summaryrefslogtreecommitdiffstats
path: root/drivers/net/hyperv/netvsc.c
blob: 82e9796c8f5e5f9f8574cfed7bfbcefb35828172 (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
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
#include <linux/prefetch.h>
#include <linux/filter.h>

#include <asm/sync_bitops.h>
#include <asm/mshyperv.h>

#include "hyperv_net.h"
#include "netvsc_trace.h"

/*
 * Switch the data path from the synthetic interface to the VF
 * interface.
 */
int netvsc_switch_datapath(struct net_device *ndev, bool vf)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct hv_device *dev = net_device_ctx->device_ctx;
	struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev);
	struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt;
	int ret, retry = 0;

	/* Block sending traffic to VF if it's about to be gone */
	if (!vf)
		net_device_ctx->data_path_is_vf = vf;

	memset(init_pkt, 0, sizeof(struct nvsp_message));
	init_pkt->hdr.msg_type = NVSP_MSG4_TYPE_SWITCH_DATA_PATH;
	if (vf)
		init_pkt->msg.v4_msg.active_dp.active_datapath =
			NVSP_DATAPATH_VF;
	else
		init_pkt->msg.v4_msg.active_dp.active_datapath =
			NVSP_DATAPATH_SYNTHETIC;

again:
	trace_nvsp_send(ndev, init_pkt);

	ret = vmbus_sendpacket(dev->channel, init_pkt,
			       sizeof(struct nvsp_message),
			       (unsigned long)init_pkt, VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);

	/* If failed to switch to/from VF, let data_path_is_vf stay false,
	 * so we use synthetic path to send data.
	 */
	if (ret) {
		if (ret != -EAGAIN) {
			netdev_err(ndev,
				   "Unable to send sw datapath msg, err: %d\n",
				   ret);
			return ret;
		}

		if (retry++ < RETRY_MAX) {
			usleep_range(RETRY_US_LO, RETRY_US_HI);
			goto again;
		} else {
			netdev_err(
				ndev,
				"Retry failed to send sw datapath msg, err: %d\n",
				ret);
			return ret;
		}
	}

	wait_for_completion(&nv_dev->channel_init_wait);
	net_device_ctx->data_path_is_vf = vf;

	return 0;
}

/* Worker to setup sub channels on initial setup
 * Initial hotplug event occurs in softirq context
 * and can't wait for channels.
 */
static void netvsc_subchan_work(struct work_struct *w)
{
	struct netvsc_device *nvdev =
		container_of(w, struct netvsc_device, subchan_work);
	struct rndis_device *rdev;
	int i, ret;

	/* Avoid deadlock with device removal already under RTNL */
	if (!rtnl_trylock()) {
		schedule_work(w);
		return;
	}

	rdev = nvdev->extension;
	if (rdev) {
		ret = rndis_set_subchannel(rdev->ndev, nvdev, NULL);
		if (ret == 0) {
			netif_device_attach(rdev->ndev);
		} else {
			/* fallback to only primary channel */
			for (i = 1; i < nvdev->num_chn; i++)
				netif_napi_del(&nvdev->chan_table[i].napi);

			nvdev->max_chn = 1;
			nvdev->num_chn = 1;
		}
	}

	rtnl_unlock();
}

static struct netvsc_device *alloc_net_device(void)
{
	struct netvsc_device *net_device;

	net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL);
	if (!net_device)
		return NULL;

	init_waitqueue_head(&net_device->wait_drain);
	net_device->destroy = false;
	net_device->tx_disable = true;

	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;

	init_completion(&net_device->channel_init_wait);
	init_waitqueue_head(&net_device->subchan_open);
	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);

	return net_device;
}

static void free_netvsc_device(struct rcu_head *head)
{
	struct netvsc_device *nvdev
		= container_of(head, struct netvsc_device, rcu);
	int i;

	kfree(nvdev->extension);
	vfree(nvdev->recv_buf);
	vfree(nvdev->send_buf);
	bitmap_free(nvdev->send_section_map);

	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
		xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq);
		kfree(nvdev->chan_table[i].recv_buf);
		vfree(nvdev->chan_table[i].mrc.slots);
	}

	kfree(nvdev);
}

static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
{
	call_rcu(&nvdev->rcu, free_netvsc_device);
}

static void netvsc_revoke_recv_buf(struct hv_device *device,
				   struct netvsc_device *net_device,
				   struct net_device *ndev)
{
	struct nvsp_message *revoke_packet;
	int ret;

	/*
	 * If we got a section count, it means we received a
	 * SendReceiveBufferComplete msg (ie sent
	 * NvspMessage1TypeSendReceiveBuffer msg) therefore, we need
	 * to send a revoke msg here
	 */
	if (net_device->recv_section_cnt) {
		/* Send the revoke receive buffer */
		revoke_packet = &net_device->revoke_packet;
		memset(revoke_packet, 0, sizeof(struct nvsp_message));

		revoke_packet->hdr.msg_type =
			NVSP_MSG1_TYPE_REVOKE_RECV_BUF;
		revoke_packet->msg.v1_msg.
		revoke_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;

		trace_nvsp_send(ndev, revoke_packet);

		ret = vmbus_sendpacket(device->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       VMBUS_RQST_ID_NO_RESPONSE,
				       VM_PKT_DATA_INBAND, 0);
		/* If the failure is because the channel is rescinded;
		 * ignore the failure since we cannot send on a rescinded
		 * channel. This would allow us to properly cleanup
		 * even when the channel is rescinded.
		 */
		if (device->channel->rescind)
			ret = 0;
		/*
		 * If we failed here, we might as well return and
		 * have a leak rather than continue and a bugchk
		 */
		if (ret != 0) {
			netdev_err(ndev, "unable to send "
				"revoke receive buffer to netvsp\n");
			return;
		}
		net_device->recv_section_cnt = 0;
	}
}

static void netvsc_revoke_send_buf(struct hv_device *device,
				   struct netvsc_device *net_device,
				   struct net_device *ndev)
{
	struct nvsp_message *revoke_packet;
	int ret;

	/* Deal with the send buffer we may have setup.
	 * If we got a  send section size, it means we received a
	 * NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE msg (ie sent
	 * NVSP_MSG1_TYPE_SEND_SEND_BUF msg) therefore, we need
	 * to send a revoke msg here
	 */
	if (net_device->send_section_cnt) {
		/* Send the revoke receive buffer */
		revoke_packet = &net_device->revoke_packet;
		memset(revoke_packet, 0, sizeof(struct nvsp_message));

		revoke_packet->hdr.msg_type =
			NVSP_MSG1_TYPE_REVOKE_SEND_BUF;
		revoke_packet->msg.v1_msg.revoke_send_buf.id =
			NETVSC_SEND_BUFFER_ID;

		trace_nvsp_send(ndev, revoke_packet);

		ret = vmbus_sendpacket(device->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       VMBUS_RQST_ID_NO_RESPONSE,
				       VM_PKT_DATA_INBAND, 0);

		/* If the failure is because the channel is rescinded;
		 * ignore the failure since we cannot send on a rescinded
		 * channel. This would allow us to properly cleanup
		 * even when the channel is rescinded.
		 */
		if (device->channel->rescind)
			ret = 0;

