-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvhost-user-bridge.c
1418 lines (1198 loc) · 38.4 KB
/
vhost-user-bridge.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
/*
* Vhost User Bridge
*
* Copyright (c) 2015 Red Hat, Inc.
*
* Authors:
* Victor Kaplansky <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
/*
* TODO:
* - main should get parameters from the command line.
* - implement all request handlers. Still not implemented:
* vubr_get_queue_num_exec()
* vubr_send_rarp_exec()
* - test for broken requests and virtqueue.
* - implement features defined by Virtio 1.0 spec.
* - support mergeable buffers and indirect descriptors.
* - implement clean shutdown.
* - implement non-blocking writes to UDP backend.
* - implement polling strategy.
* - implement clean starting/stopping of vq processing
* - implement clean starting/stopping of used and buffers
* dirty page logging.
*/
#define _FILE_OFFSET_BITS 64
#include "qemu/osdep.h"
#include <sys/socket.h>
#include <sys/un.h>
#include <sys/unistd.h>
#include <sys/mman.h>
#include <sys/eventfd.h>
#include <arpa/inet.h>
#include <netdb.h>
#include <qemu/osdep.h>
#include <linux/vhost.h>
#include "qemu/atomic.h"
#include "standard-headers/linux/virtio_net.h"
#include "standard-headers/linux/virtio_ring.h"
#define VHOST_USER_BRIDGE_DEBUG 1
#define DPRINT(...) \
do { \
if (VHOST_USER_BRIDGE_DEBUG) { \
printf(__VA_ARGS__); \
} \
} while (0)
typedef void (*CallbackFunc)(int sock, void *ctx);
typedef struct Event {
void *ctx;
CallbackFunc callback;
} Event;
typedef struct Dispatcher {
int max_sock;
fd_set fdset;
Event events[FD_SETSIZE];
} Dispatcher;
static void
vubr_die(const char *s)
{
perror(s);
exit(1);
}
static int
dispatcher_init(Dispatcher *dispr)
{
FD_ZERO(&dispr->fdset);
dispr->max_sock = -1;
return 0;
}
static int
dispatcher_add(Dispatcher *dispr, int sock, void *ctx, CallbackFunc cb)
{
if (sock >= FD_SETSIZE) {
fprintf(stderr,
"Error: Failed to add new event. sock %d should be less than %d\n",
sock, FD_SETSIZE);
return -1;
}
dispr->events[sock].ctx = ctx;
dispr->events[sock].callback = cb;
FD_SET(sock, &dispr->fdset);
if (sock > dispr->max_sock) {
dispr->max_sock = sock;
}
DPRINT("Added sock %d for watching. max_sock: %d\n",
sock, dispr->max_sock);
return 0;
}
/* dispatcher_remove() is not currently in use but may be useful
* in the future. */
static int
dispatcher_remove(Dispatcher *dispr, int sock)
{
if (sock >= FD_SETSIZE) {
fprintf(stderr,
"Error: Failed to remove event. sock %d should be less than %d\n",
sock, FD_SETSIZE);
return -1;
}
FD_CLR(sock, &dispr->fdset);
DPRINT("Sock %d removed from dispatcher watch.\n", sock);
return 0;
}
/* timeout in us */
static int
dispatcher_wait(Dispatcher *dispr, uint32_t timeout)
{
struct timeval tv;
tv.tv_sec = timeout / 1000000;
tv.tv_usec = timeout % 1000000;
fd_set fdset = dispr->fdset;
/* wait until some of sockets become readable. */
int rc = select(dispr->max_sock + 1, &fdset, 0, 0, &tv);
if (rc == -1) {
vubr_die("select");
}
/* Timeout */
if (rc == 0) {
return 0;
}
/* Now call callback for every ready socket. */
int sock;
for (sock = 0; sock < dispr->max_sock + 1; sock++) {
/* The callback on a socket can remove other sockets from the
* dispatcher, thus we have to check that the socket is
* still not removed from dispatcher's list
*/
if (FD_ISSET(sock, &fdset) && FD_ISSET(sock, &dispr->fdset)) {
Event *e = &dispr->events[sock];
e->callback(sock, e->ctx);
}
}
return 0;
}
typedef struct VubrVirtq {
int call_fd;
int kick_fd;
uint32_t size;
uint16_t last_avail_index;
uint16_t last_used_index;
struct vring_desc *desc;
struct vring_avail *avail;
struct vring_used *used;
uint64_t log_guest_addr;
int enable;
} VubrVirtq;
/* Based on qemu/hw/virtio/vhost-user.c */
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
/* v1.0 compliant. */
#define VIRTIO_F_VERSION_1 32
#define VHOST_LOG_PAGE 4096
enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_MQ = 0,
VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
VHOST_USER_PROTOCOL_F_RARP = 2,
VHOST_USER_PROTOCOL_F_MAX
};
#define VHOST_USER_PROTOCOL_FEATURE_MASK ((1 << VHOST_USER_PROTOCOL_F_MAX) - 1)
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
VHOST_USER_GET_FEATURES = 1,
VHOST_USER_SET_FEATURES = 2,
VHOST_USER_SET_OWNER = 3,
VHOST_USER_RESET_OWNER = 4,
VHOST_USER_SET_MEM_TABLE = 5,
VHOST_USER_SET_LOG_BASE = 6,
VHOST_USER_SET_LOG_FD = 7,
VHOST_USER_SET_VRING_NUM = 8,
VHOST_USER_SET_VRING_ADDR = 9,
VHOST_USER_SET_VRING_BASE = 10,
VHOST_USER_GET_VRING_BASE = 11,
VHOST_USER_SET_VRING_KICK = 12,
VHOST_USER_SET_VRING_CALL = 13,
VHOST_USER_SET_VRING_ERR = 14,
VHOST_USER_GET_PROTOCOL_FEATURES = 15,
VHOST_USER_SET_PROTOCOL_FEATURES = 16,
VHOST_USER_GET_QUEUE_NUM = 17,
VHOST_USER_SET_VRING_ENABLE = 18,
VHOST_USER_SEND_RARP = 19,
VHOST_USER_MAX
} VhostUserRequest;
typedef struct VhostUserMemoryRegion {
uint64_t guest_phys_addr;
uint64_t memory_size;
uint64_t userspace_addr;
uint64_t mmap_offset;
} VhostUserMemoryRegion;
typedef struct VhostUserMemory {
uint32_t nregions;
uint32_t padding;
VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS];
} VhostUserMemory;
typedef struct VhostUserLog {
uint64_t mmap_size;
uint64_t mmap_offset;
} VhostUserLog;
typedef struct VhostUserMsg {
VhostUserRequest request;
#define VHOST_USER_VERSION_MASK (0x3)
#define VHOST_USER_REPLY_MASK (0x1<<2)
uint32_t flags;
uint32_t size; /* the following payload size */
union {
#define VHOST_USER_VRING_IDX_MASK (0xff)
#define VHOST_USER_VRING_NOFD_MASK (0x1<<8)
uint64_t u64;
struct vhost_vring_state state;
struct vhost_vring_addr addr;
VhostUserMemory memory;
VhostUserLog log;
} payload;
int fds[VHOST_MEMORY_MAX_NREGIONS];
int fd_num;
} QEMU_PACKED VhostUserMsg;
#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64)
/* The version of the protocol we support */
#define VHOST_USER_VERSION (0x1)
#define MAX_NR_VIRTQUEUE (8)
typedef struct VubrDevRegion {
/* Guest Physical address. */
uint64_t gpa;
/* Memory region size. */
uint64_t size;
/* QEMU virtual address (userspace). */
uint64_t qva;
/* Starting offset in our mmaped space. */
uint64_t mmap_offset;
/* Start address of mmaped space. */
uint64_t mmap_addr;
} VubrDevRegion;
typedef struct VubrDev {
int sock;
Dispatcher dispatcher;
uint32_t nregions;
VubrDevRegion regions[VHOST_MEMORY_MAX_NREGIONS];
VubrVirtq vq[MAX_NR_VIRTQUEUE];
int log_call_fd;
uint64_t log_size;
uint8_t *log_table;
int backend_udp_sock;
struct sockaddr_in backend_udp_dest;
int ready;
uint64_t features;
int hdrlen;
} VubrDev;
static const char *vubr_request_str[] = {
[VHOST_USER_NONE] = "VHOST_USER_NONE",
[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
[VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES",
[VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER",
[VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER",
[VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE",
[VHOST_USER_SET_LOG_BASE] = "VHOST_USER_SET_LOG_BASE",
[VHOST_USER_SET_LOG_FD] = "VHOST_USER_SET_LOG_FD",
[VHOST_USER_SET_VRING_NUM] = "VHOST_USER_SET_VRING_NUM",
[VHOST_USER_SET_VRING_ADDR] = "VHOST_USER_SET_VRING_ADDR",
[VHOST_USER_SET_VRING_BASE] = "VHOST_USER_SET_VRING_BASE",
[VHOST_USER_GET_VRING_BASE] = "VHOST_USER_GET_VRING_BASE",
[VHOST_USER_SET_VRING_KICK] = "VHOST_USER_SET_VRING_KICK",
[VHOST_USER_SET_VRING_CALL] = "VHOST_USER_SET_VRING_CALL",
[VHOST_USER_SET_VRING_ERR] = "VHOST_USER_SET_VRING_ERR",
[VHOST_USER_GET_PROTOCOL_FEATURES] = "VHOST_USER_GET_PROTOCOL_FEATURES",
[VHOST_USER_SET_PROTOCOL_FEATURES] = "VHOST_USER_SET_PROTOCOL_FEATURES",
[VHOST_USER_GET_QUEUE_NUM] = "VHOST_USER_GET_QUEUE_NUM",
[VHOST_USER_SET_VRING_ENABLE] = "VHOST_USER_SET_VRING_ENABLE",
[VHOST_USER_SEND_RARP] = "VHOST_USER_SEND_RARP",
[VHOST_USER_MAX] = "VHOST_USER_MAX",
};
static void
print_buffer(uint8_t *buf, size_t len)
{
int i;
printf("Raw buffer:\n");
for (i = 0; i < len; i++) {
if (i % 16 == 0) {
printf("\n");
}
if (i % 4 == 0) {
printf(" ");
}
printf("%02x ", buf[i]);
}
printf("\n............................................................\n");
}
/* Translate guest physical address to our virtual address. */
static uint64_t
gpa_to_va(VubrDev *dev, uint64_t guest_addr)
{
int i;
/* Find matching memory region. */
for (i = 0; i < dev->nregions; i++) {
VubrDevRegion *r = &dev->regions[i];
if ((guest_addr >= r->gpa) && (guest_addr < (r->gpa + r->size))) {
return guest_addr - r->gpa + r->mmap_addr + r->mmap_offset;
}
}
assert(!"address not found in regions");
return 0;
}
/* Translate qemu virtual address to our virtual address. */
static uint64_t
qva_to_va(VubrDev *dev, uint64_t qemu_addr)
{
int i;
/* Find matching memory region. */
for (i = 0; i < dev->nregions; i++) {
VubrDevRegion *r = &dev->regions[i];
if ((qemu_addr >= r->qva) && (qemu_addr < (r->qva + r->size))) {
return qemu_addr - r->qva + r->mmap_addr + r->mmap_offset;
}
}
assert(!"address not found in regions");
return 0;
}
static void
vubr_message_read(int conn_fd, VhostUserMsg *vmsg)
{
char control[CMSG_SPACE(VHOST_MEMORY_MAX_NREGIONS * sizeof(int))] = { };
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),
};
size_t fd_size;
struct cmsghdr *cmsg;
int rc;
rc = recvmsg(conn_fd, &msg, 0);
if (rc == 0) {
vubr_die("recvmsg");
fprintf(stderr, "Peer disconnected.\n");
exit(1);
}
if (rc < 0) {
vubr_die("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) {
fd_size = cmsg->cmsg_len - CMSG_LEN(0);
vmsg->fd_num = fd_size / sizeof(int);
memcpy(vmsg->fds, CMSG_DATA(cmsg), fd_size);
break;
}
}
if (vmsg->size > sizeof(vmsg->payload)) {
fprintf(stderr,
"Error: too big message request: %d, size: vmsg->size: %u, "
"while sizeof(vmsg->payload) = %zu\n",
vmsg->request, vmsg->size, sizeof(vmsg->payload));
exit(1);
}
if (vmsg->size) {
rc = read(conn_fd, &vmsg->payload, vmsg->size);
if (rc == 0) {
vubr_die("recvmsg");
fprintf(stderr, "Peer disconnected.\n");
exit(1);
}
if (rc < 0) {
vubr_die("recvmsg");
}
assert(rc == vmsg->size);
}
}
static void
vubr_message_write(int conn_fd, VhostUserMsg *vmsg)
{
int rc;
do {
rc = write(conn_fd, vmsg, VHOST_USER_HDR_SIZE + vmsg->size);
} while (rc < 0 && errno == EINTR);
if (rc < 0) {
vubr_die("write");
}
}
static void
vubr_backend_udp_sendbuf(VubrDev *dev, uint8_t *buf, size_t len)
{
int slen = sizeof(struct sockaddr_in);
if (sendto(dev->backend_udp_sock, buf, len, 0,
(struct sockaddr *) &dev->backend_udp_dest, slen) == -1) {
vubr_die("sendto()");
}
}
static int
vubr_backend_udp_recvbuf(VubrDev *dev, uint8_t *buf, size_t buflen)
{
int slen = sizeof(struct sockaddr_in);
int rc;
rc = recvfrom(dev->backend_udp_sock, buf, buflen, 0,
(struct sockaddr *) &dev->backend_udp_dest,
(socklen_t *)&slen);
if (rc == -1) {
vubr_die("recvfrom()");
}
return rc;
}
static void
vubr_consume_raw_packet(VubrDev *dev, uint8_t *buf, uint32_t len)
{
int hdrlen = dev->hdrlen;
DPRINT(" hdrlen = %d\n", dev->hdrlen);
if (VHOST_USER_BRIDGE_DEBUG) {
print_buffer(buf, len);
}
vubr_backend_udp_sendbuf(dev, buf + hdrlen, len - hdrlen);
}
/* Kick the log_call_fd if required. */
static void
vubr_log_kick(VubrDev *dev)
{
if (dev->log_call_fd != -1) {
DPRINT("Kicking the QEMU's log...\n");
eventfd_write(dev->log_call_fd, 1);
}
}
/* Kick the guest if necessary. */
static void
vubr_virtqueue_kick(VubrVirtq *vq)
{
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
DPRINT("Kicking the guest...\n");
eventfd_write(vq->call_fd, 1);
}
}
static void
vubr_log_page(uint8_t *log_table, uint64_t page)
{
DPRINT("Logged dirty guest page: %"PRId64"\n", page);
atomic_or(&log_table[page / 8], 1 << (page % 8));
}
static void
vubr_log_write(VubrDev *dev, uint64_t address, uint64_t length)
{
uint64_t page;
if (!(dev->features & (1ULL << VHOST_F_LOG_ALL)) ||
!dev->log_table || !length) {
return;
}
assert(dev->log_size > ((address + length - 1) / VHOST_LOG_PAGE / 8));
page = address / VHOST_LOG_PAGE;
while (page * VHOST_LOG_PAGE < address + length) {
vubr_log_page(dev->log_table, page);
page += VHOST_LOG_PAGE;
}
vubr_log_kick(dev);
}
static void
vubr_post_buffer(VubrDev *dev, VubrVirtq *vq, uint8_t *buf, int32_t len)
{
struct vring_desc *desc = vq->desc;
struct vring_avail *avail = vq->avail;
struct vring_used *used = vq->used;
uint64_t log_guest_addr = vq->log_guest_addr;
int32_t remaining_len = len;
unsigned int size = vq->size;
uint16_t avail_index = atomic_mb_read(&avail->idx);
/* We check the available descriptors before posting the
* buffer, so here we assume that enough available
* descriptors. */
assert(vq->last_avail_index != avail_index);
uint16_t a_index = vq->last_avail_index % size;
uint16_t u_index = vq->last_used_index % size;
uint16_t d_index = avail->ring[a_index];
int i = d_index;
uint32_t written_len = 0;
do {
DPRINT("Post packet to guest on vq:\n");
DPRINT(" size = %d\n", vq->size);
DPRINT(" last_avail_index = %d\n", vq->last_avail_index);
DPRINT(" last_used_index = %d\n", vq->last_used_index);
DPRINT(" a_index = %d\n", a_index);
DPRINT(" u_index = %d\n", u_index);
DPRINT(" d_index = %d\n", d_index);
DPRINT(" desc[%d].addr = 0x%016"PRIx64"\n", i, desc[i].addr);
DPRINT(" desc[%d].len = %d\n", i, desc[i].len);
DPRINT(" desc[%d].flags = %d\n", i, desc[i].flags);
DPRINT(" avail->idx = %d\n", avail_index);
DPRINT(" used->idx = %d\n", used->idx);
if (!(desc[i].flags & VRING_DESC_F_WRITE)) {
/* FIXME: we should find writable descriptor. */
fprintf(stderr, "Error: descriptor is not writable. Exiting.\n");
exit(1);
}
void *chunk_start = (void *)(uintptr_t)gpa_to_va(dev, desc[i].addr);
uint32_t chunk_len = desc[i].len;
uint32_t chunk_write_len = MIN(remaining_len, chunk_len);
memcpy(chunk_start, buf + written_len, chunk_write_len);
vubr_log_write(dev, desc[i].addr, chunk_write_len);
remaining_len -= chunk_write_len;
written_len += chunk_write_len;
if ((remaining_len == 0) || !(desc[i].flags & VRING_DESC_F_NEXT)) {
break;
}
i = desc[i].next;
} while (1);
if (remaining_len > 0) {
fprintf(stderr,
"Too long packet for RX, remaining_len = %d, Dropping...\n",
remaining_len);
return;
}
/* Add descriptor to the used ring. */
used->ring[u_index].id = d_index;
used->ring[u_index].len = len;
vubr_log_write(dev,
log_guest_addr + offsetof(struct vring_used, ring[u_index]),
sizeof(used->ring[u_index]));
vq->last_avail_index++;
vq->last_used_index++;
atomic_mb_set(&used->idx, vq->last_used_index);
vubr_log_write(dev,
log_guest_addr + offsetof(struct vring_used, idx),
sizeof(used->idx));
/* Kick the guest if necessary. */
vubr_virtqueue_kick(vq);
}
static int
vubr_process_desc(VubrDev *dev, VubrVirtq *vq)
{
struct vring_desc *desc = vq->desc;
struct vring_avail *avail = vq->avail;
struct vring_used *used = vq->used;
uint64_t log_guest_addr = vq->log_guest_addr;
unsigned int size = vq->size;
uint16_t a_index = vq->last_avail_index % size;
uint16_t u_index = vq->last_used_index % size;
uint16_t d_index = avail->ring[a_index];
uint32_t i, len = 0;
size_t buf_size = 4096;
uint8_t buf[4096];
DPRINT("Chunks: ");
i = d_index;
do {
void *chunk_start = (void *)(uintptr_t)gpa_to_va(dev, desc[i].addr);
uint32_t chunk_len = desc[i].len;
assert(!(desc[i].flags & VRING_DESC_F_WRITE));
if (len + chunk_len < buf_size) {
memcpy(buf + len, chunk_start, chunk_len);
DPRINT("%d ", chunk_len);
} else {
fprintf(stderr, "Error: too long packet. Dropping...\n");
break;
}
len += chunk_len;
if (!(desc[i].flags & VRING_DESC_F_NEXT)) {
break;
}
i = desc[i].next;
} while (1);
DPRINT("\n");
if (!len) {
return -1;
}
/* Add descriptor to the used ring. */
used->ring[u_index].id = d_index;
used->ring[u_index].len = len;
vubr_log_write(dev,
log_guest_addr + offsetof(struct vring_used, ring[u_index]),
sizeof(used->ring[u_index]));
vubr_consume_raw_packet(dev, buf, len);
return 0;
}
static void
vubr_process_avail(VubrDev *dev, VubrVirtq *vq)
{
struct vring_avail *avail = vq->avail;
struct vring_used *used = vq->used;
uint64_t log_guest_addr = vq->log_guest_addr;
while (vq->last_avail_index != atomic_mb_read(&avail->idx)) {
vubr_process_desc(dev, vq);
vq->last_avail_index++;
vq->last_used_index++;
}
atomic_mb_set(&used->idx, vq->last_used_index);
vubr_log_write(dev,
log_guest_addr + offsetof(struct vring_used, idx),
sizeof(used->idx));
}
static void
vubr_backend_recv_cb(int sock, void *ctx)
{
VubrDev *dev = (VubrDev *) ctx;
VubrVirtq *rx_vq = &dev->vq[0];
uint8_t buf[4096];
struct virtio_net_hdr_v1 *hdr = (struct virtio_net_hdr_v1 *)buf;
int hdrlen = dev->hdrlen;
int buflen = sizeof(buf);
int len;
if (!dev->ready) {
return;
}
DPRINT("\n\n *** IN UDP RECEIVE CALLBACK ***\n\n");
DPRINT(" hdrlen = %d\n", hdrlen);
uint16_t avail_index = atomic_mb_read(&rx_vq->avail->idx);
/* If there is no available descriptors, just do nothing.
