summaryrefslogtreecommitdiffstats
path: root/drivers/hv/channel_mgmt.c
blob: f33465d78a025680d7515978fdbcc432d51a8062 (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
/*
 * 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, write to the Free Software Foundation, Inc., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/completion.h>
#include <linux/delay.h>
#include <linux/hyperv.h>
#include <asm/mshyperv.h>

#include "hyperv_vmbus.h"

static void init_vp_index(struct vmbus_channel *channel, u16 dev_type);

static const struct vmbus_device vmbus_devs[] = {
	/* IDE */
	{ .dev_type = HV_IDE,
	  HV_IDE_GUID,
	  .perf_device = true,
	},

	/* SCSI */
	{ .dev_type = HV_SCSI,
	  HV_SCSI_GUID,
	  .perf_device = true,
	},

	/* Fibre Channel */
	{ .dev_type = HV_FC,
	  HV_SYNTHFC_GUID,
	  .perf_device = true,
	},

	/* Synthetic NIC */
	{ .dev_type = HV_NIC,
	  HV_NIC_GUID,
	  .perf_device = true,
	},

	/* Network Direct */
	{ .dev_type = HV_ND,
	  HV_ND_GUID,
	  .perf_device = true,
	},

	/* PCIE */
	{ .dev_type = HV_PCIE,
	  HV_PCIE_GUID,
	  .perf_device = true,
	},

	/* Synthetic Frame Buffer */
	{ .dev_type = HV_FB,
	  HV_SYNTHVID_GUID,
	  .perf_device = false,
	},

	/* Synthetic Keyboard */
	{ .dev_type = HV_KBD,
	  HV_KBD_GUID,
	  .perf_device = false,
	},

	/* Synthetic MOUSE */
	{ .dev_type = HV_MOUSE,
	  HV_MOUSE_GUID,
	  .perf_device = false,
	},

	/* KVP */
	{ .dev_type = HV_KVP,
	  HV_KVP_GUID,
	  .perf_device = false,
	},

	/* Time Synch */
	{ .dev_type = HV_TS,
	  HV_TS_GUID,
	  .perf_device = false,
	},

	/* Heartbeat */
	{ .dev_type = HV_HB,
	  HV_HEART_BEAT_GUID,
	  .perf_device = false,
	},

	/* Shutdown */
	{ .dev_type = HV_SHUTDOWN,
	  HV_SHUTDOWN_GUID,
	  .perf_device = false,
	},

	/* File copy */
	{ .dev_type = HV_FCOPY,
	  HV_FCOPY_GUID,
	  .perf_device = false,
	},

	/* Backup */
	{ .dev_type = HV_BACKUP,
	  HV_VSS_GUID,
	  .perf_device = false,
	},

	/* Dynamic Memory */
	{ .dev_type = HV_DM,
	  HV_DM_GUID,
	  .perf_device = false,
	},

	/* Unknown GUID */
	{ .dev_type = HV_UNKNOWN,
	  .perf_device = false,
	},
};

static const struct {
	uuid_le guid;
} vmbus_unsupported_devs[] = {
	{ HV_AVMA1_GUID },
	{ HV_AVMA2_GUID },
	{ HV_RDV_GUID	},
};

/*
 * The rescinded channel may be blocked waiting for a response from the host;
 * take care of that.
 */
static void vmbus_rescind_cleanup(struct vmbus_channel *channel)
{
	struct vmbus_channel_msginfo *msginfo;
	unsigned long flags;


	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);

	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
				msglistentry) {

		if (msginfo->waiting_channel == channel) {
			complete(&msginfo->waitevent);
			break;
		}
	}
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
}

static bool is_unsupported_vmbus_devs(const uuid_le *guid)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(vmbus_unsupported_devs); i++)
		if (!uuid_le_cmp(*guid, vmbus_unsupported_devs[i].guid))
			return true;
	return false;
}

static u16 hv_get_dev_type(const struct vmbus_channel *channel)
{
	const uuid_le *guid = &channel->offermsg.offer.if_type;
	u16 i;

	if (is_hvsock_channel(channel) || is_unsupported_vmbus_devs(guid))
		return HV_UNKNOWN;

	for (i = HV_IDE; i < HV_UNKNOWN; i++) {
		if (!uuid_le_cmp(*guid, vmbus_devs[i].guid))
			return i;
	}
	pr_info("Unknown GUID: %pUl\n", guid);
	return i;
}

