summaryrefslogtreecommitdiff
path: root/Documentation/lguest/lguest.c
blob: f2668390e8f773276357917e79625790d4e98b5a (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
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
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
/*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>
#include <assert.h>
#include <sched.h>
#include "linux/lguest_launcher.h"
#include "linux/virtio_config.h"
#include "linux/virtio_net.h"
#include "linux/virtio_blk.h"
#include "linux/virtio_console.h"
#include "linux/virtio_ring.h"
#include "asm-x86/bootparam.h"
/*L:110 We can ignore the 38 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, so we define them here.  Note that u64 is always
 * unsigned long long, which works on all Linux systems: this means that we can
 * use %llu in printf for any u64. */
typedef unsigned long long u64;
typedef uint32_t u32;
typedef uint16_t u16;
typedef uint8_t u8;
/*:*/

#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
/* This fits nicely in a single 4096-byte page. */
#define VIRTQUEUE_NUM 127

/*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;

	/* Counter to assign interrupt numbers. */
	unsigned int next_irq;

	/* Counter to print out convenient device numbers. */
	unsigned int device_num;

	/* The descriptor page for the devices. */
	u8 *descpage;

	/* The tail of the last descriptor. */
	unsigned int desc_used;

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

/* The list of Guest devices, based on command line arguments. */
static struct device_list devices;

/* The device structure describes a single device. */
struct device
{
	/* The linked-list pointer. */
	struct device *next;

	/* The this device's descriptor, as mapped into the Guest. */
	struct lguest_device_desc *desc;

	/* The name of this device, for --verbose. */
	const char *name;

	/* 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);

	/* Any queues attached to this device */
	struct virtqueue *vq;

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

/* The virtqueue structure describes a queue attached to a device. */
struct virtqueue
{
	struct virtqueue *next;

	/* Which device owns me. */
	struct device *dev;

	/* The configuration for this queue. */
	struct lguest_vqconfig config;

	/* The actual ring of buffers. */
	struct vring vring;

	/* Last available index we saw. */
	u16 last_avail_idx;

	/* The routine to call when the Guest pings us. */
	void (*handle_output)(int fd, struct virtqueue *me);
};

/* Since guest is UP and we don't run at the same time, we don't need barriers.
 * But I include them in the code in case others copy it. */
#define wmb()

/* Convert an iovec element to the given type.
 *
 * This is a fairly ugly trick: we need to know the size of the type and
 * alignment requirement to check the pointer is kosher.  It's also nice to
 * have the name of the type in case we report failure.
 *
 * Typing those three things all the time is cumbersome and error prone, so we
 * have a macro which sets them all up and passes to the real function. */
#define convert(iov, type) \
	((type *)_convert((iov), sizeof(type), __alignof__(type), #type))

static void *_convert(struct iovec *iov, size_t size, size_t align,
		      const char *name)
{
	if (iov->iov_len != size)
		errx(1, "Bad iovec size %zu for %s", iov->iov_len, name);
	if ((unsigned long)iov->iov_base % align != 0)
		errx(1, "Bad alignment %p for %s", iov->iov_base, name);
	return iov->iov_base;
}

/* The virtio configuration space is defined to be little-endian.  x86 is
 * little-endian too, but it's nice to be explicit so we have these helpers. */
#define cpu_to_le16(v16) (v16)
#define cpu_to_le32(v32) (v32)
#define cpu_to_le64(v64) (v64)
#define le16_to_cpu(v16) (v16)
#define le32_to_cpu(v32) (v32)
#define le64_to_cpu(v32) (v64)

/*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;
}

/* 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)
{
	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 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);
	}

	/* The entry point is given in the ELF header. */
	return ehdr->e_entry;
}

/*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 used to have to
 * perform some hairy magic because the unpacking code scared me.
 *
 * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote
 * a small patch to jump over the tricky bits in the Guest, so now we just read
 * the funky header so we know where in the file to load, and away we go! */
static unsigned long load_bzimage(int fd)
{
	struct boot_params boot;
	int r;
	/* Modern bzImages get loaded at 1M. */
	void *p = from_guest_phys(0x100000);

	/* Go back to the start of the file and read the header.  It should be
	 * a Linux boot header (see Documentation/i386/boot.txt) */
	lseek(fd, 0, SEEK_SET);
	read(fd, &boot, sizeof(boot));

	/* Inside the setup_hdr, we expect the magic "HdrS" */
	if (memcmp(&boot.hdr.header, "HdrS", 4) != 0)
		errx(1, "This doesn't look like a bzImage to me");

	/* Skip over the extra sectors of the header. */
	lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET);

	/* Now read everything into memory. in nice big chunks. */
	while ((r = read(fd, p, 65536)) > 0)
		p += r;

	/* Finally, code32_start tells us where to enter the kernel. */
	return boot.hdr.code32_start;
}

/*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 a little
 * work, 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';
}

/*L:185 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 add_device_fd(int fd)
{
	FD_SET(fd, &devices.infds);
	if (fd > devices.max_infd)
		devices.max_infd = fd;
}

/*L:200
 * The Waker.
 *
 * With console, block 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 file descriptor to tell the Host
 * stop running the Guest.  This causes the Launcher 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)
{
	/* Add the pipe from the Launcher to the fdset in the device_list, so
	 * we watch it, too. */
	add_device_fd(pipefd);

	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 fd;
			/* If read() returns 0, it means the Launcher has
			 * exited.  We silently follow. */
			if (read(pipefd, &fd, sizeof(fd)) == 0)
				exit(0);
			/* Otherwise it's telling us to change what file
			 * descriptors we're to listen to.  Positive means
			 * listen to a new one, negative means stop
			 * listening. */
			if (fd >= 0)
				FD_SET(fd, &devices.infds);
			else
				FD_CLR(-fd - 1, &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)
{
	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) {
		/* We are the Waker: close the "writing" end of our copy of the
		 * pipe and start waiting for input. */
		close(pipefd[1]);
		wake_parent(pipefd[0], lguest_fd);
	}
	/* 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];
}

/*
 * Device Handling.
 *
 * When the Guest gives us a buffer, it sends 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 checks 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 %#lx", __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__)

/* Each buffer in the virtqueues is actually a chain of descriptors.  This
 * function returns the next descriptor in the chain, or vq->vring.num if we're
 * at the end. */
static unsigned next_desc(struct virtqueue *vq, unsigned int i)
{
	unsigned int next;

	/* If this descriptor says it doesn't chain, we're done. */
	if (!(vq->vring.desc[i].flags & VRING_DESC_F_NEXT))
		return vq->vring.num;

	/* Check they're not leading us off end of descriptors. */
	next = vq->vring.desc[i].next;
	/* Make sure compiler knows to grab that: we don't want it changing! */
	wmb();

	if (next >= vq->vring.num)
		errx(1, "Desc next is %u", next);

	return next;
}

/* This looks in the virtqueue and for the first available buffer, and converts
 * it to an iovec for convenient access.  Since descriptors consist of some
 * number of output then some number of input descriptors, it's actually two
 * iovecs, but we pack them into one and note how many of each there were.
 *
 * This function returns the descriptor number found, or vq->vring.num (which
 * is never a valid descriptor number) if none was found. */
static unsigned get_vq_desc(struct virtqueue *vq,
			    struct iovec iov[],
			    unsigned int *out_num, unsigned int *in_num)
{
	unsigned int i, head;

	/* Check it isn't doing very strange things with descriptor numbers. */
	if ((u16)(vq->vring.avail->idx - vq->last_avail_idx) > vq->vring.num)
		errx(1, "Guest moved used index from %u to %u",
		     vq->last_avail_idx, vq->vring.avail->idx);

	/* If there's nothing new since last we looked, return invalid. */
	if (vq->vring.avail->idx == vq->last_avail_idx)
		return vq->vring.num;