* The buffer will be handled by next arrived UDP packet,
* or next kick on receive virtq. */
if (rx_vq->last_avail_index == avail_index) {
DPRINT("Got UDP packet, but no available descriptors on RX virtq.\n");
return;
}
memset(buf, 0, hdrlen);
/* TODO: support mergeable buffers. */
if (hdrlen == 12)
hdr->num_buffers = 1;
len = vubr_backend_udp_recvbuf(dev, buf + hdrlen, buflen - hdrlen);
vubr_post_buffer(dev, rx_vq, buf, len + hdrlen);
}
static void
vubr_kick_cb(int sock, void *ctx)
{
VubrDev *dev = (VubrDev *) ctx;
eventfd_t kick_data;
ssize_t rc;
rc = eventfd_read(sock, &kick_data);
if (rc == -1) {
vubr_die("eventfd_read()");
} else {
DPRINT("Got kick_data: %016"PRIx64"\n", kick_data);
vubr_process_avail(dev, &dev->vq[1]);
}
}
static int
vubr_none_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
DPRINT("Function %s() not implemented yet.\n", __func__);
return 0;
}
static int
vubr_get_features_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
vmsg->payload.u64 =
((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
(1ULL << VHOST_F_LOG_ALL) |
(1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) |
(1ULL << VHOST_USER_F_PROTOCOL_FEATURES));
vmsg->size = sizeof(vmsg->payload.u64);
DPRINT("Sending back to guest u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
/* Reply */
return 1;
}
static int
vubr_set_features_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
dev->features = vmsg->payload.u64;
if ((dev->features & (1ULL << VIRTIO_F_VERSION_1)) ||
(dev->features & (1ULL << VIRTIO_NET_F_MRG_RXBUF))) {
dev->hdrlen = 12;
} else {
dev->hdrlen = 10;
}
return 0;
}
static int
vubr_set_owner_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
return 0;
}
static void
vubr_close_log(VubrDev *dev)
{
if (dev->log_table) {
if (munmap(dev->log_table, dev->log_size) != 0) {
vubr_die("munmap()");
}
dev->log_table = 0;
}
if (dev->log_call_fd != -1) {
close(dev->log_call_fd);
dev->log_call_fd = -1;
}
}
static int
vubr_reset_device_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
vubr_close_log(dev);
dev->ready = 0;
dev->features = 0;
return 0;
}
static int
vubr_set_mem_table_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
int i;
VhostUserMemory *memory = &vmsg->payload.memory;
dev->nregions = memory->nregions;
DPRINT("Nregions: %d\n", memory->nregions);
for (i = 0; i < dev->nregions; i++) {
void *mmap_addr;
VhostUserMemoryRegion *msg_region = &memory->regions[i];
VubrDevRegion *dev_region = &dev->regions[i];
DPRINT("Region %d\n", i);
DPRINT(" guest_phys_addr: 0x%016"PRIx64"\n",
msg_region->guest_phys_addr);
DPRINT(" memory_size: 0x%016"PRIx64"\n",
msg_region->memory_size);
DPRINT(" userspace_addr 0x%016"PRIx64"\n",
msg_region->userspace_addr);
DPRINT(" mmap_offset 0x%016"PRIx64"\n",
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, and we use huge
* pages. */
mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
PROT_READ | PROT_WRITE, MAP_SHARED,
vmsg->fds[i], 0);
if (mmap_addr == MAP_FAILED) {
vubr_die("mmap");
}
dev_region->mmap_addr = (uint64_t)(uintptr_t)mmap_addr;
DPRINT(" mmap_addr: 0x%016"PRIx64"\n", dev_region->mmap_addr);
close(vmsg->fds[i]);
}
return 0;
}
static int
vubr_set_log_base_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
int fd;
uint64_t log_mmap_size, log_mmap_offset;
void *rc;
assert(vmsg->fd_num == 1);
fd = vmsg->fds[0];
