forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathchannel_mgmt.c
1605 lines (1365 loc) · 44.4 KB
/
channel_mgmt.c
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
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2009, Microsoft Corporation.
*
* Authors:
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/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/cpu.h>
#include <linux/hyperv.h>
#include <asm/mshyperv.h>
#include <linux/sched/isolation.h>
#include "hyperv_vmbus.h"
static void init_vp_index(struct vmbus_channel *channel);
const struct vmbus_device vmbus_devs[] = {
/* IDE */
{ .dev_type = HV_IDE,
HV_IDE_GUID,
.perf_device = true,
.allowed_in_isolated = false,
},
/* SCSI */
{ .dev_type = HV_SCSI,
HV_SCSI_GUID,
.perf_device = true,
.allowed_in_isolated = true,
},
/* Fibre Channel */
{ .dev_type = HV_FC,
HV_SYNTHFC_GUID,
.perf_device = true,
.allowed_in_isolated = false,
},
/* Synthetic NIC */
{ .dev_type = HV_NIC,
HV_NIC_GUID,
.perf_device = true,
.allowed_in_isolated = true,
},
/* Network Direct */
{ .dev_type = HV_ND,
HV_ND_GUID,
.perf_device = true,
.allowed_in_isolated = false,
},
/* PCIE */
{ .dev_type = HV_PCIE,
HV_PCIE_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Synthetic Frame Buffer */
{ .dev_type = HV_FB,
HV_SYNTHVID_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Synthetic Keyboard */
{ .dev_type = HV_KBD,
HV_KBD_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Synthetic MOUSE */
{ .dev_type = HV_MOUSE,
HV_MOUSE_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* KVP */
{ .dev_type = HV_KVP,
HV_KVP_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Time Synch */
{ .dev_type = HV_TS,
HV_TS_GUID,
.perf_device = false,
.allowed_in_isolated = true,
},
/* Heartbeat */
{ .dev_type = HV_HB,
HV_HEART_BEAT_GUID,
.perf_device = false,
.allowed_in_isolated = true,
},
/* Shutdown */
{ .dev_type = HV_SHUTDOWN,
HV_SHUTDOWN_GUID,
.perf_device = false,
.allowed_in_isolated = true,
},
/* File copy */
{ .dev_type = HV_FCOPY,
HV_FCOPY_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Backup */
{ .dev_type = HV_BACKUP,
HV_VSS_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Dynamic Memory */
{ .dev_type = HV_DM,
HV_DM_GUID,
.perf_device = false,
.allowed_in_isolated = false,
},
/* Unknown GUID */
{ .dev_type = HV_UNKNOWN,
.perf_device = false,
.allowed_in_isolated = false,
},
};
static const struct {
guid_t guid;
} vmbus_unsupported_devs[] = {
{ HV_AVMA1_GUID },
{ HV_AVMA2_GUID },
{ HV_RDV_GUID },
{ HV_IMC_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);
channel->rescind = true;
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 guid_t *guid)
{
int i;
for (i = 0; i < ARRAY_SIZE(vmbus_unsupported_devs); i++)
if (guid_equal(guid, &vmbus_unsupported_devs[i].guid))
return true;
return false;
}
static u16 hv_get_dev_type(const struct vmbus_channel *channel)
{
const guid_t *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 (guid_equal(guid, &vmbus_devs[i].guid))
return i;
}
pr_info("Unknown GUID: %pUl\n", guid);
return i;
}
/**
* vmbus_prep_negotiate_resp() - Create default response for Negotiate message
* @icmsghdrp: Pointer to msg header structure
* @buf: Raw buffer channel data
* @buflen: Length of the raw buffer channel data.
* @fw_version: The framework versions we can support.
* @fw_vercnt: The size of @fw_version.
* @srv_version: The service versions we can support.
* @srv_vercnt: The size of @srv_version.
* @nego_fw_version: The selected framework version.
* @nego_srv_version: The selected service version.
*
* Note: Versions are given in decreasing order.
*
* Set up and fill in default negotiate response message.
* Mainly used by Hyper-V drivers.
