android_kernel_motorola_sm6375/mm
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Aneesh Kumar K.V 79e522101c mm/mremap: hold the rmap lock in write mode when moving page table entries.
commit 97113eb39fa7972722ff490b947d8af023e1f6a2 upstream.

To avoid a race between rmap walk and mremap, mremap does
take_rmap_locks().  The lock was taken to ensure that rmap walk don't miss
a page table entry due to PTE moves via move_pagetables().  The kernel
does further optimization of this lock such that if we are going to find
the newly added vma after the old vma, the rmap lock is not taken.  This
is because rmap walk would find the vmas in the same order and if we don't
find the page table attached to older vma we would find it with the new
vma which we would iterate later.

As explained in commit eb66ae0308 ("mremap: properly flush TLB before
releasing the page") mremap is special in that it doesn't take ownership
of the page.  The optimized version for PUD/PMD aligned mremap also
doesn't hold the ptl lock.  This can result in stale TLB entries as show
below.

This patch updates the rmap locking requirement in mremap to handle the race condition
explained below with optimized mremap::

Optmized PMD move

    CPU 1                           CPU 2                                   CPU 3

    mremap(old_addr, new_addr)      page_shrinker/try_to_unmap_one

    mmap_write_lock_killable()

                                    addr = old_addr
                                    lock(pte_ptl)
    lock(pmd_ptl)
    pmd = *old_pmd
    pmd_clear(old_pmd)
    flush_tlb_range(old_addr)

    *new_pmd = pmd
                                                                            *new_addr = 10; and fills
                                                                            TLB with new addr
                                                                            and old pfn

    unlock(pmd_ptl)
                                    ptep_clear_flush()
                                    old pfn is free.
                                                                            Stale TLB entry

Optimized PUD move also suffers from a similar race.  Both the above race
condition can be fixed if we force mremap path to take rmap lock.

