summaryrefslogtreecommitdiff
path: root/tools/lguest/lguest.c
blob: 485fe13db12e5808f9298577c0811f55f8488efa (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
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
/*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 opens /dev/lguest to tell the kernel about the Guest and
 * control it.
:*/
#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 <sys/eventfd.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 <assert.h>
#include <sched.h>
#include <limits.h>
#include <stddef.h>
#include <signal.h>
#include <pwd.h>
#include <grp.h>
#include <sys/user.h>

#ifndef VIRTIO_F_ANY_LAYOUT
#define VIRTIO_F_ANY_LAYOUT		27
#endif

/*L:110
 * We can ignore the 43 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;
/*:*/

#include <linux/virtio_config.h>
#include <linux/virtio_net.h>
#include <linux/virtio_blk.h>
#include <linux/virtio_console.h>
#include <linux/virtio_rng.h>
#include <linux/virtio_ring.h>
#include <asm/bootparam.h>
#include "../../include/linux/lguest_launcher.h"

#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 will occupy 3 pages: it must be a power of 2. */
#define VIRTQUEUE_NUM 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 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;
/* The /dev/lguest file descriptor. */
static int lguest_fd;

/* a per-cpu variable indicating whose vcpu is currently running */
static unsigned int __thread cpu_id;

/* This is our list of devices. */
struct device_list {
	/* 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;

	/* A single linked list of devices. */
	struct device *dev;
	/* And a pointer to the last device for easy append. */
	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 device's descriptor, as mapped into the Guest. */
	struct lguest_device_desc *desc;

	/* We can't trust desc values once Guest has booted: we use these. */
	unsigned int feature_len;
	unsigned int num_vq;

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

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

	/* Is it operational */
	bool running;

	/* 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;

	/* How many are used since we sent last irq? */
	unsigned int pending_used;

	/* Eventfd where Guest notifications arrive. */
	int eventfd;

	/* Function for the thread which is servicing this virtqueue. */
	void (*service)(struct virtqueue *vq);
	pid_t thread;
};

/* Remember the arguments to the program so we can "reboot" */
static char **main_args;

/* The original tty settings to restore on exit. */
static struct termios orig_term;

/*
 * We have to be careful with barriers: our devices are all run in separate
 * threads and so we need to make sure that changes visible to the Guest happen
 * in precise order.
 */
#define wmb() __asm__ __volatile__("" : : : "memory")
#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")
#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")

/* Wrapper for the last available index.  Makes it easier to change. */
#define lg_last_avail(vq)	((vq)->last_avail_idx)

/*
 * 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(v64) (v64)

/* Is this iovec empty? */
static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
{
	unsigned int i;

	for (i = 0; i < num_iov; i++)
		if (iov[i].iov_len)
			return false;
	return true;
}

/* Take len bytes from the front of this iovec. */
static void iov_consume(struct iovec iov[], unsigned num_iov,
			void *dest, unsigned len)
{
	unsigned int i;

	for (i = 0; i < num_iov; i++) {
		unsigned int used;

		used = iov[i].iov_len < len ? iov[i].iov_len : len;
		if (dest) {
			memcpy(dest, iov[i].iov_base, used);
			dest += used;
		}
		iov[i].iov_base += used;
		iov[i].iov_len -= used;
		len -= used;
	}
	if (len != 0)
		errx(1, "iovec too short!");
}

/* The device virtqueue descriptors are followed by feature bitmasks. */
static u8 *get_feature_bits(struct device *dev)
{
	return (u8 *)(dev->desc + 1)
		+ dev->num_vq * sizeof(struct lguest_vqconfig);
}

/*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 its
 * "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). We allocate an extra two pages PROT_NONE to act as guard
	 * pages against read/write attempts that exceed allocated space.
	 */
	addr = mmap(NULL, getpagesize() * (num+2),
		    PROT_NONE, MAP_PRIVATE, fd, 0);

	if (addr == MAP_FAILED)
		err(1, "Mmapping %u pages of /dev/zero", num);

	if (mprotect(addr + getpagesize(), getpagesize() * num,
		     PROT_READ|PROT_WRITE) == -1)
		err(1, "mprotect rw %u pages failed", num);

	/*
	 * One neat mmap feature is that you can close the fd, and it
	 * stays mapped.
	 */
	close(fd);

	/* Return address after PROT_NONE page */
	return addr + getpagesize();
}

/* 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,
		 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 we don't load.
	 */
	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/x86/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 load 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;
}
/*:*/

/*
 * 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++) {
		if (i) {
			strcat(dst+len, " ");
			len++;
		}
		strcpy(dst+len, args[i]);
		len += strlen(args[i]);
	}
	/* 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 and the
 * entry point for the Guest.
 */
static void tell_kernel(unsigned long start)
{
	unsigned long args[] = { LHREQ_INITIALIZE,
				 (unsigned long)guest_base,
				 guest_limit / getpagesize(), start };
	verbose("Guest: %p - %p (%#lx)\n",
		guest_base, guest_base + guest_limit, guest_limit);
	lguest_fd = open_or_die("/dev/lguest", O_RDWR);
	if (write(lguest_fd, args, sizeof(args)) < 0)
		err(1, "Writing to /dev/lguest");
}
/*:*/

