summaryrefslogtreecommitdiff
path: root/drivers/hv/channel.c
blob: 77d2579d612415b97bdae6c84004455e48fe3254 (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
/*
 * 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/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/hyperv.h>
#include <linux/uio.h>
#include <linux/interrupt.h>

#include "hyperv_vmbus.h"

#define NUM_PAGES_SPANNED(addr, len) \
((PAGE_ALIGN(addr + len) >> PAGE_SHIFT) - (addr >> PAGE_SHIFT))

/*
 * vmbus_setevent- Trigger an event notification on the specified
 * channel.
 */
static void vmbus_setevent(struct vmbus_channel *channel)
{
	struct hv_monitor_page *monitorpage;

	if (channel->offermsg.monitor_allocated) {
		/* Each u32 represents 32 channels */
		sync_set_bit(channel->offermsg.child_relid & 31,
			(unsigned long *) vmbus_connection.send_int_page +
			(channel->offermsg.child_relid >> 5));

		/* Get the child to parent monitor page */
		monitorpage = vmbus_connection.monitor_pages[1];

		sync_set_bit(channel->monitor_bit,
			(unsigned long *)&monitorpage->trigger_group
					[channel->monitor_grp].pending);

	} else {
		vmbus_set_event(channel);
	}
}

/*
 * vmbus_open - Open the specified channel.
 */
int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
		     u32 recv_ringbuffer_size, void *userdata, u32 userdatalen,
		     void (*onchannelcallback)(void *context), void *context)
{
	struct vmbus_channel_open_channel *open_msg;
	struct vmbus_channel_msginfo *open_info = NULL;
	void *in, *out;
	unsigned long flags;
	int ret, err = 0;
	unsigned long t;
	struct page *page;

	spin_lock_irqsave(&newchannel->lock, flags);
	if (newchannel->state == CHANNEL_OPEN_STATE) {
		newchannel->state = CHANNEL_OPENING_STATE;
	} else {
		spin_unlock_irqrestore(&newchannel->lock, flags);
		return -EINVAL;
	}
	spin_unlock_irqrestore(&newchannel->lock, flags);

	newchannel->onchannel_callback = onchannelcallback;
	newchannel->channel_callback_context = context;

	/* Allocate the ring buffer */
	page = alloc_pages_node(cpu_to_node(newchannel->target_cpu),
				GFP_KERNEL|__GFP_ZERO,
				get_order(send_ringbuffer_size +
				recv_ringbuffer_size));

	if (!page)
		out = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
					       get_order(send_ringbuffer_size +
					       recv_ringbuffer_size));
	else
		out = (void *)page_address(page);

	if (!out) {
		err = -ENOMEM;
		goto error0;
	}

	in = (void *)((unsigned long)out + send_ringbuffer_size);

	newchannel->ringbuffer_pages = out;
	newchannel->ringbuffer_pagecount = (send_ringbuffer_size +
					   recv_ringbuffer_size) >> PAGE_SHIFT;

	ret = hv_ringbuffer_init(
		&newchannel->outbound, out, send_ringbuffer_size);

	if (ret != 0) {
		err = ret;
		goto error0;
	}

	ret = hv_ringbuffer_init(
		&newchannel->inbound, in, recv_ringbuffer_size);
	if (ret != 0) {
		err = ret;
		goto error0;
	}


	/* Establish the gpadl for the ring buffer */
	newchannel->ringbuffer_gpadlhandle = 0;

	ret = vmbus_establish_gpadl(newchannel,
					 newchannel->outbound.ring_buffer,
					 send_ringbuffer_size +
					 recv_ringbuffer_size,
					 &newchannel->ringbuffer_gpadlhandle);

	if (ret != 0) {
		err = ret;
		goto error0;
	}

	/* Create and init the channel open message */
	open_info = kmalloc(sizeof(*open_info) +
			   sizeof(struct vmbus_channel_open_channel),
			   GFP_KERNEL);
	if (!open_info) {
		err = -ENOMEM;
		goto error_gpadl;
	}

	init_completion(&open_info->waitevent);

	open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
	open_msg->openid = newchannel->offermsg.child_relid;
	open_msg->child_relid = newchannel->offermsg.child_relid;
	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
	open_msg->downstream_ringbuffer_pageoffset = send_ringbuffer_size >>
						  PAGE_SHIFT;
	open_msg->target_vp = newchannel->target_vp;

	if (userdatalen > MAX_USER_DEFINED_BYTES) {
		err = -EINVAL;
		goto error_gpadl;
	}

	if (userdatalen)
		memcpy(open_msg->userdata, userdata, userdatalen);

