summaryrefslogtreecommitdiff
path: root/drivers/net/hyperv/netvsc.c
blob: 06de98a056228261a9df982421c4137827dfda01 (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
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, see <http://www.gnu.org/licenses/>.
 *
 * 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 <asm/sync_bitops.h>

#include "hyperv_net.h"


static struct netvsc_device *alloc_net_device(struct hv_device *device)
{
	struct netvsc_device *net_device;
	struct net_device *ndev = hv_get_drvdata(device);
	int i;

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

	net_device->cb_buffer = kzalloc(NETVSC_PACKET_SIZE, GFP_KERNEL);
	if (!net_device->cb_buffer) {
		kfree(net_device);
		return NULL;
	}

	init_waitqueue_head(&net_device->wait_drain);
	net_device->start_remove = false;
	net_device->destroy = false;
	net_device->dev = device;
	net_device->ndev = ndev;
	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;

	for (i = 0; i < num_online_cpus(); i++)
		spin_lock_init(&net_device->msd[i].lock);

	hv_set_drvdata(device, net_device);
	return net_device;
}

static void free_netvsc_device(struct netvsc_device *nvdev)
{
	kfree(nvdev->cb_buffer);
	kfree(nvdev);
}

static struct netvsc_device *get_outbound_net_device(struct hv_device *device)
{
	struct netvsc_device *net_device;

	net_device = hv_get_drvdata(device);
	if (net_device && net_device->destroy)
		net_device = NULL;

	return net_device;
}

static struct netvsc_device *get_inbound_net_device(struct hv_device *device)
{
	struct netvsc_device *net_device;

	net_device = hv_get_drvdata(device);

	if (!net_device)
		goto get_in_err;

	if (net_device->destroy &&
		atomic_read(&net_device->num_outstanding_sends) == 0)
		net_device = NULL;

get_in_err:
	return net_device;
}


static int netvsc_destroy_buf(struct netvsc_device *net_device)
{
	struct nvsp_message *revoke_packet;
	int ret = 0;
	struct net_device *ndev = net_device->ndev;

	/*
	 * 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;

		ret = vmbus_sendpacket(net_device->dev->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       (unsigned long)revoke_packet,
				       VM_PKT_DATA_INBAND, 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 ret;
		}
	}

	/* Teardown the gpadl on the vsp end */
	if (net_device->recv_buf_gpadl_handle) {
		ret = vmbus_teardown_gpadl(net_device->dev->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 ret;
		}
		net_device->recv_buf_gpadl_handle = 0;
	}

	if (net_device->recv_buf) {
		/* Free up the receive buffer */
		vfree(net_device->recv_buf);
		net_device->recv_buf = NULL;
	}

	if (net_device->recv_section) {
		net_device->recv_section_cnt = 0;
		kfree(net_device->recv_section);
		net_device->recv_section = NULL;
	}

	/* 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_size) {
		/* 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;

		ret = vmbus_sendpacket(net_device->dev->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       (unsigned long)revoke_packet,
				       VM_PKT_DATA_INBAND, 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 ret;
		}
	}
	/* Teardown the gpadl on the vsp end */
	if (net_device->send_buf_gpadl_handle) {
		ret = vmbus_teardown_gpadl(net_device->dev->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 ret;
		}
		net_device->send_buf_gpadl_handle = 0;
	}
	if (net_device->send_buf) {
		/* Free up the send buffer */
		vfree(net_device->send_buf);
		net_device->send_buf = NULL;
	}
	kfree(net_device->send_section_map);

	return ret;
}

static int netvsc_init_buf(struct hv_device *device)
{
	int ret = 0;
	unsigned long t;
	struct netvsc_device *net_device;
	struct nvsp_message *init_packet;
	struct net_device *ndev;
	int node;

	net_device = get_outbound_net_device(device);
	if (!net_device)
		return -ENODEV;
	ndev = net_device->ndev;

	node = cpu_to_node(device->channel->target_cpu);
	net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node);
	if (!net_device->recv_buf)
		net_device->recv_buf = vzalloc(net_device->recv_buf_size);

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

	/*
	 * 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,
				    net_device->recv_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;
	init_packet->msg.v1_msg.
		send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;

	/* 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;
	}

	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
	BUG_ON(t == 0);


