kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c, branch linux-4.13.y

drm/amdgpu: add an INFO query for monitoring VRAM CPU page faults

2017-05-24T22:24:38+00:00

v2: bump the DRM version Signed-off-by: Marek Olšák Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: validate shadow before restoring from it

2017-04-28T21:33:08+00:00

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

drm/amdgpu: Fix use of interruptible waiting

2017-04-28T21:33:06+00:00

1. The signal interrupt can affect the expected behaviour. 2. There is no good mechanism to handle the corresponding error. Signed-off-by: Alex Xie Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Refuse to pin or change acceptable domains of prime BOs to VRAM. (v2)

2017-04-07T16:20:39+00:00

Migration to VRAM will break the sharing, resulting in rendering on the exporting GPU never becoming visible on the importing GPU. v2: Don't pin BOs to GTT. Instead, refuse to migrate them out of GTT. Reviewed-by: Christian König Signed-off-by: Christopher James Halse Rogers Signed-off-by: Alex Deucher

drm/amdgpu: handle CPU access for split VRAM buffers (v2)

2017-04-06T17:26:45+00:00

This avoids merging them together on page fault. v2: squash in 64-bit division fix Signed-off-by: Christian König Acked-by: Michel Dänzer Reviewed-by: Nicolai Hähnle Signed-off-by: Alex Deucher

drm/amdgpu: use TTM_PL_FLAG_CONTIGUOUS v2

2017-04-05T03:34:27+00:00

Implement AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS using TTM_PL_FLAG_CONTIGUOUS instead of a placement limit. That allows us to better handle CPU accessible placements. v2: prevent virtual BO start address from overflowing Signed-off-by: Christian König Acked-by: Michel Dänzer Reviewed-by: Nicolai Hähnle Signed-off-by: Alex Deucher

drm/amd/amdgpu: fix performance drop when VRAM pressure

2017-03-30T03:55:48+00:00

When VRAM pressue and trigger huge evictions there is performance drop, this patch fix it. Signed-off-by: Roger.He Reviewed-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: don't validate TILE_SPLIT on GFX9

2017-03-30T03:54:40+00:00

Signed-off-by: Marek Olšák Acked-by: Alex Deucher Acked-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: simplify reservation handling during buffer creation

2017-03-30T03:53:08+00:00

By using ttm_bo_init_reserved instead of the manual initialization of the reservation object, the reservation lock will be properly unlocked and destroyed when the TTM BO initialization fails. Actual deadlocks caused by the missing unlock should have been fixed by "drm/ttm: never add BO that failed to validate to the LRU list", superseding the flawed fix in commit 38fc4856ad98 ("drm/amdgpu: fix a potential deadlock in amdgpu_bo_create_restricted()"). This change fixes remaining recursive locking errors that can be seen with lock debugging enabled, and avoids the error of freeing a locked mutex. As an additional minor bonus, buffers created with resv == NULL and the AMDGPU_GEM_CREATE_VRAM_CLEARED flag are now only added to the global LRU list after the fill commands have been issued. v2: use amdgpu_bo_unreserve instead of ttm_bo_unreserve Fixes: 12a852219583 ("drm/amdgpu: improve AMDGPU_GEM_CREATE_VRAM_CLEARED handling (v2)") Signed-off-by: Nicolai Hähnle Reviewed-by: Christian König Signed-off-by: Alex Deucher

Revert "drm/amdgpu: fix a potential deadlock in amdgpu_bo_create_restricted()"

2017-03-30T03:53:06+00:00

This reverts commit 38fc4856ad98f230bc91da0421dec69e4aee40f8, which introduces a use-after-free. The underlying bug should be properly fixed with "drm/ttm: never add BO that failed to validate to the LRU list". Cc: zhoucm1 Signed-off-by: Nicolai Hähnle Tested-by: Samuel Pitoiset Reviewed-by: Christian König Signed-off-by: Alex Deucher