	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_add_tail(&open_info->msglistentry,
		      &vmbus_connection.chn_msg_list);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

	ret = vmbus_post_msg(open_msg,
			       sizeof(struct vmbus_channel_open_channel));

	if (ret != 0) {
		err = ret;
		goto error1;
	}

	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
	if (t == 0) {
		err = -ETIMEDOUT;
		goto error1;
	}

	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_del(&open_info->msglistentry);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

	if (open_info->response.open_result.status) {
		err = -EAGAIN;
		goto error_gpadl;
	}

	newchannel->state = CHANNEL_OPENED_STATE;
	kfree(open_info);
	return 0;

error1:
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_del(&open_info->msglistentry);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

error_gpadl:
	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);

error0:
	free_pages((unsigned long)out,
		get_order(send_ringbuffer_size + recv_ringbuffer_size));
	kfree(open_info);
	newchannel->state = CHANNEL_OPEN_STATE;
	return err;
}
EXPORT_SYMBOL_GPL(vmbus_open);

/*
 * create_gpadl_header - Creates a gpadl for the specified buffer
 */
static int create_gpadl_header(void *kbuffer, u32 size,
					 struct vmbus_channel_msginfo **msginfo,
					 u32 *messagecount)
{
	int i;
	int pagecount;
	struct vmbus_channel_gpadl_header *gpadl_header;
	struct vmbus_channel_gpadl_body *gpadl_body;
	struct vmbus_channel_msginfo *msgheader;
	struct vmbus_channel_msginfo *msgbody = NULL;
	u32 msgsize;

	int pfnsum, pfncount, pfnleft, pfncurr, pfnsize;

	pagecount = size >> PAGE_SHIFT;

	/* do we need a gpadl body msg */
	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
		  sizeof(struct vmbus_channel_gpadl_header) -
		  sizeof(struct gpa_range);
	pfncount = pfnsize / sizeof(u64);

	if (pagecount > pfncount) {
		/* we need a gpadl body */
		/* fill in the header */
		msgsize = sizeof(struct vmbus_channel_msginfo) +
			  sizeof(struct vmbus_channel_gpadl_header) +
			  sizeof(struct gpa_range) + pfncount * sizeof(u64);
		msgheader =  kzalloc(msgsize, GFP_KERNEL);
		if (!msgheader)
			goto nomem;

		INIT_LIST_HEAD(&msgheader->submsglist);
		msgheader->msgsize = msgsize;

		gpadl_header = (struct vmbus_channel_gpadl_header *)
			msgheader->msg;
		gpadl_header->rangecount = 1;
		gpadl_header->range_buflen = sizeof(struct gpa_range) +
					 pagecount * sizeof(u64);
		gpadl_header->range[0].byte_offset = 0;
		gpadl_header->range[0].byte_count = size;
		for (i = 0; i < pfncount; i++)
			gpadl_header->range[0].pfn_array[i] = slow_virt_to_phys(
				kbuffer + PAGE_SIZE * i) >> PAGE_SHIFT;
		*msginfo = msgheader;
		*messagecount = 1;

		pfnsum = pfncount;
		pfnleft = pagecount - pfncount;

		/* how many pfns can we fit */
		pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
			  sizeof(struct vmbus_channel_gpadl_body);
		pfncount = pfnsize / sizeof(u64);

		/* fill in the body */
		while (pfnleft) {
			if (pfnleft > pfncount)
				pfncurr = pfncount;
			else
				pfncurr = pfnleft;

			msgsize = sizeof(struct vmbus_channel_msginfo) +
				  sizeof(struct vmbus_channel_gpadl_body) +
				  pfncurr * sizeof(u64);
			msgbody = kzalloc(msgsize, GFP_KERNEL);

			if (!msgbody) {
				struct vmbus_channel_msginfo *pos = NULL;
				struct vmbus_channel_msginfo *tmp = NULL;
				/*
				 * Free up all the allocated messages.
				 */
				list_for_each_entry_safe(pos, tmp,
					&msgheader->submsglist,
					msglistentry) {

					list_del(&pos->msglistentry);
					kfree(pos);
				}

				goto nomem;
			}

			msgbody->msgsize = msgsize;
			(*messagecount)++;
			gpadl_body =
				(struct vmbus_channel_gpadl_body *)msgbody->msg;

			/*
			 * Gpadl is u32 and we are using a pointer which could
			 * be 64-bit
			 * This is governed by the guest/host protocol and
			 * so the hypervisor gurantees that this is ok.
			 */
			for (i = 0; i < pfncurr; i++)
				gpadl_body->pfn[i] = slow_virt_to_phys(
					kbuffer + PAGE_SIZE * (pfnsum + i)) >>
					PAGE_SHIFT;

			/* add to msg header */
			list_add_tail(&msgbody->msglistentry,
				      &msgheader->submsglist);
			pfnsum += pfncurr;
			pfnleft -= pfncurr;
		}
	} else {
		/* everything fits in a header */
		msgsize = sizeof(struct vmbus_channel_msginfo) +
			  sizeof(struct vmbus_channel_gpadl_header) +
			  sizeof(struct gpa_range) + pagecount * sizeof(u64);
		msgheader = kzalloc(msgsize, GFP_KERNEL);
		if (msgheader == NULL)
			goto nomem;
		msgheader->msgsize = msgsize;

		gpadl_header = (struct vmbus_channel_gpadl_header *)
			msgheader->msg;
		gpadl_header->rangecount = 1;
		gpadl_header->range_buflen = sizeof(struct gpa_range) +
					 pagecount * sizeof(u64);
		gpadl_header->range[0].byte_offset = 0;
		gpadl_header->range[0].byte_count = size;
		for (i = 0; i < pagecount; i++)
			gpadl_header->range[0].pfn_array[i] = slow_virt_to_phys(
				kbuffer + PAGE_SIZE * i) >> PAGE_SHIFT;

		*msginfo = msgheader;
		*messagecount = 1;
	}

	return 0;
nomem:
	kfree(msgheader);
	kfree(msgbody);
	return -ENOMEM;
}

/*
 * vmbus_establish_gpadl - Estabish a GPADL for the specified buffer
 *
 * @channel: a channel
 * @kbuffer: from kmalloc or vmalloc
 * @size: page-size multiple
 * @gpadl_handle: some funky thing
 */
int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
			       u32 size, u32 *gpadl_handle)
{
	struct vmbus_channel_gpadl_header *gpadlmsg;
	struct vmbus_channel_gpadl_body *gpadl_body;
	struct vmbus_channel_msginfo *msginfo = NULL;
	struct vmbus_channel_msginfo *submsginfo;
	u32 msgcount;
	struct list_head *curr;
	u32 next_gpadl_handle;
	unsigned long flags;
	int ret = 0;

	next_gpadl_handle =
		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);

	ret = create_gpadl_header(kbuffer, size, &msginfo, &msgcount);
	if (ret)
		return ret;

	init_completion(&msginfo->waitevent);

	gpadlmsg = (struct vmbus_channel_gpadl_header *)msginfo->msg;
	gpadlmsg->header.msgtype = CHANNELMSG_GPADL_HEADER;
	gpadlmsg->child_relid = channel->offermsg.child_relid;
	gpadlmsg->gpadl = next_gpadl_handle;


	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_add_tail(&msginfo->msglistentry,
		      &vmbus_connection.chn_msg_list);

	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

	ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize -
			       sizeof(*msginfo));
	if (ret != 0)
		goto cleanup;

	if (msgcount > 1) {
		list_for_each(curr, &msginfo->submsglist) {

			submsginfo = (struct vmbus_channel_msginfo *)curr;
			gpadl_body =
			     (struct vmbus_channel_gpadl_body *)submsginfo->msg;

			gpadl_body->header.msgtype =
				CHANNELMSG_GPADL_BODY;
			gpadl_body->gpadl = next_gpadl_handle;

			ret = vmbus_post_msg(gpadl_body,
					       submsginfo->msgsize -
					       sizeof(*submsginfo));
			if (ret != 0)
				goto cleanup;

