summaryrefslogtreecommitdiff
path: root/tools/perf/util/mmap.c
blob: ab7108d22428b5271428a76dd03922f1914d2d48 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * 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.
 */

#include <sys/mman.h>
#include <inttypes.h>
#include <asm/bug.h>
#include <linux/zalloc.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h> // sysconf()
#include <perf/mmap.h>
#ifdef HAVE_LIBNUMA_SUPPORT
#include <numaif.h>
#endif
#include "cpumap.h"
#include "debug.h"
#include "event.h"
#include "mmap.h"
#include "../perf.h"
#include <internal/lib.h> /* page_size */
#include <linux/bitmap.h>

#define MASK_SIZE 1023
void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag)
{
	char buf[MASK_SIZE + 1];
	size_t len;

	len = bitmap_scnprintf(mask->bits, mask->nbits, buf, MASK_SIZE);
	buf[len] = '\0';
	pr_debug("%p: %s mask[%zd]: %s\n", mask, tag, mask->nbits, buf);
}

size_t mmap__mmap_len(struct mmap *map)
{
	return perf_mmap__mmap_len(&map->core);
}

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 evlist *evlist __maybe_unused,
					  int idx __maybe_unused,
					  bool per_cpu __maybe_unused)
{
}

#ifdef HAVE_AIO_SUPPORT
static int perf_mmap__aio_enabled(struct mmap *map)
{
	return map->aio.nr_cblocks > 0;
}

#ifdef HAVE_LIBNUMA_SUPPORT
static int perf_mmap__aio_alloc(struct mmap *map, int idx)
{
	map->aio.data[idx] = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
				  MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
	if (map->aio.data[idx] == MAP_FAILED) {
		map->aio.data[idx] = NULL;
		return -1;
	}

	return 0;
}

static void perf_mmap__aio_free(struct mmap *map, int idx)
{
	if (map->aio.data[idx]) {
		munmap(map->aio.data[idx], mmap__mmap_len(map));
		map->aio.data[idx] = NULL;
	}
}

static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
{
	void *data;
	size_t mmap_len;
	unsigned long *node_mask;
	unsigned long node_index;
	int err = 0;

	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
		data = map->aio.data[idx];
		mmap_len = mmap__mmap_len(map);
		node_index = cpu__get_node(cpu);
		node_mask = bitmap_alloc(node_index + 1);
		if (!node_mask) {
			pr_err("Failed to allocate node mask for mbind: error %m\n");
			return -1;
		}
		set_bit(node_index, node_mask);
		if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
			pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
				data, data + mmap_len, node_index);
			err = -1;
		}
		bitmap_free(node_mask);
	}

	return err;
}
#else /* !HAVE_LIBNUMA_SUPPORT */
static int perf_mmap__aio_alloc(struct mmap *map, int idx)
{
	map->aio.data[idx] = malloc(mmap__mmap_len(map));
	if (map->aio.data[idx] == NULL)
		return -1;

	return 0;
}

static void perf_mmap__aio_free(struct mmap *map, int idx)
{
	zfree(&(map->aio.data[idx]));
}

static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused,
		int cpu __maybe_unused, int affinity __maybe_unused)
{
	return 0;
}
#endif

static int perf_mmap__aio_mmap(struct mmap *map, struct mmap_params *mp)
{
	int delta_max, i, prio, ret;

	map->aio.nr_cblocks = mp->nr_cblocks;
	if (map->aio.nr_cblocks) {
		map->aio.aiocb = calloc(map->aio.nr_cblocks, sizeof(struct aiocb *));
		if (!map->aio.aiocb) {
			pr_debug2("failed to allocate aiocb for data buffer, error %m\n");
			return -1;
		}
		map->aio.cblocks = calloc(map->aio.nr_cblocks, sizeof(struct aiocb));
		if (!map->aio.cblocks) {
			pr_debug2("failed to allocate cblocks for data buffer, error %m\n");
			return -1;
		}
		map->aio.data = calloc(map->aio.nr_cblocks, sizeof(void *));
		if (!map->aio.data) {
			pr_debug2("failed to allocate data buffer, error %m\n");
			return -1;
		}
		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
		for (i = 0; i < map->aio.nr_cblocks; ++i) {
			ret = perf_mmap__aio_alloc(map, i);
			if (ret == -1) {
				pr_debug2("failed to allocate data buffer area, error %m");
				return -1;
			}
			ret = perf_mmap__aio_bind(map, i, map->core.cpu, mp->affinity);
			if (ret == -1)
				return -1;
			/*
			 * Use cblock.aio_fildes value different from -1
			 * to denote started aio write operation on the
			 * cblock so it requires explicit record__aio_sync()
			 * call prior the cblock may be reused again.
			 */
			map->aio.cblocks[i].aio_fildes = -1;
			/*
			 * Allocate cblocks with priority delta to have
			 * faster aio write system calls because queued requests
			 * are kept in separate per-prio queues and adding
			 * a new request will iterate thru shorter per-prio
			 * list. Blocks with numbers higher than
			 *  _SC_AIO_PRIO_DELTA_MAX go with priority 0.
			 */
			prio = delta_max - i;
			map->aio.cblocks[i].aio_reqprio = prio >= 0 ? prio : 0;
		}
	}

	return 0;
}

static void perf_mmap__aio_munmap(struct mmap *map)
{
	int i;

	for (i = 0; i < map->aio.nr_cblocks; ++i)
		perf_mmap__aio_free(map, i);
	if (map->aio.data)
		zfree(&map->aio.data);
	zfree(&map->aio.cblocks);
	zfree(&map->aio.aiocb);
}
#else /* !HAVE_AIO_SUPPORT */
static int perf_mmap__aio_enabled(struct mmap *map __maybe_unused)
{
	return 0;
}

static int perf_mmap__aio_mmap(struct mmap *map __maybe_unused,
			       struct mmap_params *mp __maybe_unused)
{
	return 0;
}

static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused)
{
}
#endif

void mmap__munmap(struct mmap *map)
{
	bitmap_free(map->affinity_mask.bits);

	perf_mmap__aio_munmap(map);
	if (map->data != NULL) {
		munmap(map->data, mmap__mmap_len(map));
		map->data = NULL;
	}
	auxtrace_mmap__munmap(&map->auxtrace_mmap);
}

static void build_node_mask(int node, struct mmap_cpu_mask *mask)
{
	int c, cpu, nr_cpus;
	const struct perf_cpu_map *cpu_map = NULL;

	cpu_map = cpu_map__online();
	if (!cpu_map)
		return;

	nr_cpus = perf_cpu_map__nr(cpu_map);
	for (c = 0; c < nr_cpus; c++) {
		cpu = cpu_map->map[c]; /* map c index to online cpu index */
		if (cpu__get_node(cpu) == node)
			set_bit(cpu, mask->bits);
	}
}

static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
{
	map->affinity_mask.nbits = cpu__max_cpu();
	map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits);
	if (!map->affinity_mask.bits)
		return -1;

	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
		build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
	else if (mp->affinity == PERF_AFFINITY_CPU)
		set_bit(map->core.cpu, map->affinity_mask.bits);

	return 0;
}

int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
{
	if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
			  errno);
		return -1;
	}

	if (mp->affinity != PERF_AFFINITY_SYS &&
		perf_mmap__setup_affinity_mask(map, mp)) {
		pr_debug2("failed to alloc mmap affinity mask, error %d\n",
			  errno);
		return -1;
	}

	if (verbose == 2)
		mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap");

	map->core.flush = mp->flush;

	map->comp_level = mp->comp_level;

	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
		if (map->data == MAP_FAILED) {
			pr_debug2("failed to mmap data buffer, error %d\n",
					errno);
			map->data = NULL;
			return -1;
		}
	}

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

	return perf_mmap__aio_mmap(map, mp);
}

int perf_mmap__push(struct mmap *md, void *to,
		    int push(struct mmap *map, void *to, void *buf, size_t size))
{
	u64 head = perf_mmap__read_head(&md->core);
	unsigned char *data = md->core.base + page_size;
	unsigned long size;
	void *buf;
	int rc = 0;

	rc = perf_mmap__read_init(&md->core);
	if (rc < 0)
		return (rc == -EAGAIN) ? 1 : -1;

	size = md->core.end - md->core.start;

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

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

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

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

	md->core.prev = head;
	perf_mmap__consume(&md->core);
out:
	return rc;
}