summaryrefslogtreecommitdiff
path: root/net/bpf/test_run.c
blob: 33e0dc168c16aa24fc7b9c42e17582b316b10472 (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
/* Copyright (c) 2017 Facebook
 *
 * 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/bpf.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/etherdevice.h>
#include <linux/filter.h>
#include <linux/sched/signal.h>
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <net/tcp.h>

#define CREATE_TRACE_POINTS
#include <trace/events/bpf_test_run.h>

static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
			u32 *retval, u32 *time)
{
	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL };
	enum bpf_cgroup_storage_type stype;
	u64 time_start, time_spent = 0;
	int ret = 0;
	u32 i;

	for_each_cgroup_storage_type(stype) {
		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
		if (IS_ERR(storage[stype])) {
			storage[stype] = NULL;
			for_each_cgroup_storage_type(stype)
				bpf_cgroup_storage_free(storage[stype]);
			return -ENOMEM;
		}
	}

	if (!repeat)
		repeat = 1;

	rcu_read_lock();
	preempt_disable();
	time_start = ktime_get_ns();
	for (i = 0; i < repeat; i++) {
		bpf_cgroup_storage_set(storage);
		*retval = BPF_PROG_RUN(prog, ctx);

		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		if (need_resched()) {
			time_spent += ktime_get_ns() - time_start;
			preempt_enable();
			rcu_read_unlock();

			cond_resched();

			rcu_read_lock();
			preempt_disable();
			time_start = ktime_get_ns();
		}
	}
	time_spent += ktime_get_ns() - time_start;
	preempt_enable();
	rcu_read_unlock();

	do_div(time_spent, repeat);
	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;

	for_each_cgroup_storage_type(stype)
		bpf_cgroup_storage_free(storage[stype]);

	return ret;
}

static int bpf_test_finish(const union bpf_attr *kattr,
			   union bpf_attr __user *uattr, const void *data,
			   u32 size, u32 retval, u32 duration)
{
	void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
	int err = -EFAULT;
	u32 copy_size = size;

	/* Clamp copy if the user has provided a size hint, but copy the full
	 * buffer if not to retain old behaviour.
	 */
	if (kattr->test.data_size_out &&
	    copy_size > kattr->test.data_size_out) {
		copy_size = kattr->test.data_size_out;
		err = -ENOSPC;
	}

	if (data_out && copy_to_user(data_out, data, copy_size))
		goto out;
	if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
		goto out;
	if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
		goto out;
	if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
		goto out;
	if (err != -ENOSPC)
		err = 0;
out:
	trace_bpf_test_finish(&err);
	return err;
}

static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
			   u32 headroom, u32 tailroom)
{
	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
	void *data;

	if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
		return ERR_PTR(-EINVAL);

	data = kzalloc(size + headroom + tailroom, GFP_USER);
	if (!data)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(data + headroom, data_in, size)) {
		kfree(data);
		return ERR_PTR(-EFAULT);
	}
	return data;
}

static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
{
	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
	u32 size = kattr->test.ctx_size_in;
	void *data;
	int err;

	if (!data_in && !data_out)
		return NULL;

	data = kzalloc(max_size, GFP_USER);
	if (!data)
		return ERR_PTR(-ENOMEM);

	if (data_in) {
		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
		if (err) {
			kfree(data);
			return ERR_PTR(err);
		}

		size = min_t(u32, max_size, size);
		if (copy_from_user(data, data_in, size)) {
			kfree(data);
			return ERR_PTR(-EFAULT);
		}
	}
	return data;
}

static int bpf_ctx_finish(const union bpf_attr *kattr,
			  union bpf_attr __user *uattr, const void *data,
			  u32 size)
{
	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
	int err = -EFAULT;
	u32 copy_size = size;

	if (!data || !data_out)
		return 0;

	if (copy_size > kattr->test.ctx_size_out) {
		copy_size = kattr->test.ctx_size_out;
		err = -ENOSPC;
	}

	if (copy_to_user(data_out, data, copy_size))
		goto out;
	if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
		goto out;
	if (err != -ENOSPC)
		err = 0;
out:
	return err;
}

/**
 * range_is_zero - test whether buffer is initialized
 * @buf: buffer to check
 * @from: check from this position
 * @to: check up until (excluding) this position
 *
 * This function returns true if the there is a non-zero byte
 * in the buf in the range [from,to).
 */
static inline bool range_is_zero(void *buf, size_t from, size_t to)
{
	return !memchr_inv((u8 *)buf + from, 0, to - from);
}

static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
{
	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;

	if (!__skb)
		return 0;

	/* make sure the fields we don't use are zeroed */
	if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority)))
		return -EINVAL;

	/* priority is allowed */

	if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
			   FIELD_SIZEOF(struct __sk_buff, priority),
			   offsetof(struct __sk_buff, cb)))
		return -EINVAL;

	/* cb is allowed */

	if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
			   FIELD_SIZEOF(struct __sk_buff, cb),
			   sizeof(struct __sk_buff)))
		return -EINVAL;

	skb->priority = __skb->priority;
	memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);

	return 0;
}

static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
{
	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;

	if (!__skb)
		return;

