drm/amdgpu: Fix some unload driver issues

stable inclusion
from stable-5.10.36
commit b168fffa3821809d3166e97b055c719f82aa515f
bugzilla: 51867
CVE: NA

--------------------------------

[ Upstream commit bb0cd09b ]

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: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Acked-by: NWeilong Chen <chenweilong@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

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);

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]);