summaryrefslogtreecommitdiff
path: root/drivers/vhost/vringh.c
blob: 08ad0d1f04766fe10b8a5829628983ec09f0b561 (plain)
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Helpers for the host side of a virtio ring.
 *
 * Since these may be in userspace, we use (inline) accessors.
 */
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/vringh.h>
#include <linux/virtio_ring.h>
#include <linux/kernel.h>
#include <linux/ratelimit.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <uapi/linux/virtio_config.h>

static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
{
	static DEFINE_RATELIMIT_STATE(vringh_rs,
				      DEFAULT_RATELIMIT_INTERVAL,
				      DEFAULT_RATELIMIT_BURST);
	if (__ratelimit(&vringh_rs)) {
		va_list ap;
		va_start(ap, fmt);
		printk(KERN_NOTICE "vringh:");
		vprintk(fmt, ap);
		va_end(ap);
	}
}

/* Returns vring->num if empty, -ve on error. */
static inline int __vringh_get_head(const struct vringh *vrh,
				    int (*getu16)(const struct vringh *vrh,
						  u16 *val, const __virtio16 *p),
				    u16 *last_avail_idx)
{
	u16 avail_idx, i, head;
	int err;

	err = getu16(vrh, &avail_idx, &vrh->vring.avail->idx);
	if (err) {
		vringh_bad("Failed to access avail idx at %p",
			   &vrh->vring.avail->idx);
		return err;
	}

	if (*last_avail_idx == avail_idx)
		return vrh->vring.num;

	/* Only get avail ring entries after they have been exposed by guest. */
	virtio_rmb(vrh->weak_barriers);

	i = *last_avail_idx & (vrh->vring.num - 1);

	err = getu16(vrh, &head, &vrh->vring.avail->ring[i]);
	if (err) {
		vringh_bad("Failed to read head: idx %d address %p",
			   *last_avail_idx, &vrh->vring.avail->ring[i]);
		return err;
	}

	if (head >= vrh->vring.num) {
		vringh_bad("Guest says index %u > %u is available",
			   head, vrh->vring.num);
		return -EINVAL;
	}

	(*last_avail_idx)++;
	return head;
}

/* Copy some bytes to/from the iovec.  Returns num copied. */
static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov,
				      void *ptr, size_t len,
				      int (*xfer)(void *addr, void *ptr,
						  size_t len))
{
	int err, done = 0;

	while (len && iov->i < iov->used) {
		size_t partlen;

		partlen = min(iov->iov[iov->i].iov_len, len);
		err = xfer(iov->iov[iov->i].iov_base, ptr, partlen);
		if (err)
			return err;
		done += partlen;
		len -= partlen;
		ptr += partlen;
		iov->consumed += partlen;
		iov->iov[iov->i].iov_len -= partlen;
		iov->iov[iov->i].iov_base += partlen;

		if (!iov->iov[iov->i].iov_len) {
			/* Fix up old iov element then increment. */
			iov->iov[iov->i].iov_len = iov->consumed;
			iov->iov[iov->i].iov_base -= iov->consumed;
			
			iov->consumed = 0;
			iov->i++;
		}
	}
	return done;
}

/* May reduce *len if range is shorter. */
static inline bool range_check(struct vringh *vrh, u64 addr, size_t *len,
			       struct vringh_range *range,
			       bool (*getrange)(struct vringh *,
						u64, struct vringh_range *))
{
	if (addr < range->start || addr > range->end_incl) {
		if (!getrange(vrh, addr, range))
			return false;
	}
	BUG_ON(addr < range->start || addr > range->end_incl);

	/* To end of memory? */
	if (unlikely(addr + *len == 0)) {
		if (range->end_incl == -1ULL)
			return true;
		goto truncate;
	}

	/* Otherwise, don't wrap. */
	if (addr + *len < addr) {
		vringh_bad("Wrapping descriptor %zu@0x%llx",
			   *len, (unsigned long long)addr);
		return false;
	}

	if (unlikely(addr + *len - 1 > range->end_incl))
		goto truncate;
	return true;

truncate:
	*len = range->end_incl + 1 - addr;
	return true;
}

static inline bool no_range_check(struct vringh *vrh, u64 addr, size_t *len,
				  struct vringh_range *range,
				  bool (*getrange)(struct vringh *,
						   u64, struct vringh_range *))
{
	return true;
}

