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
|
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2010-2016 Intel Corporation
*/
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <stddef.h>
#include <stdint.h>
#include <stdlib.h>
#ifdef RTE_LIBRTE_VHOST_NUMA
#include <numaif.h>
#endif
#include <rte_errno.h>
#include <rte_ethdev.h>
#include <rte_log.h>
#include <rte_string_fns.h>
#include <rte_memory.h>
#include <rte_malloc.h>
#include <rte_vhost.h>
#include <rte_rwlock.h>
#include "iotlb.h"
#include "vhost.h"
#include "vhost_user.h"
struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];
/* Called with iotlb_lock read-locked */
uint64_t
__vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint64_t iova, uint64_t *size, uint8_t perm)
{
uint64_t vva, tmp_size;
if (unlikely(!*size))
return 0;
tmp_size = *size;
vva = vhost_user_iotlb_cache_find(vq, iova, &tmp_size, perm);
if (tmp_size == *size)
return vva;
iova += tmp_size;
if (!vhost_user_iotlb_pending_miss(vq, iova, perm)) {
/*
* iotlb_lock is read-locked for a full burst,
* but it only protects the iotlb cache.
* In case of IOTLB miss, we might block on the socket,
* which could cause a deadlock with QEMU if an IOTLB update
* is being handled. We can safely unlock here to avoid it.
*/
vhost_user_iotlb_rd_unlock(vq);
vhost_user_iotlb_pending_insert(vq, iova, perm);
if (vhost_user_iotlb_miss(dev, iova, perm)) {
RTE_LOG(ERR, VHOST_CONFIG,
"IOTLB miss req failed for IOVA 0x%" PRIx64 "\n",
iova);
vhost_user_iotlb_pending_remove(vq, iova, 1, perm);
}
vhost_user_iotlb_rd_lock(vq);
}
return 0;
}
struct virtio_net *
get_device(int vid)
{
struct virtio_net *dev = vhost_devices[vid];
if (unlikely(!dev)) {
RTE_LOG(ERR, VHOST_CONFIG,
"(%d) device not found.\n", vid);
}
return dev;
}
void
cleanup_vq(struct vhost_virtqueue *vq, int destroy)
{
if ((vq->callfd >= 0) && (destroy != 0))
close(vq->callfd);
if (vq->kickfd >= 0)
close(vq->kickfd);
}
/*
* Unmap any memory, close any file descriptors and
* free any memory owned by a device.
*/
void
cleanup_device(struct virtio_net *dev, int destroy)
{
uint32_t i;
vhost_backend_cleanup(dev);
for (i = 0; i < dev->nr_vring; i++)
cleanup_vq(dev->virtqueue[i], destroy);
}
void
free_vq(struct vhost_virtqueue *vq)
{
rte_free(vq->shadow_used_ring);
rte_free(vq->batch_copy_elems);
rte_mempool_free(vq->iotlb_pool);
rte_free(vq);
}
/*
* Release virtqueues and device memory.
*/
static void
free_device(struct virtio_net *dev)
{
uint32_t i;
for (i = 0; i < dev->nr_vring; i++)
free_vq(dev->virtqueue[i]);
rte_free(dev);
}
int
vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
uint64_t req_size, size;
if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
goto out;
req_size = sizeof(struct vring_desc) * vq->size;
size = req_size;
vq->desc = (struct vring_desc *)(uintptr_t)vhost_iova_to_vva(dev, vq,
vq->ring_addrs.desc_user_addr,
&size, VHOST_ACCESS_RW);
if (!vq->desc || size != req_size)
return -1;
req_size = sizeof(struct vring_avail);
req_size += sizeof(uint16_t) * vq->size;
if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
req_size += sizeof(uint16_t);
size = req_size;
vq->avail = (struct vring_avail *)(uintptr_t)vhost_iova_to_vva(dev, vq,
vq->ring_addrs.avail_user_addr,
&size, VHOST_ACCESS_RW);
if (!vq->avail || size != req_size)
return -1;
req_size = sizeof(struct vring_used);
req_size += sizeof(struct vring_used_elem) * vq->size;
if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
req_size += sizeof(uint16_t);
size = req_size;
vq->used = (struct vring_used *)(uintptr_t)vhost_iova_to_vva(dev, vq,
vq->ring_addrs.used_user_addr,
&size, VHOST_ACCESS_RW);
if (!vq->used || size != req_size)
return -1;
out:
vq->access_ok = 1;
return 0;
}
void
vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_wr_lock(vq);
vq->access_ok = 0;
vq->desc = NULL;
vq->avail = NULL;
vq->used = NULL;
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_wr_unlock(vq);
}
static void
init_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
{
struct vhost_virtqueue *vq;
if (vring_idx >= VHOST_MAX_VRING) {
RTE_LOG(ERR, VHOST_CONFIG,
"Failed not init vring, out of bound (%d)\n",
vring_idx);
return;
}
vq = dev->virtqueue[vring_idx];
memset(vq, 0, sizeof(struct vhost_virtqueue));
vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
vq->callfd = VIRTIO_UNINITIALIZED_EVENTFD;
vhost_user_iotlb_init(dev, vring_idx);
/* Backends are set to -1 indicating an inactive device. */
vq->backend = -1;
TAILQ_INIT(&vq->zmbuf_list);
}
static void
reset_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
{
struct vhost_virtqueue *vq;
int callfd;
if (vring_idx >= VHOST_MAX_VRING) {
RTE_LOG(ERR, VHOST_CONFIG,
"Failed not init vring, out of bound (%d)\n",
vring_idx);
return;
}
vq = dev->virtqueue[vring_idx];
callfd = vq->callfd;
init_vring_queue(dev, vring_idx);
vq->callfd = callfd;
}
int
alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
{
struct vhost_virtqueue *vq;
vq = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
if (vq == NULL) {
RTE_LOG(ERR, VHOST_CONFIG,
"Failed to allocate memory for vring:%u.\n", vring_idx);
return -1;
}
dev->virtqueue[vring_idx] = vq;
init_vring_queue(dev, vring_idx);
rte_spinlock_init(&vq->access_lock);
dev->nr_vring += 1;
return 0;
}
/*
* Reset some variables in device structure, while keeping few
* others untouched, such as vid, ifname, nr_vring: they
* should be same unless the device is removed.
*/
void
reset_device(struct virtio_net *dev)
{
uint32_t i;
dev->features = 0;
dev->protocol_features = 0;
dev->flags &= VIRTIO_DEV_BUILTIN_VIRTIO_NET;
for (i = 0; i < dev->nr_vring; i++)
reset_vring_queue(dev, i);
}
/*
* Invoked when there is a new vhost-user connection established (when
* there is a new virtio device being attached).
*/
int
vhost_new_device(void)
{
struct virtio_net *dev;
int i;
dev = rte_zmalloc(NULL, sizeof(struct virtio_net), 0);
if (dev == NULL) {
RTE_LOG(ERR, VHOST_CONFIG,
"Failed to allocate memory for new dev.\n");
return -1;
}
for (i = 0; i < MAX_VHOST_DEVICE; i++) {
if (vhost_devices[i] == NULL)
break;
}
if (i == MAX_VHOST_DEVICE) {
RTE_LOG(ERR, VHOST_CONFIG,
"Failed to find a free slot for new device.\n");
rte_free(dev);
return -1;
}
vhost_devices[i] = dev;
dev->vid = i;
dev->flags = VIRTIO_DEV_BUILTIN_VIRTIO_NET;
dev->slave_req_fd = -1;
return i;
}
/*
* Invoked when there is the vhost-user connection is broken (when
* the virtio device is being detached).
*/
void
vhost_destroy_device(int vid)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return;
if (dev->flags & VIRTIO_DEV_RUNNING) {
dev->flags &= ~VIRTIO_DEV_RUNNING;
dev->notify_ops->destroy_device(vid);
}
cleanup_device(dev, 1);
free_device(dev);
vhost_devices[vid] = NULL;
}
void
vhost_set_ifname(int vid, const char *if_name, unsigned int if_len)
{
struct virtio_net *dev;
unsigned int len;
dev = get_device(vid);
if (dev == NULL)
return;
len = if_len > sizeof(dev->ifname) ?
