aboutsummaryrefslogblamecommitdiffstats
path: root/fs/eventpoll.c
blob: 9900e333655aca0e1bd8e29e3905dfcd94e05cc3 (plain) (tree)
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
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
































































































































































































































































































































                                                                                                 
                              


































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































                                                                                                
/*
 *  fs/eventpoll.c ( Efficent event polling implementation )
 *  Copyright (C) 2001,...,2003	 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/module.h>
#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/smp_lock.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <asm/atomic.h>
#include <asm/semaphore.h>


/*
 * LOCKING:
 * There are three level of locking required by epoll :
 *
 * 1) epsem (semaphore)
 * 2) ep->sem (rw_semaphore)
 * 3) ep->lock (rw_lock)
 *
 * 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
 * read-write semaphore (ep->sem). It is acquired on read during
 * the event transfer loop and in write during epoll_ctl(EPOLL_CTL_DEL)
 * and during eventpoll_release_file(). Then we also need a global
 * semaphore to serialize eventpoll_release_file() and ep_free().
 * This semaphore 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->sem" and to use the global
 * semaphore "epsem" (together with "ep->lock") to have it working,
 * but having "ep->sem" will make the interface more scalable.
 * Events that require holding "epsem" are very rare, while for
 * normal operations the epoll private "ep->sem" will guarantee
 * a greater scalability.
 */


#define EVENTPOLLFS_MAGIC 0x03111965 /* My birthday should work for this :) */

#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

/* Macro to allocate a "struct epitem" from the slab cache */
#define EPI_MEM_ALLOC()	(struct epitem *) kmem_cache_alloc(epi_cache, SLAB_KERNEL)

/* Macro to free a "struct epitem" to the slab cache */
#define EPI_MEM_FREE(p) kmem_cache_free(epi_cache, p)

/* Macro to allocate a "struct eppoll_entry" from the slab cache */
#define PWQ_MEM_ALLOC()	(struct eppoll_entry *) kmem_cache_alloc(pwq_cache, SLAB_KERNEL)

/* Macro to free a "struct eppoll_entry" to the slab cache */
#define PWQ_MEM_FREE(p) kmem_cache_free(pwq_cache, p)

/* Fast test to see if the file is an evenpoll file */
#define IS_FILE_EPOLL(f) ((f)->f_op == &eventpoll_fops)

/* Setup the structure that is used as key for the rb-tree */
#define EP_SET_FFD(p, f, d) do { (p)->file = (f); (p)->fd = (d); } while (0)

/* Compare rb-tree keys */
#define EP_CMP_FFD(p1, p2) ((p1)->file > (p2)->file ? +1: \
			    ((p1)->file < (p2)->file ? -1: (p1)->fd - (p2)->fd))

/* Special initialization for the rb-tree node to detect linkage */
#define EP_RB_INITNODE(n) (n)->rb_parent = (n)

/* Removes a node from the rb-tree and marks it for a fast is-linked check */
#define EP_RB_ERASE(n, r) do { rb_erase(n, r); (n)->rb_parent = (n); } while (0)

/* Fast check to verify that the item is linked to the main rb-tree */
#define EP_RB_LINKED(n) ((n)->rb_parent != (n))

/*
 * Remove the item from the list and perform its initialization.
 * This is useful for us because we can test if the item is linked
 * using "EP_IS_LINKED(p)".
 */
#define EP_LIST_DEL(p) do { list_del(p); INIT_LIST_HEAD(p); } while (0)

/* Tells us if the item is currently linked */
#define EP_IS_LINKED(p) (!list_empty(p))

/* Get the "struct epitem" from a wait queue pointer */
#define EP_ITEM_FROM_WAIT(p) ((struct epitem *) container_of(p, struct eppoll_entry, wait)->base)

/* Get the "struct epitem" from an epoll queue wrapper */
#define EP_ITEM_FROM_EPQUEUE(p) (container_of(p, struct ep_pqueue, pt)->epi)

/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
#define EP_OP_HASH_EVENT(op) ((op) != EPOLL_CTL_DEL)


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;
	task_t *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;
};

/*
 * 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 */
	rwlock_t lock;

	/*
	 * This semaphore is used to ensure that files are not removed
	 * while epoll is using them. This is read-held during the event
	 * collection loop and it is write-held during the file cleanup
	 * path, the epoll file exit code and the ctl operations.
	 */
	struct rw_semaphore sem;

	/* 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;
};

/* 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;
};

/*
 * Each file descriptor added to the eventpoll interface will
 * have an entry of this type linked to the hash.
 */
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;

	/* 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;

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

	/*
	 * Used to keep track of the usage count of the structure. This avoids
	 * that the structure will desappear from underneath our processing.
	 */
	atomic_t usecnt;

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

	/* List header used to link the item to the transfer list */
	struct list_head txlink;

	/*
	 * This is used during the collection/transfer of events to userspace
	 * to pin items empty events set.
	 */
	unsigned int revents;
};

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



static void ep_poll_safewake_init(struct poll_safewake *psw);
static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq);
static int ep_getfd(int *efd, struct inode **einode, struct file **efile);
static int ep_file_init(struct file *file);
static void ep_free(struct eventpoll *ep);
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd);
static void ep_use_epitem(struct epitem *epi);
static void ep_release_epitem(struct epitem *epi);
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
				 poll_table *pt);
static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi);
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
		     struct file *tfile, int fd);
static int ep_modify(struct eventpoll *ep, struct epitem *epi,
		     struct epoll_event *event);
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi);
static int ep_unlink(struct eventpoll *ep, struct epitem *epi);
static int ep_remove(struct eventpoll *ep, struct epitem *epi);
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key);
static int ep_eventpoll_close(struct inode *inode, struct file *file);
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait);
static int ep_collect_ready_items(struct eventpoll *ep,
				  struct list_head *txlist, int maxevents);
static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
			  struct epoll_event __user *events);
static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist);
static int ep_events_transfer(struct eventpoll *ep,
			      struct epoll_event __user *events,
			      int maxevents);
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
		   int maxevents, long timeout);
static int eventpollfs_delete_dentry(struct dentry *dentry);
static struct inode *ep_eventpoll_inode(void);
static struct super_block *eventpollfs_get_sb(struct file_system_type *fs_type,
					      int flags, const char *dev_name,
					      void *data);

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

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

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

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

/* Virtual fs used to allocate inodes for eventpoll files */
static struct vfsmount *eventpoll_mnt;

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

/*
 * This is used to register the virtual file system from where
 * eventpoll inodes are allocated.
 */
static struct file_system_type eventpoll_fs_type = {
	.name		= "eventpollfs",
	.get_sb		= eventpollfs_get_sb,
	.kill_sb	= kill_anon_super,
};

/* Very basic directory entry operations for the eventpoll virtual file system */
static struct dentry_operations eventpollfs_dentry_operations = {
	.d_delete	= eventpollfs_delete_dentry,
};



/* 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;
	task_t *this_task = current;
	struct list_head *lsthead = &psw->wake_task_list, *lnk;
	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(lnk, lsthead) {
		tncur = list_entry(lnk, struct wake_task_node, 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(wq);

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


/* Used to initialize the epoll bits inside the "struct file" */
void eventpoll_init_file(struct file *file)
{

	INIT_LIST_HEAD(&file->f_ep_links);
	spin_lock_init(&file->f_ep_lock);
}


/*
 * 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.
	 * The only hit might come from ep_free() but by holding the semaphore
	 * will correctly serialize the operation. We do need to acquire
	 * "ep->sem" after "epsem" because ep_remove() requires it when called
	 * from anywhere but ep_free().
	 */
	down(&epsem);

	while (!list_empty(lsthead)) {
		epi = list_entry(lsthead->next, struct epitem, fllink);

		ep = epi->ep;
		EP_LIST_DEL(&epi->fllink);
		down_write(&ep->sem);
		ep_remove(ep, epi);
		up_write(&ep->sem);
	}

	up(&epsem);
}


/*
 * It opens an eventpoll file descriptor by suggesting a storage of "size"
 * file descriptors. The size parameter is just an hint about how to size
 * data structures. It won't prevent the user to store more than "size"
 * file descriptors inside the epoll interface. It is the kernel part of
 * the userspace epoll_create(2).
 */
asmlinkage long sys_epoll_create(int size)
{
	int error, fd;
	struct inode *inode;
	struct file *file;

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

	/* Sanity check on the size parameter */
	error = -EINVAL;
	if (size <= 0)
		goto eexit_1;

	/*
	 * Creates all the items needed to setup an eventpoll file. That is,
	 * a file structure, and inode and a free file descriptor.
	 */
	error = ep_getfd(&fd, &inode, &file);
	if (error)
		goto eexit_1;

	/* Setup the file internal data structure ( "struct eventpoll" ) */
	error = ep_file_init(file);
	if (error)
		goto eexit_2;


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

	return fd;

eexit_2:
	sys_close(fd);
eexit_1:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
		     current, size, error));
	return error;
}


/*
 * The following function implements the controller interface for
 * the eventpoll file that enables the insertion/removal/change of
 * file descriptors inside the interest set.  It represents
 * the kernel part of the user space epoll_ctl(2).
 */
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_HASH_EVENT(op) &&
	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
		goto eexit_1;

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto eexit_1;

	/* Get the "struct file *" for the target file */
	tfile = fget(fd);
	if (!tfile)
		goto eexit_2;

	/* The target file descriptor must support poll */
	error = -EPERM;
	if (!tfile->f_op || !tfile->f_op->poll)
		goto eexit_3;

	/*
	 * 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 eexit_3;

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

	down_write(&ep->sem);

	/* Try to lookup the file inside our hash table */
	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;
	}

	/*
	 * The function ep_find() increments the usage count of the structure
	 * so, if this is not NULL, we need to release it.
	 */
	if (epi)
		ep_release_epitem(epi);

	up_write(&ep->sem);

eexit_3:
	fput(tfile);
eexit_2:
	fput(file);
eexit_1:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
		     current, epfd, op, fd, event, error));

	return error;
}

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

/*
 * 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 > 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 eexit_1;
	}

	/* Get the "struct file *" for the eventpoll file */
	error = -EBADF;
	file = fget(epfd);
	if (!file)
		goto eexit_1;

	/*
	 * 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 eexit_2;

	/*
	 * 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);

eexit_2:
	fput(file);
eexit_1:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
		     current, epfd, events, maxevents, timeout, error));

	return error;
}


/*
 * Creates the file descriptor to be used by the epoll interface.
 */
static int ep_getfd(int *efd, struct inode **einode, struct file **efile)
{
	struct qstr this;
	char name[32];
	struct dentry *dentry;
	struct inode *inode;
	struct file *file;
	int error, fd;

	/* Get an ready to use file */
	error = -ENFILE;
	file = get_empty_filp();
	if (!file)
		goto eexit_1;

	/* Allocates an inode from the eventpoll file system */
	inode = ep_eventpoll_inode();
	error = PTR_ERR(inode);
	if (IS_ERR(inode))
		goto eexit_2;

	/* Allocates a free descriptor to plug the file onto */
	error = get_unused_fd();
	if (error < 0)
		goto eexit_3;
	fd = error;

	/*
	 * Link the inode to a directory entry by creating a unique name
	 * using the inode number.
	 */
	error = -ENOMEM;
	sprintf(name, "[%lu]", inode->i_ino);
	this.name = name;
	this.len = strlen(name);
	this.hash = inode->i_ino;
	dentry = d_alloc(eventpoll_mnt->mnt_sb->s_root, &this);
	if (!dentry)
		goto eexit_4;
	dentry->d_op = &eventpollfs_dentry_operations;
	d_add(dentry, inode);
	file->f_vfsmnt = mntget(eventpoll_mnt);
	file->f_dentry = dentry;
	file->f_mapping = inode->i_mapping;

	file->f_pos = 0;
	file->f_flags = O_RDONLY;
	file->f_op = &eventpoll_fops;
	file->f_mode = FMODE_READ;
	file->f_version = 0;
	file->private_data = NULL;

	/* Install the new setup file into the allocated fd. */
	fd_install(fd, file);

	*efd = fd;
	*einode = inode;
	*efile = file;
	return 0;

eexit_4:
	put_unused_fd(fd);
eexit_3:
	iput(inode);
eexit_2:
	put_filp(file);
eexit_1:
	return error;
}


static int ep_file_init(struct file *file)
{
	struct eventpoll *ep;

	if (!(ep = kmalloc(sizeof(struct eventpoll), GFP_KERNEL)))
		return -ENOMEM;

	memset(ep, 0, sizeof(*ep));
	rwlock_init(&ep->lock);
	init_rwsem(&ep->sem);
	init_waitqueue_head(&ep->wq);
	init_waitqueue_head(&ep->poll_wait);
	INIT_LIST_HEAD(&ep->rdllist);
	ep->rbr = RB_ROOT;

	file->private_data = ep;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_file_init() ep=%p\n",
		     current, ep));
	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->sem" 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 "epsem" is sufficent here.
	 */
	down(&epsem);

	/*
	 * 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 hash by freeing each "struct epitem". At this
	 * point we are sure no poll callbacks will be lingering around, and also by
	 * write-holding "sem" 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)) != 0) {
		epi = rb_entry(rbp, struct epitem, rbn);
		ep_remove(ep, epi);
	}

	up(&epsem);
}


/*
 * Search the file inside the eventpoll hash. It add usage count to
 * the returned item, so the caller must call ep_release_epitem()
 * after finished using the "struct epitem".
 */
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
	int kcmp;
	unsigned long flags;
	struct rb_node *rbp;
	struct epitem *epi, *epir = NULL;
	struct epoll_filefd ffd;

	EP_SET_FFD(&ffd, file, fd);
	read_lock_irqsave(&ep->lock, flags);
	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 {
			ep_use_epitem(epi);
			epir = epi;
			break;
		}
	}
	read_unlock_irqrestore(&ep->lock, flags);

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

	return epir;
}


/*
 * Increment the usage count of the "struct epitem" making it sure
 * that the user will have a valid pointer to reference.
 */
static void ep_use_epitem(struct epitem *epi)
{

	atomic_inc(&epi->usecnt);
}


/*
 * Decrement ( release ) the usage count by signaling that the user
 * has finished using the structure. It might lead to freeing the
 * structure itself if the count goes to zero.
 */
static void ep_release_epitem(struct epitem *epi)
{

	if (atomic_dec_and_test(&epi->usecnt))
		EPI_MEM_FREE(epi);
}


/*
 * 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 = PWQ_MEM_ALLOC())) {
		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);
}


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 = EPI_MEM_ALLOC()))
		goto eexit_1;

	/* Item initialization follow here ... */
	EP_RB_INITNODE(&epi->rbn);
	INIT_LIST_HEAD(&epi->rdllink);
	INIT_LIST_HEAD(&epi->fllink);
	INIT_LIST_HEAD(&epi->txlink);
	INIT_LIST_HEAD(&epi->pwqlist);
	epi->ep = ep;
	EP_SET_FFD(&epi->ffd, tfile, fd);
	epi->event = *event;
	atomic_set(&epi->usecnt, 1);
	epi->nwait = 0;

	/* 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.
	 */
	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 eexit_2;

	/* 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);

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

	/* Add the current item to the rb-tree */
	ep_rbtree_insert(ep, epi);

	/* 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(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}

	write_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;

eexit_2:
	ep_unregister_pollwait(ep, epi);

	/*
	 * We need to do this because an event could have been arrived on some
	 * allocated wait queue.
	 */
	write_lock_irqsave(&ep->lock, flags);
	if (EP_IS_LINKED(&epi->rdllink))
		EP_LIST_DEL(&epi->rdllink);
	write_unlock_irqrestore(&ep->lock, flags);

	EPI_MEM_FREE(epi);
eexit_1:
	return error;
}


/*
 * Modify the interest event mask by dropping an event if the new mask
 * has a match in the current file status.
 */
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);

	write_lock_irqsave(&ep->lock, flags);

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

	/*
	 * If the item is not linked to the hash it means that it's on its
	 * way toward the removal. Do nothing in this case.
	 */
	if (EP_RB_LINKED(&epi->rbn)) {
		/*
		 * If the item is "hot" and it is not registered inside the ready
		 * list, push it inside. If the item is not "hot" and it is currently
		 * registered inside the ready list, unlink it.
		 */
		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(&ep->wq);
				if (waitqueue_active(&ep->poll_wait))
					pwake++;
			}
		}
	}

	write_unlock_irqrestore(&ep->lock, flags);

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

	return 0;
}


/*
 * 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_entry(lsthead->next, struct eppoll_entry, llink);

			EP_LIST_DEL(&pwq->llink);
			remove_wait_queue(pwq->whead, &pwq->wait);
			PWQ_MEM_FREE(pwq);
		}
	}
}


/*
 * Unlink the "struct epitem" from all places it might have been hooked up.
 * This function must be called with write IRQ lock on "ep->lock".
 */
static int ep_unlink(struct eventpoll *ep, struct epitem *epi)
{
	int error;

	/*
	 * It can happen that this one is called for an item already unlinked.
	 * The check protect us from doing a double unlink ( crash ).
	 */
	error = -ENOENT;
	if (!EP_RB_LINKED(&epi->rbn))
		goto eexit_1;

	/*
	 * Clear the event mask for the unlinked item. This will avoid item
	 * notifications to be sent after the unlink operation from inside
	 * the kernel->userspace event transfer loop.
	 */
	epi->event.events = 0;

	/*
	 * At this point is safe to do the job, unlink the item from our rb-tree.
	 * This operation togheter with the above check closes the door to
	 * double unlinks.
	 */
	EP_RB_ERASE(&epi->rbn, &ep->rbr);

	/*
	 * If the item we are going to remove is inside the ready file descriptors
	 * we want to remove it from this list to avoid stale events.
	 */
	if (EP_IS_LINKED(&epi->rdllink))
		EP_LIST_DEL(&epi->rdllink);

	error = 0;
eexit_1:

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n",
		     current, ep, epi->file, error));

	return error;
}


/*
 * Removes a "struct epitem" from the eventpoll hash and deallocates
 * all the associated resources.
 */
static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
	int error;
	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))
		EP_LIST_DEL(&epi->fllink);
	spin_unlock(&file->f_ep_lock);

	/* We need to acquire the write IRQ lock before calling ep_unlink() */
	write_lock_irqsave(&ep->lock, flags);

	/* Really unlink the item from the hash */
	error = ep_unlink(ep, epi);

	write_unlock_irqrestore(&ep->lock, flags);

	if (error)
		goto eexit_1;

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

	error = 0;
eexit_1:
	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p) = %d\n",
		     current, ep, file, error));

	return error;
}


/*
 * 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->file, epi, ep));

	write_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 is_disabled;

	/* 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(&ep->wq);
	if (waitqueue_active(&ep->poll_wait))
		pwake++;

is_disabled:
	write_unlock_irqrestore(&ep->lock, flags);

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

	return 1;
}


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

	if (ep) {
		ep_free(ep);
		kfree(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 */
	read_lock_irqsave(&ep->lock, flags);
	if (!list_empty(&ep->rdllist))
		pollflags = POLLIN | POLLRDNORM;
	read_unlock_irqrestore(&ep->lock, flags);

	return pollflags;
}


/*
 * Since we have to release the lock during the __copy_to_user() operation and
 * during the f_op->poll() call, we try to collect the maximum number of items
 * by reducing the irqlock/irqunlock switching rate.
 */
static int ep_collect_ready_items(struct eventpoll *ep, struct list_head *txlist, int maxevents)
{
	int nepi;
	unsigned long flags;
	struct list_head *lsthead = &ep->rdllist, *lnk;
	struct epitem *epi;

	write_lock_irqsave(&ep->lock, flags);

	for (nepi = 0, lnk = lsthead->next; lnk != lsthead && nepi < maxevents;) {
		epi = list_entry(lnk, struct epitem, rdllink);

		lnk = lnk->next;

		/* If this file is already in the ready list we exit soon */
		if (!EP_IS_LINKED(&epi->txlink)) {
			/*
			 * This is initialized in this way so that the default
			 * behaviour of the reinjecting code will be to push back
			 * the item inside the ready list.
			 */
			epi->revents = epi->event.events;

			/* Link the ready item into the transfer list */
			list_add(&epi->txlink, txlist);
			nepi++;

			/*
			 * Unlink the item from the ready list.
			 */
			EP_LIST_DEL(&epi->rdllink);
		}
	}

	write_unlock_irqrestore(&ep->lock, flags);

	return nepi;
}


/*
 * This function is called without holding the "ep->lock" since the call to
 * __copy_to_user() might sleep, and also f_op->poll() might reenable the IRQ
 * because of the way poll() is traditionally implemented in Linux.
 */
static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
			  struct epoll_event __user *events)
{
	int eventcnt = 0;
	unsigned int revents;
	struct list_head *lnk;
	struct epitem *epi;

	/*
	 * We can loop without lock because this is a task private list.
	 * The test done during the collection loop will guarantee us that
	 * another task will not try to collect this file. Also, items
	 * cannot vanish during the loop because we are holding "sem".
	 */
	list_for_each(lnk, txlist) {
		epi = list_entry(lnk, struct epitem, txlink);

		/*
		 * Get the ready file event set. We can safely use the file
		 * because we are holding the "sem" in read 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);

		/*
		 * Set the return event set for the current file descriptor.
		 * Note that only the task task was successfully able to link
		 * the item to its "txlist" will write this field.
		 */
		epi->revents = revents & epi->event.events;

		if (epi->revents) {
			if (__put_user(epi->revents,
				       &events[eventcnt].events) ||
			    __put_user(epi->event.data,
				       &events[eventcnt].data))
				return -EFAULT;
			if (epi->event.events & EPOLLONESHOT)
				epi->event.events &= EP_PRIVATE_BITS;
			eventcnt++;
		}
	}
	return eventcnt;
}


/*
 * Walk through the transfer list we collected with ep_collect_ready_items()
 * and, if 1) the item is still "alive" 2) its event set is not empty 3) it's
 * not already linked, links it to the ready list. Same as above, we are holding
 * "sem" so items cannot vanish underneath our nose.
 */
static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist)
{
	int ricnt = 0, pwake = 0;
	unsigned long flags;
	struct epitem *epi;

	write_lock_irqsave(&ep->lock, flags);

	while (!list_empty(txlist)) {
		epi = list_entry(txlist->next, struct epitem, txlink);

		/* Unlink the current item from the transfer list */
		EP_LIST_DEL(&epi->txlink);

		/*
		 * If the item is no more linked to the interest set, we don't
		 * have to push it inside the ready list because the following
		 * ep_release_epitem() is going to drop it. Also, if the current
		 * item is set to have an Edge Triggered behaviour, we don't have
		 * to push it back either.
		 */
		if (EP_RB_LINKED(&epi->rbn) && !(epi->event.events & EPOLLET) &&
		    (epi->revents & epi->event.events) && !EP_IS_LINKED(&epi->rdllink)) {
			list_add_tail(&epi->rdllink, &ep->rdllist);
			ricnt++;
		}
	}

	if (ricnt) {
		/*
		 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
		 * wait list.
		 */
		if (waitqueue_active(&ep->wq))
			wake_up(&ep->wq);
		if (waitqueue_active(&ep->poll_wait))
			pwake++;
	}

	write_unlock_irqrestore(&ep->lock, flags);

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


/*
 * Perform the transfer of events to user space.
 */
static int ep_events_transfer(struct eventpoll *ep,
			      struct epoll_event __user *events, int maxevents)
{
	int eventcnt = 0;
	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).
	 */
	down_read(&ep->sem);

	/* Collect/extract ready items */
	if (ep_collect_ready_items(ep, &txlist, maxevents) > 0) {
		/* Build result set in userspace */
		eventcnt = ep_send_events(ep, &txlist, events);

		/* Reinject ready items into the ready list */
		ep_reinject_items(ep, &txlist);
	}

	up_read(&ep->sem);

	return 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 == -1 || timeout > (MAX_SCHEDULE_TIMEOUT - 1000) / HZ ?
		MAX_SCHEDULE_TIMEOUT: (timeout * HZ + 999) / 1000;

retry:
	write_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);
		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;
			}

			write_unlock_irqrestore(&ep->lock, flags);
			jtimeout = schedule_timeout(jtimeout);
			write_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);

	write_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_events_transfer(ep, events, maxevents)) && jtimeout)
		goto retry;

	return res;
}


static int eventpollfs_delete_dentry(struct dentry *dentry)
{

	return 1;
}


static struct inode *ep_eventpoll_inode(void)
{
	int error = -ENOMEM;
	struct inode *inode = new_inode(eventpoll_mnt->mnt_sb);

	if (!inode)
		goto eexit_1;

	inode->i_fop = &eventpoll_fops;

	/*
	 * Mark the inode dirty from the very beginning,
	 * that way it will never be moved to the dirty
	 * list because mark_inode_dirty() will think
	 * that it already _is_ on the dirty list.
	 */
	inode->i_state = I_DIRTY;
	inode->i_mode = S_IRUSR | S_IWUSR;
	inode->i_uid = current->fsuid;
	inode->i_gid = current->fsgid;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	inode->i_blksize = PAGE_SIZE;
	return inode;

eexit_1:
	return ERR_PTR(error);
}


static struct super_block *
eventpollfs_get_sb(struct file_system_type *fs_type, int flags,
		   const char *dev_name, void *data)
{
	return get_sb_pseudo(fs_type, "eventpoll:", NULL, EVENTPOLLFS_MAGIC);
}


static int __init eventpoll_init(void)
{
	int error;

	init_MUTEX(&epsem);

	/* 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, 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, NULL);

	/*
	 * Register the virtual file system that will be the source of inodes
	 * for the eventpoll files
	 */
	error = register_filesystem(&eventpoll_fs_type);
	if (error)
		goto epanic;

	/* Mount the above commented virtual file system */
	eventpoll_mnt = kern_mount(&eventpoll_fs_type);
	error = PTR_ERR(eventpoll_mnt);
	if (IS_ERR(eventpoll_mnt))
		goto epanic;

	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: successfully initialized.\n",
			current));
	return 0;

epanic:
	panic("eventpoll_init() failed\n");
}


static void __exit eventpoll_exit(void)
{
	/* Undo all operations done inside eventpoll_init() */
	unregister_filesystem(&eventpoll_fs_type);
	mntput(eventpoll_mnt);
	kmem_cache_destroy(pwq_cache);
	kmem_cache_destroy(epi_cache);
}

module_init(eventpoll_init);
module_exit(eventpoll_exit);

MODULE_LICENSE("GPL");