1 files changed, 298 insertions, 62 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d03c946d5566..a9649f4b261e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -49,6 +49,7 @@
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/memory.h>
+#include <linux/compaction.h>
 #include <trace/events/kmem.h>
 #include <linux/ftrace_event.h>
 
@@ -56,6 +57,22 @@
 #include <asm/div64.h>
 #include "internal.h"
 
+#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
+DEFINE_PER_CPU(int, numa_node);
+EXPORT_PER_CPU_SYMBOL(numa_node);
+#endif
+
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+/*
+ * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
+ * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
+ * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
+ * defined in <linux/topology.h>.
+ */
+DEFINE_PER_CPU(int, _numa_mem_);		/* Kernel "local memory" node */
+EXPORT_PER_CPU_SYMBOL(_numa_mem_);
+#endif
+
 /*
  * Array of node states.
  */
@@ -475,6 +492,8 @@ static inline void __free_one_page(struct page *page,
 		int migratetype)
 {
 	unsigned long page_idx;
+	unsigned long combined_idx;
+	struct page *buddy;
 
 	if (unlikely(PageCompound(page)))
 		if (unlikely(destroy_compound_page(page, order)))
@@ -488,9 +507,6 @@ static inline void __free_one_page(struct page *page,
 	VM_BUG_ON(bad_range(zone, page));
 
 	while (order < MAX_ORDER-1) {
-		unsigned long combined_idx;
-		struct page *buddy;
-
 		buddy = __page_find_buddy(page, page_idx, order);
 		if (!page_is_buddy(page, buddy, order))
 			break;
@@ -505,8 +521,29 @@ static inline void __free_one_page(struct page *page,
 		order++;
 	}
 	set_page_order(page, order);
-	list_add(&page->lru,
-		&zone->free_area[order].free_list[migratetype]);
+
+	/*
+	 * If this is not the largest possible page, check if the buddy
+	 * of the next-highest order is free. If it is, it's possible
+	 * that pages are being freed that will coalesce soon. In case,
+	 * that is happening, add the free page to the tail of the list
+	 * so it's less likely to be used soon and more likely to be merged
+	 * as a higher order page
+	 */
+	if ((order < MAX_ORDER-1) && pfn_valid_within(page_to_pfn(buddy))) {
+		struct page *higher_page, *higher_buddy;
+		combined_idx = __find_combined_index(page_idx, order);
+		higher_page = page + combined_idx - page_idx;
+		higher_buddy = __page_find_buddy(higher_page, combined_idx, order + 1);
+		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+			list_add_tail(&page->lru,
+				&zone->free_area[order].free_list[migratetype]);
+			goto out;
+		}
+	}
+
+	list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
+out:
 	zone->free_area[order].nr_free++;
 }
 
@@ -599,20 +636,23 @@ static void free_one_page(struct zone *zone, struct page *page, int order,
 	spin_unlock(&zone->lock);
 }
 
-static void __free_pages_ok(struct page *page, unsigned int order)
+static bool free_pages_prepare(struct page *page, unsigned int order)
 {
-	unsigned long flags;
 	int i;
 	int bad = 0;
-	int wasMlocked = __TestClearPageMlocked(page);
 
 	trace_mm_page_free_direct(page, order);
 	kmemcheck_free_shadow(page, order);
 
-	for (i = 0 ; i < (1 << order) ; ++i)
-		bad += free_pages_check(page + i);
+	for (i = 0; i < (1 << order); i++) {
+		struct page *pg = page + i;
+
+		if (PageAnon(pg))
+			pg->mapping = NULL;
+		bad += free_pages_check(pg);
+	}
 	if (bad)
-		return;
+		return false;
 
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
@@ -622,6 +662,17 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	arch_free_page(page, order);
 	kernel_map_pages(page, 1 << order, 0);
 
+	return true;
+}
+
+static void __free_pages_ok(struct page *page, unsigned int order)
+{
+	unsigned long flags;
+	int wasMlocked = __TestClearPageMlocked(page);
+
+	if (!free_pages_prepare(page, order))
+		return;
+
 	local_irq_save(flags);
 	if (unlikely(wasMlocked))
 		free_page_mlock(page);
@@ -1107,21 +1158,9 @@ void free_hot_cold_page(struct page *page, int cold)
 	int migratetype;
 	int wasMlocked = __TestClearPageMlocked(page);
 
