forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xen-blkfront.c
2117 lines (1805 loc) · 55.4 KB
/
xen-blkfront.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
/*
* blkfront.c
*
* XenLinux virtual block device driver.
*
* Copyright (c) 2003-2004, Keir Fraser & Steve Hand
* Modifications by Mark A. Williamson are (c) Intel Research Cambridge
* Copyright (c) 2004, Christian Limpach
* Copyright (c) 2004, Andrew Warfield
* Copyright (c) 2005, Christopher Clark
* Copyright (c) 2005, XenSource Ltd
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation; or, when distributed
* separately from the Linux kernel or incorporated into other
* software packages, subject to the following license:
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this source file (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy, modify,
* merge, publish, distribute, sublicense, and/or sell copies of the Software,
* and to permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include <linux/interrupt.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/cdrom.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/bitmap.h>
#include <linux/list.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/grant_table.h>
#include <xen/events.h>
#include <xen/page.h>
#include <xen/platform_pci.h>
#include <xen/interface/grant_table.h>
#include <xen/interface/io/blkif.h>
#include <xen/interface/io/protocols.h>
#include <asm/xen/hypervisor.h>
enum blkif_state {
BLKIF_STATE_DISCONNECTED,
BLKIF_STATE_CONNECTED,
BLKIF_STATE_SUSPENDED,
};
struct grant {
grant_ref_t gref;
unsigned long pfn;
struct list_head node;
};
struct blk_shadow {
struct blkif_request req;
struct request *request;
struct grant **grants_used;
struct grant **indirect_grants;
struct scatterlist *sg;
};
struct split_bio {
struct bio *bio;
atomic_t pending;
int err;
};
static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;
/*
* Maximum number of segments in indirect requests, the actual value used by
* the frontend driver is the minimum of this value and the value provided
* by the backend driver.
*/
static unsigned int xen_blkif_max_segments = 32;
module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests (default is 32)");
#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)
/*
* We have one of these per vbd, whether ide, scsi or 'other'. They
* hang in private_data off the gendisk structure. We may end up
* putting all kinds of interesting stuff here :-)
*/
struct blkfront_info
{
spinlock_t io_lock;
struct mutex mutex;
struct xenbus_device *xbdev;
struct gendisk *gd;
int vdevice;
blkif_vdev_t handle;
enum blkif_state connected;
int ring_ref;
struct blkif_front_ring ring;
unsigned int evtchn, irq;
struct request_queue *rq;
struct work_struct work;
struct gnttab_free_callback callback;
struct blk_shadow shadow[BLK_RING_SIZE];
struct list_head grants;
struct list_head indirect_pages;
unsigned int persistent_gnts_c;
unsigned long shadow_free;
unsigned int feature_flush;
unsigned int flush_op;
unsigned int feature_discard:1;
unsigned int feature_secdiscard:1;
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned int feature_persistent:1;
unsigned int max_indirect_segments;
int is_ready;
};
static unsigned int nr_minors;
static unsigned long *minors;
static DEFINE_SPINLOCK(minor_lock);
#define MAXIMUM_OUTSTANDING_BLOCK_REQS \
(BLKIF_MAX_SEGMENTS_PER_REQUEST * BLK_RING_SIZE)
#define GRANT_INVALID_REF 0
#define PARTS_PER_DISK 16
#define PARTS_PER_EXT_DISK 256
#define BLKIF_MAJOR(dev) ((dev)>>8)
#define BLKIF_MINOR(dev) ((dev) & 0xff)
#define EXT_SHIFT 28
#define EXTENDED (1<<EXT_SHIFT)
#define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
#define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
#define EMULATED_HD_DISK_MINOR_OFFSET (0)
#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
#define EMULATED_SD_DISK_MINOR_OFFSET (0)
#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256)
#define DEV_NAME "xvd" /* name in /dev */
#define SEGS_PER_INDIRECT_FRAME \
(PAGE_SIZE/sizeof(struct blkif_request_segment))
#define INDIRECT_GREFS(_segs) \
((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
static int blkfront_setup_indirect(struct blkfront_info *info);
static int get_id_from_freelist(struct blkfront_info *info)
{
unsigned long free = info->shadow_free;
BUG_ON(free >= BLK_RING_SIZE);
info->shadow_free = info->shadow[free].req.u.rw.id;
info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
return free;
}
