forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
vhost.c
1607 lines (1439 loc) · 40.5 KB
/
vhost.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
/* Copyright (C) 2009 Red Hat, Inc.
* Copyright (C) 2006 Rusty Russell IBM Corporation
*
* Author: Michael S. Tsirkin <[email protected]>
*
* Inspiration, some code, and most witty comments come from
* Documentation/virtual/lguest/lguest.c, by Rusty Russell
*
* This work is licensed under the terms of the GNU GPL, version 2.
*
* Generic code for virtio server in host kernel.
*/
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/cgroup.h>
#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include "vhost.h"
enum {
VHOST_MEMORY_MAX_NREGIONS = 64,
VHOST_MEMORY_F_LOG = 0x1,
};
static unsigned vhost_zcopy_mask __read_mostly;
#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
poll_table *pt)
{
struct vhost_poll *poll;
poll = container_of(pt, struct vhost_poll, table);
poll->wqh = wqh;
add_wait_queue(wqh, &poll->wait);
}
static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
void *key)
{
struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);
if (!((unsigned long)key & poll->mask))
return 0;
vhost_poll_queue(poll);
return 0;
}
static void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
{
INIT_LIST_HEAD(&work->node);
work->fn = fn;
init_waitqueue_head(&work->done);
work->flushing = 0;
work->queue_seq = work->done_seq = 0;
}
/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
unsigned long mask, struct vhost_dev *dev)
{
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
init_poll_funcptr(&poll->table, vhost_poll_func);
poll->mask = mask;
poll->dev = dev;
vhost_work_init(&poll->work, fn);
}
/* Start polling a file. We add ourselves to file's wait queue. The caller must
* keep a reference to a file until after vhost_poll_stop is called. */
void vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
unsigned long mask;
mask = file->f_op->poll(file, &poll->table);
if (mask)
vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
}
/* Stop polling a file. After this function returns, it becomes safe to drop the
* file reference. You must also flush afterwards. */
void vhost_poll_stop(struct vhost_poll *poll)
{
remove_wait_queue(poll->wqh, &poll->wait);
}
static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work,
unsigned seq)
{
int left;
spin_lock_irq(&dev->work_lock);
left = seq - work->done_seq;
spin_unlock_irq(&dev->work_lock);
return left <= 0;
}
static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
{
unsigned seq;
int flushing;
spin_lock_irq(&dev->work_lock);
seq = work->queue_seq;
work->flushing++;
spin_unlock_irq(&dev->work_lock);
wait_event(work->done, vhost_work_seq_done(dev, work, seq));
spin_lock_irq(&dev->work_lock);
flushing = --work->flushing;
spin_unlock_irq(&dev->work_lock);
BUG_ON(flushing < 0);
}
/* Flush any work that has been scheduled. When calling this, don't hold any
* locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
vhost_work_flush(poll->dev, &poll->work);
}
static inline void vhost_work_queue(struct vhost_dev *dev,
struct vhost_work *work)
{
unsigned long flags;
spin_lock_irqsave(&dev->work_lock, flags);
if (list_empty(&work->node)) {
list_add_tail(&work->node, &dev->work_list);
work->queue_seq++;
wake_up_process(dev->worker);
}
spin_unlock_irqrestore(&dev->work_lock, flags);
}
void vhost_poll_queue(struct vhost_poll *poll)
{
vhost_work_queue(poll->dev, &poll->work);
}
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
vq->num = 1;
vq->desc = NULL;
vq->avail = NULL;
vq->used = NULL;
vq->last_avail_idx = 0;
vq->avail_idx = 0;
