-/*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. :*/
+/*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 "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.
+/*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. */
+ * use %llu in printf for any u64.
+ */
typedef unsigned long long u64;
typedef uint32_t u32;
typedef uint16_t u16;
/* 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. */
+/*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)
/* A single linked list of devices. */
struct device *dev;
- /* And a pointer to the last device for easy append and also for
- * configuration appending. */
+ /* And a pointer to the last device for easy append. */
struct device *lastdev;
};
/* 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
+/*
+ * 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. */
+ * in precise order.
+ */
#define wmb() __asm__ __volatile__("" : : : "memory")
#define mb() __asm__ __volatile__("" : : : "memory")
-/* Convert an iovec element to the given type.
+/*
+ * 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. */
+ * 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))
/* 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. */
+/*
+ * 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)
+ 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.
+/*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 ==
*
* 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: */
+ * "physical" addresses:
+ */
static void *from_guest_phys(unsigned long addr)
{
return guest_base + addr;
* Loading the Kernel.
*
* We start with couple of simple helper routines. open_or_die() avoids
- * error-checking code cluttering the callers: */
+ * error-checking code cluttering the callers:
+ */
static int open_or_die(const char *name, int flags)
{
int fd = open(name, flags);
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 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)
return addr;
}
-/* This routine is used to load the kernel or initrd. It tries mmap, but if
+/*
+ * 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. */
+ * 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.
+ /*
+ * 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. */
+ * Guests.
+ */
if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
return;
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
+/*
+ * 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.
*
* address. We use the physical address; the Guest will map itself to the
* virtual address.
*
- * We return the starting 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. */
+ /*
+ * 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"
+ /*
+ * An ELF executable contains an ELF header and a number of "program"
* headers which indicate which parts ("segments") of the program to
- * load where. */
+ * load where.
+ */
/* We read in all the program headers at once: */
if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
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. */
+ /*
+ * 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)
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.
+/*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! */
+ * 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;
/* 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) */
+ /*
+ * 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));
return boot.hdr.code32_start;
}
-/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels
+/*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. */
+ * work, we can load those, too.
+ */
static unsigned long load_kernel(int fd)
{
Elf32_Ehdr hdr;
return load_bzimage(fd);
}
-/* This is a trivial little helper to align pages. Andi Kleen hated it because
+/*
+ * 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. */
+ * 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.
+/*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). */
+ * 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;
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. */
+ /*
+ * 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. */
+ /*
+ * 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);
}
/*:*/
-/* Simple routine to roll all the commandline arguments together with spaces
- * between them. */
+/*
+ * 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;
dst[len] = '\0';
}
-/*L:185 This is where we actually tell the kernel to initialize the Guest. We
+/*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. */
+ * entry point for the Guest.
+ */
static void tell_kernel(unsigned long start)
{
unsigned long args[] = { LHREQ_INITIALIZE,
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. */
+ /*
+ * We have to separately check addr and addr+size, because size could
+ * be huge and addr + size might wrap around.
+ */
if (addr >= guest_limit || addr + size >= guest_limit)
errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
- /* We return a pointer for the caller's convenience, now we know it's
- * safe to use. */
+ /*
+ * 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
+/*
+ * 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. */
+ * at the end.
+ */
static unsigned next_desc(struct vring_desc *desc,
unsigned int i, unsigned int max)
{
err(1, "Triggering irq %i", vq->config.irq);
}
-/* This looks in the virtqueue and for the first available buffer, and converts
+/*
+ * This looks in the virtqueue and for the first available buffer, and converts
* it to an iovec for convenient access. Since descriptors consist of some
* number of output then some number of input descriptors, it's actually two
* iovecs, but we pack them into one and note how many of each there were.
*
- * This function returns the descriptor number found. */
+ * This function 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)
/* 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. */
+ /*
+ * 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;
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. */
+ /*
+ * 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)++;
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 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");
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 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)++;
return head;
}
-/* After we've used one of their buffers, we tell them about it. We'll then
- * want to send them an interrupt, using trigger_irq(). */
+/*
+ * After we've used one of their buffers, we tell them about it. We'll then
+ * want to send them an interrupt, using trigger_irq().
