From 85287f782e971778e1b32059c571020a90e4ee88 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 24 Jan 2017 15:18:38 -0800
Subject: [PATCH] mm, page_alloc: move cpuset seqcount checking to slowpath

commit 5ce9bfef1d27944c119a397a9d827bef795487ce upstream.

This is a preparation for the following patch to make review simpler.
While the primary motivation is a bug fix, this also simplifies the fast
path, although the moved code is only enabled when cpusets are in use.

Link: http://lkml.kernel.org/r/20170120103843.24587-4-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Ganapatrao Kulkarni <gpkulkarni@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4dac768c796c..6d319633432b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3424,10 +3424,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	unsigned int alloc_flags;
 	unsigned long did_some_progress;
-	enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+	enum compact_priority compact_priority;
 	enum compact_result compact_result;
-	int compaction_retries = 0;
-	int no_progress_loops = 0;
+	int compaction_retries;
+	int no_progress_loops;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3448,6 +3449,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
+retry_cpuset:
+	compaction_retries = 0;
+	no_progress_loops = 0;
+	compact_priority = DEF_COMPACT_PRIORITY;
+	cpuset_mems_cookie = read_mems_allowed_begin();
+
 	/*
 	 * The fast path uses conservative alloc_flags to succeed only until
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
@@ -3624,6 +3631,15 @@ retry:
 	}
 
 nopage:
+	/*
+	 * 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
+	 * 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 (read_mems_allowed_retry(cpuset_mems_cookie))
+		goto retry_cpuset;
+
 	warn_alloc_failed(gfp_mask, order, NULL);
 got_pg:
 	return page;
@@ -3637,7 +3653,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	struct page *page;
-	unsigned int cpuset_mems_cookie;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
@@ -3674,9 +3689,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
-
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
@@ -3689,6 +3701,11 @@ retry_cpuset:
 					ac.high_zoneidx, ac.nodemask);
 	if (!ac.preferred_zoneref->zone) {
 		page = NULL;
+		/*
+		 * This might be due to race with cpuset_current_mems_allowed
+		 * update, so make sure we retry with original nodemask in the
+		 * slow path.
+		 */
 		goto no_zone;
 	}
 
@@ -3697,6 +3714,7 @@ retry_cpuset:
 	if (likely(page))
 		goto out;
 
+no_zone:
 	/*
 	 * Runtime PM, block IO and its error handling path can deadlock
 	 * because I/O on the device might not complete.
@@ -3714,24 +3732,11 @@ retry_cpuset:
 		ac.nodemask = nodemask;
 		ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 						ac.high_zoneidx, ac.nodemask);
-		if (!ac.preferred_zoneref->zone)
-			goto no_zone;
+		/* If we have NULL preferred zone, slowpath wll handle that */
 	}
 
 	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
-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
-	 * 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))) {
-		alloc_mask = gfp_mask;
-		goto retry_cpuset;
-	}
-
 out:
 	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
 	    unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
-- 
2.10.1