ar-ack.c 34.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/* Management of Tx window, Tx resend, ACKs and out-of-sequence reception
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * 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/module.h>
#include <linux/circ_buf.h>
#include <linux/net.h>
#include <linux/skbuff.h>
16
#include <linux/slab.h>
17 18 19 20 21
#include <linux/udp.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"

22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
/*
 * How long to wait before scheduling ACK generation after seeing a
 * packet with RXRPC_REQUEST_ACK set (in jiffies).
 */
unsigned rxrpc_requested_ack_delay = 1;

/*
 * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
 *
 * We use this when we've received new data packets.  If those packets aren't
 * all consumed within this time we will send a DELAY ACK if an ACK was not
 * requested to let the sender know it doesn't need to resend.
 */
unsigned rxrpc_soft_ack_delay = 1 * HZ;

/*
 * How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
 *
 * We use this when we've consumed some previously soft-ACK'd packets when
 * further packets aren't immediately received to decide when to send an IDLE
 * ACK let the other end know that it can free up its Tx buffer space.
 */
D
David Howells 已提交
44
unsigned rxrpc_idle_ack_delay = 0.5 * HZ;
45

46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
/*
 * Receive window size in packets.  This indicates the maximum number of
 * unconsumed received packets we're willing to retain in memory.  Once this
 * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further
 * packets.
 */
unsigned rxrpc_rx_window_size = 32;

/*
 * Maximum Rx MTU size.  This indicates to the sender the size of jumbo packet
 * made by gluing normal packets together that we're willing to handle.
 */
unsigned rxrpc_rx_mtu = 5692;

/*
 * The maximum number of fragments in a received jumbo packet that we tell the
 * sender that we're willing to handle.
 */
unsigned rxrpc_rx_jumbo_max = 4;

66 67 68 69 70 71 72 73 74 75 76
static const char *rxrpc_acks(u8 reason)
{
	static const char *const str[] = {
		"---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY",
		"IDL", "-?-"
	};

	if (reason >= ARRAY_SIZE(str))
		reason = ARRAY_SIZE(str) - 1;
	return str[reason];
}
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92

static const s8 rxrpc_ack_priority[] = {
	[0]				= 0,
	[RXRPC_ACK_DELAY]		= 1,
	[RXRPC_ACK_REQUESTED]		= 2,
	[RXRPC_ACK_IDLE]		= 3,
	[RXRPC_ACK_PING_RESPONSE]	= 4,
	[RXRPC_ACK_DUPLICATE]		= 5,
	[RXRPC_ACK_OUT_OF_SEQUENCE]	= 6,
	[RXRPC_ACK_EXCEEDS_WINDOW]	= 7,
	[RXRPC_ACK_NOSPACE]		= 8,
};

/*
 * propose an ACK be sent
 */
93
void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
94 95 96 97 98 99 100 101
			 __be32 serial, bool immediate)
{
	unsigned long expiry;
	s8 prior = rxrpc_ack_priority[ack_reason];

	ASSERTCMP(prior, >, 0);

	_enter("{%d},%s,%%%x,%u",
102
	       call->debug_id, rxrpc_acks(ack_reason), ntohl(serial),
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
	       immediate);

	if (prior < rxrpc_ack_priority[call->ackr_reason]) {
		if (immediate)
			goto cancel_timer;
		return;
	}

	/* update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
	 * numbers */
	if (prior == rxrpc_ack_priority[call->ackr_reason]) {
		if (prior <= 4)
			call->ackr_serial = serial;
		if (immediate)
			goto cancel_timer;
		return;
	}

	call->ackr_reason = ack_reason;
	call->ackr_serial = serial;

	switch (ack_reason) {
	case RXRPC_ACK_DELAY:
		_debug("run delay timer");
127 128
		expiry = rxrpc_soft_ack_delay;
		goto run_timer;
129 130 131 132

	case RXRPC_ACK_IDLE:
		if (!immediate) {
			_debug("run defer timer");
133
			expiry = rxrpc_idle_ack_delay;
134 135 136 137 138
			goto run_timer;
		}
		goto cancel_timer;

	case RXRPC_ACK_REQUESTED:
139 140
		expiry = rxrpc_requested_ack_delay;
		if (!expiry)
141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
			goto cancel_timer;
		if (!immediate || serial == cpu_to_be32(1)) {
			_debug("run defer timer");
			goto run_timer;
		}

	default:
		_debug("immediate ACK");
		goto cancel_timer;
	}

run_timer:
	expiry += jiffies;
	if (!timer_pending(&call->ack_timer) ||
	    time_after(call->ack_timer.expires, expiry))
		mod_timer(&call->ack_timer, expiry);
	return;

cancel_timer:
	_debug("cancel timer %%%u", ntohl(serial));
	try_to_del_timer_sync(&call->ack_timer);
	read_lock_bh(&call->state_lock);
	if (call->state <= RXRPC_CALL_COMPLETE &&
	    !test_and_set_bit(RXRPC_CALL_ACK, &call->events))
165
		rxrpc_queue_call(call);
166 167 168 169 170 171
	read_unlock_bh(&call->state_lock);
}

/*
 * propose an ACK be sent, locking the call structure
 */
172
void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
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
		       __be32 serial, bool immediate)
{
	s8 prior = rxrpc_ack_priority[ack_reason];

	if (prior > rxrpc_ack_priority[call->ackr_reason]) {
		spin_lock_bh(&call->lock);
		__rxrpc_propose_ACK(call, ack_reason, serial, immediate);
		spin_unlock_bh(&call->lock);
	}
}

