forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathloop.c
1695 lines (1451 loc) · 40.7 KB
/
loop.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
/*
* linux/drivers/block/loop.c
*
* Written by Theodore Ts'o, 3/29/93
*
* Copyright 1993 by Theodore Ts'o. Redistribution of this file is
* permitted under the GNU General Public License.
*
* DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993
* more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996
*
* Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994
* Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996
*
* Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997
*
* Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998
*
* Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998
*
* Loadable modules and other fixes by AK, 1998
*
* Make real block number available to downstream transfer functions, enables
* CBC (and relatives) mode encryption requiring unique IVs per data block.
* Reed H. Petty, rhp@draper.net
*
* Maximum number of loop devices now dynamic via max_loop module parameter.
* Russell Kroll <rkroll@exploits.org> 19990701
*
* Maximum number of loop devices when compiled-in now selectable by passing
* max_loop=<1-255> to the kernel on boot.
* Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999
*
* Completely rewrite request handling to be make_request_fn style and
* non blocking, pushing work to a helper thread. Lots of fixes from
* Al Viro too.
* Jens Axboe <axboe@suse.de>, Nov 2000
*
* Support up to 256 loop devices
* Heinz Mauelshagen <mge@sistina.com>, Feb 2002
*
* Support for falling back on the write file operation when the address space
* operations write_begin is not available on the backing filesystem.
* Anton Altaparmakov, 16 Feb 2005
*
* Still To Fix:
* - Advisory locking is ignored here.
* - Should use an own CAP_* category instead of CAP_SYS_ADMIN
*
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/loop.h>
#include <linux/compat.h>
#include <linux/suspend.h>
#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h> /* for invalidate_bdev() */
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/kthread.h>
#include <linux/splice.h>
#include <asm/uaccess.h>
static LIST_HEAD(loop_devices);
static DEFINE_MUTEX(loop_devices_mutex);
static int max_part;
static int part_shift;
/*
* Transfer functions
*/
static int transfer_none(struct loop_device *lo, int cmd,
struct page *raw_page, unsigned raw_off,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block)
{
char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
if (cmd == READ)
memcpy(loop_buf, raw_buf, size);
else
memcpy(raw_buf, loop_buf, size);
kunmap_atomic(raw_buf, KM_USER0);
kunmap_atomic(loop_buf, KM_USER1);
cond_resched();
return 0;
}
static int transfer_xor(struct loop_device *lo, int cmd,
struct page *raw_page, unsigned raw_off,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block)
{
char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
char *in, *out, *key;
int i, keysize;
if (cmd == READ) {
in = raw_buf;
out = loop_buf;
} else {
in = loop_buf;
out = raw_buf;
}
key = lo->lo_encrypt_key;
keysize = lo->lo_encrypt_key_size;
for (i = 0; i < size; i++)
*out++ = *in++ ^ key[(i & 511) % keysize];
kunmap_atomic(raw_buf, KM_USER0);
kunmap_atomic(loop_buf, KM_USER1);
cond_resched();
return 0;
}
static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
if (unlikely(info->lo_encrypt_key_size <= 0))
return -EINVAL;
return 0;
}
static struct loop_func_table none_funcs = {
.number = LO_CRYPT_NONE,
.transfer = transfer_none,
};
static struct loop_func_table xor_funcs = {
.number = LO_CRYPT_XOR,
.transfer = transfer_xor,
.init = xor_init
};
/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
&none_funcs,
&xor_funcs
};
static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
loff_t size, offset, loopsize;
/* Compute loopsize in bytes */
size = i_size_read(file->f_mapping->host);
offset = lo->lo_offset;
loopsize = size - offset;
if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
loopsize = lo->lo_sizelimit;
/*
* Unfortunately, if we want to do I/O on the device,
* the number of 512-byte sectors has to fit into a sector_t.
*/
return loopsize >> 9;
}
static int
figure_loop_size(struct loop_device *lo)
{
loff_t size = get_loop_size(lo, lo->lo_backing_file);
sector_t x = (sector_t)size;
if (unlikely((loff_t)x != size))
return -EFBIG;
set_capacity(lo->lo_disk, x);
return 0;
}
static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
struct page *rpage, unsigned roffs,
struct page *lpage, unsigned loffs,
int size, sector_t rblock)
{
if (unlikely(!lo->transfer))
return 0;
return lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
}
/**
* do_lo_send_aops - helper for writing data to a loop device
*
* This is the fast version for backing filesystems which implement the address
* space operations write_begin and write_end.
