mm, page_alloc: move __GFP_HARDWALL modifications out of the fastpath

__GFP_HARDWALL only has meaning in the context of cpusets but the fast
path always applies the flag on the first attempt.  Move the
manipulations into the cpuset paths where they will be masked by a
static branch in the common case.

With the other micro-optimisations in this series combined, the impact
on a page allocator microbenchmark is

                                             4.6.0-rc2                  4.6.0-rc2
                                         decstat-v1r20                micro-v1r20
  Min      alloc-odr0-1               381.00 (  0.00%)           377.00 (  1.05%)
  Min      alloc-odr0-2               275.00 (  0.00%)           273.00 (  0.73%)
  Min      alloc-odr0-4               229.00 (  0.00%)           226.00 (  1.31%)
  Min      alloc-odr0-8               199.00 (  0.00%)           196.00 (  1.51%)
  Min      alloc-odr0-16              186.00 (  0.00%)           183.00 (  1.61%)
  Min      alloc-odr0-32              179.00 (  0.00%)           175.00 (  2.23%)
  Min      alloc-odr0-64              174.00 (  0.00%)           172.00 (  1.15%)
  Min      alloc-odr0-128             172.00 (  0.00%)           170.00 (  1.16%)
  Min      alloc-odr0-256             181.00 (  0.00%)           183.00 ( -1.10%)
  Min      alloc-odr0-512             193.00 (  0.00%)           191.00 (  1.04%)
  Min      alloc-odr0-1024            201.00 (  0.00%)           199.00 (  1.00%)
  Min      alloc-odr0-2048            206.00 (  0.00%)           204.00 (  0.97%)
  Min      alloc-odr0-4096            212.00 (  0.00%)           210.00 (  0.94%)
  Min      alloc-odr0-8192            215.00 (  0.00%)           213.00 (  0.93%)
  Min      alloc-odr0-16384           216.00 (  0.00%)           214.00 (  0.93%)

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/page_alloc.c

@@ -3350,7 +3350,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
-	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
+	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
 		.high_zoneidx = gfp_zone(gfp_mask),
 		.zonelist = zonelist,
@@ -3359,6 +3359,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	};
 
 	if (cpusets_enabled()) {
+		alloc_mask |= __GFP_HARDWALL;
 		alloc_flags |= ALLOC_CPUSET;
 		if (!ac.nodemask)
 			ac.nodemask = &cpuset_current_mems_allowed;
@@ -3401,7 +3402,6 @@ retry_cpuset:
 	ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
 	/* First allocation attempt */
-	alloc_mask = gfp_mask|__GFP_HARDWALL;
 	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
 	if (unlikely(!page)) {
 		/*
@@ -3427,8 +3427,10 @@ out:
 	 * the mask is being updated. If a page allocation is about to fail,
 	 * check if the cpuset changed during allocation and if so, retry.
 	 */
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
+		alloc_mask = gfp_mask;
 		goto retry_cpuset;
+	}
 
 	return page;
 }