*
* vm_stat contains the global counters
*/
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
-EXPORT_SYMBOL(vm_stat);
+atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
+atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
+EXPORT_SYMBOL(vm_zone_stat);
+EXPORT_SYMBOL(vm_node_stat);
#ifdef CONFIG_SMP
*/
void refresh_zone_stat_thresholds(void)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int cpu;
int threshold;
+ /* Zero current pgdat thresholds */
+ for_each_online_pgdat(pgdat) {
+ for_each_online_cpu(cpu) {
+ per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0;
+ }
+ }
+
for_each_populated_zone(zone) {
+ struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long max_drift, tolerate_drift;
threshold = calculate_normal_threshold(zone);
- for_each_online_cpu(cpu)
+ for_each_online_cpu(cpu) {
+ int pgdat_threshold;
+
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
= threshold;
+ /* Base nodestat threshold on the largest populated zone. */
+ pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
+ per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
+ = max(threshold, pgdat_threshold);
+ }
+
/*
* Only set percpu_drift_mark if there is a danger that
* NR_FREE_PAGES reports the low watermark is ok when in fact
}
EXPORT_SYMBOL(__mod_zone_page_state);
+void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ long x;
+ long t;
+
+ x = delta + __this_cpu_read(*p);
+
+ t = __this_cpu_read(pcp->stat_threshold);
+
+ if (unlikely(x > t || x < -t)) {
+ node_page_state_add(x, pgdat, item);
+ x = 0;
+ }
+ __this_cpu_write(*p, x);
+}
+EXPORT_SYMBOL(__mod_node_page_state);
+
/*
* Optimized increment and decrement functions.
*
}
}
+void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s8 v, t;
+
+ v = __this_cpu_inc_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v > t)) {
+ s8 overstep = t >> 1;
+
+ node_page_state_add(v + overstep, pgdat, item);
+ __this_cpu_write(*p, -overstep);
+ }
+}
+
void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
__inc_zone_state(page_zone(page), item);
}
EXPORT_SYMBOL(__inc_zone_page_state);
+void __inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ __inc_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__inc_node_page_state);
+
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
struct per_cpu_pageset __percpu *pcp = zone->pageset;
}
}
+void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s8 v, t;
+
+ v = __this_cpu_dec_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v < - t)) {
+ s8 overstep = t >> 1;
+
+ node_page_state_add(v - overstep, pgdat, item);
+ __this_cpu_write(*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 __dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ __dec_node_state(page_pgdat(page), item);
+}
+EXPORT_SYMBOL(__dec_node_page_state);
+
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
/*
* If we have cmpxchg_local support then we do not need to incur the overhead
* 1 Overstepping half of threshold
* -1 Overstepping minus half of threshold
*/
-static inline void mod_state(struct zone *zone, enum zone_stat_item item,
- long delta, int overstep_mode)
+static inline void mod_zone_state(struct zone *zone,
+ enum zone_stat_item item, long delta, int overstep_mode)
{
struct per_cpu_pageset __percpu *pcp = zone->pageset;
s8 __percpu *p = pcp->vm_stat_diff + item;
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
long delta)
{
- mod_state(zone, item, delta, 0);
+ mod_zone_state(zone, item, delta, 0);
}
EXPORT_SYMBOL(mod_zone_page_state);
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
- mod_state(zone, item, 1, 1);
-}
-
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
- mod_state(page_zone(page), item, 1, 1);
+ mod_zone_state(page_zone(page), item, 1, 1);
}
EXPORT_SYMBOL(inc_zone_page_state);
void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
- mod_state(page_zone(page), item, -1, -1);
+ mod_zone_state(page_zone(page), item, -1, -1);
}
EXPORT_SYMBOL(dec_zone_page_state);
+
+static inline void mod_node_state(struct pglist_data *pgdat,
+ enum node_stat_item item, int delta, int overstep_mode)
+{
+ struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
+ s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ long o, n, t, z;
+
+ do {
+ z = 0; /* overflow to node counters */
+
+ /*
+ * The fetching of the stat_threshold is racy. We may apply
+ * a counter threshold to the wrong the cpu if we get
+ * rescheduled while executing here. However, the next
+ * counter update will apply the threshold again and
+ * therefore bring the counter under the threshold again.
+ *
+ * Most of the time the thresholds are the same anyways
+ * for all cpus in a node.
+ */
+ t = this_cpu_read(pcp->stat_threshold);
+
+ o = this_cpu_read(*p);
+ n = delta + o;
+
+ if (n > t || n < -t) {
+ int os = overstep_mode * (t >> 1) ;
+
+ /* Overflow must be added to node counters */
+ z = n + os;
+ n = -os;
+ }
+ } while (this_cpu_cmpxchg(*p, o, n) != o);
+
+ if (z)
+ node_page_state_add(z, pgdat, item);
+}
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ mod_node_state(pgdat, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ mod_node_state(pgdat, item, 1, 1);
+}
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ mod_node_state(page_pgdat(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ mod_node_state(page_pgdat(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_node_page_state);
#else
/*
* Use interrupt disable to serialize counter updates
}
EXPORT_SYMBOL(mod_zone_page_state);
-void inc_zone_state(struct zone *zone, enum zone_stat_item item)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __inc_zone_state(zone, item);
- local_irq_restore(flags);
-}
-
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
unsigned long flags;
local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
-#endif
+void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __inc_node_state(pgdat, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_state);
+
+void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
+ long delta)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __mod_node_page_state(pgdat, item, delta);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_node_page_state);
+
+void inc_node_page_state(struct page *page, enum node_stat_item item)
+{
+ unsigned long flags;
+ struct pglist_data *pgdat;
+
+ pgdat = page_pgdat(page);
+ local_irq_save(flags);
+ __inc_node_state(pgdat, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_node_page_state);
+
+void dec_node_page_state(struct page *page, enum node_stat_item item)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __dec_node_page_state(page, item);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(dec_node_page_state);
+#endif
/*
* Fold a differential into the global counters.
* Returns the number of counters updated.
*/
-static int fold_diff(int *diff)
+static int fold_diff(int *zone_diff, int *node_diff)
{
int i;
int changes = 0;
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (diff[i]) {
- atomic_long_add(diff[i], &vm_stat[i]);
+ if (zone_diff[i]) {
+ atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
+ changes++;
+ }
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ if (node_diff[i]) {
+ atomic_long_add(node_diff[i], &vm_node_stat[i]);
changes++;
}
return changes;
*/
static int refresh_cpu_vm_stats(bool do_pagesets)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int i;
- int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
int changes = 0;
for_each_populated_zone(zone) {
if (v) {
atomic_long_add(v, &zone->vm_stat[i]);
- global_diff[i] += v;
+ global_zone_diff[i] += v;
#ifdef CONFIG_NUMA
/* 3 seconds idle till flush */
__this_cpu_write(p->expire, 3);
}
#endif
}
- changes += fold_diff(global_diff);
+
+ for_each_online_pgdat(pgdat) {
+ struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats;
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ int v;
+
+ v = this_cpu_xchg(p->vm_node_stat_diff[i], 0);
+ if (v) {
+ atomic_long_add(v, &pgdat->vm_stat[i]);
+ global_node_diff[i] += v;
+ }
+ }
+ }
+
+ changes += fold_diff(global_zone_diff, global_node_diff);
return changes;
}
*/
void cpu_vm_stats_fold(int cpu)
{
+ struct pglist_data *pgdat;
struct zone *zone;
int i;
- int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
for_each_populated_zone(zone) {
struct per_cpu_pageset *p;
v = p->vm_stat_diff[i];
p->vm_stat_diff[i] = 0;
atomic_long_add(v, &zone->vm_stat[i]);
- global_diff[i] += v;
+ global_zone_diff[i] += v;
+ }
+ }
+
+ for_each_online_pgdat(pgdat) {
+ struct per_cpu_nodestat *p;
+
+ p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);
+
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ if (p->vm_node_stat_diff[i]) {
+ int v;
+
+ v = p->vm_node_stat_diff[i];
+ p->vm_node_stat_diff[i] = 0;
+ atomic_long_add(v, &pgdat->vm_stat[i]);
+ global_node_diff[i] += v;
}
}
- fold_diff(global_diff);
+ fold_diff(global_zone_diff, global_node_diff);
}
/*
int v = pset->vm_stat_diff[i];
pset->vm_stat_diff[i] = 0;
atomic_long_add(v, &zone->vm_stat[i]);
- atomic_long_add(v, &vm_stat[i]);
+ atomic_long_add(v, &vm_zone_stat[i]);
}
}
#endif
#ifdef CONFIG_NUMA
/*
- * zonelist = the list of zones passed to the allocator
- * z = the zone from which the allocation occurred.
- *
- * Must be called with interrupts disabled.
- *
- * When __GFP_OTHER_NODE is set assume the node of the preferred
- * zone is the local node. This is useful for daemons who allocate
- * memory on behalf of other processes.
+ * Determine the per node value of a stat item. This function
+ * is called frequently in a NUMA machine, so try to be as
+ * frugal as possible.
*/
-void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags)
+unsigned long sum_zone_node_page_state(int node,
+ enum zone_stat_item item)
{
- if (z->zone_pgdat == preferred_zone->zone_pgdat) {
- __inc_zone_state(z, NUMA_HIT);
- } else {
- __inc_zone_state(z, NUMA_MISS);
- __inc_zone_state(preferred_zone, NUMA_FOREIGN);
- }
- if (z->node == ((flags & __GFP_OTHER_NODE) ?
- preferred_zone->node : numa_node_id()))
- __inc_zone_state(z, NUMA_LOCAL);
- else
- __inc_zone_state(z, NUMA_OTHER);
+ struct zone *zones = NODE_DATA(node)->node_zones;
+ int i;
+ unsigned long count = 0;
+
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ count += zone_page_state(zones + i, item);
+
+ return count;
}
/*
* Determine the per node value of a stat item.
*/
-unsigned long node_page_state(int node, enum zone_stat_item item)
+unsigned long node_page_state(struct pglist_data *pgdat,
+ enum node_stat_item item)
{
- struct zone *zones = NODE_DATA(node)->node_zones;
-
- return
-#ifdef CONFIG_ZONE_DMA
- zone_page_state(&zones[ZONE_DMA], item) +
-#endif
-#ifdef CONFIG_ZONE_DMA32
- zone_page_state(&zones[ZONE_DMA32], item) +
-#endif
-#ifdef CONFIG_HIGHMEM
- zone_page_state(&zones[ZONE_HIGHMEM], item) +
+ long x = atomic_long_read(&pgdat->vm_stat[item]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
#endif
- zone_page_state(&zones[ZONE_NORMAL], item) +
- zone_page_state(&zones[ZONE_MOVABLE], item);
+ return x;
}
-
#endif
#ifdef CONFIG_COMPACTION
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
- "nr_alloc_batch",
- "nr_inactive_anon",
- "nr_active_anon",
- "nr_inactive_file",
- "nr_active_file",
- "nr_unevictable",
+ "nr_zone_inactive_anon",
+ "nr_zone_active_anon",
+ "nr_zone_inactive_file",
+ "nr_zone_active_file",
+ "nr_zone_unevictable",
+ "nr_zone_write_pending",
"nr_mlock",
- "nr_anon_pages",
- "nr_mapped",
- "nr_file_pages",
- "nr_dirty",
- "nr_writeback",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
"nr_page_table_pages",
"nr_kernel_stack",
- "nr_unstable",
"nr_bounce",
- "nr_vmscan_write",
- "nr_vmscan_immediate_reclaim",
- "nr_writeback_temp",
- "nr_isolated_anon",
- "nr_isolated_file",
- "nr_shmem",
- "nr_dirtied",
- "nr_written",
- "nr_pages_scanned",
-
+#if IS_ENABLED(CONFIG_ZSMALLOC)
+ "nr_zspages",
+#endif
#ifdef CONFIG_NUMA
"numa_hit",
"numa_miss",
"numa_local",
"numa_other",
#endif
+ "nr_free_cma",
+
+ /* Node-based counters */
+ "nr_inactive_anon",
+ "nr_active_anon",
+ "nr_inactive_file",
+ "nr_active_file",
+ "nr_unevictable",
+ "nr_isolated_anon",
+ "nr_isolated_file",
+ "nr_pages_scanned",
"workingset_refault",
"workingset_activate",
"workingset_nodereclaim",
+ "nr_anon_pages",
+ "nr_mapped",
+ "nr_file_pages",
+ "nr_dirty",
+ "nr_writeback",
+ "nr_writeback_temp",
+ "nr_shmem",
+ "nr_shmem_hugepages",
+ "nr_shmem_pmdmapped",
"nr_anon_transparent_hugepages",
- "nr_free_cma",
+ "nr_unstable",
+ "nr_vmscan_write",
+ "nr_vmscan_immediate_reclaim",
+ "nr_dirtied",
+ "nr_written",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
"pswpout",
TEXTS_FOR_ZONES("pgalloc")
+ TEXTS_FOR_ZONES("allocstall")
+ TEXTS_FOR_ZONES("pgskip")
"pgfree",
"pgactivate",
"pgmajfault",
"pglazyfreed",
- TEXTS_FOR_ZONES("pgrefill")
- TEXTS_FOR_ZONES("pgsteal_kswapd")
- TEXTS_FOR_ZONES("pgsteal_direct")
- TEXTS_FOR_ZONES("pgscan_kswapd")
- TEXTS_FOR_ZONES("pgscan_direct")
+ "pgrefill",
+ "pgsteal_kswapd",
+ "pgsteal_direct",
+ "pgscan_kswapd",
+ "pgscan_direct",
"pgscan_direct_throttle",
#ifdef CONFIG_NUMA
"kswapd_low_wmark_hit_quickly",
"kswapd_high_wmark_hit_quickly",
"pageoutrun",
- "allocstall",
"pgrotated",
"thp_fault_fallback",
"thp_collapse_alloc",
"thp_collapse_alloc_failed",
+ "thp_file_alloc",
+ "thp_file_mapped",
"thp_split_page",
"thp_split_page_failed",
"thp_deferred_split_page",
if (!memmap_valid_within(pfn, page, zone))
continue;
+ if (page_zone(page) != zone)
+ continue;
+
mtype = get_pageblock_migratetype(page);
if (mtype < MIGRATE_TYPES)
block_end_pfn = min(block_end_pfn, end_pfn);
page = pfn_to_page(pfn);
- pageblock_mt = get_pfnblock_migratetype(page, pfn);
+ pageblock_mt = get_pageblock_migratetype(page);
for (; pfn < block_end_pfn; pfn++) {
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
+
+ if (page_zone(page) != zone)
+ continue;
+
if (PageBuddy(page)) {
pfn += (1UL << page_order(page)) - 1;
continue;
continue;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ continue;
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
.release = seq_release,
};
+static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
+{
+ int zid;
+
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ struct zone *compare = &pgdat->node_zones[zid];
+
+ if (populated_zone(compare))
+ return zone == compare;
+ }
+
+ /* The zone must be somewhere! */
+ WARN_ON_ONCE(1);
+ return false;
+}
+
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
struct zone *zone)
{
int i;
seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+ if (is_zone_first_populated(pgdat, zone)) {
+ seq_printf(m, "\n per-node stats");
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ seq_printf(m, "\n %-12s %lu",
+ vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+ node_page_state(pgdat, i));
+ }
+ }
seq_printf(m,
"\n pages free %lu"
"\n min %lu"
"\n low %lu"
"\n high %lu"
- "\n scanned %lu"
+ "\n node_scanned %lu"
"\n spanned %lu"
"\n present %lu"
"\n managed %lu",
min_wmark_pages(zone),
low_wmark_pages(zone),
high_wmark_pages(zone),
- zone_page_state(zone, NR_PAGES_SCANNED),
+ node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED),
zone->spanned_pages,
zone->present_pages,
zone->managed_pages);
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- seq_printf(m, "\n %-12s %lu", vmstat_text[i],
+ seq_printf(m, "\n %-12s %lu", vmstat_text[i],
zone_page_state(zone, i));
seq_printf(m,
#endif
}
seq_printf(m,
- "\n all_unreclaimable: %u"
- "\n start_pfn: %lu"
- "\n inactive_ratio: %u",
- !zone_reclaimable(zone),
+ "\n node_unreclaimable: %u"
+ "\n start_pfn: %lu"
+ "\n node_inactive_ratio: %u",
+ !pgdat_reclaimable(zone->zone_pgdat),
zone->zone_start_pfn,
- zone->inactive_ratio);
+ zone->zone_pgdat->inactive_ratio);
seq_putc(m, '\n');
}
if (*pos >= ARRAY_SIZE(vmstat_text))
return NULL;
stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
+ NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) +
NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
#ifdef CONFIG_VM_EVENT_COUNTERS
v[i] = global_page_state(i);
v += NR_VM_ZONE_STAT_ITEMS;
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ v[i] = global_node_page_state(i);
+ v += NR_VM_NODE_STAT_ITEMS;
+
global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
v + NR_DIRTY_THRESHOLD);
v += NR_VM_WRITEBACK_STAT_ITEMS;
{
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 struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
-static cpumask_var_t cpu_stat_off;
+
+#ifdef CONFIG_PROC_FS
+static void refresh_vm_stats(struct work_struct *work)
+{
+ refresh_cpu_vm_stats(true);
+}
+
+int vmstat_refresh(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ long val;
+ int err;
+ int i;
+
+ /*
+ * The regular update, every sysctl_stat_interval, may come later
+ * than expected: leaving a significant amount in per_cpu buckets.
