lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame] | 1 | /* |
| 2 | * net/dccp/output.c |
| 3 | * |
| 4 | * An implementation of the DCCP protocol |
| 5 | * Arnaldo Carvalho de Melo <acme@conectiva.com.br> |
| 6 | * |
| 7 | * This program is free software; you can redistribute it and/or |
| 8 | * modify it under the terms of the GNU General Public License |
| 9 | * as published by the Free Software Foundation; either version |
| 10 | * 2 of the License, or (at your option) any later version. |
| 11 | */ |
| 12 | |
| 13 | #include <linux/dccp.h> |
| 14 | #include <linux/kernel.h> |
| 15 | #include <linux/skbuff.h> |
| 16 | #include <linux/slab.h> |
| 17 | |
| 18 | #include <net/inet_sock.h> |
| 19 | #include <net/sock.h> |
| 20 | |
| 21 | #include "ackvec.h" |
| 22 | #include "ccid.h" |
| 23 | #include "dccp.h" |
| 24 | |
| 25 | static inline void dccp_event_ack_sent(struct sock *sk) |
| 26 | { |
| 27 | inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); |
| 28 | } |
| 29 | |
| 30 | /* enqueue @skb on sk_send_head for retransmission, return clone to send now */ |
| 31 | static struct sk_buff *dccp_skb_entail(struct sock *sk, struct sk_buff *skb) |
| 32 | { |
| 33 | skb_set_owner_w(skb, sk); |
| 34 | WARN_ON(sk->sk_send_head); |
| 35 | sk->sk_send_head = skb; |
| 36 | return skb_clone(sk->sk_send_head, gfp_any()); |
| 37 | } |
| 38 | |
| 39 | /* |
| 40 | * All SKB's seen here are completely headerless. It is our |
| 41 | * job to build the DCCP header, and pass the packet down to |
| 42 | * IP so it can do the same plus pass the packet off to the |
| 43 | * device. |
| 44 | */ |
| 45 | static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) |
| 46 | { |
| 47 | if (likely(skb != NULL)) { |
| 48 | struct inet_sock *inet = inet_sk(sk); |
| 49 | const struct inet_connection_sock *icsk = inet_csk(sk); |
| 50 | struct dccp_sock *dp = dccp_sk(sk); |
| 51 | struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); |
| 52 | struct dccp_hdr *dh; |
| 53 | /* XXX For now we're using only 48 bits sequence numbers */ |
| 54 | const u32 dccp_header_size = sizeof(*dh) + |
| 55 | sizeof(struct dccp_hdr_ext) + |
| 56 | dccp_packet_hdr_len(dcb->dccpd_type); |
| 57 | int err, set_ack = 1; |
| 58 | u64 ackno = dp->dccps_gsr; |
| 59 | /* |
| 60 | * Increment GSS here already in case the option code needs it. |
| 61 | * Update GSS for real only if option processing below succeeds. |
| 62 | */ |
| 63 | dcb->dccpd_seq = ADD48(dp->dccps_gss, 1); |
| 64 | |
| 65 | switch (dcb->dccpd_type) { |
| 66 | case DCCP_PKT_DATA: |
| 67 | set_ack = 0; |
| 68 | /* fall through */ |
| 69 | case DCCP_PKT_DATAACK: |
| 70 | case DCCP_PKT_RESET: |
| 71 | break; |
| 72 | |
| 73 | case DCCP_PKT_REQUEST: |
| 74 | set_ack = 0; |
| 75 | /* Use ISS on the first (non-retransmitted) Request. */ |
| 76 | if (icsk->icsk_retransmits == 0) |
| 77 | dcb->dccpd_seq = dp->dccps_iss; |
| 78 | /* fall through */ |
| 79 | |
| 80 | case DCCP_PKT_SYNC: |
| 81 | case DCCP_PKT_SYNCACK: |
| 82 | ackno = dcb->dccpd_ack_seq; |
| 83 | /* fall through */ |
| 84 | default: |
| 85 | /* |
| 86 | * Set owner/destructor: some skbs are allocated via |
| 87 | * alloc_skb (e.g. when retransmission may happen). |
| 88 | * Only Data, DataAck, and Reset packets should come |
| 89 | * through here with skb->sk set. |
| 90 | */ |
| 91 | WARN_ON(skb->sk); |
| 92 | skb_set_owner_w(skb, sk); |
| 93 | break; |
| 94 | } |
| 95 | |
| 96 | if (dccp_insert_options(sk, skb)) { |
| 97 | kfree_skb(skb); |
| 98 | return -EPROTO; |
| 99 | } |
| 100 | |
| 101 | |
| 102 | /* Build DCCP header and checksum it. */ |
| 103 | dh = dccp_zeroed_hdr(skb, dccp_header_size); |
| 104 | dh->dccph_type = dcb->dccpd_type; |
| 105 | dh->dccph_sport = inet->inet_sport; |
| 106 | dh->dccph_dport = inet->inet_dport; |
| 107 | dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4; |
| 108 | dh->dccph_ccval = dcb->dccpd_ccval; |
| 109 | dh->dccph_cscov = dp->dccps_pcslen; |
| 110 | /* XXX For now we're using only 48 bits sequence numbers */ |
| 111 | dh->dccph_x = 1; |
| 112 | |
| 113 | dccp_update_gss(sk, dcb->dccpd_seq); |
| 114 | dccp_hdr_set_seq(dh, dp->dccps_gss); |
| 115 | if (set_ack) |
| 116 | dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno); |
| 117 | |
| 118 | switch (dcb->dccpd_type) { |
| 119 | case DCCP_PKT_REQUEST: |
| 120 | dccp_hdr_request(skb)->dccph_req_service = |
| 121 | dp->dccps_service; |
| 122 | /* |
| 123 | * Limit Ack window to ISS <= P.ackno <= GSS, so that |
| 124 | * only Responses to Requests we sent are considered. |
| 125 | */ |
| 126 | dp->dccps_awl = dp->dccps_iss; |
| 127 | break; |
| 128 | case DCCP_PKT_RESET: |
| 129 | dccp_hdr_reset(skb)->dccph_reset_code = |
| 130 | dcb->dccpd_reset_code; |
| 131 | break; |
| 132 | } |
| 133 | |
| 134 | icsk->icsk_af_ops->send_check(sk, skb); |
| 135 | |
| 136 | if (set_ack) |
| 137 | dccp_event_ack_sent(sk); |
| 138 | |
| 139 | DCCP_INC_STATS(DCCP_MIB_OUTSEGS); |
| 140 | |
| 141 | err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); |
| 142 | return net_xmit_eval(err); |
| 143 | } |
| 144 | return -ENOBUFS; |
| 145 | } |
| 146 | |
| 147 | /** |
| 148 | * dccp_determine_ccmps - Find out about CCID-specific packet-size limits |
| 149 | * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), |
| 150 | * since the RX CCID is restricted to feedback packets (Acks), which are small |
| 151 | * in comparison with the data traffic. A value of 0 means "no current CCMPS". |
| 152 | */ |
| 153 | static u32 dccp_determine_ccmps(const struct dccp_sock *dp) |
| 154 | { |
| 155 | const struct ccid *tx_ccid = dp->dccps_hc_tx_ccid; |
| 156 | |
| 157 | if (tx_ccid == NULL || tx_ccid->ccid_ops == NULL) |
| 158 | return 0; |
| 159 | return tx_ccid->ccid_ops->ccid_ccmps; |
| 160 | } |
| 161 | |
| 162 | unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) |
| 163 | { |
| 164 | struct inet_connection_sock *icsk = inet_csk(sk); |
| 165 | struct dccp_sock *dp = dccp_sk(sk); |
| 166 | u32 ccmps = dccp_determine_ccmps(dp); |
| 167 | u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu; |
| 168 | |
| 169 | /* Account for header lengths and IPv4/v6 option overhead */ |
| 170 | cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len + |
| 171 | sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext)); |
| 172 | |
| 173 | /* |
| 174 | * Leave enough headroom for common DCCP header options. |
| 175 | * This only considers options which may appear on DCCP-Data packets, as |
| 176 | * per table 3 in RFC 4340, 5.8. When running out of space for other |
| 177 | * options (eg. Ack Vector which can take up to 255 bytes), it is better |
| 178 | * to schedule a separate Ack. Thus we leave headroom for the following: |
| 179 | * - 1 byte for Slow Receiver (11.6) |
| 180 | * - 6 bytes for Timestamp (13.1) |
| 181 | * - 10 bytes for Timestamp Echo (13.3) |
| 182 | * - 8 bytes for NDP count (7.7, when activated) |
| 183 | * - 6 bytes for Data Checksum (9.3) |
| 184 | * - %DCCPAV_MIN_OPTLEN bytes for Ack Vector size (11.4, when enabled) |
| 185 | */ |
| 186 | cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 + |
| 187 | (dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4); |
| 188 | |
| 189 | /* And store cached results */ |
| 190 | icsk->icsk_pmtu_cookie = pmtu; |
| 191 | dp->dccps_mss_cache = cur_mps; |
| 192 | |
| 193 | return cur_mps; |
| 194 | } |
| 195 | |
| 196 | EXPORT_SYMBOL_GPL(dccp_sync_mss); |
| 197 | |
| 198 | void dccp_write_space(struct sock *sk) |
| 199 | { |
| 200 | struct socket_wq *wq; |
| 201 | |
| 202 | rcu_read_lock(); |
| 203 | wq = rcu_dereference(sk->sk_wq); |
| 204 | if (wq_has_sleeper(wq)) |
| 205 | wake_up_interruptible(&wq->wait); |
| 206 | /* Should agree with poll, otherwise some programs break */ |
| 207 | if (sock_writeable(sk)) |
| 208 | sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); |
| 209 | |
| 210 | rcu_read_unlock(); |
| 211 | } |
| 212 | |
| 213 | /** |
| 214 | * dccp_wait_for_ccid - Await CCID send permission |
| 215 | * @sk: socket to wait for |
| 216 | * @delay: timeout in jiffies |
| 217 | * This is used by CCIDs which need to delay the send time in process context. |
| 218 | */ |
| 219 | static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) |
| 220 | { |
| 221 | DEFINE_WAIT(wait); |
| 222 | long remaining; |
| 223 | |
| 224 | prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); |
| 225 | sk->sk_write_pending++; |
| 226 | release_sock(sk); |
| 227 | |
| 228 | remaining = schedule_timeout(delay); |
| 229 | |
| 230 | lock_sock(sk); |
| 231 | sk->sk_write_pending--; |
| 232 | finish_wait(sk_sleep(sk), &wait); |
| 233 | |
| 234 | if (signal_pending(current) || sk->sk_err) |
| 235 | return -1; |
| 236 | return remaining; |
| 237 | } |
| 238 | |
| 239 | /** |
| 240 | * dccp_xmit_packet - Send data packet under control of CCID |
| 241 | * Transmits next-queued payload and informs CCID to account for the packet. |
| 242 | */ |
| 243 | static void dccp_xmit_packet(struct sock *sk) |
| 244 | { |
| 245 | int err, len; |
| 246 | struct dccp_sock *dp = dccp_sk(sk); |
| 247 | struct sk_buff *skb = dccp_qpolicy_pop(sk); |
| 248 | |
| 249 | if (unlikely(skb == NULL)) |
| 250 | return; |
| 251 | len = skb->len; |
| 252 | |
| 253 | if (sk->sk_state == DCCP_PARTOPEN) { |
| 254 | const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD; |
| 255 | /* |
| 256 | * See 8.1.5 - Handshake Completion. |
| 257 | * |
| 258 | * For robustness we resend Confirm options until the client has |
| 259 | * entered OPEN. During the initial feature negotiation, the MPS |
| 260 | * is smaller than usual, reduced by the Change/Confirm options. |
| 261 | */ |
| 262 | if (!list_empty(&dp->dccps_featneg) && len > cur_mps) { |
| 263 | DCCP_WARN("Payload too large (%d) for featneg.\n", len); |
| 264 | dccp_send_ack(sk); |
| 265 | dccp_feat_list_purge(&dp->dccps_featneg); |
| 266 | } |
| 267 | |
| 268 | inet_csk_schedule_ack(sk); |
