summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/bpf_off_cpu.c
blob: 21f4d9ba023d94bd0df4c55667eed3516d224bc7 (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
// SPDX-License-Identifier: GPL-2.0
#include "util/bpf_counter.h"
#include "util/debug.h"
#include "util/evsel.h"
#include "util/evlist.h"
#include "util/off_cpu.h"
#include "util/perf-hooks.h"
#include "util/record.h"
#include "util/session.h"
#include "util/target.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/cgroup.h"
#include "util/strlist.h"
#include <bpf/bpf.h>

#include "bpf_skel/off_cpu.skel.h"

#define MAX_STACKS  32
#define MAX_PROC  4096
/* we don't need actual timestamp, just want to put the samples at last */
#define OFF_CPU_TIMESTAMP  (~0ull << 32)

static struct off_cpu_bpf *skel;

struct off_cpu_key {
	u32 pid;
	u32 tgid;
	u32 stack_id;
	u32 state;
	u64 cgroup_id;
};

union off_cpu_data {
	struct perf_event_header hdr;
	u64 array[1024 / sizeof(u64)];
};

static int off_cpu_config(struct evlist *evlist)
{
	struct evsel *evsel;
	struct perf_event_attr attr = {
		.type	= PERF_TYPE_SOFTWARE,
		.config = PERF_COUNT_SW_BPF_OUTPUT,
		.size	= sizeof(attr), /* to capture ABI version */
	};
	char *evname = strdup(OFFCPU_EVENT);

	if (evname == NULL)
		return -ENOMEM;

	evsel = evsel__new(&attr);
	if (!evsel) {
		free(evname);
		return -ENOMEM;
	}

	evsel->core.attr.freq = 1;
	evsel->core.attr.sample_period = 1;
	/* off-cpu analysis depends on stack trace */
	evsel->core.attr.sample_type = PERF_SAMPLE_CALLCHAIN;

	evlist__add(evlist, evsel);

	free(evsel->name);
	evsel->name = evname;

	return 0;
}

static void off_cpu_start(void *arg)
{
	struct evlist *evlist = arg;

	/* update task filter for the given workload */
	if (!skel->bss->has_cpu && !skel->bss->has_task &&
	    perf_thread_map__pid(evlist->core.threads, 0) != -1) {
		int fd;
		u32 pid;
		u8 val = 1;

		skel->bss->has_task = 1;
		skel->bss->uses_tgid = 1;
		fd = bpf_map__fd(skel->maps.task_filter);
		pid = perf_thread_map__pid(evlist->core.threads, 0);
		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
	}

	skel->bss->enabled = 1;
}

static void off_cpu_finish(void *arg __maybe_unused)
{
	skel->bss->enabled = 0;
	off_cpu_bpf__destroy(skel);
}

/* v5.18 kernel added prev_state arg, so it needs to check the signature */
static void check_sched_switch_args(void)
{
	const struct btf *btf = btf__load_vmlinux_btf();
	const struct btf_type *t1, *t2, *t3;
	u32 type_id;

	type_id = btf__find_by_name_kind(btf, "btf_trace_sched_switch",
					 BTF_KIND_TYPEDEF);
	if ((s32)type_id < 0)
		return;

	t1 = btf__type_by_id(btf, type_id);
	if (t1 == NULL)
		return;

	t2 = btf__type_by_id(btf, t1->type);
	if (t2 == NULL || !btf_is_ptr(t2))
		return;

	t3 = btf__type_by_id(btf, t2->type);
	/* btf_trace func proto has one more argument for the context */
	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 5) {
		/* new format: pass prev_state as 4th arg */
		skel->rodata->has_prev_state = true;
	}
}

int off_cpu_prepare(struct evlist *evlist, struct target *target,
		    struct record_opts *opts)
{
	int err, fd, i;
	int ncpus = 1, ntasks = 1, ncgrps = 1;
	struct strlist *pid_slist = NULL;
	struct str_node *pos;

	if (off_cpu_config(evlist) < 0) {
		pr_err("Failed to config off-cpu BPF event\n");
		return -1;
	}

	skel = off_cpu_bpf__open();
	if (!skel) {
		pr_err("Failed to open off-cpu BPF skeleton\n");
		return -1;
	}