/**
 * vmbus_prep_negotiate_resp() - Create default response for Hyper-V Negotiate message
 * @icmsghdrp: Pointer to msg header structure
 * @icmsg_negotiate: Pointer to negotiate message structure
 * @buf: Raw buffer channel data
 *
 * @icmsghdrp is of type &struct icmsg_hdr.
 * Set up and fill in default negotiate response message.
 *
 * The fw_version and fw_vercnt specifies the framework version that
 * we can support.
 *
 * The srv_version and srv_vercnt specifies the service
 * versions we can support.
 *
 * Versions are given in decreasing order.
 *
 * nego_fw_version and nego_srv_version store the selected protocol versions.
 *
 * Mainly used by Hyper-V drivers.
 */
bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
				u8 *buf, const int *fw_version, int fw_vercnt,
				const int *srv_version, int srv_vercnt,
				int *nego_fw_version, int *nego_srv_version)
{
	int icframe_major, icframe_minor;
	int icmsg_major, icmsg_minor;
	int fw_major, fw_minor;
	int srv_major, srv_minor;
	int i, j;
	bool found_match = false;
	struct icmsg_negotiate *negop;

	icmsghdrp->icmsgsize = 0x10;
	negop = (struct icmsg_negotiate *)&buf[
		sizeof(struct vmbuspipe_hdr) +
		sizeof(struct icmsg_hdr)];

	icframe_major = negop->icframe_vercnt;
	icframe_minor = 0;

	icmsg_major = negop->icmsg_vercnt;
	icmsg_minor = 0;

	/*
	 * Select the framework version number we will
	 * support.
	 */

	for (i = 0; i < fw_vercnt; i++) {
		fw_major = (fw_version[i] >> 16);
		fw_minor = (fw_version[i] & 0xFFFF);

		for (j = 0; j < negop->icframe_vercnt; j++) {
			if ((negop->icversion_data[j].major == fw_major) &&
			    (negop->icversion_data[j].minor == fw_minor)) {
				icframe_major = negop->icversion_data[j].major;
				icframe_minor = negop->icversion_data[j].minor;
				found_match = true;
				break;
			}
		}

		if (found_match)
			break;
	}

	if (!found_match)
		goto fw_error;

	found_match = false;

	for (i = 0; i < srv_vercnt; i++) {
		srv_major = (srv_version[i] >> 16);
		srv_minor = (srv_version[i] & 0xFFFF);

		for (j = negop->icframe_vercnt;
			(j < negop->icframe_vercnt + negop->icmsg_vercnt);
			j++) {

			if ((negop->icversion_data[j].major == srv_major) &&
				(negop->icversion_data[j].minor == srv_minor)) {

				icmsg_major = negop->icversion_data[j].major;
				icmsg_minor = negop->icversion_data[j].minor;
				found_match = true;
				break;
			}
		}

		if (found_match)
			break;
	}

	/*
	 * Respond with the framework and service
	 * version numbers we can support.
	 */

fw_error:
	if (!found_match) {
		negop->icframe_vercnt = 0;
		negop->icmsg_vercnt = 0;
	} else {
		negop->icframe_vercnt = 1;
		negop->icmsg_vercnt = 1;
	}

	if (nego_fw_version)
		*nego_fw_version = (icframe_major << 16) | icframe_minor;

	if (nego_srv_version)
		*nego_srv_version = (icmsg_major << 16) | icmsg_minor;

	negop->icversion_data[0].major = icframe_major;
	negop->icversion_data[0].minor = icframe_minor;
	negop->icversion_data[1].major = icmsg_major;
	negop->icversion_data[1].minor = icmsg_minor;
	return found_match;
}

EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);

/*
 * alloc_channel - Allocate and initialize a vmbus channel object
 */
static struct vmbus_channel *alloc_channel(void)
{
	struct vmbus_channel *channel;

	channel = kzalloc(sizeof(*channel), GFP_ATOMIC);
	if (!channel)
		return NULL;

	spin_lock_init(&channel->inbound_lock);
	spin_lock_init(&channel->lock);

	INIT_LIST_HEAD(&channel->sc_list);
	INIT_LIST_HEAD(&channel->percpu_list);

	tasklet_init(&channel->callback_event,
		     vmbus_on_event, (unsigned long)channel);

	return channel;
}

/*
 * free_channel - Release the resources used by the vmbus channel object
 */
static void free_channel(struct vmbus_channel *channel)
{
	tasklet_kill(&channel->callback_event);
	kfree(channel);
}

static void percpu_channel_enq(void *arg)
{
	struct vmbus_channel *channel = arg;
	struct hv_per_cpu_context *hv_cpu
		= this_cpu_ptr(hv_context.cpu_context);

	list_add_tail(&channel->percpu_list, &hv_cpu->chan_list);
}

static void percpu_channel_deq(void *arg)
{
	struct vmbus_channel *channel = arg;

	list_del(&channel->percpu_list);
}


static void vmbus_release_relid(u32 relid)
{
	struct vmbus_channel_relid_released msg;

	memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
	msg.child_relid = relid;
	msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
	vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released),
		       true);
}

void hv_event_tasklet_disable(struct vmbus_channel *channel)
{
	tasklet_disable(&channel->callback_event);
}

void hv_event_tasklet_enable(struct vmbus_channel *channel)
{
	tasklet_enable(&channel->callback_event);

