summaryrefslogtreecommitdiff
path: root/net/openvswitch/meter.c
blob: bb67238f0340fdcc8cb80be190ab81913e28c6c5 (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
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
/*
 * Copyright (c) 2017 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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/if.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/kernel.h>
#include <linux/openvswitch.h>
#include <linux/netlink.h>
#include <linux/rculist.h>

#include <net/netlink.h>
#include <net/genetlink.h>

#include "datapath.h"
#include "meter.h"

#define METER_HASH_BUCKETS 1024

static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = {
	[OVS_METER_ATTR_ID] = { .type = NLA_U32, },
	[OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG },
	[OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
	[OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED },
	[OVS_METER_ATTR_USED] = { .type = NLA_U64 },
	[OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG },
	[OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 },
	[OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 },
};

static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = {
	[OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, },
	[OVS_BAND_ATTR_RATE] = { .type = NLA_U32, },
	[OVS_BAND_ATTR_BURST] = { .type = NLA_U32, },
	[OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) },
};

static void ovs_meter_free(struct dp_meter *meter)
{
	if (!meter)
		return;

	kfree_rcu(meter, rcu);
}

static struct hlist_head *meter_hash_bucket(const struct datapath *dp,
					    u32 meter_id)
{
	return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)];
}

/* Call with ovs_mutex or RCU read lock. */
static struct dp_meter *lookup_meter(const struct datapath *dp,
				     u32 meter_id)
{
	struct dp_meter *meter;
	struct hlist_head *head;

	head = meter_hash_bucket(dp, meter_id);
	hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
		if (meter->id == meter_id)
			return meter;
	}
	return NULL;
}

static void attach_meter(struct datapath *dp, struct dp_meter *meter)
{
	struct hlist_head *head = meter_hash_bucket(dp, meter->id);

	hlist_add_head_rcu(&meter->dp_hash_node, head);
}

static void detach_meter(struct dp_meter *meter)
{
	ASSERT_OVSL();
	if (meter)
		hlist_del_rcu(&meter->dp_hash_node);
}

static struct sk_buff *
ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd,
			  struct ovs_header **ovs_reply_header)
{
	struct sk_buff *skb;
	struct ovs_header *ovs_header = info->userhdr;

	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
	if (!skb)
		return ERR_PTR(-ENOMEM);

	*ovs_reply_header = genlmsg_put(skb, info->snd_portid,
					info->snd_seq,
					&dp_meter_genl_family, 0, cmd);
	if (!*ovs_reply_header) {
		nlmsg_free(skb);
		return ERR_PTR(-EMSGSIZE);
	}
	(*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex;

	return skb;
}

static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
				     struct dp_meter *meter)
{
	struct nlattr *nla;
	struct dp_meter_band *band;
	u16 i;

	if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id))
		goto error;

	if (!meter)
		return 0;

	if (nla_put(reply, OVS_METER_ATTR_STATS,
		    sizeof(struct ovs_flow_stats), &meter->stats) ||
	    nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used,
			      OVS_METER_ATTR_PAD))
		goto error;

	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
	if (!nla)
		goto error;

	band = meter->bands;

	for (i = 0; i < meter->n_bands; ++i, ++band) {
		struct nlattr *band_nla;

		band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
		if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS,
					 sizeof(struct ovs_flow_stats),
					 &band->stats))
			goto error;
		nla_nest_end(reply, band_nla);
	}
	nla_nest_end(reply, nla);

	return 0;
error:
	return -EMSGSIZE;
}

static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
{
	struct sk_buff *reply;
	struct ovs_header *ovs_reply_header;
	struct nlattr *nla, *band_nla;
	int err;

	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES,
					  &ovs_reply_header);
	if (IS_ERR(reply))
		return PTR_ERR(reply);

	if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) ||
	    nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
		goto nla_put_failure;

