vmstat.c 34.5 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
 */
11
#include <linux/fs.h>
12
#include <linux/mm.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
13
#include <linux/err.h>
14
#include <linux/module.h>
15
#include <linux/slab.h>
16
#include <linux/cpu.h>
Adrian Bunk's avatar
Adrian Bunk committed
17
#include <linux/vmstat.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
18
#include <linux/sched.h>
19
#include <linux/math64.h>
20
#include <linux/writeback.h>
21
#include <linux/compaction.h>
22

23 24 25 26
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

27
static void sum_vm_events(unsigned long *ret)
28
{
Christoph Lameter's avatar
Christoph Lameter committed
29
	int cpu;
30 31 32 33
	int i;

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

34
	for_each_online_cpu(cpu) {
35 36 37 38 39 40 41 42 43 44 45 46 47 48
		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
49
	get_online_cpus();
50
	sum_vm_events(ret);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
51
	put_online_cpus();
52
}
53
EXPORT_SYMBOL_GPL(all_vm_events);
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73

/*
 * 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 */

74 75 76 77 78
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
79
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
80 81 82 83
EXPORT_SYMBOL(vm_stat);

#ifdef CONFIG_SMP

84
int calculate_pressure_threshold(struct zone *zone)
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107
{
	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;
}

108
int calculate_normal_threshold(struct zone *zone)
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
{
	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
	 */

143
	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
144 145 146 147 148 149 150 151 152 153

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

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

	return threshold;
}
154 155

/*
156
 * Refresh the thresholds for each zone.
157
 */
158
void refresh_zone_stat_thresholds(void)
159
{
160 161 162 163
	struct zone *zone;
	int cpu;
	int threshold;

164
	for_each_populated_zone(zone) {
165 166
		unsigned long max_drift, tolerate_drift;

167
		threshold = calculate_normal_threshold(zone);
168 169

		for_each_online_cpu(cpu)
170 171
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
172 173 174 175 176 177 178 179 180 181 182

		/*
		 * 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;
183
	}
184 185
}

186 187
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *))
188 189 190 191 192 193 194 195 196 197 198
{
	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;

199 200
		threshold = (*calculate_pressure)(zone);
		for_each_possible_cpu(cpu)
201 202 203 204 205
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
}

206 207 208 209 210 211
/*
 * For use when we know that interrupts are disabled.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
212 213
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
214
	long x;
215 216 217
	long t;

	x = delta + __this_cpu_read(*p);
218

219
	t = __this_cpu_read(pcp->stat_threshold);
220

221
	if (unlikely(x > t || x < -t)) {
222 223 224
		zone_page_state_add(x, zone, item);
		x = 0;
	}
225
	__this_cpu_write(*p, x);
226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241
}
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.
 *
242 243 244
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
245 246 247 248 249 250 251
 * 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.
 */
252
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
253
{
254 255 256
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
257

258
	v = __this_cpu_inc_return(*p);
259 260 261
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;
262

263 264
		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
265 266
	}
}
267 268 269 270 271

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
272 273
EXPORT_SYMBOL(__inc_zone_page_state);

274
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
275
{
276 277 278
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
279

280
	v = __this_cpu_dec_return(*p);
281 282 283
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;
284

285 286
		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
287 288
	}
}
289 290 291 292 293

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
294 295
EXPORT_SYMBOL(__dec_zone_page_state);

296
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
/*
 * 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
322 323 324 325 326 327
		 * 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.
328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
		 */
		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);

385 386 387 388 389 390 391 392 393
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);
}

394 395 396 397 398 399 400
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);
401
	__inc_zone_state(zone, item);
402 403 404 405 406 407 408 409 410
	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);
411
	__dec_zone_page_state(page, item);
412 413 414
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
415
#endif
416

Christoph Lameter's avatar
Christoph Lameter committed
417 418 419 420 421 422 423 424 425
static inline void fold_diff(int *diff)
{
	int i;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (diff[i])
			atomic_long_add(diff[i], &vm_stat[i]);
}

