vmstat.c 52.7 KB
Newer Older
1 2 3 4 5
/*
 *  linux/mm/vmstat.c
 *
 *  Manages VM statistics
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
6 7 8 9
 *
 *  zoned VM statistics
 *  Copyright (C) 2006 Silicon Graphics, Inc.,
 *		Christoph Lameter <christoph@lameter.com>
10
 *  Copyright (C) 2008-2014 Christoph Lameter
11
 */
12
#include <linux/fs.h>
13
#include <linux/mm.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
14
#include <linux/err.h>
15
#include <linux/module.h>
16
#include <linux/slab.h>
17
#include <linux/cpu.h>
18
#include <linux/cpumask.h>
Adrian Bunk's avatar
Adrian Bunk committed
19
#include <linux/vmstat.h>
20 21 22
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
23
#include <linux/sched.h>
24
#include <linux/math64.h>
25
#include <linux/writeback.h>
26
#include <linux/compaction.h>
27
#include <linux/mm_inline.h>
28 29
#include <linux/page_ext.h>
#include <linux/page_owner.h>
30 31

#include "internal.h"
32

33 34
#define NUMA_STATS_THRESHOLD (U16_MAX - 2)

35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105
#ifdef CONFIG_NUMA
int sysctl_vm_numa_stat = ENABLE_NUMA_STAT;

/* zero numa counters within a zone */
static void zero_zone_numa_counters(struct zone *zone)
{
	int item, cpu;

	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) {
		atomic_long_set(&zone->vm_numa_stat[item], 0);
		for_each_online_cpu(cpu)
			per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]
						= 0;
	}
}

/* zero numa counters of all the populated zones */
static void zero_zones_numa_counters(void)
{
	struct zone *zone;

	for_each_populated_zone(zone)
		zero_zone_numa_counters(zone);
}

/* zero global numa counters */
static void zero_global_numa_counters(void)
{
	int item;

	for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++)
		atomic_long_set(&vm_numa_stat[item], 0);
}

static void invalid_numa_statistics(void)
{
	zero_zones_numa_counters();
	zero_global_numa_counters();
}

static DEFINE_MUTEX(vm_numa_stat_lock);

int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *length, loff_t *ppos)
{
	int ret, oldval;

	mutex_lock(&vm_numa_stat_lock);
	if (write)
		oldval = sysctl_vm_numa_stat;
	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (ret || !write)
		goto out;

	if (oldval == sysctl_vm_numa_stat)
		goto out;
	else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) {
		static_branch_enable(&vm_numa_stat_key);
		pr_info("enable numa statistics\n");
	} else {
		static_branch_disable(&vm_numa_stat_key);
		invalid_numa_statistics();
		pr_info("disable numa statistics, and clear numa counters\n");
	}

out:
	mutex_unlock(&vm_numa_stat_lock);
	return ret;
}
#endif

106 107 108 109
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);

110
static void sum_vm_events(unsigned long *ret)
111
{
Christoph Lameter's avatar
Christoph Lameter committed
112
	int cpu;
113 114 115 116
	int i;

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

117
	for_each_online_cpu(cpu) {
118 119 120 121 122 123 124 125 126 127 128 129 130 131
		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
132
	get_online_cpus();
133
	sum_vm_events(ret);
KOSAKI Motohiro's avatar
KOSAKI Motohiro committed
134
	put_online_cpus();
135
}
136
EXPORT_SYMBOL_GPL(all_vm_events);
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156

/*
 * Fold the foreign cpu events into our own.
 *
 * This is adding to the events on one processor
 * but keeps the global counts constant.
 */
void vm_events_fold_cpu(int cpu)
{
	struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu);
	int i;

	for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
		count_vm_events(i, fold_state->event[i]);
		fold_state->event[i] = 0;
	}
}

#endif /* CONFIG_VM_EVENT_COUNTERS */

157 158 159 160 161
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
162
atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
163
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp;
164 165
atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
EXPORT_SYMBOL(vm_zone_stat);
166
EXPORT_SYMBOL(vm_numa_stat);
167
EXPORT_SYMBOL(vm_node_stat);
168 169 170

#ifdef CONFIG_SMP

171
int calculate_pressure_threshold(struct zone *zone)
172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
{
	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;
}

195
int calculate_normal_threshold(struct zone *zone)
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
{
	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
	 */

230
	mem = zone->managed_pages >> (27 - PAGE_SHIFT);
231 232 233 234 235 236 237 238 239 240

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

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

	return threshold;
}
241 242

/*
243
 * Refresh the thresholds for each zone.
244
 */
245
void refresh_zone_stat_thresholds(void)
246
{
247
	struct pglist_data *pgdat;
248 249 250 251
	struct zone *zone;
	int cpu;
	int threshold;

252 253 254 255 256 257 258
	/* Zero current pgdat thresholds */
	for_each_online_pgdat(pgdat) {
		for_each_online_cpu(cpu) {
			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0;
		}
	}

259
	for_each_populated_zone(zone) {
260
		struct pglist_data *pgdat = zone->zone_pgdat;
261 262
		unsigned long max_drift, tolerate_drift;

263
		threshold = calculate_normal_threshold(zone);
264

265 266 267
		for_each_online_cpu(cpu) {
			int pgdat_threshold;

268 269
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
270

271 272 273 274 275 276
			/* Base nodestat threshold on the largest populated zone. */
			pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
			per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
				= max(threshold, pgdat_threshold);
		}

277 278 279 280 281 282 283 284 285 286
		/*
		 * 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;
287
	}
288 289
}

290 291
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *))
292 293 294 295 296 297 298 299 300 301 302
{
	struct zone *zone;
	int cpu;
	int threshold;
	int i;

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

303
		threshold = (*calculate_pressure)(zone);
304
		for_each_online_cpu(cpu)
305 306 307 308 309
			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
							= threshold;
	}
}

310
/*
311 312 313
 * For use when we know that interrupts are disabled,
 * or when we know that preemption is disabled and that
 * particular counter cannot be updated from interrupt context.
314 315
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
316
			   long delta)
317
{
318 319
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
320
	long x;
321 322 323
	long t;

	x = delta + __this_cpu_read(*p);
324

325
	t = __this_cpu_read(pcp->stat_threshold);
326

327
	if (unlikely(x > t || x < -t)) {
328 329 330
		zone_page_state_add(x, zone, item);
		x = 0;
	}
331
	__this_cpu_write(*p, x);
332 333 334
}
EXPORT_SYMBOL(__mod_zone_page_state);

335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
				long delta)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	long x;
	long t;

	x = delta + __this_cpu_read(*p);

	t = __this_cpu_read(pcp->stat_threshold);

	if (unlikely(x > t || x < -t)) {
		node_page_state_add(x, pgdat, item);
		x = 0;
	}
	__this_cpu_write(*p, x);
}
EXPORT_SYMBOL(__mod_node_page_state);

355 356 357 358 359 360 361 362 363 364 365 366 367
/*
 * 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.
 *
368 369 370
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
371 372 373 374 375 376 377
 * 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.
 */
378
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
379
{
380 381 382
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
383

384
	v = __this_cpu_inc_return(*p);
385 386 387
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v > t)) {
		s8 overstep = t >> 1;
388

389 390
		zone_page_state_add(v + overstep, zone, item);
		__this_cpu_write(*p, -overstep);
391 392
	}
}
393

394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	s8 v, t;

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

		node_page_state_add(v + overstep, pgdat, item);
		__this_cpu_write(*p, -overstep);
	}
}

410 411 412 413
void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
414 415
EXPORT_SYMBOL(__inc_zone_page_state);

416 417 418 419 420 421
void __inc_node_page_state(struct page *page, enum node_stat_item item)
{
	__inc_node_state(page_pgdat(page), item);
}
EXPORT_SYMBOL(__inc_node_page_state);

422
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
423
{
424 425 426
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	s8 v, t;
427

428
	v = __this_cpu_dec_return(*p);
429 430 431
	t = __this_cpu_read(pcp->stat_threshold);
	if (unlikely(v < - t)) {
		s8 overstep = t >> 1;
432

