summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/bpf_lock_contention.c
blob: 72cf811149829ed368256c2b6eb61efb82fadaed (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
// SPDX-License-Identifier: GPL-2.0
#include "util/debug.h"
#include "util/evlist.h"
#include "util/machine.h"
#include "util/map.h"
#include "util/symbol.h"
#include "util/target.h"
#include "util/thread.h"
#include "util/thread_map.h"
#include "util/lock-contention.h"
#include <linux/zalloc.h>
#include <linux/string.h>
#include <bpf/bpf.h>

#include "bpf_skel/lock_contention.skel.h"
#include "bpf_skel/lock_data.h"

static struct lock_contention_bpf *skel;

int lock_contention_prepare(struct lock_contention *con)
{
	int i, fd;
	int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1;
	struct evlist *evlist = con->evlist;
	struct target *target = con->target;

	skel = lock_contention_bpf__open();
	if (!skel) {
		pr_err("Failed to open lock-contention BPF skeleton\n");
		return -1;
	}

	bpf_map__set_value_size(skel->maps.stacks, con->max_stack * sizeof(u64));
	bpf_map__set_max_entries(skel->maps.lock_stat, con->map_nr_entries);
	bpf_map__set_max_entries(skel->maps.tstamp, con->map_nr_entries);

	if (con->aggr_mode == LOCK_AGGR_TASK)
		bpf_map__set_max_entries(skel->maps.task_data, con->map_nr_entries);
	else
		bpf_map__set_max_entries(skel->maps.task_data, 1);

	if (con->save_callstack)
		bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries);
	else
		bpf_map__set_max_entries(skel->maps.stacks, 1);

	if (target__has_cpu(target))
		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
	if (target__has_task(target))
		ntasks = perf_thread_map__nr(evlist->core.threads);
	if (con->filters->nr_types)
		ntypes = con->filters->nr_types;

	/* resolve lock name filters to addr */
	if (con->filters->nr_syms) {
		struct symbol *sym;
		struct map *kmap;
		unsigned long *addrs;

		for (i = 0; i < con->filters->nr_syms; i++) {
			sym = machine__find_kernel_symbol_by_name(con->machine,
								  con->filters->syms[i],
								  &kmap);
			if (sym == NULL) {
				pr_warning("ignore unknown symbol: %s\n",
					   con->filters->syms[i]);
				continue;
			}

			addrs = realloc(con->filters->addrs,
					(con->filters->nr_addrs + 1) * sizeof(*addrs));
			if (addrs == NULL) {
				pr_warning("memory allocation failure\n");
				continue;
			}

			addrs[con->filters->nr_addrs++] = kmap->unmap_ip(kmap, sym->start);
			con->filters->addrs = addrs;
		}
		naddrs = con->filters->nr_addrs;
	}

	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
	bpf_map__set_max_entries(skel->maps.addr_filter, naddrs);

	if (lock_contention_bpf__load(skel) < 0) {
		pr_err("Failed to load lock-contention BPF skeleton\n");
		return -1;
	}

	if (target__has_cpu(target)) {
		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__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 (target__none(target) && evlist->workload.pid > 0) {
		u32 pid = evlist->workload.pid;
		u8 val = 1;

		skel->bss->has_task = 1;
		fd = bpf_map__fd(skel->maps.task_filter);
		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
	}

	if (con->filters->nr_types) {
		u8 val = 1;

		skel->bss->has_type = 1;
		fd = bpf_map__fd(skel->maps.type_filter);

		for (i = 0; i < con->filters->nr_types; i++)
			bpf_map_update_elem(fd, &con->filters->types[i], &val, BPF_ANY);
	}

	if (con->filters->nr_addrs) {
		u8 val = 1;

		skel->bss->has_addr = 1;
		fd = bpf_map__fd(skel->maps.addr_filter);

		for (i = 0; i < con->filters->nr_addrs; i++)
			bpf_map_update_elem(fd, &con->filters->addrs[i], &val, BPF_ANY);
	}

	/* these don't work well if in the rodata section */
	skel->bss->stack_skip = con->stack_skip;
	skel->bss->aggr_mode = con->aggr_mode;
	skel->bss->needs_callstack = con->save_callstack;

	lock_contention_bpf__attach(skel);
	return 0;
}

int lock_contention_start(void)
{
	skel->bss->enabled = 1;
	return 0;
}

int lock_contention_stop(void)
{
	skel->bss->enabled = 0;
	return 0;
}

static const char *lock_contention_get_name(struct lock_contention *con,
					    struct contention_key *key,
					    u64 *stack_trace)
{
	int idx = 0;
	u64 addr;
	const char *name = "";
	static char name_buf[KSYM_NAME_LEN];
	struct symbol *sym;
	struct map *kmap;
	struct machine *machine = con->machine;

	if (con->aggr_mode == LOCK_AGGR_TASK) {
		struct contention_task_data task;
		int pid = key->pid;
		int task_fd = bpf_map__fd(skel->maps.task_data);

