forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
dev.c
2266 lines (1920 loc) · 51.1 KB
/
dev.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
/*
FUSE: Filesystem in Userspace
Copyright (C) 2001-2008 Miklos Szeredi <[email protected]>
This program can be distributed under the terms of the GNU GPL.
See the file COPYING.
*/
#include "fuse_i.h"
#include <linux/init.h>
#include <linux/module.h>
#include <linux/poll.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/pipe_fs_i.h>
#include <linux/swap.h>
#include <linux/splice.h>
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
static struct kmem_cache *fuse_req_cachep;
static struct fuse_dev *fuse_get_dev(struct file *file)
{
/*
* Lockless access is OK, because file->private data is set
* once during mount and is valid until the file is released.
*/
return ACCESS_ONCE(file->private_data);
}
static void fuse_request_init(struct fuse_req *req, struct page **pages,
struct fuse_page_desc *page_descs,
unsigned npages)
{
memset(req, 0, sizeof(*req));
memset(pages, 0, sizeof(*pages) * npages);
memset(page_descs, 0, sizeof(*page_descs) * npages);
INIT_LIST_HEAD(&req->list);
INIT_LIST_HEAD(&req->intr_entry);
init_waitqueue_head(&req->waitq);
atomic_set(&req->count, 1);
req->pages = pages;
req->page_descs = page_descs;
req->max_pages = npages;
__set_bit(FR_PENDING, &req->flags);
}
static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
{
struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, flags);
if (req) {
struct page **pages;
struct fuse_page_desc *page_descs;
if (npages <= FUSE_REQ_INLINE_PAGES) {
pages = req->inline_pages;
page_descs = req->inline_page_descs;
} else {
pages = kmalloc(sizeof(struct page *) * npages, flags);
page_descs = kmalloc(sizeof(struct fuse_page_desc) *
npages, flags);
}
if (!pages || !page_descs) {
kfree(pages);
kfree(page_descs);
kmem_cache_free(fuse_req_cachep, req);
return NULL;
}
fuse_request_init(req, pages, page_descs, npages);
}
return req;
}
struct fuse_req *fuse_request_alloc(unsigned npages)
{
return __fuse_request_alloc(npages, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(fuse_request_alloc);
struct fuse_req *fuse_request_alloc_nofs(unsigned npages)
{
return __fuse_request_alloc(npages, GFP_NOFS);
}
void fuse_request_free(struct fuse_req *req)
{
if (req->pages != req->inline_pages) {
kfree(req->pages);
kfree(req->page_descs);
}
kmem_cache_free(fuse_req_cachep, req);
}
void __fuse_get_request(struct fuse_req *req)
{
atomic_inc(&req->count);
}
/* Must be called with > 1 refcount */
static void __fuse_put_request(struct fuse_req *req)
{
BUG_ON(atomic_read(&req->count) < 2);
atomic_dec(&req->count);
}
static void fuse_req_init_context(struct fuse_req *req)
{
req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
req->in.h.pid = current->pid;
}
void fuse_set_initialized(struct fuse_conn *fc)
{
/* Make sure stores before this are seen on another CPU */
smp_wmb();
fc->initialized = 1;
}
static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
{
return !fc->initialized || (for_background && fc->blocked);
}
static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,
bool for_background)
{
struct fuse_req *req;
int err;
atomic_inc(&fc->num_waiting);
if (fuse_block_alloc(fc, for_background)) {
err = -EINTR;
if (wait_event_killable_exclusive(fc->blocked_waitq,
!fuse_block_alloc(fc, for_background)))
goto out;
}
/* Matches smp_wmb() in fuse_set_initialized() */
smp_rmb();
err = -ENOTCONN;
if (!fc->connected)
goto out;
err = -ECONNREFUSED;
if (fc->conn_error)
goto out;
req = fuse_request_alloc(npages);
err = -ENOMEM;
if (!req) {
if (for_background)
wake_up(&fc->blocked_waitq);
goto out;
}
fuse_req_init_context(req);
__set_bit(FR_WAITING, &req->flags);
if (for_background)
__set_bit(FR_BACKGROUND, &req->flags);
return req;
out:
atomic_dec(&fc->num_waiting);
return ERR_PTR(err);
}
struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
{
return __fuse_get_req(fc, npages, false);
}
EXPORT_SYMBOL_GPL(fuse_get_req);
struct fuse_req *fuse_get_req_for_background(struct fuse_conn *fc,
unsigned npages)
{
return __fuse_get_req(fc, npages, true);
}
EXPORT_SYMBOL_GPL(fuse_get_req_for_background);
/*
* Return request in fuse_file->reserved_req. However that may
* currently be in use. If that is the case, wait for it to become
* available.
