aboutsummaryrefslogtreecommitdiffstats
path: root/fs/eventpoll.c
blob: aec5c13f634177bab34f108e9f4891e300b873a3 (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
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
/*
 *  fs/eventpoll.c (Efficent event polling implementation)
 *  Copyright (C) 2001,...,2007	 Davide Libenzi
 *
 *  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.
 *
 *  Davide Libenzi <davidel@xmailserver.org>
 *
 */

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <asm/atomic.h>

/*
 * LOCKING:
 * There are three level of locking required by epoll :
 *
 * 1) epmutex (mutex)
 * 2) ep->mtx (mutex)
 * 3) ep->lock (spinlock)
 *
 * The acquire order is the one listed above, from 1 to 3.
 * We need a spinlock (ep->lock) because we manipulate objects
 * from inside the poll callback, that might be triggered from
 * a wake_up() that in turn might be called from IRQ context.
 * So we can't sleep inside the poll callback and hence we need
 * a spinlock. During the event transfer loop (from kernel to
 * user space) we could end up sleeping due a copy_to_user(), so
 * we need a lock that will allow us to sleep. This lock is a
 * mutex (ep->mtx). It is acquired during the event transfer loop,
 * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
 * Then we also need a global mutex to serialize eventpoll_release_file()
 * and ep_free().
 * This mutex is acquired by ep_free() during the epoll file
 * cleanup path and it is also acquired by eventpoll_release_file()
 * if a file has been pushed inside an epoll set and it is then
 * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
 * It is possible to drop the "ep->mtx" and to use the global
 * mutex "epmutex" (together with "ep->lock") to have it working,
 * but having "ep->mtx" will make the interface more scalable.
 * Events that require holding "epmutex" are very rare, while for
 * normal operations the epoll private "ep->mtx" will guarantee
 * a better scalability.
 */

#define DEBUG_EPOLL 0

#if DEBUG_EPOLL > 0
#define DPRINTK(x) printk x
#define DNPRINTK(n, x) do { if ((n) <= DEBUG_EPOLL) printk x; } while (0)
#else /* #if DEBUG_EPOLL > 0 */
#define DPRINTK(x) (void) 0
#define DNPRINTK(n, x) (void) 0
#endif /* #if DEBUG_EPOLL > 0 */

#define DEBUG_EPI 0

#if DEBUG_EPI != 0
#define EPI_SLAB_DEBUG (SLAB_DEBUG_FREE | SLAB_RED_ZONE /* | SLAB_POISON */)
#else /* #if DEBUG_EPI != 0 */
#define EPI_SLAB_DEBUG 0
#endif /* #if DEBUG_EPI != 0 */

/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)

/* Maximum number of poll wake up nests we are allowing */
#define EP_MAX_POLLWAKE_NESTS 4

/* Maximum msec timeout value storeable in a long int */
#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ)

#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))

#define EP_UNACTIVE_PTR ((void *) -1L)

struct epoll_filefd {
	struct file *file;
	int fd;
};

/*
 * Node that is linked into the "wake_task_list" member of the "struct poll_safewake".
 * It is used to keep track on all tasks that are currently inside the wake_up() code
 * to 1) short-circuit the one coming from the same task and same wait queue head
 * (loop) 2) allow a maximum number of epoll descriptors inclusion nesting
 * 3) let go the ones coming from other tasks.
 */
struct wake_task_node {
	struct list_head llink;
	struct task_struct *task;
	wait_queue_head_t *wq;
};

/*
 * This is used to implement the safe poll wake up avoiding to reenter
 * the poll callback from inside wake_up().
 */
struct poll_safewake {
	struct list_head wake_task_list;
	spinlock_t lock;
};

/*
 * Each file descriptor added to the eventpoll interface will
 * have an entry of this type linked to the "rbr" RB tree.
 */
struct epitem {
	/* RB tree node used to link this structure to the eventpoll RB tree */
	struct rb_node rbn;

	/* List header used to link this structure to the eventpoll ready list */
	struct list_head rdllink;

	/*
	 * Works together "struct eventpoll"->ovflist in keeping the
	 * single linked chain of items.
	 */
	struct epitem *next;

	/* The file descriptor information this item refers to */
	struct epoll_filefd ffd;

	/* Number of active wait queue attached to poll operations */
	int nwait;

	/* List containing poll wait queues */
	struct list_head pwqlist;

	/* The "container" of this item */
	struct eventpoll *ep;

	/* List header used to link this item to the "struct file" items list */
	struct list_head fllink;

	/* The structure that describe the interested events and the source fd */
	struct epoll_event event;
};

/*
 * This structure is stored inside the "private_data" member of the file
 * structure and rapresent the main data sructure for the eventpoll
 * interface.
 */
struct eventpoll {
	/* Protect the this structure access */
	spinlock_t lock;

	/*
	 * This mutex is used to ensure that files are not removed
	 * while epoll is using them. This is held during the event
	 * collection loop, the file cleanup path, the epoll file exit
	 * code and the ctl operations.
	 */
	struct mutex mtx;

	/* Wait queue used by sys_epoll_wait() */
	wait_queue_head_t wq;

	/* Wait queue used by file->poll() */
	wait_queue_head_t poll_wait;

	/* List of ready file descriptors */
	struct list_head rdllist;

	/* RB tree root used to store monitored fd structs */
	struct rb_root rbr;

	/*
	 * This is a single linked list that chains all the "struct epitem" that
	 * happened while transfering ready events to userspace w/out
	 * holding ->lock.
	 */
	struct epitem *ovflist;
};

/* Wait structure used by the poll hooks */
struct eppoll_entry {
	/* List header used to link this structure to the "struct epitem" */
	struct list_head llink;

	/* The "base" pointer is set to the container "struct epitem" */
	void *base;

	/*
	 * Wait queue item that will be linked to the target file wait
	 * queue head.
	 */
	wait_queue_t wait;

	/* The wait queue head that linked the "wait" wait queue item */
	wait_queue_head_t *whead;
};

/* Wrapper struct used by poll queueing */
struct ep_pqueue {
	poll_table pt;
	struct epitem *epi;
};

/*
 * This mutex is used to serialize ep_free() and eventpoll_release_file().
 */
static struct mutex epmutex;

/* Safe wake up implementation */
static struct poll_safewake psw;

/* Slab cache used to allocate "struct epitem" */
static struct kmem_cache *epi_cache __read_mostly;

/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;


/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
			      struct file *file, int fd)
{
	ffd->file = file;
	ffd->fd = fd;
}

/* Compare RB tree keys */
static inline int ep_cmp_ffd(struct epoll_filefd *p1,
			     struct epoll_filefd *p2)
{
	return (p1->file > p2->file ? +1:
	        (p1->file < p2->file ? -1 : p1->fd - p2->fd));
}

/* Tells us if the item is currently linked */
static inline int ep_is_linked(struct list_head *p)
{
	return !list_empty(p);
}

/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
{
	return container_of(p, struct eppoll_entry, wait)->base;
}

/* Get the "struct epitem" from an epoll queue wrapper */
static inline struct epitem *ep_item_from_epqueue(poll_table *p)
{
	return container_of(p, struct ep_pqueue, pt)->epi;
}

/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
static inline int ep_op_has_event(int op)
{
	return op != EPOLL_CTL_DEL;
}

/* Initialize the poll safe wake up structure */
static void ep_poll_safewake_init(struct poll_safewake *psw)
{

	INIT_LIST_HEAD(&psw->wake_task_list);
	spin_lock_init(&psw->lock);
}

/*
 * Perform a safe wake up of the poll wait list. The problem is that
 * with the new callback'd wake up system, it is possible that the
 * poll callback is reentered from inside the call to wake_up() done
 * on the poll wait queue head. The rule is that we cannot reenter the
 * wake up code from the same task more than EP_MAX_POLLWAKE_NESTS times,
 * and we cannot reenter the same wait queue head at all. This will
 * enable to have a hierarchy of epoll file descriptor of no more than
 * EP_MAX_POLLWAKE_NESTS deep. We need the irq version of the spin lock
 * because this one gets called by the poll callback, that in turn is called
 * from inside a wake_up(), that might be called from irq context.
 */
static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq)
{
	int wake_nests = 0;
	unsigned long flags;
	struct task_struct *this_task = current;
	struct list_head *lsthead = &psw->wake_task_list;
	struct wake_task_node *tncur;
	struct wake_task_node tnode;

	spin_lock_irqsave(&psw->lock, flags);

	/* Try to see if the current task is already inside this wakeup call */
	list_for_each_entry(tncur, lsthead, llink) {

		if (tncur->wq == wq ||
		    (tncur->task == this_task && ++wake_nests > EP_MAX_POLLWAKE_NESTS)) {
			/*
			 * Ops ... loop detected or maximum nest level reached.
			 * We abort this wake by breaking the cycle itself.
			 */
			spin_unlock_irqrestore(&psw->lock, flags);
			return;
		}
	}