*/
static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
loff_t pos, struct page *unused)
{
struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
struct address_space *mapping = file->f_mapping;
pgoff_t index;
unsigned offset, bv_offs;
int len, ret;
mutex_lock(&mapping->host->i_mutex);
index = pos >> PAGE_CACHE_SHIFT;
offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
bv_offs = bvec->bv_offset;
len = bvec->bv_len;
while (len > 0) {
sector_t IV;
unsigned size, copied;
int transfer_result;
struct page *page;
void *fsdata;
IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
size = PAGE_CACHE_SIZE - offset;
if (size > len)
size = len;
ret = pagecache_write_begin(file, mapping, pos, size, 0,
&page, &fsdata);
if (ret)
goto fail;
transfer_result = lo_do_transfer(lo, WRITE, page, offset,
bvec->bv_page, bv_offs, size, IV);
copied = size;
if (unlikely(transfer_result))
copied = 0;
ret = pagecache_write_end(file, mapping, pos, size, copied,
page, fsdata);
if (ret < 0 || ret != copied)
goto fail;
if (unlikely(transfer_result))
goto fail;
bv_offs += copied;
len -= copied;
offset = 0;
index++;
pos += copied;
}
ret = 0;
out:
mutex_unlock(&mapping->host->i_mutex);
return ret;
fail:
ret = -1;
goto out;
}
/**
* __do_lo_send_write - helper for writing data to a loop device
*
* This helper just factors out common code between do_lo_send_direct_write()
* and do_lo_send_write().
*/
static int __do_lo_send_write(struct file *file,
u8 *buf, const int len, loff_t pos)
{
ssize_t bw;
mm_segment_t old_fs = get_fs();
set_fs(get_ds());
bw = file->f_op->write(file, buf, len, &pos);
set_fs(old_fs);
if (likely(bw == len))
return 0;
printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
(unsigned long long)pos, len);
if (bw >= 0)
bw = -EIO;
return bw;
}
/**
* do_lo_send_direct_write - helper for writing data to a loop device
*
* This is the fast, non-transforming version for backing filesystems which do
* not implement the address space operations write_begin and write_end.
* It uses the write file operation which should be present on all writeable
* filesystems.
*/
static int do_lo_send_direct_write(struct loop_device *lo,
struct bio_vec *bvec, loff_t pos, struct page *page)
{
ssize_t bw = __do_lo_send_write(lo->lo_backing_file,
kmap(bvec->bv_page) + bvec->bv_offset,
bvec->bv_len, pos);
kunmap(bvec->bv_page);
cond_resched();
return bw;
}
/**
* do_lo_send_write - helper for writing data to a loop device
*
* This is the slow, transforming version for filesystems which do not
* implement the address space operations write_begin and write_end. It
* uses the write file operation which should be present on all writeable
* filesystems.
*
* Using fops->write is slower than using aops->{prepare,commit}_write in the
* transforming case because we need to double buffer the data as we cannot do
* the transformations in place as we do not have direct access to the
* destination pages of the backing file.
*/
static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
loff_t pos, struct page *page)
{
int ret = lo_do_transfer(lo, WRITE, page, 0, bvec->bv_page,
bvec->bv_offset, bvec->bv_len, pos >> 9);
if (likely(!ret))
return __do_lo_send_write(lo->lo_backing_file,
page_address(page), bvec->bv_len,
pos);
printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
"length %i.\n", (unsigned long long)pos, bvec->bv_len);
if (ret > 0)
ret = -EIO;
return ret;
}
static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
{
int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
struct page *page);
struct bio_vec *bvec;
struct page *page = NULL;
int i, ret = 0;
do_lo_send = do_lo_send_aops;
if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
do_lo_send = do_lo_send_direct_write;
if (lo->transfer != transfer_none) {
page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
if (unlikely(!page))
goto fail;
kmap(page);
do_lo_send = do_lo_send_write;
}
}
bio_for_each_segment(bvec, bio, i) {
ret = do_lo_send(lo, bvec, pos, page);
if (ret < 0)
break;
pos += bvec->bv_len;
}
if (page) {
kunmap(page);
__free_page(page);
}
out:
return ret;
fail:
printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
ret = -ENOMEM;
goto out;
}
struct lo_read_data {
struct loop_device *lo;
struct page *page;
unsigned offset;
int bsize;
