vmstat.c 22.7 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
 */
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/cpu.h>
Adrian Bunk's avatar
Adrian Bunk committed
16
#include <linux/vmstat.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
17
#include <linux/sched.h>
18

19 20 21 22
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

Rusty Russell's avatar
Rusty Russell committed
23
static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask)
24
{
Christoph Lameter's avatar
Christoph Lameter committed
25
	int cpu;
26 27 28 29
	int i;

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

30
	for_each_cpu(cpu, cpumask) {
31 32 33 34 35 36 37 38 39 40 41 42 43 44
		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
45
	get_online_cpus();
Rusty Russell's avatar
Rusty Russell committed
46
	sum_vm_events(ret, cpu_online_mask);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
47
	put_online_cpus();
48
}
49
EXPORT_SYMBOL_GPL(all_vm_events);
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

#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 */

72 73 74 75 76 77 78 79 80 81
/*
 * 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

82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
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;
}
128 129

/*
130
 * Refresh the thresholds for each zone.
131
 */
132
static void refresh_zone_stat_thresholds(void)
133
{
134 135 136 137
	struct zone *zone;
	int cpu;
	int threshold;

138
	for_each_populated_zone(zone) {
139 140 141 142 143
		threshold = calculate_threshold(zone);

		for_each_online_cpu(cpu)
			zone_pcp(zone, cpu)->stat_threshold = threshold;
	}
144 145 146 147 148 149 150 151
}

/*
 * For use when we know that interrupts are disabled.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
152 153
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
154 155 156 157
	long x;

	x = delta + *p;

158
	if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192
		zone_page_state_add(x, zone, item);
		x = 0;
	}
	*p = x;
}
EXPORT_SYMBOL(__mod_zone_page_state);

/*
 * For an unknown interrupt state
 */
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);

/*
 * 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.
 *
193 194 195
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
196 197 198 199 200 201 202
 * 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.
 */
203
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
204
{
205 206
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
207 208 209

	(*p)++;

210 211 212 213 214
	if (unlikely(*p > pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p + overstep, zone, item);
		*p = -overstep;
215 216
	}
}
217 218 219 220 221

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
222 223
EXPORT_SYMBOL(__inc_zone_page_state);

224
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
225
{
226 227
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
228 229 230

	(*p)--;

231 232 233 234 235
	if (unlikely(*p < - pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p - overstep, zone, item);
		*p = overstep;
236 237
	}
}
238 239 240 241 242

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
243 244
EXPORT_SYMBOL(__dec_zone_page_state);

245 246 247 248 249 250 251 252 253
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);
}

254 255 256 257 258 259 260
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);
261
	__inc_zone_state(zone, item);
262 263 264 265 266 267 268 269 270
	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);
271
	__dec_zone_page_state(page, item);
272 273 274 275 276 277
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);

/*
 * Update the zone counters for one cpu.
278
 *
279 280 281 282
 * 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.
 *
283 284 285 286 287 288 289 290 291 292
 * 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.
293 294 295 296 297
 */
void refresh_cpu_vm_stats(int cpu)
{
	struct zone *zone;
	int i;
298
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
299

300
	for_each_populated_zone(zone) {
301
		struct per_cpu_pageset *p;
302

303
		p = zone_pcp(zone, cpu);
304 305

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
306
			if (p->vm_stat_diff[i]) {
307 308 309
				unsigned long flags;
				int v;

310
				local_irq_save(flags);
311
				v = p->vm_stat_diff[i];
312
				p->vm_stat_diff[i] = 0;
313 314 315
				local_irq_restore(flags);
				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
316 317 318 319
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
				p->expire = 3;
#endif
320
			}
321
		cond_resched();
322 323 324 325 326 327 328 329
#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.
		 */
330
		if (!p->expire || !p->pcp.count)
331 332 333 334 335 336 337 338 339 340 341 342 343 344
			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;

345 346
		if (p->pcp.count)
			drain_zone_pages(zone, &p->pcp);
347
#endif
348
	}
349 350 351 352

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (global_diff[i])
			atomic_long_add(global_diff[i], &vm_stat[i]);
353 354 355 356
}

