1 files changed, 99 insertions, 86 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b2838c24e58..402a504f122 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -19,6 +19,7 @@
 #include <linux/swap.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
+#include <linux/jiffies.h>
 #include <linux/bootmem.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
@@ -43,6 +44,7 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
+#include <linux/memcontrol.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -220,13 +222,19 @@ static inline int bad_range(struct zone *zone, struct page *page)
 
 static void bad_page(struct page *page)
 {
-	printk(KERN_EMERG "Bad page state in process '%s'\n"
-		KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n"
-		KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
-		KERN_EMERG "Backtrace:\n",
+	void *pc = page_get_page_cgroup(page);
+
+	printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
+		"page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
 		current->comm, page, (int)(2*sizeof(unsigned long)),
 		(unsigned long)page->flags, page->mapping,
 		page_mapcount(page), page_count(page));
+	if (pc) {
+		printk(KERN_EMERG "cgroup:%p\n", pc);
+		page_reset_bad_cgroup(page);
+	}
+	printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+		KERN_EMERG "Backtrace:\n");
 	dump_stack();
 	page->flags &= ~(1 << PG_lru	|
 			1 << PG_private |
@@ -452,6 +460,7 @@ static inline int free_pages_check(struct page *page)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
+		(page_get_page_cgroup(page) != NULL) |
 		(page_count(page) != 0)  |
 		(page->flags & (
 			1 << PG_lru	|
@@ -537,7 +546,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 /*
  * permit the bootmem allocator to evade page validation on high-order frees
  */
-void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	if (order == 0) {
 		__ClearPageReserved(page);
@@ -601,6 +610,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
+		(page_get_page_cgroup(page) != NULL) |
 		(page_count(page) != 0)  |
 		(page->flags & (
 			1 << PG_lru	|
@@ -890,31 +900,51 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 }
 #endif
 
-static void __drain_pages(unsigned int cpu)
+/*
+ * Drain pages of the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
 {
 	unsigned long flags;
 	struct zone *zone;
-	int i;
 
 	for_each_zone(zone) {
 		struct per_cpu_pageset *pset;
+		struct per_cpu_pages *pcp;
 
 		if (!populated_zone(zone))
 			continue;
 
 		pset = zone_pcp(zone, cpu);
-		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
-			struct per_cpu_pages *pcp;
-
-			pcp = &pset->pcp[i];
-			local_irq_save(flags);
-			free_pages_bulk(zone, pcp->count, &pcp->list, 0);
-			pcp->count = 0;
-			local_irq_restore(flags);
-		}
+
+		pcp = &pset->pcp;
+		local_irq_save(flags);
+		free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+		pcp->count = 0;
+		local_irq_restore(flags);
 	}
 }
 
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void *arg)
+{
+	drain_pages(smp_processor_id());
+}
+
+/*
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ */
+void drain_all_pages(void)
+{
+	on_each_cpu(drain_local_pages, NULL, 0, 1);
+}
+
 #ifdef CONFIG_HIBERNATION
 
 void mark_free_pages(struct zone *zone)
@@ -952,40 +982,9 @@ void mark_free_pages(struct zone *zone)
 #endif /* CONFIG_PM */
 
 /*
- * Spill all of this CPU's per-cpu pages back into the buddy allocator.
- */
-void drain_local_pages(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);	
-	__drain_pages(smp_processor_id());
-	local_irq_restore(flags);	
-}
-
-void smp_drain_local_pages(void *arg)
-{
-	drain_local_pages();
-}
-
-/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
- */
-void drain_all_local_pages(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__drain_pages(smp_processor_id());
-	local_irq_restore(flags);
-
-	smp_call_function(smp_drain_local_pages, NULL, 0, 1);
-}
-
-/*
  * Free a 0-order page
  */
-static void fastcall free_hot_cold_page(struct page *page, int cold)
+static void free_hot_cold_page(struct page *page, int cold)
 {
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
@@ -1001,10 +1000,13 @@ static void fastcall free_hot_cold_page(struct page *page, int cold)
 	arch_free_page(page, 0);
 	kernel_map_pages(page, 1, 0);
 