	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
	if (!nla)
		goto nla_put_failure;

	band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
	if (!band_nla)
		goto nla_put_failure;
	/* Currently only DROP band type is supported. */
	if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP))
		goto nla_put_failure;
	nla_nest_end(reply, band_nla);
	nla_nest_end(reply, nla);

	genlmsg_end(reply, ovs_reply_header);
	return genlmsg_reply(reply, info);

nla_put_failure:
	nlmsg_free(reply);
	err = -EMSGSIZE;
	return err;
}

static struct dp_meter *dp_meter_create(struct nlattr **a)
{
	struct nlattr *nla;
	int rem;
	u16 n_bands = 0;
	struct dp_meter *meter;
	struct dp_meter_band *band;
	int err;

	/* Validate attributes, count the bands. */
	if (!a[OVS_METER_ATTR_BANDS])
		return ERR_PTR(-EINVAL);

	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem)
		if (++n_bands > DP_MAX_BANDS)
			return ERR_PTR(-EINVAL);

	/* Allocate and set up the meter before locking anything. */
	meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL);
	if (!meter)
		return ERR_PTR(-ENOMEM);

	meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]);
	meter->used = div_u64(ktime_get_ns(), 1000 * 1000);
	meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0;
	meter->keep_stats = !a[OVS_METER_ATTR_CLEAR];
	spin_lock_init(&meter->lock);
	if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) {
		meter->stats = *(struct ovs_flow_stats *)
			nla_data(a[OVS_METER_ATTR_STATS]);
	}
	meter->n_bands = n_bands;

	/* Set up meter bands. */
	band = meter->bands;
	nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) {
		struct nlattr *attr[OVS_BAND_ATTR_MAX + 1];
		u32 band_max_delta_t;

		err = nla_parse_deprecated((struct nlattr **)&attr,
					   OVS_BAND_ATTR_MAX, nla_data(nla),
					   nla_len(nla), band_policy, NULL);
		if (err)
			goto exit_free_meter;

		if (!attr[OVS_BAND_ATTR_TYPE] ||
		    !attr[OVS_BAND_ATTR_RATE] ||
		    !attr[OVS_BAND_ATTR_BURST]) {
			err = -EINVAL;
			goto exit_free_meter;
		}

		band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]);
		band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]);
		if (band->rate == 0) {
			err = -EINVAL;
			goto exit_free_meter;
		}

		band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]);
		/* Figure out max delta_t that is enough to fill any bucket.
		 * Keep max_delta_t size to the bucket units:
		 * pkts => 1/1000 packets, kilobits => bits.
		 *
		 * Start with a full bucket.
		 */
		band->bucket = (band->burst_size + band->rate) * 1000;
		band_max_delta_t = band->bucket / band->rate;
		if (band_max_delta_t > meter->max_delta_t)
			meter->max_delta_t = band_max_delta_t;
		band++;
	}

	return meter;

exit_free_meter:
	kfree(meter);
	return ERR_PTR(err);
}

static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr **a = info->attrs;
	struct dp_meter *meter, *old_meter;
	struct sk_buff *reply;
	struct ovs_header *ovs_reply_header;
	struct ovs_header *ovs_header = info->userhdr;
	struct datapath *dp;
	int err;
	u32 meter_id;
	bool failed;

	if (!a[OVS_METER_ATTR_ID]) {
		return -ENODEV;
	}

	meter = dp_meter_create(a);
	if (IS_ERR_OR_NULL(meter))
		return PTR_ERR(meter);

	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
					  &ovs_reply_header);
	if (IS_ERR(reply)) {
		err = PTR_ERR(reply);
		goto exit_free_meter;
	}

	ovs_lock();
	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
	if (!dp) {
		err = -ENODEV;
		goto exit_unlock;
	}

	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);

	/* Cannot fail after this. */
	old_meter = lookup_meter(dp, meter_id);
	detach_meter(old_meter);
	attach_meter(dp, meter);
	ovs_unlock();

	/* Build response with the meter_id and stats from
	 * the old meter, if any.
	 */
	failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id);
	WARN_ON(failed);
	if (old_meter) {
		spin_lock_bh(&old_meter->lock);
		if (old_meter->keep_stats) {
			err = ovs_meter_cmd_reply_stats(reply, meter_id,
							old_meter);
			WARN_ON(err);
		}
		spin_unlock_bh(&old_meter->lock);
		ovs_meter_free(old_meter);
	}

	genlmsg_end(reply, ovs_reply_header);
	return genlmsg_reply(reply, info);

exit_unlock:
	ovs_unlock();
	nlmsg_free(reply);
exit_free_meter:
	kfree(meter);
	return err;
}

static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr **a = info->attrs;
	u32 meter_id;
	struct ovs_header *ovs_header = info->userhdr;
	struct ovs_header *ovs_reply_header;
	struct datapath *dp;
	int err;
	struct sk_buff *reply;
	struct dp_meter *meter;

	if (!a[OVS_METER_ATTR_ID])
		return -EINVAL;

	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);

	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET,
					  &ovs_reply_header);
	if (IS_ERR(reply))
		return PTR_ERR(reply);

	ovs_lock();

	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
	if (!dp) {
		err = -ENODEV;
		goto exit_unlock;
	}

	/* Locate meter, copy stats. */
	meter = lookup_meter(dp, meter_id);
	if (!meter) {
		err = -ENOENT;
		goto exit_unlock;
	}

	spin_lock_bh(&meter->lock);
	err = ovs_meter_cmd_reply_stats(reply, meter_id, meter);
	spin_unlock_bh(&meter->lock);
	if (err)
		goto exit_unlock;

	ovs_unlock();

	genlmsg_end(reply, ovs_reply_header);
	return genlmsg_reply(reply, info);

exit_unlock:
	ovs_unlock();
	nlmsg_free(reply);
	return err;
}

static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info)
{
	struct nlattr **a = info->attrs;
	u32 meter_id;
	struct ovs_header *ovs_header = info->userhdr;
	struct ovs_header *ovs_reply_header;
	struct datapath *dp;
	int err;
	struct sk_buff *reply;
	struct dp_meter *old_meter;

	if (!a[OVS_METER_ATTR_ID])
		return -EINVAL;
	meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]);

	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL,
					  &ovs_reply_header);
	if (IS_ERR(reply))
		return PTR_ERR(reply);

	ovs_lock();

	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
	if (!dp) {
		err = -ENODEV;
		goto exit_unlock;
	}

	old_meter = lookup_meter(dp, meter_id);
	if (old_meter) {
		spin_lock_bh(&old_meter->lock);
		err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter);
		WARN_ON(err);
		spin_unlock_bh(&old_meter->lock);
		detach_meter(old_meter);
	}
	ovs_unlock();
	ovs_meter_free(old_meter);
	genlmsg_end(reply, ovs_reply_header);
	return genlmsg_reply(reply, info);

exit_unlock:
	ovs_unlock();
	nlmsg_free(reply);
	return err;
}

/* Meter action execution.
 *
 * Return true 'meter_id' drop band is triggered. The 'skb' should be
 * dropped by the caller'.
 */
bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
		       struct sw_flow_key *key, u32 meter_id)
{
	struct dp_meter *meter;
	struct dp_meter_band *band;
	long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000);
	long long int long_delta_ms;
	u32 delta_ms;
	u32 cost;
	int i, band_exceeded_max = -1;
	u32 band_exceeded_rate = 0;

	meter = lookup_meter(dp, meter_id);
	/* Do not drop the packet when there is no meter. */
	if (!meter)
		return false;

	/* Lock the meter while using it. */
	spin_lock(&meter->lock);

	long_delta_ms = (now_ms - meter->used); /* ms */

	/* Make sure delta_ms will not be too large, so that bucket will not
	 * wrap around below.
	 */
	delta_ms = (long_delta_ms > (long long int)meter->max_delta_t)
		   ? meter->max_delta_t : (u32)long_delta_ms;

	/* Update meter statistics.
	 */
	meter->used = now_ms;
	meter->stats.n_packets += 1;
	meter->stats.n_bytes += skb->len;

	/* Bucket rate is either in kilobits per second, or in packets per
	 * second.  We maintain the bucket in the units of either bits or
	 * 1/1000th of a packet, correspondingly.
	 * Then, when rate is multiplied with milliseconds, we get the
	 * bucket units:
	 * msec * kbps = bits, and
	 * msec * packets/sec = 1/1000 packets.
	 *
	 * 'cost' is the number of bucket units in this packet.
	 */
	cost = (meter->kbps) ? skb->len * 8 : 1000;

	/* Update all bands and find the one hit with the highest rate. */
	for (i = 0; i < meter->n_bands; ++i) {
		long long int max_bucket_size;

		band = &meter->bands[i];
		max_bucket_size = (band->burst_size + band->rate) * 1000LL;

		band->bucket += delta_ms * band->rate;
		if (band->bucket > max_bucket_size)
			band->bucket = max_bucket_size;

		if (band->bucket >= cost) {
			band->bucket -= cost;
		} else if (band->rate > band_exceeded_rate) {
			band_exceeded_rate = band->rate;
			band_exceeded_max = i;
		}
	}

	if (band_exceeded_max >= 0) {
		/* Update band statistics. */
		band = &meter->bands[band_exceeded_max];
		band->stats.n_packets += 1;
		band->stats.n_bytes += skb->len;

		/* Drop band triggered, let the caller drop the 'skb'.  */
		if (band->type == OVS_METER_BAND_TYPE_DROP) {
			spin_unlock(&meter->lock);
			return true;
		}
	}

	spin_unlock(&meter->lock);
	return false;
}

static struct genl_ops dp_meter_genl_ops[] = {
	{ .cmd = OVS_METER_CMD_FEATURES,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.flags = 0,		  /* OK for unprivileged users. */
		.doit = ovs_meter_cmd_features
	},
	{ .cmd = OVS_METER_CMD_SET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
					   *  privilege.
					   */
		.doit = ovs_meter_cmd_set,
	},
	{ .cmd = OVS_METER_CMD_GET,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.flags = 0,		  /* OK for unprivileged users. */
		.doit = ovs_meter_cmd_get,
	},
	{ .cmd = OVS_METER_CMD_DEL,
		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
					   *  privilege.
					   */
		.doit = ovs_meter_cmd_del
	},
};

static const struct genl_multicast_group ovs_meter_multicast_group = {
	.name = OVS_METER_MCGROUP,
};

struct genl_family dp_meter_genl_family __ro_after_init = {
	.hdrsize = sizeof(struct ovs_header),
	.name = OVS_METER_FAMILY,
	.version = OVS_METER_VERSION,
	.maxattr = OVS_METER_ATTR_MAX,
	.policy = meter_policy,
	.netnsok = true,
	.parallel_ops = true,
	.ops = dp_meter_genl_ops,
	.n_ops = ARRAY_SIZE(dp_meter_genl_ops),
	.mcgrps = &ovs_meter_multicast_group,
	.n_mcgrps = 1,
	.module = THIS_MODULE,
};

int ovs_meters_init(struct datapath *dp)
{
	int i;

	dp->meters = kmalloc_array(METER_HASH_BUCKETS,
				   sizeof(struct hlist_head), GFP_KERNEL);

	if (!dp->meters)
		return -ENOMEM;

	for (i = 0; i < METER_HASH_BUCKETS; i++)
		INIT_HLIST_HEAD(&dp->meters[i]);

	return 0;
}

void ovs_meters_exit(struct datapath *dp)
{
	int i;

	for (i = 0; i < METER_HASH_BUCKETS; i++) {
		struct hlist_head *head = &dp->meters[i];
		struct dp_meter *meter;
		struct hlist_node *n;

		hlist_for_each_entry_safe(meter, n, head, dp_hash_node)
			kfree(meter);
	}

	kfree(dp->meters);
}