+ */
static void add_used(struct virtqueue *vq, unsigned int head, int len)
{
struct vring_used_elem *used;
- /* The virtqueue contains a ring of used buffers. Get a pointer to the
- * next entry in that used ring. */
+ /*
+ * 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;
/*
* The Console
*
- * We associate some data with the console for our exit hack. */
+ * We associate some data with the console for our exit hack.
+ */
struct console_abort
{
/* How many times have they hit ^C? */
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 simplicity, dying threads kill the whole Launcher. So
+ * just nap here.
+ */
for (;;)
pause();
}
add_used_and_trigger(vq, head, len);
- /* Three ^C within one second? Exit.
+ /*
+ * 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. */
+ * slow.
+ */
if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
abort->count = 0;
return;
return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
}
-/* This is where we handle packets coming in from the tun device to our
- * Guest. */
+/* This handles packets coming in from the tun device to our Guest. */
static void net_input(struct virtqueue *vq)
{
int len;
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! */
+/*
+ * 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 create_thread(struct virtqueue *vq)
{
- /* Create stack for thread and run it. Since stack grows
- * upwards, we point the stack pointer to the end of this
- * region. */
+ /*
+ * Create stack for thread and run it. Since the stack grows upwards,
+ * we point the stack pointer to the end of this region.
+ */
char *stack = malloc(32768);
unsigned long args[] = { LHREQ_EVENTFD,
vq->config.pfn*getpagesize(), 0 };
}
}
- /* Early console write is done using notify on a nul-terminated string
- * in Guest memory. */
+ /*
+ * Early console write is done using notify on a nul-terminated string
+ * in Guest memory. It's also great for hacking debugging messages
+ * into a Guest.
+ */
if (addr >= guest_limit)
errx(1, "Bad NOTIFY %#lx", addr);
* routines to allocate and manage them.
*/
-/* The layout of the device page is a "struct lguest_device_desc" followed by a
+/*
+ * The layout of the device page is a "struct lguest_device_desc" followed by a
* number of virtqueue descriptors, then two sets of feature bits, then an
* array of configuration bytes. This routine returns the configuration
- * pointer. */
+ * pointer.
+ */
static u8 *device_config(const struct device *dev)
{
return (void *)(dev->desc + 1)
+ dev->feature_len * 2;
}
-/* This routine allocates a new "struct lguest_device_desc" from descriptor
+/*
+ * This routine allocates a new "struct lguest_device_desc" from descriptor
* table page just above the Guest's normal memory. It returns a pointer to
- * that descriptor. */
+ * that descriptor.
+ */
static struct lguest_device_desc *new_dev_desc(u16 type)
{
struct lguest_device_desc d = { .type = type };
return memcpy(p, &d, sizeof(d));
}
-/* Each device descriptor is followed by the description of its virtqueues. We
- * specify how many descriptors the virtqueue is to have. */
+/*
+ * Each device descriptor is followed by the description of its virtqueues. We
+ * specify how many descriptors the virtqueue is to have.
+ */
static void add_virtqueue(struct device *dev, unsigned int num_descs,
void (*service)(struct virtqueue *))
{
/* Initialize the vring. */
vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
- /* Append virtqueue to this device's descriptor. We use
+ /*
+ * Append virtqueue to this device's descriptor. We use
* device_config() to get the end of the device's current virtqueues;
* we check that we haven't added any config or feature information
- * yet, otherwise we'd be overwriting them. */
+ * yet, otherwise we'd be overwriting them.
+ */
assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
memcpy(device_config(dev), &vq->config, sizeof(vq->config));
dev->num_vq++;
verbose("Virtqueue page %#lx\n", to_guest_phys(p));
- /* Add to tail of list, so dev->vq is first vq, dev->vq->next is
- * second. */
+ /*
+ * Add to tail of list, so dev->vq is first vq, dev->vq->next is
+ * second.
+ */
for (i = &dev->vq; *i; i = &(*i)->next);
*i = vq;
}
-/* The first half of the feature bitmask is for us to advertise features. The
- * second half is for the Guest to accept features. */
+/*
+ * The first half of the feature bitmask is for us to advertise features. The
+ * second half is for the Guest to accept features.