vq->last_used_idx = 0;
vq->signalled_used = 0;
vq->signalled_used_valid = false;
vq->used_flags = 0;
vq->log_used = false;
vq->log_addr = -1ull;
vq->vhost_hlen = 0;
vq->sock_hlen = 0;
vq->private_data = NULL;
vq->log_base = NULL;
vq->error_ctx = NULL;
vq->error = NULL;
vq->kick = NULL;
vq->call_ctx = NULL;
vq->call = NULL;
vq->log_ctx = NULL;
vq->upend_idx = 0;
vq->done_idx = 0;
vq->ubufs = NULL;
}
static int vhost_worker(void *data)
{
struct vhost_dev *dev = data;
struct vhost_work *work = NULL;
unsigned uninitialized_var(seq);
use_mm(dev->mm);
for (;;) {
/* mb paired w/ kthread_stop */
set_current_state(TASK_INTERRUPTIBLE);
spin_lock_irq(&dev->work_lock);
if (work) {
work->done_seq = seq;
if (work->flushing)
wake_up_all(&work->done);
}
if (kthread_should_stop()) {
spin_unlock_irq(&dev->work_lock);
__set_current_state(TASK_RUNNING);
break;
}
if (!list_empty(&dev->work_list)) {
work = list_first_entry(&dev->work_list,
struct vhost_work, node);
list_del_init(&work->node);
seq = work->queue_seq;
} else
work = NULL;
spin_unlock_irq(&dev->work_lock);
if (work) {
__set_current_state(TASK_RUNNING);
work->fn(work);
} else
schedule();
}
unuse_mm(dev->mm);
return 0;
}
static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
{
kfree(vq->indirect);
vq->indirect = NULL;
kfree(vq->log);
vq->log = NULL;
kfree(vq->heads);
vq->heads = NULL;
kfree(vq->ubuf_info);
vq->ubuf_info = NULL;
}
void vhost_enable_zcopy(int vq)
{
vhost_zcopy_mask |= 0x1 << vq;
}
/* Helper to allocate iovec buffers for all vqs. */
static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
{
int i;
bool zcopy;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].indirect = kmalloc(sizeof *dev->vqs[i].indirect *
UIO_MAXIOV, GFP_KERNEL);
dev->vqs[i].log = kmalloc(sizeof *dev->vqs[i].log * UIO_MAXIOV,
GFP_KERNEL);
dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
UIO_MAXIOV, GFP_KERNEL);
zcopy = vhost_zcopy_mask & (0x1 << i);
if (zcopy)
dev->vqs[i].ubuf_info =
kmalloc(sizeof *dev->vqs[i].ubuf_info *
UIO_MAXIOV, GFP_KERNEL);
if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
!dev->vqs[i].heads ||
(zcopy && !dev->vqs[i].ubuf_info))
goto err_nomem;
}
return 0;
err_nomem:
for (; i >= 0; --i)
vhost_vq_free_iovecs(&dev->vqs[i]);
return -ENOMEM;
}
static void vhost_dev_free_iovecs(struct vhost_dev *dev)
{
int i;
for (i = 0; i < dev->nvqs; ++i)
vhost_vq_free_iovecs(&dev->vqs[i]);
}
long vhost_dev_init(struct vhost_dev *dev,
struct vhost_virtqueue *vqs, int nvqs)
{
int i;
dev->vqs = vqs;
dev->nvqs = nvqs;
mutex_init(&dev->mutex);
dev->log_ctx = NULL;
dev->log_file = NULL;
dev->memory = NULL;
dev->mm = NULL;
spin_lock_init(&dev->work_lock);
INIT_LIST_HEAD(&dev->work_list);
dev->worker = NULL;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].log = NULL;
dev->vqs[i].indirect = NULL;
dev->vqs[i].heads = NULL;
dev->vqs[i].ubuf_info = NULL;
dev->vqs[i].dev = dev;
mutex_init(&dev->vqs[i].mutex);
vhost_vq_reset(dev, dev->vqs + i);
if (dev->vqs[i].handle_kick)
vhost_poll_init(&dev->vqs[i].poll,
dev->vqs[i].handle_kick, POLLIN, dev);
}
return 0;
}
/* Caller should have device mutex */
long vhost_dev_check_owner(struct vhost_dev *dev)
{
/* Are you the owner? If not, I don't think you mean to do that */
return dev->mm == current->mm ? 0 : -EPERM;
}
struct vhost_attach_cgroups_struct {
struct vhost_work work;
struct task_struct *owner;
int ret;
};
static void vhost_attach_cgroups_work(struct vhost_work *work)
{
struct vhost_attach_cgroups_struct *s;
s = container_of(work, struct vhost_attach_cgroups_struct, work);
s->ret = cgroup_attach_task_all(s->owner, current);
}
static int vhost_attach_cgroups(struct vhost_dev *dev)
{
struct vhost_attach_cgroups_struct attach;
attach.owner = current;
vhost_work_init(&attach.work, vhost_attach_cgroups_work);
vhost_work_queue(dev, &attach.work);
vhost_work_flush(dev, &attach.work);
return attach.ret;
}
/* Caller should have device mutex */
static long vhost_dev_set_owner(struct vhost_dev *dev)
{
struct task_struct *worker;
int err;
/* Is there an owner already? */
if (dev->mm) {
err = -EBUSY;
goto err_mm;
}
/* No owner, become one */
dev->mm = get_task_mm(current);
worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
if (IS_ERR(worker)) {
err = PTR_ERR(worker);
goto err_worker;
}
dev->worker = worker;
wake_up_process(worker); /* avoid contributing to loadavg */
err = vhost_attach_cgroups(dev);
if (err)
goto err_cgroup;
err = vhost_dev_alloc_iovecs(dev);
if (err)
goto err_cgroup;
return 0;
err_cgroup:
kthread_stop(worker);
dev->worker = NULL;
err_worker:
if (dev->mm)
mmput(dev->mm);
dev->mm = NULL;
err_mm:
return err;
}
/* Caller should have device mutex */
long vhost_dev_reset_owner(struct vhost_dev *dev)
{
struct vhost_memory *memory;
/* Restore memory to default empty mapping. */
memory = kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
if (!memory)
return -ENOMEM;
vhost_dev_cleanup(dev);
memory->nregions = 0;
RCU_INIT_POINTER(dev->memory, memory);
return 0;
}
/* In case of DMA done not in order in lower device driver for some reason.
* upend_idx is used to track end of used idx, done_idx is used to track head
* of used idx. Once lower device DMA done contiguously, we will signal KVM
* guest used idx.
*/
int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq)
{
int i;
int j = 0;
for (i = vq->done_idx; i != vq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
if ((vq->heads[i].len == VHOST_DMA_DONE_LEN)) {
vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
vhost_add_used_and_signal(vq->dev, vq,
vq->heads[i].id, 0);
++j;
} else
break;
}
if (j)
vq->done_idx = i;
return j;
}
/* Caller should have device mutex */
void vhost_dev_cleanup(struct vhost_dev *dev)
{
int i;
for (i = 0; i < dev->nvqs; ++i) {
if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
vhost_poll_stop(&dev->vqs[i].poll);
vhost_poll_flush(&dev->vqs[i].poll);
}
/* Wait for all lower device DMAs done. */
if (dev->vqs[i].ubufs)
vhost_ubuf_put_and_wait(dev->vqs[i].ubufs);
/* Signal guest as appropriate. */
vhost_zerocopy_signal_used(&dev->vqs[i]);
if (dev->vqs[i].error_ctx)
eventfd_ctx_put(dev->vqs[i].error_ctx);
if (dev->vqs[i].error)
fput(dev->vqs[i].error);
if (dev->vqs[i].kick)
fput(dev->vqs[i].kick);
if (dev->vqs[i].call_ctx)
eventfd_ctx_put(dev->vqs[i].call_ctx);
if (dev->vqs[i].call)
fput(dev->vqs[i].call);
vhost_vq_reset(dev, dev->vqs + i);
}
vhost_dev_free_iovecs(dev);
if (dev->log_ctx)
eventfd_ctx_put(dev->log_ctx);
dev->log_ctx = NULL;
if (dev->log_file)
fput(dev->log_file);
dev->log_file = NULL;
/* No one will access memory at this point */
kfree(rcu_dereference_protected(dev->memory,
lockdep_is_held(&dev->mutex)));
RCU_INIT_POINTER(dev->memory, NULL);
WARN_ON(!list_empty(&dev->work_list));
if (dev->worker) {
kthread_stop(dev->worker);
dev->worker = NULL;
}
if (dev->mm)
mmput(dev->mm);
dev->mm = NULL;
}
static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
{
u64 a = addr / VHOST_PAGE_SIZE / 8;
/* Make sure 64 bit math will not overflow. */
if (a > ULONG_MAX - (unsigned long)log_base ||
a + (unsigned long)log_base > ULONG_MAX)
return 0;
return access_ok(VERIFY_WRITE, log_base + a,
(sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
}
/* Caller should have vq mutex and device mutex. */
