From 79462faa2b2aa89db029af5e61df11b5bb6ef4e3 Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Sat, 22 Feb 2025 09:42:23 +0800 Subject: KVM: TDX: Handle TDG.VP.VMCALL Convert TDG.VP.VMCALL to KVM_EXIT_SYSTEM_EVENT with a new type KVM_SYSTEM_EVENT_TDX_FATAL and forward it to userspace for handling. TD guest can use TDG.VP.VMCALL to report the fatal error it has experienced. This hypercall is special because TD guest is requesting a termination with the error information, KVM needs to forward the hypercall to userspace anyway, KVM doesn't do parsing or conversion, it just dumps the 16 general-purpose registers to userspace and let userspace decide what to do. Signed-off-by: Binbin Wu Message-ID: <20250222014225.897298-8-binbin.wu@linux.intel.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 45e6d8fca9b9..937400350317 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -375,6 +375,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_WAKEUP 4 #define KVM_SYSTEM_EVENT_SUSPEND 5 #define KVM_SYSTEM_EVENT_SEV_TERM 6 +#define KVM_SYSTEM_EVENT_TDX_FATAL 7 __u32 type; __u32 ndata; union { -- cgit v1.2.3 From d499effe1d55552ac701e90fbd17ca418b2189df Mon Sep 17 00:00:00 2001 From: Aaron Ruby Date: Thu, 27 Mar 2025 15:25:49 +0000 Subject: drm/virtio: Add capset definitions to UAPI Since the context-type additions to the virtio-gpu spec, these have been defined locally in guest user-space, and virtio-gpu backend library code. Now, these capsets have been stabilized, and should be defined in a common space, in both the virtio_gpu header, and alongside the virtgpu_drm interface that they apply to. Reviewed-by: Gurchetan Singh Signed-off-by: Aaron Ruby Signed-off-by: Dmitry Osipenko [dmitry.osipenko@collabora.com: edit commit title] Link: https://patchwork.freedesktop.org/patch/msgid/YT3PR01MB5857E808EDF6949F2DF517FDAFA12@YT3PR01MB5857.CANPRD01.PROD.OUTLOOK.COM --- include/uapi/drm/virtgpu_drm.h | 6 ++++++ include/uapi/linux/virtio_gpu.h | 3 ++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index c2ce71987e9b..9debb320c34b 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -163,6 +163,12 @@ struct drm_virtgpu_3d_wait { __u32 flags; }; +#define VIRTGPU_DRM_CAPSET_VIRGL 1 +#define VIRTGPU_DRM_CAPSET_VIRGL2 2 +#define VIRTGPU_DRM_CAPSET_GFXSTREAM_VULKAN 3 +#define VIRTGPU_DRM_CAPSET_VENUS 4 +#define VIRTGPU_DRM_CAPSET_CROSS_DOMAIN 5 +#define VIRTGPU_DRM_CAPSET_DRM 6 struct drm_virtgpu_get_caps { __u32 cap_set_id; __u32 cap_set_ver; diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index bf2c9cabd207..be109777d10d 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -309,8 +309,9 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 -/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_GFXSTREAM_VULKAN 3 #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_CROSS_DOMAIN 5 #define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ -- cgit v1.2.3 From 62aa5790cec89108a23052cc2f00fdd31f9adbac Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Mon, 31 Mar 2025 20:36:17 +0000 Subject: bpf: Fix a comment describing bpf_attr The map_fd field of the bpf_attr union is used in the BPF_MAP_FREEZE syscall. Explicitly mention this in the comments. Signed-off-by: Anton Protopopov Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20250331203618.1973691-2-a.s.protopopov@gmail.com --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 28705ae67784..07ee73cdf97b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1506,7 +1506,7 @@ union bpf_attr { __s32 map_token_fd; }; - struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */ __u32 map_fd; __aligned_u64 key; union { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 28705ae67784..07ee73cdf97b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1506,7 +1506,7 @@ union bpf_attr { __s32 map_token_fd; }; - struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */ __u32 map_fd; __aligned_u64 key; union { -- cgit v1.2.3 From ad2698efce37e910dcf3c3914263e6cb3e86f8cd Mon Sep 17 00:00:00 2001 From: Nas Chung Date: Thu, 25 Jul 2024 15:10:32 +0900 Subject: media: uapi: v4l: Change V4L2_TYPE_IS_CAPTURE condition Explicitly compare a buffer type only with valid buffer types, to avoid matching a buffer type outside of the valid buffer type set. Signed-off-by: Nas Chung Reviewed-by: Michael Tretter Signed-off-by: Sebastian Fricke Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c8cb2796130f..ccd6ad53432e 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -153,10 +153,18 @@ enum v4l2_buf_type { V4L2_BUF_TYPE_SDR_OUTPUT = 12, V4L2_BUF_TYPE_META_CAPTURE = 13, V4L2_BUF_TYPE_META_OUTPUT = 14, + /* + * Note: V4L2_TYPE_IS_VALID and V4L2_TYPE_IS_OUTPUT must + * be updated if a new type is added. + */ /* Deprecated, do not use */ V4L2_BUF_TYPE_PRIVATE = 0x80, }; +#define V4L2_TYPE_IS_VALID(type) \ + ((type) >= V4L2_BUF_TYPE_VIDEO_CAPTURE &&\ + (type) <= V4L2_BUF_TYPE_META_OUTPUT) + #define V4L2_TYPE_IS_MULTIPLANAR(type) \ ((type) == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) @@ -171,7 +179,8 @@ enum v4l2_buf_type { || (type) == V4L2_BUF_TYPE_SDR_OUTPUT \ || (type) == V4L2_BUF_TYPE_META_OUTPUT) -#define V4L2_TYPE_IS_CAPTURE(type) (!V4L2_TYPE_IS_OUTPUT(type)) +#define V4L2_TYPE_IS_CAPTURE(type) \ + (V4L2_TYPE_IS_VALID(type) && !V4L2_TYPE_IS_OUTPUT(type)) enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, -- cgit v1.2.3 From f81f69a0e3da141bdd73a16b8676f4e542533d87 Mon Sep 17 00:00:00 2001 From: Nas Chung Date: Thu, 25 Jul 2024 15:10:34 +0900 Subject: media: uapi: v4l: Fix V4L2_TYPE_IS_OUTPUT condition V4L2_TYPE_IS_OUTPUT() returns true for V4L2_BUF_TYPE_VIDEO_OVERLAY which definitely belongs to CAPTURE. Signed-off-by: Nas Chung Signed-off-by: Sebastian Fricke Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index ccd6ad53432e..af86ece741e9 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -172,7 +172,6 @@ enum v4l2_buf_type { #define V4L2_TYPE_IS_OUTPUT(type) \ ((type) == V4L2_BUF_TYPE_VIDEO_OUTPUT \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE \ - || (type) == V4L2_BUF_TYPE_VIDEO_OVERLAY \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY \ || (type) == V4L2_BUF_TYPE_VBI_OUTPUT \ || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT \ -- cgit v1.2.3 From dcbe2aeda2e09eb69f5feba7e171db2836d9999d Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Tue, 25 Feb 2025 10:40:23 +0100 Subject: media: v4l2: Add NV15 and NV20 pixel formats Add NV15 and NV20 pixel formats used by the Rockchip Video Decoder for 10-bit buffers. NV15 and NV20 is 10-bit 4:2:0/4:2:2 semi-planar YUV formats similar to NV12 and NV16, using 10-bit components with no padding between each component. Instead, a group of 4 luminance/chrominance samples are stored over 5 bytes in little endian order: YYYY = UVUV = 4 * 10 bits = 40 bits = 5 bytes The '15' and '20' suffix refers to the optimum effective bits per pixel which is achieved when the total number of luminance samples is a multiple of 8 for NV15 and 4 for NV20. Signed-off-by: Jonas Karlman Reviewed-by: Nicolas Dufresne Tested-by: Nicolas Dufresne Tested-by: Christopher Obbard Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 128 +++++++++++++++++++++ drivers/media/v4l2-core/v4l2-common.c | 2 + drivers/media/v4l2-core/v4l2-ioctl.c | 2 + include/uapi/linux/videodev2.h | 2 + 4 files changed, 134 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index b788f6933855..6e4f399f1f88 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -137,6 +137,13 @@ All components are stored with the same number of bits per component. - Cb, Cr - No - Linear + * - V4L2_PIX_FMT_NV15 + - 'NV15' + - 10 + - 4:2:0 + - Cb, Cr + - Yes + - Linear * - V4L2_PIX_FMT_NV15_4L4 - 'VT15' - 15 @@ -186,6 +193,13 @@ All components are stored with the same number of bits per component. - Cr, Cb - No - Linear + * - V4L2_PIX_FMT_NV20 + - 'NV20' + - 10 + - 4:2:2 + - Cb, Cr + - Yes + - Linear * - V4L2_PIX_FMT_NV24 - 'NV24' - 8 @@ -302,6 +316,57 @@ of the luma plane. - Cr\ :sub:`11` +.. _V4L2-PIX-FMT-NV15: + +NV15 +---- + +Semi-planar 10-bit YUV 4:2:0 format similar to NV12, using 10-bit components +with no padding between each component. A group of 4 components are stored over +5 bytes in little endian order. + +.. flat-table:: Sample 4x4 NV15 Image (1 byte per cell) + :header-rows: 0 + :stub-columns: 0 + + * - start + 0: + - Y'\ :sub:`00[7:0]` + - Y'\ :sub:`01[5:0]`\ Y'\ :sub:`00[9:8]` + - Y'\ :sub:`02[3:0]`\ Y'\ :sub:`01[9:6]` + - Y'\ :sub:`03[1:0]`\ Y'\ :sub:`02[9:4]` + - Y'\ :sub:`03[9:2]` + * - start + 5: + - Y'\ :sub:`10[7:0]` + - Y'\ :sub:`11[5:0]`\ Y'\ :sub:`10[9:8]` + - Y'\ :sub:`12[3:0]`\ Y'\ :sub:`11[9:6]` + - Y'\ :sub:`13[1:0]`\ Y'\ :sub:`12[9:4]` + - Y'\ :sub:`13[9:2]` + * - start + 10: + - Y'\ :sub:`20[7:0]` + - Y'\ :sub:`21[5:0]`\ Y'\ :sub:`20[9:8]` + - Y'\ :sub:`22[3:0]`\ Y'\ :sub:`21[9:6]` + - Y'\ :sub:`23[1:0]`\ Y'\ :sub:`22[9:4]` + - Y'\ :sub:`23[9:2]` + * - start + 15: + - Y'\ :sub:`30[7:0]` + - Y'\ :sub:`31[5:0]`\ Y'\ :sub:`30[9:8]` + - Y'\ :sub:`32[3:0]`\ Y'\ :sub:`31[9:6]` + - Y'\ :sub:`33[1:0]`\ Y'\ :sub:`32[9:4]` + - Y'\ :sub:`33[9:2]` + * - start + 20: + - Cb\ :sub:`00[7:0]` + - Cr\ :sub:`00[5:0]`\ Cb\ :sub:`00[9:8]` + - Cb\ :sub:`01[3:0]`\ Cr\ :sub:`00[9:6]` + - Cr\ :sub:`01[1:0]`\ Cb\ :sub:`01[9:4]` + - Cr\ :sub:`01[9:2]` + * - start + 25: + - Cb\ :sub:`10[7:0]` + - Cr\ :sub:`10[5:0]`\ Cb\ :sub:`10[9:8]` + - Cb\ :sub:`11[3:0]`\ Cr\ :sub:`10[9:6]` + - Cr\ :sub:`11[1:0]`\ Cb\ :sub:`11[9:4]` + - Cr\ :sub:`11[9:2]` + + .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: .. _V4L2-PIX-FMT-NV12-4L4: @@ -631,6 +696,69 @@ number of lines as the luma plane. - Cr\ :sub:`32` +.. _V4L2-PIX-FMT-NV20: + +NV20 +---- + +Semi-planar 10-bit YUV 4:2:2 format similar to NV16, using 10-bit components +with no padding between each component. A group of 4 components are stored over +5 bytes in little endian order. + +.. flat-table:: Sample 4x4 NV20 Image (1 byte per cell) + :header-rows: 0 + :stub-columns: 0 + + * - start + 0: + - Y'\ :sub:`00[7:0]` + - Y'\ :sub:`01[5:0]`\ Y'\ :sub:`00[9:8]` + - Y'\ :sub:`02[3:0]`\ Y'\ :sub:`01[9:6]` + - Y'\ :sub:`03[1:0]`\ Y'\ :sub:`02[9:4]` + - Y'\ :sub:`03[9:2]` + * - start + 5: + - Y'\ :sub:`10[7:0]` + - Y'\ :sub:`11[5:0]`\ Y'\ :sub:`10[9:8]` + - Y'\ :sub:`12[3:0]`\ Y'\ :sub:`11[9:6]` + - Y'\ :sub:`13[1:0]`\ Y'\ :sub:`12[9:4]` + - Y'\ :sub:`13[9:2]` + * - start + 10: + - Y'\ :sub:`20[7:0]` + - Y'\ :sub:`21[5:0]`\ Y'\ :sub:`20[9:8]` + - Y'\ :sub:`22[3:0]`\ Y'\ :sub:`21[9:6]` + - Y'\ :sub:`23[1:0]`\ Y'\ :sub:`22[9:4]` + - Y'\ :sub:`23[9:2]` + * - start + 15: + - Y'\ :sub:`30[7:0]` + - Y'\ :sub:`31[5:0]`\ Y'\ :sub:`30[9:8]` + - Y'\ :sub:`32[3:0]`\ Y'\ :sub:`31[9:6]` + - Y'\ :sub:`33[1:0]`\ Y'\ :sub:`32[9:4]` + - Y'\ :sub:`33[9:2]` + * - start + 20: + - Cb\ :sub:`00[7:0]` + - Cr\ :sub:`00[5:0]`\ Cb\ :sub:`00[9:8]` + - Cb\ :sub:`01[3:0]`\ Cr\ :sub:`00[9:6]` + - Cr\ :sub:`01[1:0]`\ Cb\ :sub:`01[9:4]` + - Cr\ :sub:`01[9:2]` + * - start + 25: + - Cb\ :sub:`10[7:0]` + - Cr\ :sub:`10[5:0]`\ Cb\ :sub:`10[9:8]` + - Cb\ :sub:`11[3:0]`\ Cr\ :sub:`10[9:6]` + - Cr\ :sub:`11[1:0]`\ Cb\ :sub:`11[9:4]` + - Cr\ :sub:`11[9:2]` + * - start + 30: + - Cb\ :sub:`20[7:0]` + - Cr\ :sub:`20[5:0]`\ Cb\ :sub:`20[9:8]` + - Cb\ :sub:`21[3:0]`\ Cr\ :sub:`20[9:6]` + - Cr\ :sub:`21[1:0]`\ Cb\ :sub:`21[9:4]` + - Cr\ :sub:`21[9:2]` + * - start + 35: + - Cb\ :sub:`30[7:0]` + - Cr\ :sub:`30[5:0]`\ Cb\ :sub:`30[9:8]` + - Cb\ :sub:`31[3:0]`\ Cr\ :sub:`30[9:6]` + - Cr\ :sub:`31[1:0]`\ Cb\ :sub:`31[9:4]` + - Cr\ :sub:`31[9:2]` + + .. _V4L2-PIX-FMT-NV24: .. _V4L2-PIX-FMT-NV42: diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index b7e608f1145d..aa86b8c6aa75 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -277,8 +277,10 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) /* YUV planar formats */ { .format = V4L2_PIX_FMT_NV12, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 2 }, { .format = V4L2_PIX_FMT_NV21, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 2 }, + { .format = V4L2_PIX_FMT_NV15, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 5, 10, 0, 0 }, .bpp_div = { 4, 4, 1, 1 }, .hdiv = 2, .vdiv = 2 }, { .format = V4L2_PIX_FMT_NV16, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_NV61, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 1 }, + { .format = V4L2_PIX_FMT_NV20, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 5, 10, 0, 0 }, .bpp_div = { 4, 4, 1, 1 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_NV24, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_NV42, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 }, { .format = V4L2_PIX_FMT_P010, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 2, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 1 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index a16fb44c7246..e97881f74c0d 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1363,8 +1363,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_YUV48_12: descr = "12-bit YUV 4:4:4 Packed"; break; case V4L2_PIX_FMT_NV12: descr = "Y/UV 4:2:0"; break; case V4L2_PIX_FMT_NV21: descr = "Y/VU 4:2:0"; break; + case V4L2_PIX_FMT_NV15: descr = "10-bit Y/UV 4:2:0 (Packed)"; break; case V4L2_PIX_FMT_NV16: descr = "Y/UV 4:2:2"; break; case V4L2_PIX_FMT_NV61: descr = "Y/VU 4:2:2"; break; + case V4L2_PIX_FMT_NV20: descr = "10-bit Y/UV 4:2:2 (Packed)"; break; case V4L2_PIX_FMT_NV24: descr = "Y/UV 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/VU 4:4:4"; break; case V4L2_PIX_FMT_P010: descr = "10-bit Y/UV 4:2:0"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index af86ece741e9..ca7b3e8863ca 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -651,8 +651,10 @@ struct v4l2_pix_format { /* two planes -- one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12 v4l2_fourcc('N', 'V', '1', '2') /* 12 Y/CbCr 4:2:0 */ #define V4L2_PIX_FMT_NV21 v4l2_fourcc('N', 'V', '2', '1') /* 12 Y/CrCb 4:2:0 */ +#define V4L2_PIX_FMT_NV15 v4l2_fourcc('N', 'V', '1', '5') /* 15 Y/CbCr 4:2:0 10-bit packed */ #define V4L2_PIX_FMT_NV16 v4l2_fourcc('N', 'V', '1', '6') /* 16 Y/CbCr 4:2:2 */ #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ +#define V4L2_PIX_FMT_NV20 v4l2_fourcc('N', 'V', '2', '0') /* 20 Y/CbCr 4:2:2 10-bit packed */ #define V4L2_PIX_FMT_NV24 v4l2_fourcc('N', 'V', '2', '4') /* 24 Y/CbCr 4:4:4 */ #define V4L2_PIX_FMT_NV42 v4l2_fourcc('N', 'V', '4', '2') /* 24 Y/CrCb 4:4:4 */ #define V4L2_PIX_FMT_P010 v4l2_fourcc('P', '0', '1', '0') /* 24 Y/CbCr 4:2:0 10-bit per component */ -- cgit v1.2.3 From c07d3aede2b26830ee63f64d8326f6a87dee3a6d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 4 Apr 2025 15:58:59 -0700 Subject: fscrypt: add support for hardware-wrapped keys Add support for hardware-wrapped keys to fscrypt. Such keys are protected from certain attacks, such as cold boot attacks. For more information, see the "Hardware-wrapped keys" section of Documentation/block/inline-encryption.rst. To support hardware-wrapped keys in fscrypt, we allow the fscrypt master keys to be hardware-wrapped. File contents encryption is done by passing the wrapped key to the inline encryption hardware via blk-crypto. Other fscrypt operations such as filenames encryption continue to be done by the kernel, using the "software secret" which the hardware derives. For more information, see the documentation which this patch adds to Documentation/filesystems/fscrypt.rst. Note that this feature doesn't require any filesystem-specific changes. However it does depend on inline encryption support, and thus currently it is only applicable to ext4 and f2fs. The version of this feature introduced by this patch is mostly equivalent to the version that has existed downstream in the Android Common Kernels since 2020. However, a couple fixes are included. First, the flags field in struct fscrypt_add_key_arg is now placed in the proper location. Second, key identifiers for HW-wrapped keys are now derived using a distinct HKDF context byte; this fixes a bug where a raw key could have the same identifier as a HW-wrapped key. Note that as a result of these fixes, the version of this feature introduced by this patch is not UAPI or on-disk format compatible with the version in the Android Common Kernels, though the divergence is limited to just those specific fixes. This version should be used going forwards. This patch has been heavily rewritten from the original version by Gaurav Kashyap and Barani Muthukumaran . Tested-by: Bartosz Golaszewski # sm8650 Link: https://lore.kernel.org/r/20250404225859.172344-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 187 +++++++++++++++++++++++++++------- fs/crypto/fscrypt_private.h | 75 ++++++++++++-- fs/crypto/hkdf.c | 4 +- fs/crypto/inline_crypt.c | 44 ++++++-- fs/crypto/keyring.c | 132 +++++++++++++++++------- fs/crypto/keysetup.c | 63 ++++++++++-- fs/crypto/keysetup_v1.c | 4 +- include/uapi/linux/fscrypt.h | 6 +- 8 files changed, 410 insertions(+), 105 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index e80329908549..734ee38eb89b 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -70,7 +70,7 @@ Online attacks -------------- fscrypt (and storage encryption in general) can only provide limited -protection, if any at all, against online attacks. In detail: +protection against online attacks. In detail: Side-channel attacks ~~~~~~~~~~~~~~~~~~~~ @@ -99,16 +99,23 @@ Therefore, any encryption-specific access control checks would merely be enforced by kernel *code* and therefore would be largely redundant with the wide variety of access control mechanisms already available.) -Kernel memory compromise -~~~~~~~~~~~~~~~~~~~~~~~~ +Read-only kernel memory compromise +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Unless `hardware-wrapped keys`_ are used, an attacker who gains the +ability to read from arbitrary kernel memory, e.g. by mounting a +physical attack or by exploiting a kernel security vulnerability, can +compromise all fscrypt keys that are currently in-use. This also +extends to cold boot attacks; if the system is suddenly powered off, +keys the system was using may remain in memory for a short time. -An attacker who compromises the system enough to read from arbitrary -memory, e.g. by mounting a physical attack or by exploiting a kernel -security vulnerability, can compromise all encryption keys that are -currently in use. +However, if hardware-wrapped keys are used, then the fscrypt master +keys and file contents encryption keys (but not other types of fscrypt +subkeys such as filenames encryption keys) are protected from +compromises of arbitrary kernel memory. -However, fscrypt allows encryption keys to be removed from the kernel, -which may protect them from later compromise. +In addition, fscrypt allows encryption keys to be removed from the +kernel, which may protect them from later compromise. In more detail, the FS_IOC_REMOVE_ENCRYPTION_KEY ioctl (or the FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS ioctl) can wipe a master @@ -144,6 +151,24 @@ However, these ioctls have some limitations: accelerator hardware (if used by the crypto API to implement any of the algorithms), or in other places not explicitly considered here. +Full system compromise +~~~~~~~~~~~~~~~~~~~~~~ + +An attacker who gains "root" access and/or the ability to execute +arbitrary kernel code can freely exfiltrate data that is protected by +any in-use fscrypt keys. Thus, usually fscrypt provides no meaningful +protection in this scenario. (Data that is protected by a key that is +absent throughout the entire attack remains protected, modulo the +limitations of key removal mentioned above in the case where the key +was removed prior to the attack.) + +However, if `hardware-wrapped keys`_ are used, such attackers will be +unable to exfiltrate the master keys or file contents keys in a form +that will be usable after the system is powered off. This may be +useful if the attacker is significantly time-limited and/or +bandwidth-limited, so they can only exfiltrate some data and need to +rely on a later offline attack to exfiltrate the rest of it. + Limitations of v1 policies ~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -170,6 +195,10 @@ policies on all new encrypted directories. Key hierarchy ============= +Note: this section assumes the use of raw keys rather than +hardware-wrapped keys. The use of hardware-wrapped keys modifies the +key hierarchy slightly. For details, see `Hardware-wrapped keys`_. + Master Keys ----------- @@ -832,7 +861,9 @@ a pointer to struct fscrypt_add_key_arg, defined as follows:: struct fscrypt_key_specifier key_spec; __u32 raw_size; __u32 key_id; - __u32 __reserved[8]; + #define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; __u8 raw[]; }; @@ -851,7 +882,7 @@ a pointer to struct fscrypt_add_key_arg, defined as follows:: struct fscrypt_provisioning_key_payload { __u32 type; - __u32 __reserved; + __u32 flags; __u8 raw[]; }; @@ -879,24 +910,32 @@ as follows: Alternatively, if ``key_id`` is nonzero, this field must be 0, since in that case the size is implied by the specified Linux keyring key. -- ``key_id`` is 0 if the raw key is given directly in the ``raw`` - field. Otherwise ``key_id`` is the ID of a Linux keyring key of - type "fscrypt-provisioning" whose payload is - struct fscrypt_provisioning_key_payload whose ``raw`` field contains - the raw key and whose ``type`` field matches ``key_spec.type``. - Since ``raw`` is variable-length, the total size of this key's - payload must be ``sizeof(struct fscrypt_provisioning_key_payload)`` - plus the raw key size. The process must have Search permission on - this key. - - Most users should leave this 0 and specify the raw key directly. - The support for specifying a Linux keyring key is intended mainly to +- ``key_id`` is 0 if the key is given directly in the ``raw`` field. + Otherwise ``key_id`` is the ID of a Linux keyring key of type + "fscrypt-provisioning" whose payload is struct + fscrypt_provisioning_key_payload whose ``raw`` field contains the + key, whose ``type`` field matches ``key_spec.type``, and whose + ``flags`` field matches ``flags``. Since ``raw`` is + variable-length, the total size of this key's payload must be + ``sizeof(struct fscrypt_provisioning_key_payload)`` plus the number + of key bytes. The process must have Search permission on this key. + + Most users should leave this 0 and specify the key directly. The + support for specifying a Linux keyring key is intended mainly to allow re-adding keys after a filesystem is unmounted and re-mounted, - without having to store the raw keys in userspace memory. + without having to store the keys in userspace memory. + +- ``flags`` contains optional flags from ````: + + - FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED: This denotes that the key is a + hardware-wrapped key. See `Hardware-wrapped keys`_. This flag + can't be used if FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR is used. - ``raw`` is a variable-length field which must contain the actual key, ``raw_size`` bytes long. Alternatively, if ``key_id`` is - nonzero, then this field is unused. + nonzero, then this field is unused. Note that despite being named + ``raw``, if FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED is specified then it + will contain a wrapped key, not a raw key. For v2 policy keys, the kernel keeps track of which user (identified by effective user ID) added the key, and only allows the key to be @@ -908,8 +947,8 @@ prevent that other user from unexpectedly removing it. Therefore, FS_IOC_ADD_ENCRYPTION_KEY may also be used to add a v2 policy key *again*, even if it's already added by other user(s). In this case, FS_IOC_ADD_ENCRYPTION_KEY will just install a claim to the key for the -current user, rather than actually add the key again (but the raw key -must still be provided, as a proof of knowledge). +current user, rather than actually add the key again (but the key must +still be provided, as a proof of knowledge). FS_IOC_ADD_ENCRYPTION_KEY returns 0 if either the key or a claim to the key was either added or already exists. @@ -918,20 +957,23 @@ FS_IOC_ADD_ENCRYPTION_KEY can fail with the following errors: - ``EACCES``: FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR was specified, but the caller does not have the CAP_SYS_ADMIN capability in the initial - user namespace; or the raw key was specified by Linux key ID but the + user namespace; or the key was specified by Linux key ID but the process lacks Search permission on the key. +- ``EBADMSG``: invalid hardware-wrapped key - ``EDQUOT``: the key quota for this user would be exceeded by adding the key - ``EINVAL``: invalid key size or key specifier type, or reserved bits were set -- ``EKEYREJECTED``: the raw key was specified by Linux key ID, but the - key has the wrong type -- ``ENOKEY``: the raw key was specified by Linux key ID, but no key - exists with that ID +- ``EKEYREJECTED``: the key was specified by Linux key ID, but the key + has the wrong type +- ``ENOKEY``: the key was specified by Linux key ID, but no key exists + with that ID - ``ENOTTY``: this type of filesystem does not implement encryption - ``EOPNOTSUPP``: the kernel was not configured with encryption support for this filesystem, or the filesystem superblock has not - had encryption enabled on it + had encryption enabled on it; or a hardware wrapped key was specified + but the filesystem does not support inline encryption or the hardware + does not support hardware-wrapped keys Legacy method ~~~~~~~~~~~~~ @@ -994,9 +1036,8 @@ or removed by non-root users. These ioctls don't work on keys that were added via the legacy process-subscribed keyrings mechanism. -Before using these ioctls, read the `Kernel memory compromise`_ -section for a discussion of the security goals and limitations of -these ioctls. +Before using these ioctls, read the `Online attacks`_ section for a +discussion of the security goals and limitations of these ioctls. FS_IOC_REMOVE_ENCRYPTION_KEY ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -1316,7 +1357,8 @@ inline encryption hardware doesn't have the needed crypto capabilities (e.g. support for the needed encryption algorithm and data unit size) and where blk-crypto-fallback is unusable. (For blk-crypto-fallback to be usable, it must be enabled in the kernel configuration with -CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y.) +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y, and the file must be +protected by a raw key rather than a hardware-wrapped key.) Currently fscrypt always uses the filesystem block size (which is usually 4096 bytes) as the data unit size. Therefore, it can only use @@ -1324,7 +1366,76 @@ inline encryption hardware that supports that data unit size. Inline encryption doesn't affect the ciphertext or other aspects of the on-disk format, so users may freely switch back and forth between -using "inlinecrypt" and not using "inlinecrypt". +using "inlinecrypt" and not using "inlinecrypt". An exception is that +files that are protected by a hardware-wrapped key can only be +encrypted/decrypted by the inline encryption hardware and therefore +can only be accessed when the "inlinecrypt" mount option is used. For +more information about hardware-wrapped keys, see below. + +Hardware-wrapped keys +--------------------- + +fscrypt supports using *hardware-wrapped keys* when the inline +encryption hardware supports it. Such keys are only present in kernel +memory in wrapped (encrypted) form; they can only be unwrapped +(decrypted) by the inline encryption hardware and are temporally bound +to the current boot. This prevents the keys from being compromised if +kernel memory is leaked. This is done without limiting the number of +keys that can be used and while still allowing the execution of +cryptographic tasks that are tied to the same key but can't use inline +encryption hardware, e.g. filenames encryption. + +Note that hardware-wrapped keys aren't specific to fscrypt; they are a +block layer feature (part of *blk-crypto*). For more details about +hardware-wrapped keys, see the block layer documentation at +:ref:`Documentation/block/inline-encryption.rst +`. The rest of this section just focuses on +the details of how fscrypt can use hardware-wrapped keys. + +fscrypt supports hardware-wrapped keys by allowing the fscrypt master +keys to be hardware-wrapped keys as an alternative to raw keys. To +add a hardware-wrapped key with `FS_IOC_ADD_ENCRYPTION_KEY`_, +userspace must specify FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED in the +``flags`` field of struct fscrypt_add_key_arg and also in the +``flags`` field of struct fscrypt_provisioning_key_payload when +applicable. The key must be in ephemerally-wrapped form, not +long-term wrapped form. + +Some limitations apply. First, files protected by a hardware-wrapped +key are tied to the system's inline encryption hardware. Therefore +they can only be accessed when the "inlinecrypt" mount option is used, +and they can't be included in portable filesystem images. Second, +currently the hardware-wrapped key support is only compatible with +`IV_INO_LBLK_64 policies`_ and `IV_INO_LBLK_32 policies`_, as it +assumes that there is just one file contents encryption key per +fscrypt master key rather than one per file. Future work may address +this limitation by passing per-file nonces down the storage stack to +allow the hardware to derive per-file keys. + +Implementation-wise, to encrypt/decrypt the contents of files that are +protected by a hardware-wrapped key, fscrypt uses blk-crypto, +attaching the hardware-wrapped key to the bio crypt contexts. As is +the case with raw keys, the block layer will program the key into a +keyslot when it isn't already in one. However, when programming a +hardware-wrapped key, the hardware doesn't program the given key +directly into a keyslot but rather unwraps it (using the hardware's +ephemeral wrapping key) and derives the inline encryption key from it. +The inline encryption key is the key that actually gets programmed +into a keyslot, and it is never exposed to software. + +However, fscrypt doesn't just do file contents encryption; it also +uses its master keys to derive filenames encryption keys, key +identifiers, and sometimes some more obscure types of subkeys such as +dirhash keys. So even with file contents encryption out of the +picture, fscrypt still needs a raw key to work with. To get such a +key from a hardware-wrapped key, fscrypt asks the inline encryption +hardware to derive a cryptographically isolated "software secret" from +the hardware-wrapped key. fscrypt uses this "software secret" to key +its KDF to derive all subkeys other than file contents keys. + +Note that this implies that the hardware-wrapped key feature only +protects the file contents encryption keys. It doesn't protect other +fscrypt subkeys such as filenames encryption keys. Direct I/O support ================== diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 8371e4e1f596..c1d92074b65c 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -12,6 +12,7 @@ #define _FSCRYPT_PRIVATE_H #include +#include #include #include #include @@ -27,6 +28,23 @@ */ #define FSCRYPT_MIN_KEY_SIZE 16 +/* Maximum size of a raw fscrypt master key */ +#define FSCRYPT_MAX_RAW_KEY_SIZE 64 + +/* Maximum size of a hardware-wrapped fscrypt master key */ +#define FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE + +/* Maximum size of an fscrypt master key across both key types */ +#define FSCRYPT_MAX_ANY_KEY_SIZE \ + MAX(FSCRYPT_MAX_RAW_KEY_SIZE, FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE) + +/* + * FSCRYPT_MAX_KEY_SIZE is defined in the UAPI header, but the addition of + * hardware-wrapped keys has made it misleading as it's only for raw keys. + * Don't use it in kernel code; use one of the above constants instead. + */ +#undef FSCRYPT_MAX_KEY_SIZE + #define FSCRYPT_CONTEXT_V1 1 #define FSCRYPT_CONTEXT_V2 2 @@ -360,13 +378,15 @@ int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, * outputs are unique and cryptographically isolated, i.e. knowledge of one * output doesn't reveal another. */ -#define HKDF_CONTEXT_KEY_IDENTIFIER 1 /* info= */ +#define HKDF_CONTEXT_KEY_IDENTIFIER_FOR_RAW_KEY 1 /* info= */ #define HKDF_CONTEXT_PER_FILE_ENC_KEY 2 /* info=file_nonce */ #define HKDF_CONTEXT_DIRECT_KEY 3 /* info=mode_num */ #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 /* info=mode_num||fs_uuid */ #define HKDF_CONTEXT_DIRHASH_KEY 5 /* info=file_nonce */ #define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 /* info=mode_num||fs_uuid */ #define HKDF_CONTEXT_INODE_HASH_KEY 7 /* info= */ +#define HKDF_CONTEXT_KEY_IDENTIFIER_FOR_HW_WRAPPED_KEY \ + 8 /* info= */ int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -376,7 +396,8 @@ void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf); /* inline_crypt.c */ #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT -int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci); +int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci, + bool is_hw_wrapped_key); static inline bool fscrypt_using_inline_encryption(const struct fscrypt_inode_info *ci) @@ -385,12 +406,17 @@ fscrypt_using_inline_encryption(const struct fscrypt_inode_info *ci) } int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, - const u8 *raw_key, + const u8 *key_bytes, size_t key_size, + bool is_hw_wrapped, const struct fscrypt_inode_info *ci); void fscrypt_destroy_inline_crypt_key(struct super_block *sb, struct fscrypt_prepared_key *prep_key); +int fscrypt_derive_sw_secret(struct super_block *sb, + const u8 *wrapped_key, size_t wrapped_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]); + /* * Check whether the crypto transform or blk-crypto key has been allocated in * @prep_key, depending on which encryption implementation the file will use. @@ -414,7 +440,8 @@ fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ -static inline int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci) +static inline int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci, + bool is_hw_wrapped_key) { return 0; } @@ -427,7 +454,8 @@ fscrypt_using_inline_encryption(const struct fscrypt_inode_info *ci) static inline int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, - const u8 *raw_key, + const u8 *key_bytes, size_t key_size, + bool is_hw_wrapped, const struct fscrypt_inode_info *ci) { WARN_ON_ONCE(1); @@ -440,6 +468,15 @@ fscrypt_destroy_inline_crypt_key(struct super_block *sb, { } +static inline int +fscrypt_derive_sw_secret(struct super_block *sb, + const u8 *wrapped_key, size_t wrapped_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]) +{ + fscrypt_warn(NULL, "kernel doesn't support hardware-wrapped keys"); + return -EOPNOTSUPP; +} + static inline bool fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) @@ -456,20 +493,38 @@ fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, struct fscrypt_master_key_secret { /* - * For v2 policy keys: HKDF context keyed by this master key. - * For v1 policy keys: not set (hkdf.hmac_tfm == NULL). + * The KDF with which subkeys of this key can be derived. + * + * For v1 policy keys, this isn't applicable and won't be set. + * Otherwise, this KDF will be keyed by this master key if + * ->is_hw_wrapped=false, or by the "software secret" that hardware + * derived from this master key if ->is_hw_wrapped=true. */ struct fscrypt_hkdf hkdf; /* - * Size of the raw key in bytes. This remains set even if ->raw was + * True if this key is a hardware-wrapped key; false if this key is a + * raw key (i.e. a "software key"). For v1 policy keys this will always + * be false, as v1 policy support is a legacy feature which doesn't + * support newer functionality such as hardware-wrapped keys. + */ + bool is_hw_wrapped; + + /* + * Size of the key in bytes. This remains set even if ->bytes was * zeroized due to no longer being needed. I.e. we still remember the * size of the key even if we don't need to remember the key itself. */ u32 size; - /* For v1 policy keys: the raw key. Wiped for v2 policy keys. */ - u8 raw[FSCRYPT_MAX_KEY_SIZE]; + /* + * The bytes of the key, when still needed. This can be either a raw + * key or a hardware-wrapped key, as indicated by ->is_hw_wrapped. In + * the case of a raw, v2 policy key, there is no need to remember the + * actual key separately from ->hkdf so this field will be zeroized as + * soon as ->hkdf is initialized. + */ + u8 bytes[FSCRYPT_MAX_ANY_KEY_SIZE]; } __randomize_layout; diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c index 855a0f4b7318..0f3028adc9c7 100644 --- a/fs/crypto/hkdf.c +++ b/fs/crypto/hkdf.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* - * This is used to derive keys from the fscrypt master keys. + * This is used to derive keys from the fscrypt master keys (or from the + * "software secrets" which hardware derives from the fscrypt master keys, in + * the case that the fscrypt master keys are hardware-wrapped keys). * * Copyright 2019 Google LLC */ diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 7fa53d30aec3..1d008c440cb6 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -89,7 +89,8 @@ static void fscrypt_log_blk_crypto_impl(struct fscrypt_mode *mode, } /* Enable inline encryption for this file if supported. */ -int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci) +int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci, + bool is_hw_wrapped_key) { const struct inode *inode = ci->ci_inode; struct super_block *sb = inode->i_sb; @@ -130,7 +131,8 @@ int fscrypt_select_encryption_impl(struct fscrypt_inode_info *ci) crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode; crypto_cfg.data_unit_size = 1U << ci->ci_data_unit_bits; crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci); - crypto_cfg.key_type = BLK_CRYPTO_KEY_TYPE_RAW; + crypto_cfg.key_type = is_hw_wrapped_key ? + BLK_CRYPTO_KEY_TYPE_HW_WRAPPED : BLK_CRYPTO_KEY_TYPE_RAW; devs = fscrypt_get_devices(sb, &num_devs); if (IS_ERR(devs)) @@ -151,12 +153,15 @@ out_free_devs: } int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, - const u8 *raw_key, + const u8 *key_bytes, size_t key_size, + bool is_hw_wrapped, const struct fscrypt_inode_info *ci) { const struct inode *inode = ci->ci_inode; struct super_block *sb = inode->i_sb; enum blk_crypto_mode_num crypto_mode = ci->ci_mode->blk_crypto_mode; + enum blk_crypto_key_type key_type = is_hw_wrapped ? + BLK_CRYPTO_KEY_TYPE_HW_WRAPPED : BLK_CRYPTO_KEY_TYPE_RAW; struct blk_crypto_key *blk_key; struct block_device **devs; unsigned int num_devs; @@ -167,9 +172,8 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, if (!blk_key) return -ENOMEM; - err = blk_crypto_init_key(blk_key, raw_key, ci->ci_mode->keysize, - BLK_CRYPTO_KEY_TYPE_RAW, crypto_mode, - fscrypt_get_dun_bytes(ci), + err = blk_crypto_init_key(blk_key, key_bytes, key_size, key_type, + crypto_mode, fscrypt_get_dun_bytes(ci), 1U << ci->ci_data_unit_bits); if (err) { fscrypt_err(inode, "error %d initializing blk-crypto key", err); @@ -228,6 +232,34 @@ void fscrypt_destroy_inline_crypt_key(struct super_block *sb, kfree_sensitive(blk_key); } +/* + * Ask the inline encryption hardware to derive the software secret from a + * hardware-wrapped key. Returns -EOPNOTSUPP if hardware-wrapped keys aren't + * supported on this filesystem or hardware. + */ +int fscrypt_derive_sw_secret(struct super_block *sb, + const u8 *wrapped_key, size_t wrapped_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]) +{ + int err; + + /* The filesystem must be mounted with -o inlinecrypt. */ + if (!(sb->s_flags & SB_INLINECRYPT)) { + fscrypt_warn(NULL, + "%s: filesystem not mounted with inlinecrypt\n", + sb->s_id); + return -EOPNOTSUPP; + } + + err = blk_crypto_derive_sw_secret(sb->s_bdev, wrapped_key, + wrapped_key_size, sw_secret); + if (err == -EOPNOTSUPP) + fscrypt_warn(NULL, + "%s: block device doesn't support hardware-wrapped keys\n", + sb->s_id); + return err; +} + bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) { return inode->i_crypt_info->ci_inlinecrypt; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 787e9c8938ba..ace369f13068 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -149,11 +149,11 @@ static int fscrypt_user_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { /* - * We just charge FSCRYPT_MAX_KEY_SIZE bytes to the user's key quota for - * each key, regardless of the exact key size. The amount of memory + * We just charge FSCRYPT_MAX_RAW_KEY_SIZE bytes to the user's key quota + * for each key, regardless of the exact key size. The amount of memory * actually used is greater than the size of the raw key anyway. */ - return key_payload_reserve(key, FSCRYPT_MAX_KEY_SIZE); + return key_payload_reserve(key, FSCRYPT_MAX_RAW_KEY_SIZE); } static void fscrypt_user_key_describe(const struct key *key, struct seq_file *m) @@ -558,20 +558,45 @@ static int add_master_key(struct super_block *sb, int err; if (key_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { - err = fscrypt_init_hkdf(&secret->hkdf, secret->raw, - secret->size); - if (err) - return err; + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]; + u8 *kdf_key = secret->bytes; + unsigned int kdf_key_size = secret->size; + u8 keyid_kdf_ctx = HKDF_CONTEXT_KEY_IDENTIFIER_FOR_RAW_KEY; /* - * Now that the HKDF context is initialized, the raw key is no - * longer needed. + * For raw keys, the fscrypt master key is used directly as the + * fscrypt KDF key. For hardware-wrapped keys, we have to pass + * the master key to the hardware to derive the KDF key, which + * is then only used to derive non-file-contents subkeys. + */ + if (secret->is_hw_wrapped) { + err = fscrypt_derive_sw_secret(sb, secret->bytes, + secret->size, sw_secret); + if (err) + return err; + kdf_key = sw_secret; + kdf_key_size = sizeof(sw_secret); + /* + * To avoid weird behavior if someone manages to + * determine sw_secret and add it as a raw key, ensure + * that hardware-wrapped keys and raw keys will have + * different key identifiers by deriving their key + * identifiers using different KDF contexts. + */ + keyid_kdf_ctx = + HKDF_CONTEXT_KEY_IDENTIFIER_FOR_HW_WRAPPED_KEY; + } + err = fscrypt_init_hkdf(&secret->hkdf, kdf_key, kdf_key_size); + /* + * Now that the KDF context is initialized, the raw KDF key is + * no longer needed. */ - memzero_explicit(secret->raw, secret->size); + memzero_explicit(kdf_key, kdf_key_size); + if (err) + return err; /* Calculate the key identifier */ - err = fscrypt_hkdf_expand(&secret->hkdf, - HKDF_CONTEXT_KEY_IDENTIFIER, NULL, 0, + err = fscrypt_hkdf_expand(&secret->hkdf, keyid_kdf_ctx, NULL, 0, key_spec->u.identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); if (err) @@ -580,19 +605,36 @@ static int add_master_key(struct super_block *sb, return do_add_master_key(sb, secret, key_spec); } +/* + * Validate the size of an fscrypt master key being added. Note that this is + * just an initial check, as we don't know which ciphers will be used yet. + * There is a stricter size check later when the key is actually used by a file. + */ +static inline bool fscrypt_valid_key_size(size_t size, u32 add_key_flags) +{ + u32 max_size = (add_key_flags & FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED) ? + FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE : + FSCRYPT_MAX_RAW_KEY_SIZE; + + return size >= FSCRYPT_MIN_KEY_SIZE && size <= max_size; +} + static int fscrypt_provisioning_key_preparse(struct key_preparsed_payload *prep) { const struct fscrypt_provisioning_key_payload *payload = prep->data; - if (prep->datalen < sizeof(*payload) + FSCRYPT_MIN_KEY_SIZE || - prep->datalen > sizeof(*payload) + FSCRYPT_MAX_KEY_SIZE) + if (prep->datalen < sizeof(*payload)) + return -EINVAL; + + if (!fscrypt_valid_key_size(prep->datalen - sizeof(*payload), + payload->flags)) return -EINVAL; if (payload->type != FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && payload->type != FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) return -EINVAL; - if (payload->__reserved) + if (payload->flags & ~FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED) return -EINVAL; prep->payload.data[0] = kmemdup(payload, prep->datalen, GFP_KERNEL); @@ -636,21 +678,21 @@ static struct key_type key_type_fscrypt_provisioning = { }; /* - * Retrieve the raw key from the Linux keyring key specified by 'key_id', and - * store it into 'secret'. + * Retrieve the key from the Linux keyring key specified by 'key_id', and store + * it into 'secret'. * - * The key must be of type "fscrypt-provisioning" and must have the field - * fscrypt_provisioning_key_payload::type set to 'type', indicating that it's - * only usable with fscrypt with the particular KDF version identified by - * 'type'. We don't use the "logon" key type because there's no way to - * completely restrict the use of such keys; they can be used by any kernel API - * that accepts "logon" keys and doesn't require a specific service prefix. + * The key must be of type "fscrypt-provisioning" and must have the 'type' and + * 'flags' field of the payload set to the given values, indicating that the key + * is intended for use for the specified purpose. We don't use the "logon" key + * type because there's no way to completely restrict the use of such keys; they + * can be used by any kernel API that accepts "logon" keys and doesn't require a + * specific service prefix. * * The ability to specify the key via Linux keyring key is intended for cases * where userspace needs to re-add keys after the filesystem is unmounted and - * re-mounted. Most users should just provide the raw key directly instead. + * re-mounted. Most users should just provide the key directly instead. */ -static int get_keyring_key(u32 key_id, u32 type, +static int get_keyring_key(u32 key_id, u32 type, u32 flags, struct fscrypt_master_key_secret *secret) { key_ref_t ref; @@ -667,12 +709,16 @@ static int get_keyring_key(u32 key_id, u32 type, goto bad_key; payload = key->payload.data[0]; - /* Don't allow fscrypt v1 keys to be used as v2 keys and vice versa. */ - if (payload->type != type) + /* + * Don't allow fscrypt v1 keys to be used as v2 keys and vice versa. + * Similarly, don't allow hardware-wrapped keys to be used as + * non-hardware-wrapped keys and vice versa. + */ + if (payload->type != type || payload->flags != flags) goto bad_key; secret->size = key->datalen - sizeof(*payload); - memcpy(secret->raw, payload->raw, secret->size); + memcpy(secret->bytes, payload->raw, secret->size); err = 0; goto out_put; @@ -734,19 +780,28 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg) return -EACCES; memset(&secret, 0, sizeof(secret)); + + if (arg.flags) { + if (arg.flags & ~FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED) + return -EINVAL; + if (arg.key_spec.type != FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) + return -EINVAL; + secret.is_hw_wrapped = true; + } + if (arg.key_id) { if (arg.raw_size != 0) return -EINVAL; - err = get_keyring_key(arg.key_id, arg.key_spec.type, &secret); + err = get_keyring_key(arg.key_id, arg.key_spec.type, arg.flags, + &secret); if (err) goto out_wipe_secret; } else { - if (arg.raw_size < FSCRYPT_MIN_KEY_SIZE || - arg.raw_size > FSCRYPT_MAX_KEY_SIZE) + if (!fscrypt_valid_key_size(arg.raw_size, arg.flags)) return -EINVAL; secret.size = arg.raw_size; err = -EFAULT; - if (copy_from_user(secret.raw, uarg->raw, secret.size)) + if (copy_from_user(secret.bytes, uarg->raw, secret.size)) goto out_wipe_secret; } @@ -770,13 +825,13 @@ EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key); static void fscrypt_get_test_dummy_secret(struct fscrypt_master_key_secret *secret) { - static u8 test_key[FSCRYPT_MAX_KEY_SIZE]; + static u8 test_key[FSCRYPT_MAX_RAW_KEY_SIZE]; - get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE); + get_random_once(test_key, sizeof(test_key)); memset(secret, 0, sizeof(*secret)); - secret->size = FSCRYPT_MAX_KEY_SIZE; - memcpy(secret->raw, test_key, FSCRYPT_MAX_KEY_SIZE); + secret->size = sizeof(test_key); + memcpy(secret->bytes, test_key, sizeof(test_key)); } int fscrypt_get_test_dummy_key_identifier( @@ -787,10 +842,11 @@ int fscrypt_get_test_dummy_key_identifier( fscrypt_get_test_dummy_secret(&secret); - err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size); + err = fscrypt_init_hkdf(&secret.hkdf, secret.bytes, secret.size); if (err) goto out; - err = fscrypt_hkdf_expand(&secret.hkdf, HKDF_CONTEXT_KEY_IDENTIFIER, + err = fscrypt_hkdf_expand(&secret.hkdf, + HKDF_CONTEXT_KEY_IDENTIFIER_FOR_RAW_KEY, NULL, 0, key_identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); out: diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index b4fe01ea4bd4..0d71843af946 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -153,7 +153,9 @@ int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, struct crypto_skcipher *tfm; if (fscrypt_using_inline_encryption(ci)) - return fscrypt_prepare_inline_crypt_key(prep_key, raw_key, ci); + return fscrypt_prepare_inline_crypt_key(prep_key, raw_key, + ci->ci_mode->keysize, + false, ci); tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode); if (IS_ERR(tfm)) @@ -195,14 +197,29 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; struct fscrypt_prepared_key *prep_key; - u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; + u8 mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; + bool use_hw_wrapped_key = false; int err; if (WARN_ON_ONCE(mode_num > FSCRYPT_MODE_MAX)) return -EINVAL; + if (mk->mk_secret.is_hw_wrapped && S_ISREG(inode->i_mode)) { + /* Using a hardware-wrapped key for file contents encryption */ + if (!fscrypt_using_inline_encryption(ci)) { + if (sb->s_flags & SB_INLINECRYPT) + fscrypt_warn(ci->ci_inode, + "Hardware-wrapped key required, but no suitable inline encryption capabilities are available"); + else + fscrypt_warn(ci->ci_inode, + "Hardware-wrapped keys require inline encryption (-o inlinecrypt)"); + return -EINVAL; + } + use_hw_wrapped_key = true; + } + prep_key = &keys[mode_num]; if (fscrypt_is_key_prepared(prep_key, ci)) { ci->ci_enc_key = *prep_key; @@ -214,6 +231,16 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, if (fscrypt_is_key_prepared(prep_key, ci)) goto done_unlock; + if (use_hw_wrapped_key) { + err = fscrypt_prepare_inline_crypt_key(prep_key, + mk->mk_secret.bytes, + mk->mk_secret.size, true, + ci); + if (err) + goto out_unlock; + goto done_unlock; + } + BUILD_BUG_ON(sizeof(mode_num) != 1); BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); BUILD_BUG_ON(sizeof(hkdf_info) != 17); @@ -336,6 +363,14 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, { int err; + if (mk->mk_secret.is_hw_wrapped && + !(ci->ci_policy.v2.flags & (FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 | + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32))) { + fscrypt_warn(ci->ci_inode, + "Hardware-wrapped keys are only supported with IV_INO_LBLK policies"); + return -EINVAL; + } + if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { /* * DIRECT_KEY: instead of deriving per-file encryption keys, the @@ -362,7 +397,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); } else { - u8 derived_key[FSCRYPT_MAX_KEY_SIZE]; + u8 derived_key[FSCRYPT_MAX_RAW_KEY_SIZE]; err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, HKDF_CONTEXT_PER_FILE_ENC_KEY, @@ -445,10 +480,6 @@ static int setup_file_encryption_key(struct fscrypt_inode_info *ci, struct fscrypt_master_key *mk; int err; - err = fscrypt_select_encryption_impl(ci); - if (err) - return err; - err = fscrypt_policy_to_key_spec(&ci->ci_policy, &mk_spec); if (err) return err; @@ -476,6 +507,10 @@ static int setup_file_encryption_key(struct fscrypt_inode_info *ci, if (ci->ci_policy.version != FSCRYPT_POLICY_V1) return -ENOKEY; + err = fscrypt_select_encryption_impl(ci, false); + if (err) + return err; + /* * As a legacy fallback for v1 policies, search for the key in * the current task's subscribed keyrings too. Don't move this @@ -497,9 +532,21 @@ static int setup_file_encryption_key(struct fscrypt_inode_info *ci, goto out_release_key; } + err = fscrypt_select_encryption_impl(ci, mk->mk_secret.is_hw_wrapped); + if (err) + goto out_release_key; + switch (ci->ci_policy.version) { case FSCRYPT_POLICY_V1: - err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.raw); + if (WARN_ON_ONCE(mk->mk_secret.is_hw_wrapped)) { + /* + * This should never happen, as adding a v1 policy key + * that is hardware-wrapped isn't allowed. + */ + err = -EINVAL; + goto out_release_key; + } + err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.bytes); break; case FSCRYPT_POLICY_V2: err = fscrypt_setup_v2_file_key(ci, mk, need_dirhash_key); diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c index cf3b58ec32cc..b70521c55132 100644 --- a/fs/crypto/keysetup_v1.c +++ b/fs/crypto/keysetup_v1.c @@ -118,7 +118,7 @@ find_and_lock_process_key(const char *prefix, payload = (const struct fscrypt_key *)ukp->data; if (ukp->datalen != sizeof(struct fscrypt_key) || - payload->size < 1 || payload->size > FSCRYPT_MAX_KEY_SIZE) { + payload->size < 1 || payload->size > sizeof(payload->raw)) { fscrypt_warn(NULL, "key with description '%s' has invalid payload", key->description); @@ -149,7 +149,7 @@ struct fscrypt_direct_key { const struct fscrypt_mode *dk_mode; struct fscrypt_prepared_key dk_key; u8 dk_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; - u8 dk_raw[FSCRYPT_MAX_KEY_SIZE]; + u8 dk_raw[FSCRYPT_MAX_RAW_KEY_SIZE]; }; static void free_direct_key(struct fscrypt_direct_key *dk) diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 7a8f4c290187..3aff99f2696a 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -119,7 +119,7 @@ struct fscrypt_key_specifier { */ struct fscrypt_provisioning_key_payload { __u32 type; - __u32 __reserved; + __u32 flags; __u8 raw[]; }; @@ -128,7 +128,9 @@ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; __u32 key_id; - __u32 __reserved[8]; +#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; __u8 raw[]; }; -- cgit v1.2.3 From b412fd6bcc4c1696b0674434f56b198950c0e2bf Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Tue, 8 Apr 2025 11:00:04 +0200 Subject: bpf: Clarify role of BPF_F_RECOMPUTE_CSUM BPF_F_RECOMPUTE_CSUM doesn't update the actual L3 and L4 checksums in the packet, but simply updates skb->csum (according to skb->ip_summed). This patch clarifies that to avoid confusions. Signed-off-by: Paul Chaignon Link: https://lore.kernel.org/r/ff6895d42936f03dbb82334d8bcfd50e00c79086.1744102490.git.paul.chaignon@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 14 +++++++++----- tools/include/uapi/linux/bpf.h | 14 +++++++++----- 2 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 07ee73cdf97b..14ef3db844fa 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1995,11 +1995,15 @@ union bpf_attr { * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description * Store *len* bytes from address *from* into the packet - * associated to *skb*, at *offset*. *flags* are a combination of - * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the - * checksum for the packet after storing the bytes) and - * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ - * **->swhash** and *skb*\ **->l4hash** to 0). + * associated to *skb*, at *offset*. The *flags* are a combination + * of the following values: + * + * **BPF_F_RECOMPUTE_CSUM** + * Automatically update *skb*\ **->csum** after storing the + * bytes. + * **BPF_F_INVALIDATE_HASH** + * Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\ + * **->l4hash** to 0. * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 07ee73cdf97b..14ef3db844fa 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1995,11 +1995,15 @@ union bpf_attr { * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description * Store *len* bytes from address *from* into the packet - * associated to *skb*, at *offset*. *flags* are a combination of - * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the - * checksum for the packet after storing the bytes) and - * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ - * **->swhash** and *skb*\ **->l4hash** to 0). + * associated to *skb*, at *offset*. The *flags* are a combination + * of the following values: + * + * **BPF_F_RECOMPUTE_CSUM** + * Automatically update *skb*\ **->csum** after storing the + * bytes. + * **BPF_F_INVALIDATE_HASH** + * Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\ + * **->l4hash** to 0. * * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers -- cgit v1.2.3 From 5a15a050df714959f0d5a57ac3201bd1c6594984 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Tue, 8 Apr 2025 11:00:51 +0200 Subject: bpf: Clarify the meaning of BPF_F_PSEUDO_HDR In the bpf_l4_csum_replace helper, the BPF_F_PSEUDO_HDR flag should only be set if the modified header field is part of the pseudo-header. If you modify for example the UDP ports and pass BPF_F_PSEUDO_HDR, inet_proto_csum_replace4 will update skb->csum even though it shouldn't (the port and the UDP checksum updates null each other). Signed-off-by: Paul Chaignon Link: https://lore.kernel.org/r/5126ef84ba75425b689482cbc98bffe75e5d8ab0.1744102490.git.paul.chaignon@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 14ef3db844fa..71d5ac83cf5d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2055,7 +2055,7 @@ union bpf_attr { * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates - * the checksum is to be computed against a pseudo-header. + * that the modified header field is part of the pseudo-header. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 14ef3db844fa..71d5ac83cf5d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2055,7 +2055,7 @@ union bpf_attr { * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates - * the checksum is to be computed against a pseudo-header. + * that the modified header field is part of the pseudo-header. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more -- cgit v1.2.3 From c449d5f3a3d70b6223af8df2cadca3ca6eacb613 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 9 Apr 2025 19:26:05 +0800 Subject: tcp: add LINUX_MIB_PAWS_TW_REJECTED counter When TCP is in TIME_WAIT state, PAWS verification uses LINUX_PAWSESTABREJECTED, which is ambiguous and cannot be distinguished from other PAWS verification processes. We added a new counter, like the existing PAWS_OLD_ACK one. Also we update the doc with previously missing PAWS_OLD_ACK. usage: ''' nstat -az | grep PAWSTimewait TcpExtPAWSTimewait 1 0.0 ''' Suggested-by: Eric Dumazet Signed-off-by: Jiayuan Chen Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250409112614.16153-3-jiayuan.chen@linux.dev Signed-off-by: Jakub Kicinski --- Documentation/networking/net_cachelines/snmp.rst | 2 ++ include/net/dropreason-core.h | 1 + include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_minisocks.c | 2 +- 5 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/net_cachelines/snmp.rst b/Documentation/networking/net_cachelines/snmp.rst index bc96efc92cf5..bd44b3eebbef 100644 --- a/Documentation/networking/net_cachelines/snmp.rst +++ b/Documentation/networking/net_cachelines/snmp.rst @@ -37,6 +37,8 @@ unsigned_long LINUX_MIB_TIMEWAITKILLED unsigned_long LINUX_MIB_PAWSACTIVEREJECTED unsigned_long LINUX_MIB_PAWSESTABREJECTED unsigned_long LINUX_MIB_TSECR_REJECTED +unsigned_long LINUX_MIB_PAWS_OLD_ACK +unsigned_long LINUX_MIB_PAWS_TW_REJECTED unsigned_long LINUX_MIB_DELAYEDACKLOST unsigned_long LINUX_MIB_LISTENOVERFLOWS unsigned_long LINUX_MIB_LISTENDROPS diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9701d7f936f6..bea77934a235 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -287,6 +287,7 @@ enum skb_drop_reason { /** * @SKB_DROP_REASON_TCP_RFC7323_TW_PAWS: PAWS check, socket is in * TIME_WAIT state. + * Corresponds to LINUX_MIB_PAWS_TW_REJECTED. */ SKB_DROP_REASON_TCP_RFC7323_TW_PAWS, /** diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index ec47f9b68a1b..1d234d7e1892 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -188,6 +188,7 @@ enum LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */ LINUX_MIB_TSECRREJECTED, /* TSEcrRejected */ LINUX_MIB_PAWS_OLD_ACK, /* PAWSOldAck */ + LINUX_MIB_PAWS_TW_REJECTED, /* PAWSTimewait */ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */ LINUX_MIB_DELAYEDACKLOCKED, /* DelayedACKLocked */ LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 10cbeb76c274..ea2f01584379 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -191,6 +191,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), SNMP_MIB_ITEM("TSEcrRejected", LINUX_MIB_TSECRREJECTED), SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK), + SNMP_MIB_ITEM("PAWSTimewait", LINUX_MIB_PAWS_TW_REJECTED), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED), SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 27511bf58c0f..43d7852ce07e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -248,7 +248,7 @@ kill: if (paws_reject) { *drop_reason = SKB_DROP_REASON_TCP_RFC7323_TW_PAWS; - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWSESTABREJECTED); + __NET_INC_STATS(twsk_net(tw), LINUX_MIB_PAWS_TW_REJECTED); } if (!th->rst) { -- cgit v1.2.3 From 67890d579402804b1d32b3280d9860073542528e Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Wed, 9 Apr 2025 12:47:40 -0700 Subject: ALSA: Add USB audio device jack type Add an USB jack type, in order to support notifying of a valid USB audio device. Since USB audio devices can have a slew of different configurations that reach beyond the basic headset and headphone use cases, classify these devices differently. Reviewed-by: Pierre-Louis Bossart Signed-off-by: Wesley Cheng Acked-by: Mark Brown Link: https://lore.kernel.org/r/20250409194804.3773260-8-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 2 +- include/sound/jack.h | 4 +++- include/uapi/linux/input-event-codes.h | 3 ++- sound/core/jack.c | 6 ++++-- 4 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index bd7e60c0b72f..dde836875deb 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -340,7 +340,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_LED_MAX 0x0f #define INPUT_DEVICE_ID_SND_MAX 0x07 #define INPUT_DEVICE_ID_FF_MAX 0x7f -#define INPUT_DEVICE_ID_SW_MAX 0x10 +#define INPUT_DEVICE_ID_SW_MAX 0x11 #define INPUT_DEVICE_ID_PROP_MAX 0x1f #define INPUT_DEVICE_ID_MATCH_BUS 1 diff --git a/include/sound/jack.h b/include/sound/jack.h index 1ed90e2109e9..bd3f62281c97 100644 --- a/include/sound/jack.h +++ b/include/sound/jack.h @@ -22,6 +22,7 @@ struct input_dev; * @SND_JACK_VIDEOOUT: Video out * @SND_JACK_AVOUT: AV (Audio Video) out * @SND_JACK_LINEIN: Line in + * @SND_JACK_USB: USB audio device * @SND_JACK_BTN_0: Button 0 * @SND_JACK_BTN_1: Button 1 * @SND_JACK_BTN_2: Button 2 @@ -43,6 +44,7 @@ enum snd_jack_types { SND_JACK_VIDEOOUT = 0x0010, SND_JACK_AVOUT = SND_JACK_LINEOUT | SND_JACK_VIDEOOUT, SND_JACK_LINEIN = 0x0020, + SND_JACK_USB = 0x0040, /* Kept separate from switches to facilitate implementation */ SND_JACK_BTN_0 = 0x4000, @@ -54,7 +56,7 @@ enum snd_jack_types { }; /* Keep in sync with definitions above */ -#define SND_JACK_SWITCH_TYPES 6 +#define SND_JACK_SWITCH_TYPES 7 struct snd_jack { struct list_head kctl_list; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 5a199f3d4a26..3b2524e4b667 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -925,7 +925,8 @@ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ #define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MACHINE_COVER 0x10 /* set = cover closed */ -#define SW_MAX 0x10 +#define SW_USB_INSERT 0x11 /* set = USB audio device connected */ +#define SW_MAX 0x11 #define SW_CNT (SW_MAX+1) /* diff --git a/sound/core/jack.c b/sound/core/jack.c index e4bcecdf89b7..de7c603e92b7 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -34,6 +34,7 @@ static const int jack_switch_types[SND_JACK_SWITCH_TYPES] = { SW_JACK_PHYSICAL_INSERT, SW_VIDEOOUT_INSERT, SW_LINEIN_INSERT, + SW_USB_INSERT, }; #endif /* CONFIG_SND_JACK_INPUT_DEV */ @@ -241,8 +242,9 @@ static ssize_t jack_kctl_id_read(struct file *file, static const char * const jack_events_name[] = { "HEADPHONE(0x0001)", "MICROPHONE(0x0002)", "LINEOUT(0x0004)", "MECHANICAL(0x0008)", "VIDEOOUT(0x0010)", "LINEIN(0x0020)", - "", "", "", "BTN_5(0x0200)", "BTN_4(0x0400)", "BTN_3(0x0800)", - "BTN_2(0x1000)", "BTN_1(0x2000)", "BTN_0(0x4000)", "", + "USB(0x0040)", "", "", "BTN_5(0x0200)", "BTN_4(0x0400)", + "BTN_3(0x0800)", "BTN_2(0x1000)", "BTN_1(0x2000)", "BTN_0(0x4000)", + "", }; /* the recommended buffer size is 256 */ -- cgit v1.2.3 From 4172b556fd5bdfdf9b2d1e42da39df6ce99ee989 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Mon, 7 Apr 2025 15:32:33 -0400 Subject: drm/amdkfd: add smi events for process start and end rocm-smi will be able to show the events for KFD process start/end, it is the implementation of this feature. Signed-off-by: Eric Huang Reviewed-by: Kent Russell Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 ++++ drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 21 +++++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h | 1 + include/uapi/linux/kfd_ioctl.h | 5 +++++ 4 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 7c0c24732481..41d7dc8c2850 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1054,6 +1054,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) for (i = 0; i < p->n_pdds; i++) { struct kfd_process_device *pdd = p->pdds[i]; + kfd_smi_event_process(pdd, false); + pr_debug("Releasing pdd (topology id %d, for pid %d)\n", pdd->dev->id, p->lead_thread->pid); kfd_process_device_destroy_cwsr_dgpu(pdd); @@ -1715,6 +1717,8 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd, pdd->pasid = avm->pasid; pdd->drm_file = drm_file; + kfd_smi_event_process(pdd, true); + return 0; err_get_pasid: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index 9b8169761ec5..727a4ce29fe6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -345,6 +345,27 @@ void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, pid_t pid, pid, address, last - address + 1, node->id, trigger)); } +void kfd_smi_event_process(struct kfd_process_device *pdd, bool start) +{ + struct amdgpu_task_info *task_info; + struct amdgpu_vm *avm; + + if (pdd->drm_priv) + return; + + avm = drm_priv_to_vm(pdd->drm_priv); + task_info = amdgpu_vm_get_task_info_vm(avm); + + if (task_info) { + kfd_smi_event_add(0, pdd->dev, + start ? KFD_SMI_EVENT_PROCESS_START : + KFD_SMI_EVENT_PROCESS_END, + KFD_EVENT_FMT_PROCESS(task_info->pid, + task_info->task_name)); + amdgpu_vm_put_task_info(task_info); + } +} + int kfd_smi_event_open(struct kfd_node *dev, uint32_t *fd) { struct kfd_smi_client *client; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h index 503bff13d815..bb4d72b57387 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h @@ -53,4 +53,5 @@ void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm); void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, pid_t pid, unsigned long address, unsigned long last, uint32_t trigger); +void kfd_smi_event_process(struct kfd_process_device *pdd, bool start); #endif diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 1e59344c5673..04c7d283dc7d 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -536,6 +536,8 @@ enum kfd_smi_event { KFD_SMI_EVENT_QUEUE_EVICTION = 9, KFD_SMI_EVENT_QUEUE_RESTORE = 10, KFD_SMI_EVENT_UNMAP_FROM_GPU = 11, + KFD_SMI_EVENT_PROCESS_START = 12, + KFD_SMI_EVENT_PROCESS_END = 13, /* * max event number, as a flag bit to get events from all processes, @@ -651,6 +653,9 @@ struct kfd_ioctl_smi_events_args { "%lld -%d @%lx(%lx) %x %d\n", (ns), (pid), (addr), (size),\ (node), (unmap_trigger) +#define KFD_EVENT_FMT_PROCESS(pid, task_name)\ + "%x %s\n", (pid), (task_name) + /************************************************************************************************** * CRIU IOCTLs (Checkpoint Restore In Userspace) * -- cgit v1.2.3 From e846fb5e7c5243c65ff67247cb29a9d76bbcc4e8 Mon Sep 17 00:00:00 2001 From: Joseph Huang Date: Fri, 11 Apr 2025 11:03:16 -0400 Subject: net: bridge: mcast: Add offload failed mdb flag Add MDB_FLAGS_OFFLOAD_FAILED and MDB_PG_FLAGS_OFFLOAD_FAILED to indicate that an attempt to offload the MDB entry to switchdev has failed. Signed-off-by: Joseph Huang Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20250411150323.1117797-2-Joseph.Huang@garmin.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 9 +++++---- net/bridge/br_mdb.c | 2 ++ net/bridge/br_private.h | 20 +++++++++++++++----- net/bridge/br_switchdev.c | 9 +++++---- 4 files changed, 27 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index a5b743a2f775..f2a6de424f3f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -699,10 +699,11 @@ struct br_mdb_entry { #define MDB_TEMPORARY 0 #define MDB_PERMANENT 1 __u8 state; -#define MDB_FLAGS_OFFLOAD (1 << 0) -#define MDB_FLAGS_FAST_LEAVE (1 << 1) -#define MDB_FLAGS_STAR_EXCL (1 << 2) -#define MDB_FLAGS_BLOCKED (1 << 3) +#define MDB_FLAGS_OFFLOAD (1 << 0) +#define MDB_FLAGS_FAST_LEAVE (1 << 1) +#define MDB_FLAGS_STAR_EXCL (1 << 2) +#define MDB_FLAGS_BLOCKED (1 << 3) +#define MDB_FLAGS_OFFLOAD_FAILED (1 << 4) __u8 flags; __u16 vid; struct { diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 722203b98ff7..aac96bf4ba44 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -144,6 +144,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags |= MDB_FLAGS_STAR_EXCL; if (flags & MDB_PG_FLAGS_BLOCKED) e->flags |= MDB_FLAGS_BLOCKED; + if (flags & MDB_PG_FLAGS_OFFLOAD_FAILED) + e->flags |= MDB_FLAGS_OFFLOAD_FAILED; } static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d5b3c5936a79..d9b8ed316040 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -306,11 +306,12 @@ struct net_bridge_fdb_flush_desc { u16 vlan_id; }; -#define MDB_PG_FLAGS_PERMANENT BIT(0) -#define MDB_PG_FLAGS_OFFLOAD BIT(1) -#define MDB_PG_FLAGS_FAST_LEAVE BIT(2) -#define MDB_PG_FLAGS_STAR_EXCL BIT(3) -#define MDB_PG_FLAGS_BLOCKED BIT(4) +#define MDB_PG_FLAGS_PERMANENT BIT(0) +#define MDB_PG_FLAGS_OFFLOAD BIT(1) +#define MDB_PG_FLAGS_FAST_LEAVE BIT(2) +#define MDB_PG_FLAGS_STAR_EXCL BIT(3) +#define MDB_PG_FLAGS_BLOCKED BIT(4) +#define MDB_PG_FLAGS_OFFLOAD_FAILED BIT(5) #define PG_SRC_ENT_LIMIT 32 @@ -1342,6 +1343,15 @@ br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) return !!(vlan_snooping_enabled == br_multicast_ctx_is_vlan(brmctx)); } + +static inline void +br_multicast_set_pg_offload_flags(struct net_bridge_port_group *p, + bool offloaded) +{ + p->flags &= ~(MDB_PG_FLAGS_OFFLOAD | MDB_PG_FLAGS_OFFLOAD_FAILED); + p->flags |= (offloaded ? MDB_PG_FLAGS_OFFLOAD : + MDB_PG_FLAGS_OFFLOAD_FAILED); +} #else static inline int br_multicast_rcv(struct net_bridge_mcast **brmctx, struct net_bridge_mcast_port **pmctx, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 7b41ee8740cb..2d769ef3cb8a 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -505,8 +505,8 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri struct net_bridge_port *port = data->port; struct net_bridge *br = port->br; - if (err) - goto err; + if (err == -EOPNOTSUPP) + goto out_free; spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &data->ip); @@ -516,11 +516,12 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri pp = &p->next) { if (p->key.port != port) continue; - p->flags |= MDB_PG_FLAGS_OFFLOAD; + + br_multicast_set_pg_offload_flags(p, !err); } out: spin_unlock_bh(&br->multicast_lock); -err: +out_free: kfree(priv); } -- cgit v1.2.3 From 9fbe1e3e61c21508861a72324087aeeea85f796f Mon Sep 17 00:00:00 2001 From: Joseph Huang Date: Fri, 11 Apr 2025 11:03:17 -0400 Subject: net: bridge: Add offload_fail_notification bopt Add BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION bool option. Signed-off-by: Joseph Huang Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20250411150323.1117797-3-Joseph.Huang@garmin.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br.c | 5 +++++ net/bridge/br_private.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index f2a6de424f3f..73876c0e2bba 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -831,6 +831,7 @@ enum br_boolopt_id { BR_BOOLOPT_NO_LL_LEARN, BR_BOOLOPT_MCAST_VLAN_SNOOPING, BR_BOOLOPT_MST_ENABLE, + BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION, BR_BOOLOPT_MAX }; diff --git a/net/bridge/br.c b/net/bridge/br.c index 183fcb362f9e..25dda554ca5b 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -284,6 +284,9 @@ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, case BR_BOOLOPT_MST_ENABLE: err = br_mst_set_enabled(br, on, extack); break; + case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION: + br_opt_toggle(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, on); + break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); @@ -302,6 +305,8 @@ int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); case BR_BOOLOPT_MST_ENABLE: return br_opt_get(br, BROPT_MST_ENABLED); + case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION: + return br_opt_get(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION); default: /* shouldn't be called with unsupported options */ WARN_ON(1); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d9b8ed316040..e17a3c5fe689 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -484,6 +484,7 @@ enum net_bridge_opts { BROPT_VLAN_BRIDGE_BINDING, BROPT_MCAST_VLAN_SNOOPING_ENABLED, BROPT_MST_ENABLED, + BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, }; struct net_bridge { -- cgit v1.2.3 From 5800b1cf3fd8ccab752a101865be1e76dac33142 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Apr 2025 10:52:49 +0100 Subject: rxrpc: Allow CHALLENGEs to the passed to the app for a RESPONSE Allow the app to request that CHALLENGEs be passed to it through an out-of-band queue that allows recvmsg() to pick it up so that the app can add data to it with sendmsg(). This will allow the application (AFS or userspace) to interact with the process if it wants to and put values into user-defined fields. This will be used by AFS when talking to a fileserver to supply that fileserver with a crypto key by which callback RPCs can be encrypted (ie. notifications from the fileserver to the client). Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250411095303.2316168-5-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/networking/rxrpc.rst | 2 + fs/afs/Makefile | 1 + fs/afs/cm_security.c | 73 +++++++ fs/afs/internal.h | 6 + fs/afs/main.c | 1 + fs/afs/rxrpc.c | 18 ++ include/net/af_rxrpc.h | 24 +++ include/trace/events/rxrpc.h | 18 +- include/uapi/linux/rxrpc.h | 46 +++-- net/rxrpc/Makefile | 1 + net/rxrpc/af_rxrpc.c | 52 ++++- net/rxrpc/ar-internal.h | 51 ++++- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_event.c | 134 ++++++++++++- net/rxrpc/conn_object.c | 1 + net/rxrpc/insecure.c | 13 +- net/rxrpc/io_thread.c | 12 +- net/rxrpc/oob.c | 379 +++++++++++++++++++++++++++++++++++++ net/rxrpc/output.c | 56 ++++++ net/rxrpc/recvmsg.c | 120 ++++++++++-- net/rxrpc/rxkad.c | 288 +++++++++++++++++----------- net/rxrpc/sendmsg.c | 15 +- net/rxrpc/server_key.c | 40 ++++ 23 files changed, 1188 insertions(+), 165 deletions(-) create mode 100644 fs/afs/cm_security.c create mode 100644 net/rxrpc/oob.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index 2680abd1cb26..eb941b2577dd 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -1179,7 +1179,9 @@ API Function Reference .. kernel-doc:: net/rxrpc/af_rxrpc.c .. kernel-doc:: net/rxrpc/key.c +.. kernel-doc:: net/rxrpc/oob.c .. kernel-doc:: net/rxrpc/peer_object.c .. kernel-doc:: net/rxrpc/recvmsg.c +.. kernel-doc:: net/rxrpc/rxkad.c .. kernel-doc:: net/rxrpc/sendmsg.c .. kernel-doc:: net/rxrpc/server_key.c diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 5efd7e13b304..b49b8fe682f3 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -8,6 +8,7 @@ kafs-y := \ addr_prefs.o \ callback.o \ cell.o \ + cm_security.o \ cmservice.o \ dir.o \ dir_edit.o \ diff --git a/fs/afs/cm_security.c b/fs/afs/cm_security.c new file mode 100644 index 000000000000..efe6a23c8477 --- /dev/null +++ b/fs/afs/cm_security.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Cache manager security. + * + * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include "internal.h" +#include "afs_fs.h" +#include "protocol_yfs.h" +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include + +/* + * Respond to an RxGK challenge, adding appdata. + */ +static int afs_respond_to_challenge(struct sk_buff *challenge) +{ + struct rxrpc_peer *peer; + unsigned long peer_data; + u16 service_id; + u8 security_index; + + rxrpc_kernel_query_challenge(challenge, &peer, &peer_data, + &service_id, &security_index); + + _enter("%u,%u", service_id, security_index); + + switch (service_id) { + /* We don't send CM_SERVICE RPCs, so don't expect a challenge + * therefrom. + */ + case FS_SERVICE: + case VL_SERVICE: + case YFS_FS_SERVICE: + case YFS_VL_SERVICE: + break; + default: + pr_warn("Can't respond to unknown challenge %u:%u", + service_id, security_index); + return rxrpc_kernel_reject_challenge(challenge, RX_USER_ABORT, -EPROTO, + afs_abort_unsupported_sec_class); + } + + switch (security_index) { + case RXRPC_SECURITY_RXKAD: + return rxkad_kernel_respond_to_challenge(challenge); + + default: + return rxrpc_kernel_reject_challenge(challenge, RX_USER_ABORT, -EPROTO, + afs_abort_unsupported_sec_class); + } +} + +/* + * Process the OOB message queue, processing challenge packets. + */ +void afs_process_oob_queue(struct work_struct *work) +{ + struct afs_net *net = container_of(work, struct afs_net, rx_oob_work); + struct sk_buff *oob; + enum rxrpc_oob_type type; + + while ((oob = rxrpc_kernel_dequeue_oob(net->socket, &type))) { + switch (type) { + case RXRPC_OOB_CHALLENGE: + afs_respond_to_challenge(oob); + break; + } + rxrpc_kernel_free_oob(oob); + } +} diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 440b0e731093..b3612b700c6a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -281,6 +281,7 @@ struct afs_net { struct socket *socket; struct afs_call *spare_incoming_call; struct work_struct charge_preallocation_work; + struct work_struct rx_oob_work; struct mutex socket_mutex; atomic_t nr_outstanding_calls; atomic_t nr_superblocks; @@ -1058,6 +1059,11 @@ extern void __net_exit afs_cell_purge(struct afs_net *); */ extern bool afs_cm_incoming_call(struct afs_call *); +/* + * cm_security.c + */ +void afs_process_oob_queue(struct work_struct *work); + /* * dir.c */ diff --git a/fs/afs/main.c b/fs/afs/main.c index c845c5daaeba..02475d415d88 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -73,6 +73,7 @@ static int __net_init afs_net_init(struct net *net_ns) generate_random_uuid((unsigned char *)&net->uuid); INIT_WORK(&net->charge_preallocation_work, afs_charge_preallocation); + INIT_WORK(&net->rx_oob_work, afs_process_oob_queue); mutex_init(&net->socket_mutex); net->cells = RB_ROOT; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a4734304e542..212af2aa85bf 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -25,12 +25,14 @@ static void afs_process_async_call(struct work_struct *); static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long); static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long); static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID); +static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob); static int afs_deliver_cm_op_id(struct afs_call *); static const struct rxrpc_kernel_ops afs_rxrpc_callback_ops = { .notify_new_call = afs_rx_new_call, .discard_new_call = afs_rx_discard_new_call, .user_attach_call = afs_rx_attach, + .notify_oob = afs_rx_notify_oob, }; /* asynchronous incoming call initial processing */ @@ -56,6 +58,7 @@ int afs_open_socket(struct afs_net *net) goto error_1; socket->sk->sk_allocation = GFP_NOFS; + socket->sk->sk_user_data = net; /* bind the callback manager's address to make this a server socket */ memset(&srx, 0, sizeof(srx)); @@ -71,6 +74,10 @@ int afs_open_socket(struct afs_net *net) if (ret < 0) goto error_2; + ret = rxrpc_sock_set_manage_response(socket->sk, true); + if (ret < 0) + goto error_2; + ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); if (ret == -EADDRINUSE) { srx.transport.sin6.sin6_port = 0; @@ -131,6 +138,7 @@ void afs_close_socket(struct afs_net *net) kernel_sock_shutdown(net->socket, SHUT_RDWR); flush_workqueue(afs_async_calls); + net->socket->sk->sk_user_data = NULL; sock_release(net->socket); _debug("dework"); @@ -957,3 +965,13 @@ noinline int afs_protocol_error(struct afs_call *call, call->unmarshalling_error = true; return -EBADMSG; } + +/* + * Wake up OOB notification processing. + */ +static void afs_rx_notify_oob(struct sock *sk, struct sk_buff *oob) +{ + struct afs_net *net = sk->sk_user_data; + + schedule_work(&net->rx_oob_work); +} diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index ebb6092c488b..0b209f703ffc 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -16,6 +16,7 @@ struct sock; struct socket; struct rxrpc_call; struct rxrpc_peer; +struct krb5_buffer; enum rxrpc_abort_reason; enum rxrpc_interruptibility { @@ -24,6 +25,10 @@ enum rxrpc_interruptibility { RXRPC_UNINTERRUPTIBLE, /* Call should not be interruptible at all */ }; +enum rxrpc_oob_type { + RXRPC_OOB_CHALLENGE, /* Security challenge for a connection */ +}; + /* * Debug ID counter for tracing. */ @@ -37,6 +42,7 @@ struct rxrpc_kernel_ops { unsigned long user_call_ID); void (*discard_new_call)(struct rxrpc_call *call, unsigned long user_call_ID); void (*user_attach_call)(struct rxrpc_call *call, unsigned long user_call_ID); + void (*notify_oob)(struct sock *sk, struct sk_buff *oob); }; typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *, @@ -88,5 +94,23 @@ void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *, int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val); int rxrpc_sock_set_security_keyring(struct sock *, struct key *); +int rxrpc_sock_set_manage_response(struct sock *sk, bool set); + +enum rxrpc_oob_type rxrpc_kernel_query_oob(struct sk_buff *oob, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata); +struct sk_buff *rxrpc_kernel_dequeue_oob(struct socket *sock, + enum rxrpc_oob_type *_type); +void rxrpc_kernel_free_oob(struct sk_buff *oob); +void rxrpc_kernel_query_challenge(struct sk_buff *challenge, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata, + u16 *_service_id, u8 *_security_index); +int rxrpc_kernel_reject_challenge(struct sk_buff *challenge, u32 abort_code, + int error, enum rxrpc_abort_reason why); +int rxkad_kernel_respond_to_challenge(struct sk_buff *challenge); +u32 rxgk_kernel_query_challenge(struct sk_buff *challenge); +int rxgk_kernel_respond_to_challenge(struct sk_buff *challenge, + struct krb5_buffer *appdata); #endif /* _NET_RXRPC_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index cad50d91077e..08ecebd90595 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -25,6 +25,7 @@ EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \ EM(afs_abort_send_data_error, "afs-send-data") \ EM(afs_abort_unmarshal_error, "afs-unmarshal") \ + EM(afs_abort_unsupported_sec_class, "afs-unsup-sec-class") \ /* rxperf errors */ \ EM(rxperf_abort_general_error, "rxperf-error") \ EM(rxperf_abort_oom, "rxperf-oom") \ @@ -77,6 +78,7 @@ EM(rxrpc_abort_call_timeout, "call-timeout") \ EM(rxrpc_abort_no_service_key, "no-serv-key") \ EM(rxrpc_abort_nomem, "nomem") \ + EM(rxrpc_abort_response_sendmsg, "resp-sendmsg") \ EM(rxrpc_abort_service_not_offered, "serv-not-offered") \ EM(rxrpc_abort_shut_down, "shut-down") \ EM(rxrpc_abort_unsupported_security, "unsup-sec") \ @@ -133,24 +135,33 @@ EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ + EM(rxrpc_skb_get_post_oob, "GET post-oob ") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \ EM(rxrpc_skb_get_to_recvmsg_oos, "GET to-recv-o") \ EM(rxrpc_skb_new_encap_rcv, "NEW encap-rcv") \ EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ + EM(rxrpc_skb_new_response_rxgk, "NEW resp-rxgk") \ + EM(rxrpc_skb_new_response_rxkad, "NEW resp-rxkd") \ EM(rxrpc_skb_new_unshared, "NEW unshared ") \ EM(rxrpc_skb_put_call_rx, "PUT call-rx ") \ + EM(rxrpc_skb_put_challenge, "PUT challenge") \ EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \ EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \ + EM(rxrpc_skb_put_oob, "PUT oob ") \ EM(rxrpc_skb_put_purge, "PUT purge ") \ + EM(rxrpc_skb_put_purge_oob, "PUT purge-oob") \ + EM(rxrpc_skb_put_response, "PUT response ") \ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ EM(rxrpc_skb_see_conn_work, "SEE conn-work") \ + EM(rxrpc_skb_see_oob_challenge, "SEE oob-chall") \ EM(rxrpc_skb_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_skb_see_recvmsg_oob, "SEE recvm-oob") \ EM(rxrpc_skb_see_reject, "SEE reject ") \ EM(rxrpc_skb_see_rotate, "SEE rotate ") \ E_(rxrpc_skb_see_version, "SEE version ") @@ -216,9 +227,11 @@ EM(rxrpc_conn_free, "FREE ") \ EM(rxrpc_conn_get_activate_call, "GET act-call") \ EM(rxrpc_conn_get_call_input, "GET inp-call") \ + EM(rxrpc_conn_get_challenge_input, "GET inp-chal") \ EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ EM(rxrpc_conn_get_idle, "GET idle ") \ EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \ + EM(rxrpc_conn_get_poke_response, "GET response") \ EM(rxrpc_conn_get_poke_secured, "GET secured ") \ EM(rxrpc_conn_get_poke_timer, "GET poke ") \ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ @@ -226,10 +239,12 @@ EM(rxrpc_conn_new_service, "NEW service ") \ EM(rxrpc_conn_put_call, "PUT call ") \ EM(rxrpc_conn_put_call_input, "PUT inp-call") \ + EM(rxrpc_conn_put_challenge_input, "PUT inp-chal") \ EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \ EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ + EM(rxrpc_conn_put_oob, "PUT oob ") \ EM(rxrpc_conn_put_poke, "PUT poke ") \ EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \ EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ @@ -331,6 +346,7 @@ EM(rxrpc_recvmsg_full, "FULL") \ EM(rxrpc_recvmsg_hole, "HOLE") \ EM(rxrpc_recvmsg_next, "NEXT") \ + EM(rxrpc_recvmsg_oobq, "OOBQ") \ EM(rxrpc_recvmsg_requeue, "REQU") \ EM(rxrpc_recvmsg_return, "RETN") \ EM(rxrpc_recvmsg_terminal, "TERM") \ @@ -456,7 +472,7 @@ EM(rxrpc_tx_point_conn_abort, "ConnAbort") \ EM(rxrpc_tx_point_reject, "Reject") \ EM(rxrpc_tx_point_rxkad_challenge, "RxkadChall") \ - EM(rxrpc_tx_point_rxkad_response, "RxkadResp") \ + EM(rxrpc_tx_point_response, "Response") \ EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 8f8dc7a937a4..c4e9833b0a12 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -36,26 +36,33 @@ struct sockaddr_rxrpc { #define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ #define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ #define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ +#define RXRPC_MANAGE_RESPONSE 7 /* [clnt] Want to manage RESPONSE packets */ /* * RxRPC control messages * - If neither abort or accept are specified, the message is a data message. * - terminal messages mean that a user call ID tag can be recycled + * - C/S/- indicate whether these are applicable to client, server or both * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() */ enum rxrpc_cmsg_type { - RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ - RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ - RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ - RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ - RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ - RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ - RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ - RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ - RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ - RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */ - RXRPC_CHARGE_ACCEPT = 14, /* s-: Charge the accept pool with a user call ID */ + RXRPC_USER_CALL_ID = 1, /* -sr: User call ID specifier */ + RXRPC_ABORT = 2, /* -sr: Abort request / notification [terminal] */ + RXRPC_ACK = 3, /* S-r: RPC op final ACK received [terminal] */ + RXRPC_NET_ERROR = 5, /* --r: Network error received [terminal] */ + RXRPC_BUSY = 6, /* C-r: Server busy received [terminal] */ + RXRPC_LOCAL_ERROR = 7, /* --r: Local error generated [terminal] */ + RXRPC_NEW_CALL = 8, /* S-r: New incoming call notification */ + RXRPC_EXCLUSIVE_CALL = 10, /* Cs-: Call should be on exclusive connection */ + RXRPC_UPGRADE_SERVICE = 11, /* Cs-: Request service upgrade for client call */ + RXRPC_TX_LENGTH = 12, /* -s-: Total length of Tx data */ + RXRPC_SET_CALL_TIMEOUT = 13, /* -s-: Set one or more call timeouts */ + RXRPC_CHARGE_ACCEPT = 14, /* Ss-: Charge the accept pool with a user call ID */ + RXRPC_OOB_ID = 15, /* -sr: OOB message ID */ + RXRPC_CHALLENGED = 16, /* C-r: Info on a received CHALLENGE */ + RXRPC_RESPOND = 17, /* Cs-: Respond to a challenge */ + RXRPC_RESPONDED = 18, /* S-r: Data received in RESPONSE */ + RXRPC_RESP_RXGK_APPDATA = 19, /* Cs-: RESPONSE: RxGK app data to include */ RXRPC__SUPPORTED }; @@ -118,4 +125,19 @@ enum rxrpc_cmsg_type { #define RXKADDATALEN 19270411 /* user data too long */ #define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ +/* + * Challenge information in the RXRPC_CHALLENGED control message. + */ +struct rxrpc_challenge { + __u16 service_id; /* The service ID of the connection (may be upgraded) */ + __u8 security_index; /* The security index of the connection */ + __u8 pad; /* Round out to a multiple of 4 bytes. */ + /* ... The security class gets to append extra information ... */ +}; + +struct rxgk_challenge { + struct rxrpc_challenge base; + __u32 enctype; /* Krb5 encoding type */ +}; + #endif /* _UAPI_LINUX_RXRPC_H */ diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index 210b75e3179e..0981941dea73 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -24,6 +24,7 @@ rxrpc-y := \ local_object.o \ misc.o \ net_ns.o \ + oob.o \ output.o \ peer_event.o \ peer_object.o \ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 2e4f6c9ef3de..3a558c1a541e 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -633,7 +633,10 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) fallthrough; case RXRPC_SERVER_BOUND: case RXRPC_SERVER_LISTENING: - ret = rxrpc_do_sendmsg(rx, m, len); + if (m->msg_flags & MSG_OOB) + ret = rxrpc_sendmsg_oob(rx, m, len); + else + ret = rxrpc_do_sendmsg(rx, m, len); /* The socket has been unlocked */ goto out; default: @@ -668,7 +671,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - unsigned int min_sec_level; + unsigned int min_sec_level, val; u16 service_upgrade[2]; int ret; @@ -749,6 +752,26 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, rx->service_upgrade.to = service_upgrade[1]; goto success; + case RXRPC_MANAGE_RESPONSE: + ret = -EINVAL; + if (optlen != sizeof(unsigned int)) + goto error; + ret = -EISCONN; + if (rx->sk.sk_state != RXRPC_UNBOUND) + goto error; + ret = copy_safe_from_sockptr(&val, sizeof(val), + optval, optlen); + if (ret) + goto error; + ret = -EINVAL; + if (val > 1) + goto error; + if (val) + set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); + else + clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); + goto success; + default: break; } @@ -855,6 +878,8 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, rx->calls = RB_ROOT; spin_lock_init(&rx->incoming_lock); + skb_queue_head_init(&rx->recvmsg_oobq); + rx->pending_oobq = RB_ROOT; INIT_LIST_HEAD(&rx->sock_calls); INIT_LIST_HEAD(&rx->to_be_accepted); INIT_LIST_HEAD(&rx->recvmsg_q); @@ -888,8 +913,10 @@ static int rxrpc_shutdown(struct socket *sock, int flags) lock_sock(sk); if (sk->sk_state < RXRPC_CLOSE) { + spin_lock_irq(&rx->recvmsg_lock); sk->sk_state = RXRPC_CLOSE; sk->sk_shutdown = SHUTDOWN_MASK; + spin_unlock_irq(&rx->recvmsg_lock); } else { ret = -ESHUTDOWN; } @@ -900,6 +927,23 @@ static int rxrpc_shutdown(struct socket *sock, int flags) return ret; } +/* + * Purge the out-of-band queue. + */ +static void rxrpc_purge_oob_queue(struct sock *sk) +{ + struct rxrpc_sock *rx = rxrpc_sk(sk); + struct sk_buff *skb; + + while ((skb = skb_dequeue(&rx->recvmsg_oobq))) + rxrpc_kernel_free_oob(skb); + while (!RB_EMPTY_ROOT(&rx->pending_oobq)) { + skb = rb_entry(rx->pending_oobq.rb_node, struct sk_buff, rbnode); + rb_erase(&skb->rbnode, &rx->pending_oobq); + rxrpc_kernel_free_oob(skb); + } +} + /* * RxRPC socket destructor */ @@ -907,6 +951,7 @@ static void rxrpc_sock_destructor(struct sock *sk) { _enter("%p", sk); + rxrpc_purge_oob_queue(sk); rxrpc_purge_queue(&sk->sk_receive_queue); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); @@ -945,7 +990,9 @@ static int rxrpc_release_sock(struct sock *sk) break; } + spin_lock_irq(&rx->recvmsg_lock); sk->sk_state = RXRPC_CLOSE; + spin_unlock_irq(&rx->recvmsg_lock); if (rx->local && rx->local->service == rx) { write_lock(&rx->local->services_lock); @@ -957,6 +1004,7 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_discard_prealloc(rx); rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); + rxrpc_purge_oob_queue(sk); rxrpc_purge_queue(&sk->sk_receive_queue); rxrpc_unuse_local(rx->local, rxrpc_local_unuse_release_sock); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c267b8ac1bb5..31d05784c530 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -39,6 +39,7 @@ struct rxrpc_txqueue; enum rxrpc_skb_mark { RXRPC_SKB_MARK_PACKET, /* Received packet */ RXRPC_SKB_MARK_ERROR, /* Error notification */ + RXRPC_SKB_MARK_CHALLENGE, /* Challenge notification */ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ @@ -149,6 +150,9 @@ struct rxrpc_sock { const struct rxrpc_kernel_ops *app_ops; /* Table of kernel app notification funcs */ struct rxrpc_local *local; /* local endpoint */ struct rxrpc_backlog *backlog; /* Preallocation for services */ + struct sk_buff_head recvmsg_oobq; /* OOB messages for recvmsg to pick up */ + struct rb_root pending_oobq; /* OOB messages awaiting userspace to respond to */ + u64 oob_id_counter; /* OOB message ID counter */ spinlock_t incoming_lock; /* Incoming call vs service shutdown lock */ struct list_head sock_calls; /* List of calls owned by this socket */ struct list_head to_be_accepted; /* calls awaiting acceptance */ @@ -159,6 +163,7 @@ struct rxrpc_sock { struct rb_root calls; /* User ID -> call mapping */ unsigned long flags; #define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ +#define RXRPC_SOCK_MANAGE_RESPONSE 1 /* User wants to manage RESPONSE packets */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT @@ -202,7 +207,7 @@ struct rxrpc_host_header { */ struct rxrpc_skb_priv { union { - struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ + struct rxrpc_connection *poke_conn; /* Conn referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ @@ -216,6 +221,19 @@ struct rxrpc_skb_priv { u16 nr_acks; /* Number of acks+nacks */ u8 reason; /* Reason for ack */ } ack; + struct { + struct rxrpc_connection *conn; /* Connection referred to */ + union { + u32 rxkad_nonce; + }; + } chall; + struct { + rxrpc_serial_t challenge_serial; + u32 kvno; + u32 version; + u16 len; + u16 ticket_len; + } resp; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; @@ -269,9 +287,24 @@ struct rxrpc_security { /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); + /* Validate a challenge packet */ + bool (*validate_challenge)(struct rxrpc_connection *conn, + struct sk_buff *skb); + + /* Fill out the cmsg for recvmsg() to pass on a challenge to userspace. + * The security class gets to add additional information. + */ + int (*challenge_to_recvmsg)(struct rxrpc_connection *conn, + struct sk_buff *challenge, + struct msghdr *msg); + + /* Parse sendmsg() control message and respond to challenge. */ + int (*sendmsg_respond_to_challenge)(struct sk_buff *challenge, + struct msghdr *msg); + /* respond to a challenge */ - int (*respond_to_challenge)(struct rxrpc_connection *, - struct sk_buff *); + int (*respond_to_challenge)(struct rxrpc_connection *conn, + struct sk_buff *challenge); /* verify a response */ int (*verify_response)(struct rxrpc_connection *, @@ -526,6 +559,7 @@ struct rxrpc_connection { u32 nonce; /* response re-use preventer */ } rxkad; }; + struct sk_buff *tx_response; /* Response packet to be transmitted */ unsigned long flags; unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ @@ -1199,8 +1233,11 @@ void rxrpc_error_report(struct sock *); bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); int rxrpc_io_thread(void *data); +void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { + if (!local->io_thread) + return; wake_up_process(READ_ONCE(local->io_thread)); } @@ -1289,6 +1326,13 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) return net_generic(net, rxrpc_net_id); } +/* + * out_of_band.c + */ +void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb); +void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb); +int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len); + /* * output.c */ @@ -1300,6 +1344,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); +void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *skb); /* * peer_event.c diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f428ea77f803..fc88ffe1b050 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -145,8 +145,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); INIT_LIST_HEAD(&call->attend_link); - skb_queue_head_init(&call->rx_queue); skb_queue_head_init(&call->recvmsg_queue); + skb_queue_head_init(&call->rx_queue); skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 4d9c5e21ba78..232b6986da83 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -19,7 +19,7 @@ /* * Set the completion state on an aborted connection. */ -static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb, +static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, s32 abort_code, int err, enum rxrpc_call_completion compl) { @@ -49,12 +49,20 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, s32 abort_code, int err, enum rxrpc_abort_reason why) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - if (rxrpc_set_conn_aborted(conn, skb, abort_code, err, + u32 cid = conn->proto.cid, call = 0, seq = 0; + + if (skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + cid = sp->hdr.cid; + call = sp->hdr.callNumber; + seq = sp->hdr.seq; + } + + if (rxrpc_set_conn_aborted(conn, abort_code, err, RXRPC_CALL_LOCALLY_ABORTED)) { - trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, - sp->hdr.seq, abort_code, err); + trace_rxrpc_abort(0, why, cid, call, seq, abort_code, err); rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort); } return -EPROTO; @@ -67,7 +75,7 @@ static void rxrpc_input_conn_abort(struct rxrpc_connection *conn, struct sk_buff *skb) { trace_rxrpc_rx_conn_abort(conn, skb); - rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED, + rxrpc_set_conn_aborted(conn, skb->priority, -ECONNABORTED, RXRPC_CALL_REMOTELY_ABORTED); } @@ -248,7 +256,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_CHALLENGE: - return conn->security->respond_to_challenge(conn, skb); + ret = conn->security->respond_to_challenge(conn, skb); + sp->chall.conn = NULL; + rxrpc_put_connection(conn, rxrpc_conn_put_challenge_input); + return ret; case RXRPC_PACKET_TYPE_RESPONSE: ret = conn->security->verify_response(conn, skb); @@ -270,7 +281,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, * we've already received the packet, put it on the * front of the queue. */ - sp->conn = rxrpc_get_connection(conn, rxrpc_conn_get_poke_secured); + sp->poke_conn = rxrpc_get_connection( + conn, rxrpc_conn_get_poke_secured); skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED; rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured); skb_queue_head(&conn->local->rx_queue, skb); @@ -391,6 +403,61 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); } +/* + * Post a CHALLENGE packet to the socket of one of a connection's calls so that + * it can get application data to include in the packet, possibly querying + * userspace. + */ +static bool rxrpc_post_challenge(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_call *call = NULL; + struct rxrpc_sock *rx; + bool respond = false; + + sp->chall.conn = + rxrpc_get_connection(conn, rxrpc_conn_get_challenge_input); + + if (!conn->security->challenge_to_recvmsg) { + rxrpc_post_packet_to_conn(conn, skb); + return true; + } + + rcu_read_lock(); + + for (int i = 0; i < ARRAY_SIZE(conn->channels); i++) { + if (conn->channels[i].call) { + call = conn->channels[i].call; + rx = rcu_dereference(call->socket); + if (!rx) { + call = NULL; + continue; + } + + respond = true; + if (test_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags)) + break; + call = NULL; + } + } + + if (!respond) { + rcu_read_unlock(); + rxrpc_put_connection(conn, rxrpc_conn_put_challenge_input); + sp->chall.conn = NULL; + return false; + } + + if (call) + rxrpc_notify_socket_oob(call, skb); + rcu_read_unlock(); + + if (!call) + rxrpc_post_packet_to_conn(conn, skb); + return true; +} + /* * Input a connection-level packet. */ @@ -411,6 +478,16 @@ bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) return true; case RXRPC_PACKET_TYPE_CHALLENGE: + rxrpc_see_skb(skb, rxrpc_skb_see_oob_challenge); + if (rxrpc_is_conn_aborted(conn)) { + if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED) + rxrpc_send_conn_abort(conn); + return true; + } + if (!conn->security->validate_challenge(conn, skb)) + return false; + return rxrpc_post_challenge(conn, skb); + case RXRPC_PACKET_TYPE_RESPONSE: if (rxrpc_is_conn_aborted(conn)) { if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED) @@ -436,6 +513,19 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events)) rxrpc_abort_calls(conn); + if (conn->tx_response) { + struct sk_buff *skb; + + spin_lock_irq(&conn->local->lock); + skb = conn->tx_response; + conn->tx_response = NULL; + spin_unlock_irq(&conn->local->lock); + + if (conn->state != RXRPC_CONN_ABORTED) + rxrpc_send_response(conn, skb); + rxrpc_free_skb(skb, rxrpc_skb_put_response); + } + if (skb) { switch (skb->mark) { case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: @@ -452,3 +542,31 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) rxrpc_process_delayed_final_acks(conn, false); } + +/* + * Post a RESPONSE message to the I/O thread for transmission. + */ +void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_local *local = conn->local; + struct sk_buff *old; + + _enter("%x", sp->resp.challenge_serial); + + spin_lock_irq(&local->lock); + old = conn->tx_response; + if (old) { + struct rxrpc_skb_priv *osp = rxrpc_skb(skb); + + /* Always go with the response to the most recent challenge. */ + if (after(sp->resp.challenge_serial, osp->resp.challenge_serial)) + conn->tx_response = old; + else + old = skb; + } else { + conn->tx_response = skb; + } + spin_unlock_irq(&local->lock); + rxrpc_poke_conn(conn, rxrpc_conn_get_poke_response); +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 8ac22dde8b39..d14a802d2001 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -329,6 +329,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work) } rxrpc_purge_queue(&conn->rx_queue); + rxrpc_free_skb(conn->tx_response, rxrpc_skb_put_response); rxrpc_kill_client_conn(conn); diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index e068f9b79d02..1f7c136d6d0e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -42,13 +42,19 @@ static void none_free_call_crypto(struct rxrpc_call *call) { } -static int none_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb) +static bool none_validate_challenge(struct rxrpc_connection *conn, + struct sk_buff *skb) { return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, rxrpc_eproto_rxnull_challenge); } +static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge, + struct msghdr *msg) +{ + return -EINVAL; +} + static int none_verify_response(struct rxrpc_connection *conn, struct sk_buff *skb) { @@ -82,7 +88,8 @@ const struct rxrpc_security rxrpc_no_security = { .alloc_txbuf = none_alloc_txbuf, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, - .respond_to_challenge = none_respond_to_challenge, + .validate_challenge = none_validate_challenge, + .sendmsg_respond_to_challenge = none_sendmsg_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, }; diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 64f8d77b8731..27b650d30f4d 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -489,8 +489,8 @@ int rxrpc_io_thread(void *data) rxrpc_free_skb(skb, rxrpc_skb_put_error_report); break; case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: - rxrpc_input_conn_event(sp->conn, skb); - rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke); + rxrpc_input_conn_event(sp->poke_conn, skb); + rxrpc_put_connection(sp->poke_conn, rxrpc_conn_put_poke); rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured); break; default: @@ -501,9 +501,11 @@ int rxrpc_io_thread(void *data) } /* Deal with connections that want immediate attention. */ - spin_lock_irq(&local->lock); - list_splice_tail_init(&local->conn_attend_q, &conn_attend_q); - spin_unlock_irq(&local->lock); + if (!list_empty_careful(&local->conn_attend_q)) { + spin_lock_irq(&local->lock); + list_splice_tail_init(&local->conn_attend_q, &conn_attend_q); + spin_unlock_irq(&local->lock); + } while ((conn = list_first_entry_or_null(&conn_attend_q, struct rxrpc_connection, diff --git a/net/rxrpc/oob.c b/net/rxrpc/oob.c new file mode 100644 index 000000000000..3601022b9190 --- /dev/null +++ b/net/rxrpc/oob.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Out of band message handling (e.g. challenge-response) + * + * Copyright (C) 2025 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include "ar-internal.h" + +enum rxrpc_oob_command { + RXRPC_OOB_CMD_UNSET, + RXRPC_OOB_CMD_RESPOND, +} __mode(byte); + +struct rxrpc_oob_params { + u64 oob_id; /* ID number of message if reply */ + s32 abort_code; + enum rxrpc_oob_command command; + bool have_oob_id:1; +}; + +/* + * Post an out-of-band message for attention by the socket or kernel service + * associated with a reference call. + */ +void rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_sock *rx; + struct sock *sk; + + rcu_read_lock(); + + rx = rcu_dereference(call->socket); + if (rx) { + sk = &rx->sk; + spin_lock_irq(&rx->recvmsg_lock); + + if (sk->sk_state < RXRPC_CLOSE) { + skb->skb_mstamp_ns = rx->oob_id_counter++; + rxrpc_get_skb(skb, rxrpc_skb_get_post_oob); + skb_queue_tail(&rx->recvmsg_oobq, skb); + + trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); + if (rx->app_ops) + rx->app_ops->notify_oob(sk, skb); + } + + spin_unlock_irq(&rx->recvmsg_lock); + if (!rx->app_ops && !sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + } + + rcu_read_unlock(); +} + +/* + * Locate the OOB message to respond to by its ID. + */ +static struct sk_buff *rxrpc_find_pending_oob(struct rxrpc_sock *rx, u64 oob_id) +{ + struct rb_node *p; + struct sk_buff *skb; + + p = rx->pending_oobq.rb_node; + while (p) { + skb = rb_entry(p, struct sk_buff, rbnode); + + if (oob_id < skb->skb_mstamp_ns) + p = p->rb_left; + else if (oob_id > skb->skb_mstamp_ns) + p = p->rb_right; + else + return skb; + } + + return NULL; +} + +/* + * Add an OOB message into the pending-response set. We always assign the next + * value from a 64-bit counter to the oob_id, so just assume we're always going + * to be on the right-hand edge of the tree and that the counter won't wrap. + * The tree is also given a ref to the message. + */ +void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb) +{ + struct rb_node **pp = &rx->pending_oobq.rb_node, *p = NULL; + + while (*pp) { + p = *pp; + pp = &(*pp)->rb_right; + } + + rb_link_node(&skb->rbnode, p, pp); + rb_insert_color(&skb->rbnode, &rx->pending_oobq); +} + +/* + * Extract control messages from the sendmsg() control buffer. + */ +static int rxrpc_sendmsg_oob_cmsg(struct msghdr *msg, struct rxrpc_oob_params *p) +{ + struct cmsghdr *cmsg; + int len; + + if (msg->msg_controllen == 0) + return -EINVAL; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + len = cmsg->cmsg_len - sizeof(struct cmsghdr); + _debug("CMSG %d, %d, %d", + cmsg->cmsg_level, cmsg->cmsg_type, len); + + if (cmsg->cmsg_level != SOL_RXRPC) + continue; + + switch (cmsg->cmsg_type) { + case RXRPC_OOB_ID: + if (len != sizeof(p->oob_id) || p->have_oob_id) + return -EINVAL; + memcpy(&p->oob_id, CMSG_DATA(cmsg), sizeof(p->oob_id)); + p->have_oob_id = true; + break; + case RXRPC_RESPOND: + if (p->command != RXRPC_OOB_CMD_UNSET) + return -EINVAL; + p->command = RXRPC_OOB_CMD_RESPOND; + break; + case RXRPC_ABORT: + if (len != sizeof(p->abort_code) || p->abort_code) + return -EINVAL; + memcpy(&p->abort_code, CMSG_DATA(cmsg), sizeof(p->abort_code)); + if (p->abort_code == 0) + return -EINVAL; + break; + case RXRPC_RESP_RXGK_APPDATA: + if (p->command != RXRPC_OOB_CMD_RESPOND) + return -EINVAL; + break; + default: + return -EINVAL; + } + } + + switch (p->command) { + case RXRPC_OOB_CMD_RESPOND: + if (!p->have_oob_id) + return -EBADSLT; + break; + default: + return -EINVAL; + } + + return 0; +} + +/* + * Allow userspace to respond to an OOB using sendmsg(). + */ +static int rxrpc_respond_to_oob(struct rxrpc_sock *rx, + struct rxrpc_oob_params *p, + struct msghdr *msg) +{ + struct rxrpc_connection *conn; + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + int ret; + + skb = rxrpc_find_pending_oob(rx, p->oob_id); + if (skb) + rb_erase(&skb->rbnode, &rx->pending_oobq); + release_sock(&rx->sk); + if (!skb) + return -EBADSLT; + + sp = rxrpc_skb(skb); + + switch (p->command) { + case RXRPC_OOB_CMD_RESPOND: + ret = -EPROTO; + if (skb->mark != RXRPC_OOB_CHALLENGE) + break; + conn = sp->chall.conn; + ret = -EOPNOTSUPP; + if (!conn->security->sendmsg_respond_to_challenge) + break; + if (p->abort_code) { + rxrpc_abort_conn(conn, NULL, p->abort_code, -ECONNABORTED, + rxrpc_abort_response_sendmsg); + ret = 0; + } else { + ret = conn->security->sendmsg_respond_to_challenge(skb, msg); + } + break; + default: + ret = -EINVAL; + break; + } + + rxrpc_free_skb(skb, rxrpc_skb_put_oob); + return ret; +} + +/* + * Send an out-of-band message or respond to a received out-of-band message. + * - caller gives us the socket lock + * - the socket may be either a client socket or a server socket + */ +int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) +{ + struct rxrpc_oob_params p = {}; + int ret; + + _enter(""); + + ret = rxrpc_sendmsg_oob_cmsg(msg, &p); + if (ret < 0) + goto error_release_sock; + + if (p.have_oob_id) + return rxrpc_respond_to_oob(rx, &p, msg); + + release_sock(&rx->sk); + + switch (p.command) { + default: + ret = -EINVAL; + break; + } + + _leave(" = %d", ret); + return ret; + +error_release_sock: + release_sock(&rx->sk); + return ret; +} + +/** + * rxrpc_kernel_query_oob - Query the parameters of an out-of-band message + * @oob: The message to query + * @_peer: Where to return the peer record + * @_peer_appdata: The application data attached to a peer record + * + * Extract useful parameters from an out-of-band message. The source peer + * parameters are returned through the argument list and the message type is + * returned. + * + * Return: + * * %RXRPC_OOB_CHALLENGE - Challenge wanting a response. + */ +enum rxrpc_oob_type rxrpc_kernel_query_oob(struct sk_buff *oob, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(oob); + enum rxrpc_oob_type type = oob->mark; + + switch (type) { + case RXRPC_OOB_CHALLENGE: + *_peer = sp->chall.conn->peer; + *_peer_appdata = 0; /* TODO: retrieve appdata */ + break; + default: + WARN_ON_ONCE(1); + *_peer = NULL; + *_peer_appdata = 0; + break; + } + + return type; +} +EXPORT_SYMBOL(rxrpc_kernel_query_oob); + +/** + * rxrpc_kernel_dequeue_oob - Dequeue and return the front OOB message + * @sock: The socket to query + * @_type: Where to return the message type + * + * Dequeue the front OOB message, if there is one, and return it and + * its type. + * + * Return: The sk_buff representing the OOB message or %NULL if the queue was + * empty. + */ +struct sk_buff *rxrpc_kernel_dequeue_oob(struct socket *sock, + enum rxrpc_oob_type *_type) +{ + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + struct sk_buff *oob; + + oob = skb_dequeue(&rx->recvmsg_oobq); + if (oob) + *_type = oob->mark; + return oob; +} +EXPORT_SYMBOL(rxrpc_kernel_dequeue_oob); + +/** + * rxrpc_kernel_free_oob - Free an out-of-band message + * @oob: The OOB message to free + * + * Free an OOB message along with any resources it holds. + */ +void rxrpc_kernel_free_oob(struct sk_buff *oob) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(oob); + + switch (oob->mark) { + case RXRPC_OOB_CHALLENGE: + rxrpc_put_connection(sp->chall.conn, rxrpc_conn_put_oob); + break; + } + + rxrpc_free_skb(oob, rxrpc_skb_put_purge_oob); +} +EXPORT_SYMBOL(rxrpc_kernel_free_oob); + +/** + * rxrpc_kernel_query_challenge - Query the parameters of a challenge + * @challenge: The challenge to query + * @_peer: Where to return the peer record + * @_peer_appdata: The application data attached to a peer record + * @_service_id: Where to return the connection service ID + * @_security_index: Where to return the connection security index + * + * Extract useful parameters from a CHALLENGE message. + */ +void rxrpc_kernel_query_challenge(struct sk_buff *challenge, + struct rxrpc_peer **_peer, + unsigned long *_peer_appdata, + u16 *_service_id, u8 *_security_index) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(challenge); + + *_peer = sp->chall.conn->peer; + *_peer_appdata = 0; /* TODO: retrieve appdata */ + *_service_id = sp->hdr.serviceId; + *_security_index = sp->hdr.securityIndex; +} +EXPORT_SYMBOL(rxrpc_kernel_query_challenge); + +/** + * rxrpc_kernel_reject_challenge - Allow a kernel service to reject a challenge + * @challenge: The challenge to be rejected + * @abort_code: The abort code to stick into the ABORT packet + * @error: Local error value + * @why: Indication as to why. + * + * Allow a kernel service to reject a challenge by aborting the connection if + * it's still in an abortable state. The error is returned so this function + * can be used with a return statement. + * + * Return: The %error parameter. + */ +int rxrpc_kernel_reject_challenge(struct sk_buff *challenge, u32 abort_code, + int error, enum rxrpc_abort_reason why) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(challenge); + + _enter("{%x},%d,%d,%u", sp->hdr.serial, abort_code, error, why); + + rxrpc_abort_conn(sp->chall.conn, NULL, abort_code, error, why); + return error; +} +EXPORT_SYMBOL(rxrpc_kernel_reject_challenge); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 95905b85a8d7..04c900990a40 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -916,3 +916,59 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) peer->last_tx_at = ktime_get_seconds(); _leave(""); } + +/* + * Send a RESPONSE message. + */ +void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(response); + struct scatterlist sg[16]; + struct bio_vec bvec[16]; + struct msghdr msg; + size_t len = sp->resp.len; + __be32 wserial; + u32 serial = 0; + int ret, nr_sg; + + _enter("C=%x,%x", conn->debug_id, sp->resp.challenge_serial); + + sg_init_table(sg, ARRAY_SIZE(sg)); + ret = skb_to_sgvec(response, sg, 0, len); + if (ret < 0) + goto fail; + nr_sg = ret; + + for (int i = 0; i < nr_sg; i++) + bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset); + + iov_iter_bvec(&msg.msg_iter, WRITE, bvec, nr_sg, len); + + msg.msg_name = &conn->peer->srx.transport; + msg.msg_namelen = conn->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = MSG_SPLICE_PAGES; + + serial = rxrpc_get_next_serials(conn, 1); + wserial = htonl(serial); + + ret = skb_store_bits(response, offsetof(struct rxrpc_wire_header, serial), + &wserial, sizeof(wserial)); + if (ret < 0) + goto fail; + + rxrpc_local_dont_fragment(conn->local, false); + + ret = do_udp_sendmsg(conn->local->socket, &msg, len); + if (ret < 0) + goto fail; + + conn->peer->last_tx_at = ktime_get_seconds(); + return; + +fail: + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_point_response); + kleave(" = %d", ret); +} diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 4c622752a569..86a27fb55a1c 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -154,6 +154,82 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) return call->security->verify_packet(call, skb); } +/* + * Transcribe a call's user ID to a control message. + */ +static int rxrpc_recvmsg_user_id(struct rxrpc_call *call, struct msghdr *msg, + int flags) +{ + if (!test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) + return 0; + + if (flags & MSG_CMSG_COMPAT) { + unsigned int id32 = call->user_call_ID; + + return put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + sizeof(unsigned int), &id32); + } else { + unsigned long idl = call->user_call_ID; + + return put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, + sizeof(unsigned long), &idl); + } +} + +/* + * Deal with a CHALLENGE packet. + */ +static int rxrpc_recvmsg_challenge(struct socket *sock, struct msghdr *msg, + struct sk_buff *challenge, unsigned int flags) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(challenge); + struct rxrpc_connection *conn = sp->chall.conn; + + return conn->security->challenge_to_recvmsg(conn, challenge, msg); +} + +/* + * Process OOB packets. Called with the socket locked. + */ +static int rxrpc_recvmsg_oob(struct socket *sock, struct msghdr *msg, + unsigned int flags) +{ + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + struct sk_buff *skb; + bool need_response = false; + int ret; + + skb = skb_peek(&rx->recvmsg_oobq); + if (!skb) + return -EAGAIN; + rxrpc_see_skb(skb, rxrpc_skb_see_recvmsg); + + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_OOB_ID, sizeof(u64), + &skb->skb_mstamp_ns); + if (ret < 0) + return ret; + + switch ((enum rxrpc_oob_type)skb->mark) { + case RXRPC_OOB_CHALLENGE: + need_response = true; + ret = rxrpc_recvmsg_challenge(sock, msg, skb, flags); + break; + default: + WARN_ONCE(1, "recvmsg() can't process unknown OOB type %u\n", + skb->mark); + ret = -EIO; + break; + } + + if (!(flags & MSG_PEEK)) + skb_unlink(skb, &rx->recvmsg_oobq); + if (need_response) + rxrpc_add_pending_oob(rx, skb); + else + rxrpc_free_skb(skb, rxrpc_skb_put_oob); + return ret; +} + /* * Deliver messages to a call. This keeps processing packets until the buffer * is filled and we find either more DATA (returns 0) or the end of the DATA @@ -165,6 +241,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, size_t len, int flags, size_t *_offset) { struct rxrpc_skb_priv *sp; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); struct sk_buff *skb; rxrpc_seq_t seq = 0; size_t remain; @@ -207,7 +284,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, sp->offset, sp->len, ret2); if (ret2 < 0) { - kdebug("verify = %d", ret2); ret = ret2; goto out; } @@ -255,6 +331,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (!(flags & MSG_PEEK)) rxrpc_rotate_rx_window(call); + + if (!rx->app_ops && + !skb_queue_empty_lockless(&rx->recvmsg_oobq)) { + trace_rxrpc_recvdata(call, rxrpc_recvmsg_oobq, seq, + rx_pkt_offset, rx_pkt_len, ret); + break; + } } out: @@ -262,6 +345,7 @@ out: call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; } + done: trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, rx_pkt_offset, rx_pkt_len, ret); @@ -301,6 +385,7 @@ try_again: /* Return immediately if a client socket has no outstanding calls */ if (RB_EMPTY_ROOT(&rx->calls) && list_empty(&rx->recvmsg_q) && + skb_queue_empty_lockless(&rx->recvmsg_oobq) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); return -EAGAIN; @@ -322,7 +407,8 @@ try_again: if (ret) goto wait_error; - if (list_empty(&rx->recvmsg_q)) { + if (list_empty(&rx->recvmsg_q) && + skb_queue_empty_lockless(&rx->recvmsg_oobq)) { if (signal_pending(current)) goto wait_interrupted; trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0); @@ -332,6 +418,15 @@ try_again: goto try_again; } + /* Deal with OOB messages before we consider getting normal data. */ + if (!skb_queue_empty_lockless(&rx->recvmsg_oobq)) { + ret = rxrpc_recvmsg_oob(sock, msg, flags); + release_sock(&rx->sk); + if (ret == -EAGAIN) + goto try_again; + goto error_no_call; + } + /* Find the next call and dequeue it if we're not just peeking. If we * do dequeue it, that comes with a ref that we will need to release. * We also want to weed out calls that got requeued whilst we were @@ -342,7 +437,8 @@ try_again: call = list_entry(l, struct rxrpc_call, recvmsg_link); if (!rxrpc_call_is_complete(call) && - skb_queue_empty(&call->recvmsg_queue)) { + skb_queue_empty(&call->recvmsg_queue) && + skb_queue_empty(&rx->recvmsg_oobq)) { list_del_init(&call->recvmsg_link); spin_unlock_irq(&rx->recvmsg_lock); release_sock(&rx->sk); @@ -377,21 +473,9 @@ try_again: if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); - if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { - if (flags & MSG_CMSG_COMPAT) { - unsigned int id32 = call->user_call_ID; - - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, - sizeof(unsigned int), &id32); - } else { - unsigned long idl = call->user_call_ID; - - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID, - sizeof(unsigned long), &idl); - } - if (ret < 0) - goto error_unlock_call; - } + ret = rxrpc_recvmsg_user_id(call, msg, flags); + if (ret < 0) + goto error_unlock_call; if (msg->msg_name && call->peer) { size_t len = sizeof(call->dest_srx); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 6cb37b0eb77f..8ddccee69009 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -697,62 +697,6 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return 0; } -/* - * send a Kerberos security response - */ -static int rxkad_send_response(struct rxrpc_connection *conn, - struct rxrpc_host_header *hdr, - struct rxkad_response *resp, - const struct rxkad_key *s2) -{ - struct rxrpc_wire_header whdr; - struct msghdr msg; - struct kvec iov[3]; - size_t len; - u32 serial; - int ret; - - _enter(""); - - msg.msg_name = &conn->peer->srx.transport; - msg.msg_namelen = conn->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; - - memset(&whdr, 0, sizeof(whdr)); - whdr.epoch = htonl(hdr->epoch); - whdr.cid = htonl(hdr->cid); - whdr.type = RXRPC_PACKET_TYPE_RESPONSE; - whdr.flags = conn->out_clientflag; - whdr.securityIndex = hdr->securityIndex; - whdr.serviceId = htons(hdr->serviceId); - - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = resp; - iov[1].iov_len = sizeof(*resp); - iov[2].iov_base = (void *)s2->ticket; - iov[2].iov_len = s2->ticket_len; - - len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len; - - serial = rxrpc_get_next_serial(conn); - whdr.serial = htonl(serial); - - rxrpc_local_dont_fragment(conn->local, false); - ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); - if (ret < 0) { - trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_point_rxkad_response); - return -EAGAIN; - } - - conn->peer->last_tx_at = ktime_get_seconds(); - _leave(" = 0"); - return 0; -} - /* * calculate the response checksum */ @@ -772,12 +716,21 @@ static void rxkad_calc_response_checksum(struct rxkad_response *response) * encrypt the response packet */ static int rxkad_encrypt_response(struct rxrpc_connection *conn, - struct rxkad_response *resp, + struct sk_buff *response, const struct rxkad_key *s2) { struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg[1]; + size_t encsize = sizeof(((struct rxkad_response *)0)->encrypted); + int ret; + + sg_init_table(sg, ARRAY_SIZE(sg)); + ret = skb_to_sgvec(response, sg, + sizeof(struct rxrpc_wire_header) + + offsetof(struct rxkad_response, encrypted), encsize); + if (ret < 0) + return ret; req = skcipher_request_alloc(&conn->rxkad.cipher->base, GFP_NOFS); if (!req) @@ -786,88 +739,205 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn, /* continue encrypting from where we left off */ memcpy(&iv, s2->session_key, sizeof(iv)); - sg_init_table(sg, 1); - sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted)); skcipher_request_set_sync_tfm(req, conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); - crypto_skcipher_encrypt(req); + skcipher_request_set_crypt(req, sg, sg, encsize, iv.x); + ret = crypto_skcipher_encrypt(req); skcipher_request_free(req); - return 0; + return ret; } /* - * respond to a challenge packet + * Validate a challenge packet. */ -static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb) +static bool rxkad_validate_challenge(struct rxrpc_connection *conn, + struct sk_buff *skb) { - const struct rxrpc_key_token *token; struct rxkad_challenge challenge; - struct rxkad_response *resp; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - u32 version, nonce, min_level; - int ret = -EPROTO; + u32 version, min_level; + int ret; _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); - if (!conn->key) - return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, - rxkad_abort_chall_no_key); + if (!conn->key) { + rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxkad_abort_chall_no_key); + return false; + } ret = key_validate(conn->key); - if (ret < 0) - return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, - rxkad_abort_chall_key_expired); + if (ret < 0) { + rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, + rxkad_abort_chall_key_expired); + return false; + } if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - &challenge, sizeof(challenge)) < 0) - return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, - rxkad_abort_chall_short); + &challenge, sizeof(challenge)) < 0) { + rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_chall_short); + return false; + } version = ntohl(challenge.version); - nonce = ntohl(challenge.nonce); + sp->chall.rxkad_nonce = ntohl(challenge.nonce); min_level = ntohl(challenge.min_level); - trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level); + trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, + sp->chall.rxkad_nonce, min_level); - if (version != RXKAD_VERSION) - return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, - rxkad_abort_chall_version); + if (version != RXKAD_VERSION) { + rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, + rxkad_abort_chall_version); + return false; + } - if (conn->security_level < min_level) - return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES, - rxkad_abort_chall_level); + if (conn->security_level < min_level) { + rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES, + rxkad_abort_chall_level); + return false; + } + return true; +} + +/* + * Insert the header into the response. + */ +static noinline +int rxkad_insert_response_header(struct rxrpc_connection *conn, + const struct rxrpc_key_token *token, + struct sk_buff *challenge, + struct sk_buff *response, + size_t *offset) +{ + struct rxrpc_skb_priv *csp = rxrpc_skb(challenge); + struct { + struct rxrpc_wire_header whdr; + struct rxkad_response resp; + } h; + int ret; + + h.whdr.epoch = htonl(conn->proto.epoch); + h.whdr.cid = htonl(conn->proto.cid); + h.whdr.callNumber = 0; + h.whdr.serial = 0; + h.whdr.seq = 0; + h.whdr.type = RXRPC_PACKET_TYPE_RESPONSE; + h.whdr.flags = conn->out_clientflag; + h.whdr.userStatus = 0; + h.whdr.securityIndex = conn->security_ix; + h.whdr.cksum = 0; + h.whdr.serviceId = htons(conn->service_id); + h.resp.version = htonl(RXKAD_VERSION); + h.resp.__pad = 0; + h.resp.encrypted.epoch = htonl(conn->proto.epoch); + h.resp.encrypted.cid = htonl(conn->proto.cid); + h.resp.encrypted.checksum = 0; + h.resp.encrypted.securityIndex = htonl(conn->security_ix); + h.resp.encrypted.call_id[0] = htonl(conn->channels[0].call_counter); + h.resp.encrypted.call_id[1] = htonl(conn->channels[1].call_counter); + h.resp.encrypted.call_id[2] = htonl(conn->channels[2].call_counter); + h.resp.encrypted.call_id[3] = htonl(conn->channels[3].call_counter); + h.resp.encrypted.inc_nonce = htonl(csp->chall.rxkad_nonce + 1); + h.resp.encrypted.level = htonl(conn->security_level); + h.resp.kvno = htonl(token->kad->kvno); + h.resp.ticket_len = htonl(token->kad->ticket_len); + + rxkad_calc_response_checksum(&h.resp); + + ret = skb_store_bits(response, *offset, &h, sizeof(h)); + *offset += sizeof(h); + return ret; +} + +/* + * respond to a challenge packet + */ +static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, + struct sk_buff *challenge) +{ + const struct rxrpc_key_token *token; + struct rxrpc_skb_priv *csp, *rsp; + struct sk_buff *response; + size_t len, offset = 0; + int ret = -EPROTO; + + _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); + + ret = key_validate(conn->key); + if (ret < 0) + return rxrpc_abort_conn(conn, challenge, RXKADEXPIRED, ret, + rxkad_abort_chall_key_expired); token = conn->key->payload.data[0]; /* build the response packet */ - resp = kzalloc(sizeof(struct rxkad_response), GFP_NOFS); - if (!resp) - return -ENOMEM; + len = sizeof(struct rxrpc_wire_header) + + sizeof(struct rxkad_response) + + token->kad->ticket_len; + + response = alloc_skb_with_frags(0, len, 0, &ret, GFP_NOFS); + if (!response) + goto error; + rxrpc_new_skb(response, rxrpc_skb_new_response_rxkad); + response->len = len; + response->data_len = len; + + offset = 0; + ret = rxkad_insert_response_header(conn, token, challenge, response, + &offset); + if (ret < 0) + goto error; + + ret = rxkad_encrypt_response(conn, response, token->kad); + if (ret < 0) + goto error; + + ret = skb_store_bits(response, offset, token->kad->ticket, + token->kad->ticket_len); + if (ret < 0) + goto error; - resp->version = htonl(RXKAD_VERSION); - resp->encrypted.epoch = htonl(conn->proto.epoch); - resp->encrypted.cid = htonl(conn->proto.cid); - resp->encrypted.securityIndex = htonl(conn->security_ix); - resp->encrypted.inc_nonce = htonl(nonce + 1); - resp->encrypted.level = htonl(conn->security_level); - resp->kvno = htonl(token->kad->kvno); - resp->ticket_len = htonl(token->kad->ticket_len); - resp->encrypted.call_id[0] = htonl(conn->channels[0].call_counter); - resp->encrypted.call_id[1] = htonl(conn->channels[1].call_counter); - resp->encrypted.call_id[2] = htonl(conn->channels[2].call_counter); - resp->encrypted.call_id[3] = htonl(conn->channels[3].call_counter); - - /* calculate the response checksum and then do the encryption */ - rxkad_calc_response_checksum(resp); - ret = rxkad_encrypt_response(conn, resp, token->kad); - if (ret == 0) - ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); - kfree(resp); + csp = rxrpc_skb(challenge); + rsp = rxrpc_skb(response); + rsp->resp.len = len; + rsp->resp.challenge_serial = csp->hdr.serial; + rxrpc_post_response(conn, response); + response = NULL; + ret = 0; + +error: + rxrpc_free_skb(response, rxrpc_skb_put_response); return ret; } +/* + * RxKAD does automatic response only as there's nothing to manage that isn't + * already in the key. + */ +static int rxkad_sendmsg_respond_to_challenge(struct sk_buff *challenge, + struct msghdr *msg) +{ + return -EINVAL; +} + +/** + * rxkad_kernel_respond_to_challenge - Respond to a challenge with appdata + * @challenge: The challenge to respond to + * + * Allow a kernel application to respond to a CHALLENGE. + * + * Return: %0 if successful and a negative error code otherwise. + */ +int rxkad_kernel_respond_to_challenge(struct sk_buff *challenge) +{ + struct rxrpc_skb_priv *csp = rxrpc_skb(challenge); + + return rxkad_respond_to_challenge(csp->chall.conn, challenge); +} +EXPORT_SYMBOL(rxkad_kernel_respond_to_challenge); + /* * decrypt the kerberos IV ticket in the response */ @@ -1276,6 +1346,8 @@ const struct rxrpc_security rxkad = { .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, .issue_challenge = rxkad_issue_challenge, + .validate_challenge = rxkad_validate_challenge, + .sendmsg_respond_to_challenge = rxkad_sendmsg_respond_to_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, .clear = rxkad_clear, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 2342b5f1547c..ebbb78b842de 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -758,14 +758,21 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (rxrpc_call_is_complete(call)) { /* it's too late for this call */ ret = -ESHUTDOWN; - } else if (p.command == RXRPC_CMD_SEND_ABORT) { + goto out_put_unlock; + } + + switch (p.command) { + case RXRPC_CMD_SEND_ABORT: rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, rxrpc_abort_call_sendmsg); ret = 0; - } else if (p.command != RXRPC_CMD_SEND_DATA) { - ret = -EINVAL; - } else { + break; + case RXRPC_CMD_SEND_DATA: ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock); + break; + default: + ret = -EINVAL; + break; } out_put_unlock: diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c index eb7525e92951..36b05fd842a7 100644 --- a/net/rxrpc/server_key.c +++ b/net/rxrpc/server_key.c @@ -171,3 +171,43 @@ int rxrpc_sock_set_security_keyring(struct sock *sk, struct key *keyring) return ret; } EXPORT_SYMBOL(rxrpc_sock_set_security_keyring); + +/** + * rxrpc_sock_set_manage_response - Set the manage-response flag for a kernel service + * @sk: The socket to set the keyring on + * @set: True to set, false to clear the flag + * + * Set the flag on an rxrpc socket to say that the caller wants to manage the + * RESPONSE packet and the user-defined data it may contain. Setting this + * means that recvmsg() will return messages with RXRPC_CHALLENGED in the + * control message buffer containing information about the challenge. + * + * The user should respond to the challenge by passing RXRPC_RESPOND or + * RXRPC_RESPOND_ABORT control messages with sendmsg() to the same call. + * Supplementary control messages, such as RXRPC_RESP_RXGK_APPDATA, may be + * included to indicate the parts the user wants to supply. + * + * The server will be passed the response data with a RXRPC_RESPONDED control + * message when it gets the first data from each call. + * + * Note that this is only honoured by security classes that need auxiliary data + * (e.g. RxGK). Those that don't offer the facility (e.g. RxKAD) respond + * without consulting userspace. + * + * Return: The previous setting. + */ +int rxrpc_sock_set_manage_response(struct sock *sk, bool set) +{ + struct rxrpc_sock *rx = rxrpc_sk(sk); + int ret; + + lock_sock(sk); + ret = !!test_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); + if (set) + set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); + else + clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); + release_sock(sk); + return ret; +} +EXPORT_SYMBOL(rxrpc_sock_set_manage_response); -- cgit v1.2.3 From 01af64269751f261421a9e80a527c8e987aeda8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Apr 2025 10:52:50 +0100 Subject: rxrpc: Add the security index for yfs-rxgk Add the security index and abort codes for the YFS variant of rxgk. Signed-off-by: David Howells Link: https://patch.msgid.link/20250411095303.2316168-6-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- fs/afs/misc.c | 27 +++++++++++++++++++++++++++ include/crypto/krb5.h | 5 +++++ include/uapi/linux/rxrpc.h | 31 +++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/afs/misc.c b/fs/afs/misc.c index b8180bf2281f..8f2b3a177690 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "internal.h" #include "afs_fs.h" #include "protocol_uae.h" @@ -103,6 +104,32 @@ int afs_abort_to_error(u32 abort_code) case RXKADDATALEN: return -EKEYREJECTED; case RXKADILLEGALLEVEL: return -EKEYREJECTED; + case RXGK_INCONSISTENCY: return -EPROTO; + case RXGK_PACKETSHORT: return -EPROTO; + case RXGK_BADCHALLENGE: return -EPROTO; + case RXGK_SEALEDINCON: return -EKEYREJECTED; + case RXGK_NOTAUTH: return -EKEYREJECTED; + case RXGK_EXPIRED: return -EKEYEXPIRED; + case RXGK_BADLEVEL: return -EKEYREJECTED; + case RXGK_BADKEYNO: return -EKEYREJECTED; + case RXGK_NOTRXGK: return -EKEYREJECTED; + case RXGK_UNSUPPORTED: return -EKEYREJECTED; + case RXGK_GSSERROR: return -EKEYREJECTED; +#ifdef RXGK_BADETYPE + case RXGK_BADETYPE: return -ENOPKG; +#endif +#ifdef RXGK_BADTOKEN + case RXGK_BADTOKEN: return -EKEYREJECTED; +#endif +#ifdef RXGK_BADETYPE + case RXGK_DATALEN: return -EPROTO; +#endif +#ifdef RXGK_BADQOP + case RXGK_BADQOP: return -EKEYREJECTED; +#endif + + case KRB5_PROG_KEYTYPE_NOSUPP: return -ENOPKG; + case RXGEN_OPCODE: return -ENOTSUPP; default: return -EREMOTEIO; diff --git a/include/crypto/krb5.h b/include/crypto/krb5.h index 62d998e62f47..71dd38f59be1 100644 --- a/include/crypto/krb5.h +++ b/include/crypto/krb5.h @@ -63,6 +63,11 @@ struct scatterlist; #define KEY_USAGE_SEED_ENCRYPTION (0xAA) #define KEY_USAGE_SEED_INTEGRITY (0x55) +/* + * Standard Kerberos error codes. + */ +#define KRB5_PROG_KEYTYPE_NOSUPP -1765328233 + /* * Mode of operation. */ diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index c4e9833b0a12..d9735abd4c79 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -80,6 +80,7 @@ enum rxrpc_cmsg_type { #define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ #define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ #define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ +#define RXRPC_SECURITY_YFS_RXGK 6 /* YFS gssapi-based */ /* * RxRPC-level abort codes @@ -125,6 +126,36 @@ enum rxrpc_cmsg_type { #define RXKADDATALEN 19270411 /* user data too long */ #define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ +/* + * RxGK GSSAPI security abort codes. + */ +#if 0 /* Original standard abort codes (used by OpenAFS) */ +#define RXGK_INCONSISTENCY 1233242880 /* Security module structure inconsistent */ +#define RXGK_PACKETSHORT 1233242881 /* Packet too short for security challenge */ +#define RXGK_BADCHALLENGE 1233242882 /* Invalid security challenge */ +#define RXGK_BADETYPE 1233242883 /* Invalid or impermissible encryption type */ +#define RXGK_BADLEVEL 1233242884 /* Invalid or impermissible security level */ +#define RXGK_BADKEYNO 1233242885 /* Key version number not found */ +#define RXGK_EXPIRED 1233242886 /* Token has expired */ +#define RXGK_NOTAUTH 1233242887 /* Caller not authorized */ +#define RXGK_BAD_TOKEN 1233242888 /* Security object was passed a bad token */ +#define RXGK_SEALED_INCON 1233242889 /* Sealed data inconsistent */ +#define RXGK_DATA_LEN 1233242890 /* User data too long */ +#define RXGK_BAD_QOP 1233242891 /* Inadequate quality of protection available */ +#else /* Revised standard abort codes (used by YFS) */ +#define RXGK_INCONSISTENCY 1233242880 /* Security module structure inconsistent */ +#define RXGK_PACKETSHORT 1233242881 /* Packet too short for security challenge */ +#define RXGK_BADCHALLENGE 1233242882 /* Security challenge/response failed */ +#define RXGK_SEALEDINCON 1233242883 /* Sealed data is inconsistent */ +#define RXGK_NOTAUTH 1233242884 /* Caller not authorised */ +#define RXGK_EXPIRED 1233242885 /* Authentication expired */ +#define RXGK_BADLEVEL 1233242886 /* Unsupported or not permitted security level */ +#define RXGK_BADKEYNO 1233242887 /* Bad transport key number */ +#define RXGK_NOTRXGK 1233242888 /* Security layer is not rxgk */ +#define RXGK_UNSUPPORTED 1233242889 /* Endpoint does not support rxgk */ +#define RXGK_GSSERROR 1233242890 /* GSSAPI mechanism error */ +#endif + /* * Challenge information in the RXRPC_CHALLENGED control message. */ -- cgit v1.2.3 From 2396356a945bb022aff02656f59c2a45d457043f Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Wed, 26 Feb 2025 09:14:51 +0000 Subject: fuse: add more control over cache invalidation behaviour Currently userspace is able to notify the kernel to invalidate the cache for an inode. This means that, if all the inodes in a filesystem need to be invalidated, then userspace needs to iterate through all of them and do this kernel notification separately. This patch adds the concept of 'epoch': each fuse connection will have the current epoch initialized and every new dentry will have it's d_time set to the current epoch value. A new operation will then allow userspace to increment the epoch value. Every time a dentry is d_revalidate()'ed, it's epoch is compared with the current connection epoch and invalidated if it's value is different. Signed-off-by: Luis Henriques Tested-by: Laura Promberger Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 16 ++++++++++++++++ fs/fuse/dir.c | 27 ++++++++++++++++++++++----- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 1 + fs/fuse/readdir.c | 3 +++ include/uapi/linux/fuse.h | 6 +++++- 6 files changed, 50 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 6dcbaa218b7a..00888befb5c8 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2021,6 +2021,19 @@ static int fuse_notify_resend(struct fuse_conn *fc) return 0; } +/* + * Increments the fuse connection epoch. This will result of dentries from + * previous epochs to be invalidated. + * + * XXX optimization: add call to shrink_dcache_sb()? + */ +static int fuse_notify_inc_epoch(struct fuse_conn *fc) +{ + atomic_inc(&fc->epoch); + + return 0; +} + static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { @@ -2049,6 +2062,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, case FUSE_NOTIFY_RESEND: return fuse_notify_resend(fc); + case FUSE_NOTIFY_INC_EPOCH: + return fuse_notify_inc_epoch(fc); + default: fuse_copy_finish(cs); return -EINVAL; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 83ac192e7fdd..1fb0b15a6088 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -200,9 +200,14 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name, { struct inode *inode; struct fuse_mount *fm; + struct fuse_conn *fc; struct fuse_inode *fi; int ret; + fc = get_fuse_conn_super(dir->i_sb); + if (entry->d_time < atomic_read(&fc->epoch)) + goto invalid; + inode = d_inode_rcu(entry); if (inode && fuse_is_bad(inode)) goto invalid; @@ -415,16 +420,20 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, unsigned int flags) { - int err; struct fuse_entry_out outarg; + struct fuse_conn *fc; struct inode *inode; struct dentry *newent; + int err, epoch; bool outarg_valid = true; bool locked; if (fuse_is_bad(dir)) return ERR_PTR(-EIO); + fc = get_fuse_conn_super(dir->i_sb); + epoch = atomic_read(&fc->epoch); + locked = fuse_lock_inode(dir); err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name, &outarg, &inode); @@ -446,6 +455,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, goto out_err; entry = newent ? newent : entry; + entry->d_time = epoch; if (outarg_valid) fuse_change_entry_timeout(entry, &outarg); else @@ -619,7 +629,6 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir, struct dentry *entry, struct file *file, unsigned int flags, umode_t mode, u32 opcode) { - int err; struct inode *inode; struct fuse_mount *fm = get_fuse_mount(dir); FUSE_ARGS(args); @@ -629,11 +638,13 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir, struct fuse_entry_out outentry; struct fuse_inode *fi; struct fuse_file *ff; + int epoch, err; bool trunc = flags & O_TRUNC; /* Userspace expects S_IFREG in create mode */ BUG_ON((mode & S_IFMT) != S_IFREG); + epoch = atomic_read(&fm->fc->epoch); forget = fuse_alloc_forget(); err = -ENOMEM; if (!forget) @@ -702,6 +713,7 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir, } kfree(forget); d_instantiate(entry, inode); + entry->d_time = epoch; fuse_change_entry_timeout(entry, &outentry); fuse_dir_changed(dir); err = generic_file_open(inode, file); @@ -788,12 +800,14 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun struct fuse_entry_out outarg; struct inode *inode; struct dentry *d; - int err; struct fuse_forget_link *forget; + int epoch, err; if (fuse_is_bad(dir)) return ERR_PTR(-EIO); + epoch = atomic_read(&fm->fc->epoch); + forget = fuse_alloc_forget(); if (!forget) return ERR_PTR(-ENOMEM); @@ -835,10 +849,13 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun if (IS_ERR(d)) return d; - if (d) + if (d) { + d->d_time = epoch; fuse_change_entry_timeout(d, &outarg); - else + } else { + entry->d_time = epoch; fuse_change_entry_timeout(entry, &outarg); + } fuse_dir_changed(dir); return d; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index f359efc3c2cf..74340e4eebe5 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -636,6 +636,9 @@ struct fuse_conn { /** Number of fuse_dev's */ atomic_t dev_count; + /** Current epoch for up-to-date dentries */ + atomic_t epoch; + struct rcu_head rcu; /** The user id for this mount */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9471cc57637f..bfe8d8af46f3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -962,6 +962,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, init_rwsem(&fc->killsb); refcount_set(&fc->count, 1); atomic_set(&fc->dev_count, 1); + atomic_set(&fc->epoch, 1); init_waitqueue_head(&fc->blocked_waitq); fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv); INIT_LIST_HEAD(&fc->bg_queue); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 17ce9636a2b1..46b7146f2c0d 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -161,6 +161,7 @@ static int fuse_direntplus_link(struct file *file, struct fuse_conn *fc; struct inode *inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + int epoch; if (!o->nodeid) { /* @@ -190,6 +191,7 @@ static int fuse_direntplus_link(struct file *file, return -EIO; fc = get_fuse_conn(dir); + epoch = atomic_read(&fc->epoch); name.hash = full_name_hash(parent, name.name, name.len); dentry = d_lookup(parent, &name); @@ -256,6 +258,7 @@ retry: } if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); + dentry->d_time = epoch; fuse_change_entry_timeout(dentry, o); dput(dentry); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 5ec43ecbceb7..122d6586e8d4 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -232,6 +232,9 @@ * * 7.43 * - add FUSE_REQUEST_TIMEOUT + * + * 7.44 + * - add FUSE_NOTIFY_INC_EPOCH */ #ifndef _LINUX_FUSE_H @@ -267,7 +270,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 43 +#define FUSE_KERNEL_MINOR_VERSION 44 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -671,6 +674,7 @@ enum fuse_notify_code { FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_DELETE = 6, FUSE_NOTIFY_RESEND = 7, + FUSE_NOTIFY_INC_EPOCH = 8, FUSE_NOTIFY_CODE_MAX, }; -- cgit v1.2.3 From b7a63391aa982295bbb3125e7d4470f51f31ff0f Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 15 Apr 2025 13:17:19 +0200 Subject: ovpn: add basic netlink support This commit introduces basic netlink support with family registration/unregistration functionalities and stub pre/post-doit. More importantly it introduces the YAML uAPI description along with its auto-generated files: - include/uapi/linux/ovpn.h - drivers/net/ovpn/netlink-gen.c - drivers/net/ovpn/netlink-gen.h Reviewed-by: Donald Hunter Signed-off-by: Antonio Quartulli Link: https://patch.msgid.link/20250415-b4-ovpn-v26-2-577f6097b964@openvpn.net Reviewed-by: Sabrina Dubroca Tested-by: Oleksandr Natalenko Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/ovpn.yaml | 367 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + drivers/net/ovpn/Makefile | 2 + drivers/net/ovpn/main.c | 31 +++ drivers/net/ovpn/main.h | 14 ++ drivers/net/ovpn/netlink-gen.c | 213 ++++++++++++++++++++ drivers/net/ovpn/netlink-gen.h | 41 ++++ drivers/net/ovpn/netlink.c | 160 +++++++++++++++ drivers/net/ovpn/netlink.h | 15 ++ drivers/net/ovpn/ovpnpriv.h | 21 ++ include/uapi/linux/ovpn.h | 109 ++++++++++ 11 files changed, 975 insertions(+) create mode 100644 Documentation/netlink/specs/ovpn.yaml create mode 100644 drivers/net/ovpn/main.h create mode 100644 drivers/net/ovpn/netlink-gen.c create mode 100644 drivers/net/ovpn/netlink-gen.h create mode 100644 drivers/net/ovpn/netlink.c create mode 100644 drivers/net/ovpn/netlink.h create mode 100644 drivers/net/ovpn/ovpnpriv.h create mode 100644 include/uapi/linux/ovpn.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ovpn.yaml b/Documentation/netlink/specs/ovpn.yaml new file mode 100644 index 000000000000..096c51f0c69a --- /dev/null +++ b/Documentation/netlink/specs/ovpn.yaml @@ -0,0 +1,367 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +# +# Author: Antonio Quartulli +# +# Copyright (c) 2024-2025, OpenVPN Inc. +# + +name: ovpn + +protocol: genetlink + +doc: Netlink protocol to control OpenVPN network devices + +definitions: + - + type: const + name: nonce-tail-size + value: 8 + - + type: enum + name: cipher-alg + entries: [ none, aes-gcm, chacha20-poly1305 ] + - + type: enum + name: del-peer-reason + entries: + - teardown + - userspace + - expired + - transport-error + - transport-disconnect + - + type: enum + name: key-slot + entries: [ primary, secondary ] + +attribute-sets: + - + name: peer + attributes: + - + name: id + type: u32 + doc: >- + The unique ID of the peer in the device context. To be used to identify + peers during operations for a specific device + checks: + max: 0xFFFFFF + - + name: remote-ipv4 + type: u32 + doc: The remote IPv4 address of the peer + byte-order: big-endian + display-hint: ipv4 + - + name: remote-ipv6 + type: binary + doc: The remote IPv6 address of the peer + display-hint: ipv6 + checks: + exact-len: 16 + - + name: remote-ipv6-scope-id + type: u32 + doc: The scope id of the remote IPv6 address of the peer (RFC2553) + - + name: remote-port + type: u16 + doc: The remote port of the peer + byte-order: big-endian + checks: + min: 1 + - + name: socket + type: u32 + doc: The socket to be used to communicate with the peer + - + name: socket-netnsid + type: s32 + doc: The ID of the netns the socket assigned to this peer lives in + - + name: vpn-ipv4 + type: u32 + doc: The IPv4 address assigned to the peer by the server + byte-order: big-endian + display-hint: ipv4 + - + name: vpn-ipv6 + type: binary + doc: The IPv6 address assigned to the peer by the server + display-hint: ipv6 + checks: + exact-len: 16 + - + name: local-ipv4 + type: u32 + doc: The local IPv4 to be used to send packets to the peer (UDP only) + byte-order: big-endian + display-hint: ipv4 + - + name: local-ipv6 + type: binary + doc: The local IPv6 to be used to send packets to the peer (UDP only) + display-hint: ipv6 + checks: + exact-len: 16 + - + name: local-port + type: u16 + doc: The local port to be used to send packets to the peer (UDP only) + byte-order: big-endian + checks: + min: 1 + - + name: keepalive-interval + type: u32 + doc: >- + The number of seconds after which a keep alive message is sent to the + peer + - + name: keepalive-timeout + type: u32 + doc: >- + The number of seconds from the last activity after which the peer is + assumed dead + - + name: del-reason + type: u32 + doc: The reason why a peer was deleted + enum: del-peer-reason + - + name: vpn-rx-bytes + type: uint + doc: Number of bytes received over the tunnel + - + name: vpn-tx-bytes + type: uint + doc: Number of bytes transmitted over the tunnel + - + name: vpn-rx-packets + type: uint + doc: Number of packets received over the tunnel + - + name: vpn-tx-packets + type: uint + doc: Number of packets transmitted over the tunnel + - + name: link-rx-bytes + type: uint + doc: Number of bytes received at the transport level + - + name: link-tx-bytes + type: uint + doc: Number of bytes transmitted at the transport level + - + name: link-rx-packets + type: uint + doc: Number of packets received at the transport level + - + name: link-tx-packets + type: uint + doc: Number of packets transmitted at the transport level + - + name: keyconf + attributes: + - + name: peer-id + type: u32 + doc: >- + The unique ID of the peer in the device context. To be used to + identify peers during key operations + checks: + max: 0xFFFFFF + - + name: slot + type: u32 + doc: The slot where the key should be stored + enum: key-slot + - + name: key-id + doc: >- + The unique ID of the key in the peer context. Used to fetch the + correct key upon decryption + type: u32 + checks: + max: 7 + - + name: cipher-alg + type: u32 + doc: The cipher to be used when communicating with the peer + enum: cipher-alg + - + name: encrypt-dir + type: nest + doc: Key material for encrypt direction + nested-attributes: keydir + - + name: decrypt-dir + type: nest + doc: Key material for decrypt direction + nested-attributes: keydir + - + name: keydir + attributes: + - + name: cipher-key + type: binary + doc: The actual key to be used by the cipher + checks: + max-len: 256 + - + name: nonce-tail + type: binary + doc: >- + Random nonce to be concatenated to the packet ID, in order to + obtain the actual cipher IV + checks: + exact-len: nonce-tail-size + - + name: ovpn + attributes: + - + name: ifindex + type: u32 + doc: Index of the ovpn interface to operate on + - + name: peer + type: nest + doc: >- + The peer object containing the attributed of interest for the specific + operation + nested-attributes: peer + - + name: keyconf + type: nest + doc: Peer specific cipher configuration + nested-attributes: keyconf + +operations: + list: + - + name: peer-new + attribute-set: ovpn + flags: [ admin-perm ] + doc: Add a remote peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - peer + - + name: peer-set + attribute-set: ovpn + flags: [ admin-perm ] + doc: modify a remote peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - peer + - + name: peer-get + attribute-set: ovpn + flags: [ admin-perm ] + doc: Retrieve data about existing remote peers (or a specific one) + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - peer + reply: + attributes: + - peer + dump: + request: + attributes: + - ifindex + reply: + attributes: + - peer + - + name: peer-del + attribute-set: ovpn + flags: [ admin-perm ] + doc: Delete existing remote peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - peer + - + name: peer-del-ntf + doc: Notification about a peer being deleted + notify: peer-get + mcgrp: peers + + - + name: key-new + attribute-set: ovpn + flags: [ admin-perm ] + doc: Add a cipher key for a specific peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - keyconf + - + name: key-get + attribute-set: ovpn + flags: [ admin-perm ] + doc: Retrieve non-sensitive data about peer key and cipher + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - keyconf + reply: + attributes: + - keyconf + - + name: key-swap + attribute-set: ovpn + flags: [ admin-perm ] + doc: Swap primary and secondary session keys for a specific peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - keyconf + - + name: key-swap-ntf + notify: key-get + doc: >- + Notification about key having exhausted its IV space and requiring + renegotiation + mcgrp: peers + - + name: key-del + attribute-set: ovpn + flags: [ admin-perm ] + doc: Delete cipher key for a specific peer + do: + pre: ovpn-nl-pre-doit + post: ovpn-nl-post-doit + request: + attributes: + - ifindex + - keyconf + +mcast-groups: + list: + - + name: peers diff --git a/MAINTAINERS b/MAINTAINERS index d0d77f43c5af..c50e87ef7288 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18131,7 +18131,9 @@ L: openvpn-devel@lists.sourceforge.net (subscribers-only) L: netdev@vger.kernel.org S: Supported T: git https://github.com/OpenVPN/linux-kernel-ovpn.git +F: Documentation/netlink/specs/ovpn.yaml F: drivers/net/ovpn/ +F: include/uapi/linux/ovpn.h OPENVSWITCH M: Aaron Conole diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile index 876800ebaa21..75ac62bba029 100644 --- a/drivers/net/ovpn/Makefile +++ b/drivers/net/ovpn/Makefile @@ -8,3 +8,5 @@ obj-$(CONFIG_OVPN) := ovpn.o ovpn-y += main.o +ovpn-y += netlink.o +ovpn-y += netlink-gen.o diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index d5d4ac8da6d7..719cac3db6ef 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -7,9 +7,29 @@ * James Yonan */ +#include #include #include #include +#include + +#include "ovpnpriv.h" +#include "main.h" +#include "netlink.h" + +static const struct net_device_ops ovpn_netdev_ops = { +}; + +/** + * ovpn_dev_is_valid - check if the netdevice is of type 'ovpn' + * @dev: the interface to check + * + * Return: whether the netdevice is of type 'ovpn' + */ +bool ovpn_dev_is_valid(const struct net_device *dev) +{ + return dev->netdev_ops == &ovpn_netdev_ops; +} static int ovpn_newlink(struct net_device *dev, struct rtnl_newlink_params *params, @@ -34,11 +54,22 @@ static int __init ovpn_init(void) return err; } + err = ovpn_nl_register(); + if (err) { + pr_err("ovpn: can't register netlink family: %d\n", err); + goto unreg_rtnl; + } + return 0; + +unreg_rtnl: + rtnl_link_unregister(&ovpn_link_ops); + return err; } static __exit void ovpn_cleanup(void) { + ovpn_nl_unregister(); rtnl_link_unregister(&ovpn_link_ops); rcu_barrier(); diff --git a/drivers/net/ovpn/main.h b/drivers/net/ovpn/main.h new file mode 100644 index 000000000000..017cd0100765 --- /dev/null +++ b/drivers/net/ovpn/main.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + */ + +#ifndef _NET_OVPN_MAIN_H_ +#define _NET_OVPN_MAIN_H_ + +bool ovpn_dev_is_valid(const struct net_device *dev); + +#endif /* _NET_OVPN_MAIN_H_ */ diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c new file mode 100644 index 000000000000..58e1a4342378 --- /dev/null +++ b/drivers/net/ovpn/netlink-gen.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ovpn.yaml */ +/* YNL-GEN kernel source */ + +#include +#include + +#include "netlink-gen.h" + +#include + +/* Integer value ranges */ +static const struct netlink_range_validation ovpn_a_peer_id_range = { + .max = 16777215ULL, +}; + +static const struct netlink_range_validation ovpn_a_keyconf_peer_id_range = { + .max = 16777215ULL, +}; + +/* Common nested types */ +const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1] = { + [OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range), + [OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1), + [OVPN_A_KEYCONF_KEY_ID] = NLA_POLICY_MAX(NLA_U32, 7), + [OVPN_A_KEYCONF_CIPHER_ALG] = NLA_POLICY_MAX(NLA_U32, 2), + [OVPN_A_KEYCONF_ENCRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy), + [OVPN_A_KEYCONF_DECRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy), +}; + +const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1] = { + [OVPN_A_KEYDIR_CIPHER_KEY] = NLA_POLICY_MAX_LEN(256), + [OVPN_A_KEYDIR_NONCE_TAIL] = NLA_POLICY_EXACT_LEN(OVPN_NONCE_TAIL_SIZE), +}; + +const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1] = { + [OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range), + [OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, }, + [OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_SOCKET] = { .type = NLA_U32, }, + [OVPN_A_PEER_SOCKET_NETNSID] = { .type = NLA_S32, }, + [OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, + [OVPN_A_PEER_DEL_REASON] = NLA_POLICY_MAX(NLA_U32, 4), + [OVPN_A_PEER_VPN_RX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_TX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_RX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_TX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_RX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_TX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_RX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_TX_PACKETS] = { .type = NLA_UINT, }, +}; + +/* OVPN_CMD_PEER_NEW - do */ +static const struct nla_policy ovpn_peer_new_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_SET - do */ +static const struct nla_policy ovpn_peer_set_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_GET - do */ +static const struct nla_policy ovpn_peer_get_do_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_GET - dump */ +static const struct nla_policy ovpn_peer_get_dump_nl_policy[OVPN_A_IFINDEX + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, +}; + +/* OVPN_CMD_PEER_DEL - do */ +static const struct nla_policy ovpn_peer_del_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_KEY_NEW - do */ +static const struct nla_policy ovpn_key_new_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_GET - do */ +static const struct nla_policy ovpn_key_get_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_SWAP - do */ +static const struct nla_policy ovpn_key_swap_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_DEL - do */ +static const struct nla_policy ovpn_key_del_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* Ops table for ovpn */ +static const struct genl_split_ops ovpn_nl_ops[] = { + { + .cmd = OVPN_CMD_PEER_NEW, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_new_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_new_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_SET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_set_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_set_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_GET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_get_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_get_do_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_GET, + .dumpit = ovpn_nl_peer_get_dumpit, + .policy = ovpn_peer_get_dump_nl_policy, + .maxattr = OVPN_A_IFINDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = OVPN_CMD_PEER_DEL, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_del_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_del_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_NEW, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_new_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_new_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_GET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_get_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_get_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_SWAP, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_swap_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_swap_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_DEL, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_del_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_del_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, +}; + +static const struct genl_multicast_group ovpn_nl_mcgrps[] = { + [OVPN_NLGRP_PEERS] = { "peers", }, +}; + +struct genl_family ovpn_nl_family __ro_after_init = { + .name = OVPN_FAMILY_NAME, + .version = OVPN_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = ovpn_nl_ops, + .n_split_ops = ARRAY_SIZE(ovpn_nl_ops), + .mcgrps = ovpn_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(ovpn_nl_mcgrps), +}; diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h new file mode 100644 index 000000000000..66a4e4a0a055 --- /dev/null +++ b/drivers/net/ovpn/netlink-gen.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ovpn.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_OVPN_GEN_H +#define _LINUX_OVPN_GEN_H + +#include +#include + +#include + +/* Common nested types */ +extern const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1]; +extern const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1]; +extern const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1]; + +int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); + +int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info); + +enum { + OVPN_NLGRP_PEERS, +}; + +extern struct genl_family ovpn_nl_family; + +#endif /* _LINUX_OVPN_GEN_H */ diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c new file mode 100644 index 000000000000..8d267d4c8228 --- /dev/null +++ b/drivers/net/ovpn/netlink.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + */ + +#include +#include + +#include + +#include "ovpnpriv.h" +#include "main.h" +#include "netlink.h" +#include "netlink-gen.h" + +MODULE_ALIAS_GENL_FAMILY(OVPN_FAMILY_NAME); + +/** + * ovpn_get_dev_from_attrs - retrieve the ovpn private data from the netdevice + * a netlink message is targeting + * @net: network namespace where to look for the interface + * @info: generic netlink info from the user request + * @tracker: tracker object to be used for the netdev reference acquisition + * + * Return: the ovpn private data, if found, or an error otherwise + */ +static struct ovpn_priv * +ovpn_get_dev_from_attrs(struct net *net, const struct genl_info *info, + netdevice_tracker *tracker) +{ + struct ovpn_priv *ovpn; + struct net_device *dev; + int ifindex; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_IFINDEX)) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[OVPN_A_IFINDEX]); + + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + NL_SET_ERR_MSG_MOD(info->extack, + "ifindex does not match any interface"); + return ERR_PTR(-ENODEV); + } + + if (!ovpn_dev_is_valid(dev)) { + rcu_read_unlock(); + NL_SET_ERR_MSG_MOD(info->extack, + "specified interface is not ovpn"); + NL_SET_BAD_ATTR(info->extack, info->attrs[OVPN_A_IFINDEX]); + return ERR_PTR(-EINVAL); + } + + ovpn = netdev_priv(dev); + netdev_hold(dev, tracker, GFP_ATOMIC); + rcu_read_unlock(); + + return ovpn; +} + +int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1]; + struct ovpn_priv *ovpn = ovpn_get_dev_from_attrs(genl_info_net(info), + info, tracker); + + if (IS_ERR(ovpn)) + return PTR_ERR(ovpn); + + info->user_ptr[0] = ovpn; + + return 0; +} + +void ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + + if (ovpn) + netdev_put(ovpn->dev, tracker); +} + +int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info) +{ + return -EOPNOTSUPP; +} + +/** + * ovpn_nl_register - perform any needed registration in the NL subsustem + * + * Return: 0 on success, a negative error code otherwise + */ +int __init ovpn_nl_register(void) +{ + int ret = genl_register_family(&ovpn_nl_family); + + if (ret) { + pr_err("ovpn: genl_register_family failed: %d\n", ret); + return ret; + } + + return 0; +} + +/** + * ovpn_nl_unregister - undo any module wide netlink registration + */ +void ovpn_nl_unregister(void) +{ + genl_unregister_family(&ovpn_nl_family); +} diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h new file mode 100644 index 000000000000..0d6c34e17082 --- /dev/null +++ b/drivers/net/ovpn/netlink.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + */ + +#ifndef _NET_OVPN_NETLINK_H_ +#define _NET_OVPN_NETLINK_H_ + +int ovpn_nl_register(void); +void ovpn_nl_unregister(void); + +#endif /* _NET_OVPN_NETLINK_H_ */ diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h new file mode 100644 index 000000000000..f9322536b06d --- /dev/null +++ b/drivers/net/ovpn/ovpnpriv.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan + * Antonio Quartulli + */ + +#ifndef _NET_OVPN_OVPNSTRUCT_H_ +#define _NET_OVPN_OVPNSTRUCT_H_ + +/** + * struct ovpn_priv - per ovpn interface state + * @dev: the actual netdev representing the tunnel + */ +struct ovpn_priv { + struct net_device *dev; +}; + +#endif /* _NET_OVPN_OVPNSTRUCT_H_ */ diff --git a/include/uapi/linux/ovpn.h b/include/uapi/linux/ovpn.h new file mode 100644 index 000000000000..680d1522dc87 --- /dev/null +++ b/include/uapi/linux/ovpn.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ovpn.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_OVPN_H +#define _UAPI_LINUX_OVPN_H + +#define OVPN_FAMILY_NAME "ovpn" +#define OVPN_FAMILY_VERSION 1 + +#define OVPN_NONCE_TAIL_SIZE 8 + +enum ovpn_cipher_alg { + OVPN_CIPHER_ALG_NONE, + OVPN_CIPHER_ALG_AES_GCM, + OVPN_CIPHER_ALG_CHACHA20_POLY1305, +}; + +enum ovpn_del_peer_reason { + OVPN_DEL_PEER_REASON_TEARDOWN, + OVPN_DEL_PEER_REASON_USERSPACE, + OVPN_DEL_PEER_REASON_EXPIRED, + OVPN_DEL_PEER_REASON_TRANSPORT_ERROR, + OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT, +}; + +enum ovpn_key_slot { + OVPN_KEY_SLOT_PRIMARY, + OVPN_KEY_SLOT_SECONDARY, +}; + +enum { + OVPN_A_PEER_ID = 1, + OVPN_A_PEER_REMOTE_IPV4, + OVPN_A_PEER_REMOTE_IPV6, + OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID, + OVPN_A_PEER_REMOTE_PORT, + OVPN_A_PEER_SOCKET, + OVPN_A_PEER_SOCKET_NETNSID, + OVPN_A_PEER_VPN_IPV4, + OVPN_A_PEER_VPN_IPV6, + OVPN_A_PEER_LOCAL_IPV4, + OVPN_A_PEER_LOCAL_IPV6, + OVPN_A_PEER_LOCAL_PORT, + OVPN_A_PEER_KEEPALIVE_INTERVAL, + OVPN_A_PEER_KEEPALIVE_TIMEOUT, + OVPN_A_PEER_DEL_REASON, + OVPN_A_PEER_VPN_RX_BYTES, + OVPN_A_PEER_VPN_TX_BYTES, + OVPN_A_PEER_VPN_RX_PACKETS, + OVPN_A_PEER_VPN_TX_PACKETS, + OVPN_A_PEER_LINK_RX_BYTES, + OVPN_A_PEER_LINK_TX_BYTES, + OVPN_A_PEER_LINK_RX_PACKETS, + OVPN_A_PEER_LINK_TX_PACKETS, + + __OVPN_A_PEER_MAX, + OVPN_A_PEER_MAX = (__OVPN_A_PEER_MAX - 1) +}; + +enum { + OVPN_A_KEYCONF_PEER_ID = 1, + OVPN_A_KEYCONF_SLOT, + OVPN_A_KEYCONF_KEY_ID, + OVPN_A_KEYCONF_CIPHER_ALG, + OVPN_A_KEYCONF_ENCRYPT_DIR, + OVPN_A_KEYCONF_DECRYPT_DIR, + + __OVPN_A_KEYCONF_MAX, + OVPN_A_KEYCONF_MAX = (__OVPN_A_KEYCONF_MAX - 1) +}; + +enum { + OVPN_A_KEYDIR_CIPHER_KEY = 1, + OVPN_A_KEYDIR_NONCE_TAIL, + + __OVPN_A_KEYDIR_MAX, + OVPN_A_KEYDIR_MAX = (__OVPN_A_KEYDIR_MAX - 1) +}; + +enum { + OVPN_A_IFINDEX = 1, + OVPN_A_PEER, + OVPN_A_KEYCONF, + + __OVPN_A_MAX, + OVPN_A_MAX = (__OVPN_A_MAX - 1) +}; + +enum { + OVPN_CMD_PEER_NEW = 1, + OVPN_CMD_PEER_SET, + OVPN_CMD_PEER_GET, + OVPN_CMD_PEER_DEL, + OVPN_CMD_PEER_DEL_NTF, + OVPN_CMD_KEY_NEW, + OVPN_CMD_KEY_GET, + OVPN_CMD_KEY_SWAP, + OVPN_CMD_KEY_SWAP_NTF, + OVPN_CMD_KEY_DEL, + + __OVPN_CMD_MAX, + OVPN_CMD_MAX = (__OVPN_CMD_MAX - 1) +}; + +#define OVPN_MCGRP_PEERS "peers" + +#endif /* _UAPI_LINUX_OVPN_H */ -- cgit v1.2.3 From c2d950c4672a012ea9765c15a389cdcdf919f652 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 15 Apr 2025 13:17:20 +0200 Subject: ovpn: add basic interface creation/destruction/management routines Add basic infrastructure for handling ovpn interfaces. Tested-by: Donald Hunter Signed-off-by: Antonio Quartulli Link: https://patch.msgid.link/20250415-b4-ovpn-v26-3-577f6097b964@openvpn.net Reviewed-by: Sabrina Dubroca Tested-by: Oleksandr Natalenko Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/rt-link.yaml | 16 +++++++ drivers/net/ovpn/Makefile | 1 + drivers/net/ovpn/io.c | 22 +++++++++ drivers/net/ovpn/io.h | 24 ++++++++++ drivers/net/ovpn/main.c | 82 +++++++++++++++++++++++++++++++- drivers/net/ovpn/ovpnpriv.h | 5 ++ drivers/net/ovpn/proto.h | 38 +++++++++++++++ include/uapi/linux/if_link.h | 15 ++++++ 8 files changed, 201 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ovpn/io.c create mode 100644 drivers/net/ovpn/io.h create mode 100644 drivers/net/ovpn/proto.h (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 31238455f8e9..a50d9d7d882e 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -938,6 +938,12 @@ definitions: entries: - name: none - name: default + - + name: ovpn-mode + type: enum + entries: + - p2p + - mp attribute-sets: - @@ -2272,6 +2278,13 @@ attribute-sets: - name: tailroom type: u16 + - + name: linkinfo-ovpn-attrs + attributes: + - + name: mode + type: u8 + enum: ovpn-mode sub-messages: - @@ -2322,6 +2335,9 @@ sub-messages: - value: netkit attribute-set: linkinfo-netkit-attrs + - + value: ovpn + attribute-set: linkinfo-ovpn-attrs - name: linkinfo-member-data-msg formats: diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile index 75ac62bba029..0e5f686672fb 100644 --- a/drivers/net/ovpn/Makefile +++ b/drivers/net/ovpn/Makefile @@ -8,5 +8,6 @@ obj-$(CONFIG_OVPN) := ovpn.o ovpn-y += main.o +ovpn-y += io.o ovpn-y += netlink.o ovpn-y += netlink-gen.o diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c new file mode 100644 index 000000000000..4b71c38165d7 --- /dev/null +++ b/drivers/net/ovpn/io.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan + * Antonio Quartulli + */ + +#include +#include + +#include "io.h" + +/* Send user data to the network + */ +netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) +{ + skb_tx_error(skb); + kfree_skb(skb); + return NET_XMIT_DROP; +} diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h new file mode 100644 index 000000000000..afea5f81f562 --- /dev/null +++ b/drivers/net/ovpn/io.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan + * Antonio Quartulli + */ + +#ifndef _NET_OVPN_OVPN_H_ +#define _NET_OVPN_OVPN_H_ + +/* DATA_V2 header size with AEAD encryption */ +#define OVPN_HEAD_ROOM (OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE + \ + 16 /* AEAD TAG length */ + \ + max(sizeof(struct udphdr), sizeof(struct tcphdr)) +\ + max(sizeof(struct ipv6hdr), sizeof(struct iphdr))) + +/* max padding required by encryption */ +#define OVPN_MAX_PADDING 16 + +netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev); + +#endif /* _NET_OVPN_OVPN_H_ */ diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 719cac3db6ef..ea7dad374c00 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -10,14 +10,28 @@ #include #include #include +#include +#include #include -#include +#include #include "ovpnpriv.h" #include "main.h" #include "netlink.h" +#include "io.h" +#include "proto.h" static const struct net_device_ops ovpn_netdev_ops = { + .ndo_start_xmit = ovpn_net_xmit, +}; + +static const struct device_type ovpn_type = { + .name = OVPN_FAMILY_NAME, +}; + +static const struct nla_policy ovpn_policy[IFLA_OVPN_MAX + 1] = { + [IFLA_OVPN_MODE] = NLA_POLICY_RANGE(NLA_U8, OVPN_MODE_P2P, + OVPN_MODE_MP), }; /** @@ -31,18 +45,82 @@ bool ovpn_dev_is_valid(const struct net_device *dev) return dev->netdev_ops == &ovpn_netdev_ops; } +static void ovpn_setup(struct net_device *dev) +{ + netdev_features_t feat = NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA; + + dev->needs_free_netdev = true; + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; + + dev->netdev_ops = &ovpn_netdev_ops; + + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->mtu = ETH_DATA_LEN - OVPN_HEAD_ROOM; + dev->min_mtu = IPV4_MIN_MTU; + dev->max_mtu = IP_MAX_MTU - OVPN_HEAD_ROOM; + + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP; + dev->priv_flags |= IFF_NO_QUEUE; + + dev->lltx = true; + dev->features |= feat; + dev->hw_features |= feat; + dev->hw_enc_features |= feat; + + dev->needed_headroom = ALIGN(OVPN_HEAD_ROOM, 4); + dev->needed_tailroom = OVPN_MAX_PADDING; + + SET_NETDEV_DEVTYPE(dev, &ovpn_type); +} + static int ovpn_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - return -EOPNOTSUPP; + struct ovpn_priv *ovpn = netdev_priv(dev); + struct nlattr **data = params->data; + enum ovpn_mode mode = OVPN_MODE_P2P; + + if (data && data[IFLA_OVPN_MODE]) { + mode = nla_get_u8(data[IFLA_OVPN_MODE]); + netdev_dbg(dev, "setting device mode: %u\n", mode); + } + + ovpn->dev = dev; + ovpn->mode = mode; + + /* turn carrier explicitly off after registration, this way state is + * clearly defined + */ + netif_carrier_off(dev); + + return register_netdevice(dev); +} + +static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + + if (nla_put_u8(skb, IFLA_OVPN_MODE, ovpn->mode)) + return -EMSGSIZE; + + return 0; } static struct rtnl_link_ops ovpn_link_ops = { .kind = "ovpn", .netns_refund = false, + .priv_size = sizeof(struct ovpn_priv), + .setup = ovpn_setup, + .policy = ovpn_policy, + .maxtype = IFLA_OVPN_MAX, .newlink = ovpn_newlink, .dellink = unregister_netdevice_queue, + .fill_info = ovpn_fill_info, }; static int __init ovpn_init(void) diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h index f9322536b06d..b6b644668d46 100644 --- a/drivers/net/ovpn/ovpnpriv.h +++ b/drivers/net/ovpn/ovpnpriv.h @@ -10,12 +10,17 @@ #ifndef _NET_OVPN_OVPNSTRUCT_H_ #define _NET_OVPN_OVPNSTRUCT_H_ +#include +#include + /** * struct ovpn_priv - per ovpn interface state * @dev: the actual netdev representing the tunnel + * @mode: device operation mode (i.e. p2p, mp, ..) */ struct ovpn_priv { struct net_device *dev; + enum ovpn_mode mode; }; #endif /* _NET_OVPN_OVPNSTRUCT_H_ */ diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h new file mode 100644 index 000000000000..5f95a78bebd3 --- /dev/null +++ b/drivers/net/ovpn/proto.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + * James Yonan + */ + +#ifndef _NET_OVPN_PROTO_H_ +#define _NET_OVPN_PROTO_H_ + +/* When the OpenVPN protocol is ran in AEAD mode, use + * the OpenVPN packet ID as the AEAD nonce: + * + * 00000005 521c3b01 4308c041 + * [seq # ] [ nonce_tail ] + * [ 12-byte full IV ] -> OVPN_NONCE_SIZE + * [4-bytes -> OVPN_NONCE_WIRE_SIZE + * on wire] + */ + +/* nonce size (96bits) as required by AEAD ciphers */ +#define OVPN_NONCE_SIZE 12 +/* last 8 bytes of AEAD nonce: provided by userspace and usually derived + * from key material generated during TLS handshake + */ +#define OVPN_NONCE_TAIL_SIZE 8 + +/* OpenVPN nonce size reduced by 8-byte nonce tail -- this is the + * size of the AEAD Associated Data (AD) sent over the wire + * and is normally the head of the IV + */ +#define OVPN_NONCE_WIRE_SIZE (OVPN_NONCE_SIZE - OVPN_NONCE_TAIL_SIZE) + +#define OVPN_OPCODE_SIZE 4 /* DATA_V2 opcode size */ + +#endif /* _NET_OVPN_PROTO_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 318386cc5b0d..3ad2d5d98034 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1986,4 +1986,19 @@ enum { #define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1) +/* OVPN section */ + +enum ovpn_mode { + OVPN_MODE_P2P, + OVPN_MODE_MP, +}; + +enum { + IFLA_OVPN_UNSPEC, + IFLA_OVPN_MODE, + __IFLA_OVPN_MAX, +}; + +#define IFLA_OVPN_MAX (__IFLA_OVPN_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ -- cgit v1.2.3 From f6226ae7a0cd47aaa9175aca6a1e19600f884cbf Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Tue, 15 Apr 2025 13:17:23 +0200 Subject: ovpn: introduce the ovpn_socket object This specific structure is used in the ovpn kernel module to wrap and carry around a standard kernel socket. ovpn takes ownership of passed sockets and therefore an ovpn specific objects is attached to them for status tracking purposes. Initially only UDP support is introduced. TCP will come in a later patch. Cc: willemdebruijn.kernel@gmail.com Signed-off-by: Antonio Quartulli Link: https://patch.msgid.link/20250415-b4-ovpn-v26-6-577f6097b964@openvpn.net Reviewed-by: Sabrina Dubroca Tested-by: Oleksandr Natalenko Signed-off-by: Paolo Abeni --- drivers/net/ovpn/Makefile | 2 + drivers/net/ovpn/main.c | 3 +- drivers/net/ovpn/peer.c | 28 +++++-- drivers/net/ovpn/peer.h | 6 +- drivers/net/ovpn/socket.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/net/ovpn/socket.h | 38 +++++++++ drivers/net/ovpn/udp.c | 75 ++++++++++++++++++ drivers/net/ovpn/udp.h | 19 +++++ include/uapi/linux/udp.h | 1 + 9 files changed, 362 insertions(+), 7 deletions(-) create mode 100644 drivers/net/ovpn/socket.c create mode 100644 drivers/net/ovpn/socket.h create mode 100644 drivers/net/ovpn/udp.c create mode 100644 drivers/net/ovpn/udp.h (limited to 'include/uapi/linux') diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile index 618328ae3388..164f2058ea8e 100644 --- a/drivers/net/ovpn/Makefile +++ b/drivers/net/ovpn/Makefile @@ -13,3 +13,5 @@ ovpn-y += io.o ovpn-y += netlink.o ovpn-y += netlink-gen.o ovpn-y += peer.o +ovpn-y += socket.o +ovpn-y += udp.o diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 3c2b6a7df272..e9a6dc100d46 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -116,7 +116,8 @@ static void ovpn_dellink(struct net_device *dev, struct list_head *head) struct ovpn_priv *ovpn = netdev_priv(dev); if (ovpn->mode == OVPN_MODE_P2P) - ovpn_peer_release_p2p(ovpn, OVPN_DEL_PEER_REASON_TEARDOWN); + ovpn_peer_release_p2p(ovpn, NULL, + OVPN_DEL_PEER_REASON_TEARDOWN); unregister_netdevice_queue(dev, head); } diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index 338069c99248..0bb6c1517184 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -16,17 +16,20 @@ #include "main.h" #include "netlink.h" #include "peer.h" +#include "socket.h" static void unlock_ovpn(struct ovpn_priv *ovpn, - struct llist_head *release_list) + struct llist_head *release_list) __releases(&ovpn->lock) { struct ovpn_peer *peer; spin_unlock_bh(&ovpn->lock); - llist_for_each_entry(peer, release_list->first, release_entry) + llist_for_each_entry(peer, release_list->first, release_entry) { + ovpn_socket_release(peer); ovpn_peer_put(peer); + } } /** @@ -394,18 +397,33 @@ int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason) /** * ovpn_peer_release_p2p - release peer upon P2P device teardown * @ovpn: the instance being torn down + * @sk: if not NULL, release peer only if it's using this specific socket * @reason: the reason for releasing the peer */ -void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, +void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, enum ovpn_del_peer_reason reason) { + struct ovpn_socket *ovpn_sock; LLIST_HEAD(release_list); struct ovpn_peer *peer; spin_lock_bh(&ovpn->lock); peer = rcu_dereference_protected(ovpn->peer, lockdep_is_held(&ovpn->lock)); - if (peer) - ovpn_peer_remove(peer, reason, &release_list); + if (!peer) { + spin_unlock_bh(&ovpn->lock); + return; + } + + if (sk) { + ovpn_sock = rcu_access_pointer(peer->sock); + if (!ovpn_sock || ovpn_sock->sock->sk != sk) { + spin_unlock_bh(&ovpn->lock); + ovpn_peer_put(peer); + return; + } + } + + ovpn_peer_remove(peer, reason, &release_list); unlock_ovpn(ovpn, &release_list); } diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h index fd2e7625990a..29c9065cedcc 100644 --- a/drivers/net/ovpn/peer.h +++ b/drivers/net/ovpn/peer.h @@ -12,6 +12,8 @@ #include +#include "socket.h" + /** * struct ovpn_peer - the main remote peer object * @ovpn: main openvpn instance this peer belongs to @@ -20,6 +22,7 @@ * @vpn_addrs: IP addresses assigned over the tunnel * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel + * @sock: the socket being used to talk to this peer * @dst_cache: cache for dst_entry used to send to peer * @bind: remote peer binding * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..) @@ -36,6 +39,7 @@ struct ovpn_peer { struct in_addr ipv4; struct in6_addr ipv6; } vpn_addrs; + struct ovpn_socket __rcu *sock; struct dst_cache dst_cache; struct ovpn_bind __rcu *bind; enum ovpn_del_peer_reason delete_reason; @@ -70,7 +74,7 @@ static inline void ovpn_peer_put(struct ovpn_peer *peer) struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id); int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer); int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason); -void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, +void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, enum ovpn_del_peer_reason reason); struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn, diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c new file mode 100644 index 000000000000..beec7aee35e1 --- /dev/null +++ b/drivers/net/ovpn/socket.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan + * Antonio Quartulli + */ + +#include +#include +#include + +#include "ovpnpriv.h" +#include "main.h" +#include "io.h" +#include "peer.h" +#include "socket.h" +#include "udp.h" + +static void ovpn_socket_release_kref(struct kref *kref) +{ + struct ovpn_socket *sock = container_of(kref, struct ovpn_socket, + refcount); + + if (sock->sock->sk->sk_protocol == IPPROTO_UDP) + ovpn_udp_socket_detach(sock); + + kfree_rcu(sock, rcu); +} + +/** + * ovpn_socket_put - decrease reference counter + * @peer: peer whose socket reference counter should be decreased + * @sock: the RCU protected peer socket + * + * This function is only used internally. Users willing to release + * references to the ovpn_socket should use ovpn_socket_release() + */ +static void ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock) +{ + kref_put(&sock->refcount, ovpn_socket_release_kref); +} + +/** + * ovpn_socket_release - release resources owned by socket user + * @peer: peer whose socket should be released + * + * This function should be invoked when the user is shutting + * down and wants to drop its link to the socket. + * + * In case of UDP, the detach routine will drop a reference to the + * ovpn netdev, pointed by the ovpn_socket. + * + * In case of TCP, releasing the socket will cause dropping + * the refcounter for the peer it is linked to, thus allowing the peer + * disappear as well. + * + * This function is expected to be invoked exactly once per peer + * + * NOTE: this function may sleep + */ +void ovpn_socket_release(struct ovpn_peer *peer) +{ + struct ovpn_socket *sock; + + might_sleep(); + + sock = rcu_replace_pointer(peer->sock, NULL, true); + /* release may be invoked after socket was detached */ + if (!sock) + return; + + /* sanity check: we should not end up here if the socket + * was already closed + */ + if (!sock->sock->sk) { + DEBUG_NET_WARN_ON_ONCE(1); + return; + } + + /* Drop the reference while holding the sock lock to avoid + * concurrent ovpn_socket_new call to mess up with a partially + * detached socket. + * + * Holding the lock ensures that a socket with refcnt 0 is fully + * detached before it can be picked by a concurrent reader. + */ + lock_sock(sock->sock->sk); + ovpn_socket_put(peer, sock); + release_sock(sock->sock->sk); + + /* align all readers with sk_user_data being NULL */ + synchronize_rcu(); +} + +static bool ovpn_socket_hold(struct ovpn_socket *sock) +{ + return kref_get_unless_zero(&sock->refcount); +} + +static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer) +{ + if (sock->sock->sk->sk_protocol == IPPROTO_UDP) + return ovpn_udp_socket_attach(sock, peer->ovpn); + + return -EOPNOTSUPP; +} + +/** + * ovpn_socket_new - create a new socket and initialize it + * @sock: the kernel socket to embed + * @peer: the peer reachable via this socket + * + * Return: an openvpn socket on success or a negative error code otherwise + */ +struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) +{ + struct ovpn_socket *ovpn_sock; + int ret; + + lock_sock(sock->sk); + + /* a TCP socket can only be owned by a single peer, therefore there + * can't be any other user + */ + if (sock->sk->sk_protocol == IPPROTO_TCP && sock->sk->sk_user_data) { + ovpn_sock = ERR_PTR(-EBUSY); + goto sock_release; + } + + /* a UDP socket can be shared across multiple peers, but we must make + * sure it is not owned by something else + */ + if (sock->sk->sk_protocol == IPPROTO_UDP) { + u8 type = READ_ONCE(udp_sk(sock->sk)->encap_type); + + /* socket owned by other encapsulation module */ + if (type && type != UDP_ENCAP_OVPNINUDP) { + ovpn_sock = ERR_PTR(-EBUSY); + goto sock_release; + } + + rcu_read_lock(); + ovpn_sock = rcu_dereference_sk_user_data(sock->sk); + if (ovpn_sock) { + /* socket owned by another ovpn instance, we can't use it */ + if (ovpn_sock->ovpn != peer->ovpn) { + ovpn_sock = ERR_PTR(-EBUSY); + rcu_read_unlock(); + goto sock_release; + } + + /* this socket is already owned by this instance, + * therefore we can increase the refcounter and + * use it as expected + */ + if (WARN_ON(!ovpn_socket_hold(ovpn_sock))) { + /* this should never happen because setting + * the refcnt to 0 and detaching the socket + * is expected to be atomic + */ + ovpn_sock = ERR_PTR(-EAGAIN); + rcu_read_unlock(); + goto sock_release; + } + + rcu_read_unlock(); + goto sock_release; + } + rcu_read_unlock(); + } + + /* socket is not owned: attach to this ovpn instance */ + + ovpn_sock = kzalloc(sizeof(*ovpn_sock), GFP_KERNEL); + if (!ovpn_sock) { + ovpn_sock = ERR_PTR(-ENOMEM); + goto sock_release; + } + + ovpn_sock->ovpn = peer->ovpn; + ovpn_sock->sock = sock; + kref_init(&ovpn_sock->refcount); + + ret = ovpn_socket_attach(ovpn_sock, peer); + if (ret < 0) { + kfree(ovpn_sock); + ovpn_sock = ERR_PTR(ret); + goto sock_release; + } + + rcu_assign_sk_user_data(sock->sk, ovpn_sock); +sock_release: + release_sock(sock->sk); + return ovpn_sock; +} diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h new file mode 100644 index 000000000000..ade8c94619d7 --- /dev/null +++ b/drivers/net/ovpn/socket.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan + * Antonio Quartulli + */ + +#ifndef _NET_OVPN_SOCK_H_ +#define _NET_OVPN_SOCK_H_ + +#include +#include +#include + +struct ovpn_priv; +struct ovpn_peer; + +/** + * struct ovpn_socket - a kernel socket referenced in the ovpn code + * @ovpn: ovpn instance owning this socket (UDP only) + * @sock: the low level sock object + * @refcount: amount of contexts currently referencing this object + * @rcu: member used to schedule RCU destructor callback + */ +struct ovpn_socket { + struct ovpn_priv *ovpn; + struct socket *sock; + struct kref refcount; + struct rcu_head rcu; +}; + +struct ovpn_socket *ovpn_socket_new(struct socket *sock, + struct ovpn_peer *peer); +void ovpn_socket_release(struct ovpn_peer *peer); + +#endif /* _NET_OVPN_SOCK_H_ */ diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c new file mode 100644 index 000000000000..91970e66a434 --- /dev/null +++ b/drivers/net/ovpn/udp.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + */ + +#include +#include +#include +#include + +#include "ovpnpriv.h" +#include "main.h" +#include "socket.h" +#include "udp.h" + +/** + * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn + * @ovpn_sock: socket to configure + * @ovpn: the openvp instance to link + * + * After invoking this function, the sock will be controlled by ovpn so that + * any incoming packet may be processed by ovpn first. + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, + struct ovpn_priv *ovpn) +{ + struct socket *sock = ovpn_sock->sock; + struct ovpn_socket *old_data; + int ret = 0; + + /* make sure no pre-existing encapsulation handler exists */ + rcu_read_lock(); + old_data = rcu_dereference_sk_user_data(sock->sk); + if (!old_data) { + /* socket is currently unused - we can take it */ + rcu_read_unlock(); + return 0; + } + + /* socket is in use. We need to understand if it's owned by this ovpn + * instance or by something else. + * In the former case, we can increase the refcounter and happily + * use it, because the same UDP socket is expected to be shared among + * different peers. + * + * Unlikely TCP, a single UDP socket can be used to talk to many remote + * hosts and therefore openvpn instantiates one only for all its peers + */ + if ((READ_ONCE(udp_sk(sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) && + old_data->ovpn == ovpn) { + netdev_dbg(ovpn->dev, + "provided socket already owned by this interface\n"); + ret = -EALREADY; + } else { + netdev_dbg(ovpn->dev, + "provided socket already taken by other user\n"); + ret = -EBUSY; + } + rcu_read_unlock(); + + return ret; +} + +/** + * ovpn_udp_socket_detach - clean udp-tunnel status for this socket + * @ovpn_sock: the socket to clean + */ +void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock) +{ +} diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h new file mode 100644 index 000000000000..1c8fb6fe402d --- /dev/null +++ b/drivers/net/ovpn/udp.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli + */ + +#ifndef _NET_OVPN_UDP_H_ +#define _NET_OVPN_UDP_H_ + +struct ovpn_priv; +struct socket; + +int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, + struct ovpn_priv *ovpn); +void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock); + +#endif /* _NET_OVPN_UDP_H_ */ diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index d85d671deed3..edca3e430305 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -43,5 +43,6 @@ struct udphdr { #define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */ #define UDP_ENCAP_RXRPC 6 #define TCP_ENCAP_ESPINTCP 7 /* Yikes, this is really xfrm encap types. */ +#define UDP_ENCAP_OVPNINUDP 8 /* OpenVPN traffic */ #endif /* _UAPI_LINUX_UDP_H */ -- cgit v1.2.3 From 8066e388be48f1ad62b0449dc1d31a25489fa12a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 16 Apr 2025 13:08:40 -0700 Subject: net: add UAPI to the header guard in various network headers fib_rule, ip6_tunnel, and a whole lot of if_* headers lack the customary _UAPI in the header guard. Without it YNL build can't protect from in tree and system headers both getting included. YNL doesn't need most of these but it's annoying to have to fix them one by one. Note that header installation strips this _UAPI prefix so this should result in no change to the end user. Acked-by: Jamal Hadi Salim Reviewed-by: Jason Xing Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20250416200840.1338195-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/fib_rules.h | 4 ++-- include/uapi/linux/if_addr.h | 4 ++-- include/uapi/linux/if_addrlabel.h | 4 ++-- include/uapi/linux/if_alg.h | 6 +++--- include/uapi/linux/if_arcnet.h | 6 +++--- include/uapi/linux/if_bonding.h | 6 +++--- include/uapi/linux/if_fc.h | 6 +++--- include/uapi/linux/if_hippi.h | 6 +++--- include/uapi/linux/if_packet.h | 4 ++-- include/uapi/linux/if_plip.h | 4 ++-- include/uapi/linux/if_slip.h | 4 ++-- include/uapi/linux/if_x25.h | 6 +++--- include/uapi/linux/if_xdp.h | 6 +++--- include/uapi/linux/ip6_tunnel.h | 4 ++-- include/uapi/linux/net_dropmon.h | 4 ++-- include/uapi/linux/net_tstamp.h | 6 +++--- include/uapi/linux/netlink_diag.h | 4 ++-- include/uapi/linux/pkt_cls.h | 4 ++-- include/uapi/linux/pkt_sched.h | 4 ++-- 19 files changed, 46 insertions(+), 46 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 2df6e4035d50..418c4be697ad 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_FIB_RULES_H -#define __LINUX_FIB_RULES_H +#ifndef _UAPI__LINUX_FIB_RULES_H +#define _UAPI__LINUX_FIB_RULES_H #include #include diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index 1c392dd95a5e..aa7958b4e41d 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_IF_ADDR_H -#define __LINUX_IF_ADDR_H +#ifndef _UAPI__LINUX_IF_ADDR_H +#define _UAPI__LINUX_IF_ADDR_H #include #include diff --git a/include/uapi/linux/if_addrlabel.h b/include/uapi/linux/if_addrlabel.h index d1f5974c76e1..e69db764fbba 100644 --- a/include/uapi/linux/if_addrlabel.h +++ b/include/uapi/linux/if_addrlabel.h @@ -8,8 +8,8 @@ * YOSHIFUJI Hideaki @ USAGI/WIDE */ -#ifndef __LINUX_IF_ADDRLABEL_H -#define __LINUX_IF_ADDRLABEL_H +#ifndef _UAPI__LINUX_IF_ADDRLABEL_H +#define _UAPI__LINUX_IF_ADDRLABEL_H #include diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index 0824fbc026a1..b35871cbeed7 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -11,8 +11,8 @@ * */ -#ifndef _LINUX_IF_ALG_H -#define _LINUX_IF_ALG_H +#ifndef _UAPI_LINUX_IF_ALG_H +#define _UAPI_LINUX_IF_ALG_H #include @@ -58,4 +58,4 @@ struct af_alg_iv { #define ALG_OP_DECRYPT 0 #define ALG_OP_ENCRYPT 1 -#endif /* _LINUX_IF_ALG_H */ +#endif /* _UAPI_LINUX_IF_ALG_H */ diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index b122cfac7128..473569eaf692 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -14,8 +14,8 @@ * 2 of the License, or (at your option) any later version. */ -#ifndef _LINUX_IF_ARCNET_H -#define _LINUX_IF_ARCNET_H +#ifndef _UAPI_LINUX_IF_ARCNET_H +#define _UAPI_LINUX_IF_ARCNET_H #include #include @@ -127,4 +127,4 @@ struct archdr { } soft; }; -#endif /* _LINUX_IF_ARCNET_H */ +#endif /* _UAPI_LINUX_IF_ARCNET_H */ diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index d174914a837d..3bcc03f3aa4f 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -41,8 +41,8 @@ * - added definitions for various XOR hashing policies */ -#ifndef _LINUX_IF_BONDING_H -#define _LINUX_IF_BONDING_H +#ifndef _UAPI_LINUX_IF_BONDING_H +#define _UAPI_LINUX_IF_BONDING_H #include #include @@ -152,4 +152,4 @@ enum { }; #define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1) -#endif /* _LINUX_IF_BONDING_H */ +#endif /* _UAPI_LINUX_IF_BONDING_H */ diff --git a/include/uapi/linux/if_fc.h b/include/uapi/linux/if_fc.h index 3e3173282cc3..ff5ab92d16c2 100644 --- a/include/uapi/linux/if_fc.h +++ b/include/uapi/linux/if_fc.h @@ -18,8 +18,8 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#ifndef _LINUX_IF_FC_H -#define _LINUX_IF_FC_H +#ifndef _UAPI_LINUX_IF_FC_H +#define _UAPI_LINUX_IF_FC_H #include @@ -49,4 +49,4 @@ struct fcllc { __be16 ethertype; /* ether type field */ }; -#endif /* _LINUX_IF_FC_H */ +#endif /* _UAPI_LINUX_IF_FC_H */ diff --git a/include/uapi/linux/if_hippi.h b/include/uapi/linux/if_hippi.h index 785a1452a66c..42c4ffd11dae 100644 --- a/include/uapi/linux/if_hippi.h +++ b/include/uapi/linux/if_hippi.h @@ -20,8 +20,8 @@ * 2 of the License, or (at your option) any later version. */ -#ifndef _LINUX_IF_HIPPI_H -#define _LINUX_IF_HIPPI_H +#ifndef _UAPI_LINUX_IF_HIPPI_H +#define _UAPI_LINUX_IF_HIPPI_H #include #include @@ -151,4 +151,4 @@ struct hippi_hdr { struct hippi_snap_hdr snap; } __attribute__((packed)); -#endif /* _LINUX_IF_HIPPI_H */ +#endif /* _UAPI_LINUX_IF_HIPPI_H */ diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 1d2718dd9647..6cd1d7a41dfb 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_IF_PACKET_H -#define __LINUX_IF_PACKET_H +#ifndef _UAPI__LINUX_IF_PACKET_H +#define _UAPI__LINUX_IF_PACKET_H #include #include diff --git a/include/uapi/linux/if_plip.h b/include/uapi/linux/if_plip.h index 495a366112f2..054d86a9c6e6 100644 --- a/include/uapi/linux/if_plip.h +++ b/include/uapi/linux/if_plip.h @@ -9,8 +9,8 @@ * */ -#ifndef _LINUX_IF_PLIP_H -#define _LINUX_IF_PLIP_H +#ifndef _UAPI_LINUX_IF_PLIP_H +#define _UAPI_LINUX_IF_PLIP_H #include diff --git a/include/uapi/linux/if_slip.h b/include/uapi/linux/if_slip.h index 65937be53103..299bf7adc862 100644 --- a/include/uapi/linux/if_slip.h +++ b/include/uapi/linux/if_slip.h @@ -6,8 +6,8 @@ * KISS TNC driver. */ -#ifndef __LINUX_SLIP_H -#define __LINUX_SLIP_H +#ifndef _UAPI__LINUX_SLIP_H +#define _UAPI__LINUX_SLIP_H #define SL_MODE_SLIP 0 #define SL_MODE_CSLIP 1 diff --git a/include/uapi/linux/if_x25.h b/include/uapi/linux/if_x25.h index 3a5938e38370..861cfa983db4 100644 --- a/include/uapi/linux/if_x25.h +++ b/include/uapi/linux/if_x25.h @@ -13,8 +13,8 @@ * GNU General Public License for more details. */ -#ifndef _IF_X25_H -#define _IF_X25_H +#ifndef _UAPI_IF_X25_H +#define _UAPI_IF_X25_H #include @@ -24,4 +24,4 @@ #define X25_IFACE_DISCONNECT 0x02 #define X25_IFACE_PARAMS 0x03 -#endif /* _IF_X25_H */ +#endif /* _UAPI_IF_X25_H */ diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index 42869770776e..44f2bb93e7e6 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -7,8 +7,8 @@ * Magnus Karlsson */ -#ifndef _LINUX_IF_XDP_H -#define _LINUX_IF_XDP_H +#ifndef _UAPI_LINUX_IF_XDP_H +#define _UAPI_LINUX_IF_XDP_H #include @@ -180,4 +180,4 @@ struct xdp_desc { /* TX packet carries valid metadata. */ #define XDP_TX_METADATA (1 << 1) -#endif /* _LINUX_IF_XDP_H */ +#endif /* _UAPI_LINUX_IF_XDP_H */ diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h index 0245269b037c..85182a839d42 100644 --- a/include/uapi/linux/ip6_tunnel.h +++ b/include/uapi/linux/ip6_tunnel.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _IP6_TUNNEL_H -#define _IP6_TUNNEL_H +#ifndef _UAPI_IP6_TUNNEL_H +#define _UAPI_IP6_TUNNEL_H #include #include /* For IFNAMSIZ. */ diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 84f622a66a7a..9dd41c2f58a6 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __NET_DROPMON_H -#define __NET_DROPMON_H +#ifndef _UAPI__NET_DROPMON_H +#define _UAPI__NET_DROPMON_H #include #include diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 383213de612a..a93e6ea37fb3 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -7,8 +7,8 @@ * */ -#ifndef _NET_TIMESTAMPING_H -#define _NET_TIMESTAMPING_H +#ifndef _UAPI_NET_TIMESTAMPING_H +#define _UAPI_NET_TIMESTAMPING_H #include #include /* for SO_TIMESTAMPING */ @@ -216,4 +216,4 @@ struct sock_txtime { __u32 flags; /* as defined by enum txtime_flags */ }; -#endif /* _NET_TIMESTAMPING_H */ +#endif /* _UAPI_NET_TIMESTAMPING_H */ diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index dfa61be43d2f..ff28200204bb 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __NETLINK_DIAG_H__ -#define __NETLINK_DIAG_H__ +#ifndef _UAPI__NETLINK_DIAG_H__ +#define _UAPI__NETLINK_DIAG_H__ #include diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 2c32080416b5..490821364165 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_PKT_CLS_H -#define __LINUX_PKT_CLS_H +#ifndef _UAPI__LINUX_PKT_CLS_H +#define _UAPI__LINUX_PKT_CLS_H #include #include diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 25a9a47001cd..9ea874395717 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_PKT_SCHED_H -#define __LINUX_PKT_SCHED_H +#ifndef _UAPI__LINUX_PKT_SCHED_H +#define _UAPI__LINUX_PKT_SCHED_H #include #include -- cgit v1.2.3 From 178af54a678d08735233e070a9329651e1589587 Mon Sep 17 00:00:00 2001 From: Krishna Chaitanya Chundru Date: Fri, 28 Mar 2025 15:58:32 +0530 Subject: PCI: Add lane equalization register offsets As per PCIe spec 6.0.1, add PCIe lane equalization register offset for data rates 8.0 GT/s, 32.0 GT/s and 64.0 GT/s. Also add a macro for defining data rate 64.0 GT/s physical layer capability ID. Signed-off-by: Krishna Chaitanya Chundru Signed-off-by: Manivannan Sadhasivam Reviewed-by: Manivannan Sadhasivam Link: https://patch.msgid.link/20250328-preset_v6-v9-4-22cfa0490518@oss.qualcomm.com --- include/uapi/linux/pci_regs.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ba326710f9c8..a3a3e942dedf 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -750,7 +750,8 @@ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE +#define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -1144,12 +1145,21 @@ #define PCI_DLF_CAP 0x04 /* Capabilities Register */ #define PCI_DLF_EXCHANGE_ENABLE 0x80000000 /* Data Link Feature Exchange Enable */ +/* Secondary PCIe Capability 8.0 GT/s */ +#define PCI_SECPCI_LE_CTRL 0x0c /* Lane Equalization Control Register */ + /* Physical Layer 16.0 GT/s */ #define PCI_PL_16GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ #define PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK 0x0000000F #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Physical Layer 32.0 GT/s */ +#define PCI_PL_32GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + +/* Physical Layer 64.0 GT/s */ +#define PCI_PL_64GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + /* Native PCIe Enclosure Management */ #define PCI_NPEM_CAP 0x04 /* NPEM capability register */ #define PCI_NPEM_CAP_CAPABLE 0x00000001 /* NPEM Capable */ -- cgit v1.2.3 From 53db8a71ecb42c2ec5e9c6925269a750255f9af5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 4 Apr 2025 14:50:59 -0600 Subject: io_uring: add support for IORING_OP_PIPE This works just like pipe2(2), except it also supports fixed file descriptors. Used in a similar fashion as for other fd instantiating opcodes (like accept, socket, open, etc), where sqe->file_slot is set appropriately if two direct descriptors are desired rather than a set of normal file descriptors. sqe->addr must be set to a pointer to an array of 2 integers, which is where the fixed/normal file descriptors are copied to. sqe->pipe_flags contains flags, same as what is allowed for pipe2(2). Future expansion of per-op private flags can go in sqe->ioprio, like we do for other opcodes that take both a "syscall" flag set and an io_uring opcode specific flag set. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 + io_uring/opdef.c | 7 +++ io_uring/openclose.c | 133 ++++++++++++++++++++++++++++++++++++++++++ io_uring/openclose.h | 3 + 4 files changed, 145 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8f1fc12bac46..130f3bc71a69 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -73,6 +73,7 @@ struct io_uring_sqe { __u32 futex_flags; __u32 install_fd_flags; __u32 nop_flags; + __u32 pipe_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -283,6 +284,7 @@ enum io_uring_op { IORING_OP_EPOLL_WAIT, IORING_OP_READV_FIXED, IORING_OP_WRITEV_FIXED, + IORING_OP_PIPE, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 489384c0438b..db36433c2294 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -569,6 +569,10 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_prep_writev_fixed, .issue = io_write, }, + [IORING_OP_PIPE] = { + .prep = io_pipe_prep, + .issue = io_pipe, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -815,6 +819,9 @@ const struct io_cold_def io_cold_defs[] = { .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, + [IORING_OP_PIPE] = { + .name = "PIPE", + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/openclose.c b/io_uring/openclose.c index e3357dfa14ca..4dd461163457 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -6,6 +6,8 @@ #include #include #include +#include +#include #include #include @@ -302,3 +304,134 @@ int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags) io_req_set_res(req, ret, 0); return IOU_OK; } + +struct io_pipe { + struct file *file; + int __user *fds; + int flags; + int file_slot; + unsigned long nofile; +}; + +int io_pipe_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_pipe *p = io_kiocb_to_cmd(req, struct io_pipe); + + if (sqe->fd || sqe->off || sqe->addr3) + return -EINVAL; + + p->fds = u64_to_user_ptr(READ_ONCE(sqe->addr)); + p->flags = READ_ONCE(sqe->pipe_flags); + if (p->flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) + return -EINVAL; + + p->file_slot = READ_ONCE(sqe->file_index); + p->nofile = rlimit(RLIMIT_NOFILE); + return 0; +} + +static int io_pipe_fixed(struct io_kiocb *req, struct file **files, + unsigned int issue_flags) +{ + struct io_pipe *p = io_kiocb_to_cmd(req, struct io_pipe); + struct io_ring_ctx *ctx = req->ctx; + int ret, fds[2] = { -1, -1 }; + int slot = p->file_slot; + + if (p->flags & O_CLOEXEC) + return -EINVAL; + + io_ring_submit_lock(ctx, issue_flags); + + ret = __io_fixed_fd_install(ctx, files[0], slot); + if (ret < 0) + goto err; + fds[0] = ret; + files[0] = NULL; + + /* + * If a specific slot is given, next one will be used for + * the write side. + */ + if (slot != IORING_FILE_INDEX_ALLOC) + slot++; + + ret = __io_fixed_fd_install(ctx, files[1], slot); + if (ret < 0) + goto err; + fds[1] = ret; + files[1] = NULL; + + io_ring_submit_unlock(ctx, issue_flags); + + if (!copy_to_user(p->fds, fds, sizeof(fds))) + return 0; + + ret = -EFAULT; + io_ring_submit_lock(ctx, issue_flags); +err: + if (fds[0] != -1) + io_fixed_fd_remove(ctx, fds[0]); + if (fds[1] != -1) + io_fixed_fd_remove(ctx, fds[1]); + io_ring_submit_unlock(ctx, issue_flags); + return ret; +} + +static int io_pipe_fd(struct io_kiocb *req, struct file **files) +{ + struct io_pipe *p = io_kiocb_to_cmd(req, struct io_pipe); + int ret, fds[2] = { -1, -1 }; + + ret = __get_unused_fd_flags(p->flags, p->nofile); + if (ret < 0) + goto err; + fds[0] = ret; + + ret = __get_unused_fd_flags(p->flags, p->nofile); + if (ret < 0) + goto err; + fds[1] = ret; + + if (!copy_to_user(p->fds, fds, sizeof(fds))) { + fd_install(fds[0], files[0]); + fd_install(fds[1], files[1]); + return 0; + } + ret = -EFAULT; +err: + if (fds[0] != -1) + put_unused_fd(fds[0]); + if (fds[1] != -1) + put_unused_fd(fds[1]); + return ret; +} + +int io_pipe(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_pipe *p = io_kiocb_to_cmd(req, struct io_pipe); + struct file *files[2]; + int ret; + + ret = create_pipe_files(files, p->flags); + if (ret) + return ret; + files[0]->f_mode |= FMODE_NOWAIT; + files[1]->f_mode |= FMODE_NOWAIT; + + if (!!p->file_slot) + ret = io_pipe_fixed(req, files, issue_flags); + else + ret = io_pipe_fd(req, files); + + io_req_set_res(req, ret, 0); + if (!ret) + return IOU_OK; + + req_set_fail(req); + if (files[0]) + fput(files[0]); + if (files[1]) + fput(files[1]); + return ret; +} diff --git a/io_uring/openclose.h b/io_uring/openclose.h index 8a93c98ad0ad..4ca2a9935abc 100644 --- a/io_uring/openclose.h +++ b/io_uring/openclose.h @@ -13,5 +13,8 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags); int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_close(struct io_kiocb *req, unsigned int issue_flags); +int io_pipe_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_pipe(struct io_kiocb *req, unsigned int issue_flags); + int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags); -- cgit v1.2.3 From 98b995660bff011d8e00af03abd74ac7d1ac1390 Mon Sep 17 00:00:00 2001 From: Omri Mann Date: Mon, 21 Apr 2025 13:59:50 +0300 Subject: ublk: Add UBLK_U_CMD_UPDATE_SIZE Currently ublk only allows the size of the ublkb block device to be set via UBLK_CMD_SET_PARAMS before UBLK_CMD_START_DEV is triggered. This does not provide support for extendable user-space block devices without having to stop and restart the underlying ublkb block device causing IO interruption. This patch adds a new ublk command UBLK_U_CMD_UPDATE_SIZE to allow the ublk block device to be resized on-the-fly. Feature flag UBLK_F_UPDATE_SIZE is also added to indicate support. Signed-off-by: Omri Mann Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/2a370ab1-d85b-409d-b762-f9f3f6bdf705@nvidia.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 19 ++++++++++++++++++- include/uapi/linux/ublk_cmd.h | 8 ++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 2de7b2bd409d..03653bd7a1df 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -50,6 +50,7 @@ /* private ioctl command mirror */ #define UBLK_CMD_DEL_DEV_ASYNC _IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC) +#define UBLK_CMD_UPDATE_SIZE _IOC_NR(UBLK_U_CMD_UPDATE_SIZE) #define UBLK_IO_REGISTER_IO_BUF _IOC_NR(UBLK_U_IO_REGISTER_IO_BUF) #define UBLK_IO_UNREGISTER_IO_BUF _IOC_NR(UBLK_U_IO_UNREGISTER_IO_BUF) @@ -64,7 +65,8 @@ | UBLK_F_CMD_IOCTL_ENCODE \ | UBLK_F_USER_COPY \ | UBLK_F_ZONED \ - | UBLK_F_USER_RECOVERY_FAIL_IO) + | UBLK_F_USER_RECOVERY_FAIL_IO \ + | UBLK_F_UPDATE_SIZE) #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ @@ -3075,6 +3077,16 @@ static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header) return 0; } +static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) +{ + struct ublk_param_basic *p = &ub->params.basic; + u64 new_size = header->data[0]; + + mutex_lock(&ub->mutex); + p->dev_sectors = new_size; + set_capacity_and_notify(ub->ub_disk, p->dev_sectors); + mutex_unlock(&ub->mutex); +} /* * All control commands are sent via /dev/ublk-control, so we have to check * the destination device's permission @@ -3160,6 +3172,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, case UBLK_CMD_SET_PARAMS: case UBLK_CMD_START_USER_RECOVERY: case UBLK_CMD_END_USER_RECOVERY: + case UBLK_CMD_UPDATE_SIZE: mask = MAY_READ | MAY_WRITE; break; default: @@ -3251,6 +3264,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, case UBLK_CMD_END_USER_RECOVERY: ret = ublk_ctrl_end_recovery(ub, header); break; + case UBLK_CMD_UPDATE_SIZE: + ublk_ctrl_set_size(ub, header); + ret = 0; + break; default: ret = -EOPNOTSUPP; break; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 583b86681c93..be5c6c6b16e0 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -51,6 +51,8 @@ _IOR('u', 0x13, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_DEL_DEV_ASYNC \ _IOR('u', 0x14, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_UPDATE_SIZE \ + _IOWR('u', 0x15, struct ublksrv_ctrl_cmd) /* * 64bits are enough now, and it should be easy to extend in case of @@ -211,6 +213,12 @@ */ #define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9) +/* + * Resizing a block device is possible with UBLK_U_CMD_UPDATE_SIZE + * New size is passed in cmd->data[0] and is in units of sectors + */ +#define UBLK_F_UPDATE_SIZE (1ULL << 10) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 37523c3c47b3f3cc4c7d2ff47d28ee9ec99317c1 Mon Sep 17 00:00:00 2001 From: Rameshkumar Sundaram Date: Tue, 8 Apr 2025 11:44:59 -0700 Subject: wifi: nl80211: add link id of transmitted profile for MLO MBSSID During non-transmitted (nontx) profile configuration, interface index of the transmitted (tx) profile is used to retrieve the wireless device (wdev) associated with it. With MLO, this 'wdev' may be part of an MLD with more than one link, hence only interface index is not sufficient anymore to retrieve the correct tx profile. Add a new attribute to configure link id of tx profile. Signed-off-by: Rameshkumar Sundaram Co-developed-by: Muna Sinada Signed-off-by: Muna Sinada Co-developed-by: Aloka Dixit Signed-off-by: Aloka Dixit Link: https://patch.msgid.link/20250408184501.3715887-2-aloka.dixit@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 24 +++++++++++++++++++++++- 3 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 87cb66fba621..d1848dc8ec99 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1263,11 +1263,13 @@ struct cfg80211_crypto_settings { * struct cfg80211_mbssid_config - AP settings for multi bssid * * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @tx_link_id: link ID of the transmitted profile in an MLD. * @index: index of this AP in the multi bssid group. * @ema: set to true if the beacons should be sent out in EMA mode. */ struct cfg80211_mbssid_config { struct wireless_dev *tx_wdev; + u8 tx_link_id; u8 index; bool ema; }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ddcc4cda74af..e9ccf43fe3c6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -8036,6 +8036,11 @@ enum nl80211_sar_specs_attrs { * Setting this flag is permitted only if the driver advertises EMA support * by setting wiphy->ema_max_profile_periodicity to non-zero. * + * @NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID: Link ID of the transmitted profile. + * This parameter is mandatory when NL80211_ATTR_MBSSID_CONFIG attributes + * are sent for a non-transmitted profile and if the transmitted profile + * is part of an MLD. For all other cases this parameter is unnecessary. + * * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute */ @@ -8047,6 +8052,7 @@ enum nl80211_mbssid_config_attributes { NL80211_MBSSID_CONFIG_ATTR_INDEX, NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX, NL80211_MBSSID_CONFIG_ATTR_EMA, + NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID, /* keep last */ __NL80211_MBSSID_CONFIG_ATTR_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index de6c936039f4..fd5f79266471 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -469,6 +469,8 @@ nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = { [NL80211_MBSSID_CONFIG_ATTR_INDEX] = { .type = NLA_U8 }, [NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 }, [NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG }, + [NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID] = + NLA_POLICY_MAX(NLA_U8, IEEE80211_MLD_MAX_NUM_LINKS), }; static const struct nla_policy @@ -5524,11 +5526,13 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, static int nl80211_parse_mbssid_config(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, struct nlattr *attrs, struct cfg80211_mbssid_config *config, u8 num_elems) { struct nlattr *tb[NL80211_MBSSID_CONFIG_ATTR_MAX + 1]; + int tx_link_id = -1; if (!wiphy->mbssid_max_interfaces) return -EOPNOTSUPP; @@ -5552,6 +5556,9 @@ static int nl80211_parse_mbssid_config(struct wiphy *wiphy, (!config->index && !num_elems)) return -EINVAL; + if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID]) + tx_link_id = nla_get_u8(tb[NL80211_MBSSID_CONFIG_ATTR_TX_LINK_ID]); + if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]) { u32 tx_ifindex = nla_get_u32(tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]); @@ -5573,10 +5580,25 @@ static int nl80211_parse_mbssid_config(struct wiphy *wiphy, } config->tx_wdev = tx_netdev->ieee80211_ptr; + /* Caller should call dev_put(config->tx_wdev) from this point */ + + if (config->tx_wdev->valid_links) { + if (tx_link_id == -1 || + !(config->tx_wdev->valid_links & BIT(tx_link_id))) + return -ENOLINK; + + config->tx_link_id = tx_link_id; + } } else { + if (tx_link_id >= 0 && tx_link_id != link_id) + return -EINVAL; + config->tx_wdev = dev->ieee80211_ptr; } } else if (!config->index) { + if (tx_link_id >= 0 && tx_link_id != link_id) + return -EINVAL; + config->tx_wdev = dev->ieee80211_ptr; } else { return -EINVAL; @@ -6326,7 +6348,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_MBSSID_CONFIG]) { - err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, + err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, link_id, info->attrs[NL80211_ATTR_MBSSID_CONFIG], ¶ms->mbssid_config, params->beacon.mbssid_ies ? -- cgit v1.2.3 From 2b13042d3636327eb50c8a0ee06f629d52d1b8fb Mon Sep 17 00:00:00 2001 From: Jeremy Harris Date: Wed, 23 Apr 2025 13:43:34 +0100 Subject: tcp: fastopen: pass TFO child indication through getsockopt tcp: fastopen: pass TFO child indication through getsockopt Note that this uses up the last bit of a field in struct tcp_info Signed-off-by: Jeremy Harris Reviewed-by: Eric Dumazet Reviewed-by: Neal Cardwell Link: https://patch.msgid.link/20250423124334.4916-3-jgh@exim.