	/* In case there is any pending event */
	tasklet_schedule(&channel->callback_event);
}

void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
{
	unsigned long flags;
	struct vmbus_channel *primary_channel;

	BUG_ON(!channel->rescind);
	BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));

	hv_event_tasklet_disable(channel);
	if (channel->target_cpu != get_cpu()) {
		put_cpu();
		smp_call_function_single(channel->target_cpu,
					 percpu_channel_deq, channel, true);
	} else {
		percpu_channel_deq(channel);
		put_cpu();
	}
	hv_event_tasklet_enable(channel);

	if (channel->primary_channel == NULL) {
		list_del(&channel->listentry);

		primary_channel = channel;
	} else {
		primary_channel = channel->primary_channel;
		spin_lock_irqsave(&primary_channel->lock, flags);
		list_del(&channel->sc_list);
		primary_channel->num_sc--;
		spin_unlock_irqrestore(&primary_channel->lock, flags);
	}

	/*
	 * We need to free the bit for init_vp_index() to work in the case
	 * of sub-channel, when we reload drivers like hv_netvsc.
	 */
	if (channel->affinity_policy == HV_LOCALIZED)
		cpumask_clear_cpu(channel->target_cpu,
				  &primary_channel->alloced_cpus_in_node);

	vmbus_release_relid(relid);

	free_channel(channel);
}

void vmbus_free_channels(void)
{
	struct vmbus_channel *channel, *tmp;

	mutex_lock(&vmbus_connection.channel_mutex);
	list_for_each_entry_safe(channel, tmp, &vmbus_connection.chn_list,
		listentry) {
		/* hv_process_channel_removal() needs this */
		channel->rescind = true;

		vmbus_device_unregister(channel->device_obj);
	}
	mutex_unlock(&vmbus_connection.channel_mutex);
}

/*
 * vmbus_process_offer - Process the offer by creating a channel/device
 * associated with this offer
 */
static void vmbus_process_offer(struct vmbus_channel *newchannel)
{
	struct vmbus_channel *channel;
	bool fnew = true;
	unsigned long flags;
	u16 dev_type;
	int ret;

	/* Make sure this is a new offer */
	mutex_lock(&vmbus_connection.channel_mutex);

	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
		if (!uuid_le_cmp(channel->offermsg.offer.if_type,
			newchannel->offermsg.offer.if_type) &&
			!uuid_le_cmp(channel->offermsg.offer.if_instance,
				newchannel->offermsg.offer.if_instance)) {
			fnew = false;
			break;
		}
	}

	if (fnew)
		list_add_tail(&newchannel->listentry,
			      &vmbus_connection.chn_list);

	mutex_unlock(&vmbus_connection.channel_mutex);

	if (!fnew) {
		/*
		 * Check to see if this is a sub-channel.
		 */
		if (newchannel->offermsg.offer.sub_channel_index != 0) {
			/*
			 * Process the sub-channel.
			 */
			newchannel->primary_channel = channel;
			spin_lock_irqsave(&channel->lock, flags);
			list_add_tail(&newchannel->sc_list, &channel->sc_list);
			channel->num_sc++;
			spin_unlock_irqrestore(&channel->lock, flags);
		} else
			goto err_free_chan;
	}

	dev_type = hv_get_dev_type(newchannel);

	init_vp_index(newchannel, dev_type);

	hv_event_tasklet_disable(newchannel);
	if (newchannel->target_cpu != get_cpu()) {
		put_cpu();
		smp_call_function_single(newchannel->target_cpu,
					 percpu_channel_enq,
					 newchannel, true);
	} else {
		percpu_channel_enq(newchannel);
		put_cpu();
	}
	hv_event_tasklet_enable(newchannel);

	/*
	 * This state is used to indicate a successful open
	 * so that when we do close the channel normally, we
	 * can cleanup properly
	 */
	newchannel->state = CHANNEL_OPEN_STATE;

	if (!fnew) {
		if (channel->sc_creation_callback != NULL)
			channel->sc_creation_callback(newchannel);
		return;
	}

	/*
	 * Start the process of binding this offer to the driver
	 * We need to set the DeviceObject field before calling
	 * vmbus_child_dev_add()
	 */
	newchannel->device_obj = vmbus_device_create(
		&newchannel->offermsg.offer.if_type,
		&newchannel->offermsg.offer.if_instance,
		newchannel);
	if (!newchannel->device_obj)
		goto err_deq_chan;

	newchannel->device_obj->device_id = dev_type;
	/*
	 * Add the new device to the bus. This will kick off device-driver
	 * binding which eventually invokes the device driver's AddDevice()
	 * method.
	 */
	mutex_lock(&vmbus_connection.channel_mutex);
	ret = vmbus_device_register(newchannel->device_obj);
	mutex_unlock(&vmbus_connection.channel_mutex);

	if (ret != 0) {
		pr_err("unable to add child device object (relid %d)\n",
			newchannel->offermsg.child_relid);
		kfree(newchannel->device_obj);
		goto err_deq_chan;
	}
	return;

err_deq_chan:
	mutex_lock(&vmbus_connection.channel_mutex);
	list_del(&newchannel->listentry);
	mutex_unlock(&vmbus_connection.channel_mutex);

	hv_event_tasklet_disable(newchannel);
	if (newchannel->target_cpu != get_cpu()) {
		put_cpu();
		smp_call_function_single(newchannel->target_cpu,
					 percpu_channel_deq, newchannel, true);
	} else {
		percpu_channel_deq(newchannel);
		put_cpu();
	}
	hv_event_tasklet_enable(newchannel);

	vmbus_release_relid(newchannel->offermsg.child_relid);

err_free_chan:
	free_channel(newchannel);
}

/*
 * We use this state to statically distribute the channel interrupt load.
 */
static int next_numa_node_id;

/*
 * Starting with Win8, we can statically distribute the incoming
 * channel interrupt load by binding a channel to VCPU.
 * We do this in a hierarchical fashion:
 * First distribute the primary channels across available NUMA nodes
 * and then distribute the subchannels amongst the CPUs in the NUMA
 * node assigned to the primary channel.
 *
 * For pre-win8 hosts or non-performance critical channels we assign the
 * first CPU in the first NUMA node.
 */
static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
{
	u32 cur_cpu;
	bool perf_chn = vmbus_devs[dev_type].perf_device;
	struct vmbus_channel *primary = channel->primary_channel;
	int next_node;
	struct cpumask available_mask;
	struct cpumask *alloced_mask;

	if ((vmbus_proto_version == VERSION_WS2008) ||
	    (vmbus_proto_version == VERSION_WIN7) || (!perf_chn)) {
		/*
		 * Prior to win8, all channel interrupts are
		 * delivered on cpu 0.
		 * Also if the channel is not a performance critical
		 * channel, bind it to cpu 0.
		 */
		channel->numa_node = 0;
		channel->target_cpu = 0;
		channel->target_vp = hv_context.vp_index[0];
		return;
	}

	/*
	 * Based on the channel affinity policy, we will assign the NUMA
	 * nodes.
	 */

	if ((channel->affinity_policy == HV_BALANCED) || (!primary)) {
		while (true) {
			next_node = next_numa_node_id++;
			if (next_node == nr_node_ids) {
				next_node = next_numa_node_id = 0;
				continue;
			}
			if (cpumask_empty(cpumask_of_node(next_node)))
				continue;
			break;
		}
		channel->numa_node = next_node;
		primary = channel;
	}
	alloced_mask = &hv_context.hv_numa_map[primary->numa_node];

	if (cpumask_weight(alloced_mask) ==
	    cpumask_weight(cpumask_of_node(primary->numa_node))) {
		/*
		 * We have cycled through all the CPUs in the node;
		 * reset the alloced map.
		 */
		cpumask_clear(alloced_mask);
	}

	cpumask_xor(&available_mask, alloced_mask,
		    cpumask_of_node(primary->numa_node));

	cur_cpu = -1;

	if (primary->affinity_policy == HV_LOCALIZED) {
		/*
		 * Normally Hyper-V host doesn't create more subchannels
		 * than there are VCPUs on the node but it is possible when not
		 * all present VCPUs on the node are initialized by guest.
		 * Clear the alloced_cpus_in_node to start over.
		 */
		if (cpumask_equal(&primary->alloced_cpus_in_node,
				  cpumask_of_node(primary->numa_node)))
			cpumask_clear(&primary->alloced_cpus_in_node);
	}

