X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=mm%2Fpage_alloc.c;h=3b5358a0561fa99366fbb9c7d2f858c40208b0fb;hb=123e9a5573098dbb10194c18d6d575620d0e94f3;hp=60f2feddbe5dc3ac04553d2e32afaa5e4bdac4fb;hpb=6ab3d5624e172c553004ecc862bfeac16d9d68b7;p=linux-2.6-omap-h63xx.git

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 60f2feddbe5..3b5358a0561 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -455,7 +455,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 
 	kernel_map_pages(page, 1 << order, 0);
 	local_irq_save(flags);
-	__mod_page_state(pgfree, 1 << order);
+	__count_vm_events(PGFREE, 1 << order);
 	free_one_page(page_zone(page), page, order);
 	local_irq_restore(flags);
 }
@@ -708,27 +708,6 @@ void drain_local_pages(void)
 }
 #endif /* CONFIG_PM */
 
-static void zone_statistics(struct zonelist *zonelist, struct zone *z, int cpu)
-{
-#ifdef CONFIG_NUMA
-	pg_data_t *pg = z->zone_pgdat;
-	pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
-	struct per_cpu_pageset *p;
-
-	p = zone_pcp(z, cpu);
-	if (pg == orig) {
-		p->numa_hit++;
-	} else {
-		p->numa_miss++;
-		zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
-	}
-	if (pg == NODE_DATA(numa_node_id()))
-		p->local_node++;
-	else
-		p->other_node++;
-#endif
-}
-
 /*
  * Free a 0-order page
  */
@@ -749,7 +728,7 @@ static void fastcall free_hot_cold_page(struct page *page, int cold)
 
 	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
 	local_irq_save(flags);
-	__inc_page_state(pgfree);
+	__count_vm_event(PGFREE);
 	list_add(&page->lru, &pcp->list);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
@@ -825,8 +804,8 @@ again:
 			goto failed;
 	}
 
-	__mod_page_state_zone(zone, pgalloc, 1 << order);
-	zone_statistics(zonelist, zone, cpu);
+	__count_zone_vm_events(PGALLOC, zone, 1 << order);
+	zone_statistics(zonelist, zone);
 	local_irq_restore(flags);
 	put_cpu();
 
@@ -1230,141 +1209,6 @@ static void show_node(struct zone *zone)
 #define show_node(zone)	do { } while (0)
 #endif
 
-/*
- * Accumulate the page_state information across all CPUs.
- * The result is unavoidably approximate - it can change
- * during and after execution of this function.
- */
-static DEFINE_PER_CPU(struct page_state, page_states) = {0};
-
-atomic_t nr_pagecache = ATOMIC_INIT(0);
-EXPORT_SYMBOL(nr_pagecache);
-#ifdef CONFIG_SMP
-DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
-#endif
-
-static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
-{
-	unsigned cpu;
-
-	memset(ret, 0, nr * sizeof(unsigned long));
-	cpus_and(*cpumask, *cpumask, cpu_online_map);
-
-	for_each_cpu_mask(cpu, *cpumask) {
-		unsigned long *in;
-		unsigned long *out;
-		unsigned off;
-		unsigned next_cpu;
-
-		in = (unsigned long *)&per_cpu(page_states, cpu);
-
-		next_cpu = next_cpu(cpu, *cpumask);
-		if (likely(next_cpu < NR_CPUS))
-			prefetch(&per_cpu(page_states, next_cpu));
-
-		out = (unsigned long *)ret;
-		for (off = 0; off < nr; off++)
-			*out++ += *in++;
-	}
-}
-
-void get_page_state_node(struct page_state *ret, int node)
-{
-	int nr;
-	cpumask_t mask = node_to_cpumask(node);
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr+1, &mask);
-}
-
-void get_page_state(struct page_state *ret)
-{
-	int nr;
-	cpumask_t mask = CPU_MASK_ALL;
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr + 1, &mask);
-}
-
-void get_full_page_state(struct page_state *ret)
-{
-	cpumask_t mask = CPU_MASK_ALL;
-
-	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
-}
-
-unsigned long read_page_state_offset(unsigned long offset)
-{
-	unsigned long ret = 0;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		unsigned long in;
-
-		in = (unsigned long)&per_cpu(page_states, cpu) + offset;
-		ret += *((unsigned long *)in);
-	}
-	return ret;
-}
-
-void __mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-	void *ptr;
-
-	ptr = &__get_cpu_var(page_states);
-	*(unsigned long *)(ptr + offset) += delta;
-}
-EXPORT_SYMBOL(__mod_page_state_offset);
-
-void mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-	unsigned long flags;
-	void *ptr;
-
-	local_irq_save(flags);
-	ptr = &__get_cpu_var(page_states);
-	*(unsigned long *)(ptr + offset) += delta;
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_page_state_offset);
-
-void __get_zone_counts(unsigned long *active, unsigned long *inactive,
-			unsigned long *free, struct pglist_data *pgdat)
-{
-	struct zone *zones = pgdat->node_zones;
-	int i;
-
-	*active = 0;
-	*inactive = 0;
-	*free = 0;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		*active += zones[i].nr_active;
-		*inactive += zones[i].nr_inactive;
-		*free += zones[i].free_pages;
-	}
-}
-
-void get_zone_counts(unsigned long *active,
-		unsigned long *inactive, unsigned long *free)
-{
-	struct pglist_data *pgdat;
-
-	*active = 0;
-	*inactive = 0;
-	*free = 0;
-	for_each_online_pgdat(pgdat) {
-		unsigned long l, m, n;
-		__get_zone_counts(&l, &m, &n, pgdat);
-		*active += l;
-		*inactive += m;
-		*free += n;
-	}
-}
-
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
@@ -1405,7 +1249,6 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  */
 void show_free_areas(void)
 {
-	struct page_state ps;
 	int cpu, temperature;
 	unsigned long active;
 	unsigned long inactive;
@@ -1437,7 +1280,6 @@ void show_free_areas(void)
 		}
 	}
 
