*/
#include <linux/mm.h>
+#include <linux/err.h>
#include <linux/module.h>
#include <linux/cpu.h>
-
-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;
- }
-}
+#include <linux/sched.h>
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
* in between and therefore the atomicity vs. interrupt cannot be exploited
* in a useful way here.
*/
-static void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
+void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
s8 *p = pcp->vm_stat_diff + item;
}
EXPORT_SYMBOL(__inc_zone_page_state);
-void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
- struct zone *zone = page_zone(page);
struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
s8 *p = pcp->vm_stat_diff + item;
*p = overstep;
}
}
+
+void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+ __dec_zone_state(page_zone(page), item);
+}
EXPORT_SYMBOL(__dec_zone_page_state);
void inc_zone_state(struct zone *zone, enum zone_stat_item item)
/*
* Update the zone counters for one cpu.
+ *
+ * Note that refresh_cpu_vm_stats strives to only access
+ * node local memory. The per cpu pagesets on remote zones are placed
+ * in the memory local to the processor using that pageset. So the
+ * loop over all zones will access a series of cachelines local to
+ * the processor.
+ *
+ * The call to zone_page_state_add updates the cachelines with the
+ * statistics in the remote zone struct as well as the global cachelines
+ * with the global counters. These could cause remote node cache line
+ * bouncing and will have to be only done when necessary.
*/
void refresh_cpu_vm_stats(int cpu)
{
unsigned long flags;
for_each_zone(zone) {
- struct per_cpu_pageset *pcp;
+ struct per_cpu_pageset *p;
if (!populated_zone(zone))
continue;
- pcp = zone_pcp(zone, cpu);
+ p = zone_pcp(zone, cpu);
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (pcp->vm_stat_diff[i]) {
+ if (p->vm_stat_diff[i]) {
local_irq_save(flags);
- zone_page_state_add(pcp->vm_stat_diff[i],
+ zone_page_state_add(p->vm_stat_diff[i],
zone, i);
- pcp->vm_stat_diff[i] = 0;
+ p->vm_stat_diff[i] = 0;
+#ifdef CONFIG_NUMA
+ /* 3 seconds idle till flush */
+ p->expire = 3;
+#endif
local_irq_restore(flags);
}
- }
-}
+#ifdef CONFIG_NUMA
+ /*
+ * Deal with draining the remote pageset of this
+ * processor
+ *
+ * Check if there are pages remaining in this pageset
+ * if not then there is nothing to expire.
+ */
+ if (!p->expire || (!p->pcp[0].count && !p->pcp[1].count))
+ continue;
-static void __refresh_cpu_vm_stats(void *dummy)
-{
- refresh_cpu_vm_stats(smp_processor_id());
-}
+ /*
+ * We never drain zones local to this processor.
+ */
+ if (zone_to_nid(zone) == numa_node_id()) {
+ p->expire = 0;
+ continue;
+ }
-/*
- * Consolidate all counters.
- *
- * Note that the result is less inaccurate but still inaccurate
- * if concurrent processes are allowed to run.
- */
-void refresh_vm_stats(void)
-{
- on_each_cpu(__refresh_cpu_vm_stats, NULL, 0, 1);
+ p->expire--;
+ if (p->expire)
+ continue;
+
+ if (p->pcp[0].count)
+ drain_zone_pages(zone, p->pcp + 0);
+
+ if (p->pcp[1].count)
+ drain_zone_pages(zone, p->pcp + 1);
+#endif
+ }
}
-EXPORT_SYMBOL(refresh_vm_stats);
#endif
#include <linux/seq_file.h>
+static char * const migratetype_names[MIGRATE_TYPES] = {
+ "Unmovable",
+ "Reclaimable",
+ "Movable",
+ "Reserve",
+};
+
static void *frag_start(struct seq_file *m, loff_t *pos)
{
pg_data_t *pgdat;
{
}
-/*
- * This walks the free areas for each zone.
