aboutsummaryrefslogtreecommitdiff
path: root/sys/compat/linux/linux_misc.c
blob: e85fec31ab35fdb56f8cb93f8ea69a7f4a9c6ade (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
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
/*-
 * Copyright (c) 2002 Doug Rabson
 * Copyright (c) 1994-1995 Sren Schmidt
 * 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
 *    in this position and unchanged.
 * 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.
 * 3. The name of the author may not be used to endorse or promote products
 *    derived from this software without specific prior written permission
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 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_compat.h"
#include "opt_mac.h"

#include <sys/param.h>
#include <sys/blist.h>
#include <sys/fcntl.h>
#if defined(__i386__)
#include <sys/imgact_aout.h>
#endif
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mac.h>
#include <sys/malloc.h>
#include <sys/mman.h>
#include <sys/mount.h>
#include <sys/mutex.h>
#include <sys/namei.h>
#include <sys/proc.h>
#include <sys/reboot.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/stat.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/sysproto.h>
#include <sys/systm.h>
#include <sys/time.h>
#include <sys/vmmeter.h>
#include <sys/vnode.h>
#include <sys/wait.h>

#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_kern.h>
#include <vm/vm_map.h>
#include <vm/vm_extern.h>
#include <vm/vm_object.h>
#include <vm/swap_pager.h>

#include <posix4/sched.h>

#include <compat/linux/linux_sysproto.h>

#ifdef COMPAT_LINUX32
#include <machine/../linux32/linux.h>
#include <machine/../linux32/linux32_proto.h>
#else
#include <machine/../linux/linux.h>
#include <machine/../linux/linux_proto.h>
#endif

#include <compat/linux/linux_mib.h>
#include <compat/linux/linux_util.h>

#ifdef __i386__
#include <machine/cputypes.h>
#endif

#define BSD_TO_LINUX_SIGNAL(sig)	\
	(((sig) <= LINUX_SIGTBLSZ) ? bsd_to_linux_signal[_SIG_IDX(sig)] : sig)

static unsigned int linux_to_bsd_resource[LINUX_RLIM_NLIMITS] = {
	RLIMIT_CPU, RLIMIT_FSIZE, RLIMIT_DATA, RLIMIT_STACK,
	RLIMIT_CORE, RLIMIT_RSS, RLIMIT_NPROC, RLIMIT_NOFILE,
	RLIMIT_MEMLOCK, -1
};

struct l_sysinfo {
	l_long		uptime;		/* Seconds since boot */
	l_ulong		loads[3];	/* 1, 5, and 15 minute load averages */
#define LINUX_SYSINFO_LOADS_SCALE 65536
	l_ulong		totalram;	/* Total usable main memory size */
	l_ulong		freeram;	/* Available memory size */
	l_ulong		sharedram;	/* Amount of shared memory */
	l_ulong		bufferram;	/* Memory used by buffers */
	l_ulong		totalswap;	/* Total swap space size */
	l_ulong		freeswap;	/* swap space still available */
	l_ushort	procs;		/* Number of current processes */
	l_ulong		totalbig;
	l_ulong		freebig;
	l_uint		mem_unit;
	char		_f[6];		/* Pads structure to 64 bytes */
};
int
linux_sysinfo(struct thread *td, struct linux_sysinfo_args *args)
{
	struct l_sysinfo sysinfo;
	vm_object_t object;
	int i, j;
	struct timespec ts;

	getnanouptime(&ts);
	if (ts.tv_nsec != 0)
		ts.tv_sec++;
	sysinfo.uptime = ts.tv_sec;

	/* Use the information from the mib to get our load averages */
	for (i = 0; i < 3; i++)
		sysinfo.loads[i] = averunnable.ldavg[i] *
		    LINUX_SYSINFO_LOADS_SCALE / averunnable.fscale;

	sysinfo.totalram = physmem * PAGE_SIZE;
	sysinfo.freeram = sysinfo.totalram - cnt.v_wire_count * PAGE_SIZE;

	sysinfo.sharedram = 0;
	mtx_lock(&vm_object_list_mtx);
	TAILQ_FOREACH(object, &vm_object_list, object_list)
		if (object->shadow_count > 1)
			sysinfo.sharedram += object->resident_page_count;
	mtx_unlock(&vm_object_list_mtx);

	sysinfo.sharedram *= PAGE_SIZE;
	sysinfo.bufferram = 0;

	swap_pager_status(&i, &j);
	sysinfo.totalswap= i * PAGE_SIZE;
	sysinfo.freeswap = (i - j) * PAGE_SIZE;

	sysinfo.procs = nprocs;

	/* The following are only present in newer Linux kernels. */
	sysinfo.totalbig = 0;
	sysinfo.freebig = 0;
	sysinfo.mem_unit = 1;

	return copyout(&sysinfo, args->info, sizeof(sysinfo));
}

int
linux_alarm(struct thread *td, struct linux_alarm_args *args)
{
	struct itimerval it, old_it;
	int error;

