aboutsummaryrefslogtreecommitdiff
path: root/slirp/slirp.c
blob: 2bc53e3e127eef0bd4f78dceaf90e29e1402d593 (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
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
/*
 * libslirp glue
 *
 * Copyright (c) 2004-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */
#include "slirp.h"

#ifdef WITH_QEMU
#include "state.h"
#endif

#ifndef _WIN32
#include <net/if.h>
#endif

int slirp_debug;

/* Define to 1 if you want KEEPALIVE timers */
bool slirp_do_keepalive;

/* host loopback address */
struct in_addr loopback_addr;
/* host loopback network mask */
unsigned long loopback_mask;

/* emulated hosts use the MAC addr 52:55:IP:IP:IP:IP */
static const uint8_t special_ethaddr[ETH_ALEN] = {
    0x52, 0x55, 0x00, 0x00, 0x00, 0x00
};

unsigned curtime;

static QTAILQ_HEAD(, Slirp) slirp_instances =
    QTAILQ_HEAD_INITIALIZER(slirp_instances);

static struct in_addr dns_addr;
#ifndef _WIN32
static struct in6_addr dns6_addr;
#endif
static unsigned dns_addr_time;
#ifndef _WIN32
static unsigned dns6_addr_time;
#endif

#define TIMEOUT_FAST 2  /* milliseconds */
#define TIMEOUT_SLOW 499  /* milliseconds */
/* for the aging of certain requests like DNS */
#define TIMEOUT_DEFAULT 1000  /* milliseconds */

#ifdef _WIN32

int get_dns_addr(struct in_addr *pdns_addr)
{
    FIXED_INFO *FixedInfo=NULL;
    ULONG    BufLen;
    DWORD    ret;
    IP_ADDR_STRING *pIPAddr;
    struct in_addr tmp_addr;

    if (dns_addr.s_addr != 0 && (curtime - dns_addr_time) < TIMEOUT_DEFAULT) {
        *pdns_addr = dns_addr;
        return 0;
    }

    FixedInfo = (FIXED_INFO *)GlobalAlloc(GPTR, sizeof(FIXED_INFO));
    BufLen = sizeof(FIXED_INFO);

    if (ERROR_BUFFER_OVERFLOW == GetNetworkParams(FixedInfo, &BufLen)) {
        if (FixedInfo) {
            GlobalFree(FixedInfo);
            FixedInfo = NULL;
        }
        FixedInfo = GlobalAlloc(GPTR, BufLen);
    }

    if ((ret = GetNetworkParams(FixedInfo, &BufLen)) != ERROR_SUCCESS) {
        printf("GetNetworkParams failed. ret = %08x\n", (unsigned)ret );
        if (FixedInfo) {
            GlobalFree(FixedInfo);
            FixedInfo = NULL;
        }
        return -1;
    }

    pIPAddr = &(FixedInfo->DnsServerList);
    inet_aton(pIPAddr->IpAddress.String, &tmp_addr);
    *pdns_addr = tmp_addr;
    dns_addr = tmp_addr;
    dns_addr_time = curtime;
    if (FixedInfo) {
        GlobalFree(FixedInfo);
        FixedInfo = NULL;
    }
    return 0;
}

int get_dns6_addr(struct in6_addr *pdns6_addr, uint32_t *scope_id)
{
    return -1;
}

static void winsock_cleanup(void)
{
    WSACleanup();
}

#else

static int get_dns_addr_cached(void *pdns_addr, void *cached_addr,
                               socklen_t addrlen,
                               struct stat *cached_stat, unsigned *cached_time)
{
    struct stat old_stat;
    if (curtime - *cached_time < TIMEOUT_DEFAULT) {
        memcpy(pdns_addr, cached_addr, addrlen);
        return 0;
    }
    old_stat = *cached_stat;
    if (stat("/etc/resolv.conf", cached_stat) != 0) {
        return -1;
    }
    if (cached_stat->st_dev == old_stat.st_dev
        && cached_stat->st_ino == old_stat.st_ino
        && cached_stat->st_size == old_stat.st_size
        && cached_stat->st_mtime == old_stat.st_mtime) {
        memcpy(pdns_addr, cached_addr, addrlen);
        return 0;
    }
    return 1;
}

static int get_dns_addr_resolv_conf(int af, void *pdns_addr, void *cached_addr,
                                    socklen_t addrlen, uint32_t *scope_id,
                                    unsigned *cached_time)
{
    char buff[512];
    char buff2[257];
    FILE *f;
    int found = 0;
    void *tmp_addr = alloca(addrlen);
    unsigned if_index;

    f = fopen("/etc/resolv.conf", "r");
    if (!f)
        return -1;