static int add_id_to_freelist(struct blkfront_info *info,
unsigned long id)
{
if (info->shadow[id].req.u.rw.id != id)
return -EINVAL;
if (info->shadow[id].request == NULL)
return -EINVAL;
info->shadow[id].req.u.rw.id = info->shadow_free;
info->shadow[id].request = NULL;
info->shadow_free = id;
return 0;
}
static int fill_grant_buffer(struct blkfront_info *info, int num)
{
struct page *granted_page;
struct grant *gnt_list_entry, *n;
int i = 0;
while(i < num) {
gnt_list_entry = kzalloc(sizeof(struct grant), GFP_NOIO);
if (!gnt_list_entry)
goto out_of_memory;
if (info->feature_persistent) {
granted_page = alloc_page(GFP_NOIO);
if (!granted_page) {
kfree(gnt_list_entry);
goto out_of_memory;
}
gnt_list_entry->pfn = page_to_pfn(granted_page);
}
gnt_list_entry->gref = GRANT_INVALID_REF;
list_add(&gnt_list_entry->node, &info->grants);
i++;
}
return 0;
out_of_memory:
list_for_each_entry_safe(gnt_list_entry, n,
&info->grants, node) {
list_del(&gnt_list_entry->node);
if (info->feature_persistent)
__free_page(pfn_to_page(gnt_list_entry->pfn));
kfree(gnt_list_entry);
i--;
}
BUG_ON(i != 0);
return -ENOMEM;
}
static struct grant *get_grant(grant_ref_t *gref_head,
unsigned long pfn,
struct blkfront_info *info)
{
struct grant *gnt_list_entry;
unsigned long buffer_mfn;
BUG_ON(list_empty(&info->grants));
gnt_list_entry = list_first_entry(&info->grants, struct grant,
node);
list_del(&gnt_list_entry->node);
if (gnt_list_entry->gref != GRANT_INVALID_REF) {
info->persistent_gnts_c--;
return gnt_list_entry;
}
/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
if (!info->feature_persistent) {
BUG_ON(!pfn);
gnt_list_entry->pfn = pfn;
}
buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
info->xbdev->otherend_id,
buffer_mfn, 0);
return gnt_list_entry;
}
static const char *op_name(int op)
{
static const char *const names[] = {
[BLKIF_OP_READ] = "read",
[BLKIF_OP_WRITE] = "write",
[BLKIF_OP_WRITE_BARRIER] = "barrier",
[BLKIF_OP_FLUSH_DISKCACHE] = "flush",
[BLKIF_OP_DISCARD] = "discard" };
if (op < 0 || op >= ARRAY_SIZE(names))
return "unknown";
if (!names[op])
return "reserved";
return names[op];
}
static int xlbd_reserve_minors(unsigned int minor, unsigned int nr)
{
unsigned int end = minor + nr;
int rc;
if (end > nr_minors) {
unsigned long *bitmap, *old;
bitmap = kcalloc(BITS_TO_LONGS(end), sizeof(*bitmap),
GFP_KERNEL);
if (bitmap == NULL)
return -ENOMEM;
spin_lock(&minor_lock);
if (end > nr_minors) {
old = minors;
memcpy(bitmap, minors,
BITS_TO_LONGS(nr_minors) * sizeof(*bitmap));
minors = bitmap;
nr_minors = BITS_TO_LONGS(end) * BITS_PER_LONG;
} else
old = bitmap;
spin_unlock(&minor_lock);
kfree(old);
}
spin_lock(&minor_lock);
if (find_next_bit(minors, end, minor) >= end) {
bitmap_set(minors, minor, nr);
rc = 0;
} else
rc = -EBUSY;
spin_unlock(&minor_lock);
return rc;
}
static void xlbd_release_minors(unsigned int minor, unsigned int nr)
{
unsigned int end = minor + nr;
BUG_ON(end > nr_minors);
spin_lock(&minor_lock);
bitmap_clear(minors, minor, nr);
spin_unlock(&minor_lock);
}
static void blkif_restart_queue_callback(void *arg)
{
struct blkfront_info *info = (struct blkfront_info *)arg;
schedule_work(&info->work);
}
static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
{
/* We don't have real geometry info, but let's at least return
values consistent with the size of the device */
sector_t nsect = get_capacity(bd->bd_disk);
sector_t cylinders = nsect;
hg->heads = 0xff;
hg->sectors = 0x3f;
sector_div(cylinders, hg->heads * hg->sectors);
hg->cylinders = cylinders;
if ((sector_t)(hg->cylinders + 1) * hg->heads * hg->sectors < nsect)
hg->cylinders = 0xffff;
return 0;
}
static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
unsigned command, unsigned long argument)
{
struct blkfront_info *info = bdev->bd_disk->private_data;
int i;
dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n",
command, (long)argument);
switch (command) {
case CDROMMULTISESSION:
dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n");
for (i = 0; i < sizeof(struct cdrom_multisession); i++)
if (put_user(0, (char __user *)(argument + i)))
return -EFAULT;
return 0;
case CDROM_GET_CAPABILITY: {
struct gendisk *gd = info->gd;
if (gd->flags & GENHD_FL_CD)
return 0;
return -EINVAL;
}
default:
/*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
command);*/
return -EINVAL; /* same return as native Linux */
}
return 0;
}
/*
* Generate a Xen blkfront IO request from a blk layer request. Reads
* and writes are handled as expected.
*
* @req: a request struct
*/
static int blkif_queue_request(struct request *req)
{
struct blkfront_info *info = req->rq_disk->private_data;
struct blkif_request *ring_req;
unsigned long id;
unsigned int fsect, lsect;
int i, ref, n;
struct blkif_request_segment *segments = NULL;
/*
* Used to store if we are able to queue the request by just using
* existing persistent grants, or if we have to get new grants,
* as there are not sufficiently many free.
*/
bool new_persistent_gnts;
grant_ref_t gref_head;
struct grant *gnt_list_entry = NULL;
struct scatterlist *sg;
int nseg, max_grefs;
if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
return 1;
max_grefs = req->nr_phys_segments;
if (max_grefs > BLKIF_MAX_SEGMENTS_PER_REQUEST)
/*
* If we are using indirect segments we need to account
* for the indirect grefs used in the request.
*/
max_grefs += INDIRECT_GREFS(req->nr_phys_segments);
/* Check if we have enough grants to allocate a requests */
if (info->persistent_gnts_c < max_grefs) {
new_persistent_gnts = 1;
if (gnttab_alloc_grant_references(
max_grefs - info->persistent_gnts_c,
&gref_head) < 0) {
gnttab_request_free_callback(
&info->callback,
blkif_restart_queue_callback,
info,
max_grefs);
return 1;
}
} else
new_persistent_gnts = 0;
/* Fill out a communications ring structure. */
ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
id = get_id_from_freelist(info);
info->shadow[id].request = req;
if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
ring_req->operation = BLKIF_OP_DISCARD;
ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
ring_req->u.discard.id = id;
ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
else
ring_req->u.discard.flag = 0;
} else {
BUG_ON(info->max_indirect_segments == 0 &&
req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
BUG_ON(info->max_indirect_segments &&
req->nr_phys_segments > info->max_indirect_segments);
nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
ring_req->u.rw.id = id;
if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
/*
* The indirect operation can only be a BLKIF_OP_READ or
* BLKIF_OP_WRITE
*/
BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
ring_req->operation = BLKIF_OP_INDIRECT;
ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
ring_req->u.indirect.handle = info->handle;
ring_req->u.indirect.nr_segments = nseg;
} else {
ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
ring_req->u.rw.handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
/*
* Ideally we can do an unordered flush-to-disk. In case the
* backend onlysupports barriers, use that. A barrier request
* a superset of FUA, so we can implement it the same
* way. (It's also a FLUSH+FUA, since it is
* guaranteed ordered WRT previous writes.)
*/
ring_req->operation = info->flush_op;
}
ring_req->u.rw.nr_segments = nseg;
}
for_each_sg(info->shadow[id].sg, sg, nseg, i) {
fsect = sg->offset >> 9;
lsect = fsect + (sg->length >> 9) - 1;
if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
(i % SEGS_PER_INDIRECT_FRAME == 0)) {
unsigned long uninitialized_var(pfn);
if (segments)
kunmap_atomic(segments);
n = i / SEGS_PER_INDIRECT_FRAME;
if (!info->feature_persistent) {
struct page *indirect_page;
/* Fetch a pre-allocated page to use for indirect grefs */
BUG_ON(list_empty(&info->indirect_pages));
indirect_page = list_first_entry(&info->indirect_pages,
struct page, lru);
list_del(&indirect_page->lru);
pfn = page_to_pfn(indirect_page);
}
gnt_list_entry = get_grant(&gref_head, pfn, info);
info->shadow[id].indirect_grants[n] = gnt_list_entry;
segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
}
gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
ref = gnt_list_entry->gref;
info->shadow[id].grants_used[i] = gnt_list_entry;
if (rq_data_dir(req) && info->feature_persistent) {
char *bvec_data;
void *shared_data;
BUG_ON(sg->offset + sg->length > PAGE_SIZE);
shared_data = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
bvec_data = kmap_atomic(sg_page(sg));
/*
* this does not wipe data stored outside the
* range sg->offset..sg->offset+sg->length.
* Therefore, blkback *could* see data from
* previous requests. This is OK as long as
* persistent grants are shared with just one
* domain. It may need refactoring if this
* changes
*/
memcpy(shared_data + sg->offset,
bvec_data + sg->offset,
sg->length);
kunmap_atomic(bvec_data);
kunmap_atomic(shared_data);
}
if (ring_req->operation != BLKIF_OP_INDIRECT) {
ring_req->u.rw.seg[i] =
(struct blkif_request_segment) {
.gref = ref,
.first_sect = fsect,
.last_sect = lsect };
} else {
n = i % SEGS_PER_INDIRECT_FRAME;
segments[n] =
(struct blkif_request_segment) {
.gref = ref,
.first_sect = fsect,
.last_sect = lsect };
}
}
if (segments)
kunmap_atomic(segments);
}
info->ring.req_prod_pvt++;
/* Keep a private copy so we can reissue requests when recovering. */
info->shadow[id].req = *ring_req;
if (new_persistent_gnts)
gnttab_free_grant_references(gref_head);
return 0;
}
static inline void flush_requests(struct blkfront_info *info)
{
int notify;
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&info->ring, notify);
if (notify)
notify_remote_via_irq(info->irq);
}
/*
* do_blkif_request
* read a block; request is in a request queue
*/
static void do_blkif_request(struct request_queue *rq)
{
struct blkfront_info *info = NULL;
struct request *req;
int queued;
pr_debug("Entered do_blkif_request\n");
queued = 0;
while ((req = blk_peek_request(rq)) != NULL) {
info = req->rq_disk->private_data;
if (RING_FULL(&info->ring))
goto wait;
blk_start_request(req);
if ((req->cmd_type != REQ_TYPE_FS) ||
((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
!info->flush_op)) {
__blk_end_request_all(req, -EIO);
continue;
}
pr_debug("do_blk_req %p: cmd %p, sec %lx, "
"(%u/%u) buffer:%p [%s]\n",
req, req->cmd, (unsigned long)blk_rq_pos(req),
blk_rq_cur_sectors(req), blk_rq_sectors(req),
req->buffer, rq_data_dir(req) ? "write" : "read");
if (blkif_queue_request(req)) {
blk_requeue_request(rq, req);
wait:
/* Avoid pointless unplugs. */
blk_stop_queue(rq);
break;
}
queued++;
}
if (queued != 0)
flush_requests(info);
}
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
unsigned int physical_sector_size,
unsigned int segments)
{
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;
rq = blk_init_queue(do_blkif_request, &info->io_lock);
if (rq == NULL)
return -1;
queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
if (info->feature_discard) {
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
blk_queue_max_discard_sectors(rq, get_capacity(gd));
rq->limits.discard_granularity = info->discard_granularity;
rq->limits.discard_alignment = info->discard_alignment;
if (info->feature_secdiscard)
queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
}
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, sector_size);
blk_queue_physical_block_size(rq, physical_sector_size);
blk_queue_max_hw_sectors(rq, (segments * PAGE_SIZE) / 512);
/* Each segment in a request is up to an aligned page in size. */
blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
blk_queue_max_segments(rq, segments);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
/* Make sure we don't use bounce buffers. */
blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
gd->queue = rq;
return 0;
}
static void xlvbd_flush(struct blkfront_info *info)
{
blk_queue_flush(info->rq, info->feature_flush);
printk(KERN_INFO "blkfront: %s: %s: %s %s %s %s %s\n",
info->gd->disk_name,
info->flush_op == BLKIF_OP_WRITE_BARRIER ?
"barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
"flush diskcache" : "barrier or flush"),
info->feature_flush ? "enabled;" : "disabled;",
"persistent grants:",
info->feature_persistent ? "enabled;" : "disabled;",
"indirect descriptors:",
info->max_indirect_segments ? "enabled;" : "disabled;");
}
static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
{
int major;
major = BLKIF_MAJOR(vdevice);
*minor = BLKIF_MINOR(vdevice);
switch (major) {
case XEN_IDE0_MAJOR:
*offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
*minor = ((*minor / 64) * PARTS_PER_DISK) +
EMULATED_HD_DISK_MINOR_OFFSET;
break;
case XEN_IDE1_MAJOR:
*offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
*minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
EMULATED_HD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK0_MAJOR:
*offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK1_MAJOR:
case XEN_SCSI_DISK2_MAJOR:
case XEN_SCSI_DISK3_MAJOR:
case XEN_SCSI_DISK4_MAJOR:
case XEN_SCSI_DISK5_MAJOR:
case XEN_SCSI_DISK6_MAJOR:
case XEN_SCSI_DISK7_MAJOR:
*offset = (*minor / PARTS_PER_DISK) +
((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor +
((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK8_MAJOR:
case XEN_SCSI_DISK9_MAJOR:
case XEN_SCSI_DISK10_MAJOR:
case XEN_SCSI_DISK11_MAJOR:
case XEN_SCSI_DISK12_MAJOR:
case XEN_SCSI_DISK13_MAJOR:
case XEN_SCSI_DISK14_MAJOR:
case XEN_SCSI_DISK15_MAJOR:
*offset = (*minor / PARTS_PER_DISK) +
((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor +
((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XENVBD_MAJOR:
*offset = *minor / PARTS_PER_DISK;
break;
default:
printk(KERN_WARNING "blkfront: your disk configuration is "
"incorrect, please use an xvd device instead\n");
return -ENODEV;
}
return 0;
}
static char *encode_disk_name(char *ptr, unsigned int n)
{
if (n >= 26)
ptr = encode_disk_name(ptr, n / 26 - 1);
*ptr = 'a' + n % 26;
return ptr + 1;
}
static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
struct blkfront_info *info,
u16 vdisk_info, u16 sector_size,
unsigned int physical_sector_size)
{
struct gendisk *gd;
int nr_minors = 1;
int err;
unsigned int offset;
int minor;
int nr_parts;
char *ptr;
BUG_ON(info->gd != NULL);
BUG_ON(info->rq != NULL);
if ((info->vdevice>>EXT_SHIFT) > 1) {
/* this is above the extended range; something is wrong */
printk(KERN_WARNING "blkfront: vdevice 0x%x is above the extended range; ignoring\n", info->vdevice);
return -ENODEV;
}
if (!VDEV_IS_EXTENDED(info->vdevice)) {
err = xen_translate_vdev(info->vdevice, &minor, &offset);
if (err)
return err;
nr_parts = PARTS_PER_DISK;
} else {
minor = BLKIF_MINOR_EXT(info->vdevice);
nr_parts = PARTS_PER_EXT_DISK;
offset = minor / nr_parts;
if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4)
printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
"emulated IDE disks,\n\t choose an xvd device name"
"from xvde on\n", info->vdevice);
}
if (minor >> MINORBITS) {
pr_warn("blkfront: %#x's minor (%#x) out of range; ignoring\n",
info->vdevice, minor);
return -ENODEV;
}
if ((minor % nr_parts) == 0)
nr_minors = nr_parts;
err = xlbd_reserve_minors(minor, nr_minors);
if (err)
goto out;
err = -ENODEV;
gd = alloc_disk(nr_minors);
if (gd == NULL)
goto release;
strcpy(gd->disk_name, DEV_NAME);
ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset);
BUG_ON(ptr >= gd->disk_name + DISK_NAME_LEN);
if (nr_minors > 1)
*ptr = 0;
else
snprintf(ptr, gd->disk_name + DISK_NAME_LEN - ptr,
"%d", minor & (nr_parts - 1));
gd->major = XENVBD_MAJOR;
gd->first_minor = minor;
gd->fops = &xlvbd_block_fops;
gd->private_data = info;
gd->driverfs_dev = &(info->xbdev->dev);
set_capacity(gd, capacity);
if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
info->max_indirect_segments ? :
BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
del_gendisk(gd);
goto release;
}
info->rq = gd->queue;
info->gd = gd;
xlvbd_flush(info);
if (vdisk_info & VDISK_READONLY)
set_disk_ro(gd, 1);
if (vdisk_info & VDISK_REMOVABLE)
gd->flags |= GENHD_FL_REMOVABLE;
if (vdisk_info & VDISK_CDROM)
gd->flags |= GENHD_FL_CD;
return 0;
release:
xlbd_release_minors(minor, nr_minors);
out:
return err;
}
static void xlvbd_release_gendisk(struct blkfront_info *info)
{
unsigned int minor, nr_minors;
unsigned long flags;
if (info->rq == NULL)
return;
spin_lock_irqsave(&info->io_lock, flags);
/* No more blkif_request(). */
blk_stop_queue(info->rq);
/* No more gnttab callback work. */
gnttab_cancel_free_callback(&info->callback);
spin_unlock_irqrestore(&info->io_lock, flags);
/* Flush gnttab callback work. Must be done with no locks held. */
flush_work(&info->work);
del_gendisk(info->gd);
minor = info->gd->first_minor;
nr_minors = info->gd->minors;
xlbd_release_minors(minor, nr_minors);
blk_cleanup_queue(info->rq);
info->rq = NULL;
put_disk(info->gd);
info->gd = NULL;
}
static void kick_pending_request_queues(struct blkfront_info *info)
{
if (!RING_FULL(&info->ring)) {
/* Re-enable calldowns. */
blk_start_queue(info->rq);
/* Kick things off immediately. */
do_blkif_request(info->rq);
}
}
static void blkif_restart_queue(struct work_struct *work)
{
struct blkfront_info *info = container_of(work, struct blkfront_info, work);
spin_lock_irq(&info->io_lock);
if (info->connected == BLKIF_STATE_CONNECTED)
kick_pending_request_queues(info);
spin_unlock_irq(&info->io_lock);
}
static void blkif_free(struct blkfront_info *info, int suspend)
{
struct grant *persistent_gnt;
struct grant *n;
int i, j, segs;
/* Prevent new requests being issued until we fix things up. */
spin_lock_irq(&info->io_lock);
info->connected = suspend ?
BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
/* No more blkif_request(). */
if (info->rq)
blk_stop_queue(info->rq);
/* Remove all persistent grants */
if (!list_empty(&info->grants)) {
list_for_each_entry_safe(persistent_gnt, n,
&info->grants, node) {
list_del(&persistent_gnt->node);
if (persistent_gnt->gref != GRANT_INVALID_REF) {
gnttab_end_foreign_access(persistent_gnt->gref,
0, 0UL);
info->persistent_gnts_c--;
}
if (info->feature_persistent)
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}
}
BUG_ON(info->persistent_gnts_c != 0);
/*
* Remove indirect pages, this only happens when using indirect
* descriptors but not persistent grants
*/
if (!list_empty(&info->indirect_pages)) {
struct page *indirect_page, *n;
BUG_ON(info->feature_persistent);
list_for_each_entry_safe(indirect_page, n, &info->indirect_pages, lru) {
list_del(&indirect_page->lru);
__free_page(indirect_page);
}
}
for (i = 0; i < BLK_RING_SIZE; i++) {
/*
* Clear persistent grants present in requests already
* on the shared ring
*/
if (!info->shadow[i].request)
goto free_shadow;
segs = info->shadow[i].req.operation == BLKIF_OP_INDIRECT ?
info->shadow[i].req.u.indirect.nr_segments :
info->shadow[i].req.u.rw.nr_segments;
for (j = 0; j < segs; j++) {
persistent_gnt = info->shadow[i].grants_used[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
if (info->feature_persistent)
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}
if (info->shadow[i].req.operation != BLKIF_OP_INDIRECT)
/*
* If this is not an indirect operation don't try to
* free indirect segments
*/
goto free_shadow;
for (j = 0; j < INDIRECT_GREFS(segs); j++) {
persistent_gnt = info->shadow[i].indirect_grants[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}
free_shadow:
kfree(info->shadow[i].grants_used);
info->shadow[i].grants_used = NULL;
kfree(info->shadow[i].indirect_grants);
info->shadow[i].indirect_grants = NULL;
kfree(info->shadow[i].sg);
info->shadow[i].sg = NULL;