On 12/09/2013 02:09 AM, Mel Gorman wrote: > diff --git a/mm/migrate.c b/mm/migrate.c > index cfb4190..5372521 100644 > --- a/mm/migrate.c > +++ b/mm/migrate.c > @@ -1759,6 +1759,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, > goto out_fail; > } > > + /* PTL provides a memory barrier with change_protection_range */ > + ptl = pmd_lock(mm, pmd); > + if (tlb_flush_pending(mm)) > + flush_tlb_range(vma, mmun_start, mmun_end); > + spin_unlock(ptl); > + > /* Prepare a page as a migration target */ > __set_page_locked(new_page); > SetPageSwapBacked(new_page); I don't think there is a need for that extra memory barrier. On the "set_tlb_flush_pending, turn ptes into NUMA ones" side, we have a barrier in the form of the page table lock. We only end up in this code path if the pte/pmd already is a NUMA one, and we take several spinlocks along the way to doing this test. That provides for the memory barrier in this code path. -- All rights reversed -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>