summaryrefslogtreecommitdiffstats
path: root/drivers/virtio/virtio_ring.c
blob: 409aeaa49246a0edd7c6da07ca38b58c3f876109 (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
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
/* Virtio ring implementation.
 *
 *  Copyright 2007 Rusty Russell IBM Corporation
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include <linux/virtio.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_config.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/hrtimer.h>
#include <linux/kmemleak.h>
#include <linux/dma-mapping.h>
#include <xen/xen.h>

#ifdef DEBUG
/* For development, we want to crash whenever the ring is screwed. */
#define BAD_RING(_vq, fmt, args...)				\
	do {							\
		dev_err(&(_vq)->vq.vdev->dev,			\
			"%s:"fmt, (_vq)->vq.name, ##args);	\
		BUG();						\
	} while (0)
/* Caller is supposed to guarantee no reentry. */
#define START_USE(_vq)						\
	do {							\
		if ((_vq)->in_use)				\
			panic("%s:in_use = %i\n",		\
			      (_vq)->vq.name, (_vq)->in_use);	\
		(_vq)->in_use = __LINE__;			\
	} while (0)
#define END_USE(_vq) \
	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
#else
#define BAD_RING(_vq, fmt, args...)				\
	do {							\
		dev_err(&_vq->vq.vdev->dev,			\
			"%s:"fmt, (_vq)->vq.name, ##args);	\
		(_vq)->broken = true;				\
	} while (0)
#define START_USE(vq)
#define END_USE(vq)
#endif

struct vring_desc_state {
	void *data;			/* Data for callback. */
	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
};

struct vring_virtqueue {
	struct virtqueue vq;

	/* Actual memory layout for this queue */
	struct vring vring;

	/* Can we use weak barriers? */
	bool weak_barriers;

	/* Other side has made a mess, don't try any more. */
	bool broken;

	/* Host supports indirect buffers */
	bool indirect;

	/* Host publishes avail event idx */
	bool event;

	/* Head of free buffer list. */
	unsigned int free_head;
	/* Number we've added since last sync. */
	unsigned int num_added;

	/* Last used index we've seen. */
	u16 last_used_idx;

	/* Last written value to avail->flags */
	u16 avail_flags_shadow;

	/* Last written value to avail->idx in guest byte order */
	u16 avail_idx_shadow;

	/* How to notify other side. FIXME: commonalize hcalls! */
	bool (*notify)(struct virtqueue *vq);

	/* DMA, allocation, and size information */
	bool we_own_ring;
	size_t queue_size_in_bytes;
	dma_addr_t queue_dma_addr;

#ifdef DEBUG
	/* They're supposed to lock for us. */
	unsigned int in_use;

	/* Figure out if their kicks are too delayed. */
	bool last_add_time_valid;
	ktime_t last_add_time;
#endif

	/* Per-descriptor state. */
	struct vring_desc_state desc_state[];
};

#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)

/*
 * Modern virtio devices have feature bits to specify whether they need a
 * quirk and bypass the IOMMU. If not there, just use the DMA API.
 *
 * If there, the interaction between virtio and DMA API is messy.
 *
 * On most systems with virtio, physical addresses match bus addresses,
 * and it doesn't particularly matter whether we use the DMA API.
 *
 * On some systems, including Xen and any system with a physical device
 * that speaks virtio behind a physical IOMMU, we must use the DMA API
 * for virtio DMA to work at all.
 *
 * On other systems, including SPARC and PPC64, virtio-pci devices are
 * enumerated as though they are behind an IOMMU, but the virtio host
 * ignores the IOMMU, so we must either pretend that the IOMMU isn't
 * there or somehow map everything as the identity.
 *
 * For the time being, we preserve historic behavior and bypass the DMA
 * API.
 *
 * TODO: install a per-device DMA ops structure that does the right thing
 * taking into account all the above quirks, and use the DMA API
 * unconditionally on data path.
 */

static bool vring_use_dma_api(struct virtio_device *vdev)
{
	if (!virtio_has_iommu_quirk(vdev))
		return true;

	/* Otherwise, we are left to guess. */
	/*
	 * In theory, it's possible to have a buggy QEMU-supposed
	 * emulated Q35 IOMMU and Xen enabled at the same time.  On
	 * such a configuration, virtio has never worked and will
	 * not work without an even larger kludge.  Instead, enable
	 * the DMA API if we're a Xen guest, which at least allows
	 * all of the sensible Xen configurations to work correctly.
	 */
	if (xen_domain())
		return true;

	return false;
}

/*
 * The DMA ops on various arches are rather gnarly right now, and
 * making all of the arch DMA ops work on the vring device itself
 * is a mess.  For now, we use the parent device for DMA ops.
 */
static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
	return vq->vq.vdev->dev.parent;
}

/* Map one sg entry. */
static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
				   struct scatterlist *sg,
				   enum dma_data_direction direction)
{
	if (!vring_use_dma_api(vq->vq.vdev))
		return (dma_addr_t)sg_phys(sg);

	/*
	 * We can't use dma_map_sg, because we don't use scatterlists in
	 * the way it expects (we don't guarantee that the scatterlist
	 * will exist for the lifetime of the mapping).
	 */
	return dma_map_page(vring_dma_dev(vq),
			    sg_page(sg), sg->offset, sg->length,
			    direction);
}

static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
				   void *cpu_addr, size_t size,
				   enum dma_data_direction direction)
{
	if (!vring_use_dma_api(vq->vq.vdev))
		return (dma_addr_t)virt_to_phys(cpu_addr);

	return dma_map_single(vring_dma_dev(vq),
			      cpu_addr, size, direction);
}

static void vring_unmap_one(const struct vring_virtqueue *vq,
			    struct vring_desc *desc)
{
	u16 flags;

	if (!vring_use_dma_api(vq->vq.vdev))
		return;

	flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);

	if (flags & VRING_DESC_F_INDIRECT) {
		dma_unmap_single(vring_dma_dev(vq),
				 virtio64_to_cpu(vq->vq.vdev, desc->addr),
				 virtio32_to_cpu(vq->vq.vdev, desc->len),
				 (flags & VRING_DESC_F_WRITE) ?
				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
	} else {
		dma_unmap_page(vring_dma_dev(vq),
			       virtio64_to_cpu(vq->vq.vdev, desc->addr),
			       virtio32_to_cpu(vq->vq.vdev, desc->len),
			       (flags & VRING_DESC_F_WRITE) ?
			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
	}
}

static int vring_mapping_error(const struct vring_virtqueue *vq,
			       dma_addr_t addr)
{
	if (!vring_use_dma_api(vq->vq.vdev))
		return 0;

	return dma_mapping_error(vring_dma_dev(vq), addr);
}

static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
					 unsigned int total_sg, gfp_t gfp)
{
	struct vring_desc *desc;
	unsigned int i;

	/*
	 * We require lowmem mappings for the descriptors because
	 * otherwise virt_to_phys will give us bogus addresses in the
	 * virtqueue.
	 */
	gfp &= ~__GFP_HIGHMEM;

	desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
	if (!desc)
		return NULL;

	for (i = 0; i < total_sg; i++)
		desc[i].next = cpu_to_virtio16(_vq->vdev, i + 1);
	return desc;
}

static inline int virtqueue_add(struct virtqueue *_vq,
				struct scatterlist *sgs[],
				unsigned int total_sg,
				unsigned int out_sgs,
				unsigned int in_sgs,
				void *data,
				gfp_t gfp)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	struct scatterlist *sg;
	struct vring_desc *desc;
	unsigned int i, n, avail, descs_used, uninitialized_var(prev), err_idx;
	int head;
	bool indirect;

	START_USE(vq);

	BUG_ON(data == NULL);

	if (unlikely(vq->broken)) {
		END_USE(vq);
		return -EIO;
	}

#ifdef DEBUG
	{
		ktime_t now = ktime_get();

		/* No kick or get, with .1 second between?  Warn. */
		if (vq->last_add_time_valid)
			WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
					    > 100);
		vq->last_add_time = now;
		vq->last_add_time_valid = true;
	}
#endif

	BUG_ON(total_sg > vq->vring.num);
	BUG_ON(total_sg == 0);

	head = vq->free_head;

