[PATCH] drm/amdgpu: check recovery status of xgmi hive in ras_reset_error_count

[Tao Zhou]

Handle xgmi hive case.

Suggested-by: Hawking Zhang <Hawking.Zhang at amd.com>
Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 753260745554..0093c28f4343 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1226,6 +1226,8 @@ 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",
@@ -1237,8 +1239,15 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
 	    !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)) &&
+	if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) ||
+	    hive_ras_recovery) &&
 	    mca_funcs && mca_funcs->mca_set_debug_mode)
 		return -EOPNOTSUPP;
 
-- 
2.35.1