1 files changed, 26 insertions, 18 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 95d4f43a03df..e7f06bd0f0cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -563,24 +563,38 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
-	if (!enable)
-		adev->gfx.gfx_off_req_count++;
-	else if (adev->gfx.gfx_off_req_count > 0)
+	if (enable) {
+		/* If the count is already 0, it means there's an imbalance bug somewhere.
+		 * Note that the bug may be in a different caller than the one which triggers the
+		 * WARN_ON_ONCE.
+		 */
+		if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
+			goto unlock;
+
 		adev->gfx.gfx_off_req_count--;
 
-	if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
-	} else if (!enable && adev->gfx.gfx_off_state) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
-			adev->gfx.gfx_off_state = false;
+		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+	} else {
+		if (adev->gfx.gfx_off_req_count == 0) {
+			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
+
+			if (adev->gfx.gfx_off_state &&
+			    !amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
+				adev->gfx.gfx_off_state = false;
 
-			if (adev->gfx.funcs->init_spm_golden) {
-				dev_dbg(adev->dev, "GFXOFF is disabled, re-init SPM golden settings\n");
-				amdgpu_gfx_init_spm_golden(adev);
+				if (adev->gfx.funcs->init_spm_golden) {
+					dev_dbg(adev->dev,
+						"GFXOFF is disabled, re-init SPM golden settings\n");
+					amdgpu_gfx_init_spm_golden(adev);
+				}
 			}
 		}
+
+		adev->gfx.gfx_off_req_count++;
 	}
 
+unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 
@@ -607,7 +621,6 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
 	struct ras_ih_if ih_info = {
 		.cb = amdgpu_gfx_process_ras_data_cb,
 	};
-	struct ras_query_if info = { 0 };
 
 	if (!adev->gfx.ras_if) {
 		adev->gfx.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
@@ -616,7 +629,6 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
 		adev->gfx.ras_if->block = AMDGPU_RAS_BLOCK__GFX;
 		adev->gfx.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->gfx.ras_if->sub_block_index = 0;
-		strcpy(adev->gfx.ras_if->name, "gfx");
 	}
 	fs_info.head = ih_info.head = *adev->gfx.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->gfx.ras_if,
@@ -625,12 +637,8 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
 		goto free;
 
 	if (amdgpu_ras_is_supported(adev, adev->gfx.ras_if->block)) {
-		if (adev->gmc.xgmi.connected_to_cpu) {
-			info.head = *adev->gfx.ras_if;
-			amdgpu_ras_query_error_status(adev, &info);
-		} else {
+		if (!amdgpu_persistent_edc_harvesting_supported(adev))
 			amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX);
-		}
 
 		r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
 		if (r)