1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
| | // SPDX-License-Identifier: GPL-2.0-or-later
/*
* vhost-user API, command management and virtio interface
*
* Copyright Red Hat
* Author: Laurent Vivier <lvivier@redhat.com>
*
* Some parts from QEMU subprojects/libvhost-user/libvhost-user.c
* licensed under the following terms:
*
* Copyright IBM, Corp. 2007
* Copyright (c) 2016 Red Hat, Inc.
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
* Marc-André Lureau <mlureau@redhat.com>
* Victor Kaplansky <victork@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include <assert.h>
#include <stdbool.h>
#include <inttypes.h>
#include <time.h>
#include <net/ethernet.h>
#include <netinet/in.h>
#include <sys/epoll.h>
#include <sys/eventfd.h>
#include <sys/mman.h>
#include <linux/vhost_types.h>
#include <linux/virtio_net.h>
#include "util.h"
#include "passt.h"
#include "tap.h"
#include "vhost_user.h"
/* vhost-user version we are compatible with */
#define VHOST_USER_VERSION 1
/**
* vu_print_capabilities() - print vhost-user capabilities
* this is part of the vhost-user backend
* convention.
*/
/* cppcheck-suppress unusedFunction */
void vu_print_capabilities(void)
{
info("{");
info(" \"type\": \"net\"");
info("}");
exit(EXIT_SUCCESS);
}
/**
* vu_request_to_string() - convert a vhost-user request number to its name
* @req: request number
*
* Return: the name of request number
*/
static const char *vu_request_to_string(unsigned int req)
{
if (req < VHOST_USER_MAX) {
#define REQ(req) [req] = #req
static const char * const vu_request_str[VHOST_USER_MAX] = {
REQ(VHOST_USER_NONE),
REQ(VHOST_USER_GET_FEATURES),
REQ(VHOST_USER_SET_FEATURES),
REQ(VHOST_USER_SET_OWNER),
REQ(VHOST_USER_RESET_OWNER),
REQ(VHOST_USER_SET_MEM_TABLE),
REQ(VHOST_USER_SET_LOG_BASE),
REQ(VHOST_USER_SET_LOG_FD),
REQ(VHOST_USER_SET_VRING_NUM),
REQ(VHOST_USER_SET_VRING_ADDR),
REQ(VHOST_USER_SET_VRING_BASE),
REQ(VHOST_USER_GET_VRING_BASE),
REQ(VHOST_USER_SET_VRING_KICK),
REQ(VHOST_USER_SET_VRING_CALL),
REQ(VHOST_USER_SET_VRING_ERR),
REQ(VHOST_USER_GET_PROTOCOL_FEATURES),
REQ(VHOST_USER_SET_PROTOCOL_FEATURES),
REQ(VHOST_USER_GET_QUEUE_NUM),
REQ(VHOST_USER_SET_VRING_ENABLE),
REQ(VHOST_USER_SEND_RARP),
REQ(VHOST_USER_NET_SET_MTU),
REQ(VHOST_USER_SET_BACKEND_REQ_FD),
REQ(VHOST_USER_IOTLB_MSG),
REQ(VHOST_USER_SET_VRING_ENDIAN),
REQ(VHOST_USER_GET_CONFIG),
REQ(VHOST_USER_SET_CONFIG),
REQ(VHOST_USER_POSTCOPY_ADVISE),
REQ(VHOST_USER_POSTCOPY_LISTEN),
REQ(VHOST_USER_POSTCOPY_END),
REQ(VHOST_USER_GET_INFLIGHT_FD),
REQ(VHOST_USER_SET_INFLIGHT_FD),
REQ(VHOST_USER_GPU_SET_SOCKET),
REQ(VHOST_USER_VRING_KICK),
REQ(VHOST_USER_GET_MAX_MEM_SLOTS),
REQ(VHOST_USER_ADD_MEM_REG),
REQ(VHOST_USER_REM_MEM_REG),
};
#undef REQ
return vu_request_str[req];
}
return "unknown";
}
/**
* qva_to_va() - Translate front-end (QEMU) virtual address to our virtual
* address
* @dev: vhost-user device
* @qemu_addr: front-end userspace address
*
* Return: the memory address in our process virtual address space.
*/
static void *qva_to_va(struct vu_dev *dev, uint64_t qemu_addr)
{
unsigned int i;
/* Find matching memory region. */
for (i = 0; i < dev->nregions; i++) {
const struct vu_dev_region *r = &dev->regions[i];
if ((qemu_addr >= r->qva) && (qemu_addr < (r->qva + r->size))) {
/* NOLINTNEXTLINE(performance-no-int-to-ptr) */
return (void *)(qemu_addr - r->qva + r->mmap_addr +
r->mmap_offset);
}
}
return NULL;
}
/**
* vmsg_close_fds() - Close all file descriptors of a given message
* @vmsg: vhost-user message with the list of the file descriptors
*/
static void vmsg_close_fds(const struct vhost_user_msg *vmsg)
{
int i;
for (i = 0; i < vmsg->fd_num; i++)
close(vmsg->fds[i]);
}
/**
* vu_remove_watch() - Remove a file descriptor from our passt epoll
* file descriptor
* @vdev: vhost-user device
* @fd: file descriptor to remove
*/
static void vu_remove_watch(const struct vu_dev *vdev, int fd)
{
/* Placeholder to add passt related code */
(void)vdev;
(void)fd;
}
/**
* vmsg_set_reply_u64() - Set reply payload.u64 and clear request flags
* and fd_num
* @vmsg: vhost-user message
* @val: 64-bit value to reply
*/
static void vmsg_set_reply_u64(struct vhost_user_msg *vmsg, uint64_t val)
{
vmsg->hdr.flags = 0; /* defaults will be set by vu_send_reply() */
vmsg->hdr.size = sizeof(vmsg->payload.u64);
vmsg->payload.u64 = val;
vmsg->fd_num = 0;
}
/**
* vu_message_read_default() - Read incoming vhost-user message from the
* front-end
* @conn_fd: vhost-user command socket
* @vmsg: vhost-user message
*
* Return: 0 if recvmsg() has been interrupted or if there's no data to read,
* 1 if a message has been received
*/
static int vu_message_read_default(int conn_fd, struct vhost_user_msg *vmsg)
{
char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS *
sizeof(int))] = { 0 };
struct iovec iov = {
.iov_base = (char *)vmsg,
.iov_len = VHOST_USER_HDR_SIZE,
};
struct msghdr msg = {
.msg_iov = &iov,
.msg_iovlen = 1,
.msg_control = control,
.msg_controllen = sizeof(control),
};
ssize_t ret, sz_payload;
struct cmsghdr *cmsg;
ret = recvmsg(conn_fd, &msg, MSG_DONTWAIT);
if (ret < 0) {
if (errno == EINTR || errno == EAGAIN || errno == EWOULDBLOCK)
return 0;
die_perror("vhost-user message receive (recvmsg)");
}
vmsg->fd_num = 0;
for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
cmsg = CMSG_NXTHDR(&msg, cmsg)) {
if (cmsg->cmsg_level == SOL_SOCKET &&
cmsg->cmsg_type == SCM_RIGHTS) {
size_t fd_size;
ASSERT(cmsg->cmsg_len >= CMSG_LEN(0));
fd_size = cmsg->cmsg_len - CMSG_LEN(0);
ASSERT(fd_size <= sizeof(vmsg->fds));
vmsg->fd_num = fd_size / sizeof(int);
memcpy(vmsg->fds, CMSG_DATA(cmsg), fd_size);
break;
}
}
sz_payload = vmsg->hdr.size;
if ((size_t)sz_payload > sizeof(vmsg->payload)) {
die("vhost-user message request too big: %d,"
" size: vmsg->size: %zd, "
"while sizeof(vmsg->payload) = %zu",
vmsg->hdr.request, sz_payload, sizeof(vmsg->payload));
}
if (sz_payload) {
do
ret = recv(conn_fd, &vmsg->payload, sz_payload, 0);
while (ret < 0 && errno == EINTR);
if (ret < 0)
die_perror("vhost-user message receive");
if (ret == 0)
die("EOF on vhost-user message receive");
if (ret < sz_payload)
die("Short-read on vhost-user message receive");
}
return 1;
}
/**
* vu_message_write() - Send a message to the front-end
* @conn_fd: vhost-user command socket
* @vmsg: vhost-user message
*
* #syscalls:vu sendmsg
*/
static void vu_message_write(int conn_fd, struct vhost_user_msg *vmsg)
{
char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = { 0 };
struct iovec iov = {
.iov_base = (char *)vmsg,
.iov_len = VHOST_USER_HDR_SIZE + vmsg->hdr.size,
};
struct msghdr msg = {
.msg_iov = &iov,
.msg_iovlen = 1,
.msg_control = control,
};
int rc;
ASSERT(vmsg->fd_num <= VHOST_MEMORY_BASELINE_NREGIONS);
if (vmsg->fd_num > 0) {
size_t fdsize = vmsg->fd_num * sizeof(int);
struct cmsghdr *cmsg;
msg.msg_controllen = CMSG_SPACE(fdsize);
cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_len = CMSG_LEN(fdsize);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
memcpy(CMSG_DATA(cmsg), vmsg->fds, fdsize);
}
do
rc = sendmsg(conn_fd, &msg, 0);
while (rc < 0 && errno == EINTR);
if (rc < 0)
die_perror("vhost-user message send");
if ((uint32_t)rc < VHOST_USER_HDR_SIZE + vmsg->hdr.size)
die("EOF on vhost-user message send");
}
/**
* vu_send_reply() - Update message flags and send it to front-end
* @conn_fd: vhost-user command socket
* @vmsg: vhost-user message
*/
static void vu_send_reply(int conn_fd, struct vhost_user_msg *msg)
{
msg->hdr.flags &= ~VHOST_USER_VERSION_MASK;
msg->hdr.flags |= VHOST_USER_VERSION;
msg->hdr.flags |= VHOST_USER_REPLY_MASK;
vu_message_write(conn_fd, msg);
}
/**
* vu_get_features_exec() - Provide back-end features bitmask to front-end
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: True as a reply is requested
*/
static bool vu_get_features_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
uint64_t features =
1ULL << VIRTIO_F_VERSION_1 |
1ULL << VIRTIO_NET_F_MRG_RXBUF |
1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
(void)vdev;
vmsg_set_reply_u64(msg, features);
debug("Sending back to guest u64: 0x%016"PRIx64, msg->payload.u64);
return true;
}
/**
* vu_set_enable_all_rings() - Enable/disable all the virtqueues
* @vdev: vhost-user device
* @enable: New virtqueues state
*/
static void vu_set_enable_all_rings(struct vu_dev *vdev, bool enable)
{
uint16_t i;
for (i = 0; i < VHOST_USER_MAX_QUEUES; i++)
vdev->vq[i].enable = enable;
}
/**
* vu_set_features_exec() - Enable features of the back-end
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_features_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
debug("u64: 0x%016"PRIx64, msg->payload.u64);
vdev->features = msg->payload.u64;
/* We only support devices conforming to VIRTIO 1.0 or
* later
*/
if (!vu_has_feature(vdev, VIRTIO_F_VERSION_1))
die("virtio legacy devices aren't supported by passt");
if (!vu_has_feature(vdev, VHOST_USER_F_PROTOCOL_FEATURES))
vu_set_enable_all_rings(vdev, true);
return false;
}
/**
* vu_set_owner_exec() - Session start flag, do nothing in our case
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_owner_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
(void)vdev;
(void)msg;
return false;
}
/**
* map_ring() - Convert ring front-end (QEMU) addresses to our process
* virtual address space.
* @vdev: vhost-user device
* @vq: Virtqueue
*
* Return: True if ring cannot be mapped to our address space
*/
static bool map_ring(struct vu_dev *vdev, struct vu_virtq *vq)
{
vq->vring.desc = qva_to_va(vdev, vq->vra.desc_user_addr);
vq->vring.used = qva_to_va(vdev, vq->vra.used_user_addr);
vq->vring.avail = qva_to_va(vdev, vq->vra.avail_user_addr);
debug("Setting virtq addresses:");
debug(" vring_desc at %p", (void *)vq->vring.desc);
debug(" vring_used at %p", (void *)vq->vring.used);
debug(" vring_avail at %p", (void *)vq->vring.avail);
return !(vq->vring.desc && vq->vring.used && vq->vring.avail);
}
/**
* vu_packet_check_range() - Check if a given memory zone is contained in
* a mapped guest memory region
* @buf: Array of the available memory regions
* @offset: Offset of data range in packet descriptor
* @size: Length of desired data range
* @start: Start of the packet descriptor
*
* Return: 0 if the zone is in a mapped memory region, -1 otherwise
*/
/* cppcheck-suppress unusedFunction */
int vu_packet_check_range(void *buf, size_t offset, size_t len,
const char *start)
{
struct vu_dev_region *dev_region;
for (dev_region = buf; dev_region->mmap_addr; dev_region++) {
/* NOLINTNEXTLINE(performance-no-int-to-ptr) */
char *m = (char *)dev_region->mmap_addr;
if (m <= start &&
start + offset + len <= m + dev_region->mmap_offset +
dev_region->size)
return 0;
}
return -1;
}
/**
* vu_set_mem_table_exec() - Sets the memory map regions to be able to
* translate the vring addresses.
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*
* #syscalls:vu mmap munmap
*/
static bool vu_set_mem_table_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
struct vhost_user_memory m = msg->payload.memory, *memory = &m;
unsigned int i;
for (i = 0; i < vdev->nregions; i++) {
struct vu_dev_region *r = &vdev->regions[i];
/* NOLINTNEXTLINE(performance-no-int-to-ptr) */
void *mm = (void *)r->mmap_addr;
if (mm)
munmap(mm, r->size + r->mmap_offset);
}
vdev->nregions = memory->nregions;
debug("vhost-user nregions: %u", memory->nregions);
for (i = 0; i < vdev->nregions; i++) {
struct vhost_user_memory_region *msg_region = &memory->regions[i];
struct vu_dev_region *dev_region = &vdev->regions[i];
void *mmap_addr;
debug("vhost-user region %d", i);
debug(" guest_phys_addr: 0x%016"PRIx64,
msg_region->guest_phys_addr);
debug(" memory_size: 0x%016"PRIx64,
msg_region->memory_size);
debug(" userspace_addr 0x%016"PRIx64,
msg_region->userspace_addr);
debug(" mmap_offset 0x%016"PRIx64,
msg_region->mmap_offset);
dev_region->gpa = msg_region->guest_phys_addr;
dev_region->size = msg_region->memory_size;
dev_region->qva = msg_region->userspace_addr;
dev_region->mmap_offset = msg_region->mmap_offset;
/* We don't use offset argument of mmap() since the
* mapped address has to be page aligned.
*/
mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
PROT_READ | PROT_WRITE, MAP_SHARED |
MAP_NORESERVE, msg->fds[i], 0);
if (mmap_addr == MAP_FAILED)
die_perror("vhost-user region mmap error");
dev_region->mmap_addr = (uint64_t)(uintptr_t)mmap_addr;
debug(" mmap_addr: 0x%016"PRIx64,
dev_region->mmap_addr);
close(msg->fds[i]);
}
for (i = 0; i < VHOST_USER_MAX_QUEUES; i++) {
if (vdev->vq[i].vring.desc) {
if (map_ring(vdev, &vdev->vq[i]))
die("remapping queue %d during setmemtable", i);
}
}
return false;
}
/**
* vu_set_vring_num_exec() - Set the size of the queue (vring size)
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_num_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
unsigned int idx = msg->payload.state.index;
unsigned int num = msg->payload.state.num;
debug("State.index: %u", idx);
debug("State.num: %u", num);
vdev->vq[idx].vring.num = num;
return false;
}
/**
* vu_set_vring_addr_exec() - Set the addresses of the vring
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_addr_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
/* We need to copy the payload to vhost_vring_addr structure
* to access index because address of msg->payload.addr
* can be unaligned as it is packed.