*/
bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
u32 buflen, 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;
/* Check that there's enough space for icframe_vercnt, icmsg_vercnt */
if (buflen < ICMSG_HDR + offsetof(struct icmsg_negotiate, reserved)) {
pr_err_ratelimited("Invalid icmsg negotiate\n");
return false;
}
icmsghdrp->icmsgsize = 0x10;
negop = (struct icmsg_negotiate *)&buf[ICMSG_HDR];
icframe_major = negop->icframe_vercnt;
icframe_minor = 0;
icmsg_major = negop->icmsg_vercnt;
icmsg_minor = 0;
/* Validate negop packet */
if (icframe_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT ||
icmsg_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT ||
ICMSG_NEGOTIATE_PKT_SIZE(icframe_major, icmsg_major) > buflen) {
pr_err_ratelimited("Invalid icmsg negotiate - icframe_major: %u, icmsg_major: %u\n",
icframe_major, icmsg_major);
goto fw_error;
}
/*
* 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->sched_lock);
init_completion(&channel->rescind_event);
INIT_LIST_HEAD(&channel->sc_list);
tasklet_init(&channel->callback_event,
vmbus_on_event, (unsigned long)channel);
hv_ringbuffer_pre_init(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);
vmbus_remove_channel_attr_group(channel);
kobject_put(&channel->kobj);
}
void vmbus_channel_map_relid(struct vmbus_channel *channel)
{
if (WARN_ON(channel->offermsg.child_relid >= MAX_CHANNEL_RELIDS))
return;
/*
* The mapping of the channel's relid is visible from the CPUs that
* execute vmbus_chan_sched() by the time that vmbus_chan_sched() will
* execute:
*
* (a) In the "normal (i.e., not resuming from hibernation)" path,
* the full barrier in virt_store_mb() guarantees that the store
* is propagated to all CPUs before the add_channel_work work
* is queued. In turn, add_channel_work is queued before the
* channel's ring buffer is allocated/initialized and the
* OPENCHANNEL message for the channel is sent in vmbus_open().
* Hyper-V won't start sending the interrupts for the channel
* before the OPENCHANNEL message is acked. The memory barrier
* in vmbus_chan_sched() -> sync_test_and_clear_bit() ensures
* that vmbus_chan_sched() must find the channel's relid in
* recv_int_page before retrieving the channel pointer from the
* array of channels.
*
* (b) In the "resuming from hibernation" path, the virt_store_mb()
* guarantees that the store is propagated to all CPUs before
* the VMBus connection is marked as ready for the resume event
* (cf. check_ready_for_resume_event()). The interrupt handler
* of the VMBus driver and vmbus_chan_sched() can not run before
* vmbus_bus_resume() has completed execution (cf. resume_noirq).
*/
virt_store_mb(
vmbus_connection.channels[channel->offermsg.child_relid],
channel);
}
void vmbus_channel_unmap_relid(struct vmbus_channel *channel)
{
if (WARN_ON(channel->offermsg.child_relid >= MAX_CHANNEL_RELIDS))
return;
WRITE_ONCE(
vmbus_connection.channels[channel->offermsg.child_relid],
NULL);
}
static void vmbus_release_relid(u32 relid)
{
struct vmbus_channel_relid_released msg;
int ret;
memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
msg.child_relid = relid;
msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
ret = vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released),
true);
trace_vmbus_release_relid(&msg, ret);
}
void hv_process_channel_removal(struct vmbus_channel *channel)
{
lockdep_assert_held(&vmbus_connection.channel_mutex);
BUG_ON(!channel->rescind);
/*
* hv_process_channel_removal() could find INVALID_RELID only for
* hv_sock channels. See the inline comments in vmbus_onoffer().
*/
WARN_ON(channel->offermsg.child_relid == INVALID_RELID &&
!is_hvsock_channel(channel));
/*
* Upon suspend, an in-use hv_sock channel is removed from the array of
* channels and the relid is invalidated. After hibernation, when the
* user-space application destroys the channel, it's unnecessary and
* unsafe to remove the channel from the array of channels. See also
* the inline comments before the call of vmbus_release_relid() below.
*/
if (channel->offermsg.child_relid != INVALID_RELID)
vmbus_channel_unmap_relid(channel);
if (channel->primary_channel == NULL)
list_del(&channel->listentry);
else
list_del(&channel->sc_list);
/*
* If this is a "perf" channel, updates the hv_numa_map[] masks so that
* init_vp_index() can (re-)use the CPU.
*/
if (hv_is_perf_channel(channel))
hv_clear_allocated_cpu(channel->target_cpu);
/*
* Upon suspend, an in-use hv_sock channel is marked as "rescinded" and
* the relid is invalidated; after hibernation, when the user-space app
* destroys the channel, the relid is INVALID_RELID, and in this case
* it's unnecessary and unsafe to release the old relid, since the same
* relid can refer to a completely different channel now.
*/
if (channel->offermsg.child_relid != INVALID_RELID)
vmbus_release_relid(channel->offermsg.child_relid);
free_channel(channel);
}
void vmbus_free_channels(void)
{
struct vmbus_channel *channel, *tmp;
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);
}
}
/* Note: the function can run concurrently for primary/sub channels. */
static void vmbus_add_channel_work(struct work_struct *work)
{
struct vmbus_channel *newchannel =
container_of(work, struct vmbus_channel, add_channel_work);
struct vmbus_channel *primary_channel = newchannel->primary_channel;
int ret;
/*
* 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 (primary_channel != NULL) {
/* newchannel is a sub-channel. */
struct hv_device *dev = primary_channel->device_obj;
if (vmbus_add_channel_kobj(dev, newchannel))
goto err_deq_chan;
if (primary_channel->sc_creation_callback != NULL)
primary_channel->sc_creation_callback(newchannel);
newchannel->probe_done = true;
return;
}
/*
* Start the process of binding the primary channel to the driver
*/
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 = newchannel->device_id;
/*
* Add the new device to the bus. This will kick off device-driver
* binding which eventually invokes the device driver's AddDevice()
* method.
*
* If vmbus_device_register() fails, the 'device_obj' is freed in
* vmbus_device_release() as called by device_unregister() in the
* error path of vmbus_device_register(). In the outside error
* path, there's no need to free it.
*/
ret = vmbus_device_register(newchannel->device_obj);
if (ret != 0) {
pr_err("unable to add child device object (relid %d)\n",
newchannel->offermsg.child_relid);
goto err_deq_chan;
}
newchannel->probe_done = true;
return;
err_deq_chan:
mutex_lock(&vmbus_connection.channel_mutex);
/*
* We need to set the flag, otherwise
* vmbus_onoffer_rescind() can be blocked.
*/
newchannel->probe_done = true;
if (primary_channel == NULL)
list_del(&newchannel->listentry);
else
list_del(&newchannel->sc_list);
/* vmbus_process_offer() has mapped the channel. */
vmbus_channel_unmap_relid(newchannel);
mutex_unlock(&vmbus_connection.channel_mutex);
vmbus_release_relid(newchannel->offermsg.child_relid);
free_channel(newchannel);
}
/*
* 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;
struct workqueue_struct *wq;
bool fnew = true;
/*
* Synchronize vmbus_process_offer() and CPU hotplugging:
*
* CPU1 CPU2
*
* [vmbus_process_offer()] [Hot removal of the CPU]
*
* CPU_READ_LOCK CPUS_WRITE_LOCK
* LOAD cpu_online_mask SEARCH chn_list
* STORE target_cpu LOAD target_cpu
* INSERT chn_list STORE cpu_online_mask
* CPUS_READ_UNLOCK CPUS_WRITE_UNLOCK
*
* Forbids: CPU1's LOAD from *not* seing CPU2's STORE &&
* CPU2's SEARCH from *not* seeing CPU1's INSERT
*
* Forbids: CPU2's SEARCH from seeing CPU1's INSERT &&
* CPU2's LOAD from *not* seing CPU1's STORE
*/
cpus_read_lock();
/*
* Serializes the modifications of the chn_list list as well as
* the accesses to next_numa_node_id in init_vp_index().
*/
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
if (guid_equal(&channel->offermsg.offer.if_type,
&newchannel->offermsg.offer.if_type) &&
guid_equal(&channel->offermsg.offer.if_instance,
&newchannel->offermsg.offer.if_instance)) {
fnew = false;
newchannel->primary_channel = channel;
break;
}
}
init_vp_index(newchannel);
/* Remember the channels that should be cleaned up upon suspend. */
if (is_hvsock_channel(newchannel) || is_sub_channel(newchannel))
atomic_inc(&vmbus_connection.nr_chan_close_on_suspend);
/*
* Now that we have acquired the channel_mutex,
* we can release the potentially racing rescind thread.
*/
atomic_dec(&vmbus_connection.offer_in_progress);
if (fnew) {
list_add_tail(&newchannel->listentry,
&vmbus_connection.chn_list);
} else {
/*
* Check to see if this is a valid sub-channel.
*/
if (newchannel->offermsg.offer.sub_channel_index == 0) {
mutex_unlock(&vmbus_connection.channel_mutex);
cpus_read_unlock();
/*
* Don't call free_channel(), because newchannel->kobj
* is not initialized yet.