	/* Add the current task to the list */
	tnode.task = this_task;
	tnode.wq = wq;
	list_add(&tnode.llink, lsthead);

	spin_unlock_irqrestore(&psw->lock, flags);

	/* Do really wake up now */
	wake_up_nested(wq, 1 + wake_nests);

	/* Remove the current task from the list */
	spin_lock_irqsave(&psw->lock, flags);
	list_del(&tnode.llink);
	spin_unlock_irqrestore(&psw->lock, flags);
}

/*
 * This function unregister poll callbacks from the associated file descriptor.
 * Since this must be called without holding "ep->lock" the atomic exchange trick
 * will protect us from multiple unregister.
 */
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
	int nwait;
	struct list_head *lsthead = &epi->pwqlist;
	struct eppoll_entry *pwq;

	/* This is called without locks, so we need the atomic exchange */
	nwait = xchg(&epi->nwait, 0);

	if (nwait) {
		while (!list_empty(lsthead)) {
			pwq = list_first_entry(lsthead, struct eppoll_entry, llink);

			list_del_init(&pwq->llink);
			remove_wait_queue(pwq->whead, &pwq->wait);
			kmem_cache_free(pwq_cache, pwq);
		}
	}
}

/*
 * Removes a "struct epitem" from the eventpoll RB tree and deallocates
 * all the associated resources. Must be called with "mtx" held.
 */
static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
	unsigned long flags;
	struct file *file = epi->ffd.file;

	/*
	 * Removes poll wait queue hooks. We _have_ to do this without holding
	 * the "ep->lock" otherwise a deadlock might occur. This because of the
	 * sequence of the lock acquisition. Here we do "ep->lock" then the wait
	 * queue head lock when unregistering the wait queue. The wakeup callback
	 * will run by holding the wait queue head lock and will call our callback
	 * that will try to get "ep->lock".
	 */
	ep_unregister_pollwait(ep, epi);

	/* Remove the current item from the list of epoll hooks */
	spin_lock(&file->f_ep_lock);
	if (ep_is_linked(&epi->fllink))
		list_del_init(&epi->fllink);
	spin_unlock(&file->f_ep_lock);

	rb_erase(&epi->rbn, &ep->rbr);

	spin_lock_irqsave(&ep->lock, flags);
	if (ep_is_linked(&epi->rdllink))
		list_del_init(&epi->rdllink);
	spin_unlock_irqrestore(&ep->lock, flags);

	/* At this point it is safe to free the eventpoll item */
	kmem_cache_free(epi_cache, epi);

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p)\n",
		     current, ep, file));

	return 0;
}

static void ep_free(struct eventpoll *ep)
{
	struct rb_node *rbp;
	struct epitem *epi;

	/* We need to release all tasks waiting for these file */
	if (waitqueue_active(&ep->poll_wait))
		ep_poll_safewake(&psw, &ep->poll_wait);

	/*
	 * We need to lock this because we could be hit by
	 * eventpoll_release_file() while we're freeing the "struct eventpoll".
	 * We do not need to hold "ep->mtx" here because the epoll file
	 * is on the way to be removed and no one has references to it
	 * anymore. The only hit might come from eventpoll_release_file() but
	 * holding "epmutex" is sufficent here.
	 */
	mutex_lock(&epmutex);

	/*
	 * Walks through the whole tree by unregistering poll callbacks.
	 */
	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
		epi = rb_entry(rbp, struct epitem, rbn);

		ep_unregister_pollwait(ep, epi);
	}

	/*
	 * Walks through the whole tree by freeing each "struct epitem". At this
	 * point we are sure no poll callbacks will be lingering around, and also by
	 * holding "epmutex" we can be sure that no file cleanup code will hit
	 * us during this operation. So we can avoid the lock on "ep->lock".
	 */
	while ((rbp = rb_first(&ep->rbr)) != NULL) {
		epi = rb_entry(rbp, struct epitem, rbn);
		ep_remove(ep, epi);
	}

	mutex_unlock(&epmutex);
	mutex_destroy(&ep->mtx);
	kfree(ep);
}

static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
	struct eventpoll *ep = file->private_data;

	if (ep)
		ep_free(ep);

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
	return 0;
}

static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
	unsigned int pollflags = 0;
	unsigned long flags;
	struct eventpoll *ep = file->private_data;

	/* Insert inside our poll wait queue */
	poll_wait(file, &ep->poll_wait, wait);

	/* Check our condition */
	spin_lock_irqsave(&ep->lock, flags);
	if (!list_empty(&ep->rdllist))
		pollflags = POLLIN | POLLRDNORM;
	spin_unlock_irqrestore(&ep->lock, flags);

	return pollflags;
}

/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
	.release	= ep_eventpoll_release,
	.poll		= ep_eventpoll_poll
};

/* Fast test to see if the file is an evenpoll file */
static inline int is_file_epoll(struct file *f)
{
	return f->f_op == &eventpoll_fops;
}

/*
 * This is called from eventpoll_release() to unlink files from the eventpoll
 * interface. We need to have this facility to cleanup correctly files that are
 * closed without being removed from the eventpoll interface.
 */
void eventpoll_release_file(struct file *file)
{
	struct list_head *lsthead = &file->f_ep_links;
	struct eventpoll *ep;
	struct epitem *epi;

	/*
	 * We don't want to get "file->f_ep_lock" because it is not
	 * necessary. It is not necessary because we're in the "struct file"
	 * cleanup path, and this means that noone is using this file anymore.
	 * So, for example, epoll_ctl() cannot hit here sicne if we reach this
	 * point, the file counter already went to zero and fget() would fail.
	 * The only hit might come from ep_free() but by holding the mutex
	 * will correctly serialize the operation. We do need to acquire
	 * "ep->mtx" after "epmutex" because ep_remove() requires it when called
	 * from anywhere but ep_free().
	 */
	mutex_lock(&epmutex);

	while (!list_empty(lsthead)) {
		epi = list_first_entry(lsthead, struct epitem, fllink);

		ep = epi->ep;
		list_del_init(&epi->fllink);
		mutex_lock(&ep->mtx);
		ep_remove(ep, epi);
		mutex_unlock(&ep->mtx);
	}

	mutex_unlock(&epmutex);
}

static int ep_alloc(struct eventpoll **pep)
{
	struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);

	if (!ep)
		return -ENOMEM;

	spin_lock_init(&ep->lock);
	mutex_init(&ep->mtx);
	init_waitqueue_head(&ep->wq);
	init_waitqueue_head(&ep->poll_wait);
	INIT_LIST_HEAD(&ep->rdllist);
	ep->rbr = RB_ROOT;
	ep->ovflist = EP_UNACTIVE_PTR;

	*pep = ep;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
		     current, ep));
	return 0;
}

/*
 * Search the file inside the eventpoll tree. The RB tree operations
 * are protected by the "mtx" mutex, and ep_find() must be called with
 * "mtx" held.
 */
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
	int kcmp;
	struct rb_node *rbp;
	struct epitem *epi, *epir = NULL;
	struct epoll_filefd ffd;

	ep_set_ffd(&ffd, file, fd);
	for (rbp = ep->rbr.rb_node; rbp; ) {
		epi = rb_entry(rbp, struct epitem, rbn);
		kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
		if (kcmp > 0)
			rbp = rbp->rb_right;
		else if (kcmp < 0)
			rbp = rbp->rb_left;
		else {
			epir = epi;
			break;
		}
	}

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_find(%p) -> %p\n",
		     current, file, epir));

	return epir;
}

/*
 * This is the callback that is passed to the wait queue wakeup
 * machanism. It is called by the stored file descriptors when they
 * have events to report.
 */
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	int pwake = 0;
	unsigned long flags;
	struct epitem *epi = ep_item_from_wait(wait);
	struct eventpoll *ep = epi->ep;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
		     current, epi->ffd.file, epi, ep));

	spin_lock_irqsave(&ep->lock, flags);

	/*
	 * If the event mask does not contain any poll(2) event, we consider the
	 * descriptor to be disabled. This condition is likely the effect of the
	 * EPOLLONESHOT bit that disables the descriptor when an event is received,
	 * until the next EPOLL_CTL_MOD will be issued.
	 */
	if (!(epi->event.events & ~EP_PRIVATE_BITS))
		goto out_unlock;

	/*
	 * If we are trasfering events to userspace, we can hold no locks
	 * (because we're accessing user memory, and because of linux f_op->poll()
	 * semantics). All the events that happens during that period of time are
	 * chained in ep->ovflist and requeued later on.
	 */
	if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
		if (epi->next == EP_UNACTIVE_PTR) {
			epi->next = ep->ovflist;
			ep->ovflist = epi;
		}
		goto out_unlock;
	}

	/* If this file is already in the ready list we exit soon */
	if (ep_is_linked(&epi->rdllink))
		goto is_linked;

	list_add_tail(&epi->rdllink, &ep->rdllist);

is_linked:
	/*
	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
	 * wait list.
	 */
	if (waitqueue_active(&ep->wq))
		wake_up_locked(&ep->wq);
	if (waitqueue_active(&ep->poll_wait))
		pwake++;

out_unlock:
	spin_unlock_irqrestore(&ep->lock, flags);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&psw, &ep->poll_wait);

	return 1;
}

/*
 * This is the callback that is used to add our wait queue to the
 * target file wakeup lists.
 */
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
				 poll_table *pt)
{
	struct epitem *epi = ep_item_from_epqueue(pt);
	struct eppoll_entry *pwq;

	if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
		init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
		pwq->whead = whead;
		pwq->base = epi;
		add_wait_queue(whead, &pwq->wait);
		list_add_tail(&pwq->llink, &epi->pwqlist);
		epi->nwait++;
	} else {
		/* We have to signal that an error occurred */
		epi->nwait = -1;
	}
}

static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
	int kcmp;
	struct rb_node **p = &ep->rbr.rb_node, *parent = NULL;
	struct epitem *epic;

	while (*p) {
		parent = *p;
		epic = rb_entry(parent, struct epitem, rbn);
		kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
		if (kcmp > 0)
			p = &parent->rb_right;
		else
			p = &parent->rb_left;
	}
	rb_link_node(&epi->rbn, parent, p);
	rb_insert_color(&epi->rbn, &ep->rbr);
}

/*
 * Must be called with "mtx" held.
 */
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
		     struct file *tfile, int fd)
{
	int error, revents, pwake = 0;
	unsigned long flags;
	struct epitem *epi;
	struct ep_pqueue epq;

	error = -ENOMEM;
	if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
		goto error_return;

	/* Item initialization follow here ... */
	INIT_LIST_HEAD(&epi->rdllink);
	INIT_LIST_HEAD(&epi->fllink);
	INIT_LIST_HEAD(&epi->pwqlist);
	epi->ep = ep;
	ep_set_ffd(&epi->ffd, tfile, fd);
	epi->event = *event;
	epi->nwait = 0;
	epi->next = EP_UNACTIVE_PTR;

	/* Initialize the poll table using the queue callback */
	epq.epi = epi;
	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);

	/*
	 * Attach the item to the poll hooks and get current event bits.
	 * We can safely use the file* here because its usage count has
	 * been increased by the caller of this function. Note that after
	 * this operation completes, the poll callback can start hitting
	 * the new item.
	 */
	revents = tfile->f_op->poll(tfile, &epq.pt);

	/*
	 * We have to check if something went wrong during the poll wait queue
	 * install process. Namely an allocation for a wait queue failed due
	 * high memory pressure.
	 */
	if (epi->nwait < 0)
		goto error_unregister;

	/* Add the current item to the list of active epoll hook for this file */
	spin_lock(&tfile->f_ep_lock);
	list_add_tail(&epi->fllink, &tfile->f_ep_links);
	spin_unlock(&tfile->f_ep_lock);

	/*
	 * Add the current item to the RB tree. All RB tree operations are
	 * protected by "mtx", and ep_insert() is called with "mtx" held.
	 */
	ep_rbtree_insert(ep, epi);

	/* We have to drop the new item inside our item list to keep track of it */
	spin_lock_irqsave(&ep->lock, flags);

	/* If the file is already "ready" we drop it inside the ready list */
	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
		list_add_tail(&epi->rdllink, &ep->rdllist);

		/* Notify waiting tasks that events are available */
		if (waitqueue_active(&ep->wq))
			wake_up_locked(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}

	spin_unlock_irqrestore(&ep->lock, flags);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&psw, &ep->poll_wait);

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_insert(%p, %p, %d)\n",
		     current, ep, tfile, fd));

	return 0;

error_unregister:
	ep_unregister_pollwait(ep, epi);

	/*
	 * We need to do this because an event could have been arrived on some
	 * allocated wait queue. Note that we don't care about the ep->ovflist
	 * list, since that is used/cleaned only inside a section bound by "mtx".
	 * And ep_insert() is called with "mtx" held.
	 */
	spin_lock_irqsave(&ep->lock, flags);
	if (ep_is_linked(&epi->rdllink))
		list_del_init(&epi->rdllink);
	spin_unlock_irqrestore(&ep->lock, flags);

	kmem_cache_free(epi_cache, epi);
error_return:
	return error;
}

/*
 * Modify the interest event mask by dropping an event if the new mask
 * has a match in the current file status. Must be called with "mtx" held.
 */
static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event)
{
	int pwake = 0;
	unsigned int revents;
	unsigned long flags;