		/* If we failed here, we might as well return and
		 * have a leak rather than continue and a bugchk
		 */
		if (ret != 0) {
			netdev_err(ndev, "unable to send "
				   "revoke send buffer to netvsp\n");
			return;
		}
		net_device->send_section_cnt = 0;
	}
}

static void netvsc_teardown_recv_gpadl(struct hv_device *device,
				       struct netvsc_device *net_device,
				       struct net_device *ndev)
{
	int ret;

	if (net_device->recv_buf_gpadl_handle.gpadl_handle) {
		ret = vmbus_teardown_gpadl(device->channel,
					   &net_device->recv_buf_gpadl_handle);

		/* If we failed here, we might as well return and have a leak
		 * rather than continue and a bugchk
		 */
		if (ret != 0) {
			netdev_err(ndev,
				   "unable to teardown receive buffer's gpadl\n");
			return;
		}
	}
}

static void netvsc_teardown_send_gpadl(struct hv_device *device,
				       struct netvsc_device *net_device,
				       struct net_device *ndev)
{
	int ret;

	if (net_device->send_buf_gpadl_handle.gpadl_handle) {
		ret = vmbus_teardown_gpadl(device->channel,
					   &net_device->send_buf_gpadl_handle);

		/* If we failed here, we might as well return and have a leak
		 * rather than continue and a bugchk
		 */
		if (ret != 0) {
			netdev_err(ndev,
				   "unable to teardown send buffer's gpadl\n");
			return;
		}
	}
}

int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx)
{
	struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
	int node = cpu_to_node(nvchan->channel->target_cpu);
	size_t size;

	size = net_device->recv_completion_cnt * sizeof(struct recv_comp_data);
	nvchan->mrc.slots = vzalloc_node(size, node);
	if (!nvchan->mrc.slots)
		nvchan->mrc.slots = vzalloc(size);

	return nvchan->mrc.slots ? 0 : -ENOMEM;
}

static int netvsc_init_buf(struct hv_device *device,
			   struct netvsc_device *net_device,
			   const struct netvsc_device_info *device_info)
{
	struct nvsp_1_message_send_receive_buffer_complete *resp;
	struct net_device *ndev = hv_get_drvdata(device);
	struct nvsp_message *init_packet;
	unsigned int buf_size;
	int i, ret = 0;

	/* Get receive buffer area. */
	buf_size = device_info->recv_sections * device_info->recv_section_size;
	buf_size = roundup(buf_size, PAGE_SIZE);

	/* Legacy hosts only allow smaller receive buffer */
	if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
		buf_size = min_t(unsigned int, buf_size,
				 NETVSC_RECEIVE_BUFFER_SIZE_LEGACY);

	net_device->recv_buf = vzalloc(buf_size);
	if (!net_device->recv_buf) {
		netdev_err(ndev,
			   "unable to allocate receive buffer of size %u\n",
			   buf_size);
		ret = -ENOMEM;
		goto cleanup;
	}

	net_device->recv_buf_size = buf_size;

	/*
	 * Establish the gpadl handle for this buffer on this
	 * channel.  Note: This call uses the vmbus connection rather
	 * than the channel to establish the gpadl handle.
	 */
	ret = vmbus_establish_gpadl(device->channel, net_device->recv_buf,
				    buf_size,
				    &net_device->recv_buf_gpadl_handle);
	if (ret != 0) {
		netdev_err(ndev,
			"unable to establish receive buffer's gpadl\n");
		goto cleanup;
	}

	/* Notify the NetVsp of the gpadl handle */
	init_packet = &net_device->channel_init_pkt;
	memset(init_packet, 0, sizeof(struct nvsp_message));
	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_RECV_BUF;
	init_packet->msg.v1_msg.send_recv_buf.
		gpadl_handle = net_device->recv_buf_gpadl_handle.gpadl_handle;
	init_packet->msg.v1_msg.
		send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;

	trace_nvsp_send(ndev, init_packet);

	/* Send the gpadl notification request */
	ret = vmbus_sendpacket(device->channel, init_packet,
			       sizeof(struct nvsp_message),
			       (unsigned long)init_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret != 0) {
		netdev_err(ndev,
			"unable to send receive buffer's gpadl to netvsp\n");
		goto cleanup;
	}

	wait_for_completion(&net_device->channel_init_wait);

	/* Check the response */
	resp = &init_packet->msg.v1_msg.send_recv_buf_complete;
	if (resp->status != NVSP_STAT_SUCCESS) {
		netdev_err(ndev,
			   "Unable to complete receive buffer initialization with NetVsp - status %d\n",
			   resp->status);
		ret = -EINVAL;
		goto cleanup;
	}

	/* Parse the response */
	netdev_dbg(ndev, "Receive sections: %u sub_allocs: size %u count: %u\n",
		   resp->num_sections, resp->sections[0].sub_alloc_size,
		   resp->sections[0].num_sub_allocs);

	/* There should only be one section for the entire receive buffer */
	if (resp->num_sections != 1 || resp->sections[0].offset != 0) {
		ret = -EINVAL;
		goto cleanup;
	}

	net_device->recv_section_size = resp->sections[0].sub_alloc_size;
	net_device->recv_section_cnt = resp->sections[0].num_sub_allocs;

	/* Ensure buffer will not overflow */
	if (net_device->recv_section_size < NETVSC_MTU_MIN || (u64)net_device->recv_section_size *
	    (u64)net_device->recv_section_cnt > (u64)buf_size) {
		netdev_err(ndev, "invalid recv_section_size %u\n",
			   net_device->recv_section_size);
		ret = -EINVAL;
		goto cleanup;
	}

	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
		struct netvsc_channel *nvchan = &net_device->chan_table[i];

		nvchan->recv_buf = kzalloc(net_device->recv_section_size, GFP_KERNEL);
		if (nvchan->recv_buf == NULL) {
			ret = -ENOMEM;
			goto cleanup;
		}
	}

	/* Setup receive completion ring.
	 * Add 1 to the recv_section_cnt because at least one entry in a
	 * ring buffer has to be empty.
	 */
	net_device->recv_completion_cnt = net_device->recv_section_cnt + 1;
	ret = netvsc_alloc_recv_comp_ring(net_device, 0);
	if (ret)
		goto cleanup;

	/* Now setup the send buffer. */
	buf_size = device_info->send_sections * device_info->send_section_size;
	buf_size = round_up(buf_size, PAGE_SIZE);

	net_device->send_buf = vzalloc(buf_size);
	if (!net_device->send_buf) {
		netdev_err(ndev, "unable to allocate send buffer of size %u\n",
			   buf_size);
		ret = -ENOMEM;
		goto cleanup;
	}
	net_device->send_buf_size = buf_size;

	/* Establish the gpadl handle for this buffer on this
	 * channel.  Note: This call uses the vmbus connection rather
	 * than the channel to establish the gpadl handle.
	 */
	ret = vmbus_establish_gpadl(device->channel, net_device->send_buf,
				    buf_size,
				    &net_device->send_buf_gpadl_handle);
	if (ret != 0) {
		netdev_err(ndev,
			   "unable to establish send buffer's gpadl\n");
		goto cleanup;
	}