	/* Grab the next descriptor number they're advertising, and increment
	 * the index we've seen. */
	head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num];

	/* If their number is silly, that's a fatal mistake. */
	if (head >= vq->vring.num)
		errx(1, "Guest says index %u is available", head);

	/* When we start there are none of either input nor output. */
	*out_num = *in_num = 0;

	i = head;
	do {
		/* Grab the first descriptor, and check it's OK. */
		iov[*out_num + *in_num].iov_len = vq->vring.desc[i].len;
		iov[*out_num + *in_num].iov_base
			= check_pointer(vq->vring.desc[i].addr,
					vq->vring.desc[i].len);
		/* If this is an input descriptor, increment that count. */
		if (vq->vring.desc[i].flags & VRING_DESC_F_WRITE)
			(*in_num)++;
		else {
			/* If it's an output descriptor, they're all supposed
			 * to come before any input descriptors. */
			if (*in_num)
				errx(1, "Descriptor has out after in");
			(*out_num)++;
		}

		/* If we've got too many, that implies a descriptor loop. */
		if (*out_num + *in_num > vq->vring.num)
			errx(1, "Looped descriptor");
	} while ((i = next_desc(vq, i)) != vq->vring.num);

	return head;
}

/* After we've used one of their buffers, we tell them about it.  We'll then
 * want to send them an interrupt, using trigger_irq(). */
static void add_used(struct virtqueue *vq, unsigned int head, int len)
{
	struct vring_used_elem *used;

	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
	 * next entry in that used ring. */
	used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num];
	used->id = head;
	used->len = len;
	/* Make sure buffer is written before we update index. */
	wmb();
	vq->vring.used->idx++;
}

/* This actually sends the interrupt for this virtqueue */
static void trigger_irq(int fd, struct virtqueue *vq)
{
	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };

	/* If they don't want an interrupt, don't send one. */
	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
		return;

	/* Send the Guest an interrupt tell them we used something up. */
	if (write(fd, buf, sizeof(buf)) != 0)
		err(1, "Triggering irq %i", vq->config.irq);
}

/* And here's the combo meal deal.  Supersize me! */
static void add_used_and_trigger(int fd, struct virtqueue *vq,
				 unsigned int head, int len)
{
	add_used(vq, head, len);
	trigger_irq(fd, vq);
}

/*
 * The Console
 *
 * Here is the input terminal setting we save, and the routine to restore them
 * on exit so the user gets their terminal back. */
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)
{
	int len;
	unsigned int head, in_num, out_num;
	struct iovec iov[dev->vq->vring.num];
	struct console_abort *abort = dev->priv;

	/* First we need a console buffer from the Guests's input virtqueue. */
	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);

	/* If they're not ready for input, stop listening to this file
	 * descriptor.  We'll start again once they add an input buffer. */
	if (head == dev->vq->vring.num)
		return false;

	if (out_num)
		errx(1, "Output buffers in console in queue?");

	/* 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, in_num);
	if (len <= 0) {
		/* This implies that the console is closed, is /dev/null, or
		 * something went terribly wrong. */
		warnx("Failed to get console input, ignoring console.");
		/* Put the input terminal back. */
		restore_term();
		/* Remove callback from input vq, so it doesn't restart us. */
		dev->vq->handle_output = NULL;
		/* Stop listening to this fd: don't call us again. */
		return false;
	}

	/* Tell the Guest about the new input. */
	add_used_and_trigger(fd, dev->vq, head, len);

	/* 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;

	/* Everything went OK! */
	return true;
}

/* Handling output for console is simple: we just get all the output buffers
 * and write them to stdout. */
static void handle_console_output(int fd, struct virtqueue *vq)
{
	unsigned int head, out, in;
	int len;
	struct iovec iov[vq->vring.num];

	/* Keep getting output buffers from the Guest until we run out. */
	while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
		if (in)
			errx(1, "Input buffers in output queue?");
		len = writev(STDOUT_FILENO, iov, out);
		add_used_and_trigger(fd, vq, head, len);
	}
}