		/* do not update idle comm which contains CPU number */
		if (pid) {
			struct thread *t = __machine__findnew_thread(machine, /*pid=*/-1, pid);

			if (t == NULL)
				return name;
			if (!bpf_map_lookup_elem(task_fd, &pid, &task) &&
			    thread__set_comm(t, task.comm, /*timestamp=*/0))
				name = task.comm;
		}
		return name;
	}

	if (con->aggr_mode == LOCK_AGGR_ADDR) {
		sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap);
		if (sym)
			name = sym->name;
		return name;
	}

	/* LOCK_AGGR_CALLER: skip lock internal functions */
	while (machine__is_lock_function(machine, stack_trace[idx]) &&
	       idx < con->max_stack - 1)
		idx++;

	addr = stack_trace[idx];
	sym = machine__find_kernel_symbol(machine, addr, &kmap);

	if (sym) {
		unsigned long offset;

		offset = kmap->map_ip(kmap, addr) - sym->start;

		if (offset == 0)
			return sym->name;

		snprintf(name_buf, sizeof(name_buf), "%s+%#lx", sym->name, offset);
	} else {
		snprintf(name_buf, sizeof(name_buf), "%#lx", (unsigned long)addr);
	}

	return name_buf;
}

int lock_contention_read(struct lock_contention *con)
{
	int fd, stack, err = 0;
	struct contention_key *prev_key, key;
	struct contention_data data = {};
	struct lock_stat *st = NULL;
	struct machine *machine = con->machine;
	u64 *stack_trace;
	size_t stack_size = con->max_stack * sizeof(*stack_trace);

	fd = bpf_map__fd(skel->maps.lock_stat);
	stack = bpf_map__fd(skel->maps.stacks);

	con->lost = skel->bss->lost;

	stack_trace = zalloc(stack_size);
	if (stack_trace == NULL)
		return -1;

	if (con->aggr_mode == LOCK_AGGR_TASK) {
		struct thread *idle = __machine__findnew_thread(machine,
								/*pid=*/0,
								/*tid=*/0);
		thread__set_comm(idle, "swapper", /*timestamp=*/0);
	}

	/* make sure it loads the kernel map */
	map__load(maps__first(machine->kmaps));

	prev_key = NULL;
	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
		s64 ls_key;
		const char *name;

		/* to handle errors in the loop body */
		err = -1;

		bpf_map_lookup_elem(fd, &key, &data);
		if (con->save_callstack) {
			bpf_map_lookup_elem(stack, &key.stack_id, stack_trace);

			if (!match_callstack_filter(machine, stack_trace))
				goto next;
		}

		switch (con->aggr_mode) {
		case LOCK_AGGR_CALLER:
			ls_key = key.stack_id;
			break;
		case LOCK_AGGR_TASK:
			ls_key = key.pid;
			break;
		case LOCK_AGGR_ADDR:
			ls_key = key.lock_addr;
			break;
		default:
			goto next;
		}

		st = lock_stat_find(ls_key);
		if (st != NULL) {
			st->wait_time_total += data.total_time;
			if (st->wait_time_max < data.max_time)
				st->wait_time_max = data.max_time;
			if (st->wait_time_min > data.min_time)
				st->wait_time_min = data.min_time;

			st->nr_contended += data.count;
			if (st->nr_contended)
				st->avg_wait_time = st->wait_time_total / st->nr_contended;
			goto next;
		}

		name = lock_contention_get_name(con, &key, stack_trace);
		st = lock_stat_findnew(ls_key, name, data.flags);
		if (st == NULL)
			break;

		st->nr_contended = data.count;
		st->wait_time_total = data.total_time;
		st->wait_time_max = data.max_time;
		st->wait_time_min = data.min_time;

		if (data.count)
			st->avg_wait_time = data.total_time / data.count;

		if (con->save_callstack) {
			st->callstack = memdup(stack_trace, stack_size);
			if (st->callstack == NULL)
				break;
		}

next:
		prev_key = &key;

		/* we're fine now, reset the error */
		err = 0;
	}

	free(stack_trace);

	return err;
}

int lock_contention_finish(void)
{
	if (skel) {
		skel->bss->enabled = 0;
		lock_contention_bpf__destroy(skel);
	}

	return 0;
}