1 files changed, 100 insertions, 90 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0ea758b898fd..18cee0d4c8a2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -680,9 +680,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	int migratetype = 0;
 	int batch_free = 0;
 	int to_free = count;
+	unsigned long nr_scanned;
 
 	spin_lock(&zone->lock);
-	zone->pages_scanned = 0;
+	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	if (nr_scanned)
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
 
 	while (to_free) {
 		struct page *page;
@@ -731,8 +734,11 @@ static void free_one_page(struct zone *zone,
 				unsigned int order,
 				int migratetype)
 {
+	unsigned long nr_scanned;
 	spin_lock(&zone->lock);
-	zone->pages_scanned = 0;
+	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	if (nr_scanned)
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
 
 	__free_one_page(page, pfn, zone, order, migratetype);
 	if (unlikely(!is_migrate_isolate(migratetype)))
@@ -1257,15 +1263,11 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	unsigned long flags;
-	int to_drain;
-	unsigned long batch;
+	int to_drain, batch;
 
 	local_irq_save(flags);
 	batch = ACCESS_ONCE(pcp->batch);
-	if (pcp->count >= batch)
-		to_drain = batch;
-	else
-		to_drain = pcp->count;
+	to_drain = min(pcp->count, batch);
 	if (to_drain > 0) {
 		free_pcppages_bulk(zone, to_drain, pcp);
 		pcp->count -= to_drain;
@@ -1610,6 +1612,9 @@ again:
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+	    !zone_is_fair_depleted(zone))
+		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1712,7 +1717,6 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
 	long free_cma = 0;
 
@@ -1727,7 +1731,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 		free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
 
-	if (free_pages - free_cma <= min + lowmem_reserve)
+	if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx])
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
@@ -1922,6 +1926,18 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 
 #endif	/* CONFIG_NUMA */
 
+static void reset_alloc_batches(struct zone *preferred_zone)
+{
+	struct zone *zone = preferred_zone->zone_pgdat->node_zones;
+
+	do {
+		mod_zone_page_state(zone, NR_ALLOC_BATCH,
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
+		zone_clear_flag(zone, ZONE_FAIR_DEPLETED);
+	} while (zone++ != preferred_zone);
+}
+
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -1939,8 +1955,12 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 	bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
 				(gfp_mask & __GFP_WRITE);
+	int nr_fair_skipped = 0;
+	bool zonelist_rescan;
 
 zonelist_scan:
+	zonelist_rescan = false;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
@@ -1964,9 +1984,11 @@ zonelist_scan:
 		 */
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
+				break;
+			if (zone_is_fair_depleted(zone)) {
+				nr_fair_skipped++;
 				continue;
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
-				continue;
+			}
 		}
 		/*
 		 * When allocating a page cache page for writing, we
@@ -2072,13 +2094,7 @@ this_zone_full:
 			zlc_mark_zone_full(zonelist, z);
 	}
 
-	if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) {
-		/* Disable zlc cache for second zonelist scan */
-		zlc_active = 0;
-		goto zonelist_scan;
-	}
-
-	if (page)
+	if (page) {
 		/*
 		 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
 		 * necessary to allocate the page. The expectation is
@@ -2087,8 +2103,37 @@ this_zone_full:
 		 * for !PFMEMALLOC purposes.
 		 */
 		page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+		return page;
+	}
 
-	return page;
+	/*
+	 * The first pass makes sure allocations are spread fairly within the
+	 * local node.  However, the local node might have free pages left
+	 * after the fairness batches are exhausted, and remote zones haven't
+	 * even been considered yet.  Try once more without fairness, and
+	 * include remote zones now, before entering the slowpath and waking
+	 * kswapd: prefer spilling to a remote zone over swapping locally.
+	 */
+	if (alloc_flags & ALLOC_FAIR) {
+		alloc_flags &= ~ALLOC_FAIR;
+		if (nr_fair_skipped) {
+			zonelist_rescan = true;
+			reset_alloc_batches(preferred_zone);
+		}
+		if (nr_online_nodes > 1)
+			zonelist_rescan = true;
+	}
+
+	if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) {
+		/* Disable zlc cache for second zonelist scan */
+		zlc_active = 0;
+		zonelist_rescan = true;
+	}
+
+	if (zonelist_rescan)
+		goto zonelist_scan;
+
+	return NULL;
 }
 
 /*
@@ -2201,8 +2246,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 {
 	struct page *page;
 
-	/* Acquire the OOM killer lock for the zones in zonelist */
-	if (!try_set_zonelist_oom(zonelist, gfp_mask)) {
+	/* Acquire the per-zone oom lock for each zone */
+	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -2240,7 +2285,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
 
 out:
-	clear_zonelist_oom(zonelist, gfp_mask);
+	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
 }
 