-	get_page_state(&ps);
 	get_zone_counts(&active, &inactive, &free);
 
 	printk("Free pages: %11ukB (%ukB HighMem)\n",
@@ -1448,13 +1290,13 @@ void show_free_areas(void)
 		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
 		active,
 		inactive,
-		ps.nr_dirty,
-		ps.nr_writeback,
-		ps.nr_unstable,
+		global_page_state(NR_FILE_DIRTY),
+		global_page_state(NR_WRITEBACK),
+		global_page_state(NR_UNSTABLE_NFS),
 		nr_free_pages(),
-		ps.nr_slab,
-		ps.nr_mapped,
-		ps.nr_page_table_pages);
+		global_page_state(NR_SLAB),
+		global_page_state(NR_FILE_MAPPED),
+		global_page_state(NR_PAGETABLE));
 
 	for_each_zone(zone) {
 		int i;
@@ -2163,6 +2005,10 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 
 		zone->spanned_pages = size;
 		zone->present_pages = realsize;
+#ifdef CONFIG_NUMA
+		zone->min_unmapped_ratio = (realsize*sysctl_min_unmapped_ratio)
+						/ 100;
+#endif
 		zone->name = zone_names[j];
 		spin_lock_init(&zone->lock);
 		spin_lock_init(&zone->lru_lock);
@@ -2179,6 +2025,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		zone->nr_scan_inactive = 0;
 		zone->nr_active = 0;
 		zone->nr_inactive = 0;
+		zap_zone_vm_stats(zone);
 		atomic_set(&zone->reclaim_in_progress, 0);
 		if (!size)
 			continue;
@@ -2252,307 +2099,18 @@ void __init free_area_init(unsigned long *zones_size)
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
 
