forked from freebsd/freebsd-src
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathkern_event.c
2741 lines (2400 loc) · 62.7 KB
/
kern_event.c
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
/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 1999,2000,2001 Jonathan Lemon <[email protected]>
* Copyright 2004 John-Mark Gurney <[email protected]>
* Copyright (c) 2009 Apple, Inc.
* 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ktrace.h"
#include "opt_kqueue.h"
#ifdef COMPAT_FREEBSD11
#define _WANT_FREEBSD11_KEVENT
#endif
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/capsicum.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/rwlock.h>
#include <sys/proc.h>
#include <sys/malloc.h>
#include <sys/unistd.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/filio.h>
#include <sys/fcntl.h>
#include <sys/kthread.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/resourcevar.h>
#include <sys/sigio.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/stat.h>
#include <sys/sysctl.h>
#include <sys/sysproto.h>
#include <sys/syscallsubr.h>
#include <sys/taskqueue.h>
#include <sys/uio.h>
#include <sys/user.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif
#include <machine/atomic.h>
#include <vm/uma.h>
static MALLOC_DEFINE(M_KQUEUE, "kqueue", "memory for kqueue system");
/*
* This lock is used if multiple kq locks are required. This possibly
* should be made into a per proc lock.
*/
static struct mtx kq_global;
MTX_SYSINIT(kq_global, &kq_global, "kqueue order", MTX_DEF);
#define KQ_GLOBAL_LOCK(lck, haslck) do { \
if (!haslck) \
mtx_lock(lck); \
haslck = 1; \
} while (0)
#define KQ_GLOBAL_UNLOCK(lck, haslck) do { \
if (haslck) \
mtx_unlock(lck); \
haslck = 0; \
} while (0)
TASKQUEUE_DEFINE_THREAD(kqueue_ctx);
static int kevent_copyout(void *arg, struct kevent *kevp, int count);
static int kevent_copyin(void *arg, struct kevent *kevp, int count);
static int kqueue_register(struct kqueue *kq, struct kevent *kev,
struct thread *td, int mflag);
static int kqueue_acquire(struct file *fp, struct kqueue **kqp);
static void kqueue_release(struct kqueue *kq, int locked);
static void kqueue_destroy(struct kqueue *kq);
static void kqueue_drain(struct kqueue *kq, struct thread *td);
static int kqueue_expand(struct kqueue *kq, struct filterops *fops,
uintptr_t ident, int mflag);
static void kqueue_task(void *arg, int pending);
static int kqueue_scan(struct kqueue *kq, int maxevents,
struct kevent_copyops *k_ops,
const struct timespec *timeout,
struct kevent *keva, struct thread *td);
static void kqueue_wakeup(struct kqueue *kq);
static struct filterops *kqueue_fo_find(int filt);
static void kqueue_fo_release(int filt);
struct g_kevent_args;
static int kern_kevent_generic(struct thread *td,
struct g_kevent_args *uap,
struct kevent_copyops *k_ops, const char *struct_name);
static fo_ioctl_t kqueue_ioctl;
static fo_poll_t kqueue_poll;
static fo_kqfilter_t kqueue_kqfilter;
static fo_stat_t kqueue_stat;
static fo_close_t kqueue_close;
static fo_fill_kinfo_t kqueue_fill_kinfo;
static struct fileops kqueueops = {
.fo_read = invfo_rdwr,
.fo_write = invfo_rdwr,
.fo_truncate = invfo_truncate,
.fo_ioctl = kqueue_ioctl,
.fo_poll = kqueue_poll,
.fo_kqfilter = kqueue_kqfilter,
.fo_stat = kqueue_stat,
.fo_close = kqueue_close,
.fo_chmod = invfo_chmod,
.fo_chown = invfo_chown,
.fo_sendfile = invfo_sendfile,
.fo_fill_kinfo = kqueue_fill_kinfo,
};
static int knote_attach(struct knote *kn, struct kqueue *kq);
static void knote_drop(struct knote *kn, struct thread *td);
static void knote_drop_detached(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(int mflag);
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 void filt_timerstart(struct knote *kn, sbintime_t to);
static void filt_timertouch(struct knote *kn, struct kevent *kev,
u_long type);
static int filt_timervalidate(struct knote *kn, sbintime_t *to);
static int filt_timer(struct knote *kn, long hint);
static int filt_userattach(struct knote *kn);
static void filt_userdetach(struct knote *kn);
static int filt_user(struct knote *kn, long hint);
static void filt_usertouch(struct knote *kn, struct kevent *kev,
u_long type);
static struct filterops file_filtops = {
.f_isfd = 1,
.f_attach = filt_fileattach,
};
static struct filterops kqread_filtops = {
.f_isfd = 1,
.f_detach = filt_kqdetach,
.f_event = filt_kqueue,
};
/* XXX - move to kern_proc.c? */
static struct filterops proc_filtops = {
.f_isfd = 0,
.f_attach = filt_procattach,
.f_detach = filt_procdetach,
.f_event = filt_proc,
};
static struct filterops timer_filtops = {
.f_isfd = 0,
.f_attach = filt_timerattach,
.f_detach = filt_timerdetach,
.f_event = filt_timer,
.f_touch = filt_timertouch,
};
static struct filterops user_filtops = {
.f_attach = filt_userattach,
.f_detach = filt_userdetach,
.f_event = filt_user,
.f_touch = filt_usertouch,
};
static uma_zone_t knote_zone;
static unsigned int kq_ncallouts = 0;
static unsigned int kq_calloutmax = 4 * 1024;
SYSCTL_UINT(_kern, OID_AUTO, kq_calloutmax, CTLFLAG_RW,
&kq_calloutmax, 0, "Maximum number of callouts allocated for kqueue");
/* XXX - ensure not influx ? */
#define KNOTE_ACTIVATE(kn, islock) do { \
if ((islock)) \
mtx_assert(&(kn)->kn_kq->kq_lock, MA_OWNED); \
else \
KQ_LOCK((kn)->kn_kq); \
(kn)->kn_status |= KN_ACTIVE; \
if (((kn)->kn_status & (KN_QUEUED | KN_DISABLED)) == 0) \
knote_enqueue((kn)); \
if (!(islock)) \
KQ_UNLOCK((kn)->kn_kq); \
} while(0)
#define KQ_LOCK(kq) do { \
mtx_lock(&(kq)->kq_lock); \
} while (0)
#define KQ_FLUX_WAKEUP(kq) do { \
if (((kq)->kq_state & KQ_FLUXWAIT) == KQ_FLUXWAIT) { \
(kq)->kq_state &= ~KQ_FLUXWAIT; \
wakeup((kq)); \
} \
} while (0)
#define KQ_UNLOCK_FLUX(kq) do { \
KQ_FLUX_WAKEUP(kq); \
mtx_unlock(&(kq)->kq_lock); \
} while (0)
#define KQ_UNLOCK(kq) do { \
mtx_unlock(&(kq)->kq_lock); \
} while (0)
#define KQ_OWNED(kq) do { \
mtx_assert(&(kq)->kq_lock, MA_OWNED); \
} while (0)
#define KQ_NOTOWNED(kq) do { \
mtx_assert(&(kq)->kq_lock, MA_NOTOWNED); \
} while (0)
static struct knlist *
kn_list_lock(struct knote *kn)
{
struct knlist *knl;
knl = kn->kn_knlist;
if (knl != NULL)
knl->kl_lock(knl->kl_lockarg);
return (knl);
}
static void
kn_list_unlock(struct knlist *knl)
{
bool do_free;
if (knl == NULL)
return;
do_free = knl->kl_autodestroy && knlist_empty(knl);
knl->kl_unlock(knl->kl_lockarg);
if (do_free) {
knlist_destroy(knl);
free(knl, M_KQUEUE);
}
}
static bool
kn_in_flux(struct knote *kn)
{
return (kn->kn_influx > 0);
}
static void
kn_enter_flux(struct knote *kn)
{
KQ_OWNED(kn->kn_kq);
MPASS(kn->kn_influx < INT_MAX);
kn->kn_influx++;
}
static bool
kn_leave_flux(struct knote *kn)
{
KQ_OWNED(kn->kn_kq);
MPASS(kn->kn_influx > 0);
kn->kn_influx--;
return (kn->kn_influx == 0);
}
#define KNL_ASSERT_LOCK(knl, islocked) do { \
if (islocked) \
KNL_ASSERT_LOCKED(knl); \
else \
KNL_ASSERT_UNLOCKED(knl); \
} while (0)
#ifdef INVARIANTS
#define KNL_ASSERT_LOCKED(knl) do { \
knl->kl_assert_locked((knl)->kl_lockarg); \
} while (0)
#define KNL_ASSERT_UNLOCKED(knl) do { \
knl->kl_assert_unlocked((knl)->kl_lockarg); \
} while (0)
#else /* !INVARIANTS */
#define KNL_ASSERT_LOCKED(knl) do {} while(0)
#define KNL_ASSERT_UNLOCKED(knl) do {} while (0)
#endif /* INVARIANTS */
#ifndef KN_HASHSIZE
#define KN_HASHSIZE 64 /* XXX should be tunable */
#endif
#define KN_HASH(val, mask) (((val) ^ (val >> 8)) & (mask))
static int
filt_nullattach(struct knote *kn)
{
return (ENXIO);
};
struct filterops null_filtops = {
.f_isfd = 0,
.f_attach = filt_nullattach,
};
/* XXX - make SYSINIT to add these, and move into respective modules. */
extern struct filterops sig_filtops;
extern struct filterops fs_filtops;
/*
* Table for for all system-defined filters.
*/
static struct mtx filterops_lock;
MTX_SYSINIT(kqueue_filterops, &filterops_lock, "protect sysfilt_ops",
MTX_DEF);
static struct {
struct filterops *for_fop;
int for_nolock;
int for_refcnt;
} sysfilt_ops[EVFILT_SYSCOUNT] = {
{ &file_filtops, 1 }, /* EVFILT_READ */
{ &file_filtops, 1 }, /* EVFILT_WRITE */
{ &null_filtops }, /* EVFILT_AIO */
{ &file_filtops, 1 }, /* EVFILT_VNODE */
{ &proc_filtops, 1 }, /* EVFILT_PROC */
{ &sig_filtops, 1 }, /* EVFILT_SIGNAL */
{ &timer_filtops, 1 }, /* EVFILT_TIMER */
{ &file_filtops, 1 }, /* EVFILT_PROCDESC */
{ &fs_filtops, 1 }, /* EVFILT_FS */
{ &null_filtops }, /* EVFILT_LIO */
{ &user_filtops, 1 }, /* EVFILT_USER */
{ &null_filtops }, /* EVFILT_SENDFILE */
{ &file_filtops, 1 }, /* EVFILT_EMPTY */
};
/*
* Simple redirection for all cdevsw style objects to call their fo_kqfilter
* method.
*/
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 = kn->kn_fp->f_data;
if (kn->kn_filter != EVFILT_READ)
return (EINVAL);
kn->kn_status |= KN_KQUEUE;
kn->kn_fop = &kqread_filtops;
knlist_add(&kq->kq_sel.si_note, kn, 0);
return (0);
}
static void
filt_kqdetach(struct knote *kn)
{
struct kqueue *kq = kn->kn_fp->f_data;
knlist_remove(&kq->kq_sel.si_note, kn, 0);
}
/*ARGSUSED*/
static int
filt_kqueue(struct knote *kn, long hint)
{
struct kqueue *kq = kn->kn_fp->f_data;
kn->kn_data = kq->kq_count;
return (kn->kn_data > 0);
}
/* XXX - move to kern_proc.c? */
static int
filt_procattach(struct knote *kn)
{
struct proc *p;
int error;
bool exiting, immediate;
exiting = immediate = false;
if (kn->kn_sfflags & NOTE_EXIT)
p = pfind_any(kn->kn_id);
else
p = pfind(kn->kn_id);
if (p == NULL)
return (ESRCH);
if (p->p_flag & P_WEXIT)
exiting = true;
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 for the
* purposes of getting a NOTE_CHILD notification.
*/
if (kn->kn_flags & EV_FLAG2) {
kn->kn_flags &= ~EV_FLAG2;
kn->kn_data = kn->kn_sdata; /* ppid */
kn->kn_fflags = NOTE_CHILD;
kn->kn_sfflags &= ~(NOTE_EXIT | NOTE_EXEC | NOTE_FORK);
immediate = true; /* Force immediate activation of child note. */
}
/*
* Internal flag indicating registration done by kernel (for other than
* NOTE_CHILD).
*/
if (kn->kn_flags & EV_FLAG1) {
kn->kn_flags &= ~EV_FLAG1;
}
knlist_add(p->p_klist, kn, 1);
/*
* Immediately activate any child notes or, in the case of a zombie
* target process, exit notes. The latter is necessary to handle the
* case where the target process, e.g. a child, dies before the kevent
* is registered.
*/
if (immediate || (exiting && filt_proc(kn, NOTE_EXIT)))
KNOTE_ACTIVATE(kn, 0);
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.
*/
/* XXX - move to kern_proc.c? */
static void
filt_procdetach(struct knote *kn)
{
knlist_remove(kn->kn_knlist, kn, 0);
kn->kn_ptr.p_proc = NULL;
}
/* XXX - move to kern_proc.c? */
static int
filt_proc(struct knote *kn, long hint)
{
struct proc *p;
u_int event;
p = kn->kn_ptr.p_proc;
if (p == NULL) /* already activated, from attach filter */
return (0);
/* 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_flags |= EV_EOF | EV_ONESHOT;
kn->kn_ptr.p_proc = NULL;
if (kn->kn_fflags & NOTE_EXIT)
kn->kn_data = KW_EXITCODE(p->p_xexit, p->p_xsig);
if (kn->kn_fflags == 0)
kn->kn_flags |= EV_DROP;
return (1);
}
return (kn->kn_fflags != 0);
}
/*
* Called when the process forked. It mostly does the same as the
* knote(), activating all knotes registered to be activated when the
* process forked. Additionally, for each knote attached to the
* parent, check whether user wants to track the new process. If so
* attach a new knote to it, and immediately report an event with the
* child's pid.
*/
void
knote_fork(struct knlist *list, int pid)
{
struct kqueue *kq;
struct knote *kn;
struct kevent kev;
int error;
MPASS(list != NULL);
KNL_ASSERT_LOCKED(list);
if (SLIST_EMPTY(&list->kl_list))
return;
memset(&kev, 0, sizeof(kev));
SLIST_FOREACH(kn, &list->kl_list, kn_selnext) {
kq = kn->kn_kq;
KQ_LOCK(kq);
if (kn_in_flux(kn) && (kn->kn_status & KN_SCAN) == 0) {
KQ_UNLOCK(kq);
continue;
}
/*
* The same as knote(), activate the event.
*/
if ((kn->kn_sfflags & NOTE_TRACK) == 0) {
if (kn->kn_fop->f_event(kn, NOTE_FORK))
KNOTE_ACTIVATE(kn, 1);
KQ_UNLOCK(kq);
continue;
}
/*
* The NOTE_TRACK case. In addition to the activation
* of the event, we need to register new events to
* track the child. Drop the locks in preparation for
* the call to kqueue_register().
*/
kn_enter_flux(kn);
KQ_UNLOCK(kq);
list->kl_unlock(list->kl_lockarg);
/*
* Activate existing knote and register tracking knotes with
* new process.
*
* First register a knote to get just the child notice. This
* must be a separate note from a potential NOTE_EXIT
* notification since both NOTE_CHILD and NOTE_EXIT are defined
* to use the data field (in conflicting ways).
*/
kev.ident = pid;
kev.filter = kn->kn_filter;
kev.flags = kn->kn_flags | EV_ADD | EV_ENABLE | EV_ONESHOT |
EV_FLAG2;
kev.fflags = kn->kn_sfflags;
kev.data = kn->kn_id; /* parent */
kev.udata = kn->kn_kevent.udata;/* preserve udata */
error = kqueue_register(kq, &kev, NULL, M_NOWAIT);
if (error)
kn->kn_fflags |= NOTE_TRACKERR;
/*
* Then register another knote to track other potential events
* from the new process.
*/
kev.ident = 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(kq, &kev, NULL, M_NOWAIT);
if (error)
kn->kn_fflags |= NOTE_TRACKERR;
if (kn->kn_fop->f_event(kn, NOTE_FORK))
KNOTE_ACTIVATE(kn, 0);
list->kl_lock(list->kl_lockarg);
KQ_LOCK(kq);
kn_leave_flux(kn);
KQ_UNLOCK_FLUX(kq);
}
}
/*
* XXX: EVFILT_TIMER should perhaps live in kern_time.c beside the
* interval timer support code.
*/
#define NOTE_TIMER_PRECMASK \
(NOTE_SECONDS | NOTE_MSECONDS | NOTE_USECONDS | NOTE_NSECONDS)
static sbintime_t
timer2sbintime(int64_t data, int flags)
{
int64_t secs;
/*
* Macros for converting to the fractional second portion of an
* sbintime_t using 64bit multiplication to improve precision.
*/
#define NS_TO_SBT(ns) (((ns) * (((uint64_t)1 << 63) / 500000000)) >> 32)
#define US_TO_SBT(us) (((us) * (((uint64_t)1 << 63) / 500000)) >> 32)
#define MS_TO_SBT(ms) (((ms) * (((uint64_t)1 << 63) / 500)) >> 32)
switch (flags & NOTE_TIMER_PRECMASK) {
case NOTE_SECONDS:
#ifdef __LP64__
if (data > (SBT_MAX / SBT_1S))
return (SBT_MAX);
#endif
return ((sbintime_t)data << 32);
case NOTE_MSECONDS: /* FALLTHROUGH */
case 0:
if (data >= 1000) {
secs = data / 1000;
#ifdef __LP64__
if (secs > (SBT_MAX / SBT_1S))
return (SBT_MAX);
#endif
return (secs << 32 | MS_TO_SBT(data % 1000));
}
return (MS_TO_SBT(data));
case NOTE_USECONDS:
if (data >= 1000000) {
secs = data / 1000000;
#ifdef __LP64__
if (secs > (SBT_MAX / SBT_1S))
return (SBT_MAX);
#endif
return (secs << 32 | US_TO_SBT(data % 1000000));
}
return (US_TO_SBT(data));
case NOTE_NSECONDS:
if (data >= 1000000000) {
secs = data / 1000000000;
#ifdef __LP64__
if (secs > (SBT_MAX / SBT_1S))
return (SBT_MAX);
#endif
return (secs << 32 | US_TO_SBT(data % 1000000000));
}
return (NS_TO_SBT(data));
default:
break;
}
return (-1);
}
struct kq_timer_cb_data {
struct callout c;
sbintime_t next; /* next timer event fires at */
sbintime_t to; /* precalculated timer period, 0 for abs */
};
static void
filt_timerexpire(void *knx)
{
struct knote *kn;
struct kq_timer_cb_data *kc;
kn = knx;
kn->kn_data++;
KNOTE_ACTIVATE(kn, 0); /* XXX - handle locking */
if ((kn->kn_flags & EV_ONESHOT) != 0)
return;
kc = kn->kn_ptr.p_v;
if (kc->to == 0)
return;
kc->next += kc->to;
callout_reset_sbt_on(&kc->c, kc->next, 0, filt_timerexpire, kn,
PCPU_GET(cpuid), C_ABSOLUTE);
}
/*
* data contains amount of time to sleep
*/
static int
filt_timervalidate(struct knote *kn, sbintime_t *to)
{
struct bintime bt;
sbintime_t sbt;
if (kn->kn_sdata < 0)
return (EINVAL);
if (kn->kn_sdata == 0 && (kn->kn_flags & EV_ONESHOT) == 0)
kn->kn_sdata = 1;
/*
* The only fflags values supported are the timer unit
* (precision) and the absolute time indicator.
*/
if ((kn->kn_sfflags & ~(NOTE_TIMER_PRECMASK | NOTE_ABSTIME)) != 0)
return (EINVAL);
*to = timer2sbintime(kn->kn_sdata, kn->kn_sfflags);
if ((kn->kn_sfflags & NOTE_ABSTIME) != 0) {
getboottimebin(&bt);
sbt = bttosbt(bt);
*to -= sbt;
}
if (*to < 0)
return (EINVAL);
return (0);
}
static int
filt_timerattach(struct knote *kn)
{
struct kq_timer_cb_data *kc;
sbintime_t to;
unsigned int ncallouts;
int error;
error = filt_timervalidate(kn, &to);
if (error != 0)
return (error);
do {
ncallouts = kq_ncallouts;
if (ncallouts >= kq_calloutmax)
return (ENOMEM);
} while (!atomic_cmpset_int(&kq_ncallouts, ncallouts, ncallouts + 1));
if ((kn->kn_sfflags & NOTE_ABSTIME) == 0)
kn->kn_flags |= EV_CLEAR; /* automatically set */
kn->kn_status &= ~KN_DETACHED; /* knlist_add clears it */
kn->kn_ptr.p_v = kc = malloc(sizeof(*kc), M_KQUEUE, M_WAITOK);
callout_init(&kc->c, 1);
filt_timerstart(kn, to);
return (0);
}
static void
filt_timerstart(struct knote *kn, sbintime_t to)
{
struct kq_timer_cb_data *kc;
kc = kn->kn_ptr.p_v;
if ((kn->kn_sfflags & NOTE_ABSTIME) != 0) {
kc->next = to;
kc->to = 0;
} else {
kc->next = to + sbinuptime();
kc->to = to;
}
callout_reset_sbt_on(&kc->c, kc->next, 0, filt_timerexpire, kn,
PCPU_GET(cpuid), C_ABSOLUTE);
}
static void
filt_timerdetach(struct knote *kn)
{
struct kq_timer_cb_data *kc;
unsigned int old __unused;
kc = kn->kn_ptr.p_v;
callout_drain(&kc->c);
free(kc, M_KQUEUE);
old = atomic_fetchadd_int(&kq_ncallouts, -1);
KASSERT(old > 0, ("Number of callouts cannot become negative"));
kn->kn_status |= KN_DETACHED; /* knlist_remove sets it */
}
static void
filt_timertouch(struct knote *kn, struct kevent *kev, u_long type)
{
struct kq_timer_cb_data *kc;
struct kqueue *kq;
sbintime_t to;
int error;
switch (type) {
case EVENT_REGISTER:
/* Handle re-added timers that update data/fflags */
if (kev->flags & EV_ADD) {
kc = kn->kn_ptr.p_v;
/* Drain any existing callout. */
callout_drain(&kc->c);
/* Throw away any existing undelivered record
* of the timer expiration. This is done under
* the presumption that if a process is
* re-adding this timer with new parameters,
* it is no longer interested in what may have
* happened under the old parameters. If it is
* interested, it can wait for the expiration,
* delete the old timer definition, and then
* add the new one.
*
* This has to be done while the kq is locked:
* - if enqueued, dequeue
* - make it no longer active
* - clear the count of expiration events
*/
kq = kn->kn_kq;
KQ_LOCK(kq);
if (kn->kn_status & KN_QUEUED)
knote_dequeue(kn);
kn->kn_status &= ~KN_ACTIVE;
kn->kn_data = 0;
KQ_UNLOCK(kq);
/* Reschedule timer based on new data/fflags */
kn->kn_sfflags = kev->fflags;
kn->kn_sdata = kev->data;
error = filt_timervalidate(kn, &to);
if (error != 0) {
kn->kn_flags |= EV_ERROR;
kn->kn_data = error;
} else
filt_timerstart(kn, to);
}
break;
case EVENT_PROCESS:
*kev = kn->kn_kevent;
if (kn->kn_flags & EV_CLEAR) {
kn->kn_data = 0;
kn->kn_fflags = 0;
}
break;
default:
panic("filt_timertouch() - invalid type (%ld)", type);
break;
}
}
static int
filt_timer(struct knote *kn, long hint)
{
return (kn->kn_data != 0);
}
static int
filt_userattach(struct knote *kn)
{
/*
* EVFILT_USER knotes are not attached to anything in the kernel.
*/
kn->kn_hook = NULL;
if (kn->kn_fflags & NOTE_TRIGGER)
kn->kn_hookid = 1;
else
kn->kn_hookid = 0;
return (0);
}
static void
filt_userdetach(__unused struct knote *kn)
{
/*
* EVFILT_USER knotes are not attached to anything in the kernel.
*/
}
static int
filt_user(struct knote *kn, __unused long hint)
{
return (kn->kn_hookid);
}
static void
filt_usertouch(struct knote *kn, struct kevent *kev, u_long type)
{
u_int ffctrl;
switch (type) {
case EVENT_REGISTER:
if (kev->fflags & NOTE_TRIGGER)
kn->kn_hookid = 1;
ffctrl = kev->fflags & NOTE_FFCTRLMASK;
kev->fflags &= NOTE_FFLAGSMASK;
switch (ffctrl) {
case NOTE_FFNOP:
break;
case NOTE_FFAND:
kn->kn_sfflags &= kev->fflags;
break;
case NOTE_FFOR:
kn->kn_sfflags |= kev->fflags;
break;
case NOTE_FFCOPY:
kn->kn_sfflags = kev->fflags;
break;
default:
/* XXX Return error? */
break;
}
kn->kn_sdata = kev->data;
if (kev->flags & EV_CLEAR) {
kn->kn_hookid = 0;
kn->kn_data = 0;
kn->kn_fflags = 0;
}
break;
case EVENT_PROCESS:
*kev = kn->kn_kevent;
kev->fflags = kn->kn_sfflags;
kev->data = kn->kn_sdata;
if (kn->kn_flags & EV_CLEAR) {
kn->kn_hookid = 0;
kn->kn_data = 0;
kn->kn_fflags = 0;
}
break;
default:
panic("filt_usertouch() - invalid type (%ld)", type);
break;
}
}
int
sys_kqueue(struct thread *td, struct kqueue_args *uap)
{
return (kern_kqueue(td, 0, NULL));
}
static void
kqueue_init(struct kqueue *kq)
{
mtx_init(&kq->kq_lock, "kqueue", NULL, MTX_DEF | MTX_DUPOK);
TAILQ_INIT(&kq->kq_head);
knlist_init_mtx(&kq->kq_sel.si_note, &kq->kq_lock);
TASK_INIT(&kq->kq_task, 0, kqueue_task, kq);
}
int
kern_kqueue(struct thread *td, int flags, struct filecaps *fcaps)
{
struct filedesc *fdp;
struct kqueue *kq;
struct file *fp;
struct ucred *cred;
int fd, error;
fdp = td->td_proc->p_fd;
cred = td->td_ucred;
if (!chgkqcnt(cred->cr_ruidinfo, 1, lim_cur(td, RLIMIT_KQUEUES)))
return (ENOMEM);
error = falloc_caps(td, &fp, &fd, flags, fcaps);
if (error != 0) {
chgkqcnt(cred->cr_ruidinfo, -1, 0);
return (error);
}
/* An extra reference on `fp' has been held for us by falloc(). */
kq = malloc(sizeof *kq, M_KQUEUE, M_WAITOK | M_ZERO);
kqueue_init(kq);
kq->kq_fdp = fdp;
kq->kq_cred = crhold(cred);
FILEDESC_XLOCK(fdp);
TAILQ_INSERT_HEAD(&fdp->fd_kqlist, kq, kq_list);
FILEDESC_XUNLOCK(fdp);