summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
blob: 623f73dd7738dbbb01b8f49649a4507d641b1d9a (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
/*
 * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
 *
 * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <net/tc_act/tc_mirred.h>
#include <net/tc_act/tc_pedit.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_vlan.h>

#include "cxgb4.h"
#include "cxgb4_filter.h"
#include "cxgb4_tc_flower.h"

#define STATS_CHECK_PERIOD (HZ / 2)

static struct ch_tc_pedit_fields pedits[] = {
	PEDIT_FIELDS(ETH_, DMAC_31_0, 4, dmac, 0),
	PEDIT_FIELDS(ETH_, DMAC_47_32, 2, dmac, 4),
	PEDIT_FIELDS(ETH_, SMAC_15_0, 2, smac, 0),
	PEDIT_FIELDS(ETH_, SMAC_47_16, 4, smac, 2),
	PEDIT_FIELDS(IP4_, SRC, 4, nat_fip, 0),
	PEDIT_FIELDS(IP4_, DST, 4, nat_lip, 0),
	PEDIT_FIELDS(IP6_, SRC_31_0, 4, nat_fip, 0),
	PEDIT_FIELDS(IP6_, SRC_63_32, 4, nat_fip, 4),
	PEDIT_FIELDS(IP6_, SRC_95_64, 4, nat_fip, 8),
	PEDIT_FIELDS(IP6_, SRC_127_96, 4, nat_fip, 12),
	PEDIT_FIELDS(IP6_, DST_31_0, 4, nat_lip, 0),
	PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4),
	PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8),
	PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12),
	PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0),
	PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0),
	PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0),
	PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0),
};

static struct ch_tc_flower_entry *allocate_flower_entry(void)
{
	struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL);
	spin_lock_init(&new->lock);
	return new;
}

/* Must be called with either RTNL or rcu_read_lock */
static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
						   unsigned long flower_cookie)
{
	return rhashtable_lookup_fast(&adap->flower_tbl, &flower_cookie,
				      adap->flower_ht_params);
}

static void cxgb4_process_flow_match(struct net_device *dev,
				     struct tc_cls_flower_offload *cls,
				     struct ch_filter_specification *fs)
{
	u16 addr_type = 0;

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
		struct flow_dissector_key_control *key =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_CONTROL,
						  cls->key);

		addr_type = key->addr_type;
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
		struct flow_dissector_key_basic *key =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_BASIC,
						  cls->key);
		struct flow_dissector_key_basic *mask =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_BASIC,
						  cls->mask);
		u16 ethtype_key = ntohs(key->n_proto);
		u16 ethtype_mask = ntohs(mask->n_proto);

		if (ethtype_key == ETH_P_ALL) {
			ethtype_key = 0;
			ethtype_mask = 0;
		}

		if (ethtype_key == ETH_P_IPV6)
			fs->type = 1;

		fs->val.ethtype = ethtype_key;
		fs->mask.ethtype = ethtype_mask;
		fs->val.proto = key->ip_proto;
		fs->mask.proto = mask->ip_proto;
	}

	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
		struct flow_dissector_key_ipv4_addrs *key =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
						  cls->key);
		struct flow_dissector_key_ipv4_addrs *mask =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
						  cls->mask);
		fs->type = 0;
		memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst));
		memcpy(&fs->val.fip[0], &key->src, sizeof(key->src));
		memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst));
		memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src));

		/* also initialize nat_lip/fip to same values */
		memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst));
		memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src));

	}

	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
		struct flow_dissector_key_ipv6_addrs *key =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
						  cls->key);
		struct flow_dissector_key_ipv6_addrs *mask =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
						  cls->mask);

		fs->type = 1;
		memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst));
		memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src));
		memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst));
		memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src));

		/* also initialize nat_lip/fip to same values */
		memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst));
		memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src));
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
		struct flow_dissector_key_ports *key, *mask;

		key = skb_flow_dissector_target(cls->dissector,
						FLOW_DISSECTOR_KEY_PORTS,
						cls->key);
		mask = skb_flow_dissector_target(cls->dissector,
						 FLOW_DISSECTOR_KEY_PORTS,
						 cls->mask);
		fs->val.lport = cpu_to_be16(key->dst);
		fs->mask.lport = cpu_to_be16(mask->dst);
		fs->val.fport = cpu_to_be16(key->src);
		fs->mask.fport = cpu_to_be16(mask->src);

		/* also initialize nat_lport/fport to same values */
		fs->nat_lport = cpu_to_be16(key->dst);
		fs->nat_fport = cpu_to_be16(key->src);
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
		struct flow_dissector_key_ip *key, *mask;

		key = skb_flow_dissector_target(cls->dissector,
						FLOW_DISSECTOR_KEY_IP,
						cls->key);
		mask = skb_flow_dissector_target(cls->dissector,
						 FLOW_DISSECTOR_KEY_IP,
						 cls->mask);
		fs->val.tos = key->tos;
		fs->mask.tos = mask->tos;
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
		struct flow_dissector_key_keyid *key, *mask;

		key = skb_flow_dissector_target(cls->dissector,
						FLOW_DISSECTOR_KEY_ENC_KEYID,
						cls->key);
		mask = skb_flow_dissector_target(cls->dissector,
						 FLOW_DISSECTOR_KEY_ENC_KEYID,
						 cls->mask);
		fs->val.vni = be32_to_cpu(key->keyid);
		fs->mask.vni = be32_to_cpu(mask->keyid);
		if (fs->mask.vni) {
			fs->val.encap_vld = 1;
			fs->mask.encap_vld = 1;
		}
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
		struct flow_dissector_key_vlan *key, *mask;
		u16 vlan_tci, vlan_tci_mask;

		key = skb_flow_dissector_target(cls->dissector,
						FLOW_DISSECTOR_KEY_VLAN,
						cls->key);
		mask = skb_flow_dissector_target(cls->dissector,
						 FLOW_DISSECTOR_KEY_VLAN,
						 cls->mask);
		vlan_tci = key->vlan_id | (key->vlan_priority <<
					   VLAN_PRIO_SHIFT);
		vlan_tci_mask = mask->vlan_id | (mask->vlan_priority <<
						 VLAN_PRIO_SHIFT);
		fs->val.ivlan = vlan_tci;
		fs->mask.ivlan = vlan_tci_mask;

		/* Chelsio adapters use ivlan_vld bit to match vlan packets
		 * as 802.1Q. Also, when vlan tag is present in packets,
		 * ethtype match is used then to match on ethtype of inner
		 * header ie. the header following the vlan header.
		 * So, set the ivlan_vld based on ethtype info supplied by
		 * TC for vlan packets if its 802.1Q. And then reset the
		 * ethtype value else, hw will try to match the supplied
		 * ethtype value with ethtype of inner header.
		 */
		if (fs->val.ethtype == ETH_P_8021Q) {
			fs->val.ivlan_vld = 1;
			fs->mask.ivlan_vld = 1;
			fs->val.ethtype = 0;
			fs->mask.ethtype = 0;
		}
	}

	/* Match only packets coming from the ingress port where this
	 * filter will be created.
	 */
	fs->val.iport = netdev2pinfo(dev)->port_id;
	fs->mask.iport = ~0;
}

static int cxgb4_validate_flow_match(struct net_device *dev,
				     struct tc_cls_flower_offload *cls)
{
	u16 ethtype_mask = 0;
	u16 ethtype_key = 0;

	if (cls->dissector->used_keys &
	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
	      BIT(FLOW_DISSECTOR_KEY_IP))) {
		netdev_warn(dev, "Unsupported key used: 0x%x\n",
			    cls->dissector->used_keys);
		return -EOPNOTSUPP;
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
		struct flow_dissector_key_basic *key =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_BASIC,
						  cls->key);
		struct flow_dissector_key_basic *mask =
			skb_flow_dissector_target(cls->dissector,
						  FLOW_DISSECTOR_KEY_BASIC,
						  cls->mask);
		ethtype_key = ntohs(key->n_proto);
		ethtype_mask = ntohs(mask->n_proto);
	}

	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
		u16 eth_ip_type = ethtype_key & ethtype_mask;
		struct flow_dissector_key_ip *mask;

		if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) {
			netdev_err(dev, "IP Key supported only with IPv4/v6");
			return -EINVAL;
		}

		mask = skb_flow_dissector_target(cls->dissector,
						 FLOW_DISSECTOR_KEY_IP,
						 cls->mask);
		if (mask->ttl) {
			netdev_warn(dev, "ttl match unsupported for offload");
			return -EOPNOTSUPP;
		}
	}

	return 0;
}

static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask,
			  u8 field)
{
	u32 set_val = val & ~mask;
	u32 offset = 0;
	u8 size = 1;
	int i;

