Andrea Arcangeli
d93d7bd610
mm: thp: make the THP mapcount atomic against __split_huge_pmd_locked() ...
commit c444eb564fb16645c172d550359cb3d75fe8a040 upstream.
Write protect anon page faults require an accurate mapcount to decide
if to break the COW or not. This is implemented in the THP path with
reuse_swap_page() ->
page_trans_huge_map_swapcount()/page_trans_huge_mapcount().
If the COW triggers while the other processes sharing the page are
under a huge pmd split, to do an accurate reading, we must ensure the
mapcount isn't computed while it's being transferred from the head
page to the tail pages.
reuse_swap_cache() already runs serialized by the page lock, so it's
enough to add the page lock around __split_huge_pmd_locked too, in
order to add the missing serialization.
Note: the commit in "Fixes" is just to facilitate the backporting,
because the code before such commit didn't try to do an accurate THP
mapcount calculation and it instead used the page_count() to decide if
to COW or not. Both the page_count and the pin_count are THP-wide
refcounts, so they're inaccurate if used in
reuse_swap_page(). Reverting such commit (besides the unrelated fix to
the local anon_vma assignment) would have also opened the window for
memory corruption side effects to certain workloads as documented in
such commit header.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Suggested-by: Jann Horn <jannh@google.com>
Reported-by: Jann Horn <jannh@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: 6d0a07edd1stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-06-20 10:24:19 +02:00
kasan: avoid -Wmaybe-uninitialized warning
2019-05-08 07:19:07 +02:00
writeback: synchronize sync(2) against cgroup writeback membership switches
2019-05-21 18:49:01 +02:00
mm: balloon: use general non-lru movable page feature
2016-07-26 16:19:19 -07:00
mm: kmemleak: avoid using __va() on addresses that don't have a lowmem mapping
2016-10-11 15:06:33 -07:00
mm/cma.c: fail if fixed declaration can't be honored
2019-08-06 18:29:37 +02:00
mm/cma_debug.c: fix the break condition in cma_maxchunk_get()
2019-06-22 08:17:12 +02:00
mm, compaction: fix NR_ISOLATED_* stats for pfn based migration
2017-01-12 11:39:32 +01:00
mm: get rid of vmacache_flush_all() entirely
2018-09-19 22:47:17 +02:00
mm/page_ref: add tracepoint to track down page reference manipulation
2016-03-17 15:09:34 -07:00
mm: convert printk(KERN_<LEVEL> to pr_<level>
2016-03-17 15:09:34 -07:00
mm/early_ioremap: Fix boot hang with earlyprintk=efi,keep
2018-02-25 11:05:49 +01:00
mm/fadvise.c: fix signed overflow UBSAN complaint
2018-09-15 09:42:57 +02:00
mm/filemap.c: don't initiate writeback if mapping has no dirty pages
2019-11-12 19:16:10 +01:00
mm/frame_vector.c: release a semaphore in 'get_vaddr_frames()'
2018-11-10 07:42:52 -08:00
mm, frontswap: convert frontswap_enabled to static key
2016-07-26 16:19:19 -07:00
mm: prevent get_user_pages() from overflowing page refcount
2019-06-11 12:22:45 +02:00
mm/highmem: make nr_free_highpages() handles all highmem zones by itself
2016-05-19 19:12:14 -07:00
mm: thp: make the THP mapcount atomic against __split_huge_pmd_locked()
