static void handle_output(unsigned long addr)
{
struct device *i;
for (i = devices.dev; i; i = i->next) {
struct virtqueue *vq;
if (from_guest_phys(addr) == i->desc) {
update_device_status(i);
return;
}
for (vq = i->vq; vq; vq = vq->next) {
if (addr != vq->config.pfn*getpagesize())
continue;
errx(1, "Notification on %s before setup!", i->name);
}
}
if (addr >= guest_limit)
errx(1, "Bad NOTIFY %#lx", addr);
write(STDOUT_FILENO, from_guest_phys(addr),
strnlen(from_guest_phys(addr), guest_limit - addr));
}
static void *_check_pointer(unsigned long addr, unsigned int size,
unsigned int line)
{
if ((addr + size) > guest_limit || (addr + size) < addr)
errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
return from_guest_phys(addr);
}
/*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;
}
static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
{
Elf32_Phdr phdr[ehdr->e_phnum];
unsigned int i;
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");
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);
map_at(elf_fd, from_guest_phys(phdr[i].p_paddr),
phdr[i].p_offset, phdr[i].p_filesz);
}
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;
}
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;
}
/*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);
}
/*L:215
* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. In
* particular, it's used to notify us of device status changes during boot.
*/
static void handle_output(unsigned long addr)
{
struct device *i;
/* Check each device. */
for (i = devices.dev; i; i = i->next) {
struct virtqueue *vq;
/*
* Notifications to device descriptors mean they updated the
* device status.
*/
if (from_guest_phys(addr) == i->desc) {
update_device_status(i);
return;
}
/* Devices should not be used before features are finalized. */
for (vq = i->vq; vq; vq = vq->next) {
if (addr != vq->config.pfn*getpagesize())
continue;
errx(1, "Notification on %s before setup!", i->name);
}
}
/*
* Early console write is done using notify on a nul-terminated string
* in Guest memory. It's also great for hacking debugging messages
* into a Guest.
*/
if (addr >= guest_limit)
errx(1, "Bad NOTIFY %#lx", addr);
write(STDOUT_FILENO, from_guest_phys(addr),
strnlen(from_guest_phys(addr), guest_limit - addr));
}
/*
* 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;
}
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);
if (fstat(ifd, &st) < 0)
err(1, "fstat() on initrd '%s'", name);
len = page_align(st.st_size);
map_at(ifd, from_guest_phys(mem - len), 0, st.st_size);
close(ifd);
verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len);
return len;
}
static unsigned long load_bzimage(int fd)
{
struct boot_params boot;
int r;
void *p = from_guest_phys(0x100000);
lseek(fd, 0, SEEK_SET);
read(fd, &boot, sizeof(boot));
if (memcmp(&boot.hdr.header, "HdrS", 4) != 0)
errx(1, "This doesn't look like a bzImage to me");
lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET);
while ((r = read(fd, p, 65536)) > 0)
p += r;
return boot.hdr.code32_start;
}
