mm: Close races between THP migration and PMD numa clearing

commit 3f926ab945b60a5824369d21add7710622a2eac0 upstream.

THP migration uses the page lock to guard against parallel allocations
but there are cases like this still open

  Task A					Task B
  ---------------------				---------------------
  do_huge_pmd_numa_page				do_huge_pmd_numa_page
  lock_page
  mpol_misplaced == -1
  unlock_page
  goto clear_pmdnuma
						lock_page
						mpol_misplaced == 2
						migrate_misplaced_transhuge
  pmd = pmd_mknonnuma
  set_pmd_at

During hours of testing, one crashed with weird errors and while I have
no direct evidence, I suspect something like the race above happened.
This patch extends the page lock to being held until the pmd_numa is
cleared to prevent migration starting in parallel while the pmd_numa is
being cleared. It also flushes the old pmd entry and orders pagetable
insertion before rmap insertion.

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>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-9-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 15 insertions, 18 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f276efe68c82..c403a74e4bee 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1314,24 +1314,25 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         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);
+                if (page_locked)
                         goto clear_pmdnuma;
-                }
 
-                /* Otherwise wait for potential migrations and retry fault */
+                /*
+                 * Otherwise wait for potential migrations and retry. We do
+                 * relock and check_same as the page may no longer be mapped.
+                 * As the fault is being retried, do not account for it.
+                 */
                 spin_unlock(&mm->page_table_lock);
                 wait_on_page_locked(page);
+                page_nid = -1;
                 goto out;
         }
 
         /* Page is misplaced, serialise migrations and parallel THP splits */
         get_page(page);
         spin_unlock(&mm->page_table_lock);
-        if (!page_locked) {
+        if (!page_locked)
                 lock_page(page);
-                page_locked = true;
-        }
         anon_vma = page_lock_anon_vma_read(page);
 
         /* Confirm the PTE did not while locked */
@@ -1339,32 +1340,28 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         if (unlikely(!pmd_same(pmd, *pmdp))) {
                 unlock_page(page);
                 put_page(page);
+                page_nid = -1;
                 goto out_unlock;
         }
 
-        /* Migrate the THP to the requested node */
+        /*
+         * Migrate the THP to the requested node, returns with page unlocked
+         * and pmd_numa cleared.
+         */
         spin_unlock(&mm->page_table_lock);
         migrated = migrate_misplaced_transhuge_page(mm, vma,
                                 pmdp, pmd, addr, page, target_nid);
         if (migrated)
                 page_nid = target_nid;
-        else
-                goto check_same;
 
         goto out;
-
-check_same:
-        spin_lock(&mm->page_table_lock);
-        if (unlikely(!pmd_same(pmd, *pmdp))) {
-                /* Someone else took our fault */
-                page_nid = -1;
-                goto out_unlock;
-        }
 clear_pmdnuma:
+        BUG_ON(!PageLocked(page));
         pmd = pmd_mknonnuma(pmd);
         set_pmd_at(mm, haddr, pmdp, pmd);
         VM_BUG_ON(pmd_numa(*pmdp));
         update_mmu_cache_pmd(vma, addr, pmdp);
+        unlock_page(page);
 out_unlock:
         spin_unlock(&mm->page_table_lock);