linux/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c, branch v5.3

drm/amdgpu: fix dma_fence_wait without reference

2019-08-26T20:33:36Z

We need to grab a reference to the fence we wait for. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amd: drop use of drmP.h in amdgpu/amdgpu*

2019-06-10T21:02:48Z

Drop use of drmP.h in all files named amdgpu* in drm/amd/amdgpu/ Fix fallout. Signed-off-by: Sam Ravnborg Reviewed-by: Alex Deucher Cc: "Christian König" Cc: "David (ChunMing) Zhou" Cc: David Airlie Cc: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20190609220757.10862-10-sam@ravnborg.org

drm/amdgpu: wait for VM to become idle during flush

2019-03-19T20:36:58Z

Make sure that not only the entities are flush, but that we also wait for the HW to finish all processing. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: remove non-sense NULL ptr check

2019-03-19T20:36:58Z

It's a bug having a dead pointer in the IDR, silently returning is the worst we can do. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher

drm/amdgpu: Add a new flag to AMDGPU_CTX_OP_QUERY_STATE2

2019-03-19T20:36:51Z

Add AMDGPU_CTX_QUERY2_FLAGS_RAS_CE/UE which indicate if any error happened between previous query and this query. Signed-off-by: xinhui pan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: Only add rqs for initialized rings.

2019-02-15T16:15:30Z

I don't see another way to figure out if a ring is initialized if the hardware block might not be initialized. Entities have been fixed up to handle num_rqs = 0. Signed-off-by: Bas Nieuwenhuizen Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Limit vm max ctx number to 4096

2018-12-10T20:21:13Z

driver need to reserve resource for each ctx for some hw features. so add this limitation. Reviewed-by: Christian König Signed-off-by: Rex Zhu Signed-off-by: Alex Deucher

drm/amdgpu: add VCN JPEG support amdgpu_ctx_num_entities

2018-11-30T17:01:23Z

Looks like it was missed when setting support was added. Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: amdgpu_ctx_add_fence can't fail

2018-08-27T20:12:10Z

No more waiting for a fence done here. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: rework ctx entity creation

2018-08-27T16:11:11Z

Use a fixed number of entities for each hardware IP. The number of compute entities is reduced to four, SDMA keeps it two entities and all other engines just expose one entity. Signed-off-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher