summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/radeon_mn.c
Commit message (Collapse)AuthorAgeFilesLines
* drm/radeon: make radeon_mn_get wait for mmap_sem killableMichal Hocko2016-05-231-1/+3
| | | | | | | | | | | | | | | | radeon_mn_get which is called during ioct path relies on mmap_sem for write. If the waiting task gets killed by the oom killer it would block oom_reaper from asynchronous address space reclaim and reduce the chances of timely OOM resolving. Wait for the lock in the killable mode and return with EINTR if the task got killed while waiting. Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: David Airlie <airlied@linux.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* drm/radeon: fix userptr lockupChristian König2015-05-071-0/+3
| | | | | | | | We shouldn't try to reserve and wait for a BO that isn't bound. Otherwise we can run into a deadlock if we have a fault during binding the BO. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/radeon: fix userptr return value checking (v2)Christian König2015-04-271-5/+5
| | | | | | | | | | | Otherwise we print false warning from time to time. v2: agd5f: rebase Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> CC: stable@vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/radeon: allow creating overlapping userptrsChristian König2015-04-131-27/+75
| | | | | | | | | Similar to the Intel implementation, but instead of just falling back to a global linear list when we have an overlapping userptr request we accumulate all overlapping userptrs in a local list. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/radeon: fix wait in radeon_mn_invalidate_range_startChristian König2015-04-021-7/+4
| | | | | | | | We need to wait for all fences, not just the exclusive one. Signed-off-by: Christian König <christian.koenig@amd.com> Cc: <stable@vger.kernel.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: flip the switch, and convert to dma_fenceMaarten Lankhorst2014-09-021-2/+4
| | | | Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
* drm/radeon: add userptr flag to register MMU notifier v3Christian König2014-08-111-0/+272
Whenever userspace mapping related to our userptr change we wait for it to become idle and unmap it from GTT. v2: rebased, fix mutex unlock in error path v3: improve commit message Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
OpenPOWER on IntegriCloud