433 434
		zone_page_state_add(v - overstep, zone, item);
		__this_cpu_write(*p, overstep);
435 436
	}
}
437

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	s8 v, t;

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

		node_page_state_add(v - overstep, pgdat, item);
		__this_cpu_write(*p, overstep);
	}
}

454 455 456 457
void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
458 459
EXPORT_SYMBOL(__dec_zone_page_state);

460 461 462 463 464 465
void __dec_node_page_state(struct page *page, enum node_stat_item item)
{
	__dec_node_state(page_pgdat(page), item);
}
EXPORT_SYMBOL(__dec_node_page_state);

466
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
467 468 469 470 471 472 473 474 475 476 477 478
/*
 * 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
*/
479 480
static inline void mod_zone_state(struct zone *zone,
       enum zone_stat_item item, long delta, int overstep_mode)
481 482 483 484 485 486 487 488 489 490 491
{
	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
492 493 494 495 496 497
		 * rescheduled while executing here. However, the next
		 * counter update will apply the threshold again and
		 * therefore bring the counter under the threshold again.
		 *
		 * Most of the time the thresholds are the same anyways
		 * for all cpus in a zone.
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517
		 */
		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,
518
			 long delta)
519
{
520
	mod_zone_state(zone, item, delta, 0);
521 522 523 524 525
}
EXPORT_SYMBOL(mod_zone_page_state);

void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
526
	mod_zone_state(page_zone(page), item, 1, 1);
527 528 529 530 531
}
EXPORT_SYMBOL(inc_zone_page_state);

void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
532
	mod_zone_state(page_zone(page), item, -1, -1);
533 534
}
EXPORT_SYMBOL(dec_zone_page_state);
535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596

static inline void mod_node_state(struct pglist_data *pgdat,
       enum node_stat_item item, int delta, int overstep_mode)
{
	struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
	s8 __percpu *p = pcp->vm_node_stat_diff + item;
	long o, n, t, z;

	do {
		z = 0;  /* overflow to node 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 next
		 * counter update will apply the threshold again and
		 * therefore bring the counter under the threshold again.
		 *
		 * Most of the time the thresholds are the same anyways
		 * for all cpus in a node.
		 */
		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 node counters */
			z = n + os;
			n = -os;
		}
	} while (this_cpu_cmpxchg(*p, o, n) != o);

	if (z)
		node_page_state_add(z, pgdat, item);
}

void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
					long delta)
{
	mod_node_state(pgdat, item, delta, 0);
}
EXPORT_SYMBOL(mod_node_page_state);

void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	mod_node_state(pgdat, item, 1, 1);
}

void inc_node_page_state(struct page *page, enum node_stat_item item)
{
	mod_node_state(page_pgdat(page), item, 1, 1);
}
EXPORT_SYMBOL(inc_node_page_state);

void dec_node_page_state(struct page *page, enum node_stat_item item)
{
	mod_node_state(page_pgdat(page), item, -1, -1);
}
EXPORT_SYMBOL(dec_node_page_state);
597 598 599 600 601
#else
/*
 * Use interrupt disable to serialize counter updates
 */
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
602
			 long delta)
603 604 605 606 607 608 609 610 611
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_zone_page_state(zone, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_zone_page_state);

612 613 614 615 616 617 618
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);
619
	__inc_zone_state(zone, item);
620 621 622 623 624 625 626 627 628
	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);
629
	__dec_zone_page_state(page, item);
630 631 632 633
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);

634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676
void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
	__inc_node_state(pgdat, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_node_state);

void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
					long delta)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_node_page_state(pgdat, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_node_page_state);

void inc_node_page_state(struct page *page, enum node_stat_item item)
{
	unsigned long flags;
	struct pglist_data *pgdat;

	pgdat = page_pgdat(page);
	local_irq_save(flags);
	__inc_node_state(pgdat, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_node_page_state);

void dec_node_page_state(struct page *page, enum node_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
	__dec_node_page_state(page, item);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_node_page_state);
#endif
677 678 679 680 681