#endif

357 358 359 360 361 362 363
#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.
 */
364
void zone_statistics(struct zone *preferred_zone, struct zone *z)
365
{
366
	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
367 368 369
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
370
		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
371
	}
372
	if (z->node == numa_node_id())
373 374 375 376 377 378
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

379
#ifdef CONFIG_PROC_FS
380
#include <linux/proc_fs.h>
381 382
#include <linux/seq_file.h>

383 384 385 386 387
static char * const migratetype_names[MIGRATE_TYPES] = {
	"Unmovable",
	"Reclaimable",
	"Movable",
	"Reserve",
388
	"Isolate",
389 390
};

391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414
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)
{
}

415 416 417
/* 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 *))
418 419 420 421 422 423 424 425 426 427
{
	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);
428
		print(m, pgdat, zone);
429
		spin_unlock_irqrestore(&zone->lock, flags);
430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474
	}
}

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);
		}
475 476
		seq_putc(m, '\n');
	}
477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
}

/* 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);
512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
#ifdef CONFIG_ARCH_FLATMEM_HAS_HOLES
		/*
		 * Ordinarily, memory holes in flatmem still have a valid
		 * memmap for the PFN range. However, an architecture for
		 * embedded systems (e.g. ARM) can free up the memmap backing
		 * holes to save memory on the assumption the memmap is
		 * never used. The page_zone linkages are then broken even
		 * though pfn_valid() returns true. Skip the page if the
		 * linkages are broken. Even if this test passed, the impact
		 * is that the counters for the movable type are off but
		 * fragmentation monitoring is likely meaningless on small
		 * systems.
		 */
		if (page_zone(page) != zone)
			continue;
#endif
528 529
		mtype = get_pageblock_migratetype(page);

530 531
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563
	}

	/* 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;

564 565 566 567
	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
		return 0;

568 569 570 571 572 573
	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);

574 575 576
	return 0;
}

577
static const struct seq_operations fragmentation_op = {
578 579 580 581 582 583
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

584 585 586 587 588 589 590 591 592 593 594 595
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,
};

596
static const struct seq_operations pagetypeinfo_op = {
597 598 599 600 601 602
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

603 604 605 606 607 608 609 610 611 612 613 614
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,
};

615 616 617 618 619 620
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
#define TEXT_FOR_DMA(xx)
#endif

621 622 623 624 625 626 627 628 629 630 631 632
#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

633
#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
Mel Gorman's avatar
Mel Gorman committed
634
					TEXT_FOR_HIGHMEM(xx) xx "_movable",
635

636
static const char * const vmstat_text[] = {
637
	/* Zoned VM counters */
638
	"nr_free_pages",
639 640 641 642
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
643 644
#ifdef CONFIG_UNEVICTABLE_LRU
	"nr_unevictable",
Nick Piggin's avatar
Nick Piggin committed
645
	"nr_mlock",
646
#endif
647
	"nr_anon_pages",
648
	"nr_mapped",
649
	"nr_file_pages",
650 651
	"nr_dirty",
	"nr_writeback",
652 653
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
654
	"nr_page_table_pages",
655
	"nr_unstable",
656
	"nr_bounce",
657
	"nr_vmscan_write",
658
	"nr_writeback_temp",
659

660 661 662 663 664 665 666 667 668
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif

669
#ifdef CONFIG_VM_EVENT_COUNTERS
670 671 672 673 674
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

675
	TEXTS_FOR_ZONES("pgalloc")
676 677 678 679 680 681 682 683

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

	"pgfault",
	"pgmajfault",

684 685 686 687
	TEXTS_FOR_ZONES("pgrefill")
	TEXTS_FOR_ZONES("pgsteal")
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
688 689 690 691 692 693 694 695 696

	"pginodesteal",
	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
	"pageoutrun",
	"allocstall",

	"pgrotated",
697 698 699 700
#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
701 702 703 704
#ifdef CONFIG_UNEVICTABLE_LRU
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
Nick Piggin's avatar
Nick Piggin committed
705 706 707 708
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",
709
	"unevictable_pgs_mlockfreed",
710
#endif
711
#endif
712 713
};

