forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlocks.c
2247 lines (2004 loc) · 55.1 KB
/
locks.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/fs/locks.c
*
* Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls.
* Doug Evans ([email protected]), August 07, 1992
*
* Deadlock detection added.
* FIXME: one thing isn't handled yet:
* - mandatory locks (requires lots of changes elsewhere)
* Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994.
*
* Miscellaneous edits, and a total rewrite of posix_lock_file() code.
* Kai Petzke ([email protected]), 1994
*
* Converted file_lock_table to a linked list from an array, which eliminates
* the limits on how many active file locks are open.
* Chad Page ([email protected]), November 27, 1994
*
* Removed dependency on file descriptors. dup()'ed file descriptors now
* get the same locks as the original file descriptors, and a close() on
* any file descriptor removes ALL the locks on the file for the current
* process. Since locks still depend on the process id, locks are inherited
* after an exec() but not after a fork(). This agrees with POSIX, and both
* BSD and SVR4 practice.
* Andy Walker ([email protected]), February 14, 1995
*
* Scrapped free list which is redundant now that we allocate locks
* dynamically with kmalloc()/kfree().
* Andy Walker ([email protected]), February 21, 1995
*
* Implemented two lock personalities - FL_FLOCK and FL_POSIX.
*
* FL_POSIX locks are created with calls to fcntl() and lockf() through the
* fcntl() system call. They have the semantics described above.
*
* FL_FLOCK locks are created with calls to flock(), through the flock()
* system call, which is new. Old C libraries implement flock() via fcntl()
* and will continue to use the old, broken implementation.
*
* FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated
* with a file pointer (filp). As a result they can be shared by a parent
* process and its children after a fork(). They are removed when the last
* file descriptor referring to the file pointer is closed (unless explicitly
* unlocked).
*
* FL_FLOCK locks never deadlock, an existing lock is always removed before
* upgrading from shared to exclusive (or vice versa). When this happens
* any processes blocked by the current lock are woken up and allowed to
* run before the new lock is applied.
* Andy Walker ([email protected]), June 09, 1995
*
* Removed some race conditions in flock_lock_file(), marked other possible
* races. Just grep for FIXME to see them.
* Dmitry Gorodchanin ([email protected]), February 09, 1996.
*
* Addressed Dmitry's concerns. Deadlock checking no longer recursive.
* Lock allocation changed to GFP_ATOMIC as we can't afford to sleep
* once we've checked for blocking and deadlocking.
* Andy Walker ([email protected]), April 03, 1996.
*
* Initial implementation of mandatory locks. SunOS turned out to be
* a rotten model, so I implemented the "obvious" semantics.
* See 'Documentation/mandatory.txt' for details.
* Andy Walker ([email protected]), April 06, 1996.
*
* Don't allow mandatory locks on mmap()'ed files. Added simple functions to
* check if a file has mandatory locks, used by mmap(), open() and creat() to
* see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference
* Manual, Section 2.
* Andy Walker ([email protected]), April 09, 1996.
*
* Tidied up block list handling. Added '/proc/locks' interface.
* Andy Walker ([email protected]), April 24, 1996.
*
* Fixed deadlock condition for pathological code that mixes calls to
* flock() and fcntl().
* Andy Walker ([email protected]), April 29, 1996.
*
* Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use
* for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to
* guarantee sensible behaviour in the case where file system modules might
* be compiled with different options than the kernel itself.
* Andy Walker ([email protected]), May 15, 1996.
*
* Added a couple of missing wake_up() calls. Thanks to Thomas Meckel
* ([email protected]) for spotting this.
* Andy Walker ([email protected]), May 15, 1996.
*
* Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK
* locks. Changed process synchronisation to avoid dereferencing locks that
* have already been freed.
* Andy Walker ([email protected]), Sep 21, 1996.
*
* Made the block list a circular list to minimise searching in the list.
* Andy Walker ([email protected]), Sep 25, 1996.
