Merge tag 'v4.15-rc1' into next-seccomp

Linux 4.15-rc1

1 files changed, 526 insertions, 485 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6d30e914afb6..d4096f4a5c1f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -24,7 +24,6 @@
 #include <linux/memblock.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
-#include <linux/kmemcheck.h>
 #include <linux/kasan.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
@@ -66,6 +65,8 @@
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
 #include <linux/ftrace.h>
+#include <linux/lockdep.h>
+#include <linux/nmi.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -81,6 +82,8 @@ DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
 #endif
 
+DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
+
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 /*
  * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
@@ -288,28 +291,37 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+
+/*
+ * Determine how many pages need to be initialized durig early boot
+ * (non-deferred initialization).
+ * The value of first_deferred_pfn will be set later, once non-deferred pages
+ * are initialized, but for now set it ULONG_MAX.
+ */
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
-	unsigned long max_initialise;
-	unsigned long reserved_lowmem;
+	phys_addr_t start_addr, end_addr;
+	unsigned long max_pgcnt;
+	unsigned long reserved;
 
 	/*
 	 * Initialise at least 2G of a node but also take into account that
 	 * two large system hashes that can take up 1GB for 0.25TB/node.
 	 */
-	max_initialise = max(2UL << (30 - PAGE_SHIFT),
-		(pgdat->node_spanned_pages >> 8));
+	max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
+			(pgdat->node_spanned_pages >> 8));
 
 	/*
 	 * Compensate the all the memblock reservations (e.g. crash kernel)
 	 * from the initial estimation to make sure we will initialize enough
 	 * memory to boot.
 	 */
-	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
-			pgdat->node_start_pfn + max_initialise);
-	max_initialise += reserved_lowmem;
+	start_addr = PFN_PHYS(pgdat->node_start_pfn);
+	end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
+	reserved = memblock_reserved_memory_within(start_addr, end_addr);
+	max_pgcnt += PHYS_PFN(reserved);
 
-	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
+	pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -336,7 +348,7 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
 	(*nr_initialised)++;
-	if ((*nr_initialised > pgdat->static_init_size) &&
+	if ((*nr_initialised > pgdat->static_init_pgcnt) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -1011,7 +1023,6 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
 	trace_mm_page_free(page, order);
-	kmemcheck_free_shadow(page, order);
 
 	/*
 	 * Check tail pages before head page information is cleared to
@@ -1168,6 +1179,7 @@ static void free_one_page(struct zone *zone,
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
 				unsigned long zone, int nid)
 {
+	mm_zero_struct_page(page);
 	set_page_links(page, zone, nid, pfn);
 	init_page_count(page);
 	page_mapcount_reset(page);
@@ -1188,7 +1200,7 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn)
 {
 	pg_data_t *pgdat;
 	int nid, zid;
@@ -1408,14 +1420,17 @@ void clear_zone_contiguous(struct zone *zone)
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void __init deferred_free_range(struct page *page,
-					unsigned long pfn, int nr_pages)
+static void __init deferred_free_range(unsigned long pfn,
+				       unsigned long nr_pages)
 {
-	int i;
+	struct page *page;
+	unsigned long i;
 
-	if (!page)
+	if (!nr_pages)
 		return;
 
+	page = pfn_to_page(pfn);
+
 	/* Free a large naturally-aligned chunk if possible */
 	if (nr_pages == pageblock_nr_pages &&
 	    (pfn & (pageblock_nr_pages - 1)) == 0) {
@@ -1441,19 +1456,109 @@ static inline void __init pgdat_init_report_one_done(void)
 		complete(&pgdat_init_all_done_comp);
 }
 
+/*
+ * Helper for deferred_init_range, free the given range, reset the counters, and
+ * return number of pages freed.
+ */
+static inline unsigned long __init __def_free(unsigned long *nr_free,
+					      unsigned long *free_base_pfn,
+					      struct page **page)
+{
+	unsigned long nr = *nr_free;
+
+	deferred_free_range(*free_base_pfn, nr);
+	*free_base_pfn = 0;
+	*nr_free = 0;
+	*page = NULL;
+
+	return nr;
+}
+
+static unsigned long __init deferred_init_range(int nid, int zid,
+						unsigned long start_pfn,
+						unsigned long end_pfn)
+{
+	struct mminit_pfnnid_cache nid_init_state = { };
+	unsigned long nr_pgmask = pageblock_nr_pages - 1;
+	unsigned long free_base_pfn = 0;
+	unsigned long nr_pages = 0;
+	unsigned long nr_free = 0;
+	struct page *page = NULL;
+	unsigned long pfn;
+
+	/*
+	 * First we check if pfn is valid on architectures where it is possible
+	 * to have holes within pageblock_nr_pages. On systems where it is not
+	 * possible, this function is optimized out.
+	 *
+	 * Then, we check if a current large page is valid by only checking the
+	 * validity of the head pfn.
+	 *
+	 * meminit_pfn_in_nid is checked on systems where pfns can interleave
+	 * within a node: a pfn is between start and end of a node, but does not
+	 * belong to this memory node.
+	 *
+	 * Finally, we minimize pfn page lookups and scheduler checks by
+	 * performing it only once every pageblock_nr_pages.
+	 *
+	 * We do it in two loops: first we initialize struct page, than free to
+	 * buddy allocator, becuse while we are freeing pages we can access
+	 * pages that are ahead (computing buddy page in __free_one_page()).
+	 */
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		if (!pfn_valid_within(pfn))
+			continue;
+		if ((pfn & nr_pgmask) || pfn_valid(pfn)) {
+			if (meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
+				if (page && (pfn & nr_pgmask))
+					page++;
+				else
+					page = pfn_to_page(pfn);
+				__init_single_page(page, pfn, zid, nid);
+				cond_resched();
+			}
+		}
+	}
+
+	page = NULL;
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		if (!pfn_valid_within(pfn)) {
+			nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
+		} else if (!(pfn & nr_pgmask) && !pfn_valid(pfn)) {
+			nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
+		} else if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
+			nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
+		} else if (page && (pfn & nr_pgmask)) {
+			page++;
+			nr_free++;
+		} else {
+			nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
+			page = pfn_to_page(pfn);
+			free_base_pfn = pfn;
+			nr_free = 1;
+			cond_resched();
+		}
+	}
+	/* Free the last block of pages to allocator */
+	nr_pages += __def_free(&nr_free, &free_base_pfn, &page);
+
+	return nr_pages;
+}
+
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
 {
 	pg_data_t *pgdat = data;
 	int nid = pgdat->node_id;
-	struct mminit_pfnnid_cache nid_init_state = { };
 	unsigned long start = jiffies;
 	unsigned long nr_pages = 0;
-	unsigned long walk_start, walk_end;
-	int i, zid;
+	unsigned long spfn, epfn;
+	phys_addr_t spa, epa;
+	int zid;
 	struct zone *zone;
 	unsigned long first_init_pfn = pgdat->first_deferred_pfn;
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+	u64 i;
 
 	if (first_init_pfn == ULONG_MAX) {
 		pgdat_init_report_one_done();
@@ -1475,83 +1580,12 @@ static int __init deferred_init_memmap(void *data)
 		if (first_init_pfn < zone_end_pfn(zone))
 			break;
 	}
+	first_init_pfn = max(zone->zone_start_pfn, first_init_pfn);
 
