summaryrefslogtreecommitdiff
path: root/fs/fcntl.c
blob: afed3b364979ac85766171fb39e66ceefe0c1175 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
/*
 *  linux/fs/fcntl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched/task.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/shmem_fs.h>
#include <linux/compat.h>

#include <asm/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>

#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)

static int setfl(int fd, struct file * filp, unsigned long arg)
{
	struct inode * inode = file_inode(filp);
	int error = 0;

	/*
	 * O_APPEND cannot be cleared if the file is marked as append-only
	 * and the file is open for write.
	 */
	if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
		return -EPERM;

	/* O_NOATIME can only be set by the owner or superuser */
	if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
		if (!inode_owner_or_capable(inode))
			return -EPERM;

	/* required for strict SunOS emulation */
	if (O_NONBLOCK != O_NDELAY)
	       if (arg & O_NDELAY)
		   arg |= O_NONBLOCK;

	/* Pipe packetized mode is controlled by O_DIRECT flag */
	if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) {
		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
			!filp->f_mapping->a_ops->direct_IO)
				return -EINVAL;
	}

	if (filp->f_op->check_flags)
		error = filp->f_op->check_flags(arg);
	if (error)
		return error;

	/*
	 * ->fasync() is responsible for setting the FASYNC bit.
	 */
	if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
		error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
		if (error < 0)
			goto out;
		if (error > 0)
			error = 0;
	}
	spin_lock(&filp->f_lock);
	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
	spin_unlock(&filp->f_lock);

 out:
	return error;
}

static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
                     int force)
{
	write_lock_irq(&filp->f_owner.lock);
	if (force || !filp->f_owner.pid) {
		put_pid(filp->f_owner.pid);
		filp->f_owner.pid = get_pid(pid);
		filp->f_owner.pid_type = type;

		if (pid) {
			const struct cred *cred = current_cred();
			filp->f_owner.uid = cred->uid;
			filp->f_owner.euid = cred->euid;
		}
	}
	write_unlock_irq(&filp->f_owner.lock);
}

void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
		int force)
{
	security_file_set_fowner(filp);
	f_modown(filp, pid, type, force);
}
EXPORT_SYMBOL(__f_setown);

int f_setown(struct file *filp, unsigned long arg, int force)
{
	enum pid_type type;
	struct pid *pid = NULL;
	int who = arg, ret = 0;

	type = PIDTYPE_PID;
	if (who < 0) {
		/* avoid overflow below */
		if (who == INT_MIN)
			return -EINVAL;

		type = PIDTYPE_PGID;
		who = -who;
	}

	rcu_read_lock();
	if (who) {
		pid = find_vpid(who);
		if (!pid)
			ret = -ESRCH;
	}

	if (!ret)
		__f_setown(filp, pid, type, force);
	rcu_read_unlock();

	return ret;
}
EXPORT_SYMBOL(f_setown);

void f_delown(struct file *filp)
{
	f_modown(filp, NULL, PIDTYPE_PID, 1);
}

pid_t f_getown(struct file *filp)
{
	pid_t pid;
	read_lock(&filp->f_owner.lock);
	pid = pid_vnr(filp->f_owner.pid);
	if (filp->f_owner.pid_type == PIDTYPE_PGID)
		pid = -pid;
	read_unlock(&filp->f_owner.lock);
	return pid;
}

static int f_setown_ex(struct file *filp, unsigned long arg)
{
	struct f_owner_ex __user *owner_p = (void __user *)arg;
	struct f_owner_ex owner;
	struct pid *pid;
	int type;
	int ret;

	ret = copy_from_user(&owner, owner_p, sizeof(owner));
	if (ret)
		return -EFAULT;

	switch (owner.type) {
	case F_OWNER_TID:
		type = PIDTYPE_MAX;
		break;

	case F_OWNER_PID:
		type = PIDTYPE_PID;
		break;

	case F_OWNER_PGRP:
		type = PIDTYPE_PGID;
		break;

	default:
		return -EINVAL;
	}

	rcu_read_lock();
	pid = find_vpid(owner.pid);
	if (owner.pid && !pid)
		ret = -ESRCH;
	else
		 __f_setown(filp, pid, type, 1);
	rcu_read_unlock();

	return ret;
}

static int f_getown_ex(struct file *filp, unsigned long arg)
{
	struct f_owner_ex __user *owner_p = (void __user *)arg;
	struct f_owner_ex owner;
	int ret = 0;

