drm/amdgpu: Enable mode-1 reset for RAS recovery in fatal error mode

The patch is enabling mode-1 reset for RAS recovery in fatal error mode.

Signed-off-by: YiPeng Chai <[email protected]>
Reviewed-by: Hawking Zhang <[email protected]>
Reviewed-by: Tao Zhou <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: YiPeng Chai

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -4593,6 +4593,10 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 	if (amdgpu_gpu_recovery == 0)
 		goto disabled;
 
+	/* Skip soft reset check in fatal error mode */
+	if (!amdgpu_ras_is_poison_mode_supported(adev))
+		return true;
+
 	if (!amdgpu_device_ip_check_soft_reset(adev)) {
 		dev_info(adev->dev,"Timeout, but no hardware hang detected.\n");
 		return false;

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -1948,7 +1948,12 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 
 		reset_context.method = AMD_RESET_METHOD_NONE;
 		reset_context.reset_req_dev = adev;
-		clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+		/* Perform full reset in fatal error mode */
+		if (!amdgpu_ras_is_poison_mode_supported(ras->adev))
+			set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+		else
+			clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 
 		amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
 	}