summaryrefslogtreecommitdiffstats
path: root/net/openvswitch/vport.c
blob: dc81dc619aa2344a5c7912def9d6852fcd37ebda (plain)
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
/*
 * Copyright (c) 2007-2014 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 <linux/etherdevice.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
#include <net/net_namespace.h>
#include <linux/module.h>

#include "datapath.h"
#include "vport.h"
#include "vport-internal_dev.h"

static LIST_HEAD(vport_ops_list);

/* Protected by RCU read lock for reading, ovs_mutex for writing. */
static struct hlist_head *dev_table;
#define VPORT_HASH_BUCKETS 1024

/**
 *	ovs_vport_init - initialize vport subsystem
 *
 * Called at module load time to initialize the vport subsystem.
 */
int ovs_vport_init(void)
{
	dev_table = kzalloc(VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
			    GFP_KERNEL);
	if (!dev_table)
		return -ENOMEM;

	return 0;
}

/**
 *	ovs_vport_exit - shutdown vport subsystem
 *
 * Called at module exit time to shutdown the vport subsystem.
 */
void ovs_vport_exit(void)
{
	kfree(dev_table);
}

static struct hlist_head *hash_bucket(const struct net *net, const char *name)
{
	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
}

int ovs_vport_ops_register(struct vport_ops *ops)
{
	int err = -EEXIST;
	struct vport_ops *o;

	ovs_lock();
	list_for_each_entry(o, &vport_ops_list, list)
		if (ops->type == o->type)
			goto errout;

	list_add_tail(&ops->list, &vport_ops_list);
	err = 0;
errout:
	ovs_unlock();
	return err;
}
EXPORT_SYMBOL_GPL(ovs_vport_ops_register);

void ovs_vport_ops_unregister(struct vport_ops *ops)
{
	ovs_lock();
	list_del(&ops->list);
	ovs_unlock();
}
EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);

/**
 *	ovs_vport_locate - find a port that has already been created
 *
 * @name: name of port to find
 *
 * Must be called with ovs or RCU read lock.
 */
struct vport *ovs_vport_locate(const struct net *net, const char *name)
{
	struct hlist_head *bucket = hash_bucket(net, name);
	struct vport *vport;

	hlist_for_each_entry_rcu(vport, bucket, hash_node)
		if (!strcmp(name, ovs_vport_name(vport)) &&
		    net_eq(ovs_dp_get_net(vport->dp), net))
			return vport;

	return NULL;
}

/**
 *	ovs_vport_alloc - allocate and initialize new vport
 *
 * @priv_size: Size of private data area to allocate.
 * @ops: vport device ops
 *
 * Allocate and initialize a new vport defined by @ops.  The vport will contain
 * a private data area of size @priv_size that can be accessed using
 * vport_priv().  vports that are no longer needed should be released with
 * vport_free().
 */
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
			  const struct vport_parms *parms)
{
	struct vport *vport;
	size_t alloc_size;

	alloc_size = sizeof(struct vport);
	if (priv_size) {
		alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
		alloc_size += priv_size;
	}

	vport = kzalloc(alloc_size, GFP_KERNEL);
	if (!vport)
		return ERR_PTR(-ENOMEM);

	vport->dp = parms->dp;
	vport->port_no = parms->port_no;
	vport->ops = ops;
	INIT_HLIST_NODE(&vport->dp_hash_node);

	if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
		kfree(vport);
		return ERR_PTR(-EINVAL);
	}

	return vport;
}
EXPORT_SYMBOL_GPL(ovs_vport_alloc);

/**
 *	ovs_vport_free - uninitialize and free vport
 *
 * @vport: vport to free
 *
 * Frees a vport allocated with vport_alloc() when it is no longer needed.
 *
 * The caller must ensure that an RCU grace period has passed since the last
 * time @vport was in a datapath.
 */
void ovs_vport_free(struct vport *vport)
{
	/* vport is freed from RCU callback or error path, Therefore
	 * it is safe to use raw dereference.
	 */
	kfree(rcu_dereference_raw(vport->upcall_portids));
	kfree(vport);
}
EXPORT_SYMBOL_GPL(ovs_vport_free);

static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
{
	struct vport_ops *ops;

	list_for_each_entry(ops, &vport_ops_list, list)
		if (ops->type == parms->type)
			return ops;

	return NULL;
}

/**
 *	ovs_vport_add - add vport device (for kernel callers)
 *
 * @parms: Information about new vport.
 *
 * Creates a new vport with the specified configuration (which is dependent on
 * device type).  ovs_mutex must be held.
 */
struct vport *ovs_vport_add(const struct vport_parms *parms)
{
	struct vport_ops *ops;
	struct vport *vport;

	ops = ovs_vport_lookup(parms);
	if (ops) {
		struct hlist_head *bucket;

		if (!try_module_get(ops->owner))
			return ERR_PTR(-EAFNOSUPPORT);

		vport = ops->create(parms);
		if (IS_ERR(vport)) {
			module_put(ops->owner);
			return vport;
		}

		bucket = hash_bucket(ovs_dp_get_net(vport->dp),
				     ovs_vport_name(vport));
		hlist_add_head_rcu(&vport->hash_node, bucket);
		return vport;
	}

	/* Unlock to attempt module load and return -EAGAIN if load
	 * was successful as we need to restart the port addition
	 * workflow.
	 */
	ovs_unlock();
	request_module("vport-type-%d", parms->type);
	ovs_lock();

	if (!ovs_vport_lookup(parms))
		return ERR_PTR(-EAFNOSUPPORT);
	else
		return ERR_PTR(-EAGAIN);
}

/**
 *	ovs_vport_set_options - modify existing vport device (for kernel callers)
 *
 * @vport: vport to modify.
 * @options: New configuration.
 *
 * Modifies an existing device with the specified configuration (which is
 * dependent on device type).  ovs_mutex must be held.
 */
int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
{
	if (!vport->ops->set_options)
		return -EOPNOTSUPP;
	return vport->ops->set_options(vport, options);
}

/**
 *	ovs_vport_del - delete existing vport device
 *
 * @vport: vport to delete.
 *
 * Detaches @vport from its datapath and destroys it.  It is possible to fail
 * for reasons such as lack of memory.  ovs_mutex must be held.
 */
void ovs_vport_del(struct vport *vport)
{
	ASSERT_OVSL();

	hlist_del_rcu(&vport->hash_node);
	module_put(vport->ops->owner);
	vport->ops->destroy(vport);
}

/**
 *	ovs_vport_get_stats - retrieve device stats
 *
 * @vport: vport from which to retrieve the stats
 * @stats: location to store stats
 *
 * Retrieves transmit, receive, and error stats for the given device.
 *
 * Must be called with ovs_mutex or rcu_read_lock.
 */
void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
{
	struct net_device *dev = vport->dev;
	int i;

	memset(stats, 0, sizeof(*stats));
	stats->rx_errors  = dev->stats.rx_errors;
	stats->tx_errors  = dev->stats.tx_errors;
	stats->tx_dropped = dev->stats.tx_dropped;
	stats->rx_dropped = dev->stats.rx_dropped;

	stats->rx_dropped += atomic_long_read(&dev->rx_dropped);
	stats->tx_dropped += atomic_long_read(&dev->tx_dropped);

	for_each_possible_cpu(i) {
		const struct pcpu_sw_netstats *percpu_stats;
		struct pcpu_sw_netstats local_stats;
		unsigned int start;

		percpu_stats = per_cpu_ptr(dev->tstats, i);

		do {
			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
			local_stats = *percpu_stats;
		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));

		stats->rx_bytes		+= local_stats.rx_bytes;
		stats->rx_packets	+= local_stats.rx_packets;
		stats->tx_bytes		+= local_stats.tx_bytes;
		stats->tx_packets	+= local_stats.tx_packets;
	}
}

/**
 *	ovs_vport_get_options - retrieve device options
 *
 * @vport: vport from which to retrieve the options.
 * @skb: sk_buff where options should be appended.
 *
 * Retrieves the configuration of the given device, appending an
 * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
 * vport-specific attributes to @skb.
 *
 * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
 * negative error code if a real error occurred.  If an error occurs, @skb is
 * left unmodified.
 *
 * Must be called with ovs_mutex or rcu_read_lock.
 */
int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
{
	struct nlattr *nla;
	int err;

	if (!vport->ops->get_options)
		return 0;

	nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
	if (!nla)
		return -EMSGSIZE;

	err = vport->ops->get_options(vport, skb);
	if (err) {
		nla_nest_cancel(skb, nla);
		return err;
	}

	nla_nest_end(skb, nla);
	return 0;
}

/**
 *	ovs_vport_set_upcall_portids - set upcall portids of @vport.
 *
 * @vport: vport to modify.
 * @ids: new configuration, an array of port ids.
 *
 * Sets the vport's upcall_portids to @ids.
 *
 * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
 * as an array of U32.
 *
 * Must be called with ovs_mutex.
 */
int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
{
	struct vport_portids *old, *vport_portids;

	if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
		return -EINVAL;

	old = ovsl_dereference(vport->upcall_portids);

	vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
				GFP_KERNEL);
	if (!vport_portids)
		return -ENOMEM;

	vport_portids->n_ids = nla_len(ids) / sizeof(u32);
	vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids);
	nla_memcpy(vport_portids->ids, ids, nla_len(ids));

	rcu_assign_pointer(vport->upcall_portids, vport_portids);

	if (old)
		kfree_rcu(old, rcu);
	return 0;
}

/**
 *	ovs_vport_get_upcall_portids - get the upcall_portids of @vport.
 *
 * @vport: vport from which to retrieve the portids.
 * @skb: sk_buff where portids should be appended.
 *
 * Retrieves the configuration of the given vport, appending the
 * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall
 * portids to @skb.
 *
 * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room.
 * If an error occurs, @skb is left unmodified.  Must be called with
 * ovs_mutex or rcu_read_lock.
 */
int ovs_vport_get_upcall_portids(const struct vport *vport,
				 struct sk_buff *skb)
{
	struct vport_portids *ids;

	ids = rcu_dereference_ovsl(vport->upcall_portids);

	if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS)
		return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID,
			       ids->n_ids * sizeof(u32), (void *)ids->ids);
	else
		return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]);
}

/**
 *	ovs_vport_find_upcall_portid - find the upcall portid to send upcall.
 *
 * @vport: vport from which the missed packet is received.
 * @skb: skb that the missed packet was received.
 *
 * Uses the skb_get_hash() to select the upcall portid to send the
 * upcall.
 *
 * Returns the portid of the target socket.  Must be called with rcu_read_lock.
 */
u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
{
	struct vport_portids *ids;
	u32 ids_index;
	u32 hash;

	ids = rcu_dereference(vport->upcall_portids);

	if (ids->n_ids == 1 && ids->ids[0] == 0)
		return 0;

	hash = skb_get_hash(skb);
	ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids);
	return ids->ids[ids_index];
}

/**
 *	ovs_vport_receive - pass up received packet to the datapath for processing
 *
 * @vport: vport that received the packet
 * @skb: skb that was received
 * @tun_key: tunnel (if any) that carried packet
 *
 * Must be called with rcu_read_lock.  The packet cannot be shared and
 * skb->data should point to the Ethernet header.
 */
int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
		      const struct ip_tunnel_info *tun_info)
{
	struct sw_flow_key key;
	int error;

	OVS_CB(skb)->input_vport = vport;
	OVS_CB(skb)->mru = 0;
	/* Extract flow from 'skb' into 'key'. */
	error = ovs_flow_key_extract(tun_info, skb, &key);
	if (unlikely(error)) {
		kfree_skb(skb);
		return error;
	}
	ovs_dp_process_packet(skb, &key);
	return 0;
}
EXPORT_SYMBOL_GPL(ovs_vport_receive);

static void free_vport_rcu(struct rcu_head *rcu)
{
	struct vport *vport = container_of(rcu, struct vport, rcu);

	ovs_vport_free(vport);
}

void ovs_vport_deferred_free(struct vport *vport)
{
	if (!vport)
		return;

	call_rcu(&vport->rcu, free_vport_rcu);
}
EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);

int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
			       struct net *net,
			       struct sk_buff *skb,
			       u8 ipproto,
			       __be16 tp_src,
			       __be16 tp_dst)
{
	struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info;
	const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb);
	const struct ip_tunnel_key *tun_key;
	u32 skb_mark = skb->mark;
	struct rtable *rt;
	struct flowi4 fl;

	if (unlikely(!tun_info))
		return -EINVAL;
	if (ip_tunnel_info_af(tun_info) != AF_INET)
		return -EINVAL;

	tun_key = &tun_info->key;

	/* Route lookup to get srouce IP address.
	 * The process may need to be changed if the corresponding process
	 * in vports ops changed.
	 */
	rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
	if (IS_ERR(rt))
		return PTR_ERR(rt);

	ip_rt_put(rt);

	/* Generate egress_tun_info based on tun_info,
	 * saddr, tp_src and tp_dst
	 */
	ip_tunnel_key_init(&egress_tun_info->key,
			   fl.saddr, tun_key->u.ipv4.dst,
			   tun_key->tos,
			   tun_key->ttl,
			   tp_src, tp_dst,
			   tun_key->tun_id,
			   tun_key->tun_flags);
	egress_tun_info->options_len = tun_info->options_len;
	egress_tun_info->mode = tun_info->mode;
	upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info);
	return 0;
}
EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);

int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
				  struct dp_upcall_info *upcall)
{
	/* get_egress_tun_info() is only implemented on tunnel ports. */
	if (unlikely(!vport->ops->get_egress_tun_info))
		return -EINVAL;

	return vport->ops->get_egress_tun_info(vport, skb, upcall);
}