-	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
+	pcp = &zone_pcp(zone, get_cpu())->pcp;
 	local_irq_save(flags);
 	__count_vm_event(PGFREE);
-	list_add(&page->lru, &pcp->list);
+	if (cold)
+		list_add_tail(&page->lru, &pcp->list);
+	else
+		list_add(&page->lru, &pcp->list);
 	set_page_private(page, get_pageblock_migratetype(page));
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
@@ -1015,12 +1017,12 @@ static void fastcall free_hot_cold_page(struct page *page, int cold)
 	put_cpu();
 }
 
-void fastcall free_hot_page(struct page *page)
+void free_hot_page(struct page *page)
 {
 	free_hot_cold_page(page, 0);
 }
 	
-void fastcall free_cold_page(struct page *page)
+void free_cold_page(struct page *page)
 {
 	free_hot_cold_page(page, 1);
 }
@@ -1062,7 +1064,7 @@ again:
 	if (likely(order == 0)) {
 		struct per_cpu_pages *pcp;
 
-		pcp = &zone_pcp(zone, cpu)->pcp[cold];
+		pcp = &zone_pcp(zone, cpu)->pcp;
 		local_irq_save(flags);
 		if (!pcp->count) {
 			pcp->count = rmqueue_bulk(zone, 0,
@@ -1072,9 +1074,15 @@ again:
 		}
 
 		/* Find a page of the appropriate migrate type */
-		list_for_each_entry(page, &pcp->list, lru)
-			if (page_private(page) == migratetype)
-				break;
+		if (cold) {
+			list_for_each_entry_reverse(page, &pcp->list, lru)
+				if (page_private(page) == migratetype)
+					break;
+		} else {
+			list_for_each_entry(page, &pcp->list, lru)
+				if (page_private(page) == migratetype)
+					break;
+		}
 
 		/* Allocate more to the pcp list if necessary */
 		if (unlikely(&page->lru == &pcp->list)) {
@@ -1276,7 +1284,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
 	if (!zlc)
 		return NULL;
 
-	if (jiffies - zlc->last_full_zap > 1 * HZ) {
+       if (time_after(jiffies, zlc->last_full_zap + HZ)) {
 		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
 		zlc->last_full_zap = jiffies;
 	}
@@ -1451,7 +1459,7 @@ try_next_zone:
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page * fastcall
+struct page *
 __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		struct zonelist *zonelist)
 {
@@ -1569,7 +1577,7 @@ nofail_alloc:
 	cond_resched();
 
 	if (order != 0)
-		drain_all_local_pages();
+		drain_all_pages();
 
 	if (likely(did_some_progress)) {
 		page = get_page_from_freelist(gfp_mask, order,
@@ -1643,7 +1651,7 @@ EXPORT_SYMBOL(__alloc_pages);
 /*
  * Common helper functions.
  */
-fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
 {
 	struct page * page;
 	page = alloc_pages(gfp_mask, order);
@@ -1654,7 +1662,7 @@ fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
 
 EXPORT_SYMBOL(__get_free_pages);
 
-fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
+unsigned long get_zeroed_page(gfp_t gfp_mask)
 {
 	struct page * page;
 
@@ -1680,7 +1688,7 @@ void __pagevec_free(struct pagevec *pvec)
 		free_hot_cold_page(pvec->pages[i], pvec->cold);
 }
 
-fastcall void __free_pages(struct page *page, unsigned int order)
+void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
 		if (order == 0)
@@ -1692,7 +1700,7 @@ fastcall void __free_pages(struct page *page, unsigned int order)
 
 EXPORT_SYMBOL(__free_pages);
 