*/
struct vhost_vring_addr addr = msg->payload.addr;
struct vu_virtq *vq = &vdev->vq[addr.index];
debug("vhost_vring_addr:");
debug(" index: %d", addr.index);
debug(" flags: %d", addr.flags);
debug(" desc_user_addr: 0x%016" PRIx64,
(uint64_t)addr.desc_user_addr);
debug(" used_user_addr: 0x%016" PRIx64,
(uint64_t)addr.used_user_addr);
debug(" avail_user_addr: 0x%016" PRIx64,
(uint64_t)addr.avail_user_addr);
debug(" log_guest_addr: 0x%016" PRIx64,
(uint64_t)addr.log_guest_addr);
vq->vra = msg->payload.addr;
vq->vring.flags = addr.flags;
vq->vring.log_guest_addr = addr.log_guest_addr;
if (map_ring(vdev, vq))
die("Invalid vring_addr message");
vq->used_idx = le16toh(vq->vring.used->idx);
if (vq->last_avail_idx != vq->used_idx) {
debug("Last avail index != used index: %u != %u",
vq->last_avail_idx, vq->used_idx);
}
return false;
}
/**
* vu_set_vring_base_exec() - Sets the next index to use for descriptors
* in this vring
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_base_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
unsigned int idx = msg->payload.state.index;
unsigned int num = msg->payload.state.num;
debug("State.index: %u", idx);
debug("State.num: %u", num);
vdev->vq[idx].shadow_avail_idx = vdev->vq[idx].last_avail_idx = num;
return false;
}
/**
* vu_get_vring_base_exec() - Stops the vring and returns the current
* descriptor index or indices
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: True as a reply is requested
*/
static bool vu_get_vring_base_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
unsigned int idx = msg->payload.state.index;
debug("State.index: %u", idx);
msg->payload.state.num = vdev->vq[idx].last_avail_idx;
msg->hdr.size = sizeof(msg->payload.state);
vdev->vq[idx].started = false;
if (vdev->vq[idx].call_fd != -1) {
close(vdev->vq[idx].call_fd);
vdev->vq[idx].call_fd = -1;
}
if (vdev->vq[idx].kick_fd != -1) {
vu_remove_watch(vdev, vdev->vq[idx].kick_fd);
close(vdev->vq[idx].kick_fd);
vdev->vq[idx].kick_fd = -1;
}
return true;
}
/**
* vu_set_watch() - Add a file descriptor to the passt epoll file descriptor
* @vdev: vhost-user device
* @fd: file descriptor to add
*/
static void vu_set_watch(const struct vu_dev *vdev, int fd)
{
/* Placeholder to add passt related code */
(void)vdev;
(void)fd;
}
/**
* vu_wait_queue() - wait for new free entries in the virtqueue
* @vq: virtqueue to wait on
*/
static int vu_wait_queue(const struct vu_virtq *vq)
{
eventfd_t kick_data;
ssize_t rc;
int status;
/* wait for the kernel to put new entries in the queue */
status = fcntl(vq->kick_fd, F_GETFL);
if (status == -1)
return -1;
if (fcntl(vq->kick_fd, F_SETFL, status & ~O_NONBLOCK))
return -1;
rc = eventfd_read(vq->kick_fd, &kick_data);
if (fcntl(vq->kick_fd, F_SETFL, status))
return -1;
if (rc == -1)
return -1;
return 0;
}
/**
* vu_send() - Send a buffer to the front-end using the RX virtqueue
* @vdev: vhost-user device
* @buf: address of the buffer
* @size: size of the buffer
*
* Return: number of bytes sent, -1 if there is an error
*/
/* cppcheck-suppress unusedFunction */
int vu_send(struct vu_dev *vdev, const void *buf, size_t size)
{
struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE];
struct iovec in_sg[VIRTQUEUE_MAX_SIZE];
size_t lens[VIRTQUEUE_MAX_SIZE];
__virtio16 *num_buffers_ptr = NULL;
size_t hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf);
int in_sg_count = 0;
size_t offset = 0;
int i = 0, j;
debug("vu_send size %zu hdrlen %zu", size, hdrlen);
if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) {
err("Got packet, but no available descriptors on RX virtq.");
return 0;
}
while (offset < size) {
size_t len;
int total;
int ret;
total = 0;
if (i == ARRAY_SIZE(elem) ||
in_sg_count == ARRAY_SIZE(in_sg)) {
err("virtio-net unexpected long buffer chain");
goto err;
}
elem[i].out_num = 0;
elem[i].out_sg = NULL;
elem[i].in_num = ARRAY_SIZE(in_sg) - in_sg_count;
elem[i].in_sg = &in_sg[in_sg_count];
ret = vu_queue_pop(vdev, vq, &elem[i]);
if (ret < 0) {
if (vu_wait_queue(vq) != -1)
continue;
if (i) {
err("virtio-net unexpected empty queue: "
"i %d mergeable %d offset %zd, size %zd, "
"features 0x%" PRIx64,
i, vu_has_feature(vdev,
VIRTIO_NET_F_MRG_RXBUF),
offset, size, vdev->features);
}
offset = -1;
goto err;
}
in_sg_count += elem[i].in_num;
if (elem[i].in_num < 1) {
err("virtio-net receive queue contains no in buffers");
vu_queue_detach_element(vq);
offset = -1;
goto err;
}
if (i == 0) {
struct virtio_net_hdr hdr = VU_HEADER;
ASSERT(offset == 0);
ASSERT(elem[i].in_sg[0].iov_len >= hdrlen);
len = iov_from_buf(elem[i].in_sg, elem[i].in_num, 0,
&hdr, sizeof(hdr));
num_buffers_ptr = (__virtio16 *)((char *)elem[i].in_sg[0].iov_base +
len);
total += hdrlen;
}
len = iov_from_buf(elem[i].in_sg, elem[i].in_num, total,
(char *)buf + offset, size - offset);
total += len;
offset += len;
/* If buffers can't be merged, at this point we
* must have consumed the complete packet.
