flow.c 34.7 KB
Newer Older
1
/*
2
 * Copyright (c) 2007-2011 Nicira, Inc.
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
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#include "flow.h"
#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/rcupdate.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>

static struct kmem_cache *flow_cache;

static int check_header(struct sk_buff *skb, int len)
{
	if (unlikely(skb->len < len))
		return -EINVAL;
	if (unlikely(!pskb_may_pull(skb, len)))
		return -ENOMEM;
	return 0;
}

static bool arphdr_ok(struct sk_buff *skb)
{
	return pskb_may_pull(skb, skb_network_offset(skb) +
				  sizeof(struct arp_eth_header));
}

static int check_iphdr(struct sk_buff *skb)
{
	unsigned int nh_ofs = skb_network_offset(skb);
	unsigned int ip_len;
	int err;

	err = check_header(skb, nh_ofs + sizeof(struct iphdr));
	if (unlikely(err))
		return err;

	ip_len = ip_hdrlen(skb);
	if (unlikely(ip_len < sizeof(struct iphdr) ||
		     skb->len < nh_ofs + ip_len))
		return -EINVAL;

	skb_set_transport_header(skb, nh_ofs + ip_len);
	return 0;
}

static bool tcphdr_ok(struct sk_buff *skb)
{
	int th_ofs = skb_transport_offset(skb);
	int tcp_len;

	if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr))))
		return false;

	tcp_len = tcp_hdrlen(skb);
	if (unlikely(tcp_len < sizeof(struct tcphdr) ||
		     skb->len < th_ofs + tcp_len))
		return false;

	return true;
}

static bool udphdr_ok(struct sk_buff *skb)
{
	return pskb_may_pull(skb, skb_transport_offset(skb) +
				  sizeof(struct udphdr));
}

static bool icmphdr_ok(struct sk_buff *skb)
{
	return pskb_may_pull(skb, skb_transport_offset(skb) +
				  sizeof(struct icmphdr));
}

u64 ovs_flow_used_time(unsigned long flow_jiffies)
{
	struct timespec cur_ts;
	u64 cur_ms, idle_ms;

	ktime_get_ts(&cur_ts);
	idle_ms = jiffies_to_msecs(jiffies - flow_jiffies);
	cur_ms = (u64)cur_ts.tv_sec * MSEC_PER_SEC +
		 cur_ts.tv_nsec / NSEC_PER_MSEC;

	return cur_ms - idle_ms;
}

#define SW_FLOW_KEY_OFFSET(field)		\
	(offsetof(struct sw_flow_key, field) +	\
	 FIELD_SIZEOF(struct sw_flow_key, field))

static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key,
			 int *key_lenp)
{
	unsigned int nh_ofs = skb_network_offset(skb);
	unsigned int nh_len;
	int payload_ofs;
	struct ipv6hdr *nh;
	uint8_t nexthdr;
	__be16 frag_off;
	int err;

	*key_lenp = SW_FLOW_KEY_OFFSET(ipv6.label);

	err = check_header(skb, nh_ofs + sizeof(*nh));
	if (unlikely(err))
		return err;

	nh = ipv6_hdr(skb);
	nexthdr = nh->nexthdr;
	payload_ofs = (u8 *)(nh + 1) - skb->data;

	key->ip.proto = NEXTHDR_NONE;
	key->ip.tos = ipv6_get_dsfield(nh);
	key->ip.ttl = nh->hop_limit;
	key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
	key->ipv6.addr.src = nh->saddr;
	key->ipv6.addr.dst = nh->daddr;

	payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off);
	if (unlikely(payload_ofs < 0))
		return -EINVAL;

	if (frag_off) {
		if (frag_off & htons(~0x7))
			key->ip.frag = OVS_FRAG_TYPE_LATER;
		else
			key->ip.frag = OVS_FRAG_TYPE_FIRST;
	}

	nh_len = payload_ofs - nh_ofs;
	skb_set_transport_header(skb, nh_ofs + nh_len);
	key->ip.proto = nexthdr;
	return nh_len;
}

static bool icmp6hdr_ok(struct sk_buff *skb)
{
	return pskb_may_pull(skb, skb_transport_offset(skb) +
				  sizeof(struct icmp6hdr));
}

#define TCP_FLAGS_OFFSET 13
#define TCP_FLAG_MASK 0x3f

void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
{
	u8 tcp_flags = 0;

185 186
	if ((flow->key.eth.type == htons(ETH_P_IP) ||
	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
187 188
	    flow->key.ip.proto == IPPROTO_TCP &&
	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
		u8 *tcp = (u8 *)tcp_hdr(skb);
		tcp_flags = *(tcp + TCP_FLAGS_OFFSET) & TCP_FLAG_MASK;
	}

	spin_lock(&flow->lock);
	flow->used = jiffies;
	flow->packet_count++;
	flow->byte_count += skb->len;
	flow->tcp_flags |= tcp_flags;
	spin_unlock(&flow->lock);
}

struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *actions)
{
	int actions_len = nla_len(actions);
	struct sw_flow_actions *sfa;

