summaryrefslogtreecommitdiff
path: root/src/pkg/syscall/syscall_linux.go
blob: 4f458be73d8073e7acd3a54ce8c69da554c54438 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// Linux system calls.
// This file is compiled as ordinary Go code,
// but it is also input to mksyscall,
// which parses the //sys lines and generates system call stubs.
// Note that sometimes we use a lowercase //sys name and
// wrap it in our own nicer implementation.

package syscall

import "unsafe"

/*
 * Wrapped
 */

//sys	open(path string, mode int, perm uint32) (fd int, err error)

func Open(path string, mode int, perm uint32) (fd int, err error) {
	return open(path, mode|O_LARGEFILE, perm)
}

//sys	openat(dirfd int, path string, flags int, mode uint32) (fd int, err error)

func Openat(dirfd int, path string, flags int, mode uint32) (fd int, err error) {
	return openat(dirfd, path, flags|O_LARGEFILE, mode)
}

//sysnb	pipe(p *[2]_C_int) (err error)

func Pipe(p []int) (err error) {
	if len(p) != 2 {
		return EINVAL
	}
	var pp [2]_C_int
	err = pipe(&pp)
	p[0] = int(pp[0])
	p[1] = int(pp[1])
	return
}

//sysnb pipe2(p *[2]_C_int, flags int) (err error)

func Pipe2(p []int, flags int) (err error) {
	if len(p) != 2 {
		return EINVAL
	}
	var pp [2]_C_int
	err = pipe2(&pp, flags)
	p[0] = int(pp[0])
	p[1] = int(pp[1])
	return
}

//sys	utimes(path string, times *[2]Timeval) (err error)

func Utimes(path string, tv []Timeval) (err error) {
	if len(tv) != 2 {
		return EINVAL
	}
	return utimes(path, (*[2]Timeval)(unsafe.Pointer(&tv[0])))
}

//sys	utimensat(dirfd int, path string, times *[2]Timespec) (err error)

func UtimesNano(path string, ts []Timespec) (err error) {
	if len(ts) != 2 {
		return EINVAL
	}
	err = utimensat(_AT_FDCWD, path, (*[2]Timespec)(unsafe.Pointer(&ts[0])))
	if err != ENOSYS {
		return err
	}
	// If the utimensat syscall isn't available (utimensat was added to Linux
	// in 2.6.22, Released, 8 July 2007) then fall back to utimes
	var tv [2]Timeval
	for i := 0; i < 2; i++ {
		tv[i].Sec = ts[i].Sec
		tv[i].Usec = ts[i].Nsec / 1000
	}
	return utimes(path, (*[2]Timeval)(unsafe.Pointer(&tv[0])))
}

//sys	futimesat(dirfd int, path *byte, times *[2]Timeval) (err error)

func Futimesat(dirfd int, path string, tv []Timeval) (err error) {
	if len(tv) != 2 {
		return EINVAL
	}
	pathp, err := BytePtrFromString(path)
	if err != nil {
		return err
	}
	return futimesat(dirfd, pathp, (*[2]Timeval)(unsafe.Pointer(&tv[0])))
}

func Futimes(fd int, tv []Timeval) (err error) {
	// Believe it or not, this is the best we can do on Linux
	// (and is what glibc does).
	return Utimes("/proc/self/fd/"+itoa(fd), tv)
}

const ImplementsGetwd = true

//sys	Getcwd(buf []byte) (n int, err error)

func Getwd() (wd string, err error) {
	var buf [PathMax]byte
	n, err := Getcwd(buf[0:])
	if err != nil {
		return "", err
	}
	// Getcwd returns the number of bytes written to buf, including the NUL.
	if n < 1 || n > len(buf) || buf[n-1] != 0 {
		return "", EINVAL
	}
	return string(buf[0 : n-1]), nil
}

func Getgroups() (gids []int, err error) {
	n, err := getgroups(0, nil)
	if err != nil {
		return nil, err
	}
	if n == 0 {
		return nil, nil
	}

	// Sanity check group count.  Max is 1<<16 on Linux.
	if n < 0 || n > 1<<20 {
		return nil, EINVAL
	}

	a := make([]_Gid_t, n)
	n, err = getgroups(n, &a[0])
	if err != nil {
		return nil, err
	}
	gids = make([]int, n)
	for i, v := range a[0:n] {
		gids[i] = int(v)
	}
	return
}

func Setgroups(gids []int) (err error) {
	if len(gids) == 0 {
		return setgroups(0, nil)
	}

	a := make([]_Gid_t, len(gids))
	for i, v := range gids {
		a[i] = _Gid_t(v)
	}
	return setgroups(len(a), &a[0])
}

type WaitStatus uint32

// Wait status is 7 bits at bottom, either 0 (exited),
// 0x7F (stopped), or a signal number that caused an exit.
// The 0x80 bit is whether there was a core dump.
// An extra number (exit code, signal causing a stop)
// is in the high bits.  At least that's the idea.
// There are various irregularities.  For example, the
// "continued" status is 0xFFFF, distinguishing itself
// from stopped via the core dump bit.

const (
	mask    = 0x7F
	core    = 0x80
	exited  = 0x00
	stopped = 0x7F
	shift   = 8
)

func (w WaitStatus) Exited() bool { return w&mask == exited }

func (w WaitStatus) Signaled() bool { return w&mask != stopped && w&mask != exited }

func (w WaitStatus) Stopped() bool { return w&0xFF == stopped }

func (w WaitStatus) Continued() bool { return w == 0xFFFF }

func (w WaitStatus) CoreDump() bool { return w.Signaled() && w&core != 0 }

func (w WaitStatus) ExitStatus() int {
	if !w.Exited() {
		return -1
	}
	return int(w>>shift) & 0xFF
}

func (w WaitStatus) Signal() Signal {
	if !w.Signaled() {
		return -1
	}
	return Signal(w & mask)
}

func (w WaitStatus) StopSignal() Signal {
	if !w.Stopped() {
		return -1
	}
	return Signal(w>>shift) & 0xFF
}

func (w WaitStatus) TrapCause() int {
	if w.StopSignal() != SIGTRAP {
		return -1
	}
	return int(w>>shift) >> 8
}

//sys	wait4(pid int, wstatus *_C_int, options int, rusage *Rusage) (wpid int, err error)

func Wait4(pid int, wstatus *WaitStatus, options int, rusage *Rusage) (wpid int, err error) {
	var status _C_int
	wpid, err = wait4(pid, &status, options, rusage)
	if wstatus != nil {
		*wstatus = WaitStatus(status)
	}
	return
}

func Mkfifo(path string, mode uint32) (err error) {
	return Mknod(path, mode|S_IFIFO, 0)
}

// For testing: clients can set this flag to force
// creation of IPv6 sockets to return EAFNOSUPPORT.
var SocketDisableIPv6 bool

type Sockaddr interface {
	sockaddr() (ptr uintptr, len _Socklen, err error) // lowercase; only we can define Sockaddrs
}

type SockaddrInet4 struct {
	Port int
	Addr [4]byte
	raw  RawSockaddrInet4
}

func (sa *SockaddrInet4) sockaddr() (uintptr, _Socklen, error) {
	if sa.Port < 0 || sa.Port > 0xFFFF {
		return 0, 0, EINVAL
	}
	sa.raw.Family = AF_INET
	p := (*[2]byte)(unsafe.Pointer(&sa.raw.Port))
	p[0] = byte(sa.Port >> 8)
	p[1] = byte(sa.Port)
	for i := 0; i < len(sa.Addr); i++ {
		sa.raw.Addr[i] = sa.Addr[i]
	}
	return uintptr(unsafe.Pointer(&sa.raw)), SizeofSockaddrInet4, nil
}

type SockaddrInet6 struct {
	Port   int
	ZoneId uint32
	Addr   [16]byte
	raw    RawSockaddrInet6
}

func (sa *SockaddrInet6) sockaddr() (uintptr, _Socklen, error) {
	if sa.Port < 0 || sa.Port > 0xFFFF {
		return 0, 0, EINVAL
	}
	sa.raw.Family = AF_INET6
	p := (*[2]byte)(unsafe.Pointer(&sa.raw.Port))
	p[0] = byte(sa.Port >> 8)
	p[1] = byte(sa.Port)
	sa.raw.Scope_id = sa.ZoneId
	for i := 0; i < len(sa.Addr); i++ {
		sa.raw.Addr[i] = sa.Addr[i]
	}
	return uintptr(unsafe.Pointer(&sa.raw)), SizeofSockaddrInet6, nil
}

type SockaddrUnix struct {
	Name string
	raw  RawSockaddrUnix
}

func (sa *SockaddrUnix) sockaddr() (uintptr, _Socklen, error) {
	name := sa.Name
	n := len(name)
	if n >= len(sa.raw.Path) {
		return 0, 0, EINVAL
	}
	sa.raw.Family = AF_UNIX
	for i := 0; i < n; i++ {
		sa.raw.Path[i] = int8(name[i])
	}
	// length is family (uint16), name, NUL.
	sl := _Socklen(2)
	if n > 0 {
		sl += _Socklen(n) + 1
	}
	if sa.raw.Path[0] == '@' {
		sa.raw.Path[0] = 0
		// Don't count trailing NUL for abstract address.
		sl--
	}

	return uintptr(unsafe.Pointer(&sa.raw)), sl, nil
}

type SockaddrLinklayer struct {
	Protocol uint16
	Ifindex  int
	Hatype   uint16
	Pkttype  uint8
	Halen    uint8
	Addr     [8]byte
	raw      RawSockaddrLinklayer
}

func (sa *SockaddrLinklayer) sockaddr() (uintptr, _Socklen, error) {
	if sa.Ifindex < 0 || sa.Ifindex > 0x7fffffff {
		return 0, 0, EINVAL
	}
	sa.raw.Family = AF_PACKET
	sa.raw.Protocol = sa.Protocol
	sa.raw.Ifindex = int32(sa.Ifindex)
	sa.raw.Hatype = sa.Hatype
	sa.raw.Pkttype = sa.Pkttype
	sa.raw.Halen = sa.Halen
	for i := 0; i < len(sa.Addr); i++ {
		sa.raw.Addr[i] = sa.Addr[i]
	}
	return uintptr(unsafe.Pointer(&sa.raw)), SizeofSockaddrLinklayer, nil
}

type SockaddrNetlink struct {
	Family uint16
	Pad    uint16
	Pid    uint32
	Groups uint32
	raw    RawSockaddrNetlink
}

func (sa *SockaddrNetlink) sockaddr() (uintptr, _Socklen, error) {
	sa.raw.Family = AF_NETLINK
	sa.raw.Pad = sa.Pad
	sa.raw.Pid = sa.Pid
	sa.raw.Groups = sa.Groups
	return uintptr(unsafe.Pointer(&sa.raw)), SizeofSockaddrNetlink, nil
}

func anyToSockaddr(rsa *RawSockaddrAny) (Sockaddr, error) {
	switch rsa.Addr.Family {
	case AF_NETLINK:
		pp := (*RawSockaddrNetlink)(unsafe.Pointer(rsa))
		sa := new(SockaddrNetlink)
		sa.Family = pp.Family
		sa.Pad = pp.Pad
		sa.Pid = pp.Pid
		sa.Groups = pp.Groups
		return sa, nil

	case AF_PACKET:
		pp := (*RawSockaddrLinklayer)(unsafe.Pointer(rsa))
		sa := new(SockaddrLinklayer)
		sa.Protocol = pp.Protocol
		sa.Ifindex = int(pp.Ifindex)
		sa.Hatype = pp.Hatype
		sa.Pkttype = pp.Pkttype
		sa.Halen = pp.Halen
		for i := 0; i < len(sa.Addr); i++ {
			sa.Addr[i] = pp.Addr[i]
		}
		return sa, nil

	case AF_UNIX:
		pp := (*RawSockaddrUnix)(unsafe.Pointer(rsa))
		sa := new(SockaddrUnix)
		if pp.Path[0] == 0 {
			// "Abstract" Unix domain socket.
			// Rewrite leading NUL as @ for textual display.
			// (This is the standard convention.)
			// Not friendly to overwrite in place,
			// but the callers below don't care.
			pp.Path[0] = '@'
		}

		// Assume path ends at NUL.
		// This is not technically the Linux semantics for
		// abstract Unix domain sockets--they are supposed
		// to be uninterpreted fixed-size binary blobs--but
		// everyone uses this convention.
		n := 0
		for n < len(pp.Path) && pp.Path[n] != 0 {
			n++
		}
		bytes := (*[10000]byte)(unsafe.Pointer(&pp.Path[0]))[0:n]
		sa.Name = string(bytes)
		return sa, nil

	case AF_INET:
		pp := (*RawSockaddrInet4)(unsafe.Pointer(rsa))
		sa := new(SockaddrInet4)
		p := (*[2]byte)(unsafe.Pointer(&pp.Port))
		sa.Port = int(p[0])<<8 + int(p[1])
		for i := 0; i < len(sa.Addr); i++ {
			sa.Addr[i] = pp.Addr[i]
		}
		return sa, nil

	case AF_INET6:
		pp := (*RawSockaddrInet6)(unsafe.Pointer(rsa))
		sa := new(SockaddrInet6)
		p := (*[2]byte)(unsafe.Pointer(&pp.Port))
		sa.Port = int(p[0])<<8 + int(p[1])
		sa.ZoneId = pp.Scope_id
		for i := 0; i < len(sa.Addr); i++ {
			sa.Addr[i] = pp.Addr[i]
		}
		return sa, nil
	}
	return nil, EAFNOSUPPORT
}

func Accept(fd int) (nfd int, sa Sockaddr, err error) {
	var rsa RawSockaddrAny
	var len _Socklen = SizeofSockaddrAny
	nfd, err = accept(fd, &rsa, &len)
	if err != nil {
		return
	}
	sa, err = anyToSockaddr(&rsa)
	if err != nil {
		Close(nfd)
		nfd = 0
	}
	return
}

func Accept4(fd int, flags int) (nfd int, sa Sockaddr, err error) {
	var rsa RawSockaddrAny
	var len _Socklen = SizeofSockaddrAny
	nfd, err = accept4(fd, &rsa, &len, flags)
	if err != nil {
		return
	}
	sa, err = anyToSockaddr(&rsa)
	if err != nil {
		Close(nfd)
		nfd = 0
	}
	return
}

func Getsockname(fd int) (sa Sockaddr, err error) {
	var rsa RawSockaddrAny
	var len _Socklen = SizeofSockaddrAny
	if err = getsockname(fd, &rsa, &len); err != nil {
		return
	}
	return anyToSockaddr(&rsa)
}

func Getpeername(fd int) (sa Sockaddr, err error) {
	var rsa RawSockaddrAny
	var len _Socklen = SizeofSockaddrAny
	if err = getpeername(fd, &rsa, &len); err != nil {
		return
	}
	return anyToSockaddr(&rsa)
}

func Bind(fd int, sa Sockaddr) (err error) {
	ptr, n, err := sa.sockaddr()
	if err != nil {
		return err
	}
	return bind(fd, ptr, n)
}

func Connect(fd int, sa Sockaddr) (err error) {
	ptr, n, err := sa.sockaddr()
	if err != nil {
		return err
	}
	return connect(fd, ptr, n)
}

func Socket(domain, typ, proto int) (fd int, err error) {
	if domain == AF_INET6 && SocketDisableIPv6 {
		return -1, EAFNOSUPPORT
	}
	fd, err = socket(domain, typ, proto)
	return
}

func Socketpair(domain, typ, proto int) (fd [2]int, err error) {
	var fdx [2]int32
	err = socketpair(domain, typ, proto, &fdx)
	if err == nil {
		fd[0] = int(fdx[0])
		fd[1] = int(fdx[1])
	}
	return
}

func GetsockoptInt(fd, level, opt int) (value int, err error) {
	var n int32
	vallen := _Socklen(4)
	err = getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&n)), &vallen)
	return int(n), err
}

func GetsockoptInet4Addr(fd, level, opt int) (value [4]byte, err error) {
	vallen := _Socklen(4)
	err = getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value[0])), &vallen)
	return value, err
}

func GetsockoptIPMreq(fd, level, opt int) (*IPMreq, error) {
	var value IPMreq
	vallen := _Socklen(SizeofIPMreq)
	err := getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value)), &vallen)
	return &value, err
}

func GetsockoptIPMreqn(fd, level, opt int) (*IPMreqn, error) {
	var value IPMreqn
	vallen := _Socklen(SizeofIPMreqn)
	err := getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value)), &vallen)
	return &value, err
}

func GetsockoptIPv6Mreq(fd, level, opt int) (*IPv6Mreq, error) {
	var value IPv6Mreq
	vallen := _Socklen(SizeofIPv6Mreq)
	err := getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value)), &vallen)
	return &value, err
}

func GetsockoptUcred(fd, level, opt int) (*Ucred, error) {
	var value Ucred
	vallen := _Socklen(SizeofUcred)
	err := getsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value)), &vallen)
	return &value, err
}

func SetsockoptInt(fd, level, opt int, value int) (err error) {
	var n = int32(value)
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(&n)), 4)
}

func SetsockoptInet4Addr(fd, level, opt int, value [4]byte) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(&value[0])), 4)
}

func SetsockoptTimeval(fd, level, opt int, tv *Timeval) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(tv)), unsafe.Sizeof(*tv))
}

func SetsockoptLinger(fd, level, opt int, l *Linger) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(l)), unsafe.Sizeof(*l))
}

func SetsockoptIPMreq(fd, level, opt int, mreq *IPMreq) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(mreq)), unsafe.Sizeof(*mreq))
}

func SetsockoptIPMreqn(fd, level, opt int, mreq *IPMreqn) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(mreq)), unsafe.Sizeof(*mreq))
}

func SetsockoptIPv6Mreq(fd, level, opt int, mreq *IPv6Mreq) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(mreq)), unsafe.Sizeof(*mreq))
}

func SetsockoptString(fd, level, opt int, s string) (err error) {
	return setsockopt(fd, level, opt, uintptr(unsafe.Pointer(&[]byte(s)[0])), uintptr(len(s)))
}

func Recvfrom(fd int, p []byte, flags int) (n int, from Sockaddr, err error) {
	var rsa RawSockaddrAny
	var len _Socklen = SizeofSockaddrAny
	if n, err = recvfrom(fd, p, flags, &rsa, &len); err != nil {
		return
	}
	if rsa.Addr.Family != AF_UNSPEC {
		from, err = anyToSockaddr(&rsa)
	}
	return
}

func Sendto(fd int, p []byte, flags int, to Sockaddr) (err error) {
	ptr, n, err := to.sockaddr()
	if err != nil {
		return err
	}
	return sendto(fd, p, flags, ptr, n)
}

func Recvmsg(fd int, p, oob []byte, flags int) (n, oobn int, recvflags int, from Sockaddr, err error) {
	var msg Msghdr
	var rsa RawSockaddrAny
	msg.Name = (*byte)(unsafe.Pointer(&rsa))
	msg.Namelen = uint32(SizeofSockaddrAny)
	var iov Iovec
	if len(p) > 0 {
		iov.Base = (*byte)(unsafe.Pointer(&p[0]))
		iov.SetLen(len(p))
	}
	var dummy byte
	if len(oob) > 0 {
		// receive at least one normal byte
		if len(p) == 0 {
			iov.Base = &dummy
			iov.SetLen(1)
		}
		msg.Control = (*byte)(unsafe.Pointer(&oob[0]))
		msg.SetControllen(len(oob))
	}
	msg.Iov = &iov
	msg.Iovlen = 1
	if n, err = recvmsg(fd, &msg, flags); err != nil {
		return
	}
	oobn = int(msg.Controllen)
	recvflags = int(msg.Flags)
	// source address is only specified if the socket is unconnected
	if rsa.Addr.Family != AF_UNSPEC {
		from, err = anyToSockaddr(&rsa)
	}
	return
}

func Sendmsg(fd int, p, oob []byte, to Sockaddr, flags int) (err error) {
	var ptr uintptr
	var salen _Socklen
	if to != nil {
		var err error
		ptr, salen, err = to.sockaddr()
		if err != nil {
			return err
		}
	}
	var msg Msghdr
	msg.Name = (*byte)(unsafe.Pointer(ptr))
	msg.Namelen = uint32(salen)
	var iov Iovec
	if len(p) > 0 {
		iov.Base = (*byte)(unsafe.Pointer(&p[0]))
		iov.SetLen(len(p))
	}
	var dummy byte
	if len(oob) > 0 {
		// send at least one normal byte
		if len(p) == 0 {
			iov.Base = &dummy
			iov.SetLen(1)
		}
		msg.Control = (*byte)(unsafe.Pointer(&oob[0]))
		msg.SetControllen(len(oob))
	}
	msg.Iov = &iov
	msg.Iovlen = 1
	if err = sendmsg(fd, &msg, flags); err != nil {
		return
	}
	return
}

// BindToDevice binds the socket associated with fd to device.
func BindToDevice(fd int, device string) (err error) {
	return SetsockoptString(fd, SOL_SOCKET, SO_BINDTODEVICE, device)
}

//sys	ptrace(request int, pid int, addr uintptr, data uintptr) (err error)

func ptracePeek(req int, pid int, addr uintptr, out []byte) (count int, err error) {
	// The peek requests are machine-size oriented, so we wrap it
	// to retrieve arbitrary-length data.

	// The ptrace syscall differs from glibc's ptrace.
	// Peeks returns the word in *data, not as the return value.

	var buf [sizeofPtr]byte

	// Leading edge.  PEEKTEXT/PEEKDATA don't require aligned
	// access (PEEKUSER warns that it might), but if we don't
	// align our reads, we might straddle an unmapped page
	// boundary and not get the bytes leading up to the page
	// boundary.
	n := 0
	if addr%sizeofPtr != 0 {
		err = ptrace(req, pid, addr-addr%sizeofPtr, uintptr(unsafe.Pointer(&buf[0])))
		if err != nil {
			return 0, err
		}
		n += copy(out, buf[addr%sizeofPtr:])
		out = out[n:]
	}

	// Remainder.
	for len(out) > 0 {
		// We use an internal buffer to guarantee alignment.
		// It's not documented if this is necessary, but we're paranoid.
		err = ptrace(req, pid, addr+uintptr(n), uintptr(unsafe.Pointer(&buf[0])))
		if err != nil {
			return n, err
		}
		copied := copy(out, buf[0:])
		n += copied
		out = out[copied:]
	}

	return n, nil
}

func PtracePeekText(pid int, addr uintptr, out []byte) (count int, err error) {
	return ptracePeek(PTRACE_PEEKTEXT, pid, addr, out)
}

func PtracePeekData(pid int, addr uintptr, out []byte) (count int, err error) {
	return ptracePeek(PTRACE_PEEKDATA, pid, addr, out)
}

func ptracePoke(pokeReq int, peekReq int, pid int, addr uintptr, data []byte) (count int, err error) {
	// As for ptracePeek, we need to align our accesses to deal
	// with the possibility of straddling an invalid page.

	// Leading edge.
	n := 0
	if addr%sizeofPtr != 0 {
		var buf [sizeofPtr]byte
		err = ptrace(peekReq, pid, addr-addr%sizeofPtr, uintptr(unsafe.Pointer(&buf[0])))
		if err != nil {
			return 0, err
		}
		n += copy(buf[addr%sizeofPtr:], data)
		word := *((*uintptr)(unsafe.Pointer(&buf[0])))
		err = ptrace(pokeReq, pid, addr-addr%sizeofPtr, word)
		if err != nil {
			return 0, err
		}
		data = data[n:]
	}

	// Interior.
	for len(data) > sizeofPtr {
		word := *((*uintptr)(unsafe.Pointer(&data[0])))
		err = ptrace(pokeReq, pid, addr+uintptr(n), word)
		if err != nil {
			return n, err
		}
		n += sizeofPtr
		data = data[sizeofPtr:]
	}

	// Trailing edge.
	if len(data) > 0 {
		var buf [sizeofPtr]byte
		err = ptrace(peekReq, pid, addr+uintptr(n), uintptr(unsafe.Pointer(&buf[0])))
		if err != nil {
			return n, err
		}
		copy(buf[0:], data)
		word := *((*uintptr)(unsafe.Pointer(&buf[0])))
		err = ptrace(pokeReq, pid, addr+uintptr(n), word)
		if err != nil {
			return n, err
		}
		n += len(data)
	}

	return n, nil
}

func PtracePokeText(pid int, addr uintptr, data []byte) (count int, err error) {
	return ptracePoke(PTRACE_POKETEXT, PTRACE_PEEKTEXT, pid, addr, data)
}

func PtracePokeData(pid int, addr uintptr, data []byte) (count int, err error) {
	return ptracePoke(PTRACE_POKEDATA, PTRACE_PEEKDATA, pid, addr, data)
}

func PtraceGetRegs(pid int, regsout *PtraceRegs) (err error) {
	return ptrace(PTRACE_GETREGS, pid, 0, uintptr(unsafe.Pointer(regsout)))
}

func PtraceSetRegs(pid int, regs *PtraceRegs) (err error) {
	return ptrace(PTRACE_SETREGS, pid, 0, uintptr(unsafe.Pointer(regs)))
}

func PtraceSetOptions(pid int, options int) (err error) {
	return ptrace(PTRACE_SETOPTIONS, pid, 0, uintptr(options))
}

func PtraceGetEventMsg(pid int) (msg uint, err error) {
	var data _C_long
	err = ptrace(PTRACE_GETEVENTMSG, pid, 0, uintptr(unsafe.Pointer(&data)))
	msg = uint(data)
	return
}

func PtraceCont(pid int, signal int) (err error) {
	return ptrace(PTRACE_CONT, pid, 0, uintptr(signal))
}

func PtraceSyscall(pid int, signal int) (err error) {
	return ptrace(PTRACE_SYSCALL, pid, 0, uintptr(signal))
}

func PtraceSingleStep(pid int) (err error) { return ptrace(PTRACE_SINGLESTEP, pid, 0, 0) }

func PtraceAttach(pid int) (err error) { return ptrace(PTRACE_ATTACH, pid, 0, 0) }

func PtraceDetach(pid int) (err error) { return ptrace(PTRACE_DETACH, pid, 0, 0) }

//sys	reboot(magic1 uint, magic2 uint, cmd int, arg string) (err error)

func Reboot(cmd int) (err error) {
	return reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, "")
}

func clen(n []byte) int {
	for i := 0; i < len(n); i++ {
		if n[i] == 0 {
			return i
		}
	}
	return len(n)
}

func ReadDirent(fd int, buf []byte) (n int, err error) {
	return Getdents(fd, buf)
}

func ParseDirent(buf []byte, max int, names []string) (consumed int, count int, newnames []string) {
	origlen := len(buf)
	count = 0
	for max != 0 && len(buf) > 0 {
		dirent := (*Dirent)(unsafe.Pointer(&buf[0]))
		buf = buf[dirent.Reclen:]
		if dirent.Ino == 0 { // File absent in directory.
			continue
		}
		bytes := (*[10000]byte)(unsafe.Pointer(&dirent.Name[0]))
		var name = string(bytes[0:clen(bytes[:])])
		if name == "." || name == ".." { // Useless names
			continue
		}
		max--
		count++
		names = append(names, name)
	}
	return origlen - len(buf), count, names
}

//sys	mount(source string, target string, fstype string, flags uintptr, data *byte) (err error)

func Mount(source string, target string, fstype string, flags uintptr, data string) (err error) {
	// Certain file systems get rather angry and EINVAL if you give
	// them an empty string of data, rather than NULL.
	if data == "" {
		return mount(source, target, fstype, flags, nil)
	}
	datap, err := BytePtrFromString(data)
	if err != nil {
		return err
	}
	return mount(source, target, fstype, flags, datap)
}

// Sendto
// Recvfrom
// Socketpair

/*
 * Direct access
 */
//sys	Access(path string, mode uint32) (err error)
//sys	Acct(path string) (err error)
//sys	Adjtimex(buf *Timex) (state int, err error)
//sys	Chdir(path string) (err error)
//sys	Chmod(path string, mode uint32) (err error)
//sys	Chroot(path string) (err error)
//sys	Close(fd int) (err error)
//sys	Creat(path string, mode uint32) (fd int, err error)
//sysnb	Dup(oldfd int) (fd int, err error)
//sysnb	Dup2(oldfd int, newfd int) (err error)
//sysnb	EpollCreate(size int) (fd int, err error)
//sysnb	EpollCreate1(flag int) (fd int, err error)
//sysnb	EpollCtl(epfd int, op int, fd int, event *EpollEvent) (err error)
//sys	EpollWait(epfd int, events []EpollEvent, msec int) (n int, err error)
//sys	Exit(code int) = SYS_EXIT_GROUP
//sys	Faccessat(dirfd int, path string, mode uint32, flags int) (err error)
//sys	Fallocate(fd int, mode uint32, off int64, len int64) (err error)
//sys	Fchdir(fd int) (err error)
//sys	Fchmod(fd int, mode uint32) (err error)
//sys	Fchmodat(dirfd int, path string, mode uint32, flags int) (err error)
//sys	Fchownat(dirfd int, path string, uid int, gid int, flags int) (err error)
//sys	fcntl(fd int, cmd int, arg int) (val int, err error)
//sys	Fdatasync(fd int) (err error)
//sys	Flock(fd int, how int) (err error)
//sys	Fsync(fd int) (err error)
//sys	Getdents(fd int, buf []byte) (n int, err error) = SYS_GETDENTS64
//sysnb	Getpgid(pid int) (pgid int, err error)
//sysnb	Getpgrp() (pid int)
//sysnb	Getpid() (pid int)
//sysnb	Getppid() (ppid int)
//sysnb	Getrusage(who int, rusage *Rusage) (err error)
//sysnb	Gettid() (tid int)
//sys	Getxattr(path string, attr string, dest []byte) (sz int, err error)
//sys	InotifyAddWatch(fd int, pathname string, mask uint32) (watchdesc int, err error)
//sysnb	InotifyInit() (fd int, err error)
//sysnb	InotifyInit1(flags int) (fd int, err error)
//sysnb	InotifyRmWatch(fd int, watchdesc uint32) (success int, err error)
//sysnb	Kill(pid int, sig Signal) (err error)
//sys	Klogctl(typ int, buf []byte) (n int, err error) = SYS_SYSLOG
//sys	Link(oldpath string, newpath string) (err error)
//sys	Listxattr(path string, dest []byte) (sz int, err error)
//sys	Mkdir(path string, mode uint32) (err error)
//sys	Mkdirat(dirfd int, path string, mode uint32) (err error)
//sys	Mknod(path string, mode uint32, dev int) (err error)
//sys	Mknodat(dirfd int, path string, mode uint32, dev int) (err error)
//sys	Nanosleep(time *Timespec, leftover *Timespec) (err error)
//sys	Pause() (err error)
//sys	PivotRoot(newroot string, putold string) (err error) = SYS_PIVOT_ROOT
//sysnb prlimit(pid int, resource int, old *Rlimit, newlimit *Rlimit) (err error) = SYS_PRLIMIT64
//sys	read(fd int, p []byte) (n int, err error)
//sys	Readlink(path string, buf []byte) (n int, err error)
//sys	Removexattr(path string, attr string) (err error)
//sys	Rename(oldpath string, newpath string) (err error)
//sys	Renameat(olddirfd int, oldpath string, newdirfd int, newpath string) (err error)
//sys	Rmdir(path string) (err error)
//sys	Setdomainname(p []byte) (err error)
//sys	Sethostname(p []byte) (err error)
//sysnb	Setpgid(pid int, pgid int) (err error)
//sysnb	Setsid() (pid int, err error)
//sysnb	Settimeofday(tv *Timeval) (err error)
//sysnb	Setuid(uid int) (err error)
//sys	Setxattr(path string, attr string, data []byte, flags int) (err error)
//sys	Symlink(oldpath string, newpath string) (err error)
//sys	Sync()
//sysnb	Sysinfo(info *Sysinfo_t) (err error)
//sys	Tee(rfd int, wfd int, len int, flags int) (n int64, err error)
//sysnb	Tgkill(tgid int, tid int, sig Signal) (err error)
//sysnb	Times(tms *Tms) (ticks uintptr, err error)
//sysnb	Umask(mask int) (oldmask int)
//sysnb	Uname(buf *Utsname) (err error)
//sys	Unlink(path string) (err error)
//sys	Unlinkat(dirfd int, path string) (err error)
//sys	Unmount(target string, flags int) (err error) = SYS_UMOUNT2
//sys	Unshare(flags int) (err error)
//sys	Ustat(dev int, ubuf *Ustat_t) (err error)
//sys	Utime(path string, buf *Utimbuf) (err error)
//sys	write(fd int, p []byte) (n int, err error)
//sys	exitThread(code int) (err error) = SYS_EXIT
//sys	readlen(fd int, p *byte, np int) (n int, err error) = SYS_READ
//sys	writelen(fd int, p *byte, np int) (n int, err error) = SYS_WRITE

// mmap varies by architecture; see syscall_linux_*.go.
//sys	munmap(addr uintptr, length uintptr) (err error)

var mapper = &mmapper{
	active: make(map[*byte][]byte),
	mmap:   mmap,
	munmap: munmap,
}

func Mmap(fd int, offset int64, length int, prot int, flags int) (data []byte, err error) {
	return mapper.Mmap(fd, offset, length, prot, flags)
}

func Munmap(b []byte) (err error) {
	return mapper.Munmap(b)
}

//sys	Madvise(b []byte, advice int) (err error)
//sys	Mprotect(b []byte, prot int) (err error)
//sys	Mlock(b []byte) (err error)
//sys	Munlock(b []byte) (err error)
//sys	Mlockall(flags int) (err error)
//sys	Munlockall() (err error)

/*
 * Unimplemented
 */
// AddKey
// AfsSyscall
// Alarm
// ArchPrctl
// Brk
// Capget
// Capset
// ClockGetres
// ClockGettime
// ClockNanosleep
// ClockSettime
// Clone
// CreateModule
// DeleteModule
// EpollCtlOld
// EpollPwait
// EpollWaitOld
// Eventfd
// Execve
// Fadvise64
// Fgetxattr
// Flistxattr
// Fork
// Fremovexattr
// Fsetxattr
// Futex
// GetKernelSyms
// GetMempolicy
// GetRobustList
// GetThreadArea
// Getitimer
// Getpmsg
// Getpriority
// IoCancel
// IoDestroy
// IoGetevents
// IoSetup
// IoSubmit
// Ioctl
// IoprioGet
// IoprioSet
// KexecLoad
// Keyctl
// Lgetxattr
// Llistxattr
// LookupDcookie
// Lremovexattr
// Lsetxattr
// Mbind
// MigratePages
// Mincore
// ModifyLdt
// Mount
// MovePages
// Mprotect
// MqGetsetattr
// MqNotify
// MqOpen
// MqTimedreceive
// MqTimedsend
// MqUnlink
// Mremap
// Msgctl
// Msgget
// Msgrcv
// Msgsnd
// Msync
// Newfstatat
// Nfsservctl
// Personality
// Poll
// Ppoll
// Prctl
// Pselect6
// Ptrace
// Putpmsg
// QueryModule
// Quotactl
// Readahead
// Readv
// RemapFilePages
// RequestKey
// RestartSyscall
// RtSigaction
// RtSigpending
// RtSigprocmask
// RtSigqueueinfo
// RtSigreturn
// RtSigsuspend
// RtSigtimedwait
// SchedGetPriorityMax
// SchedGetPriorityMin
// SchedGetaffinity
// SchedGetparam
// SchedGetscheduler
// SchedRrGetInterval
// SchedSetaffinity
// SchedSetparam
// SchedYield
// Security
// Semctl
// Semget
// Semop
// Semtimedop
// SetMempolicy
// SetRobustList
// SetThreadArea
// SetTidAddress
// Setpriority
// Shmat
// Shmctl
// Shmdt
// Shmget
// Sigaltstack
// Signalfd
// Swapoff
// Swapon
// Sysfs
// TimerCreate
// TimerDelete
// TimerGetoverrun
// TimerGettime
// TimerSettime
// Timerfd
// Tkill (obsolete)
// Tuxcall
// Umount2
// Uselib
// Utimensat
// Vfork
// Vhangup
// Vmsplice
// Vserver
// Waitid
// _Sysctl