aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/lguest/lguest.c
blob: 32c2eaf94c4df59a260e7990406329057fea5c68 (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
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
/*P:100 This is the Launcher code, a simple program which lays out the
 * "physical" memory for the new Guest by mapping the kernel image and the
 * virtual devices, then reads repeatedly from /dev/lguest to run the Guest.
:*/
#define _LARGEFILE64_SOURCE
#define _GNU_SOURCE
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <err.h>
#include <stdint.h>
#include <stdlib.h>
#include <elf.h>
#include <sys/mman.h>
#include <sys/param.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <fcntl.h>
#include <stdbool.h>
#include <errno.h>
#include <ctype.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <sys/time.h>
#include <time.h>
#include <netinet/in.h>
#include <net/if.h>
#include <linux/sockios.h>
#include <linux/if_tun.h>
#include <sys/uio.h>
#include <termios.h>
#include <getopt.h>
#include <zlib.h>
/*L:110 We can ignore the 28 include files we need for this program, but I do
 * want to draw attention to the use of kernel-style types.
 *
 * As Linus said, "C is a Spartan language, and so should your naming be."  I
 * like these abbreviations and the header we need uses them, so we define them
 * here.
 */
typedef unsigned long long u64;
typedef uint32_t u32;
typedef uint16_t u16;
typedef uint8_t u8;
#include "linux/lguest_launcher.h"
#include "asm-x86/e820.h"
/*:*/

#define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
#define NET_PEERNUM 1
#define BRIDGE_PFX "bridge:"
#ifndef SIOCBRADDIF
#define SIOCBRADDIF	0x89a2		/* add interface to bridge      */
#endif
/* We can have up to 256 pages for devices. */
#define DEVICE_PAGES 256

/*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
 * this, and although I wouldn't recommend it, it works quite nicely here. */
static bool verbose;
#define verbose(args...) \
	do { if (verbose) printf(args); } while(0)
/*:*/

/* The pipe to send commands to the waker process */
static int waker_fd;
/* The pointer to the start of guest memory. */
static void *guest_base;
/* The maximum guest physical address allowed, and maximum possible. */
static unsigned long guest_limit, guest_max;

/* This is our list of devices. */
struct device_list
{
	/* Summary information about the devices in our list: ready to pass to
	 * select() to ask which need servicing.*/
	fd_set infds;
	int max_infd;

	/* The descriptor page for the devices. */
	struct lguest_device_desc *descs;

	/* A single linked list of devices. */
	struct device *dev;
	/* ... And an end pointer so we can easily append new devices */
	struct device **lastdev;
};

/* The device structure describes a single device. */
struct device
{
	/* The linked-list pointer. */
	struct device *next;
	/* The descriptor for this device, as mapped into the Guest. */
	struct lguest_device_desc *desc;
	/* The memory page(s) of this device, if any.  Also mapped in Guest. */
	void *mem;

	/* If handle_input is set, it wants to be called when this file
	 * descriptor is ready. */
	int fd;
	bool (*handle_input)(int fd, struct device *me);

	/* If handle_output is set, it wants to be called when the Guest sends
	 * DMA to this key. */
	unsigned long watch_key;
	u32 (*handle_output)(int fd, const struct iovec *iov,
			     unsigned int num, struct device *me);

	/* Device-specific data. */
	void *priv;
};

/*L:100 The Launcher code itself takes us out into userspace, that scary place
 * where pointers run wild and free!  Unfortunately, like most userspace
 * programs, it's quite boring (which is why everyone likes to hack on the
 * kernel!).  Perhaps if you make up an Lguest Drinking Game at this point, it
 * will get you through this section.  Or, maybe not.
 *
 * The Launcher sets up a big chunk of memory to be the Guest's "physical"
 * memory and stores it in "guest_base".  In other words, Guest physical ==
 * Launcher virtual with an offset.
 *
 * This can be tough to get your head around, but usually it just means that we
 * use these trivial conversion functions when the Guest gives us it's
 * "physical" addresses: */
static void *from_guest_phys(unsigned long addr)
{
	return guest_base + addr;
}

static unsigned long to_guest_phys(const void *addr)
{
	return (addr - guest_base);
}

/*L:130
 * Loading the Kernel.
 *
 * We start with couple of simple helper routines.  open_or_die() avoids
 * error-checking code cluttering the callers: */
static int open_or_die(const char *name, int flags)
{
	int fd = open(name, flags);
	if (fd < 0)
		err(1, "Failed to open %s", name);
	return fd;
}

/* map_zeroed_pages() takes a number of pages. */
static void *map_zeroed_pages(unsigned int num)
{
	int fd = open_or_die("/dev/zero", O_RDONLY);
	void *addr;

	/* We use a private mapping (ie. if we write to the page, it will be
	 * copied). */
	addr = mmap(NULL, getpagesize() * num,
		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
	if (addr == MAP_FAILED)
		err(1, "Mmaping %u pages of /dev/zero", num);

	return addr;
}

/* Get some more pages for a device. */
static void *get_pages(unsigned int num)
{
	void *addr = from_guest_phys(guest_limit);

	guest_limit += num * getpagesize();
	if (guest_limit > guest_max)
		errx(1, "Not enough memory for devices");
	return addr;
}

/* To find out where to start we look for the magic Guest string, which marks
 * the code we see in lguest_asm.S.  This is a hack which we are currently
 * plotting to replace with the normal Linux entry point. */
static unsigned long entry_point(const void *start, const void *end)
{
	const void *p;

	/* The scan gives us the physical starting address.  We boot with
	 * pagetables set up with virtual and physical the same, so that's
	 * OK. */
	for (p = start; p < end; p++)
		if (memcmp(p, "GenuineLguest", strlen("GenuineLguest")) == 0)
			return to_guest_phys(p + strlen("GenuineLguest"));

	errx(1, "Is this image a genuine lguest?");
}

/* This routine is used to load the kernel or initrd.  It tries mmap, but if
 * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries),
 * it falls back to reading the memory in. */
static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
{
	ssize_t r;

	/* We map writable even though for some segments are marked read-only.
	 * The kernel really wants to be writable: it patches its own
	 * instructions.
	 *
	 * MAP_PRIVATE means that the page won't be copied until a write is
	 * done to it.  This allows us to share untouched memory between
	 * Guests. */
	if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
		 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
		return;

	/* pread does a seek and a read in one shot: saves a few lines. */
	r = pread(fd, addr, len, offset);
	if (r != len)
		err(1, "Reading offset %lu len %lu gave %zi", offset, len, r);
}