| 269 | inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, |
| 270 | inet_csk(sk)->icsk_rto, |
| 271 | DCCP_RTO_MAX); |
| 272 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; |
| 273 | } else if (dccp_ack_pending(sk)) { |
| 274 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; |
| 275 | } else { |
| 276 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA; |
| 277 | } |
| 278 | |
| 279 | err = dccp_transmit_skb(sk, skb); |
| 280 | if (err) |
| 281 | dccp_pr_debug("transmit_skb() returned err=%d\n", err); |
| 282 | /* |
| 283 | * Register this one as sent even if an error occurred. To the remote |
| 284 | * end a local packet drop is indistinguishable from network loss, i.e. |
| 285 | * any local drop will eventually be reported via receiver feedback. |
| 286 | */ |
| 287 | ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); |
| 288 | |
| 289 | /* |
| 290 | * If the CCID needs to transfer additional header options out-of-band |
| 291 | * (e.g. Ack Vectors or feature-negotiation options), it activates this |
| 292 | * flag to schedule a Sync. The Sync will automatically incorporate all |
| 293 | * currently pending header options, thus clearing the backlog. |
| 294 | */ |
| 295 | if (dp->dccps_sync_scheduled) |
| 296 | dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC); |
| 297 | } |
| 298 | |
| 299 | /** |
| 300 | * dccp_flush_write_queue - Drain queue at end of connection |
| 301 | * Since dccp_sendmsg queues packets without waiting for them to be sent, it may |
| 302 | * happen that the TX queue is not empty at the end of a connection. We give the |
| 303 | * HC-sender CCID a grace period of up to @time_budget jiffies. If this function |
| 304 | * returns with a non-empty write queue, it will be purged later. |
| 305 | */ |
| 306 | void dccp_flush_write_queue(struct sock *sk, long *time_budget) |
| 307 | { |
| 308 | struct dccp_sock *dp = dccp_sk(sk); |
| 309 | struct sk_buff *skb; |
| 310 | long delay, rc; |
| 311 | |
| 312 | while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) { |
| 313 | rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); |
| 314 | |
| 315 | switch (ccid_packet_dequeue_eval(rc)) { |
| 316 | case CCID_PACKET_WILL_DEQUEUE_LATER: |
| 317 | /* |
| 318 | * If the CCID determines when to send, the next sending |
| 319 | * time is unknown or the CCID may not even send again |
| 320 | * (e.g. remote host crashes or lost Ack packets). |
| 321 | */ |
| 322 | DCCP_WARN("CCID did not manage to send all packets\n"); |
| 323 | return; |
| 324 | case CCID_PACKET_DELAY: |
| 325 | delay = msecs_to_jiffies(rc); |
| 326 | if (delay > *time_budget) |
| 327 | return; |
| 328 | rc = dccp_wait_for_ccid(sk, delay); |
| 329 | if (rc < 0) |
| 330 | return; |
| 331 | *time_budget -= (delay - rc); |
| 332 | /* check again if we can send now */ |
| 333 | break; |
| 334 | case CCID_PACKET_SEND_AT_ONCE: |
| 335 | dccp_xmit_packet(sk); |
| 336 | break; |
| 337 | case CCID_PACKET_ERR: |
| 338 | skb_dequeue(&sk->sk_write_queue); |
| 339 | kfree_skb(skb); |
| 340 | dccp_pr_debug("packet discarded due to err=%ld\n", rc); |
| 341 | } |
| 342 | } |
| 343 | } |
| 344 | |
| 345 | void dccp_write_xmit(struct sock *sk) |
| 346 | { |
| 347 | struct dccp_sock *dp = dccp_sk(sk); |
| 348 | struct sk_buff *skb; |
| 349 | |
| 350 | while ((skb = dccp_qpolicy_top(sk))) { |
