summaryrefslogtreecommitdiff
path: root/mm/page_owner.c
blob: e4c6f3f1695bf2229cd732d46c5faa9a3b485070 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
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
475
476
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
512
513
514
515
516
517
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
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
597
598
599
600
601
602
603
604
605
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
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
677
// SPDX-License-Identifier: GPL-2.0
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/memblock.h>
#include <linux/stacktrace.h>
#include <linux/page_owner.h>
#include <linux/jump_label.h>
#include <linux/migrate.h>
#include <linux/stackdepot.h>
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
#include <linux/sched/clock.h>

#include "internal.h"

/*
 * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack)
 * to use off stack temporal storage
 */
#define PAGE_OWNER_STACK_DEPTH (16)

struct page_owner {
	unsigned short order;
	short last_migrate_reason;
	gfp_t gfp_mask;
	depot_stack_handle_t handle;
	depot_stack_handle_t free_handle;
	u64 ts_nsec;
	u64 free_ts_nsec;
	char comm[TASK_COMM_LEN];
	pid_t pid;
	pid_t tgid;
};

static bool page_owner_enabled __initdata;
DEFINE_STATIC_KEY_FALSE(page_owner_inited);

static depot_stack_handle_t dummy_handle;
static depot_stack_handle_t failure_handle;
static depot_stack_handle_t early_handle;

static void init_early_allocated_pages(void);

static int __init early_page_owner_param(char *buf)
{
	int ret = kstrtobool(buf, &page_owner_enabled);

	if (page_owner_enabled)
		stack_depot_want_early_init();

	return ret;
}
early_param("page_owner", early_page_owner_param);

static __init bool need_page_owner(void)
{
	return page_owner_enabled;
}

static __always_inline depot_stack_handle_t create_dummy_stack(void)
{
	unsigned long entries[4];
	unsigned int nr_entries;

	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
	return stack_depot_save(entries, nr_entries, GFP_KERNEL);
}

static noinline void register_dummy_stack(void)
{
	dummy_handle = create_dummy_stack();
}

static noinline void register_failure_stack(void)
{
	failure_handle = create_dummy_stack();
}

static noinline void register_early_stack(void)
{
	early_handle = create_dummy_stack();
}

static __init void init_page_owner(void)
{
	if (!page_owner_enabled)
		return;

	register_dummy_stack();
	register_failure_stack();
	register_early_stack();
	static_branch_enable(&page_owner_inited);
	init_early_allocated_pages();
}

struct page_ext_operations page_owner_ops = {
	.size = sizeof(struct page_owner),
	.need = need_page_owner,
	.init = init_page_owner,
};

static inline struct page_owner *get_page_owner(struct page_ext *page_ext)
{
	return (void *)page_ext + page_owner_ops.offset;
}

static noinline depot_stack_handle_t save_stack(gfp_t flags)
{
	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
	depot_stack_handle_t handle;
	unsigned int nr_entries;

	/*
	 * Avoid recursion.
	 *
	 * Sometimes page metadata allocation tracking requires more
	 * memory to be allocated:
	 * - when new stack trace is saved to stack depot
	 * - when backtrace itself is calculated (ia64)
	 */
	if (current->in_page_owner)
		return dummy_handle;
	current->in_page_owner = 1;

	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
	handle = stack_depot_save(entries, nr_entries, flags);
	if (!handle)
		handle = failure_handle;

	current->in_page_owner = 0;
	return handle;
}

void __reset_page_owner(struct page *page, unsigned short order)
{
	int i;
	struct page_ext *page_ext;
	depot_stack_handle_t handle;
	struct page_owner *page_owner;
	u64 free_ts_nsec = local_clock();

	page_ext = lookup_page_ext(page);
	if (unlikely(!page_ext))
		return;

	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
	for (i = 0; i < (1 << order); i++) {
		__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
		page_owner = get_page_owner(page_ext);
		page_owner->free_handle = handle;
		page_owner->free_ts_nsec = free_ts_nsec;
		page_ext = page_ext_next(page_ext);
	}
}

static inline void __set_page_owner_handle(struct page_ext *page_ext,
					depot_stack_handle_t handle,
					unsigned short order, gfp_t gfp_mask)
{
	struct page_owner *page_owner;
	int i;

