1 files changed, 55 insertions, 37 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3398d914ed83..91ace8ca97e2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
 static void accept_page(struct page *page, unsigned int order);
-static bool try_to_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order);
 static inline bool has_unaccepted_memory(void);
 static bool __free_unaccepted(struct page *page);
 
@@ -1054,6 +1054,13 @@ __always_inline bool free_pages_prepare(struct page *page,
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
 		pgalloc_tag_sub(page, 1 << order);
+
+		/*
+		 * The page is isolated and accounted for.
+		 * Mark the codetag as empty to avoid accounting error
+		 * when the page is freed by unpoison_memory().
+		 */
+		clear_page_tag_ref(page);
 		return false;
 	}
 
@@ -2343,16 +2350,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-	int count = READ_ONCE(pcp->count);
-
-	while (count) {
-		int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
-		count -= to_drain;
+	int count;
 
+	do {
 		spin_lock(&pcp->lock);
-		free_pcppages_bulk(zone, to_drain, pcp, 0);
+		count = pcp->count;
+		if (count) {
+			int to_drain = min(count,
+				pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+			free_pcppages_bulk(zone, to_drain, pcp, 0);
+			count -= to_drain;
+		}
 		spin_unlock(&pcp->lock);
-	}
+	} while (count);
 }
 
 /*
@@ -3068,9 +3079,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
 	if (!(alloc_flags & ALLOC_CMA))
 		unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
-#ifdef CONFIG_UNACCEPTED_MEMORY
-	unusable_free += zone_page_state(z, NR_UNACCEPTED);
-#endif
 
 	return unusable_free;
 }
@@ -3364,6 +3372,8 @@ retry:
 			}
 		}
 
+		cond_accept_memory(zone, order);
+
 		/*
 		 * Detect whether the number of free pages is below high
 		 * watermark.  If so, we will decrease pcp->high and free
@@ -3389,10 +3399,8 @@ check_alloc_wmark:
 				       gfp_mask)) {
 			int ret;
 
-			if (has_unaccepted_memory()) {
-				if (try_to_accept_memory(zone, order))
-					goto try_this_zone;
-			}
+			if (cond_accept_memory(zone, order))
+				goto try_this_zone;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/*
@@ -3446,10 +3454,8 @@ try_this_zone:
 
 			return page;
 		} else {
-			if (has_unaccepted_memory()) {
-				if (try_to_accept_memory(zone, order))
-					goto try_this_zone;
-			}
+			if (cond_accept_memory(zone, order))
+				goto try_this_zone;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/* Try again if zone has deferred pages */
@@ -5127,7 +5133,7 @@ static char numa_zonelist_order[] = "Node";
 /*
  * sysctl handler for numa_zonelist_order
  */
-static int numa_zonelist_order_handler(struct ctl_table *table, int write,
+static int numa_zonelist_order_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
@@ -5751,7 +5757,6 @@ void __init setup_per_cpu_pageset(void)
 	for_each_online_pgdat(pgdat)
 		pgdat->per_cpu_nodestats =
 			alloc_percpu(struct per_cpu_nodestat);
-	store_early_perpage_metadata();
 }
 
 __meminit void zone_pcp_init(struct zone *zone)
@@ -5815,6 +5820,16 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
+void free_reserved_page(struct page *page)
+{
+	clear_page_tag_ref(page);
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL(free_reserved_page);
+
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
 	struct zone *zone;
@@ -6091,7 +6106,7 @@ postcore_initcall(init_per_zone_wmark_min)
  *	that we can call two helper functions whenever min_free_kbytes
  *	changes.
  */
-static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
+static int min_free_kbytes_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6107,7 +6122,7 @@ static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
+static int watermark_scale_factor_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6137,7 +6152,7 @@ static void setup_min_unmapped_ratio(void)
 }
 
 
-static int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_unmapped_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6164,7 +6179,7 @@ static void setup_min_slab_ratio(void)
 						     sysctl_min_slab_ratio) / 100;
 }
 
-static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6188,7 +6203,7 @@ static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int wri
  * minimum watermarks. The lowmem reserve ratio can only make sense
  * if in function of the boot time zone sizes.
  */
-static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
+static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	int i;
@@ -6209,7 +6224,7 @@ static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
  * 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.
  */
-static int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
+static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
@@ -6930,9 +6945,6 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	struct page *page;
 	bool last;
 
-	if (list_empty(&zone->unaccepted_pages))
-		return false;
-
 	spin_lock_irqsave(&zone->lock, flags);
 	page = list_first_entry_or_null(&zone->unaccepted_pages,
 					struct page, lru);
@@ -6958,23 +6970,29 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	return true;
 }
 
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
 	long to_accept;
-	int ret = false;
+	bool ret = false;
+
+	if (!has_unaccepted_memory())
+		return false;
+
+	if (list_empty(&zone->unaccepted_pages))
+		return false;
 
 	/* How much to accept to get to high watermark? */
 	to_accept = high_wmark_pages(zone) -
 		    (zone_page_state(zone, NR_FREE_PAGES) -
-		    __zone_watermark_unusable_free(zone, order, 0));
+		    __zone_watermark_unusable_free(zone, order, 0) -
+		    zone_page_state(zone, NR_UNACCEPTED));
 
-	/* Accept at least one page */
-	do {
+	while (to_accept > 0) {
 		if (!try_to_accept_memory_one(zone))
 			break;
 		ret = true;
 		to_accept -= MAX_ORDER_NR_PAGES;
-	} while (to_accept > 0);
+	}
 
 	return ret;
 }
@@ -7017,7 +7035,7 @@ static void accept_page(struct page *page, unsigned int order)
 {
 }
 
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
 	return false;
 }