aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/mm/hugetlb_cgroup.c
blob: e434b05416c680b09fdc67065026c9fe292b92f3 (plain) (blame)
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
/*
 *
 * Copyright IBM Corporation, 2012
 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
 *
 * Cgroup v2
 * Copyright (C) 2019 Red Hat, Inc.
 * Author: Giuseppe Scrivano <gscrivan@redhat.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of version 2.1 of the GNU Lesser General Public License
 * as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 *
 */

#include <linux/cgroup.h>
#include <linux/page_counter.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>

enum hugetlb_memory_event {
	HUGETLB_MAX,
	HUGETLB_NR_MEMORY_EVENTS,
};

struct hugetlb_cgroup {
	struct cgroup_subsys_state css;

	/*
	 * the counter to account for hugepages from hugetlb.
	 */
	struct page_counter hugepage[HUGE_MAX_HSTATE];

	atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS];
	atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS];

	/* Handle for "hugetlb.events" */
	struct cgroup_file events_file[HUGE_MAX_HSTATE];

	/* Handle for "hugetlb.events.local" */
	struct cgroup_file events_local_file[HUGE_MAX_HSTATE];
};

#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
#define MEMFILE_IDX(val)	(((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)

#define hugetlb_cgroup_from_counter(counter, idx)                   \
	container_of(counter, struct hugetlb_cgroup, hugepage[idx])

static struct hugetlb_cgroup *root_h_cgroup __read_mostly;

static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
{
	return s ? container_of(s, struct hugetlb_cgroup, css) : NULL;
}

static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
{
	return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id));
}

static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
{
	return (h_cg == root_h_cgroup);
}

static inline struct hugetlb_cgroup *
parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg)
{
	return hugetlb_cgroup_from_css(h_cg->css.parent);
}

static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
{
	int idx;

	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
		if (page_counter_read(&h_cg->hugepage[idx]))
			return true;
	}
	return false;
}

static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup,
				struct hugetlb_cgroup *parent_h_cgroup)
{
	int idx;

	for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) {
		struct page_counter *counter = &h_cgroup->hugepage[idx];
		struct page_counter *parent = NULL;
		unsigned long limit;
		int ret;

		if (parent_h_cgroup)
			parent = &parent_h_cgroup->hugepage[idx];
		page_counter_init(counter, parent);

		limit = round_down(PAGE_COUNTER_MAX,
				   1 << huge_page_order(&hstates[idx]));
		ret = page_counter_set_max(counter, limit);
		VM_BUG_ON(ret);
	}
}

static struct cgroup_subsys_state *
hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
	struct hugetlb_cgroup *h_cgroup;

	h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
	if (!h_cgroup)
		return ERR_PTR(-ENOMEM);

	if (!parent_h_cgroup)
		root_h_cgroup = h_cgroup;

	hugetlb_cgroup_init(h_cgroup, parent_h_cgroup);
	return &h_cgroup->css;
}

static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
{
	struct hugetlb_cgroup *h_cgroup;

	h_cgroup = hugetlb_cgroup_from_css(css);
	kfree(h_cgroup);
}


/*
 * Should be called with hugetlb_lock held.
 * Since we are holding hugetlb_lock, pages cannot get moved from
 * active list or uncharged from the cgroup, So no need to get
 * page reference and test for page active here. This function
 * cannot fail.
 */
static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
				       struct page *page)
{
	unsigned int nr_pages;
	struct page_counter *counter;
	struct hugetlb_cgroup *page_hcg;
	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);

	page_hcg = hugetlb_cgroup_from_page(page);
	/*
	 * We can have pages in active list without any cgroup
	 * ie, hugepage with less than 3 pages. We can safely
	 * ignore those pages.
	 */
	if (!page_hcg || page_hcg != h_cg)
		goto out;

	nr_pages = compound_nr(page);
	if (!parent) {
		parent = root_h_cgroup;
		/* root has no limit */
		page_counter_charge(&parent->hugepage[idx], nr_pages);
	}
	counter = &h_cg->hugepage[idx];
	/* Take the pages off the local counter */
	page_counter_cancel(counter, nr_pages);