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

	/* Parse the response */

	net_device->recv_section_cnt = init_packet->msg.
		v1_msg.send_recv_buf_complete.num_sections;

	net_device->recv_section = kmemdup(
		init_packet->msg.v1_msg.send_recv_buf_complete.sections,
		net_device->recv_section_cnt *
		sizeof(struct nvsp_1_receive_buffer_section),
		GFP_KERNEL);
	if (net_device->recv_section == NULL) {
		ret = -EINVAL;
		goto cleanup;
	}

	/*
	 * For 1st release, there should only be 1 section that represents the
	 * entire receive buffer
	 */
	if (net_device->recv_section_cnt != 1 ||
	    net_device->recv_section->offset != 0) {
		ret = -EINVAL;
		goto cleanup;
	}

	/* Now setup the send buffer.
	 */
	net_device->send_buf = vzalloc_node(net_device->send_buf_size, node);
	if (!net_device->send_buf)
		net_device->send_buf = vzalloc(net_device->send_buf_size);
	if (!net_device->send_buf) {
		netdev_err(ndev, "unable to allocate send "
			   "buffer of size %d\n", net_device->send_buf_size);
		ret = -ENOMEM;
		goto cleanup;
	}

	/* 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,
				    net_device->send_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;
	init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID;

	/* 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;
	}

	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
	BUG_ON(t == 0);

	/* 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;

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

	dev_info(&device->device, "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->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
					     BITS_PER_LONG);

	net_device->send_section_map =
		kzalloc(net_device->map_words * sizeof(ulong), GFP_KERNEL);
	if (net_device->send_section_map == NULL) {
		ret = -ENOMEM;
		goto cleanup;
	}

	goto exit;

cleanup:
	netvsc_destroy_buf(net_device);

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)
{
	int ret;
	unsigned long t;

	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;

	/* 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;

	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);

	if (t == 0)
		return -ETIMEDOUT;

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

	if (nvsp_ver == NVSP_PROTOCOL_VERSION_1)
		return 0;

	/* NVSPv2 only: 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 = net_device->ndev->mtu +
						       ETH_HLEN;
	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;

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

	return ret;
}

static int netvsc_connect_vsp(struct hv_device *device)
{
	int ret;
	struct netvsc_device *net_device;
	struct nvsp_message *init_packet;
	int ndis_version;
	struct net_device *ndev;
	u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
		NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 };
	int i, num_ver = 4; /* number of different NVSP versions */

	net_device = get_outbound_net_device(device);
	if (!net_device)
		return -ENODEV;
	ndev = net_device->ndev;

	init_packet = &net_device->channel_init_pkt;

	/* Negotiate the latest NVSP protocol supported */
	for (i = num_ver - 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;
	}

	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;

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

	/* Post the big receive buffer to NetVSP */
	if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
	else
		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
	net_device->send_buf_size = NETVSC_SEND_BUFFER_SIZE;

	ret = netvsc_init_buf(device);

cleanup:
	return ret;
}

static void netvsc_disconnect_vsp(struct netvsc_device *net_device)
{
	netvsc_destroy_buf(net_device);
}

/*
 * netvsc_device_remove - Callback when the root bus device is removed
 */
int netvsc_device_remove(struct hv_device *device)
{
	struct netvsc_device *net_device;
	unsigned long flags;

	net_device = hv_get_drvdata(device);

	netvsc_disconnect_vsp(net_device);

	/*
	 * Since we have already drained, we don't need to busy wait
	 * as was done in final_release_stor_device()
	 * Note that we cannot set the ext pointer to NULL until
	 * we have drained - to drain the outgoing packets, we need to
	 * allow incoming packets.
	 */

	spin_lock_irqsave(&device->channel->inbound_lock, flags);
	hv_set_drvdata(device, NULL);
	spin_unlock_irqrestore(&device->channel->inbound_lock, flags);

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

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

	/* Release all resources */
	vfree(net_device->sub_cb_buf);
	free_netvsc_device(net_device);
	return 0;
}