-	for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) {
-		unsigned long pfn, end_pfn;
-		struct page *page = NULL;
-		struct page *free_base_page = NULL;
-		unsigned long free_base_pfn = 0;
-		int nr_to_free = 0;
-
-		end_pfn = min(walk_end, zone_end_pfn(zone));
-		pfn = first_init_pfn;
-		if (pfn < walk_start)
-			pfn = walk_start;
-		if (pfn < zone->zone_start_pfn)
-			pfn = zone->zone_start_pfn;
-
-		for (; pfn < end_pfn; pfn++) {
-			if (!pfn_valid_within(pfn))
-				goto free_range;
-
-			/*
-			 * Ensure pfn_valid is checked every
-			 * pageblock_nr_pages for memory holes
-			 */
-			if ((pfn & (pageblock_nr_pages - 1)) == 0) {
-				if (!pfn_valid(pfn)) {
-					page = NULL;
-					goto free_range;
-				}
-			}
-
-			if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
-				page = NULL;
-				goto free_range;
-			}
-
-			/* Minimise pfn page lookups and scheduler checks */
-			if (page && (pfn & (pageblock_nr_pages - 1)) != 0) {
-				page++;
-			} else {
-				nr_pages += nr_to_free;
-				deferred_free_range(free_base_page,
-						free_base_pfn, nr_to_free);
-				free_base_page = NULL;
-				free_base_pfn = nr_to_free = 0;
-
-				page = pfn_to_page(pfn);
-				cond_resched();
-			}
-
-			if (page->flags) {
-				VM_BUG_ON(page_zone(page) != zone);
-				goto free_range;
-			}
-
-			__init_single_page(page, pfn, zid, nid);
-			if (!free_base_page) {
-				free_base_page = page;
-				free_base_pfn = pfn;
-				nr_to_free = 0;
-			}
-			nr_to_free++;
-
-			/* Where possible, batch up pages for a single free */
-			continue;
-free_range:
-			/* Free the current block of pages to allocator */
-			nr_pages += nr_to_free;
-			deferred_free_range(free_base_page, free_base_pfn,
-								nr_to_free);
-			free_base_page = NULL;
-			free_base_pfn = nr_to_free = 0;
-		}
-		/* Free the last block of pages to allocator */
-		nr_pages += nr_to_free;
-		deferred_free_range(free_base_page, free_base_pfn, nr_to_free);
-
-		first_init_pfn = max(end_pfn, first_init_pfn);
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
+		spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
+		epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+		nr_pages += deferred_init_range(nid, zid, spfn, epfn);
 	}
 
 	/* Sanity check that the next zone really is unpopulated */
@@ -1584,6 +1618,10 @@ void __init page_alloc_init_late(void)
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+	/* Discard memblock private memory */
+	memblock_discard();
+#endif
 
 	for_each_populated_zone(zone)
 		set_zone_contiguous(zone);
@@ -1786,7 +1824,7 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags
  * Go through the free lists for the given migratetype and remove
  * the smallest available page from the freelists
  */
-static inline
+static __always_inline
 struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 						int migratetype)
 {
@@ -1830,7 +1868,7 @@ static int fallbacks[MIGRATE_TYPES][4] = {
 };
 
 #ifdef CONFIG_CMA
-static struct page *__rmqueue_cma_fallback(struct zone *zone,
+static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone,
 					unsigned int order)
 {
 	return __rmqueue_smallest(zone, order, MIGRATE_CMA);
@@ -2211,7 +2249,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
  * deviation from the rest of this file, to make the for loop
  * condition simpler.
  */
-static inline bool
+static __always_inline bool
 __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 {
 	struct free_area *area;
@@ -2283,8 +2321,8 @@ do_steal:
  * Do the hard work of removing an element from the buddy allocator.
  * Call me with the zone->lock already held.
  */
-static struct page *__rmqueue(struct zone *zone, unsigned int order,
-				int migratetype)
+static __always_inline struct page *
+__rmqueue(struct zone *zone, unsigned int order, int migratetype)
 {
 	struct page *page;
 
@@ -2309,7 +2347,7 @@ retry:
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
-			int migratetype, bool cold)
+			int migratetype)
 {
 	int i, alloced = 0;
 
@@ -2323,19 +2361,16 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			continue;
 
 		/*
-		 * Split buddy pages returned by expand() are received here
-		 * in physical page order. The page is added to the callers and
-		 * list and the list head then moves forward. From the callers
-		 * perspective, the linked list is ordered by page number in
-		 * some conditions. This is useful for IO devices that can
-		 * merge IO requests if the physical pages are ordered
-		 * properly.
+		 * Split buddy pages returned by expand() are received here in
+		 * physical page order. The page is added to the tail of
+		 * caller's list. From the callers perspective, the linked list
+		 * is ordered by page number under some conditions. This is
+		 * useful for IO devices that can forward direction from the
+		 * head, thus also in the physical page order. This is useful
+		 * for IO devices that can merge IO requests if the physical
+		 * pages are ordered properly.
 		 */
-		if (likely(!cold))
-			list_add(&page->lru, list);
-		else
-			list_add_tail(&page->lru, list);
-		list = &page->lru;
+		list_add_tail(&page->lru, list);
 		alloced++;
 		if (is_migrate_cma(get_pcppage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
@@ -2531,9 +2566,14 @@ void drain_all_pages(struct zone *zone)
 