sizeof(dev->ifname) : if_len;
strncpy(dev->ifname, if_name, len);
dev->ifname[sizeof(dev->ifname) - 1] = '\0';
}
void
vhost_enable_dequeue_zero_copy(int vid)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return;
dev->dequeue_zero_copy = 1;
}
void
vhost_set_builtin_virtio_net(int vid, bool enable)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return;
if (enable)
dev->flags |= VIRTIO_DEV_BUILTIN_VIRTIO_NET;
else
dev->flags &= ~VIRTIO_DEV_BUILTIN_VIRTIO_NET;
}
int
rte_vhost_get_mtu(int vid, uint16_t *mtu)
{
struct virtio_net *dev = get_device(vid);
if (!dev)
return -ENODEV;
if (!(dev->flags & VIRTIO_DEV_READY))
return -EAGAIN;
if (!(dev->features & (1ULL << VIRTIO_NET_F_MTU)))
return -ENOTSUP;
*mtu = dev->mtu;
return 0;
}
int
rte_vhost_get_numa_node(int vid)
{
#ifdef RTE_LIBRTE_VHOST_NUMA
struct virtio_net *dev = get_device(vid);
int numa_node;
int ret;
if (dev == NULL)
return -1;
ret = get_mempolicy(&numa_node, NULL, 0, dev,
MPOL_F_NODE | MPOL_F_ADDR);
if (ret < 0) {
RTE_LOG(ERR, VHOST_CONFIG,
"(%d) failed to query numa node: %s\n",
vid, rte_strerror(errno));
return -1;
}
return numa_node;
#else
RTE_SET_USED(vid);
return -1;
#endif
}
uint32_t
rte_vhost_get_queue_num(int vid)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return 0;
return dev->nr_vring / 2;
}
uint16_t
rte_vhost_get_vring_num(int vid)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return 0;
return dev->nr_vring;
}
int
rte_vhost_get_ifname(int vid, char *buf, size_t len)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return -1;
len = RTE_MIN(len, sizeof(dev->ifname));
strncpy(buf, dev->ifname, len);
buf[len - 1] = '\0';
return 0;
}
int
rte_vhost_get_negotiated_features(int vid, uint64_t *features)
{
struct virtio_net *dev;
dev = get_device(vid);
if (!dev)
return -1;
*features = dev->features;
return 0;
}
int
rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem)
{
struct virtio_net *dev;
struct rte_vhost_memory *m;
size_t size;
dev = get_device(vid);
if (!dev)
return -1;
size = dev->mem->nregions * sizeof(struct rte_vhost_mem_region);
m = malloc(sizeof(struct rte_vhost_memory) + size);
if (!m)
return -1;
m->nregions = dev->mem->nregions;
memcpy(m->regions, dev->mem->regions, size);
*mem = m;
return 0;
}
int
rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
struct rte_vhost_vring *vring)
{
struct virtio_net *dev;
struct vhost_virtqueue *vq;
dev = get_device(vid);
if (!dev)
return -1;
if (vring_idx >= VHOST_MAX_VRING)
return -1;
vq = dev->virtqueue[vring_idx];
if (!vq)
return -1;
vring->desc = vq->desc;
vring->avail = vq->avail;
vring->used = vq->used;
vring->log_guest_addr = vq->log_guest_addr;
vring->callfd = vq->callfd;
vring->kickfd = vq->kickfd;
vring->size = vq->size;
return 0;
}
int
rte_vhost_vring_call(int vid, uint16_t vring_idx)
{
struct virtio_net *dev;
struct vhost_virtqueue *vq;
dev = get_device(vid);
if (!dev)
return -1;
if (vring_idx >= VHOST_MAX_VRING)
return -1;
vq = dev->virtqueue[vring_idx];
if (!vq)
return -1;
vhost_vring_call(dev, vq);
return 0;
}
uint16_t
rte_vhost_avail_entries(int vid, uint16_t queue_id)
{
struct virtio_net *dev;
struct vhost_virtqueue *vq;
dev = get_device(vid);
if (!dev)
return 0;
vq = dev->virtqueue[queue_id];
if (!vq->enabled)
return 0;
return *(volatile uint16_t *)&vq->avail->idx - vq->last_used_idx;
}
int
rte_vhost_enable_guest_notification(int vid, uint16_t queue_id, int enable)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return -1;
if (enable) {
RTE_LOG(ERR, VHOST_CONFIG,
"guest notification isn't supported.\n");
return -1;
}
dev->virtqueue[queue_id]->used->flags = VRING_USED_F_NO_NOTIFY;
return 0;
}
void
rte_vhost_log_write(int vid, uint64_t addr, uint64_t len)
{
struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return;
vhost_log_write(dev, addr, len);
}
void
rte_vhost_log_used_vring(int vid, uint16_t vring_idx,
uint64_t offset, uint64_t len)
{
struct virtio_net *dev;
struct vhost_virtqueue *vq;
dev = get_device(vid);
if (dev == NULL)
return;
if (vring_idx >= VHOST_MAX_VRING)
return;
vq = dev->virtqueue[vring_idx];
if (!vq)
return;
vhost_log_used_vring(dev, vq, offset, len);
}
uint32_t
rte_vhost_rx_queue_count(int vid, uint16_t qid)
{
struct virtio_net *dev;
struct vhost_virtqueue *vq;
dev = get_device(vid);
if (dev == NULL)
return 0;
if (unlikely(qid >= dev->nr_vring || (qid & 1) == 0)) {
RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
dev->vid, __func__, qid);
return 0;
}
vq = dev->virtqueue[qid];
if (vq == NULL)
return 0;
if (unlikely(vq->enabled == 0 || vq->avail == NULL))
return 0;
return *((volatile uint16_t *)&vq->avail->idx) - vq->last_avail_idx;
}
|