINK_SPEED_LSE_GBPS 3 + #define USB_SSP_SUBLINK_SPEED_ST (0x3 << 6) /* Sublink type */ +#define USB_SSP_SUBLINK_SPEED_ST_SYM_RX 0 +#define USB_SSP_SUBLINK_SPEED_ST_ASYM_RX 1 +#define USB_SSP_SUBLINK_SPEED_ST_SYM_TX 2 +#define USB_SSP_SUBLINK_SPEED_ST_ASYM_TX 3 + #define USB_SSP_SUBLINK_SPEED_RSVD (0x3f << 8) /* Reserved */ #define USB_SSP_SUBLINK_SPEED_LP (0x3 << 14) /* Link protocol */ +#define USB_SSP_SUBLINK_SPEED_LP_SS 0 +#define USB_SSP_SUBLINK_SPEED_LP_SSP 1 + #define USB_SSP_SUBLINK_SPEED_LSM (0xff << 16) /* Lanespeed mantissa */ } __attribute__((packed)); -- cgit v1.2.3 From 7b8fc0103bb51d1d3e1fb5fd67958612e709f883 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 18 Jan 2021 20:09:27 -0500 Subject: bonding: add a vlan+srcmac tx hashing option This comes from an end-user request, where they're running multiple VMs on hosts with bonded interfaces connected to some interest switch topologies, where 802.3ad isn't an option. They're currently running a proprietary solution that effectively achieves load-balancing of VMs and bandwidth utilization improvements with a similar form of transmission algorithm. Basically, each VM has it's own vlan, so it always sends its traffic out the same interface, unless that interface fails. Traffic gets split between the interfaces, maintaining a consistent path, with failover still available if an interface goes down. Unlike bond_eth_hash(), this hash function is using the full source MAC address instead of just the last byte, as there are so few components to the hash, and in the no-vlan case, we would be returning just the last byte of the source MAC as the hash value. It's entirely possible to have two NICs in a bond with the same last byte of their MAC, but not the same MAC, so this adjustment should guarantee distinct hashes in all cases. This has been rudimetarily tested to provide similar results to the proprietary solution it is aiming to replace. A patch for iproute2 is also posted, to properly support the new mode there as well. Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Cc: Thomas Davis Signed-off-by: Jarod Wilson Link: https://lore.kernel.org/r/20210119010927.1191922-1-jarod@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/networking/bonding.rst | 13 +++++++++++++ drivers/net/bonding/bond_main.c | 34 ++++++++++++++++++++++++++++++++-- drivers/net/bonding/bond_options.c | 13 +++++++------ include/linux/netdevice.h | 1 + include/uapi/linux/if_bonding.h | 1 + 5 files changed, 54 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index adc314639085..5f690f0ad0e4 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -951,6 +951,19 @@ xmit_hash_policy packets will be distributed according to the encapsulated flows. + vlan+srcmac + + This policy uses a very rudimentary vlan ID and source mac + hash to load-balance traffic per-vlan, with failover + should one leg fail. The intended use case is for a bond + shared by multiple virtual machines, all configured to + use their own vlan, to give lacp-like functionality + without requiring lacp-capable switching hardware. + + The formula for the hash is simply + + hash = (vlan ID) XOR (source MAC vendor) XOR (source MAC dev) + The default value is layer2. This option was added in bonding version 2.6.3. In earlier versions of bonding, this parameter does not exist, and the layer2 policy is the only policy. The diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 539c6bc218df..74cbbb22470b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -167,7 +167,7 @@ module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " "2 for layer 2+3, 3 for encap layer 2+3, " - "4 for encap layer 3+4"); + "4 for encap layer 3+4, 5 for vlan+srcmac"); module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); @@ -1457,6 +1457,8 @@ static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond, return NETDEV_LAG_HASH_E23; case BOND_XMIT_POLICY_ENCAP34: return NETDEV_LAG_HASH_E34; + case BOND_XMIT_POLICY_VLAN_SRCMAC: + return NETDEV_LAG_HASH_VLAN_SRCMAC; default: return NETDEV_LAG_HASH_UNKNOWN; } @@ -3519,6 +3521,27 @@ static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, return true; } +static u32 bond_vlan_srcmac_hash(struct sk_buff *skb) +{ + struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb); + u32 srcmac_vendor = 0, srcmac_dev = 0; + u16 vlan; + int i; + + for (i = 0; i < 3; i++) + srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; + + for (i = 3; i < ETH_ALEN; i++) + srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i]; + + if (!skb_vlan_tag_present(skb)) + return srcmac_vendor ^ srcmac_dev; + + vlan = skb_vlan_tag_get(skb); + + return vlan ^ srcmac_vendor ^ srcmac_dev; +} + /* Extract the appropriate headers based on bond's xmit policy */ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, struct flow_keys *fk) @@ -3526,10 +3549,14 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; int noff, proto = -1; - if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) { + switch (bond->params.xmit_policy) { + case BOND_XMIT_POLICY_ENCAP23: + case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, fk, NULL, 0, 0, 0, 0); + default: + break; } fk->ports.ports = 0; @@ -3591,6 +3618,9 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) skb->l4_hash) return skb->hash; + if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC) + return bond_vlan_srcmac_hash(skb); + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || !bond_flow_dissect(bond, skb, &flow)) return bond_eth_hash(skb); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 8fcbf7f9c7b2..77d7c38bd435 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -96,12 +96,13 @@ static const struct bond_opt_value bond_pps_tbl[] = { }; static const struct bond_opt_value bond_xmit_hashtype_tbl[] = { - { "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT}, - { "layer3+4", BOND_XMIT_POLICY_LAYER34, 0}, - { "layer2+3", BOND_XMIT_POLICY_LAYER23, 0}, - { "encap2+3", BOND_XMIT_POLICY_ENCAP23, 0}, - { "encap3+4", BOND_XMIT_POLICY_ENCAP34, 0}, - { NULL, -1, 0}, + { "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT}, + { "layer3+4", BOND_XMIT_POLICY_LAYER34, 0}, + { "layer2+3", BOND_XMIT_POLICY_LAYER23, 0}, + { "encap2+3", BOND_XMIT_POLICY_ENCAP23, 0}, + { "encap3+4", BOND_XMIT_POLICY_ENCAP34, 0}, + { "vlan+srcmac", BOND_XMIT_POLICY_VLAN_SRCMAC, 0}, + { NULL, -1, 0}, }; static const struct bond_opt_value bond_arp_validate_tbl[] = { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02dcef4d66e2..ef517254367d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2617,6 +2617,7 @@ enum netdev_lag_hash { NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 45f3750aa861..e8eb4ad03cf1 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -94,6 +94,7 @@ #define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */ #define BOND_XMIT_POLICY_ENCAP23 3 /* encapsulated layer 2+3 */ #define BOND_XMIT_POLICY_ENCAP34 4 /* encapsulated layer 3+4 */ +#define BOND_XMIT_POLICY_VLAN_SRCMAC 5 /* vlan + source MAC */ /* 802.3ad port state definitions (43.4.2.2 in the 802.3ad standard) */ #define LACP_STATE_LACP_ACTIVITY 0x1 -- cgit v1.2.3 From 7baf2429a1a965369b0ce44efb6315cdd515aa9c Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 19 Jan 2021 16:31:50 +0800 Subject: net/sched: cls_flower add CT_FLAGS_INVALID flag support This patch add the TCA_FLOWER_KEY_CT_FLAGS_INVALID flag to match the ct_state with invalid for conntrack. Signed-off-by: wenxu Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/1611045110-682-1-git-send-email-wenxu@ucloud.cn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- include/net/sch_generic.h | 1 + include/uapi/linux/pkt_cls.h | 1 + net/core/dev.c | 2 ++ net/core/flow_dissector.c | 13 +++++++++---- net/sched/act_ct.c | 1 + net/sched/cls_flower.c | 4 +++- 7 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46f901adf1a8..186dad231e30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1353,8 +1353,8 @@ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, - u16 *ctinfo_map, - size_t mapsize); + u16 *ctinfo_map, size_t mapsize, + bool post_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 639e465a108f..e7bee99aebce 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -388,6 +388,7 @@ struct qdisc_skb_cb { #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; u16 mru; + bool post_ct; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..709668e264b0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ }; enum { diff --git a/net/core/dev.c b/net/core/dev.c index 00f970ba0248..d9ce02e95992 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3878,6 +3878,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { @@ -4960,6 +4961,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, qdisc_skb_cb(skb)->pkt_len = skb->len; qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2d70ded389ae..c565c7a17091 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -237,9 +237,8 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, - u16 *ctinfo_map, - size_t mapsize) + void *target_container, u16 *ctinfo_map, + size_t mapsize, bool post_ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; @@ -251,13 +250,19 @@ skb_flow_dissect_ct(const struct sk_buff *skb, return; ct = nf_ct_get(skb, &ctinfo); - if (!ct) + if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); + if (!ct) { + key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID; + return; + } + if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 83a5c6722a06..b3442078aabc 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1030,6 +1030,7 @@ out_push: out: tcf_action_update_bstats(&c->common, skb); + qdisc_skb_cb(skb)->post_ct = true; if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 84f932532db7..4a9297a89c77 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -302,6 +302,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_fl_head *head = rcu_dereference_bh(tp->root); + bool post_ct = qdisc_skb_cb(skb)->post_ct; struct fl_flow_key skb_key; struct fl_flow_mask *mask; struct cls_fl_filter *f; @@ -318,7 +319,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, - ARRAY_SIZE(fl_ct_info_to_flower_map)); + ARRAY_SIZE(fl_ct_info_to_flower_map), + post_ct); skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); -- cgit v1.2.3 From bfb3939c51d51c0de794da14f33c13e36d2e4f3d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:05 +0100 Subject: i2c: refactor documentation of struct i2c_msg The information about 'i2c_msg' was spread between kdoc and comments. Move all the explanations to kdoc and duplicate only the requirements for the flags in the comments. Also, add some redundancy and fix some typos while here. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 91 +++++++++++++++++++++++++++++------------------- 1 file changed, 55 insertions(+), 36 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index f71a1751cacf..8d2f59f53324 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -32,18 +32,41 @@ /** * struct i2c_msg - an I2C transaction segment beginning with START - * @addr: Slave address, either seven or ten bits. When this is a ten - * bit address, I2C_M_TEN must be set in @flags and the adapter - * must support I2C_FUNC_10BIT_ADDR. - * @flags: I2C_M_RD is handled by all adapters. No other flags may be - * provided unless the adapter exported the relevant I2C_FUNC_* - * flags through i2c_check_functionality(). - * @len: Number of data bytes in @buf being read from or written to the - * I2C slave address. For read transactions where I2C_M_RECV_LEN - * is set, the caller guarantees that this buffer can hold up to - * 32 bytes in addition to the initial length byte sent by the - * slave (plus, if used, the SMBus PEC); and this value will be - * incremented by the number of block data bytes received. + * + * @addr: Slave address, either 7 or 10 bits. When this is a 10 bit address, + * %I2C_M_TEN must be set in @flags and the adapter must support + * %I2C_FUNC_10BIT_ADDR. + * + * @flags: + * Supported by all adapters: + * %I2C_M_RD: read data (from slave to master). Guaranteed to be 0x0001! + * + * Optional: + * %I2C_M_DMA_SAFE: the buffer of this message is DMA safe. Makes only sense + * in kernelspace, because userspace buffers are copied anyway + * + * Only if I2C_FUNC_10BIT_ADDR is set: + * %I2C_M_TEN: this is a 10 bit chip address + * + * Only if I2C_FUNC_SMBUS_READ_BLOCK_DATA is set: + * %I2C_M_RECV_LEN: message length will be first received byte + * + * Only if I2C_FUNC_NOSTART is set: + * %I2C_M_NOSTART: skip repeated start sequence + + * Only if I2C_FUNC_PROTOCOL_MANGLING is set: + * %I2C_M_NO_RD_ACK: in a read message, master ACK/NACK bit is skipped + * %I2C_M_IGNORE_NAK: treat NACK from client as ACK + * %I2C_M_REV_DIR_ADDR: toggles the Rd/Wr bit + * %I2C_M_STOP: force a STOP condition after the message + * + * @len: Number of data bytes in @buf being read from or written to the I2C + * slave address. For read transactions where %I2C_M_RECV_LEN is set, the + * caller guarantees that this buffer can hold up to %I2C_SMBUS_BLOCK_MAX + * bytes in addition to the initial length byte sent by the slave (plus, + * if used, the SMBus PEC); and this value will be incremented by the number + * of block data bytes received. + * * @buf: The buffer into which data is read, or from which it's written. * * An i2c_msg is the low level representation of one segment of an I2C @@ -60,40 +83,36 @@ * group, it is followed by a STOP. Otherwise it is followed by the next * @i2c_msg transaction segment, beginning with a (repeated) START. * - * Alternatively, when the adapter supports I2C_FUNC_PROTOCOL_MANGLING then + * Alternatively, when the adapter supports %I2C_FUNC_PROTOCOL_MANGLING then * passing certain @flags may have changed those standard protocol behaviors. * Those flags are only for use with broken/nonconforming slaves, and with - * adapters which are known to support the specific mangling options they - * need (one or more of IGNORE_NAK, NO_RD_ACK, NOSTART, and REV_DIR_ADDR). + * adapters which are known to support the specific mangling options they need. */ struct i2c_msg { - __u16 addr; /* slave address */ + __u16 addr; __u16 flags; -#define I2C_M_RD 0x0001 /* read data, from slave to master */ - /* I2C_M_RD is guaranteed to be 0x0001! */ -#define I2C_M_TEN 0x0010 /* this is a ten bit chip address */ -#define I2C_M_DMA_SAFE 0x0200 /* the buffer of this message is DMA safe */ - /* makes only sense in kernelspace */ - /* userspace buffers are copied anyway */ -#define I2C_M_RECV_LEN 0x0400 /* length will be first received byte */ -#define I2C_M_NO_RD_ACK 0x0800 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_IGNORE_NAK 0x1000 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_REV_DIR_ADDR 0x2000 /* if I2C_FUNC_PROTOCOL_MANGLING */ -#define I2C_M_NOSTART 0x4000 /* if I2C_FUNC_NOSTART */ -#define I2C_M_STOP 0x8000 /* if I2C_FUNC_PROTOCOL_MANGLING */ - __u16 len; /* msg length */ - __u8 *buf; /* pointer to msg data */ +#define I2C_M_RD 0x0001 /* guaranteed to be 0x0001! */ +#define I2C_M_TEN 0x0010 /* use only if I2C_FUNC_10BIT_ADDR */ +#define I2C_M_DMA_SAFE 0x0200 /* use only in kernel space */ +#define I2C_M_RECV_LEN 0x0400 /* use only if I2C_FUNC_SMBUS_READ_BLOCK_DATA */ +#define I2C_M_NO_RD_ACK 0x0800 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_IGNORE_NAK 0x1000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_REV_DIR_ADDR 0x2000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_NOSTART 0x4000 /* use only if I2C_FUNC_NOSTART */ +#define I2C_M_STOP 0x8000 /* use only if I2C_FUNC_PROTOCOL_MANGLING */ + __u16 len; + __u8 *buf; }; /* To determine what functionality is present */ #define I2C_FUNC_I2C 0x00000001 -#define I2C_FUNC_10BIT_ADDR 0x00000002 -#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* I2C_M_IGNORE_NAK etc. */ +#define I2C_FUNC_10BIT_ADDR 0x00000002 /* required for I2C_M_TEN */ +#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* required for I2C_M_IGNORE_NAK etc. */ #define I2C_FUNC_SMBUS_PEC 0x00000008 -#define I2C_FUNC_NOSTART 0x00000010 /* I2C_M_NOSTART */ +#define I2C_FUNC_NOSTART 0x00000010 /* required for I2C_M_NOSTART */ #define I2C_FUNC_SLAVE 0x00000020 -#define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 */ +#define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 or later */ #define I2C_FUNC_SMBUS_QUICK 0x00010000 #define I2C_FUNC_SMBUS_READ_BYTE 0x00020000 #define I2C_FUNC_SMBUS_WRITE_BYTE 0x00040000 @@ -102,11 +121,11 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_WORD_DATA 0x00200000 #define I2C_FUNC_SMBUS_WRITE_WORD_DATA 0x00400000 #define I2C_FUNC_SMBUS_PROC_CALL 0x00800000 -#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 +#define I2C_FUNC_SMBUS_READ_BLOCK_DATA 0x01000000 /* required for I2C_M_RECV_LEN */ #define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ -#define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 +#define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) -- cgit v1.2.3 From deb0d3351b0cb7233206317ca1774bda312de28e Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:06 +0100 Subject: i2c: remove licence boilerplate from main UAPI header Remove boilerplate because we now have the SPDX header. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 8d2f59f53324..7786551eb177 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -1,29 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* ------------------------------------------------------------------------- */ -/* */ -/* i2c.h - definitions for the i2c-bus interface */ -/* */ -/* ------------------------------------------------------------------------- */ -/* Copyright (C) 1995-2000 Simon G. Vogl - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - MA 02110-1301 USA. */ -/* ------------------------------------------------------------------------- */ - -/* With some changes from Kyösti Mälkki and - Frodo Looijaard */ +/* + * i2c.h - definitions for the I2C bus interface + * + * Copyright (C) 1995-2000 Simon G. Vogl + * With some changes from Kyösti Mälkki and + * Frodo Looijaard + */ #ifndef _UAPI_LINUX_I2C_H #define _UAPI_LINUX_I2C_H -- cgit v1.2.3 From 1713d66cae8acdf3d34bafe09598fec9d1fb4793 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:07 +0100 Subject: i2c: remove licence boilerplate from i2c-dev UAPI header Remove boilerplate because we now have the SPDX header. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c-dev.h | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 85f8047afcf2..1c4cec4ddd84 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -1,25 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* - i2c-dev.h - i2c-bus driver, char device interface - - Copyright (C) 1995-97 Simon G. Vogl - Copyright (C) 1998-99 Frodo Looijaard - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - MA 02110-1301 USA. -*/ + * i2c-dev.h - I2C bus char device interface + * + * Copyright (C) 1995-97 Simon G. Vogl + * Copyright (C) 1998-99 Frodo Looijaard + */ #ifndef _UAPI_LINUX_I2C_DEV_H #define _UAPI_LINUX_I2C_DEV_H -- cgit v1.2.3 From 21500aa84024b3fc541197b2041d80538539740d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Jan 2021 13:43:09 +0100 Subject: i2c: uapi: add macro to describe support for all SMBus transfers Some I2C bus master drivers which support I2C_M_RECV_LEN do not set the functionality bits of the now supported SMBus transfers. Add a convenience macro to make this very simple. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 7786551eb177..92326ebde350 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -129,6 +129,11 @@ struct i2c_msg { I2C_FUNC_SMBUS_I2C_BLOCK | \ I2C_FUNC_SMBUS_PEC) +/* if I2C_M_RECV_LEN is also supported */ +#define I2C_FUNC_SMBUS_EMUL_ALL (I2C_FUNC_SMBUS_EMUL | \ + I2C_FUNC_SMBUS_READ_BLOCK_DATA | \ + I2C_FUNC_SMBUS_BLOCK_PROC_CALL) + /* * Data for SMBus Messages */ -- cgit v1.2.3 From b8288837ef6bdaac331752b401f5ca3b59b37430 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:13 -0800 Subject: devlink: Introduce PCI SF port flavour and port attribute A PCI sub-function (SF) represents a portion of the device similar to PCI VF. In an eswitch, PCI SF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with SF, and its representor netdevice, introduce a PCI SF port flavour. When devlink port flavour is PCI SF, fill up PCI SF attributes of the port. Extend port name creation using PCI PF and SF number scheme on best effort basis, so that vendor drivers can skip defining their own scheme. This is done as cApfNSfM, where A, N and M are controller, PCI PF and PCI SF number respectively. This is similar to existing naming for PCI PF and PCI VF ports. An example view of a PCI SF port: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state active opstate attached $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/net/devlink.h | 16 ++++++++++++++++ include/uapi/linux/devlink.h | 5 +++++ net/core/devlink.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 60 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index f466819cc477..dc3bf8000082 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -93,6 +93,18 @@ struct devlink_port_pci_vf_attrs { u8 external:1; }; +/** + * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes + * @controller: Associated controller number + * @sf: Associated PCI SF for of the PCI PF for this port. + * @pf: Associated PCI PF number for this port. + */ +struct devlink_port_pci_sf_attrs { + u32 controller; + u32 sf; + u16 pf; +}; + /** * struct devlink_port_attrs - devlink port object * @flavour: flavour of the port @@ -103,6 +115,7 @@ struct devlink_port_pci_vf_attrs { * @phys: physical port attributes * @pci_pf: PCI PF port attributes * @pci_vf: PCI VF port attributes + * @pci_sf: PCI SF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -114,6 +127,7 @@ struct devlink_port_attrs { struct devlink_port_phys_attrs phys; struct devlink_port_pci_pf_attrs pci_pf; struct devlink_port_pci_vf_attrs pci_vf; + struct devlink_port_pci_sf_attrs pci_sf; }; }; @@ -1404,6 +1418,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro u16 pf, bool external); void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external); +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, + u32 controller, u16 pf, u32 sf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cf89c318f2ac..1a241b09a7f8 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -200,6 +200,10 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but * is not used in any way. */ + DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port + * for the PCI SF. It is an internal + * port that faces the PCI SF. + */ }; enum devlink_param_cmode { @@ -529,6 +533,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ + DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index c39496311b71..4cbc02fb602d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -690,6 +690,15 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -8374,6 +8383,32 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + if (WARN_ON(devlink_port->registered)) + return; + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8422,6 +8457,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; } if (n >= len) -- cgit v1.2.3 From a556dded9c23c51c82654f1ebe389cbc0bc22057 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:15 -0800 Subject: devlink: Support get and set state of port function devlink port function can be in active or inactive state. Allow users to get and set port function's state. When the port function it activated, its operational state may change after a while when the device is created and driver binds to it. Similarly on deactivation flow. To clearly describe the state of the port function and its device's operational state in the host system, define state and opstate attributes. Example of a PCI SF port which supports a port function: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 state active $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/net/devlink.h | 32 ++++++++++++++++ include/uapi/linux/devlink.h | 20 ++++++++++ net/core/devlink.c | 90 +++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 141 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index d8edd9a10907..691ee76ca548 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1414,6 +1414,38 @@ struct devlink_ops { */ int (*port_del)(struct devlink *devlink, unsigned int port_index, struct netlink_ext_ack *extack); + /** + * port_fn_state_get() - Get the state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin configured state + * @opstate: Current operational state + * @extack: extack for reporting error messages + * + * Reports the admin and operational state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_get)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack); + /** + * port_fn_state_set() - Set the admin state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin state + * @extack: extack for reporting error messages + * + * Set the admin state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_set)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1a241b09a7f8..f6008b2fa60f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -583,9 +583,29 @@ enum devlink_resource_unit { enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ + DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 }; +enum devlink_port_fn_state { + DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE, +}; + +/** + * enum devlink_port_fn_opstate - indicates operational state of the function + * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function. + * For graceful tear down of the function, after inactivation of the + * function, user should wait for operational state to turn DETACHED. + * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function. + * It is safe to delete the port. + */ +enum devlink_port_fn_opstate { + DEVLINK_PORT_FN_OPSTATE_DETACHED, + DEVLINK_PORT_FN_OPSTATE_ATTACHED, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 541b5f549274..9f1be69bd5f8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -87,6 +87,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), }; static LIST_HEAD(devlink_list); @@ -746,6 +749,58 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * return 0; } +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int +devlink_port_fn_state_fill(struct devlink *devlink, + const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -763,6 +818,11 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por ops = devlink->ops; err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, + &msg_updated); +out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else @@ -1028,6 +1088,24 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); } +static int devlink_port_fn_state_set(struct devlink *devlink, + struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(devlink, port, state, extack); +} + static int devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) @@ -1043,8 +1121,18 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, } attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) + if (attr) { err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(devlink, port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); -- cgit v1.2.3 From e7ed11ee945438b737e2ae2370e35591e16ec371 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Wed, 20 Jan 2021 12:41:55 -0800 Subject: tcp: add TTL to SCM_TIMESTAMPING_OPT_STATS This patch adds TCP_NLA_TTL to SCM_TIMESTAMPING_OPT_STATS that exports the time-to-live or hop limit of the latest incoming packet with SCM_TSTAMP_ACK. The value exported may not be from the packet that acks the sequence when incoming packets are aggregated. Exporting the time-to-live or hop limit value of incoming packets helps to estimate the hop count of the path of the flow that may change over time. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Link: https://lore.kernel.org/r/20210120204155.552275-1-ysseung@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/linux/tcp.h | 3 ++- include/uapi/linux/tcp.h | 1 + net/core/dev.c | 2 +- net/core/skbuff.c | 6 ++++-- net/ipv4/tcp.c | 18 +++++++++++++++++- net/ipv4/tcp_input.c | 16 ++++++++-------- 7 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 186dad231e30..9313b5aaf45b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3859,7 +3859,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); -void __skb_tstamp_tx(struct sk_buff *orig_skb, +void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2f87377e9af7..48d8a363319e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -496,7 +496,8 @@ static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, - const struct sk_buff *orig_skb); + const struct sk_buff *orig_skb, + const struct sk_buff *ack_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 768e93bd5b51..16dfa40bdac3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -314,6 +314,7 @@ enum { TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ + TCP_NLA_TTL, /* TTL or hop limit of a packet received */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/core/dev.c b/net/core/dev.c index d9ce02e95992..6df3f1bcdc68 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4084,7 +4084,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_reset_mac_header(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) - __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); + __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 145503d3f06b..2af12f7e170c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4721,6 +4721,7 @@ err: EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, + const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { @@ -4743,7 +4744,8 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - skb = tcp_get_timestamping_opt_stats(sk, orig_skb); + skb = tcp_get_timestamping_opt_stats(sk, orig_skb, + ack_skb); opt_stats = true; } else #endif @@ -4772,7 +4774,7 @@ EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { - return __skb_tstamp_tx(orig_skb, hwtstamps, orig_skb->sk, + return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 856ae516ac18..a1a17b64f8cd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3767,11 +3767,24 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ + nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ 0; } +/* Returns TTL or hop limit of an incoming packet from skb. */ +static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP)) + return ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + return ipv6_hdr(skb)->hop_limit; + else + return 0; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, - const struct sk_buff *orig_skb) + const struct sk_buff *orig_skb, + const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; @@ -3827,6 +3840,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); + if (ack_skb) + nla_put_u8(stats, TCP_NLA_TTL, + tcp_skb_ttl_or_hop_limit(ack_skb)); return stats; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a7dfca0a38cd..d4f66aba9fd8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3145,7 +3145,7 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) } static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, - u32 prior_snd_una) + const struct sk_buff *ack_skb, u32 prior_snd_una) { const struct skb_shared_info *shinfo; @@ -3157,7 +3157,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, if (!before(shinfo->tskey, prior_snd_una) && before(shinfo->tskey, tcp_sk(sk)->snd_una)) { tcp_skb_tsorted_save(skb) { - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + __skb_tstamp_tx(skb, ack_skb, NULL, sk, SCM_TSTAMP_ACK); } tcp_skb_tsorted_restore(skb); } } @@ -3166,8 +3166,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, * is before the ack sequence we can discard it as it's confirmed to have * arrived at the other end. */ -static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, - u32 prior_snd_una, +static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, + u32 prior_fack, u32 prior_snd_una, struct tcp_sacktag_state *sack, bool ece_ack) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -3256,7 +3256,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (!fully_acked) break; - tcp_ack_tstamp(sk, skb, prior_snd_una); + tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una); next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) @@ -3274,7 +3274,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->snd_up = tp->snd_una; if (skb) { - tcp_ack_tstamp(sk, skb, prior_snd_una); + tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una); if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) flag |= FLAG_SACK_RENEGING; } @@ -3809,8 +3809,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) goto no_queue; /* See if we can take anything off of the retransmit queue. */ - flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state, - flag & FLAG_ECE); + flag |= tcp_clean_rtx_queue(sk, skb, prior_fack, prior_snd_una, + &sack_state, flag & FLAG_ECE); tcp_rack_update_reo_wnd(sk, &rs); -- cgit v1.2.3 From 7eeba1706eba6def15f6cb2fc7b3c3b9a2651edc Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 20 Jan 2021 16:41:48 -0800 Subject: tcp: Add receive timestamp support for receive zerocopy. tcp_recvmsg() uses the CMSG mechanism to receive control information like packet receive timestamps. This patch adds CMSG fields to struct tcp_zerocopy_receive, and provides receive timestamps if available to the user. Signed-off-by: Arjun Roy Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 4 ++ net/ipv4/tcp.c | 116 ++++++++++++++++++++++++++++++++++------------- 2 files changed, 88 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 16dfa40bdac3..42fc5a640df4 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -354,5 +354,9 @@ struct tcp_zerocopy_receive { __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ __u32 flags; /* in: flags */ + __u64 msg_control; /* ancillary data */ + __u64 msg_controllen; + __u32 msg_flags; + /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7ba0bd0675cb..e1a17c6b473c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1745,6 +1745,20 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_set_rcvlowat); +static void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss) +{ + if (skb->tstamp) + tss->ts[0] = ktime_to_timespec64(skb->tstamp); + else + tss->ts[0] = (struct timespec64) {0}; + + if (skb_hwtstamps(skb)->hwtstamp) + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); + else + tss->ts[2] = (struct timespec64) {0}; +} + #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; @@ -1848,13 +1862,13 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, - struct tcp_zerocopy_receive *zc, int inq) + struct tcp_zerocopy_receive *zc, int inq, + struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; - struct scm_timestamping_internal tss_unused; - int err, cmsg_flags_unused; struct msghdr msg = {}; struct iovec iov; + int err; zc->length = 0; zc->recv_skip_hint = 0; @@ -1868,7 +1882,7 @@ static int receive_fallback_to_copy(struct sock *sk, return err; err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0, - &tss_unused, &cmsg_flags_unused); + tss, &zc->msg_flags); if (err < 0) return err; @@ -1909,21 +1923,27 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, return (__s32)copylen; } -static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, - struct sock *sk, - struct sk_buff *skb, - u32 *seq, - s32 copybuf_len) +static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, + struct sock *sk, + struct sk_buff *skb, + u32 *seq, + s32 copybuf_len, + struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ - if (skb) + if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; - else + } else { skb = tcp_recv_skb(sk, *seq, &offset); + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } + } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); @@ -2010,9 +2030,37 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, err); } +static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); +static void tcp_zc_finalize_rx_tstamp(struct sock *sk, + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) +{ + unsigned long msg_control_addr; + struct msghdr cmsg_dummy; + + msg_control_addr = (unsigned long)zc->msg_control; + cmsg_dummy.msg_control = (void *)msg_control_addr; + cmsg_dummy.msg_controllen = + (__kernel_size_t)zc->msg_controllen; + cmsg_dummy.msg_flags = in_compat_syscall() + ? MSG_CMSG_COMPAT : 0; + zc->msg_flags = 0; + if (zc->msg_control == msg_control_addr && + zc->msg_controllen == cmsg_dummy.msg_controllen) { + tcp_recv_timestamp(&cmsg_dummy, sk, tss); + zc->msg_control = (__u64) + ((uintptr_t)cmsg_dummy.msg_control); + zc->msg_controllen = + (__u64)cmsg_dummy.msg_controllen; + zc->msg_flags = (__u32)cmsg_dummy.msg_flags; + } +} + #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, - struct tcp_zerocopy_receive *zc) + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; @@ -2029,6 +2077,7 @@ static int tcp_zerocopy_receive(struct sock *sk, int ret; zc->copybuf_len = 0; + zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; @@ -2039,7 +2088,7 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) - return receive_fallback_to_copy(sk, zc, inq); + return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; @@ -2084,6 +2133,11 @@ static int tcp_zerocopy_receive(struct sock *sk, } else { skb = tcp_recv_skb(sk, seq, &offset); } + + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) @@ -2126,8 +2180,7 @@ out: mmap_read_unlock(current->mm); /* Try to copy straggler data. */ if (!ret) - copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq, - copybuf_len); + copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); @@ -2148,20 +2201,6 @@ out: } #endif -static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping_internal *tss) -{ - if (skb->tstamp) - tss->ts[0] = ktime_to_timespec64(skb->tstamp); - else - tss->ts[0] = (struct timespec64) {0}; - - if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); - else - tss->ts[2] = (struct timespec64) {0}; -} - /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) @@ -4105,6 +4144,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { + struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; @@ -4120,11 +4160,18 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); - err = tcp_zerocopy_receive(sk, &zc); + err = tcp_zerocopy_receive(sk, &zc, &tss); release_sock(sk); - if (len >= offsetofend(struct tcp_zerocopy_receive, err)) - goto zerocopy_rcv_sk_err; + if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) + goto zerocopy_rcv_cmsg; switch (len) { + case offsetofend(struct tcp_zerocopy_receive, msg_flags): + goto zerocopy_rcv_cmsg; + case offsetofend(struct tcp_zerocopy_receive, msg_controllen): + case offsetofend(struct tcp_zerocopy_receive, msg_control): + case offsetofend(struct tcp_zerocopy_receive, flags): + case offsetofend(struct tcp_zerocopy_receive, copybuf_len): + case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): @@ -4133,6 +4180,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, default: goto zerocopy_rcv_out; } +zerocopy_rcv_cmsg: + if (zc.msg_flags & TCP_CMSG_TS) + tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); + else + zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); -- cgit v1.2.3 From d03b195b5aa015f6c11988b86a3625f8d5dbac52 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:13 +0200 Subject: sch_htb: Hierarchical QoS hardware offload HTB doesn't scale well because of contention on a single lock, and it also consumes CPU. This patch adds support for offloading HTB to hardware that supports hierarchical rate limiting. In the offload mode, HTB passes control commands to the driver using ndo_setup_tc. The driver has to replicate the whole hierarchy of classes and their settings (rate, ceil) in the NIC. Every modification of the HTB tree caused by the admin results in ndo_setup_tc being called. After this setup, the HTB algorithm is done completely in the NIC. An SQ (send queue) is created for every leaf class and attached to the hierarchy, so that the NIC can calculate and obey aggregated rate limits, too. In the future, it can be changed, so that multiple SQs will back a single leaf class. ndo_select_queue is responsible for selecting the right queue that serves the traffic class of each packet. The data path works as follows: a packet is classified by clsact, the driver selects a hardware queue according to its class, and the packet is enqueued into this queue's qdisc. This solution addresses two main problems of scaling HTB: 1. Contention by flow classification. Currently the filters are attached to the HTB instance as follows: # tc filter add dev eth0 parent 1:0 protocol ip flower dst_port 80 classid 1:10 It's possible to move classification to clsact egress hook, which is thread-safe and lock-free: # tc filter add dev eth0 egress protocol ip flower dst_port 80 action skbedit priority 1:10 This way classification still happens in software, but the lock contention is eliminated, and it happens before selecting the TX queue, allowing the driver to translate the class to the corresponding hardware queue in ndo_select_queue. Note that this is already compatible with non-offloaded HTB and doesn't require changes to the kernel nor iproute2. 2. Contention by handling packets. HTB is not multi-queue, it attaches to a whole net device, and handling of all packets takes the same lock. When HTB is offloaded, it registers itself as a multi-queue qdisc, similarly to mq: HTB is attached to the netdev, and each queue has its own qdisc. Some features of HTB may be not supported by some particular hardware, for example, the maximum number of classes may be limited, the granularity of rate and ceil parameters may be different, etc. - so, the offload is not enabled by default, a new parameter is used to enable it: # tc qdisc replace dev eth0 root handle 1: htb offload Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + include/net/pkt_cls.h | 36 +++ include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_htb.c | 501 +++++++++++++++++++++++++++++++++-- tools/include/uapi/linux/pkt_sched.h | 1 + 5 files changed, 512 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..9e8572533d8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -858,6 +858,7 @@ enum tc_setup_type { TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, + TC_SETUP_QDISC_HTB, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 0f2a9c44171c..255e4f4b521f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -783,6 +783,42 @@ struct tc_mq_qopt_offload { }; }; +enum tc_htb_command { + /* Root */ + TC_HTB_CREATE, /* Initialize HTB offload. */ + TC_HTB_DESTROY, /* Destroy HTB offload. */ + + /* Classes */ + /* Allocate qid and create leaf. */ + TC_HTB_LEAF_ALLOC_QUEUE, + /* Convert leaf to inner, preserve and return qid, create new leaf. */ + TC_HTB_LEAF_TO_INNER, + /* Delete leaf, while siblings remain. */ + TC_HTB_LEAF_DEL, + /* Delete leaf, convert parent to leaf, preserving qid. */ + TC_HTB_LEAF_DEL_LAST, + /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */ + TC_HTB_LEAF_DEL_LAST_FORCE, + /* Modify parameters of a node. */ + TC_HTB_NODE_MODIFY, + + /* Class qdisc */ + TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */ +}; + +struct tc_htb_qopt_offload { + struct netlink_ext_ack *extack; + enum tc_htb_command command; + u16 classid; + u32 parent_classid; + u16 qid; + u16 moved_qid; + u64 rate; + u64 ceil; +}; + +#define TC_HTB_CLASSID_ROOT U32_MAX + enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 9e7c2c607845..79a699f106b1 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -434,6 +434,7 @@ enum { TCA_HTB_RATE64, TCA_HTB_CEIL64, TCA_HTB_PAD, + TCA_HTB_OFFLOAD, __TCA_HTB_MAX, }; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index a8fc97b05bd8..d1b60fe3d311 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -174,6 +174,11 @@ struct htb_sched { int row_mask[TC_HTB_MAXDEPTH]; struct htb_level hlevel[TC_HTB_MAXDEPTH]; + + struct Qdisc **direct_qdiscs; + unsigned int num_direct_qdiscs; + + bool offload; }; /* find class in global hash table using given handle */ @@ -957,7 +962,7 @@ static void htb_reset(struct Qdisc *sch) if (cl->level) memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->leaf.q) + if (cl->leaf.q && !q->offload) qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; @@ -980,6 +985,7 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = { [TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 }, [TCA_HTB_RATE64] = { .type = NLA_U64 }, [TCA_HTB_CEIL64] = { .type = NLA_U64 }, + [TCA_HTB_OFFLOAD] = { .type = NLA_FLAG }, }; static void htb_work_func(struct work_struct *work) @@ -992,12 +998,27 @@ static void htb_work_func(struct work_struct *work) rcu_read_unlock(); } +static void htb_set_lockdep_class_child(struct Qdisc *q) +{ + static struct lock_class_key child_key; + + lockdep_set_class(qdisc_lock(q), &child_key); +} + +static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt) +{ + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt); +} + static int htb_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; + unsigned int ntx; int err; qdisc_watchdog_init(&q->watchdog, sch); @@ -1022,9 +1043,26 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (gopt->version != HTB_VER >> 16) return -EINVAL; + q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); + + if (q->offload) { + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + q->num_direct_qdiscs = dev->real_num_tx_queues; + q->direct_qdiscs = kcalloc(q->num_direct_qdiscs, + sizeof(*q->direct_qdiscs), + GFP_KERNEL); + if (!q->direct_qdiscs) + return -ENOMEM; + } + err = qdisc_class_hash_init(&q->clhash); if (err < 0) - return err; + goto err_free_direct_qdiscs; qdisc_skb_head_init(&q->direct_queue); @@ -1037,7 +1075,107 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, q->rate2quantum = 1; q->defcls = gopt->defcls; + if (!q->offload) + return 0; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *qdisc; + + qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, 0), extack); + if (!qdisc) { + err = -ENOMEM; + goto err_free_qdiscs; + } + + htb_set_lockdep_class_child(qdisc); + q->direct_qdiscs[ntx] = qdisc; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + } + + sch->flags |= TCQ_F_MQROOT; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_CREATE, + .parent_classid = TC_H_MAJ(sch->handle) >> 16, + .classid = TC_H_MIN(q->defcls), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + goto err_free_qdiscs; + return 0; + +err_free_qdiscs: + /* TC_HTB_CREATE call failed, avoid any further calls to the driver. */ + q->offload = false; + + for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx]; + ntx++) + qdisc_put(q->direct_qdiscs[ntx]); + + qdisc_class_hash_destroy(&q->clhash); + /* Prevent use-after-free and double-free when htb_destroy gets called. + */ + q->clhash.hash = NULL; + q->clhash.hashsize = 0; + +err_free_direct_qdiscs: + kfree(q->direct_qdiscs); + q->direct_qdiscs = NULL; + return err; +} + +static void htb_attach_offload(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct htb_sched *q = qdisc_priv(sch); + unsigned int ntx; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct Qdisc *old, *qdisc = q->direct_qdiscs[ntx]; + + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + qdisc_put(old); + qdisc_hash_add(qdisc, false); + } + for (ntx = q->num_direct_qdiscs; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, NULL); + + qdisc_put(old); + } + + kfree(q->direct_qdiscs); + q->direct_qdiscs = NULL; +} + +static void htb_attach_software(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Resemble qdisc_graft behavior. */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, sch); + + qdisc_refcount_inc(sch); + + qdisc_put(old); + } +} + +static void htb_attach(struct Qdisc *sch) +{ + struct htb_sched *q = qdisc_priv(sch); + + if (q->offload) + htb_attach_offload(sch); + else + htb_attach_software(sch); } static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -1046,6 +1184,11 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nest; struct tc_htb_glob gopt; + if (q->offload) + sch->flags |= TCQ_F_OFFLOADED; + else + sch->flags &= ~TCQ_F_OFFLOADED; + sch->qstats.overlimits = q->overlimits; /* Its safe to not acquire qdisc lock. As we hold RTNL, * no change can happen on the qdisc parameters. @@ -1063,6 +1206,8 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; + if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD)) + goto nla_put_failure; return nla_nest_end(skb, nest); @@ -1144,19 +1289,97 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); } +static struct netdev_queue * +htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; + int err; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_QUERY_QUEUE, + .classid = TC_H_MIN(tcm->tcm_parent), + }; + err = htb_offload(dev, &offload_opt); + if (err || offload_opt.qid >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, offload_opt.qid); +} + +static struct Qdisc * +htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q) +{ + struct net_device *dev = dev_queue->dev; + struct Qdisc *old_q; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + old_q = dev_graft_qdisc(dev_queue, new_q); + if (new_q) + new_q->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + if (dev->flags & IFF_UP) + dev_activate(dev); + + return old_q; +} + +static void htb_offload_move_qdisc(struct Qdisc *sch, u16 qid_old, u16 qid_new) +{ + struct netdev_queue *queue_old, *queue_new; + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + + queue_old = netdev_get_tx_queue(dev, qid_old); + queue_new = netdev_get_tx_queue(dev, qid_new); + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + qdisc = dev_graft_qdisc(queue_old, NULL); + qdisc->dev_queue = queue_new; + qdisc = dev_graft_qdisc(queue_new, qdisc); + if (dev->flags & IFF_UP) + dev_activate(dev); + + WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); +} + static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { + struct netdev_queue *dev_queue = sch->dev_queue; struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); + struct Qdisc *old_q; if (cl->level) return -EINVAL; - if (new == NULL && - (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack)) == NULL) - return -ENOBUFS; + + if (q->offload) { + dev_queue = new->dev_queue; + WARN_ON(dev_queue != cl->leaf.q->dev_queue); + } + + if (!new) { + new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + cl->common.classid, extack); + if (!new) + return -ENOBUFS; + } + + if (q->offload) { + htb_set_lockdep_class_child(new); + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + qdisc_refcount_inc(new); + old_q = htb_graft_helper(dev_queue, new); + } *old = qdisc_replace(sch, new, &cl->leaf.q); + + if (q->offload) { + WARN_ON(old_q != *old); + qdisc_put(old_q); + } + return 0; } @@ -1184,9 +1407,10 @@ static inline int htb_parent_last_child(struct htb_class *cl) return 1; } -static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, +static void htb_parent_to_leaf(struct Qdisc *sch, struct htb_class *cl, struct Qdisc *new_q) { + struct htb_sched *q = qdisc_priv(sch); struct htb_class *parent = cl->parent; WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); @@ -1204,6 +1428,71 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, parent->cmode = HTB_CAN_SEND; } +static void htb_parent_to_leaf_offload(struct Qdisc *sch, + struct netdev_queue *dev_queue, + struct Qdisc *new_q) +{ + struct Qdisc *old_q; + + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + qdisc_refcount_inc(new_q); + old_q = htb_graft_helper(dev_queue, new_q); + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); +} + +static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, + bool last_child, bool destroying, + struct netlink_ext_ack *extack) +{ + struct tc_htb_qopt_offload offload_opt; + struct Qdisc *q = cl->leaf.q; + struct Qdisc *old = NULL; + int err; + + if (cl->level) + return -EINVAL; + + WARN_ON(!q); + if (!destroying) { + /* On destroy of HTB, two cases are possible: + * 1. q is a normal qdisc, but q->dev_queue has noop qdisc. + * 2. q is a noop qdisc (for nodes that were inner), + * q->dev_queue is noop_netdev_queue. + */ + old = htb_graft_helper(q->dev_queue, NULL); + WARN_ON(!old); + WARN_ON(old != q); + } + + offload_opt = (struct tc_htb_qopt_offload) { + .command = !last_child ? TC_HTB_LEAF_DEL : + destroying ? TC_HTB_LEAF_DEL_LAST_FORCE : + TC_HTB_LEAF_DEL_LAST, + .classid = cl->common.classid, + .extack = extack, + }; + err = htb_offload(qdisc_dev(sch), &offload_opt); + + if (!err || destroying) + qdisc_put(old); + else + htb_graft_helper(q->dev_queue, old); + + if (last_child) + return err; + + if (!err && offload_opt.moved_qid != 0) { + if (destroying) + q->dev_queue = netdev_get_tx_queue(qdisc_dev(sch), + offload_opt.qid); + else + htb_offload_move_qdisc(sch, offload_opt.moved_qid, + offload_opt.qid); + } + + return err; +} + static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { @@ -1217,8 +1506,11 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) static void htb_destroy(struct Qdisc *sch) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct hlist_node *next; + bool nonempty, changed; struct htb_class *cl; unsigned int i; @@ -1237,13 +1529,58 @@ static void htb_destroy(struct Qdisc *sch) cl->block = NULL; } } - for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], - common.hnode) - htb_destroy_class(sch, cl); - } + + do { + nonempty = false; + changed = false; + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], + common.hnode) { + bool last_child; + + if (!q->offload) { + htb_destroy_class(sch, cl); + continue; + } + + nonempty = true; + + if (cl->level) + continue; + + changed = true; + + last_child = htb_parent_last_child(cl); + htb_destroy_class_offload(sch, cl, last_child, + true, NULL); + qdisc_class_hash_remove(&q->clhash, + &cl->common); + if (cl->parent) + cl->parent->children--; + if (last_child) + htb_parent_to_leaf(sch, cl, NULL); + htb_destroy_class(sch, cl); + } + } + } while (changed); + WARN_ON(nonempty); + qdisc_class_hash_destroy(&q->clhash); __qdisc_reset_queue(&q->direct_queue); + + if (!q->offload) + return; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_DESTROY, + }; + htb_offload(dev, &offload_opt); + + if (!q->direct_qdiscs) + return; + for (i = 0; i < q->num_direct_qdiscs && q->direct_qdiscs[i]; i++) + qdisc_put(q->direct_qdiscs[i]); + kfree(q->direct_qdiscs); } static int htb_delete(struct Qdisc *sch, unsigned long arg, @@ -1253,6 +1590,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, struct htb_class *cl = (struct htb_class *)arg; struct Qdisc *new_q = NULL; int last_child = 0; + int err; /* TODO: why don't allow to delete subtree ? references ? does * tc subsys guarantee us that in htb_destroy it holds no class @@ -1261,11 +1599,28 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, if (cl->children || cl->filter_cnt) return -EBUSY; - if (!cl->level && htb_parent_last_child(cl)) { - new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + if (!cl->level && htb_parent_last_child(cl)) + last_child = 1; + + if (q->offload) { + err = htb_destroy_class_offload(sch, cl, last_child, false, + extack); + if (err) + return err; + } + + if (last_child) { + struct netdev_queue *dev_queue; + + dev_queue = q->offload ? cl->leaf.q->dev_queue : sch->dev_queue; + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid, NULL); - last_child = 1; + if (q->offload) { + if (new_q) + htb_set_lockdep_class_child(new_q); + htb_parent_to_leaf_offload(sch, dev_queue, new_q); + } } sch_tree_lock(sch); @@ -1286,7 +1641,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, &q->hlevel[cl->level].wait_pq); if (last_child) - htb_parent_to_leaf(q, cl, new_q); + htb_parent_to_leaf(sch, cl, new_q); sch_tree_unlock(sch); @@ -1301,9 +1656,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, int err = -EINVAL; struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; + struct tc_htb_qopt_offload offload_opt; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; struct Qdisc *parent_qdisc = NULL; + struct netdev_queue *dev_queue; struct tc_htb_opt *hopt; u64 rate64, ceil64; int warn = 0; @@ -1336,8 +1693,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB], NULL)); + rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + if (!cl) { /* new class */ - struct Qdisc *new_q; + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *new_q, *old_q; int prio; struct { struct nlattr nla; @@ -1380,11 +1741,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); - if (err) { - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } + if (err) + goto err_block_put; } cl->children = 0; @@ -1393,12 +1751,74 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, for (prio = 0; prio < TC_HTB_NUMPRIO; prio++) RB_CLEAR_NODE(&cl->node[prio]); + cl->common.classid = classid; + + /* Make sure nothing interrupts us in between of two + * ndo_setup_tc calls. + */ + ASSERT_RTNL(); + /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) * so that can't be used inside of sch_tree_lock * -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + if (!q->offload) { + dev_queue = sch->dev_queue; + } else if (!(parent && !parent->level)) { + /* Assign a dev_queue to this classid. */ + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_ALLOC_QUEUE, + .classid = cl->common.classid, + .parent_classid = parent ? + TC_H_MIN(parent->common.classid) : + TC_HTB_CLASSID_ROOT, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + pr_err("htb: TC_HTB_LEAF_ALLOC_QUEUE failed with err = %d\n", + err); + goto err_kill_estimator; + } + dev_queue = netdev_get_tx_queue(dev, offload_opt.qid); + } else { /* First child. */ + dev_queue = parent->leaf.q->dev_queue; + old_q = htb_graft_helper(dev_queue, NULL); + WARN_ON(old_q != parent->leaf.q); + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_TO_INNER, + .classid = cl->common.classid, + .parent_classid = + TC_H_MIN(parent->common.classid), + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + pr_err("htb: TC_HTB_LEAF_TO_INNER failed with err = %d\n", + err); + htb_graft_helper(dev_queue, old_q); + goto err_kill_estimator; + } + qdisc_put(old_q); + } + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, classid, NULL); + if (q->offload) { + if (new_q) { + htb_set_lockdep_class_child(new_q); + /* One ref for cl->leaf.q, the other for + * dev_queue->qdisc. + */ + qdisc_refcount_inc(new_q); + } + old_q = htb_graft_helper(dev_queue, new_q); + /* No qdisc_put needed. */ + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); + } sch_tree_lock(sch); if (parent && !parent->level) { /* turn parent into inner node */ @@ -1416,10 +1836,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, : TC_HTB_MAXDEPTH) - 1; memset(&parent->inner, 0, sizeof(parent->inner)); } + /* leaf (we) needs elementary qdisc */ cl->leaf.q = new_q ? new_q : &noop_qdisc; - cl->common.classid = classid; cl->parent = parent; /* set class to be in HTB_CAN_SEND state */ @@ -1445,12 +1865,30 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (err) return err; } - sch_tree_lock(sch); - } - rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + if (q->offload) { + struct net_device *dev = qdisc_dev(sch); + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_NODE_MODIFY, + .classid = cl->common.classid, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + /* Estimator was replaced, and rollback may fail + * as well, so we don't try to recover it, and + * the estimator won't work property with the + * offload anyway, because bstats are updated + * only when the stats are queried. + */ + return err; + } - ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + sch_tree_lock(sch); + } psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64); psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); @@ -1493,6 +1931,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, *arg = (unsigned long)cl; return 0; +err_kill_estimator: + gen_kill_estimator(&cl->rate_est); +err_block_put: + tcf_block_put(cl->block); + kfree(cl); failure: return err; } @@ -1558,6 +2001,7 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) } static const struct Qdisc_class_ops htb_class_ops = { + .select_queue = htb_select_queue, .graft = htb_graft, .leaf = htb_leaf, .qlen_notify = htb_qlen_notify, @@ -1580,6 +2024,7 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = { .dequeue = htb_dequeue, .peek = qdisc_peek_dequeued, .init = htb_init, + .attach = htb_attach, .reset = htb_reset, .destroy = htb_destroy, .dump = htb_dump, diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h index 0d18b1d1fbbc..5c903abc9fa5 100644 --- a/tools/include/uapi/linux/pkt_sched.h +++ b/tools/include/uapi/linux/pkt_sched.h @@ -414,6 +414,7 @@ enum { TCA_HTB_RATE64, TCA_HTB_CEIL64, TCA_HTB_PAD, + TCA_HTB_OFFLOAD, __TCA_HTB_MAX, }; -- cgit v1.2.3 From dc090de854b9d7fdbc6f4df70bd7fc1b43eeccf8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 21 Jan 2021 21:40:36 +0100 Subject: net: mrp: fix definitions of MRP test packets Wireshark says that the MRP test packets cannot be decoded - and the reason for that is that there's a two-byte hole filled with garbage between the "transitions" and "timestamp" members. So Wireshark decodes the two garbage bytes and the top two bytes of the timestamp written by the kernel as the timestamp value (which thus fluctuates wildly), and interprets the lower two bytes of the timestamp as a new (type, length) pair, which is of course broken. Even though this makes the timestamp field in the struct unaligned, it actually makes it end up on a 32 bit boundary in the frame as mandated by the standard, since it is preceded by a two byte TLV header. The struct definitions live under include/uapi/, but they are not really part of any kernel<->userspace API/ABI, so fixing the definitions by adding the packed attribute should not cause any compatibility issues. Signed-off-by: Rasmus Villemoes Reviewed-by: Horatiu Vultur Signed-off-by: Jakub Kicinski --- include/uapi/linux/mrp_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 9744773de5ff..5ce771327e32 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -97,7 +97,7 @@ struct br_mrp_ring_test_hdr { __be16 state; __be16 transitions; __be32 timestamp; -}; +} __attribute__((__packed__)); struct br_mrp_ring_topo_hdr { __be16 prio; @@ -142,7 +142,7 @@ struct br_mrp_in_test_hdr { __be16 state; __be16 transitions; __be32 timestamp; -}; +} __attribute__((__packed__)); struct br_mrp_in_topo_hdr { __u8 sa[ETH_ALEN]; -- cgit v1.2.3 From 6781939054a1a161e06e7a7955a4846be770a711 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 21 Jan 2021 21:40:37 +0100 Subject: net: mrp: move struct definitions out of uapi None of these are actually used in the kernel/userspace interface - there's a userspace component of implementing MRP, and userspace will need to construct certain frames to put on the wire, but there's no reason the kernel should provide the relevant definitions in a UAPI header. In fact, some of those definitions were broken until previous commit, so only keep the few that are actually referenced in the kernel code, and move them to the br_private_mrp.h header. Signed-off-by: Rasmus Villemoes Signed-off-by: Jakub Kicinski --- include/uapi/linux/mrp_bridge.h | 86 ----------------------------------------- net/bridge/br_private_mrp.h | 29 ++++++++++++++ 2 files changed, 29 insertions(+), 86 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 5ce771327e32..bd4424de56ff 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -71,90 +71,4 @@ enum br_mrp_sub_tlv_header_type { BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR = 0x3, }; -struct br_mrp_tlv_hdr { - __u8 type; - __u8 length; -}; - -struct br_mrp_sub_tlv_hdr { - __u8 type; - __u8 length; -}; - -struct br_mrp_end_hdr { - struct br_mrp_tlv_hdr hdr; -}; - -struct br_mrp_common_hdr { - __be16 seq_id; - __u8 domain[MRP_DOMAIN_UUID_LENGTH]; -}; - -struct br_mrp_ring_test_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 state; - __be16 transitions; - __be32 timestamp; -} __attribute__((__packed__)); - -struct br_mrp_ring_topo_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 interval; -}; - -struct br_mrp_ring_link_hdr { - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 interval; - __be16 blocked; -}; - -struct br_mrp_sub_opt_hdr { - __u8 type; - __u8 manufacture_data[MRP_MANUFACTURE_DATA_LENGTH]; -}; - -struct br_mrp_test_mgr_nack_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 other_prio; - __u8 other_sa[ETH_ALEN]; -}; - -struct br_mrp_test_prop_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 other_prio; - __u8 other_sa[ETH_ALEN]; -}; - -struct br_mrp_oui_hdr { - __u8 oui[MRP_OUI_LENGTH]; -}; - -struct br_mrp_in_test_hdr { - __be16 id; - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 state; - __be16 transitions; - __be32 timestamp; -} __attribute__((__packed__)); - -struct br_mrp_in_topo_hdr { - __u8 sa[ETH_ALEN]; - __be16 id; - __be16 interval; -}; - -struct br_mrp_in_link_hdr { - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 id; - __be16 interval; -}; - #endif diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 1883118aae55..32a48e5418da 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -88,4 +88,33 @@ int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, int br_mrp_ring_port_open(struct net_device *dev, u8 loc); int br_mrp_in_port_open(struct net_device *dev, u8 loc); +/* MRP protocol data units */ +struct br_mrp_tlv_hdr { + __u8 type; + __u8 length; +}; + +struct br_mrp_common_hdr { + __be16 seq_id; + __u8 domain[MRP_DOMAIN_UUID_LENGTH]; +}; + +struct br_mrp_ring_test_hdr { + __be16 prio; + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; +} __attribute__((__packed__)); + +struct br_mrp_in_test_hdr { + __be16 id; + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; +} __attribute__((__packed__)); + #endif /* _BR_PRIVATE_MRP_H */ -- cgit v1.2.3 From 2a1867219c7b27f928e2545782b86daaf9ad50bd Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:53 +0100 Subject: fs: add mount_setattr() This implements the missing mount_setattr() syscall. While the new mount api allows to change the properties of a superblock there is currently no way to change the properties of a mount or a mount tree using file descriptors which the new mount api is based on. In addition the old mount api has the restriction that mount options cannot be applied recursively. This hasn't changed since changing mount options on a per-mount basis was implemented in [1] and has been a frequent request not just for convenience but also for security reasons. The legacy mount syscall is unable to accommodate this behavior without introducing a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND | MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost mount. Changing MS_REC to apply to the whole mount tree would mean introducing a significant uapi change and would likely cause significant regressions. The new mount_setattr() syscall allows to recursively clear and set mount options in one shot. Multiple calls to change mount options requesting the same changes are idempotent: int mount_setattr(int dfd, const char *path, unsigned flags, struct mount_attr *uattr, size_t usize); Flags to modify path resolution behavior are specified in the @flags argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW, and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to restrict path resolution as introduced with openat2() might be supported in the future. The mount_setattr() syscall can be expected to grow over time and is designed with extensibility in mind. It follows the extensible syscall pattern we have used with other syscalls such as openat2(), clone3(), sched_{set,get}attr(), and others. The set of mount options is passed in the uapi struct mount_attr which currently has the following layout: struct mount_attr { __u64 attr_set; __u64 attr_clr; __u64 propagation; __u64 userns_fd; }; The @attr_set and @attr_clr members are used to clear and set mount options. This way a user can e.g. request that a set of flags is to be raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in @attr_set while at the same time requesting that another set of flags is to be lowered such as removing noexec from a mount tree by specifying MOUNT_ATTR_NOEXEC in @attr_clr. Note, since the MOUNT_ATTR_ values are an enum starting from 0, not a bitmap, users wanting to transition to a different atime setting cannot simply specify the atime setting in @attr_set, but must also specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in @attr_clr. The @propagation field lets callers specify the propagation type of a mount tree. Propagation is a single property that has four different settings and as such is not really a flag argument but an enum. Specifically, it would be unclear what setting and clearing propagation settings in combination would amount to. The legacy mount() syscall thus forbids the combination of multiple propagation settings too. The goal is to keep the semantics of mount propagation somewhat simple as they are overly complex as it is. The @userns_fd field lets user specify a user namespace whose idmapping becomes the idmapping of the mount. This is implemented and explained in detail in the next patch. [1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount") Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com Cc: David Howells Cc: Aleksa Sarai Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + fs/namespace.c | 263 ++++++++++++++++++++++++++++ include/linux/syscalls.h | 4 + include/uapi/asm-generic/unistd.h | 4 +- include/uapi/linux/mount.h | 15 ++ tools/include/uapi/asm-generic/unistd.h | 4 +- 23 files changed, 307 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a6617067dbe6..02f0244e005c 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -481,3 +481,4 @@ 549 common faccessat2 sys_faccessat2 550 common process_madvise sys_process_madvise 551 common epoll_pwait2 sys_epoll_pwait2 +552 common mount_setattr sys_mount_setattr diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 20e1170e2e0a..dcc1191291a2 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -455,3 +455,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 86a9d7b3eabe..949788f5ba40 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 442 +#define __NR_compat_syscalls 443 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index cccfbbefbf95..3d874f624056 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -891,6 +891,8 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index bfc00f2bd437..d89231166e19 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -362,3 +362,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7fe4e45c864c..72bde6707dd3 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -441,3 +441,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a522adf194ab..d603a5ec9338 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 0f03ad223f33..8fd8c1790941 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -380,3 +380,4 @@ 439 n32 faccessat2 sys_faccessat2 440 n32 process_madvise sys_process_madvise 441 n32 epoll_pwait2 compat_sys_epoll_pwait2 +442 n32 mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 91649690b52f..169f21438065 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -356,3 +356,4 @@ 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 +442 n64 mount_setattr sys_mount_setattr diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 4bad0c40aed6..090d29ca80ff 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -429,3 +429,4 @@ 439 o32 faccessat2 sys_faccessat2 440 o32 process_madvise sys_process_madvise 441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 o32 mount_setattr sys_mount_setattr diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 6bcc31966b44..271a92519683 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -439,3 +439,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index f744eb5cba88..72e5aa67ab8a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -531,3 +531,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index d443423495e5..3abef2144dac 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr sys_mount_setattr diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 9df40ac0ebc0..d08eebad6b7f 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -444,3 +444,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 40d8c7cd8298..84403a99039c 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -487,3 +487,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 874aeacde2dd..a1c9f496fca6 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -446,3 +446,4 @@ 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise 441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 i386 mount_setattr sys_mount_setattr diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 78672124d28b..7bf01cbe582f 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 46116a28eeed..365a9b849224 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -412,3 +412,4 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr diff --git a/fs/namespace.c b/fs/namespace.c index 00ed0d6cb2ee..726a51c8c46e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -73,6 +73,14 @@ static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ +struct mount_kattr { + unsigned int attr_set; + unsigned int attr_clr; + unsigned int propagation; + unsigned int lookup_flags; + bool recurse; +}; + /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); @@ -3469,6 +3477,11 @@ out_type: (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) +#define MOUNT_SETATTR_VALID_FLAGS FSMOUNT_VALID_FLAGS + +#define MOUNT_SETATTR_PROPAGATION_FLAGS \ + (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) + static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; @@ -3820,6 +3833,256 @@ out0: return error; } +static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) +{ + unsigned int flags = mnt->mnt.mnt_flags; + + /* flags to clear */ + flags &= ~kattr->attr_clr; + /* flags to raise */ + flags |= kattr->attr_set; + + return flags; +} + +static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, + struct mount *mnt, int *err) +{ + struct mount *m = mnt, *last = NULL; + + if (!is_mounted(&m->mnt)) { + *err = -EINVAL; + goto out; + } + + if (!(mnt_has_parent(m) ? check_mnt(m) : is_anon_ns(m->mnt_ns))) { + *err = -EINVAL; + goto out; + } + + do { + unsigned int flags; + + flags = recalc_flags(kattr, m); + if (!can_change_locked_flags(m, flags)) { + *err = -EPERM; + goto out; + } + + last = m; + + if ((kattr->attr_set & MNT_READONLY) && + !(m->mnt.mnt_flags & MNT_READONLY)) { + *err = mnt_hold_writers(m); + if (*err) + goto out; + } + } while (kattr->recurse && (m = next_mnt(m, mnt))); + +out: + return last; +} + +static void mount_setattr_commit(struct mount_kattr *kattr, + struct mount *mnt, struct mount *last, + int err) +{ + struct mount *m = mnt; + + do { + if (!err) { + unsigned int flags; + + flags = recalc_flags(kattr, m); + WRITE_ONCE(m->mnt.mnt_flags, flags); + } + + /* + * We either set MNT_READONLY above so make it visible + * before ~MNT_WRITE_HOLD or we failed to recursively + * apply mount options. + */ + if ((kattr->attr_set & MNT_READONLY) && + (m->mnt.mnt_flags & MNT_WRITE_HOLD)) + mnt_unhold_writers(m); + + if (!err && kattr->propagation) + change_mnt_propagation(m, kattr->propagation); + + /* + * On failure, only cleanup until we found the first mount + * we failed to handle. + */ + if (err && m == last) + break; + } while (kattr->recurse && (m = next_mnt(m, mnt))); + + if (!err) + touch_mnt_namespace(mnt->mnt_ns); +} + +static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) +{ + struct mount *mnt = real_mount(path->mnt), *last = NULL; + int err = 0; + + if (path->dentry != mnt->mnt.mnt_root) + return -EINVAL; + + if (kattr->propagation) { + /* + * Only take namespace_lock() if we're actually changing + * propagation. + */ + namespace_lock(); + if (kattr->propagation == MS_SHARED) { + err = invent_group_ids(mnt, kattr->recurse); + if (err) { + namespace_unlock(); + return err; + } + } + } + + lock_mount_hash(); + + /* + * Get the mount tree in a shape where we can change mount + * properties without failure. + */ + last = mount_setattr_prepare(kattr, mnt, &err); + if (last) /* Commit all changes or revert to the old state. */ + mount_setattr_commit(kattr, mnt, last, err); + + unlock_mount_hash(); + + if (kattr->propagation) { + namespace_unlock(); + if (err) + cleanup_group_ids(mnt, NULL); + } + + return err; +} + +static int build_mount_kattr(const struct mount_attr *attr, + struct mount_kattr *kattr, unsigned int flags) +{ + unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; + + if (flags & AT_NO_AUTOMOUNT) + lookup_flags &= ~LOOKUP_AUTOMOUNT; + if (flags & AT_SYMLINK_NOFOLLOW) + lookup_flags &= ~LOOKUP_FOLLOW; + if (flags & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + + *kattr = (struct mount_kattr) { + .lookup_flags = lookup_flags, + .recurse = !!