linux/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c, branch v4.14

lib/interval_tree: fast overlap detection

2017-09-09T01:26:49Z

Allow interval trees to quickly check for overlaps to avoid unnecesary tree lookups in interval_tree_iter_first(). As of this patch, all interval tree flavors will require using a 'rb_root_cached' such that we can have the leftmost node easily available. While most users will make use of this feature, those with special functions (in addition to the generic insert, delete, search calls) will avoid using the cached option as they can do funky things with insertions -- for example, vma_interval_tree_insert_after(). [jglisse@redhat.com: fix deadlock from typo vm_lock_anon_vma()] Link: http://lkml.kernel.org/r/20170808225719.20723-1-jglisse@redhat.com Link: http://lkml.kernel.org/r/20170719014603.19029-12-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Signed-off-by: Jérôme Glisse Acked-by: Christian König Acked-by: Peter Zijlstra (Intel) Acked-by: Doug Ledford Acked-by: Michael S. Tsirkin Cc: David Airlie Cc: Jason Wang Cc: Christian Benvenuti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

drm/amdgpu: update to new mmu_notifier semantic

2017-08-31T23:12:59Z

Calls to mmu_notifier_invalidate_page() were replaced by calls to mmu_notifier_invalidate_range() and are now bracketed by calls to mmu_notifier_invalidate_range_start()/end() Remove now useless invalidate_page callback. Signed-off-by: Jérôme Glisse Reviewed-by: Christian König Cc: amd-gfx@lists.freedesktop.org Cc: Felix Kuehling Cc: Christian König Cc: Alex Deucher Cc: Kirill A. Shutemov Cc: Andrew Morton Cc: Andrea Arcangeli Signed-off-by: Linus Torvalds

drm/amdgpu: Use list_del_init in amdgpu_mn_unregister

2017-08-02T18:29:58Z

Otherwise bo->shadow_list (which is aliased by bo->mn_list) will not appear empty in amdgpu_ttm_bo_destroy and cause an oops when freeing former userptr BOs. Signed-off-by: Felix Kuehling Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: use a 64bit interval tree for VM management v2

2017-04-04T17:40:32Z

This only makes a difference for 32-bit systems. The idea is to have a fixed virtual address space size with 4-level page tables and to minimize differences between 32 and 64-bit systems. v2: Update commit message. Signed-off-by: Christian König Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: remove adev pointer from struct amdgpu_bo v2

2016-10-25T18:38:26Z

It's completely pointless to have two pointers to the device in the same structure. v2: rename function to amdgpu_ttm_adev, fix typos Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: make amdgpu_mn_get wait for mmap_sem killable

2016-05-24T00:04:14Z

amdgpu_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. [arnd@arndb.de: use ERR_PTR() to return from amdgpu_mn_get] Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Christian König Cc: David Airlie Cc: Alex Deucher Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

drm/amdgpu: add invalidate_page callback for userptrs

2016-03-21T15:52:14Z

Otherwise we can run into problems with the writeback code. Signed-off-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Revert "remove the userptr rmn->lock"

2016-03-21T15:52:14Z

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: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Don't call interval_tree_remove in amdgpu_mn_destroy

2016-02-17T21:10:56Z

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: Felix Kuehling Reviewed-by: Christian König

drm/amdgpu: Fix race condition in amdgpu_mn_unregister

2016-02-17T21:10:42Z

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: Felix Kuehling Reviewed-by: Christian König