static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem,
int log_all)
{
int i;
if (!mem)
return 0;
for (i = 0; i < mem->nregions; ++i) {
struct vhost_memory_region *m = mem->regions + i;
unsigned long a = m->userspace_addr;
if (m->memory_size > ULONG_MAX)
return 0;
else if (!access_ok(VERIFY_WRITE, (void __user *)a,
m->memory_size))
return 0;
else if (log_all && !log_access_ok(log_base,
m->guest_phys_addr,
m->memory_size))
return 0;
}
return 1;
}
/* Can we switch to this memory table? */
/* Caller should have device mutex but not vq mutex */
static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
int log_all)
{
int i;
for (i = 0; i < d->nvqs; ++i) {
int ok;
mutex_lock(&d->vqs[i].mutex);
/* If ring is inactive, will check when it's enabled. */
if (d->vqs[i].private_data)
ok = vq_memory_access_ok(d->vqs[i].log_base, mem,
log_all);
else
ok = 1;
mutex_unlock(&d->vqs[i].mutex);
if (!ok)
return 0;
}
return 1;
}
static int vq_access_ok(struct vhost_dev *d, unsigned int num,
struct vring_desc __user *desc,
struct vring_avail __user *avail,
struct vring_used __user *used)
{
size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
access_ok(VERIFY_READ, avail,
sizeof *avail + num * sizeof *avail->ring + s) &&
access_ok(VERIFY_WRITE, used,
sizeof *used + num * sizeof *used->ring + s);
}
/* Can we log writes? */
/* Caller should have device mutex but not vq mutex */
int vhost_log_access_ok(struct vhost_dev *dev)
{
struct vhost_memory *mp;
mp = rcu_dereference_protected(dev->memory,
lockdep_is_held(&dev->mutex));
return memory_access_ok(dev, mp, 1);
}
/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
void __user *log_base)
{
struct vhost_memory *mp;
size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
mp = rcu_dereference_protected(vq->dev->memory,
lockdep_is_held(&vq->mutex));
return vq_memory_access_ok(log_base, mp,
vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
(!vq->log_used || log_access_ok(log_base, vq->log_addr,
sizeof *vq->used +
vq->num * sizeof *vq->used->ring + s));
}
/* Can we start vq? */
/* Caller should have vq mutex and device mutex */
int vhost_vq_access_ok(struct vhost_virtqueue *vq)
{
return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
vq_log_access_ok(vq->dev, vq, vq->log_base);
}
static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
struct vhost_memory mem, *newmem, *oldmem;
unsigned long size = offsetof(struct vhost_memory, regions);
if (copy_from_user(&mem, m, size))
return -EFAULT;
if (mem.padding)
return -EOPNOTSUPP;
if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
return -E2BIG;
newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
if (!newmem)
return -ENOMEM;
memcpy(newmem, &mem, size);
if (copy_from_user(newmem->regions, m->regions,
mem.nregions * sizeof *m->regions)) {
kfree(newmem);
return -EFAULT;
}
if (!memory_access_ok(d, newmem,
vhost_has_feature(d, VHOST_F_LOG_ALL))) {
kfree(newmem);
return -EFAULT;
}
oldmem = rcu_dereference_protected(d->memory,
lockdep_is_held(&d->mutex));
rcu_assign_pointer(d->memory, newmem);
synchronize_rcu();
kfree(oldmem);
return 0;
}
static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
{
struct file *eventfp, *filep = NULL,
*pollstart = NULL, *pollstop = NULL;
struct eventfd_ctx *ctx = NULL;
u32 __user *idxp = argp;
struct vhost_virtqueue *vq;
struct vhost_vring_state s;
struct vhost_vring_file f;
struct vhost_vring_addr a;
u32 idx;
long r;
r = get_user(idx, idxp);
if (r < 0)
return r;
if (idx >= d->nvqs)
return -ENOBUFS;
vq = d->vqs + idx;
mutex_lock(&vq->mutex);
switch (ioctl) {
case VHOST_SET_VRING_NUM:
/* Resizing ring with an active backend?
