vmstat.c 42.1 KB
Newer Older
1 2 3 4 5
/*
 *  linux/mm/vmstat.c
 *
 *  Manages VM statistics
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
6 7 8 9
 *
 *  zoned VM statistics
 *  Copyright (C) 2006 Silicon Graphics, Inc.,
 *		Christoph Lameter <christoph@lameter.com>
10
 *  Copyright (C) 2008-2014 Christoph Lameter
11
 */
12
#include <linux/fs.h>
13
#include <linux/mm.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
14
#include <linux/err.h>
15
#include <linux/module.h>
16
#include <linux/slab.h>
17
#include <linux/cpu.h>
18
#include <linux/cpumask.h>
Adrian Bunk's avatar
Adrian Bunk committed
19
#include <linux/vmstat.h>
20 21 22
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
23
#include <linux/sched.h>
24
#include <linux/math64.h>
25
#include <linux/writeback.h>
26
#include <linux/compaction.h>
27
#include <linux/mm_inline.h>
28 29
#include <linux/page_ext.h>
#include <linux/page_owner.h>
30 31

#include "internal.h"
32

33 34 35 36
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

37
static void sum_vm_events(unsigned long *ret)
38
{
Christoph Lameter's avatar
Christoph Lameter committed
39
	int cpu;
40 41 42 43
	int i;

	memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));

44
	for_each_online_cpu(cpu) {
45 46 47 48 49 50 51 52 53 54 55 56 57 58
		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)
{
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
59
	get_online_cpus();
60
	sum_vm_events(ret);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
61
	put_online_cpus();
62
}
63
EXPORT_SYMBOL_GPL(all_vm_events);
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83

/*
 * 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 */

84 85 86 87 88
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
89
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
90 91 92 93
EXPORT_SYMBOL(vm_stat);

#ifdef CONFIG_SMP

94
int calculate_pressure_threshold(struct zone *zone)
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
{
	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;
}

118
int calculate_normal_threshold(struct zone *zone)
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152
{
	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
	 */

153
	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
154 155 156 157 158 159 160 161 162 163

	threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem));

	/*
	 * Maximum threshold is 125
	 */
	threshold = min(125, threshold);

	return threshold;
}
164 165

/*
166
 * Refresh the thresholds for each zone.
167
 */
168
void refresh_zone_stat_thresholds(void)
169
{
170 171 172 173
	struct zone *zone;
	int cpu;
	int threshold;

174
	for_each_populated_zone(zone) {
175 176
		unsigned long max_drift, tolerate_drift;

177
		threshold = calculate_normal_threshold(zone);
178 179

		for_each_online_cpu(cpu)
180 181
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
182 183 184 185 186 187 188 189 190 191 192

		/*
		 * 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;
193
	}
194 195
}

196 197
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *))
198 199 200 201 202 203 204 205 206 207 208
{
	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;

209
		threshold = (*calculate_pressure)(zone);
210
		for_each_online_cpu(cpu)
211 212 213 214 215
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
}

216
/*
217 218 219
 * 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.
220 221
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
222
			   long delta)
223
{
224 225
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
226
	long x;
227 228 229
	long t;

	x = delta + __this_cpu_read(*p);
230

231
	t = __this_cpu_read(pcp->stat_threshold);
232

233
	if (unlikely(x > t || x < -t)) {
234 235 236
		zone_page_state_add(x, zone, item);
		x = 0;
	}
237
	__this_cpu_write(*p, x);
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
}
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.
 *
254 255 256
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
257 258 259 260 261 262 263
 * 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.
 */
264
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
265
{
266 267 268
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
269

270
	v = __this_cpu_inc_return(*p);
271 272 273
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;
274

275 276
		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
277 278
	}
}
279 280 281 282 283

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
284 285
EXPORT_SYMBOL(__inc_zone_page_state);

286
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
287
{
288 289 290
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
291

292
	v = __this_cpu_dec_return(*p);
293 294 295
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;
296

297 298
		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
299 300
	}
}
301 302 303 304 305

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
306 307
EXPORT_SYMBOL(__dec_zone_page_state);

308
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
309 310 311 312 313 314 315 316 317 318 319 320
/*
 * 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
*/
321 322
static inline void mod_state(struct zone *zone, enum zone_stat_item item,
			     long delta, int overstep_mode)
323 324 325 326 327 328 329 330 331 332 333
{
	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
334 335 336 337 338 339
		 * 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.
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
		 */
		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,
360
			 long delta)
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386
{
	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,
387
			 long delta)
388 389 390 391 392 393 394 395 396
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_zone_page_state(zone, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_zone_page_state);

397 398 399 400 401 402 403 404 405
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);
}

406 407 408 409 410 411 412
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);
413
	__inc_zone_state(zone, item);
414 415 416 417 418 419 420 421 422
	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);
423
	__dec_zone_page_state(page, item);
424 425 426
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
427
#endif
428

429 430 431 432 433 434

/*
 * Fold a differential into the global counters.
 * Returns the number of counters updated.
 */
static int fold_diff(int *diff)
Christoph Lameter's avatar
Christoph Lameter committed
435 436
{
	int i;
437
	int changes = 0;
Christoph Lameter's avatar
Christoph Lameter committed
438 439

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
440
		if (diff[i]) {
Christoph Lameter's avatar
Christoph Lameter committed
441
			atomic_long_add(diff[i], &vm_stat[i]);
442 443 444
			changes++;
	}
	return changes;
Christoph Lameter's avatar
Christoph Lameter committed
445 446
}

447
/*
448
 * Update the zone counters for the current cpu.
449
 *
450 451 452 453 454 455 456 457 458 459
 * 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.
460 461
 *
 * The function returns the number of global counters updated.
462
 */
463
static int refresh_cpu_vm_stats(bool do_pagesets)
464 465 466
{
	struct zone *zone;
	int i;
467
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
468
	int changes = 0;
469

470
	for_each_populated_zone(zone) {
471
		struct per_cpu_pageset __percpu *p = zone->pageset;
472

473 474
		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
			int v;
475

476 477
			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
			if (v) {
478 479 480

				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
481 482
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
483
				__this_cpu_write(p->expire, 3);
484
#endif
485
			}
486
		}
487
#ifdef CONFIG_NUMA
488 489 490 491 492 493 494 495 496 497
		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) ||
498
			       !__this_cpu_read(p->pcp.count))
499
				continue;
500

501 502 503 504 505 506 507
			/*
			 * We never drain zones local to this processor.
			 */
			if (zone_to_nid(zone) == numa_node_id()) {
				__this_cpu_write(p->expire, 0);
				continue;
			}
508

509 510
			if (__this_cpu_dec_return(p->expire))
				continue;
511

512 513 514 515
			if (__this_cpu_read(p->pcp.count)) {
				drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
				changes++;
			}
516
		}
517
#endif
518
	}
519 520
	changes += fold_diff(global_diff);
	return changes;
521 522
}

523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549
/*
 * Fold the data for an offline cpu into the global array.
 * There cannot be any access by the offline cpu and therefore
 * synchronization is simplified.
 */
void cpu_vm_stats_fold(int cpu)
{
	struct zone *zone;
	int i;
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *p;

		p = per_cpu_ptr(zone->pageset, cpu);

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
			if (p->vm_stat_diff[i]) {
				int v;

				v = p->vm_stat_diff[i];
				p->vm_stat_diff[i] = 0;
				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
			}
	}

Christoph Lameter's avatar
Christoph Lameter committed
550
	fold_diff(global_diff);
551 552
}

553 554 555 556
/*
 * this is only called if !populated_zone(zone), which implies no other users of
 * pset->vm_stat_diff[] exsist.
 */
557 558 559 560 561 562 563 564 565 566 567 568
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
{
	int i;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (pset->vm_stat_diff[i]) {
			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]);
		}
}
569 570
#endif

571
#ifdef CONFIG_NUMA
572 573 574 575 576 577
/*
 * Determine the per node value of a stat item.
 */
unsigned long node_page_state(int node, enum zone_stat_item item)
{
	struct zone *zones = NODE_DATA(node)->node_zones;
578 579
	int i;
	unsigned long count = 0;
580

581 582 583 584
	for (i = 0; i < MAX_NR_ZONES; i++)
		count += zone_page_state(zones + i, item);

	return count;
585 586
}

587 588
#endif

589
#ifdef CONFIG_COMPACTION
590

591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
struct contig_page_info {
	unsigned long free_pages;
	unsigned long free_blocks_total;
	unsigned long free_blocks_suitable;
};

/*
 * Calculate the number of free pages in a zone, how many contiguous
 * pages are free and how many are large enough to satisfy an allocation of
 * the target size. Note that this function makes no attempt to estimate
 * how many suitable free blocks there *might* be if MOVABLE pages were
 * migrated. Calculating that is possible, but expensive and can be
 * figured out from userspace
 */
static void fill_contig_page_info(struct zone *zone,
				unsigned int suitable_order,
				struct contig_page_info *info)
{
	unsigned int order;

	info->free_pages = 0;
	info->free_blocks_total = 0;
	info->free_blocks_suitable = 0;

	for (order = 0; order < MAX_ORDER; order++) {
		unsigned long blocks;

		/* Count number of free blocks */
		blocks = zone->free_area[order].nr_free;
		info->free_blocks_total += blocks;

		/* Count free base pages */
		info->free_pages += blocks << order;

		/* Count the suitable free blocks */
		if (order >= suitable_order)
			info->free_blocks_suitable += blocks <<
						(order - suitable_order);
	}
}
631 632 633 634 635 636 637 638

/*
 * A fragmentation index only makes sense if an allocation of a requested
 * size would fail. If that is true, the fragmentation index indicates
 * whether external fragmentation or a lack of memory was the problem.
 * The value can be used to determine if page reclaim or compaction
 * should be used
 */
639
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
{
	unsigned long requested = 1UL << order;

	if (!info->free_blocks_total)
		return 0;

	/* Fragmentation index only makes sense when a request would fail */
	if (info->free_blocks_suitable)
		return -1000;

	/*
	 * Index is between 0 and 1 so return within 3 decimal places
	 *
	 * 0 => allocation would fail due to lack of memory
	 * 1 => allocation would fail due to fragmentation
	 */
	return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
}
658 659 660 661 662 663 664 665 666

/* Same as __fragmentation index but allocs contig_page_info on stack */
int fragmentation_index(struct zone *zone, unsigned int order)
{
	struct contig_page_info info;

	fill_contig_page_info(zone, order, &info);
	return __fragmentation_index(order, &info);
}
667 668
#endif

669
#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691
#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_DMA32(xx)
#endif

#ifdef CONFIG_HIGHMEM
#define TEXT_FOR_HIGHMEM(xx) xx "_high",
#else
#define TEXT_FOR_HIGHMEM(xx)
#endif

#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
					TEXT_FOR_HIGHMEM(xx) xx "_movable",

const char * const vmstat_text[] = {
692
	/* enum zone_stat_item countes */
693
	"nr_free_pages",
694
	"nr_alloc_batch",
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
	"nr_unevictable",
	"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",
713
	"nr_vmscan_immediate_reclaim",
714 715 716 717 718 719
	"nr_writeback_temp",
	"nr_isolated_anon",
	"nr_isolated_file",
	"nr_shmem",
	"nr_dirtied",
	"nr_written",
720
	"nr_pages_scanned",
721 722 723 724 725 726 727 728 729

#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif
730 731
	"workingset_refault",
	"workingset_activate",
732
	"workingset_nodereclaim",
733
	"nr_anon_transparent_hugepages",
734
	"nr_free_cma",
735 736

	/* enum writeback_stat_item counters */
737 738 739 740
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",

#ifdef CONFIG_VM_EVENT_COUNTERS
741
	/* enum vm_event_item counters */
742 743 744 745 746 747 748 749 750 751 752 753 754
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	TEXTS_FOR_ZONES("pgalloc")

	"pgfree",
	"pgactivate",
	"pgdeactivate",

	"pgfault",
	"pgmajfault",
Minchan Kim's avatar
Minchan Kim committed
755
	"pglazyfreed",
756 757

	TEXTS_FOR_ZONES("pgrefill")
758 759
	TEXTS_FOR_ZONES("pgsteal_kswapd")
	TEXTS_FOR_ZONES("pgsteal_direct")
760 761
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
762
	"pgscan_direct_throttle",
763 764 765 766 767 768 769 770 771 772 773 774 775 776

#ifdef CONFIG_NUMA
	"zone_reclaim_failed",
#endif
	"pginodesteal",
	"slabs_scanned",
	"kswapd_inodesteal",
	"kswapd_low_wmark_hit_quickly",
	"kswapd_high_wmark_hit_quickly",
	"pageoutrun",
	"allocstall",

	"pgrotated",

777 778 779
	"drop_pagecache",
	"drop_slab",

780 781
#ifdef CONFIG_NUMA_BALANCING
	"numa_pte_updates",
782
	"numa_huge_pte_updates",
783 784 785 786
	"numa_hint_faults",
	"numa_hint_faults_local",
	"numa_pages_migrated",
#endif
787 788 789 790
#ifdef CONFIG_MIGRATION
	"pgmigrate_success",
	"pgmigrate_fail",
#endif
791
#ifdef CONFIG_COMPACTION
792 793 794
	"compact_migrate_scanned",
	"compact_free_scanned",
	"compact_isolated",
795 796 797
	"compact_stall",
	"compact_fail",
	"compact_success",
798
	"compact_daemon_wake",
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
#endif

#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	"thp_fault_alloc",
	"thp_fault_fallback",
	"thp_collapse_alloc",
	"thp_collapse_alloc_failed",
818 819
	"thp_split_page",
	"thp_split_page_failed",
820
	"thp_deferred_split_page",
821
	"thp_split_pmd",
822 823
	"thp_zero_page_alloc",
	"thp_zero_page_alloc_failed",
824
#endif
825 826 827 828 829 830 831
#ifdef CONFIG_MEMORY_BALLOON
	"balloon_inflate",
	"balloon_deflate",
#ifdef CONFIG_BALLOON_COMPACTION
	"balloon_migrate",
#endif
#endif /* CONFIG_MEMORY_BALLOON */
832
#ifdef CONFIG_DEBUG_TLBFLUSH
833
#ifdef CONFIG_SMP
Dave Hansen's avatar
Dave Hansen committed
834 835
	"nr_tlb_remote_flush",
	"nr_tlb_remote_flush_received",
836
#endif /* CONFIG_SMP */
Dave Hansen's avatar
Dave Hansen committed
837 838
	"nr_tlb_local_flush_all",
	"nr_tlb_local_flush_one",
839
#endif /* CONFIG_DEBUG_TLBFLUSH */
840

Davidlohr Bueso's avatar
Davidlohr Bueso committed
841 842 843
#ifdef CONFIG_DEBUG_VM_VMACACHE
	"vmacache_find_calls",
	"vmacache_find_hits",
844
	"vmacache_full_flushes",
Davidlohr Bueso's avatar
Davidlohr Bueso committed
845
#endif
846 847
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
848
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
849 850


851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896
#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \
     defined(CONFIG_PROC_FS)
static void *frag_start(struct seq_file *m, loff_t *pos)
{
	pg_data_t *pgdat;
	loff_t node = *pos;

	for (pgdat = first_online_pgdat();
	     pgdat && node;
	     pgdat = next_online_pgdat(pgdat))
		--node;

	return pgdat;
}

static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	(*pos)++;
	return next_online_pgdat(pgdat);
}

static void frag_stop(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 *))
{
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!populated_zone(zone))
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		print(m, pgdat, zone);
		spin_unlock_irqrestore(&zone->lock, flags);
	}
}
#endif

897
#ifdef CONFIG_PROC_FS
898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939
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);
		}
940 941
		seq_putc(m, '\n');
	}
942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
}

/* 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;
967
	unsigned long end_pfn = zone_end_pfn(zone);
968 969 970 971 972 973 974 975 976
	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);
977 978 979

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
980
			continue;
981

982 983 984
		if (page_zone(page) != zone)
			continue;

985 986
		mtype = get_pageblock_migratetype(page);

987 988
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
	}

	/* 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;
}

1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
#ifdef CONFIG_PAGE_OWNER
static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
							pg_data_t *pgdat,
							struct zone *zone)
{
	struct page *page;
	struct page_ext *page_ext;
	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
	unsigned long end_pfn = pfn + zone->spanned_pages;
	unsigned long count[MIGRATE_TYPES] = { 0, };
	int pageblock_mt, page_mt;
	int i;

	/* Scan block by block. First and last block may be incomplete */
	pfn = zone->zone_start_pfn;

	/*
	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
	 * a zone boundary, it will be double counted between zones. This does
	 * not matter as the mixed block count will still be correct
	 */
	for (; pfn < end_pfn; ) {
		if (!pfn_valid(pfn)) {
			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
			continue;
		}

		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		page = pfn_to_page(pfn);
1044
		pageblock_mt = get_pageblock_migratetype(page);
1045 1046 1047 1048 1049 1050

		for (; pfn < block_end_pfn; pfn++) {
			if (!pfn_valid_within(pfn))
				continue;

			page = pfn_to_page(pfn);
1051 1052 1053 1054

			if (page_zone(page) != zone)
				continue;

1055 1056 1057 1058 1059 1060 1061 1062 1063
			if (PageBuddy(page)) {
				pfn += (1UL << page_order(page)) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);
1064 1065
			if (unlikely(!page_ext))
				continue;
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102

			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
				continue;

			page_mt = gfpflags_to_migratetype(page_ext->gfp_mask);
			if (pageblock_mt != page_mt) {
				if (is_migrate_cma(pageblock_mt))
					count[MIGRATE_MOVABLE]++;
				else
					count[pageblock_mt]++;

				pfn = block_end_pfn;
				break;
			}
			pfn += (1UL << page_ext->order) - 1;
		}
	}

	/* Print counts */
	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
	for (i = 0; i < MIGRATE_TYPES; i++)
		seq_printf(m, "%12lu ", count[i]);
	seq_putc(m, '\n');
}
#endif /* CONFIG_PAGE_OWNER */

/*
 * Print out the number of pageblocks for each migratetype that contain pages
 * of other types. This gives an indication of how well fallbacks are being
 * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
 * to determine what is going on
 */
static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
{
#ifdef CONFIG_PAGE_OWNER
	int mtype;

1103
	if (!static_branch_unlikely(&page_owner_inited))
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
		return;

	drain_all_pages(NULL);

	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
	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_showmixedcount_print);
#endif /* CONFIG_PAGE_OWNER */
}

1117 1118 1119 1120 1121 1122 1123 1124
/*
 * 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;

1125
	/* check memoryless node */
1126
	if (!node_state(pgdat->node_id, N_MEMORY))
1127 1128
		return 0;

1129 1130 1131 1132 1133
	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);
1134
	pagetypeinfo_showmixedcount(m, pgdat);
1135

1136 1137 1138
	return 0;
}

1139
static const struct seq_operations fragmentation_op = {
1140 1141 1142 1143 1144 1145
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
static int fragmentation_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &fragmentation_op);
}

static const struct file_operations fragmentation_file_operations = {
	.open		= fragmentation_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