/* This routine takes an open vmlinux image, which is in ELF, and maps it into
 * the Guest memory.  ELF = Embedded Linking Format, which is the format used
 * by all modern binaries on Linux including the kernel.
 *
 * The ELF headers give *two* addresses: a physical address, and a virtual
 * address.  We use the physical address; the Guest will map itself to the
 * virtual address.
 *
 * We return the starting address. */
static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
{
	void *start = (void *)-1, *end = NULL;
	Elf32_Phdr phdr[ehdr->e_phnum];
	unsigned int i;

	/* Sanity checks on the main ELF header: an x86 executable with a
	 * reasonable number of correctly-sized program headers. */
	if (ehdr->e_type != ET_EXEC
	    || ehdr->e_machine != EM_386
	    || ehdr->e_phentsize != sizeof(Elf32_Phdr)
	    || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr))
		errx(1, "Malformed elf header");

	/* An ELF executable contains an ELF header and a number of "program"
	 * headers which indicate which parts ("segments") of the program to
	 * load where. */

	/* We read in all the program headers at once: */
	if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
		err(1, "Seeking to program headers");
	if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
		err(1, "Reading program headers");

	/* Try all the headers: there are usually only three.  A read-only one,
	 * a read-write one, and a "note" section which isn't loadable. */
	for (i = 0; i < ehdr->e_phnum; i++) {
		/* If this isn't a loadable segment, we ignore it */
		if (phdr[i].p_type != PT_LOAD)
			continue;

		verbose("Section %i: size %i addr %p\n",
			i, phdr[i].p_memsz, (void *)phdr[i].p_paddr);

		/* We track the first and last address we mapped, so we can
		 * tell entry_point() where to scan. */
		if (from_guest_phys(phdr[i].p_paddr) < start)
			start = from_guest_phys(phdr[i].p_paddr);
		if (from_guest_phys(phdr[i].p_paddr) + phdr[i].p_filesz > end)
			end=from_guest_phys(phdr[i].p_paddr)+phdr[i].p_filesz;

		/* We map this section of the file at its physical address. */
		map_at(elf_fd, from_guest_phys(phdr[i].p_paddr),
		       phdr[i].p_offset, phdr[i].p_filesz);
	}

	return entry_point(start, end);
}

/*L:160 Unfortunately the entire ELF image isn't compressed: the segments
 * which need loading are extracted and compressed raw.  This denies us the
 * information we need to make a fully-general loader. */
static unsigned long unpack_bzimage(int fd)
{
	gzFile f;
	int ret, len = 0;
	/* A bzImage always gets loaded at physical address 1M.  This is
	 * actually configurable as CONFIG_PHYSICAL_START, but as the comment
	 * there says, "Don't change this unless you know what you are doing".
	 * Indeed. */
	void *img = from_guest_phys(0x100000);

	/* gzdopen takes our file descriptor (carefully placed at the start of
	 * the GZIP header we found) and returns a gzFile. */
	f = gzdopen(fd, "rb");
	/* We read it into memory in 64k chunks until we hit the end. */
	while ((ret = gzread(f, img + len, 65536)) > 0)
		len += ret;
	if (ret < 0)
		err(1, "reading image from bzImage");

	verbose("Unpacked size %i addr %p\n", len, img);

	return entry_point(img, img + len);
}

/*L:150 A bzImage, unlike an ELF file, is not meant to be loaded.  You're
 * supposed to jump into it and it will unpack itself.  We can't do that
 * because the Guest can't run the unpacking code, and adding features to
 * lguest kills puppies, so we don't want to.
 *
 * The bzImage is formed by putting the decompressing code in front of the
 * compressed kernel code.  So we can simple scan through it looking for the
 * first "gzip" header, and start decompressing from there. */
static unsigned long load_bzimage(int fd)
{
	unsigned char c;
	int state = 0;

	/* GZIP header is 0x1F 0x8B <method> <flags>... <compressed-by>. */
	while (read(fd, &c, 1) == 1) {
		switch (state) {
		case 0:
			if (c == 0x1F)
				state++;
			break;
		case 1:
			if (c == 0x8B)
				state++;
			else
				state = 0;
			break;
		case 2 ... 8:
			state++;
			break;
		case 9:
			/* Seek back to the start of the gzip header. */
			lseek(fd, -10, SEEK_CUR);
			/* One final check: "compressed under UNIX". */
			if (c != 0x03)
				state = -1;
			else
				return unpack_bzimage(fd);
		}
	}
	errx(1, "Could not find kernel in bzImage");
}

/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels
 * come wrapped up in the self-decompressing "bzImage" format.  With some funky
 * coding, we can load those, too. */
static unsigned long load_kernel(int fd)
{
	Elf32_Ehdr hdr;

	/* Read in the first few bytes. */
	if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr))
		err(1, "Reading kernel");

	/* If it's an ELF file, it starts with "\177ELF" */
	if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0)
		return map_elf(fd, &hdr);

	/* Otherwise we assume it's a bzImage, and try to unpack it */
	return load_bzimage(fd);
}

/* This is a trivial little helper to align pages.  Andi Kleen hated it because
 * it calls getpagesize() twice: "it's dumb code."
 *
 * Kernel guys get really het up about optimization, even when it's not
 * necessary.  I leave this code as a reaction against that. */
static inline unsigned long page_align(unsigned long addr)
{
	/* Add upwards and truncate downwards. */
	return ((addr + getpagesize()-1) & ~(getpagesize()-1));
}

/*L:180 An "initial ram disk" is a disk image loaded into memory along with
 * the kernel which the kernel can use to boot from without needing any
 * drivers.  Most distributions now use this as standard: the initrd contains
 * the code to load the appropriate driver modules for the current machine.
 *
 * Importantly, James Morris works for RedHat, and Fedora uses initrds for its
 * kernels.  He sent me this (and tells me when I break it). */
static unsigned long load_initrd(const char *name, unsigned long mem)
{
	int ifd;
	struct stat st;
	unsigned long len;

	ifd = open_or_die(name, O_RDONLY);
	/* fstat() is needed to get the file size. */
	if (fstat(ifd, &st) < 0)
		err(1, "fstat() on initrd '%s'", name);

	/* We map the initrd at the top of memory, but mmap wants it to be
	 * page-aligned, so we round the size up for that. */
	len = page_align(st.st_size);
	map_at(ifd, from_guest_phys(mem - len), 0, st.st_size);
	/* Once a file is mapped, you can close the file descriptor.  It's a
	 * little odd, but quite useful. */
	close(ifd);
	verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len);

