litmus-rt.git - The LITMUS^RT kernel.

index : litmus-rt.git

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

path: root/include/linux/blkdev.h

diff options

Diffstat (limited to 'include/linux/blkdev.h')

0 files changed, 0 insertions, 0 deletions

48' href='#n48'>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

/*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 <zlib.h>
#include <assert.h>
#include <sched.h>
#include <limits.h>
#include <stddef.h>
#include <signal.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_rng.h"
#include "linux/virtio_ring.h"
#include "asm/bootparam.h"
/*L:110 We can ignore the 39 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 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 and also for
	 * configuration appending. */
	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")

/* 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;
}

/* 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, 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;
		iov[i].iov_base += used;
		iov[i].iov_len -= used;
		len -= used;
	}
	assert(len == 0);
}

/* 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 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);
	close(fd);

	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 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/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 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");
}
/*:*/

/*
 * 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);


context:
space:
mode: