forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnetvsc.c
1566 lines (1303 loc) · 43.4 KB
/
netvsc.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 <[email protected]>
* Hank Janssen <[email protected]>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
#include <linux/prefetch.h>
#include <asm/sync_bitops.h>
#include "hyperv_net.h"
#include "netvsc_trace.h"
/*
* Switch the data path from the synthetic interface to the VF
* interface.
*/
void netvsc_switch_datapath(struct net_device *ndev, bool vf)
{
struct net_device_context *net_device_ctx = netdev_priv(ndev);
struct hv_device *dev = net_device_ctx->device_ctx;
struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev);
struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt;
memset(init_pkt, 0, sizeof(struct nvsp_message));
init_pkt->hdr.msg_type = NVSP_MSG4_TYPE_SWITCH_DATA_PATH;
if (vf)
init_pkt->msg.v4_msg.active_dp.active_datapath =
NVSP_DATAPATH_VF;
else
init_pkt->msg.v4_msg.active_dp.active_datapath =
NVSP_DATAPATH_SYNTHETIC;
trace_nvsp_send(ndev, init_pkt);
vmbus_sendpacket(dev->channel, init_pkt,
sizeof(struct nvsp_message),
(unsigned long)init_pkt,
VM_PKT_DATA_INBAND, 0);
}
/* Worker to setup sub channels on initial setup
* Initial hotplug event occurs in softirq context
* and can't wait for channels.
*/
static void netvsc_subchan_work(struct work_struct *w)
{
struct netvsc_device *nvdev =
container_of(w, struct netvsc_device, subchan_work);
struct rndis_device *rdev;
int i, ret;
/* Avoid deadlock with device removal already under RTNL */
if (!rtnl_trylock()) {
schedule_work(w);
return;
}
rdev = nvdev->extension;
if (rdev) {
ret = rndis_set_subchannel(rdev->ndev, nvdev, NULL);
if (ret == 0) {
netif_device_attach(rdev->ndev);
} else {
/* fallback to only primary channel */
for (i = 1; i < nvdev->num_chn; i++)
netif_napi_del(&nvdev->chan_table[i].napi);
nvdev->max_chn = 1;
nvdev->num_chn = 1;
}
}
rtnl_unlock();
}
static struct netvsc_device *alloc_net_device(void)
{
struct netvsc_device *net_device;
net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL);
if (!net_device)
return NULL;
init_waitqueue_head(&net_device->wait_drain);
net_device->destroy = false;
net_device->tx_disable = true;
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
return net_device;
}
static void free_netvsc_device(struct rcu_head *head)
{
struct netvsc_device *nvdev
= container_of(head, struct netvsc_device, rcu);
int i;
kfree(nvdev->extension);
vfree(nvdev->recv_buf);
vfree(nvdev->send_buf);
kfree(nvdev->send_section_map);
for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq);
vfree(nvdev->chan_table[i].mrc.slots);
}
kfree(nvdev);
}
static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
{
call_rcu(&nvdev->rcu, free_netvsc_device);
}
static void netvsc_revoke_recv_buf(struct hv_device *device,
struct netvsc_device *net_device,
struct net_device *ndev)
{
struct nvsp_message *revoke_packet;
int ret;
/*
* If we got a section count, it means we received a
* SendReceiveBufferComplete msg (ie sent
* NvspMessage1TypeSendReceiveBuffer msg) therefore, we need
* to send a revoke msg here
*/
if (net_device->recv_section_cnt) {
/* Send the revoke receive buffer */
revoke_packet = &net_device->revoke_packet;
memset(revoke_packet, 0, sizeof(struct nvsp_message));
revoke_packet->hdr.msg_type =
NVSP_MSG1_TYPE_REVOKE_RECV_BUF;
revoke_packet->msg.v1_msg.
revoke_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;
trace_nvsp_send(ndev, revoke_packet);
ret = vmbus_sendpacket(device->channel,
revoke_packet,
sizeof(struct nvsp_message),
(unsigned long)revoke_packet,
VM_PKT_DATA_INBAND, 0);
/* If the failure is because the channel is rescinded;
* ignore the failure since we cannot send on a rescinded
* channel. This would allow us to properly cleanup
* even when the channel is rescinded.