		}
	}
	wait_for_completion(&msginfo->waitevent);

	/* At this point, we received the gpadl created msg */
	*gpadl_handle = gpadlmsg->gpadl;

cleanup:
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_del(&msginfo->msglistentry);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

	kfree(msginfo);
	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);

/*
 * vmbus_teardown_gpadl -Teardown the specified GPADL handle
 */
int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
{
	struct vmbus_channel_gpadl_teardown *msg;
	struct vmbus_channel_msginfo *info;
	unsigned long flags;
	int ret;

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

	init_completion(&info->waitevent);

	msg = (struct vmbus_channel_gpadl_teardown *)info->msg;

	msg->header.msgtype = CHANNELMSG_GPADL_TEARDOWN;
	msg->child_relid = channel->offermsg.child_relid;
	msg->gpadl = gpadl_handle;

	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_add_tail(&info->msglistentry,
		      &vmbus_connection.chn_msg_list);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
	ret = vmbus_post_msg(msg,
			       sizeof(struct vmbus_channel_gpadl_teardown));

	if (ret)
		goto post_msg_err;

	wait_for_completion(&info->waitevent);

post_msg_err:
	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
	list_del(&info->msglistentry);
	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);

	kfree(info);
	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);

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

	channel->onchannel_callback = NULL;
}

static int vmbus_close_internal(struct vmbus_channel *channel)
{
	struct vmbus_channel_close_channel *msg;
	struct tasklet_struct *tasklet;
	int ret;

	/*
	 * process_chn_event(), running in the tasklet, can race
	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
	 * the former is accessing channel->inbound.ring_buffer, the latter
	 * could be freeing the ring_buffer pages.
	 *
	 * To resolve the race, we can serialize them by disabling the
	 * tasklet when the latter is running here.
	 */
	tasklet = hv_context.event_dpc[channel->target_cpu];
	tasklet_disable(tasklet);

	/*
	 * In case a device driver's probe() fails (e.g.,
	 * util_probe() -> vmbus_open() returns -ENOMEM) and the device is
	 * rescinded later (e.g., we dynamically disble an Integrated Service
	 * in Hyper-V Manager), the driver's remove() invokes vmbus_close():
	 * here we should skip most of the below cleanup work.
	 */
	if (channel->state != CHANNEL_OPENED_STATE) {
		ret = -EINVAL;
		goto out;
	}

	channel->state = CHANNEL_OPEN_STATE;
	channel->sc_creation_callback = NULL;
	/* Stop callback and cancel the timer asap */
	if (channel->target_cpu != get_cpu()) {
		put_cpu();
		smp_call_function_single(channel->target_cpu, reset_channel_cb,
					 channel, true);
	} else {
		reset_channel_cb(channel);
		put_cpu();
	}

	/* Send a closing message */

	msg = &channel->close_msg.msg;

	msg->header.msgtype = CHANNELMSG_CLOSECHANNEL;
	msg->child_relid = channel->offermsg.child_relid;

	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));

	if (ret) {
		pr_err("Close failed: close post msg return is %d\n", ret);
		/*
		 * If we failed to post the close msg,
		 * it is perhaps better to leak memory.
		 */
		goto out;
	}

	/* Tear down the gpadl for the channel's ring buffer */
	if (channel->ringbuffer_gpadlhandle) {
		ret = vmbus_teardown_gpadl(channel,
					   channel->ringbuffer_gpadlhandle);
		if (ret) {
			pr_err("Close failed: teardown gpadl return %d\n", ret);
			/*
			 * If we failed to teardown gpadl,
			 * it is perhaps better to leak memory.
			 */
			goto out;
		}
	}

	/* Cleanup the ring buffers for this channel */
	hv_ringbuffer_cleanup(&channel->outbound);
	hv_ringbuffer_cleanup(&channel->inbound);

	free_pages((unsigned long)channel->ringbuffer_pages,
		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));

out:
	tasklet_enable(tasklet);

	return ret;
}

/*
 * vmbus_close - Close the specified channel
 */
void vmbus_close(struct vmbus_channel *channel)
{
	struct list_head *cur, *tmp;
	struct vmbus_channel *cur_channel;

	if (channel->primary_channel != NULL) {
		/*
		 * We will only close sub-channels when
		 * the primary is closed.
		 */
		return;
	}
	/*
	 * Close all the sub-channels first and then close the
	 * primary channel.
	 */
	list_for_each_safe(cur, tmp, &channel->sc_list) {
		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
		if (cur_channel->state != CHANNEL_OPENED_STATE)
			continue;
		vmbus_close_internal(cur_channel);
	}
	/*
	 * Now close the primary.
	 */
	vmbus_close_internal(channel);
}
EXPORT_SYMBOL_GPL(vmbus_close);

int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
			   u32 bufferlen, u64 requestid,
			   enum vmbus_packet_type type, u32 flags, bool kick_q)
{
	struct vmpacket_descriptor desc;
	u32 packetlen = sizeof(struct vmpacket_descriptor) + bufferlen;
	u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
	struct kvec bufferlist[3];
	u64 aligned_data = 0;
	int ret;
	bool signal = false;
	int num_vecs = ((bufferlen != 0) ? 3 : 1);


	/* Setup the descriptor */
	desc.type = type; /* VmbusPacketTypeDataInBand; */
	desc.flags = flags; /* VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; */
	/* in 8-bytes granularity */
	desc.offset8 = sizeof(struct vmpacket_descriptor) >> 3;
	desc.len8 = (u16)(packetlen_aligned >> 3);
	desc.trans_id = requestid;

	bufferlist[0].iov_base = &desc;
	bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor);
	bufferlist[1].iov_base = buffer;
	bufferlist[1].iov_len = bufferlen;
	bufferlist[2].iov_base = &aligned_data;
	bufferlist[2].iov_len = (packetlen_aligned - packetlen);

	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, num_vecs,
				  &signal);

	/*
	 * Signalling the host is conditional on many factors:
	 * 1. The ring state changed from being empty to non-empty.
	 *    This is tracked by the variable "signal".
	 * 2. The variable kick_q tracks if more data will be placed
	 *    on the ring. We will not signal if more data is
	 *    to be placed.
	 *
	 * If we cannot write to the ring-buffer; signal the host
	 * even if we may not have written anything. This is a rare
	 * enough condition that it should not matter.
	 */
	if (((ret == 0) && kick_q && signal) || (ret))
		vmbus_setevent(channel);

	return ret;
}
EXPORT_SYMBOL(vmbus_sendpacket_ctl);

/**
 * vmbus_sendpacket() - Send the specified buffer on the given channel
 * @channel: Pointer to vmbus_channel structure.
 * @buffer: Pointer to the buffer you want to receive the data into.
 * @bufferlen: Maximum size of what the the buffer will hold
 * @requestid: Identifier of the request
 * @type: Type of packet that is being send e.g. negotiate, time
 * packet etc.
 *
 * Sends data in @buffer directly to hyper-v via the vmbus
 * This will send the data unparsed to hyper-v.
 *
 * Mainly used by Hyper-V drivers.
 */
int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
			   u32 bufferlen, u64 requestid,
			   enum vmbus_packet_type type, u32 flags)
{
	return vmbus_sendpacket_ctl(channel, buffer, bufferlen, requestid,
				    type, flags, true);
}
EXPORT_SYMBOL(vmbus_sendpacket);

/*
 * vmbus_sendpacket_pagebuffer_ctl - Send a range of single-page buffer
 * packets using a GPADL Direct packet type. This interface allows you
 * to control notifying the host. This will be useful for sending
 * batched data. Also the sender can control the send flags
 * explicitly.
 */
int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
				     struct hv_page_buffer pagebuffers[],
				     u32 pagecount, void *buffer, u32 bufferlen,
				     u64 requestid,
				     u32 flags,
				     bool kick_q)
{
	int ret;
	int i;
	struct vmbus_channel_packet_page_buffer desc;
	u32 descsize;
	u32 packetlen;
	u32 packetlen_aligned;
	struct kvec bufferlist[3];
	u64 aligned_data = 0;
	bool signal = false;

	if (pagecount > MAX_PAGE_BUFFER_COUNT)
		return -EINVAL;


