aboutsummaryrefslogtreecommitdiff
path: root/sys/kern/uipc_sockbuf.c
blob: 537f9c867bf8b986f22ad393e250a6af37298f2a (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
/*-
 * Copyright (c) 1982, 1986, 1988, 1990, 1993
 *	The Regents of the University of California.  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.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS 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 REGENTS 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.
 *
 *	@(#)uipc_socket2.c	8.1 (Berkeley) 6/10/93
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_param.h"

#include <sys/param.h>
#include <sys/aio.h> /* for aio_swake proto */
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mbuf.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>

/*
 * Function pointer set by the AIO routines so that the socket buffer code
 * can call back into the AIO module if it is loaded.
 */
void	(*aio_swake)(struct socket *, struct sockbuf *);

/*
 * Primitive routines for operating on socket buffers
 */

u_long	sb_max = SB_MAX;
u_long sb_max_adj =
       (quad_t)SB_MAX * MCLBYTES / (MSIZE + MCLBYTES); /* adjusted sb_max */

static	u_long sb_efficiency = 8;	/* parameter for sbreserve() */

static struct mbuf	*sbcut_internal(struct sockbuf *sb, int len);
static void	sbflush_internal(struct sockbuf *sb);

/*
 * Mark ready "count" mbufs starting with "m".
 */
int
sbready(struct sockbuf *sb, struct mbuf *m, int count)
{
	u_int blocker;

	SOCKBUF_LOCK_ASSERT(sb);
	KASSERT(sb->sb_fnrdy != NULL, ("%s: sb %p NULL fnrdy", __func__, sb));

	blocker = (sb->sb_fnrdy == m) ? M_BLOCKED : 0;

	for (int i = 0; i < count; i++, m = m->m_next) {
		KASSERT(m->m_flags & M_NOTREADY,
		    ("%s: m %p !M_NOTREADY", __func__, m));
		m->m_flags &= ~(M_NOTREADY | blocker);
		if (blocker)
			sb->sb_acc += m->m_len;
	}

	if (!blocker)
		return (EINPROGRESS);

	/* This one was blocking all the queue. */
	for (; m && (m->m_flags & M_NOTREADY) == 0; m = m->m_next) {
		KASSERT(m->m_flags & M_BLOCKED,
		    ("%s: m %p !M_BLOCKED", __func__, m));
		m->m_flags &= ~M_BLOCKED;
		sb->sb_acc += m->m_len;
	}

	sb->sb_fnrdy = m;

	return (0);
}

/*
 * Adjust sockbuf state reflecting allocation of m.
 */
void
sballoc(struct sockbuf *sb, struct mbuf *m)
{

	SOCKBUF_LOCK_ASSERT(sb);

	sb->sb_ccc += m->m_len;

	if (sb->sb_fnrdy == NULL) {
		if (m->m_flags & M_NOTREADY)
			sb->sb_fnrdy = m;
		else
			sb->sb_acc += m->m_len;
	} else
		m->m_flags |= M_BLOCKED;

	if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
		sb->sb_ctl += m->m_len;

	sb->sb_mbcnt += MSIZE;
	sb->sb_mcnt += 1;

	if (m->m_flags & M_EXT) {
		sb->sb_mbcnt += m->m_ext.ext_size;
		sb->sb_ccnt += 1;
	}
}

/*
 * Adjust sockbuf state reflecting freeing of m.
 */
void
sbfree(struct sockbuf *sb, struct mbuf *m)
{

#if 0	/* XXX: not yet: soclose() call path comes here w/o lock. */
	SOCKBUF_LOCK_ASSERT(sb);
#endif

	sb->sb_ccc -= m->m_len;

	if (!(m->m_flags & M_NOTAVAIL))
		sb->sb_acc -= m->m_len;

	if (m == sb->sb_fnrdy) {
		struct mbuf *n;

		KASSERT(m->m_flags & M_NOTREADY,
		    ("%s: m %p !M_NOTREADY", __func__, m));

		n = m->m_next;
		while (n != NULL && !(n->m_flags & M_NOTREADY)) {
			n->m_flags &= ~M_BLOCKED;
			sb->sb_acc += n->m_len;
			n = n->m_next;
		}
		sb->sb_fnrdy = n;
	}

	if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
		sb->sb_ctl -= m->m_len;

	sb->sb_mbcnt -= MSIZE;
	sb->sb_mcnt -= 1;
	if (m->m_flags & M_EXT) {
		sb->sb_mbcnt -= m->m_ext.ext_size;
		sb->sb_ccnt -= 1;
	}

	if (sb->sb_sndptr == m) {
		sb->sb_sndptr = NULL;
		sb->sb_sndptroff = 0;
	}
	if (sb->sb_sndptroff != 0)
		sb->sb_sndptroff -= m->m_len;
}

/*
 * Socantsendmore indicates that no more data will be sent on the socket; it
 * would normally be applied to a socket when the user informs the system
 * that no more data is to be sent, by the protocol code (in case
 * PRU_SHUTDOWN).  Socantrcvmore indicates that no more data will be
 * received, and will normally be applied to the socket by a protocol when it
 * detects that the peer will send no more data.  Data queued for reading in
 * the socket may yet be read.
 */
void
socantsendmore_locked(struct socket *so)
{

	SOCKBUF_LOCK_ASSERT(&so->so_snd);

	so->so_snd.sb_state |= SBS_CANTSENDMORE;
	sowwakeup_locked(so);
	mtx_assert(SOCKBUF_MTX(&so->so_snd), MA_NOTOWNED);
}

void
socantsendmore(struct socket *so)
{

	SOCKBUF_LOCK(&so->so_snd);
	socantsendmore_locked(so);
	mtx_assert(SOCKBUF_MTX(&so->so_snd), MA_NOTOWNED);
}

void
socantrcvmore_locked(struct socket *so)
{

	SOCKBUF_LOCK_ASSERT(&so->so_rcv);

	so->so_rcv.sb_state |= SBS_CANTRCVMORE;
	sorwakeup_locked(so);
	mtx_assert(SOCKBUF_MTX(&so->so_rcv), MA_NOTOWNED);
}

void
socantrcvmore(struct socket *so)
{

	SOCKBUF_LOCK(&so->so_rcv);
	socantrcvmore_locked(so);
	mtx_assert(SOCKBUF_MTX(&so->so_rcv), MA_NOTOWNED);
}

/*
 * Wait for data to arrive at/drain from a socket buffer.
 */
int
sbwait(struct sockbuf *sb)
{

	SOCKBUF_LOCK_ASSERT(sb);

	sb->sb_flags |= SB_WAIT;
	return (msleep_sbt(&sb->sb_acc, &sb->sb_mtx,
	    (sb->sb_flags & SB_NOINTR) ? PSOCK : PSOCK | PCATCH, "sbwait",
	    sb->sb_timeo, 0, 0));
}

int
sblock(struct sockbuf *sb, int flags)
{

	KASSERT((flags & SBL_VALID) == flags,
	    ("sblock: flags invalid (0x%x)", flags));

	if (flags & SBL_WAIT) {
		if ((sb->sb_flags & SB_NOINTR) ||
		    (flags & SBL_NOINTR)) {
			sx_xlock(&sb->sb_sx);
			return (0);
		}
		return (sx_xlock_sig(&sb->sb_sx));
	} else {
		if (sx_try_xlock(&sb->sb_sx) == 0)
			return (EWOULDBLOCK);
		return (0);
	}
}

void
sbunlock(struct sockbuf *sb)
{

	sx_xunlock(&sb->sb_sx);
}

/*
 * Wakeup processes waiting on a socket buffer.  Do asynchronous notification
 * via SIGIO if the socket has the SS_ASYNC flag set.
 *
 * Called with the socket buffer lock held; will release the lock by the end
 * of the function.  This allows the caller to acquire the socket buffer lock
 * while testing for the need for various sorts of wakeup and hold it through
 * to the point where it's no longer required.  We currently hold the lock
 * through calls out to other subsystems (with the exception of kqueue), and
 * then release it to avoid lock order issues.  It's not clear that's
 * correct.
 */
void
sowakeup(struct socket *so, struct sockbuf *sb)
{
	int ret;

	SOCKBUF_LOCK_ASSERT(sb);

	selwakeuppri(&sb->sb_sel, PSOCK);
	if (!SEL_WAITING(&sb->sb_sel))
		sb->sb_flags &= ~SB_SEL;
	if (sb->sb_flags & SB_WAIT) {
		sb->sb_flags &= ~SB_WAIT;
		wakeup(&sb->sb_acc);
	}
	KNOTE_LOCKED(&sb->sb_sel.si_note, 0);
	if (sb->sb_upcall != NULL) {
		ret = sb->sb_upcall(so, sb->sb_upcallarg, M_NOWAIT);
		if (ret == SU_ISCONNECTED) {
			KASSERT(sb == &so->so_rcv,
			    ("SO_SND upcall returned SU_ISCONNECTED"));
			soupcall_clear(so, SO_RCV);
		}
	} else
		ret = SU_OK;
	if (sb->sb_flags & SB_AIO)
		aio_swake(so, sb);
	SOCKBUF_UNLOCK(sb);
	if (ret == SU_ISCONNECTED)
		soisconnected(so);
	if ((so->so_state & SS_ASYNC) && so->so_sigio != NULL)
		pgsigio(&so->so_sigio, SIGIO, 0);
	mtx_assert(SOCKBUF_MTX(sb), MA_NOTOWNED);
}

/*
 * Socket buffer (struct sockbuf) utility routines.
 *
 * Each socket contains two socket buffers: one for sending data and one for
 * receiving data.  Each buffer contains a queue of mbufs, information about
 * the number of mbufs and amount of data in the queue, and other fields
 * allowing select() statements and notification on data availability to be
 * implemented.
 *
 * Data stored in a socket buffer is maintained as a list of records.  Each
 * record is a list of mbufs chained together with the m_next field.  Records
 * are chained together with the m_nextpkt field. The upper level routine
 * soreceive() expects the following conventions to be observed when placing
 * information in the receive buffer:
 *
 * 1. If the protocol requires each message be preceded by the sender's name,
 *    then a record containing that name must be present before any
 *    associated data (mbuf's must be of type MT_SONAME).
 * 2. If the protocol supports the exchange of ``access rights'' (really just
 *    additional data associated with the message), and there are ``rights''
 *    to be received, then a record containing this data should be present
 *    (mbuf's must be of type MT_RIGHTS).
 * 3. If a name or rights record exists, then it must be followed by a data
 *    record, perhaps of zero length.
 *
 * Before using a new socket structure it is first necessary to reserve
 * buffer space to the socket, by calling sbreserve().  This should commit
 * some of the available buffer space in the system buffer pool for the
 * socket (currently, it does nothing but enforce limits).  The space should
 * be released by calling sbrelease() when the socket is destroyed.
 */
int
soreserve(struct socket *so, u_long sndcc, u_long rcvcc)
{
	struct thread *td = curthread;

	SOCKBUF_LOCK(&so->so_snd);
	SOCKBUF_LOCK(&so->so_rcv);
	if (sbreserve_locked(&so->so_snd, sndcc, so, td) == 0)
		goto bad;
	if (sbreserve_locked(&so->so_rcv, rcvcc, so, td) == 0)
		goto bad2;
	if (so->so_rcv.sb_lowat == 0)
		so->so_rcv.sb_lowat = 1;
	if (so->so_snd.sb_lowat == 0)
		so->so_snd.sb_lowat = MCLBYTES;
	if (so->so_snd.sb_lowat > so->so_snd.sb_hiwat)
		so->so_snd.sb_lowat = so->so_snd.sb_hiwat;
	SOCKBUF_UNLOCK(&so->so_rcv);
	SOCKBUF_UNLOCK(&so->so_snd);
	return (0);
bad2:
	sbrelease_locked(&so->so_snd, so);
bad:
	SOCKBUF_UNLOCK(&so->so_rcv);
	SOCKBUF_UNLOCK(&so->so_snd);
	return (ENOBUFS);
}

static int
sysctl_handle_sb_max(SYSCTL_HANDLER_ARGS)
{
	int error = 0;
	u_long tmp_sb_max = sb_max;

	error = sysctl_handle_long(oidp, &tmp_sb_max, arg2, req);
	if (error || !req->newptr)
		return (error);
	if (tmp_sb_max < MSIZE + MCLBYTES)
		return (EINVAL);
	sb_max = tmp_sb_max;
	sb_max_adj = (u_quad_t)sb_max * MCLBYTES / (MSIZE + MCLBYTES);
	return (0);
}
	
/*
 * Allot mbufs to a sockbuf.  Attempt to scale mbmax so that mbcnt doesn't
 * become limiting if buffering efficiency is near the normal case.
 */
int
sbreserve_locked(struct sockbuf *sb, u_long cc, struct socket *so,
    struct thread *td)
{
	rlim_t sbsize_limit;

	SOCKBUF_LOCK_ASSERT(sb);

	/*
	 * When a thread is passed, we take into account the thread's socket
	 * buffer size limit.  The caller will generally pass curthread, but
	 * in the TCP input path, NULL will be passed to indicate that no
	 * appropriate thread resource limits are available.  In that case,
	 * we don't apply a process limit.
	 */
	if (cc > sb_max_adj)
		return (0);
	if (td != NULL) {
		PROC_LOCK(td->td_proc);
		sbsize_limit = lim_cur(td->td_proc, RLIMIT_SBSIZE);
		PROC_UNLOCK(td->td_proc);
	} else
		sbsize_limit = RLIM_INFINITY;
	if (!chgsbsize(so->so_cred->cr_uidinfo, &sb->sb_hiwat, cc,
	    sbsize_limit))
		return (0);
	sb->sb_mbmax = min(cc * sb_efficiency, sb_max);
	if (sb->sb_lowat > sb->sb_hiwat)
		sb->sb_lowat = sb->sb_hiwat;
	return (1);
}

int
sbreserve(struct sockbuf *sb, u_long cc, struct socket *so, 
    struct thread *td)
{
	int error;

	SOCKBUF_LOCK(sb);
	error = sbreserve_locked(sb, cc, so, td);
	SOCKBUF_UNLOCK(sb);
	return (error);
}

/*
 * Free mbufs held by a socket, and reserved mbuf space.
 */
void
sbrelease_internal(struct sockbuf *sb, struct socket *so)
{

	sbflush_internal(sb);
	(void)chgsbsize(so->so_cred->cr_uidinfo, &sb->sb_hiwat, 0,
	    RLIM_INFINITY);
	sb->sb_mbmax = 0;
}

void
sbrelease_locked(struct sockbuf *sb, struct socket *so)
{

	SOCKBUF_LOCK_ASSERT(sb);

	sbrelease_internal(sb, so);
}

void
sbrelease(struct sockbuf *sb, struct socket *so)
{

	SOCKBUF_LOCK(sb);
	sbrelease_locked(sb, so);
	SOCKBUF_UNLOCK(sb);
}

void
sbdestroy(struct sockbuf *sb, struct socket *so)
{

	sbrelease_internal(sb, so);
}

/*
 * Routines to add and remove data from an mbuf queue.
 *
 * The routines sbappend() or sbappendrecord() are normally called to append
 * new mbufs to a socket buffer, after checking that adequate space is
 * available, comparing the function sbspace() with the amount of data to be
 * added.  sbappendrecord() differs from sbappend() in that data supplied is
 * treated as the beginning of a new record.  To place a sender's address,
 * optional access rights, and data in a socket receive buffer,
 * sbappendaddr() should be used.  To place access rights and data in a
 * socket receive buffer, sbappendrights() should be used.  In either case,
 * the new data begins a new record.  Note that unlike sbappend() and
 * sbappendrecord(), these routines check for the caller that there will be
 * enough space to store the data.  Each fails if there is not enough space,
 * or if it cannot find mbufs to store additional information in.
 *
 * Reliable protocols may use the socket send buffer to hold data awaiting
 * acknowledgement.  Data is normally copied from a socket send buffer in a
 * protocol with m_copy for output to a peer, and then removing the data from
 * the socket buffer with sbdrop() or sbdroprecord() when the data is
 * acknowledged by the peer.
 */
#ifdef SOCKBUF_DEBUG
void
sblastrecordchk(struct sockbuf *sb, const char *file, int line)
{
	struct mbuf *m = sb->sb_mb;

	SOCKBUF_LOCK_ASSERT(sb);

	while (m && m->m_nextpkt)
		m = m->m_nextpkt;

	if (m != sb->sb_lastrecord) {
		printf("%s: sb_mb %p sb_lastrecord %p last %p\n",
			__func__, sb->sb_mb, sb->sb_lastrecord, m);
		printf("packet chain:\n");
		for (m = sb->sb_mb; m != NULL; m = m->m_nextpkt)
			printf("\t%p\n", m);
		panic("%s from %s:%u", __func__, file, line);
	}
}

void
sblastmbufchk(struct sockbuf *sb, const char *file, int line)
{
	struct mbuf *m = sb->sb_mb;
	struct mbuf *n;

	SOCKBUF_LOCK_ASSERT(sb);

	while (m && m->m_nextpkt)
		m = m->m_nextpkt;

	while (m && m->m_next)
		m = m->m_next;

	if (m != sb->sb_mbtail) {
		printf("%s: sb_mb %p sb_mbtail %p last %p\n",
			__func__, sb->sb_mb, sb->sb_mbtail, m);
		printf("packet tree:\n");
		for (m = sb->sb_mb; m != NULL; m = m->m_nextpkt) {
			printf("\t");
			for (n = m; n != NULL; n = n->m_next)
				printf("%p ", n);
			printf("\n");
		}
		panic("%s from %s:%u", __func__, file, line);
	}
}
#endif /* SOCKBUF_DEBUG */

#define SBLINKRECORD(sb, m0) do {					\
	SOCKBUF_LOCK_ASSERT(sb);					\
	if ((sb)->sb_lastrecord != NULL)				\
		(sb)->sb_lastrecord->m_nextpkt = (m0);			\
	else								\
		(sb)->sb_mb = (m0);					\
	(sb)->sb_lastrecord = (m0);					\
} while (/*CONSTCOND*/0)

/*
 * Append mbuf chain m to the last record in the socket buffer sb.  The
 * additional space associated the mbuf chain is recorded in sb.  Empty mbufs
 * are discarded and mbufs are compacted where possible.
 */
void
sbappend_locked(struct sockbuf *sb, struct mbuf *m)
{
	struct mbuf *n;

	SOCKBUF_LOCK_ASSERT(sb);

	if (m == 0)
		return;

	SBLASTRECORDCHK(sb);
	n = sb->sb_mb;
	if (n) {
		while (n->m_nextpkt)
			n = n->m_nextpkt;
		do {
			if (n->m_flags & M_EOR) {
				sbappendrecord_locked(sb, m); /* XXXXXX!!!! */
				return;
			}
		} while (n->m_next && (n = n->m_next));
	} else {
		/*
		 * XXX Would like to simply use sb_mbtail here, but
		 * XXX I need to verify that I won't miss an EOR that
		 * XXX way.
		 */
		if ((n = sb->sb_lastrecord) != NULL) {
			do {
				if (n->m_flags & M_EOR) {
					sbappendrecord_locked(sb, m); /* XXXXXX!!!! */
					return;
				}
			} while (n->m_next && (n = n->m_next));
		} else {
			/*
			 * If this is the first record in the socket buffer,
			 * it's also the last record.
			 */
			sb->sb_lastrecord = m;
		}
	}
	sbcompress(sb, m, n);
	SBLASTRECORDCHK(sb);
}

/*
 * Append mbuf chain m to the last record in the socket buffer sb.  The
 * additional space associated the mbuf chain is recorded in sb.  Empty mbufs
 * are discarded and mbufs are compacted where possible.
 */
void
sbappend(struct sockbuf *sb, struct mbuf *m)
{

	SOCKBUF_LOCK(sb);
	sbappend_locked(sb, m);
	SOCKBUF_UNLOCK(sb);
}

/*
 * This version of sbappend() should only be used when the caller absolutely
 * knows that there will never be more than one record in the socket buffer,
 * that is, a stream protocol (such as TCP).
 */
void
sbappendstream_locked(struct sockbuf *sb, struct mbuf *m, int flags)
{
	SOCKBUF_LOCK_ASSERT(sb);

	KASSERT(m->m_nextpkt == NULL,("sbappendstream 0"));
	KASSERT(sb->sb_mb == sb->sb_lastrecord,("sbappendstream 1"));

	SBLASTMBUFCHK(sb);

	/* Remove all packet headers and mbuf tags to get a pure data chain. */
	m_demote(m, 1, flags & PRUS_NOTREADY ? M_NOTREADY : 0);

	sbcompress(sb, m, sb->sb_mbtail);

	sb->sb_lastrecord = sb->sb_mb;
	SBLASTRECORDCHK(sb);
}

/*
 * This version of sbappend() should only be used when the caller absolutely
 * knows that there will never be more than one record in the socket buffer,
 * that is, a stream protocol (such as TCP).
 */
void
sbappendstream(struct sockbuf *sb, struct mbuf *m, int flags)
{

	SOCKBUF_LOCK(sb);
	sbappendstream_locked(sb, m, flags);
	SOCKBUF_UNLOCK(sb);
}

#ifdef SOCKBUF_DEBUG
void
sbcheck(struct sockbuf *sb, const char *file, int line)
{
	struct mbuf *m, *n, *fnrdy;
	u_long acc, ccc, mbcnt;

	SOCKBUF_LOCK_ASSERT(sb);

	acc = ccc = mbcnt = 0;
	fnrdy = NULL;

	for (m = sb->sb_mb; m; m = n) {
	    n = m->m_nextpkt;
	    for (; m; m = m->m_next) {
		if (m->m_len == 0) {
			printf("sb %p empty mbuf %p\n", sb, m);
			goto fail;
		}
		if ((m->m_flags & M_NOTREADY) && fnrdy == NULL) {
			if (m != sb->sb_fnrdy) {
				printf("sb %p: fnrdy %p != m %p\n",
				    sb, sb->sb_fnrdy, m);
				goto fail;
			}
			fnrdy = m;
		}
		if (fnrdy) {
			if (!(m->m_flags & M_NOTAVAIL)) {
				printf("sb %p: fnrdy %p, m %p is avail\n",
				    sb, sb->sb_fnrdy, m);
				goto fail;
			}
		} else
			acc += m->m_len;
		ccc += m->m_len;
		mbcnt += MSIZE;
		if (m->m_flags & M_EXT) /*XXX*/ /* pretty sure this is bogus */
			mbcnt += m->m_ext.ext_size;
	    }
	}
	if (acc != sb->sb_acc || ccc != sb->sb_ccc || mbcnt != sb->sb_mbcnt) {
		printf("acc %ld/%u ccc %ld/%u mbcnt %ld/%u\n",
		    acc, sb->sb_acc, ccc, sb->sb_ccc, mbcnt, sb->sb_mbcnt);
		goto fail;
	}
	return;
fail:
	panic("%s from %s:%u", __func__, file, line);
}
#endif

/*
 * As above, except the mbuf chain begins a new record.
 */
void
sbappendrecord_locked(struct sockbuf *sb, struct mbuf *m0)
{
	struct mbuf *m;

	SOCKBUF_LOCK_ASSERT(sb);

	if (m0 == 0)
		return;
	/*
	 * Put the first mbuf on the queue.  Note this permits zero length
	 * records.
	 */
	sballoc(sb, m0);
	SBLASTRECORDCHK(sb);
	SBLINKRECORD(sb, m0);
	sb->sb_mbtail = m0;
	m = m0->m_next;
	m0->m_next = 0;
	if (m && (m0->m_flags & M_EOR)) {
		m0->m_flags &= ~M_EOR;
		m->m_flags |= M_EOR;
	}
	/* always call sbcompress() so it can do SBLASTMBUFCHK() */
	sbcompress(sb, m, m0);
}

/*
 * As above, except the mbuf chain begins a new record.
 */
void
sbappendrecord(struct sockbuf *sb, struct mbuf *m0)
{

	SOCKBUF_LOCK(sb);
	sbappendrecord_locked(sb, m0);
	SOCKBUF_UNLOCK(sb);
}

/* Helper routine that appends data, control, and address to a sockbuf. */
static int
sbappendaddr_locked_internal(struct sockbuf *sb, const struct sockaddr *asa,
    struct mbuf *m0, struct mbuf *control, struct mbuf *ctrl_last)
{
	struct mbuf *m, *n, *nlast;
#if MSIZE <= 256
	if (asa->sa_len > MLEN)
		return (0);
#endif
	m = m_get(M_NOWAIT, MT_SONAME);
	if (m == NULL)
		return (0);
	m->m_len = asa->sa_len;
	bcopy(asa, mtod(m, caddr_t), asa->sa_len);
	if (ctrl_last)
		ctrl_last->m_next = m0;	/* concatenate data to control */
	else
		control = m0;
	m->m_next = control;
	for (n = m; n->m_next != NULL; n = n->m_next)
		sballoc(sb, n);
	sballoc(sb, n);
	nlast = n;
	SBLINKRECORD(sb, m);

	sb->sb_mbtail = nlast;
	SBLASTMBUFCHK(sb);

	SBLASTRECORDCHK(sb);
	return (1);
}

/*
 * Append address and data, and optionally, control (ancillary) data to the
 * receive queue of a socket.  If present, m0 must include a packet header
 * with total length.  Returns 0 if no space in sockbuf or insufficient
 * mbufs.
 */
int
sbappendaddr_locked(struct sockbuf *sb, const struct sockaddr *asa,
    struct mbuf *m0, struct mbuf *control)
{
	struct mbuf *ctrl_last;
	int space = asa->sa_len;

	SOCKBUF_LOCK_ASSERT(sb);

	if (m0 && (m0->m_flags & M_PKTHDR) == 0)
		panic("sbappendaddr_locked");
	if (m0)
		space += m0->m_pkthdr.len;
	space += m_length(control, &ctrl_last);

	if (space > sbspace(sb))
		return (0);
	return (sbappendaddr_locked_internal(sb, asa, m0, control, ctrl_last));
}

/*
 * Append address and data, and optionally, control (ancillary) data to the
 * receive queue of a socket.  If present, m0 must include a packet header
 * with total length.  Returns 0 if insufficient mbufs.  Does not validate space
 * on the receiving sockbuf.
 */
int
sbappendaddr_nospacecheck_locked(struct sockbuf *sb, const struct sockaddr *asa,
    struct mbuf *m0, struct mbuf *control)
{
	struct mbuf *ctrl_last;

	SOCKBUF_LOCK_ASSERT(sb);

	ctrl_last = (control == NULL) ? NULL : m_last(control);
	return (sbappendaddr_locked_internal(sb, asa, m0, control, ctrl_last));
}

/*
 * Append address and data, and optionally, control (ancillary) data to the
 * receive queue of a socket.  If present, m0 must include a packet header
 * with total length.  Returns 0 if no space in sockbuf or insufficient
 * mbufs.
 */
int
sbappendaddr(struct sockbuf *sb, const struct sockaddr *asa,
    struct mbuf *m0, struct mbuf *control)
{
	int retval;

	SOCKBUF_LOCK(sb);
	retval = sbappendaddr_locked(sb, asa, m0, control);
	SOCKBUF_UNLOCK(sb);
	return (retval);
}

int
sbappendcontrol_locked(struct sockbuf *sb, struct mbuf *m0,
    struct mbuf *control)
{
	struct mbuf *m, *n, *mlast;
	int space;

	SOCKBUF_LOCK_ASSERT(sb);

	if (control == 0)
		panic("sbappendcontrol_locked");
	space = m_length(control, &n) + m_length(m0, NULL);

	if (space > sbspace(sb))
		return (0);
	n->m_next = m0;			/* concatenate data to control */

	SBLASTRECORDCHK(sb);

	for (m = control; m->m_next; m = m->m_next)
		sballoc(sb, m);
	sballoc(sb, m);
	mlast = m;
	SBLINKRECORD(sb, control);

	sb->sb_mbtail = mlast;
	SBLASTMBUFCHK(sb);

	SBLASTRECORDCHK(sb);
	return (1);
}

int
sbappendcontrol(struct sockbuf *sb, struct mbuf *m0, struct mbuf *control)
{
	int retval;

	SOCKBUF_LOCK(sb);
	retval = sbappendcontrol_locked(sb, m0, control);
	SOCKBUF_UNLOCK(sb);
	return (retval);
}

/*
 * Append the data in mbuf chain (m) into the socket buffer sb following mbuf
 * (n).  If (n) is NULL, the buffer is presumed empty.
 *
 * When the data is compressed, mbufs in the chain may be handled in one of
 * three ways:
 *
 * (1) The mbuf may simply be dropped, if it contributes nothing (no data, no
 *     record boundary, and no change in data type).
 *
 * (2) The mbuf may be coalesced -- i.e., data in the mbuf may be copied into
 *     an mbuf already in the socket buffer.  This can occur if an
 *     appropriate mbuf exists, there is room, both mbufs are not marked as
 *     not ready, and no merging of data types will occur.
 *
 * (3) The mbuf may be appended to the end of the existing mbuf chain.
 *
 * If any of the new mbufs is marked as M_EOR, mark the last mbuf appended as
 * end-of-record.
 */
void
sbcompress(struct sockbuf *sb, struct mbuf *m, struct mbuf *n)
{
	int eor = 0;
	struct mbuf *o;

	SOCKBUF_LOCK_ASSERT(sb);

	while (m) {
		eor |= m->m_flags & M_EOR;
		if (m->m_len == 0 &&
		    (eor == 0 ||
		     (((o = m->m_next) || (o = n)) &&
		      o->m_type == m->m_type))) {
			if (sb->sb_lastrecord == m)
				sb->sb_lastrecord = m->m_next;
			m = m_free(m);
			continue;
		}
		if (n && (n->m_flags & M_EOR) == 0 &&
		    M_WRITABLE(n) &&
		    ((sb->sb_flags & SB_NOCOALESCE) == 0) &&
		    !(m->m_flags & M_NOTREADY) &&
		    !(n->m_flags & M_NOTREADY) &&
		    m->m_len <= MCLBYTES / 4 && /* XXX: Don't copy too much */
		    m->m_len <= M_TRAILINGSPACE(n) &&
		    n->m_type == m->m_type) {
			bcopy(mtod(m, caddr_t), mtod(n, caddr_t) + n->m_len,
			    (unsigned)m->m_len);
			n->m_len += m->m_len;
			sb->sb_ccc += m->m_len;
			if (sb->sb_fnrdy == NULL)
				sb->sb_acc += m->m_len;
			if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
				/* XXX: Probably don't need.*/
				sb->sb_ctl += m->m_len;
			m = m_free(m);
			continue;
		}
		if (n)
			n->m_next = m;
		else
			sb->sb_mb = m;
		sb->sb_mbtail = m;
		sballoc(sb, m);
		n = m;
		m->m_flags &= ~M_EOR;
		m = m->m_next;
		n->m_next = 0;
	}
	if (eor) {
		KASSERT(n != NULL, ("sbcompress: eor && n == NULL"));
		n->m_flags |= eor;
	}
	SBLASTMBUFCHK(sb);
}

