summaryrefslogtreecommitdiff
path: root/net/openvswitch/flow_table.c
blob: fd8a01ca7a2d53d72766d5234e1f133caf4be68e (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
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2007-2014 Nicira, Inc.
 */

#include "flow.h"
#include "datapath.h"
#include "flow_netlink.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/cpumask.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>

#define TBL_MIN_BUCKETS		1024
#define MASK_ARRAY_SIZE_MIN	16
#define REHASH_INTERVAL		(10 * 60 * HZ)

#define MC_HASH_SHIFT		8
#define MC_HASH_ENTRIES		(1u << MC_HASH_SHIFT)
#define MC_HASH_SEGS		((sizeof(uint32_t) * 8) / MC_HASH_SHIFT)

static struct kmem_cache *flow_cache;
struct kmem_cache *flow_stats_cache __read_mostly;

static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
	return range->end - range->start;
}

void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
		       bool full, const struct sw_flow_mask *mask)
{
	int start = full ? 0 : mask->range.start;
	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
	const long *m = (const long *)((const u8 *)&mask->key + start);
	const long *s = (const long *)((const u8 *)src + start);
	long *d = (long *)((u8 *)dst + start);
	int i;

	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
	 * if 'full' is false the memory outside of the 'mask->range' is left
	 * uninitialized. This can be used as an optimization when further
	 * operations on 'dst' only use contents within 'mask->range'.
	 */
	for (i = 0; i < len; i += sizeof(long))
		*d++ = *s++ & *m++;
}

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

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

	flow->stats_last_writer = -1;

	/* Initialize the default stat node. */
	stats = kmem_cache_alloc_node(flow_stats_cache,
				      GFP_KERNEL | __GFP_ZERO,
				      node_online(0) ? 0 : NUMA_NO_NODE);
	if (!stats)
		goto err;

	spin_lock_init(&stats->lock);

	RCU_INIT_POINTER(flow->stats[0], stats);

	cpumask_set_cpu(0, &flow->cpu_used_mask);

	return flow;
err:
	kmem_cache_free(flow_cache, flow);
	return ERR_PTR(-ENOMEM);
}

int ovs_flow_tbl_count(const struct flow_table *table)
{
	return table->count;
}

static void flow_free(struct sw_flow *flow)
{
	int cpu;

	if (ovs_identifier_is_key(&flow->id))
		kfree(flow->id.unmasked_key);
	if (flow->sf_acts)
		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
	/* We open code this to make sure cpu 0 is always considered */
	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
		if (flow->stats[cpu])
			kmem_cache_free(flow_stats_cache,
					(struct sw_flow_stats __force *)flow->stats[cpu]);
	kmem_cache_free(flow_cache, flow);
}

static void rcu_free_flow_callback(struct rcu_head *rcu)
{
	struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);

	flow_free(flow);
}

void ovs_flow_free(struct sw_flow *flow, bool deferred)
{
	if (!flow)
		return;

	if (deferred)
		call_rcu(&flow->rcu, rcu_free_flow_callback);
	else
		flow_free(flow);
}

static void __table_instance_destroy(struct table_instance *ti)
{
	kvfree(ti->buckets);
	kfree(ti);
}

static struct table_instance *table_instance_alloc(int new_size)
{
	struct table_instance *ti = kmalloc(sizeof(*ti), GFP_KERNEL);
	int i;

	if (!ti)
		return NULL;

	ti->buckets = kvmalloc_array(new_size, sizeof(struct hlist_head),
				     GFP_KERNEL);
	if (!ti->buckets) {
		kfree(ti);
		return NULL;
	}

	for (i = 0; i < new_size; i++)
		INIT_HLIST_HEAD(&ti->buckets[i]);

	ti->n_buckets = new_size;
	ti->node_ver = 0;
	ti->keep_flows = false;
	get_random_bytes(&ti->hash_seed, sizeof(u32));

	return ti;
}

static struct mask_array *tbl_mask_array_alloc(int size)
{
	struct mask_array *new;

	size = max(MASK_ARRAY_SIZE_MIN, size);
	new = kzalloc(sizeof(struct mask_array) +
		      sizeof(struct sw_flow_mask *) * size, GFP_KERNEL);
	if (!new)
		return NULL;

	new->count = 0;
	new->max = size;

	return new;
}

static int tbl_mask_array_realloc(struct flow_table *tbl, int size)
{
	struct mask_array *old;
	struct mask_array *new;

	new = tbl_mask_array_alloc(size);
	if (!new)
		return -ENOMEM;

	old = ovsl_dereference(tbl->mask_array);
	if (old) {
		int i;

		for (i = 0; i < old->max; i++) {
			if (ovsl_dereference(old->masks[i]))
				new->masks[new->count++] = old->masks[i];
		}
	}

	rcu_assign_pointer(tbl->mask_array, new);
	kfree_rcu(old, rcu);

	return 0;
}

static int tbl_mask_array_add_mask(struct flow_table *tbl,
				   struct sw_flow_mask *new)
{
	struct mask_array *ma = ovsl_dereference(tbl->mask_array);
	int err, ma_count = READ_ONCE(ma->count);

	if (ma_count >= ma->max) {
		err = tbl_mask_array_realloc(tbl, ma->max +
					      MASK_ARRAY_SIZE_MIN);
		if (err)
			return err;

		ma = ovsl_dereference(tbl->mask_array);
	}

	BUG_ON(ovsl_dereference(ma->masks[ma_count]));

	rcu_assign_pointer(ma->masks[ma_count], new);
	WRITE_ONCE(ma->count, ma_count +1);

	return 0;
}

static void tbl_mask_array_del_mask(struct flow_table *tbl,
				    struct sw_flow_mask *mask)
{
	struct mask_array *ma = ovsl_dereference(tbl->mask_array);
	int i, ma_count = READ_ONCE(ma->count);

	/* Remove the deleted mask pointers from the array */
	for (i = 0; i < ma_count; i++) {
		if (mask == ovsl_dereference(ma->masks[i]))
			goto found;
	}

	BUG();
	return;

found:
	WRITE_ONCE(ma->count, ma_count -1);

	rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]);
	RCU_INIT_POINTER(ma->masks[ma_count -1], NULL);

	kfree_rcu(mask, rcu);

	/* Shrink the mask array if necessary. */
	if (ma->max >= (MASK_ARRAY_SIZE_MIN * 2) &&
	    ma_count <= (ma->max / 3))
		tbl_mask_array_realloc(tbl, ma->max / 2);
}

/* Remove 'mask' from the mask list, if it is not needed any more. */
static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
{
	if (mask) {
		/* ovs-lock is required to protect mask-refcount and
		 * mask list.
		 */
		ASSERT_OVSL();
		BUG_ON(!mask->ref_count);
		mask->ref_count--;

		if (!mask->ref_count)
			tbl_mask_array_del_mask(tbl, mask);
	}
}

int ovs_flow_tbl_init(struct flow_table *table)
{
	struct table_instance *ti, *ufid_ti;
	struct mask_array *ma;

	table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) *
					   MC_HASH_ENTRIES,
					   __alignof__(struct mask_cache_entry));
	if (!table->mask_cache)
		return -ENOMEM;

	ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN);
	if (!ma)
		goto free_mask_cache;

	ti = table_instance_alloc(TBL_MIN_BUCKETS);
	if (!ti)
		goto free_mask_array;

	ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
	if (!ufid_ti)
		goto free_ti;

	rcu_assign_pointer(table->ti, ti);
	rcu_assign_pointer(table->ufid_ti, ufid_ti);
	rcu_assign_pointer(table->mask_array, ma);
	table->last_rehash = jiffies;
	table->count = 0;
	table->ufid_count = 0;
	return 0;

free_ti:
	__table_instance_destroy(ti);
free_mask_array:
	kfree(ma);
free_mask_cache:
	free_percpu(table->mask_cache);
	return -ENOMEM;
}

static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
{
	struct table_instance *ti = container_of(rcu, struct table_instance, rcu);

	__table_instance_destroy(ti);
}

static void table_instance_flow_free(struct flow_table *table,
				  struct table_instance *ti,
				  struct table_instance *ufid_ti,
				  struct sw_flow *flow,
				  bool count)
{
	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
	if (count)
		table->count--;

	if (ovs_identifier_is_ufid(&flow->id)) {
		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);

		if (count)
			table->ufid_count--;
	}

	flow_mask_remove(table, flow->mask);
}

static void table_instance_destroy(struct flow_table *table,
				   struct table_instance *ti,
				   struct table_instance *ufid_ti,
				   bool deferred)
{
	int i;

	if (!ti)
		return;

	BUG_ON(!ufid_ti);
	if (ti->keep_flows)
		goto skip_flows;

	for (i = 0; i < ti->n_buckets; i++) {
		struct sw_flow *flow;
		struct hlist_head *head = &ti->buckets[i];
		struct hlist_node *n;

		hlist_for_each_entry_safe(flow, n, head,
					  flow_table.node[ti->node_ver]) {

			table_instance_flow_free(table, ti, ufid_ti,
						 flow, false);
			ovs_flow_free(flow, deferred);
		}
	}

skip_flows:
	if (deferred) {
		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
		call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);
	} else {
		__table_instance_destroy(ti);
		__table_instance_destroy(ufid_ti);
	}
}

/* No need for locking this function is called from RCU callback or
 * error path.
 */
void ovs_flow_tbl_destroy(struct flow_table *table)
{
	struct table_instance *ti = rcu_dereference_raw(table->ti);
	struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);

	free_percpu(table->mask_cache);
	kfree_rcu(rcu_dereference_raw(table->mask_array), rcu);
	table_instance_destroy(table, ti, ufid_ti, false);
}

struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
				       u32 *bucket, u32 *last)
{
	struct sw_flow *flow;
	struct hlist_head *head;
	int ver;
	int i;

	ver = ti->node_ver;
	while (*bucket < ti->n_buckets) {
		i = 0;
		head = &ti->buckets[*bucket];
		hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
			if (i < *last) {
				i++;
				continue;
			}
			*last = i + 1;
			return flow;
		}
		(*bucket)++;
		*last = 0;
	}

	return NULL;
}

static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash)
{
	hash = jhash_1word(hash, ti->hash_seed);
	return &ti->buckets[hash & (ti->n_buckets - 1)];
}

static void table_instance_insert(struct table_instance *ti,
				  struct sw_flow *flow)
{
	struct hlist_head *head;

	head = find_bucket(ti, flow->flow_table.hash);
	hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);
}

static void ufid_table_instance_insert(struct table_instance *ti,
				       struct sw_flow *flow)
{
	struct hlist_head *head;

	head = find_bucket(ti, flow->ufid_table.hash);
	hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);
}

static void flow_table_copy_flows(struct table_instance *old,
				  struct table_instance *new, bool ufid)
{
	int old_ver;
	int i;

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

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

		if (ufid)
			hlist_for_each_entry(flow, head,
					     ufid_table.node[old_ver])
				ufid_table_instance_insert(new, flow);
		else
			hlist_for_each_entry(flow, head,
					     flow_table.node[old_ver])
				table_instance_insert(new, flow);
	}

	old->keep_flows = true;
}

static struct table_instance *table_instance_rehash(struct table_instance *ti,
						    int n_buckets, bool ufid)
{
	struct table_instance *new_ti;

	new_ti = table_instance_alloc(n_buckets);
	if (!new_ti)
		return NULL;

	flow_table_copy_flows(ti, new_ti, ufid);

	return new_ti;
}

int ovs_flow_tbl_flush(struct flow_table *flow_table)
{
	struct table_instance *old_ti, *new_ti;
	struct table_instance *old_ufid_ti, *new_ufid_ti;

	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
	if (!new_ti)
		return -ENOMEM;
	new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
	if (!new_ufid_ti)
		goto err_free_ti;

	old_ti = ovsl_dereference(flow_table->ti);
	old_ufid_ti = ovsl_dereference(flow_table->ufid_ti);

	rcu_assign_pointer(flow_table->ti, new_ti);
	rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
	flow_table->last_rehash = jiffies;
	flow_table->count = 0;
	flow_table->ufid_count = 0;

	table_instance_destroy(flow_table, old_ti, old_ufid_ti, true);
	return 0;

err_free_ti:
	__table_instance_destroy(new_ti);
	return -ENOMEM;
}

static u32 flow_hash(const struct sw_flow_key *key,
		     const struct sw_flow_key_range *range)
{
	const u32 *hash_key = (const u32 *)((const u8 *)key + range->start);

	/* Make sure number of hash bytes are multiple of u32. */
	int hash_u32s = range_n_bytes(range) >> 2;

	return jhash2(hash_key, hash_u32s, 0);
}

static int flow_key_start(const struct sw_flow_key *key)
{
	if (key->tun_proto)
		return 0;
	else
		return rounddown(offsetof(struct sw_flow_key, phy),
					  sizeof(long));
}

static bool cmp_key(const struct sw_flow_key *key1,
		    const struct sw_flow_key *key2,
		    int key_start, int key_end)
{
	const long *cp1 = (const long *)((const u8 *)key1 + key_start);
	const long *cp2 = (const long *)((const u8 *)key2 + key_start);
	long diffs = 0;
	int i;

	for (i = key_start; i < key_end;  i += sizeof(long))
		diffs |= *cp1++ ^ *cp2++;

	return diffs == 0;
}

static bool flow_cmp_masked_key(const struct sw_flow *flow,
				const struct sw_flow_key *key,
				const struct sw_flow_key_range *range)
{
	return cmp_key(&flow->key, key, range->start, range->end);
}

static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
				      const struct sw_flow_match *match)
{
	struct sw_flow_key *key = match->key;
	int key_start = flow_key_start(key);
	int key_end = match->range.end;

	BUG_ON(ovs_identifier_is_ufid(&flow->id));
	return cmp_key(flow->id.unmasked_key, key, key_start, key_end);
}

static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
					  const struct sw_flow_key *unmasked,
					  const struct sw_flow_mask *mask,
					  u32 *n_mask_hit)
{
	struct sw_flow *flow;
	struct hlist_head *head;
	u32 hash;
	struct sw_flow_key masked_key;

	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
	hash = flow_hash(&masked_key, &mask->range);
	head = find_bucket(ti, hash);
	(*n_mask_hit)++;

	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver],
				lockdep_ovsl_is_held()) {
		if (flow->mask == mask && flow->flow_table.hash == hash &&
		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
			return flow;
	}
	return NULL;
}

/* Flow lookup does full lookup on flow table. It starts with
 * mask from index passed in *index.
 */
static struct sw_flow *flow_lookup(struct flow_table *tbl,
				   struct table_instance *ti,
				   struct mask_array *ma,
				   const struct sw_flow_key *key,
				   u32 *n_mask_hit,
				   u32 *index)
{
	struct sw_flow *flow;
	struct sw_flow_mask *mask;
	int i;

	if (likely(*index < ma->max)) {
		mask = rcu_dereference_ovsl(ma->masks[*index]);
		if (mask) {
			flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
			if (flow)
				return flow;
		}
	}

	for (i = 0; i < ma->max; i++)  {

		if (i == *index)
			continue;

		mask = rcu_dereference_ovsl(ma->masks[i]);
		if (unlikely(!mask))
			break;

		flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
		if (flow) { /* Found */
			*index = i;
			return flow;
		}
	}

	return NULL;
}

/*
 * mask_cache maps flow to probable mask. This cache is not tightly
 * coupled cache, It means updates to  mask list can result in inconsistent
 * cache entry in mask cache.
 * This is per cpu cache and is divided in MC_HASH_SEGS segments.
 * In case of a hash collision the entry is hashed in next segment.
 * */
struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
					  const struct sw_flow_key *key,
					  u32 skb_hash,
					  u32 *n_mask_hit)
{
	struct mask_array *ma = rcu_dereference(tbl->mask_array);
	struct table_instance *ti = rcu_dereference(tbl->ti);
	struct mask_cache_entry *entries, *ce;
	struct sw_flow *flow;
	u32 hash;
	int seg;

	*n_mask_hit = 0;
	if (unlikely(!skb_hash)) {
		u32 mask_index = 0;

		return flow_lookup(tbl, ti, ma, key, n_mask_hit, &mask_index);
	}

	/* Pre and post recirulation flows usually have the same skb_hash
	 * value. To avoid hash collisions, rehash the 'skb_hash' with
	 * 'recirc_id'.  */
	if (key->recirc_id)
		skb_hash = jhash_1word(skb_hash, key->recirc_id);

	ce = NULL;
	hash = skb_hash;
	entries = this_cpu_ptr(tbl->mask_cache);

	/* Find the cache entry 'ce' to operate on. */
	for (seg = 0; seg < MC_HASH_SEGS; seg++) {
		int index = hash & (MC_HASH_ENTRIES - 1);
		struct mask_cache_entry *e;

		e = &entries[index];
		if (e->skb_hash == skb_hash) {
			flow = flow_lookup(tbl, ti, ma, key, n_mask_hit,
					   &e->mask_index);
			if (!flow)
				e->skb_hash = 0;
			return flow;
		}

		if (!ce || e->skb_hash < ce->skb_hash)
			ce = e;  /* A better replacement cache candidate. */

		hash >>= MC_HASH_SHIFT;
	}

	/* Cache miss, do full lookup. */
	flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &ce->mask_index);
	if (flow)
		ce->skb_hash = skb_hash;

	return flow;
}

struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
				    const struct sw_flow_key *key)
{
	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
	struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array);
	u32 __always_unused n_mask_hit;
	u32 index = 0;

	return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &index);
}

struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
					  const struct sw_flow_match *match)
{
	struct mask_array *ma = ovsl_dereference(tbl->mask_array);
	int i;

	/* Always called under ovs-mutex. */
	for (i = 0; i < ma->max; i++) {
		struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
		u32 __always_unused n_mask_hit;
		struct sw_flow_mask *mask;
		struct sw_flow *flow;

		mask = ovsl_dereference(ma->masks[i]);
		if (!mask)
			continue;

		flow = masked_flow_lookup(ti, match->key, mask, &n_mask_hit);
		if (flow && ovs_identifier_is_key(&flow->id) &&
		    ovs_flow_cmp_unmasked_key(flow, match)) {
			return flow;
		}
	}

	return NULL;
}

static u32 ufid_hash(const struct sw_flow_id *sfid)
{
	return jhash(sfid->ufid, sfid->ufid_len, 0);
}

static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
			      const struct sw_flow_id *sfid)
{
	if (flow->id.ufid_len != sfid->ufid_len)
		return false;

	return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
}

bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
{
	if (ovs_identifier_is_ufid(&flow->id))
		return flow_cmp_masked_key(flow, match->key, &match->range);

	return ovs_flow_cmp_unmasked_key(flow, match);
}

struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
					 const struct sw_flow_id *ufid)
{
	struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti);
	struct sw_flow *flow;
	struct hlist_head *head;
	u32 hash;

	hash = ufid_hash(ufid);
	head = find_bucket(ti, hash);
	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver],
				lockdep_ovsl_is_held()) {
		if (flow->ufid_table.hash == hash &&
		    ovs_flow_cmp_ufid(flow, ufid))
			return flow;
	}
	return NULL;
}

int ovs_flow_tbl_num_masks(const struct flow_table *table)
{
	struct mask_array *ma = rcu_dereference_ovsl(table->mask_array);
	return READ_ONCE(ma->count);
}

static struct table_instance *table_instance_expand(struct table_instance *ti,
						    bool ufid)
{
	return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
}

/* Must be called with OVS mutex held. */
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
{
	struct table_instance *ti = ovsl_dereference(table->ti);
	struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);

	BUG_ON(table->count == 0);
	table_instance_flow_free(table, ti, ufid_ti, flow, true);
}

static struct sw_flow_mask *mask_alloc(void)
{
	struct sw_flow_mask *mask;

	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
	if (mask)
		mask->ref_count = 1;

	return mask;
}

static bool mask_equal(const struct sw_flow_mask *a,
		       const struct sw_flow_mask *b)
{
	const u8 *a_ = (const u8 *)&a->key + a->range.start;
	const u8 *b_ = (const u8 *)&b->key + b->range.start;

	return  (a->range.end == b->range.end)
		&& (a->range.start == b->range.start)
		&& (memcmp(a_, b_, range_n_bytes(&a->range)) == 0);
}

static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
					   const struct sw_flow_mask *mask)
{
	struct mask_array *ma;
	int i;

	ma = ovsl_dereference(tbl->mask_array);
	for (i = 0; i < ma->max; i++) {
		struct sw_flow_mask *t;
		t = ovsl_dereference(ma->masks[i]);

		if (t && mask_equal(mask, t))
			return t;
	}

	return NULL;
}

/* Add 'mask' into the mask list, if it is not already there. */
static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
			    const struct sw_flow_mask *new)
{
	struct sw_flow_mask *mask;

	mask = flow_mask_find(tbl, new);
	if (!mask) {
		/* Allocate a new mask if none exsits. */
		mask = mask_alloc();
		if (!mask)
			return -ENOMEM;
		mask->key = new->key;
		mask->range = new->range;

		/* Add mask to mask-list. */
		if (tbl_mask_array_add_mask(tbl, mask)) {
			kfree(mask);
			return -ENOMEM;
		}
	} else {
		BUG_ON(!mask->ref_count);
		mask->ref_count++;
	}

	flow->mask = mask;
	return 0;
}

/* Must be called with OVS mutex held. */
static void flow_key_insert(struct flow_table *table, struct sw_flow *flow)
{
	struct table_instance *new_ti = NULL;
	struct table_instance *ti;

	flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range);
	ti = ovsl_dereference(table->ti);
	table_instance_insert(ti, flow);
	table->count++;

	/* Expand table, if necessary, to make room. */
	if (table->count > ti->n_buckets)
		new_ti = table_instance_expand(ti, false);
	else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
		new_ti = table_instance_rehash(ti, ti->n_buckets, false);

	if (new_ti) {
		rcu_assign_pointer(table->ti, new_ti);
		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
		table->last_rehash = jiffies;
	}
}

/* Must be called with OVS mutex held. */
static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow)
{
	struct table_instance *ti;

	flow->ufid_table.hash = ufid_hash(&flow->id);
	ti = ovsl_dereference(table->ufid_ti);
	ufid_table_instance_insert(ti, flow);
	table->ufid_count++;

	/* Expand table, if necessary, to make room. */
	if (table->ufid_count > ti->n_buckets) {
		struct table_instance *new_ti;

		new_ti = table_instance_expand(ti, true);
		if (new_ti) {
			rcu_assign_pointer(table->ufid_ti, new_ti);
			call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
		}
	}
}

/* Must be called with OVS mutex held. */
int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
			const struct sw_flow_mask *mask)
{
	int err;

	err = flow_mask_insert(table, flow, mask);
	if (err)
		return err;
	flow_key_insert(table, flow);
	if (ovs_identifier_is_ufid(&flow->id))
		flow_ufid_insert(table, flow);

	return 0;
}

/* Initializes the flow module.
 * Returns zero if successful or a negative error code. */
int ovs_flow_init(void)
{
	BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));

	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
				       + (nr_cpu_ids
					  * sizeof(struct sw_flow_stats *)),
				       0, 0, NULL);
	if (flow_cache == NULL)
		return -ENOMEM;

	flow_stats_cache
		= kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats),
				    0, SLAB_HWCACHE_ALIGN, NULL);
	if (flow_stats_cache == NULL) {
		kmem_cache_destroy(flow_cache);
		flow_cache = NULL;
		return -ENOMEM;
	}

	return 0;
}

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