conntrack.c 42.2 KB
Newer Older
J
Joe Stringer 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * Copyright (c) 2015 Nicira, Inc.
 *
 * 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.
 */

#include <linux/module.h>
#include <linux/openvswitch.h>
16 17 18
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/sctp.h>
J
Joe Stringer 已提交
19 20
#include <net/ip.h>
#include <net/netfilter/nf_conntrack_core.h>
21
#include <net/netfilter/nf_conntrack_helper.h>
22
#include <net/netfilter/nf_conntrack_labels.h>
23
#include <net/netfilter/nf_conntrack_seqadj.h>
J
Joe Stringer 已提交
24 25 26
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>

27 28 29 30 31 32
#ifdef CONFIG_NF_NAT_NEEDED
#include <linux/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
#endif

J
Joe Stringer 已提交
33 34 35 36 37 38
#include "datapath.h"
#include "conntrack.h"
#include "flow.h"
#include "flow_netlink.h"

struct ovs_ct_len_tbl {
39 40
	int maxlen;
	int minlen;
J
Joe Stringer 已提交
41 42
};

43 44 45 46 47 48
/* Metadata mark for masked write to conntrack mark */
struct md_mark {
	u32 value;
	u32 mask;
};

49
/* Metadata label for masked write to conntrack label. */
J
Joe Stringer 已提交
50 51 52
struct md_labels {
	struct ovs_key_ct_labels value;
	struct ovs_key_ct_labels mask;
53 54
};

55 56 57 58 59 60
enum ovs_ct_nat {
	OVS_CT_NAT = 1 << 0,     /* NAT for committed connections only. */
	OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */
	OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */
};

J
Joe Stringer 已提交
61 62
/* Conntrack action context for execution. */
struct ovs_conntrack_info {
63
	struct nf_conntrack_helper *helper;
J
Joe Stringer 已提交
64 65
	struct nf_conntrack_zone zone;
	struct nf_conn *ct;
66
	u8 commit : 1;
67
	u8 nat : 3;                 /* enum ovs_ct_nat */
J
Jarno Rajahalme 已提交
68
	u8 force : 1;
J
Joe Stringer 已提交
69
	u16 family;
70
	struct md_mark mark;
J
Joe Stringer 已提交
71
	struct md_labels labels;
72 73 74
#ifdef CONFIG_NF_NAT_NEEDED
	struct nf_nat_range range;  /* Only present for SRC NAT and DST NAT. */
#endif
J
Joe Stringer 已提交
75 76
};

77 78
static bool labels_nonzero(const struct ovs_key_ct_labels *labels);

79 80
static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info);

J
Joe Stringer 已提交
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
static u16 key_to_nfproto(const struct sw_flow_key *key)
{
	switch (ntohs(key->eth.type)) {
	case ETH_P_IP:
		return NFPROTO_IPV4;
	case ETH_P_IPV6:
		return NFPROTO_IPV6;
	default:
		return NFPROTO_UNSPEC;
	}
}

/* Map SKB connection state into the values used by flow definition. */
static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo)
{
	u8 ct_state = OVS_CS_F_TRACKED;

	switch (ctinfo) {
	case IP_CT_ESTABLISHED_REPLY:
	case IP_CT_RELATED_REPLY:
		ct_state |= OVS_CS_F_REPLY_DIR;
		break;
	default:
		break;
	}

	switch (ctinfo) {
	case IP_CT_ESTABLISHED:
	case IP_CT_ESTABLISHED_REPLY:
		ct_state |= OVS_CS_F_ESTABLISHED;
		break;
	case IP_CT_RELATED:
	case IP_CT_RELATED_REPLY:
		ct_state |= OVS_CS_F_RELATED;
		break;
	case IP_CT_NEW:
		ct_state |= OVS_CS_F_NEW;
		break;
	default:
		break;
	}

	return ct_state;
}

126 127 128 129 130 131 132 133 134
static u32 ovs_ct_get_mark(const struct nf_conn *ct)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
	return ct ? ct->mark : 0;
#else
	return 0;
#endif
}

135 136 137 138 139
/* Guard against conntrack labels max size shrinking below 128 bits. */
#if NF_CT_LABELS_MAX_SIZE < 16
#error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes
#endif

J
Joe Stringer 已提交
140 141
static void ovs_ct_get_labels(const struct nf_conn *ct,
			      struct ovs_key_ct_labels *labels)
142 143 144
{
	struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;

145 146 147
	if (cl)
		memcpy(labels, cl->bits, OVS_CT_LABELS_LEN);
	else
J
Joe Stringer 已提交
148
		memset(labels, 0, OVS_CT_LABELS_LEN);
149 150
}

151 152 153 154
static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key,
					const struct nf_conntrack_tuple *orig,
					u8 icmp_proto)
{
155
	key->ct_orig_proto = orig->dst.protonum;
156 157 158 159 160 161 162 163 164
	if (orig->dst.protonum == icmp_proto) {
		key->ct.orig_tp.src = htons(orig->dst.u.icmp.type);
		key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code);
	} else {
		key->ct.orig_tp.src = orig->src.u.all;
		key->ct.orig_tp.dst = orig->dst.u.all;
	}
}

J
Joe Stringer 已提交
165
static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
166 167
				const struct nf_conntrack_zone *zone,
				const struct nf_conn *ct)
J
Joe Stringer 已提交
168
{
169 170
	key->ct_state = state;
	key->ct_zone = zone->id;
171
	key->ct.mark = ovs_ct_get_mark(ct);
J
Joe Stringer 已提交
172
	ovs_ct_get_labels(ct, &key->ct.labels);
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

	if (ct) {
		const struct nf_conntrack_tuple *orig;

		/* Use the master if we have one. */
		if (ct->master)
			ct = ct->master;
		orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;

		/* IP version must match with the master connection. */
		if (key->eth.type == htons(ETH_P_IP) &&
		    nf_ct_l3num(ct) == NFPROTO_IPV4) {
			key->ipv4.ct_orig.src = orig->src.u3.ip;
			key->ipv4.ct_orig.dst = orig->dst.u3.ip;
			__ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP);
			return;
		} else if (key->eth.type == htons(ETH_P_IPV6) &&
			   !sw_flow_key_is_nd(key) &&
			   nf_ct_l3num(ct) == NFPROTO_IPV6) {
			key->ipv6.ct_orig.src = orig->src.u3.in6;
			key->ipv6.ct_orig.dst = orig->dst.u3.in6;
			__ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP);
			return;
		}
	}
198
	/* Clear 'ct_orig_proto' to mark the non-existence of conntrack
199 200
	 * original direction key fields.
	 */
201
	key->ct_orig_proto = 0;
J
Joe Stringer 已提交
202 203
}

