diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-11-06 11:25:10 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-11-06 11:25:14 +1000 |
| commit | 9ccde17d46554dbb2757c427f2cdf67688701f96 (patch) | |
| tree | 70a722f3ee4124fc0b4b695f5c4e40f0293ac9ce /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
| parent | f056cb9681f631c99c7c6780c82651c86f15cf5c (diff) | |
| parent | 6d5e0032a92df3a030cd47d91905310591466687 (diff) | |
Merge tag 'amd-drm-next-6.7-2023-11-03' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.7-2023-11-03:
amdgpu:
- Fix RAS support check
- RAS fixes
- MES fixes
- SMU13 fixes
- Contiguous memory allocation fix
- BACO fixes
- GPU reset fixes
- Min power limit fixes
- GFX11 fixes
- USB4/TB hotplug fixes
- ARM regression fix
- GFX9.4.3 fixes
- KASAN/KCSAN stack size check fixes
- SR-IOV fixes
- SMU14 fixes
- PSP13 fixes
- Display blend fixes
- Flexible array size fixes
amdkfd:
- GPUVM fix
radeon:
- Flexible array size fixes
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231103173203.4912-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 19 |
1 files changed, 14 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 303fbb6a48b6..b7fe5951b166 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0); struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; + struct amdgpu_hive_info *hive; + int hive_ras_recovery = 0; if (!block_obj || !block_obj->hw_ops) { dev_dbg_once(adev->dev, "%s doesn't config RAS function\n", @@ -1229,15 +1231,22 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, return -EOPNOTSUPP; } - /* skip ras error reset in gpu reset */ - if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) && - mca_funcs && mca_funcs->mca_set_debug_mode) - return -EOPNOTSUPP; - if (!amdgpu_ras_is_supported(adev, block) || !amdgpu_ras_get_mca_debug_mode(adev)) return -EOPNOTSUPP; + hive = amdgpu_get_xgmi_hive(adev); + if (hive) { + hive_ras_recovery = atomic_read(&hive->ras_recovery); + amdgpu_put_xgmi_hive(hive); + } + + /* skip ras error reset in gpu reset */ + if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) || + hive_ras_recovery) && + mca_funcs && mca_funcs->mca_set_debug_mode) + return -EOPNOTSUPP; + if (block_obj->hw_ops->reset_ras_error_count) block_obj->hw_ops->reset_ras_error_count(adev); |