assert(vmsg->size == sizeof(vmsg->payload.log));
log_mmap_offset = vmsg->payload.log.mmap_offset;
log_mmap_size = vmsg->payload.log.mmap_size;
DPRINT("Log mmap_offset: %"PRId64"\n", log_mmap_offset);
DPRINT("Log mmap_size: %"PRId64"\n", log_mmap_size);
rc = mmap(0, log_mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd,
log_mmap_offset);
if (rc == MAP_FAILED) {
vubr_die("mmap");
}
dev->log_table = rc;
dev->log_size = log_mmap_size;
vmsg->size = sizeof(vmsg->payload.u64);
/* Reply */
return 1;
}
static int
vubr_set_log_fd_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
assert(vmsg->fd_num == 1);
dev->log_call_fd = vmsg->fds[0];
DPRINT("Got log_call_fd: %d\n", vmsg->fds[0]);
return 0;
}
static int
vubr_set_vring_num_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
unsigned int index = vmsg->payload.state.index;
unsigned int num = vmsg->payload.state.num;
DPRINT("State.index: %d\n", index);
DPRINT("State.num: %d\n", num);
dev->vq[index].size = num;
return 0;
}
static int
vubr_set_vring_addr_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
struct vhost_vring_addr *vra = &vmsg->payload.addr;
unsigned int index = vra->index;
VubrVirtq *vq = &dev->vq[index];
DPRINT("vhost_vring_addr:\n");
DPRINT(" index: %d\n", vra->index);
DPRINT(" flags: %d\n", vra->flags);
DPRINT(" desc_user_addr: 0x%016llx\n", vra->desc_user_addr);
DPRINT(" used_user_addr: 0x%016llx\n", vra->used_user_addr);
DPRINT(" avail_user_addr: 0x%016llx\n", vra->avail_user_addr);
DPRINT(" log_guest_addr: 0x%016llx\n", vra->log_guest_addr);
vq->desc = (struct vring_desc *)(uintptr_t)qva_to_va(dev, vra->desc_user_addr);
vq->used = (struct vring_used *)(uintptr_t)qva_to_va(dev, vra->used_user_addr);
vq->avail = (struct vring_avail *)(uintptr_t)qva_to_va(dev, vra->avail_user_addr);
vq->log_guest_addr = vra->log_guest_addr;
DPRINT("Setting virtq addresses:\n");
DPRINT(" vring_desc at %p\n", vq->desc);
DPRINT(" vring_used at %p\n", vq->used);
DPRINT(" vring_avail at %p\n", vq->avail);
vq->last_used_index = vq->used->idx;
return 0;
}
static int
vubr_set_vring_base_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
unsigned int index = vmsg->payload.state.index;
unsigned int num = vmsg->payload.state.num;
DPRINT("State.index: %d\n", index);
DPRINT("State.num: %d\n", num);
dev->vq[index].last_avail_index = num;
return 0;
}
static int
vubr_get_vring_base_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
unsigned int index = vmsg->payload.state.index;
DPRINT("State.index: %d\n", index);
vmsg->payload.state.num = dev->vq[index].last_avail_index;
vmsg->size = sizeof(vmsg->payload.state);
/* FIXME: this is a work-around for a bug in QEMU enabling
* too early vrings. When protocol features are enabled,
* we have to respect * VHOST_USER_SET_VRING_ENABLE request. */
dev->ready = 0;
if (dev->vq[index].call_fd != -1) {
close(dev->vq[index].call_fd);
dispatcher_remove(&dev->dispatcher, dev->vq[index].call_fd);
dev->vq[index].call_fd = -1;
}
if (dev->vq[index].kick_fd != -1) {
close(dev->vq[index].kick_fd);
dispatcher_remove(&dev->dispatcher, dev->vq[index].kick_fd);
dev->vq[index].kick_fd = -1;
}
/* Reply */
return 1;
}
static int
vubr_set_vring_kick_exec(VubrDev *dev, VhostUserMsg *vmsg)
{
uint64_t u64_arg = vmsg->payload.u64;
int index = u64_arg & VHOST_USER_VRING_IDX_MASK;
DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);