/*
 * The Network
 *
 * Handling output for network is also simple: we get all the output buffers
 * and write them (ignoring the first element) to this device's file descriptor
 * (stdout). */
static void handle_net_output(int fd, struct virtqueue *vq)
{
	unsigned int head, out, in;
	int len;
	struct iovec iov[vq->vring.num];

	/* Keep getting output buffers from the Guest until we run out. */
	while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
		if (in)
			errx(1, "Input buffers in output queue?");
		/* Check header, but otherwise ignore it (we told the Guest we
		 * supported no features, so it shouldn't have anything
		 * interesting). */
		(void)convert(&iov[0], struct virtio_net_hdr);
		len = writev(vq->dev->fd, iov+1, out-1);
		add_used_and_trigger(fd, vq, head, len);
	}
}

/* This is where we handle a packet coming in from the tun device to our
 * Guest. */
static bool handle_tun_input(int fd, struct device *dev)
{
	unsigned int head, in_num, out_num;
	int len;
	struct iovec iov[dev->vq->vring.num];
	struct virtio_net_hdr *hdr;

	/* First we need a network buffer from the Guests's recv virtqueue. */
	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
	if (head == dev->vq->vring.num) {
		/* Now, it's expected that if we try to send a packet too
		 * early, the Guest won't be ready yet.  Wait until the device
		 * status says it's ready. */
		/* FIXME: Actually want DRIVER_ACTIVE here. */
		if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
			warn("network: no dma buffer!");
		/* We'll turn this back on if input buffers are registered. */
		return false;
	} else if (out_num)
		errx(1, "Output buffers in network recv queue?");

	/* First element is the header: we set it to 0 (no features). */
	hdr = convert(&iov[0], struct virtio_net_hdr);
	hdr->flags = 0;
	hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;

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

	/* Tell the Guest about the new packet. */
	add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);

	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
		((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
		head != dev->vq->vring.num ? "sent" : "discarded");

	/* All good. */
	return true;
}

/*L:215 This is the callback attached to the network and console input
 * virtqueues: it ensures we try again, in case we stopped console or net
 * delivery because Guest didn't have any buffers. */
static void enable_fd(int fd, struct virtqueue *vq)
{
	add_device_fd(vq->dev->fd);
	/* Tell waker to listen to it again */
	write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
}

/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
static void handle_output(int fd, unsigned long addr)
{
	struct device *i;
	struct virtqueue *vq;

	/* Check each virtqueue. */
	for (i = devices.dev; i; i = i->next) {
		for (vq = i->vq; vq; vq = vq->next) {
			if (vq->config.pfn == addr/getpagesize()
			    && vq->handle_output) {
				verbose("Output to %s\n", vq->dev->name);
				vq->handle_output(fd, vq);
				return;
			}
		}
	}

	/* Early console write is done using notify on a nul-terminated string
	 * in Guest memory. */
	if (addr >= guest_limit)
		errx(1, "Bad NOTIFY %#lx", addr);

	write(STDOUT_FILENO, from_guest_phys(addr),
	      strnlen(from_guest_phys(addr), guest_limit - addr));
}

/* This is called when the Waker wakes us up: check for incoming file
 * descriptors. */
static void handle_input(int fd)
{
	/* 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)) {
				int dev_fd;
				if (i->handle_input(fd, i))
					continue;

				/* If handle_input() returns false, it means we
				 * should no longer service it.  Networking and
				 * console do this when there's no input
				 * buffers to deliver into.  Console also uses
				 * it when it discovers that stdin is
				 * closed. */
				FD_CLR(i->fd, &devices.infds);
				/* Tell waker to ignore it too, by sending a
				 * negative fd number (-1, since 0 is a valid
				 * FD number). */
				dev_fd = -i->fd - 1;
				write(waker_fd, &dev_fd, sizeof(dev_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 just above the Guest's normal memory.  It returns a pointer to that
 * descriptor. */
static struct lguest_device_desc *new_dev_desc(u16 type)
{
	struct lguest_device_desc *d;