	/* If the host supports indirect descriptor tables, and we have multiple
	 * buffers, then go indirect. FIXME: tune this threshold */
	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
		desc = alloc_indirect(_vq, total_sg, gfp);
	else
		desc = NULL;

	if (desc) {
		/* Use a single buffer which doesn't continue */
		indirect = true;
		/* Set up rest to use this indirect table. */
		i = 0;
		descs_used = 1;
	} else {
		indirect = false;
		desc = vq->vring.desc;
		i = head;
		descs_used = total_sg;
	}

	if (vq->vq.num_free < descs_used) {
		pr_debug("Can't add buf len %i - avail = %i\n",
			 descs_used, vq->vq.num_free);
		/* FIXME: for historical reasons, we force a notify here if
		 * there are outgoing parts to the buffer.  Presumably the
		 * host should service the ring ASAP. */
		if (out_sgs)
			vq->notify(&vq->vq);
		if (indirect)
			kfree(desc);
		END_USE(vq);
		return -ENOSPC;
	}

	for (n = 0; n < out_sgs; n++) {
		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_TO_DEVICE);
			if (vring_mapping_error(vq, addr))
				goto unmap_release;

			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT);
			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
			prev = i;
			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
		}
	}
	for (; n < (out_sgs + in_sgs); n++) {
		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_FROM_DEVICE);
			if (vring_mapping_error(vq, addr))
				goto unmap_release;

			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE);
			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
			prev = i;
			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
		}
	}
	/* Last one doesn't continue. */
	desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);

	if (indirect) {
		/* Now that the indirect table is filled in, map it. */
		dma_addr_t addr = vring_map_single(
			vq, desc, total_sg * sizeof(struct vring_desc),
			DMA_TO_DEVICE);
		if (vring_mapping_error(vq, addr))
			goto unmap_release;

		vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
		vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr);

		vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
	}

	/* We're using some buffers from the free list. */
	vq->vq.num_free -= descs_used;

	/* Update free pointer */
	if (indirect)
		vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
	else
		vq->free_head = i;

	/* Store token and indirect buffer state. */
	vq->desc_state[head].data = data;
	if (indirect)
		vq->desc_state[head].indir_desc = desc;

	/* Put entry in available array (but don't update avail->idx until they
	 * do sync). */
	avail = vq->avail_idx_shadow & (vq->vring.num - 1);
	vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);

	/* Descriptors and available array need to be set before we expose the
	 * new available array entries. */
	virtio_wmb(vq->weak_barriers);
	vq->avail_idx_shadow++;
	vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
	vq->num_added++;

	pr_debug("Added buffer head %i to %p\n", head, vq);
	END_USE(vq);

	/* This is very unlikely, but theoretically possible.  Kick
	 * just in case. */
	if (unlikely(vq->num_added == (1 << 16) - 1))
		virtqueue_kick(_vq);

	return 0;

unmap_release:
	err_idx = i;
	i = head;

	for (n = 0; n < total_sg; n++) {
		if (i == err_idx)
			break;
		vring_unmap_one(vq, &desc[i]);
		i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
	}

	vq->vq.num_free += total_sg;

	if (indirect)
		kfree(desc);

	END_USE(vq);
	return -EIO;
}

/**
 * virtqueue_add_sgs - expose buffers to other end
 * @vq: the struct virtqueue we're talking about.
 * @sgs: array of terminated scatterlists.
 * @out_num: the number of scatterlists readable by other side
 * @in_num: the number of scatterlists which are writable (after readable ones)
 * @data: the token identifying the buffer.
 * @gfp: how to do memory allocations (if necessary).
 *
 * Caller must ensure we don't call this with other virtqueue operations
 * at the same time (except where noted).
 *
 * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
 */
int virtqueue_add_sgs(struct virtqueue *_vq,
		      struct scatterlist *sgs[],
		      unsigned int out_sgs,
		      unsigned int in_sgs,
		      void *data,
		      gfp_t gfp)
{
	unsigned int i, total_sg = 0;

	/* Count them first. */
	for (i = 0; i < out_sgs + in_sgs; i++) {
		struct scatterlist *sg;
		for (sg = sgs[i]; sg; sg = sg_next(sg))
			total_sg++;
	}
	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_sgs);

/**
 * virtqueue_add_outbuf - expose output buffers to other end
 * @vq: the struct virtqueue we're talking about.
 * @sg: scatterlist (must be well-formed and terminated!)
 * @num: the number of entries in @sg readable by other side
 * @data: the token identifying the buffer.
 * @gfp: how to do memory allocations (if necessary).
 *
 * Caller must ensure we don't call this with other virtqueue operations
 * at the same time (except where noted).
 *
 * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
 */
int virtqueue_add_outbuf(struct virtqueue *vq,
			 struct scatterlist *sg, unsigned int num,
			 void *data,
			 gfp_t gfp)
{
	return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);