Link: https://lkml.kernel.org/r/20210616045239.370802-7-aneesh.kumar@linux.ibm.com
Fixes: 2c91bd4a4e ("mm: speed up mremap by 20x on large regions")
Fixes: c49dd3401802 ("mm: speedup mremap on 1GB or larger regions")
Link: https://lore.kernel.org/linux-mm/CAHk-=wgXVR04eBNtxQfevontWnP6FDm+oj5vauQXP3S-huwbPw@mail.gmail.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[patch rewritten for backport since the code was refactored since]
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-08-25 11:17:20 +02:00
..
kasan kasan: fix incorrect arguments passing in kasan_add_zero_shadow 2021-01-27 11:47:53 +01:00
backing-dev.c mm: bdi: initialize bdi_min_ratio when bdi is unregistered 2021-12-14 14:49:00 +01:00
balloon_compaction.c
cleancache.c
cma.c
cma.h
cma_debug.c
compaction.c mm, compaction: fast_find_migrateblock() should return pfn in the target zone 2022-06-14 18:11:46 +02:00
debug.c
debug_page_ref.c
dmapool.c
early_ioremap.c
fadvise.c
failslab.c
filemap.c mm/filemap: fix storing to a THP shadow entry 2021-06-10 13:37:15 +02:00
frame_vector.c
frontswap.c
gup.c
gup_benchmark.c
highmem.c
hmm.c
huge_memory.c mm/huge_memory.c: don't discard hugepage if other processes are mapping it 2021-07-14 16:53:47 +02:00
hugetlb.c hugetlb: fix huge_pmd_unshare address update 2022-06-14 18:11:48 +02:00
hugetlb_cgroup.c
hwpoison-inject.c
init-mm.c
internal.h mm/thp: fix vma_address() if virtual address below file offset 2021-06-30 08:47:52 -04:00
interval_tree.c
Kconfig
Kconfig.debug
khugepaged.c khugepaged: fix wrong result value for trace_mm_collapse_huge_page_isolate() 2021-05-19 10:08:27 +02:00
kmemleak-test.c
kmemleak.c mm: kmemleak: take a full lowmem check in kmemleak_*_phys() 2022-04-20 09:19:38 +02:00
ksm.c ksm: fix potential missing rmap_item for stable_node 2021-05-19 10:08:27 +02:00
list_lru.c
maccess.c
madvise.c
Makefile
memblock.c memblock: use kfree() to release kmalloced memblock regions 2022-03-02 11:41:18 +01:00
memcontrol.c mm/memcontrol: return 1 from cgroup.memory __setup() handler 2022-04-15 14:18:29 +02:00
memfd.c memfd: fix F_SEAL_WRITE after shmem huge page allocated 2022-03-08 19:07:49 +01:00
memory-failure.c mm/memory-failure: make sure wait for page writeback in memory_failure 2021-06-23 14:41:23 +02:00
memory.c mm: hugetlb: fix missing cache flush in copy_huge_page_from_user() 2022-05-15 19:54:47 +02:00
memory_hotplug.c mm/memory_hotplug: use "unsigned long" for PFN in zone_for_pfn_range() 2021-09-22 12:26:43 +02:00
mempolicy.c mm/mempolicy: fix uninit-value in mpol_rebind_policy() 2022-07-29 17:14:16 +02:00
mempool.c
memremap.c
memtest.c
migrate.c mm: fix missing cache flush for all tail pages of compound page 2022-05-15 19:54:47 +02:00
mincore.c
mlock.c
mm_init.c
mmap.c mm, hugetlb: allow for "high" userspace addresses 2022-05-09 09:03:28 +02:00
mmu_context.c
mmu_gather.c
mmu_notifier.c
mmzone.c arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL 2022-05-15 19:54:46 +02:00
mprotect.c
mremap.c mm/mremap: hold the rmap lock in write mode when moving page table entries. 2022-08-25 11:17:20 +02:00
msync.c
nommu.c
oom_kill.c oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup 2022-04-27 13:50:48 +02:00
page-writeback.c
page_alloc.c mm: page_alloc: fix building error on -Werror=array-compare 2022-04-27 13:50:45 +02:00
page_counter.c
page_ext.c
page_idle.c
page_io.c mm: fix unexpected zeroed page mapping with zram swap 2022-05-12 12:23:48 +02:00
page_isolation.c
page_owner.c
page_poison.c
page_vma_mapped.c mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk() 2021-06-30 08:47:55 -04:00
pagewalk.c
percpu-internal.h
percpu-km.c
percpu-stats.c
percpu-vm.c
percpu.c
pgtable-generic.c mm/thp: fix __split_huge_pmd_locked() on shmem migration entry 2021-06-30 08:47:52 -04:00
process_vm_access.c
readahead.c
rmap.c mm: fix race between MADV_FREE reclaim and blkdev direct IO read 2022-04-15 14:18:36 +02:00
rodata_test.c
shmem.c shmem: fix a race between shmem_unused_huge_shrink and shmem_evict_inode 2022-01-27 09:19:29 +01:00
shuffle.c
shuffle.h
slab.c
slab.h mm: kmemleak: slob: respect SLAB_NOLEAKTRACE flag 2021-11-26 10:47:21 +01:00
slab_common.c mm: slab: fix kmem_cache_create failed when sysfs node not destroyed 2021-07-25 14:35:14 +02:00
slob.c
slub.c mm/slub: add missing TID updates on slab deactivation 2022-07-12 16:30:46 +02:00
sparse-vmemmap.c
sparse.c mm/sparse: add the missing sparse_buffer_fini() in error branch 2021-05-14 09:44:32 +02:00
swap.c
swap_cgroup.c
swap_slots.c
swap_state.c
swapfile.c swap: fix swapfile read/write offset 2021-03-07 12:20:49 +01:00
truncate.c mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() 2021-06-30 08:47:53 -04:00
usercopy.c mm/usercopy: return 1 from hardened_usercopy __setup() handler 2022-04-15 14:18:30 +02:00
userfaultfd.c mm: userfaultfd: fix missing cache flush in mcopy_atomic_pte() and __mcopy_atomic() 2022-05-15 19:54:47 +02:00
util.c random: move randomize_page() into mm where it belongs 2022-06-22 14:11:17 +02:00
vmacache.c
vmalloc.c
vmpressure.c
vmscan.c mm,vmscan: fix divide by zero in get_scan_count 2021-09-22 12:26:37 +02:00
vmstat.c arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL 2022-05-15 19:54:46 +02:00
workingset.c
z3fold.c mm/z3fold: fix potential memory leak in z3fold_destroy_pool() 2021-07-14 16:53:47 +02:00
zbud.c
zpool.c
zsmalloc.c zsmalloc: fix races between asynchronous zspage free and page migration 2022-06-06 08:33:50 +02:00
zswap.c