mm, page_alloc: shorten the page allocator fast path

The page allocator fast path checks page multiple times unnecessarily.
This patch avoids all the slowpath checks if the first allocation
attempt succeeds.
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

@@ -3398,31 +3398,26 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 				ac.nodemask, &ac.preferred_zone);
 	if (!ac.preferred_zone) {
 		page = NULL;
-		goto out;
+		goto no_zone;
 	}
 
 	ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
-	if (unlikely(!page)) {
+	if (likely(page))
+		goto out;
+
 	/*
-		 * Runtime PM, block IO and its error handling path
-		 * can deadlock because I/O on the device might not
-		 * complete.
+	 * Runtime PM, block IO and its error handling path can deadlock
+	 * because I/O on the device might not complete.
 	 */
 	alloc_mask = memalloc_noio_flags(gfp_mask);
 	ac.spread_dirty_pages = false;
 
 	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
-	}
 
-	if (kmemcheck_enabled && page)
-		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-
-	trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
-
-out:
+no_zone:
 	/*
 	 * When updating a task's mems_allowed, it is possible to race with
 	 * parallel threads in such a way that an allocation can fail while
@@ -3434,6 +3429,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		goto retry_cpuset;
 	}
 
+out:
+	if (kmemcheck_enabled && page)
+		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
+
+	trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);