mm, page_alloc: reduce branches in zone_statistics

zone_statistics has more branches than it really needs to take an
unlikely GFP flag into account.  Reduce the number and annotate the
unlikely flag.

The performance difference on a page allocator microbenchmark is;

                                             4.6.0-rc2                  4.6.0-rc2
                                      nocompound-v1r10           statbranch-v1r10
  Min      alloc-odr0-1               417.00 (  0.00%)           419.00 ( -0.48%)
  Min      alloc-odr0-2               308.00 (  0.00%)           305.00 (  0.97%)
  Min      alloc-odr0-4               253.00 (  0.00%)           250.00 (  1.19%)
  Min      alloc-odr0-8               221.00 (  0.00%)           219.00 (  0.90%)
  Min      alloc-odr0-16              205.00 (  0.00%)           203.00 (  0.98%)
  Min      alloc-odr0-32              199.00 (  0.00%)           195.00 (  2.01%)
  Min      alloc-odr0-64              193.00 (  0.00%)           191.00 (  1.04%)
  Min      alloc-odr0-128             191.00 (  0.00%)           189.00 (  1.05%)
  Min      alloc-odr0-256             200.00 (  0.00%)           198.00 (  1.00%)
  Min      alloc-odr0-512             212.00 (  0.00%)           210.00 (  0.94%)
  Min      alloc-odr0-1024            219.00 (  0.00%)           216.00 (  1.37%)
  Min      alloc-odr0-2048            225.00 (  0.00%)           221.00 (  1.78%)
  Min      alloc-odr0-4096            231.00 (  0.00%)           227.00 (  1.73%)
  Min      alloc-odr0-8192            234.00 (  0.00%)           232.00 (  0.85%)
  Min      alloc-odr0-16384           234.00 (  0.00%)           232.00 (  0.85%)
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>

mm/vmstat.c

@@ -581,17 +581,21 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
  */
 void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags)
 {
-	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
+	int local_nid = numa_node_id();
+	enum zone_stat_item local_stat = NUMA_LOCAL;
+
+	if (unlikely(flags & __GFP_OTHER_NODE)) {
+		local_stat = NUMA_OTHER;
+		local_nid = preferred_zone->node;
+	}
+
+	if (z->node == local_nid) {
 		__inc_zone_state(z, NUMA_HIT);
+		__inc_zone_state(z, local_stat);
 	} else {
 		__inc_zone_state(z, NUMA_MISS);
 		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
 	}
-	if (z->node == ((flags & __GFP_OTHER_NODE) ?
-			preferred_zone->node : numa_node_id()))
-		__inc_zone_state(z, NUMA_LOCAL);
-	else
-		__inc_zone_state(z, NUMA_OTHER);
 }
 
 /*