mm: Prevent parallel splits during THP migration

THP migrations are serialised by the page lock but on its own that does
not prevent THP splits. If the page is split during THP migration then
the pmd_same checks will prevent page table corruption but the unlock page
and other fix-ups potentially will cause corruption. This patch takes the
anon_vma lock to prevent parallel splits during migration.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: <stable@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-7-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e10d780c4781adfccf29271630ec06890c0e21e3..d8534b3630e495bb1b0fb75a56846030f3788f61 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1278,18 +1278,18 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                                unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+       struct anon_vma *anon_vma = NULL;
        struct page *page;
        unsigned long haddr = addr & HPAGE_PMD_MASK;
        int target_nid;
        int current_nid = -1;
-       bool migrated;
+       bool migrated, page_locked;
 
        spin_lock(&mm->page_table_lock);
        if (unlikely(!pmd_same(pmd, *pmdp)))
                goto out_unlock;
 
        page = pmd_page(pmd);
-       get_page(page);
        current_nid = page_to_nid(page);
        count_vm_numa_event(NUMA_HINT_FAULTS);
        if (current_nid == numa_node_id())
@@ -1299,12 +1299,29 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         * Acquire the page lock to serialise THP migrations but avoid dropping
         * page_table_lock if at all possible
         */
-       if (trylock_page(page))
-               goto got_lock;
+       page_locked = trylock_page(page);
+       target_nid = mpol_misplaced(page, vma, haddr);
+       if (target_nid == -1) {
+               /* If the page was locked, there are no parallel migrations */
+               if (page_locked) {
+                       unlock_page(page);
+                       goto clear_pmdnuma;
+               }
 
-       /* Serialise against migrationa and check placement check placement */
+               /* Otherwise wait for potential migrations and retry fault */
+               spin_unlock(&mm->page_table_lock);
+               wait_on_page_locked(page);
+               goto out;
+       }
+
+       /* Page is misplaced, serialise migrations and parallel THP splits */
+       get_page(page);
        spin_unlock(&mm->page_table_lock);
-       lock_page(page);
+       if (!page_locked) {
+               lock_page(page);
+               page_locked = true;
+       }
+       anon_vma = page_lock_anon_vma_read(page);
 
        /* Confirm the PTE did not while locked */
        spin_lock(&mm->page_table_lock);
@@ -1314,14 +1331,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                goto out_unlock;
        }
 
-got_lock:
-       target_nid = mpol_misplaced(page, vma, haddr);
-       if (target_nid == -1) {
-               unlock_page(page);
-               put_page(page);
-               goto clear_pmdnuma;
-       }
-
        /* Migrate the THP to the requested node */
        spin_unlock(&mm->page_table_lock);
        migrated = migrate_misplaced_transhuge_page(mm, vma,
@@ -1330,6 +1339,8 @@ got_lock:
                goto check_same;
 
        task_numa_fault(target_nid, HPAGE_PMD_NR, true);
+       if (anon_vma)
+               page_unlock_anon_vma_read(anon_vma);
        return 0;
 
 check_same:
@@ -1346,6 +1357,11 @@ clear_pmdnuma:
        update_mmu_cache_pmd(vma, addr, pmdp);
 out_unlock:
        spin_unlock(&mm->page_table_lock);
+
+out:
+       if (anon_vma)
+               page_unlock_anon_vma_read(anon_vma);
+
        if (current_nid != -1)
                task_numa_fault(current_nid, HPAGE_PMD_NR, false);
        return 0;