/* *  linux/mm/vmstat.c * *  Manages VM statistics *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds * *  zoned VM statistics *  Copyright (C) 2006 Silicon Graphics, Inc., *		Christoph Lameter <christoph@lameter.com> */#include <linux/fs.h>#include <linux/mm.h>#include <linux/err.h>#include <linux/module.h>#include <linux/slab.h>#include <linux/cpu.h>#include <linux/vmstat.h>#include <linux/sched.h>#include <linux/math64.h>#include <linux/writeback.h>#include <linux/compaction.h>#include <linux/mm_inline.h> #include "internal.h" #ifdef CONFIG_VM_EVENT_COUNTERSDEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};EXPORT_PER_CPU_SYMBOL(vm_event_states); static void sum_vm_events(unsigned long *ret){	int cpu;	int i; 	memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); 	for_each_online_cpu(cpu) {		struct vm_event_state *this = &per_cpu(vm_event_states, cpu); 		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)			ret[i] += this->event[i];	}} /* * Accumulate the vm event counters across all CPUs. * The result is unavoidably approximate - it can change * during and after execution of this function.*/void all_vm_events(unsigned long *ret){	get_online_cpus();	sum_vm_events(ret);	put_online_cpus();}EXPORT_SYMBOL_GPL(all_vm_events); /* * Fold the foreign cpu events into our own. * * This is adding to the events on one processor * but keeps the global counts constant. */void vm_events_fold_cpu(int cpu){	struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu);	int i; 	for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {		count_vm_events(i, fold_state->event[i]);		fold_state->event[i] = 0;	}} #endif /* CONFIG_VM_EVENT_COUNTERS */ /* * Manage combined zone based / global counters * * vm_stat contains the global counters */atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP int calculate_pressure_threshold(struct zone *zone){	int threshold;	int watermark_distance; 	/*	 * As vmstats are not up to date, there is drift between the estimated	 * and real values. For high thresholds and a high number of CPUs, it	 * is possible for the min watermark to be breached while the estimated	 * value looks fine. The pressure threshold is a reduced value such	 * that even the maximum amount of drift will not accidentally breach	 * the min watermark	 */	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);	threshold = max(1, (int)(watermark_distance / num_online_cpus())); 	/*	 * Maximum threshold is 125	 */	threshold = min(125, threshold); 	return threshold;} int calculate_normal_threshold(struct zone *zone){	int threshold;	int mem;	/* memory in 128 MB units */ 	/*	 * The threshold scales with the number of processors and the amount	 * of memory per zone. More memory means that we can defer updates for	 * longer, more processors could lead to more contention. 	 * fls() is used to have a cheap way of logarithmic scaling.	 *	 * Some sample thresholds:	 *	 * Threshold	Processors	(fls)	Zonesize	fls(mem+1)	 * ------------------------------------------------------------------	 * 8		1		1	0.9-1 GB	4	 * 16		2		2	0.9-1 GB	4	 * 20 		2		2	1-2 GB		5	 * 24		2		2	2-4 GB		6	 * 28		2		2	4-8 GB		7	 * 32		2		2	8-16 GB		8	 * 4		2		2	<128M		1	 * 30		4		3	2-4 GB		5	 * 48		4		3	8-16 GB		8	 * 32		8		4	1-2 GB		4	 * 32		8		4	0.9-1GB		4	 * 10		16		5	<128M		1	 * 40		16		5	900M		4	 * 70		64		7	2-4 GB		5	 * 84		64		7	4-8 GB		6	 * 108		512		9	4-8 GB		6	 * 125		1024		10	8-16 GB		8	 * 125		1024		10	16-32 GB	9	 */ 	mem = zone->managed_pages >> (27 - PAGE_SHIFT); 	threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); 	/*	 * Maximum threshold is 125	 */	threshold = min(125, threshold); 	return threshold;} /* * Refresh the thresholds for each zone. */void refresh_zone_stat_thresholds(void){	struct zone *zone;	int cpu;	int threshold; 	for_each_populated_zone(zone) {		unsigned long max_drift, tolerate_drift; 		threshold = calculate_normal_threshold(zone); 		for_each_online_cpu(cpu)			per_cpu_ptr(zone->pageset, cpu)->stat_threshold							= threshold; 		/*		 * Only set percpu_drift_mark if there is a danger that		 * NR_FREE_PAGES reports the low watermark is ok when in fact		 * the min watermark could be breached by an allocation		 */		tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone);		max_drift = num_online_cpus() * threshold;		if (max_drift > tolerate_drift)			zone->percpu_drift_mark = high_wmark_pages(zone) +					max_drift;	}} void set_pgdat_percpu_threshold(pg_data_t *pgdat,				int (*calculate_pressure)(struct zone *)){	struct zone *zone;	int cpu;	int threshold;	int i; 	for (i = 0; i < pgdat->nr_zones; i++) {		zone = &pgdat->node_zones[i];		if (!zone->percpu_drift_mark)			continue; 		threshold = (*calculate_pressure)(zone);		for_each_possible_cpu(cpu)			per_cpu_ptr(zone->pageset, cpu)->stat_threshold							= threshold;	}} /* * For use when we know that