-	trace_mm_page_free_direct(page, 0);
-	kmemcheck_free_shadow(page, 0);
-
-	if (PageAnon(page))
-		page->mapping = NULL;
-	if (free_pages_check(page))
+	if (!free_pages_prepare(page, 0))
 		return;
 
-	if (!PageHighMem(page)) {
-		debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
-		debug_check_no_obj_freed(page_address(page), PAGE_SIZE);
-	}
-	arch_free_page(page, 0);
-	kernel_map_pages(page, 1, 0);
-
 	migratetype = get_pageblock_migratetype(page);
 	set_page_private(page, migratetype);
 	local_irq_save(flags);
@@ -1188,6 +1227,51 @@ void split_page(struct page *page, unsigned int order)
 }
 
 /*
+ * Similar to split_page except the page is already free. As this is only
+ * being used for migration, the migratetype of the block also changes.
+ * As this is called with interrupts disabled, the caller is responsible
+ * for calling arch_alloc_page() and kernel_map_page() after interrupts
+ * are enabled.
+ *
+ * Note: this is probably too low level an operation for use in drivers.
+ * Please consult with lkml before using this in your driver.
+ */
+int split_free_page(struct page *page)
+{
+	unsigned int order;
+	unsigned long watermark;
+	struct zone *zone;
+
+	BUG_ON(!PageBuddy(page));
+
+	zone = page_zone(page);
+	order = page_order(page);
+
+	/* Obey watermarks as if the page was being allocated */
+	watermark = low_wmark_pages(zone) + (1 << order);
+	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		return 0;
+
+	/* Remove page from free list */
+	list_del(&page->lru);
+	zone->free_area[order].nr_free--;
+	rmv_page_order(page);
+	__mod_zone_page_state(zone, NR_FREE_PAGES, -(1UL << order));
+
+	/* Split into individual pages */
+	set_page_refcounted(page);
+	split_page(page, order);
+
+	if (order >= pageblock_order - 1) {
+		struct page *endpage = page + (1 << order) - 1;
+		for (; page < endpage; page += pageblock_nr_pages)
+			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+	}
+
+	return 1 << order;
+}
+
+/*
  * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
  * we cheat by calling it from here, in the order > 0 path.  Saves a branch
  * or two.
@@ -1654,7 +1738,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct page *page;
 
 	/* Acquire the OOM killer lock for the zones in zonelist */
-	if (!try_set_zone_oom(zonelist, gfp_mask)) {
+	if (!try_set_zonelist_oom(zonelist, gfp_mask)) {
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -1675,6 +1759,9 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		/* The OOM killer will not help higher order allocs */
 		if (order > PAGE_ALLOC_COSTLY_ORDER)
 			goto out;
+		/* The OOM killer does not needlessly kill tasks for lowmem */
+		if (high_zoneidx < ZONE_NORMAL)
+			goto out;
 		/*
 		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
 		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -1693,6 +1780,62 @@ out:
 	return page;
 }
 
+#ifdef CONFIG_COMPACTION
+/* Try memory compaction for high-order allocations before reclaim */
+static struct page *
+__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+	int migratetype, unsigned long *did_some_progress)
+{
+	struct page *page;
+
+	if (!order || compaction_deferred(preferred_zone))
+		return NULL;
+
+	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
+								nodemask);
+	if (*did_some_progress != COMPACT_SKIPPED) {
+
+		/* Page migration frees to the PCP lists but we want merging */
+		drain_pages(get_cpu());
+		put_cpu();
+
+		page = get_page_from_freelist(gfp_mask, nodemask,
+				order, zonelist, high_zoneidx,
+				alloc_flags, preferred_zone,
+				migratetype);
+		if (page) {
+			preferred_zone->compact_considered = 0;
+			preferred_zone->compact_defer_shift = 0;
+			count_vm_event(COMPACTSUCCESS);
+			return page;
+		}
+
+		/*
+		 * It's bad if compaction run occurs and fails.
+		 * The most likely reason is that pages exist,
+		 * but not enough to satisfy watermarks.
+		 */
+		count_vm_event(COMPACTFAIL);
+		defer_compaction(preferred_zone);
+
+		cond_resched();
+	}
+
+	return NULL;
+}
+#else
+static inline struct page *
+__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+	int migratetype, unsigned long *did_some_progress)
+{
+	return NULL;
+}
+#endif /* CONFIG_COMPACTION */
+
 /* The really slow allocator path where we enter direct reclaim */
 static inline struct page *
 __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -1879,6 +2022,15 @@ rebalance:
 	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
 		goto nopage;
 