#ifdef DEBUG
	if (ldebug(alarm))
		printf(ARGS(alarm, "%u"), args->secs);
#endif

	if (args->secs > 100000000)
		return (EINVAL);

	it.it_value.tv_sec = (long)args->secs;
	it.it_value.tv_usec = 0;
	it.it_interval.tv_sec = 0;
	it.it_interval.tv_usec = 0;
	error = kern_setitimer(td, ITIMER_REAL, &it, &old_it);
	if (error)
		return (error);
	if (timevalisset(&old_it.it_value)) {		
		if (old_it.it_value.tv_usec != 0)
			old_it.it_value.tv_sec++;
		td->td_retval[0] = old_it.it_value.tv_sec;
	}
	return (0);
}

int
linux_brk(struct thread *td, struct linux_brk_args *args)
{
	struct vmspace *vm = td->td_proc->p_vmspace;
	vm_offset_t new, old;
	struct obreak_args /* {
		char * nsize;
	} */ tmp;

#ifdef DEBUG
	if (ldebug(brk))
		printf(ARGS(brk, "%p"), (void *)(uintptr_t)args->dsend);
#endif
	old = (vm_offset_t)vm->vm_daddr + ctob(vm->vm_dsize);
	new = (vm_offset_t)args->dsend;
	tmp.nsize = (char *) new;
	if (((caddr_t)new > vm->vm_daddr) && !obreak(td, &tmp))
		td->td_retval[0] = (long)new;
	else
		td->td_retval[0] = (long)old;

	return 0;
}

#if defined(__i386__)
/* XXX: what about amd64/linux32? */

int
linux_uselib(struct thread *td, struct linux_uselib_args *args)
{
	struct nameidata ni;
	struct vnode *vp;
	struct exec *a_out;
	struct vattr attr;
	vm_offset_t vmaddr;
	unsigned long file_offset;
	vm_offset_t buffer;
	unsigned long bss_size;
	char *library;
	int error;
	int locked, vfslocked;

	LCONVPATHEXIST(td, args->library, &library);

#ifdef DEBUG
	if (ldebug(uselib))
		printf(ARGS(uselib, "%s"), library);
#endif

	a_out = NULL;
	vfslocked = 0;
	locked = 0;
	vp = NULL;

	NDINIT(&ni, LOOKUP, ISOPEN | FOLLOW | LOCKLEAF | MPSAFE | AUDITVNODE1,
	    UIO_SYSSPACE, library, td);
	error = namei(&ni);
	LFREEPATH(library);
	if (error)
		goto cleanup;

	vp = ni.ni_vp;
	vfslocked = NDHASGIANT(&ni);
	NDFREE(&ni, NDF_ONLY_PNBUF);

	/*
	 * From here on down, we have a locked vnode that must be unlocked.
	 * XXX: The code below largely duplicates exec_check_permissions().
	 */
	locked = 1;

	/* Writable? */
	if (vp->v_writecount) {
		error = ETXTBSY;
		goto cleanup;
	}

	/* Executable? */
	error = VOP_GETATTR(vp, &attr, td->td_ucred, td);
	if (error)
		goto cleanup;

	if ((vp->v_mount->mnt_flag & MNT_NOEXEC) ||
	    ((attr.va_mode & 0111) == 0) || (attr.va_type != VREG)) {
		/* EACCESS is what exec(2) returns. */
		error = ENOEXEC;
		goto cleanup;
	}

	/* Sensible size? */
	if (attr.va_size == 0) {
		error = ENOEXEC;
		goto cleanup;
	}

	/* Can we access it? */
	error = VOP_ACCESS(vp, VEXEC, td->td_ucred, td);
	if (error)
		goto cleanup;

	/*
	 * XXX: This should use vn_open() so that it is properly authorized,
	 * and to reduce code redundancy all over the place here.
	 * XXX: Not really, it duplicates far more of exec_check_permissions()
	 * than vn_open().
	 */
#ifdef MAC
	error = mac_check_vnode_open(td->td_ucred, vp, FREAD);
	if (error)
		goto cleanup;
#endif
	error = VOP_OPEN(vp, FREAD, td->td_ucred, td, -1);
	if (error)
		goto cleanup;

	/* Pull in executable header into kernel_map */
	error = vm_mmap(kernel_map, (vm_offset_t *)&a_out, PAGE_SIZE,
	    VM_PROT_READ, VM_PROT_READ, 0, OBJT_VNODE, vp, 0);
	if (error)
		goto cleanup;

	/* Is it a Linux binary ? */
	if (((a_out->a_magic >> 16) & 0xff) != 0x64) {
		error = ENOEXEC;
		goto cleanup;
	}

	/*
	 * While we are here, we should REALLY do some more checks
	 */

	/* Set file/virtual offset based on a.out variant. */
	switch ((int)(a_out->a_magic & 0xffff)) {
	case 0413:	/* ZMAGIC */
		file_offset = 1024;
		break;
	case 0314:	/* QMAGIC */
		file_offset = 0;
		break;
	default:
		error = ENOEXEC;
		goto cleanup;
	}

	bss_size = round_page(a_out->a_bss);

	/* Check various fields in header for validity/bounds. */
	if (a_out->a_text & PAGE_MASK || a_out->a_data & PAGE_MASK) {
		error = ENOEXEC;
		goto cleanup;
	}

	/* text + data can't exceed file size */
	if (a_out->a_data + a_out->a_text > attr.va_size) {
		error = EFAULT;
		goto cleanup;
	}

	/*
	 * text/data/bss must not exceed limits
	 * XXX - this is not complete. it should check current usage PLUS
	 * the resources needed by this library.
	 */
	PROC_LOCK(td->td_proc);
	if (a_out->a_text > maxtsiz ||
	    a_out->a_data + bss_size > lim_cur(td->td_proc, RLIMIT_DATA)) {
		PROC_UNLOCK(td->td_proc);
		error = ENOMEM;
		goto cleanup;
	}
	PROC_UNLOCK(td->td_proc);

	/*
	 * Prevent more writers.
	 * XXX: Note that if any of the VM operations fail below we don't
	 * clear this flag.
	 */
	vp->v_vflag |= VV_TEXT;

	/*
	 * Lock no longer needed
	 */
	locked = 0;
	VOP_UNLOCK(vp, 0, td);
	VFS_UNLOCK_GIANT(vfslocked);

	/*
	 * Check if file_offset page aligned. Currently we cannot handle
	 * misalinged file offsets, and so we read in the entire image
	 * (what a waste).
	 */
	if (file_offset & PAGE_MASK) {
#ifdef DEBUG
		printf("uselib: Non page aligned binary %lu\n", file_offset);
#endif
		/* Map text+data read/write/execute */

		/* a_entry is the load address and is page aligned */
		vmaddr = trunc_page(a_out->a_entry);

		/* get anon user mapping, read+write+execute */
		error = vm_map_find(&td->td_proc->p_vmspace->vm_map, NULL, 0,
		    &vmaddr, a_out->a_text + a_out->a_data, FALSE, VM_PROT_ALL,
		    VM_PROT_ALL, 0);
		if (error)
			goto cleanup;

		/* map file into kernel_map */
		error = vm_mmap(kernel_map, &buffer,
		    round_page(a_out->a_text + a_out->a_data + file_offset),
		    VM_PROT_READ, VM_PROT_READ, 0, OBJT_VNODE, vp,
		    trunc_page(file_offset));
		if (error)
			goto cleanup;

		/* copy from kernel VM space to user space */
		error = copyout(PTRIN(buffer + file_offset),
		    (void *)vmaddr, a_out->a_text + a_out->a_data);

		/* release temporary kernel space */
		vm_map_remove(kernel_map, buffer, buffer +
		    round_page(a_out->a_text + a_out->a_data + file_offset));

		if (error)
			goto cleanup;
	} else {
#ifdef DEBUG
		printf("uselib: Page aligned binary %lu\n", file_offset);
#endif
		/*
		 * for QMAGIC, a_entry is 20 bytes beyond the load address
		 * to skip the executable header
		 */
		vmaddr = trunc_page(a_out->a_entry);

		/*
		 * Map it all into the process's space as a single
		 * copy-on-write "data" segment.
		 */
		error = vm_mmap(&td->td_proc->p_vmspace->vm_map, &vmaddr,
		    a_out->a_text + a_out->a_data, VM_PROT_ALL, VM_PROT_ALL,
		    MAP_PRIVATE | MAP_FIXED, OBJT_VNODE, vp, file_offset);
		if (error)
			goto cleanup;
	}
#ifdef DEBUG
	printf("mem=%08lx = %08lx %08lx\n", (long)vmaddr, ((long*)vmaddr)[0],
	    ((long*)vmaddr)[1]);
#endif
	if (bss_size != 0) {
		/* Calculate BSS start address */
		vmaddr = trunc_page(a_out->a_entry) + a_out->a_text +
		    a_out->a_data;

		/* allocate some 'anon' space */
		error = vm_map_find(&td->td_proc->p_vmspace->vm_map, NULL, 0,
		    &vmaddr, bss_size, FALSE, VM_PROT_ALL, VM_PROT_ALL, 0);
		if (error)
			goto cleanup;
	}

cleanup:
	/* Unlock vnode if needed */
	if (locked) {
		VOP_UNLOCK(vp, 0, td);
		VFS_UNLOCK_GIANT(vfslocked);
	}

	/* Release the kernel mapping. */
	if (a_out)
		vm_map_remove(kernel_map, (vm_offset_t)a_out,
		    (vm_offset_t)a_out + PAGE_SIZE);

	return error;
}

#endif	/* __i386__ */

int
linux_select(struct thread *td, struct linux_select_args *args)
{
	l_timeval ltv;
	struct timeval tv0, tv1, utv, *tvp;
	int error;

#ifdef DEBUG
	if (ldebug(select))
		printf(ARGS(select, "%d, %p, %p, %p, %p"), args->nfds,
		    (void *)args->readfds, (void *)args->writefds,
		    (void *)args->exceptfds, (void *)args->timeout);
#endif

	/*
	 * Store current time for computation of the amount of
	 * time left.
	 */
	if (args->timeout) {
		if ((error = copyin(args->timeout, &ltv, sizeof(ltv))))
			goto select_out;
		utv.tv_sec = ltv.tv_sec;
		utv.tv_usec = ltv.tv_usec;
#ifdef DEBUG
		if (ldebug(select))
			printf(LMSG("incoming timeout (%jd/%ld)"),
			    (intmax_t)utv.tv_sec, utv.tv_usec);
#endif

		if (itimerfix(&utv)) {
			/*
			 * The timeval was invalid.  Convert it to something
			 * valid that will act as it does under Linux.
			 */
			utv.tv_sec += utv.tv_usec / 1000000;
			utv.tv_usec %= 1000000;
			if (utv.tv_usec < 0) {
				utv.tv_sec -= 1;
				utv.tv_usec += 1000000;
			}
			if (utv.tv_sec < 0)
				timevalclear(&utv);
		}
		microtime(&tv0);
		tvp = &utv;
	} else
		tvp = NULL;

	error = kern_select(td, args->nfds, args->readfds, args->writefds,
	    args->exceptfds, tvp);

#ifdef DEBUG
	if (ldebug(select))
		printf(LMSG("real select returns %d"), error);
#endif
	if (error) {
		/*
		 * See fs/select.c in the Linux kernel.  Without this,
		 * Maelstrom doesn't work.
		 */
		if (error == ERESTART)
			error = EINTR;
		goto select_out;
	}

	if (args->timeout) {
		if (td->td_retval[0]) {
			/*
			 * Compute how much time was left of the timeout,
			 * by subtracting the current time and the time
			 * before we started the call, and subtracting
			 * that result from the user-supplied value.
			 */
			microtime(&tv1);
			timevalsub(&tv1, &tv0);
			timevalsub(&utv, &tv1);
			if (utv.tv_sec < 0)
				timevalclear(&utv);
		} else
			timevalclear(&utv);
#ifdef DEBUG
		if (ldebug(select))
			printf(LMSG("outgoing timeout (%jd/%ld)"),
			    (intmax_t)utv.tv_sec, utv.tv_usec);
#endif
		ltv.tv_sec = utv.tv_sec;
		ltv.tv_usec = utv.tv_usec;
		if ((error = copyout(&ltv, args->timeout, sizeof(ltv))))
			goto select_out;
	}

select_out:
#ifdef DEBUG
	if (ldebug(select))
		printf(LMSG("select_out -> %d"), error);
#endif
	return error;
}

int
linux_mremap(struct thread *td, struct linux_mremap_args *args)
{
	struct munmap_args /* {
		void *addr;
		size_t len;
	} */ bsd_args;
	int error = 0;

#ifdef DEBUG
	if (ldebug(mremap))
		printf(ARGS(mremap, "%p, %08lx, %08lx, %08lx"),
		    (void *)(uintptr_t)args->addr,
		    (unsigned long)args->old_len,
		    (unsigned long)args->new_len,
		    (unsigned long)args->flags);
#endif
	args->new_len = round_page(args->new_len);
	args->old_len = round_page(args->old_len);

	if (args->new_len > args->old_len) {
		td->td_retval[0] = 0;
		return ENOMEM;
	}

	if (args->new_len < args->old_len) {
		bsd_args.addr =
		    (caddr_t)((uintptr_t)args->addr + args->new_len);
		bsd_args.len = args->old_len - args->new_len;
		error = munmap(td, &bsd_args);
	}

	td->td_retval[0] = error ? 0 : (uintptr_t)args->addr;
	return error;
}

#define LINUX_MS_ASYNC       0x0001
#define LINUX_MS_INVALIDATE  0x0002
#define LINUX_MS_SYNC        0x0004

int
linux_msync(struct thread *td, struct linux_msync_args *args)
{
	struct msync_args bsd_args;

	bsd_args.addr = (caddr_t)(uintptr_t)args->addr;
	bsd_args.len = (uintptr_t)args->len;
	bsd_args.flags = args->fl & ~LINUX_MS_SYNC;

	return msync(td, &bsd_args);
}

int
linux_time(struct thread *td, struct linux_time_args *args)
{
	struct timeval tv;
	l_time_t tm;
	int error;

#ifdef DEBUG
	if (ldebug(time))
		printf(ARGS(time, "*"));
#endif

	microtime(&tv);
	tm = tv.tv_sec;
	if (args->tm && (error = copyout(&tm, args->tm, sizeof(tm))))
		return error;
	td->td_retval[0] = tm;
	return 0;
}

struct l_times_argv {
	l_long		tms_utime;
	l_long		tms_stime;
	l_long		tms_cutime;
	l_long		tms_cstime;
};

#define CLK_TCK 100	/* Linux uses 100 */

#define CONVTCK(r)	(r.tv_sec * CLK_TCK + r.tv_usec / (1000000 / CLK_TCK))

int
linux_times(struct thread *td, struct linux_times_args *args)
{
	struct timeval tv, utime, stime, cutime, cstime;
	struct l_times_argv tms;
	struct proc *p;
	int error;

#ifdef DEBUG
	if (ldebug(times))
		printf(ARGS(times, "*"));
#endif

	if (args->buf != NULL) {
		p = td->td_proc;
		PROC_LOCK(p);
		calcru(p, &utime, &stime);
		calccru(p, &cutime, &cstime);
		PROC_UNLOCK(p);

		tms.tms_utime = CONVTCK(utime);
		tms.tms_stime = CONVTCK(stime);

		tms.tms_cutime = CONVTCK(cutime);
		tms.tms_cstime = CONVTCK(cstime);

		if ((error = copyout(&tms, args->buf, sizeof(tms))))
			return error;
	}

	microuptime(&tv);
	td->td_retval[0] = (int)CONVTCK(tv);
	return 0;
}

int
linux_newuname(struct thread *td, struct linux_newuname_args *args)
{
	struct l_new_utsname utsname;
	char osname[LINUX_MAX_UTSNAME];
	char osrelease[LINUX_MAX_UTSNAME];
	char *p;