	/* We only have one page for all the descriptors. */
	if (devices.desc_used + sizeof(*d) > getpagesize())
		errx(1, "Too many devices");

	/* We don't need to set config_len or status: page is 0 already. */
	d = (void *)devices.descpage + devices.desc_used;
	d->type = type;
	devices.desc_used += sizeof(*d);

	return d;
}

/* Each device descriptor is followed by some configuration information.
 * Each configuration field looks like: u8 type, u8 len, [... len bytes...].
 *
 * This routine adds a new field to an existing device's descriptor.  It only
 * works for the last device, but that's OK because that's how we use it. */
static void add_desc_field(struct device *dev, u8 type, u8 len, const void *c)
{
	/* This is the last descriptor, right? */
	assert(devices.descpage + devices.desc_used
	       == (u8 *)(dev->desc + 1) + dev->desc->config_len);

	/* We only have one page of device descriptions. */
	if (devices.desc_used + 2 + len > getpagesize())
		errx(1, "Too many devices");

	/* Copy in the new config header: type then length. */
	devices.descpage[devices.desc_used++] = type;
	devices.descpage[devices.desc_used++] = len;
	memcpy(devices.descpage + devices.desc_used, c, len);
	devices.desc_used += len;

	/* Update the device descriptor length: two byte head then data. */
	dev->desc->config_len += 2 + len;
}

/* This routine adds a virtqueue to a device.  We specify how many descriptors
 * the virtqueue is to have. */
static void add_virtqueue(struct device *dev, unsigned int num_descs,
			  void (*handle_output)(int fd, struct virtqueue *me))
{
	unsigned int pages;
	struct virtqueue **i, *vq = malloc(sizeof(*vq));
	void *p;

	/* First we need some pages for this virtqueue. */
	pages = (vring_size(num_descs) + getpagesize() - 1) / getpagesize();
	p = get_pages(pages);

	/* Initialize the configuration. */
	vq->config.num = num_descs;
	vq->config.irq = devices.next_irq++;
	vq->config.pfn = to_guest_phys(p) / getpagesize();

	/* Initialize the vring. */
	vring_init(&vq->vring, num_descs, p);

	/* Add the configuration information to this device's descriptor. */
	add_desc_field(dev, VIRTIO_CONFIG_F_VIRTQUEUE,
		       sizeof(vq->config), &vq->config);

	/* Add to tail of list, so dev->vq is first vq, dev->vq->next is
	 * second.  */
	for (i = &dev->vq; *i; i = &(*i)->next);
	*i = vq;

	/* Link virtqueue back to device. */
	vq->dev = dev;

	/* Set the routine to call when the Guest does something to this
	 * virtqueue. */
	vq->handle_output = handle_output;

	/* Set the "Don't Notify Me" flag if we don't have a handler */
	if (!handle_output)
		vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
}

/* This routine does all the creation and setup of a new device, including
 * calling new_dev_desc() to allocate the descriptor and device memory. */
static struct device *new_device(const char *name, u16 type, int fd,
				 bool (*handle_input)(int, 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/vda, 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)
		add_device_fd(dev->fd);
	dev->desc = new_dev_desc(type);
	dev->handle_input = handle_input;
	dev->name = name;
	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(void)
{
	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);
	}

	dev = new_device("console", VIRTIO_ID_CONSOLE,
			 STDIN_FILENO, handle_console_input);
	/* 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;

	/* The console needs two virtqueues: the input then the output.  When
	 * they put something the input queue, we make sure we're listening to
	 * stdin.  When they put something in the output queue, we write it to
	 * stdout. */
	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
	add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);

	verbose("device %u: console\n", devices.device_num++);
}
/*:*/

/*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
 * --sharenet=<name> option which opens or creates a named pipe.  This can be
 * used to send packets to another guest in a 1:1 manner.
 *
 * More sopisticated is to use one of the tools developed for project like UML
 * to do networking.
 *
 * Faster is to do virtio bonding in kernel.  Doing this 1:1 would be
 * completely generic ("here's my vring, attach to your vring") and would work
 * for any traffic.  Of course, namespace and permissions issues need to be
 * dealt with.  A more sophisticated "multi-channel" virtio_net.c could hide
 * multiple inter-guest channels behind one interface, although it would
 * require some manner of hotplugging new virtio channels.
 *
 * Finally, we could implement a virtio network switch in the kernel. :*/