    DEBUG_MISC("IP address of your DNS(s):");
    while (fgets(buff, 512, f) != NULL) {
        if (sscanf(buff, "nameserver%*[ \t]%256s", buff2) == 1) {
            char *c = strchr(buff2, '%');
            if (c) {
                if_index = if_nametoindex(c + 1);
                *c = '\0';
            } else {
                if_index = 0;
            }

            if (!inet_pton(af, buff2, tmp_addr)) {
                continue;
            }
            /* If it's the first one, set it to dns_addr */
            if (!found) {
                memcpy(pdns_addr, tmp_addr, addrlen);
                memcpy(cached_addr, tmp_addr, addrlen);
                if (scope_id) {
                    *scope_id = if_index;
                }
                *cached_time = curtime;
            }

            if (++found > 3) {
                DEBUG_MISC("  (more)");
                break;
            } else if (slirp_debug & DBG_MISC) {
                char s[INET6_ADDRSTRLEN];
                const char *res = inet_ntop(af, tmp_addr, s, sizeof(s));
                if (!res) {
                    res = "  (string conversion error)";
                }
                DEBUG_MISC("  %s", res);
            }
        }
    }
    fclose(f);
    if (!found)
        return -1;
    return 0;
}

int get_dns_addr(struct in_addr *pdns_addr)
{
    static struct stat dns_addr_stat;

    if (dns_addr.s_addr != 0) {
        int ret;
        ret = get_dns_addr_cached(pdns_addr, &dns_addr, sizeof(dns_addr),
                                  &dns_addr_stat, &dns_addr_time);
        if (ret <= 0) {
            return ret;
        }
    }
    return get_dns_addr_resolv_conf(AF_INET, pdns_addr, &dns_addr,
                                    sizeof(dns_addr), NULL, &dns_addr_time);
}

int get_dns6_addr(struct in6_addr *pdns6_addr, uint32_t *scope_id)
{
    static struct stat dns6_addr_stat;

    if (!in6_zero(&dns6_addr)) {
        int ret;
        ret = get_dns_addr_cached(pdns6_addr, &dns6_addr, sizeof(dns6_addr),
                                  &dns6_addr_stat, &dns6_addr_time);
        if (ret <= 0) {
            return ret;
        }
    }
    return get_dns_addr_resolv_conf(AF_INET6, pdns6_addr, &dns6_addr,
                                    sizeof(dns6_addr),
                                    scope_id, &dns6_addr_time);
}

#endif

static void slirp_init_once(void)
{
    static int initialized;
    const char *debug;
#ifdef _WIN32
    WSADATA Data;
#endif

    if (initialized) {
        return;
    }
    initialized = 1;

#ifdef _WIN32
    WSAStartup(MAKEWORD(2,0), &Data);
    atexit(winsock_cleanup);
#endif

    loopback_addr.s_addr = htonl(INADDR_LOOPBACK);
    loopback_mask = htonl(IN_CLASSA_NET);

    debug = g_getenv("SLIRP_DEBUG");
    if (debug) {
        const GDebugKey keys[] = {
            { "call", DBG_CALL },
            { "misc", DBG_MISC },
            { "error", DBG_ERROR },
            { "tftp", DBG_TFTP },
        };
        slirp_debug = g_parse_debug_string(debug, keys, G_N_ELEMENTS(keys));
    }


}

Slirp *slirp_init(int restricted, bool in_enabled, struct in_addr vnetwork,
                  struct in_addr vnetmask, struct in_addr vhost,
                  bool in6_enabled,
                  struct in6_addr vprefix_addr6, uint8_t vprefix_len,
                  struct in6_addr vhost6, const char *vhostname,
                  const char *tftp_server_name,
                  const char *tftp_path, const char *bootfile,
                  struct in_addr vdhcp_start, struct in_addr vnameserver,
                  struct in6_addr vnameserver6, const char **vdnssearch,
                  const char *vdomainname,
                  const SlirpCb *callbacks,
                  void *opaque)
{
    Slirp *slirp = g_malloc0(sizeof(Slirp));

    slirp_init_once();

    slirp->cb = callbacks;
    slirp->grand = g_rand_new();
    slirp->restricted = restricted;

    slirp->in_enabled = in_enabled;
    slirp->in6_enabled = in6_enabled;

    if_init(slirp);
    ip_init(slirp);
    ip6_init(slirp);