* You don't want to do that. */
if (vq->private_data) {
r = -EBUSY;
break;
}
if (copy_from_user(&s, argp, sizeof s)) {
r = -EFAULT;
break;
}
if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
r = -EINVAL;
break;
}
vq->num = s.num;
break;
case VHOST_SET_VRING_BASE:
/* Moving base with an active backend?
* You don't want to do that. */
if (vq->private_data) {
r = -EBUSY;
break;
}
if (copy_from_user(&s, argp, sizeof s)) {
r = -EFAULT;
break;
}
if (s.num > 0xffff) {
r = -EINVAL;
break;
}
vq->last_avail_idx = s.num;
/* Forget the cached index value. */
vq->avail_idx = vq->last_avail_idx;
break;
case VHOST_GET_VRING_BASE:
s.index = idx;
s.num = vq->last_avail_idx;
if (copy_to_user(argp, &s, sizeof s))
r = -EFAULT;
break;
case VHOST_SET_VRING_ADDR:
if (copy_from_user(&a, argp, sizeof a)) {
r = -EFAULT;
break;
}
if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
r = -EOPNOTSUPP;
break;
}
/* For 32bit, verify that the top 32bits of the user
data are set to zero. */
if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
(u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
(u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
r = -EFAULT;
break;
}
if ((a.avail_user_addr & (sizeof *vq->avail->ring - 1)) ||
(a.used_user_addr & (sizeof *vq->used->ring - 1)) ||
(a.log_guest_addr & (sizeof *vq->used->ring - 1))) {
r = -EINVAL;
break;
}
/* We only verify access here if backend is configured.
* If it is not, we don't as size might not have been setup.
* We will verify when backend is configured. */
if (vq->private_data) {
if (!vq_access_ok(d, vq->num,
(void __user *)(unsigned long)a.desc_user_addr,
(void __user *)(unsigned long)a.avail_user_addr,
(void __user *)(unsigned long)a.used_user_addr)) {
r = -EINVAL;
break;
}
/* Also validate log access for used ring if enabled. */
if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
!log_access_ok(vq->log_base, a.log_guest_addr,
sizeof *vq->used +
vq->num * sizeof *vq->used->ring)) {
r = -EINVAL;
break;
}
}
vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
vq->log_addr = a.log_guest_addr;
vq->used = (void __user *)(unsigned long)a.used_user_addr;
break;
case VHOST_SET_VRING_KICK:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->kick) {
pollstop = filep = vq->kick;
pollstart = vq->kick = eventfp;
} else
filep = eventfp;
break;
case VHOST_SET_VRING_CALL:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->call) {
filep = vq->call;
ctx = vq->call_ctx;
vq->call = eventfp;
vq->call_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
break;
case VHOST_SET_VRING_ERR:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->error) {
filep = vq->error;
vq->error = eventfp;
ctx = vq->error_ctx;
vq->error_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
break;
default:
r = -ENOIOCTLCMD;
}
if (pollstop && vq->handle_kick)
vhost_poll_stop(&vq->poll);
if (ctx)
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
if (pollstart && vq->handle_kick)
vhost_poll_start(&vq->poll, vq->kick);
mutex_unlock(&vq->mutex);
if (pollstop && vq->handle_kick)
vhost_poll_flush(&vq->poll);
return r;
}
/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct file *eventfp, *filep = NULL;
struct eventfd_ctx *ctx = NULL;
u64 p;
long r;
int i, fd;
/* If you are not the owner, you can become one */
if (ioctl == VHOST_SET_OWNER) {
r = vhost_dev_set_owner(d);
goto done;
}
/* You must be the owner to do anything else */
r = vhost_dev_check_owner(d);
if (r)
goto done;
switch (ioctl) {
case VHOST_SET_MEM_TABLE:
r = vhost_set_memory(d, argp);
break;
case VHOST_SET_LOG_BASE:
if (copy_from_user(&p, argp, sizeof p)) {
r = -EFAULT;
break;
}
if ((u64)(unsigned long)p != p) {
r = -EFAULT;
break;
}
for (i = 0; i < d->nvqs; ++i) {
struct vhost_virtqueue *vq;
void __user *base = (void __user *)(unsigned long)p;
vq = d->vqs + i;
mutex_lock(&vq->mutex);
/* If ring is inactive, will check when it's enabled. */
if (vq->private_data && !vq_log_access_ok(d, vq, base))
r = -EFAULT;
else
vq->log_base = base;
mutex_unlock(&vq->mutex);
}
break;
case VHOST_SET_LOG_FD:
r = get_user(fd, (int __user *)argp);
if (r < 0)
break;
eventfp = fd == -1 ? NULL : eventfd_fget(fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != d->log_file) {
filep = d->log_file;
ctx = d->log_ctx;
d->log_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
for (i = 0; i < d->nvqs; ++i) {
mutex_lock(&d->vqs[i].mutex);
d->vqs[i].log_ctx = d->log_ctx;
mutex_unlock(&d->vqs[i].mutex);
}
if (ctx)
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
break;
default:
r = vhost_set_vring(d, ioctl, argp);
break;
}
done:
return r;
}
static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
__u64 addr, __u32 len)
{
struct vhost_memory_region *reg;
int i;
/* linear search is not brilliant, but we really have on the order of 6
* regions in practice */
for (i = 0; i < mem->nregions; ++i) {
reg = mem->regions + i;
if (reg->guest_phys_addr <= addr &&
reg->guest_phys_addr + reg->memory_size - 1 >= addr)
return reg;
}
return NULL;
}
/* TODO: This is really inefficient. We need something like get_user()
* (instruction directly accesses the data, with an exception table entry
* returning -EFAULT). See Documentation/x86/exception-tables.txt.
*/
static int set_bit_to_user(int nr, void __user *addr)
{
unsigned long log = (unsigned long)addr;
struct page *page;
void *base;
int bit = nr + (log % PAGE_SIZE) * 8;
int r;
r = get_user_pages_fast(log, 1, 1, &page);
if (r < 0)
return r;
BUG_ON(r != 1);
base = kmap_atomic(page, KM_USER0);
set_bit(bit, base);
kunmap_atomic(base, KM_USER0);
set_page_dirty_lock(page);
put_page(page);
return 0;
}
static int log_write(void __user *log_base,
u64 write_address, u64 write_length)
{
u64 write_page = write_address / VHOST_PAGE_SIZE;
int r;
if (!write_length)
return 0;
write_length += write_address % VHOST_PAGE_SIZE;
for (;;) {
u64 base = (u64)(unsigned long)log_base;
u64 log = base + write_page / 8;
int bit = write_page % 8;
if ((u64)(unsigned long)log != log)
return -EFAULT;
r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
if (r < 0)
return r;
if (write_length <= VHOST_PAGE_SIZE)
break;
write_length -= VHOST_PAGE_SIZE;
write_page += 1;
}
return r;
}
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len)
{
int i, r;
/* Make sure data written is seen before log. */
smp_wmb();
for (i = 0; i < log_num; ++i) {
u64 l = min(log[i].len, len);
r = log_write(vq->log_base, log[i].addr, l);
if (r < 0)
return r;
len -= l;
if (!len) {
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
return 0;
}
}
/* Length written exceeds what we have stored. This is a bug. */
BUG();
return 0;
}
static int vhost_update_used_flags(struct vhost_virtqueue *vq)
{
void __user *used;