drm/amdgpu: fix userptr HMM range handling v2

Browse source

The basic problem here is that it's not allowed to page fault while
holding the reservation lock.

So it can happen that multiple processes try to validate an userptr
at the same time.

Work around that by putting the HMM range object into the mutex
protected bo list for now.

v2: make sure range is set to NULL in case of an error

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

...

This commit is contained in:

Christian König 2022-11-10 12:31:41 +01:00 • committed by Alex Deucher

parent 631945e04e

commit fec8fdb54e

7 changed files with 46 additions and 51 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

12

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

View file

1

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

View file

3

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

View file

8

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

View file

6

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

View file

45

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

View file

14

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h

View file