	/* We return the initrd size. */
	return len;
}

/* Once we know how much memory we have, we can construct simple linear page
 * tables which set virtual == physical which will get the Guest far enough
 * into the boot to create its own.
 *
 * We lay them out of the way, just below the initrd (which is why we need to
 * know its size). */
static unsigned long setup_pagetables(unsigned long mem,
				      unsigned long initrd_size)
{
	unsigned long *pgdir, *linear;
	unsigned int mapped_pages, i, linear_pages;
	unsigned int ptes_per_page = getpagesize()/sizeof(void *);

	mapped_pages = mem/getpagesize();

	/* Each PTE page can map ptes_per_page pages: how many do we need? */
	linear_pages = (mapped_pages + ptes_per_page-1)/ptes_per_page;

	/* We put the toplevel page directory page at the top of memory. */
	pgdir = from_guest_phys(mem) - initrd_size - getpagesize();

	/* Now we use the next linear_pages pages as pte pages */
	linear = (void *)pgdir - linear_pages*getpagesize();

	/* Linear mapping is easy: put every page's address into the mapping in
	 * order.  PAGE_PRESENT contains the flags Present, Writable and
	 * Executable. */
	for (i = 0; i < mapped_pages; i++)
		linear[i] = ((i * getpagesize()) | PAGE_PRESENT);

	/* The top level points to the linear page table pages above. */
	for (i = 0; i < mapped_pages; i += ptes_per_page) {
		pgdir[i/ptes_per_page]
			= ((to_guest_phys(linear) + i*sizeof(void *))
			   | PAGE_PRESENT);
	}

	verbose("Linear mapping of %u pages in %u pte pages at %#lx\n",
		mapped_pages, linear_pages, to_guest_phys(linear));

	/* We return the top level (guest-physical) address: the kernel needs
	 * to know where it is. */
	return to_guest_phys(pgdir);
}

/* Simple routine to roll all the commandline arguments together with spaces
 * between them. */
static void concat(char *dst, char *args[])
{
	unsigned int i, len = 0;

	for (i = 0; args[i]; i++) {
		strcpy(dst+len, args[i]);
		strcat(dst+len, " ");
		len += strlen(args[i]) + 1;
	}
	/* In case it's empty. */
	dst[len] = '\0';
}

/* This is where we actually tell the kernel to initialize the Guest.  We saw
 * the arguments it expects when we looked at initialize() in lguest_user.c:
 * the base of guest "physical" memory, the top physical page to allow, the
 * top level pagetable and the entry point for the Guest. */
static int tell_kernel(unsigned long pgdir, unsigned long start)
{
	unsigned long args[] = { LHREQ_INITIALIZE,
				 (unsigned long)guest_base,
				 guest_limit / getpagesize(), pgdir, start };
	int fd;

	verbose("Guest: %p - %p (%#lx)\n",
		guest_base, guest_base + guest_limit, guest_limit);
	fd = open_or_die("/dev/lguest", O_RDWR);
	if (write(fd, args, sizeof(args)) < 0)
		err(1, "Writing to /dev/lguest");

	/* We return the /dev/lguest file descriptor to control this Guest */
	return fd;
}
/*:*/

static void set_fd(int fd, struct device_list *devices)
{
	FD_SET(fd, &devices->infds);
	if (fd > devices->max_infd)
		devices->max_infd = fd;
}

/*L:200
 * The Waker.
 *
 * With a console and network devices, we can have lots of input which we need
 * to process.  We could try to tell the kernel what file descriptors to watch,
 * but handing a file descriptor mask through to the kernel is fairly icky.
 *
 * Instead, we fork off a process which watches the file descriptors and writes
 * the LHREQ_BREAK command to the /dev/lguest filedescriptor to tell the Host
 * loop to stop running the Guest.  This causes it to return from the
 * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
 * the LHREQ_BREAK and wake us up again.
 *
 * This, of course, is merely a different *kind* of icky.
 */
static void wake_parent(int pipefd, int lguest_fd, struct device_list *devices)
{
	/* Add the pipe from the Launcher to the fdset in the device_list, so
	 * we watch it, too. */
	set_fd(pipefd, devices);

	for (;;) {
		fd_set rfds = devices->infds;
		unsigned long args[] = { LHREQ_BREAK, 1 };

		/* Wait until input is ready from one of the devices. */
		select(devices->max_infd+1, &rfds, NULL, NULL, NULL);
		/* Is it a message from the Launcher? */
		if (FD_ISSET(pipefd, &rfds)) {
			int ignorefd;
			/* If read() returns 0, it means the Launcher has
			 * exited.  We silently follow. */
			if (read(pipefd, &ignorefd, sizeof(ignorefd)) == 0)
				exit(0);
			/* Otherwise it's telling us there's a problem with one
			 * of the devices, and we should ignore that file
			 * descriptor from now on. */
			FD_CLR(ignorefd, &devices->infds);
		} else /* Send LHREQ_BREAK command. */
			write(lguest_fd, args, sizeof(args));
	}
}

/* This routine just sets up a pipe to the Waker process. */
static int setup_waker(int lguest_fd, struct device_list *device_list)
{
	int pipefd[2], child;

	/* We create a pipe to talk to the waker, and also so it knows when the
	 * Launcher dies (and closes pipe). */
	pipe(pipefd);
	child = fork();
	if (child == -1)
		err(1, "forking");

	if (child == 0) {
		/* Close the "writing" end of our copy of the pipe */
		close(pipefd[1]);
		wake_parent(pipefd[0], lguest_fd, device_list);
	}
	/* Close the reading end of our copy of the pipe. */
	close(pipefd[0]);

	/* Here is the fd used to talk to the waker. */
	return pipefd[1];
}

/*L:210
 * Device Handling.
 *
 * When the Guest sends DMA to us, it sends us an array of addresses and sizes.
 * We need to make sure it's not trying to reach into the Launcher itself, so
 * we have a convenient routine which check it and exits with an error message
 * if something funny is going on:
 */
static void *_check_pointer(unsigned long addr, unsigned int size,
			    unsigned int line)
{
	/* We have to separately check addr and addr+size, because size could
	 * be huge and addr + size might wrap around. */
	if (addr >= guest_limit || addr + size >= guest_limit)
		errx(1, "%s:%i: Invalid address %li", __FILE__, line, addr);
	/* We return a pointer for the caller's convenience, now we know it's
	 * safe to use. */
	return from_guest_phys(addr);
}
/* A macro which transparently hands the line number to the real function. */
#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)