	set_hugetlb_cgroup(page, parent);
out:
	return;
}

/*
 * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
 * the parent cgroup.
 */
static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css)
{
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
	struct hstate *h;
	struct page *page;
	int idx = 0;

	do {
		for_each_hstate(h) {
			spin_lock(&hugetlb_lock);
			list_for_each_entry(page, &h->hugepage_activelist, lru)
				hugetlb_cgroup_move_parent(idx, h_cg, page);

			spin_unlock(&hugetlb_lock);
			idx++;
		}
		cond_resched();
	} while (hugetlb_cgroup_have_usage(h_cg));
}

static inline void hugetlb_event(struct hugetlb_cgroup *hugetlb, int idx,
				 enum hugetlb_memory_event event)
{
	atomic_long_inc(&hugetlb->events_local[idx][event]);
	cgroup_file_notify(&hugetlb->events_local_file[idx]);

	do {
		atomic_long_inc(&hugetlb->events[idx][event]);
		cgroup_file_notify(&hugetlb->events_file[idx]);
	} while ((hugetlb = parent_hugetlb_cgroup(hugetlb)) &&
		 !hugetlb_cgroup_is_root(hugetlb));
}

int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
				 struct hugetlb_cgroup **ptr)
{
	int ret = 0;
	struct page_counter *counter;
	struct hugetlb_cgroup *h_cg = NULL;

	if (hugetlb_cgroup_disabled())
		goto done;
	/*
	 * We don't charge any cgroup if the compound page have less
	 * than 3 pages.
	 */
	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
		goto done;
again:
	rcu_read_lock();
	h_cg = hugetlb_cgroup_from_task(current);
	if (!css_tryget(&h_cg->css)) {
		rcu_read_unlock();
		goto again;
	}
	rcu_read_unlock();

	if (!page_counter_try_charge(&h_cg->hugepage[idx], nr_pages,
				     &counter)) {
		ret = -ENOMEM;
		hugetlb_event(hugetlb_cgroup_from_counter(counter, idx), idx,
			      HUGETLB_MAX);
	}
	css_put(&h_cg->css);
done:
	*ptr = h_cg;
	return ret;
}

/* Should be called with hugetlb_lock held */
void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
				  struct hugetlb_cgroup *h_cg,
				  struct page *page)
{
	if (hugetlb_cgroup_disabled() || !h_cg)
		return;

	set_hugetlb_cgroup(page, h_cg);
	return;
}

/*
 * Should be called with hugetlb_lock held
 */
void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
				  struct page *page)
{
	struct hugetlb_cgroup *h_cg;

	if (hugetlb_cgroup_disabled())
		return;
	lockdep_assert_held(&hugetlb_lock);
	h_cg = hugetlb_cgroup_from_page(page);
	if (unlikely(!h_cg))
		return;
	set_hugetlb_cgroup(page, NULL);
	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
	return;
}

void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
				    struct hugetlb_cgroup *h_cg)
{
	if (hugetlb_cgroup_disabled() || !h_cg)
		return;

	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
		return;

	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
	return;
}

enum {
	RES_USAGE,
	RES_LIMIT,
	RES_MAX_USAGE,
	RES_FAILCNT,
};

static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
				   struct cftype *cft)
{
	struct page_counter *counter;
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);

	counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];

	switch (MEMFILE_ATTR(cft->private)) {
	case RES_USAGE:
		return (u64)page_counter_read(counter) * PAGE_SIZE;
	case RES_LIMIT:
		return (u64)counter->max * PAGE_SIZE;
	case RES_MAX_USAGE:
		return (u64)counter->watermark * PAGE_SIZE;
	case RES_FAILCNT:
		return counter->failcnt;
	default:
		BUG();
	}
}

static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v)
{
	int idx;
	u64 val;
	struct cftype *cft = seq_cft(seq);
	unsigned long limit;
	struct page_counter *counter;
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq));

	idx = MEMFILE_IDX(cft->private);
	counter = &h_cg->hugepage[idx];

