vmstat.c 40.7 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>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
20
#include <linux/sched.h>
21
#include <linux/math64.h>
22
#include <linux/writeback.h>
23
#include <linux/compaction.h>
24
#include <linux/mm_inline.h>
25 26
#include <linux/page_ext.h>
#include <linux/page_owner.h>
27 28

#include "internal.h"
29

30 31 32 33
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

34
static void sum_vm_events(unsigned long *ret)
35
{
Christoph Lameter's avatar
Christoph Lameter committed
36
	int cpu;
37 38 39 40
	int i;

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

41
	for_each_online_cpu(cpu) {
42 43 44 45 46 47 48 49 50 51 52 53 54 55
		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
56
	get_online_cpus();
57
	sum_vm_events(ret);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
58
	put_online_cpus();
59
}
60
EXPORT_SYMBOL_GPL(all_vm_events);
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80

/*
 * 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 */

81 82 83 84 85
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
86
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
87 88 89 90
EXPORT_SYMBOL(vm_stat);

#ifdef CONFIG_SMP

91
int calculate_pressure_threshold(struct zone *zone)
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
{
	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;
}

115
int calculate_normal_threshold(struct zone *zone)
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
{
	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
	 */

150
	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
151 152 153 154 155 156 157 158 159 160

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

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

	return threshold;
}
161 162

/*
163
 * Refresh the thresholds for each zone.
164
 */
165
void refresh_zone_stat_thresholds(void)
166
{
167 168 169 170
	struct zone *zone;
	int cpu;
	int threshold;

171
	for_each_populated_zone(zone) {
172 173
		unsigned long max_drift, tolerate_drift;

174
		threshold = calculate_normal_threshold(zone);
175 176

		for_each_online_cpu(cpu)
177 178
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
179 180 181 182 183 184 185 186 187 188 189

		/*
		 * 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;
190
	}
191 192
}

193 194
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *))
195 196 197 198 199 200 201 202 203 204 205
{
	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;

206
		threshold = (*calculate_pressure)(zone);
207
		for_each_online_cpu(cpu)
208 209 210 211 212
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
}

213
/*
214 215 216
 * 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.
217 218 219 220
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
221 222
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
223
	long x;
224 225 226
	long t;

	x = delta + __this_cpu_read(*p);
227

228
	t = __this_cpu_read(pcp->stat_threshold);
229

230
	if (unlikely(x > t || x < -t)) {
231 232 233
		zone_page_state_add(x, zone, item);
		x = 0;
	}
234
	__this_cpu_write(*p, x);
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
}
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.
 *
251 252 253
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
254 255 256 257 258 259 260
 * 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.
 */
261
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
262
{
263 264 265
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
266

267
	v = __this_cpu_inc_return(*p);
268 269 270
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;
271

272 273
		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
274 275
	}
}
276 277 278 279 280

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
281 282
EXPORT_SYMBOL(__inc_zone_page_state);

283
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
284
{
285 286 287
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
288

289
	v = __this_cpu_dec_return(*p);
290 291 292
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;
293

294 295
		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
296 297
	}
}
298 299 300 301 302

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
303 304
EXPORT_SYMBOL(__dec_zone_page_state);

305
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
/*
 * 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
331 332 333 334 335 336
		 * 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.
337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
		 */
		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);

394 395 396 397 398 399 400 401 402
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);
}

403 404 405 406 407 408 409
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);
410
	__inc_zone_state(zone, item);
411 412 413 414 415 416 417 418 419
	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);
420
	__dec_zone_page_state(page, item);
421 422 423
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
424
#endif
425

426 427 428 429 430 431

/*
 * 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
432 433
{
	int i;
434
	int changes = 0;
Christoph Lameter's avatar
Christoph Lameter committed
435 436

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
437
		if (diff[i]) {
Christoph Lameter's avatar
Christoph Lameter committed
438
			atomic_long_add(diff[i], &vm_stat[i]);
439 440 441
			changes++;
	}
	return changes;
Christoph Lameter's avatar
Christoph Lameter committed
442 443
}

444
/*
445
 * Update the zone counters for the current cpu.
446
 *
447 448 449 450 451 452 453 454 455 456
 * 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.
457 458
 *
 * The function returns the number of global counters updated.
459
 */
460
static int refresh_cpu_vm_stats(void)
461 462 463
{
	struct zone *zone;
	int i;
464
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
465
	int changes = 0;
466

467
	for_each_populated_zone(zone) {
468
		struct per_cpu_pageset __percpu *p = zone->pageset;
469

470 471
		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
			int v;
472

473 474
			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
			if (v) {
475 476 477

				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
478 479
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
480
				__this_cpu_write(p->expire, 3);
481
#endif
482
			}
483
		}
484
		cond_resched();
485 486 487 488 489 490 491 492
#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.
		 */
493 494
		if (!__this_cpu_read(p->expire) ||
			       !__this_cpu_read(p->pcp.count))
495 496 497 498 499 500
			continue;

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

505
		if (__this_cpu_dec_return(p->expire))
506 507
			continue;

508
		if (__this_cpu_read(p->pcp.count)) {
509
			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
510 511
			changes++;
		}
512
#endif
513
	}
514 515
	changes += fold_diff(global_diff);
	return changes;
516 517
}

518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544
/*
 * 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
545
	fold_diff(global_diff);
546 547
}

548 549 550 551
/*
 * this is only called if !populated_zone(zone), which implies no other users of
 * pset->vm_stat_diff[] exsist.
 */
552 553 554 555 556 557 558 559 560 561 562 563
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]);
		}
}
564 565
#endif

566 567 568 569 570 571
#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.
Andi Kleen's avatar
Andi Kleen committed
572 573 574 575
 *
 * 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.
576
 */
Andi Kleen's avatar
Andi Kleen committed
577
void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags)
578
{
579
	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
580 581 582
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
583
		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
584
	}
Andi Kleen's avatar
Andi Kleen committed
585 586
	if (z->node == ((flags & __GFP_OTHER_NODE) ?
			preferred_zone->node : numa_node_id()))
587 588 589 590 591 592
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

593
#ifdef CONFIG_COMPACTION
594

595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
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);
	}
}
635 636 637 638 639 640 641 642

/*
 * 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
 */
643
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661
{
	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);
}
662 663 664 665 666 667 668 669 670

/* 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);
}
671 672 673
#endif

#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
674
#include <linux/proc_fs.h>
675 676
#include <linux/seq_file.h>

677 678 679 680 681
static char * const migratetype_names[MIGRATE_TYPES] = {
	"Unmovable",
	"Reclaimable",
	"Movable",
	"Reserve",
682 683 684
#ifdef CONFIG_CMA
	"CMA",
#endif
685
#ifdef CONFIG_MEMORY_ISOLATION
686
	"Isolate",
687
#endif
688 689
};

690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
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)
{
}

714 715 716
/* 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 *))
717 718 719 720 721 722 723 724 725 726
{
	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);
727
		print(m, pgdat, zone);
728
		spin_unlock_irqrestore(&zone->lock, flags);
729 730
	}
}
731
#endif
732

733
#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755
#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[] = {
756
	/* enum zone_stat_item countes */
757
	"nr_free_pages",
758
	"nr_alloc_batch",
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
	"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",
777
	"nr_vmscan_immediate_reclaim",
778 779 780 781 782 783
	"nr_writeback_temp",
	"nr_isolated_anon",
	"nr_isolated_file",
	"nr_shmem",
	"nr_dirtied",
	"nr_written",
784
	"nr_pages_scanned",
785 786 787 788 789 790 791 792 793

#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif
794 795
	"workingset_refault",
	"workingset_activate",
796
	"workingset_nodereclaim",
797
	"nr_anon_transparent_hugepages",
798
	"nr_free_cma",
799 800

	/* enum writeback_stat_item counters */
801 802 803 804
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",

#ifdef CONFIG_VM_EVENT_COUNTERS
805
	/* enum vm_event_item counters */
806 807 808 809 810 811 812 813 814 815 816 817 818 819 820
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	TEXTS_FOR_ZONES("pgalloc")

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

	"pgfault",
	"pgmajfault",

	TEXTS_FOR_ZONES("pgrefill")
821 822
	TEXTS_FOR_ZONES("pgsteal_kswapd")
	TEXTS_FOR_ZONES("pgsteal_direct")
823 824
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
825
	"pgscan_direct_throttle",
826 827 828 829 830 831 832 833 834 835 836 837 838 839