206
	if (actions_len > MAX_ACTIONS_BUFSIZE)
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
		return ERR_PTR(-EINVAL);

	sfa = kmalloc(sizeof(*sfa) + actions_len, GFP_KERNEL);
	if (!sfa)
		return ERR_PTR(-ENOMEM);

	sfa->actions_len = actions_len;
	memcpy(sfa->actions, nla_data(actions), actions_len);
	return sfa;
}

struct sw_flow *ovs_flow_alloc(void)
{
	struct sw_flow *flow;

	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
	if (!flow)
		return ERR_PTR(-ENOMEM);

	spin_lock_init(&flow->lock);
	flow->sf_acts = NULL;

	return flow;
}

static struct hlist_head *find_bucket(struct flow_table *table, u32 hash)
{
	hash = jhash_1word(hash, table->hash_seed);
	return flex_array_get(table->buckets,
				(hash & (table->n_buckets - 1)));
}

static struct flex_array *alloc_buckets(unsigned int n_buckets)
{
	struct flex_array *buckets;
	int i, err;

	buckets = flex_array_alloc(sizeof(struct hlist_head *),
				   n_buckets, GFP_KERNEL);
	if (!buckets)
		return NULL;

	err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
	if (err) {
		flex_array_free(buckets);
		return NULL;
	}

	for (i = 0; i < n_buckets; i++)
		INIT_HLIST_HEAD((struct hlist_head *)
					flex_array_get(buckets, i));

	return buckets;
}

static void free_buckets(struct flex_array *buckets)
{
	flex_array_free(buckets);
}

struct flow_table *ovs_flow_tbl_alloc(int new_size)
{
	struct flow_table *table = kmalloc(sizeof(*table), GFP_KERNEL);

	if (!table)
		return NULL;

	table->buckets = alloc_buckets(new_size);

	if (!table->buckets) {
		kfree(table);
		return NULL;
	}
	table->n_buckets = new_size;
	table->count = 0;
	table->node_ver = 0;
	table->keep_flows = false;
	get_random_bytes(&table->hash_seed, sizeof(u32));

	return table;
}

void ovs_flow_tbl_destroy(struct flow_table *table)
{
	int i;

	if (!table)
		return;

	if (table->keep_flows)
		goto skip_flows;

	for (i = 0; i < table->n_buckets; i++) {
		struct sw_flow *flow;
		struct hlist_head *head = flex_array_get(table->buckets, i);
		struct hlist_node *node, *n;
		int ver = table->node_ver;

		hlist_for_each_entry_safe(flow, node, n, head, hash_node[ver]) {
			hlist_del_rcu(&flow->hash_node[ver]);
			ovs_flow_free(flow);
		}
	}

skip_flows:
	free_buckets(table->buckets);
	kfree(table);
}

static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
{
	struct flow_table *table = container_of(rcu, struct flow_table, rcu);

	ovs_flow_tbl_destroy(table);
}

void ovs_flow_tbl_deferred_destroy(struct flow_table *table)
{
	if (!table)
		return;

	call_rcu(&table->rcu, flow_tbl_destroy_rcu_cb);
}

struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *last)
{
	struct sw_flow *flow;
	struct hlist_head *head;
	struct hlist_node *n;
	int ver;
	int i;

	ver = table->node_ver;
	while (*bucket < table->n_buckets) {
		i = 0;
		head = flex_array_get(table->buckets, *bucket);
		hlist_for_each_entry_rcu(flow, n, head, hash_node[ver]) {
			if (i < *last) {
				i++;
				continue;
			}
			*last = i + 1;
			return flow;
		}
		(*bucket)++;
		*last = 0;
	}

	return NULL;
}

static void flow_table_copy_flows(struct flow_table *old, struct flow_table *new)
{
	int old_ver;
	int i;

	old_ver = old->node_ver;
	new->node_ver = !old_ver;

	/* Insert in new table. */
	for (i = 0; i < old->n_buckets; i++) {
		struct sw_flow *flow;
		struct hlist_head *head;
		struct hlist_node *n;

		head = flex_array_get(old->buckets, i);

		hlist_for_each_entry(flow, n, head, hash_node[old_ver])
			ovs_flow_tbl_insert(new, flow);
	}
	old->keep_flows = true;
}

static struct flow_table *__flow_tbl_rehash(struct flow_table *table, int n_buckets)
{
	struct flow_table *new_table;

	new_table = ovs_flow_tbl_alloc(n_buckets);
	if (!new_table)
		return ERR_PTR(-ENOMEM);

	flow_table_copy_flows(table, new_table);

	return new_table;
}

struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table)
{
	return __flow_tbl_rehash(table, table->n_buckets);
}

struct flow_table *ovs_flow_tbl_expand(struct flow_table *table)
{
	return __flow_tbl_rehash(table, table->n_buckets * 2);
}

void ovs_flow_free(struct sw_flow *flow)
{
	if (unlikely(!flow))
		return;

	kfree((struct sf_flow_acts __force *)flow->sf_acts);
	kmem_cache_free(flow_cache, flow);
}