	while (true) {
		cur_cpu = cpumask_next(cur_cpu, &available_mask);
		if (cur_cpu >= nr_cpu_ids) {
			cur_cpu = -1;
			cpumask_copy(&available_mask,
				     cpumask_of_node(primary->numa_node));
			continue;
		}

		if (primary->affinity_policy == HV_LOCALIZED) {
			/*
			 * NOTE: in the case of sub-channel, we clear the
			 * sub-channel related bit(s) in
			 * primary->alloced_cpus_in_node in
			 * hv_process_channel_removal(), so when we
			 * reload drivers like hv_netvsc in SMP guest, here
			 * we're able to re-allocate
			 * bit from primary->alloced_cpus_in_node.
			 */
			if (!cpumask_test_cpu(cur_cpu,
					      &primary->alloced_cpus_in_node)) {
				cpumask_set_cpu(cur_cpu,
						&primary->alloced_cpus_in_node);
				cpumask_set_cpu(cur_cpu, alloced_mask);
				break;
			}
		} else {
			cpumask_set_cpu(cur_cpu, alloced_mask);
			break;
		}
	}

	channel->target_cpu = cur_cpu;
	channel->target_vp = hv_context.vp_index[cur_cpu];
}

static void vmbus_wait_for_unload(void)
{
	int cpu;
	void *page_addr;
	struct hv_message *msg;
	struct vmbus_channel_message_header *hdr;
	u32 message_type;

	/*
	 * CHANNELMSG_UNLOAD_RESPONSE is always delivered to the CPU which was
	 * used for initial contact or to CPU0 depending on host version. When
	 * we're crashing on a different CPU let's hope that IRQ handler on
	 * the cpu which receives CHANNELMSG_UNLOAD_RESPONSE is still
	 * functional and vmbus_unload_response() will complete
	 * vmbus_connection.unload_event. If not, the last thing we can do is
	 * read message pages for all CPUs directly.
	 */
	while (1) {
		if (completion_done(&vmbus_connection.unload_event))
			break;

		for_each_online_cpu(cpu) {
			struct hv_per_cpu_context *hv_cpu
				= per_cpu_ptr(hv_context.cpu_context, cpu);

			page_addr = hv_cpu->synic_message_page;
			msg = (struct hv_message *)page_addr
				+ VMBUS_MESSAGE_SINT;

			message_type = READ_ONCE(msg->header.message_type);
			if (message_type == HVMSG_NONE)
				continue;

			hdr = (struct vmbus_channel_message_header *)
				msg->u.payload;

			if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
				complete(&vmbus_connection.unload_event);

			vmbus_signal_eom(msg, message_type);
		}

		mdelay(10);
	}

	/*
	 * We're crashing and already got the UNLOAD_RESPONSE, cleanup all
	 * maybe-pending messages on all CPUs to be able to receive new
	 * messages after we reconnect.
	 */
	for_each_online_cpu(cpu) {
		struct hv_per_cpu_context *hv_cpu
			= per_cpu_ptr(hv_context.cpu_context, cpu);

		page_addr = hv_cpu->synic_message_page;
		msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
		msg->header.message_type = HVMSG_NONE;
	}
}

/*
 * vmbus_unload_response - Handler for the unload response.
 */
static void vmbus_unload_response(struct vmbus_channel_message_header *hdr)
{
	/*
	 * This is a global event; just wakeup the waiting thread.
	 * Once we successfully unload, we can cleanup the monitor state.
	 */
	complete(&vmbus_connection.unload_event);
}

void vmbus_initiate_unload(bool crash)
{
	struct vmbus_channel_message_header hdr;

	/* Pre-Win2012R2 hosts don't support reconnect */
	if (vmbus_proto_version < VERSION_WIN8_1)
		return;

	init_completion(&vmbus_connection.unload_event);
	memset(&hdr, 0, sizeof(struct vmbus_channel_message_header));
	hdr.msgtype = CHANNELMSG_UNLOAD;
	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header),
		       !crash);

	/*
	 * vmbus_initiate_unload() is also called on crash and the crash can be
	 * happening in an interrupt context, where scheduling is impossible.
	 */
	if (!crash)
		wait_for_completion(&vmbus_connection.unload_event);
	else
		vmbus_wait_for_unload();
}

/*
 * vmbus_onoffer - Handler for channel offers from vmbus in parent partition.
 *
 */
static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_offer_channel *offer;
	struct vmbus_channel *newchannel;

	offer = (struct vmbus_channel_offer_channel *)hdr;

	/* Allocate the channel object and save this offer. */
	newchannel = alloc_channel();
	if (!newchannel) {
		pr_err("Unable to allocate channel object\n");
		return;
	}

	/*
	 * Setup state for signalling the host.
	 */
	newchannel->sig_event = (struct hv_input_signal_event *)
				(ALIGN((unsigned long)
				&newchannel->sig_buf,
				HV_HYPERCALL_PARAM_ALIGN));

	newchannel->sig_event->connectionid.asu32 = 0;
	newchannel->sig_event->connectionid.u.id = VMBUS_EVENT_CONNECTION_ID;
	newchannel->sig_event->flag_number = 0;
	newchannel->sig_event->rsvdz = 0;

	if (vmbus_proto_version != VERSION_WS2008) {
		newchannel->is_dedicated_interrupt =
				(offer->is_dedicated_interrupt != 0);
		newchannel->sig_event->connectionid.u.id =
				offer->connection_id;
	}

	memcpy(&newchannel->offermsg, offer,
	       sizeof(struct vmbus_channel_offer_channel));
	newchannel->monitor_grp = (u8)offer->monitorid / 32;
	newchannel->monitor_bit = (u8)offer->monitorid % 32;

	vmbus_process_offer(newchannel);
}

/*
 * vmbus_onoffer_rescind - Rescind offer handler.
 *
 * We queue a work item to process this offer synchronously
 */
static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_rescind_offer *rescind;
	struct vmbus_channel *channel;
	unsigned long flags;
	struct device *dev;

	rescind = (struct vmbus_channel_rescind_offer *)hdr;

	mutex_lock(&vmbus_connection.channel_mutex);
	channel = relid2channel(rescind->child_relid);

	if (channel == NULL) {
		/*
		 * This is very impossible, because in
		 * vmbus_process_offer(), we have already invoked
		 * vmbus_release_relid() on error.
		 */
		goto out;
	}

	spin_lock_irqsave(&channel->lock, flags);
	channel->rescind = true;
	spin_unlock_irqrestore(&channel->lock, flags);

	vmbus_rescind_cleanup(channel);

	if (channel->device_obj) {
		if (channel->chn_rescind_callback) {
			channel->chn_rescind_callback(channel);
			goto out;
		}
		/*
		 * We will have to unregister this device from the
		 * driver core.
		 */
		dev = get_device(&channel->device_obj->device);
		if (dev) {
			vmbus_device_unregister(channel->device_obj);
			put_device(dev);
		}
	} else {
		hv_process_channel_removal(channel,
			channel->offermsg.child_relid);
	}

out:
	mutex_unlock(&vmbus_connection.channel_mutex);
}

void vmbus_hvsock_device_unregister(struct vmbus_channel *channel)
{
	mutex_lock(&vmbus_connection.channel_mutex);

	BUG_ON(!is_hvsock_channel(channel));

	channel->rescind = true;
	vmbus_device_unregister(channel->device_obj);

	mutex_unlock(&vmbus_connection.channel_mutex);
}
EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister);


/*
 * vmbus_onoffers_delivered -
 * This is invoked when all offers have been delivered.
 *
 * Nothing to do here.
 */
static void vmbus_onoffers_delivered(
			struct vmbus_channel_message_header *hdr)
{
}

/*
 * vmbus_onopen_result - Open result handler.
 *
 * This is invoked when we received a response to our channel open request.
 * Find the matching request, copy the response and signal the requesting
 * thread.
 */
static void vmbus_onopen_result(struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_open_result *result;
	struct vmbus_channel_msginfo *msginfo;
	struct vmbus_channel_message_header *requestheader;
	struct vmbus_channel_open_channel *openmsg;
	unsigned long flags;

	result = (struct vmbus_channel_open_result *)hdr;

	/*
	 * Find the open msg, copy the result and signal/unblock the wait event
	 */
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);

	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
				msglistentry) {
		requestheader =
			(struct vmbus_channel_message_header *)msginfo->msg;

		if (requestheader->msgtype == CHANNELMSG_OPENCHANNEL) {
			openmsg =
			(struct vmbus_channel_open_channel *)msginfo->msg;
			if (openmsg->child_relid == result->child_relid &&
			    openmsg->openid == result->openid) {
				memcpy(&msginfo->response.open_result,
				       result,
				       sizeof(
					struct vmbus_channel_open_result));
				complete(&msginfo->waitevent);
				break;
			}
		}
	}
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
}

/*
 * vmbus_ongpadl_created - GPADL created handler.
 *
 * This is invoked when we received a response to our gpadl create request.
 * Find the matching request, copy the response and signal the requesting
 * thread.
 */
static void vmbus_ongpadl_created(struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_gpadl_created *gpadlcreated;
	struct vmbus_channel_msginfo *msginfo;
	struct vmbus_channel_message_header *requestheader;
	struct vmbus_channel_gpadl_header *gpadlheader;
	unsigned long flags;

	gpadlcreated = (struct vmbus_channel_gpadl_created *)hdr;

