diff options
| author | Dave Airlie <airlied@redhat.com> | 2021-11-02 12:40:57 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2021-11-02 12:40:58 +1000 |
| commit | d9bd054177fbd2c4762546aec40fc3071bfe4cc0 (patch) | |
| tree | 70e34d106c87a7a7fefb810213786a0b8a19b69c /drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | |
| parent | 31fa8cbce4664946a1688898410fee41ad05364d (diff) | |
| parent | 403475be6d8b122c3e6b8a47e075926d7299e5ef (diff) | |
| download | linux-d9bd054177fbd2c4762546aec40fc3071bfe4cc0.tar.bz2 | |
Merge tag 'amd-drm-next-5.16-2021-10-29' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.16-2021-10-29:
amdgpu:
- RAS fixes
- Fix a potential memory leak in device tear down
- Add a stutter mode quirk
- Misc display fixes
- Further display FP refactoring
- Display USB4 fixes
- Display DP2.0 fixes
- DCN 3.1 fixes
- Display 8 ch audio fix
- Fix DMA mask regression for SI parts
- Aldebaran fixes
amdkfd:
- userptr fix
- BO lifetime fix
- Misc code cleanup
UAPI:
- Minor header cleanup (no functional change)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211029184338.4863-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 37 |
1 files changed, 27 insertions, 10 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cdf46bd0d8d5..0e9cfe99ae9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1871,6 +1871,16 @@ bo_reserve_failed: return ret; } +void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem) +{ + struct amdgpu_bo *bo = mem->bo; + + amdgpu_bo_reserve(bo, true); + amdgpu_bo_kunmap(bo); + amdgpu_bo_unpin(bo); + amdgpu_bo_unreserve(bo); +} + int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd, struct kfd_vm_fault_info *mem) { @@ -2041,19 +2051,26 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, /* Get updated user pages */ ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); if (ret) { - pr_debug("%s: Failed to get user pages: %d\n", - __func__, ret); + pr_debug("Failed %d to get user pages\n", ret); + + /* Return -EFAULT bad address error as success. It will + * fail later with a VM fault if the GPU tries to access + * it. Better than hanging indefinitely with stalled + * user mode queues. + * + * Return other error -EBUSY or -ENOMEM to retry restore + */ + if (ret != -EFAULT) + return ret; + } else { - /* Return error -EBUSY or -ENOMEM, retry restore */ - return ret; + /* + * FIXME: Cannot ignore the return code, must hold + * notifier_lock + */ + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); } - /* - * FIXME: Cannot ignore the return code, must hold - * notifier_lock - */ - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); - /* Mark the BO as valid unless it was invalidated * again concurrently. */ |