vmstat.c 28.5 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

21 22 23 24
#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
25
static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask)
26
{
Christoph Lameter's avatar
Christoph Lameter committed
27
	int cpu;
28 29 30 31
	int i;

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

32
	for_each_cpu(cpu, cpumask) {
33 34 35 36 37 38 39 40 41 42 43 44 45 46
		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
47
	get_online_cpus();
Rusty Russell's avatar
Rusty Russell committed
48
	sum_vm_events(ret, cpu_online_mask);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
49
	put_online_cpus();
50
}
51
EXPORT_SYMBOL_GPL(all_vm_events);
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73

#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 */

74 75 76 77 78 79 80 81 82 83
/*
 * 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

84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
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;
}
130 131

/*
132
 * Refresh the thresholds for each zone.
133
 */
134
static void refresh_zone_stat_thresholds(void)
135
{
136 137 138 139
	struct zone *zone;
	int cpu;
	int threshold;

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

		for_each_online_cpu(cpu)
144 145
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
146
	}
147 148 149 150 151 152 153 154
}

/*
 * For use when we know that interrupts are disabled.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
155 156
	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);

157
	s8 *p = pcp->vm_stat_diff + item;
158 159 160 161
	long x;

	x = delta + *p;

162
	if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
		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.
 *
197 198 199
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
200 201 202 203 204 205 206
 * 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.
 */
207
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
208
{
209
	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
210
	s8 *p = pcp->vm_stat_diff + item;
211 212 213

	(*p)++;

214 215 216 217 218
	if (unlikely(*p > pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p + overstep, zone, item);
		*p = -overstep;
219 220
	}
}
221 222 223 224 225

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
226 227
EXPORT_SYMBOL(__inc_zone_page_state);

228
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
229
{
230
	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
231
	s8 *p = pcp->vm_stat_diff + item;
232 233 234

	(*p)--;

235 236 237 238 239
	if (unlikely(*p < - pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p - overstep, zone, item);
		*p = overstep;
240 241
	}
}
242 243 244 245 246

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
247 248
EXPORT_SYMBOL(__dec_zone_page_state);

249 250 251 252 253 254 255 256 257
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);
}

258 259 260 261 262 263 264
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);
265
	__inc_zone_state(zone, item);
266 267 268 269 270 271 272 273 274
	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);
275
	__dec_zone_page_state(page, item);
276 277 278 279 280 281
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);

/*
 * Update the zone counters for one cpu.
282
 *
283 284 285 286
 * 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.
 *
287 288 289 290 291 292 293 294 295 296
 * 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.
297 298 299 300 301
 */
void refresh_cpu_vm_stats(int cpu)
{
	struct zone *zone;
	int i;
302
	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
303

304
	for_each_populated_zone(zone) {
305
		struct per_cpu_pageset *p;
306

307
		p = per_cpu_ptr(zone->pageset, cpu);
308 309

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
310
			if (p->vm_stat_diff[i]) {
311 312 313
				unsigned long flags;
				int v;

314
				local_irq_save(flags);
315
				v = p->vm_stat_diff[i];
316
				p->vm_stat_diff[i] = 0;
317 318 319
				local_irq_restore(flags);
				atomic_long_add(v, &zone->vm_stat[i]);
				global_diff[i] += v;
320 321 322 323
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
				p->expire = 3;
#endif
324
			}
325
		cond_resched();
326 327 328 329 330 331 332 333
#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.
		 */
334
		if (!p->expire || !p->pcp.count)
335 336 337 338 339 340 341 342 343 344 345 346 347 348
			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;

349 350
		if (p->pcp.count)
			drain_zone_pages(zone, &p->pcp);
351
#endif
352
	}
353 354 355 356

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (global_diff[i])
			atomic_long_add(global_diff[i], &vm_stat[i]);
357 358 359 360
}

#endif

361 362 363 364 365 366 367
#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.
 */
368
void zone_statistics(struct zone *preferred_zone, struct zone *z)
369
{
370
	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
371 372 373
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
374
		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
375
	}
376
	if (z->node == numa_node_id())
377 378 379 380 381 382
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
#ifdef CONFIG_COMPACTION
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);
	}
}
424 425 426 427 428 429 430 431

/*
 * 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
 */
432
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450
{
	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);
}
451 452 453 454 455 456 457 458 459

/* 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);
}
460 461 462
#endif

#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
463
#include <linux/proc_fs.h>
464 465
#include <linux/seq_file.h>

466 467 468 469 470
static char * const migratetype_names[MIGRATE_TYPES] = {
	"Unmovable",
	"Reclaimable",
	"Movable",
	"Reserve",
471
	"Isolate",
472 473
};

474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497
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)
{
}

498 499 500
/* 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 *))
501 502 503 504 505 506 507 508 509 510
{
	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);
511
		print(m, pgdat, zone);
512
		spin_unlock_irqrestore(&zone->lock, flags);
513 514
	}
}
515
#endif
516

517
#ifdef CONFIG_PROC_FS
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
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);
		}
560 561
		seq_putc(m, '\n');
	}
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
}

/* 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);
597 598 599

		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
600
			continue;
601

602 603
		mtype = get_pageblock_migratetype(page);

604 605
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637
	}

	/* 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;

638 639 640 641
	/* check memoryless node */
	if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
		return 0;

642 643 644 645 646 647
	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);

648 649 650
	return 0;
}

651
static const struct seq_operations fragmentation_op = {
652 653 654 655 656 657
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

658 659 660 661 662 663 664 665 666 667 668 669
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,
};

670
static const struct seq_operations pagetypeinfo_op = {
671 672 673 674 675 676
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= pagetypeinfo_show,
};

677 678 679 680 681 682 683 684 685 686 687 688
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,
};

689 690 691 692 693 694
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
#define TEXT_FOR_DMA(xx)
#endif

695 696 697 698 699 700 701 702 703 704 705 706
#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

707
#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
Mel Gorman's avatar
Mel Gorman committed
708
					TEXT_FOR_HIGHMEM(xx) xx "_movable",
709

710
static const char * const vmstat_text[] = {
711
	/* Zoned VM counters */
712
	"nr_free_pages",
713 714 715 716
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
717
	"nr_unevictable",
Nick Piggin's avatar
Nick Piggin committed
718
	"nr_mlock",
719
	"nr_anon_pages",
720
	"nr_mapped",
721
	"nr_file_pages",
722 723
	"nr_dirty",
	"nr_writeback",
724 725
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
726
	"nr_page_table_pages",
727
	"nr_kernel_stack",
728
	"nr_unstable",
729
	"nr_bounce",
730
	"nr_vmscan_write",
731
	"nr_writeback_temp",
732 733
	"nr_isolated_anon",
	"nr_isolated_file",
734
	"nr_shmem",
735 736 737 738 739 740 741 742 743
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif

744
#ifdef CONFIG_VM_EVENT_COUNTERS
745 746 747 748 749
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

750
	TEXTS_FOR_ZONES("pgalloc")
751 752 753 754 755 756 757 758

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

	"pgfault",
	"pgmajfault",

759 760 761 762
	TEXTS_FOR_ZONES("pgrefill")
	TEXTS_FOR_ZONES("pgsteal")
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
763

764 765 766
#ifdef CONFIG_NUMA
	"zone_reclaim_failed",
#endif
767 768 769 770
	"pginodesteal",
	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
771 772 773
	"kswapd_low_wmark_hit_quickly",
	"kswapd_high_wmark_hit_quickly",
	"kswapd_skip_congestion_wait",
774 775 776 777
	"pageoutrun",
	"allocstall",

	"pgrotated",
778 779 780 781 782

#ifdef CONFIG_COMPACTION
	"compact_blocks_moved",
	"compact_pages_moved",
	"compact_pagemigrate_failed",
783 784 785
	"compact_stall",
	"compact_fail",
	"compact_success",
786 787
#endif

788 789 790 791
#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
792 793 794
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
Nick Piggin's avatar
Nick Piggin committed
795 796 797 798
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",
799
	"unevictable_pgs_mlockfreed",
800
#endif
801 802
};

803 804
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
							struct zone *zone)
805
{
806 807 808 809 810 811 812
	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"
813
		   "\n        scanned  %lu"
814 815 816
		   "\n        spanned  %lu"
		   "\n        present  %lu",
		   zone_page_state(zone, NR_FREE_PAGES),
817 818 819
		   min_wmark_pages(zone),
		   low_wmark_pages(zone),
		   high_wmark_pages(zone),
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
		   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;

839
		pageset = per_cpu_ptr(zone->pageset, i);
840 841 842 843 844 845 846 847 848
		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);
849
#ifdef CONFIG_SMP
850 851
		seq_printf(m, "\n  vm stats threshold: %d",
				pageset->stat_threshold);
852
#endif
853
	}
854 855 856
	seq_printf(m,
		   "\n  all_unreclaimable: %u"
		   "\n  prev_priority:     %i"
857 858
		   "\n  start_pfn:         %lu"
		   "\n  inactive_ratio:    %u",
859
		   zone->all_unreclaimable,
860
		   zone->prev_priority,
861 862
		   zone->zone_start_pfn,
		   zone->inactive_ratio);
863 864 865 866 867 868 869 870 871 872
	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);
873 874 875
	return 0;
}

876
static const struct seq_operations zoneinfo_op = {
877 878 879 880 881 882 883
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

884 885 886 887 888 889 890 891 892 893 894 895
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,
};

896 897
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
898
	unsigned long *v;
899 900 901
#ifdef CONFIG_VM_EVENT_COUNTERS
	unsigned long *e;
#endif
902
	int i;
903 904 905 906

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

907
#ifdef CONFIG_VM_EVENT_COUNTERS
908
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long)
909 910 911 912 913
			+ sizeof(struct vm_event_state), GFP_KERNEL);
#else
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long),
			GFP_KERNEL);
#endif
914 915
	m->private = v;
	if (!v)
916
		return ERR_PTR(-ENOMEM);
917 918
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
919 920 921 922 923 924
#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
925
	return v + *pos;
926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
}

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;
}

951
static const struct seq_operations vmstat_op = {
952 953 954 955 956 957
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

958 959 960 961 962 963 964 965 966 967 968
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,
};
969 970
#endif /* CONFIG_PROC_FS */

971
#ifdef CONFIG_SMP
972
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
973
int sysctl_stat_interval __read_mostly = HZ;
974 975 976 977

static void vmstat_update(struct work_struct *w)
{
	refresh_cpu_vm_stats(smp_processor_id());
978
	schedule_delayed_work(&__get_cpu_var(vmstat_work),
979
		round_jiffies_relative(sysctl_stat_interval));
980 981
}

982
static void __cpuinit start_cpu_timer(int cpu)
983
{
984
	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
985

986 987
	INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
988 989
}

990 991 992 993 994 995 996 997
/*
 * 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)
{
998 999
	long cpu = (long)hcpu;

1000
	switch (action) {
1001 1002 1003
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		start_cpu_timer(cpu);
1004
		node_set_state(cpu_to_node(cpu), N_CPU);
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
		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;
1015
	case CPU_DEAD:
1016
	case CPU_DEAD_FROZEN:
1017 1018 1019 1020
		refresh_zone_stat_thresholds();
		break;
	default:
		break;
1021 1022 1023 1024 1025 1026
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata vmstat_notifier =
	{ &vmstat_cpuup_callback, NULL, 0 };
1027
#endif
1028

Adrian Bunk's avatar
Adrian Bunk committed
1029
static int __init setup_vmstat(void)
1030
{
1031
#ifdef CONFIG_SMP
1032 1033
	int cpu;

1034 1035
	refresh_zone_stat_thresholds();
	register_cpu_notifier(&vmstat_notifier);
1036 1037 1038

	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
1039 1040 1041
#endif
#ifdef CONFIG_PROC_FS
	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
1042
	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
1043
	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
1044
	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
1045
#endif
1046 1047 1048
	return 0;
}
module_init(setup_vmstat)
1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136

#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,
};

1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
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);
1151
		index = __fragmentation_index(order, &info);
1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188
		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,
};

1189 1190 1191 1192 1193 1194 1195 1196 1197 1198
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;

1199 1200 1201 1202
	if (!debugfs_create_file("extfrag_index", 0444,
			extfrag_debug_root, NULL, &extfrag_file_ops))
		return -ENOMEM;

1203 1204 1205 1206 1207
	return 0;
}

module_init(extfrag_debug_init);
#endif