	__skb->priority = skb->priority;
	memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
}

int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
			  union bpf_attr __user *uattr)
{
	bool is_l2 = false, is_direct_pkt_access = false;
	u32 size = kattr->test.data_size_in;
	u32 repeat = kattr->test.repeat;
	struct __sk_buff *ctx = NULL;
	u32 retval, duration;
	int hh_len = ETH_HLEN;
	struct sk_buff *skb;
	struct sock *sk;
	void *data;
	int ret;

	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
	if (IS_ERR(data))
		return PTR_ERR(data);

	ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
	if (IS_ERR(ctx)) {
		kfree(data);
		return PTR_ERR(ctx);
	}

	switch (prog->type) {
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
		is_l2 = true;
		/* fall through */
	case BPF_PROG_TYPE_LWT_IN:
	case BPF_PROG_TYPE_LWT_OUT:
	case BPF_PROG_TYPE_LWT_XMIT:
		is_direct_pkt_access = true;
		break;
	default:
		break;
	}

	sk = kzalloc(sizeof(struct sock), GFP_USER);
	if (!sk) {
		kfree(data);
		kfree(ctx);
		return -ENOMEM;
	}
	sock_net_set(sk, current->nsproxy->net_ns);
	sock_init_data(NULL, sk);

	skb = build_skb(data, 0);
	if (!skb) {
		kfree(data);
		kfree(ctx);
		kfree(sk);
		return -ENOMEM;
	}
	skb->sk = sk;

	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
	__skb_put(skb, size);
	skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev);
	skb_reset_network_header(skb);

	if (is_l2)
		__skb_push(skb, hh_len);
	if (is_direct_pkt_access)
		bpf_compute_data_pointers(skb);
	ret = convert___skb_to_skb(skb, ctx);
	if (ret)
		goto out;
	ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
	if (ret)
		goto out;
	if (!is_l2) {
		if (skb_headroom(skb) < hh_len) {
			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));

			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
				ret = -ENOMEM;
				goto out;
			}
		}
		memset(__skb_push(skb, hh_len), 0, hh_len);
	}
	convert_skb_to___skb(skb, ctx);

	size = skb->len;
	/* bpf program can never convert linear skb to non-linear */
	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
		size = skb_headlen(skb);
	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
	if (!ret)
		ret = bpf_ctx_finish(kattr, uattr, ctx,
				     sizeof(struct __sk_buff));
out:
	kfree_skb(skb);
	bpf_sk_storage_free(sk);
	kfree(sk);
	kfree(ctx);
	return ret;
}

int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
			  union bpf_attr __user *uattr)
{
	u32 size = kattr->test.data_size_in;
	u32 repeat = kattr->test.repeat;
	struct netdev_rx_queue *rxqueue;
	struct xdp_buff xdp = {};
	u32 retval, duration;
	void *data;
	int ret;

	if (kattr->test.ctx_in || kattr->test.ctx_out)
		return -EINVAL;

	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
	if (IS_ERR(data))
		return PTR_ERR(data);

	xdp.data_hard_start = data;
	xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
	xdp.data_meta = xdp.data;
	xdp.data_end = xdp.data + size;

	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
	xdp.rxq = &rxqueue->xdp_rxq;

	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration);
	if (ret)
		goto out;
	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN ||
	    xdp.data_end != xdp.data + size)
		size = xdp.data_end - xdp.data;
	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
out:
	kfree(data);
	return ret;
}

int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
				     const union bpf_attr *kattr,
				     union bpf_attr __user *uattr)
{
	u32 size = kattr->test.data_size_in;
	struct bpf_flow_dissector ctx = {};
	u32 repeat = kattr->test.repeat;
	struct bpf_flow_keys flow_keys;
	u64 time_start, time_spent = 0;
	const struct ethhdr *eth;
	u32 retval, duration;
	void *data;
	int ret;
	u32 i;

	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
		return -EINVAL;

	if (kattr->test.ctx_in || kattr->test.ctx_out)
		return -EINVAL;

	if (size < ETH_HLEN)
		return -EINVAL;

	data = bpf_test_init(kattr, size, 0, 0);
	if (IS_ERR(data))
		return PTR_ERR(data);

	eth = (struct ethhdr *)data;

	if (!repeat)
		repeat = 1;

	ctx.flow_keys = &flow_keys;
	ctx.data = data;
	ctx.data_end = (__u8 *)data + size;

	rcu_read_lock();
	preempt_disable();
	time_start = ktime_get_ns();
	for (i = 0; i < repeat; i++) {
		retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
					  size);

		if (signal_pending(current)) {
			preempt_enable();
			rcu_read_unlock();

			ret = -EINTR;
			goto out;
		}

		if (need_resched()) {
			time_spent += ktime_get_ns() - time_start;
			preempt_enable();
			rcu_read_unlock();

			cond_resched();

			rcu_read_lock();
			preempt_disable();
			time_start = ktime_get_ns();
		}
	}
	time_spent += ktime_get_ns() - time_start;
	preempt_enable();
	rcu_read_unlock();

	do_div(time_spent, repeat);
	duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;

	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
			      retval, duration);

out:
	kfree(data);
	return ret;
}