/* The Guest has given us the address of a "struct lguest_dma".  We check it's
 * OK and convert it to an iovec (which is a simple array of ptr/size
 * pairs). */
static u32 *dma2iov(unsigned long dma, struct iovec iov[], unsigned *num)
{
	unsigned int i;
	struct lguest_dma *udma;

	/* First we make sure that the array memory itself is valid. */
	udma = check_pointer(dma, sizeof(*udma));
	/* Now we check each element */
	for (i = 0; i < LGUEST_MAX_DMA_SECTIONS; i++) {
		/* A zero length ends the array. */
		if (!udma->len[i])
			break;

		iov[i].iov_base = check_pointer(udma->addr[i], udma->len[i]);
		iov[i].iov_len = udma->len[i];
	}
	*num = i;

	/* We return the pointer to where the caller should write the amount of
	 * the buffer used. */
	return &udma->used_len;
}

/* This routine gets a DMA buffer from the Guest for a given key, and converts
 * it to an iovec array.  It returns the interrupt the Guest wants when we're
 * finished, and a pointer to the "used_len" field to fill in. */
static u32 *get_dma_buffer(int fd, void *key,
			   struct iovec iov[], unsigned int *num, u32 *irq)
{
	unsigned long buf[] = { LHREQ_GETDMA, to_guest_phys(key) };
	unsigned long udma;
	u32 *res;

	/* Ask the kernel for a DMA buffer corresponding to this key. */
	udma = write(fd, buf, sizeof(buf));
	/* They haven't registered any, or they're all used? */
	if (udma == (unsigned long)-1)
		return NULL;

	/* Convert it into our iovec array */
	res = dma2iov(udma, iov, num);
	/* The kernel stashes irq in ->used_len to get it out to us. */
	*irq = *res;
	/* Return a pointer to ((struct lguest_dma *)udma)->used_len. */
	return res;
}

/* This is a convenient routine to send the Guest an interrupt. */
static void trigger_irq(int fd, u32 irq)
{
	unsigned long buf[] = { LHREQ_IRQ, irq };
	if (write(fd, buf, sizeof(buf)) != 0)
		err(1, "Triggering irq %i", irq);
}

/* This simply sets up an iovec array where we can put data to be discarded.
 * This happens when the Guest doesn't want or can't handle the input: we have
 * to get rid of it somewhere, and if we bury it in the ceiling space it will
 * start to smell after a week. */
static void discard_iovec(struct iovec *iov, unsigned int *num)
{
	static char discard_buf[1024];
	*num = 1;
	iov->iov_base = discard_buf;
	iov->iov_len = sizeof(discard_buf);
}

/* Here is the input terminal setting we save, and the routine to restore them
 * on exit so the user can see what they type next. */
static struct termios orig_term;
static void restore_term(void)
{
	tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
}

/* We associate some data with the console for our exit hack. */
struct console_abort
{
	/* How many times have they hit ^C? */
	int count;
	/* When did they start? */
	struct timeval start;
};

/* This is the routine which handles console input (ie. stdin). */
static bool handle_console_input(int fd, struct device *dev)
{
	u32 irq = 0, *lenp;
	int len;
	unsigned int num;
	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
	struct console_abort *abort = dev->priv;

	/* First we get the console buffer from the Guest.  The key is dev->mem
	 * which was set to 0 in setup_console(). */
	lenp = get_dma_buffer(fd, dev->mem, iov, &num, &irq);
	if (!lenp) {
		/* If it's not ready for input, warn and set up to discard. */
		warn("console: no dma buffer!");
		discard_iovec(iov, &num);
	}

	/* This is why we convert to iovecs: the readv() call uses them, and so
	 * it reads straight into the Guest's buffer. */
	len = readv(dev->fd, iov, num);
	if (len <= 0) {
		/* This implies that the console is closed, is /dev/null, or
		 * something went terribly wrong.  We still go through the rest
		 * of the logic, though, especially the exit handling below. */
		warnx("Failed to get console input, ignoring console.");
		len = 0;
	}

	/* If we read the data into the Guest, fill in the length and send the
	 * interrupt. */
	if (lenp) {
		*lenp = len;
		trigger_irq(fd, irq);
	}

	/* Three ^C within one second?  Exit.
	 *
	 * This is such a hack, but works surprisingly well.  Each ^C has to be
	 * in a buffer by itself, so they can't be too fast.  But we check that
	 * we get three within about a second, so they can't be too slow. */
	if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
		if (!abort->count++)
			gettimeofday(&abort->start, NULL);
		else if (abort->count == 3) {
			struct timeval now;
			gettimeofday(&now, NULL);
			if (now.tv_sec <= abort->start.tv_sec+1) {
				unsigned long args[] = { LHREQ_BREAK, 0 };
				/* Close the fd so Waker will know it has to
				 * exit. */
				close(waker_fd);
				/* Just in case waker is blocked in BREAK, send
				 * unbreak now. */
				write(fd, args, sizeof(args));
				exit(2);
			}
			abort->count = 0;
		}
	} else
		/* Any other key resets the abort counter. */
		abort->count = 0;

	/* Now, if we didn't read anything, put the input terminal back and
	 * return failure (meaning, don't call us again). */
	if (!len) {
		restore_term();
		return false;
	}
	/* Everything went OK! */
	return true;
}

/* Handling console output is much simpler than input. */
static u32 handle_console_output(int fd, const struct iovec *iov,
				 unsigned num, struct device*dev)
{
	/* Whatever the Guest sends, write it to standard output.  Return the
	 * number of bytes written. */
	return writev(STDOUT_FILENO, iov, num);
}

/* Guest->Host network output is also pretty easy. */
static u32 handle_tun_output(int fd, const struct iovec *iov,
			     unsigned num, struct device *dev)
{
	/* We put a flag in the "priv" pointer of the network device, and set
	 * it as soon as we see output.  We'll see why in handle_tun_input() */
	*(bool *)dev->priv = true;
	/* Whatever packet the Guest sent us, write it out to the tun
	 * device. */
	return writev(dev->fd, iov, num);
}

/* This matches the peer_key() in lguest_net.c.  The key for any given slot
 * is the address of the network device's page plus 4 * the slot number. */
static unsigned long peer_offset(unsigned int peernum)
{
	return 4 * peernum;
}

/* This is where we handle a packet coming in from the tun device */
static bool handle_tun_input(int fd, struct device *dev)
{
	u32 irq = 0, *lenp;
	int len;
	unsigned num;
	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];