	/*
	 * Set the new event interest mask before calling f_op->poll(), otherwise
	 * a potential race might occur. In fact if we do this operation inside
	 * the lock, an event might happen between the f_op->poll() call and the
	 * new event set registering.
	 */
	epi->event.events = event->events;

	/*
	 * Get current event bits. We can safely use the file* here because
	 * its usage count has been increased by the caller of this function.
	 */
	revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);

	spin_lock_irqsave(&ep->lock, flags);

	/* Copy the data member from inside the lock */
	epi->event.data = event->data;

	/*
	 * If the item is "hot" and it is not registered inside the ready
	 * list, push it inside.
	 */
	if (revents & event->events) {
		if (!ep_is_linked(&epi->rdllink)) {
			list_add_tail(&epi->rdllink, &ep->rdllist);

			/* Notify waiting tasks that events are available */
			if (waitqueue_active(&ep->wq))
				wake_up_locked(&ep->wq);
			if (waitqueue_active(&ep->poll_wait))
				pwake++;
		}
	}
	spin_unlock_irqrestore(&ep->lock, flags);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&psw, &ep->poll_wait);

	return 0;
}

static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events,
			  int maxevents)
{
	int eventcnt, error = -EFAULT, pwake = 0;
	unsigned int revents;
	unsigned long flags;
	struct epitem *epi, *nepi;
	struct list_head txlist;

	INIT_LIST_HEAD(&txlist);

	/*
	 * We need to lock this because we could be hit by
	 * eventpoll_release_file() and epoll_ctl(EPOLL_CTL_DEL).
	 */
	mutex_lock(&ep->mtx);

	/*
	 * Steal the ready list, and re-init the original one to the
	 * empty list. Also, set ep->ovflist to NULL so that events
	 * happening while looping w/out locks, are not lost. We cannot
	 * have the poll callback to queue directly on ep->rdllist,
	 * because we are doing it in the loop below, in a lockless way.
	 */
	spin_lock_irqsave(&ep->lock, flags);
	list_splice(&ep->rdllist, &txlist);
	INIT_LIST_HEAD(&ep->rdllist);
	ep->ovflist = NULL;
	spin_unlock_irqrestore(&ep->lock, flags);

	/*
	 * We can loop without lock because this is a task private list.
	 * We just splice'd out the ep->rdllist in ep_collect_ready_items().
	 * Items cannot vanish during the loop because we are holding "mtx".
	 */
	for (eventcnt = 0; !list_empty(&txlist) && eventcnt < maxevents;) {
		epi = list_first_entry(&txlist, struct epitem, rdllink);

		list_del_init(&epi->rdllink);

		/*
		 * Get the ready file event set. We can safely use the file
		 * because we are holding the "mtx" and this will guarantee
		 * that both the file and the item will not vanish.
		 */
		revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
		revents &= epi->event.events;

		/*
		 * Is the event mask intersect the caller-requested one,
		 * deliver the event to userspace. Again, we are holding
		 * "mtx", so no operations coming from userspace can change
		 * the item.
		 */
		if (revents) {
			if (__put_user(revents,
				       &events[eventcnt].events) ||
			    __put_user(epi->event.data,
				       &events[eventcnt].data))
				goto errxit;
			if (epi->event.events & EPOLLONESHOT)
				epi->event.events &= EP_PRIVATE_BITS;
			eventcnt++;
		}
		/*
		 * At this point, noone can insert into ep->rdllist besides
		 * us. The epoll_ctl() callers are locked out by us holding
		 * "mtx" and the poll callback will queue them in ep->ovflist.
		 */
		if (!(epi->event.events & EPOLLET) &&
		    (revents & epi->event.events))
			list_add_tail(&epi->rdllink, &ep->rdllist);
	}
	error = 0;

errxit:

	spin_lock_irqsave(&ep->lock, flags);
	/*
	 * During the time we spent in the loop above, some other events
	 * might have been queued by the poll callback. We re-insert them
	 * inside the main ready-list here.
	 */
	for (nepi = ep->ovflist; (epi = nepi) != NULL;
	     nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
		/*
		 * If the above loop quit with errors, the epoll item might still
		 * be linked to "txlist", and the list_splice() done below will
		 * take care of those cases.
		 */
		if (!ep_is_linked(&epi->rdllink))
			list_add_tail(&epi->rdllink, &ep->rdllist);
	}
	/*
	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
	 * releasing the lock, events will be queued in the normal way inside
	 * ep->rdllist.
	 */
	ep->ovflist = EP_UNACTIVE_PTR;

	/*
	 * In case of error in the event-send loop, or in case the number of
	 * ready events exceeds the userspace limit, we need to splice the
	 * "txlist" back inside ep->rdllist.
	 */
	list_splice(&txlist, &ep->rdllist);

	if (!list_empty(&ep->rdllist)) {
		/*
		 * Wake up (if active) both the eventpoll wait list and the ->poll()
		 * wait list (delayed after we release the lock).
		 */
		if (waitqueue_active(&ep->wq))
			wake_up_locked(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}
	spin_unlock_irqrestore(&ep->lock, flags);

	mutex_unlock(&ep->mtx);

	/* We have to call this outside the lock */
	if (pwake)
		ep_poll_safewake(&psw, &ep->poll_wait);

	return eventcnt == 0 ? error: eventcnt;
}

static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
		   int maxevents, long timeout)
{
	int res, eavail;
	unsigned long flags;
	long jtimeout;
	wait_queue_t wait;

	/*
	 * Calculate the timeout by checking for the "infinite" value ( -1 )
	 * and the overflow condition. The passed timeout is in milliseconds,
	 * that why (t * HZ) / 1000.
	 */
	jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ?
		MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;

retry:
	spin_lock_irqsave(&ep->lock, flags);

	res = 0;
	if (list_empty(&ep->rdllist)) {
		/*
		 * We don't have any available event to return to the caller.
		 * We need to sleep here, and we will be wake up by
		 * ep_poll_callback() when events will become available.
		 */
		init_waitqueue_entry(&wait, current);
		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue(&ep->wq, &wait);

		for (;;) {
			/*
			 * We don't want to sleep if the ep_poll_callback() sends us
			 * a wakeup in between. That's why we set the task state
			 * to TASK_INTERRUPTIBLE before doing the checks.
			 */
			set_current_state(TASK_INTERRUPTIBLE);
			if (!list_empty(&ep->rdllist) || !jtimeout)
				break;
			if (signal_pending(current)) {
				res = -EINTR;
				break;
			}

			spin_unlock_irqrestore(&ep->lock, flags);
			jtimeout = schedule_timeout(jtimeout);
			spin_lock_irqsave(&ep->lock, flags);
		}
		__remove_wait_queue(&ep->wq, &wait);

		set_current_state(TASK_RUNNING);
	}

	/* Is it worth to try to dig for events ? */
	eavail = !list_empty(&ep->rdllist);

	spin_unlock_irqrestore(&ep->lock, flags);

	/*
	 * Try to transfer events to user space. In case we get 0 events and
	 * there's still timeout left over, we go trying again in search of
	 * more luck.
	 */
	if (!res && eavail &&
	    !(res = ep_send_events(ep, events, maxevents)) && jtimeout)
		goto retry;

	return res;
}

/*
 * Open an eventpoll file descriptor.
 */
asmlinkage long sys_epoll_create1(int flags)
{
	int error, fd = -1;
	struct eventpoll *ep;

	/* Check the EPOLL_* constant for consistency.  */
	BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);

	if (flags & ~EPOLL_CLOEXEC)
		return -EINVAL;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
		     current, flags));

	/*
	 * Create the internal data structure ( "struct eventpoll" ).
	 */
	error = ep_alloc(&ep);
	if (error < 0) {
		fd = error;
		goto error_return;
	}

	/*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure and a free file descriptor.
	 */
	fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
			      flags & O_CLOEXEC);
	if (fd < 0)
		ep_free(ep);

error_return:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
		     current, flags, fd));

	return fd;
}

asmlinkage long sys_epoll_create(int size)
{
	if (size < 0)
		return -EINVAL;

	return sys_epoll_create1(0);
}

/*
 * The following function implements the controller interface for
 * the eventpoll file that enables the insertion/removal/change of
 * file descriptors inside the interest set.
 */
asmlinkage long sys_epoll_ctl(int epfd, int op, int fd,
			      struct epoll_event __user *event)
{
	int error;
	struct file *file, *tfile;
	struct eventpoll *ep;
	struct epitem *epi;
	struct epoll_event epds;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
		     current, epfd, op, fd, event));

	error = -EFAULT;
	if (ep_op_has_event(op) &&
	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
		goto error_return;

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto error_return;

	/* Get the "struct file *" for the target file */
	tfile = fget(fd);
	if (!tfile)
		goto error_fput;

	/* The target file descriptor must support poll */
	error = -EPERM;
	if (!tfile->f_op || !tfile->f_op->poll)
		goto error_tgt_fput;

	/*
	 * We have to check that the file structure underneath the file descriptor
	 * the user passed to us _is_ an eventpoll file. And also we do not permit
	 * adding an epoll file descriptor inside itself.
	 */
	error = -EINVAL;
	if (file == tfile || !is_file_epoll(file))
		goto error_tgt_fput;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = file->private_data;

	mutex_lock(&ep->mtx);

	/*
	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
	 * above, we can be sure to be able to use the item looked up by
	 * ep_find() till we release the mutex.
	 */
	epi = ep_find(ep, tfile, fd);

	error = -EINVAL;
	switch (op) {
	case EPOLL_CTL_ADD:
		if (!epi) {
			epds.events |= POLLERR | POLLHUP;

			error = ep_insert(ep, &epds, tfile, fd);
		} else
			error = -EEXIST;
		break;
	case EPOLL_CTL_DEL:
		if (epi)
			error = ep_remove(ep, epi);
		else
			error = -ENOENT;
		break;
	case EPOLL_CTL_MOD:
		if (epi) {
			epds.events |= POLLERR | POLLHUP;
			error = ep_modify(ep, epi, &epds);
		} else
			error = -ENOENT;
		break;
	}
	mutex_unlock(&ep->mtx);

error_tgt_fput:
	fput(tfile);
error_fput:
	fput(file);
error_return:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
		     current, epfd, op, fd, event, error));

	return error;
}

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_wait(2).
 */
asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
			       int maxevents, int timeout)
{
	int error;
	struct file *file;
	struct eventpoll *ep;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
		     current, epfd, events, maxevents, timeout));

	/* The maximum number of event must be greater than zero */
	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
		return -EINVAL;

	/* Verify that the area passed by the user is writeable */
	if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
		error = -EFAULT;
		goto error_return;
	}

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto error_return;

	/*
	 * We have to check that the file structure underneath the fd
	 * the user passed to us _is_ an eventpoll file.
	 */
	error = -EINVAL;
	if (!is_file_epoll(file))
		goto error_fput;

	/*
	 * At this point it is safe to assume that the "private_data" contains
	 * our own data structure.
	 */
	ep = file->private_data;

	/* Time to fish for events ... */
	error = ep_poll(ep, events, maxevents, timeout);

error_fput:
	fput(file);
error_return:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
		     current, epfd, events, maxevents, timeout, error));

	return error;
}

#ifdef HAVE_SET_RESTORE_SIGMASK

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_pwait(2).
 */
asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
		int maxevents, int timeout, const sigset_t __user *sigmask,
		size_t sigsetsize)
{
	int error;
	sigset_t ksigmask, sigsaved;

	/*
	 * If the caller wants a certain signal mask to be set during the wait,
	 * we apply it here.
	 */
	if (sigmask) {
		if (sigsetsize != sizeof(sigset_t))
			return -EINVAL;
		if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
			return -EFAULT;
		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
	}

	error = sys_epoll_wait(epfd, events, maxevents, timeout);

	/*
	 * If we changed the signal mask, we need to restore the original one.
	 * In case we've got a signal while waiting, we do not restore the
	 * signal mask yet, and we allow do_signal() to deliver the signal on
	 * the way back to userspace, before the signal mask is restored.
	 */
	if (sigmask) {
		if (error == -EINTR) {
			memcpy(&current->saved_sigmask, &sigsaved,
			       sizeof(sigsaved));
			set_restore_sigmask();
		} else
			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
	}

	return error;
}

#endif /* HAVE_SET_RESTORE_SIGMASK */

static int __init eventpoll_init(void)
{
	mutex_init(&epmutex);

	/* Initialize the structure used to perform safe poll wait head wake ups */
	ep_poll_safewake_init(&psw);

	/* Allocates slab cache used to allocate "struct epitem" items */
	epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
			0, SLAB_HWCACHE_ALIGN|EPI_SLAB_DEBUG|SLAB_PANIC,
			NULL);

	/* Allocates slab cache used to allocate "struct eppoll_entry" */
	pwq_cache = kmem_cache_create("eventpoll_pwq",
			sizeof(struct eppoll_entry), 0,
			EPI_SLAB_DEBUG|SLAB_PANIC, NULL);

	return 0;
}
fs_initcall(eventpoll_init);