// SPDX-License-Identifier: GPL-2.0-only/* *  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 <cl@gentwo.org> *  Copyright (C) 2008-2014 Christoph Lameter */#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/cpumask.h>#include <linux/vmstat.h>#include <linux/proc_fs.h>#include <linux/seq_file.h>#include <linux/debugfs.h>#include <linux/sched.h>#include <linux/math64.h>#include <linux/writeback.h>#include <linux/compaction.h>#include <linux/mm_inline.h>#include <linux/page_owner.h>#include <linux/sched/isolation.h> #include "internal.h" #ifdef CONFIG_PROC_FS#ifdef CONFIG_NUMA#define ENABLE_NUMA_STAT 1static int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; /* zero numa counters within a zone */static void zero_zone_numa_counters(struct zone *zone){	int item, cpu; 	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) {		atomic_long_set(&zone->vm_numa_event[item], 0);		for_each_online_cpu(cpu) {			per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item]						= 0;		}	}} /* zero numa counters of all the populated zones */static void zero_zones_numa_counters(void){	struct zone *zone; 	for_each_populated_zone(zone)		zero_zone_numa_counters(zone);} /* zero global numa counters */static void zero_global_numa_counters(void){	int item; 	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)		atomic_long_set(&vm_numa_event[item], 0);} static void invalid_numa_statistics(void){	zero_zones_numa_counters();	zero_global_numa_counters();} static DEFINE_MUTEX(vm_numa_stat_lock); static int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,		void *buffer, size_t *length, loff_t *ppos){	int ret, oldval; 	mutex_lock(&vm_numa_stat_lock);	if (write)		oldval = sysctl_vm_numa_stat;	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);	if (ret || !write)		goto out; 	if (oldval == sysctl_vm_numa_stat)		goto out;	else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) {		static_branch_enable(&vm_numa_stat_key);		pr_info("enable numa statistics\n");	} else {		static_branch_disable(&vm_numa_stat_key);		invalid_numa_statistics();		pr_info("disable numa statistics, and clear numa counters\n");	} out:	mutex_unlock(&vm_numa_stat_lock);	return ret;}#endif#endif /* CONFIG_PROC_FS */ #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){	cpus_read_lock();	sum_vm_events(ret);	cpus_read_unlock();}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_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;atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp;EXPORT_SYMBOL(vm_zone_stat);EXPORT_SYMBOL(vm_node_stat); #ifdef CONFIG_NUMAstatic void fold_vm_zone_numa_events(struct zone *zone){	unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, };	int cpu;	enum numa_stat_item item; 	for_each_online_cpu(cpu) {		struct per_cpu_zonestat *pzstats; 		pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu);		for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)			zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0);	} 	for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++)		zone_numa_event_add(zone_numa_events[item], zone, item);} void fold_vm_numa_events(void){	struct zone *zone; 	for_each_populated_zone(zone)		fold_vm_zone_numa_events(zone);}#endif #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(zone) >> (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 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) {			int pgdat_threshold; 			per_cpu_ptr(zone->per_cpu_zonestats, 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		 * 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_online_cpu(cpu)			per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold							= threshold;	}} /* * For use when we know that interrupts are disabled, * or when we know that preemption is disabled and that * particular counter cannot be updated from interrupt context. */void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,			   long delta){	struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats;	s8 __percpu *p = pcp->vm_stat_diff + item;	long x;	long t; 	/*	 * Accurate vmstat updates require a RMW. On !PREEMPT_RT kernels,	 * atomicity is provided by IRQs being disabled -- either explicitly	 * or via local_lock_irq. On PREEMPT_RT, local_lock_irq only disables	 * CPU migrations and preemption potentially corrupts a counter so	 * disable preemption.	 */	preempt_disable_nested(); 	x = delta + __this_cpu_read(*p); 	t = __this_cpu_read(pcp->stat_threshold); 	if (unlikely(abs(x) > t)) {		zone_page_state_add(x, zone, item);		x = 0;	}	__this_cpu_write(*p, x); 	preempt_enable_nested();}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; 	if (vmstat_item_in_bytes(item)) {		/*		 * Only cgroups use subpage accounting right now; at		 * the global level, these items still change in		 * multiples of whole pages. Store them as pages		 * internally to keep the per-cpu counters compact.		 */		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));		delta >>= PAGE_SHIFT;	} 	/* See __mod_zone_page_state() */	preempt_disable_nested(); 	x = delta + __this_cpu_read(*p); 	t = __this_cpu_read(pcp->stat_threshold); 	if (unlikely(abs(x) > t)) {		node_page_state_add(x, pgdat, item);		x = 0;	}	__this_cpu_write(*p, x); 	preempt_enable_nested();}EXPORT_SYMBOL(__mod_node_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_zonestat __percpu *pcp = zone->per_cpu_zonestats;	s8 __percpu *p = pcp->vm_stat_diff + item;	s8 v, t; 	/* See __mod_zone_page_state() */	preempt_disable_nested(); 	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);	} 	preempt_enable_nested();} 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; 	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); 	/* See __mod_zone_page_state() */	preempt_disable_nested(); 	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);	} 	preempt_enable_nested();} 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_zonestat __percpu *pcp = zone->per_cpu_zonestats;	s8 __percpu *p = pcp->vm_stat_diff + item;	s8 v, t; 	/* See __mod_zone_page_state() */	preempt_disable_nested(); 	v = __this_cpu_dec_return(*p);

Lines 1–500 of 2435. Load more