1 files changed, 122 insertions, 68 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef19f22b2b7d..446bb36ee59d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
-#include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
@@ -126,6 +125,24 @@ unsigned long dirty_balance_reserve __read_mostly;
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
+/*
+ * A cached value of the page's pageblock's migratetype, used when the page is
+ * put on a pcplist. Used to avoid the pageblock migratetype lookup when
+ * freeing from pcplists in most cases, at the cost of possibly becoming stale.
+ * Also the migratetype set in the page does not necessarily match the pcplist
+ * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any
+ * other index - this ensures that it will be put on the correct CMA freelist.
+ */
+static inline int get_pcppage_migratetype(struct page *page)
+{
+	return page->index;
+}
+
+static inline void set_pcppage_migratetype(struct page *page, int migratetype)
+{
+	page->index = migratetype;
+}
+
 #ifdef CONFIG_PM_SLEEP
 /*
  * The following functions are used by the suspend/hibernate code to temporarily
@@ -207,6 +224,9 @@ static char * const zone_names[MAX_NR_ZONES] = {
 	 "HighMem",
 #endif
 	 "Movable",
+#ifdef CONFIG_ZONE_DEVICE
+	 "Device",
+#endif
 };
 
 int min_free_kbytes = 1024;
@@ -789,7 +809,11 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			page = list_entry(list->prev, struct page, lru);
 			/* must delete as __free_one_page list manipulates */
 			list_del(&page->lru);
-			mt = get_freepage_migratetype(page);
+
+			mt = get_pcppage_migratetype(page);
+			/* MIGRATE_ISOLATE page should not go to pcplists */
+			VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+			/* Pageblock could have been isolated meanwhile */
 			if (unlikely(has_isolate_pageblock(zone)))
 				mt = get_pageblock_migratetype(page);
 
@@ -953,7 +977,6 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	local_irq_save(flags);
 	__count_vm_events(PGFREE, 1 << order);
-	set_freepage_migratetype(page, migratetype);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
 	local_irq_restore(flags);
 }
@@ -981,21 +1004,21 @@ static void __init __free_pages_boot_core(struct page *page,
 
 #if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
 	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-/* Only safe to use early in boot when initialisation is single-threaded */
+
 static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
+	static DEFINE_SPINLOCK(early_pfn_lock);
 	int nid;
 
-	/* The system will behave unpredictably otherwise */
-	BUG_ON(system_state != SYSTEM_BOOTING);
-
+	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
-	if (nid >= 0)
-		return nid;
-	/* just returns 0 */
-	return 0;
+	if (nid < 0)
+		nid = 0;
+	spin_unlock(&early_pfn_lock);
+
+	return nid;
 }
 #endif
 
@@ -1060,7 +1083,15 @@ static void __init deferred_free_range(struct page *page,
 		__free_pages_boot_core(page, pfn, 0);
 }
 
-static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+/* Completion tracking for deferred_init_memmap() threads */
+static atomic_t pgdat_init_n_undone __initdata;
+static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
+
+static inline void __init pgdat_init_report_one_done(void)
+{
+	if (atomic_dec_and_test(&pgdat_init_n_undone))
+		complete(&pgdat_init_all_done_comp);
+}
 
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
@@ -1077,7 +1108,7 @@ static int __init deferred_init_memmap(void *data)
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (first_init_pfn == ULONG_MAX) {
-		up_read(&pgdat_init_rwsem);
+		pgdat_init_report_one_done();
 		return 0;
 	}
 
@@ -1177,7 +1208,8 @@ free_range:
 
 	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
 					jiffies_to_msecs(jiffies - start));
-	up_read(&pgdat_init_rwsem);
+
+	pgdat_init_report_one_done();
 	return 0;
 }
 
@@ -1185,14 +1217,17 @@ void __init page_alloc_init_late(void)
 {
 	int nid;
 
+	/* There will be num_node_state(N_MEMORY) threads */
+	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
 	for_each_node_state(nid, N_MEMORY) {
-		down_read(&pgdat_init_rwsem);
 		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
 	}
 
 	/* Block until all are initialised */
-	down_write(&pgdat_init_rwsem);
-	up_write(&pgdat_init_rwsem);
+	wait_for_completion(&pgdat_init_all_done_comp);
+
+	/* Reinit limits that are based on free pages after the kernel is up */
+	files_maxfiles_init();
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -1285,6 +1320,10 @@ static inline int check_new_page(struct page *page)
 		bad_reason = "non-NULL mapping";
 	if (unlikely(atomic_read(&page->_count) != 0))
 		bad_reason = "nonzero _count";
+	if (unlikely(page->flags & __PG_HWPOISON)) {
+		bad_reason = "HWPoisoned (hardware-corrupted)";
+		bad_flags = __PG_HWPOISON;
+	}
 	if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
@@ -1328,12 +1367,15 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 	set_page_owner(page, order, gfp_flags);
 
