lguest: move the lguest tool to the tools directory

This is a better location instead of having it in Documentation.

Signed-off-by: Davidlohr Bueso <dave@gnu.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (fixed compile)

5 files changed, 2261 insertions, 0 deletions

diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore
new file mode 100644
index 000000000000..115587fd5f65
--- /dev/null
+++ b/tools/lguest/.gitignore
@@ -0,0 +1 @@
+lguest
diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile
new file mode 100644
index 000000000000..0ac34206f7a7
--- /dev/null
+++ b/tools/lguest/Makefile
@@ -0,0 +1,8 @@
+# This creates the demonstration utility "lguest" which runs a Linux guest.
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
+
+all: lguest
+
+clean:
+	rm -f lguest
diff --git a/tools/lguest/extract b/tools/lguest/extract
new file mode 100644
index 000000000000..7730bb6e4b94
--- /dev/null
+++ b/tools/lguest/extract
@@ -0,0 +1,58 @@
+#! /bin/sh
+
+set -e
+
+PREFIX=$1
+shift
+
+trap 'rm -r $TMPDIR' 0
+TMPDIR=`mktemp -d`
+
+exec 3>/dev/null
+for f; do
+    while IFS="
+" read -r LINE; do
+	case "$LINE" in
+	    *$PREFIX:[0-9]*:\**)
+		NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
+		if [ -f $TMPDIR/$NUM ]; then
+		    echo "$TMPDIR/$NUM already exits prior to $f"
+		    exit 1
+		fi
+		exec 3>>$TMPDIR/$NUM
+		echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
+		/bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3
+		;;
+	    *$PREFIX:[0-9]*)
+		NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
+		if [ -f $TMPDIR/$NUM ]; then
+		    echo "$TMPDIR/$NUM already exits prior to $f"
+		    exit 1
+		fi
+		exec 3>>$TMPDIR/$NUM
+		echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
+		/bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3
+		;;
+	    *:\**)
+		/bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3
+		echo >&3
+		exec 3>/dev/null
+		;;
+	    *)
+		/bin/echo "$LINE" >&3
+		;;
+	esac
+    done < $f
+    echo >&3
+    exec 3>/dev/null
+done
+
+LASTFILE=""
+for f in $TMPDIR/*; do
+    if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then
+	LASTFILE=$(cat $TMPDIR/.$(basename $f) )
+	echo "[ $LASTFILE ]"
+    fi
+    cat $f
+done
+
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
new file mode 100644
index 000000000000..f759f4f097c7
--- /dev/null
+++ b/tools/lguest/lguest.c
@@ -0,0 +1,2065 @@
+/*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 <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"
+/*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;
+/*:*/
+
+#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 mb() __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 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);
+
+	/*
+	 * 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;
+
+	/*
+	 * 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, 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)
+{