 #ifdef CONFIG_HIBERNATION
 
+/*
+ * Touch the watchdog for every WD_PAGE_COUNT pages.
+ */
+#define WD_PAGE_COUNT	(128*1024)
+
 void mark_free_pages(struct zone *zone)
 {
-	unsigned long pfn, max_zone_pfn;
+	unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
 	unsigned long flags;
 	unsigned int order, t;
 	struct page *page;
@@ -2548,6 +2588,11 @@ void mark_free_pages(struct zone *zone)
 		if (pfn_valid(pfn)) {
 			page = pfn_to_page(pfn);
 
+			if (!--page_count) {
+				touch_nmi_watchdog();
+				page_count = WD_PAGE_COUNT;
+			}
+
 			if (page_zone(page) != zone)
 				continue;
 
@@ -2561,32 +2606,38 @@ void mark_free_pages(struct zone *zone)
 			unsigned long i;
 
 			pfn = page_to_pfn(page);
-			for (i = 0; i < (1UL << order); i++)
+			for (i = 0; i < (1UL << order); i++) {
+				if (!--page_count) {
+					touch_nmi_watchdog();
+					page_count = WD_PAGE_COUNT;
+				}
 				swsusp_set_page_free(pfn_to_page(pfn + i));
+			}
 		}
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif /* CONFIG_PM */
 
-/*
- * Free a 0-order page
- * cold == true ? free a cold page : free a hot page
- */
-void free_hot_cold_page(struct page *page, bool cold)
+static bool free_unref_page_prepare(struct page *page, unsigned long pfn)
 {
-	struct zone *zone = page_zone(page);
-	struct per_cpu_pages *pcp;
-	unsigned long flags;
-	unsigned long pfn = page_to_pfn(page);
 	int migratetype;
 
 	if (!free_pcp_prepare(page))
-		return;
+		return false;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_pcppage_migratetype(page, migratetype);
-	local_irq_save(flags);
+	return true;
+}
+
+static void free_unref_page_commit(struct page *page, unsigned long pfn)
+{
+	struct zone *zone = page_zone(page);
+	struct per_cpu_pages *pcp;
+	int migratetype;
+
+	migratetype = get_pcppage_migratetype(page);
 	__count_vm_event(PGFREE);
 
 	/*
@@ -2599,38 +2650,62 @@ void free_hot_cold_page(struct page *page, bool cold)
 	if (migratetype >= MIGRATE_PCPTYPES) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
 			free_one_page(zone, page, pfn, 0, migratetype);
-			goto out;
+			return;
 		}
 		migratetype = MIGRATE_MOVABLE;
 	}
 
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
-	if (!cold)
-		list_add(&page->lru, &pcp->lists[migratetype]);
-	else
-		list_add_tail(&page->lru, &pcp->lists[migratetype]);
+	list_add(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
 		unsigned long batch = READ_ONCE(pcp->batch);
 		free_pcppages_bulk(zone, batch, pcp);
 		pcp->count -= batch;
 	}
+}
 
-out:
+/*
+ * Free a 0-order page
+ */
+void free_unref_page(struct page *page)
+{
+	unsigned long flags;
+	unsigned long pfn = page_to_pfn(page);
+
+	if (!free_unref_page_prepare(page, pfn))
+		return;
+
+	local_irq_save(flags);
+	free_unref_page_commit(page, pfn);
 	local_irq_restore(flags);
 }
 
 /*
  * Free a list of 0-order pages
  */
-void free_hot_cold_page_list(struct list_head *list, bool cold)
+void free_unref_page_list(struct list_head *list)
 {
 	struct page *page, *next;
+	unsigned long flags, pfn;
 
+	/* Prepare pages for freeing */
 	list_for_each_entry_safe(page, next, list, lru) {
-		trace_mm_page_free_batched(page, cold);
-		free_hot_cold_page(page, cold);
+		pfn = page_to_pfn(page);
+		if (!free_unref_page_prepare(page, pfn))
+			list_del(&page->lru);
+		set_page_private(page, pfn);
 	}
+
+	local_irq_save(flags);
+	list_for_each_entry_safe(page, next, list, lru) {
+		unsigned long pfn = page_private(page);
+
+		set_page_private(page, 0);
+		trace_mm_page_free_batched(page);
+		free_unref_page_commit(page, pfn);
+	}
+	local_irq_restore(flags);
 }
 
 /*
@@ -2648,15 +2723,6 @@ void split_page(struct page *page, unsigned int order)
 	VM_BUG_ON_PAGE(PageCompound(page), page);
 	VM_BUG_ON_PAGE(!page_count(page), page);
 
-#ifdef CONFIG_KMEMCHECK
-	/*
-	 * Split shadow pages too, because free(page[0]) would
-	 * otherwise free the whole shadow.
-	 */
-	if (kmemcheck_page_is_tracked(page))
-		split_page(virt_to_page(page[0].shadow), order);
-#endif
-
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 	split_page_owner(page, order);
@@ -2720,24 +2786,28 @@ int __isolate_free_page(struct page *page, unsigned int order)
 static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 {
 #ifdef CONFIG_NUMA
-	enum zone_stat_item local_stat = NUMA_LOCAL;
+	enum numa_stat_item local_stat = NUMA_LOCAL;
+
+	/* skip numa counters update if numa stats is disabled */
+	if (!static_branch_likely(&vm_numa_stat_key))
+		return;
 
 	if (z->node != numa_node_id())
 		local_stat = NUMA_OTHER;
 
 	if (z->node == preferred_zone->node)
-		__inc_zone_state(z, NUMA_HIT);
+		__inc_numa_state(z, NUMA_HIT);
 	else {
-		__inc_zone_state(z, NUMA_MISS);
-		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
+		__inc_numa_state(z, NUMA_MISS);
+		__inc_numa_state(preferred_zone, NUMA_FOREIGN);
 	}
-	__inc_zone_state(z, local_stat);
+	__inc_numa_state(z, local_stat);
 #endif
 }
 
 /* Remove page from the per-cpu list, caller must protect the list */
 static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
-			bool cold, struct per_cpu_pages *pcp,
+			struct per_cpu_pages *pcp,
 			struct list_head *list)
 {
 	struct page *page;
@@ -2746,16 +2816,12 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
 		if (list_empty(list)) {
 			pcp->count += rmqueue_bulk(zone, 0,
 					pcp->batch, list,
-					migratetype, cold);
+					migratetype);
 			if (unlikely(list_empty(list)))
 				return NULL;
 		}
 
