[PATCH v4.9.y] mm: numa: avoid waiting on freed migrated pages

[Mark Rutland <mark.rutland@xxxxxxx>]

commit 3c226c637b69104f6b9f1c6ec5b08d7b741b3229 upstream.

In do_huge_pmd_numa_page(), we attempt to handle a migrating thp pmd by
waiting until the pmd is unlocked before we return and retry.  However, we
can race with migrate_misplaced_transhuge_page():

// do_huge_pmd_numa_page                // migrate_misplaced_transhuge_page()
// Holds 0 refs on page                 // Holds 2 refs on page

vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
/* ... */
if (pmd_trans_migrating(*vmf->pmd)) {
        page = pmd_page(*vmf->pmd);
        spin_unlock(vmf->ptl);
                                        ptl = pmd_lock(mm, pmd);
                                        if (page_count(page) != 2)) {
                                                /* roll back */
                                        }
                                        /* ... */
                                        mlock_migrate_page(new_page, page);
                                        /* ... */
                                        spin_unlock(ptl);
                                        put_page(page);
                                        put_page(page); // page freed here
        wait_on_page_locked(page);
        goto out;
}

This can result in the freed page having its waiters flag set
unexpectedly, which trips the PAGE_FLAGS_CHECK_AT_PREP checks in the page
alloc/free functions.  This has been observed on arm64 KVM guests.

We can avoid this by having do_huge_pmd_numa_page() take a reference on
the page before dropping the pmd lock, mirroring what we do in
__migration_entry_wait().

When we hit the race, migrate_misplaced_transhuge_page() will see the
reference and abort the migration, as it may do today in other cases.

Fixes: b8916634b77bffb2 ("mm: Prevent parallel splits during THP migration")
Link: http://lkml.kernel.org/r/1497349722-6731-2-git-send-email-will.deacon@xxxxxxx
Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
Acked-by: Steve Capper <steve.capper@xxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
 mm/huge_memory.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d5b2b75..e7d5db9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1227,8 +1227,11 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 	 */
 	if (unlikely(pmd_trans_migrating(*fe->pmd))) {
 		page = pmd_page(*fe->pmd);
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(fe->ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		goto out;
 	}
 
@@ -1260,8 +1263,11 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(fe->ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		page_nid = -1;
 		goto out;
 	}
-- 
1.9.1