| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1171252534.10409.43.camel@localhost.localdomain>
Date: Mon, 12 Feb 2007 14:55:34 +1100
From: Rusty Russell <rusty@...tcorp.com.au>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: lkml - Kernel Mailing List <linux-kernel@...r.kernel.org>,
virtualization <virtualization@...ts.osdl.org>
Subject: [PATCH 8/8] lguest: documentatation and example launcher
Fairly complete documentation for lguest. I actually want to get rid
of the "coding" part of lguest.txt and roll it into the code itself,
literary-programming-style.
The launcher utility is also here: I don't have delusions of interface
stability, so it makes sense to have it here as an example, and it's
only 1000 lines.
Signed-off-by: Rusty Russell <rusty@...tcorp.com.au>
diff -r 8806a441a0b1 Documentation/dontdiff
--- a/Documentation/dontdiff Mon Feb 12 13:02:02 2007 +1100
+++ b/Documentation/dontdiff Mon Feb 12 13:47:43 2007 +1100
@@ -144,3 +144,6 @@ wanxlfw.inc
wanxlfw.inc
uImage
zImage
+hypervisor-blob.c
+lguest.lds
+hypervisor-raw
diff -r 8806a441a0b1 Documentation/lguest/Makefile
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/Documentation/lguest/Makefile Mon Feb 12 13:48:13 2007 +1100
@@ -0,0 +1,21 @@
+# This creates the demonstration utility "lguest" which runs a Linux guest.
+
+# We rely on CONFIG_PAGE_OFFSET to know where to put lguest binary.
+# Some shells (dash - ubunu) can't handle numbers that big so we cheat.
+include ../../.config
+LGUEST_GUEST_TOP := ($(CONFIG_PAGE_OFFSET) - 0x08000000)
+
+CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 \
+ -static -DLGUEST_GUEST_TOP="$(LGUEST_GUEST_TOP)" -Wl,-T,lguest.lds
+LDLIBS:=-lz
+
+all: lguest.lds lguest
+
+# The linker script on x86 is so complex the only way of creating one
+# which will link our binary in the right place is to mangle the
+# default one.
+lguest.lds:
+ $(LD) --verbose | awk '/^==========/ { PRINT=1; next; } /SIZEOF_HEADERS/ { gsub(/0x[0-9A-F]*/, "$(LGUEST_GUEST_TOP)") } { if (PRINT) print $$0; }' > $@
+
+clean:
+ rm -f lguest.lds lguest
diff -r 8806a441a0b1 Documentation/lguest/lguest.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/Documentation/lguest/lguest.c Mon Feb 12 13:47:43 2007 +1100
@@ -0,0 +1,989 @@
+/* Simple program to layout "physical" memory for new lguest guest.
+ * Linked high to avoid likely physical memory. */
+#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/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <signal.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <time.h>
+#include <netinet/in.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <sys/uio.h>
+#include <termios.h>
+#include <zlib.h>
+typedef uint32_t u32;
+typedef uint16_t u16;
+typedef uint8_t u8;
+
+#include "../../include/asm/lguest_user.h"
+
+#define PAGE_PRESENT 0x7 /* Present, RW, Execute */
+#define NET_PEERNUM 1
+
+static bool verbose;
+#define verbose(args...) \
+ do { if (verbose) printf(args); fflush(stdout); } while(0)
+
+struct devices
+{
+ fd_set infds;
+ int max_infd;
+
+ struct device *dev;
+};
+
+struct device
+{
+ struct device *next;
+ struct lguest_device_desc *desc;
+ void *mem;
+
+ /* Watch this fd if handle_input non-NULL. */
+ int fd;
+ int (*handle_input)(int fd, struct device *me);
+
+ /* Watch DMA to this address if handle_input non-NULL. */
+ unsigned long watch_address;
+ u32 (*handle_output)(int fd, const struct iovec *iov,
+ unsigned int num, struct device *me);
+
+ /* Device-specific data. */
+ void *priv;
+};
+
+static char buf[1024];
+static struct iovec discard_iov = { .iov_base=buf, .iov_len=sizeof(buf) };
+static int zero_fd;
+
+static u32 memparse(const char *ptr)
+{
+ char *end;
+ unsigned long ret = strtoul(ptr, &end, 0);
+
+ switch (*end) {
+ case 'G':
+ case 'g':
+ ret <<= 10;
+ case 'M':
+ case 'm':
+ ret <<= 10;
+ case 'K':
+ case 'k':
+ ret <<= 10;
+ end++;
+ default:
+ break;
+ }
+ return ret;
+}
+
+static inline unsigned long page_align(unsigned long addr)
+{
+ return ((addr + getpagesize()-1) & ~(getpagesize()-1));
+}
+
+/* initrd gets loaded at top of memory: return length. */
+static unsigned long load_initrd(const char *name, unsigned long end)
+{
+ int ifd;
+ struct stat st;
+ void *iaddr;
+
+ if (!name)
+ return 0;
+
+ ifd = open(name, O_RDONLY, 0);
+ if (ifd < 0)
+ err(1, "Opening initrd '%s'", name);
+
+ if (fstat(ifd, &st) < 0)
+ err(1, "fstat() on initrd '%s'", name);
+
+ iaddr = mmap((void *)end - st.st_size, st.st_size,
+ PROT_READ|PROT_EXEC|PROT_WRITE,
+ MAP_FIXED|MAP_PRIVATE, ifd, 0);
+ if (iaddr != (void *)end - st.st_size)
+ err(1, "Mmaping initrd '%s' returned %p not %p",
+ name, iaddr, (void *)end - st.st_size);
+ close(ifd);
+ verbose("mapped initrd %s size=%lu @ %p\n", name, st.st_size, iaddr);
+ return st.st_size;
+}
+
+/* First map /dev/zero over entire memory, then insert kernel. */
+static void map_memory(unsigned long mem)
+{
+ if (mmap(0, mem,
+ PROT_READ|PROT_WRITE|PROT_EXEC,
+ MAP_FIXED|MAP_PRIVATE, zero_fd, 0) != (void *)0)
+ err(1, "Mmaping /dev/zero for %li bytes", mem);
+}
+
+static u32 finish(unsigned long mem, unsigned long *page_offset,
+ const char *initrd, unsigned long *ird_size)
+{
+ u32 *pgdir = NULL, *linear = NULL;
+ int i, pte_pages;
+
+ /* This is a top of mem. */
+ *ird_size = load_initrd(initrd, mem);
+
+ /* Below initrd is used as top level of pagetable. */
+ pte_pages = 1 + (mem/getpagesize() + 1023)/1024;
+
+ pgdir = (u32 *)page_align(mem - *ird_size - pte_pages*getpagesize());
+ linear = (void *)pgdir + getpagesize();
+
+ /* Linear map all of memory at page_offset (to top of mem). */
+ if (mem > -*page_offset)
+ mem = -*page_offset;
+
+ for (i = 0; i < mem / getpagesize(); i++)
+ linear[i] = ((i * getpagesize()) | PAGE_PRESENT);
+ verbose("Linear %p-%p (%i-%i) = %#08x-%#08x\n",
+ linear, linear+i-1, 0, i-1, linear[0], linear[i-1]);
+
+ /* Now set up pgd so that this memory is at page_offset */
+ for (i = 0; i < mem / getpagesize(); i += getpagesize()/sizeof(u32)) {
+ pgdir[(i + *page_offset/getpagesize())/1024]
+ = (((u32)linear + i*sizeof(u32)) | PAGE_PRESENT);
+ verbose("Top level %lu = %#08x\n",
+ (i + *page_offset/getpagesize())/1024,
+ pgdir[(i + *page_offset/getpagesize())/1024]);
+ }
+
+ return (unsigned long)pgdir;
+}
+
+/* Returns the entry point */
+static u32 map_elf(int elf_fd, const Elf32_Ehdr *ehdr, unsigned long mem,
+ unsigned long *pgdir_addr,
+ const char *initrd, unsigned long *ird_size,
+ unsigned long *page_offset)
+{
+ void *addr;
+ Elf32_Phdr phdr[ehdr->e_phnum];
+ unsigned int i;
+
+ /* Sanity checks. */
+ 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");
+
+ 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");
+
+ map_memory(mem);
+
+ *page_offset = 0;
+ /* We map the loadable segments at virtual addresses corresponding
+ * to their physical addresses (our virtual == guest physical). */
+ for (i = 0; i < ehdr->e_phnum; i++) {
+ 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 everything private, writable. */
+ if (phdr[i].p_paddr + phdr[i].p_memsz > mem)
+ errx(1, "Segment %i overlaps end of memory", i);
+
+ /* We expect linear address space. */
+ if (!*page_offset)
+ *page_offset = phdr[i].p_vaddr - phdr[i].p_paddr;
+ else if (*page_offset != phdr[i].p_vaddr - phdr[i].p_paddr)
+ errx(1, "Page offset of section %i different", i);
+
+ /* Recent ld versions don't page align any more. */
+ if (phdr[i].p_paddr % getpagesize()) {
+ phdr[i].p_filesz += (phdr[i].p_paddr % getpagesize());
+ phdr[i].p_offset -= (phdr[i].p_paddr % getpagesize());
+ phdr[i].p_paddr -= (phdr[i].p_paddr % getpagesize());
+ }
+ addr = mmap((void *)phdr[i].p_paddr,
+ phdr[i].p_filesz,
+ PROT_READ|PROT_WRITE|PROT_EXEC,
+ MAP_FIXED|MAP_PRIVATE,
+ elf_fd, phdr[i].p_offset);
+ if (addr != (void *)phdr[i].p_paddr)
+ err(1, "Mmaping vmlinux segment %i returned %p not %p (%p)",
+ i, addr, (void *)phdr[i].p_paddr, &phdr[i].p_paddr);
+ }
+
+ *pgdir_addr = finish(mem, page_offset, initrd, ird_size);
+ /* Entry is physical address: convert to virtual */
+ return ehdr->e_entry + *page_offset;
+}
+
+static unsigned long intuit_page_offset(unsigned char *img, unsigned long len)
+{
+ unsigned int i, possibilities[256];
+
+ for (i = 0; i + 4 < len; i++) {
+ /* mov 0xXXXXXXXX,%eax */
+ if (img[i] == 0xA1 && ++possibilities[img[i+4]] > 3)
+ return (unsigned long)img[i+4] << 24;
+ }
+ errx(1, "could not determine page offset");
+}
+
+static u32 bzimage(int fd, unsigned long mem, unsigned long *pgdir_addr,
+ const char *initrd, unsigned long *ird_size,
+ unsigned long *page_offset)
+{
+ gzFile f;
+ int ret, len = 0;
+ void *img = (void *)0x100000;
+
+ map_memory(mem);
+
+ f = gzdopen(fd, "rb");
+ if (gzdirect(f))
+ errx(1, "did not find correct gzip header");
+ while ((ret = gzread(f, img + len, 65536)) > 0)
+ len += ret;
+ if (ret < 0)
+ err(1, "reading image from bzImage");
+
+ verbose("Unpacked size %i addr %p\n", len, img);
+ *page_offset = intuit_page_offset(img, len);
+ *pgdir_addr = finish(mem, page_offset, initrd, ird_size);
+
+ /* Entry is physical address: convert to virtual */
+ return (u32)img + *page_offset;
+}
+
+static u32 load_bzimage(int bzimage_fd, const Elf32_Ehdr *ehdr,
+ unsigned long mem, unsigned long *pgdir_addr,
+ const char *initrd, unsigned long *ird_size,
+ unsigned long *page_offset)
+{
+ unsigned char c;
+ int state = 0;
+
+ /* Just brute force it. */
+ while (read(bzimage_fd, &c, 1) == 1) {
+ switch (state) {
+ case 0:
+ if (c == 0x1F)
+ state++;
+ break;
+ case 1:
+ if (c == 0x8B)
+ state++;
+ else
+ state = 0;
+ break;
+ case 2 ... 8:
+ state++;
+ break;
+ case 9:
+ lseek(bzimage_fd, -10, SEEK_CUR);
+ if (c != 0x03) /* Compressed under UNIX. */
+ state = -1;
+ else
+ return bzimage(bzimage_fd, mem, pgdir_addr,
+ initrd, ird_size, page_offset);
+ }
+ }
+ errx(1, "Could not find kernel in bzImage");
+}
+
+static void *map_pages(unsigned long addr, unsigned int num)
+{
+ if (mmap((void *)addr, getpagesize() * num,
+ PROT_READ|PROT_WRITE|PROT_EXEC,
+ MAP_FIXED|MAP_PRIVATE, zero_fd, 0) != (void *)addr)
+ err(1, "Mmaping %u pages of /dev/zero @%p", num, (void *)addr);
+ return (void *)addr;
+}
+
+static struct lguest_device_desc *
+get_dev_entry(struct lguest_device_desc *descs, u16 type, u16 num_pages)
+{
+ static unsigned long top = LGUEST_GUEST_TOP;
+ int i;
+ unsigned long pfn = 0;
+
+ if (num_pages) {
+ top -= num_pages*getpagesize();
+ map_pages(top, num_pages);
+ pfn = top / getpagesize();
+ }
+
+ for (i = 0; i < LGUEST_MAX_DEVICES; i++) {
+ if (!descs[i].type) {
+ descs[i].features = descs[i].status = 0;
+ descs[i].type = type;
+ descs[i].num_pages = num_pages;
+ descs[i].pfn = pfn;
+ return &descs[i];
+ }
+ }
+ errx(1, "too many devices");
+}
+
+static void set_fd(int fd, struct devices *devices)
+{
+ FD_SET(fd, &devices->infds);
+ if (fd > devices->max_infd)
+ devices->max_infd = fd;
+}
+
+static struct device *new_device(struct devices *devices,
+ struct lguest_device_desc *descs,
+ u16 type, u16 num_pages,
+ int fd,
+ int (*handle_input)(int, struct device *),
+ unsigned long watch_off,
+ u32 (*handle_output)(int,
+ const struct iovec *,
+ unsigned,
+ struct device *))
+{
+ struct device *dev = malloc(sizeof(*dev));
+
+ dev->next = devices->dev;
+ devices->dev = dev;
+
+ dev->fd = fd;
+ if (handle_input)
+ set_fd(dev->fd, devices);
+ dev->desc = get_dev_entry(descs, type, num_pages);
+ dev->mem = (void *)(dev->desc->pfn * getpagesize());
+ dev->handle_input = handle_input;
+ dev->watch_address = (unsigned long)dev->mem + watch_off;
+ dev->handle_output = handle_output;
+ return dev;
+}
+
+static int tell_kernel(u32 pagelimit, u32 pgdir, u32 start, u32 page_offset)
+{
+ u32 args[] = { LHREQ_INITIALIZE,
+ pagelimit, pgdir, start, page_offset };
+ int fd = open("/dev/lguest", O_RDWR);
+
+ if (fd < 0)
+ err(1, "Opening /dev/lguest");
+
+ verbose("Telling kernel limit %u, pgdir %i, e=%#08x page_off=0x%08x\n",
+ pagelimit, pgdir, start, page_offset);
+ if (write(fd, args, sizeof(args)) < 0)
+ err(1, "Writing to /dev/lguest");
+ return fd;
+}
+
+static void concat(char *dst, char *args[])
+{
+ unsigned int i, len = 0;
+
+ for (i = 0; args[i]; i++) {
+ strcpy(dst+len, args[i]);
+ strcat(dst+len, " ");
+ len += strlen(args[i]) + 1;
+ }
+ /* In case it's empty. */
+ dst[len] = '\0';
+}
+
+static void *_check_pointer(unsigned long addr, unsigned int size,
+ unsigned int line)
+{
+ if (addr >= LGUEST_GUEST_TOP || addr + size >= LGUEST_GUEST_TOP)
+ errx(1, "%s:%i: Invalid address %li", __FILE__, line, addr);
+ return (void *)addr;
+}
+#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
+
+/* Returns pointer to dma->used_len */
+static u32 *dma2iov(unsigned long dma, struct iovec iov[], unsigned *num)
+{
+ unsigned int i;
+ struct lguest_dma *udma;
+
+ /* No buffers? */
+ if (dma == 0) {
+ printf("no buffers\n");
+ return NULL;
+ }
+
+ udma = check_pointer(dma, sizeof(*udma));
+ for (i = 0; i < LGUEST_MAX_DMA_SECTIONS; i++) {
+ if (!udma->len[i])
+ break;
+
+ iov[i].iov_base = check_pointer(udma->addr[i], udma->len[i]);
+ iov[i].iov_len = udma->len[i];
+ }
+ *num = i;
+ return &udma->used_len;
+}
+
+static u32 *get_dma_buffer(int fd, void *addr,
+ struct iovec iov[], unsigned *num, u32 *irq)
+{
+ u32 buf[] = { LHREQ_GETDMA, (u32)addr };
+ unsigned long udma;
+ u32 *res;
+
+ udma = write(fd, buf, sizeof(buf));
+ if (udma == (unsigned long)-1)
+ return NULL;
+
+ /* Kernel stashes irq in ->used_len. */
+ res = dma2iov(udma, iov, num);
+ if (res)
+ *irq = *res;
+ return res;
+}
+
+static void trigger_irq(int fd, u32 irq)
+{
+ u32 buf[] = { LHREQ_IRQ, irq };
+ if (write(fd, buf, sizeof(buf)) != 0)
+ err(1, "Triggering irq %i", irq);
+}
+
+static struct termios orig_term;
+static void restore_term(void)
+{
+ tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+}
+
+struct console_abort
+{
+ int count;
+ struct timeval start;
+};
+
+/* We DMA input to buffer bound at start of console page. */
+static int handle_console_input(int fd, struct device *dev)
+{
+ u32 num, irq = 0, *lenp;
+ int len;
+ struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+ struct console_abort *abort = dev->priv;
+
+ lenp = get_dma_buffer(fd, dev->mem, iov, &num, &irq);
+ if (!lenp) {
+ warn("console: no dma buffer!");
+ iov[0] = discard_iov;
+ num = 1;
+ }
+
+ len = readv(dev->fd, iov, num);
+ if (len <= 0) {
+ warnx("Failed to get console input, ignoring console.");
+ len = 0;
+ }
+
+ if (lenp) {
+ *lenp = len;
+ trigger_irq(fd, irq);
+ }
+
+ /* Three ^C within one second? Exit. */
+ if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
+ if (!abort->count++)
+ gettimeofday(&abort->start, NULL);
+ else if (abort->count == 3) {
+ struct timeval now;
+ gettimeofday(&now, NULL);
+ if (now.tv_sec <= abort->start.tv_sec+1)
+ exit(2);
+ abort->count = 0;
+ }
+ } else
+ abort->count = 0;
+
+ if (!len) {
+ restore_term();
+ return 0;
+ }
+ return 1;
+}
+
+static unsigned long peer_offset(unsigned int peernum)
+{
+ return 4 * peernum;
+}
+
+static u32 handle_tun_output(int fd, const struct iovec *iov,
+ unsigned num, struct device *dev)
+{
+ /* Now we've seen output, we should warn if we can't get buffers. */
+ *(bool *)dev->priv = true;
+ return writev(dev->fd, iov, num);
+}
+
+static u32 handle_block_output(int fd, const struct iovec *iov,
+ unsigned num, struct device *dev)
+{
+ struct lguest_block_page *p = dev->mem;
+ u32 irq, reply_num, *lenp;
+ int len;
+ struct iovec reply[LGUEST_MAX_DMA_SECTIONS];
+ off64_t device_len, off = (off64_t)p->sector * 512;
+
+ device_len = *(off64_t *)dev->priv;
+
+ if (off >= device_len)
+ err(1, "Bad offset %llu vs %llu", off, device_len);
+ if (lseek64(dev->fd, off, SEEK_SET) != off)
+ err(1, "Bad seek to sector %i", p->sector);
+
+ verbose("Block: %s at offset %llu\n", p->type ? "WRITE" : "READ", off);
+
+ lenp = get_dma_buffer(fd, dev->mem, reply, &reply_num, &irq);
+ if (!lenp)
+ err(1, "Block request didn't give us a dma buffer");
+
+ if (p->type) {
+ len = writev(dev->fd, iov, num);
+ if (off + len > device_len) {
+ ftruncate(dev->fd, device_len);
+ errx(1, "Write past end %llu+%u", off, len);
+ }
+ *lenp = 0;
+ } else {
+ len = readv(dev->fd, reply, reply_num);
+ *lenp = len;
+ }
+
+ p->result = 1 + (p->bytes != len);
+ trigger_irq(fd, irq);
+ return 0;
+}
+
+#define HIPQUAD(ip) \
+ ((u8)(ip >> 24)), \
+ ((u8)(ip >> 16)), \
+ ((u8)(ip >> 8)), \
+ ((u8)(ip))
+
+static void configure_device(const char *devname, u32 ipaddr,
+ unsigned char hwaddr[6])
+{
+ struct ifreq ifr;
+ int fd;
+ struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, devname);
+ sin->sin_family = AF_INET;
+ sin->sin_addr.s_addr = htonl(ipaddr);
+ fd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+ if (fd < 0)
+ err(1, "opening IP socket");
+ if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
+ err(1, "Setting %s interface address", devname);
+ ifr.ifr_flags = IFF_UP;
+ if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
+ err(1, "Bringing interface %s up", devname);
+
+ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+ err(1, "getting hw address for %s", devname);
+
+ memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
+}
+
+/* We send lguest_add signals while input is pending: avoids races. */
+static void wake_parent(int pipefd, struct devices *devices)
+{
+ int parent = getppid();
+ nice(19);
+
+ set_fd(pipefd, devices);
+
+ for (;;) {
+ fd_set rfds = devices->infds;
+
+ select(devices->max_infd+1, &rfds, NULL, NULL, NULL);
+ if (FD_ISSET(pipefd, &rfds)) {
+ int ignorefd;
+ if (read(pipefd, &ignorefd, sizeof(ignorefd)) == 0)
+ exit(0);
+ FD_CLR(ignorefd, &devices->infds);
+ }
+ kill(parent, SIGUSR1);
+ }
+}
+
+/* We don't want signal to kill us, just jerk us out of kernel. */
+static void wakeup(int signo)
+{
+}
+
+static int handle_tun_input(int fd, struct device *dev)
+{
+ u32 irq = 0, num, *lenp;
+ int len;
+ struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+
+ lenp = get_dma_buffer(fd, dev->mem+peer_offset(NET_PEERNUM), iov, &num,
+ &irq);
+ if (!lenp) {
+ if (*(bool *)dev->priv)
+ warn("network: no dma buffer!");
+ iov[0] = discard_iov;
+ num = 1;
+ }
+
+ len = readv(dev->fd, iov, num);
+ if (len <= 0)
+ err(1, "reading network");
+ if (lenp) {
+ *lenp = len;
+ trigger_irq(fd, irq);
+ }
+ verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
+ ((u8 *)iov[0].iov_base)[0], ((u8 *)iov[0].iov_base)[1],
+ lenp ? "sent" : "discarded");
+ return 1;
+}
+
+/* We use fnctl locks to reserve network slots (autocleanup!) */
+static unsigned int find_slot(int netfd, const char *filename)
+{
+ struct flock fl;
+
+ fl.l_type = F_WRLCK;
+ fl.l_whence = SEEK_SET;
+ fl.l_len = 1;
+ for (fl.l_start = 0;
+ fl.l_start < getpagesize()/sizeof(struct lguest_net);
+ fl.l_start++) {
+ if (fcntl(netfd, F_SETLK, &fl) == 0)
+ return fl.l_start;
+ }
+ errx(1, "No free slots in network file %s", filename);
+}
+
+static void setup_net_file(const char *filename,
+ struct lguest_device_desc *descs,
+ struct devices *devices)
+{
+ int netfd;
+ struct device *dev;
+
+ netfd = open(filename, O_RDWR, 0);
+ if (netfd < 0) {
+ if (errno == ENOENT) {
+ netfd = open(filename, O_RDWR|O_CREAT, 0600);
+ if (netfd >= 0) {
+ char page[getpagesize()];
+ /* 0xFFFF == NO_GUEST */
+ memset(page, 0xFF, sizeof(page));
+ write(netfd, page, sizeof(page));
+ }
+ }
+ if (netfd < 0)
+ err(1, "cannot open net file '%s'", filename);
+ }
+
+ dev = new_device(devices, descs, LGUEST_DEVICE_T_NET, 1,
+ -1, NULL, 0, NULL);
+
+ /* This is the slot for the guest to use. */
+ dev->desc->features = find_slot(netfd, filename)|LGUEST_NET_F_NOCSUM;
+ /* We overwrite the /dev/zero mapping with the actual file. */
+ if (mmap(dev->mem, getpagesize(), PROT_READ|PROT_WRITE,
+ MAP_FIXED|MAP_SHARED, netfd, 0) != dev->mem)
+ err(1, "could not mmap '%s'", filename);
+ verbose("device %p@%p: shared net %s, peer %i\n", dev->desc,
+ (void *)(dev->desc->pfn * getpagesize()), filename,
+ dev->desc->features & ~LGUEST_NET_F_NOCSUM);
+}
+
+static u32 str2ip(const char *ipaddr)
+{
+ unsigned int byte[4];
+
+ sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
+ return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+}
+
+static void setup_tun_net(const char *ipaddr,
+ struct lguest_device_desc *descs,
+ struct devices *devices)
+{
+ struct device *dev;
+ struct ifreq ifr;
+ int netfd;
+
+ netfd = open("/dev/net/tun", O_RDWR);
+ if (netfd < 0)
+ err(1, "opening /dev/net/tun");
+
+ memset(&ifr, 0, sizeof(ifr));
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+ strcpy(ifr.ifr_name, "tap%d");
+ if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
+ err(1, "configuring /dev/net/tun");
+
+ dev = new_device(devices, descs, LGUEST_DEVICE_T_NET, 1,
+ netfd, handle_tun_input,
+ peer_offset(0), handle_tun_output);
+ dev->priv = malloc(sizeof(bool));
+ *(bool *)dev->priv = false;
+
+ /* We are peer 0, rest is all NO_GUEST */
+ memset(dev->mem, 0xFF, getpagesize());
+ configure_device(ifr.ifr_name, str2ip(ipaddr), dev->mem);
+
+ /* You will be peer 1: we should create enough jitter to randomize */
+ dev->desc->features = NET_PEERNUM|LGUEST_DEVICE_F_RANDOMNESS;
+ verbose("device %p@%p: tun net %u.%u.%u.%u\n", dev->desc,
+ (void *)(dev->desc->pfn * getpagesize()),
+ HIPQUAD(str2ip(ipaddr)));
+}
+
+static void setup_block_file(const char *filename,
+ struct lguest_device_desc *descs,
+ struct devices *devices)
+{
+ int fd;
+ struct device *dev;
+ off64_t *blocksize;
+ struct lguest_block_page *p;
+
+ fd = open(filename, O_RDWR|O_LARGEFILE|O_DIRECT, 0);
+ if (fd < 0)
+ err(1, "Opening %s", filename);
+
+ dev = new_device(devices, descs, LGUEST_DEVICE_T_BLOCK, 1,
+ fd, NULL, 0, handle_block_output);
+ dev->desc->features = LGUEST_DEVICE_F_RANDOMNESS;
+ blocksize = dev->priv = malloc(sizeof(*blocksize));
+ *blocksize = lseek64(fd, 0, SEEK_END);
+ p = dev->mem;
+
+ p->num_sectors = *blocksize/512;
+ verbose("device %p@%p: block %i sectors\n", dev->desc,
+ (void *)(dev->desc->pfn * getpagesize()), p->num_sectors);
+}
+
+static u32 handle_console_output(int fd, const struct iovec *iov,
+ unsigned num, struct device*dev)
+{
+ return writev(STDOUT_FILENO, iov, num);
+}
+
+static void setup_console(struct lguest_device_desc *descs,
+ struct devices *devices)
+{
+ struct device *dev;
+
+ if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
+ struct termios term = orig_term;
+ term.c_lflag &= ~(ISIG|ICANON|ECHO);
+ tcsetattr(STDIN_FILENO, TCSANOW, &term);
+ atexit(restore_term);
+ }
+
+ /* We don't currently require a page for the console. */
+ dev = new_device(devices, descs, LGUEST_DEVICE_T_CONSOLE, 0,
+ STDIN_FILENO, handle_console_input,
+ 4, handle_console_output);
+ dev->priv = malloc(sizeof(struct console_abort));
+ ((struct console_abort *)dev->priv)->count = 0;
+ verbose("device %p@%p: console\n", dev->desc,
+ (void *)(dev->desc->pfn * getpagesize()));
+}
+
+static const char *get_arg(const char *arg, const char *prefix)
+{
+ if (strncmp(arg, prefix, strlen(prefix)) == 0)
+ return arg + strlen(prefix);
+ return NULL;
+}
+
+static u32 handle_device(int fd, unsigned long dma, unsigned long addr,
+ struct devices *devices)
+{
+ struct device *i;
+ u32 *lenp;
+ struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+ unsigned num = 0;
+
+ lenp = dma2iov(dma, iov, &num);
+ if (!lenp)
+ errx(1, "Bad SEND_DMA %li for address %#lx\n", dma, addr);
+
+ for (i = devices->dev; i; i = i->next) {
+ if (i->handle_output && addr == i->watch_address) {
+ *lenp = i->handle_output(fd, iov, num, i);
+ return 0;
+ }
+ }
+ warnx("Pending dma %p, addr %p", (void *)dma, (void *)addr);
+ return 0;
+}
+
+static void handle_input(int fd, int childfd, struct devices *devices)
+{
+ struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };
+
+ for (;;) {
+ struct device *i;
+ fd_set fds = devices->infds;
+
+ if (select(devices->max_infd+1, &fds, NULL, NULL, &poll) == 0)
+ break;
+
+ for (i = devices->dev; i; i = i->next) {
+ if (i->handle_input && FD_ISSET(i->fd, &fds)) {
+ if (!i->handle_input(fd, i)) {
+ FD_CLR(i->fd, &devices->infds);
+ /* Tell child to ignore it too... */
+ write(childfd, &i->fd, sizeof(i->fd));
+ }
+ }
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long mem, pgdir, entry, initrd_size, page_offset;
+ int arg, kern_fd, fd, child, pipefd[2];
+ Elf32_Ehdr hdr;
+ struct sigaction act;
+ sigset_t sigset;
+ struct lguest_device_desc *devdescs;
+ struct devices devices;
+ struct lguest_boot_info *boot = (void *)0;
+ const char *initrd_name = NULL;
+ u32 (*load)(int, const Elf32_Ehdr *ehdr, unsigned long,
+ unsigned long *, const char *, unsigned long *,
+ unsigned long *);
+
+ if (argv[1] && strcmp(argv[1], "--verbose") == 0) {
+ verbose = true;
+ argv++;
+ argc--;
+ }
+
+ if (argc < 4)
+ errx(1, "Usage: lguest [--verbose] <mem> vmlinux "
+ "[--sharenet=<filename>|--tunnet=<ipaddr>|--block=<filename>"
+ "|--initrd=<filename>]... [args...]");
+
+ zero_fd = open("/dev/zero", O_RDONLY, 0);
+ if (zero_fd < 0)
+ err(1, "Opening /dev/zero");
+
+ mem = memparse(argv[1]);
+ kern_fd = open(argv[2], O_RDONLY, 0);
+ if (kern_fd < 0)
+ err(1, "Opening %s", argv[2]);
+
+ if (read(kern_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
+ err(1, "Reading %s elf header", argv[2]);
+
+ if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0)
+ load = map_elf;
+ else
+ load = load_bzimage;
+
+ devices.max_infd = -1;
+ devices.dev = NULL;
+ FD_ZERO(&devices.infds);
+
+ devdescs = map_pages(mem, 1);
+ arg = 3;
+ while (argv[arg] && argv[arg][0] == '-') {
+ const char *argval;
+
+ if ((argval = get_arg(argv[arg], "--sharenet=")) != NULL)
+ setup_net_file(argval, devdescs, &devices);
+ else if ((argval = get_arg(argv[arg], "--tunnet=")) != NULL)
+ setup_tun_net(argval, devdescs, &devices);
+ else if ((argval = get_arg(argv[arg], "--block=")) != NULL)
+ setup_block_file(argval, devdescs, &devices);
+ else if ((argval = get_arg(argv[arg], "--initrd=")) != NULL)
+ initrd_name = argval;
+ else
+ errx(1, "unknown arg '%s'", argv[arg]);
+ arg++;
+ }
+
+ entry = load(kern_fd, &hdr, mem, &pgdir, initrd_name, &initrd_size,
+ &page_offset);
+ setup_console(devdescs, &devices);
+
+ concat(boot->cmdline, argv+arg);
+ boot->max_pfn = mem/getpagesize();
+ boot->initrd_size = initrd_size;
+
+ act.sa_handler = wakeup;
+ sigemptyset(&act.sa_mask);
+ act.sa_flags = 0;
+ sigaction(SIGUSR1, &act, NULL);
+
+ pipe(pipefd);
+ child = fork();
+ if (child == -1)
+ err(1, "forking");
+
+ if (child == 0) {
+ close(pipefd[1]);
+ wake_parent(pipefd[0], &devices);
+ }
+ close(pipefd[0]);
+
+ sigemptyset(&sigset);
+ sigaddset(&sigset, SIGUSR1);
+ sigprocmask(SIG_BLOCK, &sigset, NULL);
+
+ /* LGUEST_GUEST_TOP defined in Makefile, just below us. */
+ fd = tell_kernel(LGUEST_GUEST_TOP/getpagesize(),
+ pgdir, entry, page_offset);
+
+ for (;;) {
+ unsigned long arr[2];
+ int readval;
+
+ sigprocmask(SIG_UNBLOCK, &sigset, NULL);
+ readval = read(fd, arr, sizeof(arr));
+ sigprocmask(SIG_BLOCK, &sigset, NULL);
+
+ switch (readval) {
+ case sizeof(arr):
+ handle_device(fd, arr[0], arr[1], &devices);
+ break;
+ case -1:
+ if (errno == EINTR)
+ break;
+ default:
+ if (errno == ENOENT) {
+ char reason[1024];
+ if (read(fd, reason, sizeof(reason)) > 0)
+ errx(1, "%s", reason);
+ }
+ err(1, "Running guest failed");
+ }
+ handle_input(fd, pipefd[1], &devices);
+ }
+}
diff -r 8806a441a0b1 Documentation/lguest/lguest.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/Documentation/lguest/lguest.txt Mon Feb 12 13:47:43 2007 +1100
@@ -0,0 +1,355 @@
+Rusty's Remarkably Unreliable Guide to Lguest
+ - or, A Young Coder's Illustrated Hypervisor
+http://lguest.ozlabs.org
+
+Lguest is designed to be a minimal hypervisor for the Linux kernel, for
+Linux developers and users to experiment with virtualization with the
+minimum of complexity. Nonetheless, it should have sufficient
+features to make it useful for specific tasks, and, of course, you are
+encouraged to fork and enhance it.
+
+Features:
+
+- Kernel module which runs in a normal kernel.
+- Simple I/O model for communication.
+- Simple program to create new guests.
+- Logo contains cute puppies: http://lguest.ozlabs.org
+
+Developer features:
+
+- Fun to hack on.
+- No ABI: being tied to a specific kernel anyway, you can change anything.
+- Many opportunities for improvement or feature implementation.
+
+Running Lguest:
+
+- You will need to configure your kernel with the following options:
+
+ CONFIG_HIGHMEM64G=n ("High Memory Support" "64GB")[1]
+ CONFIG_TUN=y/m ("Universal TUN/TAP device driver support")
+ CONFIG_EXPERIMENTAL=y ("Prompt for development and/or incomplete code/drivers")
+ CONFIG_PARAVIRT=y ("Paravirtualization support (EXPERIMENTAL)")
+ CONFIG_LGUEST=y/m ("Linux hypervisor example code")
+
+ and I recommend:
+ CONFIG_HZ=100 ("Timer frequency")[2]
+
+ You must have a machine with a TSC: look for "tsc" in /proc/cpuinfo.
+ It's simple to remove this restriction, but everyone has a TSC these
+ days.
+
+- A tool called "lguest" is available in this directory: type "make"
+ to build it.
+
+- Create or find a root disk image. There are several useful ones
+ around, such as the xm-test tiny root image at
+ http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img
+
+ For more serious work, I usually use a distribution ISO image and
+ install it under qemu, then make multiple copies:
+
+ dd if=/dev/zero of=rootfile bs=1M count=2048
+ qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d
+
+- "modprobe lg" if you built it as a module.
+
+- Run an lguest as root:
+
+ Documentation/lguest/lguest 64m vmlinux --tunnet=192.168.19.1 --block=rootfile root=/dev/lgba
+
+ Explanation:
+ 64m: the amount of memory to use.
+
+ vmlinux: the kernel image found in the top of your build directory. You
+ can also use a standard bzImage.
+
+ --tunnet=192.168.19.1: configures a "tap" device for networking with this
+ IP address.
+
+ --block=rootfile: a file or block device which becomes /dev/lgba
+ inside the guest.
+
+ root=/dev/lgba: this (and anything else on the command line) are
+ kernel boot parameters.
+
+- Configuring networking. I usually have the host masquerade, using
+ "iptables -t nat -o eth0 -j MASQUERADE" and "echo 1 >
+ /proc/sys/net/ipv4/ip_forward". In this example, I would configure
+ eth0 inside the guest at 192.168.19.2.
+
+- You can also create an inter-guest network using
+ "--sharenet=<filename>": any two guests using the same file are on
+ the same network. This file is created if it does not exist.
+
+
+Lguest I/O model:
+
+Lguest uses a simplified DMA model plus shared memory for I/O. Guests
+can communicate with each other if they share underlying memory
+(usually by the lguest program mmaping the same file), but they can
+use any non-shared memory to communicate with the lguest process.
+
+Guests can register DMA buffers at any physical address using the
+LHCALL_BIND_DMA(physaddr, dmabufs, num<<8|irq) hypercall. "dmabufs"
+is the physical address of an array of "num" "struct lguest_dma": each
+contains a used_len, and an array of physical addresses and lengths.
+When a transfer occurs, the "used_len" field of one of the buffers
+which has used_len 0 will be set to the length transferred and the irq
+will fire.
+
+Using an irq value of 0 unbinds the dma buffers.
+
+To send DMA, the LHCALL_SEND_DMA(physaddr, dma_physaddr) hypercall is
+used, and the bytes used is written to the used_len field. This can
+be 0 if noone else has bound a DMA buffer to that address or some
+other error. DMA buffers bound by the same guest are ignored.
+
+
+Hacking on Lguest:
+
+Lguest uses the paravirt_ops infrastructure to override various
+sensitive operations so Linux can run in ring level 1 (rather
+than 0). These operations make "hypercalls": traps into a tiny shim
+which is mapped at the top of memory which then switches back to the
+host Linux for servicing. In fact, any real interrupt and many
+traps cause a switch back to the host, which doesn't even notice that
+it was switched out. This means that the guest process is scheduled
+like any other process, although it spends most of its time in its own
+special address space.
+
+Here are the parts of the hypervisor at the moment:
+
+hypervisor.S:
+ The assembler shim which is mapped at 0xFFC01000 (-4M+1page)
+ in the host and all the guests. This is built into a .o file
+ and inserted in the source as a C array: it is simply copied
+ into the mapped memory.
+
+ The shim is entered from the host at switch_to_guest with
+ interrupts off: this saves state and switches page tables,
+ GDT, IDT, TSS and stack, then dives into the guest with an
+ iret.
+
+ There are two ways back to the host: a trap or an external
+ interrupt. A trap, such as a page fault, goes through
+ return_to_host, which simply switches back and irets to the
+ caller (init.c's lcall), which decides what to do. For an
+ interrupt we call deliver_to_host, which switches to the host
+ then jumps straight to the host interrupt routine: the
+ interrupt routine will do an "iret" at some stage, which, now
+ we've switched stacks, will return to the caller in init.c.
+
+page_tables.c:
+ We cannot let guests control their own pagetables, since they
+ must not access others' memory and their concept of physical
+ addresses is not related to the real physical addresses: the
+ guest "physical" addresses are in fact virtual addresses in
+ the host's lguest thread. The process of mapping the two
+ can be fairly complicated.
+
+ We keep up to 4 cached page tables. When a page is referred
+ to by these guest "shadow" pagetables, we keep a reference to
+ it to prevent the Linux kernel from thinking it is unused and
+ paging it out underneath us.
+ FIXME: it would be much better to have a callback in mm_struct.
+
+ The main work is done in page_in. First we check the
+ top-level guest page table: if that entry is not present, then
+ it's a real guest fault and we reflect it to the guest.
+ Otherwise, we check the real top level, and allocate a new
+ pagetable page if necessary. Then we check the next level of
+ the guest page table: if that isn't present, or this was a
+ write and the guest entry is read only, we reflect it to the
+ guest. Otherwise, we check the guest entry, convert the page
+ number to the actual physical page number, then set it in our
+ page table. At this point we also update the accessed and
+ dirty bits in the guest.
+
+ So a guest's top-level pagetable starts empty, and over time
+ we fault more pages in. If the guest switches page tables, we
+ see if it's in out 4-entry cache: if not, we clear the
+ non-kernel section of one of them and use that. (The kernel
+ page table entries will always be the same in all top levels).
+
+ We have to keep the stack pages for the guest kernel mapped at
+ all times, since we point some traps (particularly system
+ calls) directly into the guest. If the stack were not mapped
+ we would get a double fault, which means we kill the guest.
+
+ Note that there are three page tables for each guest: the
+ Linux host ones which exist for lguest just like any other
+ process, the actual ones used when we switch to running the
+ guest, and the ones inside the guest which it thinks it's
+ using (and we copy to the actual ones after checking).
+
+hypercalls.c:
+ This is where the guest used int 0x1F to ask the hypervisor
+ for something. The first hypercall is always
+ LHCALL_LGUEST_INIT, which tells us where the "struct
+ lguest_page" is. We populate the lguest_page with useful
+ information, and it's also used to indicate virtual interrupts
+ and whether the guest expects interrupts to be disabled.
+
+ Most of these calls are fairly self-explanatory, or covered
+ elsewhere. Note that LHCALL_CRASH allows a guest to get a
+ message out before any devices are enabled, which can be
+ useful for debugging.
+
+ do_async_hypercalls: a ringbuffer in the lguest page allows
+ the guest to queue hypercalls for later execution. This is
+ useful for hypercall batching during context switch, and for
+ some bulk I/O. The return value of the hypercall is
+ discarded, so it doesn't make sense to batch some hypercalls.
+ Note that we always do all these "async" calls before any
+ normal hypercall, which means that any hypercall acts as a
+ flush operation. The only trick is that an async SEND_DMA
+ hypercall may need to be serviced by the host userspace; the
+ run_guest loop is constructed so that we continue servicing
+ hypercalls when we re-enter the loop after host userspace has
+ done the I/O operation.