#ifdef DEBUG
	if (ldebug(newuname))
		printf(ARGS(newuname, "*"));
#endif

	linux_get_osname(td, osname);
	linux_get_osrelease(td, osrelease);

	bzero(&utsname, sizeof(utsname));
	strlcpy(utsname.sysname, osname, LINUX_MAX_UTSNAME);
	getcredhostname(td->td_ucred, utsname.nodename, LINUX_MAX_UTSNAME);
	strlcpy(utsname.release, osrelease, LINUX_MAX_UTSNAME);
	strlcpy(utsname.version, version, LINUX_MAX_UTSNAME);
	for (p = utsname.version; *p != '\0'; ++p)
		if (*p == '\n') {
			*p = '\0';
			break;
		}
#ifdef __i386__
	{
		const char *class;
		switch (cpu_class) {
		case CPUCLASS_686:
			class = "i686";
			break;
		case CPUCLASS_586:
			class = "i586";
			break;
		case CPUCLASS_486:
			class = "i486";
			break;
		default:
			class = "i386";
		}
		strlcpy(utsname.machine, class, LINUX_MAX_UTSNAME);
	}
#elif defined(__amd64__)	/* XXX: Linux can change 'personality'. */
#ifdef COMPAT_LINUX32
	strlcpy(utsname.machine, "i686", LINUX_MAX_UTSNAME);
#else
	strlcpy(utsname.machine, "x86_64", LINUX_MAX_UTSNAME);
#endif /* COMPAT_LINUX32 */
#else /* something other than i386 or amd64 - assume we and Linux agree */
	strlcpy(utsname.machine, machine, LINUX_MAX_UTSNAME);
#endif /* __i386__ */
	strlcpy(utsname.domainname, domainname, LINUX_MAX_UTSNAME);

	return (copyout(&utsname, args->buf, sizeof(utsname)));
}

#if defined(__i386__) || (defined(__amd64__) && defined(COMPAT_LINUX32))
struct l_utimbuf {
	l_time_t l_actime;
	l_time_t l_modtime;
};

int
linux_utime(struct thread *td, struct linux_utime_args *args)
{
	struct timeval tv[2], *tvp;
	struct l_utimbuf lut;
	char *fname;
	int error;

	LCONVPATHEXIST(td, args->fname, &fname);

#ifdef DEBUG
	if (ldebug(utime))
		printf(ARGS(utime, "%s, *"), fname);
#endif

	if (args->times) {
		if ((error = copyin(args->times, &lut, sizeof lut))) {
			LFREEPATH(fname);
			return error;
		}
		tv[0].tv_sec = lut.l_actime;
		tv[0].tv_usec = 0;
		tv[1].tv_sec = lut.l_modtime;
		tv[1].tv_usec = 0;
		tvp = tv;
	} else
		tvp = NULL;

	error = kern_utimes(td, fname, UIO_SYSSPACE, tvp, UIO_SYSSPACE);
	LFREEPATH(fname);
	return (error);
}
#endif /* __i386__ || (__amd64__ && COMPAT_LINUX32) */

#define __WCLONE 0x80000000

int
linux_waitpid(struct thread *td, struct linux_waitpid_args *args)
{
	int error, options, tmpstat;

#ifdef DEBUG
	if (ldebug(waitpid))
		printf(ARGS(waitpid, "%d, %p, %d"),
		    args->pid, (void *)args->status, args->options);
#endif

	options = (args->options & (WNOHANG | WUNTRACED));
	/* WLINUXCLONE should be equal to __WCLONE, but we make sure */
	if (args->options & __WCLONE)
		options |= WLINUXCLONE;

	error = kern_wait(td, args->pid, &tmpstat, options, NULL);
	if (error)
		return error;

	if (args->status) {
		tmpstat &= 0xffff;
		if (WIFSIGNALED(tmpstat))
			tmpstat = (tmpstat & 0xffffff80) |
			    BSD_TO_LINUX_SIGNAL(WTERMSIG(tmpstat));
		else if (WIFSTOPPED(tmpstat))
			tmpstat = (tmpstat & 0xffff00ff) |
			    (BSD_TO_LINUX_SIGNAL(WSTOPSIG(tmpstat)) << 8);
		return copyout(&tmpstat, args->status, sizeof(int));
	}

	return 0;
}

int
linux_wait4(struct thread *td, struct linux_wait4_args *args)
{
	int error, options, tmpstat;
	struct rusage ru, *rup;
	struct proc *p;

#ifdef DEBUG
	if (ldebug(wait4))
		printf(ARGS(wait4, "%d, %p, %d, %p"),
		    args->pid, (void *)args->status, args->options,
		    (void *)args->rusage);
#endif

	options = (args->options & (WNOHANG | WUNTRACED));
	/* WLINUXCLONE should be equal to __WCLONE, but we make sure */
	if (args->options & __WCLONE)
		options |= WLINUXCLONE;

	if (args->rusage != NULL)
		rup = &ru;
	else
		rup = NULL;
	error = kern_wait(td, args->pid, &tmpstat, options, rup);
	if (error)
		return error;

	p = td->td_proc;
	PROC_LOCK(p);
	sigqueue_delete(&p->p_sigqueue, SIGCHLD);
	PROC_UNLOCK(p);

	if (args->status) {
		tmpstat &= 0xffff;
		if (WIFSIGNALED(tmpstat))
			tmpstat = (tmpstat & 0xffffff80) |
			    BSD_TO_LINUX_SIGNAL(WTERMSIG(tmpstat));
		else if (WIFSTOPPED(tmpstat))
			tmpstat = (tmpstat & 0xffff00ff) |
			    (BSD_TO_LINUX_SIGNAL(WSTOPSIG(tmpstat)) << 8);
		error = copyout(&tmpstat, args->status, sizeof(int));
	}
	if (args->rusage != NULL && error == 0)
		error = copyout(&ru, args->rusage, sizeof(ru));

	return (error);
}

int
linux_mknod(struct thread *td, struct linux_mknod_args *args)
{
	char *path;
	int error;

