mm/migrate.c: stabilise page count when migrating transparent hugepages

When migrating a transparent hugepage, migrate_misplaced_transhuge_page
guards itself against a concurrent fastgup of the page by checking that
the page count is equal to 2 before and after installing the new pmd.

If the page count changes, then the pmd is reverted back to the original
entry, however there is a small window where the new (possibly writable)
pmd is installed and the underlying page could be written by userspace.
Restoring the old pmd could therefore result in loss of data.

This patch fixes the problem by freezing the page count whilst updating
the page tables, which protects against a concurrent fastgup without the
need to restore the old pmd in the failure case (since the page count
can no longer change under our feet).

Link: http://lkml.kernel.org/r/1497349722-6731-4-git-send-email-will.deacon@arm.com
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/migrate.c b/mm/migrate.c
index 8935cbe362ce77e32b7a3449d6fdae0990dd3561..62767155187356d54d1fa7333ad402e76183ca0b 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1916,7 +1916,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
        int page_lru = page_is_file_cache(page);
        unsigned long mmun_start = address & HPAGE_PMD_MASK;
        unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
-       pmd_t orig_entry;
 
        /*
         * Rate-limit the amount of data that is being migrated to a node.
@@ -1959,8 +1958,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
        /* Recheck the target PMD */
        mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
        ptl = pmd_lock(mm, pmd);
-       if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
-fail_putback:
+       if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) {
                spin_unlock(ptl);
                mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
@@ -1982,7 +1980,6 @@ fail_putback:
                goto out_unlock;
        }
 
-       orig_entry = *pmd;
        entry = mk_huge_pmd(new_page, vma->vm_page_prot);
        entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
@@ -1999,15 +1996,7 @@ fail_putback:
        set_pmd_at(mm, mmun_start, pmd, entry);
        update_mmu_cache_pmd(vma, address, &entry);
 
-       if (page_count(page) != 2) {
-               set_pmd_at(mm, mmun_start, pmd, orig_entry);
-               flush_pmd_tlb_range(vma, mmun_start, mmun_end);
-               mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
-               update_mmu_cache_pmd(vma, address, &entry);
-               page_remove_rmap(new_page, true);
-               goto fail_putback;
-       }
-
+       page_ref_unfreeze(page, 2);
        mlock_migrate_page(new_page, page);
        page_remove_rmap(page, true);
        set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);