mm, page_alloc: inline the fast path of the zonelist iterator

The page allocator iterates through a zonelist for zones that match the
addressing limitations and nodemask of the caller but many allocations
will not be restricted.  Despite this, there is always functional call
overhead which builds up.

This patch inlines the optimistic basic case and only calls the iterator
function for the complex case.  A hindrance was the fact that
cpuset_current_mems_allowed is used in the fastpath as the allowed
nodemask even though all nodes are allowed on most systems.  The patch
handles this by only considering cpuset_current_mems_allowed if a cpuset
exists.  As well as being faster in the fast-path, this removes some
junk in the slowpath.

The performance difference on a page allocator microbenchmark is;

                                             4.6.0-rc2                  4.6.0-rc2
                                      statinline-v1r20              optiter-v1r20
  Min      alloc-odr0-1               412.00 (  0.00%)           382.00 (  7.28%)
  Min      alloc-odr0-2               301.00 (  0.00%)           282.00 (  6.31%)
  Min      alloc-odr0-4               247.00 (  0.00%)           233.00 (  5.67%)
  Min      alloc-odr0-8               215.00 (  0.00%)           203.00 (  5.58%)
  Min      alloc-odr0-16              199.00 (  0.00%)           188.00 (  5.53%)
  Min      alloc-odr0-32              191.00 (  0.00%)           182.00 (  4.71%)
  Min      alloc-odr0-64              187.00 (  0.00%)           177.00 (  5.35%)
  Min      alloc-odr0-128             185.00 (  0.00%)           175.00 (  5.41%)
  Min      alloc-odr0-256             193.00 (  0.00%)           184.00 (  4.66%)
  Min      alloc-odr0-512             207.00 (  0.00%)           197.00 (  4.83%)
  Min      alloc-odr0-1024            213.00 (  0.00%)           203.00 (  4.69%)
  Min      alloc-odr0-2048            220.00 (  0.00%)           209.00 (  5.00%)
  Min      alloc-odr0-4096            226.00 (  0.00%)           214.00 (  5.31%)
  Min      alloc-odr0-8192            229.00 (  0.00%)           218.00 (  4.80%)
  Min      alloc-odr0-16384           229.00 (  0.00%)           219.00 (  4.37%)

perf indicated that next_zones_zonelist disappeared in the profile and
__next_zones_zonelist did not appear.  This is expected as the
micro-benchmark would hit the inlined fast-path every time.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Cc: 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>

2 files changed, 10 insertions, 18 deletions

diff --git a/mm/mmzone.c b/mm/mmzone.c
index 52687fb4de6f..5652be858e5e 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -52,7 +52,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
 }
 
 /* Returns the next zone at or below highest_zoneidx in a zonelist */
-struct zoneref *next_zones_zonelist(struct zoneref *z,
+struct zoneref *__next_zones_zonelist(struct zoneref *z,
 					enum zone_type highest_zoneidx,
 					nodemask_t *nodes)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 36384baa74e1..789e5f065e8d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3192,17 +3192,6 @@ retry:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
-	/*
-	 * Find the true preferred zone if the allocation is unconstrained by
-	 * cpusets.
-	 */
-	if (!(alloc_flags & ALLOC_CPUSET) && !ac->nodemask) {
-		struct zoneref *preferred_zoneref;
-		preferred_zoneref = first_zones_zonelist(ac->zonelist,
-				ac->high_zoneidx, NULL, &ac->preferred_zone);
-		ac->classzone_idx = zonelist_zone_idx(preferred_zoneref);
-	}
-
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3358,14 +3347,21 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
 	unsigned int cpuset_mems_cookie;
-	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
+	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
 	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
 		.high_zoneidx = gfp_zone(gfp_mask),
+		.zonelist = zonelist,
 		.nodemask = nodemask,
 		.migratetype = gfpflags_to_migratetype(gfp_mask),
 	};
 
+	if (cpusets_enabled()) {
+		alloc_flags |= ALLOC_CPUSET;
+		if (!ac.nodemask)
+			ac.nodemask = &cpuset_current_mems_allowed;
+	}
+
 	gfp_mask &= gfp_allowed_mask;
 
 	lockdep_trace_alloc(gfp_mask);
@@ -3389,16 +3385,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
-	/* We set it here, as __alloc_pages_slowpath might have changed it */
-	ac.zonelist = zonelist;
-
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
 	/* The preferred zone is used for statistics later */
 	preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
-				ac.nodemask ? : &cpuset_current_mems_allowed,
-				&ac.preferred_zone);
+				ac.nodemask, &ac.preferred_zone);
 	if (!ac.preferred_zone)
 		goto out;
 	ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);