/*L:200
 * 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)
{
	/*
	 * Check if the requested address and size exceeds the allocated memory,
	 * or addr + size wraps around.
	 */
	if ((addr + size) > guest_limit || (addr + size) < addr)
		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 vring_desc *desc,
			  unsigned int i, unsigned int max)
{
	unsigned int next;

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

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

	if (next >= max)
		errx(1, "Desc next is %u", next);

	return next;
}

/*
 * This actually sends the interrupt for this virtqueue, if we've used a
 * buffer.
 */
static void trigger_irq(struct virtqueue *vq)
{
	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };

	/* Don't inform them if nothing used. */
	if (!vq->pending_used)
		return;
	vq->pending_used = 0;

	/* 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(lguest_fd, buf, sizeof(buf)) != 0)
		err(1, "Triggering irq %i", vq->config.irq);
}

/*
 * This looks in the virtqueue 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 waits if necessary, and returns the descriptor number found.
 */
static unsigned wait_for_vq_desc(struct virtqueue *vq,
				 struct iovec iov[],
				 unsigned int *out_num, unsigned int *in_num)
{
	unsigned int i, head, max;
	struct vring_desc *desc;
	u16 last_avail = lg_last_avail(vq);

	/* There's nothing available? */
	while (last_avail == vq->vring.avail->idx) {
		u64 event;

		/*
		 * Since we're about to sleep, now is a good time to tell the
		 * Guest about what we've used up to now.
		 */
		trigger_irq(vq);

		/* OK, now we need to know about added descriptors. */
		vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;

		/*
		 * They could have slipped one in as we were doing that: make
		 * sure it's written, then check again.
		 */
		mb();
		if (last_avail != vq->vring.avail->idx) {
			vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
			break;
		}

		/* Nothing new?  Wait for eventfd to tell us they refilled. */
		if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event))
			errx(1, "Event read failed?");

		/* We don't need to be notified again. */
		vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
	}

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

	/* 
	 * Make sure we read the descriptor number *after* we read the ring
	 * update; don't let the cpu or compiler change the order.
	 */
	rmb();

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

	/* 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;

	max = vq->vring.num;
	desc = vq->vring.desc;
	i = head;

	/*
	 * We have to read the descriptor after we read the descriptor number,
	 * but there's a data dependency there so the CPU shouldn't reorder
	 * that: no rmb() required.
	 */

	/*
	 * If this is an indirect entry, then this buffer contains a descriptor
	 * table which we handle as if it's any normal descriptor chain.
	 */
	if (desc[i].flags & VRING_DESC_F_INDIRECT) {
		if (desc[i].len % sizeof(struct vring_desc))
			errx(1, "Invalid size for indirect buffer table");

		max = desc[i].len / sizeof(struct vring_desc);
		desc = check_pointer(desc[i].addr, desc[i].len);
		i = 0;
	}

	do {
		/* Grab the first descriptor, and check it's OK. */
		iov[*out_num + *in_num].iov_len = desc[i].len;
		iov[*out_num + *in_num].iov_base
			= check_pointer(desc[i].addr, desc[i].len);
		/* If this is an input descriptor, increment that count. */
		if (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 > max)
			errx(1, "Looped descriptor");
	} while ((i = next_desc(desc, i, max)) != max);

	return head;
}

/*
 * After we've used one of their buffers, we tell the Guest about it.  Sometime
 * later we'll want to send them an interrupt using trigger_irq(); note that
 * wait_for_vq_desc() does that for us if it has to wait.
 */
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++;
	vq->pending_used++;
}

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

/*
 * The Console
 *
 * 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 void console_input(struct virtqueue *vq)
{
	int len;
	unsigned int head, in_num, out_num;
	struct console_abort *abort = vq->dev->priv;
	struct iovec iov[vq->vring.num];

	/* Make sure there's a descriptor available. */
	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
	if (out_num)
		errx(1, "Output buffers in console in queue?");

	/* Read into it.  This is where we usually wait. */
	len = readv(STDIN_FILENO, iov, in_num);
	if (len <= 0) {
		/* Ran out of input? */
		warnx("Failed to get console input, ignoring console.");
		/*
		 * For simplicity, dying threads kill the whole Launcher.  So
		 * just nap here.
		 */
		for (;;)
			pause();
	}