+
+ setup_trampoline: this populates a stub for direct traps to
+ the guest. Using a trampoline page (which sits just below the
+ hypervisor at -4M) ensures that the page is always mapped, and
+ also ensures that we reload the %gs register before entering the
+ kernel (see guest_load_tls).
+
+io.c:
+ lguest provides DMA-style transfer, and buffer registration.
+ The guest can dma send to a particular address, or register a
+ set of DMA buffers at a particular address. This provides
+ inter-guest I/O (for shared addresses, such as a shared mmap)
+ or I/O out to the userspace process (lguest).
+
+ We currently use the futex infrastructure to see if a given
+ address is shared: if it is, we look for another guest which
+ has registered a DMA buffer at this address and copy the data,
+ then interrupt the recipient. Otherwise, we notify the guest
+ userspace (which has access to all the guest memory) to handle
+ the transfer.
+
+ TODO: We could flip whole pages between guests at this point
+ if we wanted to, however it seems unlikely to be worthwhile.
+ More optimization could be gained by having servers for certain
+ devices within the host kernel itself, avoiding at
+ least two switches into the lguest binary and back.
+
+core.c:
+ This contains the core of lguest, "run_guest", which
+ continuously lcalls into the switch_to_guest routine until
+ something interesting happens. In particular, we only return
+ to userspace (ie. "lguest") when a signal occurs or the guest
+ does a SEND_DMA destined for host userspace.
+
+ emulate_insn(): we don't paravirtualize io and out
+ instructions, so we trap and emulate them here. This is only
+ used when the guest is booting and probing for PCI busses,
+ etc.
+
+ lguest_address_ok(): the guest kernel must not be able to
+ access the lguest binary, otherwise it could break out of
+ its virtualization, so all dereferences must use the
+ lhread_u32/lhwrite_u32/lhread/lhwrite routines which check
+ this.
+
+ reflect_trap(): when we decide that the guest should handle a
+ trap (a page fault, a general protection fault, an FPU fault
+ or a virtual interrupt), we manually push a trap frame onto
+ its stack as it expects it to be. There are two kinds of
+ traps for x86: interrupt gates expect to have interrupts
+ disabled, and trap gates expect interrupts to be left alone.
+ The guest will restore interrupts in lguest_iret.
+
+ Of course, we don't actually let the guest disable interrupts,
+ just prevent us from delivering interupts to that guest (the
+ flag "irq_enabled" in the lguest_page).
+
+ kill_guest: this is used when an error occurs which can only
+ be caused by the guest kernel. You can continue as normal
+ after this: the guest will exit when it returns to run_thread.
+
+ fixup_gdt_table: we protect the hypervisor shim from being
+ accessed using segments, so we have to trim segments the guest
+ uses to exclude the hypervisor. The shim itself uses two
+ segments (only accessible to ring 0) which map the entire
+ memory range, and we use our own TSS entry.
+
+ guest_load_tls: glibc implements __thread using
+ thread-local-storage segments. These segments start at a
+ different offset for each thread, and cover the entire 4GB
+ address space. glibc then uses huge offsets into this segment
+ to wrap around and access variables below that offset.
+ Unfortunately, we cannot allow this in general, as this would
+ allow access to the hypervisor shim! Fortunately, x86 page
+ table entries contain a "user" bit, which when cleared makes
+ pages inaccessible to ring level 3. We clear this bit for the
+ pagetable entries mapping the hypervisor, so we can allow ring
+ 3 (ie. userspace) access to 4G segments. If the guest is in
+ ring 3, we setup the segment limits at the full 4G just before
+ calling into hypervisor.S. It will reload %gs, then truncate
+ these TLS segments to a single page. This ensures that any
+ reload of gs gets the truncated segments. As the guest
+ userspace will also load %gs itself, we ignore the first
+ protection fault that occurs at any given address in userspace
+ (assuming it's caused by use of the truncated segment). As
+ all traps reload gs explicitly (trampoline page) or implicitly
+ (reflect_trap), they all must reset the pointer to the
+ last-detected faulting instruction, as they will fault again.
+
+device.c:
+ This contains the host userspace interface code (ie. /dev/lguest).
+
+ The read and write routines are where the userspace program
+ lguest starts and performs I/O to the guest. The initial
+ write supplies the number of memory pages, the access limit
+ (which is used to ensure the guest doesn't overwrite the
+ lguest binary which sits above this address), the initial
+ guest pagetable top, and the address to jump into the guest
+ image. Reading from the file causes the guest to run until a
+ signal or I/O is pending.
+
+lguest_bus.c:
+ A simple bus which sits in the lguest_page and indicates what
+ devices are available. Using the interrupt model it would be
+ easy to make this dynamic.
+
+drivers/net/lguest_net.c:
+ A simple network device, which (invisible to the guest) can be
+ shared between several guests or simply talk to the lguest
+ process. There is only one unusual element: the sender
+ needs to find the packet destination.
+
+ We manually scan the shared page for mac addresses to decide
+ where to send a packet. We overload an unusable bit in that
+ mac address to indicate promiscuous mode (so the sender knows
+ to send a copy of all packets to that recipient).
+
+drivers/char/hvc_lguest.c:
+ A simple console. It could use a shared page as a ringbuffer
+ and merely use the dma mechanism for notifications, but using
+ DMA directly is less code.
+
+ TODO: The console input can be flooded if it doesn't service
+ fast enough, and will lose characters. If this is a problem,
+ switch to ringbuffer or use multiple DMA buffers and define an
+ ordering.
+
+drivers/block/lguest_blk.c:
+ A simple block device. It's actually overkill for the current
+ use: talking to the userspace side is synchronous, but this allows
+ it to be served by something else in future.
+
+arch/i386/kernel/lguest.c:
+ The guest paravirt_ops implementation. The only complexity is
+ in the implementation of lguest_iret: we need to restore the
+ interrupt state and return from the interrupt atomically. To
+ this end, we tell the hypervisor that it is not to interrupt
+ us in those instructions between the restoration (usually
+ enabling) of interrupts and the actual "iret".
+
+Cheers!
+Rusty Russell rusty@...tcorp.com.au.
+
+[1] These are on various places on the TODO list, waiting for you to
+ get annoyed enough at the limitation to fix it.
+[2] Lguest is not yet tickless when idle. See [1].
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists