bcast.c 23.3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
/*
 * net/tipc/bcast.c: TIPC broadcast code
 *
 * Copyright (c) 2004-2006, Ericsson AB
 * Copyright (c) 2004, Intel Corporation.
 * Copyright (c) 2005, 2010-2011, Wind River Systems
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "core.h"
#include "link.h"
#include "port.h"
#include "bcast.h"
#include "name_distr.h"

#define MAX_PKT_DEFAULT_MCAST 1500	/* bcast link max packet size (fixed) */

#define BCLINK_WIN_DEFAULT 20		/* bcast link window size (default) */

/**
 * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link
 * @primary: pointer to primary bearer
 * @secondary: pointer to secondary bearer
 *
 * Bearers must have same priority and same set of reachable destinations
 * to be paired.
 */

struct tipc_bcbearer_pair {
	struct tipc_bearer *primary;
	struct tipc_bearer *secondary;
};

/**
 * struct tipc_bcbearer - bearer used by broadcast link
 * @bearer: (non-standard) broadcast bearer structure
 * @media: (non-standard) broadcast media structure
 * @bpairs: array of bearer pairs
 * @bpairs_temp: temporary array of bearer pairs used by tipc_bcbearer_sort()
 * @remains: temporary node map used by tipc_bcbearer_send()
 * @remains_new: temporary node map used tipc_bcbearer_send()
 *
 * Note: The fields labelled "temporary" are incorporated into the bearer
 * to avoid consuming potentially limited stack space through the use of
 * large local variables within multicast routines.  Concurrent access is
 * prevented through use of the spinlock "bc_lock".
 */

struct tipc_bcbearer {
	struct tipc_bearer bearer;
	struct tipc_media media;
	struct tipc_bcbearer_pair bpairs[MAX_BEARERS];
	struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1];
	struct tipc_node_map remains;
	struct tipc_node_map remains_new;
};

/**
 * struct tipc_bclink - link used for broadcast messages
 * @link: (non-standard) broadcast link structure
 * @node: (non-standard) node structure representing b'cast link's peer node
 * @bcast_nodes: map of broadcast-capable nodes
 * @retransmit_to: node that most recently requested a retransmit
 *
 * Handles sequence numbering, fragmentation, bundling, etc.
 */

struct tipc_bclink {
	struct tipc_link link;
	struct tipc_node node;
	struct tipc_node_map bcast_nodes;
	struct tipc_node *retransmit_to;
};

static struct tipc_bcbearer bcast_bearer;
static struct tipc_bclink bcast_link;

static struct tipc_bcbearer *bcbearer = &bcast_bearer;
static struct tipc_bclink *bclink = &bcast_link;
static struct tipc_link *bcl = &bcast_link.link;

static DEFINE_SPINLOCK(bc_lock);

const char tipc_bclink_name[] = "broadcast-link";

static void tipc_nmap_diff(struct tipc_node_map *nm_a,
			   struct tipc_node_map *nm_b,
			   struct tipc_node_map *nm_diff);

static u32 bcbuf_acks(struct sk_buff *buf)
{
	return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle;
}

static void bcbuf_set_acks(struct sk_buff *buf, u32 acks)
{
	TIPC_SKB_CB(buf)->handle = (void *)(unsigned long)acks;
}

static void bcbuf_decr_acks(struct sk_buff *buf)
{
	bcbuf_set_acks(buf, bcbuf_acks(buf) - 1);
}

void tipc_bclink_add_node(u32 addr)
{
	spin_lock_bh(&bc_lock);
	tipc_nmap_add(&bclink->bcast_nodes, addr);
	spin_unlock_bh(&bc_lock);
}

void tipc_bclink_remove_node(u32 addr)
{
	spin_lock_bh(&bc_lock);
	tipc_nmap_remove(&bclink->bcast_nodes, addr);
	spin_unlock_bh(&bc_lock);
}

static void bclink_set_last_sent(void)
{
	if (bcl->next_out)
		bcl->fsm_msg_cnt = mod(buf_seqno(bcl->next_out) - 1);
	else
		bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1);
}

u32 tipc_bclink_get_last_sent(void)
{
	return bcl->fsm_msg_cnt;
}

/**
 * bclink_set_gap - set gap according to contents of current deferred pkt queue
 *
 * Called with 'node' locked, bc_lock unlocked
 */

static void bclink_set_gap(struct tipc_node *n_ptr)
{
	struct sk_buff *buf = n_ptr->bclink.deferred_head;

	n_ptr->bclink.gap_after = n_ptr->bclink.gap_to =
		mod(n_ptr->bclink.last_in);
	if (unlikely(buf != NULL))
		n_ptr->bclink.gap_to = mod(buf_seqno(buf) - 1);
}

/**
 * bclink_ack_allowed - test if ACK or NACK message can be sent at this moment
 *
 * This mechanism endeavours to prevent all nodes in network from trying
 * to ACK or NACK at the same time.
 *
 * Note: TIPC uses a different trigger to distribute ACKs than it does to
 *       distribute NACKs, but tries to use the same spacing (divide by 16).
 */

static int bclink_ack_allowed(u32 n)
{
	return (n % TIPC_MIN_LINK_WIN) == tipc_own_tag;
}


/**
 * tipc_bclink_retransmit_to - get most recent node to request retransmission
 *
 * Called with bc_lock locked
 */

struct tipc_node *tipc_bclink_retransmit_to(void)
{
	return bclink->retransmit_to;
}

/**
 * bclink_retransmit_pkt - retransmit broadcast packets
 * @after: sequence number of last packet to *not* retransmit
 * @to: sequence number of last packet to retransmit
 *
 * Called with bc_lock locked
 */

static void bclink_retransmit_pkt(u32 after, u32 to)
{
	struct sk_buff *buf;

	buf = bcl->first_out;
	while (buf && less_eq(buf_seqno(buf), after))
		buf = buf->next;
	tipc_link_retransmit(bcl, buf, mod(to - after));
}

/**
 * tipc_bclink_acknowledge - handle acknowledgement of broadcast packets
 * @n_ptr: node that sent acknowledgement info
 * @acked: broadcast sequence # that has been acknowledged
 *
 * Node is locked, bc_lock unlocked.
 */

void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
{
	struct sk_buff *crs;
	struct sk_buff *next;
	unsigned int released = 0;

	spin_lock_bh(&bc_lock);

	/* Bail out if tx queue is empty (no clean up is required) */
	crs = bcl->first_out;
	if (!crs)
		goto exit;

	/* Determine which messages need to be acknowledged */
	if (acked == INVALID_LINK_SEQ) {
		/*
		 * Contact with specified node has been lost, so need to
		 * acknowledge sent messages only (if other nodes still exist)
		 * or both sent and unsent messages (otherwise)
		 */
		if (bclink->bcast_nodes.count)
			acked = bcl->fsm_msg_cnt;
		else
			acked = bcl->next_out_no;
	} else {
		/*
		 * Bail out if specified sequence number does not correspond
		 * to a message that has been sent and not yet acknowledged
		 */
		if (less(acked, buf_seqno(crs)) ||
		    less(bcl->fsm_msg_cnt, acked) ||
		    less_eq(acked, n_ptr->bclink.acked))
			goto exit;
	}

	/* Skip over packets that node has previously acknowledged */
	while (crs && less_eq(buf_seqno(crs), n_ptr->bclink.acked))
		crs = crs->next;

	/* Update packets that node is now acknowledging */

	while (crs && less_eq(buf_seqno(crs), acked)) {
		next = crs->next;

		if (crs != bcl->next_out)
			bcbuf_decr_acks(crs);
		else {
			bcbuf_set_acks(crs, 0);
			bcl->next_out = next;
			bclink_set_last_sent();
		}

		if (bcbuf_acks(crs) == 0) {
			bcl->first_out = next;
			bcl->out_queue_size--;
			buf_discard(crs);
			released = 1;
		}
		crs = next;
	}
	n_ptr->bclink.acked = acked;

	/* Try resolving broadcast link congestion, if necessary */

	if (unlikely(bcl->next_out)) {
		tipc_link_push_queue(bcl);
		bclink_set_last_sent();
	}
	if (unlikely(released && !list_empty(&bcl->waiting_ports)))
		tipc_link_wakeup_ports(bcl, 0);
exit:
	spin_unlock_bh(&bc_lock);
}

/**
 * bclink_send_ack - unicast an ACK msg
 *
 * tipc_net_lock and node lock set
 */

static void bclink_send_ack(struct tipc_node *n_ptr)
{
	struct tipc_link *l_ptr = n_ptr->active_links[n_ptr->addr & 1];

	if (l_ptr != NULL)
		tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
}

/**
 * bclink_send_nack- broadcast a NACK msg
 *
 * tipc_net_lock and node lock set
 */

static void bclink_send_nack(struct tipc_node *n_ptr)
{
	struct sk_buff *buf;
	struct tipc_msg *msg;

	if (!less(n_ptr->bclink.gap_after, n_ptr->bclink.gap_to))
		return;

	buf = tipc_buf_acquire(INT_H_SIZE);
	if (buf) {
		msg = buf_msg(buf);
		tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG,
			 INT_H_SIZE, n_ptr->addr);
		msg_set_non_seq(msg, 1);
		msg_set_mc_netid(msg, tipc_net_id);
		msg_set_bcast_ack(msg, mod(n_ptr->bclink.last_in));
		msg_set_bcgap_after(msg, n_ptr->bclink.gap_after);
		msg_set_bcgap_to(msg, n_ptr->bclink.gap_to);
		msg_set_bcast_tag(msg, tipc_own_tag);

		tipc_bearer_send(&bcbearer->bearer, buf, NULL);
		bcl->stats.sent_nacks++;
		buf_discard(buf);

		/*
		 * Ensure we doesn't send another NACK msg to the node
		 * until 16 more deferred messages arrive from it
		 * (i.e. helps prevent all nodes from NACK'ing at same time)
		 */

		n_ptr->bclink.nack_sync = tipc_own_tag;
	}
}

/**
 * tipc_bclink_check_gap - send a NACK if a sequence gap exists
 *
 * tipc_net_lock and node lock set
 */

void tipc_bclink_check_gap(struct tipc_node *n_ptr, u32 last_sent)
{
	if (!n_ptr->bclink.supported ||
	    less_eq(last_sent, mod(n_ptr->bclink.last_in)))
		return;

	bclink_set_gap(n_ptr);
	if (n_ptr->bclink.gap_after == n_ptr->bclink.gap_to)
		n_ptr->bclink.gap_to = last_sent;
	bclink_send_nack(n_ptr);
}

/**
 * tipc_bclink_peek_nack - process a NACK msg meant for another node
 *
 * Only tipc_net_lock set.
 */

static void tipc_bclink_peek_nack(u32 dest, u32 sender_tag, u32 gap_after, u32 gap_to)
{
	struct tipc_node *n_ptr = tipc_node_find(dest);
	u32 my_after, my_to;

	if (unlikely(!n_ptr || !tipc_node_is_up(n_ptr)))
		return;
	tipc_node_lock(n_ptr);
	/*
	 * Modify gap to suppress unnecessary NACKs from this node
	 */
	my_after = n_ptr->bclink.gap_after;
	my_to = n_ptr->bclink.gap_to;

	if (less_eq(gap_after, my_after)) {
		if (less(my_after, gap_to) && less(gap_to, my_to))
			n_ptr->bclink.gap_after = gap_to;
		else if (less_eq(my_to, gap_to))
			n_ptr->bclink.gap_to = n_ptr->bclink.gap_after;
	} else if (less_eq(gap_after, my_to)) {
		if (less_eq(my_to, gap_to))
			n_ptr->bclink.gap_to = gap_after;
	} else {
		/*
		 * Expand gap if missing bufs not in deferred queue:
		 */
		struct sk_buff *buf = n_ptr->bclink.deferred_head;
		u32 prev = n_ptr->bclink.gap_to;

		for (; buf; buf = buf->next) {
			u32 seqno = buf_seqno(buf);

			if (mod(seqno - prev) != 1) {
				buf = NULL;
				break;
			}
			if (seqno == gap_after)
				break;
			prev = seqno;
		}
		if (buf == NULL)
			n_ptr->bclink.gap_to = gap_after;
	}
	/*
	 * Some nodes may send a complementary NACK now:
	 */
	if (bclink_ack_allowed(sender_tag + 1)) {
		if (n_ptr->bclink.gap_to != n_ptr->bclink.gap_after) {
			bclink_send_nack(n_ptr);
			bclink_set_gap(n_ptr);
		}
	}
	tipc_node_unlock(n_ptr);
}

/**
 * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster
 */

int tipc_bclink_send_msg(struct sk_buff *buf)
{
	int res;

	spin_lock_bh(&bc_lock);

	if (!bclink->bcast_nodes.count) {
		res = msg_data_sz(buf_msg(buf));
		buf_discard(buf);
		goto exit;
	}

	res = tipc_link_send_buf(bcl, buf);
	if (likely(res >= 0)) {
		bclink_set_last_sent();
		bcl->stats.queue_sz_counts++;
		bcl->stats.accu_queue_sz += bcl->out_queue_size;
	}
exit:
	spin_unlock_bh(&bc_lock);
	return res;
}

/**
 * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards
 *
 * tipc_net_lock is read_locked, no other locks set
 */

void tipc_bclink_recv_pkt(struct sk_buff *buf)
{
	struct tipc_msg *msg = buf_msg(buf);
	struct tipc_node *node;
	u32 next_in;
	u32 seqno;
	struct sk_buff *deferred;

	/* Screen out unwanted broadcast messages */

	if (msg_mc_netid(msg) != tipc_net_id)
		goto exit;

	node = tipc_node_find(msg_prevnode(msg));
	if (unlikely(!node))
		goto exit;

	tipc_node_lock(node);
	if (unlikely(!node->bclink.supported))
		goto unlock;

	if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) {
		if (msg_type(msg) != STATE_MSG)
			goto unlock;
		if (msg_destnode(msg) == tipc_own_addr) {
			tipc_bclink_acknowledge(node, msg_bcast_ack(msg));
			tipc_node_unlock(node);
			spin_lock_bh(&bc_lock);
			bcl->stats.recv_nacks++;
			bclink->retransmit_to = node;
			bclink_retransmit_pkt(msg_bcgap_after(msg),
					      msg_bcgap_to(msg));
			spin_unlock_bh(&bc_lock);
		} else {
			tipc_node_unlock(node);
			tipc_bclink_peek_nack(msg_destnode(msg),
					      msg_bcast_tag(msg),
					      msg_bcgap_after(msg),
					      msg_bcgap_to(msg));
		}
		goto exit;
	}

	/* Handle in-sequence broadcast message */

receive:
	next_in = mod(node->bclink.last_in + 1);
	seqno = msg_seqno(msg);

	if (likely(seqno == next_in)) {
		bcl->stats.recv_info++;
		node->bclink.last_in++;
		bclink_set_gap(node);
		if (unlikely(bclink_ack_allowed(seqno))) {
			bclink_send_ack(node);
			bcl->stats.sent_acks++;
		}
		if (likely(msg_isdata(msg))) {
			tipc_node_unlock(node);
			if (likely(msg_mcast(msg)))
				tipc_port_recv_mcast(buf, NULL);
			else
				buf_discard(buf);
		} else if (msg_user(msg) == MSG_BUNDLER) {
			bcl->stats.recv_bundles++;
			bcl->stats.recv_bundled += msg_msgcnt(msg);
			tipc_node_unlock(node);
			tipc_link_recv_bundle(buf);
		} else if (msg_user(msg) == MSG_FRAGMENTER) {
			bcl->stats.recv_fragments++;
			if (tipc_link_recv_fragment(&node->bclink.defragm,
						    &buf, &msg))
				bcl->stats.recv_fragmented++;
			tipc_node_unlock(node);
			tipc_net_route_msg(buf);
		} else if (msg_user(msg) == NAME_DISTRIBUTOR) {
			tipc_node_unlock(node);
			tipc_named_recv(buf);
		} else {
			tipc_node_unlock(node);
			buf_discard(buf);
		}
		buf = NULL;
		tipc_node_lock(node);
		deferred = node->bclink.deferred_head;
		if (deferred && (buf_seqno(deferred) == mod(next_in + 1))) {
			buf = deferred;
			msg = buf_msg(buf);
			node->bclink.deferred_head = deferred->next;
			goto receive;
		}
	} else if (less(next_in, seqno)) {
		u32 gap_after = node->bclink.gap_after;
		u32 gap_to = node->bclink.gap_to;

		if (tipc_link_defer_pkt(&node->bclink.deferred_head,
					&node->bclink.deferred_tail,
					buf)) {
			node->bclink.nack_sync++;
			bcl->stats.deferred_recv++;
			if (seqno == mod(gap_after + 1))
				node->bclink.gap_after = seqno;
			else if (less(gap_after, seqno) && less(seqno, gap_to))
				node->bclink.gap_to = seqno;
		}
		buf = NULL;
		if (bclink_ack_allowed(node->bclink.nack_sync)) {
			if (gap_to != gap_after)
				bclink_send_nack(node);
			bclink_set_gap(node);
		}
	} else {
		bcl->stats.duplicates++;
	}
unlock:
	tipc_node_unlock(node);
exit:
	buf_discard(buf);
}

u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr)
{
	return (n_ptr->bclink.supported &&
		(tipc_bclink_get_last_sent() != n_ptr->bclink.acked));
}


/**
 * tipc_bcbearer_send - send a packet through the broadcast pseudo-bearer
 *
 * Send packet over as many bearers as necessary to reach all nodes
 * that have joined the broadcast link.
 *
 * Returns 0 (packet sent successfully) under all circumstances,
 * since the broadcast link's pseudo-bearer never blocks
 */

static int tipc_bcbearer_send(struct sk_buff *buf,
			      struct tipc_bearer *unused1,
			      struct tipc_media_addr *unused2)
{
	int bp_index;

	/*
	 * Prepare broadcast link message for reliable transmission,
	 * if first time trying to send it;
	 * preparation is skipped for broadcast link protocol messages
	 * since they are sent in an unreliable manner and don't need it
	 */

	if (likely(!msg_non_seq(buf_msg(buf)))) {
		struct tipc_msg *msg;

		bcbuf_set_acks(buf, bclink->bcast_nodes.count);
		msg = buf_msg(buf);
		msg_set_non_seq(msg, 1);
		msg_set_mc_netid(msg, tipc_net_id);
		bcl->stats.sent_info++;

		if (WARN_ON(!bclink->bcast_nodes.count)) {
			dump_stack();
			return 0;
		}
	}

	/* Send buffer over bearers until all targets reached */

	bcbearer->remains = bclink->bcast_nodes;

	for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) {
		struct tipc_bearer *p = bcbearer->bpairs[bp_index].primary;
		struct tipc_bearer *s = bcbearer->bpairs[bp_index].secondary;

		if (!p)
			break;	/* no more bearers to try */

		tipc_nmap_diff(&bcbearer->remains, &p->nodes, &bcbearer->remains_new);
		if (bcbearer->remains_new.count == bcbearer->remains.count)
			continue;	/* bearer pair doesn't add anything */

		if (p->blocked ||
		    p->media->send_msg(buf, p, &p->media->bcast_addr)) {
			/* unable to send on primary bearer */
			if (!s || s->blocked ||
			    s->media->send_msg(buf, s,
					       &s->media->bcast_addr)) {
				/* unable to send on either bearer */
				continue;
			}
		}

		if (s) {
			bcbearer->bpairs[bp_index].primary = s;
			bcbearer->bpairs[bp_index].secondary = p;
		}

		if (bcbearer->remains_new.count == 0)
			break;	/* all targets reached */

		bcbearer->remains = bcbearer->remains_new;
	}

	return 0;
}

/**
 * tipc_bcbearer_sort - create sets of bearer pairs used by broadcast bearer
 */

void tipc_bcbearer_sort(void)
{
	struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
	struct tipc_bcbearer_pair *bp_curr;
	int b_index;
	int pri;

	spin_lock_bh(&bc_lock);

	/* Group bearers by priority (can assume max of two per priority) */

	memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp));

	for (b_index = 0; b_index < MAX_BEARERS; b_index++) {
		struct tipc_bearer *b = &tipc_bearers[b_index];

		if (!b->active || !b->nodes.count)
			continue;

		if (!bp_temp[b->priority].primary)
			bp_temp[b->priority].primary = b;
		else
			bp_temp[b->priority].secondary = b;
	}

	/* Create array of bearer pairs for broadcasting */

	bp_curr = bcbearer->bpairs;
	memset(bcbearer->bpairs, 0, sizeof(bcbearer->bpairs));

	for (pri = TIPC_MAX_LINK_PRI; pri >= 0; pri--) {

		if (!bp_temp[pri].primary)
			continue;

		bp_curr->primary = bp_temp[pri].primary;

		if (bp_temp[pri].secondary) {
			if (tipc_nmap_equal(&bp_temp[pri].primary->nodes,
					    &bp_temp[pri].secondary->nodes)) {
				bp_curr->secondary = bp_temp[pri].secondary;
			} else {
				bp_curr++;
				bp_curr->primary = bp_temp[pri].secondary;
			}
		}

		bp_curr++;
	}

	spin_unlock_bh(&bc_lock);
}


int tipc_bclink_stats(char *buf, const u32 buf_size)
{
	struct print_buf pb;

	if (!bcl)
		return 0;

	tipc_printbuf_init(&pb, buf, buf_size);

	spin_lock_bh(&bc_lock);

	tipc_printf(&pb, "Link <%s>\n"
			 "  Window:%u packets\n",
		    bcl->name, bcl->queue_limit[0]);
	tipc_printf(&pb, "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
		    bcl->stats.recv_info,
		    bcl->stats.recv_fragments,
		    bcl->stats.recv_fragmented,
		    bcl->stats.recv_bundles,
		    bcl->stats.recv_bundled);
	tipc_printf(&pb, "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
		    bcl->stats.sent_info,
		    bcl->stats.sent_fragments,
		    bcl->stats.sent_fragmented,
		    bcl->stats.sent_bundles,
		    bcl->stats.sent_bundled);
	tipc_printf(&pb, "  RX naks:%u defs:%u dups:%u\n",
		    bcl->stats.recv_nacks,
		    bcl->stats.deferred_recv,
		    bcl->stats.duplicates);
	tipc_printf(&pb, "  TX naks:%u acks:%u dups:%u\n",
		    bcl->stats.sent_nacks,
		    bcl->stats.sent_acks,
		    bcl->stats.retransmitted);
	tipc_printf(&pb, "  Congestion bearer:%u link:%u  Send queue max:%u avg:%u\n",
		    bcl->stats.bearer_congs,
		    bcl->stats.link_congs,
		    bcl->stats.max_queue_sz,
		    bcl->stats.queue_sz_counts
		    ? (bcl->stats.accu_queue_sz / bcl->stats.queue_sz_counts)
		    : 0);

	spin_unlock_bh(&bc_lock);
	return tipc_printbuf_validate(&pb);
}

int tipc_bclink_reset_stats(void)
{
	if (!bcl)
		return -ENOPROTOOPT;

	spin_lock_bh(&bc_lock);
	memset(&bcl->stats, 0, sizeof(bcl->stats));
	spin_unlock_bh(&bc_lock);
	return 0;
}

int tipc_bclink_set_queue_limits(u32 limit)
{
	if (!bcl)
		return -ENOPROTOOPT;
	if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN))
		return -EINVAL;

	spin_lock_bh(&bc_lock);
	tipc_link_set_queue_limits(bcl, limit);
	spin_unlock_bh(&bc_lock);
	return 0;
}

void tipc_bclink_init(void)
{
	INIT_LIST_HEAD(&bcbearer->bearer.cong_links);
	bcbearer->bearer.media = &bcbearer->media;
	bcbearer->media.send_msg = tipc_bcbearer_send;
	sprintf(bcbearer->media.name, "tipc-broadcast");

	INIT_LIST_HEAD(&bcl->waiting_ports);
	bcl->next_out_no = 1;
	spin_lock_init(&bclink->node.lock);
	bcl->owner = &bclink->node;
	bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
	tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
	bcl->b_ptr = &bcbearer->bearer;
	bcl->state = WORKING_WORKING;
	strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
}

void tipc_bclink_stop(void)
{
	spin_lock_bh(&bc_lock);
	tipc_link_stop(bcl);
	spin_unlock_bh(&bc_lock);

	memset(bclink, 0, sizeof(*bclink));
	memset(bcbearer, 0, sizeof(*bcbearer));
}


/**
 * tipc_nmap_add - add a node to a node map
 */

void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
{
	int n = tipc_node(node);
	int w = n / WSIZE;
	u32 mask = (1 << (n % WSIZE));

	if ((nm_ptr->map[w] & mask) == 0) {
		nm_ptr->count++;
		nm_ptr->map[w] |= mask;
	}
}

/**
 * tipc_nmap_remove - remove a node from a node map
 */

void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node)
{
	int n = tipc_node(node);
	int w = n / WSIZE;
	u32 mask = (1 << (n % WSIZE));

	if ((nm_ptr->map[w] & mask) != 0) {
		nm_ptr->map[w] &= ~mask;
		nm_ptr->count--;
	}
}

/**
 * tipc_nmap_diff - find differences between node maps
 * @nm_a: input node map A
 * @nm_b: input node map B
 * @nm_diff: output node map A-B (i.e. nodes of A that are not in B)
 */

static void tipc_nmap_diff(struct tipc_node_map *nm_a,
			   struct tipc_node_map *nm_b,
			   struct tipc_node_map *nm_diff)
{
	int stop = ARRAY_SIZE(nm_a->map);
	int w;
	int b;
	u32 map;

	memset(nm_diff, 0, sizeof(*nm_diff));
	for (w = 0; w < stop; w++) {
		map = nm_a->map[w] ^ (nm_a->map[w] & nm_b->map[w]);
		nm_diff->map[w] = map;
		if (map != 0) {
			for (b = 0 ; b < WSIZE; b++) {
				if (map & (1 << b))
					nm_diff->count++;
			}
		}
	}
}

/**
 * tipc_port_list_add - add a port to a port list, ensuring no duplicates
 */

void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port)
{
	struct tipc_port_list *item = pl_ptr;
	int i;
	int item_sz = PLSIZE;
	int cnt = pl_ptr->count;

	for (; ; cnt -= item_sz, item = item->next) {
		if (cnt < PLSIZE)
			item_sz = cnt;
		for (i = 0; i < item_sz; i++)
			if (item->ports[i] == port)
				return;
		if (i < PLSIZE) {
			item->ports[i] = port;
			pl_ptr->count++;
			return;
		}
		if (!item->next) {
			item->next = kmalloc(sizeof(*item), GFP_ATOMIC);
			if (!item->next) {
				warn("Incomplete multicast delivery, no memory\n");
				return;
			}
			item->next->next = NULL;
		}
	}
}

/**
 * tipc_port_list_free - free dynamically created entries in port_list chain
 *
 */

void tipc_port_list_free(struct tipc_port_list *pl_ptr)
{
	struct tipc_port_list *item;
	struct tipc_port_list *next;

	for (item = pl_ptr->next; item; item = next) {
		next = item->next;
		kfree(item);
	}
}