*/
static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
struct file *file)
{
struct fuse_req *req = NULL;
struct fuse_file *ff = file->private_data;
do {
wait_event(fc->reserved_req_waitq, ff->reserved_req);
spin_lock(&fc->lock);
if (ff->reserved_req) {
req = ff->reserved_req;
ff->reserved_req = NULL;
req->stolen_file = get_file(file);
}
spin_unlock(&fc->lock);
} while (!req);
return req;
}
/*
* Put stolen request back into fuse_file->reserved_req
*/
static void put_reserved_req(struct fuse_conn *fc, struct fuse_req *req)
{
struct file *file = req->stolen_file;
struct fuse_file *ff = file->private_data;
spin_lock(&fc->lock);
fuse_request_init(req, req->pages, req->page_descs, req->max_pages);
BUG_ON(ff->reserved_req);
ff->reserved_req = req;
wake_up_all(&fc->reserved_req_waitq);
spin_unlock(&fc->lock);
fput(file);
}
/*
* Gets a requests for a file operation, always succeeds
*
* This is used for sending the FLUSH request, which must get to
* userspace, due to POSIX locks which may need to be unlocked.
*
* If allocation fails due to OOM, use the reserved request in
* fuse_file.
*
* This is very unlikely to deadlock accidentally, since the
* filesystem should not have it's own file open. If deadlock is
* intentional, it can still be broken by "aborting" the filesystem.
*/
struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
struct file *file)
{
struct fuse_req *req;
atomic_inc(&fc->num_waiting);
wait_event(fc->blocked_waitq, fc->initialized);
/* Matches smp_wmb() in fuse_set_initialized() */
smp_rmb();
req = fuse_request_alloc(0);
if (!req)
req = get_reserved_req(fc, file);
fuse_req_init_context(req);
__set_bit(FR_WAITING, &req->flags);
__clear_bit(FR_BACKGROUND, &req->flags);
return req;
}
void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
if (atomic_dec_and_test(&req->count)) {
if (test_bit(FR_BACKGROUND, &req->flags)) {
/*
* We get here in the unlikely case that a background
* request was allocated but not sent
*/
spin_lock(&fc->lock);
if (!fc->blocked)
wake_up(&fc->blocked_waitq);
spin_unlock(&fc->lock);
}
if (test_bit(FR_WAITING, &req->flags)) {
__clear_bit(FR_WAITING, &req->flags);
atomic_dec(&fc->num_waiting);
}
if (req->stolen_file)
put_reserved_req(fc, req);
else
fuse_request_free(req);
}
}
EXPORT_SYMBOL_GPL(fuse_put_request);
static unsigned len_args(unsigned numargs, struct fuse_arg *args)
{
unsigned nbytes = 0;
unsigned i;
for (i = 0; i < numargs; i++)
nbytes += args[i].size;
return nbytes;
}
static u64 fuse_get_unique(struct fuse_iqueue *fiq)
{
return ++fiq->reqctr;
}
static void queue_request(struct fuse_iqueue *fiq, struct fuse_req *req)
{
req->in.h.len = sizeof(struct fuse_in_header) +
len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
list_add_tail(&req->list, &fiq->pending);
wake_up_locked(&fiq->waitq);
kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
}
void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
u64 nodeid, u64 nlookup)
{
struct fuse_iqueue *fiq = &fc->iq;
forget->forget_one.nodeid = nodeid;
forget->forget_one.nlookup = nlookup;
spin_lock(&fiq->waitq.lock);
if (fiq->connected) {
fiq->forget_list_tail->next = forget;
fiq->forget_list_tail = forget;