	read_lock(&filp->f_owner.lock);
	owner.pid = pid_vnr(filp->f_owner.pid);
	switch (filp->f_owner.pid_type) {
	case PIDTYPE_MAX:
		owner.type = F_OWNER_TID;
		break;

	case PIDTYPE_PID:
		owner.type = F_OWNER_PID;
		break;

	case PIDTYPE_PGID:
		owner.type = F_OWNER_PGRP;
		break;

	default:
		WARN_ON(1);
		ret = -EINVAL;
		break;
	}
	read_unlock(&filp->f_owner.lock);

	if (!ret) {
		ret = copy_to_user(owner_p, &owner, sizeof(owner));
		if (ret)
			ret = -EFAULT;
	}
	return ret;
}

#ifdef CONFIG_CHECKPOINT_RESTORE
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
	struct user_namespace *user_ns = current_user_ns();
	uid_t __user *dst = (void __user *)arg;
	uid_t src[2];
	int err;

	read_lock(&filp->f_owner.lock);
	src[0] = from_kuid(user_ns, filp->f_owner.uid);
	src[1] = from_kuid(user_ns, filp->f_owner.euid);
	read_unlock(&filp->f_owner.lock);

	err  = put_user(src[0], &dst[0]);
	err |= put_user(src[1], &dst[1]);

	return err;
}
#else
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
	return -EINVAL;
}
#endif

static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
		struct file *filp)
{
	void __user *argp = (void __user *)arg;
	struct flock flock;
	long err = -EINVAL;

	switch (cmd) {
	case F_DUPFD:
		err = f_dupfd(arg, filp, 0);
		break;
	case F_DUPFD_CLOEXEC:
		err = f_dupfd(arg, filp, O_CLOEXEC);
		break;
	case F_GETFD:
		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
		break;
	case F_SETFD:
		err = 0;
		set_close_on_exec(fd, arg & FD_CLOEXEC);
		break;
	case F_GETFL:
		err = filp->f_flags;
		break;
	case F_SETFL:
		err = setfl(fd, filp, arg);
		break;
#if BITS_PER_LONG != 32
	/* 32-bit arches must use fcntl64() */
	case F_OFD_GETLK:
#endif
	case F_GETLK:
		if (copy_from_user(&flock, argp, sizeof(flock)))
			return -EFAULT;
		err = fcntl_getlk(filp, cmd, &flock);
		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
			return -EFAULT;
		break;
#if BITS_PER_LONG != 32
	/* 32-bit arches must use fcntl64() */
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
#endif
		/* Fallthrough */
	case F_SETLK:
	case F_SETLKW:
		if (copy_from_user(&flock, argp, sizeof(flock)))
			return -EFAULT;
		err = fcntl_setlk(fd, filp, cmd, &flock);
		break;
	case F_GETOWN:
		/*
		 * XXX If f_owner is a process group, the
		 * negative return value will get converted
		 * into an error.  Oops.  If we keep the
		 * current syscall conventions, the only way
		 * to fix this will be in libc.
		 */
		err = f_getown(filp);
		force_successful_syscall_return();
		break;
	case F_SETOWN:
		err = f_setown(filp, arg, 1);
		break;
	case F_GETOWN_EX:
		err = f_getown_ex(filp, arg);
		break;
	case F_SETOWN_EX:
		err = f_setown_ex(filp, arg);
		break;
	case F_GETOWNER_UIDS:
		err = f_getowner_uids(filp, arg);
		break;
	case F_GETSIG:
		err = filp->f_owner.signum;
		break;
	case F_SETSIG:
		/* arg == 0 restores default behaviour. */
		if (!valid_signal(arg)) {
			break;
		}
		err = 0;
		filp->f_owner.signum = arg;
		break;
	case F_GETLEASE:
		err = fcntl_getlease(filp);
		break;
	case F_SETLEASE:
		err = fcntl_setlease(fd, filp, arg);
		break;
	case F_NOTIFY:
		err = fcntl_dirnotify(fd, filp, arg);
		break;
	case F_SETPIPE_SZ:
	case F_GETPIPE_SZ:
		err = pipe_fcntl(filp, cmd, arg);
		break;
	case F_ADD_SEALS:
	case F_GET_SEALS:
		err = shmem_fcntl(filp, cmd, arg);
		break;
	default:
		break;
	}
	return err;
}

static int check_fcntl_cmd(unsigned cmd)
{
	switch (cmd) {
	case F_DUPFD:
	case F_DUPFD_CLOEXEC:
	case F_GETFD:
	case F_SETFD:
	case F_GETFL:
		return 1;
	}
	return 0;
}

SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{	
	struct fd f = fdget_raw(fd);
	long err = -EBADF;

	if (!f.file)
		goto out;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out1;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if (!err)
		err = do_fcntl(fd, cmd, arg, f.file);

out1:
 	fdput(f);
out:
	return err;
}

#if BITS_PER_LONG == 32
SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
		unsigned long, arg)
{	
	void __user *argp = (void __user *)arg;
	struct fd f = fdget_raw(fd);
	struct flock64 flock;
	long err = -EBADF;

	if (!f.file)
		goto out;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out1;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if (err)
		goto out1;
	
	switch (cmd) {
	case F_GETLK64:
	case F_OFD_GETLK:
		err = -EFAULT;
		if (copy_from_user(&flock, argp, sizeof(flock)))
			break;
		err = fcntl_getlk64(f.file, cmd, &flock);
		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
			err = -EFAULT;
		break;
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		err = -EFAULT;
		if (copy_from_user(&flock, argp, sizeof(flock)))
			break;
		err = fcntl_setlk64(fd, f.file, cmd, &flock);
		break;
	default:
		err = do_fcntl(fd, cmd, arg, f.file);
		break;
	}
out1:
	fdput(f);
out:
	return err;
}
#endif

#ifdef CONFIG_COMPAT
static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

static unsigned int
convert_fcntl_cmd(unsigned int cmd)
{
	switch (cmd) {
	case F_GETLK64:
		return F_GETLK;
	case F_SETLK64:
		return F_SETLK;
	case F_SETLKW64:
		return F_SETLKW;
	}

	return cmd;
}

/*
 * GETLK was successful and we need to return the data, but it needs to fit in
 * the compat structure.
 * l_start shouldn't be too big, unless the original start + end is greater than
 * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return
 * -EOVERFLOW in that case.  l_len could be too big, in which case we just
 * truncate it, and only allow the app to see that part of the conflicting lock
 * that might make sense to it anyway
 */
static int fixup_compat_flock(struct flock *flock)
{
	if (flock->l_start > COMPAT_OFF_T_MAX)
		return -EOVERFLOW;
	if (flock->l_len > COMPAT_OFF_T_MAX)
		flock->l_len = COMPAT_OFF_T_MAX;
	return 0;
}

COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
		       compat_ulong_t, arg)
{
	struct fd f = fdget_raw(fd);
	struct flock flock;
	long err = -EBADF;

	if (!f.file)
		return err;

	if (unlikely(f.file->f_mode & FMODE_PATH)) {
		if (!check_fcntl_cmd(cmd))
			goto out_put;
	}

	err = security_file_fcntl(f.file, cmd, arg);
	if (err)
		goto out_put;

	switch (cmd) {
	case F_GETLK:
		err = get_compat_flock(&flock, compat_ptr(arg));
		if (err)
			break;
		err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
		if (err)
			break;
		err = fixup_compat_flock(&flock);
		if (err)
			return err;
		err = put_compat_flock(&flock, compat_ptr(arg));
		break;
	case F_GETLK64:
	case F_OFD_GETLK:
		err = get_compat_flock64(&flock, compat_ptr(arg));
		if (err)
			break;
		err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
		if (err)
			break;
		err = fixup_compat_flock(&flock);
		if (err)
			return err;
		err = put_compat_flock64(&flock, compat_ptr(arg));
		break;
	case F_SETLK:
	case F_SETLKW:
		err = get_compat_flock(&flock, compat_ptr(arg));
		if (err)
			break;
		err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
		break;
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		err = get_compat_flock64(&flock, compat_ptr(arg));
		if (err)
			break;
		err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
		break;
	default:
		err = do_fcntl(fd, cmd, arg, f.file);
		break;
	}
out_put:
	fdput(f);
	return err;
}

COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
		       compat_ulong_t, arg)
{
	switch (cmd) {
	case F_GETLK64:
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_GETLK:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		return -EINVAL;
	}
	return compat_sys_fcntl64(fd, cmd, arg);
}
#endif

/* Table to convert sigio signal codes into poll band bitmaps */

static const long band_table[NSIGPOLL] = {
	POLLIN | POLLRDNORM,			/* POLL_IN */
	POLLOUT | POLLWRNORM | POLLWRBAND,	/* POLL_OUT */
	POLLIN | POLLRDNORM | POLLMSG,		/* POLL_MSG */
	POLLERR,				/* POLL_ERR */
	POLLPRI | POLLRDBAND,			/* POLL_PRI */
	POLLHUP | POLLERR			/* POLL_HUP */
};

static inline int sigio_perm(struct task_struct *p,
                             struct fown_struct *fown, int sig)
{
	const struct cred *cred;
	int ret;

	rcu_read_lock();
	cred = __task_cred(p);
	ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) ||
		uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) ||
		uid_eq(fown->uid,  cred->suid) || uid_eq(fown->uid,  cred->uid)) &&
	       !security_file_send_sigiotask(p, fown, sig));
	rcu_read_unlock();
	return ret;
}

static void send_sigio_to_task(struct task_struct *p,
			       struct fown_struct *fown,
			       int fd, int reason, int group)
{
	/*
	 * F_SETSIG can change ->signum lockless in parallel, make
	 * sure we read it once and use the same value throughout.
	 */
	int signum = ACCESS_ONCE(fown->signum);

	if (!sigio_perm(p, fown, signum))
		return;

	switch (signum) {
		siginfo_t si;
		default:
			/* Queue a rt signal with the appropriate fd as its
			   value.  We use SI_SIGIO as the source, not 
			   SI_KERNEL, since kernel signals always get 
			   delivered even if we can't queue.  Failure to
			   queue in this case _should_ be reported; we fall
			   back to SIGIO in that case. --sct */
			si.si_signo = signum;
			si.si_errno = 0;
		        si.si_code  = reason;
			/* Make sure we are called with one of the POLL_*
			   reasons, otherwise we could leak kernel stack into
			   userspace.  */
			BUG_ON((reason & __SI_MASK) != __SI_POLL);
			if (reason - POLL_IN >= NSIGPOLL)
				si.si_band  = ~0L;
			else
				si.si_band = band_table[reason - POLL_IN];
			si.si_fd    = fd;
			if (!do_send_sig_info(signum, &si, p, group))
				break;
		/* fall-through: fall back on the old plain SIGIO signal */
		case 0:
			do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, group);
	}
}

void send_sigio(struct fown_struct *fown, int fd, int band)
{
	struct task_struct *p;
	enum pid_type type;
	struct pid *pid;
	int group = 1;
	
	read_lock(&fown->lock);

	type = fown->pid_type;
	if (type == PIDTYPE_MAX) {
		group = 0;
		type = PIDTYPE_PID;
	}

	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;
	
	read_lock(&tasklist_lock);
	do_each_pid_task(pid, type, p) {
		send_sigio_to_task(p, fown, fd, band, group);
	} while_each_pid_task(pid, type, p);
	read_unlock(&tasklist_lock);
 out_unlock_fown:
	read_unlock(&fown->lock);
}

static void send_sigurg_to_task(struct task_struct *p,
				struct fown_struct *fown, int group)
{
	if (sigio_perm(p, fown, SIGURG))
		do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, group);
}

int send_sigurg(struct fown_struct *fown)
{
	struct task_struct *p;
	enum pid_type type;
	struct pid *pid;
	int group = 1;
	int ret = 0;
	
	read_lock(&fown->lock);

	type = fown->pid_type;
	if (type == PIDTYPE_MAX) {
		group = 0;
		type = PIDTYPE_PID;
	}

	pid = fown->pid;
	if (!pid)
		goto out_unlock_fown;

	ret = 1;
	
	read_lock(&tasklist_lock);
	do_each_pid_task(pid, type, p) {
		send_sigurg_to_task(p, fown, group);
	} while_each_pid_task(pid, type, p);
	read_unlock(&tasklist_lock);
 out_unlock_fown:
	read_unlock(&fown->lock);
	return ret;
}

static DEFINE_SPINLOCK(fasync_lock);
static struct kmem_cache *fasync_cache __read_mostly;

static void fasync_free_rcu(struct rcu_head *head)
{
	kmem_cache_free(fasync_cache,
			container_of(head, struct fasync_struct, fa_rcu));
}

/*
 * Remove a fasync entry. If successfully removed, return
 * positive and clear the FASYNC flag. If no entry exists,
 * do nothing and return 0.
 *
 * NOTE! It is very important that the FASYNC flag always
 * match the state "is the filp on a fasync list".
 *
 */
int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
{
	struct fasync_struct *fa, **fp;
	int result = 0;

	spin_lock(&filp->f_lock);
	spin_lock(&fasync_lock);
	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
		if (fa->fa_file != filp)
			continue;

		spin_lock_irq(&fa->fa_lock);
		fa->fa_file = NULL;
		spin_unlock_irq(&fa->fa_lock);

		*fp = fa->fa_next;
		call_rcu(&fa->fa_rcu, fasync_free_rcu);
		filp->f_flags &= ~FASYNC;
		result = 1;
		break;
	}
	spin_unlock(&fasync_lock);
	spin_unlock(&filp->f_lock);
	return result;
}

struct fasync_struct *fasync_alloc(void)
{
	return kmem_cache_alloc(fasync_cache, GFP_KERNEL);
}

/*
 * NOTE! This can be used only for unused fasync entries:
 * entries that actually got inserted on the fasync list
 * need to be released by rcu - see fasync_remove_entry.
 */
void fasync_free(struct fasync_struct *new)
{
	kmem_cache_free(fasync_cache, new);
}

/*
 * Insert a new entry into the fasync list.  Return the pointer to the
 * old one if we didn't use the new one.
 *
 * NOTE! It is very important that the FASYNC flag always
 * match the state "is the filp on a fasync list".
 */
struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new)
{
        struct fasync_struct *fa, **fp;

	spin_lock(&filp->f_lock);
	spin_lock(&fasync_lock);
	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
		if (fa->fa_file != filp)
			continue;

		spin_lock_irq(&fa->fa_lock);
		fa->fa_fd = fd;
		spin_unlock_irq(&fa->fa_lock);
		goto out;
	}

	spin_lock_init(&new->fa_lock);
	new->magic = FASYNC_MAGIC;
	new->fa_file = filp;
	new->fa_fd = fd;
	new->fa_next = *fapp;
	rcu_assign_pointer(*fapp, new);
	filp->f_flags |= FASYNC;

out:
	spin_unlock(&fasync_lock);
	spin_unlock(&filp->f_lock);
	return fa;
}

/*
 * Add a fasync entry. Return negative on error, positive if
 * added, and zero if did nothing but change an existing one.
 */
static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
{
	struct fasync_struct *new;

	new = fasync_alloc();
	if (!new)
		return -ENOMEM;

	/*
	 * fasync_insert_entry() returns the old (update) entry if
	 * it existed.
	 *
	 * So free the (unused) new entry and return 0 to let the
	 * caller know that we didn't add any new fasync entries.
	 */
	if (fasync_insert_entry(fd, filp, fapp, new)) {
		fasync_free(new);
		return 0;
	}

	return 1;
}

/*
 * fasync_helper() is used by almost all character device drivers
 * to set up the fasync queue, and for regular files by the file
 * lease code. It returns negative on error, 0 if it did no changes
 * and positive if it added/deleted the entry.
 */
int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
{
	if (!on)
		return fasync_remove_entry(filp, fapp);
	return fasync_add_entry(fd, filp, fapp);
}

EXPORT_SYMBOL(fasync_helper);

/*
 * rcu_read_lock() is held
 */
static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
{
	while (fa) {
		struct fown_struct *fown;
		unsigned long flags;

		if (fa->magic != FASYNC_MAGIC) {
			printk(KERN_ERR "kill_fasync: bad magic number in "
			       "fasync_struct!\n");
			return;
		}
		spin_lock_irqsave(&fa->fa_lock, flags);
		if (fa->fa_file) {
			fown = &fa->fa_file->f_owner;
			/* Don't send SIGURG to processes which have not set a
			   queued signum: SIGURG has its own default signalling
			   mechanism. */
			if (!(sig == SIGURG && fown->signum == 0))
				send_sigio(fown, fa->fa_fd, band);
		}
		spin_unlock_irqrestore(&fa->fa_lock, flags);
		fa = rcu_dereference(fa->fa_next);
	}
}

void kill_fasync(struct fasync_struct **fp, int sig, int band)
{
	/* First a quick test without locking: usually
	 * the list is empty.
	 */
	if (*fp) {
		rcu_read_lock();
		kill_fasync_rcu(rcu_dereference(*fp), sig, band);
		rcu_read_unlock();
	}
}
EXPORT_SYMBOL(kill_fasync);

static int __init fcntl_init(void)
{
	/*
	 * Please add new bits here to ensure allocation uniqueness.
	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
	 * is defined as O_NONBLOCK on some platforms and not on others.
	 */
	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
		HWEIGHT32(
			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
			__FMODE_EXEC | __FMODE_NONOTIFY));

	fasync_cache = kmem_cache_create("fasync_cache",
		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
	return 0;
}

module_init(fcntl_init)