summaryrefslogtreecommitdiffstats
path: root/kernel/futex.c
blob: 50356fb5d72685fb6c68d0bcf3ed0ec1074b693b (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
/*
 *  Fast Userspace Mutexes (which I call "Futexes!").
 *  (C) Rusty Russell, IBM 2002
 *
 *  Generalized futexes, futex requeueing, misc fixes by Ingo Molnar
 *  (C) Copyright 2003 Red Hat Inc, All Rights Reserved
 *
 *  Removed page pinning, fix privately mapped COW pages and other cleanups
 *  (C) Copyright 2003, 2004 Jamie Lokier
 *
 *  Robust futex support started by Ingo Molnar
 *  (C) Copyright 2006 Red Hat Inc, All Rights Reserved
 *  Thanks to Thomas Gleixner for suggestions, analysis and fixes.
 *
 *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
 *  enough at me, Linus for the original (flawed) idea, Matthew
 *  Kirkwood for proof-of-concept implementation.
 *
 *  "The futexes are also cursed."
 *  "But they come in a choice of three flavours!"
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/futex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <asm/futex.h>

#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)

/*
 * Futexes are matched on equal values of this key.
 * The key type depends on whether it's a shared or private mapping.
 * Don't rearrange members without looking at hash_futex().
 *
 * offset is aligned to a multiple of sizeof(u32) (== 4) by definition.
 * We set bit 0 to indicate if it's an inode-based key.
 */
union futex_key {
	struct {
		unsigned long pgoff;
		struct inode *inode;
		int offset;
	} shared;
	struct {
		unsigned long address;
		struct mm_struct *mm;
		int offset;
	} private;
	struct {
		unsigned long word;
		void *ptr;
		int offset;
	} both;
};

/*
 * We use this hashed waitqueue instead of a normal wait_queue_t, so
 * we can wake only the relevant ones (hashed queues may be shared).
 *
 * A futex_q has a woken state, just like tasks have TASK_RUNNING.
 * It is considered woken when list_empty(&q->list) || q->lock_ptr == 0.
 * The order of wakup is always to make the first condition true, then
 * wake up q->waiters, then make the second condition true.
 */
struct futex_q {
	struct list_head list;
	wait_queue_head_t waiters;

	/* Which hash list lock to use: */
	spinlock_t *lock_ptr;

	/* Key which the futex is hashed on: */
	union futex_key key;

	/* For fd, sigio sent using these: */
	int fd;
	struct file *filp;
};

/*
 * Split the global futex_lock into every hash list lock.
 */
struct futex_hash_bucket {
       spinlock_t              lock;
       struct list_head       chain;
};

static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];

/* Futex-fs vfsmount entry: */
static struct vfsmount *futex_mnt;

/*
 * We hash on the keys returned from get_futex_key (see below).
 */
static struct futex_hash_bucket *hash_futex(union futex_key *key)
{
	u32 hash = jhash2((u32*)&key->both.word,
			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
			  key->both.offset);
	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
}

/*
 * Return 1 if two futex_keys are equal, 0 otherwise.
 */
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
	return (key1->both.word == key2->both.word
		&& key1->both.ptr == key2->both.ptr
		&& key1->both.offset == key2->both.offset);
}

/*
 * Get parameters which are the keys for a futex.
 *
 * For shared mappings, it's (page->index, vma->vm_file->f_dentry->d_inode,
 * offset_within_page).  For private mappings, it's (uaddr, current->mm).
 * We can usually work out the index without swapping in the page.
 *
 * Returns: 0, or negative error code.
 * The key words are stored in *key on success.
 *
 * Should be called with &current->mm->mmap_sem but NOT any spinlocks.
 */
static int get_futex_key(u32 __user *uaddr, union futex_key *key)
{
	unsigned long address = (unsigned long)uaddr;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	struct page *page;
	int err;

	/*
	 * The futex address must be "naturally" aligned.
	 */
	key->both.offset = address % PAGE_SIZE;
	if (unlikely((key->both.offset % sizeof(u32)) != 0))
		return -EINVAL;
	address -= key->both.offset;

	/*
	 * The futex is hashed differently depending on whether
	 * it's in a shared or private mapping.  So check vma first.
	 */
	vma = find_extend_vma(mm, address);
	if (unlikely(!vma))
		return -EFAULT;

	/*
	 * Permissions.
	 */
	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;

	/*
	 * Private mappings are handled in a simple way.
	 *
	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
	 * it's a read-only handle, it's expected that futexes attach to
	 * the object not the particular process.  Therefore we use
	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
	 * mappings of _writable_ handles.
	 */
	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
		key->private.mm = mm;
		key->private.address = address;
		return 0;
	}

	/*
	 * Linear file mappings are also simple.
	 */
	key->shared.inode = vma->vm_file->f_dentry->d_inode;
	key->both.offset++; /* Bit 0 of offset indicates inode-based key. */
	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
				     + vma->vm_pgoff);
		return 0;
	}

	/*
	 * We could walk the page table to read the non-linear
	 * pte, and get the page index without fetching the page
	 * from swap.  But that's a lot of code to duplicate here
	 * for a rare case, so we simply fetch the page.
	 */
	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
	if (err >= 0) {
		key->shared.pgoff =
			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
		put_page(page);
		return 0;
	}
	return err;
}

/*
 * Take a reference to the resource addressed by a key.
 * Can be called while holding spinlocks.
 *
 * NOTE: mmap_sem MUST be held between get_futex_key() and calling this
 * function, if it is called at all.  mmap_sem keeps key->shared.inode valid.
 */
static inline void get_key_refs(union futex_key *key)
{
	if (key->both.ptr != 0) {
		if (key->both.offset & 1)
			atomic_inc(&key->shared.inode->i_count);
		else
			atomic_inc(&key->private.mm->mm_count);
	}
}

/*
 * Drop a reference to the resource addressed by a key.
 * The hash bucket spinlock must not be held.
 */
static void drop_key_refs(union futex_key *key)
{
	if (key->both.ptr != 0) {
		if (key->both.offset & 1)
			iput(key->shared.inode);
		else
			mmdrop(key->private.mm);
	}
}

static inline int get_futex_value_locked(u32 *dest, u32 __user *from)
{
	int ret;

	inc_preempt_count();
	ret = __copy_from_user_inatomic(dest, from, sizeof(u32));
	dec_preempt_count();

	return ret ? -EFAULT : 0;
}

/*
 * The hash bucket lock must be held when this is called.
 * Afterwards, the futex_q must not be accessed.
 */
static void wake_futex(struct futex_q *q)
{
	list_del_init(&q->list);
	if (q->filp)
		send_sigio(&q->filp->f_owner, q->fd, POLL_IN);
	/*
	 * The lock in wake_up_all() is a crucial memory barrier after the
	 * list_del_init() and also before assigning to q->lock_ptr.
	 */
	wake_up_all(&q->waiters);
	/*
	 * The waiting task can free the futex_q as soon as this is written,
	 * without taking any locks.  This must come last.
	 *
	 * A memory barrier is required here to prevent the following store
	 * to lock_ptr from getting ahead of the wakeup. Clearing the lock
	 * at the end of wake_up_all() does not prevent this store from
	 * moving.
	 */
	wmb();
	q->lock_ptr = NULL;
}

/*
 * Wake up all waiters hashed on the physical page that is mapped
 * to this virtual address:
 */
static int futex_wake(u32 __user *uaddr, int nr_wake)
{
	struct futex_hash_bucket *hb;
	struct futex_q *this, *next;
	struct list_head *head;
	union futex_key key;
	int ret;

	down_read(&current->mm->mmap_sem);

	ret = get_futex_key(uaddr, &key);
	if (unlikely(ret != 0))
		goto out;

	hb = hash_futex(&key);
	spin_lock(&hb->lock);
	head = &hb->chain;

	list_for_each_entry_safe(this, next, head, list) {
		if (match_futex (&this->key, &key)) {
			wake_futex(this);
			if (++ret >= nr_wake)
				break;
		}
	}

	spin_unlock(&hb->lock);
out:
	up_read(&current->mm->mmap_sem);
	return ret;
}

/*
 * Wake up all waiters hashed on the physical page that is mapped
 * to this virtual address:
 */
static int
futex_wake_op(u32 __user *uaddr1, u32 __user *uaddr2,
	      int nr_wake, int nr_wake2, int op)
{
	union futex_key key1, key2;
	struct futex_hash_bucket *hb1, *hb2;
	struct list_head *head;
	struct futex_q *this, *next;
	int ret, op_ret, attempt = 0;

