aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util/mmap.c
blob: 9fe5f9c7d577e39d185d0d28d800def889fbfa3e (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
/*
 * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
 * copyright notes.
 *
 * Released under the GPL v2. (and only v2, not any later version)
 */

#include <sys/mman.h>
#include <inttypes.h>
#include <asm/bug.h>
#include "debug.h"
#include "event.h"
#include "mmap.h"
#include "util.h" /* page_size */

size_t perf_mmap__mmap_len(struct perf_mmap *map)
{
	return map->mask + 1 + page_size;
}

/* When check_messup is true, 'end' must points to a good entry */
static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup,
					 u64 start, u64 end, u64 *prev)
{
	unsigned char *data = map->base + page_size;
	union perf_event *event = NULL;
	int diff = end - start;

	if (check_messup) {
		/*
		 * If we're further behind than half the buffer, there's a chance
		 * the writer will bite our tail and mess up the samples under us.
		 *
		 * If we somehow ended up ahead of the 'end', we got messed up.
		 *
		 * In either case, truncate and restart at 'end'.
		 */
		if (diff > map->mask / 2 || diff < 0) {
			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");

			/*
			 * 'end' points to a known good entry, start there.
			 */
			start = end;
			diff = 0;
		}
	}

	if (diff >= (int)sizeof(event->header)) {
		size_t size;

		event = (union perf_event *)&data[start & map->mask];
		size = event->header.size;

		if (size < sizeof(event->header) || diff < (int)size) {
			event = NULL;
			goto broken_event;
		}

		/*
		 * Event straddles the mmap boundary -- header should always
		 * be inside due to u64 alignment of output.
		 */
		if ((start & map->mask) + size != ((start + size) & map->mask)) {
			unsigned int offset = start;
			unsigned int len = min(sizeof(*event), size), cpy;
			void *dst = map->event_copy;

			do {
				cpy = min(map->mask + 1 - (offset & map->mask), len);
				memcpy(dst, &data[offset & map->mask], cpy);
				offset += cpy;
				dst += cpy;
				len -= cpy;
			} while (len);

			event = (union perf_event *)map->event_copy;
		}

		start += size;
	}

broken_event:
	if (prev)
		*prev = start;

	return event;
}

union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup)
{
	u64 head;
	u64 old = map->prev;

	/*
	 * Check if event was unmapped due to a POLLHUP/POLLERR.
	 */
	if (!refcount_read(&map->refcnt))
		return NULL;

	head = perf_mmap__read_head(map);

	return perf_mmap__read(map, check_messup, old, head, &map->prev);
}

union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
{
	u64 head, end;
	u64 start = map->prev;

	/*
	 * Check if event was unmapped due to a POLLHUP/POLLERR.
	 */
	if (!refcount_read(&map->refcnt))
		return NULL;

	head = perf_mmap__read_head(map);
	if (!head)
		return NULL;

	/*
	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
	 * it each time when kernel writes to it, so in fact 'head' is
	 * negative. 'end' pointer is made manually by adding the size of
	 * the ring buffer to 'head' pointer, means the validate data can
	 * read is the whole ring buffer. If 'end' is positive, the ring
	 * buffer has not fully filled, so we must adjust 'end' to 0.
	 *
	 * However, since both 'head' and 'end' is unsigned, we can't
	 * simply compare 'end' against 0. Here we compare '-head' and
	 * the size of the ring buffer, where -head is the number of bytes
	 * kernel write to the ring buffer.
	 */
	if (-head < (u64)(map->mask + 1))
		end = 0;
	else
		end = head + map->mask + 1;

	return perf_mmap__read(map, false, start, end, &map->prev);
}

void perf_mmap__read_catchup(struct perf_mmap *map)
{
	u64 head;

	if (!refcount_read(&map->refcnt))
		return;

	head = perf_mmap__read_head(map);
	map->prev = head;
}

static bool perf_mmap__empty(struct perf_mmap *map)
{
	return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
}

void perf_mmap__get(struct perf_mmap *map)
{
	refcount_inc(&map->refcnt);
}

void perf_mmap__put(struct perf_mmap *map)
{
	BUG_ON(map->base && refcount_read(&map->refcnt) == 0);

	if (refcount_dec_and_test(&map->refcnt))
		perf_mmap__munmap(map);
}

void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
{
	if (!overwrite) {
		u64 old = map->prev;

		perf_mmap__write_tail(map, old);
	}

	if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
		perf_mmap__put(map);
}

int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
			       struct auxtrace_mmap_params *mp __maybe_unused,
			       void *userpg __maybe_unused,
			       int fd __maybe_unused)
{
	return 0;
}

void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
{
}

void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused,
				       off_t auxtrace_offset __maybe_unused,
				       unsigned int auxtrace_pages __maybe_unused,
				       bool auxtrace_overwrite __maybe_unused)
{
}

void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
					  struct perf_evlist *evlist __maybe_unused,
					  int idx __maybe_unused,
					  bool per_cpu __maybe_unused)
{
}

void perf_mmap__munmap(struct perf_mmap *map)
{
	if (map->base != NULL) {
		munmap(map->base, perf_mmap__mmap_len(map));
		map->base = NULL;
		map->fd = -1;
		refcount_set(&map->refcnt, 0);
	}
	auxtrace_mmap__munmap(&map->auxtrace_mmap);
}

int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
{
	/*
	 * The last one will be done at perf_evlist__mmap_consume(), so that we
	 * make sure we don't prevent tools from consuming every last event in
	 * the ring buffer.
	 *
	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
	 * anymore, but the last events for it are still in the ring buffer,
	 * waiting to be consumed.
	 *
	 * Tools can chose to ignore this at their own discretion, but the
	 * evlist layer can't just drop it when filtering events in
	 * perf_evlist__filter_pollfd().
	 */
	refcount_set(&map->refcnt, 2);
	map->prev = 0;
	map->mask = mp->mask;
	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
			 MAP_SHARED, fd, 0);
	if (map->base == MAP_FAILED) {
		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
			  errno);
		map->base = NULL;
		return -1;
	}
	map->fd = fd;

	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
				&mp->auxtrace_mp, map->base, fd))
		return -1;

	return 0;
}

static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
{
	struct perf_event_header *pheader;
	u64 evt_head = head;
	int size = mask + 1;

	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
	pheader = (struct perf_event_header *)(buf + (head & mask));
	*start = head;
	while (true) {
		if (evt_head - head >= (unsigned int)size) {
			pr_debug("Finished reading backward ring buffer: rewind\n");
			if (evt_head - head > (unsigned int)size)
				evt_head -= pheader->size;
			*end = evt_head;
			return 0;
		}

		pheader = (struct perf_event_header *)(buf + (evt_head & mask));

		if (pheader->size == 0) {
			pr_debug("Finished reading backward ring buffer: get start\n");
			*end = evt_head;
			return 0;
		}

		evt_head += pheader->size;
		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
	}
	WARN_ONCE(1, "Shouldn't get here\n");
	return -1;
}

static int rb_find_range(void *data, int mask, u64 head, u64 old,
			 u64 *start, u64 *end, bool backward)
{
	if (!backward) {
		*start = old;
		*end = head;
		return 0;
	}

	return backward_rb_find_range(data, mask, head, start, end);
}

int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
		    void *to, int push(void *to, void *buf, size_t size))
{
	u64 head = perf_mmap__read_head(md);
	u64 old = md->prev;
	u64 end = head, start = old;
	unsigned char *data = md->base + page_size;
	unsigned long size;
	void *buf;
	int rc = 0;

	if (rb_find_range(data, md->mask, head, old, &start, &end, backward))
		return -1;

	if (start == end)
		return 0;

	size = end - start;
	if (size > (unsigned long)(md->mask) + 1) {
		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");

		md->prev = head;
		perf_mmap__consume(md, overwrite || backward);
		return 0;
	}

	if ((start & md->mask) + size != (end & md->mask)) {
		buf = &data[start & md->mask];
		size = md->mask + 1 - (start & md->mask);
		start += size;

		if (push(to, buf, size) < 0) {
			rc = -1;
			goto out;
		}
	}

	buf = &data[start & md->mask];
	size = end - start;
	start += size;

	if (push(to, buf, size) < 0) {
		rc = -1;
		goto out;
	}

	md->prev = head;
	perf_mmap__consume(md, overwrite || backward);
out:
	return rc;
}