@@ -2409,28 +2454,6 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
-static void reset_alloc_batches(struct zonelist *zonelist,
-				enum zone_type high_zoneidx,
-				struct zone *preferred_zone)
-{
-	struct zoneref *z;
-	struct zone *zone;
-
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		/*
-		 * Only reset the batches of zones that were actually
-		 * considered in the fairness pass, we don't want to
-		 * trash fairness information for zones that are not
-		 * actually part of this zonelist's round-robin cycle.
-		 */
-		if (!zone_local(preferred_zone, zone))
-			continue;
-		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-	}
-}
-
 static void wake_all_kswapds(unsigned int order,
 			     struct zonelist *zonelist,
 			     enum zone_type high_zoneidx,
@@ -2447,7 +2470,7 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2456,20 +2479,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
@@ -2616,14 +2639,6 @@ rebalance:
 		goto got_pg;
 
 	/*
-	 * It can become very expensive to allocate transparent hugepages at
-	 * fault, so use asynchronous memory compaction for THP unless it is
-	 * khugepaged trying to collapse.
-	 */
-	if (!(gfp_mask & __GFP_NO_KSWAPD) || (current->flags & PF_KTHREAD))
-		migration_mode = MIGRATE_SYNC_LIGHT;
-
-	/*
 	 * If compaction is deferred for high-order allocations, it is because
 	 * sync compaction recently failed. In this is the case and the caller
 	 * requested a movable allocation that does not heavily disrupt the
@@ -2633,6 +2648,15 @@ rebalance:
 						(gfp_mask & __GFP_NO_KSWAPD))
 		goto nopage;
 
+	/*
+	 * It can become very expensive to allocate transparent hugepages at
+	 * fault, so use asynchronous memory compaction for THP unless it is
+	 * khugepaged trying to collapse.
+	 */
+	if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
+						(current->flags & PF_KTHREAD))
+		migration_mode = MIGRATE_SYNC_LIGHT;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2766,29 +2790,12 @@ retry_cpuset:
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
-retry:
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
 			preferred_zone, classzone_idx, migratetype);
 	if (unlikely(!page)) {
 		/*
-		 * The first pass makes sure allocations are spread
-		 * fairly within the local node.  However, the local
-		 * node might have free pages left after the fairness
-		 * batches are exhausted, and remote zones haven't
-		 * even been considered yet.  Try once more without
-		 * fairness, and include remote zones now, before
-		 * entering the slowpath and waking kswapd: prefer
-		 * spilling to a remote zone over swapping locally.
-		 */
-		if (alloc_flags & ALLOC_FAIR) {
-			reset_alloc_batches(zonelist, high_zoneidx,
-					    preferred_zone);
-			alloc_flags &= ~ALLOC_FAIR;
-			goto retry;
-		}
-		/*
 		 * Runtime PM, block IO and its error handling path
 		 * can deadlock because I/O on the device might not
 		 * complete.
@@ -2962,7 +2969,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
  * Note this is not alloc_pages_exact_node() which allocates on a specific node,
  * but is not exact.
  */
-void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 {
 	unsigned order = get_order(size);
 	struct page *p = alloc_pages_node(nid, gfp_mask, order);
@@ -2970,7 +2977,6 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 		return NULL;
 	return make_alloc_exact((unsigned long)page_address(p), order, size);
 }
-EXPORT_SYMBOL(alloc_pages_exact_nid);
 
 /**
  * free_pages_exact - release memory allocated via alloc_pages_exact()
@@ -3052,7 +3058,7 @@ static inline void show_node(struct zone *zone)
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
-	val->sharedram = 0;
+	val->sharedram = global_page_state(NR_SHMEM);
 	val->freeram = global_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages;
@@ -3072,6 +3078,7 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
 		managed_pages += pgdat->node_zones[zone_type].managed_pages;
 	val->totalram = managed_pages;
+	val->sharedram = node_page_state(nid, NR_SHMEM);
 	val->freeram = node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
 	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages;
@@ -3253,12 +3260,12 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
 			K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
-			zone->pages_scanned,
+			K(zone_page_state(zone, NR_PAGES_SCANNED)),
 			(!zone_reclaimable(zone) ? "yes" : "no")
 			);
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
-			printk(" %lu", zone->lowmem_reserve[i]);
+			printk(" %ld", zone->lowmem_reserve[i]);
 		printk("\n");
 	}
 
@@ -5579,7 +5586,7 @@ static void calculate_totalreserve_pages(void)
 	for_each_online_pgdat(pgdat) {
 		for (i = 0; i < MAX_NR_ZONES; i++) {
 			struct zone *zone = pgdat->node_zones + i;
-			unsigned long max = 0;
+			long max = 0;
 
 			/* Find valid and maximum lowmem_reserve in the zone */
 			for (j = i; j < MAX_NR_ZONES; j++) {
@@ -6062,11 +6069,13 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 }
 
 /**
- * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
+ * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
  * @page: The page within the block of interest
- * @start_bitidx: The first bit of interest to retrieve
- * @end_bitidx: The last bit of interest
- * returns pageblock_bits flags
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest to retrieve
+ * @mask: mask of bits that the caller is interested in
+ *
+ * Return: pageblock_bits flags
  */
 unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
 					unsigned long end_bitidx,
@@ -6091,9 +6100,10 @@ unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
 /**
  * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
- * @start_bitidx: The first bit of interest
- * @end_bitidx: The last bit of interest
  * @flags: The flags to set
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest
+ * @mask: mask of bits that the caller is interested in
  */
 void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
 					unsigned long pfn,