summaryrefslogtreecommitdiff
path: root/tools/perf/util/evlist.c
blob: 1884a7c7eb8f1d3666f47bd38a49202fffdc74d8 (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
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
/*
 * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Parts came from 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 <poll.h>
#include "cpumap.h"
#include "thread_map.h"
#include "evlist.h"
#include "evsel.h"
#include "util.h"
#include "debug.h"

#include <sys/mman.h>

#include <linux/bitops.h>
#include <linux/hash.h>

#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)

void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
		       struct thread_map *threads)
{
	int i;

	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
		INIT_HLIST_HEAD(&evlist->heads[i]);
	INIT_LIST_HEAD(&evlist->entries);
	perf_evlist__set_maps(evlist, cpus, threads);
}

struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
				     struct thread_map *threads)
{
	struct perf_evlist *evlist = zalloc(sizeof(*evlist));

	if (evlist != NULL)
		perf_evlist__init(evlist, cpus, threads);

	return evlist;
}

static void perf_evlist__purge(struct perf_evlist *evlist)
{
	struct perf_evsel *pos, *n;

	list_for_each_entry_safe(pos, n, &evlist->entries, node) {
		list_del_init(&pos->node);
		perf_evsel__delete(pos);
	}

	evlist->nr_entries = 0;
}

void perf_evlist__exit(struct perf_evlist *evlist)
{
	free(evlist->mmap);
	free(evlist->pollfd);
	evlist->mmap = NULL;
	evlist->pollfd = NULL;
}

void perf_evlist__delete(struct perf_evlist *evlist)
{
	perf_evlist__purge(evlist);
	perf_evlist__exit(evlist);
	free(evlist);
}

void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
{
	list_add_tail(&entry->node, &evlist->entries);
	++evlist->nr_entries;
}

int perf_evlist__add_default(struct perf_evlist *evlist)
{
	struct perf_event_attr attr = {
		.type = PERF_TYPE_HARDWARE,
		.config = PERF_COUNT_HW_CPU_CYCLES,
	};
	struct perf_evsel *evsel = perf_evsel__new(&attr, 0);

	if (evsel == NULL)
		return -ENOMEM;

	perf_evlist__add(evlist, evsel);
	return 0;
}

int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
{
	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
	return evlist->pollfd != NULL ? 0 : -ENOMEM;
}

void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
{
	fcntl(fd, F_SETFL, O_NONBLOCK);
	evlist->pollfd[evlist->nr_fds].fd = fd;
	evlist->pollfd[evlist->nr_fds].events = POLLIN;
	evlist->nr_fds++;
}

static void perf_evlist__id_hash(struct perf_evlist *evlist,
				 struct perf_evsel *evsel,
				 int cpu, int thread, u64 id)
{
	int hash;
	struct perf_sample_id *sid = SID(evsel, cpu, thread);

	sid->id = id;
	sid->evsel = evsel;
	hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
	hlist_add_head(&sid->node, &evlist->heads[hash]);
}

void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
			 int cpu, int thread, u64 id)
{
	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
	evsel->id[evsel->ids++] = id;
}

static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
				  struct perf_evsel *evsel,
				  int cpu, int thread, int fd)
{
	u64 read_data[4] = { 0, };
	int id_idx = 1; /* The first entry is the counter value */

	if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
	    read(fd, &read_data, sizeof(read_data)) == -1)
		return -1;

	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		++id_idx;
	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		++id_idx;

	perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
	return 0;
}

struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
{
	struct hlist_head *head;
	struct hlist_node *pos;
	struct perf_sample_id *sid;
	int hash;

	if (evlist->nr_entries == 1)
		return list_entry(evlist->entries.next, struct perf_evsel, node);

	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
	head = &evlist->heads[hash];

	hlist_for_each_entry(sid, pos, head, node)
		if (sid->id == id)
			return sid->evsel;
	return NULL;
}

union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
{
	/* XXX Move this to perf.c, making it generally available */
	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
	struct perf_mmap *md = &evlist->mmap[cpu];
	unsigned int head = perf_mmap__read_head(md);
	unsigned int old = md->prev;
	unsigned char *data = md->base + page_size;
	union perf_event *event = NULL;

	if (evlist->overwrite) {
		/*
		 * 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 head, we got messed up.
		 *
		 * In either case, truncate and restart at head.
		 */
		int diff = head - old;
		if (diff > md->mask / 2 || diff < 0) {
			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");

