diff options
| author | Tao Zhou <tao.zhou1@amd.com> | 2023-10-12 09:33:37 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-10-27 01:41:22 +0300 |
| commit | 73582be11ac8f6d6765e185bf48f22efb9d28c3b (patch) | |
| tree | e506f510dba54e20e0b055df9a79f4ca1651914a /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
| parent | f3a3bbf1566c7b6b0f9ac36e8e597c73dc0afdf8 (diff) | |
| download | linux-73582be11ac8f6d6765e185bf48f22efb9d28c3b.tar.xz | |
drm/amdgpu: bypass RAS error reset in some conditions
PMFW is responsible for RAS error reset in some conditions, driver can
skip the operation.
v2: add check for ras->in_recovery, it's set earlier than
amdgpu_in_reset.
v3: fix error in gpu reset check.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <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 | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index f4c2c737b12f..303fbb6a48b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1220,6 +1220,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block block) { 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; if (!block_obj || !block_obj->hw_ops) { dev_dbg_once(adev->dev, "%s doesn't config RAS function\n", @@ -1227,7 +1229,13 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, return -EOPNOTSUPP; } - if (!amdgpu_ras_is_supported(adev, block)) + /* 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; if (block_obj->hw_ops->reset_ras_error_count) |