#define RING_AVAIL_PERCENT_HIWATER 20
#define RING_AVAIL_PERCENT_LOWATER 10

/*
 * Get the percentage of available bytes to write in the ring.
 * The return value is in range from 0 to 100.
 */
static inline u32 hv_ringbuf_avail_percent(
		struct hv_ring_buffer_info *ring_info)
{
	u32 avail_read, avail_write;

	hv_get_ringbuffer_availbytes(ring_info, &avail_read, &avail_write);

	return avail_write * 100 / ring_info->ring_datasize;
}

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_completion(struct netvsc_device *net_device,
				   struct hv_device *device,
				   struct vmpacket_descriptor *packet)
{
	struct nvsp_message *nvsp_packet;
	struct hv_netvsc_packet *nvsc_packet;
	struct net_device *ndev;
	u32 send_index;

	ndev = net_device->ndev;

	nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
			(packet->offset8 << 3));

	if ((nvsp_packet->hdr.msg_type == NVSP_MSG_TYPE_INIT_COMPLETE) ||
	    (nvsp_packet->hdr.msg_type ==
	     NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE) ||
	    (nvsp_packet->hdr.msg_type ==
	     NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE) ||
	    (nvsp_packet->hdr.msg_type ==
	     NVSP_MSG5_TYPE_SUBCHANNEL)) {
		/* Copy the response back */
		memcpy(&net_device->channel_init_pkt, nvsp_packet,
		       sizeof(struct nvsp_message));
		complete(&net_device->channel_init_wait);
	} else if (nvsp_packet->hdr.msg_type ==
		   NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE) {
		int num_outstanding_sends;
		u16 q_idx = 0;
		struct vmbus_channel *channel = device->channel;
		int queue_sends;

		/* Get the send context */
		nvsc_packet = (struct hv_netvsc_packet *)(unsigned long)
			packet->trans_id;

		/* Notify the layer above us */
		if (nvsc_packet) {
			send_index = nvsc_packet->send_buf_index;
			if (send_index != NETVSC_INVALID_INDEX)
				netvsc_free_send_slot(net_device, send_index);
			q_idx = nvsc_packet->q_idx;
			channel = nvsc_packet->channel;
			nvsc_packet->send_completion(nvsc_packet->
						     send_completion_ctx);
		}

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

		if (net_device->destroy && num_outstanding_sends == 0)
			wake_up(&net_device->wait_drain);

		if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
		    !net_device->start_remove &&
		    (hv_ringbuf_avail_percent(&channel->outbound) >
		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1))
				netif_tx_wake_queue(netdev_get_tx_queue(
						    ndev, q_idx));
	} else {
		netdev_err(ndev, "Unknown send completion packet type- "
			   "%d received!!\n", nvsp_packet->hdr.msg_type);
	}

}

static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
{
	unsigned long index;
	u32 max_words = net_device->map_words;
	unsigned long *map_addr = (unsigned long *)net_device->send_section_map;
	u32 section_cnt = net_device->send_section_cnt;
	int ret_val = NETVSC_INVALID_INDEX;
	int i;
	int prev_val;

	for (i = 0; i < max_words; i++) {
		if (!~(map_addr[i]))
			continue;
		index = ffz(map_addr[i]);
		prev_val = sync_test_and_set_bit(index, &map_addr[i]);
		if (prev_val)
			continue;
		if ((index + (i * BITS_PER_LONG)) >= section_cnt)
			break;
		ret_val = (index + (i * BITS_PER_LONG));
		break;
	}
	return ret_val;
}

static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
				   unsigned int section_index,
				   u32 pend_size,
				   struct hv_netvsc_packet *packet)
{
	char *start = net_device->send_buf;
	char *dest = start + (section_index * net_device->send_section_size)
		     + pend_size;
	int i;
	u32 msg_size = 0;
	u32 padding = 0;
	u32 remain = packet->total_data_buflen % net_device->pkt_align;
	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
		packet->page_buf_cnt;

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

	for (i = 0; i < page_count; i++) {
		char *src = phys_to_virt(packet->page_buf[i].pfn << PAGE_SHIFT);
		u32 offset = packet->page_buf[i].offset;
		u32 len = packet->page_buf[i].len;

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

	if (padding) {
		memset(dest, 0, padding);
		msg_size += padding;
	}

	return msg_size;
}

static inline int netvsc_send_pkt(
	struct hv_netvsc_packet *packet,
	struct netvsc_device *net_device)
{
	struct nvsp_message nvmsg;
	struct vmbus_channel *out_channel = packet->channel;
	u16 q_idx = packet->q_idx;
	struct net_device *ndev = net_device->ndev;
	u64 req_id;
	int ret;
	struct hv_page_buffer *pgbuf;
	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);

	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
	if (packet->is_data_pkt) {
		/* 0 is RMC_DATA; */
		nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 0;
	} else {
		/* 1 is RMC_CONTROL; */
		nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 1;
	}

	nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_index =
		packet->send_buf_index;
	if (packet->send_buf_index == NETVSC_INVALID_INDEX)
		nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0;
	else
		nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size =
			packet->total_data_buflen;

	if (packet->send_completion)
		req_id = (ulong)packet;
	else
		req_id = 0;

	if (out_channel->rescind)
		return -ENODEV;

	/*
	 * It is possible that once we successfully place this packet
	 * on the ringbuffer, we may stop the queue. In that case, we want
	 * to notify the host independent of the xmit_more flag. We don't
	 * need to be precise here; in the worst case we may signal the host
	 * unnecessarily.
	 */
	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
		packet->xmit_more = false;

	if (packet->page_buf_cnt) {
		pgbuf = packet->cp_partial ? packet->page_buf +
			packet->rmsg_pgcnt : packet->page_buf;
		ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
						      pgbuf,
						      packet->page_buf_cnt,
						      &nvmsg,
						      sizeof(struct nvsp_message),
						      req_id,
						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
						      !packet->xmit_more);
	} else {
		ret = vmbus_sendpacket_ctl(out_channel, &nvmsg,
					   sizeof(struct nvsp_message),
					   req_id,
					   VM_PKT_DATA_INBAND,
					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
					   !packet->xmit_more);
	}

	if (ret == 0) {
		atomic_inc(&net_device->num_outstanding_sends);
		atomic_inc(&net_device->queue_sends[q_idx]);

		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
			netif_tx_stop_queue(netdev_get_tx_queue(ndev, q_idx));

			if (atomic_read(&net_device->
				queue_sends[q_idx]) < 1)
				netif_tx_wake_queue(netdev_get_tx_queue(
						    ndev, q_idx));
		}
	} else if (ret == -EAGAIN) {
		netif_tx_stop_queue(netdev_get_tx_queue(
				    ndev, q_idx));
		if (atomic_read(&net_device->queue_sends[q_idx]) < 1) {
			netif_tx_wake_queue(netdev_get_tx_queue(
					    ndev, q_idx));
			ret = -ENOSPC;
		}
	} else {
		netdev_err(ndev, "Unable to send packet %p ret %d\n",
			   packet, ret);
	}

	return ret;
}

int netvsc_send(struct hv_device *device,
		struct hv_netvsc_packet *packet)
{
	struct netvsc_device *net_device;
	int ret = 0, m_ret = 0;
	struct vmbus_channel *out_channel;
	u16 q_idx = packet->q_idx;
	u32 pktlen = packet->total_data_buflen, msd_len = 0;
	unsigned int section_index = NETVSC_INVALID_INDEX;
	unsigned long flag;
	struct multi_send_data *msdp;
	struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
	bool try_batch;

	net_device = get_outbound_net_device(device);
	if (!net_device)
		return -ENODEV;

	out_channel = net_device->chn_table[q_idx];
	if (!out_channel) {
		out_channel = device->channel;
		q_idx = 0;
		packet->q_idx = 0;
	}
	packet->channel = out_channel;
	packet->send_buf_index = NETVSC_INVALID_INDEX;
	packet->cp_partial = false;

	msdp = &net_device->msd[q_idx];

	/* batch packets in send buffer if possible */
	spin_lock_irqsave(&msdp->lock, flag);
	if (msdp->pkt)
		msd_len = msdp->pkt->total_data_buflen;

	try_batch = packet->is_data_pkt && 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 (packet->is_data_pkt && pktlen + net_device->pkt_align <
		   net_device->send_section_size) {
		section_index = netvsc_get_next_send_section(net_device);
		if (section_index != NETVSC_INVALID_INDEX) {
				msd_send = msdp->pkt;
				msdp->pkt = NULL;
				msdp->count = 0;
				msd_len = 0;
		}
	}

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

		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)
			netvsc_xmit_completion(msdp->pkt);

		if (packet->xmit_more && !packet->cp_partial) {
			msdp->pkt = packet;
			msdp->count++;
		} else {
			cur_send = packet;
			msdp->pkt = NULL;
			msdp->count = 0;
		}
	} else {
		msd_send = msdp->pkt;
		msdp->pkt = NULL;
		msdp->count = 0;
		cur_send = packet;
	}

	spin_unlock_irqrestore(&msdp->lock, flag);

	if (msd_send) {
		m_ret = netvsc_send_pkt(msd_send, net_device);

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

	if (cur_send)
		ret = netvsc_send_pkt(cur_send, net_device);

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

	return ret;
}

static void netvsc_send_recv_completion(struct hv_device *device,
					struct vmbus_channel *channel,
					struct netvsc_device *net_device,
					u64 transaction_id, u32 status)
{
	struct nvsp_message recvcompMessage;
	int retries = 0;
	int ret;
	struct net_device *ndev;

	ndev = net_device->ndev;

	recvcompMessage.hdr.msg_type =
				NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE;

	recvcompMessage.msg.v1_msg.send_rndis_pkt_complete.status = status;

retry_send_cmplt:
	/* Send the completion */
	ret = vmbus_sendpacket(channel, &recvcompMessage,
			       sizeof(struct nvsp_message), transaction_id,
			       VM_PKT_COMP, 0);
	if (ret == 0) {
		/* success */
		/* no-op */
	} else if (ret == -EAGAIN) {
		/* no more room...wait a bit and attempt to retry 3 times */
		retries++;
		netdev_err(ndev, "unable to send receive completion pkt"
			" (tid %llx)...retrying %d\n", transaction_id, retries);

		if (retries < 4) {
			udelay(100);
			goto retry_send_cmplt;
		} else {
			netdev_err(ndev, "unable to send receive "
				"completion pkt (tid %llx)...give up retrying\n",
				transaction_id);
		}
	} else {
		netdev_err(ndev, "unable to send receive "
			"completion pkt - %llx\n", transaction_id);
	}
}

static void netvsc_receive(struct netvsc_device *net_device,
			struct vmbus_channel *channel,
			struct hv_device *device,
			struct vmpacket_descriptor *packet)
{
	struct vmtransfer_page_packet_header *vmxferpage_packet;
	struct nvsp_message *nvsp_packet;
	struct hv_netvsc_packet nv_pkt;
	struct hv_netvsc_packet *netvsc_packet = &nv_pkt;
	u32 status = NVSP_STAT_SUCCESS;
	int i;
	int count = 0;
	struct net_device *ndev;

	ndev = net_device->ndev;

	/*
	 * All inbound packets other than send completion should be xfer page
	 * packet
	 */
	if (packet->type != VM_PKT_DATA_USING_XFER_PAGES) {
		netdev_err(ndev, "Unknown packet type received - %d\n",
			   packet->type);
		return;
	}

	nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
			(packet->offset8 << 3));

	/* Make sure this is a valid nvsp packet */
	if (nvsp_packet->hdr.msg_type !=
	    NVSP_MSG1_TYPE_SEND_RNDIS_PKT) {
		netdev_err(ndev, "Unknown nvsp packet type received-"
			" %d\n", nvsp_packet->hdr.msg_type);
		return;
	}

	vmxferpage_packet = (struct vmtransfer_page_packet_header *)packet;

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

	count = vmxferpage_packet->range_cnt;
	netvsc_packet->channel = channel;

	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
	for (i = 0; i < count; i++) {
		/* Initialize the netvsc packet */
		netvsc_packet->status = NVSP_STAT_SUCCESS;
		netvsc_packet->data = (void *)((unsigned long)net_device->
			recv_buf + vmxferpage_packet->ranges[i].byte_offset);
		netvsc_packet->total_data_buflen =
					vmxferpage_packet->ranges[i].byte_count;