-		if (cold)
-			page = list_last_entry(list, struct page, lru);
-		else
-			page = list_first_entry(list, struct page, lru);
-
+		page = list_first_entry(list, struct page, lru);
 		list_del(&page->lru);
 		pcp->count--;
 	} while (check_new_pcp(page));
@@ -2770,14 +2836,13 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 {
 	struct per_cpu_pages *pcp;
 	struct list_head *list;
-	bool cold = ((gfp_flags & __GFP_COLD) != 0);
 	struct page *page;
 	unsigned long flags;
 
 	local_irq_save(flags);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	list = &pcp->lists[migratetype];
-	page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
+	page = __rmqueue_pcplist(zone,  migratetype, pcp, list);
 	if (page) {
 		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 		zone_statistics(preferred_zone, zone);
@@ -2930,7 +2995,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 {
 	long min = mark;
 	int o;
-	const bool alloc_harder = (alloc_flags & ALLOC_HARDER);
+	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
 	/* free_pages may go negative - that's OK */
 	free_pages -= (1 << order) - 1;
@@ -2943,10 +3008,21 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	 * the high-atomic reserves. This will over-estimate the size of the
 	 * atomic reserve but it avoids a search.
 	 */
-	if (likely(!alloc_harder))
+	if (likely(!alloc_harder)) {
 		free_pages -= z->nr_reserved_highatomic;
-	else
-		min -= min / 4;
+	} else {
+		/*
+		 * OOM victims can try even harder than normal ALLOC_HARDER
+		 * users on the grounds that it's definitely going to be in
+		 * the exit path shortly and free memory. Any allocation it
+		 * makes during the free path will be small and short-lived.
+		 */
+		if (alloc_flags & ALLOC_OOM)
+			min -= min / 2;
+		else
+			min -= min / 4;
+	}
+
 
 #ifdef CONFIG_CMA
 	/* If allocation can't use CMA areas don't use free CMA pages */
@@ -2974,9 +3050,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		if (!area->nr_free)
 			continue;
 
-		if (alloc_harder)
-			return true;
-
 		for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
 			if (!list_empty(&area->free_list[mt]))
 				return true;
@@ -2988,6 +3061,9 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			return true;
 		}
 #endif
+		if (alloc_harder &&
+			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+			return true;
 	}
 	return false;
 }
@@ -3184,7 +3260,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 	 * of allowed nodes.
 	 */
 	if (!(gfp_mask & __GFP_NOMEMALLOC))
-		if (test_thread_flag(TIF_MEMDIE) ||
+		if (tsk_is_oom_victim(current) ||
 		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
 			filter &= ~SHOW_MEM_FILTER_NODES;
 	if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
@@ -3203,20 +3279,14 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
 		return;
 
-	pr_warn("%s: ", current->comm);
-
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
-	pr_cont("%pV", &vaf);
+	pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl\n",
+			current->comm, &vaf, gfp_mask, &gfp_mask,
+			nodemask_pr_args(nodemask));
 	va_end(args);
 
-	pr_cont(", mode:%#x(%pGg), nodemask=", gfp_mask, &gfp_mask);
-	if (nodemask)
-		pr_cont("%*pbl\n", nodemask_pr_args(nodemask));
-	else
-		pr_cont("(null)\n");
-
 	cpuset_print_current_mems_allowed();
 
 	dump_stack();
@@ -3271,10 +3341,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/*
 	 * 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.
+	 * we're still under heavy pressure. But make sure that this reclaim
+	 * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY
+	 * allocation which will never fail due to oom_lock already held.
 	 */
-	page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order,
-					ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
+	page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) &
+				      ~__GFP_DIRECT_RECLAIM, order,
+				      ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
 	if (page)
 		goto out;
 
@@ -3490,6 +3563,47 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 }
 #endif /* CONFIG_COMPACTION */
 
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map __fs_reclaim_map =
+	STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
+
+static bool __need_fs_reclaim(gfp_t gfp_mask)
+{
+	gfp_mask = current_gfp_context(gfp_mask);
+
+	/* no reclaim without waiting on it */
+	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+		return false;
+
+	/* this guy won't enter reclaim */
+	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+		return false;
+
+	/* We're only interested __GFP_FS allocations for now */
+	if (!(gfp_mask & __GFP_FS))
+		return false;
+
+	if (gfp_mask & __GFP_NOLOCKDEP)
+		return false;
+
+	return true;
+}
+
+void fs_reclaim_acquire(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_acquire(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
+
+void fs_reclaim_release(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_release(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_release);
+#endif
+
 /* Perform direct synchronous page reclaim */
 static int
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -3504,7 +3618,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
 	noreclaim_flag = memalloc_noreclaim_save();
-	lockdep_set_current_reclaim_state(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
@@ -3512,7 +3626,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 								ac->nodemask);
 
 	current->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	cond_resched();
@@ -3603,21 +3717,46 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	return alloc_flags;
 }
 
-bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+static bool oom_reserves_allowed(struct task_struct *tsk)
 {
-	if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+	if (!tsk_is_oom_victim(tsk))
+		return false;
+
+	/*
+	 * !MMU doesn't have oom reaper so give access to memory reserves
+	 * only to the thread with TIF_MEMDIE set
+	 */
+	if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE))
 		return false;
 
+	return true;
+}
+
+/*
+ * Distinguish requests which really need access to full memory
+ * reserves from oom victims which can live with a portion of it
+ */
+static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask)
+{
+	if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+		return 0;
 	if (gfp_mask & __GFP_MEMALLOC)
-		return true;
+		return ALLOC_NO_WATERMARKS;
 	if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
-		return true;
-	if (!in_interrupt() &&
-			((current->flags & PF_MEMALLOC) ||
-			 unlikely(test_thread_flag(TIF_MEMDIE))))
-		return true;
+		return ALLOC_NO_WATERMARKS;
+	if (!in_interrupt()) {
+		if (current->flags & PF_MEMALLOC)
+			return ALLOC_NO_WATERMARKS;
+		else if (oom_reserves_allowed(current))
+			return ALLOC_OOM;
+	}
 
-	return false;
+	return 0;
+}
+
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+{
+	return !!__gfp_pfmemalloc_flags(gfp_mask);
 }
 
 /*
@@ -3767,9 +3906,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	enum compact_result compact_result;
 	int compaction_retries;
 	int no_progress_loops;
-	unsigned long alloc_start = jiffies;
-	unsigned int stall_timeout = 10 * HZ;
 	unsigned int cpuset_mems_cookie;
+	int reserve_flags;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3875,15 +4013,16 @@ retry:
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
 		wake_all_kswapds(order, ac);
 