-fastcall void free_pages(unsigned long addr, unsigned int order)
+void free_pages(unsigned long addr, unsigned int order)
 {
 	if (addr != 0) {
 		VM_BUG_ON(!virt_addr_valid((void *)addr));
@@ -1801,12 +1809,9 @@ void show_free_areas(void)
 
 			pageset = zone_pcp(zone, cpu);
 
-			printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d   "
-			       "Cold: hi:%5d, btch:%4d usd:%4d\n",
-			       cpu, pageset->pcp[0].high,
-			       pageset->pcp[0].batch, pageset->pcp[0].count,
-			       pageset->pcp[1].high, pageset->pcp[1].batch,
-			       pageset->pcp[1].count);
+			printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
+			       cpu, pageset->pcp.high,
+			       pageset->pcp.batch, pageset->pcp.count);
 		}
 	}
 
@@ -1879,6 +1884,8 @@ void show_free_areas(void)
 		printk("= %lukB\n", K(total));
 	}
 
+	printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+
 	show_swap_cache_info();
 }
 
@@ -2551,8 +2558,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	}
 }
 
-static void __meminit zone_init_free_lists(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long size)
+static void __meminit zone_init_free_lists(struct zone *zone)
 {
 	int order, t;
 	for_each_migratetype_order(order, t) {
@@ -2604,17 +2610,11 @@ inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 
 	memset(p, 0, sizeof(*p));
 
-	pcp = &p->pcp[0];		/* hot */
+	pcp = &p->pcp;
 	pcp->count = 0;
 	pcp->high = 6 * batch;
 	pcp->batch = max(1UL, 1 * batch);
 	INIT_LIST_HEAD(&pcp->list);
-
-	pcp = &p->pcp[1];		/* cold*/
-	pcp->count = 0;
-	pcp->high = 2 * batch;
-	pcp->batch = max(1UL, batch/2);
-	INIT_LIST_HEAD(&pcp->list);
 }
 
 /*
@@ -2627,7 +2627,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
 {
 	struct per_cpu_pages *pcp;
 
-	pcp = &p->pcp[0]; /* hot list */
+	pcp = &p->pcp;
 	pcp->high = high;
 	pcp->batch = max(1UL, high/4);
 	if ((high/4) > (PAGE_SHIFT * 8))
@@ -2831,7 +2831,7 @@ __meminit int init_currently_empty_zone(struct zone *zone,
 
 	memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
 
-	zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+	zone_init_free_lists(zone);
 
 	return 0;
 }
@@ -3321,7 +3321,7 @@ static inline int pageblock_default_order(unsigned int order)
  *   - mark all memory queues empty
  *   - clear the memory bitmaps
  */
-static void __meminit free_area_init_core(struct pglist_data *pgdat,
+static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		unsigned long *zones_size, unsigned long *zholes_size)
 {
 	enum zone_type j;
@@ -3445,7 +3445,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 #endif /* CONFIG_FLAT_NODE_MEM_MAP */
 }
 
-void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
+void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat,
 		unsigned long *zones_size, unsigned long node_start_pfn,
 		unsigned long *zholes_size)
 {
@@ -3978,10 +3978,23 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 	int cpu = (unsigned long)hcpu;
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		local_irq_disable();
-		__drain_pages(cpu);
+		drain_pages(cpu);
+
+		/*
+		 * Spill the event counters of the dead processor
+		 * into the current processors event counters.
+		 * This artificially elevates the count of the current
+		 * processor.
+		 */
 		vm_events_fold_cpu(cpu);
-		local_irq_enable();
+
+		/*
+		 * Zero the differential counters of the dead processor
+		 * so that the vm statistics are consistent.
+		 *
+		 * This is only okay since the processor is dead and cannot
+		 * race with what we are doing.
+		 */
 		refresh_cpu_vm_stats(cpu);
 	}
 	return NOTIFY_OK;
@@ -4480,7 +4493,7 @@ int set_migratetype_isolate(struct page *page)
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
-		drain_all_local_pages();
+		drain_all_pages();
 	return ret;
 }