	limit = round_down(PAGE_COUNTER_MAX,
			   1 << huge_page_order(&hstates[idx]));

	switch (MEMFILE_ATTR(cft->private)) {
	case RES_USAGE:
		val = (u64)page_counter_read(counter);
		seq_printf(seq, "%llu\n", val * PAGE_SIZE);
		break;
	case RES_LIMIT:
		val = (u64)counter->max;
		if (val == limit)
			seq_puts(seq, "max\n");
		else
			seq_printf(seq, "%llu\n", val * PAGE_SIZE);
		break;
	default:
		BUG();
	}

	return 0;
}

static DEFINE_MUTEX(hugetlb_limit_mutex);

static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
				    char *buf, size_t nbytes, loff_t off,
				    const char *max)
{
	int ret, idx;
	unsigned long nr_pages;
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));

	if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
		return -EINVAL;

	buf = strstrip(buf);
	ret = page_counter_memparse(buf, max, &nr_pages);
	if (ret)
		return ret;

	idx = MEMFILE_IDX(of_cft(of)->private);
	nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx]));

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_LIMIT:
		mutex_lock(&hugetlb_limit_mutex);
		ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages);
		mutex_unlock(&hugetlb_limit_mutex);
		break;
	default:
		ret = -EINVAL;
		break;
	}
	return ret ?: nbytes;
}

static ssize_t hugetlb_cgroup_write_legacy(struct kernfs_open_file *of,
					   char *buf, size_t nbytes, loff_t off)
{
	return hugetlb_cgroup_write(of, buf, nbytes, off, "-1");
}

static ssize_t hugetlb_cgroup_write_dfl(struct kernfs_open_file *of,
					char *buf, size_t nbytes, loff_t off)
{
	return hugetlb_cgroup_write(of, buf, nbytes, off, "max");
}

static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
				    char *buf, size_t nbytes, loff_t off)
{
	int ret = 0;
	struct page_counter *counter;
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));

	counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];

	switch (MEMFILE_ATTR(of_cft(of)->private)) {
	case RES_MAX_USAGE:
		page_counter_reset_watermark(counter);
		break;
	case RES_FAILCNT:
		counter->failcnt = 0;
		break;
	default:
		ret = -EINVAL;
		break;
	}
	return ret ?: nbytes;
}

static char *mem_fmt(char *buf, int size, unsigned long hsize)
{
	if (hsize >= (1UL << 30))
		snprintf(buf, size, "%luGB", hsize >> 30);
	else if (hsize >= (1UL << 20))
		snprintf(buf, size, "%luMB", hsize >> 20);
	else
		snprintf(buf, size, "%luKB", hsize >> 10);
	return buf;
}

static int __hugetlb_events_show(struct seq_file *seq, bool local)
{
	int idx;
	long max;
	struct cftype *cft = seq_cft(seq);
	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq));

	idx = MEMFILE_IDX(cft->private);

	if (local)
		max = atomic_long_read(&h_cg->events_local[idx][HUGETLB_MAX]);
	else
		max = atomic_long_read(&h_cg->events[idx][HUGETLB_MAX]);

	seq_printf(seq, "max %lu\n", max);

	return 0;
}

static int hugetlb_events_show(struct seq_file *seq, void *v)
{
	return __hugetlb_events_show(seq, false);
}

static int hugetlb_events_local_show(struct seq_file *seq, void *v)
{
	return __hugetlb_events_show(seq, true);
}

static void __init __hugetlb_cgroup_file_dfl_init(int idx)
{
	char buf[32];
	struct cftype *cft;
	struct hstate *h = &hstates[idx];

	/* format the size */
	mem_fmt(buf, 32, huge_page_size(h));

	/* Add the limit file */
	cft = &h->cgroup_files_dfl[0];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max", buf);
	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
	cft->seq_show = hugetlb_cgroup_read_u64_max;
	cft->write = hugetlb_cgroup_write_dfl;
	cft->flags = CFTYPE_NOT_ON_ROOT;

