diff options
| author | Andrey Ryabinin <[email protected]> | 2017-10-13 15:57:43 -0700 |
|---|---|---|
| committer | Linus Torvalds <[email protected]> | 2017-10-13 16:18:32 -0700 |
| commit | de55c8b251974247edda38e952da8e8dd71683ec (patch) | |
| tree | d7cbecb649db0588d47ea6b439aa9209dff908b4 | |
| parent | 8a1ac5dc7be09883051b1bf89a5e57d7ad850fa5 (diff) | |
mm/mempolicy: fix NUMA_INTERLEAVE_HIT counter
Commit 3a321d2a3dde ("mm: change the call sites of numa statistics
items") separated NUMA counters from zone counters, but the
NUMA_INTERLEAVE_HIT call site wasn't updated to use the new interface.
So alloc_page_interleave() actually increments NR_ZONE_INACTIVE_FILE
instead of NUMA_INTERLEAVE_HIT.
Fix this by using __inc_numa_state() interface to increment
NUMA_INTERLEAVE_HIT.
Link: http://lkml.kernel.org/r/[email protected]
Fixes: 3a321d2a3dde ("mm: change the call sites of numa statistics items")
Signed-off-by: Andrey Ryabinin <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Kemi Wang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
| -rw-r--r-- | mm/mempolicy.c | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 006ba625c0b8..a2af6d58a68f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1920,8 +1920,11 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct page *page; page = __alloc_pages(gfp, order, nid); - if (page && page_to_nid(page) == nid) - inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); + if (page && page_to_nid(page) == nid) { + preempt_disable(); + __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); + } return page; } |