	/* Notify the NetVsp of the gpadl handle */
	init_packet = &net_device->channel_init_pkt;
	memset(init_packet, 0, sizeof(struct nvsp_message));
	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
	init_packet->msg.v1_msg.send_send_buf.gpadl_handle =
		net_device->send_buf_gpadl_handle.gpadl_handle;
	init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID;

	trace_nvsp_send(ndev, init_packet);

	/* Send the gpadl notification request */
	ret = vmbus_sendpacket(device->channel, init_packet,
			       sizeof(struct nvsp_message),
			       (unsigned long)init_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret != 0) {
		netdev_err(ndev,
			   "unable to send send buffer's gpadl to netvsp\n");
		goto cleanup;
	}

	wait_for_completion(&net_device->channel_init_wait);

	/* Check the response */
	if (init_packet->msg.v1_msg.
	    send_send_buf_complete.status != NVSP_STAT_SUCCESS) {
		netdev_err(ndev, "Unable to complete send buffer "
			   "initialization with NetVsp - status %d\n",
			   init_packet->msg.v1_msg.
			   send_send_buf_complete.status);
		ret = -EINVAL;
		goto cleanup;
	}

	/* Parse the response */
	net_device->send_section_size = init_packet->msg.
				v1_msg.send_send_buf_complete.section_size;
	if (net_device->send_section_size < NETVSC_MTU_MIN) {
		netdev_err(ndev, "invalid send_section_size %u\n",
			   net_device->send_section_size);
		ret = -EINVAL;
		goto cleanup;
	}

	/* Section count is simply the size divided by the section size. */
	net_device->send_section_cnt = buf_size / net_device->send_section_size;

	netdev_dbg(ndev, "Send section size: %d, Section count:%d\n",
		   net_device->send_section_size, net_device->send_section_cnt);

	/* Setup state for managing the send buffer. */
	net_device->send_section_map = bitmap_zalloc(net_device->send_section_cnt,
						     GFP_KERNEL);
	if (!net_device->send_section_map) {
		ret = -ENOMEM;
		goto cleanup;
	}

	goto exit;

cleanup:
	netvsc_revoke_recv_buf(device, net_device, ndev);
	netvsc_revoke_send_buf(device, net_device, ndev);
	netvsc_teardown_recv_gpadl(device, net_device, ndev);
	netvsc_teardown_send_gpadl(device, net_device, ndev);

exit:
	return ret;
}

/* Negotiate NVSP protocol version */
static int negotiate_nvsp_ver(struct hv_device *device,
			      struct netvsc_device *net_device,
			      struct nvsp_message *init_packet,
			      u32 nvsp_ver)
{
	struct net_device *ndev = hv_get_drvdata(device);
	int ret;

	memset(init_packet, 0, sizeof(struct nvsp_message));
	init_packet->hdr.msg_type = NVSP_MSG_TYPE_INIT;
	init_packet->msg.init_msg.init.min_protocol_ver = nvsp_ver;
	init_packet->msg.init_msg.init.max_protocol_ver = nvsp_ver;
	trace_nvsp_send(ndev, init_packet);

	/* Send the init request */
	ret = vmbus_sendpacket(device->channel, init_packet,
			       sizeof(struct nvsp_message),
			       (unsigned long)init_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);

	if (ret != 0)
		return ret;

	wait_for_completion(&net_device->channel_init_wait);

	if (init_packet->msg.init_msg.init_complete.status !=
	    NVSP_STAT_SUCCESS)
		return -EINVAL;

	if (nvsp_ver == NVSP_PROTOCOL_VERSION_1)
		return 0;

	/* NVSPv2 or later: Send NDIS config */
	memset(init_packet, 0, sizeof(struct nvsp_message));
	init_packet->hdr.msg_type = NVSP_MSG2_TYPE_SEND_NDIS_CONFIG;
	init_packet->msg.v2_msg.send_ndis_config.mtu = ndev->mtu + ETH_HLEN;
	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;

	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) {
		if (hv_is_isolation_supported())
			netdev_info(ndev, "SR-IOV not advertised by guests on the host supporting isolation\n");
		else
			init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;

		/* Teaming bit is needed to receive link speed updates */
		init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1;
	}

	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_61)
		init_packet->msg.v2_msg.send_ndis_config.capability.rsc = 1;

	trace_nvsp_send(ndev, init_packet);

	ret = vmbus_sendpacket(device->channel, init_packet,
				sizeof(struct nvsp_message),
				VMBUS_RQST_ID_NO_RESPONSE,
				VM_PKT_DATA_INBAND, 0);

	return ret;
}

static int netvsc_connect_vsp(struct hv_device *device,
			      struct netvsc_device *net_device,
			      const struct netvsc_device_info *device_info)
{
	struct net_device *ndev = hv_get_drvdata(device);
	static const u32 ver_list[] = {
		NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
		NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5,
		NVSP_PROTOCOL_VERSION_6, NVSP_PROTOCOL_VERSION_61
	};
	struct nvsp_message *init_packet;
	int ndis_version, i, ret;

	init_packet = &net_device->channel_init_pkt;

	/* Negotiate the latest NVSP protocol supported */
	for (i = ARRAY_SIZE(ver_list) - 1; i >= 0; i--)
		if (negotiate_nvsp_ver(device, net_device, init_packet,
				       ver_list[i])  == 0) {
			net_device->nvsp_version = ver_list[i];
			break;
		}

	if (i < 0) {
		ret = -EPROTO;
		goto cleanup;
	}

	if (hv_is_isolation_supported() && net_device->nvsp_version < NVSP_PROTOCOL_VERSION_61) {
		netdev_err(ndev, "Invalid NVSP version 0x%x (expected >= 0x%x) from the host supporting isolation\n",
			   net_device->nvsp_version, NVSP_PROTOCOL_VERSION_61);
		ret = -EPROTO;
		goto cleanup;
	}

	pr_debug("Negotiated NVSP version:%x\n", net_device->nvsp_version);

	/* Send the ndis version */
	memset(init_packet, 0, sizeof(struct nvsp_message));

	if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_4)
		ndis_version = 0x00060001;
	else
		ndis_version = 0x0006001e;

	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_NDIS_VER;
	init_packet->msg.v1_msg.
		send_ndis_ver.ndis_major_ver =
				(ndis_version & 0xFFFF0000) >> 16;
	init_packet->msg.v1_msg.
		send_ndis_ver.ndis_minor_ver =
				ndis_version & 0xFFFF;

	trace_nvsp_send(ndev, init_packet);

	/* Send the init request */
	ret = vmbus_sendpacket(device->channel, init_packet,
				sizeof(struct nvsp_message),
				VMBUS_RQST_ID_NO_RESPONSE,
				VM_PKT_DATA_INBAND, 0);
	if (ret != 0)
		goto cleanup;


	ret = netvsc_init_buf(device, net_device, device_info);

cleanup:
	return ret;
}

/*
 * netvsc_device_remove - Callback when the root bus device is removed
 */
void netvsc_device_remove(struct hv_device *device)
{
	struct net_device *ndev = hv_get_drvdata(device);
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct netvsc_device *net_device
		= rtnl_dereference(net_device_ctx->nvdev);
	int i;

	/*
	 * Revoke receive buffer. If host is pre-Win2016 then tear down
	 * receive buffer GPADL. Do the same for send buffer.
	 */
	netvsc_revoke_recv_buf(device, net_device, ndev);
	if (vmbus_proto_version < VERSION_WIN10)
		netvsc_teardown_recv_gpadl(device, net_device, ndev);

	netvsc_revoke_send_buf(device, net_device, ndev);
	if (vmbus_proto_version < VERSION_WIN10)
		netvsc_teardown_send_gpadl(device, net_device, ndev);

	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);

	/* Disable NAPI and disassociate its context from the device. */
	for (i = 0; i < net_device->num_chn; i++) {
		/* See also vmbus_reset_channel_cb(). */
		napi_disable(&net_device->chan_table[i].napi);
		netif_napi_del(&net_device->chan_table[i].napi);
	}

	/*
	 * At this point, no one should be accessing net_device
	 * except in here
	 */
	netdev_dbg(ndev, "net device safe to remove\n");

	/* Now, we can close the channel safely */
	vmbus_close(device->channel);

	/*
	 * If host is Win2016 or higher then we do the GPADL tear down
	 * here after VMBus is closed.
	*/
	if (vmbus_proto_version >= VERSION_WIN10) {
		netvsc_teardown_recv_gpadl(device, net_device, ndev);
		netvsc_teardown_send_gpadl(device, net_device, ndev);
	}

	/* Release all resources */
	free_netvsc_device_rcu(net_device);
}

#define RING_AVAIL_PERCENT_HIWATER 20
#define RING_AVAIL_PERCENT_LOWATER 10

static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
					 u32 index)
{
	sync_change_bit(index, net_device->send_section_map);
}

static void netvsc_send_tx_complete(struct net_device *ndev,
				    struct netvsc_device *net_device,
				    struct vmbus_channel *channel,
				    const struct vmpacket_descriptor *desc,
				    int budget)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct sk_buff *skb;
	u16 q_idx = 0;
	int queue_sends;
	u64 cmd_rqst;

	cmd_rqst = channel->request_addr_callback(channel, desc->trans_id);
	if (cmd_rqst == VMBUS_RQST_ERROR) {
		netdev_err(ndev, "Invalid transaction ID %llx\n", desc->trans_id);
		return;
	}

	skb = (struct sk_buff *)(unsigned long)cmd_rqst;

	/* Notify the layer above us */
	if (likely(skb)) {
		struct hv_netvsc_packet *packet
			= (struct hv_netvsc_packet *)skb->cb;
		u32 send_index = packet->send_buf_index;
		struct netvsc_stats_tx *tx_stats;

		if (send_index != NETVSC_INVALID_INDEX)
			netvsc_free_send_slot(net_device, send_index);
		q_idx = packet->q_idx;

		tx_stats = &net_device->chan_table[q_idx].tx_stats;

		u64_stats_update_begin(&tx_stats->syncp);
		tx_stats->packets += packet->total_packets;
		tx_stats->bytes += packet->total_bytes;
		u64_stats_update_end(&tx_stats->syncp);

		netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
		napi_consume_skb(skb, budget);
	}

	queue_sends =
		atomic_dec_return(&net_device->chan_table[q_idx].queue_sends);

	if (unlikely(net_device->destroy)) {
		if (queue_sends == 0)
			wake_up(&net_device->wait_drain);
	} else {
		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);

		if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
		    (hv_get_avail_to_write_percent(&channel->outbound) >
		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
			netif_tx_wake_queue(txq);
			ndev_ctx->eth_stats.wake_queue++;
		}
	}
}

static void netvsc_send_completion(struct net_device *ndev,
				   struct netvsc_device *net_device,
				   struct vmbus_channel *incoming_channel,
				   const struct vmpacket_descriptor *desc,
				   int budget)
{
	const struct nvsp_message *nvsp_packet;
	u32 msglen = hv_pkt_datalen(desc);
	struct nvsp_message *pkt_rqst;
	u64 cmd_rqst;
	u32 status;

	/* First check if this is a VMBUS completion without data payload */
	if (!msglen) {
		cmd_rqst = incoming_channel->request_addr_callback(incoming_channel,
								   desc->trans_id);
		if (cmd_rqst == VMBUS_RQST_ERROR) {
			netdev_err(ndev, "Invalid transaction ID %llx\n", desc->trans_id);
			return;
		}

		pkt_rqst = (struct nvsp_message *)(uintptr_t)cmd_rqst;
		switch (pkt_rqst->hdr.msg_type) {
		case NVSP_MSG4_TYPE_SWITCH_DATA_PATH:
			complete(&net_device->channel_init_wait);
			break;

		default:
			netdev_err(ndev, "Unexpected VMBUS completion!!\n");
		}
		return;
	}

	/* Ensure packet is big enough to read header fields */
	if (msglen < sizeof(struct nvsp_message_header)) {
		netdev_err(ndev, "nvsp_message length too small: %u\n", msglen);
		return;
	}

	nvsp_packet = hv_pkt_data(desc);
	switch (nvsp_packet->hdr.msg_type) {
	case NVSP_MSG_TYPE_INIT_COMPLETE:
		if (msglen < sizeof(struct nvsp_message_header) +
				sizeof(struct nvsp_message_init_complete)) {
			netdev_err(ndev, "nvsp_msg length too small: %u\n",
				   msglen);
			return;
		}
		fallthrough;

	case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
		if (msglen < sizeof(struct nvsp_message_header) +
				sizeof(struct nvsp_1_message_send_receive_buffer_complete)) {
			netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
				   msglen);
			return;
		}
		fallthrough;

	case NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE:
		if (msglen < sizeof(struct nvsp_message_header) +
				sizeof(struct nvsp_1_message_send_send_buffer_complete)) {
			netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
				   msglen);
			return;
		}
		fallthrough;

	case NVSP_MSG5_TYPE_SUBCHANNEL:
		if (msglen < sizeof(struct nvsp_message_header) +
				sizeof(struct nvsp_5_subchannel_complete)) {
			netdev_err(ndev, "nvsp_msg5 length too small: %u\n",
				   msglen);
			return;
		}
		/* Copy the response back */
		memcpy(&net_device->channel_init_pkt, nvsp_packet,
		       sizeof(struct nvsp_message));
		complete(&net_device->channel_init_wait);
		break;

	case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
		if (msglen < sizeof(struct nvsp_message_header) +
		    sizeof(struct nvsp_1_message_send_rndis_packet_complete)) {
			if (net_ratelimit())
				netdev_err(ndev, "nvsp_rndis_pkt_complete length too small: %u\n",
					   msglen);
			return;
		}

		/* If status indicates an error, output a message so we know
		 * there's a problem. But process the completion anyway so the
		 * resources are released.
		 */
		status = nvsp_packet->msg.v1_msg.send_rndis_pkt_complete.status;
		if (status != NVSP_STAT_SUCCESS && net_ratelimit())
			netdev_err(ndev, "nvsp_rndis_pkt_complete error status: %x\n",
				   status);

		netvsc_send_tx_complete(ndev, net_device, incoming_channel,
					desc, budget);
		break;

	default:
		netdev_err(ndev,
			   "Unknown send completion type %d received!!\n",
			   nvsp_packet->hdr.msg_type);
	}
}

static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
{
	unsigned long *map_addr = net_device->send_section_map;
	unsigned int i;

	for_each_clear_bit(i, map_addr, net_device->send_section_cnt) {
		if (sync_test_and_set_bit(i, map_addr) == 0)
			return i;
	}

	return NETVSC_INVALID_INDEX;
}

static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
				    unsigned int section_index,
				    u32 pend_size,
				    struct hv_netvsc_packet *packet,
				    struct rndis_message *rndis_msg,
				    struct hv_page_buffer *pb,
				    bool xmit_more)
{
	char *start = net_device->send_buf;
	char *dest = start + (section_index * net_device->send_section_size)
		     + pend_size;
	int i;
	u32 padding = 0;
	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
		packet->page_buf_cnt;
	u32 remain;

	/* Add padding */
	remain = packet->total_data_buflen & (net_device->pkt_align - 1);
	if (xmit_more && remain) {
		padding = net_device->pkt_align - remain;
		rndis_msg->msg_len += padding;
		packet->total_data_buflen += padding;
	}

	for (i = 0; i < page_count; i++) {
		char *src = phys_to_virt(pb[i].pfn << HV_HYP_PAGE_SHIFT);
		u32 offset = pb[i].offset;
		u32 len = pb[i].len;

		memcpy(dest, (src + offset), len);
		dest += len;
	}

	if (padding)
		memset(dest, 0, padding);
}

void netvsc_dma_unmap(struct hv_device *hv_dev,
		      struct hv_netvsc_packet *packet)
{
	int i;

	if (!hv_is_isolation_supported())
		return;

	if (!packet->dma_range)
		return;

	for (i = 0; i < packet->page_buf_cnt; i++)
		dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma,
				 packet->dma_range[i].mapping_size,
				 DMA_TO_DEVICE);

	kfree(packet->dma_range);
}

/* netvsc_dma_map - Map swiotlb bounce buffer with data page of
 * packet sent by vmbus_sendpacket_pagebuffer() in the Isolation
 * VM.
 *
 * In isolation VM, netvsc send buffer has been marked visible to
 * host and so the data copied to send buffer doesn't need to use
 * bounce buffer. The data pages handled by vmbus_sendpacket_pagebuffer()
 * may not be copied to send buffer and so these pages need to be
 * mapped with swiotlb bounce buffer. netvsc_dma_map() is to do
 * that. The pfns in the struct hv_page_buffer need to be converted
 * to bounce buffer's pfn. The loop here is necessary because the
 * entries in the page buffer array are not necessarily full
 * pages of data.  Each entry in the array has a separate offset and
 * len that may be non-zero, even for entries in the middle of the
 * array.  And the entries are not physically contiguous.  So each
 * entry must be individually mapped rather than as a contiguous unit.
 * So not use dma_map_sg() here.
 */
static int netvsc_dma_map(struct hv_device *hv_dev,
			  struct hv_netvsc_packet *packet,
			  struct hv_page_buffer *pb)
{
	u32 page_count = packet->page_buf_cnt;
	dma_addr_t dma;
	int i;

	if (!hv_is_isolation_supported())
		return 0;

	packet->dma_range = kcalloc(page_count,
				    sizeof(*packet->dma_range),
				    GFP_ATOMIC);
	if (!packet->dma_range)
		return -ENOMEM;

	for (i = 0; i < page_count; i++) {
		char *src = phys_to_virt((pb[i].pfn << HV_HYP_PAGE_SHIFT)
					 + pb[i].offset);
		u32 len = pb[i].len;

		dma = dma_map_single(&hv_dev->device, src, len,
				     DMA_TO_DEVICE);
		if (dma_mapping_error(&hv_dev->device, dma)) {
			kfree(packet->dma_range);
			return -ENOMEM;
		}

		/* pb[].offset and pb[].len are not changed during dma mapping
		 * and so not reassign.
		 */
		packet->dma_range[i].dma = dma;
		packet->dma_range[i].mapping_size = len;
		pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT;
	}

	return 0;
}

static inline int netvsc_send_pkt(
	struct hv_device *device,
	struct hv_netvsc_packet *packet,
	struct netvsc_device *net_device,
	struct hv_page_buffer *pb,
	struct sk_buff *skb)
{
	struct nvsp_message nvmsg;
	struct nvsp_1_message_send_rndis_packet *rpkt =
		&nvmsg.msg.v1_msg.send_rndis_pkt;
	struct netvsc_channel * const nvchan =
		&net_device->chan_table[packet->q_idx];
	struct vmbus_channel *out_channel = nvchan->channel;
	struct net_device *ndev = hv_get_drvdata(device);
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
	u64 req_id;
	int ret;
	u32 ring_avail = hv_get_avail_to_write_percent(&out_channel->outbound);

	memset(&nvmsg, 0, sizeof(struct nvsp_message));
	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
	if (skb)
		rpkt->channel_type = 0;		/* 0 is RMC_DATA */
	else
		rpkt->channel_type = 1;		/* 1 is RMC_CONTROL */

	rpkt->send_buf_section_index = packet->send_buf_index;
	if (packet->send_buf_index == NETVSC_INVALID_INDEX)
		rpkt->send_buf_section_size = 0;
	else
		rpkt->send_buf_section_size = packet->total_data_buflen;

	req_id = (ulong)skb;

	if (out_channel->rescind)
		return -ENODEV;

	trace_nvsp_send_pkt(ndev, out_channel, rpkt);

	packet->dma_range = NULL;
	if (packet->page_buf_cnt) {
		if (packet->cp_partial)
			pb += packet->rmsg_pgcnt;

		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
		if (ret) {
			ret = -EAGAIN;
			goto exit;
		}

		ret = vmbus_sendpacket_pagebuffer(out_channel,
						  pb, packet->page_buf_cnt,
						  &nvmsg, sizeof(nvmsg),
						  req_id);

		if (ret)
			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
	} else {
		ret = vmbus_sendpacket(out_channel,
				       &nvmsg, sizeof(nvmsg),
				       req_id, VM_PKT_DATA_INBAND,
				       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	}

exit:
	if (ret == 0) {
		atomic_inc_return(&nvchan->queue_sends);

		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
			netif_tx_stop_queue(txq);
			ndev_ctx->eth_stats.stop_queue++;
		}
	} else if (ret == -EAGAIN) {
		netif_tx_stop_queue(txq);
		ndev_ctx->eth_stats.stop_queue++;
	} else {
		netdev_err(ndev,
			   "Unable to send packet pages %u len %u, ret %d\n",
			   packet->page_buf_cnt, packet->total_data_buflen,
			   ret);
	}

	if (netif_tx_queue_stopped(txq) &&
	    atomic_read(&nvchan->queue_sends) < 1 &&
	    !net_device->tx_disable) {
		netif_tx_wake_queue(txq);
		ndev_ctx->eth_stats.wake_queue++;
		if (ret == -EAGAIN)
			ret = -ENOSPC;
	}

	return ret;
}

/* Move packet out of multi send data (msd), and clear msd */
static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
				struct sk_buff **msd_skb,
				struct multi_send_data *msdp)
{
	*msd_skb = msdp->skb;
	*msd_send = msdp->pkt;
	msdp->skb = NULL;
	msdp->pkt = NULL;
	msdp->count = 0;
}