#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",

840 841 842
	"drop_pagecache",
	"drop_slab",

843 844
#ifdef CONFIG_NUMA_BALANCING
	"numa_pte_updates",
845
	"numa_huge_pte_updates",
846 847 848 849
	"numa_hint_faults",
	"numa_hint_faults_local",
	"numa_pages_migrated",
#endif
850 851 852 853
#ifdef CONFIG_MIGRATION
	"pgmigrate_success",
	"pgmigrate_fail",
#endif
854
#ifdef CONFIG_COMPACTION
855 856 857
	"compact_migrate_scanned",
	"compact_free_scanned",
	"compact_isolated",
858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880
	"compact_stall",
	"compact_fail",
	"compact_success",
#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",
	"thp_split",
881 882
	"thp_zero_page_alloc",
	"thp_zero_page_alloc_failed",
883
#endif
884 885 886 887 888 889 890
#ifdef CONFIG_MEMORY_BALLOON
	"balloon_inflate",
	"balloon_deflate",
#ifdef CONFIG_BALLOON_COMPACTION
	"balloon_migrate",
#endif
#endif /* CONFIG_MEMORY_BALLOON */
891
#ifdef CONFIG_DEBUG_TLBFLUSH
892
#ifdef CONFIG_SMP
Dave Hansen's avatar
Dave Hansen committed
893 894
	"nr_tlb_remote_flush",
	"nr_tlb_remote_flush_received",
895
#endif /* CONFIG_SMP */
Dave Hansen's avatar
Dave Hansen committed
896 897
	"nr_tlb_local_flush_all",
	"nr_tlb_local_flush_one",
898
#endif /* CONFIG_DEBUG_TLBFLUSH */
899

Davidlohr Bueso's avatar
Davidlohr Bueso committed
900 901 902 903
#ifdef CONFIG_DEBUG_VM_VMACACHE
	"vmacache_find_calls",
	"vmacache_find_hits",
#endif
904 905
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
906
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
907 908


909
#ifdef CONFIG_PROC_FS
910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
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);
		}
952 953
		seq_putc(m, '\n');
	}
954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978
}

/* 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;
979
	unsigned long end_pfn = zone_end_pfn(zone);
980 981 982 983 984 985 986 987 988
	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);
989 990 991

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
992
			continue;
993

994 995
		mtype = get_pageblock_migratetype(page);

996 997
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021
	}

	/* 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;
}

1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 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 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119
#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);
		pageblock_mt = get_pfnblock_migratetype(page, pfn);

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

			page = pfn_to_page(pfn);
			if (PageBuddy(page)) {
				pfn += (1UL << page_order(page)) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);

			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;

	if (!page_owner_inited)
		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 */
}

1120 1121 1122 1123 1124 1125 1126 1127
/*
 * 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;

1128
	/* check memoryless node */
1129
	if (!node_state(pgdat->node_id, N_MEMORY))
1130 1131
		return 0;

1132 1133 1134 1135 1136
	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);
1137
	pagetypeinfo_showmixedcount(m, pgdat);
1138

1139 1140 1141
	return 0;
}

1142
static const struct seq_operations fragmentation_op = {
1143 1144 1145 1146 1147 1148
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160
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,
};

1161
static const struct seq_operations pagetypeinfo_op = {
1162 1163 1164 1165 1166 1167
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179
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,
};

1180 1181
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
1182
{
1183 1184 1185 1186 1187 1188 1189
	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"
1190
		   "\n        scanned  %lu"
1191
		   "\n        spanned  %lu"
1192 1193
		   "\n        present  %lu"
		   "\n        managed  %lu",
1194
		   zone_page_state(zone, NR_FREE_PAGES),
1195 1196 1197
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
1198
		   zone_page_state(zone, NR_PAGES_SCANNED),
1199
		   zone->spanned_pages,
1200 1201
		   zone->present_pages,
		   zone->managed_pages);
1202 1203 1204 1205 1206 1207

	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,
1208
		   "\n        protection: (%ld",
1209 1210
		   zone->lowmem_reserve[0]);
	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
1211
		seq_printf(m, ", %ld", zone->lowmem_reserve[i]);
1212 1213 1214 1215 1216 1217
	seq_printf(m,
		   ")"
		   "\n  pagesets");
	for_each_online_cpu(i) {
		struct per_cpu_pageset *pageset;

1218
		pageset = per_cpu_ptr(zone->pageset, i);
1219 1220 1221 1222 1223 1224 1225 1226 1227
		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);
1228
#ifdef CONFIG_SMP
1229 1230
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
1231
#endif
1232
	}
1233 1234
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
1235 1236
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
1237
		   !zone_reclaimable(zone),
1238 1239
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
	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);
1250 1251 1252
	return 0;
}

1253
static const struct seq_operations zoneinfo_op = {
1254 1255 1256 1257 1258 1259 1260
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272
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,
};

