summaryrefslogtreecommitdiffstats
path: root/src/spdk/dpdk/drivers/net/cxgbe/cxgbe_flow.c
blob: 01c945f1b14966a0c8b31c1a4cae7825b96f2877 (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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2018 Chelsio Communications.
 * All rights reserved.
 */
#include "common.h"
#include "cxgbe_flow.h"

#define __CXGBE_FILL_FS(__v, __m, fs, elem, e) \
do { \
	if (!((fs)->val.elem || (fs)->mask.elem)) { \
		(fs)->val.elem = (__v); \
		(fs)->mask.elem = (__m); \
	} else { \
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM, \
					  NULL, "a filter can be specified" \
					  " only once"); \
	} \
} while (0)

#define __CXGBE_FILL_FS_MEMCPY(__v, __m, fs, elem) \
do { \
	memcpy(&(fs)->val.elem, &(__v), sizeof(__v)); \
	memcpy(&(fs)->mask.elem, &(__m), sizeof(__m)); \
} while (0)

#define CXGBE_FILL_FS(v, m, elem) \
	__CXGBE_FILL_FS(v, m, fs, elem, e)

#define CXGBE_FILL_FS_MEMCPY(v, m, elem) \
	__CXGBE_FILL_FS_MEMCPY(v, m, fs, elem)

static int
cxgbe_validate_item(const struct rte_flow_item *i, struct rte_flow_error *e)
{
	/* rte_flow specification does not allow it. */
	if (!i->spec && (i->mask ||  i->last))
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM,
				   i, "last or mask given without spec");
	/*
	 * We don't support it.
	 * Although, we can support values in last as 0's or last == spec.
	 * But this will not provide user with any additional functionality
	 * and will only increase the complexity for us.
	 */
	if (i->last)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
				   i, "last is not supported by chelsio pmd");
	return 0;
}

static void
cxgbe_fill_filter_region(struct adapter *adap,
			 struct ch_filter_specification *fs)
{
	struct tp_params *tp = &adap->params.tp;
	u64 hash_filter_mask = tp->hash_filter_mask;
	u64 ntuple_mask = 0;

	fs->cap = 0;

	if (!is_hashfilter(adap))
		return;

	if (fs->type) {
		uint8_t biton[16] = {0xff, 0xff, 0xff, 0xff,
				     0xff, 0xff, 0xff, 0xff,
				     0xff, 0xff, 0xff, 0xff,
				     0xff, 0xff, 0xff, 0xff};
		uint8_t bitoff[16] = {0};

		if (!memcmp(fs->val.lip, bitoff, sizeof(bitoff)) ||
		    !memcmp(fs->val.fip, bitoff, sizeof(bitoff)) ||
		    memcmp(fs->mask.lip, biton, sizeof(biton)) ||
		    memcmp(fs->mask.fip, biton, sizeof(biton)))
			return;
	} else {
		uint32_t biton  = 0xffffffff;
		uint32_t bitoff = 0x0U;

		if (!memcmp(fs->val.lip, &bitoff, sizeof(bitoff)) ||
		    !memcmp(fs->val.fip, &bitoff, sizeof(bitoff)) ||
		    memcmp(fs->mask.lip, &biton, sizeof(biton)) ||
		    memcmp(fs->mask.fip, &biton, sizeof(biton)))
			return;
	}

	if (!fs->val.lport || fs->mask.lport != 0xffff)
		return;
	if (!fs->val.fport || fs->mask.fport != 0xffff)
		return;

	if (tp->protocol_shift >= 0)
		ntuple_mask |= (u64)fs->mask.proto << tp->protocol_shift;
	if (tp->ethertype_shift >= 0)
		ntuple_mask |= (u64)fs->mask.ethtype << tp->ethertype_shift;
	if (tp->port_shift >= 0)
		ntuple_mask |= (u64)fs->mask.iport << tp->port_shift;

	if (ntuple_mask != hash_filter_mask)
		return;

	fs->cap = 1;	/* use hash region */
}

static int
ch_rte_parsetype_port(const void *dmask, const struct rte_flow_item *item,
		      struct ch_filter_specification *fs,
		      struct rte_flow_error *e)
{
	const struct rte_flow_item_phy_port *val = item->spec;
	const struct rte_flow_item_phy_port *umask = item->mask;
	const struct rte_flow_item_phy_port *mask;

	mask = umask ? umask : (const struct rte_flow_item_phy_port *)dmask;

	if (val->index > 0x7)
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM,
					  item,
					  "port index upto 0x7 is supported");

