summaryrefslogtreecommitdiff
path: root/kernel/trace/bpf_trace.c
blob: e7af6cb9d5cf580b402e8211e493865f96929e9c (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
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
 *
 * 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 <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include "trace.h"

/**
 * trace_call_bpf - invoke BPF program
 * @prog: BPF program
 * @ctx: opaque context pointer
 *
 * kprobe handlers execute BPF programs via this helper.
 * Can be used from static tracepoints in the future.
 *
 * Return: BPF programs always return an integer which is interpreted by
 * kprobe handler as:
 * 0 - return from kprobe (event is filtered out)
 * 1 - store kprobe event into ring buffer
 * Other values are reserved and currently alias to 1
 */
unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
{
	unsigned int ret;

	if (in_nmi()) /* not supported yet */
		return 1;

	preempt_disable();

	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
		/*
		 * since some bpf program is already running on this cpu,
		 * don't call into another bpf program (same or different)
		 * and don't send kprobe event into ring-buffer,
		 * so return zero here
		 */
		ret = 0;
		goto out;
	}

	rcu_read_lock();
	ret = BPF_PROG_RUN(prog, ctx);
	rcu_read_unlock();

 out:
	__this_cpu_dec(bpf_prog_active);
	preempt_enable();

	return ret;
}
EXPORT_SYMBOL_GPL(trace_call_bpf);

static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
	void *dst = (void *) (long) r1;
	int ret, size = (int) r2;
	void *unsafe_ptr = (void *) (long) r3;

	ret = probe_kernel_read(dst, unsafe_ptr, size);
	if (unlikely(ret < 0))
		memset(dst, 0, size);

	return ret;
}

static const struct bpf_func_proto bpf_probe_read_proto = {
	.func		= bpf_probe_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_RAW_STACK,
	.arg2_type	= ARG_CONST_STACK_SIZE,
	.arg3_type	= ARG_ANYTHING,
};

/*
 * limited trace_printk()
 * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed
 */
static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
{
	char *fmt = (char *) (long) r1;
	bool str_seen = false;
	int mod[3] = {};
	int fmt_cnt = 0;
	u64 unsafe_addr;
	char buf[64];
	int i;

	/*
	 * bpf_check()->check_func_arg()->check_stack_boundary()
	 * guarantees that fmt points to bpf program stack,
	 * fmt_size bytes of it were initialized and fmt_size > 0
	 */
	if (fmt[--fmt_size] != 0)
		return -EINVAL;

	/* check format string for allowed specifiers */
	for (i = 0; i < fmt_size; i++) {
		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i]))
			return -EINVAL;

		if (fmt[i] != '%')
			continue;

		if (fmt_cnt >= 3)
			return -EINVAL;

		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
		i++;
		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		} else if (fmt[i] == 'p' || fmt[i] == 's') {
			mod[fmt_cnt]++;
			i++;
			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
				return -EINVAL;
			fmt_cnt++;
			if (fmt[i - 1] == 's') {
				if (str_seen)
					/* allow only one '%s' per fmt string */
					return -EINVAL;
				str_seen = true;

				switch (fmt_cnt) {
				case 1:
					unsafe_addr = r3;
					r3 = (long) buf;
					break;
				case 2:
					unsafe_addr = r4;
					r4 = (long) buf;
					break;
				case 3:
					unsafe_addr = r5;
					r5 = (long) buf;
					break;
				}
				buf[0] = 0;
				strncpy_from_unsafe(buf,
						    (void *) (long) unsafe_addr,
						    sizeof(buf));
			}
			continue;
		}

		if (fmt[i] == 'l') {
			mod[fmt_cnt]++;
			i++;
		}

		if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x')
			return -EINVAL;
		fmt_cnt++;
	}

	return __trace_printk(1/* fake ip will not be printed */, fmt,
			      mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3,
			      mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4,
			      mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5);
}

static const struct bpf_func_proto bpf_trace_printk_proto = {
	.func		= bpf_trace_printk,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_STACK,
	.arg2_type	= ARG_CONST_STACK_SIZE,
};

const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
{
	/*
	 * this program might be calling bpf_trace_printk,
	 * so allocate per-cpu printk buffers
	 */
	trace_printk_init_buffers();

	return &bpf_trace_printk_proto;
}

static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
{
	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	struct perf_event *event;
	struct file *file;

	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	file = READ_ONCE(array->ptrs[index]);
	if (unlikely(!file))
		return -ENOENT;

	event = file->private_data;

	/* make sure event is local and doesn't have pmu::count */
	if (event->oncpu != smp_processor_id() ||
	    event->pmu->count)
		return -EINVAL;

