summaryrefslogtreecommitdiff
path: root/mm/page_counter.c
blob: afe22ad335ccc2a0be5a3ee3514d97e46ee1bddd (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Lockless hierarchical page accounting & limiting
 *
 * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
 */

#include <linux/page_counter.h>
#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/bug.h>
#include <asm/page.h>

static void propagate_protected_usage(struct page_counter *c,
				      unsigned long usage)
{
	unsigned long protected, old_protected;
	unsigned long low, min;
	long delta;

	if (!c->parent)
		return;

	min = READ_ONCE(c->min);
	if (min || atomic_long_read(&c->min_usage)) {
		protected = min(usage, min);
		old_protected = atomic_long_xchg(&c->min_usage, protected);
		delta = protected - old_protected;
		if (delta)
			atomic_long_add(delta, &c->parent->children_min_usage);
	}

	low = READ_ONCE(c->low);
	if (low || atomic_long_read(&c->low_usage)) {
		protected = min(usage, low);
		old_protected = atomic_long_xchg(&c->low_usage, protected);
		delta = protected - old_protected;
		if (delta)
			atomic_long_add(delta, &c->parent->children_low_usage);
	}
}

/**
 * page_counter_cancel - take pages out of the local counter
 * @counter: counter
 * @nr_pages: number of pages to cancel
 */
void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
{
	long new;

	new = atomic_long_sub_return(nr_pages, &counter->usage);
	propagate_protected_usage(counter, new);
	/* More uncharges than charges? */
	WARN_ON_ONCE(new < 0);
}

/**
 * page_counter_charge - hierarchically charge pages
 * @counter: counter
 * @nr_pages: number of pages to charge
 *
 * NOTE: This does not consider any configured counter limits.
 */
void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
{
	struct page_counter *c;

	for (c = counter; c; c = c->parent) {
		long new;

		new = atomic_long_add_return(nr_pages, &c->usage);
		propagate_protected_usage(c, new);
		/*
		 * This is indeed racy, but we can live with some
		 * inaccuracy in the watermark.
		 */
		if (new > READ_ONCE(c->watermark))
			WRITE_ONCE(c->watermark, new);
	}
}

/**
 * page_counter_try_charge - try to hierarchically charge pages
 * @counter: counter
 * @nr_pages: number of pages to charge
 * @fail: points first counter to hit its limit, if any
 *
 * Returns %true on success, or %false and @fail if the counter or one
 * of its ancestors has hit its configured limit.
 */
bool page_counter_try_charge(struct page_counter *counter,
			     unsigned long nr_pages,
			     struct page_counter **fail)
{
	struct page_counter *c;

	for (c = counter; c; c = c->parent) {
		long new;
		/*
		 * Charge speculatively to avoid an expensive CAS.  If
		 * a bigger charge fails, it might falsely lock out a
		 * racing smaller charge and send it into reclaim
		 * early, but the error is limited to the difference
		 * between the two sizes, which is less than 2M/4M in
		 * case of a THP locking out a regular page charge.
		 *
		 * The atomic_long_add_return() implies a full memory
		 * barrier between incrementing the count and reading
		 * the limit.  When racing with page_counter_limit(),
		 * we either see the new limit or the setter sees the
		 * counter has changed and retries.
		 */
		new = atomic_long_add_return(nr_pages, &c->usage);
		if (new > c->max) {
			atomic_long_sub(nr_pages, &c->usage);
			propagate_protected_usage(c, new);
			/*
			 * This is racy, but we can live with some
			 * inaccuracy in the failcnt which is only used
			 * to report stats.
			 */
			data_race(c->failcnt++);
			*fail = c;
			goto failed;
		}
		propagate_protected_usage(c, new);
		/*
		 * Just like with failcnt, we can live with some
		 * inaccuracy in the watermark.
		 */
		if (new > READ_ONCE(c->watermark))
			WRITE_ONCE(c->watermark, new);
	}
	return true;

failed:
	for (c = counter; c != *fail; c = c->parent)
		page_counter_cancel(c, nr_pages);

	return false;
}

/**
 * page_counter_uncharge - hierarchically uncharge pages
 * @counter: counter
 * @nr_pages: number of pages to uncharge
 */
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
{
	struct page_counter *c;

	for (c = counter; c; c = c->parent)
		page_counter_cancel(c, nr_pages);
}

/**
 * page_counter_set_max - set the maximum number of pages allowed
 * @counter: counter
 * @nr_pages: limit to set
 *
 * Returns 0 on success, -EBUSY if the current number of pages on the
 * counter already exceeds the specified limit.
 *
 * The caller must serialize invocations on the same counter.
 */
int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages)
{
	for (;;) {
		unsigned long old;
		long usage;

		/*
		 * Update the limit while making sure that it's not
		 * below the concurrently-changing counter value.
		 *
		 * The xchg implies two full memory barriers before
		 * and after, so the read-swap-read is ordered and
		 * ensures coherency with page_counter_try_charge():
		 * that function modifies the count before checking
		 * the limit, so if it sees the old limit, we see the
		 * modified counter and retry.
		 */
		usage = atomic_long_read(&counter->usage);

		if (usage > nr_pages)
			return -EBUSY;

		old = xchg(&counter->max, nr_pages);

		if (atomic_long_read(&counter->usage) <= usage)
			return 0;

		counter->max = old;
		cond_resched();
	}
}

/**
 * page_counter_set_min - set the amount of protected memory
 * @counter: counter
 * @nr_pages: value to set
 *
 * The caller must serialize invocations on the same counter.
 */
void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages)
{
	struct page_counter *c;

	WRITE_ONCE(counter->min, nr_pages);

	for (c = counter; c; c = c->parent)
		propagate_protected_usage(c, atomic_long_read(&c->usage));
}

/**
 * page_counter_set_low - set the amount of protected memory
 * @counter: counter
 * @nr_pages: value to set
 *
 * The caller must serialize invocations on the same counter.
 */
void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages)
{
	struct page_counter *c;

	WRITE_ONCE(counter->low, nr_pages);

	for (c = counter; c; c = c->parent)
		propagate_protected_usage(c, atomic_long_read(&c->usage));
}

/**
 * page_counter_memparse - memparse() for page counter limits
 * @buf: string to parse
 * @max: string meaning maximum possible value
 * @nr_pages: returns the result in number of pages
 *
 * Returns -EINVAL, or 0 and @nr_pages on success.  @nr_pages will be
 * limited to %PAGE_COUNTER_MAX.
 */
int page_counter_memparse(const char *buf, const char *max,
			  unsigned long *nr_pages)
{
	char *end;
	u64 bytes;

	if (!strcmp(buf, max)) {
		*nr_pages = PAGE_COUNTER_MAX;
		return 0;
	}

	bytes = memparse(buf, &end);
	if (*end != '\0')
		return -EINVAL;

	*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);

	return 0;
}