aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
diff options
context:
space:
mode:
authorFelix Kuehling <Felix.Kuehling@amd.com>2019-06-07 11:33:21 -0400
committerAlex Deucher <alexander.deucher@amd.com>2019-07-03 14:31:51 -0500
commite7e2505326496c140db26c797fafea48a492b8c2 (patch)
treee211450c74012576612f419d3c244ab4e0f73c8c /drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
parentdrm/amdkfd: Print a warning when the runlist becomes oversubscribed (diff)
downloadlinux-dev-e7e2505326496c140db26c797fafea48a492b8c2.tar.xz
linux-dev-e7e2505326496c140db26c797fafea48a492b8c2.zip
drm/amdgpu: Use FENCE_OWNER_KFD in process_sync_pds_resv
We don't want eviction fences to trigger when waiting for page table updates to complete during restore. In theory there shouldn't be any unsignaled eviction fences in the PD reservation object, but I'm seeing them in instrumented code for reasons not fully understood. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to '')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0aa81456ec32..764c8efad372 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -813,7 +813,7 @@ static int process_sync_pds_resv(struct amdkfd_process_info *process_info,
ret = amdgpu_sync_resv(NULL,
sync, pd->tbo.resv,
- AMDGPU_FENCE_OWNER_UNDEFINED, false);
+ AMDGPU_FENCE_OWNER_KFD, false);
if (ret)
return ret;
}