wake_up_locked(&fiq->waitq);
kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
} else {
kfree(forget);
}
spin_unlock(&fiq->waitq.lock);
}
static void flush_bg_queue(struct fuse_conn *fc)
{
while (fc->active_background < fc->max_background &&
!list_empty(&fc->bg_queue)) {
struct fuse_req *req;
struct fuse_iqueue *fiq = &fc->iq;
req = list_entry(fc->bg_queue.next, struct fuse_req, list);
list_del(&req->list);
fc->active_background++;
spin_lock(&fiq->waitq.lock);
req->in.h.unique = fuse_get_unique(fiq);
queue_request(fiq, req);
spin_unlock(&fiq->waitq.lock);
}
}
/*
* This function is called when a request is finished. Either a reply
* has arrived or it was aborted (and not yet sent) or some error
* occurred during communication with userspace, or the device file
* was closed. The requester thread is woken up (if still waiting),
* the 'end' callback is called if given, else the reference to the
* request is released
*/
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_iqueue *fiq = &fc->iq;
if (test_and_set_bit(FR_FINISHED, &req->flags))
return;
spin_lock(&fiq->waitq.lock);
list_del_init(&req->intr_entry);
spin_unlock(&fiq->waitq.lock);
WARN_ON(test_bit(FR_PENDING, &req->flags));
WARN_ON(test_bit(FR_SENT, &req->flags));
if (test_bit(FR_BACKGROUND, &req->flags)) {
spin_lock(&fc->lock);
clear_bit(FR_BACKGROUND, &req->flags);
if (fc->num_background == fc->max_background)
fc->blocked = 0;
/* Wake up next waiter, if any */
if (!fc->blocked && waitqueue_active(&fc->blocked_waitq))
wake_up(&fc->blocked_waitq);
if (fc->num_background == fc->congestion_threshold &&
fc->connected && fc->bdi_initialized) {
clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
}
fc->num_background--;
fc->active_background--;
flush_bg_queue(fc);
spin_unlock(&fc->lock);
}
wake_up(&req->waitq);
if (req->end)
req->end(fc, req);
fuse_put_request(fc, req);
}
static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
{
spin_lock(&fiq->waitq.lock);
if (test_bit(FR_FINISHED, &req->flags)) {
spin_unlock(&fiq->waitq.lock);
return;
}
if (list_empty(&req->intr_entry)) {
list_add_tail(&req->intr_entry, &fiq->interrupts);
wake_up_locked(&fiq->waitq);
}
spin_unlock(&fiq->waitq.lock);
kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
}
static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_iqueue *fiq = &fc->iq;
int err;
if (!fc->no_interrupt) {
/* Any signal may interrupt this */
err = wait_event_interruptible(req->waitq,
test_bit(FR_FINISHED, &req->flags));
if (!err)
return;
set_bit(FR_INTERRUPTED, &req->flags);
/* matches barrier in fuse_dev_do_read() */
smp_mb__after_atomic();
if (test_bit(FR_SENT, &req->flags))
queue_interrupt(fiq, req);
}
if (!test_bit(FR_FORCE, &req->flags)) {
/* Only fatal signals may interrupt this */
err = wait_event_killable(req->waitq,
test_bit(FR_FINISHED, &req->flags));
if (!err)
return;
spin_lock(&fiq->waitq.lock);
/* Request is not yet in userspace, bail out */
if (test_bit(FR_PENDING, &req->flags)) {
list_del(&req->list);
spin_unlock(&fiq->waitq.lock);
__fuse_put_request(req);
req->out.h.error = -EINTR;
return;
}
spin_unlock(&fiq->waitq.lock);
}
/*
* Either request is already in userspace, or it was forced.
* Wait it out.
