linux/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c, branch v4.8

drm/amdgpu: remove fence parameter from amd_sched_job_init

2016-07-07T19:06:11Z

We return the fence as part of the job structur anyway, no need to do this twice. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: earlier free SA resources

2016-07-07T19:06:10Z

Keep the time we don't have a fence associated with the resource smaller. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: fix user fence handling once more

2016-07-07T19:06:09Z

Same problem as with the VM page tables. The user fence address must be determined before the job is scheduled, not when the IB is executed. This fixes a security problem where user fences could be used to overwrite any part of VRAM. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: don't update page tables for VM emulation

2016-07-07T19:02:00Z

It's just overhead to do so and allocating a VMID when we don't need one is actually a bit dangerous. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: validate VM PTs only on eviction

2016-07-07T18:54:49Z

We don't need to validate them again if the eviction counter didn't changed. Reviewed-by: Alex Deucher Signed-off-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: save the PD addr before scheduling the job

2016-07-07T18:54:41Z

When we pipeline evictions the page directory could already be moving somewhere else when grab_id is called. Reviewed-by: Alex Deucher Signed-off-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: fix and cleanup job destruction

2016-07-07T18:50:54Z

Remove the job reference counting and just properly destroy it from a work item which blocks on any potential running timeout handler. Signed-off-by: Christian König Reviewed-by: Monk.Liu Signed-off-by: Alex Deucher

drm/amdgpu: properly abstract scheduler timeout handling

2016-07-07T18:50:53Z

The driver shouldn't mess with the scheduler internals. Signed-off-by: Christian König Reviewed-by: Monk.Liu Signed-off-by: Alex Deucher

drm: Remove unused drm_device from drm_gem_object_lookup()

2016-05-17T06:47:30Z

drm_gem_object_lookup() has never required the drm_device for its file local translation of the user handle to the GEM object. Let's remove the unused parameter and save some space. Signed-off-by: Chris Wilson Cc: dri-devel@lists.freedesktop.org Cc: Dave Airlie Cc: Daniel Vetter [danvet: Fixup kerneldoc too.] Signed-off-by: Daniel Vetter

drm/amdgpu: fix and cleanup user fence handling v2

2016-05-11T17:30:32Z

We leaked the BO in the error pass, additional to that we only have one user fence for all IBs in a job. v2: remove white space changes Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher