mm/thp: fix __split_huge_pmd_locked() for migration PMD

[ Upstream commit ec0abae6dcdf7ef88607c869bf35a4b63ce1b370 ]

A migrating transparent huge page has to already be unmapped.  Otherwise,
the page could be modified while it is being copied to a new page and data
could be lost.  The function __split_huge_pmd() checks for a PMD migration
entry before calling __split_huge_pmd_locked() leading one to think that
__split_huge_pmd_locked() can handle splitting a migrating PMD.

However, the code always increments the page->_mapcount and adjusts the
memory control group accounting assuming the page is mapped.

Also, if the PMD entry is a migration PMD entry, the call to
is_huge_zero_pmd(*pmd) is incorrect because it calls pmd_pfn(pmd) instead
of migration_entry_to_pfn(pmd_to_swp_entry(pmd)).  Fix these problems by
checking for a PMD migration entry.

Fixes: 84c3fc4e9c56 ("mm: thp: check pmd migration entry in common path")
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>	[4.14+]
Link: https://lkml.kernel.org/r/20200903183140.19055-1-rcampbell@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da9040a6838f8a667c25a0fcdb6e4830d37e5cdf..873de55d93fb2d58a040b4d816eeb0ec1621621e 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2174,7 +2174,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
                put_page(page);
                add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
                return;
-       } else if (is_huge_zero_pmd(*pmd)) {
+       } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
                /*
                 * FIXME: Do we want to invalidate secondary mmu by calling
                 * mmu_notifier_invalidate_range() see comments below inside
@@ -2262,27 +2262,33 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
                pte = pte_offset_map(&_pmd, addr);
                BUG_ON(!pte_none(*pte));
                set_pte_at(mm, addr, pte, entry);
-               atomic_inc(&page[i]._mapcount);
-               pte_unmap(pte);
-       }
-
-       /*
-        * Set PG_double_map before dropping compound_mapcount to avoid
-        * false-negative page_mapped().
-        */
-       if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
-               for (i = 0; i < HPAGE_PMD_NR; i++)
+               if (!pmd_migration)
                        atomic_inc(&page[i]._mapcount);
+               pte_unmap(pte);
        }
 
-       if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
-               /* Last compound_mapcount is gone. */
-               __dec_node_page_state(page, NR_ANON_THPS);
-               if (TestClearPageDoubleMap(page)) {
-                       /* No need in mapcount reference anymore */
+       if (!pmd_migration) {
+               /*
+                * Set PG_double_map before dropping compound_mapcount to avoid
+                * false-negative page_mapped().
+                */
+               if (compound_mapcount(page) > 1 &&
+                   !TestSetPageDoubleMap(page)) {
                        for (i = 0; i < HPAGE_PMD_NR; i++)
-                               atomic_dec(&page[i]._mapcount);
+                               atomic_inc(&page[i]._mapcount);
+               }
+
+               lock_page_memcg(page);
+               if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+                       /* Last compound_mapcount is gone. */
+                       __dec_lruvec_page_state(page, NR_ANON_THPS);
+                       if (TestClearPageDoubleMap(page)) {
+                               /* No need in mapcount reference anymore */
+                               for (i = 0; i < HPAGE_PMD_NR; i++)
+                                       atomic_dec(&page[i]._mapcount);
+                       }
                }
+               unlock_page_memcg(page);
        }
 
        smp_wmb(); /* make pte visible before pmd */