-	if (gfp_pfmemalloc_allowed(gfp_mask))
-		alloc_flags = ALLOC_NO_WATERMARKS;
+	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
+	if (reserve_flags)
+		alloc_flags = reserve_flags;
 
 	/*
 	 * Reset the zonelist iterators if memory policies can be ignored.
 	 * These allocations are high priority and system rather than user
 	 * orientated.
 	 */
-	if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) {
+	if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
 		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->high_zoneidx, ac->nodemask);
@@ -3898,14 +4037,6 @@ retry:
 	if (!can_direct_reclaim)
 		goto nopage;
 
-	/* Make sure we know about allocations which stall for too long */
-	if (time_after(jiffies, alloc_start + stall_timeout)) {
-		warn_alloc(gfp_mask & ~__GFP_NOWARN, ac->nodemask,
-			"page allocation stalls for %ums, order:%u",
-			jiffies_to_msecs(jiffies-alloc_start), order);
-		stall_timeout += 10 * HZ;
-	}
-
 	/* Avoid recursion of direct reclaim */
 	if (current->flags & PF_MEMALLOC)
 		goto nopage;
@@ -3960,8 +4091,8 @@ retry:
 		goto got_pg;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE) &&
-	    (alloc_flags == ALLOC_NO_WATERMARKS ||
+	if (tsk_is_oom_victim(current) &&
+	    (alloc_flags == ALLOC_OOM ||
 	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
@@ -4041,7 +4172,8 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 			*alloc_flags |= ALLOC_CPUSET;
 	}
 
-	lockdep_trace_alloc(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
 
 	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
@@ -4079,10 +4211,11 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
 {
 	struct page *page;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
-	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
+	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = { };
 
 	gfp_mask &= gfp_allowed_mask;
+	alloc_mask = gfp_mask;
 	if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
 		return NULL;
 
@@ -4118,9 +4251,6 @@ out:
 		page = NULL;
 	}
 
-	if (kmemcheck_enabled && page)
-		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-
 	trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
 
 	return page;
@@ -4157,7 +4287,7 @@ void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
 		if (order == 0)
-			free_hot_cold_page(page, false);
+			free_unref_page(page);
 		else
 			__free_pages_ok(page, order);
 	}
@@ -4215,7 +4345,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 		unsigned int order = compound_order(page);
 
 		if (order == 0)
-			free_hot_cold_page(page, false);
+			free_unref_page(page);
 		else
 			__free_pages_ok(page, order);
 	}
@@ -4443,7 +4573,7 @@ long si_mem_available(void)
 	 * Estimate the amount of memory available for userspace allocations,
 	 * without causing swapping.
 	 */
-	available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
+	available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
 
 	/*
 	 * Not all the page cache can be freed, otherwise the system will
@@ -4458,8 +4588,9 @@ long si_mem_available(void)
 	 * Part of the reclaimable slab consists of items that are in use,
 	 * and cannot be freed. Cap this estimate at the low watermark.
 	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+	available += global_node_page_state(NR_SLAB_RECLAIMABLE) -
+		     min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
+			 wmark_low);
 
 	if (available < 0)
 		available = 0;
@@ -4471,7 +4602,7 @@ void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
 	val->sharedram = global_node_page_state(NR_SHMEM);
-	val->freeram = global_page_state(NR_FREE_PAGES);
+	val->freeram = global_zone_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages;
 	val->freehigh = nr_free_highpages();
@@ -4602,15 +4733,15 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state(NR_FILE_DIRTY),
 		global_node_page_state(NR_WRITEBACK),
 		global_node_page_state(NR_UNSTABLE_NFS),
-		global_page_state(NR_SLAB_RECLAIMABLE),
-		global_page_state(NR_SLAB_UNRECLAIMABLE),
+		global_node_page_state(NR_SLAB_RECLAIMABLE),
+		global_node_page_state(NR_SLAB_UNRECLAIMABLE),
 		global_node_page_state(NR_FILE_MAPPED),
 		global_node_page_state(NR_SHMEM),
-		global_page_state(NR_PAGETABLE),
-		global_page_state(NR_BOUNCE),
-		global_page_state(NR_FREE_PAGES),
+		global_zone_page_state(NR_PAGETABLE),
+		global_zone_page_state(NR_BOUNCE),
+		global_zone_page_state(NR_FREE_PAGES),
 		free_pcp,
-		global_page_state(NR_FREE_CMA_PAGES));
+		global_zone_page_state(NR_FREE_CMA_PAGES));
 
 	for_each_online_pgdat(pgdat) {
 		if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
@@ -4772,18 +4903,17 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
  *
  * Add all populated zones of a node to the zonelist.
  */
-static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
-				int nr_zones)
+static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
 {
 	struct zone *zone;
 	enum zone_type zone_type = MAX_NR_ZONES;
+	int nr_zones = 0;
 
 	do {
 		zone_type--;
 		zone = pgdat->node_zones + zone_type;
 		if (managed_zone(zone)) {
-			zoneref_set_zone(zone,
-				&zonelist->_zonerefs[nr_zones++]);
+			zoneref_set_zone(zone, &zonerefs[nr_zones++]);
 			check_highest_zone(zone_type);
 		}
 	} while (zone_type);
@@ -4791,52 +4921,18 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
 	return nr_zones;
 }
 
-
-/*
- *  zonelist_order:
- *  0 = automatic detection of better ordering.
- *  1 = order by ([node] distance, -zonetype)
- *  2 = order by (-zonetype, [node] distance)
- *
- *  If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create
- *  the same zonelist. So only NUMA can configure this param.
- */
-#define ZONELIST_ORDER_DEFAULT  0
-#define ZONELIST_ORDER_NODE     1
-#define ZONELIST_ORDER_ZONE     2
-
-/* zonelist order in the kernel.
- * set_zonelist_order() will set this to NODE or ZONE.
- */
-static int current_zonelist_order = ZONELIST_ORDER_DEFAULT;
-static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"};
-
-
 #ifdef CONFIG_NUMA
-/* The value user specified ....changed by config */
-static int user_zonelist_order = ZONELIST_ORDER_DEFAULT;
-/* string for sysctl */
-#define NUMA_ZONELIST_ORDER_LEN	16
-char numa_zonelist_order[16] = "default";
-
-/*
- * interface for configure zonelist ordering.
- * command line option "numa_zonelist_order"
- *	= "[dD]efault	- default, automatic configuration.
- *	= "[nN]ode 	- order by node locality, then by zone within node
- *	= "[zZ]one      - order by zone, then by locality within zone
- */
 
 static int __parse_numa_zonelist_order(char *s)
 {
-	if (*s == 'd' || *s == 'D') {
-		user_zonelist_order = ZONELIST_ORDER_DEFAULT;
-	} else if (*s == 'n' || *s == 'N') {
-		user_zonelist_order = ZONELIST_ORDER_NODE;
-	} else if (*s == 'z' || *s == 'Z') {
-		user_zonelist_order = ZONELIST_ORDER_ZONE;
-	} else {
-		pr_warn("Ignoring invalid numa_zonelist_order value:  %s\n", s);
+	/*
+	 * We used to support different zonlists modes but they turned
+	 * out to be just not useful. Let's keep the warning in place
+	 * if somebody still use the cmd line parameter so that we do
+	 * not fail it silently
+	 */
+	if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) {
+		pr_warn("Ignoring unsupported numa_zonelist_order value:  %s\n", s);
 		return -EINVAL;
 	}
 	return 0;
@@ -4844,19 +4940,15 @@ static int __parse_numa_zonelist_order(char *s)
 
 static __init int setup_numa_zonelist_order(char *s)
 {
-	int ret;
-
 	if (!s)
 		return 0;
 
-	ret = __parse_numa_zonelist_order(s);
-	if (ret == 0)
-		strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN);
-
-	return ret;
+	return __parse_numa_zonelist_order(s);
 }
 early_param("numa_zonelist_order", setup_numa_zonelist_order);
 
+char numa_zonelist_order[] = "Node";
+
 /*
  * sysctl handler for numa_zonelist_order
  */
@@ -4864,40 +4956,17 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
 		loff_t *ppos)
 {
-	char saved_string[NUMA_ZONELIST_ORDER_LEN];
+	char *str;
 	int ret;
-	static DEFINE_MUTEX(zl_order_mutex);
 
-	mutex_lock(&zl_order_mutex);
-	if (write) {
-		if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) {
-			ret = -EINVAL;
-			goto out;
-		}
-		strcpy(saved_string, (char *)table->data);
-	}
-	ret = proc_dostring(table, write, buffer, length, ppos);
-	if (ret)
-		goto out;
-	if (write) {
-		int oldval = user_zonelist_order;
+	if (!write)
+		return proc_dostring(table, write, buffer, length, ppos);
+	str = memdup_user_nul(buffer, 16);
+	if (IS_ERR(str))
+		return PTR_ERR(str);
 
-		ret = __parse_numa_zonelist_order((char *)table->data);
-		if (ret) {
-			/*
-			 * bogus value.  restore saved string
-			 */
-			strncpy((char *)table->data, saved_string,
-				NUMA_ZONELIST_ORDER_LEN);
-			user_zonelist_order = oldval;
-		} else if (oldval != user_zonelist_order) {
-			mutex_lock(&zonelists_mutex);
-			build_all_zonelists(NULL, NULL);
-			mutex_unlock(&zonelists_mutex);
-		}
-	}
-out:
-	mutex_unlock(&zl_order_mutex);
+	ret = __parse_numa_zonelist_order(str);
+	kfree(str);
 	return ret;
 }
 
@@ -4971,17 +5040,24 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
  * This results in maximum locality--normal zone overflows into local
  * DMA zone, if any--but risks exhausting DMA zone.
  */
-static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
+static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
+		unsigned nr_nodes)
 {
-	int j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int i;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
-		;
-	j = build_zonelists_node(NODE_DATA(node), zonelist, j);
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+
+	for (i = 0; i < nr_nodes; i++) {
+		int nr_zones;
+
+		pg_data_t *node = NODE_DATA(node_order[i]);
+
+		nr_zones = build_zonerefs_node(node, zonerefs);
+		zonerefs += nr_zones;
+	}
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 /*
@@ -4989,13 +5065,14 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
-	int j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int nr_zones;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_NOFALLBACK];
-	j = build_zonelists_node(pgdat, zonelist, 0);
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+	zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs;
+	nr_zones = build_zonerefs_node(pgdat, zonerefs);
+	zonerefs += nr_zones;
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 /*
@@ -5004,79 +5081,13 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
  * exhausted, but results in overflowing to remote node while memory
  * may still exist in local DMA zone.
  */
-static int node_order[MAX_NUMNODES];
-
-static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
-{
-	int pos, j, node;
-	int zone_type;		/* needs to be signed */
-	struct zone *z;
-	struct zonelist *zonelist;
-
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	pos = 0;
-	for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
-		for (j = 0; j < nr_nodes; j++) {
-			node = node_order[j];
-			z = &NODE_DATA(node)->node_zones[zone_type];
-			if (managed_zone(z)) {
-				zoneref_set_zone(z,
-					&zonelist->_zonerefs[pos++]);
-				check_highest_zone(zone_type);
-			}
-		}
-	}
-	zonelist->_zonerefs[pos].zone = NULL;
-	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)
-{
-	return ZONELIST_ORDER_ZONE;
-}
-#endif /* CONFIG_64BIT */
-
-static void set_zonelist_order(void)
-{
-	if (user_zonelist_order == ZONELIST_ORDER_DEFAULT)
-		current_zonelist_order = default_zonelist_order();
-	else
-		current_zonelist_order = user_zonelist_order;
-}
 
 static void build_zonelists(pg_data_t *pgdat)
 {
-	int i, node, load;
+	static int node_order[MAX_NUMNODES];
+	int node, load, nr_nodes = 0;
 	nodemask_t used_mask;
 	int local_node, prev_node;
-	struct zonelist *zonelist;
-	unsigned int order = current_zonelist_order;
-
-	/* initialize zonelists */
-	for (i = 0; i < MAX_ZONELISTS; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		zonelist->_zonerefs[0].zone = NULL;
-		zonelist->_zonerefs[0].zone_idx = 0;
-	}
 
 	/* NUMA-aware ordering of nodes */
 	local_node = pgdat->node_id;
@@ -5085,8 +5096,6 @@ static void build_zonelists(pg_data_t *pgdat)
 	nodes_clear(used_mask);
 
 	memset(node_order, 0, sizeof(node_order));
-	i = 0;
-
 	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
@@ -5097,19 +5106,12 @@ static void build_zonelists(pg_data_t *pgdat)
 		    node_distance(local_node, prev_node))
 			node_load[node] = load;
 