+	/* Try direct compaction */
+	page = __alloc_pages_direct_compact(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask,
+					alloc_flags, preferred_zone,
+					migratetype, &did_some_progress);
+	if (page)
+		goto got_pg;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -1903,15 +2055,23 @@ rebalance:
 			if (page)
 				goto got_pg;
 
-			/*
-			 * The OOM killer does not trigger for high-order
-			 * ~__GFP_NOFAIL allocations so if no progress is being
-			 * made, there are no other options and retrying is
-			 * unlikely to help.
-			 */
-			if (order > PAGE_ALLOC_COSTLY_ORDER &&
-						!(gfp_mask & __GFP_NOFAIL))
-				goto nopage;
+			if (!(gfp_mask & __GFP_NOFAIL)) {
+				/*
+				 * The oom killer is not called for high-order
+				 * allocations that may fail, so if no progress
+				 * is being made, there are no other options and
+				 * retrying is unlikely to help.
+				 */
+				if (order > PAGE_ALLOC_COSTLY_ORDER)
+					goto nopage;
+				/*
+				 * The oom killer is not called for lowmem
+				 * allocations to prevent needlessly killing
+				 * innocent tasks.
+				 */
+				if (high_zoneidx < ZONE_NORMAL)
+					goto nopage;
+			}
 
 			goto restart;
 		}
@@ -1970,10 +2130,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
+	get_mems_allowed();
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
-	if (!preferred_zone)
+	if (!preferred_zone) {
+		put_mems_allowed();
 		return NULL;
+	}
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -1983,6 +2146,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
+	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 	return page;
@@ -2434,8 +2598,11 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 			strncpy((char*)table->data, saved_string,
 				NUMA_ZONELIST_ORDER_LEN);
 			user_zonelist_order = oldval;
-		} else if (oldval != user_zonelist_order)
-			build_all_zonelists();
+		} else if (oldval != user_zonelist_order) {
+			mutex_lock(&zonelists_mutex);
+			build_all_zonelists(NULL);
+			mutex_unlock(&zonelists_mutex);
+		}
 	}
 out:
 	mutex_unlock(&zl_order_mutex);
@@ -2579,10 +2746,10 @@ static int default_zonelist_order(void)
 	struct zone *z;
 	int average_size;
 	/*
-         * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem.
+         * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
 	 * If they are really small and used heavily, the system can fall
 	 * into OOM very easily.
-	 * This function detect ZONE_DMA/DMA32 size and confgigures zone order.
+	 * This function detect ZONE_DMA/DMA32 size and configures zone order.
 	 */
 	/* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
 	low_kmem_size = 0;
@@ -2594,6 +2761,15 @@ static int default_zonelist_order(void)
 				if (zone_type < ZONE_NORMAL)
 					low_kmem_size += z->present_pages;
 				total_size += z->present_pages;
+			} else if (zone_type == ZONE_NORMAL) {
+				/*
+				 * If any node has only lowmem, then node order
+				 * is preferred to allow kernel allocations
+				 * locally; otherwise, they can easily infringe
+				 * on other nodes when there is an abundance of
+				 * lowmem available to allocate from.
+				 */
+				return ZONELIST_ORDER_NODE;
 			}
 		}
 	}
@@ -2707,6 +2883,24 @@ static void build_zonelist_cache(pg_data_t *pgdat)
 		zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
 }
 
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+/*
+ * Return node id of node used for "local" allocations.
+ * I.e., first node id of first zone in arg node's generic zonelist.
+ * Used for initializing percpu 'numa_mem', which is used primarily
+ * for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
+ */
+int local_memory_node(int node)
+{
+	struct zone *zone;
+
+	(void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
+				   gfp_zone(GFP_KERNEL),
+				   NULL,
+				   &zone);
+	return zone->node;
+}
+#endif
 
