summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/bpf_iter.c
blob: b6715964b6856199a37e9c2bcb9223700603b555 (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
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2020 Facebook */

#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/filter.h>
#include <linux/bpf.h>

struct bpf_iter_target_info {
	struct list_head list;
	const struct bpf_iter_reg *reg_info;
	u32 btf_id;	/* cached value */
};

struct bpf_iter_link {
	struct bpf_link link;
	struct bpf_iter_aux_info aux;
	struct bpf_iter_target_info *tinfo;
};

struct bpf_iter_priv_data {
	struct bpf_iter_target_info *tinfo;
	const struct bpf_iter_seq_info *seq_info;
	struct bpf_prog *prog;
	u64 session_id;
	u64 seq_num;
	bool done_stop;
	u8 target_private[] __aligned(8);
};

static struct list_head targets = LIST_HEAD_INIT(targets);
static DEFINE_MUTEX(targets_mutex);

/* protect bpf_iter_link changes */
static DEFINE_MUTEX(link_mutex);

/* incremented on every opened seq_file */
static atomic64_t session_id;

static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
			    const struct bpf_iter_seq_info *seq_info);

static void bpf_iter_inc_seq_num(struct seq_file *seq)
{
	struct bpf_iter_priv_data *iter_priv;

	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
				 target_private);
	iter_priv->seq_num++;
}

static void bpf_iter_dec_seq_num(struct seq_file *seq)
{
	struct bpf_iter_priv_data *iter_priv;

	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
				 target_private);
	iter_priv->seq_num--;
}

static void bpf_iter_done_stop(struct seq_file *seq)
{
	struct bpf_iter_priv_data *iter_priv;

	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
				 target_private);
	iter_priv->done_stop = true;
}

/* bpf_seq_read, a customized and simpler version for bpf iterator.
 * no_llseek is assumed for this file.
 * The following are differences from seq_read():
 *  . fixed buffer size (PAGE_SIZE)
 *  . assuming no_llseek
 *  . stop() may call bpf program, handling potential overflow there
 */
static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
			    loff_t *ppos)
{
	struct seq_file *seq = file->private_data;
	size_t n, offs, copied = 0;
	int err = 0;
	void *p;

	mutex_lock(&seq->lock);

	if (!seq->buf) {
		seq->size = PAGE_SIZE;
		seq->buf = kmalloc(seq->size, GFP_KERNEL);
		if (!seq->buf) {
			err = -ENOMEM;
			goto done;
		}
	}

	if (seq->count) {
		n = min(seq->count, size);
		err = copy_to_user(buf, seq->buf + seq->from, n);
		if (err) {
			err = -EFAULT;
			goto done;
		}
		seq->count -= n;
		seq->from += n;
		copied = n;
		goto done;
	}

	seq->from = 0;
	p = seq->op->start(seq, &seq->index);
	if (!p)
		goto stop;
	if (IS_ERR(p)) {
		err = PTR_ERR(p);
		seq->op->stop(seq, p);
		seq->count = 0;
		goto done;
	}

	err = seq->op->show(seq, p);
	if (err > 0) {
		/* object is skipped, decrease seq_num, so next
		 * valid object can reuse the same seq_num.
		 */
		bpf_iter_dec_seq_num(seq);
		seq->count = 0;
	} else if (err < 0 || seq_has_overflowed(seq)) {
		if (!err)
			err = -E2BIG;
		seq->op->stop(seq, p);
		seq->count = 0;
		goto done;
	}

	while (1) {
		loff_t pos = seq->index;

		offs = seq->count;
		p = seq->op->next(seq, p, &seq->index);
		if (pos == seq->index) {
			pr_info_ratelimited("buggy seq_file .next function %ps "
				"did not updated position index\n",
				seq->op->next);
			seq->index++;
		}

		if (IS_ERR_OR_NULL(p))
			break;

		/* got a valid next object, increase seq_num */
		bpf_iter_inc_seq_num(seq);

		if (seq->count >= size)
			break;

		err = seq->op->show(seq, p);
		if (err > 0) {
			bpf_iter_dec_seq_num(seq);
			seq->count = offs;
		} else if (err < 0 || seq_has_overflowed(seq)) {
			seq->count = offs;
			if (offs == 0) {
				if (!err)
					err = -E2BIG;
				seq->op->stop(seq, p);
				goto done;
			}
			break;
		}
	}
stop:
	offs = seq->count;
	/* bpf program called if !p */
	seq->op->stop(seq, p);
	if (!p) {
		if (!seq_has_overflowed(seq)) {
			bpf_iter_done_stop(seq);
		} else {
			seq->count = offs;
			if (offs == 0) {
				err = -E2BIG;
				goto done;
			}
		}
	}

	n = min(seq->count, size);
	err = copy_to_user(buf, seq->buf, n);
	if (err) {
		err = -EFAULT;
		goto done;
	}
	copied = n;
	seq->count -= n;
	seq->from = n;
done:
	if (!copied)
		copied = err;
	else
		*ppos += copied;
	mutex_unlock(&seq->lock);
	return copied;
}