714 715
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
716
{
717 718 719 720 721 722 723
	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"
724
		   "\n        scanned  %lu (aa: %lu ia: %lu af: %lu if: %lu)"
725 726 727 728 729 730 731
		   "\n        spanned  %lu"
		   "\n        present  %lu",
		   zone_page_state(zone, NR_FREE_PAGES),
		   zone->pages_min,
		   zone->pages_low,
		   zone->pages_high,
		   zone->pages_scanned,
732 733 734 735
		   zone->lru[LRU_ACTIVE_ANON].nr_scan,
		   zone->lru[LRU_INACTIVE_ANON].nr_scan,
		   zone->lru[LRU_ACTIVE_FILE].nr_scan,
		   zone->lru[LRU_INACTIVE_FILE].nr_scan,
736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
		   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;

		pageset = zone_pcp(zone, i);
755 756 757 758 759 760 761 762 763
		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);
764
#ifdef CONFIG_SMP
765 766
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
767
#endif
768
	}
769 770 771
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
		   "\n  prev_priority:     %i"
772 773
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
774
			   zone_is_all_unreclaimable(zone),
775
		   zone->prev_priority,
776 777
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
778 779 780 781 782 783 784 785 786 787
	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);
788 789 790
	return 0;
}

791
static const struct seq_operations zoneinfo_op = {
792 793 794 795 796 797 798
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

799 800 801 802 803 804 805 806 807 808 809 810
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,
};

811 812
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
813
	unsigned long *v;
814 815 816
#ifdef CONFIG_VM_EVENT_COUNTERS
	unsigned long *e;
#endif
817
	int i;
818 819 820 821

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;

822
#ifdef CONFIG_VM_EVENT_COUNTERS
823
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long)
824 825 826 827 828
			+ sizeof(struct vm_event_state), GFP_KERNEL);
#else
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long),
			GFP_KERNEL);
#endif
829 830
	m->private = v;
	if (!v)
831
		return ERR_PTR(-ENOMEM);
832 833
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
834 835 836 837 838 839
#ifdef CONFIG_VM_EVENT_COUNTERS
	e = v + NR_VM_ZONE_STAT_ITEMS;
	all_vm_events(e);
	e[PGPGIN] /= 2;		/* sectors -> kbytes */
	e[PGPGOUT] /= 2;
#endif
840
	return v + *pos;
841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865
}

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;
}

866
static const struct seq_operations vmstat_op = {
867 868 869 870 871 872
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

873 874 875 876 877 878 879 880 881 882 883
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,
};
884 885
#endif /* CONFIG_PROC_FS */

886
#ifdef CONFIG_SMP
887
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
888
int sysctl_stat_interval __read_mostly = HZ;
889 890 891 892

static void vmstat_update(struct work_struct *w)
{
	refresh_cpu_vm_stats(smp_processor_id());
893
	schedule_delayed_work(&__get_cpu_var(vmstat_work),
894
		round_jiffies_relative(sysctl_stat_interval));
895 896
}

897
static void __cpuinit start_cpu_timer(int cpu)
898 899 900
{
	struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);

901
	INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
902 903
	schedule_delayed_work_on(cpu, vmstat_work,
				 __round_jiffies_relative(HZ, cpu));
904 905
}

906 907 908 909 910 911 912 913
/*
 * 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)
{
914 915
	long cpu = (long)hcpu;

916
	switch (action) {
917 918 919 920 921 922 923 924 925 926 927 928 929
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		start_cpu_timer(cpu);
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu));
		per_cpu(vmstat_work, cpu).work.func = NULL;
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		start_cpu_timer(cpu);
		break;
930
	case CPU_DEAD:
931
	case CPU_DEAD_FROZEN:
932 933 934 935
		refresh_zone_stat_thresholds();
		break;
	default:
		break;
936 937 938 939 940 941
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata vmstat_notifier =
	{ &vmstat_cpuup_callback, NULL, 0 };
942
#endif
943

Adrian Bunk's avatar
Adrian Bunk committed
944
static int __init setup_vmstat(void)
945
{
946
#ifdef CONFIG_SMP
947 948
	int cpu;

949 950
	refresh_zone_stat_thresholds();
	register_cpu_notifier(&vmstat_notifier);
951 952 953

	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
954 955 956
#endif
#ifdef CONFIG_PROC_FS
	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
957
	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
958
	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
959
	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
960
#endif
961 962 963
	return 0;
}
module_init(setup_vmstat)