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index dc8fdc80e16b..bdac8c42fa82 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -184,6 +184,7 @@ enum tcp_fastopen_client_fail { #define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ #define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ #define TCPI_OPT_USEC_TS 64 /* usec timestamps */ +#define TCPI_OPT_TFO_CHILD 128 /* child from a Fast Open option on SYN */ /* * Sender's congestion state indicating normal or abnormal situations diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index df3eb0fb7cb3..86c427f16636 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4165,6 +4165,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; + if (tp->syn_fastopen_child) + info->tcpi_options |= TCPI_OPT_TFO_CHILD; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, -- cgit v1.2.3 From a71f402acd71a942e59c16270ad61dee06de6e24 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 25 Apr 2025 10:11:32 +0200 Subject: pidfs: get rid of __pidfd_prepare() Fold it into pidfd_prepare() and rename PIDFD_CLONE to PIDFD_STALE to indicate that the passed pid might not have task linkage and no explicit check for that should be performed. Link: https://lore.kernel.org/20250425-work-pidfs-net-v2-3-450a19461e75@kernel.org Reviewed-by: Oleg Nesterov Reviewed-by: David Rheinsberg Signed-off-by: Christian Brauner --- fs/pidfs.c | 22 +++++++----- include/linux/pid.h | 2 +- include/uapi/linux/pidfd.h | 2 +- kernel/fork.c | 83 ++++++++++++++++------------------------------ 4 files changed, 44 insertions(+), 65 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/pidfs.c b/fs/pidfs.c index ec5f9ad09bb8..9d993ecadad7 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -768,7 +768,7 @@ static inline bool pidfs_pid_valid(struct pid *pid, const struct path *path, { enum pid_type type; - if (flags & PIDFD_CLONE) + if (flags & PIDFD_STALE) return true; /* @@ -777,10 +777,14 @@ static inline bool pidfs_pid_valid(struct pid *pid, const struct path *path, * pidfd has been allocated perform another check that the pid * is still alive. If it is exit information is available even * if the task gets reaped before the pidfd is returned to - * userspace. The only exception is PIDFD_CLONE where no task - * linkage has been established for @pid yet and the kernel is - * in the middle of process creation so there's nothing for - * pidfs to miss. + * userspace. The only exception are indicated by PIDFD_STALE: + * + * (1) The kernel is in the middle of task creation and thus no + * task linkage has been established yet. + * (2) The caller knows @pid has been registered in pidfs at a + * time when the task was still alive. + * + * In both cases exit information will have been reported. */ if (flags & PIDFD_THREAD) type = PIDTYPE_PID; @@ -874,11 +878,11 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) int ret; /* - * Ensure that PIDFD_CLONE can be passed as a flag without + * Ensure that PIDFD_STALE can be passed as a flag without * overloading other uapi pidfd flags. */ - BUILD_BUG_ON(PIDFD_CLONE == PIDFD_THREAD); - BUILD_BUG_ON(PIDFD_CLONE == PIDFD_NONBLOCK); + BUILD_BUG_ON(PIDFD_STALE == PIDFD_THREAD); + BUILD_BUG_ON(PIDFD_STALE == PIDFD_NONBLOCK); ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path); if (ret < 0) @@ -887,7 +891,7 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) if (!pidfs_pid_valid(pid, &path, flags)) return ERR_PTR(-ESRCH); - flags &= ~PIDFD_CLONE; + flags &= ~PIDFD_STALE; pidfd_file = dentry_open(&path, flags, current_cred()); /* Raise PIDFD_THREAD explicitly as do_dentry_open() strips it. */ if (!IS_ERR(pidfd_file)) diff --git a/include/linux/pid.h b/include/linux/pid.h index 311ecebd7d56..453ae6d8a68d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,7 +77,7 @@ struct 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); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file); 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 2970ef44655a..8c1511edd0e9 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -12,7 +12,7 @@ #define PIDFD_THREAD O_EXCL #ifdef __KERNEL__ #include -#define PIDFD_CLONE CLONE_PIDFD +#define PIDFD_STALE CLONE_PIDFD #endif /* Flags for pidfd_send_signal(). */ diff --git a/kernel/fork.c b/kernel/fork.c index f7403e1fb0d4..1d95f4dae327 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2035,55 +2035,11 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -/** - * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd - * @pid: the struct pid for which to create a pidfd - * @flags: flags of the new @pidfd - * @ret: Where to return the file for the pidfd. - * - * 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 doesn't perform checks on @pid which makes it useful for pidfds - * created via CLONE_PIDFD where @pid has no task attached when the pidfd and - * pidfd file are prepared. - * - * If this function returns successfully the caller is responsible to either - * call fd_install() passing the returned pidfd and pidfd file as arguments in - * order to install the pidfd into its file descriptor table or they must use - * put_unused_fd() and fput() on the returned pidfd and pidfd file - * respectively. - * - * This function is useful when a pidfd must already be reserved but there - * might still be points of failure afterwards and the caller wants to ensure - * that no pidfd is leaked into its file descriptor table. - * - * Return: On success, a reserved pidfd is returned from the function and a new - * pidfd file is returned in the last argument to the function. On - * error, a negative error code is returned from the function and the - * last argument remains unchanged. - */ -static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) -{ - struct file *pidfd_file; - - CLASS(get_unused_fd, pidfd)(O_CLOEXEC); - if (pidfd < 0) - return pidfd; - - pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); - if (IS_ERR(pidfd_file)) - return PTR_ERR(pidfd_file); - - *ret = pidfd_file; - return take_fd(pidfd); -} - /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd - * @ret: Where to return the pidfd. + * @ret_file: return the new pidfs file * * 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. @@ -2106,16 +2062,26 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re * error, a negative error code is returned from the function and the * last argument remains unchanged. */ -int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { + struct file *pidfs_file; + /* - * While holding the pidfd waitqueue lock removing the task - * linkage for the thread-group leader pid (PIDTYPE_TGID) isn't - * possible. Thus, if there's still task linkage for PIDTYPE_PID - * not having thread-group leader linkage for the pid means it - * wasn't a thread-group leader in the first place. + * PIDFD_STALE is only allowed to be passed if the caller knows + * that @pid is already registered in pidfs and thus + * PIDFD_INFO_EXIT information is guaranteed to be available. */ - scoped_guard(spinlock_irq, &pid->wait_pidfd.lock) { + if (!(flags & PIDFD_STALE)) { + /* + * While holding the pidfd waitqueue lock removing the + * task linkage for the thread-group leader pid + * (PIDTYPE_TGID) isn't possible. Thus, if there's still + * task linkage for PIDTYPE_PID not having thread-group + * leader linkage for the pid means it wasn't a + * thread-group leader in the first place. + */ + guard(spinlock_irq)(&pid->wait_pidfd.lock); + /* Task has already been reaped. */ if (!pid_has_task(pid, PIDTYPE_PID)) return -ESRCH; @@ -2128,7 +2094,16 @@ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) return -ENOENT; } - return __pidfd_prepare(pid, flags, ret); + CLASS(get_unused_fd, pidfd)(O_CLOEXEC); + if (pidfd < 0) + return pidfd; + + pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); + if (IS_ERR(pidfs_file)) + return PTR_ERR(pidfs_file); + + *ret_file = pidfs_file; + return take_fd(pidfd); } static void __delayed_free_task(struct rcu_head *rhp) @@ -2477,7 +2452,7 @@ __latent_entropy struct task_struct *copy_process( * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ - retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile); + retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; -- cgit v1.2.3 From 0014af802193aa3547484b5db0f1a258bad28c81 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Apr 2025 15:55:53 +0200 Subject: netfilter: nf_tables: export set count and backend name to userspace nf_tables picks a suitable set backend implementation (bitmap, hash, rbtree..) based on the userspace requirements. Figuring out the chosen backend requires information about the set flags and the kernel version. Export this to userspace so nft can include this information in '--debug=netlink' output. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++++ net/netfilter/nf_tables_api.c | 26 ++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 49c944e78463..7d6bc19a0153 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -394,6 +394,8 @@ enum nft_set_field_attributes { * @NFTA_SET_HANDLE: set handle (NLA_U64) * @NFTA_SET_EXPR: set expression (NLA_NESTED: nft_expr_attributes) * @NFTA_SET_EXPRESSIONS: list of expressions (NLA_NESTED: nft_list_attributes) + * @NFTA_SET_TYPE: set backend type (NLA_STRING) + * @NFTA_SET_COUNT: number of set elements (NLA_U32) */ enum nft_set_attributes { NFTA_SET_UNSPEC, @@ -415,6 +417,8 @@ enum nft_set_attributes { NFTA_SET_HANDLE, NFTA_SET_EXPR, NFTA_SET_EXPRESSIONS, + NFTA_SET_TYPE, + NFTA_SET_COUNT, __NFTA_SET_MAX }; #define NFTA_SET_MAX (__NFTA_SET_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a133e1c175ce..b28f6730e26d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4569,6 +4569,8 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_HANDLE] = { .type = NLA_U64 }, [NFTA_SET_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), + [NFTA_SET_TYPE] = { .type = NLA_REJECT }, + [NFTA_SET_COUNT] = { .type = NLA_REJECT }, }; static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = { @@ -4763,6 +4765,27 @@ static u32 nft_set_userspace_size(const struct nft_set_ops *ops, u32 size) return size; } +static noinline_for_stack int +nf_tables_fill_set_info(struct sk_buff *skb, const struct nft_set *set) +{ + unsigned int nelems; + char str[40]; + int ret; + + ret = snprintf(str, sizeof(str), "%ps", set->ops); + + /* Not expected to happen and harmless: NFTA_SET_TYPE is dumped + * to userspace purely for informational/debug purposes. + */ + DEBUG_NET_WARN_ON_ONCE(ret >= sizeof(str)); + + if (nla_put_string(skb, NFTA_SET_TYPE, str)) + return -EMSGSIZE; + + nelems = nft_set_userspace_size(set->ops, atomic_read(&set->nelems)); + return nla_put_be32(skb, NFTA_SET_COUNT, htonl(nelems)); +} + static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { @@ -4843,6 +4866,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nla_nest_end(skb, nest); + if (nf_tables_fill_set_info(skb, set)) + goto nla_put_failure; + if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) -- cgit v1.2.3 From d12ddda5239826ca6978eaadea1b9280762c830a Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 10 Apr 2025 12:00:49 +0200 Subject: media: uapi: cec-funcs.h: use CEC_LOG_ADDR_BROADCAST The cec-funcs.h header sets the destination to 0xf for those messages that can only be broadcast. Instead of writing: msg->msg[0] |= 0xf; /* broadcast */ just write: msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; which is more descriptive and allows us to drop the comment. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec-funcs.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index d58fa1cdcb08..189ecf0e13cd 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -14,7 +14,7 @@ static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -59,7 +59,7 @@ static inline void cec_msg_request_active_source(struct cec_msg *msg, int reply) { msg->len = 2; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; } @@ -68,7 +68,7 @@ static inline void cec_msg_routing_information(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -86,7 +86,7 @@ static inline void cec_msg_routing_change(struct cec_msg *msg, __u16 new_phys_addr) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ROUTING_CHANGE; msg->msg[2] = orig_phys_addr >> 8; msg->msg[3] = orig_phys_addr & 0xff; @@ -106,7 +106,7 @@ static inline void cec_ops_routing_change(const struct cec_msg *msg, static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_SET_STREAM_PATH; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -791,7 +791,7 @@ static inline void cec_msg_report_physical_addr(struct cec_msg *msg, __u16 phys_addr, __u8 prim_devtype) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -817,7 +817,7 @@ static inline void cec_msg_set_menu_language(struct cec_msg *msg, const char *language) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; memcpy(msg->msg + 2, language, 3); } @@ -850,7 +850,7 @@ static inline void cec_msg_report_features(struct cec_msg *msg, __u8 rc_profile, __u8 dev_features) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_FEATURES; msg->msg[2] = cec_version; msg->msg[3] = all_device_types; @@ -1092,7 +1092,7 @@ static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; msg->msg[2] = vendor_id >> 16; msg->msg[3] = (vendor_id >> 8) & 0xff; @@ -1655,7 +1655,7 @@ static inline void cec_msg_report_current_latency(struct cec_msg *msg, __u8 audio_out_delay) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -1687,7 +1687,7 @@ static inline void cec_msg_request_current_latency(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -1707,7 +1707,7 @@ static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, __u16 phys_addr2) { msg->len = 9; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; @@ -1737,7 +1737,7 @@ static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, __u16 hec_field) { msg->len = has_field ? 10 : 8; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; @@ -1782,7 +1782,7 @@ static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, __u16 phys_addr5) { msg->len = 10; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; @@ -1832,7 +1832,7 @@ static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, __u8 hec_set_state) { msg->len = 8; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; @@ -1857,7 +1857,7 @@ static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, __u16 phys_addr3) { msg->len = 11; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; @@ -1884,7 +1884,7 @@ static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *ms static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; @@ -1899,7 +1899,7 @@ static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; @@ -1916,7 +1916,7 @@ static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, __u8 hpd_state) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; @@ -1938,7 +1938,7 @@ static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, __u8 hpd_error) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; -- cgit v1.2.3 From 80367ad01d93ac781b0e1df246edaf006928002f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 16 Apr 2025 18:29:12 +0200 Subject: futex: Add basic infrastructure for local task local hash The futex hash is system wide and shared by all tasks. Each slot is hashed based on futex address and the VMA of the thread. Due to randomized VMAs (and memory allocations) the same logical lock (pointer) can end up in a different hash bucket on each invocation of the application. This in turn means that different applications may share a hash bucket on the first invocation but not on the second and it is not always clear which applications will be involved. This can result in high latency's to acquire the futex_hash_bucket::lock especially if the lock owner is limited to a CPU and can not be effectively PI boosted. Introduce basic infrastructure for process local hash which is shared by all threads of process. This hash will only be used for a PROCESS_PRIVATE FUTEX operation. The hashmap can be allocated via: prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, num); A `num' of 0 means that the global hash is used instead of a private hash. Other values for `num' specify the number of slots for the hash and the number must be power of two, starting with two. The prctl() returns zero on success. This function can only be used before a thread is created. The current status for the private hash can be queried via: num = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS); which return the current number of slots. The value 0 means that the global hash is used. Values greater than 0 indicate the number of slots that are used. A negative number indicates an error. For optimisation, for the private hash jhash2() uses only two arguments the address and the offset. This omits the VMA which is always the same. [peterz: Use 0 for global hash. A bit shuffling and renaming. ] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-13-bigeasy@linutronix.de --- include/linux/futex.h | 26 +++++- include/linux/mm_types.h | 5 +- include/uapi/linux/prctl.h | 5 ++ init/Kconfig | 5 ++ kernel/fork.c | 2 + kernel/futex/core.c | 208 +++++++++++++++++++++++++++++++++++++++++---- kernel/futex/futex.h | 10 +++ kernel/sys.c | 4 + 8 files changed, 244 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index b70df27d7e85..8f1be08bef18 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -4,11 +4,11 @@ #include #include +#include #include struct inode; -struct mm_struct; struct task_struct; /* @@ -77,7 +77,22 @@ void futex_exec_release(struct task_struct *tsk); long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); -#else +int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4); + +#ifdef CONFIG_FUTEX_PRIVATE_HASH +void futex_hash_free(struct mm_struct *mm); + +static inline void futex_mm_init(struct mm_struct *mm) +{ + mm->futex_phash = NULL; +} + +#else /* !CONFIG_FUTEX_PRIVATE_HASH */ +static inline void futex_hash_free(struct mm_struct *mm) { } +static inline void futex_mm_init(struct mm_struct *mm) { } +#endif /* CONFIG_FUTEX_PRIVATE_HASH */ + +#else /* !CONFIG_FUTEX */ static inline void futex_init_task(struct task_struct *tsk) { } static inline void futex_exit_recursive(struct task_struct *tsk) { } static inline void futex_exit_release(struct task_struct *tsk) { } @@ -88,6 +103,13 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val, { return -EINVAL; } +static inline int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) +{ + return -EINVAL; +} +static inline void futex_hash_free(struct mm_struct *mm) { } +static inline void futex_mm_init(struct mm_struct *mm) { } + #endif #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 56d07edd01f9..a4b5661e4177 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -31,6 +31,7 @@ #define INIT_PASID 0 struct address_space; +struct futex_private_hash; struct mem_cgroup; /* @@ -1031,7 +1032,9 @@ struct mm_struct { */ seqcount_t mm_lock_seq; #endif - +#ifdef CONFIG_FUTEX_PRIVATE_HASH + struct futex_private_hash *futex_phash; +#endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 15c18ef4eb11..3b93fb906e3c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -364,4 +364,9 @@ struct prctl_mm_map { # define PR_TIMER_CREATE_RESTORE_IDS_ON 1 # define PR_TIMER_CREATE_RESTORE_IDS_GET 2 +/* FUTEX hash management */ +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define PR_FUTEX_HASH_GET_SLOTS 2 + #endif /* _LINUX_PRCTL_H */ diff --git a/init/Kconfig b/init/Kconfig index 63f5974b9fa6..4b84da2b2ec4 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1699,6 +1699,11 @@ config FUTEX_PI depends on FUTEX && RT_MUTEXES default y +config FUTEX_PRIVATE_HASH + bool + depends on FUTEX && !BASE_SMALL && MMU + default y + config EPOLL bool "Enable eventpoll support" if EXPERT default y diff --git a/kernel/fork.c b/kernel/fork.c index c4b26cd8998b..831dfec45054 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1305,6 +1305,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); + futex_mm_init(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif @@ -1387,6 +1388,7 @@ static inline void __mmput(struct mm_struct *mm) if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); + futex_hash_free(mm); mmdrop(mm); } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index afc66780f84f..818df7420a1a 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "futex.h" #include "../locking/rtmutex_common.h" @@ -55,6 +56,12 @@ static struct { #define futex_queues (__futex_data.queues) #define futex_hashmask (__futex_data.hashmask) +struct futex_private_hash { + unsigned int hash_mask; + void *mm; + bool custom; + struct futex_hash_bucket queues[]; +}; /* * Fault injections for futexes. @@ -107,9 +114,17 @@ late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAIL_FUTEX */ -struct futex_private_hash *futex_private_hash(void) +static struct futex_hash_bucket * +__futex_hash(union futex_key *key, struct futex_private_hash *fph); + +#ifdef CONFIG_FUTEX_PRIVATE_HASH +static inline bool futex_key_is_private(union futex_key *key) { - return NULL; + /* + * Relies on get_futex_key() to set either bit for shared + * futexes -- see comment with union futex_key. + */ + return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED)); } bool futex_private_hash_get(struct futex_private_hash *fph) @@ -117,21 +132,8 @@ bool futex_private_hash_get(struct futex_private_hash *fph) return false; } -void futex_private_hash_put(struct futex_private_hash *fph) { } - -/** - * futex_hash - Return the hash bucket in the global hash - * @key: Pointer to the futex key for which the hash is calculated - * - * We hash on the keys returned from get_futex_key (see below) and return the - * corresponding hash bucket in the global hash. - */ -struct futex_hash_bucket *futex_hash(union futex_key *key) +void futex_private_hash_put(struct futex_private_hash *fph) { - u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, - key->both.offset); - - return &futex_queues[hash & futex_hashmask]; } /** @@ -144,6 +146,84 @@ struct futex_hash_bucket *futex_hash(union futex_key *key) void futex_hash_get(struct futex_hash_bucket *hb) { } void futex_hash_put(struct futex_hash_bucket *hb) { } +static struct futex_hash_bucket * +__futex_hash_private(union futex_key *key, struct futex_private_hash *fph) +{ + u32 hash; + + if (!futex_key_is_private(key)) + return NULL; + + if (!fph) + fph = key->private.mm->futex_phash; + if (!fph || !fph->hash_mask) + return NULL; + + hash = jhash2((void *)&key->private.address, + sizeof(key->private.address) / 4, + key->both.offset); + return &fph->queues[hash & fph->hash_mask]; +} + +struct futex_private_hash *futex_private_hash(void) +{ + struct mm_struct *mm = current->mm; + struct futex_private_hash *fph; + + fph = mm->futex_phash; + return fph; +} + +struct futex_hash_bucket *futex_hash(union futex_key *key) +{ + struct futex_hash_bucket *hb; + + hb = __futex_hash(key, NULL); + return hb; +} + +#else /* !CONFIG_FUTEX_PRIVATE_HASH */ + +static struct futex_hash_bucket * +__futex_hash_private(union futex_key *key, struct futex_private_hash *fph) +{ + return NULL; +} + +struct futex_hash_bucket *futex_hash(union futex_key *key) +{ + return __futex_hash(key, NULL); +} + +#endif /* CONFIG_FUTEX_PRIVATE_HASH */ + +/** + * __futex_hash - Return the hash bucket + * @key: Pointer to the futex key for which the hash is calculated + * @fph: Pointer to private hash if known + * + * We hash on the keys returned from get_futex_key (see below) and return the + * corresponding hash bucket. + * If the FUTEX is PROCESS_PRIVATE then a per-process hash bucket (from the + * private hash) is returned if existing. Otherwise a hash bucket from the + * global hash is returned. + */ +static struct futex_hash_bucket * +__futex_hash(union futex_key *key, struct futex_private_hash *fph) +{ + struct futex_hash_bucket *hb; + u32 hash; + + hb = __futex_hash_private(key, fph); + if (hb) + return hb; + + hash = jhash2((u32 *)key, + offsetof(typeof(*key), both.offset) / 4, + key->both.offset); + return &futex_queues[hash & futex_hashmask]; +} + /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value @@ -985,6 +1065,13 @@ static void exit_pi_state_list(struct task_struct *curr) struct futex_pi_state *pi_state; union futex_key key = FUTEX_KEY_INIT; + /* + * Ensure the hash remains stable (no resize) during the while loop + * below. The hb pointer is acquired under the pi_lock so we can't block + * on the mutex. + */ + WARN_ON(curr != current); + guard(private_hash)(); /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful @@ -1160,13 +1247,98 @@ void futex_exit_release(struct task_struct *tsk) futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } -static void futex_hash_bucket_init(struct futex_hash_bucket *fhb) +static void futex_hash_bucket_init(struct futex_hash_bucket *fhb, + struct futex_private_hash *fph) { +#ifdef CONFIG_FUTEX_PRIVATE_HASH + fhb->priv = fph; +#endif atomic_set(&fhb->waiters, 0); plist_head_init(&fhb->chain); spin_lock_init(&fhb->lock); } +#ifdef CONFIG_FUTEX_PRIVATE_HASH +void futex_hash_free(struct mm_struct *mm) +{ + kvfree(mm->futex_phash); +} + +static int futex_hash_allocate(unsigned int hash_slots, bool custom) +{ + struct mm_struct *mm = current->mm; + struct futex_private_hash *fph; + int i; + + if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots))) + return -EINVAL; + + if (mm->futex_phash) + return -EALREADY; + + if (!thread_group_empty(current)) + return -EINVAL; + + fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + if (!fph) + return -ENOMEM; + + fph->hash_mask = hash_slots ? hash_slots - 1 : 0; + fph->custom = custom; + fph->mm = mm; + + for (i = 0; i < hash_slots; i++) + futex_hash_bucket_init(&fph->queues[i], fph); + + mm->futex_phash = fph; + return 0; +} + +static int futex_hash_get_slots(void) +{ + struct futex_private_hash *fph; + + fph = current->mm->futex_phash; + if (fph && fph->hash_mask) + return fph->hash_mask + 1; + return 0; +} + +#else + +static int futex_hash_allocate(unsigned int hash_slots, bool custom) +{ + return -EINVAL; +} + +static int futex_hash_get_slots(void) +{ + return 0; +} +#endif + +int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) +{ + int ret; + + switch (arg2) { + case PR_FUTEX_HASH_SET_SLOTS: + if (arg4 != 0) + return -EINVAL; + ret = futex_hash_allocate(arg3, true); + break; + + case PR_FUTEX_HASH_GET_SLOTS: + ret = futex_hash_get_slots(); + break; + + default: + ret = -EINVAL; + break; + } + return ret; +} + static int __init futex_init(void) { unsigned long hashsize, i; @@ -1185,7 +1357,7 @@ static int __init futex_init(void) hashsize = 1UL << futex_shift; for (i = 0; i < hashsize; i++) - futex_hash_bucket_init(&futex_queues[i]); + futex_hash_bucket_init(&futex_queues[i], NULL); futex_hashmask = hashsize - 1; return 0; diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 26e69333cb74..899aed5acde1 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -118,6 +118,7 @@ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; + struct futex_private_hash *priv; } ____cacheline_aligned_in_smp; /* @@ -204,6 +205,7 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); +#ifdef CONFIG_FUTEX_PRIVATE_HASH extern void futex_hash_get(struct futex_hash_bucket *hb); extern void futex_hash_put(struct futex_hash_bucket *hb); @@ -211,6 +213,14 @@ extern struct futex_private_hash *futex_private_hash(void); extern bool futex_private_hash_get(struct futex_private_hash *fph); extern void futex_private_hash_put(struct futex_private_hash *fph); +#else /* !CONFIG_FUTEX_PRIVATE_HASH */ +static inline void futex_hash_get(struct futex_hash_bucket *hb) { } +static inline void futex_hash_put(struct futex_hash_bucket *hb) { } +static inline struct futex_private_hash *futex_private_hash(void) { return NULL; } +static inline bool futex_private_hash_get(void) { return false; } +static inline void futex_private_hash_put(struct futex_private_hash *fph) { } +#endif + DEFINE_CLASS(hb, struct futex_hash_bucket *, if (_T) futex_hash_put(_T), futex_hash(key), union futex_key *key); diff --git a/kernel/sys.c b/kernel/sys.c index c434968e9f5d..adc0de0aa364 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include @@ -2820,6 +2821,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = posixtimer_create_prctl(arg2); break; + case PR_FUTEX_HASH: + error = futex_hash_prctl(arg2, arg3, arg4); + break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL; -- cgit v1.2.3 From 63e8595c060a1fef421e3eecfc05ad882dafb8ac Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 16 Apr 2025 18:29:15 +0200 Subject: futex: Allow to make the private hash immutable My initial testing showed that: perf bench futex hash reported less operations/sec with private hash. After using the same amount of buckets in the private hash as used by the global hash then the operations/sec were about the same. This changed once the private hash became resizable. This feature added an RCU section and reference counting via atomic inc+dec operation into the hot path. The reference counting can be avoided if the private hash is made immutable. Extend PR_FUTEX_HASH_SET_SLOTS by a fourth argument which denotes if the private should be made immutable. Once set (to true) the a further resize is not allowed (same if set to global hash). Add PR_FUTEX_HASH_GET_IMMUTABLE which returns true if the hash can not be changed. Update "perf bench" suite. For comparison, results of "perf bench futex hash -s": - Xeon CPU E5-2650, 2 NUMA nodes, total 32 CPUs: - Before the introducing task local hash shared Averaged 1.487.148 operations/sec (+- 0,53%), total secs = 10 private Averaged 2.192.405 operations/sec (+- 0,07%), total secs = 10 - With the series shared Averaged 1.326.342 operations/sec (+- 0,41%), total secs = 10 -b128 Averaged 141.394 operations/sec (+- 1,15%), total secs = 10 -Ib128 Averaged 851.490 operations/sec (+- 0,67%), total secs = 10 -b8192 Averaged 131.321 operations/sec (+- 2,13%), total secs = 10 -Ib8192 Averaged 1.923.077 operations/sec (+- 0,61%), total secs = 10 128 is the default allocation of hash buckets. 8192 was the previous amount of allocated hash buckets. - Xeon(R) CPU E7-8890 v3, 4 NUMA nodes, total 144 CPUs: - Before the introducing task local hash shared Averaged 1.810.936 operations/sec (+- 0,26%), total secs = 20 private Averaged 2.505.801 operations/sec (+- 0,05%), total secs = 20 - With the series shared Averaged 1.589.002 operations/sec (+- 0,25%), total secs = 20 -b1024 Averaged 42.410 operations/sec (+- 0,20%), total secs = 20 -Ib1024 Averaged 740.638 operations/sec (+- 1,51%), total secs = 20 -b65536 Averaged 48.811 operations/sec (+- 1,35%), total secs = 20 -Ib65536 Averaged 1.963.165 operations/sec (+- 0,18%), total secs = 20 1024 is the default allocation of hash buckets. 65536 was the previous amount of allocated hash buckets. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Acked-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20250416162921.513656-16-bigeasy@linutronix.de --- include/uapi/linux/prctl.h | 2 ++ kernel/futex/core.c | 49 ++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3b93fb906e3c..43dec6eed559 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -367,6 +367,8 @@ struct prctl_mm_map { /* FUTEX hash management */ #define PR_FUTEX_HASH 78 # define PR_FUTEX_HASH_SET_SLOTS 1 +# define FH_FLAG_IMMUTABLE (1ULL << 0) # define PR_FUTEX_HASH_GET_SLOTS 2 +# define PR_FUTEX_HASH_GET_IMMUTABLE 3 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 9e7dad52abea..8054fda94719 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -63,6 +63,7 @@ struct futex_private_hash { struct rcu_head rcu; void *mm; bool custom; + bool immutable; struct futex_hash_bucket queues[]; }; @@ -132,12 +133,16 @@ static inline bool futex_key_is_private(union futex_key *key) bool futex_private_hash_get(struct futex_private_hash *fph) { + if (fph->immutable) + return true; return rcuref_get(&fph->users); } void futex_private_hash_put(struct futex_private_hash *fph) { /* Ignore return value, last put is verified via rcuref_is_dead() */ + if (fph->immutable) + return; if (rcuref_put(&fph->users)) wake_up_var(fph->mm); } @@ -277,6 +282,8 @@ again: if (!fph) return NULL; + if (fph->immutable) + return fph; if (rcuref_get(&fph->users)) return fph; } @@ -1383,6 +1390,9 @@ static void futex_hash_bucket_init(struct futex_hash_bucket *fhb, spin_lock_init(&fhb->lock); } +#define FH_CUSTOM 0x01 +#define FH_IMMUTABLE 0x02 + #ifdef CONFIG_FUTEX_PRIVATE_HASH void futex_hash_free(struct mm_struct *mm) { @@ -1433,10 +1443,11 @@ static bool futex_hash_less(struct futex_private_hash *a, return false; /* equal */ } -static int futex_hash_allocate(unsigned int hash_slots, bool custom) +static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) { struct mm_struct *mm = current->mm; struct futex_private_hash *fph; + bool custom = flags & FH_CUSTOM; int i; if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots))) @@ -1447,7 +1458,7 @@ static int futex_hash_allocate(unsigned int hash_slots, bool custom) */ scoped_guard(rcu) { fph = rcu_dereference(mm->futex_phash); - if (fph && !fph->hash_mask) { + if (fph && (!fph->hash_mask || fph->immutable)) { if (custom) return -EBUSY; return 0; @@ -1461,6 +1472,7 @@ static int futex_hash_allocate(unsigned int hash_slots, bool custom) rcuref_init(&fph->users, 1); fph->hash_mask = hash_slots ? hash_slots - 1 : 0; fph->custom = custom; + fph->immutable = !!(flags & FH_IMMUTABLE); fph->mm = mm; for (i = 0; i < hash_slots; i++) @@ -1553,7 +1565,7 @@ int futex_hash_allocate_default(void) if (current_buckets >= buckets) return 0; - return futex_hash_allocate(buckets, false); + return futex_hash_allocate(buckets, 0); } static int futex_hash_get_slots(void) @@ -1567,9 +1579,22 @@ static int futex_hash_get_slots(void) return 0; } +static int futex_hash_get_immutable(void) +{ + struct futex_private_hash *fph; + + guard(rcu)(); + fph = rcu_dereference(current->mm->futex_phash); + if (fph && fph->immutable) + return 1; + if (fph && !fph->hash_mask) + return 1; + return 0; +} + #else -static int futex_hash_allocate(unsigned int hash_slots, bool custom) +static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) { return -EINVAL; } @@ -1578,23 +1603,35 @@ static int futex_hash_get_slots(void) { return 0; } + +static int futex_hash_get_immutable(void) +{ + return 0; +} #endif int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) { + unsigned int flags = FH_CUSTOM; int ret; switch (arg2) { case PR_FUTEX_HASH_SET_SLOTS: - if (arg4 != 0) + if (arg4 & ~FH_FLAG_IMMUTABLE) return -EINVAL; - ret = futex_hash_allocate(arg3, true); + if (arg4 & FH_FLAG_IMMUTABLE) + flags |= FH_IMMUTABLE; + ret = futex_hash_allocate(arg3, flags); break; case PR_FUTEX_HASH_GET_SLOTS: ret = futex_hash_get_slots(); break; + case PR_FUTEX_HASH_GET_IMMUTABLE: + ret = futex_hash_get_immutable(); + break; + default: ret = -EINVAL; break; -- cgit v1.2.3 From cec199c5e39bde7191a08087cc3d002ccfab31ff Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Apr 2025 18:29:16 +0200 Subject: futex: Implement FUTEX2_NUMA Extend the futex2 interface to be numa aware. When FUTEX2_NUMA is specified for a futex, the user value is extended to two words (of the same size). The first is the user value we all know, the second one will be the node to place this futex on. struct futex_numa_32 { u32 val; u32 node; }; When node is set to ~0, WAIT will set it to the current node_id such that WAKE knows where to find it. If userspace corrupts the node value between WAIT and WAKE, the futex will not be found and no wakeup will happen. When FUTEX2_NUMA is not set, the node is simply an extension of the hash, such that traditional futexes are still interleaved over the nodes. This is done to avoid having to have a separate !numa hash-table. [bigeasy: ensure to have at least hashsize of 4 in futex_init(), add pr_info() for size and allocation information. Cast the naddr math to void*] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-17-bigeasy@linutronix.de --- include/linux/futex.h | 3 ++ include/uapi/linux/futex.h | 7 ++++ kernel/futex/core.c | 100 +++++++++++++++++++++++++++++++++++++-------- kernel/futex/futex.h | 33 +++++++++++++-- 4 files changed, 123 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 40bc778b2bb4..eccc99751bd9 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -34,6 +34,7 @@ union futex_key { u64 i_seq; unsigned long pgoff; unsigned int offset; + /* unsigned int node; */ } shared; struct { union { @@ -42,11 +43,13 @@ union futex_key { }; unsigned long address; unsigned int offset; + /* unsigned int node; */ } private; struct { u64 ptr; unsigned long word; unsigned int offset; + unsigned int node; /* NOT hashed! */ } both; }; diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index d2ee625ea189..6b94da467e70 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -74,6 +74,13 @@ /* do not use */ #define FUTEX_32 FUTEX2_SIZE_U32 /* historical accident :-( */ +/* + * When FUTEX2_NUMA doubles the futex word, the second word is a node value. + * The special value -1 indicates no-node. This is the same value as + * NUMA_NO_NODE, except that value is not ABI, this is. + */ +#define FUTEX_NO_NODE (-1) + /* * Max numbers of elements in a futex_waitv array */ diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 8054fda94719..1490e6492993 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -36,6 +36,8 @@ #include #include #include +#include +#include #include #include #include @@ -51,11 +53,14 @@ * reside in the same cacheline. */ static struct { - struct futex_hash_bucket *queues; unsigned long hashmask; + unsigned int hashshift; + struct futex_hash_bucket *queues[MAX_NUMNODES]; } __futex_data __read_mostly __aligned(2*sizeof(long)); -#define futex_queues (__futex_data.queues) -#define futex_hashmask (__futex_data.hashmask) + +#define futex_hashmask (__futex_data.hashmask) +#define futex_hashshift (__futex_data.hashshift) +#define futex_queues (__futex_data.queues) struct futex_private_hash { rcuref_t users; @@ -339,15 +344,35 @@ __futex_hash(union futex_key *key, struct futex_private_hash *fph) { struct futex_hash_bucket *hb; u32 hash; + int node; hb = __futex_hash_private(key, fph); if (hb) return hb; hash = jhash2((u32 *)key, - offsetof(typeof(*key), both.offset) / 4, + offsetof(typeof(*key), both.offset) / sizeof(u32), key->both.offset); - return &futex_queues[hash & futex_hashmask]; + node = key->both.node; + + if (node == FUTEX_NO_NODE) { + /* + * In case of !FLAGS_NUMA, use some unused hash bits to pick a + * node -- this ensures regular futexes are interleaved across + * the nodes and avoids having to allocate multiple + * hash-tables. + * + * NOTE: this isn't perfectly uniform, but it is fast and + * handles sparse node masks. + */ + node = (hash >> futex_hashshift) % nr_node_ids; + if (!node_possible(node)) { + node = find_next_bit_wrap(node_possible_map.bits, + nr_node_ids, node); + } + } + + return &futex_queues[node][hash & futex_hashmask]; } /** @@ -454,25 +479,49 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, struct page *page; struct folio *folio; struct address_space *mapping; - int err, ro = 0; + int node, err, size, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; + size = futex_size(flags); + if (flags & FLAGS_NUMA) + size *= 2; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; - if (unlikely((address % sizeof(u32)) != 0)) + if (unlikely((address % size) != 0)) return -EINVAL; address -= key->both.offset; - if (unlikely(!access_ok(uaddr, sizeof(u32)))) + if (unlikely(!access_ok(uaddr, size))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; + if (flags & FLAGS_NUMA) { + u32 __user *naddr = (void *)uaddr + size / 2; + + if (futex_get_value(&node, naddr)) + return -EFAULT; + + if (node == FUTEX_NO_NODE) { + node = numa_node_id(); + if (futex_put_value(node, naddr)) + return -EFAULT; + + } else if (node >= MAX_NUMNODES || !node_possible(node)) { + return -EINVAL; + } + + key->both.node = node; + + } else { + key->both.node = FUTEX_NO_NODE; + } + /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs @@ -1642,24 +1691,41 @@ int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) static int __init futex_init(void) { unsigned long hashsize, i; - unsigned int futex_shift; + unsigned int order, n; + unsigned long size; #ifdef CONFIG_BASE_SMALL hashsize = 16; #else - hashsize = roundup_pow_of_two(256 * num_possible_cpus()); + hashsize = 256 * num_possible_cpus(); + hashsize /= num_possible_nodes(); + hashsize = max(4, hashsize); + hashsize = roundup_pow_of_two(hashsize); #endif + futex_hashshift = ilog2(hashsize); + size = sizeof(struct futex_hash_bucket) * hashsize; + order = get_order(size); - futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), - hashsize, 0, 0, - &futex_shift, NULL, - hashsize, hashsize); - hashsize = 1UL << futex_shift; + for_each_node(n) { + struct futex_hash_bucket *table; - for (i = 0; i < hashsize; i++) - futex_hash_bucket_init(&futex_queues[i], NULL); + if (order > MAX_PAGE_ORDER) + table = vmalloc_huge_node(size, GFP_KERNEL, n); + else + table = alloc_pages_exact_nid(n, size, GFP_KERNEL); + + BUG_ON(!table); + + for (i = 0; i < hashsize; i++) + futex_hash_bucket_init(&table[i], NULL); + + futex_queues[n] = table; + } futex_hashmask = hashsize - 1; + pr_info("futex hash table entries: %lu (%lu bytes on %d NUMA nodes, total %lu KiB, %s).\n", + hashsize, size, num_possible_nodes(), size * num_possible_nodes() / 1024, + order > MAX_PAGE_ORDER ? "vmalloc" : "linear"); return 0; } core_initcall(futex_init); diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 899aed5acde1..acc795367889 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -54,7 +54,7 @@ static inline unsigned int futex_to_flags(unsigned int op) return flags; } -#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) @@ -87,6 +87,19 @@ static inline bool futex_flags_valid(unsigned int flags) if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) return false; + /* + * Must be able to represent both FUTEX_NO_NODE and every valid nodeid + * in a futex word. + */ + if (flags & FLAGS_NUMA) { + int bits = 8 * futex_size(flags); + u64 max = ~0ULL; + + max >>= 64 - bits; + if (nr_node_ids >= max) + return false; + } + return true; } @@ -282,7 +295,7 @@ static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 * This looks a bit overkill, but generally just results in a couple * of instructions. */ -static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from) +static __always_inline int futex_get_value(u32 *dest, u32 __user *from) { u32 val; @@ -299,12 +312,26 @@ Efault: return -EFAULT; } +static __always_inline int futex_put_value(u32 val, u32 __user *to) +{ + if (can_do_masked_user_access()) + to = masked_user_access_begin(to); + else if (!user_read_access_begin(to, sizeof(*to))) + return -EFAULT; + unsafe_put_user(val, to, Efault); + user_read_access_end(); + return 0; +Efault: + user_read_access_end(); + return -EFAULT; +} + static inline int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); - ret = futex_read_inatomic(dest, from); + ret = futex_get_value(dest, from); pagefault_enable(); return ret; -- cgit v1.2.3 From c042c505210dc3453f378df432c10fff3d471bc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Apr 2025 18:29:17 +0200 Subject: futex: Implement FUTEX2_MPOL Extend the futex2 interface to be aware of mempolicy. When FUTEX2_MPOL is specified and there is a MPOL_PREFERRED or home_node specified covering the futex address, use that hash-map. Notably, in this case the futex will go to the global node hashtable, even if it is a PRIVATE futex. When FUTEX2_NUMA|FUTEX2_MPOL is specified and the user specified node value is FUTEX_NO_NODE, the MPOL lookup (as described above) will be tried first before reverting to setting node to the local node. [bigeasy: add CONFIG_FUTEX_MPOL, add MPOL to FUTEX2_VALID_MASK, write the node only to user if FUTEX_NO_NODE was supplied] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-18-bigeasy@linutronix.de --- include/linux/mmap_lock.h | 4 ++ include/uapi/linux/futex.h | 2 +- init/Kconfig | 5 ++ kernel/futex/core.c | 116 ++++++++++++++++++++++++++++++++++++++------- kernel/futex/futex.h | 6 ++- 5 files changed, 115 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 4706c6769902..e0eddfd306ef 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -7,6 +7,7 @@ #include #include #include +#include #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), @@ -211,6 +212,9 @@ static inline void mmap_read_unlock(struct mm_struct *mm) up_read(&mm->mmap_lock); } +DEFINE_GUARD(mmap_read_lock, struct mm_struct *, + mmap_read_lock(_T), mmap_read_unlock(_T)) + static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 6b94da467e70..7e2744ec8933 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -63,7 +63,7 @@ #define FUTEX2_SIZE_U32 0x02 #define FUTEX2_SIZE_U64 0x03 #define FUTEX2_NUMA 0x04 - /* 0x08 */ +#define FUTEX2_MPOL 0x08 /* 0x10 */ /* 0x20 */ /* 0x40 */ diff --git a/init/Kconfig b/init/Kconfig index 4b84da2b2ec4..b373267ba2e2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1704,6 +1704,11 @@ config FUTEX_PRIVATE_HASH depends on FUTEX && !BASE_SMALL && MMU default y +config FUTEX_MPOL + bool + depends on FUTEX && NUMA + default y + config EPOLL bool "Enable eventpoll support" if EXPERT default y diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 1490e6492993..19a2c65f3d37 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -43,6 +43,8 @@ #include #include #include +#include +#include #include "futex.h" #include "../locking/rtmutex_common.h" @@ -328,6 +330,75 @@ struct futex_hash_bucket *futex_hash(union futex_key *key) #endif /* CONFIG_FUTEX_PRIVATE_HASH */ +#ifdef CONFIG_FUTEX_MPOL + +static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = vma_lookup(mm, addr); + struct mempolicy *mpol; + int node = FUTEX_NO_NODE; + + if (!vma) + return FUTEX_NO_NODE; + + mpol = vma_policy(vma); + if (!mpol) + return FUTEX_NO_NODE; + + switch (mpol->mode) { + case MPOL_PREFERRED: + node = first_node(mpol->nodes); + break; + case MPOL_PREFERRED_MANY: + case MPOL_BIND: + if (mpol->home_node != NUMA_NO_NODE) + node = mpol->home_node; + break; + default: + break; + } + + return node; +} + +static int futex_key_to_node_opt(struct mm_struct *mm, unsigned long addr) +{ + int seq, node; + + guard(rcu)(); + + if (!mmap_lock_speculate_try_begin(mm, &seq)) + return -EBUSY; + + node = __futex_key_to_node(mm, addr); + + if (mmap_lock_speculate_retry(mm, seq)) + return -EAGAIN; + + return node; +} + +static int futex_mpol(struct mm_struct *mm, unsigned long addr) +{ + int node; + + node = futex_key_to_node_opt(mm, addr); + if (node >= FUTEX_NO_NODE) + return node; + + guard(mmap_read_lock)(mm); + return __futex_key_to_node(mm, addr); +} + +#else /* !CONFIG_FUTEX_MPOL */ + +static int futex_mpol(struct mm_struct *mm, unsigned long addr) +{ + return FUTEX_NO_NODE; +} + +#endif /* CONFIG_FUTEX_MPOL */ + /** * __futex_hash - Return the hash bucket * @key: Pointer to the futex key for which the hash is calculated @@ -342,18 +413,20 @@ struct futex_hash_bucket *futex_hash(union futex_key *key) static struct futex_hash_bucket * __futex_hash(union futex_key *key, struct futex_private_hash *fph) { - struct futex_hash_bucket *hb; + int node = key->both.node; u32 hash; - int node; - hb = __futex_hash_private(key, fph); - if (hb) - return hb; + if (node == FUTEX_NO_NODE) { + struct futex_hash_bucket *hb; + + hb = __futex_hash_private(key, fph); + if (hb) + return hb; + } hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / sizeof(u32), key->both.offset); - node = key->both.node; if (node == FUTEX_NO_NODE) { /* @@ -480,6 +553,7 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, struct folio *folio; struct address_space *mapping; int node, err, size, ro = 0; + bool node_updated = false; bool fshared; fshared = flags & FLAGS_SHARED; @@ -501,27 +575,37 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, if (unlikely(should_fail_futex(fshared))) return -EFAULT; + node = FUTEX_NO_NODE; + if (flags & FLAGS_NUMA) { u32 __user *naddr = (void *)uaddr + size / 2; if (futex_get_value(&node, naddr)) return -EFAULT; - if (node == FUTEX_NO_NODE) { - node = numa_node_id(); - if (futex_put_value(node, naddr)) - return -EFAULT; - - } else if (node >= MAX_NUMNODES || !node_possible(node)) { + if (node != FUTEX_NO_NODE && + (node >= MAX_NUMNODES || !node_possible(node))) return -EINVAL; - } + } - key->both.node = node; + if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) { + node = futex_mpol(mm, address); + node_updated = true; + } - } else { - key->both.node = FUTEX_NO_NODE; + if (flags & FLAGS_NUMA) { + u32 __user *naddr = (void *)uaddr + size / 2; + + if (node == FUTEX_NO_NODE) { + node = numa_node_id(); + node_updated = true; + } + if (node_updated && futex_put_value(node, naddr)) + return -EFAULT; } + key->both.node = node; + /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index acc795367889..069fc2a83080 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -39,6 +39,7 @@ #define FLAGS_HAS_TIMEOUT 0x0040 #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 +#define FLAGS_MPOL 0x0200 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) @@ -54,7 +55,7 @@ static inline unsigned int futex_to_flags(unsigned int op) return flags; } -#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_PRIVATE) +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) @@ -67,6 +68,9 @@ static inline unsigned int futex2_to_flags(unsigned int flags2) if (flags2 & FUTEX2_NUMA) flags |= FLAGS_NUMA; + if (flags2 & FUTEX2_MPOL) + flags |= FLAGS_MPOL; + return flags; } -- cgit v1.2.3 From 7734fb4ad98c3fdaf0fde82978ef8638195a5285 Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Tue, 29 Apr 2025 18:50:18 +0200 Subject: dm mpath: Interface for explicit probing of active paths Multipath cannot directly provide failover for ioctls in the kernel because it doesn't know what each ioctl means and which result could indicate a path error. Userspace generally knows what the ioctl it issued means and if it might be a path error, but neither does it know which path the ioctl took nor does it necessarily have the privileges to fail a path using the control device. In order to allow userspace to address this situation, implement a DM_MPATH_PROBE_PATHS ioctl that prompts the dm-mpath driver to probe all active paths in the current path group to see whether they still work, and fail them if not. If this returns success, userspace can retry the ioctl and expect that the previously hit bad path is now failed (or working again). The immediate motivation for this is the use of SG_IO in QEMU for SCSI passthrough. Following a failed SG_IO ioctl, QEMU will trigger probing to ensure that all active paths are actually alive, so that retrying SG_IO at least has a lower chance of failing due to a path error. However, the problem is broader than just SG_IO (it affects any ioctl), and if applications need failover support for other ioctls, the same probing can be used. This is not implemented on the DM control device, but on the DM mpath block devices, to allow all users who have access to such a block device to make use of this interface, specifically to implement failover for ioctls. For the same reason, it is also unprivileged. Its implementation is effectively just a bunch of reads, which could already be issued by userspace, just without any guarantee that all the rights paths are selected. The probing implemented here is done fully synchronously path by path; probing all paths concurrently is left as an improvement for the future. Co-developed-by: Hanna Czenczek Signed-off-by: Hanna Czenczek Signed-off-by: Kevin Wolf Reviewed-by: Benjamin Marzinski Signed-off-by: Benjamin Marzinski Signed-off-by: Mikulas Patocka --- drivers/md/dm-ioctl.c | 1 + drivers/md/dm-mpath.c | 100 +++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/dm-ioctl.h | 9 +++- 3 files changed, 107 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index d42eac944eb5..4165fef4c170 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1885,6 +1885,7 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) {DM_DEV_SET_GEOMETRY_CMD, 0, dev_set_geometry}, {DM_DEV_ARM_POLL_CMD, IOCTL_FLAGS_NO_PARAMS, dev_arm_poll}, {DM_GET_TARGET_VERSION_CMD, 0, get_target_version}, + {DM_MPATH_PROBE_PATHS_CMD, 0, NULL}, /* block device ioctl */ }; if (unlikely(cmd >= ARRAY_SIZE(_ioctls))) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 909ed6890ba5..53861ad5dd1d 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -2021,6 +2021,94 @@ out: return r; } +/* + * Perform a minimal read from the given path to find out whether the + * path still works. If a path error occurs, fail it. + */ +static int probe_path(struct pgpath *pgpath) +{ + struct block_device *bdev = pgpath->path.dev->bdev; + unsigned int read_size = bdev_logical_block_size(bdev); + struct page *page; + struct bio *bio; + blk_status_t status; + int r = 0; + + if (WARN_ON_ONCE(read_size > PAGE_SIZE)) + return -EINVAL; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + /* Perform a minimal read: Sector 0, length read_size */ + bio = bio_alloc(bdev, 1, REQ_OP_READ, GFP_KERNEL); + if (!bio) { + r = -ENOMEM; + goto out; + } + + bio->bi_iter.bi_sector = 0; + __bio_add_page(bio, page, read_size, 0); + submit_bio_wait(bio); + status = bio->bi_status; + bio_put(bio); + + if (status && blk_path_error(status)) + fail_path(pgpath); + +out: + __free_page(page); + return r; +} + +/* + * Probe all active paths in current_pg to find out whether they still work. + * Fail all paths that do not work. + * + * Return -ENOTCONN if no valid path is left (even outside of current_pg). We + * cannot probe paths in other pgs without switching current_pg, so if valid + * paths are only in different pgs, they may or may not work. Additionally + * we should not probe paths in a pathgroup that is in the process of + * Initializing. Userspace can submit a request and we'll switch and wait + * for the pathgroup to be initialized. If the request fails, it may need to + * probe again. + */ +static int probe_active_paths(struct multipath *m) +{ + struct pgpath *pgpath; + struct priority_group *pg; + unsigned long flags; + int r = 0; + + mutex_lock(&m->work_mutex); + + spin_lock_irqsave(&m->lock, flags); + if (test_bit(MPATHF_QUEUE_IO, &m->flags)) + pg = NULL; + else + pg = m->current_pg; + spin_unlock_irqrestore(&m->lock, flags); + + if (pg) { + list_for_each_entry(pgpath, &pg->pgpaths, list) { + if (!pgpath->is_active) + continue; + + r = probe_path(pgpath); + if (r < 0) + goto out; + } + } + + if (!atomic_read(&m->nr_valid_paths)) + r = -ENOTCONN; + +out: + mutex_unlock(&m->work_mutex); + return r; +} + static int multipath_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, unsigned int cmd, unsigned long arg, @@ -2031,6 +2119,16 @@ static int multipath_prepare_ioctl(struct dm_target *ti, unsigned long flags; int r; + if (_IOC_TYPE(cmd) == DM_IOCTL) { + *forward = false; + switch (cmd) { + case DM_MPATH_PROBE_PATHS: + return probe_active_paths(m); + default: + return -ENOTTY; + } + } + pgpath = READ_ONCE(m->current_pgpath); if (!pgpath || !mpath_double_check_test_bit(MPATHF_QUEUE_IO, m)) pgpath = choose_pgpath(m, 0); @@ -2182,7 +2280,7 @@ static int multipath_busy(struct dm_target *ti) */ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 14, 0}, + .version = {1, 15, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE | DM_TARGET_PASSES_INTEGRITY, .module = THIS_MODULE, diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index b08c7378164d..3225e025e30e 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -258,10 +258,12 @@ enum { DM_DEV_SET_GEOMETRY_CMD, DM_DEV_ARM_POLL_CMD, DM_GET_TARGET_VERSION_CMD, + DM_MPATH_PROBE_PATHS_CMD, }; #define DM_IOCTL 0xfd +/* Control device ioctls */ #define DM_VERSION _IOWR(DM_IOCTL, DM_VERSION_CMD, struct dm_ioctl) #define DM_REMOVE_ALL _IOWR(DM_IOCTL, DM_REMOVE_ALL_CMD, struct dm_ioctl) #define DM_LIST_DEVICES _IOWR(DM_IOCTL, DM_LIST_DEVICES_CMD, struct dm_ioctl) @@ -285,10 +287,13 @@ enum { #define DM_TARGET_MSG _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, struct dm_ioctl) #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) +/* Block device ioctls */ +#define DM_MPATH_PROBE_PATHS _IO(DM_IOCTL, DM_MPATH_PROBE_PATHS_CMD) + #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 49 +#define DM_VERSION_MINOR 50 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2025-01-17)" +#define DM_VERSION_EXTRA "-ioctl (2025-04-28)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From eeadd68e2a5f6bfe0bf1038ec49e3a8d99eb5fe8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 May 2025 10:11:25 +0200 Subject: block: remove bounce buffering support The block layer bounce buffering support is unused now, remove it. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: John Garry Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20250505081138.3435992-7-hch@lst.de Signed-off-by: Jens Axboe --- arch/mips/configs/gcw0_defconfig | 1 - block/Makefile | 1 - block/blk-map.c | 5 +- block/blk-mq.c | 2 - block/blk-settings.c | 5 - block/blk.h | 17 --- block/bounce.c | 267 -------------------------------------- include/linux/blk_types.h | 1 - include/linux/blkdev.h | 5 +- include/trace/events/block.h | 15 --- include/uapi/linux/blktrace_api.h | 2 +- kernel/trace/blktrace.c | 9 -- 12 files changed, 3 insertions(+), 327 deletions(-) delete mode 100644 block/bounce.c (limited to 'include/uapi/linux') diff --git a/arch/mips/configs/gcw0_defconfig b/arch/mips/configs/gcw0_defconfig index bc1ef66e3999..8b7ad877e07a 100644 --- a/arch/mips/configs/gcw0_defconfig +++ b/arch/mips/configs/gcw0_defconfig @@ -13,7 +13,6 @@ CONFIG_MIPS_CMDLINE_DTB_EXTEND=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_BOUNCE is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/block/Makefile b/block/Makefile index 3a941dc0d27f..36033c0f07bc 100644 --- a/block/Makefile +++ b/block/Makefile @@ -11,7 +11,6 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ disk-events.o blk-ia-ranges.o early-lookup.o -obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o diff --git a/block/blk-map.c b/block/blk-map.c index d2f22744b3d1..cadbf11b50a3 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -556,8 +556,6 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, if (map_data) copy = true; - else if (blk_queue_may_bounce(q)) - copy = true; else if (iov_iter_alignment(iter) & align) copy = true; else if (iov_iter_is_bvec(iter)) @@ -713,8 +711,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (!len || !kbuf) return -EINVAL; - if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf) || - blk_queue_may_bounce(q)) + if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf)) bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading); else bio = bio_map_kern(q, kbuf, len, gfp_mask); diff --git a/block/blk-mq.c b/block/blk-mq.c index 796baeccd37b..83c651a7facd 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3144,8 +3144,6 @@ void blk_mq_submit_bio(struct bio *bio) goto new_request; } - bio = blk_queue_bounce(bio, q); - /* * The cached request already holds a q_usage_counter reference and we * don't have to acquire a new one if we use it. diff --git a/block/blk-settings.c b/block/blk-settings.c index 4817e7ca03f8..a000daafbfb4 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -124,11 +124,6 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) return 0; } - if (lim->features & BLK_FEAT_BOUNCE_HIGH) { - pr_warn("no bounce buffer support for integrity metadata\n"); - return -EINVAL; - } - if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { pr_warn("integrity support disabled.\n"); return -EINVAL; diff --git a/block/blk.h b/block/blk.h index 328075787814..ff21f234b62f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -443,23 +443,6 @@ static inline void ioc_clear_queue(struct request_queue *q) } #endif /* CONFIG_BLK_ICQ */ -struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q); - -static inline bool blk_queue_may_bounce(struct request_queue *q) -{ - return IS_ENABLED(CONFIG_BOUNCE) && - (q->limits.features & BLK_FEAT_BOUNCE_HIGH) && - max_low_pfn >= max_pfn; -} - -static inline struct bio *blk_queue_bounce(struct bio *bio, - struct request_queue *q) -{ - if (unlikely(blk_queue_may_bounce(q) && bio_has_data(bio))) - return __blk_queue_bounce(bio, q); - return bio; -} - #ifdef CONFIG_BLK_DEV_ZONED void disk_init_zone_resources(struct gendisk *disk); void disk_free_zone_resources(struct gendisk *disk); diff --git a/block/bounce.c b/block/bounce.c deleted file mode 100644 index 09a9616cf209..000000000000 --- a/block/bounce.c +++ /dev/null @@ -1,267 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* bounce buffer handling for block devices - * - * - Split from highmem.c - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include "blk.h" -#include "blk-cgroup.h" - -#define POOL_SIZE 64 -#define ISA_POOL_SIZE 16 - -static struct bio_set bounce_bio_set, bounce_bio_split; -static mempool_t page_pool; - -static void init_bounce_bioset(void) -{ - static bool bounce_bs_setup; - int ret; - - if (bounce_bs_setup) - return; - - ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - BUG_ON(ret); - - ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0); - BUG_ON(ret); - bounce_bs_setup = true; -} - -static __init int init_emergency_pool(void) -{ - int ret; - -#ifndef CONFIG_MEMORY_HOTPLUG - if (max_pfn <= max_low_pfn) - return 0; -#endif - - ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0); - BUG_ON(ret); - pr_info("pool size: %d pages\n", POOL_SIZE); - - init_bounce_bioset(); - return 0; -} - -__initcall(init_emergency_pool); - -/* - * Simple bounce buffer support for highmem pages. Depending on the - * queue gfp mask set, *to may or may not be a highmem page. kmap it - * always, it will do the Right Thing - */ -static void copy_to_high_bio_irq(struct bio *to, struct bio *from) -{ - struct bio_vec tovec, fromvec; - struct bvec_iter iter; - /* - * The bio of @from is created by bounce, so we can iterate - * its bvec from start to end, but the @from->bi_iter can't be - * trusted because it might be changed by splitting. - */ - struct bvec_iter from_iter = BVEC_ITER_ALL_INIT; - - bio_for_each_segment(tovec, to, iter) { - fromvec = bio_iter_iovec(from, from_iter); - if (tovec.bv_page != fromvec.bv_page) { - /* - * fromvec->bv_offset and fromvec->bv_len might have - * been modified by the block layer, so use the original - * copy, bounce_copy_vec already uses tovec->bv_len - */ - memcpy_to_bvec(&tovec, page_address(fromvec.bv_page) + - tovec.bv_offset); - } - bio_advance_iter(from, &from_iter, tovec.bv_len); - } -} - -static void bounce_end_io(struct bio *bio) -{ - struct bio *bio_orig = bio->bi_private; - struct bio_vec *bvec, orig_vec; - struct bvec_iter orig_iter = bio_orig->bi_iter; - struct bvec_iter_all iter_all; - - /* - * free up bounce indirect pages used - */ - bio_for_each_segment_all(bvec, bio, iter_all) { - orig_vec = bio_iter_iovec(bio_orig, orig_iter); - if (bvec->bv_page != orig_vec.bv_page) { - dec_zone_page_state(bvec->bv_page, NR_BOUNCE); - mempool_free(bvec->bv_page, &page_pool); - } - bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len); - } - - bio_orig->bi_status = bio->bi_status; - bio_endio(bio_orig); - bio_put(bio); -} - -static void bounce_end_io_write(struct bio *bio) -{ - bounce_end_io(bio); -} - -static void bounce_end_io_read(struct bio *bio) -{ - struct bio *bio_orig = bio->bi_private; - - if (!bio->bi_status) - copy_to_high_bio_irq(bio_orig, bio); - - bounce_end_io(bio); -} - -static struct bio *bounce_clone_bio(struct bio *bio_src) -{ - struct bvec_iter iter; - struct bio_vec bv; - struct bio *bio; - - /* - * Pre immutable biovecs, __bio_clone() used to just do a memcpy from - * bio_src->bi_io_vec to bio->bi_io_vec. - * - * We can't do that anymore, because: - * - * - The point of cloning the biovec is to produce a bio with a biovec - * the caller can modify: bi_idx and bi_bvec_done should be 0. - * - * - The original bio could've had more than BIO_MAX_VECS biovecs; if - * we tried to clone the whole thing bio_alloc_bioset() would fail. - * But the clone should succeed as long as the number of biovecs we - * actually need to allocate is fewer than BIO_MAX_VECS. - * - * - Lastly, bi_vcnt should not be looked at or relied upon by code - * that does not own the bio - reason being drivers don't use it for - * iterating over the biovec anymore, so expecting it to be kept up - * to date (i.e. for clones that share the parent biovec) is just - * asking for trouble and would force extra work. - */ - bio = bio_alloc_bioset(bio_src->bi_bdev, bio_segments(bio_src), - bio_src->bi_opf, GFP_NOIO, &bounce_bio_set); - if (bio_flagged(bio_src, BIO_REMAPPED)) - bio_set_flag(bio, BIO_REMAPPED); - bio->bi_ioprio = bio_src->bi_ioprio; - bio->bi_write_hint = bio_src->bi_write_hint; - bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; - bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_ZEROES: - break; - default: - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - break; - } - - if (bio_crypt_clone(bio, bio_src, GFP_NOIO) < 0) - goto err_put; - - if (bio_integrity(bio_src) && - bio_integrity_clone(bio, bio_src, GFP_NOIO) < 0) - goto err_put; - - bio_clone_blkg_association(bio, bio_src); - - return bio; - -err_put: - bio_put(bio); - return NULL; -} - -struct bio *__blk_queue_bounce(struct bio *bio_orig, struct request_queue *q) -{ - struct bio *bio; - int rw = bio_data_dir(bio_orig); - struct bio_vec *to, from; - struct bvec_iter iter; - unsigned i = 0, bytes = 0; - bool bounce = false; - int sectors; - - bio_for_each_segment(from, bio_orig, iter) { - if (i++ < BIO_MAX_VECS) - bytes += from.bv_len; - if (PageHighMem(from.bv_page)) - bounce = true; - } - if (!bounce) - return bio_orig; - - /* - * Individual bvecs might not be logical block aligned. Round down - * the split size so that each bio is properly block size aligned, - * even if we do not use the full hardware limits. - */ - sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >> - SECTOR_SHIFT; - if (sectors < bio_sectors(bio_orig)) { - bio = bio_split(bio_orig, sectors, GFP_NOIO, &bounce_bio_split); - bio_chain(bio, bio_orig); - submit_bio_noacct(bio_orig); - bio_orig = bio; - } - bio = bounce_clone_bio(bio_orig); - - /* - * Bvec table can't be updated by bio_for_each_segment_all(), - * so retrieve bvec from the table directly. This way is safe - * because the 'bio' is single-page bvec. - */ - for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) { - struct page *bounce_page; - - if (!PageHighMem(to->bv_page)) - continue; - - bounce_page = mempool_alloc(&page_pool, GFP_NOIO); - inc_zone_page_state(bounce_page, NR_BOUNCE); - - if (rw == WRITE) { - flush_dcache_page(to->bv_page); - memcpy_from_bvec(page_address(bounce_page), to); - } - to->bv_page = bounce_page; - } - - trace_block_bio_bounce(bio_orig); - - bio->bi_flags |= (1 << BIO_BOUNCED); - - if (rw == READ) - bio->bi_end_io = bounce_end_io_read; - else - bio->bi_end_io = bounce_end_io_write; - - bio->bi_private = bio_orig; - return bio; -} diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dce7615c35e7..5a46067e85b1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -286,7 +286,6 @@ struct bio { enum { BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ - BIO_BOUNCED, /* bio is a bounce bio */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3d74f9dae8e..5ccb961ee2ae 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -331,9 +331,6 @@ typedef unsigned int __bitwise blk_features_t; /* skip this queue in blk_mq_(un)quiesce_tagset */ #define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) -/* bounce all highmem pages */ -#define BLK_FEAT_BOUNCE_HIGH ((__force blk_features_t)(1u << 14)) - /* undocumented magic for bcache */ #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ ((__force blk_features_t)(1u << 15)) @@ -347,7 +344,7 @@ typedef unsigned int __bitwise blk_features_t; */ #define BLK_FEAT_INHERIT_MASK \ (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ - BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \ + BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \ BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) /* internal flags in queue_limits.flags */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index bd0ea07338eb..ad36e73b8579 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -360,21 +360,6 @@ DECLARE_EVENT_CLASS(block_bio, __entry->nr_sector, __entry->comm) ); -/** - * block_bio_bounce - used bounce buffer when processing block operation - * @bio: block operation - * - * A bounce buffer was used to handle the block operation @bio in @q. - * This occurs when hardware limitations prevent a direct transfer of - * data between the @bio data memory area and the IO device. Use of a - * bounce buffer requires extra copying of data and decreases - * performance. - */ -DEFINE_EVENT(block_bio, block_bio_bounce, - TP_PROTO(struct bio *bio), - TP_ARGS(bio) -); - /** * block_bio_backmerge - merging block operation to the end of an existing operation * @bio: new block operation to merge diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 690621b610e5..1bfb635e309b 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -49,7 +49,7 @@ enum blktrace_act { __BLK_TA_UNPLUG_TIMER, /* queue was unplugged by timer */ __BLK_TA_INSERT, /* insert request */ __BLK_TA_SPLIT, /* bio was split */ - __BLK_TA_BOUNCE, /* bio was bounced */ + __BLK_TA_BOUNCE, /* unused, was: bio was bounced */ __BLK_TA_REMAP, /* bio was remapped */ __BLK_TA_ABORT, /* request aborted */ __BLK_TA_DRV_DATA, /* driver-specific binary data */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3679a6d18934..d5f36f415d9d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -893,11 +893,6 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, rcu_read_unlock(); } -static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio) -{ - blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BOUNCE, 0); -} - static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio) { @@ -1089,8 +1084,6 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); WARN_ON(ret); - ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); - WARN_ON(ret); ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); @@ -1125,7 +1118,6 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); - unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); @@ -1462,7 +1454,6 @@ static const struct { [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, - [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, }; -- cgit v1.2.3 From 02040353f4fedb823f011f27962325f328d0689f Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 6 May 2025 17:47:27 +0530 Subject: io_uring: enable per-io write streams Allow userspace to pass a per-I/O write stream in the SQE: __u8 write_stream; The __u8 type matches the size the filesystems and block layer support. Application can query the supported values from the block devices max_write_streams sysfs attribute. Unsupported values are ignored by file operations that do not support write streams or rejected with an error by those that support them. Reviewed-by: Hannes Reinecke Reviewed-by: Nitesh Shetty Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Kanchan Joshi Link: https://lore.kernel.org/r/20250506121732.8211-7-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 ++++ io_uring/io_uring.c | 2 ++ io_uring/rw.c | 1 + 3 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8f1fc12bac46..50e372ea97c5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -93,6 +93,10 @@ struct io_uring_sqe { __u16 addr_len; __u16 __pad3[1]; }; + struct { + __u8 write_stream; + __u8 __pad4[3]; + }; }; union { struct { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index c6209fe44cb1..479205df3485 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3919,6 +3919,8 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); BUILD_BUG_SQE_ELEM(44, __u16, addr_len); + BUILD_BUG_SQE_ELEM(44, __u8, write_stream); + BUILD_BUG_SQE_ELEM(45, __u8, __pad4[0]); BUILD_BUG_SQE_ELEM(46, __u16, __pad3[0]); BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd); diff --git a/io_uring/rw.c b/io_uring/rw.c index 039e063f7091..b8389674a747 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -276,6 +276,7 @@ static int __io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, } rw->kiocb.dio_complete = NULL; rw->kiocb.ki_flags = 0; + rw->kiocb.ki_write_stream = READ_ONCE(sqe->write_stream); if (req->ctx->flags & IORING_SETUP_IOPOLL) rw->kiocb.ki_complete = io_complete_rw_iopoll; -- cgit v1.2.3 From a5c98e9424573649e59988199a3356a79c9e1fd9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 1 May 2025 13:17:18 +0100 Subject: io_uring/zcrx: dmabuf backed zerocopy receive Add support for dmabuf backed zcrx areas. To use it, the user should pass IORING_ZCRX_AREA_DMABUF in the struct io_uring_zcrx_area_reg flags field and pass a dmabuf fd in the dmabuf_fd field. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/20bb1890e60a82ec945ab36370d1fd54be414ab6.1746097431.git.asml.silence@gmail.com Link: https://lore.kernel.org/io-uring/6e37db97303212bbd8955f9501cf99b579f8aece.1746547722.git.asml.silence@gmail.com [axboe: fold in fixup] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +- io_uring/zcrx.c | 163 +++++++++++++++++++++++++++++++++++++----- io_uring/zcrx.h | 7 ++ 3 files changed, 159 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 130f3bc71a69..5ce096090b0c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -990,12 +990,16 @@ struct io_uring_zcrx_offsets { __u64 __resv[2]; }; +enum io_uring_zcrx_area_flags { + IORING_ZCRX_AREA_DMABUF = 1, +}; + struct io_uring_zcrx_area_reg { __u64 addr; __u64 len; __u64 rq_area_token; __u32 flags; - __u32 __resv1; + __u32 dmabuf_fd; __u64 __resv2[2]; }; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 34b09beba992..9a568d049204 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -47,30 +47,118 @@ static inline struct page *io_zcrx_iov_page(const struct net_iov *niov) return area->mem.pages[net_iov_idx(niov)]; } -static void io_release_area_mem(struct io_zcrx_mem *mem) +static void io_release_dmabuf(struct io_zcrx_mem *mem) { - if (mem->pages) { - unpin_user_pages(mem->pages, mem->nr_folios); - kvfree(mem->pages); + if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) + return; + + if (mem->sgt) + dma_buf_unmap_attachment_unlocked(mem->attach, mem->sgt, + DMA_FROM_DEVICE); + if (mem->attach) + dma_buf_detach(mem->dmabuf, mem->attach); + if (mem->dmabuf) + dma_buf_put(mem->dmabuf); + + mem->sgt = NULL; + mem->attach = NULL; + mem->dmabuf = NULL; +} + +static int io_import_dmabuf(struct io_zcrx_ifq *ifq, + struct io_zcrx_mem *mem, + struct io_uring_zcrx_area_reg *area_reg) +{ + unsigned long off = (unsigned long)area_reg->addr; + unsigned long len = (unsigned long)area_reg->len; + unsigned long total_size = 0; + struct scatterlist *sg; + int dmabuf_fd = area_reg->dmabuf_fd; + int i, ret; + + if (WARN_ON_ONCE(!ifq->dev)) + return -EFAULT; + if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) + return -EINVAL; + + mem->is_dmabuf = true; + mem->dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(mem->dmabuf)) { + ret = PTR_ERR(mem->dmabuf); + mem->dmabuf = NULL; + goto err; } + + mem->attach = dma_buf_attach(mem->dmabuf, ifq->dev); + if (IS_ERR(mem->attach)) { + ret = PTR_ERR(mem->attach); + mem->attach = NULL; + goto err; + } + + mem->sgt = dma_buf_map_attachment_unlocked(mem->attach, DMA_FROM_DEVICE); + if (IS_ERR(mem->sgt)) { + ret = PTR_ERR(mem->sgt); + mem->sgt = NULL; + goto err; + } + + for_each_sgtable_dma_sg(mem->sgt, sg, i) + total_size += sg_dma_len(sg); + + if (total_size < off + len) + return -EINVAL; + + mem->dmabuf_offset = off; + mem->size = len; + return 0; +err: + io_release_dmabuf(mem); + return ret; } -static int io_import_area(struct io_zcrx_ifq *ifq, +static int io_zcrx_map_area_dmabuf(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) +{ + unsigned long off = area->mem.dmabuf_offset; + struct scatterlist *sg; + unsigned i, niov_idx = 0; + + if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) + return -EINVAL; + + for_each_sgtable_dma_sg(area->mem.sgt, sg, i) { + dma_addr_t dma = sg_dma_address(sg); + unsigned long sg_len = sg_dma_len(sg); + unsigned long sg_off = min(sg_len, off); + + off -= sg_off; + sg_len -= sg_off; + dma += sg_off; + + while (sg_len && niov_idx < area->nia.num_niovs) { + struct net_iov *niov = &area->nia.niovs[niov_idx]; + + if (net_mp_niov_set_dma_addr(niov, dma)) + return 0; + sg_len -= PAGE_SIZE; + dma += PAGE_SIZE; + niov_idx++; + } + } + return niov_idx; +} + +static int io_import_umem(struct io_zcrx_ifq *ifq, struct io_zcrx_mem *mem, struct io_uring_zcrx_area_reg *area_reg) { struct page **pages; int nr_pages; - int ret; - ret = io_validate_user_buf_range(area_reg->addr, area_reg->len); - if (ret) - return ret; + if (area_reg->dmabuf_fd) + return -EINVAL; if (!area_reg->addr) return -EFAULT; - if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK) - return -EINVAL; - pages = io_pin_pages((unsigned long)area_reg->addr, area_reg->len, &nr_pages); if (IS_ERR(pages)) @@ -82,6 +170,35 @@ static int io_import_area(struct io_zcrx_ifq *ifq, return 0; } +static void io_release_area_mem(struct io_zcrx_mem *mem) +{ + if (mem->is_dmabuf) { + io_release_dmabuf(mem); + return; + } + if (mem->pages) { + unpin_user_pages(mem->pages, mem->nr_folios); + kvfree(mem->pages); + } +} + +static int io_import_area(struct io_zcrx_ifq *ifq, + struct io_zcrx_mem *mem, + struct io_uring_zcrx_area_reg *area_reg) +{ + int ret; + + ret = io_validate_user_buf_range(area_reg->addr, area_reg->len); + if (ret) + return ret; + if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK) + return -EINVAL; + + if (area_reg->flags & IORING_ZCRX_AREA_DMABUF) + return io_import_dmabuf(ifq, mem, area_reg); + return io_import_umem(ifq, mem, area_reg); +} + static void io_zcrx_unmap_umem(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area, int nr_mapped) { @@ -101,7 +218,10 @@ static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, { int i; - io_zcrx_unmap_umem(ifq, area, nr_mapped); + if (area->mem.is_dmabuf) + io_release_dmabuf(&area->mem); + else + io_zcrx_unmap_umem(ifq, area, nr_mapped); for (i = 0; i < area->nia.num_niovs; i++) net_mp_niov_set_dma_addr(&area->nia.niovs[i], 0); @@ -145,7 +265,11 @@ static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) if (area->is_mapped) return 0; - nr = io_zcrx_map_area_umem(ifq, area); + if (area->mem.is_dmabuf) + nr = io_zcrx_map_area_dmabuf(ifq, area); + else + nr = io_zcrx_map_area_umem(ifq, area); + if (nr != area->nia.num_niovs) { __io_zcrx_unmap_area(ifq, area, nr); return -EINVAL; @@ -251,6 +375,8 @@ static void io_zcrx_free_area(struct io_zcrx_area *area) kfree(area); } +#define IO_ZCRX_AREA_SUPPORTED_FLAGS (IORING_ZCRX_AREA_DMABUF) + static int io_zcrx_create_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area **res, struct io_uring_zcrx_area_reg *area_reg) @@ -259,9 +385,11 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq, unsigned nr_iovs; int i, ret; - if (area_reg->flags || area_reg->rq_area_token) + if (area_reg->flags & ~IO_ZCRX_AREA_SUPPORTED_FLAGS) + return -EINVAL; + if (area_reg->rq_area_token) return -EINVAL; - if (area_reg->__resv1 || area_reg->__resv2[0] || area_reg->__resv2[1]) + if (area_reg->__resv2[0] || area_reg->__resv2[1]) return -EINVAL; ret = -ENOMEM; @@ -819,6 +947,9 @@ static ssize_t io_zcrx_copy_chunk(struct io_kiocb *req, struct io_zcrx_ifq *ifq, size_t copied = 0; int ret = 0; + if (area->mem.is_dmabuf) + return -EFAULT; + while (len) { size_t copy_size = min_t(size_t, PAGE_SIZE, len); const int dst_off = 0; diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h index 9c22807af807..2f5e26389f22 100644 --- a/io_uring/zcrx.h +++ b/io_uring/zcrx.h @@ -3,15 +3,22 @@ #define IOU_ZC_RX_H #include +#include #include #include #include struct io_zcrx_mem { unsigned long size; + bool is_dmabuf; struct page **pages; unsigned long nr_folios; + + struct dma_buf_attachment *attach; + struct dma_buf *dmabuf; + struct sg_table *sgt; + unsigned long dmabuf_offset; }; struct io_zcrx_area { -- cgit v1.2.3 From 429ac6211494c12b668dac59811ea8a96db6d757 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 5 May 2025 13:45:11 +0200 Subject: devlink: define enum for attr types of dynamic attributes Devlink param and health reporter fmsg use attributes with dynamic type which is determined according to a different type. Currently used values are NLA_*. The problem is, they are not part of UAPI. They may change which would cause a break. To make this future safe, introduce a enum that shadows NLA_* values in it and is part of UAPI. Also, this allows to possibly carry types that are unrelated to NLA_* values. Signed-off-by: Saeed Mahameed Signed-off-by: Jiri Pirko Link: https://patch.msgid.link/20250505114513.53370-3-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/devlink.yaml | 24 ++++++++++++++++++++++++ include/uapi/linux/devlink.h | 15 +++++++++++++++ net/devlink/health.c | 17 +++++++++++++++-- net/devlink/netlink_gen.c | 29 ++++++++++++++++++++++++++++- net/devlink/param.c | 30 +++++++++++++++--------------- 5 files changed, 97 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index bd9726269b4f..05fee1b7fe19 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -202,6 +202,28 @@ definitions: name: exception - name: control + - + type: enum + name: var-attr-type + entries: + - + name: u8 + value: 1 + - + name: u16 + - + name: u32 + - + name: u64 + - + name: string + - + name: flag + - + name: nul_string + value: 10 + - + name: binary attribute-sets: - @@ -498,6 +520,7 @@ attribute-sets: - name: param-type type: u8 + enum: var-attr-type # TODO: fill in the attributes in between @@ -592,6 +615,7 @@ attribute-sets: - name: fmsg-obj-value-type type: u8 + enum: var-attr-type # TODO: fill in the attributes in between diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 9401aa343673..a5ee0f13740a 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -385,6 +385,21 @@ enum devlink_linecard_state { DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1 }; +/* Variable attribute type. */ +enum devlink_var_attr_type { + /* Following values relate to the internal NLA_* values */ + DEVLINK_VAR_ATTR_TYPE_U8 = 1, + DEVLINK_VAR_ATTR_TYPE_U16, + DEVLINK_VAR_ATTR_TYPE_U32, + DEVLINK_VAR_ATTR_TYPE_U64, + DEVLINK_VAR_ATTR_TYPE_STRING, + DEVLINK_VAR_ATTR_TYPE_FLAG, + DEVLINK_VAR_ATTR_TYPE_NUL_STRING = 10, + DEVLINK_VAR_ATTR_TYPE_BINARY, + __DEVLINK_VAR_ATTR_TYPE_CUSTOM_BASE = 0x80, + /* Any possible custom types, unrelated to NLA_* values go below */ +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, diff --git a/net/devlink/health.c b/net/devlink/health.c index 57db6799722a..95a7a62d85a2 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -930,18 +930,31 @@ EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); static int devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) { + enum devlink_var_attr_type var_attr_type; + switch (msg->nla_type) { case NLA_FLAG: + var_attr_type = DEVLINK_VAR_ATTR_TYPE_FLAG; + break; case NLA_U8: + var_attr_type = DEVLINK_VAR_ATTR_TYPE_U8; + break; case NLA_U32: + var_attr_type = DEVLINK_VAR_ATTR_TYPE_U32; + break; case NLA_U64: + var_attr_type = DEVLINK_VAR_ATTR_TYPE_U64; + break; case NLA_NUL_STRING: + var_attr_type = DEVLINK_VAR_ATTR_TYPE_NUL_STRING; + break; case NLA_BINARY: - return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, - msg->nla_type); + var_attr_type = DEVLINK_VAR_ATTR_TYPE_BINARY; + break; default: return -EINVAL; } + return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, var_attr_type); } static int diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index f9786d51f68f..e340d955cf3b 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -10,6 +10,33 @@ #include +/* Sparse enums validation callbacks */ +static int +devlink_attr_param_type_validate(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + switch (nla_get_u8(attr)) { + case DEVLINK_VAR_ATTR_TYPE_U8: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_U16: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_U32: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_U64: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_STRING: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_FLAG: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_NUL_STRING: + fallthrough; + case DEVLINK_VAR_ATTR_TYPE_BINARY: + return 0; + } + NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value"); + return -EINVAL; +} + /* Common nested types */ const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, }, @@ -273,7 +300,7 @@ static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VA [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, }, - [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8, }, + [DEVLINK_ATTR_PARAM_TYPE] = NLA_POLICY_VALIDATE_FN(NLA_U8, &devlink_attr_param_type_validate), [DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2), }; diff --git a/net/devlink/param.c b/net/devlink/param.c index dcf0d1ccebba..d0fb7c88bdb8 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -167,19 +167,19 @@ static int devlink_param_set(struct devlink *devlink, } static int -devlink_param_type_to_nla_type(enum devlink_param_type param_type) +devlink_param_type_to_var_attr_type(enum devlink_param_type param_type) { switch (param_type) { case DEVLINK_PARAM_TYPE_U8: - return NLA_U8; + return DEVLINK_VAR_ATTR_TYPE_U8; case DEVLINK_PARAM_TYPE_U16: - return NLA_U16; + return DEVLINK_VAR_ATTR_TYPE_U16; case DEVLINK_PARAM_TYPE_U32: - return NLA_U32; + return DEVLINK_VAR_ATTR_TYPE_U32; case DEVLINK_PARAM_TYPE_STRING: - return NLA_STRING; + return DEVLINK_VAR_ATTR_TYPE_STRING; case DEVLINK_PARAM_TYPE_BOOL: - return NLA_FLAG; + return DEVLINK_VAR_ATTR_TYPE_FLAG; default: return -EINVAL; } @@ -247,7 +247,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_param_gset_ctx ctx; struct nlattr *param_values_list; struct nlattr *param_attr; - int nla_type; + int var_attr_type; void *hdr; int err; int i; @@ -294,10 +294,10 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC)) goto param_nest_cancel; - nla_type = devlink_param_type_to_nla_type(param->type); - if (nla_type < 0) + var_attr_type = devlink_param_type_to_var_attr_type(param->type); + if (var_attr_type < 0) goto param_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type)) + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, var_attr_type)) goto param_nest_cancel; param_values_list = nla_nest_start_noflag(msg, @@ -420,19 +420,19 @@ devlink_param_type_get_from_info(struct genl_info *info, return -EINVAL; switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) { - case NLA_U8: + case DEVLINK_VAR_ATTR_TYPE_U8: *param_type = DEVLINK_PARAM_TYPE_U8; break; - case NLA_U16: + case DEVLINK_VAR_ATTR_TYPE_U16: *param_type = DEVLINK_PARAM_TYPE_U16; break; - case NLA_U32: + case DEVLINK_VAR_ATTR_TYPE_U32: *param_type = DEVLINK_PARAM_TYPE_U32; break; - case NLA_STRING: + case DEVLINK_VAR_ATTR_TYPE_STRING: *param_type = DEVLINK_PARAM_TYPE_STRING; break; - case NLA_FLAG: + case DEVLINK_VAR_ATTR_TYPE_FLAG: *param_type = DEVLINK_PARAM_TYPE_BOOL; break; default: -- cgit v1.2.3 From 5d894321c49e61379189b0ff605f316e39cbd1e9 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 7 May 2025 14:18:21 -0700 Subject: fs: add atomic write unit max opt to statx XFS will be able to support large atomic writes (atomic write > 1x block) in future. This will be achieved by using different operating methods, depending on the size of the write. Specifically a new method of operation based in FS atomic extent remapping will be supported in addition to the current HW offload-based method. The FS method will generally be appreciably slower performing than the HW-offload method. However the FS method will be typically able to contribute to achieving a larger atomic write unit max limit. XFS will support a hybrid mode, where HW offload method will be used when possible, i.e. HW offload is used when the length of the write is supported, and for other times FS-based atomic writes will be used. As such, there is an atomic write length at which the user may experience appreciably slower performance. Advertise this limit in a new statx field, stx_atomic_write_unit_max_opt. When zero, it means that there is no such performance boundary. Masks STATX{_ATTR}_WRITE_ATOMIC can be used to get this new field. This is ok for older kernels which don't support this new field, as they would report 0 in this field (from zeroing in cp_statx()) already. Furthermore those older kernels don't support large atomic writes - apart from block fops, but there would be consistent performance there for atomic writes in range [unit min, unit max]. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong Acked-by: Darrick J. Wong Signed-off-by: John Garry --- block/bdev.c | 3 ++- fs/ext4/inode.c | 2 +- fs/stat.c | 6 +++++- fs/xfs/xfs_iops.c | 2 +- include/linux/fs.h | 3 ++- include/linux/stat.h | 1 + include/uapi/linux/stat.h | 8 ++++++-- 7 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/block/bdev.c b/block/bdev.c index 520515e4e64e..9f321fb94bac 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -1336,7 +1336,8 @@ void bdev_statx(struct path *path, struct kstat *stat, generic_fill_statx_atomic_writes(stat, queue_atomic_write_unit_min_bytes(bd_queue), - queue_atomic_write_unit_max_bytes(bd_queue)); + queue_atomic_write_unit_max_bytes(bd_queue), + 0); } stat->blksize = bdev_io_min(bdev); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 94c7d2d828a6..cdf01e60fa6d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5692,7 +5692,7 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path, awu_max = sbi->s_awu_max; } - generic_fill_statx_atomic_writes(stat, awu_min, awu_max); + generic_fill_statx_atomic_writes(stat, awu_min, awu_max, 0); } flags = ei->i_flags & EXT4_FL_USER_VISIBLE; diff --git a/fs/stat.c b/fs/stat.c index f13308bfdc98..c41855f62d22 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -136,13 +136,15 @@ EXPORT_SYMBOL(generic_fill_statx_attr); * @stat: Where to fill in the attribute flags * @unit_min: Minimum supported atomic write length in bytes * @unit_max: Maximum supported atomic write length in bytes + * @unit_max_opt: Optimised maximum supported atomic write length in bytes * * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from * atomic write unit_min and unit_max values. */ void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, - unsigned int unit_max) + unsigned int unit_max, + unsigned int unit_max_opt) { /* Confirm that the request type is known */ stat->result_mask |= STATX_WRITE_ATOMIC; @@ -153,6 +155,7 @@ void generic_fill_statx_atomic_writes(struct kstat *stat, if (unit_min) { stat->atomic_write_unit_min = unit_min; stat->atomic_write_unit_max = unit_max; + stat->atomic_write_unit_max_opt = unit_max_opt; /* Initially only allow 1x segment */ stat->atomic_write_segments_max = 1; @@ -732,6 +735,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; + tmp.stx_atomic_write_unit_max_opt = stat->atomic_write_unit_max_opt; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 756bd3ca8e00..f0e5d83195df 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -610,7 +610,7 @@ xfs_report_atomic_write( if (xfs_inode_can_atomicwrite(ip)) unit_min = unit_max = ip->i_mount->m_sb.sb_blocksize; - generic_fill_statx_atomic_writes(stat, unit_min, unit_max); + generic_fill_statx_atomic_writes(stat, unit_min, unit_max, 0); } STATIC int diff --git a/include/linux/fs.h b/include/linux/fs.h index 016b0fe1536e..7b19d8f99aff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3475,7 +3475,8 @@ void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, - unsigned int unit_max); + unsigned int unit_max, + unsigned int unit_max_opt); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); diff --git a/include/linux/stat.h b/include/linux/stat.h index be7496a6a0dd..e3d00e7bb26d 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -57,6 +57,7 @@ struct kstat { u32 dio_read_offset_align; u32 atomic_write_unit_min; u32 atomic_write_unit_max; + u32 atomic_write_unit_max_opt; u32 atomic_write_segments_max; }; diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index f78ee3670dd5..1686861aae20 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -182,8 +182,12 @@ struct statx { /* File offset alignment for direct I/O reads */ __u32 stx_dio_read_offset_align; - /* 0xb8 */ - __u64 __spare3[9]; /* Spare space for future expansion */ + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ /* 0x100 */ }; -- cgit v1.2.3 From d6644d737bec473a38dbd44a71553cacd636a920 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 6 May 2025 09:35:30 -0700 Subject: platform/x86: ISST: Support SST-PP revision 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SST PP revision 2 added fabric 1 P0, P1 and Pm frequencies. Export them by using a new IOCTL ISST_IF_GET_PERF_LEVEL_FABRIC_INFO. This IOCTL requires platforms with SST PP revision 2 or higher. To accommodate potential future increases in fabric count and avoid ABI changes, support is extended for up to 8 fabrics. Signed-off-by: Srinivas Pandruvada Link: https://lore.kernel.org/r/20250506163531.1061185-3-srinivas.pandruvada@linux.intel.com Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- .../x86/intel/speed_select_if/isst_tpmi_core.c | 66 ++++++++++++++++++++++ include/uapi/linux/isst_if.h | 26 +++++++++ 2 files changed, 92 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index a52fc2f5ea89..f56bb63f7947 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -1016,6 +1016,7 @@ static int isst_if_set_perf_feature(void __user *argp) #define SST_PP_INFO_10_OFFSET 80 #define SST_PP_INFO_11_OFFSET 88 +#define SST_PP_INFO_12_OFFSET 96 #define SST_PP_P1_SSE_START 0 #define SST_PP_P1_SSE_WIDTH 8 @@ -1068,6 +1069,15 @@ static int isst_if_set_perf_feature(void __user *argp) #define SST_PP_CORE_RATIO_PM_FABRIC_START 48 #define SST_PP_CORE_RATIO_PM_FABRIC_WIDTH 8 +#define SST_PP_CORE_RATIO_P0_FABRIC_1_START 0 +#define SST_PP_CORE_RATIO_P0_FABRIC_1_WIDTH 8 + +#define SST_PP_CORE_RATIO_P1_FABRIC_1_START 8 +#define SST_PP_CORE_RATIO_P1_FABRIC_1_WIDTH 8 + +#define SST_PP_CORE_RATIO_PM_FABRIC_1_START 16 +#define SST_PP_CORE_RATIO_PM_FABRIC_1_WIDTH 8 + static int isst_if_get_perf_level_info(void __user *argp) { struct isst_perf_level_data_info perf_level; @@ -1167,6 +1177,59 @@ static int isst_if_get_perf_level_info(void __user *argp) return 0; } +static int isst_if_get_perf_level_fabric_info(void __user *argp) +{ + struct isst_perf_level_fabric_info perf_level_fabric; + struct tpmi_per_power_domain_info *power_domain_info; + int start = SST_PP_CORE_RATIO_P0_FABRIC_START; + int width = SST_PP_CORE_RATIO_P0_FABRIC_WIDTH; + int offset = SST_PP_INFO_11_OFFSET; + int i; + + if (copy_from_user(&perf_level_fabric, argp, sizeof(perf_level_fabric))) + return -EFAULT; + + power_domain_info = get_instance(perf_level_fabric.socket_id, + perf_level_fabric.power_domain_id); + if (!power_domain_info) + return -EINVAL; + + if (perf_level_fabric.level > power_domain_info->max_level) + return -EINVAL; + + if (power_domain_info->pp_header.feature_rev < 2) + return -EINVAL; + + if (!(power_domain_info->pp_header.level_en_mask & BIT(perf_level_fabric.level))) + return -EINVAL; + + /* For revision 2, maximum number of fabrics is 2 */ + perf_level_fabric.max_fabrics = 2; + + for (i = 0; i < perf_level_fabric.max_fabrics; i++) { + _read_pp_level_info("p0_fabric_freq_mhz", perf_level_fabric.p0_fabric_freq_mhz[i], + perf_level_fabric.level, offset, start, width, + SST_MUL_FACTOR_FREQ) + start += width; + + _read_pp_level_info("p1_fabric_freq_mhz", perf_level_fabric.p1_fabric_freq_mhz[i], + perf_level_fabric.level, offset, start, width, + SST_MUL_FACTOR_FREQ) + start += width; + + _read_pp_level_info("pm_fabric_freq_mhz", perf_level_fabric.pm_fabric_freq_mhz[i], + perf_level_fabric.level, offset, start, width, + SST_MUL_FACTOR_FREQ) + offset = SST_PP_INFO_12_OFFSET; + start = SST_PP_CORE_RATIO_P0_FABRIC_1_START; + } + + if (copy_to_user(argp, &perf_level_fabric, sizeof(perf_level_fabric))) + return -EFAULT; + + return 0; +} + #define SST_PP_FUSED_CORE_COUNT_START 0 #define SST_PP_FUSED_CORE_COUNT_WIDTH 8 @@ -1453,6 +1516,9 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd, case ISST_IF_GET_PERF_LEVEL_INFO: ret = isst_if_get_perf_level_info(argp); break; + case ISST_IF_GET_PERF_LEVEL_FABRIC_INFO: + ret = isst_if_get_perf_level_fabric_info(argp); + break; case ISST_IF_GET_PERF_LEVEL_CPU_MASK: ret = isst_if_get_perf_level_mask(argp); break; diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index 0df1a1c3caf4..8197a4800604 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -375,6 +375,30 @@ struct isst_perf_level_data_info { __u16 trl_freq_mhz[TRL_MAX_LEVELS][TRL_MAX_BUCKETS]; }; +#define MAX_FABRIC_COUNT 8 + +/** + * struct isst_perf_level_fabric_info - Structure to get SST-PP fabric details + * @socket_id: Socket/package id + * @power_domain_id: Power Domain id + * @level: SST-PP level for which caller wants to get information + * @max_fabrics: Count of fabrics in resonse + * @p0_fabric_freq_mhz: Fabric (Uncore) maximum frequency + * @p1_fabric_freq_mhz: Fabric (Uncore) TDP frequency + * @pm_fabric_freq_mhz: Fabric (Uncore) minimum frequency + * + * Structure used to get information on frequencies for fabrics. + */ +struct isst_perf_level_fabric_info { + __u8 socket_id; + __u8 power_domain_id; + __u16 level; + __u16 max_fabrics; + __u16 p0_fabric_freq_mhz[MAX_FABRIC_COUNT]; + __u16 p1_fabric_freq_mhz[MAX_FABRIC_COUNT]; + __u16 pm_fabric_freq_mhz[MAX_FABRIC_COUNT]; +}; + /** * struct isst_perf_level_cpu_mask - Structure to get SST-PP level CPU mask * @socket_id: Socket/package id @@ -471,5 +495,7 @@ struct isst_turbo_freq_info { #define ISST_IF_GET_BASE_FREQ_INFO _IOR(ISST_IF_MAGIC, 14, struct isst_base_freq_info *) #define ISST_IF_GET_BASE_FREQ_CPU_MASK _IOR(ISST_IF_MAGIC, 15, struct isst_perf_level_cpu_mask *) #define ISST_IF_GET_TURBO_FREQ_INFO _IOR(ISST_IF_MAGIC, 16, struct isst_turbo_freq_info *) +#define ISST_IF_GET_PERF_LEVEL_FABRIC_INFO _IOR(ISST_IF_MAGIC, 17,\ + struct isst_perf_level_fabric_info *) #endif -- cgit v1.2.3 From a3aa115af25473c1309bc99cac6b2b6cd180fdd9 Mon Sep 17 00:00:00 2001 From: Keke Li Date: Sun, 27 Apr 2025 14:27:14 +0800 Subject: media: Add C3ISP_PARAMS and C3ISP_STATS meta formats C3ISP_PARAMS is the C3 ISP Parameters format. C3ISP_STATS is the C3 ISP Statistics format. Reviewed-by: Daniel Scally Reviewed-by: Jacopo Mondi Signed-off-by: Keke Li Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- drivers/media/v4l2-core/v4l2-ioctl.c | 2 ++ include/uapi/linux/videodev2.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 78f217768ae7..650dc1956f73 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1464,6 +1464,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_META_FMT_RK_ISP1_PARAMS: descr = "Rockchip ISP1 3A Parameters"; break; case V4L2_META_FMT_RK_ISP1_STAT_3A: descr = "Rockchip ISP1 3A Statistics"; break; case V4L2_META_FMT_RK_ISP1_EXT_PARAMS: descr = "Rockchip ISP1 Ext 3A Params"; break; + case V4L2_META_FMT_C3ISP_PARAMS: descr = "Amlogic C3 ISP Parameters"; break; + case V4L2_META_FMT_C3ISP_STATS: descr = "Amlogic C3 ISP Statistics"; break; case V4L2_PIX_FMT_NV12_8L128: descr = "NV12 (8x128 Linear)"; break; case V4L2_PIX_FMT_NV12M_8L128: descr = "NV12M (8x128 Linear)"; break; case V4L2_PIX_FMT_NV12_10BE_8L128: descr = "10-bit NV12 (8x128 Linear, BE)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index ca7b3e8863ca..9e3b366d5fc7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -868,6 +868,10 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ #define V4L2_META_FMT_RK_ISP1_EXT_PARAMS v4l2_fourcc('R', 'K', '1', 'E') /* Rockchip ISP1 3a Extensible Parameters */ +/* Vendor specific - used for C3_ISP */ +#define V4L2_META_FMT_C3ISP_PARAMS v4l2_fourcc('C', '3', 'P', 'M') /* Amlogic C3 ISP Parameters */ +#define V4L2_META_FMT_C3ISP_STATS v4l2_fourcc('C', '3', 'S', 'T') /* Amlogic C3 ISP Statistics */ + /* Vendor specific - used for RaspberryPi PiSP */ #define V4L2_META_FMT_RPI_BE_CFG v4l2_fourcc('R', 'P', 'B', 'C') /* PiSP BE configuration */ #define V4L2_META_FMT_RPI_FE_CFG v4l2_fourcc('R', 'P', 'F', 'C') /* PiSP FE configuration */ -- cgit v1.2.3 From 6d406187ebc092ebccf4fb5a1bc16b92c4bc109a Mon Sep 17 00:00:00 2001 From: Keke Li Date: Sun, 27 Apr 2025 14:27:15 +0800 Subject: media: uapi: Add stats info and parameters buffer for C3 ISP Add a header that describes the 3A statistics buffer and the parameters buffer for C3 ISP Reviewed-by: Jacopo Mondi Signed-off-by: Keke Li Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- MAINTAINERS | 1 + include/uapi/linux/media/amlogic/c3-isp-config.h | 564 +++++++++++++++++++++++ 2 files changed, 565 insertions(+) create mode 100644 include/uapi/linux/media/amlogic/c3-isp-config.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 4fe7e0dcd98a..e36c2ceaca79 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1259,6 +1259,7 @@ M: Keke Li L: linux-media@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/media/amlogic,c3-isp.yaml +F: include/uapi/linux/media/amlogic/ AMLOGIC MIPI ADAPTER DRIVER M: Keke Li diff --git a/include/uapi/linux/media/amlogic/c3-isp-config.h b/include/uapi/linux/media/amlogic/c3-isp-config.h new file mode 100644 index 000000000000..ed085ea62a57 --- /dev/null +++ b/include/uapi/linux/media/amlogic/c3-isp-config.h @@ -0,0 +1,564 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2024 Amlogic, Inc. All rights reserved + */ + +#ifndef _UAPI_C3_ISP_CONFIG_H_ +#define _UAPI_C3_ISP_CONFIG_H_ + +#include + +/* + * Frames are split into zones of almost equal width and height - a zone is a + * rectangular tile of a frame. The metering blocks within the ISP collect + * aggregated statistics per zone. + */ +#define C3_ISP_AE_MAX_ZONES (17 * 15) +#define C3_ISP_AF_MAX_ZONES (17 * 15) +#define C3_ISP_AWB_MAX_ZONES (32 * 24) + +/* The maximum number of point on the diagonal of the frame for statistics */ +#define C3_ISP_AE_MAX_PT_NUM 18 +#define C3_ISP_AF_MAX_PT_NUM 18 +#define C3_ISP_AWB_MAX_PT_NUM 33 + +/** + * struct c3_isp_awb_zone_stats - AWB statistics of a zone + * + * AWB zone stats is aligned with 8 bytes + * + * @rg: the ratio of R / G in a zone + * @bg: the ratio of B / G in a zone + * @pixel_sum: the total number of pixels used in a zone + */ +struct c3_isp_awb_zone_stats { + __u16 rg; + __u16 bg; + __u32 pixel_sum; +}; + +/** + * struct c3_isp_awb_stats - Auto white balance statistics information. + * + * AWB statistical information of all zones. + * + * @stats: array of auto white balance statistics + */ +struct c3_isp_awb_stats { + struct c3_isp_awb_zone_stats stats[C3_ISP_AWB_MAX_ZONES]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_ae_zone_stats - AE statistics of a zone + * + * AE zone stats is aligned with 8 bytes. + * This is a 5-bin histogram and the total sum is normalized to 0xffff. + * So hist2 = 0xffff - (hist0 + hist1 + hist3 + hist4) + * + * @hist0: the global normalized pixel count for bin 0 + * @hist1: the global normalized pixel count for bin 1 + * @hist3: the global normalized pixel count for bin 3 + * @hist4: the global normalized pixel count for bin 4 + */ +struct c3_isp_ae_zone_stats { + __u16 hist0; + __u16 hist1; + __u16 hist3; + __u16 hist4; +}; + +/** + * struct c3_isp_ae_stats - Exposure statistics information + * + * AE statistical information consists of all blocks information and a 1024-bin + * histogram. + * + * @stats: array of auto exposure block statistics + * @reserved: undefined buffer space + * @hist: a 1024-bin histogram for the entire image + */ +struct c3_isp_ae_stats { + struct c3_isp_ae_zone_stats stats[C3_ISP_AE_MAX_ZONES]; + __u32 reserved[2]; + __u32 hist[1024]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_af_zone_stats - AF statistics of a zone + * + * AF zone stats is aligned with 8 bytes. + * The zonal accumulated contrast metrics are stored in floating point format + * with 16 bits mantissa and 5 or 6 bits exponent. Apart from contrast metrics + * we accumulate squared image and quartic image data over the zone. + * + * @i2_mat: the mantissa of zonal squared image pixel sum + * @i4_mat: the mantissa of zonal quartic image pixel sum + * @e4_mat: the mantissa of zonal multi-directional quartic edge sum + * @e4_exp: the exponent of zonal multi-directional quartic edge sum + * @i2_exp: the exponent of zonal squared image pixel sum + * @i4_exp: the exponent of zonal quartic image pixel sum + */ +struct c3_isp_af_zone_stats { + __u16 i2_mat; + __u16 i4_mat; + __u16 e4_mat; + __u16 e4_exp : 5; + __u16 i2_exp : 5; + __u16 i4_exp : 6; +}; + +/** + * struct c3_isp_af_stats - Auto Focus statistics information + * + * AF statistical information of each zone + * + * @stats: array of auto focus block statistics + * @reserved: undefined buffer space + */ +struct c3_isp_af_stats { + struct c3_isp_af_zone_stats stats[C3_ISP_AF_MAX_ZONES]; + __u32 reserved[2]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_stats_info - V4L2_META_FMT_C3ISP_STATS + * + * Contains ISP statistics + * + * @awb: auto white balance stats + * @ae: auto exposure stats + * @af: auto focus stats + */ +struct c3_isp_stats_info { + struct c3_isp_awb_stats awb; + struct c3_isp_ae_stats ae; + struct c3_isp_af_stats af; +}; + +/** + * enum c3_isp_params_buffer_version - C3 ISP parameters block versioning + * + * @C3_ISP_PARAMS_BUFFER_V0: First version of C3 ISP parameters block + */ +enum c3_isp_params_buffer_version { + C3_ISP_PARAMS_BUFFER_V0, +}; + +/** + * enum c3_isp_params_block_type - Enumeration of C3 ISP parameter blocks + * + * Each block configures a specific processing block of the C3 ISP. + * The block type allows the driver to correctly interpret the parameters block + * data. + * + * @C3_ISP_PARAMS_BLOCK_AWB_GAINS: White balance gains + * @C3_ISP_PARAMS_BLOCK_AWB_CONFIG: AWB statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_AE_CONFIG: AE statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_AF_CONFIG: AF statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_PST_GAMMA: post gamma parameters + * @C3_ISP_PARAMS_BLOCK_CCM: Color correction matrix parameters + * @C3_ISP_PARAMS_BLOCK_CSC: Color space conversion parameters + * @C3_ISP_PARAMS_BLOCK_BLC: Black level correction parameters + * @C3_ISP_PARAMS_BLOCK_SENTINEL: First non-valid block index + */ +enum c3_isp_params_block_type { + C3_ISP_PARAMS_BLOCK_AWB_GAINS, + C3_ISP_PARAMS_BLOCK_AWB_CONFIG, + C3_ISP_PARAMS_BLOCK_AE_CONFIG, + C3_ISP_PARAMS_BLOCK_AF_CONFIG, + C3_ISP_PARAMS_BLOCK_PST_GAMMA, + C3_ISP_PARAMS_BLOCK_CCM, + C3_ISP_PARAMS_BLOCK_CSC, + C3_ISP_PARAMS_BLOCK_BLC, + C3_ISP_PARAMS_BLOCK_SENTINEL +}; + +#define C3_ISP_PARAMS_BLOCK_FL_DISABLE (1U << 0) +#define C3_ISP_PARAMS_BLOCK_FL_ENABLE (1U << 1) + +/** + * struct c3_isp_params_block_header - C3 ISP parameter block header + * + * This structure represents the common part of all the ISP configuration + * blocks. Each parameters block shall embed an instance of this structure type + * as its first member, followed by the block-specific configuration data. The + * driver inspects this common header to discern the block type and its size and + * properly handle the block content by casting it to the correct block-specific + * type. + * + * The @type field is one of the values enumerated by + * :c:type:`c3_isp_params_block_type` and specifies how the data should be + * interpreted by the driver. The @size field specifies the size of the + * parameters block and is used by the driver for validation purposes. The + * @flags field is a bitmask of per-block flags C3_ISP_PARAMS_FL*. + * + * When userspace wants to disable an ISP block the + * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit should be set in the @flags field. In + * this case userspace may optionally omit the remainder of the configuration + * block, which will be ignored by the driver. + * + * When a new configuration of an ISP block needs to be applied userspace + * shall fully populate the ISP block and omit setting the + * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit in the @flags field. + * + * Userspace is responsible for correctly populating the parameters block header + * fields (@type, @flags and @size) and the block-specific parameters. + * + * For example: + * + * .. code-block:: c + * + * void populate_pst_gamma(struct c3_isp_params_block_header *block) { + * struct c3_isp_params_pst_gamma *gamma = + * (struct c3_isp_params_pst_gamma *)block; + * + * gamma->header.type = C3_ISP_PARAMS_BLOCK_PST_GAMMA; + * gamma->header.flags = C3_ISP_PARAMS_BLOCK_FL_ENABLE; + * gamma->header.size = sizeof(*gamma); + * + * for (unsigned int i = 0; i < 129; i++) + * gamma->pst_gamma_lut[i] = i; + * } + * + * @type: The parameters block type from :c:type:`c3_isp_params_block_type` + * @flags: A bitmask of block flags + * @size: Size (in bytes) of the parameters block, including this header + */ +struct c3_isp_params_block_header { + __u16 type; + __u16 flags; + __u32 size; +}; + +/** + * struct c3_isp_params_awb_gains - Gains for auto-white balance + * + * This struct allows users to configure the gains for white balance. + * There are four gain settings corresponding to each colour channel in + * the bayer domain. All of the gains are stored in Q4.8 format. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AWB_GAINS + * from :c:type:`c3_isp_params_block_type` + * + * @header: The C3 ISP parameters block header + * @gr_gain: Multiplier for Gr channel (Q4.8 format) + * @r_gain: Multiplier for R channel (Q4.8 format) + * @b_gain: Multiplier for B channel (Q4.8 format) + * @gb_gain: Multiplier for Gb channel (Q4.8 format) + */ +struct c3_isp_params_awb_gains { + struct c3_isp_params_block_header header; + __u16 gr_gain; + __u16 r_gain; + __u16 b_gain; + __u16 gb_gain; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_awb_tap_points - Tap points for the AWB statistics + * @C3_ISP_AWB_STATS_TAP_OFE: immediately after the optical frontend block + * @C3_ISP_AWB_STATS_TAP_GE: immediately after the green equal block + * @C3_ISP_AWB_STATS_TAP_BEFORE_WB: immediately before the white balance block + * @C3_ISP_AWB_STATS_TAP_AFTER_WB: immediately after the white balance block + */ +enum c3_isp_params_awb_tap_points { + C3_ISP_AWB_STATS_TAP_OFE = 0, + C3_ISP_AWB_STATS_TAP_GE, + C3_ISP_AWB_STATS_TAP_BEFORE_WB, + C3_ISP_AWB_STATS_TAP_AFTER_WB, +}; + +/** + * struct c3_isp_params_awb_config - Stats settings for auto-white balance + * + * This struct allows the configuration of the statistics generated for auto + * white balance. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AWB_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @tap_point: the tap point from enum c3_isp_params_awb_tap_point + * @satur_vald: AWB statistic over saturation control + * value: 0: disable, 1: enable + * @horiz_zones_num: active number of hotizontal zones [0..32] + * @vert_zones_num: active number of vertical zones [0..24] + * @rg_min: minimum R/G ratio (Q4.8 format) + * @rg_max: maximum R/G ratio (Q4.8 format) + * @bg_min: minimum B/G ratio (Q4.8 format) + * @bg_max: maximum B/G ratio (Q4.8 format) + * @rg_low: R/G ratio trim low (Q4.8 format) + * @rg_high: R/G ratio trim hight (Q4.8 format) + * @bg_low: B/G ratio trim low (Q4.8 format) + * @bg_high: B/G ratio trim high (Q4.8 format) + * @zone_weight: array of weights for AWB statistics zones [0..15] + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + */ +struct c3_isp_params_awb_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 satur_vald; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u16 rg_min; + __u16 rg_max; + __u16 bg_min; + __u16 bg_max; + __u16 rg_low; + __u16 rg_high; + __u16 bg_low; + __u16 bg_high; + __u8 zone_weight[C3_ISP_AWB_MAX_ZONES]; + __u16 horiz_coord[C3_ISP_AWB_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AWB_MAX_PT_NUM]; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_ae_tap_points - Tap points for the AE statistics + * @C3_ISP_AE_STATS_TAP_GE: immediately after the green equal block + * @C3_ISP_AE_STATS_TAP_MLS: immediately after the mesh lens shading block + */ +enum c3_isp_params_ae_tap_points { + C3_ISP_AE_STATS_TAP_GE = 0, + C3_ISP_AE_STATS_TAP_MLS, +}; + +/** + * struct c3_isp_params_ae_config - Stats settings for auto-exposure + * + * This struct allows the configuration of the statistics generated for + * auto exposure. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AE_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @horiz_zones_num: active number of horizontal zones [0..17] + * @vert_zones_num: active number of vertical zones [0..15] + * @tap_point: the tap point from enum c3_isp_params_ae_tap_point + * @zone_weight: array of weights for AE statistics zones [0..15] + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + * @reserved: applications must zero this array + */ +struct c3_isp_params_ae_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u8 zone_weight[C3_ISP_AE_MAX_ZONES]; + __u16 horiz_coord[C3_ISP_AE_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AE_MAX_PT_NUM]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_af_tap_points - Tap points for the AF statistics + * @C3_ISP_AF_STATS_TAP_SNR: immediately after the spatial noise reduce block + * @C3_ISP_AF_STATS_TAP_DMS: immediately after the demosaic block + */ +enum c3_isp_params_af_tap_points { + C3_ISP_AF_STATS_TAP_SNR = 0, + C3_ISP_AF_STATS_TAP_DMS, +}; + +/** + * struct c3_isp_params_af_config - Stats settings for auto-focus + * + * This struct allows the configuration of the statistics generated for + * auto focus. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AF_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @tap_point: the tap point from enum c3_isp_params_af_tap_point + * @horiz_zones_num: active number of hotizontal zones [0..17] + * @vert_zones_num: active number of vertical zones [0..15] + * @reserved: applications must zero this array + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + */ +struct c3_isp_params_af_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u8 reserved[5]; + __u16 horiz_coord[C3_ISP_AF_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AF_MAX_PT_NUM]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_pst_gamma - Post gamma configuration + * + * This struct allows the configuration of the look up table for + * post gamma. The gamma curve consists of 129 points, so need to + * set lut[129]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_PST_GAMMA + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @lut: lookup table for P-Stitch gamma [0..1023] + * @reserved: applications must zero this array + */ +struct c3_isp_params_pst_gamma { + struct c3_isp_params_block_header header; + __u16 lut[129]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_ccm - ISP CCM configuration + * + * This struct allows the configuration of the matrix for + * color correction. The matrix consists of 3 x 3 points, + * so need to set matrix[3][3]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_CCM + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @matrix: a 3 x 3 matrix used for color correction, + * the value of matrix[x][y] is orig_value x 256. [-4096..4095] + * @reserved: applications must zero this array + */ +struct c3_isp_params_ccm { + struct c3_isp_params_block_header header; + __s16 matrix[3][3]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_csc - ISP Color Space Conversion configuration + * + * This struct allows the configuration of the matrix for color space + * conversion. The matrix consists of 3 x 3 points, so need to set matrix[3][3]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_CSC + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @matrix: a 3x3 matrix used for the color space conversion, + * the value of matrix[x][y] is orig_value x 256. [-4096..4095] + * @reserved: applications must zero this array + */ +struct c3_isp_params_csc { + struct c3_isp_params_block_header header; + __s16 matrix[3][3]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_blc - ISP Black Level Correction configuration + * + * This struct allows the configuration of the block level offset for each + * color channel. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_BLC + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @gr_ofst: Gr blc offset (Q4.12 format) + * @r_ofst: R blc offset (Q4.12 format) + * @b_ofst: B blc offset (Q4.12 format) + * @gb_ofst: Gb blc offset(Q4.12 format) + */ +struct c3_isp_params_blc { + struct c3_isp_params_block_header header; + __u16 gr_ofst; + __u16 r_ofst; + __u16 b_ofst; + __u16 gb_ofst; +}; + +/** + * define C3_ISP_PARAMS_MAX_SIZE - Maximum size of all C3 ISP Parameters + * + * Though the parameters for the C3 ISP are passed as optional blocks, the + * driver still needs to know the absolute maximum size so that it can allocate + * a buffer sized appropriately to accommodate userspace attempting to set all + * possible parameters in a single frame. + */ +#define C3_ISP_PARAMS_MAX_SIZE \ + (sizeof(struct c3_isp_params_awb_gains) + \ + sizeof(struct c3_isp_params_awb_config) + \ + sizeof(struct c3_isp_params_ae_config) + \ + sizeof(struct c3_isp_params_af_config) + \ + sizeof(struct c3_isp_params_pst_gamma) + \ + sizeof(struct c3_isp_params_ccm) + \ + sizeof(struct c3_isp_params_csc) + \ + sizeof(struct c3_isp_params_blc)) + +/** + * struct c3_isp_params_cfg - C3 ISP configuration parameters + * + * This struct contains the configuration parameters of the C3 ISP + * algorithms, serialized by userspace into an opaque data buffer. Each + * configuration parameter block is represented by a block-specific structure + * which contains a :c:type:`c3_isp_param_block_header` entry as first + * member. Userspace populates the @data buffer with configuration parameters + * for the blocks that it intends to configure. As a consequence, the data + * buffer effective size changes according to the number of ISP blocks that + * userspace intends to configure. + * + * The parameters buffer is versioned by the @version field to allow modifying + * and extending its definition. Userspace should populate the @version field to + * inform the driver about the version it intends to use. The driver will parse + * and handle the @data buffer according to the data layout specific to the + * indicated revision and return an error if the desired revision is not + * supported. + * + * For each ISP block that userspace wants to configure, a block-specific + * structure is appended to the @data buffer, one after the other without gaps + * in between nor overlaps. Userspace shall populate the @total_size field with + * the effective size, in bytes, of the @data buffer. + * + * The expected memory layout of the parameters buffer is:: + * + * +-------------------- struct c3_isp_params_cfg ---- ------------------+ + * | version = C3_ISP_PARAM_BUFFER_V0; | + * | data_size = sizeof(struct c3_isp_params_awb_gains) + | + * | sizeof(struct c3_isp_params_awb_config); | + * | +------------------------- data ---------------------------------+ | + * | | +------------ struct c3_isp_params_awb_gains) ------------------+ | + * | | | +--------- struct c3_isp_params_block_header header -----+ | | | + * | | | | type = C3_ISP_PARAMS_BLOCK_AWB_GAINS; | | | | + * | | | | flags = C3_ISP_PARAMS_BLOCK_FL_NONE; | | | | + * | | | | size = sizeof(struct c3_isp_params_awb_gains); | | | | + * | | | +---------------------------------------------------------+ | | | + * | | | gr_gain = ...; | | | + * | | | r_gain = ...; | | | + * | | | b_gain = ...; | | | + * | | | gb_gain = ...; | | | + * | | +------------------ struct c3_isp_params_awb_config ----------+ | | + * | | | +---------- struct c3_isp_param_block_header header ------+ | | | + * | | | | type = C3_ISP_PARAMS_BLOCK_AWB_CONFIG; | | | | + * | | | | flags = C3_ISP_PARAMS_BLOCK_FL_NONE; | | | | + * | | | | size = sizeof(struct c3_isp_params_awb_config) | | | | + * | | | +---------------------------------------------------------+ | | | + * | | | tap_point = ...; | | | + * | | | satur_vald = ...; | | | + * | | | horiz_zones_num = ...; | | | + * | | | vert_zones_num = ...; | | | + * | | +-------------------------------------------------------------+ | | + * | +-----------------------------------------------------------------+ | + * +---------------------------------------------------------------------+ + * + * @version: The C3 ISP parameters buffer version + * @data_size: The C3 ISP configuration data effective size, excluding this + * header + * @data: The C3 ISP configuration blocks data + */ +struct c3_isp_params_cfg { + __u32 version; + __u32 data_size; + __u8 data[C3_ISP_PARAMS_MAX_SIZE]; +}; + +#endif -- cgit v1.2.3 From 823153334042746604fdb416ea358a90940c1d83 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 9 May 2025 17:35:37 +0200 Subject: bpf: Add support to retrieve ref_ctr_offset for uprobe perf link Adding support to retrieve ref_ctr_offset for uprobe perf link, which got somehow omitted from the initial uprobe link info changes. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Acked-by: Yafang Shao Link: https://lore.kernel.org/bpf/20250509153539.779599-2-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 5 +++-- kernel/trace/trace_uprobe.c | 2 +- tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 71d5ac83cf5d..16e95398c91c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6724,6 +6724,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from file_name */ __u64 cookie; + __u64 ref_ctr_offset; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index df33d19c5c3b..4b5f29168618 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3800,14 +3800,14 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, static int bpf_perf_link_fill_uprobe(const struct perf_event *event, struct bpf_link_info *info) { + u64 ref_ctr_offset, offset; char __user *uname; - u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; - err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset, &type, NULL); if (err) return err; @@ -3819,6 +3819,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; + info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset; return 0; } #endif diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 3386439ec9f6..d9cf6ed2c106 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1489,7 +1489,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; - *probe_addr = 0; + *probe_addr = tu->ref_ctr_offset; return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 71d5ac83cf5d..16e95398c91c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6724,6 +6724,7 @@ struct bpf_link_info { __u32 name_len; __u32 offset; /* offset from file_name */ __u64 cookie; + __u64 ref_ctr_offset; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ -- cgit v1.2.3 From 1b2900db0119c02e6445bb61ec3fba982d10cc8d Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 May 2025 13:30:34 +0300 Subject: ethtool: Block setting of symmetric RSS when non-symmetric rx-flow-hash is requested Symmetric RSS hash requires that: * No other fields besides IP src/dst and/or L4 src/dst are set * If src is set, dst must also be set This restriction was only enforced when RXNFC was configured after symmetric hash was enabled. In the opposite order of operations (RXNFC then symmetric enablement) the check was not performed. Perform the sanity check on set_rxfh as well, by iterating over all flow types hash fields and making sure they are all symmetric. Introduce a function that returns whether a flow type is hashable (not spec only) and needs to be iterated over. To make sure that no one forgets to update the list of hashable flow types when adding new flow types, a static assert is added to draw the developer's attention. The conversion of uapi #defines to enum is not ideal, but as Jakub mentioned [1], we have precedent for that. [1] https://lore.kernel.org/netdev/20250324073509.6571ade3@kernel.org/ Reviewed-by: Tariq Toukan Signed-off-by: Gal Pressman Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250508103034.885536-1-gal@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 134 ++++++++++++++++++++++--------------------- net/ethtool/ioctl.c | 99 ++++++++++++++++++++++++++++---- 2 files changed, 158 insertions(+), 75 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 84833cca29fe..707c1844010c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2295,71 +2295,75 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define RXH_XFRM_SYM_OR_XOR (1 << 1) #define RXH_XFRM_NO_CHANGE 0xff -/* L2-L4 network traffic flow types */ -#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ -#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ -#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ -#define AH_ESP_V4_FLOW 0x04 /* hash only */ -#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */ -#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */ -#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */ -#define AH_ESP_V6_FLOW 0x08 /* hash only */ -#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */ -#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */ -#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */ -#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */ -#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ -#define IP_USER_FLOW IPV4_USER_FLOW -#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */ -#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 */ +enum { + /* L2-L4 network traffic flow types */ + TCP_V4_FLOW = 0x01, /* hash or spec (tcp_ip4_spec) */ + UDP_V4_FLOW = 0x02, /* hash or spec (udp_ip4_spec) */ + SCTP_V4_FLOW = 0x03, /* hash or spec (sctp_ip4_spec) */ + AH_ESP_V4_FLOW = 0x04, /* hash only */ + TCP_V6_FLOW = 0x05, /* hash or spec (tcp_ip6_spec; nfc only) */ + UDP_V6_FLOW = 0x06, /* hash or spec (udp_ip6_spec; nfc only) */ + SCTP_V6_FLOW = 0x07, /* hash or spec (sctp_ip6_spec; nfc only) */ + AH_ESP_V6_FLOW = 0x08, /* hash only */ + AH_V4_FLOW = 0x09, /* hash or spec (ah_ip4_spec) */ + ESP_V4_FLOW = 0x0a, /* hash or spec (esp_ip4_spec) */ + AH_V6_FLOW = 0x0b, /* hash or spec (ah_ip6_spec; nfc only) */ + ESP_V6_FLOW = 0x0c, /* hash or spec (esp_ip6_spec; nfc only) */ + IPV4_USER_FLOW = 0x0d, /* spec only (usr_ip4_spec) */ + IP_USER_FLOW = IPV4_USER_FLOW, + IPV6_USER_FLOW = 0x0e, /* spec only (usr_ip6_spec; nfc only) */ + IPV4_FLOW = 0x10, /* hash only */ + IPV6_FLOW = 0x11, /* hash only */ + 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. + */ + GTPU_V4_FLOW = 0x13, /* hash only */ + 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). + */ + GTPC_V4_FLOW = 0x15, /* hash only */ + 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. + */ + GTPC_TEID_V4_FLOW = 0x17, /* hash only */ + 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. + */ + GTPU_EH_V4_FLOW = 0x19, /* hash only */ + 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. + */ + GTPU_UL_V4_FLOW = 0x1b, /* hash only */ + GTPU_UL_V6_FLOW = 0x1c, /* hash only */ + GTPU_DL_V4_FLOW = 0x1d, /* hash only */ + GTPU_DL_V6_FLOW = 0x1e, /* hash only */ + + __FLOW_TYPE_COUNT, +}; /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 8262cc10f98d..39ec920f5de7 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -978,6 +978,88 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr, return 0; } +static bool flow_type_hashable(u32 flow_type) +{ + switch (flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV4_FLOW: + case IPV6_FLOW: + case GTPU_V4_FLOW: + case GTPU_V6_FLOW: + case GTPC_V4_FLOW: + case GTPC_V6_FLOW: + case GTPC_TEID_V4_FLOW: + case GTPC_TEID_V6_FLOW: + case GTPU_EH_V4_FLOW: + case GTPU_EH_V6_FLOW: + case GTPU_UL_V4_FLOW: + case GTPU_UL_V6_FLOW: + case GTPU_DL_V4_FLOW: + case GTPU_DL_V6_FLOW: + return true; + } + + return false; +} + +/* When adding a new type, update the assert and, if it's hashable, add it to + * the flow_type_hashable switch case. + */ +static_assert(GTPU_DL_V6_FLOW + 1 == __FLOW_TYPE_COUNT); + +static int ethtool_check_xfrm_rxfh(u32 input_xfrm, u64 rxfh) +{ + /* Sanity check: if symmetric-xor/symmetric-or-xor is set, then: + * 1 - no other fields besides IP src/dst and/or L4 src/dst are set + * 2 - If src is set, dst must also be set + */ + if ((input_xfrm != RXH_XFRM_NO_CHANGE && + input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) && + ((rxfh & ~(RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) || + (!!(rxfh & RXH_IP_SRC) ^ !!(rxfh & RXH_IP_DST)) || + (!!(rxfh & RXH_L4_B_0_1) ^ !!(rxfh & RXH_L4_B_2_3)))) + return -EINVAL; + + return 0; +} + +static int ethtool_check_flow_types(struct net_device *dev, u32 input_xfrm) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc info = { + .cmd = ETHTOOL_GRXFH, + }; + int err; + u32 i; + + for (i = 0; i < __FLOW_TYPE_COUNT; i++) { + if (!flow_type_hashable(i)) + continue; + + info.flow_type = i; + err = ops->get_rxnfc(dev, &info, NULL); + if (err) + continue; + + err = ethtool_check_xfrm_rxfh(input_xfrm, info.data); + if (err) + return err; + } + + return 0; +} + static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { @@ -1012,16 +1094,9 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, if (rc) return rc; - /* Sanity check: if symmetric-xor/symmetric-or-xor is set, then: - * 1 - no other fields besides IP src/dst and/or L4 src/dst - * 2 - If src is set, dst must also be set - */ - if ((rxfh.input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) && - ((info.data & ~(RXH_IP_SRC | RXH_IP_DST | - RXH_L4_B_0_1 | RXH_L4_B_2_3)) || - (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) || - (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3)))) - return -EINVAL; + rc = ethtool_check_xfrm_rxfh(rxfh.input_xfrm, info.data); + if (rc) + return rc; } rc = ops->set_rxnfc(dev, &info); @@ -1413,6 +1488,10 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; + ret = ethtool_check_flow_types(dev, rxfh.input_xfrm); + if (ret) + return ret; + indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); /* Check settings which may be global rather than per RSS-context */ -- cgit v1.2.3 From 26bb32768fe6552de044f782a58b3272073fbfc0 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Mon, 3 Mar 2025 13:20:44 +0200 Subject: ptrace: introduce PTRACE_SET_SYSCALL_INFO request PTRACE_SET_SYSCALL_INFO is a generic ptrace API that complements PTRACE_GET_SYSCALL_INFO by letting the ptracer modify details of system calls the tracee is blocked in. This API allows ptracers to obtain and modify system call details in a straightforward and architecture-agnostic way, providing a consistent way of manipulating the system call number and arguments across architectures. As in case of PTRACE_GET_SYSCALL_INFO, PTRACE_SET_SYSCALL_INFO also does not aim to address numerous architecture-specific system call ABI peculiarities, like differences in the number of system call arguments for such system calls as pread64 and preadv. The current implementation supports changing only those bits of system call information that are used by strace system call tampering, namely, syscall number, syscall arguments, and syscall return value. Support of changing additional details returned by PTRACE_GET_SYSCALL_INFO, such as instruction pointer and stack pointer, could be added later if needed, by using struct ptrace_syscall_info.flags to specify the additional details that should be set. Currently, "flags" and "reserved" fields of struct ptrace_syscall_info must be initialized with zeroes; "arch", "instruction_pointer", and "stack_pointer" fields are currently ignored. PTRACE_SET_SYSCALL_INFO currently supports only PTRACE_SYSCALL_INFO_ENTRY, PTRACE_SYSCALL_INFO_EXIT, and PTRACE_SYSCALL_INFO_SECCOMP operations. Other operations could be added later if needed. Ideally, PTRACE_SET_SYSCALL_INFO should have been introduced along with PTRACE_GET_SYSCALL_INFO, but it didn't happen. The last straw that convinced me to implement PTRACE_SET_SYSCALL_INFO was apparent failure to provide an API of changing the first system call argument on riscv architecture. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_SET_SYSCALL_INFO Modify information about the system call that caused the stop. The "data" argument is a pointer to struct ptrace_syscall_info that specifies the system call information to be set. The "addr" argument should be set to sizeof(struct ptrace_syscall_info)). Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Link: https://lkml.kernel.org/r/20250303112044.GF24170@strace.io Signed-off-by: Dmitry V. Levin Reviewed-by: Alexey Gladkov Reviewed-by: Charlie Jenkins Tested-by: Charlie Jenkins Reviewed-by: Eugene Syromiatnikov Reviewed-by: Oleg Nesterov Cc: Alexander Gordeev Cc: Andreas Larsson Cc: anton ivanov Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Brian Cain Cc: Christian Borntraeger Cc: Christian Zankel Cc: Christophe Leroy Cc: Dave Hansen Cc: Davide Berardi Cc: David S. Miller Cc: Dinh Nguyen Cc: Eugene Syromyatnikov Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Jonas Bonn Cc: Maciej W. Rozycki Cc: Madhavan Srinivasan Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Frysinger Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Renzo Davoi Cc: Richard Weinberger Cc: Rich Felker Cc: Russel King Cc: Shuah Khan Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- include/uapi/linux/ptrace.h | 7 ++- kernel/ptrace.c | 121 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 126 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index 72c038fc71d0..5f8ef6156752 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -74,6 +74,7 @@ struct seccomp_metadata { }; #define PTRACE_GET_SYSCALL_INFO 0x420e +#define PTRACE_SET_SYSCALL_INFO 0x4212 #define PTRACE_SYSCALL_INFO_NONE 0 #define PTRACE_SYSCALL_INFO_ENTRY 1 #define PTRACE_SYSCALL_INFO_EXIT 2 @@ -81,7 +82,8 @@ struct seccomp_metadata { struct ptrace_syscall_info { __u8 op; /* PTRACE_SYSCALL_INFO_* */ - __u8 pad[3]; + __u8 reserved; + __u16 flags; __u32 arch; __u64 instruction_pointer; __u64 stack_pointer; @@ -98,6 +100,7 @@ struct ptrace_syscall_info { __u64 nr; __u64 args[6]; __u32 ret_data; + __u32 reserved2; } seccomp; }; }; @@ -142,6 +145,8 @@ struct ptrace_sud_config { __u64 len; }; +/* 0x4212 is PTRACE_SET_SYSCALL_INFO */ + /* * These values are stored in task->ptrace_message * by ptrace_stop to describe the current syscall-stop. diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 22e7d74cf4cd..75a84efad40f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -944,7 +944,10 @@ ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, ptrace_get_syscall_info_entry(child, regs, info); info->seccomp.ret_data = child->ptrace_message; - /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ + /* + * ret_data is the last non-reserved field + * in struct ptrace_syscall_info.seccomp + */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } @@ -1016,6 +1019,118 @@ ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } + +static int +ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + unsigned long args[ARRAY_SIZE(info->entry.args)]; + int nr = info->entry.nr; + int i; + + /* + * Check that the syscall number specified in info->entry.nr + * is either a value of type "int" or a sign-extended value + * of type "int". + */ + if (nr != info->entry.nr) + return -ERANGE; + + for (i = 0; i < ARRAY_SIZE(args); i++) { + args[i] = info->entry.args[i]; + /* + * Check that the syscall argument specified in + * info->entry.args[i] is either a value of type + * "unsigned long" or a sign-extended value of type "long". + */ + if (args[i] != info->entry.args[i]) + return -ERANGE; + } + + syscall_set_nr(child, regs, nr); + /* + * If the syscall number is set to -1, setting syscall arguments is not + * just pointless, it would also clobber the syscall return value on + * those architectures that share the same register both for the first + * argument of syscall and its return value. + */ + if (nr != -1) + syscall_set_arguments(child, regs, args); + + return 0; +} + +static int +ptrace_set_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + /* + * info->entry is currently a subset of info->seccomp, + * info->seccomp.ret_data is currently ignored. + */ + return ptrace_set_syscall_info_entry(child, regs, info); +} + +static int +ptrace_set_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, + struct ptrace_syscall_info *info) +{ + long rval = info->exit.rval; + + /* + * Check that the return value specified in info->exit.rval + * is either a value of type "long" or a sign-extended value + * of type "long". + */ + if (rval != info->exit.rval) + return -ERANGE; + + if (info->exit.is_error) + syscall_set_return_value(child, regs, rval, 0); + else + syscall_set_return_value(child, regs, 0, rval); + + return 0; +} + +static int +ptrace_set_syscall_info(struct task_struct *child, unsigned long user_size, + const void __user *datavp) +{ + struct pt_regs *regs = task_pt_regs(child); + struct ptrace_syscall_info info; + + if (user_size < sizeof(info)) + return -EINVAL; + + /* + * The compatibility is tracked by info.op and info.flags: if user-space + * does not instruct us to use unknown extra bits from future versions + * of ptrace_syscall_info, we are not going to read them either. + */ + if (copy_from_user(&info, datavp, sizeof(info))) + return -EFAULT; + + /* Reserved for future use. */ + if (info.flags || info.reserved) + return -EINVAL; + + /* Changing the type of the system call stop is not supported yet. */ + if (ptrace_get_syscall_info_op(child) != info.op) + return -EINVAL; + + switch (info.op) { + case PTRACE_SYSCALL_INFO_ENTRY: + return ptrace_set_syscall_info_entry(child, regs, &info); + case PTRACE_SYSCALL_INFO_EXIT: + return ptrace_set_syscall_info_exit(child, regs, &info); + case PTRACE_SYSCALL_INFO_SECCOMP: + return ptrace_set_syscall_info_seccomp(child, regs, &info); + default: + /* Other types of system call stops are not supported yet. */ + return -EINVAL; + } +} #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, @@ -1234,6 +1349,10 @@ int ptrace_request(struct task_struct *child, long request, case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; + + case PTRACE_SET_SYSCALL_INFO: + ret = ptrace_set_syscall_info(child, addr, datavp); + break; #endif case PTRACE_SECCOMP_GET_FILTER: -- cgit v1.2.3 From a516403787e08119b70ce8bfff985272ef318a58 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Mon, 24 Mar 2025 06:53:26 +0000 Subject: fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions Patch series "fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions", v2. Introduce the PAGE_IS_GUARD flag in the PAGEMAP_SCAN ioctl to expose information about guard regions. This allows userspace tools, such as CRIU, to detect and handle guard regions. Currently, CRIU utilizes PAGEMAP_SCAN as a more efficient alternative to parsing /proc/pid/pagemap. Without this change, guard regions are incorrectly reported as swap-anon regions, leading CRIU to attempt dumping them and subsequently failing. The series includes updates to the documentation and selftests to reflect the new functionality. This patch (of 3): Introduce the PAGE_IS_GUARD flag in the PAGEMAP_SCAN ioctl to expose information about guard regions. This allows userspace tools, such as CRIU, to detect and handle guard regions. Link: https://lkml.kernel.org/r/20250324065328.107678-1-avagin@google.com Link: https://lkml.kernel.org/r/20250324065328.107678-2-avagin@google.com Signed-off-by: Andrei Vagin Acked-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Cc: Jonathan Corbet Cc: Shuah Khan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/pagemap.rst | 1 + fs/proc/task_mmu.c | 17 ++++++++++------- include/uapi/linux/fs.h | 1 + 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index afce291649dd..e60e9211fd9b 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -250,6 +250,7 @@ Following flags about pages are currently supported: - ``PAGE_IS_PFNZERO`` - Page has zero PFN - ``PAGE_IS_HUGE`` - Page is PMD-mapped THP or Hugetlb backed - ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty +- ``PAGE_IS_GUARD`` - Page is a part of a guard region The ``struct pm_scan_arg`` is used as the argument of the IOCTL. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 994cde10e3f4..b9e4fbbdf6e6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2087,7 +2087,8 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY | \ + PAGE_IS_GUARD) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -2128,12 +2129,14 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; - if (p->masks_of_interest & PAGE_IS_FILE) { - swp = pte_to_swp_entry(pte); - if (is_pfn_swap_entry(swp) && - !folio_test_anon(pfn_swap_entry_folio(swp))) - categories |= PAGE_IS_FILE; - } + swp = pte_to_swp_entry(pte); + if (is_guard_swp_entry(swp)) + categories |= PAGE_IS_GUARD; + else if ((p->masks_of_interest & PAGE_IS_FILE) && + is_pfn_swap_entry(swp) && + !folio_test_anon(pfn_swap_entry_folio(swp))) + categories |= PAGE_IS_FILE; + if (pte_swp_soft_dirty(pte)) categories |= PAGE_IS_SOFT_DIRTY; } diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index e762e1af650c..0098b0ce8ccb 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -361,6 +361,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) #define PAGE_IS_SOFT_DIRTY (1 << 7) +#define PAGE_IS_GUARD (1 << 8) /* * struct page_region - Page region with flags -- cgit v1.2.3 From 8802087d20c0e1c26c4b4fe30e22264bf8285e51 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 8 May 2025 00:48:23 +0000 Subject: net: devmem: TCP tx netlink api Add bind-tx netlink call to attach dmabuf for TX; queue is not required, only ifindex and dmabuf fd for attachment. Signed-off-by: Stanislav Fomichev Signed-off-by: Mina Almasry Link: https://patch.msgid.link/20250508004830.4100853-4-almasrymina@google.com Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/netdev.yaml | 12 ++++++++++++ include/uapi/linux/netdev.h | 1 + net/core/netdev-genl-gen.c | 13 +++++++++++++ net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 6 ++++++ tools/include/uapi/linux/netdev.h | 1 + 6 files changed, 34 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f5e0750ab71d..c0ef6d0d7786 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -743,6 +743,18 @@ operations: - defer-hard-irqs - gro-flush-timeout - irq-suspend-timeout + - + name: bind-tx + doc: Bind dmabuf to netdev for TX + attribute-set: dmabuf + do: + request: + attributes: + - ifindex + - fd + reply: + attributes: + - id kernel-family: headers: [ "net/netdev_netlink.h"] diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 7600bf62dbdf..7eb9571786b8 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -219,6 +219,7 @@ enum { NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, __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 739f7b6506a6..4fc44587f493 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -99,6 +99,12 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPE [NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, }, }; +/* NETDEV_CMD_BIND_TX - do */ +static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1] = { + [NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -190,6 +196,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NETDEV_CMD_BIND_TX, + .doit = netdev_nl_bind_tx_doit, + .policy = netdev_bind_tx_nl_policy, + .maxattr = NETDEV_A_DMABUF_FD, + .flags = GENL_CMD_CAP_DO, + }, }; 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 17d39fd64c94..cf3fad74511f 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -34,6 +34,7 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 17aa9e42e8d5..3beef87235d8 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -968,6 +968,12 @@ err_genlmsg_free: return err; } +/* stub */ +int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info) +{ + return 0; +} + void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) { INIT_LIST_HEAD(&priv->bindings); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7600bf62dbdf..7eb9571786b8 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -219,6 +219,7 @@ enum { NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From 1119e5519dcdb7b3527f5d85accf9c7aa02b2b28 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 13 May 2025 15:17:52 -0700 Subject: net: sched: uapi: add more sanely named duplicate defines The TCA_FLOWER_KEY_CFM enum has a UNSPEC and MAX with _OPT in the name, but the real attributes don't. Add a MAX that more reasonably matches the attrs. The PAD in TCA_TAPRIO is the only attr which doesn't have _ATTR in it, perhaps signifying that it's not a real attr? If so interesting idea in abstract but it makes codegen painful. Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250513221752.843102-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/pkt_sched.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 490821364165..28d94b11d1aa 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -697,6 +697,7 @@ enum { }; #define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1) +#define TCA_FLOWER_KEY_CFM_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1) #define TCA_FLOWER_MASK_FLAGS_RANGE (1 << 0) /* Range-based match */ diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 9ea874395717..3e41349f3fa2 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1182,6 +1182,7 @@ enum { TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ TCA_TAPRIO_PAD, + TCA_TAPRIO_ATTR_PAD = TCA_TAPRIO_PAD, TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */ -- cgit v1.2.3 From a7484c80e5ca1ae0c397bb8003bc588f0dcf43f4 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 14 May 2025 11:34:59 +0100 Subject: KVM: arm64: Allow userspace to request KVM_ARM_VCPU_EL2* Since we're (almost) feature complete, let's allow userspace to request KVM_ARM_VCPU_EL2* by bumping KVM_VCPU_MAX_FEATURES up. We also now advertise the features to userspace with new capabilities. It's going to be great... Reviewed-by: Oliver Upton Reviewed-by: Joey Gouly Reviewed-by: Ganapatrao Kulkarni Link: https://lore.kernel.org/r/20250514103501.2225951-17-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 2 +- arch/arm64/kvm/arm.c | 6 ++++++ include/uapi/linux/kvm.h | 2 ++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b2c535036a06..79e175a16d35 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -39,7 +39,7 @@ #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS -#define KVM_VCPU_MAX_FEATURES 7 +#define KVM_VCPU_MAX_FEATURES 9 #define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1) #define KVM_REQ_SLEEP \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 528743587360..b021ce1e42c5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -368,6 +368,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_EL1_32BIT: r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1); break; + case KVM_CAP_ARM_EL2: + r = cpus_have_final_cap(ARM64_HAS_NESTED_VIRT); + break; + case KVM_CAP_ARM_EL2_E2H0: + r = cpus_have_final_cap(ARM64_HAS_HCR_NV1); + break; case KVM_CAP_GUEST_DEBUG_HW_BPS: r = get_num_brps(); break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b6ae8ad8934b..c9d4a908976e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -930,6 +930,8 @@ struct kvm_enable_cap { #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 #define KVM_CAP_X86_GUEST_MODE 238 #define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_ARM_EL2 240 +#define KVM_CAP_ARM_EL2_E2H0 241 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 99c1e4eb6a3fbbec27c7c70e5fce15cdc1422893 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 20 May 2025 12:54:33 +0800 Subject: ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG Add UBLK_F_AUTO_BUF_REG for supporting to register buffer automatically to local io_uring context with provided buffer index. Add UAPI structure `struct ublk_auto_buf_reg` for holding user parameter to register request buffer automatically, one 'flags' field is defined, and there is still 32bit available for future extension, such as, adding one io_ring FD field for registering buffer to external io_uring. `struct ublk_auto_buf_reg` is populated from ublk uring_cmd's sqe->addr, and all existing ublk commands are data-less, so it is just fine to reuse sqe->addr for this purpose. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250520045455.515691-4-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 56 ++++++++++++++++++++++++++++++++----- include/uapi/linux/ublk_cmd.h | 64 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 3e56a9d267fb..1aabc655652b 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -66,7 +66,8 @@ | UBLK_F_USER_COPY \ | UBLK_F_ZONED \ | UBLK_F_USER_RECOVERY_FAIL_IO \ - | UBLK_F_UPDATE_SIZE) + | UBLK_F_UPDATE_SIZE \ + | UBLK_F_AUTO_BUF_REG) #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ @@ -80,6 +81,9 @@ struct ublk_rq_data { refcount_t ref; + + /* for auto-unregister buffer in case of UBLK_F_AUTO_BUF_REG */ + u16 buf_index; }; struct ublk_uring_cmd_pdu { @@ -101,6 +105,9 @@ struct ublk_uring_cmd_pdu { * setup in ublk uring_cmd handler */ struct ublk_queue *ubq; + + struct ublk_auto_buf_reg buf; + u16 tag; }; @@ -630,7 +637,7 @@ static inline bool ublk_support_zero_copy(const struct ublk_queue *ubq) static inline bool ublk_support_auto_buf_reg(const struct ublk_queue *ubq) { - return false; + return ubq->flags & UBLK_F_AUTO_BUF_REG; } static inline bool ublk_support_user_copy(const struct ublk_queue *ubq) @@ -1178,17 +1185,20 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, static bool ublk_auto_buf_reg(struct request *req, struct ublk_io *io, unsigned int issue_flags) { + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(io->cmd); struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); int ret; - ret = io_buffer_register_bvec(io->cmd, req, ublk_io_release, 0, - issue_flags); + ret = io_buffer_register_bvec(io->cmd, req, ublk_io_release, + pdu->buf.index, issue_flags); if (ret) { blk_mq_end_request(req, BLK_STS_IOERR); return false; } /* one extra reference is dropped by ublk_io_release */ refcount_set(&data->ref, 2); + /* store buffer index in request payload */ + data->buf_index = pdu->buf.index; io->flags |= UBLK_IO_FLAG_AUTO_BUF_REG; return true; } @@ -1952,6 +1962,18 @@ static inline void ublk_prep_cancel(struct io_uring_cmd *cmd, io_uring_cmd_mark_cancelable(cmd, issue_flags); } +static inline int ublk_set_auto_buf_reg(struct io_uring_cmd *cmd) +{ + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + pdu->buf = ublk_sqe_addr_to_auto_buf_reg(READ_ONCE(cmd->sqe->addr)); + + if (pdu->buf.reserved0 || pdu->buf.reserved1) + return -EINVAL; + + return 0; +} + static void ublk_io_release(void *priv) { struct request *rq = priv; @@ -2034,6 +2056,12 @@ static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq, goto out; } + if (ublk_support_auto_buf_reg(ubq)) { + ret = ublk_set_auto_buf_reg(cmd); + if (ret) + return ret; + } + ublk_fill_io_cmd(io, cmd, buf_addr); ublk_mark_io_ready(ub, ubq); out: @@ -2065,11 +2093,20 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq, } if (ublk_support_auto_buf_reg(ubq)) { + int ret; + if (io->flags & UBLK_IO_FLAG_AUTO_BUF_REG) { - WARN_ON_ONCE(io_buffer_unregister_bvec(cmd, 0, + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + WARN_ON_ONCE(io_buffer_unregister_bvec(cmd, + data->buf_index, issue_flags)); io->flags &= ~UBLK_IO_FLAG_AUTO_BUF_REG; } + + ret = ublk_set_auto_buf_reg(cmd); + if (ret) + return ret; } ublk_fill_io_cmd(io, cmd, ub_cmd->addr); @@ -2791,8 +2828,11 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) * For USER_COPY, we depends on userspace to fill request * buffer by pwrite() to ublk char device, which can't be * used for unprivileged device + * + * Same with zero copy or auto buffer register. */ - if (info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY)) + if (info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY | + UBLK_F_AUTO_BUF_REG)) return -EINVAL; } @@ -2850,7 +2890,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) UBLK_F_URING_CMD_COMP_IN_TASK; /* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */ - if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY)) + if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY | + UBLK_F_AUTO_BUF_REG)) ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; /* @@ -3377,6 +3418,7 @@ static int __init ublk_init(void) BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET + UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET); + BUILD_BUG_ON(sizeof(struct ublk_auto_buf_reg) != 8); init_waitqueue_head(&ublk_idr_wq); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index be5c6c6b16e0..f6f516b1223b 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -219,6 +219,29 @@ */ #define UBLK_F_UPDATE_SIZE (1ULL << 10) +/* + * request buffer is registered automatically to uring_cmd's io_uring + * context before delivering this io command to ublk server, meantime + * it is un-registered automatically when completing this io command. + * + * For using this feature: + * + * - ublk server has to create sparse buffer table + * + * - ublk server passes auto buf register data via uring_cmd's sqe->addr, + * `struct ublk_auto_buf_reg` is populated from sqe->addr, please see + * the definition of ublk_sqe_addr_to_auto_buf_reg() + * + * - pass buffer index from `ublk_auto_buf_reg.index` + * + * - all reserved fields in `ublk_auto_buf_reg` need to be zeroed + * + * This way avoids extra cost from two uring_cmd, but also simplifies backend + * implementation, such as, the dependency on IO_REGISTER_IO_BUF and + * IO_UNREGISTER_IO_BUF becomes not necessary. + */ +#define UBLK_F_AUTO_BUF_REG (1ULL << 11) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -339,6 +362,47 @@ static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod) return iod->op_flags >> 8; } +struct ublk_auto_buf_reg { + /* index for registering the delivered request buffer */ + __u16 index; + __u16 reserved0; + + /* + * io_ring FD can be passed via the reserve field in future for + * supporting to register io buffer to external io_uring + */ + __u32 reserved1; +}; + +/* + * For UBLK_F_AUTO_BUF_REG, auto buffer register data is carried via + * uring_cmd's sqe->addr: + * + * - bit0 ~ bit15: buffer index + * - bit24 ~ bit31: reserved0 + * - bit32 ~ bit63: reserved1 + */ +static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( + __u64 sqe_addr) +{ + struct ublk_auto_buf_reg reg = { + .index = sqe_addr & 0xffff, + .reserved0 = (sqe_addr >> 16) & 0xffff, + .reserved1 = sqe_addr >> 32, + }; + + return reg; +} + +static inline __u64 +ublk_auto_buf_reg_to_sqe_addr(const struct ublk_auto_buf_reg *buf) +{ + __u64 addr = buf->index | (__u64)buf->reserved0 << 16 | + (__u64)buf->reserved1 << 32; + + return addr; +} + /* issued to ublk driver via /dev/ublkcN */ struct ublksrv_io_cmd { __u16 q_id; -- cgit v1.2.3 From 53f427e7944b4f288866cc4a69835086e0958c6a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 20 May 2025 12:54:34 +0800 Subject: ublk: support UBLK_AUTO_BUF_REG_FALLBACK For UBLK_F_AUTO_BUF_REG, buffer is registered to uring_cmd context automatically with the provided buffer index. User may provide one wrong buffer index, or the specified buffer is registered by application already. Add UBLK_AUTO_BUF_REG_FALLBACK for supporting to auto buffer registering fallback by completing the uring_cmd and telling ublk server the register failure via UBLK_AUTO_BUF_REG_FALLBACK, then ublk server still can register the buffer from userspace. So we can provide reliable way for supporting auto buffer register. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250520045455.515691-5-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 16 ++++++++++++++++ include/uapi/linux/ublk_cmd.h | 39 ++++++++++++++++++++++++++++++++++++--- 2 files changed, 52 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 1aabc655652b..2474788ef263 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1182,6 +1182,16 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, blk_mq_end_request(rq, BLK_STS_IOERR); } +static void ublk_auto_buf_reg_fallback(struct request *req, struct ublk_io *io) +{ + const struct ublk_queue *ubq = req->mq_hctx->driver_data; + struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag); + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + iod->op_flags |= UBLK_IO_F_NEED_REG_BUF; + refcount_set(&data->ref, 1); +} + static bool ublk_auto_buf_reg(struct request *req, struct ublk_io *io, unsigned int issue_flags) { @@ -1192,6 +1202,10 @@ static bool ublk_auto_buf_reg(struct request *req, struct ublk_io *io, ret = io_buffer_register_bvec(io->cmd, req, ublk_io_release, pdu->buf.index, issue_flags); if (ret) { + if (pdu->buf.flags & UBLK_AUTO_BUF_REG_FALLBACK) { + ublk_auto_buf_reg_fallback(req, io); + return true; + } blk_mq_end_request(req, BLK_STS_IOERR); return false; } @@ -1971,6 +1985,8 @@ static inline int ublk_set_auto_buf_reg(struct io_uring_cmd *cmd) if (pdu->buf.reserved0 || pdu->buf.reserved1) return -EINVAL; + if (pdu->buf.flags & ~UBLK_AUTO_BUF_REG_F_MASK) + return -EINVAL; return 0; } diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index f6f516b1223b..c4b9942697fc 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -236,9 +236,16 @@ * * - all reserved fields in `ublk_auto_buf_reg` need to be zeroed * + * - pass flags from `ublk_auto_buf_reg.flags` if needed + * * This way avoids extra cost from two uring_cmd, but also simplifies backend * implementation, such as, the dependency on IO_REGISTER_IO_BUF and * IO_UNREGISTER_IO_BUF becomes not necessary. + * + * If wrong data or flags are provided, both IO_FETCH_REQ and + * IO_COMMIT_AND_FETCH_REQ are failed, for the latter, the ublk IO request + * won't be completed until new IO_COMMIT_AND_FETCH_REQ command is issued + * successfully */ #define UBLK_F_AUTO_BUF_REG (1ULL << 11) @@ -328,6 +335,17 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_F_FUA (1U << 13) #define UBLK_IO_F_NOUNMAP (1U << 15) #define UBLK_IO_F_SWAP (1U << 16) +/* + * For UBLK_F_AUTO_BUF_REG & UBLK_AUTO_BUF_REG_FALLBACK only. + * + * This flag is set if auto buffer register is failed & ublk server passes + * UBLK_AUTO_BUF_REG_FALLBACK, and ublk server need to register buffer + * manually for handling the delivered IO command if this flag is observed + * + * ublk server has to check this flag if UBLK_AUTO_BUF_REG_FALLBACK is + * passed in. + */ +#define UBLK_IO_F_NEED_REG_BUF (1U << 17) /* * io cmd is described by this structure, and stored in share memory, indexed @@ -362,10 +380,23 @@ static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod) return iod->op_flags >> 8; } +/* + * If this flag is set, fallback by completing the uring_cmd and setting + * `UBLK_IO_F_NEED_REG_BUF` in case of auto-buf-register failure; + * otherwise the client ublk request is failed silently + * + * If ublk server passes this flag, it has to check if UBLK_IO_F_NEED_REG_BUF + * is set in `ublksrv_io_desc.op_flags`. If UBLK_IO_F_NEED_REG_BUF is set, + * ublk server needs to register io buffer manually for handling IO command. + */ +#define UBLK_AUTO_BUF_REG_FALLBACK (1 << 0) +#define UBLK_AUTO_BUF_REG_F_MASK UBLK_AUTO_BUF_REG_FALLBACK + struct ublk_auto_buf_reg { /* index for registering the delivered request buffer */ __u16 index; - __u16 reserved0; + __u8 flags; + __u8 reserved0; /* * io_ring FD can be passed via the reserve field in future for @@ -379,6 +410,7 @@ struct ublk_auto_buf_reg { * uring_cmd's sqe->addr: * * - bit0 ~ bit15: buffer index + * - bit16 ~ bit23: flags * - bit24 ~ bit31: reserved0 * - bit32 ~ bit63: reserved1 */ @@ -387,7 +419,8 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( { struct ublk_auto_buf_reg reg = { .index = sqe_addr & 0xffff, - .reserved0 = (sqe_addr >> 16) & 0xffff, + .flags = (sqe_addr >> 16) & 0xff, + .reserved0 = (sqe_addr >> 24) & 0xff, .reserved1 = sqe_addr >> 32, }; @@ -397,7 +430,7 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( static inline __u64 ublk_auto_buf_reg_to_sqe_addr(const struct ublk_auto_buf_reg *buf) { - __u64 addr = buf->index | (__u64)buf->reserved0 << 16 | + __u64 addr = buf->index | (__u64)buf->flags << 16 | (__u64)buf->reserved0 << 24 | (__u64)buf->reserved1 << 32; return addr; -- cgit v1.2.3 From 5b9db9c16f428ada473314ad1c49e55681be7a72 Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Thu, 15 May 2025 16:37:25 +0200 Subject: RISC-V: KVM: add KVM_CAP_RISCV_MP_STATE_RESET MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a toggleable VM capability to reset the VCPU from userspace by setting MP_STATE_INIT_RECEIVED through IOCTL. Reset through a mp_state to avoid adding a new IOCTL. Do not reset on a transition from STOPPED to RUNNABLE, because it's better to avoid side effects that would complicate userspace adoption. The MP_STATE_INIT_RECEIVED is not a permanent mp_state -- IOCTL resets the VCPU while preserving the original mp_state -- because we wouldn't gain much from having a new state it in the rest of KVM, but it's a very non-standard use of the IOCTL. Signed-off-by: Radim Krčmář Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20250515143723.2450630-5-rkrcmar@ventanamicro.com Signed-off-by: Anup Patel --- Documentation/virt/kvm/api.rst | 11 +++++++++++ arch/riscv/include/asm/kvm_host.h | 3 +++ arch/riscv/include/asm/kvm_vcpu_sbi.h | 1 + arch/riscv/kvm/vcpu.c | 27 ++++++++++++++------------- arch/riscv/kvm/vcpu_sbi.c | 17 +++++++++++++++++ arch/riscv/kvm/vm.c | 13 +++++++++++++ include/uapi/linux/kvm.h | 1 + 7 files changed, 60 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 47c7c3f92314..e107694fb41f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8496,6 +8496,17 @@ aforementioned registers before the first KVM_RUN. These registers are VM scoped, meaning that the same set of values are presented on all vCPUs in a given VM. +7.43 KVM_CAP_RISCV_MP_STATE_RESET +--------------------------------- + +:Architectures: riscv +:Type: VM +:Parameters: None +:Returns: 0 on success, -EINVAL if arg[0] is not zero + +When this capability is enabled, KVM resets the VCPU when setting +MP_STATE_INIT_RECEIVED through IOCTL. The original MP_STATE is preserved. + 8. Other capabilities. ====================== diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index f673ebfdadf3..85cfebc32e4c 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -119,6 +119,9 @@ struct kvm_arch { /* AIA Guest/VM context */ struct kvm_aia aia; + + /* KVM_CAP_RISCV_MP_STATE_RESET */ + bool mp_state_reset; }; struct kvm_cpu_trap { diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index da28235939d1..439ab2b3534f 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -57,6 +57,7 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, u32 type, u64 flags); void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, unsigned long pc, unsigned long a1); +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a7188e007db9..e0a01af426ff 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -51,11 +51,11 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu) +static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, + bool kvm_sbi_reset) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; - struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state; void *vector_datap = cntx->vector.datap; memset(cntx, 0, sizeof(*cntx)); @@ -65,13 +65,8 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu) /* Restore datap as it's not a part of the guest context. */ cntx->vector.datap = vector_datap; - /* Load SBI reset values */ - cntx->a0 = vcpu->vcpu_id; - - spin_lock(&reset_state->lock); - cntx->sepc = reset_state->pc; - cntx->a1 = reset_state->a1; - spin_unlock(&reset_state->lock); + if (kvm_sbi_reset) + kvm_riscv_vcpu_sbi_load_reset_state(vcpu); /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ cntx->sstatus = SR_SPP | SR_SPIE; @@ -81,7 +76,7 @@ static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu) cntx->hstatus |= HSTATUS_SPV; } -static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) +static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) { bool loaded; @@ -97,7 +92,7 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.last_exit_cpu = -1; - kvm_riscv_vcpu_context_reset(vcpu); + kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset); kvm_riscv_vcpu_fp_reset(vcpu); @@ -174,7 +169,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_sbi_init(vcpu); /* Reset VCPU */ - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, false); return 0; } @@ -523,6 +518,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, case KVM_MP_STATE_STOPPED: __kvm_riscv_vcpu_power_off(vcpu); break; + case KVM_MP_STATE_INIT_RECEIVED: + if (vcpu->kvm->arch.mp_state_reset) + kvm_riscv_reset_vcpu(vcpu, false); + else + ret = -EINVAL; + break; default: ret = -EINVAL; } @@ -711,7 +712,7 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, true); if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) kvm_riscv_gstage_update_hgatp(vcpu); diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 0afef0bb261d..31fd3cc98d66 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -167,6 +167,23 @@ void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); } +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state; + + cntx->a0 = vcpu->vcpu_id; + + spin_lock(&vcpu->arch.reset_state.lock); + cntx->sepc = reset_state->pc; + cntx->a1 = reset_state->a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + cntx->sstatus &= ~SR_SIE; + csr->vsatp = 0; +} + int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7396b8654f45..b27ec8f96697 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -209,6 +209,19 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) +{ + switch (cap->cap) { + case KVM_CAP_RISCV_MP_STATE_RESET: + if (cap->flags) + return -EINVAL; + kvm->arch.mp_state_reset = true; + return 0; + default: + return -EINVAL; + } +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b6ae8ad8934b..454b7d4a0448 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -930,6 +930,7 @@ struct kvm_enable_cap { #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 #define KVM_CAP_X86_GUEST_MODE 238 #define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_RISCV_MP_STATE_RESET 240 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 0bf2d838de1ffb6d0bb6f8d18a6ccc59b7d9a705 Mon Sep 17 00:00:00 2001 From: Wang Yaxin Date: Sat, 10 May 2025 15:54:13 +0800 Subject: taskstats: fix struct taskstats breaks backward compatibility since version 15 Problem ======== commit 658eb5ab916d ("delayacct: add delay max to record delay peak") - adding more fields commit f65c64f311ee ("delayacct: add delay min to record delay peak") - adding more fields commit b016d0873777 ("taskstats: modify taskstats version") - version bump to 15 Since version 15 (TASKSTATS_VERSION=15) the new layout of the structure adds fields in the middle of the structure, rendering all old software incompatible with newer kernels and software compiled against the new kernel headers incompatible with older kernels. Solution ========= move delay max and delay min to the end of taskstat, and bump the version to 16 after the change [wang.yaxin@zte.com.cn: adjust indentation] Link: https://lkml.kernel.org/r/202505192131489882NSciXV4EGd8zzjLuwoOK@zte.com.cn Link: https://lkml.kernel.org/r/20250510155413259V4JNRXxukdDgzsaL0Fo6a@zte.com.cn Fixes: f65c64f311ee ("delayacct: add delay min to record delay peak") Signed-off-by: Wang Yaxin Signed-off-by: xu xin Signed-off-by: Kun Jiang Reviewed-by: Yang Yang Cc: Balbir Singh Cc: Signed-off-by: Andrew Morton --- include/uapi/linux/taskstats.h | 47 ++++++++++++++++++++++++++---------------- 1 file changed, 29 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 95762232e018..5929030d4e8b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 15 +#define TASKSTATS_VERSION 16 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -72,8 +72,6 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; - __u64 cpu_delay_max; - __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -82,14 +80,10 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; - __u64 blkio_delay_max; - __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; - __u64 swapin_delay_max; - __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -172,14 +166,11 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; - __u64 freepages_delay_max; - __u64 freepages_delay_min; + /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; - __u64 thrashing_delay_max; - __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -187,8 +178,6 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; - __u64 compact_delay_max; - __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -210,15 +199,37 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; - __u64 wpcopy_delay_max; - __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; - __u64 irq_delay_max; - __u64 irq_delay_min; - /* v15: add Delay max */ + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; }; -- cgit v1.2.3 From 80fa7a03378588582eb40f89b6f418c0c256cf24 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 20 May 2025 13:16:43 -0400 Subject: vt: bracketed paste support This is comprised of 3 aspects: - Take note of when applications advertise bracketed paste support via "\e[?2004h" and "\e[?2004l". - Insert bracketed paste markers ("\e[200~" and "\e[201~") around pasted content in paste_selection() when bracketed paste is active. - Add TIOCL_GETBRACKETEDPASTE to return bracketed paste status so user space daemons implementing cut-and-paste functionality (e.g. gpm, BRLTTY) may know when to insert bracketed paste markers. Link: https://en.wikipedia.org/wiki/Bracketed-paste Signed-off-by: Nicolas Pitre Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20250520171851.1219676-2-nico@fluxnic.net Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/selection.c | 31 +++++++++++++++++++++++++++---- drivers/tty/vt/vt.c | 15 +++++++++++++++ include/linux/console_struct.h | 1 + include/uapi/linux/tiocl.h | 1 + 4 files changed, 44 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 791e2f1f7c0b..24b0a53e5a79 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -403,6 +403,12 @@ int paste_selection(struct tty_struct *tty) DECLARE_WAITQUEUE(wait, current); int ret = 0; + bool bp = vc->vc_bracketed_paste; + static const char bracketed_paste_start[] = "\033[200~"; + static const char bracketed_paste_end[] = "\033[201~"; + const char *bps = bp ? bracketed_paste_start : NULL; + const char *bpe = bp ? bracketed_paste_end : NULL; + console_lock(); poke_blanked_console(); console_unlock(); @@ -414,7 +420,7 @@ int paste_selection(struct tty_struct *tty) add_wait_queue(&vc->paste_wait, &wait); mutex_lock(&vc_sel.lock); - while (vc_sel.buffer && vc_sel.buf_len > pasted) { + while (vc_sel.buffer && (vc_sel.buf_len > pasted || bpe)) { set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) { ret = -EINTR; @@ -427,10 +433,27 @@ int paste_selection(struct tty_struct *tty) continue; } __set_current_state(TASK_RUNNING); + + if (bps) { + bps += tty_ldisc_receive_buf(ld, bps, NULL, strlen(bps)); + if (*bps != '\0') + continue; + bps = NULL; + } + count = vc_sel.buf_len - pasted; - count = tty_ldisc_receive_buf(ld, vc_sel.buffer + pasted, NULL, - count); - pasted += count; + if (count) { + pasted += tty_ldisc_receive_buf(ld, vc_sel.buffer + pasted, + NULL, count); + if (vc_sel.buf_len > pasted) + continue; + } + + if (bpe) { + bpe += tty_ldisc_receive_buf(ld, bpe, NULL, strlen(bpe)); + if (*bpe == '\0') + bpe = NULL; + } } mutex_unlock(&vc_sel.lock); remove_wait_queue(&vc->paste_wait, &wait); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index efb761454166..ed39d9cb4432 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1870,6 +1870,14 @@ int mouse_reporting(void) return vc_cons[fg_console].d->vc_report_mouse; } +/* invoked via ioctl(TIOCLINUX) */ +static int get_bracketed_paste(struct tty_struct *tty) +{ + struct vc_data *vc = tty->driver_data; + + return vc->vc_bracketed_paste; +} + enum { CSI_DEC_hl_CURSOR_KEYS = 1, /* CKM: cursor keys send ^[Ox/^[[x */ CSI_DEC_hl_132_COLUMNS = 3, /* COLM: 80/132 mode switch */ @@ -1880,6 +1888,7 @@ enum { CSI_DEC_hl_MOUSE_X10 = 9, CSI_DEC_hl_SHOW_CURSOR = 25, /* TCEM */ CSI_DEC_hl_MOUSE_VT200 = 1000, + CSI_DEC_hl_BRACKETED_PASTE = 2004, }; /* console_lock is held */ @@ -1932,6 +1941,9 @@ static void csi_DEC_hl(struct vc_data *vc, bool on_off) case CSI_DEC_hl_MOUSE_VT200: vc->vc_report_mouse = on_off ? 2 : 0; break; + case CSI_DEC_hl_BRACKETED_PASTE: + vc->vc_bracketed_paste = on_off; + break; } } @@ -2157,6 +2169,7 @@ static void reset_terminal(struct vc_data *vc, int do_clear) vc->state.charset = 0; vc->vc_need_wrap = 0; vc->vc_report_mouse = 0; + vc->vc_bracketed_paste = 0; vc->vc_utf = default_utf8; vc->vc_utf_count = 0; @@ -3483,6 +3496,8 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) break; case TIOCL_BLANKEDSCREEN: return console_blanked; + case TIOCL_GETBRACKETEDPASTE: + return get_bracketed_paste(tty); default: return -EINVAL; } diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 20f564e98552..59b4fec5f254 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -145,6 +145,7 @@ struct vc_data { unsigned int vc_need_wrap : 1; unsigned int vc_can_do_color : 1; unsigned int vc_report_mouse : 2; + unsigned int vc_bracketed_paste : 1; unsigned char vc_utf : 1; /* Unicode UTF-8 encoding */ unsigned char vc_utf_count; int vc_utf_char; diff --git a/include/uapi/linux/tiocl.h b/include/uapi/linux/tiocl.h index b32acc229024..88faba506c3d 100644 --- a/include/uapi/linux/tiocl.h +++ b/include/uapi/linux/tiocl.h @@ -36,5 +36,6 @@ struct tiocl_selection { #define TIOCL_BLANKSCREEN 14 /* keep screen blank even if a key is pressed */ #define TIOCL_BLANKEDSCREEN 15 /* return which vt was blanked */ #define TIOCL_GETKMSGREDIRECT 17 /* get the vt the kernel messages are restricted to */ +#define TIOCL_GETBRACKETEDPASTE 18 /* get whether paste may be bracketed */ #endif /* _LINUX_TIOCL_H */ -- cgit v1.2.3 From 81cf4d7d2379df853a0cbb8486286783c7380ac3 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 20 May 2025 13:16:44 -0400 Subject: vt: add VT_GETCONSIZECSRPOS to retrieve console size and cursor position The console dimension and cursor position are available through the /dev/vcsa interface already. However the /dev/vcsa header format uses single-byte fields therefore those values are clamped to 255. As surprizing as this may seem, some people do use 240-column 67-row screens (a 1920x1080 monitor with 8x16 pixel fonts) which is getting close to the limit. Monitors with higher resolution are not uncommon these days (3840x2160 producing a 480x135 character display) and it is just a matter of time before someone with, say, a braille display using the Linux VT console and BRLTTY on such a screen reports a bug about missing and oddly misaligned screen content. Let's add VT_GETCONSIZECSRPOS for the retrieval of console size and cursor position without byte-sized limitations. The actual console size limit as encoded in vt.c is 32767x32767 so using a short here is appropriate. Then this can be used to get the cursor position when /dev/vcsa reports 255. The screen dimension may already be obtained using TIOCGWINSZ and adding the same information to VT_GETCONSIZECSRPOS might be redundant. However applications that care about cursor position also care about display size and having 2 separate system calls to obtain them separately is wasteful. Also, the cursor position can be queried by writing "\e[6n" to a tty and reading back the result but that may be done only by the actual application using that tty and not a sideline observer. Signed-off-by: Nicolas Pitre Link: https://lore.kernel.org/r/20250520171851.1219676-3-nico@fluxnic.net Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt_ioctl.c | 16 ++++++++++++++++ include/uapi/linux/vt.h | 11 +++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 1f2bdd2e1cc5..61342e06970a 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -951,6 +951,22 @@ int vt_ioctl(struct tty_struct *tty, (unsigned short __user *)arg); case VT_WAITEVENT: return vt_event_wait_ioctl((struct vt_event __user *)arg); + + case VT_GETCONSIZECSRPOS: + { + struct vt_consizecsrpos concsr; + + console_lock(); + concsr.con_cols = vc->vc_cols; + concsr.con_rows = vc->vc_rows; + concsr.csr_col = vc->state.x; + concsr.csr_row = vc->state.y; + console_unlock(); + if (copy_to_user(up, &concsr, sizeof(concsr))) + return -EFAULT; + return 0; + } + default: return -ENOIOCTLCMD; } diff --git a/include/uapi/linux/vt.h b/include/uapi/linux/vt.h index e9d39c48520a..e5b0c492aa18 100644 --- a/include/uapi/linux/vt.h +++ b/include/uapi/linux/vt.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_VT_H #define _UAPI_LINUX_VT_H +#include +#include /* * These constants are also useful for user-level apps (e.g., VC @@ -84,4 +86,13 @@ struct vt_setactivate { #define VT_SETACTIVATE 0x560F /* Activate and set the mode of a console */ +/* get console size and cursor position */ +struct vt_consizecsrpos { + __u16 con_rows; /* number of console rows */ + __u16 con_cols; /* number of console columns */ + __u16 csr_row; /* current cursor's row */ + __u16 csr_col; /* current cursor's column */ +}; +#define VT_GETCONSIZECSRPOS _IOR('V', 0x10, struct vt_consizecsrpos) + #endif /* _UAPI_LINUX_VT_H */ -- cgit v1.2.3 From 1d8db6fd698de1f73b1a7d72aea578fdd18d9a87 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 16 May 2025 13:25:32 +0200 Subject: pidfs, coredump: add PIDFD_INFO_COREDUMP Extend the PIDFD_INFO_COREDUMP ioctl() with the new PIDFD_INFO_COREDUMP mask flag. This adds the @coredump_mask field to struct pidfd_info. When a task coredumps the kernel will provide the following information to userspace in @coredump_mask: * PIDFD_COREDUMPED is raised if the task did actually coredump. * PIDFD_COREDUMP_SKIP is raised if the task skipped coredumping (e.g., undumpable). * PIDFD_COREDUMP_USER is raised if this is a regular coredump and doesn't need special care by the coredump server. * PIDFD_COREDUMP_ROOT is raised if the generated coredump should be treated as sensitive and the coredump server should restrict to the generated coredump to sufficiently privileged users. The kernel guarantees that by the time the connection is made the all PIDFD_INFO_COREDUMP info is available. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-5-664f3caf2516@kernel.org Acked-by: Luca Boccassi Reviewed-by: Alexander Mikhalitsyn Reviewed-by: Jann Horn Signed-off-by: Christian Brauner --- fs/coredump.c | 31 ++++++++++++++++++++++++++ fs/pidfs.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pidfs.h | 5 +++++ include/uapi/linux/pidfd.h | 16 ++++++++++++++ 4 files changed, 107 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/coredump.c b/fs/coredump.c index af4aa57353ba..b0ee99992ea5 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -46,7 +46,9 @@ #include #include #include +#include #include +#include #include #include @@ -599,6 +601,8 @@ static int umh_coredump_setup(struct subprocess_info *info, struct cred *new) if (IS_ERR(pidfs_file)) return PTR_ERR(pidfs_file); + pidfs_coredump(cp); + /* * Usermode helpers are childen of either * system_unbound_wq or of kthreadd. So we know that @@ -875,8 +879,31 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (IS_ERR(file)) goto close_fail; + /* + * Set the thread-group leader pid which is used for the + * peer credentials during connect() below. Then + * immediately register it in pidfs... + */ + cprm.pid = task_tgid(current); + retval = pidfs_register_pid(cprm.pid); + if (retval) + goto close_fail; + + /* + * ... and set the coredump information so userspace + * has it available after connect()... + */ + pidfs_coredump(&cprm); + retval = kernel_connect(socket, (struct sockaddr *)(&addr), addr_len, O_NONBLOCK | SOCK_COREDUMP); + + /* + * ... Make sure to only put our reference after connect() took + * its own reference keeping the pidfs entry alive ... + */ + pidfs_put_pid(cprm.pid); + if (retval) { if (retval == -EAGAIN) coredump_report_failure("Coredump socket %s receive queue full", addr.sun_path); @@ -885,6 +912,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto close_fail; } + /* ... and validate that @sk_peer_pid matches @cprm.pid. */ + if (WARN_ON_ONCE(unix_peer(socket->sk)->sk_peer_pid != cprm.pid)) + goto close_fail; + cprm.limit = RLIM_INFINITY; cprm.file = no_free_ptr(file); #else diff --git a/fs/pidfs.c b/fs/pidfs.c index 3b39e471840b..c0069fd52dd4 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "internal.h" #include "mount.h" @@ -33,6 +34,7 @@ static struct kmem_cache *pidfs_cachep __ro_after_init; struct pidfs_exit_info { __u64 cgroupid; __s32 exit_code; + __u32 coredump_mask; }; struct pidfs_inode { @@ -240,6 +242,22 @@ static inline bool pid_in_current_pidns(const struct pid *pid) return false; } +static __u32 pidfs_coredump_mask(unsigned long mm_flags) +{ + switch (__get_dumpable(mm_flags)) { + case SUID_DUMP_USER: + return PIDFD_COREDUMP_USER; + case SUID_DUMP_ROOT: + return PIDFD_COREDUMP_ROOT; + case SUID_DUMP_DISABLE: + return PIDFD_COREDUMP_SKIP; + default: + WARN_ON_ONCE(true); + } + + return 0; +} + static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) { struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg; @@ -280,6 +298,11 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) } } + if (mask & PIDFD_INFO_COREDUMP) { + kinfo.mask |= PIDFD_INFO_COREDUMP; + kinfo.coredump_mask = READ_ONCE(pidfs_i(inode)->__pei.coredump_mask); + } + task = get_pid_task(pid, PIDTYPE_PID); if (!task) { /* @@ -296,6 +319,13 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) if (!c) return -ESRCH; + if (!(kinfo.mask & PIDFD_INFO_COREDUMP)) { + task_lock(task); + if (task->mm) + kinfo.coredump_mask = pidfs_coredump_mask(task->mm->flags); + task_unlock(task); + } + /* Unconditionally return identifiers and credentials, the rest only on request */ user_ns = current_user_ns(); @@ -559,6 +589,31 @@ void pidfs_exit(struct task_struct *tsk) } } +#ifdef CONFIG_COREDUMP +void pidfs_coredump(const struct coredump_params *cprm) +{ + struct pid *pid = cprm->pid; + struct pidfs_exit_info *exit_info; + struct dentry *dentry; + struct inode *inode; + __u32 coredump_mask = 0; + + dentry = pid->stashed; + if (WARN_ON_ONCE(!dentry)) + return; + + inode = d_inode(dentry); + exit_info = &pidfs_i(inode)->__pei; + /* Note how we were coredumped. */ + coredump_mask = pidfs_coredump_mask(cprm->mm_flags); + /* Note that we actually did coredump. */ + coredump_mask |= PIDFD_COREDUMPED; + /* If coredumping is set to skip we should never end up here. */ + VFS_WARN_ON_ONCE(coredump_mask & PIDFD_COREDUMP_SKIP); + smp_store_release(&exit_info->coredump_mask, coredump_mask); +} +#endif + static struct vfsmount *pidfs_mnt __ro_after_init; /* diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 2676890c4d0d..77e7db194914 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,11 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +struct coredump_params; + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); void pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); void pidfs_exit(struct task_struct *tsk); +#ifdef CONFIG_COREDUMP +void pidfs_coredump(const struct coredump_params *cprm); +#endif extern const struct dentry_operations pidfs_dentry_operations; int pidfs_register_pid(struct pid *pid); void pidfs_get_pid(struct pid *pid); diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 8c1511edd0e9..c27a4e238e4b 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -25,9 +25,23 @@ #define PIDFD_INFO_CREDS (1UL << 1) /* Always returned, even if not requested */ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ +#define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ +/* + * Values for @coredump_mask in pidfd_info. + * Only valid if PIDFD_INFO_COREDUMP is set in @mask. + * + * Note, the @PIDFD_COREDUMP_ROOT flag indicates that the generated + * coredump should be treated as sensitive and access should only be + * granted to privileged users. + */ +#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */ +#define PIDFD_COREDUMP_SKIP (1U << 1) /* coredumping generation was skipped. */ +#define PIDFD_COREDUMP_USER (1U << 2) /* coredump was done as the user. */ +#define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ + /* * The concept of process and threads in userland and the kernel is a confusing * one - within the kernel every thread is a 'task' with its own individual PID, @@ -92,6 +106,8 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; + __u32 coredump_mask; + __u32 __spare1; }; #define PIDFS_IOCTL_MAGIC 0xFF -- cgit v1.2.3 From 8b8762eeec59b959fbca60afffe21265bce67168 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 20 May 2025 09:19:05 -0700 Subject: tools: ynl-gen: add makefile deps for neigh Kory is reporting build issues after recent additions to YNL if the system headers are old. Link: https://lore.kernel.org/20250519164949.597d6e92@kmaincent-XPS-13-7390 Reported-by: Kory Maincent Fixes: 0939a418b3b0 ("tools: ynl: submsg: reverse parse / error reporting") Tested-by: Kory Maincent Link: https://patch.msgid.link/20250520161916.413298-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/neighbour.h | 4 ++-- tools/net/ynl/Makefile.deps | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 5e67a7eaf4a7..b851c36ad25d 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_NEIGHBOUR_H -#define __LINUX_NEIGHBOUR_H +#ifndef _UAPI__LINUX_NEIGHBOUR_H +#define _UAPI__LINUX_NEIGHBOUR_H #include #include diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index e5a5cb1b2cff..8c378356fc87 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -35,7 +35,8 @@ CFLAGS_rt-addr:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \ $(call get_hdr_inc,__LINUX_IF_ADDR_H,if_addr.h) CFLAGS_rt-link:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \ $(call get_hdr_inc,_LINUX_IF_LINK_H,if_link.h) -CFLAGS_rt-neigh:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) +CFLAGS_rt-neigh:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \ + $(call get_hdr_inc,__LINUX_NEIGHBOUR_H,neighbour.h) CFLAGS_rt-route:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) CFLAGS_rt-rule:=$(call get_hdr_inc,__LINUX_FIB_RULES_H,fib_rules.h) CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h) -- cgit v1.2.3 From f4b18ff2c147d3b56384fcc8adb30bf733bf2300 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 21 May 2025 15:15:28 -0700 Subject: perf/uapi: Fix PERF_RECORD_SAMPLE comments in AAUX data for PERF_SAMPLE_AUX appears last. PERF_SAMPLE_CGROUP is missing from the comment. This makes the comment match that in the perf_event_open man page. Signed-off-by: Ian Rogers Signed-off-by: Ingo Molnar Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-perf-users@vger.kernel.org Link: https://lore.kernel.org/r/20250521221529.2547099-1-irogers@google.com --- include/uapi/linux/perf_event.h | 5 +++-- tools/include/uapi/linux/perf_event.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 5fc753c23734..b2722dae6f1e 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1035,10 +1035,11 @@ enum perf_event_type { * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR - * { u64 size; - * char data[size]; } && PERF_SAMPLE_AUX + * { u64 cgroup;} && PERF_SAMPLE_CGROUP * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX * }; */ PERF_RECORD_SAMPLE = 9, diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 5fc753c23734..b2722dae6f1e 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1035,10 +1035,11 @@ enum perf_event_type { * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR - * { u64 size; - * char data[size]; } && PERF_SAMPLE_AUX + * { u64 cgroup;} && PERF_SAMPLE_CGROUP * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX * }; */ PERF_RECORD_SAMPLE = 9, -- cgit v1.2.3 From 44889ff67cee7b9ee2d305690ce7a5488b137a66 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 22 May 2025 09:51:22 +0200 Subject: perf/uapi: Clean up a bit When applying a recent commit to the header I noticed that we have accumulated quite a bit of historic noise in this header, so do a bit of spring cleaning: - Define bitfields in a vertically aligned fashion, like perf_event_mmap_page::capabilities already does. This makes it easier to see the distribution and sizing of bits within a word, at a glance. The following is much more readable: __u64 cap_bit0 : 1, cap_bit0_is_deprecated : 1, cap_user_rdpmc : 1, cap_user_time : 1, cap_user_time_zero : 1, cap_user_time_short : 1, cap_____res : 58; Than: __u64 cap_bit0:1, cap_bit0_is_deprecated:1, cap_user_rdpmc:1, cap_user_time:1, cap_user_time_zero:1, cap_user_time_short:1, cap_____res:58; So convert all bitfield definitions from the latter style to the former style. - Fix typos and grammar - Fix capitalization - Remove whitespace noise - Harmonize the definitions of various generations and groups of PERF_MEM_ ABI values. - Vertically align all definitions and assignments to the same column (48), as the first definition (enum perf_type_id), throughout the entire header. - And in general make the code and comments to be more in sync with each other and to be more readable overall. No change in functionality. Copy the changes over to tools/include/uapi/linux/perf_event.h. Signed-off-by: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Ian Rogers Link: https://lore.kernel.org/r/20250521221529.2547099-1-irogers@google.com --- include/uapi/linux/perf_event.h | 652 +++++++++++++++++----------------- tools/include/uapi/linux/perf_event.h | 652 +++++++++++++++++----------------- 2 files changed, 662 insertions(+), 642 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b2722dae6f1e..78a362b80027 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -39,18 +39,21 @@ enum perf_type_id { /* * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA * AA: hardware event ID * EEEEEEEE: PMU type ID + * * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB * BB: hardware cache ID * CC: hardware cache op ID * DD: hardware cache op result ID * EEEEEEEE: PMU type ID - * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + * + * If the PMU type ID is 0, PERF_TYPE_RAW will be applied. */ -#define PERF_PMU_TYPE_SHIFT 32 -#define PERF_HW_EVENT_MASK 0xffffffff +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff /* * Generalized performance event event_id types, used by the @@ -112,7 +115,7 @@ enum perf_hw_cache_op_result_id { /* * Special "software" events provided by the kernel, even if the hardware * does not support performance events. These events measure various - * physical and sw events of the kernel (and allow the profiling of them as + * physical and SW events of the kernel (and allow the profiling of them as * well): */ enum perf_sw_ids { @@ -167,8 +170,9 @@ enum perf_event_sample_format { }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) + /* - * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * Values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set. * * If the user does not pass priv level information via branch_sample_type, * the kernel uses the event's priv level. Branch and event priv levels do @@ -178,20 +182,20 @@ enum perf_event_sample_format { * of branches and therefore it supersedes all the other types. */ enum perf_branch_sample_type_shift { - PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ - PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ - PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ - - PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ - PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ - PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ - PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ - PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ - PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ - PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ - PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* CALL/RET stack */ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ @@ -210,96 +214,95 @@ enum perf_branch_sample_type_shift { }; enum perf_branch_sample_type { - PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, - PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, - PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, - PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, - PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, - PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, - PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, - PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, - PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, - PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, - PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, - PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, - PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, - PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, - PERF_SAMPLE_BRANCH_TYPE_SAVE = - 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, - PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, - PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; /* - * Common flow change classification + * Common control flow change classifications: */ enum { - PERF_BR_UNKNOWN = 0, /* unknown */ - PERF_BR_COND = 1, /* conditional */ - PERF_BR_UNCOND = 2, /* unconditional */ - PERF_BR_IND = 3, /* indirect */ - PERF_BR_CALL = 4, /* function call */ - PERF_BR_IND_CALL = 5, /* indirect function call */ - PERF_BR_RET = 6, /* function return */ - PERF_BR_SYSCALL = 7, /* syscall */ - PERF_BR_SYSRET = 8, /* syscall return */ - PERF_BR_COND_CALL = 9, /* conditional function call */ - PERF_BR_COND_RET = 10, /* conditional function return */ - PERF_BR_ERET = 11, /* exception return */ - PERF_BR_IRQ = 12, /* irq */ - PERF_BR_SERROR = 13, /* system error */ - PERF_BR_NO_TX = 14, /* not in transaction */ - PERF_BR_EXTEND_ABI = 15, /* extend ABI */ + PERF_BR_UNKNOWN = 0, /* Unknown */ + PERF_BR_COND = 1, /* Conditional */ + PERF_BR_UNCOND = 2, /* Unconditional */ + PERF_BR_IND = 3, /* Indirect */ + PERF_BR_CALL = 4, /* Function call */ + PERF_BR_IND_CALL = 5, /* Indirect function call */ + PERF_BR_RET = 6, /* Function return */ + PERF_BR_SYSCALL = 7, /* Syscall */ + PERF_BR_SYSRET = 8, /* Syscall return */ + PERF_BR_COND_CALL = 9, /* Conditional function call */ + PERF_BR_COND_RET = 10, /* Conditional function return */ + PERF_BR_ERET = 11, /* Exception return */ + PERF_BR_IRQ = 12, /* IRQ */ + PERF_BR_SERROR = 13, /* System error */ + PERF_BR_NO_TX = 14, /* Not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* Extend ABI */ PERF_BR_MAX, }; /* - * Common branch speculation outcome classification + * Common branch speculation outcome classifications: */ enum { - PERF_BR_SPEC_NA = 0, /* Not available */ - PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ - PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ - PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ PERF_BR_SPEC_MAX, }; enum { - PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ - PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ - PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ - PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ - PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ - PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ - PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ - PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ PERF_BR_NEW_MAX, }; enum { - PERF_BR_PRIV_UNKNOWN = 0, - PERF_BR_PRIV_USER = 1, - PERF_BR_PRIV_KERNEL = 2, - PERF_BR_PRIV_HV = 3, + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, }; -#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 -#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 -#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 -#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 -#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ @@ -310,9 +313,9 @@ enum { * Values to determine ABI of the registers dump. */ enum perf_sample_regs_abi { - PERF_SAMPLE_REGS_ABI_NONE = 0, - PERF_SAMPLE_REGS_ABI_32 = 1, - PERF_SAMPLE_REGS_ABI_64 = 2, + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, }; /* @@ -320,21 +323,21 @@ enum perf_sample_regs_abi { * abort events. Multiple bits can be set. */ enum { - PERF_TXN_ELISION = (1 << 0), /* From elision */ - PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ - PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ - PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ - PERF_TXN_RETRY = (1 << 4), /* Retry possible */ - PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ - PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ - PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction is not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ - PERF_TXN_MAX = (1 << 8), /* non-ABI */ + PERF_TXN_MAX = (1 << 8), /* non-ABI */ - /* bits 32..63 are reserved for the abort code */ + /* Bits 32..63 are reserved for the abort code */ - PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), - PERF_TXN_ABORT_SHIFT = 32, + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, }; /* @@ -369,24 +372,22 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; -#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ -#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ -#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ -#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ - /* add: sample_stack_user */ -#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ -#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ -#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ -#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ -#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ +#define PERF_ATTR_SIZE_VER0 64 /* Size of first published 'struct perf_event_attr' */ +#define PERF_ATTR_SIZE_VER1 72 /* Add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* Add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* Add: sample_regs_user */ + /* Add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* Add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* Add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ /* - * Hardware event_id to monitor via a performance monitoring event: - * - * @sample_max_stack: Max number of frame pointers in a callchain, - * should be < /proc/sys/kernel/perf_event_max_stack - * Max number of entries of branch stack - * should be < hardware limit + * 'struct perf_event_attr' contains various attributes that define + * a performance event - most of them hardware related configuration + * details, but also a lot of behavioral switches and values implemented + * by the kernel. */ struct perf_event_attr { @@ -396,7 +397,7 @@ struct perf_event_attr { __u32 type; /* - * Size of the attr structure, for fwd/bwd compat. + * Size of the attr structure, for forward/backwards compatibility. */ __u32 size; @@ -451,21 +452,21 @@ struct perf_event_attr { comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ - write_backward : 1, /* Write ring buffer from end to beginning */ + write_backward : 1, /* write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - bpf_event : 1, /* include bpf events */ + bpf_event : 1, /* include BPF events */ aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - build_id : 1, /* use build id in mmap2 events */ + build_id : 1, /* use build ID in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ __reserved_1 : 26; union { - __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_events; /* wake up every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; @@ -474,13 +475,13 @@ struct perf_event_attr { __u64 bp_addr; __u64 kprobe_func; /* for perf_kprobe */ __u64 uprobe_path; /* for perf_uprobe */ - __u64 config1; /* extension of config */ + __u64 config1; /* extension of config */ }; union { __u64 bp_len; - __u64 kprobe_addr; /* when kprobe_func == NULL */ + __u64 kprobe_addr; /* when kprobe_func == NULL */ __u64 probe_offset; /* for perf_[k,u]probe */ - __u64 config2; /* extension of config1 */ + __u64 config2; /* extension of config1 */ }; __u64 branch_sample_type; /* enum perf_branch_sample_type */ @@ -510,7 +511,16 @@ struct perf_event_attr { * Wakeup watermark for AUX area */ __u32 aux_watermark; + + /* + * Max number of frame pointers in a callchain, should be + * lower than /proc/sys/kernel/perf_event_max_stack. + * + * Max number of entries of branch stack should be lower + * than the hardware limit. + */ __u16 sample_max_stack; + __u16 __reserved_2; __u32 aux_sample_size; @@ -537,7 +547,7 @@ struct perf_event_attr { /* * Structure used by below PERF_EVENT_IOC_QUERY_BPF command - * to query bpf programs attached to the same perf tracepoint + * to query BPF programs attached to the same perf tracepoint * as the given perf event. */ struct perf_event_query_bpf { @@ -559,21 +569,21 @@ struct perf_event_query_bpf { /* * Ioctls that can be done on a perf event fd: */ -#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) -#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) -#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) -#define PERF_EVENT_IOC_RESET _IO ('$', 3) -#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) -#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) -#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) -#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) -#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) -#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW ('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW ('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR ('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW ('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW ('$', 9, __u32) #define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) -#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *) +#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW ('$', 11, struct perf_event_attr *) enum perf_event_ioc_flags { - PERF_IOC_FLAG_GROUP = 1U << 0, + PERF_IOC_FLAG_GROUP = 1U << 0, }; /* @@ -584,7 +594,7 @@ struct perf_event_mmap_page { __u32 compat_version; /* lowest version this is compat with */ /* - * Bits needed to read the hw events in user-space. + * Bits needed to read the HW events in user-space. * * u32 seq, time_mult, time_shift, index, width; * u64 count, enabled, running; @@ -622,7 +632,7 @@ struct perf_event_mmap_page { __u32 index; /* hardware event identifier */ __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ - __u64 time_running; /* time event on cpu */ + __u64 time_running; /* time event on CPU */ union { __u64 capabilities; struct { @@ -650,7 +660,7 @@ struct perf_event_mmap_page { /* * If cap_usr_time the below fields can be used to compute the time - * delta since time_enabled (in ns) using rdtsc or similar. + * delta since time_enabled (in ns) using RDTSC or similar. * * u64 quot, rem; * u64 delta; @@ -723,7 +733,7 @@ struct perf_event_mmap_page { * after reading this value. * * When the mapping is PROT_WRITE the @data_tail value should be - * written by userspace to reflect the last read data, after issueing + * written by user-space to reflect the last read data, after issuing * an smp_mb() to separate the data read from the ->data_tail store. * In this case the kernel will not over-write unread data. * @@ -739,7 +749,7 @@ struct perf_event_mmap_page { /* * AUX area is defined by aux_{offset,size} fields that should be set - * by the userspace, so that + * by the user-space, so that * * aux_offset >= data_offset + data_size * @@ -813,7 +823,7 @@ struct perf_event_mmap_page { * Indicates that thread was preempted in TASK_RUNNING state. * * PERF_RECORD_MISC_MMAP_BUILD_ID: - * Indicates that mmap2 event carries build id data. + * Indicates that mmap2 event carries build ID data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) @@ -824,26 +834,26 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) struct perf_event_header { - __u32 type; - __u16 misc; - __u16 size; + __u32 type; + __u16 misc; + __u16 size; }; struct perf_ns_link_info { - __u64 dev; - __u64 ino; + __u64 dev; + __u64 ino; }; enum { - NET_NS_INDEX = 0, - UTS_NS_INDEX = 1, - IPC_NS_INDEX = 2, - PID_NS_INDEX = 3, - USER_NS_INDEX = 4, - MNT_NS_INDEX = 5, - CGROUP_NS_INDEX = 6, - - NR_NAMESPACES, /* number of available namespaces */ + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ }; enum perf_event_type { @@ -859,11 +869,11 @@ enum perf_event_type { * optional fields being ignored. * * struct sample_id { - * { u32 pid, tid; } && PERF_SAMPLE_TID - * { u64 time; } && PERF_SAMPLE_TIME - * { u64 id; } && PERF_SAMPLE_ID - * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID - * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 id; } && PERF_SAMPLE_IDENTIFIER * } && perf_event_attr::sample_id_all * @@ -874,7 +884,7 @@ enum perf_event_type { /* * The MMAP events record the PROT_EXEC mappings so that we can - * correlate userspace IPs to code. They have the following structure: + * correlate user-space IPs to code. They have the following structure: * * struct { * struct perf_event_header header; @@ -884,7 +894,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -894,7 +904,7 @@ enum perf_event_type { * struct perf_event_header header; * u64 id; * u64 lost; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_LOST = 2, @@ -905,7 +915,7 @@ enum perf_event_type { * * u32 pid, tid; * char comm[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_COMM = 3, @@ -916,7 +926,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_EXIT = 4, @@ -927,7 +937,7 @@ enum perf_event_type { * u64 time; * u64 id; * u64 stream_id; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_THROTTLE = 5, @@ -939,7 +949,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_FORK = 7, @@ -950,7 +960,7 @@ enum perf_event_type { * u32 pid, tid; * * struct read_format values; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_READ = 8, @@ -1005,12 +1015,12 @@ enum perf_event_type { * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * - * { u64 abi; # enum perf_sample_regs_abi - * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER * - * { u64 size; - * char data[size]; - * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * * { union perf_sample_weight * { @@ -1071,7 +1081,7 @@ enum perf_event_type { * }; * u32 prot, flags; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP2 = 10, @@ -1080,12 +1090,12 @@ enum perf_event_type { * Records that new data landed in the AUX buffer part. * * struct { - * struct perf_event_header header; + * struct perf_event_header header; * - * u64 aux_offset; - * u64 aux_size; + * u64 aux_offset; + * u64 aux_size; * u64 flags; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_AUX = 11, @@ -1168,7 +1178,7 @@ enum perf_event_type { PERF_RECORD_KSYMBOL = 17, /* - * Record bpf events: + * Record BPF events: * enum perf_bpf_event_type { * PERF_BPF_EVENT_UNKNOWN = 0, * PERF_BPF_EVENT_PROG_LOAD = 1, @@ -1246,181 +1256,181 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) enum perf_bpf_event_type { - PERF_BPF_EVENT_UNKNOWN = 0, - PERF_BPF_EVENT_PROG_LOAD = 1, - PERF_BPF_EVENT_PROG_UNLOAD = 2, - PERF_BPF_EVENT_MAX, /* non-ABI */ + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ }; -#define PERF_MAX_STACK_DEPTH 127 -#define PERF_MAX_CONTEXTS_PER_STACK 8 +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 enum perf_callchain_context { - PERF_CONTEXT_HV = (__u64)-32, - PERF_CONTEXT_KERNEL = (__u64)-128, - PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, - PERF_CONTEXT_GUEST = (__u64)-2048, - PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, - PERF_CONTEXT_GUEST_USER = (__u64)-2560, + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, - PERF_CONTEXT_MAX = (__u64)-4095, + PERF_CONTEXT_MAX = (__u64)-4095, }; /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x0001 /* Record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x0002 /* Snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x0004 /* Record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x0008 /* Sample collided with another */ #define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ /* CoreSight PMU AUX buffer formats */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ -#define PERF_FLAG_FD_NO_GROUP (1UL << 0) -#define PERF_FLAG_FD_OUTPUT (1UL << 1) -#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup ID, per-CPU mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ #if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_op:5, /* type of opcode */ - mem_lvl:14, /* memory hierarchy level */ - mem_snoop:5, /* snoop mode */ - mem_lock:2, /* lock instr */ - mem_dtlb:7, /* tlb access */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_remote:1, /* remote */ - mem_snoopx:2, /* snoop mode, ext */ - mem_blk:3, /* access blocked */ - mem_hops:3, /* hop level */ - mem_rsvd:18; + __u64 mem_op : 5, /* Type of opcode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_snoop : 5, /* Snoop mode */ + mem_lock : 2, /* Lock instr */ + mem_dtlb : 7, /* TLB access */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_remote : 1, /* Remote */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_blk : 3, /* Access blocked */ + mem_hops : 3, /* Hop level */ + mem_rsvd : 18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:18, - mem_hops:3, /* hop level */ - mem_blk:3, /* access blocked */ - mem_snoopx:2, /* snoop mode, ext */ - mem_remote:1, /* remote */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_dtlb:7, /* tlb access */ - mem_lock:2, /* lock instr */ - mem_snoop:5, /* snoop mode */ - mem_lvl:14, /* memory hierarchy level */ - mem_op:5; /* type of opcode */ + __u64 mem_rsvd : 18, + mem_hops : 3, /* Hop level */ + mem_blk : 3, /* Access blocked */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_remote : 1, /* Remote */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_dtlb : 7, /* TLB access */ + mem_lock : 2, /* Lock instr */ + mem_snoop : 5, /* Snoop mode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_op : 5; /* Type of opcode */ }; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif -/* type of opcode (load/store/prefetch,code) */ -#define PERF_MEM_OP_NA 0x01 /* not available */ -#define PERF_MEM_OP_LOAD 0x02 /* load instruction */ -#define PERF_MEM_OP_STORE 0x04 /* store instruction */ -#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */ -#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ -#define PERF_MEM_OP_SHIFT 0 +/* Type of memory opcode: */ +#define PERF_MEM_OP_NA 0x0001 /* Not available */ +#define PERF_MEM_OP_LOAD 0x0002 /* Load instruction */ +#define PERF_MEM_OP_STORE 0x0004 /* Store instruction */ +#define PERF_MEM_OP_PFETCH 0x0008 /* Prefetch */ +#define PERF_MEM_OP_EXEC 0x0010 /* Code (execution) */ +#define PERF_MEM_OP_SHIFT 0 /* - * PERF_MEM_LVL_* namespace being depricated to some extent in the + * The PERF_MEM_LVL_* namespace is being deprecated to some extent in * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. - * Supporting this namespace inorder to not break defined ABIs. + * We support this namespace in order to not break defined ABIs. * - * memory hierarchy (memory level, hit or miss) + * Memory hierarchy (memory level, hit or miss) */ -#define PERF_MEM_LVL_NA 0x01 /* not available */ -#define PERF_MEM_LVL_HIT 0x02 /* hit level */ -#define PERF_MEM_LVL_MISS 0x04 /* miss level */ -#define PERF_MEM_LVL_L1 0x08 /* L1 */ -#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ -#define PERF_MEM_LVL_L2 0x20 /* L2 */ -#define PERF_MEM_LVL_L3 0x40 /* L3 */ -#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ -#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ -#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ -#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ -#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ -#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ -#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ -#define PERF_MEM_LVL_SHIFT 5 - -#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ -#define PERF_MEM_REMOTE_SHIFT 37 - -#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ -#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ -#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ -#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ -/* 0x7 available */ -#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ -#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ -#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ -#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ -#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ -#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ - -#define PERF_MEM_LVLNUM_SHIFT 33 - -/* snoop mode */ -#define PERF_MEM_SNOOP_NA 0x01 /* not available */ -#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ -#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */ -#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */ -#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ -#define PERF_MEM_SNOOP_SHIFT 19 - -#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ -#define PERF_MEM_SNOOPX_SHIFT 38 - -/* locked instruction */ -#define PERF_MEM_LOCK_NA 0x01 /* not available */ -#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ -#define PERF_MEM_LOCK_SHIFT 24 +#define PERF_MEM_LVL_NA 0x0001 /* Not available */ +#define PERF_MEM_LVL_HIT 0x0002 /* Hit level */ +#define PERF_MEM_LVL_MISS 0x0004 /* Miss level */ +#define PERF_MEM_LVL_L1 0x0008 /* L1 */ +#define PERF_MEM_LVL_LFB 0x0010 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x0020 /* L2 */ +#define PERF_MEM_LVL_L3 0x0040 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x0080 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x0100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x0200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x0400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x0800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +#define PERF_MEM_REMOTE_REMOTE 0x0001 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x0001 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x0002 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x0003 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ +#define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ +/* 0x007 available */ +#define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x000b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x000c /* LFB / L1 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_RAM 0x000d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x000e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x000f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + +/* Snoop mode */ +#define PERF_MEM_SNOOP_NA 0x0001 /* Not available */ +#define PERF_MEM_SNOOP_NONE 0x0002 /* No snoop */ +#define PERF_MEM_SNOOP_HIT 0x0004 /* Snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x0008 /* Snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x0010 /* Snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +#define PERF_MEM_SNOOPX_FWD 0x0001 /* Forward */ +#define PERF_MEM_SNOOPX_PEER 0x0002 /* Transfer from peer */ +#define PERF_MEM_SNOOPX_SHIFT 38 + +/* Locked instruction */ +#define PERF_MEM_LOCK_NA 0x0001 /* Not available */ +#define PERF_MEM_LOCK_LOCKED 0x0002 /* Locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 /* TLB access */ -#define PERF_MEM_TLB_NA 0x01 /* not available */ -#define PERF_MEM_TLB_HIT 0x02 /* hit level */ -#define PERF_MEM_TLB_MISS 0x04 /* miss level */ -#define PERF_MEM_TLB_L1 0x08 /* L1 */ -#define PERF_MEM_TLB_L2 0x10 /* L2 */ -#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/ -#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ -#define PERF_MEM_TLB_SHIFT 26 +#define PERF_MEM_TLB_NA 0x0001 /* Not available */ +#define PERF_MEM_TLB_HIT 0x0002 /* Hit level */ +#define PERF_MEM_TLB_MISS 0x0004 /* Miss level */ +#define PERF_MEM_TLB_L1 0x0008 /* L1 */ +#define PERF_MEM_TLB_L2 0x0010 /* L2 */ +#define PERF_MEM_TLB_WK 0x0020 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x0040 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 /* Access blocked */ -#define PERF_MEM_BLK_NA 0x01 /* not available */ -#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ -#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ -#define PERF_MEM_BLK_SHIFT 40 - -/* hop level */ -#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_BLK_NA 0x0001 /* Not available */ +#define PERF_MEM_BLK_DATA 0x0002 /* Data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x0004 /* Address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + +/* Hop level */ +#define PERF_MEM_HOPS_0 0x0001 /* Remote core, same node */ +#define PERF_MEM_HOPS_1 0x0002 /* Remote node, same socket */ +#define PERF_MEM_HOPS_2 0x0003 /* Remote socket, same board */ +#define PERF_MEM_HOPS_3 0x0004 /* Remote board */ /* 5-7 available */ -#define PERF_MEM_HOPS_SHIFT 43 +#define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) /* - * single taken branch record layout: + * Layout of single taken branch records: * * from: source instruction (may not always be a branch insn) * to: branch target @@ -1439,37 +1449,37 @@ union perf_mem_data_src { struct perf_branch_entry { __u64 from; __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - cycles:16, /* cycle count to last branch */ - type:4, /* branch type */ - spec:2, /* branch speculation info */ - new_type:4, /* additional branch type */ - priv:3, /* privilege level */ - reserved:31; + __u64 mispred : 1, /* target mispredicted */ + predicted : 1, /* target predicted */ + in_tx : 1, /* in transaction */ + abort : 1, /* transaction abort */ + cycles : 16, /* cycle count to last branch */ + type : 4, /* branch type */ + spec : 2, /* branch speculation info */ + new_type : 4, /* additional branch type */ + priv : 3, /* privilege level */ + reserved : 31; }; /* Size of used info bits in struct perf_branch_entry */ #define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 union perf_sample_weight { - __u64 full; + __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) struct { - __u32 var1_dw; - __u16 var2_w; - __u16 var3_w; + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; }; #elif defined(__BIG_ENDIAN_BITFIELD) struct { - __u16 var3_w; - __u16 var2_w; - __u32 var1_dw; + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif }; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b2722dae6f1e..78a362b80027 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -39,18 +39,21 @@ enum perf_type_id { /* * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA * AA: hardware event ID * EEEEEEEE: PMU type ID + * * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB * BB: hardware cache ID * CC: hardware cache op ID * DD: hardware cache op result ID * EEEEEEEE: PMU type ID - * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + * + * If the PMU type ID is 0, PERF_TYPE_RAW will be applied. */ -#define PERF_PMU_TYPE_SHIFT 32 -#define PERF_HW_EVENT_MASK 0xffffffff +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff /* * Generalized performance event event_id types, used by the @@ -112,7 +115,7 @@ enum perf_hw_cache_op_result_id { /* * Special "software" events provided by the kernel, even if the hardware * does not support performance events. These events measure various - * physical and sw events of the kernel (and allow the profiling of them as + * physical and SW events of the kernel (and allow the profiling of them as * well): */ enum perf_sw_ids { @@ -167,8 +170,9 @@ enum perf_event_sample_format { }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) + /* - * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * Values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set. * * If the user does not pass priv level information via branch_sample_type, * the kernel uses the event's priv level. Branch and event priv levels do @@ -178,20 +182,20 @@ enum perf_event_sample_format { * of branches and therefore it supersedes all the other types. */ enum perf_branch_sample_type_shift { - PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ - PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ - PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ - - PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ - PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ - PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ - PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ - PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ - PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ - PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ - PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* CALL/RET stack */ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ @@ -210,96 +214,95 @@ enum perf_branch_sample_type_shift { }; enum perf_branch_sample_type { - PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, - PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, - PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, - PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, - PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, - PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, - PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, - PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, - PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, - PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, - PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, - PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, - PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, - PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, - PERF_SAMPLE_BRANCH_TYPE_SAVE = - 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, - PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, - PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; /* - * Common flow change classification + * Common control flow change classifications: */ enum { - PERF_BR_UNKNOWN = 0, /* unknown */ - PERF_BR_COND = 1, /* conditional */ - PERF_BR_UNCOND = 2, /* unconditional */ - PERF_BR_IND = 3, /* indirect */ - PERF_BR_CALL = 4, /* function call */ - PERF_BR_IND_CALL = 5, /* indirect function call */ - PERF_BR_RET = 6, /* function