* Otherwise, drop it.
*/
if (!vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) &&
offset < size) {
vu_queue_unpop(vq);
goto err;
}
lens[i] = total;
i++;
}
if (num_buffers_ptr && vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
*num_buffers_ptr = htole16(i);
for (j = 0; j < i; j++) {
debug("filling total %zd idx %d", lens[j], j);
vu_queue_fill(vq, &elem[j], lens[j], j);
}
vu_queue_flush(vq, i);
vu_queue_notify(vdev, vq);
debug("vhost-user sent %zu", offset);
return offset;
err:
for (j = 0; j < i; j++)
vu_queue_detach_element(vq);
return offset;
}
/**
* vu_handle_tx() - Receive data from the TX virtqueue
* @vdev: vhost-user device
* @index: index of the virtqueue
* @now: Current timestamp
*/
static void vu_handle_tx(struct vu_dev *vdev, int index,
const struct timespec *now)
{
struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE];
struct iovec out_sg[VIRTQUEUE_MAX_SIZE];
struct vu_virtq *vq = &vdev->vq[index];
int hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf);
int out_sg_count;
int count;
if (!VHOST_USER_IS_QUEUE_TX(index)) {
debug("vhost-user: index %d is not a TX queue", index);
return;
}
tap_flush_pools();
count = 0;
out_sg_count = 0;
while (count < VIRTQUEUE_MAX_SIZE) {
int ret;
elem[count].out_num = 1;
elem[count].out_sg = &out_sg[out_sg_count];
elem[count].in_num = 0;
elem[count].in_sg = NULL;
ret = vu_queue_pop(vdev, vq, &elem[count]);
if (ret < 0)
break;
out_sg_count += elem[count].out_num;
if (elem[count].out_num < 1) {
debug("virtio-net header not in first element");
break;
}
ASSERT(elem[count].out_num == 1);
tap_add_packet(vdev->context,
elem[count].out_sg[0].iov_len - hdrlen,
(char *)elem[count].out_sg[0].iov_base + hdrlen);
count++;
}
tap_handler(vdev->context, now);
if (count) {
int i;
for (i = 0; i < count; i++)
vu_queue_fill(vq, &elem[i], 0, i);
vu_queue_flush(vq, count);
vu_queue_notify(vdev, vq);
}
}
/**
* vu_kick_cb() - Called on a kick event to start to receive data
* @vdev: vhost-user device
* @ref: epoll reference information
* @now: Current timestamp
*/
/* cppcheck-suppress unusedFunction */
void vu_kick_cb(struct vu_dev *vdev, union epoll_ref ref,
const struct timespec *now)
{
eventfd_t kick_data;
ssize_t rc;
int idx;
for (idx = 0; idx < VHOST_USER_MAX_QUEUES; idx++) {
if (vdev->vq[idx].kick_fd == ref.fd)
break;
}
if (idx == VHOST_USER_MAX_QUEUES)
return;
rc = eventfd_read(ref.fd, &kick_data);
if (rc == -1)
die_perror("vhost-user kick eventfd_read()");
debug("vhost-user: ot kick_data: %016"PRIx64" idx:%d",
kick_data, idx);
if (VHOST_USER_IS_QUEUE_TX(idx))
vu_handle_tx(vdev, idx, now);
}
/**
* vu_check_queue_msg_file() - Check if a message is valid,
* close fds if NOFD bit is set
* @vmsg: vhost-user message
*/
static void vu_check_queue_msg_file(struct vhost_user_msg *msg)
{
bool nofd = msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
int idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
if (idx >= VHOST_USER_MAX_QUEUES)
die("Invalid vhost-user queue index: %u", idx);
if (nofd) {
vmsg_close_fds(msg);
return;
}
if (msg->fd_num != 1)
die("Invalid fds in vhost-user request: %d", msg->hdr.request);
}
/**
* vu_set_vring_kick_exec() - Set the event file descriptor for adding buffers
* to the vring
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_kick_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
bool nofd = msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
int idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
debug("u64: 0x%016"PRIx64, msg->payload.u64);