	/*
	 * we don't know if the function is run successfully by the
	 * return value. It can be judged in other places, such as
	 * eBPF programs.
	 */
	return perf_event_read_local(event);
}

static const struct bpf_func_proto bpf_perf_event_read_proto = {
	.func		= bpf_perf_event_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_CONST_MAP_PTR,
	.arg2_type	= ARG_ANYTHING,
};

static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
{
	struct pt_regs *regs = (struct pt_regs *) (long) r1;
	struct bpf_map *map = (struct bpf_map *) (long) r2;
	struct bpf_array *array = container_of(map, struct bpf_array, map);
	u64 index = flags & BPF_F_INDEX_MASK;
	void *data = (void *) (long) r4;
	struct perf_sample_data sample_data;
	struct perf_event *event;
	struct file *file;
	struct perf_raw_record raw = {
		.size = size,
		.data = data,
	};

	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
		return -EINVAL;
	if (index == BPF_F_CURRENT_CPU)
		index = raw_smp_processor_id();
	if (unlikely(index >= array->map.max_entries))
		return -E2BIG;

	file = READ_ONCE(array->ptrs[index]);
	if (unlikely(!file))
		return -ENOENT;

	event = file->private_data;

	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
		return -EINVAL;

	if (unlikely(event->oncpu != smp_processor_id()))
		return -EOPNOTSUPP;

	perf_sample_data_init(&sample_data, 0, 0);
	sample_data.raw = &raw;
	perf_event_output(event, &sample_data, regs);
	return 0;
}

static const struct bpf_func_proto bpf_perf_event_output_proto = {
	.func		= bpf_perf_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_STACK,
	.arg5_type	= ARG_CONST_STACK_SIZE,
};

static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);

static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
{
	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);

	perf_fetch_caller_regs(regs);

	return bpf_perf_event_output((long)regs, r2, flags, r4, size);
}

static const struct bpf_func_proto bpf_event_output_proto = {
	.func		= bpf_event_output,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_STACK,
	.arg5_type	= ARG_CONST_STACK_SIZE,
};

const struct bpf_func_proto *bpf_get_event_output_proto(void)
{
	return &bpf_event_output_proto;
}

static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_probe_read:
		return &bpf_probe_read_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	case BPF_FUNC_tail_call:
		return &bpf_tail_call_proto;
	case BPF_FUNC_get_current_pid_tgid:
		return &bpf_get_current_pid_tgid_proto;
	case BPF_FUNC_get_current_uid_gid:
		return &bpf_get_current_uid_gid_proto;
	case BPF_FUNC_get_current_comm:
		return &bpf_get_current_comm_proto;
	case BPF_FUNC_trace_printk:
		return bpf_get_trace_printk_proto();
	case BPF_FUNC_get_smp_processor_id:
		return &bpf_get_smp_processor_id_proto;
	case BPF_FUNC_perf_event_read:
		return &bpf_perf_event_read_proto;
	default:
		return NULL;
	}
}

static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto;
	default:
		return tracing_func_proto(func_id);
	}
}

/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
					enum bpf_reg_type *reg_type)
{
	/* check bounds */
	if (off < 0 || off >= sizeof(struct pt_regs))
		return false;

	/* only read is allowed */
	if (type != BPF_READ)
		return false;

	/* disallow misaligned access */
	if (off % size != 0)
		return false;

	return true;
}

static const struct bpf_verifier_ops kprobe_prog_ops = {
	.get_func_proto  = kprobe_prog_func_proto,
	.is_valid_access = kprobe_prog_is_valid_access,
};

static struct bpf_prog_type_list kprobe_tl = {
	.ops	= &kprobe_prog_ops,
	.type	= BPF_PROG_TYPE_KPROBE,
};

static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
{
	/*
	 * r1 points to perf tracepoint buffer where first 8 bytes are hidden
	 * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
	 * from there and call the same bpf_perf_event_output() helper
	 */
	u64 ctx = *(long *)(uintptr_t)r1;

	return bpf_perf_event_output(ctx, r2, index, r4, size);
}

static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
	.func		= bpf_perf_event_output_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
	.arg4_type	= ARG_PTR_TO_STACK,
	.arg5_type	= ARG_CONST_STACK_SIZE,
};

static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
	u64 ctx = *(long *)(uintptr_t)r1;

	return bpf_get_stackid(ctx, r2, r3, r4, r5);
}

static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
	.func		= bpf_get_stackid_tp,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_perf_event_output:
		return &bpf_perf_event_output_proto_tp;
	case BPF_FUNC_get_stackid:
		return &bpf_get_stackid_proto_tp;
	default:
		return tracing_func_proto(func_id);
	}
}

static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
				    enum bpf_reg_type *reg_type)
{
	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
		return false;
	if (type != BPF_READ)
		return false;
	if (off % size != 0)
		return false;
	return true;
}

static const struct bpf_verifier_ops tracepoint_prog_ops = {
	.get_func_proto  = tp_prog_func_proto,
	.is_valid_access = tp_prog_is_valid_access,
};

static struct bpf_prog_type_list tracepoint_tl = {
	.ops	= &tracepoint_prog_ops,
	.type	= BPF_PROG_TYPE_TRACEPOINT,
};

static int __init register_kprobe_prog_ops(void)
{
	bpf_register_prog_type(&kprobe_tl);
	bpf_register_prog_type(&tracepoint_tl);
	return 0;
}
late_initcall(register_kprobe_prog_ops);