			/*
			 * head points to a known good entry, start there.
			 */
			old = head;
		}
	}

	if (old != head) {
		size_t size;

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

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

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

			event = &evlist->event_copy;
		}

		old += size;
	}

	md->prev = old;

	if (!evlist->overwrite)
		perf_mmap__write_tail(md, old);

	return event;
}

void perf_evlist__munmap(struct perf_evlist *evlist)
{
	int cpu;

	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
		if (evlist->mmap[cpu].base != NULL) {
			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
			evlist->mmap[cpu].base = NULL;
		}
	}
}

int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
{
	evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
	return evlist->mmap != NULL ? 0 : -ENOMEM;
}

static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
			       int cpu, int prot, int mask, int fd)
{
	evlist->mmap[cpu].prev = 0;
	evlist->mmap[cpu].mask = mask;
	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
				      MAP_SHARED, fd, 0);
	if (evlist->mmap[cpu].base == MAP_FAILED) {
		if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit)
			ui__warning("Inherit is not allowed on per-task "
				    "events using mmap.\n");
		return -1;
	}

	perf_evlist__add_pollfd(evlist, fd);
	return 0;
}

/** perf_evlist__mmap - Create per cpu maps to receive events
 *
 * @evlist - list of events
 * @pages - map length in pages
 * @overwrite - overwrite older events?
 *
 * If overwrite is false the user needs to signal event consuption using:
 *
 *	struct perf_mmap *m = &evlist->mmap[cpu];
 *	unsigned int head = perf_mmap__read_head(m);
 *
 *	perf_mmap__write_tail(m, head)
 *
 * Using perf_evlist__read_on_cpu does this automatically.
 */
int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
{
	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
	int mask = pages * page_size - 1, cpu;
	struct perf_evsel *first_evsel, *evsel;
	const struct cpu_map *cpus = evlist->cpus;
	const struct thread_map *threads = evlist->threads;
	int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);

	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
		return -ENOMEM;

	if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
		return -ENOMEM;

	evlist->overwrite = overwrite;
	evlist->mmap_len = (pages + 1) * page_size;
	first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);

	list_for_each_entry(evsel, &evlist->entries, node) {
		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
		    evsel->sample_id == NULL &&
		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
			return -ENOMEM;

		for (cpu = 0; cpu < cpus->nr; cpu++) {
			for (thread = 0; thread < threads->nr; thread++) {
				int fd = FD(evsel, cpu, thread);

				if (evsel->idx || thread) {
					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
						  FD(first_evsel, cpu, 0)) != 0)
						goto out_unmap;
				} else if (__perf_evlist__mmap(evlist, evsel, cpu,
							       prot, mask, fd) < 0)
					goto out_unmap;

				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
					goto out_unmap;
			}
		}
	}

	return 0;

out_unmap:
	for (cpu = 0; cpu < cpus->nr; cpu++) {
		if (evlist->mmap[cpu].base != NULL) {
			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
			evlist->mmap[cpu].base = NULL;
		}
	}
	return -1;
}

int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
			     pid_t target_tid, const char *cpu_list)
{
	evlist->threads = thread_map__new(target_pid, target_tid);

	if (evlist->threads == NULL)
		return -1;

	if (cpu_list == NULL && target_tid != -1)
		evlist->cpus = cpu_map__dummy_new();
	else
		evlist->cpus = cpu_map__new(cpu_list);

	if (evlist->cpus == NULL)
		goto out_delete_threads;

	return 0;

out_delete_threads:
	thread_map__delete(evlist->threads);
	return -1;
}

void perf_evlist__delete_maps(struct perf_evlist *evlist)
{
	cpu_map__delete(evlist->cpus);
	thread_map__delete(evlist->threads);
	evlist->cpus	= NULL;
	evlist->threads = NULL;
}

int perf_evlist__set_filters(struct perf_evlist *evlist)
{
	const struct thread_map *threads = evlist->threads;
	const struct cpu_map *cpus = evlist->cpus;
	struct perf_evsel *evsel;
	char *filter;
	int thread;
	int cpu;
	int err;
	int fd;

	list_for_each_entry(evsel, &evlist->entries, node) {
		filter = evsel->filter;
		if (!filter)
			continue;
		for (cpu = 0; cpu < cpus->nr; cpu++) {
			for (thread = 0; thread < threads->nr; thread++) {
				fd = FD(evsel, cpu, thread);
				err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
				if (err)
					return err;
			}
		}
	}

	return 0;
}