(flags & AT_RECURSIVE), + }; + + if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) + return -EINVAL; + if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) + return -EINVAL; + kattr->propagation = attr->propagation; + + if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) + return -EINVAL; + + if (attr->userns_fd) + return -EINVAL; + + kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); + kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); + + /* + * Since the MOUNT_ATTR_ values are an enum, not a bitmap, + * users wanting to transition to a different atime setting cannot + * simply specify the atime setting in @attr_set, but must also + * specify MOUNT_ATTR__ATIME in the @attr_clr field. + * So ensure that MOUNT_ATTR__ATIME can't be partially set in + * @attr_clr and that @attr_set can't have any atime bits set if + * MOUNT_ATTR__ATIME isn't set in @attr_clr. + */ + if (attr->attr_clr & MOUNT_ATTR__ATIME) { + if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) + return -EINVAL; + + /* + * Clear all previous time settings as they are mutually + * exclusive. + */ + kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; + switch (attr->attr_set & MOUNT_ATTR__ATIME) { + case MOUNT_ATTR_RELATIME: + kattr->attr_set |= MNT_RELATIME; + break; + case MOUNT_ATTR_NOATIME: + kattr->attr_set |= MNT_NOATIME; + break; + case MOUNT_ATTR_STRICTATIME: + break; + default: + return -EINVAL; + } + } else { + if (attr->attr_set & MOUNT_ATTR__ATIME) + return -EINVAL; + } + + return 0; +} + +SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, + unsigned int, flags, struct mount_attr __user *, uattr, + size_t, usize) +{ + int err; + struct path target; + struct mount_attr attr; + struct mount_kattr kattr; + + BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); + + if (flags & ~(AT_EMPTY_PATH | + AT_RECURSIVE | + AT_SYMLINK_NOFOLLOW | + AT_NO_AUTOMOUNT)) + return -EINVAL; + + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; + if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) + return -EINVAL; + + if (!may_mount()) + return -EPERM; + + err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); + if (err) + return err; + + /* Don't bother walking through the mounts if this is a nop. */ + if (attr.attr_set == 0 && + attr.attr_clr == 0 && + attr.propagation == 0) + return 0; + + err = build_mount_kattr(&attr, &kattr, flags); + if (err) + return err; + + err = user_path_at(dfd, path, kattr.lookup_flags, &target); + if (err) + return err; + + err = do_mount_setattr(&target, &kattr); + path_put(&target); + return err; +} + static void __init init_mount_tree(void) { struct vfsmount *mnt; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7688bc983de5..cd7b5c817ba2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -68,6 +68,7 @@ union bpf_attr; struct io_uring_params; struct clone_args; struct open_how; +struct mount_attr; #include #include @@ -1028,6 +1029,9 @@ asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags); asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path, int to_dfd, const char __user *to_path, unsigned int ms_flags); +asmlinkage long sys_mount_setattr(int dfd, const char __user *path, + unsigned int flags, + struct mount_attr __user *uattr, size_t usize); asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags); asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key, const void __user *value, int aux); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 728752917785..ce58cff99b66 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -861,9 +861,11 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) #undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 443 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index dd8306ea336c..d3bcefdfa73d 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -1,6 +1,8 @@ #ifndef _UAPI_LINUX_MOUNT_H #define _UAPI_LINUX_MOUNT_H +#include + /* * These are the fs-independent mount-flags: up to 32 flags are supported * @@ -118,4 +120,17 @@ enum fsconfig_command { #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +/* + * mount_setattr() + */ +struct mount_attr { + __u64 attr_set; + __u64 attr_clr; + __u64 propagation; + __u64 userns_fd; +}; + +/* List of all mount_attr versions. */ +#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 728752917785..ce58cff99b66 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -861,9 +861,11 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) #undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 443 /* * 32 bit systems traditionally used different -- cgit v1.2.3 From 9caccd41541a6f7d6279928d9f971f6642c361af Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:54 +0100 Subject: fs: introduce MOUNT_ATTR_IDMAP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new mount bind mount property to allow idmapping mounts. The MOUNT_ATTR_IDMAP flag can be set via the new mount_setattr() syscall together with a file descriptor referring to a user namespace. The user namespace referenced by the namespace file descriptor will be attached to the bind mount. All interactions with the filesystem going through that mount will be mapped according to the mapping specified in the user namespace attached to it. Using user namespaces to mark mounts means we can reuse all the existing infrastructure in the kernel that already exists to handle idmappings and can also use this for permission checking to allow unprivileged user to create idmapped mounts in the future. Idmapping a mount is decoupled from the caller's user and mount namespace. This means idmapped mounts can be created in the initial user namespace which is an important use-case for systemd-homed, portable usb-sticks between systems, sharing data between the initial user namespace and unprivileged containers, and other use-cases that have been brought up. For example, assume a home directory where all files are owned by uid and gid 1000 and the home directory is brought to a new laptop where the user has id 12345. The system administrator can simply create a mount of this home directory with a mapping of 1000:12345:1 and other mappings to indicate the ids should be kept. (With this it is e.g. also possible to create idmapped mounts on the host with an identity mapping 1:1:100000 where the root user is not mapped. A user with root access that e.g. has been pivot rooted into such a mount on the host will be not be able to execute, read, write, or create files as root.) Given that mapping a mount is decoupled from the caller's user namespace a sufficiently privileged process such as a container manager can set up an idmapped mount for the container and the container can simply pivot root to it. There's no need for the container to do anything. The mount will appear correctly mapped independent of the user namespace the container uses. This means we don't need to mark a mount as idmappable. In order to create an idmapped mount the caller must currently be privileged in the user namespace of the superblock the mount belongs to. Once a mount has been idmapped we don't allow it to change its mapping. This keeps permission checking and life-cycle management simple. Users wanting to change the idmapped can always create a new detached mount with a different idmapping. Link: https://lore.kernel.org/r/20210121131959.646623-36-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Mauricio Vásquez Bernal Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/namespace.c | 122 ++++++++++++++++++++++++++++++++++++++++++--- fs/proc_namespace.c | 3 ++ include/linux/mount.h | 3 +- include/uapi/linux/mount.h | 1 + 4 files changed, 121 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 726a51c8c46e..062fe984a697 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -79,6 +80,7 @@ struct mount_kattr { unsigned int propagation; unsigned int lookup_flags; bool recurse; + struct user_namespace *mnt_userns; }; /* /sys/fs */ @@ -3477,7 +3479,7 @@ out_type: (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) -#define MOUNT_SETATTR_VALID_FLAGS FSMOUNT_VALID_FLAGS +#define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) @@ -3845,6 +3847,36 @@ static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) return flags; } +static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct vfsmount *m = &mnt->mnt; + + if (!kattr->mnt_userns) + return 0; + + /* + * Once a mount has been idmapped we don't allow it to change its + * mapping. It makes things simpler and callers can just create + * another bind-mount they can idmap if they want to. + */ + if (mnt_user_ns(m) != &init_user_ns) + return -EPERM; + + /* The underlying filesystem doesn't support idmapped mounts yet. */ + if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) + return -EINVAL; + + /* We're not controlling the superblock. */ + if (!ns_capable(m->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Mount has already been visible in the filesystem hierarchy. */ + if (!is_anon_ns(mnt->mnt_ns)) + return -EINVAL; + + return 0; +} + static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt, int *err) { @@ -3869,6 +3901,10 @@ static struct mount *mount_setattr_prepare(struct mount_kattr *kattr, goto out; } + *err = can_idmap_mount(kattr, m); + if (*err) + goto out; + last = m; if ((kattr->attr_set & MNT_READONLY) && @@ -3883,6 +3919,18 @@ out: return last; } +static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) +{ + struct user_namespace *mnt_userns; + + if (!kattr->mnt_userns) + return; + + mnt_userns = get_user_ns(kattr->mnt_userns); + /* Pairs with smp_load_acquire() in mnt_user_ns(). */ + smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); +} + static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt, struct mount *last, int err) @@ -3893,6 +3941,7 @@ static void mount_setattr_commit(struct mount_kattr *kattr, if (!err) { unsigned int flags; + do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); } @@ -3965,7 +4014,62 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) return err; } -static int build_mount_kattr(const struct mount_attr *attr, +static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, + struct mount_kattr *kattr, unsigned int flags) +{ + int err = 0; + struct ns_common *ns; + struct user_namespace *mnt_userns; + struct file *file; + + if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) + return 0; + + /* + * We currently do not support clearing an idmapped mount. If this ever + * is a use-case we can revisit this but for now let's keep it simple + * and not allow it. + */ + if (attr->attr_clr & MOUNT_ATTR_IDMAP) + return -EINVAL; + + if (attr->userns_fd > INT_MAX) + return -EINVAL; + + file = fget(attr->userns_fd); + if (!file) + return -EBADF; + + if (!proc_ns_file(file)) { + err = -EINVAL; + goto out_fput; + } + + ns = get_proc_ns(file_inode(file)); + if (ns->ops->type != CLONE_NEWUSER) { + err = -EINVAL; + goto out_fput; + } + + /* + * The init_user_ns is used to indicate that a vfsmount is not idmapped. + * This is simpler than just having to treat NULL as unmapped. Users + * wanting to idmap a mount to init_user_ns can just use a namespace + * with an identity mapping. + */ + mnt_userns = container_of(ns, struct user_namespace, ns); + if (mnt_userns == &init_user_ns) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); + +out_fput: + fput(file); + return err; +} + +static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; @@ -3991,9 +4095,6 @@ static int build_mount_kattr(const struct mount_attr *attr, if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; - if (attr->userns_fd) - return -EINVAL; - kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); @@ -4032,7 +4133,13 @@ static int build_mount_kattr(const struct mount_attr *attr, return -EINVAL; } - return 0; + return build_mount_idmapped(attr, usize, kattr, flags); +} + +static void finish_mount_kattr(struct mount_kattr *kattr) +{ + put_user_ns(kattr->mnt_userns); + kattr->mnt_userns = NULL; } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, @@ -4070,7 +4177,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, attr.propagation == 0) return 0; - err = build_mount_kattr(&attr, &kattr, flags); + err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; @@ -4079,6 +4186,7 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, return err; err = do_mount_setattr(&target, &kattr); + finish_mount_kattr(&kattr); path_put(&target); return err; } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index eafb75755fa3..392ef5162655 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -79,6 +79,9 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) if (mnt->mnt_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } + + if (mnt_user_ns(mnt) != &init_user_ns) + seq_puts(m, ",idmapped"); } static inline void mangle(struct seq_file *m, const char *s) diff --git a/include/linux/mount.h b/include/linux/mount.h index 52de25e08319..161f4419db6c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -77,7 +77,8 @@ struct vfsmount { static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) { - return mnt->mnt_userns; + /* Pairs with smp_store_release() in do_idmap_mount(). */ + return smp_load_acquire(&mnt->mnt_userns); } struct file; /* forward dec */ diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index d3bcefdfa73d..e6524ead2b7b 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -119,6 +119,7 @@ enum fsconfig_command { #define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ /* * mount_setattr() -- cgit v1.2.3 From 9cde9360d18d8b352b737d10f90f2aecccf93dbe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 20 Oct 2020 15:48:22 -0400 Subject: NFSD: Update the SETATTR3args decoder to use struct xdr_stream Signed-off-by: Chuck Lever --- fs/nfsd/nfs3xdr.c | 138 ++++++++++++++++++++++++++++++++++++++++------ include/uapi/linux/nfs3.h | 6 ++ 2 files changed, 127 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 9437dda2646f..6a6bf8e34d82 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -39,12 +39,18 @@ encode_time3(__be32 *p, struct timespec64 *time) return p; } -static __be32 * -decode_time3(__be32 *p, struct timespec64 *time) +static bool +svcxdr_decode_nfstime3(struct xdr_stream *xdr, struct timespec64 *timep) { - time->tv_sec = ntohl(*p++); - time->tv_nsec = ntohl(*p++); - return p; + __be32 *p; + + p = xdr_inline_decode(xdr, XDR_UNIT * 2); + if (!p) + return false; + timep->tv_sec = be32_to_cpup(p++); + timep->tv_nsec = be32_to_cpup(p); + + return true; } static bool @@ -150,6 +156,112 @@ svcxdr_decode_diropargs3(struct xdr_stream *xdr, struct svc_fh *fhp, svcxdr_decode_filename3(xdr, name, len); } +static bool +svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct iattr *iap) +{ + u32 set_it; + + iap->ia_valid = 0; + + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 mode; + + if (xdr_stream_decode_u32(xdr, &mode) < 0) + return false; + iap->ia_valid |= ATTR_MODE; + iap->ia_mode = mode; + } + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 uid; + + if (xdr_stream_decode_u32(xdr, &uid) < 0) + return false; + iap->ia_uid = make_kuid(nfsd_user_namespace(rqstp), uid); + if (uid_valid(iap->ia_uid)) + iap->ia_valid |= ATTR_UID; + } + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 gid; + + if (xdr_stream_decode_u32(xdr, &gid) < 0) + return false; + iap->ia_gid = make_kgid(nfsd_user_namespace(rqstp), gid); + if (gid_valid(iap->ia_gid)) + iap->ia_valid |= ATTR_GID; + } + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u64 newsize; + + if (xdr_stream_decode_u64(xdr, &newsize) < 0) + return false; + iap->ia_valid |= ATTR_SIZE; + iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX); + } + if (xdr_stream_decode_u32(xdr, &set_it) < 0) + return false; + switch (set_it) { + case DONT_CHANGE: + break; + case SET_TO_SERVER_TIME: + iap->ia_valid |= ATTR_ATIME; + break; + case SET_TO_CLIENT_TIME: + if (!svcxdr_decode_nfstime3(xdr, &iap->ia_atime)) + return false; + iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; + break; + default: + return false; + } + if (xdr_stream_decode_u32(xdr, &set_it) < 0) + return false; + switch (set_it) { + case DONT_CHANGE: + break; + case SET_TO_SERVER_TIME: + iap->ia_valid |= ATTR_MTIME; + break; + case SET_TO_CLIENT_TIME: + if (!svcxdr_decode_nfstime3(xdr, &iap->ia_mtime)) + return false; + iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; + break; + default: + return false; + } + + return true; +} + +static bool +svcxdr_decode_sattrguard3(struct xdr_stream *xdr, struct nfsd3_sattrargs *args) +{ + __be32 *p; + u32 check; + + if (xdr_stream_decode_bool(xdr, &check) < 0) + return false; + if (check) { + p = xdr_inline_decode(xdr, XDR_UNIT * 2); + if (!p) + return false; + args->check_guard = 1; + args->guardtime = be32_to_cpup(p); + } else + args->check_guard = 0; + + return true; +} + static __be32 * decode_sattr3(__be32 *p, struct iattr *iap, struct user_namespace *userns) { @@ -377,20 +489,12 @@ nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_sattrargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - - if ((args->check_guard = ntohl(*p++)) != 0) { - struct timespec64 time; - p = decode_time3(p, &time); - args->guardtime = time.tv_sec; - } - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_nfs_fh3(xdr, &args->fh) && + svcxdr_decode_sattr3(rqstp, xdr, &args->attrs) && + svcxdr_decode_sattrguard3(xdr, args); } int diff --git a/include/uapi/linux/nfs3.h b/include/uapi/linux/nfs3.h index 37e4b34e6b43..c22ab77713bd 100644 --- a/include/uapi/linux/nfs3.h +++ b/include/uapi/linux/nfs3.h @@ -63,6 +63,12 @@ enum nfs3_ftype { NF3BAD = 8 }; +enum nfs3_time_how { + DONT_CHANGE = 0, + SET_TO_SERVER_TIME = 1, + SET_TO_CLIENT_TIME = 2, +}; + struct nfs3_fh { unsigned short size; unsigned char data[NFS3_FHSIZE]; -- cgit v1.2.3 From 882227626459ce7a24191f13c6d9749a00992059 Mon Sep 17 00:00:00 2001 From: Scott Branden Date: Wed, 20 Jan 2021 09:58:15 -0800 Subject: bcm-vk: add bcm_vk UAPI Add user space api for bcm-vk driver. Provide ioctl api to load images and issue reset command to card. FW status registers in PCI BAR space also defined as part of API so that user space is able to interpret these memory locations as needed via direct PCIe access. Acked-by: Olof Johansson Signed-off-by: Scott Branden Link: https://lore.kernel.org/r/20210120175827.14820-2-scott.branden@broadcom.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/misc/bcm_vk.h | 84 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/uapi/linux/misc/bcm_vk.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/misc/bcm_vk.h b/include/uapi/linux/misc/bcm_vk.h new file mode 100644 index 000000000000..ec28e0bd46a9 --- /dev/null +++ b/include/uapi/linux/misc/bcm_vk.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2018-2020 Broadcom. + */ + +#ifndef __UAPI_LINUX_MISC_BCM_VK_H +#define __UAPI_LINUX_MISC_BCM_VK_H + +#include +#include + +#define BCM_VK_MAX_FILENAME 64 + +struct vk_image { + __u32 type; /* Type of image */ +#define VK_IMAGE_TYPE_BOOT1 1 /* 1st stage (load to SRAM) */ +#define VK_IMAGE_TYPE_BOOT2 2 /* 2nd stage (load to DDR) */ + __u8 filename[BCM_VK_MAX_FILENAME]; /* Filename of image */ +}; + +struct vk_reset { + __u32 arg1; + __u32 arg2; +}; + +#define VK_MAGIC 0x5e + +/* Load image to Valkyrie */ +#define VK_IOCTL_LOAD_IMAGE _IOW(VK_MAGIC, 0x2, struct vk_image) + +/* Send Reset to Valkyrie */ +#define VK_IOCTL_RESET _IOW(VK_MAGIC, 0x4, struct vk_reset) + +/* + * Firmware Status accessed directly via BAR space + */ +#define VK_BAR_FWSTS 0x41c +#define VK_BAR_COP_FWSTS 0x428 +/* VK_FWSTS definitions */ +#define VK_FWSTS_RELOCATION_ENTRY (1UL << 0) +#define VK_FWSTS_RELOCATION_EXIT (1UL << 1) +#define VK_FWSTS_INIT_START (1UL << 2) +#define VK_FWSTS_ARCH_INIT_DONE (1UL << 3) +#define VK_FWSTS_PRE_KNL1_INIT_DONE (1UL << 4) +#define VK_FWSTS_PRE_KNL2_INIT_DONE (1UL << 5) +#define VK_FWSTS_POST_KNL_INIT_DONE (1UL << 6) +#define VK_FWSTS_INIT_DONE (1UL << 7) +#define VK_FWSTS_APP_INIT_START (1UL << 8) +#define VK_FWSTS_APP_INIT_DONE (1UL << 9) +#define VK_FWSTS_MASK 0xffffffff +#define VK_FWSTS_READY (VK_FWSTS_INIT_START | \ + VK_FWSTS_ARCH_INIT_DONE | \ + VK_FWSTS_PRE_KNL1_INIT_DONE | \ + VK_FWSTS_PRE_KNL2_INIT_DONE | \ + VK_FWSTS_POST_KNL_INIT_DONE | \ + VK_FWSTS_INIT_DONE | \ + VK_FWSTS_APP_INIT_START | \ + VK_FWSTS_APP_INIT_DONE) +/* Deinit */ +#define VK_FWSTS_APP_DEINIT_START (1UL << 23) +#define VK_FWSTS_APP_DEINIT_DONE (1UL << 24) +#define VK_FWSTS_DRV_DEINIT_START (1UL << 25) +#define VK_FWSTS_DRV_DEINIT_DONE (1UL << 26) +#define VK_FWSTS_RESET_DONE (1UL << 27) +#define VK_FWSTS_DEINIT_TRIGGERED (VK_FWSTS_APP_DEINIT_START | \ + VK_FWSTS_APP_DEINIT_DONE | \ + VK_FWSTS_DRV_DEINIT_START | \ + VK_FWSTS_DRV_DEINIT_DONE) +/* Last nibble for reboot reason */ +#define VK_FWSTS_RESET_REASON_SHIFT 28 +#define VK_FWSTS_RESET_REASON_MASK (0xf << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_SYS_PWRUP (0x0 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_MBOX_DB (0x1 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_M7_WDOG (0x2 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_TEMP (0x3 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_FLR (0x4 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_HOT (0x5 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_WARM (0x6 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_PCI_COLD (0x7 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_L1 (0x8 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_L0 (0x9 << VK_FWSTS_RESET_REASON_SHIFT) +#define VK_FWSTS_RESET_UNKNOWN (0xf << VK_FWSTS_RESET_REASON_SHIFT) + +#endif /* __UAPI_LINUX_MISC_BCM_VK_H */ -- cgit v1.2.3 From 07d46d93c9acdfe0614071d73c415dd5f745cc6e Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Thu, 21 Jan 2021 23:00:44 +0100 Subject: uapi: fix big endian definition of ipv6_rpl_sr_hdr Following RFC 6554 [1], the current order of fields is wrong for big endian definition. Indeed, here is how the header looks like: +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Next Header | Hdr Ext Len | Routing Type | Segments Left | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CmprI | CmprE | Pad | Reserved | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ This patch reorders fields so that big endian definition is now correct. [1] https://tools.ietf.org/html/rfc6554#section-3 Fixes: cfa933d938d8 ("include: uapi: linux: add rpl sr header definition") Signed-off-by: Justin Iurman Signed-off-by: Jakub Kicinski --- include/uapi/linux/rpl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h index 1dccb55cf8c6..708adddf9f13 100644 --- a/include/uapi/linux/rpl.h +++ b/include/uapi/linux/rpl.h @@ -28,10 +28,10 @@ struct ipv6_rpl_sr_hdr { pad:4, reserved1:16; #elif defined(__BIG_ENDIAN_BITFIELD) - __u32 reserved:20, + __u32 cmpri:4, + cmpre:4, pad:4, - cmpri:4, - cmpre:4; + reserved:20; #else #error "Please fix " #endif -- cgit v1.2.3 From a53e3c189cc6460b60e152af3fc24edf8e0ea9d2 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 18 Jan 2021 16:37:00 +0100 Subject: media: v4l2-subdev.h: BIT() is not available in userspace The BIT macro is not available in userspace, so replace BIT(0) by 0x00000001. Signed-off-by: Hans Verkuil Fixes: 6446ec6cbf46 ("media: v4l2-subdev: add VIDIOC_SUBDEV_QUERYCAP ioctl") Cc: Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-subdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 00850b98078a..a38454d9e0f5 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -176,7 +176,7 @@ struct v4l2_subdev_capability { }; /* The v4l2 sub-device video device node is registered in read-only mode. */ -#define V4L2_SUBDEV_CAP_RO_SUBDEV BIT(0) +#define V4L2_SUBDEV_CAP_RO_SUBDEV 0x00000001 /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid -- cgit v1.2.3 From 6b2e04bc240fe9be9e690059f710e9f95346d34d Mon Sep 17 00:00:00 2001 From: Praveen Chaudhary Date: Mon, 25 Jan 2021 13:44:30 -0800 Subject: net: allow user to set metric on default route learned via Router Advertisement For IPv4, default route is learned via DHCPv4 and user is allowed to change metric using config etc/network/interfaces. But for IPv6, default route can be learned via RA, for which, currently a fixed metric value 1024 is used. Ideally, user should be able to configure metric on default route for IPv6 similar to IPv4. This patch adds sysctl for the same. Logs: For IPv4: Config in etc/network/interfaces: auto eth0 iface eth0 inet dhcp metric 4261413864 IPv4 Kernel Route Table: $ ip route list default via 172.21.47.1 dev eth0 metric 4261413864 FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over DHCPv4 default route.] Codes: K - kernel route, C - connected, S - static, R - RIP, O - OSPF, I - IS-IS, B - BGP, P - PIM, E - EIGRP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* 0.0.0.0/0 [20/0] is directly connected, eth0, 00:00:03 K 0.0.0.0/0 [254/1000] via 172.21.47.1, eth0, 6d08h51m i.e. User can prefer Default Router learned via Routing Protocol in IPv4. Similar behavior is not possible for IPv6, without this fix. After fix [for IPv6]: sudo sysctl -w net.ipv6.conf.eth0.net.ipv6.conf.eth0.ra_defrtr_metric=1996489705 IP monitor: [When IPv6 RA is received] default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 pref high Kernel IPv6 routing table $ ip -6 route list default via fe80::be16:65ff:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 21sec hoplimit 64 pref high FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over IPv6 RA default route.] Codes: K - kernel route, C - connected, S - static, R - RIPng, O - OSPFv3, I - IS-IS, B - BGP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* ::/0 [20/0] is directly connected, eth0, 00:00:06 K ::/0 [119/1001] via fe80::xx16:xxxx:feb3:ce8e, eth0, 6d07h43m If the metric is changed later, the effect will be seen only when next IPv6 RA is received, because the default route must be fully controlled by RA msg. Below metric is changed from 1996489705 to 1996489704. $ sudo sysctl -w net.ipv6.conf.eth0.ra_defrtr_metric=1996489704 net.ipv6.conf.eth0.ra_defrtr_metric = 1996489704 IP monitor: [On next IPv6 RA msg, Kernel deletes prev route and installs new route with updated metric] Deleted default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 3sec hoplimit 64 pref high default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489704 pref high Signed-off-by: Praveen Chaudhary Signed-off-by: Zhenggen Xu Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20210125214430.24079-1-pchaudhary@linkedin.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 10 ++++++++++ include/linux/ipv6.h | 1 + include/net/ip6_route.h | 3 ++- include/uapi/linux/ipv6.h | 1 + include/uapi/linux/sysctl.h | 1 + net/ipv6/addrconf.c | 11 +++++++++++ net/ipv6/ndisc.c | 12 ++++++++---- net/ipv6/route.c | 5 +++-- 8 files changed, 37 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index dd2b12a32b73..0e51ddd9a2f1 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1871,6 +1871,16 @@ accept_ra_defrtr - BOOLEAN - enabled if accept_ra is enabled. - disabled if accept_ra is disabled. +ra_defrtr_metric - UNSIGNED INTEGER + Route metric for default route learned in Router Advertisement. This value + will be assigned as metric for the default route learned via IPv6 Router + Advertisement. Takes affect only if accept_ra_defrtr is enabled. + + Possible values: + 1 to 0xFFFFFFFF + + Default: IP6_RT_PRIO_USER i.e. 1024. + accept_ra_from_local - BOOLEAN Accept RA with source-address that is found on local machine if the RA is otherwise proper and able to be accepted. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index dda61d150a13..9d1f29f0c512 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -31,6 +31,7 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 2a5277758379..f51a118bfce8 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -174,7 +174,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, - struct net_device *dev, unsigned int pref); + struct net_device *dev, unsigned int pref, + u32 defrtr_usr_metric); void rt6_purge_dflt_routers(struct net *net); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 13e8751bf24a..70603775fe91 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -189,6 +189,7 @@ enum { DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, DEVCONF_NDISC_TCLASS, DEVCONF_RPL_SEG_ENABLED, + DEVCONF_RA_DEFRTR_METRIC, DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 458179df9b27..1e05d3caa712 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -571,6 +571,7 @@ enum { NET_IPV6_ACCEPT_SOURCE_ROUTE=25, NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27, + NET_IPV6_RA_DEFRTR_METRIC=28, __NET_IPV6_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9edc5bb2d531..f2337fb756ac 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -205,6 +205,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -5476,6 +5478,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF @@ -6668,6 +6671,14 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "ra_defrtr_metric", + .data = &ipv6_devconf.ra_defrtr_metric, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)SYSCTL_ONE, + }, { .procname = "accept_ra_min_hop_limit", .data = &ipv6_devconf.accept_ra_min_hop_limit, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 76717478f173..c467c6419893 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1173,6 +1173,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; struct fib6_info *rt = NULL; + u32 defrtr_usr_metric; struct net *net; int lifetime; struct ndisc_options ndopts; @@ -1303,18 +1304,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } } - if (rt && lifetime == 0) { + /* Set default route metric as specified by user */ + defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; + /* delete the route if lifetime is 0 or if metric needs change */ + if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } - ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", - rt, lifetime, skb->dev->name); + ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", + rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, - skb->dev, pref); + skb->dev, pref, defrtr_usr_metric); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 188e114b29b4..41d8f801b75f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4252,11 +4252,12 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, - unsigned int pref) + unsigned int pref, + u32 defrtr_usr_metric) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, - .fc_metric = IP6_RT_PRIO_USER, + .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), -- cgit v1.2.3 From 8544717cdacc2f33f0f53a3b34c5125b37e13ce9 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 14 Jan 2021 19:07:48 +0200 Subject: bus: fsl-mc: move fsl_mc_command struct in a uapi header Define "struct fsl_mc_command" as a structure that can cross the user/kernel boundary. Acked-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20210114170752.2927915-2-ciorneiioana@gmail.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 + include/linux/fsl/mc.h | 8 +------- include/uapi/linux/fsl_mc.h | 25 +++++++++++++++++++++++++ 3 files changed, 27 insertions(+), 7 deletions(-) create mode 100644 include/uapi/linux/fsl_mc.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 23273a59da6f..128455811980 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14652,6 +14652,7 @@ S: Maintained F: Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst F: drivers/bus/fsl-mc/ +F: include/uapi/linux/fsl_mc.h QT1010 MEDIA DRIVER M: Antti Palosaari diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index db244874e834..63b56aba925a 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -13,6 +13,7 @@ #include #include #include +#include #define FSL_MC_VENDOR_FREESCALE 0x1957 @@ -209,8 +210,6 @@ struct fsl_mc_device { #define to_fsl_mc_device(_dev) \ container_of(_dev, struct fsl_mc_device, dev) -#define MC_CMD_NUM_OF_PARAMS 7 - struct mc_cmd_header { u8 src_id; u8 flags_hw; @@ -220,11 +219,6 @@ struct mc_cmd_header { __le16 cmd_id; }; -struct fsl_mc_command { - __le64 header; - __le64 params[MC_CMD_NUM_OF_PARAMS]; -}; - enum mc_cmd_status { MC_CMD_STATUS_OK = 0x0, /* Completed successfully */ MC_CMD_STATUS_READY = 0x1, /* Ready to be processed */ diff --git a/include/uapi/linux/fsl_mc.h b/include/uapi/linux/fsl_mc.h new file mode 100644 index 000000000000..cf56d46f052e --- /dev/null +++ b/include/uapi/linux/fsl_mc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Management Complex (MC) userspace public interface + * + * Copyright 2021 NXP + * + */ +#ifndef _UAPI_FSL_MC_H_ +#define _UAPI_FSL_MC_H_ + +#include + +#define MC_CMD_NUM_OF_PARAMS 7 + +/** + * struct fsl_mc_command - Management Complex (MC) command structure + * @header: MC command header + * @params: MC command parameters + */ +struct fsl_mc_command { + __le64 header; + __le64 params[MC_CMD_NUM_OF_PARAMS]; +}; + +#endif /* _UAPI_FSL_MC_H_ */ -- cgit v1.2.3 From 2cf1e703f066cfa82eb5a358ae84c29fe15a3b3a Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 14 Jan 2021 19:07:50 +0200 Subject: bus: fsl-mc: add fsl-mc userspace support Adding userspace support for the MC (Management Complex) means exporting an ioctl capable device file representing the root resource container. This new functionality in the fsl-mc bus driver intends to provide userspace applications an interface to interact with the MC firmware. Commands that are composed in userspace are sent to the MC firmware through the FSL_MC_SEND_MC_COMMAND ioctl. By default the implicit MC I/O portal is used for this operation, but if the implicit one is busy, a dynamic portal is allocated and then freed upon execution. The command received through the ioctl interface is checked against a known whitelist of accepted MC commands. Commands that attempt a change in hardware configuration will need CAP_NET_ADMIN, while commands used in debugging do not need it. Acked-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20210114170752.2927915-4-ciorneiioana@gmail.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + drivers/bus/fsl-mc/Kconfig | 7 + drivers/bus/fsl-mc/Makefile | 3 + drivers/bus/fsl-mc/dprc-driver.c | 12 + drivers/bus/fsl-mc/fsl-mc-private.h | 39 ++ drivers/bus/fsl-mc/fsl-mc-uapi.c | 547 +++++++++++++++++++++ include/uapi/linux/fsl_mc.h | 9 + 7 files changed, 618 insertions(+) create mode 100644 drivers/bus/fsl-mc/fsl-mc-uapi.c (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..19d730f9d136 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -180,6 +180,7 @@ Code Seq# Include File Comments 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! 'R' C0-DF net/bluetooth/rfcomm.h +'R' E0 uapi/linux/fsl_mc.h 'S' all linux/cdrom.h conflict! 'S' 80-81 scsi/scsi_ioctl.h conflict! 'S' 82-FF scsi/scsi.h conflict! diff --git a/drivers/bus/fsl-mc/Kconfig b/drivers/bus/fsl-mc/Kconfig index c23c77c9b705..b1fd55901c50 100644 --- a/drivers/bus/fsl-mc/Kconfig +++ b/drivers/bus/fsl-mc/Kconfig @@ -14,3 +14,10 @@ config FSL_MC_BUS architecture. The fsl-mc bus driver handles discovery of DPAA2 objects (which are represented as Linux devices) and binding objects to drivers. + +config FSL_MC_UAPI_SUPPORT + bool "Management Complex (MC) userspace support" + depends on FSL_MC_BUS + help + Provides userspace support for interrogating, creating, destroying or + configuring DPAA2 objects exported by the Management Complex. diff --git a/drivers/bus/fsl-mc/Makefile b/drivers/bus/fsl-mc/Makefile index 3c518c7e8374..4ae292a30e53 100644 --- a/drivers/bus/fsl-mc/Makefile +++ b/drivers/bus/fsl-mc/Makefile @@ -16,3 +16,6 @@ mc-bus-driver-objs := fsl-mc-bus.o \ fsl-mc-allocator.o \ fsl-mc-msi.o \ dpmcp.o + +# MC userspace support +obj-$(CONFIG_FSL_MC_UAPI_SUPPORT) += fsl-mc-uapi.o diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 68488a7ad0d6..ccec375095f2 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -603,6 +603,7 @@ int dprc_setup(struct fsl_mc_device *mc_dev) struct irq_domain *mc_msi_domain; bool mc_io_created = false; bool msi_domain_set = false; + bool uapi_created = false; u16 major_ver, minor_ver; size_t region_size; int error; @@ -635,6 +636,11 @@ int dprc_setup(struct fsl_mc_device *mc_dev) return error; mc_io_created = true; + } else { + error = fsl_mc_uapi_create_device_file(mc_bus); + if (error < 0) + return -EPROBE_DEFER; + uapi_created = true; } mc_msi_domain = fsl_mc_find_msi_domain(&mc_dev->dev); @@ -692,6 +698,9 @@ error_cleanup_msi_domain: mc_dev->mc_io = NULL; } + if (uapi_created) + fsl_mc_uapi_remove_device_file(mc_bus); + return error; } EXPORT_SYMBOL_GPL(dprc_setup); @@ -763,6 +772,7 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev) int dprc_cleanup(struct fsl_mc_device *mc_dev) { + struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev); int error; /* this function should be called only for DPRCs, it @@ -793,6 +803,8 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev) if (!fsl_mc_is_root_dprc(&mc_dev->dev)) { fsl_destroy_mc_io(mc_dev->mc_io); mc_dev->mc_io = NULL; + } else { + fsl_mc_uapi_remove_device_file(mc_bus); } return 0; diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h index be686c363121..6293a24de456 100644 --- a/drivers/bus/fsl-mc/fsl-mc-private.h +++ b/drivers/bus/fsl-mc/fsl-mc-private.h @@ -10,6 +10,8 @@ #include #include +#include +#include /* * Data Path Management Complex (DPMNG) General API @@ -542,6 +544,22 @@ struct fsl_mc_resource_pool { struct fsl_mc_bus *mc_bus; }; +/** + * struct fsl_mc_uapi - information associated with a device file + * @misc: struct miscdevice linked to the root dprc + * @device: newly created device in /dev + * @mutex: mutex lock to serialize the open/release operations + * @local_instance_in_use: local MC I/O instance in use or not + * @static_mc_io: pointer to the static MC I/O object + */ +struct fsl_mc_uapi { + struct miscdevice misc; + struct device *device; + struct mutex mutex; /* serialize open/release operations */ + u32 local_instance_in_use; + struct fsl_mc_io *static_mc_io; +}; + /** * struct fsl_mc_bus - logical bus that corresponds to a physical DPRC * @mc_dev: fsl-mc device for the bus device itself. @@ -551,6 +569,7 @@ struct fsl_mc_resource_pool { * @irq_resources: Pointer to array of IRQ objects for the IRQ pool * @scan_mutex: Serializes bus scanning * @dprc_attr: DPRC attributes + * @uapi_misc: struct that abstracts the interaction with userspace */ struct fsl_mc_bus { struct fsl_mc_device mc_dev; @@ -558,6 +577,7 @@ struct fsl_mc_bus { struct fsl_mc_device_irq *irq_resources; struct mutex scan_mutex; /* serializes bus scanning */ struct dprc_attributes dprc_attr; + struct fsl_mc_uapi uapi_misc; }; #define to_fsl_mc_bus(_mc_dev) \ @@ -614,4 +634,23 @@ struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc, u16 mc_cmd_hdr_read_cmdid(struct fsl_mc_command *cmd); +#ifdef CONFIG_FSL_MC_UAPI_SUPPORT + +int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus); + +void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus); + +#else + +static inline int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus) +{ + return 0; +} + +static inline void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus) +{ +} + +#endif + #endif /* _FSL_MC_PRIVATE_H_ */ diff --git a/drivers/bus/fsl-mc/fsl-mc-uapi.c b/drivers/bus/fsl-mc/fsl-mc-uapi.c new file mode 100644 index 000000000000..eeb988c9f4bb --- /dev/null +++ b/drivers/bus/fsl-mc/fsl-mc-uapi.c @@ -0,0 +1,547 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Complex (MC) userspace support + * + * Copyright 2021 NXP + * + */ + +#include +#include +#include +#include + +#include "fsl-mc-private.h" + +struct uapi_priv_data { + struct fsl_mc_uapi *uapi; + struct fsl_mc_io *mc_io; +}; + +struct fsl_mc_cmd_desc { + u16 cmdid_value; + u16 cmdid_mask; + int size; + bool token; + int flags; +}; + +#define FSL_MC_CHECK_MODULE_ID BIT(0) +#define FSL_MC_CAP_NET_ADMIN_NEEDED BIT(1) + +enum fsl_mc_cmd_index { + DPDBG_DUMP = 0, + DPDBG_SET, + DPRC_GET_CONTAINER_ID, + DPRC_CREATE_CONT, + DPRC_DESTROY_CONT, + DPRC_ASSIGN, + DPRC_UNASSIGN, + DPRC_GET_OBJ_COUNT, + DPRC_GET_OBJ, + DPRC_GET_RES_COUNT, + DPRC_GET_RES_IDS, + DPRC_SET_OBJ_LABEL, + DPRC_SET_LOCKED, + DPRC_CONNECT, + DPRC_DISCONNECT, + DPRC_GET_POOL, + DPRC_GET_POOL_COUNT, + DPRC_GET_CONNECTION, + DPCI_GET_LINK_STATE, + DPCI_GET_PEER_ATTR, + DPAIOP_GET_SL_VERSION, + DPAIOP_GET_STATE, + DPMNG_GET_VERSION, + DPSECI_GET_TX_QUEUE, + DPMAC_GET_COUNTER, + DPMAC_GET_MAC_ADDR, + DPNI_SET_PRIM_MAC, + DPNI_GET_PRIM_MAC, + DPNI_GET_STATISTICS, + DPNI_GET_LINK_STATE, + GET_ATTR, + GET_IRQ_MASK, + GET_IRQ_STATUS, + CLOSE, + OPEN, + GET_API_VERSION, + DESTROY, + CREATE, +}; + +static struct fsl_mc_cmd_desc fsl_mc_accepted_cmds[] = { + [DPDBG_DUMP] = { + .cmdid_value = 0x1300, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 28, + }, + [DPDBG_SET] = { + .cmdid_value = 0x1400, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 28, + }, + [DPRC_GET_CONTAINER_ID] = { + .cmdid_value = 0x8300, + .cmdid_mask = 0xFFF0, + .token = false, + .size = 8, + }, + [DPRC_CREATE_CONT] = { + .cmdid_value = 0x1510, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_DESTROY_CONT] = { + .cmdid_value = 0x1520, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_ASSIGN] = { + .cmdid_value = 0x1570, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_UNASSIGN] = { + .cmdid_value = 0x1580, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_GET_OBJ_COUNT] = { + .cmdid_value = 0x1590, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + }, + [DPRC_GET_OBJ] = { + .cmdid_value = 0x15A0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + }, + [DPRC_GET_RES_COUNT] = { + .cmdid_value = 0x15B0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + }, + [DPRC_GET_RES_IDS] = { + .cmdid_value = 0x15C0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 40, + }, + [DPRC_SET_OBJ_LABEL] = { + .cmdid_value = 0x1610, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 48, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_SET_LOCKED] = { + .cmdid_value = 0x16B0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_CONNECT] = { + .cmdid_value = 0x1670, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 56, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_DISCONNECT] = { + .cmdid_value = 0x1680, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPRC_GET_POOL] = { + .cmdid_value = 0x1690, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 12, + }, + [DPRC_GET_POOL_COUNT] = { + .cmdid_value = 0x16A0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPRC_GET_CONNECTION] = { + .cmdid_value = 0x16C0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 32, + }, + + [DPCI_GET_LINK_STATE] = { + .cmdid_value = 0x0E10, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPCI_GET_PEER_ATTR] = { + .cmdid_value = 0x0E20, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPAIOP_GET_SL_VERSION] = { + .cmdid_value = 0x2820, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPAIOP_GET_STATE] = { + .cmdid_value = 0x2830, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPMNG_GET_VERSION] = { + .cmdid_value = 0x8310, + .cmdid_mask = 0xFFF0, + .token = false, + .size = 8, + }, + [DPSECI_GET_TX_QUEUE] = { + .cmdid_value = 0x1970, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 14, + }, + [DPMAC_GET_COUNTER] = { + .cmdid_value = 0x0c40, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 9, + }, + [DPMAC_GET_MAC_ADDR] = { + .cmdid_value = 0x0c50, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPNI_SET_PRIM_MAC] = { + .cmdid_value = 0x2240, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 16, + .flags = FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [DPNI_GET_PRIM_MAC] = { + .cmdid_value = 0x2250, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [DPNI_GET_STATISTICS] = { + .cmdid_value = 0x25D0, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 10, + }, + [DPNI_GET_LINK_STATE] = { + .cmdid_value = 0x2150, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [GET_ATTR] = { + .cmdid_value = 0x0040, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + [GET_IRQ_MASK] = { + .cmdid_value = 0x0150, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 13, + }, + [GET_IRQ_STATUS] = { + .cmdid_value = 0x0160, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 13, + }, + [CLOSE] = { + .cmdid_value = 0x8000, + .cmdid_mask = 0xFFF0, + .token = true, + .size = 8, + }, + + /* Common commands amongst all types of objects. Must be checked last. */ + [OPEN] = { + .cmdid_value = 0x8000, + .cmdid_mask = 0xFC00, + .token = false, + .size = 12, + .flags = FSL_MC_CHECK_MODULE_ID, + }, + [GET_API_VERSION] = { + .cmdid_value = 0xA000, + .cmdid_mask = 0xFC00, + .token = false, + .size = 8, + .flags = FSL_MC_CHECK_MODULE_ID, + }, + [DESTROY] = { + .cmdid_value = 0x9800, + .cmdid_mask = 0xFC00, + .token = true, + .size = 12, + .flags = FSL_MC_CHECK_MODULE_ID | FSL_MC_CAP_NET_ADMIN_NEEDED, + }, + [CREATE] = { + .cmdid_value = 0x9000, + .cmdid_mask = 0xFC00, + .token = true, + .size = 64, + .flags = FSL_MC_CHECK_MODULE_ID | FSL_MC_CAP_NET_ADMIN_NEEDED, + }, +}; + +#define FSL_MC_NUM_ACCEPTED_CMDS ARRAY_SIZE(fsl_mc_accepted_cmds) + +#define FSL_MC_MAX_MODULE_ID 0x10 + +static int fsl_mc_command_check(struct fsl_mc_device *mc_dev, + struct fsl_mc_command *mc_cmd) +{ + struct fsl_mc_cmd_desc *desc = NULL; + int mc_cmd_max_size, i; + bool token_provided; + u16 cmdid, module_id; + char *mc_cmd_end; + char sum = 0; + + /* Check if this is an accepted MC command */ + cmdid = mc_cmd_hdr_read_cmdid(mc_cmd); + for (i = 0; i < FSL_MC_NUM_ACCEPTED_CMDS; i++) { + desc = &fsl_mc_accepted_cmds[i]; + if ((cmdid & desc->cmdid_mask) == desc->cmdid_value) + break; + } + if (!desc) { + dev_err(&mc_dev->dev, "MC command 0x%04x: cmdid not accepted\n", cmdid); + return -EACCES; + } + + /* Check if the size of the command is honored. Anything beyond the + * last valid byte of the command should be zeroed. + */ + mc_cmd_max_size = sizeof(*mc_cmd); + mc_cmd_end = ((char *)mc_cmd) + desc->size; + for (i = desc->size; i < mc_cmd_max_size; i++) + sum |= *mc_cmd_end++; + if (sum) { + dev_err(&mc_dev->dev, "MC command 0x%04x: garbage beyond max size of %d bytes!\n", + cmdid, desc->size); + return -EACCES; + } + + /* Some MC commands request a token to be passed so that object + * identification is possible. Check if the token passed in the command + * is as expected. + */ + token_provided = mc_cmd_hdr_read_token(mc_cmd) ? true : false; + if (token_provided != desc->token) { + dev_err(&mc_dev->dev, "MC command 0x%04x: token 0x%04x is invalid!\n", + cmdid, mc_cmd_hdr_read_token(mc_cmd)); + return -EACCES; + } + + /* If needed, check if the module ID passed is valid */ + if (desc->flags & FSL_MC_CHECK_MODULE_ID) { + /* The module ID is represented by bits [4:9] from the cmdid */ + module_id = (cmdid & GENMASK(9, 4)) >> 4; + if (module_id == 0 || module_id > FSL_MC_MAX_MODULE_ID) { + dev_err(&mc_dev->dev, "MC command 0x%04x: unknown module ID 0x%x\n", + cmdid, module_id); + return -EACCES; + } + } + + /* Some commands alter how hardware resources are managed. For these + * commands, check for CAP_NET_ADMIN. + */ + if (desc->flags & FSL_MC_CAP_NET_ADMIN_NEEDED) { + if (!capable(CAP_NET_ADMIN)) { + dev_err(&mc_dev->dev, "MC command 0x%04x: needs CAP_NET_ADMIN!\n", + cmdid); + return -EPERM; + } + } + + return 0; +} + +static int fsl_mc_uapi_send_command(struct fsl_mc_device *mc_dev, unsigned long arg, + struct fsl_mc_io *mc_io) +{ + struct fsl_mc_command mc_cmd; + int error; + + error = copy_from_user(&mc_cmd, (void __user *)arg, sizeof(mc_cmd)); + if (error) + return -EFAULT; + + error = fsl_mc_command_check(mc_dev, &mc_cmd); + if (error) + return error; + + error = mc_send_command(mc_io, &mc_cmd); + if (error) + return error; + + error = copy_to_user((void __user *)arg, &mc_cmd, sizeof(mc_cmd)); + if (error) + return -EFAULT; + + return 0; +} + +static int fsl_mc_uapi_dev_open(struct inode *inode, struct file *filep) +{ + struct fsl_mc_device *root_mc_device; + struct uapi_priv_data *priv_data; + struct fsl_mc_io *dynamic_mc_io; + struct fsl_mc_uapi *mc_uapi; + struct fsl_mc_bus *mc_bus; + int error; + + priv_data = kzalloc(sizeof(*priv_data), GFP_KERNEL); + if (!priv_data) + return -ENOMEM; + + mc_uapi = container_of(filep->private_data, struct fsl_mc_uapi, misc); + mc_bus = container_of(mc_uapi, struct fsl_mc_bus, uapi_misc); + root_mc_device = &mc_bus->mc_dev; + + mutex_lock(&mc_uapi->mutex); + + if (!mc_uapi->local_instance_in_use) { + priv_data->mc_io = mc_uapi->static_mc_io; + mc_uapi->local_instance_in_use = 1; + } else { + error = fsl_mc_portal_allocate(root_mc_device, 0, + &dynamic_mc_io); + if (error) { + dev_dbg(&root_mc_device->dev, + "Could not allocate MC portal\n"); + goto error_portal_allocate; + } + + priv_data->mc_io = dynamic_mc_io; + } + priv_data->uapi = mc_uapi; + filep->private_data = priv_data; + + mutex_unlock(&mc_uapi->mutex); + + return 0; + +error_portal_allocate: + mutex_unlock(&mc_uapi->mutex); + kfree(priv_data); + + return error; +} + +static int fsl_mc_uapi_dev_release(struct inode *inode, struct file *filep) +{ + struct uapi_priv_data *priv_data; + struct fsl_mc_uapi *mc_uapi; + struct fsl_mc_io *mc_io; + + priv_data = filep->private_data; + mc_uapi = priv_data->uapi; + mc_io = priv_data->mc_io; + + mutex_lock(&mc_uapi->mutex); + + if (mc_io == mc_uapi->static_mc_io) + mc_uapi->local_instance_in_use = 0; + else + fsl_mc_portal_free(mc_io); + + kfree(filep->private_data); + filep->private_data = NULL; + + mutex_unlock(&mc_uapi->mutex); + + return 0; +} + +static long fsl_mc_uapi_dev_ioctl(struct file *file, + unsigned int cmd, + unsigned long arg) +{ + struct uapi_priv_data *priv_data = file->private_data; + struct fsl_mc_device *root_mc_device; + struct fsl_mc_bus *mc_bus; + int error; + + mc_bus = container_of(priv_data->uapi, struct fsl_mc_bus, uapi_misc); + root_mc_device = &mc_bus->mc_dev; + + switch (cmd) { + case FSL_MC_SEND_MC_COMMAND: + error = fsl_mc_uapi_send_command(root_mc_device, arg, priv_data->mc_io); + break; + default: + dev_dbg(&root_mc_device->dev, "unexpected ioctl call number\n"); + error = -EINVAL; + } + + return error; +} + +static const struct file_operations fsl_mc_uapi_dev_fops = { + .owner = THIS_MODULE, + .open = fsl_mc_uapi_dev_open, + .release = fsl_mc_uapi_dev_release, + .unlocked_ioctl = fsl_mc_uapi_dev_ioctl, +}; + +int fsl_mc_uapi_create_device_file(struct fsl_mc_bus *mc_bus) +{ + struct fsl_mc_device *mc_dev = &mc_bus->mc_dev; + struct fsl_mc_uapi *mc_uapi = &mc_bus->uapi_misc; + int error; + + mc_uapi->misc.minor = MISC_DYNAMIC_MINOR; + mc_uapi->misc.name = dev_name(&mc_dev->dev); + mc_uapi->misc.fops = &fsl_mc_uapi_dev_fops; + + error = misc_register(&mc_uapi->misc); + if (error) + return error; + + mc_uapi->static_mc_io = mc_bus->mc_dev.mc_io; + + mutex_init(&mc_uapi->mutex); + + return 0; +} + +void fsl_mc_uapi_remove_device_file(struct fsl_mc_bus *mc_bus) +{ + misc_deregister(&mc_bus->uapi_misc.misc); +} diff --git a/include/uapi/linux/fsl_mc.h b/include/uapi/linux/fsl_mc.h index cf56d46f052e..e57451570033 100644 --- a/include/uapi/linux/fsl_mc.h +++ b/include/uapi/linux/fsl_mc.h @@ -16,10 +16,19 @@ * struct fsl_mc_command - Management Complex (MC) command structure * @header: MC command header * @params: MC command parameters + * + * Used by FSL_MC_SEND_MC_COMMAND */ struct fsl_mc_command { __le64 header; __le64 params[MC_CMD_NUM_OF_PARAMS]; }; +#define FSL_MC_SEND_CMD_IOCTL_TYPE 'R' +#define FSL_MC_SEND_CMD_IOCTL_SEQ 0xE0 + +#define FSL_MC_SEND_MC_COMMAND \ + _IOWR(FSL_MC_SEND_CMD_IOCTL_TYPE, FSL_MC_SEND_CMD_IOCTL_SEQ, \ + struct fsl_mc_command) + #endif /* _UAPI_FSL_MC_H_ */ -- cgit v1.2.3 From 2dba407f994e5b0eb3b70a8cb280e014ec4a7ff3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 26 Jan 2021 11:35:33 +0200 Subject: net: bridge: multicast: make tracked EHT hosts limit configurable Add two new port attributes which make EHT hosts limit configurable and export the current number of tracked EHT hosts: - IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT: configure/retrieve current limit - IFLA_BRPORT_MCAST_EHT_HOSTS_CNT: current number of tracked hosts Setting IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT to 0 is currently not allowed. Note that we have to increase RTNL_SLAVE_MAX_TYPE to 38 minimum, I've increased it to 40 to have space for two more future entries. v2: move br_multicast_eht_set_hosts_limit() to br_multicast_eht.c, no functional change Signed-off-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_multicast_eht.c | 15 +++++++++++++++ net/bridge/br_netlink.c | 19 ++++++++++++++++++- net/bridge/br_private_mcast_eht.h | 2 ++ net/bridge/br_sysfs_if.c | 26 ++++++++++++++++++++++++++ net/core/rtnetlink.c | 2 +- 6 files changed, 64 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2bd0d8bbcdb2..eb8018c3a737 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -525,6 +525,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_multicast_eht.c b/net/bridge/br_multicast_eht.c index 445768c8495f..fea38b9a7268 100644 --- a/net/bridge/br_multicast_eht.c +++ b/net/bridge/br_multicast_eht.c @@ -861,3 +861,18 @@ bool br_multicast_eht_handle(struct net_bridge_port_group *pg, out: return changed; } + +int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, + u32 eht_hosts_limit) +{ + struct net_bridge *br = p->br; + + if (!eht_hosts_limit) + return -EINVAL; + + spin_lock_bh(&br->multicast_lock); + p->multicast_eht_hosts_limit = eht_hosts_limit; + spin_unlock_bh(&br->multicast_lock); + + return 0; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 762f273802cd..bd3962da345a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -18,6 +18,7 @@ #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" +#include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) @@ -199,6 +200,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + 0; } @@ -283,7 +286,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, - p->multicast_router)) + p->multicast_router) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + p->multicast_eht_hosts_limit) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + p->multicast_eht_hosts_cnt)) return -EMSGSIZE; #endif @@ -820,6 +827,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -955,6 +963,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { + u32 hlimit; + + hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); + err = br_multicast_eht_set_hosts_limit(p, hlimit); + if (err) + return err; + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_private_mcast_eht.h b/net/bridge/br_private_mcast_eht.h index b2c8d988721f..f89049f4892c 100644 --- a/net/bridge/br_private_mcast_eht.h +++ b/net/bridge/br_private_mcast_eht.h @@ -57,6 +57,8 @@ bool br_multicast_eht_handle(struct net_bridge_port_group *pg, u32 nsrcs, size_t addr_size, int grec_type); +int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, + u32 eht_hosts_limit); static inline bool br_multicast_eht_should_del_pg(const struct net_bridge_port_group *pg) diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 7a59cdddd3ce..b66305fae26b 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -16,6 +16,7 @@ #include #include "br_private.h" +#include "br_private_mcast_eht.h" struct brport_attribute { struct attribute attr; @@ -245,6 +246,29 @@ static int store_multicast_router(struct net_bridge_port *p, static BRPORT_ATTR(multicast_router, 0644, show_multicast_router, store_multicast_router); +static ssize_t show_multicast_eht_hosts_limit(struct net_bridge_port *p, + char *buf) +{ + return sprintf(buf, "%u\n", p->multicast_eht_hosts_limit); +} + +static int store_multicast_eht_hosts_limit(struct net_bridge_port *p, + unsigned long v) +{ + return br_multicast_eht_set_hosts_limit(p, v); +} +static BRPORT_ATTR(multicast_eht_hosts_limit, 0644, + show_multicast_eht_hosts_limit, + store_multicast_eht_hosts_limit); + +static ssize_t show_multicast_eht_hosts_cnt(struct net_bridge_port *p, + char *buf) +{ + return sprintf(buf, "%u\n", p->multicast_eht_hosts_cnt); +} +static BRPORT_ATTR(multicast_eht_hosts_cnt, 0444, show_multicast_eht_hosts_cnt, + NULL); + BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE); BRPORT_ATTR_FLAG(multicast_to_unicast, BR_MULTICAST_TO_UNICAST); #endif @@ -274,6 +298,8 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_router, &brport_attr_multicast_fast_leave, &brport_attr_multicast_to_unicast, + &brport_attr_multicast_eht_hosts_limit, + &brport_attr_multicast_eht_hosts_cnt, #endif &brport_attr_proxyarp, &brport_attr_proxyarp_wifi, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3d6ab194d0f5..c313aaf2bce1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -55,7 +55,7 @@ #include #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 36 +#define RTNL_SLAVE_MAX_TYPE 40 struct rtnl_link { rtnl_doit_func doit; -- cgit v1.2.3 From 31f190e0ccac8b75d33fdc95a797c526cf9b149e Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Thu, 21 Jan 2021 15:44:02 +0100 Subject: media: rkisp1: uapi: change hist_bins array type from __u16 to __u32 Each entry in the array is a 20 bits value composed of 16 bits unsigned integer and 4 bits fractional part. So the type should change to __u32. In addition add a documentation of how the measurements are done. Signed-off-by: Dafna Hirschfeld Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 6e449e784260..24f05d6d258f 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -844,13 +844,18 @@ struct rkisp1_cif_isp_af_stat { /** * struct rkisp1_cif_isp_hist_stat - statistics histogram data * - * @hist_bins: measured bin counters + * @hist_bins: measured bin counters. Each bin is a 20 bits unsigned fixed point + * type. Bits 0-4 are the fractional part and bits 5-19 are the + * integer part. * - * Measurement window divided into 25 sub-windows, set - * with ISP_HIST_XXX + * The window of the measurements area is divided to 5x5 sub-windows. The + * histogram is then computed for each sub-window independently and the final + * result is a weighted average of the histogram measurements on all + * sub-windows. The window of the measurements area and the weight of each + * sub-window are configurable using struct @rkisp1_cif_isp_hst_config. */ struct rkisp1_cif_isp_hist_stat { - __u16 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; + __u32 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; }; /** -- cgit v1.2.3 From 66d81de7ea9d2b0775e5bfd5e770483a1c24b9ca Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:05 +0100 Subject: media: rockchip: rkisp1: reduce number of histogram grid elements in uapi The uapi right now specifies an array size of 28 but the actual number of elements is only 25 with the last 3 being unused. Reduce the array size to the correct number of elements and change the params code to iterate the array 25 times. Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/rockchip/rkisp1/rkisp1-params.c | 3 ++- include/uapi/linux/rkisp1-config.h | 3 +-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c index 6af4d551ffb5..021939466b24 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c @@ -589,7 +589,6 @@ static void rkisp1_hst_config(struct rkisp1_params *params, RKISP1_CIF_ISP_HIST_WEIGHT_22TO03, RKISP1_CIF_ISP_HIST_WEIGHT_13TO43, RKISP1_CIF_ISP_HIST_WEIGHT_04TO34, - RKISP1_CIF_ISP_HIST_WEIGHT_44, }; const u8 *weight; unsigned int i; @@ -622,6 +621,8 @@ static void rkisp1_hst_config(struct rkisp1_params *params, weight[2], weight[3]), hist_weight_regs[i]); + + rkisp1_write(params->rkisp1, weight[0] & 0x1F, RKISP1_CIF_ISP_HIST_WEIGHT_44); } static void diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 24f05d6d258f..35aa82d5f6dd 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -102,8 +102,7 @@ /* * Histogram calculation */ -/* Last 3 values unused. */ -#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 28 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 /* * Defect Pixel Cluster Correction -- cgit v1.2.3 From fc672d806bd77eff26117479e90ccdcfd2a8ecb4 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:06 +0100 Subject: media: rockchip: rkisp1: carry ip version information The IP block evolved from its rk3288/rk3399 base and the vendor designates them with a numerical version. rk3399 for example is designated V10 probably meaning V1.0. There doesn't seem to be an actual version register we could read that information from, so allow the match_data to carry that information for future differentiation. Also carry that information in the hw_revision field of the media- controller API, so that userspace also has access to that. The added versions are: - V10: at least rk3288 + rk3399 - V11: seemingly unused as of now, but probably appeared in some soc - V12: at least rk3326 + px30 - V13: at least rk1808 [fix checkpatch warning don't use multiple blank lines] Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Reviewed-by: Ezequiel Garcia Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/media/rkisp1.rst | 16 ++++++++++++++++ drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c | 21 ++++++++++++--------- include/uapi/linux/rkisp1-config.h | 15 +++++++++++++++ 3 files changed, 43 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/media/rkisp1.rst b/Documentation/admin-guide/media/rkisp1.rst index 2267e4fb475e..ccf418713623 100644 --- a/Documentation/admin-guide/media/rkisp1.rst +++ b/Documentation/admin-guide/media/rkisp1.rst @@ -13,6 +13,22 @@ This file documents the driver for the Rockchip ISP1 that is part of RK3288 and RK3399 SoCs. The driver is located under drivers/staging/media/rkisp1 and uses the Media-Controller API. +Revisions +========= + +There exist multiple smaller revisions to this ISP that got introduced in +later SoCs. Revisions can be found in the enum :c:type:`rkisp1_cif_isp_version` +in the UAPI and the revision of the ISP inside the running SoC can be read +in the field hw_revision of struct media_device_info as returned by +ioctl MEDIA_IOC_DEVICE_INFO. + +Versions in use are: + +- RKISP1_V10: used at least in rk3288 and rk3399 +- RKISP1_V11: declared in the original vendor code, but not used +- RKISP1_V12: used at least in rk3326 and px30 +- RKISP1_V13: used at least in rk1808 + Topology ======== .. _rkisp1_topology_graph: diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index 68da1eed753d..f7e9fd305548 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -104,6 +104,7 @@ struct rkisp1_match_data { const char * const *clks; unsigned int size; + enum rkisp1_cif_isp_version isp_ver; }; /* ---------------------------------------------------------------------------- @@ -411,15 +412,16 @@ static const char * const rk3399_isp_clks[] = { "hclk", }; -static const struct rkisp1_match_data rk3399_isp_clk_data = { +static const struct rkisp1_match_data rk3399_isp_match_data = { .clks = rk3399_isp_clks, .size = ARRAY_SIZE(rk3399_isp_clks), + .isp_ver = RKISP1_V10, }; static const struct of_device_id rkisp1_of_match[] = { { .compatible = "rockchip,rk3399-cif-isp", - .data = &rk3399_isp_clk_data, + .data = &rk3399_isp_match_data, }, {}, }; @@ -457,15 +459,15 @@ static void rkisp1_debug_init(struct rkisp1_device *rkisp1) static int rkisp1_probe(struct platform_device *pdev) { - const struct rkisp1_match_data *clk_data; + const struct rkisp1_match_data *match_data; struct device *dev = &pdev->dev; struct rkisp1_device *rkisp1; struct v4l2_device *v4l2_dev; unsigned int i; int ret, irq; - clk_data = of_device_get_match_data(&pdev->dev); - if (!clk_data) + match_data = of_device_get_match_data(&pdev->dev); + if (!match_data) return -ENODEV; rkisp1 = devm_kzalloc(dev, sizeof(*rkisp1), GFP_KERNEL); @@ -494,15 +496,16 @@ static int rkisp1_probe(struct platform_device *pdev) rkisp1->irq = irq; - for (i = 0; i < clk_data->size; i++) - rkisp1->clks[i].id = clk_data->clks[i]; - ret = devm_clk_bulk_get(dev, clk_data->size, rkisp1->clks); + for (i = 0; i < match_data->size; i++) + rkisp1->clks[i].id = match_data->clks[i]; + ret = devm_clk_bulk_get(dev, match_data->size, rkisp1->clks); if (ret) return ret; - rkisp1->clk_size = clk_data->size; + rkisp1->clk_size = match_data->size; pm_runtime_enable(&pdev->dev); + rkisp1->media_dev.hw_revision = match_data->isp_ver; strscpy(rkisp1->media_dev.model, RKISP1_DRIVER_NAME, sizeof(rkisp1->media_dev.model)); rkisp1->media_dev.dev = &pdev->dev; diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 35aa82d5f6dd..bee4413fe0d3 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -123,6 +123,21 @@ #define RKISP1_CIF_ISP_STAT_AFM (1U << 2) #define RKISP1_CIF_ISP_STAT_HIST (1U << 3) +/** + * enum rkisp1_cif_isp_version - ISP variants + * + * @RKISP1_V10: used at least in rk3288 and rk3399 + * @RKISP1_V11: declared in the original vendor code, but not used + * @RKISP1_V12: used at least in rk3326 and px30 + * @RKISP1_V13: used at least in rk1808 + */ +enum rkisp1_cif_isp_version { + RKISP1_V10 = 10, + RKISP1_V11, + RKISP1_V12, + RKISP1_V13, +}; + enum rkisp1_cif_isp_histogram_mode { RKISP1_CIF_ISP_HISTOGRAM_MODE_DISABLE, RKISP1_CIF_ISP_HISTOGRAM_MODE_RGB_COMBINED, -- cgit v1.2.3 From ef357e02b6c420dc2d668ebf3165838c77358acd Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:07 +0100 Subject: media: rockchip: rkisp1: extend uapi array sizes Later variants of the rkisp1 block use more entries in some arrays: RKISP1_CIF_ISP_AE_MEAN_MAX 25 -> 81 RKISP1_CIF_ISP_HIST_BIN_N_MAX 16 -> 32 RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES 17 -> 34 RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 -> 81 and we can still extend the uapi during the 5.11-rc cycle, so do that now to be on the safe side. V10 and V11 only need the smaller sizes, while V12 and V13 needed the larger sizes. When adding the bigger sizes make sure, values filled from hardware values and transmitted to userspace don't leak kernel data by zeroing them beforehand. Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Reviewed-by: Ezequiel Garcia Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../media/platform/rockchip/rkisp1/rkisp1-params.c | 2 +- .../media/platform/rockchip/rkisp1/rkisp1-stats.c | 4 +- include/uapi/linux/rkisp1-config.h | 67 ++++++++++++++++++---- 3 files changed, 60 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c index 021939466b24..aa5f45749543 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c @@ -391,7 +391,7 @@ static void rkisp1_goc_config(struct rkisp1_params *params, RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA); rkisp1_write(params->rkisp1, arg->mode, RKISP1_CIF_ISP_GAMMA_OUT_MODE); - for (i = 0; i < RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES; i++) + for (i = 0; i < RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10; i++) rkisp1_write(params->rkisp1, arg->gamma_y[i], RKISP1_CIF_ISP_GAMMA_OUT_Y_0 + i * 4); } diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c index 3b2783700abc..c1d07a2e8839 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c @@ -203,7 +203,7 @@ static void rkisp1_stats_get_aec_meas(struct rkisp1_stats *stats, unsigned int i; pbuf->meas_type |= RKISP1_CIF_ISP_STAT_AUTOEXP; - for (i = 0; i < RKISP1_CIF_ISP_AE_MEAN_MAX; i++) + for (i = 0; i < RKISP1_CIF_ISP_AE_MEAN_MAX_V10; i++) pbuf->params.ae.exp_mean[i] = (u8)rkisp1_read(rkisp1, RKISP1_CIF_ISP_EXP_MEAN_00 + i * 4); @@ -233,7 +233,7 @@ static void rkisp1_stats_get_hst_meas(struct rkisp1_stats *stats, unsigned int i; pbuf->meas_type |= RKISP1_CIF_ISP_STAT_HIST; - for (i = 0; i < RKISP1_CIF_ISP_HIST_BIN_N_MAX; i++) { + for (i = 0; i < RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10; i++) { u32 reg_val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_HIST_BIN_0 + i * 4); pbuf->params.hist.hist_bins[i] = RKISP1_CIF_ISP_HIST_GET_BIN(reg_val); diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index bee4413fe0d3..36e3efb81b01 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -49,8 +49,14 @@ #define RKISP1_CIF_ISP_CTK_COEFF_MAX 0x100 #define RKISP1_CIF_ISP_CTK_OFFSET_MAX 0x800 -#define RKISP1_CIF_ISP_AE_MEAN_MAX 25 -#define RKISP1_CIF_ISP_HIST_BIN_N_MAX 16 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V10 25 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V12 81 +#define RKISP1_CIF_ISP_AE_MEAN_MAX RKISP1_CIF_ISP_AE_MEAN_MAX_V12 + +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 16 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 32 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 + #define RKISP1_CIF_ISP_AFM_MAX_WINDOWS 3 #define RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE 17 @@ -86,7 +92,9 @@ * Gamma out */ /* Maximum number of color samples supported */ -#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 34 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 /* * Lens shade correction @@ -102,7 +110,9 @@ /* * Histogram calculation */ -#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 25 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 81 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 /* * Defect Pixel Cluster Correction @@ -524,6 +534,15 @@ enum rkisp1_cif_isp_goc_mode { * * @mode: goc mode (from enum rkisp1_cif_isp_goc_mode) * @gamma_y: gamma out curve y-axis for all color components + * + * The number of entries of @gamma_y depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 + * entries. RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_goc_config { __u32 mode; @@ -538,6 +557,15 @@ struct rkisp1_cif_isp_goc_config { * skipped * @meas_window: coordinates of the measure window * @hist_weight: weighting factor for sub-windows + * + * The number of entries of @hist_weight depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 + * entries. RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_hst_config { __u32 mode; @@ -825,7 +853,15 @@ struct rkisp1_cif_isp_bls_meas_val { * @exp_mean: Mean luminance value of block xx * @bls_val: BLS measured values * - * Image is divided into 5x5 blocks. + * The number of entries of @exp_mean depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_AE_MEAN_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_AE_MEAN_MAX_V12 entries. + * RKISP1_CIF_ISP_AE_MEAN_MAX is equal to the maximum of the two. + * + * Image is divided into 5x5 blocks on V10 and 9x9 blocks on V12. */ struct rkisp1_cif_isp_ae_stat { __u8 exp_mean[RKISP1_CIF_ISP_AE_MEAN_MAX]; @@ -862,11 +898,22 @@ struct rkisp1_cif_isp_af_stat { * type. Bits 0-4 are the fractional part and bits 5-19 are the * integer part. * - * The window of the measurements area is divided to 5x5 sub-windows. The - * histogram is then computed for each sub-window independently and the final - * result is a weighted average of the histogram measurements on all - * sub-windows. The window of the measurements area and the weight of each - * sub-window are configurable using struct @rkisp1_cif_isp_hst_config. + * The window of the measurements area is divided to 5x5 sub-windows for + * V10/V11 and to 9x9 sub-windows for V12. The histogram is then computed for + * each sub-window independently and the final result is a weighted average of + * the histogram measurements on all sub-windows. The window of the + * measurements area and the weight of each sub-window are configurable using + * struct @rkisp1_cif_isp_hst_config. + * + * The histogram contains 16 bins in V10/V11 and 32 bins in V12/V13. + * + * The number of entries of @hist_bins depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 entries. + * RKISP1_CIF_ISP_HIST_BIN_N_MAX is equal to the maximum of the two. */ struct rkisp1_cif_isp_hist_stat { __u32 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; -- cgit v1.2.3 From 8c85d18ce647ac2517a1a1bb01b02648e23700e6 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 27 Jan 2021 16:32:45 +0200 Subject: net/sched: cls_flower: Add match on the ct_state reply flag Add match on the ct_state reply flag. Example: $ tc filter add dev ens1f0_0 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est+rpl \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est-rpl \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 1 + net/sched/cls_flower.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 709668e264b0..afe6836e44b1 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -592,6 +592,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ + TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */ }; enum { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 4a9297a89c77..caf7643e9c83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -291,9 +291,11 @@ static u16 fl_ct_info_to_flower_map[] = { [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_RELATED, [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED, + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_RELATED, + TCA_FLOWER_KEY_CT_FLAGS_RELATED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_NEW, }; -- cgit v1.2.3 From 2a6c6b7d7ad346f0679d0963cb19b3f0ea7ef32c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:07 -0800 Subject: perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT Current PERF_SAMPLE_WEIGHT sample type is very useful to expresses the cost of an action represented by the sample. This allows the profiler to scale the samples to be more informative to the programmer. It could also help to locate a hotspot, e.g., when profiling by memory latencies, the expensive load appear higher up in the histograms. But current PERF_SAMPLE_WEIGHT sample type is solely determined by one factor. This could be a problem, if users want two or more factors to contribute to the weight. For example, Golden Cove core PMU can provide both the instruction latency and the cache Latency information as factors for the memory profiling. For current X86 platforms, although meminfo::latency is defined as a u64, only the lower 32 bits include the valid data in practice (No memory access could last than 4G cycles). The higher 32 bits can be used to store new factors. Add a new sample type, PERF_SAMPLE_WEIGHT_STRUCT, to indicate the new sample weight structure. It shares the same space as the PERF_SAMPLE_WEIGHT sample type. Users can apply either the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but they cannot apply both sample types simultaneously. Currently, only X86 and PowerPC use the PERF_SAMPLE_WEIGHT sample type. - For PowerPC, there is nothing changed for the PERF_SAMPLE_WEIGHT sample type. There is no effect for the new PERF_SAMPLE_WEIGHT_STRUCT sample type. PowerPC can re-struct the weight field similarly later. - For X86, the same value will be dumped for the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type for now. The following patches will apply the new factors for the PERF_SAMPLE_WEIGHT_STRUCT sample type. The field in the union perf_sample_weight should be shared among different architectures. A generic name is required, but it's hard to abstract a name that applies to all architectures. For example, on X86, the fields are to store all kinds of latency. While on PowerPC, it stores MMCRA[TECX/TECM], which should not be latency. So a general name prefix 'var$NUM' is used here. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-2-git-send-email-kan.liang@linux.intel.com --- arch/powerpc/perf/core-book3s.c | 2 +- arch/x86/events/intel/ds.c | 17 +++++++++-------- include/linux/perf_event.h | 4 ++-- include/uapi/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++-- kernel/events/core.c | 11 +++++++---- 5 files changed, 59 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 28206b1fe172..869d999a836e 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2195,7 +2195,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_WEIGHT && ppmu->get_mem_weight) - ppmu->get_mem_weight(&data.weight); + ppmu->get_mem_weight(&data.weight.full); if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 67dbc91bccfe..2f54b1fbb895 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -960,7 +960,8 @@ static void adaptive_pebs_record_size_update(void) } #define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ - PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \ + PERF_SAMPLE_PHYS_ADDR | \ + PERF_SAMPLE_WEIGHT_TYPE | \ PERF_SAMPLE_TRANSACTION | \ PERF_SAMPLE_DATA_PAGE_SIZE) @@ -987,7 +988,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && (attr->sample_regs_intr & PEBS_GP_REGS); - tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) && + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) && ((attr->config & INTEL_ARCH_EVENT_MASK) == x86_pmu.rtm_abort_event); @@ -1369,8 +1370,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, /* * Use latency for weight (only avail with PEBS-LL) */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data->weight = pebs->lat; + if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) + data->weight.full = pebs->lat; /* * data.data_src encodes the data source @@ -1462,8 +1463,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data->weight = intel_get_tsx_weight(pebs->tsx_tuning); + if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) + data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning); if (sample_type & PERF_SAMPLE_TRANSACTION) data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, @@ -1577,8 +1578,8 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } if (format_size & PEBS_DATACFG_MEMINFO) { - if (sample_type & PERF_SAMPLE_WEIGHT) - data->weight = meminfo->latency ?: + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) + data->weight.full = meminfo->latency ?: intel_get_tsx_weight(meminfo->tsx_tuning); if (sample_type & PERF_SAMPLE_DATA_SRC) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9a38f579bc76..fab42cfbd350 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -998,7 +998,7 @@ struct perf_sample_data { struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; - u64 weight; + union perf_sample_weight weight; u64 txn; union perf_mem_data_src data_src; @@ -1047,7 +1047,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->raw = NULL; data->br_stack = NULL; data->period = period; - data->weight = 0; + data->weight.full = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..b2cc246ec119 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -145,12 +145,14 @@ enum perf_event_sample_format { PERF_SAMPLE_CGROUP = 1U << 21, PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22, PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23, + PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, - PERF_SAMPLE_MAX = 1U << 24, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; +#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) /* * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set * @@ -890,7 +892,24 @@ enum perf_event_type { * char data[size]; * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * - * { u64 weight; } && PERF_SAMPLE_WEIGHT + * { union perf_sample_weight + * { + * u64 full; && PERF_SAMPLE_WEIGHT + * #if defined(__LITTLE_ENDIAN_BITFIELD) + * struct { + * u32 var1_dw; + * u16 var2_w; + * u16 var3_w; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #elif defined(__BIG_ENDIAN_BITFIELD) + * struct { + * u16 var3_w; + * u16 var2_w; + * u32 var1_dw; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #endif + * } + * } * { u64 data_src; } && PERF_SAMPLE_DATA_SRC * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * { u64 abi; # enum perf_sample_regs_abi @@ -1248,4 +1267,23 @@ struct perf_branch_entry { reserved:40; }; +union perf_sample_weight { + __u64 full; +#if defined(__LITTLE_ENDIAN_BITFIELD) + struct { + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; + }; +#elif defined(__BIG_ENDIAN_BITFIELD) + struct { + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; + }; +#else +#error "Unknown endianness" +#endif +}; + #endif /* _UAPI_LINUX_PERF_EVENT_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 55d18791a72d..5206097d4d3d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1879,8 +1879,8 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) if (sample_type & PERF_SAMPLE_PERIOD) size += sizeof(data->period); - if (sample_type & PERF_SAMPLE_WEIGHT) - size += sizeof(data->weight); + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) + size += sizeof(data->weight.full); if (sample_type & PERF_SAMPLE_READ) size += event->read_size; @@ -6907,8 +6907,8 @@ void perf_output_sample(struct perf_output_handle *handle, data->regs_user.regs); } - if (sample_type & PERF_SAMPLE_WEIGHT) - perf_output_put(handle, data->weight); + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) + perf_output_put(handle, data->weight.full); if (sample_type & PERF_SAMPLE_DATA_SRC) perf_output_put(handle, data->data_src.val); @@ -11564,6 +11564,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (attr->sample_type & PERF_SAMPLE_CGROUP) return -EINVAL; #endif + if ((attr->sample_type & PERF_SAMPLE_WEIGHT) && + (attr->sample_type & PERF_SAMPLE_WEIGHT_STRUCT)) + return -EINVAL; out: return ret; -- cgit v1.2.3 From 61b985e3e775a3a75fda04ce7ef1b1aefc4758bc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:10 -0800 Subject: perf/x86/intel: Add perf core PMU support for Sapphire Rapids Add perf core PMU support for the Intel Sapphire Rapids server, which is the successor of the Intel Ice Lake server. The enabling code is based on Ice Lake, but there are several new features introduced. The event encoding is changed and simplified, e.g., the event codes which are below 0x90 are restricted to counters 0-3. The event codes which above 0x90 are likely to have no restrictions. The event constraints, extra_regs(), and hardware cache events table are changed accordingly. A new Precise Distribution (PDist) facility is introduced, which further minimizes the skid when a precise event is programmed on the GP counter 0. Enable the Precise Distribution (PDist) facility with :ppp event. For this facility to work, the period must be initialized with a value larger than 127. Add spr_limit_period() to apply the limit for :ppp event. Two new data source fields, data block & address block, are added in the PEBS Memory Info Record for the load latency event. To enable the feature, - An auxiliary event has to be enabled together with the load latency event on Sapphire Rapids. A new flag PMU_FL_MEM_LOADS_AUX is introduced to indicate the case. A new event, mem-loads-aux, is exposed to sysfs for the user tool. Add a check in hw_config(). If the auxiliary event is not detected, return an unique error -ENODATA. - The union perf_mem_data_src is extended to support the new fields. - Ice Lake and earlier models do not support block information, but the fields may be set by HW on some machines. Add pebs_no_block to explicitly indicate the previous platforms which don't support the new block fields. Accessing the new block fields are ignored on those platforms. A new store Latency facility is introduced, which leverages the PEBS facility where it can provide additional information about sampled stores. The additional information includes the data address, memory auxiliary info (e.g. Data Source, STLB miss) and the latency of the store access. To enable the facility, the new event (0x02cd) has to be programed on the GP counter 0. A new flag PERF_X86_EVENT_PEBS_STLAT is introduced to indicate the event. The store_latency_data() is introduced to parse the memory auxiliary info. The layout of access latency field of PEBS Memory Info Record has been changed. Two latency, instruction latency (bit 15:0) and cache access latency (bit 47:32) are recorded. - The cache access latency is similar to previous memory access latency. For loads, the latency starts by the actual cache access until the data is returned by the memory subsystem. For stores, the latency starts when the demand write accesses the L1 data cache and lasts until the cacheline write is completed in the memory subsystem. The cache access latency is stored in low 32bits of the sample type PERF_SAMPLE_WEIGHT_STRUCT. - The instruction latency starts by the dispatch of the load operation for execution and lasts until completion of the instruction it belongs to. Add a new flag PMU_FL_INSTR_LATENCY to indicate the instruction latency support. The instruction latency is stored in the bit 47:32 of the sample type PERF_SAMPLE_WEIGHT_STRUCT. Extends the PERF_METRICS MSR to feature TMA method level 2 metrics. The lower half of the register is the TMA level 1 metrics (legacy). The upper half is also divided into four 8-bit fields for the new level 2 metrics. Expose all eight Topdown metrics events to user space. The full description for the SPR features can be found at Intel Architecture Instruction Set Extensions and Future Features Programming Reference, 319433-041. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-5-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 307 +++++++++++++++++++++++++++++++++++++- arch/x86/events/intel/ds.c | 118 ++++++++++++++- arch/x86/events/perf_event.h | 12 +- arch/x86/include/asm/perf_event.h | 8 +- include/uapi/linux/perf_event.h | 12 +- 5 files changed, 443 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 37830ac34ae1..58cd64e1fc4d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -275,6 +275,55 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct extra_reg intel_spr_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_spr_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7), + + INTEL_EVENT_CONSTRAINT(0x2e, 0xff), + INTEL_EVENT_CONSTRAINT(0x3c, 0xff), + /* + * Generally event codes < 0x90 are restricted to counters 0-3. + * The 0x2E and 0x3C are exception, which has no restriction. + */ + INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf), + + INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x08a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1), + INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1), + INTEL_UEVENT_CONSTRAINT(0x02cd, 0x1), + INTEL_EVENT_CONSTRAINT(0xce, 0x1), + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf), + /* + * Generally event codes >= 0x90 are likely to have no restrictions. + * The exception are defined as above. + */ + INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0xff), + + EVENT_CONSTRAINT_END +}; + + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -314,11 +363,15 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles, EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale, "4", "2"); -EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4"); -EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80"); -EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81"); -EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82"); -EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83"); +EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4"); +EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80"); +EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81"); +EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82"); +EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83"); +EVENT_ATTR_STR(topdown-heavy-ops, td_heavy_ops, "event=0x00,umask=0x84"); +EVENT_ATTR_STR(topdown-br-mispredict, td_br_mispredict, "event=0x00,umask=0x85"); +EVENT_ATTR_STR(topdown-fetch-lat, td_fetch_lat, "event=0x00,umask=0x86"); +EVENT_ATTR_STR(topdown-mem-bound, td_mem_bound, "event=0x00,umask=0x87"); static struct attribute *snb_events_attrs[] = { EVENT_PTR(td_slots_issued), @@ -384,6 +437,108 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +static __initconst const u64 spr_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, + [ C(RESULT_MISS) ] = 0xe124, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_MISS) ] = 0xe424, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, + [ C(RESULT_MISS) ] = 0xe12, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, + [ C(RESULT_MISS) ] = 0xe13, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = 0xe11, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x4c4, + [ C(RESULT_MISS) ] = 0x4c5, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + }, +}; + +static __initconst const u64 spr_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x10001, + [ C(RESULT_MISS) ] = 0x3fbfc00001, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x3f3ffc0002, + [ C(RESULT_MISS) ] = 0x3f3fc00002, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x10c000001, + [ C(RESULT_MISS) ] = 0x3fb3000001, + }, + }, +}; + /* * Notes on the events: * - data reads do not include code reads (comparable to earlier tables) @@ -3478,6 +3633,17 @@ static bool is_available_metric_event(struct perf_event *event) event->attr.config <= INTEL_TD_METRIC_AVAILABLE_MAX; } +static inline bool is_mem_loads_event(struct perf_event *event) +{ + return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xcd, .umask=0x01); +} + +static inline bool is_mem_loads_aux_event(struct perf_event *event) +{ + return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0x03, .umask=0x82); +} + + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -3580,6 +3746,33 @@ static int intel_pmu_hw_config(struct perf_event *event) } } + /* + * The load latency event X86_CONFIG(.event=0xcd, .umask=0x01) on SPR + * doesn't function quite right. As a work-around it needs to always be + * co-scheduled with a auxiliary event X86_CONFIG(.event=0x03, .umask=0x82). + * The actual count of this second event is irrelevant it just needs + * to be active to make the first event function correctly. + * + * In a group, the auxiliary event must be in front of the load latency + * event. The rule is to simplify the implementation of the check. + * That's because perf cannot have a complete group at the moment. + */ + if (x86_pmu.flags & PMU_FL_MEM_LOADS_AUX && + (event->attr.sample_type & PERF_SAMPLE_DATA_SRC) && + is_mem_loads_event(event)) { + struct perf_event *leader = event->group_leader; + struct perf_event *sibling = NULL; + + if (!is_mem_loads_aux_event(leader)) { + for_each_sibling_event(sibling, leader) { + if (is_mem_loads_aux_event(sibling)) + break; + } + if (list_entry_is_head(sibling, &leader->sibling_list, sibling_list)) + return -ENODATA; + } + } + if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY)) return 0; @@ -3759,6 +3952,29 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return hsw_get_event_constraints(cpuc, idx, event); } +static struct event_constraint * +spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + c = icl_get_event_constraints(cpuc, idx, event); + + /* + * The :ppp indicates the Precise Distribution (PDist) facility, which + * is only supported on the GP counter 0. If a :ppp event which is not + * available on the GP counter 0, error out. + */ + if (event->attr.precise_ip == 3) { + if (c->idxmsk64 & BIT_ULL(0)) + return &counter0_constraint; + + return &emptyconstraint; + } + + return c; +} + static struct event_constraint * glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -3848,6 +4064,14 @@ static u64 nhm_limit_period(struct perf_event *event, u64 left) return max(left, 32ULL); } +static u64 spr_limit_period(struct perf_event *event, u64 left) +{ + if (event->attr.precise_ip == 3) + return max(left, 128ULL); + + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -4559,6 +4783,42 @@ static struct attribute *icl_tsx_events_attrs[] = { NULL, }; + +EVENT_ATTR_STR(mem-stores, mem_st_spr, "event=0xcd,umask=0x2"); +EVENT_ATTR_STR(mem-loads-aux, mem_ld_aux, "event=0x03,umask=0x82"); + +static struct attribute *spr_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_spr), + EVENT_PTR(mem_ld_aux), + NULL, +}; + +static struct attribute *spr_td_events_attrs[] = { + EVENT_PTR(slots), + EVENT_PTR(td_retiring), + EVENT_PTR(td_bad_spec), + EVENT_PTR(td_fe_bound), + EVENT_PTR(td_be_bound), + EVENT_PTR(td_heavy_ops), + EVENT_PTR(td_br_mispredict), + EVENT_PTR(td_fetch_lat), + EVENT_PTR(td_mem_bound), + NULL, +}; + +static struct attribute *spr_tsx_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_capacity_read), + EVENT_PTR(tx_capacity_write), + EVENT_PTR(tx_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), + NULL, +}; + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -5341,6 +5601,43 @@ __init int intel_pmu_init(void) name = "icelake"; break; + case INTEL_FAM6_SAPPHIRERAPIDS_X: + pmem = true; + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + x86_pmu.event_constraints = intel_spr_event_constraints; + x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; + x86_pmu.extra_regs = intel_spr_extra_regs; + x86_pmu.limit_period = spr_limit_period; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = spr_get_event_constraints; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_skl_attr = skl_format_attr; + mem_attr = spr_events_attrs; + td_attr = spr_td_events_attrs; + tsx_attr = spr_tsx_events_attrs; + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); + x86_pmu.lbr_pt_coexist = true; + intel_pmu_pebs_data_source_skl(pmem); + x86_pmu.num_topdown_events = 8; + x86_pmu.update_topdown_event = icl_update_topdown_event; + x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; + pr_cont("Sapphire Rapids events, "); + name = "sapphire_rapids"; + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2f54b1fbb895..7ebae1826403 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -36,7 +36,9 @@ union intel_x86_pebs_dse { unsigned int ld_dse:4; unsigned int ld_stlb_miss:1; unsigned int ld_locked:1; - unsigned int ld_reserved:26; + unsigned int ld_data_blk:1; + unsigned int ld_addr_blk:1; + unsigned int ld_reserved:24; }; struct { unsigned int st_l1d_hit:1; @@ -45,6 +47,12 @@ union intel_x86_pebs_dse { unsigned int st_locked:1; unsigned int st_reserved2:26; }; + struct { + unsigned int st_lat_dse:4; + unsigned int st_lat_stlb_miss:1; + unsigned int st_lat_locked:1; + unsigned int ld_reserved3:26; + }; }; @@ -198,6 +206,63 @@ static u64 load_latency_data(u64 status) if (dse.ld_locked) val |= P(LOCK, LOCKED); + /* + * Ice Lake and earlier models do not support block infos. + */ + if (!x86_pmu.pebs_block) { + val |= P(BLK, NA); + return val; + } + /* + * bit 6: load was blocked since its data could not be forwarded + * from a preceding store + */ + if (dse.ld_data_blk) + val |= P(BLK, DATA); + + /* + * bit 7: load was blocked due to potential address conflict with + * a preceding store + */ + if (dse.ld_addr_blk) + val |= P(BLK, ADDR); + + if (!dse.ld_data_blk && !dse.ld_addr_blk) + val |= P(BLK, NA); + + return val; +} + +static u64 store_latency_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val; + + dse.val = status; + + /* + * use the mapping table for bit 0-3 + */ + val = pebs_data_source[dse.st_lat_dse]; + + /* + * bit 4: TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (dse.st_lat_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* + * bit 5: locked prefix + */ + if (dse.st_lat_locked) + val |= P(LOCK, LOCKED); + + val |= P(BLK, NA); + return val; } @@ -870,6 +935,28 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_spr_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), + + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), + INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), + INTEL_PSD_CONSTRAINT(0x2cd, 0x1), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -1332,6 +1419,8 @@ static u64 get_data_src(struct perf_event *event, u64 aux) if (fl & PERF_X86_EVENT_PEBS_LDLAT) val = load_latency_data(aux); + else if (fl & PERF_X86_EVENT_PEBS_STLAT) + val = store_latency_data(aux); else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) val = precise_datala_hsw(event, aux); else if (fst) @@ -1508,6 +1597,9 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, #endif } +#define PEBS_LATENCY_MASK 0xffff +#define PEBS_CACHE_LATENCY_OFFSET 32 + /* * With adaptive PEBS the layout depends on what fields are configured. */ @@ -1578,9 +1670,27 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } if (format_size & PEBS_DATACFG_MEMINFO) { - if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) - data->weight.full = meminfo->latency ?: - intel_get_tsx_weight(meminfo->tsx_tuning); + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { + u64 weight = meminfo->latency; + + if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) { + data->weight.var2_w = weight & PEBS_LATENCY_MASK; + weight >>= PEBS_CACHE_LATENCY_OFFSET; + } + + /* + * Although meminfo::latency is defined as a u64, + * only the lower 32 bits include the valid data + * in practice on Ice Lake and earlier platforms. + */ + if (sample_type & PERF_SAMPLE_WEIGHT) { + data->weight.full = weight ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + } else { + data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + } + } if (sample_type & PERF_SAMPLE_DATA_SRC) data->data_src.val = get_data_src(event, meminfo->aux); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 15343cc25d47..b8bf2ce23913 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -80,6 +80,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ #define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */ #define PERF_X86_EVENT_TOPDOWN 0x4000 /* Count Topdown slots/metrics events */ +#define PERF_X86_EVENT_PEBS_STLAT 0x8000 /* st+stlat data address sampling */ static inline bool is_topdown_count(struct perf_event *event) { @@ -443,6 +444,10 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) +#define INTEL_PSD_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_STLAT) + #define INTEL_PST_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) @@ -723,7 +728,8 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_block :1; int pebs_record_size; int pebs_buffer_size; int max_pebs_events; @@ -871,6 +877,8 @@ do { \ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ #define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ +#define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */ +#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -1157,6 +1165,8 @@ extern struct event_constraint intel_skl_pebs_event_constraints[]; extern struct event_constraint intel_icl_pebs_event_constraints[]; +extern struct event_constraint intel_spr_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7c2c3023532a..544f41a179fb 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -261,8 +261,12 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_TD_BAD_SPEC (INTEL_PMC_IDX_METRIC_BASE + 1) #define INTEL_PMC_IDX_TD_FE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 2) #define INTEL_PMC_IDX_TD_BE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 3) -#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_BE_BOUND -#define INTEL_PMC_MSK_TOPDOWN ((0xfull << INTEL_PMC_IDX_METRIC_BASE) | \ +#define INTEL_PMC_IDX_TD_HEAVY_OPS (INTEL_PMC_IDX_METRIC_BASE + 4) +#define INTEL_PMC_IDX_TD_BR_MISPREDICT (INTEL_PMC_IDX_METRIC_BASE + 5) +#define INTEL_PMC_IDX_TD_FETCH_LAT (INTEL_PMC_IDX_METRIC_BASE + 6) +#define INTEL_PMC_IDX_TD_MEM_BOUND (INTEL_PMC_IDX_METRIC_BASE + 7) +#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_MEM_BOUND +#define INTEL_PMC_MSK_TOPDOWN ((0xffull << INTEL_PMC_IDX_METRIC_BASE) | \ INTEL_PMC_MSK_FIXED_SLOTS) /* diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b2cc246ec119..7d292de51410 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1146,14 +1146,16 @@ union perf_mem_data_src { mem_lvl_num:4, /* memory hierarchy level number */ mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ - mem_rsvd:24; + mem_blk:3, /* access blocked */ + mem_rsvd:21; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:24, + __u64 mem_rsvd:21, + mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ mem_lvl_num:4, /* memory hierarchy level number */ @@ -1236,6 +1238,12 @@ union perf_mem_data_src { #define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ #define PERF_MEM_TLB_SHIFT 26 +/* Access blocked */ +#define PERF_MEM_BLK_NA 0x01 /* not available */ +#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3 From 269bbe5fd4d2fdd3b0d3a82a3c3c1dd1209aa8b8 Mon Sep 17 00:00:00 2001 From: Bijan Mottahedeh Date: Fri, 15 Jan 2021 17:37:44 +0000 Subject: io_uring: rename file related variables to rsrc This is a prep rename patch for subsequent patches to generalize file registration. [io_uring_rsrc_update:: rename fds -> data] Reviewed-by: Pavel Begunkov Signed-off-by: Bijan Mottahedeh [leave io_uring_files_update as struct] Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 228 ++++++++++++++++++++++-------------------- include/uapi/linux/io_uring.h | 7 ++ 2 files changed, 124 insertions(+), 111 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 4cdf0f906f12..95b3b8747a65 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -195,24 +195,29 @@ struct io_mapped_ubuf { unsigned long acct_pages; }; -struct fixed_file_table { +struct io_rsrc_put { + struct list_head list; + struct file *file; +}; + +struct fixed_rsrc_table { struct file **files; }; -struct fixed_file_ref_node { +struct fixed_rsrc_ref_node { struct percpu_ref refs; struct list_head node; - struct list_head file_list; - struct fixed_file_data *file_data; + struct list_head rsrc_list; + struct fixed_rsrc_data *rsrc_data; struct llist_node llist; bool done; }; -struct fixed_file_data { - struct fixed_file_table *table; +struct fixed_rsrc_data { + struct fixed_rsrc_table *table; struct io_ring_ctx *ctx; - struct fixed_file_ref_node *node; + struct fixed_rsrc_ref_node *node; struct percpu_ref refs; struct completion done; struct list_head ref_list; @@ -319,7 +324,7 @@ struct io_ring_ctx { * readers must ensure that ->refs is alive as long as the file* is * used. Only updated through io_uring_register(2). */ - struct fixed_file_data *file_data; + struct fixed_rsrc_data *file_data; unsigned nr_user_files; /* if used, fixed mapped user buffers */ @@ -384,8 +389,8 @@ struct io_ring_ctx { struct list_head inflight_list; } ____cacheline_aligned_in_smp; - struct delayed_work file_put_work; - struct llist_head file_put_llist; + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; struct work_struct exit_work; struct io_restriction restrictions; @@ -494,7 +499,7 @@ struct io_open { unsigned long nofile; }; -struct io_files_update { +struct io_rsrc_update { struct file *file; u64 arg; u32 nr_args; @@ -688,7 +693,7 @@ struct io_kiocb { struct io_sr_msg sr_msg; struct io_open open; struct io_close close; - struct io_files_update files_update; + struct io_rsrc_update rsrc_update; struct io_fadvise fadvise; struct io_madvise madvise; struct io_epoll epoll; @@ -718,7 +723,7 @@ struct io_kiocb { u64 user_data; struct io_kiocb *link; - struct percpu_ref *fixed_file_refs; + struct percpu_ref *fixed_rsrc_refs; /* * 1. used with ctx->iopoll_list with reads/writes @@ -996,8 +1001,8 @@ enum io_mem_account { static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, struct task_struct *task); -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( +static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node); +static struct fixed_rsrc_ref_node *alloc_fixed_file_ref_node( struct io_ring_ctx *ctx); static void __io_complete_rw(struct io_kiocb *req, long res, long res2, @@ -1010,13 +1015,13 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); static void __io_queue_linked_timeout(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *ip, + struct io_uring_rsrc_update *ip, unsigned nr_args); static void __io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_submit_state *state, struct io_kiocb *req, int fd, bool fixed); static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs); -static void io_file_put_work(struct work_struct *work); +static void io_rsrc_put_work(struct work_struct *work); static ssize_t io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter, @@ -1057,9 +1062,9 @@ static inline void io_set_resource_node(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!req->fixed_file_refs) { - req->fixed_file_refs = &ctx->file_data->node->refs; - percpu_ref_get(req->fixed_file_refs); + if (!req->fixed_rsrc_refs) { + req->fixed_rsrc_refs = &ctx->file_data->node->refs; + percpu_ref_get(req->fixed_rsrc_refs); } } @@ -1330,8 +1335,8 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->timeout_list); spin_lock_init(&ctx->inflight_lock); INIT_LIST_HEAD(&ctx->inflight_list); - INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work); - init_llist_head(&ctx->file_put_llist); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); return ctx; err: if (ctx->fallback_req) @@ -2011,8 +2016,8 @@ static void io_dismantle_req(struct io_kiocb *req) kfree(req->async_data); if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - if (req->fixed_file_refs) - percpu_ref_put(req->fixed_file_refs); + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); io_req_clean_work(req); } @@ -5988,7 +5993,7 @@ static int io_async_cancel(struct io_kiocb *req) return 0; } -static int io_files_update_prep(struct io_kiocb *req, +static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) @@ -5998,11 +6003,11 @@ static int io_files_update_prep(struct io_kiocb *req, if (sqe->ioprio || sqe->rw_flags) return -EINVAL; - req->files_update.offset = READ_ONCE(sqe->off); - req->files_update.nr_args = READ_ONCE(sqe->len); - if (!req->files_update.nr_args) + req->rsrc_update.offset = READ_ONCE(sqe->off); + req->rsrc_update.nr_args = READ_ONCE(sqe->len); + if (!req->rsrc_update.nr_args) return -EINVAL; - req->files_update.arg = READ_ONCE(sqe->addr); + req->rsrc_update.arg = READ_ONCE(sqe->addr); return 0; } @@ -6010,17 +6015,17 @@ static int io_files_update(struct io_kiocb *req, bool force_nonblock, struct io_comp_state *cs) { struct io_ring_ctx *ctx = req->ctx; - struct io_uring_files_update up; + struct io_uring_rsrc_update up; int ret; if (force_nonblock) return -EAGAIN; - up.offset = req->files_update.offset; - up.fds = req->files_update.arg; + up.offset = req->rsrc_update.offset; + up.data = req->rsrc_update.arg; mutex_lock(&ctx->uring_lock); - ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args); + ret = __io_sqe_files_update(ctx, &up, req->rsrc_update.nr_args); mutex_unlock(&ctx->uring_lock); if (ret < 0) @@ -6075,7 +6080,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_CLOSE: return io_close_prep(req, sqe); case IORING_OP_FILES_UPDATE: - return io_files_update_prep(req, sqe); + return io_rsrc_update_prep(req, sqe); case IORING_OP_STATX: return io_statx_prep(req, sqe); case IORING_OP_FADVISE: @@ -6444,7 +6449,7 @@ static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { - struct fixed_file_table *table; + struct fixed_rsrc_table *table; table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT]; return table->files[index & IORING_FILE_TABLE_MASK]; @@ -6840,7 +6845,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->ctx = ctx; req->flags = 0; req->link = NULL; - req->fixed_file_refs = NULL; + req->fixed_rsrc_refs = NULL; /* one is dropped after submission, the other at completion */ refcount_set(&req->refs, 2); req->task = current; @@ -7328,28 +7333,28 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) #endif } -static void io_file_ref_kill(struct percpu_ref *ref) +static void io_rsrc_ref_kill(struct percpu_ref *ref) { - struct fixed_file_data *data; + struct fixed_rsrc_data *data; - data = container_of(ref, struct fixed_file_data, refs); + data = container_of(ref, struct fixed_rsrc_data, refs); complete(&data->done); } -static void io_sqe_files_set_node(struct fixed_file_data *file_data, - struct fixed_file_ref_node *ref_node) +static void io_sqe_rsrc_set_node(struct fixed_rsrc_data *rsrc_data, + struct fixed_rsrc_ref_node *ref_node) { - spin_lock_bh(&file_data->lock); - file_data->node = ref_node; - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); + spin_lock_bh(&rsrc_data->lock); + rsrc_data->node = ref_node; + list_add_tail(&ref_node->node, &rsrc_data->ref_list); + spin_unlock_bh(&rsrc_data->lock); + percpu_ref_get(&rsrc_data->refs); } static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *backup_node, *ref_node = NULL; + struct fixed_rsrc_data *data = ctx->file_data; + struct fixed_rsrc_ref_node *backup_node, *ref_node = NULL; unsigned nr_tables, i; int ret; @@ -7368,7 +7373,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) percpu_ref_kill(&data->refs); /* wait for all refs nodes to complete */ - flush_delayed_work(&ctx->file_put_work); + flush_delayed_work(&ctx->rsrc_put_work); do { ret = wait_for_completion_interruptible(&data->done); if (!ret) @@ -7377,7 +7382,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) if (ret < 0) { percpu_ref_resurrect(&data->refs); reinit_completion(&data->done); - io_sqe_files_set_node(data, backup_node); + io_sqe_rsrc_set_node(data, backup_node); return ret; } } while (1); @@ -7391,7 +7396,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) kfree(data); ctx->file_data = NULL; ctx->nr_user_files = 0; - destroy_fixed_file_ref_node(backup_node); + destroy_fixed_rsrc_ref_node(backup_node); return 0; } @@ -7614,13 +7619,13 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif -static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, +static int io_sqe_alloc_file_tables(struct fixed_rsrc_data *file_data, unsigned nr_tables, unsigned nr_files) { int i; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; + struct fixed_rsrc_table *table = &file_data->table[i]; unsigned this_files; this_files = min(nr_files, IORING_MAX_FILES_TABLE); @@ -7635,7 +7640,7 @@ static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, return 0; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; + struct fixed_rsrc_table *table = &file_data->table[i]; kfree(table->files); } return 1; @@ -7703,56 +7708,51 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) #endif } -struct io_file_put { - struct list_head list; - struct file *file; -}; - -static void __io_file_put_work(struct fixed_file_ref_node *ref_node) +static void __io_rsrc_put_work(struct fixed_rsrc_ref_node *ref_node) { - struct fixed_file_data *file_data = ref_node->file_data; - struct io_ring_ctx *ctx = file_data->ctx; - struct io_file_put *pfile, *tmp; + struct fixed_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; - list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) { - list_del(&pfile->list); - io_ring_file_put(ctx, pfile->file); - kfree(pfile); + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + io_ring_file_put(ctx, prsrc->file); + kfree(prsrc); } percpu_ref_exit(&ref_node->refs); kfree(ref_node); - percpu_ref_put(&file_data->refs); + percpu_ref_put(&rsrc_data->refs); } -static void io_file_put_work(struct work_struct *work) +static void io_rsrc_put_work(struct work_struct *work) { struct io_ring_ctx *ctx; struct llist_node *node; - ctx = container_of(work, struct io_ring_ctx, file_put_work.work); - node = llist_del_all(&ctx->file_put_llist); + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); while (node) { - struct fixed_file_ref_node *ref_node; + struct fixed_rsrc_ref_node *ref_node; struct llist_node *next = node->next; - ref_node = llist_entry(node, struct fixed_file_ref_node, llist); - __io_file_put_work(ref_node); + ref_node = llist_entry(node, struct fixed_rsrc_ref_node, llist); + __io_rsrc_put_work(ref_node); node = next; } } -static void io_file_data_ref_zero(struct percpu_ref *ref) +static void io_rsrc_data_ref_zero(struct percpu_ref *ref) { - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *data; + struct fixed_rsrc_ref_node *ref_node; + struct fixed_rsrc_data *data; struct io_ring_ctx *ctx; bool first_add = false; int delay = HZ; - ref_node = container_of(ref, struct fixed_file_ref_node, refs); - data = ref_node->file_data; + ref_node = container_of(ref, struct fixed_rsrc_ref_node, refs); + data = ref_node->rsrc_data; ctx = data->ctx; spin_lock_bh(&data->lock); @@ -7760,12 +7760,12 @@ static void io_file_data_ref_zero(struct percpu_ref *ref) while (!list_empty(&data->ref_list)) { ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + struct fixed_rsrc_ref_node, node); /* recycle ref nodes in order */ if (!ref_node->done) break; list_del(&ref_node->node); - first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + first_add |= llist_add(&ref_node->llist, &ctx->rsrc_put_llist); } spin_unlock_bh(&data->lock); @@ -7773,33 +7773,33 @@ static void io_file_data_ref_zero(struct percpu_ref *ref) delay = 0; if (!delay) - mod_delayed_work(system_wq, &ctx->file_put_work, 0); + mod_delayed_work(system_wq, &ctx->rsrc_put_work, 0); else if (first_add) - queue_delayed_work(system_wq, &ctx->file_put_work, delay); + queue_delayed_work(system_wq, &ctx->rsrc_put_work, delay); } -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( +static struct fixed_rsrc_ref_node *alloc_fixed_file_ref_node( struct io_ring_ctx *ctx) { - struct fixed_file_ref_node *ref_node; + struct fixed_rsrc_ref_node *ref_node; ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); if (!ref_node) return NULL; - if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, + if (percpu_ref_init(&ref_node->refs, io_rsrc_data_ref_zero, 0, GFP_KERNEL)) { kfree(ref_node); return NULL; } INIT_LIST_HEAD(&ref_node->node); - INIT_LIST_HEAD(&ref_node->file_list); - ref_node->file_data = ctx->file_data; + INIT_LIST_HEAD(&ref_node->rsrc_list); + ref_node->rsrc_data = ctx->file_data; ref_node->done = false; return ref_node; } -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node) +static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node) { percpu_ref_exit(&ref_node->refs); kfree(ref_node); @@ -7812,8 +7812,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_tables, i; struct file *file; int fd, ret = -ENOMEM; - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *file_data; + struct fixed_rsrc_ref_node *ref_node; + struct fixed_rsrc_data *file_data; if (ctx->file_data) return -EBUSY; @@ -7836,7 +7836,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, if (!file_data->table) goto out_free; - if (percpu_ref_init(&file_data->refs, io_file_ref_kill, + if (percpu_ref_init(&file_data->refs, io_rsrc_ref_kill, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto out_free; @@ -7845,7 +7845,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, ctx->file_data = file_data; for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct fixed_file_table *table; + struct fixed_rsrc_table *table; unsigned index; if (copy_from_user(&fd, &fds[i], sizeof(fd))) { @@ -7889,7 +7889,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -ENOMEM; } - io_sqe_files_set_node(file_data, ref_node); + io_sqe_rsrc_set_node(file_data, ref_node); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7952,28 +7952,34 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static int io_queue_file_removal(struct fixed_file_data *data, - struct file *file) +static int io_queue_rsrc_removal(struct fixed_rsrc_data *data, + struct file *rsrc) { - struct io_file_put *pfile; - struct fixed_file_ref_node *ref_node = data->node; + struct io_rsrc_put *prsrc; + struct fixed_rsrc_ref_node *ref_node = data->node; - pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); - if (!pfile) + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) return -ENOMEM; - pfile->file = file; - list_add(&pfile->list, &ref_node->file_list); + prsrc->file = rsrc; + list_add(&prsrc->list, &ref_node->rsrc_list); return 0; } +static inline int io_queue_file_removal(struct fixed_rsrc_data *data, + struct file *file) +{ + return io_queue_rsrc_removal(data, file); +} + static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *up, + struct io_uring_rsrc_update *up, unsigned nr_args) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node; + struct fixed_rsrc_data *data = ctx->file_data; + struct fixed_rsrc_ref_node *ref_node; struct file *file; __s32 __user *fds; int fd, i, err; @@ -7990,9 +7996,9 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, return -ENOMEM; done = 0; - fds = u64_to_user_ptr(up->fds); + fds = u64_to_user_ptr(up->data); while (nr_args) { - struct fixed_file_table *table; + struct fixed_rsrc_table *table; unsigned index; err = 0; @@ -8045,9 +8051,9 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); - io_sqe_files_set_node(data, ref_node); + io_sqe_rsrc_set_node(data, ref_node); } else - destroy_fixed_file_ref_node(ref_node); + destroy_fixed_rsrc_ref_node(ref_node); return done ? done : err; } @@ -8055,7 +8061,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { - struct io_uring_files_update up; + struct io_uring_rsrc_update up; if (!ctx->file_data) return -ENXIO; @@ -9482,7 +9488,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { - struct fixed_file_table *table; + struct fixed_rsrc_table *table; struct file *f; table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d31a2a1e8ef9..f9f106c54d90 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -285,12 +285,19 @@ enum { IORING_REGISTER_LAST }; +/* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; __u32 resv; __aligned_u64 /* __s32 * */ fds; }; +struct io_uring_rsrc_update { + __u32 offset; + __u32 resv; + __aligned_u64 data; +}; + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { -- cgit v1.2.3 From 4e0377a1c5c633852f443a562ec55f7dfea65350 Mon Sep 17 00:00:00 2001 From: noah Date: Tue, 26 Jan 2021 15:23:28 -0500 Subject: io_uring: Add skip option for __io_sqe_files_update This patch adds support for skipping a file descriptor when using IORING_REGISTER_FILES_UPDATE. __io_sqe_files_update will skip fds set to IORING_REGISTER_FILES_SKIP. IORING_REGISTER_FILES_SKIP is inturn added as a #define in io_uring.h Signed-off-by: noah Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 +++ include/uapi/linux/io_uring.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 0ca99bd5c316..dd83a64ba709 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8038,6 +8038,9 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EFAULT; break; } + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + i = array_index_nospec(up->offset + done, ctx->nr_user_files); table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; index = i & IORING_FILE_TABLE_MASK; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f9f106c54d90..ac4e1738a9af 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -298,6 +298,9 @@ struct io_uring_rsrc_update { __aligned_u64 data; }; +/* Skip updating fd indexes set to this value in the fd table */ +#define IORING_REGISTER_FILES_SKIP (-2) + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { -- cgit v1.2.3 From c98fe7c2a2038af2bc24f039ccdb5a65c22ba11a Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:04 -0800 Subject: vfio: option to unmap all For the UNMAP_DMA ioctl, delete all mappings if VFIO_DMA_UNMAP_FLAG_ALL is set. Define the corresponding VFIO_UNMAP_ALL extension. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d1812777139f..78462599e5ed 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -46,6 +46,9 @@ */ #define VFIO_NOIOMMU_IOMMU 8 +/* Supports VFIO_DMA_UNMAP_FLAG_ALL */ +#define VFIO_UNMAP_ALL 9 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -1102,6 +1105,7 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap * before unmapping IO virtual addresses. When this flag is set, the user must * provide a struct vfio_bitmap in data[]. User must provide zero-allocated @@ -1111,11 +1115,15 @@ struct vfio_bitmap { * indicates that the page at that offset from iova is dirty. A Bitmap of the * pages in the range of unmapped size is returned in the user-provided * vfio_bitmap.data. + * + * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size + * must be 0. This cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) +#define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; -- cgit v1.2.3 From 441e8106a238920f28e2e79cff462044551f60e2 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:07 -0800 Subject: vfio: interfaces to update vaddr Define interfaces that allow the underlying memory object of an iova range to be mapped to a new host virtual address in the host process: - VFIO_DMA_UNMAP_FLAG_VADDR for VFIO_IOMMU_UNMAP_DMA - VFIO_DMA_MAP_FLAG_VADDR flag for VFIO_IOMMU_MAP_DMA - VFIO_UPDATE_VADDR extension for VFIO_CHECK_EXTENSION Unmap vaddr invalidates the host virtual address in an iova range, and blocks vfio translation of host virtual addresses. DMA to already-mapped pages continues. Map vaddr updates the base VA and resumes translation. See comments in uapi/linux/vfio.h for more details. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 78462599e5ed..8ce36c1d53ca 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -49,6 +49,9 @@ /* Supports VFIO_DMA_UNMAP_FLAG_ALL */ #define VFIO_UNMAP_ALL 9 +/* Supports the vaddr flag for DMA map and unmap */ +#define VFIO_UPDATE_VADDR 10 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -1077,12 +1080,22 @@ struct vfio_iommu_type1_info_dma_avail { * * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + * + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and + * unblock translation of host virtual addresses in the iova range. The vaddr + * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To + * maintain memory consistency within the user application, the updated vaddr + * must address the same memory object as originally mapped. Failure to do so + * will result in user memory corruption and/or device misbehavior. iova and + * size must match those in the original MAP_DMA call. Protection is not + * changed, and the READ & WRITE flags must be 0. */ struct vfio_iommu_type1_dma_map { __u32 argsz; __u32 flags; #define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ +#define VFIO_DMA_MAP_FLAG_VADDR (1 << 2) __u64 vaddr; /* Process virtual address */ __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ @@ -1118,12 +1131,18 @@ struct vfio_bitmap { * * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size * must be 0. This cannot be combined with the get-dirty-bitmap flag. + * + * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host + * virtual addresses in the iova range. Tasks that attempt to translate an + * iova's vaddr will block. DMA to already-mapped pages continues. This + * cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) #define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) +#define VFIO_DMA_UNMAP_FLAG_VADDR (1 << 2) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; -- cgit v1.2.3 From c7020068bf2397b60bb62a1f71ca0fe626c1f7e7 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sun, 20 Sep 2020 04:58:57 +0300 Subject: tee: fix some comment typos in header files struct tee_param: revc -> recv. TEE_IOC_SUPPL_SEND: typo introduced by copy-pasting, replace invalid description with description from the according argument struct. Signed-off-by: Elvira Khabirova Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 2 +- include/uapi/linux/tee.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index cdd049a724b1..54269e47ac9a 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -88,7 +88,7 @@ struct tee_param { * @close_session: close a session * @invoke_func: invoke a trusted function * @cancel_req: request cancel of an ongoing invoke or open - * @supp_revc: called for supplicant to get a command + * @supp_recv: called for supplicant to get a command * @supp_send: called for supplicant to send a response * @shm_register: register shared memory buffer in TEE * @shm_unregister: unregister shared memory buffer in TEE diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index d67cadf221fc..25a6c534beb1 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -355,7 +355,7 @@ struct tee_iocl_supp_send_arg { }; /** - * TEE_IOC_SUPPL_SEND - Receive a request for a supplicant function + * TEE_IOC_SUPPL_SEND - Send a response to a received request * * Takes a struct tee_ioctl_buf_data which contains a struct * tee_iocl_supp_send_arg followed by any array of struct tee_param -- cgit v1.2.3 From 012ce4dd3102a0f4d80167de343e9d44b257c1b8 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:06 +0200 Subject: ethtool: Extend link modes settings uAPI with lanes Currently, when auto negotiation is on, the user can advertise all the linkmodes which correspond to a specific speed, but does not have a similar selector for the number of lanes. This is significant when a specific speed can be achieved using different number of lanes. For example, 2x50 or 4x25. Add 'ETHTOOL_A_LINKMODES_LANES' attribute and expand 'struct ethtool_link_settings' with lanes field in order to implement a new lanes-selector that will enable the user to advertise a specific number of lanes as well. When auto negotiation is off, lanes parameter can be forced only if the driver supports it. Add a capability bit in 'struct ethtool_ops' that allows ethtool know if the driver can handle the lanes parameter when auto negotiation is off, so if it does not, an error message will be returned when trying to set lanes. Example: $ ethtool -s swp1 lanes 4 $ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseKX/Full 10000baseKR/Full 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 25000baseCR/Full 25000baseSR/Full 50000baseCR2/Full 100000baseSR4/Full 100000baseCR4/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Supported FEC modes: Not reported Advertised link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Advertised FEC modes: Not reported Speed: Unknown! Duplex: Unknown! (255) Auto-negotiation: on Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Link detected: no Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 11 ++-- include/linux/ethtool.h | 4 ++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/linkmodes.c | 96 +++++++++++++++++++++++----- net/ethtool/netlink.h | 2 +- 5 files changed, 93 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 30b98245979f..05073482db05 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -431,16 +431,17 @@ Request contents: ``ETHTOOL_A_LINKMODES_SPEED`` u32 link speed (Mb/s) ``ETHTOOL_A_LINKMODES_DUPLEX`` u8 duplex mode ``ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG`` u8 Master/slave port mode + ``ETHTOOL_A_LINKMODES_LANES`` u32 lanes ========================================== ====== ========================== ``ETHTOOL_A_LINKMODES_OURS`` bit set allows setting advertised link modes. If autonegotiation is on (either set now or kept from before), advertised modes are not changed (no ``ETHTOOL_A_LINKMODES_OURS`` attribute) and at least one -of speed and duplex is specified, kernel adjusts advertised modes to all -supported modes matching speed, duplex or both (whatever is specified). This -autoselection is done on ethtool side with ioctl interface, netlink interface -is supposed to allow requesting changes without knowing what exactly kernel -supports. +of speed, duplex and lanes is specified, kernel adjusts advertised modes to all +supported modes matching speed, duplex, lanes or all (whatever is specified). +This autoselection is done on ethtool side with ioctl interface, netlink +interface is supposed to allow requesting changes without knowing what exactly +kernel supports. LINKSTATE_GET diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e3da25b51ae4..1ab13c5dfb2f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -128,6 +128,7 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; + u32 lanes; }; /** @@ -265,6 +266,8 @@ struct ethtool_pause_stats { /** * struct ethtool_ops - optional netdev operations + * @cap_link_lanes_supported: indicates if the driver supports lanes + * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -420,6 +423,7 @@ struct ethtool_pause_stats { * of the generic netdev features interface. */ struct ethtool_ops { + u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index e2bf36e6964b..a286635ac9b8 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -227,6 +227,7 @@ enum { ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */ + ETHTOOL_A_LINKMODES_LANES, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKMODES_CNT, diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index bb8a3351fb72..db3e31fc6709 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -152,12 +152,47 @@ const struct ethnl_request_ops ethnl_linkmodes_request_ops = { struct link_mode_info { int speed; + u8 lanes; u8 duplex; }; -#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ - [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ - .speed = SPEED_ ## _speed, \ +#define __LINK_MODE_LANES_CR 1 +#define __LINK_MODE_LANES_CR2 2 +#define __LINK_MODE_LANES_CR4 4 +#define __LINK_MODE_LANES_CR8 8 +#define __LINK_MODE_LANES_DR 1 +#define __LINK_MODE_LANES_DR2 2 +#define __LINK_MODE_LANES_DR4 4 +#define __LINK_MODE_LANES_DR8 8 +#define __LINK_MODE_LANES_KR 1 +#define __LINK_MODE_LANES_KR2 2 +#define __LINK_MODE_LANES_KR4 4 +#define __LINK_MODE_LANES_KR8 8 +#define __LINK_MODE_LANES_SR 1 +#define __LINK_MODE_LANES_SR2 2 +#define __LINK_MODE_LANES_SR4 4 +#define __LINK_MODE_LANES_SR8 8 +#define __LINK_MODE_LANES_ER 1 +#define __LINK_MODE_LANES_KX 1 +#define __LINK_MODE_LANES_KX4 4 +#define __LINK_MODE_LANES_LR 1 +#define __LINK_MODE_LANES_LR4 4 +#define __LINK_MODE_LANES_LR4_ER4 4 +#define __LINK_MODE_LANES_LR_ER_FR 1 +#define __LINK_MODE_LANES_LR2_ER2_FR2 2 +#define __LINK_MODE_LANES_LR4_ER4_FR4 4 +#define __LINK_MODE_LANES_LR8_ER8_FR8 8 +#define __LINK_MODE_LANES_LRM 1 +#define __LINK_MODE_LANES_MLD2 2 +#define __LINK_MODE_LANES_T 1 +#define __LINK_MODE_LANES_T1 1 +#define __LINK_MODE_LANES_X 1 +#define __LINK_MODE_LANES_FX 1 + +#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ + [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ + .speed = SPEED_ ## _speed, \ + .lanes = __LINK_MODE_LANES_ ## _type, \ .duplex = __DUPLEX_ ## _duplex \ } #define __DUPLEX_Half DUPLEX_HALF @@ -165,6 +200,7 @@ struct link_mode_info { #define __DEFINE_SPECIAL_MODE_PARAMS(_mode) \ [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = { \ .speed = SPEED_UNKNOWN, \ + .lanes = 0, \ .duplex = DUPLEX_UNKNOWN, \ } @@ -274,16 +310,17 @@ const struct nla_policy ethnl_linkmodes_set_policy[] = { [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKMODES_LANES] = NLA_POLICY_RANGE(NLA_U32, 1, 8), }; -/* Set advertised link modes to all supported modes matching requested speed - * and duplex values. Called when autonegotiation is on, speed or duplex is - * requested but no link mode change. This is done in userspace with ioctl() - * interface, move it into kernel for netlink. +/* Set advertised link modes to all supported modes matching requested speed, + * lanes and duplex values. Called when autonegotiation is on, speed, lanes or + * duplex is requested but no link mode change. This is done in userspace with + * ioctl() interface, move it into kernel for netlink. * Returns true if advertised modes bitmap was modified. */ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, - bool req_speed, bool req_duplex) + bool req_speed, bool req_lanes, bool req_duplex) { unsigned long *advertising = ksettings->link_modes.advertising; unsigned long *supported = ksettings->link_modes.supported; @@ -302,6 +339,7 @@ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, continue; if (test_bit(i, supported) && (!req_speed || info->speed == ksettings->base.speed) && + (!req_lanes || info->lanes == ksettings->lanes) && (!req_duplex || info->duplex == ksettings->base.duplex)) set_bit(i, advertising); else @@ -327,7 +365,7 @@ static bool ethnl_validate_master_slave_cfg(u8 cfg) static int ethnl_check_linkmodes(struct genl_info *info, struct nlattr **tb) { - const struct nlattr *master_slave_cfg; + const struct nlattr *master_slave_cfg, *lanes_cfg; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg && @@ -337,16 +375,23 @@ static int ethnl_check_linkmodes(struct genl_info *info, struct nlattr **tb) return -EOPNOTSUPP; } + lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; + if (lanes_cfg && !is_power_of_2(nla_get_u32(lanes_cfg))) { + NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, + "lanes value is invalid"); + return -EINVAL; + } + return 0; } static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, - bool *mod) + bool *mod, const struct net_device *dev) { struct ethtool_link_settings *lsettings = &ksettings->base; - bool req_speed, req_duplex; - const struct nlattr *master_slave_cfg; + bool req_speed, req_lanes, req_duplex; + const struct nlattr *master_slave_cfg, *lanes_cfg; int ret; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; @@ -360,10 +405,30 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, *mod = false; req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; + req_lanes = tb[ETHTOOL_A_LINKMODES_LANES]; req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; ethnl_update_u8(&lsettings->autoneg, tb[ETHTOOL_A_LINKMODES_AUTONEG], mod); + + lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; + if (lanes_cfg) { + /* If autoneg is off and lanes parameter is not supported by the + * driver, return an error. + */ + if (!lsettings->autoneg && + !dev->ethtool_ops->cap_link_lanes_supported) { + NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, + "lanes configuration not supported by device"); + return -EOPNOTSUPP; + } + } else if (!lsettings->autoneg) { + /* If autoneg is off and lanes parameter is not passed from user, + * set the lanes parameter to 0. + */ + ksettings->lanes = 0; + } + ret = ethnl_update_bitset(ksettings->link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_LINKMODES_OURS], link_mode_names, @@ -372,13 +437,14 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, return ret; ethnl_update_u32(&lsettings->speed, tb[ETHTOOL_A_LINKMODES_SPEED], mod); + ethnl_update_u32(&ksettings->lanes, lanes_cfg, mod); ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], mod); ethnl_update_u8(&lsettings->master_slave_cfg, master_slave_cfg, mod); if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && - (req_speed || req_duplex) && - ethnl_auto_linkmodes(ksettings, req_speed, req_duplex)) + (req_speed || req_lanes || req_duplex) && + ethnl_auto_linkmodes(ksettings, req_speed, req_lanes, req_duplex)) *mod = true; return 0; @@ -420,7 +486,7 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) goto out_ops; } - ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod); + ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod, dev); if (ret < 0) goto out_ops; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index d8efec516d86..6eabd58d81bf 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -351,7 +351,7 @@ extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_O extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1]; -extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG + 1]; +extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_LANES + 1]; extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1]; extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1]; extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1]; -- cgit v1.2.3 From 2c07ded06427dd3339278487a1413d5e478f05f9 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 4 Jan 2021 09:17:49 -0600 Subject: KVM/SVM: add support for SEV attestation command The SEV FW version >= 0.23 added a new command that can be used to query the attestation report containing the SHA-256 digest of the guest memory encrypted through the KVM_SEV_LAUNCH_UPDATE_{DATA, VMSA} commands and sign the report with the Platform Endorsement Key (PEK). See the SEV FW API spec section 6.8 for more details. Note there already exist a command (KVM_SEV_LAUNCH_MEASURE) that can be used to get the SHA-256 digest. The main difference between the KVM_SEV_LAUNCH_MEASURE and KVM_SEV_ATTESTATION_REPORT is that the latter can be called while the guest is running and the measurement value is signed with PEK. Cc: James Bottomley Cc: Tom Lendacky Cc: David Rientjes Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Borislav Petkov Cc: John Allen Cc: Herbert Xu Cc: linux-crypto@vger.kernel.org Reviewed-by: Tom Lendacky Acked-by: David Rientjes Tested-by: James Bottomley Signed-off-by: Brijesh Singh Message-Id: <20210104151749.30248-1-brijesh.singh@amd.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/amd-memory-encryption.rst | 21 +++++++ arch/x86/kvm/svm/sev.c | 71 ++++++++++++++++++++++++ drivers/crypto/ccp/sev-dev.c | 1 + include/linux/psp-sev.h | 17 ++++++ include/uapi/linux/kvm.h | 8 +++ 5 files changed, 118 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index 09a8f2a34e39..469a6308765b 100644 --- a/Documentation/virt/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst @@ -263,6 +263,27 @@ Returns: 0 on success, -negative on error __u32 trans_len; }; +10. KVM_SEV_GET_ATTESTATION_REPORT +---------------------------------- + +The KVM_SEV_GET_ATTESTATION_REPORT command can be used by the hypervisor to query the attestation +report containing the SHA-256 digest of the guest memory and VMSA passed through the KVM_SEV_LAUNCH +commands and signed with the PEK. The digest returned by the command should match the digest +used by the guest owner with the KVM_SEV_LAUNCH_MEASURE. + +Parameters (in): struct kvm_sev_attestation + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_attestation_report { + __u8 mnonce[16]; /* A random mnonce that will be placed in the report */ + + __u64 uaddr; /* userspace address where the report should be copied */ + __u32 len; + }; + References ========== diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 48017fef1cd9..8dfe8988be8d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1041,6 +1041,74 @@ e_unpin_memory: return ret; } +static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + void __user *report = (void __user *)(uintptr_t)argp->data; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_attestation_report *data; + struct kvm_sev_attestation_report params; + void __user *p; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) { + ret = -EINVAL; + goto e_free; + } + + ret = -ENOMEM; + blob = kmalloc(params.len, GFP_KERNEL); + if (!blob) + goto e_free; + + data->address = __psp_pa(blob); + data->len = params.len; + memcpy(data->mnonce, params.mnonce, sizeof(params.mnonce)); + } +cmd: + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, data, &argp->error); + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user(p, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data->len; + if (copy_to_user(report, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1091,6 +1159,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) case KVM_SEV_LAUNCH_SECRET: r = sev_launch_secret(kvm, &sev_cmd); break; + case KVM_SEV_GET_ATTESTATION_REPORT: + r = sev_get_attestation_report(kvm, &sev_cmd); + break; default: r = -EINVAL; goto out; diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 476113e12489..cb9b4c4e371e 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -128,6 +128,7 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_LAUNCH_UPDATE_SECRET: return sizeof(struct sev_data_launch_secret); case SEV_CMD_DOWNLOAD_FIRMWARE: return sizeof(struct sev_data_download_firmware); case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); + case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); default: return 0; } diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 49d155cd2dfe..b801ead1e2bb 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -66,6 +66,7 @@ enum sev_cmd { SEV_CMD_LAUNCH_MEASURE = 0x033, SEV_CMD_LAUNCH_UPDATE_SECRET = 0x034, SEV_CMD_LAUNCH_FINISH = 0x035, + SEV_CMD_ATTESTATION_REPORT = 0x036, /* Guest migration commands (outgoing) */ SEV_CMD_SEND_START = 0x040, @@ -483,6 +484,22 @@ struct sev_data_dbg { u32 len; /* In */ } __packed; +/** + * struct sev_data_attestation_report - SEV_ATTESTATION_REPORT command parameters + * + * @handle: handle of the VM + * @mnonce: a random nonce that will be included in the report. + * @address: physical address where the report will be copied. + * @len: length of the physical buffer. + */ +struct sev_data_attestation_report { + u32 handle; /* In */ + u32 reserved; + u64 address; /* In */ + u8 mnonce[16]; /* In */ + u32 len; /* In/Out */ +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 374c67875cdb..07c194e2c302 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1593,6 +1593,8 @@ enum sev_cmd_id { KVM_SEV_DBG_ENCRYPT, /* Guest certificates commands */ KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, KVM_SEV_NR_MAX, }; @@ -1645,6 +1647,12 @@ struct kvm_sev_dbg { __u32 len; }; +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) -- cgit v1.2.3 From fe6b6bc802b40081e8a7a1abe8d32b88d10a03e1 Mon Sep 17 00:00:00 2001 From: Chenyi Qiang Date: Fri, 6 Nov 2020 17:03:14 +0800 Subject: KVM: VMX: Enable bus lock VM exit Virtual Machine can exploit bus locks to degrade the performance of system. Bus lock can be caused by split locked access to writeback(WB) memory or by using locks on uncacheable(UC) memory. The bus lock is typically >1000 cycles slower than an atomic operation within a cache line. It also disrupts performance on other cores (which must wait for the bus lock to be released before their memory operations can complete). To address the threat, bus lock VM exit is introduced to notify the VMM when a bus lock was acquired, allowing it to enforce throttling or other policy based mitigations. A VMM can enable VM exit due to bus locks by setting a new "Bus Lock Detection" VM-execution control(bit 30 of Secondary Processor-based VM execution controls). If delivery of this VM exit was preempted by a higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of exit reason in vmcs field is set to 1. In current implementation, the KVM exposes this capability through KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap (i.e. off and exit) and enable it explicitly (disabled by default). If bus locks in guest are detected by KVM, exit to user space even when current exit reason is handled by KVM internally. Set a new field KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there is a bus lock detected in guest. Document for Bus Lock VM exit is now available at the latest "Intel Architecture Instruction Set Extensions Programming Reference". Document Link: https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Chenyi Qiang Message-Id: <20201106090315.18606-4-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 7 +++++++ arch/x86/include/asm/vmx.h | 1 + arch/x86/include/asm/vmxfeatures.h | 1 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/include/uapi/asm/vmx.h | 4 +++- arch/x86/kvm/vmx/capabilities.h | 6 ++++++ arch/x86/kvm/vmx/vmx.c | 37 +++++++++++++++++++++++++++++++++++-- arch/x86/kvm/vmx/vmx.h | 2 +- arch/x86/kvm/x86.c | 23 +++++++++++++++++++++++ include/uapi/linux/kvm.h | 5 +++++ 10 files changed, 83 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ed575c5655dd..c0706022d22f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -52,6 +52,9 @@ #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) +#define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ + KVM_BUS_LOCK_DETECTION_EXIT) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) @@ -996,6 +999,8 @@ struct kvm_arch { struct msr_bitmap_range ranges[16]; } msr_filter; + bool bus_lock_detection_enabled; + struct kvm_pmu_event_filter *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; @@ -1418,6 +1423,8 @@ extern u8 kvm_tsc_scaling_ratio_frac_bits; extern u64 kvm_max_tsc_scaling_ratio; /* 1ull << kvm_tsc_scaling_ratio_frac_bits */ extern u64 kvm_default_tsc_scaling_ratio; +/* bus lock detection supported? */ +extern bool kvm_has_bus_lock_exit; extern u64 kvm_mce_cap_supported; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 38ca445a8429..358707f60d99 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -73,6 +73,7 @@ #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) #define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) +#define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index 9915990fd8cf..d9a74681a77d 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -83,5 +83,6 @@ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ #define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ +#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 8e76d3701db3..5a3022c8af82 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -112,6 +112,7 @@ struct kvm_ioapic_state { #define KVM_NR_IRQCHIPS 3 #define KVM_RUN_X86_SMM (1 << 0) +#define KVM_RUN_X86_BUS_LOCK (1 << 1) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index ada955c5ebb6..b8e650a985e3 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -89,6 +89,7 @@ #define EXIT_REASON_XRSTORS 64 #define EXIT_REASON_UMWAIT 67 #define EXIT_REASON_TPAUSE 68 +#define EXIT_REASON_BUS_LOCK 74 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -150,7 +151,8 @@ { EXIT_REASON_XSAVES, "XSAVES" }, \ { EXIT_REASON_XRSTORS, "XRSTORS" }, \ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ - { EXIT_REASON_TPAUSE, "TPAUSE" } + { EXIT_REASON_TPAUSE, "TPAUSE" }, \ + { EXIT_REASON_BUS_LOCK, "BUS_LOCK" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 3a1861403d73..5366ccdd134c 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -262,6 +262,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void) SECONDARY_EXEC_TSC_SCALING; } +static inline bool cpu_has_vmx_bus_lock_detection(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_BUS_LOCK_DETECTION; +} + static inline bool cpu_has_vmx_apicv(void) { return cpu_has_vmx_apic_register_virt() && diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 880a2617820c..af8d3a2db3d2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2428,7 +2428,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC; + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_BUS_LOCK_DETECTION; if (cpu_has_sgx()) opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, @@ -4269,6 +4270,9 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG, ENABLE_USR_WAIT_PAUSE, false); + if (!vcpu->kvm->arch.bus_lock_detection_enabled) + exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; + vmx->secondary_exec_control = exec_control; } @@ -5600,6 +5604,13 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } +static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5656,6 +5667,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, + [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -5908,7 +5920,7 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); union vmx_exit_reason exit_reason = vmx->exit_reason; @@ -6061,6 +6073,25 @@ unexpected_vmexit: return 0; } +static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +{ + int ret = __vmx_handle_exit(vcpu, exit_fastpath); + + /* + * Even when current exit reason is handled by KVM internally, we + * still need to exit to user space when bus lock detected to inform + * that there is a bus lock in guest. + */ + if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { + if (ret > 0) + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; + } + return ret; +} + /* * Software based L1D cache flush which is used when microcode providing * the cache control MSR is not loaded. @@ -7812,6 +7843,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } + kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4dd71b7494ea..cf335e94f198 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -83,7 +83,7 @@ union vmx_exit_reason { u32 reserved23 : 1; u32 reserved24 : 1; u32 reserved25 : 1; - u32 reserved26 : 1; + u32 bus_lock_detected : 1; u32 enclave_mode : 1; u32 smi_pending_mtf : 1; u32 smi_from_vmx_root : 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 90a2335498a2..8719877fe799 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,6 +136,8 @@ u64 __read_mostly kvm_max_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); u64 __read_mostly kvm_default_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); +bool __read_mostly kvm_has_bus_lock_exit; +EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; @@ -3843,6 +3845,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_STEAL_TIME: r = sched_info_on(); break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + if (kvm_has_bus_lock_exit) + r = KVM_BUS_LOCK_DETECTION_OFF | + KVM_BUS_LOCK_DETECTION_EXIT; + else + r = 0; + break; default: break; } @@ -5298,6 +5307,20 @@ split_irqchip_unlock: kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + r = -EINVAL; + if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) + break; + + if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && + (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) + break; + + if (kvm_has_bus_lock_exit && + cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) + kvm->arch.bus_lock_detection_enabled = true; + r = 0; + break; default: r = -EINVAL; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 07c194e2c302..dfe3ba5cf262 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -252,6 +252,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 #define KVM_EXIT_AP_RESET_HOLD 32 +#define KVM_EXIT_X86_BUS_LOCK 33 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -1058,6 +1059,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 +#define KVM_CAP_X86_BUS_LOCK_EXIT 193 #ifdef KVM_CAP_IRQ_ROUTING @@ -1774,4 +1776,7 @@ struct kvm_dirty_gfn { __u64 offset; }; +#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) +#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From 23200b7a30de315d0e9a40663c905869d29d833c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 13 Jun 2018 09:55:44 -0400 Subject: KVM: x86/xen: intercept xen hypercalls if enabled Add a new exit reason for emulator to handle Xen hypercalls. Since this means KVM owns the ABI, dispense with the facility for the VMM to provide its own copy of the hypercall pages; just fill them in directly using VMCALL/VMMCALL as we do for the Hyper-V hypercall page. This behaviour is enabled by a new INTERCEPT_HCALL flag in the KVM_XEN_HVM_CONFIG ioctl structure, and advertised by the same flag being returned from the KVM_CAP_XEN_HVM check. Rename xen_hvm_config() to kvm_xen_write_hypercall_page() and move it to the nascent xen.c while we're at it, and add a test case. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 6 + arch/x86/kvm/Makefile | 2 +- arch/x86/kvm/trace.h | 36 ++++++ arch/x86/kvm/x86.c | 49 +++---- arch/x86/kvm/xen.c | 142 +++++++++++++++++++++ arch/x86/kvm/xen.h | 21 +++ include/uapi/linux/kvm.h | 20 +++ tools/testing/selftests/kvm/Makefile | 1 + tools/testing/selftests/kvm/lib/kvm_util.c | 1 + .../testing/selftests/kvm/x86_64/xen_vmcall_test.c | 123 ++++++++++++++++++ 10 files changed, 369 insertions(+), 32 deletions(-) create mode 100644 arch/x86/kvm/xen.c create mode 100644 arch/x86/kvm/xen.h create mode 100644 tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index bcbb32ef9f00..b4bcdebd6e4c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -531,6 +531,11 @@ struct kvm_vcpu_hv { cpumask_t tlb_flush; }; +/* Xen HVM per vcpu emulation context */ +struct kvm_vcpu_xen { + u64 hypercall_rip; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -729,6 +734,7 @@ struct kvm_vcpu_arch { unsigned long singlestep_rip; struct kvm_vcpu_hv hyperv; + struct kvm_vcpu_xen xen; cpumask_var_t wbinvd_dirty_mask; diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 4bd14ab01323..a50041235530 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -14,7 +14,7 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ $(KVM)/dirty_ring.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o -kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ +kvm-y += x86.o emulate.o i8259.o irq.o lapic.o xen.