	for (i = 0; i < (1 << order); i++) {
		page_owner = get_page_owner(page_ext);
		page_owner->handle = handle;
		page_owner->order = order;
		page_owner->gfp_mask = gfp_mask;
		page_owner->last_migrate_reason = -1;
		page_owner->pid = current->pid;
		page_owner->tgid = current->tgid;
		page_owner->ts_nsec = local_clock();
		strscpy(page_owner->comm, current->comm,
			sizeof(page_owner->comm));
		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
		__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);

		page_ext = page_ext_next(page_ext);
	}
}

noinline void __set_page_owner(struct page *page, unsigned short order,
					gfp_t gfp_mask)
{
	struct page_ext *page_ext = lookup_page_ext(page);
	depot_stack_handle_t handle;

	if (unlikely(!page_ext))
		return;

	handle = save_stack(gfp_mask);
	__set_page_owner_handle(page_ext, handle, order, gfp_mask);
}

void __set_page_owner_migrate_reason(struct page *page, int reason)
{
	struct page_ext *page_ext = lookup_page_ext(page);
	struct page_owner *page_owner;

	if (unlikely(!page_ext))
		return;

	page_owner = get_page_owner(page_ext);
	page_owner->last_migrate_reason = reason;
}

void __split_page_owner(struct page *page, unsigned int nr)
{
	int i;
	struct page_ext *page_ext = lookup_page_ext(page);
	struct page_owner *page_owner;

	if (unlikely(!page_ext))
		return;

	for (i = 0; i < nr; i++) {
		page_owner = get_page_owner(page_ext);
		page_owner->order = 0;
		page_ext = page_ext_next(page_ext);
	}
}

void __folio_copy_owner(struct folio *newfolio, struct folio *old)
{
	struct page_ext *old_ext = lookup_page_ext(&old->page);
	struct page_ext *new_ext = lookup_page_ext(&newfolio->page);
	struct page_owner *old_page_owner, *new_page_owner;

	if (unlikely(!old_ext || !new_ext))
		return;

	old_page_owner = get_page_owner(old_ext);
	new_page_owner = get_page_owner(new_ext);
	new_page_owner->order = old_page_owner->order;
	new_page_owner->gfp_mask = old_page_owner->gfp_mask;
	new_page_owner->last_migrate_reason =
		old_page_owner->last_migrate_reason;
	new_page_owner->handle = old_page_owner->handle;
	new_page_owner->pid = old_page_owner->pid;
	new_page_owner->tgid = old_page_owner->tgid;
	new_page_owner->ts_nsec = old_page_owner->ts_nsec;
	new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
	strcpy(new_page_owner->comm, old_page_owner->comm);

	/*
	 * We don't clear the bit on the old folio as it's going to be freed
	 * after migration. Until then, the info can be useful in case of
	 * a bug, and the overall stats will be off a bit only temporarily.
	 * Also, migrate_misplaced_transhuge_page() can still fail the
	 * migration and then we want the old folio to retain the info. But
	 * in that case we also don't need to explicitly clear the info from
	 * the new page, which will be freed.
	 */
	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
	__set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
}

void pagetypeinfo_showmixedcount_print(struct seq_file *m,
				       pg_data_t *pgdat, struct zone *zone)
{
	struct page *page;
	struct page_ext *page_ext;
	struct page_owner *page_owner;
	unsigned long pfn, block_end_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	unsigned long count[MIGRATE_TYPES] = { 0, };
	int pageblock_mt, page_mt;
	int i;

	/* Scan block by block. First and last block may be incomplete */
	pfn = zone->zone_start_pfn;

	/*
	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
	 * a zone boundary, it will be double counted between zones. This does
	 * not matter as the mixed block count will still be correct
	 */
	for (; pfn < end_pfn; ) {
		page = pfn_to_online_page(pfn);
		if (!page) {
			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
			continue;
		}

		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		pageblock_mt = get_pageblock_migratetype(page);

		for (; pfn < block_end_pfn; pfn++) {
			/* The pageblock is online, no need to recheck. */
			page = pfn_to_page(pfn);

			if (page_zone(page) != zone)
				continue;

			if (PageBuddy(page)) {
				unsigned long freepage_order;

				freepage_order = buddy_order_unsafe(page);
				if (freepage_order < MAX_ORDER)
					pfn += (1UL << freepage_order) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);
			if (unlikely(!page_ext))
				continue;

			if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
				continue;

			page_owner = get_page_owner(page_ext);
			page_mt = gfp_migratetype(page_owner->gfp_mask);
			if (pageblock_mt != page_mt) {
				if (is_migrate_cma(pageblock_mt))
					count[MIGRATE_MOVABLE]++;
				else
					count[pageblock_mt]++;

				pfn = block_end_pfn;
				break;
			}
			pfn += (1UL << page_owner->order) - 1;
		}
	}

