[PATCH 5/6] drm/amdgpu: bypass RAS error reset in some conditions

[Tao Zhou]

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 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 0eb3dbd9d548..95c181cd1fea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1178,6 +1178,8 @@ 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",
@@ -1185,7 +1187,13 @@ 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)
-- 
2.35.1