	/*
	 * Adjust the size down since vmbus_channel_packet_page_buffer is the
	 * largest size we support
	 */
	descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
			  ((MAX_PAGE_BUFFER_COUNT - pagecount) *
			  sizeof(struct hv_page_buffer));
	packetlen = descsize + bufferlen;
	packetlen_aligned = ALIGN(packetlen, sizeof(u64));

	/* Setup the descriptor */
	desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
	desc.flags = flags;
	desc.dataoffset8 = descsize >> 3; /* in 8-bytes grandularity */
	desc.length8 = (u16)(packetlen_aligned >> 3);
	desc.transactionid = requestid;
	desc.rangecount = pagecount;

	for (i = 0; i < pagecount; i++) {
		desc.range[i].len = pagebuffers[i].len;
		desc.range[i].offset = pagebuffers[i].offset;
		desc.range[i].pfn	 = pagebuffers[i].pfn;
	}

	bufferlist[0].iov_base = &desc;
	bufferlist[0].iov_len = descsize;
	bufferlist[1].iov_base = buffer;
	bufferlist[1].iov_len = bufferlen;
	bufferlist[2].iov_base = &aligned_data;
	bufferlist[2].iov_len = (packetlen_aligned - packetlen);

	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);

	/*
	 * Signalling the host is conditional on many factors:
	 * 1. The ring state changed from being empty to non-empty.
	 *    This is tracked by the variable "signal".
	 * 2. The variable kick_q tracks if more data will be placed
	 *    on the ring. We will not signal if more data is
	 *    to be placed.
	 *
	 * If we cannot write to the ring-buffer; signal the host
	 * even if we may not have written anything. This is a rare
	 * enough condition that it should not matter.
	 */
	if (((ret == 0) && kick_q && signal) || (ret))
		vmbus_setevent(channel);

	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl);

/*
 * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
 * packets using a GPADL Direct packet type.
 */
int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
				     struct hv_page_buffer pagebuffers[],
				     u32 pagecount, void *buffer, u32 bufferlen,
				     u64 requestid)
{
	u32 flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
	return vmbus_sendpacket_pagebuffer_ctl(channel, pagebuffers, pagecount,
					       buffer, bufferlen, requestid,
					       flags, true);

}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);

/*
 * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
 * using a GPADL Direct packet type.
 * The buffer includes the vmbus descriptor.
 */
int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
			      struct vmbus_packet_mpb_array *desc,
			      u32 desc_size,
			      void *buffer, u32 bufferlen, u64 requestid)
{
	int ret;
	u32 packetlen;
	u32 packetlen_aligned;
	struct kvec bufferlist[3];
	u64 aligned_data = 0;
	bool signal = false;

	packetlen = desc_size + bufferlen;
	packetlen_aligned = ALIGN(packetlen, sizeof(u64));

	/* Setup the descriptor */
	desc->type = VM_PKT_DATA_USING_GPA_DIRECT;
	desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
	desc->dataoffset8 = desc_size >> 3; /* in 8-bytes grandularity */
	desc->length8 = (u16)(packetlen_aligned >> 3);
	desc->transactionid = requestid;
	desc->rangecount = 1;

	bufferlist[0].iov_base = desc;
	bufferlist[0].iov_len = desc_size;
	bufferlist[1].iov_base = buffer;
	bufferlist[1].iov_len = bufferlen;
	bufferlist[2].iov_base = &aligned_data;
	bufferlist[2].iov_len = (packetlen_aligned - packetlen);

	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);

	if (ret == 0 && signal)
		vmbus_setevent(channel);

	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);

/*
 * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
 * using a GPADL Direct packet type.
 */
int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
				struct hv_multipage_buffer *multi_pagebuffer,
				void *buffer, u32 bufferlen, u64 requestid)
{
	int ret;
	struct vmbus_channel_packet_multipage_buffer desc;
	u32 descsize;
	u32 packetlen;
	u32 packetlen_aligned;
	struct kvec bufferlist[3];
	u64 aligned_data = 0;
	bool signal = false;
	u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset,
					 multi_pagebuffer->len);

	if (pfncount > MAX_MULTIPAGE_BUFFER_COUNT)
		return -EINVAL;

	/*
	 * Adjust the size down since vmbus_channel_packet_multipage_buffer is
	 * the largest size we support
	 */
	descsize = sizeof(struct vmbus_channel_packet_multipage_buffer) -
			  ((MAX_MULTIPAGE_BUFFER_COUNT - pfncount) *
			  sizeof(u64));
	packetlen = descsize + bufferlen;
	packetlen_aligned = ALIGN(packetlen, sizeof(u64));


	/* Setup the descriptor */
	desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
	desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
	desc.dataoffset8 = descsize >> 3; /* in 8-bytes grandularity */
	desc.length8 = (u16)(packetlen_aligned >> 3);
	desc.transactionid = requestid;
	desc.rangecount = 1;

	desc.range.len = multi_pagebuffer->len;
	desc.range.offset = multi_pagebuffer->offset;

	memcpy(desc.range.pfn_array, multi_pagebuffer->pfn_array,
	       pfncount * sizeof(u64));

	bufferlist[0].iov_base = &desc;
	bufferlist[0].iov_len = descsize;
	bufferlist[1].iov_base = buffer;
	bufferlist[1].iov_len = bufferlen;
	bufferlist[2].iov_base = &aligned_data;
	bufferlist[2].iov_len = (packetlen_aligned - packetlen);

	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);

	if (ret == 0 && signal)
		vmbus_setevent(channel);

	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer);

/**
 * vmbus_recvpacket() - Retrieve the user packet on the specified channel
 * @channel: Pointer to vmbus_channel structure.
 * @buffer: Pointer to the buffer you want to receive the data into.
 * @bufferlen: Maximum size of what the the buffer will hold
 * @buffer_actual_len: The actual size of the data after it was received
 * @requestid: Identifier of the request
 *
 * Receives directly from the hyper-v vmbus and puts the data it received
 * into Buffer. This will receive the data unparsed from hyper-v.
 *
 * Mainly used by Hyper-V drivers.
 */
int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
			u32 bufferlen, u32 *buffer_actual_len, u64 *requestid)
{
	struct vmpacket_descriptor desc;
	u32 packetlen;
	u32 userlen;
	int ret;
	bool signal = false;

	*buffer_actual_len = 0;
	*requestid = 0;


	ret = hv_ringbuffer_peek(&channel->inbound, &desc,
			     sizeof(struct vmpacket_descriptor));
	if (ret != 0)
		return 0;

	packetlen = desc.len8 << 3;
	userlen = packetlen - (desc.offset8 << 3);

	*buffer_actual_len = userlen;

	if (userlen > bufferlen) {

		pr_err("Buffer too small - got %d needs %d\n",
			   bufferlen, userlen);
		return -ETOOSMALL;
	}

	*requestid = desc.trans_id;

	/* Copy over the packet to the user buffer */
	ret = hv_ringbuffer_read(&channel->inbound, buffer, userlen,
			     (desc.offset8 << 3), &signal);

	if (signal)
		vmbus_setevent(channel);

	return 0;
}
EXPORT_SYMBOL(vmbus_recvpacket);

/*
 * vmbus_recvpacket_raw - Retrieve the raw packet on the specified channel
 */
int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer,
			      u32 bufferlen, u32 *buffer_actual_len,
			      u64 *requestid)
{
	struct vmpacket_descriptor desc;
	u32 packetlen;
	int ret;
	bool signal = false;

	*buffer_actual_len = 0;
	*requestid = 0;


	ret = hv_ringbuffer_peek(&channel->inbound, &desc,
			     sizeof(struct vmpacket_descriptor));
	if (ret != 0)
		return 0;


	packetlen = desc.len8 << 3;

	*buffer_actual_len = packetlen;

	if (packetlen > bufferlen)
		return -ENOBUFS;

	*requestid = desc.trans_id;

	/* Copy over the entire packet to the user buffer */
	ret = hv_ringbuffer_read(&channel->inbound, buffer, packetlen, 0,
				 &signal);

	if (signal)
		vmbus_setevent(channel);

	return ret;
}
EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw);