vmstat.c 32.9 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 74 75

#ifdef CONFIG_HOTPLUG
/*
 * 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_HOTPLUG */

#endif /* CONFIG_VM_EVENT_COUNTERS */

76 77 78 79 80 81 82 83 84 85
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
EXPORT_SYMBOL(vm_stat);

#ifdef CONFIG_SMP

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
static int calculate_pressure_threshold(struct zone *zone)
{
	int threshold;
	int watermark_distance;

	/*
	 * As vmstats are not up to date, there is drift between the estimated
	 * and real values. For high thresholds and a high number of CPUs, it
	 * is possible for the min watermark to be breached while the estimated
	 * value looks fine. The pressure threshold is a reduced value such
	 * that even the maximum amount of drift will not accidentally breach
	 * the min watermark
	 */
	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
	threshold = max(1, (int)(watermark_distance / num_online_cpus()));

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

	return threshold;
}

110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
static int calculate_threshold(struct zone *zone)
{
	int threshold;
	int mem;	/* memory in 128 MB units */

	/*
	 * The threshold scales with the number of processors and the amount
	 * of memory per zone. More memory means that we can defer updates for
	 * longer, more processors could lead to more contention.
 	 * fls() is used to have a cheap way of logarithmic scaling.
	 *
	 * Some sample thresholds:
	 *
	 * Threshold	Processors	(fls)	Zonesize	fls(mem+1)
	 * ------------------------------------------------------------------
	 * 8		1		1	0.9-1 GB	4
	 * 16		2		2	0.9-1 GB	4
	 * 20 		2		2	1-2 GB		5
	 * 24		2		2	2-4 GB		6
	 * 28		2		2	4-8 GB		7
	 * 32		2		2	8-16 GB		8
	 * 4		2		2	<128M		1
	 * 30		4		3	2-4 GB		5
	 * 48		4		3	8-16 GB		8
	 * 32		8		4	1-2 GB		4
	 * 32		8		4	0.9-1GB		4
	 * 10		16		5	<128M		1
	 * 40		16		5	900M		4
	 * 70		64		7	2-4 GB		5
	 * 84		64		7	4-8 GB		6
	 * 108		512		9	4-8 GB		6
	 * 125		1024		10	8-16 GB		8
	 * 125		1024		10	16-32 GB	9
	 */

	mem = zone->present_pages >> (27 - PAGE_SHIFT);

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

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

	return threshold;
}
156 157

/*
158
 * Refresh the thresholds for each zone.
159
 */
160
static void refresh_zone_stat_thresholds(void)
161
{
162 163 164 165
	struct zone *zone;
	int cpu;
	int threshold;

166
	for_each_populated_zone(zone) {
167 168
		unsigned long max_drift, tolerate_drift;

169 170 171
		threshold = calculate_threshold(zone);

		for_each_online_cpu(cpu)
172 173
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
174 175 176 177 178 179 180 181 182 183 184

		/*
		 * 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;
185
	}
186 187
}

188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
void reduce_pgdat_percpu_threshold(pg_data_t *pgdat)
{
	struct zone *zone;
	int cpu;
	int threshold;
	int i;

	get_online_cpus();
	for (i = 0; i < pgdat->nr_zones; i++) {
		zone = &pgdat->node_zones[i];
		if (!zone->percpu_drift_mark)
			continue;

		threshold = calculate_pressure_threshold(zone);
		for_each_online_cpu(cpu)
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
	put_online_cpus();
}

void restore_pgdat_percpu_threshold(pg_data_t *pgdat)
{
	struct zone *zone;
	int cpu;
	int threshold;
	int i;

	get_online_cpus();
	for (i = 0; i < pgdat->nr_zones; i++) {
		zone = &pgdat->node_zones[i];
		if (!zone->percpu_drift_mark)
			continue;

		threshold = calculate_threshold(zone);
		for_each_online_cpu(cpu)
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
	put_online_cpus();
}

230 231 232 233 234 235
/*
 * For use when we know that interrupts are disabled.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
236 237
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
238
	long x;
239 240 241
	long t;

	x = delta + __this_cpu_read(*p);
242

243
	t = __this_cpu_read(pcp->stat_threshold);
244

245
	if (unlikely(x > t || x < -t)) {
246 247 248
		zone_page_state_add(x, zone, item);
		x = 0;
	}
249
	__this_cpu_write(*p, x);
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
}
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.
 *
266 267 268
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
269 270 271 272 273 274 275
 * 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.
 */
276
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
277
{
278 279 280
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
281

282
	v = __this_cpu_inc_return(*p);
283 284 285
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;
286

287 288
		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
289 290
	}
}
291 292 293 294 295

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
296 297
EXPORT_SYMBOL(__inc_zone_page_state);

298
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
299
{
300 301 302
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
303

