1 files changed, 238 insertions, 332 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef44ad736ca1..616a2c956b4b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -53,8 +53,6 @@
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
 #include <trace/events/kmem.h>
-#include <linux/ftrace_event.h>
-#include <linux/memcontrol.h>
 #include <linux/prefetch.h>
 #include <linux/mm_inline.h>
 #include <linux/migrate.h>
@@ -85,6 +83,7 @@ EXPORT_PER_CPU_SYMBOL(numa_node);
  */
 DEFINE_PER_CPU(int, _numa_mem_);		/* Kernel "local memory" node */
 EXPORT_PER_CPU_SYMBOL(_numa_mem_);
+int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 /*
@@ -468,29 +467,6 @@ static inline void rmv_page_order(struct page *page)
 }
 
 /*
- * Locate the struct page for both the matching buddy in our
- * pair (buddy1) and the combined O(n+1) page they form (page).
- *
- * 1) Any buddy B1 will have an order O twin B2 which satisfies
- * the following equation:
- *     B2 = B1 ^ (1 << O)
- * For example, if the starting buddy (buddy2) is #8 its order
- * 1 buddy is #10:
- *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
- *
- * 2) Any buddy B will have an order O+1 parent P which
- * satisfies the following equation:
- *     P = B & ~(1 << O)
- *
- * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
- */
-static inline unsigned long
-__find_buddy_index(unsigned long page_idx, unsigned int order)
-{
-	return page_idx ^ (1 << order);
-}
-
-/*
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
  * (a) the buddy is not in a hole &&
@@ -570,6 +546,7 @@ static inline void __free_one_page(struct page *page,
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
+	int max_order = MAX_ORDER;
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 
@@ -578,13 +555,24 @@ static inline void __free_one_page(struct page *page,
 			return;
 
 	VM_BUG_ON(migratetype == -1);
+	if (is_migrate_isolate(migratetype)) {
+		/*
+		 * We restrict max order of merging to prevent merge
+		 * between freepages on isolate pageblock and normal
+		 * pageblock. Without this, pageblock isolation
+		 * could cause incorrect freepage accounting.
+		 */
+		max_order = min(MAX_ORDER, pageblock_order + 1);
+	} else {
+		__mod_zone_freepage_state(zone, 1 << order, migratetype);
+	}
 
-	page_idx = pfn & ((1 << MAX_ORDER) - 1);
+	page_idx = pfn & ((1 << max_order) - 1);
 
 	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
-	while (order < MAX_ORDER-1) {
+	while (order < max_order - 1) {
 		buddy_idx = __find_buddy_index(page_idx, order);
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
@@ -595,9 +583,11 @@ static inline void __free_one_page(struct page *page,
 		 */
 		if (page_is_guard(buddy)) {
 			clear_page_guard_flag(buddy);
-			set_page_private(page, 0);
-			__mod_zone_freepage_state(zone, 1 << order,
-						  migratetype);
+			set_page_private(buddy, 0);
+			if (!is_migrate_isolate(migratetype)) {
+				__mod_zone_freepage_state(zone, 1 << order,
+							  migratetype);
+			}
 		} else {
 			list_del(&buddy->lru);
 			zone->free_area[order].nr_free--;
@@ -680,9 +670,12 @@ 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;
@@ -713,14 +706,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			/* must delete as __free_one_page list manipulates */
 			list_del(&page->lru);
 			mt = get_freepage_migratetype(page);
+			if (unlikely(has_isolate_pageblock(zone)))
+				mt = get_pageblock_migratetype(page);
+
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
 			__free_one_page(page, page_to_pfn(page), zone, 0, mt);
 			trace_mm_page_pcpu_drain(page, 0, mt);
-			if (likely(!is_migrate_isolate_page(page))) {
-				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
-				if (is_migrate_cma(mt))
-					__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
-			}
 		} while (--to_free && --batch_free && !list_empty(list));
 	}
 	spin_unlock(&zone->lock);
@@ -731,12 +722,17 @@ 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);
 
+	if (unlikely(has_isolate_pageblock(zone) ||
+		is_migrate_isolate(migratetype))) {
+		migratetype = get_pfnblock_migratetype(page, pfn);
+	}
 	__free_one_page(page, pfn, zone, order, migratetype);
-	if (unlikely(!is_migrate_isolate(migratetype)))
-		__mod_zone_freepage_state(zone, 1 << order, migratetype);
 	spin_unlock(&zone->lock);
 }
 
@@ -1008,7 +1004,7 @@ int move_freepages(struct zone *zone,
 	 * Remove at a later date when no bug reports exist related to
 	 * grouping pages by mobility
 	 */
-	BUG_ON(page_zone(start_page) != page_zone(end_page));
+	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
 #endif
 
 	for (page = start_page; page <= end_page;) {
@@ -1257,15 +1253,11 @@ 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;
@@ -1483,7 +1475,7 @@ void split_page(struct page *page, unsigned int order)
 }
 EXPORT_SYMBOL_GPL(split_page);
 
-static int __isolate_free_page(struct page *page, unsigned int order)
+int __isolate_free_page(struct page *page, unsigned int order)
 {
 	unsigned long watermark;
 	struct zone *zone;
@@ -1610,6 +1602,9 @@ again:
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
+	    !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
+		set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1712,7 +1707,6 @@ 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 +1721,7 @@ 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 +1916,18 @@ 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]));
+		clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
+	} while (zone++ != preferred_zone);
+}
+
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -1939,8 +1945,12 @@ 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 +1974,11 @@ zonelist_scan:
 		 */
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
+				break;
+			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
+				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 +2084,7 @@ 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 +2093,37 @@ 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;
 }
 
 /*
@@ -2201,13 +2236,21 @@ __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;
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.
@@ -2240,7 +2283,7 @@ __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;
 }
 
@@ -2251,58 +2294,72 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
-	bool *contended_compaction, bool *deferred_compaction,
-	unsigned long *did_some_progress)
+	int *contended_compaction, bool *deferred_compaction)
 {
-	if (!order)
-		return NULL;
+	struct zone *last_compact_zone = NULL;
+	unsigned long compact_result;
+	struct page *page;
 
-	if (compaction_deferred(preferred_zone, order)) {
-		*deferred_compaction = true;
+	if (!order)
 		return NULL;
-	}
 
 	current->flags |= PF_MEMALLOC;
-	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
+	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
-						contended_compaction);
+						contended_compaction,
+						&last_compact_zone);
 	current->flags &= ~PF_MEMALLOC;
 
-	if (*did_some_progress != COMPACT_SKIPPED) {
-		struct page *page;
+	switch (compact_result) {
+	case COMPACT_DEFERRED:
+		*deferred_compaction = true;
+		/* fall-through */
+	case COMPACT_SKIPPED:
+		return NULL;
+	default:
+		break;
+	}
 
-		/* Page migration frees to the PCP lists but we want merging */
-		drain_pages(get_cpu());
-		put_cpu();
+	/*
+	 * At least in one zone compaction wasn't deferred or skipped, so let's
+	 * count a compaction stall
+	 */
+	count_vm_event(COMPACTSTALL);
 
-		page = get_page_from_freelist(gfp_mask, nodemask,
-				order, zonelist, high_zoneidx,
-				alloc_flags & ~ALLOC_NO_WATERMARKS,
-				preferred_zone, classzone_idx, migratetype);
-		if (page) {
-			preferred_zone->compact_blockskip_flush = false;
-			compaction_defer_reset(preferred_zone, order, true);
-			count_vm_event(COMPACTSUCCESS);
-			return page;
-		}
+	/* Page migration frees to the PCP lists but we want merging */
+	drain_pages(get_cpu());
+	put_cpu();
 
-		/*
-		 * It's bad if compaction run occurs and fails.
-		 * The most likely reason is that pages exist,
-		 * but not enough to satisfy watermarks.
-		 */
-		count_vm_event(COMPACTFAIL);
+	page = get_page_from_freelist(gfp_mask, nodemask,
+			order, zonelist, high_zoneidx,
+			alloc_flags & ~ALLOC_NO_WATERMARKS,
+			preferred_zone, classzone_idx, migratetype);
 
-		/*
-		 * As async compaction considers a subset of pageblocks, only
-		 * defer if the failure was a sync compaction failure.
-		 */
-		if (mode != MIGRATE_ASYNC)
-			defer_compaction(preferred_zone, order);
+	if (page) {
+		struct zone *zone = page_zone(page);
 
-		cond_resched();
+		zone->compact_blockskip_flush = false;
+		compaction_defer_reset(zone, order, true);
+		count_vm_event(COMPACTSUCCESS);
+		return page;
 	}
 
+	/*
+	 * last_compact_zone is where try_to_compact_pages thought allocation
+	 * should succeed, so it did not defer compaction. But here we know
+	 * that it didn't succeed, so we do the defer.
+	 */
+	if (last_compact_zone && mode != MIGRATE_ASYNC)
+		defer_compaction(last_compact_zone, order);
+
+	/*
+	 * It's bad if compaction run occurs and fails. The most likely reason
+	 * is that pages exist, but not enough to satisfy watermarks.
+	 */
+	count_vm_event(COMPACTFAIL);
+
+	cond_resched();
+
 	return NULL;
 }
 #else
@@ -2310,9 +2367,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int classzone_idx, int migratetype,
-	enum migrate_mode mode, bool *contended_compaction,
-	bool *deferred_compaction, unsigned long *did_some_progress)
+	int classzone_idx, int migratetype, enum migrate_mode mode,
+	int *contended_compaction, bool *deferred_compaction)
 {
 	return NULL;
 }
@@ -2409,37 +2465,17 @@ __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,
-			     struct zone *preferred_zone)
+			     struct zone *preferred_zone,
+			     nodemask_t *nodemask)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						high_zoneidx, nodemask)
 		wakeup_kswapd(zone, order, zone_idx(preferred_zone));
 }
 
@@ -2486,7 +2522,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 #ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
 	return alloc_flags;
@@ -2510,7 +2546,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	bool deferred_compaction = false;
-	bool contended_compaction = false;
+	int contended_compaction = COMPACT_CONTENDED_NONE;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2537,7 +2573,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 restart:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
-		wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone);
+		wake_all_kswapds(order, zonelist, high_zoneidx,
+				preferred_zone, nodemask);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2610,29 +2647,50 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 	if (page)
 		goto got_pg;
 
+	/* Checks for THP-specific high-order allocations */
+	if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+		/*
+		 * If compaction is deferred for high-order allocations, it is
+		 * because sync compaction recently failed. If this is the case
+		 * and the caller requested a THP allocation, we do not want
+		 * to heavily disrupt the system, so we fail the allocation
+		 * instead of entering direct reclaim.
+		 */
+		if (deferred_compaction)
+			goto nopage;
+
+		/*
+		 * In all zones where compaction was attempted (and not
+		 * deferred or skipped), lock contention has been detected.
+		 * For THP allocation we do not want to disrupt the others
+		 * so we fallback to base pages instead.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_LOCK)
+			goto nopage;
+
+		/*
+		 * If compaction was aborted due to need_resched(), we do not
+		 * want to further increase allocation latency, unless it is
+		 * khugepaged trying to collapse.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_SCHED
+			&& !(current->flags & PF_KTHREAD))
+			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_NO_KSWAPD) || (current->flags & PF_KTHREAD))
+	if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
+						(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
-	 * system then fail the allocation instead of entering direct reclaim.
-	 */
-	if ((deferred_compaction || contended_compaction) &&
-						(gfp_mask & __GFP_NO_KSWAPD))
-		goto nopage;
-
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2702,8 +2760,7 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 		if (page)
 			goto got_pg;
 	}
@@ -2729,7 +2786,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct zone *preferred_zone;
 	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
-	int migratetype = allocflags_to_migratetype(gfp_mask);
+	int migratetype = gfpflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	int classzone_idx;
@@ -2751,6 +2808,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
+	if (IS_ENABLED(CONFIG_CMA) && migratetype == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
@@ -2762,33 +2822,12 @@ retry_cpuset:
 		goto out;
 	classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
-#ifdef CONFIG_CMA
-	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 +3001,7 @@ 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 +3009,6 @@ 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 +3090,7 @@ 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 +3110,7 @@ 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 +3292,12 @@ 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");
 	}
 
@@ -3572,68 +3611,30 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 	zonelist->_zonerefs[pos].zone_idx = 0;
 }
 
+#if defined(CONFIG_64BIT)
+/*
+ * Devices that require DMA32/DMA are relatively rare and do not justify a
+ * penalty to every machine in case the specialised case applies. Default
+ * to Node-ordering on 64-bit NUMA machines
+ */
+static int default_zonelist_order(void)
+{
+	return ZONELIST_ORDER_NODE;
+}
+#else
+/*
+ * On 32-bit, the Normal zone needs to be preserved for allocations accessible
+ * by the kernel. If processes running on node 0 deplete the low memory zone
+ * then reclaim will occur more frequency increasing stalls and potentially
+ * be easier to OOM if a large percentage of the zone is under writeback or
+ * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set.
+ * Hence, default to zone ordering on 32-bit.
+ */
 static int default_zonelist_order(void)
 {
-	int nid, zone_type;
-	unsigned long low_kmem_size, total_size;
-	struct zone *z;
-	int average_size;
-	/*
-	 * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
-	 * If they are really small and used heavily, the system can fall
-	 * into OOM very easily.
-	 * This function detect ZONE_DMA/DMA32 size and configures zone order.
-	 */
-	/* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
-	low_kmem_size = 0;
-	total_size = 0;
-	for_each_online_node(nid) {
-		for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
-			z = &NODE_DATA(nid)->node_zones[zone_type];
-			if (populated_zone(z)) {
-				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->managed_pages;
-				total_size += z->managed_pages;
-			} else if (zone_type == ZONE_NORMAL) {
-				/*
-				 * If any node has only lowmem, then node order
-				 * is preferred to allow kernel allocations
-				 * locally; otherwise, they can easily infringe
-				 * on other nodes when there is an abundance of
-				 * lowmem available to allocate from.
-				 */
-				return ZONELIST_ORDER_NODE;
-			}
-		}
-	}
-	if (!low_kmem_size ||  /* there are no DMA area. */
-	    low_kmem_size > total_size/2) /* DMA/DMA32 is big. */
-		return ZONELIST_ORDER_NODE;
-	/*
-	 * look into each node's config.
-	 * If there is a node whose DMA/DMA32 memory is very big area on
-	 * local memory, NODE_ORDER may be suitable.
-	 */
-	average_size = total_size /
-				(nodes_weight(node_states[N_MEMORY]) + 1);
-	for_each_online_node(nid) {
-		low_kmem_size = 0;
-		total_size = 0;
-		for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
-			z = &NODE_DATA(nid)->node_zones[zone_type];
-			if (populated_zone(z)) {
-				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->present_pages;
-				total_size += z->present_pages;
-			}
-		}
-		if (low_kmem_size &&
-		    total_size > average_size && /* ignore small node */
-		    low_kmem_size > total_size * 70/100)
-			return ZONELIST_ORDER_NODE;
-	}
 	return ZONELIST_ORDER_ZONE;
 }
+#endif /* CONFIG_64BIT */
 
 static void set_zonelist_order(void)
 {
@@ -4969,6 +4970,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			(u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
@@ -5579,7 +5582,7 @@ 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++) {
@@ -5694,9 +5697,8 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				      high_wmark_pages(zone) -
-				      low_wmark_pages(zone) -
-				      zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
@@ -6271,8 +6273,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		if (list_empty(&cc->migratepages)) {
 			cc->nr_migratepages = 0;
-			pfn = isolate_migratepages_range(cc->zone, cc,
-							 pfn, end, true);
+			pfn = isolate_migratepages_range(cc, pfn, end);
 			if (!pfn) {
 				ret = -EINTR;
 				break;
@@ -6398,13 +6399,12 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/* Make sure the range is really isolated. */
 	if (test_pages_isolated(outer_start, end, false)) {
-		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
-		       outer_start, end);
+		pr_info("%s: [%lx, %lx) PFNs busy\n",
+			__func__, outer_start, end);
 		ret = -EBUSY;
 		goto done;
 	}
 
-
 	/* Grab isolated pages from freelists. */
 	outer_end = isolate_freepages_range(&cc, outer_start, end);
 	if (!outer_end) {
@@ -6548,97 +6548,3 @@ bool is_free_buddy_page(struct page *page)
 	return order < MAX_ORDER;
 }
 #endif
-
-static const struct trace_print_flags pageflag_names[] = {
-	{1UL << PG_locked,		"locked"	},
-	{1UL << PG_error,		"error"		},
-	{1UL << PG_referenced,		"referenced"	},
-	{1UL << PG_uptodate,		"uptodate"	},
-	{1UL << PG_dirty,		"dirty"		},
-	{1UL << PG_lru,			"lru"		},
-	{1UL << PG_active,		"active"	},
-	{1UL << PG_slab,		"slab"		},
-	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
-	{1UL << PG_arch_1,		"arch_1"	},
-	{1UL << PG_reserved,		"reserved"	},
-	{1UL << PG_private,		"private"	},
-	{1UL << PG_private_2,		"private_2"	},
-	{1UL << PG_writeback,		"writeback"	},
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
-	{1UL << PG_head,		"head"		},
-	{1UL << PG_tail,		"tail"		},
-#else
-	{1UL << PG_compound,		"compound"	},
-#endif
-	{1UL << PG_swapcache,		"swapcache"	},
-	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
-	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_swapbacked,		"swapbacked"	},
-	{1UL << PG_unevictable,		"unevictable"	},
-#ifdef CONFIG_MMU
-	{1UL << PG_mlocked,		"mlocked"	},
-#endif
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-	{1UL << PG_uncached,		"uncached"	},
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
-	{1UL << PG_hwpoison,		"hwpoison"	},
-#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	{1UL << PG_compound_lock,	"compound_lock"	},
-#endif
-};
-
-static void dump_page_flags(unsigned long flags)
-{
-	const char *delim = "";
-	unsigned long mask;
-	int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
-
-	printk(KERN_ALERT "page flags: %#lx(", flags);
-
-	/* remove zone id */
-	flags &= (1UL << NR_PAGEFLAGS) - 1;
-
-	for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) {
-
-		mask = pageflag_names[i].mask;
-		if ((flags & mask) != mask)
-			continue;
-
-		flags &= ~mask;
-		printk("%s%s", delim, pageflag_names[i].name);
-		delim = "|";
-	}
-
-	/* check for left over flags */
-	if (flags)
-		printk("%s%#lx", delim, flags);
-
-	printk(")\n");
-}
-
-void dump_page_badflags(struct page *page, const char *reason,
-		unsigned long badflags)
-{
-	printk(KERN_ALERT
-	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
-		page, atomic_read(&page->_count), page_mapcount(page),
-		page->mapping, page->index);
-	dump_page_flags(page->flags);
-	if (reason)
-		pr_alert("page dumped because: %s\n", reason);
-	if (page->flags & badflags) {
-		pr_alert("bad because of flags:\n");
-		dump_page_flags(page->flags & badflags);
-	}
-	mem_cgroup_print_bad_page(page);
-}
-
-void dump_page(struct page *page, const char *reason)
-{
-	dump_page_badflags(page, reason, 0);
-}
-EXPORT_SYMBOL(dump_page);