*/
if (device->channel->rescind)
ret = 0;
/*
* If we failed here, we might as well return and
* have a leak rather than continue and a bugchk
*/
if (ret != 0) {
netdev_err(ndev, "unable to send "
"revoke receive buffer to netvsp\n");
return;
}
net_device->recv_section_cnt = 0;
}
}
static void netvsc_revoke_send_buf(struct hv_device *device,
struct netvsc_device *net_device,
struct net_device *ndev)
{
struct nvsp_message *revoke_packet;
int ret;
/* Deal with the send buffer we may have setup.
* If we got a send section size, it means we received a
* NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE msg (ie sent
* NVSP_MSG1_TYPE_SEND_SEND_BUF msg) therefore, we need
* to send a revoke msg here
*/
if (net_device->send_section_cnt) {
/* Send the revoke receive buffer */
revoke_packet = &net_device->revoke_packet;
memset(revoke_packet, 0, sizeof(struct nvsp_message));
revoke_packet->hdr.msg_type =
NVSP_MSG1_TYPE_REVOKE_SEND_BUF;
revoke_packet->msg.v1_msg.revoke_send_buf.id =
NETVSC_SEND_BUFFER_ID;
trace_nvsp_send(ndev, revoke_packet);
ret = vmbus_sendpacket(device->channel,
revoke_packet,
sizeof(struct nvsp_message),
(unsigned long)revoke_packet,
VM_PKT_DATA_INBAND, 0);
/* If the failure is because the channel is rescinded;
* ignore the failure since we cannot send on a rescinded
* channel. This would allow us to properly cleanup
* even when the channel is rescinded.
*/
if (device->channel->rescind)
ret = 0;
/* If we failed here, we might as well return and
* have a leak rather than continue and a bugchk
*/
if (ret != 0) {
netdev_err(ndev, "unable to send "
"revoke send buffer to netvsp\n");
return;
}
net_device->send_section_cnt = 0;
}
}
static void netvsc_teardown_recv_gpadl(struct hv_device *device,
struct netvsc_device *net_device,
struct net_device *ndev)
{
int ret;
if (net_device->recv_buf_gpadl_handle) {
ret = vmbus_teardown_gpadl(device->channel,
net_device->recv_buf_gpadl_handle);
/* If we failed here, we might as well return and have a leak
* rather than continue and a bugchk
*/
if (ret != 0) {
netdev_err(ndev,
"unable to teardown receive buffer's gpadl\n");
return;
}
net_device->recv_buf_gpadl_handle = 0;
}
}
static void netvsc_teardown_send_gpadl(struct hv_device *device,
struct netvsc_device *net_device,
struct net_device *ndev)
{
int ret;
if (net_device->send_buf_gpadl_handle) {
ret = vmbus_teardown_gpadl(device->channel,
net_device->send_buf_gpadl_handle);
/* If we failed here, we might as well return and have a leak
* rather than continue and a bugchk
*/
if (ret != 0) {
netdev_err(ndev,
"unable to teardown send buffer's gpadl\n");
return;
}
net_device->send_buf_gpadl_handle = 0;
}
}
int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx)
{
struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
int node = cpu_to_node(nvchan->channel->target_cpu);
size_t size;
size = net_device->recv_completion_cnt * sizeof(struct recv_comp_data);
nvchan->mrc.slots = vzalloc_node(size, node);
if (!nvchan->mrc.slots)
nvchan->mrc.slots = vzalloc(size);
return nvchan->mrc.slots ? 0 : -ENOMEM;
}
static int netvsc_init_buf(struct hv_device *device,
struct netvsc_device *net_device,
const struct netvsc_device_info *device_info)
{
struct nvsp_1_message_send_receive_buffer_complete *resp;
struct net_device *ndev = hv_get_drvdata(device);
struct nvsp_message *init_packet;
unsigned int buf_size;
size_t map_words;
int ret = 0;
/* Get receive buffer area. */
buf_size = device_info->recv_sections * device_info->recv_section_size;
buf_size = roundup(buf_size, PAGE_SIZE);
/* Legacy hosts only allow smaller receive buffer */
if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
buf_size = min_t(unsigned int, buf_size,
NETVSC_RECEIVE_BUFFER_SIZE_LEGACY);
net_device->recv_buf = vzalloc(buf_size);
if (!net_device->recv_buf) {
netdev_err(ndev,
"unable to allocate receive buffer of size %u\n",
buf_size);
ret = -ENOMEM;
goto cleanup;
}
net_device->recv_buf_size = buf_size;
/*
* Establish the gpadl handle for this buffer on this
* channel. Note: This call uses the vmbus connection rather
* than the channel to establish the gpadl handle.
*/
ret = vmbus_establish_gpadl(device->channel, net_device->recv_buf,
buf_size,
&net_device->recv_buf_gpadl_handle);
if (ret != 0) {
netdev_err(ndev,
"unable to establish receive buffer's gpadl\n");
goto cleanup;
}
/* Notify the NetVsp of the gpadl handle */
init_packet = &net_device->channel_init_pkt;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_RECV_BUF;
init_packet->msg.v1_msg.send_recv_buf.
gpadl_handle = net_device->recv_buf_gpadl_handle;
init_packet->msg.v1_msg.
send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;
trace_nvsp_send(ndev, init_packet);
/* Send the gpadl notification request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret != 0) {
netdev_err(ndev,
"unable to send receive buffer's gpadl to netvsp\n");
goto cleanup;
}
wait_for_completion(&net_device->channel_init_wait);
/* Check the response */
resp = &init_packet->msg.v1_msg.send_recv_buf_complete;
if (resp->status != NVSP_STAT_SUCCESS) {
netdev_err(ndev,
"Unable to complete receive buffer initialization with NetVsp - status %d\n",
resp->status);
ret = -EINVAL;
goto cleanup;
}
/* Parse the response */
netdev_dbg(ndev, "Receive sections: %u sub_allocs: size %u count: %u\n",
resp->num_sections, resp->sections[0].sub_alloc_size,
resp->sections[0].num_sub_allocs);
/* There should only be one section for the entire receive buffer */
if (resp->num_sections != 1 || resp->sections[0].offset != 0) {
ret = -EINVAL;
goto cleanup;
}
net_device->recv_section_size = resp->sections[0].sub_alloc_size;
net_device->recv_section_cnt = resp->sections[0].num_sub_allocs;
/* Ensure buffer will not overflow */
if (net_device->recv_section_size < NETVSC_MTU_MIN || (u64)net_device->recv_section_size *
(u64)net_device->recv_section_cnt > (u64)buf_size) {
netdev_err(ndev, "invalid recv_section_size %u\n",
net_device->recv_section_size);
ret = -EINVAL;
goto cleanup;
}
/* Setup receive completion ring.
* Add 1 to the recv_section_cnt because at least one entry in a
* ring buffer has to be empty.
*/
net_device->recv_completion_cnt = net_device->recv_section_cnt + 1;
ret = netvsc_alloc_recv_comp_ring(net_device, 0);
if (ret)
goto cleanup;
/* Now setup the send buffer. */
buf_size = device_info->send_sections * device_info->send_section_size;
buf_size = round_up(buf_size, PAGE_SIZE);
net_device->send_buf = vzalloc(buf_size);
if (!net_device->send_buf) {
netdev_err(ndev, "unable to allocate send buffer of size %u\n",
buf_size);
ret = -ENOMEM;
goto cleanup;
}
/* Establish the gpadl handle for this buffer on this
* channel. Note: This call uses the vmbus connection rather
* than the channel to establish the gpadl handle.