304
	v = __this_cpu_dec_return(*p);
305 306 307
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;
308

309 310
		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
311 312
	}
}
313 314 315 316 317

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
318 319
EXPORT_SYMBOL(__dec_zone_page_state);

320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
#ifdef CONFIG_CMPXCHG_LOCAL
/*
 * If we have cmpxchg_local support then we do not need to incur the overhead
 * that comes with local_irq_save/restore if we use this_cpu_cmpxchg.
 *
 * mod_state() modifies the zone counter state through atomic per cpu
 * operations.
 *
 * Overstep mode specifies how overstep should handled:
 *     0       No overstepping
 *     1       Overstepping half of threshold
 *     -1      Overstepping minus half of threshold
*/
static inline void mod_state(struct zone *zone,
       enum zone_stat_item item, int delta, int overstep_mode)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	long o, n, t, z;

	do {
		z = 0;  /* overflow to zone counters */

		/*
		 * The fetching of the stat_threshold is racy. We may apply
		 * a counter threshold to the wrong the cpu if we get
		 * rescheduled while executing here. However, the following
		 * will apply the threshold again and therefore bring the
		 * counter under the threshold.
		 */
		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);

406 407 408 409 410 411 412 413 414
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);
}

415 416 417 418 419 420 421
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);
422
	__inc_zone_state(zone, item);
423 424 425 426 427 428 429 430 431
	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);
432
	__dec_zone_page_state(page, item);
433 434 435
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);
436
#endif
437 438 439

/*
 * Update the zone counters for one cpu.
440
 *
441 442 443 444
 * The cpu specified must be either the current cpu or a processor that
 * is not online. If it is the current cpu then the execution thread must
 * be pinned to the current cpu.
 *
445 446 447 448 449 450 451 452 453 454
 * 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.
455 456 457 458 459
 */
void refresh_cpu_vm_stats(int cpu)
{
	struct zone *zone;
	int i;
460
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
461

462
	for_each_populated_zone(zone) {
463
		struct per_cpu_pageset *p;
464

465
		p = per_cpu_ptr(zone->pageset, cpu);
466 467

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
468
			if (p->vm_stat_diff[i]) {
469 470 471
				unsigned long flags;
				int v;

472
				local_irq_save(flags);
473
				v = p->vm_stat_diff[i];
474
				p->vm_stat_diff[i] = 0;
475 476 477
				local_irq_restore(flags);
				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
478 479 480 481
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
				p->expire = 3;
#endif
482
			}
483
		cond_resched();
484 485 486 487 488 489 490 491
#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.
		 */
492
		if (!p->expire || !p->pcp.count)
493 494 495 496 497 498 499 500 501 502 503 504 505 506
			continue;

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

		p->expire--;
		if (p->expire)
			continue;

507 508
		if (p->pcp.count)
			drain_zone_pages(zone, &p->pcp);
509
#endif
510
	}
511 512 513 514

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (global_diff[i])
			atomic_long_add(global_diff[i], &vm_stat[i]);
515 516 517 518
}

#endif

519 520 521 522 523 524 525
#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.
 */
526
void zone_statistics(struct zone *preferred_zone, struct zone *z)
527
{
528
	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
529 530 531
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
532
		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
533
	}
534
	if (z->node == numa_node_id())
535 536 537 538 539 540
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

541
#ifdef CONFIG_COMPACTION
542

543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582
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);
	}
}
583 584 585 586 587 588 589 590

/*
 * 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
 */
591
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
{
	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);
}
610 611 612 613 614 615 616 617 618

/* 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);
}
619 620 621
#endif

#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
622
#include <linux/proc_fs.h>
623 624
#include <linux/seq_file.h>

625 626 627 628 629
static char * const migratetype_names[MIGRATE_TYPES] = {
	"Unmovable",
	"Reclaimable",
	"Movable",
	"Reserve",
630
	"Isolate",
631 632
};

633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
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)
{
}

657 658 659
/* 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 *))
660 661 662 663 664 665 666 667 668 669
{
	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);
670
		print(m, pgdat, zone);
671
		spin_unlock_irqrestore(&zone->lock, flags);
672 673
	}
}
674
#endif
675

676
#ifdef CONFIG_PROC_FS
677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
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);
		}
719 720
		seq_putc(m, '\n');
	}
721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755
}

/* 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;
	unsigned long end_pfn = start_pfn + zone->spanned_pages;
	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);
756 757 758

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
759
			continue;
760

761 762
		mtype = get_pageblock_migratetype(page);

763 764
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796
	}

	/* 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;

797 798 799 800
	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
		return 0;

801 802 803 804 805 806
	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);

807 808 809
	return 0;
}

810
static const struct seq_operations fragmentation_op = {
811 812 813 814 815 816
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

