diff options
| author | Eric Huang <JinhuiEric.Huang@amd.com> | 2019-01-11 14:38:51 -0500 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2019-03-19 15:36:51 -0500 |
| commit | 9b54d2017687df9fa827faf9e4022973b87fc0ff (patch) | |
| tree | bbe1df5476b9ba2c9292279a0fa23c75262e2d04 /drivers/gpu/drm/amd/amdgpu | |
| parent | 0dee45a25a63f7ded9f0f0bec41fe40e397aa438 (diff) | |
drm/amdkfd: add RAS ECC event support (v3)
RAS ECC event will combine with GPU reset event, due to
ECC interrupts are caused by uncorrectable error that triggers
GPU reset.
v2: Fix misleading-indentation warning
v3: fix build with CONFIG_HSA_AMD disabled
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@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 | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 2 |
5 files changed, 9 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index fe1d7368c1e6..acf8ae0cee9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -640,4 +640,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd) void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry) { } + +void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd) +{ +} #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 0e1711a75b68..e6a503760b62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -229,5 +229,6 @@ int kgd2kfd_quiesce_mm(struct mm_struct *mm); int kgd2kfd_resume_mm(struct mm_struct *mm); int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm, struct dma_fence *fence); +void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd); #endif /* AMDGPU_AMDKFD_H_INCLUDED */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 88c45f990f05..6bb71f6ee18e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4805,6 +4805,7 @@ static int gfx_v9_0_process_ras_data_cb(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { /* TODO ue will trigger an interrupt. */ + kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); amdgpu_ras_reset_gpu(adev, 0); return AMDGPU_RAS_UE; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 2daa5ea1c2ea..0252345a1f08 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -354,6 +354,7 @@ static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev, static int gmc_v9_0_process_ras_data_cb(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { + kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); amdgpu_ras_reset_gpu(adev, 0); return AMDGPU_RAS_UE; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 058b9daec514..f7a6fafd70ae 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1851,6 +1851,8 @@ static int sdma_v4_0_process_ras_data_cb(struct amdgpu_device *adev, return 0; } + kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); + amdgpu_ras_reset_gpu(adev, 0); return AMDGPU_RAS_UE; |