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-
-static void *frag_start(struct seq_file *m, loff_t *pos)
-{
-	pg_data_t *pgdat;
-	loff_t node = *pos;
-	for (pgdat = first_online_pgdat();
-	     pgdat && node;
-	     pgdat = next_online_pgdat(pgdat))
-		--node;
-
-	return pgdat;
-}
-
-static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-	pg_data_t *pgdat = (pg_data_t *)arg;
-
-	(*pos)++;
-	return next_online_pgdat(pgdat);
-}
-
-static void frag_stop(struct seq_file *m, void *arg)
-{
-}
-
-/* 
- * This walks the free areas for each zone.
- */
-static int frag_show(struct seq_file *m, void *arg)
-{
-	pg_data_t *pgdat = (pg_data_t *)arg;
-	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
-	unsigned long flags;
-	int order;
-
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
-		if (!populated_zone(zone))
-			continue;
-
-		spin_lock_irqsave(&zone->lock, flags);
-		seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
-		for (order = 0; order < MAX_ORDER; ++order)
-			seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
-		spin_unlock_irqrestore(&zone->lock, flags);
-		seq_putc(m, '\n');
-	}
-	return 0;
-}
-
-struct seq_operations fragmentation_op = {
-	.start	= frag_start,
-	.next	= frag_next,
-	.stop	= frag_stop,
-	.show	= frag_show,
-};
-
-/*
- * Output information about zones in @pgdat.
- */
-static int zoneinfo_show(struct seq_file *m, void *arg)
-{
-	pg_data_t *pgdat = arg;
-	struct zone *zone;
-	struct zone *node_zones = pgdat->node_zones;
-	unsigned long flags;
-
-	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
-		int i;
-
-		if (!populated_zone(zone))
-			continue;
-
-		spin_lock_irqsave(&zone->lock, flags);
-		seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
-		seq_printf(m,
-			   "\n  pages free     %lu"
-			   "\n        min      %lu"
-			   "\n        low      %lu"
-			   "\n        high     %lu"
-			   "\n        active   %lu"
-			   "\n        inactive %lu"
-			   "\n        scanned  %lu (a: %lu i: %lu)"
-			   "\n        spanned  %lu"
-			   "\n        present  %lu",
-			   zone->free_pages,
-			   zone->pages_min,
-			   zone->pages_low,
-			   zone->pages_high,
-			   zone->nr_active,
-			   zone->nr_inactive,
-			   zone->pages_scanned,
-			   zone->nr_scan_active, zone->nr_scan_inactive,
-			   zone->spanned_pages,
-			   zone->present_pages);
-		seq_printf(m,
-			   "\n        protection: (%lu",
-			   zone->lowmem_reserve[0]);
-		for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
-			seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
-		seq_printf(m,
-			   ")"
-			   "\n  pagesets");
-		for_each_online_cpu(i) {
-			struct per_cpu_pageset *pageset;
-			int j;
-
-			pageset = zone_pcp(zone, i);
-			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-				if (pageset->pcp[j].count)
-					break;
-			}
-			if (j == ARRAY_SIZE(pageset->pcp))
-				continue;
-			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-				seq_printf(m,
-					   "\n    cpu: %i pcp: %i"
-					   "\n              count: %i"
-					   "\n              high:  %i"
-					   "\n              batch: %i",
-					   i, j,
-					   pageset->pcp[j].count,
-					   pageset->pcp[j].high,
-					   pageset->pcp[j].batch);
-			}
-#ifdef CONFIG_NUMA
-			seq_printf(m,
-				   "\n            numa_hit:       %lu"
-				   "\n            numa_miss:      %lu"
-				   "\n            numa_foreign:   %lu"
-				   "\n            interleave_hit: %lu"
-				   "\n            local_node:     %lu"
-				   "\n            other_node:     %lu",
-				   pageset->numa_hit,
-				   pageset->numa_miss,
-				   pageset->numa_foreign,
-				   pageset->interleave_hit,
-				   pageset->local_node,
-				   pageset->other_node);
-#endif
-		}
-		seq_printf(m,
-			   "\n  all_unreclaimable: %u"
-			   "\n  prev_priority:     %i"
-			   "\n  temp_priority:     %i"
-			   "\n  start_pfn:         %lu",
-			   zone->all_unreclaimable,
-			   zone->prev_priority,
-			   zone->temp_priority,
-			   zone->zone_start_pfn);
-		spin_unlock_irqrestore(&zone->lock, flags);
-		seq_putc(m, '\n');
-	}
-	return 0;
-}
-
-struct seq_operations zoneinfo_op = {
-	.start	= frag_start, /* iterate over all zones. The same as in
-			       * fragmentation. */
-	.next	= frag_next,
-	.stop	= frag_stop,
-	.show	= zoneinfo_show,
-};
-
-static char *vmstat_text[] = {
-	"nr_dirty",
-	"nr_writeback",
-	"nr_unstable",
-	"nr_page_table_pages",
-	"nr_mapped",
-	"nr_slab",
-
-	"pgpgin",
-	"pgpgout",
-	"pswpin",
-	"pswpout",
-
-	"pgalloc_high",
-	"pgalloc_normal",
-	"pgalloc_dma32",
-	"pgalloc_dma",
-
-	"pgfree",
-	"pgactivate",
-	"pgdeactivate",
-
-	"pgfault",
-	"pgmajfault",
-
-	"pgrefill_high",
-	"pgrefill_normal",
-	"pgrefill_dma32",
-	"pgrefill_dma",
-
-	"pgsteal_high",
-	"pgsteal_normal",
-	"pgsteal_dma32",
-	"pgsteal_dma",
-
-	"pgscan_kswapd_high",
-	"pgscan_kswapd_normal",
-	"pgscan_kswapd_dma32",
-	"pgscan_kswapd_dma",
-
-	"pgscan_direct_high",
-	"pgscan_direct_normal",
-	"pgscan_direct_dma32",
-	"pgscan_direct_dma",
-
-	"pginodesteal",
-	"slabs_scanned",
-	"kswapd_steal",
-	"kswapd_inodesteal",
-	"pageoutrun",
-	"allocstall",
-
-	"pgrotated",
-	"nr_bounce",
-};
-
-static void *vmstat_start(struct seq_file *m, loff_t *pos)
-{
-	struct page_state *ps;
-
-	if (*pos >= ARRAY_SIZE(vmstat_text))
-		return NULL;
-
-	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
-	m->private = ps;
-	if (!ps)
-		return ERR_PTR(-ENOMEM);
-	get_full_page_state(ps);
-	ps->pgpgin /= 2;		/* sectors -> kbytes */
-	ps->pgpgout /= 2;
-	return (unsigned long *)ps + *pos;
-}
-
-static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-	(*pos)++;
-	if (*pos >= ARRAY_SIZE(vmstat_text))
-		return NULL;
-	return (unsigned long *)m->private + *pos;
-}
-
-static int vmstat_show(struct seq_file *m, void *arg)
-{
-	unsigned long *l = arg;
-	unsigned long off = l - (unsigned long *)m->private;
-
-	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
-	return 0;
-}
-
-static void vmstat_stop(struct seq_file *m, void *arg)
-{
-	kfree(m->private);
-	m->private = NULL;
-}
-
-struct seq_operations vmstat_op = {
-	.start	= vmstat_start,
-	.next	= vmstat_next,
-	.stop	= vmstat_stop,
-	.show	= vmstat_show,
-};
-
-#endif /* CONFIG_PROC_FS */
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int page_alloc_cpu_notify(struct notifier_block *self,
 				 unsigned long action, void *hcpu)
 {
 	int cpu = (unsigned long)hcpu;
-	long *count;
-	unsigned long *src, *dest;
 
