mm: Close races between THP migration and PMD numa clearing

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>
Cc: <stable@kernel.org>
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>

1 files changed, 11 insertions, 8 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 7a7325ee1d08..c04692774e88 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1715,12 +1715,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
-
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+		goto out_fail;
 	}
 
 	/*
@@ -1737,9 +1737,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1758,7 +1758,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1767,6 +1766,10 @@ out:
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
 	unlock_page(page);
 	put_page(page);
 	return 0;