1 files changed, 98 insertions, 64 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 378a15bcd649..ed06c1dffc9b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -65,6 +65,9 @@
 #include <asm/div64.h>
 #include "internal.h"
 
+/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
+static DEFINE_MUTEX(pcp_batch_high_lock);
+
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -1179,10 +1182,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	unsigned long flags;
 	int to_drain;
+	unsigned long batch;
 
 	local_irq_save(flags);
-	if (pcp->count >= pcp->batch)
-		to_drain = pcp->batch;
+	batch = ACCESS_ONCE(pcp->batch);
+	if (pcp->count >= batch)
+		to_drain = batch;
 	else
 		to_drain = pcp->count;
 	if (to_drain > 0) {
@@ -1350,8 +1355,9 @@ void free_hot_cold_page(struct page *page, int cold)
 		list_add(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
-		free_pcppages_bulk(zone, pcp->batch, pcp);
-		pcp->count -= pcp->batch;
+		unsigned long batch = ACCESS_ONCE(pcp->batch);
+		free_pcppages_bulk(zone, batch, pcp);
+		pcp->count -= batch;
 	}
 
 out:
@@ -1628,6 +1634,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	long min = mark;
 	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
+	long free_cma = 0;
 
 	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
@@ -1637,9 +1644,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 #ifdef CONFIG_CMA
 	/* If allocation can't use CMA areas don't use free CMA pages */
 	if (!(alloc_flags & ALLOC_CMA))
-		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+		free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
-	if (free_pages <= min + lowmem_reserve)
+
+	if (free_pages - free_cma <= min + lowmem_reserve)
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
@@ -3703,12 +3711,12 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 		mminit_verify_zonelist();
 		cpuset_init_current_mems_allowed();
 	} else {
-		/* we have to stop all cpus to guarantee there is no user
-		   of zonelist */
 #ifdef CONFIG_MEMORY_HOTPLUG
 		if (zone)
 			setup_zone_pageset(zone);
 #endif
+		/* we have to stop all cpus to guarantee there is no user
+		   of zonelist */
 		stop_machine(__build_all_zonelists, pgdat, NULL);
 		/* cpuset refresh routine should be here */
 	}
@@ -3926,8 +3934,11 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * exist on hotplugged memory.
 		 */
 		if (context == MEMMAP_EARLY) {
-			if (!early_pfn_valid(pfn))
+			if (!early_pfn_valid(pfn)) {
+				pfn = ALIGN(pfn + MAX_ORDER_NR_PAGES,
+						MAX_ORDER_NR_PAGES) - 1;
 				continue;
+			}
 			if (!early_pfn_in_nid(pfn, nid))
 				continue;
 		}
@@ -4030,7 +4041,40 @@ static int __meminit zone_batchsize(struct zone *zone)
 #endif
 }
 
-static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+/*
+ * pcp->high and pcp->batch values are related and dependent on one another:
+ * ->batch must never be higher then ->high.
+ * The following function updates them in a safe manner without read side
+ * locking.
+ *
+ * Any new users of pcp->batch and pcp->high should ensure they can cope with
+ * those fields changing asynchronously (acording the the above rule).
+ *
+ * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
+ * outside of boot time (or some other assurance that no concurrent updaters
+ * exist).
+ */
+static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
+		unsigned long batch)
+{
+       /* start with a fail safe value for batch */
+	pcp->batch = 1;
+	smp_wmb();
+
+       /* Update high, then batch, in order */
+	pcp->high = high;
+	smp_wmb();
+
+	pcp->batch = batch;
+}
+
+/* a companion to pageset_set_high() */
+static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
+{
+	pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
+}
+
+static void pageset_init(struct per_cpu_pageset *p)
 {
 	struct per_cpu_pages *pcp;
 	int migratetype;
@@ -4039,45 +4083,49 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 
 	pcp = &p->pcp;
 	pcp->count = 0;
-	pcp->high = 6 * batch;
-	pcp->batch = max(1UL, 1 * batch);
 	for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
 		INIT_LIST_HEAD(&pcp->lists[migratetype]);
 }
 
