linux-stable.git/drivers/gpu/drm/amd/scheduler, branch linux-4.6.y

drm/amdgpu: RCU protected amd_sched_fence_release

2016-03-16T21:59:01+00:00

Fences must be freed RCU protected, otherwise the reservation_object_*_rcu()
functions can run into problems.

Signed-off-by: Christian König 
Reviewed-by: Alex Deucher

drm/amdgpu: drop a dummy wakeup scheduler

2016-02-10T19:17:02+00:00

since the dependency job is also scheduled by the same
scheduler with the job depended on it, no need to
call wake up scheduler when the dep is scheduled.

Signed-off-by: Monk Liu 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: add entity only when first job come

2015-12-15T00:41:19+00:00

umd somtimes will create a context for every ring,
that means some entities wouldn't be used at all.

Signed-off-by: Chunming Zhou 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu: fix race condition in amd_sched_entity_push_job

2015-12-04T16:26:52+00:00

As soon as we leave the spinlock after the job has been added to the job
queue, we can no longer rely on the job's data to be available.

I have seen a null-pointer dereference due to sched == NULL in
amd_sched_wakeup via amd_sched_entity_push_job and
amd_sched_ib_submit_kernel_helper. Since the latter initializes
sched_job->sched with the address of the ring scheduler, which is
guaranteed to be non-NULL, this race appears to be a likely culprit.

Signed-off-by: Nicolai Hähnle 
Bugzilla: https://bugs.freedesktop.org/attachment.cgi?bugid=93079
Reviewed-by: Christian König

drm/amd: abstract kernel rq and normal rq to priority of run queue

2015-12-02T20:54:33+00:00

Allows us to set priorities in the scheduler.

Signed-off-by: Chunming Zhou 
Reviewed-by: Christian König 
Reviewed-by: Junwei Zhang

drm/amdgpu: move dependency handling out of atomic section v2

2015-11-23T17:20:15+00:00

This way the driver isn't limited in the dependency handling callback.

v2: remove extra check in amd_sched_entity_pop_job()

Signed-off-by: Christian König 
Reviewed-by: Chunming Zhou

drm/amdgpu: optimize scheduler fence handling

2015-11-23T17:19:58+00:00

We only need to wait for jobs to be scheduled when
the dependency is from the same scheduler.

Signed-off-by: Christian König 
Reviewed-by: Chunming Zhou

drm/amdgpu: fix incorrect mutex usage v3

2015-11-16T16:05:58+00:00

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

2015-11-16T16:05:58+00:00

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

2015-11-16T16:05:57+00:00

OGL needs these tracepoints to investigate performance issue.

Change-Id: I5e58187d061253f7d665dfce8e4e163ba91d3e2b
Signed-off-by: Chunming Zhou