* particular counter cannot be updated from interrupt context.
*/
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
- int delta)
+ long delta)
{
struct per_cpu_pageset __percpu *pcp = zone->pageset;
s8 __percpu *p = pcp->vm_stat_diff + item;
* 1 Overstepping half of threshold
* -1 Overstepping minus half of threshold
*/
-static inline void mod_state(struct zone *zone,
- enum zone_stat_item item, int delta, int overstep_mode)
+static inline void mod_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,
- int delta)
+ long delta)
{
mod_state(zone, item, delta, 0);
}
* Use interrupt disable to serialize counter updates
*/
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
- int delta)
+ long delta)
{
unsigned long flags;
*
* The function returns the number of global counters updated.
*/
-static int refresh_cpu_vm_stats(void)
+static int refresh_cpu_vm_stats(bool do_pagesets)
{
struct zone *zone;
int i;
#endif
}
}
- cond_resched();
#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 (!__this_cpu_read(p->expire) ||
+ if (do_pagesets) {
+ cond_resched();
+ /*
+ * 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 (!__this_cpu_read(p->expire) ||
!__this_cpu_read(p->pcp.count))
- continue;
+ continue;
- /*
- * We never drain zones local to this processor.
- */
- if (zone_to_nid(zone) == numa_node_id()) {
- __this_cpu_write(p->expire, 0);
- continue;
- }
+ /*
+ * We never drain zones local to this processor.
+ */
+ if (zone_to_nid(zone) == numa_node_id()) {
+ __this_cpu_write(p->expire, 0);
+ continue;
+ }
- if (__this_cpu_dec_return(p->expire))
- continue;
+ if (__this_cpu_dec_return(p->expire))
+ continue;
- if (__this_cpu_read(p->pcp.count)) {
- drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
- changes++;
+ if (__this_cpu_read(p->pcp.count)) {
+ drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
+ changes++;
+ }
}
#endif
}
"nr_slab_unreclaimable",
"nr_page_table_pages",
"nr_kernel_stack",
+ "nr_overhead",
"nr_unstable",
"nr_bounce",
"nr_vmscan_write",
#endif
#endif /* CONFIG_MEMORY_BALLOON */
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
"nr_tlb_remote_flush",
"nr_tlb_remote_flush_received",
-#endif /* CONFIG_SMP */
"nr_tlb_local_flush_all",
"nr_tlb_local_flush_one",
#endif /* CONFIG_DEBUG_TLBFLUSH */
#ifdef CONFIG_DEBUG_VM_VMACACHE
"vmacache_find_calls",
"vmacache_find_hits",
- "vmacache_full_flushes",
#endif
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
continue;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ continue;
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
unsigned long *l = arg;
unsigned long off = l - (unsigned long *)m->private;
- seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
+ seq_puts(m, vmstat_text[off]);
+ seq_put_decimal_ull(m, ' ', *l);
+ seq_putc(m, '\n');
return 0;
}
static void vmstat_update(struct work_struct *w)
{
- if (refresh_cpu_vm_stats()) {
+ if (refresh_cpu_vm_stats(true)) {
/*
* 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.
*/
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
- this_cpu_ptr(&vmstat_work),
- round_jiffies_relative(sysctl_stat_interval));
+ if (!cpumask_test_and_clear_cpu(smp_processor_id(),
+ cpu_stat_off)) {
+ 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
* Defer the checking for differentials to the
* shepherd thread on a different processor.
*/
- int r;
- /*
- * Shepherd work thread does not race since it never
- * changes the bit if its zero but the cpu
- * online / off line code may race if
- * worker threads are still allowed during
- * shutdown / startup.
- */
- r = cpumask_test_and_set_cpu(smp_processor_id(),
- cpu_stat_off);
- VM_BUG_ON(r);
+ cpumask_set_cpu(smp_processor_id(), cpu_stat_off);
}
}
/*
+ * 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.
+ */
+/*
* Check if the diffs for a certain cpu indicate that
* an update is needed.
*/
return false;
}
+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))
+ return;
+
+ if (!need_update(smp_processor_id()))
+ return;
+
+ /*
+ * Just refresh counters and do not care about the pending delayed
+ * vmstat_update. It doesn't fire that often to matter and canceling
+ * it would be too expensive from this path.
+ * vmstat_shepherd will take care about that for us.
+ */
+ refresh_cpu_vm_stats(false);
+}
+
/*
* Shepherd worker thread that checks the
*/
static void vmstat_shepherd(struct work_struct *w);
-static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);
+static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd);
static void vmstat_shepherd(struct work_struct *w)
{
get_online_cpus();
/* Check processors whose vmstat worker threads have been disabled */
- for_each_cpu(cpu, cpu_stat_off)
- if (need_update(cpu) &&
- cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
-
- queue_delayed_work_on(cpu, vmstat_wq,
- &per_cpu(vmstat_work, cpu), 0);
-
+ for_each_cpu(cpu, cpu_stat_off) {
+ 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);
+ }
+ }
put_online_cpus();
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
-
}
static void __init start_shepherd_timer(void)
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));
}
start_shepherd_timer();
cpu_notifier_register_done();
- vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
#endif
#ifdef CONFIG_PROC_FS
proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
- proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
+ proc_create("pagetypeinfo", 0400, NULL, &pagetypeinfo_file_ops);
proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
#endif
OSDN Git Service