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. */
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 Our network is a Host<->Guest network.  This can either use bridging 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 *dev;
	struct ifreq ifr;
	int netfd, ipfd;
	u32 ip;
	const char *br_name = NULL;
	u8 hwaddr[6];

	/* 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);

	/* First we create a new network device. */
	dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);

	/* Network devices need a receive and a send queue, just like
	 * console. */
	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
	add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);

	/* 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);

	/* Set up the tun device, and get the mac address for the interface. */
	configure_device(ipfd, ifr.ifr_name, ip, hwaddr);

	/* Tell Guest what MAC address to use. */
	add_desc_field(dev, VIRTIO_CONFIG_NET_MAC_F, sizeof(hwaddr), hwaddr);

	/* We don't seed the socket any more; setup is done. */
	close(ipfd);

	verbose("device %u: tun net %u.%u.%u.%u\n",
		devices.device_num++,
		(u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
	if (br_name)
		verbose("attached to bridge: %s\n", br_name);
}

/* Our block (disk) device should be really simple: the Guest asks for a block
 * number and we read or write that position in the file.  Unfortunately, that
 * was amazingly slow: the Guest waits until the read is finished before
 * running anything else, even if it could have been doing useful work.
 *
 * We could use async I/O, except it's reputed to suck so hard that characters
 * actually go missing from your code when you try to use it.
 *
 * So we farm the I/O out to thread, and communicate with it via a pipe. */

/* This hangs off device->priv. */
struct vblk_info
{
	/* The size of the file. */
	off64_t len;

	/* The file descriptor for the file. */
	int fd;

	/* IO thread listens on this file descriptor [0]. */
	int workpipe[2];

	/* IO thread writes to this file descriptor to mark it done, then
	 * Launcher triggers interrupt to Guest. */
	int done_fd;
};
/*:*/

/*L:210
 * The Disk
 *
 * Remember that the block device is handled by a separate I/O thread.  We head
 * straight into the core of that thread here:
 */
static bool service_io(struct device *dev)
{
	struct vblk_info *vblk = dev->priv;
	unsigned int head, out_num, in_num, wlen;
	int ret;
	struct virtio_blk_inhdr *in;
	struct virtio_blk_outhdr *out;
	struct iovec iov[dev->vq->vring.num];
	off64_t off;

	/* See if there's a request waiting.  If not, nothing to do. */
	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
	if (head == dev->vq->vring.num)
		return false;

	/* Every block request should contain at least one output buffer
	 * (detailing the location on disk and the type of request) and one
	 * input buffer (to hold the result). */
	if (out_num == 0 || in_num == 0)
		errx(1, "Bad virtblk cmd %u out=%u in=%u",
		     head, out_num, in_num);

	out = convert(&iov[0], struct virtio_blk_outhdr);
	in = convert(&iov[out_num+in_num-1], struct virtio_blk_inhdr);
	off = out->sector * 512;

	/* The block device implements "barriers", where the Guest indicates
	 * that it wants all previous writes to occur before this write.  We
	 * don't have a way of asking our kernel to do a barrier, so we just
	 * synchronize all the data in the file.  Pretty poor, no? */
	if (out->type & VIRTIO_BLK_T_BARRIER)
		fdatasync(vblk->fd);

	/* In general the virtio block driver is allowed to try SCSI commands.
	 * It'd be nice if we supported eject, for example, but we don't. */
	if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
		fprintf(stderr, "Scsi commands unsupported\n");
		in->status = VIRTIO_BLK_S_UNSUPP;
		wlen = sizeof(in);
	} else if (out->type & VIRTIO_BLK_T_OUT) {
		/* Write */

		/* Move to the right location in the block file.  This can fail
		 * if they try to write past end. */
		if (lseek64(vblk->fd, off, SEEK_SET) != off)
			err(1, "Bad seek to sector %llu", out->sector);

		ret = writev(vblk->fd, iov+1, out_num-1);
		verbose("WRITE to sector %llu: %i\n", out->sector, ret);

		/* Grr... Now we know how long the descriptor they sent was, we
		 * make sure they didn't try to write over the end of the block
		 * file (possibly extending it). */
		if (ret > 0 && off + ret > vblk->len) {
			/* Trim it back to the correct length */
			ftruncate64(vblk->fd, vblk->len);
			/* Die, bad Guest, die. */
			errx(1, "Write past end %llu+%u", off, ret);
		}
		wlen = sizeof(in);
		in->status = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
	} else {
		/* Read */

		/* Move to the right location in the block file.  This can fail
		 * if they try to read past end. */
		if (lseek64(vblk->fd, off, SEEK_SET) != off)
			err(1, "Bad seek to sector %llu", out->sector);

		ret = readv(vblk->fd, iov+1, in_num-1);
		verbose("READ from sector %llu: %i\n", out->sector, ret);
		if (ret >= 0) {
			wlen = sizeof(in) + ret;
			in->status = VIRTIO_BLK_S_OK;
		} else {
			wlen = sizeof(in);
			in->status = VIRTIO_BLK_S_IOERR;
		}
	}

	/* We can't trigger an IRQ, because we're not the Launcher.  It does
	 * that when we tell it we're done. */
	add_used(dev->vq, head, wlen);
	return true;
}

/* This is the thread which actually services the I/O. */
static int io_thread(void *_dev)
{
	struct device *dev = _dev;
	struct vblk_info *vblk = dev->priv;
	char c;

	/* Close other side of workpipe so we get 0 read when main dies. */
	close(vblk->workpipe[1]);
	/* Close the other side of the done_fd pipe. */
	close(dev->fd);

	/* When this read fails, it means Launcher died, so we follow. */
	while (read(vblk->workpipe[0], &c, 1) == 1) {
		/* We acknowledge each request immediately to reduce latency,
		 * rather than waiting until we've done them all.  I haven't
		 * measured to see if it makes any difference. */
		while (service_io(dev))
			write(vblk->done_fd, &c, 1);
	}
	return 0;
}

/* Now we've seen the I/O thread, we return to the Launcher to see what happens
 * when the thread tells us it's completed some I/O. */
static bool handle_io_finish(int fd, struct device *dev)
{
	char c;

	/* If the I/O thread died, presumably it printed the error, so we
	 * simply exit. */
	if (read(dev->fd, &c, 1) != 1)
		exit(1);

	/* It did some work, so trigger the irq. */
	trigger_irq(fd, dev->vq);
	return true;
}

/* When the Guest submits some I/O, we just need to wake the I/O thread. */
static void handle_virtblk_output(int fd, struct virtqueue *vq)
{
	struct vblk_info *vblk = vq->dev->priv;
	char c = 0;

	/* Wake up I/O thread and tell it to go to work! */
	if (write(vblk->workpipe[1], &c, 1) != 1)
		/* Presumably it indicated why it died. */
		exit(1);
}

/*L:198 This actually sets up a virtual block device. */
static void setup_block_file(const char *filename)
{
	int p[2];
	struct device *dev;
	struct vblk_info *vblk;
	void *stack;
	u64 cap;
	unsigned int val;

	/* This is the pipe the I/O thread will use to tell us I/O is done. */
	pipe(p);

	/* The device responds to return from I/O thread. */
	dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish);

	/* The device has one virtqueue, where the Guest places requests. */
	add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output);

	/* Allocate the room for our own bookkeeping */
	vblk = dev->priv = malloc(sizeof(*vblk));

	/* First we open the file and store the length. */
	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
	vblk->len = lseek64(vblk->fd, 0, SEEK_END);

	/* Tell Guest how many sectors this device has. */
	cap = cpu_to_le64(vblk->len / 512);
	add_desc_field(dev, VIRTIO_CONFIG_BLK_F_CAPACITY, sizeof(cap), &cap);

	/* Tell Guest not to put in too many descriptors at once: two are used
	 * for the in and out elements. */
	val = cpu_to_le32(VIRTQUEUE_NUM - 2);
	add_desc_field(dev, VIRTIO_CONFIG_BLK_F_SEG_MAX, sizeof(val), &val);

	/* The I/O thread writes to this end of the pipe when done. */
	vblk->done_fd = p[1];

	/* This is the second pipe, which is how we tell the I/O thread about
	 * more work. */
	pipe(vblk->workpipe);

	/* Create stack for thread and run it */
	stack = malloc(32768);
	if (clone(io_thread, stack + 32768, CLONE_VM, dev) == -1)
		err(1, "Creating clone");

	/* We don't need to keep the I/O thread's end of the pipes open. */
	close(vblk->done_fd);
	close(vblk->workpipe[0]);

	verbose("device %u: virtblock %llu sectors\n",
		devices.device_num, cap);
}
/* 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)
{
	for (;;) {
		unsigned long args[] = { LHREQ_BREAK, 0 };
		unsigned long notify_addr;
		int readval;

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

		/* One unsigned long means the Guest did HCALL_NOTIFY */
		if (readval == sizeof(notify_addr)) {
			verbose("Notify on address %#lx\n", notify_addr);
			handle_output(lguest_fd, notify_addr);
			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 to release the Waker. */
		handle_input(lguest_fd);
		if (write(lguest_fd, args, sizeof(args)) < 0)
			err(1, "Resetting break");
	}
}
/*
 * This is the end of the Launcher.  The good news: we are over halfway
 * through!  The bad news: the most fiendish part of the code still lies ahead
 * of us.
 *
 * Are you ready?  Take a deep breath and join me in the core of the Host, in
 * "make Host".
 :*/

static struct option opts[] = {
	{ "verbose", 0, NULL, 'v' },
	{ "tunnet", 1, NULL, 't' },
	{ "block", 1, NULL, 'b' },
	{ "initrd", 1, NULL, 'i' },
	{ NULL },
};
static void usage(void)
{
	errx(1, "Usage: lguest [--verbose] "
	     "[--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;
	/* Two temporaries and the /dev/lguest file descriptor. */
	int i, c, lguest_fd;
	/* The boot information for the Guest. */
	struct boot_params *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.  Finally, we keep the next interrupt number to hand out
	 * (1: remember that 0 is used by the timer). */
	FD_ZERO(&devices.infds);
	devices.max_infd = -1;
	devices.lastdev = &devices.dev;
	devices.next_irq = 1;

	/* 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();
			devices.descpage = 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 't':
			setup_tun_net(optarg);
			break;
		case 'b':
			setup_block_file(optarg);
			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();

	/* 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. */
		boot->hdr.ramdisk_image = mem - initrd_size;
		boot->hdr.ramdisk_size = initrd_size;
		/* The bootloader type 0xFF means "unknown"; that's OK. */
		boot->hdr.type_of_loader = 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. */
	boot->e820_entries = 1;
	boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
	/* The boot header contains a command line pointer: we put the command
	 * line after the boot header. */
	boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1);
	/* We use a simple helper to copy the arguments separated by spaces. */
	concat((char *)(boot + 1), argv+optind+2);

	/* Boot protocol version: 2.07 supports the fields for lguest. */
	boot->hdr.version = 0x207;

	/* The hardware_subarch value of "1" tells the Guest it's an lguest. */
	boot->hdr.hardware_subarch = 1;

	/* Tell the entry path not to try to reload segment registers. */
	boot->hdr.loadflags |= KEEP_SEGMENTS;

	/* 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);

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

/*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.
 */