	for (i = 0; i < ARRAY_SIZE(pedits); i++) {
		if (pedits[i].field == field) {
			offset = pedits[i].offset;
			size = pedits[i].size;
			break;
		}
	}
	memcpy((u8 *)fs + offset, &set_val, size);
}

static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
				u32 mask, u32 offset, u8 htype)
{
	switch (htype) {
	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
		switch (offset) {
		case PEDIT_ETH_DMAC_31_0:
			fs->newdmac = 1;
			offload_pedit(fs, val, mask, ETH_DMAC_31_0);
			break;
		case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
			if (~mask & PEDIT_ETH_DMAC_MASK)
				offload_pedit(fs, val, mask, ETH_DMAC_47_32);
			else
				offload_pedit(fs, val >> 16, mask >> 16,
					      ETH_SMAC_15_0);
			break;
		case PEDIT_ETH_SMAC_47_16:
			fs->newsmac = 1;
			offload_pedit(fs, val, mask, ETH_SMAC_47_16);
		}
		break;
	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
		switch (offset) {
		case PEDIT_IP4_SRC:
			offload_pedit(fs, val, mask, IP4_SRC);
			break;
		case PEDIT_IP4_DST:
			offload_pedit(fs, val, mask, IP4_DST);
		}
		fs->nat_mode = NAT_MODE_ALL;
		break;
	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
		switch (offset) {
		case PEDIT_IP6_SRC_31_0:
			offload_pedit(fs, val, mask, IP6_SRC_31_0);
			break;
		case PEDIT_IP6_SRC_63_32:
			offload_pedit(fs, val, mask, IP6_SRC_63_32);
			break;
		case PEDIT_IP6_SRC_95_64:
			offload_pedit(fs, val, mask, IP6_SRC_95_64);
			break;
		case PEDIT_IP6_SRC_127_96:
			offload_pedit(fs, val, mask, IP6_SRC_127_96);
			break;
		case PEDIT_IP6_DST_31_0:
			offload_pedit(fs, val, mask, IP6_DST_31_0);
			break;
		case PEDIT_IP6_DST_63_32:
			offload_pedit(fs, val, mask, IP6_DST_63_32);
			break;
		case PEDIT_IP6_DST_95_64:
			offload_pedit(fs, val, mask, IP6_DST_95_64);
			break;
		case PEDIT_IP6_DST_127_96:
			offload_pedit(fs, val, mask, IP6_DST_127_96);
		}
		fs->nat_mode = NAT_MODE_ALL;
		break;
	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
		switch (offset) {
		case PEDIT_TCP_SPORT_DPORT:
			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
				offload_pedit(fs, cpu_to_be32(val) >> 16,
					      cpu_to_be32(mask) >> 16,
					      TCP_SPORT);
			else
				offload_pedit(fs, cpu_to_be32(val),
					      cpu_to_be32(mask), TCP_DPORT);
		}
		fs->nat_mode = NAT_MODE_ALL;
		break;
	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
		switch (offset) {
		case PEDIT_UDP_SPORT_DPORT:
			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
				offload_pedit(fs, cpu_to_be32(val) >> 16,
					      cpu_to_be32(mask) >> 16,
					      UDP_SPORT);
			else
				offload_pedit(fs, cpu_to_be32(val),
					      cpu_to_be32(mask), UDP_DPORT);
		}
		fs->nat_mode = NAT_MODE_ALL;
	}
}

static void cxgb4_process_flow_actions(struct net_device *in,
				       struct tc_cls_flower_offload *cls,
				       struct ch_filter_specification *fs)
{
	const struct tc_action *a;
	LIST_HEAD(actions);

	tcf_exts_to_list(cls->exts, &actions);
	list_for_each_entry(a, &actions, list) {
		if (is_tcf_gact_ok(a)) {
			fs->action = FILTER_PASS;
		} else if (is_tcf_gact_shot(a)) {
			fs->action = FILTER_DROP;
		} else if (is_tcf_mirred_egress_redirect(a)) {
			struct net_device *out = tcf_mirred_dev(a);
			struct port_info *pi = netdev_priv(out);

			fs->action = FILTER_SWITCH;
			fs->eport = pi->port_id;
		} else if (is_tcf_vlan(a)) {
			u32 vlan_action = tcf_vlan_action(a);
			u8 prio = tcf_vlan_push_prio(a);
			u16 vid = tcf_vlan_push_vid(a);
			u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid;

			switch (vlan_action) {
			case TCA_VLAN_ACT_POP:
				fs->newvlan |= VLAN_REMOVE;
				break;
			case TCA_VLAN_ACT_PUSH:
				fs->newvlan |= VLAN_INSERT;
				fs->vlan = vlan_tci;
				break;
			case TCA_VLAN_ACT_MODIFY:
				fs->newvlan |= VLAN_REWRITE;
				fs->vlan = vlan_tci;
				break;
			default:
				break;
			}
		} else if (is_tcf_pedit(a)) {
			u32 mask, val, offset;
			int nkeys, i;
			u8 htype;

			nkeys = tcf_pedit_nkeys(a);
			for (i = 0; i < nkeys; i++) {
				htype = tcf_pedit_htype(a, i);
				mask = tcf_pedit_mask(a, i);
				val = tcf_pedit_val(a, i);
				offset = tcf_pedit_offset(a, i);

				process_pedit_field(fs, val, mask, offset,
						    htype);
			}
		}
	}
}

static bool valid_l4_mask(u32 mask)
{
	u16 hi, lo;

	/* Either the upper 16-bits (SPORT) OR the lower
	 * 16-bits (DPORT) can be set, but NOT BOTH.
	 */
	hi = (mask >> 16) & 0xFFFF;
	lo = mask & 0xFFFF;

	return hi && lo ? false : true;
}

static bool valid_pedit_action(struct net_device *dev,
			       const struct tc_action *a)
{
	u32 mask, offset;
	u8 cmd, htype;
	int nkeys, i;

	nkeys = tcf_pedit_nkeys(a);
	for (i = 0; i < nkeys; i++) {
		htype = tcf_pedit_htype(a, i);
		cmd = tcf_pedit_cmd(a, i);
		mask = tcf_pedit_mask(a, i);
		offset = tcf_pedit_offset(a, i);

		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) {
			netdev_err(dev, "%s: Unsupported pedit cmd\n",
				   __func__);
			return false;
		}

		switch (htype) {
		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
			switch (offset) {
			case PEDIT_ETH_DMAC_31_0:
			case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
			case PEDIT_ETH_SMAC_47_16:
				break;
			default:
				netdev_err(dev, "%s: Unsupported pedit field\n",
					   __func__);
				return false;
			}
			break;
		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
			switch (offset) {
			case PEDIT_IP4_SRC:
			case PEDIT_IP4_DST:
				break;
			default:
				netdev_err(dev, "%s: Unsupported pedit field\n",
					   __func__);
				return false;
			}
			break;
		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
			switch (offset) {
			case PEDIT_IP6_SRC_31_0:
			case PEDIT_IP6_SRC_63_32:
			case PEDIT_IP6_SRC_95_64:
			case PEDIT_IP6_SRC_127_96:
			case PEDIT_IP6_DST_31_0:
			case PEDIT_IP6_DST_63_32:
			case PEDIT_IP6_DST_95_64:
			case PEDIT_IP6_DST_127_96:
				break;
			default:
				netdev_err(dev, "%s: Unsupported pedit field\n",
					   __func__);
				return false;
			}
			break;
		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
			switch (offset) {
			case PEDIT_TCP_SPORT_DPORT:
				if (!valid_l4_mask(~mask)) {
					netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
						   __func__);
					return false;
				}
				break;
			default:
				netdev_err(dev, "%s: Unsupported pedit field\n",
					   __func__);
				return false;
			}
			break;
		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
			switch (offset) {
			case PEDIT_UDP_SPORT_DPORT:
				if (!valid_l4_mask(~mask)) {
					netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
						   __func__);
					return false;
				}
				break;
			default:
				netdev_err(dev, "%s: Unsupported pedit field\n",
					   __func__);
				return false;
			}
			break;
		default:
			netdev_err(dev, "%s: Unsupported pedit type\n",
				   __func__);
			return false;
		}
	}
	return true;
}

static int cxgb4_validate_flow_actions(struct net_device *dev,
				       struct tc_cls_flower_offload *cls)
{
	const struct tc_action *a;
	bool act_redir = false;
	bool act_pedit = false;
	bool act_vlan = false;
	LIST_HEAD(actions);

	tcf_exts_to_list(cls->exts, &actions);
	list_for_each_entry(a, &actions, list) {
		if (is_tcf_gact_ok(a)) {
			/* Do nothing */
		} else if (is_tcf_gact_shot(a)) {
			/* Do nothing */
		} else if (is_tcf_mirred_egress_redirect(a)) {
			struct adapter *adap = netdev2adap(dev);
			struct net_device *n_dev, *target_dev;
			unsigned int i;
			bool found = false;

			target_dev = tcf_mirred_dev(a);
			for_each_port(adap, i) {
				n_dev = adap->port[i];
				if (target_dev == n_dev) {
					found = true;
					break;
				}
			}

			/* If interface doesn't belong to our hw, then
			 * the provided output port is not valid
			 */
			if (!found) {
				netdev_err(dev, "%s: Out port invalid\n",
					   __func__);
				return -EINVAL;
			}
			act_redir = true;
		} else if (is_tcf_vlan(a)) {
			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
			u32 vlan_action = tcf_vlan_action(a);

			switch (vlan_action) {
			case TCA_VLAN_ACT_POP:
				break;
			case TCA_VLAN_ACT_PUSH:
			case TCA_VLAN_ACT_MODIFY:
				if (proto != ETH_P_8021Q) {
					netdev_err(dev, "%s: Unsupported vlan proto\n",
						   __func__);
					return -EOPNOTSUPP;
				}
				break;
			default:
				netdev_err(dev, "%s: Unsupported vlan action\n",
					   __func__);
				return -EOPNOTSUPP;
			}
			act_vlan = true;
		} else if (is_tcf_pedit(a)) {
			bool pedit_valid = valid_pedit_action(dev, a);

			if (!pedit_valid)
				return -EOPNOTSUPP;
			act_pedit = true;
		} else {
			netdev_err(dev, "%s: Unsupported action\n", __func__);
			return -EOPNOTSUPP;
		}
	}

	if ((act_pedit || act_vlan) && !act_redir) {
		netdev_err(dev, "%s: pedit/vlan rewrite invalid without egress redirect\n",
			   __func__);
		return -EINVAL;
	}

	return 0;
}

int cxgb4_tc_flower_replace(struct net_device *dev,
			    struct tc_cls_flower_offload *cls)
{
	struct adapter *adap = netdev2adap(dev);
	struct ch_tc_flower_entry *ch_flower;
	struct ch_filter_specification *fs;
	struct filter_ctx ctx;
	int fidx;
	int ret;

	if (cxgb4_validate_flow_actions(dev, cls))
		return -EOPNOTSUPP;

	if (cxgb4_validate_flow_match(dev, cls))
		return -EOPNOTSUPP;

	ch_flower = allocate_flower_entry();
	if (!ch_flower) {
		netdev_err(dev, "%s: ch_flower alloc failed.\n", __func__);
		return -ENOMEM;
	}

	fs = &ch_flower->fs;
	fs->hitcnts = 1;
	cxgb4_process_flow_match(dev, cls, fs);
	cxgb4_process_flow_actions(dev, cls, fs);

	fs->hash = is_filter_exact_match(adap, fs);
	if (fs->hash) {
		fidx = 0;
	} else {
		fidx = cxgb4_get_free_ftid(dev, fs->type ? PF_INET6 : PF_INET);
		if (fidx < 0) {
			netdev_err(dev, "%s: No fidx for offload.\n", __func__);
			ret = -ENOMEM;
			goto free_entry;
		}
	}

	init_completion(&ctx.completion);
	ret = __cxgb4_set_filter(dev, fidx, fs, &ctx);
	if (ret) {
		netdev_err(dev, "%s: filter creation err %d\n",
			   __func__, ret);
		goto free_entry;
	}

	/* Wait for reply */
	ret = wait_for_completion_timeout(&ctx.completion, 10 * HZ);
	if (!ret) {
		ret = -ETIMEDOUT;
		goto free_entry;
	}

	ret = ctx.result;
	/* Check if hw returned error for filter creation */
	if (ret) {
		netdev_err(dev, "%s: filter creation err %d\n",
			   __func__, ret);
		goto free_entry;
	}

	ch_flower->tc_flower_cookie = cls->cookie;
	ch_flower->filter_id = ctx.tid;
	ret = rhashtable_insert_fast(&adap->flower_tbl, &ch_flower->node,
				     adap->flower_ht_params);
	if (ret)
		goto del_filter;

	return 0;

del_filter:
	cxgb4_del_filter(dev, ch_flower->filter_id, &ch_flower->fs);

free_entry:
	kfree(ch_flower);
	return ret;
}

int cxgb4_tc_flower_destroy(struct net_device *dev,
			    struct tc_cls_flower_offload *cls)
{
	struct adapter *adap = netdev2adap(dev);
	struct ch_tc_flower_entry *ch_flower;
	int ret;

	ch_flower = ch_flower_lookup(adap, cls->cookie);
	if (!ch_flower)
		return -ENOENT;

	ret = cxgb4_del_filter(dev, ch_flower->filter_id, &ch_flower->fs);
	if (ret)
		goto err;

	ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
				     adap->flower_ht_params);
	if (ret) {
		netdev_err(dev, "Flow remove from rhashtable failed");
		goto err;
	}
	kfree_rcu(ch_flower, rcu);

err:
	return ret;
}

static void ch_flower_stats_handler(struct work_struct *work)
{
	struct adapter *adap = container_of(work, struct adapter,
					    flower_stats_work);
	struct ch_tc_flower_entry *flower_entry;
	struct ch_tc_flower_stats *ofld_stats;
	struct rhashtable_iter iter;
	u64 packets;
	u64 bytes;
	int ret;

	rhashtable_walk_enter(&adap->flower_tbl, &iter);
	do {
		rhashtable_walk_start(&iter);

		while ((flower_entry = rhashtable_walk_next(&iter)) &&
		       !IS_ERR(flower_entry)) {
			ret = cxgb4_get_filter_counters(adap->port[0],
							flower_entry->filter_id,
							&packets, &bytes,
							flower_entry->fs.hash);
			if (!ret) {
				spin_lock(&flower_entry->lock);
				ofld_stats = &flower_entry->stats;

				if (ofld_stats->prev_packet_count != packets) {
					ofld_stats->prev_packet_count = packets;
					ofld_stats->last_used = jiffies;
				}
				spin_unlock(&flower_entry->lock);
			}
		}

		rhashtable_walk_stop(&iter);

	} while (flower_entry == ERR_PTR(-EAGAIN));
	rhashtable_walk_exit(&iter);
	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
}

static void ch_flower_stats_cb(struct timer_list *t)
{
	struct adapter *adap = from_timer(adap, t, flower_stats_timer);

	schedule_work(&adap->flower_stats_work);
}

int cxgb4_tc_flower_stats(struct net_device *dev,
			  struct tc_cls_flower_offload *cls)
{
	struct adapter *adap = netdev2adap(dev);
	struct ch_tc_flower_stats *ofld_stats;
	struct ch_tc_flower_entry *ch_flower;
	u64 packets;
	u64 bytes;
	int ret;

	ch_flower = ch_flower_lookup(adap, cls->cookie);
	if (!ch_flower) {
		ret = -ENOENT;
		goto err;
	}

	ret = cxgb4_get_filter_counters(dev, ch_flower->filter_id,
					&packets, &bytes,
					ch_flower->fs.hash);
	if (ret < 0)
		goto err;

	spin_lock_bh(&ch_flower->lock);
	ofld_stats = &ch_flower->stats;
	if (ofld_stats->packet_count != packets) {
		if (ofld_stats->prev_packet_count != packets)
			ofld_stats->last_used = jiffies;
		tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count,
				      packets - ofld_stats->packet_count,
				      ofld_stats->last_used);

		ofld_stats->packet_count = packets;
		ofld_stats->byte_count = bytes;
		ofld_stats->prev_packet_count = packets;
	}
	spin_unlock_bh(&ch_flower->lock);
	return 0;

err:
	return ret;
}

static const struct rhashtable_params cxgb4_tc_flower_ht_params = {
	.nelem_hint = 384,
	.head_offset = offsetof(struct ch_tc_flower_entry, node),
	.key_offset = offsetof(struct ch_tc_flower_entry, tc_flower_cookie),
	.key_len = sizeof(((struct ch_tc_flower_entry *)0)->tc_flower_cookie),
	.max_size = 524288,
	.min_size = 512,
	.automatic_shrinking = true
};

int cxgb4_init_tc_flower(struct adapter *adap)
{
	int ret;

	if (adap->tc_flower_initialized)
		return -EEXIST;

	adap->flower_ht_params = cxgb4_tc_flower_ht_params;
	ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params);
	if (ret)
		return ret;

	INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler);
	timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0);
	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
	adap->tc_flower_initialized = true;
	return 0;
}

void cxgb4_cleanup_tc_flower(struct adapter *adap)
{
	if (!adap->tc_flower_initialized)
		return;

	if (adap->flower_stats_timer.function)
		del_timer_sync(&adap->flower_stats_timer);
	cancel_work_sync(&adap->flower_stats_work);
	rhashtable_destroy(&adap->flower_tbl);
	adap->tc_flower_initialized = false;
}