204
/* Update 'key' based on skb->_nfct.  If 'post_ct' is true, then OVS has
205 206 207
 * previously sent the packet to conntrack via the ct action.  If
 * 'keep_nat_flags' is true, the existing NAT flags retained, else they are
 * initialized from the connection status.
J
Joe Stringer 已提交
208 209
 */
static void ovs_ct_update_key(const struct sk_buff *skb,
210
			      const struct ovs_conntrack_info *info,
211 212
			      struct sw_flow_key *key, bool post_ct,
			      bool keep_nat_flags)
J
Joe Stringer 已提交
213 214 215 216 217 218 219 220 221
{
	const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;
	u8 state = 0;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct) {
		state = ovs_ct_get_state(ctinfo);
222
		/* All unconfirmed entries are NEW connections. */
223 224
		if (!nf_ct_is_confirmed(ct))
			state |= OVS_CS_F_NEW;
225 226 227
		/* OVS persists the related flag for the duration of the
		 * connection.
		 */
J
Joe Stringer 已提交
228 229
		if (ct->master)
			state |= OVS_CS_F_RELATED;
230
		if (keep_nat_flags) {
231
			state |= key->ct_state & OVS_CS_F_NAT_MASK;
232 233 234 235 236 237
		} else {
			if (ct->status & IPS_SRC_NAT)
				state |= OVS_CS_F_SRC_NAT;
			if (ct->status & IPS_DST_NAT)
				state |= OVS_CS_F_DST_NAT;
		}
J
Joe Stringer 已提交
238 239 240
		zone = nf_ct_zone(ct);
	} else if (post_ct) {
		state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
241 242
		if (info)
			zone = &info->zone;
J
Joe Stringer 已提交
243
	}
244
	__ovs_ct_update_key(key, state, zone, ct);
J
Joe Stringer 已提交
245 246
}

247 248 249
/* This is called to initialize CT key fields possibly coming in from the local
 * stack.
 */
J
Joe Stringer 已提交
250 251
void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
{
252
	ovs_ct_update_key(skb, NULL, key, false, false);
J
Joe Stringer 已提交
253 254
}

255 256 257 258 259 260
#define IN6_ADDR_INITIALIZER(ADDR) \
	{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
	  (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }

int ovs_ct_put_key(const struct sw_flow_key *swkey,
		   const struct sw_flow_key *output, struct sk_buff *skb)
J
Joe Stringer 已提交
261
{
262
	if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state))
J
Joe Stringer 已提交
263 264 265
		return -EMSGSIZE;

	if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
266
	    nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone))
J
Joe Stringer 已提交
267 268
		return -EMSGSIZE;

269
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
270
	    nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark))
271 272
		return -EMSGSIZE;

273
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
274 275
	    nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels),
		    &output->ct.labels))
276 277
		return -EMSGSIZE;

278
	if (swkey->ct_orig_proto) {
279 280 281 282 283 284
		if (swkey->eth.type == htons(ETH_P_IP)) {
			struct ovs_key_ct_tuple_ipv4 orig = {
				output->ipv4.ct_orig.src,
				output->ipv4.ct_orig.dst,
				output->ct.orig_tp.src,
				output->ct.orig_tp.dst,
285
				output->ct_orig_proto,
286 287 288 289 290 291 292 293 294 295
			};
			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
				    sizeof(orig), &orig))
				return -EMSGSIZE;
		} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
			struct ovs_key_ct_tuple_ipv6 orig = {
				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
				output->ct.orig_tp.src,
				output->ct.orig_tp.dst,
296
				output->ct_orig_proto,
297 298 299 300 301 302 303
			};
			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
				    sizeof(orig), &orig))
				return -EMSGSIZE;
		}
	}

304 305 306
	return 0;
}

307
static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key,
308 309
			   u32 ct_mark, u32 mask)
{
310
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
311 312 313 314 315
	u32 new_mark;

	new_mark = ct_mark | (ct->mark & ~(mask));
	if (ct->mark != new_mark) {
		ct->mark = new_mark;
316 317
		if (nf_ct_is_confirmed(ct))
			nf_conntrack_event_cache(IPCT_MARK, ct);
318 319 320
		key->ct.mark = new_mark;
	}

J
Joe Stringer 已提交
321
	return 0;
322 323 324
#else
	return -ENOTSUPP;
#endif
J
Joe Stringer 已提交
325 326
}

327
static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct)
328 329 330 331 332 333 334 335
{
	struct nf_conn_labels *cl;

	cl = nf_ct_labels_find(ct);
	if (!cl) {
		nf_ct_labels_ext_add(ct);
		cl = nf_ct_labels_find(ct);
	}
336 337 338 339 340 341

	return cl;
}

/* Initialize labels for a new, yet to be committed conntrack entry.  Note that
 * since the new connection is not yet confirmed, and thus no-one else has
342
 * access to it's labels, we simply write them over.
343 344 345 346 347
 */
static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key,
			      const struct ovs_key_ct_labels *labels,
			      const struct ovs_key_ct_labels *mask)
{
348 349 350 351 352 353 354 355
	struct nf_conn_labels *cl, *master_cl;
	bool have_mask = labels_nonzero(mask);

	/* Inherit master's labels to the related connection? */
	master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL;

	if (!master_cl && !have_mask)
		return 0;   /* Nothing to do. */
356 357

	cl = ovs_ct_get_conn_labels(ct);
358
	if (!cl)
359 360
		return -ENOSPC;

361 362 363 364 365 366 367 368 369 370 371 372 373
	/* Inherit the master's labels, if any. */
	if (master_cl)
		*cl = *master_cl;

	if (have_mask) {
		u32 *dst = (u32 *)cl->bits;
		int i;

		for (i = 0; i < OVS_CT_LABELS_LEN_32; i++)
			dst[i] = (dst[i] & ~mask->ct_labels_32[i]) |
				(labels->ct_labels_32[i]
				 & mask->ct_labels_32[i]);
	}
374

375 376 377 378 379
	/* Labels are included in the IPCTNL_MSG_CT_NEW event only if the
	 * IPCT_LABEL bit it set in the event cache.
	 */
	nf_conntrack_event_cache(IPCT_LABEL, ct);

380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402
	memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);

	return 0;
}

static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key,
			     const struct ovs_key_ct_labels *labels,
			     const struct ovs_key_ct_labels *mask)
{
	struct nf_conn_labels *cl;
	int err;

	cl = ovs_ct_get_conn_labels(ct);
	if (!cl)
		return -ENOSPC;

	err = nf_connlabels_replace(ct, labels->ct_labels_32,
				    mask->ct_labels_32,
				    OVS_CT_LABELS_LEN_32);
	if (err)
		return err;

	memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);
403 404 405 406

	return 0;
}

407 408 409 410 411 412 413 414
/* 'skb' should already be pulled to nh_ofs. */
static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
{
	const struct nf_conntrack_helper *helper;
	const struct nf_conn_help *help;
	enum ip_conntrack_info ctinfo;
	unsigned int protoff;
	struct nf_conn *ct;
415
	int err;
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435

	ct = nf_ct_get(skb, &ctinfo);
	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
		return NF_ACCEPT;

	help = nfct_help(ct);
	if (!help)
		return NF_ACCEPT;

	helper = rcu_dereference(help->helper);
	if (!helper)
		return NF_ACCEPT;

	switch (proto) {
	case NFPROTO_IPV4:
		protoff = ip_hdrlen(skb);
		break;
	case NFPROTO_IPV6: {
		u8 nexthdr = ipv6_hdr(skb)->nexthdr;
		__be16 frag_off;
436
		int ofs;
437

438 439 440
		ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
				       &frag_off);
		if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
441 442 443
			pr_debug("proto header not found\n");
			return NF_ACCEPT;
		}
444
		protoff = ofs;
445 446 447 448 449 450 451
		break;
	}
	default:
		WARN_ONCE(1, "helper invoked on non-IP family!");
		return NF_DROP;
	}

452 453 454 455 456 457 458 459 460 461 462 463
	err = helper->help(skb, protoff, ct, ctinfo);
	if (err != NF_ACCEPT)
		return err;

	/* Adjust seqs after helper.  This is needed due to some helpers (e.g.,
	 * FTP with NAT) adusting the TCP payload size when mangling IP
	 * addresses and/or port numbers in the text-based control connection.
	 */
	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
	    !nf_ct_seq_adjust(skb, ct, ctinfo, protoff))
		return NF_DROP;
	return NF_ACCEPT;
464 465
}

466 467 468
/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
 * value if 'skb' is freed.
 */
J
Joe Stringer 已提交
469 470 471 472
static int handle_fragments(struct net *net, struct sw_flow_key *key,
			    u16 zone, struct sk_buff *skb)
{
	struct ovs_skb_cb ovs_cb = *OVS_CB(skb);
473
	int err;
J
Joe Stringer 已提交
474 475 476 477 478

	if (key->eth.type == htons(ETH_P_IP)) {
		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;

		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
479
		err = ip_defrag(net, skb, user);
J
Joe Stringer 已提交
480 481 482 483 484
		if (err)
			return err;

		ovs_cb.mru = IPCB(skb)->frag_max_size;
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
485
	} else if (key->eth.type == htons(ETH_P_IPV6)) {
J
Joe Stringer 已提交
486 487 488
		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;

		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
489
		err = nf_ct_frag6_gather(net, skb, user);
490 491 492
		if (err) {
			if (err != -EINPROGRESS)
				kfree_skb(skb);
493
			return err;
494
		}
J
Joe Stringer 已提交
495

496
		key->ip.proto = ipv6_hdr(skb)->nexthdr;
J
Joe Stringer 已提交
497 498 499
		ovs_cb.mru = IP6CB(skb)->frag_max_size;
#endif
	} else {
500
		kfree_skb(skb);
J
Joe Stringer 已提交
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516
		return -EPFNOSUPPORT;
	}

	key->ip.frag = OVS_FRAG_TYPE_NONE;
	skb_clear_hash(skb);
	skb->ignore_df = 1;
	*OVS_CB(skb) = ovs_cb;

	return 0;
}

static struct nf_conntrack_expect *
ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
		   u16 proto, const struct sk_buff *skb)
{
	struct nf_conntrack_tuple tuple;
517
	struct nf_conntrack_expect *exp;
J
Joe Stringer 已提交
518

519
	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple))
J
Joe Stringer 已提交
520
		return NULL;
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

	exp = __nf_ct_expect_find(net, zone, &tuple);
	if (exp) {
		struct nf_conntrack_tuple_hash *h;

		/* Delete existing conntrack entry, if it clashes with the
		 * expectation.  This can happen since conntrack ALGs do not
		 * check for clashes between (new) expectations and existing
		 * conntrack entries.  nf_conntrack_in() will check the
		 * expectations only if a conntrack entry can not be found,
		 * which can lead to OVS finding the expectation (here) in the
		 * init direction, but which will not be removed by the
		 * nf_conntrack_in() call, if a matching conntrack entry is
		 * found instead.  In this case all init direction packets
		 * would be reported as new related packets, while reply
		 * direction packets would be reported as un-related
		 * established packets.
		 */
		h = nf_conntrack_find_get(net, zone, &tuple);
		if (h) {
			struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

			nf_ct_delete(ct, 0, 0);
			nf_conntrack_put(&ct->ct_general);
		}
	}

	return exp;
J
Joe Stringer 已提交
549 550
}

551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568
/* This replicates logic from nf_conntrack_core.c that is not exported. */
static enum ip_conntrack_info
ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h)
{
	const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
		return IP_CT_ESTABLISHED_REPLY;
	/* Once we've had two way comms, always ESTABLISHED. */
	if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status))
		return IP_CT_ESTABLISHED;
	if (test_bit(IPS_EXPECTED_BIT, &ct->status))
		return IP_CT_RELATED;
	return IP_CT_NEW;
}

/* Find an existing connection which this packet belongs to without
 * re-attributing statistics or modifying the connection state.  This allows an
569
 * skb->_nfct lost due to an upcall to be recovered during actions execution.
570 571 572
 *
 * Must be called with rcu_read_lock.
 *
573 574
 * On success, populates skb->_nfct and returns the connection.  Returns NULL
 * if there is no existing entry.
575 576 577
 */
static struct nf_conn *
ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
578
		     u8 l3num, struct sk_buff *skb, bool natted)
579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
{
	struct nf_conntrack_l3proto *l3proto;
	struct nf_conntrack_l4proto *l4proto;
	struct nf_conntrack_tuple tuple;
	struct nf_conntrack_tuple_hash *h;
	struct nf_conn *ct;
	unsigned int dataoff;
	u8 protonum;

	l3proto = __nf_ct_l3proto_find(l3num);
	if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
				 &protonum) <= 0) {
		pr_debug("ovs_ct_find_existing: Can't get protonum\n");
		return NULL;
	}
	l4proto = __nf_ct_l4proto_find(l3num, protonum);
	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
			     protonum, net, &tuple, l3proto, l4proto)) {
		pr_debug("ovs_ct_find_existing: Can't get tuple\n");
		return NULL;
	}

601 602 603 604 605 606 607 608 609 610 611
	/* Must invert the tuple if skb has been transformed by NAT. */
	if (natted) {
		struct nf_conntrack_tuple inverse;

		if (!nf_ct_invert_tuple(&inverse, &tuple, l3proto, l4proto)) {
			pr_debug("ovs_ct_find_existing: Inversion failed!\n");
			return NULL;
		}
		tuple = inverse;
	}

612 613 614 615 616 617 618
	/* look for tuple match */
	h = nf_conntrack_find_get(net, zone, &tuple);
	if (!h)
		return NULL;   /* Not found. */

	ct = nf_ct_tuplehash_to_ctrack(h);

619 620 621 622 623 624 625
	/* Inverted packet tuple matches the reverse direction conntrack tuple,
	 * select the other tuplehash to get the right 'ctinfo' bits for this
	 * packet.
	 */
	if (natted)
		h = &ct->tuplehash[!h->tuple.dst.dir];

626
	nf_ct_set(skb, ct, ovs_ct_get_info(h));
627 628 629
	return ct;
}

630
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
631 632 633 634
static bool skb_nfct_cached(struct net *net,
			    const struct sw_flow_key *key,
			    const struct ovs_conntrack_info *info,
			    struct sk_buff *skb)
J
Joe Stringer 已提交
635 636 637 638 639
{
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;

	ct = nf_ct_get(skb, &ctinfo);
640
	/* If no ct, check if we have evidence that an existing conntrack entry
641
	 * might be found for this skb.  This happens when we lose a skb->_nfct
642 643 644
	 * due to an upcall.  If the connection was not confirmed, it is not
	 * cached and needs to be run through conntrack again.
	 */
645 646 647
	if (!ct && key->ct_state & OVS_CS_F_TRACKED &&
	    !(key->ct_state & OVS_CS_F_INVALID) &&
	    key->ct_zone == info->zone.id) {
648
		ct = ovs_ct_find_existing(net, &info->zone, info->family, skb,
649
					  !!(key->ct_state
650
					     & OVS_CS_F_NAT_MASK));
J
Jarno Rajahalme 已提交
651 652 653
		if (ct)
			nf_ct_get(skb, &ctinfo);
	}
J
Joe Stringer 已提交
654 655 656 657 658 659
	if (!ct)
		return false;
	if (!net_eq(net, read_pnet(&ct->ct_net)))
		return false;
	if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct)))
		return false;
660 661 662 663 664 665 666
	if (info->helper) {
		struct nf_conn_help *help;

		help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
		if (help && rcu_access_pointer(help->helper) != info->helper)
			return false;
	}
J
Jarno Rajahalme 已提交
667 668 669 670 671 672 673
	/* Force conntrack entry direction to the current packet? */
	if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
		/* Delete the conntrack entry if confirmed, else just release
		 * the reference.
		 */
		if (nf_ct_is_confirmed(ct))
			nf_ct_delete(ct, 0, 0);
674 675

		nf_conntrack_put(&ct->ct_general);
J
Jarno Rajahalme 已提交
676 677 678
		nf_ct_set(skb, NULL, 0);
		return false;
	}
J
Joe Stringer 已提交
679 680 681 682

	return true;
}

683 684 685 686 687 688 689 690 691 692 693 694 695
#ifdef CONFIG_NF_NAT_NEEDED
/* Modelled after nf_nat_ipv[46]_fn().
 * range is only used for new, uninitialized NAT state.
 * Returns either NF_ACCEPT or NF_DROP.
 */
static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
			      enum ip_conntrack_info ctinfo,
			      const struct nf_nat_range *range,
			      enum nf_nat_manip_type maniptype)
{
	int hooknum, nh_off, err = NF_ACCEPT;

	nh_off = skb_network_offset(skb);
696
	skb_pull_rcsum(skb, nh_off);
697 698 699 700 701 702 703 704 705 706

	/* See HOOK2MANIP(). */
	if (maniptype == NF_NAT_MANIP_SRC)
		hooknum = NF_INET_LOCAL_IN; /* Source NAT */
	else
		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */

	switch (ctinfo) {
	case IP_CT_RELATED:
	case IP_CT_RELATED_REPLY:
707 708
		if (IS_ENABLED(CONFIG_NF_NAT_IPV4) &&
		    skb->protocol == htons(ETH_P_IP) &&
709 710 711 712 713
		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
							   hooknum))
				err = NF_DROP;
			goto push;
714 715
		} else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) &&
			   skb->protocol == htons(ETH_P_IPV6)) {
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
			__be16 frag_off;
			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
			int hdrlen = ipv6_skip_exthdr(skb,
						      sizeof(struct ipv6hdr),
						      &nexthdr, &frag_off);

			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
				if (!nf_nat_icmpv6_reply_translation(skb, ct,
								     ctinfo,
								     hooknum,
								     hdrlen))
					err = NF_DROP;
				goto push;
			}
		}
		/* Non-ICMP, fall thru to initialize if needed. */
	case IP_CT_NEW:
		/* Seen it before?  This can happen for loopback, retrans,
		 * or local packets.
		 */
		if (!nf_nat_initialized(ct, maniptype)) {
			/* Initialize according to the NAT action. */
			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
				/* Action is set up to establish a new
				 * mapping.
				 */
				? nf_nat_setup_info(ct, range, maniptype)
				: nf_nat_alloc_null_binding(ct, hooknum);
			if (err != NF_ACCEPT)
				goto push;
		}
		break;

	case IP_CT_ESTABLISHED:
	case IP_CT_ESTABLISHED_REPLY:
		break;

	default:
		err = NF_DROP;
		goto push;
	}

	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
push:
	skb_push(skb, nh_off);
761
	skb_postpush_rcsum(skb, skb->data, nh_off);
762 763 764 765 766 767 768 769 770 771 772

	return err;
}

static void ovs_nat_update_key(struct sw_flow_key *key,
			       const struct sk_buff *skb,
			       enum nf_nat_manip_type maniptype)
{
	if (maniptype == NF_NAT_MANIP_SRC) {
		__be16 src;

773
		key->ct_state |= OVS_CS_F_SRC_NAT;
774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
		if (key->eth.type == htons(ETH_P_IP))
			key->ipv4.addr.src = ip_hdr(skb)->saddr;
		else if (key->eth.type == htons(ETH_P_IPV6))
			memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
			       sizeof(key->ipv6.addr.src));
		else
			return;

		if (key->ip.proto == IPPROTO_UDP)
			src = udp_hdr(skb)->source;
		else if (key->ip.proto == IPPROTO_TCP)
			src = tcp_hdr(skb)->source;
		else if (key->ip.proto == IPPROTO_SCTP)
			src = sctp_hdr(skb)->source;
		else
			return;

		key->tp.src = src;
	} else {
		__be16 dst;

795
		key->ct_state |= OVS_CS_F_DST_NAT;
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
		if (key->eth.type == htons(ETH_P_IP))
			key->ipv4.addr.dst = ip_hdr(skb)->daddr;
		else if (key->eth.type == htons(ETH_P_IPV6))
			memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
			       sizeof(key->ipv6.addr.dst));
		else
			return;

		if (key->ip.proto == IPPROTO_UDP)
			dst = udp_hdr(skb)->dest;
		else if (key->ip.proto == IPPROTO_TCP)
			dst = tcp_hdr(skb)->dest;
		else if (key->ip.proto == IPPROTO_SCTP)
			dst = sctp_hdr(skb)->dest;
		else
			return;

		key->tp.dst = dst;
	}
}

/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
		      const struct ovs_conntrack_info *info,
		      struct sk_buff *skb, struct nf_conn *ct,
		      enum ip_conntrack_info ctinfo)
{
	enum nf_nat_manip_type maniptype;
	int err;

	if (nf_ct_is_untracked(ct)) {
		/* A NAT action may only be performed on tracked packets. */
		return NF_ACCEPT;
	}

	/* Add NAT extension if not confirmed yet. */
	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
		return NF_ACCEPT;   /* Can't NAT. */

	/* Determine NAT type.
	 * Check if the NAT type can be deduced from the tracked connection.
837 838
	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
	 * when committing.
839 840 841
	 */
	if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW &&
	    ct->status & IPS_NAT_MASK &&
842
	    (ctinfo != IP_CT_RELATED || info->commit)) {
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
		/* NAT an established or related connection like before. */
		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
			/* This is the REPLY direction for a connection
			 * for which NAT was applied in the forward
			 * direction.  Do the reverse NAT.
			 */
			maniptype = ct->status & IPS_SRC_NAT
				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
		else
			maniptype = ct->status & IPS_SRC_NAT
				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
	} else if (info->nat & OVS_CT_SRC_NAT) {
		maniptype = NF_NAT_MANIP_SRC;
	} else if (info->nat & OVS_CT_DST_NAT) {
		maniptype = NF_NAT_MANIP_DST;
	} else {
		return NF_ACCEPT; /* Connection is not NATed. */
	}
	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);

	/* Mark NAT done if successful and update the flow key. */
	if (err == NF_ACCEPT)
		ovs_nat_update_key(key, skb, maniptype);

	return err;
}
#else /* !CONFIG_NF_NAT_NEEDED */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
		      const struct ovs_conntrack_info *info,
		      struct sk_buff *skb, struct nf_conn *ct,
		      enum ip_conntrack_info ctinfo)
{
	return NF_ACCEPT;
}
#endif

879
/* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if
880 881
 * not done already.  Update key with new CT state after passing the packet
 * through conntrack.
882
 * Note that if the packet is deemed invalid by conntrack, skb->_nfct will be
883 884
 * set to NULL and 0 will be returned.
 */
885
static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
J
Joe Stringer 已提交
886 887 888 889 890 891 892 893
			   const struct ovs_conntrack_info *info,
			   struct sk_buff *skb)
{
	/* If we are recirculating packets to match on conntrack fields and
	 * committing with a separate conntrack action,  then we don't need to
	 * actually run the packet through conntrack twice unless it's for a
	 * different zone.
	 */
894 895 896 897 898
	bool cached = skb_nfct_cached(net, key, info, skb);
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;

	if (!cached) {
J
Joe Stringer 已提交
899
		struct nf_conn *tmpl = info->ct;
900
		int err;
J
Joe Stringer 已提交
901 902 903

		/* Associate skb with specified zone. */
		if (tmpl) {
904 905
			if (skb_nfct(skb))
				nf_conntrack_put(skb_nfct(skb));
J
Joe Stringer 已提交
906
			nf_conntrack_get(&tmpl->ct_general);
907
			nf_ct_set(skb, tmpl, IP_CT_NEW);
J
Joe Stringer 已提交
908 909
		}

910 911
		err = nf_conntrack_in(net, info->family,
				      NF_INET_PRE_ROUTING, skb);
912
		if (err != NF_ACCEPT)
J
Joe Stringer 已提交
913
			return -ENOENT;
914

915 916 917 918
		/* Clear CT state NAT flags to mark that we have not yet done
		 * NAT after the nf_conntrack_in() call.  We can actually clear
		 * the whole state, as it will be re-initialized below.
		 */
919
		key->ct_state = 0;
920 921 922

		/* Update the key, but keep the NAT flags. */
		ovs_ct_update_key(skb, info, key, true, true);
923
	}
924

925
	ct = nf_ct_get(skb, &ctinfo);
926 927 928 929 930 931 932 933 934
	if (ct) {
		/* Packets starting a new connection must be NATted before the
		 * helper, so that the helper knows about the NAT.  We enforce
		 * this by delaying both NAT and helper calls for unconfirmed
		 * connections until the committing CT action.  For later
		 * packets NAT and Helper may be called in either order.
		 *
		 * NAT will be done only if the CT action has NAT, and only
		 * once per packet (per zone), as guarded by the NAT bits in
935
		 * the key->ct_state.
936
		 */
937
		if (info->nat && !(key->ct_state & OVS_CS_F_NAT_MASK) &&
938 939 940 941 942
		    (nf_ct_is_confirmed(ct) || info->commit) &&
		    ovs_ct_nat(net, key, info, skb, ct, ctinfo) != NF_ACCEPT) {
			return -EINVAL;
		}

943 944 945 946 947 948 949 950 951 952 953 954 955
		/* Userspace may decide to perform a ct lookup without a helper
		 * specified followed by a (recirculate and) commit with one.
		 * Therefore, for unconfirmed connections which we will commit,
		 * we need to attach the helper here.
		 */
		if (!nf_ct_is_confirmed(ct) && info->commit &&
		    info->helper && !nfct_help(ct)) {
			int err = __nf_ct_try_assign_helper(ct, info->ct,
							    GFP_ATOMIC);
			if (err)
				return err;
		}

956 957 958 959 960 961 962 963 964
		/* Call the helper only if:
		 * - nf_conntrack_in() was executed above ("!cached") for a
		 *   confirmed connection, or
		 * - When committing an unconfirmed connection.
		 */
		if ((nf_ct_is_confirmed(ct) ? !cached : info->commit) &&
		    ovs_ct_helper(skb, info->family) != NF_ACCEPT) {
			return -EINVAL;
		}
J
Joe Stringer 已提交
965 966 967 968 969 970 971 972 973 974 975 976
	}

	return 0;
}

/* Lookup connection and read fields into key. */
static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
			 const struct ovs_conntrack_info *info,
			 struct sk_buff *skb)
{
	struct nf_conntrack_expect *exp;

977 978 979 980 981 982 983
	/* If we pass an expected packet through nf_conntrack_in() the
	 * expectation is typically removed, but the packet could still be
	 * lost in upcall processing.  To prevent this from happening we
	 * perform an explicit expectation lookup.  Expected connections are
	 * always new, and will be passed through conntrack only when they are
	 * committed, as it is OK to remove the expectation at that time.
	 */
J
Joe Stringer 已提交
984 985 986 987
	exp = ovs_ct_expect_find(net, &info->zone, info->family, skb);
	if (exp) {
		u8 state;

988 989 990
		/* NOTE: New connections are NATted and Helped only when
		 * committed, so we are not calling into NAT here.
		 */
J
Joe Stringer 已提交
991
		state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED;
992
		__ovs_ct_update_key(key, state, &info->zone, exp->master);
993 994 995 996 997 998 999 1000
	} else {
		struct nf_conn *ct;
		int err;

		err = __ovs_ct_lookup(net, key, info, skb);
		if (err)
			return err;

1001
		ct = (struct nf_conn *)skb_nfct(skb);
1002 1003 1004
		if (ct)
			nf_ct_deliver_cached_events(ct);
	}
J
Joe Stringer 已提交
1005 1006 1007 1008

	return 0;
}

J
Joe Stringer 已提交
1009
static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
1010 1011 1012
{
	size_t i;

1013 1014
	for (i = 0; i < OVS_CT_LABELS_LEN_32; i++)
		if (labels->ct_labels_32[i])
1015 1016 1017 1018 1019
			return true;

	return false;
}

1020 1021 1022 1023 1024
/* Lookup connection and confirm if unconfirmed. */
static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
			 const struct ovs_conntrack_info *info,
			 struct sk_buff *skb)
{
1025 1026
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;
1027 1028 1029 1030 1031 1032
	int err;

	err = __ovs_ct_lookup(net, key, info, skb);
	if (err)
		return err;

1033 1034 1035 1036 1037
	/* The connection could be invalid, in which case this is a no-op.*/
	ct = nf_ct_get(skb, &ctinfo);
	if (!ct)
		return 0;

1038 1039 1040 1041 1042
	/* Apply changes before confirming the connection so that the initial
	 * conntrack NEW netlink event carries the values given in the CT
	 * action.
	 */
	if (info->mark.mask) {
1043
		err = ovs_ct_set_mark(ct, key, info->mark.value,
1044 1045 1046 1047
				      info->mark.mask);
		if (err)
			return err;
	}
1048 1049 1050 1051 1052 1053 1054 1055
	if (!nf_ct_is_confirmed(ct)) {
		err = ovs_ct_init_labels(ct, key, &info->labels.value,
					 &info->labels.mask);
		if (err)
			return err;
	} else if (labels_nonzero(&info->labels.mask)) {
		err = ovs_ct_set_labels(ct, key, &info->labels.value,
					&info->labels.mask);
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067
		if (err)
			return err;
	}
	/* This will take care of sending queued events even if the connection
	 * is already confirmed.
	 */
	if (nf_conntrack_confirm(skb) != NF_ACCEPT)
		return -EINVAL;

	return 0;
}

1068 1069 1070
/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
 * value if 'skb' is freed.
 */
J
Joe Stringer 已提交
1071 1072 1073 1074 1075 1076 1077 1078 1079
int ovs_ct_execute(struct net *net, struct sk_buff *skb,
		   struct sw_flow_key *key,
		   const struct ovs_conntrack_info *info)
{
	int nh_ofs;
	int err;

	/* The conntrack module expects to be working at L3. */
	nh_ofs = skb_network_offset(skb);
1080
	skb_pull_rcsum(skb, nh_ofs);
J
Joe Stringer 已提交
1081 1082 1083 1084 1085 1086 1087

	if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
		err = handle_fragments(net, key, info->zone.id, skb);
		if (err)
			return err;
	}

1088
	if (info->commit)
1089
		err = ovs_ct_commit(net, key, info, skb);
J
Joe Stringer 已提交
1090 1091 1092 1093
	else
		err = ovs_ct_lookup(net, key, info, skb);

	skb_push(skb, nh_ofs);
1094
	skb_postpush_rcsum(skb, skb->data, nh_ofs);
1095 1096
	if (err)
		kfree_skb(skb);
J
Joe Stringer 已提交
1097 1098 1099
	return err;
}

1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
			     const struct sw_flow_key *key, bool log)
{
	struct nf_conntrack_helper *helper;
	struct nf_conn_help *help;

	helper = nf_conntrack_helper_try_module_get(name, info->family,
						    key->ip.proto);
	if (!helper) {
		OVS_NLERR(log, "Unknown helper \"%s\"", name);
		return -EINVAL;
	}

	help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL);
	if (!help) {
		module_put(helper->me);
		return -ENOMEM;
	}

	rcu_assign_pointer(help->helper, helper);
	info->helper = helper;
	return 0;
}

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
#ifdef CONFIG_NF_NAT_NEEDED
static int parse_nat(const struct nlattr *attr,
		     struct ovs_conntrack_info *info, bool log)
{
	struct nlattr *a;
	int rem;
	bool have_ip_max = false;
	bool have_proto_max = false;
	bool ip_vers = (info->family == NFPROTO_IPV6);

	nla_for_each_nested(a, attr, rem) {
		static const int ovs_nat_attr_lens[OVS_NAT_ATTR_MAX + 1][2] = {
			[OVS_NAT_ATTR_SRC] = {0, 0},
			[OVS_NAT_ATTR_DST] = {0, 0},
			[OVS_NAT_ATTR_IP_MIN] = {sizeof(struct in_addr),
						 sizeof(struct in6_addr)},
			[OVS_NAT_ATTR_IP_MAX] = {sizeof(struct in_addr),
						 sizeof(struct in6_addr)},
			[OVS_NAT_ATTR_PROTO_MIN] = {sizeof(u16), sizeof(u16)},
			[OVS_NAT_ATTR_PROTO_MAX] = {sizeof(u16), sizeof(u16)},
			[OVS_NAT_ATTR_PERSISTENT] = {0, 0},
			[OVS_NAT_ATTR_PROTO_HASH] = {0, 0},
			[OVS_NAT_ATTR_PROTO_RANDOM] = {0, 0},
		};
		int type = nla_type(a);

		if (type > OVS_NAT_ATTR_MAX) {
			OVS_NLERR(log,
				  "Unknown NAT attribute (type=%d, max=%d).\n",
				  type, OVS_NAT_ATTR_MAX);
			return -EINVAL;
		}

		if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) {
			OVS_NLERR(log,
				  "NAT attribute type %d has unexpected length (%d != %d).\n",
				  type, nla_len(a),
				  ovs_nat_attr_lens[type][ip_vers]);
			return -EINVAL;
		}

		switch (type) {
		case OVS_NAT_ATTR_SRC:
		case OVS_NAT_ATTR_DST:
			if (info->nat) {
				OVS_NLERR(log,
					  "Only one type of NAT may be specified.\n"
					  );
				return -ERANGE;
			}
			info->nat |= OVS_CT_NAT;
			info->nat |= ((type == OVS_NAT_ATTR_SRC)
					? OVS_CT_SRC_NAT : OVS_CT_DST_NAT);
			break;

		case OVS_NAT_ATTR_IP_MIN:
1180 1181
			nla_memcpy(&info->range.min_addr, a,
				   sizeof(info->range.min_addr));
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 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
			info->range.flags |= NF_NAT_RANGE_MAP_IPS;
			break;

		case OVS_NAT_ATTR_IP_MAX:
			have_ip_max = true;
			nla_memcpy(&info->range.max_addr, a,
				   sizeof(info->range.max_addr));
			info->range.flags |= NF_NAT_RANGE_MAP_IPS;
			break;

		case OVS_NAT_ATTR_PROTO_MIN:
			info->range.min_proto.all = htons(nla_get_u16(a));
			info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
			break;

		case OVS_NAT_ATTR_PROTO_MAX:
			have_proto_max = true;
			info->range.max_proto.all = htons(nla_get_u16(a));
			info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
			break;

		case OVS_NAT_ATTR_PERSISTENT:
			info->range.flags |= NF_NAT_RANGE_PERSISTENT;
			break;

		case OVS_NAT_ATTR_PROTO_HASH:
			info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM;
			break;

		case OVS_NAT_ATTR_PROTO_RANDOM:
			info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM_FULLY;
			break;

		default:
			OVS_NLERR(log, "Unknown nat attribute (%d).\n", type);
			return -EINVAL;
		}
	}

	if (rem > 0) {
		OVS_NLERR(log, "NAT attribute has %d unknown bytes.\n", rem);
		return -EINVAL;
	}
	if (!info->nat) {
		/* Do not allow flags if no type is given. */
		if (info->range.flags) {
			OVS_NLERR(log,
				  "NAT flags may be given only when NAT range (SRC or DST) is also specified.\n"
				  );
			return -EINVAL;
		}
		info->nat = OVS_CT_NAT;   /* NAT existing connections. */
	} else if (!info->commit) {
		OVS_NLERR(log,
			  "NAT attributes may be specified only when CT COMMIT flag is also specified.\n"
			  );
		return -EINVAL;
	}
	/* Allow missing IP_MAX. */
	if (info->range.flags & NF_NAT_RANGE_MAP_IPS && !have_ip_max) {
		memcpy(&info->range.max_addr, &info->range.min_addr,
		       sizeof(info->range.max_addr));
	}
	/* Allow missing PROTO_MAX. */
	if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED &&
	    !have_proto_max) {
		info->range.max_proto.all = info->range.min_proto.all;
	}
	return 0;
}
#endif

J
Joe Stringer 已提交
1254
static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
1255
	[OVS_CT_ATTR_COMMIT]	= { .minlen = 0, .maxlen = 0 },
J
Jarno Rajahalme 已提交
1256
	[OVS_CT_ATTR_FORCE_COMMIT]	= { .minlen = 0, .maxlen = 0 },
J
Joe Stringer 已提交
1257 1258
	[OVS_CT_ATTR_ZONE]	= { .minlen = sizeof(u16),
				    .maxlen = sizeof(u16) },
1259 1260
	[OVS_CT_ATTR_MARK]	= { .minlen = sizeof(struct md_mark),
				    .maxlen = sizeof(struct md_mark) },
J
Joe Stringer 已提交
1261 1262
	[OVS_CT_ATTR_LABELS]	= { .minlen = sizeof(struct md_labels),
				    .maxlen = sizeof(struct md_labels) },
1263
	[OVS_CT_ATTR_HELPER]	= { .minlen = 1,
1264 1265 1266 1267 1268
				    .maxlen = NF_CT_HELPER_NAME_LEN },
#ifdef CONFIG_NF_NAT_NEEDED
	/* NAT length is checked when parsing the nested attributes. */
	[OVS_CT_ATTR_NAT]	= { .minlen = 0, .maxlen = INT_MAX },
#endif
J
Joe Stringer 已提交
1269 1270 1271
};

static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
1272
		    const char **helper, bool log)
J
Joe Stringer 已提交
1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295
{
	struct nlattr *a;
	int rem;

	nla_for_each_nested(a, attr, rem) {
		int type = nla_type(a);
		int maxlen = ovs_ct_attr_lens[type].maxlen;
		int minlen = ovs_ct_attr_lens[type].minlen;

		if (type > OVS_CT_ATTR_MAX) {
			OVS_NLERR(log,
				  "Unknown conntrack attr (type=%d, max=%d)",
				  type, OVS_CT_ATTR_MAX);
			return -EINVAL;
		}
		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
			OVS_NLERR(log,
				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
				  type, nla_len(a), maxlen);
			return -EINVAL;
		}

		switch (type) {
J
Jarno Rajahalme 已提交
1296 1297 1298
		case OVS_CT_ATTR_FORCE_COMMIT:
			info->force = true;
			/* fall through. */
1299 1300
		case OVS_CT_ATTR_COMMIT:
			info->commit = true;
J
Joe Stringer 已提交
1301 1302 1303 1304 1305
			break;
#ifdef CONFIG_NF_CONNTRACK_ZONES
		case OVS_CT_ATTR_ZONE:
			info->zone.id = nla_get_u16(a);
			break;
1306 1307 1308 1309 1310
#endif
#ifdef CONFIG_NF_CONNTRACK_MARK
		case OVS_CT_ATTR_MARK: {
			struct md_mark *mark = nla_data(a);

1311 1312 1313 1314
			if (!mark->mask) {
				OVS_NLERR(log, "ct_mark mask cannot be 0");
				return -EINVAL;
			}
1315 1316 1317
			info->mark = *mark;
			break;
		}
1318 1319
#endif
#ifdef CONFIG_NF_CONNTRACK_LABELS
J
Joe Stringer 已提交
1320 1321
		case OVS_CT_ATTR_LABELS: {
			struct md_labels *labels = nla_data(a);
1322

1323 1324 1325 1326
			if (!labels_nonzero(&labels->mask)) {
				OVS_NLERR(log, "ct_labels mask cannot be 0");
				return -EINVAL;
			}
J
Joe Stringer 已提交
1327
			info->labels = *labels;
1328 1329
			break;
		}
J
Joe Stringer 已提交
1330
#endif
1331 1332 1333 1334 1335 1336 1337
		case OVS_CT_ATTR_HELPER:
			*helper = nla_data(a);
			if (!memchr(*helper, '\0', nla_len(a))) {
				OVS_NLERR(log, "Invalid conntrack helper");
				return -EINVAL;
			}
			break;
1338 1339 1340 1341 1342 1343 1344 1345 1346
#ifdef CONFIG_NF_NAT_NEEDED
		case OVS_CT_ATTR_NAT: {
			int err = parse_nat(a, info, log);

			if (err)
				return err;
			break;
		}
#endif
J
Joe Stringer 已提交
1347 1348 1349 1350 1351 1352 1353
		default:
			OVS_NLERR(log, "Unknown conntrack attr (%d)",
				  type);
			return -EINVAL;
		}
	}

1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
#ifdef CONFIG_NF_CONNTRACK_MARK
	if (!info->commit && info->mark.mask) {
		OVS_NLERR(log,
			  "Setting conntrack mark requires 'commit' flag.");
		return -EINVAL;
	}
#endif
#ifdef CONFIG_NF_CONNTRACK_LABELS
	if (!info->commit && labels_nonzero(&info->labels.mask)) {
		OVS_NLERR(log,
			  "Setting conntrack labels requires 'commit' flag.");
		return -EINVAL;
	}
#endif
J
Joe Stringer 已提交
1368 1369 1370 1371 1372 1373 1374 1375
	if (rem > 0) {
		OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem);
		return -EINVAL;
	}

	return 0;
}

1376
bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr)
J
Joe Stringer 已提交
1377 1378 1379 1380 1381 1382
{
	if (attr == OVS_KEY_ATTR_CT_STATE)
		return true;
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
	    attr == OVS_KEY_ATTR_CT_ZONE)
		return true;
1383 1384 1385
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
	    attr == OVS_KEY_ATTR_CT_MARK)
		return true;
1386
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
J
Joe Stringer 已提交
1387
	    attr == OVS_KEY_ATTR_CT_LABELS) {
1388 1389 1390 1391
		struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

		return ovs_net->xt_label;
	}
J
Joe Stringer 已提交
1392 1393 1394 1395 1396 1397 1398 1399 1400

	return false;
}

int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
		       const struct sw_flow_key *key,
		       struct sw_flow_actions **sfa,  bool log)
{
	struct ovs_conntrack_info ct_info;
1401
	const char *helper = NULL;
J
Joe Stringer 已提交
1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416
	u16 family;
	int err;

	family = key_to_nfproto(key);
	if (family == NFPROTO_UNSPEC) {
		OVS_NLERR(log, "ct family unspecified");
		return -EINVAL;
	}

	memset(&ct_info, 0, sizeof(ct_info));
	ct_info.family = family;

	nf_ct_zone_init(&ct_info.zone, NF_CT_DEFAULT_ZONE_ID,
			NF_CT_DEFAULT_ZONE_DIR, 0);

1417
	err = parse_ct(attr, &ct_info, &helper, log);
J
Joe Stringer 已提交
1418 1419 1420 1421 1422 1423 1424 1425 1426
	if (err)
		return err;

	/* Set up template for tracking connections in specific zones. */
	ct_info.ct = nf_ct_tmpl_alloc(net, &ct_info.zone, GFP_KERNEL);
	if (!ct_info.ct) {
		OVS_NLERR(log, "Failed to allocate conntrack template");
		return -ENOMEM;
	}
1427 1428 1429 1430

	__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
	nf_conntrack_get(&ct_info.ct->ct_general);

1431 1432 1433 1434 1435
	if (helper) {
		err = ovs_ct_add_helper(&ct_info, helper, key, log);
		if (err)
			goto err_free_ct;
	}
J
Joe Stringer 已提交
1436 1437 1438 1439 1440 1441 1442 1443

	err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info,
				 sizeof(ct_info), log);
	if (err)
		goto err_free_ct;

	return 0;
err_free_ct:
1444
	__ovs_ct_free_action(&ct_info);
J
Joe Stringer 已提交
1445 1446 1447
	return err;
}

1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
#ifdef CONFIG_NF_NAT_NEEDED
static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
			       struct sk_buff *skb)
{
	struct nlattr *start;

	start = nla_nest_start(skb, OVS_CT_ATTR_NAT);
	if (!start)
		return false;

	if (info->nat & OVS_CT_SRC_NAT) {
		if (nla_put_flag(skb, OVS_NAT_ATTR_SRC))
			return false;
	} else if (info->nat & OVS_CT_DST_NAT) {
		if (nla_put_flag(skb, OVS_NAT_ATTR_DST))
			return false;
	} else {
		goto out;
	}

	if (info->range.flags & NF_NAT_RANGE_MAP_IPS) {
1469 1470
		if (IS_ENABLED(CONFIG_NF_NAT_IPV4) &&
		    info->family == NFPROTO_IPV4) {
1471 1472 1473 1474 1475 1476 1477
			if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN,
					    info->range.min_addr.ip) ||
			    (info->range.max_addr.ip
			     != info->range.min_addr.ip &&
			     (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX,
					      info->range.max_addr.ip))))
				return false;
1478 1479
		} else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) &&
			   info->family == NFPROTO_IPV6) {
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
			if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN,
					     &info->range.min_addr.in6) ||
			    (memcmp(&info->range.max_addr.in6,
				    &info->range.min_addr.in6,
				    sizeof(info->range.max_addr.in6)) &&
			     (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX,
					       &info->range.max_addr.in6))))
				return false;
		} else {
			return false;
		}
	}
	if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED &&
	    (nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MIN,
			 ntohs(info->range.min_proto.all)) ||
	     (info->range.max_proto.all != info->range.min_proto.all &&
	      nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MAX,
			  ntohs(info->range.max_proto.all)))))
		return false;

	if (info->range.flags & NF_NAT_RANGE_PERSISTENT &&
	    nla_put_flag(skb, OVS_NAT_ATTR_PERSISTENT))
		return false;
	if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM &&
	    nla_put_flag(skb, OVS_NAT_ATTR_PROTO_HASH))
		return false;
	if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY &&
	    nla_put_flag(skb, OVS_NAT_ATTR_PROTO_RANDOM))
		return false;
out:
	nla_nest_end(skb, start);

	return true;
}
#endif

J
Joe Stringer 已提交
1516 1517 1518 1519 1520 1521 1522 1523 1524
int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
			  struct sk_buff *skb)
{
	struct nlattr *start;

	start = nla_nest_start(skb, OVS_ACTION_ATTR_CT);
	if (!start)
		return -EMSGSIZE;

J
Jarno Rajahalme 已提交
1525 1526 1527
	if (ct_info->commit && nla_put_flag(skb, ct_info->force
					    ? OVS_CT_ATTR_FORCE_COMMIT
					    : OVS_CT_ATTR_COMMIT))
J
Joe Stringer 已提交
1528 1529 1530 1531
		return -EMSGSIZE;
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
	    nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id))
		return -EMSGSIZE;
1532
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask &&
1533 1534 1535
	    nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark),
		    &ct_info->mark))
		return -EMSGSIZE;
1536
	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
1537
	    labels_nonzero(&ct_info->labels.mask) &&
J
Joe Stringer 已提交
1538 1539
	    nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels),
		    &ct_info->labels))
1540
		return -EMSGSIZE;
1541 1542 1543 1544 1545
	if (ct_info->helper) {
		if (nla_put_string(skb, OVS_CT_ATTR_HELPER,
				   ct_info->helper->name))
			return -EMSGSIZE;
	}
1546 1547 1548 1549
#ifdef CONFIG_NF_NAT_NEEDED
	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
		return -EMSGSIZE;
#endif
J
Joe Stringer 已提交
1550 1551 1552 1553 1554 1555 1556 1557 1558
	nla_nest_end(skb, start);

	return 0;
}

void ovs_ct_free_action(const struct nlattr *a)
{
	struct ovs_conntrack_info *ct_info = nla_data(a);

1559 1560 1561 1562 1563
	__ovs_ct_free_action(ct_info);
}

static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
{
1564 1565
	if (ct_info->helper)
		module_put(ct_info->helper->me);
J
Joe Stringer 已提交
1566
	if (ct_info->ct)
1567
		nf_ct_tmpl_free(ct_info->ct);
J
Joe Stringer 已提交
1568
}
1569 1570 1571

void ovs_ct_init(struct net *net)
{
J
Joe Stringer 已提交
1572
	unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
1573 1574
	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

1575
	if (nf_connlabels_get(net, n_bits - 1)) {
1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589
		ovs_net->xt_label = false;
		OVS_NLERR(true, "Failed to set connlabel length");
	} else {
		ovs_net->xt_label = true;
	}
}

void ovs_ct_exit(struct net *net)
{
	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

	if (ovs_net->xt_label)
		nf_connlabels_put(net);
}