- */
-static int frag_show(struct seq_file *m, void *arg)
+/* Walk all the zones in a node and print using a callback */
+static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
+ void (*print)(struct seq_file *m, pg_data_t *, struct zone *))
{
- 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);
+ print(m, pgdat, zone);
spin_unlock_irqrestore(&zone->lock, flags);
+ }
+}
+
+static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
+ struct zone *zone)
+{
+ int order;
+
+ 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);
+ seq_putc(m, '\n');
+}
+
+/*
+ * 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;
+ walk_zones_in_node(m, pgdat, frag_show_print);
+ return 0;
+}
+
+static void pagetypeinfo_showfree_print(struct seq_file *m,
+ pg_data_t *pgdat, struct zone *zone)
+{
+ int order, mtype;
+
+ for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) {
+ seq_printf(m, "Node %4d, zone %8s, type %12s ",
+ pgdat->node_id,
+ zone->name,
+ migratetype_names[mtype]);
+ for (order = 0; order < MAX_ORDER; ++order) {
+ unsigned long freecount = 0;
+ struct free_area *area;
+ struct list_head *curr;
+
+ area = &(zone->free_area[order]);
+
+ list_for_each(curr, &area->free_list[mtype])
+ freecount++;
+ seq_printf(m, "%6lu ", freecount);
+ }
seq_putc(m, '\n');
}
+}
+
+/* Print out the free pages at each order for each migatetype */
+static int pagetypeinfo_showfree(struct seq_file *m, void *arg)
+{
+ int order;
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ /* Print header */
+ seq_printf(m, "%-43s ", "Free pages count per migrate type at order");
+ for (order = 0; order < MAX_ORDER; ++order)
+ seq_printf(m, "%6d ", order);
+ seq_putc(m, '\n');
+
+ walk_zones_in_node(m, pgdat, pagetypeinfo_showfree_print);
+
+ return 0;
+}
+
+static void pagetypeinfo_showblockcount_print(struct seq_file *m,
+ pg_data_t *pgdat, struct zone *zone)
+{
+ int mtype;
+ unsigned long pfn;
+ unsigned long start_pfn = zone->zone_start_pfn;
+ unsigned long end_pfn = start_pfn + zone->spanned_pages;
+ unsigned long count[MIGRATE_TYPES] = { 0, };
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+ struct page *page;
+
+ if (!pfn_valid(pfn))
+ continue;
+
+ page = pfn_to_page(pfn);
+ mtype = get_pageblock_migratetype(page);
+
+ count[mtype]++;
+ }
+
+ /* Print counts */
+ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+ for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
+ seq_printf(m, "%12lu ", count[mtype]);
+ seq_putc(m, '\n');
+}
+
+/* Print out the free pages at each order for each migratetype */
+static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
+{
+ int mtype;
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ seq_printf(m, "\n%-23s", "Number of blocks type ");
+ for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
+ seq_printf(m, "%12s ", migratetype_names[mtype]);
+ seq_putc(m, '\n');
+ walk_zones_in_node(m, pgdat, pagetypeinfo_showblockcount_print);
+
+ return 0;
+}
+
+/*
+ * This prints out statistics in relation to grouping pages by mobility.
+ * It is expensive to collect so do not constantly read the file.
+ */
+static int pagetypeinfo_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ seq_printf(m, "Page block order: %d\n", pageblock_order);
+ seq_printf(m, "Pages per block: %lu\n", pageblock_nr_pages);
+ seq_putc(m, '\n');
+ pagetypeinfo_showfree(m, pgdat);
+ pagetypeinfo_showblockcount(m, pgdat);
+
return 0;
}
-struct seq_operations fragmentation_op = {
+const struct seq_operations fragmentation_op = {
.start = frag_start,
.next = frag_next,
.stop = frag_stop,
.show = frag_show,
};
+const struct seq_operations pagetypeinfo_op = {
+ .start = frag_start,
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = pagetypeinfo_show,
+};
+
+#ifdef CONFIG_ZONE_DMA
+#define TEXT_FOR_DMA(xx) xx "_dma",
+#else
+#define TEXT_FOR_DMA(xx)
+#endif
+
#ifdef CONFIG_ZONE_DMA32
#define TEXT_FOR_DMA32(xx) xx "_dma32",
#else
#define TEXT_FOR_HIGHMEM(xx)
#endif
-#define TEXTS_FOR_ZONES(xx) xx "_dma", TEXT_FOR_DMA32(xx) xx "_normal", \
- TEXT_FOR_HIGHMEM(xx)
+#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
+ TEXT_FOR_HIGHMEM(xx) xx "_movable",
-static char *vmstat_text[] = {
+static const char * const vmstat_text[] = {
/* Zoned VM counters */
+ "nr_free_pages",
+ "nr_inactive",
+ "nr_active",
"nr_anon_pages",
"nr_mapped",
"nr_file_pages",
+ "nr_dirty",
+ "nr_writeback",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
"nr_page_table_pages",
- "nr_dirty",
- "nr_writeback",
"nr_unstable",
"nr_bounce",
"nr_vmscan_write",
#endif
};
-/*
- * Output information about zones in @pgdat.
