aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ena/ena_ethdev.c
blob: e157587b1d9df71437ab7a6734651de830de25b2 (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
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
/*-
* BSD LICENSE
*
* Copyright (c) 2015-2016 Amazon.com, Inc. or its affiliates.
* All rights reserved.
*
* 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.
* * Neither the name of copyright holder nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/

#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_tcp.h>
#include <rte_atomic.h>
#include <rte_dev.h>
#include <rte_errno.h>

#include "ena_ethdev.h"
#include "ena_logs.h"
#include "ena_platform.h"
#include "ena_com.h"
#include "ena_eth_com.h"

#include <ena_common_defs.h>
#include <ena_regs_defs.h>
#include <ena_admin_defs.h>
#include <ena_eth_io_defs.h>

#define ENA_IO_TXQ_IDX(q)	(2 * (q))
#define ENA_IO_RXQ_IDX(q)	(2 * (q) + 1)
/*reverse version of ENA_IO_RXQ_IDX*/
#define ENA_IO_RXQ_IDX_REV(q)	((q - 1) / 2)

/* While processing submitted and completed descriptors (rx and tx path
 * respectively) in a loop it is desired to:
 *  - perform batch submissions while populating sumbissmion queue
 *  - avoid blocking transmission of other packets during cleanup phase
 * Hence the utilization ratio of 1/8 of a queue size.
 */
#define ENA_RING_DESCS_RATIO(ring_size)	(ring_size / 8)

#define __MERGE_64B_H_L(h, l) (((uint64_t)h << 32) | l)
#define TEST_BIT(val, bit_shift) (val & (1UL << bit_shift))

#define GET_L4_HDR_LEN(mbuf)					\
	((rte_pktmbuf_mtod_offset(mbuf,	struct tcp_hdr *,	\
		mbuf->l3_len + mbuf->l2_len)->data_off) >> 4)

#define ENA_RX_RSS_TABLE_LOG_SIZE  7
#define ENA_RX_RSS_TABLE_SIZE	(1 << ENA_RX_RSS_TABLE_LOG_SIZE)
#define ENA_HASH_KEY_SIZE	40

/** Vendor ID used by Amazon devices */
#define PCI_VENDOR_ID_AMAZON 0x1D0F
/** Amazon devices */
#define PCI_DEVICE_ID_ENA_VF	0xEC20
#define PCI_DEVICE_ID_ENA_LLQ_VF	0xEC21

static struct rte_pci_id pci_id_ena_map[] = {
#define RTE_PCI_DEV_ID_DECL_ENA(vend, dev) {RTE_PCI_DEVICE(vend, dev)},

	RTE_PCI_DEV_ID_DECL_ENA(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_ENA_VF)
	RTE_PCI_DEV_ID_DECL_ENA(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_ENA_LLQ_VF)
	{.device_id = 0},
};

static int ena_device_init(struct ena_com_dev *ena_dev,
			   struct ena_com_dev_get_features_ctx *get_feat_ctx);
static int ena_dev_configure(struct rte_eth_dev *dev);
static uint16_t eth_ena_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
				  uint16_t nb_pkts);
static int ena_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
			      uint16_t nb_desc, unsigned int socket_id,
			      const struct rte_eth_txconf *tx_conf);
static int ena_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
			      uint16_t nb_desc, unsigned int socket_id,
			      const struct rte_eth_rxconf *rx_conf,
			      struct rte_mempool *mp);
static uint16_t eth_ena_recv_pkts(void *rx_queue,
				  struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
static int ena_populate_rx_queue(struct ena_ring *rxq, unsigned int count);
static void ena_init_rings(struct ena_adapter *adapter);
static int ena_mtu_set(struct rte_eth_dev *dev, uint16_t mtu);
static int ena_start(struct rte_eth_dev *dev);
static void ena_close(struct rte_eth_dev *dev);
static void ena_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats);
static void ena_rx_queue_release_all(struct rte_eth_dev *dev);
static void ena_tx_queue_release_all(struct rte_eth_dev *dev);
static void ena_rx_queue_release(void *queue);
static void ena_tx_queue_release(void *queue);
static void ena_rx_queue_release_bufs(struct ena_ring *ring);
static void ena_tx_queue_release_bufs(struct ena_ring *ring);
static int ena_link_update(struct rte_eth_dev *dev,
			   __rte_unused int wait_to_complete);
static int ena_queue_restart(struct ena_ring *ring);
static int ena_queue_restart_all(struct rte_eth_dev *dev,
				 enum ena_ring_type ring_type);
static void ena_stats_restart(struct rte_eth_dev *dev);
static void ena_infos_get(__rte_unused struct rte_eth_dev *dev,
			  struct rte_eth_dev_info *dev_info);
static int ena_rss_reta_update(struct rte_eth_dev *dev,
			       struct rte_eth_rss_reta_entry64 *reta_conf,
			       uint16_t reta_size);
static int ena_rss_reta_query(struct rte_eth_dev *dev,
			      struct rte_eth_rss_reta_entry64 *reta_conf,
			      uint16_t reta_size);

static struct eth_dev_ops ena_dev_ops = {
	.dev_configure        = ena_dev_configure,
	.dev_infos_get        = ena_infos_get,
	.rx_queue_setup       = ena_rx_queue_setup,
	.tx_queue_setup       = ena_tx_queue_setup,
	.dev_start            = ena_start,
	.link_update          = ena_link_update,
	.stats_get            = ena_stats_get,
	.mtu_set              = ena_mtu_set,
	.rx_queue_release     = ena_rx_queue_release,
	.tx_queue_release     = ena_tx_queue_release,
	.dev_close            = ena_close,
	.reta_update          = ena_rss_reta_update,
	.reta_query           = ena_rss_reta_query,
};

static inline void ena_rx_mbuf_prepare(struct rte_mbuf *mbuf,
				       struct ena_com_rx_ctx *ena_rx_ctx)
{
	uint64_t ol_flags = 0;

	if (ena_rx_ctx->l4_proto == ENA_ETH_IO_L4_PROTO_TCP)
		ol_flags |= PKT_TX_TCP_CKSUM;
	else if (ena_rx_ctx->l4_proto == ENA_ETH_IO_L4_PROTO_UDP)
		ol_flags |= PKT_TX_UDP_CKSUM;

	if (ena_rx_ctx->l3_proto == ENA_ETH_IO_L3_PROTO_IPV4)
		ol_flags |= PKT_TX_IPV4;
	else if (ena_rx_ctx->l3_proto == ENA_ETH_IO_L3_PROTO_IPV6)
		ol_flags |= PKT_TX_IPV6;

	if (unlikely(ena_rx_ctx->l4_csum_err))
		ol_flags |= PKT_RX_L4_CKSUM_BAD;
	if (unlikely(ena_rx_ctx->l3_csum_err))
		ol_flags |= PKT_RX_IP_CKSUM_BAD;

	mbuf->ol_flags = ol_flags;
}

static inline void ena_tx_mbuf_prepare(struct rte_mbuf *mbuf,
				       struct ena_com_tx_ctx *ena_tx_ctx)
{
	struct ena_com_tx_meta *ena_meta = &ena_tx_ctx->ena_meta;

	if (mbuf->ol_flags &
	    (PKT_TX_L4_MASK | PKT_TX_IP_CKSUM | PKT_TX_TCP_SEG)) {
		/* check if TSO is required */
		if (mbuf->ol_flags & PKT_TX_TCP_SEG) {
			ena_tx_ctx->tso_enable = true;

			ena_meta->l4_hdr_len = GET_L4_HDR_LEN(mbuf);
		}

		/* check if L3 checksum is needed */
		if (mbuf->ol_flags & PKT_TX_IP_CKSUM)
			ena_tx_ctx->l3_csum_enable = true;

		if (mbuf->ol_flags & PKT_TX_IPV6) {
			ena_tx_ctx->l3_proto = ENA_ETH_IO_L3_PROTO_IPV6;
		} else {
			ena_tx_ctx->l3_proto = ENA_ETH_IO_L3_PROTO_IPV4;

			/* set don't fragment (DF) flag */
			if (mbuf->packet_type &
				(RTE_PTYPE_L4_NONFRAG
				 | RTE_PTYPE_INNER_L4_NONFRAG))
				ena_tx_ctx->df = true;
		}

		/* check if L4 checksum is needed */
		switch (mbuf->ol_flags & PKT_TX_L4_MASK) {
		case PKT_TX_TCP_CKSUM:
			ena_tx_ctx->l4_proto = ENA_ETH_IO_L4_PROTO_TCP;
			ena_tx_ctx->l4_csum_enable = true;
			break;
		case PKT_TX_UDP_CKSUM:
			ena_tx_ctx->l4_proto = ENA_ETH_IO_L4_PROTO_UDP;
			ena_tx_ctx->l4_csum_enable = true;
			break;
		default:
			ena_tx_ctx->l4_proto = ENA_ETH_IO_L4_PROTO_UNKNOWN;
			ena_tx_ctx->l4_csum_enable = false;
			break;
		}

		ena_meta->mss = mbuf->tso_segsz;
		ena_meta->l3_hdr_len = mbuf->l3_len;
		ena_meta->l3_hdr_offset = mbuf->l2_len;
		/* this param needed only for TSO */
		ena_meta->l3_outer_hdr_len = 0;
		ena_meta->l3_outer_hdr_offset = 0;

		ena_tx_ctx->meta_valid = true;
	} else {
		ena_tx_ctx->meta_valid = false;
	}
}

static void ena_close(struct rte_eth_dev *dev)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);

	adapter->state = ENA_ADAPTER_STATE_STOPPED;

	ena_rx_queue_release_all(dev);
	ena_tx_queue_release_all(dev);
}

static int ena_rss_reta_update(struct rte_eth_dev *dev,
			       struct rte_eth_rss_reta_entry64 *reta_conf,
			       uint16_t reta_size)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	struct ena_com_dev *ena_dev = &adapter->ena_dev;
	int ret, i;
	u16 entry_value;
	int conf_idx;
	int idx;

	if ((reta_size == 0) || (reta_conf == NULL))
		return -EINVAL;

	if (reta_size > ENA_RX_RSS_TABLE_SIZE) {
		RTE_LOG(WARNING, PMD,
			"indirection table %d is bigger than supported (%d)\n",
			reta_size, ENA_RX_RSS_TABLE_SIZE);
		ret = -EINVAL;
		goto err;
	}

	for (i = 0 ; i < reta_size ; i++) {
		/* each reta_conf is for 64 entries.
		 * to support 128 we use 2 conf of 64
		 */
		conf_idx = i / RTE_RETA_GROUP_SIZE;
		idx = i % RTE_RETA_GROUP_SIZE;
		if (TEST_BIT(reta_conf[conf_idx].mask, idx)) {
			entry_value =
				ENA_IO_RXQ_IDX(reta_conf[conf_idx].reta[idx]);
			ret = ena_com_indirect_table_fill_entry(ena_dev,
								i,
								entry_value);
			if (unlikely(ret && (ret != ENA_COM_PERMISSION))) {
				RTE_LOG(ERR, PMD,
					"Cannot fill indirect table\n");
				ret = -ENOTSUP;
				goto err;
			}
		}
	}

	ret = ena_com_indirect_table_set(ena_dev);
	if (unlikely(ret && (ret != ENA_COM_PERMISSION))) {
		RTE_LOG(ERR, PMD, "Cannot flush the indirect table\n");
		ret = -ENOTSUP;
		goto err;
	}

	RTE_LOG(DEBUG, PMD, "%s(): RSS configured %d entries  for port %d\n",
		__func__, reta_size, adapter->rte_dev->data->port_id);
err:
	return ret;
}

/* Query redirection table. */
static int ena_rss_reta_query(struct rte_eth_dev *dev,
			      struct rte_eth_rss_reta_entry64 *reta_conf,
			      uint16_t reta_size)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	struct ena_com_dev *ena_dev = &adapter->ena_dev;
	int ret;
	int i;
	u32 indirect_table[ENA_RX_RSS_TABLE_SIZE] = {0};
	int reta_conf_idx;
	int reta_idx;

	if (reta_size == 0 || reta_conf == NULL ||
	    (reta_size > RTE_RETA_GROUP_SIZE && ((reta_conf + 1) == NULL)))
		return -EINVAL;

	ret = ena_com_indirect_table_get(ena_dev, indirect_table);
	if (unlikely(ret && (ret != ENA_COM_PERMISSION))) {
		RTE_LOG(ERR, PMD, "cannot get indirect table\n");
		ret = -ENOTSUP;
		goto err;
	}

	for (i = 0 ; i < reta_size ; i++) {
		reta_conf_idx = i / RTE_RETA_GROUP_SIZE;
		reta_idx = i % RTE_RETA_GROUP_SIZE;
		if (TEST_BIT(reta_conf[reta_conf_idx].mask, reta_idx))
			reta_conf[reta_conf_idx].reta[reta_idx] =
				ENA_IO_RXQ_IDX_REV(indirect_table[i]);
	}
err:
	return ret;
}

static int ena_rss_init_default(struct ena_adapter *adapter)
{
	struct ena_com_dev *ena_dev = &adapter->ena_dev;
	uint16_t nb_rx_queues = adapter->rte_dev->data->nb_rx_queues;
	int rc, i;
	u32 val;

	rc = ena_com_rss_init(ena_dev, ENA_RX_RSS_TABLE_LOG_SIZE);
	if (unlikely(rc)) {
		RTE_LOG(ERR, PMD, "Cannot init indirect table\n");
		goto err_rss_init;
	}

	for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) {
		val = i % nb_rx_queues;
		rc = ena_com_indirect_table_fill_entry(ena_dev, i,
						       ENA_IO_RXQ_IDX(val));
		if (unlikely(rc && (rc != ENA_COM_PERMISSION))) {
			RTE_LOG(ERR, PMD, "Cannot fill indirect table\n");
			goto err_fill_indir;
		}
	}

	rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_CRC32, NULL,
					ENA_HASH_KEY_SIZE, 0xFFFFFFFF);
	if (unlikely(rc && (rc != ENA_COM_PERMISSION))) {
		RTE_LOG(INFO, PMD, "Cannot fill hash function\n");
		goto err_fill_indir;
	}

	rc = ena_com_set_default_hash_ctrl(ena_dev);
	if (unlikely(rc && (rc != ENA_COM_PERMISSION))) {
		RTE_LOG(INFO, PMD, "Cannot fill hash control\n");
		goto err_fill_indir;
	}

	rc = ena_com_indirect_table_set(ena_dev);
	if (unlikely(rc && (rc != ENA_COM_PERMISSION))) {
		RTE_LOG(ERR, PMD, "Cannot flush the indirect table\n");
		goto err_fill_indir;
	}
	RTE_LOG(DEBUG, PMD, "RSS configured for port %d\n",
		adapter->rte_dev->data->port_id);

	return 0;

err_fill_indir:
	ena_com_rss_destroy(ena_dev);
err_rss_init:

	return rc;
}

static void ena_rx_queue_release_all(struct rte_eth_dev *dev)
{
	struct ena_ring **queues = (struct ena_ring **)dev->data->rx_queues;
	int nb_queues = dev->data->nb_rx_queues;
	int i;

	for (i = 0; i < nb_queues; i++)
		ena_rx_queue_release(queues[i]);
}

static void ena_tx_queue_release_all(struct rte_eth_dev *dev)
{
	struct ena_ring **queues = (struct ena_ring **)dev->data->tx_queues;
	int nb_queues = dev->data->nb_tx_queues;
	int i;

	for (i = 0; i < nb_queues; i++)
		ena_tx_queue_release(queues[i]);
}

static void ena_rx_queue_release(void *queue)
{
	struct ena_ring *ring = (struct ena_ring *)queue;
	struct ena_adapter *adapter = ring->adapter;
	int ena_qid;

	ena_assert_msg(ring->configured,
		       "API violation - releasing not configured queue");
	ena_assert_msg(ring->adapter->state != ENA_ADAPTER_STATE_RUNNING,
		       "API violation");

	/* Destroy HW queue */
	ena_qid = ENA_IO_RXQ_IDX(ring->id);
	ena_com_destroy_io_queue(&adapter->ena_dev, ena_qid);

	/* Free all bufs */
	ena_rx_queue_release_bufs(ring);

	/* Free ring resources */
	if (ring->rx_buffer_info)
		rte_free(ring->rx_buffer_info);
	ring->rx_buffer_info = NULL;

	ring->configured = 0;

	RTE_LOG(NOTICE, PMD, "RX Queue %d:%d released\n",
		ring->port_id, ring->id);
}

static void ena_tx_queue_release(void *queue)
{
	struct ena_ring *ring = (struct ena_ring *)queue;
	struct ena_adapter *adapter = ring->adapter;
	int ena_qid;

	ena_assert_msg(ring->configured,
		       "API violation. Releasing not configured queue");
	ena_assert_msg(ring->adapter->state != ENA_ADAPTER_STATE_RUNNING,
		       "API violation");

	/* Destroy HW queue */
	ena_qid = ENA_IO_TXQ_IDX(ring->id);
	ena_com_destroy_io_queue(&adapter->ena_dev, ena_qid);

	/* Free all bufs */
	ena_tx_queue_release_bufs(ring);

	/* Free ring resources */
	if (ring->tx_buffer_info)
		rte_free(ring->tx_buffer_info);

	if (ring->empty_tx_reqs)
		rte_free(ring->empty_tx_reqs);

	ring->empty_tx_reqs = NULL;
	ring->tx_buffer_info = NULL;

	ring->configured = 0;

	RTE_LOG(NOTICE, PMD, "TX Queue %d:%d released\n",
		ring->port_id, ring->id);
}

static void ena_rx_queue_release_bufs(struct ena_ring *ring)
{
	unsigned int ring_mask = ring->ring_size - 1;

	while (ring->next_to_clean != ring->next_to_use) {
		struct rte_mbuf *m =
			ring->rx_buffer_info[ring->next_to_clean & ring_mask];

		if (m)
			__rte_mbuf_raw_free(m);

		ring->next_to_clean =
			ENA_CIRC_INC(ring->next_to_clean, 1, ring->ring_size);
	}
}

static void ena_tx_queue_release_bufs(struct ena_ring *ring)
{
	unsigned int ring_mask = ring->ring_size - 1;

	while (ring->next_to_clean != ring->next_to_use) {
		struct ena_tx_buffer *tx_buf =
			&ring->tx_buffer_info[ring->next_to_clean & ring_mask];

		if (tx_buf->mbuf)
			rte_pktmbuf_free(tx_buf->mbuf);

		ring->next_to_clean =
			ENA_CIRC_INC(ring->next_to_clean, 1, ring->ring_size);
	}
}

static int ena_link_update(struct rte_eth_dev *dev,
			   __rte_unused int wait_to_complete)
{
	struct rte_eth_link *link = &dev->data->dev_link;

	link->link_status = 1;
	link->link_speed = ETH_SPEED_NUM_10G;
	link->link_duplex = ETH_LINK_FULL_DUPLEX;

	return 0;
}

static int ena_queue_restart_all(struct rte_eth_dev *dev,
				 enum ena_ring_type ring_type)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	struct ena_ring *queues = NULL;
	int i = 0;
	int rc = 0;

	queues = (ring_type == ENA_RING_TYPE_RX) ?
		adapter->rx_ring : adapter->tx_ring;

	for (i = 0; i < adapter->num_queues; i++) {
		if (queues[i].configured) {
			if (ring_type == ENA_RING_TYPE_RX) {
				ena_assert_msg(
					dev->data->rx_queues[i] == &queues[i],
					"Inconsistent state of rx queues\n");
			} else {
				ena_assert_msg(
					dev->data->tx_queues[i] == &queues[i],
					"Inconsistent state of tx queues\n");
			}

			rc = ena_queue_restart(&queues[i]);

			if (rc) {
				PMD_INIT_LOG(ERR,
					     "failed to restart queue %d type(%d)\n",
					     i, ring_type);
				return -1;
			}
		}
	}

	return 0;
}

static uint32_t ena_get_mtu_conf(struct ena_adapter *adapter)
{
	uint32_t max_frame_len = adapter->max_mtu;

	if (adapter->rte_eth_dev_data->dev_conf.rxmode.jumbo_frame == 1)
		max_frame_len =
			adapter->rte_eth_dev_data->dev_conf.rxmode.max_rx_pkt_len;

	return max_frame_len;
}

static int ena_check_valid_conf(struct ena_adapter *adapter)
{
	uint32_t max_frame_len = ena_get_mtu_conf(adapter);

	if (max_frame_len > adapter->max_mtu) {
		PMD_INIT_LOG(ERR, "Unsupported MTU of %d\n", max_frame_len);
		return -1;
	}

	return 0;
}

static int
ena_calc_queue_size(struct ena_com_dev *ena_dev,
		    struct ena_com_dev_get_features_ctx *get_feat_ctx)
{
	uint32_t queue_size = ENA_DEFAULT_RING_SIZE;

	queue_size = RTE_MIN(queue_size,
			     get_feat_ctx->max_queues.max_cq_depth);
	queue_size = RTE_MIN(queue_size,
			     get_feat_ctx->max_queues.max_sq_depth);

	if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
		queue_size = RTE_MIN(queue_size,
				     get_feat_ctx->max_queues.max_llq_depth);

	/* Round down to power of 2 */
	if (!rte_is_power_of_2(queue_size))
		queue_size = rte_align32pow2(queue_size >> 1);

	if (queue_size == 0) {
		PMD_INIT_LOG(ERR, "Invalid queue size\n");
		return -EFAULT;
	}

	return queue_size;
}

static void ena_stats_restart(struct rte_eth_dev *dev)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);

	rte_atomic64_init(&adapter->drv_stats->ierrors);
	rte_atomic64_init(&adapter->drv_stats->oerrors);
	rte_atomic64_init(&adapter->drv_stats->rx_nombuf);
}

static void ena_stats_get(struct rte_eth_dev *dev,
			  struct rte_eth_stats *stats)
{
	struct ena_admin_basic_stats ena_stats;
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	struct ena_com_dev *ena_dev = &adapter->ena_dev;
	int rc;

	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
		return;

	memset(&ena_stats, 0, sizeof(ena_stats));
	rc = ena_com_get_dev_basic_stats(ena_dev, &ena_stats);
	if (unlikely(rc)) {
		RTE_LOG(ERR, PMD, "Could not retrieve statistics from ENA");
		return;
	}

	/* Set of basic statistics from ENA */
	stats->ipackets = __MERGE_64B_H_L(ena_stats.rx_pkts_high,
					  ena_stats.rx_pkts_low);
	stats->opackets = __MERGE_64B_H_L(ena_stats.tx_pkts_high,
					  ena_stats.tx_pkts_low);
	stats->ibytes = __MERGE_64B_H_L(ena_stats.rx_bytes_high,
					ena_stats.rx_bytes_low);
	stats->obytes = __MERGE_64B_H_L(ena_stats.tx_bytes_high,
					ena_stats.tx_bytes_low);
	stats->imissed = __MERGE_64B_H_L(ena_stats.rx_drops_high,
					 ena_stats.rx_drops_low);

	/* Driver related stats */
	stats->ierrors = rte_atomic64_read(&adapter->drv_stats->ierrors);
	stats->oerrors = rte_atomic64_read(&adapter->drv_stats->oerrors);
	stats->rx_nombuf = rte_atomic64_read(&adapter->drv_stats->rx_nombuf);
}

static int ena_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
{
	struct ena_adapter *adapter;
	struct ena_com_dev *ena_dev;
	int rc = 0;

	ena_assert_msg(dev->data != NULL, "Uninitialized device");
	ena_assert_msg(dev->data->dev_private != NULL, "Uninitialized device");
	adapter = (struct ena_adapter *)(dev->data->dev_private);

	ena_dev = &adapter->ena_dev;
	ena_assert_msg(ena_dev != NULL, "Uninitialized device");

	if (mtu > ena_get_mtu_conf(adapter)) {
		RTE_LOG(ERR, PMD,
			"Given MTU (%d) exceeds maximum MTU supported (%d)\n",
			mtu, ena_get_mtu_conf(adapter));
		rc = -EINVAL;
		goto err;
	}

	rc = ena_com_set_dev_mtu(ena_dev, mtu);
	if (rc)
		RTE_LOG(ERR, PMD, "Could not set MTU: %d\n", mtu);
	else
		RTE_LOG(NOTICE, PMD, "Set MTU: %d\n", mtu);

err:
	return rc;
}

static int ena_start(struct rte_eth_dev *dev)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	int rc = 0;

	if (!(adapter->state == ENA_ADAPTER_STATE_CONFIG ||
	      adapter->state == ENA_ADAPTER_STATE_STOPPED)) {
		PMD_INIT_LOG(ERR, "API violation");
		return -1;
	}

	rc = ena_check_valid_conf(adapter);
	if (rc)
		return rc;

	rc = ena_queue_restart_all(dev, ENA_RING_TYPE_RX);
	if (rc)
		return rc;

	rc = ena_queue_restart_all(dev, ENA_RING_TYPE_TX);
	if (rc)
		return rc;

	if (adapter->rte_dev->data->dev_conf.rxmode.mq_mode &
	    ETH_MQ_RX_RSS_FLAG) {
		rc = ena_rss_init_default(adapter);
		if (rc)
			return rc;
	}

	ena_stats_restart(dev);

	adapter->state = ENA_ADAPTER_STATE_RUNNING;

	return 0;
}

static int ena_queue_restart(struct ena_ring *ring)
{
	int rc;

	ena_assert_msg(ring->configured == 1,
		       "Trying to restart unconfigured queue\n");

	ring->next_to_clean = 0;
	ring->next_to_use = 0;

	if (ring->type == ENA_RING_TYPE_TX)
		return 0;

	rc = ena_populate_rx_queue(ring, ring->ring_size - 1);
	if ((unsigned int)rc != ring->ring_size - 1) {
		PMD_INIT_LOG(ERR, "Failed to populate rx ring !\n");
		return (-1);
	}

	return 0;
}

static int ena_tx_queue_setup(struct rte_eth_dev *dev,
			      uint16_t queue_idx,
			      uint16_t nb_desc,
			      __rte_unused unsigned int socket_id,
			      __rte_unused const struct rte_eth_txconf *tx_conf)
{
	struct ena_ring *txq = NULL;
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	unsigned int i;
	int ena_qid;
	int rc;
	struct ena_com_dev *ena_dev = &adapter->ena_dev;

	txq = &adapter->tx_ring[queue_idx];

	if (txq->configured) {
		RTE_LOG(CRIT, PMD,
			"API violation. Queue %d is already configured\n",
			queue_idx);
		return -1;
	}

	if (nb_desc > adapter->tx_ring_size) {
		RTE_LOG(ERR, PMD,
			"Unsupported size of TX queue (max size: %d)\n",
			adapter->tx_ring_size);
		return -EINVAL;
	}

	ena_qid = ENA_IO_TXQ_IDX(queue_idx);
	rc = ena_com_create_io_queue(ena_dev, ena_qid,
				     ENA_COM_IO_QUEUE_DIRECTION_TX,
				     ena_dev->tx_mem_queue_type,
				     -1 /* admin interrupts is not used */,
				     nb_desc);
	if (rc) {
		RTE_LOG(ERR, PMD,
			"failed to create io TX queue #%d (qid:%d) rc: %d\n",
			queue_idx, ena_qid, rc);
	}
	txq->ena_com_io_cq = &ena_dev->io_cq_queues[ena_qid];
	txq->ena_com_io_sq = &ena_dev->io_sq_queues[ena_qid];

	txq->port_id = dev->data->port_id;
	txq->next_to_clean = 0;
	txq->next_to_use = 0;
	txq->ring_size = nb_desc;

	txq->tx_buffer_info = rte_zmalloc("txq->tx_buffer_info",
					  sizeof(struct ena_tx_buffer) *
					  txq->ring_size,
					  RTE_CACHE_LINE_SIZE);
	if (!txq->tx_buffer_info) {
		RTE_LOG(ERR, PMD, "failed to alloc mem for tx buffer info\n");
		return -ENOMEM;
	}

	txq->empty_tx_reqs = rte_zmalloc("txq->empty_tx_reqs",
					 sizeof(u16) * txq->ring_size,
					 RTE_CACHE_LINE_SIZE);
	if (!txq->empty_tx_reqs) {
		RTE_LOG(ERR, PMD, "failed to alloc mem for tx reqs\n");
		rte_free(txq->tx_buffer_info);
		return -ENOMEM;
	}
	for (i = 0; i < txq->ring_size; i++)
		txq->empty_tx_reqs[i] = i;

	/* Store pointer to this queue in upper layer */
	txq->configured = 1;
	dev->data->tx_queues[queue_idx] = txq;

	return rc;
}

static int ena_rx_queue_setup(struct rte_eth_dev *dev,
			      uint16_t queue_idx,
			      uint16_t nb_desc,
			      __rte_unused unsigned int socket_id,
			      __rte_unused const struct rte_eth_rxconf *rx_conf,
			      struct rte_mempool *mp)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);
	struct ena_ring *rxq = NULL;
	uint16_t ena_qid = 0;
	int rc = 0;
	struct ena_com_dev *ena_dev = &adapter->ena_dev;

	rxq = &adapter->rx_ring[queue_idx];
	if (rxq->configured) {
		RTE_LOG(CRIT, PMD,
			"API violation. Queue %d is already configured\n",
			queue_idx);
		return -1;
	}

	if (nb_desc > adapter->rx_ring_size) {
		RTE_LOG(ERR, PMD,
			"Unsupported size of RX queue (max size: %d)\n",
			adapter->rx_ring_size);
		return -EINVAL;
	}

	ena_qid = ENA_IO_RXQ_IDX(queue_idx);
	rc = ena_com_create_io_queue(ena_dev, ena_qid,
				     ENA_COM_IO_QUEUE_DIRECTION_RX,
				     ENA_ADMIN_PLACEMENT_POLICY_HOST,
				     -1 /* admin interrupts not used */,
				     nb_desc);
	if (rc)
		RTE_LOG(ERR, PMD, "failed to create io RX queue #%d rc: %d\n",
			queue_idx, rc);

	rxq->ena_com_io_cq = &ena_dev->io_cq_queues[ena_qid];
	rxq->ena_com_io_sq = &ena_dev->io_sq_queues[ena_qid];

	rxq->port_id = dev->data->port_id;
	rxq->next_to_clean = 0;
	rxq->next_to_use = 0;
	rxq->ring_size = nb_desc;
	rxq->mb_pool = mp;

	rxq->rx_buffer_info = rte_zmalloc("rxq->buffer_info",
					  sizeof(struct rte_mbuf *) * nb_desc,
					  RTE_CACHE_LINE_SIZE);
	if (!rxq->rx_buffer_info) {
		RTE_LOG(ERR, PMD, "failed to alloc mem for rx buffer info\n");
		return -ENOMEM;
	}

	/* Store pointer to this queue in upper layer */
	rxq->configured = 1;
	dev->data->rx_queues[queue_idx] = rxq;

	return rc;
}

static int ena_populate_rx_queue(struct ena_ring *rxq, unsigned int count)
{
	unsigned int i;
	int rc;
	unsigned int ring_size = rxq->ring_size;
	unsigned int ring_mask = ring_size - 1;
	int next_to_use = rxq->next_to_use & ring_mask;
	struct rte_mbuf **mbufs = &rxq->rx_buffer_info[0];

	if (unlikely(!count))
		return 0;

	ena_assert_msg((((ENA_CIRC_COUNT(rxq->next_to_use, rxq->next_to_clean,
					 rxq->ring_size)) +
			 count) < rxq->ring_size), "bad ring state");

	count = RTE_MIN(count, ring_size - next_to_use);

	/* get resources for incoming packets */
	rc = rte_mempool_get_bulk(rxq->mb_pool,
				  (void **)(&mbufs[next_to_use]), count);
	if (unlikely(rc < 0)) {
		rte_atomic64_inc(&rxq->adapter->drv_stats->rx_nombuf);
		PMD_RX_LOG(DEBUG, "there are no enough free buffers");
		return 0;
	}

	for (i = 0; i < count; i++) {
		struct rte_mbuf *mbuf = mbufs[next_to_use];
		struct ena_com_buf ebuf;

		rte_prefetch0(mbufs[((next_to_use + 4) & ring_mask)]);
		/* prepare physical address for DMA transaction */
		ebuf.paddr = mbuf->buf_physaddr + RTE_PKTMBUF_HEADROOM;
		ebuf.len = mbuf->buf_len - RTE_PKTMBUF_HEADROOM;
		/* pass resource to device */
		rc = ena_com_add_single_rx_desc(rxq->ena_com_io_sq,
						&ebuf, next_to_use);
		if (unlikely(rc)) {
			RTE_LOG(WARNING, PMD, "failed adding rx desc\n");
			break;
		}
		next_to_use = ENA_RX_RING_IDX_NEXT(next_to_use, ring_size);
	}

	rte_wmb();
	rxq->next_to_use = next_to_use;
	/* let HW know that it can fill buffers with data */
	ena_com_write_sq_doorbell(rxq->ena_com_io_sq);

	return i;
}

static int ena_device_init(struct ena_com_dev *ena_dev,
			   struct ena_com_dev_get_features_ctx *get_feat_ctx)
{
	int rc;

	/* Initialize mmio registers */
	rc = ena_com_mmio_reg_read_request_init(ena_dev);
	if (rc) {
		RTE_LOG(ERR, PMD, "failed to init mmio read less\n");
		return rc;
	}

	/* reset device */
	rc = ena_com_dev_reset(ena_dev);
	if (rc) {
		RTE_LOG(ERR, PMD, "cannot reset device\n");
		goto err_mmio_read_less;
	}

	/* check FW version */
	rc = ena_com_validate_version(ena_dev);
	if (rc) {
		RTE_LOG(ERR, PMD, "device version is too low\n");
		goto err_mmio_read_less;
	}

	ena_dev->dma_addr_bits = ena_com_get_dma_width(ena_dev);

	/* ENA device administration layer init */
	rc = ena_com_admin_init(ena_dev, NULL, true);
	if (rc) {
		RTE_LOG(ERR, PMD,
			"cannot initialize ena admin queue with device\n");
		goto err_mmio_read_less;
	}

	/* To enable the msix interrupts the driver needs to know the number
	 * of queues. So the driver uses polling mode to retrieve this
	 * information.
	 */
	ena_com_set_admin_polling_mode(ena_dev, true);

	/* Get Device Attributes and features */
	rc = ena_com_get_dev_attr_feat(ena_dev, get_feat_ctx);
	if (rc) {
		RTE_LOG(ERR, PMD,
			"cannot get attribute for ena device rc= %d\n", rc);
		goto err_admin_init;
	}

	return 0;

err_admin_init:
	ena_com_admin_destroy(ena_dev);

err_mmio_read_less:
	ena_com_mmio_reg_read_request_destroy(ena_dev);

	return rc;
}

static int eth_ena_dev_init(struct rte_eth_dev *eth_dev)
{
	struct rte_pci_device *pci_dev;
	struct ena_adapter *adapter =
		(struct ena_adapter *)(eth_dev->data->dev_private);
	struct ena_com_dev *ena_dev = &adapter->ena_dev;
	struct ena_com_dev_get_features_ctx get_feat_ctx;
	int queue_size, rc;

	static int adapters_found;

	memset(adapter, 0, sizeof(struct ena_adapter));
	ena_dev = &adapter->ena_dev;

	eth_dev->dev_ops = &ena_dev_ops;
	eth_dev->rx_pkt_burst = &eth_ena_recv_pkts;
	eth_dev->tx_pkt_burst = &eth_ena_xmit_pkts;
	adapter->rte_eth_dev_data = eth_dev->data;
	adapter->rte_dev = eth_dev;

	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
		return 0;

	pci_dev = eth_dev->pci_dev;
	adapter->pdev = pci_dev;

	PMD_INIT_LOG(INFO, "Initializing %x:%x:%x.%d\n",
		     pci_dev->addr.domain,
		     pci_dev->addr.bus,
		     pci_dev->addr.devid,
		     pci_dev->addr.function);

	adapter->regs = pci_dev->mem_resource[ENA_REGS_BAR].addr;
	adapter->dev_mem_base = pci_dev->mem_resource[ENA_MEM_BAR].addr;

	/* Present ENA_MEM_BAR indicates available LLQ mode.
	 * Use corresponding policy
	 */
	if (adapter->dev_mem_base)
		ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_DEV;
	else if (adapter->regs)
		ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
	else
		PMD_INIT_LOG(CRIT, "Failed to access registers BAR(%d)\n",
			     ENA_REGS_BAR);

	ena_dev->reg_bar = adapter->regs;
	ena_dev->dmadev = adapter->pdev;

	adapter->id_number = adapters_found;

	snprintf(adapter->name, ENA_NAME_MAX_LEN, "ena_%d",
		 adapter->id_number);

	/* device specific initialization routine */
	rc = ena_device_init(ena_dev, &get_feat_ctx);
	if (rc) {
		PMD_INIT_LOG(CRIT, "Failed to init ENA device\n");
		return -1;
	}

	if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
		if (get_feat_ctx.max_queues.max_llq_num == 0) {
			PMD_INIT_LOG(ERR,
				     "Trying to use LLQ but llq_num is 0.\n"
				     "Fall back into regular queues.\n");
			ena_dev->tx_mem_queue_type =
				ENA_ADMIN_PLACEMENT_POLICY_HOST;
			adapter->num_queues =
				get_feat_ctx.max_queues.max_sq_num;
		} else {
			adapter->num_queues =
				get_feat_ctx.max_queues.max_llq_num;
		}
	} else {
		adapter->num_queues = get_feat_ctx.max_queues.max_sq_num;
	}

	queue_size = ena_calc_queue_size(ena_dev, &get_feat_ctx);
	if ((queue_size <= 0) || (adapter->num_queues <= 0))
		return -EFAULT;

	adapter->tx_ring_size = queue_size;
	adapter->rx_ring_size = queue_size;

	/* prepare ring structures */
	ena_init_rings(adapter);

	/* Set max MTU for this device */
	adapter->max_mtu = get_feat_ctx.dev_attr.max_mtu;

	/* Copy MAC address and point DPDK to it */
	eth_dev->data->mac_addrs = (struct ether_addr *)adapter->mac_addr;
	ether_addr_copy((struct ether_addr *)get_feat_ctx.dev_attr.mac_addr,
			(struct ether_addr *)adapter->mac_addr);

	adapter->drv_stats = rte_zmalloc("adapter stats",
					 sizeof(*adapter->drv_stats),
					 RTE_CACHE_LINE_SIZE);
	if (!adapter->drv_stats) {
		RTE_LOG(ERR, PMD, "failed to alloc mem for adapter stats\n");
		return -ENOMEM;
	}

	adapters_found++;
	adapter->state = ENA_ADAPTER_STATE_INIT;

	return 0;
}

static int ena_dev_configure(struct rte_eth_dev *dev)
{
	struct ena_adapter *adapter =
		(struct ena_adapter *)(dev->data->dev_private);

	if (!(adapter->state == ENA_ADAPTER_STATE_INIT ||
	      adapter->state == ENA_ADAPTER_STATE_STOPPED)) {
		PMD_INIT_LOG(ERR, "Illegal adapter state: %d\n",
			     adapter->state);
		return -1;
	}

	switch (adapter->state) {
	case ENA_ADAPTER_STATE_INIT:
	case ENA_ADAPTER_STATE_STOPPED:
		adapter->state = ENA_ADAPTER_STATE_CONFIG;
		break;
	case ENA_ADAPTER_STATE_CONFIG:
		RTE_LOG(WARNING, PMD,
			"Ivalid driver state while trying to configure device\n");
		break;
	default:
		break;
	}

	return 0;
}

static void ena_init_rings(struct ena_adapter *adapter)
{
	int i;

	for (i = 0; i < adapter->num_queues; i++) {
		struct ena_ring *ring = &adapter->tx_ring[i];

		ring->configured = 0;
		ring->type = ENA_RING_TYPE_TX;
		ring->adapter = adapter;
		ring->id = i;
		ring->tx_mem_queue_type = adapter->ena_dev.tx_mem_queue_type;
		ring->tx_max_header_size = adapter->ena_dev.tx_max_header_size;
	}

	for (i = 0; i < adapter->num_queues; i++) {
		struct ena_ring *ring = &adapter->rx_ring[i];

		ring->configured = 0;
		ring->type = ENA_RING_TYPE_RX;
		ring->adapter = adapter;
		ring->id = i;
	}
}

static void ena_infos_get(struct rte_eth_dev *dev,
			  struct rte_eth_dev_info *dev_info)
{
	struct ena_adapter *adapter;
	struct ena_com_dev *ena_dev;
	struct ena_com_dev_get_features_ctx feat;
	uint32_t rx_feat = 0, tx_feat = 0;
	int rc = 0;

	ena_assert_msg(dev->data != NULL, "Uninitialized device");
	ena_assert_msg(dev->data->dev_private != NULL, "Uninitialized device");
	adapter = (struct ena_adapter *)(dev->data->dev_private);

	ena_dev = &adapter->ena_dev;
	ena_assert_msg(ena_dev != NULL, "Uninitialized device");

	dev_info->speed_capa =
			ETH_LINK_SPEED_1G   |
			ETH_LINK_SPEED_2_5G |
			ETH_LINK_SPEED_5G   |
			ETH_LINK_SPEED_10G  |
			ETH_LINK_SPEED_25G  |
			ETH_LINK_SPEED_40G  |
			ETH_LINK_SPEED_50G  |
			ETH_LINK_SPEED_100G;

	/* Get supported features from HW */
	rc = ena_com_get_dev_attr_feat(ena_dev, &feat);
	if (unlikely(rc)) {
		RTE_LOG(ERR, PMD,
			"Cannot get attribute for ena device rc= %d\n", rc);
		return;
	}

	/* Set Tx & Rx features available for device */
	if (feat.offload.tx & ENA_ADMIN_FEATURE_OFFLOAD_DESC_TSO_IPV4_MASK)
		tx_feat	|= DEV_TX_OFFLOAD_TCP_TSO;

	if (feat.offload.tx &
	    ENA_ADMIN_FEATURE_OFFLOAD_DESC_TX_L4_IPV4_CSUM_PART_MASK)
		tx_feat |= DEV_TX_OFFLOAD_IPV4_CKSUM |
			DEV_TX_OFFLOAD_UDP_CKSUM |
			DEV_TX_OFFLOAD_TCP_CKSUM;

	if (feat.offload.tx &
	    ENA_ADMIN_FEATURE_OFFLOAD_DESC_RX_L4_IPV4_CSUM_MASK)
		rx_feat |= DEV_RX_OFFLOAD_IPV4_CKSUM |
			DEV_RX_OFFLOAD_UDP_CKSUM  |
			DEV_RX_OFFLOAD_TCP_CKSUM;

	/* Inform framework about available features */
	dev_info->rx_offload_capa = rx_feat;
	dev_info->tx_offload_capa = tx_feat;

	dev_info->min_rx_bufsize = ENA_MIN_FRAME_LEN;
	dev_info->max_rx_pktlen  = adapter->max_mtu;
	dev_info->max_mac_addrs = 1;

	dev_info->max_rx_queues = adapter->num_queues;
	dev_info->max_tx_queues = adapter->num_queues;
	dev_info->reta_size = ENA_RX_RSS_TABLE_SIZE;
}

static uint16_t eth_ena_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
				  uint16_t nb_pkts)
{
	struct ena_ring *rx_ring = (struct ena_ring *)(rx_queue);
	unsigned int ring_size = rx_ring->ring_size;
	unsigned int ring_mask = ring_size - 1;
	uint16_t next_to_clean = rx_ring->next_to_clean;
	int desc_in_use = 0;
	unsigned int recv_idx = 0;
	struct rte_mbuf *mbuf = NULL;
	struct rte_mbuf *mbuf_head = NULL;
	struct rte_mbuf *mbuf_prev = NULL;
	struct rte_mbuf **rx_buff_info = rx_ring->rx_buffer_info;
	unsigned int completed;

	struct ena_com_rx_ctx ena_rx_ctx;
	int rc = 0;

	/* Check adapter state */
	if (unlikely(rx_ring->adapter->state != ENA_ADAPTER_STATE_RUNNING)) {
		RTE_LOG(ALERT, PMD,
			"Trying to receive pkts while device is NOT running\n");
		return 0;
	}

	desc_in_use = ENA_CIRC_COUNT(rx_ring->next_to_use,
				     next_to_clean, ring_size);
	if (unlikely(nb_pkts > desc_in_use))
		nb_pkts = desc_in_use;

	for (completed = 0; completed < nb_pkts; completed++) {
		int segments = 0;

		ena_rx_ctx.max_bufs = rx_ring->ring_size;
		ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
		ena_rx_ctx.descs = 0;
		/* receive packet context */
		rc = ena_com_rx_pkt(rx_ring->ena_com_io_cq,
				    rx_ring->ena_com_io_sq,
				    &ena_rx_ctx);
		if (unlikely(rc)) {
			RTE_LOG(ERR, PMD, "ena_com_rx_pkt error %d\n", rc);
			return 0;
		}

		if (unlikely(ena_rx_ctx.descs == 0))
			break;

		while (segments < ena_rx_ctx.descs) {
			mbuf = rx_buff_info[next_to_clean & ring_mask];
			mbuf->data_len = ena_rx_ctx.ena_bufs[segments].len;
			mbuf->data_off = RTE_PKTMBUF_HEADROOM;
			mbuf->refcnt = 1;
			mbuf->next = NULL;
			if (segments == 0) {
				mbuf->nb_segs = ena_rx_ctx.descs;
				mbuf->port = rx_ring->port_id;
				mbuf->pkt_len = 0;
				mbuf_head = mbuf;
			} else {
				/* for multi-segment pkts create mbuf chain */
				mbuf_prev->next = mbuf;
			}
			mbuf_head->pkt_len += mbuf->data_len;

			mbuf_prev = mbuf;
			segments++;
			next_to_clean =
				ENA_RX_RING_IDX_NEXT(next_to_clean, ring_size);
		}

		/* fill mbuf attributes if any */
		ena_rx_mbuf_prepare(mbuf_head, &ena_rx_ctx);
		mbuf_head->hash.rss = (uint32_t)rx_ring->id;

		/* pass to DPDK application head mbuf */
		rx_pkts[recv_idx] = mbuf_head;
		recv_idx++;
	}

	/* Burst refill to save doorbells, memory barriers, const interval */
	if (ring_size - desc_in_use - 1 > ENA_RING_DESCS_RATIO(ring_size))
		ena_populate_rx_queue(rx_ring, ring_size - desc_in_use - 1);

	rx_ring->next_to_clean = next_to_clean & ring_mask;

	return recv_idx;
}

static uint16_t eth_ena_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
				  uint16_t nb_pkts)
{
	struct ena_ring *tx_ring = (struct ena_ring *)(tx_queue);
	unsigned int next_to_use = tx_ring->next_to_use;
	struct rte_mbuf *mbuf;
	unsigned int ring_size = tx_ring->ring_size;
	unsigned int ring_mask = ring_size - 1;
	struct ena_com_tx_ctx ena_tx_ctx;
	struct ena_tx_buffer *tx_info;
	struct ena_com_buf *ebuf;
	uint16_t rc, req_id, total_tx_descs = 0;
	int sent_idx = 0;
	int nb_hw_desc;

	/* Check adapter state */
	if (unlikely(tx_ring->adapter->state != ENA_ADAPTER_STATE_RUNNING)) {
		RTE_LOG(ALERT, PMD,
			"Trying to xmit pkts while device is NOT running\n");
		return 0;
	}

	for (sent_idx = 0; sent_idx < nb_pkts; sent_idx++) {
		mbuf = tx_pkts[sent_idx];

		req_id = tx_ring->empty_tx_reqs[next_to_use];
		tx_info = &tx_ring->tx_buffer_info[req_id];
		tx_info->mbuf = mbuf;
		tx_info->num_of_bufs = 0;
		ebuf = tx_info->bufs;

		/* Prepare TX context */
		memset(&ena_tx_ctx, 0x0, sizeof(struct ena_com_tx_ctx));
		memset(&ena_tx_ctx.ena_meta, 0x0,
		       sizeof(struct ena_com_tx_meta));
		ena_tx_ctx.ena_bufs = ebuf;
		ena_tx_ctx.req_id = req_id;
		if (tx_ring->tx_mem_queue_type ==
				ENA_ADMIN_PLACEMENT_POLICY_DEV) {
			/* prepare the push buffer with
			 * virtual address of the data
			 */
			ena_tx_ctx.header_len =
				RTE_MIN(mbuf->data_len,
					tx_ring->tx_max_header_size);
			ena_tx_ctx.push_header =
				(void *)((char *)mbuf->buf_addr +
					 mbuf->data_off);
		} /* there's no else as we take advantage of memset zeroing */

		/* Set TX offloads flags, if applicable */
		ena_tx_mbuf_prepare(mbuf, &ena_tx_ctx);

		if (unlikely(mbuf->ol_flags &
			     (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD)))
			rte_atomic64_inc(&tx_ring->adapter->drv_stats->ierrors);

		rte_prefetch0(tx_pkts[(sent_idx + 4) & ring_mask]);

		/* Process first segment taking into
		 * consideration pushed header
		 */
		if (mbuf->data_len > ena_tx_ctx.header_len) {
			ebuf->paddr = mbuf->buf_physaddr +
				      mbuf->data_off +
				      ena_tx_ctx.header_len;
			ebuf->len = mbuf->data_len - ena_tx_ctx.header_len;
			ebuf++;
			tx_info->num_of_bufs++;
		}

		while ((mbuf = mbuf->next) != NULL) {
			ebuf->paddr = mbuf->buf_physaddr + mbuf->data_off;
			ebuf->len = mbuf->data_len;
			ebuf++;
			tx_info->num_of_bufs++;
		}

		ena_tx_ctx.num_bufs = tx_info->num_of_bufs;

		/* Write data to device */
		rc = ena_com_prepare_tx(tx_ring->ena_com_io_sq,
					&ena_tx_ctx, &nb_hw_desc);
		if (unlikely(rc))
			break;

		tx_info->tx_descs = nb_hw_desc;

		next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use, ring_size);
	}

	/* Let HW do it's best :-) */
	rte_wmb();
	ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);

	/* Clear complete packets  */
	while (ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq, &req_id) >= 0) {
		/* Get Tx info & store how many descs were processed  */
		tx_info = &tx_ring->tx_buffer_info[req_id];
		total_tx_descs += tx_info->tx_descs;

		/* Free whole mbuf chain  */
		mbuf = tx_info->mbuf;
		rte_pktmbuf_free(mbuf);

		/* Put back descriptor to the ring for reuse */
		tx_ring->empty_tx_reqs[tx_ring->next_to_clean] = req_id;
		tx_ring->next_to_clean =
			ENA_TX_RING_IDX_NEXT(tx_ring->next_to_clean,
					     tx_ring->ring_size);

		/* If too many descs to clean, leave it for another run */
		if (unlikely(total_tx_descs > ENA_RING_DESCS_RATIO(ring_size)))
			break;
	}

	/* acknowledge completion of sent packets */
	ena_com_comp_ack(tx_ring->ena_com_io_sq, total_tx_descs);
	tx_ring->next_to_use = next_to_use;
	return sent_idx;
}

static struct eth_driver rte_ena_pmd = {
	{
		.name = "rte_ena_pmd",
		.id_table = pci_id_ena_map,
		.drv_flags = RTE_PCI_DRV_NEED_MAPPING,
	},
	.eth_dev_init = eth_ena_dev_init,
	.dev_private_size = sizeof(struct ena_adapter),
};

static int
rte_ena_pmd_init(const char *name __rte_unused,
		 const char *params __rte_unused)
{
	rte_eth_driver_register(&rte_ena_pmd);
	return 0;
};

struct rte_driver ena_pmd_drv = {
	.name = "ena_driver",
	.type = PMD_PDEV,
	.init = rte_ena_pmd_init,
};

PMD_REGISTER_DRIVER(ena_pmd_drv);