linux/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c, branch v4.4

drm/amdgpu: fix incorrect mutex usage v3

2015-11-16T16:05:58Z

Before this patch the scheduler fence was created when we push the job into the queue, so we could only get the fence after pushing it. The mutex now was necessary to prevent the thread pushing the jobs to the hardware from running faster than the thread pushing the jobs into the queue. Otherwise the thread pushing jobs into the queue would have accessed possible freed up memory when it tries to get a reference to the fence. So what you get in the end is thread A: mutex_lock(&job->lock); ... Kick of thread B. ... mutex_unlock(&job->lock); And thread B: mutex_lock(&job->lock); .... mutex_unlock(&job->lock); kfree(job); I'm actually not sure if I'm still up to date on this, but this usage pattern used to be not allowed with mutexes. See here as well https://lwn.net/Articles/575460/. v2: remove unrelated changes, fix missing owner v3: rebased, add more commit message Signed-off-by: Christian König Reviewed-by: Alex Deucher

drm/amdgpu: cleanup scheduler fence get/put dance

2015-11-16T16:05:58Z

The code was correct, but getting two references when the ownership is linearly moved on is a bit awkward and just overhead. Signed: Christian König Reviewed-by: Alex Deucher

drm/amdgpu: add command submission workflow tracepoint

2015-11-16T16:05:57Z

OGL needs these tracepoints to investigate performance issue. Change-Id: I5e58187d061253f7d665dfce8e4e163ba91d3e2b Signed-off-by: Chunming Zhou

drm/amdgpu: remove amdgpu_fence_ref/unref

2015-10-30T05:58:22Z

Just move the remaining users to fence_put/get. Signed-off-by: Christian König Reviewed-by: Alex Deucher

drm/amdgpu: more scheduler cleanups v2

2015-09-23T21:23:39Z

Embed the scheduler into the ring structure instead of allocating it. Use the ring name directly instead of the id. v2: rebased, whitespace cleanup Signed-off-by: Christian König Reviewed-by: Junwei Zhang Reviewed-by: Chunming Zhou

drm/amdgpu: rename fence->scheduler to sched v2

2015-09-23T21:23:37Z

Just to be consistent with the other members. v2: rename the ring member as well. Signed-off-by: Christian König Reviewed-by: Junwei Zhang (v1) Reviewed-by: Chunming Zhou

drm/amdgpu: refine the scheduler job type conversion

2015-09-23T21:23:36Z

Use container_of rather than casting. Reviewed-by: Christian König Reviewed-by: David Zhou Signed-off-by: Junwei Zhang

drm/amdgpu: refine the job naming for amdgpu_job and amdgpu_sched_job

2015-09-23T21:23:36Z

Use consistent naming across functions. Reviewed-by: Christian König Reviewed-by: David Zhou Signed-off-by: Junwei Zhang

drm/amdgpu: remove process_job callback from the scheduler

2015-09-23T21:23:33Z

Just free the resources immediately after submitting the job. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Reviewed-by: Junwei Zhang Reviewed-by: Jammy Zhou

drm/amdgpu: add scheduler dependency callback v2

2015-08-28T19:04:17Z

This way the scheduler doesn't wait in it's work thread any more. v2: fix race conditions Signed-off-by: Christian König Reviewed-by: Chunming Zhou Reviewed-by: Jammy Zhou