/*
 * Fold a differential into the global counters.
 * Returns the number of counters updated.
 */
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
#ifdef CONFIG_NUMA
static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
{
	int i;
	int changes = 0;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (zone_diff[i]) {
			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		if (numa_diff[i]) {
			atomic_long_add(numa_diff[i], &vm_numa_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
		if (node_diff[i]) {
			atomic_long_add(node_diff[i], &vm_node_stat[i]);
			changes++;
	}
	return changes;
}
#else
708
static int fold_diff(int *zone_diff, int *node_diff)
Christoph Lameter's avatar
Christoph Lameter committed
709 710
{
	int i;
711
	int changes = 0;
Christoph Lameter's avatar
Christoph Lameter committed
712 713

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
714 715 716 717 718 719 720 721
		if (zone_diff[i]) {
			atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
			changes++;
	}

	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
		if (node_diff[i]) {
			atomic_long_add(node_diff[i], &vm_node_stat[i]);
722 723 724
			changes++;
	}
	return changes;
Christoph Lameter's avatar
Christoph Lameter committed
725
}
726
#endif /* CONFIG_NUMA */
Christoph Lameter's avatar
Christoph Lameter committed
727

728
/*
729
 * Update the zone counters for the current cpu.
730
 *
731 732 733 734 735 736 737 738 739 740
 * 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.
741 742
 *
 * The function returns the number of global counters updated.
743
 */
744
static int refresh_cpu_vm_stats(bool do_pagesets)
745
{
746
	struct pglist_data *pgdat;
747 748
	struct zone *zone;
	int i;
749
	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
750 751 752
#ifdef CONFIG_NUMA
	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
#endif
753
	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
754
	int changes = 0;
755

756
	for_each_populated_zone(zone) {
757
		struct per_cpu_pageset __percpu *p = zone->pageset;
758

759 760
		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
			int v;
761

762 763
			v = this_cpu_xchg(p->vm_stat_diff[i], 0);
			if (v) {
764 765

				atomic_long_add(v, &zone->vm_stat[i]);
766
				global_zone_diff[i] += v;
767 768
#ifdef CONFIG_NUMA
				/* 3 seconds idle till flush */
769
				__this_cpu_write(p->expire, 3);
770
#endif
771
			}
772
		}
773
#ifdef CONFIG_NUMA
774 775 776 777 778 779 780 781 782 783 784 785
		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
			int v;

			v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0);
			if (v) {

				atomic_long_add(v, &zone->vm_numa_stat[i]);
				global_numa_diff[i] += v;
				__this_cpu_write(p->expire, 3);
			}
		}

786 787 788 789 790 791 792 793 794 795
		if (do_pagesets) {
			cond_resched();
			/*
			 * 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.
			 */
			if (!__this_cpu_read(p->expire) ||
796
			       !__this_cpu_read(p->pcp.count))
797
				continue;
798

799 800 801 802 803 804 805
			/*
			 * We never drain zones local to this processor.
			 */
			if (zone_to_nid(zone) == numa_node_id()) {
				__this_cpu_write(p->expire, 0);
				continue;
			}
806

807 808
			if (__this_cpu_dec_return(p->expire))
				continue;
809

810 811 812 813
			if (__this_cpu_read(p->pcp.count)) {
				drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
				changes++;
			}
814
		}
815
#endif
816
	}
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831

	for_each_online_pgdat(pgdat) {
		struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats;

		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
			int v;

			v = this_cpu_xchg(p->vm_node_stat_diff[i], 0);
			if (v) {
				atomic_long_add(v, &pgdat->vm_stat[i]);
				global_node_diff[i] += v;
			}
		}
	}

832 833 834 835
#ifdef CONFIG_NUMA
	changes += fold_diff(global_zone_diff, global_numa_diff,
			     global_node_diff);
#else
836
	changes += fold_diff(global_zone_diff, global_node_diff);
837
#endif
838
	return changes;
839 840
}

841 842 843 844 845 846 847
/*
 * Fold the data for an offline cpu into the global array.
 * There cannot be any access by the offline cpu and therefore
 * synchronization is simplified.
 */
void cpu_vm_stats_fold(int cpu)
{
848
	struct pglist_data *pgdat;
849 850
	struct zone *zone;
	int i;
851
	int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
852 853 854
#ifdef CONFIG_NUMA
	int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
#endif
855
	int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
856 857 858 859 860 861 862 863 864 865 866 867 868