vu_check_queue_msg_file(msg);
if (vdev->vq[idx].kick_fd != -1) {
vu_remove_watch(vdev, vdev->vq[idx].kick_fd);
close(vdev->vq[idx].kick_fd);
vdev->vq[idx].kick_fd = -1;
}
if (!nofd)
vdev->vq[idx].kick_fd = msg->fds[0];
debug("Got kick_fd: %d for vq: %d", vdev->vq[idx].kick_fd, idx);
vdev->vq[idx].started = true;
if (vdev->vq[idx].kick_fd != -1 && VHOST_USER_IS_QUEUE_TX(idx)) {
vu_set_watch(vdev, vdev->vq[idx].kick_fd);
debug("Waiting for kicks on fd: %d for vq: %d",
vdev->vq[idx].kick_fd, idx);
}
return false;
}
/**
* vu_set_vring_call_exec() - Set the event file descriptor to signal when
* buffers are used
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_call_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
bool nofd = msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
int idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
debug("u64: 0x%016"PRIx64, msg->payload.u64);
vu_check_queue_msg_file(msg);
if (vdev->vq[idx].call_fd != -1) {
close(vdev->vq[idx].call_fd);
vdev->vq[idx].call_fd = -1;
}
if (!nofd)
vdev->vq[idx].call_fd = msg->fds[0];
/* in case of I/O hang after reconnecting */
if (vdev->vq[idx].call_fd != -1)
eventfd_write(msg->fds[0], 1);
debug("Got call_fd: %d for vq: %d", vdev->vq[idx].call_fd, idx);
return false;
}
/**
* vu_set_vring_err_exec() - Set the event file descriptor to signal when
* error occurs
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_err_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
bool nofd = msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
int idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
debug("u64: 0x%016"PRIx64, msg->payload.u64);
vu_check_queue_msg_file(msg);
if (vdev->vq[idx].err_fd != -1) {
close(vdev->vq[idx].err_fd);
vdev->vq[idx].err_fd = -1;
}
if (!nofd)
vdev->vq[idx].err_fd = msg->fds[0];
return false;
}
/**
* vu_get_protocol_features_exec() - Provide the protocol (vhost-user) features
* to the front-end
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: True as a reply is requested
*/
static bool vu_get_protocol_features_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
uint64_t features = 1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK;
(void)vdev;
vmsg_set_reply_u64(msg, features);
return true;
}
/**
* vu_set_protocol_features_exec() - Enable protocol (vhost-user) features
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_protocol_features_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
uint64_t features = msg->payload.u64;
debug("u64: 0x%016"PRIx64, features);
vdev->protocol_features = msg->payload.u64;
return false;
}
/**
* vu_get_queue_num_exec() - Tell how many queues we support
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: True as a reply is requested
*/
static bool vu_get_queue_num_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
(void)vdev;
vmsg_set_reply_u64(msg, VHOST_USER_MAX_QUEUES);
return true;
}
/**
* vu_set_vring_enable_exec() - Enable or disable corresponding vring
* @vdev: vhost-user device
* @vmsg: vhost-user message
*
* Return: False as no reply is requested
*/
static bool vu_set_vring_enable_exec(struct vu_dev *vdev,
struct vhost_user_msg *msg)
{
unsigned int enable = msg->payload.state.num;
unsigned int idx = msg->payload.state.index;
debug("State.index: %u", idx);
debug("State.enable: %u", enable);
if (idx >= VHOST_USER_MAX_QUEUES)
die("Invalid vring_enable index: %u", idx);
vdev->vq[idx].enable = enable;
return false;
}
/**
* vu_init() - Initialize vhost-user device structure