+		node_order[nr_nodes++] = node;
 		prev_node = node;
 		load--;
-		if (order == ZONELIST_ORDER_NODE)
-			build_zonelists_in_node_order(pgdat, node);
-		else
-			node_order[i++] = node;	/* remember order */
-	}
-
-	if (order == ZONELIST_ORDER_ZONE) {
-		/* calculate node order -- i.e., DMA last! */
-		build_zonelists_in_zone_order(pgdat, i);
 	}
 
+	build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
 	build_thisnode_zonelists(pgdat);
 }
 
@@ -5135,21 +5137,17 @@ static void setup_min_unmapped_ratio(void);
 static void setup_min_slab_ratio(void);
 #else	/* CONFIG_NUMA */
 
-static void set_zonelist_order(void)
-{
-	current_zonelist_order = ZONELIST_ORDER_ZONE;
-}
-
 static void build_zonelists(pg_data_t *pgdat)
 {
 	int node, local_node;
-	enum zone_type j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int nr_zones;
 
 	local_node = pgdat->node_id;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	j = build_zonelists_node(pgdat, zonelist, 0);
+	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+	nr_zones = build_zonerefs_node(pgdat, zonerefs);
+	zonerefs += nr_zones;
 
 	/*
 	 * Now we build the zonelist so that it contains the zones
@@ -5162,16 +5160,18 @@ static void build_zonelists(pg_data_t *pgdat)
 	for (node = local_node + 1; node < MAX_NUMNODES; node++) {
 		if (!node_online(node))
 			continue;
-		j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+		zonerefs += nr_zones;
 	}
 	for (node = 0; node < local_node; node++) {
 		if (!node_online(node))
 			continue;
-		j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+		zonerefs += nr_zones;
 	}
 
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 #endif	/* CONFIG_NUMA */
@@ -5194,50 +5194,32 @@ static void build_zonelists(pg_data_t *pgdat)
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
 static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
-static void setup_zone_pageset(struct zone *zone);
-
-/*
- * Global mutex to protect against size modification of zonelists
- * as well as to serialize pageset setup for the new populated zone.
- */
-DEFINE_MUTEX(zonelists_mutex);
 
-/* return values int ....just for stop_machine() */
-static int __build_all_zonelists(void *data)
+static void __build_all_zonelists(void *data)
 {
 	int nid;
-	int cpu;
+	int __maybe_unused cpu;
 	pg_data_t *self = data;
+	static DEFINE_SPINLOCK(lock);
+
+	spin_lock(&lock);
 
 #ifdef CONFIG_NUMA
 	memset(node_load, 0, sizeof(node_load));
 #endif
 
+	/*
+	 * This node is hotadded and no memory is yet present.   So just
+	 * building zonelists is fine - no need to touch other nodes.
+	 */
 	if (self && !node_online(self->node_id)) {
 		build_zonelists(self);
-	}
-
-	for_each_online_node(nid) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-
-		build_zonelists(pgdat);
-	}
+	} else {
+		for_each_online_node(nid) {
+			pg_data_t *pgdat = NODE_DATA(nid);
 
-	/*
-	 * Initialize the boot_pagesets that are going to be used
-	 * for bootstrapping processors. The real pagesets for
-	 * each zone will be allocated later when the per cpu
-	 * allocator is available.
-	 *
-	 * boot_pagesets are used also for bootstrapping offline
-	 * cpus if the system is already booted because the pagesets
-	 * are needed to initialize allocators on a specific cpu too.
-	 * F.e. the percpu allocator needs the page allocator which
-	 * needs the percpu allocator in order to allocate its pagesets
-	 * (a chicken-egg dilemma).
-	 */
-	for_each_possible_cpu(cpu) {
-		setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+			build_zonelists(pgdat);
+		}
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 		/*
@@ -5248,45 +5230,53 @@ static int __build_all_zonelists(void *data)
 		 * secondary cpus' numa_mem as they come on-line.  During
 		 * node/memory hotplug, we'll fixup all on-line cpus.
 		 */
-		if (cpu_online(cpu))
+		for_each_online_cpu(cpu)
 			set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
 #endif
 	}
 
-	return 0;
+	spin_unlock(&lock);
 }
 
 static noinline void __init
 build_all_zonelists_init(void)
 {
+	int cpu;
+
 	__build_all_zonelists(NULL);
+
+	/*
+	 * Initialize the boot_pagesets that are going to be used
+	 * for bootstrapping processors. The real pagesets for
+	 * each zone will be allocated later when the per cpu
+	 * allocator is available.
+	 *
+	 * boot_pagesets are used also for bootstrapping offline
+	 * cpus if the system is already booted because the pagesets
+	 * are needed to initialize allocators on a specific cpu too.
+	 * F.e. the percpu allocator needs the page allocator which
+	 * needs the percpu allocator in order to allocate its pagesets
+	 * (a chicken-egg dilemma).
+	 */
+	for_each_possible_cpu(cpu)
+		setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
 	mminit_verify_zonelist();
 	cpuset_init_current_mems_allowed();
 }
 
 /*
- * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
  *
- * __ref due to (1) call of __meminit annotated setup_zone_pageset
- * [we're only called with non-NULL zone through __meminit paths] and
- * (2) call of __init annotated helper build_all_zonelists_init
+ * __ref due to call of __init annotated helper build_all_zonelists_init
  * [protected by SYSTEM_BOOTING].
  */
-void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
+void __ref build_all_zonelists(pg_data_t *pgdat)
 {
-	set_zonelist_order();
-
 	if (system_state == SYSTEM_BOOTING) {
 		build_all_zonelists_init();
 	} else {
-#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_cpuslocked(__build_all_zonelists, pgdat, NULL);
+		__build_all_zonelists(pgdat);
 		/* cpuset refresh routine should be here */
 	}
 	vm_total_pages = nr_free_pagecache_pages();
@@ -5302,9 +5292,8 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 	else
 		page_group_by_mobility_disabled = 0;
 
-	pr_info("Built %i zonelists in %s order, mobility grouping %s.  Total pages: %ld\n",
+	pr_info("Built %i zonelists, mobility grouping %s.  Total pages: %ld\n",
 		nr_online_nodes,
-		zonelist_order_name[current_zonelist_order],
 		page_group_by_mobility_disabled ? "off" : "on",
 		vm_total_pages);
 #ifdef CONFIG_NUMA
@@ -5403,6 +5392,7 @@ not_early:
 