/* No reason for this code to be inline. */
static int move_to_indirect(const struct vringh *vrh,
			    int *up_next, u16 *i, void *addr,
			    const struct vring_desc *desc,
			    struct vring_desc **descs, int *desc_max)
{
	u32 len;

	/* Indirect tables can't have indirect. */
	if (*up_next != -1) {
		vringh_bad("Multilevel indirect %u->%u", *up_next, *i);
		return -EINVAL;
	}

	len = vringh32_to_cpu(vrh, desc->len);
	if (unlikely(len % sizeof(struct vring_desc))) {
		vringh_bad("Strange indirect len %u", desc->len);
		return -EINVAL;
	}

	/* We will check this when we follow it! */
	if (desc->flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT))
		*up_next = vringh16_to_cpu(vrh, desc->next);
	else
		*up_next = -2;
	*descs = addr;
	*desc_max = len / sizeof(struct vring_desc);

	/* Now, start at the first indirect. */
	*i = 0;
	return 0;
}

static int resize_iovec(struct vringh_kiov *iov, gfp_t gfp)
{
	struct kvec *new;
	unsigned int flag, new_num = (iov->max_num & ~VRINGH_IOV_ALLOCATED) * 2;

	if (new_num < 8)
		new_num = 8;

	flag = (iov->max_num & VRINGH_IOV_ALLOCATED);
	if (flag)
		new = krealloc(iov->iov, new_num * sizeof(struct iovec), gfp);
	else {
		new = kmalloc_array(new_num, sizeof(struct iovec), gfp);
		if (new) {
			memcpy(new, iov->iov,
			       iov->max_num * sizeof(struct iovec));
			flag = VRINGH_IOV_ALLOCATED;
		}
	}
	if (!new)
		return -ENOMEM;
	iov->iov = new;
	iov->max_num = (new_num | flag);
	return 0;
}

static u16 __cold return_from_indirect(const struct vringh *vrh, int *up_next,
				       struct vring_desc **descs, int *desc_max)
{
	u16 i = *up_next;

	*up_next = -1;
	*descs = vrh->vring.desc;
	*desc_max = vrh->vring.num;
	return i;
}

static int slow_copy(struct vringh *vrh, void *dst, const void *src,
		     bool (*rcheck)(struct vringh *vrh, u64 addr, size_t *len,
				    struct vringh_range *range,
				    bool (*getrange)(struct vringh *vrh,
						     u64,
						     struct vringh_range *)),
		     bool (*getrange)(struct vringh *vrh,
				      u64 addr,
				      struct vringh_range *r),
		     struct vringh_range *range,
		     int (*copy)(void *dst, const void *src, size_t len))
{
	size_t part, len = sizeof(struct vring_desc);

	do {
		u64 addr;
		int err;

		part = len;
		addr = (u64)(unsigned long)src - range->offset;

		if (!rcheck(vrh, addr, &part, range, getrange))
			return -EINVAL;

		err = copy(dst, src, part);
		if (err)
			return err;

		dst += part;
		src += part;
		len -= part;
	} while (len);
	return 0;
}

static inline int
__vringh_iov(struct vringh *vrh, u16 i,
	     struct vringh_kiov *riov,
	     struct vringh_kiov *wiov,
	     bool (*rcheck)(struct vringh *vrh, u64 addr, size_t *len,
			    struct vringh_range *range,
			    bool (*getrange)(struct vringh *, u64,
					     struct vringh_range *)),
	     bool (*getrange)(struct vringh *, u64, struct vringh_range *),
	     gfp_t gfp,
	     int (*copy)(void *dst, const void *src, size_t len))
{
	int err, count = 0, up_next, desc_max;
	struct vring_desc desc, *descs;
	struct vringh_range range = { -1ULL, 0 }, slowrange;
	bool slow = false;

	/* We start traversing vring's descriptor table. */
	descs = vrh->vring.desc;
	desc_max = vrh->vring.num;
	up_next = -1;

	if (riov)
		riov->i = riov->used = 0;
	else if (wiov)
		wiov->i = wiov->used = 0;
	else
		/* You must want something! */
		BUG();

	for (;;) {
		void *addr;
		struct vringh_kiov *iov;
		size_t len;

		if (unlikely(slow))
			err = slow_copy(vrh, &desc, &descs[i], rcheck, getrange,
					&slowrange, copy);
		else
			err = copy(&desc, &descs[i], sizeof(desc));
		if (unlikely(err))
			goto fail;

		if (unlikely(desc.flags &
			     cpu_to_vringh16(vrh, VRING_DESC_F_INDIRECT))) {
			u64 a = vringh64_to_cpu(vrh, desc.addr);

			/* Make sure it's OK, and get offset. */
			len = vringh32_to_cpu(vrh, desc.len);
			if (!rcheck(vrh, a, &len, &range, getrange)) {
				err = -EINVAL;
				goto fail;
			}

			if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) {
				slow = true;
				/* We need to save this range to use offset */
				slowrange = range;
			}

			addr = (void *)(long)(a + range.offset);
			err = move_to_indirect(vrh, &up_next, &i, addr, &desc,
					       &descs, &desc_max);
			if (err)
				goto fail;
			continue;
		}

		if (count++ == vrh->vring.num) {
			vringh_bad("Descriptor loop in %p", descs);
			err = -ELOOP;
			goto fail;
		}

		if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_WRITE))
			iov = wiov;
		else {
			iov = riov;
			if (unlikely(wiov && wiov->i)) {
				vringh_bad("Readable desc %p after writable",
					   &descs[i]);
				err = -EINVAL;
				goto fail;
			}
		}

		if (!iov) {
			vringh_bad("Unexpected %s desc",
				   !wiov ? "writable" : "readable");
			err = -EPROTO;
			goto fail;
		}

	again:
		/* Make sure it's OK, and get offset. */
		len = vringh32_to_cpu(vrh, desc.len);
		if (!rcheck(vrh, vringh64_to_cpu(vrh, desc.addr), &len, &range,
			    getrange)) {
			err = -EINVAL;
			goto fail;
		}
		addr = (void *)(unsigned long)(vringh64_to_cpu(vrh, desc.addr) +
					       range.offset);

		if (unlikely(iov->used == (iov->max_num & ~VRINGH_IOV_ALLOCATED))) {
			err = resize_iovec(iov, gfp);
			if (err)
				goto fail;
		}

		iov->iov[iov->used].iov_base = addr;
		iov->iov[iov->used].iov_len = len;
		iov->used++;

		if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) {
			desc.len = cpu_to_vringh32(vrh,
				   vringh32_to_cpu(vrh, desc.len) - len);
			desc.addr = cpu_to_vringh64(vrh,
				    vringh64_to_cpu(vrh, desc.addr) + len);
			goto again;
		}

		if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT)) {
			i = vringh16_to_cpu(vrh, desc.next);
		} else {
			/* Just in case we need to finish traversing above. */
			if (unlikely(up_next > 0)) {
				i = return_from_indirect(vrh, &up_next,
							 &descs, &desc_max);
				slow = false;
			} else
				break;
		}

		if (i >= desc_max) {
			vringh_bad("Chained index %u > %u", i, desc_max);
			err = -EINVAL;
			goto fail;
		}
	}

	return 0;

fail:
	return err;
}

static inline int __vringh_complete(struct vringh *vrh,
				    const struct vring_used_elem *used,
				    unsigned int num_used,
				    int (*putu16)(const struct vringh *vrh,
						  __virtio16 *p, u16 val),
				    int (*putused)(struct vring_used_elem *dst,
						   const struct vring_used_elem
						   *src, unsigned num))
{
	struct vring_used *used_ring;
	int err;
	u16 used_idx, off;

	used_ring = vrh->vring.used;
	used_idx = vrh->last_used_idx + vrh->completed;

	off = used_idx % vrh->vring.num;

	/* Compiler knows num_used == 1 sometimes, hence extra check */
	if (num_used > 1 && unlikely(off + num_used >= vrh->vring.num)) {
		u16 part = vrh->vring.num - off;
		err = putused(&used_ring->ring[off], used, part);
		if (!err)
			err = putused(&used_ring->ring[0], used + part,
				      num_used - part);
	} else
		err = putused(&used_ring->ring[off], used, num_used);

	if (err) {
		vringh_bad("Failed to write %u used entries %u at %p",
			   num_used, off, &used_ring->ring[off]);
		return err;
	}

	/* Make sure buffer is written before we update index. */
	virtio_wmb(vrh->weak_barriers);

	err = putu16(vrh, &vrh->vring.used->idx, used_idx + num_used);
	if (err) {
		vringh_bad("Failed to update used index at %p",
			   &vrh->vring.used->idx);
		return err;
	}

	vrh->completed += num_used;
	return 0;
}


static inline int __vringh_need_notify(struct vringh *vrh,
				       int (*getu16)(const struct vringh *vrh,
						     u16 *val,
						     const __virtio16 *p))
{
	bool notify;
	u16 used_event;
	int err;

	/* Flush out used index update. This is paired with the
	 * barrier that the Guest executes when enabling
	 * interrupts. */
	virtio_mb(vrh->weak_barriers);

	/* Old-style, without event indices. */
	if (!vrh->event_indices) {
		u16 flags;
		err = getu16(vrh, &flags, &vrh->vring.avail->flags);
		if (err) {
			vringh_bad("Failed to get flags at %p",
				   &vrh->vring.avail->flags);
			return err;
		}
		return (!(flags & VRING_AVAIL_F_NO_INTERRUPT));
	}

	/* Modern: we know when other side wants to know. */
	err = getu16(vrh, &used_event, &vring_used_event(&vrh->vring));
	if (err) {
		vringh_bad("Failed to get used event idx at %p",
			   &vring_used_event(&vrh->vring));
		return err;
	}

	/* Just in case we added so many that we wrap. */
	if (unlikely(vrh->completed > 0xffff))
		notify = true;
	else
		notify = vring_need_event(used_event,
					  vrh->last_used_idx + vrh->completed,
					  vrh->last_used_idx);

	vrh->last_used_idx += vrh->completed;
	vrh->completed = 0;
	return notify;
}

static inline bool __vringh_notify_enable(struct vringh *vrh,
					  int (*getu16)(const struct vringh *vrh,
							u16 *val, const __virtio16 *p),
					  int (*putu16)(const struct vringh *vrh,
							__virtio16 *p, u16 val))
{
	u16 avail;

	if (!vrh->event_indices) {
		/* Old-school; update flags. */
		if (putu16(vrh, &vrh->vring.used->flags, 0) != 0) {
			vringh_bad("Clearing used flags %p",
				   &vrh->vring.used->flags);
			return true;
		}
	} else {
		if (putu16(vrh, &vring_avail_event(&vrh->vring),
			   vrh->last_avail_idx) != 0) {
			vringh_bad("Updating avail event index %p",
				   &vring_avail_event(&vrh->vring));
			return true;
		}
	}

	/* They could have slipped one in as we were doing that: make
	 * sure it's written, then check again. */
	virtio_mb(vrh->weak_barriers);

	if (getu16(vrh, &avail, &vrh->vring.avail->idx) != 0) {
		vringh_bad("Failed to check avail idx at %p",
			   &vrh->vring.avail->idx);
		return true;
	}

	/* This is unlikely, so we just leave notifications enabled
	 * (if we're using event_indices, we'll only get one
	 * notification anyway). */
	return avail == vrh->last_avail_idx;
}

static inline void __vringh_notify_disable(struct vringh *vrh,
					   int (*putu16)(const struct vringh *vrh,
							 __virtio16 *p, u16 val))
{
	if (!vrh->event_indices) {
		/* Old-school; update flags. */
		if (putu16(vrh, &vrh->vring.used->flags,
			   VRING_USED_F_NO_NOTIFY)) {
			vringh_bad("Setting used flags %p",
				   &vrh->vring.used->flags);
		}
	}
}