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o mmu/tdp_iter.o mmu/tdp_mmu.o diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 5ef238621881..a61c015870e3 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -92,6 +92,42 @@ TRACE_EVENT(kvm_hv_hypercall, __entry->outgpa) ); +/* + * Tracepoint for Xen hypercall. + */ +TRACE_EVENT(kvm_xen_hypercall, + TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5), + TP_ARGS(nr, a0, a1, a2, a3, a4, a5), + + TP_STRUCT__entry( + __field(unsigned long, nr) + __field(unsigned long, a0) + __field(unsigned long, a1) + __field(unsigned long, a2) + __field(unsigned long, a3) + __field(unsigned long, a4) + __field(unsigned long, a5) + ), + + TP_fast_assign( + __entry->nr = nr; + __entry->a0 = a0; + __entry->a1 = a1; + __entry->a2 = a2; + __entry->a3 = a3; + __entry->a4 = a4; + __entry->a4 = a5; + ), + + TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", + __entry->nr, __entry->a0, __entry->a1, __entry->a2, + __entry->a3, __entry->a4, __entry->a5) +); + + + /* * Tracepoint for PIO. */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 34ca136a608e..5a41d465134d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -29,6 +29,7 @@ #include "pmu.h" #include "hyperv.h" #include "lapic.h" +#include "xen.h" #include #include @@ -2870,34 +2871,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - int lm = is_long_mode(vcpu); - u64 blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64 - : kvm->arch.xen_hvm_config.blob_addr_32; - u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 - : kvm->arch.xen_hvm_config.blob_size_32; - u32 page_num = data & ~PAGE_MASK; - u64 page_addr = data & PAGE_MASK; - u8 *page; - - if (page_num >= blob_size) - return 1; - - blob_addr += page_num * PAGE_SIZE; - - page = memdup_user((u8 __user *)blob_addr, PAGE_SIZE); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); - return 1; - } - return 0; -} - static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; @@ -3032,7 +3005,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) u64 data = msr_info->data; if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr) - return xen_hvm_config(vcpu, data); + return kvm_xen_write_hypercall_page(vcpu, data); switch (msr) { case MSR_AMD64_NB_CFG: @@ -3741,7 +3714,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: - case KVM_CAP_XEN_HVM: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: @@ -3781,6 +3753,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: r = 1; break; + case KVM_CAP_XEN_HVM: + r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL; + break; case KVM_CAP_SYNC_REGS: r = KVM_SYNC_X86_VALID_FIELDS; break; @@ -5652,7 +5628,15 @@ set_pit2_out: if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; r = -EINVAL; - if (xhc.flags) + if (xhc.flags & ~KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) + goto out; + /* + * With hypercall interception the kernel generates its own + * hypercall page so it must not be provided. + */ + if ((xhc.flags & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) && + (xhc.blob_addr_32 || xhc.blob_addr_64 || + xhc.blob_size_32 || xhc.blob_size_64)) goto out; memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc)); r = 0; @@ -8143,6 +8127,9 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit; + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c new file mode 100644 index 000000000000..62569ca43857 --- /dev/null +++ b/arch/x86/kvm/xen.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2019 Oracle and/or its affiliates. All rights reserved. + * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * KVM Xen emulation + */ + +#include "x86.h" +#include "xen.h" + +#include + +#include + +#include "trace.h" + +int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + + /* + * If Xen hypercall intercept is enabled, fill the hypercall + * page with VMCALL/VMMCALL instructions since that's what + * we catch. Else the VMM has provided the hypercall pages + * with instructions of its own choosing, so use those. + */ + if (kvm_xen_hypercall_enabled(kvm)) { + u8 instructions[32]; + int i; + + if (page_num) + return 1; + + /* mov imm32, %eax */ + instructions[0] = 0xb8; + + /* vmcall / vmmcall */ + kvm_x86_ops.patch_hypercall(vcpu, instructions + 5); + + /* ret */ + instructions[8] = 0xc3; + + /* int3 to pad */ + memset(instructions + 9, 0xcc, sizeof(instructions) - 9); + + for (i = 0; i < PAGE_SIZE / sizeof(instructions); i++) { + *(u32 *)&instructions[1] = i; + if (kvm_vcpu_write_guest(vcpu, + page_addr + (i * sizeof(instructions)), + instructions, sizeof(instructions))) + return 1; + } + } else { + int lm = is_long_mode(vcpu); + u64 blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64 + : kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u8 *page; + + if (page_num >= blob_size) + return 1; + + blob_addr += page_num * PAGE_SIZE; + + page = memdup_user((u8 __user *)blob_addr, PAGE_SIZE); + if (IS_ERR(page)) + return PTR_ERR(page); + + if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { + kfree(page); + return 1; + } + } + return 0; +} + +static int kvm_xen_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) +{ + kvm_rax_write(vcpu, result); + return kvm_skip_emulated_instruction(vcpu); +} + +static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.xen.hypercall_rip))) + return 1; + + return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); +} + +int kvm_xen_hypercall(struct kvm_vcpu *vcpu) +{ + bool longmode; + u64 input, params[6]; + + input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); + + longmode = is_64_bit_mode(vcpu); + if (!longmode) { + params[0] = (u32)kvm_rbx_read(vcpu); + params[1] = (u32)kvm_rcx_read(vcpu); + params[2] = (u32)kvm_rdx_read(vcpu); + params[3] = (u32)kvm_rsi_read(vcpu); + params[4] = (u32)kvm_rdi_read(vcpu); + params[5] = (u32)kvm_rbp_read(vcpu); + } +#ifdef CONFIG_X86_64 + else { + params[0] = (u64)kvm_rdi_read(vcpu); + params[1] = (u64)kvm_rsi_read(vcpu); + params[2] = (u64)kvm_rdx_read(vcpu); + params[3] = (u64)kvm_r10_read(vcpu); + params[4] = (u64)kvm_r8_read(vcpu); + params[5] = (u64)kvm_r9_read(vcpu); + } +#endif + trace_kvm_xen_hypercall(input, params[0], params[1], params[2], + params[3], params[4], params[5]); + + vcpu->run->exit_reason = KVM_EXIT_XEN; + vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; + vcpu->run->xen.u.hcall.longmode = longmode; + vcpu->run->xen.u.hcall.cpl = kvm_x86_ops.get_cpl(vcpu); + vcpu->run->xen.u.hcall.input = input; + vcpu->run->xen.u.hcall.params[0] = params[0]; + vcpu->run->xen.u.hcall.params[1] = params[1]; + vcpu->run->xen.u.hcall.params[2] = params[2]; + vcpu->run->xen.u.hcall.params[3] = params[3]; + vcpu->run->xen.u.hcall.params[4] = params[4]; + vcpu->run->xen.u.hcall.params[5] = params[5]; + vcpu->arch.xen.hypercall_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = + kvm_xen_hypercall_complete_userspace; + + return 0; +} diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h new file mode 100644 index 000000000000..276ed59e476b --- /dev/null +++ b/arch/x86/kvm/xen.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2019 Oracle and/or its affiliates. All rights reserved. + * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * KVM Xen emulation + */ + +#ifndef __ARCH_X86_KVM_XEN_H__ +#define __ARCH_X86_KVM_XEN_H__ + +int kvm_xen_hypercall(struct kvm_vcpu *vcpu); +int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data); + +static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.xen_hvm_config.flags & + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL; +} + +#endif /* __ARCH_X86_KVM_XEN_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dfe3ba5cf262..c87defe5db4f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -216,6 +216,20 @@ struct kvm_hyperv_exit { } u; }; +struct kvm_xen_exit { +#define KVM_EXIT_XEN_HCALL 1 + __u32 type; + union { + struct { + __u32 longmode; + __u32 cpl; + __u64 input; + __u64 result; + __u64 params[6]; + } hcall; + } u; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -253,6 +267,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_DIRTY_RING_FULL 31 #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 +#define KVM_EXIT_XEN 34 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -429,6 +444,8 @@ struct kvm_run { __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ } msr; + /* KVM_EXIT_XEN */ + struct kvm_xen_exit xen; /* Fix the size of the union. */ char padding[256]; }; @@ -1133,6 +1150,9 @@ struct kvm_x86_mce { #endif #ifdef KVM_CAP_XEN_HVM +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) + struct kvm_xen_hvm_config { __u32 flags; __u32 msr; diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 9616f77cc5af..be9613dd6d9b 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -62,6 +62,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test +TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fa5a90e6c6f0..d787cb802b4a 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1801,6 +1801,7 @@ static struct exit_reason { {KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"}, {KVM_EXIT_X86_RDMSR, "RDMSR"}, {KVM_EXIT_X86_WRMSR, "WRMSR"}, + {KVM_EXIT_XEN, "XEN"}, #ifdef KVM_EXIT_MEMORY_NOT_PRESENT {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, #endif diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c new file mode 100644 index 000000000000..234c9da286aa --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * xen_vmcall_test + * + * Copyright © 2020 Amazon.com, Inc. or its affiliates. + * + * Userspace hypercall testing + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 5 + +#define HCALL_REGION_GPA 0xc0000000ULL +#define HCALL_REGION_SLOT 10 + +static struct kvm_vm *vm; + +#define INPUTVALUE 17 +#define ARGVALUE(x) (0xdeadbeef5a5a0000UL + x) +#define RETVALUE 0xcafef00dfbfbffffUL + +#define XEN_HYPERCALL_MSR 0x40000000 + +static void guest_code(void) +{ + unsigned long rax = INPUTVALUE; + unsigned long rdi = ARGVALUE(1); + unsigned long rsi = ARGVALUE(2); + unsigned long rdx = ARGVALUE(3); + register unsigned long r10 __asm__("r10") = ARGVALUE(4); + register unsigned long r8 __asm__("r8") = ARGVALUE(5); + register unsigned long r9 __asm__("r9") = ARGVALUE(6); + + /* First a direct invocation of 'vmcall' */ + __asm__ __volatile__("vmcall" : + "=a"(rax) : + "a"(rax), "D"(rdi), "S"(rsi), "d"(rdx), + "r"(r10), "r"(r8), "r"(r9)); + GUEST_ASSERT(rax == RETVALUE); + + /* Now fill in the hypercall page */ + __asm__ __volatile__("wrmsr" : : "c" (XEN_HYPERCALL_MSR), + "a" (HCALL_REGION_GPA & 0xffffffff), + "d" (HCALL_REGION_GPA >> 32)); + + /* And invoke the same hypercall that way */ + __asm__ __volatile__("call *%1" : "=a"(rax) : + "r"(HCALL_REGION_GPA + INPUTVALUE * 32), + "a"(rax), "D"(rdi), "S"(rsi), "d"(rdx), + "r"(r10), "r"(r8), "r"(r9)); + GUEST_ASSERT(rax == RETVALUE); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + if (!(kvm_check_cap(KVM_CAP_XEN_HVM) & + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) ) { + print_skip("KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL not available"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + struct kvm_xen_hvm_config hvmc = { + .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, + .msr = XEN_HYPERCALL_MSR, + }; + vm_ioctl(vm, KVM_XEN_HVM_CONFIG, &hvmc); + + /* Map a region for the hypercall page */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + HCALL_REGION_GPA, HCALL_REGION_SLOT, + getpagesize(), 0); + virt_map(vm, HCALL_REGION_GPA, HCALL_REGION_GPA, 1, 0); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_XEN) { + ASSERT_EQ(run->xen.type, KVM_EXIT_XEN_HCALL); + ASSERT_EQ(run->xen.u.hcall.cpl, 0); + ASSERT_EQ(run->xen.u.hcall.longmode, 1); + ASSERT_EQ(run->xen.u.hcall.input, INPUTVALUE); + ASSERT_EQ(run->xen.u.hcall.params[0], ARGVALUE(1)); + ASSERT_EQ(run->xen.u.hcall.params[1], ARGVALUE(2)); + ASSERT_EQ(run->xen.u.hcall.params[2], ARGVALUE(3)); + ASSERT_EQ(run->xen.u.hcall.params[3], ARGVALUE(4)); + ASSERT_EQ(run->xen.u.hcall.params[4], ARGVALUE(5)); + ASSERT_EQ(run->xen.u.hcall.params[5], ARGVALUE(6)); + run->xen.u.hcall.result = RETVALUE; + continue; + } + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } + } +done: + kvm_vm_free(vm); + return 0; +} -- cgit v1.2.3 From a76b9641ad1c0b045045727a6cbbeebf80b6b9bb Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Dec 2020 15:52:25 +0000 Subject: KVM: x86/xen: add KVM_XEN_HVM_SET_ATTR/KVM_XEN_HVM_GET_ATTR This will be used to set up shared info pages etc. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- arch/x86/kvm/x86.c | 20 ++++++++++++++++++++ arch/x86/kvm/xen.c | 30 ++++++++++++++++++++++++++++++ arch/x86/kvm/xen.h | 2 ++ include/uapi/linux/kvm.h | 11 +++++++++++ 4 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ffc4ab3bd6ec..59bcba1ea59f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5630,6 +5630,26 @@ set_pit2_out: r = kvm_xen_hvm_config(kvm, &xhc); break; } + case KVM_XEN_HVM_GET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) + goto out; + r = kvm_xen_hvm_get_attr(kvm, &xha); + if (!r && copy_to_user(argp, &xha, sizeof(xha))) + r = -EFAULT; + break; + } + case KVM_XEN_HVM_SET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) + goto out; + r = kvm_xen_hvm_set_attr(kvm, &xha); + break; + } case KVM_SET_CLOCK: { struct kvm_clock_data user_ns; u64 now_ns; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 7d03d918e595..a3fd791b0354 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -18,6 +18,36 @@ DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); +int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) +{ + int r = -ENOENT; + + mutex_unlock(&kvm->lock); + + switch (data->type) { + default: + break; + } + + mutex_unlock(&kvm->lock); + return r; +} + +int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&kvm->lock); + + switch (data->type) { + default: + break; + } + + mutex_unlock(&kvm->lock); + return r; +} + int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) { struct kvm *kvm = vcpu->kvm; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ec3d8f6d0ef5..0e2467fcfb9f 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -13,6 +13,8 @@ extern struct static_key_false_deferred kvm_xen_enabled; +int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); +int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); int kvm_xen_hypercall(struct kvm_vcpu *vcpu); int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data); int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c87defe5db4f..334796799dbc 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1587,6 +1587,17 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_DIRTY_LOG_RING */ #define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) +#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) +#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 pad[8]; + } u; +}; + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From a3833b81b05d0ae92ae085959dd8da136ec91868 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Dec 2020 16:20:32 +0000 Subject: KVM: x86/xen: latch long_mode when hypercall page is set up Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 6 ++++++ arch/x86/kvm/xen.c | 16 +++++++++++++++- include/uapi/linux/kvm.h | 3 +++ 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b4bcdebd6e4c..016a005cc2ad 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -905,6 +905,11 @@ struct msr_bitmap_range { unsigned long *bitmap; }; +/* Xen emulation context */ +struct kvm_xen { + bool long_mode; +}; + enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ @@ -984,6 +989,7 @@ struct kvm_arch { struct hlist_head mask_notifier_list; struct kvm_hv hyperv; + struct kvm_xen xen; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index a3fd791b0354..55da739267b1 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -25,6 +25,13 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) mutex_unlock(&kvm->lock); switch (data->type) { + case KVM_XEN_ATTR_TYPE_LONG_MODE: + if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) + return -EINVAL; + + kvm->arch.xen.long_mode = !!data->u.long_mode; + r = 0; + break; default: break; } @@ -40,6 +47,10 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) mutex_lock(&kvm->lock); switch (data->type) { + case KVM_XEN_ATTR_TYPE_LONG_MODE: + data->u.long_mode = kvm->arch.xen.long_mode; + r = 0; + break; default: break; } @@ -53,6 +64,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) struct kvm *kvm = vcpu->kvm; u32 page_num = data & ~PAGE_MASK; u64 page_addr = data & PAGE_MASK; + bool lm = is_long_mode(vcpu); + + /* Latch long_mode for shared_info pages etc. */ + vcpu->kvm->arch.xen.long_mode = lm; /* * If Xen hypercall intercept is enabled, fill the hypercall @@ -87,7 +102,6 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) return 1; } } else { - int lm = is_long_mode(vcpu); u64 blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64 : kvm->arch.xen_hvm_config.blob_addr_32; u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 334796799dbc..11644954a2e2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1594,10 +1594,13 @@ struct kvm_xen_hvm_attr { __u16 type; __u16 pad[3]; union { + __u8 long_mode; __u64 pad[8]; } u; }; +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From 13ffb97a3b11998450d51457b6b3617781953f7c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 15 Jun 2018 21:17:14 -0400 Subject: KVM: x86/xen: register shared_info page Add KVM_XEN_ATTR_TYPE_SHARED_INFO to allow hypervisor to know where the guest's shared info page is. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/xen.c | 40 ++++++++++++++++++++++++++++++++++++---- include/uapi/linux/kvm.h | 4 ++++ 3 files changed, 42 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 016a005cc2ad..00d1233cfd55 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -908,6 +908,8 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { bool long_mode; + bool shinfo_set; + struct gfn_to_hva_cache shinfo_cache; }; enum kvm_irqchip_mode { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 55da739267b1..924d4e853108 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -13,25 +13,49 @@ #include #include +#include #include "trace.h" DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); +static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) +{ + int ret; + int idx = srcu_read_lock(&kvm->srcu); + + ret = kvm_gfn_to_hva_cache_init(kvm, &kvm->arch.xen.shinfo_cache, + gfn_to_gpa(gfn), PAGE_SIZE); + if (!ret) { + kvm->arch.xen.shinfo_set = true; + } + + srcu_read_unlock(&kvm->srcu, idx); + return ret; +} + int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) { int r = -ENOENT; + mutex_lock(&kvm->lock); + mutex_unlock(&kvm->lock); switch (data->type) { case KVM_XEN_ATTR_TYPE_LONG_MODE: - if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) - return -EINVAL; + if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) { + r = -EINVAL; + } else { + kvm->arch.xen.long_mode = !!data->u.long_mode; + r = 0; + } + break; - kvm->arch.xen.long_mode = !!data->u.long_mode; - r = 0; + case KVM_XEN_ATTR_TYPE_SHARED_INFO: + r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); break; + default: break; } @@ -51,6 +75,14 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) data->u.long_mode = kvm->arch.xen.long_mode; r = 0; break; + + case KVM_XEN_ATTR_TYPE_SHARED_INFO: + if (kvm->arch.xen.shinfo_set) { + data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); + r = 0; + } + break; + default: break; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 11644954a2e2..f57f6e741a28 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1595,11 +1595,15 @@ struct kvm_xen_hvm_attr { __u16 pad[3]; union { __u8 long_mode; + struct { + __u64 gfn; + } shared_info; __u64 pad[8]; } u; }; #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 3e3246158808d46b81edb8246214c0ab5a852594 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 2 Feb 2021 16:53:25 +0000 Subject: KVM: x86/xen: Add KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR This will be used for per-vCPU setup such as runstate and vcpu_info. Signed-off-by: David Woodhouse --- arch/x86/kvm/x86.c | 20 ++++++++++++++++++++ arch/x86/kvm/xen.c | 30 ++++++++++++++++++++++++++++++ arch/x86/kvm/xen.h | 2 ++ include/uapi/linux/kvm.h | 13 +++++++++++++ 4 files changed, 65 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 040d3d470173..66cd574ee458 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5016,6 +5016,26 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; + case KVM_XEN_VCPU_GET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_get_attr(vcpu, &xva); + if (!r && copy_to_user(argp, &xva, sizeof(xva))) + r = -EFAULT; + break; + } + case KVM_XEN_VCPU_SET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_set_attr(vcpu, &xva); + break; + } default: r = -EINVAL; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index eab4dce93be1..5cbf6955e509 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -118,6 +118,36 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) return r; } +int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&vcpu->kvm->lock); + + switch (data->type) { + default: + break; + } + + mutex_unlock(&vcpu->kvm->lock); + return r; +} + +int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&vcpu->kvm->lock); + + switch (data->type) { + default: + break; + } + + mutex_unlock(&vcpu->kvm->lock); + return r; +} + int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) { struct kvm *kvm = vcpu->kvm; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index 12a3dc32e78e..fb85377fdbdc 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -13,6 +13,8 @@ extern struct static_key_false_deferred kvm_xen_enabled; +int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); +int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); int kvm_xen_hypercall(struct kvm_vcpu *vcpu); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f57f6e741a28..e2b0cbde1908 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1587,6 +1587,7 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_DIRTY_LOG_RING */ #define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) +/* Per-VM Xen attributes */ #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) @@ -1605,6 +1606,18 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +/* Per-vCPU Xen attributes */ +#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) +#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 pad[8]; + } u; +}; + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From 73e69a86347afe8156aa50c436fc192b280b0cd7 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 29 Jun 2018 10:52:52 -0400 Subject: KVM: x86/xen: register vcpu info The vcpu info supersedes the per vcpu area of the shared info page and the guest vcpus will use this instead. Signed-off-by: Joao Martins Signed-off-by: Ankur Arora Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/xen.c | 25 ++++++++++++++++++++++++- include/uapi/linux/kvm.h | 3 +++ 3 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00d1233cfd55..4e864f2bd59a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -534,6 +534,8 @@ struct kvm_vcpu_hv { /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; + bool vcpu_info_set; + struct gfn_to_hva_cache vcpu_info_cache; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 5cbf6955e509..2712f1aa9ac9 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -120,15 +120,31 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { - int r = -ENOENT; + int idx, r = -ENOENT; mutex_lock(&vcpu->kvm->lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); switch (data->type) { + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + /* No compat necessary here. */ + BUILD_BUG_ON(sizeof(struct vcpu_info) != + sizeof(struct compat_vcpu_info)); + + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.vcpu_info_cache, + data->u.gpa, + sizeof(struct vcpu_info)); + if (!r) + vcpu->arch.xen.vcpu_info_set = true; + break; + + default: break; } + srcu_read_unlock(&vcpu->kvm->srcu, idx); mutex_unlock(&vcpu->kvm->lock); return r; } @@ -140,6 +156,13 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) mutex_lock(&vcpu->kvm->lock); switch (data->type) { + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + if (vcpu->arch.xen.vcpu_info_set) { + data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; + r = 0; + } + break; + default: break; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e2b0cbde1908..2db0657b3337 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1614,10 +1614,13 @@ struct kvm_xen_vcpu_attr { __u16 type; __u16 pad[3]; union { + __u64 gpa; __u64 pad[8]; } u; }; +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From f2340cd9e41dc463cb1189274f3db560c1dfa1f4 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Mon, 23 Jul 2018 11:20:57 -0400 Subject: KVM: x86/xen: register vcpu time info region Allow the Xen emulated guest the ability to register secondary vcpu time information. On Xen guests this is used in order to be mapped to userspace and hence allow vdso gettimeofday to work. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/x86.c | 2 ++ arch/x86/kvm/xen.c | 18 ++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 4 files changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4e864f2bd59a..c6c84c4ef7b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -535,7 +535,9 @@ struct kvm_vcpu_hv { struct kvm_vcpu_xen { u64 hypercall_rip; bool vcpu_info_set; + bool vcpu_time_info_set; struct gfn_to_hva_cache vcpu_info_cache; + struct gfn_to_hva_cache vcpu_time_info_cache; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a295fb8a8978..0f648434796f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2757,6 +2757,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (vcpu->xen.vcpu_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time)); + if (vcpu->xen.vcpu_time_info_set) + kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); if (v == kvm_get_vcpu(v->kvm, 0)) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index c307f8b7a8a3..bd343222e740 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -141,6 +141,17 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache, + data->u.gpa, + sizeof(struct pvclock_vcpu_time_info)); + if (!r) { + vcpu->arch.xen.vcpu_time_info_set = true; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + } + break; + default: break; } @@ -164,6 +175,13 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: + if (vcpu->arch.xen.vcpu_time_info_set) { + data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; + r = 0; + } + break; + default: break; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2db0657b3337..0f045ffd9cb6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1620,6 +1620,7 @@ struct kvm_xen_vcpu_attr { }; #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 40da8ccd724f7ca2f08550a46268bc3a91cc8869 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 9 Dec 2020 20:08:30 +0000 Subject: KVM: x86/xen: Add event channel interrupt vector upcall It turns out that we can't handle event channels *entirely* in userspace by delivering them as ExtINT, because KVM is a bit picky about when it accepts ExtINT interrupts from a legacy PIC. The in-kernel local APIC has to have LVT0 configured in APIC_MODE_EXTINT and unmasked, which isn't necessarily the case for Xen guests especially on secondary CPUs. To cope with this, add kvm_xen_get_interrupt() which checks the evtchn_pending_upcall field in the Xen vcpu_info, and delivers the Xen upcall vector (configured by KVM_XEN_ATTR_TYPE_UPCALL_VECTOR) if it's set regardless of LAPIC LVT0 configuration. This gives us the minimum support we need for completely userspace-based implementation of event channels. This does mean that vcpu_enter_guest() needs to check for the evtchn_pending_upcall flag being set, because it can't rely on someone having set KVM_REQ_EVENT unless we were to add some way for userspace to do so manually. Signed-off-by: David Woodhouse --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/irq.c | 7 ++++++ arch/x86/kvm/x86.c | 3 ++- arch/x86/kvm/xen.c | 53 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/xen.h | 9 +++++++ include/uapi/linux/kvm.h | 2 ++ 6 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c6c84c4ef7b0..b37afd856bab 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -913,6 +913,7 @@ struct msr_bitmap_range { struct kvm_xen { bool long_mode; bool shinfo_set; + u8 upcall_vector; struct gfn_to_hva_cache shinfo_cache; }; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index a035cca82f8f..172b05343cfd 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -14,6 +14,7 @@ #include "irq.h" #include "i8254.h" #include "x86.h" +#include "xen.h" /* * check if there are pending timer events @@ -56,6 +57,9 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (kvm_xen_has_interrupt(v)) + return 1; + if (!kvm_apic_accept_pic_intr(v)) return 0; @@ -110,6 +114,9 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; + if (kvm_xen_has_interrupt(v)) + return v->kvm->arch.xen.upcall_vector; + if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0f648434796f..1cedbc3d2455 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8987,7 +8987,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) static_call(kvm_x86_msr_filter_changed)(vcpu); } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || + kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index bd343222e740..39a7ffcdcf22 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -61,6 +61,44 @@ out: return ret; } +int __kvm_xen_has_interrupt(struct kvm_vcpu *v) +{ + u8 rc = 0; + + /* + * If the global upcall vector (HVMIRQ_callback_vector) is set and + * the vCPU's evtchn_upcall_pending flag is set, the IRQ is pending. + */ + struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending); + + /* No need for compat handling here */ + BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) != + offsetof(struct compat_vcpu_info, evtchn_upcall_pending)); + BUILD_BUG_ON(sizeof(rc) != + sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending)); + BUILD_BUG_ON(sizeof(rc) != + sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending)); + + /* + * For efficiency, this mirrors the checks for using the valid + * cache in kvm_read_guest_offset_cached(), but just uses + * __get_user() instead. And falls back to the slow path. + */ + if (likely(slots->generation == ghc->generation && + !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { + /* Fast path */ + __get_user(rc, (u8 __user *)ghc->hva + offset); + } else { + /* Slow path */ + kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, + sizeof(rc)); + } + + return rc; +} + int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) { int r = -ENOENT; @@ -83,6 +121,16 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); break; + + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: + if (data->u.vector < 0x10) + r = -EINVAL; + else { + kvm->arch.xen.upcall_vector = data->u.vector; + r = 0; + } + break; + default: break; } @@ -110,6 +158,11 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) } break; + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: + data->u.vector = kvm->arch.xen.upcall_vector; + r = 0; + break; + default: break; } diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index fb85377fdbdc..4b32489c0cec 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -13,6 +13,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; +int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -29,6 +30,14 @@ static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL); } +static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu) +{ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_set && vcpu->kvm->arch.xen.upcall_vector) + return __kvm_xen_has_interrupt(vcpu); + + return 0; +} /* 32-bit compatibility definitions, also used natively in 32-bit build */ #include diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0f045ffd9cb6..4d4cd001c908 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1596,6 +1596,7 @@ struct kvm_xen_hvm_attr { __u16 pad[3]; union { __u8 long_mode; + __u8 vector; struct { __u64 gfn; } shared_info; @@ -1605,6 +1606,7 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From 8d4e7e80838f45d3466d36d4fcb890424825faa9 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 4 Dec 2020 01:02:04 +0000 Subject: KVM: x86: declare Xen HVM shared info capability and add test case Instead of adding a plethora of new KVM_CAP_XEN_FOO capabilities, just add bits to the return value of KVM_CAP_XEN_HVM. Signed-off-by: David Woodhouse --- arch/x86/kvm/x86.c | 3 +- include/uapi/linux/kvm.h | 3 + tools/testing/selftests/kvm/Makefile | 1 + .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 169 +++++++++++++++++++++ 4 files changed, 175 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1cedbc3d2455..838ce5e9814b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3769,7 +3769,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | - KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL; + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | + KVM_XEN_HVM_CONFIG_SHARED_INFO; break; case KVM_CAP_SYNC_REGS: r = KVM_SYNC_X86_VALID_FIELDS; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4d4cd001c908..63f8f6e95648 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1152,6 +1152,7 @@ struct kvm_x86_mce { #ifdef KVM_CAP_XEN_HVM #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) struct kvm_xen_hvm_config { __u32 flags; @@ -1604,6 +1605,7 @@ struct kvm_xen_hvm_attr { } u; }; +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 @@ -1621,6 +1623,7 @@ struct kvm_xen_vcpu_attr { } u; }; +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index be9613dd6d9b..8c8eda429576 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -62,6 +62,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test +TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c new file mode 100644 index 000000000000..bdb3feb86b5b --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_vmcall_test + * + * Copyright © 2021 Amazon.com, Inc. or its affiliates. + * + * Xen shared_info / pvclock testing + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +#include +#include + +#define VCPU_ID 5 + +#define SHINFO_REGION_GPA 0xc0000000ULL +#define SHINFO_REGION_SLOT 10 +#define PAGE_SIZE 4096 + +#define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) + +static struct kvm_vm *vm; + +#define XEN_HYPERCALL_MSR 0x40000000 + +struct pvclock_vcpu_time_info { + u32 version; + u32 pad0; + u64 tsc_timestamp; + u64 system_time; + u32 tsc_to_system_mul; + s8 tsc_shift; + u8 flags; + u8 pad[2]; +} __attribute__((__packed__)); /* 32 bytes */ + +struct pvclock_wall_clock { + u32 version; + u32 sec; + u32 nsec; +} __attribute__((__packed__)); + +static void guest_code(void) +{ + GUEST_DONE(); +} + +static int cmp_timespec(struct timespec *a, struct timespec *b) +{ + if (a->tv_sec > b->tv_sec) + return 1; + else if (a->tv_sec < b->tv_sec) + return -1; + else if (a->tv_nsec > b->tv_nsec) + return 1; + else if (a->tv_nsec < b->tv_nsec) + return -1; + else + return 0; +} + +int main(int argc, char *argv[]) +{ + struct timespec min_ts, max_ts, vm_ts; + + if (!(kvm_check_cap(KVM_CAP_XEN_HVM) & + KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { + print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available"); + exit(KSFT_SKIP); + } + + clock_gettime(CLOCK_REALTIME, &min_ts); + + vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + /* Map a region for the shared_info page */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + SHINFO_REGION_GPA, SHINFO_REGION_SLOT, + 2 * getpagesize(), 0); + virt_map(vm, SHINFO_REGION_GPA, SHINFO_REGION_GPA, 2, 0); + + struct kvm_xen_hvm_config hvmc = { + .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, + .msr = XEN_HYPERCALL_MSR, + }; + vm_ioctl(vm, KVM_XEN_HVM_CONFIG, &hvmc); + + struct kvm_xen_hvm_attr lm = { + .type = KVM_XEN_ATTR_TYPE_LONG_MODE, + .u.long_mode = 1, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &lm); + + struct kvm_xen_hvm_attr ha = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + + struct kvm_xen_vcpu_attr vi = { + .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, + .u.gpa = SHINFO_REGION_GPA + 40, + }; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); + + struct kvm_xen_vcpu_attr pvclock = { + .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO, + .u.gpa = PVTIME_ADDR, + }; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } + } + + done: + clock_gettime(CLOCK_REALTIME, &max_ts); + + /* + * Just a *really* basic check that things are being put in the + * right place. The actual calculations are much the same for + * Xen as they are for the KVM variants, so no need to check. + */ + struct pvclock_wall_clock *wc; + struct pvclock_vcpu_time_info *ti, *ti2; + + wc = addr_gva2hva(vm, SHINFO_REGION_GPA + 0xc00); + ti = addr_gva2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); + ti2 = addr_gva2hva(vm, PVTIME_ADDR); + + vm_ts.tv_sec = wc->sec; + vm_ts.tv_nsec = wc->nsec; + TEST_ASSERT(wc->version && !(wc->version & 1), + "Bad wallclock version %x", wc->version); + TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old"); + TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new"); + + TEST_ASSERT(ti->version && !(ti->version & 1), + "Bad time_info version %x", ti->version); + TEST_ASSERT(ti2->version && !(ti2->version & 1), + "Bad time_info version %x", ti->version); + + kvm_vm_free(vm); + return 0; +} -- cgit v1.2.3 From 49ecc587dca2754571791bebd36e9e36e2a0d973 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Wed, 3 Feb 2021 08:07:59 +0100 Subject: Revert "GTP: add support for flow based tunneling API" This reverts commit 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a. This patch was committed without maintainer approval and despite a number of unaddressed concerns from review. There are several issues that impede the acceptance of this patch and that make a reversion of this particular instance of these changes the best way forward: i) the patch contains several logically separate changes that would be better served as smaller patches (for review purposes) ii) functionality like the handling of end markers has been introduced without further explanation iii) symmetry between the handling of GTPv0 and GTPv1 has been unnecessarily broken iv) the patchset produces 'broken' packets when extension headers are included v) there are no available userspace tools to allow for testing this functionality vi) there is an unaddressed Coverity report against the patch concering memory leakage vii) most importantly, the patch contains a large amount of superfluous churn that impedes other ongoing work with this driver This patch will be reworked into a series that aligns with other ongoing work and facilitates review. Signed-off-by: Jonas Bonn Acked-by: Harald Welte Acked-by: Pravin B Shelar Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 527 ++++++++++--------------------------- include/uapi/linux/gtp.h | 12 - include/uapi/linux/if_link.h | 1 - include/uapi/linux/if_tunnel.h | 1 - tools/include/uapi/linux/if_link.h | 1 - 5 files changed, 144 insertions(+), 398 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 851364314ecc..4c04e271f184 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -21,7 +21,6 @@ #include #include -#include #include #include #include @@ -74,9 +73,6 @@ struct gtp_dev { unsigned int hash_size; struct hlist_head *tid_hash; struct hlist_head *addr_hash; - /* Used by LWT tunnel. */ - bool collect_md; - struct socket *collect_md_sock; }; static unsigned int gtp_net_id __read_mostly; @@ -183,121 +179,33 @@ static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx, return false; } -static int gtp_set_tun_dst(struct gtp_dev *gtp, struct sk_buff *skb, - unsigned int hdrlen, u8 gtp_version, - __be64 tid, u8 flags) +static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, + unsigned int hdrlen, unsigned int role) { - struct metadata_dst *tun_dst; - int opts_len = 0; - - if (unlikely(flags & GTP1_F_MASK)) - opts_len = sizeof(struct gtpu_metadata); - - tun_dst = udp_tun_rx_dst(skb, gtp->sk1u->sk_family, TUNNEL_KEY, tid, opts_len); - if (!tun_dst) { - netdev_dbg(gtp->dev, "Failed to allocate tun_dst"); - goto err; + if (!gtp_check_ms(skb, pctx, hdrlen, role)) { + netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); + return 1; } - netdev_dbg(gtp->dev, "attaching metadata_dst to skb, gtp ver %d hdrlen %d\n", - gtp_version, hdrlen); - if (unlikely(opts_len)) { - struct gtpu_metadata *opts; - struct gtp1_header *gtp1; - - opts = ip_tunnel_info_opts(&tun_dst->u.tun_info); - gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); - opts->ver = GTP_METADATA_V1; - opts->flags = gtp1->flags; - opts->type = gtp1->type; - netdev_dbg(gtp->dev, "recved control pkt: flag %x type: %d\n", - opts->flags, opts->type); - tun_dst->u.tun_info.key.tun_flags |= TUNNEL_GTPU_OPT; - tun_dst->u.tun_info.options_len = opts_len; - skb->protocol = htons(0xffff); /* Unknown */ - } /* Get rid of the GTP + UDP headers. */ if (iptunnel_pull_header(skb, hdrlen, skb->protocol, - !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)))) { - gtp->dev->stats.rx_length_errors++; - goto err; - } - - skb_dst_set(skb, &tun_dst->dst); - return 0; -err: - return -1; -} - -static int gtp_rx(struct gtp_dev *gtp, struct sk_buff *skb, - unsigned int hdrlen, u8 gtp_version, unsigned int role, - __be64 tid, u8 flags, u8 type) -{ - if (ip_tunnel_collect_metadata() || gtp->collect_md) { - int err; - - err = gtp_set_tun_dst(gtp, skb, hdrlen, gtp_version, tid, flags); - if (err) - goto err; - } else { - struct pdp_ctx *pctx; - - if (flags & GTP1_F_MASK) - hdrlen += 4; - - if (type != GTP_TPDU) - return 1; + !net_eq(sock_net(pctx->sk), dev_net(pctx->dev)))) + return -1; - if (gtp_version == GTP_V0) - pctx = gtp0_pdp_find(gtp, be64_to_cpu(tid)); - else - pctx = gtp1_pdp_find(gtp, be64_to_cpu(tid)); - if (!pctx) { - netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); - return 1; - } - - if (!gtp_check_ms(skb, pctx, hdrlen, role)) { - netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); - return 1; - } - /* Get rid of the GTP + UDP headers. */ - if (iptunnel_pull_header(skb, hdrlen, skb->protocol, - !net_eq(sock_net(pctx->sk), dev_net(gtp->dev)))) { - gtp->dev->stats.rx_length_errors++; - goto err; - } - } - netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n"); + netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n"); /* Now that the UDP and the GTP header have been removed, set up the * new network header. This is required by the upper layer to * calculate the transport header. */ skb_reset_network_header(skb); - if (pskb_may_pull(skb, sizeof(struct iphdr))) { - struct iphdr *iph; - - iph = ip_hdr(skb); - if (iph->version == 4) { - netdev_dbg(gtp->dev, "inner pkt: ipv4"); - skb->protocol = htons(ETH_P_IP); - } else if (iph->version == 6) { - netdev_dbg(gtp->dev, "inner pkt: ipv6"); - skb->protocol = htons(ETH_P_IPV6); - } else { - netdev_dbg(gtp->dev, "inner pkt error: Unknown type"); - } - } - skb->dev = gtp->dev; - dev_sw_netstats_rx_add(gtp->dev, skb->len); + skb->dev = pctx->dev; + + dev_sw_netstats_rx_add(pctx->dev, skb->len); + netif_rx(skb); return 0; - -err: - gtp->dev->stats.rx_dropped++; - return -1; } /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */ @@ -306,6 +214,7 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp0_header); struct gtp0_header *gtp0; + struct pdp_ctx *pctx; if (!pskb_may_pull(skb, hdrlen)) return -1; @@ -315,7 +224,16 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) if ((gtp0->flags >> 5) != GTP_V0) return 1; - return gtp_rx(gtp, skb, hdrlen, GTP_V0, gtp->role, gtp0->tid, gtp0->flags, gtp0->type); + if (gtp0->type != GTP_TPDU) + return 1; + + pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid)); + if (!pctx) { + netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); + return 1; + } + + return gtp_rx(pctx, skb, hdrlen, gtp->role); } static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) @@ -323,30 +241,41 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb) unsigned int hdrlen = sizeof(struct udphdr) + sizeof(struct gtp1_header); struct gtp1_header *gtp1; + struct pdp_ctx *pctx; if (!pskb_may_pull(skb, hdrlen)) return -1; gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); - netdev_dbg(gtp->dev, "GTPv1 recv: flags %x\n", gtp1->flags); if ((gtp1->flags >> 5) != GTP_V1) return 1; + if (gtp1->type != GTP_TPDU) + return 1; + /* From 29.060: "This field shall be present if and only if any one or * more of the S, PN and E flags are set.". * * If any of the bit is set, then the remaining ones also have to be * set. */ + if (gtp1->flags & GTP1_F_MASK) + hdrlen += 4; + /* Make sure the header is larger enough, including extensions. */ if (!pskb_may_pull(skb, hdrlen)) return -1; gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr)); - return gtp_rx(gtp, skb, hdrlen, GTP_V1, gtp->role, - key32_to_tunnel_id(gtp1->tid), gtp1->flags, gtp1->type); + pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid)); + if (!pctx) { + netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb); + return 1; + } + + return gtp_rx(pctx, skb, hdrlen, gtp->role); } static void __gtp_encap_destroy(struct sock *sk) @@ -386,11 +315,6 @@ static void gtp_encap_disable(struct gtp_dev *gtp) { gtp_encap_disable_sock(gtp->sk0); gtp_encap_disable_sock(gtp->sk1u); - if (gtp->collect_md_sock) { - udp_tunnel_sock_release(gtp->collect_md_sock); - gtp->collect_md_sock = NULL; - netdev_dbg(gtp->dev, "GTP socket released.\n"); - } } /* UDP encapsulation receive handler. See net/ipv4/udp.c. @@ -405,8 +329,7 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!gtp) return 1; - netdev_dbg(gtp->dev, "encap_recv sk=%p type %d\n", - sk, udp_sk(sk)->encap_type); + netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); switch (udp_sk(sk)->encap_type) { case UDP_ENCAP_GTP0: @@ -460,13 +383,12 @@ static void gtp_dev_uninit(struct net_device *dev) static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, const struct sock *sk, - __be32 daddr, - __be32 saddr) + __be32 daddr) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = sk->sk_bound_dev_if; fl4->daddr = daddr; - fl4->saddr = saddr; + fl4->saddr = inet_sk(sk)->inet_saddr; fl4->flowi4_tos = RT_CONN_FLAGS(sk); fl4->flowi4_proto = sk->sk_protocol; @@ -490,7 +412,7 @@ static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) gtp0->tid = cpu_to_be64(pctx->u.v0.tid); } -static inline void gtp1_push_header(struct sk_buff *skb, __be32 tid) +static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) { int payload_len = skb->len; struct gtp1_header *gtp1; @@ -506,63 +428,46 @@ static inline void gtp1_push_header(struct sk_buff *skb, __be32 tid) gtp1->flags = 0x30; /* v1, GTP-non-prime. */ gtp1->type = GTP_TPDU; gtp1->length = htons(payload_len); - gtp1->tid = tid; + gtp1->tid = htonl(pctx->u.v1.o_tei); /* TODO: Suppport for extension header, sequence number and N-PDU. * Update the length field if any of them is available. */ } -static inline int gtp1_push_control_header(struct sk_buff *skb, - __be32 tid, - struct gtpu_metadata *opts, - struct net_device *dev) -{ - struct gtp1_header *gtp1c; - int payload_len; - - if (opts->ver != GTP_METADATA_V1) - return -ENOENT; +struct gtp_pktinfo { + struct sock *sk; + struct iphdr *iph; + struct flowi4 fl4; + struct rtable *rt; + struct pdp_ctx *pctx; + struct net_device *dev; + __be16 gtph_port; +}; - if (opts->type == 0xFE) { - /* for end marker ignore skb data. */ - netdev_dbg(dev, "xmit pkt with null data"); - pskb_trim(skb, 0); +static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo) +{ + switch (pktinfo->pctx->gtp_version) { + case GTP_V0: + pktinfo->gtph_port = htons(GTP0_PORT); + gtp0_push_header(skb, pktinfo->pctx); + break; + case GTP_V1: + pktinfo->gtph_port = htons(GTP1U_PORT); + gtp1_push_header(skb, pktinfo->pctx); + break; } - if (skb_cow_head(skb, sizeof(*gtp1c)) < 0) - return -ENOMEM; - - payload_len = skb->len; - - gtp1c = skb_push(skb, sizeof(*gtp1c)); - - gtp1c->flags = opts->flags; - gtp1c->type = opts->type; - gtp1c->length = htons(payload_len); - gtp1c->tid = tid; - netdev_dbg(dev, "xmit control pkt: ver %d flags %x type %x pkt len %d tid %x", - opts->ver, opts->flags, opts->type, skb->len, tid); - return 0; } -struct gtp_pktinfo { - struct sock *sk; - __u8 tos; - struct flowi4 fl4; - struct rtable *rt; - struct net_device *dev; - __be16 gtph_port; -}; - static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo, - struct sock *sk, - __u8 tos, - struct rtable *rt, + struct sock *sk, struct iphdr *iph, + struct pdp_ctx *pctx, struct rtable *rt, struct flowi4 *fl4, struct net_device *dev) { pktinfo->sk = sk; - pktinfo->tos = tos; + pktinfo->iph = iph; + pktinfo->pctx = pctx; pktinfo->rt = rt; pktinfo->fl4 = *fl4; pktinfo->dev = dev; @@ -572,99 +477,40 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, struct gtp_pktinfo *pktinfo) { struct gtp_dev *gtp = netdev_priv(dev); - struct gtpu_metadata *opts = NULL; - struct sock *sk = NULL; struct pdp_ctx *pctx; struct rtable *rt; struct flowi4 fl4; - u8 gtp_version; - __be16 df = 0; - __be32 tun_id; - __be32 daddr; - __be32 saddr; - __u8 tos; + struct iphdr *iph; + __be16 df; int mtu; - if (gtp->collect_md) { - /* LWT GTP1U encap */ - struct ip_tunnel_info *info = NULL; - - info = skb_tunnel_info(skb); - if (!info) { - netdev_dbg(dev, "missing tunnel info"); - return -ENOENT; - } - if (info->key.tp_dst && ntohs(info->key.tp_dst) != GTP1U_PORT) { - netdev_dbg(dev, "unexpected GTP dst port: %d", ntohs(info->key.tp_dst)); - return -EOPNOTSUPP; - } - pctx = NULL; - gtp_version = GTP_V1; - tun_id = tunnel_id_to_key32(info->key.tun_id); - daddr = info->key.u.ipv4.dst; - saddr = info->key.u.ipv4.src; - sk = gtp->sk1u; - if (!sk) { - netdev_dbg(dev, "missing tunnel sock"); - return -EOPNOTSUPP; - } - tos = info->key.tos; - if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) - df = htons(IP_DF); - - if (info->options_len != 0) { - if (info->key.tun_flags & TUNNEL_GTPU_OPT) { - opts = ip_tunnel_info_opts(info); - } else { - netdev_dbg(dev, "missing tunnel metadata for control pkt"); - return -EOPNOTSUPP; - } - } - netdev_dbg(dev, "flow-based GTP1U encap: tunnel id %d\n", - be32_to_cpu(tun_id)); - } else { - struct iphdr *iph; - - if (ntohs(skb->protocol) != ETH_P_IP) - return -EOPNOTSUPP; - - iph = ip_hdr(skb); - - /* Read the IP destination address and resolve the PDP context. - * Prepend PDP header with TEI/TID from PDP ctx. - */ - if (gtp->role == GTP_ROLE_SGSN) - pctx = ipv4_pdp_find(gtp, iph->saddr); - else - pctx = ipv4_pdp_find(gtp, iph->daddr); + /* Read the IP destination address and resolve the PDP context. + * Prepend PDP header with TEI/TID from PDP ctx. + */ + iph = ip_hdr(skb); + if (gtp->role == GTP_ROLE_SGSN) + pctx = ipv4_pdp_find(gtp, iph->saddr); + else + pctx = ipv4_pdp_find(gtp, iph->daddr); - if (!pctx) { - netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n", - &iph->daddr); - return -ENOENT; - } - sk = pctx->sk; - netdev_dbg(dev, "found PDP context %p\n", pctx); - - gtp_version = pctx->gtp_version; - tun_id = htonl(pctx->u.v1.o_tei); - daddr = pctx->peer_addr_ip4.s_addr; - saddr = inet_sk(sk)->inet_saddr; - tos = iph->tos; - df = iph->frag_off; - netdev_dbg(dev, "gtp -> IP src: %pI4 dst: %pI4\n", - &iph->saddr, &iph->daddr); + if (!pctx) { + netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n", + &iph->daddr); + return -ENOENT; } + netdev_dbg(dev, "found PDP context %p\n", pctx); - rt = ip4_route_output_gtp(&fl4, sk, daddr, saddr); + rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr); if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to SSGN %pI4\n", &daddr); + netdev_dbg(dev, "no route to SSGN %pI4\n", + &pctx->peer_addr_ip4.s_addr); dev->stats.tx_carrier_errors++; goto err; } if (rt->dst.dev == dev) { - netdev_dbg(dev, "circular route to SSGN %pI4\n", &daddr); + netdev_dbg(dev, "circular route to SSGN %pI4\n", + &pctx->peer_addr_ip4.s_addr); dev->stats.collisions++; goto err_rt; } @@ -672,10 +518,11 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* This is similar to tnl_update_pmtu(). */ + df = iph->frag_off; if (df) { mtu = dst_mtu(&rt->dst) - dev->hard_header_len - sizeof(struct iphdr) - sizeof(struct udphdr); - switch (gtp_version) { + switch (pctx->gtp_version) { case GTP_V0: mtu -= sizeof(struct gtp0_header); break; @@ -689,38 +536,17 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false); - if (!skb_is_gso(skb) && (df & htons(IP_DF)) && mtu < skb->len) { - netdev_dbg(dev, "packet too big, fragmentation needed"); + if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && + mtu < ntohs(iph->tot_len)) { + netdev_dbg(dev, "packet too big, fragmentation needed\n"); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; } - gtp_set_pktinfo_ipv4(pktinfo, sk, tos, rt, &fl4, dev); - - if (unlikely(opts)) { - int err; - - pktinfo->gtph_port = htons(GTP1U_PORT); - err = gtp1_push_control_header(skb, tun_id, opts, dev); - if (err) { - netdev_info(dev, "cntr pkt error %d", err); - goto err_rt; - } - return 0; - } - - switch (gtp_version) { - case GTP_V0: - pktinfo->gtph_port = htons(GTP0_PORT); - gtp0_push_header(skb, pctx); - break; - case GTP_V1: - pktinfo->gtph_port = htons(GTP1U_PORT); - gtp1_push_header(skb, tun_id); - break; - } + gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev); + gtp_push_header(skb, pktinfo); return 0; err_rt: @@ -731,6 +557,7 @@ err: static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) { + unsigned int proto = ntohs(skb->protocol); struct gtp_pktinfo pktinfo; int err; @@ -742,22 +569,32 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ rcu_read_lock(); - err = gtp_build_skb_ip4(skb, dev, &pktinfo); + switch (proto) { + case ETH_P_IP: + err = gtp_build_skb_ip4(skb, dev, &pktinfo); + break; + default: + err = -EOPNOTSUPP; + break; + } rcu_read_unlock(); if (err < 0) goto tx_err; - udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb, - pktinfo.fl4.saddr, - pktinfo.fl4.daddr, - pktinfo.tos, - ip4_dst_hoplimit(&pktinfo.rt->dst), - 0, - pktinfo.gtph_port, - pktinfo.gtph_port, - true, - false); + switch (proto) { + case ETH_P_IP: + netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n", + &pktinfo.iph->saddr, &pktinfo.iph->daddr); + udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb, + pktinfo.fl4.saddr, pktinfo.fl4.daddr, + pktinfo.iph->tos, + ip4_dst_hoplimit(&pktinfo.rt->dst), + 0, + pktinfo.gtph_port, pktinfo.gtph_port, + true, false); + break; + } return NETDEV_TX_OK; tx_err: @@ -773,19 +610,6 @@ static const struct net_device_ops gtp_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, }; -static struct gtp_dev *gtp_find_flow_based_dev(struct net *net) -{ - struct gtp_net *gn = net_generic(net, gtp_net_id); - struct gtp_dev *gtp; - - list_for_each_entry(gtp, &gn->gtp_dev_list, list) { - if (gtp->collect_md) - return gtp; - } - - return NULL; -} - static void gtp_link_setup(struct net_device *dev) { dev->netdev_ops = >p_netdev_ops; @@ -810,7 +634,7 @@ static void gtp_link_setup(struct net_device *dev) } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); -static int gtp_encap_enable(struct gtp_dev *gtp, struct net_device *dev, struct nlattr *data[]); +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); static void gtp_destructor(struct net_device *dev) { @@ -828,24 +652,11 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, struct gtp_net *gn; int hashsize, err; - if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1] && - !data[IFLA_GTP_COLLECT_METADATA]) + if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1]) return -EINVAL; gtp = netdev_priv(dev); - if (data[IFLA_GTP_COLLECT_METADATA]) { - if (data[IFLA_GTP_FD0]) { - netdev_dbg(dev, "LWT device does not support setting v0 socket"); - return -EINVAL; - } - if (gtp_find_flow_based_dev(src_net)) { - netdev_dbg(dev, "LWT device already exist"); - return -EBUSY; - } - gtp->collect_md = true; - } - if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; } else { @@ -858,7 +669,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - err = gtp_encap_enable(gtp, dev, data); + err = gtp_encap_enable(gtp, data); if (err < 0) goto out_hashtable; @@ -872,7 +683,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, list_add_rcu(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; - netdev_dbg(dev, "registered new GTP interface %s\n", dev->name); + netdev_dbg(dev, "registered new GTP interface\n"); return 0; @@ -903,7 +714,6 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_FD1] = { .type = NLA_U32 }, [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 }, [IFLA_GTP_ROLE] = { .type = NLA_U32 }, - [IFLA_GTP_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], @@ -927,9 +737,6 @@ static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size)) goto nla_put_failure; - if (gtp->collect_md && nla_put_flag(skb, IFLA_GTP_COLLECT_METADATA)) - goto nla_put_failure; - return 0; nla_put_failure: @@ -975,24 +782,35 @@ err1: return -ENOMEM; } -static int __gtp_encap_enable_socket(struct socket *sock, int type, - struct gtp_dev *gtp) +static struct sock *gtp_encap_enable_socket(int fd, int type, + struct gtp_dev *gtp) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; + struct socket *sock; struct sock *sk; + int err; + + pr_debug("enable gtp on %d, %d\n", fd, type); + + sock = sockfd_lookup(fd, &err); + if (!sock) { + pr_debug("gtp socket fd=%d not found\n", fd); + return NULL; + } sk = sock->sk; if (sk->sk_protocol != IPPROTO_UDP || sk->sk_type != SOCK_DGRAM || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { - pr_debug("socket not UDP\n"); - return -EINVAL; + pr_debug("socket fd=%d not UDP\n", fd); + sk = ERR_PTR(-EINVAL); + goto out_sock; } lock_sock(sk); if (sk->sk_user_data) { - release_sock(sock->sk); - return -EBUSY; + sk = ERR_PTR(-EBUSY); + goto out_rel_sock; } sock_hold(sk); @@ -1003,58 +821,15 @@ static int __gtp_encap_enable_socket(struct socket *sock, int type, tuncfg.encap_destroy = gtp_encap_destroy; setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); - release_sock(sock->sk); - return 0; -} -static struct sock *gtp_encap_enable_socket(int fd, int type, - struct gtp_dev *gtp) -{ - struct socket *sock; - int err; - - pr_debug("enable gtp on %d, %d\n", fd, type); - - sock = sockfd_lookup(fd, &err); - if (!sock) { - pr_debug("gtp socket fd=%d not found\n", fd); - return NULL; - } - err = __gtp_encap_enable_socket(sock, type, gtp); +out_rel_sock: + release_sock(sock->sk); +out_sock: sockfd_put(sock); - if (err) - return ERR_PTR(err); - - return sock->sk; + return sk; } -static struct socket *gtp_create_gtp_socket(struct gtp_dev *gtp, struct net_device *dev) -{ - struct udp_port_cfg udp_conf; - struct socket *sock; - int err; - - memset(&udp_conf, 0, sizeof(udp_conf)); - udp_conf.family = AF_INET; - udp_conf.local_ip.s_addr = htonl(INADDR_ANY); - udp_conf.local_udp_port = htons(GTP1U_PORT); - - err = udp_sock_create(dev_net(dev), &udp_conf, &sock); - if (err < 0) { - pr_debug("create gtp sock failed: %d\n", err); - return ERR_PTR(err); - } - err = __gtp_encap_enable_socket(sock, UDP_ENCAP_GTP1U, gtp); - if (err) { - pr_debug("enable gtp sock encap failed: %d\n", err); - udp_tunnel_sock_release(sock); - return ERR_PTR(err); - } - pr_debug("create gtp sock done\n"); - return sock; -} - -static int gtp_encap_enable(struct gtp_dev *gtp, struct net_device *dev, struct nlattr *data[]) +static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) { struct sock *sk1u = NULL; struct sock *sk0 = NULL; @@ -1078,25 +853,11 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct net_device *dev, struct } } - if (data[IFLA_GTP_COLLECT_METADATA]) { - struct socket *sock; - - if (!sk1u) { - sock = gtp_create_gtp_socket(gtp, dev); - if (IS_ERR(sock)) - return PTR_ERR(sock); - - gtp->collect_md_sock = sock; - sk1u = sock->sk; - } else { - gtp->collect_md_sock = NULL; - } - } - if (data[IFLA_GTP_ROLE]) { role = nla_get_u32(data[IFLA_GTP_ROLE]); if (role > GTP_ROLE_SGSN) { - gtp_encap_disable(gtp); + gtp_encap_disable_sock(sk0); + gtp_encap_disable_sock(sk1u); return -EINVAL; } } @@ -1655,7 +1416,7 @@ static int __init gtp_init(void) if (err < 0) goto unreg_genl_family; - pr_info("GTP module loaded (pdp ctx size %zd bytes) with tnl-md support\n", + pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 62aff78b7c56..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,8 +2,6 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ -#include - #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -36,14 +34,4 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) -enum { - GTP_METADATA_V1 -}; - -struct gtpu_metadata { - __u8 ver; - __u8 flags; - __u8 type; -}; - #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eb8018c3a737..91c8dda6d95d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -811,7 +811,6 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, - IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 802da679fab1..7d9105533c7b 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,7 +176,6 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) -#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 28d649bda686..d208b2af697f 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -617,7 +617,6 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, - IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From 36a6c843fd0d8e02506681577e96dabd203dd8e8 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 5 Feb 2021 13:43:21 -0500 Subject: entry: Use different define for selector variable in SUD Michael Kerrisk suggested that, from an API perspective, it is a bad idea to share the PR_SYS_DISPATCH_ defines between the prctl operation and the selector variable. Therefore, define two new constants to be used by SUD's selector variable and update the corresponding documentation and test cases. While this changes the API syscall user dispatch has never been part of a Linux release, it will show up for the first time in 5.11. Suggested-by: Michael Kerrisk (man-pages) Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210205184321.2062251-1-krisman@collabora.com --- Documentation/admin-guide/syscall-user-dispatch.rst | 4 ++-- include/uapi/linux/prctl.h | 3 +++ kernel/entry/syscall_user_dispatch.c | 4 ++-- .../selftests/syscall_user_dispatch/sud_benchmark.c | 8 +++++--- tools/testing/selftests/syscall_user_dispatch/sud_test.c | 14 ++++++++------ 5 files changed, 20 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/syscall-user-dispatch.rst b/Documentation/admin-guide/syscall-user-dispatch.rst index a380d6515774..60314953c728 100644 --- a/Documentation/admin-guide/syscall-user-dispatch.rst +++ b/Documentation/admin-guide/syscall-user-dispatch.rst @@ -70,8 +70,8 @@ trampoline code on the vDSO, that trampoline is never intercepted. [selector] is a pointer to a char-sized region in the process memory region, that provides a quick way to enable disable syscall redirection thread-wide, without the need to invoke the kernel directly. selector -can be set to PR_SYS_DISPATCH_ON or PR_SYS_DISPATCH_OFF. Any other -value should terminate the program with a SIGSYS. +can be set to SYSCALL_DISPATCH_FILTER_ALLOW or SYSCALL_DISPATCH_FILTER_BLOCK. +Any other value should terminate the program with a SIGSYS. Security Notes -------------- diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 90deb41c8a34..667f1aed091c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -251,5 +251,8 @@ struct prctl_mm_map { #define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index b0338a5625d9..c240302f56e2 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -50,10 +50,10 @@ bool syscall_user_dispatch(struct pt_regs *regs) if (unlikely(__get_user(state, sd->selector))) do_exit(SIGSEGV); - if (likely(state == PR_SYS_DISPATCH_OFF)) + if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != PR_SYS_DISPATCH_ON) + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) do_exit(SIGSYS); } diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c index 6689f1183dbf..073a03702ff5 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c @@ -22,6 +22,8 @@ # define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif #ifdef __NR_syscalls @@ -55,8 +57,8 @@ unsigned long trapped_call_count = 0; unsigned long native_call_count = 0; char selector; -#define SYSCALL_BLOCK (selector = PR_SYS_DISPATCH_ON) -#define SYSCALL_UNBLOCK (selector = PR_SYS_DISPATCH_OFF) +#define SYSCALL_BLOCK (selector = SYSCALL_DISPATCH_FILTER_BLOCK) +#define SYSCALL_UNBLOCK (selector = SYSCALL_DISPATCH_FILTER_ALLOW) #define CALIBRATION_STEP 100000 #define CALIBRATE_TO_SECS 5 @@ -170,7 +172,7 @@ int main(void) syscall(MAGIC_SYSCALL_1); #ifdef TEST_BLOCKED_RETURN - if (selector == PR_SYS_DISPATCH_OFF) { + if (selector == SYSCALL_DISPATCH_FILTER_ALLOW) { fprintf(stderr, "Failed to return with selector blocked.\n"); exit(-1); } diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index 6498b050ef89..b5d592d4099e 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -18,6 +18,8 @@ # define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif #ifndef SYS_USER_DISPATCH @@ -30,8 +32,8 @@ # define MAGIC_SYSCALL_1 (0xff00) /* Bad Linux syscall number */ #endif -#define SYSCALL_DISPATCH_ON(x) ((x) = 1) -#define SYSCALL_DISPATCH_OFF(x) ((x) = 0) +#define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK) +#define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW) /* Test Summary: * @@ -56,7 +58,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) { - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; struct sysinfo info; int ret; @@ -79,7 +81,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) TEST(bad_prctl_param) { - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; int op; /* Invalid op */ @@ -220,7 +222,7 @@ TEST_SIGNAL(bad_selector, SIGSYS) sigset_t mask; struct sysinfo info; - glob_sel = 0; + glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW; nr_syscalls_emulated = 0; si_code = 0; si_errno = 0; @@ -288,7 +290,7 @@ TEST(direct_dispatch_range) { int ret = 0; struct sysinfo info; - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; /* * Instead of calculating libc addresses; allow the entire -- cgit v1.2.3 From cfa55c6d47b1e75ccc4b950616e881f3fd07712e Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 1 Jan 2021 00:00:01 +0100 Subject: batman-adv: Drop publication years from copyright info The batman-adv source code was using the year of publication (to net-next) as "last" year for the copyright statement. The whole source code mentioned in the MAINTAINERS "BATMAN ADVANCED" section was handled as a single entity regarding the publishing year. This avoided having outdated (in sense of year information - not copyright holder) publishing information inside several files. But since the simple "update copyright year" commit (without other changes) in the file was not well received in the upstream kernel, the option to not have a copyright year (for initial and last publication) in the files are chosen instead. More detailed information about the years can still be retrieved from the SCM system. Signed-off-by: Sven Eckelmann Acked-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 2 +- include/uapi/linux/batman_adv.h | 2 +- net/batman-adv/Kconfig | 2 +- net/batman-adv/Makefile | 2 +- net/batman-adv/bat_algo.c | 2 +- net/batman-adv/bat_algo.h | 2 +- net/batman-adv/bat_iv_ogm.c | 2 +- net/batman-adv/bat_iv_ogm.h | 2 +- net/batman-adv/bat_v.c | 2 +- net/batman-adv/bat_v.h | 2 +- net/batman-adv/bat_v_elp.c | 2 +- net/batman-adv/bat_v_elp.h | 2 +- net/batman-adv/bat_v_ogm.c | 2 +- net/batman-adv/bat_v_ogm.h | 2 +- net/batman-adv/bitarray.c | 2 +- net/batman-adv/bitarray.h | 2 +- net/batman-adv/bridge_loop_avoidance.c | 2 +- net/batman-adv/bridge_loop_avoidance.h | 2 +- net/batman-adv/distributed-arp-table.c | 2 +- net/batman-adv/distributed-arp-table.h | 2 +- net/batman-adv/fragmentation.c | 2 +- net/batman-adv/fragmentation.h | 2 +- net/batman-adv/gateway_client.c | 2 +- net/batman-adv/gateway_client.h | 2 +- net/batman-adv/gateway_common.c | 2 +- net/batman-adv/gateway_common.h | 2 +- net/batman-adv/hard-interface.c | 2 +- net/batman-adv/hard-interface.h | 2 +- net/batman-adv/hash.c | 2 +- net/batman-adv/hash.h | 2 +- net/batman-adv/log.c | 2 +- net/batman-adv/log.h | 2 +- net/batman-adv/main.c | 2 +- net/batman-adv/main.h | 2 +- net/batman-adv/multicast.c | 2 +- net/batman-adv/multicast.h | 2 +- net/batman-adv/netlink.c | 2 +- net/batman-adv/netlink.h | 2 +- net/batman-adv/network-coding.c | 2 +- net/batman-adv/network-coding.h | 2 +- net/batman-adv/originator.c | 2 +- net/batman-adv/originator.h | 2 +- net/batman-adv/routing.c | 2 +- net/batman-adv/routing.h | 2 +- net/batman-adv/send.c | 2 +- net/batman-adv/send.h | 2 +- net/batman-adv/soft-interface.c | 2 +- net/batman-adv/soft-interface.h | 2 +- net/batman-adv/tp_meter.c | 2 +- net/batman-adv/tp_meter.h | 2 +- net/batman-adv/trace.c | 2 +- net/batman-adv/trace.h | 2 +- net/batman-adv/translation-table.c | 2 +- net/batman-adv/translation-table.h | 2 +- net/batman-adv/tvlv.c | 2 +- net/batman-adv/tvlv.h | 2 +- net/batman-adv/types.h | 2 +- 57 files changed, 57 insertions(+), 57 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 9c8604c5b5f6..ea4692c339ce 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index bdb317faa1dc..35dc016c9bb4 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 993afd5ff7bb..dd853dc22d32 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +# Copyright (C) B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 8010c34b987c..3bd0760c76a2 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +# Copyright (C) B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index c5f404f6892f..4eee53d19eb0 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 43b045ac8ac7..2c486374af58 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 168621c9a081..a5e313cd6f44 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index 0c57c1000c64..04b01bd684e8 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index e4455babe4c2..e1ca2b8c3152 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index 5e0be10bc84e..964431f4dc8d 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 0512ea6cd818..423c2d171703 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 4358d436be2a..9e2740195fa2 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 798d659855d0..a0a9636d1740 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 0ae2575f70bb..edeffedecade 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 4bc695cda397..649c41f393e1 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 533c6d44cb58..37f7ae413bc6 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index d2de12e527ba..360bdbf44748 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 7dc6d3571925..5c22955bb9d5 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fd7ba6bbdf85..01e0f84cb1ff 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index e980fb45693a..bed7f3d20844 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index e522f1fcfd9a..a5d9d800082b 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll */ diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 881ef328b6cd..dbf0871f8703 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index cffe72f4edd7..007f2827935d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 2fbc500f0ac1..2ae5846ef958 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 16cd9450ceb1..fdde305a198e 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index c3a0c5a7f7e9..87c37f907261 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 0f186ddc15e3..4a6a25d551a8 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index f4b8e9efef19..83d11b46a9d8 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 68638e0450a6..8016e619787f 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 91ae9f32b580..46696759f194 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index b7e9923b11a2..f0e5d1429662 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 979864c0fa6b..6717c965f0fa 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index ed9d87ce3407..e48f7ac8a854 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 2486efe4ffa6..8f0102b71656 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 854e5ff28a3f..71d0bc323471 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index d61593d02072..9fee5da08311 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 97bcf149633d..fdd76eeaa6be 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 7ee48f916997..48102cc7490c 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 0cec108b7a99..4bb76b434d07 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 8fb2c01e7837..368cc3130e4c 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 77431e59b228..da7249448474 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index e75d4c4d11f5..805be87d55b8 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 49cbca4aa428..40f5cffde6a3 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 2ed49db6eff5..5f387786e9a7 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 87017332b567..157abe92d827 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0d36e15589f6..2b0daf8b2bc4 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 97118efbe678..6b8181bc3122 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 74716d9ca4f6..38b0ad182584 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index d4e10005df6c..07e6c1d864a4 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 140105215aa2..f0046d366eac 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 3444d9e4e90d..ec8b9519076b 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index a87547570b4e..d673ebdd0426 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index cd09916f97fe..f8761281aab0 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 57192c817229..e1285904f885 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 6a23a566cde1..253f5a33a914 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index d509d00c7a23..54f2a35653d0 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 2f96e96a5ca4..2c654ec964b7 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ -- cgit v1.2.3 From e17fe6579de023725ec22a16965e9099e4a05ac9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:16 -0800 Subject: fs-verity: add FS_IOC_READ_VERITY_METADATA ioctl Add an ioctl FS_IOC_READ_VERITY_METADATA which will allow reading verity metadata from a file that has fs-verity enabled, including: - The Merkle tree - The fsverity_descriptor (not including the signature if present) - The built-in signature, if present This ioctl has similar semantics to pread(). It is passed the type of metadata to read (one of the above three), and a buffer, offset, and size. It returns the number of bytes read or an error. Separate patches will add support for each of the above metadata types. This patch just adds the ioctl itself. This ioctl doesn't make any assumption about where the metadata is stored on-disk. It does assume the metadata is in a stable format, but that's basically already the case: - The Merkle tree and fsverity_descriptor are defined by how fs-verity file digests are computed; see the "File digest computation" section of Documentation/filesystems/fsverity.rst. Technically, the way in which the levels of the tree are ordered relative to each other wasn't previously specified, but it's logical to put the root level first. - The built-in signature is the value passed to FS_IOC_ENABLE_VERITY. This ioctl is useful because it allows writing a server program that takes a verity file and serves it to a client program, such that the client can do its own fs-verity compatible verification of the file. This only makes sense if the client doesn't trust the server and if the server needs to provide the storage for the client. More concretely, there is interest in using this ability in Android to export APK files (which are protected by fs-verity) to "protected VMs". This would use Protected KVM (https://lwn.net/Articles/836693), which provides an isolated execution environment without having to trust the traditional "host". A "guest" VM can boot from a signed image and perform specific tasks in a minimum trusted environment using files that have fs-verity enabled on the host, without trusting the host or requiring that the guest has its own trusted storage. Technically, it would be possible to duplicate the metadata and store it in separate files for serving. However, that would be less efficient and would require extra care in userspace to maintain file consistency. In addition to the above, the ability to read the built-in signatures is useful because it allows a system that is using the in-kernel signature verification to migrate to userspace signature verification. Link: https://lore.kernel.org/r/20210115181819.34732-4-ebiggers@kernel.org Reviewed-by: Victor Hsieh Acked-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- Documentation/filesystems/fsverity.rst | 57 ++++++++++++++++++++++++++++++++++ fs/ext4/ioctl.c | 7 +++++ fs/f2fs/file.c | 11 +++++++ fs/verity/Makefile | 1 + fs/verity/read_metadata.c | 55 ++++++++++++++++++++++++++++++++ include/linux/fsverity.h | 12 +++++++ include/uapi/linux/fsverity.h | 10 ++++++ 7 files changed, 153 insertions(+) create mode 100644 fs/verity/read_metadata.c (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index e0204a23e997..9ef7a7de6008 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -217,6 +217,63 @@ FS_IOC_MEASURE_VERITY can fail with the following errors: - ``EOVERFLOW``: the digest is longer than the specified ``digest_size`` bytes. Try providing a larger buffer. +FS_IOC_READ_VERITY_METADATA +--------------------------- + +The FS_IOC_READ_VERITY_METADATA ioctl reads verity metadata from a +verity file. This ioctl is available since Linux v5.12. + +This ioctl allows writing a server program that takes a verity file +and serves it to a client program, such that the client can do its own +fs-verity compatible verification of the file. This only makes sense +if the client doesn't trust the server and if the server needs to +provide the storage for the client. + +This is a fairly specialized use case, and most fs-verity users won't +need this ioctl. + +This ioctl takes in a pointer to the following structure:: + + struct fsverity_read_metadata_arg { + __u64 metadata_type; + __u64 offset; + __u64 length; + __u64 buf_ptr; + __u64 __reserved; + }; + +``metadata_type`` specifies the type of metadata to read. + +The semantics are similar to those of ``pread()``. ``offset`` +specifies the offset in bytes into the metadata item to read from, and +``length`` specifies the maximum number of bytes to read from the +metadata item. ``buf_ptr`` is the pointer to the buffer to read into, +cast to a 64-bit integer. ``__reserved`` must be 0. On success, the +number of bytes read is returned. 