	/* Tell the Guest we used a buffer. */
	add_used_and_trigger(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) {
		abort->count = 0;
		return;
	}

	abort->count++;
	if (abort->count == 1)
		gettimeofday(&abort->start, NULL);
	else if (abort->count == 3) {
		struct timeval now;
		gettimeofday(&now, NULL);
		/* Kill all Launcher processes with SIGINT, like normal ^C */
		if (now.tv_sec <= abort->start.tv_sec+1)
			kill(0, SIGINT);
		abort->count = 0;
	}
}

/* This is the routine which handles console output (ie. stdout). */
static void console_output(struct virtqueue *vq)
{
	unsigned int head, out, in;
	struct iovec iov[vq->vring.num];

	/* We usually wait in here, for the Guest to give us something. */
	head = wait_for_vq_desc(vq, iov, &out, &in);
	if (in)
		errx(1, "Input buffers in console output queue?");

	/* writev can return a partial write, so we loop here. */
	while (!iov_empty(iov, out)) {
		int len = writev(STDOUT_FILENO, iov, out);
		if (len <= 0) {
			warn("Write to stdout gave %i (%d)", len, errno);
			break;
		}
		iov_consume(iov, out, NULL, len);
	}

	/*
	 * We're finished with that buffer: if we're going to sleep,
	 * wait_for_vq_desc() will prod the Guest with an interrupt.
	 */
	add_used(vq, head, 0);
}

/*
 * The Network
 *
 * Handling output for network is also simple: we get all the output buffers
 * and write them to /dev/net/tun.
 */
struct net_info {
	int tunfd;
};

static void net_output(struct virtqueue *vq)
{
	struct net_info *net_info = vq->dev->priv;
	unsigned int head, out, in;
	struct iovec iov[vq->vring.num];

	/* We usually wait in here for the Guest to give us a packet. */
	head = wait_for_vq_desc(vq, iov, &out, &in);
	if (in)
		errx(1, "Input buffers in net output queue?");
	/*
	 * Send the whole thing through to /dev/net/tun.  It expects the exact
	 * same format: what a coincidence!
	 */
	if (writev(net_info->tunfd, iov, out) < 0)
		warnx("Write to tun failed (%d)?", errno);

	/*
	 * Done with that one; wait_for_vq_desc() will send the interrupt if
	 * all packets are processed.
	 */
	add_used(vq, head, 0);
}

/*
 * Handling network input is a bit trickier, because I've tried to optimize it.
 *
 * First we have a helper routine which tells is if from this file descriptor
 * (ie. the /dev/net/tun device) will block:
 */
static bool will_block(int fd)
{
	fd_set fdset;
	struct timeval zero = { 0, 0 };
	FD_ZERO(&fdset);
	FD_SET(fd, &fdset);
	return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
}

/*
 * This handles packets coming in from the tun device to our Guest.  Like all
 * service routines, it gets called again as soon as it returns, so you don't
 * see a while(1) loop here.
 */
static void net_input(struct virtqueue *vq)
{
	int len;
	unsigned int head, out, in;
	struct iovec iov[vq->vring.num];
	struct net_info *net_info = vq->dev->priv;

	/*
	 * Get a descriptor to write an incoming packet into.  This will also
	 * send an interrupt if they're out of descriptors.
	 */
	head = wait_for_vq_desc(vq, iov, &out, &in);
	if (out)
		errx(1, "Output buffers in net input queue?");

	/*
	 * If it looks like we'll block reading from the tun device, send them
	 * an interrupt.
	 */
	if (vq->pending_used && will_block(net_info->tunfd))
		trigger_irq(vq);

	/*
	 * Read in the packet.  This is where we normally wait (when there's no
	 * incoming network traffic).
	 */
	len = readv(net_info->tunfd, iov, in);
	if (len <= 0)
		warn("Failed to read from tun (%d).", errno);

	/*
	 * Mark that packet buffer as used, but don't interrupt here.  We want
	 * to wait until we've done as much work as we can.
	 */
	add_used(vq, head, len);
}
/*:*/

/* This is the helper to create threads: run the service routine in a loop. */
static int do_thread(void *_vq)
{
	struct virtqueue *vq = _vq;

	for (;;)
		vq->service(vq);
	return 0;
}

/*
 * When a child dies, we kill our entire process group with SIGTERM.  This
 * also has the side effect that the shell restores the console for us!
 */
static void kill_launcher(int signal)
{
	kill(0, SIGTERM);
}

static void reset_device(struct device *dev)
{
	struct virtqueue *vq;

	verbose("Resetting device %s\n", dev->name);

	/* Clear any features they've acked. */
	memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len);

	/* We're going to be explicitly killing threads, so ignore them. */
	signal(SIGCHLD, SIG_IGN);

	/* Zero out the virtqueues, get rid of their threads */
	for (vq = dev->vq; vq; vq = vq->next) {
		if (vq->thread != (pid_t)-1) {
			kill(vq->thread, SIGTERM);
			waitpid(vq->thread, NULL, 0);
			vq->thread = (pid_t)-1;
		}
		memset(vq->vring.desc, 0,
		       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
		lg_last_avail(vq) = 0;
	}
	dev->running = false;