- */
-static int zoneinfo_show(struct seq_file *m, void *arg)
+static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
+ struct zone *zone)
{
- 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);
+ int i;
+ 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 scanned %lu (a: %lu i: %lu)"
+ "\n spanned %lu"
+ "\n present %lu",
+ zone_page_state(zone, NR_FREE_PAGES),
+ zone->pages_min,
+ zone->pages_low,
+ zone->pages_high,
+ zone->pages_scanned,
+ zone->nr_scan_active, zone->nr_scan_inactive,
+ zone->spanned_pages,
+ zone->present_pages);
- for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- seq_printf(m, "\n %-12s %lu", vmstat_text[i],
- zone_page_state(zone, i));
-
- 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);
+ for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+ seq_printf(m, "\n %-12s %lu", vmstat_text[i],
+ zone_page_state(zone, i));
+
+ 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++) {
+ 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_SMP
- seq_printf(m, "\n vm stats threshold: %d",
- pageset->stat_threshold);
+ seq_printf(m, "\n vm stats threshold: %d",
+ pageset->stat_threshold);
#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');
}
+ seq_printf(m,
+ "\n all_unreclaimable: %u"
+ "\n prev_priority: %i"
+ "\n start_pfn: %lu",
+ zone_is_all_unreclaimable(zone),
+ zone->prev_priority,
+ zone->zone_start_pfn);
+ seq_putc(m, '\n');
+}
+
+/*
+ * Output information about zones in @pgdat.
+ */
+static int zoneinfo_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+ walk_zones_in_node(m, pgdat, zoneinfo_show_print);
return 0;
}
-struct seq_operations zoneinfo_op = {
+const struct seq_operations zoneinfo_op = {
.start = frag_start, /* iterate over all zones. The same as in
* fragmentation. */
.next = frag_next,
m->private = NULL;
}
-struct seq_operations vmstat_op = {
+const struct seq_operations vmstat_op = {
.start = vmstat_start,
.next = vmstat_next,
.stop = vmstat_stop,
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
+int sysctl_stat_interval __read_mostly = HZ;
+
+static void vmstat_update(struct work_struct *w)
+{
+ refresh_cpu_vm_stats(smp_processor_id());
+ schedule_delayed_work(&__get_cpu_var(vmstat_work),
+ sysctl_stat_interval);
+}
+
+static void __cpuinit start_cpu_timer(int cpu)
+{
+ struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+
+ INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
+ schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+}
+
/*
* Use the cpu notifier to insure that the thresholds are recalculated
* when necessary.
unsigned long action,
void *hcpu)
{
+ long cpu = (long)hcpu;
+
switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_CANCELED:
- case CPU_DEAD:
- refresh_zone_stat_thresholds();
- break;
- default:
- break;
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ start_cpu_timer(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu));
+ per_cpu(vmstat_work, cpu).work.func = NULL;
+ break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ start_cpu_timer(cpu);
+ break;
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ refresh_zone_stat_thresholds();
+ break;
+ default:
+ break;
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata vmstat_notifier =
{ &vmstat_cpuup_callback, NULL, 0 };
-int __init setup_vmstat(void)
+static int __init setup_vmstat(void)
{
+ int cpu;
+
refresh_zone_stat_thresholds();
register_cpu_notifier(&vmstat_notifier);
+
+ for_each_online_cpu(cpu)
+ start_cpu_timer(cpu);
return 0;
}
module_init(setup_vmstat)