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *p;

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

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
			if (p->vm_stat_diff[i]) {
				int v;

				v = p->vm_stat_diff[i];
				p->vm_stat_diff[i] = 0;
				atomic_long_add(v, &zone->vm_stat[i]);
869
				global_zone_diff[i] += v;
870
			}
871 872 873 874 875 876 877 878 879 880 881 882

#ifdef CONFIG_NUMA
		for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
			if (p->vm_numa_stat_diff[i]) {
				int v;

				v = p->vm_numa_stat_diff[i];
				p->vm_numa_stat_diff[i] = 0;
				atomic_long_add(v, &zone->vm_numa_stat[i]);
				global_numa_diff[i] += v;
			}
#endif
883 884
	}

885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900
	for_each_online_pgdat(pgdat) {
		struct per_cpu_nodestat *p;

		p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);

		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
			if (p->vm_node_stat_diff[i]) {
				int v;

				v = p->vm_node_stat_diff[i];
				p->vm_node_stat_diff[i] = 0;
				atomic_long_add(v, &pgdat->vm_stat[i]);
				global_node_diff[i] += v;
			}
	}

901 902 903
#ifdef CONFIG_NUMA
	fold_diff(global_zone_diff, global_numa_diff, global_node_diff);
#else
904
	fold_diff(global_zone_diff, global_node_diff);
905
#endif
906 907
}

908 909 910 911
/*
 * this is only called if !populated_zone(zone), which implies no other users of
 * pset->vm_stat_diff[] exsist.
 */
912 913 914 915 916 917 918 919 920
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
{
	int i;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		if (pset->vm_stat_diff[i]) {
			int v = pset->vm_stat_diff[i];
			pset->vm_stat_diff[i] = 0;
			atomic_long_add(v, &zone->vm_stat[i]);
921
			atomic_long_add(v, &vm_zone_stat[i]);
922
		}
923 924 925 926 927 928 929 930 931 932 933

#ifdef CONFIG_NUMA
	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
		if (pset->vm_numa_stat_diff[i]) {
			int v = pset->vm_numa_stat_diff[i];

			pset->vm_numa_stat_diff[i] = 0;
			atomic_long_add(v, &zone->vm_numa_stat[i]);
			atomic_long_add(v, &vm_numa_stat[i]);
		}
#endif
934
}
935 936
#endif

937
#ifdef CONFIG_NUMA
938 939 940 941
void __inc_numa_state(struct zone *zone,
				 enum numa_stat_item item)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
942 943
	u16 __percpu *p = pcp->vm_numa_stat_diff + item;
	u16 v;
944 945 946

	v = __this_cpu_inc_return(*p);

947 948 949
	if (unlikely(v > NUMA_STATS_THRESHOLD)) {
		zone_numa_state_add(v, zone, item);
		__this_cpu_write(*p, 0);
950 951 952
	}
}

953
/*
954 955 956
 * Determine the per node value of a stat item. This function
 * is called frequently in a NUMA machine, so try to be as
 * frugal as possible.
957
 */
958 959
unsigned long sum_zone_node_page_state(int node,
				 enum zone_stat_item item)
960 961
{
	struct zone *zones = NODE_DATA(node)->node_zones;
962 963
	int i;
	unsigned long count = 0;
964

965 966 967 968
	for (i = 0; i < MAX_NR_ZONES; i++)
		count += zone_page_state(zones + i, item);

	return count;
969 970
}

971 972 973 974
/*
 * Determine the per node value of a numa stat item. To avoid deviation,
 * the per cpu stat number in vm_numa_stat_diff[] is also included.
 */
975 976 977 978 979 980 981 982
unsigned long sum_zone_numa_state(int node,
				 enum numa_stat_item item)
{
	struct zone *zones = NODE_DATA(node)->node_zones;
	int i;
	unsigned long count = 0;

	for (i = 0; i < MAX_NR_ZONES; i++)
983
		count += zone_numa_state_snapshot(zones + i, item);
984 985 986 987

	return count;
}

988 989 990 991 992 993 994 995 996 997 998 999 1000
/*
 * Determine the per node value of a stat item.
 */
unsigned long node_page_state(struct pglist_data *pgdat,
				enum node_stat_item item)
{
	long x = atomic_long_read(&pgdat->vm_stat[item]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}
1001 1002
#endif

