linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c, branch dev

drm/amdgpu: remove the queue manager

2018-08-27T16:10:47+00:00

Not needed any more since that is now done by the scheduler. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: implement harvesting support for UVD 7.2 (v3)

2018-07-27T14:07:44+00:00

Properly handle cases where one or more instance of the IP block may be harvested. v2: make sure ip_num_rings is initialized amdgpu_queue_mgr.c v3: rebase on Christian's UVD changes, drop unused var Reviewed-by: James Zhu Signed-off-by: Alex Deucher

drm/amdgpu: expose only the first UVD instance for now

2018-07-25T20:05:32+00:00

Going to completely rework the context to ring mapping with Nayan's GSoC work, but for now just stopping to expose the second UVD instance should do it. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: add AMDGPU_HW_IP_VCN_JPEG to queue mgr

2018-06-15T17:20:40+00:00

Add AMDGPU_HW_IP_VCN_JPEG to queue mgr Signed-off-by: Boyuan Zhang Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu/vg20:Enable 2nd instance queue maping for uvd 7.2

2018-05-18T21:08:14+00:00

Enable 2nd instance uvd queue maping for uvd 7.2. For user, only one UVD instance presents. there is two rings for uvd decode, and 4 rings for uvd encode. Signed-off-by: James Zhu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu/vg20:Restruct uvd to support multiple uvds

2018-05-18T21:08:12+00:00

Vega20 has dual-UVD. Need Restruct amdgpu_device::uvd to support multiple uvds. There are no any logical changes here. Signed-off-by: James Zhu Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: Downgrade DRM_ERROR to DRM_DEBUG in amdgpu_queue_mgr_map

2017-12-06T17:48:06+00:00

Prevent buggy userspace from spamming dmesg. Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher

drm/amdgpu: Use unsigned ring indices in amdgpu_queue_mgr_map

2017-11-28T22:44:14+00:00

This matches the corresponding UAPI fields. Treating the ring index as signed could result in accessing random unrelated memory if the MSB was set. Fixes: effd924d2f3b ("drm/amdgpu: untie user ring ids from kernel ring ids v6") Cc: stable@vger.kernel.org Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher

drm/amdgpu: map compute rings by least recently used pipe

2017-09-28T20:03:22+00:00

This patch provides a guarantee that the first n queues allocated by an application will be on different pipes. Where n is the number of pipes available from the hardware. This helps avoid ring aliasing which can result in work executing in time-sliced mode instead of truly parallel mode. Reviewed-by: Alex Deucher Signed-off-by: Andres Rodriguez Signed-off-by: Alex Deucher

drm/amdgpu: use LRU mapping policy for SDMA engines

2017-05-31T20:49:04+00:00

Spreading the load across multiple SDMA engines can increase memory transfer performance. Signed-off-by: Andres Rodriguez Reviewed-by: Nicolai Hähnle Signed-off-by: Alex Deucher