	/* don't need to set cpu filter for system-wide mode */
	if (target->cpu_list) {
		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
	}

	if (target->pid) {
		pid_slist = strlist__new(target->pid, NULL);
		if (!pid_slist) {
			pr_err("Failed to create a strlist for pid\n");
			return -1;
		}

		ntasks = 0;
		strlist__for_each_entry(pos, pid_slist) {
			char *end_ptr;
			int pid = strtol(pos->s, &end_ptr, 10);

			if (pid == INT_MIN || pid == INT_MAX ||
			    (*end_ptr != '\0' && *end_ptr != ','))
				continue;

			ntasks++;
		}

		if (ntasks < MAX_PROC)
			ntasks = MAX_PROC;

		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
	} else if (target__has_task(target)) {
		ntasks = perf_thread_map__nr(evlist->core.threads);
		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
	} else if (target__none(target)) {
		bpf_map__set_max_entries(skel->maps.task_filter, MAX_PROC);
	}

	if (evlist__first(evlist)->cgrp) {
		ncgrps = evlist->core.nr_entries - 1; /* excluding a dummy */
		bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);

		if (!cgroup_is_v2("perf_event"))
			skel->rodata->uses_cgroup_v1 = true;
	}

	if (opts->record_cgroup) {
		skel->rodata->needs_cgroup = true;

		if (!cgroup_is_v2("perf_event"))
			skel->rodata->uses_cgroup_v1 = true;
	}

	set_max_rlimit();
	check_sched_switch_args();

	err = off_cpu_bpf__load(skel);
	if (err) {
		pr_err("Failed to load off-cpu skeleton\n");
		goto out;
	}

	if (target->cpu_list) {
		u32 cpu;
		u8 val = 1;

		skel->bss->has_cpu = 1;
		fd = bpf_map__fd(skel->maps.cpu_filter);

		for (i = 0; i < ncpus; i++) {
			cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, i).cpu;
			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
		}
	}

	if (target->pid) {
		u8 val = 1;

		skel->bss->has_task = 1;
		skel->bss->uses_tgid = 1;
		fd = bpf_map__fd(skel->maps.task_filter);

		strlist__for_each_entry(pos, pid_slist) {
			char *end_ptr;
			u32 tgid;
			int pid = strtol(pos->s, &end_ptr, 10);

			if (pid == INT_MIN || pid == INT_MAX ||
			    (*end_ptr != '\0' && *end_ptr != ','))
				continue;

			tgid = pid;
			bpf_map_update_elem(fd, &tgid, &val, BPF_ANY);
		}
	} else if (target__has_task(target)) {
		u32 pid;
		u8 val = 1;

		skel->bss->has_task = 1;
		fd = bpf_map__fd(skel->maps.task_filter);

		for (i = 0; i < ntasks; i++) {
			pid = perf_thread_map__pid(evlist->core.threads, i);
			bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
		}
	}

	if (evlist__first(evlist)->cgrp) {
		struct evsel *evsel;
		u8 val = 1;

		skel->bss->has_cgroup = 1;
		fd = bpf_map__fd(skel->maps.cgroup_filter);

		evlist__for_each_entry(evlist, evsel) {
			struct cgroup *cgrp = evsel->cgrp;

			if (cgrp == NULL)
				continue;

			if (!cgrp->id && read_cgroup_id(cgrp) < 0) {
				pr_err("Failed to read cgroup id of %s\n",
				       cgrp->name);
				goto out;
			}

			bpf_map_update_elem(fd, &cgrp->id, &val, BPF_ANY);
		}
	}

	err = off_cpu_bpf__attach(skel);
	if (err) {
		pr_err("Failed to attach off-cpu BPF skeleton\n");
		goto out;
	}

	if (perf_hooks__set_hook("record_start", off_cpu_start, evlist) ||
	    perf_hooks__set_hook("record_end", off_cpu_finish, evlist)) {
		pr_err("Failed to attach off-cpu skeleton\n");
		goto out;
	}

	return 0;

out:
	off_cpu_bpf__destroy(skel);
	return -1;
}

int off_cpu_write(struct perf_session *session)
{
	int bytes = 0, size;
	int fd, stack;
	u64 sample_type, val, sid = 0;
	struct evsel *evsel;
	struct perf_data_file *file = &session->data->file;
	struct off_cpu_key prev, key;
	union off_cpu_data data = {
		.hdr = {
			.type = PERF_RECORD_SAMPLE,
			.misc = PERF_RECORD_MISC_USER,
		},
	};
	u64 tstamp = OFF_CPU_TIMESTAMP;

	skel->bss->enabled = 0;

	evsel = evlist__find_evsel_by_str(session->evlist, OFFCPU_EVENT);
	if (evsel == NULL) {
		pr_err("%s evsel not found\n", OFFCPU_EVENT);
		return 0;
	}

	sample_type = evsel->core.attr.sample_type;

	if (sample_type & ~OFFCPU_SAMPLE_TYPES) {
		pr_err("not supported sample type: %llx\n",
		       (unsigned long long)sample_type);
		return -1;
	}

	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) {
		if (evsel->core.id)
			sid = evsel->core.id[0];
	}

	fd = bpf_map__fd(skel->maps.off_cpu);
	stack = bpf_map__fd(skel->maps.stacks);
	memset(&prev, 0, sizeof(prev));

	while (!bpf_map_get_next_key(fd, &prev, &key)) {
		int n = 1;  /* start from perf_event_header */
		int ip_pos = -1;

		bpf_map_lookup_elem(fd, &key, &val);

		if (sample_type & PERF_SAMPLE_IDENTIFIER)
			data.array[n++] = sid;
		if (sample_type & PERF_SAMPLE_IP) {
			ip_pos = n;
			data.array[n++] = 0;  /* will be updated */
		}
		if (sample_type & PERF_SAMPLE_TID)
			data.array[n++] = (u64)key.pid << 32 | key.tgid;
		if (sample_type & PERF_SAMPLE_TIME)
			data.array[n++] = tstamp;
		if (sample_type & PERF_SAMPLE_ID)
			data.array[n++] = sid;
		if (sample_type & PERF_SAMPLE_CPU)
			data.array[n++] = 0;
		if (sample_type & PERF_SAMPLE_PERIOD)
			data.array[n++] = val;
		if (sample_type & PERF_SAMPLE_CALLCHAIN) {
			int len = 0;

			/* data.array[n] is callchain->nr (updated later) */
			data.array[n + 1] = PERF_CONTEXT_USER;
			data.array[n + 2] = 0;

			bpf_map_lookup_elem(stack, &key.stack_id, &data.array[n + 2]);
			while (data.array[n + 2 + len])
				len++;

			/* update length of callchain */
			data.array[n] = len + 1;

			/* update sample ip with the first callchain entry */
			if (ip_pos >= 0)
				data.array[ip_pos] = data.array[n + 2];

			/* calculate sample callchain data array length */
			n += len + 2;
		}
		if (sample_type & PERF_SAMPLE_CGROUP)
			data.array[n++] = key.cgroup_id;

		size = n * sizeof(u64);
		data.hdr.size = size;
		bytes += size;

		if (perf_data_file__write(file, &data, size) < 0) {
			pr_err("failed to write perf data, error: %m\n");
			return bytes;
		}

		prev = key;
		/* increase dummy timestamp to sort later samples */
		tstamp++;
	}
	return bytes;
}