mm, page_alloc: use __dec_zone_state for order-0 page allocation

__dec_zone_state is cheaper to use for removing an order-0 page as it
has fewer conditions to check.

The performance difference on a page allocator microbenchmark is;

                                             4.6.0-rc2                  4.6.0-rc2
                                         optiter-v1r20              decstat-v1r20
  Min      alloc-odr0-1               382.00 (  0.00%)           381.00 (  0.26%)
  Min      alloc-odr0-2               282.00 (  0.00%)           275.00 (  2.48%)
  Min      alloc-odr0-4               233.00 (  0.00%)           229.00 (  1.72%)
  Min      alloc-odr0-8               203.00 (  0.00%)           199.00 (  1.97%)
  Min      alloc-odr0-16              188.00 (  0.00%)           186.00 (  1.06%)
  Min      alloc-odr0-32              182.00 (  0.00%)           179.00 (  1.65%)
  Min      alloc-odr0-64              177.00 (  0.00%)           174.00 (  1.69%)
  Min      alloc-odr0-128             175.00 (  0.00%)           172.00 (  1.71%)
  Min      alloc-odr0-256             184.00 (  0.00%)           181.00 (  1.63%)
  Min      alloc-odr0-512             197.00 (  0.00%)           193.00 (  2.03%)
  Min      alloc-odr0-1024            203.00 (  0.00%)           201.00 (  0.99%)
  Min      alloc-odr0-2048            209.00 (  0.00%)           206.00 (  1.44%)
  Min      alloc-odr0-4096            214.00 (  0.00%)           212.00 (  0.93%)
  Min      alloc-odr0-8192            218.00 (  0.00%)           215.00 (  1.38%)
  Min      alloc-odr0-16384           219.00 (  0.00%)           216.00 (  1.37%)

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 789e5f0..8f6b6ea 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2417,6 +2417,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
                else
                        page = list_first_entry(list, struct page, lru);
 
+               __dec_zone_state(zone, NR_ALLOC_BATCH);
                list_del(&page->lru);
                pcp->count--;
        } else {
@@ -2438,11 +2439,11 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
                spin_unlock(&zone->lock);
                if (!page)
                        goto failed;
+               __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
                __mod_zone_freepage_state(zone, -(1 << order),
                                          get_pcppage_migratetype(page));
        }
 
-       __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
        if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
            !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
                set_bit(ZONE_FAIR_DEPLETED, &zone->flags);