	/* Add the current usage file */
	cft = &h->cgroup_files_dfl[1];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.current", buf);
	cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
	cft->seq_show = hugetlb_cgroup_read_u64_max;
	cft->flags = CFTYPE_NOT_ON_ROOT;

	/* Add the events file */
	cft = &h->cgroup_files_dfl[2];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf);
	cft->private = MEMFILE_PRIVATE(idx, 0);
	cft->seq_show = hugetlb_events_show;
	cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]),
	cft->flags = CFTYPE_NOT_ON_ROOT;

	/* Add the events.local file */
	cft = &h->cgroup_files_dfl[3];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events.local", buf);
	cft->private = MEMFILE_PRIVATE(idx, 0);
	cft->seq_show = hugetlb_events_local_show;
	cft->file_offset = offsetof(struct hugetlb_cgroup,
				    events_local_file[idx]),
	cft->flags = CFTYPE_NOT_ON_ROOT;

	/* NULL terminate the last cft */
	cft = &h->cgroup_files_dfl[4];
	memset(cft, 0, sizeof(*cft));

	WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys,
				       h->cgroup_files_dfl));
}

static void __init __hugetlb_cgroup_file_legacy_init(int idx)
{
	char buf[32];
	struct cftype *cft;
	struct hstate *h = &hstates[idx];

	/* format the size */
	mem_fmt(buf, 32, huge_page_size(h));

	/* Add the limit file */
	cft = &h->cgroup_files_legacy[0];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
	cft->read_u64 = hugetlb_cgroup_read_u64;
	cft->write = hugetlb_cgroup_write_legacy;

	/* Add the usage file */
	cft = &h->cgroup_files_legacy[1];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);
	cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
	cft->read_u64 = hugetlb_cgroup_read_u64;

	/* Add the MAX usage file */
	cft = &h->cgroup_files_legacy[2];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
	cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
	cft->write = hugetlb_cgroup_reset;
	cft->read_u64 = hugetlb_cgroup_read_u64;

	/* Add the failcntfile */
	cft = &h->cgroup_files_legacy[3];
	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
	cft->private  = MEMFILE_PRIVATE(idx, RES_FAILCNT);
	cft->write = hugetlb_cgroup_reset;
	cft->read_u64 = hugetlb_cgroup_read_u64;

	/* NULL terminate the last cft */
	cft = &h->cgroup_files_legacy[4];
	memset(cft, 0, sizeof(*cft));

	WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,
					  h->cgroup_files_legacy));
}

static void __init __hugetlb_cgroup_file_init(int idx)
{
	__hugetlb_cgroup_file_dfl_init(idx);
	__hugetlb_cgroup_file_legacy_init(idx);
}

void __init hugetlb_cgroup_file_init(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		/*
		 * Add cgroup control files only if the huge page consists
		 * of more than two normal pages. This is because we use
		 * page[2].private for storing cgroup details.
		 */
		if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
			__hugetlb_cgroup_file_init(hstate_index(h));
	}
}

/*
 * hugetlb_lock will make sure a parallel cgroup rmdir won't happen
 * when we migrate hugepages
 */
void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
{
	struct hugetlb_cgroup *h_cg;
	struct hstate *h = page_hstate(oldhpage);

	if (hugetlb_cgroup_disabled())
		return;

	VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage);
	spin_lock(&hugetlb_lock);
	h_cg = hugetlb_cgroup_from_page(oldhpage);
	set_hugetlb_cgroup(oldhpage, NULL);

	/* move the h_cg details to new cgroup */
	set_hugetlb_cgroup(newhpage, h_cg);
	list_move(&newhpage->lru, &h->hugepage_activelist);
	spin_unlock(&hugetlb_lock);
	return;
}

static struct cftype hugetlb_files[] = {
	{} /* terminate */
};

struct cgroup_subsys hugetlb_cgrp_subsys = {
	.css_alloc	= hugetlb_cgroup_css_alloc,
	.css_offline	= hugetlb_cgroup_css_offline,
	.css_free	= hugetlb_cgroup_css_free,
	.dfl_cftypes	= hugetlb_files,
	.legacy_cftypes	= hugetlb_files,
};