	/* Now we care if threads die. */
	signal(SIGCHLD, (void *)kill_launcher);
}

/*L:216
 * This actually creates the thread which services the virtqueue for a device.
 */
static void create_thread(struct virtqueue *vq)
{
	/*
	 * Create stack for thread.  Since the stack grows upwards, we point
	 * the stack pointer to the end of this region.
	 */
	char *stack = malloc(32768);
	unsigned long args[] = { LHREQ_EVENTFD,
				 vq->config.pfn*getpagesize(), 0 };

	/* Create a zero-initialized eventfd. */
	vq->eventfd = eventfd(0, 0);
	if (vq->eventfd < 0)
		err(1, "Creating eventfd");
	args[2] = vq->eventfd;

	/*
	 * Attach an eventfd to this virtqueue: it will go off when the Guest
	 * does an LHCALL_NOTIFY for this vq.
	 */
	if (write(lguest_fd, &args, sizeof(args)) != 0)
		err(1, "Attaching eventfd");

	/*
	 * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
	 * we get a signal if it dies.
	 */
	vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
	if (vq->thread == (pid_t)-1)
		err(1, "Creating clone");

	/* We close our local copy now the child has it. */
	close(vq->eventfd);
}

static void start_device(struct device *dev)
{
	unsigned int i;
	struct virtqueue *vq;

	verbose("Device %s OK: offered", dev->name);
	for (i = 0; i < dev->feature_len; i++)
		verbose(" %02x", get_feature_bits(dev)[i]);
	verbose(", accepted");
	for (i = 0; i < dev->feature_len; i++)
		verbose(" %02x", get_feature_bits(dev)
			[dev->feature_len+i]);

	for (vq = dev->vq; vq; vq = vq->next) {
		if (vq->service)
			create_thread(vq);
	}
	dev->running = true;
}

static void cleanup_devices(void)
{
	struct device *dev;

	for (dev = devices.dev; dev; dev = dev->next)
		reset_device(dev);

	/* If we saved off the original terminal settings, restore them now. */
	if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
		tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
}

/* When the Guest tells us they updated the status field, we handle it. */
static void update_device_status(struct device *dev)
{
	/* A zero status is a reset, otherwise it's a set of flags. */
	if (dev->desc->status == 0)
		reset_device(dev);
	else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
		warnx("Device %s configuration FAILED", dev->name);
		if (dev->running)
			reset_device(dev);
	} else {
		if (dev->running)
			err(1, "Device %s features finalized twice", dev->name);
		start_device(dev);
	}
}

/*L:215
 * This is the generic routine we call when the Guest uses LHCALL_NOTIFY.  In
 * particular, it's used to notify us of device status changes during boot.
 */
static void handle_output(unsigned long addr)
{
	struct device *i;

	/* Check each device. */
	for (i = devices.dev; i; i = i->next) {
		struct virtqueue *vq;

		/*
		 * Notifications to device descriptors mean they updated the
		 * device status.
		 */
		if (from_guest_phys(addr) == i->desc) {
			update_device_status(i);
			return;
		}

		/* Devices should not be used before features are finalized. */
		for (vq = i->vq; vq; vq = vq->next) {
			if (addr != vq->config.pfn*getpagesize())
				continue;
			errx(1, "Notification on %s before setup!", i->name);
		}
	}

	/*
	 * Early console write is done using notify on a nul-terminated string
	 * in Guest memory.  It's also great for hacking debugging messages
	 * into a Guest.
	 */
	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));
}

/*L:216
 * This is where we emulate a handful of Guest instructions.  It's ugly
 * and we used to do it in the kernel but it grew over time.
 */

/*
 * We use the ptrace syscall's pt_regs struct to talk about registers
 * to lguest: these macros convert the names to the offsets.
 */
#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name))
#define setreg(name, val) \
	setreg_off(offsetof(struct user_regs_struct, name), (val))

static u32 getreg_off(size_t offset)
{
	u32 r;
	unsigned long args[] = { LHREQ_GETREG, offset };

	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
		err(1, "Getting register %u", offset);
	if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r))
		err(1, "Reading register %u", offset);

	return r;
}

static void setreg_off(size_t offset, u32 val)
{
	unsigned long args[] = { LHREQ_SETREG, offset, val };

	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
		err(1, "Setting register %u", offset);
}

static void emulate_insn(const u8 insn[])
{
	unsigned long args[] = { LHREQ_TRAP, 13 };
	unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access;
	unsigned int eax, port, mask;
	/*
	 * We always return all-ones on IO port reads, which traditionally
	 * means "there's nothing there".
	 */
	u32 val = 0xFFFFFFFF;

	/*
	 * This must be the Guest kernel trying to do something, not userspace!
	 * The bottom two bits of the CS segment register are the privilege
	 * level.
	 */
	if ((getreg(xcs) & 3) != 0x1)
		goto no_emulate;