+ */
static void add_feature(struct device *dev, unsigned bit)
{
u8 *features = get_feature_bits(dev);
features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
}
-/* This routine sets the configuration fields for an existing device's
+/*
+ * This routine sets the configuration fields for an existing device's
* descriptor. It only works for the last device, but that's OK because that's
- * how we use it. */
+ * how we use it.
+ */
static void set_config(struct device *dev, unsigned len, const void *conf)
{
/* Check we haven't overflowed our single page. */
assert(dev->desc->config_len == len);
}
-/* This routine does all the creation and setup of a new device, including
+/*
+ * This routine does all the creation and setup of a new device, including
* calling new_dev_desc() to allocate the descriptor and device memory.
*
- * See what I mean about userspace being boring? */
+ * See what I mean about userspace being boring?
+ */
static struct device *new_device(const char *name, u16 type)
{
struct device *dev = malloc(sizeof(*dev));
dev->num_vq = 0;
dev->running = false;
- /* Append to device list. Prepending to a single-linked list is
+ /*
+ * Append to device list. Prepending to a single-linked list is
* easier, but the user expects the devices to be arranged on the bus
* in command-line order. The first network device on the command line
- * is eth0, the first block device /dev/vda, etc. */
+ * is eth0, the first block device /dev/vda, etc.
+ */
if (devices.lastdev)
devices.lastdev->next = dev;
else
return dev;
}
-/* Our first setup routine is the console. It's a fairly simple device, but
- * UNIX tty handling makes it uglier than it could be. */
+/*
+ * Our first setup routine is the console. It's a fairly simple device, but
+ * UNIX tty handling makes it uglier than it could be.
+ */
static void setup_console(void)
{
struct device *dev;
/* If we can save the initial standard input settings... */
if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
struct termios term = orig_term;
- /* Then we turn off echo, line buffering and ^C etc. We want a
- * raw input stream to the Guest. */
+ /*
+ * Then we turn off echo, line buffering and ^C etc: We want a
+ * raw input stream to the Guest.
+ */
term.c_lflag &= ~(ISIG|ICANON|ECHO);
tcsetattr(STDIN_FILENO, TCSANOW, &term);
}
dev->priv = malloc(sizeof(struct console_abort));
((struct console_abort *)dev->priv)->count = 0;
- /* The console needs two virtqueues: the input then the output. When
+ /*
+ * The console needs two virtqueues: the input then the output. When
* they put something the input queue, we make sure we're listening to
* stdin. When they put something in the output queue, we write it to
- * stdout. */
+ * stdout.
+ */
add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
}
/*:*/
-/*M:010 Inter-guest networking is an interesting area. Simplest is to have a
+/*M:010
+ * Inter-guest networking is an interesting area. Simplest is to have a
* --sharenet=<name> option which opens or creates a named pipe. This can be
* used to send packets to another guest in a 1:1 manner.
*
* multiple inter-guest channels behind one interface, although it would
* require some manner of hotplugging new virtio channels.
*
- * Finally, we could implement a virtio network switch in the kernel. :*/
+ * Finally, we could implement a virtio network switch in the kernel.
+:*/
static u32 str2ip(const char *ipaddr)
{
mac[5] = m[5];
}
-/* This code is "adapted" from libbridge: it attaches the Host end of the
+/*
+ * This code is "adapted" from libbridge: it attaches the Host end of the
* network device to the bridge device specified by the command line.
*
* This is yet another James Morris contribution (I'm an IP-level guy, so I
- * dislike bridging), and I just try not to break it. */
+ * dislike bridging), and I just try not to break it.
+ */
static void add_to_bridge(int fd, const char *if_name, const char *br_name)
{
int ifidx;
err(1, "can't add %s to bridge %s", if_name, br_name);
}
-/* This sets up the Host end of the network device with an IP address, brings
+/*
+ * This sets up the Host end of the network device with an IP address, brings
* it up so packets will flow, the copies the MAC address into the hwaddr
- * pointer. */
+ * pointer.