1003
#ifdef CONFIG_COMPACTION
1004

1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044
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);
	}
}
1045 1046 1047 1048 1049 1050 1051 1052

/*
 * 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
 */
1053
static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
1054 1055 1056
{
	unsigned long requested = 1UL << order;

1057 1058 1059
	if (WARN_ON_ONCE(order >= MAX_ORDER))
		return 0;

1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
	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);
}
1075 1076 1077 1078 1079 1080 1081 1082 1083

/* 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);
}
1084 1085
#endif

1086
#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
#define TEXT_FOR_DMA(xx)
#endif

#ifdef CONFIG_ZONE_DMA32
#define TEXT_FOR_DMA32(xx) xx "_dma32",
#else
#define TEXT_FOR_DMA32(xx)
#endif

#ifdef CONFIG_HIGHMEM
#define TEXT_FOR_HIGHMEM(xx) xx "_high",
#else
#define TEXT_FOR_HIGHMEM(xx)
#endif

#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
					TEXT_FOR_HIGHMEM(xx) xx "_movable",

const char * const vmstat_text[] = {
1109
	/* enum zone_stat_item countes */
1110
	"nr_free_pages",
Minchan Kim's avatar
Minchan Kim committed
1111 1112 1113 1114 1115
	"nr_zone_inactive_anon",
	"nr_zone_active_anon",
	"nr_zone_inactive_file",
	"nr_zone_active_file",
	"nr_zone_unevictable",
1116
	"nr_zone_write_pending",
1117 1118 1119 1120
	"nr_mlock",
	"nr_page_table_pages",
	"nr_kernel_stack",
	"nr_bounce",
Minchan Kim's avatar
Minchan Kim committed
1121 1122 1123
#if IS_ENABLED(CONFIG_ZSMALLOC)
	"nr_zspages",
#endif
1124 1125 1126
	"nr_free_cma",

	/* enum numa_stat_item counters */
1127 1128 1129 1130 1131 1132 1133 1134
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif
1135

1136 1137 1138 1139 1140 1141
	/* Node-based counters */
	"nr_inactive_anon",
	"nr_active_anon",
	"nr_inactive_file",
	"nr_active_file",
	"nr_unevictable",
1142 1143
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
1144 1145
	"nr_isolated_anon",
	"nr_isolated_file",
1146 1147 1148
	"workingset_refault",
	"workingset_activate",
	"workingset_nodereclaim",
1149 1150
	"nr_anon_pages",
	"nr_mapped",
1151 1152 1153 1154 1155 1156 1157 1158 1159
	"nr_file_pages",
	"nr_dirty",
	"nr_writeback",
	"nr_writeback_temp",
	"nr_shmem",
	"nr_shmem_hugepages",
	"nr_shmem_pmdmapped",
	"nr_anon_transparent_hugepages",
	"nr_unstable",
1160 1161 1162 1163
	"nr_vmscan_write",
	"nr_vmscan_immediate_reclaim",
	"nr_dirtied",
	"nr_written",
1164

1165
	/* enum writeback_stat_item counters */
1166 1167 1168 1169
	"nr_dirty_threshold",
	"nr_dirty_background_threshold",

#ifdef CONFIG_VM_EVENT_COUNTERS
1170
	/* enum vm_event_item counters */
1171 1172 1173 1174 1175 1176
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

	TEXTS_FOR_ZONES("pgalloc")
1177 1178
	TEXTS_FOR_ZONES("allocstall")
	TEXTS_FOR_ZONES("pgskip")
1179 1180 1181 1182

	"pgfree",
	"pgactivate",
	"pgdeactivate",
1183
	"pglazyfree",
1184 1185 1186

	"pgfault",
	"pgmajfault",
Minchan Kim's avatar
Minchan Kim committed
1187
	"pglazyfreed",
1188

1189 1190 1191 1192 1193
	"pgrefill",
	"pgsteal_kswapd",
	"pgsteal_direct",
	"pgscan_kswapd",
	"pgscan_direct",
1194
	"pgscan_direct_throttle",
1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207

#ifdef CONFIG_NUMA
	"zone_reclaim_failed",
#endif
	"pginodesteal",
	"slabs_scanned",
	"kswapd_inodesteal",
	"kswapd_low_wmark_hit_quickly",
	"kswapd_high_wmark_hit_quickly",
	"pageoutrun",

	"pgrotated",

1208 1209
	"drop_pagecache",
	"drop_slab",
1210
	"oom_kill",
1211

1212 1213
#ifdef CONFIG_NUMA_BALANCING
	"numa_pte_updates",
1214
	"numa_huge_pte_updates",
1215 1216 1217 1218
	"numa_hint_faults",
	"numa_hint_faults_local",
	"numa_pages_migrated",
#endif
1219 1220 1221 1222
#ifdef CONFIG_MIGRATION
	"pgmigrate_success",
	"pgmigrate_fail",
#endif
1223
#ifdef CONFIG_COMPACTION
1224 1225 1226
	"compact_migrate_scanned",
	"compact_free_scanned",
	"compact_isolated",
1227 1228 1229
	"compact_stall",
	"compact_fail",
	"compact_success",
1230
	"compact_daemon_wake",
1231 1232
	"compact_daemon_migrate_scanned",
	"compact_daemon_free_scanned",
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
#endif

#ifdef CONFIG_HUGETLB_PAGE
	"htlb_buddy_alloc_success",
	"htlb_buddy_alloc_fail",
#endif
	"unevictable_pgs_culled",
	"unevictable_pgs_scanned",
	"unevictable_pgs_rescued",
	"unevictable_pgs_mlocked",
	"unevictable_pgs_munlocked",
	"unevictable_pgs_cleared",
	"unevictable_pgs_stranded",

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	"thp_fault_alloc",
	"thp_fault_fallback",
	"thp_collapse_alloc",
	"thp_collapse_alloc_failed",
1252 1253
	"thp_file_alloc",
	"thp_file_mapped",
1254 1255
	"thp_split_page",
	"thp_split_page_failed",
1256
	"thp_deferred_split_page",
1257
	"thp_split_pmd",
1258 1259 1260
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
	"thp_split_pud",
#endif
1261 1262
	"thp_zero_page_alloc",
	"thp_zero_page_alloc_failed",
1263
	"thp_swpout",
1264
	"thp_swpout_fallback",
1265
#endif
1266 1267 1268 1269 1270 1271 1272
#ifdef CONFIG_MEMORY_BALLOON
	"balloon_inflate",
	"balloon_deflate",
#ifdef CONFIG_BALLOON_COMPACTION
	"balloon_migrate",
#endif
#endif /* CONFIG_MEMORY_BALLOON */
1273
#ifdef CONFIG_DEBUG_TLBFLUSH
1274
#ifdef CONFIG_SMP
Dave Hansen's avatar
Dave Hansen committed
1275 1276
	"nr_tlb_remote_flush",
	"nr_tlb_remote_flush_received",
1277
#endif /* CONFIG_SMP */
Dave Hansen's avatar
Dave Hansen committed
1278 1279
	"nr_tlb_local_flush_all",
	"nr_tlb_local_flush_one",
1280
#endif /* CONFIG_DEBUG_TLBFLUSH */
1281

Davidlohr Bueso's avatar
Davidlohr Bueso committed
1282 1283 1284
#ifdef CONFIG_DEBUG_VM_VMACACHE
	"vmacache_find_calls",
	"vmacache_find_hits",
1285
	"vmacache_full_flushes",
Davidlohr Bueso's avatar
Davidlohr Bueso committed
1286
#endif
1287 1288 1289 1290
#ifdef CONFIG_SWAP
	"swap_ra",
	"swap_ra_hit",
#endif
1291 1292
#endif /* CONFIG_VM_EVENTS_COUNTERS */
};
1293
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
1294

1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321
#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \
     defined(CONFIG_PROC_FS)
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)
{
}

1322 1323 1324 1325
/*
 * Walk zones in a node and print using a callback.
 * If @assert_populated is true, only use callback for zones that are populated.
 */
1326
static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
1327
		bool assert_populated, bool nolock,
1328 1329 1330 1331 1332 1333 1334
		void (*print)(struct seq_file *m, pg_data_t *, struct zone *))
{
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
1335
		if (assert_populated && !populated_zone(zone))
1336 1337
			continue;

1338 1339
		if (!nolock)
			spin_lock_irqsave(&zone->lock, flags);
1340
		print(m, pgdat, zone);
1341 1342
		if (!nolock)
			spin_unlock_irqrestore(&zone->lock, flags);
1343 1344 1345 1346
	}
}
#endif

1347
#ifdef CONFIG_PROC_FS
1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364
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;
1365
	walk_zones_in_node(m, pgdat, true, false, frag_show_print);
1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389
	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);
		}
1390 1391
		seq_putc(m, '\n');
	}
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405
}

/* 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');

1406
	walk_zones_in_node(m, pgdat, true, false, pagetypeinfo_showfree_print);
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416

	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;
1417
	unsigned long end_pfn = zone_end_pfn(zone);
1418 1419 1420 1421 1422
	unsigned long count[MIGRATE_TYPES] = { 0, };

	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		struct page *page;

1423 1424
		page = pfn_to_online_page(pfn);
		if (!page)
1425 1426
			continue;

1427 1428
		/* Watch for unexpected holes punched in the memmap */
		if (!memmap_valid_within(pfn, page, zone))
1429
			continue;
1430

1431 1432 1433
		if (page_zone(page) != zone)
			continue;

1434 1435
		mtype = get_pageblock_migratetype(page);

1436 1437
		if (mtype < MIGRATE_TYPES)
			count[mtype]++;
1438 1439 1440 1441 1442 1443 1444 1445 1446
	}

	/* 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');
}

SeongJae Park's avatar
SeongJae Park committed
1447
/* Print out the number of pageblocks for each migratetype */
1448 1449 1450 1451 1452 1453 1454 1455 1456
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');
1457 1458
	walk_zones_in_node(m, pgdat, true, false,
		pagetypeinfo_showblockcount_print);
1459 1460 1461 1462

	return 0;
}

1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473
/*
 * Print out the number of pageblocks for each migratetype that contain pages
 * of other types. This gives an indication of how well fallbacks are being
 * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
 * to determine what is going on
 */
static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
{
#ifdef CONFIG_PAGE_OWNER
	int mtype;

1474
	if (!static_branch_unlikely(&page_owner_inited))
1475 1476 1477 1478 1479 1480 1481 1482 1483
		return;

	drain_all_pages(NULL);

	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
		seq_printf(m, "%12s ", migratetype_names[mtype]);
	seq_putc(m, '\n');

1484 1485
	walk_zones_in_node(m, pgdat, true, true,
		pagetypeinfo_showmixedcount_print);
1486 1487 1488
#endif /* CONFIG_PAGE_OWNER */
}

1489 1490 1491 1492 1493 1494 1495 1496
/*
 * 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;

1497
	/* check memoryless node */
1498
	if (!node_state(pgdat->node_id, N_MEMORY))
1499 1500
		return 0;

1501 1502 1503 1504 1505
	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);
1506
	pagetypeinfo_showmixedcount(m, pgdat);
1507

1508 1509 1510
	return 0;
}

1511
static const struct seq_operations fragmentation_op = {
1512 1513 1514 1515 1516 1517
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

1518 1519 1520 1521 1522
static int fragmentation_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &fragmentation_op);
}

1523
static const struct file_operations buddyinfo_file_operations = {
1524 1525 1526 1527 1528 1529
	.open		= fragmentation_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

1530
static const struct seq_operations pagetypeinfo_op = {
Mel Gorman's avatar