/* Userspace access helpers: in this case, addresses are really userspace. */
static inline int getu16_user(const struct vringh *vrh, u16 *val, const __virtio16 *p)
{
	__virtio16 v = 0;
	int rc = get_user(v, (__force __virtio16 __user *)p);
	*val = vringh16_to_cpu(vrh, v);
	return rc;
}

static inline int putu16_user(const struct vringh *vrh, __virtio16 *p, u16 val)
{
	__virtio16 v = cpu_to_vringh16(vrh, val);
	return put_user(v, (__force __virtio16 __user *)p);
}

static inline int copydesc_user(void *dst, const void *src, size_t len)
{
	return copy_from_user(dst, (__force void __user *)src, len) ?
		-EFAULT : 0;
}

static inline int putused_user(struct vring_used_elem *dst,
			       const struct vring_used_elem *src,
			       unsigned int num)
{
	return copy_to_user((__force void __user *)dst, src,
			    sizeof(*dst) * num) ? -EFAULT : 0;
}

static inline int xfer_from_user(void *src, void *dst, size_t len)
{
	return copy_from_user(dst, (__force void __user *)src, len) ?
		-EFAULT : 0;
}

static inline int xfer_to_user(void *dst, void *src, size_t len)
{
	return copy_to_user((__force void __user *)dst, src, len) ?
		-EFAULT : 0;
}

/**
 * vringh_init_user - initialize a vringh for a userspace vring.
 * @vrh: the vringh to initialize.
 * @features: the feature bits for this ring.
 * @num: the number of elements.
 * @weak_barriers: true if we only need memory barriers, not I/O.
 * @desc: the userpace descriptor pointer.
 * @avail: the userpace avail pointer.
 * @used: the userpace used pointer.
 *
 * Returns an error if num is invalid: you should check pointers
 * yourself!
 */
int vringh_init_user(struct vringh *vrh, u64 features,
		     unsigned int num, bool weak_barriers,
		     struct vring_desc __user *desc,
		     struct vring_avail __user *avail,
		     struct vring_used __user *used)
{
	/* Sane power of 2 please! */
	if (!num || num > 0xffff || (num & (num - 1))) {
		vringh_bad("Bad ring size %u", num);
		return -EINVAL;
	}

	vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1));
	vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
	vrh->weak_barriers = weak_barriers;
	vrh->completed = 0;
	vrh->last_avail_idx = 0;
	vrh->last_used_idx = 0;
	vrh->vring.num = num;
	/* vring expects kernel addresses, but only used via accessors. */
	vrh->vring.desc = (__force struct vring_desc *)desc;
	vrh->vring.avail = (__force struct vring_avail *)avail;
	vrh->vring.used = (__force struct vring_used *)used;
	return 0;
}
EXPORT_SYMBOL(vringh_init_user);

/**
 * vringh_getdesc_user - get next available descriptor from userspace ring.
 * @vrh: the userspace vring.
 * @riov: where to put the readable descriptors (or NULL)
 * @wiov: where to put the writable descriptors (or NULL)
 * @getrange: function to call to check ranges.
 * @head: head index we received, for passing to vringh_complete_user().
 *
 * Returns 0 if there was no descriptor, 1 if there was, or -errno.
 *
 * Note that on error return, you can tell the difference between an
 * invalid ring and a single invalid descriptor: in the former case,
 * *head will be vrh->vring.num.  You may be able to ignore an invalid
 * descriptor, but there's not much you can do with an invalid ring.
 *
 * Note that you may need to clean up riov and wiov, even on error!
 */
int vringh_getdesc_user(struct vringh *vrh,
			struct vringh_iov *riov,
			struct vringh_iov *wiov,
			bool (*getrange)(struct vringh *vrh,
					 u64 addr, struct vringh_range *r),
			u16 *head)
{
	int err;

	*head = vrh->vring.num;
	err = __vringh_get_head(vrh, getu16_user, &vrh->last_avail_idx);
	if (err < 0)
		return err;

	/* Empty... */
	if (err == vrh->vring.num)
		return 0;

	/* We need the layouts to be the identical for this to work */
	BUILD_BUG_ON(sizeof(struct vringh_kiov) != sizeof(struct vringh_iov));
	BUILD_BUG_ON(offsetof(struct vringh_kiov, iov) !=
		     offsetof(struct vringh_iov, iov));
	BUILD_BUG_ON(offsetof(struct vringh_kiov, i) !=
		     offsetof(struct vringh_iov, i));
	BUILD_BUG_ON(offsetof(struct vringh_kiov, used) !=
		     offsetof(struct vringh_iov, used));
	BUILD_BUG_ON(offsetof(struct vringh_kiov, max_num) !=
		     offsetof(struct vringh_iov, max_num));
	BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec));
	BUILD_BUG_ON(offsetof(struct iovec, iov_base) !=
		     offsetof(struct kvec, iov_base));
	BUILD_BUG_ON(offsetof(struct iovec, iov_len) !=
		     offsetof(struct kvec, iov_len));
	BUILD_BUG_ON(sizeof(((struct iovec *)NULL)->iov_base)
		     != sizeof(((struct kvec *)NULL)->iov_base));
	BUILD_BUG_ON(sizeof(((struct iovec *)NULL)->iov_len)
		     != sizeof(((struct kvec *)NULL)->iov_len));

	*head = err;
	err = __vringh_iov(vrh, *head, (struct vringh_kiov *)riov,
			   (struct vringh_kiov *)wiov,
			   range_check, getrange, GFP_KERNEL, copydesc_user);
	if (err)
		return err;

	return 1;
}
EXPORT_SYMBOL(vringh_getdesc_user);

/**
 * vringh_iov_pull_user - copy bytes from vring_iov.
 * @riov: the riov as passed to vringh_getdesc_user() (updated as we consume)
 * @dst: the place to copy.
 * @len: the maximum length to copy.
 *
 * Returns the bytes copied <= len or a negative errno.
 */
ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len)
{
	return vringh_iov_xfer((struct vringh_kiov *)riov,
			       dst, len, xfer_from_user);
}
EXPORT_SYMBOL(vringh_iov_pull_user);

/**
 * vringh_iov_push_user - copy bytes into vring_iov.
 * @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume)
 * @dst: the place to copy.
 * @len: the maximum length to copy.
 *
 * Returns the bytes copied <= len or a negative errno.
 */
ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
			     const void *src, size_t len)
{
	return vringh_iov_xfer((struct vringh_kiov *)wiov,
			       (void *)src, len, xfer_to_user);
}
EXPORT_SYMBOL(vringh_iov_push_user);

/**
 * vringh_abandon_user - we've decided not to handle the descriptor(s).
 * @vrh: the vring.
 * @num: the number of descriptors to put back (ie. num
 *	 vringh_get_user() to undo).
 *
 * The next vringh_get_user() will return the old descriptor(s) again.
 */
void vringh_abandon_user(struct vringh *vrh, unsigned int num)
{
	/* We only update vring_avail_event(vr) when we want to be notified,
	 * so we haven't changed that yet. */
	vrh->last_avail_idx -= num;
}
EXPORT_SYMBOL(vringh_abandon_user);

/**
 * vringh_complete_user - we've finished with descriptor, publish it.
 * @vrh: the vring.
 * @head: the head as filled in by vringh_getdesc_user.
 * @len: the length of data we have written.
 *
 * You should check vringh_need_notify_user() after one or more calls
 * to this function.
 */
int vringh_complete_user(struct vringh *vrh, u16 head, u32 len)
{
	struct vring_used_elem used;

	used.id = cpu_to_vringh32(vrh, head);
	used.len = cpu_to_vringh32(vrh, len);
	return __vringh_complete(vrh, &used, 1, putu16_user, putused_user);
}
EXPORT_SYMBOL(vringh_complete_user);

/**
 * vringh_complete_multi_user - we've finished with many descriptors.
 * @vrh: the vring.
 * @used: the head, length pairs.
 * @num_used: the number of used elements.
 *
 * You should check vringh_need_notify_user() after one or more calls
 * to this function.
 */
int vringh_complete_multi_user(struct vringh *vrh,
			       const struct vring_used_elem used[],
			       unsigned num_used)
{
	return __vringh_complete(vrh, used, num_used,
				 putu16_user, putused_user);
}
EXPORT_SYMBOL(vringh_complete_multi_user);