/* RCU callback used by ovs_flow_deferred_free. */
static void rcu_free_flow_callback(struct rcu_head *rcu)
{
	struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);

	ovs_flow_free(flow);
}

/* Schedules 'flow' to be freed after the next RCU grace period.
 * The caller must hold rcu_read_lock for this to be sensible. */
void ovs_flow_deferred_free(struct sw_flow *flow)
{
	call_rcu(&flow->rcu, rcu_free_flow_callback);
}

/* Schedules 'sf_acts' to be freed after the next RCU grace period.
 * The caller must hold rcu_read_lock for this to be sensible. */
void ovs_flow_deferred_free_acts(struct sw_flow_actions *sf_acts)
{
431
	kfree_rcu(sf_acts, rcu);
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
}

static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
{
	struct qtag_prefix {
		__be16 eth_type; /* ETH_P_8021Q */
		__be16 tci;
	};
	struct qtag_prefix *qp;

	if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16)))
		return 0;

	if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
					 sizeof(__be16))))
		return -ENOMEM;

	qp = (struct qtag_prefix *) skb->data;
	key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT);
	__skb_pull(skb, sizeof(struct qtag_prefix));

	return 0;
}

static __be16 parse_ethertype(struct sk_buff *skb)
{
	struct llc_snap_hdr {
		u8  dsap;  /* Always 0xAA */
		u8  ssap;  /* Always 0xAA */
		u8  ctrl;
		u8  oui[3];
		__be16 ethertype;
	};
	struct llc_snap_hdr *llc;
	__be16 proto;

	proto = *(__be16 *) skb->data;
	__skb_pull(skb, sizeof(__be16));

	if (ntohs(proto) >= 1536)
		return proto;

	if (skb->len < sizeof(struct llc_snap_hdr))
		return htons(ETH_P_802_2);

	if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr))))
		return htons(0);

	llc = (struct llc_snap_hdr *) skb->data;
	if (llc->dsap != LLC_SAP_SNAP ||
	    llc->ssap != LLC_SAP_SNAP ||
	    (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0)
		return htons(ETH_P_802_2);

	__skb_pull(skb, sizeof(struct llc_snap_hdr));
	return llc->ethertype;
}

static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
			int *key_lenp, int nh_len)
{
	struct icmp6hdr *icmp = icmp6_hdr(skb);
	int error = 0;
	int key_len;

	/* The ICMPv6 type and code fields use the 16-bit transport port
	 * fields, so we need to store them in 16-bit network byte order.
	 */
	key->ipv6.tp.src = htons(icmp->icmp6_type);
	key->ipv6.tp.dst = htons(icmp->icmp6_code);
	key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);

	if (icmp->icmp6_code == 0 &&
	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
	     icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) {
		int icmp_len = skb->len - skb_transport_offset(skb);
		struct nd_msg *nd;
		int offset;

		key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);

		/* In order to process neighbor discovery options, we need the
		 * entire packet.
		 */
		if (unlikely(icmp_len < sizeof(*nd)))
			goto out;
		if (unlikely(skb_linearize(skb))) {
			error = -ENOMEM;
			goto out;
		}

		nd = (struct nd_msg *)skb_transport_header(skb);
		key->ipv6.nd.target = nd->target;
		key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);

		icmp_len -= sizeof(*nd);
		offset = 0;
		while (icmp_len >= 8) {
			struct nd_opt_hdr *nd_opt =
				 (struct nd_opt_hdr *)(nd->opt + offset);
			int opt_len = nd_opt->nd_opt_len * 8;

			if (unlikely(!opt_len || opt_len > icmp_len))
				goto invalid;

			/* Store the link layer address if the appropriate
			 * option is provided.  It is considered an error if
			 * the same link layer option is specified twice.
			 */
			if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR
			    && opt_len == 8) {
				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
					goto invalid;
				memcpy(key->ipv6.nd.sll,
				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
				   && opt_len == 8) {
				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
					goto invalid;
				memcpy(key->ipv6.nd.tll,
				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
			}

			icmp_len -= opt_len;
			offset += opt_len;
		}
	}

	goto out;

invalid:
	memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target));
	memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll));
	memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll));