426
/*
427
 * Update the zone counters for the current cpu.
428
 *
429 430 431 432 433 434 435 436 437 438
 * 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.
439
 */
440
static void refresh_cpu_vm_stats(void)
441 442 443
{
	struct zone *zone;
	int i;
444
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
445

446
	for_each_populated_zone(zone) {
447
		struct per_cpu_pageset __percpu *p = zone->pageset;
448

449 450
		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
			int v;
451

452 453
			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
			if (v) {
454 455 456

				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
457 458
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
459
				__this_cpu_write(p->expire, 3);
460
#endif
461
			}
462
		}
463
		cond_resched();
464 465 466 467 468 469 470 471
#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.
		 */
472 473
		if (!__this_cpu_read(p->expire) ||
			       !__this_cpu_read(p->pcp.count))
474 475 476 477 478 479
			continue;

		/*
		 * We never drain zones local to this processor.
		 */
		if (zone_to_nid(zone) == numa_node_id()) {
480
			__this_cpu_write(p->expire, 0);
481 482 483
			continue;
		}

484 485

		if (__this_cpu_dec_return(p->expire))
486 487
			continue;

488 489
		if (__this_cpu_read(p->pcp.count))
			drain_zone_pages(zone, __this_cpu_ptr(&p->pcp));
490
#endif
491
	}
Christoph Lameter's avatar
Christoph Lameter committed
492
	fold_diff(global_diff);
493 494
}

495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521
/*
 * 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
522
	fold_diff(global_diff);
523 524
}

525 526 527 528
/*
 * this is only called if !populated_zone(zone), which implies no other users of
 * pset->vm_stat_diff[] exsist.
 */
529 530 531 532 533 534 535 536 537 538 539 540
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]);
		}
}
541 542
#endif

543 544 545 546 547 548
#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
549 550 551 552
 *
 * 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.
553
 */
Andi Kleen's avatar
Andi Kleen committed
554
void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags)
555
{
556
	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
557 558 559
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
560
		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
561
	}
Andi Kleen's avatar
Andi Kleen committed
562 563
	if (z->node == ((flags & __GFP_OTHER_NODE) ?
			preferred_zone->node : numa_node_id()))
564 565 566 567 568 569
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

570
#ifdef CONFIG_COMPACTION
571

572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
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);
	}
}
612 613 614 615 616 617 618 619

/*
 * 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
 */
620
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
{
	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);
}
639 640 641 642 643 644 645 646 647

/* 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);
}
648 649 650
#endif

#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
651
#include <linux/proc_fs.h>
652 653
#include <linux/seq_file.h>

654 655 656 657 658
static char * const migratetype_names[MIGRATE_TYPES] = {
	"Unmovable",
	"Reclaimable",
	"Movable",
	"Reserve",
659 660 661
#ifdef CONFIG_CMA
	"CMA",
#endif
662
#ifdef CONFIG_MEMORY_ISOLATION
663
	"Isolate",
664
#endif
665 666
};

667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
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)
{
}

691 692 693
/* 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 *))
694 695 696 697 698 699 700 701 702 703
{
	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);
704
		print(m, pgdat, zone);
705
		spin_unlock_irqrestore(&zone->lock, flags);
706 707
	}
}
708
#endif
709

710
#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734
#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[] = {
	/* Zoned VM counters */
	"nr_free_pages",
735
	"nr_alloc_batch",
736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
	"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",
754
	"nr_vmscan_immediate_reclaim",
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
	"nr_writeback_temp",
	"nr_isolated_anon",
	"nr_isolated_file",
	"nr_shmem",
	"nr_dirtied",
	"nr_written",

#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif
	"nr_anon_transparent_hugepages",
771
	"nr_free_cma",
772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",

#ifdef CONFIG_VM_EVENT_COUNTERS
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	TEXTS_FOR_ZONES("pgalloc")

