From 7889968e64754149f9c84a6ebcafee7db856d8dc Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 9 Jan 2024 22:02:17 +0800 Subject: gpio: uapi: improve description of fd fields Only a successful operation modifies fd fields, but the current documentation wording could be taken to imply that a positive fd value after an ioctl() returns indicates a success. Reword documentation to clarify that the fd is only valid after a successful operation. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index cb9966d49a16..650c1099d1a6 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -189,9 +189,8 @@ struct gpio_v2_line_config { * buffer. If this field is zero then the buffer size defaults to a minimum * of @num_lines * 16. * @padding: reserved for future use and must be zero filled - * @fd: if successful this field will contain a valid anonymous file handle - * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means - * error + * @fd: after a successful %GPIO_V2_GET_LINE_IOCTL operation, contains + * a valid anonymous file descriptor representing the request */ struct gpio_v2_line_request { __u32 offsets[GPIO_V2_LINES_MAX]; @@ -402,9 +401,8 @@ struct gpioline_info_changed { * such as "my-bitbanged-relay" * @lines: number of lines requested in this request, i.e. the number of * valid fields in the above arrays, set to 1 to request a single line - * @fd: if successful this field will contain a valid anonymous file handle - * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value - * means error + * @fd: after a successful %GPIO_GET_LINEHANDLE_IOCTL operation, contains + * a valid anonymous file descriptor representing the request * * Note: This struct is part of ABI v1 and is deprecated. * Use &struct gpio_v2_line_request instead. @@ -465,9 +463,8 @@ struct gpiohandle_data { * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE * @consumer_label: a desired consumer label for the selected GPIO line(s) * such as "my-listener" - * @fd: if successful this field will contain a valid anonymous file handle - * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value - * means error + * @fd: after a successful %GPIO_GET_LINEEVENT_IOCTL operation, contains a + * valid anonymous file descriptor representing the request * * Note: This struct is part of ABI v1 and is deprecated. * Use &struct gpio_v2_line_request instead. -- cgit v1.2.3 From f75d508eeb24de5462c77835229f61d700914db0 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 9 Jan 2024 22:02:18 +0800 Subject: gpio: uapi: clarify hte references The full name of the HTE subsystem is "hardware timestamping engine", so correct references and highlight that this refers to the HTE subsystem. Extend the description of struct gpio_v2_line_event to clarify that the timestamp_ns is sourced from the HTE if the GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE is set. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 650c1099d1a6..88c2a326940e 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -67,7 +67,7 @@ struct gpiochip_info { * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME: line events contain REALTIME timestamps * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE: line events contain timestamps from - * hardware timestamp engine + * the hardware timestamping engine (HTE) subsystem */ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_USED = _BITULL(0), @@ -288,6 +288,10 @@ enum gpio_v2_line_event_id { * * If the %GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME flag is set then the * @timestamp_ns is read from %CLOCK_REALTIME. + * + * If the %GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE flag is set then the + * @timestamp_ns is provided by the hardware timestamping engine (HTE) + * subsystem. */ struct gpio_v2_line_event { __aligned_u64 timestamp_ns; -- cgit v1.2.3 From a6beb0b46121d9667208f367d99ca17b9daf7a0c Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 9 Jan 2024 22:02:19 +0800 Subject: gpio: uapi: drop trailing period from one sentence descriptions Make documentation more consistent by using trailing periods only for multi-sentence field descriptions, not single sentence descriptions. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 88c2a326940e..3ba8996e496c 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -88,10 +88,10 @@ enum gpio_v2_line_flag { /** * struct gpio_v2_line_values - Values of GPIO lines * @bits: a bitmap containing the value of the lines, set to 1 for active - * and 0 for inactive. + * and 0 for inactive * @mask: a bitmap identifying the lines to get or set, with each bit * number corresponding to the index into &struct - * gpio_v2_line_request.offsets. + * gpio_v2_line_request.offsets */ struct gpio_v2_line_values { __aligned_u64 bits; @@ -123,7 +123,7 @@ enum gpio_v2_line_attr_id { * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap * containing the values to which the lines will be set, with each bit * number corresponding to the index into &struct - * gpio_v2_line_request.offsets. + * gpio_v2_line_request.offsets * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the * desired debounce period, in microseconds */ @@ -143,7 +143,7 @@ struct gpio_v2_line_attribute { * @attr: the configurable attribute * @mask: a bitmap identifying the lines to which the attribute applies, * with each bit number corresponding to the index into &struct - * gpio_v2_line_request.offsets. + * gpio_v2_line_request.offsets */ struct gpio_v2_line_config_attribute { struct gpio_v2_line_attribute attr; @@ -178,7 +178,7 @@ struct gpio_v2_line_config { * associated GPIO chip * @consumer: a desired consumer label for the selected GPIO lines such as * "my-bitbanged-relay" - * @config: requested configuration for the lines. + * @config: requested configuration for the lines * @num_lines: number of lines requested in this request, i.e. the number * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to * request a single line @@ -216,7 +216,7 @@ struct gpio_v2_line_request { * @num_attrs: the number of attributes in @attrs * @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. + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together * @attrs: the configuration attributes associated with the line * @padding: reserved for future use */ @@ -273,7 +273,7 @@ enum gpio_v2_line_event_id { /** * struct gpio_v2_line_event - The actual event being pushed to userspace - * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. + * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds * @id: event identifier with value from &enum gpio_v2_line_event_id * @offset: the offset of the line that triggered the event * @seqno: the sequence number for this event in the sequence of events for -- cgit v1.2.3 From ead7c5817cff33aff2762b43caec6bc5b8dfff9a Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 9 Jan 2024 22:02:20 +0800 Subject: gpio: uapi: document possible values of gpioevent_data.id Clarify the possible values of event id, rather than requiring the reader to infer. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 3ba8996e496c..e68a56969f36 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -490,7 +490,8 @@ struct gpioevent_request { /** * struct gpioevent_data - The actual event being pushed to userspace * @timestamp: best estimate of time of event occurrence, in nanoseconds - * @id: event identifier + * @id: event identifier, one of %GPIOEVENT_EVENT_RISING_EDGE or + * %GPIOEVENT_EVENT_FALLING_EDGE * * Note: This struct is part of ABI v1 and is deprecated. * Use &struct gpio_v2_line_event instead. -- cgit v1.2.3 From b6747ef69fa44717f7ee6bbf012324bfdbdb5aa4 Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Tue, 9 Jan 2024 22:02:21 +0800 Subject: gpio: uapi: clarify using v2 rather than v1 The documentation contains notes like This struct is part of ABI v1 and is deprecated. Use struct gpio_v2_line_info instead. This could be interpreted to mean the structs can be directly substituted in v1 calls. Clarify that the user should use the corresponding v2 ioctl() and structs. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index e68a56969f36..103cd3c6c81e 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -333,7 +333,7 @@ struct gpio_v2_line_event { * also be empty if the consumer doesn't set this up * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_info instead. + * Use ABI v2 and &struct gpio_v2_line_info instead. */ struct gpioline_info { __u32 line_offset; @@ -368,7 +368,7 @@ enum { * at the end of the structure on 64-bit architectures. * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_info_changed instead. + * Use ABI v2 and &struct gpio_v2_line_info_changed instead. */ struct gpioline_info_changed { struct gpioline_info info; @@ -409,7 +409,7 @@ struct gpioline_info_changed { * a valid anonymous file descriptor representing the request * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_request instead. + * Use ABI v2 and &struct gpio_v2_line_request instead. */ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; @@ -431,7 +431,7 @@ struct gpiohandle_request { * @padding: reserved for future use and should be zero filled * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_config instead. + * Use ABI v2 and &struct gpio_v2_line_config instead. */ struct gpiohandle_config { __u32 flags; @@ -446,7 +446,7 @@ struct gpiohandle_config { * the desired target state * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_values instead. + * Use ABI v2 and &struct gpio_v2_line_values instead. */ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; @@ -471,7 +471,7 @@ struct gpiohandle_data { * valid anonymous file descriptor representing the request * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_request instead. + * Use ABI v2 and &struct gpio_v2_line_request instead. */ struct gpioevent_request { __u32 lineoffset; @@ -494,7 +494,7 @@ struct gpioevent_request { * %GPIOEVENT_EVENT_FALLING_EDGE * * Note: This struct is part of ABI v1 and is deprecated. - * Use &struct gpio_v2_line_event instead. + * Use ABI v2 and &struct gpio_v2_line_event instead. */ struct gpioevent_data { __u64 timestamp; -- cgit v1.2.3 From 73fa7547c70b32cc69685f79be31135797734eb6 Mon Sep 17 00:00:00 2001 From: Rich Felker Date: Mon, 31 Aug 2020 11:32:08 -0400 Subject: vfs: add RWF_NOAPPEND flag for pwritev2 The pwrite function, originally defined by POSIX (thus the "p"), is defined to ignore O_APPEND and write at the offset passed as its argument. However, historically Linux honored O_APPEND if set and ignored the offset. This cannot be changed due to stability policy, but is documented in the man page as a bug. Now that there's a pwritev2 syscall providing a superset of the pwrite functionality that has a flags argument, the conforming behavior can be offered to userspace via a new flag. Since pwritev2 checks flag validity (in kiocb_set_rw_flags) and reports unknown ones with EOPNOTSUPP, callers will not get wrong behavior on old kernels that don't support the new flag; the error is reported and the caller can decide how to handle it. Signed-off-by: Rich Felker Link: https://lore.kernel.org/r/20200831153207.GO3265@brightrain.aerifal.cx Reviewed-by: Jann Horn Signed-off-by: Christian Brauner --- include/linux/fs.h | 8 ++++++++ include/uapi/linux/fs.h | 5 ++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..4f7cfda29143 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3335,6 +3335,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; + if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) + return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) @@ -3345,6 +3347,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; + if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { + if (IS_APPEND(file_inode(ki->ki_filp))) + return -EPERM; + ki->ki_flags &= ~IOCB_APPEND; + } + ki->ki_flags |= kiocb_flags; return 0; } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 48ad69f7722e..2203d3194b91 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -301,9 +301,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_NOAPPEND) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) -- cgit v1.2.3 From 1dccdba084897443d116508a8ed71e0ac8a031a4 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Tue, 21 Nov 2023 07:32:59 +0100 Subject: drm/etnaviv: Expose a few more chipspecs to userspace These ones will be needed to make use fo the NN and TP units in the NPUs based on Vivante IP. Also fix the number of NN cores in the VIPNano-qi. Signed-off-by: Tomeu Vizoso Acked-by: Christian Gmeiner Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 20 ++++++++++++++++++++ drivers/gpu/drm/etnaviv/etnaviv_gpu.h | 12 ++++++++++++ drivers/gpu/drm/etnaviv/etnaviv_hwdb.c | 34 ++++++++++++++++++++++++++++++++++ include/uapi/drm/etnaviv_drm.h | 5 +++++ 4 files changed, 71 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 1dcfa23db3be..18725ff5c79b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -164,6 +164,26 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.eco_id; break; + case ETNAVIV_PARAM_GPU_NN_CORE_COUNT: + *value = gpu->identity.nn_core_count; + break; + + case ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE: + *value = gpu->identity.nn_mad_per_core; + break; + + case ETNAVIV_PARAM_GPU_TP_CORE_COUNT: + *value = gpu->identity.tp_core_count; + break; + + case ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE: + *value = gpu->identity.on_chip_sram_size; + break; + + case ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE: + *value = gpu->identity.axi_sram_size; + break; + default: DBG("%s: invalid param: %u", dev_name(gpu->dev), param); return -EINVAL; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 197e0037732e..7d5e9158e13c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -54,6 +54,18 @@ struct etnaviv_chip_identity { /* Number of Neural Network cores. */ u32 nn_core_count; + /* Number of MAD units per Neural Network core. */ + u32 nn_mad_per_core; + + /* Number of Tensor Processing cores. */ + u32 tp_core_count; + + /* Size in bytes of the SRAM inside the NPU. */ + u32 on_chip_sram_size; + + /* Size in bytes of the SRAM across the AXI bus. */ + u32 axi_sram_size; + /* Size of the vertex cache. */ u32 vertex_cache_size; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index 67201242438b..9eb8ca7c5034 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -17,6 +17,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 128, .shader_core_count = 1, .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -48,6 +52,11 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 256, .shader_core_count = 1, + .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 512, .pixel_pipes = 1, @@ -80,6 +89,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -112,6 +125,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -143,6 +160,11 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 512, .shader_core_count = 2, + .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -175,6 +197,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 1024, .shader_core_count = 4, .nn_core_count = 0, + .nn_mad_per_core = 0, + .tp_core_count = 0, + .on_chip_sram_size = 0, + .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 2, @@ -207,6 +233,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 8, + .nn_mad_per_core = 64, + .tp_core_count = 4, + .on_chip_sram_size = 524288, + .axi_sram_size = 1048576, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -239,6 +269,10 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 6, + .nn_mad_per_core = 64, + .tp_core_count = 3, + .on_chip_sram_size = 262144, + .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index af024d90453d..d87410a8443a 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -77,6 +77,11 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_PRODUCT_ID 0x1c #define ETNAVIV_PARAM_GPU_CUSTOMER_ID 0x1d #define ETNAVIV_PARAM_GPU_ECO_ID 0x1e +#define ETNAVIV_PARAM_GPU_NN_CORE_COUNT 0x1f +#define ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE 0x20 +#define ETNAVIV_PARAM_GPU_TP_CORE_COUNT 0x21 +#define ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE 0x22 +#define ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE 0x23 #define ETNA_MAX_PIPES 4 -- cgit v1.2.3 From f98df79bf7f772597313adca2720cb38770490dd Mon Sep 17 00:00:00 2001 From: Victor Stewart Date: Tue, 16 Jan 2024 20:29:52 +0000 Subject: bpf, docs: Fix bpf_redirect_peer header doc Amend the bpf_redirect_peer() header documentation to also mention support for the netkit device type. Signed-off-by: Victor Stewart Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240116202952.241009-1-v@nametag.social Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 754e68ca8744..a00f8a5623e1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4839,9 +4839,9 @@ union bpf_attr { * going through the CPU's backlog queue. * * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types at the ingress - * hook and for veth device types. The peer device must reside in a - * different network namespace. + * currently only supported for tc BPF program types at the + * ingress hook and for veth and netkit target device types. The + * peer device must reside in a different network namespace. * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. -- cgit v1.2.3 From d5c16492c66fbfca85f36e42363d32212df5927b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 19 Jan 2024 12:04:58 +0100 Subject: bpf: Add cookie to perf_event bpf_link_info records At the moment we don't store cookie for perf_event probes, while we do that for the rest of the probes. Adding cookie fields to struct bpf_link_info perf event probe records: perf_event.uprobe perf_event.kprobe perf_event.tracepoint perf_event.perf_event And the code to store that in bpf_link_info struct. Signed-off-by: Jiri Olsa Acked-by: Song Liu Acked-by: Yafang Shao Link: https://lore.kernel.org/r/20240119110505.400573-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 6 ++++++ kernel/bpf/syscall.c | 4 ++++ tools/include/uapi/linux/bpf.h | 6 ++++++ 3 files changed, 16 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a00f8a5623e1..181e74433272 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6582,6 +6582,7 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ @@ -6589,14 +6590,19 @@ struct bpf_link_info { __u32 offset; /* offset from func_name */ __u64 addr; __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1f18681721c..13193aaafb64 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3501,6 +3501,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; + info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3526,6 +3527,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.offset = offset; + info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3553,6 +3555,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; + info->perf_event.tracepoint.cookie = event->bpf_cookie; return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); } @@ -3561,6 +3564,7 @@ static int bpf_perf_link_fill_perf_event(const struct perf_event *event, { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; + info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a00f8a5623e1..181e74433272 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6582,6 +6582,7 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ @@ -6589,14 +6590,19 @@ struct bpf_link_info { __u32 offset; /* offset from func_name */ __u64 addr; __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; -- cgit v1.2.3 From 9fd112b1f82b587ffb12fb67dd032f551fdb571a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 19 Jan 2024 12:04:59 +0100 Subject: bpf: Store cookies in kprobe_multi bpf_link_info data Storing cookies in kprobe_multi bpf_link_info data. The cookies field is optional and if provided it needs to be an array of __u64 with kprobe_multi.count length. Acked-by: Yafang Shao Signed-off-by: Jiri Olsa Acked-by: Song Liu Link: https://lore.kernel.org/r/20240119110505.400573-3-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/trace/bpf_trace.c | 15 +++++++++++++++ tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 181e74433272..287d05732668 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6563,6 +6563,7 @@ struct bpf_link_info { __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; __u64 missed; + __aligned_u64 cookies; } kprobe_multi; struct { __aligned_u64 path; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7ac6c52b25eb..c98c20abaf99 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2679,6 +2679,7 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { + u64 __user *ucookies = u64_to_user_ptr(info->kprobe_multi.cookies); u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs); struct bpf_kprobe_multi_link *kmulti_link; u32 ucount = info->kprobe_multi.count; @@ -2686,6 +2687,8 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, if (!uaddrs ^ !ucount) return -EINVAL; + if (ucookies && !ucount) + return -EINVAL; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); info->kprobe_multi.count = kmulti_link->cnt; @@ -2699,6 +2702,18 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, else ucount = kmulti_link->cnt; + if (ucookies) { + if (kmulti_link->cookies) { + if (copy_to_user(ucookies, kmulti_link->cookies, ucount * sizeof(u64))) + return -EFAULT; + } else { + for (i = 0; i < ucount; i++) { + if (put_user(0, ucookies + i)) + return -EFAULT; + } + } + } + if (kallsyms_show_value(current_cred())) { if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64))) return -EFAULT; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 181e74433272..287d05732668 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6563,6 +6563,7 @@ struct bpf_link_info { __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; __u64 missed; + __aligned_u64 cookies; } kprobe_multi; struct { __aligned_u64 path; -- cgit v1.2.3 From 1338b93346587a2a6ac79bbcf55ef5b357745573 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:57 -0800 Subject: bpf: pass btf object id in bpf_map_info. Include btf object id (btf_obj_id) in bpf_map_info so that tools (ex: bpftools struct_ops dump) know the correct btf from the kernel to look up type information of struct_ops types. Since struct_ops types can be defined and registered in a module. The type information of a struct_ops type are defined in the btf of the module defining it. The userspace tools need to know which btf is for the module defining a struct_ops type. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-7-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 ++++ include/uapi/linux/bpf.h | 2 +- kernel/bpf/bpf_struct_ops.c | 7 +++++++ kernel/bpf/syscall.c | 2 ++ tools/include/uapi/linux/bpf.h | 2 +- 5 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7fc95e7babab..29fcae9fa8ed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1732,6 +1732,7 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { @@ -1759,6 +1760,9 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ +} #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5ddcca4c4fba..5e98af4fc2e2 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -947,3 +947,10 @@ err_out: kfree(link); return err; } + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 13193aaafb64..55b458429705 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4691,6 +4691,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From fcc2c1fb0651477c8ed78a3a293c175ccd70697a Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:59 -0800 Subject: bpf: pass attached BTF to the bpf_struct_ops subsystem Pass the fd of a btf from the userspace to the bpf() syscall, and then convert the fd into a btf. The btf is generated from the module that defines the target BPF struct_ops type. In order to inform the kernel about the module that defines the target struct_ops type, the userspace program needs to provide a btf fd for the respective module's btf. This btf contains essential information on the types defined within the module, including the target struct_ops type. A btf fd must be provided to the kernel for struct_ops maps and for the bpf programs attached to those maps. In the case of the bpf programs, the attach_btf_obj_fd parameter is passed as part of the bpf_attr and is converted into a btf. This btf is then stored in the prog->aux->attach_btf field. Here, it just let the verifier access attach_btf directly. In the case of struct_ops maps, a btf fd is passed as value_type_btf_obj_fd of bpf_attr. The bpf_struct_ops_map_alloc() function converts the fd to a btf and stores it as st_map->btf. A flag BPF_F_VTYPE_BTF_OBJ_FD is added for map_flags to indicate that the value of value_type_btf_obj_fd is set. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-9-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 8 ++++++ kernel/bpf/bpf_struct_ops.c | 65 ++++++++++++++++++++++++++++++------------ kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 9 ++++-- tools/include/uapi/linux/bpf.h | 8 ++++++ 5 files changed, 70 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a380047c86af..1fef6d5a1330 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1330,6 +1330,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1406,11 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 7505f515aac3..3b8d689ece5d 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -641,6 +641,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) bpf_jit_uncharge_modmem(PAGE_SIZE); } bpf_map_area_free(st_map->uvalue); + btf_put(st_map->btf); bpf_map_area_free(st_map); } @@ -669,7 +670,8 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) || + !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } @@ -681,15 +683,36 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; struct bpf_map *map; + struct btf *btf; int ret; - st_ops_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id); - if (!st_ops_desc) - return ERR_PTR(-ENOTSUPP); + if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) { + /* The map holds btf for its whole life time. */ + btf = btf_get_by_fd(attr->value_type_btf_obj_fd); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf_is_module(btf)) { + btf_put(btf); + return ERR_PTR(-EINVAL); + } + } else { + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return ERR_CAST(btf); + btf_get(btf); + } + + st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) { + ret = -ENOTSUPP; + goto errout; + } vt = st_ops_desc->value_type; - if (attr->value_size != vt->size) - return ERR_PTR(-EINVAL); + if (attr->value_size != vt->size) { + ret = -EINVAL; + goto errout; + } t = st_ops_desc->type; @@ -700,17 +723,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) (vt->size - sizeof(struct bpf_struct_ops_value)); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) - return ERR_PTR(-ENOMEM); + if (!st_map) { + ret = -ENOMEM; + goto errout; + } st_map->st_ops_desc = st_ops_desc; map = &st_map->map; ret = bpf_jit_charge_modmem(PAGE_SIZE); - if (ret) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(ret); - } + if (ret) + goto errout_free; st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); if (!st_map->image) { @@ -719,24 +742,30 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) * here. */ bpf_jit_uncharge_modmem(PAGE_SIZE); - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto errout_free; } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); st_map->links = bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), NUMA_NO_NODE); if (!st_map->uvalue || !st_map->links) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto errout_free; } - - st_map->btf = btf_vmlinux; + st_map->btf = btf; mutex_init(&st_map->lock); bpf_map_init_from_attr(map, attr); return map; + +errout_free: + __bpf_struct_ops_map_free(map); +errout: + btf_put(btf); + + return ERR_PTR(ret); } static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 55b458429705..f8124b3229e2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1123,7 +1123,7 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2a0fd2ccdb11..6081512deb79 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20290,6 +20290,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; + struct btf *btf; const char *mname; if (!prog->gpl_compatible) { @@ -20297,8 +20298,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux(); + btf_id = prog->aux->attach_btf_id; - st_ops_desc = bpf_struct_ops_find(btf_vmlinux, btf_id); + st_ops_desc = bpf_struct_ops_find(btf, btf_id); if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); @@ -20315,8 +20318,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } member = &btf_type_member(t)[member_idx]; - mname = btf_name_by_offset(btf_vmlinux, member->name_off); - func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + mname = btf_name_by_offset(btf, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a380047c86af..1fef6d5a1330 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1330,6 +1330,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1406,11 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ -- cgit v1.2.3 From 35f96de04127d332a5c5e8a155d31f452f88c76d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:00 -0800 Subject: bpf: Introduce BPF token object Add new kind of BPF kernel object, BPF token. BPF token is meant to allow delegating privileged BPF functionality, like loading a BPF program or creating a BPF map, from privileged process to a *trusted* unprivileged process, all while having a good amount of control over which privileged operations could be performed using provided BPF token. This is achieved through mounting BPF FS instance with extra delegation mount options, which determine what operations are delegatable, and also constraining it to the owning user namespace (as mentioned in the previous patch). BPF token itself is just a derivative from BPF FS and can be created through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF FS FD, which can be attained through open() API by opening BPF FS mount point. Currently, BPF token "inherits" delegated command, map types, prog type, and attach type bit sets from BPF FS as is. In the future, having an BPF token as a separate object with its own FD, we can allow to further restrict BPF token's allowable set of things either at the creation time or after the fact, allowing the process to guard itself further from unintentionally trying to load undesired kind of BPF programs. But for now we keep things simple and just copy bit sets as is. When BPF token is created from BPF FS mount, we take reference to the BPF super block's owning user namespace, and then use that namespace for checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN} capabilities that are normally only checked against init userns (using capable()), but now we check them using ns_capable() instead (if BPF token is provided). See bpf_token_capable() for details. Such setup means that BPF token in itself is not sufficient to grant BPF functionality. User namespaced process has to *also* have necessary combination of capabilities inside that user namespace. So while previously CAP_BPF was useless when granted within user namespace, now it gains a meaning and allows container managers and sys admins to have a flexible control over which processes can and need to use BPF functionality within the user namespace (i.e., container in practice). And BPF FS delegation mount options and derived BPF tokens serve as a per-container "flag" to grant overall ability to use bpf() (plus further restrict on which parts of bpf() syscalls are treated as namespaced). Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF) within the BPF FS owning user namespace, rounding up the ns_capable() story of BPF token. Also creating BPF token in init user namespace is currently not supported, given BPF token doesn't have any effect in init user namespace anyways. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Christian Brauner Link: https://lore.kernel.org/bpf/20240124022127.2379740-4-andrii@kernel.org --- include/linux/bpf.h | 41 ++++++++ include/uapi/linux/bpf.h | 37 +++++++ kernel/bpf/Makefile | 2 +- kernel/bpf/inode.c | 12 ++- kernel/bpf/syscall.c | 17 ++++ kernel/bpf/token.c | 217 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 37 +++++++ 7 files changed, 357 insertions(+), 6 deletions(-) create mode 100644 kernel/bpf/token.c (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 28374cec49df..d9ff7ce547b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -52,6 +52,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1621,6 +1625,13 @@ struct bpf_mount_opts { u64 delegate_attachs; }; +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; +}; + struct bpf_struct_ops_value; struct btf_member; @@ -2109,6 +2120,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2243,6 +2255,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; +bool bpf_token_capable(const struct bpf_token *token, int cap); + static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); @@ -2277,8 +2291,17 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2638,6 +2661,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 70b748f6228c..565be1f3f1ea 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -99,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -603,6 +603,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + u64 mask; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -613,7 +614,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); - if (opts->delegate_cmds == ~0ULL) + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((opts->delegate_cmds & mask) == mask) seq_printf(m, ",delegate_cmds=any"); else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); @@ -646,7 +648,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d5f1edee2d50..3ecba592b8ed 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5426,6 +5426,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5559,6 +5573,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..bdb6fe697568 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,217 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool bpf_ns_capable(struct user_namespace *ns, int cap) +{ + return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); +} + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + struct user_namespace *userns; + + /* BPF token allows ns_capable() level of capabilities */ + userns = token ? token->userns : &init_user_ns; + if (!bpf_ns_capable(userns, cap)) + return false; + return true; +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + put_user_ns(token->userns); + kfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + /* Creating BPF token in init_user_ns doesn't make much sense. */ + if (current_user_ns() == &init_user_ns) { + err = -EOPNOTSUPP; + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + mnt_opts = path.dentry->d_sb->s_fs_info; + token->allowed_cmds = mnt_opts->delegate_cmds; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + if (!token) + return false; + return token->allowed_cmds & (1ULL << cmd); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From a177fc2bf6fd83704854feaf7aae926b1df4f0b9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:01 -0800 Subject: bpf: Add BPF token support to BPF_MAP_CREATE command Allow providing token_fd for BPF_MAP_CREATE command to allow controlled BPF map creation from unprivileged process through delegated BPF token. New BPF_F_TOKEN_FD flag is added to specify together with BPF token FD for BPF_MAP_CREATE command. Wire through a set of allowed BPF map types to BPF token, derived from BPF FS at BPF token creation time. This, in combination with allowed_cmds allows to create a narrowly-focused BPF token (controlled by privileged agent) with a restrictive set of BPF maps that application can attempt to create. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-5-andrii@kernel.org --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 8 +++ kernel/bpf/inode.c | 3 +- kernel/bpf/syscall.c | 59 +++++++++++++++++----- kernel/bpf/token.c | 16 ++++++ tools/include/uapi/linux/bpf.h | 8 +++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 ++ 8 files changed, 86 insertions(+), 15 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d9ff7ce547b4..8252452d0c4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1630,6 +1630,7 @@ struct bpf_token { atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; + u64 allowed_maps; }; struct bpf_struct_ops_value; @@ -2297,6 +2298,7 @@ int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 565be1f3f1ea..034b7e4d8f19 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -620,7 +620,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); - if (opts->delegate_maps == ~0ULL) + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((opts->delegate_maps & mask) == mask) seq_printf(m, ",delegate_maps=any"); else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3ecba592b8ed..b13a4bdcd3a0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1128,14 +1128,16 @@ static bool bpf_net_capable(void) return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } -#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -1143,6 +1145,12 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it + * to avoid per-map type checks tripping on unknown flag + */ + token_flag = attr->map_flags & BPF_F_TOKEN_FD; + attr->map_flags &= ~BPF_F_TOKEN_FD; + if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) @@ -1183,14 +1191,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (token_flag) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1223,25 +1249,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!bpf_net_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1278,7 +1306,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1299,6 +1327,7 @@ static int map_create(union bpf_attr *attr) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1319,6 +1348,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bdb6fe697568..bc86be4ca567 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -73,6 +73,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -168,6 +175,7 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -215,3 +223,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) return false; return token->allowed_cmds & (1ULL << cmd); } + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..573249a2814d 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index eb34d612d6f8..1f328c0d8aff 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); -- cgit v1.2.3 From 9ea7c4bf17e39d463eb4782f948f401d9764b1b3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:02 -0800 Subject: bpf: Add BPF token support to BPF_BTF_LOAD command Accept BPF token FD in BPF_BTF_LOAD command to allow BTF data loading through delegated BPF token. BPF_F_TOKEN_FD flag has to be specified when passing BPF token FD. Given BPF_BTF_LOAD command didn't have flags field before, we also add btf_flags field. BTF loading is a pretty straightforward operation, so as long as BPF token is created with allow_cmds granting BPF_BTF_LOAD command, kernel proceeds to parsing BTF data and creating BTF object. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-6-andrii@kernel.org --- include/uapi/linux/bpf.h | 5 +++++ kernel/bpf/syscall.c | 23 +++++++++++++++++++++-- tools/include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 31 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c78cab8b462d..cb2c888e3bb4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1632,6 +1632,11 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_flags; + /* BPF token FD to use with BPF_BTF_LOAD operation. + * If provided, btf_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 btf_token_fd; }; struct { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b13a4bdcd3a0..45b3a55896eb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4831,15 +4831,34 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->btf_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c78cab8b462d..cb2c888e3bb4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1632,6 +1632,11 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_flags; + /* BPF token FD to use with BPF_BTF_LOAD operation. + * If provided, btf_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 btf_token_fd; }; struct { -- cgit v1.2.3 From caf8f28e036c4ba1e823355da6c0c01c39e70ab9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:03 -0800 Subject: bpf: Add BPF token support to BPF_PROG_LOAD command Add basic support of BPF token to BPF_PROG_LOAD. BPF_F_TOKEN_FD flag should be set in prog_flags field when providing prog_token_fd. Wire through a set of allowed BPF program types and attach types, derived from BPF FS at BPF token creation time. Then make sure we perform bpf_token_capable() checks everywhere where it's relevant. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-7-andrii@kernel.org --- include/linux/bpf.h | 6 ++ include/uapi/linux/bpf.h | 5 ++ kernel/bpf/core.c | 1 + kernel/bpf/inode.c | 6 +- kernel/bpf/syscall.c | 90 ++++++++++++++++------ kernel/bpf/token.c | 27 +++++++ tools/include/uapi/linux/bpf.h | 5 ++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 + 9 files changed, 118 insertions(+), 27 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8252452d0c4d..d0bf37e3f166 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1489,6 +1489,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1631,6 +1632,8 @@ struct bpf_token { struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; }; struct bpf_struct_ops_value; @@ -2299,6 +2302,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fbb1d95a9b44..00dccba29769 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2779,6 +2779,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 034b7e4d8f19..5fb10da5717f 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -626,12 +626,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); - if (opts->delegate_progs == ~0ULL) + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) seq_printf(m, ",delegate_progs=any"); else if (opts->delegate_progs) seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); - if (opts->delegate_attachs == ~0ULL) + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) seq_printf(m, ",delegate_attachs=any"); else if (opts->delegate_attachs) seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45b3a55896eb..61b4bf4cc287 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2626,13 +2626,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2646,13 +2648,35 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | - BPF_F_TEST_REG_INVARIANTS)) + BPF_F_TEST_REG_INVARIANTS | + BPF_F_TOKEN_FD)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2661,21 +2685,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !bpf_net_capable()) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2685,27 +2711,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2713,7 +2745,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2723,7 +2756,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2734,6 +2768,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; @@ -2851,6 +2889,8 @@ free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3858,7 +3898,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_net_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bc86be4ca567..c13c73788d8c 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -80,6 +80,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -176,6 +190,8 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -231,3 +247,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t return token->allowed_maps & (1ULL << type); } + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 573249a2814d..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 1f328c0d8aff..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); -- cgit v1.2.3 From 2518e89d5b1913c360f8e4cd9fc6eda6146b8800 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 2 Jan 2024 21:35:39 +0200 Subject: wifi: cfg80211: add support for SPP A-MSDUs Add SPP (signaling and payload protected) AMSDU support. Since userspace has to build the RSNX element, add an extended feature flag to indicate that this is supported. In order to avoid downgrade/mismatch attacks, add a flag to the assoc command on the station side, so that we can be sure that the value of the flag comes from the same RSNX element that will be validated by the supplicant against the 4-way-handshake. If we just pulled the data out of a beacon/probe response, we could theoretically look an RSNX element from a different frame, with a different value for this flag, than the supplicant is using to validate in the 4-way-handshake. Note that this patch is only geared towards software crypto implementations or hardware ones that can perfectly implement SPP A-MSDUs, i.e. are able to switch the AAD construction on the fly for each TX/RX frame. For more limited hardware implementations, more capability advertisement would be required, e.g. if the hardware has no way to switch this on the fly but has only a global configuration that must apply to all stations. The driver could of course *reject* mismatches, but the supplicant must know so it can do things like not negotiating SPP A-MSDUs on a T-DLS link when connected to an AP that doesn't support it, or similar. Signed-off-by: Johannes Berg Signed-off-by: Daniel Gabay Reviewed-by: Gregory Greenman Signed-off-by: Miri Korenblit Link: https://msgid.link/20240102213313.fadac8df7030.I9240aebcba1be49636a73c647ed0af862713fc6f@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 14 ++++++++++++++ net/wireless/nl80211.c | 24 +++++++++++++++++++++--- 3 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cf79656ce09c..56bce924bec6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3059,6 +3059,7 @@ struct cfg80211_assoc_link { * @CONNECT_REQ_MLO_SUPPORT: Userspace indicates support for handling MLD links. * Drivers shall disable MLO features for the current association if this * flag is not set. + * @ASSOC_REQ_SPP_AMSDU: SPP A-MSDUs will be used on this connection (if any) */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -3068,6 +3069,7 @@ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HE = BIT(4), ASSOC_REQ_DISABLE_EHT = BIT(5), CONNECT_REQ_MLO_SUPPORT = BIT(6), + ASSOC_REQ_SPP_AMSDU = BIT(7), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1ccdcae24372..3e239df3528f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2851,6 +2851,10 @@ enum nl80211_commands { * mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element) * in Draft P802.11be_D4.0. * + * @NL80211_ATTR_ASSOC_SPP_AMSDU: flag attribute used with + * %NL80211_CMD_ASSOCIATE indicating the SPP A-MSDUs + * are used on this connection + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3394,6 +3398,8 @@ enum nl80211_attrs { NL80211_ATTR_MLO_TTLM_DLINK, NL80211_ATTR_MLO_TTLM_ULINK, + NL80211_ATTR_ASSOC_SPP_AMSDU, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3534,6 +3540,7 @@ enum nl80211_iftype { * @NL80211_STA_FLAG_ASSOCIATED: station is associated; used with drivers * that support %NL80211_FEATURE_FULL_AP_CLIENT_STATE to transition a * previously added station into associated state + * @NL80211_STA_FLAG_SPP_AMSDU: station supports SPP A-MSDUs * @NL80211_STA_FLAG_MAX: highest station flag number currently defined * @__NL80211_STA_FLAG_AFTER_LAST: internal use */ @@ -3546,6 +3553,7 @@ enum nl80211_sta_flags { NL80211_STA_FLAG_AUTHENTICATED, NL80211_STA_FLAG_TDLS_PEER, NL80211_STA_FLAG_ASSOCIATED, + NL80211_STA_FLAG_SPP_AMSDU, /* keep last */ __NL80211_STA_FLAG_AFTER_LAST, @@ -6520,6 +6528,11 @@ enum nl80211_feature_flags { * DFS master on the same channel as described in FCC-594280 D01 * (Section B.3). This, for example, allows P2P GO and P2P clients to * operate on DFS channels as long as there's a concurrent BSS connection. + * + * @NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT: The driver has support for SPP + * (signaling and payload protected) A-MSDUs and this shall be advertised + * in the RSNXE. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6594,6 +6607,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_OWE_OFFLOAD, NL80211_EXT_FEATURE_OWE_OFFLOAD_AP, NL80211_EXT_FEATURE_DFS_CONCURRENT, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b09700400d09..b267317aa33c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -821,6 +821,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG }, [NL80211_ATTR_MLO_TTLM_DLINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), [NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), + [NL80211_ATTR_ASSOC_SPP_AMSDU] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -6874,7 +6875,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; /* When you run into this, adjust the code below for the new flag */ - BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); + BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 8); switch (statype) { case CFG80211_STA_MESH_PEER_KERNEL: @@ -6934,6 +6935,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, params->link_sta_params.he_capa || params->link_sta_params.eht_capa) return -EINVAL; + if (params->sta_flags_mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) + return -EINVAL; } if (statype != CFG80211_STA_AP_CLIENT && @@ -6957,7 +6960,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, BIT(NL80211_STA_FLAG_ASSOCIATED) | BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | BIT(NL80211_STA_FLAG_WME) | - BIT(NL80211_STA_FLAG_MFP))) + BIT(NL80211_STA_FLAG_MFP) | + BIT(NL80211_STA_FLAG_SPP_AMSDU))) return -EINVAL; /* but authenticated/associated only if driver handles it */ @@ -7516,7 +7520,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) return -EINVAL; /* When you run into this, adjust the code below for the new flag */ - BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); + BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 8); switch (dev->ieee80211_ptr->iftype) { case NL80211_IFTYPE_AP: @@ -7540,6 +7544,11 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.sta_flags_mask & auth_assoc) return -EINVAL; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT) && + params.sta_flags_mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) + return -EINVAL; + /* Older userspace, or userspace wanting to be compatible with * !NL80211_FEATURE_FULL_AP_CLIENT_STATE, will not set the auth * and assoc flags in the mask, but assumes the station will be @@ -11102,6 +11111,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) sizeof(req.s1g_capa)); } + if (nla_get_flag(info->attrs[NL80211_ATTR_ASSOC_SPP_AMSDU])) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT)) { + GENL_SET_ERR_MSG(info, "SPP A-MSDUs not supported"); + return -EINVAL; + } + req.flags |= ASSOC_REQ_SPP_AMSDU; + } + req.link_id = nl80211_link_id_or_invalid(info->attrs); if (info->attrs[NL80211_ATTR_MLO_LINKS]) { -- cgit v1.2.3 From a923ff876f4b6133a093482a6d465cde3bc2e65c Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Thu, 25 Jan 2024 14:55:47 -0800 Subject: Revert "nl80211/cfg80211: Specify band specific min RSSI thresholds with sched scan" This *mostly* reverts commit 1e1b11b6a111 ("nl80211/cfg80211: Specify band specific min RSSI thresholds with sched scan"). During the review of a new patch [1] it was observed that the functionality being modified was not actually being used by any in-tree driver. Further research determined that the functionality was originally introduced to support a new Android interface, but that interface was subsequently abandoned. Since the functionality has apparently never been used, remove it. However, to mantain the sanctity of the UABI, keep the nl80211.h assignments, but clearly mark them as obsolete. Cc: Lin Ma Cc: Vamsi Krishna Link: https://lore.kernel.org/linux-wireless/20240119151201.8670-1-linma@zju.edu.cn/ [1] Signed-off-by: Jeff Johnson Link: https://msgid.link/20240125-for-next-v1-1-fd79e01c6c09@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 8 ------- include/uapi/linux/nl80211.h | 16 ++++--------- net/wireless/nl80211.c | 55 -------------------------------------------- 3 files changed, 4 insertions(+), 75 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 56bce924bec6..51b9e6fa12f8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2695,19 +2695,11 @@ static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) * @bssid: BSSID to be matched; may be all-zero BSSID in case of SSID match * or no match (RSSI only) * @rssi_thold: don't report scan results below this threshold (in s32 dBm) - * @per_band_rssi_thold: Minimum rssi threshold for each band to be applied - * for filtering out scan results received. Drivers advertise this support - * of band specific rssi based filtering through the feature capability - * %NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD. These band - * specific rssi thresholds take precedence over rssi_thold, if specified. - * If not specified for any band, it will be assigned with rssi_thold of - * corresponding matchset. */ struct cfg80211_match_set { struct cfg80211_ssid ssid; u8 bssid[ETH_ALEN]; s32 rssi_thold; - s32 per_band_rssi_thold[NUM_NL80211_BANDS]; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3e239df3528f..853ac538a686 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4463,14 +4463,7 @@ enum nl80211_reg_rule_attr { * value as specified by &struct nl80211_bss_select_rssi_adjust. * @NL80211_SCHED_SCAN_MATCH_ATTR_BSSID: BSSID to be used for matching * (this cannot be used together with SSID). - * @NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI: Nested attribute that carries the - * band specific minimum rssi thresholds for the bands defined in - * enum nl80211_band. The minimum rssi threshold value(s32) specific to a - * band shall be encapsulated in attribute with type value equals to one - * of the NL80211_BAND_* defined in enum nl80211_band. For example, the - * minimum rssi threshold value for 2.4GHZ band shall be encapsulated - * within an attribute of type NL80211_BAND_2GHZ. And one or more of such - * attributes will be nested within this attribute. + * @NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI: Obsolete * @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter * attribute number currently defined * @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use @@ -4483,7 +4476,7 @@ enum nl80211_sched_scan_match_attr { NL80211_SCHED_SCAN_MATCH_ATTR_RELATIVE_RSSI, NL80211_SCHED_SCAN_MATCH_ATTR_RSSI_ADJUST, NL80211_SCHED_SCAN_MATCH_ATTR_BSSID, - NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI, + NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI, /* obsolete */ /* keep last */ __NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST, @@ -6418,8 +6411,7 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_AP_PMKSA_CACHING: Driver/device supports PMKSA caching * (set/del PMKSA operations) in AP mode. * - * @NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD: Driver supports - * filtering of sched scan results using band specific RSSI thresholds. + * @NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD: Obsolete * * @NL80211_EXT_FEATURE_STA_TX_PWR: This driver supports controlling tx power * to a station. @@ -6574,7 +6566,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER, NL80211_EXT_FEATURE_AIRTIME_FAIRNESS, NL80211_EXT_FEATURE_AP_PMKSA_CACHING, - NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD, + NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD, /* obsolete */ NL80211_EXT_FEATURE_EXT_KEY_ID, NL80211_EXT_FEATURE_STA_TX_PWR, NL80211_EXT_FEATURE_SAE_OFFLOAD, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0809f721f045..e4f41f86e295 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -906,23 +906,12 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, }; -static const struct nla_policy -nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = { - [NL80211_BAND_2GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_5GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_6GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_60GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_LC] = { .type = NLA_S32 }, -}; - static const struct nla_policy nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { [NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_SSID_LEN }, [NL80211_SCHED_SCAN_MATCH_ATTR_BSSID] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, - [NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI] = - NLA_POLICY_NESTED(nl80211_match_band_rssi_policy), }; static const struct nla_policy @@ -9490,41 +9479,6 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans, return 0; } -static int -nl80211_parse_sched_scan_per_band_rssi(struct wiphy *wiphy, - struct cfg80211_match_set *match_sets, - struct nlattr *tb_band_rssi, - s32 rssi_thold) -{ - struct nlattr *attr; - int i, tmp, ret = 0; - - if (!wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD)) { - if (tb_band_rssi) - ret = -EOPNOTSUPP; - else - for (i = 0; i < NUM_NL80211_BANDS; i++) - match_sets->per_band_rssi_thold[i] = - NL80211_SCAN_RSSI_THOLD_OFF; - return ret; - } - - for (i = 0; i < NUM_NL80211_BANDS; i++) - match_sets->per_band_rssi_thold[i] = rssi_thold; - - nla_for_each_nested(attr, tb_band_rssi, tmp) { - enum nl80211_band band = nla_type(attr); - - if (band < 0 || band >= NUM_NL80211_BANDS) - return -EINVAL; - - match_sets->per_band_rssi_thold[band] = nla_get_s32(attr); - } - - return 0; -} - static struct cfg80211_sched_scan_request * nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, struct nlattr **attrs, int max_match_sets) @@ -9799,15 +9753,6 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (rssi) request->match_sets[i].rssi_thold = nla_get_s32(rssi); - - /* Parse per band RSSI attribute */ - err = nl80211_parse_sched_scan_per_band_rssi(wiphy, - &request->match_sets[i], - tb[NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI], - request->match_sets[i].rssi_thold); - if (err) - goto out_free; - i++; } -- cgit v1.2.3 From b558469580f82b925d6651ac8d7a01070402dbf8 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 18 Jan 2024 19:36:33 +0100 Subject: USB: uapi: OTG 3.0 Add attribute bits defined in version 3.0 Signed-off-by: Oliver Neukum Link: https://lore.kernel.org/r/20240118183644.16125-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 8a147abfc680..44d73ba8788d 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -763,6 +763,8 @@ struct usb_otg20_descriptor { #define USB_OTG_SRP (1 << 0) #define USB_OTG_HNP (1 << 1) /* swap host/device roles */ #define USB_OTG_ADP (1 << 2) /* support ADP */ +/* OTG 3.0 */ +#define USB_OTG_RSP (1 << 3) /* support RSP */ #define OTG_STS_SELECTOR 0xF000 /* OTG status selector */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From ace4ebf9b70a7daea12102c09ba5ef6bb73223aa Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 22 Jan 2024 12:03:46 +0100 Subject: tty: vt: define a common enum for VESA blanking constants There are currently two places with VESA blanking constants definitions: fb.h and console.h. Extract/unify the two to a separate header (vesa.h). Given the fb's is in an uapi header, create the common header in uapi too. Note that instead of macros, an enum (vesa_blank_mode) is created. But the macros are kept too (they now expand to the enum constants), just in case someone in userspace performs some #ifdeffery. Signed-off-by: "Jiri Slaby (SUSE)" Cc: Helge Deller Cc: linux-kernel@vger.kernel.org Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: Thomas Zimmermann Tested-by: Helge Deller # parisc STI console Link: https://lore.kernel.org/r/20240122110401.7289-33-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 7 +------ include/uapi/linux/fb.h | 8 +------- include/uapi/linux/vesa.h | 18 ++++++++++++++++++ 3 files changed, 20 insertions(+), 13 deletions(-) create mode 100644 include/uapi/linux/vesa.h (limited to 'include/uapi') diff --git a/include/linux/console.h b/include/linux/console.h index f7c6b5fc3a36..860f82756c9c 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -18,6 +18,7 @@ #include #include #include +#include struct vc_data; struct console_font_op; @@ -520,12 +521,6 @@ void vcs_remove_sysfs(int index); */ extern atomic_t ignore_console_lock_warning; -/* VESA Blanking Levels */ -#define VESA_NO_BLANKING 0 -#define VESA_VSYNC_SUSPEND 1 -#define VESA_HSYNC_SUSPEND 2 -#define VESA_POWERDOWN 3 - extern void console_init(void); /* For deferred console takeover */ diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 3a49913d006c..cde8f173f566 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -4,6 +4,7 @@ #include #include +#include /* Definitions of frame buffers */ @@ -293,13 +294,6 @@ struct fb_con2fbmap { __u32 framebuffer; }; -/* VESA Blanking Levels */ -#define VESA_NO_BLANKING 0 -#define VESA_VSYNC_SUSPEND 1 -#define VESA_HSYNC_SUSPEND 2 -#define VESA_POWERDOWN 3 - - enum { /* screen: unblanked, hsync: on, vsync: on */ FB_BLANK_UNBLANK = VESA_NO_BLANKING, diff --git a/include/uapi/linux/vesa.h b/include/uapi/linux/vesa.h new file mode 100644 index 000000000000..81947f5088cd --- /dev/null +++ b/include/uapi/linux/vesa.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_VESA_H +#define _UAPI_LINUX_VESA_H + +/* VESA Blanking Levels */ +enum vesa_blank_mode { + VESA_NO_BLANKING = 0, +#define VESA_NO_BLANKING VESA_NO_BLANKING + VESA_VSYNC_SUSPEND = 1, +#define VESA_VSYNC_SUSPEND VESA_VSYNC_SUSPEND + VESA_HSYNC_SUSPEND = 2, +#define VESA_HSYNC_SUSPEND VESA_HSYNC_SUSPEND + VESA_POWERDOWN = VESA_VSYNC_SUSPEND | VESA_HSYNC_SUSPEND, +#define VESA_POWERDOWN VESA_POWERDOWN + VESA_BLANK_MAX = VESA_POWERDOWN, +}; + +#endif -- cgit v1.2.3 From 6f6c72acddf4357fcc83593c20ef9064fb42db92 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Sat, 27 Jan 2024 21:02:08 +0100 Subject: iio: move LIGHT_UVA and LIGHT_UVB to the end of iio_modifier The new modifiers should have added to the end of the enum, so they do not affect the existing entries. No modifiers were added since then, so they can be moved safely to the end of the list. Move IIO_MOD_LIGHT_UVA and IIO_MOD_LIGHT_UVB to the end of iio_modifier. Fixes: b89710bd215e ("iio: add modifiers for A and B ultraviolet light") Suggested-by: Paul Cercueil Signed-off-by: Javier Carrasco Link: https://lore.kernel.org/r/20240127200208.185815-1-javier.carrasco.cruz@gmail.com Signed-off-by: Jonathan Cameron --- include/uapi/linux/iio/types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 5060963707b1..f2e0b2d50e6b 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -91,8 +91,6 @@ enum iio_modifier { IIO_MOD_CO2, IIO_MOD_VOC, IIO_MOD_LIGHT_UV, - IIO_MOD_LIGHT_UVA, - IIO_MOD_LIGHT_UVB, IIO_MOD_LIGHT_DUV, IIO_MOD_PM1, IIO_MOD_PM2P5, @@ -107,6 +105,8 @@ enum iio_modifier { IIO_MOD_PITCH, IIO_MOD_YAW, IIO_MOD_ROLL, + IIO_MOD_LIGHT_UVA, + IIO_MOD_LIGHT_UVB, }; enum iio_event_type { -- cgit v1.2.3 From ea1cc3ee34a5f3144f6c2cdc07c19c914ccb9526 Mon Sep 17 00:00:00 2001 From: Min Li Date: Wed, 24 Jan 2024 13:49:46 -0500 Subject: ptp: introduce PTP_CLOCK_EXTOFF event for the measured external offset This change is for the PHC devices that can measure the phase offset between PHC signal and the external signal, such as the 1PPS signal of GNSS. Reporting PTP_CLOCK_EXTOFF to user space will be piggy-backed to the existing ptp_extts_event so that application such as ts2phc can poll the external offset the same way as extts. Hence, ts2phc can use the offset to achieve the alignment between PHC and the external signal by the help of either SW or HW filters. Signed-off-by: Min Li Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 16 +++++++++++++++- include/linux/ptp_clock_kernel.h | 3 +++ include/uapi/linux/ptp_clock.h | 13 ++++++++++--- 3 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 15b804ba4868..3aaf1a3430c5 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -44,18 +44,31 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, struct ptp_clock_event *src) { struct ptp_extts_event *dst; + struct timespec64 offset_ts; unsigned long flags; s64 seconds; u32 remainder; - seconds = div_u64_rem(src->timestamp, 1000000000, &remainder); + if (src->type == PTP_CLOCK_EXTTS) { + seconds = div_u64_rem(src->timestamp, 1000000000, &remainder); + } else if (src->type == PTP_CLOCK_EXTOFF) { + offset_ts = ns_to_timespec64(src->offset); + seconds = offset_ts.tv_sec; + remainder = offset_ts.tv_nsec; + } else { + WARN(1, "%s: unknown type %d\n", __func__, src->type); + return; + } spin_lock_irqsave(&queue->lock, flags); dst = &queue->buf[queue->tail]; dst->index = src->index; + dst->flags = PTP_EXTTS_EVENT_VALID; dst->t.sec = seconds; dst->t.nsec = remainder; + if (src->type == PTP_CLOCK_EXTOFF) + dst->flags |= PTP_EXT_OFFSET; /* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */ if (!queue_free(queue)) @@ -417,6 +430,7 @@ void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event) break; case PTP_CLOCK_EXTTS: + case PTP_CLOCK_EXTOFF: /* Enqueue timestamp on selected queues */ spin_lock_irqsave(&ptp->tsevqs_lock, flags); list_for_each_entry(tsevq, &ptp->tsevqs, qlist) { diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 1ef4e0f9bd2a..6e4b8206c7d0 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -200,6 +200,7 @@ struct ptp_clock; enum ptp_clock_events { PTP_CLOCK_ALARM, PTP_CLOCK_EXTTS, + PTP_CLOCK_EXTOFF, PTP_CLOCK_PPS, PTP_CLOCK_PPSUSR, }; @@ -210,6 +211,7 @@ enum ptp_clock_events { * @type: One of the ptp_clock_events enumeration values. * @index: Identifies the source of the event. * @timestamp: When the event occurred (%PTP_CLOCK_EXTTS only). + * @offset: When the event occurred (%PTP_CLOCK_EXTOFF only). * @pps_times: When the event occurred (%PTP_CLOCK_PPSUSR only). */ @@ -218,6 +220,7 @@ struct ptp_clock_event { int index; union { u64 timestamp; + s64 offset; struct pps_event_time pps_times; }; }; diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index da700999cad4..053b40d642de 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -32,6 +32,7 @@ #define PTP_RISING_EDGE (1<<1) #define PTP_FALLING_EDGE (1<<2) #define PTP_STRICT_FLAGS (1<<3) +#define PTP_EXT_OFFSET (1<<4) #define PTP_EXTTS_EDGES (PTP_RISING_EDGE | PTP_FALLING_EDGE) /* @@ -40,7 +41,8 @@ #define PTP_EXTTS_VALID_FLAGS (PTP_ENABLE_FEATURE | \ PTP_RISING_EDGE | \ PTP_FALLING_EDGE | \ - PTP_STRICT_FLAGS) + PTP_STRICT_FLAGS | \ + PTP_EXT_OFFSET) /* * flag fields valid for the original PTP_EXTTS_REQUEST ioctl. @@ -50,6 +52,11 @@ PTP_RISING_EDGE | \ PTP_FALLING_EDGE) +/* + * flag fields valid for the ptp_extts_event report. + */ +#define PTP_EXTTS_EVENT_VALID (PTP_ENABLE_FEATURE) + /* * Bits of the ptp_perout_request.flags field: */ @@ -228,9 +235,9 @@ struct ptp_pin_desc { #define PTP_MASK_EN_SINGLE _IOW(PTP_CLK_MAGIC, 20, unsigned int) struct ptp_extts_event { - struct ptp_clock_time t; /* Time event occured. */ + struct ptp_clock_time t; /* Time event occurred. */ unsigned int index; /* Which channel produced the event. */ - unsigned int flags; /* Reserved for future use. */ + unsigned int flags; /* Event type. */ unsigned int rsv[2]; /* Reserved for future use. */ }; -- cgit v1.2.3 From 941988af572434e4aa93fb0f2f509f92adfd691a Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 21 Dec 2023 14:31:57 +0100 Subject: netfilter: uapi: Document NFT_TABLE_F_OWNER flag Add at least this one-liner describing the obvious. Fixes: 6001a930ce03 ("netfilter: nftables: introduce table ownership") Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter/nf_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index ca30232b7bc8..fbce238abdc1 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -179,6 +179,7 @@ enum nft_hook_attributes { * enum nft_table_flags - nf_tables table flags * * @NFT_TABLE_F_DORMANT: this table is not active + * @NFT_TABLE_F_OWNER: this table is owned by a process */ enum nft_table_flags { NFT_TABLE_F_DORMANT = 0x1, -- cgit v1.2.3 From da5141bbe0c2693d85f14a89ee991921904f4d0c Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 21 Dec 2023 14:31:58 +0100 Subject: netfilter: nf_tables: Introduce NFT_TABLE_F_PERSIST This companion flag to NFT_TABLE_F_OWNER requests the kernel to keep the table around after the process has exited. It marks such table as orphaned (by dropping OWNER flag but keeping PERSIST flag in place), which opens it for other processes to manipulate. For the sake of simplicity, PERSIST flag may not be altered though. Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter/nf_tables.h | 5 ++++- net/netfilter/nf_tables_api.c | 7 +++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index fbce238abdc1..3fee994721cd 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -180,13 +180,16 @@ enum nft_hook_attributes { * * @NFT_TABLE_F_DORMANT: this table is not active * @NFT_TABLE_F_OWNER: this table is owned by a process + * @NFT_TABLE_F_PERSIST: this table shall outlive its owner */ enum nft_table_flags { NFT_TABLE_F_DORMANT = 0x1, NFT_TABLE_F_OWNER = 0x2, + NFT_TABLE_F_PERSIST = 0x4, }; #define NFT_TABLE_F_MASK (NFT_TABLE_F_DORMANT | \ - NFT_TABLE_F_OWNER) + NFT_TABLE_F_OWNER | \ + NFT_TABLE_F_PERSIST) /** * enum nft_table_attributes - nf_tables table netlink attributes diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c537104411e7..6a96f0003faa 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1219,6 +1219,9 @@ static int nf_tables_updtable(struct nft_ctx *ctx) flags & NFT_TABLE_F_OWNER)) return -EOPNOTSUPP; + if ((flags ^ ctx->table->flags) & NFT_TABLE_F_PERSIST) + return -EOPNOTSUPP; + /* No dormant off/on/off/on games in single transaction */ if (ctx->table->flags & __NFT_TABLE_F_UPDATE) return -EINVAL; @@ -11345,6 +11348,10 @@ again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { + if (table->flags & NFT_TABLE_F_PERSIST) { + table->flags &= ~NFT_TABLE_F_OWNER; + continue; + } __nft_release_hook(net, table); list_del_rcu(&table->list); to_delete[deleted++] = table; -- cgit v1.2.3 From 3a45dc2b419e691f3dd7fb42c2a1b1cc8146be4f Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 25 Jan 2024 22:11:12 -0600 Subject: crypto: ccp: Define the SEV-SNP commands AMD introduced the next generation of SEV called SEV-SNP (Secure Nested Paging). SEV-SNP builds upon existing SEV and SEV-ES functionality while adding new hardware security protection. Define the commands and structures used to communicate with the AMD-SP when creating and managing the SEV-SNP guests. The SEV-SNP firmware spec is available at developer.amd.com/sev. [ mdr: update SNP command list and SNP status struct based on current spec, use C99 flexible arrays, fix kernel-doc issues. ] Signed-off-by: Brijesh Singh Co-developed-by: Ashish Kalra Signed-off-by: Ashish Kalra Signed-off-by: Michael Roth Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240126041126.1927228-13-michael.roth@amd.com --- drivers/crypto/ccp/sev-dev.c | 16 +++ include/linux/psp-sev.h | 265 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/psp-sev.h | 56 +++++++++ 3 files changed, 337 insertions(+) (limited to 'include/uapi') diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index e4d3f45242f6..e38986d39b63 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -130,6 +130,8 @@ static int sev_cmd_buffer_len(int cmd) switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); + case SEV_CMD_SNP_SHUTDOWN_EX: return sizeof(struct sev_data_snp_shutdown_ex); + case SEV_CMD_SNP_INIT_EX: return sizeof(struct sev_data_snp_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -158,6 +160,20 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); case SEV_CMD_SEND_CANCEL: return sizeof(struct sev_data_send_cancel); + case SEV_CMD_SNP_GCTX_CREATE: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_LAUNCH_START: return sizeof(struct sev_data_snp_launch_start); + case SEV_CMD_SNP_LAUNCH_UPDATE: return sizeof(struct sev_data_snp_launch_update); + case SEV_CMD_SNP_ACTIVATE: return sizeof(struct sev_data_snp_activate); + case SEV_CMD_SNP_DECOMMISSION: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_PAGE_RECLAIM: return sizeof(struct sev_data_snp_page_reclaim); + case SEV_CMD_SNP_GUEST_STATUS: return sizeof(struct sev_data_snp_guest_status); + case SEV_CMD_SNP_LAUNCH_FINISH: return sizeof(struct sev_data_snp_launch_finish); + case SEV_CMD_SNP_DBG_DECRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_DBG_ENCRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_PAGE_UNSMASH: return sizeof(struct sev_data_snp_page_unsmash); + case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); + case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); default: return 0; } diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 7fd17e82bab4..006e4cdbeb78 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -78,6 +78,36 @@ enum sev_cmd { SEV_CMD_DBG_DECRYPT = 0x060, SEV_CMD_DBG_ENCRYPT = 0x061, + /* SNP specific commands */ + SEV_CMD_SNP_INIT = 0x081, + SEV_CMD_SNP_SHUTDOWN = 0x082, + SEV_CMD_SNP_PLATFORM_STATUS = 0x083, + SEV_CMD_SNP_DF_FLUSH = 0x084, + SEV_CMD_SNP_INIT_EX = 0x085, + SEV_CMD_SNP_SHUTDOWN_EX = 0x086, + SEV_CMD_SNP_DECOMMISSION = 0x090, + SEV_CMD_SNP_ACTIVATE = 0x091, + SEV_CMD_SNP_GUEST_STATUS = 0x092, + SEV_CMD_SNP_GCTX_CREATE = 0x093, + SEV_CMD_SNP_GUEST_REQUEST = 0x094, + SEV_CMD_SNP_ACTIVATE_EX = 0x095, + SEV_CMD_SNP_LAUNCH_START = 0x0A0, + SEV_CMD_SNP_LAUNCH_UPDATE = 0x0A1, + SEV_CMD_SNP_LAUNCH_FINISH = 0x0A2, + SEV_CMD_SNP_DBG_DECRYPT = 0x0B0, + SEV_CMD_SNP_DBG_ENCRYPT = 0x0B1, + SEV_CMD_SNP_PAGE_SWAP_OUT = 0x0C0, + SEV_CMD_SNP_PAGE_SWAP_IN = 0x0C1, + SEV_CMD_SNP_PAGE_MOVE = 0x0C2, + SEV_CMD_SNP_PAGE_MD_INIT = 0x0C3, + SEV_CMD_SNP_PAGE_SET_STATE = 0x0C6, + SEV_CMD_SNP_PAGE_RECLAIM = 0x0C7, + SEV_CMD_SNP_PAGE_UNSMASH = 0x0C8, + SEV_CMD_SNP_CONFIG = 0x0C9, + SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX = 0x0CA, + SEV_CMD_SNP_COMMIT = 0x0CB, + SEV_CMD_SNP_VLEK_LOAD = 0x0CD, + SEV_CMD_MAX, }; @@ -523,6 +553,241 @@ struct sev_data_attestation_report { u32 len; /* In/Out */ } __packed; +/** + * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params + * + * @address: physical address of firmware image + * @len: length of the firmware image + */ +struct sev_data_snp_download_firmware { + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_snp_activate - SNP_ACTIVATE command params + * + * @gctx_paddr: system physical address guest context page + * @asid: ASID to bind to the guest + */ +struct sev_data_snp_activate { + u64 gctx_paddr; /* In */ + u32 asid; /* In */ +} __packed; + +/** + * struct sev_data_snp_addr - generic SNP command params + * + * @address: physical address of generic data param + */ +struct sev_data_snp_addr { + u64 address; /* In/Out */ +} __packed; + +/** + * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params + * + * @gctx_paddr: system physical address of guest context page + * @policy: guest policy + * @ma_gctx_paddr: system physical address of migration agent + * @ma_en: the guest is associated with a migration agent + * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the + * purpose of guest-assisted migration. + * @rsvd: reserved + * @gosvw: guest OS-visible workarounds, as defined by hypervisor + */ +struct sev_data_snp_launch_start { + u64 gctx_paddr; /* In */ + u64 policy; /* In */ + u64 ma_gctx_paddr; /* In */ + u32 ma_en:1; /* In */ + u32 imi_en:1; /* In */ + u32 rsvd:30; + u8 gosvw[16]; /* In */ +} __packed; + +/* SNP support page type */ +enum { + SNP_PAGE_TYPE_NORMAL = 0x1, + SNP_PAGE_TYPE_VMSA = 0x2, + SNP_PAGE_TYPE_ZERO = 0x3, + SNP_PAGE_TYPE_UNMEASURED = 0x4, + SNP_PAGE_TYPE_SECRET = 0x5, + SNP_PAGE_TYPE_CPUID = 0x6, + + SNP_PAGE_TYPE_MAX +}; + +/** + * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params + * + * @gctx_paddr: system physical address of guest context page + * @page_size: page size 0 indicates 4K and 1 indicates 2MB page + * @page_type: encoded page type + * @imi_page: indicates that this page is part of the IMI (Incoming Migration + * Image) of the guest + * @rsvd: reserved + * @rsvd2: reserved + * @address: system physical address of destination page to encrypt + * @rsvd3: reserved + * @vmpl1_perms: VMPL permission mask for VMPL1 + * @vmpl2_perms: VMPL permission mask for VMPL2 + * @vmpl3_perms: VMPL permission mask for VMPL3 + * @rsvd4: reserved + */ +struct sev_data_snp_launch_update { + u64 gctx_paddr; /* In */ + u32 page_size:1; /* In */ + u32 page_type:3; /* In */ + u32 imi_page:1; /* In */ + u32 rsvd:27; + u32 rsvd2; + u64 address; /* In */ + u32 rsvd3:8; + u32 vmpl1_perms:8; /* In */ + u32 vmpl2_perms:8; /* In */ + u32 vmpl3_perms:8; /* In */ + u32 rsvd4; +} __packed; + +/** + * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params + * + * @gctx_paddr: system physical address of guest context page + * @id_block_paddr: system physical address of ID block + * @id_auth_paddr: system physical address of ID block authentication structure + * @id_block_en: indicates whether ID block is present + * @auth_key_en: indicates whether author key is present in authentication structure + * @rsvd: reserved + * @host_data: host-supplied data for guest, not interpreted by firmware + */ +struct sev_data_snp_launch_finish { + u64 gctx_paddr; + u64 id_block_paddr; + u64 id_auth_paddr; + u8 id_block_en:1; + u8 auth_key_en:1; + u64 rsvd:62; + u8 host_data[32]; +} __packed; + +/** + * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params + * + * @gctx_paddr: system physical address of guest context page + * @address: system physical address of guest status page + */ +struct sev_data_snp_guest_status { + u64 gctx_paddr; + u64 address; +} __packed; + +/** + * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params + * + * @paddr: system physical address of page to be claimed. The 0th bit in the + * address indicates the page size. 0h indicates 4KB and 1h indicates + * 2MB page. + */ +struct sev_data_snp_page_reclaim { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params + * + * @paddr: system physical address of page to be unsmashed. The 0th bit in the + * address indicates the page size. 0h indicates 4 KB and 1h indicates + * 2 MB page. + */ +struct sev_data_snp_page_unsmash { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters + * + * @gctx_paddr: system physical address of guest context page + * @src_addr: source address of data to operate on + * @dst_addr: destination address of data to operate on + */ +struct sev_data_snp_dbg { + u64 gctx_paddr; /* In */ + u64 src_addr; /* In */ + u64 dst_addr; /* In */ +} __packed; + +/** + * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params + * + * @gctx_paddr: system physical address of guest context page + * @req_paddr: system physical address of request page + * @res_paddr: system physical address of response page + */ +struct sev_data_snp_guest_request { + u64 gctx_paddr; /* In */ + u64 req_paddr; /* In */ + u64 res_paddr; /* In */ +} __packed; + +/** + * struct sev_data_snp_init_ex - SNP_INIT_EX structure + * + * @init_rmp: indicate that the RMP should be initialized. + * @list_paddr_en: indicate that list_paddr is valid + * @rsvd: reserved + * @rsvd1: reserved + * @list_paddr: system physical address of range list + * @rsvd2: reserved + */ +struct sev_data_snp_init_ex { + u32 init_rmp:1; + u32 list_paddr_en:1; + u32 rsvd:30; + u32 rsvd1; + u64 list_paddr; + u8 rsvd2[48]; +} __packed; + +/** + * struct sev_data_range - RANGE structure + * + * @base: system physical address of first byte of range + * @page_count: number of 4KB pages in this range + * @rsvd: reserved + */ +struct sev_data_range { + u64 base; + u32 page_count; + u32 rsvd; +} __packed; + +/** + * struct sev_data_range_list - RANGE_LIST structure + * + * @num_elements: number of elements in RANGE_ARRAY + * @rsvd: reserved + * @ranges: array of num_elements of type RANGE + */ +struct sev_data_range_list { + u32 num_elements; + u32 rsvd; + struct sev_data_range ranges[]; +} __packed; + +/** + * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure + * + * @len: length of the command buffer read by the PSP + * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU + * @rsvd1: reserved + */ +struct sev_data_snp_shutdown_ex { + u32 len; + u32 iommu_snp_shutdown:1; + u32 rsvd1:31; +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index b44ba7dcdefc..207e34217528 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -69,6 +69,12 @@ typedef enum { SEV_RET_RESOURCE_LIMIT, SEV_RET_SECURE_DATA_INVALID, SEV_RET_INVALID_KEY = 0x27, + SEV_RET_INVALID_PAGE_SIZE, + SEV_RET_INVALID_PAGE_STATE, + SEV_RET_INVALID_MDATA_ENTRY, + SEV_RET_INVALID_PAGE_OWNER, + SEV_RET_INVALID_PAGE_AEAD_OFLOW, + SEV_RET_RMP_INIT_REQUIRED, SEV_RET_MAX, } sev_ret_code; @@ -155,6 +161,56 @@ struct sev_user_data_get_id2 { __u32 length; /* In/Out */ } __packed; +/** + * struct sev_user_data_snp_status - SNP status + * + * @api_major: API major version + * @api_minor: API minor version + * @state: current platform state + * @is_rmp_initialized: whether RMP is initialized or not + * @rsvd: reserved + * @build_id: firmware build id for the API version + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @vlek_en: VLEK (Version Loaded Endorsement Key) hashstick is loaded + * @rsvd1: reserved + * @guest_count: the number of guest currently managed by the firmware + * @current_tcb_version: current TCB version + * @reported_tcb_version: reported TCB version + */ +struct sev_user_data_snp_status { + __u8 api_major; /* Out */ + __u8 api_minor; /* Out */ + __u8 state; /* Out */ + __u8 is_rmp_initialized:1; /* Out */ + __u8 rsvd:7; + __u32 build_id; /* Out */ + __u32 mask_chip_id:1; /* Out */ + __u32 mask_chip_key:1; /* Out */ + __u32 vlek_en:1; /* Out */ + __u32 rsvd1:29; + __u32 guest_count; /* Out */ + __u64 current_tcb_version; /* Out */ + __u64 reported_tcb_version; /* Out */ +} __packed; + +/** + * struct sev_user_data_snp_config - system wide configuration value for SNP. + * + * @reported_tcb: the TCB version to report in the guest attestation report. + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @rsvd: reserved + * @rsvd1: reserved + */ +struct sev_user_data_snp_config { + __u64 reported_tcb ; /* In */ + __u32 mask_chip_id:1; /* In */ + __u32 mask_chip_key:1; /* In */ + __u32 rsvd:30; /* In */ + __u8 rsvd1[52]; +} __packed; + /** * struct sev_issue_cmd - SEV ioctl parameters * -- cgit v1.2.3 From f5db8841ebe59dbdf07fda797c88ccb51e0c893d Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 25 Jan 2024 22:11:23 -0600 Subject: crypto: ccp: Add the SNP_PLATFORM_STATUS command This command is used to query the SNP platform status. See the SEV-SNP spec for more details. Signed-off-by: Brijesh Singh Signed-off-by: Ashish Kalra Signed-off-by: Michael Roth Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240126041126.1927228-24-michael.roth@amd.com --- Documentation/virt/coco/sev-guest.rst | 27 ++++++++++++++++++ drivers/crypto/ccp/sev-dev.c | 52 +++++++++++++++++++++++++++++++++++ include/uapi/linux/psp-sev.h | 1 + 3 files changed, 80 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index 68b0d2363af8..6d3d5d336e5f 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -67,6 +67,22 @@ counter (e.g. counter overflow), then -EIO will be returned. }; }; +The host ioctls are issued to a file descriptor of the /dev/sev device. +The ioctl accepts the command ID/input structure documented below. + +:: + struct sev_issue_cmd { + /* Command ID */ + __u32 cmd; + + /* Command request structure */ + __u64 data; + + /* Firmware error code on failure (see psp-sev.h) */ + __u32 error; + }; + + 2.1 SNP_GET_REPORT ------------------ @@ -124,6 +140,17 @@ be updated with the expected value. See GHCB specification for further detail on how to parse the certificate blob. +2.4 SNP_PLATFORM_STATUS +----------------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (out): struct sev_user_data_snp_status +:Returns (out): 0 on success, -negative on error + +The SNP_PLATFORM_STATUS command is used to query the SNP platform status. The +status includes API major, minor version and more. See the SEV-SNP +specification for further details. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 504a2216bded..ae02efe2736c 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -1941,6 +1941,55 @@ e_free_pdh: return ret; } +static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_addr buf; + struct page *status_page; + void *data; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + status_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!status_page) + return -ENOMEM; + + data = page_address(status_page); + + /* + * Firmware expects status page to be in firmware-owned state, otherwise + * it will report firmware error code INVALID_PAGE_STATE (0x1A). + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } + + buf.address = __psp_pa(data); + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); + + /* + * Status page will be transitioned to Reclaim state upon success, or + * left in Firmware state in failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) + return -EFAULT; + + if (ret) + goto cleanup; + + if (copy_to_user((void __user *)argp->data, data, + sizeof(struct sev_user_data_snp_status))) + ret = -EFAULT; + +cleanup: + __free_pages(status_page, 0); + return ret; +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -1992,6 +2041,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SEV_GET_ID2: ret = sev_ioctl_do_get_id2(&input); break; + case SNP_PLATFORM_STATUS: + ret = sev_ioctl_do_snp_platform_status(&input); + break; default: ret = -EINVAL; goto out; diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 207e34217528..f1e2c55a92b4 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -28,6 +28,7 @@ enum { SEV_PEK_CERT_IMPORT, SEV_GET_ID, /* This command is deprecated, use SEV_GET_ID2 */ SEV_GET_ID2, + SNP_PLATFORM_STATUS, SEV_MAX, }; -- cgit v1.2.3 From fad133c79afa02344d05001324a0474e20f3e055 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 25 Jan 2024 22:11:24 -0600 Subject: crypto: ccp: Add the SNP_COMMIT command The SNP_COMMIT command is used to commit the currently installed version of the SEV firmware. Once committed, the firmware cannot be replaced with a previous firmware version (cannot be rolled back). This command will also update the reported TCB to match that of the currently installed firmware. [ mdr: Note the reported TCB update in the documentation/commit. ] Signed-off-by: Tom Lendacky Signed-off-by: Michael Roth Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240126041126.1927228-25-michael.roth@amd.com --- Documentation/virt/coco/sev-guest.rst | 11 +++++++++++ drivers/crypto/ccp/sev-dev.c | 17 +++++++++++++++++ include/linux/psp-sev.h | 9 +++++++++ include/uapi/linux/psp-sev.h | 1 + 4 files changed, 38 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index 6d3d5d336e5f..007ae828aa2a 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -151,6 +151,17 @@ The SNP_PLATFORM_STATUS command is used to query the SNP platform status. The status includes API major, minor version and more. See the SEV-SNP specification for further details. +2.5 SNP_COMMIT +-------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Returns (out): 0 on success, -negative on error + +SNP_COMMIT is used to commit the currently installed firmware using the +SEV-SNP firmware SNP_COMMIT command. This prevents roll-back to a previously +committed firmware version. This will also update the reported TCB to match +that of the currently installed firmware. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index ae02efe2736c..6e375d15755c 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -222,6 +222,7 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); + case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit); default: return 0; } @@ -1990,6 +1991,19 @@ cleanup: return ret; } +static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_commit buf; + + if (!sev->snp_initialized) + return -EINVAL; + + buf.len = sizeof(buf); + + return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -2044,6 +2058,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SNP_PLATFORM_STATUS: ret = sev_ioctl_do_snp_platform_status(&input); break; + case SNP_COMMIT: + ret = sev_ioctl_do_snp_commit(&input); + break; default: ret = -EINVAL; goto out; diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 84eabbfbbc08..3705c2044fc0 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -801,6 +801,15 @@ struct sev_platform_init_args { bool probe; }; +/** + * struct sev_data_snp_commit - SNP_COMMIT structure + * + * @len: length of the command buffer read by the PSP + */ +struct sev_data_snp_commit { + u32 len; +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index f1e2c55a92b4..35c207664e95 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -29,6 +29,7 @@ enum { SEV_GET_ID, /* This command is deprecated, use SEV_GET_ID2 */ SEV_GET_ID2, SNP_PLATFORM_STATUS, + SNP_COMMIT, SEV_MAX, }; -- cgit v1.2.3 From cb645fe478eaad32b6168059bb6b584295af863e Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 25 Jan 2024 22:11:25 -0600 Subject: crypto: ccp: Add the SNP_SET_CONFIG command The SEV-SNP firmware provides the SNP_CONFIG command used to set various system-wide configuration values for SNP guests, such as the reported TCB version used when signing guest attestation reports. Add an interface to set this via userspace. [ mdr: Squash in doc patch from Dionna, drop extended request/ certificate handling and simplify this to a simple wrapper around SNP_CONFIG fw cmd. ] Signed-off-by: Brijesh Singh Co-developed-by: Alexey Kardashevskiy Signed-off-by: Alexey Kardashevskiy Co-developed-by: Dionna Glaze Signed-off-by: Dionna Glaze Signed-off-by: Ashish Kalra Signed-off-by: Michael Roth Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240126041126.1927228-26-michael.roth@amd.com --- Documentation/virt/coco/sev-guest.rst | 13 +++++++++++++ drivers/crypto/ccp/sev-dev.c | 20 ++++++++++++++++++++ include/uapi/linux/psp-sev.h | 1 + 3 files changed, 34 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index 007ae828aa2a..14c9de997b7d 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -162,6 +162,19 @@ SEV-SNP firmware SNP_COMMIT command. This prevents roll-back to a previously committed firmware version. This will also update the reported TCB to match that of the currently installed firmware. +2.6 SNP_SET_CONFIG +------------------ +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_config +:Returns (out): 0 on success, -negative on error + +SNP_SET_CONFIG is used to set the system-wide configuration such as +reported TCB version in the attestation report. The command is similar +to SNP_CONFIG command defined in the SEV-SNP spec. The current values of +the firmware parameters affected by this command can be queried via +SNP_PLATFORM_STATUS. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 6e375d15755c..f1a5795ffadb 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -2004,6 +2004,23 @@ static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); } +static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_config config; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&config, (void __user *)argp->data, sizeof(config))) + return -EFAULT; + + return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -2061,6 +2078,9 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SNP_COMMIT: ret = sev_ioctl_do_snp_commit(&input); break; + case SNP_SET_CONFIG: + ret = sev_ioctl_do_snp_set_config(&input, writable); + break; default: ret = -EINVAL; goto out; diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 35c207664e95..b7a2c2ee35b7 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -30,6 +30,7 @@ enum { SEV_GET_ID2, SNP_PLATFORM_STATUS, SNP_COMMIT, + SNP_SET_CONFIG, SEV_MAX, }; -- cgit v1.2.3 From 14d89e55dec9c4e49d196b9d5d659d02dcc8252b Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Mon, 29 Jan 2024 11:21:43 +0530 Subject: ASoC: SOF: amd: Add Soundwire DAI configuration support for AMD platforms Add support for configuring AMD Soundwire DAI from topology. Signed-off-by: Vijendar Mukunda Link: https://msgid.link/r/20240129055147.1493853-10-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown --- include/sound/sof/dai-amd.h | 7 +++++++ include/sound/sof/dai.h | 2 ++ include/uapi/sound/sof/tokens.h | 4 ++++ sound/soc/sof/ipc3-pcm.c | 25 +++++++++++++++++++++++++ sound/soc/sof/ipc3-topology.c | 40 ++++++++++++++++++++++++++++++++++++++++ sound/soc/sof/sof-audio.h | 1 + sound/soc/sof/topology.c | 5 +++++ 7 files changed, 84 insertions(+) (limited to 'include/uapi') diff --git a/include/sound/sof/dai-amd.h b/include/sound/sof/dai-amd.h index 9df7ac824efe..59cd014392c1 100644 --- a/include/sound/sof/dai-amd.h +++ b/include/sound/sof/dai-amd.h @@ -26,4 +26,11 @@ struct sof_ipc_dai_acpdmic_params { uint32_t pdm_ch; } __packed; +/* ACP_SDW Configuration Request - SOF_IPC_DAI_AMD_SDW_CONFIG */ +struct sof_ipc_dai_acp_sdw_params { + struct sof_ipc_hdr hdr; + u32 rate; + u32 channels; +} __packed; + #endif diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 4773a5f616a4..0764a80c17a9 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -89,6 +89,7 @@ enum sof_ipc_dai_type { SOF_DAI_AMD_SP_VIRTUAL, /**< AMD ACP SP VIRTUAL */ SOF_DAI_AMD_HS_VIRTUAL, /**< AMD ACP HS VIRTUAL */ SOF_DAI_IMX_MICFIL, /** < i.MX MICFIL PDM */ + SOF_DAI_AMD_SDW, /**< AMD ACP SDW */ }; /* general purpose DAI configuration */ @@ -119,6 +120,7 @@ struct sof_ipc_dai_config { struct sof_ipc_dai_acp_params acphs; struct sof_ipc_dai_mtk_afe_params afe; struct sof_ipc_dai_micfil_params micfil; + struct sof_ipc_dai_acp_sdw_params acp_sdw; }; } __packed; diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index ee5708934614..6bf00c09d30d 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -218,4 +218,8 @@ #define SOF_TKN_IMX_MICFIL_RATE 2000 #define SOF_TKN_IMX_MICFIL_CH 2001 +/* ACP SDW */ +#define SOF_TKN_AMD_ACP_SDW_RATE 2100 +#define SOF_TKN_AMD_ACP_SDW_CH 2101 + #endif diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c index 330f04bcd75d..35769dd7905e 100644 --- a/sound/soc/sof/ipc3-pcm.c +++ b/sound/soc/sof/ipc3-pcm.c @@ -395,6 +395,31 @@ static int sof_ipc3_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, dev_dbg(component->dev, "MICFIL PDM channels_min: %d channels_max: %d\n", channels->min, channels->max); break; + case SOF_DAI_AMD_SDW: + /* change the default trigger sequence as per HW implementation */ + for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) { + struct snd_soc_pcm_runtime *fe = dpcm->fe; + + fe->dai_link->trigger[SNDRV_PCM_STREAM_PLAYBACK] = + SND_SOC_DPCM_TRIGGER_POST; + } + + for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_CAPTURE, dpcm) { + struct snd_soc_pcm_runtime *fe = dpcm->fe; + + fe->dai_link->trigger[SNDRV_PCM_STREAM_CAPTURE] = + SND_SOC_DPCM_TRIGGER_POST; + } + rate->min = private->dai_config->acp_sdw.rate; + rate->max = private->dai_config->acp_sdw.rate; + channels->min = private->dai_config->acp_sdw.channels; + channels->max = private->dai_config->acp_sdw.channels; + + dev_dbg(component->dev, + "AMD_SDW rate_min: %d rate_max: %d\n", rate->min, rate->max); + dev_dbg(component->dev, "AMD_SDW channels_min: %d channels_max: %d\n", + channels->min, channels->max); + break; default: dev_err(component->dev, "Invalid DAI type %d\n", private->dai_config->type); break; diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index a8832a1c1a24..0970dbdfa78a 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -298,6 +298,14 @@ static const struct sof_topology_token micfil_pdm_tokens[] = { offsetof(struct sof_ipc_dai_micfil_params, pdm_ch)}, }; +/* ACP_SDW */ +static const struct sof_topology_token acp_sdw_tokens[] = { + {SOF_TKN_AMD_ACP_SDW_RATE, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + offsetof(struct sof_ipc_dai_acp_sdw_params, rate)}, + {SOF_TKN_AMD_ACP_SDW_CH, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + offsetof(struct sof_ipc_dai_acp_sdw_params, channels)}, +}; + /* Core tokens */ static const struct sof_topology_token core_tokens[] = { {SOF_TKN_COMP_CORE_ID, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, @@ -336,6 +344,7 @@ static const struct sof_token_info ipc3_token_list[SOF_TOKEN_COUNT] = { [SOF_ACPI2S_TOKENS] = {"ACPI2S tokens", acpi2s_tokens, ARRAY_SIZE(acpi2s_tokens)}, [SOF_MICFIL_TOKENS] = {"MICFIL PDM tokens", micfil_pdm_tokens, ARRAY_SIZE(micfil_pdm_tokens)}, + [SOF_ACP_SDW_TOKENS] = {"ACP_SDW tokens", acp_sdw_tokens, ARRAY_SIZE(acp_sdw_tokens)}, }; /** @@ -1315,6 +1324,34 @@ static int sof_link_acp_hs_load(struct snd_soc_component *scomp, struct snd_sof_ return 0; } +static int sof_link_acp_sdw_load(struct snd_soc_component *scomp, struct snd_sof_dai_link *slink, + struct sof_ipc_dai_config *config, struct snd_sof_dai *dai) +{ + struct sof_dai_private_data *private = dai->private; + u32 size = sizeof(*config); + int ret; + + /* parse the required set of ACP_SDW tokens based on num_hw_cfgs */ + ret = sof_update_ipc_object(scomp, &config->acp_sdw, SOF_ACP_SDW_TOKENS, slink->tuples, + slink->num_tuples, size, slink->num_hw_configs); + if (ret < 0) + return ret; + + /* init IPC */ + config->hdr.size = size; + dev_dbg(scomp->dev, "ACP SDW config rate %d channels %d\n", + config->acp_sdw.rate, config->acp_sdw.channels); + + /* set config for all DAI's with name matching the link name */ + dai->number_configs = 1; + dai->current_config = 0; + private->dai_config = kmemdup(config, size, GFP_KERNEL); + if (!private->dai_config) + return -ENOMEM; + + return 0; +} + static int sof_link_afe_load(struct snd_soc_component *scomp, struct snd_sof_dai_link *slink, struct sof_ipc_dai_config *config, struct snd_sof_dai *dai) { @@ -1629,6 +1666,9 @@ static int sof_ipc3_widget_setup_comp_dai(struct snd_sof_widget *swidget) case SOF_DAI_MEDIATEK_AFE: ret = sof_link_afe_load(scomp, slink, config, dai); break; + case SOF_DAI_AMD_SDW: + ret = sof_link_acp_sdw_load(scomp, slink, config, dai); + break; default: break; } diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index 8874ee5f557f..f98242a404db 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -276,6 +276,7 @@ enum sof_tokens { SOF_ACPDMIC_TOKENS, SOF_ACPI2S_TOKENS, SOF_MICFIL_TOKENS, + SOF_ACP_SDW_TOKENS, /* this should be the last */ SOF_TOKEN_COUNT, diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 617a225fff24..25fb0d1443b6 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -297,6 +297,7 @@ static const struct sof_dai_types sof_dais[] = { {"ACPSP_VIRTUAL", SOF_DAI_AMD_SP_VIRTUAL}, {"ACPHS_VIRTUAL", SOF_DAI_AMD_HS_VIRTUAL}, {"MICFIL", SOF_DAI_IMX_MICFIL}, + {"ACP_SDW", SOF_DAI_AMD_SDW}, }; @@ -1968,6 +1969,10 @@ static int sof_link_load(struct snd_soc_component *scomp, int index, struct snd_ token_id = SOF_MICFIL_TOKENS; num_tuples += token_list[SOF_MICFIL_TOKENS].count; break; + case SOF_DAI_AMD_SDW: + token_id = SOF_ACP_SDW_TOKENS; + num_tuples += token_list[SOF_ACP_SDW_TOKENS].count; + break; default: break; } -- cgit v1.2.3 From cf4f0f1e1c465da7c1f6bc89c3ff50bf42f0ab02 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 30 Jan 2024 13:08:29 +0100 Subject: dpll: extend uapi by lock status error attribute If the dpll devices goes to state "unlocked" or "holdover", it may be caused by an error. In that case, allow user to see what the error was. Introduce a new attribute and values it can carry. Signed-off-by: Jiri Pirko Acked-by: Vadim Fedorenko Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/dpll.yaml | 39 +++++++++++++++++++++++++++++++++++ include/uapi/linux/dpll.h | 30 +++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index b14aed18065f..1755066d8308 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -51,6 +51,40 @@ definitions: if dpll lock-state was not DPLL_LOCK_STATUS_LOCKED_HO_ACQ, the dpll's lock-state shall remain DPLL_LOCK_STATUS_UNLOCKED) render-max: true + - + type: enum + name: lock-status-error + doc: | + if previous status change was done due to a failure, this provides + information of dpll device lock status error. + Valid values for DPLL_A_LOCK_STATUS_ERROR attribute + entries: + - + name: none + doc: | + dpll device lock status was changed without any error + value: 1 + - + name: undefined + doc: | + dpll device lock status was changed due to undefined error. + Driver fills this value up in case it is not able + to obtain suitable exact error type. + - + name: media-down + doc: | + dpll device lock status was changed because of associated + media got down. + This may happen for example if dpll device was previously + locked on an input pin of type PIN_TYPE_SYNCE_ETH_PORT. + - + name: fractional-frequency-offset-too-high + doc: | + the FFO (Fractional Frequency Offset) between the RX and TX + symbol rate on the media got too high. + This may happen for example if dpll device was previously + locked on an input pin of type PIN_TYPE_SYNCE_ETH_PORT. + render-max: true - type: const name: temp-divider @@ -214,6 +248,10 @@ attribute-sets: name: type type: u32 enum: type + - + name: lock-status-error + type: u32 + enum: lock-status-error - name: pin enum-name: dpll_a_pin @@ -379,6 +417,7 @@ operations: - mode - mode-supported - lock-status + - lock-status-error - temp - clock-id - type diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index b4e947f9bfbc..0c13d7f1a1bc 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -50,6 +50,35 @@ enum dpll_lock_status { DPLL_LOCK_STATUS_MAX = (__DPLL_LOCK_STATUS_MAX - 1) }; +/** + * enum dpll_lock_status_error - if previous status change was done due to a + * failure, this provides information of dpll device lock status error. Valid + * values for DPLL_A_LOCK_STATUS_ERROR attribute + * @DPLL_LOCK_STATUS_ERROR_NONE: dpll device lock status was changed without + * any error + * @DPLL_LOCK_STATUS_ERROR_UNDEFINED: dpll device lock status was changed due + * to undefined error. Driver fills this value up in case it is not able to + * obtain suitable exact error type. + * @DPLL_LOCK_STATUS_ERROR_MEDIA_DOWN: dpll device lock status was changed + * because of associated media got down. This may happen for example if dpll + * device was previously locked on an input pin of type + * PIN_TYPE_SYNCE_ETH_PORT. + * @DPLL_LOCK_STATUS_ERROR_FRACTIONAL_FREQUENCY_OFFSET_TOO_HIGH: the FFO + * (Fractional Frequency Offset) between the RX and TX symbol rate on the + * media got too high. This may happen for example if dpll device was + * previously locked on an input pin of type PIN_TYPE_SYNCE_ETH_PORT. + */ +enum dpll_lock_status_error { + DPLL_LOCK_STATUS_ERROR_NONE = 1, + DPLL_LOCK_STATUS_ERROR_UNDEFINED, + DPLL_LOCK_STATUS_ERROR_MEDIA_DOWN, + DPLL_LOCK_STATUS_ERROR_FRACTIONAL_FREQUENCY_OFFSET_TOO_HIGH, + + /* private: */ + __DPLL_LOCK_STATUS_ERROR_MAX, + DPLL_LOCK_STATUS_ERROR_MAX = (__DPLL_LOCK_STATUS_ERROR_MAX - 1) +}; + #define DPLL_TEMP_DIVIDER 1000 /** @@ -150,6 +179,7 @@ enum dpll_a { DPLL_A_LOCK_STATUS, DPLL_A_TEMP, DPLL_A_TYPE, + DPLL_A_LOCK_STATUS_ERROR, __DPLL_A_MAX, DPLL_A_MAX = (__DPLL_A_MAX - 1) -- cgit v1.2.3 From 64bef697d33b75fc06c5789b3f8108680271529f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 31 Jan 2024 14:26:02 +0100 Subject: pidfd: implement PIDFD_THREAD flag for pidfd_open() With this flag: - pidfd_open() doesn't require that the target task must be a thread-group leader - pidfd_poll() succeeds when the task exits and becomes a zombie (iow, passes exit_notify()), even if it is a leader and thread-group is not empty. This means that the behaviour of pidfd_poll(PIDFD_THREAD, pid-of-group-leader) is not well defined if it races with exec() from its sub-thread; pidfd_poll() can succeed or not depending on whether pidfd_task_exited() is called before or after exchange_tids(). Perhaps we can improve this behaviour later, pidfd_poll() can probably take sig->group_exec_task into account. But this doesn't really differ from the case when the leader exits before other threads (so pidfd_poll() succeeds) and then another thread execs and pidfd_poll() will block again. thread_group_exited() is no longer used, perhaps it can die. Co-developed-by: Tycho Andersen Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240131132602.GA23641@redhat.com Tested-by: Tycho Andersen Reviewed-by: Tycho Andersen Signed-off-by: Christian Brauner --- fs/exec.c | 6 +++++- include/linux/pid.h | 3 ++- include/uapi/linux/pidfd.h | 3 ++- kernel/exit.c | 7 +++++++ kernel/fork.c | 38 +++++++++++++++++++++++++++++++------- kernel/pid.c | 14 +++----------- kernel/signal.c | 6 ++++-- 7 files changed, 54 insertions(+), 23 deletions(-) (limited to 'include/uapi') diff --git a/fs/exec.c b/fs/exec.c index 8cdd5b2dd09c..b68f61bbcaa8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1143,7 +1143,11 @@ static int de_thread(struct task_struct *tsk) BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; - + /* + * leader and tsk exhanged their pids, the old pid dies, + * wake up the PIDFD_THREAD waiters. + */ + do_notify_pidfd(leader); /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees diff --git a/include/linux/pid.h b/include/linux/pid.h index e6a041cb8bac..8124d57752b9 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -70,10 +70,11 @@ extern const struct file_operations pidfd_fops; struct file; -extern struct pid *pidfd_pid(const struct file *file); +struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); +void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 5406fbc13074..2e6461459877 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -7,6 +7,7 @@ #include /* Flags for pidfd_open(). */ -#define PIDFD_NONBLOCK O_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#define PIDFD_THREAD O_EXCL #endif /* _UAPI_LINUX_PIDFD_H */ diff --git a/kernel/exit.c b/kernel/exit.c index 3988a02efaef..c038d10dfb38 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; + /* + * sub-thread or delay_group_leader(), wake up the + * PIDFD_THREAD waiters. + */ + if (!thread_group_empty(tsk)) + do_notify_pidfd(tsk); + if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && diff --git a/kernel/fork.c b/kernel/fork.c index 726a92043531..1a9b91055916 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -101,6 +101,7 @@ #include #include #include +#include #include #include @@ -2050,6 +2051,8 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) seq_put_decimal_ll(m, "Pid:\t", nr); + /* TODO: report PIDFD_THREAD */ + #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { @@ -2068,22 +2071,35 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) } #endif +static bool pidfd_task_exited(struct pid *pid, bool thread) +{ + struct task_struct *task; + bool exited; + + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + exited = !task || + (READ_ONCE(task->exit_state) && (thread || thread_group_empty(task))); + rcu_read_unlock(); + + return exited; +} + /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; + bool thread = file->f_flags & PIDFD_THREAD; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); - /* - * Inform pollers only when the whole thread group exits. - * If the thread group leader exits before all other threads in the - * group, then poll(2) should block, similar to the wait(2) family. + * Depending on PIDFD_THREAD, inform pollers when the thread + * or the whole thread-group exits. */ - if (thread_group_exited(pid)) + if (pidfd_task_exited(pid, thread)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; @@ -2141,6 +2157,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re return PTR_ERR(pidfd_file); } get_pid(pid); /* held by pidfd_file now */ + /* + * anon_inode_getfile() ignores everything outside of the + * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. + */ + pidfd_file->f_flags |= (flags & PIDFD_THREAD); *ret = pidfd_file; return pidfd; } @@ -2154,7 +2175,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * - * The helper verifies that @pid is used as a thread group leader. + * The helper verifies that @pid is still in use, without PIDFD_THREAD the + * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in @@ -2173,7 +2195,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) + bool thread = flags & PIDFD_THREAD; + + if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); diff --git a/kernel/pid.c b/kernel/pid.c index c7a3e359f8f5..e11144466828 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -552,11 +552,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * - * Currently, the process identified by @pidfd is always a thread-group leader. - * This restriction currently exists for all aspects of pidfds including pidfd - * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling - * (only supports thread group leaders). - * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ @@ -615,11 +610,8 @@ static int pidfd_create(struct pid *pid, unsigned int flags) * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for - * the process identified by @pid. Currently, the process identified by - * @pid must be a thread-group leader. This restriction currently exists - * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot - * be used with CLONE_THREAD) and pidfd polling (only supports thread group - * leaders). + * the task identified by @pid. Without PIDFD_THREAD flag the target task + * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. @@ -629,7 +621,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) int fd; struct pid *p; - if (flags & ~PIDFD_NONBLOCK) + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) diff --git a/kernel/signal.c b/kernel/signal.c index 9561a3962ca6..9b40109f0c56 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2019,7 +2019,7 @@ ret: return ret; } -static void do_notify_pidfd(struct task_struct *task) +void do_notify_pidfd(struct task_struct *task) { struct pid *pid; @@ -2051,7 +2051,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); /* - * tsk is a group leader and has no threads, wake up the pidfd waiters. + * tsk is a group leader and has no threads, wake up the + * non-PIDFD_THREAD waiters. */ if (thread_group_empty(tsk)) do_notify_pidfd(tsk); @@ -3926,6 +3927,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, prepare_kill_siginfo(sig, &kinfo); } + /* TODO: respect PIDFD_THREAD */ ret = kill_pid_info(sig, &kinfo, pid); err: -- cgit v1.2.3 From 27b9e36d0e08fdbb5b406260dcfe0cb59342593f Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 26 Jan 2024 23:16:01 +0000 Subject: media: videodev2.h: Fix kerneldoc Named nested unions need their prefix: https://www.kernel.org/doc/html/latest/doc-guide/kernel-doc.html#nested-structs-unions Signed-off-by: Ricardo Ribalda Reviewed-by: Randy Dunlap Tested-by: Randy Dunlap Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 68e7ac178cc2..a8015e5e7fa4 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1041,13 +1041,13 @@ struct v4l2_requestbuffers { * struct v4l2_plane - plane info for multi-planar buffers * @bytesused: number of bytes occupied by data in the plane (payload) * @length: size of this plane (NOT the payload) in bytes - * @mem_offset: when memory in the associated struct v4l2_buffer is + * @m.mem_offset: when memory in the associated struct v4l2_buffer is * V4L2_MEMORY_MMAP, equals the offset from the start of * the device memory for this plane (or is a "cookie" that * should be passed to mmap() called on the video node) - * @userptr: when memory is V4L2_MEMORY_USERPTR, a userspace pointer + * @m.userptr: when memory is V4L2_MEMORY_USERPTR, a userspace pointer * pointing to this plane - * @fd: when memory is V4L2_MEMORY_DMABUF, a userspace file + * @m.fd: when memory is V4L2_MEMORY_DMABUF, a userspace file * descriptor associated with this plane * @m: union of @mem_offset, @userptr and @fd * @data_offset: offset in the plane to the start of data; usually 0, @@ -1085,14 +1085,14 @@ struct v4l2_plane { * @sequence: sequence count of this frame * @memory: enum v4l2_memory; the method, in which the actual video data is * passed - * @offset: for non-multiplanar buffers with memory == V4L2_MEMORY_MMAP; + * @m.offset: for non-multiplanar buffers with memory == V4L2_MEMORY_MMAP; * offset from the start of the device memory for this plane, * (or a "cookie" that should be passed to mmap() as offset) - * @userptr: for non-multiplanar buffers with memory == V4L2_MEMORY_USERPTR; + * @m.userptr: for non-multiplanar buffers with memory == V4L2_MEMORY_USERPTR; * a userspace pointer pointing to this buffer - * @fd: for non-multiplanar buffers with memory == V4L2_MEMORY_DMABUF; + * @m.fd: for non-multiplanar buffers with memory == V4L2_MEMORY_DMABUF; * a userspace file descriptor associated with this buffer - * @planes: for multiplanar buffers; userspace pointer to the array of plane + * @m.planes: for multiplanar buffers; userspace pointer to the array of plane * info structs for this buffer * @m: union of @offset, @userptr, @planes and @fd * @length: size in bytes of the buffer (NOT its payload) for single-plane @@ -2423,15 +2423,15 @@ struct v4l2_meta_format { /** * struct v4l2_format - stream data format - * @type: enum v4l2_buf_type; type of the data stream - * @pix: definition of an image format - * @pix_mp: definition of a multiplanar image format - * @win: definition of an overlaid image - * @vbi: raw VBI capture or output parameters - * @sliced: sliced VBI capture or output parameters - * @raw_data: placeholder for future extensions and custom formats - * @fmt: union of @pix, @pix_mp, @win, @vbi, @sliced, @sdr, @meta - * and @raw_data + * @type: enum v4l2_buf_type; type of the data stream + * @fmt.pix: definition of an image format + * @fmt.pix_mp: definition of a multiplanar image format + * @fmt.win: definition of an overlaid image + * @fmt.vbi: raw VBI capture or output parameters + * @fmt.sliced: sliced VBI capture or output parameters + * @fmt.raw_data: placeholder for future extensions and custom formats + * @fmt: union of @pix, @pix_mp, @win, @vbi, @sliced, @sdr, + * @meta and @raw_data */ struct v4l2_format { __u32 type; -- cgit v1.2.3 From 240fd405528bbf7fafa0559202ca7aa524c9cd96 Mon Sep 17 00:00:00 2001 From: Aahil Awatramani Date: Fri, 2 Feb 2024 17:58:58 +0000 Subject: bonding: Add independent control state machine Add support for the independent control state machine per IEEE 802.1AX-2008 5.4.15 in addition to the existing implementation of the coupled control state machine. Introduces two new states, AD_MUX_COLLECTING and AD_MUX_DISTRIBUTING in the LACP MUX state machine for separated handling of an initial Collecting state before the Collecting and Distributing state. This enables a port to be in a state where it can receive incoming packets while not still distributing. This is useful for reducing packet loss when a port begins distributing before its partner is able to collect. Added new functions such as bond_set_slave_tx_disabled_flags and bond_set_slave_rx_enabled_flags to precisely manage the port's collecting and distributing states. Previously, there was no dedicated method to disable TX while keeping RX enabled, which this patch addresses. Note that the regular flow process in the kernel's bonding driver remains unaffected by this patch. The extension requires explicit opt-in by the user (in order to ensure no disruptions for existing setups) via netlink support using the new bonding parameter coupled_control. The default value for coupled_control is set to 1 so as to preserve existing behaviour. Signed-off-by: Aahil Awatramani Reviewed-by: Hangbin Liu Link: https://lore.kernel.org/r/20240202175858.1573852-1-aahila@google.com Signed-off-by: Paolo Abeni --- Documentation/networking/bonding.rst | 12 +++ drivers/net/bonding/bond_3ad.c | 157 +++++++++++++++++++++++++++++++++-- drivers/net/bonding/bond_main.c | 1 + drivers/net/bonding/bond_netlink.c | 16 ++++ drivers/net/bonding/bond_options.c | 28 ++++++- include/net/bond_3ad.h | 2 + include/net/bond_options.h | 1 + include/net/bonding.h | 23 +++++ include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 10 files changed, 234 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index f7a73421eb76..e774b48de9f5 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -444,6 +444,18 @@ arp_missed_max The default value is 2, and the allowable range is 1 - 255. +coupled_control + + Specifies whether the LACP state machine's MUX in the 802.3ad mode + should have separate Collecting and Distributing states. + + This is by implementing the independent control state machine per + IEEE 802.1AX-2008 5.4.15 in addition to the existing coupled control + state machine. + + The default value is 1. This setting does not separate the Collecting + and Distributing states, maintaining the bond in coupled control. + downdelay Specifies the time, in milliseconds, to wait before disabling diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index c99ffe6c683a..f2942e8c6c91 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -106,6 +106,9 @@ static void ad_agg_selection_logic(struct aggregator *aggregator, static void ad_clear_agg(struct aggregator *aggregator); static void ad_initialize_agg(struct aggregator *aggregator); static void ad_initialize_port(struct port *port, int lacp_fast); +static void ad_enable_collecting(struct port *port); +static void ad_disable_distributing(struct port *port, + bool *update_slave_arr); static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr); static void ad_disable_collecting_distributing(struct port *port, @@ -171,9 +174,38 @@ static inline int __agg_has_partner(struct aggregator *agg) return !is_zero_ether_addr(agg->partner_system.mac_addr_value); } +/** + * __disable_distributing_port - disable the port's slave for distributing. + * Port will still be able to collect. + * @port: the port we're looking at + * + * This will disable only distributing on the port's slave. + */ +static void __disable_distributing_port(struct port *port) +{ + bond_set_slave_tx_disabled_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); +} + +/** + * __enable_collecting_port - enable the port's slave for collecting, + * if it's up + * @port: the port we're looking at + * + * This will enable only collecting on the port's slave. + */ +static void __enable_collecting_port(struct port *port) +{ + struct slave *slave = port->slave; + + if (slave->link == BOND_LINK_UP && bond_slave_is_up(slave)) + bond_set_slave_rx_enabled_flags(slave, BOND_SLAVE_NOTIFY_LATER); +} + /** * __disable_port - disable the port's slave * @port: the port we're looking at + * + * This will disable both collecting and distributing on the port's slave. */ static inline void __disable_port(struct port *port) { @@ -183,6 +215,8 @@ static inline void __disable_port(struct port *port) /** * __enable_port - enable the port's slave, if it's up * @port: the port we're looking at + * + * This will enable both collecting and distributing on the port's slave. */ static inline void __enable_port(struct port *port) { @@ -193,10 +227,27 @@ static inline void __enable_port(struct port *port) } /** - * __port_is_enabled - check if the port's slave is in active state + * __port_move_to_attached_state - check if port should transition back to attached + * state. + * @port: the port we're looking at + */ +static bool __port_move_to_attached_state(struct port *port) +{ + if (!(port->sm_vars & AD_PORT_SELECTED) || + (port->sm_vars & AD_PORT_STANDBY) || + !(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) || + !(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) + port->sm_mux_state = AD_MUX_ATTACHED; + + return port->sm_mux_state == AD_MUX_ATTACHED; +} + +/** + * __port_is_collecting_distributing - check if the port's slave is in the + * combined collecting/distributing state * @port: the port we're looking at */ -static inline int __port_is_enabled(struct port *port) +static int __port_is_collecting_distributing(struct port *port) { return bond_is_active_slave(port->slave); } @@ -942,6 +993,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) */ static void ad_mux_machine(struct port *port, bool *update_slave_arr) { + struct bonding *bond = __get_bond_by_port(port); mux_states_t last_state; /* keep current State Machine state to compare later if it was @@ -999,9 +1051,13 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - if (port->aggregator->is_active) - port->sm_mux_state = - AD_MUX_COLLECTING_DISTRIBUTING; + if (port->aggregator->is_active) { + int state = AD_MUX_COLLECTING_DISTRIBUTING; + + if (!bond->params.coupled_control) + state = AD_MUX_COLLECTING; + port->sm_mux_state = state; + } } else if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) { /* if UNSELECTED or STANDBY */ @@ -1019,11 +1075,45 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) } break; case AD_MUX_COLLECTING_DISTRIBUTING: + if (!__port_move_to_attached_state(port)) { + /* if port state hasn't changed make + * sure that a collecting distributing + * port in an active aggregator is enabled + */ + if (port->aggregator->is_active && + !__port_is_collecting_distributing(port)) { + __enable_port(port); + *update_slave_arr = true; + } + } + break; + case AD_MUX_COLLECTING: + if (!__port_move_to_attached_state(port)) { + if ((port->sm_vars & AD_PORT_SELECTED) && + (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && + (port->partner_oper.port_state & LACP_STATE_COLLECTING)) { + port->sm_mux_state = AD_MUX_DISTRIBUTING; + } else { + /* If port state hasn't changed, make sure that a collecting + * port is enabled for an active aggregator. + */ + struct slave *slave = port->slave; + + if (port->aggregator->is_active && + bond_is_slave_rx_disabled(slave)) { + ad_enable_collecting(port); + *update_slave_arr = true; + } + } + } + break; + case AD_MUX_DISTRIBUTING: if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY) || + !(port->partner_oper.port_state & LACP_STATE_COLLECTING) || !(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) || !(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) { - port->sm_mux_state = AD_MUX_ATTACHED; + port->sm_mux_state = AD_MUX_COLLECTING; } else { /* if port state hasn't changed make * sure that a collecting distributing @@ -1031,7 +1121,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ if (port->aggregator && port->aggregator->is_active && - !__port_is_enabled(port)) { + !__port_is_collecting_distributing(port)) { __enable_port(port); *update_slave_arr = true; } @@ -1082,6 +1172,20 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) update_slave_arr); port->ntt = true; break; + case AD_MUX_COLLECTING: + port->actor_oper_port_state |= LACP_STATE_COLLECTING; + port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING; + port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; + ad_enable_collecting(port); + ad_disable_distributing(port, update_slave_arr); + port->ntt = true; + break; + case AD_MUX_DISTRIBUTING: + port->actor_oper_port_state |= LACP_STATE_DISTRIBUTING; + port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; + ad_enable_collecting_distributing(port, + update_slave_arr); + break; default: break; } @@ -1906,6 +2010,45 @@ static void ad_initialize_port(struct port *port, int lacp_fast) } } +/** + * ad_enable_collecting - enable a port's receive + * @port: the port we're looking at + * + * Enable @port if it's in an active aggregator + */ +static void ad_enable_collecting(struct port *port) +{ + if (port->aggregator->is_active) { + struct slave *slave = port->slave; + + slave_dbg(slave->bond->dev, slave->dev, + "Enabling collecting on port %d (LAG %d)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + __enable_collecting_port(port); + } +} + +/** + * ad_disable_distributing - disable a port's transmit + * @port: the port we're looking at + * @update_slave_arr: Does slave array need update? + */ +static void ad_disable_distributing(struct port *port, bool *update_slave_arr) +{ + if (port->aggregator && + !MAC_ADDRESS_EQUAL(&port->aggregator->partner_system, + &(null_mac_addr))) { + slave_dbg(port->slave->bond->dev, port->slave->dev, + "Disabling distributing on port %d (LAG %d)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + __disable_distributing_port(port); + /* Slave array needs an update */ + *update_slave_arr = true; + } +} + /** * ad_enable_collecting_distributing - enable a port's transmit/receive * @port: the port we're looking at diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4e0600c7b050..ae9d32c0faf4 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6306,6 +6306,7 @@ static int __init bond_check_params(struct bond_params *params) params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; + params->coupled_control = 1; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index cfa74cf8bb1a..29b4c3d1b9b6 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -122,6 +122,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, + [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -549,6 +550,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; } + if (data[IFLA_BOND_COUPLED_CONTROL]) { + int coupled_control = nla_get_u8(data[IFLA_BOND_COUPLED_CONTROL]); + + bond_opt_initval(&newval, coupled_control); + err = __bond_opt_set(bond, BOND_OPT_COUPLED_CONTROL, &newval, + data[IFLA_BOND_COUPLED_CONTROL], extack); + if (err) + return err; + } + return 0; } @@ -615,6 +626,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) /* IFLA_BOND_NS_IP6_TARGET */ nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + + nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */ 0; } @@ -774,6 +786,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.missed_max)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL, + bond->params.coupled_control)) + goto nla_put_failure; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index f3f27f0bd2a6..4cdbc7e084f4 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -84,7 +84,8 @@ static int bond_option_ad_user_port_key_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_missed_max_set(struct bonding *bond, const struct bond_opt_value *newval); - +static int bond_option_coupled_control_set(struct bonding *bond, + const struct bond_opt_value *newval); static const struct bond_opt_value bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT}, @@ -232,6 +233,12 @@ static const struct bond_opt_value bond_missed_max_tbl[] = { { NULL, -1, 0}, }; +static const struct bond_opt_value bond_coupled_control_tbl[] = { + { "on", 1, BOND_VALFLAG_DEFAULT}, + { "off", 0, 0}, + { NULL, -1, 0}, +}; + static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_MODE] = { .id = BOND_OPT_MODE, @@ -496,6 +503,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .desc = "Delay between each peer notification on failover event, in milliseconds", .values = bond_peer_notif_delay_tbl, .set = bond_option_peer_notif_delay_set + }, + [BOND_OPT_COUPLED_CONTROL] = { + .id = BOND_OPT_COUPLED_CONTROL, + .name = "coupled_control", + .desc = "Opt into using coupled control MUX for LACP states", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .flags = BOND_OPTFLAG_IFDOWN, + .values = bond_coupled_control_tbl, + .set = bond_option_coupled_control_set, } }; @@ -1692,3 +1708,13 @@ static int bond_option_ad_user_port_key_set(struct bonding *bond, bond->params.ad_user_port_key = newval->value; return 0; } + +static int bond_option_coupled_control_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + netdev_info(bond->dev, "Setting coupled_control to %s (%llu)\n", + newval->string, newval->value); + + bond->params.coupled_control = newval->value; + return 0; +} diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index c5e57c6bd873..9ce5ac2bfbad 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -54,6 +54,8 @@ typedef enum { AD_MUX_DETACHED, /* mux machine */ AD_MUX_WAITING, /* mux machine */ AD_MUX_ATTACHED, /* mux machine */ + AD_MUX_COLLECTING, /* mux machine */ + AD_MUX_DISTRIBUTING, /* mux machine */ AD_MUX_COLLECTING_DISTRIBUTING /* mux machine */ } mux_states_t; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 69292ecc0325..473a0147769e 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -76,6 +76,7 @@ enum { BOND_OPT_MISSED_MAX, BOND_OPT_NS_TARGETS, BOND_OPT_PRIO, + BOND_OPT_COUPLED_CONTROL, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 5b8b1b644a2d..b61fb1aa3a56 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -148,6 +148,7 @@ struct bond_params { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif + int coupled_control; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; @@ -167,6 +168,7 @@ struct slave { u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ + rx_disabled:1, /* indicates whether slave's Rx is disabled */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; @@ -568,6 +570,14 @@ static inline void bond_set_slave_inactive_flags(struct slave *slave, bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; + if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) + slave->rx_disabled = 1; +} + +static inline void bond_set_slave_tx_disabled_flags(struct slave *slave, + bool notify) +{ + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); } static inline void bond_set_slave_active_flags(struct slave *slave, @@ -575,6 +585,14 @@ static inline void bond_set_slave_active_flags(struct slave *slave, { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; + if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) + slave->rx_disabled = 0; +} + +static inline void bond_set_slave_rx_enabled_flags(struct slave *slave, + bool notify) +{ + slave->rx_disabled = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) @@ -582,6 +600,11 @@ static inline bool bond_is_slave_inactive(struct slave *slave) return slave->inactive; } +static inline bool bond_is_slave_rx_disabled(struct slave *slave) +{ + return slave->rx_disabled; +} + static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ab9bcff96e4d..ffa637b38c93 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1505,6 +1505,7 @@ enum { IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, IFLA_BOND_NS_IP6_TARGET, + IFLA_BOND_COUPLED_CONTROL, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index a0aa05a28cf2..f0d71b2a3f1e 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -974,6 +974,7 @@ enum { IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, IFLA_BOND_NS_IP6_TARGET, + IFLA_BOND_COUPLED_CONTROL, __IFLA_BOND_MAX, }; -- cgit v1.2.3 From 5f8408aca66772d3aa9b4831577b2ac5ec41bcd9 Mon Sep 17 00:00:00 2001 From: Grzegorz Trzebiatowski Date: Fri, 26 Jan 2024 13:28:04 +0100 Subject: accel/ivpu: Add job status for jobs aborted by the driver Add DRM_IVPU_JOB_STATUS_ABORTED to indicate that the job was aborted by the driver due to e.g. TDR or user context MMU faults. This will help UMD and tests distinguish if job was aborted by the FW or the driver. Signed-off-by: Grzegorz Trzebiatowski Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-8-jacek.lawrynowicz@linux.intel.com --- drivers/accel/ivpu/ivpu_job.c | 4 ++-- include/uapi/drm/ivpu_accel.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 0440bee3ecaf..e70cfb859339 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32 return -ENOENT; if (job->file_priv->has_mmu_faults) - job_status = VPU_JSM_STATUS_ABORTED; + job_status = DRM_IVPU_JOB_STATUS_ABORTED; job->bos[CMD_BUF_IDX]->job_status = job_status; dma_fence_signal(job->done_fence); @@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev) unsigned long id; xa_for_each(&vdev->submitted_jobs_xa, id, job) - ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED); + ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED); } static int ivpu_job_submit(struct ivpu_job *job) diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h index 63c49318a863..19a13468eca5 100644 --- a/include/uapi/drm/ivpu_accel.h +++ b/include/uapi/drm/ivpu_accel.h @@ -305,6 +305,7 @@ struct drm_ivpu_submit { /* drm_ivpu_bo_wait job status codes */ #define DRM_IVPU_JOB_STATUS_SUCCESS 0 +#define DRM_IVPU_JOB_STATUS_ABORTED 256 /** * struct drm_ivpu_bo_wait - Wait for BO to become inactive -- cgit v1.2.3 From 292781c3c5485ce33bd22b2ef1b2bed709b4d672 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 1 Feb 2024 23:33:29 +0100 Subject: netfilter: nft_compat: reject unused compat flag Flag (1 << 0) is ignored is set, never used, reject it it with EINVAL instead. Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables") Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_compat.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index ca30232b7bc8..117c6a9b845b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -285,9 +285,11 @@ enum nft_rule_attributes { /** * enum nft_rule_compat_flags - nf_tables rule compat flags * + * @NFT_RULE_COMPAT_F_UNUSED: unused * @NFT_RULE_COMPAT_F_INV: invert the check result */ enum nft_rule_compat_flags { + NFT_RULE_COMPAT_F_UNUSED = (1 << 0), NFT_RULE_COMPAT_F_INV = (1 << 1), NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV, }; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 001b6841a4b6..ed71d5ecbe0a 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -212,7 +212,8 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; -- cgit v1.2.3 From 6c06c88fa838fcc1b7e5380facd086f57fd9d1c4 Mon Sep 17 00:00:00 2001 From: Marek Behún Date: Sun, 4 Feb 2024 15:16:46 +0100 Subject: net: mdio: add 2.5g and 5g related PMA speed constants MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add constants indicating 2.5g and 5g ability in the MMD PMA speed register. Signed-off-by: Marek Behún Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/98e15038-d96c-442f-93e4-410100d27866@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/mdio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index d03863da180e..3c9097502403 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -138,6 +138,8 @@ #define MDIO_PMA_SPEED_1000 0x0010 /* 1000M capable */ #define MDIO_PMA_SPEED_100 0x0020 /* 100M capable */ #define MDIO_PMA_SPEED_10 0x0040 /* 10M capable */ +#define MDIO_PMA_SPEED_2_5G 0x2000 /* 2.5G capable */ +#define MDIO_PMA_SPEED_5G 0x4000 /* 5G capable */ #define MDIO_PCS_SPEED_10P2B 0x0002 /* 10PASS-TS/2BASE-TL capable */ #define MDIO_PCS_SPEED_2_5G 0x0040 /* 2.5G capable */ #define MDIO_PCS_SPEED_5G 0x0080 /* 5G capable */ -- cgit v1.2.3 From a5766cd479fd212e9831ceef8e9ab630c91445ab Mon Sep 17 00:00:00 2001 From: Amadeusz Sławiński Date: Thu, 8 Feb 2024 11:23:58 +0100 Subject: ASoC: Intel: avs: UAPI: Add tokens for initial config feature MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow for defining initial config which will be send after module initialization to configure initial module state. This is only useful for modules which need to be configured on init. Reviewed-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20240208102400.2497791-2-amadeuszx.slawinski@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/intel/avs/tokens.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/intel/avs/tokens.h b/include/uapi/sound/intel/avs/tokens.h index 4ffe546aa409..4beca03405c0 100644 --- a/include/uapi/sound/intel/avs/tokens.h +++ b/include/uapi/sound/intel/avs/tokens.h @@ -19,6 +19,8 @@ enum avs_tplg_token { AVS_TKN_MANIFEST_NUM_MODCFGS_EXT_U32 = 6, AVS_TKN_MANIFEST_NUM_PPLCFGS_U32 = 7, AVS_TKN_MANIFEST_NUM_BINDINGS_U32 = 8, + AVS_TKN_MANIFEST_NUM_CONDPATH_TMPLS_U32 = 9, + AVS_TKN_MANIFEST_NUM_INIT_CONFIGS_U32 = 10, /* struct avs_tplg_library */ AVS_TKN_LIBRARY_ID_U32 = 101, @@ -109,6 +111,8 @@ enum avs_tplg_token { AVS_TKN_MOD_PROC_DOMAIN_U8 = 1705, AVS_TKN_MOD_MODCFG_EXT_ID_U32 = 1706, AVS_TKN_MOD_KCONTROL_ID_U32 = 1707, + AVS_TKN_MOD_INIT_CONFIG_NUM_IDS_U32 = 1708, + AVS_TKN_MOD_INIT_CONFIG_ID_U32 = 1709, /* struct avs_tplg_path_template */ AVS_TKN_PATH_TMPL_ID_U32 = 1801, @@ -125,6 +129,11 @@ enum avs_tplg_token { /* struct avs_tplg_kcontrol */ AVS_TKN_KCONTROL_ID_U32 = 2301, + + /* struct avs_tplg_init_config */ + AVS_TKN_INIT_CONFIG_ID_U32 = 2401, + AVS_TKN_INIT_CONFIG_PARAM_U8 = 2402, + AVS_TKN_INIT_CONFIG_LENGTH_U32 = 2403, }; #endif -- cgit v1.2.3 From 3c7a8e190bc580813ddd9259f62971c8d2a6b5ad Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 12 Dec 2023 11:15:28 -0500 Subject: uapi: introduce uapi-friendly macros for GENMASK Move __GENMASK and __GENMASK_ULL from include/ to include/uapi/ so that they can be used to define masks in userspace API headers. Compared to what is already in include/linux/bits.h, the definitions need to use the uglified versions of UL(), ULL(), BITS_PER_LONG and BITS_PER_LONG_LONG (which did not even exist), but otherwise expand to the same content. Signed-off-by: Paolo Bonzini --- include/linux/bits.h | 8 +------- include/uapi/asm-generic/bitsperlong.h | 4 ++++ include/uapi/linux/bits.h | 15 +++++++++++++++ 3 files changed, 20 insertions(+), 7 deletions(-) create mode 100644 include/uapi/linux/bits.h (limited to 'include/uapi') diff --git a/include/linux/bits.h b/include/linux/bits.h index 7c0cf5031abe..0eb24d21aac2 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -4,6 +4,7 @@ #include #include +#include #include #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) @@ -30,15 +31,8 @@ #define GENMASK_INPUT_CHECK(h, l) 0 #endif -#define __GENMASK(h, l) \ - (((~UL(0)) - (UL(1) << (l)) + 1) & \ - (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) - -#define __GENMASK_ULL(h, l) \ - (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ - (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) diff --git a/include/uapi/asm-generic/bitsperlong.h b/include/uapi/asm-generic/bitsperlong.h index 352cb81947b8..fadb3f857f28 100644 --- a/include/uapi/asm-generic/bitsperlong.h +++ b/include/uapi/asm-generic/bitsperlong.h @@ -24,4 +24,8 @@ #endif #endif +#ifndef __BITS_PER_LONG_LONG +#define __BITS_PER_LONG_LONG 64 +#endif + #endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */ diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h new file mode 100644 index 000000000000..3c2a101986a3 --- /dev/null +++ b/include/uapi/linux/bits.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* bits.h: Macros for dealing with bitmasks. */ + +#ifndef _UAPI_LINUX_BITS_H +#define _UAPI_LINUX_BITS_H + +#define __GENMASK(h, l) \ + (((~_UL(0)) - (_UL(1) << (l)) + 1) & \ + (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) + +#define __GENMASK_ULL(h, l) \ + (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ + (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* _UAPI_LINUX_BITS_H */ -- cgit v1.2.3 From c0a411904e1548d287dc4a031ff19d00e0569202 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 31 Jan 2024 18:20:47 -0500 Subject: KVM: remove more traces of device assignment UAPI Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 50 ------------------------------------------------ 1 file changed, 50 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c3308536482b..e107ea953585 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1965,56 +1965,6 @@ struct kvm_sev_receive_update_data { __u32 trans_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) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) -- cgit v1.2.3 From bcac0477277e44b0b4b5c93b24159d86eeff566a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:19:08 -0500 Subject: KVM: x86: move x86-specific structs to uapi/asm/kvm.h Several capabilities that exist only on x86 nevertheless have their structs defined in include/uapi/linux/kvm.h. Move them to arch/x86/include/uapi/asm/kvm.h for cleanliness. Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 262 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 265 ---------------------------------------- 2 files changed, 262 insertions(+), 265 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index bd36d74b593b..bf68e56fd484 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -531,6 +531,268 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for 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) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + struct { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } 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 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } 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 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e107ea953585..9744e1891c16 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1224,40 +1224,6 @@ struct kvm_irq_routing { #endif -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#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) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) -#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) -#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) -#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1737,58 +1703,6 @@ struct kvm_pv_cmd { #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 { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } 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 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* 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) @@ -1799,175 +1713,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } 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 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - /* Available with KVM_CAP_ARM_USER_IRQ */ /* Bits for run->s.regs.device_irq_level */ @@ -1975,16 +1720,6 @@ struct kvm_sev_receive_update_data { #define KVM_ARM_DEV_EL1_PTIMER (1 << 1) #define KVM_ARM_DEV_PMU (1 << 2) -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -- cgit v1.2.3 From d750951c9ed78804d775784af9f159354d9804d4 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:19:08 -0500 Subject: KVM: powerpc: move powerpc-specific structs to uapi/asm/kvm.h While this in principle breaks the appearance of KVM_PPC_* ioctls on architectures other than powerpc, this seems unlikely to be a problem considering that there are already many "struct kvm_ppc_*" definitions in arch/powerpc/include/uapi. Signed-off-by: Paolo Bonzini --- arch/powerpc/include/uapi/asm/kvm.h | 44 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 44 ------------------------------------- 2 files changed, 44 insertions(+), 44 deletions(-) (limited to 'include/uapi') diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 9f18fa090f1f..a96ef6b36bba 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -733,4 +733,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 9744e1891c16..a5458aeee018 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -810,50 +810,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ -- cgit v1.2.3 From 71cd774ad2f98d4c78bc868e7e55397810be3540 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:19:08 -0500 Subject: KVM: s390: move s390-specific structs to uapi/asm/kvm.h While this in principle breaks the appearance of KVM_S390_* ioctls on architectures other than s390, this seems unlikely to be a problem considering that there are already many "struct kvm_s390_*" definitions in arch/s390/include/uapi. Signed-off-by: Paolo Bonzini --- arch/s390/include/uapi/asm/kvm.h | 314 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 312 -------------------------------------- 2 files changed, 314 insertions(+), 312 deletions(-) (limited to 'include/uapi') diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index abe926d43cbe..fee712ff1cf8 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -14,6 +14,320 @@ #define __KVM_S390 #define __KVM_HAVE_GUEST_DEBUG +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) + /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 #define KVM_DEV_FLIC_ENQUEUE 2 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a5458aeee018..b7c8054e9d14 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -85,43 +85,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -315,11 +278,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -536,43 +494,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* types for kvm_s390_mem_op->op */ -#define KVM_S390_MEMOP_LOGICAL_READ 0 -#define KVM_S390_MEMOP_LOGICAL_WRITE 1 -#define KVM_S390_MEMOP_SIDA_READ 2 -#define KVM_S390_MEMOP_SIDA_WRITE 3 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* flags for kvm_s390_mem_op->flags */ -#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) -#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -637,124 +558,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -1364,11 +1167,6 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ -struct kvm_s390_ucas_mapping { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1563,89 +1361,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -struct kvm_s390_pv_sec_parm { - __u64 origin; - __u64 length; -}; - -struct kvm_s390_pv_unp { - __u64 addr; - __u64 size; - __u64 tweak; -}; - -enum pv_cmd_dmp_id { - KVM_PV_DUMP_INIT, - KVM_PV_DUMP_CONFIG_STOR_STATE, - KVM_PV_DUMP_COMPLETE, - KVM_PV_DUMP_CPU, -}; - -struct kvm_s390_pv_dmp { - __u64 subcmd; - __u64 buff_addr; - __u64 buff_len; - __u64 gaddr; /* For dump storage state */ - __u64 reserved[4]; -}; - -enum pv_cmd_info_id { - KVM_PV_INFO_VM, - KVM_PV_INFO_DUMP, -}; - -struct kvm_s390_pv_info_dump { - __u64 dump_cpu_buffer_len; - __u64 dump_config_mem_buffer_per_1m; - __u64 dump_config_finalize_len; -}; - -struct kvm_s390_pv_info_vm { - __u64 inst_calls_list[4]; - __u64 max_cpus; - __u64 max_guests; - __u64 max_guest_addr; - __u64 feature_indication; -}; - -struct kvm_s390_pv_info_header { - __u32 id; - __u32 len_max; - __u32 len_written; - __u32 reserved; -}; - -struct kvm_s390_pv_info { - struct kvm_s390_pv_info_header header; - union { - struct kvm_s390_pv_info_dump dump; - struct kvm_s390_pv_info_vm vm; - }; -}; - -enum pv_cmd_id { - KVM_PV_ENABLE, - KVM_PV_DISABLE, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -struct kvm_pv_cmd { - __u32 cmd; /* Command to be executed */ - __u16 rc; /* Ultravisor return code */ - __u16 rrc; /* Ultravisor return reason code */ - __u64 data; /* Data or address */ - __u32 flags; /* flags for future extensions. Must be 0 for now */ - __u32 reserved[3]; -}; - /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) @@ -1821,33 +1536,6 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_ZPCI_OP */ #define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) -struct kvm_s390_zpci_op { - /* in */ - __u32 fh; /* target device */ - __u8 op; /* operation to perform */ - __u8 pad[3]; - union { - /* for KVM_S390_ZPCIOP_REG_AEN */ - struct { - __u64 ibv; /* Guest addr of interrupt bit vector */ - __u64 sb; /* Guest addr of summary bit */ - __u32 flags; - __u32 noi; /* Number of interrupts */ - __u8 isc; /* Guest interrupt subclass */ - __u8 sbo; /* Offset of guest summary bit vector */ - __u16 pad; - } reg_aen; - __u64 reserved[8]; - } u; -}; - -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 - -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) - /* Available with KVM_CAP_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) -- cgit v1.2.3 From 5d9cb71642db11a5149c9a7234a9a62d387de449 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:19:08 -0500 Subject: KVM: arm64: move ARM-specific defines to uapi/asm/kvm.h While this in principle breaks userspace code that mentions KVM_ARM_DEV_* on architectures other than aarch64, this seems unlikely to be a problem considering that run->s.regs.device_irq_level is only defined on that architecture. Signed-off-by: Paolo Bonzini --- arch/arm64/include/uapi/asm/kvm.h | 5 +++++ include/uapi/linux/kvm.h | 7 ------- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 6b8b57b97228..75809c8dc2f0 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -162,6 +162,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b7c8054e9d14..00d5cecd057d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1384,13 +1384,6 @@ struct kvm_enc_region { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -- cgit v1.2.3 From 6bda055d625860736f7ea5b4eda816f276899d8b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:12:59 -0500 Subject: KVM: define __KVM_HAVE_GUEST_DEBUG unconditionally Since all architectures (for historical reasons) have to define struct kvm_guest_debug_arch, and since userspace has to check KVM_CHECK_EXTENSION(KVM_CAP_SET_GUEST_DEBUG) anyway, there is no advantage in masking the capability #define itself. Remove the #define __KVM_HAVE_GUEST_DEBUG from architecture-specific headers. Signed-off-by: Paolo Bonzini --- arch/arm64/include/uapi/asm/kvm.h | 1 - arch/powerpc/include/uapi/asm/kvm.h | 1 - arch/s390/include/uapi/asm/kvm.h | 1 - arch/x86/include/uapi/asm/kvm.h | 1 - include/uapi/linux/kvm.h | 7 +++++-- 5 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9c1040dad4eb..964df31da975 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -37,7 +37,6 @@ #include #include -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_VCPU_EVENTS diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index a96ef6b36bba..1691297a766a 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index fee712ff1cf8..05eaf6db3ad4 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -12,7 +12,6 @@ #include #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG struct kvm_s390_skeys { __u64 start_gfn; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c5e682ee7726..0ad6bda1fc39 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -42,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 00d5cecd057d..2ad6aa81b03f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -16,6 +16,11 @@ #define KVM_API_VERSION 12 +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -682,9 +687,7 @@ struct kvm_enable_cap { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif -- cgit v1.2.3 From db7d6fbc10447090bab8691a907a7c383ec66f58 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jan 2024 03:16:47 -0500 Subject: KVM: remove unnecessary #ifdef KVM_CAP_IRQ_ROUTING is always defined, so there is no need to check if it is. Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2ad6aa81b03f..2190adbe3002 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -918,8 +918,6 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 -#ifdef KVM_CAP_IRQ_ROUTING - struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; @@ -984,8 +982,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE -- cgit v1.2.3 From 41bcbe59c3b3fa7171dd2e3a365e6d5154198f30 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 6 Feb 2024 21:56:17 -0500 Subject: fs: FS_IOC_GETUUID Add a new generic ioctls for querying the filesystem UUID. These are lifted versions of the ext4 ioctls, with one change: we're not using a flexible array member, because UUIDs will never be more than 16 bytes. This patch adds a generic implementation of FS_IOC_GETFSUUID, which reads from super_block->s_uuid. We're not lifting SETFSUUID from ext4 - that can be done on offline filesystems by the people who need it, trying to do it online is just asking for too much trouble. Cc: Christian Brauner Cc: Jan Kara Cc: Dave Chinner Cc: Darrick J. Wong Cc: Theodore Ts'o Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Kent Overstreet Link: https://lore.kernel.org/r/20240207025624.1019754-4-kent.overstreet@linux.dev Signed-off-by: Christian Brauner --- Documentation/userspace-api/ioctl/ioctl-number.rst | 3 ++- fs/ioctl.c | 16 ++++++++++++++++ include/uapi/linux/fs.h | 15 +++++++++++++++ 3 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 457e16f06e04..3731ecf1e437 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -82,8 +82,9 @@ Code Seq# Include File Comments 0x10 00-0F drivers/char/s390/vmcp.h 0x10 10-1F arch/s390/include/uapi/sclp_ctl.h 0x10 20-2F arch/s390/include/uapi/asm/hypfs.h -0x12 all linux/fs.h +0x12 all linux/fs.h BLK* ioctls linux/blkpg.h +0x15 all linux/fs.h FS_IOC_* ioctls 0x1b all InfiniBand Subsystem 0x20 all drivers/cdrom/cm206.h diff --git a/fs/ioctl.c b/fs/ioctl.c index 76cf22ac97d7..74eab9549383 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -763,6 +763,19 @@ static int ioctl_fssetxattr(struct file *file, void __user *argp) return err; } +static int ioctl_getfsuuid(struct file *file, void __user *argp) +{ + struct super_block *sb = file_inode(file)->i_sb; + struct fsuuid2 u = { .len = sb->s_uuid_len, }; + + if (!sb->s_uuid_len) + return -ENOIOCTLCMD; + + memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); + + return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; +} + /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. @@ -845,6 +858,9 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); + case FS_IOC_GETFSUUID: + return ioctl_getfsuuid(filp, argp); + default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 48ad69f7722e..40880ce99d02 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -64,6 +64,19 @@ struct fstrim_range { __u64 minlen; }; +/* + * We include a length field because some filesystems (vfat) have an identifier + * that we do want to expose as a UUID, but doesn't have the standard length. + * + * We use a fixed size buffer beacuse this interface will, by fiat, never + * support "UUIDs" longer than 16 bytes; we don't want to force all downstream + * users to have to deal with that. + */ +struct fsuuid2 { + __u8 len; + __u8 uuid[16]; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -215,6 +228,8 @@ struct fsxattr { #define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) #define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +/* Returns the external filesystem UUID, the same one blkid returns */ +#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) -- cgit v1.2.3 From d6568e3de42dd971a1356f7ba581e6600d53f0a0 Mon Sep 17 00:00:00 2001 From: Anton Yakovlev Date: Mon, 15 Jan 2024 14:36:54 +0100 Subject: ALSA: virtio: add support for audio controls Implementation of support for audio controls in accordance with the extension of the virtio sound device specification [1] planned for virtio-v1.3-cs01. The device can announce the VIRTIO_SND_F_CTLS feature. If the feature is negotiated, then an additional field appears in the configuration space: struct virtio_snd_config { ... /* number of available control elements */ __le32 controls; }; The driver can send the following requests to manage audio controls: enum { ... /* control element request types */ VIRTIO_SND_R_CTL_INFO = 0x0300, VIRTIO_SND_R_CTL_ENUM_ITEMS, VIRTIO_SND_R_CTL_READ, VIRTIO_SND_R_CTL_WRITE, VIRTIO_SND_R_CTL_TLV_READ, VIRTIO_SND_R_CTL_TLV_WRITE, VIRTIO_SND_R_CTL_TLV_COMMAND, ... }; And the device can send the following audio control event notification: enum { ... /* control element event types */ VIRTIO_SND_EVT_CTL_NOTIFY = 0x1200, ... }; See additional details in [1]. [1] https://lists.oasis-open.org/archives/virtio-comment/202104/msg00013.html Signed-off-by: Anton Yakovlev Signed-off-by: Aiswarya Cyriac Link: https://lore.kernel.org/r/20240115133654.576068-2-aiswarya.cyriac@opensynergy.com Signed-off-by: Takashi Iwai --- include/uapi/linux/virtio_snd.h | 154 +++++++++++++ sound/virtio/Makefile | 1 + sound/virtio/virtio_card.c | 21 ++ sound/virtio/virtio_card.h | 22 ++ sound/virtio/virtio_kctl.c | 466 ++++++++++++++++++++++++++++++++++++++++ 5 files changed, 664 insertions(+) create mode 100644 sound/virtio/virtio_kctl.c (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_snd.h b/include/uapi/linux/virtio_snd.h index dfe49547a7b0..5f4100c2cf04 100644 --- a/include/uapi/linux/virtio_snd.h +++ b/include/uapi/linux/virtio_snd.h @@ -7,6 +7,14 @@ #include +/******************************************************************************* + * FEATURE BITS + */ +enum { + /* device supports control elements */ + VIRTIO_SND_F_CTLS = 0 +}; + /******************************************************************************* * CONFIGURATION SPACE */ @@ -17,6 +25,8 @@ struct virtio_snd_config { __le32 streams; /* # of available channel maps */ __le32 chmaps; + /* # of available control elements */ + __le32 controls; }; enum { @@ -55,6 +65,15 @@ enum { /* channel map control request types */ VIRTIO_SND_R_CHMAP_INFO = 0x0200, + /* control element request types */ + VIRTIO_SND_R_CTL_INFO = 0x0300, + VIRTIO_SND_R_CTL_ENUM_ITEMS, + VIRTIO_SND_R_CTL_READ, + VIRTIO_SND_R_CTL_WRITE, + VIRTIO_SND_R_CTL_TLV_READ, + VIRTIO_SND_R_CTL_TLV_WRITE, + VIRTIO_SND_R_CTL_TLV_COMMAND, + /* jack event types */ VIRTIO_SND_EVT_JACK_CONNECTED = 0x1000, VIRTIO_SND_EVT_JACK_DISCONNECTED, @@ -63,6 +82,9 @@ enum { VIRTIO_SND_EVT_PCM_PERIOD_ELAPSED = 0x1100, VIRTIO_SND_EVT_PCM_XRUN, + /* control element event types */ + VIRTIO_SND_EVT_CTL_NOTIFY = 0x1200, + /* common status codes */ VIRTIO_SND_S_OK = 0x8000, VIRTIO_SND_S_BAD_MSG, @@ -331,4 +353,136 @@ struct virtio_snd_chmap_info { __u8 positions[VIRTIO_SND_CHMAP_MAX_SIZE]; }; +/******************************************************************************* + * CONTROL ELEMENTS MESSAGES + */ +struct virtio_snd_ctl_hdr { + /* VIRTIO_SND_R_CTL_XXX */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::controls - 1 */ + __le32 control_id; +}; + +/* supported roles for control elements */ +enum { + VIRTIO_SND_CTL_ROLE_UNDEFINED = 0, + VIRTIO_SND_CTL_ROLE_VOLUME, + VIRTIO_SND_CTL_ROLE_MUTE, + VIRTIO_SND_CTL_ROLE_GAIN +}; + +/* supported value types for control elements */ +enum { + VIRTIO_SND_CTL_TYPE_BOOLEAN = 0, + VIRTIO_SND_CTL_TYPE_INTEGER, + VIRTIO_SND_CTL_TYPE_INTEGER64, + VIRTIO_SND_CTL_TYPE_ENUMERATED, + VIRTIO_SND_CTL_TYPE_BYTES, + VIRTIO_SND_CTL_TYPE_IEC958 +}; + +/* supported access rights for control elements */ +enum { + VIRTIO_SND_CTL_ACCESS_READ = 0, + VIRTIO_SND_CTL_ACCESS_WRITE, + VIRTIO_SND_CTL_ACCESS_VOLATILE, + VIRTIO_SND_CTL_ACCESS_INACTIVE, + VIRTIO_SND_CTL_ACCESS_TLV_READ, + VIRTIO_SND_CTL_ACCESS_TLV_WRITE, + VIRTIO_SND_CTL_ACCESS_TLV_COMMAND +}; + +struct virtio_snd_ctl_info { + /* common header */ + struct virtio_snd_info hdr; + /* element role (VIRTIO_SND_CTL_ROLE_XXX) */ + __le32 role; + /* element value type (VIRTIO_SND_CTL_TYPE_XXX) */ + __le32 type; + /* element access right bit map (1 << VIRTIO_SND_CTL_ACCESS_XXX) */ + __le32 access; + /* # of members in the element value */ + __le32 count; + /* index for an element with a non-unique name */ + __le32 index; + /* name identifier string for the element */ + __u8 name[44]; + /* additional information about the element's value */ + union { + /* VIRTIO_SND_CTL_TYPE_INTEGER */ + struct { + /* minimum supported value */ + __le32 min; + /* maximum supported value */ + __le32 max; + /* fixed step size for value (0 = variable size) */ + __le32 step; + } integer; + /* VIRTIO_SND_CTL_TYPE_INTEGER64 */ + struct { + /* minimum supported value */ + __le64 min; + /* maximum supported value */ + __le64 max; + /* fixed step size for value (0 = variable size) */ + __le64 step; + } integer64; + /* VIRTIO_SND_CTL_TYPE_ENUMERATED */ + struct { + /* # of options supported for value */ + __le32 items; + } enumerated; + } value; +}; + +struct virtio_snd_ctl_enum_item { + /* option name */ + __u8 item[64]; +}; + +struct virtio_snd_ctl_iec958 { + /* AES/IEC958 channel status bits */ + __u8 status[24]; + /* AES/IEC958 subcode bits */ + __u8 subcode[147]; + /* nothing */ + __u8 pad; + /* AES/IEC958 subframe bits */ + __u8 dig_subframe[4]; +}; + +struct virtio_snd_ctl_value { + union { + /* VIRTIO_SND_CTL_TYPE_BOOLEAN|INTEGER value */ + __le32 integer[128]; + /* VIRTIO_SND_CTL_TYPE_INTEGER64 value */ + __le64 integer64[64]; + /* VIRTIO_SND_CTL_TYPE_ENUMERATED value (option indexes) */ + __le32 enumerated[128]; + /* VIRTIO_SND_CTL_TYPE_BYTES value */ + __u8 bytes[512]; + /* VIRTIO_SND_CTL_TYPE_IEC958 value */ + struct virtio_snd_ctl_iec958 iec958; + } value; +}; + +/* supported event reason types */ +enum { + /* element's value has changed */ + VIRTIO_SND_CTL_EVT_MASK_VALUE = 0, + /* element's information has changed */ + VIRTIO_SND_CTL_EVT_MASK_INFO, + /* element's metadata has changed */ + VIRTIO_SND_CTL_EVT_MASK_TLV +}; + +struct virtio_snd_ctl_event { + /* VIRTIO_SND_EVT_CTL_NOTIFY */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::controls - 1 */ + __le16 control_id; + /* event reason bit map (1 << VIRTIO_SND_CTL_EVT_MASK_XXX) */ + __le16 mask; +}; + #endif /* VIRTIO_SND_IF_H */ diff --git a/sound/virtio/Makefile b/sound/virtio/Makefile index 2742bddb8874..a839f8c8b5e6 100644 --- a/sound/virtio/Makefile +++ b/sound/virtio/Makefile @@ -7,6 +7,7 @@ virtio_snd-objs := \ virtio_chmap.o \ virtio_ctl_msg.o \ virtio_jack.o \ + virtio_kctl.o \ virtio_pcm.o \ virtio_pcm_msg.o \ virtio_pcm_ops.o diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c index b158c3cb8e5f..2da20c625247 100644 --- a/sound/virtio/virtio_card.c +++ b/sound/virtio/virtio_card.c @@ -64,6 +64,9 @@ static void virtsnd_event_dispatch(struct virtio_snd *snd, case VIRTIO_SND_EVT_PCM_XRUN: virtsnd_pcm_event(snd, event); break; + case VIRTIO_SND_EVT_CTL_NOTIFY: + virtsnd_kctl_event(snd, event); + break; } } @@ -233,6 +236,12 @@ static int virtsnd_build_devs(struct virtio_snd *snd) if (rc) return rc; + if (virtio_has_feature(vdev, VIRTIO_SND_F_CTLS)) { + rc = virtsnd_kctl_parse_cfg(snd); + if (rc) + return rc; + } + if (snd->njacks) { rc = virtsnd_jack_build_devs(snd); if (rc) @@ -251,6 +260,12 @@ static int virtsnd_build_devs(struct virtio_snd *snd) return rc; } + if (snd->nkctls) { + rc = virtsnd_kctl_build_devs(snd); + if (rc) + return rc; + } + return snd_card_register(snd->card); } @@ -417,10 +432,16 @@ static const struct virtio_device_id id_table[] = { { 0 }, }; +static unsigned int features[] = { + VIRTIO_SND_F_CTLS +}; + static struct virtio_driver virtsnd_driver = { .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .validate = virtsnd_validate, .probe = virtsnd_probe, .remove = virtsnd_remove, diff --git a/sound/virtio/virtio_card.h b/sound/virtio/virtio_card.h index 86ef3941895e..3ceee4e416fc 100644 --- a/sound/virtio/virtio_card.h +++ b/sound/virtio/virtio_card.h @@ -31,6 +31,16 @@ struct virtio_snd_queue { struct virtqueue *vqueue; }; +/** + * struct virtio_kctl - VirtIO control element. + * @kctl: ALSA control element. + * @items: Items for the ENUMERATED element type. + */ +struct virtio_kctl { + struct snd_kcontrol *kctl; + struct virtio_snd_ctl_enum_item *items; +}; + /** * struct virtio_snd - VirtIO sound card device. * @vdev: Underlying virtio device. @@ -45,6 +55,9 @@ struct virtio_snd_queue { * @nsubstreams: Number of PCM substreams. * @chmaps: VirtIO channel maps. * @nchmaps: Number of channel maps. + * @kctl_infos: VirtIO control element information. + * @kctls: VirtIO control elements. + * @nkctls: Number of control elements. */ struct virtio_snd { struct virtio_device *vdev; @@ -59,6 +72,9 @@ struct virtio_snd { u32 nsubstreams; struct virtio_snd_chmap_info *chmaps; u32 nchmaps; + struct virtio_snd_ctl_info *kctl_infos; + struct virtio_kctl *kctls; + u32 nkctls; }; /* Message completion timeout in milliseconds (module parameter). */ @@ -108,4 +124,10 @@ int virtsnd_chmap_parse_cfg(struct virtio_snd *snd); int virtsnd_chmap_build_devs(struct virtio_snd *snd); +int virtsnd_kctl_parse_cfg(struct virtio_snd *snd); + +int virtsnd_kctl_build_devs(struct virtio_snd *snd); + +void virtsnd_kctl_event(struct virtio_snd *snd, struct virtio_snd_event *event); + #endif /* VIRTIO_SND_CARD_H */ diff --git a/sound/virtio/virtio_kctl.c b/sound/virtio/virtio_kctl.c new file mode 100644 index 000000000000..0c6ac74aca1e --- /dev/null +++ b/sound/virtio/virtio_kctl.c @@ -0,0 +1,466 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * virtio-snd: Virtio sound device + * Copyright (C) 2022 OpenSynergy GmbH + */ +#include +#include + +#include "virtio_card.h" + +/* Map for converting VirtIO types to ALSA types. */ +static const snd_ctl_elem_type_t g_v2a_type_map[] = { + [VIRTIO_SND_CTL_TYPE_BOOLEAN] = SNDRV_CTL_ELEM_TYPE_BOOLEAN, + [VIRTIO_SND_CTL_TYPE_INTEGER] = SNDRV_CTL_ELEM_TYPE_INTEGER, + [VIRTIO_SND_CTL_TYPE_INTEGER64] = SNDRV_CTL_ELEM_TYPE_INTEGER64, + [VIRTIO_SND_CTL_TYPE_ENUMERATED] = SNDRV_CTL_ELEM_TYPE_ENUMERATED, + [VIRTIO_SND_CTL_TYPE_BYTES] = SNDRV_CTL_ELEM_TYPE_BYTES, + [VIRTIO_SND_CTL_TYPE_IEC958] = SNDRV_CTL_ELEM_TYPE_IEC958 +}; + +/* Map for converting VirtIO access rights to ALSA access rights. */ +static const unsigned int g_v2a_access_map[] = { + [VIRTIO_SND_CTL_ACCESS_READ] = SNDRV_CTL_ELEM_ACCESS_READ, + [VIRTIO_SND_CTL_ACCESS_WRITE] = SNDRV_CTL_ELEM_ACCESS_WRITE, + [VIRTIO_SND_CTL_ACCESS_VOLATILE] = SNDRV_CTL_ELEM_ACCESS_VOLATILE, + [VIRTIO_SND_CTL_ACCESS_INACTIVE] = SNDRV_CTL_ELEM_ACCESS_INACTIVE, + [VIRTIO_SND_CTL_ACCESS_TLV_READ] = SNDRV_CTL_ELEM_ACCESS_TLV_READ, + [VIRTIO_SND_CTL_ACCESS_TLV_WRITE] = SNDRV_CTL_ELEM_ACCESS_TLV_WRITE, + [VIRTIO_SND_CTL_ACCESS_TLV_COMMAND] = SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND +}; + +/* Map for converting VirtIO event masks to ALSA event masks. */ +static const unsigned int g_v2a_mask_map[] = { + [VIRTIO_SND_CTL_EVT_MASK_VALUE] = SNDRV_CTL_EVENT_MASK_VALUE, + [VIRTIO_SND_CTL_EVT_MASK_INFO] = SNDRV_CTL_EVENT_MASK_INFO, + [VIRTIO_SND_CTL_EVT_MASK_TLV] = SNDRV_CTL_EVENT_MASK_TLV +}; + +/** + * virtsnd_kctl_info() - Returns information about the control. + * @kcontrol: ALSA control element. + * @uinfo: Element information. + * + * Context: Process context. + * Return: 0 on success, -errno on failure. + */ +static int virtsnd_kctl_info(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_info *uinfo) +{ + struct virtio_snd *snd = kcontrol->private_data; + struct virtio_kctl *kctl = &snd->kctls[kcontrol->private_value]; + struct virtio_snd_ctl_info *kinfo = + &snd->kctl_infos[kcontrol->private_value]; + unsigned int i; + + uinfo->type = g_v2a_type_map[le32_to_cpu(kinfo->type)]; + uinfo->count = le32_to_cpu(kinfo->count); + + switch (uinfo->type) { + case SNDRV_CTL_ELEM_TYPE_INTEGER: + uinfo->value.integer.min = + le32_to_cpu(kinfo->value.integer.min); + uinfo->value.integer.max = + le32_to_cpu(kinfo->value.integer.max); + uinfo->value.integer.step = + le32_to_cpu(kinfo->value.integer.step); + + break; + case SNDRV_CTL_ELEM_TYPE_INTEGER64: + uinfo->value.integer64.min = + le64_to_cpu(kinfo->value.integer64.min); + uinfo->value.integer64.max = + le64_to_cpu(kinfo->value.integer64.max); + uinfo->value.integer64.step = + le64_to_cpu(kinfo->value.integer64.step); + + break; + case SNDRV_CTL_ELEM_TYPE_ENUMERATED: + uinfo->value.enumerated.items = + le32_to_cpu(kinfo->value.enumerated.items); + i = uinfo->value.enumerated.item; + if (i >= uinfo->value.enumerated.items) + return -EINVAL; + + strscpy(uinfo->value.enumerated.name, kctl->items[i].item, + sizeof(uinfo->value.enumerated.name)); + + break; + } + + return 0; +} + +/** + * virtsnd_kctl_get() - Read the value from the control. + * @kcontrol: ALSA control element. + * @uvalue: Element value. + * + * Context: Process context. + * Return: 0 on success, -errno on failure. + */ +static int virtsnd_kctl_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *uvalue) +{ + struct virtio_snd *snd = kcontrol->private_data; + struct virtio_snd_ctl_info *kinfo = + &snd->kctl_infos[kcontrol->private_value]; + unsigned int type = le32_to_cpu(kinfo->type); + unsigned int count = le32_to_cpu(kinfo->count); + struct virtio_snd_msg *msg; + struct virtio_snd_ctl_hdr *hdr; + struct virtio_snd_ctl_value *kvalue; + size_t request_size = sizeof(*hdr); + size_t response_size = sizeof(struct virtio_snd_hdr) + sizeof(*kvalue); + unsigned int i; + int rc; + + msg = virtsnd_ctl_msg_alloc(request_size, response_size, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + virtsnd_ctl_msg_ref(msg); + + hdr = virtsnd_ctl_msg_request(msg); + hdr->hdr.code = cpu_to_le32(VIRTIO_SND_R_CTL_READ); + hdr->control_id = cpu_to_le32(kcontrol->private_value); + + rc = virtsnd_ctl_msg_send_sync(snd, msg); + if (rc) + goto on_failure; + + kvalue = (void *)((u8 *)virtsnd_ctl_msg_response(msg) + + sizeof(struct virtio_snd_hdr)); + + switch (type) { + case VIRTIO_SND_CTL_TYPE_BOOLEAN: + case VIRTIO_SND_CTL_TYPE_INTEGER: + for (i = 0; i < count; ++i) + uvalue->value.integer.value[i] = + le32_to_cpu(kvalue->value.integer[i]); + break; + case VIRTIO_SND_CTL_TYPE_INTEGER64: + for (i = 0; i < count; ++i) + uvalue->value.integer64.value[i] = + le64_to_cpu(kvalue->value.integer64[i]); + break; + case VIRTIO_SND_CTL_TYPE_ENUMERATED: + for (i = 0; i < count; ++i) + uvalue->value.enumerated.item[i] = + le32_to_cpu(kvalue->value.enumerated[i]); + break; + case VIRTIO_SND_CTL_TYPE_BYTES: + memcpy(uvalue->value.bytes.data, kvalue->value.bytes, count); + break; + case VIRTIO_SND_CTL_TYPE_IEC958: + memcpy(&uvalue->value.iec958, &kvalue->value.iec958, + sizeof(uvalue->value.iec958)); + break; + } + +on_failure: + virtsnd_ctl_msg_unref(msg); + + return rc; +} + +/** + * virtsnd_kctl_put() - Write the value to the control. + * @kcontrol: ALSA control element. + * @uvalue: Element value. + * + * Context: Process context. + * Return: 0 on success, -errno on failure. + */ +static int virtsnd_kctl_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *uvalue) +{ + struct virtio_snd *snd = kcontrol->private_data; + struct virtio_snd_ctl_info *kinfo = + &snd->kctl_infos[kcontrol->private_value]; + unsigned int type = le32_to_cpu(kinfo->type); + unsigned int count = le32_to_cpu(kinfo->count); + struct virtio_snd_msg *msg; + struct virtio_snd_ctl_hdr *hdr; + struct virtio_snd_ctl_value *kvalue; + size_t request_size = sizeof(*hdr) + sizeof(*kvalue); + size_t response_size = sizeof(struct virtio_snd_hdr); + unsigned int i; + + msg = virtsnd_ctl_msg_alloc(request_size, response_size, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = virtsnd_ctl_msg_request(msg); + hdr->hdr.code = cpu_to_le32(VIRTIO_SND_R_CTL_WRITE); + hdr->control_id = cpu_to_le32(kcontrol->private_value); + + kvalue = (void *)((u8 *)hdr + sizeof(*hdr)); + + switch (type) { + case VIRTIO_SND_CTL_TYPE_BOOLEAN: + case VIRTIO_SND_CTL_TYPE_INTEGER: + for (i = 0; i < count; ++i) + kvalue->value.integer[i] = + cpu_to_le32(uvalue->value.integer.value[i]); + break; + case VIRTIO_SND_CTL_TYPE_INTEGER64: + for (i = 0; i < count; ++i) + kvalue->value.integer64[i] = + cpu_to_le64(uvalue->value.integer64.value[i]); + break; + case VIRTIO_SND_CTL_TYPE_ENUMERATED: + for (i = 0; i < count; ++i) + kvalue->value.enumerated[i] = + cpu_to_le32(uvalue->value.enumerated.item[i]); + break; + case VIRTIO_SND_CTL_TYPE_BYTES: + memcpy(kvalue->value.bytes, uvalue->value.bytes.data, count); + break; + case VIRTIO_SND_CTL_TYPE_IEC958: + memcpy(&kvalue->value.iec958, &uvalue->value.iec958, + sizeof(kvalue->value.iec958)); + break; + } + + return virtsnd_ctl_msg_send_sync(snd, msg); +} + +/** + * virtsnd_kctl_tlv_op() - Perform an operation on the control's metadata. + * @kcontrol: ALSA control element. + * @op_flag: Operation code (SNDRV_CTL_TLV_OP_XXX). + * @size: Size of the TLV data in bytes. + * @utlv: TLV data. + * + * Context: Process context. + * Return: 0 on success, -errno on failure. + */ +static int virtsnd_kctl_tlv_op(struct snd_kcontrol *kcontrol, int op_flag, + unsigned int size, unsigned int __user *utlv) +{ + struct virtio_snd *snd = kcontrol->private_data; + struct virtio_snd_msg *msg; + struct virtio_snd_ctl_hdr *hdr; + unsigned int *tlv; + struct scatterlist sg; + int rc; + + msg = virtsnd_ctl_msg_alloc(sizeof(*hdr), sizeof(struct virtio_snd_hdr), + GFP_KERNEL); + if (!msg) + return -ENOMEM; + + tlv = kzalloc(size, GFP_KERNEL); + if (!tlv) { + virtsnd_ctl_msg_unref(msg); + return -ENOMEM; + } + + sg_init_one(&sg, tlv, size); + + hdr = virtsnd_ctl_msg_request(msg); + hdr->control_id = cpu_to_le32(kcontrol->private_value); + + switch (op_flag) { + case SNDRV_CTL_TLV_OP_READ: + hdr->hdr.code = cpu_to_le32(VIRTIO_SND_R_CTL_TLV_READ); + + rc = virtsnd_ctl_msg_send(snd, msg, NULL, &sg, false); + if (!rc) { + if (copy_to_user(utlv, tlv, size)) + rc = -EFAULT; + } + + break; + case SNDRV_CTL_TLV_OP_WRITE: + case SNDRV_CTL_TLV_OP_CMD: + if (op_flag == SNDRV_CTL_TLV_OP_WRITE) + hdr->hdr.code = cpu_to_le32(VIRTIO_SND_R_CTL_TLV_WRITE); + else + hdr->hdr.code = + cpu_to_le32(VIRTIO_SND_R_CTL_TLV_COMMAND); + + if (copy_from_user(tlv, utlv, size)) + rc = -EFAULT; + else + rc = virtsnd_ctl_msg_send(snd, msg, &sg, NULL, false); + + break; + } + + kfree(tlv); + + return rc; +} + +/** + * virtsnd_kctl_get_enum_items() - Query items for the ENUMERATED element type. + * @snd: VirtIO sound device. + * @cid: Control element ID. + * + * This function is called during initial device initialization. + * + * Context: Any context that permits to sleep. + * Return: 0 on success, -errno on failure. + */ +static int virtsnd_kctl_get_enum_items(struct virtio_snd *snd, unsigned int cid) +{ + struct virtio_device *vdev = snd->vdev; + struct virtio_snd_ctl_info *kinfo = &snd->kctl_infos[cid]; + struct virtio_kctl *kctl = &snd->kctls[cid]; + struct virtio_snd_msg *msg; + struct virtio_snd_ctl_hdr *hdr; + unsigned int n = le32_to_cpu(kinfo->value.enumerated.items); + struct scatterlist sg; + + msg = virtsnd_ctl_msg_alloc(sizeof(*hdr), + sizeof(struct virtio_snd_hdr), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + kctl->items = devm_kcalloc(&vdev->dev, n, sizeof(*kctl->items), + GFP_KERNEL); + if (!kctl->items) { + virtsnd_ctl_msg_unref(msg); + return -ENOMEM; + } + + sg_init_one(&sg, kctl->items, n * sizeof(*kctl->items)); + + hdr = virtsnd_ctl_msg_request(msg); + hdr->hdr.code = cpu_to_le32(VIRTIO_SND_R_CTL_ENUM_ITEMS); + hdr->control_id = cpu_to_le32(cid); + + return virtsnd_ctl_msg_send(snd, msg, NULL, &sg, false); +} + +/** + * virtsnd_kctl_parse_cfg() - Parse the control element configuration. + * @snd: VirtIO sound device. + * + * This function is called during initial device initialization. + * + * Context: Any context that permits to sleep. + * Return: 0 on success, -errno on failure. + */ +int virtsnd_kctl_parse_cfg(struct virtio_snd *snd) +{ + struct virtio_device *vdev = snd->vdev; + u32 i; + int rc; + + virtio_cread_le(vdev, struct virtio_snd_config, controls, + &snd->nkctls); + if (!snd->nkctls) + return 0; + + snd->kctl_infos = devm_kcalloc(&vdev->dev, snd->nkctls, + sizeof(*snd->kctl_infos), GFP_KERNEL); + if (!snd->kctl_infos) + return -ENOMEM; + + snd->kctls = devm_kcalloc(&vdev->dev, snd->nkctls, sizeof(*snd->kctls), + GFP_KERNEL); + if (!snd->kctls) + return -ENOMEM; + + rc = virtsnd_ctl_query_info(snd, VIRTIO_SND_R_CTL_INFO, 0, snd->nkctls, + sizeof(*snd->kctl_infos), snd->kctl_infos); + if (rc) + return rc; + + for (i = 0; i < snd->nkctls; ++i) { + struct virtio_snd_ctl_info *kinfo = &snd->kctl_infos[i]; + unsigned int type = le32_to_cpu(kinfo->type); + + if (type == VIRTIO_SND_CTL_TYPE_ENUMERATED) { + rc = virtsnd_kctl_get_enum_items(snd, i); + if (rc) + return rc; + } + } + + return 0; +} + +/** + * virtsnd_kctl_build_devs() - Build ALSA control elements. + * @snd: VirtIO sound device. + * + * Context: Any context that permits to sleep. + * Return: 0 on success, -errno on failure. + */ +int virtsnd_kctl_build_devs(struct virtio_snd *snd) +{ + unsigned int cid; + + for (cid = 0; cid < snd->nkctls; ++cid) { + struct virtio_snd_ctl_info *kinfo = &snd->kctl_infos[cid]; + struct virtio_kctl *kctl = &snd->kctls[cid]; + struct snd_kcontrol_new kctl_new; + unsigned int i; + int rc; + + memset(&kctl_new, 0, sizeof(kctl_new)); + + kctl_new.iface = SNDRV_CTL_ELEM_IFACE_MIXER; + kctl_new.name = kinfo->name; + kctl_new.index = le32_to_cpu(kinfo->index); + + for (i = 0; i < ARRAY_SIZE(g_v2a_access_map); ++i) + if (le32_to_cpu(kinfo->access) & (1 << i)) + kctl_new.access |= g_v2a_access_map[i]; + + if (kctl_new.access & (SNDRV_CTL_ELEM_ACCESS_TLV_READ | + SNDRV_CTL_ELEM_ACCESS_TLV_WRITE | + SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND)) { + kctl_new.access |= SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK; + kctl_new.tlv.c = virtsnd_kctl_tlv_op; + } + + kctl_new.info = virtsnd_kctl_info; + kctl_new.get = virtsnd_kctl_get; + kctl_new.put = virtsnd_kctl_put; + kctl_new.private_value = cid; + + kctl->kctl = snd_ctl_new1(&kctl_new, snd); + if (!kctl->kctl) + return -ENOMEM; + + rc = snd_ctl_add(snd->card, kctl->kctl); + if (rc) + return rc; + } + + return 0; +} + +/** + * virtsnd_kctl_event() - Handle the control element event notification. + * @snd: VirtIO sound device. + * @event: VirtIO sound event. + * + * Context: Interrupt context. + */ +void virtsnd_kctl_event(struct virtio_snd *snd, struct virtio_snd_event *event) +{ + struct virtio_snd_ctl_event *kevent = + (struct virtio_snd_ctl_event *)event; + struct virtio_kctl *kctl; + unsigned int cid = le16_to_cpu(kevent->control_id); + unsigned int mask = 0; + unsigned int i; + + if (cid >= snd->nkctls) + return; + + for (i = 0; i < ARRAY_SIZE(g_v2a_mask_map); ++i) + if (le16_to_cpu(kevent->mask) & (1 << i)) + mask |= g_v2a_mask_map[i]; + + + kctl = &snd->kctls[cid]; + + snd_ctl_notify(snd->card, mask, &kctl->kctl->id); +} -- cgit v1.2.3 From b4bb1900c12e6a0fe11ff51e1aa6eea19a4ad635 Mon Sep 17 00:00:00 2001 From: Tony Solomonik Date: Fri, 2 Feb 2024 14:17:24 +0200 Subject: io_uring: add support for ftruncate Adds support for doing truncate through io_uring, eliminating the need for applications to roll their own thread pool or offload mechanism to be able to do non-blocking truncates. Signed-off-by: Tony Solomonik Link: https://lore.kernel.org/r/20240202121724.17461-3-tony.solomonik@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/Makefile | 2 +- io_uring/opdef.c | 10 +++++++++ io_uring/truncate.c | 48 +++++++++++++++++++++++++++++++++++++++++++ io_uring/truncate.h | 4 ++++ 5 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 io_uring/truncate.c create mode 100644 io_uring/truncate.h (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7a673b52827b..fb812f1b6bb5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -255,6 +255,7 @@ enum io_uring_op { IORING_OP_FUTEX_WAKE, IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, + IORING_OP_FTRUNCATE, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/Makefile b/io_uring/Makefile index 2cdc51825405..42afe4a1ff31 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -8,6 +8,6 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ statx.o net.o msg_ring.o timeout.o \ sqpoll.o fdinfo.o tctx.o poll.o \ cancel.o kbuf.o rsrc.o rw.o opdef.o \ - notif.o waitid.o register.o + notif.o waitid.o register.o truncate.o obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FUTEX) += futex.o diff --git a/io_uring/opdef.c b/io_uring/opdef.c index b1ee3a9c3807..9c080aadc5a6 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -35,6 +35,7 @@ #include "rw.h" #include "waitid.h" #include "futex.h" +#include "truncate.h" static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) { @@ -474,6 +475,12 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_install_fixed_fd_prep, .issue = io_install_fixed_fd, }, + [IORING_OP_FTRUNCATE] = { + .needs_file = 1, + .hash_reg_file = 1, + .prep = io_ftruncate_prep, + .issue = io_ftruncate, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -712,6 +719,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FIXED_FD_INSTALL] = { .name = "FIXED_FD_INSTALL", }, + [IORING_OP_FTRUNCATE] = { + .name = "FTRUNCATE", + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/truncate.c b/io_uring/truncate.c new file mode 100644 index 000000000000..62ee73d34d72 --- /dev/null +++ b/io_uring/truncate.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "../fs/internal.h" + +#include "io_uring.h" +#include "truncate.h" + +struct io_ftrunc { + struct file *file; + loff_t len; +}; + +int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc); + + if (sqe->rw_flags || sqe->addr || sqe->len || sqe->buf_index || + sqe->splice_fd_in || sqe->addr3) + return -EINVAL; + + ft->len = READ_ONCE(sqe->off); + + req->flags |= REQ_F_FORCE_ASYNC; + return 0; +} + +int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc); + int ret; + + WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); + + ret = do_ftruncate(req->file, ft->len, 1); + + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/truncate.h b/io_uring/truncate.h new file mode 100644 index 000000000000..ec088293a478 --- /dev/null +++ b/io_uring/truncate.h @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 + +int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags); -- cgit v1.2.3 From ef1186c1a875bfa8a8cbfc2a9670b14b082187a9 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Thu, 8 Jun 2023 09:38:38 -0700 Subject: io_uring: add register/unregister napi function This adds an api to register and unregister the napi for io-uring. If the arg value is specified when unregistering, the current napi setting for the busy poll timeout is copied into the user structure. If this is not required, NULL can be passed as the arg value. Signed-off-by: Stefan Roesch Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230608163839.2891748-7-shr@devkernel.io Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 ++++++++++ io_uring/napi.c | 52 +++++++++++++++++++++++++++++++++++++++++++ io_uring/napi.h | 11 +++++++++ io_uring/register.c | 13 +++++++++++ 4 files changed, 88 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index fb812f1b6bb5..7bd10201a02b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -571,6 +571,10 @@ enum { /* return status information for a buffer group */ IORING_REGISTER_PBUF_STATUS = 26, + /* set/clear busy poll settings */ + IORING_REGISTER_NAPI = 27, + IORING_UNREGISTER_NAPI = 28, + /* this goes last */ IORING_REGISTER_LAST, @@ -704,6 +708,14 @@ struct io_uring_buf_status { __u32 resv[8]; }; +/* argument for IORING_(UN)REGISTER_NAPI */ +struct io_uring_napi { + __u32 busy_poll_to; + __u8 prefer_busy_poll; + __u8 pad[3]; + __u64 resv; +}; + /* * io_uring_restriction->opcode values */ diff --git a/io_uring/napi.c b/io_uring/napi.c index 3e578df36cc5..8ec016899539 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -207,6 +207,58 @@ void io_napi_free(struct io_ring_ctx *ctx) spin_unlock(&ctx->napi_lock); } +/* + * io_napi_register() - Register napi with io-uring + * @ctx: pointer to io-uring context structure + * @arg: pointer to io_uring_napi structure + * + * Register napi in the io-uring context. + */ +int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll + }; + struct io_uring_napi napi; + + if (copy_from_user(&napi, arg, sizeof(napi))) + return -EFAULT; + if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv) + return -EINVAL; + + WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to); + WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll); + + if (copy_to_user(arg, &curr, sizeof(curr))) + return -EFAULT; + + return 0; +} + +/* + * io_napi_unregister() - Unregister napi with io-uring + * @ctx: pointer to io-uring context structure + * @arg: pointer to io_uring_napi structure + * + * Unregister napi. If arg has been specified copy the busy poll timeout and + * prefer busy poll setting to the passed in structure. + */ +int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll + }; + + if (arg && copy_to_user(arg, &curr, sizeof(curr))) + return -EFAULT; + + WRITE_ONCE(ctx->napi_busy_poll_to, 0); + WRITE_ONCE(ctx->napi_prefer_busy_poll, false); + return 0; +} + /* * __io_napi_adjust_timeout() - Add napi id to the busy poll list * @ctx: pointer to io-uring context structure diff --git a/io_uring/napi.h b/io_uring/napi.h index b6d6243fc7fe..6fc0393d0dbe 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -12,6 +12,9 @@ void io_napi_init(struct io_ring_ctx *ctx); void io_napi_free(struct io_ring_ctx *ctx); +int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); +int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); + void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock); void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, @@ -68,6 +71,14 @@ static inline void io_napi_init(struct io_ring_ctx *ctx) static inline void io_napi_free(struct io_ring_ctx *ctx) { } +static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + return -EOPNOTSUPP; +} +static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + return -EOPNOTSUPP; +} static inline bool io_napi(struct io_ring_ctx *ctx) { return false; diff --git a/io_uring/register.c b/io_uring/register.c index 5e62c1208996..99c37775f974 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -26,6 +26,7 @@ #include "register.h" #include "cancel.h" #include "kbuf.h" +#include "napi.h" #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) @@ -550,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_pbuf_status(ctx, arg); break; + case IORING_REGISTER_NAPI: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_napi(ctx, arg); + break; + case IORING_UNREGISTER_NAPI: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_unregister_napi(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit v1.2.3 From ae8c511757304e0c393661b5ed2ad7073e2a351d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 6 Feb 2024 21:56:19 -0500 Subject: fs: add FS_IOC_GETFSSYSFSPATH Add a new ioctl for getting the sysfs name of a filesystem - the path under /sys/fs. This is going to let us standardize exporting data from sysfs across filesystems, e.g. time stats. The returned path will always be of the form "$FSTYP/$SYSFS_IDENTIFIER", where the sysfs identifier may be a UUID (for bcachefs) or a device name (xfs). Cc: Christian Brauner Cc: Jan Kara Cc: Dave Chinner Cc: Darrick J. Wong Cc: Theodore Ts'o Cc: Josef Bacik Signed-off-by: Kent Overstreet Link: https://lore.kernel.org/r/20240207025624.1019754-6-kent.overstreet@linux.dev Signed-off-by: Christian Brauner --- fs/ioctl.c | 17 +++++++++++++++++ include/linux/fs.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fs.h | 10 ++++++++++ 3 files changed, 70 insertions(+) (limited to 'include/uapi') diff --git a/fs/ioctl.c b/fs/ioctl.c index 74eab9549383..1d5abfdf0f22 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -776,6 +776,20 @@ static int ioctl_getfsuuid(struct file *file, void __user *argp) return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } +static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) +{ + struct super_block *sb = file_inode(file)->i_sb; + + if (!strlen(sb->s_sysfs_name)) + return -ENOIOCTLCMD; + + struct fs_sysfs_path u = {}; + + u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name); + + return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; +} + /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. @@ -861,6 +875,9 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, case FS_IOC_GETFSUUID: return ioctl_getfsuuid(filp, argp); + case FS_IOC_GETFSSYSFSPATH: + return ioctl_get_fs_sysfs_path(filp, argp); + default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); diff --git a/include/linux/fs.h b/include/linux/fs.h index acdc56987cb1..c6d9e1b7032c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1255,10 +1255,23 @@ struct super_block { struct fsnotify_mark_connector __rcu *s_fsnotify_marks; #endif + /* + * q: why are s_id and s_sysfs_name not the same? both are human + * readable strings that identify the filesystem + * a: s_id is allowed to change at runtime; it's used in log messages, + * and we want to when a device starts out as single device (s_id is dev + * name) but then a device is hot added and we have to switch to + * identifying it by UUID + * but s_sysfs_name is a handle for programmatic access, and can't + * change at runtime + */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ + /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ + char s_sysfs_name[UUID_STRING_LEN + 1]; + unsigned int s_max_links; /* @@ -2541,6 +2554,36 @@ static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsign memcpy(&sb->s_uuid, uuid, len); } +/* set sb sysfs name based on sb->s_bdev */ +static inline void super_set_sysfs_name_bdev(struct super_block *sb) +{ + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); +} + +/* set sb sysfs name based on sb->s_uuid */ +static inline void super_set_sysfs_name_uuid(struct super_block *sb) +{ + WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); +} + +/* set sb sysfs name based on sb->s_id */ +static inline void super_set_sysfs_name_id(struct super_block *sb) +{ + strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); +} + +/* try to use something standard before you use this */ +__printf(2, 3) +static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); + va_end(args); +} + extern int current_umask(void); extern void ihold(struct inode * inode); diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 40880ce99d02..dcd6c8c7d2c7 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -77,6 +77,11 @@ struct fsuuid2 { __u8 uuid[16]; }; +struct fs_sysfs_path { + __u8 len; + __u8 name[128]; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -230,6 +235,11 @@ struct fsxattr { #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) /* Returns the external filesystem UUID, the same one blkid returns */ #define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) +/* + * Returns the path component under /sys/fs/ that refers to this filesystem; + * also /sys/kernel/debug/ for filesystems with debugfs exports + */ +#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) -- cgit v1.2.3 From e1aa35e16399d600215470411dfb56e1d6f8e017 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 8 Dec 2023 17:57:29 +0100 Subject: can: isotp: support dynamic flow control parameters The ISO15765-2 standard supports to take the PDUs communication parameters blocksize (BS) and Separation Time minimum (STmin) either from the first received flow control (FC) "static" or from every received FC "dynamic". Add a new CAN_ISOTP_DYN_FC_PARMS flag to support dynamic FC parameters. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20231208165729.3011-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 1 + net/can/isotp.c | 5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 439c982f7e81..6cde62371b6f 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -137,6 +137,7 @@ struct can_isotp_ll_options { #define CAN_ISOTP_WAIT_TX_DONE 0x0400 /* wait for tx completion */ #define CAN_ISOTP_SF_BROADCAST 0x0800 /* 1-to-N functional addressing */ #define CAN_ISOTP_CF_BROADCAST 0x1000 /* 1-to-N transmission w/o FC */ +#define CAN_ISOTP_DYN_FC_PARMS 0x2000 /* dynamic FC parameters BS/STmin */ /* protocol machine default values */ diff --git a/net/can/isotp.c b/net/can/isotp.c index d1c6f206f429..25bac0fafc83 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -381,8 +381,9 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) return 1; } - /* get communication parameters only from the first FC frame */ - if (so->tx.state == ISOTP_WAIT_FIRST_FC) { + /* get static/dynamic communication params from first/every FC frame */ + if (so->tx.state == ISOTP_WAIT_FIRST_FC || + so->opt.flags & CAN_ISOTP_DYN_FC_PARMS) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; -- cgit v1.2.3 From f6ca96aa51a4ae1b3a416fbe85acdf1197c405a6 Mon Sep 17 00:00:00 2001 From: Aditya Kumar Singh Date: Mon, 5 Feb 2024 21:59:50 +0530 Subject: wifi: cfg80211: add support for link id attribute in NL80211_CMD_DEL_STATION Currently whenever NL80211_CMD_DEL_STATION command is called without any MAC address, all stations present on that interface are flushed. However with MLO there is a need to flush such stations only which are using at least a particular link from the AP MLD interface. For example - 2 GHz and 5 GHz are part of an AP MLD. To this interface, following stations are connected - 1. One non-EHT STA on 2 GHz link. 2. One non-EHT STA on 5 GHz link. 3. One Multi-Link STA having 2 GHz and 5 GHz as active links. Now if currently, NL80211_CMD_DEL_STATION is issued by the 2 GHz link without any MAC address, it would flush all station entries. However, flushing of station entry #2 at least is not desireable since it is connected to 5 GHz link alone. Hence, add an option to pass link ID as well in the command so that if link ID is passed, stations using that passed link ID alone would be flushed and others will not. So after this, station entries #1 and #3 alone would be flushed and #2 will remain as it is. Signed-off-by: Aditya Kumar Singh Link: https://msgid.link/20240205162952.1697646-2-quic_adisi@quicinc.com [clarify documentation] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 3 ++- net/wireless/nl80211.c | 19 ++++++++++++++++++- net/wireless/trace.h | 7 +++++-- 4 files changed, 29 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f52f989a54ad..62894b024e88 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1780,11 +1780,15 @@ struct station_parameters { * @subtype: Management frame subtype to use for indicating removal * (10 = Disassociation, 12 = Deauthentication) * @reason_code: Reason code for the Disassociation/Deauthentication frame + * @link_id: Link ID indicating a link that stations to be flushed must be + * using; valid only for MLO, but can also be -1 for MLO to really + * remove all stations. */ struct station_del_parameters { const u8 *mac; u8 subtype; u16 reason_code; + int link_id; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 853ac538a686..805bfe712971 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -438,7 +438,8 @@ * %NL80211_ATTR_REASON_CODE can optionally be used to specify which type * of disconnection indication should be sent to the station * (Deauthentication or Disassociation frame and reason code for that - * frame). + * frame). %NL80211_ATTR_MLO_LINK_ID can be used optionally to remove + * stations connected and using at least that link as one of its links. * * @NL80211_CMD_GET_MPATH: Get mesh path attributes for mesh path to * destination %NL80211_ATTR_MAC on the interface identified by diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e1106ae35e21..5ca545753810 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7624,14 +7624,16 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; struct station_del_parameters params; + int link_id = nl80211_link_id_or_invalid(info->attrs); memset(¶ms, 0, sizeof(params)); if (info->attrs[NL80211_ATTR_MAC]) params.mac = nla_data(info->attrs[NL80211_ATTR_MAC]); - switch (dev->ieee80211_ptr->iftype) { + switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MESH_POINT: @@ -7672,6 +7674,17 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) params.reason_code = WLAN_REASON_PREV_AUTH_NOT_VALID; } + /* Link ID not expected in case of non-ML operation */ + if (!wdev->valid_links && link_id != -1) + return -EINVAL; + + /* If given, a valid link ID should be passed during MLO */ + if (wdev->valid_links && link_id >= 0 && + !(wdev->valid_links & BIT(link_id))) + return -EINVAL; + + params.link_id = link_id; + return rdev_del_station(rdev, dev, ¶ms); } @@ -16773,6 +16786,10 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_station, .flags = GENL_UNS_ADMIN_PERM, + /* cannot use NL80211_FLAG_MLO_VALID_LINK_ID, depends on + * whether MAC address is passed or not. If MAC address is + * passed, then even during MLO, link ID is not required. + */ .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 194ea2471717..361331c29116 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -867,6 +867,7 @@ DECLARE_EVENT_CLASS(station_del, MAC_ENTRY(sta_mac) __field(u8, subtype) __field(u16, reason_code) + __field(int, link_id) ), TP_fast_assign( WIPHY_ASSIGN; @@ -874,11 +875,13 @@ DECLARE_EVENT_CLASS(station_del, MAC_ASSIGN(sta_mac, params->mac); __entry->subtype = params->subtype; __entry->reason_code = params->reason_code; + __entry->link_id = params->link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" - ", subtype: %u, reason_code: %u", + ", subtype: %u, reason_code: %u, link_id: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sta_mac, - __entry->subtype, __entry->reason_code) + __entry->subtype, __entry->reason_code, + __entry->link_id) ); DEFINE_EVENT(station_del, rdev_del_station, -- cgit v1.2.3 From 7b5e25b8baebc02db728bfbdc3080be863144c7b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Feb 2024 16:54:07 +0200 Subject: wifi: cfg80211: rename UHB to 6 GHz UHB stands for "Ultra High Band", but this term doesn't really exist in the spec. Rename all occurrences to "6 GHz", but keep a few defines for userspace API compatibility. Link: https://msgid.link/20240206164849.c9cfb9400839.I153db3b951934a1d84409c17fbe1f1d1782543fa@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 10 +++++----- include/uapi/linux/nl80211.h | 31 ++++++++++++++++++++----------- net/wireless/nl80211.c | 8 ++++---- net/wireless/reg.c | 10 +++++----- net/wireless/scan.c | 8 ++++---- 5 files changed, 38 insertions(+), 29 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 62894b024e88..7bb8484e859e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -118,9 +118,9 @@ struct wiphy; * restrictions. * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT - * @IEEE80211_CHAN_NO_UHB_VLP_CLIENT: Client connection with VLP AP + * @IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT: Client connection with VLP AP * not permitted using this channel - * @IEEE80211_CHAN_NO_UHB_AFC_CLIENT: Client connection with AFC AP + * @IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT: Client connection with AFC AP * not permitted using this channel */ enum ieee80211_channel_flags { @@ -146,8 +146,8 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_320MHZ = 1<<19, IEEE80211_CHAN_NO_EHT = 1<<20, IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, - IEEE80211_CHAN_NO_UHB_VLP_CLIENT= 1<<22, - IEEE80211_CHAN_NO_UHB_AFC_CLIENT= 1<<23, + IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = 1<<22, + IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = 1<<23, }; #define IEEE80211_CHAN_NO_HT40 \ @@ -4935,7 +4935,7 @@ struct cfg80211_ops { * enum wiphy_flags - wiphy capability flags * * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split - * into two, first for legacy bands and second for UHB. + * into two, first for legacy bands and second for 6 GHz. * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this * wiphy at all * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 805bfe712971..13fa10804909 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -4269,9 +4269,9 @@ enum nl80211_wmm_rule { * allowed for peer-to-peer or adhoc communication under the control * of a DFS master which operates on the same channel (FCC-594280 D01 * Section B.3). Should be used together with %NL80211_RRF_DFS only. - * @NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT: Client connection to VLP AP + * @NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP * not allowed using this channel - * @NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT: Client connection to AFC AP + * @NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP * not allowed using this channel * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined @@ -4313,8 +4313,8 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_EHT, NL80211_FREQUENCY_ATTR_PSD, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT, - NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT, - NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT, + NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT, + NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4327,6 +4327,10 @@ enum nl80211_frequency_attr { #define NL80211_FREQUENCY_ATTR_NO_IR NL80211_FREQUENCY_ATTR_NO_IR #define NL80211_FREQUENCY_ATTR_GO_CONCURRENT \ NL80211_FREQUENCY_ATTR_IR_CONCURRENT +#define NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT \ + NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT +#define NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT \ + NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT /** * enum nl80211_bitrate_attr - bitrate attributes @@ -4517,8 +4521,8 @@ enum nl80211_sched_scan_match_attr { peer-to-peer or adhoc communication under the control of a DFS master which operates on the same channel (FCC-594280 D01 Section B.3). Should be used together with %NL80211_RRF_DFS only. - * @NL80211_RRF_NO_UHB_VLP_CLIENT: Client connection to VLP AP not allowed - * @NL80211_RRF_NO_UHB_AFC_CLIENT: Client connection to AFC AP not allowed + * @NL80211_RRF_NO_6GHZ_VLP_CLIENT: Client connection to VLP AP not allowed + * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4541,8 +4545,8 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_EHT = 1<<19, NL80211_RRF_PSD = 1<<20, NL80211_RRF_DFS_CONCURRENT = 1<<21, - NL80211_RRF_NO_UHB_VLP_CLIENT = 1<<22, - NL80211_RRF_NO_UHB_AFC_CLIENT = 1<<23, + NL80211_RRF_NO_6GHZ_VLP_CLIENT = 1<<22, + NL80211_RRF_NO_6GHZ_AFC_CLIENT = 1<<23, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR @@ -4551,6 +4555,8 @@ enum nl80211_reg_rule_flags { #define NL80211_RRF_NO_HT40 (NL80211_RRF_NO_HT40MINUS |\ NL80211_RRF_NO_HT40PLUS) #define NL80211_RRF_GO_CONCURRENT NL80211_RRF_IR_CONCURRENT +#define NL80211_RRF_NO_UHB_VLP_CLIENT NL80211_RRF_NO_6GHZ_VLP_CLIENT +#define NL80211_RRF_NO_UHB_AFC_CLIENT NL80211_RRF_NO_6GHZ_AFC_CLIENT /* For backport compatibility with older userspace */ #define NL80211_RRF_NO_IR_ALL (NL80211_RRF_NO_IR | __NL80211_RRF_NO_IBSS) @@ -5098,14 +5104,17 @@ enum nl80211_bss_use_for { * BSS isn't possible * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't * supported by the device, and this BSS entry represents one. - * @NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH: STA is not supporting + * @NL80211_BSS_CANNOT_USE_6GHZ_PWR_MISMATCH: STA is not supporting * the AP power type (SP, VLP, AP) that the AP uses. */ enum nl80211_bss_cannot_use_reasons { NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY = 1 << 0, - NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH = 1 << 1, + NL80211_BSS_CANNOT_USE_6GHZ_PWR_MISMATCH = 1 << 1, }; +#define NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH \ + NL80211_BSS_CANNOT_USE_6GHZ_PWR_MISMATCH + /** * enum nl80211_bss - netlink attributes for a BSS * diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5ca545753810..3b3b511f9f69 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1198,11 +1198,11 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT)) + if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT)) + if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT)) goto nla_put_failure; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2741b626919a..50cadbad485f 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -5,7 +5,7 @@ * Copyright 2008-2011 Luis R. Rodriguez * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -1595,10 +1595,10 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_EHT; if (rd_flags & NL80211_RRF_DFS_CONCURRENT) channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT; - if (rd_flags & NL80211_RRF_NO_UHB_VLP_CLIENT) - channel_flags |= IEEE80211_CHAN_NO_UHB_VLP_CLIENT; - if (rd_flags & NL80211_RRF_NO_UHB_AFC_CLIENT) - channel_flags |= IEEE80211_CHAN_NO_UHB_AFC_CLIENT; + if (rd_flags & NL80211_RRF_NO_6GHZ_VLP_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT; + if (rd_flags & NL80211_RRF_NO_6GHZ_AFC_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; return channel_flags; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 04039e9dbd05..88e8b25c073a 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include #include @@ -3041,9 +3041,9 @@ static bool cfg80211_uhb_power_type_valid(const u8 *ie, case IEEE80211_6GHZ_CTRL_REG_LPI_AP: return true; case IEEE80211_6GHZ_CTRL_REG_SP_AP: - return !(flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT); + return !(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT); case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - return !(flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT); + return !(flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT); } } return false; @@ -3112,7 +3112,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, data->restrict_use = 1; data->use_for = 0; data->cannot_use_reasons = - NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH; + NL80211_BSS_CANNOT_USE_6GHZ_PWR_MISMATCH; } if (ext) { -- cgit v1.2.3 From a110a3b79177ddd7e7295671df97fb5386406835 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Feb 2024 16:54:08 +0200 Subject: wifi: cfg80211: optionally support monitor on disabled channels If the hardware supports a disabled channel, it may in some cases be possible to use monitor mode (without any transmit) on it when it's otherwise disabled. Add a new channel flag IEEE80211_CHAN_CAN_MONITOR that makes it possible for a driver to indicate such a thing. Make it per channel so drivers could have a choice with it, perhaps it's only possible on some channels, perhaps some channels are not supported at all, but still there and marked disabled. In _nl80211_parse_chandef() simplify the code and check only for an unknown channel, _cfg80211_chandef_usable() will later check for IEEE80211_CHAN_DISABLED anyway. Signed-off-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://msgid.link/20240206164849.87fad3a21a09.I9116b2fdc2e2c9fd59a9273a64db7fcb41fc0328@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 4 ++++ net/wireless/chan.c | 26 +++++++++++++++++++------- net/wireless/core.h | 5 ++++- net/wireless/nl80211.c | 27 ++++++++++++++++++--------- 5 files changed, 49 insertions(+), 17 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7bb8484e859e..0a3151587556 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -122,6 +122,9 @@ struct wiphy; * not permitted using this channel * @IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT: Client connection with AFC AP * not permitted using this channel + * @IEEE80211_CHAN_CAN_MONITOR: This channel can be used for monitor + * mode even in the presence of other (regulatory) restrictions, + * even if it is otherwise disabled. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -148,6 +151,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = 1<<22, IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = 1<<23, + IEEE80211_CHAN_CAN_MONITOR = 1<<24, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 13fa10804909..546cc176c2a9 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4273,6 +4273,9 @@ enum nl80211_wmm_rule { * not allowed using this channel * @NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP * not allowed using this channel + * @NL80211_FREQUENCY_ATTR_CAN_MONITOR: This channel can be used in monitor + * mode despite other (regulatory) restrictions, even if the channel is + * otherwise completely disabled. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4315,6 +4318,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_DFS_CONCURRENT, NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT, + NL80211_FREQUENCY_ATTR_CAN_MONITOR, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, diff --git a/net/wireless/chan.c b/net/wireless/chan.c index e2ce89afa9ff..3414b2c3abcc 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -1145,7 +1145,7 @@ EXPORT_SYMBOL(cfg80211_chandef_dfs_cac_time); static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, u32 center_freq, u32 bandwidth, - u32 prohibited_flags) + u32 prohibited_flags, bool monitor) { struct ieee80211_channel *c; u32 freq, start_freq, end_freq; @@ -1155,7 +1155,11 @@ static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { c = ieee80211_get_channel_khz(wiphy, freq); - if (!c || c->flags & prohibited_flags) + if (!c) + return false; + if (monitor && c->flags & IEEE80211_CHAN_CAN_MONITOR) + continue; + if (c->flags & prohibited_flags) return false; } @@ -1215,9 +1219,9 @@ static bool cfg80211_edmg_usable(struct wiphy *wiphy, u8 edmg_channels, return true; } -bool cfg80211_chandef_usable(struct wiphy *wiphy, - const struct cfg80211_chan_def *chandef, - u32 prohibited_flags) +bool _cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags, bool monitor) { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; @@ -1379,14 +1383,22 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, if (!cfg80211_secondary_chans_ok(wiphy, ieee80211_chandef_to_khz(chandef), - width, prohibited_flags)) + width, prohibited_flags, monitor)) return false; if (!chandef->center_freq2) return true; return cfg80211_secondary_chans_ok(wiphy, MHZ_TO_KHZ(chandef->center_freq2), - width, prohibited_flags); + width, prohibited_flags, monitor); +} + +bool cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags) +{ + return _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, + false); } EXPORT_SYMBOL(cfg80211_chandef_usable); diff --git a/net/wireless/core.h b/net/wireless/core.h index debf63e6c61f..118f2f619828 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -3,7 +3,7 @@ * Wireless configuration interface internals. * * Copyright 2006-2010 Johannes Berg - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -492,6 +492,9 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, bool cfg80211_wdev_on_sub_chan(struct wireless_dev *wdev, struct ieee80211_channel *chan, bool primary_only); +bool _cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags, bool monitor); static inline unsigned int elapsed_jiffies_msecs(unsigned long start) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3b3b511f9f69..612ca99fbf39 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3218,9 +3218,9 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_P2P_GO; } -int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, - struct genl_info *info, - struct cfg80211_chan_def *chandef) +static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, + struct genl_info *info, bool monitor, + struct cfg80211_chan_def *chandef) { struct netlink_ext_ack *extack = info->extack; struct nlattr **attrs = info->attrs; @@ -3245,10 +3245,9 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, chandef->freq1_offset = control_freq % 1000; chandef->center_freq2 = 0; - /* Primary channel not allowed */ - if (!chandef->chan || chandef->chan->flags & IEEE80211_CHAN_DISABLED) { + if (!chandef->chan) { NL_SET_ERR_MSG_ATTR(extack, attrs[NL80211_ATTR_WIPHY_FREQ], - "Channel is disabled"); + "Unknown channel"); return -EINVAL; } @@ -3343,8 +3342,9 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, return -EINVAL; } - if (!cfg80211_chandef_usable(&rdev->wiphy, chandef, - IEEE80211_CHAN_DISABLED)) { + if (!_cfg80211_chandef_usable(&rdev->wiphy, chandef, + IEEE80211_CHAN_DISABLED, + monitor)) { NL_SET_ERR_MSG(extack, "(extension) channel is disabled"); return -EINVAL; } @@ -3359,6 +3359,13 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, return 0; } +int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, + struct genl_info *info, + struct cfg80211_chan_def *chandef) +{ + return _nl80211_parse_chandef(rdev, info, false, chandef); +} + static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct genl_info *info, @@ -3383,7 +3390,9 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, link_id = 0; } - result = nl80211_parse_chandef(rdev, info, &chandef); + result = _nl80211_parse_chandef(rdev, info, + iftype == NL80211_IFTYPE_MONITOR, + &chandef); if (result) return result; -- cgit v1.2.3 From 93d9f26db5b34ec4d2d5056aeb8819cbef35519c Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Tue, 6 Feb 2024 16:54:10 +0200 Subject: wifi: nl80211: allow reporting wakeup for unprot deauth/disassoc Add a report reason for waking up due to an unprotected deauth/disassoc when MFP is used. If setting wowlan to wake on disconnection, and an unprotected deatuh/disassoc arrived (in MFP), some drivers might want to report wakeup due to unprotected deauth/disassoc, rather than dissassociation. Add support for that. Signed-off-by: Shaul Triebitz Signed-off-by: Miri Korenblit Link: https://msgid.link/20240206164849.8dc9ad531a17.I7f8e926adf927f762e11aaa3458f6354665c7fc5@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 546cc176c2a9..f23ecbdd84a2 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5757,6 +5757,8 @@ struct nl80211_pattern_support { * %NL80211_ATTR_SCAN_FREQUENCIES contains more than one * frequency, it means that the match occurred in more than one * channel. + * @NL80211_WOWLAN_TRIG_UNPROTECTED_DEAUTH_DISASSOC: For wakeup reporting only. + * Wake up happened due to unprotected deauth or disassoc frame in MFP. * @NUM_NL80211_WOWLAN_TRIG: number of wake on wireless triggers * @MAX_NL80211_WOWLAN_TRIG: highest wowlan trigger attribute number * @@ -5784,6 +5786,7 @@ enum nl80211_wowlan_triggers { NL80211_WOWLAN_TRIG_WAKEUP_TCP_NOMORETOKENS, NL80211_WOWLAN_TRIG_NET_DETECT, NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS, + NL80211_WOWLAN_TRIG_UNPROTECTED_DEAUTH_DISASSOC, /* keep last */ NUM_NL80211_WOWLAN_TRIG, -- cgit v1.2.3 From bf5802238dc181b1f7375d358af1d01cd72d1c11 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 6 Feb 2024 09:03:24 -0800 Subject: xen/gntalloc: Replace UAPI 1-element array Without changing the structure size (since it is UAPI), add a proper flexible array member, and reference it in the kernel so that it will not be trip the array-bounds sanitizer[1]. Link: https://github.com/KSPP/linux/issues/113 [1] Cc: Juergen Gross Cc: Stefano Stabellini Cc: Oleksandr Tyshchenko Cc: Gustavo A. R. Silva Cc: xen-devel@lists.xenproject.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20240206170320.work.437-kees@kernel.org Signed-off-by: Juergen Gross --- drivers/xen/gntalloc.c | 2 +- include/uapi/xen/gntalloc.h | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 26ffb8755ffb..f93f73ecefee 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv, rc = -EFAULT; goto out_free; } - if (copy_to_user(arg->gref_ids, gref_ids, + if (copy_to_user(arg->gref_ids_flex, gref_ids, sizeof(gref_ids[0]) * op.count)) { rc = -EFAULT; goto out_free; diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h index 48d2790ef928..3109282672f3 100644 --- a/include/uapi/xen/gntalloc.h +++ b/include/uapi/xen/gntalloc.h @@ -31,7 +31,10 @@ struct ioctl_gntalloc_alloc_gref { __u64 index; /* The grant references of the newly created grant, one per page */ /* Variable size, depending on count */ - __u32 gref_ids[1]; + union { + __u32 gref_ids[1]; + __DECLARE_FLEX_ARRAY(__u32, gref_ids_flex); + }; }; #define GNTALLOC_FLAG_WRITABLE 1 -- cgit v1.2.3 From c83c22ec1493c0b7cc77327bedbd387e295872b6 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Feb 2024 22:35:50 +0100 Subject: can: canxl: add virtual CAN network identifier support CAN XL data frames contain an 8-bit virtual CAN network identifier (VCID). A VCID value of zero represents an 'untagged' CAN XL frame. To receive and send these optional VCIDs via CAN_RAW sockets a new socket option CAN_RAW_XL_VCID_OPTS is introduced to define/access VCID content: - tx: set the outgoing VCID value by the kernel (one fixed 8-bit value) - tx: pass through VCID values from the user space (e.g. for traffic replay) - rx: apply VCID receive filter (value/mask) to be passed to the user space With the 'tx pass through' option CAN_RAW_XL_VCID_TX_PASS all valid VCID values can be sent, e.g. to replay full qualified CAN XL traffic. The VCID value provided for the CAN_RAW_XL_VCID_TX_SET option will override the VCID value in the struct canxl_frame.prio defined for CAN_RAW_XL_VCID_TX_PASS when both flags are set. With a rx_vcid_mask of zero all possible VCID values (0x00 - 0xFF) are passed to the user space when the CAN_RAW_XL_VCID_RX_FILTER flag is set. Without this flag only untagged CAN XL frames (VCID = 0x00) are delivered to the user space (default). The 8-bit VCID is stored inside the CAN XL prio element (only in CAN XL frames!) to not interfere with other CAN content or the CAN filters provided by the CAN_RAW sockets and kernel infrastruture. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20240212213550.18516-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can.h | 9 ++++- include/uapi/linux/can/raw.h | 16 ++++++++ net/can/af_can.c | 2 + net/can/raw.c | 93 ++++++++++++++++++++++++++++++++++++++++---- 4 files changed, 110 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 939db2388208..e78cbd85ce7c 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -193,9 +193,14 @@ struct canfd_frame { #define CANXL_XLF 0x80 /* mandatory CAN XL frame flag (must always be set!) */ #define CANXL_SEC 0x01 /* Simple Extended Content (security/segmentation) */ +/* the 8-bit VCID is optionally placed in the canxl_frame.prio element */ +#define CANXL_VCID_OFFSET 16 /* bit offset of VCID in prio element */ +#define CANXL_VCID_VAL_MASK 0xFFUL /* VCID is an 8-bit value */ +#define CANXL_VCID_MASK (CANXL_VCID_VAL_MASK << CANXL_VCID_OFFSET) + /** * struct canxl_frame - CAN with e'X'tended frame 'L'ength frame structure - * @prio: 11 bit arbitration priority with zero'ed CAN_*_FLAG flags + * @prio: 11 bit arbitration priority with zero'ed CAN_*_FLAG flags / VCID * @flags: additional flags for CAN XL * @sdt: SDU (service data unit) type * @len: frame payload length in byte (CANXL_MIN_DLEN .. CANXL_MAX_DLEN) @@ -205,7 +210,7 @@ struct canfd_frame { * @prio shares the same position as @can_id from struct can[fd]_frame. */ struct canxl_frame { - canid_t prio; /* 11 bit priority for arbitration (canid_t) */ + canid_t prio; /* 11 bit priority for arbitration / 8 bit VCID */ __u8 flags; /* additional flags for CAN XL */ __u8 sdt; /* SDU (service data unit) type */ __u16 len; /* frame payload length in byte */ diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index 31622c9b7988..e024d896e278 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -65,6 +65,22 @@ enum { CAN_RAW_FD_FRAMES, /* allow CAN FD frames (default:off) */ CAN_RAW_JOIN_FILTERS, /* all filters must match to trigger */ CAN_RAW_XL_FRAMES, /* allow CAN XL frames (default:off) */ + CAN_RAW_XL_VCID_OPTS, /* CAN XL VCID configuration options */ }; +/* configuration for CAN XL virtual CAN identifier (VCID) handling */ +struct can_raw_vcid_options { + + __u8 flags; /* flags for vcid (filter) behaviour */ + __u8 tx_vcid; /* VCID value set into canxl_frame.prio */ + __u8 rx_vcid; /* VCID value for VCID filter */ + __u8 rx_vcid_mask; /* VCID mask for VCID filter */ + +}; + +/* can_raw_vcid_options.flags for CAN XL virtual CAN identifier handling */ +#define CAN_RAW_XL_VCID_TX_SET 0x01 +#define CAN_RAW_XL_VCID_TX_PASS 0x02 +#define CAN_RAW_XL_VCID_RX_FILTER 0x04 + #endif /* !_UAPI_CAN_RAW_H */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 7343fd487dbe..707576eeeb58 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -865,6 +865,8 @@ static __init int can_init(void) /* check for correct padding to be able to use the structs similarly */ BUILD_BUG_ON(offsetof(struct can_frame, len) != offsetof(struct canfd_frame, len) || + offsetof(struct can_frame, len) != + offsetof(struct canxl_frame, flags) || offsetof(struct can_frame, data) != offsetof(struct canfd_frame, data)); diff --git a/net/can/raw.c b/net/can/raw.c index e6b822624ba2..cb8e6f788af8 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -91,6 +91,10 @@ struct raw_sock { int recv_own_msgs; int fd_frames; int xl_frames; + struct can_raw_vcid_options raw_vcid_opts; + canid_t tx_vcid_shifted; + canid_t rx_vcid_shifted; + canid_t rx_vcid_mask_shifted; int join_filters; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ @@ -134,10 +138,29 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; /* make sure to not pass oversized frames to the socket */ - if ((!ro->fd_frames && can_is_canfd_skb(oskb)) || - (!ro->xl_frames && can_is_canxl_skb(oskb))) + if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; + if (can_is_canxl_skb(oskb)) { + struct canxl_frame *cxl = (struct canxl_frame *)oskb->data; + + /* make sure to not pass oversized frames to the socket */ + if (!ro->xl_frames) + return; + + /* filter CAN XL VCID content */ + if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) { + /* apply VCID filter if user enabled the filter */ + if ((cxl->prio & ro->rx_vcid_mask_shifted) != + (ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted)) + return; + } else { + /* no filter => do not forward VCID tagged frames */ + if (cxl->prio & CANXL_VCID_MASK) + return; + } + } + /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { @@ -698,6 +721,19 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->fd_frames = ro->xl_frames; break; + case CAN_RAW_XL_VCID_OPTS: + if (optlen != sizeof(ro->raw_vcid_opts)) + return -EINVAL; + + if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen)) + return -EFAULT; + + /* prepare 32 bit values for handling in hot path */ + ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET; + ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET; + ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET; + break; + case CAN_RAW_JOIN_FILTERS: if (optlen != sizeof(ro->join_filters)) return -EINVAL; @@ -786,6 +822,21 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, val = &ro->xl_frames; break; + case CAN_RAW_XL_VCID_OPTS: + /* user space buffer to small for VCID opts? */ + if (len < sizeof(ro->raw_vcid_opts)) { + /* return -ERANGE and needed space in optlen */ + err = -ERANGE; + if (put_user(sizeof(ro->raw_vcid_opts), optlen)) + err = -EFAULT; + } else { + if (len > sizeof(ro->raw_vcid_opts)) + len = sizeof(ro->raw_vcid_opts); + if (copy_to_user(optval, &ro->raw_vcid_opts, len)) + err = -EFAULT; + } + break; + case CAN_RAW_JOIN_FILTERS: if (len > sizeof(int)) len = sizeof(int); @@ -803,23 +854,41 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } -static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) +{ + struct canxl_frame *cxl = (struct canxl_frame *)skb->data; + + /* sanitize non CAN XL bits */ + cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK); + + /* clear VCID in CAN XL frame if pass through is disabled */ + if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS)) + cxl->prio &= CANXL_PRIO_MASK; + + /* set VCID in CAN XL frame if enabled */ + if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) { + cxl->prio &= CANXL_PRIO_MASK; + cxl->prio |= ro->tx_vcid_shifted; + } +} + +static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) { /* Classical CAN -> no checks for flags and device capabilities */ if (can_is_can_skb(skb)) - return false; + return CAN_MTU; /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ if (ro->fd_frames && can_is_canfd_skb(skb) && (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) - return false; + return CANFD_MTU; /* CAN XL -> needs to be enabled and a CAN XL device */ if (ro->xl_frames && can_is_canxl_skb(skb) && can_is_canxl_dev_mtu(mtu)) - return false; + return CANXL_MTU; - return true; + return 0; } static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) @@ -829,6 +898,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; struct sk_buff *skb; struct net_device *dev; + unsigned int txmtu; int ifindex; int err = -EINVAL; @@ -869,9 +939,16 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto free_skb; err = -EINVAL; - if (raw_bad_txframe(ro, skb, dev->mtu)) + + /* check for valid CAN (CC/FD/XL) frame content */ + txmtu = raw_check_txframe(ro, skb, dev->mtu); + if (!txmtu) goto free_skb; + /* only CANXL: clear/forward/set VCID value */ + if (txmtu == CANXL_MTU) + raw_put_canxl_vcid(ro, skb); + sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); -- cgit v1.2.3 From 18e2bf0edf4dd88d9656ec92395aa47392e85b61 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 13 Feb 2024 06:16:45 +0000 Subject: eventpoll: Add epoll ioctl for epoll_params Add an ioctl for getting and setting epoll_params. User programs can use this ioctl to get and set the busy poll usec time, packet budget, and prefer busy poll params for a specific epoll context. Parameters are limited: - busy_poll_usecs is limited to <= s32_max - busy_poll_budget is limited to <= NAPI_POLL_WEIGHT by unprivileged users (!capable(CAP_NET_ADMIN)) - prefer_busy_poll must be 0 or 1 - __pad must be 0 Signed-off-by: Joe Damato Acked-by: Stanislav Fomichev Reviewed-by: Jiri Slaby Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + fs/eventpoll.c | 73 ++++++++++++++++++++++ include/uapi/linux/eventpoll.h | 13 ++++ 3 files changed, 87 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 457e16f06e04..b33918232f78 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -309,6 +309,7 @@ Code Seq# Include File Comments 0x89 0B-DF linux/sockios.h 0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range 0x89 F0-FF linux/sockios.h SIOCDEVPRIVATE range +0x8A 00-1F linux/eventpoll.h 0x8B all linux/wireless.h 0x8C 00-3F WiNRADiO driver diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1b8d01af0c2c..df2ed3af486e 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -37,6 +37,7 @@ #include #include #include +#include #include /* @@ -494,6 +495,49 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) ep->napi_id = napi_id; } +static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct eventpoll *ep = file->private_data; + void __user *uarg = (void __user *)arg; + struct epoll_params epoll_params; + + switch (cmd) { + case EPIOCSPARAMS: + if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) + return -EFAULT; + + /* pad byte must be zero */ + if (epoll_params.__pad) + return -EINVAL; + + if (epoll_params.busy_poll_usecs > S32_MAX) + return -EINVAL; + + if (epoll_params.prefer_busy_poll > 1) + return -EINVAL; + + if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && + !capable(CAP_NET_ADMIN)) + return -EPERM; + + WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); + WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); + WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); + return 0; + case EPIOCGPARAMS: + memset(&epoll_params, 0, sizeof(epoll_params)); + epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); + epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); + epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); + if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) + return -EFAULT; + return 0; + default: + return -ENOIOCTLCMD; + } +} + #else static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) @@ -505,6 +549,12 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } +static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NET_RX_BUSY_POLL */ /* @@ -864,6 +914,27 @@ static void ep_clear_and_put(struct eventpoll *ep) ep_free(ep); } +static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret; + + if (!is_file_epoll(file)) + return -EINVAL; + + switch (cmd) { + case EPIOCSPARAMS: + case EPIOCGPARAMS: + ret = ep_eventpoll_bp_ioctl(file, cmd, arg); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; @@ -970,6 +1041,8 @@ static const struct file_operations eventpoll_fops = { .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, + .unlocked_ioctl = ep_eventpoll_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; /* diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index cfbcc4cc49ac..4f4b948ef381 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -85,4 +85,17 @@ struct epoll_event { __u64 data; } EPOLL_PACKED; +struct epoll_params { + __u32 busy_poll_usecs; + __u16 busy_poll_budget; + __u8 prefer_busy_poll; + + /* pad the struct to a multiple of 64bits */ + __u8 __pad; +}; + +#define EPOLL_IOC_TYPE 0x8A +#define EPIOCSPARAMS _IOW(EPOLL_IOC_TYPE, 0x01, struct epoll_params) +#define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params) + #endif /* _UAPI_LINUX_EVENTPOLL_H */ -- cgit v1.2.3 From 8ff0d55ba3fb56b69e40c50ff030a77c27a072ca Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Sun, 11 Feb 2024 18:14:21 +0800 Subject: gpio: uapi: clarify default_values being logical The documentation for default_values mentions high/low which can be confusing, particularly when the ACTIVE_LOW flag is set. Replace high/low with active/inactive to clarify that the values are logical not physical. Similarly, clarify the interpretation of values in struct gpiohandle_data. Signed-off-by: Kent Gibson Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 103cd3c6c81e..f7cb8ae87df7 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -399,8 +399,8 @@ struct gpioline_info_changed { * a batch of input or output lines, but they must all have the same * characteristics, i.e. all inputs or all outputs, all active low etc * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested - * line, this specifies the default output value, should be 0 (low) or - * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) + * line, this specifies the default output value, should be 0 (inactive) or + * 1 (active). Anything other than 0 or 1 will be interpreted as active. * @consumer_label: a desired consumer label for the selected GPIO line(s) * such as "my-bitbanged-relay" * @lines: number of lines requested in this request, i.e. the number of @@ -426,8 +426,8 @@ struct gpiohandle_request { * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags, - * this specifies the default output value, should be 0 (low) or - * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) + * this specifies the default output value, should be 0 (inactive) or + * 1 (active). Anything other than 0 or 1 will be interpreted as active. * @padding: reserved for future use and should be zero filled * * Note: This struct is part of ABI v1 and is deprecated. @@ -443,7 +443,8 @@ struct gpiohandle_config { * struct gpiohandle_data - Information of values on a GPIO handle * @values: when getting the state of lines this contains the current * state of a line, when setting the state of lines these should contain - * the desired target state + * the desired target state. States are 0 (inactive) or 1 (active). + * When setting, anything other than 0 or 1 will be interpreted as active. * * Note: This struct is part of ABI v1 and is deprecated. * Use ABI v2 and &struct gpio_v2_line_values instead. -- cgit v1.2.3 From 3281366a8e79a512956382885091565db1036b64 Mon Sep 17 00:00:00 2001 From: Peter Bergner Date: Wed, 14 Feb 2024 16:34:06 -0600 Subject: uapi/auxvec: Define AT_HWCAP3 and AT_HWCAP4 aux vector, entries The powerpc toolchain keeps a copy of the HWCAP bit masks in the TCB for fast access by the __builtin_cpu_supports() built-in function. The TCB space for the HWCAP entries - which are created in pairs - is an ABI extension, so waiting to create the space for HWCAP3 and HWCAP4 until they are needed is problematic. Define AT_HWCAP3 and AT_HWCAP4 in the generic uapi header so they can be used in glibc to reserve space in the powerpc TCB for their future use. I scanned through the Linux and GLIBC source codes looking for unused AT_* values and 29 and 30 did not seem to be used, so they are what I went with. Signed-off-by: Peter Bergner Acked-by: Adhemerval Zanella Acked-by: Nicholas Piggin Acked-by: Szabolcs Nagy Acked-by: Arnd Bergmann Signed-off-by: Michael Ellerman Link: https://msgid.link/a406b535-dc55-4856-8ae9-5a063644a1af@linux.ibm.com --- include/uapi/linux/auxvec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/auxvec.h b/include/uapi/linux/auxvec.h index 6991c4b8ab18..cc61cb9b3e9a 100644 --- a/include/uapi/linux/auxvec.h +++ b/include/uapi/linux/auxvec.h @@ -32,6 +32,8 @@ #define AT_HWCAP2 26 /* extension of AT_HWCAP */ #define AT_RSEQ_FEATURE_SIZE 27 /* rseq supported feature size */ #define AT_RSEQ_ALIGN 28 /* rseq allocation alignment */ +#define AT_HWCAP3 29 /* extension of AT_HWCAP */ +#define AT_HWCAP4 30 /* extension of AT_HWCAP */ #define AT_EXECFN 31 /* filename of program */ -- cgit v1.2.3 From cd3cec0a02c7338ce2901c574f3935b8f6984aab Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Thu, 15 Feb 2024 11:31:08 +0100 Subject: ima: Move to LSM infrastructure Move hardcoded IMA function calls (not appraisal-specific functions) from various places in the kernel to the LSM infrastructure, by introducing a new LSM named 'ima' (at the end of the LSM list and always enabled like 'integrity'). Having IMA before EVM in the Makefile is sufficient to preserve the relative order of the new 'ima' LSM in respect to the upcoming 'evm' LSM, and thus the order of IMA and EVM function calls as when they were hardcoded. Make moved functions as static (except ima_post_key_create_or_update(), which is not in ima_main.c), and register them as implementation of the respective hooks in the new function init_ima_lsm(). Select CONFIG_SECURITY_PATH, to ensure that the path-based LSM hook path_post_mknod is always available and ima_post_path_mknod() is always executed to mark files as new, as before the move. A slight difference is that IMA and EVM functions registered for the inode_post_setattr, inode_post_removexattr, path_post_mknod, inode_post_create_tmpfile, inode_post_set_acl and inode_post_remove_acl won't be executed for private inodes. Since those inodes are supposed to be fs-internal, they should not be of interest to IMA or EVM. The S_PRIVATE flag is used for anonymous inodes, hugetlbfs, reiserfs xattrs, XFS scrub and kernel-internal tmpfs files. Conditionally register ima_post_key_create_or_update() if CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS is enabled. Also, conditionally register ima_kernel_module_request() if CONFIG_INTEGRITY_ASYMMETRIC_KEYS is enabled. Finally, add the LSM_ID_IMA case in lsm_list_modules_test.c. Signed-off-by: Roberto Sassu Acked-by: Chuck Lever Acked-by: Casey Schaufler Acked-by: Christian Brauner Reviewed-by: Stefan Berger Reviewed-by: Mimi Zohar Acked-by: Mimi Zohar Signed-off-by: Paul Moore --- fs/file_table.c | 2 - fs/namei.c | 6 -- fs/nfsd/vfs.c | 7 -- fs/open.c | 1 - include/linux/ima.h | 104 --------------------- include/uapi/linux/lsm.h | 1 + security/integrity/Makefile | 1 + security/integrity/ima/Kconfig | 1 + security/integrity/ima/ima.h | 6 ++ security/integrity/ima/ima_main.c | 78 +++++++++++----- security/integrity/integrity.h | 1 + security/keys/key.c | 9 +- security/security.c | 63 +++---------- .../testing/selftests/lsm/lsm_list_modules_test.c | 3 + 14 files changed, 83 insertions(+), 200 deletions(-) (limited to 'include/uapi') diff --git a/fs/file_table.c b/fs/file_table.c index 725407f374fa..1a0962981b48 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include @@ -368,7 +367,6 @@ static void __fput(struct file *file) locks_remove_file(file); security_file_release(file); - ima_file_free(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); diff --git a/fs/namei.c b/fs/namei.c index c7ac7fdf0f25..1bf7435cdf76 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -3641,8 +3640,6 @@ static int do_open(struct nameidata *nd, error = vfs_open(&nd->path, file); if (!error) error = security_file_post_open(file, op->acc_mode); - if (!error) - error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(idmap, file); if (unlikely(error > 0)) { @@ -3706,7 +3703,6 @@ static int vfs_tmpfile(struct mnt_idmap *idmap, spin_unlock(&inode->i_lock); } security_inode_post_create_tmpfile(idmap, inode); - ima_post_create_tmpfile(idmap, inode); return 0; } @@ -4052,8 +4048,6 @@ retry: case 0: case S_IFREG: error = vfs_create(idmap, path.dentry->d_inode, dentry, mode, true); - if (!error) - ima_post_path_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index e44d8239545b..4349dde92154 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -883,12 +882,6 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, goto out; } - host_err = ima_file_check(file, may_flags); - if (host_err) { - fput(file); - goto out; - } - if (may_flags & NFSD_MAY_64BIT_COOKIE) file->f_mode |= FMODE_64BITHASH; else diff --git a/fs/open.c b/fs/open.c index a84d21e55c39..1cf05a1413aa 100644 --- a/fs/open.c +++ b/fs/open.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/ima.h b/include/linux/ima.h index 0f9af283cbc8..23ae24b60ecf 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -16,24 +16,6 @@ struct linux_binprm; #ifdef CONFIG_IMA extern enum hash_algo ima_get_current_hash_algo(void); -extern int ima_bprm_check(struct linux_binprm *bprm); -extern int ima_file_check(struct file *file, int mask); -extern void ima_post_create_tmpfile(struct mnt_idmap *idmap, - struct inode *inode); -extern void ima_file_free(struct file *file); -extern int ima_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags); -extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, - unsigned long prot); -extern int ima_load_data(enum kernel_load_data_id id, bool contents); -extern int ima_post_load_data(char *buf, loff_t size, - enum kernel_load_data_id id, char *description); -extern int ima_read_file(struct file *file, enum kernel_read_file_id id, - bool contents); -extern int ima_post_read_file(struct file *file, char *buf, loff_t size, - enum kernel_read_file_id id); -extern void ima_post_path_mknod(struct mnt_idmap *idmap, - struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); @@ -58,68 +40,6 @@ static inline enum hash_algo ima_get_current_hash_algo(void) return HASH_ALGO__LAST; } -static inline int ima_bprm_check(struct linux_binprm *bprm) -{ - return 0; -} - -static inline int ima_file_check(struct file *file, int mask) -{ - return 0; -} - -static inline void ima_post_create_tmpfile(struct mnt_idmap *idmap, - struct inode *inode) -{ -} - -static inline void ima_file_free(struct file *file) -{ - return; -} - -static inline int ima_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags) -{ - return 0; -} - -static inline int ima_file_mprotect(struct vm_area_struct *vma, - unsigned long reqprot, unsigned long prot) -{ - return 0; -} - -static inline int ima_load_data(enum kernel_load_data_id id, bool contents) -{ - return 0; -} - -static inline int ima_post_load_data(char *buf, loff_t size, - enum kernel_load_data_id id, - char *description) -{ - return 0; -} - -static inline int ima_read_file(struct file *file, enum kernel_read_file_id id, - bool contents) -{ - return 0; -} - -static inline int ima_post_read_file(struct file *file, char *buf, loff_t size, - enum kernel_read_file_id id) -{ - return 0; -} - -static inline void ima_post_path_mknod(struct mnt_idmap *idmap, - struct dentry *dentry) -{ - return; -} - static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size) { return -EOPNOTSUPP; @@ -170,20 +90,6 @@ static inline void ima_add_kexec_buffer(struct kimage *image) {} #endif -#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS -extern void ima_post_key_create_or_update(struct key *keyring, - struct key *key, - const void *payload, size_t plen, - unsigned long flags, bool create); -#else -static inline void ima_post_key_create_or_update(struct key *keyring, - struct key *key, - const void *payload, - size_t plen, - unsigned long flags, - bool create) {} -#endif /* CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS */ - #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); extern void ima_inode_post_setattr(struct mnt_idmap *idmap, @@ -256,14 +162,4 @@ static inline bool ima_appraise_signature(enum kernel_read_file_id func) return false; } #endif /* CONFIG_IMA_APPRAISE && CONFIG_INTEGRITY_TRUSTED_KEYRING */ - -#if defined(CONFIG_IMA) && defined(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) -extern int ima_kernel_module_request(char *kmod_name); -#else -static inline int ima_kernel_module_request(char *kmod_name) -{ - return 0; -} - -#endif #endif /* _LINUX_IMA_H */ diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h index f8aef9ade549..b3b7fd699b63 100644 --- a/include/uapi/linux/lsm.h +++ b/include/uapi/linux/lsm.h @@ -62,6 +62,7 @@ struct lsm_ctx { #define LSM_ID_LOCKDOWN 108 #define LSM_ID_BPF 109 #define LSM_ID_LANDLOCK 110 +#define LSM_ID_IMA 111 /* * LSM_ATTR_XXX definitions identify different LSM attributes diff --git a/security/integrity/Makefile b/security/integrity/Makefile index d0ffe37dc1d6..92b63039c654 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -18,5 +18,6 @@ integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o integrity-$(CONFIG_LOAD_PPC_KEYS) += platform_certs/efi_parser.o \ platform_certs/load_powerpc.o \ platform_certs/keyring_handler.o +# The relative order of the 'ima' and 'evm' LSMs depends on the order below. obj-$(CONFIG_IMA) += ima/ obj-$(CONFIG_EVM) += evm/ diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index b98bfe9efd0c..475c32615006 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -8,6 +8,7 @@ config IMA select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_HASH_INFO + select SECURITY_PATH select TCG_TPM if HAS_IOMEM select TCG_TIS if TCG_TPM && X86 select TCG_CRB if TCG_TPM && ACPI diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index c29db699c996..c0412100023e 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -127,6 +127,12 @@ void ima_load_kexec_buffer(void); static inline void ima_load_kexec_buffer(void) {} #endif /* CONFIG_HAVE_IMA_KEXEC */ +#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS +void ima_post_key_create_or_update(struct key *keyring, struct key *key, + const void *payload, size_t plen, + unsigned long flags, bool create); +#endif + /* * The default binary_runtime_measurements list format is defined as the * platform native format. The canonical format is defined as little-endian. diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 3891b83efdb3..d0826e864c29 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -189,7 +189,7 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint, * * Flag files that changed, based on i_version */ -void ima_file_free(struct file *file) +static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct integrity_iint_cache *iint; @@ -427,8 +427,8 @@ out: * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_file_mmap(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags) +static int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { u32 secid; int ret; @@ -466,8 +466,8 @@ int ima_file_mmap(struct file *file, unsigned long reqprot, * * On mprotect change success, return 0. On failure, return -EACESS. */ -int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, - unsigned long prot) +static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, + unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; @@ -525,7 +525,7 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_bprm_check(struct linux_binprm *bprm) +static int ima_bprm_check(struct linux_binprm *bprm) { int ret; u32 secid; @@ -551,7 +551,7 @@ int ima_bprm_check(struct linux_binprm *bprm) * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_file_check(struct file *file, int mask) +static int ima_file_check(struct file *file, int mask) { u32 secid; @@ -560,7 +560,6 @@ int ima_file_check(struct file *file, int mask) mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } -EXPORT_SYMBOL_GPL(ima_file_check); static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) @@ -685,8 +684,9 @@ EXPORT_SYMBOL_GPL(ima_inode_hash); * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ -void ima_post_create_tmpfile(struct mnt_idmap *idmap, - struct inode *inode) +static void ima_post_create_tmpfile(struct mnt_idmap *idmap, + struct inode *inode) + { struct integrity_iint_cache *iint; int must_appraise; @@ -717,8 +717,7 @@ void ima_post_create_tmpfile(struct mnt_idmap *idmap, * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ -void ima_post_path_mknod(struct mnt_idmap *idmap, - struct dentry *dentry) +static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct integrity_iint_cache *iint; struct inode *inode = dentry->d_inode; @@ -753,8 +752,8 @@ void ima_post_path_mknod(struct mnt_idmap *idmap, * * For permission return 0, otherwise return -EACCES. */ -int ima_read_file(struct file *file, enum kernel_read_file_id read_id, - bool contents) +static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, + bool contents) { enum ima_hooks func; u32 secid; @@ -803,8 +802,8 @@ const int read_idmap[READING_MAX_ID] = { * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_post_read_file(struct file *file, char *buf, loff_t size, - enum kernel_read_file_id read_id) +static int ima_post_read_file(struct file *file, char *buf, loff_t size, + enum kernel_read_file_id read_id) { enum ima_hooks func; u32 secid; @@ -837,7 +836,7 @@ int ima_post_read_file(struct file *file, char *buf, loff_t size, * * For permission return 0, otherwise return -EACCES. */ -int ima_load_data(enum kernel_load_data_id id, bool contents) +static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; @@ -891,9 +890,9 @@ int ima_load_data(enum kernel_load_data_id id, bool contents) * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_post_load_data(char *buf, loff_t size, - enum kernel_load_data_id load_id, - char *description) +static int ima_post_load_data(char *buf, loff_t size, + enum kernel_load_data_id load_id, + char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && @@ -1114,7 +1113,7 @@ EXPORT_SYMBOL_GPL(ima_measure_critical_data); * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ -int ima_kernel_module_request(char *kmod_name) +static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0) return -EINVAL; @@ -1155,4 +1154,41 @@ static int __init init_ima(void) return error; } +static struct security_hook_list ima_hooks[] __ro_after_init = { + LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), + LSM_HOOK_INIT(file_post_open, ima_file_check), + LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), + LSM_HOOK_INIT(file_release, ima_file_free), + LSM_HOOK_INIT(mmap_file, ima_file_mmap), + LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), + LSM_HOOK_INIT(kernel_load_data, ima_load_data), + LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), + LSM_HOOK_INIT(kernel_read_file, ima_read_file), + LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), + LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), +#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS + LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), +#endif +#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS + LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), +#endif +}; + +static const struct lsm_id ima_lsmid = { + .name = "ima", + .id = LSM_ID_IMA, +}; + +static int __init init_ima_lsm(void) +{ + security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); + return 0; +} + +DEFINE_LSM(ima) = { + .name = "ima", + .init = init_ima_lsm, + .order = LSM_ORDER_LAST, +}; + late_initcall(init_ima); /* Start IMA after the TPM is available */ diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 9561db7cf6b4..59eaddd84434 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -18,6 +18,7 @@ #include #include #include +#include /* iint action cache flags */ #define IMA_MEASURE 0x00000001 diff --git a/security/keys/key.c b/security/keys/key.c index 31a8b9408b7c..560790038329 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include "internal.h" @@ -932,8 +931,6 @@ static key_ref_t __key_create_or_update(key_ref_t keyring_ref, security_key_post_create_or_update(keyring, key, payload, plen, flags, true); - ima_post_key_create_or_update(keyring, key, payload, plen, - flags, true); key_ref = make_key_ref(key, is_key_possessed(keyring_ref)); @@ -965,13 +962,9 @@ error: key_ref = __key_update(key_ref, &prep); - if (!IS_ERR(key_ref)) { + if (!IS_ERR(key_ref)) security_key_post_create_or_update(keyring, key, payload, plen, flags, false); - ima_post_key_create_or_update(keyring, key, - payload, plen, - flags, false); - } goto error_free_prep; } diff --git a/security/security.c b/security/security.c index bc3c6790aeaf..8495890a5a37 100644 --- a/security/security.c +++ b/security/security.c @@ -50,7 +50,8 @@ (IS_ENABLED(CONFIG_SECURITY_SAFESETID) ? 1 : 0) + \ (IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) ? 1 : 0) + \ (IS_ENABLED(CONFIG_BPF_LSM) ? 1 : 0) + \ - (IS_ENABLED(CONFIG_SECURITY_LANDLOCK) ? 1 : 0)) + (IS_ENABLED(CONFIG_SECURITY_LANDLOCK) ? 1 : 0) + \ + (IS_ENABLED(CONFIG_IMA) ? 1 : 0)) /* * These are descriptions of the reasons that can be passed to the @@ -1182,12 +1183,7 @@ int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file * */ int security_bprm_check(struct linux_binprm *bprm) { - int ret; - - ret = call_int_hook(bprm_check_security, 0, bprm); - if (ret) - return ret; - return ima_bprm_check(bprm); + return call_int_hook(bprm_check_security, 0, bprm); } /** @@ -2895,13 +2891,8 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot) int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { - unsigned long prot_adj = mmap_prot(file, prot); - int ret; - - ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); - if (ret) - return ret; - return ima_file_mmap(file, prot, prot_adj, flags); + return call_int_hook(mmap_file, 0, file, prot, mmap_prot(file, prot), + flags); } /** @@ -2930,12 +2921,7 @@ int security_mmap_addr(unsigned long addr) int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { - int ret; - - ret = call_int_hook(file_mprotect, 0, vma, reqprot, prot); - if (ret) - return ret; - return ima_file_mprotect(vma, reqprot, prot); + return call_int_hook(file_mprotect, 0, vma, reqprot, prot); } /** @@ -3244,12 +3230,7 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode) */ int security_kernel_module_request(char *kmod_name) { - int ret; - - ret = call_int_hook(kernel_module_request, 0, kmod_name); - if (ret) - return ret; - return ima_kernel_module_request(kmod_name); + return call_int_hook(kernel_module_request, 0, kmod_name); } /** @@ -3265,12 +3246,7 @@ int security_kernel_module_request(char *kmod_name) int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { - int ret; - - ret = call_int_hook(kernel_read_file, 0, file, id, contents); - if (ret) - return ret; - return ima_read_file(file, id, contents); + return call_int_hook(kernel_read_file, 0, file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); @@ -3290,12 +3266,7 @@ EXPORT_SYMBOL_GPL(security_kernel_read_file); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { - int ret; - - ret = call_int_hook(kernel_post_read_file, 0, file, buf, size, id); - if (ret) - return ret; - return ima_post_read_file(file, buf, size, id); + return call_int_hook(kernel_post_read_file, 0, file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); @@ -3310,12 +3281,7 @@ EXPORT_SYMBOL_GPL(security_kernel_post_read_file); */ int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { - int ret; - - ret = call_int_hook(kernel_load_data, 0, id, contents); - if (ret) - return ret; - return ima_load_data(id, contents); + return call_int_hook(kernel_load_data, 0, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); @@ -3337,13 +3303,8 @@ int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { - int ret; - - ret = call_int_hook(kernel_post_load_data, 0, buf, size, id, - description); - if (ret) - return ret; - return ima_post_load_data(buf, size, id, description); + return call_int_hook(kernel_post_load_data, 0, buf, size, id, + description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); diff --git a/tools/testing/selftests/lsm/lsm_list_modules_test.c b/tools/testing/selftests/lsm/lsm_list_modules_test.c index 9df29b1e3497..17333787cb2f 100644 --- a/tools/testing/selftests/lsm/lsm_list_modules_test.c +++ b/tools/testing/selftests/lsm/lsm_list_modules_test.c @@ -122,6 +122,9 @@ TEST(correct_lsm_list_modules) case LSM_ID_LANDLOCK: name = "landlock"; break; + case LSM_ID_IMA: + name = "ima"; + break; default: name = "INVALID"; break; -- cgit v1.2.3 From 9238311176115aac1b1a86e8e968c04ebec747a1 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Thu, 15 Feb 2024 11:31:10 +0100 Subject: evm: Move to LSM infrastructure As for IMA, move hardcoded EVM function calls from various places in the kernel to the LSM infrastructure, by introducing a new LSM named 'evm' (last and always enabled like 'ima'). The order in the Makefile ensures that 'evm' hooks are executed after 'ima' ones. Make EVM functions as static (except for evm_inode_init_security(), which is exported), and register them as hook implementations in init_evm_lsm(). Also move the inline functions evm_inode_remove_acl(), evm_inode_post_remove_acl(), and evm_inode_post_set_acl() from the public evm.h header to evm_main.c. Unlike before (see commit to move IMA to the LSM infrastructure), evm_inode_post_setattr(), evm_inode_post_set_acl(), evm_inode_post_remove_acl(), and evm_inode_post_removexattr() are not executed for private inodes. Finally, add the LSM_ID_EVM case in lsm_list_modules_test.c Signed-off-by: Roberto Sassu Reviewed-by: Casey Schaufler Acked-by: Christian Brauner Reviewed-by: Stefan Berger Reviewed-by: Mimi Zohar Acked-by: Mimi Zohar Signed-off-by: Paul Moore --- fs/attr.c | 2 - fs/posix_acl.c | 3 - fs/xattr.c | 2 - include/linux/evm.h | 113 -------------------- include/uapi/linux/lsm.h | 1 + security/integrity/evm/evm_main.c | 118 ++++++++++++++++++--- security/security.c | 43 ++------ .../testing/selftests/lsm/lsm_list_modules_test.c | 3 + 8 files changed, 116 insertions(+), 169 deletions(-) (limited to 'include/uapi') diff --git a/fs/attr.c b/fs/attr.c index 7e97313e7f70..4d0d75953107 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -16,7 +16,6 @@ #include #include #include -#include #include "internal.h" @@ -502,7 +501,6 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, if (!error) { fsnotify_change(dentry, ia_valid); security_inode_post_setattr(idmap, dentry, ia_valid); - evm_inode_post_setattr(idmap, dentry, ia_valid); } return error; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 0d2371240c1b..5c90239e3f2b 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include @@ -1138,7 +1137,6 @@ retry_deleg: if (!error) { fsnotify_xattr(dentry); security_inode_post_set_acl(dentry, acl_name, kacl); - evm_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: @@ -1247,7 +1245,6 @@ retry_deleg: if (!error) { fsnotify_xattr(dentry); security_inode_post_remove_acl(idmap, dentry, acl_name); - evm_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: diff --git a/fs/xattr.c b/fs/xattr.c index f891c260a971..f8b643f91a98 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -557,7 +556,6 @@ __vfs_removexattr_locked(struct mnt_idmap *idmap, fsnotify_xattr(dentry); security_inode_post_removexattr(dentry, name); - evm_inode_post_removexattr(dentry, name); out: return error; diff --git a/include/linux/evm.h b/include/linux/evm.h index 3faabdd47852..cb481eccc967 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -21,45 +21,6 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, void *xattr_value, size_t xattr_value_len, struct integrity_iint_cache *iint); -extern int evm_inode_setattr(struct mnt_idmap *idmap, - struct dentry *dentry, struct iattr *attr); -extern void evm_inode_post_setattr(struct mnt_idmap *idmap, - struct dentry *dentry, int ia_valid); -extern int evm_inode_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -extern void evm_inode_post_setxattr(struct dentry *dentry, - const char *xattr_name, - const void *xattr_value, - size_t xattr_value_len, - int flags); -extern int evm_inode_copy_up_xattr(const char *name); -extern int evm_inode_removexattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *xattr_name); -extern void evm_inode_post_removexattr(struct dentry *dentry, - const char *xattr_name); -static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, - struct dentry *dentry, - const char *acl_name) -{ - evm_inode_post_removexattr(dentry, acl_name); -} -extern int evm_inode_set_acl(struct mnt_idmap *idmap, - struct dentry *dentry, const char *acl_name, - struct posix_acl *kacl); -static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, - struct dentry *dentry, - const char *acl_name) -{ - return evm_inode_set_acl(idmap, dentry, acl_name, NULL); -} -static inline void evm_inode_post_set_acl(struct dentry *dentry, - const char *acl_name, - struct posix_acl *kacl) -{ - return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); -} - int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count); @@ -94,80 +55,6 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif -static inline int evm_inode_setattr(struct mnt_idmap *idmap, - struct dentry *dentry, struct iattr *attr) -{ - return 0; -} - -static inline void evm_inode_post_setattr(struct mnt_idmap *idmap, - struct dentry *dentry, int ia_valid) -{ - return; -} - -static inline int evm_inode_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) -{ - return 0; -} - -static inline void evm_inode_post_setxattr(struct dentry *dentry, - const char *xattr_name, - const void *xattr_value, - size_t xattr_value_len, - int flags) -{ - return; -} - -static inline int evm_inode_copy_up_xattr(const char *name) -{ - return 0; -} - -static inline int evm_inode_removexattr(struct mnt_idmap *idmap, - struct dentry *dentry, - const char *xattr_name) -{ - return 0; -} - -static inline void evm_inode_post_removexattr(struct dentry *dentry, - const char *xattr_name) -{ - return; -} - -static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, - struct dentry *dentry, - const char *acl_name) -{ - return; -} - -static inline int evm_inode_set_acl(struct mnt_idmap *idmap, - struct dentry *dentry, const char *acl_name, - struct posix_acl *kacl) -{ - return 0; -} - -static inline int evm_inode_remove_acl(struct mnt_idmap *idmap, - struct dentry *dentry, - const char *acl_name) -{ - return 0; -} - -static inline void evm_inode_post_set_acl(struct dentry *dentry, - const char *acl_name, - struct posix_acl *kacl) -{ - return; -} - static inline int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h index b3b7fd699b63..33d8c9f4aa6b 100644 --- a/include/uapi/linux/lsm.h +++ b/include/uapi/linux/lsm.h @@ -63,6 +63,7 @@ struct lsm_ctx { #define LSM_ID_BPF 109 #define LSM_ID_LANDLOCK 110 #define LSM_ID_IMA 111 +#define LSM_ID_EVM 112 /* * LSM_ATTR_XXX definitions identify different LSM attributes diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index d35143179699..0a089af83a45 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -589,9 +589,9 @@ out: * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ -int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, - const char *xattr_name, const void *xattr_value, - size_t xattr_value_len, int flags) +static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, + const char *xattr_name, const void *xattr_value, + size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xattr_data = xattr_value; @@ -621,8 +621,8 @@ int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ -int evm_inode_removexattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *xattr_name) +static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, + const char *xattr_name) { /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded @@ -672,9 +672,11 @@ static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, * Prevent modifying posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. + * + * Return: zero on success, -EPERM on failure. */ -int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, - const char *acl_name, struct posix_acl *kacl) +static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, + const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; @@ -713,6 +715,24 @@ int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, return -EPERM; } +/** + * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls + * @idmap: idmap of the mount + * @dentry: pointer to the affected dentry + * @acl_name: name of the posix acl + * + * Prevent removing posix acls causing the EVM HMAC to be re-calculated + * and 'security.evm' xattr updated, unless the existing 'security.evm' is + * valid. + * + * Return: zero on success, -EPERM on failure. + */ +static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, + const char *acl_name) +{ + return evm_inode_set_acl(idmap, dentry, acl_name, NULL); +} + static void evm_reset_status(struct inode *inode) { struct integrity_iint_cache *iint; @@ -761,9 +781,11 @@ bool evm_revalidate_status(const char *xattr_name) * __vfs_setxattr_noperm(). The caller of which has taken the inode's * i_mutex lock. */ -void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, - const void *xattr_value, size_t xattr_value_len, - int flags) +static void evm_inode_post_setxattr(struct dentry *dentry, + const char *xattr_name, + const void *xattr_value, + size_t xattr_value_len, + int flags) { if (!evm_revalidate_status(xattr_name)) return; @@ -782,6 +804,21 @@ void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } +/** + * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls + * @dentry: pointer to the affected dentry + * @acl_name: name of the posix acl + * @kacl: pointer to the posix acls + * + * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting + * posix acls. + */ +static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, + struct posix_acl *kacl) +{ + return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); +} + /** * evm_inode_post_removexattr - update 'security.evm' after removing the xattr * @dentry: pointer to the affected dentry @@ -792,7 +829,8 @@ void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, * No need to take the i_mutex lock here, as this function is called from * vfs_removexattr() which takes the i_mutex. */ -void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) +static void evm_inode_post_removexattr(struct dentry *dentry, + const char *xattr_name) { if (!evm_revalidate_status(xattr_name)) return; @@ -808,6 +846,22 @@ void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) evm_update_evmxattr(dentry, xattr_name, NULL, 0); } +/** + * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls + * @idmap: idmap of the mount + * @dentry: pointer to the affected dentry + * @acl_name: name of the posix acl + * + * Update the 'security.evm' xattr with the EVM HMAC re-calculated after + * removing posix acls. + */ +static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, + struct dentry *dentry, + const char *acl_name) +{ + evm_inode_post_removexattr(dentry, acl_name); +} + static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { @@ -831,8 +885,8 @@ static int evm_attr_change(struct mnt_idmap *idmap, * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ -int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, - struct iattr *attr) +static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; enum integrity_status evm_status; @@ -883,8 +937,8 @@ int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ -void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, - int ia_valid) +static void evm_inode_post_setattr(struct mnt_idmap *idmap, + struct dentry *dentry, int ia_valid) { if (!evm_revalidate_status(NULL)) return; @@ -901,7 +955,7 @@ void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, evm_update_evmxattr(dentry, NULL, NULL, 0); } -int evm_inode_copy_up_xattr(const char *name) +static int evm_inode_copy_up_xattr(const char *name) { if (strcmp(name, XATTR_NAME_EVM) == 0) return 1; /* Discard */ @@ -1004,4 +1058,36 @@ error: return error; } +static struct security_hook_list evm_hooks[] __ro_after_init = { + LSM_HOOK_INIT(inode_setattr, evm_inode_setattr), + LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr), + LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr), + LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr), + LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr), + LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl), + LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl), + LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl), + LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl), + LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr), + LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr), + LSM_HOOK_INIT(inode_init_security, evm_inode_init_security), +}; + +static const struct lsm_id evm_lsmid = { + .name = "evm", + .id = LSM_ID_EVM, +}; + +static int __init init_evm_lsm(void) +{ + security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid); + return 0; +} + +DEFINE_LSM(evm) = { + .name = "evm", + .init = init_evm_lsm, + .order = LSM_ORDER_LAST, +}; + late_initcall(init_evm); diff --git a/security/security.c b/security/security.c index bed659b53e59..59cb0e6cbae3 100644 --- a/security/security.c +++ b/security/security.c @@ -20,13 +20,13 @@ #include #include #include -#include #include #include #include #include #include #include +#include #include #include @@ -50,7 +50,8 @@ (IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) ? 1 : 0) + \ (IS_ENABLED(CONFIG_BPF_LSM) ? 1 : 0) + \ (IS_ENABLED(CONFIG_SECURITY_LANDLOCK) ? 1 : 0) + \ - (IS_ENABLED(CONFIG_IMA) ? 1 : 0)) + (IS_ENABLED(CONFIG_IMA) ? 1 : 0) + \ + (IS_ENABLED(CONFIG_EVM) ? 1 : 0)) /* * These are descriptions of the reasons that can be passed to the @@ -1740,10 +1741,6 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, if (!xattr_count) goto out; - ret = evm_inode_init_security(inode, dir, qstr, new_xattrs, - &xattr_count); - if (ret) - goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (; xattr_count > 0; xattr_count--) @@ -2235,14 +2232,9 @@ int security_inode_permission(struct inode *inode, int mask) int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { - int ret; - if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - ret = call_int_hook(inode_setattr, 0, idmap, dentry, attr); - if (ret) - return ret; - return evm_inode_setattr(idmap, dentry, attr); + return call_int_hook(inode_setattr, 0, idmap, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); @@ -2307,9 +2299,7 @@ int security_inode_setxattr(struct mnt_idmap *idmap, if (ret == 1) ret = cap_inode_setxattr(dentry, name, value, size, flags); - if (ret) - return ret; - return evm_inode_setxattr(idmap, dentry, name, value, size, flags); + return ret; } /** @@ -2328,15 +2318,10 @@ int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { - int ret; - if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - ret = call_int_hook(inode_set_acl, 0, idmap, dentry, acl_name, - kacl); - if (ret) - return ret; - return evm_inode_set_acl(idmap, dentry, acl_name, kacl); + return call_int_hook(inode_set_acl, 0, idmap, dentry, acl_name, + kacl); } /** @@ -2389,14 +2374,9 @@ int security_inode_get_acl(struct mnt_idmap *idmap, int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { - int ret; - if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - ret = call_int_hook(inode_remove_acl, 0, idmap, dentry, acl_name); - if (ret) - return ret; - return evm_inode_remove_acl(idmap, dentry, acl_name); + return call_int_hook(inode_remove_acl, 0, idmap, dentry, acl_name); } /** @@ -2432,7 +2412,6 @@ void security_inode_post_setxattr(struct dentry *dentry, const char *name, if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); - evm_inode_post_setxattr(dentry, name, value, size, flags); } /** @@ -2493,9 +2472,7 @@ int security_inode_removexattr(struct mnt_idmap *idmap, ret = call_int_hook(inode_removexattr, 1, idmap, dentry, name); if (ret == 1) ret = cap_inode_removexattr(idmap, dentry, name); - if (ret) - return ret; - return evm_inode_removexattr(idmap, dentry, name); + return ret; } /** @@ -2699,7 +2676,7 @@ int security_inode_copy_up_xattr(const char *name) return rc; } - return evm_inode_copy_up_xattr(name); + return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); diff --git a/tools/testing/selftests/lsm/lsm_list_modules_test.c b/tools/testing/selftests/lsm/lsm_list_modules_test.c index 17333787cb2f..4d5d4cee2586 100644 --- a/tools/testing/selftests/lsm/lsm_list_modules_test.c +++ b/tools/testing/selftests/lsm/lsm_list_modules_test.c @@ -125,6 +125,9 @@ TEST(correct_lsm_list_modules) case LSM_ID_IMA: name = "ima"; break; + case LSM_ID_EVM: + name = "evm"; + break; default: name = "INVALID"; break; -- cgit v1.2.3 From 00a9bc6070434814d39118a0de70c1645f64bf60 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 12 Feb 2024 09:22:12 +0800 Subject: iommu: Move iommu fault data to linux/iommu.h The iommu fault data is currently defined in uapi/linux/iommu.h, but is only used inside the iommu subsystem. Move it to linux/iommu.h, where it will be more accessible to kernel drivers. With this done, uapi/linux/iommu.h becomes empty and can be removed from the tree. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Yi Liu Tested-by: Yan Zhao Tested-by: Longfang Liu Link: https://lore.kernel.org/r/20240212012227.119381-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- MAINTAINERS | 1 - include/linux/iommu.h | 152 +++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/iommu.h | 161 --------------------------------------------- 3 files changed, 151 insertions(+), 163 deletions(-) delete mode 100644 include/uapi/linux/iommu.h (limited to 'include/uapi') diff --git a/MAINTAINERS b/MAINTAINERS index 960512bec428..1bcdf3144415 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11240,7 +11240,6 @@ F: drivers/iommu/ F: include/linux/iommu.h F: include/linux/iova.h F: include/linux/of_iommu.h -F: include/uapi/linux/iommu.h IOMMUFD M: Jason Gunthorpe diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1ea2a820e1eb..472a8ce029b1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -14,7 +14,6 @@ #include #include #include -#include #define IOMMU_READ (1 << 0) #define IOMMU_WRITE (1 << 1) @@ -44,6 +43,157 @@ struct iommu_sva; struct iommu_fault_event; struct iommu_dma_cookie; +#define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ +#define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ +#define IOMMU_FAULT_PERM_EXEC (1 << 2) /* exec */ +#define IOMMU_FAULT_PERM_PRIV (1 << 3) /* privileged */ + +/* Generic fault types, can be expanded IRQ remapping fault */ +enum iommu_fault_type { + IOMMU_FAULT_DMA_UNRECOV = 1, /* unrecoverable fault */ + IOMMU_FAULT_PAGE_REQ, /* page request fault */ +}; + +enum iommu_fault_reason { + IOMMU_FAULT_REASON_UNKNOWN = 0, + + /* Could not access the PASID table (fetch caused external abort) */ + IOMMU_FAULT_REASON_PASID_FETCH, + + /* PASID entry is invalid or has configuration errors */ + IOMMU_FAULT_REASON_BAD_PASID_ENTRY, + + /* + * PASID is out of range (e.g. exceeds the maximum PASID + * supported by the IOMMU) or disabled. + */ + IOMMU_FAULT_REASON_PASID_INVALID, + + /* + * An external abort occurred fetching (or updating) a translation + * table descriptor + */ + IOMMU_FAULT_REASON_WALK_EABT, + + /* + * Could not access the page table entry (Bad address), + * actual translation fault + */ + IOMMU_FAULT_REASON_PTE_FETCH, + + /* Protection flag check failed */ + IOMMU_FAULT_REASON_PERMISSION, + + /* access flag check failed */ + IOMMU_FAULT_REASON_ACCESS, + + /* Output address of a translation stage caused Address Size fault */ + IOMMU_FAULT_REASON_OOR_ADDRESS, +}; + +/** + * struct iommu_fault_unrecoverable - Unrecoverable fault data + * @reason: reason of the fault, from &enum iommu_fault_reason + * @flags: parameters of this fault (IOMMU_FAULT_UNRECOV_* values) + * @pasid: Process Address Space ID + * @perm: requested permission access using by the incoming transaction + * (IOMMU_FAULT_PERM_* values) + * @addr: offending page address + * @fetch_addr: address that caused a fetch abort, if any + */ +struct iommu_fault_unrecoverable { + __u32 reason; +#define IOMMU_FAULT_UNRECOV_PASID_VALID (1 << 0) +#define IOMMU_FAULT_UNRECOV_ADDR_VALID (1 << 1) +#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID (1 << 2) + __u32 flags; + __u32 pasid; + __u32 perm; + __u64 addr; + __u64 fetch_addr; +}; + +/** + * struct iommu_fault_page_request - Page Request data + * @flags: encodes whether the corresponding fields are valid and whether this + * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values). + * When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response + * must have the same PASID value as the page request. When it is clear, + * the page response should not have a PASID. + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @perm: requested page permissions (IOMMU_FAULT_PERM_* values) + * @addr: page address + * @private_data: device-specific private information + */ +struct iommu_fault_page_request { +#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) +#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) +#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) + __u32 flags; + __u32 pasid; + __u32 grpid; + __u32 perm; + __u64 addr; + __u64 private_data[2]; +}; + +/** + * struct iommu_fault - Generic fault data + * @type: fault type from &enum iommu_fault_type + * @padding: reserved for future use (should be zero) + * @event: fault event, when @type is %IOMMU_FAULT_DMA_UNRECOV + * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ + * @padding2: sets the fault size to allow for future extensions + */ +struct iommu_fault { + __u32 type; + __u32 padding; + union { + struct iommu_fault_unrecoverable event; + struct iommu_fault_page_request prm; + __u8 padding2[56]; + }; +}; + +/** + * enum iommu_page_response_code - Return status of fault handlers + * @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables + * populated, retry the access. This is "Success" in PCI PRI. + * @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from + * this device if possible. This is "Response Failure" in PCI PRI. + * @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the + * access. This is "Invalid Request" in PCI PRI. + */ +enum iommu_page_response_code { + IOMMU_PAGE_RESP_SUCCESS = 0, + IOMMU_PAGE_RESP_INVALID, + IOMMU_PAGE_RESP_FAILURE, +}; + +/** + * struct iommu_page_response - Generic page response information + * @argsz: User filled size of this data + * @version: API version of this structure + * @flags: encodes whether the corresponding fields are valid + * (IOMMU_FAULT_PAGE_RESPONSE_* values) + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @code: response code from &enum iommu_page_response_code + */ +struct iommu_page_response { + __u32 argsz; +#define IOMMU_PAGE_RESP_VERSION_1 1 + __u32 version; +#define IOMMU_PAGE_RESP_PASID_VALID (1 << 0) + __u32 flags; + __u32 pasid; + __u32 grpid; + __u32 code; +}; + + /* iommu fault flags */ #define IOMMU_FAULT_READ 0x0 #define IOMMU_FAULT_WRITE 0x1 diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h deleted file mode 100644 index 65d8b0234f69..000000000000 --- a/include/uapi/linux/iommu.h +++ /dev/null @@ -1,161 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * IOMMU user API definitions - */ - -#ifndef _UAPI_IOMMU_H -#define _UAPI_IOMMU_H - -#include - -#define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ -#define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ -#define IOMMU_FAULT_PERM_EXEC (1 << 2) /* exec */ -#define IOMMU_FAULT_PERM_PRIV (1 << 3) /* privileged */ - -/* Generic fault types, can be expanded IRQ remapping fault */ -enum iommu_fault_type { - IOMMU_FAULT_DMA_UNRECOV = 1, /* unrecoverable fault */ - IOMMU_FAULT_PAGE_REQ, /* page request fault */ -}; - -enum iommu_fault_reason { - IOMMU_FAULT_REASON_UNKNOWN = 0, - - /* Could not access the PASID table (fetch caused external abort) */ - IOMMU_FAULT_REASON_PASID_FETCH, - - /* PASID entry is invalid or has configuration errors */ - IOMMU_FAULT_REASON_BAD_PASID_ENTRY, - - /* - * PASID is out of range (e.g. exceeds the maximum PASID - * supported by the IOMMU) or disabled. - */ - IOMMU_FAULT_REASON_PASID_INVALID, - - /* - * An external abort occurred fetching (or updating) a translation - * table descriptor - */ - IOMMU_FAULT_REASON_WALK_EABT, - - /* - * Could not access the page table entry (Bad address), - * actual translation fault - */ - IOMMU_FAULT_REASON_PTE_FETCH, - - /* Protection flag check failed */ - IOMMU_FAULT_REASON_PERMISSION, - - /* access flag check failed */ - IOMMU_FAULT_REASON_ACCESS, - - /* Output address of a translation stage caused Address Size fault */ - IOMMU_FAULT_REASON_OOR_ADDRESS, -}; - -/** - * struct iommu_fault_unrecoverable - Unrecoverable fault data - * @reason: reason of the fault, from &enum iommu_fault_reason - * @flags: parameters of this fault (IOMMU_FAULT_UNRECOV_* values) - * @pasid: Process Address Space ID - * @perm: requested permission access using by the incoming transaction - * (IOMMU_FAULT_PERM_* values) - * @addr: offending page address - * @fetch_addr: address that caused a fetch abort, if any - */ -struct iommu_fault_unrecoverable { - __u32 reason; -#define IOMMU_FAULT_UNRECOV_PASID_VALID (1 << 0) -#define IOMMU_FAULT_UNRECOV_ADDR_VALID (1 << 1) -#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID (1 << 2) - __u32 flags; - __u32 pasid; - __u32 perm; - __u64 addr; - __u64 fetch_addr; -}; - -/** - * struct iommu_fault_page_request - Page Request data - * @flags: encodes whether the corresponding fields are valid and whether this - * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values). - * When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response - * must have the same PASID value as the page request. When it is clear, - * the page response should not have a PASID. - * @pasid: Process Address Space ID - * @grpid: Page Request Group Index - * @perm: requested page permissions (IOMMU_FAULT_PERM_* values) - * @addr: page address - * @private_data: device-specific private information - */ -struct iommu_fault_page_request { -#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) -#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) -#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) -#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) - __u32 flags; - __u32 pasid; - __u32 grpid; - __u32 perm; - __u64 addr; - __u64 private_data[2]; -}; - -/** - * struct iommu_fault - Generic fault data - * @type: fault type from &enum iommu_fault_type - * @padding: reserved for future use (should be zero) - * @event: fault event, when @type is %IOMMU_FAULT_DMA_UNRECOV - * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ - * @padding2: sets the fault size to allow for future extensions - */ -struct iommu_fault { - __u32 type; - __u32 padding; - union { - struct iommu_fault_unrecoverable event; - struct iommu_fault_page_request prm; - __u8 padding2[56]; - }; -}; - -/** - * enum iommu_page_response_code - Return status of fault handlers - * @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables - * populated, retry the access. This is "Success" in PCI PRI. - * @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from - * this device if possible. This is "Response Failure" in PCI PRI. - * @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the - * access. This is "Invalid Request" in PCI PRI. - */ -enum iommu_page_response_code { - IOMMU_PAGE_RESP_SUCCESS = 0, - IOMMU_PAGE_RESP_INVALID, - IOMMU_PAGE_RESP_FAILURE, -}; - -/** - * struct iommu_page_response - Generic page response information - * @argsz: User filled size of this data - * @version: API version of this structure - * @flags: encodes whether the corresponding fields are valid - * (IOMMU_FAULT_PAGE_RESPONSE_* values) - * @pasid: Process Address Space ID - * @grpid: Page Request Group Index - * @code: response code from &enum iommu_page_response_code - */ -struct iommu_page_response { - __u32 argsz; -#define IOMMU_PAGE_RESP_VERSION_1 1 - __u32 version; -#define IOMMU_PAGE_RESP_PASID_VALID (1 << 0) - __u32 flags; - __u32 pasid; - __u32 grpid; - __u32 code; -}; - -#endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3 From 7b07a2a7ca02a20124b552be96c5a56910795488 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 30 Jan 2024 13:23:39 +0100 Subject: usb: gadget: functionfs: Add DMABUF import interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch introduces three new ioctls. They all should be called on a data endpoint (ie. not ep0). They are: - FUNCTIONFS_DMABUF_ATTACH, which takes the file descriptor of a DMABUF object to attach to the endpoint. - FUNCTIONFS_DMABUF_DETACH, which takes the file descriptor of the DMABUF to detach from the endpoint. Note that closing the endpoint's file descriptor will automatically detach all attached DMABUFs. - FUNCTIONFS_DMABUF_TRANSFER, which requests a data transfer from / to the given DMABUF. Its argument is a structure that packs the DMABUF's file descriptor, the size in bytes to transfer (which should generally be set to the size of the DMABUF), and a 'flags' field which is unused for now. Before this ioctl can be used, the related DMABUF must be attached with FUNCTIONFS_DMABUF_ATTACH. These three ioctls enable the FunctionFS code to transfer data between the USB stack and a DMABUF object, which can be provided by a driver from a completely different subsystem, in a zero-copy fashion. Signed-off-by: Paul Cercueil Acked-by: Daniel Vetter Acked-by: Christian König Link: https://lore.kernel.org/r/20240130122340.54813-4-paul@crapouillou.net Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/Kconfig | 1 + drivers/usb/gadget/function/f_fs.c | 467 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/usb/functionfs.h | 41 ++++ 3 files changed, 509 insertions(+) (limited to 'include/uapi') diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index b3592bcb0f96..566ff0b1282a 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -190,6 +190,7 @@ config USB_F_MASS_STORAGE tristate config USB_F_FS + select DMA_SHARED_BUFFER tristate config USB_F_UAC1 diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 491a1e0f4fa3..bffbc1dc651f 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -15,6 +15,9 @@ /* #define VERBOSE_DEBUG */ #include +#include +#include +#include #include #include #include @@ -43,6 +46,8 @@ #define FUNCTIONFS_MAGIC 0xa647361 /* Chosen by a honest dice roll ;) */ +MODULE_IMPORT_NS(DMA_BUF); + /* Reference counter handling */ static void ffs_data_get(struct ffs_data *ffs); static void ffs_data_put(struct ffs_data *ffs); @@ -124,6 +129,25 @@ struct ffs_ep { u8 num; }; +struct ffs_dmabuf_priv { + struct list_head entry; + struct kref ref; + struct ffs_data *ffs; + struct dma_buf_attachment *attach; + struct sg_table *sgt; + enum dma_data_direction dir; + spinlock_t lock; + u64 context; + struct usb_request *req; /* P: ffs->eps_lock */ + struct usb_ep *ep; /* P: ffs->eps_lock */ +}; + +struct ffs_dma_fence { + struct dma_fence base; + struct ffs_dmabuf_priv *priv; + struct work_struct work; +}; + struct ffs_epfile { /* Protects ep->ep and ep->req. */ struct mutex mutex; @@ -197,6 +221,11 @@ struct ffs_epfile { unsigned char isoc; /* P: ffs->eps_lock */ unsigned char _pad; + + /* Protects dmabufs */ + struct mutex dmabufs_mutex; + struct list_head dmabufs; /* P: dmabufs_mutex */ + atomic_t seqno; }; struct ffs_buffer { @@ -1271,10 +1300,58 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) return res; } +static void ffs_dmabuf_release(struct kref *ref) +{ + struct ffs_dmabuf_priv *priv = container_of(ref, struct ffs_dmabuf_priv, ref); + struct dma_buf_attachment *attach = priv->attach; + struct dma_buf *dmabuf = attach->dmabuf; + + pr_vdebug("FFS DMABUF release\n"); + dma_resv_lock(dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); + dma_resv_unlock(dmabuf->resv); + + dma_buf_detach(attach->dmabuf, attach); + dma_buf_put(dmabuf); + kfree(priv); +} + +static void ffs_dmabuf_get(struct dma_buf_attachment *attach) +{ + struct ffs_dmabuf_priv *priv = attach->importer_priv; + + kref_get(&priv->ref); +} + +static void ffs_dmabuf_put(struct dma_buf_attachment *attach) +{ + struct ffs_dmabuf_priv *priv = attach->importer_priv; + + kref_put(&priv->ref, ffs_dmabuf_release); +} + static int ffs_epfile_release(struct inode *inode, struct file *file) { struct ffs_epfile *epfile = inode->i_private; + struct ffs_dmabuf_priv *priv, *tmp; + struct ffs_data *ffs = epfile->ffs; + + mutex_lock(&epfile->dmabufs_mutex); + + /* Close all attached DMABUFs */ + list_for_each_entry_safe(priv, tmp, &epfile->dmabufs, entry) { + /* Cancel any pending transfer */ + spin_lock_irq(&ffs->eps_lock); + if (priv->ep && priv->req) + usb_ep_dequeue(priv->ep, priv->req); + spin_unlock_irq(&ffs->eps_lock); + + list_del(&priv->entry); + ffs_dmabuf_put(priv->attach); + } + + mutex_unlock(&epfile->dmabufs_mutex); __ffs_epfile_read_buffer_free(epfile); ffs_data_closed(epfile->ffs); @@ -1282,6 +1359,356 @@ ffs_epfile_release(struct inode *inode, struct file *file) return 0; } +static void ffs_dmabuf_cleanup(struct work_struct *work) +{ + struct ffs_dma_fence *dma_fence = + container_of(work, struct ffs_dma_fence, work); + struct ffs_dmabuf_priv *priv = dma_fence->priv; + struct dma_buf_attachment *attach = priv->attach; + struct dma_fence *fence = &dma_fence->base; + + ffs_dmabuf_put(attach); + dma_fence_put(fence); +} + +static void ffs_dmabuf_signal_done(struct ffs_dma_fence *dma_fence, int ret) +{ + struct ffs_dmabuf_priv *priv = dma_fence->priv; + struct dma_fence *fence = &dma_fence->base; + bool cookie = dma_fence_begin_signalling(); + + dma_fence_get(fence); + fence->error = ret; + dma_fence_signal(fence); + dma_fence_end_signalling(cookie); + + /* + * The fence will be unref'd in ffs_dmabuf_cleanup. + * It can't be done here, as the unref functions might try to lock + * the resv object, which would deadlock. + */ + INIT_WORK(&dma_fence->work, ffs_dmabuf_cleanup); + queue_work(priv->ffs->io_completion_wq, &dma_fence->work); +} + +static void ffs_epfile_dmabuf_io_complete(struct usb_ep *ep, + struct usb_request *req) +{ + pr_vdebug("FFS: DMABUF transfer complete, status=%d\n", req->status); + ffs_dmabuf_signal_done(req->context, req->status); + usb_ep_free_request(ep, req); +} + +static const char *ffs_dmabuf_get_driver_name(struct dma_fence *fence) +{ + return "functionfs"; +} + +static const char *ffs_dmabuf_get_timeline_name(struct dma_fence *fence) +{ + return ""; +} + +static void ffs_dmabuf_fence_release(struct dma_fence *fence) +{ + struct ffs_dma_fence *dma_fence = + container_of(fence, struct ffs_dma_fence, base); + + kfree(dma_fence); +} + +static const struct dma_fence_ops ffs_dmabuf_fence_ops = { + .get_driver_name = ffs_dmabuf_get_driver_name, + .get_timeline_name = ffs_dmabuf_get_timeline_name, + .release = ffs_dmabuf_fence_release, +}; + +static int ffs_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock) +{ + if (!nonblock) + return dma_resv_lock_interruptible(dmabuf->resv, NULL); + + if (!dma_resv_trylock(dmabuf->resv)) + return -EBUSY; + + return 0; +} + +static struct dma_buf_attachment * +ffs_dmabuf_find_attachment(struct ffs_epfile *epfile, struct dma_buf *dmabuf) +{ + struct device *dev = epfile->ffs->gadget->dev.parent; + struct dma_buf_attachment *attach = NULL; + struct ffs_dmabuf_priv *priv; + + mutex_lock(&epfile->dmabufs_mutex); + + list_for_each_entry(priv, &epfile->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + attach = priv->attach; + break; + } + } + + if (attach) + ffs_dmabuf_get(attach); + + mutex_unlock(&epfile->dmabufs_mutex); + + return attach ?: ERR_PTR(-EPERM); +} + +static int ffs_dmabuf_attach(struct file *file, int fd) +{ + bool nonblock = file->f_flags & O_NONBLOCK; + struct ffs_epfile *epfile = file->private_data; + struct usb_gadget *gadget = epfile->ffs->gadget; + struct dma_buf_attachment *attach; + struct ffs_dmabuf_priv *priv; + enum dma_data_direction dir; + struct sg_table *sg_table; + struct dma_buf *dmabuf; + int err; + + if (!gadget || !gadget->sg_supported) + return -EPERM; + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + attach = dma_buf_attach(dmabuf, gadget->dev.parent); + if (IS_ERR(attach)) { + err = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto err_dmabuf_detach; + } + + dir = epfile->in ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + err = ffs_dma_resv_lock(dmabuf, nonblock); + if (err) + goto err_free_priv; + + sg_table = dma_buf_map_attachment(attach, dir); + dma_resv_unlock(dmabuf->resv); + + if (IS_ERR(sg_table)) { + err = PTR_ERR(sg_table); + goto err_free_priv; + } + + attach->importer_priv = priv; + + priv->sgt = sg_table; + priv->dir = dir; + priv->ffs = epfile->ffs; + priv->attach = attach; + spin_lock_init(&priv->lock); + kref_init(&priv->ref); + priv->context = dma_fence_context_alloc(1); + + mutex_lock(&epfile->dmabufs_mutex); + list_add(&priv->entry, &epfile->dmabufs); + mutex_unlock(&epfile->dmabufs_mutex); + + return 0; + +err_free_priv: + kfree(priv); +err_dmabuf_detach: + dma_buf_detach(dmabuf, attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return err; +} + +static int ffs_dmabuf_detach(struct file *file, int fd) +{ + struct ffs_epfile *epfile = file->private_data; + struct ffs_data *ffs = epfile->ffs; + struct device *dev = ffs->gadget->dev.parent; + struct ffs_dmabuf_priv *priv, *tmp; + struct dma_buf *dmabuf; + int ret = -EPERM; + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + mutex_lock(&epfile->dmabufs_mutex); + + list_for_each_entry_safe(priv, tmp, &epfile->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + /* Cancel any pending transfer */ + spin_lock_irq(&ffs->eps_lock); + if (priv->ep && priv->req) + usb_ep_dequeue(priv->ep, priv->req); + spin_unlock_irq(&ffs->eps_lock); + + list_del(&priv->entry); + + /* Unref the reference from ffs_dmabuf_attach() */ + ffs_dmabuf_put(priv->attach); + ret = 0; + break; + } + } + + mutex_unlock(&epfile->dmabufs_mutex); + dma_buf_put(dmabuf); + + return ret; +} + +static int ffs_dmabuf_transfer(struct file *file, + const struct usb_ffs_dmabuf_transfer_req *req) +{ + bool nonblock = file->f_flags & O_NONBLOCK; + struct ffs_epfile *epfile = file->private_data; + struct dma_buf_attachment *attach; + struct ffs_dmabuf_priv *priv; + struct ffs_dma_fence *fence; + struct usb_request *usb_req; + struct dma_buf *dmabuf; + struct ffs_ep *ep; + bool cookie; + u32 seqno; + int ret; + + if (req->flags & ~USB_FFS_DMABUF_TRANSFER_MASK) + return -EINVAL; + + dmabuf = dma_buf_get(req->fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + if (req->length > dmabuf->size || req->length == 0) { + ret = -EINVAL; + goto err_dmabuf_put; + } + + attach = ffs_dmabuf_find_attachment(epfile, dmabuf); + if (IS_ERR(attach)) { + ret = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = attach->importer_priv; + + ep = ffs_epfile_wait_ep(file); + if (IS_ERR(ep)) { + ret = PTR_ERR(ep); + goto err_attachment_put; + } + + ret = ffs_dma_resv_lock(dmabuf, nonblock); + if (ret) + goto err_attachment_put; + + /* Make sure we don't have writers */ + if (!dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_WRITE)) { + pr_vdebug("FFS WRITE fence is not signaled\n"); + ret = -EBUSY; + goto err_resv_unlock; + } + + /* If we're writing to the DMABUF, make sure we don't have readers */ + if (epfile->in && + !dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_READ)) { + pr_vdebug("FFS READ fence is not signaled\n"); + ret = -EBUSY; + goto err_resv_unlock; + } + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (ret) + goto err_resv_unlock; + + fence = kmalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) { + ret = -ENOMEM; + goto err_resv_unlock; + } + + fence->priv = priv; + + spin_lock_irq(&epfile->ffs->eps_lock); + + /* In the meantime, endpoint got disabled or changed. */ + if (epfile->ep != ep) { + ret = -ESHUTDOWN; + goto err_fence_put; + } + + usb_req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC); + if (!usb_req) { + ret = -ENOMEM; + goto err_fence_put; + } + + /* + * usb_ep_queue() guarantees that all transfers are processed in the + * order they are enqueued, so we can use a simple incrementing + * sequence number for the dma_fence. + */ + seqno = atomic_add_return(1, &epfile->seqno); + + dma_fence_init(&fence->base, &ffs_dmabuf_fence_ops, + &priv->lock, priv->context, seqno); + + dma_resv_add_fence(dmabuf->resv, &fence->base, + dma_resv_usage_rw(epfile->in)); + dma_resv_unlock(dmabuf->resv); + + /* Now that the dma_fence is in place, queue the transfer. */ + + usb_req->length = req->length; + usb_req->buf = NULL; + usb_req->sg = priv->sgt->sgl; + usb_req->num_sgs = sg_nents_for_len(priv->sgt->sgl, req->length); + usb_req->sg_was_mapped = true; + usb_req->context = fence; + usb_req->complete = ffs_epfile_dmabuf_io_complete; + + cookie = dma_fence_begin_signalling(); + ret = usb_ep_queue(ep->ep, usb_req, GFP_ATOMIC); + dma_fence_end_signalling(cookie); + if (!ret) { + priv->req = usb_req; + priv->ep = ep->ep; + } else { + pr_warn("FFS: Failed to queue DMABUF: %d\n", ret); + ffs_dmabuf_signal_done(fence, ret); + usb_ep_free_request(ep->ep, usb_req); + } + + spin_unlock_irq(&epfile->ffs->eps_lock); + dma_buf_put(dmabuf); + + return ret; + +err_fence_put: + spin_unlock_irq(&epfile->ffs->eps_lock); + dma_fence_put(&fence->base); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_attachment_put: + ffs_dmabuf_put(attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return ret; +} + static long ffs_epfile_ioctl(struct file *file, unsigned code, unsigned long value) { @@ -1292,6 +1719,44 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, if (WARN_ON(epfile->ffs->state != FFS_ACTIVE)) return -ENODEV; + switch (code) { + case FUNCTIONFS_DMABUF_ATTACH: + { + int fd; + + if (copy_from_user(&fd, (void __user *)value, sizeof(fd))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_attach(file, fd); + } + case FUNCTIONFS_DMABUF_DETACH: + { + int fd; + + if (copy_from_user(&fd, (void __user *)value, sizeof(fd))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_detach(file, fd); + } + case FUNCTIONFS_DMABUF_TRANSFER: + { + struct usb_ffs_dmabuf_transfer_req req; + + if (copy_from_user(&req, (void __user *)value, sizeof(req))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_transfer(file, &req); + } + default: + break; + } + /* Wait for endpoint to be enabled */ ep = ffs_epfile_wait_ep(file); if (IS_ERR(ep)) @@ -1869,6 +2334,8 @@ static int ffs_epfiles_create(struct ffs_data *ffs) for (i = 1; i <= count; ++i, ++epfile) { epfile->ffs = ffs; mutex_init(&epfile->mutex); + mutex_init(&epfile->dmabufs_mutex); + INIT_LIST_HEAD(&epfile->dmabufs); if (ffs->user_flags & FUNCTIONFS_VIRTUAL_ADDR) sprintf(epfile->name, "ep%02x", ffs->eps_addrmap[i]); else diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 078098e73fd3..9f88de9c3d66 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -86,6 +86,22 @@ struct usb_ext_prop_desc { __le16 wPropertyNameLength; } __attribute__((packed)); +/* Flags for usb_ffs_dmabuf_transfer_req->flags (none for now) */ +#define USB_FFS_DMABUF_TRANSFER_MASK 0x0 + +/** + * struct usb_ffs_dmabuf_transfer_req - Transfer request for a DMABUF object + * @fd: file descriptor of the DMABUF object + * @flags: one or more USB_FFS_DMABUF_TRANSFER_* flags + * @length: number of bytes used in this DMABUF for the data transfer. + * Should generally be set to the DMABUF's size. + */ +struct usb_ffs_dmabuf_transfer_req { + int fd; + __u32 flags; + __u64 length; +} __attribute__((packed)); + #ifndef __KERNEL__ /* @@ -290,6 +306,31 @@ struct usb_functionfs_event { #define FUNCTIONFS_ENDPOINT_DESC _IOR('g', 130, \ struct usb_endpoint_descriptor) +/* + * Attach the DMABUF object, identified by its file descriptor, to the + * data endpoint. Returns zero on success, and a negative errno value + * on error. + */ +#define FUNCTIONFS_DMABUF_ATTACH _IOW('g', 131, int) + +/* + * Detach the given DMABUF object, identified by its file descriptor, + * from the data endpoint. Returns zero on success, and a negative + * errno value on error. Note that closing the endpoint's file + * descriptor will automatically detach all attached DMABUFs. + */ +#define FUNCTIONFS_DMABUF_DETACH _IOW('g', 132, int) + +/* + * Enqueue the previously attached DMABUF to the transfer queue. + * The argument is a structure that packs the DMABUF's file descriptor, + * the size in bytes to transfer (which should generally correspond to + * the size of the DMABUF), and a 'flags' field which is unused + * for now. Returns zero on success, and a negative errno value on + * error. + */ +#define FUNCTIONFS_DMABUF_TRANSFER _IOW('g', 133, \ + struct usb_ffs_dmabuf_transfer_req) #endif /* _UAPI__LINUX_FUNCTIONFS_H__ */ -- cgit v1.2.3 From 1e63e5a813fa6203d7430af51d6bffb728525015 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Feb 2024 15:27:44 -0800 Subject: net: sched: Annotate struct tc_pedit with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct tc_pedit. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. Link: https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci [1] Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_pedit.h | 2 +- net/sched/act_pedit.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index f3e61b04fa01..f5cab7fc96ab 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -62,7 +62,7 @@ struct tc_pedit_sel { tc_gen; unsigned char nkeys; unsigned char flags; - struct tc_pedit_key keys[0]; + struct tc_pedit_key keys[] __counted_by(nkeys); }; #define tc_pedit tc_pedit_sel diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index df5a02d5f919..fc0a35a7b62a 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -515,11 +515,11 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, spin_unlock_bh(&p->tcf_lock); return -ENOBUFS; } + opt->nkeys = parms->tcfp_nkeys; memcpy(opt->keys, parms->tcfp_keys, flex_array_size(opt, keys, parms->tcfp_nkeys)); opt->index = p->tcf_index; - opt->nkeys = parms->tcfp_nkeys; opt->flags = parms->tcfp_flags; opt->action = p->tcf_action; opt->refcnt = refcount_read(&p->tcf_refcnt) - ref; -- cgit v1.2.3 From 5cf0fbf7637410aea88819e64a4bd5ea14ccbbfc Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Mon, 19 Feb 2024 13:25:17 +0000 Subject: drm/i915: Add some boring kerneldoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Tooling appears very strict so lets pacify it by adding some comments, even if fields are completely self-explanatory. Signed-off-by: Tvrtko Ursulin Fixes: b11236486749 ("drm/i915: Add GuC submission interface version query") Reported-by: Stephen Rothwell Cc: Jose Souza Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20240219132517.1868604-1-tvrtko.ursulin@linux.intel.com --- include/uapi/drm/i915_drm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index bd87386a8243..2ee338860b7e 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -3572,9 +3572,13 @@ struct drm_i915_query_memory_regions { * struct drm_i915_query_guc_submission_version - query GuC submission interface version */ struct drm_i915_query_guc_submission_version { + /** @branch: Firmware branch version. */ __u32 branch; + /** @major: Firmware major version. */ __u32 major; + /** @minor: Firmware minor version. */ __u32 minor; + /** @patch: Firmware patch version. */ __u32 patch; }; -- cgit v1.2.3 From e1fb1dc08e73466830612bcf2f9f72180965c9ba Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 9 Feb 2024 15:49:45 +0100 Subject: pidfd: allow to override signal scope in pidfd_send_signal() Right now we determine the scope of the signal based on the type of pidfd. There are use-cases where it's useful to override the scope of the signal. For example in [1]. Add flags to determine the scope of the signal: (1) PIDFD_SIGNAL_THREAD: send signal to specific thread reference by @pidfd (2) PIDFD_SIGNAL_THREAD_GROUP: send signal to thread-group of @pidfd (2) PIDFD_SIGNAL_PROCESS_GROUP: send signal to process-group of @pidfd Since we now allow specifying PIDFD_SEND_PROCESS_GROUP for pidfd_send_signal() to send signals to process groups we need to adjust the check restricting si_code emulation by userspace to account for PIDTYPE_PGID. Reviewed-by: Oleg Nesterov Link: https://github.com/systemd/systemd/issues/31093 [1] Link: https://lore.kernel.org/r/20240210-chihuahua-hinzog-3945b6abd44a@brauner Link: https://lore.kernel.org/r/20240214123655.GB16265@redhat.com Signed-off-by: Christian Brauner --- include/uapi/linux/pidfd.h | 5 +++++ kernel/signal.c | 46 +++++++++++++++++++++++++++++++++++++--------- 2 files changed, 42 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 2e6461459877..72ec000a97cd 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -10,4 +10,9 @@ #define PIDFD_NONBLOCK O_NONBLOCK #define PIDFD_THREAD O_EXCL +/* Flags for pidfd_send_signal(). */ +#define PIDFD_SIGNAL_THREAD (1UL << 0) +#define PIDFD_SIGNAL_THREAD_GROUP (1UL << 1) +#define PIDFD_SIGNAL_PROCESS_GROUP (1UL << 2) + #endif /* _UAPI_LINUX_PIDFD_H */ diff --git a/kernel/signal.c b/kernel/signal.c index 8b8169623850..bdca529f0f7b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1905,16 +1905,19 @@ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, return send_sig_info(info.si_signo, &info, t); } -int kill_pgrp(struct pid *pid, int sig, int priv) +static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { int ret; - read_lock(&tasklist_lock); - ret = __kill_pgrp_info(sig, __si_special(priv), pid); + ret = __kill_pgrp_info(sig, info, pgrp); read_unlock(&tasklist_lock); - return ret; } + +int kill_pgrp(struct pid *pid, int sig, int priv) +{ + return kill_pgrp_info(sig, __si_special(priv), pid); +} EXPORT_SYMBOL(kill_pgrp); int kill_pid(struct pid *pid, int sig, int priv) @@ -3873,6 +3876,10 @@ static struct pid *pidfd_to_pid(const struct file *file) return tgid_pidfd_to_pid(file); } +#define PIDFD_SEND_SIGNAL_FLAGS \ + (PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \ + PIDFD_SIGNAL_PROCESS_GROUP) + /** * sys_pidfd_send_signal - Signal a process through a pidfd * @pidfd: file descriptor of the process @@ -3897,7 +3904,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, enum pid_type type; /* Enforce flags be set to 0 until we add an extension. */ - if (flags) + if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) + return -EINVAL; + + /* Ensure that only a single signal scope determining flag is set. */ + if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1) return -EINVAL; f = fdget(pidfd); @@ -3915,10 +3926,24 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (!access_pidfd_pidns(pid)) goto err; - if (f.file->f_flags & PIDFD_THREAD) + switch (flags) { + case 0: + /* Infer scope from the type of pidfd. */ + if (f.file->f_flags & PIDFD_THREAD) + type = PIDTYPE_PID; + else + type = PIDTYPE_TGID; + break; + case PIDFD_SIGNAL_THREAD: type = PIDTYPE_PID; - else + break; + case PIDFD_SIGNAL_THREAD_GROUP: type = PIDTYPE_TGID; + break; + case PIDFD_SIGNAL_PROCESS_GROUP: + type = PIDTYPE_PGID; + break; + } if (info) { ret = copy_siginfo_from_user_any(&kinfo, info); @@ -3931,14 +3956,17 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, /* Only allow sending arbitrary signals to yourself. */ ret = -EPERM; - if ((task_pid(current) != pid) && + if ((task_pid(current) != pid || type > PIDTYPE_TGID) && (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) goto err; } else { prepare_kill_siginfo(sig, &kinfo, type); } - ret = kill_pid_info_type(sig, &kinfo, pid, type); + if (type == PIDTYPE_PGID) + ret = kill_pgrp_info(sig, &kinfo, pid); + else + ret = kill_pid_info_type(sig, &kinfo, pid, type); err: fdput(f); return ret; -- cgit v1.2.3 From 77aebae1ea12de6eae5ce70d05b3d4724eec4023 Mon Sep 17 00:00:00 2001 From: Thomas Hellström Date: Fri, 9 Feb 2024 12:34:44 +0100 Subject: drm/xe/uapi: Remove support for persistent exec_queues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Persistent exec_queues delays explicit destruction of exec_queues until they are done executing, but destruction on process exit is still immediate. It turns out no UMD is relying on this functionality, so remove it. If there turns out to be a use-case in the future, let's re-add. Persistent exec_queues were never used for LR VMs v2: - Don't add an "UNUSED" define for the missing property (Lucas, Rodrigo) v3: - Remove the remaining struct xe_exec_queue::persistent state (Niranjana, Lucas) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Rodrigo Vivi Cc: Matthew Brost Cc: David Airlie Cc: Daniel Vetter Cc: Lucas De Marchi Cc: Francois Dugast Signed-off-by: Thomas Hellström Reviewed-by: Lucas De Marchi Acked-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20240209113444.8396-1-thomas.hellstrom@linux.intel.com (cherry picked from commit f1a9abc0cf311375695bede1590364864c05976d) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_device.c | 39 -------------------------------- drivers/gpu/drm/xe/xe_device.h | 4 ---- drivers/gpu/drm/xe/xe_device_types.h | 8 ------- drivers/gpu/drm/xe/xe_exec_queue.c | 33 ++++----------------------- drivers/gpu/drm/xe/xe_exec_queue_types.h | 10 -------- drivers/gpu/drm/xe/xe_execlist.c | 2 -- drivers/gpu/drm/xe/xe_guc_submit.c | 2 -- include/uapi/drm/xe_drm.h | 1 - 8 files changed, 5 insertions(+), 94 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 1f0b4b9ce84f..5176c27e4b6a 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -83,9 +83,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) return 0; } -static void device_kill_persistent_exec_queues(struct xe_device *xe, - struct xe_file *xef); - static void xe_file_close(struct drm_device *dev, struct drm_file *file) { struct xe_device *xe = to_xe_device(dev); @@ -102,8 +99,6 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file) mutex_unlock(&xef->exec_queue.lock); xa_destroy(&xef->exec_queue.xa); mutex_destroy(&xef->exec_queue.lock); - device_kill_persistent_exec_queues(xe, xef); - mutex_lock(&xef->vm.lock); xa_for_each(&xef->vm.xa, idx, vm) xe_vm_close_and_put(vm); @@ -255,9 +250,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xa_erase(&xe->usm.asid_to_vm, asid); } - drmm_mutex_init(&xe->drm, &xe->persistent_engines.lock); - INIT_LIST_HEAD(&xe->persistent_engines.list); - spin_lock_init(&xe->pinned.lock); INIT_LIST_HEAD(&xe->pinned.kernel_bo_present); INIT_LIST_HEAD(&xe->pinned.external_vram); @@ -570,37 +562,6 @@ void xe_device_shutdown(struct xe_device *xe) { } -void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q) -{ - mutex_lock(&xe->persistent_engines.lock); - list_add_tail(&q->persistent.link, &xe->persistent_engines.list); - mutex_unlock(&xe->persistent_engines.lock); -} - -void xe_device_remove_persistent_exec_queues(struct xe_device *xe, - struct xe_exec_queue *q) -{ - mutex_lock(&xe->persistent_engines.lock); - if (!list_empty(&q->persistent.link)) - list_del(&q->persistent.link); - mutex_unlock(&xe->persistent_engines.lock); -} - -static void device_kill_persistent_exec_queues(struct xe_device *xe, - struct xe_file *xef) -{ - struct xe_exec_queue *q, *next; - - mutex_lock(&xe->persistent_engines.lock); - list_for_each_entry_safe(q, next, &xe->persistent_engines.list, - persistent.link) - if (q->persistent.xef == xef) { - xe_exec_queue_kill(q); - list_del_init(&q->persistent.link); - } - mutex_unlock(&xe->persistent_engines.lock); -} - void xe_device_wmb(struct xe_device *xe) { struct xe_gt *gt = xe_root_mmio_gt(xe); diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index 3da83b233206..08d8b72c7731 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -42,10 +42,6 @@ int xe_device_probe(struct xe_device *xe); void xe_device_remove(struct xe_device *xe); void xe_device_shutdown(struct xe_device *xe); -void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q); -void xe_device_remove_persistent_exec_queues(struct xe_device *xe, - struct xe_exec_queue *q); - void xe_device_wmb(struct xe_device *xe); static inline struct xe_file *to_xe_file(const struct drm_file *file) diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 5dc9127a2029..e8491979a6f2 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -341,14 +341,6 @@ struct xe_device { struct mutex lock; } usm; - /** @persistent_engines: engines that are closed but still running */ - struct { - /** @lock: protects persistent engines */ - struct mutex lock; - /** @list: list of persistent engines */ - struct list_head list; - } persistent_engines; - /** @pinned: pinned BO state */ struct { /** @lock: protected pinned BO list state */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 254b1d3af4cb..3acfd4f07666 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -60,7 +60,6 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe, q->fence_irq = >->fence_irq[hwe->class]; q->ring_ops = gt->ring_ops[hwe->class]; q->ops = gt->exec_queue_ops; - INIT_LIST_HEAD(&q->persistent.link); INIT_LIST_HEAD(&q->compute.link); INIT_LIST_HEAD(&q->multi_gt_link); @@ -326,23 +325,6 @@ static int exec_queue_set_preemption_timeout(struct xe_device *xe, return q->ops->set_preempt_timeout(q, value); } -static int exec_queue_set_persistence(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, xe_vm_in_preempt_fence_mode(q->vm))) - return -EINVAL; - - if (value) - q->flags |= EXEC_QUEUE_FLAG_PERSISTENT; - else - q->flags &= ~EXEC_QUEUE_FLAG_PERSISTENT; - - return 0; -} - static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q, u64 value, bool create) { @@ -414,7 +396,6 @@ static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = { [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE] = exec_queue_set_persistence, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify, @@ -441,6 +422,9 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe, return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs)); + if (!exec_queue_set_property_funcs[idx]) + return -EINVAL; + return exec_queue_set_property_funcs[idx](xe, q, ext.value, create); } @@ -704,9 +688,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, } q = xe_exec_queue_create(xe, vm, logical_mask, - args->width, hwe, - xe_vm_in_lr_mode(vm) ? 0 : - EXEC_QUEUE_FLAG_PERSISTENT); + args->width, hwe, 0); up_read(&vm->lock); xe_vm_put(vm); if (IS_ERR(q)) @@ -728,8 +710,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, goto kill_exec_queue; } - q->persistent.xef = xef; - mutex_lock(&xef->exec_queue.lock); err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL); mutex_unlock(&xef->exec_queue.lock); @@ -872,10 +852,7 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data, if (XE_IOCTL_DBG(xe, !q)) return -ENOENT; - if (!(q->flags & EXEC_QUEUE_FLAG_PERSISTENT)) - xe_exec_queue_kill(q); - else - xe_device_add_persistent_exec_queues(xe, q); + xe_exec_queue_kill(q); trace_xe_exec_queue_close(q); xe_exec_queue_put(q); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 8d4b7feb8c30..947bbc4b285d 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -105,16 +105,6 @@ struct xe_exec_queue { struct xe_guc_exec_queue *guc; }; - /** - * @persistent: persistent exec queue state - */ - struct { - /** @xef: file which this exec queue belongs to */ - struct xe_file *xef; - /** @link: link in list of persistent exec queues */ - struct list_head link; - } persistent; - union { /** * @parallel: parallel submission state diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 96b5224eb478..42d01bbbf7d0 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -378,8 +378,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w) list_del(&exl->active_link); spin_unlock_irqrestore(&exl->port->lock, flags); - if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT) - xe_device_remove_persistent_exec_queues(xe, q); drm_sched_entity_fini(&exl->entity); drm_sched_fini(&exl->sched); kfree(exl); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 54ffcfcdd41f..f22ae717b0b2 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1028,8 +1028,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); - if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT) - xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q); release_guc_id(guc, q); xe_sched_entity_fini(&ge->entity); xe_sched_fini(&ge->sched); diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 9fa3ae324731..6d11ee9e571a 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1046,7 +1046,6 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE 3 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 -- cgit v1.2.3 From 953cc643329b38434bb7d6206951d1a48016e38b Mon Sep 17 00:00:00 2001 From: Dimitri Fedrau Date: Sun, 18 Feb 2024 08:57:38 +0100 Subject: net: phy: Add BaseT1 auto-negotiation constants Added constants for advertising 100BT1 and 1000BT1 in register BASE-T1 auto-negotiation advertisement register [31:16] (Register 7.515) Reviewed-by: Andrew Lunn Signed-off-by: Dimitri Fedrau Link: https://lore.kernel.org/r/20240218075753.18067-2-dima.fedrau@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/mdio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 3c9097502403..c0c8ec995b06 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -350,6 +350,8 @@ /* BASE-T1 auto-negotiation advertisement register [31:16] */ #define MDIO_AN_T1_ADV_M_B10L 0x4000 /* device is compatible with 10BASE-T1L */ +#define MDIO_AN_T1_ADV_M_1000BT1 0x0080 /* advertise 1000BASE-T1 */ +#define MDIO_AN_T1_ADV_M_100BT1 0x0020 /* advertise 100BASE-T1 */ #define MDIO_AN_T1_ADV_M_MST 0x0010 /* advertise master preference */ /* BASE-T1 auto-negotiation advertisement register [47:32] */ -- cgit v1.2.3 From c16d2380e8fdd9fc1fd0e9c60e068f264b2d0ced Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Mon, 19 Feb 2024 17:51:51 +0800 Subject: net: mctp: provide a more specific tag allocation ioctl Now that we have net-specific tags, extend the tag allocation ioctls (SIOCMCTPALLOCTAG / SIOCMCTPDROPTAG) to allow a network parameter to be passed to the tag allocation. We also add a local_addr member to the ioc struct, to allow for a future finer-grained tag allocation using local EIDs too. We don't add any specific support for that now though, so require MCTP_ADDR_ANY or MCTP_ADDR_NULL for those at present. The old ioctls will still work, but allocate for the default MCTP net. These are now marked as deprecated in the header. Signed-off-by: Jeremy Kerr Signed-off-by: Paolo Abeni --- include/uapi/linux/mctp.h | 32 +++++++++++++ net/mctp/af_mctp.c | 117 ++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 129 insertions(+), 20 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 154ab56651f1..e1db65df9359 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -50,7 +50,14 @@ struct sockaddr_mctp_ext { #define SIOCMCTPALLOCTAG (SIOCPROTOPRIVATE + 0) #define SIOCMCTPDROPTAG (SIOCPROTOPRIVATE + 1) +#define SIOCMCTPALLOCTAG2 (SIOCPROTOPRIVATE + 2) +#define SIOCMCTPDROPTAG2 (SIOCPROTOPRIVATE + 3) +/* Deprecated: use mctp_ioc_tag_ctl2 / TAG2 ioctls instead, which defines the + * MCTP network ID as part of the allocated tag. Using this assumes the default + * net ID for allocated tags, which may not give correct behaviour on system + * with multiple networks configured. + */ struct mctp_ioc_tag_ctl { mctp_eid_t peer_addr; @@ -65,4 +72,29 @@ struct mctp_ioc_tag_ctl { __u16 flags; }; +struct mctp_ioc_tag_ctl2 { + /* Peer details: network ID, peer EID, local EID. All set by the + * caller. + * + * Local EID must be MCTP_ADDR_NULL or MCTP_ADDR_ANY in current + * kernels. + */ + unsigned int net; + mctp_eid_t peer_addr; + mctp_eid_t local_addr; + + /* Set by caller, but no flags defined currently. Must be 0 */ + __u16 flags; + + /* For SIOCMCTPALLOCTAG2: must be passed as zero, kernel will + * populate with the allocated tag value. Returned tag value will + * always have TO and PREALLOC set. + * + * For SIOCMCTPDROPTAG2: userspace provides tag value to drop, from + * a prior SIOCMCTPALLOCTAG2 call (and so must have TO and PREALLOC set). + */ + __u8 tag; + +}; + #endif /* __UAPI_MCTP_H */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 05315a422ffb..de52a9191da0 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -350,30 +350,102 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; } -static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) +/* helpers for reading/writing the tag ioc, handling compatibility across the + * two versions, and some basic API error checking + */ +static int mctp_ioctl_tag_copy_from_user(unsigned long arg, + struct mctp_ioc_tag_ctl2 *ctl, + bool tagv2) +{ + struct mctp_ioc_tag_ctl ctl_compat; + unsigned long size; + void *ptr; + int rc; + + if (tagv2) { + size = sizeof(*ctl); + ptr = ctl; + } else { + size = sizeof(ctl_compat); + ptr = &ctl_compat; + } + + rc = copy_from_user(ptr, (void __user *)arg, size); + if (rc) + return -EFAULT; + + if (!tagv2) { + /* compat, using defaults for new fields */ + ctl->net = MCTP_INITIAL_DEFAULT_NET; + ctl->peer_addr = ctl_compat.peer_addr; + ctl->local_addr = MCTP_ADDR_ANY; + ctl->flags = ctl_compat.flags; + ctl->tag = ctl_compat.tag; + } + + if (ctl->flags) + return -EINVAL; + + if (ctl->local_addr != MCTP_ADDR_ANY && + ctl->local_addr != MCTP_ADDR_NULL) + return -EINVAL; + + return 0; +} + +static int mctp_ioctl_tag_copy_to_user(unsigned long arg, + struct mctp_ioc_tag_ctl2 *ctl, + bool tagv2) +{ + struct mctp_ioc_tag_ctl ctl_compat; + unsigned long size; + void *ptr; + int rc; + + if (tagv2) { + ptr = ctl; + size = sizeof(*ctl); + } else { + ctl_compat.peer_addr = ctl->peer_addr; + ctl_compat.tag = ctl->tag; + ctl_compat.flags = ctl->flags; + + ptr = &ctl_compat; + size = sizeof(ctl_compat); + } + + rc = copy_to_user((void __user *)arg, ptr, size); + if (rc) + return -EFAULT; + + return 0; +} + +static int mctp_ioctl_alloctag(struct mctp_sock *msk, bool tagv2, + unsigned long arg) { struct net *net = sock_net(&msk->sk); struct mctp_sk_key *key = NULL; - struct mctp_ioc_tag_ctl ctl; + struct mctp_ioc_tag_ctl2 ctl; unsigned long flags; u8 tag; + int rc; - if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) - return -EFAULT; + rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); + if (rc) + return rc; if (ctl.tag) return -EINVAL; - if (ctl.flags) - return -EINVAL; - - key = mctp_alloc_local_tag(msk, MCTP_INITIAL_DEFAULT_NET, - MCTP_ADDR_ANY, ctl.peer_addr, true, &tag); + key = mctp_alloc_local_tag(msk, ctl.net, MCTP_ADDR_ANY, + ctl.peer_addr, true, &tag); if (IS_ERR(key)) return PTR_ERR(key); ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; - if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) { + rc = mctp_ioctl_tag_copy_to_user(arg, &ctl, tagv2); + if (rc) { unsigned long fl2; /* Unwind our key allocation: the keys list lock needs to be * taken before the individual key locks, and we need a valid @@ -385,28 +457,27 @@ static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_DROPPED); mctp_key_unref(key); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - return -EFAULT; + return rc; } mctp_key_unref(key); return 0; } -static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) +static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, + unsigned long arg) { struct net *net = sock_net(&msk->sk); - struct mctp_ioc_tag_ctl ctl; + struct mctp_ioc_tag_ctl2 ctl; unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; int rc; u8 tag; - if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) - return -EFAULT; - - if (ctl.flags) - return -EINVAL; + rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); + if (rc) + return rc; /* Must be a local tag, TO set, preallocated */ if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC)) @@ -422,6 +493,7 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) */ spin_lock_irqsave(&key->lock, fl2); if (key->manual_alloc && + ctl.net == key->net && ctl.peer_addr == key->peer_addr && tag == key->tag) { __mctp_key_remove(key, net, fl2, @@ -439,12 +511,17 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + bool tagv2 = false; switch (cmd) { + case SIOCMCTPALLOCTAG2: case SIOCMCTPALLOCTAG: - return mctp_ioctl_alloctag(msk, arg); + tagv2 = cmd == SIOCMCTPALLOCTAG2; + return mctp_ioctl_alloctag(msk, tagv2, arg); case SIOCMCTPDROPTAG: - return mctp_ioctl_droptag(msk, arg); + case SIOCMCTPDROPTAG2: + tagv2 = cmd == SIOCMCTPDROPTAG2; + return mctp_ioctl_droptag(msk, tagv2, arg); } return -EINVAL; -- cgit v1.2.3 From 58fd62e0aa50fdd20bc41a01e787001f3af8a925 Mon Sep 17 00:00:00 2001 From: Martin Kelly Date: Wed, 21 Feb 2024 13:18:38 -0800 Subject: bpf: Clarify batch lookup/lookup_and_delete semantics The batch lookup and lookup_and_delete APIs have two parameters, in_batch and out_batch, to facilitate iterative lookup/lookup_and_deletion operations for supported maps. Except NULL for in_batch at the start of these two batch operations, both parameters need to point to memory equal or larger than the respective map key size, except for various hashmaps (hash, percpu_hash, lru_hash, lru_percpu_hash) where the in_batch/out_batch memory size should be at least 4 bytes. Document these semantics to clarify the API. Signed-off-by: Martin Kelly Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20240221211838.1241578-1-martin.kelly@crowdstrike.com Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 6 +++++- tools/include/uapi/linux/bpf.h | 6 +++++- tools/lib/bpf/bpf.h | 17 ++++++++++++----- 3 files changed, 22 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d96708380e52..d2e6c5fcec01 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -617,7 +617,11 @@ union bpf_iter_link_info { * to NULL to begin the batched operation. After each subsequent * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant * *out_batch* as the *in_batch* for the next operation to - * continue iteration from the current point. + * continue iteration from the current point. Both *in_batch* and + * *out_batch* must point to memory large enough to hold a key, + * except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters + * must be at least 4 bytes wide regardless of key size. * * The *keys* and *values* are output parameters which must point * to memory large enough to hold *count* items based on the key diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d96708380e52..d2e6c5fcec01 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -617,7 +617,11 @@ union bpf_iter_link_info { * to NULL to begin the batched operation. After each subsequent * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant * *out_batch* as the *in_batch* for the next operation to - * continue iteration from the current point. + * continue iteration from the current point. Both *in_batch* and + * *out_batch* must point to memory large enough to hold a key, + * except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters + * must be at least 4 bytes wide regardless of key size. * * The *keys* and *values* are output parameters which must point * to memory large enough to hold *count* items based on the key diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index ab2570d28aec..df0db2f0cdb7 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -190,10 +190,14 @@ LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, /** * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. * - * The parameter *in_batch* is the address of the first element in the batch to read. - * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent - * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate - * that the batched lookup starts from the beginning of the map. + * The parameter *in_batch* is the address of the first element in the batch to + * read. *out_batch* is an output parameter that should be passed as *in_batch* + * to subsequent calls to **bpf_map_lookup_batch()**. NULL can be passed for + * *in_batch* to indicate that the batched lookup starts from the beginning of + * the map. Both *in_batch* and *out_batch* must point to memory large enough to + * hold a single key, except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which the memory size must be at + * least 4 bytes wide regardless of key size. * * The *keys* and *values* are output parameters which must point to memory large enough to * hold *count* items based on the key and value size of the map *map_fd*. The *keys* @@ -226,7 +230,10 @@ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, * * @param fd BPF map file descriptor * @param in_batch address of the first element in batch to read, can pass NULL to - * get address of the first element in *out_batch* + * get address of the first element in *out_batch*. If not NULL, must be large + * enough to hold a key. For **BPF_MAP_TYPE_{HASH, PERCPU_HASH, LRU_HASH, + * LRU_PERCPU_HASH}**, the memory size must be at least 4 bytes wide regardless + * of key size. * @param out_batch output parameter that should be passed to next call as *in_batch* * @param keys pointer to an array of *count* keys * @param values pointer to an array large enough for *count* values -- cgit v1.2.3 From fa3bea4e1f8202d787709b7e3654eb0a99aed758 Mon Sep 17 00:00:00 2001 From: Gregory Price Date: Fri, 2 Feb 2024 12:02:37 -0500 Subject: mm/mempolicy: introduce MPOL_WEIGHTED_INTERLEAVE for weighted interleaving When a system has multiple NUMA nodes and it becomes bandwidth hungry, using the current MPOL_INTERLEAVE could be an wise option. However, if those NUMA nodes consist of different types of memory such as socket-attached DRAM and CXL/PCIe attached DRAM, the round-robin based interleave policy does not optimally distribute data to make use of their different bandwidth characteristics. Instead, interleave is more effective when the allocation policy follows each NUMA nodes' bandwidth weight rather than a simple 1:1 distribution. This patch introduces a new memory policy, MPOL_WEIGHTED_INTERLEAVE, enabling weighted interleave between NUMA nodes. Weighted interleave allows for proportional distribution of memory across multiple numa nodes, preferably apportioned to match the bandwidth of each node. For example, if a system has 1 CPU node (0), and 2 memory nodes (0,1), with bandwidth of (100GB/s, 50GB/s) respectively, the appropriate weight distribution is (2:1). Weights for each node can be assigned via the new sysfs extension: /sys/kernel/mm/mempolicy/weighted_interleave/ For now, the default value of all nodes will be `1`, which matches the behavior of standard 1:1 round-robin interleave. An extension will be added in the future to allow default values to be registered at kernel and device bringup time. The policy allocates a number of pages equal to the set weights. For example, if the weights are (2,1), then 2 pages will be allocated on node0 for every 1 page allocated on node1. The new flag MPOL_WEIGHTED_INTERLEAVE can be used in set_mempolicy(2) and mbind(2). Some high level notes about the pieces of weighted interleave: current->il_prev: Tracks the node previously allocated from. current->il_weight: The active weight of the current node (current->il_prev) When this reaches 0, current->il_prev is set to the next node and current->il_weight is set to the next weight. weighted_interleave_nodes: Counts the number of allocations as they occur, and applies the weight for the current node. When the weight reaches 0, switch to the next node. Operates only on task->mempolicy. weighted_interleave_nid: Gets the total weight of the nodemask as well as each individual node weight, then calculates the node based on the given index. Operates on VMA policies. bulk_array_weighted_interleave: Gets the total weight of the nodemask as well as each individual node weight, then calculates the number of "interleave rounds" as well as any delta ("partial round"). Calculates the number of pages for each node and allocates them. If a node was scheduled for interleave via interleave_nodes, the current weight will be allocated first. Operates only on the task->mempolicy. One piece of complexity is the interaction between a recent refactor which split the logic to acquire the "ilx" (interleave index) of an allocation and the actually application of the interleave. If a call to alloc_pages_mpol() were made with a weighted-interleave policy and ilx set to NO_INTERLEAVE_INDEX, weighted_interleave_nodes() would operate on a VMA policy - violating the description above. An inspection of all callers of alloc_pages_mpol() shows that all external callers set ilx to `0`, an index value, or will call get_vma_policy() to acquire the ilx. For example, mm/shmem.c may call into alloc_pages_mpol. The call stacks all set (pgoff_t ilx) or end up in `get_vma_policy()`. This enforces the `weighted_interleave_nodes()` and `weighted_interleave_nid()` policy requirements (task/vma respectively). Link: https://lkml.kernel.org/r/20240202170238.90004-4-gregory.price@memverge.com Suggested-by: Hasan Al Maruf Signed-off-by: Gregory Price Co-developed-by: Rakie Kim Signed-off-by: Rakie Kim Co-developed-by: Honggyu Kim Signed-off-by: Honggyu Kim Co-developed-by: Hyeongtak Ji Signed-off-by: Hyeongtak Ji Co-developed-by: Srinivasulu Thanneeru Signed-off-by: Srinivasulu Thanneeru Co-developed-by: Ravi Jonnalagadda Signed-off-by: Ravi Jonnalagadda Reviewed-by: "Huang, Ying" Cc: Dan Williams Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michal Hocko Signed-off-by: Andrew Morton --- .../admin-guide/mm/numa_memory_policy.rst | 9 + include/linux/sched.h | 1 + include/uapi/linux/mempolicy.h | 1 + mm/mempolicy.c | 218 ++++++++++++++++++++- 4 files changed, 225 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst index eca38fa81e0f..a70f20ce1ffb 100644 --- a/Documentation/admin-guide/mm/numa_memory_policy.rst +++ b/Documentation/admin-guide/mm/numa_memory_policy.rst @@ -250,6 +250,15 @@ MPOL_PREFERRED_MANY can fall back to all existing numa nodes. This is effectively MPOL_PREFERRED allowed for a mask rather than a single node. +MPOL_WEIGHTED_INTERLEAVE + This mode operates the same as MPOL_INTERLEAVE, except that + interleaving behavior is executed based on weights set in + /sys/kernel/mm/mempolicy/weighted_interleave/ + + Weighted interleave allocates pages on nodes according to a + weight. For example if nodes [0,1] are weighted [5,2], 5 pages + will be allocated on node0 for every 2 pages allocated on node1. + NUMA memory policy supports the following optional mode flags: MPOL_F_STATIC_NODES diff --git a/include/linux/sched.h b/include/linux/sched.h index ffe8f618ab86..b9ce285d8c9c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1259,6 +1259,7 @@ struct task_struct { /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; + u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index a8963f7ef4c2..1f9bb10d1a47 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -23,6 +23,7 @@ enum { MPOL_INTERLEAVE, MPOL_LOCAL, MPOL_PREFERRED_MANY, + MPOL_WEIGHTED_INTERLEAVE, MPOL_MAX, /* always last member of enum */ }; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 1bdc7d0d1b0b..a8db92c23697 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -19,6 +19,13 @@ * for anonymous memory. For process policy an process counter * is used. * + * weighted interleave + * Allocate memory interleaved over a set of nodes based on + * a set of weights (per-node), with normal fallback if it + * fails. Otherwise operates the same as interleave. + * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated + * on node 0 for every 1 page allocated on node 1. + * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node @@ -441,6 +448,10 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, + [MPOL_WEIGHTED_INTERLEAVE] = { + .create = mpol_new_nodemask, + .rebind = mpol_rebind_nodemask, + }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, @@ -858,8 +869,11 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, old = current->mempolicy; current->mempolicy = new; - if (new && new->mode == MPOL_INTERLEAVE) + if (new && (new->mode == MPOL_INTERLEAVE || + new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; + current->il_weight = 0; + } task_unlock(current); mpol_put(old); ret = 0; @@ -884,6 +898,7 @@ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: + case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: @@ -968,6 +983,13 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); + } else if (pol == current->mempolicy && + pol->mode == MPOL_WEIGHTED_INTERLEAVE) { + if (current->il_weight) + *policy = current->il_prev; + else + *policy = next_node_in(current->il_prev, + pol->nodes); } else { err = -EINVAL; goto out; @@ -1332,7 +1354,8 @@ static long do_mbind(unsigned long start, unsigned long len, * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ - if (new->mode == MPOL_INTERLEAVE) { + if (new->mode == MPOL_INTERLEAVE || + new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct page *page; unsigned int order; unsigned long addr = -EFAULT; @@ -1780,7 +1803,8 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving - * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE + * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or + * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. @@ -1797,7 +1821,8 @@ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); - if (pol->mode == MPOL_INTERLEAVE) { + if (pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } @@ -1847,6 +1872,22 @@ bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) return zone >= dynamic_policy_zone; } +static unsigned int weighted_interleave_nodes(struct mempolicy *policy) +{ + unsigned int node = current->il_prev; + + if (!current->il_weight || !node_isset(node, policy->nodes)) { + node = next_node_in(node, policy->nodes); + /* can only happen if nodemask is being rebound */ + if (node == MAX_NUMNODES) + return node; + current->il_prev = node; + current->il_weight = get_il_weight(node); + } + current->il_weight--; + return node; +} + /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { @@ -1881,6 +1922,9 @@ unsigned int mempolicy_slab_node(void) case MPOL_INTERLEAVE: return interleave_nodes(policy); + case MPOL_WEIGHTED_INTERLEAVE: + return weighted_interleave_nodes(policy); + case MPOL_BIND: case MPOL_PREFERRED_MANY: { @@ -1919,6 +1963,45 @@ static unsigned int read_once_policy_nodemask(struct mempolicy *pol, return nodes_weight(*mask); } +static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) +{ + nodemask_t nodemask; + unsigned int target, nr_nodes; + u8 *table; + unsigned int weight_total = 0; + u8 weight; + int nid; + + nr_nodes = read_once_policy_nodemask(pol, &nodemask); + if (!nr_nodes) + return numa_node_id(); + + rcu_read_lock(); + table = rcu_dereference(iw_table); + /* calculate the total weight */ + for_each_node_mask(nid, nodemask) { + /* detect system default usage */ + weight = table ? table[nid] : 1; + weight = weight ? weight : 1; + weight_total += weight; + } + + /* Calculate the node offset based on totals */ + target = ilx % weight_total; + nid = first_node(nodemask); + while (target) { + /* detect system default usage */ + weight = table ? table[nid] : 1; + weight = weight ? weight : 1; + if (target < weight) + break; + target -= weight; + nid = next_node_in(nid, nodemask); + } + rcu_read_unlock(); + return nid; +} + /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx @@ -1979,6 +2062,11 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; + case MPOL_WEIGHTED_INTERLEAVE: + *nid = (ilx == NO_INTERLEAVE_INDEX) ? + weighted_interleave_nodes(pol) : + weighted_interleave_nid(pol, ilx); + break; } return nodemask; @@ -2040,6 +2128,7 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; @@ -2140,6 +2229,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && + pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but @@ -2275,6 +2365,114 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, return total_allocated; } +static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + struct task_struct *me = current; + unsigned long total_allocated = 0; + unsigned long nr_allocated = 0; + unsigned long rounds; + unsigned long node_pages, delta; + u8 *table, *weights, weight; + unsigned int weight_total = 0; + unsigned long rem_pages = nr_pages; + nodemask_t nodes; + int nnodes, node; + int resume_node = MAX_NUMNODES - 1; + u8 resume_weight = 0; + int prev_node; + int i; + + if (!nr_pages) + return 0; + + nnodes = read_once_policy_nodemask(pol, &nodes); + if (!nnodes) + return 0; + + /* Continue allocating from most recent node and adjust the nr_pages */ + node = me->il_prev; + weight = me->il_weight; + if (weight && node_isset(node, nodes)) { + node_pages = min(rem_pages, weight); + nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, + NULL, page_array); + page_array += nr_allocated; + total_allocated += nr_allocated; + /* if that's all the pages, no need to interleave */ + if (rem_pages <= weight) { + me->il_weight -= rem_pages; + return total_allocated; + } + /* Otherwise we adjust remaining pages, continue from there */ + rem_pages -= weight; + } + /* clear active weight in case of an allocation failure */ + me->il_weight = 0; + prev_node = node; + + /* create a local copy of node weights to operate on outside rcu */ + weights = kzalloc(nr_node_ids, GFP_KERNEL); + if (!weights) + return total_allocated; + + rcu_read_lock(); + table = rcu_dereference(iw_table); + if (table) + memcpy(weights, table, nr_node_ids); + rcu_read_unlock(); + + /* calculate total, detect system default usage */ + for_each_node_mask(node, nodes) { + if (!weights[node]) + weights[node] = 1; + weight_total += weights[node]; + } + + /* + * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. + * Track which node weighted interleave should resume from. + * + * if (rounds > 0) and (delta == 0), resume_node will always be + * the node following prev_node and its weight. + */ + rounds = rem_pages / weight_total; + delta = rem_pages % weight_total; + resume_node = next_node_in(prev_node, nodes); + resume_weight = weights[resume_node]; + for (i = 0; i < nnodes; i++) { + node = next_node_in(prev_node, nodes); + weight = weights[node]; + node_pages = weight * rounds; + /* If a delta exists, add this node's portion of the delta */ + if (delta > weight) { + node_pages += weight; + delta -= weight; + } else if (delta) { + /* when delta is depleted, resume from that node */ + node_pages += delta; + resume_node = node; + resume_weight = weight - delta; + delta = 0; + } + /* node_pages can be 0 if an allocation fails and rounds == 0 */ + if (!node_pages) + break; + nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, + NULL, page_array); + page_array += nr_allocated; + total_allocated += nr_allocated; + if (total_allocated == nr_pages) + break; + prev_node = node; + } + me->il_prev = resume_node; + me->il_weight = resume_weight; + kfree(weights); + return total_allocated; +} + static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) @@ -2315,6 +2513,10 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, return alloc_pages_bulk_array_interleave(gfp, pol, nr_pages, page_array); + if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) + return alloc_pages_bulk_array_weighted_interleave( + gfp, pol, nr_pages, page_array); + if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); @@ -2390,6 +2592,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: + case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; @@ -2526,6 +2729,10 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, polnid = interleave_nid(pol, ilx); break; + case MPOL_WEIGHTED_INTERLEAVE: + polnid = weighted_interleave_nid(pol, ilx); + break; + case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; @@ -2900,6 +3107,7 @@ static const char * const policy_modes[] = [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", + [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; @@ -2959,6 +3167,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) } break; case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ @@ -3069,6 +3278,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: + case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: -- cgit v1.2.3 From 3f4d8aac6e768c2215ce68275256971c2f54f0c8 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 24 Jan 2024 13:50:58 +1000 Subject: nouveau: add an ioctl to return vram bar size. This returns the BAR resources size so userspace can make decisions based on rebar support. userspace using this has been proposed for nvk, but it's a rather trivial uapi addition. Reviewed-by: Faith Ekstrand Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 4 ++++ include/uapi/drm/nouveau_drm.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index d1bb8151a1df..4cb323bc3233 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -199,6 +199,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) struct nouveau_cli *cli = nouveau_cli(file_priv); struct nouveau_drm *drm = nouveau_drm(dev); struct nvif_device *device = &drm->client.device; + struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device); struct nvkm_gr *gr = nvxx_gr(device); struct drm_nouveau_getparam *getparam = data; struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -263,6 +264,9 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) getparam->value = nouveau_exec_push_max_from_ib_max(ib_max); break; } + case NOUVEAU_GETPARAM_VRAM_BAR_SIZE: + getparam->value = nvkm_device->func->resource_size(nvkm_device, 1); + break; default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 0bade1592f34..10a917639d8d 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -54,6 +54,13 @@ extern "C" { */ #define NOUVEAU_GETPARAM_EXEC_PUSH_MAX 17 +/* + * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size + * + * Query the VRAM BAR size. + */ +#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18 + struct drm_nouveau_getparam { __u64 param; __u64 value; -- cgit v1.2.3 From 72fa02fdf83306c52bc1eede28359e3fa32a151a Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 24 Jan 2024 14:24:25 +1000 Subject: nouveau: add an ioctl to report vram usage This reports the currently used vram allocations. userspace using this has been proposed for nvk, but it's a rather trivial uapi addition. Reviewed-by: Faith Ekstrand Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 5 +++++ include/uapi/drm/nouveau_drm.h | 7 +++++++ 2 files changed, 12 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 4cb323bc3233..cd14f993bdd1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -267,6 +267,11 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) case NOUVEAU_GETPARAM_VRAM_BAR_SIZE: getparam->value = nvkm_device->func->resource_size(nvkm_device, 1); break; + case NOUVEAU_GETPARAM_VRAM_USED: { + struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM); + getparam->value = (u64)ttm_resource_manager_usage(vram_mgr) << PAGE_SHIFT; + break; + } default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 10a917639d8d..77d7ff0d5b11 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -61,6 +61,13 @@ extern "C" { */ #define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18 +/* + * NOUVEAU_GETPARAM_VRAM_USED + * + * Get remaining VRAM size. + */ +#define NOUVEAU_GETPARAM_VRAM_USED 19 + struct drm_nouveau_getparam { __u64 param; __u64 value; -- cgit v1.2.3 From 85df6b5a6658c788d7e27d52ea334aa83abcbf56 Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Thu, 22 Feb 2024 18:36:49 +0100 Subject: ALSA: pcm: clarify and fix default msbits value for all formats Return used most significant bits from sample bit-width rather than the whole physical sample word size. The starting bit offset is defined in the format itself. The behaviour is not changed for 32-bit formats like S32_LE. But with this change - msbits value 24 instead 32 is returned for 24-bit formats like S24_LE etc. Also, commit 2112aa034907 ("ALSA: pcm: Introduce MSBITS subformat interface") compares sample bit-width not physical sample bit-width to reset MSBITS_MAX bit from the subformat bitmask. Probably no applications are using msbits value for other than S32_LE/U32_LE formats, because no drivers are reducing msbits value for other formats (with the msb offset) at the moment. For sanity, increase PCM protocol version, letting the user space to detect the changed behaviour. Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20240222173649.1447549-1-perex@perex.cz Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 4 ++-- sound/core/pcm_native.c | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index d5b9cfbd9cea..628d46a0da92 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index f5ff00f99788..21baf6bf7e25 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -486,6 +486,11 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream, i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS); if (snd_interval_single(i)) params->msbits = snd_interval_value(i); + m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); + if (snd_mask_single(m)) { + snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m); + params->msbits = snd_pcm_format_width(format); + } } if (params->msbits) { -- cgit v1.2.3 From 6e6822893fa913f8573da21c693e8edc250ca0c8 Mon Sep 17 00:00:00 2001 From: Paul Elder Date: Fri, 16 Feb 2024 18:54:52 +0900 Subject: media: rkisp1: Add version enum for i.MX8MP ISP The NXP i.MX8MP integrates an ISP8000Nano from VeriSilicon, which is a derivative of the ISP found in earlier Rockchip SoCs. It isn't clear at which exact point the two product lines have diverged, and there is no public information regarding the version numbering scheme of the ISP8000Nano. Nonetheless, this ISP is close enough to the V10 found in the RK3399 to be supported by the same driver. Add an entry for the ISP found in the NXP i.MX8MP to the version enum. Given the lack of information on the version numbering scheme, and on whether or not the version in the i.MX8MP is identical to other ISP8000Nano versions or has been customized for the i.MX8MP, depart from the number-based versions and name this new version V_IMX8MP. Update comments for the other versions and for relevant parameters blocks to clearly indicate the size of grids and histogram for the different versions. Signed-off-by: Paul Elder Signed-off-by: Laurent Pinchart Tested-by: Alexander Stein --- include/uapi/linux/rkisp1-config.h | 50 ++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 23 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 730673ecc63d..6eeaf8bf2362 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -175,16 +175,21 @@ /** * 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 + * @RKISP1_V10: Used at least in RK3288 and RK3399. + * @RKISP1_V11: Declared in the original vendor code, but not used. Same number + * of entries in grids and histogram as v10. + * @RKISP1_V12: Used at least in RK3326 and PX30. + * @RKISP1_V13: Used at least in RK1808. Same number of entries in grids and + * histogram as v12. + * @RKISP1_V_IMX8MP: Used in at least i.MX8MP. Same number of entries in grids + * and histogram as v10. */ enum rkisp1_cif_isp_version { RKISP1_V10 = 10, RKISP1_V11, RKISP1_V12, RKISP1_V13, + RKISP1_V_IMX8MP, }; enum rkisp1_cif_isp_histogram_mode { @@ -584,10 +589,9 @@ enum rkisp1_cif_isp_goc_mode { * 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. + * V10 has RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 entries, V12 has + * 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; @@ -607,10 +611,10 @@ struct rkisp1_cif_isp_goc_config { * 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. + * V10 has RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 entries, V12 has + * 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; @@ -902,9 +906,9 @@ struct rkisp1_cif_isp_bls_meas_val { * 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. + * V10 has RKISP1_CIF_ISP_AE_MEAN_MAX_V10 entries, V12 has + * 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. */ @@ -944,21 +948,21 @@ struct rkisp1_cif_isp_af_stat { * integer part. * * 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 + * V10 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 histogram contains 16 bins in V10 and 32 bins in V12. * * 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. + * V10 has RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 entries, V12 has + * 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 7dc4e97a4f9a55bae6ed6ab3f96c92921259d59f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 9 Feb 2024 16:57:17 +0200 Subject: fuse: introduce FUSE_PASSTHROUGH capability FUSE_PASSTHROUGH capability to passthrough FUSE operations to backing files will be made available with kernel config CONFIG_FUSE_PASSTHROUGH. When requesting FUSE_PASSTHROUGH, userspace needs to specify the max_stack_depth that is allowed for FUSE on top of backing files. Introduce the flag FOPEN_PASSTHROUGH and backing_id to fuse_open_out argument that can be used when replying to OPEN request, to setup passthrough of io operations on the fuse inode to a backing file. Introduce a refcounted fuse_backing object that will be used to associate an open backing file with a fuse inode. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/fuse/Kconfig | 11 +++++++++++ fs/fuse/Makefile | 1 + fs/fuse/fuse_i.h | 42 ++++++++++++++++++++++++++++++++++++++++++ fs/fuse/inode.c | 26 ++++++++++++++++++++++++++ fs/fuse/passthrough.c | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/fuse.h | 14 +++++++++++--- 6 files changed, 121 insertions(+), 3 deletions(-) create mode 100644 fs/fuse/passthrough.c (limited to 'include/uapi') diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 038ed0b9aaa5..8674dbfbe59d 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -52,3 +52,14 @@ config FUSE_DAX If you want to allow mounting a Virtio Filesystem with the "dax" option, answer Y. + +config FUSE_PASSTHROUGH + bool "FUSE passthrough operations support" + default y + depends on FUSE_FS + select FS_STACK + help + This allows bypassing FUSE server by mapping specific FUSE operations + to be performed directly on a backing file. + + If you want to allow passthrough operations, answer Y. diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index b734cc2a5e65..6e0228c6d0cb 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -10,5 +10,6 @@ obj-$(CONFIG_VIRTIO_FS) += virtiofs.o fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o fuse-y += iomode.o fuse-$(CONFIG_FUSE_DAX) += dax.o +fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o virtiofs-y := virtio_fs.o diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 2e7af883e4b3..19a86acc9dd0 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -76,6 +76,15 @@ struct fuse_submount_lookup { struct fuse_forget_link *forget; }; +/** Container for data related to mapping to backing file */ +struct fuse_backing { + struct file *file; + + /** refcount */ + refcount_t count; + struct rcu_head rcu; +}; + /** FUSE inode */ struct fuse_inode { /** Inode data */ @@ -179,6 +188,10 @@ struct fuse_inode { #endif /** Submount specific lookup tracking */ struct fuse_submount_lookup *submount_lookup; +#ifdef CONFIG_FUSE_PASSTHROUGH + /** Reference to backing file in passthrough mode */ + struct fuse_backing *fb; +#endif }; /** FUSE inode state bits */ @@ -829,6 +842,12 @@ struct fuse_conn { /* Is statx not implemented by fs? */ unsigned int no_statx:1; + /** Passthrough support for read/write IO */ + unsigned int passthrough:1; + + /** Maximum stack depth for passthrough backing files */ + int max_stack_depth; + /** The number of requests waiting for completion */ atomic_t num_waiting; @@ -1368,4 +1387,27 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid, void fuse_file_release(struct inode *inode, struct fuse_file *ff, unsigned int open_flags, fl_owner_t id, bool isdir); +/* passthrough.c */ +static inline struct fuse_backing *fuse_inode_backing(struct fuse_inode *fi) +{ +#ifdef CONFIG_FUSE_PASSTHROUGH + return READ_ONCE(fi->fb); +#else + return NULL; +#endif +} + +static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi, + struct fuse_backing *fb) +{ +#ifdef CONFIG_FUSE_PASSTHROUGH + return xchg(&fi->fb, fb); +#else + return NULL; +#endif +} + +struct fuse_backing *fuse_backing_get(struct fuse_backing *fb); +void fuse_backing_put(struct fuse_backing *fb); + #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2a6d44f91729..c771bd3c1336 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -111,6 +111,9 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi)) goto out_free_forget; + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + fuse_inode_backing_set(fi, NULL); + return &fi->inode; out_free_forget: @@ -129,6 +132,9 @@ static void fuse_free_inode(struct inode *inode) #ifdef CONFIG_FUSE_DAX kfree(fi->dax); #endif + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + fuse_backing_put(fuse_inode_backing(fi)); + kmem_cache_free(fuse_inode_cachep, fi); } @@ -1284,6 +1290,24 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->create_supp_group = 1; if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) fc->direct_io_allow_mmap = 1; + /* + * max_stack_depth is the max stack depth of FUSE fs, + * so it has to be at least 1 to support passthrough + * to backing files. + * + * with max_stack_depth > 1, the backing files can be + * on a stacked fs (e.g. overlayfs) themselves and with + * max_stack_depth == 1, FUSE fs can be stacked as the + * underlying fs of a stacked fs (e.g. overlayfs). + */ + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) && + (flags & FUSE_PASSTHROUGH) && + arg->max_stack_depth > 0 && + arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) { + fc->passthrough = 1; + fc->max_stack_depth = arg->max_stack_depth; + fm->sb->s_stack_depth = arg->max_stack_depth; + } } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1339,6 +1363,8 @@ void fuse_send_init(struct fuse_mount *fm) #endif if (fm->fc->auto_submounts) flags |= FUSE_SUBMOUNTS; + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + flags |= FUSE_PASSTHROUGH; ia->in.flags = flags; ia->in.flags2 = flags >> 32; diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c new file mode 100644 index 000000000000..e8639c0a9ac6 --- /dev/null +++ b/fs/fuse/passthrough.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FUSE passthrough to backing file. + * + * Copyright (c) 2023 CTERA Networks. + */ + +#include "fuse_i.h" + +#include + +struct fuse_backing *fuse_backing_get(struct fuse_backing *fb) +{ + if (fb && refcount_inc_not_zero(&fb->count)) + return fb; + return NULL; +} + +static void fuse_backing_free(struct fuse_backing *fb) +{ + if (fb->file) + fput(fb->file); + kfree_rcu(fb, rcu); +} + +void fuse_backing_put(struct fuse_backing *fb) +{ + if (fb && refcount_dec_and_test(&fb->count)) + fuse_backing_free(fb); +} diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index e7418d15fe39..7bb6219cfda0 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -211,6 +211,10 @@ * 7.39 * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures + * + * 7.40 + * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag + * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag */ #ifndef _LINUX_FUSE_H @@ -246,7 +250,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 39 +#define FUSE_KERNEL_MINOR_VERSION 40 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -353,6 +357,7 @@ struct fuse_file_lock { * FOPEN_STREAM: the file is stream-like (no file position at all) * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE) * FOPEN_PARALLEL_DIRECT_WRITES: Allow concurrent direct writes on the same inode + * FOPEN_PASSTHROUGH: passthrough read/write io for this open file */ #define FOPEN_DIRECT_IO (1 << 0) #define FOPEN_KEEP_CACHE (1 << 1) @@ -361,6 +366,7 @@ struct fuse_file_lock { #define FOPEN_STREAM (1 << 4) #define FOPEN_NOFLUSH (1 << 5) #define FOPEN_PARALLEL_DIRECT_WRITES (1 << 6) +#define FOPEN_PASSTHROUGH (1 << 7) /** * INIT request/reply flags @@ -449,6 +455,7 @@ struct fuse_file_lock { #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) +#define FUSE_PASSTHROUGH (1ULL << 37) /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP @@ -761,7 +768,7 @@ struct fuse_create_in { struct fuse_open_out { uint64_t fh; uint32_t open_flags; - uint32_t padding; + int32_t backing_id; }; struct fuse_release_in { @@ -877,7 +884,8 @@ struct fuse_init_out { uint16_t max_pages; uint16_t map_alignment; uint32_t flags2; - uint32_t unused[7]; + uint32_t max_stack_depth; + uint32_t unused[6]; }; #define CUSE_INIT_INFO_MAX 4096 -- cgit v1.2.3 From 6a2008641920a9c6fe1abbeb9acbec463215d505 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Mon, 26 Feb 2024 13:49:21 +0100 Subject: uapi: in6: replace temporary label with rfc9486 Not really a fix per se, but IPV6_TLV_IOAM is still tagged as "TEMPORARY IANA allocation for IOAM", while RFC 9486 is available for some time now. Just update the reference. Fixes: 9ee11f0fff20 ("ipv6: ioam: Data plane support for Pre-allocated Trace") Signed-off-by: Justin Iurman Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240226124921.9097-1-justin.iurman@uliege.be Signed-off-by: Jakub Kicinski --- include/uapi/linux/in6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index c4c53a9ab959..ff8d21f9e95b 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -145,7 +145,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 #define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ -#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */ +#define IPV6_TLV_IOAM 49 /* RFC 9486 */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */ -- cgit v1.2.3 From 5fa918a33563e050d45fb8f260f9240b2039f432 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Mon, 26 Feb 2024 14:14:10 +0100 Subject: uapi: ioam6: API for netlink multicast events Add new api to support ioam6 events for generic netlink multicast. A first "trace" event is added to the list of ioam6 events, which will represent an IOAM Pre-allocated Trace Option-Type. It provides another solution to share IOAM data with user space. Reviewed-by: David Ahern Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/uapi/linux/ioam6_genl.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ioam6_genl.h b/include/uapi/linux/ioam6_genl.h index ca4b22833754..1733fbc51fb5 100644 --- a/include/uapi/linux/ioam6_genl.h +++ b/include/uapi/linux/ioam6_genl.h @@ -49,4 +49,24 @@ enum { #define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1) +#define IOAM6_GENL_EV_GRP_NAME "ioam6_events" + +enum ioam6_event_type { + IOAM6_EVENT_UNSPEC, + IOAM6_EVENT_TRACE, +}; + +enum ioam6_event_attr { + IOAM6_EVENT_ATTR_UNSPEC, + + IOAM6_EVENT_ATTR_TRACE_NAMESPACE, /* u16 */ + IOAM6_EVENT_ATTR_TRACE_NODELEN, /* u8 */ + IOAM6_EVENT_ATTR_TRACE_TYPE, /* u32 */ + IOAM6_EVENT_ATTR_TRACE_DATA, /* Binary */ + + __IOAM6_EVENT_ATTR_MAX +}; + +#define IOAM6_EVENT_ATTR_MAX (__IOAM6_EVENT_ATTR_MAX - 1) + #endif /* _UAPI_LINUX_IOAM6_GENL_H */ -- cgit v1.2.3 From 13fe8e6825e44129b6cbeee41d3012554bf8d687 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 23 Feb 2024 15:55:39 +0800 Subject: ublk: add UBLK_CMD_DEL_DEV_ASYNC The current command UBLK_CMD_DEL_DEV won't return until the device is released, this way looks more reliable, but makes userspace more difficult to implement, especially about orders: unmap command buffer(which holds one ublkc reference), ublkc close, io_uring_file_unregister, ublkb close. Add UBLK_CMD_DEL_DEV_ASYNC so that device deletion won't wait release, then userspace needn't worry about the above order. Actually both loop and nbd is deleted in this async way. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20240223075539.89945-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 9 ++++++--- include/uapi/linux/ublk_cmd.h | 2 ++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 06d88d2008ba..bea3d5cf8a83 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2468,7 +2468,7 @@ static inline bool ublk_idr_freed(int id) return ptr == NULL; } -static int ublk_ctrl_del_dev(struct ublk_device **p_ub) +static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait) { struct ublk_device *ub = *p_ub; int idx = ub->ub_number; @@ -2502,7 +2502,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub) * - the device number is freed already, we will not find this * device via ublk_get_device_from_id() */ - if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx))) + if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx))) return -EINTR; return 0; } @@ -2901,7 +2901,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_add_dev(cmd); break; case UBLK_CMD_DEL_DEV: - ret = ublk_ctrl_del_dev(&ub); + ret = ublk_ctrl_del_dev(&ub, true); + break; + case UBLK_U_CMD_DEL_DEV_ASYNC: + ret = ublk_ctrl_del_dev(&ub, false); break; case UBLK_CMD_GET_QUEUE_AFFINITY: ret = ublk_ctrl_get_queue_affinity(ub, cmd); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index b9cfc5c96268..c8dc5f8ea699 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -49,6 +49,8 @@ _IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_GET_FEATURES \ _IOR('u', 0x13, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_DEL_DEV_ASYNC \ + _IOR('u', 0x14, struct ublksrv_ctrl_cmd) /* * 64bits are enough now, and it should be easy to extend in case of -- cgit v1.2.3 From 7e10d87e63f7f9c324d533bb4369e35bb19ab9a9 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 21 Feb 2024 14:30:18 +0100 Subject: drm/xe: Add uapi for dumpable bos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the flag XE_VM_BIND_FLAG_DUMPABLE to notify devcoredump that this mapping should be dumped. This is not hooked up, but the uapi should be ready before merging. It's likely easier to dump the contents of the bo's at devcoredump readout time, so it's better if the bos will stay unmodified after a hang. The NEEDS_CPU_MAPPING flag is removed as requirement. Signed-off-by: Maarten Lankhorst Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20240221133024.898315-3-maarten.lankhorst@linux.intel.com (cherry picked from commit 76a86b58d2b3de31e88acb487ebfa0c3cc7c41d2) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_vm.c | 3 ++- include/uapi/drm/xe_drm.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 921ca28d49dd..945c89b5e4b5 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2722,7 +2722,8 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, #define SUPPORTED_FLAGS \ (DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL) + DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \ + DRM_XE_VM_BIND_FLAG_DUMPABLE) #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 6d11ee9e571a..4f010949f812 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -931,6 +931,7 @@ struct drm_xe_vm_bind_op { #define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) #define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) #define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) +#define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) /** @flags: Bind flags */ __u32 flags; -- cgit v1.2.3 From b6f4fb397db09024c189834d638abbd21bf00769 Mon Sep 17 00:00:00 2001 From: José Roberto de Souza Date: Tue, 26 Dec 2023 08:11:14 -0800 Subject: drm/xe/uapi: Remove DRM_XE_VM_BIND_FLAG_ASYNC comment left over MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a comment left over of commit d3d767396a02 ("drm/xe/uapi: Remove sync binds"). Fixes: d3d767396a02 ("drm/xe/uapi: Remove sync binds") Reviewed-by: Rodrigo Vivi Cc: Matthew Brost Signed-off-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20231226172321.61518-1-jose.souza@intel.com (cherry picked from commit f031c3a7af8ea06790dd0a71872c4f0175084baa) Signed-off-by: Thomas Hellström --- include/uapi/drm/xe_drm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 4f010949f812..a7274a99d456 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -832,7 +832,6 @@ struct drm_xe_vm_destroy { * * and the @flags can be: * - %DRM_XE_VM_BIND_FLAG_READONLY - * - %DRM_XE_VM_BIND_FLAG_ASYNC * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the * MAP operation immediately rather than deferring the MAP to the page * fault handler. -- cgit v1.2.3 From eaa367a0317ea4cbc7aa60f25829c89c0e12717b Mon Sep 17 00:00:00 2001 From: Francois Dugast Date: Thu, 22 Feb 2024 18:23:56 -0500 Subject: drm/xe/uapi: Remove unused flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those cases missed in previous uAPI cleanups were mostly accidentally brought in from i915 or created to exercise the possibilities of gpuvm but they are not used by userspace yet, so let's remove them. They can still be brought back later if needed. v2: - Fix XE_VM_FLAG_FAULT_MODE support in xe_lrc.c (Brian Welty) - Leave DRM_XE_VM_BIND_OP_UNMAP_ALL (José Roberto de Souza) - Ensure invalid flag values are rejected (Rodrigo Vivi) v3: Rebase after removal of persistent exec_queues (Francois Dugast) v4: Rodrigo: Rebase after the new dumpable flag. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Thomas Hellström Cc: Rodrigo Vivi Signed-off-by: Francois Dugast Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240222232356.175431-1-rodrigo.vivi@intel.com (cherry picked from commit 84a1ed5e67565b09b8fd22a26754d2897de55ce0) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_exec_queue.c | 88 ++------------------------------ drivers/gpu/drm/xe/xe_exec_queue_types.h | 10 ---- drivers/gpu/drm/xe/xe_lrc.c | 10 +--- drivers/gpu/drm/xe/xe_vm.c | 12 +---- drivers/gpu/drm/xe/xe_vm_types.h | 4 -- include/uapi/drm/xe_drm.h | 19 ------- 6 files changed, 6 insertions(+), 137 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 3acfd4f07666..49223026c89f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -309,85 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue * return q->ops->set_timeslice(q, value); } -static int exec_queue_set_preemption_timeout(struct xe_device *xe, - struct xe_exec_queue *q, u64 value, - bool create) -{ - u32 min = 0, max = 0; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_preempt_timeout(q, value); -} - -static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - u32 min = 0, max = 0; - - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_job_timeout(q, value); -} - -static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_trigger = value; - - return 0; -} - -static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_notify = value; - - return 0; -} - -static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - if (value > DRM_XE_ACC_GRANULARITY_64M) - return -EINVAL; - - q->usm.acc_granularity = value; - - return 0; -} - typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, struct xe_exec_queue *q, u64 value, bool create); @@ -395,11 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = { [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity, }; static int exec_queue_user_ext_set_property(struct xe_device *xe, @@ -418,7 +334,9 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe, if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(exec_queue_set_property_funcs)) || - XE_IOCTL_DBG(xe, ext.pad)) + XE_IOCTL_DBG(xe, ext.pad) || + XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY && + ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE)) return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs)); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 947bbc4b285d..36f4901d8d7e 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -150,16 +150,6 @@ struct xe_exec_queue { spinlock_t lock; } compute; - /** @usm: unified shared memory state */ - struct { - /** @acc_trigger: access counter trigger */ - u32 acc_trigger; - /** @acc_notify: access counter notify */ - u32 acc_notify; - /** @acc_granularity: access counter granularity */ - u32 acc_granularity; - } usm; - /** @ops: submission backend exec queue operations */ const struct xe_exec_queue_ops *ops; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 0ec5ad2539f1..b38319d2801e 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm) #define PVC_CTX_ASID (0x2e + 1) #define PVC_CTX_ACC_CTR_THOLD (0x2a + 1) -#define ACC_GRANULARITY_S 20 -#define ACC_NOTIFY_S 16 int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size) @@ -754,13 +752,7 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL, RING_CTL_SIZE(lrc->ring.size) | RING_VALID); if (xe->info.has_asid && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, - (q->usm.acc_granularity << - ACC_GRANULARITY_S) | vm->usm.asid); - if (xe->info.has_usm && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD, - (q->usm.acc_notify << ACC_NOTIFY_S) | - q->usm.acc_trigger); + xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid); lrc->desc = LRC_VALID; lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 945c89b5e4b5..1d82616aa935 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -2117,10 +2117,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, struct xe_vma_op *op = gpuva_op_to_vma_op(__op); if (__op->op == DRM_GPUVA_OP_MAP) { - op->map.immediate = - flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE; - op->map.read_only = - flags & DRM_XE_VM_BIND_FLAG_READONLY; op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; op->map.pat_index = pat_index; } else if (__op->op == DRM_GPUVA_OP_PREFETCH) { @@ -2313,8 +2309,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, switch (op->base.op) { case DRM_GPUVA_OP_MAP: { - flags |= op->map.read_only ? - VMA_CREATE_FLAG_READ_ONLY : 0; flags |= op->map.is_null ? VMA_CREATE_FLAG_IS_NULL : 0; @@ -2445,7 +2439,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm, case DRM_GPUVA_OP_MAP: err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma), op->syncs, op->num_syncs, - op->map.immediate || !xe_vm_in_fault_mode(vm), + !xe_vm_in_fault_mode(vm), op->flags & XE_VMA_OP_FIRST, op->flags & XE_VMA_OP_LAST); break; @@ -2720,9 +2714,7 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, return 0; } -#define SUPPORTED_FLAGS \ - (DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \ +#define SUPPORTED_FLAGS (DRM_XE_VM_BIND_FLAG_NULL | \ DRM_XE_VM_BIND_FLAG_DUMPABLE) #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index a603cc2eb56b..0f220b5d2e7b 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -288,10 +288,6 @@ struct xe_vm { struct xe_vma_op_map { /** @vma: VMA to map */ struct xe_vma *vma; - /** @immediate: Immediate bind */ - bool immediate; - /** @read_only: Read only */ - bool read_only; /** @is_null: is NULL binding */ bool is_null; /** @pat_index: The pat index to use for this operation. */ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index a7274a99d456..bb0c8a994116 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -831,10 +831,6 @@ struct drm_xe_vm_destroy { * - %DRM_XE_VM_BIND_OP_PREFETCH * * and the @flags can be: - * - %DRM_XE_VM_BIND_FLAG_READONLY - * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the - * MAP operation immediately rather than deferring the MAP to the page - * fault handler. * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page * tables are setup with a special bit which indicates writes are * dropped and all reads return zero. In the future, the NULL flags @@ -927,8 +923,6 @@ struct drm_xe_vm_bind_op { /** @op: Bind operation to perform */ __u32 op; -#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) -#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) #define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) #define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) /** @flags: Bind flags */ @@ -1045,19 +1039,6 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7 -/* Monitor 128KB contiguous region with 4K sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_128K 0 -/* Monitor 2MB contiguous region with 64KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_2M 1 -/* Monitor 16MB contiguous region with 512KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_16M 2 -/* Monitor 64MB contiguous region with 2M sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_64M 3 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; -- cgit v1.2.3 From 896880ff30866f386ebed14ab81ce1ad3710cfc4 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 22 Feb 2024 07:56:15 -0800 Subject: bpf: Replace bpf_lpm_trie_key 0-length array with flexible array Replace deprecated 0-length array in struct bpf_lpm_trie_key with flexible array. Found with GCC 13: ../kernel/bpf/lpm_trie.c:207:51: warning: array subscript i is outside array bounds of 'const __u8[0]' {aka 'const unsigned char[]'} [-Warray-bounds=] 207 | *(__be16 *)&key->data[i]); | ^~~~~~~~~~~~~ ../include/uapi/linux/swab.h:102:54: note: in definition of macro '__swab16' 102 | #define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) | ^ ../include/linux/byteorder/generic.h:97:21: note: in expansion of macro '__be16_to_cpu' 97 | #define be16_to_cpu __be16_to_cpu | ^~~~~~~~~~~~~ ../kernel/bpf/lpm_trie.c:206:28: note: in expansion of macro 'be16_to_cpu' 206 | u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ | ^~~~~~~~~~~ In file included from ../include/linux/bpf.h:7: ../include/uapi/linux/bpf.h:82:17: note: while referencing 'data' 82 | __u8 data[0]; /* Arbitrary size */ | ^~~~ And found at run-time under CONFIG_FORTIFY_SOURCE: UBSAN: array-index-out-of-bounds in kernel/bpf/lpm_trie.c:218:49 index 0 is out of range for type '__u8 [*]' Changing struct bpf_lpm_trie_key is difficult since has been used by userspace. For example, in Cilium: struct egress_gw_policy_key { struct bpf_lpm_trie_key lpm_key; __u32 saddr; __u32 daddr; }; While direct references to the "data" member haven't been found, there are static initializers what include the final member. For example, the "{}" here: struct egress_gw_policy_key in_key = { .lpm_key = { 32 + 24, {} }, .saddr = CLIENT_IP, .daddr = EXTERNAL_SVC_IP & 0Xffffff, }; To avoid the build time and run time warnings seen with a 0-sized trailing array for struct bpf_lpm_trie_key, introduce a new struct that correctly uses a flexible array for the trailing bytes, struct bpf_lpm_trie_key_u8. As part of this, include the "header" portion (which is just the "prefixlen" member), so it can be used by anything building a bpf_lpr_trie_key that has trailing members that aren't a u8 flexible array (like the self-test[1]), which is named struct bpf_lpm_trie_key_hdr. Unfortunately, C++ refuses to parse the __struct_group() helper, so it is not possible to define struct bpf_lpm_trie_key_hdr directly in struct bpf_lpm_trie_key_u8, so we must open-code the union directly. Adjust the kernel code to use struct bpf_lpm_trie_key_u8 through-out, and for the selftest to use struct bpf_lpm_trie_key_hdr. Add a comment to the UAPI header directing folks to the two new options. Reported-by: Mark Rutland Signed-off-by: Kees Cook Signed-off-by: Daniel Borkmann Acked-by: Gustavo A. R. Silva Closes: https://paste.debian.net/hidden/ca500597/ Link: https://lore.kernel.org/all/202206281009.4332AA33@keescook/ [1] Link: https://lore.kernel.org/bpf/20240222155612.it.533-kees@kernel.org --- Documentation/bpf/map_lpm_trie.rst | 2 +- include/uapi/linux/bpf.h | 19 ++++++++++++++++++- kernel/bpf/lpm_trie.c | 20 ++++++++++---------- samples/bpf/map_perf_test_user.c | 2 +- samples/bpf/xdp_router_ipv4_user.c | 2 +- tools/include/uapi/linux/bpf.h | 19 ++++++++++++++++++- tools/testing/selftests/bpf/progs/map_ptr_kern.c | 2 +- tools/testing/selftests/bpf/test_lpm_map.c | 18 +++++++++--------- 8 files changed, 59 insertions(+), 25 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/bpf/map_lpm_trie.rst b/Documentation/bpf/map_lpm_trie.rst index 74d64a30f500..f9cd579496c9 100644 --- a/Documentation/bpf/map_lpm_trie.rst +++ b/Documentation/bpf/map_lpm_trie.rst @@ -17,7 +17,7 @@ significant byte. LPM tries may be created with a maximum prefix length that is a multiple of 8, in the range from 8 to 2048. The key used for lookup and update -operations is a ``struct bpf_lpm_trie_key``, extended by +operations is a ``struct bpf_lpm_trie_key_u8``, extended by ``max_prefixlen/8`` bytes. - For IPv4 addresses the data length is 4 bytes diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d2e6c5fcec01..a241f407c234 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -77,12 +77,29 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; -/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for + * byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for + * the trailing flexible array member) instead. + */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ __u8 data[0]; /* Arbitrary size */ }; +/* Header for bpf_lpm_trie_key structs */ +struct bpf_lpm_trie_key_hdr { + __u32 prefixlen; +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */ +struct bpf_lpm_trie_key_u8 { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + __u8 data[]; /* Arbitrary size */ +}; + struct bpf_cgroup_storage_key { __u64 cgroup_inode_id; /* cgroup inode id */ __u32 attach_type; /* program attach type (enum bpf_attach_type) */ diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b32be680da6c..050fe1ebf0f7 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -164,13 +164,13 @@ static inline int extract_bit(const u8 *data, size_t index) */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, - const struct bpf_lpm_trie_key *key) + const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); - BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key_u8, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) @@ -229,7 +229,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; if (key->prefixlen > trie->max_prefixlen) return NULL; @@ -309,7 +309,7 @@ static long trie_update_elem(struct bpf_map *map, struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; @@ -437,7 +437,7 @@ out: static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; @@ -536,7 +536,7 @@ out: sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 -#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) +#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key_u8) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) @@ -565,7 +565,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - - offsetof(struct bpf_lpm_trie_key, data); + offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; spin_lock_init(&trie->lock); @@ -616,7 +616,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; + struct bpf_lpm_trie_key_u8 *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; @@ -703,7 +703,7 @@ find_leftmost: } do_copy: next_key->prefixlen = next_node->prefixlen; - memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), + memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key_u8, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); @@ -715,7 +715,7 @@ static int trie_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - /* Keys must have struct bpf_lpm_trie_key embedded. */ + /* Keys must have struct bpf_lpm_trie_key_u8 embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index d2fbcf963cdf..07ff471ed6ae 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -370,7 +370,7 @@ static void run_perf_test(int tasks) static void fill_lpm_trie(void) { - struct bpf_lpm_trie_key *key; + struct bpf_lpm_trie_key_u8 *key; unsigned long value = 0; unsigned int i; int r; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 9d41db09c480..266fdd0b025d 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -91,7 +91,7 @@ static int recv_msg(struct sockaddr_nl sock_addr, int sock) static void read_route(struct nlmsghdr *nh, int nll) { char dsts[24], gws[24], ifs[16], dsts_len[24], metrics[24]; - struct bpf_lpm_trie_key *prefix_key; + struct bpf_lpm_trie_key_u8 *prefix_key; struct rtattr *rt_attr; struct rtmsg *rt_msg; int rtm_family; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d2e6c5fcec01..a241f407c234 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -77,12 +77,29 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; -/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for + * byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for + * the trailing flexible array member) instead. + */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ __u8 data[0]; /* Arbitrary size */ }; +/* Header for bpf_lpm_trie_key structs */ +struct bpf_lpm_trie_key_hdr { + __u32 prefixlen; +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */ +struct bpf_lpm_trie_key_u8 { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + __u8 data[]; /* Arbitrary size */ +}; + struct bpf_cgroup_storage_key { __u64 cgroup_inode_id; /* cgroup inode id */ __u32 attach_type; /* program attach type (enum bpf_attach_type) */ diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index 3325da17ec81..efaf622c28dd 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -316,7 +316,7 @@ struct lpm_trie { } __attribute__((preserve_access_index)); struct lpm_key { - struct bpf_lpm_trie_key trie_key; + struct bpf_lpm_trie_key_hdr trie_key; __u32 data; }; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index c028d621c744..d98c72dc563e 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -211,7 +211,7 @@ static void test_lpm_map(int keysize) volatile size_t n_matches, n_matches_after_delete; size_t i, j, n_nodes, n_lookups; struct tlpm_node *t, *list = NULL; - struct bpf_lpm_trie_key *key; + struct bpf_lpm_trie_key_u8 *key; uint8_t *data, *value; int r, map; @@ -331,8 +331,8 @@ static void test_lpm_map(int keysize) static void test_lpm_ipaddr(void) { LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key *key_ipv4; - struct bpf_lpm_trie_key *key_ipv6; + struct bpf_lpm_trie_key_u8 *key_ipv4; + struct bpf_lpm_trie_key_u8 *key_ipv6; size_t key_size_ipv4; size_t key_size_ipv6; int map_fd_ipv4; @@ -423,7 +423,7 @@ static void test_lpm_ipaddr(void) static void test_lpm_delete(void) { LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key *key; + struct bpf_lpm_trie_key_u8 *key; size_t key_size; int map_fd; __u64 value; @@ -532,7 +532,7 @@ static void test_lpm_delete(void) static void test_lpm_get_next_key(void) { LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key *key_p, *next_key_p; + struct bpf_lpm_trie_key_u8 *key_p, *next_key_p; size_t key_size; __u32 value = 0; int map_fd; @@ -693,9 +693,9 @@ static void *lpm_test_command(void *arg) { int i, j, ret, iter, key_size; struct lpm_mt_test_info *info = arg; - struct bpf_lpm_trie_key *key_p; + struct bpf_lpm_trie_key_u8 *key_p; - key_size = sizeof(struct bpf_lpm_trie_key) + sizeof(__u32); + key_size = sizeof(*key_p) + sizeof(__u32); key_p = alloca(key_size); for (iter = 0; iter < info->iter; iter++) for (i = 0; i < MAX_TEST_KEYS; i++) { @@ -717,7 +717,7 @@ static void *lpm_test_command(void *arg) ret = bpf_map_lookup_elem(info->map_fd, key_p, &value); assert(ret == 0 || errno == ENOENT); } else { - struct bpf_lpm_trie_key *next_key_p = alloca(key_size); + struct bpf_lpm_trie_key_u8 *next_key_p = alloca(key_size); ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p); assert(ret == 0 || errno == ENOENT || errno == ENOMEM); } @@ -752,7 +752,7 @@ static void test_lpm_multi_thread(void) /* create a trie */ value_size = sizeof(__u32); - key_size = sizeof(struct bpf_lpm_trie_key) + value_size; + key_size = sizeof(struct bpf_lpm_trie_key_hdr) + value_size; map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts); /* create 4 threads to test update, delete, lookup and get_next_key */ -- cgit v1.2.3 From 0f25e493a2462dbdd2e34f4e100405380cc0201a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 29 Feb 2024 17:22:15 +0100 Subject: drm/panthor: Add uAPI Panthor follows the lead of other recently submitted drivers with ioctls allowing us to support modern Vulkan features, like sparse memory binding: - Pretty standard GEM management ioctls (BO_CREATE and BO_MMAP_OFFSET), with the 'exclusive-VM' bit to speed-up BO reservation on job submission - VM management ioctls (VM_CREATE, VM_DESTROY and VM_BIND). The VM_BIND ioctl is loosely based on the Xe model, and can handle both asynchronous and synchronous requests - GPU execution context creation/destruction, tiler heap context creation and job submission. Those ioctls reflect how the hardware/scheduler works and are thus driver specific. We also have a way to expose IO regions, such that the usermode driver can directly access specific/well-isolate registers, like the LATEST_FLUSH register used to implement cache-flush reduction. This uAPI intentionally keeps usermode queues out of the scope, which explains why doorbell registers and command stream ring-buffers are not directly exposed to userspace. v6: - Add Maxime's and Heiko's acks v5: - Fix typo - Add Liviu's R-b v4: - Add a VM_GET_STATE ioctl - Fix doc - Expose the CORE_FEATURES register so we can deal with variants in the UMD - Add Steve's R-b v3: - Add the concept of sync-only VM operation - Fix support for 32-bit userspace - Rework drm_panthor_vm_create to pass the user VA size instead of the kernel VA size (suggested by Robin Murphy) - Typo fixes - Explicitly cast enums with top bit set to avoid compiler warnings in -pedantic mode. - Drop property core_group_count as it can be easily calculated by the number of bits set in l2_present. Co-developed-by: Steven Price Signed-off-by: Steven Price Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Reviewed-by: Liviu Dudau Acked-by: Maxime Ripard Acked-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20240229162230.2634044-2-boris.brezillon@collabora.com --- Documentation/gpu/driver-uapi.rst | 5 + include/uapi/drm/panthor_drm.h | 945 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 950 insertions(+) create mode 100644 include/uapi/drm/panthor_drm.h (limited to 'include/uapi') diff --git a/Documentation/gpu/driver-uapi.rst b/Documentation/gpu/driver-uapi.rst index e5070a0e95ab..971cdb4816fc 100644 --- a/Documentation/gpu/driver-uapi.rst +++ b/Documentation/gpu/driver-uapi.rst @@ -18,6 +18,11 @@ VM_BIND / EXEC uAPI .. kernel-doc:: include/uapi/drm/nouveau_drm.h +drm/panthor uAPI +================ + +.. kernel-doc:: include/uapi/drm/panthor_drm.h + drm/xe uAPI =========== diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h new file mode 100644 index 000000000000..373df80f41ed --- /dev/null +++ b/include/uapi/drm/panthor_drm.h @@ -0,0 +1,945 @@ +/* SPDX-License-Identifier: MIT */ +/* Copyright (C) 2023 Collabora ltd. */ +#ifndef _PANTHOR_DRM_H_ +#define _PANTHOR_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: Introduction + * + * This documentation describes the Panthor IOCTLs. + * + * Just a few generic rules about the data passed to the Panthor IOCTLs: + * + * - Structures must be aligned on 64-bit/8-byte. If the object is not + * naturally aligned, a padding field must be added. + * - Fields must be explicitly aligned to their natural type alignment with + * pad[0..N] fields. + * - All padding fields will be checked by the driver to make sure they are + * zeroed. + * - Flags can be added, but not removed/replaced. + * - New fields can be added to the main structures (the structures + * directly passed to the ioctl). Those fields can be added at the end of + * the structure, or replace existing padding fields. Any new field being + * added must preserve the behavior that existed before those fields were + * added when a value of zero is passed. + * - New fields can be added to indirect objects (objects pointed by the + * main structure), iff those objects are passed a size to reflect the + * size known by the userspace driver (see drm_panthor_obj_array::stride + * or drm_panthor_dev_query::size). + * - If the kernel driver is too old to know some fields, those will be + * ignored if zero, and otherwise rejected (and so will be zero on output). + * - If userspace is too old to know some fields, those will be zeroed + * (input) before the structure is parsed by the kernel driver. + * - Each new flag/field addition must come with a driver version update so + * the userspace driver doesn't have to trial and error to know which + * flags are supported. + * - Structures should not contain unions, as this would defeat the + * extensibility of such structures. + * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed + * at the end of the drm_panthor_ioctl_id enum. + */ + +/** + * DOC: MMIO regions exposed to userspace. + * + * .. c:macro:: DRM_PANTHOR_USER_MMIO_OFFSET + * + * File offset for all MMIO regions being exposed to userspace. Don't use + * this value directly, use DRM_PANTHOR_USER__OFFSET values instead. + * pgoffset passed to mmap2() is an unsigned long, which forces us to use a + * different offset on 32-bit and 64-bit systems. + * + * .. c:macro:: DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET + * + * File offset for the LATEST_FLUSH_ID register. The Userspace driver controls + * GPU cache flushing through CS instructions, but the flush reduction + * mechanism requires a flush_id. This flush_id could be queried with an + * ioctl, but Arm provides a well-isolated register page containing only this + * read-only register, so let's expose this page through a static mmap offset + * and allow direct mapping of this MMIO region so we can avoid the + * user <-> kernel round-trip. + */ +#define DRM_PANTHOR_USER_MMIO_OFFSET_32BIT (1ull << 43) +#define DRM_PANTHOR_USER_MMIO_OFFSET_64BIT (1ull << 56) +#define DRM_PANTHOR_USER_MMIO_OFFSET (sizeof(unsigned long) < 8 ? \ + DRM_PANTHOR_USER_MMIO_OFFSET_32BIT : \ + DRM_PANTHOR_USER_MMIO_OFFSET_64BIT) +#define DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET (DRM_PANTHOR_USER_MMIO_OFFSET | 0) + +/** + * DOC: IOCTL IDs + * + * enum drm_panthor_ioctl_id - IOCTL IDs + * + * Place new ioctls at the end, don't re-order, don't replace or remove entries. + * + * These IDs are not meant to be used directly. Use the DRM_IOCTL_PANTHOR_xxx + * definitions instead. + */ +enum drm_panthor_ioctl_id { + /** @DRM_PANTHOR_DEV_QUERY: Query device information. */ + DRM_PANTHOR_DEV_QUERY = 0, + + /** @DRM_PANTHOR_VM_CREATE: Create a VM. */ + DRM_PANTHOR_VM_CREATE, + + /** @DRM_PANTHOR_VM_DESTROY: Destroy a VM. */ + DRM_PANTHOR_VM_DESTROY, + + /** @DRM_PANTHOR_VM_BIND: Bind/unbind memory to a VM. */ + DRM_PANTHOR_VM_BIND, + + /** @DRM_PANTHOR_VM_GET_STATE: Get VM state. */ + DRM_PANTHOR_VM_GET_STATE, + + /** @DRM_PANTHOR_BO_CREATE: Create a buffer object. */ + DRM_PANTHOR_BO_CREATE, + + /** + * @DRM_PANTHOR_BO_MMAP_OFFSET: Get the file offset to pass to + * mmap to map a GEM object. + */ + DRM_PANTHOR_BO_MMAP_OFFSET, + + /** @DRM_PANTHOR_GROUP_CREATE: Create a scheduling group. */ + DRM_PANTHOR_GROUP_CREATE, + + /** @DRM_PANTHOR_GROUP_DESTROY: Destroy a scheduling group. */ + DRM_PANTHOR_GROUP_DESTROY, + + /** + * @DRM_PANTHOR_GROUP_SUBMIT: Submit jobs to queues belonging + * to a specific scheduling group. + */ + DRM_PANTHOR_GROUP_SUBMIT, + + /** @DRM_PANTHOR_GROUP_GET_STATE: Get the state of a scheduling group. */ + DRM_PANTHOR_GROUP_GET_STATE, + + /** @DRM_PANTHOR_TILER_HEAP_CREATE: Create a tiler heap. */ + DRM_PANTHOR_TILER_HEAP_CREATE, + + /** @DRM_PANTHOR_TILER_HEAP_DESTROY: Destroy a tiler heap. */ + DRM_PANTHOR_TILER_HEAP_DESTROY, +}; + +/** + * DRM_IOCTL_PANTHOR() - Build a Panthor IOCTL number + * @__access: Access type. Must be R, W or RW. + * @__id: One of the DRM_PANTHOR_xxx id. + * @__type: Suffix of the type being passed to the IOCTL. + * + * Don't use this macro directly, use the DRM_IOCTL_PANTHOR_xxx + * values instead. + * + * Return: An IOCTL number to be passed to ioctl() from userspace. + */ +#define DRM_IOCTL_PANTHOR(__access, __id, __type) \ + DRM_IO ## __access(DRM_COMMAND_BASE + DRM_PANTHOR_ ## __id, \ + struct drm_panthor_ ## __type) + +#define DRM_IOCTL_PANTHOR_DEV_QUERY \ + DRM_IOCTL_PANTHOR(WR, DEV_QUERY, dev_query) +#define DRM_IOCTL_PANTHOR_VM_CREATE \ + DRM_IOCTL_PANTHOR(WR, VM_CREATE, vm_create) +#define DRM_IOCTL_PANTHOR_VM_DESTROY \ + DRM_IOCTL_PANTHOR(WR, VM_DESTROY, vm_destroy) +#define DRM_IOCTL_PANTHOR_VM_BIND \ + DRM_IOCTL_PANTHOR(WR, VM_BIND, vm_bind) +#define DRM_IOCTL_PANTHOR_VM_GET_STATE \ + DRM_IOCTL_PANTHOR(WR, VM_GET_STATE, vm_get_state) +#define DRM_IOCTL_PANTHOR_BO_CREATE \ + DRM_IOCTL_PANTHOR(WR, BO_CREATE, bo_create) +#define DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET \ + DRM_IOCTL_PANTHOR(WR, BO_MMAP_OFFSET, bo_mmap_offset) +#define DRM_IOCTL_PANTHOR_GROUP_CREATE \ + DRM_IOCTL_PANTHOR(WR, GROUP_CREATE, group_create) +#define DRM_IOCTL_PANTHOR_GROUP_DESTROY \ + DRM_IOCTL_PANTHOR(WR, GROUP_DESTROY, group_destroy) +#define DRM_IOCTL_PANTHOR_GROUP_SUBMIT \ + DRM_IOCTL_PANTHOR(WR, GROUP_SUBMIT, group_submit) +#define DRM_IOCTL_PANTHOR_GROUP_GET_STATE \ + DRM_IOCTL_PANTHOR(WR, GROUP_GET_STATE, group_get_state) +#define DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE \ + DRM_IOCTL_PANTHOR(WR, TILER_HEAP_CREATE, tiler_heap_create) +#define DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY \ + DRM_IOCTL_PANTHOR(WR, TILER_HEAP_DESTROY, tiler_heap_destroy) + +/** + * DOC: IOCTL arguments + */ + +/** + * struct drm_panthor_obj_array - Object array. + * + * This object is used to pass an array of objects whose size is subject to changes in + * future versions of the driver. In order to support this mutability, we pass a stride + * describing the size of the object as known by userspace. + * + * You shouldn't fill drm_panthor_obj_array fields directly. You should instead use + * the DRM_PANTHOR_OBJ_ARRAY() macro that takes care of initializing the stride to + * the object size. + */ +struct drm_panthor_obj_array { + /** @stride: Stride of object struct. Used for versioning. */ + __u32 stride; + + /** @count: Number of objects in the array. */ + __u32 count; + + /** @array: User pointer to an array of objects. */ + __u64 array; +}; + +/** + * DRM_PANTHOR_OBJ_ARRAY() - Initialize a drm_panthor_obj_array field. + * @cnt: Number of elements in the array. + * @ptr: Pointer to the array to pass to the kernel. + * + * Macro initializing a drm_panthor_obj_array based on the object size as known + * by userspace. + */ +#define DRM_PANTHOR_OBJ_ARRAY(cnt, ptr) \ + { .stride = sizeof((ptr)[0]), .count = (cnt), .array = (__u64)(uintptr_t)(ptr) } + +/** + * enum drm_panthor_sync_op_flags - Synchronization operation flags. + */ +enum drm_panthor_sync_op_flags { + /** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK: Synchronization handle type mask. */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK = 0xff, + + /** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ: Synchronization object type. */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ = 0, + + /** + * @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ: Timeline synchronization + * object type. + */ + DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ = 1, + + /** @DRM_PANTHOR_SYNC_OP_WAIT: Wait operation. */ + DRM_PANTHOR_SYNC_OP_WAIT = 0 << 31, + + /** @DRM_PANTHOR_SYNC_OP_SIGNAL: Signal operation. */ + DRM_PANTHOR_SYNC_OP_SIGNAL = (int)(1u << 31), +}; + +/** + * struct drm_panthor_sync_op - Synchronization operation. + */ +struct drm_panthor_sync_op { + /** @flags: Synchronization operation flags. Combination of DRM_PANTHOR_SYNC_OP values. */ + __u32 flags; + + /** @handle: Sync handle. */ + __u32 handle; + + /** + * @timeline_value: MBZ if + * (flags & DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK) != + * DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ. + */ + __u64 timeline_value; +}; + +/** + * enum drm_panthor_dev_query_type - Query type + * + * Place new types at the end, don't re-order, don't remove or replace. + */ +enum drm_panthor_dev_query_type { + /** @DRM_PANTHOR_DEV_QUERY_GPU_INFO: Query GPU information. */ + DRM_PANTHOR_DEV_QUERY_GPU_INFO = 0, + + /** @DRM_PANTHOR_DEV_QUERY_CSIF_INFO: Query command-stream interface information. */ + DRM_PANTHOR_DEV_QUERY_CSIF_INFO, +}; + +/** + * struct drm_panthor_gpu_info - GPU information + * + * Structure grouping all queryable information relating to the GPU. + */ +struct drm_panthor_gpu_info { + /** @gpu_id : GPU ID. */ + __u32 gpu_id; +#define DRM_PANTHOR_ARCH_MAJOR(x) ((x) >> 28) +#define DRM_PANTHOR_ARCH_MINOR(x) (((x) >> 24) & 0xf) +#define DRM_PANTHOR_ARCH_REV(x) (((x) >> 20) & 0xf) +#define DRM_PANTHOR_PRODUCT_MAJOR(x) (((x) >> 16) & 0xf) +#define DRM_PANTHOR_VERSION_MAJOR(x) (((x) >> 12) & 0xf) +#define DRM_PANTHOR_VERSION_MINOR(x) (((x) >> 4) & 0xff) +#define DRM_PANTHOR_VERSION_STATUS(x) ((x) & 0xf) + + /** @gpu_rev: GPU revision. */ + __u32 gpu_rev; + + /** @csf_id: Command stream frontend ID. */ + __u32 csf_id; +#define DRM_PANTHOR_CSHW_MAJOR(x) (((x) >> 26) & 0x3f) +#define DRM_PANTHOR_CSHW_MINOR(x) (((x) >> 20) & 0x3f) +#define DRM_PANTHOR_CSHW_REV(x) (((x) >> 16) & 0xf) +#define DRM_PANTHOR_MCU_MAJOR(x) (((x) >> 10) & 0x3f) +#define DRM_PANTHOR_MCU_MINOR(x) (((x) >> 4) & 0x3f) +#define DRM_PANTHOR_MCU_REV(x) ((x) & 0xf) + + /** @l2_features: L2-cache features. */ + __u32 l2_features; + + /** @tiler_features: Tiler features. */ + __u32 tiler_features; + + /** @mem_features: Memory features. */ + __u32 mem_features; + + /** @mmu_features: MMU features. */ + __u32 mmu_features; +#define DRM_PANTHOR_MMU_VA_BITS(x) ((x) & 0xff) + + /** @thread_features: Thread features. */ + __u32 thread_features; + + /** @max_threads: Maximum number of threads. */ + __u32 max_threads; + + /** @thread_max_workgroup_size: Maximum workgroup size. */ + __u32 thread_max_workgroup_size; + + /** + * @thread_max_barrier_size: Maximum number of threads that can wait + * simultaneously on a barrier. + */ + __u32 thread_max_barrier_size; + + /** @coherency_features: Coherency features. */ + __u32 coherency_features; + + /** @texture_features: Texture features. */ + __u32 texture_features[4]; + + /** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */ + __u32 as_present; + + /** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */ + __u64 shader_present; + + /** @l2_present: Bitmask encoding the L2 caches exposed by the GPU. */ + __u64 l2_present; + + /** @tiler_present: Bitmask encoding the tiler units exposed by the GPU. */ + __u64 tiler_present; + + /* @core_features: Used to discriminate core variants when they exist. */ + __u32 core_features; + + /* @pad: MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_csif_info - Command stream interface information + * + * Structure grouping all queryable information relating to the command stream interface. + */ +struct drm_panthor_csif_info { + /** @csg_slot_count: Number of command stream group slots exposed by the firmware. */ + __u32 csg_slot_count; + + /** @cs_slot_count: Number of command stream slots per group. */ + __u32 cs_slot_count; + + /** @cs_reg_count: Number of command stream registers. */ + __u32 cs_reg_count; + + /** @scoreboard_slot_count: Number of scoreboard slots. */ + __u32 scoreboard_slot_count; + + /** + * @unpreserved_cs_reg_count: Number of command stream registers reserved by + * the kernel driver to call a userspace command stream. + * + * All registers can be used by a userspace command stream, but the + * [cs_slot_count - unpreserved_cs_reg_count .. cs_slot_count] registers are + * used by the kernel when DRM_PANTHOR_IOCTL_GROUP_SUBMIT is called. + */ + __u32 unpreserved_cs_reg_count; + + /** + * @pad: Padding field, set to zero. + */ + __u32 pad; +}; + +/** + * struct drm_panthor_dev_query - Arguments passed to DRM_PANTHOR_IOCTL_DEV_QUERY + */ +struct drm_panthor_dev_query { + /** @type: the query type (see drm_panthor_dev_query_type). */ + __u32 type; + + /** + * @size: size of the type being queried. + * + * If pointer is NULL, size is updated by the driver to provide the + * output structure size. If pointer is not NULL, the driver will + * only copy min(size, actual_structure_size) bytes to the pointer, + * and update the size accordingly. This allows us to extend query + * types without breaking userspace. + */ + __u32 size; + + /** + * @pointer: user pointer to a query type struct. + * + * Pointer can be NULL, in which case, nothing is copied, but the + * actual structure size is returned. If not NULL, it must point to + * a location that's large enough to hold size bytes. + */ + __u64 pointer; +}; + +/** + * struct drm_panthor_vm_create - Arguments passed to DRM_PANTHOR_IOCTL_VM_CREATE + */ +struct drm_panthor_vm_create { + /** @flags: VM flags, MBZ. */ + __u32 flags; + + /** @id: Returned VM ID. */ + __u32 id; + + /** + * @user_va_range: Size of the VA space reserved for user objects. + * + * The kernel will pick the remaining space to map kernel-only objects to the + * VM (heap chunks, heap context, ring buffers, kernel synchronization objects, + * ...). If the space left for kernel objects is too small, kernel object + * allocation will fail further down the road. One can use + * drm_panthor_gpu_info::mmu_features to extract the total virtual address + * range, and chose a user_va_range that leaves some space to the kernel. + * + * If user_va_range is zero, the kernel will pick a sensible value based on + * TASK_SIZE and the virtual range supported by the GPU MMU (the kernel/user + * split should leave enough VA space for userspace processes to support SVM, + * while still allowing the kernel to map some amount of kernel objects in + * the kernel VA range). The value chosen by the driver will be returned in + * @user_va_range. + * + * User VA space always starts at 0x0, kernel VA space is always placed after + * the user VA range. + */ + __u64 user_va_range; +}; + +/** + * struct drm_panthor_vm_destroy - Arguments passed to DRM_PANTHOR_IOCTL_VM_DESTROY + */ +struct drm_panthor_vm_destroy { + /** @id: ID of the VM to destroy. */ + __u32 id; + + /** @pad: MBZ. */ + __u32 pad; +}; + +/** + * enum drm_panthor_vm_bind_op_flags - VM bind operation flags + */ +enum drm_panthor_vm_bind_op_flags { + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_READONLY: Map the memory read-only. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_READONLY = 1 << 0, + + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC: Map the memory not-executable. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC = 1 << 1, + + /** + * @DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED: Map the memory uncached. + * + * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP. + */ + DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED = 1 << 2, + + /** + * @DRM_PANTHOR_VM_BIND_OP_TYPE_MASK: Mask used to determine the type of operation. + */ + DRM_PANTHOR_VM_BIND_OP_TYPE_MASK = (int)(0xfu << 28), + + /** @DRM_PANTHOR_VM_BIND_OP_TYPE_MAP: Map operation. */ + DRM_PANTHOR_VM_BIND_OP_TYPE_MAP = 0 << 28, + + /** @DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP: Unmap operation. */ + DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP = 1 << 28, + + /** + * @DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY: No VM operation. + * + * Just serves as a synchronization point on a VM queue. + * + * Only valid if %DRM_PANTHOR_VM_BIND_ASYNC is set in drm_panthor_vm_bind::flags, + * and drm_panthor_vm_bind_op::syncs contains at least one element. + */ + DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY = 2 << 28, +}; + +/** + * struct drm_panthor_vm_bind_op - VM bind operation + */ +struct drm_panthor_vm_bind_op { + /** @flags: Combination of drm_panthor_vm_bind_op_flags flags. */ + __u32 flags; + + /** + * @bo_handle: Handle of the buffer object to map. + * MBZ for unmap or sync-only operations. + */ + __u32 bo_handle; + + /** + * @bo_offset: Buffer object offset. + * MBZ for unmap or sync-only operations. + */ + __u64 bo_offset; + + /** + * @va: Virtual address to map/unmap. + * MBZ for sync-only operations. + */ + __u64 va; + + /** + * @size: Size to map/unmap. + * MBZ for sync-only operations. + */ + __u64 size; + + /** + * @syncs: Array of struct drm_panthor_sync_op synchronization + * operations. + * + * This array must be empty if %DRM_PANTHOR_VM_BIND_ASYNC is not set on + * the drm_panthor_vm_bind object containing this VM bind operation. + * + * This array shall not be empty for sync-only operations. + */ + struct drm_panthor_obj_array syncs; + +}; + +/** + * enum drm_panthor_vm_bind_flags - VM bind flags + */ +enum drm_panthor_vm_bind_flags { + /** + * @DRM_PANTHOR_VM_BIND_ASYNC: VM bind operations are queued to the VM + * queue instead of being executed synchronously. + */ + DRM_PANTHOR_VM_BIND_ASYNC = 1 << 0, +}; + +/** + * struct drm_panthor_vm_bind - Arguments passed to DRM_IOCTL_PANTHOR_VM_BIND + */ +struct drm_panthor_vm_bind { + /** @vm_id: VM targeted by the bind request. */ + __u32 vm_id; + + /** @flags: Combination of drm_panthor_vm_bind_flags flags. */ + __u32 flags; + + /** @ops: Array of struct drm_panthor_vm_bind_op bind operations. */ + struct drm_panthor_obj_array ops; +}; + +/** + * enum drm_panthor_vm_state - VM states. + */ +enum drm_panthor_vm_state { + /** + * @DRM_PANTHOR_VM_STATE_USABLE: VM is usable. + * + * New VM operations will be accepted on this VM. + */ + DRM_PANTHOR_VM_STATE_USABLE, + + /** + * @DRM_PANTHOR_VM_STATE_UNUSABLE: VM is unusable. + * + * Something put the VM in an unusable state (like an asynchronous + * VM_BIND request failing for any reason). + * + * Once the VM is in this state, all new MAP operations will be + * rejected, and any GPU job targeting this VM will fail. + * UNMAP operations are still accepted. + * + * The only way to recover from an unusable VM is to create a new + * VM, and destroy the old one. + */ + DRM_PANTHOR_VM_STATE_UNUSABLE, +}; + +/** + * struct drm_panthor_vm_get_state - Get VM state. + */ +struct drm_panthor_vm_get_state { + /** @vm_id: VM targeted by the get_state request. */ + __u32 vm_id; + + /** + * @state: state returned by the driver. + * + * Must be one of the enum drm_panthor_vm_state values. + */ + __u32 state; +}; + +/** + * enum drm_panthor_bo_flags - Buffer object flags, passed at creation time. + */ +enum drm_panthor_bo_flags { + /** @DRM_PANTHOR_BO_NO_MMAP: The buffer object will never be CPU-mapped in userspace. */ + DRM_PANTHOR_BO_NO_MMAP = (1 << 0), +}; + +/** + * struct drm_panthor_bo_create - Arguments passed to DRM_IOCTL_PANTHOR_BO_CREATE. + */ +struct drm_panthor_bo_create { + /** + * @size: Requested size for the object + * + * The (page-aligned) allocated size for the object will be returned. + */ + __u64 size; + + /** + * @flags: Flags. Must be a combination of drm_panthor_bo_flags flags. + */ + __u32 flags; + + /** + * @exclusive_vm_id: Exclusive VM this buffer object will be mapped to. + * + * If not zero, the field must refer to a valid VM ID, and implies that: + * - the buffer object will only ever be bound to that VM + * - cannot be exported as a PRIME fd + */ + __u32 exclusive_vm_id; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + + /** @pad: MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_bo_mmap_offset - Arguments passed to DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET. + */ +struct drm_panthor_bo_mmap_offset { + /** @handle: Handle of the object we want an mmap offset for. */ + __u32 handle; + + /** @pad: MBZ. */ + __u32 pad; + + /** @offset: The fake offset to use for subsequent mmap calls. */ + __u64 offset; +}; + +/** + * struct drm_panthor_queue_create - Queue creation arguments. + */ +struct drm_panthor_queue_create { + /** + * @priority: Defines the priority of queues inside a group. Goes from 0 to 15, + * 15 being the highest priority. + */ + __u8 priority; + + /** @pad: Padding fields, MBZ. */ + __u8 pad[3]; + + /** @ringbuf_size: Size of the ring buffer to allocate to this queue. */ + __u32 ringbuf_size; +}; + +/** + * enum drm_panthor_group_priority - Scheduling group priority + */ +enum drm_panthor_group_priority { + /** @PANTHOR_GROUP_PRIORITY_LOW: Low priority group. */ + PANTHOR_GROUP_PRIORITY_LOW = 0, + + /** @PANTHOR_GROUP_PRIORITY_MEDIUM: Medium priority group. */ + PANTHOR_GROUP_PRIORITY_MEDIUM, + + /** @PANTHOR_GROUP_PRIORITY_HIGH: High priority group. */ + PANTHOR_GROUP_PRIORITY_HIGH, +}; + +/** + * struct drm_panthor_group_create - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_CREATE + */ +struct drm_panthor_group_create { + /** @queues: Array of drm_panthor_queue_create elements. */ + struct drm_panthor_obj_array queues; + + /** + * @max_compute_cores: Maximum number of cores that can be used by compute + * jobs across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @compute_core_mask. + */ + __u8 max_compute_cores; + + /** + * @max_fragment_cores: Maximum number of cores that can be used by fragment + * jobs across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @fragment_core_mask. + */ + __u8 max_fragment_cores; + + /** + * @max_tiler_cores: Maximum number of tilers that can be used by tiler jobs + * across CS queues bound to this group. + * + * Must be less or equal to the number of bits set in @tiler_core_mask. + */ + __u8 max_tiler_cores; + + /** @priority: Group priority (see enum drm_panthor_group_priority). */ + __u8 priority; + + /** @pad: Padding field, MBZ. */ + __u32 pad; + + /** + * @compute_core_mask: Mask encoding cores that can be used for compute jobs. + * + * This field must have at least @max_compute_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::shader_present. + */ + __u64 compute_core_mask; + + /** + * @fragment_core_mask: Mask encoding cores that can be used for fragment jobs. + * + * This field must have at least @max_fragment_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::shader_present. + */ + __u64 fragment_core_mask; + + /** + * @tiler_core_mask: Mask encoding cores that can be used for tiler jobs. + * + * This field must have at least @max_tiler_cores bits set. + * + * The bits set here should also be set in drm_panthor_gpu_info::tiler_present. + */ + __u64 tiler_core_mask; + + /** + * @vm_id: VM ID to bind this group to. + * + * All submission to queues bound to this group will use this VM. + */ + __u32 vm_id; + + /** + * @group_handle: Returned group handle. Passed back when submitting jobs or + * destroying a group. + */ + __u32 group_handle; +}; + +/** + * struct drm_panthor_group_destroy - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_DESTROY + */ +struct drm_panthor_group_destroy { + /** @group_handle: Group to destroy */ + __u32 group_handle; + + /** @pad: Padding field, MBZ. */ + __u32 pad; +}; + +/** + * struct drm_panthor_queue_submit - Job submission arguments. + * + * This is describing the userspace command stream to call from the kernel + * command stream ring-buffer. Queue submission is always part of a group + * submission, taking one or more jobs to submit to the underlying queues. + */ +struct drm_panthor_queue_submit { + /** @queue_index: Index of the queue inside a group. */ + __u32 queue_index; + + /** + * @stream_size: Size of the command stream to execute. + * + * Must be 64-bit/8-byte aligned (the size of a CS instruction) + * + * Can be zero if stream_addr is zero too. + */ + __u32 stream_size; + + /** + * @stream_addr: GPU address of the command stream to execute. + * + * Must be aligned on 64-byte. + * + * Can be zero is stream_size is zero too. + */ + __u64 stream_addr; + + /** + * @latest_flush: FLUSH_ID read at the time the stream was built. + * + * This allows cache flush elimination for the automatic + * flush+invalidate(all) done at submission time, which is needed to + * ensure the GPU doesn't get garbage when reading the indirect command + * stream buffers. If you want the cache flush to happen + * unconditionally, pass a zero here. + */ + __u32 latest_flush; + + /** @pad: MBZ. */ + __u32 pad; + + /** @syncs: Array of struct drm_panthor_sync_op sync operations. */ + struct drm_panthor_obj_array syncs; +}; + +/** + * struct drm_panthor_group_submit - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_SUBMIT + */ +struct drm_panthor_group_submit { + /** @group_handle: Handle of the group to queue jobs to. */ + __u32 group_handle; + + /** @pad: MBZ. */ + __u32 pad; + + /** @queue_submits: Array of drm_panthor_queue_submit objects. */ + struct drm_panthor_obj_array queue_submits; +}; + +/** + * enum drm_panthor_group_state_flags - Group state flags + */ +enum drm_panthor_group_state_flags { + /** + * @DRM_PANTHOR_GROUP_STATE_TIMEDOUT: Group had unfinished jobs. + * + * When a group ends up with this flag set, no jobs can be submitted to its queues. + */ + DRM_PANTHOR_GROUP_STATE_TIMEDOUT = 1 << 0, + + /** + * @DRM_PANTHOR_GROUP_STATE_FATAL_FAULT: Group had fatal faults. + * + * When a group ends up with this flag set, no jobs can be submitted to its queues. + */ + DRM_PANTHOR_GROUP_STATE_FATAL_FAULT = 1 << 1, +}; + +/** + * struct drm_panthor_group_get_state - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_GET_STATE + * + * Used to query the state of a group and decide whether a new group should be created to + * replace it. + */ +struct drm_panthor_group_get_state { + /** @group_handle: Handle of the group to query state on */ + __u32 group_handle; + + /** + * @state: Combination of DRM_PANTHOR_GROUP_STATE_* flags encoding the + * group state. + */ + __u32 state; + + /** @fatal_queues: Bitmask of queues that faced fatal faults. */ + __u32 fatal_queues; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_panthor_tiler_heap_create - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE + */ +struct drm_panthor_tiler_heap_create { + /** @vm_id: VM ID the tiler heap should be mapped to */ + __u32 vm_id; + + /** @initial_chunk_count: Initial number of chunks to allocate. */ + __u32 initial_chunk_count; + + /** @chunk_size: Chunk size. Must be a power of two at least 256KB large. */ + __u32 chunk_size; + + /** @max_chunks: Maximum number of chunks that can be allocated. */ + __u32 max_chunks; + + /** + * @target_in_flight: Maximum number of in-flight render passes. + * + * If the heap has more than tiler jobs in-flight, the FW will wait for render + * passes to finish before queuing new tiler jobs. + */ + __u32 target_in_flight; + + /** @handle: Returned heap handle. Passed back to DESTROY_TILER_HEAP. */ + __u32 handle; + + /** @tiler_heap_ctx_gpu_va: Returned heap GPU virtual address returned */ + __u64 tiler_heap_ctx_gpu_va; + + /** + * @first_heap_chunk_gpu_va: First heap chunk. + * + * The tiler heap is formed of heap chunks forming a single-link list. This + * is the first element in the list. + */ + __u64 first_heap_chunk_gpu_va; +}; + +/** + * struct drm_panthor_tiler_heap_destroy - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY + */ +struct drm_panthor_tiler_heap_destroy { + /** @handle: Handle of the tiler heap to destroy */ + __u32 handle; + + /** @pad: Padding field, MBZ. */ + __u32 pad; +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _PANTHOR_DRM_H_ */ -- cgit v1.2.3 From cb12fd8e0dabb9a1c8aef55a6a41e2c255fcdf4b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 12 Feb 2024 16:32:38 +0100 Subject: pidfd: add pidfs This moves pidfds from the anonymous inode infrastructure to a tiny pseudo filesystem. This has been on my todo for quite a while as it will unblock further work that we weren't able to do simply because of the very justified limitations of anonymous inodes. Moving pidfds to a tiny pseudo filesystem allows: * statx() on pidfds becomes useful for the first time. * pidfds can be compared simply via statx() and then comparing inode numbers. * pidfds have unique inode numbers for the system lifetime. * struct pid is now stashed in inode->i_private instead of file->private_data. This means it is now possible to introduce concepts that operate on a process once all file descriptors have been closed. A concrete example is kill-on-last-close. * file->private_data is freed up for per-file options for pidfds. * Each struct pid will refer to a different inode but the same struct pid will refer to the same inode if it's opened multiple times. In contrast to now where each struct pid refers to the same inode. Even if we were to move to anon_inode_create_getfile() which creates new inodes we'd still be associating the same struct pid with multiple different inodes. The tiny pseudo filesystem is not visible anywhere in userspace exactly like e.g., pipefs and sockfs. There's no lookup, there's no complex inode operations, nothing. Dentries and inodes are always deleted when the last pidfd is closed. We allocate a new inode for each struct pid and we reuse that inode for all pidfds. We use iget_locked() to find that inode again based on the inode number which isn't recycled. We allocate a new dentry for each pidfd that uses the same inode. That is similar to anonymous inodes which reuse the same inode for thousands of dentries. For pidfds we're talking way less than that. There usually won't be a lot of concurrent openers of the same struct pid. They can probably often be counted on two hands. I know that systemd does use separate pidfd for the same struct pid for various complex process tracking issues. So I think with that things actually become way simpler. Especially because we don't have to care about lookup. Dentries and inodes continue to be always deleted. The code is entirely optional and fairly small. If it's not selected we fallback to anonymous inodes. Heavily inspired by nsfs which uses a similar stashing mechanism just for namespaces. Link: https://lore.kernel.org/r/20240213-vfs-pidfd_fs-v1-2-f863f58cfce1@kernel.org Signed-off-by: Christian Brauner --- fs/Kconfig | 7 ++ fs/pidfs.c | 156 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/pid.h | 5 +- include/linux/pidfs.h | 8 +++ include/uapi/linux/magic.h | 1 + init/main.c | 2 + kernel/fork.c | 13 +--- kernel/nsproxy.c | 2 +- kernel/pid.c | 11 ++++ 9 files changed, 188 insertions(+), 17 deletions(-) create mode 100644 include/linux/pidfs.h (limited to 'include/uapi') diff --git a/fs/Kconfig b/fs/Kconfig index 89fdbefd1075..f3dbd84a0e40 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -174,6 +174,13 @@ source "fs/proc/Kconfig" source "fs/kernfs/Kconfig" source "fs/sysfs/Kconfig" +config FS_PID + bool "Pseudo filesystem for process file descriptors" + depends on 64BIT + default y + help + Pidfs implements advanced features for process file descriptors. + config TMPFS bool "Tmpfs virtual memory file system support (former shm fs)" depends on SHMEM diff --git a/fs/pidfs.c b/fs/pidfs.c index eccb291862a0..6c3f010074af 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include #include #include +#include #include #include #include @@ -14,10 +16,12 @@ static int pidfd_release(struct inode *inode, struct file *file) { +#ifndef CONFIG_FS_PID struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); +#endif return 0; } @@ -59,7 +63,7 @@ static int pidfd_release(struct inode *inode, struct file *file) */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { - struct pid *pid = f->private_data; + struct pid *pid = pidfd_pid(f); struct pid_namespace *ns; pid_t nr = -1; @@ -93,7 +97,7 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { - struct pid *pid = file->private_data; + struct pid *pid = pidfd_pid(file); bool thread = file->f_flags & PIDFD_THREAD; struct task_struct *task; __poll_t poll_flags = 0; @@ -113,10 +117,156 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) return poll_flags; } -const struct file_operations pidfd_fops = { +static const struct file_operations pidfs_file_operations = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; + +struct pid *pidfd_pid(const struct file *file) +{ + if (file->f_op != &pidfs_file_operations) + return ERR_PTR(-EBADF); +#ifdef CONFIG_FS_PID + return file_inode(file)->i_private; +#else + return file->private_data; +#endif +} + +#ifdef CONFIG_FS_PID +static struct vfsmount *pidfs_mnt __ro_after_init; +static struct super_block *pidfs_sb __ro_after_init; + +/* + * The vfs falls back to simple_setattr() if i_op->setattr() isn't + * implemented. Let's reject it completely until we have a clean + * permission concept for pidfds. + */ +static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EOPNOTSUPP; +} + +static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); + return 0; +} + +static const struct inode_operations pidfs_inode_operations = { + .getattr = pidfs_getattr, + .setattr = pidfs_setattr, +}; + +static void pidfs_evict_inode(struct inode *inode) +{ + struct pid *pid = inode->i_private; + + clear_inode(inode); + put_pid(pid); +} + +static const struct super_operations pidfs_sops = { + .drop_inode = generic_delete_inode, + .evict_inode = pidfs_evict_inode, + .statfs = simple_statfs, +}; + +static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) +{ + return dynamic_dname(buffer, buflen, "pidfd:[%lu]", + d_inode(dentry)->i_ino); +} + +static const struct dentry_operations pidfs_dentry_operations = { + .d_delete = always_delete_dentry, + .d_dname = pidfs_dname, +}; + +static int pidfs_init_fs_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, PID_FS_MAGIC); + if (!ctx) + return -ENOMEM; + + ctx->ops = &pidfs_sops; + ctx->dops = &pidfs_dentry_operations; + return 0; +} + +static struct file_system_type pidfs_type = { + .name = "pidfs", + .init_fs_context = pidfs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) +{ + + struct inode *inode; + struct file *pidfd_file; + + inode = iget_locked(pidfs_sb, pid->ino); + if (!inode) + return ERR_PTR(-ENOMEM); + + if (inode->i_state & I_NEW) { + /* + * Inode numbering for pidfs start at RESERVED_PIDS + 1. + * This avoids collisions with the root inode which is 1 + * for pseudo filesystems. + */ + inode->i_ino = pid->ino; + inode->i_mode = S_IFREG | S_IRUGO; + inode->i_op = &pidfs_inode_operations; + inode->i_fop = &pidfs_file_operations; + inode->i_flags |= S_IMMUTABLE; + inode->i_private = get_pid(pid); + simple_inode_init_ts(inode); + unlock_new_inode(inode); + } + + pidfd_file = alloc_file_pseudo(inode, pidfs_mnt, "", flags, + &pidfs_file_operations); + if (IS_ERR(pidfd_file)) + iput(inode); + + return pidfd_file; +} + +void __init pidfs_init(void) +{ + pidfs_mnt = kern_mount(&pidfs_type); + if (IS_ERR(pidfs_mnt)) + panic("Failed to mount pidfs pseudo filesystem"); + + pidfs_sb = pidfs_mnt->mnt_sb; +} + +#else /* !CONFIG_FS_PID */ + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) +{ + struct file *pidfd_file; + + pidfd_file = anon_inode_getfile("[pidfd]", &pidfs_file_operations, pid, + flags | O_RDWR); + if (IS_ERR(pidfd_file)) + return pidfd_file; + + get_pid(pid); + return pidfd_file; +} + +void __init pidfs_init(void) { } +#endif diff --git a/include/linux/pid.h b/include/linux/pid.h index 8124d57752b9..956481128e8d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -55,6 +55,9 @@ struct pid refcount_t count; unsigned int level; spinlock_t lock; +#ifdef CONFIG_FS_PID + unsigned long ino; +#endif /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; @@ -66,8 +69,6 @@ struct pid extern struct pid init_struct_pid; -extern const struct file_operations pidfd_fops; - struct file; struct pid *pidfd_pid(const struct file *file); diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h new file mode 100644 index 000000000000..75bdf9807802 --- /dev/null +++ b/include/linux/pidfs.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PID_FS_H +#define _LINUX_PID_FS_H + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); +void __init pidfs_init(void); + +#endif /* _LINUX_PID_FS_H */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 6325d1d0e90f..1b40a968ba91 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -101,5 +101,6 @@ #define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */ #define DEVMEM_MAGIC 0x454d444d /* "DMEM" */ #define SECRETMEM_MAGIC 0x5345434d /* "SECM" */ +#define PID_FS_MAGIC 0x50494446 /* "PIDF" */ #endif /* __LINUX_MAGIC_H__ */ diff --git a/init/main.c b/init/main.c index e24b0780fdff..2fbf6a3114d5 100644 --- a/init/main.c +++ b/init/main.c @@ -99,6 +99,7 @@ #include #include #include +#include #include #include @@ -1059,6 +1060,7 @@ void start_kernel(void) seq_file_init(); proc_root_init(); nsfs_init(); + pidfs_init(); cpuset_init(); cgroup_init(); taskstats_init_early(); diff --git a/kernel/fork.c b/kernel/fork.c index 662a61f340ce..2f839c290dcf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -102,6 +102,7 @@ #include #include #include +#include #include #include @@ -1985,14 +1986,6 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -struct pid *pidfd_pid(const struct file *file) -{ - if (file->f_op == &pidfd_fops) - return file->private_data; - - return ERR_PTR(-EBADF); -} - /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd @@ -2030,13 +2023,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re if (pidfd < 0) return pidfd; - pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, - flags | O_RDWR); + pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } - get_pid(pid); /* held by pidfd_file now */ /* * anon_inode_getfile() ignores everything outside of the * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 15781acaac1c..6ec3deec68c2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) if (proc_ns_file(f.file)) err = validate_ns(&nsset, ns); else - err = validate_nsset(&nsset, f.file->private_data); + err = validate_nsset(&nsset, pidfd_pid(f.file)); if (!err) { commit_nsset(&nsset); perf_event_namespaces(current); diff --git a/kernel/pid.c b/kernel/pid.c index c1d940fbd314..581cc34341fd 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -65,6 +66,13 @@ int pid_max = PID_MAX_DEFAULT; int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; +#ifdef CONFIG_FS_PID +/* + * Pseudo filesystems start inode numbering after one. We use Reserved + * PIDs as a natural offset. + */ +static u64 pidfs_ino = RESERVED_PIDS; +#endif /* * PID-map pages start out as NULL, they get allocated upon @@ -272,6 +280,9 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; +#ifdef CONFIG_FS_PID + pid->ino = ++pidfs_ino; +#endif for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); -- cgit v1.2.3 From 6ec429d5887a41b2dc8d92e391552f5604085cc2 Mon Sep 17 00:00:00 2001 From: Junxian Huang Date: Fri, 1 Mar 2024 18:48:45 +0800 Subject: RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity Currently, congestion control algorithm is statically configured in FW, and all QPs use the same algorithm(except UD which has a fixed configuration of DCQCN). This is not flexible enough. Support userspace configuring congestion control algorithm with QP granularity while creating QPs. If the algorithm is not specified in userspace, use the default one. Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20240301104845.1141083-1-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hns/hns_roce_device.h | 3 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 12 +----- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 3 +- drivers/infiniband/hw/hns/hns_roce_main.c | 3 ++ drivers/infiniband/hw/hns/hns_roce_qp.c | 60 +++++++++++++++++++++++++++++ include/uapi/rdma/hns-abi.h | 16 ++++++++ 6 files changed, 85 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 1d062c522d69..bc015901a7d3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -845,7 +845,8 @@ struct hns_roce_caps { u16 default_aeq_period; u16 default_aeq_arm_st; u16 default_ceq_arm_st; - enum hns_roce_cong_type cong_type; + u8 cong_cap; + enum hns_roce_cong_type default_cong_type; }; enum hns_roce_device_state { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 42e28586cefa..38e426f4afb5 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2209,11 +2209,12 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) caps->max_wqes = 1 << le16_to_cpu(resp_c->sq_depth); caps->num_srqs = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_SRQS); - caps->cong_type = hr_reg_read(resp_d, PF_CAPS_D_CONG_TYPE); + caps->cong_cap = hr_reg_read(resp_d, PF_CAPS_D_CONG_CAP); caps->max_srq_wrs = 1 << le16_to_cpu(resp_d->srq_depth); caps->ceqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_CEQ_DEPTH); caps->num_comp_vectors = hr_reg_read(resp_d, PF_CAPS_D_NUM_CEQS); caps->aeqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_AEQ_DEPTH); + caps->default_cong_type = hr_reg_read(resp_d, PF_CAPS_D_DEFAULT_ALG); caps->reserved_pds = hr_reg_read(resp_d, PF_CAPS_D_RSV_PDS); caps->num_uars = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_UARS); caps->reserved_qps = hr_reg_read(resp_d, PF_CAPS_D_RSV_QPS); @@ -4737,14 +4738,8 @@ enum { static int check_cong_type(struct ib_qp *ibqp, struct hns_roce_congestion_algorithm *cong_alg) { - struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); - if (ibqp->qp_type == IB_QPT_UD || ibqp->qp_type == IB_QPT_GSI) - hr_qp->cong_type = CONG_TYPE_DCQCN; - else - hr_qp->cong_type = hr_dev->caps.cong_type; - /* different congestion types match different configurations */ switch (hr_qp->cong_type) { case CONG_TYPE_DCQCN: @@ -4772,9 +4767,6 @@ static int check_cong_type(struct ib_qp *ibqp, cong_alg->wnd_mode_sel = WND_LIMIT; break; default: - ibdev_warn(&hr_dev->ib_dev, - "invalid type(%u) for congestion selection.\n", - hr_qp->cong_type); hr_qp->cong_type = CONG_TYPE_DCQCN; cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index cd97cbee682a..359a74672ba1 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -1214,12 +1214,13 @@ struct hns_roce_query_pf_caps_d { #define PF_CAPS_D_RQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(21, 20) #define PF_CAPS_D_EX_SGE_HOP_NUM PF_CAPS_D_FIELD_LOC(23, 22) #define PF_CAPS_D_SQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(25, 24) -#define PF_CAPS_D_CONG_TYPE PF_CAPS_D_FIELD_LOC(29, 26) +#define PF_CAPS_D_CONG_CAP PF_CAPS_D_FIELD_LOC(29, 26) #define PF_CAPS_D_CEQ_DEPTH PF_CAPS_D_FIELD_LOC(85, 64) #define PF_CAPS_D_NUM_CEQS PF_CAPS_D_FIELD_LOC(95, 86) #define PF_CAPS_D_AEQ_DEPTH PF_CAPS_D_FIELD_LOC(117, 96) #define PF_CAPS_D_AEQ_ARM_ST PF_CAPS_D_FIELD_LOC(119, 118) #define PF_CAPS_D_CEQ_ARM_ST PF_CAPS_D_FIELD_LOC(121, 120) +#define PF_CAPS_D_DEFAULT_ALG PF_CAPS_D_FIELD_LOC(127, 122) #define PF_CAPS_D_RSV_PDS PF_CAPS_D_FIELD_LOC(147, 128) #define PF_CAPS_D_NUM_UARS PF_CAPS_D_FIELD_LOC(155, 148) #define PF_CAPS_D_RSV_QPS PF_CAPS_D_FIELD_LOC(179, 160) diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index b55fe6911f9f..1dc60c2b2b7a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -394,6 +394,9 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx, resp.config |= HNS_ROCE_RSP_CQE_INLINE_FLAGS; } + if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) + resp.congest_type = hr_dev->caps.cong_cap; + ret = hns_roce_uar_alloc(hr_dev, &context->uar); if (ret) goto error_out; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 31b147210688..f35a66325d9a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -1004,6 +1004,60 @@ static void free_kernel_wrid(struct hns_roce_qp *hr_qp) kfree(hr_qp->sq.wrid); } +static void default_congest_type(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp) +{ + if (hr_qp->ibqp.qp_type == IB_QPT_UD || + hr_qp->ibqp.qp_type == IB_QPT_GSI) + hr_qp->cong_type = CONG_TYPE_DCQCN; + else + hr_qp->cong_type = hr_dev->caps.default_cong_type; +} + +static int set_congest_type(struct hns_roce_qp *hr_qp, + struct hns_roce_ib_create_qp *ucmd) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(hr_qp->ibqp.device); + + switch (ucmd->cong_type_flags) { + case HNS_ROCE_CREATE_QP_FLAGS_DCQCN: + hr_qp->cong_type = CONG_TYPE_DCQCN; + break; + case HNS_ROCE_CREATE_QP_FLAGS_LDCP: + hr_qp->cong_type = CONG_TYPE_LDCP; + break; + case HNS_ROCE_CREATE_QP_FLAGS_HC3: + hr_qp->cong_type = CONG_TYPE_HC3; + break; + case HNS_ROCE_CREATE_QP_FLAGS_DIP: + hr_qp->cong_type = CONG_TYPE_DIP; + break; + default: + return -EINVAL; + } + + if (!test_bit(hr_qp->cong_type, (unsigned long *)&hr_dev->caps.cong_cap)) + return -EOPNOTSUPP; + + if (hr_qp->ibqp.qp_type == IB_QPT_UD && + hr_qp->cong_type != CONG_TYPE_DCQCN) + return -EOPNOTSUPP; + + return 0; +} + +static int set_congest_param(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp, + struct hns_roce_ib_create_qp *ucmd) +{ + if (ucmd->comp_mask & HNS_ROCE_CREATE_QP_MASK_CONGEST_TYPE) + return set_congest_type(hr_qp, ucmd); + + default_congest_type(hr_dev, hr_qp); + + return 0; +} + static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, struct ib_qp_init_attr *init_attr, struct ib_udata *udata, @@ -1043,6 +1097,10 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, ibdev_err(ibdev, "failed to set user SQ size, ret = %d.