 #else	/* CONFIG_NUMA */
 
@@ -2776,9 +2970,16 @@ static void build_zonelist_cache(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 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 *dummy)
+static __init_refok int __build_all_zonelists(void *data)
 {
 	int nid;
 	int cpu;
@@ -2793,6 +2994,14 @@ static int __build_all_zonelists(void *dummy)
 		build_zonelist_cache(pgdat);
 	}
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* Setup real pagesets for the new zone */
+	if (data) {
+		struct zone *zone = data;
+		setup_zone_pageset(zone);
+	}
+#endif
+
 	/*
 	 * Initialize the boot_pagesets that are going to be used
 	 * for bootstrapping processors. The real pagesets for
@@ -2806,13 +3015,31 @@ static int __build_all_zonelists(void *dummy)
 	 * needs the percpu allocator in order to allocate its pagesets
 	 * (a chicken-egg dilemma).
 	 */
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		setup_pageset(&per_cpu(boot_pageset, cpu), 0);
 
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+		/*
+		 * We now know the "local memory node" for each node--
+		 * i.e., the node of the first zone in the generic zonelist.
+		 * Set up numa_mem percpu variable for on-line cpus.  During
+		 * boot, only the boot cpu should be on-line;  we'll init the
+		 * secondary cpus' numa_mem as they come on-line.  During
+		 * node/memory hotplug, we'll fixup all on-line cpus.
+		 */
+		if (cpu_online(cpu))
+			set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
+#endif
+	}
+
 	return 0;
 }
 
-void build_all_zonelists(void)
+/*
+ * Called with zonelists_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
+void build_all_zonelists(void *data)
 {
 	set_zonelist_order();
 
@@ -2823,7 +3050,7 @@ void build_all_zonelists(void)
 	} else {
 		/* we have to stop all cpus to guarantee there is no user
 		   of zonelist */
-		stop_machine(__build_all_zonelists, NULL, NULL);
+		stop_machine(__build_all_zonelists, data, NULL);
 		/* cpuset refresh routine should be here */
 	}
 	vm_total_pages = nr_free_pagecache_pages();
@@ -3146,31 +3373,34 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
 		pcp->batch = PAGE_SHIFT * 8;
 }
 
+static __meminit void setup_zone_pageset(struct zone *zone)
+{
+	int cpu;
+
+	zone->pageset = alloc_percpu(struct per_cpu_pageset);
+
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
+
+		setup_pageset(pcp, zone_batchsize(zone));
+
+		if (percpu_pagelist_fraction)
+			setup_pagelist_highmark(pcp,
+				(zone->present_pages /
+					percpu_pagelist_fraction));
+	}
+}
+
 /*
  * Allocate per cpu pagesets and initialize them.
  * Before this call only boot pagesets were available.
- * Boot pagesets will no longer be used by this processorr
- * after setup_per_cpu_pageset().
  */
 void __init setup_per_cpu_pageset(void)
 {
 	struct zone *zone;
-	int cpu;
-
-	for_each_populated_zone(zone) {
-		zone->pageset = alloc_percpu(struct per_cpu_pageset);
 
-		for_each_possible_cpu(cpu) {
-			struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
-
-			setup_pageset(pcp, zone_batchsize(zone));
-
-			if (percpu_pagelist_fraction)
-				setup_pagelist_highmark(pcp,
-					(zone->present_pages /
-						percpu_pagelist_fraction));
-		}
-	}
+	for_each_populated_zone(zone)
+		setup_zone_pageset(zone);
 }
 
 static noinline __init_refok
@@ -3415,6 +3645,9 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 	int i;
 	void *ptr;
 
+	if (limit > get_max_mapped())
+		limit = get_max_mapped();
+
 	/* need to go over early_node_map to find out good range for node */
 	for_each_active_range_index_in_nid(i, nid) {
 		u64 addr;
@@ -3440,6 +3673,11 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 		ptr = phys_to_virt(addr);
 		memset(ptr, 0, size);
 		reserve_early_without_check(addr, addr + size, "BOOTMEM");
+		/*
+		 * The min_count is set to 0 so that bootmem allocated blocks
+		 * are never reported as leaks.
+		 */
+		kmemleak_alloc(ptr, size, 0, 0);
 		return ptr;
 	}
 
@@ -3862,8 +4100,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone_seqlock_init(zone);
 		zone->zone_pgdat = pgdat;
 
-		zone->prev_priority = DEF_PRIORITY;
-
 		zone_pcp_init(zone);
 		for_each_lru(l) {
 			INIT_LIST_HEAD(&zone->lru[l].list);