retryfull:
	down_read(&current->mm->mmap_sem);

	ret = get_futex_key(uaddr1, &key1);
	if (unlikely(ret != 0))
		goto out;
	ret = get_futex_key(uaddr2, &key2);
	if (unlikely(ret != 0))
		goto out;

	hb1 = hash_futex(&key1);
	hb2 = hash_futex(&key2);

retry:
	if (hb1 < hb2)
		spin_lock(&hb1->lock);
	spin_lock(&hb2->lock);
	if (hb1 > hb2)
		spin_lock(&hb1->lock);

	op_ret = futex_atomic_op_inuser(op, uaddr2);
	if (unlikely(op_ret < 0)) {
		u32 dummy;

		spin_unlock(&hb1->lock);
		if (hb1 != hb2)
			spin_unlock(&hb2->lock);

#ifndef CONFIG_MMU
		/*
		 * we don't get EFAULT from MMU faults if we don't have an MMU,
		 * but we might get them from range checking
		 */
		ret = op_ret;
		goto out;
#endif

		if (unlikely(op_ret != -EFAULT)) {
			ret = op_ret;
			goto out;
		}

		/*
		 * futex_atomic_op_inuser needs to both read and write
		 * *(int __user *)uaddr2, but we can't modify it
		 * non-atomically.  Therefore, if get_user below is not
		 * enough, we need to handle the fault ourselves, while
		 * still holding the mmap_sem.
		 */
		if (attempt++) {
			struct vm_area_struct * vma;
			struct mm_struct *mm = current->mm;
			unsigned long address = (unsigned long)uaddr2;

			ret = -EFAULT;
			if (attempt >= 2 ||
			    !(vma = find_vma(mm, address)) ||
			    vma->vm_start > address ||
			    !(vma->vm_flags & VM_WRITE))
				goto out;

			switch (handle_mm_fault(mm, vma, address, 1)) {
			case VM_FAULT_MINOR:
				current->min_flt++;
				break;
			case VM_FAULT_MAJOR:
				current->maj_flt++;
				break;
			default:
				goto out;
			}
			goto retry;
		}

		/*
		 * If we would have faulted, release mmap_sem,
		 * fault it in and start all over again.
		 */
		up_read(&current->mm->mmap_sem);

		ret = get_user(dummy, uaddr2);
		if (ret)
			return ret;

		goto retryfull;
	}

	head = &hb1->chain;

	list_for_each_entry_safe(this, next, head, list) {
		if (match_futex (&this->key, &key1)) {
			wake_futex(this);
			if (++ret >= nr_wake)
				break;
		}
	}

	if (op_ret > 0) {
		head = &hb2->chain;

		op_ret = 0;
		list_for_each_entry_safe(this, next, head, list) {
			if (match_futex (&this->key, &key2)) {
				wake_futex(this);
				if (++op_ret >= nr_wake2)
					break;
			}
		}
		ret += op_ret;
	}

	spin_unlock(&hb1->lock);
	if (hb1 != hb2)
		spin_unlock(&hb2->lock);
out:
	up_read(&current->mm->mmap_sem);
	return ret;
}

/*
 * Requeue all waiters hashed on one physical page to another
 * physical page.
 */
static int futex_requeue(u32 __user *uaddr1, u32 __user *uaddr2,
			 int nr_wake, int nr_requeue, u32 *cmpval)
{
	union futex_key key1, key2;
	struct futex_hash_bucket *hb1, *hb2;
	struct list_head *head1;
	struct futex_q *this, *next;
	int ret, drop_count = 0;

 retry:
	down_read(&current->mm->mmap_sem);

	ret = get_futex_key(uaddr1, &key1);
	if (unlikely(ret != 0))
		goto out;
	ret = get_futex_key(uaddr2, &key2);
	if (unlikely(ret != 0))
		goto out;

	hb1 = hash_futex(&key1);
	hb2 = hash_futex(&key2);

	if (hb1 < hb2)
		spin_lock(&hb1->lock);
	spin_lock(&hb2->lock);
	if (hb1 > hb2)
		spin_lock(&hb1->lock);

	if (likely(cmpval != NULL)) {
		u32 curval;

		ret = get_futex_value_locked(&curval, uaddr1);

		if (unlikely(ret)) {
			spin_unlock(&hb1->lock);
			if (hb1 != hb2)
				spin_unlock(&hb2->lock);

			/*
			 * If we would have faulted, release mmap_sem, fault
			 * it in and start all over again.
			 */
			up_read(&current->mm->mmap_sem);

			ret = get_user(curval, uaddr1);

			if (!ret)
				goto retry;

			return ret;
		}
		if (curval != *cmpval) {
			ret = -EAGAIN;
			goto out_unlock;
		}
	}

	head1 = &hb1->chain;
	list_for_each_entry_safe(this, next, head1, list) {
		if (!match_futex (&this->key, &key1))
			continue;
		if (++ret <= nr_wake) {
			wake_futex(this);
		} else {
			list_move_tail(&this->list, &hb2->chain);
			this->lock_ptr = &hb2->lock;
			this->key = key2;
			get_key_refs(&key2);
			drop_count++;

			if (ret - nr_wake >= nr_requeue)
				break;
			/* Make sure to stop if key1 == key2: */
			if (head1 == &hb2->chain && head1 != &next->list)
				head1 = &this->list;
		}
	}

out_unlock:
	spin_unlock(&hb1->lock);
	if (hb1 != hb2)
		spin_unlock(&hb2->lock);

	/* drop_key_refs() must be called outside the spinlocks. */
	while (--drop_count >= 0)
		drop_key_refs(&key1);

out:
	up_read(&current->mm->mmap_sem);
	return ret;
}

/* The key must be already stored in q->key. */
static inline struct futex_hash_bucket *
queue_lock(struct futex_q *q, int fd, struct file *filp)
{
	struct futex_hash_bucket *hb;

	q->fd = fd;
	q->filp = filp;

	init_waitqueue_head(&q->waiters);

	get_key_refs(&q->key);
	hb = hash_futex(&q->key);
	q->lock_ptr = &hb->lock;

	spin_lock(&hb->lock);
	return hb;
}

static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
{
	list_add_tail(&q->list, &hb->chain);
	spin_unlock(&hb->lock);
}

static inline void
queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
{
	spin_unlock(&hb->lock);
	drop_key_refs(&q->key);
}

/*
 * queue_me and unqueue_me must be called as a pair, each
 * exactly once.  They are called with the hashed spinlock held.
 */

/* The key must be already stored in q->key. */
static void queue_me(struct futex_q *q, int fd, struct file *filp)
{
	struct futex_hash_bucket *hb;

	hb = queue_lock(q, fd, filp);
	__queue_me(q, hb);
}

/* Return 1 if we were still queued (ie. 0 means we were woken) */
static int unqueue_me(struct futex_q *q)
{
	spinlock_t *lock_ptr;
	int ret = 0;

	/* In the common case we don't take the spinlock, which is nice. */
 retry:
	lock_ptr = q->lock_ptr;
	if (lock_ptr != 0) {
		spin_lock(lock_ptr);
		/*
		 * q->lock_ptr can change between reading it and
		 * spin_lock(), causing us to take the wrong lock.  This
		 * corrects the race condition.
		 *
		 * Reasoning goes like this: if we have the wrong lock,
		 * q->lock_ptr must have changed (maybe several times)
		 * between reading it and the spin_lock().  It can
		 * change again after the spin_lock() but only if it was
		 * already changed before the spin_lock().  It cannot,
		 * however, change back to the original value.  Therefore
		 * we can detect whether we acquired the correct lock.
		 */
		if (unlikely(lock_ptr != q->lock_ptr)) {
			spin_unlock(lock_ptr);
			goto retry;
		}
		WARN_ON(list_empty(&q->list));
		list_del(&q->list);
		spin_unlock(lock_ptr);
		ret = 1;
	}

	drop_key_refs(&q->key);
	return ret;
}

static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
{
	DECLARE_WAITQUEUE(wait, current);
	struct futex_hash_bucket *hb;
	struct futex_q q;
	u32 uval;
	int ret;

 retry:
	down_read(&current->mm->mmap_sem);

	ret = get_futex_key(uaddr, &q.key);
	if (unlikely(ret != 0))
		goto out_release_sem;

	hb = queue_lock(&q, -1, NULL);

	/*
	 * Access the page AFTER the futex is queued.
	 * Order is important:
	 *
	 *   Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
	 *   Userspace waker:  if (cond(var)) { var = new; futex_wake(&var); }
	 *
	 * The basic logical guarantee of a futex is that it blocks ONLY
	 * if cond(var) is known to be true at the time of blocking, for
	 * any cond.  If we queued after testing *uaddr, that would open
	 * a race condition where we could block indefinitely with
	 * cond(var) false, which would violate the guarantee.
	 *
	 * A consequence is that futex_wait() can return zero and absorb
	 * a wakeup when *uaddr != val on entry to the syscall.  This is
	 * rare, but normal.
	 *
	 * We hold the mmap semaphore, so the mapping cannot have changed
	 * since we looked it up in get_futex_key.
	 */
	ret = get_futex_value_locked(&uval, uaddr);

	if (unlikely(ret)) {
		queue_unlock(&q, hb);

		/*
		 * If we would have faulted, release mmap_sem, fault it in and
		 * start all over again.
		 */
		up_read(&current->mm->mmap_sem);

		ret = get_user(uval, uaddr);

		if (!ret)
			goto retry;
		return ret;
	}
	if (uval != val) {
		ret = -EWOULDBLOCK;
		queue_unlock(&q, hb);
		goto out_release_sem;
	}

	/* Only actually queue if *uaddr contained val.  */
	__queue_me(&q, hb);

	/*
	 * Now the futex is queued and we have checked the data, we
	 * don't want to hold mmap_sem while we sleep.
	 */	
	up_read(&current->mm->mmap_sem);

	/*
	 * There might have been scheduling since the queue_me(), as we
	 * cannot hold a spinlock across the get_user() in case it
	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
	 * queueing ourselves into the futex hash.  This code thus has to
	 * rely on the futex_wake() code removing us from hash when it
	 * wakes us up.
	 */

	/* add_wait_queue is the barrier after __set_current_state. */
	__set_current_state(TASK_INTERRUPTIBLE);
	add_wait_queue(&q.waiters, &wait);
	/*
	 * !list_empty() is safe here without any lock.
	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
	 */
	if (likely(!list_empty(&q.list)))
		time = schedule_timeout(time);
	__set_current_state(TASK_RUNNING);

	/*
	 * NOTE: we don't remove ourselves from the waitqueue because
	 * we are the only user of it.
	 */

	/* If we were woken (and unqueued), we succeeded, whatever. */
	if (!unqueue_me(&q))
		return 0;
	if (time == 0)
		return -ETIMEDOUT;
	/*
	 * We expect signal_pending(current), but another thread may
	 * have handled it for us already.
	 */
	return -EINTR;

 out_release_sem:
	up_read(&current->mm->mmap_sem);
	return ret;
}

static int futex_close(struct inode *inode, struct file *filp)
{
	struct futex_q *q = filp->private_data;

	unqueue_me(q);
	kfree(q);

	return 0;
}

/* This is one-shot: once it's gone off you need a new fd */
static unsigned int futex_poll(struct file *filp,
			       struct poll_table_struct *wait)
{
	struct futex_q *q = filp->private_data;
	int ret = 0;

	poll_wait(filp, &q->waiters, wait);

	/*
	 * list_empty() is safe here without any lock.
	 * q->lock_ptr != 0 is not safe, because of ordering against wakeup.
	 */
	if (list_empty(&q->list))
		ret = POLLIN | POLLRDNORM;

	return ret;
}

static struct file_operations futex_fops = {
	.release	= futex_close,
	.poll		= futex_poll,
};

/*
 * Signal allows caller to avoid the race which would occur if they
 * set the sigio stuff up afterwards.
 */
static int futex_fd(u32 __user *uaddr, int signal)
{
	struct futex_q *q;
	struct file *filp;
	int ret, err;

	ret = -EINVAL;
	if (!valid_signal(signal))
		goto out;

	ret = get_unused_fd();
	if (ret < 0)
		goto out;
	filp = get_empty_filp();
	if (!filp) {
		put_unused_fd(ret);
		ret = -ENFILE;
		goto out;
	}
	filp->f_op = &futex_fops;
	filp->f_vfsmnt = mntget(futex_mnt);
	filp->f_dentry = dget(futex_mnt->mnt_root);
	filp->f_mapping = filp->f_dentry->d_inode->i_mapping;

	if (signal) {
		err = f_setown(filp, current->pid, 1);
		if (err < 0) {
			goto error;
		}
		filp->f_owner.signum = signal;
	}

	q = kmalloc(sizeof(*q), GFP_KERNEL);
	if (!q) {
		err = -ENOMEM;
		goto error;
	}

	down_read(&current->mm->mmap_sem);
	err = get_futex_key(uaddr, &q->key);

	if (unlikely(err != 0)) {
		up_read(&current->mm->mmap_sem);
		kfree(q);
		goto error;
	}

	/*
	 * queue_me() must be called before releasing mmap_sem, because
	 * key->shared.inode needs to be referenced while holding it.
	 */
	filp->private_data = q;

	queue_me(q, ret, filp);
	up_read(&current->mm->mmap_sem);

	/* Now we map fd to filp, so userspace can access it */
	fd_install(ret, filp);
out:
	return ret;
error:
	put_unused_fd(ret);
	put_filp(filp);
	ret = err;
	goto out;
}

/*
 * Support for robust futexes: the kernel cleans up held futexes at
 * thread exit time.
 *
 * Implementation: user-space maintains a per-thread list of locks it
 * is holding. Upon do_exit(), the kernel carefully walks this list,
 * and marks all locks that are owned by this thread with the
 * FUTEX_OWNER_DEAD bit, and wakes up a waiter (if any). The list is
 * always manipulated with the lock held, so the list is private and
 * per-thread. Userspace also maintains a per-thread 'list_op_pending'
 * field, to allow the kernel to clean up if the thread dies after
 * acquiring the lock, but just before it could have added itself to
 * the list. There can only be one such pending lock.
 */

/**
 * sys_set_robust_list - set the robust-futex list head of a task
 * @head: pointer to the list-head
 * @len: length of the list-head, as userspace expects
 */
asmlinkage long
sys_set_robust_list(struct robust_list_head __user *head,
		    size_t len)
{
	/*
	 * The kernel knows only one size for now:
	 */
	if (unlikely(len != sizeof(*head)))
		return -EINVAL;

	current->robust_list = head;

	return 0;
}

/**
 * sys_get_robust_list - get the robust-futex list head of a task
 * @pid: pid of the process [zero for current task]
 * @head_ptr: pointer to a list-head pointer, the kernel fills it in
 * @len_ptr: pointer to a length field, the kernel fills in the header size
 */
asmlinkage long
sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
		    size_t __user *len_ptr)
{
	struct robust_list_head *head;
	unsigned long ret;

	if (!pid)
		head = current->robust_list;
	else {
		struct task_struct *p;

		ret = -ESRCH;
		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);
		if (!p)
			goto err_unlock;
		ret = -EPERM;
		if ((current->euid != p->euid) && (current->euid != p->uid) &&
				!capable(CAP_SYS_PTRACE))
			goto err_unlock;
		head = p->robust_list;
		read_unlock(&tasklist_lock);
	}

	if (put_user(sizeof(*head), len_ptr))
		return -EFAULT;
	return put_user(head, head_ptr);

err_unlock:
	read_unlock(&tasklist_lock);

	return ret;
}

/*
 * Process a futex-list entry, check whether it's owned by the
 * dying task, and do notification if so:
 */
int handle_futex_death(u32 __user *uaddr, struct task_struct *curr)
{
	u32 uval;

retry:
	if (get_user(uval, uaddr))
		return -1;

	if ((uval & FUTEX_TID_MASK) == curr->pid) {
		/*
		 * Ok, this dying thread is truly holding a futex
		 * of interest. Set the OWNER_DIED bit atomically
		 * via cmpxchg, and if the value had FUTEX_WAITERS
		 * set, wake up a waiter (if any). (We have to do a
		 * futex_wake() even if OWNER_DIED is already set -
		 * to handle the rare but possible case of recursive
		 * thread-death.) The rest of the cleanup is done in
		 * userspace.
		 */
		if (futex_atomic_cmpxchg_inatomic(uaddr, uval,
					 uval | FUTEX_OWNER_DIED) != uval)
			goto retry;

		if (uval & FUTEX_WAITERS)
			futex_wake(uaddr, 1);
	}
	return 0;
}

/*
 * Walk curr->robust_list (very carefully, it's a userspace list!)
 * and mark any locks found there dead, and notify any waiters.
 *
 * We silently return on any sign of list-walking problem.
 */
void exit_robust_list(struct task_struct *curr)
{
	struct robust_list_head __user *head = curr->robust_list;
	struct robust_list __user *entry, *pending;
	unsigned int limit = ROBUST_LIST_LIMIT;
	unsigned long futex_offset;

	/*
	 * Fetch the list head (which was registered earlier, via
	 * sys_set_robust_list()):
	 */
	if (get_user(entry, &head->list.next))
		return;
	/*
	 * Fetch the relative futex offset:
	 */
	if (get_user(futex_offset, &head->futex_offset))
		return;
	/*
	 * Fetch any possibly pending lock-add first, and handle it
	 * if it exists:
	 */
	if (get_user(pending, &head->list_op_pending))
		return;
	if (pending)
		handle_futex_death((void *)pending + futex_offset, curr);

	while (entry != &head->list) {
		/*
		 * A pending lock might already be on the list, so
		 * dont process it twice:
		 */
		if (entry != pending)
			if (handle_futex_death((void *)entry + futex_offset,
						curr))
				return;
		/*
		 * Fetch the next entry in the list:
		 */
		if (get_user(entry, &entry->next))
			return;
		/*
		 * Avoid excessively long or circular lists:
		 */
		if (!--limit)
			break;

		cond_resched();
	}
}

long do_futex(u32 __user *uaddr, int op, u32 val, unsigned long timeout,
		u32 __user *uaddr2, u32 val2, u32 val3)
{
	int ret;

	switch (op) {
	case FUTEX_WAIT:
		ret = futex_wait(uaddr, val, timeout);
		break;
	case FUTEX_WAKE:
		ret = futex_wake(uaddr, val);
		break;
	case FUTEX_FD:
		/* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */
		ret = futex_fd(uaddr, val);
		break;
	case FUTEX_REQUEUE:
		ret = futex_requeue(uaddr, uaddr2, val, val2, NULL);
		break;
	case FUTEX_CMP_REQUEUE:
		ret = futex_requeue(uaddr, uaddr2, val, val2, &val3);
		break;
	case FUTEX_WAKE_OP:
		ret = futex_wake_op(uaddr, uaddr2, val, val2, val3);
		break;
	default:
		ret = -ENOSYS;
	}
	return ret;
}


asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
			  struct timespec __user *utime, u32 __user *uaddr2,
			  u32 val3)
{
	struct timespec t;
	unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
	u32 val2 = 0;

	if (utime && (op == FUTEX_WAIT)) {
		if (copy_from_user(&t, utime, sizeof(t)) != 0)
			return -EFAULT;
		if (!timespec_valid(&t))
			return -EINVAL;
		timeout = timespec_to_jiffies(&t) + 1;
	}
	/*
	 * requeue parameter in 'utime' if op == FUTEX_REQUEUE.
	 */
	if (op >= FUTEX_REQUEUE)
		val2 = (u32) (unsigned long) utime;

	return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);
}

static int futexfs_get_sb(struct file_system_type *fs_type,
			  int flags, const char *dev_name, void *data,
			  struct vfsmount *mnt)
{
	return get_sb_pseudo(fs_type, "futex", NULL, 0xBAD1DEA, mnt);
}

static struct file_system_type futex_fs_type = {
	.name		= "futexfs",
	.get_sb		= futexfs_get_sb,
	.kill_sb	= kill_anon_super,
};

static int __init init(void)
{
	unsigned int i;

	register_filesystem(&futex_fs_type);
	futex_mnt = kern_mount(&futex_fs_type);

	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
		INIT_LIST_HEAD(&futex_queues[i].chain);
		spin_lock_init(&futex_queues[i].lock);
	}
	return 0;
}
__initcall(init);