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
|
// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
*
* Copyright (c) 2017 - 2019, Intel Corporation.
*/
#include <linux/kernel.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"
static bool mptcp_cap_flag_sha256(u8 flags)
{
return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
}
void mptcp_parse_option(const unsigned char *ptr, int opsize,
struct tcp_options_received *opt_rx)
{
struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
u8 subtype = *ptr >> 4;
int expected_opsize;
u8 version;
u8 flags;
switch (subtype) {
case MPTCPOPT_MP_CAPABLE:
if (opsize != TCPOLEN_MPTCP_MPC_SYN &&
opsize != TCPOLEN_MPTCP_MPC_ACK)
break;
version = *ptr++ & MPTCP_VERSION_MASK;
if (version != MPTCP_SUPPORTED_VERSION)
break;
flags = *ptr++;
if (!mptcp_cap_flag_sha256(flags) ||
(flags & MPTCP_CAP_EXTENSIBILITY))
break;
/* RFC 6824, Section 3.1:
* "For the Checksum Required bit (labeled "A"), if either
* host requires the use of checksums, checksums MUST be used.
* In other words, the only way for checksums not to be used
* is if both hosts in their SYNs set A=0."
*
* Section 3.3.0:
* "If a checksum is not present when its use has been
* negotiated, the receiver MUST close the subflow with a RST as
* it is considered broken."
*
* We don't implement DSS checksum - fall back to TCP.
*/
if (flags & MPTCP_CAP_CHECKSUM_REQD)
break;
mp_opt->mp_capable = 1;
mp_opt->sndr_key = get_unaligned_be64(ptr);
ptr += 8;
if (opsize == TCPOLEN_MPTCP_MPC_ACK) {
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
pr_debug("MP_CAPABLE sndr=%llu, rcvr=%llu",
mp_opt->sndr_key, mp_opt->rcvr_key);
} else {
pr_debug("MP_CAPABLE sndr=%llu", mp_opt->sndr_key);
}
break;
case MPTCPOPT_DSS:
pr_debug("DSS");
ptr++;
flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
mp_opt->data_fin, mp_opt->dsn64,
mp_opt->use_map, mp_opt->ack64,
mp_opt->use_ack);
expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
if (mp_opt->use_ack) {
if (mp_opt->ack64)
expected_opsize += TCPOLEN_MPTCP_DSS_ACK64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_ACK32;
}
if (mp_opt->use_map) {
if (mp_opt->dsn64)
expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
}
/* RFC 6824, Section 3.3:
* If a checksum is present, but its use had
* not been negotiated in the MP_CAPABLE handshake,
* the checksum field MUST be ignored.
*/
if (opsize != expected_opsize &&
opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
break;
mp_opt->dss = 1;
if (mp_opt->use_ack) {
if (mp_opt->ack64) {
mp_opt->data_ack = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_ack = get_unaligned_be32(ptr);
ptr += 4;
}
pr_debug("data_ack=%llu", mp_opt->data_ack);
}
if (mp_opt->use_map) {
if (mp_opt->dsn64) {
mp_opt->data_seq = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_seq = get_unaligned_be32(ptr);
ptr += 4;
}
mp_opt->subflow_seq = get_unaligned_be32(ptr);
ptr += 4;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len);
}
break;
default:
break;
}
}
void mptcp_get_options(const struct sk_buff *skb,
struct tcp_options_received *opt_rx)
{
const unsigned char *ptr;
const struct tcphdr *th = tcp_hdr(skb);
int length = (th->doff * 4) - sizeof(struct tcphdr);
ptr = (const unsigned char *)(th + 1);
while (length > 0) {
int opcode = *ptr++;
int opsize;
switch (opcode) {
case TCPOPT_EOL:
return;
case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
length--;
continue;
default:
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
if (opsize > length)
return; /* don't parse partial options */
if (opcode == TCPOPT_MPTCP)
mptcp_parse_option(ptr, opsize, opt_rx);
ptr += opsize - 2;
length -= opsize;
}
}
}
bool mptcp_syn_options(struct sock *sk, unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
if (subflow->request_mptcp) {
pr_debug("local_key=%llu", subflow->local_key);
opts->suboptions = OPTION_MPTCP_MPC_SYN;
opts->sndr_key = subflow->local_key;
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
}
return false;
}
void mptcp_rcv_synsent(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct tcp_sock *tp = tcp_sk(sk);
pr_debug("subflow=%p", subflow);
if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
subflow->mp_capable = 1;
subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
} else {
tcp_sk(sk)->is_mptcp = 0;
}
}
static bool mptcp_established_options_mp(struct sock *sk, unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
if (!subflow->fourth_ack) {
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
*size = TCPOLEN_MPTCP_MPC_ACK;
subflow->fourth_ack = 1;
pr_debug("subflow=%p, local_key=%llu, remote_key=%llu",
subflow, subflow->local_key, subflow->remote_key);
return true;
}
return false;
}
static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
struct mptcp_ext *ext)
{
ext->data_fin = 1;
if (!ext->use_map) {
/* RFC6824 requires a DSS mapping with specific values
* if DATA_FIN is set but no data payload is mapped
*/
ext->use_map = 1;
ext->dsn64 = 1;
ext->data_seq = mptcp_sk(subflow->conn)->write_seq;
ext->subflow_seq = 0;
ext->data_len = 1;
} else {
/* If there's an existing DSS mapping, DATA_FIN consumes
* 1 additional byte of mapping space.