*/
ret = vmbus_establish_gpadl(device->channel, net_device->send_buf,
buf_size,
&net_device->send_buf_gpadl_handle);
if (ret != 0) {
netdev_err(ndev,
"unable to establish send buffer's gpadl\n");
goto cleanup;
}
/* Notify the NetVsp of the gpadl handle */
init_packet = &net_device->channel_init_pkt;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
init_packet->msg.v1_msg.send_send_buf.gpadl_handle =
net_device->send_buf_gpadl_handle;
init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID;
trace_nvsp_send(ndev, init_packet);
/* Send the gpadl notification request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret != 0) {
netdev_err(ndev,
"unable to send send buffer's gpadl to netvsp\n");
goto cleanup;
}
wait_for_completion(&net_device->channel_init_wait);
/* Check the response */
if (init_packet->msg.v1_msg.
send_send_buf_complete.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "Unable to complete send buffer "
"initialization with NetVsp - status %d\n",
init_packet->msg.v1_msg.
send_send_buf_complete.status);
ret = -EINVAL;
goto cleanup;
}
/* Parse the response */
net_device->send_section_size = init_packet->msg.
v1_msg.send_send_buf_complete.section_size;
if (net_device->send_section_size < NETVSC_MTU_MIN) {
netdev_err(ndev, "invalid send_section_size %u\n",
net_device->send_section_size);
ret = -EINVAL;
goto cleanup;
}
/* Section count is simply the size divided by the section size. */
net_device->send_section_cnt = buf_size / net_device->send_section_size;
netdev_dbg(ndev, "Send section size: %d, Section count:%d\n",
net_device->send_section_size, net_device->send_section_cnt);
/* Setup state for managing the send buffer. */
map_words = DIV_ROUND_UP(net_device->send_section_cnt, BITS_PER_LONG);
net_device->send_section_map = kcalloc(map_words, sizeof(ulong), GFP_KERNEL);
if (net_device->send_section_map == NULL) {
ret = -ENOMEM;
goto cleanup;
}
goto exit;
cleanup:
netvsc_revoke_recv_buf(device, net_device, ndev);
netvsc_revoke_send_buf(device, net_device, ndev);
netvsc_teardown_recv_gpadl(device, net_device, ndev);
netvsc_teardown_send_gpadl(device, net_device, ndev);
exit:
return ret;
}
/* Negotiate NVSP protocol version */
static int negotiate_nvsp_ver(struct hv_device *device,
struct netvsc_device *net_device,
struct nvsp_message *init_packet,
u32 nvsp_ver)
{
struct net_device *ndev = hv_get_drvdata(device);
int ret;
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG_TYPE_INIT;
init_packet->msg.init_msg.init.min_protocol_ver = nvsp_ver;
init_packet->msg.init_msg.init.max_protocol_ver = nvsp_ver;
trace_nvsp_send(ndev, init_packet);
/* Send the init request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret != 0)
return ret;
wait_for_completion(&net_device->channel_init_wait);
if (init_packet->msg.init_msg.init_complete.status !=
NVSP_STAT_SUCCESS)
return -EINVAL;
if (nvsp_ver == NVSP_PROTOCOL_VERSION_1)
return 0;
/* NVSPv2 or later: Send NDIS config */
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG2_TYPE_SEND_NDIS_CONFIG;
init_packet->msg.v2_msg.send_ndis_config.mtu = ndev->mtu + ETH_HLEN;
init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;
if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) {
init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
/* Teaming bit is needed to receive link speed updates */
init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1;
}
if (nvsp_ver >= NVSP_PROTOCOL_VERSION_61)
init_packet->msg.v2_msg.send_ndis_config.capability.rsc = 1;
trace_nvsp_send(ndev, init_packet);
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND, 0);
return ret;
}
static int netvsc_connect_vsp(struct hv_device *device,
struct netvsc_device *net_device,
const struct netvsc_device_info *device_info)
{
struct net_device *ndev = hv_get_drvdata(device);
static const u32 ver_list[] = {
NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5,
NVSP_PROTOCOL_VERSION_6, NVSP_PROTOCOL_VERSION_61
};
struct nvsp_message *init_packet;
int ndis_version, i, ret;
init_packet = &net_device->channel_init_pkt;
/* Negotiate the latest NVSP protocol supported */
for (i = ARRAY_SIZE(ver_list) - 1; i >= 0; i--)
if (negotiate_nvsp_ver(device, net_device, init_packet,
ver_list[i]) == 0) {
net_device->nvsp_version = ver_list[i];
break;
}
if (i < 0) {
ret = -EPROTO;
goto cleanup;
}
pr_debug("Negotiated NVSP version:%x\n", net_device->nvsp_version);
/* Send the ndis version */
memset(init_packet, 0, sizeof(struct nvsp_message));
if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_4)
ndis_version = 0x00060001;
else
ndis_version = 0x0006001e;
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_NDIS_VER;
init_packet->msg.v1_msg.