	/* Print counts */
	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
	for (i = 0; i < MIGRATE_TYPES; i++)
		seq_printf(m, "%12lu ", count[i]);
	seq_putc(m, '\n');
}

/*
 * Looking for memcg information and print it out
 */
static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret,
					 struct page *page)
{
#ifdef CONFIG_MEMCG
	unsigned long memcg_data;
	struct mem_cgroup *memcg;
	bool online;
	char name[80];

	rcu_read_lock();
	memcg_data = READ_ONCE(page->memcg_data);
	if (!memcg_data)
		goto out_unlock;

	if (memcg_data & MEMCG_DATA_OBJCGS)
		ret += scnprintf(kbuf + ret, count - ret,
				"Slab cache page\n");

	memcg = page_memcg_check(page);
	if (!memcg)
		goto out_unlock;

	online = (memcg->css.flags & CSS_ONLINE);
	cgroup_name(memcg->css.cgroup, name, sizeof(name));
	ret += scnprintf(kbuf + ret, count - ret,
			"Charged %sto %smemcg %s\n",
			PageMemcgKmem(page) ? "(via objcg) " : "",
			online ? "" : "offline ",
			name);
out_unlock:
	rcu_read_unlock();
#endif /* CONFIG_MEMCG */

	return ret;
}

static ssize_t
print_page_owner(char __user *buf, size_t count, unsigned long pfn,
		struct page *page, struct page_owner *page_owner,
		depot_stack_handle_t handle)
{
	int ret, pageblock_mt, page_mt;
	char *kbuf;

	count = min_t(size_t, count, PAGE_SIZE);
	kbuf = kmalloc(count, GFP_KERNEL);
	if (!kbuf)
		return -ENOMEM;

	ret = scnprintf(kbuf, count,
			"Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns, free_ts %llu ns\n",
			page_owner->order, page_owner->gfp_mask,
			&page_owner->gfp_mask, page_owner->pid,
			page_owner->tgid, page_owner->comm,
			page_owner->ts_nsec, page_owner->free_ts_nsec);

	/* Print information relevant to grouping pages by mobility */
	pageblock_mt = get_pageblock_migratetype(page);
	page_mt  = gfp_migratetype(page_owner->gfp_mask);
	ret += scnprintf(kbuf + ret, count - ret,
			"PFN %lu type %s Block %lu type %s Flags %pGp\n",
			pfn,
			migratetype_names[page_mt],
			pfn >> pageblock_order,
			migratetype_names[pageblock_mt],
			&page->flags);

	ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0);
	if (ret >= count)
		goto err;

	if (page_owner->last_migrate_reason != -1) {
		ret += scnprintf(kbuf + ret, count - ret,
			"Page has been migrated, last migrate reason: %s\n",
			migrate_reason_names[page_owner->last_migrate_reason]);
	}

	ret = print_page_owner_memcg(kbuf, count, ret, page);

	ret += snprintf(kbuf + ret, count - ret, "\n");
	if (ret >= count)
		goto err;

	if (copy_to_user(buf, kbuf, ret))
		ret = -EFAULT;

	kfree(kbuf);
	return ret;

err:
	kfree(kbuf);
	return -ENOMEM;
}

void __dump_page_owner(const struct page *page)
{
	struct page_ext *page_ext = lookup_page_ext(page);
	struct page_owner *page_owner;
	depot_stack_handle_t handle;
	gfp_t gfp_mask;
	int mt;

	if (unlikely(!page_ext)) {
		pr_alert("There is not page extension available.\n");
		return;
	}

	page_owner = get_page_owner(page_ext);
	gfp_mask = page_owner->gfp_mask;
	mt = gfp_migratetype(gfp_mask);