 			__init_single_page(page, pfn, zone, nid);
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			cond_resched();
 		} else {
 			__init_single_pfn(pfn, zone, nid);
 		}
@@ -5558,7 +5548,7 @@ static void __meminit zone_pageset_init(struct zone *zone, int cpu)
 	pageset_set_high_and_batch(zone, pcp);
 }
 
-static void __meminit setup_zone_pageset(struct zone *zone)
+void __meminit setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
 	zone->pageset = alloc_percpu(struct per_cpu_pageset);
@@ -6161,6 +6151,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	}
 }
 
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
 static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 {
 	unsigned long __maybe_unused start = 0;
@@ -6170,7 +6161,6 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 	if (!pgdat->node_spanned_pages)
 		return;
 
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
 	start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
 	offset = pgdat->node_start_pfn - start;
 	/* ia64 gets its own node_mem_map, before this, without bootmem */
@@ -6192,6 +6182,9 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 							       pgdat->node_id);
 		pgdat->node_mem_map = map + offset;
 	}
+	pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
+				__func__, pgdat->node_id, (unsigned long)pgdat,
+				(unsigned long)pgdat->node_mem_map);
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 	/*
 	 * With no DISCONTIG, the global mem_map is just set as node 0's
@@ -6204,8 +6197,10 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 	}
 #endif
-#endif /* CONFIG_FLAT_NODE_MEM_MAP */
 }
+#else
+static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { }
+#endif /* CONFIG_FLAT_NODE_MEM_MAP */
 
 void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		unsigned long node_start_pfn, unsigned long *zholes_size)
@@ -6232,16 +6227,49 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 				  zones_size, zholes_size);
 
 	alloc_node_mem_map(pgdat);
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
-	printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
-		nid, (unsigned long)pgdat,
-		(unsigned long)pgdat->node_mem_map);
-#endif
 
 	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+/*
+ * Only struct pages that are backed by physical memory are zeroed and
+ * initialized by going through __init_single_page(). But, there are some
+ * struct pages which are reserved in memblock allocator and their fields
+ * may be accessed (for example page_to_pfn() on some configuration accesses
+ * flags). We must explicitly zero those struct pages.
+ */
+void __paginginit zero_resv_unavail(void)
+{
+	phys_addr_t start, end;
+	unsigned long pfn;
+	u64 i, pgcnt;
+
+	/*
+	 * Loop through ranges that are reserved, but do not have reported
+	 * physical memory backing.
+	 */
+	pgcnt = 0;
+	for_each_resv_unavail_range(i, &start, &end) {
+		for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) {
+			mm_zero_struct_page(pfn_to_page(pfn));
+			pgcnt++;
+		}
+	}
+
+	/*
+	 * Struct pages that do not have backing memory. This could be because
+	 * firmware is using some of this memory, or for some other reasons.
+	 * Once memblock is changed so such behaviour is not allowed: i.e.
+	 * list of "reserved" memory must be a subset of list of "memory", then
+	 * this code can be removed.
+	 */
+	if (pgcnt)
+		pr_info("Reserved but unavailable: %lld pages", pgcnt);
+}
+#endif /* CONFIG_HAVE_MEMBLOCK */
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
 #if MAX_NUMNODES > 1
@@ -6665,6 +6693,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
+	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core)
@@ -6828,6 +6857,7 @@ void __init free_area_init(unsigned long *zones_size)
 {
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
+	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)
@@ -7012,9 +7042,11 @@ static void __setup_per_zone_wmarks(void)
  */
 void setup_per_zone_wmarks(void)
 {
-	mutex_lock(&zonelists_mutex);
+	static DEFINE_SPINLOCK(lock);
+
+	spin_lock(&lock);
 	__setup_per_zone_wmarks();
-	mutex_unlock(&zonelists_mutex);
+	spin_unlock(&lock);
 }
 
 /*
@@ -7338,18 +7370,17 @@ void *__init alloc_large_system_hash(const char *tablename,
 
 	log2qty = ilog2(numentries);
 
-	/*
-	 * memblock allocator returns zeroed memory already, so HASH_ZERO is
-	 * currently not used when HASH_EARLY is specified.
-	 */
 	gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC;
 	do {
 		size = bucketsize << log2qty;
-		if (flags & HASH_EARLY)
-			table = memblock_virt_alloc_nopanic(size, 0);
-		else if (hashdist)
+		if (flags & HASH_EARLY) {
+			if (flags & HASH_ZERO)
+				table = memblock_virt_alloc_nopanic(size, 0);
+			else
+				table = memblock_virt_alloc_raw(size, 0);
+		} else if (hashdist) {
 			table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
-		else {
+		} else {
 			/*
 			 * If bucketsize is not a power-of-two, we may free
 			 * some pages at the end of hash table which
@@ -7386,10 +7417,10 @@ void *__init alloc_large_system_hash(const char *tablename,
  * race condition. So you can't expect this function should be exact.
  */
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+			 int migratetype,
 			 bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn, iter, found;
-	int mt;
 
 	/*
 	 * For avoiding noise data, lru_add_drain_all() should be called
@@ -7397,8 +7428,14 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 	 */
 	if (zone_idx(zone) == ZONE_MOVABLE)
 		return false;
-	mt = get_pageblock_migratetype(page);
-	if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt))
+
+	/*
+	 * CMA allocations (alloc_contig_range) really need to mark isolate
+	 * CMA pageblocks even when they are not movable in fact so consider
+	 * them movable here.
+	 */
+	if (is_migrate_cma(migratetype) &&
+			is_migrate_cma(get_pageblock_migratetype(page)))
 		return false;
 
 	pfn = page_to_pfn(page);
@@ -7410,6 +7447,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 
 		page = pfn_to_page(check);
 
+		if (PageReserved(page))
+			return true;
+
 		/*
 		 * Hugepages are not in LRU lists, but they're movable.
 		 * We need not scan over tail pages bacause we don't
@@ -7483,7 +7523,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 	if (!zone_spans_pfn(zone, pfn))
 		return false;
 
-	return !has_unmovable_pages(zone, page, 0, true);
+	return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, true);
 }
 
 #if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
@@ -7579,6 +7619,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.zone = page_zone(pfn_to_page(start)),
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
+		.no_set_skip_hint = true,
 		.gfp_mask = current_gfp_context(gfp_mask),
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -7666,7 +7707,7 @@ 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_info("%s: [%lx, %lx) PFNs busy\n",
+		pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
 			__func__, outer_start, end);
 		ret = -EBUSY;
 		goto done;