- 21 3月, 2016 2 次提交
-
-
由 Christian König 提交于
Otherwise we can run into problems with the writeback code. Signed-off-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Christian König 提交于
This reverts commit c02196834456f2d5fad334088b70e98ce4967c34. In the meantime we moved get_user_pages() outside of the reservation lock, so that shouldn't be an issue any more Signed-off-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 18 2月, 2016 2 次提交
-
-
由 Felix Kuehling 提交于
rbtree_postorder_for_each_entry_safe can skip over some entries if the tree is rebalanced in interval_tree_remove. interval_tree_remove is also redundant when the tree is just about to be freed. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NChristian König <christian.koenig@amd.com>
-
由 Felix Kuehling 提交于
Exchange locking order of adev->mn_lock and mm_sem, so that rmn->mm->mmap_sem can be taken safely, protected by adev->mn_lock, when amdgpu_mn_destroy runs concurrently. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NChristian König <christian.koenig@amd.com>
-
- 17 2月, 2016 1 次提交
-
-
由 Felix Kuehling 提交于
The release notifier can get called a second time from mmu_notifier_unregister depending on a race between __mmu_notifier_release and amdgpu_mn_destroy. Use mmu_notifier_unregister_no_release to avoid this. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NChristian König <christian.koenig@amd.com>
-
- 13 2月, 2016 1 次提交
-
-
由 Christian König 提交于
Avoid a lock inversion problem by just using the mmap_sem to protect the entries of the intervall tree. Signed-off-by: NChristian König <christian.koenig@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
-
- 11 2月, 2016 2 次提交
-
-
由 Christian König 提交于
Otherwise we could try to evict overlapping userptr BOs in get_user_pages(), leading to a possible circular locking dependency. Signed-off-by: NChristian König <christian.koenig@amd.com> Acked-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Christian König 提交于
Otherwise we could try to evict overlapping userptr BOs in get_user_pages(), leading to a possible circular locking dependency. Signed-off-by: NChristian König <christian.koenig@amd.com> Acked-by: NAlex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
-
- 04 6月, 2015 3 次提交
-
-
由 Christian König 提交于
Signed-off-by: NChristian König <christian.koenig@amd.com> Reviewed-by: NJammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: NMonk Liu <monk.liu@amd.com>
-
由 Jack Xiao 提交于
Signed-off-by: NJack Xiao <Jack.Xiao@amd.com> Reviewed-by: NMonk Liu <monk.liu@amd.com> Reviewed-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
由 Alex Deucher 提交于
This adds the non-asic specific core driver code. v2: remove extra kconfig option v3: implement minor fixes from Fengguang Wu v4: fix cast in amdgpu_ucode.c Acked-by: NChristian König <christian.koenig@amd.com> Acked-by: NJammy Zhou <Jammy.Zhou@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 07 5月, 2015 1 次提交
-
-
由 Christian König 提交于
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: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 27 4月, 2015 1 次提交
-
-
由 Christian König 提交于
Otherwise we print false warning from time to time. v2: agd5f: rebase Signed-off-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NJack Xiao <Jack.Xiao@amd.com> CC: stable@vger.kernel.org Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 13 4月, 2015 1 次提交
-
-
由 Christian König 提交于
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: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 02 4月, 2015 1 次提交
-
-
由 Christian König 提交于
We need to wait for all fences, not just the exclusive one. Signed-off-by: NChristian König <christian.koenig@amd.com> Cc: <stable@vger.kernel.org> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 02 9月, 2014 1 次提交
-
-
由 Maarten Lankhorst 提交于
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@canonical.com>
-
- 11 8月, 2014 1 次提交
-
-
由 Christian König 提交于
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: NChristian König <christian.koenig@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-