amd/amdgpu: improve VF recover time

1. change AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT from 30 to 5.
2. set fatel error detected flag.
Signed-off-by: Zhigang Luo <Zhigang.Luo@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -4994,6 +4994,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 		r = amdgpu_virt_reset_gpu(adev);
 	if (r)
 		return r;
+	amdgpu_ras_set_fed(adev, false);
 	amdgpu_irq_gpu_reset_resume_helper(adev);
 
 	/* some sw clean up VF needs to do before recover */

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

@@ -598,6 +598,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
 		adev->virt.vf2pf_update_retry_cnt++;
 		if ((adev->virt.vf2pf_update_retry_cnt >= AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT) &&
 		    amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) {
+			amdgpu_ras_set_fed(adev, true);
 			if (amdgpu_reset_domain_schedule(adev->reset_domain,
 							  &adev->virt.flr_work))
 				return;

drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h

@@ -52,7 +52,7 @@
 /* tonga/fiji use this offset */
 #define mmBIF_IOV_FUNC_IDENTIFIER 0x1503
 
-#define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 30
+#define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 5
 
 enum amdgpu_sriov_vf_mode {
 	SRIOV_VF_MODE_BARE_METAL = 0,