1158
static const struct seq_operations pagetypeinfo_op = {
1159 1160 1161 1162 1163 1164
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
static int pagetypeinfo_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &pagetypeinfo_op);
}

static const struct file_operations pagetypeinfo_file_ops = {
	.open		= pagetypeinfo_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

1177 1178
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
1179
{
1180 1181 1182 1183 1184 1185 1186
	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"
1187
		   "\n        scanned  %lu"
1188
		   "\n        spanned  %lu"
1189 1190
		   "\n        present  %lu"
		   "\n        managed  %lu",
1191
		   zone_page_state(zone, NR_FREE_PAGES),
1192 1193 1194
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
1195
		   zone_page_state(zone, NR_PAGES_SCANNED),
1196
		   zone->spanned_pages,
1197 1198
		   zone->present_pages,
		   zone->managed_pages);
1199 1200 1201 1202 1203 1204

	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,
1205
		   "\n        protection: (%ld",
1206 1207
		   zone->lowmem_reserve[0]);
	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
1208
		seq_printf(m, ", %ld", zone->lowmem_reserve[i]);
1209 1210 1211 1212 1213 1214
	seq_printf(m,
		   ")"
		   "\n  pagesets");
	for_each_online_cpu(i) {
		struct per_cpu_pageset *pageset;

1215
		pageset = per_cpu_ptr(zone->pageset, i);
1216 1217 1218 1219 1220 1221 1222 1223 1224
		seq_printf(m,
			   "\n    cpu: %i"
			   "\n              count: %i"
			   "\n              high:  %i"
			   "\n              batch: %i",
			   i,
			   pageset->pcp.count,
			   pageset->pcp.high,
			   pageset->pcp.batch);
1225
#ifdef CONFIG_SMP
1226 1227
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
1228
#endif
1229
	}
1230 1231
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
1232 1233
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
1234
		   !zone_reclaimable(zone),
1235 1236
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246
	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);
1247 1248 1249
	return 0;
}

1250
static const struct seq_operations zoneinfo_op = {
1251 1252 1253 1254 1255 1256 1257
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
static int zoneinfo_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &zoneinfo_op);
}

static const struct file_operations proc_zoneinfo_file_operations = {
	.open		= zoneinfo_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

1270 1271 1272 1273 1274 1275
enum writeback_stat_item {
	NR_DIRTY_THRESHOLD,
	NR_DIRTY_BG_THRESHOLD,
	NR_VM_WRITEBACK_STAT_ITEMS,
};

1276 1277
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
1278
	unsigned long *v;
1279
	int i, stat_items_size;
1280 1281 1282

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
1283 1284
	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
1285

1286
#ifdef CONFIG_VM_EVENT_COUNTERS
1287
	stat_items_size += sizeof(struct vm_event_state);
1288
#endif
1289 1290

	v = kmalloc(stat_items_size, GFP_KERNEL);
1291 1292
	m->private = v;
	if (!v)
1293
		return ERR_PTR(-ENOMEM);
1294 1295
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
1296 1297 1298 1299 1300 1301
	v += NR_VM_ZONE_STAT_ITEMS;

	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
			    v + NR_DIRTY_THRESHOLD);
	v += NR_VM_WRITEBACK_STAT_ITEMS;

1302
#ifdef CONFIG_VM_EVENT_COUNTERS
1303 1304 1305
	all_vm_events(v);
	v[PGPGIN] /= 2;		/* sectors -> kbytes */
	v[PGPGOUT] /= 2;
1306
#endif
1307
	return (unsigned long *)m->private + *pos;
1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332
}

static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
{
	(*pos)++;
	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	return (unsigned long *)m->private + *pos;
}

static int vmstat_show(struct seq_file *m, void *arg)
{
	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 void vmstat_stop(struct seq_file *m, void *arg)
{
	kfree(m->private);
	m->private = NULL;
}

1333
static const struct seq_operations vmstat_op = {
1334 1335 1336 1337 1338 1339
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350
static int vmstat_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &vmstat_op);
}

static const struct file_operations proc_vmstat_file_operations = {
	.open		= vmstat_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};
1351 1352
#endif /* CONFIG_PROC_FS */

1353
#ifdef CONFIG_SMP
1354
static struct workqueue_struct *vmstat_wq;
1355
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
1356
int sysctl_stat_interval __read_mostly = HZ;
1357

1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
#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_stat[i]);
		if (val < 0) {
			switch (i) {
			case NR_ALLOC_BATCH:
			case NR_PAGES_SCANNED:
				/*
				 * These are 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 */

1418 1419
static void vmstat_update(struct work_struct *w)
{
1420
	if (refresh_cpu_vm_stats(true)) {
1421 1422 1423 1424 1425
		/*
		 * Counters were updated so we expect more updates
		 * to occur in the future. Keep on running the
		 * update worker thread.
		 */
1426
		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
1427 1428
				this_cpu_ptr(&vmstat_work),
				round_jiffies_relative(sysctl_stat_interval));
1429 1430 1431
	}
}

1432 1433 1434 1435 1436
/*
 * 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.
 */
1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459
/*
 * Check if the diffs for a certain cpu indicate that
 * an update is needed.
 */
static bool need_update(int cpu)
{
	struct zone *zone;

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);

		BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
		/*
		 * The fast way of checking if there are any vmstat diffs.
		 * This works because the diffs are byte sized items.
		 */
		if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS))
			return true;

	}
	return false;
}

1460 1461 1462 1463 1464
/*
 * 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.
 */
1465 1466 1467 1468 1469
void quiet_vmstat(void)
{
	if (system_state != SYSTEM_RUNNING)
		return;

1470
	if (!delayed_work_pending(this_cpu_ptr(&vmstat_work)))
1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484
		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);
}

1485 1486 1487 1488 1489 1490 1491 1492
/*
 * Shepherd worker thread that checks the
 * differentials of processors that have their worker
 * threads for vm statistics updates disabled because of
 * inactivity.
 */
static void vmstat_shepherd(struct work_struct *w);

1493
static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd);
1494 1495 1496 1497 1498 1499 1500

static void vmstat_shepherd(struct work_struct *w)
{
	int cpu;

	get_online_cpus();
	/* Check processors whose vmstat worker threads have been disabled */
1501
	for_each_online_cpu(cpu) {
1502
		struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
1503

1504 1505
		if (!delayed_work_pending(dw) && need_update(cpu))
			queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
1506
	}
1507 1508 1509
	put_online_cpus();

	schedule_delayed_work(&shepherd,
1510
		round_jiffies_relative(sysctl_stat_interval));
1511 1512
}

1513
static void __init start_shepherd_timer(void)
1514
{
1515 1516 1517
	int cpu;

	for_each_possible_cpu(cpu)
1518
		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
1519 1520
			vmstat_update);

1521
	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
1522 1523
	schedule_delayed_work(&shepherd,
		round_jiffies_relative(sysctl_stat_interval));
1524 1525
}

1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539
static void vmstat_cpu_dead(int node)
{
	int cpu;

	get_online_cpus();
	for_each_online_cpu(cpu)
		if (cpu_to_node(cpu) == node)
			goto end;

	node_clear_state(node, N_CPU);
end:
	put_online_cpus();
}

1540 1541 1542 1543
/*
 * Use the cpu notifier to insure that the thresholds are recalculated
 * when necessary.
 */
1544
static int vmstat_cpuup_callback(struct notifier_block *nfb,
1545 1546 1547
		unsigned long action,
		void *hcpu)
{
1548 1549
	long cpu = (long)hcpu;

1550
	switch (action) {
1551 1552
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
1553
		refresh_zone_stat_thresholds();
1554
		node_set_state(cpu_to_node(cpu), N_CPU);