drm/amdgpu: add new INFO ioctl query for the last GPU page fault

Add a interface to query the last GPU page fault for the process.
Useful for debugging context lost errors.

v2: split vmhub representation between kernel and userspace
v3: add locking when fetching fault info in INFO IOCTL

Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238
libdrm MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23238

Cc: samuel.pitoiset@gmail.com
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher
2020-10-06 16:54:35 -04:00
parent 9cff0879ae
commit 7a41ed8b59
5 changed files with 63 additions and 5 deletions

View File

@@ -906,6 +906,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
#define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1
/* Query the max number of IBs per gang per submission */
#define AMDGPU_INFO_MAX_IBS 0x22
/* query last page fault info */
#define AMDGPU_INFO_GPUVM_FAULT 0x23
#define AMDGPU_INFO_MMR_SE_INDEX_SHIFT 0
#define AMDGPU_INFO_MMR_SE_INDEX_MASK 0xff
@@ -1231,6 +1233,20 @@ struct drm_amdgpu_info_video_caps {
struct drm_amdgpu_info_video_codec_info codec_info[AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_COUNT];
};
#define AMDGPU_VMHUB_TYPE_MASK 0xff
#define AMDGPU_VMHUB_TYPE_SHIFT 0
#define AMDGPU_VMHUB_TYPE_GFX 0
#define AMDGPU_VMHUB_TYPE_MM0 1
#define AMDGPU_VMHUB_TYPE_MM1 2
#define AMDGPU_VMHUB_IDX_MASK 0xff00
#define AMDGPU_VMHUB_IDX_SHIFT 8
struct drm_amdgpu_info_gpuvm_fault {
__u64 addr;
__u32 status;
__u32 vmhub;
};
/*
* Supported GPU families
*/