0 is returned at the end of the +metadata item. The returned length may be less than ``length``, for +example if the ioctl is interrupted. + +The metadata returned by FS_IOC_READ_VERITY_METADATA isn't guaranteed +to be authenticated against the file digest that would be returned by +`FS_IOC_MEASURE_VERITY`_, as the metadata is expected to be used to +implement fs-verity compatible verification anyway (though absent a +malicious disk, the metadata will indeed match). E.g. to implement +this ioctl, the filesystem is allowed to just read the Merkle tree +blocks from disk without actually verifying the path to the root node. + +FS_IOC_READ_VERITY_METADATA can fail with the following errors: + +- ``EFAULT``: the caller provided inaccessible memory +- ``EINTR``: the ioctl was interrupted before any data was read +- ``EINVAL``: reserved fields were set, or ``offset + length`` + overflowed +- ``ENODATA``: the file is not a verity file +- ``ENOTTY``: this type of filesystem does not implement fs-verity, or + this ioctl is not yet implemented on it +- ``EOPNOTSUPP``: the kernel was not configured with fs-verity + support, or the filesystem superblock has not had the 'verity' + feature enabled on it. (See `Filesystem support`_.) + FS_IOC_GETFLAGS --------------- diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index d9665d2f82db..713b1ae44c1a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1309,6 +1309,12 @@ out: return -EOPNOTSUPP; return fsverity_ioctl_measure(filp, (void __user *)arg); + case FS_IOC_READ_VERITY_METADATA: + if (!ext4_has_feature_verity(sb)) + return -EOPNOTSUPP; + return fsverity_ioctl_read_metadata(filp, + (const void __user *)arg); + default: return -ENOTTY; } @@ -1391,6 +1397,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FS_IOC_GETFSMAP: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: + case FS_IOC_READ_VERITY_METADATA: case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f585545277d7..d0aefb5b97fa 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3357,6 +3357,14 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) return fsverity_ioctl_measure(filp, (void __user *)arg); } +static int f2fs_ioc_read_verity_metadata(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); +} + static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -4272,6 +4280,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_enable_verity(filp, arg); case FS_IOC_MEASURE_VERITY: return f2fs_ioc_measure_verity(filp, arg); + case FS_IOC_READ_VERITY_METADATA: + return f2fs_ioc_read_verity_metadata(filp, arg); case FS_IOC_GETFSLABEL: return f2fs_ioc_getfslabel(filp, arg); case FS_IOC_SETFSLABEL: @@ -4523,6 +4533,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_RESIZE_FS: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: + case FS_IOC_READ_VERITY_METADATA: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: case F2FS_IOC_GET_COMPRESS_BLOCKS: diff --git a/fs/verity/Makefile b/fs/verity/Makefile index 570e9136334d..435559a4fa9e 100644 --- a/fs/verity/Makefile +++ b/fs/verity/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_FS_VERITY) += enable.o \ init.o \ measure.o \ open.o \ + read_metadata.o \ verify.o obj-$(CONFIG_FS_VERITY_BUILTIN_SIGNATURES) += signature.o diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c new file mode 100644 index 000000000000..43be990fd53e --- /dev/null +++ b/fs/verity/read_metadata.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Ioctl to read verity metadata + * + * Copyright 2021 Google LLC + */ + +#include "fsverity_private.h" + +#include + +/** + * fsverity_ioctl_read_metadata() - read verity metadata from a file + * @filp: file to read the metadata from + * @uarg: user pointer to fsverity_read_metadata_arg + * + * Return: length read on success, 0 on EOF, -errno on failure + */ +int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg) +{ + struct inode *inode = file_inode(filp); + const struct fsverity_info *vi; + struct fsverity_read_metadata_arg arg; + int length; + void __user *buf; + + vi = fsverity_get_info(inode); + if (!vi) + return -ENODATA; /* not a verity file */ + /* + * Note that we don't have to explicitly check that the file is open for + * reading, since verity files can only be opened for reading. + */ + + if (copy_from_user(&arg, uarg, sizeof(arg))) + return -EFAULT; + + if (arg.__reserved) + return -EINVAL; + + /* offset + length must not overflow. */ + if (arg.offset + arg.length < arg.offset) + return -EINVAL; + + /* Ensure that the return value will fit in INT_MAX. */ + length = min_t(u64, arg.length, INT_MAX); + + buf = u64_to_user_ptr(arg.buf_ptr); + + switch (arg.metadata_type) { + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(fsverity_ioctl_read_metadata); diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index c1144a450392..b568b3c7d095 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -138,6 +138,10 @@ int fsverity_file_open(struct inode *inode, struct file *filp); int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); void fsverity_cleanup_inode(struct inode *inode); +/* read_metadata.c */ + +int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg); + /* verify.c */ bool fsverity_verify_page(struct page *page); @@ -183,6 +187,14 @@ static inline void fsverity_cleanup_inode(struct inode *inode) { } +/* read_metadata.c */ + +static inline int fsverity_ioctl_read_metadata(struct file *filp, + const void __user *uarg) +{ + return -EOPNOTSUPP; +} + /* verify.c */ static inline bool fsverity_verify_page(struct page *page) diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 33f44156f8ea..e062751294d0 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -83,7 +83,17 @@ struct fsverity_formatted_digest { __u8 digest[]; }; +struct fsverity_read_metadata_arg { + __u64 metadata_type; + __u64 offset; + __u64 length; + __u64 buf_ptr; + __u64 __reserved; +}; + #define FS_IOC_ENABLE_VERITY _IOW('f', 133, struct fsverity_enable_arg) #define FS_IOC_MEASURE_VERITY _IOWR('f', 134, struct fsverity_digest) +#define FS_IOC_READ_VERITY_METADATA \ + _IOWR('f', 135, struct fsverity_read_metadata_arg) #endif /* _UAPI_LINUX_FSVERITY_H */ -- cgit v1.2.3 From 622699cfe6ec5578f52727002d5717ff3f092e23 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:17 -0800 Subject: fs-verity: support reading Merkle tree with ioctl Add support for FS_VERITY_METADATA_TYPE_MERKLE_TREE to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the Merkle tree of a verity file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-5-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- Documentation/filesystems/fsverity.rst | 10 ++++- fs/verity/read_metadata.c | 70 ++++++++++++++++++++++++++++++++++ include/uapi/linux/fsverity.h | 2 + 3 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 9ef7a7de6008..50b47a6d9ea1 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -234,6 +234,8 @@ need this ioctl. This ioctl takes in a pointer to the following structure:: + #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 + struct fsverity_read_metadata_arg { __u64 metadata_type; __u64 offset; @@ -242,7 +244,13 @@ This ioctl takes in a pointer to the following structure:: __u64 __reserved; }; -``metadata_type`` specifies the type of metadata to read. +``metadata_type`` specifies the type of metadata to read: + +- ``FS_VERITY_METADATA_TYPE_MERKLE_TREE`` reads the blocks of the + Merkle tree. The blocks are returned in order from the root level + to the leaf level. Within each level, the blocks are returned in + the same order that their hashes are themselves hashed. + See `Merkle tree`_ for more information. The semantics are similar to those of ``pread()``. ``offset`` specifies the offset in bytes into the metadata item to read from, and diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 43be990fd53e..0f8ad2991cf9 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -7,8 +7,75 @@ #include "fsverity_private.h" +#include +#include +#include #include +static int fsverity_read_merkle_tree(struct inode *inode, + const struct fsverity_info *vi, + void __user *buf, u64 offset, int length) +{ + const struct fsverity_operations *vops = inode->i_sb->s_vop; + u64 end_offset; + unsigned int offs_in_page; + pgoff_t index, last_index; + int retval = 0; + int err = 0; + + end_offset = min(offset + length, vi->tree_params.tree_size); + if (offset >= end_offset) + return 0; + offs_in_page = offset_in_page(offset); + last_index = (end_offset - 1) >> PAGE_SHIFT; + + /* + * Iterate through each Merkle tree page in the requested range and copy + * the requested portion to userspace. Note that the Merkle tree block + * size isn't important here, as we are returning a byte stream; i.e., + * we can just work with pages even if the tree block size != PAGE_SIZE. + */ + for (index = offset >> PAGE_SHIFT; index <= last_index; index++) { + unsigned long num_ra_pages = + min_t(unsigned long, last_index - index + 1, + inode->i_sb->s_bdi->io_pages); + unsigned int bytes_to_copy = min_t(u64, end_offset - offset, + PAGE_SIZE - offs_in_page); + struct page *page; + const void *virt; + + page = vops->read_merkle_tree_page(inode, index, num_ra_pages); + if (IS_ERR(page)) { + err = PTR_ERR(page); + fsverity_err(inode, + "Error %d reading Merkle tree page %lu", + err, index); + break; + } + + virt = kmap(page); + if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) { + kunmap(page); + put_page(page); + err = -EFAULT; + break; + } + kunmap(page); + put_page(page); + + retval += bytes_to_copy; + buf += bytes_to_copy; + offset += bytes_to_copy; + + if (fatal_signal_pending(current)) { + err = -EINTR; + break; + } + cond_resched(); + offs_in_page = 0; + } + return retval ? retval : err; +} /** * fsverity_ioctl_read_metadata() - read verity metadata from a file * @filp: file to read the metadata from @@ -48,6 +115,9 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg) buf = u64_to_user_ptr(arg.buf_ptr); switch (arg.metadata_type) { + case FS_VERITY_METADATA_TYPE_MERKLE_TREE: + return fsverity_read_merkle_tree(inode, vi, buf, arg.offset, + length); default: return -EINVAL; } diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index e062751294d0..94003b153cb3 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -83,6 +83,8 @@ struct fsverity_formatted_digest { __u8 digest[]; }; +#define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 + struct fsverity_read_metadata_arg { __u64 metadata_type; __u64 offset; -- cgit v1.2.3 From 947191ac8caba85e25e0e036b0f097fee9e817f3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:18 -0800 Subject: fs-verity: support reading descriptor with ioctl Add support for FS_VERITY_METADATA_TYPE_DESCRIPTOR to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the fs-verity descriptor of a file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. "fs-verity descriptor" here means only the part that userspace cares about because it is hashed to produce the file digest. It doesn't include the signature which ext4 and f2fs append to the fsverity_descriptor struct when storing it on-disk, since that way of storing the signature is an implementation detail. The next patch adds a separate metadata_type value for retrieving the signature separately. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-6-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- Documentation/filesystems/fsverity.rst | 4 ++++ fs/verity/read_metadata.c | 40 ++++++++++++++++++++++++++++++++++ include/uapi/linux/fsverity.h | 1 + 3 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 50b47a6d9ea1..6dc5772037ef 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -235,6 +235,7 @@ need this ioctl. This ioctl takes in a pointer to the following structure:: #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 + #define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 struct fsverity_read_metadata_arg { __u64 metadata_type; @@ -252,6 +253,9 @@ This ioctl takes in a pointer to the following structure:: the same order that their hashes are themselves hashed. See `Merkle tree`_ for more information. +- ``FS_VERITY_METADATA_TYPE_DESCRIPTOR`` reads the fs-verity + descriptor. See `fs-verity descriptor`_. + The semantics are similar to those of ``pread()``. ``offset`` specifies the offset in bytes into the metadata item to read from, and ``length`` specifies the maximum number of bytes to read from the diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 0f8ad2991cf9..2dea6dd3bb05 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -76,6 +76,44 @@ static int fsverity_read_merkle_tree(struct inode *inode, } return retval ? retval : err; } + +/* Copy the requested portion of the buffer to userspace. */ +static int fsverity_read_buffer(void __user *dst, u64 offset, int length, + const void *src, size_t src_length) +{ + if (offset >= src_length) + return 0; + src += offset; + src_length -= offset; + + length = min_t(size_t, length, src_length); + + if (copy_to_user(dst, src, length)) + return -EFAULT; + + return length; +} + +static int fsverity_read_descriptor(struct inode *inode, + void __user *buf, u64 offset, int length) +{ + struct fsverity_descriptor *desc; + size_t desc_size; + int res; + + res = fsverity_get_descriptor(inode, &desc, &desc_size); + if (res) + return res; + + /* don't include the signature */ + desc_size = offsetof(struct fsverity_descriptor, signature); + desc->sig_size = 0; + + res = fsverity_read_buffer(buf, offset, length, desc, desc_size); + + kfree(desc); + return res; +} /** * fsverity_ioctl_read_metadata() - read verity metadata from a file * @filp: file to read the metadata from @@ -118,6 +156,8 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg) case FS_VERITY_METADATA_TYPE_MERKLE_TREE: return fsverity_read_merkle_tree(inode, vi, buf, arg.offset, length); + case FS_VERITY_METADATA_TYPE_DESCRIPTOR: + return fsverity_read_descriptor(inode, buf, arg.offset, length); default: return -EINVAL; } diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 94003b153cb3..41abc283dbcc 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -84,6 +84,7 @@ struct fsverity_formatted_digest { }; #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 +#define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 struct fsverity_read_metadata_arg { __u64 metadata_type; -- cgit v1.2.3 From 07c99001312cbf90a357d4877a358f796eede65b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:19 -0800 Subject: fs-verity: support reading signature with ioctl Add support for FS_VERITY_METADATA_TYPE_SIGNATURE to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the built-in signature (if present) of a verity file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. The ability for userspace to read the built-in signatures is also useful because it allows a system that is using the in-kernel signature verification to migrate to userspace signature verification. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-7-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- Documentation/filesystems/fsverity.rst | 9 ++++++++- fs/verity/read_metadata.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/fsverity.h | 1 + 3 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 6dc5772037ef..1d831e3cbcb3 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -236,6 +236,7 @@ This ioctl takes in a pointer to the following structure:: #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 #define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 + #define FS_VERITY_METADATA_TYPE_SIGNATURE 3 struct fsverity_read_metadata_arg { __u64 metadata_type; @@ -256,6 +257,10 @@ This ioctl takes in a pointer to the following structure:: - ``FS_VERITY_METADATA_TYPE_DESCRIPTOR`` reads the fs-verity descriptor. See `fs-verity descriptor`_. +- ``FS_VERITY_METADATA_TYPE_SIGNATURE`` reads the signature which was + passed to FS_IOC_ENABLE_VERITY, if any. See `Built-in signature + verification`_. + The semantics are similar to those of ``pread()``. ``offset`` specifies the offset in bytes into the metadata item to read from, and ``length`` specifies the maximum number of bytes to read from the @@ -279,7 +284,9 @@ FS_IOC_READ_VERITY_METADATA can fail with the following errors: - ``EINTR``: the ioctl was interrupted before any data was read - ``EINVAL``: reserved fields were set, or ``offset + length`` overflowed -- ``ENODATA``: the file is not a verity file +- ``ENODATA``: the file is not a verity file, or + FS_VERITY_METADATA_TYPE_SIGNATURE was requested but the file doesn't + have a built-in signature - ``ENOTTY``: this type of filesystem does not implement fs-verity, or this ioctl is not yet implemented on it - ``EOPNOTSUPP``: the kernel was not configured with fs-verity diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 2dea6dd3bb05..7e2d0c7bdf0d 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -114,6 +114,34 @@ static int fsverity_read_descriptor(struct inode *inode, kfree(desc); return res; } + +static int fsverity_read_signature(struct inode *inode, + void __user *buf, u64 offset, int length) +{ + struct fsverity_descriptor *desc; + size_t desc_size; + int res; + + res = fsverity_get_descriptor(inode, &desc, &desc_size); + if (res) + return res; + + if (desc->sig_size == 0) { + res = -ENODATA; + goto out; + } + + /* + * Include only the signature. Note that fsverity_get_descriptor() + * already verified that sig_size is in-bounds. + */ + res = fsverity_read_buffer(buf, offset, length, desc->signature, + le32_to_cpu(desc->sig_size)); +out: + kfree(desc); + return res; +} + /** * fsverity_ioctl_read_metadata() - read verity metadata from a file * @filp: file to read the metadata from @@ -158,6 +186,8 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg) length); case FS_VERITY_METADATA_TYPE_DESCRIPTOR: return fsverity_read_descriptor(inode, buf, arg.offset, length); + case FS_VERITY_METADATA_TYPE_SIGNATURE: + return fsverity_read_signature(inode, buf, arg.offset, length); default: return -EINVAL; } diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 41abc283dbcc..15384e22e331 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -85,6 +85,7 @@ struct fsverity_formatted_digest { #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 #define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 +#define FS_VERITY_METADATA_TYPE_SIGNATURE 3 struct fsverity_read_metadata_arg { __u64 metadata_type; -- cgit v1.2.3 From 866eef48d80234e1ea3a2f78b54afc563be3ea4a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 5 Feb 2021 17:10:18 +0000 Subject: gfs2: Add trusted xattr support Add support for an additional filesystem version (sb_fs_format = 1802). When a filesystem with the new version is mounted, the filesystem supports "trusted.*" xattrs. In addition, version 1802 filesystems implement a form of forward compatibility for xattrs: when xattrs with an unknown prefix (ea_type) are found on a version 1802 filesystem, those attributes are not shown by listxattr, and they are not accessible by getxattr, setxattr, or removexattr. This mechanism might turn out to be what we need in the future, but if not, we can always bump the filesystem version and break compatibility instead. Signed-off-by: Andreas Gruenbacher Signed-off-by: Andrew Price --- fs/gfs2/ops_fstype.c | 14 +++++++++++- fs/gfs2/super.h | 4 +++- fs/gfs2/xattr.c | 48 ++++++++++++++++++++++++++++++++++++---- include/uapi/linux/gfs2_ondisk.h | 5 +++-- 4 files changed, 63 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6537e94f4d8..d89764856f21 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -489,6 +489,19 @@ static int init_sb(struct gfs2_sbd *sdp, int silent) goto out; } + switch(sdp->sd_sb.sb_fs_format) { + case GFS2_FS_FORMAT_MAX: + sb->s_xattr = gfs2_xattr_handlers_max; + break; + + case GFS2_FS_FORMAT_MIN: + sb->s_xattr = gfs2_xattr_handlers_min; + break; + + default: + BUG(); + } + /* Set up the buffer cache and SB for real */ if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) { ret = -EINVAL; @@ -1110,7 +1123,6 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &gfs2_super_ops; sb->s_d_op = &gfs2_dops; sb->s_export_op = &gfs2_export_ops; - sb->s_xattr = gfs2_xattr_handlers; sb->s_qcop = &gfs2_quotactl_ops; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 977079693bdc..08e502dec7ec 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -58,7 +58,9 @@ extern struct file_system_type gfs2meta_fs_type; extern const struct export_operations gfs2_export_ops; extern const struct super_operations gfs2_super_ops; extern const struct dentry_operations gfs2_dops; -extern const struct xattr_handler *gfs2_xattr_handlers[]; + +extern const struct xattr_handler *gfs2_xattr_handlers_max[]; +extern const struct xattr_handler **gfs2_xattr_handlers_min; #endif /* __SUPER_DOT_H__ */ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 9d7667bc4292..2b520ac49d5f 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -70,6 +70,20 @@ static int ea_check_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize) return 0; } +static bool gfs2_eatype_valid(struct gfs2_sbd *sdp, u8 type) +{ + switch(sdp->sd_sb.sb_fs_format) { + case GFS2_FS_FORMAT_MAX: + return true; + + case GFS2_FS_FORMAT_MIN: + return type <= GFS2_EATYPE_SECURITY; + + default: + return false; + } +} + typedef int (*ea_call_t) (struct gfs2_inode *ip, struct buffer_head *bh, struct gfs2_ea_header *ea, struct gfs2_ea_header *prev, void *private); @@ -77,6 +91,7 @@ typedef int (*ea_call_t) (struct gfs2_inode *ip, struct buffer_head *bh, static int ea_foreach_i(struct gfs2_inode *ip, struct buffer_head *bh, ea_call_t ea_call, void *data) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_ea_header *ea, *prev = NULL; int error = 0; @@ -89,9 +104,8 @@ static int ea_foreach_i(struct gfs2_inode *ip, struct buffer_head *bh, if (!(bh->b_data <= (char *)ea && (char *)GFS2_EA2NEXT(ea) <= bh->b_data + bh->b_size)) goto fail; - if (!GFS2_EATYPE_VALID(ea->ea_type)) + if (!gfs2_eatype_valid(sdp, ea->ea_type)) goto fail; - error = ea_call(ip, bh, ea, prev, data); if (error) return error; @@ -344,6 +358,7 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, struct gfs2_ea_header *ea, struct gfs2_ea_header *prev, void *private) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct ea_list *ei = private; struct gfs2_ea_request *er = ei->ei_er; unsigned int ea_size; @@ -353,6 +368,8 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, if (ea->ea_type == GFS2_EATYPE_UNUSED) return 0; + BUG_ON(ea->ea_type > GFS2_EATYPE_SECURITY && + sdp->sd_sb.sb_fs_format == GFS2_FS_FORMAT_MIN); switch (ea->ea_type) { case GFS2_EATYPE_USR: prefix = "user."; @@ -366,8 +383,12 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh, prefix = "security."; l = 9; break; + case GFS2_EATYPE_TRUSTED: + prefix = "trusted."; + l = 8; + break; default: - BUG(); + return 0; } ea_size = l + ea->ea_name_len + 1; @@ -1463,7 +1484,25 @@ static const struct xattr_handler gfs2_xattr_security_handler = { .set = gfs2_xattr_set, }; -const struct xattr_handler *gfs2_xattr_handlers[] = { +static bool +gfs2_xattr_trusted_list(struct dentry *dentry) +{ + return capable(CAP_SYS_ADMIN); +} + +static const struct xattr_handler gfs2_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .flags = GFS2_EATYPE_TRUSTED, + .list = gfs2_xattr_trusted_list, + .get = gfs2_xattr_get, + .set = gfs2_xattr_set, +}; + +const struct xattr_handler *gfs2_xattr_handlers_max[] = { + /* GFS2_FS_FORMAT_MAX */ + &gfs2_xattr_trusted_handler, + + /* GFS2_FS_FORMAT_MIN */ &gfs2_xattr_user_handler, &gfs2_xattr_security_handler, &posix_acl_access_xattr_handler, @@ -1471,3 +1510,4 @@ const struct xattr_handler *gfs2_xattr_handlers[] = { NULL, }; +const struct xattr_handler **gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h index 07e508e6691b..6ec4291bcc7a 100644 --- a/include/uapi/linux/gfs2_ondisk.h +++ b/include/uapi/linux/gfs2_ondisk.h @@ -47,7 +47,7 @@ #define GFS2_FORMAT_DE 1200 #define GFS2_FORMAT_QU 1500 /* These are part of the superblock */ -#define GFS2_FORMAT_FS 1801 +#define GFS2_FORMAT_FS 1802 #define GFS2_FORMAT_MULTI 1900 /* @@ -389,8 +389,9 @@ struct gfs2_leaf { #define GFS2_EATYPE_USR 1 #define GFS2_EATYPE_SYS 2 #define GFS2_EATYPE_SECURITY 3 +#define GFS2_EATYPE_TRUSTED 4 -#define GFS2_EATYPE_LAST 3 +#define GFS2_EATYPE_LAST 4 #define GFS2_EATYPE_VALID(x) ((x) <= GFS2_EATYPE_LAST) #define GFS2_EAFLAG_LAST 0x01 /* last ea in block */ -- cgit v1.2.3 From 49fc251360a10e6bff0d886c9e3c62008a1c4caf Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 7 Feb 2021 10:22:49 +0200 Subject: rtnetlink: Add RTM_F_OFFLOAD_FAILED flag The flag indicates to user space that route offload failed. Previous patch set added the ability to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed, but if the offload fails there is no indication to user-space. The flag will be used in subsequent patches by netdevsim and mlxsw to indicate to user space that route offload failed, so that users will have better visibility into the offload process. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index b841caa4657e..91e4ca064d61 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -319,6 +319,11 @@ enum rt_scope_t { #define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */ #define RTM_F_OFFLOAD 0x4000 /* route is offloaded */ #define RTM_F_TRAP 0x8000 /* route is trapping packets */ +#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value + * is chosen to avoid conflicts with + * other flags defined in + * include/uapi/linux/ipv6_route.h + */ /* Reserved table identifiers */ -- cgit v1.2.3 From 9c5137aedd112f78a968bdd2325de2ea06df46c0 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:28 +0800 Subject: virt: acrn: Introduce VM management interfaces The VM management interfaces expose several VM operations to ACRN userspace via ioctls. For example, creating VM, starting VM, destroying VM and so on. The ACRN Hypervisor needs to exchange data with the ACRN userspace during the VM operations. HSM provides VM operation ioctls to the ACRN userspace and communicates with the ACRN Hypervisor for VM operations via hypercalls. HSM maintains a list of User VM. Each User VM will be bound to an existing file descriptor of /dev/acrn_hsm. The User VM will be destroyed when the file descriptor is closed. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-7-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + MAINTAINERS | 1 + drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 21 +++++- drivers/virt/acrn/hsm.c | 76 ++++++++++++++++++++- drivers/virt/acrn/hypercall.h | 78 ++++++++++++++++++++++ drivers/virt/acrn/vm.c | 68 +++++++++++++++++++ include/uapi/linux/acrn.h | 58 ++++++++++++++++ 8 files changed, 301 insertions(+), 4 deletions(-) create mode 100644 drivers/virt/acrn/hypercall.h create mode 100644 drivers/virt/acrn/vm.c create mode 100644 include/uapi/linux/acrn.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 19d730f9d136..76c27dbae96b 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -320,6 +320,7 @@ Code Seq# Include File Comments 0xA0 all linux/sdp/sdp.h Industrial Device Project 0xA1 0 linux/vtpm_proxy.h TPM Emulator Proxy Driver +0xA2 all uapi/linux/acrn.h ACRN hypervisor 0xA3 80-8F Port ACL in development: 0xA3 90-9F linux/dtlk.h diff --git a/MAINTAINERS b/MAINTAINERS index 4ac781da514f..6b5990a28b44 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -443,6 +443,7 @@ S: Supported W: https://projectacrn.org F: Documentation/virt/acrn/ F: drivers/virt/acrn/ +F: include/uapi/linux/acrn.h AD1889 ALSA SOUND DRIVER L: linux-parisc@vger.kernel.org diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 6920ed798aaf..cf8b4ed5e74e 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o +acrn-y := hsm.o vm.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 29eedd696327..e5aba86cad8c 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -3,16 +3,35 @@ #ifndef __ACRN_HSM_DRV_H #define __ACRN_HSM_DRV_H +#include +#include +#include #include +#include "hypercall.h" + +extern struct miscdevice acrn_dev; + #define ACRN_INVALID_VMID (0xffffU) +#define ACRN_VM_FLAG_DESTROYED 0U /** * struct acrn_vm - Properties of ACRN User VM. + * @list: Entry within global list of all VMs * @vmid: User VM ID + * @vcpu_num: Number of virtual CPUs in the VM + * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM flag management + * in HSM which is different from the &acrn_vm_creation.vm_flag. */ struct acrn_vm { - u16 vmid; + struct list_head list; + u16 vmid; + int vcpu_num; + unsigned long flags; }; +struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, + struct acrn_vm_creation *vm_param); +int acrn_vm_destroy(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index a8dcb250649d..5fd933471683 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -9,7 +9,6 @@ * Yakui Zhao */ -#include #include #include #include @@ -38,10 +37,82 @@ static int acrn_dev_open(struct inode *inode, struct file *filp) return 0; } +/* + * HSM relies on hypercall layer of the ACRN hypervisor to do the + * sanity check against the input parameters. + */ +static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, + unsigned long ioctl_param) +{ + struct acrn_vm *vm = filp->private_data; + struct acrn_vm_creation *vm_param; + int ret = 0; + + if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { + dev_dbg(acrn_dev.this_device, + "ioctl 0x%x: Invalid VM state!\n", cmd); + return -EINVAL; + } + + switch (cmd) { + case ACRN_IOCTL_CREATE_VM: + vm_param = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vm_creation)); + if (IS_ERR(vm_param)) + return PTR_ERR(vm_param); + + if ((vm_param->reserved0 | vm_param->reserved1) != 0) + return -EINVAL; + + vm = acrn_vm_create(vm, vm_param); + if (!vm) { + ret = -EINVAL; + kfree(vm_param); + break; + } + + if (copy_to_user((void __user *)ioctl_param, vm_param, + sizeof(struct acrn_vm_creation))) { + acrn_vm_destroy(vm); + ret = -EFAULT; + } + + kfree(vm_param); + break; + case ACRN_IOCTL_START_VM: + ret = hcall_start_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to start VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_PAUSE_VM: + ret = hcall_pause_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to pause VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_RESET_VM: + ret = hcall_reset_vm(vm->vmid); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to restart VM %u!\n", vm->vmid); + break; + case ACRN_IOCTL_DESTROY_VM: + ret = acrn_vm_destroy(vm); + break; + default: + dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); + ret = -ENOTTY; + } + + return ret; +} + static int acrn_dev_release(struct inode *inode, struct file *filp) { struct acrn_vm *vm = filp->private_data; + acrn_vm_destroy(vm); kfree(vm); return 0; } @@ -50,9 +121,10 @@ static const struct file_operations acrn_fops = { .owner = THIS_MODULE, .open = acrn_dev_open, .release = acrn_dev_release, + .unlocked_ioctl = acrn_dev_ioctl, }; -static struct miscdevice acrn_dev = { +struct miscdevice acrn_dev = { .minor = MISC_DYNAMIC_MINOR, .name = "acrn_hsm", .fops = &acrn_fops, diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h new file mode 100644 index 000000000000..426b66cadb1f --- /dev/null +++ b/drivers/virt/acrn/hypercall.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * ACRN HSM: hypercalls of ACRN Hypervisor + */ +#ifndef __ACRN_HSM_HYPERCALL_H +#define __ACRN_HSM_HYPERCALL_H +#include + +/* + * Hypercall IDs of the ACRN Hypervisor + */ +#define _HC_ID(x, y) (((x) << 24) | (y)) + +#define HC_ID 0x80UL + +#define HC_ID_VM_BASE 0x10UL +#define HC_CREATE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x00) +#define HC_DESTROY_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x01) +#define HC_START_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x02) +#define HC_PAUSE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x03) +#define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) + +/** + * hcall_create_vm() - Create a User VM + * @vminfo: Service VM GPA of info of User VM creation + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_create_vm(u64 vminfo) +{ + return acrn_hypercall1(HC_CREATE_VM, vminfo); +} + +/** + * hcall_start_vm() - Start a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_start_vm(u64 vmid) +{ + return acrn_hypercall1(HC_START_VM, vmid); +} + +/** + * hcall_pause_vm() - Pause a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_pause_vm(u64 vmid) +{ + return acrn_hypercall1(HC_PAUSE_VM, vmid); +} + +/** + * hcall_destroy_vm() - Destroy a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_destroy_vm(u64 vmid) +{ + return acrn_hypercall1(HC_DESTROY_VM, vmid); +} + +/** + * hcall_reset_vm() - Reset a User VM + * @vmid: User VM ID + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_reset_vm(u64 vmid) +{ + return acrn_hypercall1(HC_RESET_VM, vmid); +} + +#endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c new file mode 100644 index 000000000000..3f667ac8ac1e --- /dev/null +++ b/drivers/virt/acrn/vm.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN_HSM: Virtual Machine management + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Jason Chen CJ + * Yakui Zhao + */ +#include +#include +#include + +#include "acrn_drv.h" + +/* List of VMs */ +static LIST_HEAD(acrn_vm_list); +/* To protect acrn_vm_list */ +static DEFINE_MUTEX(acrn_vm_list_lock); + +struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, + struct acrn_vm_creation *vm_param) +{ + int ret; + + ret = hcall_create_vm(virt_to_phys(vm_param)); + if (ret < 0 || vm_param->vmid == ACRN_INVALID_VMID) { + dev_err(acrn_dev.this_device, + "Failed to create VM! Error: %d\n", ret); + return NULL; + } + + vm->vmid = vm_param->vmid; + vm->vcpu_num = vm_param->vcpu_num; + + mutex_lock(&acrn_vm_list_lock); + list_add(&vm->list, &acrn_vm_list); + mutex_unlock(&acrn_vm_list_lock); + + dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); + return vm; +} + +int acrn_vm_destroy(struct acrn_vm *vm) +{ + int ret; + + if (vm->vmid == ACRN_INVALID_VMID || + test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags)) + return 0; + + /* Remove from global VM list */ + mutex_lock(&acrn_vm_list_lock); + list_del_init(&vm->list); + mutex_unlock(&acrn_vm_list_lock); + + ret = hcall_destroy_vm(vm->vmid); + if (ret < 0) { + dev_err(acrn_dev.this_device, + "Failed to destroy VM %u\n", vm->vmid); + clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); + return ret; + } + dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid); + vm->vmid = ACRN_INVALID_VMID; + return 0; +} diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h new file mode 100644 index 000000000000..32521168075f --- /dev/null +++ b/include/uapi/linux/acrn.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace interface for /dev/acrn_hsm - ACRN Hypervisor Service Module + * + * This file can be used by applications that need to communicate with the HSM + * via the ioctl interface. + * + * Copyright (C) 2021 Intel Corporation. All rights reserved. + */ + +#ifndef _UAPI_ACRN_H +#define _UAPI_ACRN_H + +#include +#include + +/** + * struct acrn_vm_creation - Info to create a User VM + * @vmid: User VM ID returned from the hypervisor + * @reserved0: Reserved and must be 0 + * @vcpu_num: Number of vCPU in the VM. Return from hypervisor. + * @reserved1: Reserved and must be 0 + * @uuid: UUID of the VM. Pass to hypervisor directly. + * @vm_flag: Flag of the VM creating. Pass to hypervisor directly. + * @ioreq_buf: Service VM GPA of I/O request buffer. Pass to + * hypervisor directly. + * @cpu_affinity: CPU affinity of the VM. Pass to hypervisor directly. + * It's a bitmap which indicates CPUs used by the VM. + */ +struct acrn_vm_creation { + __u16 vmid; + __u16 reserved0; + __u16 vcpu_num; + __u16 reserved1; + guid_t uuid; + __u64 vm_flag; + __u64 ioreq_buf; + __u64 cpu_affinity; +}; + +/* The ioctl type, documented in ioctl-number.rst */ +#define ACRN_IOCTL_TYPE 0xA2 + +/* + * Common IOCTL IDs definition for ACRN userspace + */ +#define ACRN_IOCTL_CREATE_VM \ + _IOWR(ACRN_IOCTL_TYPE, 0x10, struct acrn_vm_creation) +#define ACRN_IOCTL_DESTROY_VM \ + _IO(ACRN_IOCTL_TYPE, 0x11) +#define ACRN_IOCTL_START_VM \ + _IO(ACRN_IOCTL_TYPE, 0x12) +#define ACRN_IOCTL_PAUSE_VM \ + _IO(ACRN_IOCTL_TYPE, 0x13) +#define ACRN_IOCTL_RESET_VM \ + _IO(ACRN_IOCTL_TYPE, 0x15) + +#endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 2ad2aaee1bc9568d0c146463483d2c926ef20055 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:29 +0800 Subject: virt: acrn: Introduce an ioctl to set vCPU registers state A virtual CPU of User VM has different context due to the different registers state. ACRN userspace needs to set the virtual CPU registers state (e.g. giving a initial registers state to a virtual BSP of a User VM). HSM provides an ioctl ACRN_IOCTL_SET_VCPU_REGS to do the virtual CPU registers state setting. The ioctl passes the registers state from ACRN userspace to the hypervisor directly. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-8-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 34 +++++++++++- drivers/virt/acrn/hypercall.h | 13 +++++ include/uapi/linux/acrn.h | 119 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 5fd933471683..ee5cc7413239 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -9,6 +9,7 @@ * Yakui Zhao */ +#include #include #include #include @@ -46,7 +47,8 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, { struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; - int ret = 0; + struct acrn_vcpu_regs *cpu_regs; + int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { dev_dbg(acrn_dev.this_device, @@ -100,6 +102,36 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, case ACRN_IOCTL_DESTROY_VM: ret = acrn_vm_destroy(vm); break; + case ACRN_IOCTL_SET_VCPU_REGS: + cpu_regs = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vcpu_regs)); + if (IS_ERR(cpu_regs)) + return PTR_ERR(cpu_regs); + + for (i = 0; i < ARRAY_SIZE(cpu_regs->reserved); i++) + if (cpu_regs->reserved[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_32); i++) + if (cpu_regs->vcpu_regs.reserved_32[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_64); i++) + if (cpu_regs->vcpu_regs.reserved_64[i]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.gdt.reserved); i++) + if (cpu_regs->vcpu_regs.gdt.reserved[i] | + cpu_regs->vcpu_regs.idt.reserved[i]) + return -EINVAL; + + ret = hcall_set_vcpu_regs(vm->vmid, virt_to_phys(cpu_regs)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set regs state of VM%u!\n", + vm->vmid); + kfree(cpu_regs); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 426b66cadb1f..f29cfae08862 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -19,6 +19,7 @@ #define HC_START_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x02) #define HC_PAUSE_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x03) #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) +#define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) /** * hcall_create_vm() - Create a User VM @@ -75,4 +76,16 @@ static inline long hcall_reset_vm(u64 vmid) return acrn_hypercall1(HC_RESET_VM, vmid); } +/** + * hcall_set_vcpu_regs() - Set up registers of virtual CPU of a User VM + * @vmid: User VM ID + * @regs_state: Service VM GPA of registers state + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) +{ + return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 32521168075f..775c58bad026 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -38,6 +38,123 @@ struct acrn_vm_creation { __u64 cpu_affinity; }; +/** + * struct acrn_gp_regs - General registers of a User VM + * @rax: Value of register RAX + * @rcx: Value of register RCX + * @rdx: Value of register RDX + * @rbx: Value of register RBX + * @rsp: Value of register RSP + * @rbp: Value of register RBP + * @rsi: Value of register RSI + * @rdi: Value of register RDI + * @r8: Value of register R8 + * @r9: Value of register R9 + * @r10: Value of register R10 + * @r11: Value of register R11 + * @r12: Value of register R12 + * @r13: Value of register R13 + * @r14: Value of register R14 + * @r15: Value of register R15 + */ +struct acrn_gp_regs { + __le64 rax; + __le64 rcx; + __le64 rdx; + __le64 rbx; + __le64 rsp; + __le64 rbp; + __le64 rsi; + __le64 rdi; + __le64 r8; + __le64 r9; + __le64 r10; + __le64 r11; + __le64 r12; + __le64 r13; + __le64 r14; + __le64 r15; +}; + +/** + * struct acrn_descriptor_ptr - Segment descriptor table of a User VM. + * @limit: Limit field. + * @base: Base field. + * @reserved: Reserved and must be 0. + */ +struct acrn_descriptor_ptr { + __le16 limit; + __le64 base; + __le16 reserved[3]; +} __attribute__ ((__packed__)); + +/** + * struct acrn_regs - Registers structure of a User VM + * @gprs: General registers + * @gdt: Global Descriptor Table + * @idt: Interrupt Descriptor Table + * @rip: Value of register RIP + * @cs_base: Base of code segment selector + * @cr0: Value of register CR0 + * @cr4: Value of register CR4 + * @cr3: Value of register CR3 + * @ia32_efer: Value of IA32_EFER MSR + * @rflags: Value of regsiter RFLAGS + * @reserved_64: Reserved and must be 0 + * @cs_ar: Attribute field of code segment selector + * @cs_limit: Limit field of code segment selector + * @reserved_32: Reserved and must be 0 + * @cs_sel: Value of code segment selector + * @ss_sel: Value of stack segment selector + * @ds_sel: Value of data segment selector + * @es_sel: Value of extra segment selector + * @fs_sel: Value of FS selector + * @gs_sel: Value of GS selector + * @ldt_sel: Value of LDT descriptor selector + * @tr_sel: Value of TSS descriptor selector + */ +struct acrn_regs { + struct acrn_gp_regs gprs; + struct acrn_descriptor_ptr gdt; + struct acrn_descriptor_ptr idt; + + __le64 rip; + __le64 cs_base; + __le64 cr0; + __le64 cr4; + __le64 cr3; + __le64 ia32_efer; + __le64 rflags; + __le64 reserved_64[4]; + + __le32 cs_ar; + __le32 cs_limit; + __le32 reserved_32[3]; + + __le16 cs_sel; + __le16 ss_sel; + __le16 ds_sel; + __le16 es_sel; + __le16 fs_sel; + __le16 gs_sel; + __le16 ldt_sel; + __le16 tr_sel; +}; + +/** + * struct acrn_vcpu_regs - Info of vCPU registers state + * @vcpu_id: vCPU ID + * @reserved: Reserved and must be 0 + * @vcpu_regs: vCPU registers state + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_vcpu_regs { + __u16 vcpu_id; + __u16 reserved[3]; + struct acrn_regs vcpu_regs; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -54,5 +171,7 @@ struct acrn_vm_creation { _IO(ACRN_IOCTL_TYPE, 0x13) #define ACRN_IOCTL_RESET_VM \ _IO(ACRN_IOCTL_TYPE, 0x15) +#define ACRN_IOCTL_SET_VCPU_REGS \ + _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 88f537d5e8ddc89c2622f4a2bc1eb28455e8339c Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:30 +0800 Subject: virt: acrn: Introduce EPT mapping management The HSM provides hypervisor services to the ACRN userspace. While launching a User VM, ACRN userspace needs to allocate memory and request the ACRN Hypervisor to set up the EPT mapping for the VM. A mapping cache is introduced for accelerating the translation between the Service VM kernel virtual address and User VM physical address. >From the perspective of the hypervisor, the types of GPA of User VM can be listed as following: 1) RAM region, which is used by User VM as system ram. 2) MMIO region, which is recognized by User VM as MMIO. MMIO region is used to be utilized for devices emulation. Generally, User VM RAM regions mapping is set up before VM started and is released in the User VM destruction. MMIO regions mapping may be set and unset dynamically during User VM running. To achieve this, ioctls ACRN_IOCTL_SET_MEMSEG and ACRN_IOCTL_UNSET_MEMSEG are introduced in HSM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-9-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 96 +++++++++++-- drivers/virt/acrn/hsm.c | 15 +++ drivers/virt/acrn/hypercall.h | 14 ++ drivers/virt/acrn/mm.c | 306 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 4 + include/uapi/linux/acrn.h | 49 +++++++ 7 files changed, 476 insertions(+), 10 deletions(-) create mode 100644 drivers/virt/acrn/mm.c (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index cf8b4ed5e74e..38bc44b6edcd 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o +acrn-y := hsm.o vm.o mm.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e5aba86cad8c..e47a45280eea 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -12,26 +12,104 @@ extern struct miscdevice acrn_dev; +#define ACRN_MEM_MAPPING_MAX 256 + +#define ACRN_MEM_REGION_ADD 0 +#define ACRN_MEM_REGION_DEL 2 +/** + * struct vm_memory_region_op - Hypervisor memory operation + * @type: Operation type (ACRN_MEM_REGION_*) + * @attr: Memory attribute (ACRN_MEM_TYPE_* | ACRN_MEM_ACCESS_*) + * @user_vm_pa: Physical address of User VM to be mapped. + * @service_vm_pa: Physical address of Service VM to be mapped. + * @size: Size of this region. + * + * Structure containing needed information that is provided to ACRN Hypervisor + * to manage the EPT mappings of a single memory region of the User VM. Several + * &struct vm_memory_region_op can be batched to ACRN Hypervisor, see &struct + * vm_memory_region_batch. + */ +struct vm_memory_region_op { + u32 type; + u32 attr; + u64 user_vm_pa; + u64 service_vm_pa; + u64 size; +}; + +/** + * struct vm_memory_region_batch - A batch of vm_memory_region_op. + * @vmid: A User VM ID. + * @reserved: Reserved. + * @regions_num: The number of vm_memory_region_op. + * @regions_gpa: Physical address of a vm_memory_region_op array. + * + * HC_VM_SET_MEMORY_REGIONS uses this structure to manage EPT mappings of + * multiple memory regions of a User VM. A &struct vm_memory_region_batch + * contains multiple &struct vm_memory_region_op for batch processing in the + * ACRN Hypervisor. + */ +struct vm_memory_region_batch { + u16 vmid; + u16 reserved[3]; + u32 regions_num; + u64 regions_gpa; +}; + +/** + * struct vm_memory_mapping - Memory map between a User VM and the Service VM + * @pages: Pages in Service VM kernel. + * @npages: Number of pages. + * @service_vm_va: Virtual address in Service VM kernel. + * @user_vm_pa: Physical address in User VM. + * @size: Size of this memory region. + * + * HSM maintains memory mappings between a User VM GPA and the Service VM + * kernel VA for accelerating the User VM GPA translation. + */ +struct vm_memory_mapping { + struct page **pages; + int npages; + void *service_vm_va; + u64 user_vm_pa; + size_t size; +}; + #define ACRN_INVALID_VMID (0xffffU) #define ACRN_VM_FLAG_DESTROYED 0U /** * struct acrn_vm - Properties of ACRN User VM. - * @list: Entry within global list of all VMs - * @vmid: User VM ID - * @vcpu_num: Number of virtual CPUs in the VM - * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM flag management - * in HSM which is different from the &acrn_vm_creation.vm_flag. + * @list: Entry within global list of all VMs. + * @vmid: User VM ID. + * @vcpu_num: Number of virtual CPUs in the VM. + * @flags: Flags (ACRN_VM_FLAG_*) of the VM. This is VM + * flag management in HSM which is different + * from the &acrn_vm_creation.vm_flag. + * @regions_mapping_lock: Lock to protect &acrn_vm.regions_mapping and + * &acrn_vm.regions_mapping_count. + * @regions_mapping: Memory mappings of this VM. + * @regions_mapping_count: Number of memory mapping of this VM. */ struct acrn_vm { - struct list_head list; - u16 vmid; - int vcpu_num; - unsigned long flags; + struct list_head list; + u16 vmid; + int vcpu_num; + unsigned long flags; + struct mutex regions_mapping_lock; + struct vm_memory_mapping regions_mapping[ACRN_MEM_MAPPING_MAX]; + int regions_mapping_count; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, struct acrn_vm_creation *vm_param); int acrn_vm_destroy(struct acrn_vm *vm); +int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa, + u64 size, u32 mem_type, u32 mem_access_right); +int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size); +int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); +void acrn_vm_all_ram_unmap(struct acrn_vm *vm); #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index ee5cc7413239..2c40d3dc5e94 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -48,6 +48,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; + struct acrn_vm_memmap memmap; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -132,6 +133,20 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, vm->vmid); kfree(cpu_regs); break; + case ACRN_IOCTL_SET_MEMSEG: + if (copy_from_user(&memmap, (void __user *)ioctl_param, + sizeof(memmap))) + return -EFAULT; + + ret = acrn_vm_memseg_map(vm, &memmap); + break; + case ACRN_IOCTL_UNSET_MEMSEG: + if (copy_from_user(&memmap, (void __user *)ioctl_param, + sizeof(memmap))) + return -EFAULT; + + ret = acrn_vm_memseg_unmap(vm, &memmap); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f29cfae08862..a1a70a071713 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,9 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_MEM_BASE 0x40UL +#define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -88,4 +91,15 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_set_memory_regions() - Inform the hypervisor to set up EPT mappings + * @regions_pa: Service VM GPA of &struct vm_memory_region_batch + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_memory_regions(u64 regions_pa) +{ + return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/drivers/virt/acrn/mm.c b/drivers/virt/acrn/mm.c new file mode 100644 index 000000000000..c4f2e15c8a2b --- /dev/null +++ b/drivers/virt/acrn/mm.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN: Memory mapping management + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Fei Li + * Shuo Liu + */ + +#include +#include +#include + +#include "acrn_drv.h" + +static int modify_region(struct acrn_vm *vm, struct vm_memory_region_op *region) +{ + struct vm_memory_region_batch *regions; + int ret; + + regions = kzalloc(sizeof(*regions), GFP_KERNEL); + if (!regions) + return -ENOMEM; + + regions->vmid = vm->vmid; + regions->regions_num = 1; + regions->regions_gpa = virt_to_phys(region); + + ret = hcall_set_memory_regions(virt_to_phys(regions)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set memory region for VM[%u]!\n", vm->vmid); + + kfree(regions); + return ret; +} + +/** + * acrn_mm_region_add() - Set up the EPT mapping of a memory region. + * @vm: User VM. + * @user_gpa: A GPA of User VM. + * @service_gpa: A GPA of Service VM. + * @size: Size of the region. + * @mem_type: Combination of ACRN_MEM_TYPE_*. + * @mem_access_right: Combination of ACRN_MEM_ACCESS_*. + * + * Return: 0 on success, <0 on error. + */ +int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa, + u64 size, u32 mem_type, u32 mem_access_right) +{ + struct vm_memory_region_op *region; + int ret = 0; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->type = ACRN_MEM_REGION_ADD; + region->user_vm_pa = user_gpa; + region->service_vm_pa = service_gpa; + region->size = size; + region->attr = ((mem_type & ACRN_MEM_TYPE_MASK) | + (mem_access_right & ACRN_MEM_ACCESS_RIGHT_MASK)); + ret = modify_region(vm, region); + + dev_dbg(acrn_dev.this_device, + "%s: user-GPA[%pK] service-GPA[%pK] size[0x%llx].\n", + __func__, (void *)user_gpa, (void *)service_gpa, size); + kfree(region); + return ret; +} + +/** + * acrn_mm_region_del() - Del the EPT mapping of a memory region. + * @vm: User VM. + * @user_gpa: A GPA of the User VM. + * @size: Size of the region. + * + * Return: 0 on success, <0 for error. + */ +int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size) +{ + struct vm_memory_region_op *region; + int ret = 0; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->type = ACRN_MEM_REGION_DEL; + region->user_vm_pa = user_gpa; + region->service_vm_pa = 0UL; + region->size = size; + region->attr = 0U; + + ret = modify_region(vm, region); + + dev_dbg(acrn_dev.this_device, "%s: user-GPA[%pK] size[0x%llx].\n", + __func__, (void *)user_gpa, size); + kfree(region); + return ret; +} + +int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + int ret; + + if (memmap->type == ACRN_MEMMAP_RAM) + return acrn_vm_ram_map(vm, memmap); + + if (memmap->type != ACRN_MEMMAP_MMIO) { + dev_dbg(acrn_dev.this_device, + "Invalid memmap type: %u\n", memmap->type); + return -EINVAL; + } + + ret = acrn_mm_region_add(vm, memmap->user_vm_pa, + memmap->service_vm_pa, memmap->len, + ACRN_MEM_TYPE_UC, memmap->attr); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Add memory region failed, VM[%u]!\n", vm->vmid); + + return ret; +} + +int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + int ret; + + if (memmap->type != ACRN_MEMMAP_MMIO) { + dev_dbg(acrn_dev.this_device, + "Invalid memmap type: %u\n", memmap->type); + return -EINVAL; + } + + ret = acrn_mm_region_del(vm, memmap->user_vm_pa, memmap->len); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Del memory region failed, VM[%u]!\n", vm->vmid); + + return ret; +} + +/** + * acrn_vm_ram_map() - Create a RAM EPT mapping of User VM. + * @vm: The User VM pointer + * @memmap: Info of the EPT mapping + * + * Return: 0 on success, <0 for error. + */ +int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) +{ + struct vm_memory_region_batch *regions_info; + int nr_pages, i = 0, order, nr_regions = 0; + struct vm_memory_mapping *region_mapping; + struct vm_memory_region_op *vm_region; + struct page **pages = NULL, *page; + void *remap_vaddr; + int ret, pinned; + u64 user_vm_pa; + + if (!vm || !memmap) + return -EINVAL; + + /* Get the page number of the map region */ + nr_pages = memmap->len >> PAGE_SHIFT; + pages = vzalloc(nr_pages * sizeof(struct page *)); + if (!pages) + return -ENOMEM; + + /* Lock the pages of user memory map region */ + pinned = pin_user_pages_fast(memmap->vma_base, + nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages); + if (pinned < 0) { + ret = pinned; + goto free_pages; + } else if (pinned != nr_pages) { + ret = -EFAULT; + goto put_pages; + } + + /* Create a kernel map for the map region */ + remap_vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!remap_vaddr) { + ret = -ENOMEM; + goto put_pages; + } + + /* Record Service VM va <-> User VM pa mapping */ + mutex_lock(&vm->regions_mapping_lock); + region_mapping = &vm->regions_mapping[vm->regions_mapping_count]; + if (vm->regions_mapping_count < ACRN_MEM_MAPPING_MAX) { + region_mapping->pages = pages; + region_mapping->npages = nr_pages; + region_mapping->size = memmap->len; + region_mapping->service_vm_va = remap_vaddr; + region_mapping->user_vm_pa = memmap->user_vm_pa; + vm->regions_mapping_count++; + } else { + dev_warn(acrn_dev.this_device, + "Run out of memory mapping slots!\n"); + ret = -ENOMEM; + mutex_unlock(&vm->regions_mapping_lock); + goto unmap_no_count; + } + mutex_unlock(&vm->regions_mapping_lock); + + /* Calculate count of vm_memory_region_op */ + while (i < nr_pages) { + page = pages[i]; + VM_BUG_ON_PAGE(PageTail(page), page); + order = compound_order(page); + nr_regions++; + i += 1 << order; + } + + /* Prepare the vm_memory_region_batch */ + regions_info = kzalloc(sizeof(*regions_info) + + sizeof(*vm_region) * nr_regions, + GFP_KERNEL); + if (!regions_info) { + ret = -ENOMEM; + goto unmap_kernel_map; + } + + /* Fill each vm_memory_region_op */ + vm_region = (struct vm_memory_region_op *)(regions_info + 1); + regions_info->vmid = vm->vmid; + regions_info->regions_num = nr_regions; + regions_info->regions_gpa = virt_to_phys(vm_region); + user_vm_pa = memmap->user_vm_pa; + i = 0; + while (i < nr_pages) { + u32 region_size; + + page = pages[i]; + VM_BUG_ON_PAGE(PageTail(page), page); + order = compound_order(page); + region_size = PAGE_SIZE << order; + vm_region->type = ACRN_MEM_REGION_ADD; + vm_region->user_vm_pa = user_vm_pa; + vm_region->service_vm_pa = page_to_phys(page); + vm_region->size = region_size; + vm_region->attr = (ACRN_MEM_TYPE_WB & ACRN_MEM_TYPE_MASK) | + (memmap->attr & ACRN_MEM_ACCESS_RIGHT_MASK); + + vm_region++; + user_vm_pa += region_size; + i += 1 << order; + } + + /* Inform the ACRN Hypervisor to set up EPT mappings */ + ret = hcall_set_memory_regions(virt_to_phys(regions_info)); + if (ret < 0) { + dev_dbg(acrn_dev.this_device, + "Failed to set regions, VM[%u]!\n", vm->vmid); + goto unset_region; + } + kfree(regions_info); + + dev_dbg(acrn_dev.this_device, + "%s: VM[%u] service-GVA[%pK] user-GPA[%pK] size[0x%llx]\n", + __func__, vm->vmid, + remap_vaddr, (void *)memmap->user_vm_pa, memmap->len); + return ret; + +unset_region: + kfree(regions_info); +unmap_kernel_map: + mutex_lock(&vm->regions_mapping_lock); + vm->regions_mapping_count--; + mutex_unlock(&vm->regions_mapping_lock); +unmap_no_count: + vunmap(remap_vaddr); +put_pages: + for (i = 0; i < pinned; i++) + unpin_user_page(pages[i]); +free_pages: + vfree(pages); + return ret; +} + +/** + * acrn_vm_all_ram_unmap() - Destroy a RAM EPT mapping of User VM. + * @vm: The User VM + */ +void acrn_vm_all_ram_unmap(struct acrn_vm *vm) +{ + struct vm_memory_mapping *region_mapping; + int i, j; + + mutex_lock(&vm->regions_mapping_lock); + for (i = 0; i < vm->regions_mapping_count; i++) { + region_mapping = &vm->regions_mapping[i]; + vunmap(region_mapping->service_vm_va); + for (j = 0; j < region_mapping->npages; j++) + unpin_user_page(region_mapping->pages[j]); + vfree(region_mapping->pages); + } + mutex_unlock(&vm->regions_mapping_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 3f667ac8ac1e..ff5df7acb551 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -31,6 +31,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, return NULL; } + mutex_init(&vm->regions_mapping_lock); vm->vmid = vm_param->vmid; vm->vcpu_num = vm_param->vcpu_num; @@ -62,6 +63,9 @@ int acrn_vm_destroy(struct acrn_vm *vm) clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags); return ret; } + + acrn_vm_all_ram_unmap(vm); + dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid); vm->vmid = ACRN_INVALID_VMID; return 0; diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 775c58bad026..ec4c61e7c170 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -155,6 +155,50 @@ struct acrn_vcpu_regs { struct acrn_regs vcpu_regs; }; +#define ACRN_MEM_ACCESS_RIGHT_MASK 0x00000007U +#define ACRN_MEM_ACCESS_READ 0x00000001U +#define ACRN_MEM_ACCESS_WRITE 0x00000002U +#define ACRN_MEM_ACCESS_EXEC 0x00000004U +#define ACRN_MEM_ACCESS_RWX (ACRN_MEM_ACCESS_READ | \ + ACRN_MEM_ACCESS_WRITE | \ + ACRN_MEM_ACCESS_EXEC) + +#define ACRN_MEM_TYPE_MASK 0x000007C0U +#define ACRN_MEM_TYPE_WB 0x00000040U +#define ACRN_MEM_TYPE_WT 0x00000080U +#define ACRN_MEM_TYPE_UC 0x00000100U +#define ACRN_MEM_TYPE_WC 0x00000200U +#define ACRN_MEM_TYPE_WP 0x00000400U + +/* Memory mapping types */ +#define ACRN_MEMMAP_RAM 0 +#define ACRN_MEMMAP_MMIO 1 + +/** + * struct acrn_vm_memmap - A EPT memory mapping info for a User VM. + * @type: Type of the memory mapping (ACRM_MEMMAP_*). + * Pass to hypervisor directly. + * @attr: Attribute of the memory mapping. + * Pass to hypervisor directly. + * @user_vm_pa: Physical address of User VM. + * Pass to hypervisor directly. + * @service_vm_pa: Physical address of Service VM. + * Pass to hypervisor directly. + * @vma_base: VMA address of Service VM. Pass to hypervisor directly. + * @len: Length of the memory mapping. + * Pass to hypervisor directly. + */ +struct acrn_vm_memmap { + __u32 type; + __u32 attr; + __u64 user_vm_pa; + union { + __u64 service_vm_pa; + __u64 vma_base; + }; + __u64 len; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -174,4 +218,9 @@ struct acrn_vcpu_regs { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_SET_MEMSEG \ + _IOW(ACRN_IOCTL_TYPE, 0x41, struct acrn_vm_memmap) +#define ACRN_IOCTL_UNSET_MEMSEG \ + _IOW(ACRN_IOCTL_TYPE, 0x42, struct acrn_vm_memmap) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 72f293de3ff40b57db573c1bf623f494f3446f74 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:31 +0800 Subject: virt: acrn: Introduce I/O request management An I/O request of a User VM, which is constructed by the hypervisor, is distributed by the ACRN Hypervisor Service Module to an I/O client corresponding to the address range of the I/O request. For each User VM, there is a shared 4-KByte memory region used for I/O requests communication between the hypervisor and Service VM. An I/O request is a 256-byte structure buffer, which is 'struct acrn_io_request', that is filled by an I/O handler of the hypervisor when a trapped I/O access happens in a User VM. ACRN userspace in the Service VM first allocates a 4-KByte page and passes the GPA (Guest Physical Address) of the buffer to the hypervisor. The buffer is used as an array of 16 I/O request slots with each I/O request slot being 256 bytes. This array is indexed by vCPU ID. An I/O client, which is 'struct acrn_ioreq_client', is responsible for handling User VM I/O requests whose accessed GPA falls in a certain range. Multiple I/O clients can be associated with each User VM. There is a special client associated with each User VM, called the default client, that handles all I/O requests that do not fit into the range of any other I/O clients. The ACRN userspace acts as the default client for each User VM. The state transitions of a ACRN I/O request are as follows. FREE -> PENDING -> PROCESSING -> COMPLETE -> FREE -> ... FREE: this I/O request slot is empty PENDING: a valid I/O request is pending in this slot PROCESSING: the I/O request is being processed COMPLETE: the I/O request has been processed An I/O request in COMPLETE or FREE state is owned by the hypervisor. HSM and ACRN userspace are in charge of processing the others. The processing flow of I/O requests are listed as following: a) The I/O handler of the hypervisor will fill an I/O request with PENDING state when a trapped I/O access happens in a User VM. b) The hypervisor makes an upcall, which is a notification interrupt, to the Service VM. c) The upcall handler schedules a worker to dispatch I/O requests. d) The worker looks for the PENDING I/O requests, assigns them to different registered clients based on the address of the I/O accesses, updates their state to PROCESSING, and notifies the corresponding client to handle. e) The notified client handles the assigned I/O requests. f) The HSM updates I/O requests states to COMPLETE and notifies the hypervisor of the completion via hypercalls. Cc: Davidlohr Bueso Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Acked-by: Davidlohr Bueso Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-10-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 82 +++++++ drivers/virt/acrn/hsm.c | 43 +++- drivers/virt/acrn/hypercall.h | 28 +++ drivers/virt/acrn/ioreq.c | 521 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 27 ++- include/uapi/linux/acrn.h | 150 ++++++++++++ 7 files changed, 843 insertions(+), 10 deletions(-) create mode 100644 drivers/virt/acrn/ioreq.c (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 38bc44b6edcd..21721cbf6a80 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o +acrn-y := hsm.o vm.o mm.o ioreq.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e47a45280eea..68bd8db6c8be 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -12,10 +12,15 @@ extern struct miscdevice acrn_dev; +#define ACRN_NAME_LEN 16 #define ACRN_MEM_MAPPING_MAX 256 #define ACRN_MEM_REGION_ADD 0 #define ACRN_MEM_REGION_DEL 2 + +struct acrn_vm; +struct acrn_ioreq_client; + /** * struct vm_memory_region_op - Hypervisor memory operation * @type: Operation type (ACRN_MEM_REGION_*) @@ -75,9 +80,63 @@ struct vm_memory_mapping { size_t size; }; +/** + * struct acrn_ioreq_buffer - Data for setting the ioreq buffer of User VM + * @ioreq_buf: The GPA of the IO request shared buffer of a VM + * + * The parameter for the HC_SET_IOREQ_BUFFER hypercall used to set up + * the shared I/O request buffer between Service VM and ACRN hypervisor. + */ +struct acrn_ioreq_buffer { + u64 ioreq_buf; +}; + +struct acrn_ioreq_range { + struct list_head list; + u32 type; + u64 start; + u64 end; +}; + +#define ACRN_IOREQ_CLIENT_DESTROYING 0U +typedef int (*ioreq_handler_t)(struct acrn_ioreq_client *client, + struct acrn_io_request *req); +/** + * struct acrn_ioreq_client - Structure of I/O client. + * @name: Client name + * @vm: The VM that the client belongs to + * @list: List node for this acrn_ioreq_client + * @is_default: If this client is the default one + * @flags: Flags (ACRN_IOREQ_CLIENT_*) + * @range_list: I/O ranges + * @range_lock: Lock to protect range_list + * @ioreqs_map: The pending I/O requests bitmap. + * @handler: I/O requests handler of this client + * @thread: The thread which executes the handler + * @wq: The wait queue for the handler thread parking + * @priv: Data for the thread + */ +struct acrn_ioreq_client { + char name[ACRN_NAME_LEN]; + struct acrn_vm *vm; + struct list_head list; + bool is_default; + unsigned long flags; + struct list_head range_list; + rwlock_t range_lock; + DECLARE_BITMAP(ioreqs_map, ACRN_IO_REQUEST_MAX); + ioreq_handler_t handler; + struct task_struct *thread; + wait_queue_head_t wq; + void *priv; +}; + #define ACRN_INVALID_VMID (0xffffU) #define ACRN_VM_FLAG_DESTROYED 0U +#define ACRN_VM_FLAG_CLEARING_IOREQ 1U +extern struct list_head acrn_vm_list; +extern rwlock_t acrn_vm_list_lock; /** * struct acrn_vm - Properties of ACRN User VM. * @list: Entry within global list of all VMs. @@ -90,6 +149,11 @@ struct vm_memory_mapping { * &acrn_vm.regions_mapping_count. * @regions_mapping: Memory mappings of this VM. * @regions_mapping_count: Number of memory mapping of this VM. + * @ioreq_clients_lock: Lock to protect ioreq_clients and default_client + * @ioreq_clients: The I/O request clients list of this VM + * @default_client: The default I/O request client + * @ioreq_buf: I/O request shared buffer + * @ioreq_page: The page of the I/O request shared buffer */ struct acrn_vm { struct list_head list; @@ -99,6 +163,11 @@ struct acrn_vm { struct mutex regions_mapping_lock; struct vm_memory_mapping regions_mapping[ACRN_MEM_MAPPING_MAX]; int regions_mapping_count; + spinlock_t ioreq_clients_lock; + struct list_head ioreq_clients; + struct acrn_ioreq_client *default_client; + struct acrn_io_request_buffer *ioreq_buf; + struct page *ioreq_page; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -112,4 +181,17 @@ int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap); void acrn_vm_all_ram_unmap(struct acrn_vm *vm); +int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma); +void acrn_ioreq_deinit(struct acrn_vm *vm); +int acrn_ioreq_intr_setup(void); +void acrn_ioreq_intr_remove(void); +void acrn_ioreq_request_clear(struct acrn_vm *vm); +int acrn_ioreq_client_wait(struct acrn_ioreq_client *client); +int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu); +struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, + ioreq_handler_t handler, + void *data, bool is_default, + const char *name); +void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 2c40d3dc5e94..1cc0c612dc09 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -48,6 +48,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm *vm = filp->private_data; struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; + struct acrn_ioreq_notify notify; struct acrn_vm_memmap memmap; int i, ret = 0; @@ -147,6 +148,35 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_CREATE_IOREQ_CLIENT: + if (vm->default_client) + return -EEXIST; + if (!acrn_ioreq_client_create(vm, NULL, NULL, true, "acrndm")) + ret = -EINVAL; + break; + case ACRN_IOCTL_DESTROY_IOREQ_CLIENT: + if (vm->default_client) + acrn_ioreq_client_destroy(vm->default_client); + break; + case ACRN_IOCTL_ATTACH_IOREQ_CLIENT: + if (vm->default_client) + ret = acrn_ioreq_client_wait(vm->default_client); + else + ret = -ENODEV; + break; + case ACRN_IOCTL_NOTIFY_REQUEST_FINISH: + if (copy_from_user(¬ify, (void __user *)ioctl_param, + sizeof(struct acrn_ioreq_notify))) + return -EFAULT; + + if (notify.reserved != 0) + return -EINVAL; + + ret = acrn_ioreq_request_default_complete(vm, notify.vcpu); + break; + case ACRN_IOCTL_CLEAR_VM_IOREQ: + acrn_ioreq_request_clear(vm); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; @@ -188,14 +218,23 @@ static int __init hsm_init(void) return -EPERM; ret = misc_register(&acrn_dev); - if (ret) + if (ret) { pr_err("Create misc dev failed!\n"); + return ret; + } - return ret; + ret = acrn_ioreq_intr_setup(); + if (ret) { + pr_err("Setup I/O request handler failed!\n"); + misc_deregister(&acrn_dev); + return ret; + } + return 0; } static void __exit hsm_exit(void) { + acrn_ioreq_intr_remove(); misc_deregister(&acrn_dev); } module_init(hsm_init); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index a1a70a071713..5eba29e3ed38 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,10 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_IOREQ_BASE 0x30UL +#define HC_SET_IOREQ_BUFFER _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x00) +#define HC_NOTIFY_REQUEST_FINISH _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x01) + #define HC_ID_MEM_BASE 0x40UL #define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) @@ -91,6 +95,30 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_set_ioreq_buffer() - Set up the shared buffer for I/O Requests. + * @vmid: User VM ID + * @buffer: Service VM GPA of the shared buffer + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_ioreq_buffer(u64 vmid, u64 buffer) +{ + return acrn_hypercall2(HC_SET_IOREQ_BUFFER, vmid, buffer); +} + +/** + * hcall_notify_req_finish() - Notify ACRN Hypervisor of I/O request completion. + * @vmid: User VM ID + * @vcpu: The vCPU which initiated the I/O request + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_notify_req_finish(u64 vmid, u64 vcpu) +{ + return acrn_hypercall2(HC_NOTIFY_REQUEST_FINISH, vmid, vcpu); +} + /** * hcall_set_memory_regions() - Inform the hypervisor to set up EPT mappings * @regions_pa: Service VM GPA of &struct vm_memory_region_batch diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c new file mode 100644 index 000000000000..51cb41ef7c72 --- /dev/null +++ b/drivers/virt/acrn/ioreq.c @@ -0,0 +1,521 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN_HSM: Handle I/O requests + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Jason Chen CJ + * Fengwei Yin + */ + +#include +#include +#include +#include +#include + +#include + +#include "acrn_drv.h" + +static void ioreq_pause(void); +static void ioreq_resume(void); + +static void ioreq_dispatcher(struct work_struct *work); +static struct workqueue_struct *ioreq_wq; +static DECLARE_WORK(ioreq_work, ioreq_dispatcher); + +static inline bool has_pending_request(struct acrn_ioreq_client *client) +{ + return !bitmap_empty(client->ioreqs_map, ACRN_IO_REQUEST_MAX); +} + +static inline bool is_destroying(struct acrn_ioreq_client *client) +{ + return test_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags); +} + +static int ioreq_complete_request(struct acrn_vm *vm, u16 vcpu, + struct acrn_io_request *acrn_req) +{ + bool polling_mode; + int ret = 0; + + polling_mode = acrn_req->completion_polling; + /* Add barrier() to make sure the writes are done before completion */ + smp_store_release(&acrn_req->processed, ACRN_IOREQ_STATE_COMPLETE); + + /* + * To fulfill the requirement of real-time in several industry + * scenarios, like automotive, ACRN can run under the partition mode, + * in which User VMs and Service VM are bound to dedicated CPU cores. + * Polling mode of handling the I/O request is introduced to achieve a + * faster I/O request handling. In polling mode, the hypervisor polls + * I/O request's completion. Once an I/O request is marked as + * ACRN_IOREQ_STATE_COMPLETE, hypervisor resumes from the polling point + * to continue the I/O request flow. Thus, the completion notification + * from HSM of I/O request is not needed. Please note, + * completion_polling needs to be read before the I/O request being + * marked as ACRN_IOREQ_STATE_COMPLETE to avoid racing with the + * hypervisor. + */ + if (!polling_mode) { + ret = hcall_notify_req_finish(vm->vmid, vcpu); + if (ret < 0) + dev_err(acrn_dev.this_device, + "Notify I/O request finished failed!\n"); + } + + return ret; +} + +static int acrn_ioreq_complete_request(struct acrn_ioreq_client *client, + u16 vcpu, + struct acrn_io_request *acrn_req) +{ + int ret; + + if (vcpu >= client->vm->vcpu_num) + return -EINVAL; + + clear_bit(vcpu, client->ioreqs_map); + if (!acrn_req) { + acrn_req = (struct acrn_io_request *)client->vm->ioreq_buf; + acrn_req += vcpu; + } + + ret = ioreq_complete_request(client->vm, vcpu, acrn_req); + + return ret; +} + +int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu) +{ + int ret = 0; + + spin_lock_bh(&vm->ioreq_clients_lock); + if (vm->default_client) + ret = acrn_ioreq_complete_request(vm->default_client, + vcpu, NULL); + spin_unlock_bh(&vm->ioreq_clients_lock); + + return ret; +} + +/* + * ioreq_task() is the execution entity of handler thread of an I/O client. + * The handler callback of the I/O client is called within the handler thread. + */ +static int ioreq_task(void *data) +{ + struct acrn_ioreq_client *client = data; + struct acrn_io_request *req; + unsigned long *ioreqs_map; + int vcpu, ret; + + /* + * Lockless access to ioreqs_map is safe, because + * 1) set_bit() and clear_bit() are atomic operations. + * 2) I/O requests arrives serialized. The access flow of ioreqs_map is: + * set_bit() - in ioreq_work handler + * Handler callback handles corresponding I/O request + * clear_bit() - in handler thread (include ACRN userspace) + * Mark corresponding I/O request completed + * Loop again if a new I/O request occurs + */ + ioreqs_map = client->ioreqs_map; + while (!kthread_should_stop()) { + acrn_ioreq_client_wait(client); + while (has_pending_request(client)) { + vcpu = find_first_bit(ioreqs_map, client->vm->vcpu_num); + req = client->vm->ioreq_buf->req_slot + vcpu; + ret = client->handler(client, req); + if (ret < 0) { + dev_err(acrn_dev.this_device, + "IO handle failure: %d\n", ret); + break; + } + acrn_ioreq_complete_request(client, vcpu, req); + } + } + + return 0; +} + +/* + * For the non-default I/O clients, give them chance to complete the current + * I/O requests if there are any. For the default I/O client, it is safe to + * clear all pending I/O requests because the clearing request is from ACRN + * userspace. + */ +void acrn_ioreq_request_clear(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client; + bool has_pending = false; + unsigned long vcpu; + int retry = 10; + + /* + * IO requests of this VM will be completed directly in + * acrn_ioreq_dispatch if ACRN_VM_FLAG_CLEARING_IOREQ flag is set. + */ + set_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags); + + /* + * acrn_ioreq_request_clear is only called in VM reset case. Simply + * wait 100ms in total for the IO requests' completion. + */ + do { + spin_lock_bh(&vm->ioreq_clients_lock); + list_for_each_entry(client, &vm->ioreq_clients, list) { + has_pending = has_pending_request(client); + if (has_pending) + break; + } + spin_unlock_bh(&vm->ioreq_clients_lock); + + if (has_pending) + schedule_timeout_interruptible(HZ / 100); + } while (has_pending && --retry > 0); + if (retry == 0) + dev_warn(acrn_dev.this_device, + "%s cannot flush pending request!