1 files changed, 29 insertions, 9 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a09a009..979378deccbf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-		__SetPageTail(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -1236,6 +1238,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	}
 	local_irq_restore(flags);
 }
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+	return false;
+}
 #endif
 
 /*
@@ -1572,7 +1583,13 @@ again:
 					  get_pageblock_migratetype(page));
 	}
 
-	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	/*
+	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+	 * aging protocol, so they can't be fair.
+	 */
+	if (!gfp_thisnode_allocation(gfp_flags))
+		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
@@ -1944,8 +1961,12 @@ zonelist_scan:
 		 * ultimately fall back to remote zones that do not
 		 * partake in the fairness round-robin cycle of this
 		 * zonelist.
+		 *
+		 * NOTE: GFP_THISNODE allocations do not partake in
+		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if (alloc_flags & ALLOC_WMARK_LOW) {
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    !gfp_thisnode_allocation(gfp_mask)) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
 			if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (IS_ENABLED(CONFIG_NUMA) &&
-			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (gfp_thisnode_allocation(gfp_mask))
 		goto nopage;
 
 restart:
@@ -2719,7 +2739,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
@@ -2757,7 +2777,7 @@ 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(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	memcg_kmem_commit_charge(page, memcg, order);
@@ -3025,9 +3045,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
 		goto out;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 out:
 	return ret;
 }