};
static int
lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct lo_read_data *p = sd->u.data;
struct loop_device *lo = p->lo;
struct page *page = buf->page;
sector_t IV;
int size, ret;
ret = buf->ops->confirm(pipe, buf);
if (unlikely(ret))
return ret;
IV = ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9)) +
(buf->offset >> 9);
size = sd->len;
if (size > p->bsize)
size = p->bsize;
if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
printk(KERN_ERR "loop: transfer error block %ld\n",
page->index);
size = -EINVAL;
}
flush_dcache_page(p->page);
if (size > 0)
p->offset += size;
return size;
}
static int
lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
return __splice_from_pipe(pipe, sd, lo_splice_actor);
}
static int
do_lo_receive(struct loop_device *lo,
struct bio_vec *bvec, int bsize, loff_t pos)
{
struct lo_read_data cookie;
struct splice_desc sd;
struct file *file;
long retval;
cookie.lo = lo;
cookie.page = bvec->bv_page;
cookie.offset = bvec->bv_offset;
cookie.bsize = bsize;
sd.len = 0;
sd.total_len = bvec->bv_len;
sd.flags = 0;
sd.pos = pos;
sd.u.data = &cookie;
file = lo->lo_backing_file;
retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor);
if (retval < 0)
return retval;
return 0;
}
static int
lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
{
struct bio_vec *bvec;
int i, ret = 0;
bio_for_each_segment(bvec, bio, i) {
ret = do_lo_receive(lo, bvec, bsize, pos);
if (ret < 0)
break;
pos += bvec->bv_len;
}
return ret;
}
static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
{
loff_t pos;
int ret;
pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
if (bio_rw(bio) == WRITE) {
int barrier = bio_barrier(bio);
struct file *file = lo->lo_backing_file;
if (barrier) {
if (unlikely(!file->f_op->fsync)) {
ret = -EOPNOTSUPP;
goto out;
}
ret = vfs_fsync(file, file->f_path.dentry, 0);
if (unlikely(ret)) {
ret = -EIO;
goto out;
}
}
ret = lo_send(lo, bio, pos);
if (barrier && !ret) {
ret = vfs_fsync(file, file->f_path.dentry, 0);
if (unlikely(ret))
ret = -EIO;
}
} else
ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
out:
return ret;
}
/*
* Add bio to back of pending list
*/
static void loop_add_bio(struct loop_device *lo, struct bio *bio)
{
if (lo->lo_biotail) {
lo->lo_biotail->bi_next = bio;
lo->lo_biotail = bio;
} else
lo->lo_bio = lo->lo_biotail = bio;
}
/*
* Grab first pending buffer
*/
static struct bio *loop_get_bio(struct loop_device *lo)
{
struct bio *bio;
if ((bio = lo->lo_bio)) {
if (bio == lo->lo_biotail)
lo->lo_biotail = NULL;
lo->lo_bio = bio->bi_next;
bio->bi_next = NULL;
}
return bio;
}
static int loop_make_request(struct request_queue *q, struct bio *old_bio)
{
struct loop_device *lo = q->queuedata;
int rw = bio_rw(old_bio);
if (rw == READA)
rw = READ;
BUG_ON(!lo || (rw != READ && rw != WRITE));
spin_lock_irq(&lo->lo_lock);
if (lo->lo_state != Lo_bound)
goto out;
if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
goto out;
loop_add_bio(lo, old_bio);
wake_up(&lo->lo_event);
spin_unlock_irq(&lo->lo_lock);
return 0;
out:
spin_unlock_irq(&lo->lo_lock);
bio_io_error(old_bio);
return 0;
}
/*
* kick off io on the underlying address space
*/
static void loop_unplug(struct request_queue *q)
{
struct loop_device *lo = q->queuedata;
queue_flag_clear_unlocked(QUEUE_FLAG_PLUGGED, q);
blk_run_address_space(lo->lo_backing_file->f_mapping);
}
struct switch_request {
struct file *file;
struct completion wait;
};
static void do_loop_switch(struct loop_device *, struct switch_request *);
static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio)
{
if (unlikely(!bio->bi_bdev)) {
do_loop_switch(lo, bio->bi_private);
bio_put(bio);
} else {
int ret = do_bio_filebacked(lo, bio);
bio_endio(bio, ret);
}
}
/*
* worker thread that handles reads/writes to file backed loop devices,
* to avoid blocking in our make_request_fn. it also does loop decrypting
* on reads for block backed loop, as that is too heavy to do from
* b_end_io context where irqs may be disabled.
*
* Loop explanation: loop_clr_fd() sets lo_state to Lo_rundown before
* calling kthread_stop(). Therefore once kthread_should_stop() is
* true, make_request will not place any more requests. Therefore
* once kthread_should_stop() is true and lo_bio is NULL, we are
* done with the loop.
*/
static int loop_thread(void *data)
{
struct loop_device *lo = data;
struct bio *bio;
set_user_nice(current, -20);
while (!kthread_should_stop() || lo->lo_bio) {
wait_event_interruptible(lo->lo_event,
lo->lo_bio || kthread_should_stop());
if (!lo->lo_bio)
continue;
spin_lock_irq(&lo->lo_lock);
bio = loop_get_bio(lo);
spin_unlock_irq(&lo->lo_lock);
BUG_ON(!bio);
loop_handle_bio(lo, bio);
}
return 0;
}
/*
* loop_switch performs the hard work of switching a backing store.
* First it needs to flush existing IO, it does this by sending a magic
* BIO down the pipe. The completion of this BIO does the actual switch.
*/
static int loop_switch(struct loop_device *lo, struct file *file)
{
struct switch_request w;
struct bio *bio = bio_alloc(GFP_KERNEL, 0);
if (!bio)
return -ENOMEM;
init_completion(&w.wait);
w.file = file;
bio->bi_private = &w;
bio->bi_bdev = NULL;
loop_make_request(lo->lo_queue, bio);
wait_for_completion(&w.wait);
return 0;
}
/*
* Helper to flush the IOs in loop, but keeping loop thread running
*/
static int loop_flush(struct loop_device *lo)
{
/* loop not yet configured, no running thread, nothing to flush */
if (!lo->lo_thread)
return 0;
return loop_switch(lo, NULL);
}
/*
* Do the actual switch; called from the BIO completion routine
*/
static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
{
struct file *file = p->file;
struct file *old_file = lo->lo_backing_file;
struct address_space *mapping;
/* if no new file, only flush of queued bios requested */
if (!file)
goto out;
mapping = file->f_mapping;
mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
lo->lo_backing_file = file;
lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
lo->old_gfp_mask = mapping_gfp_mask(mapping);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
out:
complete(&p->wait);
}
/*
* loop_change_fd switched the backing store of a loopback device to
* a new file. This is useful for operating system installers to free up
* the original file and in High Availability environments to switch to
* an alternative location for the content in case of server meltdown.
* This can only work if the loop device is used read-only, and if the
* new backing store is the same size and type as the old backing store.
*/
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
unsigned int arg)
{
struct file *file, *old_file;
struct inode *inode;
int error;
error = -ENXIO;
if (lo->lo_state != Lo_bound)
goto out;
/* the loop device has to be read-only */
error = -EINVAL;
if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
goto out;
error = -EBADF;
file = fget(arg);
if (!file)
goto out;
inode = file->f_mapping->host;
old_file = lo->lo_backing_file;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
goto out_putf;
/* new backing store needs to support loop (eg splice_read) */
if (!inode->i_fop->splice_read)
goto out_putf;
/* size of the new backing store needs to be the same */
if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
goto out_putf;
/* and ... switch */
error = loop_switch(lo, file);
if (error)
goto out_putf;
fput(old_file);
if (max_part > 0)
ioctl_by_bdev(bdev, BLKRRPART, 0);
return 0;
out_putf:
fput(file);
out:
return error;
}
static inline int is_loop_device(struct file *file)
{
struct inode *i = file->f_mapping->host;
return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
}
static int loop_set_fd(struct loop_device *lo, fmode_t mode,
struct block_device *bdev, unsigned int arg)
{
struct file *file, *f;
struct inode *inode;
struct address_space *mapping;
unsigned lo_blocksize;
int lo_flags = 0;
int error;
loff_t size;
/* This is safe, since we have a reference from open(). */
__module_get(THIS_MODULE);
error = -EBADF;
file = fget(arg);
if (!file)
goto out;
error = -EBUSY;
if (lo->lo_state != Lo_unbound)
goto out_putf;
/* Avoid recursion */
f = file;
while (is_loop_device(f)) {
struct loop_device *l;
if (f->f_mapping->host->i_bdev == bdev)
goto out_putf;
l = f->f_mapping->host->i_bdev->bd_disk->private_data;
if (l->lo_state == Lo_unbound) {
error = -EINVAL;
goto out_putf;
}
f = l->lo_backing_file;
}
mapping = file->f_mapping;
inode = mapping->host;
if (!(file->f_mode & FMODE_WRITE))
lo_flags |= LO_FLAGS_READ_ONLY;
error = -EINVAL;
if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
const struct address_space_operations *aops = mapping->a_ops;
/*
* If we can't read - sorry. If we only can't write - well,
* it's going to be read-only.
*/
if (!file->f_op->splice_read)
goto out_putf;
if (aops->write_begin)
lo_flags |= LO_FLAGS_USE_AOPS;
if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
lo_flags |= LO_FLAGS_READ_ONLY;
lo_blocksize = S_ISBLK(inode->i_mode) ?
inode->i_bdev->bd_block_size : PAGE_SIZE;
error = 0;
} else {
goto out_putf;
}
size = get_loop_size(lo, file);
if ((loff_t)(sector_t)size != size) {
error = -EFBIG;
goto out_putf;
}
if (!(mode & FMODE_WRITE))
lo_flags |= LO_FLAGS_READ_ONLY;
set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
lo->lo_blocksize = lo_blocksize;
lo->lo_device = bdev;
lo->lo_flags = lo_flags;
lo->lo_backing_file = file;
lo->transfer = transfer_none;
lo->ioctl = NULL;
lo->lo_sizelimit = 0;
lo->old_gfp_mask = mapping_gfp_mask(mapping);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
lo->lo_bio = lo->lo_biotail = NULL;
/*
* set queue make_request_fn, and add limits based on lower level
* device
*/
blk_queue_make_request(lo->lo_queue, loop_make_request);
lo->lo_queue->queuedata = lo;
lo->lo_queue->unplug_fn = loop_unplug;
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN, NULL);
set_capacity(lo->lo_disk, size);
bd_set_size(bdev, size << 9);
set_blocksize(bdev, lo_blocksize);
lo->lo_thread = kthread_create(loop_thread, lo, "loop%d",
lo->lo_number);
if (IS_ERR(lo->lo_thread)) {
error = PTR_ERR(lo->lo_thread);
goto out_clr;
}
lo->lo_state = Lo_bound;
wake_up_process(lo->lo_thread);
if (max_part > 0)
ioctl_by_bdev(bdev, BLKRRPART, 0);
return 0;
out_clr:
lo->lo_thread = NULL;
lo->lo_device = NULL;
lo->lo_backing_file = NULL;
lo->lo_flags = 0;
set_capacity(lo->lo_disk, 0);
invalidate_bdev(bdev);
bd_set_size(bdev, 0);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
lo->lo_state = Lo_unbound;
out_putf:
fput(file);
out:
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
return error;
}
static int
loop_release_xfer(struct loop_device *lo)
{
int err = 0;
struct loop_func_table *xfer = lo->lo_encryption;
if (xfer) {
if (xfer->release)
err = xfer->release(lo);
lo->transfer = NULL;
lo->lo_encryption = NULL;
module_put(xfer->owner);
}
return err;
}
static int
loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
const struct loop_info64 *i)
{
int err = 0;
if (xfer) {
struct module *owner = xfer->owner;
if (!try_module_get(owner))
return -EINVAL;
if (xfer->init)
err = xfer->init(lo, i);
if (err)
module_put(owner);
else
lo->lo_encryption = xfer;
}
return err;
}
static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
{
struct file *filp = lo->lo_backing_file;
gfp_t gfp = lo->old_gfp_mask;
if (lo->lo_state != Lo_bound)
return -ENXIO;
if (lo->lo_refcnt > 1) /* we needed one fd for the ioctl */
return -EBUSY;
if (filp == NULL)
return -EINVAL;
spin_lock_irq(&lo->lo_lock);
lo->lo_state = Lo_rundown;
spin_unlock_irq(&lo->lo_lock);
kthread_stop(lo->lo_thread);
lo->lo_queue->unplug_fn = NULL;
lo->lo_backing_file = NULL;
loop_release_xfer(lo);
lo->transfer = NULL;
lo->ioctl = NULL;
lo->lo_device = NULL;
lo->lo_encryption = NULL;
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
lo->lo_encrypt_key_size = 0;
lo->lo_flags = 0;
lo->lo_thread = NULL;
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
if (bdev)
invalidate_bdev(bdev);
set_capacity(lo->lo_disk, 0);
if (bdev)
bd_set_size(bdev, 0);
mapping_set_gfp_mask(filp->f_mapping, gfp);
lo->lo_state = Lo_unbound;
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
if (max_part > 0)
ioctl_by_bdev(bdev, BLKRRPART, 0);
mutex_unlock(&lo->lo_ctl_mutex);
/*
* Need not hold lo_ctl_mutex to fput backing file.
* Calling fput holding lo_ctl_mutex triggers a circular
* lock dependency possibility warning as fput can take
* bd_mutex which is usually taken before lo_ctl_mutex.
*/
fput(filp);
return 0;
}
static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
struct loop_func_table *xfer;
uid_t uid = current_uid();
if (lo->lo_encrypt_key_size &&
lo->lo_key_owner != uid &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (lo->lo_state != Lo_bound)
return -ENXIO;
if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)