	CXGBE_FILL_FS(val->index, mask->index, iport);

	return 0;
}

static int
ch_rte_parsetype_udp(const void *dmask, const struct rte_flow_item *item,
		     struct ch_filter_specification *fs,
		     struct rte_flow_error *e)
{
	const struct rte_flow_item_udp *val = item->spec;
	const struct rte_flow_item_udp *umask = item->mask;
	const struct rte_flow_item_udp *mask;

	mask = umask ? umask : (const struct rte_flow_item_udp *)dmask;

	if (mask->hdr.dgram_len || mask->hdr.dgram_cksum)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
					  item,
					  "udp: only src/dst port supported");

	CXGBE_FILL_FS(IPPROTO_UDP, 0xff, proto);
	if (!val)
		return 0;
	CXGBE_FILL_FS(be16_to_cpu(val->hdr.src_port),
		      be16_to_cpu(mask->hdr.src_port), fport);
	CXGBE_FILL_FS(be16_to_cpu(val->hdr.dst_port),
		      be16_to_cpu(mask->hdr.dst_port), lport);
	return 0;
}

static int
ch_rte_parsetype_tcp(const void *dmask, const struct rte_flow_item *item,
		     struct ch_filter_specification *fs,
		     struct rte_flow_error *e)
{
	const struct rte_flow_item_tcp *val = item->spec;
	const struct rte_flow_item_tcp *umask = item->mask;
	const struct rte_flow_item_tcp *mask;

	mask = umask ? umask : (const struct rte_flow_item_tcp *)dmask;

	if (mask->hdr.sent_seq || mask->hdr.recv_ack || mask->hdr.data_off ||
	    mask->hdr.tcp_flags || mask->hdr.rx_win || mask->hdr.cksum ||
	    mask->hdr.tcp_urp)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
					  item,
					  "tcp: only src/dst port supported");

	CXGBE_FILL_FS(IPPROTO_TCP, 0xff, proto);
	if (!val)
		return 0;
	CXGBE_FILL_FS(be16_to_cpu(val->hdr.src_port),
		      be16_to_cpu(mask->hdr.src_port), fport);
	CXGBE_FILL_FS(be16_to_cpu(val->hdr.dst_port),
		      be16_to_cpu(mask->hdr.dst_port), lport);
	return 0;
}

static int
ch_rte_parsetype_ipv4(const void *dmask, const struct rte_flow_item *item,
		      struct ch_filter_specification *fs,
		      struct rte_flow_error *e)
{
	const struct rte_flow_item_ipv4 *val = item->spec;
	const struct rte_flow_item_ipv4 *umask = item->mask;
	const struct rte_flow_item_ipv4 *mask;

	mask = umask ? umask : (const struct rte_flow_item_ipv4 *)dmask;

	if (mask->hdr.time_to_live || mask->hdr.type_of_service)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
					  item, "ttl/tos are not supported");

	fs->type = FILTER_TYPE_IPV4;
	CXGBE_FILL_FS(ETHER_TYPE_IPv4, 0xffff, ethtype);
	if (!val)
		return 0; /* ipv4 wild card */