send_ndis_ver.ndis_major_ver =
(ndis_version & 0xFFFF0000) >> 16;
init_packet->msg.v1_msg.
send_ndis_ver.ndis_minor_ver =
ndis_version & 0xFFFF;
trace_nvsp_send(ndev, init_packet);
/* Send the init request */
ret = vmbus_sendpacket(device->channel, init_packet,
sizeof(struct nvsp_message),
(unsigned long)init_packet,
VM_PKT_DATA_INBAND, 0);
if (ret != 0)
goto cleanup;
ret = netvsc_init_buf(device, net_device, device_info);
cleanup:
return ret;
}
/*
* netvsc_device_remove - Callback when the root bus device is removed
*/
void netvsc_device_remove(struct hv_device *device)
{
struct net_device *ndev = hv_get_drvdata(device);
struct net_device_context *net_device_ctx = netdev_priv(ndev);
struct netvsc_device *net_device
= rtnl_dereference(net_device_ctx->nvdev);
int i;
/*
* Revoke receive buffer. If host is pre-Win2016 then tear down
* receive buffer GPADL. Do the same for send buffer.
*/
netvsc_revoke_recv_buf(device, net_device, ndev);
if (vmbus_proto_version < VERSION_WIN10)
netvsc_teardown_recv_gpadl(device, net_device, ndev);
netvsc_revoke_send_buf(device, net_device, ndev);
if (vmbus_proto_version < VERSION_WIN10)
netvsc_teardown_send_gpadl(device, net_device, ndev);
RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
/* Disable NAPI and disassociate its context from the device. */
for (i = 0; i < net_device->num_chn; i++) {
/* See also vmbus_reset_channel_cb(). */
napi_disable(&net_device->chan_table[i].napi);
netif_napi_del(&net_device->chan_table[i].napi);
}
/*
* At this point, no one should be accessing net_device
* except in here
*/
netdev_dbg(ndev, "net device safe to remove\n");
/* Now, we can close the channel safely */
vmbus_close(device->channel);
/*
* If host is Win2016 or higher then we do the GPADL tear down
* here after VMBus is closed.
*/
if (vmbus_proto_version >= VERSION_WIN10) {
netvsc_teardown_recv_gpadl(device, net_device, ndev);
netvsc_teardown_send_gpadl(device, net_device, ndev);
}
/* Release all resources */
free_netvsc_device_rcu(net_device);
}
#define RING_AVAIL_PERCENT_HIWATER 20
#define RING_AVAIL_PERCENT_LOWATER 10
static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
u32 index)
{
sync_change_bit(index, net_device->send_section_map);
}
static void netvsc_send_tx_complete(struct net_device *ndev,
struct netvsc_device *net_device,
struct vmbus_channel *channel,
const struct vmpacket_descriptor *desc,
int budget)
{
struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
struct net_device_context *ndev_ctx = netdev_priv(ndev);
u16 q_idx = 0;
int queue_sends;
/* Notify the layer above us */
if (likely(skb)) {
const struct hv_netvsc_packet *packet
= (struct hv_netvsc_packet *)skb->cb;
u32 send_index = packet->send_buf_index;
struct netvsc_stats *tx_stats;
if (send_index != NETVSC_INVALID_INDEX)
netvsc_free_send_slot(net_device, send_index);
q_idx = packet->q_idx;
tx_stats = &net_device->chan_table[q_idx].tx_stats;
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->packets += packet->total_packets;
tx_stats->bytes += packet->total_bytes;
u64_stats_update_end(&tx_stats->syncp);
napi_consume_skb(skb, budget);
}
queue_sends =
atomic_dec_return(&net_device->chan_table[q_idx].queue_sends);
if (unlikely(net_device->destroy)) {
if (queue_sends == 0)
wake_up(&net_device->wait_drain);
} else {
struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
(hv_get_avail_to_write_percent(&channel->outbound) >
RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