/*
 * Free all mbufs in a sockbuf.  Check that all resources are reclaimed.
 */
static void
sbflush_internal(struct sockbuf *sb)
{

	while (sb->sb_mbcnt) {
		/*
		 * Don't call sbcut(sb, 0) if the leading mbuf is non-empty:
		 * we would loop forever. Panic instead.
		 */
		if (sb->sb_ccc == 0 && (sb->sb_mb == NULL || sb->sb_mb->m_len))
			break;
		m_freem(sbcut_internal(sb, (int)sb->sb_ccc));
	}
	KASSERT(sb->sb_ccc == 0 && sb->sb_mb == 0 && sb->sb_mbcnt == 0,
	    ("%s: ccc %u mb %p mbcnt %u", __func__,
	    sb->sb_ccc, (void *)sb->sb_mb, sb->sb_mbcnt));
}

void
sbflush_locked(struct sockbuf *sb)
{

	SOCKBUF_LOCK_ASSERT(sb);
	sbflush_internal(sb);
}

void
sbflush(struct sockbuf *sb)
{

	SOCKBUF_LOCK(sb);
	sbflush_locked(sb);
	SOCKBUF_UNLOCK(sb);
}

/*
 * Cut data from (the front of) a sockbuf.
 */
static struct mbuf *
sbcut_internal(struct sockbuf *sb, int len)
{
	struct mbuf *m, *next, *mfree;

	next = (m = sb->sb_mb) ? m->m_nextpkt : 0;
	mfree = NULL;

	while (len > 0) {
		if (m == NULL) {
			KASSERT(next, ("%s: no next, len %d", __func__, len));
			m = next;
			next = m->m_nextpkt;
		}
		if (m->m_len > len) {
			KASSERT(!(m->m_flags & M_NOTAVAIL),
			    ("%s: m %p M_NOTAVAIL", __func__, m));
			m->m_len -= len;
			m->m_data += len;
			sb->sb_ccc -= len;
			sb->sb_acc -= len;
			if (sb->sb_sndptroff != 0)
				sb->sb_sndptroff -= len;
			if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
				sb->sb_ctl -= len;
			break;
		}
		len -= m->m_len;
		sbfree(sb, m);
		/*
		 * Do not put M_NOTREADY buffers to the free list, they
		 * are referenced from outside.
		 */
		if (m->m_flags & M_NOTREADY)
			m = m->m_next;
		else {
			struct mbuf *n;

			n = m->m_next;
			m->m_next = mfree;
			mfree = m;
			m = n;
		}
	}
	if (m) {
		sb->sb_mb = m;
		m->m_nextpkt = next;
	} else
		sb->sb_mb = next;
	/*
	 * First part is an inline SB_EMPTY_FIXUP().  Second part makes sure
	 * sb_lastrecord is up-to-date if we dropped part of the last record.
	 */
	m = sb->sb_mb;
	if (m == NULL) {
		sb->sb_mbtail = NULL;
		sb->sb_lastrecord = NULL;
	} else if (m->m_nextpkt == NULL) {
		sb->sb_lastrecord = m;
	}

	return (mfree);
}

/*
 * Drop data from (the front of) a sockbuf.
 */
void
sbdrop_locked(struct sockbuf *sb, int len)
{

	SOCKBUF_LOCK_ASSERT(sb);
	m_freem(sbcut_internal(sb, len));
}

/*
 * Drop data from (the front of) a sockbuf,
 * and return it to caller.
 */
struct mbuf *
sbcut_locked(struct sockbuf *sb, int len)
{

	SOCKBUF_LOCK_ASSERT(sb);
	return (sbcut_internal(sb, len));
}

void
sbdrop(struct sockbuf *sb, int len)
{
	struct mbuf *mfree;

	SOCKBUF_LOCK(sb);
	mfree = sbcut_internal(sb, len);
	SOCKBUF_UNLOCK(sb);

	m_freem(mfree);
}

/*
 * Maintain a pointer and offset pair into the socket buffer mbuf chain to
 * avoid traversal of the entire socket buffer for larger offsets.
 */
struct mbuf *
sbsndptr(struct sockbuf *sb, u_int off, u_int len, u_int *moff)
{
	struct mbuf *m, *ret;

	KASSERT(sb->sb_mb != NULL, ("%s: sb_mb is NULL", __func__));
	KASSERT(off + len <= sb->sb_acc, ("%s: beyond sb", __func__));
	KASSERT(sb->sb_sndptroff <= sb->sb_acc, ("%s: sndptroff broken", __func__));

	/*
	 * Is off below stored offset? Happens on retransmits.
	 * Just return, we can't help here.
	 */
	if (sb->sb_sndptroff > off) {
		*moff = off;
		return (sb->sb_mb);
	}

	/* Return closest mbuf in chain for current offset. */
	*moff = off - sb->sb_sndptroff;
	m = ret = sb->sb_sndptr ? sb->sb_sndptr : sb->sb_mb;
	if (*moff == m->m_len) {
		*moff = 0;
		sb->sb_sndptroff += m->m_len;
		m = ret = m->m_next;
		KASSERT(ret->m_len > 0,
		    ("mbuf %p in sockbuf %p chain has no valid data", ret, sb));
	}

	/* Advance by len to be as close as possible for the next transmit. */
	for (off = off - sb->sb_sndptroff + len - 1;
	     off > 0 && m != NULL && off >= m->m_len;
	     m = m->m_next) {
		sb->sb_sndptroff += m->m_len;
		off -= m->m_len;
	}
	if (off > 0 && m == NULL)
		panic("%s: sockbuf %p and mbuf %p clashing", __func__, sb, ret);
	sb->sb_sndptr = m;

	return (ret);
}

/*
 * Return the first mbuf and the mbuf data offset for the provided
 * send offset without changing the "sb_sndptroff" field.
 */
struct mbuf *
sbsndmbuf(struct sockbuf *sb, u_int off, u_int *moff)
{
	struct mbuf *m;

	KASSERT(sb->sb_mb != NULL, ("%s: sb_mb is NULL", __func__));

	/*
	 * If the "off" is below the stored offset, which happens on
	 * retransmits, just use "sb_mb":
	 */
	if (sb->sb_sndptr == NULL || sb->sb_sndptroff > off) {
		m = sb->sb_mb;
	} else {
		m = sb->sb_sndptr;
		off -= sb->sb_sndptroff;
	}
	while (off > 0 && m != NULL) {
		if (off < m->m_len)
			break;
		off -= m->m_len;
		m = m->m_next;
	}
	*moff = off;
	return (m);
}

/*
 * Drop a record off the front of a sockbuf and move the next record to the
 * front.
 */
void
sbdroprecord_locked(struct sockbuf *sb)
{
	struct mbuf *m;

	SOCKBUF_LOCK_ASSERT(sb);

	m = sb->sb_mb;
	if (m) {
		sb->sb_mb = m->m_nextpkt;
		do {
			sbfree(sb, m);
			m = m_free(m);
		} while (m);
	}
	SB_EMPTY_FIXUP(sb);
}

/*
 * Drop a record off the front of a sockbuf and move the next record to the
 * front.
 */
void
sbdroprecord(struct sockbuf *sb)
{

	SOCKBUF_LOCK(sb);
	sbdroprecord_locked(sb);
	SOCKBUF_UNLOCK(sb);
}

/*
 * Create a "control" mbuf containing the specified data with the specified
 * type for presentation on a socket buffer.
 */
struct mbuf *
sbcreatecontrol(caddr_t p, int size, int type, int level)
{
	struct cmsghdr *cp;
	struct mbuf *m;

	if (CMSG_SPACE((u_int)size) > MCLBYTES)
		return ((struct mbuf *) NULL);
	if (CMSG_SPACE((u_int)size) > MLEN)
		m = m_getcl(M_NOWAIT, MT_CONTROL, 0);
	else
		m = m_get(M_NOWAIT, MT_CONTROL);
	if (m == NULL)
		return ((struct mbuf *) NULL);
	cp = mtod(m, struct cmsghdr *);
	m->m_len = 0;
	KASSERT(CMSG_SPACE((u_int)size) <= M_TRAILINGSPACE(m),
	    ("sbcreatecontrol: short mbuf"));
	/*
	 * Don't leave the padding between the msg header and the
	 * cmsg data and the padding after the cmsg data un-initialized.
	 */
	bzero(cp, CMSG_SPACE((u_int)size));
	if (p != NULL)
		(void)memcpy(CMSG_DATA(cp), p, size);
	m->m_len = CMSG_SPACE(size);
	cp->cmsg_len = CMSG_LEN(size);
	cp->cmsg_level = level;
	cp->cmsg_type = type;
	return (m);
}

/*
 * This does the same for socket buffers that sotoxsocket does for sockets:
 * generate an user-format data structure describing the socket buffer.  Note
 * that the xsockbuf structure, since it is always embedded in a socket, does
 * not include a self pointer nor a length.  We make this entry point public
 * in case some other mechanism needs it.
 */
void
sbtoxsockbuf(struct sockbuf *sb, struct xsockbuf *xsb)
{

	xsb->sb_cc = sb->sb_ccc;
	xsb->sb_hiwat = sb->sb_hiwat;
	xsb->sb_mbcnt = sb->sb_mbcnt;
	xsb->sb_mcnt = sb->sb_mcnt;	
	xsb->sb_ccnt = sb->sb_ccnt;
	xsb->sb_mbmax = sb->sb_mbmax;
	xsb->sb_lowat = sb->sb_lowat;
	xsb->sb_flags = sb->sb_flags;
	xsb->sb_timeo = sb->sb_timeo;
}

/* This takes the place of kern.maxsockbuf, which moved to kern.ipc. */
static int dummy;
SYSCTL_INT(_kern, KERN_DUMMY, dummy, CTLFLAG_RW, &dummy, 0, "");
SYSCTL_OID(_kern_ipc, KIPC_MAXSOCKBUF, maxsockbuf, CTLTYPE_ULONG|CTLFLAG_RW,
    &sb_max, 0, sysctl_handle_sb_max, "LU", "Maximum socket buffer size");
SYSCTL_ULONG(_kern_ipc, KIPC_SOCKBUF_WASTE, sockbuf_waste_factor, CTLFLAG_RW,
    &sb_efficiency, 0, "Socket buffer size waste factor");