* @c: execution context
* @vdev: vhost-user device
*/
/* cppcheck-suppress unusedFunction */
void vu_init(struct ctx *c, struct vu_dev *vdev)
{
int i;
vdev->context = c;
for (i = 0; i < VHOST_USER_MAX_QUEUES; i++) {
vdev->vq[i] = (struct vu_virtq){
.call_fd = -1,
.kick_fd = -1,
.err_fd = -1,
.notification = true,
};
}
}
/**
* vu_cleanup() - Reset vhost-user device
* @vdev: vhost-user device
*/
/* cppcheck-suppress unusedFunction */
void vu_cleanup(struct vu_dev *vdev)
{
unsigned int i;
for (i = 0; i < VHOST_USER_MAX_QUEUES; i++) {
struct vu_virtq *vq = &vdev->vq[i];
vq->started = false;
vq->notification = true;
if (vq->call_fd != -1) {
close(vq->call_fd);
vq->call_fd = -1;
}
if (vq->err_fd != -1) {
close(vq->err_fd);
vq->err_fd = -1;
}
if (vq->kick_fd != -1) {
vu_remove_watch(vdev, vq->kick_fd);
close(vq->kick_fd);
vq->kick_fd = -1;
}
vq->vring.desc = 0;
vq->vring.used = 0;
vq->vring.avail = 0;
}
for (i = 0; i < vdev->nregions; i++) {
const struct vu_dev_region *r = &vdev->regions[i];
/* NOLINTNEXTLINE(performance-no-int-to-ptr) */
void *m = (void *)r->mmap_addr;
if (m)
munmap(m, r->size + r->mmap_offset);
}
vdev->nregions = 0;
}
/**
* vu_sock_reset() - Reset connection socket
* @vdev: vhost-user device
*/
static void vu_sock_reset(struct vu_dev *vdev)
{
/* Placeholder to add passt related code */
(void)vdev;
}
static bool (*vu_handle[VHOST_USER_MAX])(struct vu_dev *vdev,
struct vhost_user_msg *msg) = {
[VHOST_USER_GET_FEATURES] = vu_get_features_exec,
[VHOST_USER_SET_FEATURES] = vu_set_features_exec,
[VHOST_USER_GET_PROTOCOL_FEATURES] = vu_get_protocol_features_exec,
[VHOST_USER_SET_PROTOCOL_FEATURES] = vu_set_protocol_features_exec,
[VHOST_USER_GET_QUEUE_NUM] = vu_get_queue_num_exec,
[VHOST_USER_SET_OWNER] = vu_set_owner_exec,
[VHOST_USER_SET_MEM_TABLE] = vu_set_mem_table_exec,
[VHOST_USER_SET_VRING_NUM] = vu_set_vring_num_exec,
[VHOST_USER_SET_VRING_ADDR] = vu_set_vring_addr_exec,
[VHOST_USER_SET_VRING_BASE] = vu_set_vring_base_exec,
[VHOST_USER_GET_VRING_BASE] = vu_get_vring_base_exec,
[VHOST_USER_SET_VRING_KICK] = vu_set_vring_kick_exec,
[VHOST_USER_SET_VRING_CALL] = vu_set_vring_call_exec,
[VHOST_USER_SET_VRING_ERR] = vu_set_vring_err_exec,
[VHOST_USER_SET_VRING_ENABLE] = vu_set_vring_enable_exec,
};
/**
* vu_control_handler() - Handle control commands for vhost-user
* @vdev: vhost-user device
* @fd: vhost-user message socket
* @events: epoll events
*/
/* cppcheck-suppress unusedFunction */
void vu_control_handler(struct vu_dev *vdev, int fd, uint32_t events)
{
struct vhost_user_msg msg = { 0 };
bool need_reply, reply_requested;
int ret;
if (events & (EPOLLRDHUP | EPOLLHUP | EPOLLERR)) {
vu_sock_reset(vdev);
return;
}
ret = vu_message_read_default(fd, &msg);
if (ret == 0) {
vu_sock_reset(vdev);
return;
}
debug("================ Vhost user message ================");
debug("Request: %s (%d)", vu_request_to_string(msg.hdr.request),
msg.hdr.request);
debug("Flags: 0x%x", msg.hdr.flags);
debug("Size: %u", msg.hdr.size);
need_reply = msg.hdr.flags & VHOST_USER_NEED_REPLY_MASK;
if (msg.hdr.request >= 0 && msg.hdr.request < VHOST_USER_MAX &&
vu_handle[msg.hdr.request])
reply_requested = vu_handle[msg.hdr.request](vdev, &msg);
else
die("Unhandled request: %d", msg.hdr.request);
/* cppcheck-suppress legacyUninitvar */
if (!reply_requested && need_reply) {
msg.payload.u64 = 0;
msg.hdr.flags = 0;
msg.hdr.size = sizeof(msg.payload.u64);
msg.fd_num = 0;
reply_requested = true;
}
if (reply_requested)
vu_send_reply(fd, &msg);
}
|