[RFC,v3,05/12] drm/amd/virt: For SRIOV send GPU reset directly to TDR queue.

Commit Message

Andrey Grodzovsky Jan. 25, 2022, 10:37 p.m. UTC

No need to to trigger another work queue inside the work queue.

v3:

Problem:
Extra reset caused by host side FLR notification
following guest side triggered reset.
Fix: Preven qeuing flr_work from mailbox irq if guest
already executing a reset.

Suggested-by: Liu Shaoyun <[e-mail]>
Signed-off-by: Andrey Grodzovsky <[e-mail]>
---
 drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 9 ++++++---
 drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 9 ++++++---
 drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 9 ++++++---
 3 files changed, 18 insertions(+), 9 deletions(-)

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 23b066bcffb2..b2b40e169342 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -276,7 +276,7 @@  static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	if (amdgpu_device_should_recover_gpu(adev)
 		&& (!amdgpu_device_has_job_running(adev) ||
 		adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
-		amdgpu_device_gpu_recover(adev, NULL);
+		amdgpu_device_gpu_recover_imp(adev, NULL);
 }
 
 static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -301,8 +301,11 @@  static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 
 	switch (event) {
 		case IDH_FLR_NOTIFICATION:
-		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.flr_work);
+		if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
+			WARN_ONCE(!queue_work(adev->reset_domain.wq,
+					      &adev->virt.flr_work),
+				  "Failed to queue work! at %s",
+				  __func__);
 		break;
 		case IDH_QUERY_ALIVE:
 			xgpu_ai_mailbox_send_ack(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index a35e6d87e537..08411924150d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -308,7 +308,7 @@  static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
-		amdgpu_device_gpu_recover(adev, NULL);
+		amdgpu_device_gpu_recover_imp(adev, NULL);
 }
 
 static int xgpu_nv_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -336,8 +336,11 @@  static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
 
 	switch (event) {
 	case IDH_FLR_NOTIFICATION:
-		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.flr_work);
+		if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
+			WARN_ONCE(!queue_work(adev->reset_domain.wq,
+					      &adev->virt.flr_work),
+				  "Failed to queue work! at %s",
+				  __func__);
 		break;
 		/* READY_TO_ACCESS_GPU is fetched by kernel polling, IRQ can ignore
 		 * it byfar since that polling thread will handle it,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index aef9d059ae52..02290febfcf4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -521,7 +521,7 @@  static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
 
 	/* Trigger recovery due to world switch failure */
 	if (amdgpu_device_should_recover_gpu(adev))
-		amdgpu_device_gpu_recover(adev, NULL);
+		amdgpu_device_gpu_recover_imp(adev, NULL);
 }
 
 static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
@@ -550,8 +550,11 @@  static int xgpu_vi_mailbox_rcv_irq(struct amdgpu_device *adev,
 		r = xgpu_vi_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
 
 		/* only handle FLR_NOTIFY now */
-		if (!r)
-			schedule_work(&adev->virt.flr_work);
+		if (!r && !amdgpu_in_reset(adev))
+			WARN_ONCE(!queue_work(adev->reset_domain.wq,
+					      &adev->virt.flr_work),
+				  "Failed to queue work! at %s",
+				  __func__);
 	}
 
 	return 0;