817 818 819 820 821 822 823 824 825 826 827 828
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,
};

829
static const struct seq_operations pagetypeinfo_op = {
830 831 832 833 834 835
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

836 837 838 839 840 841 842 843 844 845 846 847
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,
};

848 849 850 851 852 853
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
#define TEXT_FOR_DMA(xx)
#endif

854 855 856 857 858 859 860 861 862 863 864 865
#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

866
#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
Mel Gorman's avatar
Mel Gorman committed
867
					TEXT_FOR_HIGHMEM(xx) xx "_movable",
868

869
static const char * const vmstat_text[] = {
870
	/* Zoned VM counters */
871
	"nr_free_pages",
872 873 874 875
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
876
	"nr_unevictable",
Nick Piggin's avatar
Nick Piggin committed
877
	"nr_mlock",
878
	"nr_anon_pages",
879
	"nr_mapped",
880
	"nr_file_pages",
881 882
	"nr_dirty",
	"nr_writeback",
883 884
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
885
	"nr_page_table_pages",
886
	"nr_kernel_stack",
887
	"nr_unstable",
888
	"nr_bounce",
889
	"nr_vmscan_write",
890
	"nr_writeback_temp",
891 892
	"nr_isolated_anon",
	"nr_isolated_file",
893
	"nr_shmem",
894 895 896
	"nr_dirtied",
	"nr_written",

897 898 899 900 901 902 903 904
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif
905 906
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",
907

908
#ifdef CONFIG_VM_EVENT_COUNTERS
909 910 911 912 913
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

914
	TEXTS_FOR_ZONES("pgalloc")
915 916 917 918 919 920 921 922

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

	"pgfault",
	"pgmajfault",

923 924 925 926
	TEXTS_FOR_ZONES("pgrefill")
	TEXTS_FOR_ZONES("pgsteal")
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
927

928 929 930
#ifdef CONFIG_NUMA
	"zone_reclaim_failed",
#endif
931 932 933 934
	"pginodesteal",
	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
935 936 937
	"kswapd_low_wmark_hit_quickly",
	"kswapd_high_wmark_hit_quickly",
	"kswapd_skip_congestion_wait",
938 939 940 941
	"pageoutrun",
	"allocstall",

	"pgrotated",
942 943 944 945 946

#ifdef CONFIG_COMPACTION
	"compact_blocks_moved",
	"compact_pages_moved",
	"compact_pagemigrate_failed",
947 948 949
	"compact_stall",
	"compact_fail",
	"compact_success",
950 951
#endif

952 953 954 955
#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
956 957 958
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
Nick Piggin's avatar
Nick Piggin committed
959 960 961 962
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",
963
	"unevictable_pgs_mlockfreed",
964
#endif
965 966
};

967 968
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
969
{
970 971 972 973 974 975 976
	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"
977
		   "\n        scanned  %lu"
978 979
		   "\n        spanned  %lu"
		   "\n        present  %lu",
980
		   zone_page_state(zone, NR_FREE_PAGES),
981 982 983
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
		   zone->pages_scanned,
		   zone->spanned_pages,
		   zone->present_pages);

	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;

1003
		pageset = per_cpu_ptr(zone->pageset, i);
1004 1005 1006 1007 1008 1009 1010 1011 1012
		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);
1013
#ifdef CONFIG_SMP
1014 1015
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
1016
#endif
1017
	}
1018 1019
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
1020 1021
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
1022
		   zone->all_unreclaimable,
1023 1024
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034
	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);
1035 1036 1037
	return 0;
}

1038
static const struct seq_operations zoneinfo_op = {
1039 1040 1041 1042 1043 1044 1045
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057
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,
};

1058 1059 1060 1061 1062 1063
enum writeback_stat_item {
	NR_DIRTY_THRESHOLD,
	NR_DIRTY_BG_THRESHOLD,
	NR_VM_WRITEBACK_STAT_ITEMS,
};

1064 1065
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
1066
	unsigned long *v;
1067
	int i, stat_items_size;
1068 1069 1070

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
1071 1072
	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
1073

1074
#ifdef CONFIG_VM_EVENT_COUNTERS
1075
	stat_items_size += sizeof(struct vm_event_state);
1076
#endif
1077 1078

	v = kmalloc(stat_items_size, GFP_KERNEL);
1079 1080
	m->private = v;
	if (!v)
1081
		return ERR_PTR(-ENOMEM);
1082 1083
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
1084 1085 1086 1087 1088 1089
	v += NR_VM_ZONE_STAT_ITEMS;

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

1090
#ifdef CONFIG_VM_EVENT_COUNTERS
1091 1092 1093
	all_vm_events(v);
	v[PGPGIN] /= 2;		/* sectors -> kbytes */
	v[PGPGOUT] /= 2;
1094
#endif
1095
	return (unsigned long *)m->private + *pos;
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
}