/*
 * set the resend timer
 */
static void rxrpc_set_resend(struct rxrpc_call *call, u8 resend,
			     unsigned long resend_at)
{
	read_lock_bh(&call->state_lock);
	if (call->state >= RXRPC_CALL_COMPLETE)
		resend = 0;

	if (resend & 1) {
		_debug("SET RESEND");
		set_bit(RXRPC_CALL_RESEND, &call->events);
	}

	if (resend & 2) {
		_debug("MODIFY RESEND TIMER");
		set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
		mod_timer(&call->resend_timer, resend_at);
	} else {
		_debug("KILL RESEND TIMER");
		del_timer_sync(&call->resend_timer);
		clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events);
		clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
	}
	read_unlock_bh(&call->state_lock);
}

/*
 * resend packets
 */
static void rxrpc_resend(struct rxrpc_call *call)
{
	struct rxrpc_skb_priv *sp;
	struct rxrpc_header *hdr;
	struct sk_buff *txb;
	unsigned long *p_txb, resend_at;
221 222
	bool stop;
	int loop;
223 224 225 226 227 228 229
	u8 resend;

	_enter("{%d,%d,%d,%d},",
	       call->acks_hard, call->acks_unacked,
	       atomic_read(&call->sequence),
	       CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz));

230
	stop = false;
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
	resend = 0;
	resend_at = 0;

	for (loop = call->acks_tail;
	     loop != call->acks_head || stop;
	     loop = (loop + 1) &  (call->acks_winsz - 1)
	     ) {
		p_txb = call->acks_window + loop;
		smp_read_barrier_depends();
		if (*p_txb & 1)
			continue;

		txb = (struct sk_buff *) *p_txb;
		sp = rxrpc_skb(txb);

		if (sp->need_resend) {
247
			sp->need_resend = false;
248 249 250 251 252 253 254 255 256 257 258

			/* each Tx packet has a new serial number */
			sp->hdr.serial =
				htonl(atomic_inc_return(&call->conn->serial));

			hdr = (struct rxrpc_header *) txb->head;
			hdr->serial = sp->hdr.serial;

			_proto("Tx DATA %%%u { #%d }",
			       ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
			if (rxrpc_send_packet(call->conn->trans, txb) < 0) {
259
				stop = true;
260 261 262
				sp->resend_at = jiffies + 3;
			} else {
				sp->resend_at =
263
					jiffies + rxrpc_resend_timeout;
264 265 266 267
			}
		}

		if (time_after_eq(jiffies + 1, sp->resend_at)) {
268
			sp->need_resend = true;
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
			resend |= 1;
		} else if (resend & 2) {
			if (time_before(sp->resend_at, resend_at))
				resend_at = sp->resend_at;
		} else {
			resend_at = sp->resend_at;
			resend |= 2;
		}
	}

	rxrpc_set_resend(call, resend, resend_at);
	_leave("");
}

/*
 * handle resend timer expiry
 */
static void rxrpc_resend_timer(struct rxrpc_call *call)
{
	struct rxrpc_skb_priv *sp;
	struct sk_buff *txb;
	unsigned long *p_txb, resend_at;
	int loop;
	u8 resend;

	_enter("%d,%d,%d",
	       call->acks_tail, call->acks_unacked, call->acks_head);

297 298 299
	if (call->state >= RXRPC_CALL_COMPLETE)
		return;

300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
	resend = 0;
	resend_at = 0;

	for (loop = call->acks_unacked;
	     loop != call->acks_head;
	     loop = (loop + 1) &  (call->acks_winsz - 1)
	     ) {
		p_txb = call->acks_window + loop;
		smp_read_barrier_depends();
		txb = (struct sk_buff *) (*p_txb & ~1);
		sp = rxrpc_skb(txb);

		ASSERT(!(*p_txb & 1));

		if (sp->need_resend) {
			;
		} else if (time_after_eq(jiffies + 1, sp->resend_at)) {
317
			sp->need_resend = true;
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
			resend |= 1;
		} else if (resend & 2) {
			if (time_before(sp->resend_at, resend_at))
				resend_at = sp->resend_at;
		} else {
			resend_at = sp->resend_at;
			resend |= 2;
		}
	}

	rxrpc_set_resend(call, resend, resend_at);
	_leave("");
}

/*
 * process soft ACKs of our transmitted packets
 * - these indicate packets the peer has or has not received, but hasn't yet
 *   given to the consumer, and so can still be discarded and re-requested
 */
static int rxrpc_process_soft_ACKs(struct rxrpc_call *call,
				   struct rxrpc_ackpacket *ack,
				   struct sk_buff *skb)
{
	struct rxrpc_skb_priv *sp;
	struct sk_buff *txb;
	unsigned long *p_txb, resend_at;
	int loop;
	u8 sacks[RXRPC_MAXACKS], resend;

	_enter("{%d,%d},{%d},",
	       call->acks_hard,
	       CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz),
	       ack->nAcks);

	if (skb_copy_bits(skb, 0, sacks, ack->nAcks) < 0)
		goto protocol_error;

	resend = 0;
	resend_at = 0;
	for (loop = 0; loop < ack->nAcks; loop++) {
		p_txb = call->acks_window;
		p_txb += (call->acks_tail + loop) & (call->acks_winsz - 1);
		smp_read_barrier_depends();
		txb = (struct sk_buff *) (*p_txb & ~1);
		sp = rxrpc_skb(txb);

		switch (sacks[loop]) {
		case RXRPC_ACK_TYPE_ACK:
366
			sp->need_resend = false;
367 368 369
			*p_txb |= 1;
			break;
		case RXRPC_ACK_TYPE_NACK:
370
			sp->need_resend = true;
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
			*p_txb &= ~1;
			resend = 1;
			break;
		default:
			_debug("Unsupported ACK type %d", sacks[loop]);
			goto protocol_error;
		}
	}

	smp_mb();
	call->acks_unacked = (call->acks_tail + loop) & (call->acks_winsz - 1);

	/* anything not explicitly ACK'd is implicitly NACK'd, but may just not
	 * have been received or processed yet by the far end */
	for (loop = call->acks_unacked;
	     loop != call->acks_head;
	     loop = (loop + 1) &  (call->acks_winsz - 1)
	     ) {
		p_txb = call->acks_window + loop;
		smp_read_barrier_depends();
		txb = (struct sk_buff *) (*p_txb & ~1);
		sp = rxrpc_skb(txb);

		if (*p_txb & 1) {
			/* packet must have been discarded */
396
			sp->need_resend = true;
397 398 399 400 401
			*p_txb &= ~1;
			resend |= 1;
		} else if (sp->need_resend) {
			;
		} else if (time_after_eq(jiffies + 1, sp->resend_at)) {
402
			sp->need_resend = true;
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
			resend |= 1;
		} else if (resend & 2) {
			if (time_before(sp->resend_at, resend_at))
				resend_at = sp->resend_at;
		} else {
			resend_at = sp->resend_at;
			resend |= 2;
		}
	}

	rxrpc_set_resend(call, resend, resend_at);
	_leave(" = 0");
	return 0;

protocol_error:
	_leave(" = -EPROTO");
	return -EPROTO;
}

/*
 * discard hard-ACK'd packets from the Tx window
 */
static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard)
{
	unsigned long _skb;
	int tail = call->acks_tail, old_tail;
	int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz);

	_enter("{%u,%u},%u", call->acks_hard, win, hard);

	ASSERTCMP(hard - call->acks_hard, <=, win);

	while (call->acks_hard < hard) {
		smp_read_barrier_depends();
		_skb = call->acks_window[tail] & ~1;
		rxrpc_free_skb((struct sk_buff *) _skb);
		old_tail = tail;
		tail = (tail + 1) & (call->acks_winsz - 1);
		call->acks_tail = tail;
		if (call->acks_unacked == old_tail)
			call->acks_unacked = tail;
		call->acks_hard++;
	}

	wake_up(&call->tx_waitq);
}

/*
 * clear the Tx window in the event of a failure
 */
static void rxrpc_clear_tx_window(struct rxrpc_call *call)
{
	rxrpc_rotate_tx_window(call, atomic_read(&call->sequence));
}

/*
 * drain the out of sequence received packet queue into the packet Rx queue
 */
static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call)
{
	struct rxrpc_skb_priv *sp;
	struct sk_buff *skb;
	bool terminal;
	int ret;

	_enter("{%d,%d}", call->rx_data_post, call->rx_first_oos);

	spin_lock_bh(&call->lock);

	ret = -ECONNRESET;
	if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
		goto socket_unavailable;

	skb = skb_dequeue(&call->rx_oos_queue);
	if (skb) {
		sp = rxrpc_skb(skb);

		_debug("drain OOS packet %d [%d]",
		       ntohl(sp->hdr.seq), call->rx_first_oos);

		if (ntohl(sp->hdr.seq) != call->rx_first_oos) {
			skb_queue_head(&call->rx_oos_queue, skb);
			call->rx_first_oos = ntohl(rxrpc_skb(skb)->hdr.seq);
			_debug("requeue %p {%u}", skb, call->rx_first_oos);
		} else {
			skb->mark = RXRPC_SKB_MARK_DATA;
			terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) &&
				!(sp->hdr.flags & RXRPC_CLIENT_INITIATED));
			ret = rxrpc_queue_rcv_skb(call, skb, true, terminal);
			BUG_ON(ret < 0);
			_debug("drain #%u", call->rx_data_post);
			call->rx_data_post++;

			/* find out what the next packet is */
			skb = skb_peek(&call->rx_oos_queue);
			if (skb)
				call->rx_first_oos =
					ntohl(rxrpc_skb(skb)->hdr.seq);
			else
				call->rx_first_oos = 0;
			_debug("peek %p {%u}", skb, call->rx_first_oos);
		}
	}

	ret = 0;
socket_unavailable:
	spin_unlock_bh(&call->lock);
	_leave(" = %d", ret);
	return ret;
}

/*
 * insert an out of sequence packet into the buffer
 */
static void rxrpc_insert_oos_packet(struct rxrpc_call *call,
				    struct sk_buff *skb)
{
	struct rxrpc_skb_priv *sp, *psp;
	struct sk_buff *p;
	u32 seq;

	sp = rxrpc_skb(skb);
	seq = ntohl(sp->hdr.seq);
	_enter(",,{%u}", seq);

	skb->destructor = rxrpc_packet_destructor;
	ASSERTCMP(sp->call, ==, NULL);
	sp->call = call;
	rxrpc_get_call(call);

	/* insert into the buffer in sequence order */
	spin_lock_bh(&call->lock);

	skb_queue_walk(&call->rx_oos_queue, p) {
		psp = rxrpc_skb(p);
		if (ntohl(psp->hdr.seq) > seq) {
			_debug("insert oos #%u before #%u",
			       seq, ntohl(psp->hdr.seq));
			skb_insert(p, skb, &call->rx_oos_queue);
			goto inserted;
		}
	}

	_debug("append oos #%u", seq);
	skb_queue_tail(&call->rx_oos_queue, skb);
inserted:

	/* we might now have a new front to the queue */
	if (call->rx_first_oos == 0 || seq < call->rx_first_oos)
		call->rx_first_oos = seq;

	read_lock(&call->state_lock);
	if (call->state < RXRPC_CALL_COMPLETE &&
	    call->rx_data_post == call->rx_first_oos) {
		_debug("drain rx oos now");
		set_bit(RXRPC_CALL_DRAIN_RX_OOS, &call->events);
	}
	read_unlock(&call->state_lock);

	spin_unlock_bh(&call->lock);
	_leave(" [stored #%u]", call->rx_first_oos);
}

/*
 * clear the Tx window on final ACK reception
 */
static void rxrpc_zap_tx_window(struct rxrpc_call *call)
{
	struct rxrpc_skb_priv *sp;
	struct sk_buff *skb;
	unsigned long _skb, *acks_window;
574
	u8 winsz = call->acks_winsz;
575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595
	int tail;

	acks_window = call->acks_window;
	call->acks_window = NULL;

	while (CIRC_CNT(call->acks_head, call->acks_tail, winsz) > 0) {
		tail = call->acks_tail;
		smp_read_barrier_depends();
		_skb = acks_window[tail] & ~1;
		smp_mb();
		call->acks_tail = (call->acks_tail + 1) & (winsz - 1);

		skb = (struct sk_buff *) _skb;
		sp = rxrpc_skb(skb);
		_debug("+++ clear Tx %u", ntohl(sp->hdr.seq));
		rxrpc_free_skb(skb);
	}

	kfree(acks_window);
}

596 597 598 599
/*
 * process the extra information that may be appended to an ACK packet
 */
static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
600
				  unsigned int latest, int nAcks)
601 602 603
{
	struct rxrpc_ackinfo ackinfo;
	struct rxrpc_peer *peer;
604
	unsigned int mtu;
605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627

	if (skb_copy_bits(skb, nAcks + 3, &ackinfo, sizeof(ackinfo)) < 0) {
		_leave(" [no ackinfo]");
		return;
	}

	_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
	       latest,
	       ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU),
	       ntohl(ackinfo.rwind), ntohl(ackinfo.jumbo_max));

	mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU));

	peer = call->conn->trans->peer;
	if (mtu < peer->maxdata) {
		spin_lock_bh(&peer->lock);
		peer->maxdata = mtu;
		peer->mtu = mtu + peer->hdrsize;
		spin_unlock_bh(&peer->lock);
		_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
	}
}

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
/*
 * process packets in the reception queue
 */
static int rxrpc_process_rx_queue(struct rxrpc_call *call,
				  u32 *_abort_code)
{
	struct rxrpc_ackpacket ack;
	struct rxrpc_skb_priv *sp;
	struct sk_buff *skb;
	bool post_ACK;
	int latest;
	u32 hard, tx;

	_enter("");

process_further:
	skb = skb_dequeue(&call->rx_queue);
	if (!skb)
		return -EAGAIN;

	_net("deferred skb %p", skb);

	sp = rxrpc_skb(skb);

	_debug("process %s [st %d]", rxrpc_pkts[sp->hdr.type], call->state);

	post_ACK = false;

	switch (sp->hdr.type) {
		/* data packets that wind up here have been received out of
		 * order, need security processing or are jumbo packets */
	case RXRPC_PACKET_TYPE_DATA:
		_proto("OOSQ DATA %%%u { #%u }",
		       ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));

		/* secured packets must be verified and possibly decrypted */
		if (rxrpc_verify_packet(call, skb, _abort_code) < 0)
			goto protocol_error;

		rxrpc_insert_oos_packet(call, skb);
		goto process_further;

		/* partial ACK to process */
	case RXRPC_PACKET_TYPE_ACK:
		if (skb_copy_bits(skb, 0, &ack, sizeof(ack)) < 0) {
			_debug("extraction failure");
			goto protocol_error;
		}
		if (!skb_pull(skb, sizeof(ack)))
			BUG();

		latest = ntohl(sp->hdr.serial);
		hard = ntohl(ack.firstPacket);
		tx = atomic_read(&call->sequence);

		_proto("Rx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
		       latest,
		       ntohs(ack.maxSkew),
		       hard,
		       ntohl(ack.previousPacket),
		       ntohl(ack.serial),
689
		       rxrpc_acks(ack.reason),
690 691
		       ack.nAcks);

692 693
		rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks);

694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
		if (ack.reason == RXRPC_ACK_PING) {
			_proto("Rx ACK %%%u PING Request", latest);
			rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
					  sp->hdr.serial, true);
		}

		/* discard any out-of-order or duplicate ACKs */
		if (latest - call->acks_latest <= 0) {
			_debug("discard ACK %d <= %d",
			       latest, call->acks_latest);
			goto discard;
		}
		call->acks_latest = latest;

		if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
		    call->state != RXRPC_CALL_CLIENT_AWAIT_REPLY &&
		    call->state != RXRPC_CALL_SERVER_SEND_REPLY &&
		    call->state != RXRPC_CALL_SERVER_AWAIT_ACK)
			goto discard;

		_debug("Tx=%d H=%u S=%d", tx, call->acks_hard, call->state);

		if (hard > 0) {
			if (hard - 1 > tx) {
				_debug("hard-ACK'd packet %d not transmitted"
				       " (%d top)",
				       hard - 1, tx);
				goto protocol_error;
			}

			if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY ||
			     call->state == RXRPC_CALL_SERVER_AWAIT_ACK) &&
			    hard > tx)
				goto all_acked;

			smp_rmb();
			rxrpc_rotate_tx_window(call, hard - 1);
		}

		if (ack.nAcks > 0) {
			if (hard - 1 + ack.nAcks > tx) {
				_debug("soft-ACK'd packet %d+%d not"
				       " transmitted (%d top)",
				       hard - 1, ack.nAcks, tx);
				goto protocol_error;
			}

			if (rxrpc_process_soft_ACKs(call, &ack, skb) < 0)
				goto protocol_error;
		}
		goto discard;

		/* complete ACK to process */
	case RXRPC_PACKET_TYPE_ACKALL:
		goto all_acked;

		/* abort and busy are handled elsewhere */
	case RXRPC_PACKET_TYPE_BUSY:
	case RXRPC_PACKET_TYPE_ABORT:
		BUG();

		/* connection level events - also handled elsewhere */
	case RXRPC_PACKET_TYPE_CHALLENGE:
	case RXRPC_PACKET_TYPE_RESPONSE:
	case RXRPC_PACKET_TYPE_DEBUG:
		BUG();
	}

	/* if we've had a hard ACK that covers all the packets we've sent, then
	 * that ends that phase of the operation */
all_acked:
	write_lock_bh(&call->state_lock);
	_debug("ack all %d", call->state);

	switch (call->state) {
	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
		call->state = RXRPC_CALL_CLIENT_RECV_REPLY;
		break;
	case RXRPC_CALL_SERVER_AWAIT_ACK:
		_debug("srv complete");
		call->state = RXRPC_CALL_COMPLETE;
		post_ACK = true;
		break;
	case RXRPC_CALL_CLIENT_SEND_REQUEST:
	case RXRPC_CALL_SERVER_RECV_REQUEST:
		goto protocol_error_unlock; /* can't occur yet */
	default:
		write_unlock_bh(&call->state_lock);
		goto discard; /* assume packet left over from earlier phase */
	}

	write_unlock_bh(&call->state_lock);

	/* if all the packets we sent are hard-ACK'd, then we can discard
	 * whatever we've got left */
	_debug("clear Tx %d",
	       CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz));

	del_timer_sync(&call->resend_timer);
	clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
	clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events);

	if (call->acks_window)
		rxrpc_zap_tx_window(call);

	if (post_ACK) {
		/* post the final ACK message for userspace to pick up */
		_debug("post ACK");
		skb->mark = RXRPC_SKB_MARK_FINAL_ACK;
		sp->call = call;
		rxrpc_get_call(call);
		spin_lock_bh(&call->lock);
		if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0)
			BUG();
		spin_unlock_bh(&call->lock);
		goto process_further;
	}

discard:
	rxrpc_free_skb(skb);
	goto process_further;

protocol_error_unlock:
	write_unlock_bh(&call->state_lock);
protocol_error:
	rxrpc_free_skb(skb);
	_leave(" = -EPROTO");
	return -EPROTO;
}

/*
 * post a message to the socket Rx queue for recvmsg() to pick up
 */
static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error,
			      bool fatal)
{
	struct rxrpc_skb_priv *sp;
	struct sk_buff *skb;
	int ret;

	_enter("{%d,%lx},%u,%u,%d",
	       call->debug_id, call->flags, mark, error, fatal);

	/* remove timers and things for fatal messages */
	if (fatal) {
		del_timer_sync(&call->resend_timer);
		del_timer_sync(&call->ack_timer);
		clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
	}

	if (mark != RXRPC_SKB_MARK_NEW_CALL &&
	    !test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
		_leave("[no userid]");
		return 0;
	}

	if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) {
		skb = alloc_skb(0, GFP_NOFS);
		if (!skb)
			return -ENOMEM;

		rxrpc_new_skb(skb);

		skb->mark = mark;

		sp = rxrpc_skb(skb);
		memset(sp, 0, sizeof(*sp));
		sp->error = error;
		sp->call = call;
		rxrpc_get_call(call);

		spin_lock_bh(&call->lock);
		ret = rxrpc_queue_rcv_skb(call, skb, true, fatal);
		spin_unlock_bh(&call->lock);
J
Julia Lawall 已提交
868
		BUG_ON(ret < 0);
869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887
	}

	return 0;
}

/*
 * handle background processing of incoming call packets and ACK / abort
 * generation
 */
void rxrpc_process_call(struct work_struct *work)
{
	struct rxrpc_call *call =
		container_of(work, struct rxrpc_call, processor);
	struct rxrpc_ackpacket ack;
	struct rxrpc_ackinfo ackinfo;
	struct rxrpc_header hdr;
	struct msghdr msg;
	struct kvec iov[5];
	unsigned long bits;
888
	__be32 data, pad;
889
	size_t len;
890
	int genbit, loop, nbit, ioc, ret, mtu;
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986
	u32 abort_code = RX_PROTOCOL_ERROR;
	u8 *acks = NULL;

	//printk("\n--------------------\n");
	_enter("{%d,%s,%lx} [%lu]",
	       call->debug_id, rxrpc_call_states[call->state], call->events,
	       (jiffies - call->creation_jif) / (HZ / 10));

	if (test_and_set_bit(RXRPC_CALL_PROC_BUSY, &call->flags)) {
		_debug("XXXXXXXXXXXXX RUNNING ON MULTIPLE CPUS XXXXXXXXXXXXX");
		return;
	}

	/* there's a good chance we're going to have to send a message, so set
	 * one up in advance */
	msg.msg_name	= &call->conn->trans->peer->srx.transport.sin;
	msg.msg_namelen	= sizeof(call->conn->trans->peer->srx.transport.sin);
	msg.msg_control	= NULL;
	msg.msg_controllen = 0;
	msg.msg_flags	= 0;

	hdr.epoch	= call->conn->epoch;
	hdr.cid		= call->cid;
	hdr.callNumber	= call->call_id;
	hdr.seq		= 0;
	hdr.type	= RXRPC_PACKET_TYPE_ACK;
	hdr.flags	= call->conn->out_clientflag;
	hdr.userStatus	= 0;
	hdr.securityIndex = call->conn->security_ix;
	hdr._rsvd	= 0;
	hdr.serviceId	= call->conn->service_id;

	memset(iov, 0, sizeof(iov));
	iov[0].iov_base	= &hdr;
	iov[0].iov_len	= sizeof(hdr);

	/* deal with events of a final nature */
	if (test_bit(RXRPC_CALL_RELEASE, &call->events)) {
		rxrpc_release_call(call);
		clear_bit(RXRPC_CALL_RELEASE, &call->events);
	}

	if (test_bit(RXRPC_CALL_RCVD_ERROR, &call->events)) {
		int error;

		clear_bit(RXRPC_CALL_CONN_ABORT, &call->events);
		clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events);
		clear_bit(RXRPC_CALL_ABORT, &call->events);

		error = call->conn->trans->peer->net_error;
		_debug("post net error %d", error);

		if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR,
				       error, true) < 0)
			goto no_mem;
		clear_bit(RXRPC_CALL_RCVD_ERROR, &call->events);
		goto kill_ACKs;
	}

	if (test_bit(RXRPC_CALL_CONN_ABORT, &call->events)) {
		ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE);

		clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events);
		clear_bit(RXRPC_CALL_ABORT, &call->events);

		_debug("post conn abort");

		if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
				       call->conn->error, true) < 0)
			goto no_mem;
		clear_bit(RXRPC_CALL_CONN_ABORT, &call->events);
		goto kill_ACKs;
	}

	if (test_bit(RXRPC_CALL_REJECT_BUSY, &call->events)) {
		hdr.type = RXRPC_PACKET_TYPE_BUSY;
		genbit = RXRPC_CALL_REJECT_BUSY;
		goto send_message;
	}

	if (test_bit(RXRPC_CALL_ABORT, &call->events)) {
		ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE);

		if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
				       ECONNABORTED, true) < 0)
			goto no_mem;
		hdr.type = RXRPC_PACKET_TYPE_ABORT;
		data = htonl(call->abort_code);
		iov[1].iov_base = &data;
		iov[1].iov_len = sizeof(data);
		genbit = RXRPC_CALL_ABORT;
		goto send_message;
	}

	if (test_bit(RXRPC_CALL_ACK_FINAL, &call->events)) {
		genbit = RXRPC_CALL_ACK_FINAL;
987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009

		ack.bufferSpace	= htons(8);
		ack.maxSkew	= 0;
		ack.serial	= 0;
		ack.reason	= RXRPC_ACK_IDLE;
		ack.nAcks	= 0;
		call->ackr_reason = 0;

		spin_lock_bh(&call->lock);
		ack.serial = call->ackr_serial;
		ack.previousPacket = call->ackr_prev_seq;
		ack.firstPacket = htonl(call->rx_data_eaten + 1);
		spin_unlock_bh(&call->lock);

		pad = 0;

		iov[1].iov_base = &ack;
		iov[1].iov_len	= sizeof(ack);
		iov[2].iov_base = &pad;
		iov[2].iov_len	= 3;
		iov[3].iov_base = &ackinfo;
		iov[3].iov_len	= sizeof(ackinfo);
		goto send_ACK;
1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
	}

	if (call->events & ((1 << RXRPC_CALL_RCVD_BUSY) |
			    (1 << RXRPC_CALL_RCVD_ABORT))
	    ) {
		u32 mark;

		if (test_bit(RXRPC_CALL_RCVD_ABORT, &call->events))
			mark = RXRPC_SKB_MARK_REMOTE_ABORT;
		else
			mark = RXRPC_SKB_MARK_BUSY;

		_debug("post abort/busy");
		rxrpc_clear_tx_window(call);
		if (rxrpc_post_message(call, mark, ECONNABORTED, true) < 0)
			goto no_mem;

		clear_bit(RXRPC_CALL_RCVD_BUSY, &call->events);
		clear_bit(RXRPC_CALL_RCVD_ABORT, &call->events);
		goto kill_ACKs;
	}

	if (test_and_clear_bit(RXRPC_CALL_RCVD_ACKALL, &call->events)) {
		_debug("do implicit ackall");
		rxrpc_clear_tx_window(call);
	}

	if (test_bit(RXRPC_CALL_LIFE_TIMER, &call->events)) {
		write_lock_bh(&call->state_lock);
		if (call->state <= RXRPC_CALL_COMPLETE) {
			call->state = RXRPC_CALL_LOCALLY_ABORTED;
			call->abort_code = RX_CALL_TIMEOUT;
			set_bit(RXRPC_CALL_ABORT, &call->events);
		}
		write_unlock_bh(&call->state_lock);

		_debug("post timeout");
		if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
				       ETIME, true) < 0)
			goto no_mem;

		clear_bit(RXRPC_CALL_LIFE_TIMER, &call->events);
		goto kill_ACKs;
	}

	/* deal with assorted inbound messages */
	if (!skb_queue_empty(&call->rx_queue)) {
		switch (rxrpc_process_rx_queue(call, &abort_code)) {
		case 0:
		case -EAGAIN:
			break;
		case -ENOMEM:
			goto no_mem;
		case -EKEYEXPIRED:
		case -EKEYREJECTED:
		case -EPROTO:
			rxrpc_abort_call(call, abort_code);
			goto kill_ACKs;
		}
	}

	/* handle resending */
	if (test_and_clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events))
		rxrpc_resend_timer(call);
	if (test_and_clear_bit(RXRPC_CALL_RESEND, &call->events))
		rxrpc_resend(call);

	/* consider sending an ordinary ACK */
	if (test_bit(RXRPC_CALL_ACK, &call->events)) {
		_debug("send ACK: window: %d - %d { %lx }",
		       call->rx_data_eaten, call->ackr_win_top,
		       call->ackr_window[0]);

		if (call->state > RXRPC_CALL_SERVER_ACK_REQUEST &&
		    call->ackr_reason != RXRPC_ACK_PING_RESPONSE) {
			/* ACK by sending reply DATA packet in this state */
			clear_bit(RXRPC_CALL_ACK, &call->events);
			goto maybe_reschedule;
		}

		genbit = RXRPC_CALL_ACK;

		acks = kzalloc(call->ackr_win_top - call->rx_data_eaten,
			       GFP_NOFS);
		if (!acks)
			goto no_mem;

		//hdr.flags	= RXRPC_SLOW_START_OK;
		ack.bufferSpace	= htons(8);
		ack.maxSkew	= 0;
		ack.serial	= 0;
		ack.reason	= 0;

		spin_lock_bh(&call->lock);
		ack.reason = call->ackr_reason;
		ack.serial = call->ackr_serial;
		ack.previousPacket = call->ackr_prev_seq;
		ack.firstPacket = htonl(call->rx_data_eaten + 1);

		ack.nAcks = 0;
		for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) {
			nbit = loop * BITS_PER_LONG;
			for (bits = call->ackr_window[loop]; bits; bits >>= 1
			     ) {
				_debug("- l=%d n=%d b=%lx", loop, nbit, bits);
				if (bits & 1) {
					acks[nbit] = RXRPC_ACK_TYPE_ACK;
					ack.nAcks = nbit + 1;
				}
				nbit++;
			}
		}
		call->ackr_reason = 0;
		spin_unlock_bh(&call->lock);

		pad = 0;

		iov[1].iov_base = &ack;
		iov[1].iov_len	= sizeof(ack);
		iov[2].iov_base = acks;
		iov[2].iov_len	= ack.nAcks;
		iov[3].iov_base = &pad;
		iov[3].iov_len	= 3;
		iov[4].iov_base = &ackinfo;
		iov[4].iov_len	= sizeof(ackinfo);

		switch (ack.reason) {
		case RXRPC_ACK_REQUESTED:
		case RXRPC_ACK_DUPLICATE:
		case RXRPC_ACK_OUT_OF_SEQUENCE:
		case RXRPC_ACK_EXCEEDS_WINDOW:
		case RXRPC_ACK_NOSPACE:
		case RXRPC_ACK_PING:
		case RXRPC_ACK_PING_RESPONSE:
			goto send_ACK_with_skew;
		case RXRPC_ACK_DELAY:
		case RXRPC_ACK_IDLE:
			goto send_ACK;
		}
	}

	/* handle completion of security negotiations on an incoming
	 * connection */
	if (test_and_clear_bit(RXRPC_CALL_SECURED, &call->events)) {
		_debug("secured");
		spin_lock_bh(&call->lock);

		if (call->state == RXRPC_CALL_SERVER_SECURING) {
			_debug("securing");
			write_lock(&call->conn->lock);
			if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
			    !test_bit(RXRPC_CALL_RELEASE, &call->events)) {
				_debug("not released");
				call->state = RXRPC_CALL_SERVER_ACCEPTING;
				list_move_tail(&call->accept_link,
					       &call->socket->acceptq);
			}
			write_unlock(&call->conn->lock);
			read_lock(&call->state_lock);
			if (call->state < RXRPC_CALL_COMPLETE)
				set_bit(RXRPC_CALL_POST_ACCEPT, &call->events);
			read_unlock(&call->state_lock);
		}

		spin_unlock_bh(&call->lock);
		if (!test_bit(RXRPC_CALL_POST_ACCEPT, &call->events))
			goto maybe_reschedule;
	}

	/* post a notification of an acceptable connection to the app */
	if (test_bit(RXRPC_CALL_POST_ACCEPT, &call->events)) {
		_debug("post accept");
		if (rxrpc_post_message(call, RXRPC_SKB_MARK_NEW_CALL,
				       0, false) < 0)
			goto no_mem;
		clear_bit(RXRPC_CALL_POST_ACCEPT, &call->events);
		goto maybe_reschedule;
	}

	/* handle incoming call acceptance */
	if (test_and_clear_bit(RXRPC_CALL_ACCEPTED, &call->events)) {
		_debug("accepted");
		ASSERTCMP(call->rx_data_post, ==, 0);
		call->rx_data_post = 1;
		read_lock_bh(&call->state_lock);
		if (call->state < RXRPC_CALL_COMPLETE)
			set_bit(RXRPC_CALL_DRAIN_RX_OOS, &call->events);
		read_unlock_bh(&call->state_lock);
	}

	/* drain the out of sequence received packet queue into the packet Rx
	 * queue */
	if (test_and_clear_bit(RXRPC_CALL_DRAIN_RX_OOS, &call->events)) {
		while (call->rx_data_post == call->rx_first_oos)
			if (rxrpc_drain_rx_oos_queue(call) < 0)
				break;
		goto maybe_reschedule;
	}

	/* other events may have been raised since we started checking */
	goto maybe_reschedule;

send_ACK_with_skew:
	ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) -
			    ntohl(ack.serial));
send_ACK:
1216 1217 1218
	mtu = call->conn->trans->peer->if_mtu;
	mtu -= call->conn->trans->peer->hdrsize;
	ackinfo.maxMTU	= htonl(mtu);
1219
	ackinfo.rwind	= htonl(rxrpc_rx_window_size);
1220 1221

	/* permit the peer to send us jumbo packets if it wants to */
1222 1223
	ackinfo.rxMTU	= htonl(rxrpc_rx_mtu);
	ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max);
1224

1225 1226 1227 1228 1229 1230 1231
	hdr.serial = htonl(atomic_inc_return(&call->conn->serial));
	_proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
	       ntohl(hdr.serial),
	       ntohs(ack.maxSkew),
	       ntohl(ack.firstPacket),
	       ntohl(ack.previousPacket),
	       ntohl(ack.serial),
1232
	       rxrpc_acks(ack.reason),
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
	       ack.nAcks);

	del_timer_sync(&call->ack_timer);
	if (ack.nAcks > 0)
		set_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags);
	goto send_message_2;

send_message:
	_debug("send message");

	hdr.serial = htonl(atomic_inc_return(&call->conn->serial));
	_proto("Tx %s %%%u", rxrpc_pkts[hdr.type], ntohl(hdr.serial));
send_message_2:

	len = iov[0].iov_len;
	ioc = 1;
	if (iov[4].iov_len) {
		ioc = 5;
		len += iov[4].iov_len;
		len += iov[3].iov_len;
		len += iov[2].iov_len;
		len += iov[1].iov_len;
	} else if (iov[3].iov_len) {
		ioc = 4;
		len += iov[3].iov_len;
		len += iov[2].iov_len;
		len += iov[1].iov_len;
	} else if (iov[2].iov_len) {
		ioc = 3;
		len += iov[2].iov_len;
		len += iov[1].iov_len;
	} else if (iov[1].iov_len) {
		ioc = 2;
		len += iov[1].iov_len;
	}

	ret = kernel_sendmsg(call->conn->trans->local->socket,
			     &msg, iov, ioc, len);
	if (ret < 0) {
		_debug("sendmsg failed: %d", ret);
		read_lock_bh(&call->state_lock);
		if (call->state < RXRPC_CALL_DEAD)
1275
			rxrpc_queue_call(call);
1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318
		read_unlock_bh(&call->state_lock);
		goto error;
	}

	switch (genbit) {
	case RXRPC_CALL_ABORT:
		clear_bit(genbit, &call->events);
		clear_bit(RXRPC_CALL_RCVD_ABORT, &call->events);
		goto kill_ACKs;

	case RXRPC_CALL_ACK_FINAL:
		write_lock_bh(&call->state_lock);
		if (call->state == RXRPC_CALL_CLIENT_FINAL_ACK)
			call->state = RXRPC_CALL_COMPLETE;
		write_unlock_bh(&call->state_lock);
		goto kill_ACKs;

	default:
		clear_bit(genbit, &call->events);
		switch (call->state) {
		case RXRPC_CALL_CLIENT_AWAIT_REPLY:
		case RXRPC_CALL_CLIENT_RECV_REPLY:
		case RXRPC_CALL_SERVER_RECV_REQUEST:
		case RXRPC_CALL_SERVER_ACK_REQUEST:
			_debug("start ACK timer");
			rxrpc_propose_ACK(call, RXRPC_ACK_DELAY,
					  call->ackr_serial, false);
		default:
			break;
		}
		goto maybe_reschedule;
	}

kill_ACKs:
	del_timer_sync(&call->ack_timer);
	if (test_and_clear_bit(RXRPC_CALL_ACK_FINAL, &call->events))
		rxrpc_put_call(call);
	clear_bit(RXRPC_CALL_ACK, &call->events);

maybe_reschedule:
	if (call->events || !skb_queue_empty(&call->rx_queue)) {
		read_lock_bh(&call->state_lock);
		if (call->state < RXRPC_CALL_DEAD)
1319
			rxrpc_queue_call(call);
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332
		read_unlock_bh(&call->state_lock);
	}

	/* don't leave aborted connections on the accept queue */
	if (call->state >= RXRPC_CALL_COMPLETE &&
	    !list_empty(&call->accept_link)) {
		_debug("X unlinking once-pending call %p { e=%lx f=%lx c=%x }",
		       call, call->events, call->flags,
		       ntohl(call->conn->cid));

		read_lock_bh(&call->state_lock);
		if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
		    !test_and_set_bit(RXRPC_CALL_RELEASE, &call->events))
1333
			rxrpc_queue_call(call);
1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
		read_unlock_bh(&call->state_lock);
	}

error:
	clear_bit(RXRPC_CALL_PROC_BUSY, &call->flags);
	kfree(acks);

	/* because we don't want two CPUs both processing the work item for one
	 * call at the same time, we use a flag to note when it's busy; however
	 * this means there's a race between clearing the flag and setting the
	 * work pending bit and the work item being processed again */
	if (call->events && !work_pending(&call->processor)) {
		_debug("jumpstart %x", ntohl(call->conn->cid));
1347
		rxrpc_queue_call(call);
1348 1349 1350 1351 1352 1353 1354 1355 1356
	}

	_leave("");
	return;

no_mem:
	_debug("out of memory");
	goto maybe_reschedule;
}