interrupts are disabled. */void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,				int delta){	struct per_cpu_pageset __percpu *pcp = zone->pageset;	s8 __percpu *p = pcp->vm_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)) {		zone_page_state_add(x, zone, item);		x = 0;	}	__this_cpu_write(*p, x);}EXPORT_SYMBOL(__mod_zone_page_state); /* * Optimized increment and decrement functions. * * These are only for a single page and therefore can take a struct page * * argument instead of struct zone *. This allows the inclusion of the code * generated for page_zone(page) into the optimized functions. * * No overflow check is necessary and therefore the differential can be * incremented or decremented in place which may allow the compilers to * generate better code. * The increment or decrement is known and therefore one boundary check can * be omitted. * * NOTE: These functions are very performance sensitive. Change only * with care. * * Some processors have inc/dec instructions that are atomic vs an interrupt. * However, the code must first determine the differential location in a zone * based on the processor number and then inc/dec the counter. There is no * guarantee without disabling preemption that the processor will not change * in between and therefore the atomicity vs. interrupt cannot be exploited * in a useful way here. */void __inc_zone_state(struct zone *zone, enum zone_stat_item item){	struct per_cpu_pageset __percpu *pcp = zone->pageset;	s8 __percpu *p = pcp->vm_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; 		zone_page_state_add(v + overstep, zone, 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 __dec_zone_state(struct zone *zone, enum zone_stat_item item){	struct per_cpu_pageset __percpu *pcp = zone->pageset;	s8 __percpu *p = pcp->vm_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; 		zone_page_state_add(v - overstep, zone, 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); #ifdef CONFIG_HAVE_CMPXCHG_LOCAL/* * If we have cmpxchg_local support then we do not need to incur the overhead * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. * * mod_state() modifies the zone counter state through atomic per cpu * operations. * * Overstep mode specifies how overstep should handled: *     0       No overstepping *     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){	struct per_cpu_pageset __percpu *pcp = zone->pageset;	s8 __percpu *p = pcp->vm_stat_diff + item;	long o, n, t, z; 	do {		z = 0;  /* overflow to zone 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 zone.		 */		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 zone counters */			z = n + os;			n = -os;		}	} while (this_cpu_cmpxchg(*p, o, n) != o); 	if (z)		zone_page_state_add(z, zone, item);} void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,					int delta){	mod_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);}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);}EXPORT_SYMBOL(dec_zone_page_state);#else/* * Use interrupt disable to serialize counter updates */void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,					int delta){	unsigned long flags; 	local_irq_save(flags);	__mod_zone_page_state(zone, item, delta);	local_irq_restore(flags);}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;	struct zone *zone; 	zone = page_zone(page);	local_irq_save(flags);	__inc_zone_state(zone, item);	local_irq_restore(flags);}EXPORT_SYMBOL(inc_zone_page_state); void dec_zone_page_state(struct page *page, enum zone_stat_item item){	unsigned long flags; 	local_irq_save(flags);	__dec_zone_page_state(page, item);	local_irq_restore(flags);}EXPORT_SYMBOL(dec_zone_page_state);#endif static inline void fold_diff(int *diff){	int i; 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)		if (diff[i])			atomic_long_add(diff[i], &vm_stat[i]);} /* * Update the zone counters for the current 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. */static void refresh_cpu_vm_stats(void){	struct zone *zone;	int i;	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; 	for_each_populated_zone(zone) {		struct per_cpu_pageset __percpu *p = zone->pageset; 		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {			int v; 			v = this_cpu_xchg(p->vm_stat_diff[i], 0);			if (v) { 				atomic_long_add(v, &zone->vm_stat[i]);				global_diff[i] += v;#ifdef CONFIG_NUMA				/* 3 seconds idle till flush */				__this_cpu_write(p->expire, 3);#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) ||			       !__this_cpu_read(p->pcp.count))			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_read(p->pcp.count))			drain_zone_pages(zone, __this_cpu_ptr(&p->pcp));#endif	}	fold_diff(global_diff);} /* * Fold the data for an offline cpu into the global array. * There cannot be any access by the offline cpu and therefore

Lines 1–500 of 1473. Load more