*/
wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags));
}
static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_iqueue *fiq = &fc->iq;
BUG_ON(test_bit(FR_BACKGROUND, &req->flags));
spin_lock(&fiq->waitq.lock);
if (!fiq->connected) {
spin_unlock(&fiq->waitq.lock);
req->out.h.error = -ENOTCONN;
} else {
req->in.h.unique = fuse_get_unique(fiq);
queue_request(fiq, req);
/* acquire extra reference, since request is still needed
after request_end() */
__fuse_get_request(req);
spin_unlock(&fiq->waitq.lock);
request_wait_answer(fc, req);
/* Pairs with smp_wmb() in request_end() */
smp_rmb();
}
}
void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
__set_bit(FR_ISREPLY, &req->flags);
if (!test_bit(FR_WAITING, &req->flags)) {
__set_bit(FR_WAITING, &req->flags);
atomic_inc(&fc->num_waiting);
}
__fuse_request_send(fc, req);
}
EXPORT_SYMBOL_GPL(fuse_request_send);
static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args)
{
if (fc->minor < 4 && args->in.h.opcode == FUSE_STATFS)
args->out.args[0].size = FUSE_COMPAT_STATFS_SIZE;
if (fc->minor < 9) {
switch (args->in.h.opcode) {
case FUSE_LOOKUP:
case FUSE_CREATE:
case FUSE_MKNOD:
case FUSE_MKDIR:
case FUSE_SYMLINK:
case FUSE_LINK:
args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
break;
case FUSE_GETATTR:
case FUSE_SETATTR:
args->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
break;
}
}
if (fc->minor < 12) {
switch (args->in.h.opcode) {
case FUSE_CREATE:
args->in.args[0].size = sizeof(struct fuse_open_in);
break;
case FUSE_MKNOD:
args->in.args[0].size = FUSE_COMPAT_MKNOD_IN_SIZE;
break;
}
}
}
ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
{
struct fuse_req *req;
ssize_t ret;
req = fuse_get_req(fc, 0);
if (IS_ERR(req))
return PTR_ERR(req);
/* Needs to be done after fuse_get_req() so that fc->minor is valid */
fuse_adjust_compat(fc, args);
req->in.h.opcode = args->in.h.opcode;
req->in.h.nodeid = args->in.h.nodeid;
req->in.numargs = args->in.numargs;
memcpy(req->in.args, args->in.args,
args->in.numargs * sizeof(struct fuse_in_arg));
req->out.argvar = args->out.argvar;
req->out.numargs = args->out.numargs;
memcpy(req->out.args, args->out.args,
args->out.numargs * sizeof(struct fuse_arg));
fuse_request_send(fc, req);
ret = req->out.h.error;
if (!ret && args->out.argvar) {
BUG_ON(args->out.numargs != 1);
ret = req->out.args[0].size;
}
fuse_put_request(fc, req);
return ret;
}
/*
* Called under fc->lock
*
* fc->connected must have been checked previously
*/
void fuse_request_send_background_locked(struct fuse_conn *fc,
struct fuse_req *req)
{
BUG_ON(!test_bit(FR_BACKGROUND, &req->flags));
if (!test_bit(FR_WAITING, &req->flags)) {
__set_bit(FR_WAITING, &req->flags);
atomic_inc(&fc->num_waiting);
}
__set_bit(FR_ISREPLY, &req->flags);
fc->num_background++;
if (fc->num_background == fc->max_background)
fc->blocked = 1;
if (fc->num_background == fc->congestion_threshold &&
fc->bdi_initialized) {
set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
}
list_add_tail(&req->list, &fc->bg_queue);
flush_bg_queue(fc);
}
void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
{
BUG_ON(!req->end);
spin_lock(&fc->lock);
if (fc->connected) {
fuse_request_send_background_locked(fc, req);
spin_unlock(&fc->lock);
} else {
spin_unlock(&fc->lock);
req->out.h.error = -ENOTCONN;
req->end(fc, req);
fuse_put_request(fc, req);
}
}
EXPORT_SYMBOL_GPL(fuse_request_send_background);
static int fuse_request_send_notify_reply(struct fuse_conn *fc,
struct fuse_req *req, u64 unique)
{
int err = -ENODEV;
struct fuse_iqueue *fiq = &fc->iq;
__clear_bit(FR_ISREPLY, &req->flags);
req->in.h.unique = unique;
spin_lock(&fiq->waitq.lock);
if (fiq->connected) {
queue_request(fiq, req);
err = 0;
}
spin_unlock(&fiq->waitq.lock);
return err;
}
void fuse_force_forget(struct file *file, u64 nodeid)
{
struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_forget_in inarg;
memset(&inarg, 0, sizeof(inarg));
inarg.nlookup = 1;
req = fuse_get_req_nofail_nopages(fc, file);
req->in.h.opcode = FUSE_FORGET;
req->in.h.nodeid = nodeid;
req->in.numargs = 1;
req->in.args[0].size = sizeof(inarg);
req->in.args[0].value = &inarg;
__clear_bit(FR_ISREPLY, &req->flags);
__fuse_request_send(fc, req);
/* ignore errors */
fuse_put_request(fc, req);
}
/*
* Lock the request. Up to the next unlock_request() there mustn't be
* anything that could cause a page-fault. If the request was already
* aborted bail out.
*/
static int lock_request(struct fuse_req *req)
{
int err = 0;
if (req) {
spin_lock(&req->waitq.lock);
if (test_bit(FR_ABORTED, &req->flags))
err = -ENOENT;
else
set_bit(FR_LOCKED, &req->flags);
spin_unlock(&req->waitq.lock);
}
return err;
}
/*
* Unlock request. If it was aborted while locked, caller is responsible
* for unlocking and ending the request.
*/
static int unlock_request(struct fuse_req *req)
{
int err = 0;
if (req) {
spin_lock(&req->waitq.lock);
if (test_bit(FR_ABORTED, &req->flags))
err = -ENOENT;
else
clear_bit(FR_LOCKED, &req->flags);
spin_unlock(&req->waitq.lock);
}
return err;
}
struct fuse_copy_state {
int write;
struct fuse_req *req;
struct iov_iter *iter;
struct pipe_buffer *pipebufs;
struct pipe_buffer *currbuf;
struct pipe_inode_info *pipe;
unsigned long nr_segs;
struct page *pg;
unsigned len;
unsigned offset;
unsigned move_pages:1;
};
static void fuse_copy_init(struct fuse_copy_state *cs, int write,
struct iov_iter *iter)
{
memset(cs, 0, sizeof(*cs));
cs->write = write;
cs->iter = iter;
}
/* Unmap and put previous page of userspace buffer */
static void fuse_copy_finish(struct fuse_copy_state *cs)
{
if (cs->currbuf) {
struct pipe_buffer *buf = cs->currbuf;
if (cs->write)
buf->len = PAGE_SIZE - cs->len;
cs->currbuf = NULL;
} else if (cs->pg) {
if (cs->write) {
flush_dcache_page(cs->pg);
set_page_dirty_lock(cs->pg);
}
put_page(cs->pg);
}
cs->pg = NULL;
}
/*
* Get another pagefull of userspace buffer, and map it to kernel
* address space, and lock request
*/
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
struct page *page;
int err;
err = unlock_request(cs->req);
if (err)
return err;
fuse_copy_finish(cs);
if (cs->pipebufs) {
struct pipe_buffer *buf = cs->pipebufs;
if (!cs->write) {
err = pipe_buf_confirm(cs->pipe, buf);
if (err)
return err;
BUG_ON(!cs->nr_segs);
cs->currbuf = buf;
cs->pg = buf->page;
cs->offset = buf->offset;
cs->len = buf->len;
cs->pipebufs++;
cs->nr_segs--;
} else {
if (cs->nr_segs == cs->pipe->buffers)
return -EIO;
page = alloc_page(GFP_HIGHUSER);
if (!page)
return -ENOMEM;
buf->page = page;
buf->offset = 0;
buf->len = 0;
cs->currbuf = buf;
cs->pg = page;
cs->offset = 0;
cs->len = PAGE_SIZE;
cs->pipebufs++;
cs->nr_segs++;
}
} else {
size_t off;
err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
if (err < 0)
return err;
BUG_ON(!err);
cs->len = err;
cs->offset = off;
cs->pg = page;
iov_iter_advance(cs->iter, err);
}
return lock_request(cs->req);
}
/* Do as much copy to/from userspace buffer as we can */
static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
unsigned ncpy = min(*size, cs->len);
if (val) {
void *pgaddr = kmap_atomic(cs->pg);
void *buf = pgaddr + cs->offset;
if (cs->write)
memcpy(buf, *val, ncpy);
else
memcpy(*val, buf, ncpy);
kunmap_atomic(pgaddr);
*val += ncpy;
}
*size -= ncpy;
cs->len -= ncpy;
cs->offset += ncpy;
return ncpy;
}
static int fuse_check_page(struct page *page)
{
if (page_mapcount(page) ||
page->mapping != NULL ||
page_count(page) != 1 ||
(page->flags & PAGE_FLAGS_CHECK_AT_PREP &
~(1 << PG_locked |
1 << PG_referenced |
1 << PG_uptodate |
1 << PG_lru |
1 << PG_active |
1 << PG_reclaim))) {
printk(KERN_WARNING "fuse: trying to steal weird page\n");
printk(KERN_WARNING " page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping);
return 1;
}
return 0;
}
static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
{
int err;
struct page *oldpage = *pagep;
struct page *newpage;
struct pipe_buffer *buf = cs->pipebufs;
err = unlock_request(cs->req);
if (err)
return err;
fuse_copy_finish(cs);
err = pipe_buf_confirm(cs->pipe, buf);
if (err)
return err;
BUG_ON(!cs->nr_segs);
cs->currbuf = buf;
cs->len = buf->len;
cs->pipebufs++;
cs->nr_segs--;
if (cs->len != PAGE_SIZE)
goto out_fallback;
if (pipe_buf_steal(cs->pipe, buf) != 0)
goto out_fallback;
newpage = buf->page;
if (!PageUptodate(newpage))
SetPageUptodate(newpage);
ClearPageMappedToDisk(newpage);
if (fuse_check_page(newpage) != 0)
goto out_fallback_unlock;
/*
* This is a new and locked page, it shouldn't be mapped or
* have any special flags on it
*/
if (WARN_ON(page_mapped(oldpage)))
goto out_fallback_unlock;
if (WARN_ON(page_has_private(oldpage)))
goto out_fallback_unlock;
if (WARN_ON(PageDirty(oldpage) || PageWriteback(oldpage)))
goto out_fallback_unlock;
if (WARN_ON(PageMlocked(oldpage)))
goto out_fallback_unlock;
err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL);
if (err) {
unlock_page(newpage);
return err;
}
get_page(newpage);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add_file(newpage);
err = 0;
spin_lock(&cs->req->waitq.lock);
if (test_bit(FR_ABORTED, &cs->req->flags))
err = -ENOENT;
else
*pagep = newpage;
spin_unlock(&cs->req->waitq.lock);
if (err) {
unlock_page(newpage);
put_page(newpage);
return err;
}
unlock_page(oldpage);
put_page(oldpage);
cs->len = 0;
return 0;
out_fallback_unlock:
unlock_page(newpage);
out_fallback:
cs->pg = buf->page;
cs->offset = buf->offset;
err = lock_request(cs->req);
if (err)
return err;
return 1;
}
static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
unsigned offset, unsigned count)
{
struct pipe_buffer *buf;
int err;
if (cs->nr_segs == cs->pipe->buffers)
return -EIO;
err = unlock_request(cs->req);
if (err)
return err;
fuse_copy_finish(cs);
buf = cs->pipebufs;
get_page(page);
buf->page = page;
buf->offset = offset;
buf->len = count;
cs->pipebufs++;
cs->nr_segs++;
cs->len = 0;
return 0;
}
/*
* Copy a page in the request to/from the userspace buffer. Must be
* done atomically
*/
static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
unsigned offset, unsigned count, int zeroing)
{
int err;
struct page *page = *pagep;
if (page && zeroing && count < PAGE_SIZE)
clear_highpage(page);
while (count) {
if (cs->write && cs->pipebufs && page) {
return fuse_ref_page(cs, page, offset, count);
} else if (!cs->len) {
if (cs->move_pages && page &&
offset == 0 && count == PAGE_SIZE) {
err = fuse_try_move_page(cs, pagep);
if (err <= 0)
return err;
} else {
err = fuse_copy_fill(cs);
if (err)
return err;
}
}
if (page) {
void *mapaddr = kmap_atomic(page);
void *buf = mapaddr + offset;
offset += fuse_copy_do(cs, &buf, &count);
kunmap_atomic(mapaddr);
} else
offset += fuse_copy_do(cs, NULL, &count);
}
if (page && !cs->write)
flush_dcache_page(page);
return 0;
}
/* Copy pages in the request to/from userspace buffer */
static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
int zeroing)
{
unsigned i;
struct fuse_req *req = cs->req;
for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) {
int err;
unsigned offset = req->page_descs[i].offset;
unsigned count = min(nbytes, req->page_descs[i].length);
err = fuse_copy_page(cs, &req->pages[i], offset, count,
zeroing);
if (err)