summaryrefslogtreecommitdiff
path: root/kernel/trace/trace_event_perf.c
blob: e11108f1d19735026e66fe7336650a9c7559501e (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
/*
 * trace event based perf event profiling/tracing
 *
 * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
 * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
 */

#include <linux/module.h>
#include <linux/kprobes.h>
#include "trace.h"

static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];

/*
 * Force it to be aligned to unsigned long to avoid misaligned accesses
 * suprises
 */
typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
	perf_trace_t;

/* Count the events in use (per event id, not per instance) */
static int	total_ref_count;

static int perf_trace_event_perm(struct trace_event_call *tp_event,
				 struct perf_event *p_event)
{
	if (tp_event->perf_perm) {
		int ret = tp_event->perf_perm(tp_event, p_event);
		if (ret)
			return ret;
	}

	/*
	 * We checked and allowed to create parent,
	 * allow children without checking.
	 */
	if (p_event->parent)
		return 0;

	/*
	 * It's ok to check current process (owner) permissions in here,
	 * because code below is called only via perf_event_open syscall.
	 */

	/* The ftrace function trace is allowed only for root. */
	if (ftrace_event_is_function(tp_event)) {
		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
			return -EPERM;

		if (!is_sampling_event(p_event))
			return 0;

		/*
		 * We don't allow user space callchains for  function trace
		 * event, due to issues with page faults while tracing page
		 * fault handler and its overall trickiness nature.
		 */
		if (!p_event->attr.exclude_callchain_user)
			return -EINVAL;

		/*
		 * Same reason to disable user stack dump as for user space
		 * callchains above.
		 */
		if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
			return -EINVAL;
	}

	/* No tracing, just counting, so no obvious leak */
	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
		return 0;

	/* Some events are ok to be traced by non-root users... */
	if (p_event->attach_state == PERF_ATTACH_TASK) {
		if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
			return 0;
	}

	/*
	 * ...otherwise raw tracepoint data can be a severe data leak,
	 * only allow root to have these.
	 */
	if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	return 0;
}

static int perf_trace_event_reg(struct trace_event_call *tp_event,
				struct perf_event *p_event)
{
	struct hlist_head __percpu *list;
	int ret = -ENOMEM;
	int cpu;

	p_event->tp_event = tp_event;
	if (tp_event->perf_refcount++ > 0)
		return 0;

	list = alloc_percpu(struct hlist_head);
	if (!list)
		goto fail;

	for_each_possible_cpu(cpu)
		INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));

	tp_event->perf_events = list;

	if (!total_ref_count) {
		char __percpu *buf;
		int i;

		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
			buf = (char __percpu *)alloc_percpu(perf_trace_t);
			if (!buf)
				goto fail;

			perf_trace_buf[i] = buf;
		}
	}

	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
	if (ret)
		goto fail;

	total_ref_count++;
	return 0;

fail:
	if (!total_ref_count) {
		int i;

		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
			free_percpu(perf_trace_buf[i]);
			perf_trace_buf[i] = NULL;
		}
	}

	if (!--tp_event->perf_refcount) {
		free_percpu(tp_event->perf_events);
		tp_event->perf_events = NULL;
	}

	return ret;
}

static void perf_trace_event_unreg(struct perf_event *p_event)
{
	struct trace_event_call *tp_event = p_event->tp_event;
	int i;

	if (--tp_event->perf_refcount > 0)
		goto out;

	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);

	/*
	 * Ensure our callback won't be called anymore. The buffers
	 * will be freed after that.
	 */
	tracepoint_synchronize_unregister();

	free_percpu(tp_event->perf_events);
	tp_event->perf_events = NULL;

	if (!--total_ref_count) {
		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
			free_percpu(perf_trace_buf[i]);
			perf_trace_buf[i] = NULL;
		}
	}
out:
	module_put(tp_event->mod);
}

static int perf_trace_event_open(struct perf_event *p_event)
{
	struct trace_event_call *tp_event = p_event->tp_event;
	return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
}

static void perf_trace_event_close(struct perf_event *p_event)
{
	struct trace_event_call *tp_event = p_event->tp_event;
	tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
}

static int perf_trace_event_init(struct trace_event_call *tp_event,
				 struct perf_event *p_event)
{
	int ret;

	ret = perf_trace_event_perm(tp_event, p_event);
	if (ret)
		return ret;

	ret = perf_trace_event_reg(tp_event, p_event);
	if (ret)
		return ret;

	ret = perf_trace_event_open(p_event);
	if (ret) {
		perf_trace_event_unreg(p_event);
		return ret;
	}

	return 0;
}

int perf_trace_init(struct perf_event *p_event)
{
	struct trace_event_call *tp_event;
	u64 event_id = p_event->attr.config;
	int ret = -EINVAL;

	mutex_lock(&event_mutex);
	list_for_each_entry(tp_event, &ftrace_events, list) {
		if (tp_event->event.type == event_id &&
		    tp_event->class && tp_event->class->reg &&
		    try_module_get(tp_event->mod)) {
			ret = perf_trace_event_init(tp_event, p_event);
			if (ret)
				module_put(tp_event->mod);
			break;
		}
	}
	mutex_unlock(&event_mutex);

	return ret;
}

void perf_trace_destroy(struct perf_event *p_event)
{
	mutex_lock(&event_mutex);
	perf_trace_event_close(p_event);
	perf_trace_event_unreg(p_event);
	mutex_unlock(&event_mutex);
}

int perf_trace_add(struct perf_event *p_event, int flags)
{
	struct trace_event_call *tp_event = p_event->tp_event;
	struct hlist_head __percpu *pcpu_list;
	struct hlist_head *list;

	pcpu_list = tp_event->perf_events;
	if (WARN_ON_ONCE(!pcpu_list))
		return -EINVAL;

	if (!(flags & PERF_EF_START))
		p_event->hw.state = PERF_HES_STOPPED;

	list = this_cpu_ptr(pcpu_list);
	hlist_add_head_rcu(&p_event->hlist_entry, list);

	return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
}

void perf_trace_del(struct perf_event *p_event, int flags)
{
	struct trace_event_call *tp_event = p_event->tp_event;
	hlist_del_rcu(&p_event->hlist_entry);
	tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
}

void *perf_trace_buf_prepare(int size, unsigned short type,
			     struct pt_regs **regs, int *rctxp)
{
	struct trace_entry *entry;
	unsigned long flags;
	char *raw_data;
	int pc;

	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));

	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
			"perf buffer not large enough"))
		return NULL;

	pc = preempt_count();

	*rctxp = perf_swevent_get_recursion_context();
	if (*rctxp < 0)
		return NULL;

	if (regs)
		*regs = this_cpu_ptr(&__perf_regs[*rctxp]);
	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);

	/* zero the dead bytes from align to not leak stack to user */
	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));

	entry = (struct trace_entry *)raw_data;
	local_save_flags(flags);
	tracing_generic_entry_update(entry, flags, pc);
	entry->type = type;

	return raw_data;
}
EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
NOKPROBE_SYMBOL(perf_trace_buf_prepare);

#ifdef CONFIG_FUNCTION_TRACER
static void
perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
{
	struct ftrace_entry *entry;
	struct hlist_head *head;
	struct pt_regs regs;
	int rctx;

	head = this_cpu_ptr(event_function.perf_events);
	if (hlist_empty(head))
		return;

#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
		    sizeof(u64)) - sizeof(u32))

	BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);

	perf_fetch_caller_regs(&regs);

	entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
	if (!entry)
		return;

	entry->ip = ip;
	entry->parent_ip = parent_ip;
	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
			      1, &regs, head, NULL);

#undef ENTRY_SIZE
}

static int perf_ftrace_function_register(struct perf_event *event)
{
	struct ftrace_ops *ops = &event->ftrace_ops;

	ops->flags |= FTRACE_OPS_FL_PER_CPU | FTRACE_OPS_FL_RCU;
	ops->func = perf_ftrace_function_call;
	return register_ftrace_function(ops);
}

static int perf_ftrace_function_unregister(struct perf_event *event)
{
	struct ftrace_ops *ops = &event->ftrace_ops;
	int ret = unregister_ftrace_function(ops);
	ftrace_free_filter(ops);
	return ret;
}

static void perf_ftrace_function_enable(struct perf_event *event)
{
	ftrace_function_local_enable(&event->ftrace_ops);
}

static void perf_ftrace_function_disable(struct perf_event *event)
{
	ftrace_function_local_disable(&event->ftrace_ops);
}

int perf_ftrace_event_register(struct trace_event_call *call,
			       enum trace_reg type, void *data)
{
	switch (type) {
	case TRACE_REG_REGISTER:
	case TRACE_REG_UNREGISTER:
		break;
	case TRACE_REG_PERF_REGISTER:
	case TRACE_REG_PERF_UNREGISTER:
		return 0;
	case TRACE_REG_PERF_OPEN:
		return perf_ftrace_function_register(data);
	case TRACE_REG_PERF_CLOSE:
		return perf_ftrace_function_unregister(data);
	case TRACE_REG_PERF_ADD:
		perf_ftrace_function_enable(data);
		return 0;
	case TRACE_REG_PERF_DEL:
		perf_ftrace_function_disable(data);
		return 0;
	}

	return -EINVAL;
}
#endif /* CONFIG_FUNCTION_TRACER */