2016-04-27-15-21 merged
Andrea Arcangeli (1):
mm: thp: kvm: fix memory corruption in KVM with THP enabled
Andrew Morton (9):
mm-page_alloc-only-check-pagecompound-for-high-order-pages-fix
mm-page_alloc-remove-unnecessary-initialisation-from-__alloc_pages_nodemask-fix
mm-page_alloc-shorten-the-page-allocator-fast-path-fix
mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice-fix
mm-page_alloc-un-inline-the-bad-part-of-free_pages_check-fix
mm-page_alloc-defer-debugging-checks-of-freed-pages-until-a-pcp-drain-fix
mm-page_alloc-dont-duplicate-code-in-free_pcp_prepare-fix
mm-slab-freelist-randomization-v5-fix
mm-thp-avoid-unnecessary-swapin-in-khugepaged-fix
Chen Gang (2):
include/linux/hugetlb*.h: clean up code
include/linux/hugetlb.h: use bool instead of int for hugepage_migration_supported()
Chen Yucong (1):
memory-failure-replace-mce-with-memory-failure-fix
Christian König (2):
drm/amdgpu: remove the userptr rmn->lock
drm/amdgpu: Revert "remove the userptr rmn->lock"
Dan Streetman (1):
mm/zswap: use workqueue to destroy pool
David Rientjes (1):
mm, hugetlb_cgroup: round limit_in_bytes down to hugepage size
Ebru Akagunduz (2):
mm, vmstat: calculate particular vm event
mm, thp: avoid unnecessary swapin in khugepaged
Eric Dumazet (1):
mm: tighten fault_in_pages_writeable()
Eric Engestrom (1):
MAINTAINERS: fix Rajendra Nayak's address
Felix Kuehling (3):
drm/amdgpu: Fix race condition in MMU notifier release
drm/amdgpu: Fix race condition in amdgpu_mn_unregister
drm/amdgpu: Don't call interval_tree_remove in amdgpu_mn_destroy
Hugh Dickins (2):
mm, cma: prevent nr_isolated_* counters from going negative
mm, compaction: prevent nr_isolated_* from going negative
Joonsoo Kim (1):
mm/slab: fix bug
Konstantin Khlebnikov (1):
mm: enable RLIMIT_DATA by default with workaround for valgrind
Mel Gorman (26):
mm, page_alloc: only check PageCompound for high-order pages
mm, page_alloc: use new PageAnonHead helper in the free page fast path
mm, page_alloc: reduce branches in zone_statistics
mm, page_alloc: inline zone_statistics
mm, page_alloc: use __dec_zone_state for order-0 page allocation
mm, page_alloc: avoid unnecessary zone lookups during pageblock operations
mm, page_alloc: convert nr_fair_skipped to bool
mm, page_alloc: remove unnecessary local variable in get_page_from_freelist
mm, page_alloc: remove unnecessary initialisation in get_page_from_freelist
mm, page_alloc: remove unnecessary initialisation from __alloc_pages_nodemask()
mm, page_alloc: simplify last cpupid reset
mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath
mm, page_alloc: check once if a zone has isolated pageblocks
mm, page_alloc: Check once if a zone has isolated pageblocks -fix
mm, page_alloc: shorten the page allocator fast path
mm, page_alloc: reduce cost of fair zone allocation policy retry
mm, page_alloc: shortcut watermark checks for order-0 pages
mm, page_alloc: avoid looking up the first zone in a zonelist twice
mm, page_alloc: remove field from alloc_context
mm, page_alloc: check multiple page fields with a single branch
mm, page_alloc: pull out side effects from free_pages_check
mm, page_alloc: remove unnecessary variable from free_pcppages_bulk
mm, page_alloc: inline pageblock lookup in page free fast paths
mm, page_alloc: defer debugging checks of freed pages until a PCP drain
mm, page_alloc: defer debugging checks of pages allocated from the PCP
mm, page_alloc: don't duplicate code in free_pcp_prepare
Michal Hocko (61):
Reverted "mm, compaction: direct freepage allocation for async direct compaction"
Reverted "mm: fix incorrect pfn passed to untrack_pfn() in remap_pfn_range()"
Reverted "mm-kasan-initial-memory-quarantine-implementation-v8-fix"
Reverted "mm, page_alloc: defer debugging checks of pages allocated from the PCP"
Reverted "mm, page_alloc: defer debugging checks of freed pages until a PCP drain"
Reverted "cpuset: use static key better and convert to new API"
Reverted "mm, page_alloc: inline pageblock lookup in page free fast paths"
Reverted "mm, page_alloc: remove unnecessary variable from free_pcppages_bulk"
Reverted "mm, page_alloc: check multiple page fields with a single branch"