	LCONVPATHCREAT(td, args->path, &path);

#ifdef DEBUG
	if (ldebug(mknod))
		printf(ARGS(mknod, "%s, %d, %d"), path, args->mode, args->dev);
#endif

	if (args->mode & S_IFIFO)
		error = kern_mkfifo(td, path, UIO_SYSSPACE, args->mode);
	else
		error = kern_mknod(td, path, UIO_SYSSPACE, args->mode,
		    args->dev);
	LFREEPATH(path);
	return (error);
}

/*
 * UGH! This is just about the dumbest idea I've ever heard!!
 */
int
linux_personality(struct thread *td, struct linux_personality_args *args)
{
#ifdef DEBUG
	if (ldebug(personality))
		printf(ARGS(personality, "%lu"), (unsigned long)args->per);
#endif
	if (args->per != 0)
		return EINVAL;

	/* Yes Jim, it's still a Linux... */
	td->td_retval[0] = 0;
	return 0;
}

struct l_itimerval {
	l_timeval it_interval;
	l_timeval it_value;
};

#define	B2L_ITIMERVAL(bip, lip) 					\
	(bip)->it_interval.tv_sec = (lip)->it_interval.tv_sec;		\
	(bip)->it_interval.tv_usec = (lip)->it_interval.tv_usec;	\
	(bip)->it_value.tv_sec = (lip)->it_value.tv_sec;		\
	(bip)->it_value.tv_usec = (lip)->it_value.tv_usec;

int
linux_setitimer(struct thread *td, struct linux_setitimer_args *uap)
{
	int error;
	struct l_itimerval ls;
	struct itimerval aitv, oitv;

#ifdef DEBUG
	if (ldebug(setitimer))
		printf(ARGS(setitimer, "%p, %p"),
		    (void *)uap->itv, (void *)uap->oitv);
#endif

	if (uap->itv == NULL) {
		uap->itv = uap->oitv;
		return (linux_getitimer(td, (struct linux_getitimer_args *)uap));
	}

	error = copyin(uap->itv, &ls, sizeof(ls));
	if (error != 0)
		return (error);
	B2L_ITIMERVAL(&aitv, &ls);
#ifdef DEBUG
	if (ldebug(setitimer)) {
		printf("setitimer: value: sec: %jd, usec: %ld\n",
		    (intmax_t)aitv.it_value.tv_sec, aitv.it_value.tv_usec);
		printf("setitimer: interval: sec: %jd, usec: %ld\n",
		    (intmax_t)aitv.it_interval.tv_sec, aitv.it_interval.tv_usec);
	}
#endif
	error = kern_setitimer(td, uap->which, &aitv, &oitv);
	if (error != 0 || uap->oitv == NULL)
		return (error);
	B2L_ITIMERVAL(&ls, &oitv);

	return (copyout(&ls, uap->oitv, sizeof(ls)));
}

int
linux_getitimer(struct thread *td, struct linux_getitimer_args *uap)
{
	int error;
	struct l_itimerval ls;
	struct itimerval aitv;

#ifdef DEBUG
	if (ldebug(getitimer))
		printf(ARGS(getitimer, "%p"), (void *)uap->itv);
#endif
	error = kern_getitimer(td, uap->which, &aitv);
	if (error != 0)
		return (error);
	B2L_ITIMERVAL(&ls, &aitv);
	return (copyout(&ls, uap->itv, sizeof(ls)));
}

int
linux_nice(struct thread *td, struct linux_nice_args *args)
{
	struct setpriority_args	bsd_args;

	bsd_args.which = PRIO_PROCESS;
	bsd_args.who = 0;	/* current process */
	bsd_args.prio = args->inc;
	return setpriority(td, &bsd_args);
}

int
linux_setgroups(struct thread *td, struct linux_setgroups_args *args)
{
	struct ucred *newcred, *oldcred;
	l_gid_t linux_gidset[NGROUPS];
	gid_t *bsd_gidset;
	int ngrp, error;
	struct proc *p;

	ngrp = args->gidsetsize;
	if (ngrp < 0 || ngrp >= NGROUPS)
		return (EINVAL);
	error = copyin(args->grouplist, linux_gidset, ngrp * sizeof(l_gid_t));
	if (error)
		return (error);
	newcred = crget();
	p = td->td_proc;
	PROC_LOCK(p);
	oldcred = p->p_ucred;

	/*
	 * cr_groups[0] holds egid. Setting the whole set from
	 * the supplied set will cause egid to be changed too.
	 * Keep cr_groups[0] unchanged to prevent that.
	 */

	if ((error = suser_cred(oldcred, SUSER_ALLOWJAIL)) != 0) {
		PROC_UNLOCK(p);
		crfree(newcred);
		return (error);
	}

	crcopy(newcred, oldcred);
	if (ngrp > 0) {
		newcred->cr_ngroups = ngrp + 1;

		bsd_gidset = newcred->cr_groups;
		ngrp--;
		while (ngrp >= 0) {
			bsd_gidset[ngrp + 1] = linux_gidset[ngrp];
			ngrp--;
		}
	}
	else
		newcred->cr_ngroups = 1;

	setsugid(p);
	p->p_ucred = newcred;
	PROC_UNLOCK(p);
	crfree(oldcred);
	return (0);
}

int
linux_getgroups(struct thread *td, struct linux_getgroups_args *args)
{
	struct ucred *cred;
	l_gid_t linux_gidset[NGROUPS];
	gid_t *bsd_gidset;
	int bsd_gidsetsz, ngrp, error;

	cred = td->td_ucred;
	bsd_gidset = cred->cr_groups;
	bsd_gidsetsz = cred->cr_ngroups - 1;

	/*
	 * cr_groups[0] holds egid. Returning the whole set
	 * here will cause a duplicate. Exclude cr_groups[0]
	 * to prevent that.
	 */

	if ((ngrp = args->gidsetsize) == 0) {
		td->td_retval[0] = bsd_gidsetsz;
		return (0);
	}

	if (ngrp < bsd_gidsetsz)
		return (EINVAL);

	ngrp = 0;
	while (ngrp < bsd_gidsetsz) {
		linux_gidset[ngrp] = bsd_gidset[ngrp + 1];
		ngrp++;
	}

	if ((error = copyout(linux_gidset, args->grouplist,
	    ngrp * sizeof(l_gid_t))))
		return (error);

	td->td_retval[0] = ngrp;
	return (0);
}

int
linux_setrlimit(struct thread *td, struct linux_setrlimit_args *args)
{
	struct rlimit bsd_rlim;
	struct l_rlimit rlim;
	u_int which;
	int error;

#ifdef DEBUG
	if (ldebug(setrlimit))
		printf(ARGS(setrlimit, "%d, %p"),
		    args->resource, (void *)args->rlim);
#endif

	if (args->resource >= LINUX_RLIM_NLIMITS)
		return (EINVAL);

	which = linux_to_bsd_resource[args->resource];
	if (which == -1)
		return (EINVAL);

	error = copyin(args->rlim, &rlim, sizeof(rlim));
	if (error)
		return (error);

	bsd_rlim.rlim_cur = (rlim_t)rlim.rlim_cur;
	bsd_rlim.rlim_max = (rlim_t)rlim.rlim_max;
	return (kern_setrlimit(td, which, &bsd_rlim));
}

int
linux_old_getrlimit(struct thread *td, struct linux_old_getrlimit_args *args)
{
	struct l_rlimit rlim;
	struct proc *p = td->td_proc;
	struct rlimit bsd_rlim;
	u_int which;

#ifdef DEBUG
	if (ldebug(old_getrlimit))
		printf(ARGS(old_getrlimit, "%d, %p"),
		    args->resource, (void *)args->rlim);
#endif

	if (args->resource >= LINUX_RLIM_NLIMITS)
		return (EINVAL);

	which = linux_to_bsd_resource[args->resource];
	if (which == -1)
		return (EINVAL);

	PROC_LOCK(p);
	lim_rlimit(p, which, &bsd_rlim);
	PROC_UNLOCK(p);

#ifdef COMPAT_LINUX32
	rlim.rlim_cur = (unsigned int)bsd_rlim.rlim_cur;
	if (rlim.rlim_cur == UINT_MAX)
		rlim.rlim_cur = INT_MAX;
	rlim.rlim_max = (unsigned int)bsd_rlim.rlim_max;
	if (rlim.rlim_max == UINT_MAX)
		rlim.rlim_max = INT_MAX;
#else
	rlim.rlim_cur = (unsigned long)bsd_rlim.rlim_cur;
	if (rlim.rlim_cur == ULONG_MAX)
		rlim.rlim_cur = LONG_MAX;
	rlim.rlim_max = (unsigned long)bsd_rlim.rlim_max;
	if (rlim.rlim_max == ULONG_MAX)
		rlim.rlim_max = LONG_MAX;
#endif
	return (copyout(&rlim, args->rlim, sizeof(rlim)));
}

int
linux_getrlimit(struct thread *td, struct linux_getrlimit_args *args)
{
	struct l_rlimit rlim;
	struct proc *p = td->td_proc;
	struct rlimit bsd_rlim;
	u_int which;

#ifdef DEBUG
	if (ldebug(getrlimit))
		printf(ARGS(getrlimit, "%d, %p"),
		    args->resource, (void *)args->rlim);
#endif

	if (args->resource >= LINUX_RLIM_NLIMITS)
		return (EINVAL);

	which = linux_to_bsd_resource[args->resource];
	if (which == -1)
		return (EINVAL);

	PROC_LOCK(p);
	lim_rlimit(p, which, &bsd_rlim);
	PROC_UNLOCK(p);

	rlim.rlim_cur = (l_ulong)bsd_rlim.rlim_cur;
	rlim.rlim_max = (l_ulong)bsd_rlim.rlim_max;
	return (copyout(&rlim, args->rlim, sizeof(rlim)));
}

int
linux_sched_setscheduler(struct thread *td,
    struct linux_sched_setscheduler_args *args)
{
	struct sched_setscheduler_args bsd;

#ifdef DEBUG
	if (ldebug(sched_setscheduler))
		printf(ARGS(sched_setscheduler, "%d, %d, %p"),
		    args->pid, args->policy, (const void *)args->param);
#endif

	switch (args->policy) {
	case LINUX_SCHED_OTHER:
		bsd.policy = SCHED_OTHER;
		break;
	case LINUX_SCHED_FIFO:
		bsd.policy = SCHED_FIFO;
		break;
	case LINUX_SCHED_RR:
		bsd.policy = SCHED_RR;
		break;
	default:
		return EINVAL;
	}

	bsd.pid = args->pid;
	bsd.param = (struct sched_param *)args->param;
	return sched_setscheduler(td, &bsd);
}

int
linux_sched_getscheduler(struct thread *td,
    struct linux_sched_getscheduler_args *args)
{
	struct sched_getscheduler_args bsd;
	int error;

#ifdef DEBUG
	if (ldebug(sched_getscheduler))
		printf(ARGS(sched_getscheduler, "%d"), args->pid);
#endif

	bsd.pid = args->pid;
	error = sched_getscheduler(td, &bsd);

	switch (td->td_retval[0]) {
	case SCHED_OTHER:
		td->td_retval[0] = LINUX_SCHED_OTHER;
		break;
	case SCHED_FIFO:
		td->td_retval[0] = LINUX_SCHED_FIFO;
		break;
	case SCHED_RR:
		td->td_retval[0] = LINUX_SCHED_RR;
		break;
	}

	return error;
}

int
linux_sched_get_priority_max(struct thread *td,
    struct linux_sched_get_priority_max_args *args)
{
	struct sched_get_priority_max_args bsd;

#ifdef DEBUG
	if (ldebug(sched_get_priority_max))
		printf(ARGS(sched_get_priority_max, "%d"), args->policy);
#endif

	switch (args->policy) {
	case LINUX_SCHED_OTHER:
		bsd.policy = SCHED_OTHER;
		break;
	case LINUX_SCHED_FIFO:
		bsd.policy = SCHED_FIFO;
		break;
	case LINUX_SCHED_RR:
		bsd.policy = SCHED_RR;
		break;
	default:
		return EINVAL;
	}
	return sched_get_priority_max(td, &bsd);
}

int
linux_sched_get_priority_min(struct thread *td,
    struct linux_sched_get_priority_min_args *args)
{
	struct sched_get_priority_min_args bsd;

#ifdef DEBUG
	if (ldebug(sched_get_priority_min))
		printf(ARGS(sched_get_priority_min, "%d"), args->policy);
#endif

	switch (args->policy) {
	case LINUX_SCHED_OTHER:
		bsd.policy = SCHED_OTHER;
		break;
	case LINUX_SCHED_FIFO:
		bsd.policy = SCHED_FIFO;
		break;
	case LINUX_SCHED_RR:
		bsd.policy = SCHED_RR;
		break;
	default:
		return EINVAL;
	}
	return sched_get_priority_min(td, &bsd);
}

#define REBOOT_CAD_ON	0x89abcdef
#define REBOOT_CAD_OFF	0
#define REBOOT_HALT	0xcdef0123

int
linux_reboot(struct thread *td, struct linux_reboot_args *args)
{
	struct reboot_args bsd_args;

#ifdef DEBUG
	if (ldebug(reboot))
		printf(ARGS(reboot, "0x%x"), args->cmd);
#endif
	if (args->cmd == REBOOT_CAD_ON || args->cmd == REBOOT_CAD_OFF)
		return (0);
	bsd_args.opt = (args->cmd == REBOOT_HALT) ? RB_HALT : 0;
	return (reboot(td, &bsd_args));
}


/*
 * The FreeBSD native getpid(2), getgid(2) and getuid(2) also modify
 * td->td_retval[1] when COMPAT_43 is defined. This
 * globbers registers that are assumed to be preserved. The following
 * lightweight syscalls fixes this. See also linux_getgid16() and
 * linux_getuid16() in linux_uid16.c.
 *
 * linux_getpid() - MP SAFE
 * linux_getgid() - MP SAFE
 * linux_getuid() - MP SAFE
 */

int
linux_getpid(struct thread *td, struct linux_getpid_args *args)
{

	td->td_retval[0] = td->td_proc->p_pid;
	return (0);
}

int
linux_getgid(struct thread *td, struct linux_getgid_args *args)
{

	td->td_retval[0] = td->td_ucred->cr_rgid;
	return (0);
}

int
linux_getuid(struct thread *td, struct linux_getuid_args *args)
{

	td->td_retval[0] = td->td_ucred->cr_ruid;
	return (0);
}


int
linux_getsid(struct thread *td, struct linux_getsid_args *args)
{
	struct getsid_args bsd;
	bsd.pid = args->pid;
	return getsid(td, &bsd);
}

int
linux_nosys(struct thread *td, struct nosys_args *ignore)
{

	return (ENOSYS);
}

int
linux_getpriority(struct thread *td, struct linux_getpriority_args *args)
{
	struct getpriority_args	bsd_args;
	int error;

	bsd_args.which = args->which;
	bsd_args.who = args->who;
	error = getpriority(td, &bsd_args);
	td->td_retval[0] = 20 - td->td_retval[0];
	return error;
}

int
linux_sethostname(struct thread *td, struct linux_sethostname_args *args)
{
	int name[2];
	int error;

	name[0] = CTL_KERN;
	name[1] = KERN_HOSTNAME;
	if ((error = suser_cred(td->td_ucred, SUSER_ALLOWJAIL)))
		return (error);
	return (userland_sysctl(td, name, 2, 0, 0, 0, args->hostname, 
		 args->len, 0, 0));
}