aboutsummaryrefslogtreecommitdiffstats
path: root/net/openvswitch/flow.c
blob: d07ab538fc9d37b78082e88906fe41c433467166 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
/*
 * Copyright (c) 2007-2013 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.
 *
 * 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/sctp.h>
#include <linux/smp.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/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ndisc.h>

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 TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))

void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
			   struct sk_buff *skb)
{
	struct flow_stats *stats;
	int node = numa_node_id();

	stats = rcu_dereference(flow->stats[node]);

	/* Check if already have node-specific stats. */
	if (likely(stats)) {
		spin_lock(&stats->lock);
		/* Mark if we write on the pre-allocated stats. */
		if (node == 0 && unlikely(flow->stats_last_writer != node))
			flow->stats_last_writer = node;
	} else {
		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
		spin_lock(&stats->lock);

		/* If the current NUMA-node is the only writer on the
		 * pre-allocated stats keep using them.
		 */
		if (unlikely(flow->stats_last_writer != node)) {
			/* A previous locker may have already allocated the
			 * stats, so we need to check again.  If node-specific
			 * stats were already allocated, we update the pre-
			 * allocated stats as we have already locked them.
			 */
			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
			    && likely(!rcu_dereference(flow->stats[node]))) {
				/* Try to allocate node-specific stats. */
				struct flow_stats *new_stats;

				new_stats =
					kmem_cache_alloc_node(flow_stats_cache,
							      GFP_THISNODE |
							      __GFP_NOMEMALLOC,
							      node);
				if (likely(new_stats)) {
					new_stats->used = jiffies;
					new_stats->packet_count = 1;
					new_stats->byte_count = skb->len;
					new_stats->tcp_flags = tcp_flags;
					spin_lock_init(&new_stats->lock);

					rcu_assign_pointer(flow->stats[node],
							   new_stats);
					goto unlock;
				}
			}
			flow->stats_last_writer = node;
		}
	}

	stats->used = jiffies;
	stats->packet_count++;
	stats->byte_count += skb->len;
	stats->tcp_flags |= tcp_flags;
unlock:
	spin_unlock(&stats->lock);
}

/* Must be called with rcu_read_lock or ovs_mutex. */
void ovs_flow_stats_get(const struct sw_flow *flow,
			struct ovs_flow_stats *ovs_stats,
			unsigned long *used, __be16 *tcp_flags)
{
	int node;

	*used = 0;
	*tcp_flags = 0;
	memset(ovs_stats, 0, sizeof(*ovs_stats));

	for_each_node(node) {
		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);

		if (stats) {
			/* Local CPU may write on non-local stats, so we must
			 * block bottom-halves here.
			 */
			spin_lock_bh(&stats->lock);
			if (!*used || time_after(stats->used, *used))
				*used = stats->used;
			*tcp_flags |= stats->tcp_flags;
			ovs_stats->n_packets += stats->packet_count;
			ovs_stats->n_bytes += stats->byte_count;
			spin_unlock_bh(&stats->lock);
		}
	}
}

/* Called with ovs_mutex. */
void ovs_flow_stats_clear(struct sw_flow *flow)
{
	int node;

	for_each_node(node) {
		struct flow_stats *stats = ovsl_dereference(flow->stats[node]);

		if (stats) {
			spin_lock_bh(&stats->lock);
			stats->used = 0;
			stats->packet_count = 0;
			stats->byte_count = 0;
			stats->tcp_flags = 0;
			spin_unlock_bh(&stats->lock);
		}
	}
}

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 sctphdr_ok(struct sk_buff *skb)
{
	return pskb_may_pull(skb, skb_transport_offset(skb) +
				  sizeof(struct sctphdr));
}

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

static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
{
	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;

	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));
}

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) >= ETH_P_802_3_MIN)
		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));

	if (ntohs(llc->ethertype) >= ETH_P_802_3_MIN)
		return llc->ethertype;

	return htons(ETH_P_802_2);
}

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

	/* 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->tp.src = htons(icmp->icmp6_type);
	key->tp.dst = htons(icmp->icmp6_code);

	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;

		/* In order to process neighbor discovery options, we need the
		 * entire packet.
		 */
		if (unlikely(icmp_len < sizeof(*nd)))
			return 0;

		if (unlikely(skb_linearize(skb)))
			return -ENOMEM;

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

		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))
				return 0;

			/* 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;
				ether_addr_copy(key->ipv6.nd.sll,
						&nd->opt[offset+sizeof(*nd_opt)]);
			} 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;
				ether_addr_copy(key->ipv6.nd.tll,
						&nd->opt[offset+sizeof(*nd_opt)]);
			}

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

	return 0;

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));

	return 0;
}

/**
 * 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
 *
 * 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->eth.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->eth.type values it is left untouched.
 */
int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
{
	int error;
	struct ethhdr *eth;

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

	key->phy.priority = skb->priority;
	if (OVS_CB(skb)->tun_key)
		memcpy(&key->tun_key, OVS_CB(skb)->tun_key, sizeof(key->tun_key));
	key->phy.in_port = in_port;
	key->phy.skb_mark = skb->mark;

	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);
	ether_addr_copy(key->eth.src, eth->h_source);
	ether_addr_copy(key->eth.dst, eth->h_dest);

	__skb_pull(skb, 2 * ETH_ALEN);
	/* We are going to push all headers that we pull, so no need to
	 * update skb->csum here.
	 */

	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;

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

		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;
			return 0;
		}
		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) {
			if (tcphdr_ok(skb)) {
				struct tcphdr *tcp = tcp_hdr(skb);
				key->tp.src = tcp->source;
				key->tp.dst = tcp->dest;
				key->tp.flags = TCP_FLAGS_BE16(tcp);
			}
		} else if (key->ip.proto == IPPROTO_UDP) {
			if (udphdr_ok(skb)) {
				struct udphdr *udp = udp_hdr(skb);
				key->tp.src = udp->source;
				key->tp.dst = udp->dest;
			}
		} else if (key->ip.proto == IPPROTO_SCTP) {
			if (sctphdr_ok(skb)) {
				struct sctphdr *sctp = sctp_hdr(skb);
				key->tp.src = sctp->source;
				key->tp.dst = sctp->dest;
			}
		} else if (key->ip.proto == IPPROTO_ICMP) {
			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->tp.src = htons(icmp->type);
				key->tp.dst = htons(icmp->code);
			}
		}

	} else if ((key->eth.type == htons(ETH_P_ARP) ||
		   key->eth.type == htons(ETH_P_RARP)) && 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);
			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));
			ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
			ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
		}
	} else if (key->eth.type == htons(ETH_P_IPV6)) {
		int nh_len;             /* IPv6 Header + Extensions */

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

		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
			return 0;
		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
			key->ip.frag = OVS_FRAG_TYPE_FIRST;

		/* Transport layer. */
		if (key->ip.proto == NEXTHDR_TCP) {
			if (tcphdr_ok(skb)) {
				struct tcphdr *tcp = tcp_hdr(skb);
				key->tp.src = tcp->source;
				key->tp.dst = tcp->dest;
				key->tp.flags = TCP_FLAGS_BE16(tcp);
			}
		} else if (key->ip.proto == NEXTHDR_UDP) {
			if (udphdr_ok(skb)) {
				struct udphdr *udp = udp_hdr(skb);
				key->tp.src = udp->source;
				key->tp.dst = udp->dest;
			}
		} else if (key->ip.proto == NEXTHDR_SCTP) {
			if (sctphdr_ok(skb)) {
				struct sctphdr *sctp = sctp_hdr(skb);
				key->tp.src = sctp->source;
				key->tp.dst = sctp->dest;
			}
		} else if (key->ip.proto == NEXTHDR_ICMP) {
			if (icmp6hdr_ok(skb)) {
				error = parse_icmpv6(skb, key, nh_len);
				if (error)
					return error;
			}
		}
	}

	return 0;
}