	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
		pr_alert("page_owner info is not present (never set?)\n");
		return;
	}

	if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
		pr_alert("page_owner tracks the page as allocated\n");
	else
		pr_alert("page_owner tracks the page as freed\n");

	pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu, free_ts %llu\n",
		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask,
		 page_owner->pid, page_owner->tgid, page_owner->comm,
		 page_owner->ts_nsec, page_owner->free_ts_nsec);

	handle = READ_ONCE(page_owner->handle);
	if (!handle)
		pr_alert("page_owner allocation stack trace missing\n");
	else
		stack_depot_print(handle);

	handle = READ_ONCE(page_owner->free_handle);
	if (!handle) {
		pr_alert("page_owner free stack trace missing\n");
	} else {
		pr_alert("page last free stack trace:\n");
		stack_depot_print(handle);
	}

	if (page_owner->last_migrate_reason != -1)
		pr_alert("page has been migrated, last migrate reason: %s\n",
			migrate_reason_names[page_owner->last_migrate_reason]);
}

static ssize_t
read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	unsigned long pfn;
	struct page *page;
	struct page_ext *page_ext;
	struct page_owner *page_owner;
	depot_stack_handle_t handle;

	if (!static_branch_unlikely(&page_owner_inited))
		return -EINVAL;

	page = NULL;
	pfn = min_low_pfn + *ppos;

	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
		pfn++;

	drain_all_pages(NULL);

	/* Find an allocated page */
	for (; pfn < max_pfn; pfn++) {
		/*
		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
		 * validate the area as existing, skip it if not
		 */
		if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
			pfn += MAX_ORDER_NR_PAGES - 1;
			continue;
		}

		page = pfn_to_page(pfn);
		if (PageBuddy(page)) {
			unsigned long freepage_order = buddy_order_unsafe(page);

			if (freepage_order < MAX_ORDER)
				pfn += (1UL << freepage_order) - 1;
			continue;
		}

		page_ext = lookup_page_ext(page);
		if (unlikely(!page_ext))
			continue;

		/*
		 * Some pages could be missed by concurrent allocation or free,
		 * because we don't hold the zone lock.
		 */
		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
			continue;

		/*
		 * Although we do have the info about past allocation of free
		 * pages, it's not relevant for current memory usage.
		 */
		if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
			continue;

		page_owner = get_page_owner(page_ext);

		/*
		 * Don't print "tail" pages of high-order allocations as that
		 * would inflate the stats.
		 */
		if (!IS_ALIGNED(pfn, 1 << page_owner->order))
			continue;

		/*
		 * Access to page_ext->handle isn't synchronous so we should
		 * be careful to access it.
		 */
		handle = READ_ONCE(page_owner->handle);
		if (!handle)
			continue;

		/* Record the next PFN to read in the file offset */
		*ppos = (pfn - min_low_pfn) + 1;

		return print_page_owner(buf, count, pfn, page,
				page_owner, handle);
	}

	return 0;
}

static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
	unsigned long pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	unsigned long count = 0;

	/*
	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
	 * a zone boundary, it will be double counted between zones. This does
	 * not matter as the mixed block count will still be correct
	 */
	for (; pfn < end_pfn; ) {
		unsigned long block_end_pfn;

		if (!pfn_valid(pfn)) {
			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
			continue;
		}

		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		for (; pfn < block_end_pfn; pfn++) {
			struct page *page = pfn_to_page(pfn);
			struct page_ext *page_ext;

			if (page_zone(page) != zone)
				continue;

			/*
			 * To avoid having to grab zone->lock, be a little
			 * careful when reading buddy page order. The only
			 * danger is that we skip too much and potentially miss
			 * some early allocated pages, which is better than
			 * heavy lock contention.
			 */
			if (PageBuddy(page)) {
				unsigned long order = buddy_order_unsafe(page);

				if (order > 0 && order < MAX_ORDER)
					pfn += (1UL << order) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);
			if (unlikely(!page_ext))
				continue;

			/* Maybe overlapping zone */
			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
				continue;

			/* Found early allocated page */
			__set_page_owner_handle(page_ext, early_handle,
						0, 0);
			count++;
		}
		cond_resched();
	}

	pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
		pgdat->node_id, zone->name, count);
}

static void init_zones_in_node(pg_data_t *pgdat)
{
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!populated_zone(zone))
			continue;

		init_pages_in_zone(pgdat, zone);
	}
}

static void init_early_allocated_pages(void)
{
	pg_data_t *pgdat;

	for_each_online_pgdat(pgdat)
		init_zones_in_node(pgdat);
}

static const struct file_operations proc_page_owner_operations = {
	.read		= read_page_owner,
};

static int __init pageowner_init(void)
{
	if (!static_branch_unlikely(&page_owner_inited)) {
		pr_info("page_owner is disabled\n");
		return 0;
	}

	debugfs_create_file("page_owner", 0400, NULL, NULL,
			    &proc_page_owner_operations);

	return 0;
}
late_initcall(pageowner_init)