	/* First we get a buffer the Guest has bound to its key. */
	lenp = get_dma_buffer(fd, dev->mem+peer_offset(NET_PEERNUM), iov, &num,
			      &irq);
	if (!lenp) {
		/* Now, it's expected that if we try to send a packet too
		 * early, the Guest won't be ready yet.  This is why we set a
		 * flag when the Guest sends its first packet.  If it's sent a
		 * packet we assume it should be ready to receive them.
		 *
		 * Actually, this is what the status bits in the descriptor are
		 * for: we should *use* them.  FIXME! */
		if (*(bool *)dev->priv)
			warn("network: no dma buffer!");
		discard_iovec(iov, &num);
	}

	/* Read the packet from the device directly into the Guest's buffer. */
	len = readv(dev->fd, iov, num);
	if (len <= 0)
		err(1, "reading network");

	/* Write the used_len, and trigger the interrupt for the Guest */
	if (lenp) {
		*lenp = len;
		trigger_irq(fd, irq);
	}
	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
		((u8 *)iov[0].iov_base)[0], ((u8 *)iov[0].iov_base)[1],
		lenp ? "sent" : "discarded");
	/* All good. */
	return true;
}

/* The last device handling routine is block output: the Guest has sent a DMA
 * to the block device.  It will have placed the command it wants in the
 * "struct lguest_block_page". */
static u32 handle_block_output(int fd, const struct iovec *iov,
			       unsigned num, struct device *dev)
{
	struct lguest_block_page *p = dev->mem;
	u32 irq, *lenp;
	unsigned int len, reply_num;
	struct iovec reply[LGUEST_MAX_DMA_SECTIONS];
	off64_t device_len, off = (off64_t)p->sector * 512;

	/* First we extract the device length from the dev->priv pointer. */
	device_len = *(off64_t *)dev->priv;

	/* We first check that the read or write is within the length of the
	 * block file. */
	if (off >= device_len)
		errx(1, "Bad offset %llu vs %llu", off, device_len);
	/* Move to the right location in the block file.  This shouldn't fail,
	 * but best to check. */
	if (lseek64(dev->fd, off, SEEK_SET) != off)
		err(1, "Bad seek to sector %i", p->sector);

	verbose("Block: %s at offset %llu\n", p->type ? "WRITE" : "READ", off);

	/* They were supposed to bind a reply buffer at key equal to the start
	 * of the block device memory.  We need this to tell them when the
	 * request is finished. */
	lenp = get_dma_buffer(fd, dev->mem, reply, &reply_num, &irq);
	if (!lenp)
		err(1, "Block request didn't give us a dma buffer");

	if (p->type) {
		/* A write request.  The DMA they sent contained the data, so
		 * write it out. */
		len = writev(dev->fd, iov, num);
		/* Grr... Now we know how long the "struct lguest_dma" they
		 * sent was, we make sure they didn't try to write over the end
		 * of the block file (possibly extending it). */
		if (off + len > device_len) {
			/* Trim it back to the correct length */
			ftruncate64(dev->fd, device_len);
			/* Die, bad Guest, die. */
			errx(1, "Write past end %llu+%u", off, len);
		}
		/* The reply length is 0: we just send back an empty DMA to
		 * interrupt them and tell them the write is finished. */
		*lenp = 0;
	} else {
		/* A read request.  They sent an empty DMA to start the
		 * request, and we put the read contents into the reply
		 * buffer. */
		len = readv(dev->fd, reply, reply_num);
		*lenp = len;
	}

	/* The result is 1 (done), 2 if there was an error (short read or
	 * write). */
	p->result = 1 + (p->bytes != len);
	/* Now tell them we've used their reply buffer. */
	trigger_irq(fd, irq);

	/* We're supposed to return the number of bytes of the output buffer we
	 * used.  But the block device uses the "result" field instead, so we
	 * don't bother. */
	return 0;
}

/* This is the generic routine we call when the Guest sends some DMA out. */
static void handle_output(int fd, unsigned long dma, unsigned long key,
			  struct device_list *devices)
{
	struct device *i;
	u32 *lenp;
	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
	unsigned num = 0;

	/* Convert the "struct lguest_dma" they're sending to a "struct
	 * iovec". */
	lenp = dma2iov(dma, iov, &num);

	/* Check each device: if they expect output to this key, tell them to
	 * handle it. */
	for (i = devices->dev; i; i = i->next) {
		if (i->handle_output && key == i->watch_key) {
			/* We write the result straight into the used_len field
			 * for them. */
			*lenp = i->handle_output(fd, iov, num, i);
			return;
		}
	}

	/* This can happen: the kernel sends any SEND_DMA which doesn't match
	 * another Guest to us.  It could be that another Guest just left a
	 * network, for example.  But it's unusual. */
	warnx("Pending dma %p, key %p", (void *)dma, (void *)key);
}

/* This is called when the waker wakes us up: check for incoming file
 * descriptors. */
static void handle_input(int fd, struct device_list *devices)
{
	/* select() wants a zeroed timeval to mean "don't wait". */
	struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };

	for (;;) {
		struct device *i;
		fd_set fds = devices->infds;

		/* If nothing is ready, we're done. */
		if (select(devices->max_infd+1, &fds, NULL, NULL, &poll) == 0)
			break;

		/* Otherwise, call the device(s) which have readable
		 * file descriptors and a method of handling them.  */
		for (i = devices->dev; i; i = i->next) {
			if (i->handle_input && FD_ISSET(i->fd, &fds)) {
				/* If handle_input() returns false, it means we
				 * should no longer service it.
				 * handle_console_input() does this. */
				if (!i->handle_input(fd, i)) {
					/* Clear it from the set of input file
					 * descriptors kept at the head of the
					 * device list. */
					FD_CLR(i->fd, &devices->infds);
					/* Tell waker to ignore it too... */
					write(waker_fd, &i->fd, sizeof(i->fd));
				}
			}
		}
	}
}

/*L:190
 * Device Setup
 *
 * All devices need a descriptor so the Guest knows it exists, and a "struct
 * device" so the Launcher can keep track of it.  We have common helper
 * routines to allocate them.
 *
 * This routine allocates a new "struct lguest_device_desc" from descriptor
 * table in the devices array just above the Guest's normal memory. */
static struct lguest_device_desc *
new_dev_desc(struct lguest_device_desc *descs,
	     u16 type, u16 features, u16 num_pages)
{
	unsigned int i;

	for (i = 0; i < LGUEST_MAX_DEVICES; i++) {
		if (!descs[i].type) {
			descs[i].type = type;
			descs[i].features = features;
			descs[i].num_pages = num_pages;
			/* If they said the device needs memory, we allocate
			 * that now. */
			if (num_pages) {
				unsigned long pa;
				pa = to_guest_phys(get_pages(num_pages));
				descs[i].pfn = pa / getpagesize();
			}
			return &descs[i];
		}
	}
	errx(1, "too many devices");
}

/* This monster routine does all the creation and setup of a new device,
 * including caling new_dev_desc() to allocate the descriptor and device
 * memory. */
static struct device *new_device(struct device_list *devices,
				 u16 type, u16 num_pages, u16 features,
				 int fd,
				 bool (*handle_input)(int, struct device *),
				 unsigned long watch_off,
				 u32 (*handle_output)(int,
						      const struct iovec *,
						      unsigned,
						      struct device *))
{
	struct device *dev = malloc(sizeof(*dev));

	/* Append to device list.  Prepending to a single-linked list is
	 * easier, but the user expects the devices to be arranged on the bus
	 * in command-line order.  The first network device on the command line
	 * is eth0, the first block device /dev/lgba, etc. */
	*devices->lastdev = dev;
	dev->next = NULL;
	devices->lastdev = &dev->next;

	/* Now we populate the fields one at a time. */
	dev->fd = fd;
	/* If we have an input handler for this file descriptor, then we add it
	 * to the device_list's fdset and maxfd. */
	if (handle_input)
		set_fd(dev->fd, devices);
	dev->desc = new_dev_desc(devices->descs, type, features, num_pages);
	dev->mem = from_guest_phys(dev->desc->pfn * getpagesize());
	dev->handle_input = handle_input;
	dev->watch_key = to_guest_phys(dev->mem) + watch_off;
	dev->handle_output = handle_output;
	return dev;
}

/* Our first setup routine is the console.  It's a fairly simple device, but
 * UNIX tty handling makes it uglier than it could be. */
static void setup_console(struct device_list *devices)
{
	struct device *dev;

	/* If we can save the initial standard input settings... */
	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
		struct termios term = orig_term;
		/* Then we turn off echo, line buffering and ^C etc.  We want a
		 * raw input stream to the Guest. */
		term.c_lflag &= ~(ISIG|ICANON|ECHO);
		tcsetattr(STDIN_FILENO, TCSANOW, &term);
		/* If we exit gracefully, the original settings will be
		 * restored so the user can see what they're typing. */
		atexit(restore_term);
	}

	/* We don't currently require any memory for the console, so we ask for
	 * 0 pages. */
	dev = new_device(devices, LGUEST_DEVICE_T_CONSOLE, 0, 0,
			 STDIN_FILENO, handle_console_input,
			 LGUEST_CONSOLE_DMA_KEY, handle_console_output);
	/* We store the console state in dev->priv, and initialize it. */
	dev->priv = malloc(sizeof(struct console_abort));
	((struct console_abort *)dev->priv)->count = 0;
	verbose("device %p: console\n",
		(void *)(dev->desc->pfn * getpagesize()));
}

/* Setting up a block file is also fairly straightforward. */
static void setup_block_file(const char *filename, struct device_list *devices)
{
	int fd;
	struct device *dev;
	off64_t *device_len;
	struct lguest_block_page *p;

	/* We open with O_LARGEFILE because otherwise we get stuck at 2G.  We
	 * open with O_DIRECT because otherwise our benchmarks go much too
	 * fast. */
	fd = open_or_die(filename, O_RDWR|O_LARGEFILE|O_DIRECT);

	/* We want one page, and have no input handler (the block file never
	 * has anything interesting to say to us).  Our timing will be quite
	 * random, so it should be a reasonable randomness source. */
	dev = new_device(devices, LGUEST_DEVICE_T_BLOCK, 1,
			 LGUEST_DEVICE_F_RANDOMNESS,
			 fd, NULL, 0, handle_block_output);

	/* We store the device size in the private area */
	device_len = dev->priv = malloc(sizeof(*device_len));
	/* This is the safe way of establishing the size of our device: it
	 * might be a normal file or an actual block device like /dev/hdb. */
	*device_len = lseek64(fd, 0, SEEK_END);

	/* The device memory is a "struct lguest_block_page".  It's zeroed
	 * already, we just need to put in the device size.  Block devices
	 * think in sectors (ie. 512 byte chunks), so we translate here. */
	p = dev->mem;
	p->num_sectors = *device_len/512;
	verbose("device %p: block %i sectors\n",
		(void *)(dev->desc->pfn * getpagesize()), p->num_sectors);
}

/*
 * Network Devices.
 *
 * Setting up network devices is quite a pain, because we have three types.
 * First, we have the inter-Guest network.  This is a file which is mapped into
 * the address space of the Guests who are on the network.  Because it is a
 * shared mapping, the same page underlies all the devices, and they can send
 * DMA to each other.
 *
 * Remember from our network driver, the Guest is told what slot in the page it
 * is to use.  We use exclusive fnctl locks to reserve a slot.  If another
 * Guest is using a slot, the lock will fail and we try another.  Because fnctl
 * locks are cleaned up automatically when we die, this cleverly means that our
 * reservation on the slot will vanish if we crash. */
static unsigned int find_slot(int netfd, const char *filename)
{
	struct flock fl;

	fl.l_type = F_WRLCK;
	fl.l_whence = SEEK_SET;
	fl.l_len = 1;
	/* Try a 1 byte lock in each possible position number */
	for (fl.l_start = 0;
	     fl.l_start < getpagesize()/sizeof(struct lguest_net);
	     fl.l_start++) {
		/* If we succeed, return the slot number. */
		if (fcntl(netfd, F_SETLK, &fl) == 0)
			return fl.l_start;
	}
	errx(1, "No free slots in network file %s", filename);
}

/* This function sets up the network file */
static void setup_net_file(const char *filename,
			   struct device_list *devices)
{
	int netfd;
	struct device *dev;

	/* We don't use open_or_die() here: for friendliness we create the file
	 * if it doesn't already exist. */
	netfd = open(filename, O_RDWR, 0);
	if (netfd < 0) {
		if (errno == ENOENT) {
			netfd = open(filename, O_RDWR|O_CREAT, 0600);
			if (netfd >= 0) {
				/* If we succeeded, initialize the file with a
				 * blank page. */
				char page[getpagesize()];
				memset(page, 0, sizeof(page));
				write(netfd, page, sizeof(page));
			}
		}
		if (netfd < 0)
			err(1, "cannot open net file '%s'", filename);
	}