/**
 * vringh_notify_enable_user - we want to know if something changes.
 * @vrh: the vring.
 *
 * This always enables notifications, but returns false if there are
 * now more buffers available in the vring.
 */
bool vringh_notify_enable_user(struct vringh *vrh)
{
	return __vringh_notify_enable(vrh, getu16_user, putu16_user);
}
EXPORT_SYMBOL(vringh_notify_enable_user);

/**
 * vringh_notify_disable_user - don't tell us if something changes.
 * @vrh: the vring.
 *
 * This is our normal running state: we disable and then only enable when
 * we're going to sleep.
 */
void vringh_notify_disable_user(struct vringh *vrh)
{
	__vringh_notify_disable(vrh, putu16_user);
}
EXPORT_SYMBOL(vringh_notify_disable_user);

/**
 * vringh_need_notify_user - must we tell the other side about used buffers?
 * @vrh: the vring we've called vringh_complete_user() on.
 *
 * Returns -errno or 0 if we don't need to tell the other side, 1 if we do.
 */
int vringh_need_notify_user(struct vringh *vrh)
{
	return __vringh_need_notify(vrh, getu16_user);
}
EXPORT_SYMBOL(vringh_need_notify_user);

/* Kernelspace access helpers. */
static inline int getu16_kern(const struct vringh *vrh,
			      u16 *val, const __virtio16 *p)
{
	*val = vringh16_to_cpu(vrh, READ_ONCE(*p));
	return 0;
}

static inline int putu16_kern(const struct vringh *vrh, __virtio16 *p, u16 val)
{
	WRITE_ONCE(*p, cpu_to_vringh16(vrh, val));
	return 0;
}

static inline int copydesc_kern(void *dst, const void *src, size_t len)
{
	memcpy(dst, src, len);
	return 0;
}

static inline int putused_kern(struct vring_used_elem *dst,
			       const struct vring_used_elem *src,
			       unsigned int num)
{
	memcpy(dst, src, num * sizeof(*dst));
	return 0;
}

static inline int xfer_kern(void *src, void *dst, size_t len)
{
	memcpy(dst, src, len);
	return 0;
}

/**
 * vringh_init_kern - initialize a vringh for a kernelspace vring.
 * @vrh: the vringh to initialize.
 * @features: the feature bits for this ring.
 * @num: the number of elements.
 * @weak_barriers: true if we only need memory barriers, not I/O.
 * @desc: the userpace descriptor pointer.
 * @avail: the userpace avail pointer.
 * @used: the userpace used pointer.
 *
 * Returns an error if num is invalid.
 */
int vringh_init_kern(struct vringh *vrh, u64 features,
		     unsigned int num, bool weak_barriers,
		     struct vring_desc *desc,
		     struct vring_avail *avail,
		     struct vring_used *used)
{
	/* Sane power of 2 please! */
	if (!num || num > 0xffff || (num & (num - 1))) {
		vringh_bad("Bad ring size %u", num);
		return -EINVAL;
	}

	vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1));
	vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
	vrh->weak_barriers = weak_barriers;
	vrh->completed = 0;
	vrh->last_avail_idx = 0;
	vrh->last_used_idx = 0;
	vrh->vring.num = num;
	vrh->vring.desc = desc;
	vrh->vring.avail = avail;
	vrh->vring.used = used;
	return 0;
}
EXPORT_SYMBOL(vringh_init_kern);

/**
 * vringh_getdesc_kern - get next available descriptor from kernelspace ring.
 * @vrh: the kernelspace vring.
 * @riov: where to put the readable descriptors (or NULL)
 * @wiov: where to put the writable descriptors (or NULL)
 * @head: head index we received, for passing to vringh_complete_kern().
 * @gfp: flags for allocating larger riov/wiov.
 *
 * Returns 0 if there was no descriptor, 1 if there was, or -errno.
 *
 * Note that on error return, you can tell the difference between an
 * invalid ring and a single invalid descriptor: in the former case,
 * *head will be vrh->vring.num.  You may be able to ignore an invalid
 * descriptor, but there's not much you can do with an invalid ring.
 *
 * Note that you may need to clean up riov and wiov, even on error!
 */
int vringh_getdesc_kern(struct vringh *vrh,
			struct vringh_kiov *riov,
			struct vringh_kiov *wiov,
			u16 *head,
			gfp_t gfp)
{
	int err;

	err = __vringh_get_head(vrh, getu16_kern, &vrh->last_avail_idx);
	if (err < 0)
		return err;

