[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20171003191003.8573-1-aryabinin@virtuozzo.com>
Date: Tue, 3 Oct 2017 22:10:03 +0300
From: Andrey Ryabinin <aryabinin@...tuozzo.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Kemi Wang <kemi.wang@...el.com>,
Mel Gorman <mgorman@...hsingularity.net>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Andrey Ryabinin <aryabinin@...tuozzo.com>
Subject: [PATCH v2] mm/mempolicy: fix NUMA_INTERLEAVE_HIT counter
Commit 3a321d2a3dde 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.
Fixes: 3a321d2a3dde ("mm: change the call sites of numa statistics items")
Signed-off-by: Andrey Ryabinin <aryabinin@...tuozzo.com>
---
mm/mempolicy.c | 7 +++++--
1 file 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;
}
--
2.13.6
Powered by blists - more mailing lists