static const struct bpf_iter_seq_info *
__get_seq_info(struct bpf_iter_link *link)
{
	const struct bpf_iter_seq_info *seq_info;

	if (link->aux.map) {
		seq_info = link->aux.map->ops->iter_seq_info;
		if (seq_info)
			return seq_info;
	}

	return link->tinfo->reg_info->seq_info;
}

static int iter_open(struct inode *inode, struct file *file)
{
	struct bpf_iter_link *link = inode->i_private;

	return prepare_seq_file(file, link, __get_seq_info(link));
}

static int iter_release(struct inode *inode, struct file *file)
{
	struct bpf_iter_priv_data *iter_priv;
	struct seq_file *seq;

	seq = file->private_data;
	if (!seq)
		return 0;

	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
				 target_private);

	if (iter_priv->seq_info->fini_seq_private)
		iter_priv->seq_info->fini_seq_private(seq->private);

	bpf_prog_put(iter_priv->prog);
	seq->private = iter_priv;

	return seq_release_private(inode, file);
}

const struct file_operations bpf_iter_fops = {
	.open		= iter_open,
	.llseek		= no_llseek,
	.read		= bpf_seq_read,
	.release	= iter_release,
};

/* The argument reg_info will be cached in bpf_iter_target_info.
 * The common practice is to declare target reg_info as
 * a const static variable and passed as an argument to
 * bpf_iter_reg_target().
 */
int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info)
{
	struct bpf_iter_target_info *tinfo;

	tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
	if (!tinfo)
		return -ENOMEM;

	tinfo->reg_info = reg_info;
	INIT_LIST_HEAD(&tinfo->list);

	mutex_lock(&targets_mutex);
	list_add(&tinfo->list, &targets);
	mutex_unlock(&targets_mutex);

	return 0;
}

void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info)
{
	struct bpf_iter_target_info *tinfo;
	bool found = false;

	mutex_lock(&targets_mutex);
	list_for_each_entry(tinfo, &targets, list) {
		if (reg_info == tinfo->reg_info) {
			list_del(&tinfo->list);
			kfree(tinfo);
			found = true;
			break;
		}
	}
	mutex_unlock(&targets_mutex);

	WARN_ON(found == false);
}

static void cache_btf_id(struct bpf_iter_target_info *tinfo,
			 struct bpf_prog *prog)
{
	tinfo->btf_id = prog->aux->attach_btf_id;
}

bool bpf_iter_prog_supported(struct bpf_prog *prog)
{
	const char *attach_fname = prog->aux->attach_func_name;
	u32 prog_btf_id = prog->aux->attach_btf_id;
	const char *prefix = BPF_ITER_FUNC_PREFIX;
	struct bpf_iter_target_info *tinfo;
	int prefix_len = strlen(prefix);
	bool supported = false;

	if (strncmp(attach_fname, prefix, prefix_len))
		return false;

	mutex_lock(&targets_mutex);
	list_for_each_entry(tinfo, &targets, list) {
		if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) {
			supported = true;
			break;
		}
		if (!strcmp(attach_fname + prefix_len, tinfo->reg_info->target)) {
			cache_btf_id(tinfo, prog);
			supported = true;
			break;
		}
	}
	mutex_unlock(&targets_mutex);

	if (supported) {
		prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size;
		prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info;
	}

	return supported;
}

static void bpf_iter_link_release(struct bpf_link *link)
{
	struct bpf_iter_link *iter_link =
		container_of(link, struct bpf_iter_link, link);

	if (iter_link->tinfo->reg_info->detach_target)
		iter_link->tinfo->reg_info->detach_target(&iter_link->aux);
}

static void bpf_iter_link_dealloc(struct bpf_link *link)
{
	struct bpf_iter_link *iter_link =
		container_of(link, struct bpf_iter_link, link);

	kfree(iter_link);
}

static int bpf_iter_link_replace(struct bpf_link *link,
				 struct bpf_prog *new_prog,
				 struct bpf_prog *old_prog)
{
	int ret = 0;

	mutex_lock(&link_mutex);
	if (old_prog && link->prog != old_prog) {
		ret = -EPERM;
		goto out_unlock;
	}

	if (link->prog->type != new_prog->type ||
	    link->prog->expected_attach_type != new_prog->expected_attach_type ||
	    link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) {
		ret = -EINVAL;
		goto out_unlock;
	}

	old_prog = xchg(&link->prog, new_prog);
	bpf_prog_put(old_prog);

out_unlock:
	mutex_unlock(&link_mutex);
	return ret;
}

static const struct bpf_link_ops bpf_iter_link_lops = {
	.release = bpf_iter_link_release,
	.dealloc = bpf_iter_link_dealloc,
	.update_prog = bpf_iter_link_replace,
};

bool bpf_link_is_iter(struct bpf_link *link)
{
	return link->ops == &bpf_iter_link_lops;
}

int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
	union bpf_iter_link_info __user *ulinfo;
	struct bpf_link_primer link_primer;
	struct bpf_iter_target_info *tinfo;
	union bpf_iter_link_info linfo;
	struct bpf_iter_link *link;
	u32 prog_btf_id, linfo_len;
	bool existed = false;
	int err;

	if (attr->link_create.target_fd || attr->link_create.flags)
		return -EINVAL;

	memset(&linfo, 0, sizeof(union bpf_iter_link_info));

	ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
	linfo_len = attr->link_create.iter_info_len;
	if (!ulinfo ^ !linfo_len)
		return -EINVAL;

	if (ulinfo) {
		err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
					       linfo_len);
		if (err)
			return err;
		linfo_len = min_t(u32, linfo_len, sizeof(linfo));
		if (copy_from_user(&linfo, ulinfo, linfo_len))
			return -EFAULT;
	}

	prog_btf_id = prog->aux->attach_btf_id;
	mutex_lock(&targets_mutex);
	list_for_each_entry(tinfo, &targets, list) {
		if (tinfo->btf_id == prog_btf_id) {
			existed = true;
			break;
		}
	}
	mutex_unlock(&targets_mutex);
	if (!existed)
		return -ENOENT;

	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
	if (!link)
		return -ENOMEM;

	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);
	link->tinfo = tinfo;

	err  = bpf_link_prime(&link->link, &link_primer);
	if (err) {
		kfree(link);
		return err;
	}

	if (tinfo->reg_info->attach_target) {
		err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux);
		if (err) {
			bpf_link_cleanup(&link_primer);
			return err;
		}
	}

	return bpf_link_settle(&link_primer);
}

static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
			  struct bpf_iter_target_info *tinfo,
			  const struct bpf_iter_seq_info *seq_info,
			  struct bpf_prog *prog)
{
	priv_data->tinfo = tinfo;
	priv_data->seq_info = seq_info;
	priv_data->prog = prog;
	priv_data->session_id = atomic64_inc_return(&session_id);
	priv_data->seq_num = 0;
	priv_data->done_stop = false;
}

static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
			    const struct bpf_iter_seq_info *seq_info)
{
	struct bpf_iter_priv_data *priv_data;
	struct bpf_iter_target_info *tinfo;
	struct bpf_prog *prog;
	u32 total_priv_dsize;
	struct seq_file *seq;
	int err = 0;

	mutex_lock(&link_mutex);
	prog = link->link.prog;
	bpf_prog_inc(prog);
	mutex_unlock(&link_mutex);

	tinfo = link->tinfo;
	total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) +
			   seq_info->seq_priv_size;
	priv_data = __seq_open_private(file, seq_info->seq_ops,
				       total_priv_dsize);
	if (!priv_data) {
		err = -ENOMEM;
		goto release_prog;
	}

	if (seq_info->init_seq_private) {
		err = seq_info->init_seq_private(priv_data->target_private, &link->aux);
		if (err)
			goto release_seq_file;
	}

	init_seq_meta(priv_data, tinfo, seq_info, prog);
	seq = file->private_data;
	seq->private = priv_data->target_private;

	return 0;

release_seq_file:
	seq_release_private(file->f_inode, file);
	file->private_data = NULL;
release_prog:
	bpf_prog_put(prog);
	return err;
}

int bpf_iter_new_fd(struct bpf_link *link)
{
	struct bpf_iter_link *iter_link;
	struct file *file;
	unsigned int flags;
	int err, fd;

	if (link->ops != &bpf_iter_link_lops)
		return -EINVAL;

	flags = O_RDONLY | O_CLOEXEC;
	fd = get_unused_fd_flags(flags);
	if (fd < 0)
		return fd;

	file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags);
	if (IS_ERR(file)) {
		err = PTR_ERR(file);
		goto free_fd;
	}

	iter_link = container_of(link, struct bpf_iter_link, link);
	err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link));
	if (err)
		goto free_file;

	fd_install(fd, file);
	return fd;

free_file:
	fput(file);
free_fd:
	put_unused_fd(fd);
	return err;
}

struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)
{
	struct bpf_iter_priv_data *iter_priv;
	struct seq_file *seq;
	void *seq_priv;

	seq = meta->seq;
	if (seq->file->f_op != &bpf_iter_fops)
		return NULL;

	seq_priv = seq->private;
	iter_priv = container_of(seq_priv, struct bpf_iter_priv_data,
				 target_private);

	if (in_stop && iter_priv->done_stop)
		return NULL;

	meta->session_id = iter_priv->session_id;
	meta->seq_num = iter_priv->seq_num;

	return iter_priv->prog;
}

int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
{
	int ret;

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

	/* bpf program can only return 0 or 1:
	 *  0 : okay
	 *  1 : retry the same object
	 * The bpf_iter_run_prog() return value
	 * will be seq_ops->show() return value.
	 */
	return ret == 0 ? 0 : -EAGAIN;
}