out:
	*key_lenp = key_len;
	return error;
}

/**
 * ovs_flow_extract - extracts a flow key from an Ethernet frame.
 * @skb: sk_buff that contains the frame, with skb->data pointing to the
 * Ethernet header
 * @in_port: port number on which @skb was received.
 * @key: output flow key
 * @key_lenp: length of output flow key
 *
 * The caller must ensure that skb->len >= ETH_HLEN.
 *
 * Returns 0 if successful, otherwise a negative errno value.
 *
 * Initializes @skb header pointers as follows:
 *
 *    - skb->mac_header: the Ethernet header.
 *
 *    - skb->network_header: just past the Ethernet header, or just past the
 *      VLAN header, to the first byte of the Ethernet payload.
 *
 *    - skb->transport_header: If key->dl_type is ETH_P_IP or ETH_P_IPV6
 *      on output, then just past the IP header, if one is present and
 *      of a correct length, otherwise the same as skb->network_header.
 *      For other key->dl_type values it is left untouched.
 */
int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key,
		 int *key_lenp)
{
	int error = 0;
	int key_len = SW_FLOW_KEY_OFFSET(eth);
	struct ethhdr *eth;

	memset(key, 0, sizeof(*key));

	key->phy.priority = skb->priority;
	key->phy.in_port = in_port;

	skb_reset_mac_header(skb);

	/* Link layer.  We are guaranteed to have at least the 14 byte Ethernet
	 * header in the linear data area.
	 */
	eth = eth_hdr(skb);
	memcpy(key->eth.src, eth->h_source, ETH_ALEN);
	memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);

	__skb_pull(skb, 2 * ETH_ALEN);

	if (vlan_tx_tag_present(skb))
		key->eth.tci = htons(skb->vlan_tci);
	else if (eth->h_proto == htons(ETH_P_8021Q))
		if (unlikely(parse_vlan(skb, key)))
			return -ENOMEM;

	key->eth.type = parse_ethertype(skb);
	if (unlikely(key->eth.type == htons(0)))
		return -ENOMEM;

	skb_reset_network_header(skb);
	__skb_push(skb, skb->data - skb_mac_header(skb));

	/* Network layer. */
	if (key->eth.type == htons(ETH_P_IP)) {
		struct iphdr *nh;
		__be16 offset;

		key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);

		error = check_iphdr(skb);
		if (unlikely(error)) {
			if (error == -EINVAL) {
				skb->transport_header = skb->network_header;
				error = 0;
			}
			goto out;
		}

		nh = ip_hdr(skb);
		key->ipv4.addr.src = nh->saddr;
		key->ipv4.addr.dst = nh->daddr;

		key->ip.proto = nh->protocol;
		key->ip.tos = nh->tos;
		key->ip.ttl = nh->ttl;

		offset = nh->frag_off & htons(IP_OFFSET);
		if (offset) {
			key->ip.frag = OVS_FRAG_TYPE_LATER;
			goto out;
		}
		if (nh->frag_off & htons(IP_MF) ||
			 skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
			key->ip.frag = OVS_FRAG_TYPE_FIRST;

		/* Transport layer. */
		if (key->ip.proto == IPPROTO_TCP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
			if (tcphdr_ok(skb)) {
				struct tcphdr *tcp = tcp_hdr(skb);
				key->ipv4.tp.src = tcp->source;
				key->ipv4.tp.dst = tcp->dest;
			}
		} else if (key->ip.proto == IPPROTO_UDP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
			if (udphdr_ok(skb)) {
				struct udphdr *udp = udp_hdr(skb);
				key->ipv4.tp.src = udp->source;
				key->ipv4.tp.dst = udp->dest;
			}
		} else if (key->ip.proto == IPPROTO_ICMP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
			if (icmphdr_ok(skb)) {
				struct icmphdr *icmp = icmp_hdr(skb);
				/* The ICMP type and code fields use the 16-bit
				 * transport port fields, so we need to store
				 * them in 16-bit network byte order. */
				key->ipv4.tp.src = htons(icmp->type);
				key->ipv4.tp.dst = htons(icmp->code);
			}
		}

	} else if (key->eth.type == htons(ETH_P_ARP) && arphdr_ok(skb)) {
		struct arp_eth_header *arp;

		arp = (struct arp_eth_header *)skb_network_header(skb);

		if (arp->ar_hrd == htons(ARPHRD_ETHER)
				&& arp->ar_pro == htons(ETH_P_IP)
				&& arp->ar_hln == ETH_ALEN
				&& arp->ar_pln == 4) {

			/* We only match on the lower 8 bits of the opcode. */
			if (ntohs(arp->ar_op) <= 0xff)
				key->ip.proto = ntohs(arp->ar_op);

			if (key->ip.proto == ARPOP_REQUEST
					|| key->ip.proto == ARPOP_REPLY) {
				memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
				memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
				memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
				memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
				key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
			}
		}
	} else if (key->eth.type == htons(ETH_P_IPV6)) {
		int nh_len;             /* IPv6 Header + Extensions */

		nh_len = parse_ipv6hdr(skb, key, &key_len);
		if (unlikely(nh_len < 0)) {
			if (nh_len == -EINVAL)
				skb->transport_header = skb->network_header;
			else
				error = nh_len;
			goto out;
		}

		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
			goto out;
		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
			key->ip.frag = OVS_FRAG_TYPE_FIRST;