/**
 * virtqueue_add_inbuf - expose input buffers to other end
 * @vq: the struct virtqueue we're talking about.
 * @sg: scatterlist (must be well-formed and terminated!)
 * @num: the number of entries in @sg writable by other side
 * @data: the token identifying the buffer.
 * @gfp: how to do memory allocations (if necessary).
 *
 * Caller must ensure we don't call this with other virtqueue operations
 * at the same time (except where noted).
 *
 * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
 */
int virtqueue_add_inbuf(struct virtqueue *vq,
			struct scatterlist *sg, unsigned int num,
			void *data,
			gfp_t gfp)
{
	return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);

/**
 * virtqueue_kick_prepare - first half of split virtqueue_kick call.
 * @vq: the struct virtqueue
 *
 * Instead of virtqueue_kick(), you can do:
 *	if (virtqueue_kick_prepare(vq))
 *		virtqueue_notify(vq);
 *
 * This is sometimes useful because the virtqueue_kick_prepare() needs
 * to be serialized, but the actual virtqueue_notify() call does not.
 */
bool virtqueue_kick_prepare(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	u16 new, old;
	bool needs_kick;

	START_USE(vq);
	/* We need to expose available array entries before checking avail
	 * event. */
	virtio_mb(vq->weak_barriers);

	old = vq->avail_idx_shadow - vq->num_added;
	new = vq->avail_idx_shadow;
	vq->num_added = 0;

#ifdef DEBUG
	if (vq->last_add_time_valid) {
		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
					      vq->last_add_time)) > 100);
	}
	vq->last_add_time_valid = false;
#endif

	if (vq->event) {
		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
					      new, old);
	} else {
		needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
	}
	END_USE(vq);
	return needs_kick;
}
EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);

/**
 * virtqueue_notify - second half of split virtqueue_kick call.
 * @vq: the struct virtqueue
 *
 * This does not need to be serialized.
 *
 * Returns false if host notify failed or queue is broken, otherwise true.
 */
bool virtqueue_notify(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	if (unlikely(vq->broken))
		return false;

	/* Prod other side to tell it about changes. */
	if (!vq->notify(_vq)) {
		vq->broken = true;
		return false;
	}
	return true;
}
EXPORT_SYMBOL_GPL(virtqueue_notify);

/**
 * virtqueue_kick - update after add_buf
 * @vq: the struct virtqueue
 *
 * After one or more virtqueue_add_* calls, invoke this to kick
 * the other side.
 *
 * Caller must ensure we don't call this with other virtqueue
 * operations at the same time (except where noted).
 *
 * Returns false if kick failed, otherwise true.
 */
bool virtqueue_kick(struct virtqueue *vq)
{
	if (virtqueue_kick_prepare(vq))
		return virtqueue_notify(vq);
	return true;
}
EXPORT_SYMBOL_GPL(virtqueue_kick);

static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
{
	unsigned int i, j;
	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);

	/* Clear data ptr. */
	vq->desc_state[head].data = NULL;

	/* Put back on free list: unmap first-level descriptors and find end */
	i = head;

	while (vq->vring.desc[i].flags & nextflag) {
		vring_unmap_one(vq, &vq->vring.desc[i]);
		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
		vq->vq.num_free++;
	}

	vring_unmap_one(vq, &vq->vring.desc[i]);
	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
	vq->free_head = head;

	/* Plus final descriptor */
	vq->vq.num_free++;

	/* Free the indirect table, if any, now that it's unmapped. */
	if (vq->desc_state[head].indir_desc) {
		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
		u32 len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);

		BUG_ON(!(vq->vring.desc[head].flags &
			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
		BUG_ON(len == 0 || len % sizeof(struct vring_desc));

		for (j = 0; j < len / sizeof(struct vring_desc); j++)
			vring_unmap_one(vq, &indir_desc[j]);

		kfree(vq->desc_state[head].indir_desc);
		vq->desc_state[head].indir_desc = NULL;
	}
}

static inline bool more_used(const struct vring_virtqueue *vq)
{
	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
}

/**
 * virtqueue_get_buf - get the next used buffer
 * @vq: the struct virtqueue we're talking about.
 * @len: the length written into the buffer
 *
 * If the device wrote data into the buffer, @len will be set to the
 * amount written.  This means you don't need to clear the buffer
 * beforehand to ensure there's no data leakage in the case of short
 * writes.
 *
 * Caller must ensure we don't call this with other virtqueue
 * operations at the same time (except where noted).
 *
 * Returns NULL if there are no used buffers, or the "data" token
 * handed to virtqueue_add_*().
 */
void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	void *ret;
	unsigned int i;
	u16 last_used;

	START_USE(vq);

	if (unlikely(vq->broken)) {
		END_USE(vq);
		return NULL;
	}

	if (!more_used(vq)) {
		pr_debug("No more buffers in queue\n");
		END_USE(vq);
		return NULL;
	}

	/* Only get used array entries after they have been exposed by host. */
	virtio_rmb(vq->weak_barriers);

	last_used = (vq->last_used_idx & (vq->vring.num - 1));
	i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
	*len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);

	if (unlikely(i >= vq->vring.num)) {
		BAD_RING(vq, "id %u out of range\n", i);
		return NULL;
	}
	if (unlikely(!vq->desc_state[i].data)) {
		BAD_RING(vq, "id %u is not a head!\n", i);
		return NULL;
	}

	/* detach_buf clears data, so grab it now. */
	ret = vq->desc_state[i].data;
	detach_buf(vq, i);
	vq->last_used_idx++;
	/* If we expect an interrupt for the next entry, tell host
	 * by writing event index and flush out the write before
	 * the read in the next get_buf call. */
	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
		virtio_store_mb(vq->weak_barriers,
				&vring_used_event(&vq->vring),
				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));

#ifdef DEBUG
	vq->last_add_time_valid = false;
#endif

	END_USE(vq);
	return ret;
}
EXPORT_SYMBOL_GPL(virtqueue_get_buf);

/**
 * virtqueue_disable_cb - disable callbacks
 * @vq: the struct virtqueue we're talking about.
 *
 * Note that this is not necessarily synchronous, hence unreliable and only
 * useful as an optimization.
 *
 * Unlike other operations, this need not be serialized.
 */
void virtqueue_disable_cb(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
		if (!vq->event)
			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
	}

}
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);

/**
 * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
 * @vq: the struct virtqueue we're talking about.
 *
 * This re-enables callbacks; it returns current queue state
 * in an opaque unsigned value. This value should be later tested by
 * virtqueue_poll, to detect a possible race between the driver checking for
 * more work, and enabling callbacks.
 *
 * Caller must ensure we don't call this with other virtqueue
 * operations at the same time (except where noted).
 */
unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	u16 last_used_idx;

	START_USE(vq);

	/* We optimistically turn back on interrupts, then check if there was
	 * more to do. */
	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
	 * either clear the flags bit or point the event index at the next
	 * entry. Always do both to keep code simple. */
	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
		if (!vq->event)
			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
	}
	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
	END_USE(vq);
	return last_used_idx;
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);

/**
 * virtqueue_poll - query pending used buffers
 * @vq: the struct virtqueue we're talking about.
 * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
 *
 * Returns "true" if there are pending used buffers in the queue.
 *
 * This does not need to be serialized.
 */
bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	virtio_mb(vq->weak_barriers);
	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
}
EXPORT_SYMBOL_GPL(virtqueue_poll);

/**
 * virtqueue_enable_cb - restart callbacks after disable_cb.
 * @vq: the struct virtqueue we're talking about.
 *
 * This re-enables callbacks; it returns "false" if there are pending
 * buffers in the queue, to detect a possible race between the driver
 * checking for more work, and enabling callbacks.
 *
 * Caller must ensure we don't call this with other virtqueue
 * operations at the same time (except where noted).
 */
bool virtqueue_enable_cb(struct virtqueue *_vq)
{
	unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
	return !virtqueue_poll(_vq, last_used_idx);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb);

/**
 * virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
 * @vq: the struct virtqueue we're talking about.
 *
 * This re-enables callbacks but hints to the other side to delay
 * interrupts until most of the available buffers have been processed;
 * it returns "false" if there are many pending buffers in the queue,
 * to detect a possible race between the driver checking for more work,
 * and enabling callbacks.
 *
 * Caller must ensure we don't call this with other virtqueue
 * operations at the same time (except where noted).
 */
bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	u16 bufs;

	START_USE(vq);

	/* We optimistically turn back on interrupts, then check if there was
	 * more to do. */
	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
	 * either clear the flags bit or point the event index at the next
	 * entry. Always update the event index to keep code simple. */
	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
		if (!vq->event)
			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
	}
	/* TODO: tune this threshold */
	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;

	virtio_store_mb(vq->weak_barriers,
			&vring_used_event(&vq->vring),
			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));

	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
		END_USE(vq);
		return false;
	}

	END_USE(vq);
	return true;
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);

/**
 * virtqueue_detach_unused_buf - detach first unused buffer
 * @vq: the struct virtqueue we're talking about.
 *
 * Returns NULL or the "data" token handed to virtqueue_add_*().
 * This is not valid on an active queue; it is useful only for device
 * shutdown.
 */
void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);
	unsigned int i;
	void *buf;

	START_USE(vq);

	for (i = 0; i < vq->vring.num; i++) {
		if (!vq->desc_state[i].data)
			continue;
		/* detach_buf clears data, so grab it now. */
		buf = vq->desc_state[i].data;
		detach_buf(vq, i);
		vq->avail_idx_shadow--;
		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
		END_USE(vq);
		return buf;
	}
	/* That should have freed everything. */
	BUG_ON(vq->vq.num_free != vq->vring.num);

	END_USE(vq);
	return NULL;
}
EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);

irqreturn_t vring_interrupt(int irq, void *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	if (!more_used(vq)) {
		pr_debug("virtqueue interrupt with no work for %p\n", vq);
		return IRQ_NONE;
	}

	if (unlikely(vq->broken))
		return IRQ_HANDLED;

	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
	if (vq->vq.callback)
		vq->vq.callback(&vq->vq);

	return IRQ_HANDLED;
}
EXPORT_SYMBOL_GPL(vring_interrupt);

struct virtqueue *__vring_new_virtqueue(unsigned int index,
					struct vring vring,
					struct virtio_device *vdev,
					bool weak_barriers,
					bool (*notify)(struct virtqueue *),
					void (*callback)(struct virtqueue *),
					const char *name)
{
	unsigned int i;
	struct vring_virtqueue *vq;

	vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
		     GFP_KERNEL);
	if (!vq)
		return NULL;

	vq->vring = vring;
	vq->vq.callback = callback;
	vq->vq.vdev = vdev;
	vq->vq.name = name;
	vq->vq.num_free = vring.num;
	vq->vq.index = index;
	vq->we_own_ring = false;
	vq->queue_dma_addr = 0;
	vq->queue_size_in_bytes = 0;
	vq->notify = notify;
	vq->weak_barriers = weak_barriers;
	vq->broken = false;
	vq->last_used_idx = 0;
	vq->avail_flags_shadow = 0;
	vq->avail_idx_shadow = 0;
	vq->num_added = 0;
	list_add_tail(&vq->vq.list, &vdev->vqs);
#ifdef DEBUG
	vq->in_use = false;
	vq->last_add_time_valid = false;
#endif

	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);

	/* No callback?  Tell other side not to bother us. */
	if (!callback) {
		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
		if (!vq->event)
			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
	}

	/* Put everything in free lists. */
	vq->free_head = 0;
	for (i = 0; i < vring.num-1; i++)
		vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));

	return &vq->vq;
}
EXPORT_SYMBOL_GPL(__vring_new_virtqueue);

static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
			      dma_addr_t *dma_handle, gfp_t flag)
{
	if (vring_use_dma_api(vdev)) {
		return dma_alloc_coherent(vdev->dev.parent, size,
					  dma_handle, flag);
	} else {
		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
		if (queue) {
			phys_addr_t phys_addr = virt_to_phys(queue);
			*dma_handle = (dma_addr_t)phys_addr;

			/*
			 * Sanity check: make sure we dind't truncate
			 * the address.  The only arches I can find that
			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
			 * are certain non-highmem MIPS and x86
			 * configurations, but these configurations
			 * should never allocate physical pages above 32
			 * bits, so this is fine.  Just in case, throw a
			 * warning and abort if we end up with an
			 * unrepresentable address.
			 */
			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
				free_pages_exact(queue, PAGE_ALIGN(size));
				return NULL;
			}
		}
		return queue;
	}
}

static void vring_free_queue(struct virtio_device *vdev, size_t size,
			     void *queue, dma_addr_t dma_handle)
{
	if (vring_use_dma_api(vdev)) {
		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
	} else {
		free_pages_exact(queue, PAGE_ALIGN(size));
	}
}

struct virtqueue *vring_create_virtqueue(
	unsigned int index,
	unsigned int num,
	unsigned int vring_align,
	struct virtio_device *vdev,
	bool weak_barriers,
	bool may_reduce_num,
	bool (*notify)(struct virtqueue *),
	void (*callback)(struct virtqueue *),
	const char *name)
{
	struct virtqueue *vq;
	void *queue = NULL;
	dma_addr_t dma_addr;
	size_t queue_size_in_bytes;
	struct vring vring;

	/* We assume num is a power of 2. */
	if (num & (num - 1)) {
		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
		return NULL;
	}

	/* TODO: allocate each queue chunk individually */
	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
					  &dma_addr,
					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
		if (queue)
			break;
	}

	if (!num)
		return NULL;

	if (!queue) {
		/* Try to get a single page. You are my only hope! */
		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
	}
	if (!queue)
		return NULL;

	queue_size_in_bytes = vring_size(num, vring_align);
	vring_init(&vring, num, queue, vring_align);

	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers,
				   notify, callback, name);
	if (!vq) {
		vring_free_queue(vdev, queue_size_in_bytes, queue,
				 dma_addr);
		return NULL;
	}

	to_vvq(vq)->queue_dma_addr = dma_addr;
	to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes;
	to_vvq(vq)->we_own_ring = true;

	return vq;
}
EXPORT_SYMBOL_GPL(vring_create_virtqueue);

struct virtqueue *vring_new_virtqueue(unsigned int index,
				      unsigned int num,
				      unsigned int vring_align,
				      struct virtio_device *vdev,
				      bool weak_barriers,
				      void *pages,
				      bool (*notify)(struct virtqueue *vq),
				      void (*callback)(struct virtqueue *vq),
				      const char *name)
{
	struct vring vring;
	vring_init(&vring, num, pages, vring_align);
	return __vring_new_virtqueue(index, vring, vdev, weak_barriers,
				     notify, callback, name);
}
EXPORT_SYMBOL_GPL(vring_new_virtqueue);

void vring_del_virtqueue(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	if (vq->we_own_ring) {
		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
				 vq->vring.desc, vq->queue_dma_addr);
	}
	list_del(&_vq->list);
	kfree(vq);
}
EXPORT_SYMBOL_GPL(vring_del_virtqueue);

/* Manipulates transport-specific feature bits. */
void vring_transport_features(struct virtio_device *vdev)
{
	unsigned int i;

	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) {
		switch (i) {
		case VIRTIO_RING_F_INDIRECT_DESC:
			break;
		case VIRTIO_RING_F_EVENT_IDX:
			break;
		case VIRTIO_F_VERSION_1:
			break;
		case VIRTIO_F_IOMMU_PLATFORM:
			break;
		default:
			/* We don't understand this bit. */
			__virtio_clear_bit(vdev, i);
		}
	}
}
EXPORT_SYMBOL_GPL(vring_transport_features);

/**
 * virtqueue_get_vring_size - return the size of the virtqueue's vring
 * @vq: the struct virtqueue containing the vring of interest.
 *
 * Returns the size of the vring.  This is mainly used for boasting to
 * userspace.  Unlike other operations, this need not be serialized.
 */
unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
{

	struct vring_virtqueue *vq = to_vvq(_vq);

	return vq->vring.num;
}
EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);

bool virtqueue_is_broken(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	return vq->broken;
}
EXPORT_SYMBOL_GPL(virtqueue_is_broken);

/*
 * This should prevent the device from being used, allowing drivers to
 * recover.  You may need to grab appropriate locks to flush.
 */
void virtio_break_device(struct virtio_device *dev)
{
	struct virtqueue *_vq;

	list_for_each_entry(_vq, &dev->vqs, list) {
		struct vring_virtqueue *vq = to_vvq(_vq);
		vq->broken = true;
	}
}
EXPORT_SYMBOL_GPL(virtio_break_device);

dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	BUG_ON(!vq->we_own_ring);

	return vq->queue_dma_addr;
}
EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);

dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	BUG_ON(!vq->we_own_ring);

	return vq->queue_dma_addr +
		((char *)vq->vring.avail - (char *)vq->vring.desc);
}
EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);

dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
{
	struct vring_virtqueue *vq = to_vvq(_vq);

	BUG_ON(!vq->we_own_ring);

	return vq->queue_dma_addr +
		((char *)vq->vring.used - (char *)vq->vring.desc);
}
EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);

const struct vring *virtqueue_get_vring(struct virtqueue *vq)
{
	return &to_vvq(vq)->vring;
}
EXPORT_SYMBOL_GPL(virtqueue_get_vring);

MODULE_LICENSE("GPL");