	/* We need 1 page, and the features indicate the slot to use and that
	 * no checksum is needed.  We never touch this device again; it's
	 * between the Guests on the network, so we don't register input or
	 * output handlers. */
	dev = new_device(devices, LGUEST_DEVICE_T_NET, 1,
			 find_slot(netfd, filename)|LGUEST_NET_F_NOCSUM,
			 -1, NULL, 0, NULL);

	/* Map the shared file. */
	if (mmap(dev->mem, getpagesize(), PROT_READ|PROT_WRITE,
			 MAP_FIXED|MAP_SHARED, netfd, 0) != dev->mem)
			err(1, "could not mmap '%s'", filename);
	verbose("device %p: shared net %s, peer %i\n",
		(void *)(dev->desc->pfn * getpagesize()), filename,
		dev->desc->features & ~LGUEST_NET_F_NOCSUM);
}
/*:*/

static u32 str2ip(const char *ipaddr)
{
	unsigned int byte[4];

	sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
	return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
}

/* This code is "adapted" from libbridge: it attaches the Host end of the
 * network device to the bridge device specified by the command line.
 *
 * This is yet another James Morris contribution (I'm an IP-level guy, so I
 * dislike bridging), and I just try not to break it. */
static void add_to_bridge(int fd, const char *if_name, const char *br_name)
{
	int ifidx;
	struct ifreq ifr;

	if (!*br_name)
		errx(1, "must specify bridge name");

	ifidx = if_nametoindex(if_name);
	if (!ifidx)
		errx(1, "interface %s does not exist!", if_name);

	strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
	ifr.ifr_ifindex = ifidx;
	if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
		err(1, "can't add %s to bridge %s", if_name, br_name);
}

/* This sets up the Host end of the network device with an IP address, brings
 * it up so packets will flow, the copies the MAC address into the hwaddr
 * pointer (in practice, the Host's slot in the network device's memory). */
static void configure_device(int fd, const char *devname, u32 ipaddr,
			     unsigned char hwaddr[6])
{
	struct ifreq ifr;
	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;

	/* Don't read these incantations.  Just cut & paste them like I did! */
	memset(&ifr, 0, sizeof(ifr));
	strcpy(ifr.ifr_name, devname);
	sin->sin_family = AF_INET;
	sin->sin_addr.s_addr = htonl(ipaddr);
	if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
		err(1, "Setting %s interface address", devname);
	ifr.ifr_flags = IFF_UP;
	if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
		err(1, "Bringing interface %s up", devname);

	/* SIOC stands for Socket I/O Control.  G means Get (vs S for Set
	 * above).  IF means Interface, and HWADDR is hardware address.
	 * Simple! */
	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
		err(1, "getting hw address for %s", devname);
	memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
}

/*L:195 The other kind of network is a Host<->Guest network.  This can either
 * use briding or routing, but the principle is the same: it uses the "tun"
 * device to inject packets into the Host as if they came in from a normal
 * network card.  We just shunt packets between the Guest and the tun
 * device. */
static void setup_tun_net(const char *arg, struct device_list *devices)
{
	struct device *dev;
	struct ifreq ifr;
	int netfd, ipfd;
	u32 ip;
	const char *br_name = NULL;

	/* We open the /dev/net/tun device and tell it we want a tap device.  A
	 * tap device is like a tun device, only somehow different.  To tell
	 * the truth, I completely blundered my way through this code, but it
	 * works now! */
	netfd = open_or_die("/dev/net/tun", O_RDWR);
	memset(&ifr, 0, sizeof(ifr));
	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
	strcpy(ifr.ifr_name, "tap%d");
	if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
		err(1, "configuring /dev/net/tun");
	/* We don't need checksums calculated for packets coming in this
	 * device: trust us! */
	ioctl(netfd, TUNSETNOCSUM, 1);

	/* We create the net device with 1 page, using the features field of
	 * the descriptor to tell the Guest it is in slot 1 (NET_PEERNUM), and
	 * that the device has fairly random timing.  We do *not* specify
	 * LGUEST_NET_F_NOCSUM: these packets can reach the real world.
	 *
	 * We will put our MAC address is slot 0 for the Guest to see, so
	 * it will send packets to us using the key "peer_offset(0)": */
	dev = new_device(devices, LGUEST_DEVICE_T_NET, 1,
			 NET_PEERNUM|LGUEST_DEVICE_F_RANDOMNESS, netfd,
			 handle_tun_input, peer_offset(0), handle_tun_output);

	/* We keep a flag which says whether we've seen packets come out from
	 * this network device. */
	dev->priv = malloc(sizeof(bool));
	*(bool *)dev->priv = false;

	/* We need a socket to perform the magic network ioctls to bring up the
	 * tap interface, connect to the bridge etc.  Any socket will do! */
	ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
	if (ipfd < 0)
		err(1, "opening IP socket");

	/* If the command line was --tunnet=bridge:<name> do bridging. */
	if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
		ip = INADDR_ANY;
		br_name = arg + strlen(BRIDGE_PFX);
		add_to_bridge(ipfd, ifr.ifr_name, br_name);
	} else /* It is an IP address to set up the device with */
		ip = str2ip(arg);

	/* We are peer 0, ie. first slot, so we hand dev->mem to this routine
	 * to write the MAC address at the start of the device memory.  */
	configure_device(ipfd, ifr.ifr_name, ip, dev->mem);

	/* Set "promisc" bit: we want every single packet if we're going to
	 * bridge to other machines (and otherwise it doesn't matter). */
	*((u8 *)dev->mem) |= 0x1;

	close(ipfd);

	verbose("device %p: tun net %u.%u.%u.%u\n",
		(void *)(dev->desc->pfn * getpagesize()),
		(u8)(ip>>24), (u8)(ip>>16), (u8)(ip>>8), (u8)ip);
	if (br_name)
		verbose("attached to bridge: %s\n", br_name);
}
/* That's the end of device setup. */

/*L:220 Finally we reach the core of the Launcher, which runs the Guest, serves
 * its input and output, and finally, lays it to rest. */
static void __attribute__((noreturn))
run_guest(int lguest_fd, struct device_list *device_list)
{
	for (;;) {
		unsigned long args[] = { LHREQ_BREAK, 0 };
		unsigned long arr[2];
		int readval;

		/* We read from the /dev/lguest device to run the Guest. */
		readval = read(lguest_fd, arr, sizeof(arr));

		/* The read can only really return sizeof(arr) (the Guest did a
		 * SEND_DMA to us), or an error. */

		/* For a successful read, arr[0] is the address of the "struct
		 * lguest_dma", and arr[1] is the key the Guest sent to. */
		if (readval == sizeof(arr)) {
			handle_output(lguest_fd, arr[0], arr[1], device_list);
			continue;
		/* ENOENT means the Guest died.  Reading tells us why. */
		} else if (errno == ENOENT) {
			char reason[1024] = { 0 };
			read(lguest_fd, reason, sizeof(reason)-1);
			errx(1, "%s", reason);
		/* EAGAIN means the waker wanted us to look at some input.
		 * Anything else means a bug or incompatible change. */
		} else if (errno != EAGAIN)
			err(1, "Running guest failed");

		/* Service input, then unset the BREAK which releases
		 * the Waker. */
		handle_input(lguest_fd, device_list);
		if (write(lguest_fd, args, sizeof(args)) < 0)
			err(1, "Resetting break");
	}
}
/*
 * This is the end of the Launcher.
 *
 * But wait!  We've seen I/O from the Launcher, and we've seen I/O from the
 * Drivers.  If we were to see the Host kernel I/O code, our understanding
 * would be complete... :*/

static struct option opts[] = {
	{ "verbose", 0, NULL, 'v' },
	{ "sharenet", 1, NULL, 's' },
	{ "tunnet", 1, NULL, 't' },
	{ "block", 1, NULL, 'b' },
	{ "initrd", 1, NULL, 'i' },
	{ NULL },
};
static void usage(void)
{
	errx(1, "Usage: lguest [--verbose] "
	     "[--sharenet=<filename>|--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
	     "|--block=<filename>|--initrd=<filename>]...\n"
	     "<mem-in-mb> vmlinux [args...]");
}

/*L:105 The main routine is where the real work begins: */
int main(int argc, char *argv[])
{
	/* Memory, top-level pagetable, code startpoint and size of the
	 * (optional) initrd. */
	unsigned long mem = 0, pgdir, start, initrd_size = 0;
	/* A temporary and the /dev/lguest file descriptor. */
	int i, c, lguest_fd;
	/* The list of Guest devices, based on command line arguments. */
	struct device_list device_list;
	/* The boot information for the Guest. */
	void *boot;
	/* If they specify an initrd file to load. */
	const char *initrd_name = NULL;

	/* First we initialize the device list.  Since console and network
	 * device receive input from a file descriptor, we keep an fdset
	 * (infds) and the maximum fd number (max_infd) with the head of the
	 * list.  We also keep a pointer to the last device, for easy appending
	 * to the list. */
	device_list.max_infd = -1;
	device_list.dev = NULL;
	device_list.lastdev = &device_list.dev;
	FD_ZERO(&device_list.infds);

	/* We need to know how much memory so we can set up the device
	 * descriptor and memory pages for the devices as we parse the command
	 * line.  So we quickly look through the arguments to find the amount
	 * of memory now. */
	for (i = 1; i < argc; i++) {
		if (argv[i][0] != '-') {
			mem = atoi(argv[i]) * 1024 * 1024;
			/* We start by mapping anonymous pages over all of
			 * guest-physical memory range.  This fills it with 0,
			 * and ensures that the Guest won't be killed when it
			 * tries to access it. */
			guest_base = map_zeroed_pages(mem / getpagesize()
						      + DEVICE_PAGES);
			guest_limit = mem;
			guest_max = mem + DEVICE_PAGES*getpagesize();
			device_list.descs = get_pages(1);
			break;
		}
	}

	/* The options are fairly straight-forward */
	while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) {
		switch (c) {
		case 'v':
			verbose = true;
			break;
		case 's':
			setup_net_file(optarg, &device_list);
			break;
		case 't':
			setup_tun_net(optarg, &device_list);
			break;
		case 'b':
			setup_block_file(optarg, &device_list);
			break;
		case 'i':
			initrd_name = optarg;
			break;
		default:
			warnx("Unknown argument %s", argv[optind]);
			usage();
		}
	}
	/* After the other arguments we expect memory and kernel image name,
	 * followed by command line arguments for the kernel. */
	if (optind + 2 > argc)
		usage();

	verbose("Guest base is at %p\n", guest_base);

	/* We always have a console device */
	setup_console(&device_list);

	/* Now we load the kernel */
	start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));

	/* Boot information is stashed at physical address 0 */
	boot = from_guest_phys(0);

	/* Map the initrd image if requested (at top of physical memory) */
	if (initrd_name) {
		initrd_size = load_initrd(initrd_name, mem);
		/* These are the location in the Linux boot header where the
		 * start and size of the initrd are expected to be found. */
		*(unsigned long *)(boot+0x218) = mem - initrd_size;
		*(unsigned long *)(boot+0x21c) = initrd_size;
		/* The bootloader type 0xFF means "unknown"; that's OK. */
		*(unsigned char *)(boot+0x210) = 0xFF;
	}

	/* Set up the initial linear pagetables, starting below the initrd. */
	pgdir = setup_pagetables(mem, initrd_size);

	/* The Linux boot header contains an "E820" memory map: ours is a
	 * simple, single region. */
	*(char*)(boot+E820NR) = 1;
	*((struct e820entry *)(boot+E820MAP))
		= ((struct e820entry) { 0, mem, E820_RAM });
	/* The boot header contains a command line pointer: we put the command
	 * line after the boot header (at address 4096) */
	*(u32 *)(boot + 0x228) = 4096;
	concat(boot + 4096, argv+optind+2);

	/* The guest type value of "1" tells the Guest it's under lguest. */
	*(int *)(boot + 0x23c) = 1;

	/* We tell the kernel to initialize the Guest: this returns the open
	 * /dev/lguest file descriptor. */
	lguest_fd = tell_kernel(pgdir, start);

	/* We fork off a child process, which wakes the Launcher whenever one
	 * of the input file descriptors needs attention.  Otherwise we would
	 * run the Guest until it tries to output something. */
	waker_fd = setup_waker(lguest_fd, &device_list);

	/* Finally, run the Guest.  This doesn't return. */
	run_guest(lguest_fd, &device_list);
}
/*:*/

/*M:999
 * Mastery is done: you now know everything I do.
 *
 * But surely you have seen code, features and bugs in your wanderings which
 * you now yearn to attack?  That is the real game, and I look forward to you
 * patching and forking lguest into the Your-Name-Here-visor.
 *
 * Farewell, and good coding!
 * Rusty Russell.
 */