	/* Decoding x86 instructions is icky. */

	/*
	 * Around 2.6.33, the kernel started using an emulation for the
	 * cmpxchg8b instruction in early boot on many configurations.  This
	 * code isn't paravirtualized, and it tries to disable interrupts.
	 * Ignore it, which will Mostly Work.
	 */
	if (insn[insnlen] == 0xfa) {
		/* "cli", or Clear Interrupt Enable instruction.  Skip it. */
		insnlen = 1;
		goto skip_insn;
	}

	/*
	 * 0x66 is an "operand prefix".  It means a 16, not 32 bit in/out.
	 */
	if (insn[insnlen] == 0x66) {
		small_operand = 1;
		/* The instruction is 1 byte so far, read the next byte. */
		insnlen = 1;
	}

	/* If the lower bit isn't set, it's a single byte access */
	byte_access = !(insn[insnlen] & 1);

	/*
	 * Now we can ignore the lower bit and decode the 4 opcodes
	 * we need to emulate.
	 */
	switch (insn[insnlen] & 0xFE) {
	case 0xE4: /* in     <next byte>,%al */
		port = insn[insnlen+1];
		insnlen += 2;
		in = 1;
		break;
	case 0xEC: /* in     (%dx),%al */
		port = getreg(edx) & 0xFFFF;
		insnlen += 1;
		in = 1;
		break;
	case 0xE6: /* out    %al,<next byte> */
		port = insn[insnlen+1];
		insnlen += 2;
		break;
	case 0xEE: /* out    %al,(%dx) */
		port = getreg(edx) & 0xFFFF;
		insnlen += 1;
		break;
	default:
		/* OK, we don't know what this is, can't emulate. */
		goto no_emulate;
	}

	/* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */
	if (byte_access)
		mask = 0xFF;
	else if (small_operand)
		mask = 0xFFFF;
	else
		mask = 0xFFFFFFFF;

	/* This is the PS/2 keyboard status; 1 means ready for output */
	if (port == 0x64)
		val = 1;

	/*
	 * If it was an "IN" instruction, they expect the result to be read
	 * into %eax, so we change %eax.
	 */
	eax = getreg(eax);

	if (in) {
		/* Clear the bits we're about to read */
		eax &= ~mask;
		/* Copy bits in from val. */
		eax |= val & mask;
		/* Now update the register. */
		setreg(eax, eax);
	}

	verbose("IO %s of %x to %u: %#08x\n",
		in ? "IN" : "OUT", mask, port, eax);
skip_insn:
	/* Finally, we've "done" the instruction, so move past it. */
	setreg(eip, getreg(eip) + insnlen);
	return;

no_emulate:
	/* Inject trap into Guest. */
	if (write(lguest_fd, args, sizeof(args)) < 0)
		err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip));
}


/*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 and manage them.
 */

/*
 * The layout of the device page is a "struct lguest_device_desc" followed by a
 * number of virtqueue descriptors, then two sets of feature bits, then an
 * array of configuration bytes.  This routine returns the configuration
 * pointer.
 */
static u8 *device_config(const struct device *dev)
{
	return (void *)(dev->desc + 1)
		+ dev->num_vq * sizeof(struct lguest_vqconfig)
		+ dev->feature_len * 2;
}

/*
 * This routine allocates a new "struct lguest_device_desc" from descriptor
 * table page 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 = { .type = type };
	void *p;

	/* Figure out where the next device config is, based on the last one. */
	if (devices.lastdev)
		p = device_config(devices.lastdev)
			+ devices.lastdev->desc->config_len;
	else
		p = devices.descpage;

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

	/* p might not be aligned, so we memcpy in. */
	return memcpy(p, &d, sizeof(d));
}

/*
 * Each device descriptor is followed by the description of its virtqueues.  We
 * specify how many descriptors the virtqueue is to have.
 */
static void add_virtqueue(struct device *dev, unsigned int num_descs,
			  void (*service)(struct virtqueue *))
{
	unsigned int pages;
	struct virtqueue **i, *vq = malloc(sizeof(*vq));
	void *p;

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

	/* Initialize the virtqueue */
	vq->next = NULL;
	vq->last_avail_idx = 0;
	vq->dev = dev;

	/*
	 * This is the routine the service thread will run, and its Process ID
	 * once it's running.
	 */
	vq->service = service;
	vq->thread = (pid_t)-1;

	/* 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, LGUEST_VRING_ALIGN);

	/*
	 * Append virtqueue to this device's descriptor.  We use
	 * device_config() to get the end of the device's current virtqueues;
	 * we check that we haven't added any config or feature information
	 * yet, otherwise we'd be overwriting them.
	 */
	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
	memcpy(device_config(dev), &vq->config, sizeof(vq->config));
	dev->num_vq++;
	dev->desc->num_vq++;

	verbose("Virtqueue page %#lx\n", to_guest_phys(p));