\n", client->name); + + /* Clear all ioreqs belonging to the default client */ + spin_lock_bh(&vm->ioreq_clients_lock); + client = vm->default_client; + if (client) { + vcpu = find_next_bit(client->ioreqs_map, + ACRN_IO_REQUEST_MAX, 0); + while (vcpu < ACRN_IO_REQUEST_MAX) { + acrn_ioreq_complete_request(client, vcpu, NULL); + vcpu = find_next_bit(client->ioreqs_map, + ACRN_IO_REQUEST_MAX, vcpu + 1); + } + } + spin_unlock_bh(&vm->ioreq_clients_lock); + + /* Clear ACRN_VM_FLAG_CLEARING_IOREQ flag after the clearing */ + clear_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags); +} + +int acrn_ioreq_client_wait(struct acrn_ioreq_client *client) +{ + if (client->is_default) { + /* + * In the default client, a user space thread waits on the + * waitqueue. The is_destroying() check is used to notify user + * space the client is going to be destroyed. + */ + wait_event_interruptible(client->wq, + has_pending_request(client) || + is_destroying(client)); + if (is_destroying(client)) + return -ENODEV; + } else { + wait_event_interruptible(client->wq, + has_pending_request(client) || + kthread_should_stop()); + } + + return 0; +} + +static bool in_range(struct acrn_ioreq_range *range, + struct acrn_io_request *req) +{ + bool ret = false; + + if (range->type == req->type) { + switch (req->type) { + case ACRN_IOREQ_TYPE_MMIO: + if (req->reqs.mmio_request.address >= range->start && + (req->reqs.mmio_request.address + + req->reqs.mmio_request.size - 1) <= range->end) + ret = true; + break; + case ACRN_IOREQ_TYPE_PORTIO: + if (req->reqs.pio_request.address >= range->start && + (req->reqs.pio_request.address + + req->reqs.pio_request.size - 1) <= range->end) + ret = true; + break; + default: + break; + } + } + + return ret; +} + +static struct acrn_ioreq_client *find_ioreq_client(struct acrn_vm *vm, + struct acrn_io_request *req) +{ + struct acrn_ioreq_client *client, *found = NULL; + struct acrn_ioreq_range *range; + + lockdep_assert_held(&vm->ioreq_clients_lock); + + list_for_each_entry(client, &vm->ioreq_clients, list) { + read_lock_bh(&client->range_lock); + list_for_each_entry(range, &client->range_list, list) { + if (in_range(range, req)) { + found = client; + break; + } + } + read_unlock_bh(&client->range_lock); + if (found) + break; + } + return found ? found : vm->default_client; +} + +/** + * acrn_ioreq_client_create() - Create an ioreq client + * @vm: The VM that this client belongs to + * @handler: The ioreq_handler of ioreq client acrn_hsm will create a kernel + * thread and call the handler to handle I/O requests. + * @priv: Private data for the handler + * @is_default: If it is the default client + * @name: The name of ioreq client + * + * Return: acrn_ioreq_client pointer on success, NULL on error + */ +struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, + ioreq_handler_t handler, + void *priv, bool is_default, + const char *name) +{ + struct acrn_ioreq_client *client; + + if (!handler && !is_default) { + dev_dbg(acrn_dev.this_device, + "Cannot create non-default client w/o handler!\n"); + return NULL; + } + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return NULL; + + client->handler = handler; + client->vm = vm; + client->priv = priv; + client->is_default = is_default; + if (name) + strncpy(client->name, name, sizeof(client->name) - 1); + rwlock_init(&client->range_lock); + INIT_LIST_HEAD(&client->range_list); + init_waitqueue_head(&client->wq); + + if (client->handler) { + client->thread = kthread_run(ioreq_task, client, "VM%u-%s", + client->vm->vmid, client->name); + if (IS_ERR(client->thread)) { + kfree(client); + return NULL; + } + } + + spin_lock_bh(&vm->ioreq_clients_lock); + if (is_default) + vm->default_client = client; + else + list_add(&client->list, &vm->ioreq_clients); + spin_unlock_bh(&vm->ioreq_clients_lock); + + dev_dbg(acrn_dev.this_device, "Created ioreq client %s.\n", name); + return client; +} + +/** + * acrn_ioreq_client_destroy() - Destroy an ioreq client + * @client: The ioreq client + */ +void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client) +{ + struct acrn_ioreq_range *range, *next; + struct acrn_vm *vm = client->vm; + + dev_dbg(acrn_dev.this_device, + "Destroy ioreq client %s.\n", client->name); + ioreq_pause(); + set_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags); + if (client->is_default) + wake_up_interruptible(&client->wq); + else + kthread_stop(client->thread); + + spin_lock_bh(&vm->ioreq_clients_lock); + if (client->is_default) + vm->default_client = NULL; + else + list_del(&client->list); + spin_unlock_bh(&vm->ioreq_clients_lock); + + write_lock_bh(&client->range_lock); + list_for_each_entry_safe(range, next, &client->range_list, list) { + list_del(&range->list); + kfree(range); + } + write_unlock_bh(&client->range_lock); + kfree(client); + + ioreq_resume(); +} + +static int acrn_ioreq_dispatch(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client; + struct acrn_io_request *req; + int i; + + for (i = 0; i < vm->vcpu_num; i++) { + req = vm->ioreq_buf->req_slot + i; + + /* barrier the read of processed of acrn_io_request */ + if (smp_load_acquire(&req->processed) == + ACRN_IOREQ_STATE_PENDING) { + /* Complete the IO request directly in clearing stage */ + if (test_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags)) { + ioreq_complete_request(vm, i, req); + continue; + } + + spin_lock_bh(&vm->ioreq_clients_lock); + client = find_ioreq_client(vm, req); + if (!client) { + dev_err(acrn_dev.this_device, + "Failed to find ioreq client!\n"); + spin_unlock_bh(&vm->ioreq_clients_lock); + return -EINVAL; + } + if (!client->is_default) + req->kernel_handled = 1; + else + req->kernel_handled = 0; + /* + * Add barrier() to make sure the writes are done + * before setting ACRN_IOREQ_STATE_PROCESSING + */ + smp_store_release(&req->processed, + ACRN_IOREQ_STATE_PROCESSING); + set_bit(i, client->ioreqs_map); + wake_up_interruptible(&client->wq); + spin_unlock_bh(&vm->ioreq_clients_lock); + } + } + + return 0; +} + +static void ioreq_dispatcher(struct work_struct *work) +{ + struct acrn_vm *vm; + + read_lock(&acrn_vm_list_lock); + list_for_each_entry(vm, &acrn_vm_list, list) { + if (!vm->ioreq_buf) + break; + acrn_ioreq_dispatch(vm); + } + read_unlock(&acrn_vm_list_lock); +} + +static void ioreq_intr_handler(void) +{ + queue_work(ioreq_wq, &ioreq_work); +} + +static void ioreq_pause(void) +{ + /* Flush and unarm the handler to ensure no I/O requests pending */ + acrn_remove_intr_handler(); + drain_workqueue(ioreq_wq); +} + +static void ioreq_resume(void) +{ + /* Schedule after enabling in case other clients miss interrupt */ + acrn_setup_intr_handler(ioreq_intr_handler); + queue_work(ioreq_wq, &ioreq_work); +} + +int acrn_ioreq_intr_setup(void) +{ + acrn_setup_intr_handler(ioreq_intr_handler); + ioreq_wq = alloc_workqueue("ioreq_wq", + WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); + if (!ioreq_wq) { + dev_err(acrn_dev.this_device, "Failed to alloc workqueue!\n"); + acrn_remove_intr_handler(); + return -ENOMEM; + } + return 0; +} + +void acrn_ioreq_intr_remove(void) +{ + if (ioreq_wq) + destroy_workqueue(ioreq_wq); + acrn_remove_intr_handler(); +} + +int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma) +{ + struct acrn_ioreq_buffer *set_buffer; + struct page *page; + int ret; + + if (vm->ioreq_buf) + return -EEXIST; + + set_buffer = kzalloc(sizeof(*set_buffer), GFP_KERNEL); + if (!set_buffer) + return -ENOMEM; + + ret = pin_user_pages_fast(buf_vma, 1, + FOLL_WRITE | FOLL_LONGTERM, &page); + if (unlikely(ret != 1) || !page) { + dev_err(acrn_dev.this_device, "Failed to pin ioreq page!\n"); + ret = -EFAULT; + goto free_buf; + } + + vm->ioreq_buf = page_address(page); + vm->ioreq_page = page; + set_buffer->ioreq_buf = page_to_phys(page); + ret = hcall_set_ioreq_buffer(vm->vmid, virt_to_phys(set_buffer)); + if (ret < 0) { + dev_err(acrn_dev.this_device, "Failed to init ioreq buffer!\n"); + unpin_user_page(page); + vm->ioreq_buf = NULL; + goto free_buf; + } + + dev_dbg(acrn_dev.this_device, + "Init ioreq buffer %pK!\n", vm->ioreq_buf); + ret = 0; +free_buf: + kfree(set_buffer); + return ret; +} + +void acrn_ioreq_deinit(struct acrn_vm *vm) +{ + struct acrn_ioreq_client *client, *next; + + dev_dbg(acrn_dev.this_device, + "Deinit ioreq buffer %pK!\n", vm->ioreq_buf); + /* Destroy all clients belonging to this VM */ + list_for_each_entry_safe(client, next, &vm->ioreq_clients, list) + acrn_ioreq_client_destroy(client); + if (vm->default_client) + acrn_ioreq_client_destroy(vm->default_client); + + if (vm->ioreq_buf && vm->ioreq_page) { + unpin_user_page(vm->ioreq_page); + vm->ioreq_buf = NULL; + } +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index ff5df7acb551..2bc649c7c1d3 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -15,9 +15,12 @@ #include "acrn_drv.h" /* List of VMs */ -static LIST_HEAD(acrn_vm_list); -/* To protect acrn_vm_list */ -static DEFINE_MUTEX(acrn_vm_list_lock); +LIST_HEAD(acrn_vm_list); +/* + * acrn_vm_list is read in a worker thread which dispatch I/O requests and + * is wrote in VM creation ioctl. Use the rwlock mechanism to protect it. + */ +DEFINE_RWLOCK(acrn_vm_list_lock); struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, struct acrn_vm_creation *vm_param) @@ -32,12 +35,20 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, } mutex_init(&vm->regions_mapping_lock); + INIT_LIST_HEAD(&vm->ioreq_clients); + spin_lock_init(&vm->ioreq_clients_lock); vm->vmid = vm_param->vmid; vm->vcpu_num = vm_param->vcpu_num; - mutex_lock(&acrn_vm_list_lock); + if (acrn_ioreq_init(vm, vm_param->ioreq_buf) < 0) { + hcall_destroy_vm(vm_param->vmid); + vm->vmid = ACRN_INVALID_VMID; + return NULL; + } + + write_lock_bh(&acrn_vm_list_lock); list_add(&vm->list, &acrn_vm_list); - mutex_unlock(&acrn_vm_list_lock); + write_unlock_bh(&acrn_vm_list_lock); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; @@ -52,9 +63,11 @@ int acrn_vm_destroy(struct acrn_vm *vm) return 0; /* Remove from global VM list */ - mutex_lock(&acrn_vm_list_lock); + write_lock_bh(&acrn_vm_list_lock); list_del_init(&vm->list); - mutex_unlock(&acrn_vm_list_lock); + write_unlock_bh(&acrn_vm_list_lock); + + acrn_ioreq_deinit(vm); ret = hcall_destroy_vm(vm->vmid); if (ret < 0) { diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index ec4c61e7c170..b0f73ab5e4e8 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -14,6 +14,145 @@ #include #include +#define ACRN_IO_REQUEST_MAX 16 + +#define ACRN_IOREQ_STATE_PENDING 0 +#define ACRN_IOREQ_STATE_COMPLETE 1 +#define ACRN_IOREQ_STATE_PROCESSING 2 +#define ACRN_IOREQ_STATE_FREE 3 + +#define ACRN_IOREQ_TYPE_PORTIO 0 +#define ACRN_IOREQ_TYPE_MMIO 1 + +#define ACRN_IOREQ_DIR_READ 0 +#define ACRN_IOREQ_DIR_WRITE 1 + +/** + * struct acrn_mmio_request - Info of a MMIO I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @address: Access address of this MMIO I/O request + * @size: Access size of this MMIO I/O request + * @value: Read/write value of this MMIO I/O request + */ +struct acrn_mmio_request { + __u32 direction; + __u32 reserved; + __u64 address; + __u64 size; + __u64 value; +}; + +/** + * struct acrn_pio_request - Info of a PIO I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @address: Access address of this PIO I/O request + * @size: Access size of this PIO I/O request + * @value: Read/write value of this PIO I/O request + */ +struct acrn_pio_request { + __u32 direction; + __u32 reserved; + __u64 address; + __u64 size; + __u32 value; +}; + +/** + * struct acrn_io_request - 256-byte ACRN I/O request + * @type: Type of this request (ACRN_IOREQ_TYPE_*). + * @completion_polling: Polling flag. Hypervisor will poll completion of the + * I/O request if this flag set. + * @reserved0: Reserved fields. + * @reqs: Union of different types of request. Byte offset: 64. + * @reqs.pio_request: PIO request data of the I/O request. + * @reqs.mmio_request: MMIO request data of the I/O request. + * @reqs.data: Raw data of the I/O request. + * @reserved1: Reserved fields. + * @kernel_handled: Flag indicates this request need be handled in kernel. + * @processed: The status of this request (ACRN_IOREQ_STATE_*). + * + * The state transitions of ACRN I/O request: + * + * FREE -> PENDING -> PROCESSING -> COMPLETE -> FREE -> ... + * + * An I/O request in COMPLETE or FREE state is owned by the hypervisor. HSM and + * ACRN userspace are in charge of processing the others. + * + * On basis of the states illustrated above, a typical lifecycle of ACRN IO + * request would look like: + * + * Flow (assume the initial state is FREE) + * | + * | Service VM vCPU 0 Service VM vCPU x User vCPU y + * | + * | hypervisor: + * | fills in type, addr, etc. + * | pauses the User VM vCPU y + * | sets the state to PENDING (a) + * | fires an upcall to Service VM + * | + * | HSM: + * | scans for PENDING requests + * | sets the states to PROCESSING (b) + * | assigns the requests to clients (c) + * V + * | client: + * | scans for the assigned requests + * | handles the requests (d) + * | HSM: + * | sets states to COMPLETE + * | notifies the hypervisor + * | + * | hypervisor: + * | resumes User VM vCPU y (e) + * | + * | hypervisor: + * | post handling (f) + * V sets states to FREE + * + * Note that the procedures (a) to (f) in the illustration above require to be + * strictly processed in the order. One vCPU cannot trigger another request of + * I/O emulation before completing the previous one. + * + * Atomic and barriers are required when HSM and hypervisor accessing the state + * of &struct acrn_io_request. + * + */ +struct acrn_io_request { + __u32 type; + __u32 completion_polling; + __u32 reserved0[14]; + union { + struct acrn_pio_request pio_request; + struct acrn_mmio_request mmio_request; + __u64 data[8]; + } reqs; + __u32 reserved1; + __u32 kernel_handled; + __u32 processed; +} __attribute__((aligned(256))); + +struct acrn_io_request_buffer { + union { + struct acrn_io_request req_slot[ACRN_IO_REQUEST_MAX]; + __u8 reserved[4096]; + }; +}; + +/** + * struct acrn_ioreq_notify - The structure of ioreq completion notification + * @vmid: User VM ID + * @reserved: Reserved and should be 0 + * @vcpu: vCPU ID + */ +struct acrn_ioreq_notify { + __u16 vmid; + __u16 reserved; + __u32 vcpu; +}; + /** * struct acrn_vm_creation - Info to create a User VM * @vmid: User VM ID returned from the hypervisor @@ -218,6 +357,17 @@ struct acrn_vm_memmap { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_NOTIFY_REQUEST_FINISH \ + _IOW(ACRN_IOCTL_TYPE, 0x31, struct acrn_ioreq_notify) +#define ACRN_IOCTL_CREATE_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x32) +#define ACRN_IOCTL_ATTACH_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x33) +#define ACRN_IOCTL_DESTROY_IOREQ_CLIENT \ + _IO(ACRN_IOCTL_TYPE, 0x34) +#define ACRN_IOCTL_CLEAR_VM_IOREQ \ + _IO(ACRN_IOCTL_TYPE, 0x35) + #define ACRN_IOCTL_SET_MEMSEG \ _IOW(ACRN_IOCTL_TYPE, 0x41, struct acrn_vm_memmap) #define ACRN_IOCTL_UNSET_MEMSEG \ -- cgit v1.2.3 From 3c4c331667d4d9f1b5f3fdff9c4db36776da30ae Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:32 +0800 Subject: virt: acrn: Introduce PCI configuration space PIO accesses combiner A User VM can access its virtual PCI configuration spaces via port IO approach, which has two following steps: 1) writes address into port 0xCF8 2) put/get data in/from port 0xCFC To distribute a complete PCI configuration space access one time, HSM need to combine such two accesses together. Combine two paired PIO I/O requests into one PCI I/O request and continue the I/O request distribution. Cc: Greg Kroah-Hartman Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-11-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/acrn_drv.h | 2 ++ drivers/virt/acrn/ioreq.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 27 ++++++++++++++++ 3 files changed, 105 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 68bd8db6c8be..6c92a505fa20 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -154,6 +154,7 @@ extern rwlock_t acrn_vm_list_lock; * @default_client: The default I/O request client * @ioreq_buf: I/O request shared buffer * @ioreq_page: The page of the I/O request shared buffer + * @pci_conf_addr: Address of a PCI configuration access emulation */ struct acrn_vm { struct list_head list; @@ -168,6 +169,7 @@ struct acrn_vm { struct acrn_ioreq_client *default_client; struct acrn_io_request_buffer *ioreq_buf; struct page *ioreq_page; + u32 pci_conf_addr; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c index 51cb41ef7c72..d19c05582d38 100644 --- a/drivers/virt/acrn/ioreq.c +++ b/drivers/virt/acrn/ioreq.c @@ -222,6 +222,80 @@ int acrn_ioreq_client_wait(struct acrn_ioreq_client *client) return 0; } +static bool is_cfg_addr(struct acrn_io_request *req) +{ + return ((req->type == ACRN_IOREQ_TYPE_PORTIO) && + (req->reqs.pio_request.address == 0xcf8)); +} + +static bool is_cfg_data(struct acrn_io_request *req) +{ + return ((req->type == ACRN_IOREQ_TYPE_PORTIO) && + ((req->reqs.pio_request.address >= 0xcfc) && + (req->reqs.pio_request.address < (0xcfc + 4)))); +} + +/* The low 8-bit of supported pci_reg addr.*/ +#define PCI_LOWREG_MASK 0xFC +/* The high 4-bit of supported pci_reg addr */ +#define PCI_HIGHREG_MASK 0xF00 +/* Max number of supported functions */ +#define PCI_FUNCMAX 7 +/* Max number of supported slots */ +#define PCI_SLOTMAX 31 +/* Max number of supported buses */ +#define PCI_BUSMAX 255 +#define CONF1_ENABLE 0x80000000UL +/* + * A PCI configuration space access via PIO 0xCF8 and 0xCFC normally has two + * following steps: + * 1) writes address into 0xCF8 port + * 2) accesses data in/from 0xCFC + * This function combines such paired PCI configuration space I/O requests into + * one ACRN_IOREQ_TYPE_PCICFG type I/O request and continues the processing. + */ +static bool handle_cf8cfc(struct acrn_vm *vm, + struct acrn_io_request *req, u16 vcpu) +{ + int offset, pci_cfg_addr, pci_reg; + bool is_handled = false; + + if (is_cfg_addr(req)) { + WARN_ON(req->reqs.pio_request.size != 4); + if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_WRITE) + vm->pci_conf_addr = req->reqs.pio_request.value; + else + req->reqs.pio_request.value = vm->pci_conf_addr; + is_handled = true; + } else if (is_cfg_data(req)) { + if (!(vm->pci_conf_addr & CONF1_ENABLE)) { + if (req->reqs.pio_request.direction == + ACRN_IOREQ_DIR_READ) + req->reqs.pio_request.value = 0xffffffff; + is_handled = true; + } else { + offset = req->reqs.pio_request.address - 0xcfc; + + req->type = ACRN_IOREQ_TYPE_PCICFG; + pci_cfg_addr = vm->pci_conf_addr; + req->reqs.pci_request.bus = + (pci_cfg_addr >> 16) & PCI_BUSMAX; + req->reqs.pci_request.dev = + (pci_cfg_addr >> 11) & PCI_SLOTMAX; + req->reqs.pci_request.func = + (pci_cfg_addr >> 8) & PCI_FUNCMAX; + pci_reg = (pci_cfg_addr & PCI_LOWREG_MASK) + + ((pci_cfg_addr >> 16) & PCI_HIGHREG_MASK); + req->reqs.pci_request.reg = pci_reg + offset; + } + } + + if (is_handled) + ioreq_complete_request(vm, vcpu, req); + + return is_handled; +} + static bool in_range(struct acrn_ioreq_range *range, struct acrn_io_request *req) { @@ -382,6 +456,8 @@ static int acrn_ioreq_dispatch(struct acrn_vm *vm) ioreq_complete_request(vm, i, req); continue; } + if (handle_cf8cfc(vm, req, i)) + continue; spin_lock_bh(&vm->ioreq_clients_lock); client = find_ioreq_client(vm, req); diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b0f73ab5e4e8..da40f7ad13d9 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -23,6 +23,7 @@ #define ACRN_IOREQ_TYPE_PORTIO 0 #define ACRN_IOREQ_TYPE_MMIO 1 +#define ACRN_IOREQ_TYPE_PCICFG 2 #define ACRN_IOREQ_DIR_READ 0 #define ACRN_IOREQ_DIR_WRITE 1 @@ -59,6 +60,30 @@ struct acrn_pio_request { __u32 value; }; +/** + * struct acrn_pci_request - Info of a PCI I/O request + * @direction: Access direction of this request (ACRN_IOREQ_DIR_*) + * @reserved: Reserved for alignment and should be 0 + * @size: Access size of this PCI I/O request + * @value: Read/write value of this PIO I/O request + * @bus: PCI bus value of this PCI I/O request + * @dev: PCI device value of this PCI I/O request + * @func: PCI function value of this PCI I/O request + * @reg: PCI config space offset of this PCI I/O request + * + * Need keep same header layout with &struct acrn_pio_request. + */ +struct acrn_pci_request { + __u32 direction; + __u32 reserved[3]; + __u64 size; + __u32 value; + __u32 bus; + __u32 dev; + __u32 func; + __u32 reg; +}; + /** * struct acrn_io_request - 256-byte ACRN I/O request * @type: Type of this request (ACRN_IOREQ_TYPE_*). @@ -67,6 +92,7 @@ struct acrn_pio_request { * @reserved0: Reserved fields. * @reqs: Union of different types of request. Byte offset: 64. * @reqs.pio_request: PIO request data of the I/O request. + * @reqs.pci_request: PCI configuration space request data of the I/O request. * @reqs.mmio_request: MMIO request data of the I/O request. * @reqs.data: Raw data of the I/O request. * @reserved1: Reserved fields. @@ -126,6 +152,7 @@ struct acrn_io_request { __u32 reserved0[14]; union { struct acrn_pio_request pio_request; + struct acrn_pci_request pci_request; struct acrn_mmio_request mmio_request; __u64 data[8]; } reqs; -- cgit v1.2.3 From ce011e1363a1fe43de0ca05abc394022ee4fefeb Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:33 +0800 Subject: virt: acrn: Introduce interfaces for PCI device passthrough PCI device passthrough enables an OS in a virtual machine to directly access a PCI device in the host. It promises almost the native performance, which is required in performance-critical scenarios of ACRN. HSM provides the following ioctls: - Assign - ACRN_IOCTL_ASSIGN_PCIDEV Pass data struct acrn_pcidev from userspace to the hypervisor, and inform the hypervisor to assign a PCI device to a User VM. - De-assign - ACRN_IOCTL_DEASSIGN_PCIDEV Pass data struct acrn_pcidev from userspace to the hypervisor, and inform the hypervisor to de-assign a PCI device from a User VM. - Set a interrupt of a passthrough device - ACRN_IOCTL_SET_PTDEV_INTR Pass data struct acrn_ptdev_irq from userspace to the hypervisor, and inform the hypervisor to map a INTx interrupt of passthrough device of User VM. - Reset passthrough device interrupt - ACRN_IOCTL_RESET_PTDEV_INTR Pass data struct acrn_ptdev_irq from userspace to the hypervisor, and inform the hypervisor to unmap a INTx interrupt of passthrough device of User VM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-12-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 50 +++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 54 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 61 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 165 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 1cc0c612dc09..94d70b1c1e5c 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -49,7 +49,9 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm_creation *vm_param; struct acrn_vcpu_regs *cpu_regs; struct acrn_ioreq_notify notify; + struct acrn_ptdev_irq *irq_info; struct acrn_vm_memmap memmap; + struct acrn_pcidev *pcidev; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -148,6 +150,54 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_ASSIGN_PCIDEV: + pcidev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_pcidev)); + if (IS_ERR(pcidev)) + return PTR_ERR(pcidev); + + ret = hcall_assign_pcidev(vm->vmid, virt_to_phys(pcidev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to assign pci device!\n"); + kfree(pcidev); + break; + case ACRN_IOCTL_DEASSIGN_PCIDEV: + pcidev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_pcidev)); + if (IS_ERR(pcidev)) + return PTR_ERR(pcidev); + + ret = hcall_deassign_pcidev(vm->vmid, virt_to_phys(pcidev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to deassign pci device!\n"); + kfree(pcidev); + break; + case ACRN_IOCTL_SET_PTDEV_INTR: + irq_info = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_ptdev_irq)); + if (IS_ERR(irq_info)) + return PTR_ERR(irq_info); + + ret = hcall_set_ptdev_intr(vm->vmid, virt_to_phys(irq_info)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to configure intr for ptdev!\n"); + kfree(irq_info); + break; + case ACRN_IOCTL_RESET_PTDEV_INTR: + irq_info = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_ptdev_irq)); + if (IS_ERR(irq_info)) + return PTR_ERR(irq_info); + + ret = hcall_reset_ptdev_intr(vm->vmid, virt_to_phys(irq_info)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to reset intr for ptdev!\n"); + kfree(irq_info); + break; case ACRN_IOCTL_CREATE_IOREQ_CLIENT: if (vm->default_client) return -EEXIST; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 5eba29e3ed38..f448301832cf 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -28,6 +28,12 @@ #define HC_ID_MEM_BASE 0x40UL #define HC_VM_SET_MEMORY_REGIONS _HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02) +#define HC_ID_PCI_BASE 0x50UL +#define HC_SET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x03) +#define HC_RESET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x04) +#define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) +#define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -130,4 +136,52 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_assign_pcidev() - Assign a PCI device to a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_pcidev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_assign_pcidev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_ASSIGN_PCIDEV, vmid, addr); +} + +/** + * hcall_deassign_pcidev() - De-assign a PCI device from a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_pcidev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_deassign_pcidev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DEASSIGN_PCIDEV, vmid, addr); +} + +/** + * hcall_set_ptdev_intr() - Configure an interrupt for an assigned PCI device. + * @vmid: User VM ID + * @irq: Service VM GPA of the &struct acrn_ptdev_irq + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_ptdev_intr(u64 vmid, u64 irq) +{ + return acrn_hypercall2(HC_SET_PTDEV_INTR, vmid, irq); +} + +/** + * hcall_reset_ptdev_intr() - Reset an interrupt for an assigned PCI device. + * @vmid: User VM ID + * @irq: Service VM GPA of the &struct acrn_ptdev_irq + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_reset_ptdev_intr(u64 vmid, u64 irq) +{ + return acrn_hypercall2(HC_RESET_PTDEV_INTR, vmid, irq); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index da40f7ad13d9..b25ca8c33b92 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -365,6 +365,58 @@ struct acrn_vm_memmap { __u64 len; }; +/* Type of interrupt of a passthrough device */ +#define ACRN_PTDEV_IRQ_INTX 0 +#define ACRN_PTDEV_IRQ_MSI 1 +#define ACRN_PTDEV_IRQ_MSIX 2 +/** + * struct acrn_ptdev_irq - Interrupt data of a passthrough device. + * @type: Type (ACRN_PTDEV_IRQ_*) + * @virt_bdf: Virtual Bus/Device/Function + * @phys_bdf: Physical Bus/Device/Function + * @intx: Info of interrupt + * @intx.virt_pin: Virtual IOAPIC pin + * @intx.phys_pin: Physical IOAPIC pin + * @intx.is_pic_pin: Is PIC pin or not + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_ptdev_irq { + __u32 type; + __u16 virt_bdf; + __u16 phys_bdf; + + struct { + __u32 virt_pin; + __u32 phys_pin; + __u32 is_pic_pin; + } intx; +}; + +/* Type of PCI device assignment */ +#define ACRN_PTDEV_QUIRK_ASSIGN (1U << 0) + +#define ACRN_PCI_NUM_BARS 6 +/** + * struct acrn_pcidev - Info for assigning or de-assigning a PCI device + * @type: Type of the assignment + * @virt_bdf: Virtual Bus/Device/Function + * @phys_bdf: Physical Bus/Device/Function + * @intr_line: PCI interrupt line + * @intr_pin: PCI interrupt pin + * @bar: PCI BARs. + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_pcidev { + __u32 type; + __u16 virt_bdf; + __u16 phys_bdf; + __u8 intr_line; + __u8 intr_pin; + __u32 bar[ACRN_PCI_NUM_BARS]; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -400,4 +452,13 @@ struct acrn_vm_memmap { #define ACRN_IOCTL_UNSET_MEMSEG \ _IOW(ACRN_IOCTL_TYPE, 0x42, struct acrn_vm_memmap) +#define ACRN_IOCTL_SET_PTDEV_INTR \ + _IOW(ACRN_IOCTL_TYPE, 0x53, struct acrn_ptdev_irq) +#define ACRN_IOCTL_RESET_PTDEV_INTR \ + _IOW(ACRN_IOCTL_TYPE, 0x54, struct acrn_ptdev_irq) +#define ACRN_IOCTL_ASSIGN_PCIDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x55, struct acrn_pcidev) +#define ACRN_IOCTL_DEASSIGN_PCIDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From c7cf8d27244f2ccdde30c79eb6314c943bbeac28 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:34 +0800 Subject: virt: acrn: Introduce interrupt injection interfaces ACRN userspace need to inject virtual interrupts into a User VM in devices emulation. HSM needs provide interfaces to do so. Introduce following interrupt injection interfaces: ioctl ACRN_IOCTL_SET_IRQLINE: Pass data from userspace to the hypervisor, and inform the hypervisor to inject a virtual IOAPIC GSI interrupt to a User VM. ioctl ACRN_IOCTL_INJECT_MSI: Pass data struct acrn_msi_entry from userspace to the hypervisor, and inform the hypervisor to inject a virtual MSI to a User VM. ioctl ACRN_IOCTL_VM_INTR_MONITOR: Set a 4-Kbyte aligned shared page for statistics information of interrupts of a User VM. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-13-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/acrn_drv.h | 4 ++++ drivers/virt/acrn/hsm.c | 40 ++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 41 +++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 17 +++++++++++++++++ 5 files changed, 138 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 6c92a505fa20..068f0be769f6 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -155,6 +155,7 @@ extern rwlock_t acrn_vm_list_lock; * @ioreq_buf: I/O request shared buffer * @ioreq_page: The page of the I/O request shared buffer * @pci_conf_addr: Address of a PCI configuration access emulation + * @monitor_page: Page of interrupt statistics of User VM */ struct acrn_vm { struct list_head list; @@ -170,6 +171,7 @@ struct acrn_vm { struct acrn_io_request_buffer *ioreq_buf; struct page *ioreq_page; u32 pci_conf_addr; + struct page *monitor_page; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -196,4 +198,6 @@ struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm, const char *name); void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client); +int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 94d70b1c1e5c..419271f32be8 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -51,7 +51,9 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_ioreq_notify notify; struct acrn_ptdev_irq *irq_info; struct acrn_vm_memmap memmap; + struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; + struct page *page; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -198,6 +200,44 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, "Failed to reset intr for ptdev!\n"); kfree(irq_info); break; + case ACRN_IOCTL_SET_IRQLINE: + ret = hcall_set_irqline(vm->vmid, ioctl_param); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to set interrupt line!\n"); + break; + case ACRN_IOCTL_INJECT_MSI: + msi = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_msi_entry)); + if (IS_ERR(msi)) + return PTR_ERR(msi); + + ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to inject MSI!\n"); + kfree(msi); + break; + case ACRN_IOCTL_VM_INTR_MONITOR: + ret = pin_user_pages_fast(ioctl_param, 1, + FOLL_WRITE | FOLL_LONGTERM, &page); + if (unlikely(ret != 1)) { + dev_dbg(acrn_dev.this_device, + "Failed to pin intr hdr buffer!\n"); + return -EFAULT; + } + + ret = hcall_vm_intr_monitor(vm->vmid, page_to_phys(page)); + if (ret < 0) { + unpin_user_page(page); + dev_dbg(acrn_dev.this_device, + "Failed to monitor intr data!\n"); + return ret; + } + if (vm->monitor_page) + unpin_user_page(vm->monitor_page); + vm->monitor_page = page; + break; case ACRN_IOCTL_CREATE_IOREQ_CLIENT: if (vm->default_client) return -EEXIST; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f448301832cf..a8813397a3fe 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -21,6 +21,11 @@ #define HC_RESET_VM _HC_ID(HC_ID, HC_ID_VM_BASE + 0x05) #define HC_SET_VCPU_REGS _HC_ID(HC_ID, HC_ID_VM_BASE + 0x06) +#define HC_ID_IRQ_BASE 0x20UL +#define HC_INJECT_MSI _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x03) +#define HC_VM_INTR_MONITOR _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x04) +#define HC_SET_IRQLINE _HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x05) + #define HC_ID_IOREQ_BASE 0x30UL #define HC_SET_IOREQ_BUFFER _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x00) #define HC_NOTIFY_REQUEST_FINISH _HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x01) @@ -101,6 +106,42 @@ static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state) return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state); } +/** + * hcall_inject_msi() - Deliver a MSI interrupt to a User VM + * @vmid: User VM ID + * @msi: Service VM GPA of MSI message + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_inject_msi(u64 vmid, u64 msi) +{ + return acrn_hypercall2(HC_INJECT_MSI, vmid, msi); +} + +/** + * hcall_vm_intr_monitor() - Set a shared page for User VM interrupt statistics + * @vmid: User VM ID + * @addr: Service VM GPA of the shared page + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_vm_intr_monitor(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_VM_INTR_MONITOR, vmid, addr); +} + +/** + * hcall_set_irqline() - Set or clear an interrupt line + * @vmid: User VM ID + * @op: Service VM GPA of interrupt line operations + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_set_irqline(u64 vmid, u64 op) +{ + return acrn_hypercall2(HC_SET_IRQLINE, vmid, op); +} + /** * hcall_set_ioreq_buffer() - Set up the shared buffer for I/O Requests. * @vmid: User VM ID diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 2bc649c7c1d3..db597f27690a 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -68,6 +68,10 @@ int acrn_vm_destroy(struct acrn_vm *vm) write_unlock_bh(&acrn_vm_list_lock); acrn_ioreq_deinit(vm); + if (vm->monitor_page) { + put_page(vm->monitor_page); + vm->monitor_page = NULL; + } ret = hcall_destroy_vm(vm->vmid); if (ret < 0) { @@ -83,3 +87,35 @@ int acrn_vm_destroy(struct acrn_vm *vm) vm->vmid = ACRN_INVALID_VMID; return 0; } + +/** + * acrn_inject_msi() - Inject a MSI interrupt into a User VM + * @vm: User VM + * @msi_addr: The MSI address + * @msi_data: The MSI data + * + * Return: 0 on success, <0 on error + */ +int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data) +{ + struct acrn_msi_entry *msi; + int ret; + + /* might be used in interrupt context, so use GFP_ATOMIC */ + msi = kzalloc(sizeof(*msi), GFP_ATOMIC); + if (!msi) + return -ENOMEM; + + /* + * msi_addr: addr[19:12] with dest vcpu id + * msi_data: data[7:0] with vector + */ + msi->msi_addr = msi_addr; + msi->msi_data = msi_data; + ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi)); + if (ret < 0) + dev_err(acrn_dev.this_device, + "Failed to inject MSI to VM %u!\n", vm->vmid); + kfree(msi); + return ret; +} diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b25ca8c33b92..b1c06b28ebdc 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -417,6 +417,16 @@ struct acrn_pcidev { __u32 bar[ACRN_PCI_NUM_BARS]; }; +/** + * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM + * @msi_addr: MSI addr[19:12] with dest vCPU ID + * @msi_data: MSI data[7:0] with vector + */ +struct acrn_msi_entry { + __u64 msi_addr; + __u64 msi_data; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -436,6 +446,13 @@ struct acrn_pcidev { #define ACRN_IOCTL_SET_VCPU_REGS \ _IOW(ACRN_IOCTL_TYPE, 0x16, struct acrn_vcpu_regs) +#define ACRN_IOCTL_INJECT_MSI \ + _IOW(ACRN_IOCTL_TYPE, 0x23, struct acrn_msi_entry) +#define ACRN_IOCTL_VM_INTR_MONITOR \ + _IOW(ACRN_IOCTL_TYPE, 0x24, unsigned long) +#define ACRN_IOCTL_SET_IRQLINE \ + _IOW(ACRN_IOCTL_TYPE, 0x25, __u64) + #define ACRN_IOCTL_NOTIFY_REQUEST_FINISH \ _IOW(ACRN_IOCTL_TYPE, 0x31, struct acrn_ioreq_notify) #define ACRN_IOCTL_CREATE_IOREQ_CLIENT \ -- cgit v1.2.3 From 3d679d5aec648f50e645702929890b9611998a0b Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:35 +0800 Subject: virt: acrn: Introduce interfaces to query C-states and P-states allowed by hypervisor The C-states and P-states data are used to support CPU power management. The hypervisor controls C-states and P-states for a User VM. ACRN userspace need to query the data from the hypervisor to build ACPI tables for a User VM. HSM provides ioctls for ACRN userspace to query C-states and P-states data obtained from the hypervisor. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-14-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 69 +++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 12 ++++++++ include/uapi/linux/acrn.h | 55 ++++++++++++++++++++++++++++++++++ 3 files changed, 136 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 419271f32be8..b7f2deddc3e7 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -38,6 +38,67 @@ static int acrn_dev_open(struct inode *inode, struct file *filp) return 0; } +static int pmcmd_ioctl(u64 cmd, void __user *uptr) +{ + struct acrn_pstate_data *px_data; + struct acrn_cstate_data *cx_data; + u64 *pm_info; + int ret = 0; + + switch (cmd & PMCMD_TYPE_MASK) { + case ACRN_PMCMD_GET_PX_CNT: + case ACRN_PMCMD_GET_CX_CNT: + pm_info = kmalloc(sizeof(u64), GFP_KERNEL); + if (!pm_info) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(pm_info)); + if (ret < 0) { + kfree(pm_info); + break; + } + + if (copy_to_user(uptr, pm_info, sizeof(u64))) + ret = -EFAULT; + kfree(pm_info); + break; + case ACRN_PMCMD_GET_PX_DATA: + px_data = kmalloc(sizeof(*px_data), GFP_KERNEL); + if (!px_data) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(px_data)); + if (ret < 0) { + kfree(px_data); + break; + } + + if (copy_to_user(uptr, px_data, sizeof(*px_data))) + ret = -EFAULT; + kfree(px_data); + break; + case ACRN_PMCMD_GET_CX_DATA: + cx_data = kmalloc(sizeof(*cx_data), GFP_KERNEL); + if (!cx_data) + return -ENOMEM; + + ret = hcall_get_cpu_state(cmd, virt_to_phys(cx_data)); + if (ret < 0) { + kfree(cx_data); + break; + } + + if (copy_to_user(uptr, cx_data, sizeof(*cx_data))) + ret = -EFAULT; + kfree(cx_data); + break; + default: + break; + } + + return ret; +} + /* * HSM relies on hypercall layer of the ACRN hypervisor to do the * sanity check against the input parameters. @@ -54,6 +115,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct page *page; + u64 cstate_cmd; int i, ret = 0; if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) { @@ -267,6 +329,13 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, case ACRN_IOCTL_CLEAR_VM_IOREQ: acrn_ioreq_request_clear(vm); break; + case ACRN_IOCTL_PM_GET_CPU_STATE: + if (copy_from_user(&cstate_cmd, (void *)ioctl_param, + sizeof(cstate_cmd))) + return -EFAULT; + + ret = pmcmd_ioctl(cstate_cmd, (void __user *)ioctl_param); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index a8813397a3fe..e640632366f0 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -39,6 +39,9 @@ #define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) +#define HC_ID_PM_BASE 0x80UL +#define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) + /** * hcall_create_vm() - Create a User VM * @vminfo: Service VM GPA of info of User VM creation @@ -225,4 +228,13 @@ static inline long hcall_reset_ptdev_intr(u64 vmid, u64 irq) return acrn_hypercall2(HC_RESET_PTDEV_INTR, vmid, irq); } +/* + * hcall_get_cpu_state() - Get P-states and C-states info from the hypervisor + * @state: Service VM GPA of buffer of P-states and C-states + */ +static inline long hcall_get_cpu_state(u64 cmd, u64 state) +{ + return acrn_hypercall2(HC_PM_GET_CPU_STATE, cmd, state); +} + #endif /* __ACRN_HSM_HYPERCALL_H */ diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index b1c06b28ebdc..e997d80a0cc7 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -427,6 +427,58 @@ struct acrn_msi_entry { __u64 msi_data; }; +struct acrn_acpi_generic_address { + __u8 space_id; + __u8 bit_width; + __u8 bit_offset; + __u8 access_size; + __u64 address; +} __attribute__ ((__packed__)); + +/** + * struct acrn_cstate_data - A C state package defined in ACPI + * @cx_reg: Register of the C state object + * @type: Type of the C state object + * @latency: The worst-case latency to enter and exit this C state + * @power: The average power consumption when in this C state + */ +struct acrn_cstate_data { + struct acrn_acpi_generic_address cx_reg; + __u8 type; + __u32 latency; + __u64 power; +}; + +/** + * struct acrn_pstate_data - A P state package defined in ACPI + * @core_frequency: CPU frequency (in MHz). + * @power: Power dissipation (in milliwatts). + * @transition_latency: The worst-case latency in microseconds that CPU is + * unavailable during a transition from any P state to + * this P state. + * @bus_master_latency: The worst-case latency in microseconds that Bus Masters + * are prevented from accessing memory during a transition + * from any P state to this P state. + * @control: The value to be written to Performance Control Register + * @status: Transition status. + */ +struct acrn_pstate_data { + __u64 core_frequency; + __u64 power; + __u64 transition_latency; + __u64 bus_master_latency; + __u64 control; + __u64 status; +}; + +#define PMCMD_TYPE_MASK 0x000000ff +enum acrn_pm_cmd_type { + ACRN_PMCMD_GET_PX_CNT, + ACRN_PMCMD_GET_PX_DATA, + ACRN_PMCMD_GET_CX_CNT, + ACRN_PMCMD_GET_CX_DATA, +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -478,4 +530,7 @@ struct acrn_msi_entry { #define ACRN_IOCTL_DEASSIGN_PCIDEV \ _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) +#define ACRN_IOCTL_PM_GET_CPU_STATE \ + _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From d8ad515156b66e7e79a6e4c814f997ee54eb47c7 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:37 +0800 Subject: virt: acrn: Introduce ioeventfd ioeventfd is a mechanism to register PIO/MMIO regions to trigger an eventfd signal when written to by a User VM. ACRN userspace can register any arbitrary I/O address with a corresponding eventfd and then pass the eventfd to a specific end-point of interest for handling. Vhost is a kernel-level virtio server which uses eventfd for signalling. To support vhost on ACRN, ioeventfd is introduced in HSM. A new I/O client dedicated to ioeventfd is associated with a User VM during VM creation. HSM provides ioctls to associate an I/O region with a eventfd. The I/O client signals a eventfd once its corresponding I/O region is matched with an I/O request. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-16-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Kconfig | 1 + drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 10 ++ drivers/virt/acrn/hsm.c | 11 ++ drivers/virt/acrn/ioeventfd.c | 273 ++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 2 + include/uapi/linux/acrn.h | 29 +++++ 7 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 drivers/virt/acrn/ioeventfd.c (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/Kconfig b/drivers/virt/acrn/Kconfig index 36c80378c30c..3e1a61c9d8d8 100644 --- a/drivers/virt/acrn/Kconfig +++ b/drivers/virt/acrn/Kconfig @@ -2,6 +2,7 @@ config ACRN_HSM tristate "ACRN Hypervisor Service Module" depends on ACRN_GUEST + select EVENTFD help ACRN Hypervisor Service Module (HSM) is a kernel module which communicates with ACRN userspace through ioctls and talks to diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 21721cbf6a80..755b583b32ca 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o ioreq.o +acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index 8a7d7721f505..e3f8190bd972 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -156,6 +156,9 @@ extern rwlock_t acrn_vm_list_lock; * @ioreq_page: The page of the I/O request shared buffer * @pci_conf_addr: Address of a PCI configuration access emulation * @monitor_page: Page of interrupt statistics of User VM + * @ioeventfds_lock: Lock to protect ioeventfds list + * @ioeventfds: List to link all hsm_ioeventfd + * @ioeventfd_client: I/O client for ioeventfds of the VM */ struct acrn_vm { struct list_head list; @@ -172,6 +175,9 @@ struct acrn_vm { struct page *ioreq_page; u32 pci_conf_addr; struct page *monitor_page; + struct mutex ioeventfds_lock; + struct list_head ioeventfds; + struct acrn_ioreq_client *ioeventfd_client; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -204,4 +210,8 @@ void acrn_ioreq_range_del(struct acrn_ioreq_client *client, int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data); +int acrn_ioeventfd_init(struct acrn_vm *vm); +int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args); +void acrn_ioeventfd_deinit(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index b7f2deddc3e7..0b4e88b0b6bc 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -111,6 +111,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vcpu_regs *cpu_regs; struct acrn_ioreq_notify notify; struct acrn_ptdev_irq *irq_info; + struct acrn_ioeventfd ioeventfd; struct acrn_vm_memmap memmap; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; @@ -336,6 +337,16 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = pmcmd_ioctl(cstate_cmd, (void __user *)ioctl_param); break; + case ACRN_IOCTL_IOEVENTFD: + if (copy_from_user(&ioeventfd, (void __user *)ioctl_param, + sizeof(ioeventfd))) + return -EFAULT; + + if (ioeventfd.reserved != 0) + return -EINVAL; + + ret = acrn_ioeventfd_config(vm, &ioeventfd); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c new file mode 100644 index 000000000000..ac4037e9f947 --- /dev/null +++ b/drivers/virt/acrn/ioeventfd.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN HSM eventfd - use eventfd objects to signal expected I/O requests + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Shuo Liu + * Yakui Zhao + */ + +#include +#include + +#include "acrn_drv.h" + +/** + * struct hsm_ioeventfd - Properties of HSM ioeventfd + * @list: Entry within &acrn_vm.ioeventfds of ioeventfds of a VM + * @eventfd: Eventfd of the HSM ioeventfd + * @addr: Address of I/O range + * @data: Data for matching + * @length: Length of I/O range + * @type: Type of I/O range (ACRN_IOREQ_TYPE_MMIO/ACRN_IOREQ_TYPE_PORTIO) + * @wildcard: Data matching or not + */ +struct hsm_ioeventfd { + struct list_head list; + struct eventfd_ctx *eventfd; + u64 addr; + u64 data; + int length; + int type; + bool wildcard; +}; + +static inline int ioreq_type_from_flags(int flags) +{ + return flags & ACRN_IOEVENTFD_FLAG_PIO ? + ACRN_IOREQ_TYPE_PORTIO : ACRN_IOREQ_TYPE_MMIO; +} + +static void acrn_ioeventfd_shutdown(struct acrn_vm *vm, struct hsm_ioeventfd *p) +{ + lockdep_assert_held(&vm->ioeventfds_lock); + + eventfd_ctx_put(p->eventfd); + list_del(&p->list); + kfree(p); +} + +static bool hsm_ioeventfd_is_conflict(struct acrn_vm *vm, + struct hsm_ioeventfd *ioeventfd) +{ + struct hsm_ioeventfd *p; + + lockdep_assert_held(&vm->ioeventfds_lock); + + /* Either one is wildcard, the data matching will be skipped. */ + list_for_each_entry(p, &vm->ioeventfds, list) + if (p->eventfd == ioeventfd->eventfd && + p->addr == ioeventfd->addr && + p->type == ioeventfd->type && + (p->wildcard || ioeventfd->wildcard || + p->data == ioeventfd->data)) + return true; + + return false; +} + +/* + * Assign an eventfd to a VM and create a HSM ioeventfd associated with the + * eventfd. The properties of the HSM ioeventfd are built from a &struct + * acrn_ioeventfd. + */ +static int acrn_ioeventfd_assign(struct acrn_vm *vm, + struct acrn_ioeventfd *args) +{ + struct eventfd_ctx *eventfd; + struct hsm_ioeventfd *p; + int ret; + + /* Check for range overflow */ + if (args->addr + args->len < args->addr) + return -EINVAL; + + /* + * Currently, acrn_ioeventfd is used to support vhost. 1,2,4,8 width + * accesses can cover vhost's requirements. + */ + if (!(args->len == 1 || args->len == 2 || + args->len == 4 || args->len == 8)) + return -EINVAL; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + ret = -ENOMEM; + goto fail; + } + + INIT_LIST_HEAD(&p->list); + p->addr = args->addr; + p->length = args->len; + p->eventfd = eventfd; + p->type = ioreq_type_from_flags(args->flags); + + /* + * ACRN_IOEVENTFD_FLAG_DATAMATCH flag is set in virtio 1.0 support, the + * writing of notification register of each virtqueue may trigger the + * notification. There is no data matching requirement. + */ + if (args->flags & ACRN_IOEVENTFD_FLAG_DATAMATCH) + p->data = args->data; + else + p->wildcard = true; + + mutex_lock(&vm->ioeventfds_lock); + + if (hsm_ioeventfd_is_conflict(vm, p)) { + ret = -EEXIST; + goto unlock_fail; + } + + /* register the I/O range into ioreq client */ + ret = acrn_ioreq_range_add(vm->ioeventfd_client, p->type, + p->addr, p->addr + p->length - 1); + if (ret < 0) + goto unlock_fail; + + list_add_tail(&p->list, &vm->ioeventfds); + mutex_unlock(&vm->ioeventfds_lock); + + return 0; + +unlock_fail: + mutex_unlock(&vm->ioeventfds_lock); + kfree(p); +fail: + eventfd_ctx_put(eventfd); + return ret; +} + +static int acrn_ioeventfd_deassign(struct acrn_vm *vm, + struct acrn_ioeventfd *args) +{ + struct hsm_ioeventfd *p; + struct eventfd_ctx *eventfd; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + mutex_lock(&vm->ioeventfds_lock); + list_for_each_entry(p, &vm->ioeventfds, list) { + if (p->eventfd != eventfd) + continue; + + acrn_ioreq_range_del(vm->ioeventfd_client, p->type, + p->addr, p->addr + p->length - 1); + acrn_ioeventfd_shutdown(vm, p); + break; + } + mutex_unlock(&vm->ioeventfds_lock); + + eventfd_ctx_put(eventfd); + return 0; +} + +static struct hsm_ioeventfd *hsm_ioeventfd_match(struct acrn_vm *vm, u64 addr, + u64 data, int len, int type) +{ + struct hsm_ioeventfd *p = NULL; + + lockdep_assert_held(&vm->ioeventfds_lock); + + list_for_each_entry(p, &vm->ioeventfds, list) { + if (p->type == type && p->addr == addr && p->length >= len && + (p->wildcard || p->data == data)) + return p; + } + + return NULL; +} + +static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client, + struct acrn_io_request *req) +{ + struct hsm_ioeventfd *p; + u64 addr, val; + int size; + + if (req->type == ACRN_IOREQ_TYPE_MMIO) { + /* + * I/O requests are dispatched by range check only, so a + * acrn_ioreq_client need process both READ and WRITE accesses + * of same range. READ accesses are safe to be ignored here + * because virtio PCI devices write the notify registers for + * notification. + */ + if (req->reqs.mmio_request.direction == ACRN_IOREQ_DIR_READ) { + /* reading does nothing and return 0 */ + req->reqs.mmio_request.value = 0; + return 0; + } + addr = req->reqs.mmio_request.address; + size = req->reqs.mmio_request.size; + val = req->reqs.mmio_request.value; + } else { + if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_READ) { + /* reading does nothing and return 0 */ + req->reqs.pio_request.value = 0; + return 0; + } + addr = req->reqs.pio_request.address; + size = req->reqs.pio_request.size; + val = req->reqs.pio_request.value; + } + + mutex_lock(&client->vm->ioeventfds_lock); + p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type); + if (p) + eventfd_signal(p->eventfd, 1); + mutex_unlock(&client->vm->ioeventfds_lock); + + return 0; +} + +int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args) +{ + int ret; + + if (args->flags & ACRN_IOEVENTFD_FLAG_DEASSIGN) + ret = acrn_ioeventfd_deassign(vm, args); + else + ret = acrn_ioeventfd_assign(vm, args); + + return ret; +} + +int acrn_ioeventfd_init(struct acrn_vm *vm) +{ + char name[ACRN_NAME_LEN]; + + mutex_init(&vm->ioeventfds_lock); + INIT_LIST_HEAD(&vm->ioeventfds); + snprintf(name, sizeof(name), "ioeventfd-%u", vm->vmid); + vm->ioeventfd_client = acrn_ioreq_client_create(vm, + acrn_ioeventfd_handler, + NULL, false, name); + if (!vm->ioeventfd_client) { + dev_err(acrn_dev.this_device, "Failed to create ioeventfd ioreq client!\n"); + return -EINVAL; + } + + dev_dbg(acrn_dev.this_device, "VM %u ioeventfd init.\n", vm->vmid); + return 0; +} + +void acrn_ioeventfd_deinit(struct acrn_vm *vm) +{ + struct hsm_ioeventfd *p, *next; + + dev_dbg(acrn_dev.this_device, "VM %u ioeventfd deinit.\n", vm->vmid); + acrn_ioreq_client_destroy(vm->ioeventfd_client); + mutex_lock(&vm->ioeventfds_lock); + list_for_each_entry_safe(p, next, &vm->ioeventfds, list) + acrn_ioeventfd_shutdown(vm, p); + mutex_unlock(&vm->ioeventfds_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index db597f27690a..2b322d956a8c 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -50,6 +50,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, list_add(&vm->list, &acrn_vm_list); write_unlock_bh(&acrn_vm_list_lock); + acrn_ioeventfd_init(vm); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; } @@ -67,6 +68,7 @@ int acrn_vm_destroy(struct acrn_vm *vm) list_del_init(&vm->list); write_unlock_bh(&acrn_vm_list_lock); + acrn_ioeventfd_deinit(vm); acrn_ioreq_deinit(vm); if (vm->monitor_page) { put_page(vm->monitor_page); diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index e997d80a0cc7..132c5ff95967 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -479,6 +479,32 @@ enum acrn_pm_cmd_type { ACRN_PMCMD_GET_CX_DATA, }; +#define ACRN_IOEVENTFD_FLAG_PIO 0x01 +#define ACRN_IOEVENTFD_FLAG_DATAMATCH 0x02 +#define ACRN_IOEVENTFD_FLAG_DEASSIGN 0x04 +/** + * struct acrn_ioeventfd - Data to operate a &struct hsm_ioeventfd + * @fd: The fd of eventfd associated with a hsm_ioeventfd + * @flags: Logical-OR of ACRN_IOEVENTFD_FLAG_* + * @addr: The start address of IO range of ioeventfd + * @len: The length of IO range of ioeventfd + * @reserved: Reserved and should be 0 + * @data: Data for data matching + * + * Without flag ACRN_IOEVENTFD_FLAG_DEASSIGN, ioctl ACRN_IOCTL_IOEVENTFD + * creates a &struct hsm_ioeventfd with properties originated from &struct + * acrn_ioeventfd. With flag ACRN_IOEVENTFD_FLAG_DEASSIGN, ioctl + * ACRN_IOCTL_IOEVENTFD destroys the &struct hsm_ioeventfd matching the fd. + */ +struct acrn_ioeventfd { + __u32 fd; + __u32 flags; + __u64 addr; + __u32 len; + __u32 reserved; + __u64 data; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -533,4 +559,7 @@ enum acrn_pm_cmd_type { #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) +#define ACRN_IOCTL_IOEVENTFD \ + _IOW(ACRN_IOCTL_TYPE, 0x70, struct acrn_ioeventfd) + #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From aa3b483ff1d71c50b33db154048dff9a8f08ac71 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Sun, 7 Feb 2021 11:10:38 +0800 Subject: virt: acrn: Introduce irqfd irqfd is a mechanism to inject a specific interrupt to a User VM using a decoupled eventfd mechanism. Vhost is a kernel-level virtio server which uses eventfd for interrupt injection. To support vhost on ACRN, irqfd is introduced in HSM. HSM provides ioctls to associate a virtual Message Signaled Interrupt (MSI) with an eventfd. The corresponding virtual MSI will be injected into a User VM once the eventfd got signal. Cc: Zhi Wang Cc: Zhenyu Wang Cc: Yu Wang Cc: Reinette Chatre Cc: Greg Kroah-Hartman Reviewed-by: Zhi Wang Reviewed-by: Reinette Chatre Signed-off-by: Shuo Liu Link: https://lore.kernel.org/r/20210207031040.49576-17-shuo.a.liu@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/Makefile | 2 +- drivers/virt/acrn/acrn_drv.h | 10 ++ drivers/virt/acrn/hsm.c | 7 ++ drivers/virt/acrn/irqfd.c | 235 +++++++++++++++++++++++++++++++++++++++++++ drivers/virt/acrn/vm.c | 3 + include/uapi/linux/acrn.h | 15 +++ 6 files changed, 271 insertions(+), 1 deletion(-) create mode 100644 drivers/virt/acrn/irqfd.c (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile index 755b583b32ca..08ce641dcfa1 100644 --- a/drivers/virt/acrn/Makefile +++ b/drivers/virt/acrn/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACRN_HSM) := acrn.o -acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o +acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o irqfd.o diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h index e3f8190bd972..1be54efa666c 100644 --- a/drivers/virt/acrn/acrn_drv.h +++ b/drivers/virt/acrn/acrn_drv.h @@ -159,6 +159,9 @@ extern rwlock_t acrn_vm_list_lock; * @ioeventfds_lock: Lock to protect ioeventfds list * @ioeventfds: List to link all hsm_ioeventfd * @ioeventfd_client: I/O client for ioeventfds of the VM + * @irqfds_lock: Lock to protect irqfds list + * @irqfds: List to link all hsm_irqfd + * @irqfd_wq: Workqueue for irqfd async shutdown */ struct acrn_vm { struct list_head list; @@ -178,6 +181,9 @@ struct acrn_vm { struct mutex ioeventfds_lock; struct list_head ioeventfds; struct acrn_ioreq_client *ioeventfd_client; + struct mutex irqfds_lock; + struct list_head irqfds; + struct workqueue_struct *irqfd_wq; }; struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, @@ -214,4 +220,8 @@ int acrn_ioeventfd_init(struct acrn_vm *vm); int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args); void acrn_ioeventfd_deinit(struct acrn_vm *vm); +int acrn_irqfd_init(struct acrn_vm *vm); +int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args); +void acrn_irqfd_deinit(struct acrn_vm *vm); + #endif /* __ACRN_HSM_DRV_H */ diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 0b4e88b0b6bc..93f6abe10fa6 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -115,6 +115,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_vm_memmap memmap; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; + struct acrn_irqfd irqfd; struct page *page; u64 cstate_cmd; int i, ret = 0; @@ -347,6 +348,12 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_ioeventfd_config(vm, &ioeventfd); break; + case ACRN_IOCTL_IRQFD: + if (copy_from_user(&irqfd, (void __user *)ioctl_param, + sizeof(irqfd))) + return -EFAULT; + ret = acrn_irqfd_config(vm, &irqfd); + break; default: dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd); ret = -ENOTTY; diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c new file mode 100644 index 000000000000..a8766d528e29 --- /dev/null +++ b/drivers/virt/acrn/irqfd.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACRN HSM irqfd: use eventfd objects to inject virtual interrupts + * + * Copyright (C) 2020 Intel Corporation. All rights reserved. + * + * Authors: + * Shuo Liu + * Yakui Zhao + */ + +#include +#include +#include +#include + +#include "acrn_drv.h" + +static LIST_HEAD(acrn_irqfd_clients); +static DEFINE_MUTEX(acrn_irqfds_mutex); + +/** + * struct hsm_irqfd - Properties of HSM irqfd + * @vm: Associated VM pointer + * @wait: Entry of wait-queue + * @shutdown: Async shutdown work + * @eventfd: Associated eventfd + * @list: Entry within &acrn_vm.irqfds of irqfds of a VM + * @pt: Structure for select/poll on the associated eventfd + * @msi: MSI data + */ +struct hsm_irqfd { + struct acrn_vm *vm; + wait_queue_entry_t wait; + struct work_struct shutdown; + struct eventfd_ctx *eventfd; + struct list_head list; + poll_table pt; + struct acrn_msi_entry msi; +}; + +static void acrn_irqfd_inject(struct hsm_irqfd *irqfd) +{ + struct acrn_vm *vm = irqfd->vm; + + acrn_msi_inject(vm, irqfd->msi.msi_addr, + irqfd->msi.msi_data); +} + +static void hsm_irqfd_shutdown(struct hsm_irqfd *irqfd) +{ + u64 cnt; + + lockdep_assert_held(&irqfd->vm->irqfds_lock); + + /* remove from wait queue */ + list_del_init(&irqfd->list); + eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt); + eventfd_ctx_put(irqfd->eventfd); + kfree(irqfd); +} + +static void hsm_irqfd_shutdown_work(struct work_struct *work) +{ + struct hsm_irqfd *irqfd; + struct acrn_vm *vm; + + irqfd = container_of(work, struct hsm_irqfd, shutdown); + vm = irqfd->vm; + mutex_lock(&vm->irqfds_lock); + if (!list_empty(&irqfd->list)) + hsm_irqfd_shutdown(irqfd); + mutex_unlock(&vm->irqfds_lock); +} + +/* Called with wqh->lock held and interrupts disabled */ +static int hsm_irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, + int sync, void *key) +{ + unsigned long poll_bits = (unsigned long)key; + struct hsm_irqfd *irqfd; + struct acrn_vm *vm; + + irqfd = container_of(wait, struct hsm_irqfd, wait); + vm = irqfd->vm; + if (poll_bits & POLLIN) + /* An event has been signaled, inject an interrupt */ + acrn_irqfd_inject(irqfd); + + if (poll_bits & POLLHUP) + /* Do shutdown work in thread to hold wqh->lock */ + queue_work(vm->irqfd_wq, &irqfd->shutdown); + + return 0; +} + +static void hsm_irqfd_poll_func(struct file *file, wait_queue_head_t *wqh, + poll_table *pt) +{ + struct hsm_irqfd *irqfd; + + irqfd = container_of(pt, struct hsm_irqfd, pt); + add_wait_queue(wqh, &irqfd->wait); +} + +/* + * Assign an eventfd to a VM and create a HSM irqfd associated with the + * eventfd. The properties of the HSM irqfd are built from a &struct + * acrn_irqfd. + */ +static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args) +{ + struct eventfd_ctx *eventfd = NULL; + struct hsm_irqfd *irqfd, *tmp; + unsigned int events; + struct fd f; + int ret = 0; + + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); + if (!irqfd) + return -ENOMEM; + + irqfd->vm = vm; + memcpy(&irqfd->msi, &args->msi, sizeof(args->msi)); + INIT_LIST_HEAD(&irqfd->list); + INIT_WORK(&irqfd->shutdown, hsm_irqfd_shutdown_work); + + f = fdget(args->fd); + if (!f.file) { + ret = -EBADF; + goto out; + } + + eventfd = eventfd_ctx_fileget(f.file); + if (IS_ERR(eventfd)) { + ret = PTR_ERR(eventfd); + goto fail; + } + + irqfd->eventfd = eventfd; + + /* + * Install custom wake-up handling to be notified whenever underlying + * eventfd is signaled. + */ + init_waitqueue_func_entry(&irqfd->wait, hsm_irqfd_wakeup); + init_poll_funcptr(&irqfd->pt, hsm_irqfd_poll_func); + + mutex_lock(&vm->irqfds_lock); + list_for_each_entry(tmp, &vm->irqfds, list) { + if (irqfd->eventfd != tmp->eventfd) + continue; + ret = -EBUSY; + mutex_unlock(&vm->irqfds_lock); + goto fail; + } + list_add_tail(&irqfd->list, &vm->irqfds); + mutex_unlock(&vm->irqfds_lock); + + /* Check the pending event in this stage */ + events = f.file->f_op->poll(f.file, &irqfd->pt); + + if (events & POLLIN) + acrn_irqfd_inject(irqfd); + + fdput(f); + return 0; +fail: + if (eventfd && !IS_ERR(eventfd)) + eventfd_ctx_put(eventfd); + + fdput(f); +out: + kfree(irqfd); + return ret; +} + +static int acrn_irqfd_deassign(struct acrn_vm *vm, + struct acrn_irqfd *args) +{ + struct hsm_irqfd *irqfd, *tmp; + struct eventfd_ctx *eventfd; + + eventfd = eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + mutex_lock(&vm->irqfds_lock); + list_for_each_entry_safe(irqfd, tmp, &vm->irqfds, list) { + if (irqfd->eventfd == eventfd) { + hsm_irqfd_shutdown(irqfd); + break; + } + } + mutex_unlock(&vm->irqfds_lock); + eventfd_ctx_put(eventfd); + + return 0; +} + +int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args) +{ + int ret; + + if (args->flags & ACRN_IRQFD_FLAG_DEASSIGN) + ret = acrn_irqfd_deassign(vm, args); + else + ret = acrn_irqfd_assign(vm, args); + + return ret; +} + +int acrn_irqfd_init(struct acrn_vm *vm) +{ + INIT_LIST_HEAD(&vm->irqfds); + mutex_init(&vm->irqfds_lock); + vm->irqfd_wq = alloc_workqueue("acrn_irqfd-%u", 0, 0, vm->vmid); + if (!vm->irqfd_wq) + return -ENOMEM; + + dev_dbg(acrn_dev.this_device, "VM %u irqfd init.\n", vm->vmid); + return 0; +} + +void acrn_irqfd_deinit(struct acrn_vm *vm) +{ + struct hsm_irqfd *irqfd, *next; + + dev_dbg(acrn_dev.this_device, "VM %u irqfd deinit.\n", vm->vmid); + destroy_workqueue(vm->irqfd_wq); + mutex_lock(&vm->irqfds_lock); + list_for_each_entry_safe(irqfd, next, &vm->irqfds, list) + hsm_irqfd_shutdown(irqfd); + mutex_unlock(&vm->irqfds_lock); +} diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c index 2b322d956a8c..7804a2492ad7 100644 --- a/drivers/virt/acrn/vm.c +++ b/drivers/virt/acrn/vm.c @@ -51,6 +51,7 @@ struct acrn_vm *acrn_vm_create(struct acrn_vm *vm, write_unlock_bh(&acrn_vm_list_lock); acrn_ioeventfd_init(vm); + acrn_irqfd_init(vm); dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid); return vm; } @@ -69,7 +70,9 @@ int acrn_vm_destroy(struct acrn_vm *vm) write_unlock_bh(&acrn_vm_list_lock); acrn_ioeventfd_deinit(vm); + acrn_irqfd_deinit(vm); acrn_ioreq_deinit(vm); + if (vm->monitor_page) { put_page(vm->monitor_page); vm->monitor_page = NULL; diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 132c5ff95967..353b2a2e4536 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -505,6 +505,19 @@ struct acrn_ioeventfd { __u64 data; }; +#define ACRN_IRQFD_FLAG_DEASSIGN 0x01 +/** + * struct acrn_irqfd - Data to operate a &struct hsm_irqfd + * @fd: The fd of eventfd associated with a hsm_irqfd + * @flags: Logical-OR of ACRN_IRQFD_FLAG_* + * @msi: Info of MSI associated with the irqfd + */ +struct acrn_irqfd { + __s32 fd; + __u32 flags; + struct acrn_msi_entry msi; +}; + /* The ioctl type, documented in ioctl-number.rst */ #define ACRN_IOCTL_TYPE 0xA2 @@ -561,5 +574,7 @@ struct acrn_ioeventfd { #define ACRN_IOCTL_IOEVENTFD \ _IOW(ACRN_IOCTL_TYPE, 0x70, struct acrn_ioeventfd) +#define ACRN_IOCTL_IRQFD \ + _IOW(ACRN_IOCTL_TYPE, 0x71, struct acrn_irqfd) #endif /* _UAPI_ACRN_H */ -- cgit v1.2.3 From 0566752c3e8681ec47fee37374cb38081d801e95 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 7 Feb 2021 14:05:43 +0100 Subject: uapi: map_to_7segment: Update example in documentation The device_attribute .show() and .store() methods gained an extra parameter in v2.6.13, but the example in the documentation for the 7-segment header file was never updated. Add the missing parameters. While at it, get rid of the (misspelled) deprecated symbolic permissions, and switch to DEVICE_ATTR_RW(), which was introduced in v3.11 Fixes: 54b6f35c99974e99 ("[PATCH] Driver core: change device_attribute callbacks") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210207130543.2128980-1-geert@linux-m68k.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/map_to_7segment.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h index 13a06e5e966e..8b02088f96e3 100644 --- a/include/uapi/linux/map_to_7segment.h +++ b/include/uapi/linux/map_to_7segment.h @@ -45,17 +45,22 @@ * In device drivers it is recommended, if required, to make the char map * accessible via the sysfs interface using the following scheme: * - * static ssize_t show_map(struct device *dev, char *buf) { + * static ssize_t map_seg7_show(struct device *dev, + * struct device_attribute *attr, char *buf) + * { * memcpy(buf, &map_seg7, sizeof(map_seg7)); * return sizeof(map_seg7); * } - * static ssize_t store_map(struct device *dev, const char *buf, size_t cnt) { + * static ssize_t map_seg7_store(struct device *dev, + * struct device_attribute *attr, const char *buf, + * size_t cnt) + * { * if(cnt != sizeof(map_seg7)) * return -EINVAL; * memcpy(&map_seg7, buf, cnt); * return cnt; * } - * static DEVICE_ATTR(map_seg7, PERMS_RW, show_map, store_map); + * static DEVICE_ATTR_RW(map_seg7); * * History: * 2005-05-31 RFC linux-kernel@vger.kernel.org -- cgit v1.2.3 From d9a47edabc4f948102753fa9d41f2dc1dbeb28be Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 16 Dec 2020 16:12:19 +0530 Subject: KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR Introduce KVM_CAP_PPC_DAWR1 which can be used by QEMU to query whether KVM supports 2nd DAWR or not. The capability is by default disabled even when the underlying CPU supports 2nd DAWR. QEMU needs to check and enable it manually to use the feature. Signed-off-by: Ravi Bangoria Signed-off-by: Paul Mackerras --- Documentation/virt/kvm/api.rst | 10 ++++++++++ arch/powerpc/include/asm/kvm_ppc.h | 1 + arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++++ arch/powerpc/kvm/powerpc.c | 10 ++++++++++ include/uapi/linux/kvm.h | 1 + tools/include/uapi/linux/kvm.h | 1 + 6 files changed, 35 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a783a8da818b..45fd862ac128 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6215,6 +6215,16 @@ the bus lock vm exit can be preempted by a higher priority VM exit, the exit notifications to userspace can be KVM_EXIT_BUS_LOCK or other reasons. KVM_RUN_BUS_LOCK flag is used to distinguish between them. +7.22 KVM_CAP_PPC_DAWR1 +---------------------- + +:Architectures: ppc +:Parameters: none +:Returns: 0 on success, -EINVAL when CPU doesn't support 2nd DAWR + +This capability can be used to check / enable 2nd DAWR feature provided +by POWER10 processor. + 8. Other capabilities. ====================== diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 0a056c64c317..13c39d24dda5 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -314,6 +314,7 @@ struct kvmppc_ops { int size); int (*enable_svm)(struct kvm *kvm); int (*svm_off)(struct kvm *kvm); + int (*enable_dawr1)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b37bddfead1b..dffbfd1ab47b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -5642,6 +5642,17 @@ out: return ret; } +static int kvmhv_enable_dawr1(struct kvm *kvm) +{ + if (!cpu_has_feature(CPU_FTR_DAWR1)) + return -ENODEV; + + /* kvm == NULL means the caller is testing if the capability exists */ + if (kvm) + kvm->arch.dawr1_enabled = true; + return 0; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -5685,6 +5696,7 @@ static struct kvmppc_ops kvm_ops_hv = { .store_to_eaddr = kvmhv_store_to_eaddr, .enable_svm = kvmhv_enable_svm, .svm_off = kvmhv_svm_off, + .enable_dawr1 = kvmhv_enable_dawr1, }; static int kvm_init_subcore_bitmap(void) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index cf52d26f49cd..5914c32d9ef3 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -678,6 +678,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = hv_enabled && kvmppc_hv_ops->enable_svm && !kvmppc_hv_ops->enable_svm(NULL); break; + case KVM_CAP_PPC_DAWR1: + r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 && + !kvmppc_hv_ops->enable_dawr1(NULL)); + break; #endif default: r = 0; @@ -2187,6 +2191,12 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, break; r = kvm->arch.kvm_ops->enable_svm(kvm); break; + case KVM_CAP_PPC_DAWR1: + r = -EINVAL; + if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_dawr1) + break; + r = kvm->arch.kvm_ops->enable_dawr1(kvm); + break; #endif default: r = -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 63f8f6e95648..8b281f722e5b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1077,6 +1077,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 +#define KVM_CAP_PPC_DAWR1 194 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 886802b8ffba..9c284a9c3ac5 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1056,6 +1056,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 +#define KVM_CAP_PPC_DAWR1 194 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 1bcc51ac0731aab1b109b2cd5c3d495f1884e5ca Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 9 Feb 2021 14:37:49 +0800 Subject: net/sched: cls_flower: Reject invalid ct_state flags rules Reject the unsupported and invalid ct_state flags of cls flower rules. Fixes: e0ace68af2ac ("net/sched: cls_flower: Add matching on conntrack info") Signed-off-by: wenxu Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ net/sched/cls_flower.c | 39 +++++++++++++++++++++++++++++++++++++-- 2 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..88f4bf0047e7 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,8 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + + __TCA_FLOWER_KEY_CT_FLAGS_MAX, }; enum { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 84f932532db7..46c1b3e9f66a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -30,6 +30,11 @@ #include +#define TCA_FLOWER_KEY_CT_FLAGS_MAX \ + ((__TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) << 1) +#define TCA_FLOWER_KEY_CT_FLAGS_MASK \ + (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) + struct fl_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; @@ -686,8 +691,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED }, - [TCA_FLOWER_KEY_CT_STATE] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_CT_STATE_MASK] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CT_STATE] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), + [TCA_FLOWER_KEY_CT_STATE_MASK] = + NLA_POLICY_MASK(NLA_U16, TCA_FLOWER_KEY_CT_FLAGS_MASK), [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 }, @@ -1390,12 +1397,33 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return 0; } +static int fl_validate_ct_state(u16 state, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + if (state && !(state & TCA_FLOWER_KEY_CT_FLAGS_TRACKED)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "no trk, so no other flag can be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and est are mutually exclusive"); + return -EINVAL; + } + + return 0; +} + static int fl_set_key_ct(struct nlattr **tb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask, struct netlink_ext_ack *extack) { if (tb[TCA_FLOWER_KEY_CT_STATE]) { + int err; + if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) { NL_SET_ERR_MSG(extack, "Conntrack isn't enabled"); return -EOPNOTSUPP; @@ -1403,6 +1431,13 @@ static int fl_set_key_ct(struct nlattr **tb, fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE, &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, sizeof(key->ct_state)); + + err = fl_validate_ct_state(mask->ct_state, + tb[TCA_FLOWER_KEY_CT_STATE_MASK], + extack); + if (err) + return err; + } if (tb[TCA_FLOWER_KEY_CT_ZONE]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { -- cgit v1.2.3 From aa6ce87a768226802f9a231b3909fe81c503852c Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:17 +0000 Subject: dm: add support for passing through inline crypto support Update the device-mapper core to support exposing the inline crypto support of the underlying device(s) through the device-mapper device. This works by creating a "passthrough keyslot manager" for the dm device, which declares support for encryption settings which all underlying devices support. When a supported setting is used, the bio cloning code handles cloning the crypto context to the bios for all the underlying devices. When an unsupported setting is used, the blk-crypto fallback is used as usual. Crypto support on each underlying device is ignored unless the corresponding dm target opts into exposing it. This is needed because for inline crypto to semantically operate on the original bio, the data must not be transformed by the dm target. Thus, targets like dm-linear can expose crypto support of the underlying device, but targets like dm-crypt can't. (dm-crypt could use inline crypto itself, though.) A DM device's table can only be changed if the "new" inline encryption capabilities are a (*not* necessarily strict) superset of the "old" inline encryption capabilities. Attempts to make changes to the table that result in some inline encryption capability becoming no longer supported will be rejected. For the sake of clarity, key eviction from underlying devices will be handled in a future patch. Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers Signed-off-by: Satya Tangirala Signed-off-by: Mike Snitzer --- drivers/md/dm-core.h | 5 ++ drivers/md/dm-table.c | 162 ++++++++++++++++++++++++++++++++++++++++++ drivers/md/dm.c | 18 ++++- include/linux/device-mapper.h | 11 +++ include/uapi/linux/dm-ioctl.h | 4 +- 5 files changed, 197 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 086d293c2b03..bf3e66f39a4a 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -162,6 +163,10 @@ struct dm_table { void *event_context; struct dm_md_mempools *mempools; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct blk_keyslot_manager *ksm; +#endif }; static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2bc256d61550..8c4ed3ec9409 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -187,6 +187,8 @@ static void free_devices(struct list_head *devices, struct mapped_device *md) } } +static void dm_table_destroy_keyslot_manager(struct dm_table *t); + void dm_table_destroy(struct dm_table *t) { unsigned int i; @@ -215,6 +217,8 @@ void dm_table_destroy(struct dm_table *t) dm_free_md_mempools(t->mempools); + dm_table_destroy_keyslot_manager(t); + kfree(t); } @@ -1203,6 +1207,157 @@ static int dm_table_register_integrity(struct dm_table *t) return 0; } +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +struct dm_keyslot_manager { + struct blk_keyslot_manager ksm; + struct mapped_device *md; +}; + +static int device_intersect_crypto_modes(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct blk_keyslot_manager *parent = data; + struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm; + + blk_ksm_intersect_modes(parent, child); + return 0; +} + +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +{ + struct dm_keyslot_manager *dksm = container_of(ksm, + struct dm_keyslot_manager, + ksm); + + if (!ksm) + return; + + blk_ksm_destroy(ksm); + kfree(dksm); +} + +static void dm_table_destroy_keyslot_manager(struct dm_table *t) +{ + dm_destroy_keyslot_manager(t->ksm); + t->ksm = NULL; +} + +/* + * Constructs and initializes t->ksm with a keyslot manager that + * represents the common set of crypto capabilities of the devices + * described by the dm_table. However, if the constructed keyslot + * manager does not support a superset of the crypto capabilities + * supported by the current keyslot manager of the mapped_device, + * it returns an error instead, since we don't support restricting + * crypto capabilities on table changes. Finally, if the constructed + * keyslot manager doesn't actually support any crypto modes at all, + * it just returns NULL. + */ +static int dm_table_construct_keyslot_manager(struct dm_table *t) +{ + struct dm_keyslot_manager *dksm; + struct blk_keyslot_manager *ksm; + struct dm_target *ti; + unsigned int i; + bool ksm_is_empty = true; + + dksm = kmalloc(sizeof(*dksm), GFP_KERNEL); + if (!dksm) + return -ENOMEM; + dksm->md = t->md; + + ksm = &dksm->ksm; + blk_ksm_init_passthrough(ksm); + ksm->max_dun_bytes_supported = UINT_MAX; + memset(ksm->crypto_modes_supported, 0xFF, + sizeof(ksm->crypto_modes_supported)); + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (!dm_target_passes_crypto(ti->type)) { + blk_ksm_intersect_modes(ksm, NULL); + break; + } + if (!ti->type->iterate_devices) + continue; + ti->type->iterate_devices(ti, device_intersect_crypto_modes, + ksm); + } + + if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) { + DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); + dm_destroy_keyslot_manager(ksm); + return -EINVAL; + } + + /* + * If the new KSM doesn't actually support any crypto modes, we may as + * well represent it with a NULL ksm. + */ + ksm_is_empty = true; + for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) { + if (ksm->crypto_modes_supported[i]) { + ksm_is_empty = false; + break; + } + } + + if (ksm_is_empty) { + dm_destroy_keyslot_manager(ksm); + ksm = NULL; + } + + /* + * t->ksm is only set temporarily while the table is being set + * up, and it gets set to NULL after the capabilities have + * been transferred to the request_queue. + */ + t->ksm = ksm; + + return 0; +} + +static void dm_update_keyslot_manager(struct request_queue *q, + struct dm_table *t) +{ + if (!t->ksm) + return; + + /* Make the ksm less restrictive */ + if (!q->ksm) { + blk_ksm_register(t->ksm, q); + } else { + blk_ksm_update_capabilities(q->ksm, t->ksm); + dm_destroy_keyslot_manager(t->ksm); + } + t->ksm = NULL; +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static int dm_table_construct_keyslot_manager(struct dm_table *t) +{ + return 0; +} + +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +{ +} + +static void dm_table_destroy_keyslot_manager(struct dm_table *t) +{ +} + +static void dm_update_keyslot_manager(struct request_queue *q, + struct dm_table *t) +{ +} + +#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ + /* * Prepares the table for use by building the indices, * setting the type, and allocating mempools. @@ -1229,6 +1384,12 @@ int dm_table_complete(struct dm_table *t) return r; } + r = dm_table_construct_keyslot_manager(t); + if (r) { + DMERR("could not construct keyslot manager."); + return r; + } + r = dm_table_alloc_md_mempools(t, t->md); if (r) DMERR("unable to allocate mempools"); @@ -1863,6 +2024,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } #endif + dm_update_keyslot_manager(q, t); blk_queue_update_readahead(q); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 64fda1429e39..7021aea82aa4 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -28,6 +28,7 @@ #include #include #include +#include #define DM_MSG_PREFIX "core" @@ -1722,6 +1723,19 @@ static const struct dax_operations dm_dax_ops; static void dm_wq_work(struct work_struct *work); +#ifdef CONFIG_BLK_INLINE_ENCRYPTION +static void dm_queue_destroy_keyslot_manager(struct request_queue *q) +{ + dm_destroy_keyslot_manager(q->ksm); +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q) +{ +} +#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ + static void cleanup_mapped_device(struct mapped_device *md) { if (md->wq) @@ -1743,8 +1757,10 @@ static void cleanup_mapped_device(struct mapped_device *md) put_disk(md->disk); } - if (md->queue) + if (md->queue) { + dm_queue_destroy_keyslot_manager(md->queue); blk_cleanup_queue(md->queue); + } cleanup_srcu_struct(&md->io_barrier); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 61a66fb8ebb3..47588130ef5e 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -257,6 +257,12 @@ struct target_type { #define DM_TARGET_NOWAIT 0x00000080 #define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT) +/* + * A target supports passing through inline crypto support. + */ +#define DM_TARGET_PASSES_CRYPTO 0x00000100 +#define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -533,6 +539,11 @@ void dm_table_run_md_queue_async(struct dm_table *t); struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *t); +/* + * Table keyslot manager functions + */ +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); + /* * A wrapper around vmalloc. */ diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 4933b6b67b85..fcff6669137b 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -272,9 +272,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 43 +#define DM_VERSION_MINOR 44 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2020-10-01)" +#define DM_VERSION_EXTRA "-ioctl (2021-02-01)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 9ed9e9ba2337205311398a312796c213737bac35 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:31 -0800 Subject: bpf: Count the number of times recursion was prevented Add per-program counter for number of times recursion prevention mechanism was triggered and expose it via show_fdinfo and bpf_prog_info. Teach bpftool to print it. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-7-alexei.starovoitov@gmail.com --- include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 14 ++++++++++---- kernel/bpf/trampoline.c | 18 ++++++++++++++++-- tools/bpf/bpftool/prog.c | 4 ++++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 33 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a06f3c69f4e..3b00fc906ccd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,6 +543,7 @@ struct bpf_binary_header { struct bpf_prog_stats { u64 cnt; u64 nsecs; + u64 misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c001766adcbc..c547ad1ffe43 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4501,6 +4501,7 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f7df56a704de..c859bc46d06c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1731,25 +1731,28 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_stats *stats) { - u64 nsecs = 0, cnt = 0; + u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; - u64 tnsecs, tcnt; + u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); tnsecs = st->nsecs; tcnt = st->cnt; + tmisses = st->misses; } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; + misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; + stats->misses = misses; } #ifdef CONFIG_PROC_FS @@ -1768,14 +1771,16 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" - "run_cnt:\t%llu\n", + "run_cnt:\t%llu\n" + "recursion_misses:\t%llu\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, - stats.cnt); + stats.cnt, + stats.misses); } #endif @@ -3438,6 +3443,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; + info.recursion_misses = stats.misses; if (!bpf_capable()) { info.jited_prog_len = 0; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 89ef6320d19b..7bc3b3209224 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -394,6 +394,16 @@ static u64 notrace bpf_prog_start_time(void) return start; } +static void notrace inc_misses_counter(struct bpf_prog *prog) +{ + struct bpf_prog_stats *stats; + + stats = this_cpu_ptr(prog->stats); + u64_stats_update_begin(&stats->syncp); + stats->misses++; + u64_stats_update_end(&stats->syncp); +} + /* The logic is similar to BPF_PROG_RUN, but with an explicit * rcu_read_lock() and migrate_disable() which are required * for the trampoline. The macro is split into @@ -412,8 +422,10 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog) { rcu_read_lock(); migrate_disable(); - if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) + if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) { + inc_misses_counter(prog); return 0; + } return bpf_prog_start_time(); } @@ -451,8 +463,10 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog) rcu_read_lock_trace(); migrate_disable(); might_fault(); - if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) + if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) { + inc_misses_counter(prog); return 0; + } return bpf_prog_start_time(); } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 1fe3ba255bad..f2b915b20546 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -368,6 +368,8 @@ static void print_prog_header_json(struct bpf_prog_info *info) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } + if (info->recursion_misses) + jsonw_uint_field(json_wtr, "recursion_misses", info->recursion_misses); } static void print_prog_json(struct bpf_prog_info *info, int fd) @@ -446,6 +448,8 @@ static void print_prog_header_plain(struct bpf_prog_info *info) if (info->run_time_ns) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); + if (info->recursion_misses) + printf(" recursion_misses %lld", info->recursion_misses); printf("\n"); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c001766adcbc..c547ad1ffe43 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4501,6 +4501,7 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From 07881ccbf40cc7893869f3f170301889ddca54ac Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:02 +0100 Subject: bpf: Be less specific about socket cookies guarantees Since "92acdc58ab11 bpf, net: Rework cookie generator as per-cpu one" socket cookies are not guaranteed to be non-decreasing. The bpf_get_socket_cookie helper descriptions are currently specifying that cookies are non-decreasing but we don't want users to rely on that. Reported-by: Daniel Borkmann Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210111406.785541-1-revest@chromium.org --- include/uapi/linux/bpf.h | 8 ++++---- tools/include/uapi/linux/bpf.h | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c547ad1ffe43..dbf10bf08582 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1656,22 +1656,22 @@ union bpf_attr { * networking traffic statistics as it provides a global socket * identifier that can be assumed unique. * Return - * A 8-byte long non-decreasing number on success, or 0 if the - * socket field is missing inside *skb*. + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. * * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c547ad1ffe43..dbf10bf08582 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1656,22 +1656,22 @@ union bpf_attr { * networking traffic statistics as it provides a global socket * identifier that can be assumed unique. * Return - * A 8-byte long non-decreasing number on success, or 0 if the - * socket field is missing inside *skb*. + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. * * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return -- cgit v1.2.3 From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:03 +0100 Subject: bpf: Expose bpf_get_socket_cookie to tracing programs This needs a new helper that: - can work in a sleepable context (using sock_gen_cookie) - takes a struct sock pointer and checks that it's not NULL Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 12 ++++++++++++ tools/include/uapi/linux/bpf.h | 8 ++++++++ 5 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c8ea682c007..cccaef1088ea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1885,6 +1885,7 @@ extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; +extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index dbf10bf08582..07cc2e404291 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1673,6 +1673,14 @@ union bpf_attr { * Return * A 8-byte long unique number. * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. + * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return * The owner UID of the socket associated to *skb*. If the socket diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6c0018abe68a..845b2168e006 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1760,6 +1760,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_delete_tracing_proto; case BPF_FUNC_sock_from_file: return &bpf_sock_from_file_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_ptr_cookie_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? diff --git a/net/core/filter.c b/net/core/filter.c index e15d4741719a..57aaed478362 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4631,6 +4631,18 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) +{ + return sk ? sock_gen_cookie(sk) : 0; +} + +const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { + .func = bpf_get_socket_ptr_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, +}; + BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index dbf10bf08582..07cc2e404291 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1673,6 +1673,14 @@ union bpf_attr { * Return * A 8-byte long unique number. * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. + * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return * The owner UID of the socket associated to *skb*. If the socket -- cgit v1.2.3 From 3c5a2fd042d0bfac71a2dfb99515723d318df47b Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Thu, 11 Feb 2021 13:21:07 -0800 Subject: tcp: Sanitize CMSG flags and reserved args in tcp_zerocopy_receive. Explicitly define reserved field and require it and any subsequent fields to be zero-valued for now. Additionally, limit the valid CMSG flags that tcp_zerocopy_receive accepts. Fixes: 7eeba1706eba ("tcp: Add receive timestamp support for receive zerocopy.") Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Suggested-by: David Ahern Suggested-by: Leon Romanovsky Suggested-by: Jakub Kicinski Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 2 +- net/ipv4/tcp.c | 11 ++++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 42fc5a640df4..8fc09e8638b3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -357,6 +357,6 @@ struct tcp_zerocopy_receive { __u64 msg_control; /* ancillary data */ __u64 msg_controllen; __u32 msg_flags; - /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ + __u32 reserved; /* set to 0 for now */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e1a17c6b473c..9896ca10bb34 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2030,6 +2030,7 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, err); } +#define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss); static void tcp_zc_finalize_rx_tstamp(struct sock *sk, @@ -4152,13 +4153,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; - if (len > sizeof(zc)) { + if (unlikely(len > sizeof(zc))) { + err = check_zeroed_user(optval + sizeof(zc), + len - sizeof(zc)); + if (err < 1) + return err == 0 ? -EINVAL : err; len = sizeof(zc); if (put_user(len, optlen)) return -EFAULT; } if (copy_from_user(&zc, optval, len)) return -EFAULT; + if (zc.reserved) + return -EINVAL; + if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) + return -EINVAL; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); release_sock(sk); -- cgit v1.2.3 From b6db0f899a16a23f5a9ea6c8b0fafc7bbd38e03d Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Thu, 4 Feb 2021 06:46:10 -0800 Subject: cfg80211/mac80211: Support disabling HE mode Allow user to disable HE mode, similar to how VHT and HT can be disabled. Useful for testing. Signed-off-by: Ben Greear Link: https://lore.kernel.org/r/20210204144610.25971-1-greearb@candelatech.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 2 ++ net/mac80211/mlme.c | 3 +++ net/wireless/nl80211.c | 7 +++++++ 4 files changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4cdd75449d73..911fae42b0c0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2583,12 +2583,14 @@ struct cfg80211_auth_request { * authentication capability. Drivers can offload authentication to * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). + * @ASSOC_REQ_DISABLE_HE: Disable HE */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), ASSOC_REQ_DISABLE_VHT = BIT(1), ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), + ASSOC_REQ_DISABLE_HE = BIT(4), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 40832d13c2f1..5188fe581efc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3045,6 +3045,8 @@ enum nl80211_attrs { NL80211_ATTR_SAR_SPEC, + NL80211_ATTR_DISABLE_HE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0e4d950cf907..2e33a1263518 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5754,6 +5754,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->flags & ASSOC_REQ_DISABLE_VHT) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + if (req->flags & ASSOC_REQ_DISABLE_HE) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + err = ieee80211_prep_connection(sdata, req->bss, true, override); if (err) goto err_clear; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3b45a9593e71..521d36bb0803 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -752,6 +752,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NL80211_SAE_PWE_BOTH), [NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT }, [NL80211_ATTR_SAR_SPEC] = NLA_POLICY_NESTED(sar_policy), + [NL80211_ATTR_DISABLE_HE] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -10019,6 +10020,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_VHT])) req.flags |= ASSOC_REQ_DISABLE_VHT; + if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_HE])) + req.flags |= ASSOC_REQ_DISABLE_HE; + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]) memcpy(&req.vht_capa_mask, nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]), @@ -10802,6 +10806,9 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_VHT])) connect.flags |= ASSOC_REQ_DISABLE_VHT; + if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_HE])) + connect.flags |= ASSOC_REQ_DISABLE_HE; + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]) memcpy(&connect.vht_capa_mask, nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]), -- cgit v1.2.3 From 735a48481cca453525d9199772f9c3733a47cff4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 12 Feb 2021 10:50:23 +0100 Subject: nl80211: add documentation for HT/VHT/HE disable attributes These were missed earlier, add the necessary documentation and, while at it, clarify it. Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20210212105023.895c3389f063.I46dea3bfc64385bc6f600c50d294007510994f8f@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5188fe581efc..ac78da99fccd 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1963,8 +1963,15 @@ enum nl80211_commands { * @NL80211_ATTR_PROBE_RESP: Probe Response template data. Contains the entire * probe-response frame. The DA field in the 802.11 header is zero-ed out, * to be filled by the FW. - * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable - * this feature. Currently, only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_VHT: Force VHT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HE: Force HE capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. * @NL80211_ATTR_HT_CAPABILITY_MASK: Specify which bits of the * ATTR_HT_CAPABILITY to which attention should be paid. * Currently, only mac80211 NICs support this feature. -- cgit v1.2.3 From e1850ea9bd9eca3656820b4875967d6f9c11c237 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:19 +0100 Subject: bpf: bpf_fib_lookup return MTU value as output when looked up The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog don't know the MTU value that caused this rejection. If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it need to know this MTU value for the ICMP packet. Patch change lookup and result struct bpf_fib_lookup, to contain this MTU value as output via a union with 'tot_len' as this is the value used for the MTU lookup. V5: - Fixed uninit value spotted by Dan Carpenter. - Name struct output member mtu_result Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287789952.790810.13134700381067698781.stgit@firesoul --- include/uapi/linux/bpf.h | 11 +++++++++-- net/core/filter.c | 22 +++++++++++++++------- tools/include/uapi/linux/bpf.h | 11 +++++++++-- 3 files changed, 33 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 07cc2e404291..6b1f6058cccf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2239,6 +2239,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4990,9 +4993,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/net/core/filter.c b/net/core/filter.c index 1fec2e998e37..e7a9b1667dd6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5301,12 +5301,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, const struct neighbour *neigh, - const struct net_device *dev) + const struct net_device *dev, u32 mtu) { memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + if (mtu) + params->mtu_result = mtu; /* union with tot_len */ return 0; } @@ -5322,8 +5324,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct net_device *dev; struct fib_result res; struct flowi4 fl4; + u32 mtu = 0; int err; - u32 mtu; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -5390,8 +5392,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } nhc = res.nhc; @@ -5425,7 +5429,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5442,7 +5446,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct flowi6 fl6; int strict = 0; int oif, err; - u32 mtu; + u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) @@ -5517,8 +5521,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } if (res.nh->fib_nh_lws) @@ -5538,7 +5544,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5614,6 +5620,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; + + params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 07cc2e404291..6b1f6058cccf 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2239,6 +2239,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4990,9 +4993,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ -- cgit v1.2.3 From 34b2021cc61642d61c3cf943d9e71925b827941b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:24 +0100 Subject: bpf: Add BPF-helper for MTU checking This BPF-helper bpf_check_mtu() works for both XDP and TC-BPF programs. The SKB object is complex and the skb->len value (accessible from BPF-prog) also include the length of any extra GRO/GSO segments, but without taking into account that these GRO/GSO segments get added transport (L4) and network (L3) headers before being transmitted. Thus, this BPF-helper is created such that the BPF-programmer don't need to handle these details in the BPF-prog. The API is designed to help the BPF-programmer, that want to do packet context size changes, which involves other helpers. These other helpers usually does a delta size adjustment. This helper also support a delta size (len_diff), which allow BPF-programmer to reuse arguments needed by these other helpers, and perform the MTU check prior to doing any actual size adjustment of the packet context. It is on purpose, that we allow the len adjustment to become a negative result, that will pass the MTU check. This might seem weird, but it's not this helpers responsibility to "catch" wrong len_diff adjustments. Other helpers will take care of these checks, if BPF-programmer chooses to do actual size adjustment. V14: - Improve man-page desc of len_diff. V13: - Enforce flag BPF_MTU_CHK_SEGS cannot use len_diff. V12: - Simplify segment check that calls skb_gso_validate_network_len. - Helpers should return long V9: - Use dev->hard_header_len (instead of ETH_HLEN) - Annotate with unlikely req from Daniel - Fix logic error using skb_gso_validate_network_len from Daniel V6: - Took John's advice and dropped BPF_MTU_CHK_RELAX - Returned MTU is kept at L3-level (like fib_lookup) V4: Lot of changes - ifindex 0 now use current netdev for MTU lookup - rename helper from bpf_mtu_check to bpf_check_mtu - fix bug for GSO pkt length (as skb->len is total len) - remove __bpf_len_adj_positive, simply allow negative len adj Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790461.790810.3429728639563297353.stgit@firesoul --- include/uapi/linux/bpf.h | 75 +++++++++++++++++++++++++++ net/core/filter.c | 114 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 75 +++++++++++++++++++++++++++ 3 files changed, 264 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b1f6058cccf..4c24daa43bac 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3847,6 +3847,69 @@ union bpf_attr { * Return * A pointer to a struct socket on success or NULL if the file is * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + + * Check ctx packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing an *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, why it is not considered a + * failure. Other BPF-helpers are needed for performing the + * planned size change, why the responsability for catch a negative + * packet size belong in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TX length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. On input *mtu_len* must be a valid + * pointer and be initialized (to zero), else verifier will reject + * BPF program. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4012,6 +4075,7 @@ union bpf_attr { FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ FN(sock_from_file), \ + FN(check_mtu), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5045,6 +5109,17 @@ struct bpf_redir_neigh { }; }; +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ diff --git a/net/core/filter.c b/net/core/filter.c index e7a9b1667dd6..439f43f00483 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5637,6 +5637,116 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .arg4_type = ARG_ANYTHING, }; +static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, + u32 ifindex) +{ + struct net *netns = dev_net(dev_curr); + + /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ + if (ifindex == 0) + return dev_curr; + + return dev_get_by_index_rcu(netns, ifindex); +} + +BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, + u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) +{ + int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; + struct net_device *dev = skb->dev; + int skb_len, dev_len; + int mtu; + + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) + return -EINVAL; + + if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff)) + return -EINVAL; + + dev = __dev_via_ifindex(dev, ifindex); + if (unlikely(!dev)) + return -ENODEV; + + mtu = READ_ONCE(dev->mtu); + + dev_len = mtu + dev->hard_header_len; + skb_len = skb->len + len_diff; /* minus result pass check */ + if (skb_len <= dev_len) { + ret = BPF_MTU_CHK_RET_SUCCESS; + goto out; + } + /* At this point, skb->len exceed MTU, but as it include length of all + * segments, it can still be below MTU. The SKB can possibly get + * re-segmented in transmit path (see validate_xmit_skb). Thus, user + * must choose if segs are to be MTU checked. + */ + if (skb_is_gso(skb)) { + ret = BPF_MTU_CHK_RET_SUCCESS; + + if (flags & BPF_MTU_CHK_SEGS && + !skb_gso_validate_network_len(skb, mtu)) + ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + } +out: + /* BPF verifier guarantees valid pointer */ + *mtu_len = mtu; + + return ret; +} + +BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, + u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) +{ + struct net_device *dev = xdp->rxq->dev; + int xdp_len = xdp->data_end - xdp->data; + int ret = BPF_MTU_CHK_RET_SUCCESS; + int mtu, dev_len; + + /* XDP variant doesn't support multi-buffer segment check (yet) */ + if (unlikely(flags)) + return -EINVAL; + + dev = __dev_via_ifindex(dev, ifindex); + if (unlikely(!dev)) + return -ENODEV; + + mtu = READ_ONCE(dev->mtu); + + /* Add L2-header as dev MTU is L3 size */ + dev_len = mtu + dev->hard_header_len; + + xdp_len += len_diff; /* minus result pass check */ + if (xdp_len > dev_len) + ret = BPF_MTU_CHK_RET_FRAG_NEEDED; + + /* BPF verifier guarantees valid pointer */ + *mtu_len = mtu; + + return ret; +} + +static const struct bpf_func_proto bpf_skb_check_mtu_proto = { + .func = bpf_skb_check_mtu, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_INT, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { + .func = bpf_xdp_check_mtu, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_INT, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { @@ -7222,6 +7332,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; + case BPF_FUNC_check_mtu: + return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: @@ -7291,6 +7403,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; + case BPF_FUNC_check_mtu: + return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6b1f6058cccf..4c24daa43bac 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3847,6 +3847,69 @@ union bpf_attr { * Return * A pointer to a struct socket on success or NULL if the file is * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + + * Check ctx packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing an *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, why it is not considered a + * failure. Other BPF-helpers are needed for performing the + * planned size change, why the responsability for catch a negative + * packet size belong in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TX length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. On input *mtu_len* must be a valid + * pointer and be initialized (to zero), else verifier will reject + * BPF program. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4012,6 +4075,7 @@ union bpf_attr { FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ FN(sock_from_file), \ + FN(check_mtu), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5045,6 +5109,17 @@ struct bpf_redir_neigh { }; }; +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ -- cgit v1.2.3 From b911c97c7dc771633c68ea9b8f15070f8af3d323 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 12 Feb 2021 16:00:01 -0800 Subject: mptcp: add netlink event support Allow userspace (mptcpd) to subscribe to mptcp genl multicast events. This implementation reuses the same event API as the mptcp kernel fork to ease integration of existing tools, e.g. mptcpd. Supported events include: 1. start and close of an mptcp connection 2. start and close of subflows (joins) 3. announce and withdrawals of addresses 4. subflow priority (backup/non-backup) change. Reviewed-by: Matthieu Baerts Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 74 +++++++++++++ net/mptcp/pm.c | 20 +++- net/mptcp/pm_netlink.c | 261 ++++++++++++++++++++++++++++++++++++++++++++- net/mptcp/protocol.c | 10 +- net/mptcp/protocol.h | 6 ++ 5 files changed, 364 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3674a451a18c..c91578aaab32 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -36,6 +36,7 @@ enum { /* netlink interface */ #define MPTCP_PM_NAME "mptcp_pm" #define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds" +#define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events" #define MPTCP_PM_VER 0x1 /* @@ -104,4 +105,77 @@ struct mptcp_info { __u64 mptcpi_rcv_nxt; }; +/* + * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A new MPTCP connection has been created. It is the good time to allocate + * memory and send ADD_ADDR if needed. Depending on the traffic-patterns + * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. + * + * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A MPTCP connection is established (can start new subflows). + * + * MPTCP_EVENT_CLOSED: token + * A MPTCP connection has stopped. + * + * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] + * A new address has been announced by the peer. + * + * MPTCP_EVENT_REMOVED: token, rem_id + * An address has been lost by the peer. + * + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, + * if_idx [, error] + * A new subflow has been established. 'error' should not be set. + * + * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, backup, if_idx [, error] + * A subflow has been closed. An error (copy of sk_err) could be set if an + * error has been detected for this subflow. + * + * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, backup, if_idx [, error] + * The priority of a subflow has changed. 'error' should not be set. + */ +enum mptcp_event_type { + MPTCP_EVENT_UNSPEC = 0, + MPTCP_EVENT_CREATED = 1, + MPTCP_EVENT_ESTABLISHED = 2, + MPTCP_EVENT_CLOSED = 3, + + MPTCP_EVENT_ANNOUNCED = 6, + MPTCP_EVENT_REMOVED = 7, + + MPTCP_EVENT_SUB_ESTABLISHED = 10, + MPTCP_EVENT_SUB_CLOSED = 11, + + MPTCP_EVENT_SUB_PRIORITY = 13, +}; + +enum mptcp_event_attr { + MPTCP_ATTR_UNSPEC = 0, + + MPTCP_ATTR_TOKEN, /* u32 */ + MPTCP_ATTR_FAMILY, /* u16 */ + MPTCP_ATTR_LOC_ID, /* u8 */ + MPTCP_ATTR_REM_ID, /* u8 */ + MPTCP_ATTR_SADDR4, /* be32 */ + MPTCP_ATTR_SADDR6, /* struct in6_addr */ + MPTCP_ATTR_DADDR4, /* be32 */ + MPTCP_ATTR_DADDR6, /* struct in6_addr */ + MPTCP_ATTR_SPORT, /* be16 */ + MPTCP_ATTR_DPORT, /* be16 */ + MPTCP_ATTR_BACKUP, /* u8 */ + MPTCP_ATTR_ERROR, /* u8 */ + MPTCP_ATTR_FLAGS, /* u16 */ + MPTCP_ATTR_TIMEOUT, /* u32 */ + MPTCP_ATTR_IF_IDX, /* s32 */ + + __MPTCP_ATTR_AFTER_LAST +}; + +#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) + #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 1dd0e9d7ed06..6fd4b2c1b076 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -75,6 +75,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int pr_debug("msk=%p, token=%u side=%d", msk, msk->token, server_side); WRITE_ONCE(pm->server_side, server_side); + mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); } bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) @@ -122,13 +123,10 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct mptcp_pm_data *pm = &msk->pm; + bool announce = false; pr_debug("msk=%p", msk); - /* try to avoid acquiring the lock below */ - if (!READ_ONCE(pm->work_pending)) - return; - spin_lock_bh(&pm->lock); /* mptcp_pm_fully_established() can be invoked by multiple @@ -138,9 +136,15 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, if (READ_ONCE(pm->work_pending) && !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED))) mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED); - msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED); + if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0) + announce = true; + + msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED); spin_unlock_bh(&pm->lock); + + if (announce) + mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, gfp); } void mptcp_pm_connection_closed(struct mptcp_sock *msk) @@ -179,6 +183,8 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, READ_ONCE(pm->accept_addr)); + mptcp_event_addr_announced(msk, addr); + spin_lock_bh(&pm->lock); if (!READ_ONCE(pm->accept_addr)) { @@ -205,6 +211,8 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id) pr_debug("msk=%p remote_id=%d", msk, rm_id); + mptcp_event_addr_removed(msk, rm_id); + spin_lock_bh(&pm->lock); mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED); pm->rm_id = rm_id; @@ -217,6 +225,8 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup) pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup); subflow->backup = bkup; + + mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC); } /* path manager helpers */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c3abff40fa4e..229fd1af2e29 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -860,10 +860,14 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk) WRITE_ONCE(pm->accept_subflow, subflows); } -#define MPTCP_PM_CMD_GRP_OFFSET 0 +#define MPTCP_PM_CMD_GRP_OFFSET 0 +#define MPTCP_PM_EV_GRP_OFFSET 1 static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, + [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, + .flags = GENL_UNS_ADMIN_PERM, + }, }; static const struct nla_policy @@ -1482,6 +1486,261 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) return 0; } +static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) +{ + genlmsg_multicast_netns(&mptcp_genl_family, net, + nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp); +} + +static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) +{ + const struct inet_sock *issk = inet_sk(ssk); + const struct mptcp_subflow_context *sf; + + if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) + return -EMSGSIZE; + + switch (ssk->sk_family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) + return -EMSGSIZE; + if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr)) + return -EMSGSIZE; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: { + const struct ipv6_pinfo *np = inet6_sk(ssk); + + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + return -EMSGSIZE; + if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) + return -EMSGSIZE; + break; + } +#endif + default: + WARN_ON_ONCE(1); + return -EMSGSIZE; + } + + if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) + return -EMSGSIZE; + if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport)) + return -EMSGSIZE; + + sf = mptcp_subflow_ctx(ssk); + if (WARN_ON_ONCE(!sf)) + return -EINVAL; + + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + return -EMSGSIZE; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + const struct sock *sk = (const struct sock *)msk; + const struct mptcp_subflow_context *sf; + u8 sk_err; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + return -EMSGSIZE; + + if (mptcp_event_add_subflow(skb, ssk)) + return -EMSGSIZE; + + sf = mptcp_subflow_ctx(ssk); + if (WARN_ON_ONCE(!sf)) + return -EINVAL; + + if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup)) + return -EMSGSIZE; + + if (ssk->sk_bound_dev_if && + nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) + return -EMSGSIZE; + + sk_err = ssk->sk_err; + if (sk_err && sk->sk_state == TCP_ESTABLISHED && + nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_sub_established(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + return mptcp_event_put_token_and_ssk(skb, msk, ssk); +} + +static int mptcp_event_sub_closed(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + if (mptcp_event_put_token_and_ssk(skb, msk, ssk)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_created(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token); + + if (err) + return err; + + return mptcp_event_add_subflow(skb, ssk); +} + +void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + goto nla_put_failure; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) + goto nla_put_failure; + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); + return; + +nla_put_failure: + kfree_skb(skb); +} + +void mptcp_event_addr_announced(const struct mptcp_sock *msk, + const struct mptcp_addr_info *info) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, + MPTCP_EVENT_ANNOUNCED); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + goto nla_put_failure; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) + goto nla_put_failure; + + if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port)) + goto nla_put_failure; + + switch (info->family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr)) + goto nla_put_failure; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: + if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6)) + goto nla_put_failure; + break; +#endif + default: + WARN_ON_ONCE(1); + goto nla_put_failure; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); + return; + +nla_put_failure: + kfree_skb(skb); +} + +void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, + const struct sock *ssk, gfp_t gfp) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type); + if (!nlh) + goto nla_put_failure; + + switch (type) { + case MPTCP_EVENT_UNSPEC: + WARN_ON_ONCE(1); + break; + case MPTCP_EVENT_CREATED: + case MPTCP_EVENT_ESTABLISHED: + if (mptcp_event_created(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_CLOSED: + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_ANNOUNCED: + case MPTCP_EVENT_REMOVED: + /* call mptcp_event_addr_announced()/removed instead */ + WARN_ON_ONCE(1); + break; + case MPTCP_EVENT_SUB_ESTABLISHED: + case MPTCP_EVENT_SUB_PRIORITY: + if (mptcp_event_sub_established(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_SUB_CLOSED: + if (mptcp_event_sub_closed(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, gfp); + return; + +nla_put_failure: + kfree_skb(skb); +} + static const struct genl_small_ops mptcp_pm_ops[] = { { .cmd = MPTCP_PM_CMD_ADD_ADDR, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index fe6da1b77723..c2a8392254dc 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2150,6 +2150,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + if (sk->sk_state == TCP_ESTABLISHED) + mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); __mptcp_close_ssk(sk, ssk, subflow); } @@ -2586,6 +2588,10 @@ cleanup: release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); + + if (mptcp_sk(sk)->token) + mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); + sock_put(sk); } @@ -3057,7 +3063,7 @@ bool mptcp_finish_join(struct sock *ssk) return false; if (!msk->pm.server_side) - return true; + goto out; if (!mptcp_pm_allow_new_subflow(msk)) return false; @@ -3084,6 +3090,8 @@ bool mptcp_finish_join(struct sock *ssk) if (parent_sock && !ssk->sk_socket) mptcp_sock_graft(ssk, parent_sock); subflow->map_seq = READ_ONCE(msk->ack_seq); +out: + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f620e2f98d19..d31edbae8da8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -10,6 +10,7 @@ #include #include #include +#include #define MPTCP_SUPPORTED_VERSION 1 @@ -666,6 +667,11 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id); +void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, + const struct sock *ssk, gfp_t gfp); +void mptcp_event_addr_announced(const struct mptcp_sock *msk, const struct mptcp_addr_info *info); +void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); + static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL); -- cgit v1.2.3 From f61d3f0c6912c54f6a468318907a5c554e116516 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 19 Jan 2021 21:57:27 +0800 Subject: gpio: uapi: fix line info flags description The description of the flags field of the struct gpio_v2_line_info mentions "the GPIO lines" while the info only applies to an individual GPIO line. This was accidentally changed from "the GPIO line" during formatting improvements. Reword to "this GPIO line" to clarify and to be consistent with other struct gpio_v2_line_info fields. Fixes: 2cc522d3931b ("gpio: uapi: kernel-doc formatting improvements") Signed-off-by: Kent Gibson Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index e4eb0b8c5cf9..7a6f7948a7df 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -212,7 +212,7 @@ struct gpio_v2_line_request { * @offset: the local offset on this GPIO chip, fill this in when * requesting the line information from the kernel * @num_attrs: the number of attributes in @attrs - * @flags: flags for the GPIO lines, with values from &enum + * @flags: flags for this GPIO line, with values from &enum * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. * @attrs: the configuration attributes associated with the line -- cgit v1.2.3 From 50f9a6c254c60bbad4cde050dbc39b46b61f7a5d Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 4 Feb 2021 13:43:57 +0100 Subject: gpio: uapi: use the preferred SPDX license identifier GPL-2.0 license identifier is deprecated. User-space projects that want to include the kernel header with their source-code will be unable to become fully REUSE compliant due to the reuse tool complaining about deprecated licenses. Change the SPDX identifier to GPL-2.0-only. Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 7a6f7948a7df..eaaea3d8e6b4 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * - userspace ABI for the GPIO character devices * -- cgit v1.2.3 From 6001a930ce0378b62210d4f83583fc88a903d89d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Feb 2021 12:28:07 +0100 Subject: netfilter: nftables: introduce table ownership A userspace daemon like firewalld might need to monitor for netlink updates to detect its ruleset removal by the (global) flush ruleset command to ensure ruleset persistency. This adds extra complexity from userspace and, for some little time, the firewall policy is not in place. This patch adds the NFT_TABLE_F_OWNER flag which allows a userspace program to own the table that creates in exclusivity. Tables that are owned... - can only be updated and removed by the owner, non-owners hit EPERM if they try to update it or remove it. - are destroyed when the owner closes the netlink socket or the process is gone (implicit netlink socket closure). - are skipped by the global flush ruleset command. - are listed in the global ruleset. The userspace process that sets on the NFT_TABLE_F_OWNER flag need to leave open the netlink socket. A new NFTA_TABLE_OWNER netlink attribute specifies the netlink port ID to identify the owner from userspace. This patch also updates error reporting when an unknown table flag is specified to change it from EINVAL to EOPNOTSUPP given that EINVAL is usually reserved to report for malformed netlink messages to userspace. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 ++ include/uapi/linux/netfilter/nf_tables.h | 5 + net/netfilter/nf_tables_api.c | 163 ++++++++++++++++++++++--------- 3 files changed, 128 insertions(+), 46 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 80bc2e8282ae..fdec57d862b7 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1106,11 +1106,17 @@ struct nft_table { u16 family:6, flags:8, genmask:2; + u32 nlpid; char *name; u16 udlen; u8 *udata; }; +static inline bool nft_table_has_owner(const struct nft_table *table) +{ + return table->flags & NFT_TABLE_F_OWNER; +} + static inline bool nft_base_chain_netdev(int family, u32 hooknum) { return family == NFPROTO_NETDEV || diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b1633e7ba529..79bab7a36b30 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -164,7 +164,10 @@ enum nft_hook_attributes { */ enum nft_table_flags { NFT_TABLE_F_DORMANT = 0x1, + NFT_TABLE_F_OWNER = 0x2, }; +#define NFT_TABLE_F_MASK (NFT_TABLE_F_DORMANT | \ + NFT_TABLE_F_OWNER) /** * enum nft_table_attributes - nf_tables table netlink attributes @@ -173,6 +176,7 @@ enum nft_table_flags { * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) + * @NFTA_TABLE_OWNER: owner of this table through netlink portID (NLA_U32) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -182,6 +186,7 @@ enum nft_table_attributes { NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, NFTA_TABLE_USERDATA, + NFTA_TABLE_OWNER, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dffb4f8ef17f..c1eb5cdb3033 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -508,7 +508,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, - u8 family, u8 genmask) + u8 family, u8 genmask, u32 nlpid) { struct nft_table *table; @@ -519,8 +519,13 @@ static struct nft_table *nft_table_lookup(const struct net *net, lockdep_is_held(&net->nft.commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -679,6 +684,9 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; + if (nft_table_has_owner(table) && + nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) + goto nla_put_failure; if (table->udata) { if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) @@ -821,7 +829,7 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask); + table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); @@ -902,8 +910,8 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; if (flags == ctx->table->flags) return 0; @@ -1003,7 +1011,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); @@ -1021,8 +1030,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (nla[NFTA_TABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; } err = -ENOMEM; @@ -1053,6 +1062,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, table->family = family; table->flags = flags; table->handle = ++table_handle; + if (table->flags & NFT_TABLE_F_OWNER) + table->nlpid = NETLINK_CB(skb).portid; nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); @@ -1160,6 +1171,9 @@ static int nft_flush(struct nft_ctx *ctx, int family) if (!nft_is_active_next(ctx->net, table)) continue; + if (nft_table_has_owner(table) && table->nlpid != ctx->portid) + continue; + if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; @@ -1196,7 +1210,8 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, table = nft_table_lookup_byhandle(net, attr, genmask); } else { attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); } if (IS_ERR(table)) { @@ -1579,7 +1594,7 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2299,7 +2314,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2395,7 +2411,8 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, u32 use; int err; - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -3041,7 +3058,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3179,7 +3196,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3403,7 +3421,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3584,7 +3603,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct nlmsghdr *nlh, const struct nlattr * const nla[], struct netlink_ext_ack *extack, - u8 genmask) + u8 genmask, u32 nlpid) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; @@ -3592,7 +3611,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, if (nla[NFTA_SET_TABLE] != NULL) { table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask); + genmask, nlpid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); @@ -4007,7 +4026,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, /* Verify existence before starting dump */ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, 0); if (err < 0) return err; @@ -4236,7 +4255,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) desc.expr = true; - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); @@ -4413,7 +4433,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return -EINVAL; err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -4608,14 +4628,14 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct nlmsghdr *nlh, const struct nlattr * const nla[], struct netlink_ext_ack *extack, - u8 genmask) + u8 genmask, u32 nlpid) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; struct nft_table *table; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask); + genmask, nlpid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); @@ -5032,7 +5052,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, int rem, err = 0; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5613,7 +5633,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return -EINVAL; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5821,7 +5841,7 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, int rem, err = 0; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -6124,7 +6144,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_DATA]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6394,7 +6415,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_TYPE]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6468,7 +6489,8 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6885,7 +6907,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -7069,7 +7091,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -7277,7 +7299,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, 0); if (IS_ERR(table)) return PTR_ERR(table); @@ -9051,14 +9073,55 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nf_tables_table_destroy(&ctx); } -static void __nft_release_tables(struct net *net) +static void __nft_release_tables(struct net *net, u32 nlpid) { struct nft_table *table, *nt; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) + list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + nlpid != table->nlpid) + continue; + __nft_release_table(net, table); + } +} + +static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct netlink_notify *n = ptr; + struct nft_table *table, *nt; + struct net *net = n->net; + bool release = false; + + if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) + return NOTIFY_DONE; + + mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(table, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + n->portid == table->nlpid) { + __nft_release_hook(net, table); + release = true; + } + } + if (release) { + synchronize_rcu(); + list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + n->portid == table->nlpid) + __nft_release_table(net, table); + } + } + mutex_unlock(&net->nft.commit_mutex); + + return NOTIFY_DONE; } +static struct notifier_block nft_nl_notifier = { + .notifier_call = nft_rcv_nl_event, +}; + static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); @@ -9082,7 +9145,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); - __nft_release_tables(net); + __nft_release_tables(net, 0); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); @@ -9106,43 +9169,50 @@ static int __init nf_tables_module_init(void) err = nft_chain_filter_init(); if (err < 0) - goto err1; + goto err_chain_filter; err = nf_tables_core_module_init(); if (err < 0) - goto err2; + goto err_core_module; err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) - goto err3; + goto err_netdev_notifier; err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); if (err < 0) - goto err4; + goto err_rht_objname; err = nft_offload_init(); if (err < 0) - goto err5; + goto err_offload; + + err = netlink_register_notifier(&nft_nl_notifier); + if (err < 0) + goto err_netlink_notifier; /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err6; + goto err_nfnl_subsys; nft_chain_route_init(); return err; -err6: + +err_nfnl_subsys: + netlink_unregister_notifier(&nft_nl_notifier); +err_netlink_notifier: nft_offload_exit(); -err5: +err_offload: rhltable_destroy(&nft_objname_ht); -err4: +err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); -err3: +err_netdev_notifier: nf_tables_core_module_exit(); -err2: +err_core_module: nft_chain_filter_fini(); -err1: +err_chain_filter: unregister_pernet_subsys(&nf_tables_net_ops); return err; } @@ -9150,6 +9220,7 @@ err1: static void __exit nf_tables_module_exit(void) { nfnetlink_subsys_unregister(&nf_tables_subsys); + netlink_unregister_notifier(&nft_nl_notifier); nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); -- cgit v1.2.3 From 2347961b11d4079deace3c81dceed460c08a8fc1 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Tue, 28 Jan 2020 14:25:39 +0100 Subject: binfmt_misc: pass binfmt_misc flags to the interpreter It can be useful to the interpreter to know which flags are in use. For instance, knowing if the preserve-argv[0] is in use would allow to skip the pathname argument. This patch uses an unused auxiliary vector, AT_FLAGS, to add a flag to inform interpreter if the preserve-argv[0] is enabled. Note by Helge Deller: The real-world user of this patch is qemu-user, which needs to know if it has to preserve the argv[0]. See Debian bug #970460. Signed-off-by: Laurent Vivier Reviewed-by: YunQiang Su URL: http://bugs.debian.org/970460 Signed-off-by: Helge Deller --- fs/binfmt_elf.c | 5 ++++- fs/binfmt_elf_fdpic.c | 5 ++++- fs/binfmt_misc.c | 4 +++- include/linux/binfmts.h | 4 ++++ include/uapi/linux/binfmts.h | 4 ++++ 5 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 950bc177238a..11fb68e68f65 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -186,6 +186,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, unsigned char k_rand_bytes[16]; int items; elf_addr_t *elf_info; + elf_addr_t flags = 0; int ei_index; const struct cred *cred = current_cred(); struct vm_area_struct *vma; @@ -260,7 +261,9 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); NEW_AUX_ENT(AT_PHNUM, exec->e_phnum); NEW_AUX_ENT(AT_BASE, interp_load_addr); - NEW_AUX_ENT(AT_FLAGS, 0); + if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0) + flags |= AT_FLAGS_PRESERVE_ARGV0; + NEW_AUX_ENT(AT_FLAGS, flags); NEW_AUX_ENT(AT_ENTRY, e_entry); NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid)); NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid)); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index be4062b8ba75..7a78c91bc1c1 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -506,6 +506,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, char __user *u_platform, *u_base_platform, *p; int loop; int nr; /* reset for each csp adjustment */ + unsigned long flags = 0; #ifdef CONFIG_MMU /* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions @@ -648,7 +649,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); NEW_AUX_ENT(AT_PHNUM, exec_params->hdr.e_phnum); NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); - NEW_AUX_ENT(AT_FLAGS, 0); + if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0) + flags |= AT_FLAGS_PRESERVE_ARGV0; + NEW_AUX_ENT(AT_FLAGS, flags); NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); NEW_AUX_ENT(AT_UID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid)); NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid)); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 3880a82da1dc..c457334de43f 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -153,7 +153,9 @@ static int load_misc_binary(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; - if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { + if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { + bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; + } else { retval = remove_arg_zero(bprm); if (retval) goto ret; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 0571701ab1c5..0abd93efc181 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -73,6 +73,10 @@ struct linux_binprm { #define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2 #define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT) +/* preserve argv0 for the interpreter */ +#define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 +#define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) + /* Function parameter for binfmt->coredump */ struct coredump_params { const kernel_siginfo_t *siginfo; diff --git a/include/uapi/linux/binfmts.h b/include/uapi/linux/binfmts.h index 689025d9c185..c6f9450efc12 100644 --- a/include/uapi/linux/binfmts.h +++ b/include/uapi/linux/binfmts.h @@ -18,4 +18,8 @@ struct pt_regs; /* sizeof(linux_binprm->buf) */ #define BINPRM_BUF_SIZE 256 +/* preserve argv0 for the interpreter */ +#define AT_FLAGS_PRESERVE_ARGV0_BIT 0 +#define AT_FLAGS_PRESERVE_ARGV0 (1 << AT_FLAGS_PRESERVE_ARGV0_BIT) + #endif /* _UAPI_LINUX_BINFMTS_H */ -- cgit v1.2.3 From 0caf3ada24e4623d4b2c938a5b6d2d09e4ccee18 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 12 Feb 2021 16:52:02 -0800 Subject: mptcp: add local addr info in mptcp_info Add mptcpi_local_addr_used and mptcpi_local_addr_max in struct mptcp_info. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ net/mptcp/mptcp_diag.c | 2 ++ net/mptcp/pm_netlink.c | 3 ++- net/mptcp/protocol.h | 1 + 4 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c91578aaab32..e1172c1ffdfd 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -103,6 +103,8 @@ struct mptcp_info { __u64 mptcpi_write_seq; __u64 mptcpi_snd_una; __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; }; /* diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 00ed742f48a4..f16d9b5ee978 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -128,11 +128,13 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); + info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk); val = mptcp_pm_get_add_addr_signal_max(msk); info->mptcpi_add_addr_signal_max = val; val = mptcp_pm_get_add_addr_accept_max(msk); info->mptcpi_add_addr_accepted_max = val; + info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk); if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) flags |= MPTCP_INFO_FLAG_FALLBACK; if (READ_ONCE(msk->can_ack)) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 229fd1af2e29..8e8e35fa4002 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -228,13 +228,14 @@ unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); -static unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); return READ_ONCE(pernet->local_addr_max); } +EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max); static void check_work_pending(struct mptcp_sock *msk) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d31edbae8da8..1b6ec1773678 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -725,6 +725,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) { -- cgit v1.2.3 From 583fa5e71caeb79e04e477e9837e2f7fa53b71e4 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:53 -0800 Subject: cxl/mem: Add basic IOCTL interface Add a straightforward IOCTL that provides a mechanism for userspace to query the supported memory device commands. CXL commands as they appear to userspace are described as part of the UAPI kerneldoc. The command list returned via this IOCTL will contain the full set of commands that the driver supports, however, some of those commands may not be available for use by userspace. Memory device commands first appear in the CXL 2.0 specification. They are submitted through a mailbox mechanism specified in the CXL 2.0 specification. The send command allows userspace to issue mailbox commands directly to the hardware. The list of available commands to send are the output of the query command. The driver verifies basic properties of the command and possibly inspect the input (or output) payload to determine whether or not the command is allowed (or might taint the kernel). Reported-by: kernel test robot # bug in earlier revision Reported-by: Stephen Rothwell Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Cc: Al Viro Link: https://lore.kernel.org/r/20210217040958.1354670-5-ben.widawsky@intel.com Signed-off-by: Dan Williams --- .clang-format | 1 + Documentation/driver-api/cxl/memory-devices.rst | 12 + Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + drivers/cxl/mem.c | 283 ++++++++++++++++++++- include/uapi/linux/cxl_mem.h | 156 ++++++++++++ 5 files changed, 452 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/cxl_mem.h (limited to 'include/uapi/linux') diff --git a/.clang-format b/.clang-format index 10dc5a9a61b3..3f11c8901b43 100644 --- a/.clang-format +++ b/.clang-format @@ -109,6 +109,7 @@ ForEachMacros: - 'css_for_each_child' - 'css_for_each_descendant_post' - 'css_for_each_descendant_pre' + - 'cxl_for_each_cmd' - 'device_for_each_child_node' - 'dma_fence_chain_for_each' - 'do_for_each_ftrace_op' diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst index 1fef2c0a167d..1bad466f9167 100644 --- a/Documentation/driver-api/cxl/memory-devices.rst +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -32,3 +32,15 @@ CXL Bus ------- .. kernel-doc:: drivers/cxl/bus.c :doc: cxl bus + +External Interfaces +=================== + +CXL IOCTL Interface +------------------- + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :doc: UAPI + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :internal: diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index a4c75a28c839..6eb8e634664d 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -352,6 +352,7 @@ Code Seq# Include File Comments 0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver 0xCD 01 linux/reiserfs_fs.h +0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices 0xCF 02 fs/cifs/ioctl.c 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 1c0195b07063..aa8f843fcca1 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include #include #include #include @@ -40,6 +41,7 @@ #define CXL_MAILBOX_TIMEOUT_MS (2 * HZ) enum opcode { + CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_MAX = 0x10000 }; @@ -95,6 +97,49 @@ struct cxl_memdev { static int cxl_mem_major; static DEFINE_IDA(cxl_memdev_ida); +/** + * struct cxl_mem_command - Driver representation of a memory device command + * @info: Command information as it exists for the UAPI + * @opcode: The actual bits used for the mailbox protocol + * + * The cxl_mem_command is the driver's internal representation of commands that + * are supported by the driver. Some of these commands may not be supported by + * the hardware. The driver will use @info to validate the fields passed in by + * the user then submit the @opcode to the hardware. + * + * See struct cxl_command_info. + */ +struct cxl_mem_command { + struct cxl_command_info info; + enum opcode opcode; +}; + +#define CXL_CMD(_id, sin, sout) \ + [CXL_MEM_COMMAND_ID_##_id] = { \ + .info = { \ + .id = CXL_MEM_COMMAND_ID_##_id, \ + .size_in = sin, \ + .size_out = sout, \ + }, \ + .opcode = CXL_MBOX_OP_##_id, \ + } + +/* + * This table defines the supported mailbox commands for the driver. This table + * is made up of a UAPI structure. Non-negative values as parameters in the + * table will be validated against the user's input. For example, if size_in is + * 0, and the user passed in 1, it is an error. + */ +static struct cxl_mem_command mem_commands[] = { + CXL_CMD(IDENTIFY, 0, 0x43), +}; + +#define cxl_for_each_cmd(cmd) \ + for ((cmd) = &mem_commands[0]; \ + ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++) + +#define cxl_cmd_count ARRAY_SIZE(mem_commands) + static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) { const unsigned long start = jiffies; @@ -324,6 +369,242 @@ static void cxl_mem_mbox_put(struct cxl_mem *cxlm) mutex_unlock(&cxlm->mbox_mutex); } +/** + * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. + * @cxlm: The CXL memory device to communicate with. + * @cmd: The validated command. + * @in_payload: Pointer to userspace's input payload. + * @out_payload: Pointer to userspace's output payload. + * @size_out: (Input) Max payload size to copy out. + * (Output) Payload size hardware generated. + * @retval: Hardware generated return code from the operation. + * + * Return: + * * %0 - Mailbox transaction succeeded. This implies the mailbox + * protocol completed successfully not that the operation itself + * was successful. + * * %-ENOMEM - Couldn't allocate a bounce buffer. + * * %-EFAULT - Something happened with copy_to/from_user. + * * %-EINTR - Mailbox acquisition interrupted. + * * %-EXXX - Transaction level failures. + * + * Creates the appropriate mailbox command and dispatches it on behalf of a + * userspace request. The input and output payloads are copied between + * userspace. + * + * See cxl_send_cmd(). + */ +static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_mem_command *cmd, + u64 in_payload, u64 out_payload, + s32 *size_out, u32 *retval) +{ + struct device *dev = &cxlm->pdev->dev; + struct mbox_cmd mbox_cmd = { + .opcode = cmd->opcode, + .size_in = cmd->info.size_in, + .size_out = cmd->info.size_out, + }; + int rc; + + if (cmd->info.size_out) { + mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL); + if (!mbox_cmd.payload_out) + return -ENOMEM; + } + + if (cmd->info.size_in) { + mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload), + cmd->info.size_in); + if (IS_ERR(mbox_cmd.payload_in)) + return PTR_ERR(mbox_cmd.payload_in); + } + + rc = cxl_mem_mbox_get(cxlm); + if (rc) + goto out; + + dev_dbg(dev, + "Submitting %s command for user\n" + "\topcode: %x\n" + "\tsize: %ub\n", + cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, + cmd->info.size_in); + + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); + cxl_mem_mbox_put(cxlm); + if (rc) + goto out; + + /* + * @size_out contains the max size that's allowed to be written back out + * to userspace. While the payload may have written more output than + * this it will have to be ignored. + */ + if (mbox_cmd.size_out) { + dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out, + "Invalid return size\n"); + if (copy_to_user(u64_to_user_ptr(out_payload), + mbox_cmd.payload_out, mbox_cmd.size_out)) { + rc = -EFAULT; + goto out; + } + } + + *size_out = mbox_cmd.size_out; + *retval = mbox_cmd.return_code; + +out: + kvfree(mbox_cmd.payload_in); + kvfree(mbox_cmd.payload_out); + return rc; +} + +/** + * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. + * @cxlm: &struct cxl_mem device whose mailbox will be used. + * @send_cmd: &struct cxl_send_command copied in from userspace. + * @out_cmd: Sanitized and populated &struct cxl_mem_command. + * + * Return: + * * %0 - @out_cmd is ready to send. + * * %-ENOTTY - Invalid command specified. + * * %-EINVAL - Reserved fields or invalid values were used. + * * %-ENOMEM - Input or output buffer wasn't sized properly. + * + * The result of this command is a fully validated command in @out_cmd that is + * safe to send to the hardware. + * + * See handle_mailbox_cmd_from_user() + */ +static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_send_command *send_cmd, + struct cxl_mem_command *out_cmd) +{ + const struct cxl_command_info *info; + struct cxl_mem_command *c; + + if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX) + return -ENOTTY; + + /* + * The user can never specify an input payload larger than what hardware + * supports, but output can be arbitrarily large (simply write out as + * much data as the hardware provides). + */ + if (send_cmd->in.size > cxlm->payload_size) + return -EINVAL; + + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) + return -EINVAL; + + if (send_cmd->rsvd) + return -EINVAL; + + if (send_cmd->in.rsvd || send_cmd->out.rsvd) + return -EINVAL; + + /* Convert user's command into the internal representation */ + c = &mem_commands[send_cmd->id]; + info = &c->info; + + /* Check the input buffer is the expected size */ + if (info->size_in >= 0 && info->size_in != send_cmd->in.size) + return -ENOMEM; + + /* Check the output buffer is at least large enough */ + if (info->size_out >= 0 && send_cmd->out.size < info->size_out) + return -ENOMEM; + + memcpy(out_cmd, c, sizeof(*c)); + out_cmd->info.size_in = send_cmd->in.size; + /* + * XXX: out_cmd->info.size_out will be controlled by the driver, and the + * specified number of bytes @send_cmd->out.size will be copied back out + * to userspace. + */ + + return 0; +} + +static int cxl_query_cmd(struct cxl_memdev *cxlmd, + struct cxl_mem_query_commands __user *q) +{ + struct device *dev = &cxlmd->dev; + struct cxl_mem_command *cmd; + u32 n_commands; + int j = 0; + + dev_dbg(dev, "Query IOCTL\n"); + + if (get_user(n_commands, &q->n_commands)) + return -EFAULT; + + /* returns the total number if 0 elements are requested. */ + if (n_commands == 0) + return put_user(cxl_cmd_count, &q->n_commands); + + /* + * otherwise, return max(n_commands, total commands) cxl_command_info + * structures. + */ + cxl_for_each_cmd(cmd) { + const struct cxl_command_info *info = &cmd->info; + + if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + return -EFAULT; + + if (j == n_commands) + break; + } + + return 0; +} + +static int cxl_send_cmd(struct cxl_memdev *cxlmd, + struct cxl_send_command __user *s) +{ + struct cxl_mem *cxlm = cxlmd->cxlm; + struct device *dev = &cxlmd->dev; + struct cxl_send_command send; + struct cxl_mem_command c; + int rc; + + dev_dbg(dev, "Send IOCTL\n"); + + if (copy_from_user(&send, s, sizeof(send))) + return -EFAULT; + + rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c); + if (rc) + return rc; + + /* Prepare to handle a full payload for variable sized output */ + if (c.info.size_out < 0) + c.info.size_out = cxlm->payload_size; + + rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload, + send.out.payload, &send.out.size, + &send.retval); + if (rc) + return rc; + + return copy_to_user(s, &send, sizeof(send)); +} + +static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case CXL_MEM_QUERY_COMMANDS: + return cxl_query_cmd(cxlmd, (void __user *)arg); + case CXL_MEM_SEND_COMMAND: + return cxl_send_cmd(cxlmd, (void __user *)arg); + default: + return -ENOTTY; + } +} + static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -337,7 +618,7 @@ static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, if (!percpu_ref_tryget_live(&cxlmd->ops_active)) return -ENXIO; - /* TODO: ioctl body */ + rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); percpu_ref_put(&cxlmd->ops_active); diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h new file mode 100644 index 000000000000..887781dc3b6c --- /dev/null +++ b/include/uapi/linux/cxl_mem.