 	if (action == CPU_DEAD) {
-		int i;
-
-		/* Drain local pagecache count. */
-		count = &per_cpu(nr_pagecache_local, cpu);
-		atomic_add(*count, &nr_pagecache);
-		*count = 0;
 		local_irq_disable();
 		__drain_pages(cpu);
-
-		/* Add dead cpu's page_states to our own. */
-		dest = (unsigned long *)&__get_cpu_var(page_states);
-		src = (unsigned long *)&per_cpu(page_states, cpu);
-
-		for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
-				i++) {
-			dest[i] += src[i];
-			src[i] = 0;
-		}
-
+		vm_events_fold_cpu(cpu);
 		local_irq_enable();
+		refresh_cpu_vm_stats(cpu);
 	}
 	return NOTIFY_OK;
 }
@@ -2744,6 +2302,24 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 	return 0;
 }
 
+#ifdef CONFIG_NUMA
+int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
+	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+	struct zone *zone;
+	int rc;
+
+	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	if (rc)
+		return rc;
+
+	for_each_zone(zone)
+		zone->min_unmapped_ratio = (zone->present_pages *
+				sysctl_min_unmapped_ratio) / 100;
+	return 0;
+}
+#endif
+
 /*
  * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
  *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
@@ -2787,7 +2363,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	return 0;
 }
 
-__initdata int hashdist = HASHDIST_DEFAULT;
+int hashdist = HASHDIST_DEFAULT;
 
 #ifdef CONFIG_NUMA
 static int __init set_hashdist(char *str)