summaryrefslogtreecommitdiffstats
path: root/tools/bpf/bpftool/map_perf_ring.c
blob: 6d41323be291bbf7e18348375aa88006d36facda (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (C) 2018 Netronome Systems, Inc. */
/* This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 */
#include <errno.h>
#include <fcntl.h>
#include <libbpf.h>
#include <poll.h>
#include <signal.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
#include <linux/bpf.h>
#include <linux/perf_event.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/syscall.h>

#include <bpf.h>
#include <perf-sys.h>

#include "main.h"

#define MMAP_PAGE_CNT	16

static bool stop;

struct event_ring_info {
	int fd;
	int key;
	unsigned int cpu;
	void *mem;
};

struct perf_event_sample {
	struct perf_event_header header;
	u64 time;
	__u32 size;
	unsigned char data[];
};

static void int_exit(int signo)
{
	fprintf(stderr, "Stopping...\n");
	stop = true;
}

static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
{
	struct event_ring_info *ring = priv;
	struct perf_event_sample *e = event;
	struct {
		struct perf_event_header header;
		__u64 id;
		__u64 lost;
	} *lost = event;

	if (json_output) {
		jsonw_start_object(json_wtr);
		jsonw_name(json_wtr, "type");
		jsonw_uint(json_wtr, e->header.type);
		jsonw_name(json_wtr, "cpu");
		jsonw_uint(json_wtr, ring->cpu);
		jsonw_name(json_wtr, "index");
		jsonw_uint(json_wtr, ring->key);
		if (e->header.type == PERF_RECORD_SAMPLE) {
			jsonw_name(json_wtr, "timestamp");
			jsonw_uint(json_wtr, e->time);
			jsonw_name(json_wtr, "data");
			print_data_json(e->data, e->size);
		} else if (e->header.type == PERF_RECORD_LOST) {
			jsonw_name(json_wtr, "lost");
			jsonw_start_object(json_wtr);
			jsonw_name(json_wtr, "id");
			jsonw_uint(json_wtr, lost->id);
			jsonw_name(json_wtr, "count");
			jsonw_uint(json_wtr, lost->lost);
			jsonw_end_object(json_wtr);
		}
		jsonw_end_object(json_wtr);
	} else {
		if (e->header.type == PERF_RECORD_SAMPLE) {
			printf("== @%lld.%09lld CPU: %d index: %d =====\n",
			       e->time / 1000000000ULL, e->time % 1000000000ULL,
			       ring->cpu, ring->key);
			fprint_hex(stdout, e->data, e->size, " ");
			printf("\n");
		} else if (e->header.type == PERF_RECORD_LOST) {
			printf("lost %lld events\n", lost->lost);
		} else {
			printf("unknown event type=%d size=%d\n",
			       e->header.type, e->header.size);
		}
	}

	return LIBBPF_PERF_EVENT_CONT;
}

static void
perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len)
{
	enum bpf_perf_event_ret ret;

	ret = bpf_perf_event_read_simple(ring->mem,
					 MMAP_PAGE_CNT * get_page_size(),
					 get_page_size(), buf, buf_len,
					 print_bpf_output, ring);
	if (ret != LIBBPF_PERF_EVENT_CONT) {
		fprintf(stderr, "perf read loop failed with %d\n", ret);
		stop = true;
	}
}

static int perf_mmap_size(void)
{
	return get_page_size() * (MMAP_PAGE_CNT + 1);
}

static void *perf_event_mmap(int fd)
{
	int mmap_size = perf_mmap_size();
	void *base;

	base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
	if (base == MAP_FAILED) {
		p_err("event mmap failed: %s\n", strerror(errno));
		return NULL;
	}

	return base;
}

static void perf_event_unmap(void *mem)
{
	if (munmap(mem, perf_mmap_size()))
		fprintf(stderr, "Can't unmap ring memory!\n");
}

static int bpf_perf_event_open(int map_fd, int key, int cpu)
{
	struct perf_event_attr attr = {
		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
		.type = PERF_TYPE_SOFTWARE,
		.config = PERF_COUNT_SW_BPF_OUTPUT,
	};
	int pmu_fd;

	pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
	if (pmu_fd < 0) {
		p_err("failed to open perf event %d for CPU %d", key, cpu);
		return -1;
	}

	if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
		p_err("failed to update map for event %d for CPU %d", key, cpu);
		goto err_close;
	}
	if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
		p_err("failed to enable event %d for CPU %d", key, cpu);
		goto err_close;
	}

	return pmu_fd;

err_close:
	close(pmu_fd);
	return -1;
}

int do_event_pipe(int argc, char **argv)
{
	int i, nfds, map_fd, index = -1, cpu = -1;
	struct bpf_map_info map_info = {};
	struct event_ring_info *rings;
	size_t tmp_buf_sz = 0;
	void *tmp_buf = NULL;
	struct pollfd *pfds;
	__u32 map_info_len;
	bool do_all = true;

	map_info_len = sizeof(map_info);
	map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
	if (map_fd < 0)
		return -1;

	if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
		p_err("map is not a perf event array");
		goto err_close_map;
	}

	while (argc) {
		if (argc < 2) {
			BAD_ARG();
			goto err_close_map;
		}

		if (is_prefix(*argv, "cpu")) {
			char *endptr;

			NEXT_ARG();
			cpu = strtoul(*argv, &endptr, 0);
			if (*endptr) {
				p_err("can't parse %s as CPU ID", **argv);
				goto err_close_map;
			}

			NEXT_ARG();
		} else if (is_prefix(*argv, "index")) {
			char *endptr;

			NEXT_ARG();
			index = strtoul(*argv, &endptr, 0);
			if (*endptr) {
				p_err("can't parse %s as index", **argv);
				goto err_close_map;
			}

			NEXT_ARG();
		} else {
			BAD_ARG();
			goto err_close_map;
		}

		do_all = false;
	}

	if (!do_all) {
		if (index == -1 || cpu == -1) {
			p_err("cpu and index must be specified together");
			goto err_close_map;
		}

		nfds = 1;
	} else {
		nfds = min(get_possible_cpus(), map_info.max_entries);
		cpu = 0;
		index = 0;
	}

	rings = calloc(nfds, sizeof(rings[0]));
	if (!rings)
		goto err_close_map;

	pfds = calloc(nfds, sizeof(pfds[0]));
	if (!pfds)
		goto err_free_rings;

	for (i = 0; i < nfds; i++) {
		rings[i].cpu = cpu + i;
		rings[i].key = index + i;

		rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
						  rings[i].cpu);
		if (rings[i].fd < 0)
			goto err_close_fds_prev;

		rings[i].mem = perf_event_mmap(rings[i].fd);
		if (!rings[i].mem)
			goto err_close_fds_current;

		pfds[i].fd = rings[i].fd;
		pfds[i].events = POLLIN;
	}

	signal(SIGINT, int_exit);
	signal(SIGHUP, int_exit);
	signal(SIGTERM, int_exit);

	if (json_output)
		jsonw_start_array(json_wtr);

	while (!stop) {
		poll(pfds, nfds, 200);
		for (i = 0; i < nfds; i++)
			perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
	}
	free(tmp_buf);

	if (json_output)
		jsonw_end_array(json_wtr);

	for (i = 0; i < nfds; i++) {
		perf_event_unmap(rings[i].mem);
		close(rings[i].fd);
	}
	free(pfds);
	free(rings);
	close(map_fd);

	return 0;

err_close_fds_prev:
	while (i--) {
		perf_event_unmap(rings[i].mem);
err_close_fds_current:
		close(rings[i].fd);
	}
	free(pfds);
err_free_rings:
	free(rings);
err_close_map:
	close(map_fd);
	return -1;
}