		/* Transport layer. */
		if (key->ip.proto == NEXTHDR_TCP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
			if (tcphdr_ok(skb)) {
				struct tcphdr *tcp = tcp_hdr(skb);
				key->ipv6.tp.src = tcp->source;
				key->ipv6.tp.dst = tcp->dest;
			}
		} else if (key->ip.proto == NEXTHDR_UDP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
			if (udphdr_ok(skb)) {
				struct udphdr *udp = udp_hdr(skb);
				key->ipv6.tp.src = udp->source;
				key->ipv6.tp.dst = udp->dest;
			}
		} else if (key->ip.proto == NEXTHDR_ICMP) {
			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
			if (icmp6hdr_ok(skb)) {
				error = parse_icmpv6(skb, key, &key_len, nh_len);
				if (error < 0)
					goto out;
			}
		}
	}

out:
	*key_lenp = key_len;
	return error;
}

u32 ovs_flow_hash(const struct sw_flow_key *key, int key_len)
{
	return jhash2((u32 *)key, DIV_ROUND_UP(key_len, sizeof(u32)), 0);
}

struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
				struct sw_flow_key *key, int key_len)
{
	struct sw_flow *flow;
	struct hlist_node *n;
	struct hlist_head *head;
	u32 hash;

	hash = ovs_flow_hash(key, key_len);

	head = find_bucket(table, hash);
	hlist_for_each_entry_rcu(flow, n, head, hash_node[table->node_ver]) {

		if (flow->hash == hash &&
		    !memcmp(&flow->key, key, key_len)) {
			return flow;
		}
	}
	return NULL;
}

void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow)
{
	struct hlist_head *head;

	head = find_bucket(table, flow->hash);
	hlist_add_head_rcu(&flow->hash_node[table->node_ver], head);
	table->count++;
}

void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
{
	hlist_del_rcu(&flow->hash_node[table->node_ver]);
	table->count--;
	BUG_ON(table->count < 0);
}

/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
	[OVS_KEY_ATTR_ENCAP] = -1,
	[OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
	[OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
	[OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
	[OVS_KEY_ATTR_VLAN] = sizeof(__be16),
	[OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
	[OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
	[OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
	[OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
	[OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
	[OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
	[OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
	[OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
	[OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
};

static int ipv4_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
				  const struct nlattr *a[], u32 *attrs)
{
	const struct ovs_key_icmp *icmp_key;
	const struct ovs_key_tcp *tcp_key;
	const struct ovs_key_udp *udp_key;

	switch (swkey->ip.proto) {
	case IPPROTO_TCP:
		if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_TCP);

		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
		swkey->ipv4.tp.src = tcp_key->tcp_src;
		swkey->ipv4.tp.dst = tcp_key->tcp_dst;
		break;

	case IPPROTO_UDP:
		if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_UDP);

		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
		swkey->ipv4.tp.src = udp_key->udp_src;
		swkey->ipv4.tp.dst = udp_key->udp_dst;
		break;

	case IPPROTO_ICMP:
		if (!(*attrs & (1 << OVS_KEY_ATTR_ICMP)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_ICMP);

		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
		icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
		swkey->ipv4.tp.src = htons(icmp_key->icmp_type);
		swkey->ipv4.tp.dst = htons(icmp_key->icmp_code);
		break;
	}

	return 0;
}

static int ipv6_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
				  const struct nlattr *a[], u32 *attrs)
{
	const struct ovs_key_icmpv6 *icmpv6_key;
	const struct ovs_key_tcp *tcp_key;
	const struct ovs_key_udp *udp_key;

	switch (swkey->ip.proto) {
	case IPPROTO_TCP:
		if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_TCP);

		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
		swkey->ipv6.tp.src = tcp_key->tcp_src;
		swkey->ipv6.tp.dst = tcp_key->tcp_dst;
		break;

	case IPPROTO_UDP:
		if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_UDP);

		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
		swkey->ipv6.tp.src = udp_key->udp_src;
		swkey->ipv6.tp.dst = udp_key->udp_dst;
		break;

	case IPPROTO_ICMPV6:
		if (!(*attrs & (1 << OVS_KEY_ATTR_ICMPV6)))
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);

		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
		icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
		swkey->ipv6.tp.src = htons(icmpv6_key->icmpv6_type);
		swkey->ipv6.tp.dst = htons(icmpv6_key->icmpv6_code);

		if (swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
		    swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
			const struct ovs_key_nd *nd_key;

			if (!(*attrs & (1 << OVS_KEY_ATTR_ND)))
				return -EINVAL;
			*attrs &= ~(1 << OVS_KEY_ATTR_ND);

			*key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
			nd_key = nla_data(a[OVS_KEY_ATTR_ND]);
			memcpy(&swkey->ipv6.nd.target, nd_key->nd_target,
			       sizeof(swkey->ipv6.nd.target));
			memcpy(swkey->ipv6.nd.sll, nd_key->nd_sll, ETH_ALEN);
			memcpy(swkey->ipv6.nd.tll, nd_key->nd_tll, ETH_ALEN);
		}
		break;
	}

	return 0;
}

static int parse_flow_nlattrs(const struct nlattr *attr,
			      const struct nlattr *a[], u32 *attrsp)
{
	const struct nlattr *nla;
	u32 attrs;
	int rem;

	attrs = 0;
	nla_for_each_nested(nla, attr, rem) {
		u16 type = nla_type(nla);
		int expected_len;

		if (type > OVS_KEY_ATTR_MAX || attrs & (1 << type))
			return -EINVAL;

		expected_len = ovs_key_lens[type];
		if (nla_len(nla) != expected_len && expected_len != -1)
			return -EINVAL;

		attrs |= 1 << type;
		a[type] = nla;
	}
	if (rem)
		return -EINVAL;

	*attrsp = attrs;
	return 0;
}

/**
 * ovs_flow_from_nlattrs - parses Netlink attributes into a flow key.
 * @swkey: receives the extracted flow key.
 * @key_lenp: number of bytes used in @swkey.
 * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
 * sequence.
 */
int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
		      const struct nlattr *attr)
{
	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
	const struct ovs_key_ethernet *eth_key;
	int key_len;
	u32 attrs;
	int err;

	memset(swkey, 0, sizeof(struct sw_flow_key));
	key_len = SW_FLOW_KEY_OFFSET(eth);

	err = parse_flow_nlattrs(attr, a, &attrs);
	if (err)
		return err;

	/* Metadata attributes. */
	if (attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
		swkey->phy.priority = nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]);
		attrs &= ~(1 << OVS_KEY_ATTR_PRIORITY);
	}
	if (attrs & (1 << OVS_KEY_ATTR_IN_PORT)) {
		u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);
		if (in_port >= DP_MAX_PORTS)
			return -EINVAL;
		swkey->phy.in_port = in_port;
		attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT);
	} else {
992
		swkey->phy.in_port = DP_MAX_PORTS;
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 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
	}

	/* Data attributes. */
	if (!(attrs & (1 << OVS_KEY_ATTR_ETHERNET)))
		return -EINVAL;
	attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);

	eth_key = nla_data(a[OVS_KEY_ATTR_ETHERNET]);
	memcpy(swkey->eth.src, eth_key->eth_src, ETH_ALEN);
	memcpy(swkey->eth.dst, eth_key->eth_dst, ETH_ALEN);

	if (attrs & (1u << OVS_KEY_ATTR_ETHERTYPE) &&
	    nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q)) {
		const struct nlattr *encap;
		__be16 tci;

		if (attrs != ((1 << OVS_KEY_ATTR_VLAN) |
			      (1 << OVS_KEY_ATTR_ETHERTYPE) |
			      (1 << OVS_KEY_ATTR_ENCAP)))
			return -EINVAL;

		encap = a[OVS_KEY_ATTR_ENCAP];
		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
		if (tci & htons(VLAN_TAG_PRESENT)) {
			swkey->eth.tci = tci;

			err = parse_flow_nlattrs(encap, a, &attrs);
			if (err)
				return err;
		} else if (!tci) {
			/* Corner case for truncated 802.1Q header. */
			if (nla_len(encap))
				return -EINVAL;

			swkey->eth.type = htons(ETH_P_8021Q);
			*key_lenp = key_len;
			return 0;
		} else {
			return -EINVAL;
		}
	}

	if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
		swkey->eth.type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
		if (ntohs(swkey->eth.type) < 1536)
			return -EINVAL;
		attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
	} else {
		swkey->eth.type = htons(ETH_P_802_2);
	}

	if (swkey->eth.type == htons(ETH_P_IP)) {
		const struct ovs_key_ipv4 *ipv4_key;

		if (!(attrs & (1 << OVS_KEY_ATTR_IPV4)))
			return -EINVAL;
		attrs &= ~(1 << OVS_KEY_ATTR_IPV4);

		key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);
		ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
		if (ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX)
			return -EINVAL;
		swkey->ip.proto = ipv4_key->ipv4_proto;
		swkey->ip.tos = ipv4_key->ipv4_tos;
		swkey->ip.ttl = ipv4_key->ipv4_ttl;
		swkey->ip.frag = ipv4_key->ipv4_frag;
		swkey->ipv4.addr.src = ipv4_key->ipv4_src;
		swkey->ipv4.addr.dst = ipv4_key->ipv4_dst;

		if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
			err = ipv4_flow_from_nlattrs(swkey, &key_len, a, &attrs);
			if (err)
				return err;
		}
	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
		const struct ovs_key_ipv6 *ipv6_key;

		if (!(attrs & (1 << OVS_KEY_ATTR_IPV6)))
			return -EINVAL;
		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);

		key_len = SW_FLOW_KEY_OFFSET(ipv6.label);
		ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
		if (ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX)
			return -EINVAL;
		swkey->ipv6.label = ipv6_key->ipv6_label;
		swkey->ip.proto = ipv6_key->ipv6_proto;
		swkey->ip.tos = ipv6_key->ipv6_tclass;
		swkey->ip.ttl = ipv6_key->ipv6_hlimit;
		swkey->ip.frag = ipv6_key->ipv6_frag;
		memcpy(&swkey->ipv6.addr.src, ipv6_key->ipv6_src,
		       sizeof(swkey->ipv6.addr.src));
		memcpy(&swkey->ipv6.addr.dst, ipv6_key->ipv6_dst,
		       sizeof(swkey->ipv6.addr.dst));

		if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
			err = ipv6_flow_from_nlattrs(swkey, &key_len, a, &attrs);
			if (err)
				return err;
		}
	} else if (swkey->eth.type == htons(ETH_P_ARP)) {
		const struct ovs_key_arp *arp_key;

		if (!(attrs & (1 << OVS_KEY_ATTR_ARP)))
			return -EINVAL;
		attrs &= ~(1 << OVS_KEY_ATTR_ARP);

		key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
		arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
		swkey->ipv4.addr.src = arp_key->arp_sip;
		swkey->ipv4.addr.dst = arp_key->arp_tip;
		if (arp_key->arp_op & htons(0xff00))
			return -EINVAL;
		swkey->ip.proto = ntohs(arp_key->arp_op);
		memcpy(swkey->ipv4.arp.sha, arp_key->arp_sha, ETH_ALEN);
		memcpy(swkey->ipv4.arp.tha, arp_key->arp_tha, ETH_ALEN);
	}

	if (attrs)
		return -EINVAL;
	*key_lenp = key_len;

	return 0;
}

/**
 * ovs_flow_metadata_from_nlattrs - parses Netlink attributes into a flow key.
 * @in_port: receives the extracted input port.
 * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
 * sequence.
 *
 * This parses a series of Netlink attributes that form a flow key, which must
 * take the same form accepted by flow_from_nlattrs(), but only enough of it to
 * get the metadata, that is, the parts of the flow key that cannot be
 * extracted from the packet itself.
 */
int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
			       const struct nlattr *attr)
{
	const struct nlattr *nla;
	int rem;

1135
	*in_port = DP_MAX_PORTS;
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
	*priority = 0;

	nla_for_each_nested(nla, attr, rem) {
		int type = nla_type(nla);

		if (type <= OVS_KEY_ATTR_MAX && ovs_key_lens[type] > 0) {
			if (nla_len(nla) != ovs_key_lens[type])
				return -EINVAL;

			switch (type) {
			case OVS_KEY_ATTR_PRIORITY:
				*priority = nla_get_u32(nla);
				break;

			case OVS_KEY_ATTR_IN_PORT:
				if (nla_get_u32(nla) >= DP_MAX_PORTS)
					return -EINVAL;
				*in_port = nla_get_u32(nla);
				break;
			}
		}
	}
	if (rem)
		return -EINVAL;
	return 0;
}

int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb)
{
	struct ovs_key_ethernet *eth_key;
	struct nlattr *nla, *encap;

1168 1169 1170
	if (swkey->phy.priority &&
	    nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, swkey->phy.priority))
		goto nla_put_failure;
1171

1172
	if (swkey->phy.in_port != DP_MAX_PORTS &&
1173 1174
	    nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port))
		goto nla_put_failure;
1175 1176 1177 1178 1179 1180 1181 1182 1183

	nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
	if (!nla)
		goto nla_put_failure;
	eth_key = nla_data(nla);
	memcpy(eth_key->eth_src, swkey->eth.src, ETH_ALEN);
	memcpy(eth_key->eth_dst, swkey->eth.dst, ETH_ALEN);

	if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
1184 1185 1186
		if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, htons(ETH_P_8021Q)) ||
		    nla_put_be16(skb, OVS_KEY_ATTR_VLAN, swkey->eth.tci))
			goto nla_put_failure;
1187 1188 1189 1190 1191 1192 1193 1194 1195 1196
		encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
		if (!swkey->eth.tci)
			goto unencap;
	} else {
		encap = NULL;
	}

	if (swkey->eth.type == htons(ETH_P_802_2))
		goto unencap;

1197 1198
	if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, swkey->eth.type))
		goto nla_put_failure;
1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 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 1275 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 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340

	if (swkey->eth.type == htons(ETH_P_IP)) {
		struct ovs_key_ipv4 *ipv4_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV4, sizeof(*ipv4_key));
		if (!nla)
			goto nla_put_failure;
		ipv4_key = nla_data(nla);
		ipv4_key->ipv4_src = swkey->ipv4.addr.src;
		ipv4_key->ipv4_dst = swkey->ipv4.addr.dst;
		ipv4_key->ipv4_proto = swkey->ip.proto;
		ipv4_key->ipv4_tos = swkey->ip.tos;
		ipv4_key->ipv4_ttl = swkey->ip.ttl;
		ipv4_key->ipv4_frag = swkey->ip.frag;
	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
		struct ovs_key_ipv6 *ipv6_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
		if (!nla)
			goto nla_put_failure;
		ipv6_key = nla_data(nla);
		memcpy(ipv6_key->ipv6_src, &swkey->ipv6.addr.src,
				sizeof(ipv6_key->ipv6_src));
		memcpy(ipv6_key->ipv6_dst, &swkey->ipv6.addr.dst,
				sizeof(ipv6_key->ipv6_dst));
		ipv6_key->ipv6_label = swkey->ipv6.label;
		ipv6_key->ipv6_proto = swkey->ip.proto;
		ipv6_key->ipv6_tclass = swkey->ip.tos;
		ipv6_key->ipv6_hlimit = swkey->ip.ttl;
		ipv6_key->ipv6_frag = swkey->ip.frag;
	} else if (swkey->eth.type == htons(ETH_P_ARP)) {
		struct ovs_key_arp *arp_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key));
		if (!nla)
			goto nla_put_failure;
		arp_key = nla_data(nla);
		memset(arp_key, 0, sizeof(struct ovs_key_arp));
		arp_key->arp_sip = swkey->ipv4.addr.src;
		arp_key->arp_tip = swkey->ipv4.addr.dst;
		arp_key->arp_op = htons(swkey->ip.proto);
		memcpy(arp_key->arp_sha, swkey->ipv4.arp.sha, ETH_ALEN);
		memcpy(arp_key->arp_tha, swkey->ipv4.arp.tha, ETH_ALEN);
	}

	if ((swkey->eth.type == htons(ETH_P_IP) ||
	     swkey->eth.type == htons(ETH_P_IPV6)) &&
	     swkey->ip.frag != OVS_FRAG_TYPE_LATER) {

		if (swkey->ip.proto == IPPROTO_TCP) {
			struct ovs_key_tcp *tcp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_TCP, sizeof(*tcp_key));
			if (!nla)
				goto nla_put_failure;
			tcp_key = nla_data(nla);
			if (swkey->eth.type == htons(ETH_P_IP)) {
				tcp_key->tcp_src = swkey->ipv4.tp.src;
				tcp_key->tcp_dst = swkey->ipv4.tp.dst;
			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
				tcp_key->tcp_src = swkey->ipv6.tp.src;
				tcp_key->tcp_dst = swkey->ipv6.tp.dst;
			}
		} else if (swkey->ip.proto == IPPROTO_UDP) {
			struct ovs_key_udp *udp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_UDP, sizeof(*udp_key));
			if (!nla)
				goto nla_put_failure;
			udp_key = nla_data(nla);
			if (swkey->eth.type == htons(ETH_P_IP)) {
				udp_key->udp_src = swkey->ipv4.tp.src;
				udp_key->udp_dst = swkey->ipv4.tp.dst;
			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
				udp_key->udp_src = swkey->ipv6.tp.src;
				udp_key->udp_dst = swkey->ipv6.tp.dst;
			}
		} else if (swkey->eth.type == htons(ETH_P_IP) &&
			   swkey->ip.proto == IPPROTO_ICMP) {
			struct ovs_key_icmp *icmp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMP, sizeof(*icmp_key));
			if (!nla)
				goto nla_put_failure;
			icmp_key = nla_data(nla);
			icmp_key->icmp_type = ntohs(swkey->ipv4.tp.src);
			icmp_key->icmp_code = ntohs(swkey->ipv4.tp.dst);
		} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
			   swkey->ip.proto == IPPROTO_ICMPV6) {
			struct ovs_key_icmpv6 *icmpv6_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMPV6,
						sizeof(*icmpv6_key));
			if (!nla)
				goto nla_put_failure;
			icmpv6_key = nla_data(nla);
			icmpv6_key->icmpv6_type = ntohs(swkey->ipv6.tp.src);
			icmpv6_key->icmpv6_code = ntohs(swkey->ipv6.tp.dst);

			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
				struct ovs_key_nd *nd_key;

				nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
				if (!nla)
					goto nla_put_failure;
				nd_key = nla_data(nla);
				memcpy(nd_key->nd_target, &swkey->ipv6.nd.target,
							sizeof(nd_key->nd_target));
				memcpy(nd_key->nd_sll, swkey->ipv6.nd.sll, ETH_ALEN);
				memcpy(nd_key->nd_tll, swkey->ipv6.nd.tll, ETH_ALEN);
			}
		}
	}

unencap:
	if (encap)
		nla_nest_end(skb, encap);

	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

/* Initializes the flow module.
 * Returns zero if successful or a negative error code. */
int ovs_flow_init(void)
{
	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
					0, NULL);
	if (flow_cache == NULL)
		return -ENOMEM;

	return 0;
}

/* Uninitializes the flow module. */
void ovs_flow_exit(void)
{
	kmem_cache_destroy(flow_cache);
}