1 files changed, 291 insertions, 201 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 77e4d3c5c57b..76c9688b6a0a 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>
@@ -83,6 +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.
@@ -290,28 +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;
 }
 
@@ -338,7 +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;
@@ -1013,7 +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
@@ -1170,6 +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);
@@ -1410,14 +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) {
@@ -1443,19 +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();
@@ -1477,83 +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 */
@@ -1792,7 +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)
 {
@@ -1836,7 +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);
@@ -2217,7 +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;
@@ -2289,8 +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;
 
@@ -2315,7 +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;
 
@@ -2329,19 +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,
@@ -2478,10 +2507,6 @@ void drain_all_pages(struct zone *zone)
 	if (WARN_ON_ONCE(!mm_percpu_wq))
 		return;
 
-	/* Workqueues cannot recurse */
-	if (current->flags & PF_WQ_WORKER)
-		return;
-
 	/*
 	 * Do not drain if one is already in progress unless it's specific to
 	 * a zone. Such callers are primarily CMA and memory hotplug and need
@@ -2590,24 +2615,25 @@ void mark_free_pages(struct zone *zone)
 }
 #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);
 
 	/*
@@ -2620,38 +2646,73 @@ 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;
+	int batch_count = 0;
 
+	/* 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);
+
+		/*
+		 * Guard against excessive IRQ disabled times when we get
+		 * a large list of pages to free.
+		 */
+		if (++batch_count == SWAP_CLUSTER_MAX) {
+			local_irq_restore(flags);
+			batch_count = 0;
+			local_irq_save(flags);
+		}
+	}
+	local_irq_restore(flags);
 }
 
 /*
@@ -2669,15 +2730,6 @@ 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);
@@ -2743,6 +2795,10 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 #ifdef CONFIG_NUMA
 	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;
 
@@ -2758,7 +2814,7 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 
 /* 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;
@@ -2767,16 +2823,12 @@ 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));
@@ -2791,14 +2843,13 @@ 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);
@@ -3006,9 +3057,6 @@ 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;
@@ -3020,6 +3068,9 @@ 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;
 }
@@ -3235,20 +3286,14 @@ 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();
@@ -3868,8 +3913,6 @@ __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;
 
@@ -4001,14 +4044,6 @@ 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;
@@ -4223,9 +4258,6 @@ 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;
@@ -4262,7 +4294,7 @@ 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);
 	}
@@ -4320,7 +4352,7 @@ 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);
 	}
@@ -6126,6 +6158,7 @@ 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;
@@ -6135,7 +6168,6 @@ 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 */
@@ -6157,6 +6189,9 @@ 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
@@ -6169,8 +6204,10 @@ 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)
@@ -6197,16 +6234,51 @@ 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++) {
+			if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages)))
+				continue;
+			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
@@ -6630,6 +6702,7 @@ 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)
@@ -6793,6 +6866,7 @@ 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)
@@ -7305,18 +7379,17 @@ 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
@@ -7353,10 +7426,10 @@ 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
@@ -7364,8 +7437,14 @@ 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);
@@ -7377,6 +7456,9 @@ 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
@@ -7450,7 +7532,7 @@ 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)
@@ -7546,6 +7628,7 @@ 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);
@@ -7582,11 +7665,18 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/*
 	 * In case of -EBUSY, we'd like to know which page causes problem.
-	 * So, just fall through. We will check it in test_pages_isolated().
+	 * So, just fall through. test_pages_isolated() has a tracepoint
+	 * which will report the busy page.
+	 *
+	 * It is possible that busy pages could become available before
+	 * the call to test_pages_isolated, and the range will actually be
+	 * allocated.  So, if we fall through be sure to clear ret so that
+	 * -EBUSY is not accidentally used or returned to caller.
 	 */
 	ret = __alloc_contig_migrate_range(&cc, start, end);
 	if (ret && ret != -EBUSY)
 		goto done;
+	ret =0;
 
 	/*
 	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES