drm/amdgpu: Block all job scheduling activity during DPC recovery

DPC recovery involves ASIC reset just as normal GPU recovery so block
SW GPU schedulers and wait on all concurrent GPU resets.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -4745,6 +4745,20 @@ int amdgpu_device_baco_exit(struct drm_device *dev)
 	return 0;
 }
 
+static void amdgpu_cancel_all_tdr(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+
+		cancel_delayed_work_sync(&ring->sched.work_tdr);
+	}
+}
+
 /**
  * amdgpu_pci_error_detected - Called when a PCI error is detected.
  * @pdev: PCI device struct
@@ -4758,15 +4772,37 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	int i;
 
 	DRM_INFO("PCI error: detected callback, state(%d)!!\n", state);
 
 	switch (state) {
 	case pci_channel_io_normal:
 		return PCI_ERS_RESULT_CAN_RECOVER;
-	case pci_channel_io_frozen:
-		/* Fatal error, prepare for slot reset */
-		amdgpu_device_lock_adev(adev);
+	/* Fatal error, prepare for slot reset */
+	case pci_channel_io_frozen:		
+		/*		
+		 * Cancel and wait for all TDRs in progress if failing to
+		 * set  adev->in_gpu_reset in amdgpu_device_lock_adev
+		 *
+		 * Locking adev->reset_sem will prevent any external access
+		 * to GPU during PCI error recovery
+		 */
+		while (!amdgpu_device_lock_adev(adev, NULL))
+			amdgpu_cancel_all_tdr(adev);
+
+		/*
+		 * Block any work scheduling as we do for regular GPU reset
+		 * for the duration of the recovery
+		 */
+		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+			struct amdgpu_ring *ring = adev->rings[i];
+
+			if (!ring || !ring->sched.thread)
+				continue;
+
+			drm_sched_stop(&ring->sched, NULL);
+		}
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		/* Permanent error, prepare for device removal */
@@ -4899,8 +4935,21 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	int i;
 
-	amdgpu_device_unlock_adev(adev);
 
 	DRM_INFO("PCI error: resume callback!!\n");
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+
+
+		drm_sched_resubmit_jobs(&ring->sched);
+		drm_sched_start(&ring->sched, true);
+	}
+
+	amdgpu_device_unlock_adev(adev);
 }