	/*
	 * Find the establish msg, copy the result and signal/unblock the wait
	 * event
	 */
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);

	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
				msglistentry) {
		requestheader =
			(struct vmbus_channel_message_header *)msginfo->msg;

		if (requestheader->msgtype == CHANNELMSG_GPADL_HEADER) {
			gpadlheader =
			(struct vmbus_channel_gpadl_header *)requestheader;

			if ((gpadlcreated->child_relid ==
			     gpadlheader->child_relid) &&
			    (gpadlcreated->gpadl == gpadlheader->gpadl)) {
				memcpy(&msginfo->response.gpadl_created,
				       gpadlcreated,
				       sizeof(
					struct vmbus_channel_gpadl_created));
				complete(&msginfo->waitevent);
				break;
			}
		}
	}
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
}

/*
 * vmbus_ongpadl_torndown - GPADL torndown handler.
 *
 * This is invoked when we received a response to our gpadl teardown request.
 * Find the matching request, copy the response and signal the requesting
 * thread.
 */
static void vmbus_ongpadl_torndown(
			struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_gpadl_torndown *gpadl_torndown;
	struct vmbus_channel_msginfo *msginfo;
	struct vmbus_channel_message_header *requestheader;
	struct vmbus_channel_gpadl_teardown *gpadl_teardown;
	unsigned long flags;

	gpadl_torndown = (struct vmbus_channel_gpadl_torndown *)hdr;

	/*
	 * Find the open msg, copy the result and signal/unblock the wait event
	 */
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);

	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
				msglistentry) {
		requestheader =
			(struct vmbus_channel_message_header *)msginfo->msg;

		if (requestheader->msgtype == CHANNELMSG_GPADL_TEARDOWN) {
			gpadl_teardown =
			(struct vmbus_channel_gpadl_teardown *)requestheader;

			if (gpadl_torndown->gpadl == gpadl_teardown->gpadl) {
				memcpy(&msginfo->response.gpadl_torndown,
				       gpadl_torndown,
				       sizeof(
					struct vmbus_channel_gpadl_torndown));
				complete(&msginfo->waitevent);
				break;
			}
		}
	}
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
}

/*
 * vmbus_onversion_response - Version response handler
 *
 * This is invoked when we received a response to our initiate contact request.
 * Find the matching request, copy the response and signal the requesting
 * thread.
 */
static void vmbus_onversion_response(
		struct vmbus_channel_message_header *hdr)
{
	struct vmbus_channel_msginfo *msginfo;
	struct vmbus_channel_message_header *requestheader;
	struct vmbus_channel_version_response *version_response;
	unsigned long flags;

	version_response = (struct vmbus_channel_version_response *)hdr;
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);

	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
				msglistentry) {
		requestheader =
			(struct vmbus_channel_message_header *)msginfo->msg;

		if (requestheader->msgtype ==
		    CHANNELMSG_INITIATE_CONTACT) {
			memcpy(&msginfo->response.version_response,
			      version_response,
			      sizeof(struct vmbus_channel_version_response));
			complete(&msginfo->waitevent);
		}
	}
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
}

/* Channel message dispatch table */
struct vmbus_channel_message_table_entry
	channel_message_table[CHANNELMSG_COUNT] = {
	{CHANNELMSG_INVALID,			0, NULL},
	{CHANNELMSG_OFFERCHANNEL,		0, vmbus_onoffer},
	{CHANNELMSG_RESCIND_CHANNELOFFER,	0, vmbus_onoffer_rescind},
	{CHANNELMSG_REQUESTOFFERS,		0, NULL},
	{CHANNELMSG_ALLOFFERS_DELIVERED,	1, vmbus_onoffers_delivered},
	{CHANNELMSG_OPENCHANNEL,		0, NULL},
	{CHANNELMSG_OPENCHANNEL_RESULT,		1, vmbus_onopen_result},
	{CHANNELMSG_CLOSECHANNEL,		0, NULL},
	{CHANNELMSG_GPADL_HEADER,		0, NULL},
	{CHANNELMSG_GPADL_BODY,			0, NULL},
	{CHANNELMSG_GPADL_CREATED,		1, vmbus_ongpadl_created},
	{CHANNELMSG_GPADL_TEARDOWN,		0, NULL},
	{CHANNELMSG_GPADL_TORNDOWN,		1, vmbus_ongpadl_torndown},
	{CHANNELMSG_RELID_RELEASED,		0, NULL},
	{CHANNELMSG_INITIATE_CONTACT,		0, NULL},
	{CHANNELMSG_VERSION_RESPONSE,		1, vmbus_onversion_response},
	{CHANNELMSG_UNLOAD,			0, NULL},
	{CHANNELMSG_UNLOAD_RESPONSE,		1, vmbus_unload_response},
	{CHANNELMSG_18,				0, NULL},
	{CHANNELMSG_19,				0, NULL},
	{CHANNELMSG_20,				0, NULL},
	{CHANNELMSG_TL_CONNECT_REQUEST,		0, NULL},
};

/*
 * vmbus_onmessage - Handler for channel protocol messages.
 *
 * This is invoked in the vmbus worker thread context.
 */
void vmbus_onmessage(void *context)
{
	struct hv_message *msg = context;
	struct vmbus_channel_message_header *hdr;
	int size;

	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
	size = msg->header.payload_size;

	if (hdr->msgtype >= CHANNELMSG_COUNT) {
		pr_err("Received invalid channel message type %d size %d\n",
			   hdr->msgtype, size);
		print_hex_dump_bytes("", DUMP_PREFIX_NONE,
				     (unsigned char *)msg->u.payload, size);
		return;
	}

	if (channel_message_table[hdr->msgtype].message_handler)
		channel_message_table[hdr->msgtype].message_handler(hdr);
	else
		pr_err("Unhandled channel message type %d\n", hdr->msgtype);
}

/*
 * vmbus_request_offers - Send a request to get all our pending offers.
 */
int vmbus_request_offers(void)
{
	struct vmbus_channel_message_header *msg;
	struct vmbus_channel_msginfo *msginfo;
	int ret;

	msginfo = kmalloc(sizeof(*msginfo) +
			  sizeof(struct vmbus_channel_message_header),
			  GFP_KERNEL);
	if (!msginfo)
		return -ENOMEM;

	msg = (struct vmbus_channel_message_header *)msginfo->msg;

	msg->msgtype = CHANNELMSG_REQUESTOFFERS;


	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header),
			     true);
	if (ret != 0) {
		pr_err("Unable to request offers - %d\n", ret);

		goto cleanup;
	}

cleanup:
	kfree(msginfo);

	return ret;
}

/*
 * Retrieve the (sub) channel on which to send an outgoing request.
 * When a primary channel has multiple sub-channels, we try to
 * distribute the load equally amongst all available channels.
 */
struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary)
{
	struct list_head *cur, *tmp;
	int cur_cpu;
	struct vmbus_channel *cur_channel;
	struct vmbus_channel *outgoing_channel = primary;
	int next_channel;
	int i = 1;

	if (list_empty(&primary->sc_list))
		return outgoing_channel;

	next_channel = primary->next_oc++;

	if (next_channel > (primary->num_sc)) {
		primary->next_oc = 0;
		return outgoing_channel;
	}

	cur_cpu = hv_context.vp_index[get_cpu()];
	put_cpu();
	list_for_each_safe(cur, tmp, &primary->sc_list) {
		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
		if (cur_channel->state != CHANNEL_OPENED_STATE)
			continue;

		if (cur_channel->target_vp == cur_cpu)
			return cur_channel;

		if (i == next_channel)
			return cur_channel;

		i++;
	}

	return outgoing_channel;
}
EXPORT_SYMBOL_GPL(vmbus_get_outgoing_channel);

static void invoke_sc_cb(struct vmbus_channel *primary_channel)
{
	struct list_head *cur, *tmp;
	struct vmbus_channel *cur_channel;

	if (primary_channel->sc_creation_callback == NULL)
		return;

	list_for_each_safe(cur, tmp, &primary_channel->sc_list) {
		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);

		primary_channel->sc_creation_callback(cur_channel);
	}
}

void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel,
				void (*sc_cr_cb)(struct vmbus_channel *new_sc))
{
	primary_channel->sc_creation_callback = sc_cr_cb;
}
EXPORT_SYMBOL_GPL(vmbus_set_sc_create_callback);

bool vmbus_are_subchannels_present(struct vmbus_channel *primary)
{
	bool ret;

	ret = !list_empty(&primary->sc_list);

	if (ret) {
		/*
		 * Invoke the callback on sub-channel creation.
		 * This will present a uniform interface to the
		 * clients.
		 */
		invoke_sc_cb(primary);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_are_subchannels_present);

void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel,
		void (*chn_rescind_cb)(struct vmbus_channel *))
{
	channel->chn_rescind_callback = chn_rescind_cb;
}
EXPORT_SYMBOL_GPL(vmbus_set_chn_rescind_callback);