Reverted "mm, page_alloc: remove field from alloc_context"
Reverted "mm, page_alloc: avoid looking up the first zone in a zonelist twice"
Reverted "mm, page_alloc: shortcut watermark checks for order-0 pages"
Reverted "mm, page_alloc: reduce cost of fair zone allocation policy retry"
Reverted "mm, page_alloc: shorten the page allocator fast path"
Reverted "mm, page_alloc: check once if a zone has isolated pageblocks"
Reverted "mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath"
Reverted "mm, page_alloc: move might_sleep_if check to the allocator slowpath"
Reverted "mm, page_alloc: simplify last cpupid reset"
Reverted "mm, page_alloc: remove redundant check for empty zonelist"
Reverted "mm, page_alloc: remove unnecessary initialisation from __alloc_pages_nodemask()"
Reverted "mm, page_alloc: remove unnecessary initialisation in get_page_from_freelist"
Reverted "mm, page_alloc: remove unnecessary local variable in get_page_from_freelist"
Reverted "mm, page_alloc: convert nr_fair_skipped to bool"
Reverted "mm, page_alloc: avoid unnecessary zone lookups during pageblock operations"
Reverted "mm, page_alloc: use __dec_zone_state for order-0 page allocation"
Reverted "mm, page_alloc: inline zone_statistics"
Reverted "mm, page_alloc: reduce branches in zone_statistics"
Reverted "mm, page_alloc: use new PageAnonHead helper in the free page fast path"
Reverted "mm, page_alloc: only check PageCompound for high-order pages"
mm, oom_reaper: hide oom reaped tasks from OOM killer more carefully
mm, oom_reaper: do not mmput synchronously from the oom reaper context
mm-fix: mm, oom_reaper: do not mmput synchronously from the oom reaper context
locking/rwsem: Get rid of __down_write_nested()
locking/rwsem: Drop explicit memory barriers
locking/rwsem, xtensa: Drop superfluous arch specific implementation
locking/rwsem, sh: Drop superfluous arch specific implementation
locking/rwsem, sparc: Drop superfluous arch specific implementation
locking/rwsem: Introduce basis for down_write_killable()
locking/rwsem, alpha: Provide __down_write_killable()
locking/rwsem, ia64: Provide __down_write_killable()
locking/rwsem, s390: Provide __down_write_killable()
locking/rwsem, x86: Provide __down_write_killable()
locking/rwsem: Provide down_write_killable()
mm: make mmap_sem for write waits killable for mm syscalls
mm: make vm_mmap killable
mm: make vm_munmap killable
mm, aout: handle vm_brk failures
mm, elf: handle vm_brk error
mm: make vm_brk killable
mm, proc: make clear_refs killable
mm, fork: make dup_mmap wait for mmap_sem for write killable
ipc, shm: make shmem attach/detach wait for mmap_sem killable
vdso: make arch_setup_additional_pages wait for mmap_sem for write killable
coredump: make coredump_wait wait for mmap_sem for write killable
aio: make aio_setup_ring killable
exec: make exec path waiting for mmap_sem killable
prctl: make PR_SET_THP_DISABLE wait for mmap_sem killable
uprobes: wait for mmap_sem for write killable
drm/i915: make i915_gem_mmap_ioctl wait for mmap_sem killable
drm/radeon: make radeon_mn_get wait for mmap_sem killable
drm/amdgpu: make amdgpu_mn_get wait for mmap_sem killable
Ming Li (1):
mm/swap.c: put activate_page_pvecs and other pagevecs together
Rich Felker (1):
tmpfs/ramfs: fix VM_MAYSHARE mappings for NOMMU
Thomas Garnier (2):
mm: SLAB freelist randomization
mm: SLAB freelist randomization
Vitaly Wool (1):
z3fold-the-3-fold-allocator-for-compressed-pages-v3
Vlastimil Babka (4):
mm, page_alloc: un-inline the bad part of free_pages_check
cpuset: use static key better and convert to new API
mm, page_alloc: uninline the bad page part of check_new_page()
mm, compaction: fix crash in get_pfnblock_flags_mask() from isolate_freepages():
Weijie Yang (1):
mm fix commmets: If SPARSEMEM, pgdata doesn't have page_ext
Xishi Qiu (1):
Documentation/sysctl/vm.txt: update numa_zonelist_order description
Yongji Xie (1):
mm: fix incorrect pfn passed to untrack_pfn() in remap_pfn_range()
drm/amdgpu: make amdgpu_mn_get wait for mmap_sem killable
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.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
1 file changed