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

	"pgfault",
	"pgmajfault",

	TEXTS_FOR_ZONES("pgrefill")
791 792
	TEXTS_FOR_ZONES("pgsteal_kswapd")
	TEXTS_FOR_ZONES("pgsteal_direct")
793 794
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
795
	"pgscan_direct_throttle",
796 797 798 799 800 801 802 803 804 805 806 807 808 809

#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",

810 811 812 813 814 815
#ifdef CONFIG_NUMA_BALANCING
	"numa_pte_updates",
	"numa_hint_faults",
	"numa_hint_faults_local",
	"numa_pages_migrated",
#endif
816 817 818 819
#ifdef CONFIG_MIGRATION
	"pgmigrate_success",
	"pgmigrate_fail",
#endif
820
#ifdef CONFIG_COMPACTION
821 822 823
	"compact_migrate_scanned",
	"compact_free_scanned",
	"compact_isolated",
824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
	"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",
847 848
	"thp_zero_page_alloc",
	"thp_zero_page_alloc_failed",
849
#endif
850
#ifdef CONFIG_SMP
Dave Hansen's avatar
Dave Hansen committed
851 852
	"nr_tlb_remote_flush",
	"nr_tlb_remote_flush_received",
853
#endif
Dave Hansen's avatar
Dave Hansen committed
854 855
	"nr_tlb_local_flush_all",
	"nr_tlb_local_flush_one",
856 857 858

#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
859
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
860 861


862
#ifdef CONFIG_PROC_FS
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904
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);
		}
905 906
		seq_putc(m, '\n');
	}
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
}

/* 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;
932
	unsigned long end_pfn = zone_end_pfn(zone);
933 934 935 936 937 938 939 940 941
	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);
942 943 944

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
945
			continue;
946

947 948
		mtype = get_pageblock_migratetype(page);

949 950
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982
	}

	/* 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;
}

/*
 * 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;

983
	/* check memoryless node */
984
	if (!node_state(pgdat->node_id, N_MEMORY))
985 986
		return 0;

987 988 989 990 991 992
	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);

993 994 995
	return 0;
}

996
static const struct seq_operations fragmentation_op = {
997 998 999 1000 1001 1002
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
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,
};

1015
static const struct seq_operations pagetypeinfo_op = {
1016 1017 1018 1019 1020 1021
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
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,
};

1034 1035
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
1036
{
1037 1038 1039 1040 1041 1042 1043
	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"
1044
		   "\n        scanned  %lu"
1045
		   "\n        spanned  %lu"
1046 1047
		   "\n        present  %lu"
		   "\n        managed  %lu",
1048
		   zone_page_state(zone, NR_FREE_PAGES),
1049 1050 1051
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
1052 1053
		   zone->pages_scanned,
		   zone->spanned_pages,
1054 1055
		   zone->present_pages,
		   zone->managed_pages);
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071

	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,
		   "\n        protection: (%lu",
		   zone->lowmem_reserve[0]);
	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
		seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
	seq_printf(m,
		   ")"
		   "\n  pagesets");
	for_each_online_cpu(i) {
		struct per_cpu_pageset *pageset;

1072
		pageset = per_cpu_ptr(zone->pageset, i);
1073 1074 1075 1076 1077 1078 1079 1080 1081
		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);
1082
#ifdef CONFIG_SMP
1083 1084
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
1085
#endif
1086
	}
1087 1088
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
1089 1090
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
1091
		   zone->all_unreclaimable,
1092 1093
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
1094 1095 1096 1097 1098 1099 1100 1101 1102 1103
	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);
1104 1105 1106
	return 0;
}

1107
static const struct seq_operations zoneinfo_op = {
1108 1109 1110 1111 1112 1113 1114
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126
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,
};

1127 1128 1129 1130 1131 1132
enum writeback_stat_item {
	NR_DIRTY_THRESHOLD,
	NR_DIRTY_BG_THRESHOLD,
	NR_VM_WRITEBACK_STAT_ITEMS,
};

1133 1134
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
1135
	unsigned long *v;
1136
	int i, stat_items_size;
1137 1138 1139

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
1140 1141
	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
1142

1143
#ifdef CONFIG_VM_EVENT_COUNTERS
1144
	stat_items_size += sizeof(struct vm_event_state);
1145
#endif
1146 1147

	v = kmalloc(stat_items_size, GFP_KERNEL);
1148 1149
	m->private = v;
	if (!v)
1150
		return ERR_PTR(-ENOMEM);
1151 1152
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
1153 1154 1155 1156 1157 1158
	v += NR_VM_ZONE_STAT_ITEMS;

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

1159
#ifdef CONFIG_VM_EVENT_COUNTERS
1160 1161 1162
	all_vm_events(v);
	v[PGPGIN] /= 2;		/* sectors -> kbytes */
	v[PGPGOUT] /= 2;
1163
#endif
1164
	return (unsigned long *)m->private + *pos;
1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
}

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;
}

1190
static const struct seq_operations vmstat_op = {
1191 1192 1193 1194 1195 1196
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
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,
};
1208 1209
#endif /* CONFIG_PROC_FS */

1210
#ifdef CONFIG_SMP
1211
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
1212
int sysctl_stat_interval __read_mostly = HZ;
1213 1214 1215

static void vmstat_update(struct work_struct *w)
{
1216
	refresh_cpu_vm_stats();
1217
	schedule_delayed_work(&__get_cpu_var(vmstat_work),
1218
		round_jiffies_relative(sysctl_stat_interval));
1219 1220
}

1221
static void start_cpu_timer(int cpu)
1222
{
1223
	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
1224

1225
	INIT_DEFERRABLE_WORK(work, vmstat_update);
1226
	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
1227 1228
}

1229 1230 1231 1232
/*
 * Use the cpu notifier to insure that the thresholds are recalculated
 * when necessary.
 */
1233
static int vmstat_cpuup_callback(struct notifier_block *nfb,
1234 1235 1236
		unsigned long action,
		void *hcpu)
{
1237 1238
	long cpu = (long)hcpu;

1239
	switch (action) {
1240 1241
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
1242
		refresh_zone_stat_thresholds();
1243
		start_cpu_timer(cpu);
1244
		node_set_state(cpu_to_node(cpu), N_CPU);
1245 1246 1247
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
1248
		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
1249 1250 1251 1252 1253 1254
		per_cpu(vmstat_work, cpu).work.func = NULL;
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		start_cpu_timer(cpu);
		break;
1255
	case CPU_DEAD:
1256
	case CPU_DEAD_FROZEN:
1257 1258 1259 1260
		refresh_zone_stat_thresholds();
		break;
	default:
		break;
1261 1262 1263 1264
	}
	return NOTIFY_OK;
}

1265
static struct notifier_block vmstat_notifier =
1266
	{ &vmstat_cpuup_callback, NULL, 0 };
1267
#endif
1268

Adrian Bunk's avatar
Adrian Bunk committed
1269
static int __init setup_vmstat(void)
1270
{
1271
#ifdef CONFIG_SMP
1272 1273
	int cpu;

1274
	register_cpu_notifier(&vmstat_notifier);
1275 1276 1277

	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
1278 1279 1280
#endif
#ifdef CONFIG_PROC_FS
	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
1281
	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
1282
	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
1283
	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
1284
#endif
1285 1286 1287
	return 0;
}
module_init(setup_vmstat)
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 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 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347

#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
#include <linux/debugfs.h>


/*
 * Return an index indicating how much of the available free memory is
 * unusable for an allocation of the requested size.
 */
static int unusable_free_index(unsigned int order,
				struct contig_page_info *info)
{
	/* No free memory is interpreted as all free memory is unusable */
	if (info->free_pages == 0)
		return 1000;

	/*
	 * Index should be a value between 0 and 1. Return a value to 3
	 * decimal places.
	 *
	 * 0 => no fragmentation
	 * 1 => high fragmentation
	 */
	return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages);

}

static void unusable_show_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	unsigned int order;
	int index;
	struct contig_page_info info;

	seq_printf(m, "Node %d, zone %8s ",
				pgdat<