	/* Empty... */
	if (err == vrh->vring.num)
		return 0;

	*head = err;
	err = __vringh_iov(vrh, *head, riov, wiov, no_range_check, NULL,
			   gfp, copydesc_kern);
	if (err)
		return err;

	return 1;
}
EXPORT_SYMBOL(vringh_getdesc_kern);

/**
 * vringh_iov_pull_kern - copy bytes from vring_iov.
 * @riov: the riov as passed to vringh_getdesc_kern() (updated as we consume)
 * @dst: the place to copy.
 * @len: the maximum length to copy.
 *
 * Returns the bytes copied <= len or a negative errno.
 */
ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len)
{
	return vringh_iov_xfer(riov, dst, len, xfer_kern);
}
EXPORT_SYMBOL(vringh_iov_pull_kern);

/**
 * vringh_iov_push_kern - copy bytes into vring_iov.
 * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume)
 * @dst: the place to copy.
 * @len: the maximum length to copy.
 *
 * Returns the bytes copied <= len or a negative errno.
 */
ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
			     const void *src, size_t len)
{
	return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern);
}
EXPORT_SYMBOL(vringh_iov_push_kern);

/**
 * vringh_abandon_kern - we've decided not to handle the descriptor(s).
 * @vrh: the vring.
 * @num: the number of descriptors to put back (ie. num
 *	 vringh_get_kern() to undo).
 *
 * The next vringh_get_kern() will return the old descriptor(s) again.
 */
void vringh_abandon_kern(struct vringh *vrh, unsigned int num)
{
	/* We only update vring_avail_event(vr) when we want to be notified,
	 * so we haven't changed that yet. */
	vrh->last_avail_idx -= num;
}
EXPORT_SYMBOL(vringh_abandon_kern);

/**
 * vringh_complete_kern - we've finished with descriptor, publish it.
 * @vrh: the vring.
 * @head: the head as filled in by vringh_getdesc_kern.
 * @len: the length of data we have written.
 *
 * You should check vringh_need_notify_kern() after one or more calls
 * to this function.
 */
int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len)
{
	struct vring_used_elem used;

	used.id = cpu_to_vringh32(vrh, head);
	used.len = cpu_to_vringh32(vrh, len);

	return __vringh_complete(vrh, &used, 1, putu16_kern, putused_kern);
}
EXPORT_SYMBOL(vringh_complete_kern);

/**
 * vringh_notify_enable_kern - we want to know if something changes.
 * @vrh: the vring.
 *
 * This always enables notifications, but returns false if there are
 * now more buffers available in the vring.
 */
bool vringh_notify_enable_kern(struct vringh *vrh)
{
	return __vringh_notify_enable(vrh, getu16_kern, putu16_kern);
}
EXPORT_SYMBOL(vringh_notify_enable_kern);

/**
 * vringh_notify_disable_kern - don't tell us if something changes.
 * @vrh: the vring.
 *
 * This is our normal running state: we disable and then only enable when
 * we're going to sleep.
 */
void vringh_notify_disable_kern(struct vringh *vrh)
{
	__vringh_notify_disable(vrh, putu16_kern);
}
EXPORT_SYMBOL(vringh_notify_disable_kern);

/**
 * vringh_need_notify_kern - must we tell the other side about used buffers?
 * @vrh: the vring we've called vringh_complete_kern() on.
 *
 * Returns -errno or 0 if we don't need to tell the other side, 1 if we do.
 */
int vringh_need_notify_kern(struct vringh *vrh)
{
	return __vringh_need_notify(vrh, getu16_kern);
}
EXPORT_SYMBOL(vringh_need_notify_kern);

MODULE_LICENSE("GPL");