return */ - PERF_BR_SYSCALL = 7, /* syscall */ - PERF_BR_SYSRET = 8, /* syscall return */ - PERF_BR_COND_CALL = 9, /* conditional function call */ - PERF_BR_COND_RET = 10, /* conditional function return */ - PERF_BR_ERET = 11, /* exception return */ - PERF_BR_IRQ = 12, /* irq */ - PERF_BR_SERROR = 13, /* system error */ - PERF_BR_NO_TX = 14, /* not in transaction */ - PERF_BR_EXTEND_ABI = 15, /* extend ABI */ + PERF_BR_UNKNOWN = 0, /* Unknown */ + PERF_BR_COND = 1, /* Conditional */ + PERF_BR_UNCOND = 2, /* Unconditional */ + PERF_BR_IND = 3, /* Indirect */ + PERF_BR_CALL = 4, /* Function call */ + PERF_BR_IND_CALL = 5, /* Indirect function call */ + PERF_BR_RET = 6, /* Function return */ + PERF_BR_SYSCALL = 7, /* Syscall */ + PERF_BR_SYSRET = 8, /* Syscall return */ + PERF_BR_COND_CALL = 9, /* Conditional function call */ + PERF_BR_COND_RET = 10, /* Conditional function return */ + PERF_BR_ERET = 11, /* Exception return */ + PERF_BR_IRQ = 12, /* IRQ */ + PERF_BR_SERROR = 13, /* System error */ + PERF_BR_NO_TX = 14, /* Not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* Extend ABI */ PERF_BR_MAX, }; /* - * Common branch speculation outcome classification + * Common branch speculation outcome classifications: */ enum { - PERF_BR_SPEC_NA = 0, /* Not available */ - PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ - PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ - PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ PERF_BR_SPEC_MAX, }; enum { - PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ - PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ - PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ - PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ - PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ - PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ - PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ - PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ PERF_BR_NEW_MAX, }; enum { - PERF_BR_PRIV_UNKNOWN = 0, - PERF_BR_PRIV_USER = 1, - PERF_BR_PRIV_KERNEL = 2, - PERF_BR_PRIV_HV = 3, + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, }; -#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 -#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 -#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 -#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 -#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ @@ -310,9 +313,9 @@ enum { * Values to determine ABI of the registers dump. */ enum perf_sample_regs_abi { - PERF_SAMPLE_REGS_ABI_NONE = 0, - PERF_SAMPLE_REGS_ABI_32 = 1, - PERF_SAMPLE_REGS_ABI_64 = 2, + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, }; /* @@ -320,21 +323,21 @@ enum perf_sample_regs_abi { * abort events. Multiple bits can be set. */ enum { - PERF_TXN_ELISION = (1 << 0), /* From elision */ - PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ - PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ - PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ - PERF_TXN_RETRY = (1 << 4), /* Retry possible */ - PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ - PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ - PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction is not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ - PERF_TXN_MAX = (1 << 8), /* non-ABI */ + PERF_TXN_MAX = (1 << 8), /* non-ABI */ - /* bits 32..63 are reserved for the abort code */ + /* Bits 32..63 are reserved for the abort code */ - PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), - PERF_TXN_ABORT_SHIFT = 32, + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, }; /* @@ -369,24 +372,22 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; -#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ -#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ -#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ -#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ - /* add: sample_stack_user */ -#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ -#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ -#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ -#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ -#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ +#define PERF_ATTR_SIZE_VER0 64 /* Size of first published 'struct perf_event_attr' */ +#define PERF_ATTR_SIZE_VER1 72 /* Add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* Add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* Add: sample_regs_user */ + /* Add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* Add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* Add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ /* - * Hardware event_id to monitor via a performance monitoring event: - * - * @sample_max_stack: Max number of frame pointers in a callchain, - * should be < /proc/sys/kernel/perf_event_max_stack - * Max number of entries of branch stack - * should be < hardware limit + * 'struct perf_event_attr' contains various attributes that define + * a performance event - most of them hardware related configuration + * details, but also a lot of behavioral switches and values implemented + * by the kernel. */ struct perf_event_attr { @@ -396,7 +397,7 @@ struct perf_event_attr { __u32 type; /* - * Size of the attr structure, for fwd/bwd compat. + * Size of the attr structure, for forward/backwards compatibility. */ __u32 size; @@ -451,21 +452,21 @@ struct perf_event_attr { comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ - write_backward : 1, /* Write ring buffer from end to beginning */ + write_backward : 1, /* write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - bpf_event : 1, /* include bpf events */ + bpf_event : 1, /* include BPF events */ aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - build_id : 1, /* use build id in mmap2 events */ + build_id : 1, /* use build ID in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ __reserved_1 : 26; union { - __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_events; /* wake up every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; @@ -474,13 +475,13 @@ struct perf_event_attr { __u64 bp_addr; __u64 kprobe_func; /* for perf_kprobe */ __u64 uprobe_path; /* for perf_uprobe */ - __u64 config1; /* extension of config */ + __u64 config1; /* extension of config */ }; union { __u64 bp_len; - __u64 kprobe_addr; /* when kprobe_func == NULL */ + __u64 kprobe_addr; /* when kprobe_func == NULL */ __u64 probe_offset; /* for perf_[k,u]probe */ - __u64 config2; /* extension of config1 */ + __u64 config2; /* extension of config1 */ }; __u64 branch_sample_type; /* enum perf_branch_sample_type */ @@ -510,7 +511,16 @@ struct perf_event_attr { * Wakeup watermark for AUX area */ __u32 aux_watermark; + + /* + * Max number of frame pointers in a callchain, should be + * lower than /proc/sys/kernel/perf_event_max_stack. + * + * Max number of entries of branch stack should be lower + * than the hardware limit. + */ __u16 sample_max_stack; + __u16 __reserved_2; __u32 aux_sample_size; @@ -537,7 +547,7 @@ struct perf_event_attr { /* * Structure used by below PERF_EVENT_IOC_QUERY_BPF command - * to query bpf programs attached to the same perf tracepoint + * to query BPF programs attached to the same perf tracepoint * as the given perf event. */ struct perf_event_query_bpf { @@ -559,21 +569,21 @@ struct perf_event_query_bpf { /* * Ioctls that can be done on a perf event fd: */ -#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) -#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) -#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) -#define PERF_EVENT_IOC_RESET _IO ('$', 3) -#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) -#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) -#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) -#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) -#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) -#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW ('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW ('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR ('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW ('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW ('$', 9, __u32) #define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) -#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *) +#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW ('$', 11, struct perf_event_attr *) enum perf_event_ioc_flags { - PERF_IOC_FLAG_GROUP = 1U << 0, + PERF_IOC_FLAG_GROUP = 1U << 0, }; /* @@ -584,7 +594,7 @@ struct perf_event_mmap_page { __u32 compat_version; /* lowest version this is compat with */ /* - * Bits needed to read the hw events in user-space. + * Bits needed to read the HW events in user-space. * * u32 seq, time_mult, time_shift, index, width; * u64 count, enabled, running; @@ -622,7 +632,7 @@ struct perf_event_mmap_page { __u32 index; /* hardware event identifier */ __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ - __u64 time_running; /* time event on cpu */ + __u64 time_running; /* time event on CPU */ union { __u64 capabilities; struct { @@ -650,7 +660,7 @@ struct perf_event_mmap_page { /* * If cap_usr_time the below fields can be used to compute the time - * delta since time_enabled (in ns) using rdtsc or similar. + * delta since time_enabled (in ns) using RDTSC or similar. * * u64 quot, rem; * u64 delta; @@ -723,7 +733,7 @@ struct perf_event_mmap_page { * after reading this value. * * When the mapping is PROT_WRITE the @data_tail value should be - * written by userspace to reflect the last read data, after issueing + * written by user-space to reflect the last read data, after issuing * an smp_mb() to separate the data read from the ->data_tail store. * In this case the kernel will not over-write unread data. * @@ -739,7 +749,7 @@ struct perf_event_mmap_page { /* * AUX area is defined by aux_{offset,size} fields that should be set - * by the userspace, so that + * by the user-space, so that * * aux_offset >= data_offset + data_size * @@ -813,7 +823,7 @@ struct perf_event_mmap_page { * Indicates that thread was preempted in TASK_RUNNING state. * * PERF_RECORD_MISC_MMAP_BUILD_ID: - * Indicates that mmap2 event carries build id data. + * Indicates that mmap2 event carries build ID data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) @@ -824,26 +834,26 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) struct perf_event_header { - __u32 type; - __u16 misc; - __u16 size; + __u32 type; + __u16 misc; + __u16 size; }; struct perf_ns_link_info { - __u64 dev; - __u64 ino; + __u64 dev; + __u64 ino; }; enum { - NET_NS_INDEX = 0, - UTS_NS_INDEX = 1, - IPC_NS_INDEX = 2, - PID_NS_INDEX = 3, - USER_NS_INDEX = 4, - MNT_NS_INDEX = 5, - CGROUP_NS_INDEX = 6, - - NR_NAMESPACES, /* number of available namespaces */ + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ }; enum perf_event_type { @@ -859,11 +869,11 @@ enum perf_event_type { * optional fields being ignored. * * struct sample_id { - * { u32 pid, tid; } && PERF_SAMPLE_TID - * { u64 time; } && PERF_SAMPLE_TIME - * { u64 id; } && PERF_SAMPLE_ID - * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID - * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 id; } && PERF_SAMPLE_IDENTIFIER * } && perf_event_attr::sample_id_all * @@ -874,7 +884,7 @@ enum perf_event_type { /* * The MMAP events record the PROT_EXEC mappings so that we can - * correlate userspace IPs to code. They have the following structure: + * correlate user-space IPs to code. They have the following structure: * * struct { * struct perf_event_header header; @@ -884,7 +894,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -894,7 +904,7 @@ enum perf_event_type { * struct perf_event_header header; * u64 id; * u64 lost; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_LOST = 2, @@ -905,7 +915,7 @@ enum perf_event_type { * * u32 pid, tid; * char comm[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_COMM = 3, @@ -916,7 +926,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_EXIT = 4, @@ -927,7 +937,7 @@ enum perf_event_type { * u64 time; * u64 id; * u64 stream_id; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_THROTTLE = 5, @@ -939,7 +949,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_FORK = 7, @@ -950,7 +960,7 @@ enum perf_event_type { * u32 pid, tid; * * struct read_format values; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_READ = 8, @@ -1005,12 +1015,12 @@ enum perf_event_type { * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * - * { u64 abi; # enum perf_sample_regs_abi - * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER * - * { u64 size; - * char data[size]; - * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * * { union perf_sample_weight * { @@ -1071,7 +1081,7 @@ enum perf_event_type { * }; * u32 prot, flags; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP2 = 10, @@ -1080,12 +1090,12 @@ enum perf_event_type { * Records that new data landed in the AUX buffer part. * * struct { - * struct perf_event_header header; + * struct perf_event_header header; * - * u64 aux_offset; - * u64 aux_size; + * u64 aux_offset; + * u64 aux_size; * u64 flags; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_AUX = 11, @@ -1168,7 +1178,7 @@ enum perf_event_type { PERF_RECORD_KSYMBOL = 17, /* - * Record bpf events: + * Record BPF events: * enum perf_bpf_event_type { * PERF_BPF_EVENT_UNKNOWN = 0, * PERF_BPF_EVENT_PROG_LOAD = 1, @@ -1246,181 +1256,181 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) enum perf_bpf_event_type { - PERF_BPF_EVENT_UNKNOWN = 0, - PERF_BPF_EVENT_PROG_LOAD = 1, - PERF_BPF_EVENT_PROG_UNLOAD = 2, - PERF_BPF_EVENT_MAX, /* non-ABI */ + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ }; -#define PERF_MAX_STACK_DEPTH 127 -#define PERF_MAX_CONTEXTS_PER_STACK 8 +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 enum perf_callchain_context { - PERF_CONTEXT_HV = (__u64)-32, - PERF_CONTEXT_KERNEL = (__u64)-128, - PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, - PERF_CONTEXT_GUEST = (__u64)-2048, - PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, - PERF_CONTEXT_GUEST_USER = (__u64)-2560, + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, - PERF_CONTEXT_MAX = (__u64)-4095, + PERF_CONTEXT_MAX = (__u64)-4095, }; /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x0001 /* Record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x0002 /* Snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x0004 /* Record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x0008 /* Sample collided with another */ #define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ /* CoreSight PMU AUX buffer formats */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ -#define PERF_FLAG_FD_NO_GROUP (1UL << 0) -#define PERF_FLAG_FD_OUTPUT (1UL << 1) -#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup ID, per-CPU mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ #if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_op:5, /* type of opcode */ - mem_lvl:14, /* memory hierarchy level */ - mem_snoop:5, /* snoop mode */ - mem_lock:2, /* lock instr */ - mem_dtlb:7, /* tlb access */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_remote:1, /* remote */ - mem_snoopx:2, /* snoop mode, ext */ - mem_blk:3, /* access blocked */ - mem_hops:3, /* hop level */ - mem_rsvd:18; + __u64 mem_op : 5, /* Type of opcode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_snoop : 5, /* Snoop mode */ + mem_lock : 2, /* Lock instr */ + mem_dtlb : 7, /* TLB access */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_remote : 1, /* Remote */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_blk : 3, /* Access blocked */ + mem_hops : 3, /* Hop level */ + mem_rsvd : 18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:18, - mem_hops:3, /* hop level */ - mem_blk:3, /* access blocked */ - mem_snoopx:2, /* snoop mode, ext */ - mem_remote:1, /* remote */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_dtlb:7, /* tlb access */ - mem_lock:2, /* lock instr */ - mem_snoop:5, /* snoop mode */ - mem_lvl:14, /* memory hierarchy level */ - mem_op:5; /* type of opcode */ + __u64 mem_rsvd : 18, + mem_hops : 3, /* Hop level */ + mem_blk : 3, /* Access blocked */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_remote : 1, /* Remote */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_dtlb : 7, /* TLB access */ + mem_lock : 2, /* Lock instr */ + mem_snoop : 5, /* Snoop mode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_op : 5; /* Type of opcode */ }; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif -/* type of opcode (load/store/prefetch,code) */ -#define PERF_MEM_OP_NA 0x01 /* not available */ -#define PERF_MEM_OP_LOAD 0x02 /* load instruction */ -#define PERF_MEM_OP_STORE 0x04 /* store instruction */ -#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */ -#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ -#define PERF_MEM_OP_SHIFT 0 +/* Type of memory opcode: */ +#define PERF_MEM_OP_NA 0x0001 /* Not available */ +#define PERF_MEM_OP_LOAD 0x0002 /* Load instruction */ +#define PERF_MEM_OP_STORE 0x0004 /* Store instruction */ +#define PERF_MEM_OP_PFETCH 0x0008 /* Prefetch */ +#define PERF_MEM_OP_EXEC 0x0010 /* Code (execution) */ +#define PERF_MEM_OP_SHIFT 0 /* - * PERF_MEM_LVL_* namespace being depricated to some extent in the + * The PERF_MEM_LVL_* namespace is being deprecated to some extent in * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. - * Supporting this namespace inorder to not break defined ABIs. + * We support this namespace in order to not break defined ABIs. * - * memory hierarchy (memory level, hit or miss) + * Memory hierarchy (memory level, hit or miss) */ -#define PERF_MEM_LVL_NA 0x01 /* not available */ -#define PERF_MEM_LVL_HIT 0x02 /* hit level */ -#define PERF_MEM_LVL_MISS 0x04 /* miss level */ -#define PERF_MEM_LVL_L1 0x08 /* L1 */ -#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ -#define PERF_MEM_LVL_L2 0x20 /* L2 */ -#define PERF_MEM_LVL_L3 0x40 /* L3 */ -#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ -#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ -#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ -#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ -#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ -#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ -#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ -#define PERF_MEM_LVL_SHIFT 5 - -#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ -#define PERF_MEM_REMOTE_SHIFT 37 - -#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ -#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ -#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ -#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ -/* 0x7 available */ -#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ -#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ -#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ -#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ -#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ -#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ - -#define PERF_MEM_LVLNUM_SHIFT 33 - -/* snoop mode */ -#define PERF_MEM_SNOOP_NA 0x01 /* not available */ -#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ -#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */ -#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */ -#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ -#define PERF_MEM_SNOOP_SHIFT 19 - -#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ -#define PERF_MEM_SNOOPX_SHIFT 38 - -/* locked instruction */ -#define PERF_MEM_LOCK_NA 0x01 /* not available */ -#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ -#define PERF_MEM_LOCK_SHIFT 24 +#define PERF_MEM_LVL_NA 0x0001 /* Not available */ +#define PERF_MEM_LVL_HIT 0x0002 /* Hit level */ +#define PERF_MEM_LVL_MISS 0x0004 /* Miss level */ +#define PERF_MEM_LVL_L1 0x0008 /* L1 */ +#define PERF_MEM_LVL_LFB 0x0010 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x0020 /* L2 */ +#define PERF_MEM_LVL_L3 0x0040 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x0080 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x0100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x0200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x0400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x0800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +#define PERF_MEM_REMOTE_REMOTE 0x0001 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x0001 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x0002 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x0003 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ +#define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ +/* 0x007 available */ +#define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x000b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x000c /* LFB / L1 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_RAM 0x000d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x000e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x000f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + +/* Snoop mode */ +#define PERF_MEM_SNOOP_NA 0x0001 /* Not available */ +#define PERF_MEM_SNOOP_NONE 0x0002 /* No snoop */ +#define PERF_MEM_SNOOP_HIT 0x0004 /* Snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x0008 /* Snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x0010 /* Snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +#define PERF_MEM_SNOOPX_FWD 0x0001 /* Forward */ +#define PERF_MEM_SNOOPX_PEER 0x0002 /* Transfer from peer */ +#define PERF_MEM_SNOOPX_SHIFT 38 + +/* Locked instruction */ +#define PERF_MEM_LOCK_NA 0x0001 /* Not available */ +#define PERF_MEM_LOCK_LOCKED 0x0002 /* Locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 /* TLB access */ -#define PERF_MEM_TLB_NA 0x01 /* not available */ -#define PERF_MEM_TLB_HIT 0x02 /* hit level */ -#define PERF_MEM_TLB_MISS 0x04 /* miss level */ -#define PERF_MEM_TLB_L1 0x08 /* L1 */ -#define PERF_MEM_TLB_L2 0x10 /* L2 */ -#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/ -#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ -#define PERF_MEM_TLB_SHIFT 26 +#define PERF_MEM_TLB_NA 0x0001 /* Not available */ +#define PERF_MEM_TLB_HIT 0x0002 /* Hit level */ +#define PERF_MEM_TLB_MISS 0x0004 /* Miss level */ +#define PERF_MEM_TLB_L1 0x0008 /* L1 */ +#define PERF_MEM_TLB_L2 0x0010 /* L2 */ +#define PERF_MEM_TLB_WK 0x0020 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x0040 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 /* Access blocked */ -#define PERF_MEM_BLK_NA 0x01 /* not available */ -#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ -#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ -#define PERF_MEM_BLK_SHIFT 40 - -/* hop level */ -#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_BLK_NA 0x0001 /* Not available */ +#define PERF_MEM_BLK_DATA 0x0002 /* Data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x0004 /* Address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + +/* Hop level */ +#define PERF_MEM_HOPS_0 0x0001 /* Remote core, same node */ +#define PERF_MEM_HOPS_1 0x0002 /* Remote node, same socket */ +#define PERF_MEM_HOPS_2 0x0003 /* Remote socket, same board */ +#define PERF_MEM_HOPS_3 0x0004 /* Remote board */ /* 5-7 available */ -#define PERF_MEM_HOPS_SHIFT 43 +#define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) /* - * single taken branch record layout: + * Layout of single taken branch records: * * from: source instruction (may not always be a branch insn) * to: branch target @@ -1439,37 +1449,37 @@ union perf_mem_data_src { struct perf_branch_entry { __u64 from; __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - cycles:16, /* cycle count to last branch */ - type:4, /* branch type */ - spec:2, /* branch speculation info */ - new_type:4, /* additional branch type */ - priv:3, /* privilege level */ - reserved:31; + __u64 mispred : 1, /* target mispredicted */ + predicted : 1, /* target predicted */ + in_tx : 1, /* in transaction */ + abort : 1, /* transaction abort */ + cycles : 16, /* cycle count to last branch */ + type : 4, /* branch type */ + spec : 2, /* branch speculation info */ + new_type : 4, /* additional branch type */ + priv : 3, /* privilege level */ + reserved : 31; }; /* Size of used info bits in struct perf_branch_entry */ #define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 union perf_sample_weight { - __u64 full; + __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) struct { - __u32 var1_dw; - __u16 var2_w; - __u16 var3_w; + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; }; #elif defined(__BIG_ENDIAN_BITFIELD) struct { - __u16 var3_w; - __u16 var2_w; - __u32 var1_dw; + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif }; -- cgit v1.2.3 From 4ff4d86f6cceb6bea583bdb230e5439655778cce Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Mon, 19 May 2025 10:45:05 +0200 Subject: net: Add support for providing the PTP hardware source in tsinfo Multi-PTP source support within a network topology has been merged, but the hardware timestamp source is not yet exposed to users. Currently, users only see the PTP index, which does not indicate whether the timestamp comes from a PHY or a MAC. Add support for reporting the hwtstamp source using a hwtstamp-source field, alongside hwtstamp-phyindex, to describe the origin of the hardware timestamp. Remove HWTSTAMP_SOURCE_UNSPEC enum value as it is not used at all. Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20250519-feature_ptp_source-v4-1-5d10e19a0265@bootlin.com Signed-off-by: Paolo Abeni --- Documentation/netlink/specs/ethtool.yaml | 27 ++++++++++++++++++++++++ include/linux/ethtool.h | 5 +++++ include/linux/net_tstamp.h | 7 +------ include/uapi/linux/ethtool_netlink_generated.h | 14 +++++++++++++ net/ethtool/common.c | 29 +++++++++++++++++++++----- net/ethtool/tsinfo.c | 23 ++++++++++++++++++++ 6 files changed, 94 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index c650cd3dcb80..9f98715a6512 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -98,6 +98,24 @@ definitions: name: tcp-data-split type: enum entries: [ unknown, disabled, enabled ] + - + name: hwtstamp-source + doc: Source of the hardware timestamp + enum-name: hwtstamp-source + name-prefix: hwtstamp-source- + type: enum + entries: + - + name: netdev + doc: | + Hardware timestamp comes from a MAC or a device + which has MAC and PHY integrated + value: 1 + - + name: phylib + doc: | + Hardware timestamp comes from one PHY device + of the network topology attribute-sets: - @@ -896,6 +914,13 @@ attribute-sets: name: hwtstamp-provider type: nest nested-attributes: ts-hwtstamp-provider + - + name: hwtstamp-source + type: u32 + enum: hwtstamp-source + - + name: hwtstamp-phyindex + type: u32 - name: cable-result attr-cnt-name: __ethtool-a-cable-result-cnt @@ -1981,6 +2006,8 @@ operations: - phc-index - stats - hwtstamp-provider + - hwtstamp-source + - hwtstamp-phyindex dump: *tsinfo-get-op - name: cable-test-act diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 117718c24814..5e0dd333ad1f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #define ETHTOOL_MM_MAX_VERIFY_TIME_MS 128 @@ -830,6 +831,8 @@ struct ethtool_rxfh_param { * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none * @phc_qualifier: qualifier of the associated PHC + * @phc_source: source device of the associated PHC + * @phc_phyindex: index of PHY device source of the associated PHC * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values */ @@ -838,6 +841,8 @@ struct kernel_ethtool_ts_info { u32 so_timestamping; int phc_index; enum hwtstamp_provider_qualifier phc_qualifier; + enum hwtstamp_source phc_source; + int phc_phyindex; enum hwtstamp_tx_types tx_types; enum hwtstamp_rx_filters rx_filters; }; diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index ff0758e88ea1..f4936d9c2b3c 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -4,6 +4,7 @@ #define _LINUX_NET_TIMESTAMPING_H_ #include +#include #define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ SOF_TIMESTAMPING_TX_SOFTWARE | \ @@ -13,12 +14,6 @@ SOF_TIMESTAMPING_TX_HARDWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) -enum hwtstamp_source { - HWTSTAMP_SOURCE_UNSPEC, - HWTSTAMP_SOURCE_NETDEV, - HWTSTAMP_SOURCE_PHYLIB, -}; - /** * struct hwtstamp_provider_desc - hwtstamp provider description * diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 30c8dad6214e..9a02f579de22 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -37,6 +37,18 @@ enum ethtool_tcp_data_split { ETHTOOL_TCP_DATA_SPLIT_ENABLED, }; +/** + * enum hwtstamp_source - Source of the hardware timestamp + * @HWTSTAMP_SOURCE_NETDEV: Hardware timestamp comes from a MAC or a device + * which has MAC and PHY integrated + * @HWTSTAMP_SOURCE_PHYLIB: Hardware timestamp comes from one PHY device of the + * network topology + */ +enum hwtstamp_source { + HWTSTAMP_SOURCE_NETDEV = 1, + HWTSTAMP_SOURCE_PHYLIB, +}; + enum { ETHTOOL_A_HEADER_UNSPEC, ETHTOOL_A_HEADER_DEV_INDEX, @@ -401,6 +413,8 @@ enum { ETHTOOL_A_TSINFO_PHC_INDEX, ETHTOOL_A_TSINFO_STATS, ETHTOOL_A_TSINFO_HWTSTAMP_PROVIDER, + ETHTOOL_A_TSINFO_HWTSTAMP_SOURCE, + ETHTOOL_A_TSINFO_HWTSTAMP_PHYINDEX, __ETHTOOL_A_TSINFO_CNT, ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 49bea6b45bd5..eb253e0fd61b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -921,9 +921,18 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); if (IS_ERR(phy)) - err = PTR_ERR(phy); - else - err = 0; + return PTR_ERR(phy); + + /* Report the phc source only if we have a real + * phc source with an index. + */ + if (info->phc_index >= 0) { + info->phc_source = HWTSTAMP_SOURCE_PHYLIB; + info->phc_phyindex = phy->phyindex; + } + err = 0; + } else if (!err && info->phc_index >= 0) { + info->phc_source = HWTSTAMP_SOURCE_NETDEV; } info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | @@ -947,10 +956,20 @@ int __ethtool_get_ts_info(struct net_device *dev, ethtool_init_tsinfo(info); if (phy_is_default_hwtstamp(phydev) && - phy_has_tsinfo(phydev)) + phy_has_tsinfo(phydev)) { err = phy_ts_info(phydev, info); - else if (ops->get_ts_info) + /* Report the phc source only if we have a real + * phc source with an index. + */ + if (!err && info->phc_index >= 0) { + info->phc_source = HWTSTAMP_SOURCE_PHYLIB; + info->phc_phyindex = phydev->phyindex; + } + } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, info); + if (!err && info->phc_index >= 0) + info->phc_source = HWTSTAMP_SOURCE_NETDEV; + } info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 8130b406ef10..8c654caa6805 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -160,6 +160,12 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, /* _TSINFO_HWTSTAMP_PROVIDER */ len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); } + if (ts_info->phc_source) { + len += nla_total_size(sizeof(u32)); /* _TSINFO_HWTSTAMP_SOURCE */ + if (ts_info->phc_phyindex) + /* _TSINFO_HWTSTAMP_PHYINDEX */ + len += nla_total_size(sizeof(u32)); + } if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _TSINFO_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; @@ -259,6 +265,16 @@ static int tsinfo_fill_reply(struct sk_buff *skb, nla_nest_end(skb, nest); } + if (ts_info->phc_source) { + if (nla_put_u32(skb, ETHTOOL_A_TSINFO_HWTSTAMP_SOURCE, + ts_info->phc_source)) + return -EMSGSIZE; + + if (ts_info->phc_phyindex && + nla_put_u32(skb, ETHTOOL_A_TSINFO_HWTSTAMP_PHYINDEX, + ts_info->phc_phyindex)) + return -EMSGSIZE; + } if (req_base->flags & ETHTOOL_FLAG_STATS && tsinfo_put_stats(skb, &data->stats)) return -EMSGSIZE; @@ -346,6 +362,11 @@ static int ethnl_tsinfo_dump_one_phydev(struct sk_buff *skb, if (ret < 0) goto err; + if (reply_data->ts_info.phc_index >= 0) { + reply_data->ts_info.phc_source = HWTSTAMP_SOURCE_PHYLIB; + reply_data->ts_info.phc_phyindex = phydev->phyindex; + } + ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); if (ret < 0) goto err; @@ -389,6 +410,8 @@ static int ethnl_tsinfo_dump_one_netdev(struct sk_buff *skb, if (ret < 0) goto err; + if (reply_data->ts_info.phc_index >= 0) + reply_data->ts_info.phc_source = HWTSTAMP_SOURCE_NETDEV; ret = ethnl_tsinfo_end_dump(skb, dev, req_info, reply_data, ehdr); if (ret < 0) -- cgit v1.2.3 From 914e0dc5082a335ea5e7d905e99e1a1cde001369 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 22 May 2025 23:20:40 +0800 Subject: ublk: run auto buf unregisgering in same io_ring_ctx with registering UBLK_F_AUTO_BUF_REG requires that the buffer registered automatically is unregistered in same `io_ring_ctx`, so check it explicitly. Document this requirement for UBLK_F_AUTO_BUF_REG. Drop WARN_ON_ONCE() which is triggered from userspace code path. Fixes: 99c1e4eb6a3f ("ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG") Reported-by: Caleb Sander Mateos Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250522152043.399824-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 19 ++++++++++++++++--- include/uapi/linux/ublk_cmd.h | 6 +++++- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index f818733901dc..33fadca3ee90 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -84,6 +84,7 @@ struct ublk_rq_data { /* for auto-unregister buffer in case of UBLK_F_AUTO_BUF_REG */ u16 buf_index; + void *buf_ctx_handle; }; struct ublk_uring_cmd_pdu { @@ -1211,6 +1212,8 @@ static bool ublk_auto_buf_reg(struct request *req, struct ublk_io *io, } /* one extra reference is dropped by ublk_io_release */ refcount_set(&data->ref, 2); + + data->buf_ctx_handle = io_uring_cmd_ctx_handle(io->cmd); /* store buffer index in request payload */ data->buf_index = pdu->buf.index; io->flags |= UBLK_IO_FLAG_AUTO_BUF_REG; @@ -2111,12 +2114,22 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq, if (ublk_support_auto_buf_reg(ubq)) { int ret; + /* + * `UBLK_F_AUTO_BUF_REG` only works iff `UBLK_IO_FETCH_REQ` + * and `UBLK_IO_COMMIT_AND_FETCH_REQ` are issued from same + * `io_ring_ctx`. + * + * If this uring_cmd's io_ring_ctx isn't same with the + * one for registering the buffer, it is ublk server's + * responsibility for unregistering the buffer, otherwise + * this ublk request gets stuck. + */ if (io->flags & UBLK_IO_FLAG_AUTO_BUF_REG) { struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - WARN_ON_ONCE(io_buffer_unregister_bvec(cmd, - data->buf_index, - issue_flags)); + if (data->buf_ctx_handle == io_uring_cmd_ctx_handle(cmd)) + io_buffer_unregister_bvec(cmd, data->buf_index, + issue_flags); io->flags &= ~UBLK_IO_FLAG_AUTO_BUF_REG; } diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index c4b9942697fc..1c40632cb164 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -226,7 +226,11 @@ * * For using this feature: * - * - ublk server has to create sparse buffer table + * - ublk server has to create sparse buffer table on the same `io_ring_ctx` + * for issuing `UBLK_IO_FETCH_REQ` and `UBLK_IO_COMMIT_AND_FETCH_REQ`. + * If uring_cmd isn't issued on same `io_ring_ctx`, it is ublk server's + * responsibility to unregister the buffer by issuing `IO_UNREGISTER_IO_BUF` + * manually, otherwise this ublk request won't complete. * * - ublk server passes auto buf register data via uring_cmd's sqe->addr, * `struct ublk_auto_buf_reg` is populated from sqe->addr, please see -- cgit v1.2.3 From 7e5c6aa67e6f6133c5a2c53852e1dd9af2c0c3fc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 22 May 2025 15:49:34 +0200 Subject: netfilter: nf_tables: add packets conntrack state to debug trace info Add the minimal relevant info needed for userspace ("nftables monitor trace") to provide the conntrack view of the packet: - state (new, related, established) - direction (original, reply) - status (e.g., if connection is subject to dnat) - id (allows to query ctnetlink for remaining conntrack state info) Example: trace id a62 inet filter PRE_RAW packet: iif "enp0s3" ether [..] [..] trace id a62 inet filter PRE_MANGLE conntrack: ct direction original ct state new ct id 32 trace id a62 inet filter PRE_MANGLE packet: [..] [..] trace id a62 inet filter IN conntrack: ct direction original ct state new ct status dnat-done ct id 32 [..] In this case one can see that while NAT is active, the new connection isn't subject to a translation. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 8 +++++ net/netfilter/nf_tables_trace.c | 54 +++++++++++++++++++++++++++++++- 2 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7d6bc19a0153..2beb30be2c5f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1841,6 +1841,10 @@ enum nft_xfrm_keys { * @NFTA_TRACE_MARK: nfmark (NLA_U32) * @NFTA_TRACE_NFPROTO: nf protocol processed (NLA_U32) * @NFTA_TRACE_POLICY: policy that decided fate of packet (NLA_U32) + * @NFTA_TRACE_CT_ID: conntrack id (NLA_U32) + * @NFTA_TRACE_CT_DIRECTION: packets direction (NLA_U8) + * @NFTA_TRACE_CT_STATUS: conntrack status (NLA_U32) + * @NFTA_TRACE_CT_STATE: packet state (new, established, ...) (NLA_U32) */ enum nft_trace_attributes { NFTA_TRACE_UNSPEC, @@ -1861,6 +1865,10 @@ enum nft_trace_attributes { NFTA_TRACE_NFPROTO, NFTA_TRACE_POLICY, NFTA_TRACE_PAD, + NFTA_TRACE_CT_ID, + NFTA_TRACE_CT_DIRECTION, + NFTA_TRACE_CT_STATUS, + NFTA_TRACE_CT_STATE, __NFTA_TRACE_MAX }; #define NFTA_TRACE_MAX (__NFTA_TRACE_MAX - 1) diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 580c55268f65..ae3fe87195ab 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -90,6 +91,49 @@ static int nf_trace_fill_dev_info(struct sk_buff *nlskb, return 0; } +static int nf_trace_fill_ct_info(struct sk_buff *nlskb, + const struct sk_buff *skb) +{ + const struct nf_ct_hook *ct_hook; + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + u32 state; + + ct_hook = rcu_dereference(nf_ct_hook); + if (!ct_hook) + return 0; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) { + if (ctinfo != IP_CT_UNTRACKED) /* not seen by conntrack or invalid */ + return 0; + + state = NF_CT_STATE_UNTRACKED_BIT; + } else { + state = NF_CT_STATE_BIT(ctinfo); + } + + if (nla_put_be32(nlskb, NFTA_TRACE_CT_STATE, htonl(state))) + return -1; + + if (ct) { + u32 id = ct_hook->get_id(&ct->ct_general); + u32 status = READ_ONCE(ct->status); + u8 dir = CTINFO2DIR(ctinfo); + + if (nla_put_u8(nlskb, NFTA_TRACE_CT_DIRECTION, dir)) + return -1; + + if (nla_put_be32(nlskb, NFTA_TRACE_CT_ID, (__force __be32)id)) + return -1; + + if (status && nla_put_be32(nlskb, NFTA_TRACE_CT_STATUS, htonl(status))) + return -1; + } + + return 0; +} + static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, const struct nft_pktinfo *pkt) { @@ -210,7 +254,11 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, nla_total_size(sizeof(__be32)) + /* trace type */ nla_total_size(0) + /* VERDICT, nested */ nla_total_size(sizeof(u32)) + /* verdict code */ - nla_total_size(sizeof(u32)) + /* id */ + nla_total_size(sizeof(u32)) + /* ct id */ + nla_total_size(sizeof(u8)) + /* ct direction */ + nla_total_size(sizeof(u32)) + /* ct state */ + nla_total_size(sizeof(u32)) + /* ct status */ + nla_total_size(sizeof(u32)) + /* trace id */ nla_total_size(NFT_TRACETYPE_LL_HSIZE) + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + nla_total_size(NFT_TRACETYPE_TRANSPORT_HSIZE) + @@ -291,6 +339,10 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, if (nf_trace_fill_pkt_info(skb, pkt)) goto nla_put_failure; + + if (nf_trace_fill_ct_info(skb, pkt->skb)) + goto nla_put_failure; + info->packet_dumped = true; } -- cgit v1.2.3 From 465b9ee0ee7bc268d7f261356afd6c4262e48d82 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 21 May 2025 22:44:33 +0200 Subject: netfilter: nf_tables: Add notifications for hook changes Notify user space if netdev hooks are updated due to netdev add/remove events. Send minimal notification messages by introducing NFT_MSG_NEWDEV/DELDEV message types describing a single device only. Upon NETDEV_CHANGENAME, the callback has no information about the interface's old name. To provide a clear message to user space, include the hook's stored interface name in the notification. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 +++ include/uapi/linux/netfilter/nf_tables.h | 10 ++++++ include/uapi/linux/netfilter/nfnetlink.h | 2 ++ net/netfilter/nf_tables_api.c | 59 ++++++++++++++++++++++++++++++++ net/netfilter/nfnetlink.c | 1 + net/netfilter/nft_chain_filter.c | 2 ++ 6 files changed, 79 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5e49619ae49c..e4d8e451e935 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1142,6 +1142,11 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +struct nft_hook; +void nf_tables_chain_device_notify(const struct nft_chain *chain, + const struct nft_hook *hook, + const struct net_device *dev, int event); + enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 2beb30be2c5f..518ba144544c 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -142,6 +142,8 @@ enum nf_tables_msg_types { NFT_MSG_DESTROYOBJ, NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_GETSETELEM_RESET, + NFT_MSG_NEWDEV, + NFT_MSG_DELDEV, NFT_MSG_MAX, }; @@ -1784,10 +1786,18 @@ enum nft_synproxy_attributes { * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) + * @NFTA_DEVICE_TABLE: table containing the flowtable or chain hooking into the device (NLA_STRING) + * @NFTA_DEVICE_FLOWTABLE: flowtable hooking into the device (NLA_STRING) + * @NFTA_DEVICE_CHAIN: chain hooking into the device (NLA_STRING) + * @NFTA_DEVICE_SPEC: hook spec matching the device (NLA_STRING) */ enum nft_devices_attributes { NFTA_DEVICE_UNSPEC, NFTA_DEVICE_NAME, + NFTA_DEVICE_TABLE, + NFTA_DEVICE_FLOWTABLE, + NFTA_DEVICE_CHAIN, + NFTA_DEVICE_SPEC, __NFTA_DEVICE_MAX }; #define NFTA_DEVICE_MAX (__NFTA_DEVICE_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 6cd58cd2a6f0..50d807af2649 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -25,6 +25,8 @@ enum nfnetlink_groups { #define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA NFNLGRP_NFTRACE, #define NFNLGRP_NFTRACE NFNLGRP_NFTRACE + NFNLGRP_NFT_DEV, +#define NFNLGRP_NFT_DEV NFNLGRP_NFT_DEV __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a7240736f98e..24c71ecb2179 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9686,6 +9686,64 @@ struct nf_hook_ops *nft_hook_find_ops_rcu(const struct nft_hook *hook, } EXPORT_SYMBOL_GPL(nft_hook_find_ops_rcu); +static void +nf_tables_device_notify(const struct nft_table *table, int attr, + const char *name, const struct nft_hook *hook, + const struct net_device *dev, int event) +{ + struct net *net = dev_net(dev); + struct nlmsghdr *nlh; + struct sk_buff *skb; + u16 flags = 0; + + if (!nfnetlink_has_listeners(net, NFNLGRP_NFT_DEV)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + goto err; + + event = event == NETDEV_REGISTER ? NFT_MSG_NEWDEV : NFT_MSG_DELDEV; + event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); + nlh = nfnl_msg_put(skb, 0, 0, event, flags, table->family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) + goto err; + + if (nla_put_string(skb, NFTA_DEVICE_TABLE, table->name) || + nla_put_string(skb, attr, name) || + nla_put(skb, NFTA_DEVICE_SPEC, hook->ifnamelen, hook->ifname) || + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) + goto err; + + nlmsg_end(skb, nlh); + nfnetlink_send(skb, net, 0, NFNLGRP_NFT_DEV, + nlmsg_report(nlh), GFP_KERNEL); + return; +err: + if (skb) + kfree_skb(skb); + nfnetlink_set_err(net, 0, NFNLGRP_NFT_DEV, -ENOBUFS); +} + +void +nf_tables_chain_device_notify(const struct nft_chain *chain, + const struct nft_hook *hook, + const struct net_device *dev, int event) +{ + nf_tables_device_notify(chain->table, NFTA_DEVICE_CHAIN, + chain->name, hook, dev, event); +} + +static void +nf_tables_flowtable_device_notify(const struct nft_flowtable *ft, + const struct nft_hook *hook, + const struct net_device *dev, int event) +{ + nf_tables_device_notify(ft->table, NFTA_DEVICE_FLOWTABLE, + ft->name, hook, dev, event); +} + static int nft_flowtable_event(unsigned long event, struct net_device *dev, struct nft_flowtable *flowtable, bool changename) { @@ -9733,6 +9791,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, list_add_tail_rcu(&ops->list, &hook->ops_list); break; } + nf_tables_flowtable_device_notify(flowtable, hook, dev, event); break; } return 0; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e598a2a252b0..ac77fc21632d 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -86,6 +86,7 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, + [NFNLGRP_NFT_DEV] = NFNL_SUBSYS_NFTABLES, }; static struct nfnl_net *nfnl_pernet(struct net *net) diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index b16185e9a6dd..846d48ba8965 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -363,6 +363,8 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev, list_add_tail_rcu(&ops->list, &hook->ops_list); break; } + nf_tables_chain_device_notify(&basechain->chain, + hook, dev, event); break; } return 0; -- cgit v1.2.3 From b465ae7b2524170cb14fa25dbcb84923bfb1a0a9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 23 May 2025 00:35:20 +0800 Subject: ublk: add feature UBLK_F_QUIESCE Add feature UBLK_F_QUIESCE, which adds control command `UBLK_U_CMD_QUIESCE_DEV` for quiescing device, then device state can become `UBLK_S_DEV_QUIESCED` or `UBLK_S_DEV_FAIL_IO` finally from ublk_ch_release() with ublk server cooperation. This feature can help to support to upgrade ublk server application by shutting down ublk server gracefully, meantime keep ublk block device persistent during the upgrading period. The feature is only available for UBLK_F_USER_RECOVERY. Suggested-by: Yoav Cohen Link: https://lore.kernel.org/linux-block/DM4PR12MB632807AB7CDCE77D1E5AB7D0A9B92@DM4PR12MB6328.namprd12.prod.outlook.com/ Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250522163523.406289-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 124 +++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/ublk_cmd.h | 19 +++++++ 2 files changed, 142 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 33fadca3ee90..1b47341962d0 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -51,6 +51,7 @@ /* private ioctl command mirror */ #define UBLK_CMD_DEL_DEV_ASYNC _IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC) #define UBLK_CMD_UPDATE_SIZE _IOC_NR(UBLK_U_CMD_UPDATE_SIZE) +#define UBLK_CMD_QUIESCE_DEV _IOC_NR(UBLK_U_CMD_QUIESCE_DEV) #define UBLK_IO_REGISTER_IO_BUF _IOC_NR(UBLK_U_IO_REGISTER_IO_BUF) #define UBLK_IO_UNREGISTER_IO_BUF _IOC_NR(UBLK_U_IO_UNREGISTER_IO_BUF) @@ -67,7 +68,8 @@ | UBLK_F_ZONED \ | UBLK_F_USER_RECOVERY_FAIL_IO \ | UBLK_F_UPDATE_SIZE \ - | UBLK_F_AUTO_BUF_REG) + | UBLK_F_AUTO_BUF_REG \ + | UBLK_F_QUIESCE) #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ @@ -2841,6 +2843,11 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) return -EINVAL; } + if ((info.flags & UBLK_F_QUIESCE) && !(info.flags & UBLK_F_USER_RECOVERY)) { + pr_warn("UBLK_F_QUIESCE requires UBLK_F_USER_RECOVERY\n"); + return -EINVAL; + } + /* * unprivileged device can't be trusted, but RECOVERY and * RECOVERY_REISSUE still may hang error handling, so can't @@ -3233,6 +3240,117 @@ static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl set_capacity_and_notify(ub->ub_disk, p->dev_sectors); mutex_unlock(&ub->mutex); } + +struct count_busy { + const struct ublk_queue *ubq; + unsigned int nr_busy; +}; + +static bool ublk_count_busy_req(struct request *rq, void *data) +{ + struct count_busy *idle = data; + + if (!blk_mq_request_started(rq) && rq->mq_hctx->driver_data == idle->ubq) + idle->nr_busy += 1; + return true; +} + +/* uring_cmd is guaranteed to be active if the associated request is idle */ +static bool ubq_has_idle_io(const struct ublk_queue *ubq) +{ + struct count_busy data = { + .ubq = ubq, + }; + + blk_mq_tagset_busy_iter(&ubq->dev->tag_set, ublk_count_busy_req, &data); + return data.nr_busy < ubq->q_depth; +} + +/* Wait until each hw queue has at least one idle IO */ +static int ublk_wait_for_idle_io(struct ublk_device *ub, + unsigned int timeout_ms) +{ + unsigned int elapsed = 0; + int ret; + + while (elapsed < timeout_ms && !signal_pending(current)) { + unsigned int queues_cancelable = 0; + int i; + + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + + queues_cancelable += !!ubq_has_idle_io(ubq); + } + + /* + * Each queue needs at least one active command for + * notifying ublk server + */ + if (queues_cancelable == ub->dev_info.nr_hw_queues) + break; + + msleep(UBLK_REQUEUE_DELAY_MS); + elapsed += UBLK_REQUEUE_DELAY_MS; + } + + if (signal_pending(current)) + ret = -EINTR; + else if (elapsed >= timeout_ms) + ret = -EBUSY; + else + ret = 0; + + return ret; +} + +static int ublk_ctrl_quiesce_dev(struct ublk_device *ub, + const struct ublksrv_ctrl_cmd *header) +{ + /* zero means wait forever */ + u64 timeout_ms = header->data[0]; + struct gendisk *disk; + int i, ret = -ENODEV; + + if (!(ub->dev_info.flags & UBLK_F_QUIESCE)) + return -EOPNOTSUPP; + + mutex_lock(&ub->mutex); + disk = ublk_get_disk(ub); + if (!disk) + goto unlock; + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + goto put_disk; + + ret = 0; + /* already in expected state */ + if (ub->dev_info.state != UBLK_S_DEV_LIVE) + goto put_disk; + + /* Mark all queues as canceling */ + blk_mq_quiesce_queue(disk->queue); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + + ubq->canceling = true; + } + blk_mq_unquiesce_queue(disk->queue); + + if (!timeout_ms) + timeout_ms = UINT_MAX; + ret = ublk_wait_for_idle_io(ub, timeout_ms); + +put_disk: + ublk_put_disk(disk); +unlock: + mutex_unlock(&ub->mutex); + + /* Cancel pending uring_cmd */ + if (!ret) + ublk_cancel_dev(ub); + return ret; +} + /* * All control commands are sent via /dev/ublk-control, so we have to check * the destination device's permission @@ -3319,6 +3437,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, case UBLK_CMD_START_USER_RECOVERY: case UBLK_CMD_END_USER_RECOVERY: case UBLK_CMD_UPDATE_SIZE: + case UBLK_CMD_QUIESCE_DEV: mask = MAY_READ | MAY_WRITE; break; default: @@ -3414,6 +3533,9 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ublk_ctrl_set_size(ub, header); ret = 0; break; + case UBLK_CMD_QUIESCE_DEV: + ret = ublk_ctrl_quiesce_dev(ub, header); + break; default: ret = -EOPNOTSUPP; break; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 1c40632cb164..56c7e3fc666f 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -53,6 +53,8 @@ _IOR('u', 0x14, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_UPDATE_SIZE \ _IOWR('u', 0x15, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_QUIESCE_DEV \ + _IOWR('u', 0x16, struct ublksrv_ctrl_cmd) /* * 64bits are enough now, and it should be easy to extend in case of @@ -253,6 +255,23 @@ */ #define UBLK_F_AUTO_BUF_REG (1ULL << 11) +/* + * Control command `UBLK_U_CMD_QUIESCE_DEV` is added for quiescing device, + * which state can be transitioned to `UBLK_S_DEV_QUIESCED` or + * `UBLK_S_DEV_FAIL_IO` finally, and it needs ublk server cooperation for + * handling `UBLK_IO_RES_ABORT` correctly. + * + * Typical use case is for supporting to upgrade ublk server application, + * meantime keep ublk block device persistent during the period. + * + * This feature is only available when UBLK_F_USER_RECOVERY is enabled. + * + * Note, this command returns -EBUSY in case that all IO commands are being + * handled by ublk server and not completed in specified time period which + * is passed from the control command parameter. + */ +#define UBLK_F_QUIESCE (1ULL << 12) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From ba3d7b93dbe3202bf8ead473d75885af773068bc Mon Sep 17 00:00:00 2001 From: Jordan Rife Date: Wed, 21 May 2025 23:27:06 +0200 Subject: wireguard: allowedips: add WGALLOWEDIP_F_REMOVE_ME flag The current netlink API for WireGuard does not directly support removal of allowed ips from a peer. A user can remove an allowed ip from a peer in one of two ways: 1. By using the WGPEER_F_REPLACE_ALLOWEDIPS flag and providing a new list of allowed ips which omits the allowed ip that is to be removed. 2. By reassigning an allowed ip to a "dummy" peer then removing that peer with WGPEER_F_REMOVE_ME. With the first approach, the driver completely rebuilds the allowed ip list for a peer. If my current configuration is such that a peer has allowed ips 192.168.0.2 and 192.168.0.3 and I want to remove 192.168.0.2 the actual transition looks like this. [192.168.0.2, 192.168.0.3] <-- Initial state [] <-- Step 1: Allowed ips removed for peer [192.168.0.3] <-- Step 2: Allowed ips added back for peer This is true even if the allowed ip list is small and the update does not need to be batched into multiple WG_CMD_SET_DEVICE requests, as the removal and subsequent addition of ips is non-atomic within a single request. Consequently, wg_allowedips_lookup_dst and wg_allowedips_lookup_src may return NULL while reconfiguring a peer even for packets bound for ips a user did not intend to remove leading to unintended interruptions in connectivity. This presents in userspace as failed calls to sendto and sendmsg for UDP sockets. In my case, I ran netperf while repeatedly reconfiguring the allowed ips for a peer with wg. /usr/local/bin/netperf -H 10.102.73.72 -l 10m -t UDP_STREAM -- -R 1 -m 1024 send_data: data send error: No route to host (errno 113) netperf: send_omni: send_data failed: No route to host While this may not be of particular concern for environments where peers and allowed ips are mostly static, systems like Cilium manage peers and allowed ips in a dynamic environment where peers (i.e. Kubernetes nodes) and allowed ips (i.e. pods running on those nodes) can frequently change making WGPEER_F_REPLACE_ALLOWEDIPS problematic. The second approach avoids any possible connectivity interruptions but is hacky and less direct, requiring the creation of a temporary peer just to dispose of an allowed ip. Introduce a new flag called WGALLOWEDIP_F_REMOVE_ME which in the same way that WGPEER_F_REMOVE_ME allows a user to remove a single peer from a WireGuard device's configuration allows a user to remove an ip from a peer's set of allowed ips. This enables incremental updates to a device's configuration without any connectivity blips or messy workarounds. A corresponding patch for wg extends the existing `wg set` interface to leverage this feature. $ wg set wg0 peer allowed-ips +192.168.88.0/24,-192.168.0.1/32 When '+' or '-' is prepended to any ip in the list, wg clears WGPEER_F_REPLACE_ALLOWEDIPS and sets the WGALLOWEDIP_F_REMOVE_ME flag on any ip prefixed with '-'. Signed-off-by: Jordan Rife [Jason: minor style nits, fixes to selftest, bump of wireguard-tools version] Signed-off-by: Jason A. Donenfeld Link: https://patch.msgid.link/20250521212707.1767879-5-Jason@zx2c4.com Signed-off-by: Paolo Abeni --- drivers/net/wireguard/allowedips.c | 102 +++++++++++++++++------- drivers/net/wireguard/allowedips.h | 4 + drivers/net/wireguard/netlink.c | 37 ++++++--- drivers/net/wireguard/selftest/allowedips.c | 48 +++++++++++ include/uapi/linux/wireguard.h | 9 +++ tools/testing/selftests/wireguard/netns.sh | 29 +++++++ tools/testing/selftests/wireguard/qemu/Makefile | 2 +- 7 files changed, 187 insertions(+), 44 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 4b8528206cc8..09f7fcd7da78 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -249,6 +249,52 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, return 0; } +static void remove_node(struct allowedips_node *node, struct mutex *lock) +{ + struct allowedips_node *child, **parent_bit, *parent; + bool free_parent; + + list_del_init(&node->peer_list); + RCU_INIT_POINTER(node->peer, NULL); + if (node->bit[0] && node->bit[1]) + return; + child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); + if (child) + child->parent_bit_packed = node->parent_bit_packed; + parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); + *parent_bit = child; + parent = (void *)parent_bit - + offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); + free_parent = !rcu_access_pointer(node->bit[0]) && !rcu_access_pointer(node->bit[1]) && + (node->parent_bit_packed & 3) <= 1 && !rcu_access_pointer(parent->peer); + if (free_parent) + child = rcu_dereference_protected(parent->bit[!(node->parent_bit_packed & 1)], + lockdep_is_held(lock)); + call_rcu(&node->rcu, node_free_rcu); + if (!free_parent) + return; + if (child) + child->parent_bit_packed = parent->parent_bit_packed; + *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; + call_rcu(&parent->rcu, node_free_rcu); +} + +static int remove(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + struct allowedips_node *node; + + if (unlikely(cidr > bits)) + return -EINVAL; + if (!rcu_access_pointer(*trie) || !node_placement(*trie, key, cidr, bits, &node, lock) || + peer != rcu_access_pointer(node->peer)) + return 0; + + remove_node(node, lock); + return 0; +} + void wg_allowedips_init(struct allowedips *table) { table->root4 = table->root6 = NULL; @@ -300,44 +346,38 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, return add(&table->root6, 128, key, cidr, peer, lock); } +int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + /* Aligned so it can be passed to fls */ + u8 key[4] __aligned(__alignof(u32)); + + ++table->seq; + swap_endian(key, (const u8 *)ip, 32); + return remove(&table->root4, 32, key, cidr, peer, lock); +} + +int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + /* Aligned so it can be passed to fls64 */ + u8 key[16] __aligned(__alignof(u64)); + + ++table->seq; + swap_endian(key, (const u8 *)ip, 128); + return remove(&table->root6, 128, key, cidr, peer, lock); +} + void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { - struct allowedips_node *node, *child, **parent_bit, *parent, *tmp; - bool free_parent; + struct allowedips_node *node, *tmp; if (list_empty(&peer->allowedips_list)) return; ++table->seq; - list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) { - list_del_init(&node->peer_list); - RCU_INIT_POINTER(node->peer, NULL); - if (node->bit[0] && node->bit[1]) - continue; - child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], - lockdep_is_held(lock)); - if (child) - child->parent_bit_packed = node->parent_bit_packed; - parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); - *parent_bit = child; - parent = (void *)parent_bit - - offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); - free_parent = !rcu_access_pointer(node->bit[0]) && - !rcu_access_pointer(node->bit[1]) && - (node->parent_bit_packed & 3) <= 1 && - !rcu_access_pointer(parent->peer); - if (free_parent) - child = rcu_dereference_protected( - parent->bit[!(node->parent_bit_packed & 1)], - lockdep_is_held(lock)); - call_rcu(&node->rcu, node_free_rcu); - if (!free_parent) - continue; - if (child) - child->parent_bit_packed = parent->parent_bit_packed; - *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; - call_rcu(&parent->rcu, node_free_rcu); - } + list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) + remove_node(node, lock); } int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr) diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h index 2346c797eb4d..931958cb6e10 100644 --- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -38,6 +38,10 @@ int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip, u8 cidr, struct wg_peer *peer, struct mutex *lock); int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, u8 cidr, struct wg_peer *peer, struct mutex *lock); +int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock); +int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock); void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock); /* The ip input pointer should be __aligned(__alignof(u64))) */ diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index bbb1a7fe1c57..67f962eb8b46 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -46,7 +46,8 @@ static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = { [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 }, [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)), - [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 } + [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }, + [WGALLOWEDIP_A_FLAGS] = NLA_POLICY_MASK(NLA_U32, __WGALLOWEDIP_F_ALL), }; static struct wg_device *lookup_interface(struct nlattr **attrs, @@ -329,6 +330,7 @@ static int set_port(struct wg_device *wg, u16 port) static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs) { int ret = -EINVAL; + u32 flags = 0; u16 family; u8 cidr; @@ -337,19 +339,30 @@ static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs) return ret; family = nla_get_u16(attrs[WGALLOWEDIP_A_FAMILY]); cidr = nla_get_u8(attrs[WGALLOWEDIP_A_CIDR_MASK]); + if (attrs[WGALLOWEDIP_A_FLAGS]) + flags = nla_get_u32(attrs[WGALLOWEDIP_A_FLAGS]); if (family == AF_INET && cidr <= 32 && - nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr)) - ret = wg_allowedips_insert_v4( - &peer->device->peer_allowedips, - nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, - &peer->device->device_update_lock); - else if (family == AF_INET6 && cidr <= 128 && - nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr)) - ret = wg_allowedips_insert_v6( - &peer->device->peer_allowedips, - nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, - &peer->device->device_update_lock); + nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr)) { + if (flags & WGALLOWEDIP_F_REMOVE_ME) + ret = wg_allowedips_remove_v4(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, + peer, &peer->device->device_update_lock); + else + ret = wg_allowedips_insert_v4(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, + peer, &peer->device->device_update_lock); + } else if (family == AF_INET6 && cidr <= 128 && + nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr)) { + if (flags & WGALLOWEDIP_F_REMOVE_ME) + ret = wg_allowedips_remove_v6(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, + peer, &peer->device->device_update_lock); + else + ret = wg_allowedips_insert_v6(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, + peer, &peer->device->device_update_lock); + } return ret; } diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 25de7058701a..41837efa70cb 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -460,6 +460,10 @@ static __init struct wg_peer *init_peer(void) wg_allowedips_insert_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \ cidr, mem, &mutex) +#define remove(version, mem, ipa, ipb, ipc, ipd, cidr) \ + wg_allowedips_remove_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \ + cidr, mem, &mutex) + #define maybe_fail() do { \ ++i; \ if (!_s) { \ @@ -585,6 +589,50 @@ bool __init wg_allowedips_selftest(void) test_negative(4, a, 192, 0, 0, 0); test_negative(4, a, 255, 0, 0, 0); + insert(4, a, 1, 0, 0, 0, 32); + insert(4, a, 192, 0, 0, 0, 24); + insert(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128); + insert(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test(4, a, 1, 0, 0, 0); + test(4, a, 192, 0, 0, 1); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + test(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + /* Must be an exact match to remove */ + remove(4, a, 192, 0, 0, 0, 32); + test(4, a, 192, 0, 0, 1); + /* NULL peer should have no effect and return 0 */ + test_boolean(!remove(4, NULL, 192, 0, 0, 0, 24)); + test(4, a, 192, 0, 0, 1); + /* different peer should have no effect and return 0 */ + test_boolean(!remove(4, b, 192, 0, 0, 0, 24)); + test(4, a, 192, 0, 0, 1); + /* invalid CIDR should have no effect and return -EINVAL */ + test_boolean(remove(4, b, 192, 0, 0, 0, 33) == -EINVAL); + test(4, a, 192, 0, 0, 1); + remove(4, a, 192, 0, 0, 0, 24); + test_negative(4, a, 192, 0, 0, 1); + remove(4, a, 1, 0, 0, 0, 32); + test_negative(4, a, 1, 0, 0, 0); + /* Must be an exact match to remove */ + remove(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 96); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + /* NULL peer should have no effect and return 0 */ + test_boolean(!remove(6, NULL, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128)); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + /* different peer should have no effect and return 0 */ + test_boolean(!remove(6, b, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128)); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + /* invalid CIDR should have no effect and return -EINVAL */ + test_boolean(remove(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 129) == -EINVAL); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + remove(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128); + test_negative(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + /* Must match the peer to remove */ + remove(6, b, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + remove(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test_negative(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); insert(4, a, 192, 168, 0, 0, 16); diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index ae88be14c947..8c26391196d5 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -101,6 +101,10 @@ * WGALLOWEDIP_A_FAMILY: NLA_U16 * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 + * WGALLOWEDIP_A_FLAGS: NLA_U32, WGALLOWEDIP_F_REMOVE_ME if + * the specified IP should be removed; + * otherwise, this IP will be added if + * it is not already present. * 0: NLA_NESTED * ... * 0: NLA_NESTED @@ -184,11 +188,16 @@ enum wgpeer_attribute { }; #define WGPEER_A_MAX (__WGPEER_A_LAST - 1) +enum wgallowedip_flag { + WGALLOWEDIP_F_REMOVE_ME = 1U << 0, + __WGALLOWEDIP_F_ALL = WGALLOWEDIP_F_REMOVE_ME +}; enum wgallowedip_attribute { WGALLOWEDIP_A_UNSPEC, WGALLOWEDIP_A_FAMILY, WGALLOWEDIP_A_IPADDR, WGALLOWEDIP_A_CIDR_MASK, + WGALLOWEDIP_A_FLAGS, __WGALLOWEDIP_A_LAST }; #define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 55500f901fbc..a8f550aecb35 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -611,6 +611,35 @@ n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" } < <(n0 wg show wg0 allowed-ips) ip0 link del wg0 +allowedips=( ) +for i in {1..197}; do + allowedips+=( 192.168.0.$i ) + allowedips+=( abcd::$i ) +done +saved_ifs="$IFS" +IFS=, +allowedips="${allowedips[*]}" +IFS="$saved_ifs" +ip0 link add wg0 type wireguard +n0 wg set wg0 peer "$pub1" allowed-ips "$allowedips" +n0 wg set wg0 peer "$pub1" allowed-ips -192.168.0.1/32,-192.168.0.20/32,-192.168.0.100/32,-abcd::1/128,-abcd::20/128,-abcd::100/128 +{ + read -r pub allowedips + [[ $pub == "$pub1" ]] + i=0 + for ip in $allowedips; do + [[ $ip != "192.168.0.1" ]] + [[ $ip != "192.168.0.20" ]] + [[ $ip != "192.168.0.100" ]] + [[ $ip != "abcd::1" ]] + [[ $ip != "abcd::20" ]] + [[ $ip != "abcd::100" ]] + ((++i)) + done + ((i == 388)) +} < <(n0 wg show wg0 allowed-ips) +ip0 link del wg0 + ! n0 wg show doesnotexist || false ip0 link add wg0 type wireguard diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index 35856b11c143..f6fbd88914ee 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -43,7 +43,7 @@ $(eval $(call tar_download,IPROUTE2,iproute2,5.17.0,.tar.gz,https://www.kernel.o $(eval $(call tar_download,IPTABLES,iptables,1.8.7,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,c109c96bb04998cd44156622d36f8e04b140701ec60531a10668cfdff5e8d8f0)) $(eval $(call tar_download,NMAP,nmap,7.92,.tgz,https://nmap.org/dist/,064183ea642dc4c12b1ab3b5358ce1cef7d2e7e11ffa2849f16d339f5b717117)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20210914,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,97ff31489217bb265b7ae850d3d0f335ab07d2652ba1feec88b734bc96bd05ac)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20250521,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,b6f2628b85b1b23cc06517ec9c74f82d52c4cdbd020f3dd2f00c972a1782950e)) export CFLAGS := -O3 -pipe ifeq ($(HOST_ARCH),$(ARCH)) -- cgit v1.2.3 From 0623c759276885c3ae88197ba6fb5c9c6ba8612f Mon Sep 17 00:00:00 2001 From: Peter Hilber Date: Fri, 9 May 2025 18:07:22 +0200 Subject: virtio_rtc: Add module and driver core Add the virtio_rtc module and driver core. The virtio_rtc module implements a driver compatible with the proposed Virtio RTC device specification. The Virtio RTC (Real Time Clock) device provides information about current time. The device can provide different clocks, e.g. for the UTC or TAI time standards, or for physical time elapsed since some past epoch. The driver can read the clocks with simple or more accurate methods. Implement the core, which interacts with the Virtio RTC device. Apart from this, the core does not expose functionality outside of the virtio_rtc module. Follow-up patches will expose PTP clocks and an RTC Class device. Provide synchronous messaging, which is enough for the expected time synchronization use cases through PTP clocks (similar to ptp_kvm) or RTC Class device. Signed-off-by: Peter Hilber Message-Id: <20250509160734.1772-2-quic_philber@quicinc.com> Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 7 + drivers/virtio/Kconfig | 13 + drivers/virtio/Makefile | 2 + drivers/virtio/virtio_rtc_driver.c | 786 +++++++++++++++++++++++++++++++++++ drivers/virtio/virtio_rtc_internal.h | 24 ++ include/uapi/linux/virtio_rtc.h | 151 +++++++ 6 files changed, 983 insertions(+) create mode 100644 drivers/virtio/virtio_rtc_driver.c create mode 100644 drivers/virtio/virtio_rtc_internal.h create mode 100644 include/uapi/linux/virtio_rtc.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index d48dd6726fe6..56c487bbea9c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25827,6 +25827,13 @@ S: Maintained F: drivers/nvdimm/nd_virtio.c F: drivers/nvdimm/virtio_pmem.c +VIRTIO RTC DRIVER +M: Peter Hilber +L: virtualization@lists.linux.dev +S: Maintained +F: drivers/virtio/virtio_rtc_* +F: include/uapi/linux/virtio_rtc.h + VIRTIO SOUND DRIVER M: Anton Yakovlev M: "Michael S. Tsirkin" diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 2eb747311bfd..83bcb06acb6c 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -188,4 +188,17 @@ config VIRTIO_DEBUG If unsure, say N. +config VIRTIO_RTC + tristate "Virtio RTC driver" + depends on VIRTIO + depends on PTP_1588_CLOCK_OPTIONAL + help + This driver provides current time from a Virtio RTC device. The driver + provides the time through one or more clocks. + + To compile this code as a module, choose M here: the module will be + called virtio_rtc. + + If unsure, say M. + endif # VIRTIO_MENU diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 58b2b0489fc9..c41c4c0f9264 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -14,3 +14,5 @@ obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o obj-$(CONFIG_VIRTIO_MEM) += virtio_mem.o obj-$(CONFIG_VIRTIO_DMA_SHARED_BUFFER) += virtio_dma_buf.o obj-$(CONFIG_VIRTIO_DEBUG) += virtio_debug.o +obj-$(CONFIG_VIRTIO_RTC) += virtio_rtc.o +virtio_rtc-y := virtio_rtc_driver.o diff --git a/drivers/virtio/virtio_rtc_driver.c b/drivers/virtio/virtio_rtc_driver.c new file mode 100644 index 000000000000..c87ee4e63424 --- /dev/null +++ b/drivers/virtio/virtio_rtc_driver.c @@ -0,0 +1,786 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * virtio_rtc driver core + * + * Copyright (C) 2022-2024 OpenSynergy GmbH + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "virtio_rtc_internal.h" + +/* virtqueue order */ +enum { + VIORTC_REQUESTQ, + VIORTC_MAX_NR_QUEUES, +}; + +/** + * struct viortc_vq - virtqueue abstraction + * @vq: virtqueue + * @lock: protects access to vq + */ +struct viortc_vq { + struct virtqueue *vq; + spinlock_t lock; +}; + +/** + * struct viortc_dev - virtio_rtc device data + * @vdev: virtio device + * @vqs: virtqueues + * @num_clocks: # of virtio_rtc clocks + */ +struct viortc_dev { + struct virtio_device *vdev; + struct viortc_vq vqs[VIORTC_MAX_NR_QUEUES]; + u16 num_clocks; +}; + +/** + * struct viortc_msg - Message requested by driver, responded by device. + * @viortc: device data + * @req: request buffer + * @resp: response buffer + * @responded: vqueue callback signals response reception + * @refcnt: Message reference count, message and buffers will be deallocated + * once 0. refcnt is decremented in the vqueue callback and in the + * thread waiting on the responded completion. + * If a message response wait function times out, the message will be + * freed upon late reception (refcnt will reach 0 in the callback), or + * device removal. + * @req_size: size of request in bytes + * @resp_cap: maximum size of response in bytes + * @resp_actual_size: actual size of response + */ +struct viortc_msg { + struct viortc_dev *viortc; + void *req; + void *resp; + struct completion responded; + refcount_t refcnt; + unsigned int req_size; + unsigned int resp_cap; + unsigned int resp_actual_size; +}; + +/** + * viortc_msg_init() - Allocate and initialize requestq message. + * @viortc: device data + * @msg_type: virtio_rtc message type + * @req_size: size of request buffer to be allocated + * @resp_cap: size of response buffer to be allocated + * + * Initializes the message refcnt to 2. The refcnt will be decremented once in + * the virtqueue callback, and once in the thread waiting on the message (on + * completion or timeout). + * + * Context: Process context. + * Return: non-NULL on success. + */ +static struct viortc_msg *viortc_msg_init(struct viortc_dev *viortc, + u16 msg_type, unsigned int req_size, + unsigned int resp_cap) +{ + struct device *dev = &viortc->vdev->dev; + struct virtio_rtc_req_head *req_head; + struct viortc_msg *msg; + + msg = devm_kzalloc(dev, sizeof(*msg), GFP_KERNEL); + if (!msg) + return NULL; + + init_completion(&msg->responded); + + msg->req = devm_kzalloc(dev, req_size, GFP_KERNEL); + if (!msg->req) + goto err_free_msg; + + req_head = msg->req; + + msg->resp = devm_kzalloc(dev, resp_cap, GFP_KERNEL); + if (!msg->resp) + goto err_free_msg_req; + + msg->viortc = viortc; + msg->req_size = req_size; + msg->resp_cap = resp_cap; + + refcount_set(&msg->refcnt, 2); + + req_head->msg_type = virtio_cpu_to_le(msg_type, req_head->msg_type); + + return msg; + +err_free_msg_req: + devm_kfree(dev, msg->req); + +err_free_msg: + devm_kfree(dev, msg); + + return NULL; +} + +/** + * viortc_msg_release() - Decrement message refcnt, potentially free message. + * @msg: message requested by driver + * + * Context: Any context. + */ +static void viortc_msg_release(struct viortc_msg *msg) +{ + struct device *dev; + + if (refcount_dec_and_test(&msg->refcnt)) { + dev = &msg->viortc->vdev->dev; + + devm_kfree(dev, msg->req); + devm_kfree(dev, msg->resp); + devm_kfree(dev, msg); + } +} + +/** + * viortc_do_cb() - generic virtqueue callback logic + * @vq: virtqueue + * @handle_buf: function to process a used buffer + * + * Context: virtqueue callback, typically interrupt. Takes and releases vq lock. + */ +static void viortc_do_cb(struct virtqueue *vq, + void (*handle_buf)(void *token, unsigned int len, + struct virtqueue *vq, + struct viortc_vq *viortc_vq, + struct viortc_dev *viortc)) +{ + struct viortc_dev *viortc = vq->vdev->priv; + struct viortc_vq *viortc_vq; + bool cb_enabled = true; + unsigned long flags; + unsigned int len; + void *token; + + viortc_vq = &viortc->vqs[vq->index]; + + for (;;) { + spin_lock_irqsave(&viortc_vq->lock, flags); + + if (cb_enabled) { + virtqueue_disable_cb(vq); + cb_enabled = false; + } + + token = virtqueue_get_buf(vq, &len); + if (!token) { + if (virtqueue_enable_cb(vq)) { + spin_unlock_irqrestore(&viortc_vq->lock, flags); + return; + } + cb_enabled = true; + } + + spin_unlock_irqrestore(&viortc_vq->lock, flags); + + if (token) + handle_buf(token, len, vq, viortc_vq, viortc); + } +} + +/** + * viortc_requestq_hdlr() - process a requestq used buffer + * @token: token identifying the buffer + * @len: bytes written by device + * @vq: virtqueue + * @viortc_vq: device specific data for virtqueue + * @viortc: device data + * + * Signals completion for each received message. + * + * Context: virtqueue callback + */ +static void viortc_requestq_hdlr(void *token, unsigned int len, + struct virtqueue *vq, + struct viortc_vq *viortc_vq, + struct viortc_dev *viortc) +{ + struct viortc_msg *msg = token; + + msg->resp_actual_size = len; + + complete(&msg->responded); + viortc_msg_release(msg); +} + +/** + * viortc_cb_requestq() - callback for requestq + * @vq: virtqueue + * + * Context: virtqueue callback + */ +static void viortc_cb_requestq(struct virtqueue *vq) +{ + viortc_do_cb(vq, viortc_requestq_hdlr); +} + +/** + * viortc_get_resp_errno() - converts virtio_rtc errnos to system errnos + * @resp_head: message response header + * + * Return: negative system errno, or 0 + */ +static int viortc_get_resp_errno(struct virtio_rtc_resp_head *resp_head) +{ + switch (virtio_le_to_cpu(resp_head->status)) { + case VIRTIO_RTC_S_OK: + return 0; + case VIRTIO_RTC_S_EOPNOTSUPP: + return -EOPNOTSUPP; + case VIRTIO_RTC_S_EINVAL: + return -EINVAL; + case VIRTIO_RTC_S_ENODEV: + return -ENODEV; + case VIRTIO_RTC_S_EIO: + default: + return -EIO; + } +} + +/** + * viortc_msg_xfer() - send message request, wait until message response + * @vq: virtqueue + * @msg: message with driver request + * @timeout_jiffies: message response timeout, 0 for no timeout + * + * Context: Process context. Takes and releases vq.lock. May sleep. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_msg_xfer(struct viortc_vq *vq, struct viortc_msg *msg, + unsigned long timeout_jiffies) +{ + struct scatterlist out_sg[1]; + struct scatterlist in_sg[1]; + struct scatterlist *sgs[2]; + unsigned long flags; + long timeout_ret; + bool notify; + int ret; + + sgs[0] = out_sg; + sgs[1] = in_sg; + + sg_init_one(out_sg, msg->req, msg->req_size); + sg_init_one(in_sg, msg->resp, msg->resp_cap); + + spin_lock_irqsave(&vq->lock, flags); + + ret = virtqueue_add_sgs(vq->vq, sgs, 1, 1, msg, GFP_ATOMIC); + if (ret) { + spin_unlock_irqrestore(&vq->lock, flags); + /* + * Release in place of the response callback, which will never + * come. + */ + viortc_msg_release(msg); + return ret; + } + + notify = virtqueue_kick_prepare(vq->vq); + + spin_unlock_irqrestore(&vq->lock, flags); + + if (notify) + virtqueue_notify(vq->vq); + + if (timeout_jiffies) { + timeout_ret = wait_for_completion_interruptible_timeout( + &msg->responded, timeout_jiffies); + + if (!timeout_ret) + return -ETIMEDOUT; + else if (timeout_ret < 0) + return (int)timeout_ret; + } else { + ret = wait_for_completion_interruptible(&msg->responded); + if (ret) + return ret; + } + + if (msg->resp_actual_size < sizeof(struct virtio_rtc_resp_head)) + return -EINVAL; + + ret = viortc_get_resp_errno(msg->resp); + if (ret) + return ret; + + /* + * There is not yet a case where returning a short message would make + * sense, so consider any deviation an error. + */ + if (msg->resp_actual_size != msg->resp_cap) + return -EINVAL; + + return 0; +} + +/* + * common message handle macros for messages of different types + */ + +/** + * VIORTC_DECLARE_MSG_HDL_ONSTACK() - declare message handle on stack + * @hdl: message handle name + * @msg_id: message type id + * @msg_req: message request type + * @msg_resp: message response type + */ +#define VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, msg_id, msg_req, msg_resp) \ + struct { \ + struct viortc_msg *msg; \ + msg_req *req; \ + msg_resp *resp; \ + unsigned int req_size; \ + unsigned int resp_cap; \ + u16 msg_type; \ + } hdl = { \ + NULL, NULL, NULL, sizeof(msg_req), sizeof(msg_resp), (msg_id), \ + } + +/** + * VIORTC_MSG() - extract message from message handle + * @hdl: message handle + * + * Return: struct viortc_msg + */ +#define VIORTC_MSG(hdl) ((hdl).msg) + +/** + * VIORTC_MSG_INIT() - initialize message handle + * @hdl: message handle + * @viortc: device data (struct viortc_dev *) + * + * Context: Process context. + * Return: 0 on success, -ENOMEM otherwise. + */ +#define VIORTC_MSG_INIT(hdl, viortc) \ + ({ \ + typeof(hdl) *_hdl = &(hdl); \ + \ + _hdl->msg = viortc_msg_init((viortc), _hdl->msg_type, \ + _hdl->req_size, _hdl->resp_cap); \ + if (_hdl->msg) { \ + _hdl->req = _hdl->msg->req; \ + _hdl->resp = _hdl->msg->resp; \ + } \ + _hdl->msg ? 0 : -ENOMEM; \ + }) + +/** + * VIORTC_MSG_WRITE() - write a request message field + * @hdl: message handle + * @dest_member: request message field name + * @src_ptr: pointer to data of compatible type + * + * Writes the field in little-endian format. + */ +#define VIORTC_MSG_WRITE(hdl, dest_member, src_ptr) \ + do { \ + typeof(hdl) _hdl = (hdl); \ + typeof(src_ptr) _src_ptr = (src_ptr); \ + \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu(_hdl.req->dest_member)), \ + *_src_ptr); \ + \ + _hdl.req->dest_member = \ + virtio_cpu_to_le(*_src_ptr, _hdl.req->dest_member); \ + } while (0) + +/** + * VIORTC_MSG_READ() - read from a response message field + * @hdl: message handle + * @src_member: response message field name + * @dest_ptr: pointer to data of compatible type + * + * Converts from little-endian format and writes to dest_ptr. + */ +#define VIORTC_MSG_READ(hdl, src_member, dest_ptr) \ + do { \ + typeof(dest_ptr) _dest_ptr = (dest_ptr); \ + \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu((hdl).resp->src_member)), \ + *_dest_ptr); \ + \ + *_dest_ptr = virtio_le_to_cpu((hdl).resp->src_member); \ + } while (0) + +/* + * read requests + */ + +/** timeout for clock readings, where timeouts are considered non-fatal */ +#define VIORTC_MSG_READ_TIMEOUT secs_to_jiffies(60) + +/** + * viortc_read() - VIRTIO_RTC_REQ_READ wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @reading: clock reading [ns] + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_read(struct viortc_dev *viortc, u16 vio_clk_id, u64 *reading) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_READ, + struct virtio_rtc_req_read, + struct virtio_rtc_resp_read); + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + VIORTC_MSG_READ_TIMEOUT); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, clock_reading, reading); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/** + * viortc_read_cross() - VIRTIO_RTC_REQ_READ_CROSS wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @hw_counter: virtio_rtc HW counter type + * @reading: clock reading [ns] + * @cycles: HW counter cycles during clock reading + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_read_cross(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, + u64 *reading, u64 *cycles) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_READ_CROSS, + struct virtio_rtc_req_read_cross, + struct virtio_rtc_resp_read_cross); + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + VIORTC_MSG_WRITE(hdl, hw_counter, &hw_counter); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + VIORTC_MSG_READ_TIMEOUT); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, clock_reading, reading); + VIORTC_MSG_READ(hdl, counter_cycles, cycles); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/* + * control requests + */ + +/** + * viortc_cfg() - VIRTIO_RTC_REQ_CFG wrapper + * @viortc: device data + * @num_clocks: # of virtio_rtc clocks + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_cfg(struct viortc_dev *viortc, u16 *num_clocks) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_CFG, + struct virtio_rtc_req_cfg, + struct virtio_rtc_resp_cfg); + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, num_clocks, num_clocks); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/** + * viortc_clock_cap() - VIRTIO_RTC_REQ_CLOCK_CAP wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @type: virtio_rtc clock type + * @leap_second_smearing: virtio_rtc smearing variant + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_clock_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 *type, + u8 *leap_second_smearing) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_CLOCK_CAP, + struct virtio_rtc_req_clock_cap, + struct virtio_rtc_resp_clock_cap); + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, type, type); + VIORTC_MSG_READ(hdl, leap_second_smearing, leap_second_smearing); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/** + * viortc_cross_cap() - VIRTIO_RTC_REQ_CROSS_CAP wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @hw_counter: virtio_rtc HW counter type + * @supported: xtstamping is supported for the vio_clk_id/hw_counter pair + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_cross_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, + bool *supported) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_CROSS_CAP, + struct virtio_rtc_req_cross_cap, + struct virtio_rtc_resp_cross_cap); + u8 flags; + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + VIORTC_MSG_WRITE(hdl, hw_counter, &hw_counter); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, flags, &flags); + *supported = !!(flags & VIRTIO_RTC_FLAG_CROSS_CAP); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/* + * init, deinit + */ + +/** + * viortc_clocks_init() - init local representations of virtio_rtc clocks + * @viortc: device data + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_clocks_init(struct viortc_dev *viortc) +{ + u16 num_clocks; + int ret; + + ret = viortc_cfg(viortc, &num_clocks); + if (ret) + return ret; + + if (num_clocks < 1) { + dev_err(&viortc->vdev->dev, "device reported 0 clocks\n"); + return -ENODEV; + } + + viortc->num_clocks = num_clocks; + + /* In the future, PTP clocks will be initialized here. */ + (void)viortc_clock_cap; + + return ret; +} + +/** + * viortc_init_vqs() - init virtqueues + * @viortc: device data + * + * Inits virtqueues and associated data. + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_init_vqs(struct viortc_dev *viortc) +{ + struct virtqueue *vqs[VIORTC_MAX_NR_QUEUES]; + struct virtqueue_info vqs_info[] = { + { "requestq", viortc_cb_requestq }, + }; + struct virtio_device *vdev = viortc->vdev; + int nr_queues, ret; + + nr_queues = VIORTC_REQUESTQ + 1; + + ret = virtio_find_vqs(vdev, nr_queues, vqs, vqs_info, NULL); + if (ret) + return ret; + + viortc->vqs[VIORTC_REQUESTQ].vq = vqs[VIORTC_REQUESTQ]; + spin_lock_init(&viortc->vqs[VIORTC_REQUESTQ].lock); + + return 0; +} + +/** + * viortc_probe() - probe a virtio_rtc virtio device + * @vdev: virtio device + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_probe(struct virtio_device *vdev) +{ + struct viortc_dev *viortc; + int ret; + + viortc = devm_kzalloc(&vdev->dev, sizeof(*viortc), GFP_KERNEL); + if (!viortc) + return -ENOMEM; + + vdev->priv = viortc; + viortc->vdev = vdev; + + ret = viortc_init_vqs(viortc); + if (ret) + return ret; + + virtio_device_ready(vdev); + + ret = viortc_clocks_init(viortc); + if (ret) + goto err_reset_vdev; + + return 0; + +err_reset_vdev: + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); + + return ret; +} + +/** + * viortc_remove() - remove a virtio_rtc virtio device + * @vdev: virtio device + */ +static void viortc_remove(struct virtio_device *vdev) +{ + /* In the future, PTP clocks will be deinitialized here. */ + + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); +} + +static int viortc_freeze(struct virtio_device *dev) +{ + /* + * Do not reset the device, so that the device may still wake up the + * system through an alarmq notification. + */ + + return 0; +} + +static int viortc_restore(struct virtio_device *dev) +{ + struct viortc_dev *viortc = dev->priv; + + return viortc_init_vqs(viortc); +} + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_CLOCK, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; +MODULE_DEVICE_TABLE(virtio, id_table); + +static struct virtio_driver virtio_rtc_drv = { + .driver.name = KBUILD_MODNAME, + .id_table = id_table, + .probe = viortc_probe, + .remove = viortc_remove, + .freeze = pm_sleep_ptr(viortc_freeze), + .restore = pm_sleep_ptr(viortc_restore), +}; + +module_virtio_driver(virtio_rtc_drv); + +MODULE_DESCRIPTION("Virtio RTC driver"); +MODULE_AUTHOR("Qualcomm Innovation Center, Inc."); +MODULE_LICENSE("GPL"); diff --git a/drivers/virtio/virtio_rtc_internal.h b/drivers/virtio/virtio_rtc_internal.h new file mode 100644 index 000000000000..9c249c15b68f --- /dev/null +++ b/drivers/virtio/virtio_rtc_internal.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * virtio_rtc internal interfaces + * + * Copyright (C) 2022-2023 OpenSynergy GmbH + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _VIRTIO_RTC_INTERNAL_H_ +#define _VIRTIO_RTC_INTERNAL_H_ + +#include + +/* driver core IFs */ + +struct viortc_dev; + +int viortc_read(struct viortc_dev *viortc, u16 vio_clk_id, u64 *reading); +int viortc_read_cross(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, + u64 *reading, u64 *cycles); +int viortc_cross_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, + bool *supported); + +#endif /* _VIRTIO_RTC_INTERNAL_H_ */ diff --git a/include/uapi/linux/virtio_rtc.h b/include/uapi/linux/virtio_rtc.h new file mode 100644 index 000000000000..6b3af4e9bbfb --- /dev/null +++ b/include/uapi/linux/virtio_rtc.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* + * Copyright (C) 2022-2024 OpenSynergy GmbH + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _LINUX_VIRTIO_RTC_H +#define _LINUX_VIRTIO_RTC_H + +#include + +/* read request message types */ + +#define VIRTIO_RTC_REQ_READ 0x0001 +#define VIRTIO_RTC_REQ_READ_CROSS 0x0002 + +/* control request message types */ + +#define VIRTIO_RTC_REQ_CFG 0x1000 +#define VIRTIO_RTC_REQ_CLOCK_CAP 0x1001 +#define VIRTIO_RTC_REQ_CROSS_CAP 0x1002 + +/* Message headers */ + +/** common request header */ +struct virtio_rtc_req_head { + __le16 msg_type; + __u8 reserved[6]; +}; + +/** common response header */ +struct virtio_rtc_resp_head { +#define VIRTIO_RTC_S_OK 0 +#define VIRTIO_RTC_S_EOPNOTSUPP 2 +#define VIRTIO_RTC_S_ENODEV 3 +#define VIRTIO_RTC_S_EINVAL 4 +#define VIRTIO_RTC_S_EIO 5 + __u8 status; + __u8 reserved[7]; +}; + +/* read requests */ + +/* VIRTIO_RTC_REQ_READ message */ + +struct virtio_rtc_req_read { + struct virtio_rtc_req_head head; + __le16 clock_id; + __u8 reserved[6]; +}; + +struct virtio_rtc_resp_read { + struct virtio_rtc_resp_head head; + __le64 clock_reading; +}; + +/* VIRTIO_RTC_REQ_READ_CROSS message */ + +struct virtio_rtc_req_read_cross { + struct virtio_rtc_req_head head; + __le16 clock_id; +/* Arm Generic Timer Counter-timer Virtual Count Register (CNTVCT_EL0) */ +#define VIRTIO_RTC_COUNTER_ARM_VCT 0 +/* x86 Time-Stamp Counter */ +#define VIRTIO_RTC_COUNTER_X86_TSC 1 +/* Invalid */ +#define VIRTIO_RTC_COUNTER_INVALID 0xFF + __u8 hw_counter; + __u8 reserved[5]; +}; + +struct virtio_rtc_resp_read_cross { + struct virtio_rtc_resp_head head; + __le64 clock_reading; + __le64 counter_cycles; +}; + +/* control requests */ + +/* VIRTIO_RTC_REQ_CFG message */ + +struct virtio_rtc_req_cfg { + struct virtio_rtc_req_head head; + /* no request params */ +}; + +struct virtio_rtc_resp_cfg { + struct virtio_rtc_resp_head head; + /** # of clocks -> clock ids < num_clocks are valid */ + __le16 num_clocks; + __u8 reserved[6]; +}; + +/* VIRTIO_RTC_REQ_CLOCK_CAP message */ + +struct virtio_rtc_req_clock_cap { + struct virtio_rtc_req_head head; + __le16 clock_id; + __u8 reserved[6]; +}; + +struct virtio_rtc_resp_clock_cap { + struct virtio_rtc_resp_head head; +#define VIRTIO_RTC_CLOCK_UTC 0 +#define VIRTIO_RTC_CLOCK_TAI 1 +#define VIRTIO_RTC_CLOCK_MONOTONIC 2 +#define VIRTIO_RTC_CLOCK_UTC_SMEARED 3 +#define VIRTIO_RTC_CLOCK_UTC_MAYBE_SMEARED 4 + __u8 type; +#define VIRTIO_RTC_SMEAR_UNSPECIFIED 0 +#define VIRTIO_RTC_SMEAR_NOON_LINEAR 1 +#define VIRTIO_RTC_SMEAR_UTC_SLS 2 + __u8 leap_second_smearing; + __u8 reserved[6]; +}; + +/* VIRTIO_RTC_REQ_CROSS_CAP message */ + +struct virtio_rtc_req_cross_cap { + struct virtio_rtc_req_head head; + __le16 clock_id; + __u8 hw_counter; + __u8 reserved[5]; +}; + +struct virtio_rtc_resp_cross_cap { + struct virtio_rtc_resp_head head; +#define VIRTIO_RTC_FLAG_CROSS_CAP (1 << 0) + __u8 flags; + __u8 reserved[7]; +}; + +/** Union of request types for requestq */ +union virtio_rtc_req_requestq { + struct virtio_rtc_req_read read; + struct virtio_rtc_req_read_cross read_cross; + struct virtio_rtc_req_cfg cfg; + struct virtio_rtc_req_clock_cap clock_cap; + struct virtio_rtc_req_cross_cap cross_cap; +}; + +/** Union of response types for requestq */ +union virtio_rtc_resp_requestq { + struct virtio_rtc_resp_read read; + struct virtio_rtc_resp_read_cross read_cross; + struct virtio_rtc_resp_cfg cfg; + struct virtio_rtc_resp_clock_cap clock_cap; + struct virtio_rtc_resp_cross_cap cross_cap; +}; + +#endif /* _LINUX_VIRTIO_RTC_H */ -- cgit v1.2.3 From 9d4f22fd563e0cd02e8448e84d057e7c0132a586 Mon Sep 17 00:00:00 2001 From: Peter Hilber Date: Fri, 9 May 2025 18:07:25 +0200 Subject: virtio_rtc: Add RTC class driver Expose the virtio-rtc UTC-like clock as an RTC clock to userspace - if it is present, and if it does not step on leap seconds. The RTC class enables the virtio-rtc device to resume the system from sleep states on RTC alarm. Support RTC alarm if the virtio-rtc alarm feature is present. The virtio-rtc device signals an alarm by marking an alarmq buffer as used. Peculiarities ------------- A virtio-rtc clock is a bit special for an RTC clock in that - the clock may step (also backwards) autonomously at any time and - the device, and its notification mechanism, will be reset during boot or resume from sleep. The virtio-rtc device avoids that the driver might miss an alarm. The device signals an alarm whenever the clock has reached or passed the alarm time, and also when the device is reset (on boot or resume from sleep), if the alarm time is in the past. Open Issue ---------- The CLOCK_BOOTTIME_ALARM will use the RTC clock to wake up from sleep, and implicitly assumes that no RTC clock steps will occur during sleep. The RTC class driver does not know whether the current alarm is a real-time alarm or a boot-time alarm. Perhaps this might be handled by the driver also setting a virtio-rtc monotonic alarm (which uses a clock similar to CLOCK_BOOTTIME_ALARM). The virtio-rtc monotonic alarm would just be used to wake up in case it was a CLOCK_BOOTTIME_ALARM alarm. Otherwise, the behavior should not differ from other RTC class drivers. Signed-off-by: Peter Hilber Acked-by: Alexandre Belloni Message-Id: <20250509160734.1772-5-quic_philber@quicinc.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/Kconfig | 22 +- drivers/virtio/Makefile | 1 + drivers/virtio/virtio_rtc_class.c | 262 ++++++++++++++++++ drivers/virtio/virtio_rtc_driver.c | 520 ++++++++++++++++++++++++++++++++++- drivers/virtio/virtio_rtc_internal.h | 52 ++++ include/uapi/linux/virtio_rtc.h | 88 +++++- 6 files changed, 934 insertions(+), 11 deletions(-) create mode 100644 drivers/virtio/virtio_rtc_class.c (limited to 'include/uapi/linux') diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 3d8b366c0625..6db5235a7693 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -195,7 +195,8 @@ config VIRTIO_RTC help This driver provides current time from a Virtio RTC device. The driver provides the time through one or more clocks. The Virtio RTC PTP - clocks must be enabled to expose the clocks to userspace. + clocks and/or the Real Time Clock driver for Virtio RTC must be + enabled to expose the clocks to userspace. To compile this code as a module, choose M here: the module will be called virtio_rtc. @@ -204,8 +205,8 @@ config VIRTIO_RTC if VIRTIO_RTC -comment "WARNING: Consider enabling VIRTIO_RTC_PTP." - depends on !VIRTIO_RTC_PTP +comment "WARNING: Consider enabling VIRTIO_RTC_PTP and/or VIRTIO_RTC_CLASS." + depends on !VIRTIO_RTC_PTP && !VIRTIO_RTC_CLASS comment "Enable PTP_1588_CLOCK in order to enable VIRTIO_RTC_PTP." depends on PTP_1588_CLOCK=n @@ -234,6 +235,21 @@ config VIRTIO_RTC_ARM If unsure, say Y. +comment "Enable RTC_CLASS in order to enable VIRTIO_RTC_CLASS." + depends on RTC_CLASS=n + +config VIRTIO_RTC_CLASS + bool "Real Time Clock driver for Virtio RTC" + default y + depends on RTC_CLASS + help + This exposes the Virtio RTC UTC-like clock as a Linux Real Time Clock. + It only has an effect if the Virtio RTC device has a UTC-like clock + which smears leap seconds to avoid steps. The Real Time Clock is + read-only, and may support setting an alarm. + + If unsure, say Y. + endif # VIRTIO_RTC endif # VIRTIO_MENU diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index dbd77f124ba9..eefcfe90d6b8 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -18,3 +18,4 @@ obj-$(CONFIG_VIRTIO_RTC) += virtio_rtc.o virtio_rtc-y := virtio_rtc_driver.o virtio_rtc-$(CONFIG_VIRTIO_RTC_PTP) += virtio_rtc_ptp.o virtio_rtc-$(CONFIG_VIRTIO_RTC_ARM) += virtio_rtc_arm.o +virtio_rtc-$(CONFIG_VIRTIO_RTC_CLASS) += virtio_rtc_class.o diff --git a/drivers/virtio/virtio_rtc_class.c b/drivers/virtio/virtio_rtc_class.c new file mode 100644 index 000000000000..05d6d28255cf --- /dev/null +++ b/drivers/virtio/virtio_rtc_class.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * virtio_rtc RTC class driver + * + * Copyright (C) 2023 OpenSynergy GmbH + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include + +#include + +#include "virtio_rtc_internal.h" + +/** + * struct viortc_class - RTC class wrapper + * @viortc: virtio_rtc device data + * @rtc: RTC device + * @vio_clk_id: virtio_rtc clock id + * @stopped: Whether RTC ops are disallowed. Access protected by rtc_lock(). + */ +struct viortc_class { + struct viortc_dev *viortc; + struct rtc_device *rtc; + u16 vio_clk_id; + bool stopped; +}; + +/** + * viortc_class_get_locked() - get RTC class wrapper, if ops allowed + * @dev: virtio device + * + * Gets the RTC class wrapper from the virtio device, if it is available and + * ops are allowed. + * + * Context: Caller must hold rtc_lock(). + * Return: RTC class wrapper if available and ops allowed, ERR_PTR otherwise. + */ +static struct viortc_class *viortc_class_get_locked(struct device *dev) +{ + struct viortc_class *viortc_class; + + viortc_class = viortc_class_from_dev(dev); + if (IS_ERR(viortc_class)) + return viortc_class; + + if (viortc_class->stopped) + return ERR_PTR(-EBUSY); + + return viortc_class; +} + +/** + * viortc_class_read_time() - RTC class op read_time + * @dev: virtio device + * @tm: read time + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_class_read_time(struct device *dev, struct rtc_time *tm) +{ + struct viortc_class *viortc_class; + time64_t sec; + int ret; + u64 ns; + + viortc_class = viortc_class_get_locked(dev); + if (IS_ERR(viortc_class)) + return PTR_ERR(viortc_class); + + ret = viortc_read(viortc_class->viortc, viortc_class->vio_clk_id, &ns); + if (ret) + return ret; + + sec = div_u64(ns, NSEC_PER_SEC); + + rtc_time64_to_tm(sec, tm); + + return 0; +} + +/** + * viortc_class_read_alarm() - RTC class op read_alarm + * @dev: virtio device + * @alrm: alarm read out + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_class_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct viortc_class *viortc_class; + time64_t alarm_time_sec; + u64 alarm_time_ns; + bool enabled; + int ret; + + viortc_class = viortc_class_get_locked(dev); + if (IS_ERR(viortc_class)) + return PTR_ERR(viortc_class); + + ret = viortc_read_alarm(viortc_class->viortc, viortc_class->vio_clk_id, + &alarm_time_ns, &enabled); + if (ret) + return ret; + + alarm_time_sec = div_u64(alarm_time_ns, NSEC_PER_SEC); + rtc_time64_to_tm(alarm_time_sec, &alrm->time); + + alrm->enabled = enabled; + + return 0; +} + +/** + * viortc_class_set_alarm() - RTC class op set_alarm + * @dev: virtio device + * @alrm: alarm to set + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_class_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct viortc_class *viortc_class; + time64_t alarm_time_sec; + u64 alarm_time_ns; + + viortc_class = viortc_class_get_locked(dev); + if (IS_ERR(viortc_class)) + return PTR_ERR(viortc_class); + + alarm_time_sec = rtc_tm_to_time64(&alrm->time); + + if (alarm_time_sec < 0) + return -EINVAL; + + if (check_mul_overflow((u64)alarm_time_sec, (u64)NSEC_PER_SEC, + &alarm_time_ns)) + return -EINVAL; + + return viortc_set_alarm(viortc_class->viortc, viortc_class->vio_clk_id, + alarm_time_ns, alrm->enabled); +} + +/** + * viortc_class_alarm_irq_enable() - RTC class op alarm_irq_enable + * @dev: virtio device + * @enabled: enable or disable alarm IRQ + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_class_alarm_irq_enable(struct device *dev, + unsigned int enabled) +{ + struct viortc_class *viortc_class; + + viortc_class = viortc_class_get_locked(dev); + if (IS_ERR(viortc_class)) + return PTR_ERR(viortc_class); + + return viortc_set_alarm_enabled(viortc_class->viortc, + viortc_class->vio_clk_id, enabled); +} + +static const struct rtc_class_ops viortc_class_ops = { + .read_time = viortc_class_read_time, + .read_alarm = viortc_class_read_alarm, + .set_alarm = viortc_class_set_alarm, + .alarm_irq_enable = viortc_class_alarm_irq_enable, +}; + +/** + * viortc_class_alarm() - propagate alarm notification as alarm interrupt + * @viortc_class: RTC class wrapper + * @vio_clk_id: virtio_rtc clock id + * + * Context: Any context. + */ +void viortc_class_alarm(struct viortc_class *viortc_class, u16 vio_clk_id) +{ + if (vio_clk_id != viortc_class->vio_clk_id) { + dev_warn_ratelimited(&viortc_class->rtc->dev, + "ignoring alarm for clock id %d, expected id %d\n", + vio_clk_id, viortc_class->vio_clk_id); + return; + } + + rtc_update_irq(viortc_class->rtc, 1, RTC_AF | RTC_IRQF); +} + +/** + * viortc_class_stop() - disallow RTC class ops + * @viortc_class: RTC class wrapper + * + * Context: Process context. Caller must NOT hold rtc_lock(). + */ +void viortc_class_stop(struct viortc_class *viortc_class) +{ + rtc_lock(viortc_class->rtc); + + viortc_class->stopped = true; + + rtc_unlock(viortc_class->rtc); +} + +/** + * viortc_class_register() - register RTC class device + * @viortc_class: RTC class wrapper + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_class_register(struct viortc_class *viortc_class) +{ + return devm_rtc_register_device(viortc_class->rtc); +} + +/** + * viortc_class_init() - init RTC class wrapper and device + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @have_alarm: have alarm feature + * @parent_dev: virtio device + * + * Context: Process context. + * Return: RTC class wrapper on success, ERR_PTR otherwise. + */ +struct viortc_class *viortc_class_init(struct viortc_dev *viortc, + u16 vio_clk_id, bool have_alarm, + struct device *parent_dev) +{ + struct viortc_class *viortc_class; + struct rtc_device *rtc; + + viortc_class = + devm_kzalloc(parent_dev, sizeof(*viortc_class), GFP_KERNEL); + if (!viortc_class) + return ERR_PTR(-ENOMEM); + + rtc = devm_rtc_allocate_device(parent_dev); + if (IS_ERR(rtc)) + return ERR_CAST(rtc); + + viortc_class->viortc = viortc; + viortc_class->rtc = rtc; + viortc_class->vio_clk_id = vio_clk_id; + + if (!have_alarm) + clear_bit(RTC_FEATURE_ALARM, rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); + + rtc->ops = &viortc_class_ops; + rtc->range_max = div_u64(U64_MAX, NSEC_PER_SEC); + + return viortc_class; +} diff --git a/drivers/virtio/virtio_rtc_driver.c b/drivers/virtio/virtio_rtc_driver.c index 7499908ee34c..a57d5e06e19d 100644 --- a/drivers/virtio/virtio_rtc_driver.c +++ b/drivers/virtio/virtio_rtc_driver.c @@ -18,9 +18,12 @@ #include "virtio_rtc_internal.h" +#define VIORTC_ALARMQ_BUF_CAP sizeof(union virtio_rtc_notif_alarmq) + /* virtqueue order */ enum { VIORTC_REQUESTQ, + VIORTC_ALARMQ, VIORTC_MAX_NR_QUEUES, }; @@ -37,17 +40,23 @@ struct viortc_vq { /** * struct viortc_dev - virtio_rtc device data * @vdev: virtio device + * @viortc_class: RTC class wrapper for UTC-like clock, NULL if not available * @vqs: virtqueues * @clocks_to_unregister: Clock references, which are only used during device * removal. * For other uses, there would be a race between device * creation and setting the pointers here. + * @alarmq_bufs: alarmq buffers list + * @num_alarmq_bufs: # of alarmq buffers * @num_clocks: # of virtio_rtc clocks */ struct viortc_dev { struct virtio_device *vdev; + struct viortc_class *viortc_class; struct viortc_vq vqs[VIORTC_MAX_NR_QUEUES]; struct viortc_ptp_clock **clocks_to_unregister; + void **alarmq_bufs; + unsigned int num_alarmq_bufs; u16 num_clocks; }; @@ -78,6 +87,60 @@ struct viortc_msg { unsigned int resp_actual_size; }; +/** + * viortc_class_from_dev() - Get RTC class object from virtio device. + * @dev: virtio device + * + * Context: Any context. + * Return: RTC class object if available, ERR_PTR otherwise. + */ +struct viortc_class *viortc_class_from_dev(struct device *dev) +{ + struct virtio_device *vdev; + struct viortc_dev *viortc; + + vdev = container_of(dev, typeof(*vdev), dev); + viortc = vdev->priv; + + return viortc->viortc_class ?: ERR_PTR(-ENODEV); +} + +/** + * viortc_alarms_supported() - Whether device and driver support alarms. + * @vdev: virtio device + * + * NB: Device and driver may not support alarms for the same clocks. + * + * Context: Any context. + * Return: True if both device and driver can support alarms. + */ +static bool viortc_alarms_supported(struct virtio_device *vdev) +{ + return IS_ENABLED(CONFIG_VIRTIO_RTC_CLASS) && + virtio_has_feature(vdev, VIRTIO_RTC_F_ALARM); +} + +/** + * viortc_feed_vq() - Make a device write-only buffer available. + * @viortc: device data + * @vq: notification virtqueue + * @buf: buffer + * @buf_len: buffer capacity in bytes + * @data: token, identifying buffer + * + * Context: Caller must prevent concurrent access to vq. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_feed_vq(struct viortc_dev *viortc, struct virtqueue *vq, + void *buf, unsigned int buf_len, void *data) +{ + struct scatterlist sg; + + sg_init_one(&sg, buf, buf_len); + + return virtqueue_add_inbuf(vq, &sg, 1, data, GFP_ATOMIC); +} + /** * viortc_msg_init() - Allocate and initialize requestq message. * @viortc: device data @@ -236,6 +299,85 @@ static void viortc_cb_requestq(struct virtqueue *vq) viortc_do_cb(vq, viortc_requestq_hdlr); } +/** + * viortc_alarmq_hdlr() - process an alarmq used buffer + * @token: token identifying the buffer + * @len: bytes written by device + * @vq: virtqueue + * @viortc_vq: device specific data for virtqueue + * @viortc: device data + * + * Processes a VIRTIO_RTC_NOTIF_ALARM notification by calling the RTC class + * driver. Makes the buffer available again. + * + * Context: virtqueue callback + */ +static void viortc_alarmq_hdlr(void *token, unsigned int len, + struct virtqueue *vq, + struct viortc_vq *viortc_vq, + struct viortc_dev *viortc) +{ + struct virtio_rtc_notif_alarm *notif = token; + struct virtio_rtc_notif_head *head = token; + unsigned long flags; + u16 clock_id; + bool notify; + + if (len < sizeof(*head)) { + dev_err_ratelimited(&viortc->vdev->dev, + "%s: ignoring notification with short header\n", + __func__); + goto feed_vq; + } + + if (virtio_le_to_cpu(head->msg_type) != VIRTIO_RTC_NOTIF_ALARM) { + dev_err_ratelimited(&viortc->vdev->dev, + "%s: ignoring unknown notification type 0x%x\n", + __func__, virtio_le_to_cpu(head->msg_type)); + goto feed_vq; + } + + if (len < sizeof(*notif)) { + dev_err_ratelimited(&viortc->vdev->dev, + "%s: ignoring too small alarm notification\n", + __func__); + goto feed_vq; + } + + clock_id = virtio_le_to_cpu(notif->clock_id); + + if (!viortc->viortc_class) + dev_warn_ratelimited(&viortc->vdev->dev, + "ignoring alarm, no RTC class device available\n"); + else + viortc_class_alarm(viortc->viortc_class, clock_id); + +feed_vq: + spin_lock_irqsave(&viortc_vq->lock, flags); + + if (viortc_feed_vq(viortc, vq, notif, VIORTC_ALARMQ_BUF_CAP, token)) + dev_warn(&viortc->vdev->dev, + "%s: failed to re-expose input buffer\n", __func__); + + notify = virtqueue_kick_prepare(vq); + + spin_unlock_irqrestore(&viortc_vq->lock, flags); + + if (notify) + virtqueue_notify(vq); +} + +/** + * viortc_cb_alarmq() - callback for alarmq + * @vq: virtqueue + * + * Context: virtqueue callback + */ +static void viortc_cb_alarmq(struct virtqueue *vq) +{ + viortc_do_cb(vq, viortc_alarmq_hdlr); +} + /** * viortc_get_resp_errno() - converts virtio_rtc errnos to system errnos * @resp_head: message response header @@ -561,12 +703,13 @@ out_release: * @vio_clk_id: virtio_rtc clock id * @type: virtio_rtc clock type * @leap_second_smearing: virtio_rtc smearing variant + * @flags: struct virtio_rtc_resp_clock_cap.flags * * Context: Process context. * Return: Zero on success, negative error code otherwise. */ static int viortc_clock_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 *type, - u8 *leap_second_smearing) + u8 *leap_second_smearing, u8 *flags) { VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_CLOCK_CAP, struct virtio_rtc_req_clock_cap, @@ -589,6 +732,7 @@ static int viortc_clock_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 *type, VIORTC_MSG_READ(hdl, type, type); VIORTC_MSG_READ(hdl, leap_second_smearing, leap_second_smearing); + VIORTC_MSG_READ(hdl, flags, flags); out_release: viortc_msg_release(VIORTC_MSG(hdl)); @@ -639,10 +783,189 @@ out_release: return ret; } +/** + * viortc_read_alarm() - VIRTIO_RTC_REQ_READ_ALARM wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @alarm_time: alarm time in ns + * @enabled: whether alarm is enabled + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_read_alarm(struct viortc_dev *viortc, u16 vio_clk_id, + u64 *alarm_time, bool *enabled) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_READ_ALARM, + struct virtio_rtc_req_read_alarm, + struct virtio_rtc_resp_read_alarm); + u8 flags; + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + + VIORTC_MSG_READ(hdl, alarm_time, alarm_time); + VIORTC_MSG_READ(hdl, flags, &flags); + + *enabled = !!(flags & VIRTIO_RTC_FLAG_ALARM_ENABLED); + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/** + * viortc_set_alarm() - VIRTIO_RTC_REQ_SET_ALARM wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @alarm_time: alarm time in ns + * @alarm_enable: enable or disable alarm + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_set_alarm(struct viortc_dev *viortc, u16 vio_clk_id, u64 alarm_time, + bool alarm_enable) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_SET_ALARM, + struct virtio_rtc_req_set_alarm, + struct virtio_rtc_resp_set_alarm); + u8 flags = 0; + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + if (alarm_enable) + flags |= VIRTIO_RTC_FLAG_ALARM_ENABLED; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + VIORTC_MSG_WRITE(hdl, alarm_time, &alarm_time); + VIORTC_MSG_WRITE(hdl, flags, &flags); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + +/** + * viortc_set_alarm_enabled() - VIRTIO_RTC_REQ_SET_ALARM_ENABLED wrapper + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @alarm_enable: enable or disable alarm + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +int viortc_set_alarm_enabled(struct viortc_dev *viortc, u16 vio_clk_id, + bool alarm_enable) +{ + VIORTC_DECLARE_MSG_HDL_ONSTACK(hdl, VIRTIO_RTC_REQ_SET_ALARM_ENABLED, + struct virtio_rtc_req_set_alarm_enabled, + struct virtio_rtc_resp_set_alarm_enabled); + u8 flags = 0; + int ret; + + ret = VIORTC_MSG_INIT(hdl, viortc); + if (ret) + return ret; + + if (alarm_enable) + flags |= VIRTIO_RTC_FLAG_ALARM_ENABLED; + + VIORTC_MSG_WRITE(hdl, clock_id, &vio_clk_id); + VIORTC_MSG_WRITE(hdl, flags, &flags); + + ret = viortc_msg_xfer(&viortc->vqs[VIORTC_REQUESTQ], VIORTC_MSG(hdl), + 0); + if (ret) { + dev_dbg(&viortc->vdev->dev, "%s: xfer returned %d\n", __func__, + ret); + goto out_release; + } + +out_release: + viortc_msg_release(VIORTC_MSG(hdl)); + + return ret; +} + /* * init, deinit */ +/** + * viortc_init_rtc_class_clock() - init and register a RTC class device + * @viortc: device data + * @vio_clk_id: virtio_rtc clock id + * @clock_type: virtio_rtc clock type + * @flags: struct virtio_rtc_resp_clock_cap.flags + * + * The clock must be a UTC-like clock. + * + * Context: Process context. + * Return: Positive if registered, zero if not supported by configuration, + * negative error code otherwise. + */ +static int viortc_init_rtc_class_clock(struct viortc_dev *viortc, + u16 vio_clk_id, u8 clock_type, u8 flags) +{ + struct virtio_device *vdev = viortc->vdev; + struct viortc_class *viortc_class; + struct device *dev = &vdev->dev; + bool have_alarm; + + if (clock_type != VIRTIO_RTC_CLOCK_UTC_SMEARED) { + dev_info(dev, + "not creating RTC class device for clock %d, which may step on leap seconds\n", + vio_clk_id); + return 0; + } + + if (viortc->viortc_class) { + dev_warn_once(dev, + "multiple UTC-like clocks are present, but creating only one RTC class device\n"); + return 0; + } + + have_alarm = viortc_alarms_supported(vdev) && + !!(flags & VIRTIO_RTC_FLAG_ALARM_CAP); + + viortc_class = viortc_class_init(viortc, vio_clk_id, have_alarm, dev); + if (IS_ERR(viortc_class)) + return PTR_ERR(viortc_class); + + viortc->viortc_class = viortc_class; + + if (have_alarm) + devm_device_init_wakeup(dev); + + return viortc_class_register(viortc_class) ?: 1; +} + /** * viortc_init_ptp_clock() - init and register PTP clock * @viortc: device data @@ -682,22 +1005,34 @@ static int viortc_init_ptp_clock(struct viortc_dev *viortc, u16 vio_clk_id, * @viortc: device data * @vio_clk_id: virtio_rtc clock id * - * Initializes PHC to represent virtio_rtc clock. + * Initializes PHC and/or RTC class device to represent virtio_rtc clock. * * Context: Process context. * Return: Zero on success, negative error code otherwise. */ static int viortc_init_clock(struct viortc_dev *viortc, u16 vio_clk_id) { - u8 clock_type, leap_second_smearing; + u8 clock_type, leap_second_smearing, flags; bool is_exposed = false; int ret; ret = viortc_clock_cap(viortc, vio_clk_id, &clock_type, - &leap_second_smearing); + &leap_second_smearing, &flags); if (ret) return ret; + if (IS_ENABLED(CONFIG_VIRTIO_RTC_CLASS) && + (clock_type == VIRTIO_RTC_CLOCK_UTC || + clock_type == VIRTIO_RTC_CLOCK_UTC_SMEARED || + clock_type == VIRTIO_RTC_CLOCK_UTC_MAYBE_SMEARED)) { + ret = viortc_init_rtc_class_clock(viortc, vio_clk_id, + clock_type, flags); + if (ret < 0) + return ret; + if (ret > 0) + is_exposed = true; + } + if (IS_ENABLED(CONFIG_VIRTIO_RTC_PTP)) { ret = viortc_init_ptp_clock(viortc, vio_clk_id, clock_type, leap_second_smearing); @@ -716,7 +1051,7 @@ static int viortc_init_clock(struct viortc_dev *viortc, u16 vio_clk_id) } /** - * viortc_clocks_deinit() - unregister PHCs + * viortc_clocks_deinit() - unregister PHCs, stop RTC ops * @viortc: device data */ static void viortc_clocks_deinit(struct viortc_dev *viortc) @@ -734,6 +1069,9 @@ static void viortc_clocks_deinit(struct viortc_dev *viortc) WARN_ON(viortc_ptp_unregister(vio_ptp, &viortc->vdev->dev)); } + + if (viortc->viortc_class) + viortc_class_stop(viortc->viortc_class); } /** @@ -780,6 +1118,88 @@ err_deinit_clocks: return ret; } +/** + * viortc_populate_vq() - populate alarmq with device-writable buffers + * @viortc: device data + * @viortc_vq: device specific data for virtqueue + * @buf_cap: device-writable buffer size in bytes + * @lock: lock queue during accesses + * + * Populates the alarmq with pre-allocated buffers. + * + * The caller is responsible for kicking the device. + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_populate_vq(struct viortc_dev *viortc, + struct viortc_vq *viortc_vq, u32 buf_cap, + bool lock) +{ + unsigned int num_elems, i; + struct virtqueue *vq; + unsigned long flags; + void *buf; + int ret; + + num_elems = viortc->num_alarmq_bufs; + vq = viortc_vq->vq; + + for (i = 0; i < num_elems; i++) { + buf = viortc->alarmq_bufs[i]; + + if (lock) { + spin_lock_irqsave(&viortc_vq->lock, flags); + + ret = viortc_feed_vq(viortc, vq, buf, buf_cap, buf); + + spin_unlock_irqrestore(&viortc_vq->lock, flags); + } else { + ret = viortc_feed_vq(viortc, vq, buf, buf_cap, buf); + } + + if (ret) + return ret; + } + + return 0; +} + +/** + * viortc_alloc_vq_bufs() - allocate alarmq buffers + * @viortc: device data + * @num_elems: # of buffers + * @buf_cap: per-buffer device-writable bytes + * + * Context: Process context. + * Return: Zero on success, negative error code otherwise. + */ +static int viortc_alloc_vq_bufs(struct viortc_dev *viortc, + unsigned int num_elems, u32 buf_cap) +{ + struct device *dev = &viortc->vdev->dev; + void **buf_list; + unsigned int i; + void *buf; + + buf_list = devm_kcalloc(dev, num_elems, sizeof(*buf_list), GFP_KERNEL); + if (!buf_list) + return -ENOMEM; + + viortc->alarmq_bufs = buf_list; + viortc->num_alarmq_bufs = num_elems; + + for (i = 0; i < num_elems; i++) { + buf = devm_kzalloc(dev, buf_cap, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf_list[i] = buf; + } + + return 0; +} + /** * viortc_init_vqs() - init virtqueues * @viortc: device data @@ -794,11 +1214,19 @@ static int viortc_init_vqs(struct viortc_dev *viortc) struct virtqueue *vqs[VIORTC_MAX_NR_QUEUES]; struct virtqueue_info vqs_info[] = { { "requestq", viortc_cb_requestq }, + { "alarmq", viortc_cb_alarmq }, }; struct virtio_device *vdev = viortc->vdev; + unsigned int num_elems; int nr_queues, ret; + bool have_alarms; - nr_queues = VIORTC_REQUESTQ + 1; + have_alarms = viortc_alarms_supported(vdev); + + if (have_alarms) + nr_queues = VIORTC_ALARMQ + 1; + else + nr_queues = VIORTC_REQUESTQ + 1; ret = virtio_find_vqs(vdev, nr_queues, vqs, vqs_info, NULL); if (ret) @@ -807,6 +1235,25 @@ static int viortc_init_vqs(struct viortc_dev *viortc) viortc->vqs[VIORTC_REQUESTQ].vq = vqs[VIORTC_REQUESTQ]; spin_lock_init(&viortc->vqs[VIORTC_REQUESTQ].lock); + if (have_alarms) { + viortc->vqs[VIORTC_ALARMQ].vq = vqs[VIORTC_ALARMQ]; + spin_lock_init(&viortc->vqs[VIORTC_ALARMQ].lock); + + num_elems = virtqueue_get_vring_size(vqs[VIORTC_ALARMQ]); + if (num_elems == 0) + return -ENOSPC; + + if (!viortc->alarmq_bufs) { + ret = viortc_alloc_vq_bufs(viortc, num_elems, + VIORTC_ALARMQ_BUF_CAP); + if (ret) + return ret; + } else { + viortc->num_alarmq_bufs = + min(num_elems, viortc->num_alarmq_bufs); + } + } + return 0; } @@ -819,7 +1266,11 @@ static int viortc_init_vqs(struct viortc_dev *viortc) */ static int viortc_probe(struct virtio_device *vdev) { + struct viortc_vq *alarm_viortc_vq; + struct virtqueue *alarm_vq; struct viortc_dev *viortc; + unsigned long flags; + bool notify; int ret; viortc = devm_kzalloc(&vdev->dev, sizeof(*viortc), GFP_KERNEL); @@ -839,8 +1290,30 @@ static int viortc_probe(struct virtio_device *vdev) if (ret) goto err_reset_vdev; + if (viortc_alarms_supported(vdev)) { + alarm_viortc_vq = &viortc->vqs[VIORTC_ALARMQ]; + alarm_vq = alarm_viortc_vq->vq; + + ret = viortc_populate_vq(viortc, alarm_viortc_vq, + VIORTC_ALARMQ_BUF_CAP, true); + if (ret) + goto err_deinit_clocks; + + spin_lock_irqsave(&alarm_viortc_vq->lock, flags); + notify = virtqueue_kick_prepare(alarm_vq); + spin_unlock_irqrestore(&alarm_viortc_vq->lock, flags); + + if (notify && !virtqueue_notify(alarm_vq)) { + ret = -EIO; + goto err_deinit_clocks; + } + } + return 0; +err_deinit_clocks: + viortc_clocks_deinit(viortc); + err_reset_vdev: virtio_reset_device(vdev); vdev->config->del_vqs(vdev); @@ -875,10 +1348,41 @@ static int viortc_freeze(struct virtio_device *dev) static int viortc_restore(struct virtio_device *dev) { struct viortc_dev *viortc = dev->priv; + struct viortc_vq *alarm_viortc_vq; + struct virtqueue *alarm_vq; + bool notify = false; + int ret; - return viortc_init_vqs(viortc); + ret = viortc_init_vqs(viortc); + if (ret) + return ret; + + alarm_viortc_vq = &viortc->vqs[VIORTC_ALARMQ]; + alarm_vq = alarm_viortc_vq->vq; + + if (viortc_alarms_supported(dev)) { + ret = viortc_populate_vq(viortc, alarm_viortc_vq, + VIORTC_ALARMQ_BUF_CAP, false); + if (ret) + return ret; + + notify = virtqueue_kick_prepare(alarm_vq); + } + + virtio_device_ready(dev); + + if (notify && !virtqueue_notify(alarm_vq)) + ret = -EIO; + + return ret; } +static unsigned int features[] = { +#if IS_ENABLED(CONFIG_VIRTIO_RTC_CLASS) + VIRTIO_RTC_F_ALARM, +#endif +}; + static struct virtio_device_id id_table[] = { { VIRTIO_ID_CLOCK, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -887,6 +1391,8 @@ MODULE_DEVICE_TABLE(virtio, id_table); static struct virtio_driver virtio_rtc_drv = { .driver.name = KBUILD_MODNAME, + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .id_table = id_table, .probe = viortc_probe, .remove = viortc_remove, diff --git a/drivers/virtio/virtio_rtc_internal.h b/drivers/virtio/virtio_rtc_internal.h index 2e589903d04f..296afee6719b 100644 --- a/drivers/virtio/virtio_rtc_internal.h +++ b/drivers/virtio/virtio_rtc_internal.h @@ -9,6 +9,8 @@ #ifndef _VIRTIO_RTC_INTERNAL_H_ #define _VIRTIO_RTC_INTERNAL_H_ +#include +#include #include #include @@ -21,6 +23,16 @@ int viortc_read_cross(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, u64 *reading, u64 *cycles); int viortc_cross_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter, bool *supported); +int viortc_read_alarm(struct viortc_dev *viortc, u16 vio_clk_id, + u64 *alarm_time, bool *enabled); +int viortc_set_alarm(struct viortc_dev *viortc, u16 vio_clk_id, u64 alarm_time, + bool alarm_enable); +int viortc_set_alarm_enabled(struct viortc_dev *viortc, u16 vio_clk_id, + bool alarm_enable); + +struct viortc_class; + +struct viortc_class *viortc_class_from_dev(struct device *dev); /* PTP IFs */ @@ -67,4 +79,44 @@ static inline int viortc_ptp_unregister(struct viortc_ptp_clock *vio_ptp, */ int viortc_hw_xtstamp_params(u8 *hw_counter, enum clocksource_ids *cs_id); +/* RTC class IFs */ + +#if IS_ENABLED(CONFIG_VIRTIO_RTC_CLASS) + +void viortc_class_alarm(struct viortc_class *viortc_class, u16 vio_clk_id); + +void viortc_class_stop(struct viortc_class *viortc_class); + +int viortc_class_register(struct viortc_class *viortc_class); + +struct viortc_class *viortc_class_init(struct viortc_dev *viortc, + u16 vio_clk_id, bool have_alarm, + struct device *parent_dev); + +#else /* CONFIG_VIRTIO_RTC_CLASS */ + +static inline void viortc_class_alarm(struct viortc_class *viortc_class, + u16 vio_clk_id) +{ +} + +static inline void viortc_class_stop(struct viortc_class *viortc_class) +{ +} + +static inline int viortc_class_register(struct viortc_class *viortc_class) +{ + return -ENODEV; +} + +static inline struct viortc_class *viortc_class_init(struct viortc_dev *viortc, + u16 vio_clk_id, + bool have_alarm, + struct device *parent_dev) +{ + return ERR_PTR(-ENODEV); +} + +#endif /* CONFIG_VIRTIO_RTC_CLASS */ + #endif /* _VIRTIO_RTC_INTERNAL_H_ */ diff --git a/include/uapi/linux/virtio_rtc.h b/include/uapi/linux/virtio_rtc.h index 6b3af4e9bbfb..85ee8f013661 100644 --- a/include/uapi/linux/virtio_rtc.h +++ b/include/uapi/linux/virtio_rtc.h @@ -9,6 +9,9 @@ #include +/* alarm feature */ +#define VIRTIO_RTC_F_ALARM 0 + /* read request message types */ #define VIRTIO_RTC_REQ_READ 0x0001 @@ -19,6 +22,13 @@ #define VIRTIO_RTC_REQ_CFG 0x1000 #define VIRTIO_RTC_REQ_CLOCK_CAP 0x1001 #define VIRTIO_RTC_REQ_CROSS_CAP 0x1002 +#define VIRTIO_RTC_REQ_READ_ALARM 0x1003 +#define VIRTIO_RTC_REQ_SET_ALARM 0x1004 +#define VIRTIO_RTC_REQ_SET_ALARM_ENABLED 0x1005 + +/* alarmq message types */ + +#define VIRTIO_RTC_NOTIF_ALARM 0x2000 /* Message headers */ @@ -39,6 +49,12 @@ struct virtio_rtc_resp_head { __u8 reserved[7]; }; +/** common notification header */ +struct virtio_rtc_notif_head { + __le16 msg_type; + __u8 reserved[6]; +}; + /* read requests */ /* VIRTIO_RTC_REQ_READ message */ @@ -111,7 +127,9 @@ struct virtio_rtc_resp_clock_cap { #define VIRTIO_RTC_SMEAR_NOON_LINEAR 1 #define VIRTIO_RTC_SMEAR_UTC_SLS 2 __u8 leap_second_smearing; - __u8 reserved[6]; +#define VIRTIO_RTC_FLAG_ALARM_CAP (1 << 0) + __u8 flags; + __u8 reserved[5]; }; /* VIRTIO_RTC_REQ_CROSS_CAP message */ @@ -130,6 +148,53 @@ struct virtio_rtc_resp_cross_cap { __u8 reserved[7]; }; +/* VIRTIO_RTC_REQ_READ_ALARM message */ + +struct virtio_rtc_req_read_alarm { + struct virtio_rtc_req_head head; + __le16 clock_id; + __u8 reserved[6]; +}; + +struct virtio_rtc_resp_read_alarm { + struct virtio_rtc_resp_head head; + __le64 alarm_time; +#define VIRTIO_RTC_FLAG_ALARM_ENABLED (1 << 0) + __u8 flags; + __u8 reserved[7]; +}; + +/* VIRTIO_RTC_REQ_SET_ALARM message */ + +struct virtio_rtc_req_set_alarm { + struct virtio_rtc_req_head head; + __le64 alarm_time; + __le16 clock_id; + /* flag VIRTIO_RTC_FLAG_ALARM_ENABLED */ + __u8 flags; + __u8 reserved[5]; +}; + +struct virtio_rtc_resp_set_alarm { + struct virtio_rtc_resp_head head; + /* no response params */ +}; + +/* VIRTIO_RTC_REQ_SET_ALARM_ENABLED message */ + +struct virtio_rtc_req_set_alarm_enabled { + struct virtio_rtc_req_head head; + __le16 clock_id; + /* flag VIRTIO_RTC_ALARM_ENABLED */ + __u8 flags; + __u8 reserved[5]; +}; + +struct virtio_rtc_resp_set_alarm_enabled { + struct virtio_rtc_resp_head head; + /* no response params */ +}; + /** Union of request types for requestq */ union virtio_rtc_req_requestq { struct virtio_rtc_req_read read; @@ -137,6 +202,9 @@ union virtio_rtc_req_requestq { struct virtio_rtc_req_cfg cfg; struct virtio_rtc_req_clock_cap clock_cap; struct virtio_rtc_req_cross_cap cross_cap; + struct virtio_rtc_req_read_alarm read_alarm; + struct virtio_rtc_req_set_alarm set_alarm; + struct virtio_rtc_req_set_alarm_enabled set_alarm_enabled; }; /** Union of response types for requestq */ @@ -146,6 +214,24 @@ union virtio_rtc_resp_requestq { struct virtio_rtc_resp_cfg cfg; struct virtio_rtc_resp_clock_cap clock_cap; struct virtio_rtc_resp_cross_cap cross_cap; + struct virtio_rtc_resp_read_alarm read_alarm; + struct virtio_rtc_resp_set_alarm set_alarm; + struct virtio_rtc_resp_set_alarm_enabled set_alarm_enabled; +}; + +/* alarmq notifications */ + +/* VIRTIO_RTC_NOTIF_ALARM notification */ + +struct virtio_rtc_notif_alarm { + struct virtio_rtc_notif_head head; + __le16 clock_id; + __u8 reserved[6]; +}; + +/** Union of notification types for alarmq */ +union virtio_rtc_notif_alarmq { + struct virtio_rtc_notif_alarm alarm; }; #endif /* _LINUX_VIRTIO_RTC_H */ -- cgit v1.2.3 From ead7f9b8de65632ef8060b84b0c55049a33cfea1 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Thu, 29 May 2025 12:28:35 +0200 Subject: bpf: Fix L4 csum update on IPv6 in CHECKSUM_COMPLETE In Cilium, we use bpf_csum_diff + bpf_l4_csum_replace to, among other things, update the L4 checksum after reverse SNATing IPv6 packets. That use case is however not currently supported and leads to invalid skb->csum values in some cases. This patch adds support for IPv6 address changes in bpf_l4_csum_update via a new flag. When calling bpf_l4_csum_replace in Cilium, it ends up calling inet_proto_csum_replace_by_diff: 1: void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, 2: __wsum diff, bool pseudohdr) 3: { 4: if (skb->ip_summed != CHECKSUM_PARTIAL) { 5: csum_replace_by_diff(sum, diff); 6: if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) 7: skb->csum = ~csum_sub(diff, skb->csum); 8: } else if (pseudohdr) { 9: *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); 10: } 11: } The bug happens when we're in the CHECKSUM_COMPLETE state. We've just updated one of the IPv6 addresses. The helper now updates the L4 header checksum on line 5. Next, it updates skb->csum on line 7. It shouldn't. For an IPv6 packet, the updates of the IPv6 address and of the L4 checksum will cancel each other. The checksums are set such that computing a checksum over the packet including its checksum will result in a sum of 0. So the same is true here when we update the L4 checksum on line 5. We'll update it as to cancel the previous IPv6 address update. Hence skb->csum should remain untouched in this case. The same bug doesn't affect IPv4 packets because, in that case, three fields are updated: the IPv4 address, the IP checksum, and the L4 checksum. The change to the IPv4 address and one of the checksums still cancel each other in skb->csum, but we're left with one checksum update and should therefore update skb->csum accordingly. That's exactly what inet_proto_csum_replace_by_diff does. This special case for IPv6 L4 checksums is also described atop inet_proto_csum_replace16, the function we should be using in this case. This patch introduces a new bpf_l4_csum_replace flag, BPF_F_IPV6, to indicate that we're updating the L4 checksum of an IPv6 packet. When the flag is set, inet_proto_csum_replace_by_diff will skip the skb->csum update. Fixes: 7d672345ed295 ("bpf: add generic bpf_csum_diff helper") Signed-off-by: Paul Chaignon Acked-by: Daniel Borkmann Link: https://patch.msgid.link/96a6bc3a443e6f0b21ff7b7834000e17fb549e05.1748509484.git.paul.chaignon@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/bpf.h | 2 ++ net/core/filter.c | 5 +++-- tools/include/uapi/linux/bpf.h | 2 ++ 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 85180e4aaa5a..0b4a2f124d11 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2056,6 +2056,7 @@ union bpf_attr { * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates * that the modified header field is part of the pseudo-header. + * Flag **BPF_F_IPV6** should be set for IPv6 packets. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more @@ -6072,6 +6073,7 @@ enum { BPF_F_PSEUDO_HDR = (1ULL << 4), BPF_F_MARK_MANGLED_0 = (1ULL << 5), BPF_F_MARK_ENFORCE = (1ULL << 6), + BPF_F_IPV6 = (1ULL << 7), }; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ diff --git a/net/core/filter.c b/net/core/filter.c index f1de7bd8b547..327ca73f9cd7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1968,10 +1968,11 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; + bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | - BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) + BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; @@ -1987,7 +1988,7 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, if (unlikely(from != 0)) return -EINVAL; - inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, false); + inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 85180e4aaa5a..0b4a2f124d11 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2056,6 +2056,7 @@ union bpf_attr { * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates * that the modified header field is part of the pseudo-header. + * Flag **BPF_F_IPV6** should be set for IPv6 packets. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more @@ -6072,6 +6073,7 @@ enum { BPF_F_PSEUDO_HDR = (1ULL << 4), BPF_F_MARK_MANGLED_0 = (1ULL << 5), BPF_F_MARK_ENFORCE = (1ULL << 6), + BPF_F_IPV6 = (1ULL << 7), }; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ -- cgit v1.2.3 From ab03a61c66149327e022bdafa5843c6f82be267e Mon Sep 17 00:00:00 2001 From: Uday Shankar Date: Thu, 29 May 2025 17:47:10 -0600 Subject: ublk: have a per-io daemon instead of a per-queue daemon Currently, ublk_drv associates to each hardware queue (hctx) a unique task (called the queue's ubq_daemon) which is allowed to issue COMMIT_AND_FETCH commands against the hctx. If any other task attempts to do so, the command fails immediately with EINVAL. When considered together with the block layer architecture, the result is that for each CPU C on the system, there is a unique ublk server thread which is allowed to handle I/O submitted on CPU C. This can lead to suboptimal performance under imbalanced load generation. For an extreme example, suppose all the load is generated on CPUs mapping to a single ublk server thread. Then that thread may be fully utilized and become the bottleneck in the system, while other ublk server threads are totally idle. This issue can also be addressed directly in the ublk server without kernel support by having threads dequeue I/Os and pass them around to ensure even load. But this solution requires inter-thread communication at least twice for each I/O (submission and completion), which is generally a bad pattern for performance. The problem gets even worse with zero copy, as more inter-thread communication would be required to have the buffer register/unregister calls to come from the correct thread. Therefore, address this issue in ublk_drv by allowing each I/O to have its own daemon task. Two I/Os in the same queue are now allowed to be serviced by different daemon tasks - this was not possible before. Imbalanced load can then be balanced across all ublk server threads by having the ublk server threads issue FETCH_REQs in a round-robin manner. As a small toy example, consider a system with a single ublk device having 2 queues, each of depth 4. A ublk server having 4 threads could issue its FETCH_REQs against this device as follows (where each entry is the qid,tag pair that the FETCH_REQ targets): ublk server thread: T0 T1 T2 T3 0,0 0,1 0,2 0,3 1,3 1,0 1,1 1,2 This setup allows for load that is concentrated on one hctx/ublk_queue to be spread out across all ublk server threads, alleviating the issue described above. Add the new UBLK_F_PER_IO_DAEMON feature to ublk_drv, which ublk servers can use to essentially test for the presence of this change and tailor their behavior accordingly. Signed-off-by: Uday Shankar Reviewed-by: Caleb Sander Mateos Reviewed-by: Ming Lei Reviewed-by: Jens Axboe Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-1-e9d3b119336a@purestorage.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 111 +++++++++++++++++++++--------------------- include/uapi/linux/ublk_cmd.h | 9 ++++ 2 files changed, 65 insertions(+), 55 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6f51072776f1..c637ea010d34 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -69,7 +69,8 @@ | UBLK_F_USER_RECOVERY_FAIL_IO \ | UBLK_F_UPDATE_SIZE \ | UBLK_F_AUTO_BUF_REG \ - | UBLK_F_QUIESCE) + | UBLK_F_QUIESCE \ + | UBLK_F_PER_IO_DAEMON) #define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ @@ -166,6 +167,8 @@ struct ublk_io { /* valid if UBLK_IO_FLAG_OWNED_BY_SRV is set */ struct request *req; }; + + struct task_struct *task; }; struct ublk_queue { @@ -173,11 +176,9 @@ struct ublk_queue { int q_depth; unsigned long flags; - struct task_struct *ubq_daemon; struct ublksrv_io_desc *io_cmd_buf; bool force_abort; - bool timeout; bool canceling; bool fail_io; /* copy of dev->state == UBLK_S_DEV_FAIL_IO */ unsigned short nr_io_ready; /* how many ios setup */ @@ -1099,11 +1100,6 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( return io_uring_cmd_to_pdu(ioucmd, struct ublk_uring_cmd_pdu); } -static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq) -{ - return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING; -} - /* todo: handle partial completion */ static inline void __ublk_complete_rq(struct request *req) { @@ -1275,13 +1271,13 @@ static void ublk_dispatch_req(struct ublk_queue *ubq, /* * Task is exiting if either: * - * (1) current != ubq_daemon. + * (1) current != io->task. * io_uring_cmd_complete_in_task() tries to run task_work - * in a workqueue if ubq_daemon(cmd's task) is PF_EXITING. + * in a workqueue if cmd's task is PF_EXITING. * * (2) current->flags & PF_EXITING. */ - if (unlikely(current != ubq->ubq_daemon || current->flags & PF_EXITING)) { + if (unlikely(current != io->task || current->flags & PF_EXITING)) { __ublk_abort_rq(ubq, req); return; } @@ -1330,24 +1326,22 @@ static void ublk_cmd_list_tw_cb(struct io_uring_cmd *cmd, { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct request *rq = pdu->req_list; - struct ublk_queue *ubq = pdu->ubq; struct request *next; do { next = rq->rq_next; rq->rq_next = NULL; - ublk_dispatch_req(ubq, rq, issue_flags); + ublk_dispatch_req(rq->mq_hctx->driver_data, rq, issue_flags); rq = next; } while (rq); } -static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l) +static void ublk_queue_cmd_list(struct ublk_io *io, struct rq_list *l) { - struct request *rq = rq_list_peek(l); - struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd; + struct io_uring_cmd *cmd = io->cmd; struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - pdu->req_list = rq; + pdu->req_list = rq_list_peek(l); rq_list_init(l); io_uring_cmd_complete_in_task(cmd, ublk_cmd_list_tw_cb); } @@ -1355,13 +1349,10 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l) static enum blk_eh_timer_return ublk_timeout(struct request *rq) { struct ublk_queue *ubq = rq->mq_hctx->driver_data; + struct ublk_io *io = &ubq->ios[rq->tag]; if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) { - if (!ubq->timeout) { - send_sig(SIGKILL, ubq->ubq_daemon, 0); - ubq->timeout = true; - } - + send_sig(SIGKILL, io->task, 0); return BLK_EH_DONE; } @@ -1429,24 +1420,25 @@ static void ublk_queue_rqs(struct rq_list *rqlist) { struct rq_list requeue_list = { }; struct rq_list submit_list = { }; - struct ublk_queue *ubq = NULL; + struct ublk_io *io = NULL; struct request *req; while ((req = rq_list_pop(rqlist))) { struct ublk_queue *this_q = req->mq_hctx->driver_data; + struct ublk_io *this_io = &this_q->ios[req->tag]; - if (ubq && ubq != this_q && !rq_list_empty(&submit_list)) - ublk_queue_cmd_list(ubq, &submit_list); - ubq = this_q; + if (io && io->task != this_io->task && !rq_list_empty(&submit_list)) + ublk_queue_cmd_list(io, &submit_list); + io = this_io; - if (ublk_prep_req(ubq, req, true) == BLK_STS_OK) + if (ublk_prep_req(this_q, req, true) == BLK_STS_OK) rq_list_add_tail(&submit_list, req); else rq_list_add_tail(&requeue_list, req); } - if (ubq && !rq_list_empty(&submit_list)) - ublk_queue_cmd_list(ubq, &submit_list); + if (!rq_list_empty(&submit_list)) + ublk_queue_cmd_list(io, &submit_list); *rqlist = requeue_list; } @@ -1474,17 +1466,6 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) /* All old ioucmds have to be completed */ ubq->nr_io_ready = 0; - /* - * old daemon is PF_EXITING, put it now - * - * It could be NULL in case of closing one quisced device. - */ - if (ubq->ubq_daemon) - put_task_struct(ubq->ubq_daemon); - /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ - ubq->ubq_daemon = NULL; - ubq->timeout = false; - for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; @@ -1495,6 +1476,17 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) io->flags &= UBLK_IO_FLAG_CANCELED; io->cmd = NULL; io->addr = 0; + + /* + * old task is PF_EXITING, put it now + * + * It could be NULL in case of closing one quiesced + * device. + */ + if (io->task) { + put_task_struct(io->task); + io->task = NULL; + } } } @@ -1516,7 +1508,7 @@ static void ublk_reset_ch_dev(struct ublk_device *ub) for (i = 0; i < ub->dev_info.nr_hw_queues; i++) ublk_queue_reinit(ub, ublk_get_queue(ub, i)); - /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ + /* set to NULL, otherwise new tasks cannot mmap io_cmd_buf */ ub->mm = NULL; ub->nr_queues_ready = 0; ub->nr_privileged_daemon = 0; @@ -1783,6 +1775,7 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; struct task_struct *task; + struct ublk_io *io; if (WARN_ON_ONCE(!ubq)) return; @@ -1791,13 +1784,14 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, return; task = io_uring_cmd_get_task(cmd); - if (WARN_ON_ONCE(task && task != ubq->ubq_daemon)) + io = &ubq->ios[pdu->tag]; + if (WARN_ON_ONCE(task && task != io->task)) return; if (!ubq->canceling) ublk_start_cancel(ubq); - WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd); + WARN_ON_ONCE(io->cmd != cmd); ublk_cancel_cmd(ubq, pdu->tag, issue_flags); } @@ -1930,8 +1924,6 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) { ubq->nr_io_ready++; if (ublk_queue_ready(ubq)) { - ubq->ubq_daemon = current; - get_task_struct(ubq->ubq_daemon); ub->nr_queues_ready++; if (capable(CAP_SYS_ADMIN)) @@ -2084,6 +2076,7 @@ static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq, } ublk_fill_io_cmd(io, cmd, buf_addr); + WRITE_ONCE(io->task, get_task_struct(current)); ublk_mark_io_ready(ub, ubq); out: mutex_unlock(&ub->mutex); @@ -2179,6 +2172,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, const struct ublksrv_io_cmd *ub_cmd) { struct ublk_device *ub = cmd->file->private_data; + struct task_struct *task; struct ublk_queue *ubq; struct ublk_io *io; u32 cmd_op = cmd->cmd_op; @@ -2193,13 +2187,14 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, goto out; ubq = ublk_get_queue(ub, ub_cmd->q_id); - if (ubq->ubq_daemon && ubq->ubq_daemon != current) - goto out; if (tag >= ubq->q_depth) goto out; io = &ubq->ios[tag]; + task = READ_ONCE(io->task); + if (task && task != current) + goto out; /* there is pending io cmd, something must be wrong */ if (io->flags & UBLK_IO_FLAG_ACTIVE) { @@ -2449,9 +2444,14 @@ static void ublk_deinit_queue(struct ublk_device *ub, int q_id) { int size = ublk_queue_cmd_buf_size(ub, q_id); struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + int i; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + if (io->task) + put_task_struct(io->task); + } - if (ubq->ubq_daemon) - put_task_struct(ubq->ubq_daemon); if (ubq->io_cmd_buf) free_pages((unsigned long)ubq->io_cmd_buf, get_order(size)); } @@ -2923,7 +2923,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) ub->dev_info.flags &= UBLK_F_ALL; ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE | - UBLK_F_URING_CMD_COMP_IN_TASK; + UBLK_F_URING_CMD_COMP_IN_TASK | + UBLK_F_PER_IO_DAEMON; /* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */ if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY | @@ -3188,14 +3189,14 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, int ublksrv_pid = (int)header->data[0]; int ret = -EINVAL; - pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", - __func__, ub->dev_info.nr_hw_queues, header->dev_id); - /* wait until new ubq_daemon sending all FETCH_REQ */ + pr_devel("%s: Waiting for all FETCH_REQs, dev id %d...\n", __func__, + header->dev_id); + if (wait_for_completion_interruptible(&ub->completion)) return -EINTR; - pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n", - __func__, ub->dev_info.nr_hw_queues, header->dev_id); + pr_devel("%s: All FETCH_REQs received, dev id %d\n", __func__, + header->dev_id); mutex_lock(&ub->mutex); if (ublk_nosrv_should_stop_dev(ub)) diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 56c7e3fc666f..77d9d6af46da 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -272,6 +272,15 @@ */ #define UBLK_F_QUIESCE (1ULL << 12) +/* + * If this feature is set, ublk_drv supports each (qid,tag) pair having + * its own independent daemon task that is responsible for handling it. + * If it is not set, daemons are per-queue instead, so for two pairs + * (qid1,tag1) and (qid2,tag2), if qid1 == qid2, then the same task must + * be responsible for handling (qid1,tag1) and (qid2,tag2). + */ +#define UBLK_F_PER_IO_DAEMON (1ULL << 13) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 97c01e65ef4c1878532be245b2899fc4363cc453 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Sun, 27 Jul 2025 01:15:17 -0700 Subject: Input: Add and document BTN_GRIP* Many controllers these days have started including grip buttons. As there has been no particular assigned BTN_* constants for these, they've been haphazardly assigned to BTN_TRIGGER_HAPPY*. Unfortunately, the assignment of these has varied significantly between drivers. Add and document new constants for these grip buttons. Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20250702040102.125432-2-vi@endrift.com Signed-off-by: Dmitry Torokhov --- Documentation/input/gamepad.rst | 13 +++++++++++++ drivers/hid/hid-debug.c | 2 ++ include/uapi/linux/input-event-codes.h | 5 +++++ 3 files changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/input/gamepad.rst b/Documentation/input/gamepad.rst index 2bba721aa20b..0c918b6f288b 100644 --- a/Documentation/input/gamepad.rst +++ b/Documentation/input/gamepad.rst @@ -190,6 +190,19 @@ Gamepads report the following events: Rumble is advertised as FF_RUMBLE. +- Grip buttons: + + Many pads include buttons on the rear, usually referred to as either grip or + rear buttons, or paddles. These are often reprogrammable by the firmware to + appear as "normal" buttons, but are sometimes exposed to software too. Some + notable examples of this are the Steam Deck, which has R4, R5, L4, and L5 on + the back; the Xbox Elite pads, which have P1-P4; and the Switch 2 Pro + Controller, which has GL and GR. + + For these controllers, BTN_GRIPR and BTN_GRIPR2 should be used for the top + and bottom (if present) right grip button(s), and BTN_GRIPL and BTN_GRIPL2 + should be used for the top and bottom (if present) left grip button(s). + - Profile: Some pads provide a multi-value profile selection switch. Examples include diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 8433306148d5..3cd9c1150cdf 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3291,6 +3291,8 @@ static const char *keys[KEY_MAX + 1] = { [BTN_TR2] = "BtnTR2", [BTN_SELECT] = "BtnSelect", [BTN_START] = "BtnStart", [BTN_MODE] = "BtnMode", [BTN_THUMBL] = "BtnThumbL", [BTN_THUMBR] = "BtnThumbR", + [BTN_GRIPL] = "BtnGripL", [BTN_GRIPR] = "BtnGripR", + [BTN_GRIPL2] = "BtnGripL2", [BTN_GRIPR2] = "BtnGripR2", [BTN_TOOL_PEN] = "ToolPen", [BTN_TOOL_RUBBER] = "ToolRubber", [BTN_TOOL_BRUSH] = "ToolBrush", [BTN_TOOL_PENCIL] = "ToolPencil", [BTN_TOOL_AIRBRUSH] = "ToolAirbrush", [BTN_TOOL_FINGER] = "ToolFinger", diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 5a199f3d4a26..5426297d93fd 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -601,6 +601,11 @@ #define BTN_DPAD_LEFT 0x222 #define BTN_DPAD_RIGHT 0x223 +#define BTN_GRIPL 0x224 +#define BTN_GRIPR 0x225 +#define BTN_GRIPL2 0x226 +#define BTN_GRIPR2 0x227 + #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 */ -- cgit v1.2.3 From 89c52146392948f4cdda3853da9d82ec6d1dd1f4 Mon Sep 17 00:00:00 2001 From: Marcos Alano Date: Tue, 5 Aug 2025 13:44:29 -0700 Subject: Input: add keycode for performance mode key Alienware calls this key "Performance Boost". Dell calls it "G-Mode". The goal is to have a specific keycode to detect when this key is pressed, so userspace can act upon it and do what have to do, usually starting the power profile for performance. Signed-off-by: Marcos Alano Link: https://lore.kernel.org/r/20250509193708.2190586-1-marcoshalano@gmail.com Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 08cb157ab593..ca5851e97fac 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -770,6 +770,9 @@ #define KEY_KBD_LCD_MENU4 0x2bb #define KEY_KBD_LCD_MENU5 0x2bc +/* Performance Boost key (Alienware)/G-Mode key (Dell) */ +#define KEY_PERFORMANCE 0x2bd + #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 #define BTN_TRIGGER_HAPPY2 0x2c1 -- cgit v1.2.3