	CXGBE_FILL_FS(val->hdr.next_proto_id, mask->hdr.next_proto_id, proto);
	CXGBE_FILL_FS_MEMCPY(val->hdr.dst_addr, mask->hdr.dst_addr, lip);
	CXGBE_FILL_FS_MEMCPY(val->hdr.src_addr, mask->hdr.src_addr, fip);

	return 0;
}

static int
ch_rte_parsetype_ipv6(const void *dmask, const struct rte_flow_item *item,
		      struct ch_filter_specification *fs,
		      struct rte_flow_error *e)
{
	const struct rte_flow_item_ipv6 *val = item->spec;
	const struct rte_flow_item_ipv6 *umask = item->mask;
	const struct rte_flow_item_ipv6 *mask;

	mask = umask ? umask : (const struct rte_flow_item_ipv6 *)dmask;

	if (mask->hdr.vtc_flow ||
	    mask->hdr.payload_len || mask->hdr.hop_limits)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ITEM,
					  item,
					  "tc/flow/hop are not supported");

	fs->type = FILTER_TYPE_IPV6;
	CXGBE_FILL_FS(ETHER_TYPE_IPv6, 0xffff, ethtype);
	if (!val)
		return 0; /* ipv6 wild card */

	CXGBE_FILL_FS(val->hdr.proto, mask->hdr.proto, proto);
	CXGBE_FILL_FS_MEMCPY(val->hdr.dst_addr, mask->hdr.dst_addr, lip);
	CXGBE_FILL_FS_MEMCPY(val->hdr.src_addr, mask->hdr.src_addr, fip);

	return 0;
}

static int
cxgbe_rtef_parse_attr(struct rte_flow *flow, const struct rte_flow_attr *attr,
		      struct rte_flow_error *e)
{
	if (attr->egress)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR,
					  attr, "attribute:<egress> is"
					  " not supported !");
	if (attr->group > 0)
		return rte_flow_error_set(e, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR,
					  attr, "group parameter is"
					  " not supported.");

	flow->fidx = attr->priority ? attr->priority - 1 : FILTER_ID_MAX;

	return 0;
}

static inline int check_rxq(struct rte_eth_dev *dev, uint16_t rxq)
{
	struct port_info *pi = ethdev2pinfo(dev);

	if (rxq > pi->n_rx_qsets)
		return -EINVAL;
	return 0;
}

static int cxgbe_validate_fidxondel(struct filter_entry *f, unsigned int fidx)
{
	struct adapter *adap = ethdev2adap(f->dev);
	struct ch_filter_specification fs = f->fs;

	if (fidx >= adap->tids.nftids) {
		dev_err(adap, "invalid flow index %d.\n", fidx);
		return -EINVAL;
	}
	if (!is_filter_set(&adap->tids, fidx, fs.type)) {
		dev_err(adap, "Already free fidx:%d f:%p\n", fidx, f);
		return -EINVAL;
	}

	return 0;
}

static int
cxgbe_validate_fidxonadd(struct ch_filter_specification *fs,
			 struct adapter *adap, unsigned int fidx)
{
	if (is_filter_set(&adap->tids, fidx, fs->type)) {
		dev_err(adap, "filter index: %d is busy.\n", fidx);
		return -EBUSY;
	}
	if (fidx >= adap->tids.nftids) {
		dev_err(adap, "filter index (%u) >= max(%u)\n",
			fidx, adap->tids.nftids);
		return -ERANGE;
	}

	return 0;
}

static int
cxgbe_verify_fidx(struct rte_flow *flow, unsigned int fidx, uint8_t del)
{
	if (flow->fs.cap)
		return 0; /* Hash filters */
	return del ? cxgbe_validate_fidxondel(flow->f, fidx) :
		cxgbe_validate_fidxonadd(&flow->fs,
					 ethdev2adap(flow->dev), fidx);
}

static int cxgbe_get_fidx(struct rte_flow *flow, unsigned int *fidx)
{
	struct ch_filter_specification *fs = &flow->fs;
	struct adapter *adap = ethdev2adap(flow->dev);

	/* For tcam get the next available slot, if default value specified */
	if (flow->fidx == FILTER_ID_MAX) {
		int idx;

		idx = cxgbe_alloc_ftid(adap, fs->type);
		if (idx < 0) {
			dev_err(adap, "unable to get a filter index in tcam\n");
			return -ENOMEM;
		}
		*fidx = (unsigned int)idx;
	} else {
		*fidx = flow->fidx;
	}

	return 0;
}

static int
ch_rte_parse_atype_switch(const struct rte_flow_action *a,
			  struct ch_filter_specification *fs,
			  struct rte_flow_error *e)
{
	const struct rte_flow_action_phy_port *port;

	switch (a->type) {
	case RTE_FLOW_ACTION_TYPE_PHY_PORT:
		port = (const struct rte_flow_action_phy_port *)a->conf;
		fs->eport = port->index;
		break;
	default:
		/* We are not supposed to come here */
		return rte_flow_error_set(e, EINVAL,
					  RTE_FLOW_ERROR_TYPE_ACTION, a,
					  "Action not supported");
	}

	return 0;
}

static int
cxgbe_rtef_parse_actions(struct rte_flow *flow,
			 const struct rte_flow_action action[],
			 struct rte_flow_error *e)
{
	struct ch_filter_specification *fs = &flow->fs;
	const struct rte_flow_action_queue *q;
	const struct rte_flow_action *a;
	char abit = 0;
	int ret;

	for (a = action; a->type != RTE_FLOW_ACTION_TYPE_END; a++) {
		switch (a->type) {
		case RTE_FLOW_ACTION_TYPE_VOID:
			continue;
		case RTE_FLOW_ACTION_TYPE_DROP:
			if (abit++)
				return rte_flow_error_set(e, EINVAL,
						RTE_FLOW_ERROR_TYPE_ACTION, a,
						"specify only 1 pass/drop");
			fs->action = FILTER_DROP;
			break;
		case RTE_FLOW_ACTION_TYPE_QUEUE:
			q = (const struct rte_flow_action_queue *)a->conf;
			if (!q)
				return rte_flow_error_set(e, EINVAL,
						RTE_FLOW_ERROR_TYPE_ACTION, q,
						"specify rx queue index");
			if (check_rxq(flow->dev, q->index))
				return rte_flow_error_set(e, EINVAL,
						RTE_FLOW_ERROR_TYPE_ACTION, q,
						"Invalid rx queue");
			if (abit++)
				return rte_flow_error_set(e, EINVAL,
						RTE_FLOW_ERROR_TYPE_ACTION, a,
						"specify only 1 pass/drop");
			fs->action = FILTER_PASS;
			fs->dirsteer = 1;
			fs->iq = q->index;
			break;
		case RTE_FLOW_ACTION_TYPE_COUNT:
			fs->hitcnts = 1;
			break;
		case RTE_FLOW_ACTION_TYPE_PHY_PORT:
			/* We allow multiple switch actions, but switch is
			 * not compatible with either queue or drop
			 */
			if (abit++ && fs->action != FILTER_SWITCH)
				return rte_flow_error_set(e, EINVAL,
						RTE_FLOW_ERROR_TYPE_ACTION, a,
						"overlapping action specified");
			ret = ch_rte_parse_atype_switch(a, fs, e);
			if (ret)
				return ret;
			fs->action = FILTER_SWITCH;
			break;
		default:
			/* Not supported action : return error */
			return rte_flow_error_set(e, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ACTION,
						  a, "Action not supported");
		}
	}

	return 0;
}

struct chrte_fparse parseitem[] = {
		[RTE_FLOW_ITEM_TYPE_PHY_PORT] = {
		.fptr = ch_rte_parsetype_port,
		.dmask = &(const struct rte_flow_item_phy_port){
			.index = 0x7,
		}
	},

	[RTE_FLOW_ITEM_TYPE_IPV4] = {
		.fptr  = ch_rte_parsetype_ipv4,
		.dmask = &rte_flow_item_ipv4_mask,
	},

	[RTE_FLOW_ITEM_TYPE_IPV6] = {
		.fptr  = ch_rte_parsetype_ipv6,
		.dmask = &rte_flow_item_ipv6_mask,
	},

	[RTE_FLOW_ITEM_TYPE_UDP] = {
		.fptr  = ch_rte_parsetype_udp,
		.dmask = &rte_flow_item_udp_mask,
	},

	[RTE_FLOW_ITEM_TYPE_TCP] = {
		.fptr  = ch_rte_parsetype_tcp,
		.dmask = &rte_flow_item_tcp_mask,
	},
};

static int
cxgbe_rtef_parse_items(struct rte_flow *flow,
		       const struct rte_flow_item items[],
		       struct rte_flow_error *e)
{
	struct adapter *adap = ethdev2adap(flow->dev);
	const struct rte_flow_item *i;
	char repeat[ARRAY_SIZE(parseitem)] = {0};

	for (i = items; i->type != RTE_FLOW_ITEM_TYPE_END; i++) {
		struct chrte_fparse *idx = &flow->item_parser[i->type];
		int ret;

		if (i->type > ARRAY_SIZE(parseitem))
			return rte_flow_error_set(e, ENOTSUP,
						  RTE_FLOW_ERROR_TYPE_ITEM,
						  i, "Item not supported");

		switch (i->type) {
		case RTE_FLOW_ITEM_TYPE_VOID:
			continue;
		default:
			/* check if item is repeated */
			if (repeat[i->type])
				return rte_flow_error_set(e, ENOTSUP,
						RTE_FLOW_ERROR_TYPE_ITEM, i,
						"parse items cannot be repeated (except void)");
			repeat[i->type] = 1;

			/* validate the item */
			ret = cxgbe_validate_item(i, e);
			if (ret)
				return ret;

			if (!idx || !idx->fptr) {
				return rte_flow_error_set(e, ENOTSUP,
						RTE_FLOW_ERROR_TYPE_ITEM, i,
						"Item not supported");
			} else {
				ret = idx->fptr(idx->dmask, i, &flow->fs, e);
				if (ret)
					return ret;
			}
		}
	}

	cxgbe_fill_filter_region(adap, &flow->fs);

	return 0;
}

static int
cxgbe_flow_parse(struct rte_flow *flow,
		 const struct rte_flow_attr *attr,
		 const struct rte_flow_item item[],
		 const struct rte_flow_action action[],
		 struct rte_flow_error *e)
{
	int ret;

	/* parse user request into ch_filter_specification */
	ret = cxgbe_rtef_parse_attr(flow, attr, e);
	if (ret)
		return ret;
	ret = cxgbe_rtef_parse_items(flow, item, e);
	if (ret)
		return ret;
	return cxgbe_rtef_parse_actions(flow, action, e);
}

static int __cxgbe_flow_create(struct rte_eth_dev *dev, struct rte_flow *flow)
{
	struct ch_filter_specification *fs = &flow->fs;
	struct adapter *adap = ethdev2adap(dev);
	struct tid_info *t = &adap->tids;
	struct filter_ctx ctx;
	unsigned int fidx;
	int err;

	if (cxgbe_get_fidx(flow, &fidx))
		return -ENOMEM;
	if (cxgbe_verify_fidx(flow, fidx, 0))
		return -1;

	t4_init_completion(&ctx.completion);
	/* go create the filter */
	err = cxgbe_set_filter(dev, fidx, fs, &ctx);
	if (err) {
		dev_err(adap, "Error %d while creating filter.\n", err);
		return err;
	}

	/* Poll the FW for reply */
	err = cxgbe_poll_for_completion(&adap->sge.fw_evtq,
					CXGBE_FLOW_POLL_US,
					CXGBE_FLOW_POLL_CNT,
					&ctx.completion);
	if (err) {
		dev_err(adap, "Filter set operation timed out (%d)\n", err);
		return err;
	}
	if (ctx.result) {
		dev_err(adap, "Hardware error %d while creating the filter.\n",
			ctx.result);
		return ctx.result;
	}

	if (fs->cap) { /* to destroy the filter */
		flow->fidx = ctx.tid;
		flow->f = lookup_tid(t, ctx.tid);
	} else {
		flow->fidx = fidx;
		flow->f = &adap->tids.ftid_tab[fidx];
	}

	return 0;
}

static struct rte_flow *
cxgbe_flow_create(struct rte_eth_dev *dev,
		  const struct rte_flow_attr *attr,
		  const struct rte_flow_item item[],
		  const struct rte_flow_action action[],
		  struct rte_flow_error *e)
{
	struct rte_flow *flow;
	int ret;

	flow = t4_os_alloc(sizeof(struct rte_flow));
	if (!flow) {
		rte_flow_error_set(e, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
				   NULL, "Unable to allocate memory for"
				   " filter_entry");
		return NULL;
	}

	flow->item_parser = parseitem;
	flow->dev = dev;

	if (cxgbe_flow_parse(flow, attr, item, action, e)) {
		t4_os_free(flow);
		return NULL;
	}

	/* go, interact with cxgbe_filter */
	ret = __cxgbe_flow_create(dev, flow);
	if (ret) {
		rte_flow_error_set(e, ret, RTE_FLOW_ERROR_TYPE_HANDLE,
				   NULL, "Unable to create flow rule");
		t4_os_free(flow);
		return NULL;
	}

	flow->f->private = flow; /* Will be used during flush */

	return flow;
}

static int __cxgbe_flow_destroy(struct rte_eth_dev *dev, struct rte_flow *flow)
{
	struct adapter *adap = ethdev2adap(dev);
	struct filter_entry *f = flow->f;
	struct ch_filter_specification *fs;
	struct filter_ctx ctx;
	int err;

	fs = &f->fs;
	if (cxgbe_verify_fidx(flow, flow->fidx, 1))
		return -1;

	t4_init_completion(&ctx.completion);
	err = cxgbe_del_filter(dev, flow->fidx, fs, &ctx);
	if (err) {
		dev_err(adap, "Error %d while deleting filter.\n", err);
		return err;
	}

	/* Poll the FW for reply */
	err = cxgbe_poll_for_completion(&adap->sge.fw_evtq,
					CXGBE_FLOW_POLL_US,
					CXGBE_FLOW_POLL_CNT,
					&ctx.completion);
	if (err) {
		dev_err(adap, "Filter delete operation timed out (%d)\n", err);
		return err;
	}
	if (ctx.result) {
		dev_err(adap, "Hardware error %d while deleting the filter.\n",
			ctx.result);
		return ctx.result;
	}

	return 0;
}

static int
cxgbe_flow_destroy(struct rte_eth_dev *dev, struct rte_flow *flow,
		   struct rte_flow_error *e)
{
	int ret;

	ret = __cxgbe_flow_destroy(dev, flow);
	if (ret)
		return rte_flow_error_set(e, ret, RTE_FLOW_ERROR_TYPE_HANDLE,
					  flow, "error destroying filter.");
	t4_os_free(flow);
	return 0;
}

static int __cxgbe_flow_query(struct rte_flow *flow, u64 *count,
			      u64 *byte_count)
{
	struct adapter *adap = ethdev2adap(flow->dev);
	struct ch_filter_specification fs = flow->f->fs;
	unsigned int fidx = flow->fidx;
	int ret = 0;

	ret = cxgbe_get_filter_count(adap, fidx, count, fs.cap, 0);
	if (ret)
		return ret;
	return cxgbe_get_filter_count(adap, fidx, byte_count, fs.cap, 1);
}

static int
cxgbe_flow_query(struct rte_eth_dev *dev, struct rte_flow *flow,
		 const struct rte_flow_action *action, void *data,
		 struct rte_flow_error *e)
{
	struct ch_filter_specification fs;
	struct rte_flow_query_count *c;
	struct filter_entry *f;
	int ret;

	RTE_SET_USED(dev);

	f = flow->f;
	fs = f->fs;

	if (action->type != RTE_FLOW_ACTION_TYPE_COUNT)
		return rte_flow_error_set(e, ENOTSUP,
					  RTE_FLOW_ERROR_TYPE_ACTION, NULL,
					  "only count supported for query");

	/*
	 * This is a valid operation, Since we are allowed to do chelsio
	 * specific operations in rte side of our code but not vise-versa
	 *
	 * So, fs can be queried/modified here BUT rte_flow_query_count
	 * cannot be worked on by the lower layer since we want to maintain
	 * it as rte_flow agnostic.
	 */
	if (!fs.hitcnts)
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ACTION,
					  &fs, "filter hit counters were not"
					  " enabled during filter creation");

	c = (struct rte_flow_query_count *)data;
	ret = __cxgbe_flow_query(flow, &c->hits, &c->bytes);
	if (ret)
		return rte_flow_error_set(e, -ret, RTE_FLOW_ERROR_TYPE_ACTION,
					  f, "cxgbe pmd failed to"
					  " perform query");

	/* Query was successful */
	c->bytes_set = 1;
	c->hits_set = 1;

	return 0; /* success / partial_success */
}

static int
cxgbe_flow_validate(struct rte_eth_dev *dev,
		    const struct rte_flow_attr *attr,
		    const struct rte_flow_item item[],
		    const struct rte_flow_action action[],
		    struct rte_flow_error *e)
{
	struct adapter *adap = ethdev2adap(dev);
	struct rte_flow *flow;
	unsigned int fidx;
	int ret;

	flow = t4_os_alloc(sizeof(struct rte_flow));
	if (!flow)
		return rte_flow_error_set(e, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
				NULL,
				"Unable to allocate memory for filter_entry");

	flow->item_parser = parseitem;
	flow->dev = dev;

	ret = cxgbe_flow_parse(flow, attr, item, action, e);
	if (ret) {
		t4_os_free(flow);
		return ret;
	}

	if (validate_filter(adap, &flow->fs)) {
		t4_os_free(flow);
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_HANDLE,
				NULL,
				"validation failed. Check f/w config file.");
	}

	if (cxgbe_get_fidx(flow, &fidx)) {
		t4_os_free(flow);
		return rte_flow_error_set(e, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
					  NULL, "no memory in tcam.");
	}

	if (cxgbe_verify_fidx(flow, fidx, 0)) {
		t4_os_free(flow);
		return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_HANDLE,
					  NULL, "validation failed");
	}

	t4_os_free(flow);
	return 0;
}

/*
 * @ret : > 0 filter destroyed succsesfully
 *        < 0 error destroying filter
 *        == 1 filter not active / not found
 */
static int
cxgbe_check_n_destroy(struct filter_entry *f, struct rte_eth_dev *dev,
		      struct rte_flow_error *e)
{
	if (f && (f->valid || f->pending) &&
	    f->dev == dev && /* Only if user has asked for this port */
	     f->private) /* We (rte_flow) created this filter */
		return cxgbe_flow_destroy(dev, (struct rte_flow *)f->private,
					  e);
	return 1;
}

static int cxgbe_flow_flush(struct rte_eth_dev *dev, struct rte_flow_error *e)
{
	struct adapter *adap = ethdev2adap(dev);
	unsigned int i;
	int ret = 0;

	if (adap->tids.ftid_tab) {
		struct filter_entry *f = &adap->tids.ftid_tab[0];

		for (i = 0; i < adap->tids.nftids; i++, f++) {
			ret = cxgbe_check_n_destroy(f, dev, e);
			if (ret < 0)
				goto out;
		}
	}

	if (is_hashfilter(adap) && adap->tids.tid_tab) {
		struct filter_entry *f;

		for (i = adap->tids.hash_base; i <= adap->tids.ntids; i++) {
			f = (struct filter_entry *)adap->tids.tid_tab[i];

			ret = cxgbe_check_n_destroy(f, dev, e);
			if (ret < 0)
				goto out;
		}
	}

out:
	return ret >= 0 ? 0 : ret;
}

static const struct rte_flow_ops cxgbe_flow_ops = {
	.validate	= cxgbe_flow_validate,
	.create		= cxgbe_flow_create,
	.destroy	= cxgbe_flow_destroy,
	.flush		= cxgbe_flow_flush,
	.query		= cxgbe_flow_query,
	.isolate	= NULL,
};

int
cxgbe_dev_filter_ctrl(struct rte_eth_dev *dev,
		      enum rte_filter_type filter_type,
		      enum rte_filter_op filter_op,
		      void *arg)
{
	int ret = 0;

	RTE_SET_USED(dev);
	switch (filter_type) {
	case RTE_ETH_FILTER_GENERIC:
		if (filter_op != RTE_ETH_FILTER_GET)
			return -EINVAL;
		*(const void **)arg = &cxgbe_flow_ops;
		break;
	default:
		ret = -ENOTSUP;
		break;
	}
	return ret;
}