2020-06-20 10:24:19 +02:00
hugetlbfs: on restore reserve error path retain subpool reservation
2019-06-22 08:17:12 +02:00
mm: hugetlb: switch to css_tryget() in hugetlb_cgroup_charge_cgroup()
2019-11-25 09:51:58 +01:00
mm: Add a user_ns owner to mm_struct and fix ptrace permission checks
2017-01-06 10:40:13 +01:00
vmscan: return NODE_RECLAIM_NOSCAN in node_reclaim() when CONFIG_NUMA is n
2019-12-05 15:35:02 +01:00
mm: don't allow deferred pages with NEED_PER_CPU_KM
2018-05-22 16:57:57 +02:00
PM / Hibernate: allow hibernation with PAGE_POISONING_ZERO
2016-09-13 02:35:27 +02:00
coredump: fix race condition between collapse_huge_page() and core dumping
2019-08-06 18:29:41 +02:00
mm: convert printk(KERN_<LEVEL> to pr_<level>
2016-03-17 15:09:34 -07:00
mm: convert printk(KERN_<LEVEL> to pr_<level>
2016-03-17 15:09:34 -07:00
mm/kmemleak.c: fix check for softirq context
2019-08-04 09:33:41 +02:00
mm/ksm.c: don't WARN if page is still mapped in remove_stable_node()
2019-11-28 18:28:09 +01:00
mm/list_lru.c: fix memory leak in __memcg_init_list_lru_node
2019-06-22 08:17:18 +02:00
x86: remove more uaccess_32.h complexity
2016-05-22 17:21:27 -07:00
mm: madvise(MADV_DODUMP): allow hugetlbfs pages
2018-10-10 08:53:20 +02:00
Disable the __builtin_return_address() warning globally after all
2016-10-12 10:23:41 -07:00
mm/memblock.c: reversed logic in memblock_discard()
2017-08-30 10:21:47 +02:00
memcg: fix NULL pointer dereference in __mem_cgroup_usage_unregister_event
2020-04-02 17:20:26 +02:00
mm: hwpoison: fix thp split handing in soft_offline_in_use_page()
2019-03-23 13:19:49 +01:00
mm: stop leaking PageTables
2019-02-20 10:18:34 +01:00
mm/memory_hotplug: make add_memory() take the device_hotplug_lock
2019-11-28 18:28:51 +01:00
mm: mempolicy: require at least one nodeid for MPOL_PREFERRED
2020-04-13 10:32:54 +02:00
Revert "mm, mempool: only set __GFP_NOMEMALLOC if there are free elements"
2016-07-28 16:07:41 -07:00
hugetlbfs: fix races and page leaks during migration
2019-03-13 14:04:54 -07:00
mm/mincore.c: make mincore() more conservative
2019-05-21 18:48:58 +02:00
mm/mlock.c: change count_mm_mlocked_page_nr return type
2019-07-10 09:55:43 +02:00
mm: convert printk(KERN_<LEVEL> to pr_<level>
2016-03-17 15:09:34 -07:00
arm64: Revert support for execute-only user mappings
2020-01-12 11:24:15 +01:00
mm/mmu_context, sched/core: Fix mmu_context.h assumption
2016-04-28 11:44:19 +02:00
mm/mmu_notifier: use hlist_add_head_rcu()
2019-08-04 09:33:42 +02:00
mm, page_alloc: inline the fast path of the zonelist iterator
2016-05-19 19:12:14 -07:00
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings
2018-08-15 18:14:45 +02:00
mm: Fix mremap not considering huge pmd devmap
2020-06-11 09:22:20 +02:00
mm: discard memblock data later
2017-08-24 17:12:19 -07:00
x86/mm: split vmalloc_sync_all()
2020-04-02 17:20:26 +02:00
oom, oom_reaper: do not enqueue same task twice
2019-02-12 19:45:02 +01:00
mm/page-writeback.c: avoid potential division by zero in wb_min_max_ratio()
2020-01-23 08:19:40 +01:00
mm/page_alloc: fix watchdog soft lockups during set_zone_contiguous()
2020-05-20 08:15:28 +02:00
mm/page_ext.c: fix an imbalance with kmemleak
2019-04-05 22:29:06 +02:00
mm/page_idle.c: fix oops because end_pfn is larger than max_pfn
2019-07-10 09:55:38 +02:00
mm/page_io.c: replace some BUG_ON()s with VM_BUG_ON_PAGE()
2016-10-07 18:46:29 -07:00
mm/page_isolation: fix typo: "paes" -> "pages"
2016-10-07 18:46:29 -07:00
mm/page_owner: don't define fields on struct page_ext by hard-coding
2016-10-07 18:46:27 -07:00
mm: check the return value of lookup_page_ext for all call sites
2016-06-03 15:06:22 -07:00
mm/pagewalk.c: report holes in hugetlb ranges
2017-11-24 08:33:42 +01:00
mm: percpu: use pr_fmt to prefix output
2016-03-17 15:09:34 -07:00
percpu: stop printing kernel addresses
2019-04-27 09:34:47 +02:00
mm/thp/migration: switch from flush_tlb_range to flush_pmd_tlb_range
2016-03-17 15:09:34 -07:00
mm: remove write/force parameters from __get_user_pages_unlocked()
2016-10-18 14:13:37 -07:00
fix Christoph's email addresses
2016-03-17 15:09:34 -07:00
mm: silently skip readahead for DAX inodes
2016-08-26 17:39:35 -07:00
mm: migration: fix migration of huge PMD shared pages
2018-11-21 09:26:03 +01:00
shmem: fix possible deadlocks on shmlock_user_lock
2020-05-20 08:15:33 +02:00
mm/slab.c: fix an infinite loop in leaks_show()
2019-06-22 08:17:13 +02:00
slub: move synchronize_sched out of slab_mutex on shrink
2017-03-22 12:43:38 +01:00
mm: don't warn about large allocations for slab
2018-12-01 09:44:19 +01:00
slub: move synchronize_sched out of slab_mutex on shrink
2017-03-22 12:43:38 +01:00
mm/slub: fix a memory leak in sysfs_slab_add()
2020-06-20 10:24:12 +02:00
treewide: replace obsolete _refok by __ref
2016-08-02 17:31:41 -04:00
mm/memory_hotplug: set magic number to page->freelist instead of page->lru.next
2017-10-21 17:21:36 +02:00
thp: reduce usage of huge zero page's atomic counter
2016-10-07 18:46:28 -07:00
mm, swap_cgroup: reschedule when neeed in swap_cgroup_swapoff()
2017-07-05 14:40:17 +02:00
mm, swap: use offset of swap entry as key of swap cache
2016-10-07 18:46:28 -07:00
x86/speculation/l1tf: Limit swap file size to MAX_PA/2
2018-08-15 18:14:45 +02:00
mm: cleancache: fix corruption on missed inode invalidation
2018-12-08 13:05:09 +01:00
usercopy: Avoid HIGHMEM pfn warning
2019-10-17 13:42:06 -07:00
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
2016-04-04 10:41:08 -07:00
mm: page_mapped: don't assume compound page is huge or THP
2019-01-16 22:12:32 +01:00
mm: get rid of vmacache_flush_all() entirely
2018-09-19 22:47:17 +02:00
mm/vmalloc.c: don't dereference possible NULL pointer in __vunmap()
2020-06-03 08:16:47 +02:00
mm: vmpressure: fix sending wrong events on underflow
2017-03-12 06:41:43 +01:00
mm: remove seemingly spurious reclaimability check from laptop_mode gating
2018-09-19 22:47:12 +02:00
mm, vmstat: hide /proc/pagetypeinfo from normal users
2019-11-12 19:15:43 +01:00
mm: workingset: fix premature shadow node shrinking with cgroups
2017-04-08 09:30:36 +02:00
mm/z3fold.c: avoid modifying HEADLESS page and minor cleanup
2016-06-03 16:02:55 -07:00
mm/zsmalloc.c: fix the migrated zspage statistics.
2020-01-12 11:24:13 +01:00
zswap: re-check zswap_is_full() after do zswap_shrink()
2018-09-05 09:20:02 +02:00
d93d7bd610