 	/*
-	 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to
+	 * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
 	 * allocate the page. The expectation is that the caller is taking
 	 * steps that will free more memory. The caller should avoid the page
 	 * being used for !PFMEMALLOC purposes.
 	 */
-	page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+	if (alloc_flags & ALLOC_NO_WATERMARKS)
+		set_page_pfmemalloc(page);
+	else
+		clear_page_pfmemalloc(page);
 
 	return 0;
 }
@@ -1362,7 +1404,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		rmv_page_order(page);
 		area->nr_free--;
 		expand(zone, page, order, current_order, area, migratetype);
-		set_freepage_migratetype(page, migratetype);
+		set_pcppage_migratetype(page, migratetype);
 		return page;
 	}
 
@@ -1439,7 +1481,6 @@ int move_freepages(struct zone *zone,
 		order = page_order(page);
 		list_move(&page->lru,
 			  &zone->free_area[order].free_list[migratetype]);
-		set_freepage_migratetype(page, migratetype);
 		page += 1 << order;
 		pages_moved += 1 << order;
 	}
@@ -1609,14 +1650,13 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 		expand(zone, page, order, current_order, area,
 					start_migratetype);
 		/*
-		 * The freepage_migratetype may differ from pageblock's
+		 * The pcppage_migratetype may differ from pageblock's
 		 * migratetype depending on the decisions in
-		 * try_to_steal_freepages(). This is OK as long as it
-		 * does not differ for MIGRATE_CMA pageblocks. For CMA
-		 * we need to make sure unallocated pages flushed from
-		 * pcp lists are returned to the correct freelist.
+		 * find_suitable_fallback(). This is OK as long as it does not
+		 * differ for MIGRATE_CMA pageblocks. Those can be used as
+		 * fallback only via special __rmqueue_cma_fallback() function
 		 */
-		set_freepage_migratetype(page, start_migratetype);
+		set_pcppage_migratetype(page, start_migratetype);
 
 		trace_mm_page_alloc_extfrag(page, order, current_order,
 			start_migratetype, fallback_mt);
@@ -1692,7 +1732,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		else
 			list_add_tail(&page->lru, list);
 		list = &page->lru;
-		if (is_migrate_cma(get_freepage_migratetype(page)))
+		if (is_migrate_cma(get_pcppage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
 					      -(1 << order));
 	}
@@ -1889,7 +1929,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
-	set_freepage_migratetype(page, migratetype);
+	set_pcppage_migratetype(page, migratetype);
 	local_irq_save(flags);
 	__count_vm_event(PGFREE);
 
@@ -2094,7 +2134,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 		if (!page)
 			goto failed;
 		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_freepage_migratetype(page));
+					  get_pcppage_migratetype(page));
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
@@ -2119,13 +2159,13 @@ failed:
 static struct {
 	struct fault_attr attr;
 
-	u32 ignore_gfp_highmem;
-	u32 ignore_gfp_wait;
+	bool ignore_gfp_highmem;
+	bool ignore_gfp_wait;
 	u32 min_order;
 } fail_page_alloc = {
 	.attr = FAULT_ATTR_INITIALIZER,
-	.ignore_gfp_wait = 1,
-	.ignore_gfp_highmem = 1,
+	.ignore_gfp_wait = true,
+	.ignore_gfp_highmem = true,
 	.min_order = 1,
 };
 
@@ -2675,6 +2715,12 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	const struct alloc_context *ac, unsigned long *did_some_progress)
 {
+	struct oom_control oc = {
+		.zonelist = ac->zonelist,
+		.nodemask = ac->nodemask,
+		.gfp_mask = gfp_mask,
+		.order = order,
+	};
 	struct page *page;
 
 	*did_some_progress = 0;
@@ -2726,8 +2772,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)
-			|| WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
+	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
 		*did_some_progress = 1;
 out:
 	mutex_unlock(&oom_lock);
@@ -3330,7 +3375,7 @@ refill:
 		atomic_add(size - 1, &page->_count);
 
 		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page->pfmemalloc;
+		nc->pfmemalloc = page_is_pfmemalloc(page);
 		nc->pagecnt_bias = size;
 		nc->offset = size;
 	}
@@ -3383,24 +3428,24 @@ EXPORT_SYMBOL(__free_page_frag);
 struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order)
 {
 	struct page *page;
-	struct mem_cgroup *memcg = NULL;
 
-	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
-		return NULL;
 	page = alloc_pages(gfp_mask, order);
-	memcg_kmem_commit_charge(page, memcg, order);
+	if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
+		__free_pages(page, order);
+		page = NULL;
+	}
 	return page;
 }
 
 struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	struct page *page;
-	struct mem_cgroup *memcg = NULL;
 
-	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
-		return NULL;
 	page = alloc_pages_node(nid, gfp_mask, order);
-	memcg_kmem_commit_charge(page, memcg, order);
+	if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
+		__free_pages(page, order);
+		page = NULL;
+	}
 	return page;
 }
 
@@ -3410,7 +3455,7 @@ struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
  */
 void __free_kmem_pages(struct page *page, unsigned int order)
 {
-	memcg_kmem_uncharge_pages(page, order);
+	memcg_kmem_uncharge(page, order);
 	__free_pages(page, order);
 }
 
@@ -3469,8 +3514,6 @@ EXPORT_SYMBOL(alloc_pages_exact);
  *
  * Like alloc_pages_exact(), but try to allocate on node nid first before falling
  * back.
- * Note this is not alloc_pages_exact_node() which allocates on a specific node,
- * but is not exact.
  */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 {
@@ -4857,8 +4900,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
 
 int __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long zone_start_pfn,
-					unsigned long size,
-					enum memmap_context context)
+					unsigned long size)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int ret;
@@ -5045,6 +5087,10 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 {
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node from cpu_up(), the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	/* Get the start and end of the zone */
 	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
 	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
@@ -5108,6 +5154,10 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node from cpu_up(), the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
 	zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
 
@@ -5277,8 +5327,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
  *
  * NOTE: pgdat should get zeroed by caller.
  */
-static void __paginginit free_area_init_core(struct pglist_data *pgdat,
-		unsigned long node_start_pfn, unsigned long node_end_pfn)
+static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
@@ -5363,8 +5412,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
 		set_pageblock_order();
 		setup_usemap(pgdat, zone, zone_start_pfn, size);
-		ret = init_currently_empty_zone(zone, zone_start_pfn,
-						size, MEMMAP_EARLY);
+		ret = init_currently_empty_zone(zone, zone_start_pfn, size);
 		BUG_ON(ret);
 		memmap_init(size, nid, j, zone_start_pfn);
 		zone_start_pfn += size;
@@ -5373,6 +5421,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
 static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 {
+	unsigned long __maybe_unused offset = 0;
+
 	/* Skip empty nodes */
 	if (!pgdat->node_spanned_pages)
 		return;
@@ -5389,6 +5439,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		 * for the buddy allocator to function correctly.
 		 */
 		start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
+		offset = pgdat->node_start_pfn - start;
 		end = pgdat_end_pfn(pgdat);
 		end = ALIGN(end, MAX_ORDER_NR_PAGES);
 		size =  (end - start) * sizeof(struct page);
@@ -5396,7 +5447,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		if (!map)
 			map = memblock_virt_alloc_node_nopanic(size,
 							       pgdat->node_id);
-		pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
+		pgdat->node_mem_map = map + offset;
 	}
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 	/*
@@ -5404,9 +5455,9 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 	 */
 	if (pgdat == NODE_DATA(0)) {
 		mem_map = NODE_DATA(0)->node_mem_map;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM)
 		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
-			mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
+			mem_map -= offset;
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 	}
 #endif
@@ -5429,7 +5480,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 	pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
-		(u64)start_pfn << PAGE_SHIFT, ((u64)end_pfn << PAGE_SHIFT) - 1);
+		(u64)start_pfn << PAGE_SHIFT,
+		end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
@@ -5441,7 +5493,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
-	free_area_init_core(pgdat, start_pfn, end_pfn);
+	free_area_init_core(pgdat);
 }
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -5452,11 +5504,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
  */
 void __init setup_nr_node_ids(void)
 {
-	unsigned int node;
-	unsigned int highest = 0;
+	unsigned int highest;
 
-	for_each_node_mask(node, node_possible_map)
-		highest = node;
+	highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES);
 	nr_node_ids = highest + 1;
 }
 #endif
@@ -5619,13 +5669,17 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 		 */
 		required_movablecore =
 			roundup(required_movablecore, MAX_ORDER_NR_PAGES);
+		required_movablecore = min(totalpages, required_movablecore);
 		corepages = totalpages - required_movablecore;
 
 		required_kernelcore = max(required_kernelcore, corepages);
 	}
 
-	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
-	if (!required_kernelcore)
+	/*
+	 * If kernelcore was not specified or kernelcore size is larger
+	 * than totalpages, there is no ZONE_MOVABLE.
+	 */
+	if (!required_kernelcore || required_kernelcore >= totalpages)
 		goto out;
 
 	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
@@ -5977,7 +6031,7 @@ void __init mem_init_print_info(const char *str)
  * set_dma_reserve - set the specified number of pages reserved in the first zone
  * @new_dma_reserve: The number of pages to mark reserved
  *
- * The per-cpu batchsize and zone watermarks are determined by present_pages.
+ * The per-cpu batchsize and zone watermarks are determined by managed_pages.
  * In the DMA zone, a significant percentage may be consumed by kernel image
  * and other unfreeable allocations which can skew the watermarks badly. This
  * function may optionally be used to account for unfreeable pages in the
@@ -6030,7 +6084,7 @@ void __init page_alloc_init(void)
 }
 
 /*
- * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
+ * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio
  *	or min_free_kbytes changes.
  */
 static void calculate_totalreserve_pages(void)
@@ -6074,7 +6128,7 @@ static void calculate_totalreserve_pages(void)
 
 /*
  * setup_per_zone_lowmem_reserve - called whenever
- *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
+ *	sysctl_lowmem_reserve_ratio changes.  Ensures that each zone
  *	has a correct pages reserved value, so an adequate number of
  *	pages are left in the zone after a successful __alloc_pages().
  */