input.c 21.6 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
/*
 *  net/dccp/input.c
 *
 *  An implementation of the DCCP protocol
 *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 */

#include <linux/dccp.h>
#include <linux/skbuff.h>
#include <linux/slab.h>

#include <net/sock.h>

#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"

/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
int sysctl_dccp_sync_ratelimit	__read_mostly = HZ / 8;

static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb)
{
	__skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4);
	__skb_queue_tail(&sk->sk_receive_queue, skb);
	skb_set_owner_r(skb, sk);
	sk->sk_data_ready(sk, 0);
}

static void dccp_fin(struct sock *sk, struct sk_buff *skb)
{
	/*
	 * On receiving Close/CloseReq, both RD/WR shutdown are performed.
	 * RFC 4340, 8.3 says that we MAY send further Data/DataAcks after
	 * receiving the closing segment, but there is no guarantee that such
	 * data will be processed at all.
	 */
	sk->sk_shutdown = SHUTDOWN_MASK;
	sock_set_flag(sk, SOCK_DONE);
	dccp_enqueue_skb(sk, skb);
}

static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
{
	int queued = 0;

	switch (sk->sk_state) {
	/*
	 * We ignore Close when received in one of the following states:
	 *  - CLOSED		(may be a late or duplicate packet)
	 *  - PASSIVE_CLOSEREQ	(the peer has sent a CloseReq earlier)
	 *  - RESPOND		(already handled by dccp_check_req)
	 */
	case DCCP_CLOSING:
		/*
		 * Simultaneous-close: receiving a Close after sending one. This
		 * can happen if both client and server perform active-close and
		 * will result in an endless ping-pong of crossing and retrans-
		 * mitted Close packets, which only terminates when one of the
		 * nodes times out (min. 64 seconds). Quicker convergence can be
		 * achieved when one of the nodes acts as tie-breaker.
		 * This is ok as both ends are done with data transfer and each
		 * end is just waiting for the other to acknowledge termination.
		 */
		if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT)
			break;
		/* fall through */
	case DCCP_REQUESTING:
	case DCCP_ACTIVE_CLOSEREQ:
		dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
		dccp_done(sk);
		break;
	case DCCP_OPEN:
	case DCCP_PARTOPEN:
		/* Give waiting application a chance to read pending data */
		queued = 1;
		dccp_fin(sk, skb);
		dccp_set_state(sk, DCCP_PASSIVE_CLOSE);
		/* fall through */
	case DCCP_PASSIVE_CLOSE:
		/*
		 * Retransmitted Close: we have already enqueued the first one.
		 */
		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
	}
	return queued;
}

static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
{
	int queued = 0;

	/*
	 *   Step 7: Check for unexpected packet types
	 *      If (S.is_server and P.type == CloseReq)
	 *	  Send Sync packet acknowledging P.seqno
	 *	  Drop packet and return
	 */
	if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) {
		dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
		return queued;
	}

	/* Step 13: process relevant Client states < CLOSEREQ */
	switch (sk->sk_state) {
	case DCCP_REQUESTING:
		dccp_send_close(sk, 0);
		dccp_set_state(sk, DCCP_CLOSING);
		break;
	case DCCP_OPEN:
	case DCCP_PARTOPEN:
		/* Give waiting application a chance to read pending data */
		queued = 1;
		dccp_fin(sk, skb);
		dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ);
		/* fall through */
	case DCCP_PASSIVE_CLOSEREQ:
		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
	}
	return queued;
}

static u16 dccp_reset_code_convert(const u8 code)
{
	const u16 error_code[] = {
	[DCCP_RESET_CODE_CLOSED]	     = 0,	/* normal termination */
	[DCCP_RESET_CODE_UNSPECIFIED]	     = 0,	/* nothing known */
	[DCCP_RESET_CODE_ABORTED]	     = ECONNRESET,

	[DCCP_RESET_CODE_NO_CONNECTION]	     = ECONNREFUSED,
	[DCCP_RESET_CODE_CONNECTION_REFUSED] = ECONNREFUSED,
	[DCCP_RESET_CODE_TOO_BUSY]	     = EUSERS,
	[DCCP_RESET_CODE_AGGRESSION_PENALTY] = EDQUOT,

	[DCCP_RESET_CODE_PACKET_ERROR]	     = ENOMSG,
	[DCCP_RESET_CODE_BAD_INIT_COOKIE]    = EBADR,
	[DCCP_RESET_CODE_BAD_SERVICE_CODE]   = EBADRQC,
	[DCCP_RESET_CODE_OPTION_ERROR]	     = EILSEQ,
	[DCCP_RESET_CODE_MANDATORY_ERROR]    = EOPNOTSUPP,
	};

	return code >= DCCP_MAX_RESET_CODES ? 0 : error_code[code];
}

static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb)
{
	u16 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code);

	sk->sk_err = err;

	/* Queue the equivalent of TCP fin so that dccp_recvmsg exits the loop */
	dccp_fin(sk, skb);

	if (err && !sock_flag(sk, SOCK_DEAD))
		sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
	dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
}

static void dccp_handle_ackvec_processing(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_ackvec *av = dccp_sk(sk)->dccps_hc_rx_ackvec;

	if (av == NULL)
		return;
	if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
		dccp_ackvec_clear_state(av, DCCP_SKB_CB(skb)->dccpd_ack_seq);
	dccp_ackvec_input(av, skb);
}

static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb)
{
	const struct dccp_sock *dp = dccp_sk(sk);

	/* Don't deliver to RX CCID when node has shut down read end. */
	if (!(sk->sk_shutdown & RCV_SHUTDOWN))
		ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
	/*
	 * Until the TX queue has been drained, we can not honour SHUT_WR, since
	 * we need received feedback as input to adjust congestion control.
	 */
	if (sk->sk_write_queue.qlen > 0 || !(sk->sk_shutdown & SEND_SHUTDOWN))
		ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
}

static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
{
	const struct dccp_hdr *dh = dccp_hdr(skb);
	struct dccp_sock *dp = dccp_sk(sk);
	u64 lswl, lawl, seqno = DCCP_SKB_CB(skb)->dccpd_seq,
			ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;

	/*
	 *   Step 5: Prepare sequence numbers for Sync
	 *     If P.type == Sync or P.type == SyncAck,
	 *	  If S.AWL <= P.ackno <= S.AWH and P.seqno >= S.SWL,
	 *	     / * P is valid, so update sequence number variables
	 *		 accordingly.  After this update, P will pass the tests
	 *		 in Step 6.  A SyncAck is generated if necessary in
	 *		 Step 15 * /
	 *	     Update S.GSR, S.SWL, S.SWH
	 *	  Otherwise,
	 *	     Drop packet and return
	 */
	if (dh->dccph_type == DCCP_PKT_SYNC ||
	    dh->dccph_type == DCCP_PKT_SYNCACK) {
		if (between48(ackno, dp->dccps_awl, dp->dccps_awh) &&
		    dccp_delta_seqno(dp->dccps_swl, seqno) >= 0)
			dccp_update_gsr(sk, seqno);
		else
			return -1;
	}

	/*
	 *   Step 6: Check sequence numbers
	 *      Let LSWL = S.SWL and LAWL = S.AWL
	 *      If P.type == CloseReq or P.type == Close or P.type == Reset,
	 *	  LSWL := S.GSR + 1, LAWL := S.GAR
	 *      If LSWL <= P.seqno <= S.SWH
	 *	     and (P.ackno does not exist or LAWL <= P.ackno <= S.AWH),
	 *	  Update S.GSR, S.SWL, S.SWH
	 *	  If P.type != Sync,
	 *	     Update S.GAR
	 */
	lswl = dp->dccps_swl;
	lawl = dp->dccps_awl;

	if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
	    dh->dccph_type == DCCP_PKT_CLOSE ||
	    dh->dccph_type == DCCP_PKT_RESET) {
		lswl = ADD48(dp->dccps_gsr, 1);
		lawl = dp->dccps_gar;
	}

	if (between48(seqno, lswl, dp->dccps_swh) &&
	    (ackno == DCCP_PKT_WITHOUT_ACK_SEQ ||
	     between48(ackno, lawl, dp->dccps_awh))) {
		dccp_update_gsr(sk, seqno);

		if (dh->dccph_type != DCCP_PKT_SYNC &&
		    ackno != DCCP_PKT_WITHOUT_ACK_SEQ &&
		    after48(ackno, dp->dccps_gar))
			dp->dccps_gar = ackno;
	} else {
		unsigned long now = jiffies;
		/*
		 *   Step 6: Check sequence numbers
		 *      Otherwise,
		 *         If P.type == Reset,
		 *            Send Sync packet acknowledging S.GSR
		 *         Otherwise,
		 *            Send Sync packet acknowledging P.seqno
		 *      Drop packet and return
		 *
		 *   These Syncs are rate-limited as per RFC 4340, 7.5.4:
		 *   at most 1 / (dccp_sync_rate_limit * HZ) Syncs per second.
		 */
		if (time_before(now, (dp->dccps_rate_last +
				      sysctl_dccp_sync_ratelimit)))
			return -1;

		DCCP_WARN("Step 6 failed for %s packet, "
			  "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
			  "(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
			  "sending SYNC...\n",  dccp_packet_name(dh->dccph_type),
			  (unsigned long long) lswl, (unsigned long long) seqno,
			  (unsigned long long) dp->dccps_swh,
			  (ackno == DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist"
							      : "exists",
			  (unsigned long long) lawl, (unsigned long long) ackno,
			  (unsigned long long) dp->dccps_awh);

		dp->dccps_rate_last = now;

		if (dh->dccph_type == DCCP_PKT_RESET)
			seqno = dp->dccps_gsr;
		dccp_send_sync(sk, seqno, DCCP_PKT_SYNC);
		return -1;
	}

	return 0;
}

static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
				  const struct dccp_hdr *dh, const unsigned int len)
{
	struct dccp_sock *dp = dccp_sk(sk);

	switch (dccp_hdr(skb)->dccph_type) {
	case DCCP_PKT_DATAACK:
	case DCCP_PKT_DATA:
		/*
		 * FIXME: schedule DATA_DROPPED (RFC 4340, 11.7.2) if and when
		 * - sk_shutdown == RCV_SHUTDOWN, use Code 1, "Not Listening"
		 * - sk_receive_queue is full, use Code 2, "Receive Buffer"
		 */
		dccp_enqueue_skb(sk, skb);
		return 0;
	case DCCP_PKT_ACK:
		goto discard;
	case DCCP_PKT_RESET:
		/*
		 *  Step 9: Process Reset
		 *	If P.type == Reset,
		 *		Tear down connection
		 *		S.state := TIMEWAIT
		 *		Set TIMEWAIT timer
		 *		Drop packet and return
		 */
		dccp_rcv_reset(sk, skb);
		return 0;
	case DCCP_PKT_CLOSEREQ:
		if (dccp_rcv_closereq(sk, skb))
			return 0;
		goto discard;
	case DCCP_PKT_CLOSE:
		if (dccp_rcv_close(sk, skb))
			return 0;
		goto discard;
	case DCCP_PKT_REQUEST:
		/* Step 7
		 *   or (S.is_server and P.type == Response)
		 *   or (S.is_client and P.type == Request)
		 *   or (S.state >= OPEN and P.type == Request
		 *	and P.seqno >= S.OSR)
		 *    or (S.state >= OPEN and P.type == Response
		 *	and P.seqno >= S.OSR)
		 *    or (S.state == RESPOND and P.type == Data),
		 *  Send Sync packet acknowledging P.seqno
		 *  Drop packet and return
		 */
		if (dp->dccps_role != DCCP_ROLE_LISTEN)
			goto send_sync;
		goto check_seq;
	case DCCP_PKT_RESPONSE:
		if (dp->dccps_role != DCCP_ROLE_CLIENT)
			goto send_sync;
check_seq:
		if (dccp_delta_seqno(dp->dccps_osr,
				     DCCP_SKB_CB(skb)->dccpd_seq) >= 0) {
send_sync:
			dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
				       DCCP_PKT_SYNC);
		}
		break;
	case DCCP_PKT_SYNC:
		dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
			       DCCP_PKT_SYNCACK);
		/*
		 * From RFC 4340, sec. 5.7
		 *
		 * As with DCCP-Ack packets, DCCP-Sync and DCCP-SyncAck packets
		 * MAY have non-zero-length application data areas, whose
		 * contents receivers MUST ignore.
		 */
		goto discard;
	}

	DCCP_INC_STATS_BH(DCCP_MIB_INERRS);
discard:
	__kfree_skb(skb);
	return 0;
}

int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
			 const struct dccp_hdr *dh, const unsigned int len)
{
	if (dccp_check_seqno(sk, skb))
		goto discard;

	if (dccp_parse_options(sk, NULL, skb))
		return 1;

	dccp_handle_ackvec_processing(sk, skb);
	dccp_deliver_input_to_ccids(sk, skb);

	return __dccp_rcv_established(sk, skb, dh, len);
discard:
	__kfree_skb(skb);
	return 0;
}

EXPORT_SYMBOL_GPL(dccp_rcv_established);

static int dccp_rcv_request_sent_state_process(struct sock *sk,
					       struct sk_buff *skb,
					       const struct dccp_hdr *dh,
					       const unsigned int len)
{
	/*
	 *  Step 4: Prepare sequence numbers in REQUEST
	 *     If S.state == REQUEST,
	 *	  If (P.type == Response or P.type == Reset)
	 *		and S.AWL <= P.ackno <= S.AWH,
	 *	     / * Set sequence number variables corresponding to the
	 *		other endpoint, so P will pass the tests in Step 6 * /
	 *	     Set S.GSR, S.ISR, S.SWL, S.SWH
	 *	     / * Response processing continues in Step 10; Reset
	 *		processing continues in Step 9 * /
	*/
	if (dh->dccph_type == DCCP_PKT_RESPONSE) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		struct dccp_sock *dp = dccp_sk(sk);
		long tstamp = dccp_timestamp();

		if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
			       dp->dccps_awl, dp->dccps_awh)) {
			dccp_pr_debug("invalid ackno: S.AWL=%llu, "
				      "P.ackno=%llu, S.AWH=%llu\n",
				      (unsigned long long)dp->dccps_awl,
			   (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
				      (unsigned long long)dp->dccps_awh);
			goto out_invalid_packet;
		}

		/*
		 * If option processing (Step 8) failed, return 1 here so that
		 * dccp_v4_do_rcv() sends a Reset. The Reset code depends on
		 * the option type and is set in dccp_parse_options().
		 */
		if (dccp_parse_options(sk, NULL, skb))
			return 1;

		/* Obtain usec RTT sample from SYN exchange (used by TFRC). */
		if (likely(dp->dccps_options_received.dccpor_timestamp_echo))
			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
			    dp->dccps_options_received.dccpor_timestamp_echo));

		/* Stop the REQUEST timer */
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
		WARN_ON(sk->sk_send_head == NULL);
		kfree_skb(sk->sk_send_head);
		sk->sk_send_head = NULL;

		/*
		 * Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect
		 * and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH
		 * is done as part of activating the feature values below, since
		 * these settings depend on the local/remote Sequence Window
		 * features, which were undefined or not confirmed until now.
		 */
		dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;

		dccp_sync_mss(sk, icsk->icsk_pmtu_cookie);

		/*
		 *    Step 10: Process REQUEST state (second part)
		 *       If S.state == REQUEST,
		 *	  / * If we get here, P is a valid Response from the
		 *	      server (see Step 4), and we should move to
		 *	      PARTOPEN state. PARTOPEN means send an Ack,
		 *	      don't send Data packets, retransmit Acks
		 *	      periodically, and always include any Init Cookie
		 *	      from the Response * /
		 *	  S.state := PARTOPEN
		 *	  Set PARTOPEN timer
		 *	  Continue with S.state == PARTOPEN
		 *	  / * Step 12 will send the Ack completing the
		 *	      three-way handshake * /
		 */
		dccp_set_state(sk, DCCP_PARTOPEN);

		/*
		 * If feature negotiation was successful, activate features now;
		 * an activation failure means that this host could not activate
		 * one ore more features (e.g. insufficient memory), which would
		 * leave at least one feature in an undefined state.
		 */
		if (dccp_feat_activate_values(sk, &dp->dccps_featneg))
			goto unable_to_proceed;

		/* Make sure socket is routed, for correct metrics. */
		icsk->icsk_af_ops->rebuild_header(sk);

		if (!sock_flag(sk, SOCK_DEAD)) {
			sk->sk_state_change(sk);
			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
		}

		if (sk->sk_write_pending || icsk->icsk_ack.pingpong ||
		    icsk->icsk_accept_queue.rskq_defer_accept) {
			/* Save one ACK. Data will be ready after
			 * several ticks, if write_pending is set.
			 *
			 * It may be deleted, but with this feature tcpdumps
			 * look so _wonderfully_ clever, that I was not able
			 * to stand against the temptation 8)     --ANK
			 */
			/*
			 * OK, in DCCP we can as well do a similar trick, its
			 * even in the draft, but there is no need for us to
			 * schedule an ack here, as dccp_sendmsg does this for
			 * us, also stated in the draft. -acme
			 */
			__kfree_skb(skb);
			return 0;
		}
		dccp_send_ack(sk);
		return -1;
	}

out_invalid_packet:
	/* dccp_v4_do_rcv will send a reset */
	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
	return 1;

unable_to_proceed:
	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_ABORTED;
	/*
	 * We mark this socket as no longer usable, so that the loop in
	 * dccp_sendmsg() terminates and the application gets notified.
	 */
	dccp_set_state(sk, DCCP_CLOSED);
	sk->sk_err = ECOMM;
	return 1;
}

static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
						   struct sk_buff *skb,
						   const struct dccp_hdr *dh,
						   const unsigned int len)
{
	struct dccp_sock *dp = dccp_sk(sk);
	u32 sample = dp->dccps_options_received.dccpor_timestamp_echo;
	int queued = 0;

	switch (dh->dccph_type) {
	case DCCP_PKT_RESET:
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
		break;
	case DCCP_PKT_DATA:
		if (sk->sk_state == DCCP_RESPOND)
			break;
	case DCCP_PKT_DATAACK:
	case DCCP_PKT_ACK:
		/*
		 * FIXME: we should be reseting the PARTOPEN (DELACK) timer
		 * here but only if we haven't used the DELACK timer for
		 * something else, like sending a delayed ack for a TIMESTAMP
		 * echo, etc, for now were not clearing it, sending an extra
		 * ACK when there is nothing else to do in DELACK is not a big
		 * deal after all.
		 */

		/* Stop the PARTOPEN timer */
		if (sk->sk_state == DCCP_PARTOPEN)
			inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);

		/* Obtain usec RTT sample from SYN exchange (used by TFRC). */
		if (likely(sample)) {
			long delta = dccp_timestamp() - sample;

			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * delta);
		}

		dp->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq;
		dccp_set_state(sk, DCCP_OPEN);

		if (dh->dccph_type == DCCP_PKT_DATAACK ||
		    dh->dccph_type == DCCP_PKT_DATA) {
			__dccp_rcv_established(sk, skb, dh, len);
			queued = 1; /* packet was queued
				       (by __dccp_rcv_established) */
		}
		break;
	}

	return queued;
}

int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
			   struct dccp_hdr *dh, unsigned int len)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
	const int old_state = sk->sk_state;
	int queued = 0;

	/*
	 *  Step 3: Process LISTEN state
	 *
	 *     If S.state == LISTEN,
	 *	 If P.type == Request or P contains a valid Init Cookie option,
	 *	      (* Must scan the packet's options to check for Init
	 *		 Cookies.  Only Init Cookies are processed here,
	 *		 however; other options are processed in Step 8.  This
	 *		 scan need only be performed if the endpoint uses Init
	 *		 Cookies *)
	 *	      (* Generate a new socket and switch to that socket *)
	 *	      Set S := new socket for this port pair
	 *	      S.state = RESPOND
	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
	 *	      Initialize S.GAR := S.ISS
	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init
	 *	      Cookies Continue with S.state == RESPOND
	 *	      (* A Response packet will be generated in Step 11 *)
	 *	 Otherwise,
	 *	      Generate Reset(No Connection) unless P.type == Reset
	 *	      Drop packet and return
	 */
	if (sk->sk_state == DCCP_LISTEN) {
		if (dh->dccph_type == DCCP_PKT_REQUEST) {
			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
								    skb) < 0)
				return 1;
			goto discard;
		}
		if (dh->dccph_type == DCCP_PKT_RESET)
			goto discard;

		/* Caller (dccp_v4_do_rcv) will send Reset */
		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
		return 1;
	} else if (sk->sk_state == DCCP_CLOSED) {
		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
		return 1;
	}

	/* Step 6: Check sequence numbers (omitted in LISTEN/REQUEST state) */
	if (sk->sk_state != DCCP_REQUESTING && dccp_check_seqno(sk, skb))
		goto discard;

	/*
	 *   Step 7: Check for unexpected packet types
	 *      If (S.is_server and P.type == Response)
	 *	    or (S.is_client and P.type == Request)
	 *	    or (S.state == RESPOND and P.type == Data),
	 *	  Send Sync packet acknowledging P.seqno
	 *	  Drop packet and return
	 */
	if ((dp->dccps_role != DCCP_ROLE_CLIENT &&
	     dh->dccph_type == DCCP_PKT_RESPONSE) ||
	    (dp->dccps_role == DCCP_ROLE_CLIENT &&
	     dh->dccph_type == DCCP_PKT_REQUEST) ||
	    (sk->sk_state == DCCP_RESPOND && dh->dccph_type == DCCP_PKT_DATA)) {
		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC);
		goto discard;
	}

	/*  Step 8: Process options */
	if (dccp_parse_options(sk, NULL, skb))
		return 1;

	/*
	 *  Step 9: Process Reset
	 *	If P.type == Reset,
	 *		Tear down connection
	 *		S.state := TIMEWAIT
	 *		Set TIMEWAIT timer
	 *		Drop packet and return
	 */
	if (dh->dccph_type == DCCP_PKT_RESET) {
		dccp_rcv_reset(sk, skb);
		return 0;
	} else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) {	/* Step 13 */
		if (dccp_rcv_closereq(sk, skb))
			return 0;
		goto discard;
	} else if (dh->dccph_type == DCCP_PKT_CLOSE) {		/* Step 14 */
		if (dccp_rcv_close(sk, skb))
			return 0;
		goto discard;
	}

	switch (sk->sk_state) {
	case DCCP_REQUESTING:
		queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
		if (queued >= 0)
			return queued;

		__kfree_skb(skb);
		return 0;

	case DCCP_PARTOPEN:
		/* Step 8: if using Ack Vectors, mark packet acknowledgeable */
		dccp_handle_ackvec_processing(sk, skb);
		dccp_deliver_input_to_ccids(sk, skb);
		/* fall through */
	case DCCP_RESPOND:
		queued = dccp_rcv_respond_partopen_state_process(sk, skb,
								 dh, len);
		break;
	}

	if (dh->dccph_type == DCCP_PKT_ACK ||
	    dh->dccph_type == DCCP_PKT_DATAACK) {
		switch (old_state) {
		case DCCP_PARTOPEN:
			sk->sk_state_change(sk);
			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
			break;
		}
	} else if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
		goto discard;
	}

	if (!queued) {
discard:
		__kfree_skb(skb);
	}
	return 0;
}

EXPORT_SYMBOL_GPL(dccp_rcv_state_process);

/**
 *  dccp_sample_rtt  -  Validate and finalise computation of RTT sample
 *  @delta:	number of microseconds between packet and acknowledgment
 *
 *  The routine is kept generic to work in different contexts. It should be
 *  called immediately when the ACK used for the RTT sample arrives.
 */
u32 dccp_sample_rtt(struct sock *sk, long delta)
{
	/* dccpor_elapsed_time is either zeroed out or set and > 0 */
	delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10;

	if (unlikely(delta <= 0)) {
		DCCP_WARN("unusable RTT sample %ld, using min\n", delta);
		return DCCP_SANE_RTT_MIN;
	}
	if (unlikely(delta > DCCP_SANE_RTT_MAX)) {
		DCCP_WARN("RTT sample %ld too large, using max\n", delta);
		return DCCP_SANE_RTT_MAX;
	}

	return delta;
}