mm: numa: guarantee that tlb_flush_pending updates are visible before page table updates

According to documentation on barriers, stores issued before a LOCK can
complete after the lock implying that it's possible tlb_flush_pending
can be visible after a page table update.  As per revised documentation,
this patch adds a smp_mb__before_spinlock to guarantee the correct
ordering.

Signed-off-by: Mel Gorman <[email protected]>
Acked-by: Paul E. McKenney <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This commit is contained in:
Mel Gorman authored and Linus Torvalds committed 2013-12-18 19:04:51 -08:00
1 parent 2084140594
commit af2c1401e6
1 file changed
+6 -1
+6 -1
View File
@@ -482,7 +482,12 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
static inline void set_tlb_flush_pending(struct mm_struct *mm)
{
mm->tlb_flush_pending = true;
barrier();
/*
* Guarantee that the tlb_flush_pending store does not leak into the
* critical section updating the page tables
*/
smp_mb__before_spinlock();
}
/* Clearing is done after a TLB flush, which also provides a barrier. */
static inline void clear_tlb_flush_pending(struct mm_struct *mm)