*/
kfree(newchannel);
WARN_ON_ONCE(1);
return;
}
/*
* Process the sub-channel.
*/
list_add_tail(&newchannel->sc_list, &channel->sc_list);
}
vmbus_channel_map_relid(newchannel);
mutex_unlock(&vmbus_connection.channel_mutex);
cpus_read_unlock();
/*
* vmbus_process_offer() mustn't call channel->sc_creation_callback()
* directly for sub-channels, because sc_creation_callback() ->
* vmbus_open() may never get the host's response to the
* OPEN_CHANNEL message (the host may rescind a channel at any time,
* e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind()
* may not wake up the vmbus_open() as it's blocked due to a non-zero
* vmbus_connection.offer_in_progress, and finally we have a deadlock.
*
* The above is also true for primary channels, if the related device
* drivers use sync probing mode by default.
*
* And, usually the handling of primary channels and sub-channels can
* depend on each other, so we should offload them to different
* workqueues to avoid possible deadlock, e.g. in sync-probing mode,
* NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() ->
* rtnl_lock(), and causes deadlock: the former gets the rtnl_lock
* and waits for all the sub-channels to appear, but the latter
* can't get the rtnl_lock and this blocks the handling of
* sub-channels.
*/
INIT_WORK(&newchannel->add_channel_work, vmbus_add_channel_work);
wq = fnew ? vmbus_connection.handle_primary_chan_wq :
vmbus_connection.handle_sub_chan_wq;
queue_work(wq, &newchannel->add_channel_work);
}
/*
* Check if CPUs used by other channels of the same device.
* It should only be called by init_vp_index().
*/
static bool hv_cpuself_used(u32 cpu, struct vmbus_channel *chn)
{
struct vmbus_channel *primary = chn->primary_channel;
struct vmbus_channel *sc;
lockdep_assert_held(&vmbus_connection.channel_mutex);
if (!primary)
return false;
if (primary->target_cpu == cpu)
return true;
list_for_each_entry(sc, &primary->sc_list, sc_list)
if (sc != chn && sc->target_cpu == cpu)
return true;
return false;
}
/*
* We use this state to statically distribute the channel interrupt load.
*/
static int next_numa_node_id;
/*
* We can statically distribute the incoming channel interrupt load
* by binding a channel to VCPU.
*
* For non-performance critical channels we assign the VMBUS_CONNECT_CPU.
* Performance critical channels will be distributed evenly among all
* the available NUMA nodes. Once the node is assigned, we will assign
* the CPU based on a simple round robin scheme.
*/
static void init_vp_index(struct vmbus_channel *channel)
{
bool perf_chn = hv_is_perf_channel(channel);
u32 i, ncpu = num_online_cpus();
cpumask_var_t available_mask;
struct cpumask *allocated_mask;
const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
u32 target_cpu;
int numa_node;
if (!perf_chn ||
!alloc_cpumask_var(&available_mask, GFP_KERNEL) ||
cpumask_empty(hk_mask)) {
/*
* If the channel is not a performance critical
* channel, bind it to VMBUS_CONNECT_CPU.
* In case alloc_cpumask_var() fails, bind it to
* VMBUS_CONNECT_CPU.
* If all the cpus are isolated, bind it to
* VMBUS_CONNECT_CPU.
*/
channel->target_cpu = VMBUS_CONNECT_CPU;
if (perf_chn)
hv_set_allocated_cpu(VMBUS_CONNECT_CPU);
return;
}
for (i = 1; i <= ncpu + 1; i++) {
while (true) {
numa_node = next_numa_node_id++;
if (numa_node == nr_node_ids) {
next_numa_node_id = 0;
continue;
}
if (cpumask_empty(cpumask_of_node(numa_node)))
continue;
break;
}
allocated_mask = &hv_context.hv_numa_map[numa_node];
retry:
cpumask_xor(available_mask, allocated_mask, cpumask_of_node(numa_node));
cpumask_and(available_mask, available_mask, hk_mask);
if (cpumask_empty(available_mask)) {
/*
* We have cycled through all the CPUs in the node;
* reset the allocated map.
*/
cpumask_clear(allocated_mask);
goto retry;
}
target_cpu = cpumask_first(available_mask);
cpumask_set_cpu(target_cpu, allocated_mask);
if (channel->offermsg.offer.sub_channel_index >= ncpu ||
i > ncpu || !hv_cpuself_used(target_cpu, channel))
break;
}
channel->target_cpu = target_cpu;
free_cpumask_var(available_mask);
}
#define UNLOAD_DELAY_UNIT_MS 10 /* 10 milliseconds */
#define UNLOAD_WAIT_MS (100*1000) /* 100 seconds */
#define UNLOAD_WAIT_LOOPS (UNLOAD_WAIT_MS/UNLOAD_DELAY_UNIT_MS)
#define UNLOAD_MSG_MS (5*1000) /* Every 5 seconds */
#define UNLOAD_MSG_LOOPS (UNLOAD_MSG_MS/UNLOAD_DELAY_UNIT_MS)
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, i;
/*
* 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.
*
* Wait up to 100 seconds since an Azure host must writeback any dirty
* data in its disk cache before the VMbus UNLOAD request will
* complete. This flushing has been empirically observed to take up
* to 50 seconds in cases with a lot of dirty data, so allow additional
* leeway and for inaccuracies in mdelay(). But eventually time out so
* that the panic path can't get hung forever in case the response
* message isn't seen.
*/
for (i = 1; i <= UNLOAD_WAIT_LOOPS; i++) {
if (completion_done(&vmbus_connection.unload_event))
goto completed;
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);
}
/*
* Give a notice periodically so someone watching the
* serial output won't think it is completely hung.
*/
if (!(i % UNLOAD_MSG_LOOPS))
pr_notice("Waiting for VMBus UNLOAD to complete\n");
mdelay(UNLOAD_DELAY_UNIT_MS);
}
pr_err("Continuing even though VMBus UNLOAD did not complete\n");
completed:
/*
* 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.
*
* NB. A malicious or compromised Hyper-V could send a spurious
* message of type CHANNELMSG_UNLOAD_RESPONSE, and trigger a call
* of the complete() below. Make sure that unload_event has been
* initialized by the time this complete() is executed.
*/
complete(&vmbus_connection.unload_event);
}
void vmbus_initiate_unload(bool crash)
{
struct vmbus_channel_message_header hdr;
if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
return;
/* Pre-Win2012R2 hosts don't support reconnect */
if (vmbus_proto_version < VERSION_WIN8_1)
return;
reinit_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();
}
static void check_ready_for_resume_event(void)
{
/*
* If all the old primary channels have been fixed up, then it's safe
* to resume.
*/
if (atomic_dec_and_test(&vmbus_connection.nr_chan_fixup_on_resume))
complete(&vmbus_connection.ready_for_resume_event);
}
static void vmbus_setup_channel_state(struct vmbus_channel *channel,
struct vmbus_channel_offer_channel *offer)
{
/*
* Setup state for signalling the host.
*/
channel->sig_event = VMBUS_EVENT_CONNECTION_ID;
channel->is_dedicated_interrupt =
(offer->is_dedicated_interrupt != 0);
channel->sig_event = offer->connection_id;
memcpy(&channel->offermsg, offer,
sizeof(struct vmbus_channel_offer_channel));
channel->monitor_grp = (u8)offer->monitorid / 32;
channel->monitor_bit = (u8)offer->monitorid % 32;
channel->device_id = hv_get_dev_type(channel);
}
/*
* find_primary_channel_by_offer - Get the channel object given the new offer.
* This is only used in the resume path of hibernation.
*/
static struct vmbus_channel *
find_primary_channel_by_offer(const struct vmbus_channel_offer_channel *offer)
{
struct vmbus_channel *channel = NULL, *iter;
const guid_t *inst1, *inst2;
/* Ignore sub-channel offers. */
if (offer->offer.sub_channel_index != 0)
return NULL;
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(iter, &vmbus_connection.chn_list, listentry) {
inst1 = &iter->offermsg.offer.if_instance;
inst2 = &offer->offer.if_instance;
if (guid_equal(inst1, inst2)) {
channel = iter;
break;
}
}
mutex_unlock(&vmbus_connection.channel_mutex);
return channel;
}
static bool vmbus_is_valid_offer(const struct vmbus_channel_offer_channel *offer)
{
const guid_t *guid = &offer->offer.if_type;
u16 i;
if (!hv_is_isolation_supported())
return true;
if (is_hvsock_offer(offer))
return true;
for (i = 0; i < ARRAY_SIZE(vmbus_devs); i++) {
if (guid_equal(guid, &vmbus_devs[i].guid))
return vmbus_devs[i].allowed_in_isolated;
}
return false;
}