    /* Initialise mbufs *after* setting the MTU */
    m_init(slirp);

    slirp->vnetwork_addr = vnetwork;
    slirp->vnetwork_mask = vnetmask;
    slirp->vhost_addr = vhost;
    slirp->vprefix_addr6 = vprefix_addr6;
    slirp->vprefix_len = vprefix_len;
    slirp->vhost_addr6 = vhost6;
    if (vhostname) {
        slirp_pstrcpy(slirp->client_hostname, sizeof(slirp->client_hostname),
                      vhostname);
    }
    slirp->tftp_prefix = g_strdup(tftp_path);
    slirp->bootp_filename = g_strdup(bootfile);
    slirp->vdomainname = g_strdup(vdomainname);
    slirp->vdhcp_startaddr = vdhcp_start;
    slirp->vnameserver_addr = vnameserver;
    slirp->vnameserver_addr6 = vnameserver6;
    slirp->tftp_server_name = g_strdup(tftp_server_name);

    if (vdnssearch) {
        translate_dnssearch(slirp, vdnssearch);
    }

    slirp->opaque = opaque;

#ifdef WITH_QEMU
    slirp_state_register(slirp);
#endif
    QTAILQ_INSERT_TAIL(&slirp_instances, slirp, entry);

    return slirp;
}

void slirp_cleanup(Slirp *slirp)
{
    struct gfwd_list *e, *next;

    for (e = slirp->guestfwd_list; e; e = next) {
        next = e->ex_next;
        g_free(e->ex_exec);
        g_free(e);
    }

    QTAILQ_REMOVE(&slirp_instances, slirp, entry);
#ifdef WITH_QEMU
    slirp_state_unregister(slirp);
#endif
    ip_cleanup(slirp);
    ip6_cleanup(slirp);
    m_cleanup(slirp);

    g_rand_free(slirp->grand);

    g_free(slirp->vdnssearch);
    g_free(slirp->tftp_prefix);
    g_free(slirp->bootp_filename);
    g_free(slirp->vdomainname);
    g_free(slirp);
}

#define CONN_CANFSEND(so) (((so)->so_state & (SS_FCANTSENDMORE|SS_ISFCONNECTED)) == SS_ISFCONNECTED)
#define CONN_CANFRCV(so) (((so)->so_state & (SS_FCANTRCVMORE|SS_ISFCONNECTED)) == SS_ISFCONNECTED)

static void slirp_update_timeout(uint32_t *timeout)
{
    Slirp *slirp;
    uint32_t t;

    if (*timeout <= TIMEOUT_FAST) {
        return;
    }

    t = MIN(1000, *timeout);

    /* If we have tcp timeout with slirp, then we will fill @timeout with
     * more precise value.
     */
    QTAILQ_FOREACH(slirp, &slirp_instances, entry) {
        if (slirp->time_fasttimo) {
            *timeout = TIMEOUT_FAST;
            return;
        }
        if (slirp->do_slowtimo) {
            t = MIN(TIMEOUT_SLOW, t);
        }
    }
    *timeout = t;
}

void slirp_pollfds_fill(GArray *pollfds, uint32_t *timeout)
{
    Slirp *slirp;
    struct socket *so, *so_next;

    if (QTAILQ_EMPTY(&slirp_instances)) {
        return;
    }

    /*
     * First, TCP sockets
     */

    QTAILQ_FOREACH(slirp, &slirp_instances, entry) {
        /*
         * *_slowtimo needs calling if there are IP fragments
         * in the fragment queue, or there are TCP connections active
         */
        slirp->do_slowtimo = ((slirp->tcb.so_next != &slirp->tcb) ||
                (&slirp->ipq.ip_link != slirp->ipq.ip_link.next));

        for (so = slirp->tcb.so_next; so != &slirp->tcb;
                so = so_next) {
            int events = 0;

            so_next = so->so_next;

            so->pollfds_idx = -1;

            /*
             * See if we need a tcp_fasttimo
             */
            if (slirp->time_fasttimo == 0 &&
                so->so_tcpcb->t_flags & TF_DELACK) {
                slirp->time_fasttimo = curtime; /* Flag when want a fasttimo */
            }

            /*
             * NOFDREF can include still connecting to local-host,
             * newly socreated() sockets etc. Don't want to select these.
             */
            if (so->so_state & SS_NOFDREF || so->s == -1) {
                continue;
            }

            /*
             * Set for reading sockets which are accepting
             */
            if (so->so_state & SS_FACCEPTCONN) {
                GPollFD pfd = {
                    .fd = so->s,
                    .events = G_IO_IN | G_IO_HUP | G_IO_ERR,
                };
                so->pollfds_idx = pollfds->len;
                g_array_append_val(pollfds, pfd);
                continue;
            }

            /*
             * Set for writing sockets which are connecting
             */
            if (so->so_state & SS_ISFCONNECTING) {
                GPollFD pfd = {
                    .fd = so->s,
                    .events = G_IO_OUT | G_IO_ERR,
                };
                so->pollfds_idx = pollfds->len;
                g_array_append_val(pollfds, pfd);
                continue;
            }

            /*
             * Set for writing if we are connected, can send more, and
             * we have something to send
             */
            if (CONN_CANFSEND(so) && so->so_rcv.sb_cc) {
                events |= G_IO_OUT | G_IO_ERR;
            }

            /*
             * Set for reading (and urgent data) if we are connected, can
             * receive more, and we have room for it XXX /2 ?
             */
            if (CONN_CANFRCV(so) &&
                (so->so_snd.sb_cc < (so->so_snd.sb_datalen/2))) {
                events |= G_IO_IN | G_IO_HUP | G_IO_ERR | G_IO_PRI;
            }

            if (events) {
                GPollFD pfd = {
                    .fd = so->s,
                    .events = events,
                };
                so->pollfds_idx = pollfds->len;
                g_array_append_val(pollfds, pfd);
            }
        }

        /*
         * UDP sockets
         */
        for (so = slirp->udb.so_next; so != &slirp->udb;
                so = so_next) {
            so_next = so->so_next;

            so->pollfds_idx = -1;

            /*
             * See if it's timed out
             */
            if (so->so_expire) {
                if (so->so_expire <= curtime) {
                    udp_detach(so);
                    continue;
                } else {
                    slirp->do_slowtimo = true; /* Let socket expire */
                }
            }

            /*
             * When UDP packets are received from over the
             * link, they're sendto()'d straight away, so
             * no need for setting for writing
             * Limit the number of packets queued by this session
             * to 4.  Note that even though we try and limit this
             * to 4 packets, the session could have more queued
             * if the packets needed to be fragmented
             * (XXX <= 4 ?)
             */
            if ((so->so_state & SS_ISFCONNECTED) && so->so_queued <= 4) {
                GPollFD pfd = {
                    .fd = so->s,
                    .events = G_IO_IN | G_IO_HUP | G_IO_ERR,
                };
                so->pollfds_idx = pollfds->len;
                g_array_append_val(pollfds, pfd);
            }
        }

        /*
         * ICMP sockets
         */
        for (so = slirp->icmp.so_next; so != &slirp->icmp;
                so = so_next) {
            so_next = so->so_next;

            so->pollfds_idx = -1;

            /*
             * See if it's timed out
             */
            if (so->so_expire) {
                if (so->so_expire <= curtime) {
                    icmp_detach(so);
                    continue;
                } else {
                    slirp->do_slowtimo = true; /* Let socket expire */
                }
            }

            if (so->so_state & SS_ISFCONNECTED) {
                GPollFD pfd = {
                    .fd = so->s,
                    .events = G_IO_IN | G_IO_HUP | G_IO_ERR,
                };
                so->pollfds_idx = pollfds->len;
                g_array_append_val(pollfds, pfd);
            }
        }
    }
    slirp_update_timeout(timeout);
}

void slirp_pollfds_poll(GArray *pollfds, int select_error)
{
    Slirp *slirp = QTAILQ_FIRST(&slirp_instances);
    struct socket *so, *so_next;
    int ret;

    if (!slirp) {
        return;
    }

    curtime = slirp->cb->clock_get_ns() / SCALE_MS;

    QTAILQ_FOREACH(slirp, &slirp_instances, entry) {
        /*
         * See if anything has timed out
         */
        if (slirp->time_fasttimo &&
            ((curtime - slirp->time_fasttimo) >= TIMEOUT_FAST)) {
            tcp_fasttimo(slirp);
            slirp->time_fasttimo = 0;
        }
        if (slirp->do_slowtimo &&
            ((curtime - slirp->last_slowtimo) >= TIMEOUT_SLOW)) {
            ip_slowtimo(slirp);
            tcp_slowtimo(slirp);
            slirp->last_slowtimo = curtime;
        }

        /*
         * Check sockets
         */
        if (!select_error) {
            /*
             * Check TCP sockets
             */
            for (so = slirp->tcb.so_next; so != &slirp->tcb;
                    so = so_next) {
                int revents;

                so_next = so->so_next;

                revents = 0;
                if (so->pollfds_idx != -1) {
                    revents = g_array_index(pollfds, GPollFD,
                                            so->pollfds_idx).revents;
                }

                if (so->so_state & SS_NOFDREF || so->s == -1) {
                    continue;
                }

                /*
                 * Check for URG data
                 * This will soread as well, so no need to
                 * test for G_IO_IN below if this succeeds
                 */
                if (revents & G_IO_PRI) {
                    ret = sorecvoob(so);
                    if (ret < 0) {
                        /* Socket error might have resulted in the socket being
                         * removed, do not try to do anything more with it. */
                        continue;
                    }
                }
                /*
                 * Check sockets for reading
                 */
                else if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) {
                    /*
                     * Check for incoming connections
                     */
                    if (so->so_state & SS_FACCEPTCONN) {
                        tcp_connect(so);
                        continue;
                    } /* else */
                    ret = soread(so);

                    /* Output it if we read something */
                    if (ret > 0) {
                        tcp_output(sototcpcb(so));
                    }
                    if (ret < 0) {
                        /* Socket error might have resulted in the socket being
                         * removed, do not try to do anything more with it. */
                        continue;
                    }
                }

                /*
                 * Check sockets for writing
                 */
                if (!(so->so_state & SS_NOFDREF) &&
                        (revents & (G_IO_OUT | G_IO_ERR))) {
                    /*
                     * Check for non-blocking, still-connecting sockets
                     */
                    if (so->so_state & SS_ISFCONNECTING) {
                        /* Connected */
                        so->so_state &= ~SS_ISFCONNECTING;

                        ret = send(so->s, (const void *) &ret, 0, 0);
                        if (ret < 0) {
                            /* XXXXX Must fix, zero bytes is a NOP */
                            if (errno == EAGAIN || errno == EWOULDBLOCK ||
                                errno == EINPROGRESS || errno == ENOTCONN) {
                                continue;
                            }

                            /* else failed */
                            so->so_state &= SS_PERSISTENT_MASK;
                            so->so_state |= SS_NOFDREF;
                        }
                        /* else so->so_state &= ~SS_ISFCONNECTING; */

                        /*
                         * Continue tcp_input
                         */
                        tcp_input((struct mbuf *)NULL, sizeof(struct ip), so,
                                  so->so_ffamily);
                        /* continue; */
                    } else {
                        ret = sowrite(so);
                        if (ret > 0) {
                            /* Call tcp_output in case we need to send a window
                             * update to the guest, otherwise it will be stuck
                             * until it sends a window probe. */
                            tcp_output(sototcpcb(so));
                        }
                    }
                }
            }

            /*
             * Now UDP sockets.
             * Incoming packets are sent straight away, they're not buffered.
             * Incoming UDP data isn't buffered either.
             */
            for (so = slirp->udb.so_next; so != &slirp->udb;
                    so = so_next) {
                int revents;

                so_next = so->so_next;

                revents = 0;
                if (so->pollfds_idx != -1) {
                    revents = g_array_index(pollfds, GPollFD,
                            so->pollfds_idx).revents;
                }

                if (so->s != -1 &&
                    (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR))) {
                    sorecvfrom(so);
                }
            }

            /*
             * Check incoming ICMP relies.
             */
            for (so = slirp->icmp.so_next; so != &slirp->icmp;
                    so = so_next) {
                    int revents;

                    so_next = so->so_next;

                    revents = 0;
                    if (so->pollfds_idx != -1) {
                        revents = g_array_index(pollfds, GPollFD,
                                                so->pollfds_idx).revents;
                    }

                    if (so->s != -1 &&
                        (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR))) {
                    icmp_receive(so);
                }
            }
        }

        if_start(slirp);
    }
}

static void arp_input(Slirp *slirp, const uint8_t *pkt, int pkt_len)
{
    struct slirp_arphdr *ah = (struct slirp_arphdr *)(pkt + ETH_HLEN);
    uint8_t arp_reply[MAX(ETH_HLEN + sizeof(struct slirp_arphdr), 64)];
    struct ethhdr *reh = (struct ethhdr *)arp_reply;
    struct slirp_arphdr *rah = (struct slirp_arphdr *)(arp_reply + ETH_HLEN);
    int ar_op;
    struct gfwd_list *ex_ptr;

    if (!slirp->in_enabled) {
        return;
    }

    ar_op = ntohs(ah->ar_op);
    switch(ar_op) {
    case ARPOP_REQUEST:
        if (ah->ar_tip == ah->ar_sip) {
            /* Gratuitous ARP */
            arp_table_add(slirp, ah->ar_sip, ah->ar_sha);
            return;
        }

        if ((ah->ar_tip & slirp->vnetwork_mask.s_addr) ==
            slirp->vnetwork_addr.s_addr) {
            if (ah->ar_tip == slirp->vnameserver_addr.s_addr ||
                ah->ar_tip == slirp->vhost_addr.s_addr)
                goto arp_ok;
            for (ex_ptr = slirp->guestfwd_list; ex_ptr; ex_ptr = ex_ptr->ex_next) {
                if (ex_ptr->ex_addr.s_addr == ah->ar_tip)
                    goto arp_ok;
            }
            return;
        arp_ok:
            memset(arp_reply, 0, sizeof(arp_reply));

            arp_table_add(slirp, ah->ar_sip, ah->ar_sha);

            /* ARP request for alias/dns mac address */
            memcpy(reh->h_dest, pkt + ETH_ALEN, ETH_ALEN);
            memcpy(reh->h_source, special_ethaddr, ETH_ALEN - 4);
            memcpy(&reh->h_source[2], &ah->ar_tip, 4);
            reh->h_proto = htons(ETH_P_ARP);

            rah->ar_hrd = htons(1);
            rah->ar_pro = htons(ETH_P_IP);
            rah->ar_hln = ETH_ALEN;
            rah->ar_pln = 4;
            rah->ar_op = htons(ARPOP_REPLY);
            memcpy(rah->ar_sha, reh->h_source, ETH_ALEN);
            rah->ar_sip = ah->ar_tip;
            memcpy(rah->ar_tha, ah->ar_sha, ETH_ALEN);
            rah->ar_tip = ah->ar_sip;
            slirp_send_packet_all(slirp, arp_reply, sizeof(arp_reply));
        }
        break;
    case ARPOP_REPLY:
        arp_table_add(slirp, ah->ar_sip, ah->ar_sha);
        break;
    default:
        break;
    }
}

void slirp_input(Slirp *slirp, const uint8_t *pkt, int pkt_len)
{
    struct mbuf *m;
    int proto;

    if (pkt_len < ETH_HLEN)
        return;

    proto = (((uint16_t) pkt[12]) << 8) + pkt[13];
    switch(proto) {
    case ETH_P_ARP:
        arp_input(slirp, pkt, pkt_len);
        break;
    case ETH_P_IP:
    case ETH_P_IPV6:
        m = m_get(slirp);
        if (!m)
            return;
        /* Note: we add 2 to align the IP header on 4 bytes,
         * and add the margin for the tcpiphdr overhead  */
        if (M_FREEROOM(m) < pkt_len + TCPIPHDR_DELTA + 2) {
            m_inc(m, pkt_len + TCPIPHDR_DELTA + 2);
        }
        m->m_len = pkt_len + TCPIPHDR_DELTA + 2;
        memcpy(m->m_data + TCPIPHDR_DELTA + 2, pkt, pkt_len);

        m->m_data += TCPIPHDR_DELTA + 2 + ETH_HLEN;
        m->m_len -= TCPIPHDR_DELTA + 2 + ETH_HLEN;

        if (proto == ETH_P_IP) {
            ip_input(m);
        } else if (proto == ETH_P_IPV6) {
            ip6_input(m);
        }
        break;

    case ETH_P_NCSI:
        ncsi_input(slirp, pkt, pkt_len);
        break;

    default:
        break;
    }
}

/* Prepare the IPv4 packet to be sent to the ethernet device. Returns 1 if no
 * packet should be sent, 0 if the packet must be re-queued, 2 if the packet
 * is ready to go.
 */
static int if_encap4(Slirp *slirp, struct mbuf *ifm, struct ethhdr *eh,
        uint8_t ethaddr[ETH_ALEN])
{
    const struct ip *iph = (const struct ip *)ifm->m_data;

    if (iph->ip_dst.s_addr == 0) {
        /* 0.0.0.0 can not be a destination address, something went wrong,
         * avoid making it worse */
        return 1;
    }
    if (!arp_table_search(slirp, iph->ip_dst.s_addr, ethaddr)) {
        uint8_t arp_req[ETH_HLEN + sizeof(struct slirp_arphdr)];
        struct ethhdr *reh = (struct ethhdr *)arp_req;
        struct slirp_arphdr *rah = (struct slirp_arphdr *)(arp_req + ETH_HLEN);

        if (!ifm->resolution_requested) {
            /* If the client addr is not known, send an ARP request */
            memset(reh->h_dest, 0xff, ETH_ALEN);
            memcpy(reh->h_source, special_ethaddr, ETH_ALEN - 4);
            memcpy(&reh->h_source[2], &slirp->vhost_addr, 4);
            reh->h_proto = htons(ETH_P_ARP);
            rah->ar_hrd = htons(1);
            rah->ar_pro = htons(ETH_P_IP);
            rah->ar_hln = ETH_ALEN;
            rah->ar_pln = 4;
            rah->ar_op = htons(ARPOP_REQUEST);

            /* source hw addr */
            memcpy(rah->ar_sha, special_ethaddr, ETH_ALEN - 4);
            memcpy(&rah->ar_sha[2], &slirp->vhost_addr, 4);

            /* source IP */
            rah->ar_sip = slirp->vhost_addr.s_addr;

            /* target hw addr (none) */
            memset(rah->ar_tha, 0, ETH_ALEN);

            /* target IP */
            rah->ar_tip = iph->ip_dst.s_addr;
            slirp->client_ipaddr = iph->ip_dst;
            slirp_send_packet_all(slirp, arp_req, sizeof(arp_req));
            ifm->resolution_requested = true;

            /* Expire request and drop outgoing packet after 1 second */
            ifm->expiration_date = slirp->cb->clock_get_ns() + 1000000000ULL;
        }
        return 0;
    } else {
        memcpy(eh->h_source, special_ethaddr, ETH_ALEN - 4);
        /* XXX: not correct */
        memcpy(&eh->h_source[2], &slirp->vhost_addr, 4);
        eh->h_proto = htons(ETH_P_IP);

        /* Send this */
        return 2;
    }
}

/* Prepare the IPv6 packet to be sent to the ethernet device. Returns 1 if no
 * packet should be sent, 0 if the packet must be re-queued, 2 if the packet
 * is ready to go.
 */
static int if_encap6(Slirp *slirp, struct mbuf *ifm, struct ethhdr *eh,
        uint8_t ethaddr[ETH_ALEN])
{
    const struct ip6 *ip6h = mtod(ifm, const struct ip6 *);
    if (!ndp_table_search(slirp, ip6h->ip_dst, ethaddr)) {
        if (!ifm->resolution_requested) {
            ndp_send_ns(slirp, ip6h->ip_dst);
            ifm->resolution_requested = true;
            ifm->expiration_date = slirp->cb->clock_get_ns() + 1000000000ULL;
        }
        return 0;
    } else {
        eh->h_proto = htons(ETH_P_IPV6);
        in6_compute_ethaddr(ip6h->ip_src, eh->h_source);

        /* Send this */
        return 2;
    }
}

/* Output the IP packet to the ethernet device. Returns 0 if the packet must be
 * re-queued.
 */
int if_encap(Slirp *slirp, struct mbuf *ifm)
{
    uint8_t buf[1600];
    struct ethhdr *eh = (struct ethhdr *)buf;
    uint8_t ethaddr[ETH_ALEN];
    const struct ip *iph = (const struct ip *)ifm->m_data;
    int ret;

    if (ifm->m_len + ETH_HLEN > sizeof(buf)) {
        return 1;
    }

    switch (iph->ip_v) {
    case IPVERSION:
        ret = if_encap4(slirp, ifm, eh, ethaddr);
        if (ret < 2) {
            return ret;
        }
        break;

    case IP6VERSION:
        ret = if_encap6(slirp, ifm, eh, ethaddr);
        if (ret < 2) {
            return ret;
        }
        break;

    default:
        g_assert_not_reached();
        break;
    }

    memcpy(eh->h_dest, ethaddr, ETH_ALEN);
    DEBUG_ARG("src = %02x:%02x:%02x:%02x:%02x:%02x",
              eh->h_source[0], eh->h_source[1], eh->h_source[2],
              eh->h_source[3], eh->h_source[4], eh->h_source[5]);
    DEBUG_ARG("dst = %02x:%02x:%02x:%02x:%02x:%02x",
              eh->h_dest[0], eh->h_dest[1], eh->h_dest[2],
              eh->h_dest[3], eh->h_dest[4], eh->h_dest[5]);
    memcpy(buf + sizeof(struct ethhdr), ifm->m_data, ifm->m_len);
    slirp_send_packet_all(slirp, buf, ifm->m_len + ETH_HLEN);
    return 1;
}

/* Drop host forwarding rule, return 0 if found. */
int slirp_remove_hostfwd(Slirp *slirp, int is_udp, struct in_addr host_addr,
                         int host_port)
{
    struct socket *so;
    struct socket *head = (is_udp ? &slirp->udb : &slirp->tcb);
    struct sockaddr_in addr;
    int port = htons(host_port);
    socklen_t addr_len;

    for (so = head->so_next; so != head; so = so->so_next) {
        addr_len = sizeof(addr);
        if ((so->so_state & SS_HOSTFWD) &&
            getsockname(so->s, (struct sockaddr *)&addr, &addr_len) == 0 &&
            addr.sin_addr.s_addr == host_addr.s_addr &&
            addr.sin_port == port) {
            so->slirp->cb->unregister_poll_fd(so->s);
            slirp_closesocket(so->s);
            sofree(so);
            return 0;
        }
    }

    return -1;
}

int slirp_add_hostfwd(Slirp *slirp, int is_udp, struct in_addr host_addr,
                      int host_port, struct in_addr guest_addr, int guest_port)
{
    if (!guest_addr.s_addr) {
        guest_addr = slirp->vdhcp_startaddr;
    }
    if (is_udp) {
        if (!udp_listen(slirp, host_addr.s_addr, htons(host_port),
                        guest_addr.s_addr, htons(guest_port), SS_HOSTFWD))
            return -1;
    } else {
        if (!tcp_listen(slirp, host_addr.s_addr, htons(host_port),
                        guest_addr.s_addr, htons(guest_port), SS_HOSTFWD))
            return -1;
    }
    return 0;
}

static bool
check_guestfwd(Slirp *slirp, struct in_addr *guest_addr, int guest_port)
{
    struct gfwd_list *tmp_ptr;

    if (!guest_addr->s_addr) {
        guest_addr->s_addr = slirp->vnetwork_addr.s_addr |
            (htonl(0x0204) & ~slirp->vnetwork_mask.s_addr);
    }
    if ((guest_addr->s_addr & slirp->vnetwork_mask.s_addr) !=
        slirp->vnetwork_addr.s_addr ||
        guest_addr->s_addr == slirp->vhost_addr.s_addr ||
        guest_addr->s_addr == slirp->vnameserver_addr.s_addr) {
        return false;
    }

    /* check if the port is "bound" */
    for (tmp_ptr = slirp->guestfwd_list; tmp_ptr; tmp_ptr = tmp_ptr->ex_next) {
        if (guest_port == tmp_ptr->ex_fport &&
            guest_addr->s_addr == tmp_ptr->ex_addr.s_addr)
            return false;
    }

    return true;
}

int slirp_add_exec(Slirp *slirp, const char *cmdline,
                   struct in_addr *guest_addr, int guest_port)
{
    if (!check_guestfwd(slirp, guest_addr, guest_port)) {
        return -1;
    }

    add_exec(&slirp->guestfwd_list, cmdline, *guest_addr, htons(guest_port));
    return 0;
}

int slirp_add_guestfwd(Slirp *slirp, SlirpWriteCb write_cb, void *opaque,
                       struct in_addr *guest_addr, int guest_port)
{
    if (!check_guestfwd(slirp, guest_addr, guest_port)) {
        return -1;
    }

    add_guestfwd(&slirp->guestfwd_list, write_cb, opaque,
                 *guest_addr, htons(guest_port));
    return 0;
}

ssize_t slirp_send(struct socket *so, const void *buf, size_t len, int flags)
{
    if (so->s == -1 && so->guestfwd) {
        /* XXX this blocks entire thread. Rewrite to use
         * qemu_chr_fe_write and background I/O callbacks */
        so->guestfwd->write_cb(buf, len, so->guestfwd->opaque);
        return len;
    }

    if (so->s == -1) {
        /*
         * This should in theory not happen but it is hard to be
         * sure because some code paths will end up with so->s == -1
         * on a failure but don't dispose of the struct socket.
         * Check specifically, so we don't pass -1 to send().
         */
        errno = EBADF;
        return -1;
    }

    return send(so->s, buf, len, flags);
}

struct socket *
slirp_find_ctl_socket(Slirp *slirp, struct in_addr guest_addr, int guest_port)
{
    struct socket *so;

    for (so = slirp->tcb.so_next; so != &slirp->tcb; so = so->so_next) {
        if (so->so_faddr.s_addr == guest_addr.s_addr &&
            htons(so->so_fport) == guest_port) {
            return so;
        }
    }
    return NULL;
}

size_t slirp_socket_can_recv(Slirp *slirp, struct in_addr guest_addr,
                             int guest_port)
{
    struct iovec iov[2];
    struct socket *so;

    so = slirp_find_ctl_socket(slirp, guest_addr, guest_port);

    if (!so || so->so_state & SS_NOFDREF) {
        return 0;
    }

    if (!CONN_CANFRCV(so) || so->so_snd.sb_cc >= (so->so_snd.sb_datalen/2)) {
        return 0;
    }

    return sopreprbuf(so, iov, NULL);
}

void slirp_socket_recv(Slirp *slirp, struct in_addr guest_addr, int guest_port,
                       const uint8_t *buf, int size)
{
    int ret;
    struct socket *so = slirp_find_ctl_socket(slirp, guest_addr, guest_port);

    if (!so)
        return;

    ret = soreadbuf(so, (const char *)buf, size);

    if (ret > 0)
        tcp_output(sototcpcb(so));
}

void slirp_send_packet_all(Slirp *slirp, const void *buf, size_t len)
{
    ssize_t ret = slirp->cb->send_packet(buf, len, slirp->opaque);

    if (ret < 0) {
        g_critical("Failed to send packet, ret: %ld", (long) ret);
    } else if (ret < len) {
        DEBUG_ERROR("send_packet() didn't send all data: %ld < %lu",
                (long) ret, (unsigned long) len);
    }
}