*
* Made mandatory locking a mount option. Default is not to allow mandatory
* locking.
* Andy Walker ([email protected]), Oct 04, 1996.
*
* Some adaptations for NFS support.
* Olaf Kirch ([email protected]), Dec 1996,
*
* Fixed /proc/locks interface so that we can't overrun the buffer we are handed.
* Andy Walker ([email protected]), May 12, 1997.
*
* Use slab allocator instead of kmalloc/kfree.
* Use generic list implementation from <linux/list.h>.
* Sped up posix_locks_deadlock by only considering blocked locks.
* Matthew Wilcox <[email protected]>, March, 2000.
*
* Leases and LOCK_MAND
* Matthew Wilcox <[email protected]>, June, 2000.
* Stephen Rothwell <[email protected]>, June, 2000.
*/
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/syscalls.h>
#include <linux/time.h>
#include <linux/rcupdate.h>
#include <asm/semaphore.h>
#include <asm/uaccess.h>
#define IS_POSIX(fl) (fl->fl_flags & FL_POSIX)
#define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK)
#define IS_LEASE(fl) (fl->fl_flags & FL_LEASE)
int leases_enable = 1;
int lease_break_time = 45;
#define for_each_lock(inode, lockp) \
for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)
LIST_HEAD(file_lock_list);
EXPORT_SYMBOL(file_lock_list);
static LIST_HEAD(blocked_list);
static kmem_cache_t *filelock_cache;
/* Allocate an empty lock structure. */
static struct file_lock *locks_alloc_lock(void)
{
return kmem_cache_alloc(filelock_cache, SLAB_KERNEL);
}
/* Free a lock which is not in use. */
static inline void locks_free_lock(struct file_lock *fl)
{
if (fl == NULL) {
BUG();
return;
}
if (waitqueue_active(&fl->fl_wait))
panic("Attempting to free lock with active wait queue");
if (!list_empty(&fl->fl_block))
panic("Attempting to free lock with active block list");
if (!list_empty(&fl->fl_link))
panic("Attempting to free lock on active lock list");
if (fl->fl_ops) {
if (fl->fl_ops->fl_release_private)
fl->fl_ops->fl_release_private(fl);
fl->fl_ops = NULL;
}
if (fl->fl_lmops) {
if (fl->fl_lmops->fl_release_private)
fl->fl_lmops->fl_release_private(fl);
fl->fl_lmops = NULL;
}
kmem_cache_free(filelock_cache, fl);
}
void locks_init_lock(struct file_lock *fl)
{
INIT_LIST_HEAD(&fl->fl_link);
INIT_LIST_HEAD(&fl->fl_block);
init_waitqueue_head(&fl->fl_wait);
fl->fl_next = NULL;
fl->fl_fasync = NULL;
fl->fl_owner = NULL;
fl->fl_pid = 0;
fl->fl_file = NULL;
fl->fl_flags = 0;
fl->fl_type = 0;
fl->fl_start = fl->fl_end = 0;
fl->fl_ops = NULL;
fl->fl_lmops = NULL;
}
EXPORT_SYMBOL(locks_init_lock);
/*
* Initialises the fields of the file lock which are invariant for
* free file_locks.
*/
static void init_once(void *foo, kmem_cache_t *cache, unsigned long flags)
{
struct file_lock *lock = (struct file_lock *) foo;
if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) !=
SLAB_CTOR_CONSTRUCTOR)
return;
locks_init_lock(lock);
}
/*
* Initialize a new lock from an existing file_lock structure.