netif_tx_wake_queue(txq);
ndev_ctx->eth_stats.wake_queue++;
}
}
}
static void netvsc_send_completion(struct net_device *ndev,
struct netvsc_device *net_device,
struct vmbus_channel *incoming_channel,
const struct vmpacket_descriptor *desc,
int budget)
{
const struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
u32 msglen = hv_pkt_datalen(desc);
/* Ensure packet is big enough to read header fields */
if (msglen < sizeof(struct nvsp_message_header)) {
netdev_err(ndev, "nvsp_message length too small: %u\n", msglen);
return;
}
switch (nvsp_packet->hdr.msg_type) {
case NVSP_MSG_TYPE_INIT_COMPLETE:
if (msglen < sizeof(struct nvsp_message_header) +
sizeof(struct nvsp_message_init_complete)) {
netdev_err(ndev, "nvsp_msg length too small: %u\n",
msglen);
return;
}
fallthrough;
case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
if (msglen < sizeof(struct nvsp_message_header) +
sizeof(struct nvsp_1_message_send_receive_buffer_complete)) {
netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
msglen);
return;
}
fallthrough;
case NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE:
if (msglen < sizeof(struct nvsp_message_header) +
sizeof(struct nvsp_1_message_send_send_buffer_complete)) {
netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
msglen);
return;
}
fallthrough;
case NVSP_MSG5_TYPE_SUBCHANNEL:
if (msglen < sizeof(struct nvsp_message_header) +
sizeof(struct nvsp_5_subchannel_complete)) {
netdev_err(ndev, "nvsp_msg5 length too small: %u\n",
msglen);
return;
}
/* Copy the response back */
memcpy(&net_device->channel_init_pkt, nvsp_packet,
sizeof(struct nvsp_message));
complete(&net_device->channel_init_wait);
break;
case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
netvsc_send_tx_complete(ndev, net_device, incoming_channel,
desc, budget);
break;
default:
netdev_err(ndev,
"Unknown send completion type %d received!!\n",
nvsp_packet->hdr.msg_type);
}
}
static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
{
unsigned long *map_addr = net_device->send_section_map;
unsigned int i;
for_each_clear_bit(i, map_addr, net_device->send_section_cnt) {
if (sync_test_and_set_bit(i, map_addr) == 0)
return i;
}
return NETVSC_INVALID_INDEX;
}
static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
unsigned int section_index,
u32 pend_size,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
struct hv_page_buffer *pb,
bool xmit_more)
{
char *start = net_device->send_buf;
char *dest = start + (section_index * net_device->send_section_size)
+ pend_size;
int i;
u32 padding = 0;
u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
packet->page_buf_cnt;
u32 remain;
/* Add padding */
remain = packet->total_data_buflen & (net_device->pkt_align - 1);
if (xmit_more && remain) {
padding = net_device->pkt_align - remain;
rndis_msg->msg_len += padding;
packet->total_data_buflen += padding;
}
for (i = 0; i < page_count; i++) {
char *src = phys_to_virt(pb[i].pfn << HV_HYP_PAGE_SHIFT);
u32 offset = pb[i].offset;
u32 len = pb[i].len;
memcpy(dest, (src + offset), len);
dest += len;
}
if (padding)
memset(dest, 0, padding);
}
static inline int netvsc_send_pkt(
struct hv_device *device,
struct hv_netvsc_packet *packet,
struct netvsc_device *net_device,
struct hv_page_buffer *pb,
struct sk_buff *skb)
{
struct nvsp_message nvmsg;
struct nvsp_1_message_send_rndis_packet *rpkt =
&nvmsg.msg.v1_msg.send_rndis_pkt;
struct netvsc_channel * const nvchan =