| 351 | int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); |
| 352 | |
| 353 | switch (ccid_packet_dequeue_eval(rc)) { |
| 354 | case CCID_PACKET_WILL_DEQUEUE_LATER: |
| 355 | return; |
| 356 | case CCID_PACKET_DELAY: |
| 357 | sk_reset_timer(sk, &dp->dccps_xmit_timer, |
| 358 | jiffies + msecs_to_jiffies(rc)); |
| 359 | return; |
| 360 | case CCID_PACKET_SEND_AT_ONCE: |
| 361 | dccp_xmit_packet(sk); |
| 362 | break; |
| 363 | case CCID_PACKET_ERR: |
| 364 | dccp_qpolicy_drop(sk, skb); |
| 365 | dccp_pr_debug("packet discarded due to err=%d\n", rc); |
| 366 | } |
| 367 | } |
| 368 | } |
| 369 | |
| 370 | /** |
| 371 | * dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets |
| 372 | * There are only four retransmittable packet types in DCCP: |
| 373 | * - Request in client-REQUEST state (sec. 8.1.1), |
| 374 | * - CloseReq in server-CLOSEREQ state (sec. 8.3), |
| 375 | * - Close in node-CLOSING state (sec. 8.3), |
| 376 | * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()). |
| 377 | * This function expects sk->sk_send_head to contain the original skb. |
| 378 | */ |
| 379 | int dccp_retransmit_skb(struct sock *sk) |
| 380 | { |
| 381 | WARN_ON(sk->sk_send_head == NULL); |
| 382 | |
| 383 | if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0) |
| 384 | return -EHOSTUNREACH; /* Routing failure or similar. */ |
| 385 | |
| 386 | /* this count is used to distinguish original and retransmitted skb */ |
| 387 | inet_csk(sk)->icsk_retransmits++; |
| 388 | |
| 389 | return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC)); |
| 390 | } |
| 391 | |
| 392 | struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, |
| 393 | struct request_sock *req) |
| 394 | { |
| 395 | struct dccp_hdr *dh; |
| 396 | struct dccp_request_sock *dreq; |
| 397 | const u32 dccp_header_size = sizeof(struct dccp_hdr) + |
| 398 | sizeof(struct dccp_hdr_ext) + |
| 399 | sizeof(struct dccp_hdr_response); |
| 400 | struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, |
| 401 | GFP_ATOMIC); |
| 402 | if (skb == NULL) |
| 403 | return NULL; |
| 404 | |
| 405 | /* Reserve space for headers. */ |
| 406 | skb_reserve(skb, sk->sk_prot->max_header); |
| 407 | |
| 408 | skb_dst_set(skb, dst_clone(dst)); |
| 409 | |
| 410 | dreq = dccp_rsk(req); |
| 411 | if (inet_rsk(req)->acked) /* increase GSS upon retransmission */ |
| 412 | dccp_inc_seqno(&dreq->dreq_gss); |
| 413 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE; |
| 414 | DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_gss; |
| 415 | |
| 416 | /* Resolve feature dependencies resulting from choice of CCID */ |
| 417 | if (dccp_feat_server_ccid_dependencies(dreq)) |
| 418 | goto response_failed; |
| 419 | |
| 420 | if (dccp_insert_options_rsk(dreq, skb)) |
| 421 | goto response_failed; |
| 422 | |
| 423 | /* Build and checksum header */ |
| 424 | dh = dccp_zeroed_hdr(skb, dccp_header_size); |
| 425 | |
| 426 | dh->dccph_sport = inet_rsk(req)->loc_port; |
| 427 | dh->dccph_dport = inet_rsk(req)->rmt_port; |
| 428 | dh->dccph_doff = (dccp_header_size + |
| 429 | DCCP_SKB_CB(skb)->dccpd_opt_len) / 4; |
| 430 | dh->dccph_type = DCCP_PKT_RESPONSE; |
| 431 | dh->dccph_x = 1; |
| 432 | dccp_hdr_set_seq(dh, dreq->dreq_gss); |
| 433 | dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_gsr); |
| 434 | dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service; |
| 435 | |
| 436 | dccp_csum_outgoing(skb); |
| 437 | |
| 438 | /* We use `acked' to remember that a Response was already sent. */ |
| 439 | inet_rsk(req)->acked = 1; |
| 440 | DCCP_INC_STATS(DCCP_MIB_OUTSEGS); |
| 441 | return skb; |
| 442 | response_failed: |
| 443 | kfree_skb(skb); |
| 444 | return NULL; |
| 445 | } |
| 446 | |
| 447 | EXPORT_SYMBOL_GPL(dccp_make_response); |
| 448 | |
| 449 | /* answer offending packet in @rcv_skb with Reset from control socket @ctl */ |
| 450 | struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb) |
| 451 | { |
| 452 | struct dccp_hdr *rxdh = dccp_hdr(rcv_skb), *dh; |
| 453 | struct dccp_skb_cb *dcb = DCCP_SKB_CB(rcv_skb); |
| 454 | const u32 dccp_hdr_reset_len = sizeof(struct dccp_hdr) + |
| 455 | sizeof(struct dccp_hdr_ext) + |
| 456 | sizeof(struct dccp_hdr_reset); |
| 457 | struct dccp_hdr_reset *dhr; |
| 458 | struct sk_buff *skb; |
| 459 | |
| 460 | skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC); |
| 461 | if (skb == NULL) |
| 462 | return NULL; |
| 463 | |
| 464 | skb_reserve(skb, sk->sk_prot->max_header); |
| 465 | |
| 466 | /* Swap the send and the receive. */ |
| 467 | dh = dccp_zeroed_hdr(skb, dccp_hdr_reset_len); |
| 468 | dh->dccph_type = DCCP_PKT_RESET; |
| 469 | dh->dccph_sport = rxdh->dccph_dport; |
| 470 | dh->dccph_dport = rxdh->dccph_sport; |
| 471 | dh->dccph_doff = dccp_hdr_reset_len / 4; |
| 472 | dh->dccph_x = 1; |
| 473 | |
| 474 | dhr = dccp_hdr_reset(skb); |
| 475 | dhr->dccph_reset_code = dcb->dccpd_reset_code; |
| 476 | |
| 477 | switch (dcb->dccpd_reset_code) { |
| 478 | case DCCP_RESET_CODE_PACKET_ERROR: |
| 479 | dhr->dccph_reset_data[0] = rxdh->dccph_type; |
| 480 | break; |
| 481 | case DCCP_RESET_CODE_OPTION_ERROR: /* fall through */ |
| 482 | case DCCP_RESET_CODE_MANDATORY_ERROR: |
| 483 | memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3); |
| 484 | break; |
| 485 | } |
| 486 | /* |
| 487 | * From RFC 4340, 8.3.1: |
| 488 | * If P.ackno exists, set R.seqno := P.ackno + 1. |
| 489 | * Else set R.seqno := 0. |
| 490 | */ |
| 491 | if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) |
| 492 | dccp_hdr_set_seq(dh, ADD48(dcb->dccpd_ack_seq, 1)); |
| 493 | dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dcb->dccpd_seq); |
| 494 | |
| 495 | dccp_csum_outgoing(skb); |
| 496 | return skb; |
| 497 | } |
| 498 | |
| 499 | EXPORT_SYMBOL_GPL(dccp_ctl_make_reset); |
| 500 | |
| 501 | /* send Reset on established socket, to close or abort the connection */ |
| 502 | int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code) |
| 503 | { |
| 504 | struct sk_buff *skb; |
| 505 | /* |
| 506 | * FIXME: what if rebuild_header fails? |
| 507 | * Should we be doing a rebuild_header here? |
| 508 | */ |
| 509 | int err = inet_csk(sk)->icsk_af_ops->rebuild_header(sk); |
| 510 | |
| 511 | if (err != 0) |
| 512 | return err; |
| 513 | |
| 514 | skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC); |
| 515 | if (skb == NULL) |
| 516 | return -ENOBUFS; |
| 517 | |
| 518 | /* Reserve space for headers and prepare control bits. */ |
| 519 | skb_reserve(skb, sk->sk_prot->max_header); |
| 520 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESET; |
| 521 | DCCP_SKB_CB(skb)->dccpd_reset_code = code; |
| 522 | |
| 523 | return dccp_transmit_skb(sk, skb); |
| 524 | } |
| 525 | |
| 526 | /* |
| 527 | * Do all connect socket setups that can be done AF independent. |
| 528 | */ |
| 529 | int dccp_connect(struct sock *sk) |
| 530 | { |
| 531 | struct sk_buff *skb; |
| 532 | struct dccp_sock *dp = dccp_sk(sk); |
| 533 | struct dst_entry *dst = __sk_dst_get(sk); |
| 534 | struct inet_connection_sock *icsk = inet_csk(sk); |
| 535 | |
| 536 | sk->sk_err = 0; |
| 537 | sock_reset_flag(sk, SOCK_DONE); |
| 538 | |
| 539 | dccp_sync_mss(sk, dst_mtu(dst)); |
| 540 | |
| 541 | /* do not connect if feature negotiation setup fails */ |
| 542 | if (dccp_feat_finalise_settings(dccp_sk(sk))) |
| 543 | return -EPROTO; |
| 544 | |
| 545 | /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ |
| 546 | dp->dccps_gar = dp->dccps_iss; |
| 547 | |
| 548 | skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); |
| 549 | if (unlikely(skb == NULL)) |
| 550 | return -ENOBUFS; |
| 551 | |
| 552 | /* Reserve space for headers. */ |
| 553 | skb_reserve(skb, sk->sk_prot->max_header); |
| 554 | |
| 555 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST; |
| 556 | |
| 557 | dccp_transmit_skb(sk, dccp_skb_entail(sk, skb)); |
| 558 | DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS); |
| 559 | |
| 560 | /* Timer for repeating the REQUEST until an answer. */ |
| 561 | icsk->icsk_retransmits = 0; |
| 562 | inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, |
| 563 | icsk->icsk_rto, DCCP_RTO_MAX); |
| 564 | return 0; |
| 565 | } |
| 566 | |
| 567 | EXPORT_SYMBOL_GPL(dccp_connect); |
| 568 | |
| 569 | void dccp_send_ack(struct sock *sk) |
| 570 | { |
| 571 | /* If we have been reset, we may not send again. */ |
| 572 | if (sk->sk_state != DCCP_CLOSED) { |
| 573 | struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, |
| 574 | GFP_ATOMIC); |
| 575 | |
| 576 | if (skb == NULL) { |
| 577 | inet_csk_schedule_ack(sk); |
| 578 | inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; |
| 579 | inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, |
| 580 | TCP_DELACK_MAX, |
| 581 | DCCP_RTO_MAX); |
| 582 | return; |
| 583 | } |
| 584 | |
| 585 | /* Reserve space for headers */ |
| 586 | skb_reserve(skb, sk->sk_prot->max_header); |
| 587 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_ACK; |
| 588 | dccp_transmit_skb(sk, skb); |
| 589 | } |
| 590 | } |
| 591 | |
| 592 | EXPORT_SYMBOL_GPL(dccp_send_ack); |
| 593 | |
| 594 | #if 0 |
| 595 | /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */ |
| 596 | void dccp_send_delayed_ack(struct sock *sk) |
| 597 | { |
| 598 | struct inet_connection_sock *icsk = inet_csk(sk); |
| 599 | /* |
| 600 | * FIXME: tune this timer. elapsed time fixes the skew, so no problem |
| 601 | * with using 2s, and active senders also piggyback the ACK into a |
| 602 | * DATAACK packet, so this is really for quiescent senders. |
| 603 | */ |
| 604 | unsigned long timeout = jiffies + 2 * HZ; |
| 605 | |
| 606 | /* Use new timeout only if there wasn't a older one earlier. */ |
| 607 | if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { |
| 608 | /* If delack timer was blocked or is about to expire, |
| 609 | * send ACK now. |
| 610 | * |
| 611 | * FIXME: check the "about to expire" part |
| 612 | */ |
| 613 | if (icsk->icsk_ack.blocked) { |
| 614 | dccp_send_ack(sk); |
| 615 | return; |
| 616 | } |
| 617 | |
| 618 | if (!time_before(timeout, icsk->icsk_ack.timeout)) |
| 619 | timeout = icsk->icsk_ack.timeout; |
| 620 | } |
| 621 | icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; |
| 622 | icsk->icsk_ack.timeout = timeout; |
| 623 | sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); |
| 624 | } |
| 625 | #endif |
| 626 | |
| 627 | void dccp_send_sync(struct sock *sk, const u64 ackno, |
| 628 | const enum dccp_pkt_type pkt_type) |
| 629 | { |
| 630 | /* |
| 631 | * We are not putting this on the write queue, so |
| 632 | * dccp_transmit_skb() will set the ownership to this |
| 633 | * sock. |
| 634 | */ |
| 635 | struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC); |
| 636 | |
| 637 | if (skb == NULL) { |
| 638 | /* FIXME: how to make sure the sync is sent? */ |
| 639 | DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type)); |
| 640 | return; |
| 641 | } |
| 642 | |
| 643 | /* Reserve space for headers and prepare control bits. */ |
| 644 | skb_reserve(skb, sk->sk_prot->max_header); |
| 645 | DCCP_SKB_CB(skb)->dccpd_type = pkt_type; |
| 646 | DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno; |
| 647 | |
| 648 | /* |
| 649 | * Clear the flag in case the Sync was scheduled for out-of-band data, |
| 650 | * such as carrying a long Ack Vector. |
| 651 | */ |
| 652 | dccp_sk(sk)->dccps_sync_scheduled = 0; |
| 653 | |
| 654 | dccp_transmit_skb(sk, skb); |
| 655 | } |
| 656 | |
| 657 | EXPORT_SYMBOL_GPL(dccp_send_sync); |
| 658 | |
| 659 | /* |
| 660 | * Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This |
| 661 | * cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under |
| 662 | * any circumstances. |
| 663 | */ |
| 664 | void dccp_send_close(struct sock *sk, const int active) |
| 665 | { |
| 666 | struct dccp_sock *dp = dccp_sk(sk); |
| 667 | struct sk_buff *skb; |
| 668 | const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC; |
| 669 | |
| 670 | skb = alloc_skb(sk->sk_prot->max_header, prio); |
| 671 | if (skb == NULL) |
| 672 | return; |
| 673 | |
| 674 | /* Reserve space for headers and prepare control bits. */ |
| 675 | skb_reserve(skb, sk->sk_prot->max_header); |
| 676 | if (dp->dccps_role == DCCP_ROLE_SERVER && !dp->dccps_server_timewait) |
| 677 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSEREQ; |
| 678 | else |
| 679 | DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE; |
| 680 | |
| 681 | if (active) { |
| 682 | skb = dccp_skb_entail(sk, skb); |
| 683 | /* |
| 684 | * Retransmission timer for active-close: RFC 4340, 8.3 requires |
| 685 | * to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ |
| 686 | * state can be left. The initial timeout is 2 RTTs. |
| 687 | * Since RTT measurement is done by the CCIDs, there is no easy |
| 688 | * way to get an RTT sample. The fallback RTT from RFC 4340, 3.4 |
| 689 | * is too low (200ms); we use a high value to avoid unnecessary |
| 690 | * retransmissions when the link RTT is > 0.2 seconds. |
| 691 | * FIXME: Let main module sample RTTs and use that instead. |
| 692 | */ |
| 693 | inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, |
| 694 | DCCP_TIMEOUT_INIT, DCCP_RTO_MAX); |
| 695 | } |
| 696 | dccp_transmit_skb(sk, skb); |
| 697 | } |