This is a note to let you know that I've just added the patch titled
drm/amdgpu: Fix some unload driver issues
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdgpu-fix-some-unload-driver-issues.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit cb1ee92537075115025e0429d9977369e764b09c
Author: Emily Deng <Emily.Deng@xxxxxxx>
Date: Thu Mar 4 19:30:51 2021 +0800
drm/amdgpu: Fix some unload driver issues
[ Upstream commit bb0cd09be45ea457f25fdcbcb3d6cf2230f26c46 ]
When unloading driver after killing some applications, it will hit sdma
flush tlb job timeout which is called by ttm_bo_delay_delete. So
to avoid the job submit after fence driver fini, call ttm_bo_lock_delayed_workqueue
before fence driver fini. And also put drm_sched_fini before waiting fence.
Signed-off-by: Emily Deng <Emily.Deng@xxxxxxx>
Reviewed-by: Christian König <christian.koenig@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 76d10f1c579b..7f2689d4b86d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3551,6 +3551,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
{
dev_info(adev->dev, "amdgpu: finishing device.\n");
flush_delayed_work(&adev->delayed_init_work);
+ ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
adev->shutdown = true;
kfree(adev->pci_state);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index fe2d495d08ab..d07c458c0bed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -532,6 +532,8 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
if (!ring || !ring->fence_drv.initialized)
continue;
+ if (!ring->no_scheduler)
+ drm_sched_fini(&ring->sched);
r = amdgpu_fence_wait_empty(ring);
if (r) {
/* no need to trigger GPU reset as we are unloading */
@@ -540,8 +542,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
if (ring->fence_drv.irq_src)
amdgpu_irq_put(adev, ring->fence_drv.irq_src,
ring->fence_drv.irq_type);
- if (!ring->no_scheduler)
- drm_sched_fini(&ring->sched);
+
del_timer_sync(&ring->fence_drv.fallback_timer);
for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
dma_fence_put(ring->fence_drv.fences[j]);
