diff options
| author | Tao Zhou <tao.zhou1@amd.com> | 2021-12-06 15:54:54 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2021-12-28 16:02:59 -0500 |
| commit | b6485bed40d7859735bdbfedbd55dcc8366a88a7 (patch) | |
| tree | 367edc60dcecfb6eaca11767011032e81bccae5e /drivers/gpu/drm/amd/amdgpu | |
| parent | dec63443380cf2ce6bc41258159cda4165fa4279 (diff) | |
drm/amdkfd: reset queue which consumes RAS poison (v2)
CP supports unmap queue with reset mode which only destroys specific queue without affecting others.
Replacing whole gpu reset with reset queue mode for RAS poison consumption
saves much time, and we can also fallback to gpu reset solution if reset
queue fails.
v2: Return directly if process is NULL;
Reset queue solution is not applicable to SDMA, fallback to legacy
way;
Call kfd_unref_process after lookup process.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 3 |
2 files changed, 5 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 46cf48b3904a..0bf09a94d944 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -721,13 +721,13 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev) return adev->have_atomics_support; } -void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev) +void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, bool reset) { struct ras_err_data err_data = {0, 0, 0, NULL}; /* CPU MCA will handle page retirement if connected_to_cpu is 1 */ if (!adev->gmc.xgmi.connected_to_cpu) - amdgpu_umc_process_ras_data_cb(adev, &err_data, NULL); - else + amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset); + else if (reset) amdgpu_amdkfd_gpu_reset(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index fcbc8a9c9e06..61f899e54fd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -296,7 +296,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, uint64_t *mmap_offset); int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev, struct tile_config *config); -void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev); +void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, + bool reset); #if IS_ENABLED(CONFIG_HSA_AMD) void amdgpu_amdkfd_gpuvm_init_mem_limits(void); void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, |