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * CXL IOCTLs for Memory Devices + */ + +#ifndef _UAPI_CXL_MEM_H_ +#define _UAPI_CXL_MEM_H_ + +#include + +/** + * DOC: UAPI + * + * Not all of all commands that the driver supports are always available for use + * by userspace. Userspace must check the results from the QUERY command in + * order to determine the live set of commands. + */ + +#define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands) +#define CXL_MEM_SEND_COMMAND _IOWR(0xCE, 2, struct cxl_send_command) + +#define CXL_CMDS \ + ___C(INVALID, "Invalid Command"), \ + ___C(IDENTIFY, "Identify Command"), \ + ___C(MAX, "invalid / last command") + +#define ___C(a, b) CXL_MEM_COMMAND_ID_##a +enum { CXL_CMDS }; + +#undef ___C +#define ___C(a, b) { b } +static const struct { + const char *name; +} cxl_command_names[] = { CXL_CMDS }; + +/* + * Here's how this actually breaks out: + * cxl_command_names[] = { + * [CXL_MEM_COMMAND_ID_INVALID] = { "Invalid Command" }, + * [CXL_MEM_COMMAND_ID_IDENTIFY] = { "Identify Command" }, + * ... + * [CXL_MEM_COMMAND_ID_MAX] = { "invalid / last command" }, + * }; + */ + +#undef ___C + +/** + * struct cxl_command_info - Command information returned from a query. + * @id: ID number for the command. + * @flags: Flags that specify command behavior. + * @size_in: Expected input size, or -1 if variable length. + * @size_out: Expected output size, or -1 if variable length. + * + * Represents a single command that is supported by both the driver and the + * hardware. This is returned as part of an array from the query ioctl. The + * following would be a command that takes a variable length input and returns 0 + * bytes of output. + * + * - @id = 10 + * - @flags = 0 + * - @size_in = -1 + * - @size_out = 0 + * + * See struct cxl_mem_query_commands. + */ +struct cxl_command_info { + __u32 id; + + __u32 flags; +#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) + + __s32 size_in; + __s32 size_out; +}; + +/** + * struct cxl_mem_query_commands - Query supported commands. + * @n_commands: In/out parameter. When @n_commands is > 0, the driver will + * return min(num_support_commands, n_commands). When @n_commands + * is 0, driver will return the number of total supported commands. + * @rsvd: Reserved for future use. + * @commands: Output array of supported commands. This array must be allocated + * by userspace to be at least min(num_support_commands, @n_commands) + * + * Allow userspace to query the available commands supported by both the driver, + * and the hardware. Commands that aren't supported by either the driver, or the + * hardware are not returned in the query. + * + * Examples: + * + * - { .n_commands = 0 } // Get number of supported commands + * - { .n_commands = 15, .commands = buf } // Return first 15 (or less) + * supported commands + * + * See struct cxl_command_info. + */ +struct cxl_mem_query_commands { + /* + * Input: Number of commands to return (space allocated by user) + * Output: Number of commands supported by the driver/hardware + * + * If n_commands is 0, kernel will only return number of commands and + * not try to populate commands[], thus allowing userspace to know how + * much space to allocate + */ + __u32 n_commands; + __u32 rsvd; + + struct cxl_command_info __user commands[]; /* out: supported commands */ +}; + +/** + * struct cxl_send_command - Send a command to a memory device. + * @id: The command to send to the memory device. This must be one of the + * commands returned by the query command. + * @flags: Flags for the command (input). + * @rsvd: Must be zero. + * @retval: Return value from the memory device (output). + * @in: Parameters associated with input payload. + * @in.size: Size of the payload to provide to the device (input). + * @in.rsvd: Must be zero. + * @in.payload: Pointer to memory for payload input, payload is little endian. + * @out: Parameters associated with output payload. + * @out.size: Size of the payload received from the device (input/output). This + * field is filled in by userspace to let the driver know how much + * space was allocated for output. It is populated by the driver to + * let userspace know how large the output payload actually was. + * @out.rsvd: Must be zero. + * @out.payload: Pointer to memory for payload output, payload is little endian. + * + * Mechanism for userspace to send a command to the hardware for processing. The + * driver will do basic validation on the command sizes. In some cases even the + * payload may be introspected. Userspace is required to allocate large enough + * buffers for size_out which can be variable length in certain situations. + */ +struct cxl_send_command { + __u32 id; + __u32 flags; + __u32 rsvd; + __u32 retval; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } in; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } out; +}; + +#endif -- cgit v1.2.3 From 13237183c735f5cba4ae26bc782c613ae0d4e4d3 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:54 -0800 Subject: cxl/mem: Add a "RAW" send command The CXL memory device send interface will have a number of supported commands. The raw command is not such a command. Raw commands allow userspace to send a specified opcode to the underlying hardware and bypass all driver checks on the command. The primary use for this command is to [begrudgingly] allow undocumented vendor specific hardware commands. While not the main motivation, it also allows prototyping new hardware commands without a driver patch and rebuild. While this all sounds very powerful it comes with a couple of caveats: 1. Bug reports using raw commands will not get the same level of attention as bug reports using supported commands (via taint). 2. Supported commands will be rejected by the RAW command. With this comes new debugfs knob to allow full access to your toes with your weapon of choice. Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Reviewed-by: Jonathan Cameron Cc: Ariel Sibley Link: https://lore.kernel.org/r/20210217040958.1354670-6-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/Kconfig | 18 ++++++ drivers/cxl/mem.c | 132 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 12 +++- 3 files changed, 161 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 9e80b311e928..97dc4d751651 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -32,4 +32,22 @@ config CXL_MEM Chapter 2.3 Type 3 CXL Device in the CXL 2.0 specification. If unsure say 'm'. + +config CXL_MEM_RAW_COMMANDS + bool "RAW Command Interface for Memory Devices" + depends on CXL_MEM + help + Enable CXL RAW command interface. + + The CXL driver ioctl interface may assign a kernel ioctl command + number for each specification defined opcode. At any given point in + time the number of opcodes that the specification defines and a device + may implement may exceed the kernel's set of associated ioctl function + numbers. The mismatch is either by omission, specification is too new, + or by design. When prototyping new hardware, or developing / debugging + the driver it is useful to be able to submit any possible command to + the hardware, even commands that may crash the kernel due to their + potential impact to memory currently in use by the kernel. + + If developing CXL hardware or the driver say Y, otherwise say N. endif diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index aa8f843fcca1..5319412e245c 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ #include +#include +#include #include #include #include @@ -42,7 +44,14 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, + CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_ACTIVATE_FW = 0x0202, CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, + CXL_MBOX_OP_SCAN_MEDIA = 0x4304, + CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, CXL_MBOX_OP_MAX = 0x10000 }; @@ -96,6 +105,8 @@ struct cxl_memdev { static int cxl_mem_major; static DEFINE_IDA(cxl_memdev_ida); +static struct dentry *cxl_debugfs; +static bool cxl_raw_allow_all; /** * struct cxl_mem_command - Driver representation of a memory device command @@ -132,6 +143,49 @@ struct cxl_mem_command { */ static struct cxl_mem_command mem_commands[] = { CXL_CMD(IDENTIFY, 0, 0x43), +#ifdef CONFIG_CXL_MEM_RAW_COMMANDS + CXL_CMD(RAW, ~0, ~0), +#endif +}; + +/* + * Commands that RAW doesn't permit. The rationale for each: + * + * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment / + * coordination of transaction timeout values at the root bridge level. + * + * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live + * and needs to be coordinated with HDM updates. + * + * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the + * driver and any writes from userspace invalidates those contents. + * + * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes + * to the device after it is marked clean, userspace can not make that + * assertion. + * + * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that + * is kept up to date with patrol notifications and error management. + */ +static u16 cxl_disabled_raw_commands[] = { + CXL_MBOX_OP_ACTIVATE_FW, + CXL_MBOX_OP_SET_PARTITION_INFO, + CXL_MBOX_OP_SET_LSA, + CXL_MBOX_OP_SET_SHUTDOWN_STATE, + CXL_MBOX_OP_SCAN_MEDIA, + CXL_MBOX_OP_GET_SCAN_MEDIA, +}; + +/* + * Command sets that RAW doesn't permit. All opcodes in this set are + * disabled because they pass plain text security payloads over the + * user/kernel boundary. This functionality is intended to be wrapped + * behind the keys ABI which allows for encrypted payloads in the UAPI + */ +static u8 security_command_sets[] = { + 0x44, /* Sanitize */ + 0x45, /* Persistent Memory Data-at-rest Security */ + 0x46, /* Security Passthrough */ }; #define cxl_for_each_cmd(cmd) \ @@ -162,6 +216,16 @@ static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) return 0; } +static bool cxl_is_security_command(u16 opcode) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(security_command_sets); i++) + if (security_command_sets[i] == (opcode >> 8)) + return true; + return false; +} + static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, struct mbox_cmd *mbox_cmd) { @@ -431,6 +495,9 @@ static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, cmd->info.size_in); + dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, + "raw command path used\n"); + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); cxl_mem_mbox_put(cxlm); if (rc) @@ -460,6 +527,29 @@ out: return rc; } +static bool cxl_mem_raw_command_allowed(u16 opcode) +{ + int i; + + if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS)) + return false; + + if (security_locked_down(LOCKDOWN_NONE)) + return false; + + if (cxl_raw_allow_all) + return true; + + if (cxl_is_security_command(opcode)) + return false; + + for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++) + if (cxl_disabled_raw_commands[i] == opcode) + return false; + + return true; +} + /** * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. * @cxlm: &struct cxl_mem device whose mailbox will be used. @@ -471,6 +561,7 @@ out: * * %-ENOTTY - Invalid command specified. * * %-EINVAL - Reserved fields or invalid values were used. * * %-ENOMEM - Input or output buffer wasn't sized properly. + * * %-EPERM - Attempted to use a protected command. * * The result of this command is a fully validated command in @out_cmd that is * safe to send to the hardware. @@ -495,6 +586,40 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, if (send_cmd->in.size > cxlm->payload_size) return -EINVAL; + /* + * Checks are bypassed for raw commands but a WARN/taint will occur + * later in the callchain + */ + if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) { + const struct cxl_mem_command temp = { + .info = { + .id = CXL_MEM_COMMAND_ID_RAW, + .flags = 0, + .size_in = send_cmd->in.size, + .size_out = send_cmd->out.size, + }, + .opcode = send_cmd->raw.opcode + }; + + if (send_cmd->raw.rsvd) + return -EINVAL; + + /* + * Unlike supported commands, the output size of RAW commands + * gets passed along without further checking, so it must be + * validated here. + */ + if (send_cmd->out.size > cxlm->payload_size) + return -EINVAL; + + if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) + return -EPERM; + + memcpy(out_cmd, &temp, sizeof(temp)); + + return 0; + } + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) return -EINVAL; @@ -1166,6 +1291,7 @@ static struct pci_driver cxl_mem_driver = { static __init int cxl_mem_init(void) { + struct dentry *mbox_debugfs; dev_t devt; int rc; @@ -1182,11 +1308,17 @@ static __init int cxl_mem_init(void) return rc; } + cxl_debugfs = debugfs_create_dir("cxl", NULL); + mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs); + debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs, + &cxl_raw_allow_all); + return 0; } static __exit void cxl_mem_exit(void) { + debugfs_remove_recursive(cxl_debugfs); pci_unregister_driver(&cxl_mem_driver); unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS); } diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 887781dc3b6c..c316028730e7 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -22,6 +22,7 @@ #define CXL_CMDS \ ___C(INVALID, "Invalid Command"), \ ___C(IDENTIFY, "Identify Command"), \ + ___C(RAW, "Raw device command"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a @@ -115,6 +116,9 @@ struct cxl_mem_query_commands { * @id: The command to send to the memory device. This must be one of the * commands returned by the query command. * @flags: Flags for the command (input). + * @raw: Special fields for raw commands + * @raw.opcode: Opcode passed to hardware when using the RAW command. + * @raw.rsvd: Must be zero. * @rsvd: Must be zero. * @retval: Return value from the memory device (output). * @in: Parameters associated with input payload. @@ -137,7 +141,13 @@ struct cxl_mem_query_commands { struct cxl_send_command { __u32 id; __u32 flags; - __u32 rsvd; + union { + struct { + __u16 opcode; + __u16 rsvd; + } raw; + __u32 rsvd; + }; __u32 retval; struct { -- cgit v1.2.3 From 472b1ce6e9d6396ab3f11fc5101c6b63b934a018 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:55 -0800 Subject: cxl/mem: Enable commands via CEL CXL devices identified by the memory-device class code must implement the Device Command Interface (described in 8.2.9 of the CXL 2.0 spec). While the driver already maintains a list of commands it supports, there is still a need to be able to distinguish between commands that the driver knows about from commands that are optionally supported by the hardware. The Command Effects Log (CEL) is specified in the CXL 2.0 specification. The CEL is one of two types of logs, the other being vendor specific. They are distinguished in hardware/spec via UUID. The CEL is useful for 2 things: 1. Determine which optional commands are supported by the CXL device. 2. Enumerate any vendor specific commands The CEL is used by the driver to determine which commands are available in the hardware and therefore which commands userspace is allowed to execute. The set of enabled commands might be a subset of commands which are advertised in UAPI via CXL_MEM_SEND_COMMAND IOCTL. With the CEL enabling comes a internal flag to indicate a base set of commands that are enabled regardless of CEL. Such commands are required for basic interaction with the hardware and thus can be useful in debug cases, for example if the CEL is corrupted. The implementation leaves the statically defined table of commands and supplements it with a bitmap to determine commands that are enabled. This organization was chosen for the following reasons: - Smaller memory footprint. Doesn't need a table per device. - Reduce memory allocation complexity. - Fixed command IDs to opcode mapping for all devices makes development and debugging easier. - Certain helpers are easily achievable, like cxl_for_each_cmd(). Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams (v2) Reviewed-by: Jonathan Cameron (v3) Link: https://lore.kernel.org/r/20210217040958.1354670-7-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/cxl.h | 2 + drivers/cxl/mem.c | 223 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/cxl_mem.h | 1 + 3 files changed, 219 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 8fd4a177fe25..6f14838c2d25 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -69,6 +69,7 @@ struct cxl_memdev; * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. + * @enabled_commands: Hardware commands found enabled in CEL. * @pmem_range: Persistent memory capacity information. * @ram_range: Volatile memory capacity information. */ @@ -84,6 +85,7 @@ struct cxl_mem { size_t payload_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; + unsigned long *enabled_cmds; struct range pmem_range; struct range ram_range; diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 5319412e245c..e31b3045e231 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -46,6 +46,8 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, + CXL_MBOX_OP_GET_LOG = 0x0401, CXL_MBOX_OP_IDENTIFY = 0x4000, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, CXL_MBOX_OP_SET_LSA = 0x4103, @@ -108,10 +110,28 @@ static DEFINE_IDA(cxl_memdev_ida); static struct dentry *cxl_debugfs; static bool cxl_raw_allow_all; +enum { + CEL_UUID, + VENDOR_DEBUG_UUID, +}; + +/* See CXL 2.0 Table 170. Get Log Input Payload */ +static const uuid_t log_uuid[] = { + [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, + 0xb1, 0x62, 0x3b, 0x3f, 0x17), + [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, + 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), +}; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI * @opcode: The actual bits used for the mailbox protocol + * @flags: Set of flags effecting driver behavior. + * + * * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag + * will be enabled by the driver regardless of what hardware may have + * advertised. * * The cxl_mem_command is the driver's internal representation of commands that * are supported by the driver. Some of these commands may not be supported by @@ -123,9 +143,12 @@ static bool cxl_raw_allow_all; struct cxl_mem_command { struct cxl_command_info info; enum opcode opcode; + u32 flags; +#define CXL_CMD_FLAG_NONE 0 +#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) }; -#define CXL_CMD(_id, sin, sout) \ +#define CXL_CMD(_id, sin, sout, _flags) \ [CXL_MEM_COMMAND_ID_##_id] = { \ .info = { \ .id = CXL_MEM_COMMAND_ID_##_id, \ @@ -133,6 +156,7 @@ struct cxl_mem_command { .size_out = sout, \ }, \ .opcode = CXL_MBOX_OP_##_id, \ + .flags = _flags, \ } /* @@ -142,10 +166,11 @@ struct cxl_mem_command { * 0, and the user passed in 1, it is an error. */ static struct cxl_mem_command mem_commands[] = { - CXL_CMD(IDENTIFY, 0, 0x43), + CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), #ifdef CONFIG_CXL_MEM_RAW_COMMANDS - CXL_CMD(RAW, ~0, ~0), + CXL_CMD(RAW, ~0, ~0, 0), #endif + CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), }; /* @@ -633,6 +658,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, c = &mem_commands[send_cmd->id]; info = &c->info; + /* Check that the command is enabled for hardware */ + if (!test_bit(info->id, cxlm->enabled_cmds)) + return -ENOTTY; + /* Check the input buffer is the expected size */ if (info->size_in >= 0 && info->size_in != send_cmd->in.size) return -ENOMEM; @@ -757,6 +786,17 @@ static const struct file_operations cxl_memdev_fops = { .llseek = noop_llseek, }; +static inline struct cxl_mem_command *cxl_mem_find_command(u16 opcode) +{ + struct cxl_mem_command *c; + + cxl_for_each_cmd(c) + if (c->opcode == opcode) + return c; + + return NULL; +} + /** * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device. * @cxlm: The CXL memory device to communicate with. @@ -777,9 +817,7 @@ static const struct file_operations cxl_memdev_fops = { * * Mailbox commands may execute successfully yet the device itself reported an * error. While this distinction can be useful for commands from userspace, the - * kernel will only be able to use results when both are successful. It's - * expected that all callers of this function know exactly the size of the data - * they will consume from the hardware. + * kernel will only be able to use results when both are successful. * * See __cxl_mem_mbox_send_cmd() */ @@ -787,6 +825,7 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, void *in, size_t in_size, void *out, size_t out_size) { + const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); struct mbox_cmd mbox_cmd = { .opcode = opcode, .payload_in = in, @@ -812,7 +851,11 @@ static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, if (mbox_cmd.return_code != CXL_MBOX_SUCCESS) return -ENXIO; - if (mbox_cmd.size_out != out_size) + /* + * Variable sized commands can't be validated and so it's up to the + * caller to do that if they wish. + */ + if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size) return -EIO; return 0; @@ -947,6 +990,14 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo, mutex_init(&cxlm->mbox_mutex); cxlm->pdev = pdev; cxlm->regs = regs + offset; + cxlm->enabled_cmds = + devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), + sizeof(unsigned long), + GFP_KERNEL | __GFP_ZERO); + if (!cxlm->enabled_cmds) { + dev_err(dev, "No memory available for bitmap\n"); + return NULL; + } dev_dbg(dev, "Mapped CXL Memory Device resource\n"); return cxlm; @@ -1166,6 +1217,160 @@ err_ref: return rc; } +static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) +{ + u32 remaining = size; + u32 offset = 0; + + while (remaining) { + u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); + struct cxl_mbox_get_log { + uuid_t uuid; + __le32 offset; + __le32 length; + } __packed log = { + .uuid = *uuid, + .offset = cpu_to_le32(offset), + .length = cpu_to_le32(xfer_size) + }; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log, + sizeof(log), out, xfer_size); + if (rc < 0) + return rc; + + out += xfer_size; + remaining -= xfer_size; + offset += xfer_size; + } + + return 0; +} + +/** + * cxl_walk_cel() - Walk through the Command Effects Log. + * @cxlm: Device. + * @size: Length of the Command Effects Log. + * @cel: CEL + * + * Iterate over each entry in the CEL and determine if the driver supports the + * command. If so, the command is enabled for the device and can be used later. + */ +static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) +{ + struct cel_entry { + __le16 opcode; + __le16 effect; + } __packed * cel_entry; + const int cel_entries = size / sizeof(*cel_entry); + int i; + + cel_entry = (struct cel_entry *)cel; + + for (i = 0; i < cel_entries; i++) { + u16 opcode = le16_to_cpu(cel_entry[i].opcode); + struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + + if (!cmd) { + dev_dbg(&cxlm->pdev->dev, + "Opcode 0x%04x unsupported by driver", opcode); + continue; + } + + set_bit(cmd->info.id, cxlm->enabled_cmds); + } +} + +struct cxl_mbox_get_supported_logs { + __le16 entries; + u8 rsvd[6]; + struct gsl_entry { + uuid_t uuid; + __le32 size; + } __packed entry[]; +} __packed; + +static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *ret; + int rc; + + ret = kvmalloc(cxlm->payload_size, GFP_KERNEL); + if (!ret) + return ERR_PTR(-ENOMEM); + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL, + 0, ret, cxlm->payload_size); + if (rc < 0) { + kvfree(ret); + return ERR_PTR(rc); + } + + return ret; +} + +/** + * cxl_mem_enumerate_cmds() - Enumerate commands for a device. + * @cxlm: The device. + * + * Returns 0 if enumerate completed successfully. + * + * CXL devices have optional support for certain commands. This function will + * determine the set of supported commands for the hardware and update the + * enabled_cmds bitmap in the @cxlm. + */ +static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *gsl; + struct device *dev = &cxlm->pdev->dev; + struct cxl_mem_command *cmd; + int i, rc; + + gsl = cxl_get_gsl(cxlm); + if (IS_ERR(gsl)) + return PTR_ERR(gsl); + + rc = -ENOENT; + for (i = 0; i < le16_to_cpu(gsl->entries); i++) { + u32 size = le32_to_cpu(gsl->entry[i].size); + uuid_t uuid = gsl->entry[i].uuid; + u8 *log; + + dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size); + + if (!uuid_equal(&uuid, &log_uuid[CEL_UUID])) + continue; + + log = kvmalloc(size, GFP_KERNEL); + if (!log) { + rc = -ENOMEM; + goto out; + } + + rc = cxl_xfer_log(cxlm, &uuid, size, log); + if (rc) { + kvfree(log); + goto out; + } + + cxl_walk_cel(cxlm, size, log); + kvfree(log); + + /* In case CEL was bogus, enable some default commands. */ + cxl_for_each_cmd(cmd) + if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE) + set_bit(cmd->info.id, cxlm->enabled_cmds); + + /* Found the required CEL */ + rc = 0; + } + +out: + kvfree(gsl); + return rc; +} + /** * cxl_mem_identify() - Send the IDENTIFY command to the device. * @cxlm: The device to identify. @@ -1266,6 +1471,10 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; + rc = cxl_mem_enumerate_cmds(cxlm); + if (rc) + return rc; + rc = cxl_mem_identify(cxlm); if (rc) return rc; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index c316028730e7..59227f82a4c1 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -23,6 +23,7 @@ ___C(INVALID, "Invalid Command"), \ ___C(IDENTIFY, "Identify Command"), \ ___C(RAW, "Raw device command"), \ + ___C(GET_SUPPORTED_LOGS, "Get Supported Logs"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit v1.2.3 From 57ee605b976c30a86613648935d255bbe704aeab Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Tue, 16 Feb 2021 20:09:56 -0800 Subject: cxl/mem: Add set of informational commands Add initial set of formal commands beyond basic identify and command enumeration. Signed-off-by: Ben Widawsky Reviewed-by: Dan Williams Reviewed-by: Jonathan Cameron (v2) Link: https://lore.kernel.org/r/20210217040958.1354670-8-ben.widawsky@intel.com Signed-off-by: Dan Williams --- drivers/cxl/mem.c | 9 +++++++++ include/uapi/linux/cxl_mem.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index e31b3045e231..6d7d3870b5da 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -45,12 +45,16 @@ enum opcode { CXL_MBOX_OP_INVALID = 0x0000, CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_GET_FW_INFO = 0x0200, CXL_MBOX_OP_ACTIVATE_FW = 0x0202, CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, CXL_MBOX_OP_GET_LOG = 0x0401, CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_GET_LSA = 0x4102, CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_GET_HEALTH_INFO = 0x4200, CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, CXL_MBOX_OP_SCAN_MEDIA = 0x4304, CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, @@ -171,6 +175,11 @@ static struct cxl_mem_command mem_commands[] = { CXL_CMD(RAW, ~0, ~0, 0), #endif CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(GET_FW_INFO, 0, 0x50, 0), + CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0), + CXL_CMD(GET_LSA, 0x8, ~0, 0), + CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), + CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE), }; /* diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 59227f82a4c1..3155382dfc9b 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -24,6 +24,11 @@ ___C(IDENTIFY, "Identify Command"), \ ___C(RAW, "Raw device command"), \ ___C(GET_SUPPORTED_LOGS, "Get Supported Logs"), \ + ___C(GET_FW_INFO, "Get FW Info"), \ + ___C(GET_PARTITION_INFO, "Get Partition Information"), \ + ___C(GET_LSA, "Get Label Storage Area"), \ + ___C(GET_HEALTH_INFO, "Get Health Info"), \ + ___C(GET_LOG, "Get Log"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit v1.2.3 From 33b347503f014ebf76257327cbc7001c6b721956 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:00 +0200 Subject: vdpa: Define vdpa mgmt device, ops and a netlink interface To add one or more VDPA devices, define a management device which allows adding or removing vdpa device. A management device defines set of callbacks to manage vdpa devices. To begin with, it defines add and remove callbacks through which a user defined vdpa device can be added or removed. A unique management device is identified by its unique handle identified by management device name and optionally the bus name. Hence, introduce routine through which driver can register a management device and its callback operations for adding and remove a vdpa device. Introduce vdpa netlink socket family so that user can query management device and its attributes. Example of show vdpa management device which allows creating vdpa device of networking class (device id = 0x1) of virtio specification 1.1 section 5.1.1. $ vdpa mgmtdev show vdpasim_net: supported_classes: net Example of showing vdpa management device in JSON format. $ vdpa mgmtdev show -jp { "show": { "vdpasim_net": { "supported_classes": [ "net" ] } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin Including a bugfix: vpda: correctly size vdpa_nl_policy We need to ensure last entry of vdpa_nl_policy[] is zero, otherwise out-of-bounds access is hurting us. Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Parav Pandit Cc: Eli Cohen Cc: Jason Wang Cc: Michael S. Tsirkin Link: https://lore.kernel.org/r/20210210134911.4119555-1-eric.dumazet@gmail.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/Kconfig | 1 + drivers/vdpa/vdpa.c | 213 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/vdpa.h | 31 +++++++ include/uapi/linux/vdpa.h | 31 +++++++ 4 files changed, 275 insertions(+), 1 deletion(-) create mode 100644 include/uapi/linux/vdpa.h (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 92a6396f8a73..ffd1e098bfd2 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig VDPA tristate "vDPA drivers" + depends on NET help Enable this module to support vDPA device that uses a datapath which complies with virtio specifications with diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 7414bbd9057c..586e66b7f671 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -11,11 +11,17 @@ #include #include #include +#include +#include +#include +static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); +static struct genl_family vdpa_nl_family; + static int vdpa_dev_probe(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); @@ -195,13 +201,218 @@ void vdpa_unregister_driver(struct vdpa_driver *drv) } EXPORT_SYMBOL_GPL(vdpa_unregister_driver); +/** + * vdpa_mgmtdev_register - register a vdpa management device + * + * @mdev: Pointer to vdpa management device + * vdpa_mgmtdev_register() register a vdpa management device which supports + * vdpa device management. + */ +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) +{ + if (!mdev->device || !mdev->ops || !mdev->ops->dev_add || !mdev->ops->dev_del) + return -EINVAL; + + INIT_LIST_HEAD(&mdev->list); + mutex_lock(&vdpa_dev_mutex); + list_add_tail(&mdev->list, &mdev_head); + mutex_unlock(&vdpa_dev_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); + +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) +{ + mutex_lock(&vdpa_dev_mutex); + list_del(&mdev->list); + mutex_unlock(&vdpa_dev_mutex); +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); + +static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev, + const char *busname, const char *devname) +{ + /* Bus name is optional for simulated management device, so ignore the + * device with bus if bus attribute is provided. + */ + if ((busname && !mdev->device->bus) || (!busname && mdev->device->bus)) + return false; + + if (!busname && strcmp(dev_name(mdev->device), devname) == 0) + return true; + + if (busname && (strcmp(mdev->device->bus->name, busname) == 0) && + (strcmp(dev_name(mdev->device), devname) == 0)) + return true; + + return false; +} + +static struct vdpa_mgmt_dev *vdpa_mgmtdev_get_from_attr(struct nlattr **attrs) +{ + struct vdpa_mgmt_dev *mdev; + const char *busname = NULL; + const char *devname; + + if (!attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]) + return ERR_PTR(-EINVAL); + devname = nla_data(attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]); + if (attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]) + busname = nla_data(attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]); + + list_for_each_entry(mdev, &mdev_head, list) { + if (mgmtdev_handle_match(mdev, busname, devname)) + return mdev; + } + return ERR_PTR(-ENODEV); +} + +static int vdpa_nl_mgmtdev_handle_fill(struct sk_buff *msg, const struct vdpa_mgmt_dev *mdev) +{ + if (mdev->device->bus && + nla_put_string(msg, VDPA_ATTR_MGMTDEV_BUS_NAME, mdev->device->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, dev_name(mdev->device))) + return -EMSGSIZE; + return 0; +} + +static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *msg, + u32 portid, u32 seq, int flags) +{ + u64 supported_classes = 0; + void *hdr; + int i = 0; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_MGMTDEV_NEW); + if (!hdr) + return -EMSGSIZE; + err = vdpa_nl_mgmtdev_handle_fill(msg, mdev); + if (err) + goto msg_err; + + while (mdev->id_table[i].device) { + supported_classes |= BIT(mdev->id_table[i].device); + i++; + } + + if (nla_put_u64_64bit(msg, VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, + supported_classes, VDPA_ATTR_UNSPEC)) { + err = -EMSGSIZE; + goto msg_err; + } + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_mgmtdev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + mutex_unlock(&vdpa_dev_mutex); + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified mgmt device"); + err = PTR_ERR(mdev); + goto out; + } + + err = vdpa_mgmtdev_fill(mdev, msg, info->snd_portid, info->snd_seq, 0); + mutex_unlock(&vdpa_dev_mutex); + if (err) + goto out; + err = genlmsg_reply(msg, info); + return err; + +out: + nlmsg_free(msg); + return err; +} + +static int +vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_mgmt_dev *mdev; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&vdpa_dev_mutex); + list_for_each_entry(mdev, &mdev_head, list) { + if (idx < start) { + idx++; + continue; + } + err = vdpa_mgmtdev_fill(mdev, msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = idx; + return msg->len; +} + +static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { + [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, + [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, +}; + +static const struct genl_ops vdpa_nl_ops[] = { + { + .cmd = VDPA_CMD_MGMTDEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_mgmtdev_get_doit, + .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, + }, +}; + +static struct genl_family vdpa_nl_family __ro_after_init = { + .name = VDPA_GENL_NAME, + .version = VDPA_GENL_VERSION, + .maxattr = VDPA_ATTR_MAX, + .policy = vdpa_nl_policy, + .netnsok = false, + .module = THIS_MODULE, + .ops = vdpa_nl_ops, + .n_ops = ARRAY_SIZE(vdpa_nl_ops), +}; + static int vdpa_init(void) { - return bus_register(&vdpa_bus); + int err; + + err = bus_register(&vdpa_bus); + if (err) + return err; + err = genl_register_family(&vdpa_nl_family); + if (err) + goto err; + return 0; + +err: + bus_unregister(&vdpa_bus); + return err; } static void __exit vdpa_exit(void) { + genl_unregister_family(&vdpa_nl_family); bus_unregister(&vdpa_bus); ida_destroy(&vdpa_index_ida); } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5700baa22356..6b8b4222bca6 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -35,6 +35,8 @@ struct vdpa_vq_state { u16 avail_index; }; +struct vdpa_mgmt_dev; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -335,4 +337,33 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, ops->get_config(vdev, offset, buf, len); } +/** + * vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). + */ +struct vdpa_mgmtdev_ops { + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); +}; + +struct vdpa_mgmt_dev { + struct device *device; + const struct vdpa_mgmtdev_ops *ops; + const struct virtio_device_id *id_table; /* supported ids */ + struct list_head list; +}; + +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev); + #endif /* _LINUX_VDPA_H */ diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h new file mode 100644 index 000000000000..d44d82e567b1 --- /dev/null +++ b/include/uapi/linux/vdpa.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * vdpa device management interface + * Copyright (c) 2020 Mellanox Technologies Ltd. All rights reserved. + */ + +#ifndef _UAPI_LINUX_VDPA_H_ +#define _UAPI_LINUX_VDPA_H_ + +#define VDPA_GENL_NAME "vdpa" +#define VDPA_GENL_VERSION 0x1 + +enum vdpa_command { + VDPA_CMD_UNSPEC, + VDPA_CMD_MGMTDEV_NEW, + VDPA_CMD_MGMTDEV_GET, /* can dump */ +}; + +enum vdpa_attr { + VDPA_ATTR_UNSPEC, + + /* bus name (optional) + dev name together make the parent device handle */ + VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ + VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ + VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ + + /* new attributes must be added above here */ + VDPA_ATTR_MAX, +}; + +#endif -- cgit v1.2.3 From 903f7bcaedb84ca47998e609015a34ddde93742e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:01 +0200 Subject: vdpa: Enable a user to add and delete a vdpa device Add the ability to add and delete a vdpa device. Examples: Create a vdpa device of type network named "foo2" from the management device vdpasim: $ vdpa dev add mgmtdev vdpasim_net name foo2 Delete the vdpa device after its use: $ vdpa dev del foo2 Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 143 ++++++++++++++++++++++++++++++++++++++++++---- include/linux/vdpa.h | 6 ++ include/uapi/linux/vdpa.h | 4 ++ 3 files changed, 143 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 586e66b7f671..f1228189814f 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -136,6 +136,37 @@ static int vdpa_name_match(struct device *dev, const void *data) return (strcmp(dev_name(&vdev->dev), data) == 0); } +static int __vdpa_register_device(struct vdpa_device *vdev) +{ + struct device *dev; + + lockdep_assert_held(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); + if (dev) { + put_device(dev); + return -EEXIST; + } + return device_add(&vdev->dev); +} + +/** + * _vdpa_register_device - register a vDPA device with vdpa lock held + * Caller must have a succeed call of vdpa_alloc_device() before. + * Caller must invoke this routine in the management device dev_add() + * callback after setting up valid mgmtdev for this vdpa device. + * @vdev: the vdpa device to be registered to vDPA bus + * + * Returns an error when fail to add device to vDPA bus + */ +int _vdpa_register_device(struct vdpa_device *vdev) +{ + if (!vdev->mdev) + return -EINVAL; + + return __vdpa_register_device(vdev); +} +EXPORT_SYMBOL_GPL(_vdpa_register_device); + /** * vdpa_register_device - register a vDPA device * Callers must have a succeed call of vdpa_alloc_device() before. @@ -145,24 +176,29 @@ static int vdpa_name_match(struct device *dev, const void *data) */ int vdpa_register_device(struct vdpa_device *vdev) { - struct device *dev; int err; mutex_lock(&vdpa_dev_mutex); - dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); - if (dev) { - put_device(dev); - err = -EEXIST; - goto name_err; - } - - err = device_add(&vdev->dev); -name_err: + err = __vdpa_register_device(vdev); mutex_unlock(&vdpa_dev_mutex); return err; } EXPORT_SYMBOL_GPL(vdpa_register_device); +/** + * _vdpa_unregister_device - unregister a vDPA device + * Caller must invoke this routine as part of management device dev_del() + * callback. + * @vdev: the vdpa device to be unregisted from vDPA bus + */ +void _vdpa_unregister_device(struct vdpa_device *vdev) +{ + lockdep_assert_held(&vdpa_dev_mutex); + WARN_ON(!vdev->mdev); + device_unregister(&vdev->dev); +} +EXPORT_SYMBOL_GPL(_vdpa_unregister_device); + /** * vdpa_unregister_device - unregister a vDPA device * @vdev: the vdpa device to be unregisted from vDPA bus @@ -221,10 +257,25 @@ int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); +static int vdpa_match_remove(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_mgmt_dev *mdev = vdev->mdev; + + if (mdev == data) + mdev->ops->dev_del(mdev, vdev); + return 0; +} + void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) { mutex_lock(&vdpa_dev_mutex); + list_del(&mdev->list); + + /* Filter out all the entries belong to this management device and delete it. */ + bus_for_each_dev(&vdpa_bus, NULL, mdev, vdpa_match_remove); + mutex_unlock(&vdpa_dev_mutex); } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); @@ -368,9 +419,69 @@ out: return msg->len; } +static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified management device"); + err = PTR_ERR(mdev); + goto err; + } + + err = mdev->ops->dev_add(mdev, name); +err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + +static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct vdpa_device *vdev; + struct device *dev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "Only user created device can be deleted by user"); + err = -EINVAL; + goto mdev_err; + } + mdev = vdev->mdev; + mdev->ops->dev_del(mdev, vdev); +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, + [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, }; static const struct genl_ops vdpa_nl_ops[] = { @@ -380,6 +491,18 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_mgmtdev_get_doit, .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_NEW, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_add_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = VDPA_CMD_DEV_DEL, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_del_set_doit, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6b8b4222bca6..4ab5494503a8 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -45,6 +45,8 @@ struct vdpa_mgmt_dev; * @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: maximum number of supported virtqueues + * @mdev: management device pointer; caller must setup when registering device as part + * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). */ struct vdpa_device { struct device dev; @@ -53,6 +55,7 @@ struct vdpa_device { unsigned int index; bool features_valid; int nvqs; + struct vdpa_mgmt_dev *mdev; }; /** @@ -260,6 +263,9 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, int vdpa_register_device(struct vdpa_device *vdev); void vdpa_unregister_device(struct vdpa_device *vdev); +int _vdpa_register_device(struct vdpa_device *vdev); +void _vdpa_unregister_device(struct vdpa_device *vdev); + /** * vdpa_driver - operations for a vDPA driver * @driver: underlying device driver diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index d44d82e567b1..bb4a1f00eb1c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -14,6 +14,8 @@ enum vdpa_command { VDPA_CMD_UNSPEC, VDPA_CMD_MGMTDEV_NEW, VDPA_CMD_MGMTDEV_GET, /* can dump */ + VDPA_CMD_DEV_NEW, + VDPA_CMD_DEV_DEL, }; enum vdpa_attr { @@ -24,6 +26,8 @@ enum vdpa_attr { VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ + VDPA_ATTR_DEV_NAME, /* string */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From bc0d90ee021f1baecd6aaa010d787eb373aa74dd Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:02 +0200 Subject: vdpa: Enable user to query vdpa device info Enable user to query vdpa device information. $ vdpa dev add mgmtdev vdpasim_net name foo2 Show the newly created vdpa device by its name: $ vdpa dev show foo2 foo2: type network mgmtdev vdpasim_net vendor_id 0 max_vqs 2 max_vq_size 256 $ vdpa dev show foo2 -jp { "dev": { "foo2": { "type": "network", "mgmtdev": "vdpasim_net", "vendor_id": 0, "max_vqs": 2, "max_vq_size": 256 } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-6-parav@nvidia.com Including a memory leak fix: Link: https://lore.kernel.org/r/20210217060614.59561-1-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 5 ++ 2 files changed, 136 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index f1228189814f..da67f07e24fd 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -478,6 +478,131 @@ dev_err: return err; } +static int +vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u16 max_vq_size; + u32 device_id; + u32 vendor_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_DEV_NEW); + if (!hdr) + return -EMSGSIZE; + + err = vdpa_nl_mgmtdev_handle_fill(msg, vdev->mdev); + if (err) + goto msg_err; + + device_id = vdev->config->get_device_id(vdev); + vendor_id = vdev->config->get_vendor_id(vdev); + max_vq_size = vdev->config->get_vq_num_max(vdev); + + err = -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_VENDOR_ID, vendor_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_MAX_VQS, vdev->nvqs)) + goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_fill(vdev, msg, info->snd_portid, info->snd_seq, 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); +mdev_err: + put_device(dev); +err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +struct vdpa_dev_dump_info { + struct sk_buff *msg; + struct netlink_callback *cb; + int start_idx; + int idx; +}; + +static int vdpa_dev_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, @@ -503,6 +628,12 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_del_set_doit, .flags = GENL_ADMIN_PERM, }, + { + .cmd = VDPA_CMD_DEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_get_doit, + .dumpit = vdpa_nl_cmd_dev_get_dumpit, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index bb4a1f00eb1c..66a41e4ec163 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -16,6 +16,7 @@ enum vdpa_command { VDPA_CMD_MGMTDEV_GET, /* can dump */ VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, + VDPA_CMD_DEV_GET, /* can dump */ }; enum vdpa_attr { @@ -27,6 +28,10 @@ enum vdpa_attr { VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ VDPA_ATTR_DEV_NAME, /* string */ + VDPA_ATTR_DEV_ID, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ + VDPA_ATTR_DEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 1c0aa1fae1acb77c5f9917adb0e4cb4500b9f3a6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 20 Feb 2021 11:55:28 -0700 Subject: io_uring: flag new native workers with IORING_FEAT_NATIVE_WORKERS A few reasons to do this: - The naming of the manager and worker have changed. That's a user visible change, so makes sense to flag it. - Opening certain files that use ->signal (like /proc/self or /dev/tty) now works, and the flag tells the application upfront that this is the case. - Related to the above, using signalfd will now work as well. Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- include/uapi/linux/io_uring.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 378cf79e66c9..cf9a5fa1ad03 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9467,7 +9467,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | - IORING_FEAT_EXT_ARG; + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ac4e1738a9af..2514eb6b1cf2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -262,6 +262,7 @@ struct io_uring_params { #define IORING_FEAT_POLL_32BITS (1U << 6) #define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) #define IORING_FEAT_EXT_ARG (1U << 8) +#define IORING_FEAT_NATIVE_WORKERS (1U << 9) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From bda420b985054a3badafef23807c4b4fa38a3dff Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 24 Feb 2021 12:09:43 -0800 Subject: numa balancing: migrate on fault among multiple bound nodes Now, NUMA balancing can only optimize the page placement among the NUMA nodes if the default memory policy is used. Because the memory policy specified explicitly should take precedence. But this seems too strict in some situations. For example, on a system with 4 NUMA nodes, if the memory of an application is bound to the node 0 and 1, NUMA balancing can potentially migrate the pages between the node 0 and 1 to reduce cross-node accessing without breaking the explicit memory binding policy. So in this patch, we add MPOL_F_NUMA_BALANCING mode flag to set_mempolicy() when mode is MPOL_BIND. With the flag specified, NUMA balancing will be enabled within the thread to optimize the page placement within the constrains of the specified memory binding policy. With the newly added flag, the NUMA balancing control mechanism becomes, - sysctl knob numa_balancing can enable/disable the NUMA balancing globally. - even if sysctl numa_balancing is enabled, the NUMA balancing will be disabled for the memory areas or applications with the explicit memory policy by default. - MPOL_F_NUMA_BALANCING can be used to enable the NUMA balancing for the applications when specifying the explicit memory policy (MPOL_BIND). Various page placement optimization based on the NUMA balancing can be done with these flags. As the first step, in this patch, if the memory of the application is bound to multiple nodes (MPOL_BIND), and in the hint page fault handler the accessing node are in the policy nodemask, the page will be tried to be migrated to the accessing node to reduce the cross-node accessing. If the newly added MPOL_F_NUMA_BALANCING flag is specified by an application on an old kernel version without its support, set_mempolicy() will return -1 and errno will be set to EINVAL. The application can use this behavior to run on both old and new kernel versions. And if the MPOL_F_NUMA_BALANCING flag is specified for the mode other than MPOL_BIND, set_mempolicy() will return -1 and errno will be set to EINVAL as before. Because we don't support optimization based on the NUMA balancing for these modes. In the previous version of the patch, we tried to reuse MPOL_MF_LAZY for mbind(). But that flag is tied to MPOL_MF_MOVE.*, so it seems not a good API/ABI for the purpose of the patch. And because it's not clear whether it's necessary to enable NUMA balancing for a specific memory area inside an application, so we only add the flag at the thread level (set_mempolicy()) instead of the memory area level (mbind()). We can do that when it become necessary. To test the patch, we run a test case as follows on a 4-node machine with 192 GB memory (48 GB per node). 1. Change pmbench memory accessing benchmark to call set_mempolicy() to bind its memory to node 1 and 3 and enable NUMA balancing. Some related code snippets are as follows, #include #include struct bitmask *bmp; int ret; bmp = numa_parse_nodestring("1,3"); ret = set_mempolicy(MPOL_BIND | MPOL_F_NUMA_BALANCING, bmp->maskp, bmp->size + 1); /* If MPOL_F_NUMA_BALANCING isn't supported, fall back to MPOL_BIND */ if (ret < 0 && errno == EINVAL) ret = set_mempolicy(MPOL_BIND, bmp->maskp, bmp->size + 1); if (ret < 0) { perror("Failed to call set_mempolicy"); exit(-1); } 2. Run a memory eater on node 3 to use 40 GB memory before running pmbench. 3. Run pmbench with 64 processes, the working-set size of each process is 640 MB, so the total working-set size is 64 * 640 MB = 40 GB. The CPU and the memory (as in step 1.) of all pmbench processes is bound to node 1 and 3. So, after CPU usage is balanced, some pmbench processes run on the CPUs of the node 3 will access the memory of the node 1. 4. After the pmbench processes run for 100 seconds, kill the memory eater. Now it's possible for some pmbench processes to migrate their pages from node 1 to node 3 to reduce cross-node accessing. Test results show that, with the patch, the pages can be migrated from node 1 to node 3 after killing the memory eater, and the pmbench score can increase about 17.5%. Link: https://lkml.kernel.org/r/20210120061235.148637-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Acked-by: Mel Gorman Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Rik van Riel Cc: Johannes Weiner Cc: "Matthew Wilcox (Oracle)" Cc: Dave Hansen Cc: Andi Kleen Cc: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/mempolicy.h | 4 +++- mm/mempolicy.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 3354774af61e..8948467b3992 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -28,12 +28,14 @@ enum { /* Flags for set_mempolicy */ #define MPOL_F_STATIC_NODES (1 << 15) #define MPOL_F_RELATIVE_NODES (1 << 14) +#define MPOL_F_NUMA_BALANCING (1 << 13) /* Optimize with NUMA balancing if possible */ /* * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to * either set_mempolicy() or mbind(). */ -#define MPOL_MODE_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) +#define MPOL_MODE_FLAGS \ + (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES | MPOL_F_NUMA_BALANCING) /* Flags for get_mempolicy */ #define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2c3a86502053..6961238c7ef5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -875,6 +875,16 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, goto out; } + if (flags & MPOL_F_NUMA_BALANCING) { + if (new && new->mode == MPOL_BIND) { + new->flags |= (MPOL_F_MOF | MPOL_F_MORON); + } else { + ret = -EINVAL; + mpol_put(new); + goto out; + } + } + ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { mpol_put(new); @@ -2486,6 +2496,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_BIND: + /* Optimize placement among multiple nodes via NUMA balancing */ + if (pol->flags & MPOL_F_MORON) { + if (node_isset(thisnid, pol->v.nodes)) + break; + goto out; + } /* * allows binding to multiple nodes. -- cgit v1.2.3 From df54714f579a77662054132161612ce3da876b0d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 25 Feb 2021 17:20:56 -0800 Subject: include/linux: remove repeated words Drop the doubled word "for" in a comment. {firewire-cdev.h} Drop the doubled word "in" in a comment. {input.h} Drop the doubled word "a" in a comment. {mdev.h} Drop the doubled word "the" in a comment. {ptrace.h} Link: https://lkml.kernel.org/r/20210126232444.22861-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Stefan Richter Cc: Dmitry Torokhov Cc: Kirti Wankhede Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mdev.h | 2 +- include/linux/ptrace.h | 2 +- include/uapi/linux/firewire-cdev.h | 2 +- include/uapi/linux/input.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 9004375c462e..27eb383cb95d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -42,7 +42,7 @@ struct device *mdev_get_iommu_device(struct device *dev); * @mdev: mdev_device structure on of mediated device * that is being created * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for a + * @remove: Called to free resources in parent device's driver for * a mediated device. It is mandatory to provide 'remove' * ops. * @mdev: mdev_device device structure which is being diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 2a9df80ea887..b5ebf6c01292 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -171,7 +171,7 @@ static inline void ptrace_event(int event, unsigned long message) * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the - * the ptrace parent's pid namespace. + * ptrace parent's pid namespace. * * Called without locks. */ diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 7e5b5c10a49c..5effa9832802 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -844,7 +844,7 @@ struct fw_cdev_queue_iso { * struct fw_cdev_start_iso - Start an isochronous transmission or reception * @cycle: Cycle in which to start I/O. If @cycle is greater than or * equal to 0, the I/O will start on that cycle. - * @sync: Determines the value to wait for for receive packets that have + * @sync: Determines the value to wait for receive packets that have * the %FW_CDEV_ISO_SYNC bit set * @tags: Tag filter bit mask. Only valid for isochronous reception. * Determines the tag values for which packets will be accepted. diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 9a61c28ed3ae..ee3127461ee0 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -84,7 +84,7 @@ struct input_id { * in units per radian. * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in - * in units per g (units/g) and in units per degree per second + * units per g (units/g) and in units per degree per second * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ). */ struct input_absinfo { -- cgit v1.2.3 From 30b5c851af7991ad08abe90c1e7c31615fa98a1a Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 1 Mar 2021 12:53:09 +0000 Subject: KVM: x86/xen: Add support for vCPU runstate information This is how Xen guests do steal time accounting. The hypervisor records the amount of time spent in each of running/runnable/blocked/offline states. In the Xen accounting, a vCPU is still in state RUNSTATE_running while in Xen for a hypercall or I/O trap, etc. Only if Xen explicitly schedules does the state become RUNSTATE_blocked. In KVM this means that even when the vCPU exits the kvm_run loop, the state remains RUNSTATE_running. The VMM can explicitly set the vCPU to RUNSTATE_blocked by using the KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT attribute, and can also use KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST to retrospectively add a given amount of time to the blocked state and subtract it from the running state. The state_entry_time corresponds to get_kvmclock_ns() at the time the vCPU entered the current state, and the total times of all four states should always add up to state_entry_time. Co-developed-by: Joao Martins Signed-off-by: Joao Martins Signed-off-by: David Woodhouse Message-Id: <20210301125309.874953-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 41 +++ arch/x86/include/asm/kvm_host.h | 6 + arch/x86/kvm/x86.c | 13 +- arch/x86/kvm/xen.c | 286 +++++++++++++++++++++ arch/x86/kvm/xen.h | 40 ++- include/uapi/linux/kvm.h | 13 + .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 159 +++++++++++- 7 files changed, 553 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 359435d4e417..1a2b5210cdbf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4878,6 +4878,14 @@ see KVM_XEN_HVM_SET_ATTR above. union { __u64 gpa; __u64 pad[4]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; } u; }; @@ -4890,6 +4898,31 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO Sets the guest physical address of an additional pvclock structure for a given vCPU. This is typically used for guest vsyscall support. +KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR + Sets the guest physical address of the vcpu_runstate_info for a given + vCPU. This is how a Xen guest tracks CPU state such as steal time. + +KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT + Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of + the given vCPU from the .u.runstate.state member of the structure. + KVM automatically accounts running and runnable time but blocked + and offline states are only entered explicitly. + +KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA + Sets all fields of the vCPU runstate data from the .u.runstate member + of the structure, including the current runstate. The state_entry_time + must equal the sum of the other four times. + +KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST + This *adds* the contents of the .u.runstate members of the structure + to the corresponding members of the given vCPU's runstate data, thus + permitting atomic adjustments to the runstate times. The adjustment + to the state_entry_time must equal the sum of the adjustments to the + other four times. The state field must be set to -1, or to a valid + runstate value (RUNSTATE_running, RUNSTATE_runnable, RUNSTATE_blocked + or RUNSTATE_offline) to set the current accounted state as of the + adjusted state_entry_time. + 4.130 KVM_XEN_VCPU_GET_ATTR --------------------------- @@ -4902,6 +4935,9 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO Allows Xen vCPU attributes to be read. For the structure and types, see KVM_XEN_VCPU_SET_ATTR above. +The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used +with the KVM_XEN_VCPU_GET_ATTR ioctl. + 5. The kvm_run structure ======================== @@ -6666,6 +6702,7 @@ PVHVM guests. Valid flags are:: #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) + #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 2) The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG ioctl is available, for the guest to set its hypercall page. @@ -6680,3 +6717,7 @@ KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, KVM_XEN_VCPU_SET_ATTR and KVM_XEN_VCPU_GET_ATTR ioctls, as well as the delivery of exception vectors for event channel upcalls when the evtchn_upcall_pending field of a vcpu's vcpu_info is set. + +The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related +features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are +supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 85ccbd4b7c52..877a4025d8da 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -535,10 +535,16 @@ struct kvm_vcpu_hv { /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; + u32 current_runstate; bool vcpu_info_set; bool vcpu_time_info_set; + bool runstate_set; struct gfn_to_hva_cache vcpu_info_cache; struct gfn_to_hva_cache vcpu_time_info_cache; + struct gfn_to_hva_cache runstate_cache; + u64 last_steal; + u64 runstate_entry_time; + u64 runstate_times[4]; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4a5ce57b0bb2..868213ca4f98 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2956,6 +2956,11 @@ static void record_steal_time(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + if (kvm_xen_msr_enabled(vcpu->kvm)) { + kvm_xen_runstate_set_running(vcpu); + return; + } + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -3760,6 +3765,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO; + if (sched_info_on()) + r |= KVM_XEN_HVM_CONFIG_RUNSTATE; break; #endif case KVM_CAP_SYNC_REGS: @@ -4039,7 +4046,11 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) if (vcpu->preempted && !vcpu->arch.guest_state_protected) vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); - kvm_steal_time_set_preempted(vcpu); + if (kvm_xen_msr_enabled(vcpu->kvm)) + kvm_xen_runstate_set_preempted(vcpu); + else + kvm_steal_time_set_preempted(vcpu); + static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 77b20ff09078..ae17250e1efe 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -11,9 +11,11 @@ #include "hyperv.h" #include +#include #include #include +#include #include "trace.h" @@ -61,6 +63,132 @@ out: return ret; } +static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) +{ + struct kvm_vcpu_xen *vx = &v->arch.xen; + u64 now = get_kvmclock_ns(v->kvm); + u64 delta_ns = now - vx->runstate_entry_time; + u64 run_delay = current->sched_info.run_delay; + + if (unlikely(!vx->runstate_entry_time)) + vx->current_runstate = RUNSTATE_offline; + + /* + * Time waiting for the scheduler isn't "stolen" if the + * vCPU wasn't running anyway. + */ + if (vx->current_runstate == RUNSTATE_running) { + u64 steal_ns = run_delay - vx->last_steal; + + delta_ns -= steal_ns; + + vx->runstate_times[RUNSTATE_runnable] += steal_ns; + } + vx->last_steal = run_delay; + + vx->runstate_times[vx->current_runstate] += delta_ns; + vx->current_runstate = state; + vx->runstate_entry_time = now; +} + +void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) +{ + struct kvm_vcpu_xen *vx = &v->arch.xen; + uint64_t state_entry_time; + unsigned int offset; + + kvm_xen_update_runstate(v, state); + + if (!vx->runstate_set) + return; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); +#ifdef CONFIG_X86_64 + /* + * The only difference is alignment of uint64_t in 32-bit. + * So the first field 'state' is accessed directly using + * offsetof() (where its offset happens to be zero), while the + * remaining fields which are all uint64_t, start at 'offset' + * which we tweak here by adding 4. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != + offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != + offsetof(struct compat_vcpu_runstate_info, time) + 4); + + if (v->kvm->arch.xen.long_mode) + offset = offsetof(struct vcpu_runstate_info, state_entry_time); +#endif + /* + * First write the updated state_entry_time at the appropriate + * location determined by 'offset'. + */ + state_entry_time = vx->runstate_entry_time; + state_entry_time |= XEN_RUNSTATE_UPDATE; + + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) != + sizeof(state_entry_time)); + BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) != + sizeof(state_entry_time)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &state_entry_time, offset, + sizeof(state_entry_time))) + return; + smp_wmb(); + + /* + * Next, write the new runstate. This is in the *same* place + * for 32-bit and 64-bit guests, asserted here for paranoia. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != + offsetof(struct compat_vcpu_runstate_info, state)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) != + sizeof(vx->current_runstate)); + BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) != + sizeof(vx->current_runstate)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &vx->current_runstate, + offsetof(struct vcpu_runstate_info, state), + sizeof(vx->current_runstate))) + return; + + /* + * Write the actual runstate times immediately after the + * runstate_entry_time. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != + offsetof(struct vcpu_runstate_info, time) - sizeof(u64)); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) != + offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + sizeof(((struct compat_vcpu_runstate_info *)0)->time)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + sizeof(vx->runstate_times)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &vx->runstate_times[0], + offset + sizeof(u64), + sizeof(vx->runstate_times))) + return; + + smp_wmb(); + + /* + * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's + * runstate_entry_time field. + */ + + state_entry_time &= ~XEN_RUNSTATE_UPDATE; + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &state_entry_time, offset, + sizeof(state_entry_time))) + return; +} + int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { u8 rc = 0; @@ -223,6 +351,121 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } break; + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.gpa == GPA_INVALID) { + vcpu->arch.xen.runstate_set = false; + r = 0; + break; + } + + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.runstate_cache, + data->u.gpa, + sizeof(struct vcpu_runstate_info)); + if (!r) { + vcpu->arch.xen.runstate_set = true; + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline) { + r = -EINVAL; + break; + } + + kvm_xen_update_runstate(vcpu, data->u.runstate.state); + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline) { + r = -EINVAL; + break; + } + if (data->u.runstate.state_entry_time != + (data->u.runstate.time_running + + data->u.runstate.time_runnable + + data->u.runstate.time_blocked + + data->u.runstate.time_offline)) { + r = -EINVAL; + break; + } + if (get_kvmclock_ns(vcpu->kvm) < + data->u.runstate.state_entry_time) { + r = -EINVAL; + break; + } + + vcpu->arch.xen.current_runstate = data->u.runstate.state; + vcpu->arch.xen.runstate_entry_time = + data->u.runstate.state_entry_time; + vcpu->arch.xen.runstate_times[RUNSTATE_running] = + data->u.runstate.time_running; + vcpu->arch.xen.runstate_times[RUNSTATE_runnable] = + data->u.runstate.time_runnable; + vcpu->arch.xen.runstate_times[RUNSTATE_blocked] = + data->u.runstate.time_blocked; + vcpu->arch.xen.runstate_times[RUNSTATE_offline] = + data->u.runstate.time_offline; + vcpu->arch.xen.last_steal = current->sched_info.run_delay; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline && + data->u.runstate.state != (u64)-1) { + r = -EINVAL; + break; + } + /* The adjustment must add up */ + if (data->u.runstate.state_entry_time != + (data->u.runstate.time_running + + data->u.runstate.time_runnable + + data->u.runstate.time_blocked + + data->u.runstate.time_offline)) { + r = -EINVAL; + break; + } + + if (get_kvmclock_ns(vcpu->kvm) < + (vcpu->arch.xen.runstate_entry_time + + data->u.runstate.state_entry_time)) { + r = -EINVAL; + break; + } + + vcpu->arch.xen.runstate_entry_time += + data->u.runstate.state_entry_time; + vcpu->arch.xen.runstate_times[RUNSTATE_running] += + data->u.runstate.time_running; + vcpu->arch.xen.runstate_times[RUNSTATE_runnable] += + data->u.runstate.time_runnable; + vcpu->arch.xen.runstate_times[RUNSTATE_blocked] += + data->u.runstate.time_blocked; + vcpu->arch.xen.runstate_times[RUNSTATE_offline] += + data->u.runstate.time_offline; + + if (data->u.runstate.state <= RUNSTATE_offline) + kvm_xen_update_runstate(vcpu, data->u.runstate.state); + r = 0; + break; + default: break; } @@ -255,6 +498,49 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) r = 0; break; + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (vcpu->arch.xen.runstate_set) { + data->u.gpa = vcpu->arch.xen.runstate_cache.gpa; + r = 0; + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate.state = vcpu->arch.xen.current_runstate; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate.state = vcpu->arch.xen.current_runstate; + data->u.runstate.state_entry_time = + vcpu->arch.xen.runstate_entry_time; + data->u.runstate.time_running = + vcpu->arch.xen.runstate_times[RUNSTATE_running]; + data->u.runstate.time_runnable = + vcpu->arch.xen.runstate_times[RUNSTATE_runnable]; + data->u.runstate.time_blocked = + vcpu->arch.xen.runstate_times[RUNSTATE_blocked]; + data->u.runstate.time_offline = + vcpu->arch.xen.runstate_times[RUNSTATE_offline]; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST: + r = -EINVAL; + break; + default: break; } diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index 87eaf2be9549..463a7844a8ca 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -23,6 +23,12 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data); int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); void kvm_xen_destroy_vm(struct kvm *kvm); +static inline bool kvm_xen_msr_enabled(struct kvm *kvm) +{ + return static_branch_unlikely(&kvm_xen_enabled.key) && + kvm->arch.xen_hvm_config.msr; +} + static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -48,6 +54,11 @@ static inline void kvm_xen_destroy_vm(struct kvm *kvm) { } +static inline bool kvm_xen_msr_enabled(struct kvm *kvm) +{ + return false; +} + static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) { return false; @@ -61,10 +72,31 @@ static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu) int kvm_xen_hypercall(struct kvm_vcpu *vcpu); -/* 32-bit compatibility definitions, also used natively in 32-bit build */ #include #include +#include +void kvm_xen_update_runstate_guest(struct kvm_vcpu *vcpu, int state); + +static inline void kvm_xen_runstate_set_running(struct kvm_vcpu *vcpu) +{ + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_running); +} + +static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) +{ + /* + * If the vCPU wasn't preempted but took a normal exit for + * some reason (hypercalls, I/O, etc.), that is accounted as + * still RUNSTATE_running, as the VMM is still operating on + * behalf of the vCPU. Only if the VMM does actually block + * does it need to enter RUNSTATE_blocked. + */ + if (vcpu->preempted) + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); +} + +/* 32-bit compatibility definitions, also used natively in 32-bit build */ struct compat_arch_vcpu_info { unsigned int cr2; unsigned int pad[5]; @@ -97,4 +129,10 @@ struct compat_shared_info { struct compat_arch_shared_info arch; }; +struct compat_vcpu_runstate_info { + int state; + uint64_t state_entry_time; + uint64_t time[4]; +} __attribute__((packed)); + #endif /* __ARCH_X86_KVM_XEN_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8b281f722e5b..f6afee209620 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1154,6 +1154,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) struct kvm_xen_hvm_config { __u32 flags; @@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr { union { __u64 gpa; __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; } u; }; /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 9246ea310587..804ff5ff022d 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -13,19 +13,27 @@ #include #include +#include +#include #define VCPU_ID 5 +#define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 #define PAGE_SIZE 4096 #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) +#define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) + +#define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) static struct kvm_vm *vm; #define XEN_HYPERCALL_MSR 0x40000000 +#define MIN_STEAL_TIME 50000 + struct pvclock_vcpu_time_info { u32 version; u32 pad0; @@ -43,11 +51,67 @@ struct pvclock_wall_clock { u32 nsec; } __attribute__((__packed__)); +struct vcpu_runstate_info { + uint32_t state; + uint64_t state_entry_time; + uint64_t time[4]; +}; + +#define RUNSTATE_running 0 +#define RUNSTATE_runnable 1 +#define RUNSTATE_blocked 2 +#define RUNSTATE_offline 3 + static void guest_code(void) { + struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + + /* Test having the host set runstates manually */ + GUEST_SYNC(RUNSTATE_runnable); + GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); + GUEST_ASSERT(rs->state == 0); + + GUEST_SYNC(RUNSTATE_blocked); + GUEST_ASSERT(rs->time[RUNSTATE_blocked] != 0); + GUEST_ASSERT(rs->state == 0); + + GUEST_SYNC(RUNSTATE_offline); + GUEST_ASSERT(rs->time[RUNSTATE_offline] != 0); + GUEST_ASSERT(rs->state == 0); + + /* Test runstate time adjust */ + GUEST_SYNC(4); + GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x5a); + GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x6b6b); + + /* Test runstate time set */ + GUEST_SYNC(5); + GUEST_ASSERT(rs->state_entry_time >= 0x8000); + GUEST_ASSERT(rs->time[RUNSTATE_runnable] == 0); + GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x6b6b); + GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x5a); + + /* sched_yield() should result in some 'runnable' time */ + GUEST_SYNC(6); + GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); + GUEST_DONE(); } +static long get_run_delay(void) +{ + char path[64]; + long val[2]; + FILE *fp; + + sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); + fp = fopen(path, "r"); + fscanf(fp, "%ld %ld ", &val[0], &val[1]); + fclose(fp); + + return val[1]; +} + static int cmp_timespec(struct timespec *a, struct timespec *b) { if (a->tv_sec > b->tv_sec) @@ -66,12 +130,14 @@ int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; - if (!(kvm_check_cap(KVM_CAP_XEN_HVM) & - KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { + int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); + if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available"); exit(KSFT_SKIP); } + bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + clock_gettime(CLOCK_REALTIME, &min_ts); vm = vm_create_default(VCPU_ID, 0, (void *) guest_code); @@ -80,6 +146,7 @@ int main(int argc, char *argv[]) /* Map a region for the shared_info page */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); + virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2, 0); struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, @@ -111,6 +178,17 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + if (do_runstate_tests) { + struct kvm_xen_vcpu_attr st = { + .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, + .u.gpa = RUNSTATE_ADDR, + }; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); + } + + struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);; + rs->state = 0x5a; + for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; @@ -126,8 +204,56 @@ int main(int argc, char *argv[]) case UCALL_ABORT: TEST_FAIL("%s", (const char *)uc.args[0]); /* NOT REACHED */ - case UCALL_SYNC: + case UCALL_SYNC: { + struct kvm_xen_vcpu_attr rst; + long rundelay; + + /* If no runstate support, bail out early */ + if (!do_runstate_tests) + goto done; + + TEST_ASSERT(rs->state_entry_time == rs->time[0] + + rs->time[1] + rs->time[2] + rs->time[3], + "runstate times don't add up"); + + switch (uc.args[1]) { + case RUNSTATE_running...RUNSTATE_offline: + rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; + rst.u.runstate.state = uc.args[1]; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + break; + case 4: + rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; + memset(&rst.u, 0, sizeof(rst.u)); + rst.u.runstate.state = (uint64_t)-1; + rst.u.runstate.time_blocked = + 0x5a - rs->time[RUNSTATE_blocked]; + rst.u.runstate.time_offline = + 0x6b6b - rs->time[RUNSTATE_offline]; + rst.u.runstate.time_runnable = -rst.u.runstate.time_blocked - + rst.u.runstate.time_offline; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + break; + + case 5: + rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; + memset(&rst.u, 0, sizeof(rst.u)); + rst.u.runstate.state = RUNSTATE_running; + rst.u.runstate.state_entry_time = 0x6b6b + 0x5a; + rst.u.runstate.time_blocked = 0x6b6b; + rst.u.runstate.time_offline = 0x5a; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); + break; + case 6: + /* Yield until scheduler delay exceeds target */ + rundelay = get_run_delay() + MIN_STEAL_TIME; + do { + sched_yield(); + } while (get_run_delay() < rundelay); + break; + } break; + } case UCALL_DONE: goto done; default: @@ -162,6 +288,33 @@ int main(int argc, char *argv[]) TEST_ASSERT(ti2->version && !(ti2->version & 1), "Bad time_info version %x", ti->version); + if (do_runstate_tests) { + /* + * Fetch runstate and check sanity. Strictly speaking in the + * general case we might not expect the numbers to be identical + * but in this case we know we aren't running the vCPU any more. + */ + struct kvm_xen_vcpu_attr rst = { + .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA, + }; + vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + + TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); + TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, + "State entry time mismatch"); + TEST_ASSERT(rs->time[RUNSTATE_running] == rst.u.runstate.time_running, + "Running time mismatch"); + TEST_ASSERT(rs->time[RUNSTATE_runnable] == rst.u.runstate.time_runnable, + "Runnable time mismatch"); + TEST_ASSERT(rs->time[RUNSTATE_blocked] == rst.u.runstate.time_blocked, + "Blocked time mismatch"); + TEST_ASSERT(rs->time[RUNSTATE_offline] == rst.u.runstate.time_offline, + "Offline time mismatch"); + + TEST_ASSERT(rs->state_entry_time == rs->time[0] + + rs->time[1] + rs->time[2] + rs->time[3], + "runstate times don't add up"); + } kvm_vm_free(vm); return 0; } -- cgit v1.2.3