*/
ext->data_len++;
}
}
static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
unsigned int dss_size = 0;
struct mptcp_ext *mpext;
struct mptcp_sock *msk;
unsigned int ack_size;
u8 tcp_fin;
if (skb) {
mpext = mptcp_get_ext(skb);
tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
} else {
mpext = NULL;
tcp_fin = 0;
}
if (!skb || (mpext && mpext->use_map) || tcp_fin) {
unsigned int map_size;
map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
remaining -= map_size;
dss_size = map_size;
if (mpext)
opts->ext_copy = *mpext;
if (skb && tcp_fin &&
subflow->conn->sk_state != TCP_ESTABLISHED)
mptcp_write_data_fin(subflow, &opts->ext_copy);
}
ack_size = TCPOLEN_MPTCP_DSS_ACK64;
/* Add kind/length/subtype/flag overhead if mapping is not populated */
if (dss_size == 0)
ack_size += TCPOLEN_MPTCP_DSS_BASE;
dss_size += ack_size;
msk = mptcp_sk(mptcp_subflow_ctx(sk)->conn);
if (msk) {
opts->ext_copy.data_ack = msk->ack_seq;
} else {
mptcp_crypto_key_sha(mptcp_subflow_ctx(sk)->remote_key,
NULL, &opts->ext_copy.data_ack);
opts->ext_copy.data_ack++;
}
opts->ext_copy.ack64 = 1;
opts->ext_copy.use_ack = 1;
*size = ALIGN(dss_size, 4);
return true;
}
bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts)
{
unsigned int opt_size = 0;
bool ret = false;
if (mptcp_established_options_mp(sk, &opt_size, remaining, opts))
ret = true;
else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
opts))
ret = true;
/* we reserved enough space for the above options, and exceeding the
* TCP option space would be fatal
*/
if (WARN_ON_ONCE(opt_size > remaining))
return false;
*size += opt_size;
remaining -= opt_size;
return ret;
}
bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
if (subflow_req->mp_capable) {
opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
opts->sndr_key = subflow_req->local_key;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
pr_debug("subflow_req=%p, local_key=%llu",
subflow_req, subflow_req->local_key);
return true;
}
return false;
}
void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
struct tcp_options_received *opt_rx)
{
struct mptcp_options_received *mp_opt;
struct mptcp_ext *mpext;
mp_opt = &opt_rx->mptcp;
if (!mp_opt->dss)
return;
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
return;
memset(mpext, 0, sizeof(*mpext));
if (mp_opt->use_map) {
mpext->data_seq = mp_opt->data_seq;
mpext->subflow_seq = mp_opt->subflow_seq;
mpext->data_len = mp_opt->data_len;
mpext->use_map = 1;
mpext->dsn64 = mp_opt->dsn64;
}
if (mp_opt->use_ack) {
mpext->data_ack = mp_opt->data_ack;
mpext->use_ack = 1;
mpext->ack64 = mp_opt->ack64;
}
mpext->data_fin = mp_opt->data_fin;
}
void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
{
if ((OPTION_MPTCP_MPC_SYN |
OPTION_MPTCP_MPC_SYNACK |
OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
u8 len;
if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYN;
else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYNACK;
else
len = TCPOLEN_MPTCP_MPC_ACK;
*ptr++ = htonl((TCPOPT_MPTCP << 24) | (len << 16) |
(MPTCPOPT_MP_CAPABLE << 12) |
(MPTCP_SUPPORTED_VERSION << 8) |
MPTCP_CAP_HMAC_SHA256);
put_unaligned_be64(opts->sndr_key, ptr);
ptr += 2;
if (OPTION_MPTCP_MPC_ACK & opts->suboptions) {
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
}
}
if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
struct mptcp_ext *mpext = &opts->ext_copy;
u8 len = TCPOLEN_MPTCP_DSS_BASE;
u8 flags = 0;
if (mpext->use_ack) {
len += TCPOLEN_MPTCP_DSS_ACK64;
flags = MPTCP_DSS_HAS_ACK | MPTCP_DSS_ACK64;
}
if (mpext->use_map) {
len += TCPOLEN_MPTCP_DSS_MAP64;
/* Use only 64-bit mapping flags for now, add
* support for optional 32-bit mappings later.
*/
flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
if (mpext->data_fin)
flags |= MPTCP_DSS_DATA_FIN;
}
*ptr++ = htonl((TCPOPT_MPTCP << 24) |
(len << 16) |
(MPTCPOPT_DSS << 12) |
(flags));
if (mpext->use_ack) {
put_unaligned_be64(mpext->data_ack, ptr);
ptr += 2;
}
if (mpext->use_map) {
put_unaligned_be64(mpext->data_seq, ptr);
ptr += 2;
put_unaligned_be32(mpext->subflow_seq, ptr);
ptr += 1;
put_unaligned_be32(mpext->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
}
}
|