+ * This is particularly misleading when checking a quantity of HUGE
+ * pages, immediately after running a test. /proc/sys/vm/stat_refresh,
+ * which can equally be echo'ed to or cat'ted from (by root),
+ * can be used to update the stats just before reading them.
+ *
+ * Oh, and since global_page_state() etc. are so careful to hide
+ * transiently negative values, report an error here if any of
+ * the stats is negative, so we know to go looking for imbalance.
+ */
+ err = schedule_on_each_cpu(refresh_vm_stats);
+ if (err)
+ return err;
+ for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
+ val = atomic_long_read(&vm_zone_stat[i]);
+ if (val < 0) {
+ switch (i) {
+ case NR_PAGES_SCANNED:
+ /*
+ * This is often seen to go negative in
+ * recent kernels, but not to go permanently
+ * negative. Whilst it would be nicer not to
+ * have exceptions, rooting them out would be
+ * another task, of rather low priority.
+ */
+ break;
+ default:
+ pr_warn("%s: %s %ld\n",
+ __func__, vmstat_text[i], val);
+ err = -EINVAL;
+ break;
+ }
+ }
+ }
+ if (err)
+ return err;
+ if (write)
+ *ppos += *lenp;
+ else
+ *lenp = 0;
+ return 0;
+}
+#endif /* CONFIG_PROC_FS */
static void vmstat_update(struct work_struct *w)
{
* Counters were updated so we expect more updates
* to occur in the future. Keep on running the
* update worker thread.
- * If we were marked on cpu_stat_off clear the flag
- * so that vmstat_shepherd doesn't schedule us again.
*/
- if (!cpumask_test_and_clear_cpu(smp_processor_id(),
- cpu_stat_off)) {
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+ queue_delayed_work_on(smp_processor_id(), vmstat_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
- }
- } else {
- /*
- * We did not update any counters so the app may be in
- * a mode where it does not cause counter updates.
- * We may be uselessly running vmstat_update.
- * Defer the checking for differentials to the
- * shepherd thread on a different processor.
- */
- cpumask_set_cpu(smp_processor_id(), cpu_stat_off);
}
}
return false;
}
+/*
+ * Switch off vmstat processing and then fold all the remaining differentials
+ * until the diffs stay at zero. The function is used by NOHZ and can only be
+ * invoked when tick processing is not active.
+ */
void quiet_vmstat(void)
{
if (system_state != SYSTEM_RUNNING)
return;
- /*
- * If we are already in hands of the shepherd then there
- * is nothing for us to do here.
- */
- if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
+ if (!delayed_work_pending(this_cpu_ptr(&vmstat_work)))
return;
if (!need_update(smp_processor_id()))
refresh_cpu_vm_stats(false);
}
-
/*
* Shepherd worker thread that checks the
* differentials of processors that have their worker
get_online_cpus();
/* Check processors whose vmstat worker threads have been disabled */
- for_each_cpu(cpu, cpu_stat_off) {
+ for_each_online_cpu(cpu) {
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
- if (need_update(cpu)) {
- if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
- queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
- } else {
- /*
- * Cancel the work if quiet_vmstat has put this
- * cpu on cpu_stat_off because the work item might
- * be still scheduled
- */
- cancel_delayed_work(dw);
- }
+ if (!delayed_work_pending(dw) && need_update(cpu))
+ queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
}
put_online_cpus();
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
vmstat_update);
- if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
- BUG();
- cpumask_copy(cpu_stat_off, cpu_online_mask);
-
vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
case CPU_ONLINE_FROZEN:
refresh_zone_stat_thresholds();
node_set_state(cpu_to_node(cpu), N_CPU);
- cpumask_set_cpu(cpu, cpu_stat_off);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
- cpumask_clear_cpu(cpu, cpu_stat_off);
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- cpumask_set_cpu(cpu, cpu_stat_off);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN: