aboutsummaryrefslogtreecommitdiff
path: root/mm/mmap_lock.c
blob: dcdde4f722a408ff05fa0d5e86ba1465a60ce0ea (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
// SPDX-License-Identifier: GPL-2.0
#define CREATE_TRACE_POINTS
#include <trace/events/mmap_lock.h>

#include <linux/mm.h>
#include <linux/cgroup.h>
#include <linux/memcontrol.h>
#include <linux/mmap_lock.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/trace_events.h>

EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking);
EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned);
EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released);

#ifdef CONFIG_MEMCG

/*
 * Our various events all share the same buffer (because we don't want or need
 * to allocate a set of buffers *per event type*), so we need to protect against
 * concurrent _reg() and _unreg() calls, and count how many _reg() calls have
 * been made.
 */
static DEFINE_MUTEX(reg_lock);
static int reg_refcount; /* Protected by reg_lock. */

/*
 * Size of the buffer for memcg path names. Ignoring stack trace support,
 * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it.
 */
#define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL

/*
 * How many contexts our trace events might be called in: normal, softirq, irq,
 * and NMI.
 */
#define CONTEXT_COUNT 4

static DEFINE_PER_CPU(char __rcu *, memcg_path_buf);
static char **tmp_bufs;
static DEFINE_PER_CPU(int, memcg_path_buf_idx);

/* Called with reg_lock held. */
static void free_memcg_path_bufs(void)
{
	int cpu;
	char **old = tmp_bufs;

	for_each_possible_cpu(cpu) {
		*(old++) = rcu_dereference_protected(
			per_cpu(memcg_path_buf, cpu),
			lockdep_is_held(&reg_lock));
		rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), NULL);
	}

	/* Wait for inflight memcg_path_buf users to finish. */
	synchronize_rcu();

	old = tmp_bufs;
	for_each_possible_cpu(cpu) {
		kfree(*(old++));
	}

	kfree(tmp_bufs);
	tmp_bufs = NULL;
}

int trace_mmap_lock_reg(void)
{
	int cpu;
	char *new;

	mutex_lock(&reg_lock);

	/* If the refcount is going 0->1, proceed with allocating buffers. */
	if (reg_refcount++)
		goto out;

	tmp_bufs = kmalloc_array(num_possible_cpus(), sizeof(*tmp_bufs),
				 GFP_KERNEL);
	if (tmp_bufs == NULL)
		goto out_fail;

	for_each_possible_cpu(cpu) {
		new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL);
		if (new == NULL)
			goto out_fail_free;
		rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), new);
		/* Don't need to wait for inflights, they'd have gotten NULL. */
	}

out:
	mutex_unlock(&reg_lock);
	return 0;

out_fail_free:
	free_memcg_path_bufs();
out_fail:
	/* Since we failed, undo the earlier ref increment. */
	--reg_refcount;

	mutex_unlock(&reg_lock);
	return -ENOMEM;
}

void trace_mmap_lock_unreg(void)
{
	mutex_lock(&reg_lock);

	/* If the refcount is going 1->0, proceed with freeing buffers. */
	if (--reg_refcount)
		goto out;

	free_memcg_path_bufs();

out:
	mutex_unlock(&reg_lock);
}

static inline char *get_memcg_path_buf(void)
{
	char *buf;
	int idx;

	rcu_read_lock();
	buf = rcu_dereference(*this_cpu_ptr(&memcg_path_buf));
	if (buf == NULL) {
		rcu_read_unlock();
		return NULL;
	}
	idx = this_cpu_add_return(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE) -
	      MEMCG_PATH_BUF_SIZE;
	return &buf[idx];
}

static inline void put_memcg_path_buf(void)
{
	this_cpu_sub(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE);
	rcu_read_unlock();
}

/*
 * Write the given mm_struct's memcg path to a percpu buffer, and return a
 * pointer to it. If the path cannot be determined, or no buffer was available
 * (because the trace event is being unregistered), NULL is returned.
 *
 * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
 * disabled by the caller before calling us, and re-enabled only after the
 * caller is done with the pointer.
 *
 * The caller must call put_memcg_path_buf() once the buffer is no longer
 * needed. This must be done while preemption is still disabled.
 */
static const char *get_mm_memcg_path(struct mm_struct *mm)
{
	char *buf = NULL;
	struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);

	if (memcg == NULL)
		goto out;
	if (unlikely(memcg->css.cgroup == NULL))
		goto out_put;

	buf = get_memcg_path_buf();
	if (buf == NULL)
		goto out_put;

	cgroup_path(memcg->css.cgroup, buf, MEMCG_PATH_BUF_SIZE);

out_put:
	css_put(&memcg->css);
out:
	return buf;
}

#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
	do {                                                                   \
		const char *memcg_path;                                        \
		preempt_disable();                                             \
		memcg_path = get_mm_memcg_path(mm);                            \
		trace_mmap_lock_##type(mm,                                     \
				       memcg_path != NULL ? memcg_path : "",   \
				       ##__VA_ARGS__);                         \
		if (likely(memcg_path != NULL))                                \
			put_memcg_path_buf();                                  \
		preempt_enable();                                              \
	} while (0)

#else /* !CONFIG_MEMCG */

int trace_mmap_lock_reg(void)
{
	return 0;
}

void trace_mmap_lock_unreg(void)
{
}

#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
	trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)

#endif /* CONFIG_MEMCG */

/*
 * Trace calls must be in a separate file, as otherwise there's a circular
 * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
 */

void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
{
	TRACE_MMAP_LOCK_EVENT(start_locking, mm, write);
}
EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);

void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
					   bool success)
{
	TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
}
EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);

void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
{
	TRACE_MMAP_LOCK_EVENT(released, mm, write);
}
EXPORT_SYMBOL(__mmap_lock_do_trace_released);