	/*
	 * 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;
}

/*
 * The first half of the feature bitmask is for us to advertise features.  The
 * second half is for the Guest to accept features.
 */
static void add_feature(struct device *dev, unsigned bit)
{
	u8 *features = get_feature_bits(dev);

	/* We can't extend the feature bits once we've added config bytes */
	if (dev->desc->feature_len <= bit / CHAR_BIT) {
		assert(dev->desc->config_len == 0);
		dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1;
	}

	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
}

/*
 * This routine sets the configuration fields for 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 set_config(struct device *dev, unsigned len, const void *conf)
{
	/* Check we haven't overflowed our single page. */
	if (device_config(dev) + len > devices.descpage + getpagesize())
		errx(1, "Too many devices");

	/* Copy in the config information, and store the length. */
	memcpy(device_config(dev), conf, len);
	dev->desc->config_len = len;

	/* Size must fit in config_len field (8 bits)! */
	assert(dev->desc->config_len == len);
}

/*
 * This routine does all the creation and setup of a new device, including
 * calling new_dev_desc() to allocate the descriptor and device memory.  We
 * don't actually start the service threads until later.
 *
 * See what I mean about userspace being boring?
 */
static struct device *new_device(const char *name, u16 type)
{
	struct device *dev = malloc(sizeof(*dev));

	/* Now we populate the fields one at a time. */
	dev->desc = new_dev_desc(type);
	dev->name = name;
	dev->vq = NULL;
	dev->feature_len = 0;
	dev->num_vq = 0;
	dev->running = false;
	dev->next = NULL;

	/*
	 * 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.
	 */
	if (devices.lastdev)
		devices.lastdev->next = dev;
	else
		devices.dev = dev;
	devices.lastdev = dev;

	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);
	}

	dev = new_device("console", VIRTIO_ID_CONSOLE);

	/* 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, console_input);
	add_virtqueue(dev, VIRTQUEUE_NUM, 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 sophisticated 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 use a virtio network switch in the kernel, ie. vhost.
:*/

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

	if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
		errx(1, "Failed to parse IP address '%s'", ipaddr);
	return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
}

static void str2mac(const char *macaddr, unsigned char mac[6])
{
	unsigned int m[6];
	if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
		   &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
		errx(1, "Failed to parse mac address '%s'", macaddr);
	mac[0] = m[0];
	mac[1] = m[1];
	mac[2] = m[2];
	mac[3] = m[3];
	mac[4] = m[4];
	mac[5] = m[5];
}

/*
 * 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_name[IFNAMSIZ-1] = '\0';
	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 *tapif, u32 ipaddr)
{
	struct ifreq ifr;
	struct sockaddr_in sin;

	memset(&ifr, 0, sizeof(ifr));
	strcpy(ifr.ifr_name, tapif);

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

static int get_tun_device(char tapif[IFNAMSIZ])
{
	struct ifreq ifr;
	int netfd;

	/* Start with this zeroed.  Messy but sure. */
	memset(&ifr, 0, sizeof(ifr));

	/*
	 * 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);
	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
	strcpy(ifr.ifr_name, "tap%d");
	if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
		err(1, "configuring /dev/net/tun");

	if (ioctl(netfd, TUNSETOFFLOAD,
		  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
		err(1, "Could not set features for tun device");

	/*
	 * We don't need checksums calculated for packets coming in this
	 * device: trust us!
	 */
	ioctl(netfd, TUNSETNOCSUM, 1);

	memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
	return netfd;
}

/*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(char *arg)
{
	struct device *dev;
	struct net_info *net_info = malloc(sizeof(*net_info));
	int ipfd;
	u32 ip = INADDR_ANY;
	bool bridging = false;
	char tapif[IFNAMSIZ], *p;
	struct virtio_net_config conf;

	net_info->tunfd = get_tun_device(tapif);

	/* First we create a new network device. */
	dev = new_device("net", VIRTIO_ID_NET);
	dev->priv = net_info;

	/* Network devices need a recv and a send queue, just like console. */
	add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
	add_virtqueue(dev, VIRTQUEUE_NUM, 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))) {
		arg += strlen(BRIDGE_PFX);
		bridging = true;
	}

	/* A mac address may follow the bridge name or IP address */
	p = strchr(arg, ':');
	if (p) {
		str2mac(p+1, conf.mac);
		add_feature(dev, VIRTIO_NET_F_MAC);
		*p = '\0';
	}

	/* arg is now either an IP address or a bridge name */
	if (bridging)
		add_to_bridge(ipfd, tapif, arg);
	else
		ip = str2ip(arg);

	/* Set up the tun device. */
	configure_device(ipfd, tapif, ip);

	/* Expect Guest to handle everything except UFO */
	add_feature(dev, VIRTIO_NET_F_CSUM);
	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
	add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
	add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
	add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
	add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
	add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
	add_feature(dev, VIRTIO_NET_F_HOST_ECN);
	/* We handle indirect ring entries */
	add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
	/* We're compliant with the damn spec. */
	add_feature(dev, VIRTIO_F_ANY_LAYOUT);
	set_config(dev, sizeof(conf), &conf);

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

	devices.device_num++;

	if (bridging)
		verbose("device %u: tun %s attached to bridge: %s\n",
			devices.device_num, tapif, arg);
	else
		verbose("device %u: tun %s: %s\n",
			devices.device_num, tapif, arg);
}
/*:*/

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

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

};

/*L:210
 * The Disk
 *
 * The disk only has one virtqueue, so it only has one thread.  It is really
 * simple: the Guest asks for a block number and we read or write that position
 * in the file.
 *
 * Before we serviced each virtqueue in a separate thread, that was unacceptably
 * slow: the Guest waits until the read is finished before running anything
 * else, even if it could have been doing useful work.
 *
 * We could have used 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.
 */
static void blk_request(struct virtqueue *vq)
{
	struct vblk_info *vblk = vq->dev->priv;
	unsigned int head, out_num, in_num, wlen;
	int ret, i;
	u8 *in;
	struct virtio_blk_outhdr out;
	struct iovec iov[vq->vring.num];
	off64_t off;

	/*
	 * Get the next request, where we normally wait.  It triggers the
	 * interrupt to acknowledge previously serviced requests (if any).
	 */
	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);

	/* Copy the output header from the front of the iov (adjusts iov) */
	iov_consume(iov, out_num, &out, sizeof(out));

	/* Find and trim end of iov input array, for our status byte. */
	in = NULL;
	for (i = out_num + in_num - 1; i >= out_num; i--) {
		if (iov[i].iov_len > 0) {
			in = iov[i].iov_base + iov[i].iov_len - 1;
			iov[i].iov_len--;
			break;
		}
	}
	if (!in)
		errx(1, "Bad virtblk cmd with no room for status");

	/*
	 * For historical reasons, block operations are expressed in 512 byte
	 * "sectors".
	 */
	off = out.sector * 512;

	/*
	 * 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 = 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, out_num);
		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 = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
	} else if (out.type & VIRTIO_BLK_T_FLUSH) {
		/* Flush */
		ret = fdatasync(vblk->fd);
		verbose("FLUSH fdatasync: %i\n", ret);
		wlen = sizeof(*in);
		*in = (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 + out_num, in_num);
		if (ret >= 0) {
			wlen = sizeof(*in) + ret;
			*in = VIRTIO_BLK_S_OK;
		} else {
			wlen = sizeof(*in);
			*in = VIRTIO_BLK_S_IOERR;
		}
	}

	/* Finished that request. */
	add_used(vq, head, wlen);
}

/*L:198 This actually sets up a virtual block device. */
static void setup_block_file(const char *filename)
{
	struct device *dev;
	struct vblk_info *vblk;
	struct virtio_blk_config conf;

	/* Creat the device. */
	dev = new_device("block", VIRTIO_ID_BLOCK);

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

	/* 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);

	/* We support FLUSH. */
	add_feature(dev, VIRTIO_BLK_F_FLUSH);

	/* Tell Guest how many sectors this device has. */
	conf.capacity = cpu_to_le64(vblk->len / 512);

	/*
	 * Tell Guest not to put in too many descriptors at once: two are used
	 * for the in and out elements.
	 */
	add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
	conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);

	/* Don't try to put whole struct: we have 8 bit limit. */
	set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf);

	verbose("device %u: virtblock %llu sectors\n",
		++devices.device_num, le64_to_cpu(conf.capacity));
}

/*L:211
 * Our random number generator device reads from /dev/urandom into the Guest's
 * input buffers.  The usual case is that the Guest doesn't want random numbers
 * and so has no buffers although /dev/urandom is still readable, whereas
 * console is the reverse.
 *
 * The same logic applies, however.
 */
struct rng_info {
	int rfd;
};

static void rng_input(struct virtqueue *vq)
{
	int len;
	unsigned int head, in_num, out_num, totlen = 0;
	struct rng_info *rng_info = vq->dev->priv;
	struct iovec iov[vq->vring.num];

	/* First we need a buffer from the Guests's virtqueue. */
	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
	if (out_num)
		errx(1, "Output buffers in rng?");

	/*
	 * Just like the console write, we loop to cover the whole iovec.
	 * In this case, short reads actually happen quite a bit.
	 */
	while (!iov_empty(iov, in_num)) {
		len = readv(rng_info->rfd, iov, in_num);
		if (len <= 0)
			err(1, "Read from /dev/urandom gave %i", len);
		iov_consume(iov, in_num, NULL, len);
		totlen += len;
	}

	/* Tell the Guest about the new input. */
	add_used(vq, head, totlen);
}

/*L:199
 * This creates a "hardware" random number device for the Guest.
 */
static void setup_rng(void)
{
	struct device *dev;
	struct rng_info *rng_info = malloc(sizeof(*rng_info));

	/* Our device's private info simply contains the /dev/urandom fd. */
	rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY);

	/* Create the new device. */
	dev = new_device("rng", VIRTIO_ID_RNG);
	dev->priv = rng_info;

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

	verbose("device %u: rng\n", devices.device_num++);
}
/* That's the end of device setup. */

/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
static void __attribute__((noreturn)) restart_guest(void)
{
	unsigned int i;

	/*
	 * Since we don't track all open fds, we simply close everything beyond
	 * stderr.
	 */
	for (i = 3; i < FD_SETSIZE; i++)
		close(i);

	/* Reset all the devices (kills all threads). */
	cleanup_devices();

	execv(main_args[0], main_args);
	err(1, "Could not exec %s", main_args[0]);
}

/*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(void)
{
	for (;;) {
		struct lguest_pending notify;
		int readval;

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

		/* One unsigned long means the Guest did HCALL_NOTIFY */
		if (readval == sizeof(notify)) {
			if (notify.trap == 0x1F) {
				verbose("Notify on address %#08x\n",
					notify.addr);
				handle_output(notify.addr);
			} else if (notify.trap == 13) {
				verbose("Emulating instruction at %#x\n",
					getreg(eip));
				emulate_insn(notify.insn);
			} else
				errx(1, "Unknown trap %i addr %#08x\n",
				     notify.trap, notify.addr);
		/* ENOENT means the Guest died.  Reading tells us why. */
		} else if (errno == ENOENT) {
			char reason[1024] = { 0 };
			pread(lguest_fd, reason, sizeof(reason)-1, cpu_id);
			errx(1, "%s", reason);
		/* ERESTART means that we need to reboot the guest */
		} else if (errno == ERESTART) {
			restart_guest();
		/* Anything else means a bug or incompatible change. */
		} else
			err(1, "Running guest failed");
	}
}
/*L:240
 * 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' },
	{ "rng", 0, NULL, 'r' },
	{ "initrd", 1, NULL, 'i' },
	{ "username", 1, NULL, 'u' },
	{ "chroot", 1, NULL, 'c' },
	{ NULL },
};
static void usage(void)
{
	errx(1, "Usage: lguest [--verbose] "
	     "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\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, code startpoint and size of the (optional) initrd. */
	unsigned long mem = 0, start, initrd_size = 0;
	/* Two temporaries. */
	int i, c;
	/* The boot information for the Guest. */
	struct boot_params *boot;
	/* If they specify an initrd file to load. */
	const char *initrd_name = NULL;

	/* Password structure for initgroups/setres[gu]id */
	struct passwd *user_details = NULL;

	/* Directory to chroot to */
	char *chroot_path = NULL;

	/* Save the args: we "reboot" by execing ourselves again. */
	main_args = argv;

	/*
	 * First we initialize the device list.  We keep a pointer to the last
	 * device, and the next interrupt number to use for devices (1:
	 * remember that 0 is used by the timer).
	 */
	devices.lastdev = NULL;
	devices.next_irq = 1;

	/* We're CPU 0.  In fact, that's the only CPU possible right now. */
	cpu_id = 0;

	/*
	 * 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 'r':
			setup_rng();
			break;
		case 'i':
			initrd_name = optarg;
			break;
		case 'u':
			user_details = getpwnam(optarg);
			if (!user_details)
				err(1, "getpwnam failed, incorrect username?");
			break;
		case 'c':
			chroot_path = 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;
	}

	/*
	 * 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);

	/* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
	boot->hdr.kernel_alignment = 0x1000000;

	/* 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. */
	tell_kernel(start);

	/* Ensure that we terminate if a device-servicing child dies. */
	signal(SIGCHLD, kill_launcher);

	/* If we exit via err(), this kills all the threads, restores tty. */
	atexit(cleanup_devices);

	/* If requested, chroot to a directory */
	if (chroot_path) {
		if (chroot(chroot_path) != 0)
			err(1, "chroot(\"%s\") failed", chroot_path);

		if (chdir("/") != 0)
			err(1, "chdir(\"/\") failed");

		verbose("chroot done\n");
	}

	/* If requested, drop privileges */
	if (user_details) {
		uid_t u;
		gid_t g;

		u = user_details->pw_uid;
		g = user_details->pw_gid;

		if (initgroups(user_details->pw_name, g) != 0)
			err(1, "initgroups failed");

		if (setresgid(g, g, g) != 0)
			err(1, "setresgid failed");

		if (setresuid(u, u, u) != 0)
			err(1, "setresuid failed");

		verbose("Dropping privileges completed\n");
	}

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

/*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.
 */