		/* Pass it to the upper layer */
		rndis_filter_receive(device, netvsc_packet);

		if (netvsc_packet->status != NVSP_STAT_SUCCESS)
			status = NVSP_STAT_FAIL;
	}

	netvsc_send_recv_completion(device, channel, net_device,
				    vmxferpage_packet->d.trans_id, status);
}


static void netvsc_send_table(struct hv_device *hdev,
			      struct vmpacket_descriptor *vmpkt)
{
	struct netvsc_device *nvscdev;
	struct net_device *ndev;
	struct nvsp_message *nvmsg;
	int i;
	u32 count, *tab;

	nvscdev = get_outbound_net_device(hdev);
	if (!nvscdev)
		return;
	ndev = nvscdev->ndev;

	nvmsg = (struct nvsp_message *)((unsigned long)vmpkt +
					(vmpkt->offset8 << 3));

	if (nvmsg->hdr.msg_type != NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE)
		return;

	count = nvmsg->msg.v5_msg.send_table.count;
	if (count != VRSS_SEND_TAB_SIZE) {
		netdev_err(ndev, "Received wrong send-table size:%u\n", count);
		return;
	}

	tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table +
		      nvmsg->msg.v5_msg.send_table.offset);

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

void netvsc_channel_cb(void *context)
{
	int ret;
	struct vmbus_channel *channel = (struct vmbus_channel *)context;
	struct hv_device *device;
	struct netvsc_device *net_device;
	u32 bytes_recvd;
	u64 request_id;
	struct vmpacket_descriptor *desc;
	unsigned char *buffer;
	int bufferlen = NETVSC_PACKET_SIZE;
	struct net_device *ndev;

	if (channel->primary_channel != NULL)
		device = channel->primary_channel->device_obj;
	else
		device = channel->device_obj;

	net_device = get_inbound_net_device(device);
	if (!net_device)
		return;
	ndev = net_device->ndev;
	buffer = get_per_channel_state(channel);

	do {
		ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
					   &bytes_recvd, &request_id);
		if (ret == 0) {
			if (bytes_recvd > 0) {
				desc = (struct vmpacket_descriptor *)buffer;
				switch (desc->type) {
				case VM_PKT_COMP:
					netvsc_send_completion(net_device,
								device, desc);
					break;

				case VM_PKT_DATA_USING_XFER_PAGES:
					netvsc_receive(net_device, channel,
						       device, desc);
					break;

				case VM_PKT_DATA_INBAND:
					netvsc_send_table(device, desc);
					break;

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

			} else {
				/*
				 * We are done for this pass.
				 */
				break;
			}

		} else if (ret == -ENOBUFS) {
			if (bufferlen > NETVSC_PACKET_SIZE)
				kfree(buffer);
			/* Handle large packet */
			buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
			if (buffer == NULL) {
				/* Try again next time around */
				netdev_err(ndev,
					   "unable to allocate buffer of size "
					   "(%d)!!\n", bytes_recvd);
				break;
			}

			bufferlen = bytes_recvd;
		}
	} while (1);

	if (bufferlen > NETVSC_PACKET_SIZE)
		kfree(buffer);
	return;
}

/*
 * netvsc_device_add - Callback when the device belonging to this
 * driver is added
 */
int netvsc_device_add(struct hv_device *device, void *additional_info)
{
	int ret = 0;
	int ring_size =
	((struct netvsc_device_info *)additional_info)->ring_size;
	struct netvsc_device *net_device;
	struct net_device *ndev;

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

	net_device->ring_size = ring_size;

	/*
	 * Coming into this function, struct net_device * is
	 * registered as the driver private data.
	 * In alloc_net_device(), we register struct netvsc_device *
	 * as the driver private data and stash away struct net_device *
	 * in struct netvsc_device *.
	 */
	ndev = net_device->ndev;

	/* Add netvsc_device context to netvsc_device */
	net_device->nd_ctx = netdev_priv(ndev);

	/* Initialize the NetVSC channel extension */
	init_completion(&net_device->channel_init_wait);

	set_per_channel_state(device->channel, net_device->cb_buffer);

	/* Open the channel */
	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
			 ring_size * PAGE_SIZE, NULL, 0,
			 netvsc_channel_cb, device->channel);

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

	/* Channel is opened */
	pr_info("hv_netvsc channel opened successfully\n");

	net_device->chn_table[0] = device->channel;

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

	return ret;

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

cleanup:
	free_netvsc_device(net_device);

	return ret;
}