*/
void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
new->fl_owner = fl->fl_owner;
new->fl_pid = fl->fl_pid;
new->fl_file = fl->fl_file;
new->fl_flags = fl->fl_flags;
new->fl_type = fl->fl_type;
new->fl_start = fl->fl_start;
new->fl_end = fl->fl_end;
new->fl_ops = fl->fl_ops;
new->fl_lmops = fl->fl_lmops;
if (fl->fl_ops && fl->fl_ops->fl_copy_lock)
fl->fl_ops->fl_copy_lock(new, fl);
if (fl->fl_lmops && fl->fl_lmops->fl_copy_lock)
fl->fl_lmops->fl_copy_lock(new, fl);
}
EXPORT_SYMBOL(locks_copy_lock);
static inline int flock_translate_cmd(int cmd) {
if (cmd & LOCK_MAND)
return cmd & (LOCK_MAND | LOCK_RW);
switch (cmd) {
case LOCK_SH:
return F_RDLCK;
case LOCK_EX:
return F_WRLCK;
case LOCK_UN:
return F_UNLCK;
}
return -EINVAL;
}
/* Fill in a file_lock structure with an appropriate FLOCK lock. */
static int flock_make_lock(struct file *filp, struct file_lock **lock,
unsigned int cmd)
{
struct file_lock *fl;
int type = flock_translate_cmd(cmd);
if (type < 0)
return type;
fl = locks_alloc_lock();
if (fl == NULL)
return -ENOMEM;
fl->fl_file = filp;
fl->fl_pid = current->tgid;
fl->fl_flags = FL_FLOCK;
fl->fl_type = type;
fl->fl_end = OFFSET_MAX;
*lock = fl;
return 0;
}
static int assign_type(struct file_lock *fl, int type)
{
switch (type) {
case F_RDLCK:
case F_WRLCK:
case F_UNLCK:
fl->fl_type = type;
break;
default:
return -EINVAL;
}
return 0;
}
/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
* style lock.
*/
static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
struct flock *l)
{
off_t start, end;
switch (l->l_whence) {
case 0: /*SEEK_SET*/
start = 0;
break;
case 1: /*SEEK_CUR*/
start = filp->f_pos;
break;
case 2: /*SEEK_END*/
start = i_size_read(filp->f_dentry->d_inode);
break;
default:
return -EINVAL;
}
/* POSIX-1996 leaves the case l->l_len < 0 undefined;
POSIX-2001 defines it. */
start += l->l_start;
if (start < 0)
return -EINVAL;
fl->fl_end = OFFSET_MAX;
if (l->l_len > 0) {
end = start + l->l_len - 1;
fl->fl_end = end;
} else if (l->l_len < 0) {
end = start - 1;
fl->fl_end = end;
start += l->l_len;
if (start < 0)
return -EINVAL;
}
fl->fl_start = start; /* we record the absolute position */
if (fl->fl_end < fl->fl_start)
return -EOVERFLOW;
fl->fl_owner = current->files;
fl->fl_pid = current->tgid;
fl->fl_file = filp;
fl->fl_flags = FL_POSIX;
fl->fl_ops = NULL;
fl->fl_lmops = NULL;
return assign_type(fl, l->l_type);
}
#if BITS_PER_LONG == 32
static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
struct flock64 *l)
{
loff_t start;
switch (l->l_whence) {
case 0: /*SEEK_SET*/
start = 0;
break;
case 1: /*SEEK_CUR*/
start = filp->f_pos;
break;
case 2: /*SEEK_END*/
start = i_size_read(filp->f_dentry->d_inode);
break;
default:
return -EINVAL;
}
start += l->l_start;
if (start < 0)
return -EINVAL;
fl->fl_end = OFFSET_MAX;
if (l->l_len > 0) {
fl->fl_end = start + l->l_len - 1;
} else if (l->l_len < 0) {
fl->fl_end = start - 1;
start += l->l_len;
if (start < 0)
return -EINVAL;
}
fl->fl_start = start; /* we record the absolute position */
if (fl->fl_end < fl->fl_start)
return -EOVERFLOW;
fl->fl_owner = current->files;
fl->fl_pid = current->tgid;
fl->fl_file = filp;
fl->fl_flags = FL_POSIX;
fl->fl_ops = NULL;
fl->fl_lmops = NULL;
switch (l->l_type) {
case F_RDLCK:
case F_WRLCK:
case F_UNLCK:
fl->fl_type = l->l_type;
break;
default:
return -EINVAL;
}
return (0);
}
#endif
/* default lease lock manager operations */
static void lease_break_callback(struct file_lock *fl)
{
kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
}
static void lease_release_private_callback(struct file_lock *fl)
{
if (!fl->fl_file)
return;
f_delown(fl->fl_file);
fl->fl_file->f_owner.signum = 0;
}
static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try)
{
return fl->fl_file == try->fl_file;
}
static struct lock_manager_operations lease_manager_ops = {
.fl_break = lease_break_callback,
.fl_release_private = lease_release_private_callback,
.fl_mylease = lease_mylease_callback,
.fl_change = lease_modify,
};
/*
* Initialize a lease, use the default lock manager operations
*/
static int lease_init(struct file *filp, int type, struct file_lock *fl)
{
fl->fl_owner = current->files;
fl->fl_pid = current->tgid;
fl->fl_file = filp;
fl->fl_flags = FL_LEASE;
if (assign_type(fl, type) != 0) {
locks_free_lock(fl);
return -EINVAL;
}
fl->fl_start = 0;
fl->fl_end = OFFSET_MAX;
fl->fl_ops = NULL;
fl->fl_lmops = &lease_manager_ops;
return 0;
}
/* Allocate a file_lock initialised to this type of lease */
static int lease_alloc(struct file *filp, int type, struct file_lock **flp)
{
struct file_lock *fl = locks_alloc_lock();
int error;
if (fl == NULL)
return -ENOMEM;
error = lease_init(filp, type, fl);
if (error)
return error;
*flp = fl;
return 0;
}
/* Check if two locks overlap each other.
*/
static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
{
return ((fl1->fl_end >= fl2->fl_start) &&
(fl2->fl_end >= fl1->fl_start));
}
/*
* Check whether two locks have the same owner.
*/
static inline int
posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
{
if (fl1->fl_lmops && fl1->fl_lmops->fl_compare_owner)
return fl2->fl_lmops == fl1->fl_lmops &&
fl1->fl_lmops->fl_compare_owner(fl1, fl2);
return fl1->fl_owner == fl2->fl_owner;
}
/* Remove waiter from blocker's block list.
* When blocker ends up pointing to itself then the list is empty.
*/
static inline void __locks_delete_block(struct file_lock *waiter)
{
list_del_init(&waiter->fl_block);
list_del_init(&waiter->fl_link);
waiter->fl_next = NULL;
}
/*
*/
static void locks_delete_block(struct file_lock *waiter)
{
lock_kernel();
__locks_delete_block(waiter);
unlock_kernel();
}
/* Insert waiter into blocker's block list.
* We use a circular list so that processes can be easily woken up in
* the order they blocked. The documentation doesn't require this but
* it seems like the reasonable thing to do.
*/
static void locks_insert_block(struct file_lock *blocker,
struct file_lock *waiter)
{
if (!list_empty(&waiter->fl_block)) {
printk(KERN_ERR "locks_insert_block: removing duplicated lock "
"(pid=%d %Ld-%Ld type=%d)\n", waiter->fl_pid,
waiter->fl_start, waiter->fl_end, waiter->fl_type);
__locks_delete_block(waiter);
}
list_add_tail(&waiter->fl_block, &blocker->fl_block);
waiter->fl_next = blocker;
if (IS_POSIX(blocker))
list_add(&waiter->fl_link, &blocked_list);
}
/* Wake up processes blocked waiting for blocker.
* If told to wait then schedule the processes until the block list
* is empty, otherwise empty the block list ourselves.
*/
static void locks_wake_up_blocks(struct file_lock *blocker)
{
while (!list_empty(&blocker->fl_block)) {
struct file_lock *waiter = list_entry(blocker->fl_block.next,
struct file_lock, fl_block);
__locks_delete_block(waiter);
if (waiter->fl_lmops && waiter->fl_lmops->fl_notify)
waiter->fl_lmops->fl_notify(waiter);
else
wake_up(&waiter->fl_wait);
}
}
/* Insert file lock fl into an inode's lock list at the position indicated
* by pos. At the same time add the lock to the global file lock list.
*/
static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
{
list_add(&fl->fl_link, &file_lock_list);
/* insert into file's list */
fl->fl_next = *pos;
*pos = fl;
if (fl->fl_ops && fl->fl_ops->fl_insert)
fl->fl_ops->fl_insert(fl);
}
/*
* Delete a lock and then free it.
* Wake up processes that are blocked waiting for this lock,
* notify the FS that the lock has been cleared and
* finally free the lock.
*/
static void locks_delete_lock(struct file_lock **thisfl_p)
{
struct file_lock *fl = *thisfl_p;
*thisfl_p = fl->fl_next;
fl->fl_next = NULL;
list_del_init(&fl->fl_link);
fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
if (fl->fl_fasync != NULL) {
printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
fl->fl_fasync = NULL;
}
if (fl->fl_ops && fl->fl_ops->fl_remove)
fl->fl_ops->fl_remove(fl);
locks_wake_up_blocks(fl);
locks_free_lock(fl);
}
/* Determine if lock sys_fl blocks lock caller_fl. Common functionality
* checks for shared/exclusive status of overlapping locks.
*/
static int locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
if (sys_fl->fl_type == F_WRLCK)
return 1;
if (caller_fl->fl_type == F_WRLCK)
return 1;
return 0;
}
/* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
* checking before calling the locks_conflict().
*/
static int posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
/* POSIX locks owned by the same process do not conflict with
* each other.
*/
if (!IS_POSIX(sys_fl) || posix_same_owner(caller_fl, sys_fl))
return (0);
/* Check whether they overlap */
if (!locks_overlap(caller_fl, sys_fl))
return 0;
return (locks_conflict(caller_fl, sys_fl));
}
/* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
* checking before calling the locks_conflict().
*/
static int flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
/* FLOCK locks referring to the same filp do not conflict with
* each other.
*/
if (!IS_FLOCK(sys_fl) || (caller_fl->fl_file == sys_fl->fl_file))
return (0);
if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
return 0;
return (locks_conflict(caller_fl, sys_fl));
}
static int interruptible_sleep_on_locked(wait_queue_head_t *fl_wait, int timeout)
{
int result = 0;
DECLARE_WAITQUEUE(wait, current);
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(fl_wait, &wait);
if (timeout == 0)
schedule();
else
result = schedule_timeout(timeout);
if (signal_pending(current))
result = -ERESTARTSYS;
remove_wait_queue(fl_wait, &wait);
__set_current_state(TASK_RUNNING);
return result;
}
static int locks_block_on_timeout(struct file_lock *blocker, struct file_lock *waiter, int time)
{
int result;
locks_insert_block(blocker, waiter);
result = interruptible_sleep_on_locked(&waiter->fl_wait, time);
__locks_delete_block(waiter);
return result;
}
struct file_lock *
posix_test_lock(struct file *filp, struct file_lock *fl)
{
struct file_lock *cfl;
lock_kernel();
for (cfl = filp->f_dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
if (!IS_POSIX(cfl))
continue;
if (posix_locks_conflict(cfl, fl))
break;
}
unlock_kernel();
return (cfl);
}
EXPORT_SYMBOL(posix_test_lock);
/* This function tests for deadlock condition before putting a process to
* sleep. The detection scheme is no longer recursive. Recursive was neat,
* but dangerous - we risked stack corruption if the lock data was bad, or
* if the recursion was too deep for any other reason.
*
* We rely on the fact that a task can only be on one lock's wait queue
* at a time. When we find blocked_task on a wait queue we can re-search
* with blocked_task equal to that queue's owner, until either blocked_task
* isn't found, or blocked_task is found on a queue owned by my_task.
*
* Note: the above assumption may not be true when handling lock requests
* from a broken NFS client. But broken NFS clients have a lot more to
* worry about than proper deadlock detection anyway... --okir
*/
int posix_locks_deadlock(struct file_lock *caller_fl,
struct file_lock *block_fl)
{
struct list_head *tmp;
next_task:
if (posix_same_owner(caller_fl, block_fl))
return 1;
list_for_each(tmp, &blocked_list) {
struct file_lock *fl = list_entry(tmp, struct file_lock, fl_link);
if (posix_same_owner(fl, block_fl)) {
fl = fl->fl_next;
block_fl = fl;
goto next_task;
}
}
return 0;
}
EXPORT_SYMBOL(posix_locks_deadlock);
/* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
* at the head of the list, but that's secret knowledge known only to
* flock_lock_file and posix_lock_file.
*/
static int flock_lock_file(struct file *filp, struct file_lock *new_fl)
{
struct file_lock **before;
struct inode * inode = filp->f_dentry->d_inode;
int error = 0;
int found = 0;
lock_kernel();
for_each_lock(inode, before) {
struct file_lock *fl = *before;
if (IS_POSIX(fl))
break;
if (IS_LEASE(fl))
continue;
if (filp != fl->fl_file)
continue;
if (new_fl->fl_type == fl->fl_type)
goto out;
found = 1;
locks_delete_lock(before);
break;
}
unlock_kernel();
if (new_fl->fl_type == F_UNLCK)
return 0;
/*
* If a higher-priority process was blocked on the old file lock,
* give it the opportunity to lock the file.
*/
if (found)
cond_resched();
lock_kernel();
for_each_lock(inode, before) {
struct file_lock *fl = *before;
if (IS_POSIX(fl))
break;
if (IS_LEASE(fl))
continue;
if (!flock_locks_conflict(new_fl, fl))
continue;
error = -EAGAIN;
if (new_fl->fl_flags & FL_SLEEP) {
locks_insert_block(fl, new_fl);
}
goto out;
}
locks_insert_lock(&inode->i_flock, new_fl);
error = 0;
out:
unlock_kernel();
return error;
}
EXPORT_SYMBOL(posix_lock_file);
static int __posix_lock_file(struct inode *inode, struct file_lock *request)
{
struct file_lock *fl;
struct file_lock *new_fl, *new_fl2;
struct file_lock *left = NULL;
struct file_lock *right = NULL;
struct file_lock **before;
int error, added = 0;
/*
* We may need two file_lock structures for this operation,
* so we get them in advance to avoid races.
*/
new_fl = locks_alloc_lock();
new_fl2 = locks_alloc_lock();
lock_kernel();
if (request->fl_type != F_UNLCK) {
for_each_lock(inode, before) {
struct file_lock *fl = *before;
if (!IS_POSIX(fl))
continue;
if (!posix_locks_conflict(request, fl))
continue;
error = -EAGAIN;
if (!(request->fl_flags & FL_SLEEP))
goto out;
error = -EDEADLK;
if (posix_locks_deadlock(request, fl))
goto out;
error = -EAGAIN;
locks_insert_block(fl, request);
goto out;
}
}
/* If we're just looking for a conflict, we're done. */
error = 0;
if (request->fl_flags & FL_ACCESS)
goto out;
error = -ENOLCK; /* "no luck" */
if (!(new_fl && new_fl2))
goto out;
/*
* We've allocated the new locks in advance, so there are no
* errors possible (and no blocking operations) from here on.
*
* Find the first old lock with the same owner as the new lock.
*/
before = &inode->i_flock;
/* First skip locks owned by other processes. */
while ((fl = *before) && (!IS_POSIX(fl) ||
!posix_same_owner(request, fl))) {
before = &fl->fl_next;
}
/* Process locks with this owner. */
while ((fl = *before) && posix_same_owner(request, fl)) {
/* Detect adjacent or overlapping regions (if same lock type)
*/
if (request->fl_type == fl->fl_type) {
/* In all comparisons of start vs end, use
* "start - 1" rather than "end + 1". If end
* is OFFSET_MAX, end + 1 will become negative.
*/
if (fl->fl_end < request->fl_start - 1)
goto next_lock;
/* If the next lock in the list has entirely bigger
* addresses than the new one, insert the lock here.
*/
if (fl->fl_start - 1 > request->fl_end)
break;
/* If we come here, the new and old lock are of the
* same type and adjacent or overlapping. Make one
* lock yielding from the lower start address of both
* locks to the higher end address.
*/
if (fl->fl_start > request->fl_start)
fl->fl_start = request->fl_start;
else
request->fl_start = fl->fl_start;
if (fl->fl_end < request->fl_end)
fl->fl_end = request->fl_end;
else
request->fl_end = fl->fl_end;
if (added) {
locks_delete_lock(before);
continue;
}
request = fl;
added = 1;
}
else {
/* Processing for different lock types is a bit
* more complex.
*/
if (fl->fl_end < request->fl_start)
goto next_lock;
if (fl->fl_start > request->fl_end)
break;
if (request->fl_type == F_UNLCK)
added = 1;
if (fl->fl_start < request->fl_start)
left = fl;
/* If the next lock in the list has a higher end
* address than the new one, insert the new one here.
*/
if (fl->fl_end > request->fl_end) {
right = fl;
break;
}
if (fl->fl_start >= request->fl_start) {
/* The new lock completely replaces an old
* one (This may happen several times).
*/
if (added) {
locks_delete_lock(before);
continue;
}
/* Replace the old lock with the new one.
* Wake up anybody waiting for the old one,
* as the change in lock type might satisfy
* their needs.
*/
locks_wake_up_blocks(fl);
fl->fl_start = request->fl_start;
fl->fl_end = request->fl_end;
fl->fl_type = request->fl_type;
fl->fl_u = request->fl_u;
request = fl;
added = 1;
}
}
/* Go on to next lock.
*/
next_lock:
before = &fl->fl_next;
}
error = 0;
if (!added) {
if (request->fl_type == F_UNLCK)
goto out;
locks_copy_lock(new_fl, request);
locks_insert_lock(before, new_fl);
new_fl = NULL;
}
if (right) {
if (left == right) {
/* The new lock breaks the old one in two pieces,
* so we have to use the second new lock.
*/
left = new_fl2;
new_fl2 = NULL;
locks_copy_lock(left, right);
locks_insert_lock(before, left);
}
right->fl_start = request->fl_end + 1;
locks_wake_up_blocks(right);
}
if (left) {
left->fl_end = request->fl_start - 1;
locks_wake_up_blocks(left);
}
out:
unlock_kernel();
/*
* Free any unused locks.
*/
if (new_fl)
locks_free_lock(new_fl);
if (new_fl2)
locks_free_lock(new_fl2);
return error;
}
/**
* posix_lock_file - Apply a POSIX-style lock to a file
* @filp: The file to apply the lock to
* @fl: The lock to be applied
*
* Add a POSIX style lock to a file.
* We merge adjacent & overlapping locks whenever possible.
* POSIX locks are sorted by owner task, then by starting address
*/
int posix_lock_file(struct file *filp, struct file_lock *fl)
{
return __posix_lock_file(filp->f_dentry->d_inode, fl);
}
/**
* posix_lock_file_wait - Apply a POSIX-style lock to a file
* @filp: The file to apply the lock to
* @fl: The lock to be applied
*
* Add a POSIX style lock to a file.
* We merge adjacent & overlapping locks whenever possible.
* POSIX locks are sorted by owner task, then by starting address
*/
int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
{
int error;
might_sleep ();
for (;;) {
error = __posix_lock_file(filp->f_dentry->d_inode, fl);
if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
break;
error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
if (!error)
continue;
locks_delete_block(fl);
break;
}
return error;
}
EXPORT_SYMBOL(posix_lock_file_wait);
/**
* locks_mandatory_locked - Check for an active lock
* @inode: the file to check