&net_device->chan_table[packet->q_idx];
struct vmbus_channel *out_channel = nvchan->channel;
struct net_device *ndev = hv_get_drvdata(device);
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
u64 req_id;
int ret;
u32 ring_avail = hv_get_avail_to_write_percent(&out_channel->outbound);
nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
if (skb)
rpkt->channel_type = 0; /* 0 is RMC_DATA */
else
rpkt->channel_type = 1; /* 1 is RMC_CONTROL */
rpkt->send_buf_section_index = packet->send_buf_index;
if (packet->send_buf_index == NETVSC_INVALID_INDEX)
rpkt->send_buf_section_size = 0;
else
rpkt->send_buf_section_size = packet->total_data_buflen;
req_id = (ulong)skb;
if (out_channel->rescind)
return -ENODEV;
trace_nvsp_send_pkt(ndev, out_channel, rpkt);
if (packet->page_buf_cnt) {
if (packet->cp_partial)
pb += packet->rmsg_pgcnt;
ret = vmbus_sendpacket_pagebuffer(out_channel,
pb, packet->page_buf_cnt,
&nvmsg, sizeof(nvmsg),
req_id);
} else {
ret = vmbus_sendpacket(out_channel,
&nvmsg, sizeof(nvmsg),
req_id, VM_PKT_DATA_INBAND,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
}
if (ret == 0) {
atomic_inc_return(&nvchan->queue_sends);
if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
netif_tx_stop_queue(txq);
ndev_ctx->eth_stats.stop_queue++;
}
} else if (ret == -EAGAIN) {
netif_tx_stop_queue(txq);
ndev_ctx->eth_stats.stop_queue++;
} else {
netdev_err(ndev,
"Unable to send packet pages %u len %u, ret %d\n",
packet->page_buf_cnt, packet->total_data_buflen,
ret);
}
if (netif_tx_queue_stopped(txq) &&
atomic_read(&nvchan->queue_sends) < 1 &&
!net_device->tx_disable) {
netif_tx_wake_queue(txq);
ndev_ctx->eth_stats.wake_queue++;
if (ret == -EAGAIN)
ret = -ENOSPC;
}
return ret;
}
/* Move packet out of multi send data (msd), and clear msd */
static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
struct sk_buff **msd_skb,
struct multi_send_data *msdp)
{
*msd_skb = msdp->skb;
*msd_send = msdp->pkt;
msdp->skb = NULL;
msdp->pkt = NULL;
msdp->count = 0;
}
/* RCU already held by caller */
int netvsc_send(struct net_device *ndev,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
struct hv_page_buffer *pb,
struct sk_buff *skb,
bool xdp_tx)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct netvsc_device *net_device
= rcu_dereference_bh(ndev_ctx->nvdev);
struct hv_device *device = ndev_ctx->device_ctx;
int ret = 0;
struct netvsc_channel *nvchan;
u32 pktlen = packet->total_data_buflen, msd_len = 0;
unsigned int section_index = NETVSC_INVALID_INDEX;
struct multi_send_data *msdp;
struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
struct sk_buff *msd_skb = NULL;
bool try_batch, xmit_more;
/* If device is rescinded, return error and packet will get dropped. */
if (unlikely(!net_device || net_device->destroy))
return -ENODEV;
nvchan = &net_device->chan_table[packet->q_idx];
packet->send_buf_index = NETVSC_INVALID_INDEX;
packet->cp_partial = false;
/* Send a control message or XDP packet directly without accessing
* msd (Multi-Send Data) field which may be changed during data packet
* processing.
*/
if (!skb || xdp_tx)
return netvsc_send_pkt(device, packet, net_device, pb, skb);
/* batch packets in send buffer if possible */
msdp = &nvchan->msd;
if (msdp->pkt)
msd_len = msdp->pkt->total_data_buflen;
try_batch = msd_len > 0 && msdp->count < net_device->max_pkt;
if (try_batch && msd_len + pktlen + net_device->pkt_align <
net_device->send_section_size) {
section_index = msdp->pkt->send_buf_index;