summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_event.c
blob: 9fa9de74d4553511cf83e92b17e843afe2810fd5 (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
/*-
 * Copyright (c) 1999,2000,2001 Jonathan Lemon <jlemon@FreeBSD.org>
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 * $FreeBSD$
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/malloc.h> 
#include <sys/unistd.h>
#include <sys/file.h>
#include <sys/fcntl.h>
#include <sys/selinfo.h>
#include <sys/queue.h>
#include <sys/event.h>
#include <sys/eventvar.h>
#include <sys/poll.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/stat.h>
#include <sys/sysctl.h>
#include <sys/sysproto.h>
#include <sys/uio.h>

#include <vm/uma.h>

MALLOC_DEFINE(M_KQUEUE, "kqueue", "memory for kqueue system");

static int	kqueue_scan(struct file *fp, int maxevents,
		    struct kevent *ulistp, const struct timespec *timeout,
		    struct thread *td);
static int 	kqueue_read(struct file *fp, struct uio *uio,
		    struct ucred *active_cred, int flags, struct thread *td);
static int	kqueue_write(struct file *fp, struct uio *uio,
		    struct ucred *active_cred, int flags, struct thread *td);
static int	kqueue_ioctl(struct file *fp, u_long com, void *data,
		    struct ucred *active_cred, struct thread *td);
static int 	kqueue_poll(struct file *fp, int events,
		    struct ucred *active_cred, struct thread *td);
static int 	kqueue_kqfilter(struct file *fp, struct knote *kn);
static int 	kqueue_stat(struct file *fp, struct stat *st,
		    struct ucred *active_cred, struct thread *td);
static int 	kqueue_close(struct file *fp, struct thread *td);
static void 	kqueue_wakeup(struct kqueue *kq);

static struct fileops kqueueops = {
	kqueue_read,
	kqueue_write,
	kqueue_ioctl,
	kqueue_poll,
	kqueue_kqfilter,
	kqueue_stat,
	kqueue_close
};

static void 	knote_attach(struct knote *kn, struct filedesc *fdp);
static void 	knote_drop(struct knote *kn, struct thread *td);
static void 	knote_enqueue(struct knote *kn);
static void 	knote_dequeue(struct knote *kn);
static void 	knote_init(void);
static struct 	knote *knote_alloc(void);
static void 	knote_free(struct knote *kn);

static void	filt_kqdetach(struct knote *kn);
static int	filt_kqueue(struct knote *kn, long hint);
static int	filt_procattach(struct knote *kn);
static void	filt_procdetach(struct knote *kn);
static int	filt_proc(struct knote *kn, long hint);
static int	filt_fileattach(struct knote *kn);
static void	filt_timerexpire(void *knx);
static int	filt_timerattach(struct knote *kn);
static void	filt_timerdetach(struct knote *kn);
static int	filt_timer(struct knote *kn, long hint);

static struct filterops file_filtops =
	{ 1, filt_fileattach, NULL, NULL };
static struct filterops kqread_filtops =
	{ 1, NULL, filt_kqdetach, filt_kqueue };
static struct filterops proc_filtops =
	{ 0, filt_procattach, filt_procdetach, filt_proc };
static struct filterops timer_filtops =
	{ 0, filt_timerattach, filt_timerdetach, filt_timer };

static uma_zone_t	knote_zone;
static int 		kq_ncallouts = 0;
static int 		kq_calloutmax = (4 * 1024);
SYSCTL_INT(_kern, OID_AUTO, kq_calloutmax, CTLFLAG_RW,
    &kq_calloutmax, 0, "Maximum number of callouts allocated for kqueue");

#define KNOTE_ACTIVATE(kn) do { 					\
	kn->kn_status |= KN_ACTIVE;					\
	if ((kn->kn_status & (KN_QUEUED | KN_DISABLED)) == 0)		\
		knote_enqueue(kn);					\
} while(0)

#define	KN_HASHSIZE		64		/* XXX should be tunable */
#define KN_HASH(val, mask)	(((val) ^ (val >> 8)) & (mask))

static int
filt_nullattach(struct knote *kn)
{

	return (ENXIO);
};

struct filterops null_filtops =
	{ 0, filt_nullattach, NULL, NULL };

extern struct filterops sig_filtops;

/*
 * Table for for all system-defined filters.
 */
static struct filterops *sysfilt_ops[] = {
	&file_filtops,			/* EVFILT_READ */
	&file_filtops,			/* EVFILT_WRITE */
	&null_filtops,			/* EVFILT_AIO */
	&file_filtops,			/* EVFILT_VNODE */
	&proc_filtops,			/* EVFILT_PROC */
	&sig_filtops,			/* EVFILT_SIGNAL */
	&timer_filtops,			/* EVFILT_TIMER */
	&file_filtops,			/* EVFILT_NETDEV */
};

static int
filt_fileattach(struct knote *kn)
{
	
	return (fo_kqfilter(kn->kn_fp, kn));
}

/*ARGSUSED*/
static int
kqueue_kqfilter(struct file *fp, struct knote *kn)
{
	struct kqueue *kq = (struct kqueue *)kn->kn_fp->f_data;

	if (kn->kn_filter != EVFILT_READ)
		return (1);

	kn->kn_fop = &kqread_filtops;
	SLIST_INSERT_HEAD(&kq->kq_sel.si_note, kn, kn_selnext);
	return (0);
}

static void
filt_kqdetach(struct knote *kn)
{
	struct kqueue *kq = (struct kqueue *)kn->kn_fp->f_data;

	SLIST_REMOVE(&kq->kq_sel.si_note, kn, knote, kn_selnext);
}

/*ARGSUSED*/
static int
filt_kqueue(struct knote *kn, long hint)
{
	struct kqueue *kq = (struct kqueue *)kn->kn_fp->f_data;

	kn->kn_data = kq->kq_count;
	return (kn->kn_data > 0);
}

static int
filt_procattach(struct knote *kn)
{
	struct proc *p;
	int error;

	p = pfind(kn->kn_id);
	if (p == NULL)
		return (ESRCH);
	if ((error = p_cansee(curthread, p))) {
		PROC_UNLOCK(p);
		return (error);
	}

	kn->kn_ptr.p_proc = p;
	kn->kn_flags |= EV_CLEAR;		/* automatically set */

	/*
	 * internal flag indicating registration done by kernel
	 */
	if (kn->kn_flags & EV_FLAG1) {
		kn->kn_data = kn->kn_sdata;		/* ppid */
		kn->kn_fflags = NOTE_CHILD;
		kn->kn_flags &= ~EV_FLAG1;
	}

	SLIST_INSERT_HEAD(&p->p_klist, kn, kn_selnext);
	PROC_UNLOCK(p);

	return (0);
}

/*
 * The knote may be attached to a different process, which may exit,
 * leaving nothing for the knote to be attached to.  So when the process
 * exits, the knote is marked as DETACHED and also flagged as ONESHOT so
 * it will be deleted when read out.  However, as part of the knote deletion,
 * this routine is called, so a check is needed to avoid actually performing
 * a detach, because the original process does not exist any more.
 */
static void
filt_procdetach(struct knote *kn)
{
	struct proc *p = kn->kn_ptr.p_proc;

	if (kn->kn_status & KN_DETACHED)
		return;

	PROC_LOCK(p);
	SLIST_REMOVE(&p->p_klist, kn, knote, kn_selnext);
	PROC_UNLOCK(p);
}

static int
filt_proc(struct knote *kn, long hint)
{
	u_int event;

	/*
	 * mask off extra data
	 */
	event = (u_int)hint & NOTE_PCTRLMASK;

	/*
	 * if the user is interested in this event, record it.
	 */
	if (kn->kn_sfflags & event)
		kn->kn_fflags |= event;

	/*
	 * process is gone, so flag the event as finished.
	 */
	if (event == NOTE_EXIT) {
		kn->kn_status |= KN_DETACHED;
		kn->kn_flags |= (EV_EOF | EV_ONESHOT); 
		return (1);
	}

	/*
	 * process forked, and user wants to track the new process,
	 * so attach a new knote to it, and immediately report an
	 * event with the parent's pid.
	 */
	if ((event == NOTE_FORK) && (kn->kn_sfflags & NOTE_TRACK)) {
		struct kevent kev;
		int error;

		/*
		 * register knote with new process.
		 */
		kev.ident = hint & NOTE_PDATAMASK;	/* pid */
		kev.filter = kn->kn_filter;
		kev.flags = kn->kn_flags | EV_ADD | EV_ENABLE | EV_FLAG1;
		kev.fflags = kn->kn_sfflags;
		kev.data = kn->kn_id;			/* parent */
		kev.udata = kn->kn_kevent.udata;	/* preserve udata */
		error = kqueue_register(kn->kn_kq, &kev, NULL);
		if (error)
			kn->kn_fflags |= NOTE_TRACKERR;
	}

	return (kn->kn_fflags != 0);
}

static void
filt_timerexpire(void *knx)
{
	struct knote *kn = knx;
	struct callout *calloutp;
	struct timeval tv;
	int tticks;

	kn->kn_data++;
	KNOTE_ACTIVATE(kn);

	if ((kn->kn_flags & EV_ONESHOT) == 0) {
		tv.tv_sec = kn->kn_sdata / 1000;
		tv.tv_usec = (kn->kn_sdata % 1000) * 1000;
		tticks = tvtohz(&tv);
		calloutp = (struct callout *)kn->kn_hook;
		callout_reset(calloutp, tticks, filt_timerexpire, kn);
	}
}

/*
 * data contains amount of time to sleep, in milliseconds
 */ 
static int
filt_timerattach(struct knote *kn)
{
	struct callout *calloutp;
	struct timeval tv;
	int tticks;

	if (kq_ncallouts >= kq_calloutmax)
		return (ENOMEM);
	kq_ncallouts++;

	tv.tv_sec = kn->kn_sdata / 1000;
	tv.tv_usec = (kn->kn_sdata % 1000) * 1000;
	tticks = tvtohz(&tv);

	kn->kn_flags |= EV_CLEAR;		/* automatically set */
	MALLOC(calloutp, struct callout *, sizeof(*calloutp),
	    M_KQUEUE, M_WAITOK);
	callout_init(calloutp, 0);
	callout_reset(calloutp, tticks, filt_timerexpire, kn);
	kn->kn_hook = calloutp;

	return (0);
}

static void
filt_timerdetach(struct knote *kn)
{
	struct callout *calloutp;

	calloutp = (struct callout *)kn->kn_hook;
	callout_stop(calloutp);
	FREE(calloutp, M_KQUEUE);
	kq_ncallouts--;
}

static int
filt_timer(struct knote *kn, long hint)
{

	return (kn->kn_data != 0);
}

/*
 * MPSAFE
 */
int
kqueue(struct thread *td, struct kqueue_args *uap)
{
	struct filedesc *fdp;
	struct kqueue *kq;
	struct file *fp;
	int fd, error;

	mtx_lock(&Giant);
	fdp = td->td_proc->p_fd;
	error = falloc(td, &fp, &fd);
	if (error)
		goto done2;
	kq = malloc(sizeof(struct kqueue), M_KQUEUE, M_WAITOK | M_ZERO);
	TAILQ_INIT(&kq->kq_head);
	FILE_LOCK(fp);
	fp->f_flag = FREAD | FWRITE;
	fp->f_type = DTYPE_KQUEUE;
	fp->f_ops = &kqueueops;
	TAILQ_INIT(&kq->kq_head);
	fp->f_data = kq;
	FILE_UNLOCK(fp);
	FILEDESC_LOCK(fdp);
	td->td_retval[0] = fd;
	if (fdp->fd_knlistsize < 0)
		fdp->fd_knlistsize = 0;		/* this process has a kq */
	FILEDESC_UNLOCK(fdp);
	kq->kq_fdp = fdp;
done2:
	mtx_unlock(&Giant);
	return (error);
}

#ifndef _SYS_SYSPROTO_H_
struct kevent_args {
	int	fd;
	const struct kevent *changelist;
	int	nchanges;
	struct	kevent *eventlist;
	int	nevents;
	const struct timespec *timeout;
};
#endif
/*
 * MPSAFE
 */
int
kevent(struct thread *td, struct kevent_args *uap)
{
	struct kevent *kevp;
	struct kqueue *kq;
	struct file *fp;
	struct timespec ts;
	int i, n, nerrors, error;

	if ((error = fget(td, uap->fd, &fp)) != 0)
		return (error);
	if (fp->f_type != DTYPE_KQUEUE) {
		fdrop(fp, td);
		return (EBADF);
	}
	if (uap->timeout != NULL) {
		error = copyin(uap->timeout, &ts, sizeof(ts));
		if (error)
			goto done_nogiant;
		uap->timeout = &ts;
	}
	mtx_lock(&Giant);

	kq = (struct kqueue *)fp->f_data;
	nerrors = 0;

	while (uap->nchanges > 0) {
		n = uap->nchanges > KQ_NEVENTS ? KQ_NEVENTS : uap->nchanges;
		error = copyin(uap->changelist, kq->kq_kev,
		    n * sizeof(struct kevent));
		if (error)
			goto done;
		for (i = 0; i < n; i++) {
			kevp = &kq->kq_kev[i];
			kevp->flags &= ~EV_SYSFLAGS;
			error = kqueue_register(kq, kevp, td);
			if (error) {
				if (uap->nevents != 0) {
					kevp->flags = EV_ERROR;
					kevp->data = error;
					(void) copyout(kevp,
					    uap->eventlist,
					    sizeof(*kevp));
					uap->eventlist++;
					uap->nevents--;
					nerrors++;
				} else {
					goto done;
				}
			}
		}
		uap->nchanges -= n;
		uap->changelist += n;
	}
	if (nerrors) {
        	td->td_retval[0] = nerrors;
		error = 0;
		goto done;
	}

	error = kqueue_scan(fp, uap->nevents, uap->eventlist, uap->timeout, td);
done:
	mtx_unlock(&Giant);
done_nogiant:
	if (fp != NULL)
		fdrop(fp, td);
	return (error);
}

int
kqueue_add_filteropts(int filt, struct filterops *filtops)
{

	if (filt > 0)
		panic("filt(%d) > 0", filt);
	if (filt + EVFILT_SYSCOUNT < 0)
		panic("filt(%d) + EVFILT_SYSCOUNT(%d) == %d < 0",
		    filt, EVFILT_SYSCOUNT, filt + EVFILT_SYSCOUNT);
	if (sysfilt_ops[~filt] != &null_filtops)
		panic("sysfilt_ops[~filt(%d)] != &null_filtops", filt);
	sysfilt_ops[~filt] = filtops;
	return (0);
}

int
kqueue_del_filteropts(int filt)
{

	if (filt > 0)
		panic("filt(%d) > 0", filt);
	if (filt + EVFILT_SYSCOUNT < 0)
		panic("filt(%d) + EVFILT_SYSCOUNT(%d) == %d < 0",
		    filt, EVFILT_SYSCOUNT, filt + EVFILT_SYSCOUNT);
	if (sysfilt_ops[~filt] == &null_filtops)
		panic("sysfilt_ops[~filt(%d)] != &null_filtops", filt);
	sysfilt_ops[~filt] = &null_filtops;
	return (0);
}

int
kqueue_register(struct kqueue *kq, struct kevent *kev, struct thread *td)
{
	struct filedesc *fdp = kq->kq_fdp;
	struct filterops *fops;
	struct file *fp = NULL;
	struct knote *kn = NULL;
	int s, error = 0;

	if (kev->filter < 0) {
		if (kev->filter + EVFILT_SYSCOUNT < 0)
			return (EINVAL);
		fops = sysfilt_ops[~kev->filter];	/* to 0-base index */
	} else {
		/*
		 * XXX
		 * filter attach routine is responsible for insuring that
		 * the identifier can be attached to it.
		 */
		printf("unknown filter: %d\n", kev->filter);
		return (EINVAL);
	}

	FILEDESC_LOCK(fdp);
	if (fops->f_isfd) {
		/* validate descriptor */
		if ((u_int)kev->ident >= fdp->fd_nfiles ||
		    (fp = fdp->fd_ofiles[kev->ident]) == NULL) {
			FILEDESC_UNLOCK(fdp);
			return (EBADF);
		}
		fhold(fp);

		if (kev->ident < fdp->fd_knlistsize) {
			SLIST_FOREACH(kn, &fdp->fd_knlist[kev->ident], kn_link)
				if (kq == kn->kn_kq &&
				    kev->filter == kn->kn_filter)
					break;
		}
	} else {
		if (fdp->fd_knhashmask != 0) {
			struct klist *list;
			
			list = &fdp->fd_knhash[
			    KN_HASH((u_long)kev->ident, fdp->fd_knhashmask)];
			SLIST_FOREACH(kn, list, kn_link)
				if (kev->ident == kn->kn_id &&
				    kq == kn->kn_kq &&
				    kev->filter == kn->kn_filter)
					break;
		}
	}
	FILEDESC_UNLOCK(fdp);

	if (kn == NULL && ((kev->flags & EV_ADD) == 0)) {
		error = ENOENT;
		goto done;
	}

	/*
	 * kn now contains the matching knote, or NULL if no match
	 */
	if (kev->flags & EV_ADD) {

		if (kn == NULL) {
			kn = knote_alloc();
			if (kn == NULL) {
				error = ENOMEM;
				goto done;
			}
			kn->kn_fp = fp;
			kn->kn_kq = kq;
			kn->kn_fop = fops;

			/*
			 * apply reference count to knote structure, and
			 * do not release it at the end of this routine.
			 */
			fp = NULL;

			kn->kn_sfflags = kev->fflags;
			kn->kn_sdata = kev->data;
			kev->fflags = 0;
			kev->data = 0;
			kn->kn_kevent = *kev;

			knote_attach(kn, fdp);
			if ((error = fops->f_attach(kn)) != 0) {
				knote_drop(kn, td);
				goto done;
			}
		} else {
			/*
			 * The user may change some filter values after the
			 * initial EV_ADD, but doing so will not reset any 
			 * filter which has already been triggered.
			 */
			kn->kn_sfflags = kev->fflags;
			kn->kn_sdata = kev->data;
			kn->kn_kevent.udata = kev->udata;
		}

		s = splhigh();
		if (kn->kn_fop->f_event(kn, 0))
			KNOTE_ACTIVATE(kn);
		splx(s);

	} else if (kev->flags & EV_DELETE) {
		kn->kn_fop->f_detach(kn);
		knote_drop(kn, td);
		goto done;
	}

	if ((kev->flags & EV_DISABLE) &&
	    ((kn->kn_status & KN_DISABLED) == 0)) {
		s = splhigh();
		kn->kn_status |= KN_DISABLED;
		splx(s);
	}

	if ((kev->flags & EV_ENABLE) && (kn->kn_status & KN_DISABLED)) {
		s = splhigh();
		kn->kn_status &= ~KN_DISABLED;
		if ((kn->kn_status & KN_ACTIVE) &&
		    ((kn->kn_status & KN_QUEUED) == 0))
			knote_enqueue(kn);
		splx(s);
	}

done:
	if (fp != NULL)
		fdrop(fp, td);
	return (error);
}

static int
kqueue_scan(struct file *fp, int maxevents, struct kevent *ulistp,
	const struct timespec *tsp, struct thread *td)
{
	struct kqueue *kq;
	struct kevent *kevp;
	struct timeval atv, rtv, ttv;
	struct knote *kn, marker;
	int s, count, timeout, nkev = 0, error = 0;

	FILE_LOCK_ASSERT(fp, MA_NOTOWNED);

	kq = (struct kqueue *)fp->f_data;
	count = maxevents;
	if (count == 0)
		goto done;

	if (tsp != NULL) {
		TIMESPEC_TO_TIMEVAL(&atv, tsp);
		if (itimerfix(&atv)) {
			error = EINVAL;
			goto done;
		}
		if (tsp->tv_sec == 0 && tsp->tv_nsec == 0)
			timeout = -1;
		else 
			timeout = atv.tv_sec > 24 * 60 * 60 ?
			    24 * 60 * 60 * hz : tvtohz(&atv);
		getmicrouptime(&rtv);
		timevaladd(&atv, &rtv);
	} else {
		atv.tv_sec = 0;
		atv.tv_usec = 0;
		timeout = 0;
	}
	goto start;

retry:
	if (atv.tv_sec || atv.tv_usec) {
		getmicrouptime(&rtv);
		if (timevalcmp(&rtv, &atv, >=))
			goto done;
		ttv = atv;
		timevalsub(&ttv, &rtv);
		timeout = ttv.tv_sec > 24 * 60 * 60 ?
			24 * 60 * 60 * hz : tvtohz(&ttv);
	}

start:
	kevp = kq->kq_kev;
	s = splhigh();
	if (kq->kq_count == 0) {
		if (timeout < 0) { 
			error = EWOULDBLOCK;
		} else {
			kq->kq_state |= KQ_SLEEP;
			error = tsleep(kq, PSOCK | PCATCH, "kqread", timeout);
		}
		splx(s);
		if (error == 0)
			goto retry;
		/* don't restart after signals... */
		if (error == ERESTART)
			error = EINTR;
		else if (error == EWOULDBLOCK)
			error = 0;
		goto done;
	}

	TAILQ_INSERT_TAIL(&kq->kq_head, &marker, kn_tqe); 
	while (count) {
		kn = TAILQ_FIRST(&kq->kq_head);
		TAILQ_REMOVE(&kq->kq_head, kn, kn_tqe); 
		if (kn == &marker) {
			splx(s);
			if (count == maxevents)
				goto retry;
			goto done;
		}
		if (kn->kn_status & KN_DISABLED) {
			kn->kn_status &= ~KN_QUEUED;
			kq->kq_count--;
			continue;
		}
		if ((kn->kn_flags & EV_ONESHOT) == 0 &&
		    kn->kn_fop->f_event(kn, 0) == 0) {
			kn->kn_status &= ~(KN_QUEUED | KN_ACTIVE);
			kq->kq_count--;
			continue;
		}
		*kevp = kn->kn_kevent;
		kevp++;
		nkev++;
		if (kn->kn_flags & EV_ONESHOT) {
			kn->kn_status &= ~KN_QUEUED;
			kq->kq_count--;
			splx(s);
			kn->kn_fop->f_detach(kn);
			knote_drop(kn, td);
			s = splhigh();
		} else if (kn->kn_flags & EV_CLEAR) {
			kn->kn_data = 0;
			kn->kn_fflags = 0;
			kn->kn_status &= ~(KN_QUEUED | KN_ACTIVE);
			kq->kq_count--;
		} else {
			TAILQ_INSERT_TAIL(&kq->kq_head, kn, kn_tqe); 
		}
		count--;
		if (nkev == KQ_NEVENTS) {
			splx(s);
			error = copyout(&kq->kq_kev, ulistp,
			    sizeof(struct kevent) * nkev);
			ulistp += nkev;
			nkev = 0;
			kevp = kq->kq_kev;
			s = splhigh();
			if (error)
				break;
		}
	}
	TAILQ_REMOVE(&kq->kq_head, &marker, kn_tqe); 
	splx(s);
done:
	if (nkev != 0)
		error = copyout(&kq->kq_kev, ulistp,
		    sizeof(struct kevent) * nkev);
        td->td_retval[0] = maxevents - count;
	return (error);
}

/*
 * XXX
 * This could be expanded to call kqueue_scan, if desired.
 */
/*ARGSUSED*/
static int
kqueue_read(struct file *fp, struct uio *uio, struct ucred *active_cred,
	int flags, struct thread *td)
{
	return (ENXIO);
}

/*ARGSUSED*/
static int
kqueue_write(struct file *fp, struct uio *uio, struct ucred *active_cred,
	 int flags, struct thread *td)
{
	return (ENXIO);
}

/*ARGSUSED*/
static int
kqueue_ioctl(struct file *fp, u_long com, void *data,
	struct ucred *active_cred, struct thread *td)
{
	return (ENOTTY);
}

/*ARGSUSED*/
static int
kqueue_poll(struct file *fp, int events, struct ucred *active_cred,
	struct thread *td)
{
	struct kqueue *kq;
	int revents = 0;
	int s = splnet();

	kq = (struct kqueue *)fp->f_data;
        if (events & (POLLIN | POLLRDNORM)) {
                if (kq->kq_count) {
                        revents |= events & (POLLIN | POLLRDNORM);
		} else {
                        selrecord(td, &kq->kq_sel);
			kq->kq_state |= KQ_SEL;
		}
	}
	splx(s);
	return (revents);
}

/*ARGSUSED*/
static int
kqueue_stat(struct file *fp, struct stat *st, struct ucred *active_cred,
	struct thread *td)
{
	struct kqueue *kq;

	kq = (struct kqueue *)fp->f_data;
	bzero((void *)st, sizeof(*st));
	st->st_size = kq->kq_count;
	st->st_blksize = sizeof(struct kevent);
	st->st_mode = S_IFIFO;
	return (0);
}

/*ARGSUSED*/
static int
kqueue_close(struct file *fp, struct thread *td)
{
	struct kqueue *kq = (struct kqueue *)fp->f_data;
	struct filedesc *fdp = td->td_proc->p_fd;
	struct knote **knp, *kn, *kn0;
	int i;

	FILEDESC_LOCK(fdp);
	for (i = 0; i < fdp->fd_knlistsize; i++) {
		knp = &SLIST_FIRST(&fdp->fd_knlist[i]);
		kn = *knp;
		while (kn != NULL) {
			kn0 = SLIST_NEXT(kn, kn_link);
			if (kq == kn->kn_kq) {
				kn->kn_fop->f_detach(kn);
				*knp = kn0;
				FILE_LOCK(kn->kn_fp);
				FILEDESC_UNLOCK(fdp);
				fdrop_locked(kn->kn_fp, td);
				knote_free(kn);
				FILEDESC_LOCK(fdp);
			} else {
				knp = &SLIST_NEXT(kn, kn_link);
			}
			kn = kn0;
		}
	}
	if (fdp->fd_knhashmask != 0) {
		for (i = 0; i < fdp->fd_knhashmask + 1; i++) {
			knp = &SLIST_FIRST(&fdp->fd_knhash[i]);
			kn = *knp;
			while (kn != NULL) {
				kn0 = SLIST_NEXT(kn, kn_link);
				if (kq == kn->kn_kq) {
					kn->kn_fop->f_detach(kn);
					*knp = kn0;
		/* XXX non-fd release of kn->kn_ptr */
					FILEDESC_UNLOCK(fdp);
					knote_free(kn);
					FILEDESC_LOCK(fdp);
				} else {
					knp = &SLIST_NEXT(kn, kn_link);
				}
				kn = kn0;
			}
		}
	}
	FILEDESC_UNLOCK(fdp);
	free(kq, M_KQUEUE);
	fp->f_data = NULL;

	return (0);
}

static void
kqueue_wakeup(struct kqueue *kq)
{

	if (kq->kq_state & KQ_SLEEP) {
		kq->kq_state &= ~KQ_SLEEP;
		wakeup(kq);
	}
	if (kq->kq_state & KQ_SEL) {
		kq->kq_state &= ~KQ_SEL;
		selwakeup(&kq->kq_sel);
	}
	KNOTE(&kq->kq_sel.si_note, 0);
}

/*
 * walk down a list of knotes, activating them if their event has triggered.
 */
void
knote(struct klist *list, long hint)
{
	struct knote *kn;

	SLIST_FOREACH(kn, list, kn_selnext)
		if (kn->kn_fop->f_event(kn, hint))
			KNOTE_ACTIVATE(kn);
}

/*
 * remove all knotes from a specified klist
 */
void
knote_remove(struct thread *td, struct klist *list)
{
	struct knote *kn;

	while ((kn = SLIST_FIRST(list)) != NULL) {
		kn->kn_fop->f_detach(kn);
		knote_drop(kn, td);
	}
}

/*
 * remove all knotes referencing a specified fd
 */
void
knote_fdclose(struct thread *td, int fd)
{
	struct filedesc *fdp = td->td_proc->p_fd;
	struct klist *list;

	FILEDESC_LOCK(fdp);
	list = &fdp->fd_knlist[fd];
	FILEDESC_UNLOCK(fdp);
	knote_remove(td, list);
}

static void
knote_attach(struct knote *kn, struct filedesc *fdp)
{
	struct klist *list, *oldlist, *tmp_knhash;
	u_long tmp_knhashmask;
	int size, newsize;

	FILEDESC_LOCK(fdp);

	if (! kn->kn_fop->f_isfd) {
		if (fdp->fd_knhashmask == 0) {
			FILEDESC_UNLOCK(fdp);
			tmp_knhash = hashinit(KN_HASHSIZE, M_KQUEUE,
			    &tmp_knhashmask);
			FILEDESC_LOCK(fdp);
			if (fdp->fd_knhashmask == 0) {
				fdp->fd_knhash = tmp_knhash;
				fdp->fd_knhashmask = tmp_knhashmask;
			} else {
				FILEDESC_UNLOCK(fdp);
				free(tmp_knhash, M_KQUEUE);
				FILEDESC_LOCK(fdp);
			}
		}
		list = &fdp->fd_knhash[KN_HASH(kn->kn_id, fdp->fd_knhashmask)];
		goto done;
	}

	if (fdp->fd_knlistsize <= kn->kn_id) {
retry:
		size = fdp->fd_knlistsize;
		while (size <= kn->kn_id)
			size += KQEXTENT;
		FILEDESC_UNLOCK(fdp);
		MALLOC(list, struct klist *,
		    size * sizeof(struct klist *), M_KQUEUE, M_WAITOK);
		FILEDESC_LOCK(fdp);
		newsize = fdp->fd_knlistsize;
		while (newsize <= kn->kn_id)
			newsize += KQEXTENT;
		if (newsize != size) {
			FILEDESC_UNLOCK(fdp);
			free(list, M_TEMP);
			FILEDESC_LOCK(fdp);
			goto retry;
		}
		bcopy(fdp->fd_knlist, list,
		    fdp->fd_knlistsize * sizeof(struct klist *));
		bzero((caddr_t)list +
		    fdp->fd_knlistsize * sizeof(struct klist *),
		    (size - fdp->fd_knlistsize) * sizeof(struct klist *));
		if (fdp->fd_knlist != NULL)
			oldlist = fdp->fd_knlist;
		else
			oldlist = NULL;
		fdp->fd_knlistsize = size;
		fdp->fd_knlist = list;
		FILEDESC_UNLOCK(fdp);
		if (oldlist != NULL)
			FREE(oldlist, M_KQUEUE);
		FILEDESC_LOCK(fdp);
	}
	list = &fdp->fd_knlist[kn->kn_id];
done:
	FILEDESC_UNLOCK(fdp);
	SLIST_INSERT_HEAD(list, kn, kn_link);
	kn->kn_status = 0;
}

/*
 * should be called at spl == 0, since we don't want to hold spl
 * while calling fdrop and free.
 */
static void
knote_drop(struct knote *kn, struct thread *td)
{
        struct filedesc *fdp = td->td_proc->p_fd;
	struct klist *list;

	FILEDESC_LOCK(fdp);
	if (kn->kn_fop->f_isfd)
		list = &fdp->fd_knlist[kn->kn_id];
	else
		list = &fdp->fd_knhash[KN_HASH(kn->kn_id, fdp->fd_knhashmask)];
	if (kn->kn_fop->f_isfd)
		FILE_LOCK(kn->kn_fp);
	FILEDESC_UNLOCK(fdp);

	SLIST_REMOVE(list, kn, knote, kn_link);
	if (kn->kn_status & KN_QUEUED)
		knote_dequeue(kn);
	if (kn->kn_fop->f_isfd)
		fdrop_locked(kn->kn_fp, td);
	knote_free(kn);
}


static void
knote_enqueue(struct knote *kn)
{
	struct kqueue *kq = kn->kn_kq;
	int s = splhigh();

	KASSERT((kn->kn_status & KN_QUEUED) == 0, ("knote already queued"));

	TAILQ_INSERT_TAIL(&kq->kq_head, kn, kn_tqe); 
	kn->kn_status |= KN_QUEUED;
	kq->kq_count++;
	splx(s);
	kqueue_wakeup(kq);
}

static void
knote_dequeue(struct knote *kn)
{
	struct kqueue *kq = kn->kn_kq;
	int s = splhigh();

	KASSERT(kn->kn_status & KN_QUEUED, ("knote not queued"));

	TAILQ_REMOVE(&kq->kq_head, kn, kn_tqe); 
	kn->kn_status &= ~KN_QUEUED;
	kq->kq_count--;
	splx(s);
}

static void
knote_init(void)
{
	knote_zone = uma_zcreate("KNOTE", sizeof(struct knote), NULL, NULL,
	    NULL, NULL, UMA_ALIGN_PTR, 0);

}
SYSINIT(knote, SI_SUB_PSEUDO, SI_ORDER_ANY, knote_init, NULL)

static struct knote *
knote_alloc(void)
{
	return ((struct knote *)uma_zalloc(knote_zone, M_WAITOK));
}

static void
knote_free(struct knote *kn)
{
	uma_zfree(knote_zone, kn);
}
OpenPOWER on IntegriCloud