diff options
| author | Jonathan Kim <jonathan.kim@amd.com> | 2021-12-10 00:48:56 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2022-01-15 01:52:00 +0300 |
| commit | cb5cc4f573e18deb7d9143de0ccb62c08181bc85 (patch) | |
| tree | b3f34dec7112248a460d5b6ceff3a8f6aacc5158 /drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | |
| parent | 7389a5b837cde5e5cd771619e9f006ae102f5d7d (diff) | |
| download | linux-cb5cc4f573e18deb7d9143de0ccb62c08181bc85.tar.xz | |
drm/amdgpu: improve debug VRAM access performance using sdma
For better performance during VRAM access for debugged processes, do
read/write copies over SDMA.
In order to fulfill post mortem debugging on a broken device, fallback to
stable MMIO access when gpu recovery is disabled or when job submission
time outs are set to max. Failed SDMA access should automatically fall
back to MMIO access.
Use a pre-allocated GTT bounce buffer pre-mapped into GART to avoid
page-table updates and TLB flushes on access.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index f8f48be16d80..f06fd19b4895 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -98,6 +98,10 @@ struct amdgpu_mman { u64 fw_vram_usage_size; struct amdgpu_bo *fw_vram_usage_reserved_bo; void *fw_vram_usage_va; + + /* PAGE_SIZE'd BO for process memory r/w over SDMA. */ + struct amdgpu_bo *sdma_access_bo; + void *sdma_access_ptr; }; struct amdgpu_copy_mem { |