/* RCU already held by caller */
/* Batching/bouncing logic is designed to attempt to optimize
 * performance.
 *
 * For small, non-LSO packets we copy the packet to a send buffer
 * which is pre-registered with the Hyper-V side. This enables the
 * hypervisor to avoid remapping the aperture to access the packet
 * descriptor and data.
 *
 * If we already started using a buffer and the netdev is transmitting
 * a burst of packets, keep on copying into the buffer until it is
 * full or we are done collecting a burst. If there is an existing
 * buffer with space for the RNDIS descriptor but not the packet, copy
 * the RNDIS descriptor to the buffer, keeping the packet in place.
 *
 * If we do batching and send more than one packet using a single
 * NetVSC message, free the SKBs of the packets copied, except for the
 * last packet. This is done to streamline the handling of the case
 * where the last packet only had the RNDIS descriptor copied to the
 * send buffer, with the data pointers included in the NetVSC message.
 */
int netvsc_send(struct net_device *ndev,
		struct hv_netvsc_packet *packet,
		struct rndis_message *rndis_msg,
		struct hv_page_buffer *pb,
		struct sk_buff *skb,
		bool xdp_tx)
{
	struct net_device_context *ndev_ctx = netdev_priv(ndev);
	struct netvsc_device *net_device
		= rcu_dereference_bh(ndev_ctx->nvdev);
	struct hv_device *device = ndev_ctx->device_ctx;
	int ret = 0;
	struct netvsc_channel *nvchan;
	u32 pktlen = packet->total_data_buflen, msd_len = 0;
	unsigned int section_index = NETVSC_INVALID_INDEX;
	struct multi_send_data *msdp;
	struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
	struct sk_buff *msd_skb = NULL;
	bool try_batch, xmit_more;

	/* If device is rescinded, return error and packet will get dropped. */
	if (unlikely(!net_device || net_device->destroy))
		return -ENODEV;

	nvchan = &net_device->chan_table[packet->q_idx];
	packet->send_buf_index = NETVSC_INVALID_INDEX;
	packet->cp_partial = false;

	/* Send a control message or XDP packet directly without accessing
	 * msd (Multi-Send Data) field which may be changed during data packet
	 * processing.
	 */
	if (!skb || xdp_tx)
		return netvsc_send_pkt(device, packet, net_device, pb, skb);

	/* batch packets in send buffer if possible */
	msdp = &nvchan->msd;
	if (msdp->pkt)
		msd_len = msdp->pkt->total_data_buflen;

	try_batch =  msd_len > 0 && msdp->count < net_device->max_pkt;
	if (try_batch && msd_len + pktlen + net_device->pkt_align <
	    net_device->send_section_size) {
		section_index = msdp->pkt->send_buf_index;

	} else if (try_batch && msd_len + packet->rmsg_size <
		   net_device->send_section_size) {
		section_index = msdp->pkt->send_buf_index;
		packet->cp_partial = true;

	} else if (pktlen + net_device->pkt_align <
		   net_device->send_section_size) {
		section_index = netvsc_get_next_send_section(net_device);
		if (unlikely(section_index == NETVSC_INVALID_INDEX)) {
			++ndev_ctx->eth_stats.tx_send_full;
		} else {
			move_pkt_msd(&msd_send, &msd_skb, msdp);
			msd_len = 0;
		}
	}

	/* Keep aggregating only if stack says more data is coming
	 * and not doing mixed modes send and not flow blocked
	 */
	xmit_more = netdev_xmit_more() &&
		!packet->cp_partial &&
		!netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx));

	if (section_index != NETVSC_INVALID_INDEX) {
		netvsc_copy_to_send_buf(net_device,
					section_index, msd_len,
					packet, rndis_msg, pb, xmit_more);

		packet->send_buf_index = section_index;

		if (packet->cp_partial) {
			packet->page_buf_cnt -= packet->rmsg_pgcnt;
			packet->total_data_buflen = msd_len + packet->rmsg_size;
		} else {
			packet->page_buf_cnt = 0;
			packet->total_data_buflen += msd_len;
		}

		if (msdp->pkt) {
			packet->total_packets += msdp->pkt->total_packets;
			packet->total_bytes += msdp->pkt->total_bytes;
		}

		if (msdp->skb)
			dev_consume_skb_any(msdp->skb);

		if (xmit_more) {
			msdp->skb = skb;
			msdp->pkt = packet;
			msdp->count++;
		} else {
			cur_send = packet;
			msdp->skb = NULL;
			msdp->pkt = NULL;
			msdp->count = 0;
		}
	} else {
		move_pkt_msd(&msd_send, &msd_skb, msdp);
		cur_send = packet;
	}

	if (msd_send) {
		int m_ret = netvsc_send_pkt(device, msd_send, net_device,
					    NULL, msd_skb);

		if (m_ret != 0) {
			netvsc_free_send_slot(net_device,
					      msd_send->send_buf_index);
			dev_kfree_skb_any(msd_skb);
		}
	}

	if (cur_send)
		ret = netvsc_send_pkt(device, cur_send, net_device, pb, skb);

	if (ret != 0 && section_index != NETVSC_INVALID_INDEX)
		netvsc_free_send_slot(net_device, section_index);

	return ret;
}

/* Send pending recv completions */
static int send_recv_completions(struct net_device *ndev,
				 struct netvsc_device *nvdev,
				 struct netvsc_channel *nvchan)
{
	struct multi_recv_comp *mrc = &nvchan->mrc;
	struct recv_comp_msg {
		struct nvsp_message_header hdr;
		u32 status;
	}  __packed;
	struct recv_comp_msg msg = {
		.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE,
	};
	int ret;

	while (mrc->first != mrc->next) {
		const struct recv_comp_data *rcd
			= mrc->slots + mrc->first;

		msg.status = rcd->status;
		ret = vmbus_sendpacket(nvchan->channel, &msg, sizeof(msg),
				       rcd->tid, VM_PKT_COMP, 0);
		if (unlikely(ret)) {
			struct net_device_context *ndev_ctx = netdev_priv(ndev);

			++ndev_ctx->eth_stats.rx_comp_busy;
			return ret;
		}

		if (++mrc->first == nvdev->recv_completion_cnt)
			mrc->first = 0;
	}

	/* receive completion ring has been emptied */
	if (unlikely(nvdev->destroy))
		wake_up(&nvdev->wait_drain);

	return 0;
}

/* Count how many receive completions are outstanding */
static void recv_comp_slot_avail(const struct netvsc_device *nvdev,
				 const struct multi_recv_comp *mrc,
				 u32 *filled, u32 *avail)
{
	u32 count = nvdev->recv_completion_cnt;

	if (mrc->next >= mrc->first)
		*filled = mrc->next - mrc->first;
	else
		*filled = (count - mrc->first) + mrc->next;

	*avail = count - *filled - 1;
}

/* Add receive complete to ring to send to host. */
static void enq_receive_complete(struct net_device *ndev,
				 struct netvsc_device *nvdev, u16 q_idx,
				 u64 tid, u32 status)
{
	struct netvsc_channel *nvchan = &nvdev->chan_table[q_idx];
	struct multi_recv_comp *mrc = &nvchan->mrc;
	struct recv_comp_data *rcd;
	u32 filled, avail;

	recv_comp_slot_avail(nvdev, mrc, &filled, &avail);

	if (unlikely(filled > NAPI_POLL_WEIGHT)) {
		send_recv_completions(ndev, nvdev, nvchan);
		recv_comp_slot_avail(nvdev, mrc, &filled, &avail);
	}

	if (unlikely(!avail)) {
		netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
			   q_idx, tid);
		return;
	}

	rcd = mrc->slots + mrc->next;
	rcd->tid = tid;
	rcd->status = status;

	if (++mrc->next == nvdev->recv_completion_cnt)
		mrc->next = 0;
}

static int netvsc_receive(struct net_device *ndev,
			  struct netvsc_device *net_device,
			  struct netvsc_channel *nvchan,
			  const struct vmpacket_descriptor *desc)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct vmbus_channel *channel = nvchan->channel;
	const struct vmtransfer_page_packet_header *vmxferpage_packet
		= container_of(desc, const struct vmtransfer_page_packet_header, d);
	const struct nvsp_message *nvsp = hv_pkt_data(desc);
	u32 msglen = hv_pkt_datalen(desc);
	u16 q_idx = channel->offermsg.offer.sub_channel_index;
	char *recv_buf = net_device->recv_buf;
	u32 status = NVSP_STAT_SUCCESS;
	int i;
	int count = 0;

	/* Ensure packet is big enough to read header fields */
	if (msglen < sizeof(struct nvsp_message_header)) {
		netif_err(net_device_ctx, rx_err, ndev,
			  "invalid nvsp header, length too small: %u\n",
			  msglen);
		return 0;
	}

	/* Make sure this is a valid nvsp packet */
	if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) {
		netif_err(net_device_ctx, rx_err, ndev,
			  "Unknown nvsp packet type received %u\n",
			  nvsp->hdr.msg_type);
		return 0;
	}

	/* Validate xfer page pkt header */
	if ((desc->offset8 << 3) < sizeof(struct vmtransfer_page_packet_header)) {
		netif_err(net_device_ctx, rx_err, ndev,
			  "Invalid xfer page pkt, offset too small: %u\n",
			  desc->offset8 << 3);
		return 0;
	}

	if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) {
		netif_err(net_device_ctx, rx_err, ndev,
			  "Invalid xfer page set id - expecting %x got %x\n",
			  NETVSC_RECEIVE_BUFFER_ID,
			  vmxferpage_packet->xfer_pageset_id);
		return 0;
	}

	count = vmxferpage_packet->range_cnt;

	/* Check count for a valid value */
	if (NETVSC_XFER_HEADER_SIZE(count) > desc->offset8 << 3) {
		netif_err(net_device_ctx, rx_err, ndev,
			  "Range count is not valid: %d\n",
			  count);
		return 0;
	}

	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
	for (i = 0; i < count; i++) {
		u32 offset = vmxferpage_packet->ranges[i].byte_offset;
		u32 buflen = vmxferpage_packet->ranges[i].byte_count;
		void *data;
		int ret;

		if (unlikely(offset > net_device->recv_buf_size ||
			     buflen > net_device->recv_buf_size - offset)) {
			nvchan->rsc.cnt = 0;
			status = NVSP_STAT_FAIL;
			netif_err(net_device_ctx, rx_err, ndev,
				  "Packet offset:%u + len:%u too big\n",
				  offset, buflen);

			continue;
		}

		/* We're going to copy (sections of) the packet into nvchan->recv_buf;
		 * make sure that nvchan->recv_buf is large enough to hold the packet.
		 */
		if (unlikely(buflen > net_device->recv_section_size)) {
			nvchan->rsc.cnt = 0;
			status = NVSP_STAT_FAIL;
			netif_err(net_device_ctx, rx_err, ndev,
				  "Packet too big: buflen=%u recv_section_size=%u\n",
				  buflen, net_device->recv_section_size);

			continue;
		}

		data = recv_buf + offset;

		nvchan->rsc.is_last = (i == count - 1);

		trace_rndis_recv(ndev, q_idx, data);

		/* Pass it to the upper layer */
		ret = rndis_filter_receive(ndev, net_device,
					   nvchan, data, buflen);

		if (unlikely(ret != NVSP_STAT_SUCCESS)) {
			/* Drop incomplete packet */
			nvchan->rsc.cnt = 0;
			status = NVSP_STAT_FAIL;
		}
	}

	enq_receive_complete(ndev, net_device, q_idx,
			     vmxferpage_packet->d.trans_id, status);

	return count;
}

static void netvsc_send_table(struct net_device *ndev,
			      struct netvsc_device *nvscdev,
			      const struct nvsp_message *nvmsg,
			      u32 msglen)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	u32 count, offset, *tab;
	int i;

	/* Ensure packet is big enough to read send_table fields */
	if (msglen < sizeof(struct nvsp_message_header) +
		     sizeof(struct nvsp_5_send_indirect_table)) {
		netdev_err(ndev, "nvsp_v5_msg length too small: %u\n", msglen);
		return;
	}

	count = nvmsg->msg.v5_msg.send_table.count;
	offset = nvmsg->msg.v5_msg.send_table.offset;

	if (count != VRSS_SEND_TAB_SIZE) {
		netdev_err(ndev, "Received wrong send-table size:%u\n", count);
		return;
	}

	/* If negotiated version <= NVSP_PROTOCOL_VERSION_6, the offset may be
	 * wrong due to a host bug. So fix the offset here.
	 */
	if (nvscdev->nvsp_version <= NVSP_PROTOCOL_VERSION_6 &&
	    msglen >= sizeof(struct nvsp_message_header) +
	    sizeof(union nvsp_6_message_uber) + count * sizeof(u32))
		offset = sizeof(struct nvsp_message_header) +
			 sizeof(union nvsp_6_message_uber);

	/* Boundary check for all versions */
	if (msglen < count * sizeof(u32) || offset > msglen - count * sizeof(u32)) {
		netdev_err(ndev, "Received send-table offset too big:%u\n",
			   offset);
		return;
	}

	tab = (void *)nvmsg + offset;

	for (i = 0; i < count; i++)
		net_device_ctx->tx_table[i] = tab[i];
}

static void netvsc_send_vf(struct net_device *ndev,
			   const struct nvsp_message *nvmsg,
			   u32 msglen)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);

	/* Ensure packet is big enough to read its fields */
	if (msglen < sizeof(struct nvsp_message_header) +
		     sizeof(struct nvsp_4_send_vf_association)) {
		netdev_err(ndev, "nvsp_v4_msg length too small: %u\n", msglen);
		return;
	}

	net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
	net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;

	if (net_device_ctx->vf_alloc)
		complete(&net_device_ctx->vf_add);

	netdev_info(ndev, "VF slot %u %s\n",
		    net_device_ctx->vf_serial,
		    net_device_ctx->vf_alloc ? "added" : "removed");
}

static void netvsc_receive_inband(struct net_device *ndev,
				  struct netvsc_device *nvscdev,
				  const struct vmpacket_descriptor *desc)
{
	const struct nvsp_message *nvmsg = hv_pkt_data(desc);
	u32 msglen = hv_pkt_datalen(desc);

	/* Ensure packet is big enough to read header fields */
	if (msglen < sizeof(struct nvsp_message_header)) {
		netdev_err(ndev, "inband nvsp_message length too small: %u\n", msglen);
		return;
	}

	switch (nvmsg->hdr.msg_type) {
	case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE:
		netvsc_send_table(ndev, nvscdev, nvmsg, msglen);
		break;

	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
		if (hv_is_isolation_supported())
			netdev_err(ndev, "Ignore VF_ASSOCIATION msg from the host supporting isolation\n");
		else
			netvsc_send_vf(ndev, nvmsg, msglen);
		break;
	}
}

static int netvsc_process_raw_pkt(struct hv_device *device,
				  struct netvsc_channel *nvchan,
				  struct netvsc_device *net_device,
				  struct net_device *ndev,
				  const struct vmpacket_descriptor *desc,
				  int budget)
{
	struct vmbus_channel *channel = nvchan->channel;
	const struct nvsp_message *nvmsg = hv_pkt_data(desc);

	trace_nvsp_recv(ndev, channel, nvmsg);

	switch (desc->type) {
	case VM_PKT_COMP:
		netvsc_send_completion(ndev, net_device, channel, desc, budget);
		break;

	case VM_PKT_DATA_USING_XFER_PAGES:
		return netvsc_receive(ndev, net_device, nvchan, desc);

	case VM_PKT_DATA_INBAND:
		netvsc_receive_inband(ndev, net_device, desc);
		break;

	default:
		netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
			   desc->type, desc->trans_id);
		break;
	}

	return 0;
}

static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel)
{
	struct vmbus_channel *primary = channel->primary_channel;

	return primary ? primary->device_obj : channel->device_obj;
}

/* Network processing softirq
 * Process data in incoming ring buffer from host
 * Stops when ring is empty or budget is met or exceeded.
 */
int netvsc_poll(struct napi_struct *napi, int budget)
{
	struct netvsc_channel *nvchan
		= container_of(napi, struct netvsc_channel, napi);
	struct netvsc_device *net_device = nvchan->net_device;
	struct vmbus_channel *channel = nvchan->channel;
	struct hv_device *device = netvsc_channel_to_device(channel);
	struct net_device *ndev = hv_get_drvdata(device);
	int work_done = 0;
	int ret;

	/* If starting a new interval */
	if (!nvchan->desc)
		nvchan->desc = hv_pkt_iter_first(channel);

	nvchan->xdp_flush = false;

	while (nvchan->desc && work_done < budget) {
		work_done += netvsc_process_raw_pkt(device, nvchan, net_device,
						    ndev, nvchan->desc, budget);
		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
	}

	if (nvchan->xdp_flush)
		xdp_do_flush();

	/* Send any pending receive completions */
	ret = send_recv_completions(ndev, net_device, nvchan);

	/* If it did not exhaust NAPI budget this time
	 *  and not doing busy poll
	 * then re-enable host interrupts
	 *  and reschedule if ring is not empty
	 *   or sending receive completion failed.
	 */
	if (work_done < budget &&
	    napi_complete_done(napi, work_done) &&
	    (ret || hv_end_read(&channel->inbound)) &&
	    napi_schedule_prep(napi)) {
		hv_begin_read(&channel->inbound);
		__napi_schedule(napi);
	}

	/* Driver may overshoot since multiple packets per descriptor */
	return min(work_done, budget);
}

/* Call back when data is available in host ring buffer.
 * Processing is deferred until network softirq (NAPI)
 */
void netvsc_channel_cb(void *context)
{
	struct netvsc_channel *nvchan = context;
	struct vmbus_channel *channel = nvchan->channel;
	struct hv_ring_buffer_info *rbi = &channel->inbound;

	/* preload first vmpacket descriptor */
	prefetch(hv_get_ring_buffer(rbi) + rbi->priv_read_index);

	if (napi_schedule_prep(&nvchan->napi)) {
		/* disable interrupts from host */
		hv_begin_read(rbi);

		__napi_schedule_irqoff(&nvchan->napi);
	}
}

/*
 * netvsc_device_add - Callback when the device belonging to this
 * driver is added
 */
struct netvsc_device *netvsc_device_add(struct hv_device *device,
				const struct netvsc_device_info *device_info)
{
	int i, ret = 0;
	struct netvsc_device *net_device;
	struct net_device *ndev = hv_get_drvdata(device);
	struct net_device_context *net_device_ctx = netdev_priv(ndev);

	net_device = alloc_net_device();
	if (!net_device)
		return ERR_PTR(-ENOMEM);

	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
		net_device_ctx->tx_table[i] = 0;

	/* Because the device uses NAPI, all the interrupt batching and
	 * control is done via Net softirq, not the channel handling
	 */
	set_channel_read_mode(device->channel, HV_CALL_ISR);

	/* If we're reopening the device we may have multiple queues, fill the
	 * chn_table with the default channel to use it before subchannels are
	 * opened.
	 * Initialize the channel state before we open;
	 * we can be interrupted as soon as we open the channel.
	 */

	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
		struct netvsc_channel *nvchan = &net_device->chan_table[i];

		nvchan->channel = device->channel;
		nvchan->net_device = net_device;
		u64_stats_init(&nvchan->tx_stats.syncp);
		u64_stats_init(&nvchan->rx_stats.syncp);

		ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i, 0);

		if (ret) {
			netdev_err(ndev, "xdp_rxq_info_reg fail: %d\n", ret);
			goto cleanup2;
		}

		ret = xdp_rxq_info_reg_mem_model(&nvchan->xdp_rxq,
						 MEM_TYPE_PAGE_SHARED, NULL);

		if (ret) {
			netdev_err(ndev, "xdp reg_mem_model fail: %d\n", ret);
			goto cleanup2;
		}
	}

	/* Enable NAPI handler before init callbacks */
	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);

	/* Open the channel */
	device->channel->next_request_id_callback = vmbus_next_request_id;
	device->channel->request_addr_callback = vmbus_request_addr;
	device->channel->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
	device->channel->max_pkt_size = NETVSC_MAX_PKT_SIZE;

	ret = vmbus_open(device->channel, netvsc_ring_bytes,
			 netvsc_ring_bytes,  NULL, 0,
			 netvsc_channel_cb, net_device->chan_table);

	if (ret != 0) {
		netdev_err(ndev, "unable to open channel: %d\n", ret);
		goto cleanup;
	}

	/* Channel is opened */
	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");

	napi_enable(&net_device->chan_table[0].napi);

	/* Connect with the NetVsp */
	ret = netvsc_connect_vsp(device, net_device, device_info);
	if (ret != 0) {
		netdev_err(ndev,
			"unable to connect to NetVSP - %d\n", ret);
		goto close;
	}

	/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
	 * populated.
	 */
	rcu_assign_pointer(net_device_ctx->nvdev, net_device);

	return net_device;

close:
	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
	napi_disable(&net_device->chan_table[0].napi);

	/* Now, we can close the channel safely */
	vmbus_close(device->channel);

cleanup:
	netif_napi_del(&net_device->chan_table[0].napi);

cleanup2:
	free_netvsc_device(&net_device->rcu);

	return ERR_PTR(ret);
}