[PATCH 3.13 159/163] mm: page_alloc: fix zone allocation fairness on UP

Kamal Mostafa kamal at canonical.com
Thu Oct 9 21:03:04 UTC 2014 -stable review patch.  If anyone has any objections, please let me know.


From: Johannes Weiner <hannes at cmpxchg.org>

commit abe5f972912d086c080be4bde67750630b6fb38b upstream.

The zone allocation batches can easily underflow due to higher-order
allocations or spills to remote nodes.  On SMP that's fine, because
underflows are expected from concurrency and dealt with by returning 0.
But on UP, zone_page_state will just return a wrapped unsigned long, which
will get past the <= 0 check and then consider the zone eligible until its
watermarks are hit.

3a025760fc15 ("mm: page_alloc: spill to remote nodes before waking
kswapd") already made the counter-resetting use atomic_long_read() to
accomodate underflows from remote spills, but it didn't go all the way
with it.  Make it clear that these batches are expected to go negative
regardless of concurrency, and use atomic_long_read() everywhere.

Fixes: 81c0a2bb515f ("mm: page_alloc: fair zone allocator policy")
Reported-by: Vlastimil Babka <vbabka at suse.cz>
Reported-by: Leon Romanovsky <leon at leon.nu>
Signed-off-by: Johannes Weiner <hannes at cmpxchg.org>
Acked-by: Mel Gorman <mgorman at suse.de>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
[ kamal: Johannes' 3.12 backport applied to 3.13-stable ]
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
 mm/page_alloc.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9aad4f1..38dca81 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1932,7 +1932,7 @@ zonelist_scan:
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+			if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0)
@@ -5599,9 +5599,8 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				      high_wmark_pages(zone) -
-				      low_wmark_pages(zone) -
-				      zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 		spin_unlock_irqrestore(&zone->lock, flags);

More information about the kernel-team mailing list