\n", ret); + + ret = set_congest_param(hr_dev, hr_qp, ucmd); + if (ret) + return ret; } else { if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) hr_qp->config = HNS_ROCE_EXSGE_FLAGS; @@ -1051,6 +1109,8 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, ibdev_err(ibdev, "failed to set kernel SQ size, ret = %d.\n", ret); + + default_congest_type(hr_dev, hr_qp); } return ret; diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index c996e151081e..158670da2b2a 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -73,6 +73,17 @@ struct hns_roce_ib_create_srq_resp { __u32 cap_flags; /* Use enum hns_roce_srq_cap_flags */ }; +enum hns_roce_congest_type_flags { + HNS_ROCE_CREATE_QP_FLAGS_DCQCN, + HNS_ROCE_CREATE_QP_FLAGS_LDCP, + HNS_ROCE_CREATE_QP_FLAGS_HC3, + HNS_ROCE_CREATE_QP_FLAGS_DIP, +}; + +enum hns_roce_create_qp_comp_mask { + HNS_ROCE_CREATE_QP_MASK_CONGEST_TYPE = 1 << 0, +}; + struct hns_roce_ib_create_qp { __aligned_u64 buf_addr; __aligned_u64 db_addr; @@ -81,6 +92,9 @@ struct hns_roce_ib_create_qp { __u8 sq_no_prefetch; __u8 reserved[5]; __aligned_u64 sdb_addr; + __aligned_u64 comp_mask; /* Use enum hns_roce_create_qp_comp_mask */ + __aligned_u64 create_flags; + __aligned_u64 cong_type_flags; }; enum hns_roce_qp_cap_flags { @@ -114,6 +128,8 @@ struct hns_roce_ib_alloc_ucontext_resp { __u32 reserved; __u32 config; __u32 max_inline_data; + __u8 congest_type; + __u8 reserved0[7]; }; struct hns_roce_ib_alloc_ucontext { -- cgit v1.2.3 From 44350256ab943d424d70aa60a34f45060b3a36e8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 11 Sep 2023 17:09:27 +0300 Subject: fuse: implement ioctls to manage backing files FUSE server calls the FUSE_DEV_IOC_BACKING_OPEN ioctl with a backing file descriptor. If the call succeeds, a backing file identifier is returned. A later change will be using this backing file id in a reply to OPEN request with the flag FOPEN_PASSTHROUGH to setup passthrough of file operations on the open FUSE file to the backing file. The FUSE server should call FUSE_DEV_IOC_BACKING_CLOSE ioctl to close the backing file by its id. This can be done at any time, but if an open reply with FOPEN_PASSTHROUGH flag is still in progress, the open may fail if the backing file is closed before the fuse file was opened. Setting up backing files requires a server with CAP_SYS_ADMIN privileges. For the backing file to be successfully setup, the backing file must implement both read_iter and write_iter file operations. The limitation on the level of filesystem stacking allowed for the backing file is enforced before setting up the backing file. Signed-off-by: Alessio Balsini Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 41 ++++++++++++++ fs/fuse/fuse_i.h | 10 ++++ fs/fuse/inode.c | 5 ++ fs/fuse/passthrough.c | 136 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fuse.h | 9 +++ 5 files changed, 201 insertions(+) (limited to 'include/uapi') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index eba68b57bd7c..5a5fb56deb92 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2283,6 +2283,41 @@ static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp) return res; } +static long fuse_dev_ioctl_backing_open(struct file *file, + struct fuse_backing_map __user *argp) +{ + struct fuse_dev *fud = fuse_get_dev(file); + struct fuse_backing_map map; + + if (!fud) + return -EPERM; + + if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + return -EOPNOTSUPP; + + if (copy_from_user(&map, argp, sizeof(map))) + return -EFAULT; + + return fuse_backing_open(fud->fc, &map); +} + +static long fuse_dev_ioctl_backing_close(struct file *file, __u32 __user *argp) +{ + struct fuse_dev *fud = fuse_get_dev(file); + int backing_id; + + if (!fud) + return -EPERM; + + if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + return -EOPNOTSUPP; + + if (get_user(backing_id, argp)) + return -EFAULT; + + return fuse_backing_close(fud->fc, backing_id); +} + static long fuse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2292,6 +2327,12 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, case FUSE_DEV_IOC_CLONE: return fuse_dev_ioctl_clone(file, argp); + case FUSE_DEV_IOC_BACKING_OPEN: + return fuse_dev_ioctl_backing_open(file, argp); + + case FUSE_DEV_IOC_BACKING_CLOSE: + return fuse_dev_ioctl_backing_close(file, argp); + default: return -ENOTTY; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 19a86acc9dd0..4f1681650f57 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -79,6 +79,7 @@ struct fuse_submount_lookup { /** Container for data related to mapping to backing file */ struct fuse_backing { struct file *file; + struct cred *cred; /** refcount */ refcount_t count; @@ -897,6 +898,11 @@ struct fuse_conn { /* New writepages go into this bucket */ struct fuse_sync_bucket __rcu *curr_bucket; + +#ifdef CONFIG_FUSE_PASSTHROUGH + /** IDR for backing files ids */ + struct idr backing_files_map; +#endif }; /* @@ -1409,5 +1415,9 @@ static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi, struct fuse_backing *fuse_backing_get(struct fuse_backing *fb); void fuse_backing_put(struct fuse_backing *fb); +void fuse_backing_files_init(struct fuse_conn *fc); +void fuse_backing_files_free(struct fuse_conn *fc); +int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map); +int fuse_backing_close(struct fuse_conn *fc, int backing_id); #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index c771bd3c1336..0186df5fc9ea 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -930,6 +930,9 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; fc->max_pages_limit = FUSE_MAX_MAX_PAGES; + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + fuse_backing_files_init(fc); + INIT_LIST_HEAD(&fc->mounts); list_add(&fm->fc_entry, &fc->mounts); fm->fc = fc; @@ -953,6 +956,8 @@ void fuse_conn_put(struct fuse_conn *fc) WARN_ON(atomic_read(&bucket->count) != 1); kfree(bucket); } + if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) + fuse_backing_files_free(fc); fc->release(fc); } } diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c index e8639c0a9ac6..7ec92a54c2e0 100644 --- a/fs/fuse/passthrough.c +++ b/fs/fuse/passthrough.c @@ -18,8 +18,11 @@ struct fuse_backing *fuse_backing_get(struct fuse_backing *fb) static void fuse_backing_free(struct fuse_backing *fb) { + pr_debug("%s: fb=0x%p\n", __func__, fb); + if (fb->file) fput(fb->file); + put_cred(fb->cred); kfree_rcu(fb, rcu); } @@ -28,3 +31,136 @@ void fuse_backing_put(struct fuse_backing *fb) if (fb && refcount_dec_and_test(&fb->count)) fuse_backing_free(fb); } + +void fuse_backing_files_init(struct fuse_conn *fc) +{ + idr_init(&fc->backing_files_map); +} + +static int fuse_backing_id_alloc(struct fuse_conn *fc, struct fuse_backing *fb) +{ + int id; + + idr_preload(GFP_KERNEL); + spin_lock(&fc->lock); + /* FIXME: xarray might be space inefficient */ + id = idr_alloc_cyclic(&fc->backing_files_map, fb, 1, 0, GFP_ATOMIC); + spin_unlock(&fc->lock); + idr_preload_end(); + + WARN_ON_ONCE(id == 0); + return id; +} + +static struct fuse_backing *fuse_backing_id_remove(struct fuse_conn *fc, + int id) +{ + struct fuse_backing *fb; + + spin_lock(&fc->lock); + fb = idr_remove(&fc->backing_files_map, id); + spin_unlock(&fc->lock); + + return fb; +} + +static int fuse_backing_id_free(int id, void *p, void *data) +{ + struct fuse_backing *fb = p; + + WARN_ON_ONCE(refcount_read(&fb->count) != 1); + fuse_backing_free(fb); + return 0; +} + +void fuse_backing_files_free(struct fuse_conn *fc) +{ + idr_for_each(&fc->backing_files_map, fuse_backing_id_free, NULL); + idr_destroy(&fc->backing_files_map); +} + +int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map) +{ + struct file *file; + struct super_block *backing_sb; + struct fuse_backing *fb = NULL; + int res; + + pr_debug("%s: fd=%d flags=0x%x\n", __func__, map->fd, map->flags); + + /* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */ + res = -EPERM; + if (!fc->passthrough || !capable(CAP_SYS_ADMIN)) + goto out; + + res = -EINVAL; + if (map->flags) + goto out; + + file = fget(map->fd); + res = -EBADF; + if (!file) + goto out; + + res = -EOPNOTSUPP; + if (!file->f_op->read_iter || !file->f_op->write_iter) + goto out_fput; + + backing_sb = file_inode(file)->i_sb; + res = -ELOOP; + if (backing_sb->s_stack_depth >= fc->max_stack_depth) + goto out_fput; + + fb = kmalloc(sizeof(struct fuse_backing), GFP_KERNEL); + res = -ENOMEM; + if (!fb) + goto out_fput; + + fb->file = file; + fb->cred = prepare_creds(); + refcount_set(&fb->count, 1); + + res = fuse_backing_id_alloc(fc, fb); + if (res < 0) { + fuse_backing_free(fb); + fb = NULL; + } + +out: + pr_debug("%s: fb=0x%p, ret=%i\n", __func__, fb, res); + + return res; + +out_fput: + fput(file); + goto out; +} + +int fuse_backing_close(struct fuse_conn *fc, int backing_id) +{ + struct fuse_backing *fb = NULL; + int err; + + pr_debug("%s: backing_id=%d\n", __func__, backing_id); + + /* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */ + err = -EPERM; + if (!fc->passthrough || !capable(CAP_SYS_ADMIN)) + goto out; + + err = -EINVAL; + if (backing_id <= 0) + goto out; + + err = -ENOENT; + fb = fuse_backing_id_remove(fc, backing_id); + if (!fb) + goto out; + + fuse_backing_put(fb); + err = 0; +out: + pr_debug("%s: fb=0x%p, err=%i\n", __func__, fb, err); + + return err; +} diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 7bb6219cfda0..1162a47b6a42 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -1057,9 +1057,18 @@ struct fuse_notify_retrieve_in { uint64_t dummy4; }; +struct fuse_backing_map { + int32_t fd; + uint32_t flags; + uint64_t padding; +}; + /* Device ioctls: */ #define FUSE_DEV_IOC_MAGIC 229 #define FUSE_DEV_IOC_CLONE _IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t) +#define FUSE_DEV_IOC_BACKING_OPEN _IOW(FUSE_DEV_IOC_MAGIC, 1, \ + struct fuse_backing_map) +#define FUSE_DEV_IOC_BACKING_CLOSE _IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t) struct fuse_lseek_in { uint64_t fh; -- cgit v1.2.3 From 460be1d527a8e296d85301e8b14923299508d4fc Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Tue, 5 Mar 2024 14:38:53 +0100 Subject: drm/nouveau: move more missing UAPI bits Those are already de-facto UAPI, so let's just move it into the uapi header. Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Reviewed-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240305133853.2214268-2-kherbst@redhat.com --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 20 +++++++++++++++----- drivers/gpu/drm/nouveau/nouveau_abi16.h | 12 ------------ include/uapi/drm/nouveau_drm.h | 22 ++++++++++++++++++++++ 3 files changed, 37 insertions(+), 17 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index cd14f993bdd1..92f9127b284a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -312,11 +312,21 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) { if (init->fb_ctxdma_handle == ~0) { switch (init->tt_ctxdma_handle) { - case 0x01: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR ; break; - case 0x02: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPDEC; break; - case 0x04: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPPP ; break; - case 0x08: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSVLD ; break; - case 0x30: engine = NV_DEVICE_HOST_RUNLIST_ENGINES_CE ; break; + case NOUVEAU_FIFO_ENGINE_GR: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR; + break; + case NOUVEAU_FIFO_ENGINE_VP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPDEC; + break; + case NOUVEAU_FIFO_ENGINE_PPP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSPPP; + break; + case NOUVEAU_FIFO_ENGINE_BSP: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_MSVLD; + break; + case NOUVEAU_FIFO_ENGINE_CE: + engine = NV_DEVICE_HOST_RUNLIST_ENGINES_CE; + break; default: return nouveau_abi16_put(abi16, -ENOSYS); } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h index 11c8c4a80079..661b901d8ecc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.h +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h @@ -50,18 +50,6 @@ struct drm_nouveau_grobj_alloc { int class; }; -struct drm_nouveau_notifierobj_alloc { - uint32_t channel; - uint32_t handle; - uint32_t size; - uint32_t offset; -}; - -struct drm_nouveau_gpuobj_free { - int channel; - uint32_t handle; -}; - struct drm_nouveau_setparam { uint64_t param; uint64_t value; diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index cd84227f1b42..8ad8d1cd1566 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -73,6 +73,16 @@ struct drm_nouveau_getparam { __u64 value; }; +/* + * Those are used to support selecting the main engine used on Kepler. + * This goes into drm_nouveau_channel_alloc::tt_ctxdma_handle + */ +#define NOUVEAU_FIFO_ENGINE_GR 0x01 +#define NOUVEAU_FIFO_ENGINE_VP 0x02 +#define NOUVEAU_FIFO_ENGINE_PPP 0x04 +#define NOUVEAU_FIFO_ENGINE_BSP 0x08 +#define NOUVEAU_FIFO_ENGINE_CE 0x30 + struct drm_nouveau_channel_alloc { __u32 fb_ctxdma_handle; __u32 tt_ctxdma_handle; @@ -95,6 +105,18 @@ struct drm_nouveau_channel_free { __s32 channel; }; +struct drm_nouveau_notifierobj_alloc { + __u32 channel; + __u32 handle; + __u32 size; + __u32 offset; +}; + +struct drm_nouveau_gpuobj_free { + __s32 channel; + __u32 handle; +}; + #define NOUVEAU_GEM_DOMAIN_CPU (1 << 0) #define NOUVEAU_GEM_DOMAIN_VRAM (1 << 1) #define NOUVEAU_GEM_DOMAIN_GART (1 << 2) -- cgit v1.2.3 From 86211eea8ae1676cc819d2b4fdc8d995394be07d Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 27 Feb 2024 13:45:35 +1030 Subject: btrfs: qgroup: validate btrfs_qgroup_inherit parameter [BUG] Currently btrfs can create subvolume with an invalid qgroup inherit without triggering any error: # mkfs.btrfs -O quota -f $dev # mount $dev $mnt # btrfs subvolume create -i 2/0 $mnt/subv1 # btrfs qgroup show -prce --sync $mnt Qgroupid Referenced Exclusive Path -------- ---------- --------- ---- 0/5 16.00KiB 16.00KiB 0/256 16.00KiB 16.00KiB subv1 [CAUSE] We only do a very basic size check for btrfs_qgroup_inherit structure, but never really verify if the values are correct. Thus in btrfs_qgroup_inherit() function, we have to skip non-existing qgroups, and never return any error. [FIX] Fix the behavior and introduce extra checks: - Introduce early check for btrfs_qgroup_inherit structure Not only the size, but also all the qgroup ids would be verified. And the timing is very early, so we can return error early. This early check is very important for snapshot creation, as snapshot is delayed to transaction commit. - Drop support for btrfs_qgroup_inherit::num_ref_copies and num_excl_copies Those two members are used to specify to copy refr/excl numbers from other qgroups. This would definitely mark qgroup inconsistent, and btrfs-progs has dropped the support for them for a long time. It's time to drop the support for kernel. - Verify the supported btrfs_qgroup_inherit::flags Just in case we want to add extra flags for btrfs_qgroup_inherit. Now above subvolume creation would fail with -ENOENT other than silently ignore the non-existing qgroup. CC: stable@vger.kernel.org # 6.7+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 16 +++------------ fs/btrfs/qgroup.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/qgroup.h | 3 +++ include/uapi/linux/btrfs.h | 1 + 4 files changed, 58 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 29e2b8e23363..38459a89b27c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1382,7 +1382,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - u64 nums; + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); if (vol_args->size < sizeof(*inherit) || vol_args->size > PAGE_SIZE) { @@ -1395,19 +1395,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, goto free_args; } - if (inherit->num_qgroups > PAGE_SIZE || - inherit->num_ref_copies > PAGE_SIZE || - inherit->num_excl_copies > PAGE_SIZE) { - ret = -EINVAL; - goto free_inherit; - } - - nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + - 2 * inherit->num_excl_copies; - if (vol_args->size != struct_size(inherit, qgroups, nums)) { - ret = -EINVAL; + ret = btrfs_qgroup_check_inherit(fs_info, inherit, vol_args->size); + if (ret < 0) goto free_inherit; - } } ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index b3bf08fc2a39..af241aaa654a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3046,6 +3046,57 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) return ret; } +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size) +{ + if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP) + return -EOPNOTSUPP; + if (size < sizeof(*inherit) || size > PAGE_SIZE) + return -EINVAL; + + /* + * In the past we allowed btrfs_qgroup_inherit to specify to copy + * rfer/excl numbers directly from other qgroups. This behavior has + * been disabled in userspace for a very long time, but here we should + * also disable it in kernel, as this behavior is known to mark qgroup + * inconsistent, and a rescan would wipe out the changes anyway. + * + * Reject any btrfs_qgroup_inherit with num_ref_copies or num_excl_copies. + */ + if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0) + return -EINVAL; + + if (inherit->num_qgroups > PAGE_SIZE) + return -EINVAL; + + if (size != struct_size(inherit, qgroups, inherit->num_qgroups)) + return -EINVAL; + + /* + * Now check all the remaining qgroups, they should all: + * + * - Exist + * - Be higher level qgroups. + */ + for (int i = 0; i < inherit->num_qgroups; i++) { + struct btrfs_qgroup *qgroup; + u64 qgroupid = inherit->qgroups[i]; + + if (btrfs_qgroup_level(qgroupid) == 0) + return -EINVAL; + + spin_lock(&fs_info->qgroup_lock); + qgroup = find_qgroup_rb(fs_info, qgroupid); + if (!qgroup) { + spin_unlock(&fs_info->qgroup_lock); + return -ENOENT; + } + spin_unlock(&fs_info->qgroup_lock); + } + return 0; +} + static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info, u64 inode_rootid, struct btrfs_qgroup_inherit **inherit) diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 1f664261c064..706640be0ec2 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -350,6 +350,9 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, struct ulist *new_roots); int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans); int btrfs_run_qgroups(struct btrfs_trans_handle *trans); +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size); int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, u64 objectid, u64 inode_rootid, struct btrfs_qgroup_inherit *inherit); diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index f8bc34a6bcfa..cdf6ad872149 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -92,6 +92,7 @@ struct btrfs_qgroup_limit { * struct btrfs_qgroup_inherit.flags */ #define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0) +#define BTRFS_QGROUP_INHERIT_FLAGS_SUPP (BTRFS_QGROUP_INHERIT_SET_LIMITS) struct btrfs_qgroup_inherit { __u64 flags; -- cgit v1.2.3 From e022f6a1c711ab6d76e9e59dce77e2b25df75076 Mon Sep 17 00:00:00 2001 From: Jingbo Xu Date: Mon, 26 Feb 2024 11:54:35 +0800 Subject: fuse: add support for explicit export disabling open_by_handle_at(2) can fail with -ESTALE with a valid handle returned by a previous name_to_handle_at(2) for evicted fuse inodes, which is especially common when entry_valid_timeout is 0, e.g. when the fuse daemon is in "cache=none" mode. The time sequence is like: name_to_handle_at(2) # succeed evict fuse inode open_by_handle_at(2) # fail The root cause is that, with 0 entry_valid_timeout, the dput() called in name_to_handle_at(2) will trigger iput -> evict(), which will send FUSE_FORGET to the daemon. The following open_by_handle_at(2) will send a new FUSE_LOOKUP request upon inode cache miss since the previous inode eviction. Then the fuse daemon may fail the FUSE_LOOKUP request with -ENOENT as the cached metadata of the requested inode has already been cleaned up during the previous FUSE_FORGET. The returned -ENOENT is treated as -ESTALE when open_by_handle_at(2) returns. This confuses the application somehow, as open_by_handle_at(2) fails when the previous name_to_handle_at(2) succeeds. The returned errno is also confusing as the requested file is not deleted and already there. It is reasonable to fail name_to_handle_at(2) early in this case, after which the application can fallback to open(2) to access files. Since this issue typically appears when entry_valid_timeout is 0 which is configured by the fuse daemon, the fuse daemon is the right person to explicitly disable the export when required. Also considering FUSE_EXPORT_SUPPORT actually indicates the support for lookups of "." and "..", and there are existing fuse daemons supporting export without FUSE_EXPORT_SUPPORT set, for compatibility, we add a new INIT flag for such purpose. Reviewed-by: Amir Goldstein Signed-off-by: Jingbo Xu Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 11 ++++++++++- include/uapi/linux/fuse.h | 3 +++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4829e667f9ad..ca5fad57bfa4 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1124,6 +1124,11 @@ static struct dentry *fuse_get_parent(struct dentry *child) return parent; } +/* only for fid encoding; no support for file handle */ +static const struct export_operations fuse_export_fid_operations = { + .encode_fh = fuse_encode_fh, +}; + static const struct export_operations fuse_export_operations = { .fh_to_dentry = fuse_fh_to_dentry, .fh_to_parent = fuse_fh_to_parent, @@ -1316,6 +1321,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->max_stack_depth = arg->max_stack_depth; fm->sb->s_stack_depth = arg->max_stack_depth; } + if (flags & FUSE_NO_EXPORT_SUPPORT) + fm->sb->s_export_op = &fuse_export_fid_operations; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1362,7 +1369,8 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | + FUSE_NO_EXPORT_SUPPORT; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; @@ -1561,6 +1569,7 @@ static int fuse_fill_super_submount(struct super_block *sb, sb->s_bdi = bdi_get(parent_sb->s_bdi); sb->s_xattr = parent_sb->s_xattr; + sb->s_export_op = parent_sb->s_export_op; sb->s_time_gran = parent_sb->s_time_gran; sb->s_blocksize = parent_sb->s_blocksize; sb->s_blocksize_bits = parent_sb->s_blocksize_bits; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 1162a47b6a42..a86c2cad65ad 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -215,6 +215,7 @@ * 7.40 * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag + * - add FUSE_NO_EXPORT_SUPPORT init flag */ #ifndef _LINUX_FUSE_H @@ -416,6 +417,7 @@ struct fuse_file_lock { * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. + * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -456,6 +458,7 @@ struct fuse_file_lock { #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) #define FUSE_PASSTHROUGH (1ULL << 37) +#define FUSE_NO_EXPORT_SUPPORT (1ULL << 38) /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP -- cgit v1.2.3 From 760eac73f9f69aa28fcb3050b4946c2dcc656d12 Mon Sep 17 00:00:00 2001 From: Zhao Chen Date: Tue, 9 Jan 2024 17:24:42 +0800 Subject: fuse: Introduce a new notification type for resend pending requests When a FUSE daemon panics and failover, we aim to minimize the impact on applications by reusing the existing FUSE connection. During this process, another daemon is employed to preserve the FUSE connection's file descriptor. The new started FUSE Daemon will takeover the fd and continue to provide service. However, it is possible for some inflight requests to be lost and never returned. As a result, applications awaiting replies would become stuck forever. To address this, we can resend these pending requests to the new started FUSE daemon. This patch introduces a new notification type "FUSE_NOTIFY_RESEND", which can trigger resending of the pending requests, ensuring they are properly processed again. Signed-off-by: Zhao Chen Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fuse.h | 2 ++ 2 files changed, 58 insertions(+) (limited to 'include/uapi') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 5a5fb56deb92..3c15a6b7f6f2 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1775,6 +1775,59 @@ copy_finish: return err; } +/* + * Resending all processing queue requests. + * + * During a FUSE daemon panics and failover, it is possible for some inflight + * requests to be lost and never returned. As a result, applications awaiting + * replies would become stuck forever. To address this, we can use notification + * to trigger resending of these pending requests to the FUSE daemon, ensuring + * they are properly processed again. + * + * Please note that this strategy is applicable only to idempotent requests or + * if the FUSE daemon takes careful measures to avoid processing duplicated + * non-idempotent requests. + */ +static void fuse_resend(struct fuse_conn *fc) +{ + struct fuse_dev *fud; + struct fuse_req *req, *next; + struct fuse_iqueue *fiq = &fc->iq; + LIST_HEAD(to_queue); + unsigned int i; + + spin_lock(&fc->lock); + if (!fc->connected) { + spin_unlock(&fc->lock); + return; + } + + list_for_each_entry(fud, &fc->devices, entry) { + struct fuse_pqueue *fpq = &fud->pq; + + spin_lock(&fpq->lock); + for (i = 0; i < FUSE_PQ_HASH_SIZE; i++) + list_splice_tail_init(&fpq->processing[i], &to_queue); + spin_unlock(&fpq->lock); + } + spin_unlock(&fc->lock); + + list_for_each_entry_safe(req, next, &to_queue, list) { + __set_bit(FR_PENDING, &req->flags); + } + + spin_lock(&fiq->lock); + /* iq and pq requests are both oldest to newest */ + list_splice(&to_queue, &fiq->pending); + fiq->ops->wake_pending_and_unlock(fiq); +} + +static int fuse_notify_resend(struct fuse_conn *fc) +{ + fuse_resend(fc); + return 0; +} + static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { @@ -1800,6 +1853,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, case FUSE_NOTIFY_DELETE: return fuse_notify_delete(fc, size, cs); + case FUSE_NOTIFY_RESEND: + return fuse_notify_resend(fc); + default: fuse_copy_finish(cs); return -EINVAL; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index a86c2cad65ad..659932eb35e1 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -216,6 +216,7 @@ * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag * - add FUSE_NO_EXPORT_SUPPORT init flag + * - add FUSE_NOTIFY_RESEND */ #ifndef _LINUX_FUSE_H @@ -645,6 +646,7 @@ enum fuse_notify_code { FUSE_NOTIFY_STORE = 4, FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_DELETE = 6, + FUSE_NOTIFY_RESEND = 7, FUSE_NOTIFY_CODE_MAX, }; -- cgit v1.2.3 From 9e7f5296f475ba5ab887ae3e55b922e17e99752b Mon Sep 17 00:00:00 2001 From: Zhao Chen Date: Tue, 9 Jan 2024 17:24:43 +0800 Subject: fuse: Use the high bit of request ID for indicating resend requests Some FUSE daemons want to know if the received request is a resend request. The high bit of the fuse request ID is utilized for indicating this, enabling the receiver to perform appropriate handling. The init flag "FUSE_HAS_RESEND" is added to indicate this feature. Signed-off-by: Zhao Chen Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 2 ++ fs/fuse/inode.c | 2 +- include/uapi/linux/fuse.h | 13 ++++++++++++- 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 3c15a6b7f6f2..3ec8bb5e68ff 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1814,6 +1814,8 @@ static void fuse_resend(struct fuse_conn *fc) list_for_each_entry_safe(req, next, &to_queue, list) { __set_bit(FR_PENDING, &req->flags); + /* mark the request as resend request */ + req->in.h.unique |= FUSE_UNIQUE_RESEND; } spin_lock(&fiq->lock); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ca5fad57bfa4..02869edf72f3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1370,7 +1370,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | - FUSE_NO_EXPORT_SUPPORT; + FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 659932eb35e1..d08b99d60f6f 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -216,7 +216,7 @@ * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag * - add FUSE_NO_EXPORT_SUPPORT init flag - * - add FUSE_NOTIFY_RESEND + * - add FUSE_NOTIFY_RESEND, add FUSE_HAS_RESEND init flag */ #ifndef _LINUX_FUSE_H @@ -419,6 +419,8 @@ struct fuse_file_lock { * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support + * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit + * of the request ID indicates resend requests */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -460,6 +462,7 @@ struct fuse_file_lock { #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) #define FUSE_PASSTHROUGH (1ULL << 37) #define FUSE_NO_EXPORT_SUPPORT (1ULL << 38) +#define FUSE_HAS_RESEND (1ULL << 39) /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP @@ -973,6 +976,14 @@ struct fuse_fallocate_in { uint32_t padding; }; +/** + * FUSE request unique ID flag + * + * Indicates whether this is a resend request. The receiver should handle this + * request accordingly. + */ +#define FUSE_UNIQUE_RESEND (1ULL << 63) + struct fuse_in_header { uint32_t len; uint32_t opcode; -- cgit v1.2.3 From e225555028bd3671ad6f4ce72405a95d62e17371 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Tue, 5 Mar 2024 18:08:26 -0800 Subject: inotify: Fix misspelling of "writable" Several file system notification system headers have "writable" misspelled as "writtable" in the comments. This patch fixes it in the inotify header. Signed-off-by: Vicki Pfau Signed-off-by: Jan Kara Message-Id: <20240306020831.1404033-1-vi@endrift.com> --- include/uapi/linux/inotify.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/inotify.h b/include/uapi/linux/inotify.h index b3e165853d5b..d94f20e38e5d 100644 --- a/include/uapi/linux/inotify.h +++ b/include/uapi/linux/inotify.h @@ -30,8 +30,8 @@ struct inotify_event { #define IN_ACCESS 0x00000001 /* File was accessed */ #define IN_MODIFY 0x00000002 /* File was modified */ #define IN_ATTRIB 0x00000004 /* Metadata changed */ -#define IN_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ -#define IN_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ +#define IN_CLOSE_WRITE 0x00000008 /* Writable file was closed */ +#define IN_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define IN_OPEN 0x00000020 /* File was opened */ #define IN_MOVED_FROM 0x00000040 /* File was moved from X */ #define IN_MOVED_TO 0x00000080 /* File was moved to Y */ -- cgit v1.2.3 From 8c2c2549fb32f2e6dd247cfed2e23cf8456dd458 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Tue, 5 Mar 2024 18:08:28 -0800 Subject: fanotify: Fix misspelling of "writable" Several file system notification system headers have "writable" misspelled as "writtable" in the comments. This patch fixes it in the fanotify header. Signed-off-by: Vicki Pfau Signed-off-by: Jan Kara Message-Id: <20240306020831.1404033-3-vi@endrift.com> --- include/uapi/linux/fanotify.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index cd14c94e9a1e..a37de58ca571 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -8,8 +8,8 @@ #define FAN_ACCESS 0x00000001 /* File was accessed */ #define FAN_MODIFY 0x00000002 /* File was modified */ #define FAN_ATTRIB 0x00000004 /* Metadata changed */ -#define FAN_CLOSE_WRITE 0x00000008 /* Writtable file closed */ -#define FAN_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ +#define FAN_CLOSE_WRITE 0x00000008 /* Writable file closed */ +#define FAN_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FAN_OPEN 0x00000020 /* File was opened */ #define FAN_MOVED_FROM 0x00000040 /* File was moved from X */ #define FAN_MOVED_TO 0x00000080 /* File was moved to Y */ -- cgit v1.2.3 From 0ed3bba16d37618c7776a44ef02ad3039966d687 Mon Sep 17 00:00:00 2001 From: Takeru Hayasaka Date: Mon, 12 Feb 2024 02:04:03 +0000 Subject: ethtool: Add GTP RSS hash options to ethtool.h This is a patch that enables RSS functionality for GTP packets using ethtool. A user can include TEID and make RSS work for GTP-U over IPv4 by doing the following:`ethtool -N ens3 rx-flow-hash gtpu4 sde` In addition to gtpu(4|6), we now support gtpc(4|6),gtpc(4|6)t,gtpu(4|6)e, gtpu(4|6)u, and gtpu(4|6)d. gtpc(4|6): Used for GTP-C in IPv4 and IPv6, where the GTP header format does not include a TEID. gtpc(4|6)t: Used for GTP-C in IPv4 and IPv6, with a GTP header format that includes a TEID. gtpu(4|6): Used for GTP-U in both IPv4 and IPv6 scenarios. gtpu(4|6)e: Used for GTP-U with extended headers in both IPv4 and IPv6. gtpu(4|6)u: Used when the PSC (PDU session container) in the GTP-U extended header includes Uplink, applicable to both IPv4 and IPv6. gtpu(4|6)d: Used when the PSC in the GTP-U extended header includes Downlink, for both IPv4 and IPv6. GTP generates a flow that includes an ID called TEID to identify the tunnel. This tunnel is created for each UE (User Equipment).By performing RSS based on this flow, it is possible to apply RSS for each communication unit from the UE. Without this, RSS would only be effective within the range of IP addresses. For instance, the PGW can only perform RSS within the IP range of the SGW. Problematic from a load distribution perspective, especially if there's a bias in the terminals connected to a particular base station.This case can be solved by using this patch. Signed-off-by: Takeru Hayasaka Reviewed-by: Marcin Szycik Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- include/uapi/linux/ethtool.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 06ef6b78b7de..11fc18988bc2 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2023,6 +2023,53 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define IPV4_FLOW 0x10 /* hash only */ #define IPV6_FLOW 0x11 /* hash only */ #define ETHER_FLOW 0x12 /* spec only (ether_spec) */ + +/* Used for GTP-U IPv4 and IPv6. + * The format of GTP packets only includes + * elements such as TEID and GTP version. + * It is primarily intended for data communication of the UE. + */ +#define GTPU_V4_FLOW 0x13 /* hash only */ +#define GTPU_V6_FLOW 0x14 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * The format of these GTP packets does not include TEID. + * Primarily expected to be used for communication + * to create sessions for UE data communication, + * commonly referred to as CSR (Create Session Request). + */ +#define GTPC_V4_FLOW 0x15 /* hash only */ +#define GTPC_V6_FLOW 0x16 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. + * After session creation, it becomes this packet. + * This is mainly used for requests to realize UE handover. + */ +#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ +#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ + +/* Use for GTP-U and extended headers for the PSC (PDU Session Container). + * The format of these GTP packets includes TEID and QFI. + * In 5G communication using UPF (User Plane Function), + * data communication with this extended header is performed. + */ +#define GTPU_EH_V4_FLOW 0x19 /* hash only */ +#define GTPU_EH_V6_FLOW 0x1a /* hash only */ + +/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by + * UL/DL included in the PSC. + * There are differences in the data included based on Downlink/Uplink, + * and can be used to distinguish packets. + * The functions described so far are useful when you want to + * handle communication from the mobile network in UPF, PGW, etc. + */ +#define GTPU_UL_V4_FLOW 0x1b /* hash only */ +#define GTPU_UL_V6_FLOW 0x1c /* hash only */ +#define GTPU_DL_V4_FLOW 0x1d /* hash only */ +#define GTPU_DL_V6_FLOW 0x1e /* hash only */ + /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 #define FLOW_MAC_EXT 0x40000000 @@ -2037,6 +2084,7 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define RXH_IP_DST (1 << 5) #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ +#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL -- cgit v1.2.3 From 011832b97b311bb9e3c27945bc0d1089a14209c9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 5 Mar 2024 19:19:26 -0800 Subject: bpf: Introduce may_goto instruction Introduce may_goto instruction that from the verifier pov is similar to open coded iterators bpf_for()/bpf_repeat() and bpf_loop() helper, but it doesn't iterate any objects. In assembly 'may_goto' is a nop most of the time until bpf runtime has to terminate the program for whatever reason. In the current implementation may_goto has a hidden counter, but other mechanisms can be used. For programs written in C the later patch introduces 'cond_break' macro that combines 'may_goto' with 'break' statement and has similar semantics: cond_break is a nop until bpf runtime has to break out of this loop. It can be used in any normal "for" or "while" loop, like for (i = zero; i < cnt; cond_break, i++) { The verifier recognizes that may_goto is used in the program, reserves additional 8 bytes of stack, initializes them in subprog prologue, and replaces may_goto instruction with: aux_reg = *(u64 *)(fp - 40) if aux_reg == 0 goto pc+off aux_reg -= 1 *(u64 *)(fp - 40) = aux_reg may_goto instruction can be used by LLVM to implement __builtin_memcpy, __builtin_strcmp. may_goto is not a full substitute for bpf_for() macro. bpf_for() doesn't have induction variable that verifiers sees, so 'i' in bpf_for(i, 0, 100) is seen as imprecise and bounded. But when the code is written as: for (i = 0; i < 100; cond_break, i++) the verifier see 'i' as precise constant zero, hence cond_break (aka may_goto) doesn't help to converge the loop. A static or global variable can be used as a workaround: static int zero = 0; for (i = zero; i < 100; cond_break, i++) // works! may_goto works well with arena pointers that don't need to be bounds checked on access. Load/store from arena returns imprecise unbounded scalar and loops with may_goto pass the verifier. Reserve new opcode BPF_JMP | BPF_JCOND for may_goto insn. JCOND stands for conditional pseudo jump. Since goto_or_nop insn was proposed, it may use the same opcode. may_goto vs goto_or_nop can be distinguished by src_reg: code = BPF_JMP | BPF_JCOND src_reg = 0 - may_goto src_reg = 1 - goto_or_nop Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: Eduard Zingerman Acked-by: John Fastabend Tested-by: John Fastabend Link: https://lore.kernel.org/bpf/20240306031929.42666-2-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 2 + include/uapi/linux/bpf.h | 5 ++ kernel/bpf/core.c | 1 + kernel/bpf/disasm.c | 4 + kernel/bpf/verifier.c | 163 +++++++++++++++++++++++++++++++++-------- tools/include/uapi/linux/bpf.h | 5 ++ 6 files changed, 150 insertions(+), 30 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 84365e6dd85d..4b0f6600e499 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -449,6 +449,7 @@ struct bpf_verifier_state { u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; + u32 may_goto_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -619,6 +620,7 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ + u16 stack_extra; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a241f407c234..85ec7fc799d7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -42,6 +42,7 @@ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSLT 0xc0 /* SLT is signed, '<' */ #define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -50,6 +51,10 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + /* Register numbers */ enum { BPF_REG_0 = 0, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 71c459a51d9e..9ee4536d0a09 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1675,6 +1675,7 @@ bool bpf_opcode_in_insntable(u8 code) [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, + [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 49940c26a227..82b2dbdd048f 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -322,6 +322,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_JCOND) && + insn->src_reg == BPF_MAY_GOTO) { + verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", + insn->code, insn->off); } else if (insn->code == (BPF_JMP32 | BPF_JA)) { verbose(cbs->private_data, "(%02x) gotol pc%+d\n", insn->code, insn->imm); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4dd84e13bbfe..8030b50d3b45 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -533,6 +533,16 @@ static bool is_async_callback_calling_insn(struct bpf_insn *insn) return bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm); } +static bool is_may_goto_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; +} + +static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) +{ + return is_may_goto_insn(&env->prog->insnsi[insn_idx]); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1429,6 +1439,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->dfs_depth = src->dfs_depth; dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; + dst_state->may_goto_depth = src->may_goto_depth; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -14871,11 +14882,36 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, int err; /* Only conditional jumps are expected to reach here. */ - if (opcode == BPF_JA || opcode > BPF_JSLE) { + if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } + if (opcode == BPF_JCOND) { + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; + int idx = *insn_idx; + + if (insn->code != (BPF_JMP | BPF_JCOND) || + insn->src_reg != BPF_MAY_GOTO || + insn->dst_reg || insn->imm || insn->off == 0) { + verbose(env, "invalid may_goto off %d imm %d\n", + insn->off, insn->imm); + return -EINVAL; + } + prev_st = find_prev_entry(env, cur_st->parent, idx); + + /* branch out 'fallthrough' insn as a new state to explore */ + queued_st = push_stack(env, idx + 1, idx, false); + if (!queued_st) + return -ENOMEM; + + queued_st->may_goto_depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); + *insn_idx += insn->off; + return 0; + } + /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) @@ -15659,6 +15695,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) default: /* conditional jump with two edges */ mark_prune_point(env, t); + if (is_may_goto_insn(insn)) + mark_force_checkpoint(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) @@ -17135,6 +17173,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } goto skip_inf_loop_check; } + if (is_may_goto_insn_at(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, true)) { + update_loop_entry(cur, &sl->state); + goto hit; + } + goto skip_inf_loop_check; + } if (calls_callback(env, insn_idx)) { if (states_equal(env, &sl->state, cur, true)) goto hit; @@ -17144,6 +17189,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, true) && !iter_active_depths_differ(&sl->state, cur) && + sl->state.may_goto_depth == cur->may_goto_depth && sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); @@ -19408,7 +19454,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, ret, cnt, delta = 0; + int i, ret, cnt, delta = 0, cur_subprog = 0; + struct bpf_subprog_info *subprogs = env->subprog_info; + u16 stack_depth = subprogs[cur_subprog].stack_depth; + u16 stack_depth_extra = 0; if (env->seen_exception && !env->exception_callback_subprog) { struct bpf_insn patch[] = { @@ -19428,7 +19477,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) mark_subprog_exc_cb(env, env->exception_callback_subprog); } - for (i = 0; i < insn_cnt; i++, insn++) { + for (i = 0; i < insn_cnt;) { /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || @@ -19467,7 +19516,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ @@ -19487,7 +19536,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ @@ -19502,7 +19551,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) - continue; + goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == @@ -19540,19 +19589,39 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; + } + + if (is_may_goto_insn(insn)) { + int stack_off = -stack_depth - 8; + + stack_depth_extra = 8; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); + cnt = 4; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; } if (insn->code != (BPF_JMP | BPF_CALL)) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) - continue; + goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) @@ -19561,7 +19630,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_get_route_realm) @@ -19609,11 +19678,11 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } insn->imm = ret + 1; - continue; + goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) - continue; + goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: @@ -19642,7 +19711,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { @@ -19754,7 +19823,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, @@ -19785,31 +19854,31 @@ patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); - continue; + goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); - continue; + goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); - continue; + goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); - continue; + goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); - continue; + goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); - continue; + goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); - continue; + goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); - continue; + goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); - continue; + goto next_insn; } goto patch_call_imm; @@ -19837,7 +19906,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_arg inline. */ @@ -19862,7 +19931,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ret inline. */ @@ -19890,7 +19959,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement get_func_arg_cnt inline. */ @@ -19905,7 +19974,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ip inline. */ @@ -19920,7 +19989,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_kptr_xchg inline */ @@ -19938,7 +20007,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); @@ -19952,6 +20021,40 @@ patch_call_imm: return -EFAULT; } insn->imm = fn->func - __bpf_call_base; +next_insn: + if (subprogs[cur_subprog + 1].start == i + delta + 1) { + subprogs[cur_subprog].stack_depth += stack_depth_extra; + subprogs[cur_subprog].stack_extra = stack_depth_extra; + cur_subprog++; + stack_depth = subprogs[cur_subprog].stack_depth; + stack_depth_extra = 0; + } + i++; + insn++; + } + + env->prog->aux->stack_depth = subprogs[0].stack_depth; + for (i = 0; i < env->subprog_cnt; i++) { + int subprog_start = subprogs[i].start; + int stack_slots = subprogs[i].stack_extra / 8; + + if (!stack_slots) + continue; + if (stack_slots > 1) { + verbose(env, "verifier bug: stack_slots supports may_goto only\n"); + return -EFAULT; + } + + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, + -subprogs[i].stack_depth, BPF_MAX_LOOPS); + /* Copy first actual insn to preserve it */ + insn_buf[1] = env->prog->insnsi[subprog_start]; + + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); + if (!new_prog) + return -ENOMEM; + env->prog = prog = new_prog; } /* Since poke tab is now finalized, publish aux to tracker. */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a241f407c234..85ec7fc799d7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -42,6 +42,7 @@ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ #define BPF_JSLT 0xc0 /* SLT is signed, '<' */ #define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -50,6 +51,10 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From 4035c22ef7d43a6c00d6a6584c60e902b95b46af Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 6 Mar 2024 23:14:50 +0000 Subject: arm64/ptrace: Expose FPMR via ptrace Add a new regset to expose FPMR via ptrace. It is not added to the FPSIMD registers since that structure is exposed elsewhere without any allowance for extension we don't add there. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20240306-arm64-2023-dpisa-v5-5-c568edc8ed7f@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/kernel/ptrace.c | 42 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 43 insertions(+) (limited to 'include/uapi') diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index dc6cf0e37194..aacb45bd36e6 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -698,6 +698,39 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, return ret; } +static int fpmr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_fpmr()) + return -EINVAL; + + if (target == current) + fpsimd_preserve_current_state(); + + return membuf_store(&to, target->thread.uw.fpmr); +} + +static int fpmr_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + unsigned long fpmr; + + if (!system_supports_fpmr()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); + if (ret) + return ret; + + target->thread.uw.fpmr = fpmr; + + fpsimd_flush_task_state(target); + + return 0; +} + static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) @@ -1419,6 +1452,7 @@ enum aarch64_regset { REGSET_HW_BREAK, REGSET_HW_WATCH, #endif + REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, @@ -1497,6 +1531,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = system_call_get, .set = system_call_set, }, + [REGSET_FPMR] = { + .core_note_type = NT_ARM_FPMR, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = fpmr_get, + .set = fpmr_set, + }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 9417309b7230..b54b313bcf07 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -440,6 +440,7 @@ typedef struct elf64_shdr { #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From ab63a2387cb906d43b72a8effb611bbaecb2d0cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Mar 2024 11:55:07 -0800 Subject: netdev: add per-queue statistics The ethtool-nl family does a good job exposing various protocol related and IEEE/IETF statistics which used to get dumped under ethtool -S, with creative names. Queue stats don't have a netlink API, yet, and remain a lion's share of ethtool -S output for new drivers. Not only is that bad because the names differ driver to driver but it's also bug-prone. Intuitively drivers try to report only the stats for active queues, but querying ethtool stats involves multiple system calls, and the number of stats is read separately from the stats themselves. Worse still when user space asks for values of the stats, it doesn't inform the kernel how big the buffer is. If number of stats increases in the meantime kernel will overflow user buffer. Add a netlink API for dumping queue stats. Queue information is exposed via the netdev-genl family, so add the stats there. Support per-queue and sum-for-device dumps. Latter will be useful when subsequent patches add more interesting common stats than just bytes and packets. The API does not currently distinguish between HW and SW stats. The expectation is that the source of the stats will either not matter much (good packets) or be obvious (skb alloc errors). Acked-by: Stanislav Fomichev Reviewed-by: Amritha Nambiar Reviewed-by: Xuan Zhuo Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 84 +++++++++++++ Documentation/networking/statistics.rst | 15 +++ include/linux/netdevice.h | 3 + include/net/netdev_queues.h | 54 ++++++++ include/uapi/linux/netdev.h | 19 +++ net/core/netdev-genl-gen.c | 12 ++ net/core/netdev-genl-gen.h | 2 + net/core/netdev-genl.c | 213 ++++++++++++++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 19 +++ 9 files changed, 421 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 3addac970680..a1e48c3c84c9 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -74,6 +74,10 @@ definitions: name: queue-type type: enum entries: [ rx, tx ] + - + name: qstats-scope + type: flags + entries: [ queue ] attribute-sets: - @@ -265,6 +269,66 @@ attribute-sets: doc: ID of the NAPI instance which services this queue. type: u32 + - + name: qstats + doc: | + Get device statistics, scoped to a device or a queue. + These statistics extend (and partially duplicate) statistics available + in struct rtnl_link_stats64. + Value of the `scope` attribute determines how statistics are + aggregated. When aggregated for the entire device the statistics + represent the total number of events since last explicit reset of + the device (i.e. not a reconfiguration like changing queue count). + When reported per-queue, however, the statistics may not add + up to the total number of events, will only be reported for currently + active objects, and will likely report the number of events since last + reconfiguration. + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which stats belong. + type: u32 + checks: + min: 1 + - + name: queue-type + doc: Queue type as rx, tx, for queue-id. + type: u32 + enum: queue-type + - + name: queue-id + doc: Queue ID, if stats are scoped to a single queue instance. + type: u32 + - + name: scope + doc: | + What object type should be used to iterate over the stats. + type: uint + enum: qstats-scope + - + name: rx-packets + doc: | + Number of wire packets successfully received and passed to the stack. + For drivers supporting XDP, XDP is considered the first layer + of the stack, so packets consumed by XDP are still counted here. + type: uint + value: 8 # reserve some attr ids in case we need more metadata later + - + name: rx-bytes + doc: Successfully received bytes, see `rx-packets`. + type: uint + - + name: tx-packets + doc: | + Number of wire packets successfully sent. Packet is considered to be + successfully sent once it is in device memory (usually this means + the device has issued a DMA completion for the packet). + type: uint + - + name: tx-bytes + doc: Successfully sent bytes, see `tx-packets`. + type: uint + operations: list: - @@ -405,6 +469,26 @@ operations: attributes: - ifindex reply: *napi-get-op + - + name: qstats-get + doc: | + Get / dump fine grained statistics. Which statistics are reported + depends on the device and the driver, and whether the driver stores + software counters per-queue. + attribute-set: qstats + dump: + request: + attributes: + - scope + reply: + attributes: + - ifindex + - queue-type + - queue-id + - rx-packets + - rx-bytes + - tx-packets + - tx-bytes mcast-groups: list: diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 551b3cc29a41..75e017dfa825 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -41,6 +41,15 @@ If `-s` is specified once the detailed errors won't be shown. `ip` supports JSON formatting via the `-j` option. +Queue statistics +~~~~~~~~~~~~~~~~ + +Queue statistics are accessible via the netdev netlink family. + +Currently no widely distributed CLI exists to access those statistics. +Kernel development tools (ynl) can be used to experiment with them, +see `Documentation/userspace-api/netlink/intro-specs.rst`. + Protocol-specific statistics ---------------------------- @@ -147,6 +156,12 @@ Statistics are reported both in the responses to link information requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`, when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request). +netdev (netlink) +~~~~~~~~~~~~~~~~ + +`netdev` generic netlink family allows accessing page pool and per queue +statistics. + ethtool ------- diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 416a800d72ba..4230c7f3b959 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1955,6 +1955,7 @@ enum netdev_reg_state { * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops + * @stat_ops: Optional ops for queue-aware statistics * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2335,6 +2336,8 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; + const struct netdev_stat_ops *stat_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 8b8ed4e13d74..d633347eeda5 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,60 @@ #include +struct netdev_queue_stats_rx { + u64 bytes; + u64 packets; +}; + +struct netdev_queue_stats_tx { + u64 bytes; + u64 packets; +}; + +/** + * struct netdev_stat_ops - netdev ops for fine grained stats + * @get_queue_stats_rx: get stats for a given Rx queue + * @get_queue_stats_tx: get stats for a given Tx queue + * @get_base_stats: get base stats (not belonging to any live instance) + * + * Query stats for a given object. The values of the statistics are undefined + * on entry (specifically they are *not* zero-initialized). Drivers should + * assign values only to the statistics they collect. Statistics which are not + * collected must be left undefined. + * + * Queue objects are not necessarily persistent, and only currently active + * queues are queried by the per-queue callbacks. This means that per-queue + * statistics will not generally add up to the total number of events for + * the device. The @get_base_stats callback allows filling in the delta + * between events for currently live queues and overall device history. + * When the statistics for the entire device are queried, first @get_base_stats + * is issued to collect the delta, and then a series of per-queue callbacks. + * Only statistics which are set in @get_base_stats will be reported + * at the device level, meaning that unlike in queue callbacks, setting + * a statistic to zero in @get_base_stats is a legitimate thing to do. + * This is because @get_base_stats has a second function of designating which + * statistics are in fact correct for the entire device (e.g. when history + * for some of the events is not maintained, and reliable "total" cannot + * be provided). + * + * Device drivers can assume that when collecting total device stats, + * the @get_base_stats and subsequent per-queue calls are performed + * "atomically" (without releasing the rtnl_lock). + * + * Device drivers are encouraged to reset the per-queue statistics when + * number of queues change. This is because the primary use case for + * per-queue statistics is currently to detect traffic imbalance. + */ +struct netdev_stat_ops { + void (*get_queue_stats_rx)(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *stats); + void (*get_queue_stats_tx)(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *stats); + void (*get_base_stats)(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 93cb411adf72..639ffa04c172 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -132,6 +136,20 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) }; +enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -144,6 +162,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..8d8ace9ef87f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_QSTATS_GET - dump */ +static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_QSTATS_GET, + .dumpit = netdev_nl_qstats_get_dumpit, + .policy = netdev_qstats_get_nl_policy, + .maxattr = NETDEV_A_QSTATS_SCOPE, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..4db40fd5b4a9 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 918b109e0cf4..7fa75e13dc6d 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include "netdev-genl-gen.h" @@ -460,6 +461,218 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return err; } +#define NETDEV_STAT_NOT_SET (~0ULL) + +static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) +{ + const u64 *add = _add; + u64 *sum = _sum; + + while (size) { + if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) + *sum += *add; + sum++; + add++; + size -= 8; + } +} + +static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) +{ + if (value == NETDEV_STAT_NOT_SET) + return 0; + return nla_put_uint(rsp, attr_id, value); +} + +static int +netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, + u32 q_type, int i, const struct genl_info *info) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + memset(&rx, 0xff, sizeof(rx)); + ops->get_queue_stats_rx(netdev, i, &rx); + if (!memchr_inv(&rx, 0xff, sizeof(rx))) + goto nla_cancel; + if (netdev_nl_stats_write_rx(rsp, &rx)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + memset(&tx, 0xff, sizeof(tx)); + ops->get_queue_stats_tx(netdev, i, &tx); + if (!memchr_inv(&tx, 0xff, sizeof(tx))) + goto nla_cancel; + if (netdev_nl_stats_write_tx(rsp, &tx)) + goto nla_put_failure; + break; + } + + genlmsg_end(rsp, hdr); + return 0; + +nla_cancel: + genlmsg_cancel(rsp, hdr); + return 0; +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int +netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + int i, err; + + if (!(netdev->flags & IFF_UP)) + return 0; + + i = ctx->rxq_idx; + while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, + i, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + i = ctx->txq_idx; + while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, + i, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + return 0; +} + +static int +netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info) +{ + struct netdev_queue_stats_rx rx_sum, rx; + struct netdev_queue_stats_tx tx_sum, tx; + const struct netdev_stat_ops *ops; + void *hdr; + int i; + + ops = netdev->stat_ops; + /* Netdev can't guarantee any complete counters */ + if (!ops->get_base_stats) + return 0; + + memset(&rx_sum, 0xff, sizeof(rx_sum)); + memset(&tx_sum, 0xff, sizeof(tx_sum)); + + ops->get_base_stats(netdev, &rx_sum, &tx_sum); + + /* The op was there, but nothing reported, don't bother */ + if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && + !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + for (i = 0; i < netdev->real_num_rx_queues; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); + } + for (i = 0; i < netdev->real_num_tx_queues; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); + } + + if (netdev_nl_stats_write_rx(rsp, &rx_sum) || + netdev_nl_stats_write_tx(rsp, &tx_sum)) + goto nla_put_failure; + + genlmsg_end(rsp, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + unsigned int scope; + int err = 0; + + scope = 0; + if (info->attrs[NETDEV_A_QSTATS_SCOPE]) + scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); + + rtnl_lock(); + for_each_netdev_dump(net, netdev, ctx->ifindex) { + if (!netdev->stat_ops) + continue; + + switch (scope) { + case 0: + err = netdev_nl_stats_by_netdev(netdev, skb, info); + break; + case NETDEV_QSTATS_SCOPE_QUEUE: + err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); + break; + } + if (err < 0) + break; + } + rtnl_unlock(); + + return err; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 93cb411adf72..639ffa04c172 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -132,6 +136,20 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) }; +enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -144,6 +162,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From 92f8b1f5ca0f157f564e75cef4c63641c172e0f1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Mar 2024 11:55:08 -0800 Subject: netdev: add queue stat for alloc failures Rx alloc failures are commonly counted by drivers. Support reporting those via netdev-genl queue stats. Acked-by: Stanislav Fomichev Reviewed-by: Amritha Nambiar Reviewed-by: Xuan Zhuo Link: https://lore.kernel.org/r/20240306195509.1502746-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 7 +++++++ include/net/netdev_queues.h | 2 ++ include/uapi/linux/netdev.h | 1 + net/core/netdev-genl.c | 3 ++- tools/include/uapi/linux/netdev.h | 1 + 5 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index a1e48c3c84c9..76352dbd2be4 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -328,6 +328,13 @@ attribute-sets: name: tx-bytes doc: Successfully sent bytes, see `tx-packets`. type: uint + - + name: rx-alloc-fail + doc: | + Number of times skb or buffer allocation failed on the Rx datapath. + Allocation failure may, or may not result in a packet drop, depending + on driver implementation and whether system recovers quickly. + type: uint operations: list: diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index d633347eeda5..1ec408585373 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,9 +4,11 @@ #include +/* See the netdev.yaml spec for definition of each statistic */ struct netdev_queue_stats_rx { u64 bytes; u64 packets; + u64 alloc_fail; }; struct netdev_queue_stats_tx { diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 639ffa04c172..bb65ee840cda 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -145,6 +145,7 @@ enum { NETDEV_A_QSTATS_RX_BYTES, NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 7fa75e13dc6d..7004b3399c2b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -488,7 +488,8 @@ static int netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) return -EMSGSIZE; return 0; } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 639ffa04c172..bb65ee840cda 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -145,6 +145,7 @@ enum { NETDEV_A_QSTATS_RX_BYTES, NETDEV_A_QSTATS_TX_PACKETS, NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, __NETDEV_A_QSTATS_MAX, NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) -- cgit v1.2.3 From a207eab1039b501daddc8e729c9cc5d99fe93d18 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 6 Mar 2024 13:49:16 +0100 Subject: net: nexthop: Add NHA_OP_FLAGS In order to add per-nexthop statistics, but still not increase netlink message size for consumers that do not care about them, there needs to be a toggle through which the user indicates their desire to get the statistics. To that end, add a new attribute, NHA_OP_FLAGS. The idea is to be able to use the attribute for carrying of arbitrary operation-specific flags, i.e. not make it specific for get / dump. Add the new attribute to get and dump policies, but do not actually allow any flags yet -- those will come later as the flags themselves are defined. Add the necessary parsing code. Signed-off-by: Petr Machata Reviewed-by: David Ahern Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/nexthop.h | 3 +++ net/ipv4/nexthop.c | 24 ++++++++++++++++++++---- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index d8ffa8c9ca78..086444e2946c 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -60,6 +60,9 @@ enum { /* nested; nexthop bucket attributes */ NHA_RES_BUCKET, + /* u32; operation-specific flags */ + NHA_OP_FLAGS, + __NHA_MAX, }; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index bcd4df2f1cad..576981f4ca49 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -41,6 +41,7 @@ static const struct nla_policy rtm_nh_policy_new[] = { static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0), }; static const struct nla_policy rtm_nh_policy_del[] = { @@ -52,6 +53,7 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -2971,7 +2973,7 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, } static int nh_valid_get_del_req(const struct nlmsghdr *nlh, - struct nlattr **tb, u32 *id, + struct nlattr **tb, u32 *id, u32 *op_flags, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); @@ -2992,6 +2994,11 @@ static int nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } + if (tb[NHA_OP_FLAGS]) + *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + *op_flags = 0; + return 0; } @@ -3007,6 +3014,7 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; + u32 op_flags; int err; u32 id; @@ -3015,7 +3023,7 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - err = nh_valid_get_del_req(nlh, tb, &id, extack); + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3036,6 +3044,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct nlattr *tb[NHA_MAX + 1]; struct sk_buff *skb = NULL; struct nexthop *nh; + u32 op_flags; int err; u32 id; @@ -3044,7 +3053,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) return err; - err = nh_valid_get_del_req(nlh, tb, &id, extack); + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3080,6 +3089,7 @@ struct nh_dump_filter { bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; + u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -3151,6 +3161,11 @@ static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, return -EINVAL; } + if (tb[NHA_OP_FLAGS]) + filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + filter->op_flags = 0; + return 0; } @@ -3474,6 +3489,7 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[NHA_MAX + 1]; + u32 op_flags; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, @@ -3481,7 +3497,7 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, if (err < 0) return err; - err = nh_valid_get_del_req(nlh, tb, id, extack); + err = nh_valid_get_del_req(nlh, tb, id, &op_flags, extack); if (err) return err; -- cgit v1.2.3 From 95fedd7685912f96304615efe50485588b1c3567 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Mar 2024 13:49:18 +0100 Subject: net: nexthop: Expose nexthop group stats to user space Add netlink support for reading NH group stats. This data is only for statistics of the traffic in the SW datapath. HW nexthop group statistics will be added in the following patches. Emission of the stats is keyed to a new op_stats flag to avoid cluttering the netlink message with stats if the user doesn't need them: NHA_OP_FLAG_DUMP_STATS. Co-developed-by: Petr Machata Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/nexthop.h | 30 ++++++++++++++ net/ipv4/nexthop.c | 95 ++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 117 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index 086444e2946c..f4db63c17085 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -30,6 +30,8 @@ enum { #define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) +#define NHA_OP_FLAG_DUMP_STATS BIT(0) + enum { NHA_UNSPEC, NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ @@ -63,6 +65,9 @@ enum { /* u32; operation-specific flags */ NHA_OP_FLAGS, + /* nested; nexthop group stats */ + NHA_GROUP_STATS, + __NHA_MAX, }; @@ -104,4 +109,29 @@ enum { #define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1) +enum { + NHA_GROUP_STATS_UNSPEC, + + /* nested; nexthop group entry stats */ + NHA_GROUP_STATS_ENTRY, + + __NHA_GROUP_STATS_MAX, +}; + +#define NHA_GROUP_STATS_MAX (__NHA_GROUP_STATS_MAX - 1) + +enum { + NHA_GROUP_STATS_ENTRY_UNSPEC, + + /* u32; nexthop id of the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_ID, + + /* uint; number of packets forwarded via the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_PACKETS, + + __NHA_GROUP_STATS_ENTRY_MAX, +}; + +#define NHA_GROUP_STATS_ENTRY_MAX (__NHA_GROUP_STATS_ENTRY_MAX - 1) + #endif diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 92dc21a231f8..3365c41eee9a 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,6 +26,8 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS) + static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, @@ -41,7 +43,8 @@ static const struct nla_policy rtm_nh_policy_new[] = { static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, - [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0), + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_policy_del[] = { @@ -53,7 +56,8 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, - [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0), + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -671,8 +675,78 @@ static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) u64_stats_update_end(&cpu_stats->syncp); } -static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, + u64 *ret_packets) +{ + int i; + + *ret_packets = 0; + + for_each_possible_cpu(i) { + struct nh_grp_entry_stats *cpu_stats; + unsigned int start; + u64 packets; + + cpu_stats = per_cpu_ptr(nhge->stats, i); + do { + start = u64_stats_fetch_begin(&cpu_stats->syncp); + packets = u64_stats_read(&cpu_stats->packets); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + *ret_packets += packets; + } +} + +static int nla_put_nh_group_stats_entry(struct sk_buff *skb, + struct nh_grp_entry *nhge) +{ + struct nlattr *nest; + u64 packets; + + nh_grp_entry_stats_read(nhge, &packets); + + nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, packets)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh) { + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + struct nlattr *nest; + int i; + + nest = nla_nest_start(skb, NHA_GROUP_STATS); + if (!nest) + return -EMSGSIZE; + + for (i = 0; i < nhg->num_nh; i++) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i])) + goto cancel_out; + + nla_nest_end(skb, nest); + return 0; + +cancel_out: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; @@ -701,6 +775,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; + if (op_flags & NHA_OP_FLAG_DUMP_STATS && + nla_put_nh_group_stats(skb, nh)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -708,7 +786,8 @@ nla_put_failure: } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, - int event, u32 portid, u32 seq, unsigned int nlflags) + int event, u32 portid, u32 seq, unsigned int nlflags, + u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; @@ -735,7 +814,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nhg)) + if (nla_put_nh_group(skb, nh, op_flags)) goto nla_put_failure; goto out; } @@ -866,7 +945,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) if (!skb) goto errout; - err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -3095,7 +3174,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; @@ -3265,7 +3344,7 @@ static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ -- cgit v1.2.3 From 746c19a52ec50b81422fd4772254d55e588d7df6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Mar 2024 13:49:20 +0100 Subject: net: nexthop: Add ability to enable / disable hardware statistics Add netlink support for enabling collection of HW statistics on nexthop groups. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- include/net/nexthop.h | 2 ++ include/uapi/linux/nexthop.h | 3 +++ net/ipv4/nexthop.c | 15 ++++++++++++++- 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 584c37120c20..1ba6d3668518 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -47,6 +47,8 @@ struct nh_config { bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; + bool nh_hw_stats; + struct nlattr *nh_encap; u16 nh_encap_type; diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index f4db63c17085..b86af80d4e09 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -68,6 +68,9 @@ enum { /* nested; nexthop group stats */ NHA_GROUP_STATS, + /* u32; nexthop hardware stats enable */ + NHA_HW_STATS_ENABLE, + __NHA_MAX, }; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index c0d14e16e9c8..e75b1aae5a81 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -39,6 +39,7 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, + [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { @@ -778,7 +779,8 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_STATS && - nla_put_nh_group_stats(skb, nh)) + (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || + nla_put_nh_group_stats(skb, nh))) goto nla_put_failure; return 0; @@ -1202,6 +1204,7 @@ static int nh_check_attr_group(struct net *net, if (!tb[i]) continue; switch (i) { + case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: @@ -2622,6 +2625,9 @@ static struct nexthop *nexthop_create_group(struct net *net, if (cfg->nh_fdb) nhg->fdb_nh = 1; + if (cfg->nh_hw_stats) + nhg->hw_stats = true; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -2964,6 +2970,9 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); + if (tb[NHA_HW_STATS_ENABLE]) + cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); + /* no other attributes should be set */ goto out; } @@ -3055,6 +3064,10 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } + if (tb[NHA_HW_STATS_ENABLE]) { + NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); + goto out; + } err = 0; out: -- cgit v1.2.3 From 5072ae00aea434d922cabd1c3e6236350a77c4d7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Mar 2024 13:49:21 +0100 Subject: net: nexthop: Expose nexthop group HW stats to user space Add netlink support for reading NH group hardware stats. Stats collection is done through a new notifier, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA. Drivers that implement HW counters for a given NH group are thereby asked to collect the stats and report back to core by calling nh_grp_hw_stats_report_delta(). This is similar to what netdevice L3 stats do. Besides exposing number of packets that passed in the HW datapath, also include information on whether any driver actually realizes the counters. The core can tell based on whether it got any _report_delta() reports from the drivers. This allows enabling the statistics at the group at any time, with drivers opting into supporting them. This is also in line with what netdevice L3 stats are doing. So as not to waste time and space, tie the collection and reporting of HW stats with a new op flag, NHA_OP_FLAG_DUMP_HW_STATS. Co-developed-by: Petr Machata Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Reviewed-by: Kees Cook # For the __counted_by bits Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 18 ++++++ include/uapi/linux/nexthop.h | 9 +++ net/ipv4/nexthop.c | 130 ++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 149 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 1ba6d3668518..7ec9cc80f11c 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -122,6 +122,7 @@ struct nh_grp_entry { struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ + u64 packets_hw; }; struct nh_group { @@ -166,6 +167,7 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { @@ -173,6 +175,7 @@ enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, + NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { @@ -214,6 +217,17 @@ struct nh_notifier_res_table_info { struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; +struct nh_notifier_grp_hw_stats_entry_info { + u32 id; + u64 packets; +}; + +struct nh_notifier_grp_hw_stats_info { + u16 num_nh; + bool hw_stats_used; + struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); +}; + struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; @@ -224,6 +238,7 @@ struct nh_notifier_info { struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; + struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; @@ -236,6 +251,9 @@ void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index b86af80d4e09..dd8787f9cf39 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -31,6 +31,7 @@ enum { #define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) #define NHA_OP_FLAG_DUMP_STATS BIT(0) +#define NHA_OP_FLAG_DUMP_HW_STATS BIT(1) enum { NHA_UNSPEC, @@ -71,6 +72,9 @@ enum { /* u32; nexthop hardware stats enable */ NHA_HW_STATS_ENABLE, + /* u32; read-only; whether any driver collects HW stats */ + NHA_HW_STATS_USED, + __NHA_MAX, }; @@ -132,6 +136,11 @@ enum { /* uint; number of packets forwarded via the nexthop group entry */ NHA_GROUP_STATS_ENTRY_PACKETS, + /* uint; number of packets forwarded via the nexthop group entry in + * hardware + */ + NHA_GROUP_STATS_ENTRY_PACKETS_HW, + __NHA_GROUP_STATS_ENTRY_MAX, }; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e75b1aae5a81..e34466751d7b 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,7 +26,8 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) -#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ + NHA_OP_FLAG_DUMP_HW_STATS) static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, @@ -700,8 +701,95 @@ static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, } } +static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + info->id = nh->id; + info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; + info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, + stats, nhg->num_nh), + GFP_KERNEL); + if (!info->nh_grp_hw_stats) + return -ENOMEM; + + info->nh_grp_hw_stats->num_nh = nhg->num_nh; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; + } + + return 0; +} + +static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp_hw_stats); +} + +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets) +{ + info->hw_stats_used = true; + info->stats[nh_idx].packets += delta_packets; +} +EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); + +static void nh_grp_hw_stats_apply_update(struct nexthop *nh, + struct nh_notifier_info *info) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; + } +} + +static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) +{ + struct nh_notifier_info info = { + .net = nh->net, + }; + struct net *net = nh->net; + int err; + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_grp_hw_stats_init(&info, nh); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, + &info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + nh_grp_hw_stats_apply_update(nh, &info); + *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; + + nh_notifier_grp_hw_stats_fini(&info); + return notifier_to_errno(err); +} + static int nla_put_nh_group_stats_entry(struct sk_buff *skb, - struct nh_grp_entry *nhge) + struct nh_grp_entry *nhge, + u32 op_flags) { struct nlattr *nest; u64 packets; @@ -713,7 +801,13 @@ static int nla_put_nh_group_stats_entry(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || - nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, packets)) + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, + packets + nhge->packets_hw)) + goto nla_put_failure; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, + nhge->packets_hw)) goto nla_put_failure; nla_nest_end(skb, nest); @@ -724,18 +818,35 @@ nla_put_failure: return -EMSGSIZE; } -static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh) +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nlattr *nest; + bool hw_stats_used; + int err; int i; + if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) + goto err_out; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nhg->hw_stats) { + err = nh_grp_hw_stats_update(nh, &hw_stats_used); + if (err) + goto out; + + if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) + goto err_out; + } + nest = nla_nest_start(skb, NHA_GROUP_STATS); if (!nest) - return -EMSGSIZE; + goto err_out; for (i = 0; i < nhg->num_nh; i++) - if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i])) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], + op_flags)) goto cancel_out; nla_nest_end(skb, nest); @@ -743,7 +854,10 @@ static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh) cancel_out: nla_nest_cancel(skb, nest); - return -EMSGSIZE; +err_out: + err = -EMSGSIZE; +out: + return err; } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, @@ -780,7 +894,7 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, if (op_flags & NHA_OP_FLAG_DUMP_STATS && (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || - nla_put_nh_group_stats(skb, nh))) + nla_put_nh_group_stats(skb, nh, op_flags))) goto nla_put_failure; return 0; -- cgit v1.2.3 From 317460317a02a1af512697e6e964298dedd8a163 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:07:59 -0800 Subject: bpf: Introduce bpf_arena. Introduce bpf_arena, which is a sparse shared memory region between the bpf program and user space. Use cases: 1. User space mmap-s bpf_arena and uses it as a traditional mmap-ed anonymous region, like memcached or any key/value storage. The bpf program implements an in-kernel accelerator. XDP prog can search for a key in bpf_arena and return a value without going to user space. 2. The bpf program builds arbitrary data structures in bpf_arena (hash tables, rb-trees, sparse arrays), while user space consumes it. 3. bpf_arena is a "heap" of memory from the bpf program's point of view. The user space may mmap it, but bpf program will not convert pointers to user base at run-time to improve bpf program speed. Initially, the kernel vm_area and user vma are not populated. User space can fault in pages within the range. While servicing a page fault, bpf_arena logic will insert a new page into the kernel and user vmas. The bpf program can allocate pages from that region via bpf_arena_alloc_pages(). This kernel function will insert pages into the kernel vm_area. The subsequent fault-in from user space will populate that page into the user vma. The BPF_F_SEGV_ON_FAULT flag at arena creation time can be used to prevent fault-in from user space. In such a case, if a page is not allocated by the bpf program and not present in the kernel vm_area, the user process will segfault. This is useful for use cases 2 and 3 above. bpf_arena_alloc_pages() is similar to user space mmap(). It allocates pages either at a specific address within the arena or allocates a range with the maple tree. bpf_arena_free_pages() is analogous to munmap(), which frees pages and removes the range from the kernel vm_area and from user process vmas. bpf_arena can be used as a bpf program "heap" of up to 4GB. The speed of bpf program is more important than ease of sharing with user space. This is use case 3. In such a case, the BPF_F_NO_USER_CONV flag is recommended. It will tell the verifier to treat the rX = bpf_arena_cast_user(rY) instruction as a 32-bit move wX = wY, which will improve bpf prog performance. Otherwise, bpf_arena_cast_user is translated by JIT to conditionally add the upper 32 bits of user vm_start (if the pointer is not NULL) to arena pointers before they are stored into memory. This way, user space sees them as valid 64-bit pointers. Diff https://github.com/llvm/llvm-project/pull/84410 enables LLVM BPF backend generate the bpf_addr_space_cast() instruction to cast pointers between address_space(1) which is reserved for bpf_arena pointers and default address space zero. All arena pointers in a bpf program written in C language are tagged as __attribute__((address_space(1))). Hence, clang provides helpful diagnostics when pointers cross address space. Libbpf and the kernel support only address_space == 1. All other address space identifiers are reserved. rX = bpf_addr_space_cast(rY, /* dst_as */ 1, /* src_as */ 0) tells the verifier that rX->type = PTR_TO_ARENA. Any further operations on PTR_TO_ARENA register have to be in the 32-bit domain. The verifier will mark load/store through PTR_TO_ARENA with PROBE_MEM32. JIT will generate them as kern_vm_start + 32bit_addr memory accesses. The behavior is similar to copy_from_kernel_nofault() except that no address checks are necessary. The address is guaranteed to be in the 4GB range. If the page is not present, the destination register is zeroed on read, and the operation is ignored on write. rX = bpf_addr_space_cast(rY, 0, 1) tells the verifier that rX->type = unknown scalar. If arena->map_flags has BPF_F_NO_USER_CONV set, then the verifier converts such cast instructions to mov32. Otherwise, JIT will emit native code equivalent to: rX = (u32)rY; if (rY) rX |= clear_lo32_bits(arena->user_vm_start); /* replace hi32 bits in rX */ After such conversion, the pointer becomes a valid user pointer within bpf_arena range. The user process can access data structures created in bpf_arena without any additional computations. For example, a linked list built by a bpf program can be walked natively by user space. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Reviewed-by: Barret Rhoden Link: https://lore.kernel.org/bpf/20240308010812.89848-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 7 +- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 10 + kernel/bpf/Makefile | 3 + kernel/bpf/arena.c | 558 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 11 + kernel/bpf/syscall.c | 36 +++ kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 10 + 9 files changed, 635 insertions(+), 2 deletions(-) create mode 100644 kernel/bpf/arena.c (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 95e07673cdc1..ea6ab6e0eef9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; +struct bpf_arena; struct sock; struct seq_file; struct btf; @@ -528,8 +529,8 @@ void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); - - +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena); +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -2215,6 +2216,8 @@ int generic_map_delete_batch(struct bpf_map *map, struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG_KMEM void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 94baced5a1ad..9f2a6b83b49e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -132,6 +132,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_ARENA, arena_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 85ec7fc799d7..e30d943db8a4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1009,6 +1009,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, __MAX_BPF_MAP_TYPE }; @@ -1396,6 +1397,12 @@ enum { /* BPF token FD is passed in a corresponding command's token_fd field */ BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), }; /* Flags for BPF_PROG_QUERY. */ @@ -1467,6 +1474,9 @@ union bpf_attr { * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the * number of hash functions (if 0, the bloom filter will default * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. */ __u64 map_extra; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 4ce95acfcaa7..368c5d86b5b7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -15,6 +15,9 @@ obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o +ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy) +obj-$(CONFIG_BPF_SYSCALL) += arena.o +endif obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c new file mode 100644 index 000000000000..86571e760dd6 --- /dev/null +++ b/kernel/bpf/arena.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include +#include +#include + +/* + * bpf_arena is a sparsely populated shared memory region between bpf program and + * user space process. + * + * For example on x86-64 the values could be: + * user_vm_start 7f7d26200000 // picked by mmap() + * kern_vm_start ffffc90001e69000 // picked by get_vm_area() + * For user space all pointers within the arena are normal 8-byte addresses. + * In this example 7f7d26200000 is the address of the first page (pgoff=0). + * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr + * (u32)7f7d26200000 -> 26200000 + * hence + * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb + * kernel memory region. + * + * BPF JITs generate the following code to access arena: + * mov eax, eax // eax has lower 32-bit of user pointer + * mov word ptr [rax + r12 + off], bx + * where r12 == kern_vm_start and off is s16. + * Hence allocate 4Gb + GUARD_SZ/2 on each side. + * + * Initially kernel vm_area and user vma are not populated. + * User space can fault-in any address which will insert the page + * into kernel and user vma. + * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc + * which will insert it into kernel vm_area. + * The later fault-in from user space will populate that page into user vma. + */ + +/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ +#define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8) +#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ) + +struct bpf_arena { + struct bpf_map map; + u64 user_vm_start; + u64 user_vm_end; + struct vm_struct *kern_vm; + struct maple_tree mt; + struct list_head vma_list; + struct mutex lock; +}; + +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0; +} + +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return arena ? arena->user_vm_start : 0; +} + +static long arena_map_peek_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static long arena_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + +static long compute_pgoff(struct bpf_arena *arena, long uaddr) +{ + return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT; +} + +static struct bpf_map *arena_map_alloc(union bpf_attr *attr) +{ + struct vm_struct *kern_vm; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_arena *arena; + u64 vm_range; + int err = -ENOMEM; + + if (attr->key_size || attr->value_size || attr->max_entries == 0 || + /* BPF_F_MMAPABLE must be set */ + !(attr->map_flags & BPF_F_MMAPABLE) || + /* No unsupported flags present */ + (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV))) + return ERR_PTR(-EINVAL); + + if (attr->map_extra & ~PAGE_MASK) + /* If non-zero the map_extra is an expected user VMA start address */ + return ERR_PTR(-EINVAL); + + vm_range = (u64)attr->max_entries * PAGE_SIZE; + if (vm_range > (1ull << 32)) + return ERR_PTR(-E2BIG); + + if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) + /* user vma must not cross 32-bit boundary */ + return ERR_PTR(-ERANGE); + + kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP); + if (!kern_vm) + return ERR_PTR(-ENOMEM); + + arena = bpf_map_area_alloc(sizeof(*arena), numa_node); + if (!arena) + goto err; + + arena->kern_vm = kern_vm; + arena->user_vm_start = attr->map_extra; + if (arena->user_vm_start) + arena->user_vm_end = arena->user_vm_start + vm_range; + + INIT_LIST_HEAD(&arena->vma_list); + bpf_map_init_from_attr(&arena->map, attr); + mt_init_flags(&arena->mt, MT_FLAGS_ALLOC_RANGE); + mutex_init(&arena->lock); + + return &arena->map; +err: + free_vm_area(kern_vm); + return ERR_PTR(err); +} + +static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data) +{ + struct page *page; + pte_t pte; + + pte = ptep_get(ptep); + if (!pte_present(pte)) /* sanity check */ + return 0; + page = pte_page(pte); + /* + * We do not update pte here: + * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug + * 2. TLB flushing is batched or deferred. Even if we clear pte, + * the TLB entries can stick around and continue to permit access to + * the freed page. So it all relies on 1. + */ + __free_page(page); + return 0; +} + +static void arena_map_free(struct bpf_map *map) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + /* + * Check that user vma-s are not around when bpf map is freed. + * mmap() holds vm_file which holds bpf_map refcnt. + * munmap() must have happened on vma followed by arena_vm_close() + * which would clear arena->vma_list. + */ + if (WARN_ON_ONCE(!list_empty(&arena->vma_list))) + return; + + /* + * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area(). + * It unmaps everything from vmalloc area and clears pgtables. + * Call apply_to_existing_page_range() first to find populated ptes and + * free those pages. + */ + apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena), + KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL); + free_vm_area(arena->kern_vm); + mtree_destroy(&arena->mt); + bpf_map_area_free(arena); +} + +static void *arena_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static long arena_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + return 0; +} + +static u64 arena_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + +struct vma_list { + struct vm_area_struct *vma; + struct list_head head; +}; + +static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) +{ + struct vma_list *vml; + + vml = kmalloc(sizeof(*vml), GFP_KERNEL); + if (!vml) + return -ENOMEM; + vma->vm_private_data = vml; + vml->vma = vma; + list_add(&vml->head, &arena->vma_list); + return 0; +} + +static void arena_vm_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct vma_list *vml; + + guard(mutex)(&arena->lock); + vml = vma->vm_private_data; + list_del(&vml->head); + vma->vm_private_data = NULL; + kfree(vml); +} + +#define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */ + +static vm_fault_t arena_vm_fault(struct vm_fault *vmf) +{ + struct bpf_map *map = vmf->vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct page *page; + long kbase, kaddr; + int ret; + + kbase = bpf_arena_get_kern_vm_start(arena); + kaddr = kbase + (u32)(vmf->address & PAGE_MASK); + + guard(mutex)(&arena->lock); + page = vmalloc_to_page((void *)kaddr); + if (page) + /* already have a page vmap-ed */ + goto out; + + if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT) + /* User space requested to segfault when page is not allocated by bpf prog */ + return VM_FAULT_SIGSEGV; + + ret = mtree_insert(&arena->mt, vmf->pgoff, MT_ENTRY, GFP_KERNEL); + if (ret) + return VM_FAULT_SIGSEGV; + + /* Account into memcg of the process that created bpf_arena */ + ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + return VM_FAULT_SIGSEGV; + } + + ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + __free_page(page); + return VM_FAULT_SIGSEGV; + } +out: + page_ref_add(page, 1); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct arena_vm_ops = { + .close = arena_vm_close, + .fault = arena_vm_fault, +}; + +static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + long ret; + + if (pgoff) + return -EINVAL; + if (len > (1ull << 32)) + return -E2BIG; + + /* if user_vm_start was specified at arena creation time */ + if (arena->user_vm_start) { + if (len > arena->user_vm_end - arena->user_vm_start) + return -E2BIG; + if (len != arena->user_vm_end - arena->user_vm_start) + return -EINVAL; + if (addr != arena->user_vm_start) + return -EINVAL; + } + + ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags); + if (IS_ERR_VALUE(ret)) + return ret; + if ((ret >> 32) == ((ret + len - 1) >> 32)) + return ret; + if (WARN_ON_ONCE(arena->user_vm_start)) + /* checks at map creation time should prevent this */ + return -EFAULT; + return round_up(ret, 1ull << 32); +} + +static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + guard(mutex)(&arena->lock); + if (arena->user_vm_start && arena->user_vm_start != vma->vm_start) + /* + * If map_extra was not specified at arena creation time then + * 1st user process can do mmap(NULL, ...) to pick user_vm_start + * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..); + * or + * specify addr in map_extra and + * use the same addr later with mmap(addr, MAP_FIXED..); + */ + return -EBUSY; + + if (arena->user_vm_end && arena->user_vm_end != vma->vm_end) + /* all user processes must have the same size of mmap-ed region */ + return -EBUSY; + + /* Earlier checks should prevent this */ + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff)) + return -EFAULT; + + if (remember_vma(arena, vma)) + return -ENOMEM; + + arena->user_vm_start = vma->vm_start; + arena->user_vm_end = vma->vm_end; + /* + * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and + * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid + * potential change of user_vm_start. + */ + vm_flags_set(vma, VM_DONTEXPAND); + vma->vm_ops = &arena_vm_ops; + return 0; +} + +static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if ((u64)off > arena->user_vm_end - arena->user_vm_start) + return -ERANGE; + *imm = (unsigned long)arena->user_vm_start; + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena) +const struct bpf_map_ops arena_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = arena_map_alloc, + .map_free = arena_map_free, + .map_direct_value_addr = arena_map_direct_value_addr, + .map_mmap = arena_map_mmap, + .map_get_unmapped_area = arena_get_unmapped_area, + .map_get_next_key = arena_map_get_next_key, + .map_push_elem = arena_map_push_elem, + .map_peek_elem = arena_map_peek_elem, + .map_pop_elem = arena_map_pop_elem, + .map_lookup_elem = arena_map_lookup_elem, + .map_update_elem = arena_map_update_elem, + .map_delete_elem = arena_map_delete_elem, + .map_check_btf = arena_map_check_btf, + .map_mem_usage = arena_map_mem_usage, + .map_btf_id = &bpf_arena_map_btf_ids[0], +}; + +static u64 clear_lo32(u64 val) +{ + return val & ~(u64)~0U; +} + +/* + * Allocate pages and vmap them into kernel vmalloc area. + * Later the pages will be mmaped into user space vma. + */ +static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id) +{ + /* user_vm_end/start are fixed before bpf prog runs */ + long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; + u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena); + struct page **pages; + long pgoff = 0; + u32 uaddr32; + int ret, i; + + if (page_cnt > page_cnt_max) + return 0; + + if (uaddr) { + if (uaddr & ~PAGE_MASK) + return 0; + pgoff = compute_pgoff(arena, uaddr); + if (pgoff + page_cnt > page_cnt_max) + /* requested address will be outside of user VMA */ + return 0; + } + + /* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */ + pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return 0; + + guard(mutex)(&arena->lock); + + if (uaddr) + ret = mtree_insert_range(&arena->mt, pgoff, pgoff + page_cnt - 1, + MT_ENTRY, GFP_KERNEL); + else + ret = mtree_alloc_range(&arena->mt, &pgoff, MT_ENTRY, + page_cnt, 0, page_cnt_max - 1, GFP_KERNEL); + if (ret) + goto out_free_pages; + + ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO, + node_id, page_cnt, pages); + if (ret) + goto out; + + uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); + /* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */ + ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, + kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); + if (ret) { + for (i = 0; i < page_cnt; i++) + __free_page(pages[i]); + goto out; + } + kvfree(pages); + return clear_lo32(arena->user_vm_start) + uaddr32; +out: + mtree_erase(&arena->mt, pgoff); +out_free_pages: + kvfree(pages); + return 0; +} + +/* + * If page is present in vmalloc area, unmap it from vmalloc area, + * unmap it from all user space vma-s, + * and free it. + */ +static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + struct vma_list *vml; + + list_for_each_entry(vml, &arena->vma_list, head) + zap_page_range_single(vml->vma, uaddr, + PAGE_SIZE * page_cnt, NULL); +} + +static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + u64 full_uaddr, uaddr_end; + long kaddr, pgoff, i; + struct page *page; + + /* only aligned lower 32-bit are relevant */ + uaddr = (u32)uaddr; + uaddr &= PAGE_MASK; + full_uaddr = clear_lo32(arena->user_vm_start) + uaddr; + uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT)); + if (full_uaddr >= uaddr_end) + return; + + page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT; + + guard(mutex)(&arena->lock); + + pgoff = compute_pgoff(arena, uaddr); + /* clear range */ + mtree_store_range(&arena->mt, pgoff, pgoff + page_cnt - 1, NULL, GFP_KERNEL); + + if (page_cnt > 1) + /* bulk zap if multiple pages being freed */ + zap_pages(arena, full_uaddr, page_cnt); + + kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr; + for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) { + page = vmalloc_to_page((void *)kaddr); + if (!page) + continue; + if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ + zap_pages(arena, full_uaddr, 1); + vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); + __free_page(page); + } +} + +__bpf_kfunc_start_defs(); + +__bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt, + int node_id, u64 flags) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt) + return NULL; + + return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id); +} + +__bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign) + return; + arena_free_pages(arena, (long)ptr__ign, page_cnt); +} +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(arena_kfuncs) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_KFUNCS_END(arena_kfuncs) + +static const struct btf_kfunc_id_set common_kfunc_set = { + .owner = THIS_MODULE, + .set = &arena_kfuncs, +}; + +static int __init kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); +} +late_initcall(kfunc_init); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 134b7979f537..a8ecf69c7754 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2976,6 +2976,17 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, { } +/* for configs without MMU or 32-bit */ +__weak const struct bpf_map_ops arena_map_ops; +__weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return 0; +} +__weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return 0; +} + #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f63f4da4db5e..67923e41a07e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -164,6 +164,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || @@ -479,6 +480,39 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + unsigned long nr_pages, struct page **pages) +{ + unsigned long i, j; + struct page *pg; + int ret = 0; +#ifdef CONFIG_MEMCG_KMEM + struct mem_cgroup *memcg, *old_memcg; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); +#endif + for (i = 0; i < nr_pages; i++) { + pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); + + if (pg) { + pages[i] = pg; + continue; + } + for (j = 0; j < i; j++) + __free_page(pages[j]); + ret = -ENOMEM; + break; + } + +#ifdef CONFIG_MEMCG_KMEM + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +#endif + return ret; +} + + static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; @@ -1176,6 +1210,7 @@ static int map_create(union bpf_attr *attr) } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; @@ -1265,6 +1300,7 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_ARENA: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bf084c693507..fbcf2e5e635a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18108,6 +18108,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_ARENA: break; default: verbose(env, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 85ec7fc799d7..e30d943db8a4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1009,6 +1009,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, __MAX_BPF_MAP_TYPE }; @@ -1396,6 +1397,12 @@ enum { /* BPF token FD is passed in a corresponding command's token_fd field */ BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), }; /* Flags for BPF_PROG_QUERY. */ @@ -1467,6 +1474,9 @@ union bpf_attr { * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the * number of hash functions (if 0, the bloom filter will default * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. */ __u64 map_extra; -- cgit v1.2.3 From 667a86ad9b71d934c444eec193cf3508016f35c5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 7 Mar 2024 17:08:00 -0800 Subject: bpf: Disasm support for addr_space_cast instruction. LLVM generates rX = addr_space_cast(rY, dst_addr_space, src_addr_space) instruction when pointers in non-zero address space are used by the bpf program. Recognize this insn in uapi and in bpf disassembler. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/bpf/20240308010812.89848-3-alexei.starovoitov@gmail.com --- include/uapi/linux/bpf.h | 4 ++++ kernel/bpf/disasm.c | 10 ++++++++++ tools/include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e30d943db8a4..3c42b9f1bada 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1339,6 +1339,10 @@ enum { */ #define BPF_PSEUDO_KFUNC_CALL 2 +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + /* flags for BPF_MAP_UPDATE_ELEM command */ enum { BPF_ANY = 0, /* create new element or update existing */ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 82b2dbdd048f..bd2e2dd04740 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -166,6 +166,12 @@ static bool is_movsx(const struct bpf_insn *insn) (insn->off == 8 || insn->off == 16 || insn->off == 32); } +static bool is_addr_space_cast(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST; +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -184,6 +190,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); + } else if (is_addr_space_cast(insn)) { + verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %d, %d)\n", + insn->code, insn->dst_reg, + insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e30d943db8a4..3c42b9f1bada 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1339,6 +1339,10 @@ enum { */ #define BPF_PSEUDO_KFUNC_CALL 2 +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + /* flags for BPF_MAP_UPDATE_ELEM command */ enum { BPF_ANY = 0, /* create new element or update existing */ -- cgit v1.2.3 From eaf657f7adba8984509db7403ac6bdaa219e5722 Mon Sep 17 00:00:00 2001 From: William Tu Date: Sun, 10 Mar 2024 16:55:03 +0200 Subject: devlink: Add comments to use netlink gen tool Add the comment to remind people not to manually modify the net/devlink/netlink_gen.c, but to use tools/net/ynl/ynl-regen.sh to generate it. Signed-off-by: William Tu Suggested-by: Jiri Pirko Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20240310145503.32721-1-witu@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/devlink.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 130cae0d3e20..2da0c7eb6710 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -614,7 +614,10 @@ enum devlink_attr { DEVLINK_ATTR_REGION_DIRECT, /* flag */ - /* add new attributes above here, update the policy in devlink.c */ + /* Add new attributes above here, update the spec in + * Documentation/netlink/specs/devlink.yaml and re-generate + * net/devlink/netlink_gen.c. + */ __DEVLINK_ATTR_MAX, DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1 -- cgit v1.2.3 From cfeb98b95fff25c442f78a6f616c627bc48a26b7 Mon Sep 17 00:00:00 2001 From: Gergo Koteles Date: Sun, 10 Mar 2024 12:31:41 +0100 Subject: Input: allocate keycode for Display refresh rate toggle MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Newer Lenovo Yogas and Legions with 60Hz/90Hz displays send a wmi event when Fn + R is pressed. This is intended for use to switch between the two refresh rates. Allocate a new KEY_REFRESH_RATE_TOGGLE keycode for it. Signed-off-by: Gergo Koteles Acked-by: Dmitry Torokhov Link: https://lore.kernel.org/r/15a5d08c84cf4d7b820de34ebbcf8ae2502fb3ca.1710065750.git.soyer@irl.hu Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- include/uapi/linux/input-event-codes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 022a520e31fc..03edf2ccdf6c 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ -- cgit v1.2.3 From 64805e4039f1687b9857034123a9ec10bb9abddd Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 22 Feb 2024 00:18:05 +0000 Subject: tracing/user_events: Introduce multi-format events Currently user_events supports 1 event with the same name and must have the exact same format when referenced by multiple programs. This opens an opportunity for malicious or poorly thought through programs to create events that others use with different formats. Another scenario is user programs wishing to use the same event name but add more fields later when the software updates. Various versions of a program may be running side-by-side, which is prevented by the current single format requirement. Add a new register flag (USER_EVENT_REG_MULTI_FORMAT) which indicates the user program wishes to use the same user_event name, but may have several different formats of the event. When this flag is used, create the underlying tracepoint backing the user_event with a unique name per-version of the format. It's important that existing ABI users do not get this logic automatically, even if one of the multi format events matches the format. This ensures existing programs that create events and assume the tracepoint name will match exactly continue to work as expected. Add logic to only check multi-format events with other multi-format events and single-format events to only check single-format events during find. Change system name of the multi-format event tracepoint to ensure that multi-format events are isolated completely from single-format events. This prevents single-format names from conflicting with multi-format events if they end with the same suffix as the multi-format events. Add a register_name (reg_name) to the user_event struct which allows for split naming of events. We now have the name that was used to register within user_events as well as the unique name for the tracepoint. Upon registering events ensure matches based on first the reg_name, followed by the fields and format of the event. This allows for multiple events with the same registered name to have different formats. The underlying tracepoint will have a unique name in the format of {reg_name}.{unique_id}. For example, if both "test u32 value" and "test u64 value" are used with the USER_EVENT_REG_MULTI_FORMAT the system would have 2 unique tracepoints. The dynamic_events file would then show the following: u:test u64 count u:test u32 count The actual tracepoint names look like this: test.0 test.1 Both would be under the new user_events_multi system name to prevent the older ABI from being used to squat on multi-formatted events and block their use. Deleting events via "!u:test u64 count" would only delete the first tracepoint that matched that format. When the delete ABI is used all events with the same name will be attempted to be deleted. If per-version deletion is required, user programs should either not use persistent events or delete them via dynamic_events. Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-3-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 6 ++- kernel/trace/trace_events_user.c | 102 ++++++++++++++++++++++++++++++++++----- 2 files changed, 95 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index f74f3aedd49c..a03de03dccbc 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -12,6 +12,7 @@ #include #define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_MULTI_SYSTEM "user_events_multi" #define USER_EVENTS_PREFIX "u:" /* Create dynamic location entry within a 32-bit value */ @@ -22,8 +23,11 @@ enum user_reg_flag { /* Event will not delete upon last reference closing */ USER_EVENT_REG_PERSIST = 1U << 0, + /* Event will be allowed to have multiple formats */ + USER_EVENT_REG_MULTI_FORMAT = 1U << 1, + /* This value or above is currently non-ABI */ - USER_EVENT_REG_MAX = 1U << 1, + USER_EVENT_REG_MAX = 1U << 2, }; /* diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index fce5ed5fec50..70d428c394b6 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -34,7 +34,8 @@ /* Limit how long of an event name plus args within the subsystem. */ #define MAX_EVENT_DESC 512 -#define EVENT_NAME(user_event) ((user_event)->tracepoint.name) +#define EVENT_NAME(user_event) ((user_event)->reg_name) +#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 /* @@ -54,10 +55,13 @@ * allows isolation for events by various means. */ struct user_event_group { - char *system_name; - struct hlist_node node; - struct mutex reg_mutex; + char *system_name; + char *system_multi_name; + struct hlist_node node; + struct mutex reg_mutex; DECLARE_HASHTABLE(register_table, 8); + /* ID that moves forward within the group for multi-event names */ + u64 multi_id; }; /* Group for init_user_ns mapping, top-most group */ @@ -78,6 +82,7 @@ static unsigned int current_user_events; */ struct user_event { struct user_event_group *group; + char *reg_name; struct tracepoint tracepoint; struct trace_event_call call; struct trace_event_class class; @@ -127,6 +132,8 @@ struct user_event_enabler { #define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) +#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT) + /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { struct work_struct work; @@ -330,6 +337,7 @@ out: static void user_event_group_destroy(struct user_event_group *group) { kfree(group->system_name); + kfree(group->system_multi_name); kfree(group); } @@ -348,6 +356,11 @@ static char *user_event_group_system_name(void) return system_name; } +static char *user_event_group_system_multi_name(void) +{ + return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL); +} + static struct user_event_group *current_user_event_group(void) { return init_group; @@ -367,6 +380,11 @@ static struct user_event_group *user_event_group_create(void) if (!group->system_name) goto error; + group->system_multi_name = user_event_group_system_multi_name(); + + if (!group->system_multi_name) + goto error; + mutex_init(&group->reg_mutex); hash_init(group->register_table); @@ -1482,6 +1500,11 @@ static int destroy_user_event(struct user_event *user) hash_del(&user->node); user_event_destroy_validators(user); + + /* If we have different names, both must be freed */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user->call.print_fmt); kfree(EVENT_NAME(user)); kfree(user); @@ -1504,12 +1527,24 @@ static struct user_event *find_user_event(struct user_event_group *group, *outkey = key; hash_for_each_possible(group->register_table, user, node, key) { + /* + * Single-format events shouldn't return multi-format + * events. Callers expect the underlying tracepoint to match + * the name exactly in these cases. Only check like-formats. + */ + if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags)) + continue; + if (strcmp(EVENT_NAME(user), name)) continue; if (user_fields_match(user, argc, argv)) return user_event_get(user); + /* Scan others if this is a multi-format event */ + if (EVENT_MULTI_FORMAT(flags)) + continue; + return ERR_PTR(-EADDRINUSE); } @@ -1889,8 +1924,12 @@ static bool user_event_match(const char *system, const char *event, struct user_event *user = container_of(ev, struct user_event, devent); bool match; - match = strcmp(EVENT_NAME(user), event) == 0 && - (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); + match = strcmp(EVENT_NAME(user), event) == 0; + + if (match && system) { + match = strcmp(system, user->group->system_name) == 0 || + strcmp(system, user->group->system_multi_name) == 0; + } if (match) match = user_fields_match(user, argc, argv); @@ -1923,6 +1962,33 @@ static int user_event_trace_register(struct user_event *user) return ret; } +static int user_event_set_tp_name(struct user_event *user) +{ + lockdep_assert_held(&user->group->reg_mutex); + + if (EVENT_MULTI_FORMAT(user->reg_flags)) { + char *multi_name; + + multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx", + user->reg_name, user->group->multi_id); + + if (!multi_name) + return -ENOMEM; + + user->call.name = multi_name; + user->tracepoint.name = multi_name; + + /* Inc to ensure unique multi-event name next time */ + user->group->multi_id++; + } else { + /* Non Multi-format uses register name */ + user->call.name = user->reg_name; + user->tracepoint.name = user->reg_name; + } + + return 0; +} + /* * Parses the event name, arguments and flags then registers if successful. * The name buffer lifetime is owned by this method for success cases only. @@ -1985,7 +2051,13 @@ static int user_event_parse(struct user_event_group *group, char *name, INIT_LIST_HEAD(&user->validators); user->group = group; - user->tracepoint.name = name; + user->reg_name = name; + user->reg_flags = reg_flags; + + ret = user_event_set_tp_name(user); + + if (ret) + goto put_user; ret = user_event_parse_fields(user, args); @@ -1999,11 +2071,14 @@ static int user_event_parse(struct user_event_group *group, char *name, user->call.data = user; user->call.class = &user->class; - user->call.name = name; user->call.flags = TRACE_EVENT_FL_TRACEPOINT; user->call.tp = &user->tracepoint; user->call.event.funcs = &user_event_funcs; - user->class.system = group->system_name; + + if (EVENT_MULTI_FORMAT(user->reg_flags)) + user->class.system = group->system_multi_name; + else + user->class.system = group->system_name; user->class.fields_array = user_event_fields_array; user->class.get_fields = user_event_get_fields; @@ -2025,8 +2100,6 @@ static int user_event_parse(struct user_event_group *group, char *name, if (ret) goto put_user_lock; - user->reg_flags = reg_flags; - if (user->reg_flags & USER_EVENT_REG_PERSIST) { /* Ensure we track self ref and caller ref (2) */ refcount_set(&user->refcnt, 2); @@ -2050,6 +2123,11 @@ put_user: user_event_destroy_fields(user); user_event_destroy_validators(user); kfree(user->call.print_fmt); + + /* Caller frees reg_name on error, but not multi-name */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user); return ret; } @@ -2639,7 +2717,7 @@ static int user_seq_show(struct seq_file *m, void *p) hash_for_each(group->register_table, i, user, node) { status = user->status; - seq_printf(m, "%s", EVENT_NAME(user)); + seq_printf(m, "%s", EVENT_TP_NAME(user)); if (status != 0) seq_puts(m, " #"); -- cgit v1.2.3 From ec6ecb844d14d38b7dae8beb74e3d65db9c7b3e6 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Jan 2024 23:20:39 +0000 Subject: virtio: uapi: Drop __packed attribute in linux/virtio_pci.h Commit 92792ac752aa ("virtio-pci: Introduce admin command sending function") added "__packed" structures to UAPI header linux/virtio_pci.h. This triggers build failures in the consumer userspace applications without proper "definition" of __packed (e.g., kvmtool build fails). Moreover, the structures are already packed well, and doesn't need explicit packing, similar to the rest of the structures in all virtio_* headers. Remove the __packed attribute. Fixes: 92792ac752aa ("virtio-pci: Introduce admin command sending function") Cc: Feng Liu Cc: Michael S. Tsirkin Cc: Yishai Hadas Cc: Alex Williamson Cc: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Acked-by: Michael S. Tsirkin Signed-off-by: Suzuki K Poulose Message-Id: <20240125232039.913606-1-suzuki.poulose@arm.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_pci.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index ef3810dee7ef..a8208492e822 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -240,7 +240,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 #define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 -struct __packed virtio_admin_cmd_hdr { +struct virtio_admin_cmd_hdr { __le16 opcode; /* * 1 - SR-IOV @@ -252,20 +252,20 @@ struct __packed virtio_admin_cmd_hdr { __le64 group_member_id; }; -struct __packed virtio_admin_cmd_status { +struct virtio_admin_cmd_status { __le16 status; __le16 status_qualifier; /* Unused, reserved for future extensions. */ __u8 reserved2[4]; }; -struct __packed virtio_admin_cmd_legacy_wr_data { +struct virtio_admin_cmd_legacy_wr_data { __u8 offset; /* Starting offset of the register(s) to write. */ __u8 reserved[7]; __u8 registers[]; }; -struct __packed virtio_admin_cmd_legacy_rd_data { +struct virtio_admin_cmd_legacy_rd_data { __u8 offset; /* Starting offset of the register(s) to read. */ }; @@ -275,7 +275,7 @@ struct __packed virtio_admin_cmd_legacy_rd_data { #define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 -struct __packed virtio_admin_cmd_notify_info_data { +struct virtio_admin_cmd_notify_info_data { __u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */ __u8 bar; /* BAR of the member or the owner device */ __u8 padding[6]; -- cgit v1.2.3 From 1496c47065f9f8413296780c63374daee9bdae20 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Sat, 3 Feb 2024 00:38:56 +0800 Subject: vhost-vdpa: uapi to support reporting per vq size The size of a virtqueue is a per vq configuration. This commit introduce a new ioctl uAPI to support this flexibility. Signed-off-by: Zhu Lingshan Message-Id: <20240202163905.8834-2-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 649560c685f1..bea697390613 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -227,4 +227,11 @@ */ #define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ struct vhost_vring_state) + +/* Get the queue size of a specific virtqueue. + * userspace set the vring index in vhost_vring_state.index + * kernel set the queue size in vhost_vring_state.num + */ +#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x80, \ + struct vhost_vring_state) #endif -- cgit v1.2.3 From c2475a9a789721bfdcc1b16aaf61ccfecb891914 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:57 +0800 Subject: vDPA: report virtio-block capacity to user space This commit allows userspace to query capacity of a virtio-block device. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-2-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 1 + include/uapi/linux/vdpa.h | 2 ++ 3 files changed, 38 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index c73c06102e7e..613bec31f59e 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -944,6 +944,38 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms return vdpa_dev_net_mq_config_fill(msg, features_device, &config); } +static int +vdpa_dev_blk_capacity_config_fill(struct sk_buff *msg, + const struct virtio_blk_config *config) +{ + u64 val_u64; + + val_u64 = __virtio64_to_cpu(true, config->capacity); + + return nla_put_u64_64bit(msg, VDPA_ATTR_DEV_BLK_CFG_CAPACITY, + val_u64, VDPA_ATTR_PAD); +} + +static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg) +{ + struct virtio_blk_config config = {}; + u64 features_device; + + vdev->config->get_config(vdev, 0, &config, sizeof(config)); + + features_device = vdev->config->get_device_features(vdev); + + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device, + VDPA_ATTR_PAD)) + return -EMSGSIZE; + + if (vdpa_dev_blk_capacity_config_fill(msg, &config)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) @@ -988,6 +1020,9 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, case VIRTIO_ID_NET: err = vdpa_dev_net_config_fill(vdev, msg); break; + case VIRTIO_ID_BLOCK: + err = vdpa_dev_blk_config_fill(vdev, msg); + break; default: err = -EOPNOTSUPP; break; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 4097e8e92860..7977ca03ac7a 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -7,6 +7,7 @@ #include #include #include +#include #include /** diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 54b649ab0f22..1bf69226cb96 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -56,6 +56,8 @@ enum vdpa_attr { /* virtio features that are provisioned to the vDPA device */ VDPA_ATTR_DEV_FEATURES, /* u64 */ + VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From 330b8aea692410fbe8f0d058e01aea2986613ff7 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:58 +0800 Subject: vDPA: report virtio-block max segment size to user space This commit allows reporting the max size of any single segment of virtio-block devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-3-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 17 +++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 613bec31f59e..db355d4683ba 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -956,6 +956,20 @@ vdpa_dev_blk_capacity_config_fill(struct sk_buff *msg, val_u64, VDPA_ATTR_PAD); } +static int +vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_SIZE_MAX)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->size_max); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -973,6 +987,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_capacity_config_fill(msg, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_seg_size_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 1bf69226cb96..586bce3c906a 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -57,6 +57,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_FEATURES, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ + VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 3a1d33fb7e5f96471aa7bfe97dd09afc2aa03b39 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:59 +0800 Subject: vDPA: report virtio-block block-size to user space This commit allows reporting the block size of a virtio-block device to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-4-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 18 ++++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index db355d4683ba..d96dc2ad48aa 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -970,6 +970,21 @@ vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32); } +/* fill the block size*/ +static int +vdpa_dev_blk_block_size_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_BLK_SIZE)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->blk_size); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -990,6 +1005,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_seg_size_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_block_size_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 586bce3c906a..f3baf7ea7d6d 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -58,6 +58,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 81f64e1d911550832b8065631c28c87c96ffca36 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:00 +0800 Subject: vDPA: report virtio-block max segments in a request to user space This commit allows vDPA reporting the maximum number of segments in a request of virtio-block devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-5-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 17 +++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index d96dc2ad48aa..3e3c84bd0337 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -985,6 +985,20 @@ vdpa_dev_blk_block_size_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, val_u32); } +static int +vdpa_dev_blk_seg_max_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_SEG_MAX)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->seg_max); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1008,6 +1022,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_block_size_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_seg_max_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index f3baf7ea7d6d..2dc92fca2052 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -59,6 +59,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 54fb04b02efd8f56e388443d5f9e03e68eef48e6 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:01 +0800 Subject: vDPA: report virtio-block MQ info to user space This commits allows vDPA reporting virtio-block multi-queue configuration to user sapce. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-6-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 16 ++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 3e3c84bd0337..4c348da1f2f7 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -999,6 +999,19 @@ vdpa_dev_blk_seg_max_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, val_u32); } +static int vdpa_dev_blk_mq_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u16 val_u16; + + if ((features & BIT_ULL(VIRTIO_BLK_F_MQ)) == 0) + return 0; + + val_u16 = __virtio16_to_cpu(true, config->num_queues); + + return nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, val_u16); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1025,6 +1038,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_seg_max_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_mq_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 2dc92fca2052..3c8e3c87a864 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -60,6 +60,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From c9d989b4ababe3ec7291b204f365eaadec0afa26 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:02 +0800 Subject: vDPA: report virtio-block topology info to user space This commit allows vDPA reporting topology information of virtio-blk devices to user space, includes: 1) the number of logical blocks per physical block 2) offset of first aligned logical block 3) suggested minimum I/O size in blocks 4) optimal (suggested maximum) I/O size in blocks Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-7-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 32 ++++++++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 4 ++++ 2 files changed, 36 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 4c348da1f2f7..76b2e31d6229 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1012,6 +1012,35 @@ static int vdpa_dev_blk_mq_config_fill(struct sk_buff *msg, u64 features, return nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, val_u16); } +static int vdpa_dev_blk_topology_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u16 min_io_size; + u32 opt_io_size; + + if ((features & BIT_ULL(VIRTIO_BLK_F_TOPOLOGY)) == 0) + return 0; + + min_io_size = __virtio16_to_cpu(true, config->min_io_size); + opt_io_size = __virtio32_to_cpu(true, config->opt_io_size); + + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_PHY_BLK_EXP, + config->physical_block_exp)) + return -EMSGSIZE; + + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, + config->alignment_offset)) + return -EMSGSIZE; + + if (nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, min_io_size)) + return -EMSGSIZE; + + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, opt_io_size)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1041,6 +1070,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_mq_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_topology_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 3c8e3c87a864..5cc70614c97a 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -61,6 +61,10 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ + VDPA_ATTR_DEV_BLK_CFG_PHY_BLK_EXP, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, /* u16 */ + VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 65848f46e1d6c01fbd0d79a1c051d978a6e6002e Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:03 +0800 Subject: vDPA: report virtio-block discarding configuration to user space This commit reports virtio-blk discarding configuration to user space,includes: 1) the maximum discard sectors 2) maximum number of discard segments for the block driver to use 3) the alignment for splitting a discarding request Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-8-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 26 ++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 3 +++ 2 files changed, 29 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 76b2e31d6229..9348818b8bf9 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1041,6 +1041,29 @@ static int vdpa_dev_blk_topology_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int vdpa_dev_blk_discard_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_DISCARD)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->max_discard_sectors); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->max_discard_seg); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->discard_sector_alignment); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN, val_u32)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1073,6 +1096,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_topology_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_discard_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 5cc70614c97a..30887931a220 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -65,6 +65,9 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, /* u8 */ VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, /* u16 */ VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 6bdc7846e627ec21fc79a6d2554f69546a7b4985 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:04 +0800 Subject: vDPA: report virtio-block write zeroes configuration to user space This commits reports write zeroes configuration of virtio-block devices to user space, includes: 1)maximum write zeroes sectors size 2)maximum write zeroes segment number Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-9-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 23 +++++++++++++++++++++++ include/uapi/linux/vdpa.h | 2 ++ 2 files changed, 25 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 9348818b8bf9..bcea9f880042 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1064,6 +1064,26 @@ static int vdpa_dev_blk_discard_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int +vdpa_dev_blk_write_zeroes_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_WRITE_ZEROES)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->max_write_zeroes_sectors); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->max_write_zeroes_seg); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, val_u32)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1099,6 +1119,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_discard_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_write_zeroes_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 30887931a220..797d5708492f 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -68,6 +68,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From ae1374b7f72c973631ce881a654664fd2b40c4b9 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:05 +0800 Subject: vDPA: report virtio-block read-only info to user space This commit report read-only information of virtio-blk devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-10-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 14 ++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index bcea9f880042..2d02ea60af0c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1084,6 +1084,17 @@ vdpa_dev_blk_write_zeroes_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) +{ + u8 ro; + + ro = ((features & BIT_ULL(VIRTIO_BLK_F_RO)) == 0) ? 0 : 1; + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, ro)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1122,6 +1133,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_write_zeroes_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_ro_config_fill(msg, features_device)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 797d5708492f..4be8e3a15874 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -70,6 +70,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 1ac61ddfee93278f87370f6c43ed669b845f9037 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:06 +0800 Subject: vDPA: report virtio-blk flush info to user space This commit reports whether a virtio-blk device support cache flush command to user space Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-11-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 14 ++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 2d02ea60af0c..b246067e074b 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1095,6 +1095,17 @@ static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) return 0; } +static int vdpa_dev_blk_flush_config_fill(struct sk_buff *msg, u64 features) +{ + u8 flush; + + flush = ((features & BIT_ULL(VIRTIO_BLK_F_FLUSH)) == 0) ? 0 : 1; + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_FLUSH, flush)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1136,6 +1147,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_ro_config_fill(msg, features_device)) return -EMSGSIZE; + if (vdpa_dev_blk_flush_config_fill(msg, features_device)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 4be8e3a15874..43c51698195c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -71,6 +71,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_FLUSH, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 429846b4b6ce9853e0d803a2357bb2e55083adf0 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Sat, 23 Mar 2024 17:41:55 +0900 Subject: scsi: mpi3mr: Avoid memcpy field-spanning write WARNING When the "storcli2 show" command is executed for eHBA-9600, mpi3mr driver prints this WARNING message: memcpy: detected field-spanning write (size 128) of single field "bsg_reply_buf->reply_buf" at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 (size 1) WARNING: CPU: 0 PID: 12760 at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 mpi3mr_bsg_request+0x6b12/0x7f10 [mpi3mr] The cause of the WARN is 128 bytes memcpy to the 1 byte size array "__u8 replay_buf[1]" in the struct mpi3mr_bsg_in_reply_buf. The array is intended to be a flexible length array, so the WARN is a false positive. To suppress the WARN, remove the constant number '1' from the array declaration and clarify that it has flexible length. Also, adjust the memory allocation size to match the change. Suggested-by: Sathya Prakash Veerichetty Signed-off-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/20240323084155.166835-1-shinichiro.kawasaki@wdc.com Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_app.c | 2 +- include/uapi/scsi/scsi_bsg_mpi3mr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 0380996b5ad2..55d590b91947 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -1644,7 +1644,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if ((mpirep_offset != 0xFF) && drv_bufs[mpirep_offset].bsg_buf_len) { drv_buf_iter = &drv_bufs[mpirep_offset]; - drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) - 1 + + drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) + mrioc->reply_sz); bsg_reply_buf = kzalloc(drv_buf_iter->kern_buf_len, GFP_KERNEL); diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index c72ce387286a..30a5c1a59376 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -382,7 +382,7 @@ struct mpi3mr_bsg_in_reply_buf { __u8 mpi_reply_type; __u8 rsvd1; __u16 rsvd2; - __u8 reply_buf[1]; + __u8 reply_buf[]; }; /** -- cgit v1.2.3 From 462a7c0f8e3f833e5ca3dd3f427882b60b3f38e9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 26 Mar 2024 10:30:55 +0100 Subject: drm/panthor: Fix wrong kernel-doc format in the uAPI header The kernel doc prefix is /** not /*. Reported-by: Stephen Rothwell Signed-off-by: Boris Brezillon Acked-by: Liviu Dudau Link: https://patchwork.freedesktop.org/patch/msgid/20240326093055.411932-1-boris.brezillon@collabora.com --- include/uapi/drm/panthor_drm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index 373df80f41ed..dadb05ab1235 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -336,10 +336,10 @@ struct drm_panthor_gpu_info { /** @tiler_present: Bitmask encoding the tiler units exposed by the GPU. */ __u64 tiler_present; - /* @core_features: Used to discriminate core variants when they exist. */ + /** @core_features: Used to discriminate core variants when they exist. */ __u32 core_features; - /* @pad: MBZ. */ + /** @pad: MBZ. */ __u32 pad; }; -- cgit v1.2.3 From 0cac183b98d8a8c692c98e8dba37df15a9e9210d Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Fri, 1 Mar 2024 12:25:17 -0500 Subject: drm/amdkfd: range check cp bad op exception interrupts Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well. Signed-off-by: Jonathan Kim Tested-by: Jesse Zhang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c | 3 ++- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c | 3 ++- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 3 ++- include/uapi/linux/kfd_ioctl.h | 17 ++++++++++++++--- 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index 9a06c6fb6605..40a21be6c07c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index 7e2859736a55..fe2ad0c0de95 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev, /* CP */ if (source_id == SOC15_INTSRC_CP_END_OF_PIPE) kfd_signal_event_interrupt(pasid, context_id0, 32); - else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) + else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0))) kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 91dd5e045b51..c4c6a29052ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, sq_int_data, 24); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 9ce46edc62a5..2040a470ddb4 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -913,14 +913,25 @@ enum kfd_dbg_trap_exception_code { KFD_EC_MASK(EC_DEVICE_NEW)) #define KFD_EC_MASK_PROCESS (KFD_EC_MASK(EC_PROCESS_RUNTIME) | \ KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE)) +#define KFD_EC_MASK_PACKET (KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED)) /* Checks for exception code types for KFD search */ +#define KFD_DBG_EC_IS_VALID(ecode) (ecode > EC_NONE && ecode < EC_MAX) #define KFD_DBG_EC_TYPE_IS_QUEUE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) #define KFD_DBG_EC_TYPE_IS_DEVICE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) #define KFD_DBG_EC_TYPE_IS_PROCESS(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) +#define KFD_DBG_EC_TYPE_IS_PACKET(ecode) \ + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PACKET)) /* Runtime enable states */ -- cgit v1.2.3