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;
}

1121
static const struct seq_operations vmstat_op = {
1122 1123 1124 1125 1126 1127
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138
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,
};
1139 1140
#endif /* CONFIG_PROC_FS */

1141
#ifdef CONFIG_SMP
1142
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
1143
int sysctl_stat_interval __read_mostly = HZ;
1144 1145 1146 1147

static void vmstat_update(struct work_struct *w)
{
	refresh_cpu_vm_stats(smp_processor_id());
1148
	schedule_delayed_work(&__get_cpu_var(vmstat_work),
1149
		round_jiffies_relative(sysctl_stat_interval));
1150 1151
}

1152
static void __cpuinit start_cpu_timer(int cpu)
1153
{
1154
	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
1155

1156 1157
	INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
1158 1159
}

1160 1161 1162 1163 1164 1165 1166 1167
/*
 * Use the cpu notifier to insure that the thresholds are recalculated
 * when necessary.
 */
static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
		unsigned long action,
		void *hcpu)
{
1168 1169
	long cpu = (long)hcpu;

1170
	switch (action) {
1171 1172
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
1173
		refresh_zone_stat_thresholds();
1174
		start_cpu_timer(cpu);
1175
		node_set_state(cpu_to_node(cpu), N_CPU);
1176 1177 1178
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
1179
		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
1180 1181 1182 1183 1184 1185
		per_cpu(vmstat_work, cpu).work.func = NULL;
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		start_cpu_timer(cpu);
		break;
1186
	case CPU_DEAD:
1187
	case CPU_DEAD_FROZEN:
1188 1189 1190 1191
		refresh_zone_stat_thresholds();
		break;
	default:
		break;
1192 1193 1194 1195 1196 1197
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata vmstat_notifier =
	{ &vmstat_cpuup_callback, NULL, 0 };
1198
#endif
1199

Adrian Bunk's avatar
Adrian Bunk committed
1200
static int __init setup_vmstat(void)
1201
{
1202
#ifdef CONFIG_SMP
1203 1204
	int cpu;

1205 1206
	refresh_zone_stat_thresholds();
	register_cpu_notifier(&vmstat_notifier);
1207 1208 1209

	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
1210 1211 1212
#endif
#ifdef CONFIG_PROC_FS
	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
1213
	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
1214
	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
1215
	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
1216
#endif
1217 1218 1219
	return 0;
}
module_init(setup_vmstat)
1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307

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

static struct dentry *extfrag_debug_root;

/*
 * 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->node_id,
				zone->name);
	for (order = 0; order < MAX_ORDER; ++order) {
		fill_contig_page_info(zone, order, &info);
		index = unusable_free_index(order, &info);
		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
	}

	seq_putc(m, '\n');
}

/*
 * Display unusable free space index
 *
 * The unusable free space index measures how much of the available free
 * memory cannot be used to satisfy an allocation of a given size and is a
 * value between 0 and 1. The higher the value, the more of free memory is
 * unusable and by implication, the worse the external fragmentation is. This
 * can be expressed as a percentage by multiplying by 100.
 */
static int unusable_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
		return 0;

	walk_zones_in_node(m, pgdat, unusable_show_print);

	return 0;
}

static const struct seq_operations unusable_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= unusable_show,
};

static int unusable_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &unusable_op);
}

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

1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321
static void extfrag_show_print(struct seq_file *m,
					pg_data_t *pgdat, struct zone *zone)
{
	unsigned int order;
	int index;

	/* Alloc on stack as interrupts are disabled for zone walk */
	struct contig_page_info info;

	seq_printf(m, "Node %d, zone %8s ",
				pgdat->node_id,
				zone->name);
	for (order = 0; order < MAX_ORDER; ++order) {
		fill_contig_page_info(zone, order, &info);
1322
		index = __fragmentation_index(order, &info);
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 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
	}

	seq_putc(m, '\n');
}

/*
 * Display fragmentation index for orders that allocations would fail for
 */
static int extfrag_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	walk_zones_in_node(m, pgdat, extfrag_show_print);

	return 0;
}

static const struct seq_operations extfrag_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= extfrag_show,
};

static int extfrag_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &extfrag_op);
}

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

1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
static int __init extfrag_debug_init(void)
{
	extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
	if (!extfrag_debug_root)
		return -ENOMEM;

	if (!debugfs_create_file("unusable_index", 0444,
			extfrag_debug_root, NULL, &unusable_file_ops))
		return -ENOMEM;

1370 1371 1372 1373
	if (!debugfs_create_file("extfrag_index", 0444,
			extfrag_debug_root, NULL, &extfrag_file_ops))
		return -ENOMEM;

1374 1375 1376 1377 1378
	return 0;
}

module_init(extfrag_debug_init);
#endif