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+{
+	pageset_init(p);
+	pageset_set_batch(p, batch);
+}
+
 /*
- * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
+ * pageset_set_high() sets the high water mark for hot per_cpu_pagelist
  * to the value high for the pageset p.
  */
-
-static void setup_pagelist_highmark(struct per_cpu_pageset *p,
+static void pageset_set_high(struct per_cpu_pageset *p,
 				unsigned long high)
 {
-	struct per_cpu_pages *pcp;
+	unsigned long batch = max(1UL, high / 4);
+	if ((high / 4) > (PAGE_SHIFT * 8))
+		batch = PAGE_SHIFT * 8;
 
-	pcp = &p->pcp;
-	pcp->high = high;
-	pcp->batch = max(1UL, high/4);
-	if ((high/4) > (PAGE_SHIFT * 8))
-		pcp->batch = PAGE_SHIFT * 8;
+	pageset_update(&p->pcp, high, batch);
+}
+
+static void __meminit zone_pageset_init(struct zone *zone, int cpu)
+{
+	struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
+
+	pageset_init(pcp);
+	if (percpu_pagelist_fraction)
+		pageset_set_high(pcp,
+			(zone->managed_pages /
+				percpu_pagelist_fraction));
+	else
+		pageset_set_batch(pcp, zone_batchsize(zone));
 }
 
 static void __meminit setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
-
 	zone->pageset = alloc_percpu(struct per_cpu_pageset);
-
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
-
-		setup_pageset(pcp, zone_batchsize(zone));
-
-		if (percpu_pagelist_fraction)
-			setup_pagelist_highmark(pcp,
-				(zone->managed_pages /
-					percpu_pagelist_fraction));
-	}
+	for_each_possible_cpu(cpu)
+		zone_pageset_init(zone, cpu);
 }
 
 /*
@@ -5538,7 +5586,6 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
  * cpu.  It is the fraction of total pages in each zone that a hot per cpu pagelist
  * can have before it gets flushed back to buddy allocator.
  */
-
 int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
@@ -5549,14 +5596,16 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (!write || (ret < 0))
 		return ret;
+
+	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		for_each_possible_cpu(cpu) {
-			unsigned long  high;
-			high = zone->managed_pages / percpu_pagelist_fraction;
-			setup_pagelist_highmark(
-				per_cpu_ptr(zone->pageset, cpu), high);
-		}
+		unsigned long  high;
+		high = zone->managed_pages / percpu_pagelist_fraction;
+		for_each_possible_cpu(cpu)
+			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
+					 high);
 	}
+	mutex_unlock(&pcp_batch_high_lock);
 	return 0;
 }
 
@@ -6045,32 +6094,17 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit __zone_pcp_update(void *data)
-{
-	struct zone *zone = data;
-	int cpu;
-	unsigned long batch = zone_batchsize(zone), flags;
-
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
-
-		pset = per_cpu_ptr(zone->pageset, cpu);
-		pcp = &pset->pcp;
-
-		local_irq_save(flags);
-		if (pcp->count > 0)
-			free_pcppages_bulk(zone, pcp->count, pcp);
-		drain_zonestat(zone, pset);
-		setup_pageset(pset, batch);
-		local_irq_restore(flags);
-	}
-	return 0;
-}
-
+/*
+ * The zone indicated has a new number of managed_pages; batch sizes and percpu
+ * page high values need to be recalulated.
+ */
 void __meminit zone_pcp_update(struct zone *zone)
 {
-	stop_machine(__zone_pcp_update, zone, NULL);
+	unsigned cpu;
+	mutex_lock(&pcp_batch_high_lock);
+	for_each_possible_cpu(cpu)
+		zone_pageset_init(zone, cpu);
+	mutex_unlock(&pcp_batch_high_lock);
 }
 #endif