From: Andrey Grodzovsky andrey.grodzovsky@amd.com
[ Upstream commit a28fda312a9fabdf0e5f5652449d6197c9fb0a90 ]
Problem: During GPU reset we call the GPU scheduler to suspend it's thread, those two functions in amdgpu also suspend and resume the sceduler for their needs but this can collide with GPU reset in progress and accidently restart a suspended thread before time.
Fix: Serialize with GPU reset.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 5652cc72ed3a..81842ba8cd75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -859,6 +859,9 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data) struct amdgpu_device *adev = dev->dev_private; int r = 0, i;
+ /* Avoid accidently unparking the sched thread during GPU reset */ + mutex_lock(&adev->lock_reset); + /* hold on the scheduler */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -884,6 +887,8 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data) kthread_unpark(ring->sched.thread); }
+ mutex_unlock(&adev->lock_reset); + return 0; }
@@ -1036,6 +1041,9 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) if (!fences) return -ENOMEM;
+ /* Avoid accidently unparking the sched thread during GPU reset */ + mutex_lock(&adev->lock_reset); + /* stop the scheduler */ kthread_park(ring->sched.thread);
@@ -1075,6 +1083,8 @@ failure: /* restart the scheduler */ kthread_unpark(ring->sched.thread);
+ mutex_unlock(&adev->lock_reset); + ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
if (fences)