summaryrefslogtreecommitdiffstats
path: root/net/ipv4/bpf_tcp_ca.c
blob: f79ab942f03b6fee8aa3263d84a22b787a1406e6 (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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook  */

#include <linux/init.h>
#include <linux/types.h>
#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/filter.h>
#include <net/tcp.h>
#include <net/bpf_sk_storage.h>

/* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
extern struct bpf_struct_ops bpf_tcp_congestion_ops;

static u32 optional_ops[] = {
	offsetof(struct tcp_congestion_ops, init),
	offsetof(struct tcp_congestion_ops, release),
	offsetof(struct tcp_congestion_ops, set_state),
	offsetof(struct tcp_congestion_ops, cwnd_event),
	offsetof(struct tcp_congestion_ops, in_ack_event),
	offsetof(struct tcp_congestion_ops, pkts_acked),
	offsetof(struct tcp_congestion_ops, min_tso_segs),
	offsetof(struct tcp_congestion_ops, sndbuf_expand),
	offsetof(struct tcp_congestion_ops, cong_control),
};

static u32 unsupported_ops[] = {
	offsetof(struct tcp_congestion_ops, get_info),
};

static const struct btf_type *tcp_sock_type;
static u32 tcp_sock_id, sock_id;

static int bpf_tcp_ca_init(struct btf *btf)
{
	s32 type_id;

	type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT);
	if (type_id < 0)
		return -EINVAL;
	sock_id = type_id;

	type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT);
	if (type_id < 0)
		return -EINVAL;
	tcp_sock_id = type_id;
	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);

	return 0;
}

static bool is_optional(u32 member_offset)
{
	unsigned int i;

	for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
		if (member_offset == optional_ops[i])
			return true;
	}

	return false;
}

static bool is_unsupported(u32 member_offset)
{
	unsigned int i;

	for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) {
		if (member_offset == unsupported_ops[i])
			return true;
	}

	return false;
}

extern struct btf *btf_vmlinux;

static bool bpf_tcp_ca_is_valid_access(int off, int size,
				       enum bpf_access_type type,
				       const struct bpf_prog *prog,
				       struct bpf_insn_access_aux *info)
{
	if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info))
		return false;

	if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id)
		/* promote it to tcp_sock */
		info->btf_id = tcp_sock_id;

	return true;
}

static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
					const struct btf *btf,
					const struct btf_type *t, int off,
					int size, enum bpf_access_type atype,
					u32 *next_btf_id,
					enum bpf_type_flag *flag)
{
	size_t end;

	if (atype == BPF_READ)
		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
					 flag);

	if (t != tcp_sock_type) {
		bpf_log(log, "only read is supported\n");
		return -EACCES;
	}

	switch (off) {
	case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv):
		end = offsetofend(struct inet_connection_sock, icsk_ca_priv);
		break;
	case offsetof(struct inet_connection_sock, icsk_ack.pending):
		end = offsetofend(struct inet_connection_sock,
				  icsk_ack.pending);
		break;
	case offsetof(struct tcp_sock, snd_cwnd):
		end = offsetofend(struct tcp_sock, snd_cwnd);
		break;
	case offsetof(struct tcp_sock, snd_cwnd_cnt):
		end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
		break;
	case offsetof(struct tcp_sock, snd_ssthresh):
		end = offsetofend(struct tcp_sock, snd_ssthresh);
		break;
	case offsetof(struct tcp_sock, ecn_flags):
		end = offsetofend(struct tcp_sock, ecn_flags);
		break;
	default:
		bpf_log(log, "no write support to tcp_sock at off %d\n", off);
		return -EACCES;
	}

	if (off + size > end) {
		bpf_log(log,
			"write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n",
			off, size, end);
		return -EACCES;
	}

	return NOT_INIT;
}

BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
{
	/* bpf_tcp_ca prog cannot have NULL tp */
	__tcp_send_ack((struct sock *)tp, rcv_nxt);
	return 0;
}

static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
	.func		= bpf_tcp_send_ack,
	.gpl_only	= false,
	/* In case we want to report error later */
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_BTF_ID,
	.arg1_btf_id	= &tcp_sock_id,
	.arg2_type	= ARG_ANYTHING,
};

static u32 prog_ops_moff(const struct bpf_prog *prog)
{
	const struct btf_member *m;
	const struct btf_type *t;
	u32 midx;

	midx = prog->expected_attach_type;
	t = bpf_tcp_congestion_ops.type;
	m = &btf_type_member(t)[midx];

	return __btf_member_bit_offset(t, m) / 8;
}

static const struct bpf_func_proto *
bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
			  const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_tcp_send_ack:
		return &bpf_tcp_send_ack_proto;
	case BPF_FUNC_sk_storage_get:
		return &bpf_sk_storage_get_proto;
	case BPF_FUNC_sk_storage_delete:
		return &bpf_sk_storage_delete_proto;
	case BPF_FUNC_setsockopt:
		/* Does not allow release() to call setsockopt.
		 * release() is called when the current bpf-tcp-cc
		 * is retiring.  It is not allowed to call
		 * setsockopt() to make further changes which
		 * may potentially allocate new resources.
		 */
		if (prog_ops_moff(prog) !=
		    offsetof(struct tcp_congestion_ops, release))
			return &bpf_sk_setsockopt_proto;
		return NULL;
	case BPF_FUNC_getsockopt:
		/* Since get/setsockopt is usually expected to
		 * be available together, disable getsockopt for
		 * release also to avoid usage surprise.
		 * The bpf-tcp-cc already has a more powerful way
		 * to read tcp_sock from the PTR_TO_BTF_ID.
		 */
		if (prog_ops_moff(prog) !=
		    offsetof(struct tcp_congestion_ops, release))
			return &bpf_sk_getsockopt_proto;
		return NULL;
	case BPF_FUNC_ktime_get_coarse_ns:
		return &bpf_ktime_get_coarse_ns_proto;
	default:
		return bpf_base_func_proto(func_id);
	}
}

BTF_SET_START(bpf_tcp_ca_check_kfunc_ids)
BTF_ID(func, tcp_reno_ssthresh)
BTF_ID(func, tcp_reno_cong_avoid)
BTF_ID(func, tcp_reno_undo_cwnd)
BTF_ID(func, tcp_slow_start)
BTF_ID(func, tcp_cong_avoid_ai)
BTF_SET_END(bpf_tcp_ca_check_kfunc_ids)

static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = {
	.owner     = THIS_MODULE,
	.check_set = &bpf_tcp_ca_check_kfunc_ids,
};

static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
	.get_func_proto		= bpf_tcp_ca_get_func_proto,
	.is_valid_access	= bpf_tcp_ca_is_valid_access,
	.btf_struct_access	= bpf_tcp_ca_btf_struct_access,
};

static int bpf_tcp_ca_init_member(const struct btf_type *t,
				  const struct btf_member *member,
				  void *kdata, const void *udata)
{
	const struct tcp_congestion_ops *utcp_ca;
	struct tcp_congestion_ops *tcp_ca;
	int prog_fd;
	u32 moff;

	utcp_ca = (const struct tcp_congestion_ops *)udata;
	tcp_ca = (struct tcp_congestion_ops *)kdata;

	moff = __btf_member_bit_offset(t, member) / 8;
	switch (moff) {
	case offsetof(struct tcp_congestion_ops, flags):
		if (utcp_ca->flags & ~TCP_CONG_MASK)
			return -EINVAL;
		tcp_ca->flags = utcp_ca->flags;
		return 1;
	case offsetof(struct tcp_congestion_ops, name):
		if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name,
				     sizeof(tcp_ca->name)) <= 0)
			return -EINVAL;
		if (tcp_ca_find(utcp_ca->name))
			return -EEXIST;
		return 1;
	}

	if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
		return 0;

	/* Ensure bpf_prog is provided for compulsory func ptr */
	prog_fd = (int)(*(unsigned long *)(udata + moff));
	if (!prog_fd && !is_optional(moff) && !is_unsupported(moff))
		return -EINVAL;

	return 0;
}

static int bpf_tcp_ca_check_member(const struct btf_type *t,
				   const struct btf_member *member)
{
	if (is_unsupported(__btf_member_bit_offset(t, member) / 8))
		return -ENOTSUPP;
	return 0;
}

static int bpf_tcp_ca_reg(void *kdata)
{
	return tcp_register_congestion_control(kdata);
}

static void bpf_tcp_ca_unreg(void *kdata)
{
	tcp_unregister_congestion_control(kdata);
}

struct bpf_struct_ops bpf_tcp_congestion_ops = {
	.verifier_ops = &bpf_tcp_ca_verifier_ops,
	.reg = bpf_tcp_ca_reg,
	.unreg = bpf_tcp_ca_unreg,
	.check_member = bpf_tcp_ca_check_member,
	.init_member = bpf_tcp_ca_init_member,
	.init = bpf_tcp_ca_init,
	.name = "tcp_congestion_ops",
};

static int __init bpf_tcp_ca_kfunc_init(void)
{
	return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set);
}
late_initcall(bpf_tcp_ca_kfunc_init);