1273 1274 1275 1276 1277 1278
enum writeback_stat_item {
	NR_DIRTY_THRESHOLD,
	NR_DIRTY_BG_THRESHOLD,
	NR_VM_WRITEBACK_STAT_ITEMS,
};

1279 1280
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
1281
	unsigned long *v;
1282
	int i, stat_items_size;
1283 1284 1285

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
1286 1287
	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
1288

1289
#ifdef CONFIG_VM_EVENT_COUNTERS
1290
	stat_items_size += sizeof(struct vm_event_state);
1291
#endif
1292 1293

	v = kmalloc(stat_items_size, GFP_KERNEL);
1294 1295
	m->private = v;
	if (!v)
1296
		return ERR_PTR(-ENOMEM);
1297 1298
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
1299 1300 1301 1302 1303 1304
	v += NR_VM_ZONE_STAT_ITEMS;

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

1305
#ifdef CONFIG_VM_EVENT_COUNTERS
1306 1307 1308
	all_vm_events(v);
	v[PGPGIN] /= 2;		/* sectors -> kbytes */
	v[PGPGOUT] /= 2;
1309
#endif
1310
	return (unsigned long *)m->private + *pos;
1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
}

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;
}

1336
static const struct seq_operations vmstat_op = {
1337 1338 1339 1340 1341 1342
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353
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,
};
1354 1355
#endif /* CONFIG_PROC_FS */

1356
#ifdef CONFIG_SMP
1357
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
1358
int sysctl_stat_interval __read_mostly = HZ;
1359
static cpumask_var_t cpu_stat_off;
1360 1361 1362

static void vmstat_update(struct work_struct *w)
{
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 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442
	if (refresh_cpu_vm_stats())
		/*
		 * Counters were updated so we expect more updates
		 * to occur in the future. Keep on running the
		 * update worker thread.
		 */
		schedule_delayed_work(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.
		 */
		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);
	}
}

/*
 * 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;
}


/*
 * 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);

static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);

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

	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))

			schedule_delayed_work_on(cpu, &per_cpu(vmstat_work, cpu),
				__round_jiffies_relative(sysctl_stat_interval, cpu));

	put_online_cpus();

	schedule_delayed_work(&shepherd,
1443
		round_jiffies_relative(sysctl_stat_interval));
1444

1445 1446
}

1447
static void __init start_shepherd_timer(void)
1448
{
1449 1450 1451 1452 1453 1454 1455 1456 1457
	int cpu;

	for_each_possible_cpu(cpu)
		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);
1458

1459 1460
	schedule_delayed_work(&shepherd,
		round_jiffies_relative(sysctl_stat_interval));
1461 1462
}

1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476
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();
}

1477 1478 1479 1480
/*
 * Use the cpu notifier to insure that the thresholds are recalculated
 * when necessary.
 */
1481
static int vmstat_cpuup_callback(struct notifier_block *nfb,
1482 1483 1484
		unsigned long action,
		void *hcpu)
{
1485 1486
	long cpu = (long)hcpu;

1487
	switch (action) {
1488 1489
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
1490
		refresh_zone_stat_thresholds();
1491
		node_set_state(cpu_to_node(cpu), N_CPU);
1492
		cpumask_set_cpu(cpu, cpu_stat_off);
1493 1494 1495
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
1496
		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
1497
		cpumask_clear_cpu(cpu, cpu_stat_off);
1498 1499 1500
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
1501
		cpumask_set_cpu(cpu, cpu_stat_off);
1502
		break;
1503
	case CPU_DEAD:
1504
	case CPU_DEAD_FROZEN:
1505
		refresh_zone_stat_thresholds();
1506
		vmstat_cpu_dead(cpu_to_node(cpu));
1507 1508 1509
		break;
	default:
		break;
1510 1511 1512 1513
	}
	return NOTIFY_OK;
}

1514
static struct notifier_block vmstat_notifier =
1515
	{ &vmstat_cpuup_callback, NULL, 0 };
1516
#endif
1517

Adrian Bunk's avatar
Adrian Bunk committed
1518
static int __init setup_vmstat(void)
1519
{
1520
#ifdef CONFIG_SMP
1521 1522
	cpu_notifier_register_begin();
	__register_cpu_notifier(&vmstat_notifier);
1523

1524
	start_shepherd_timer();
1525
	cpu_notifier_register_done();
1526 1527 1528
#endif
#ifdef CONFIG_PROC_FS
	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
1529
	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
1530
	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
1531
	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
1532
#endif
1533 1534 1535
	return 0;
}
module_init(setup_vmstat)
1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568