+ */
static void configure_device(int fd, const char *tapif, u32 ipaddr)
{
struct ifreq ifr;
/* Start with this zeroed. Messy but sure. */
memset(&ifr, 0, sizeof(ifr));
- /* We open the /dev/net/tun device and tell it we want a tap device. A
+ /*
+ * We open the /dev/net/tun device and tell it we want a tap device. A
* tap device is like a tun device, only somehow different. To tell
* the truth, I completely blundered my way through this code, but it
- * works now! */
+ * works now!
+ */
netfd = open_or_die("/dev/net/tun", O_RDWR);
ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
strcpy(ifr.ifr_name, "tap%d");
TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
err(1, "Could not set features for tun device");
- /* We don't need checksums calculated for packets coming in this
- * device: trust us! */
+ /*
+ * We don't need checksums calculated for packets coming in this
+ * device: trust us!
+ */
ioctl(netfd, TUNSETNOCSUM, 1);
memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
return netfd;
}
-/*L:195 Our network is a Host<->Guest network. This can either use bridging or
+/*L:195
+ * Our network is a Host<->Guest network. This can either use bridging or
* routing, but the principle is the same: it uses the "tun" device to inject
* packets into the Host as if they came in from a normal network card. We
- * just shunt packets between the Guest and the tun device. */
+ * just shunt packets between the Guest and the tun device.
+ */
static void setup_tun_net(char *arg)
{
struct device *dev;
dev = new_device("net", VIRTIO_ID_NET);
dev->priv = net_info;
- /* Network devices need a receive and a send queue, just like
- * console. */
+ /* Network devices need a recv and a send queue, just like console. */
add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
- /* We need a socket to perform the magic network ioctls to bring up the
- * tap interface, connect to the bridge etc. Any socket will do! */
+ /*
+ * We need a socket to perform the magic network ioctls to bring up the
+ * tap interface, connect to the bridge etc. Any socket will do!
+ */
ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
if (ipfd < 0)
err(1, "opening IP socket");
devices.device_num, tapif, arg);
}
-/* Our block (disk) device should be really simple: the Guest asks for a block
+/*
+ * Our block (disk) device should be really simple: the Guest asks for a block
* number and we read or write that position in the file. Unfortunately, that
* was amazingly slow: the Guest waits until the read is finished before
* running anything else, even if it could have been doing useful work.
* We could use async I/O, except it's reputed to suck so hard that characters
* actually go missing from your code when you try to use it.
*
- * So we farm the I/O out to thread, and communicate with it via a pipe. */
+ * So this was one reason why lguest now does all virtqueue servicing in
+ * separate threads: it's more efficient and more like a real device.
+ */
/* This hangs off device->priv. */
struct vblk_info
/* Get the next request. */
head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
- /* Every block request should contain at least one output buffer
+ /*
+ * Every block request should contain at least one output buffer
* (detailing the location on disk and the type of request) and one
- * input buffer (to hold the result). */
+ * input buffer (to hold the result).
+ */
if (out_num == 0 || in_num == 0)
errx(1, "Bad virtblk cmd %u out=%u in=%u",
head, out_num, in_num);
in = convert(&iov[out_num+in_num-1], u8);
off = out->sector * 512;
- /* The block device implements "barriers", where the Guest indicates
+ /*
+ * The block device implements "barriers", where the Guest indicates
* that it wants all previous writes to occur before this write. We
* don't have a way of asking our kernel to do a barrier, so we just
- * synchronize all the data in the file. Pretty poor, no? */
+ * synchronize all the data in the file. Pretty poor, no?
+ */
if (out->type & VIRTIO_BLK_T_BARRIER)
fdatasync(vblk->fd);
- /* In general the virtio block driver is allowed to try SCSI commands.
- * It'd be nice if we supported eject, for example, but we don't. */
+ /*
+ * In general the virtio block driver is allowed to try SCSI commands.
+ * It'd be nice if we supported eject, for example, but we don't.
+ */
if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
fprintf(stderr, "Scsi commands unsupported\n");
*in = VIRTIO_BLK_S_UNSUPP;
wlen = sizeof(*in);
} else if (out->type & VIRTIO_BLK_T_OUT) {
- /* Write */
-
- /* Move to the right location in the block file. This can fail
- * if they try to write past end. */
+ /*
+ * Write
+ *
+ * Move to the right location in the block file. This can fail
+ * if they try to write past end.
+ */
if (lseek64(vblk->fd, off, SEEK_SET) != off)
err(1, "Bad seek to sector %llu", out->sector);
ret = writev(vblk->fd, iov+1, out_num-1);
verbose("WRITE to sector %llu: %i\n", out->sector, ret);
- /* Grr... Now we know how long the descriptor they sent was, we
+ /*
+ * Grr... Now we know how long the descriptor they sent was, we
* make sure they didn't try to write over the end of the block
- * file (possibly extending it). */
+ * file (possibly extending it).
+ */
if (ret > 0 && off + ret > vblk->len) {
/* Trim it back to the correct length */
ftruncate64(vblk->fd, vblk->len);
wlen = sizeof(*in);
*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
} else {
- /* Read */
-
- /* Move to the right location in the block file. This can fail
- * if they try to read past end. */
+ /*
+ * Read
+ *
+ * Move to the right location in the block file. This can fail
+ * if they try to read past end.
+ */
if (lseek64(vblk->fd, off, SEEK_SET) != off)
err(1, "Bad seek to sector %llu", out->sector);
}
}
- /* OK, so we noted that it was pretty poor to use an fdatasync as a
+ /*
+ * OK, so we noted that it was pretty poor to use an fdatasync as a
* barrier. But Christoph Hellwig points out that we need a sync
* *afterwards* as well: "Barriers specify no reordering to the front
- * or the back." And Jens Axboe confirmed it, so here we are: */
+ * or the back." And Jens Axboe confirmed it, so here we are:
+ */
if (out->type & VIRTIO_BLK_T_BARRIER)
fdatasync(vblk->fd);
struct vblk_info *vblk;
struct virtio_blk_config conf;
- /* The device responds to return from I/O thread. */
+ /* Creat the device. */
dev = new_device("block", VIRTIO_ID_BLOCK);
/* The device has one virtqueue, where the Guest places requests. */
/* Tell Guest how many sectors this device has. */
conf.capacity = cpu_to_le64(vblk->len / 512);
- /* Tell Guest not to put in too many descriptors at once: two are used
- * for the in and out elements. */
+ /*
+ * Tell Guest not to put in too many descriptors at once: two are used
+ * for the in and out elements.
+ */
add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
++devices.device_num, le64_to_cpu(conf.capacity));
}
-struct rng_info {
- int rfd;
-};
-
-/* Our random number generator device reads from /dev/random into the Guest's
+/*L:211
+ * Our random number generator device reads from /dev/random into the Guest's
* input buffers. The usual case is that the Guest doesn't want random numbers
* and so has no buffers although /dev/random is still readable, whereas
* console is the reverse.
*
- * The same logic applies, however. */
+ * The same logic applies, however.
+ */
+struct rng_info {
+ int rfd;
+};
+
static void rng_input(struct virtqueue *vq)
{
int len;
if (out_num)
errx(1, "Output buffers in rng?");
- /* This is why we convert to iovecs: the readv() call uses them, and so
+ /*
+ * This is why we convert to iovecs: the readv() call uses them, and so
* it reads straight into the Guest's buffer. We loop to make sure we
- * fill it. */
+ * fill it.
+ */
while (!iov_empty(iov, in_num)) {
len = readv(rng_info->rfd, iov, in_num);
if (len <= 0)
add_used(vq, head, totlen);
}
-/* And this creates a "hardware" random number device for the Guest. */
+/*L:199
+ * This creates a "hardware" random number device for the Guest.
+ */
static void setup_rng(void)
{
struct device *dev;
struct rng_info *rng_info = malloc(sizeof(*rng_info));
+ /* Our device's privat info simply contains the /dev/random fd. */
rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
- /* The device responds to return from I/O thread. */
+ /* Create the new device. */
dev = new_device("rng", VIRTIO_ID_RNG);
dev->priv = rng_info;
{
unsigned int i;
- /* Since we don't track all open fds, we simply close everything beyond
- * stderr. */
+ /*
+ * Since we don't track all open fds, we simply close everything beyond
+ * stderr.
+ */
for (i = 3; i < FD_SETSIZE; i++)
close(i);
err(1, "Could not exec %s", main_args[0]);
}
-/*L:220 Finally we reach the core of the Launcher which runs the Guest, serves
- * its input and output, and finally, lays it to rest. */
+/*L:220
+ * Finally we reach the core of the Launcher which runs the Guest, serves
+ * its input and output, and finally, lays it to rest.
+ */
static void __attribute__((noreturn)) run_guest(void)
{
for (;;) {
*
* Are you ready? Take a deep breath and join me in the core of the Host, in
* "make Host".
- :*/
+:*/
static struct option opts[] = {
{ "verbose", 0, NULL, 'v' },
/*L:105 The main routine is where the real work begins: */
int main(int argc, char *argv[])
{
- /* Memory, top-level pagetable, code startpoint and size of the
- * (optional) initrd. */
+ /* Memory, code startpoint and size of the (optional) initrd. */
unsigned long mem = 0, start, initrd_size = 0;
/* Two temporaries. */
int i, c;
/* Save the args: we "reboot" by execing ourselves again. */
main_args = argv;
- /* First we initialize the device list. We keep a pointer to the last
+ /*
+ * First we initialize the device list. We keep a pointer to the last
* device, and the next interrupt number to use for devices (1:
- * remember that 0 is used by the timer). */
+ * remember that 0 is used by the timer).
+ */
devices.lastdev = NULL;
devices.next_irq = 1;
cpu_id = 0;
- /* We need to know how much memory so we can set up the device
+ /*
+ * We need to know how much memory so we can set up the device
* descriptor and memory pages for the devices as we parse the command
* line. So we quickly look through the arguments to find the amount
- * of memory now. */
+ * of memory now.
+ */
for (i = 1; i < argc; i++) {
if (argv[i][0] != '-') {
mem = atoi(argv[i]) * 1024 * 1024;
- /* We start by mapping anonymous pages over all of
+ /*
+ * We start by mapping anonymous pages over all of
* guest-physical memory range. This fills it with 0,
* and ensures that the Guest won't be killed when it
- * tries to access it. */
+ * tries to access it.
+ */
guest_base = map_zeroed_pages(mem / getpagesize()
+ DEVICE_PAGES);
guest_limit = mem;
usage();
}
}
- /* After the other arguments we expect memory and kernel image name,
- * followed by command line arguments for the kernel. */
+ /*
+ * After the other arguments we expect memory and kernel image name,
+ * followed by command line arguments for the kernel.
+ */
if (optind + 2 > argc)
usage();
/* Map the initrd image if requested (at top of physical memory) */
if (initrd_name) {
initrd_size = load_initrd(initrd_name, mem);
- /* These are the location in the Linux boot header where the
- * start and size of the initrd are expected to be found. */
+ /*
+ * These are the location in the Linux boot header where the
+ * start and size of the initrd are expected to be found.
+ */
boot->hdr.ramdisk_image = mem - initrd_size;
boot->hdr.ramdisk_size = initrd_size;
/* The bootloader type 0xFF means "unknown"; that's OK. */
boot->hdr.type_of_loader = 0xFF;
}
- /* The Linux boot header contains an "E820" memory map: ours is a
- * simple, single region. */
+ /*
+ * The Linux boot header contains an "E820" memory map: ours is a
+ * simple, single region.
+ */
boot->e820_entries = 1;
boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
- /* The boot header contains a command line pointer: we put the command
- * line after the boot header. */
+ /*
+ * The boot header contains a command line pointer: we put the command
+ * line after the boot header.
+ */
boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1);
/* We use a simple helper to copy the arguments separated by spaces. */
concat((char *)(boot + 1), argv+optind+2);
/* Tell the entry path not to try to reload segment registers. */
boot->hdr.loadflags |= KEEP_SEGMENTS;
- /* We tell the kernel to initialize the Guest: this returns the open
- * /dev/lguest file descriptor. */
+ /*
+ * We tell the kernel to initialize the Guest: this returns the open
+ * /dev/lguest file descriptor.
+ */
tell_kernel(start);
/* Ensure that we terminate if a child dies. */
projects / cascardo / linux.git / blobdiff