#include <zlib.h>
#include <assert.h>
#include <sched.h>
-/*L:110 We can ignore the 30 include files we need for this program, but I do
+#include "linux/lguest_launcher.h"
+#include "linux/virtio_config.h"
+#include "linux/virtio_net.h"
+#include "linux/virtio_blk.h"
+#include "linux/virtio_console.h"
+#include "linux/virtio_ring.h"
+#include "asm-x86/bootparam.h"
+/*L:110 We can ignore the 38 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 and the header we need uses them, so we define them
- * here.
- */
+ * 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;
-#include "linux/lguest_launcher.h"
-#include "linux/pci_ids.h"
-#include "linux/virtio_config.h"
-#include "linux/virtio_net.h"
-#include "linux/virtio_blk.h"
-#include "linux/virtio_console.h"
-#include "linux/virtio_ring.h"
-#include "asm-x86/e820.h"
/*:*/
#define PAGE_PRESENT 0x7 /* Present, RW, Execute */
return addr;
}
-/* To find out where to start we look for the magic Guest string, which marks
- * the code we see in lguest_asm.S. This is a hack which we are currently
- * plotting to replace with the normal Linux entry point. */
-static unsigned long entry_point(const void *start, const void *end)
-{
- const void *p;
-
- /* The scan gives us the physical starting address. We boot with
- * pagetables set up with virtual and physical the same, so that's
- * OK. */
- for (p = start; p < end; p++)
- if (memcmp(p, "GenuineLguest", strlen("GenuineLguest")) == 0)
- return to_guest_phys(p + strlen("GenuineLguest"));
-
- errx(1, "Is this image a genuine lguest?");
-}
-
/* 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. */
* We return the starting address. */
static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
{
- void *start = (void *)-1, *end = NULL;
Elf32_Phdr phdr[ehdr->e_phnum];
unsigned int i;
verbose("Section %i: size %i addr %p\n",
i, phdr[i].p_memsz, (void *)phdr[i].p_paddr);
- /* We track the first and last address we mapped, so we can
- * tell entry_point() where to scan. */
- if (from_guest_phys(phdr[i].p_paddr) < start)
- start = from_guest_phys(phdr[i].p_paddr);
- if (from_guest_phys(phdr[i].p_paddr) + phdr[i].p_filesz > end)
- end=from_guest_phys(phdr[i].p_paddr)+phdr[i].p_filesz;
-
/* 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);
}
- return entry_point(start, end);
-}
-
-/*L:160 Unfortunately the entire ELF image isn't compressed: the segments
- * which need loading are extracted and compressed raw. This denies us the
- * information we need to make a fully-general loader. */
-static unsigned long unpack_bzimage(int fd)
-{
- gzFile f;
- int ret, len = 0;
- /* A bzImage always gets loaded at physical address 1M. This is
- * actually configurable as CONFIG_PHYSICAL_START, but as the comment
- * there says, "Don't change this unless you know what you are doing".
- * Indeed. */
- void *img = from_guest_phys(0x100000);
-
- /* gzdopen takes our file descriptor (carefully placed at the start of
- * the GZIP header we found) and returns a gzFile. */
- f = gzdopen(fd, "rb");
- /* We read it into memory in 64k chunks until we hit the end. */
- 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);
-
- return entry_point(img, img + len);
+ /* 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 can't do that
- * because the Guest can't run the unpacking code, and adding features to
- * lguest kills puppies, so we don't want to.
+ * 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.
*
- * The bzImage is formed by putting the decompressing code in front of the
- * compressed kernel code. So we can simple scan through it looking for the
- * first "gzip" header, and start decompressing from there. */
+ * 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)
{
- unsigned char c;
- int state = 0;
-
- /* GZIP header is 0x1F 0x8B <method> <flags>... <compressed-by>. */
- while (read(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:
- /* Seek back to the start of the gzip header. */
- lseek(fd, -10, SEEK_CUR);
- /* One final check: "compressed under UNIX". */
- if (c != 0x03)
- state = -1;
- else
- return unpack_bzimage(fd);
- }
- }
- errx(1, "Could not find kernel in bzImage");
+ 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/i386/boot.txt) */
+ lseek(fd, 0, SEEK_SET);
+ read(fd, &boot, sizeof(boot));
+
+ /* Inside the setup_hdr, we expect the magic "HdrS" */
+ if (memcmp(&boot.hdr.header, "HdrS", 4) != 0)
+ errx(1, "This doesn't look like a bzImage to me");
+
+ /* Skip over the extra sectors of the header. */
+ lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET);
+
+ /* Now read everything into memory. in nice big chunks. */
+ while ((r = read(fd, p, 65536)) > 0)
+ p += r;
+
+ /* Finally, code32_start tells us where to enter the kernel. */
+ return boot.hdr.code32_start;
}
/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels
- * come wrapped up in the self-decompressing "bzImage" format. With some funky
- * coding, we can load those, too. */
+ * 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;
* to know where it is. */
return to_guest_phys(pgdir);
}
+/*:*/
/* Simple routine to roll all the commandline arguments together with spaces
* between them. */
dst[len] = '\0';
}
-/* 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, the
+/*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, the
* top level pagetable and the entry point for the Guest. */
static int tell_kernel(unsigned long pgdir, unsigned long start)
{
/*L:200
* The Waker.
*
- * With a console and network devices, we can have lots of input which we need
- * to process. We could try to tell the kernel what file descriptors to watch,
- * but handing a file descriptor mask through to the kernel is fairly icky.
+ * With console, block and network devices, we can have lots of input which we
+ * need to process. We could try to tell the kernel what file descriptors to
+ * watch, but handing a file descriptor mask through to the kernel is fairly
+ * icky.
*
* Instead, we fork off a process which watches the file descriptors and writes
- * the LHREQ_BREAK command to the /dev/lguest filedescriptor to tell the Host
- * loop to stop running the Guest. This causes it to return from the
+ * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
+ * stop running the Guest. This causes the Launcher to return from the
* /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
* the LHREQ_BREAK and wake us up again.
*
select(devices.max_infd+1, &rfds, NULL, NULL, NULL);
/* Is it a message from the Launcher? */
if (FD_ISSET(pipefd, &rfds)) {
- int ignorefd;
+ int fd;
/* If read() returns 0, it means the Launcher has
* exited. We silently follow. */
- if (read(pipefd, &ignorefd, sizeof(ignorefd)) == 0)
+ if (read(pipefd, &fd, sizeof(fd)) == 0)
exit(0);
- /* Otherwise it's telling us there's a problem with one
- * of the devices, and we should ignore that file
- * descriptor from now on. */
- FD_CLR(ignorefd, &devices.infds);
+ /* Otherwise it's telling us to change what file
+ * descriptors we're to listen to. Positive means
+ * listen to a new one, negative means stop
+ * listening. */
+ if (fd >= 0)
+ FD_SET(fd, &devices.infds);
+ else
+ FD_CLR(-fd - 1, &devices.infds);
} else /* Send LHREQ_BREAK command. */
write(lguest_fd, args, sizeof(args));
}
{
int pipefd[2], child;
- /* We create a pipe to talk to the waker, and also so it knows when the
+ /* We create a pipe to talk to the Waker, and also so it knows when the
* Launcher dies (and closes pipe). */
pipe(pipefd);
child = fork();
err(1, "forking");
if (child == 0) {
- /* Close the "writing" end of our copy of the pipe */
+ /* We are the Waker: close the "writing" end of our copy of the
+ * pipe and start waiting for input. */
close(pipefd[1]);
wake_parent(pipefd[0], lguest_fd);
}
return pipefd[1];
}
-/*L:210
+/*
* Device Handling.
*
- * When the Guest sends DMA to us, it sends us an array of addresses and sizes.
+ * 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 check it and exits with an error message
+ * 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,
/* A macro which transparently hands the line number to the real function. */
#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
-/* This simply sets up an iovec array where we can put data to be discarded.
- * This happens when the Guest doesn't want or can't handle the input: we have
- * to get rid of it somewhere, and if we bury it in the ceiling space it will
- * start to smell after a week. */
-static void discard_iovec(struct iovec *iov, unsigned int *num)
-{
- static char discard_buf[1024];
- *num = 1;
- iov->iov_base = discard_buf;
- iov->iov_len = sizeof(discard_buf);
-}
-
-/* This function returns the next descriptor in the chain, or vq->vring.num. */
+/* 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 virtqueue *vq, unsigned int i)
{
unsigned int next;
return head;
}
-/* Once we've used one of their buffers, we tell them about it. We'll then
+/* 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;
- /* Get a pointer to the next entry in the 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;
{
unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
+ /* If they don't want an interrupt, don't send one. */
if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
return;
trigger_irq(fd, vq);
}
-/* Here is the input terminal setting we save, and the routine to restore them
- * on exit so the user can see what they type next. */
+/*
+ * The Console
+ *
+ * Here is the input terminal setting we save, and the routine to restore them
+ * on exit so the user gets their terminal back. */
static struct termios orig_term;
static void restore_term(void)
{
/* First we need a console buffer from the Guests's input virtqueue. */
head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
- if (head == dev->vq->vring.num) {
- /* If they're not ready for input, we warn and set up to
- * discard. */
- warnx("console: no dma buffer!");
- discard_iovec(iov, &in_num);
- } else if (out_num)
+
+ /* If they're not ready for input, stop listening to this file
+ * descriptor. We'll start again once they add an input buffer. */
+ if (head == dev->vq->vring.num)
+ return false;
+
+ if (out_num)
errx(1, "Output buffers in console in queue?");
/* This is why we convert to iovecs: the readv() call uses them, and so
/* This implies that the console is closed, is /dev/null, or
* something went terribly wrong. */
warnx("Failed to get console input, ignoring console.");
- /* Put the input terminal back and return failure (meaning,
- * don't call us again). */
+ /* Put the input terminal back. */
restore_term();
+ /* Remove callback from input vq, so it doesn't restart us. */
+ dev->vq->handle_output = NULL;
+ /* Stop listening to this fd: don't call us again. */
return false;
}
- /* If we actually read the data into the Guest, tell them about it. */
- if (head != dev->vq->vring.num)
- add_used_and_trigger(fd, dev->vq, head, len);
+ /* Tell the Guest about the new input. */
+ add_used_and_trigger(fd, dev->vq, head, len);
/* Three ^C within one second? Exit.
*
}
}
-/* Handling output for network is also simple: we get all the output buffers
+/*
+ * The Network
+ *
+ * Handling output for network is also simple: we get all the output buffers
* and write them (ignoring the first element) to this device's file descriptor
* (stdout). */
static void handle_net_output(int fd, struct virtqueue *vq)
while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
if (in)
errx(1, "Input buffers in output queue?");
- /* Check header, but otherwise ignore it (we said we supported
- * no features). */
+ /* Check header, but otherwise ignore it (we told the Guest we
+ * supported no features, so it shouldn't have anything
+ * interesting). */
(void)convert(&iov[0], struct virtio_net_hdr);
len = writev(vq->dev->fd, iov+1, out-1);
add_used_and_trigger(fd, vq, head, len);
/* FIXME: Actually want DRIVER_ACTIVE here. */
if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
warn("network: no dma buffer!");
- discard_iovec(iov, &in_num);
+ /* We'll turn this back on if input buffers are registered. */
+ return false;
} else if (out_num)
errx(1, "Output buffers in network recv queue?");
if (len <= 0)
err(1, "reading network");
- /* If we actually read the data into the Guest, tell them about it. */
- if (head != dev->vq->vring.num)
- add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);
+ /* Tell the Guest about the new packet. */
+ add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);
verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
return true;
}
+/*L:215 This is the callback attached to the network and console input
+ * virtqueues: it ensures we try again, in case we stopped console or net
+ * delivery because Guest didn't have any buffers. */
+static void enable_fd(int fd, struct virtqueue *vq)
+{
+ add_device_fd(vq->dev->fd);
+ /* Tell waker to listen to it again */
+ write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+}
+
/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
static void handle_output(int fd, unsigned long addr)
{
strnlen(from_guest_phys(addr), guest_limit - addr));
}
-/* This is called when the waker wakes us up: check for incoming file
+/* This is called when the Waker wakes us up: check for incoming file
* descriptors. */
static void handle_input(int fd)
{
* file descriptors and a method of handling them. */
for (i = devices.dev; i; i = i->next) {
if (i->handle_input && FD_ISSET(i->fd, &fds)) {
+ int dev_fd;
+ if (i->handle_input(fd, i))
+ continue;
+
/* If handle_input() returns false, it means we
- * should no longer service it.
- * handle_console_input() does this. */
- if (!i->handle_input(fd, i)) {
- /* Clear it from the set of input file
- * descriptors kept at the head of the
- * device list. */
- FD_CLR(i->fd, &devices.infds);
- /* Tell waker to ignore it too... */
- write(waker_fd, &i->fd, sizeof(i->fd));
- }
+ * should no longer service it. Networking and
+ * console do this when there's no input
+ * buffers to deliver into. Console also uses
+ * it when it discovers that stdin is
+ * closed. */
+ FD_CLR(i->fd, &devices.infds);
+ /* Tell waker to ignore it too, by sending a
+ * negative fd number (-1, since 0 is a valid
+ * FD number). */
+ dev_fd = -i->fd - 1;
+ write(waker_fd, &dev_fd, sizeof(dev_fd));
}
}
}
}
/* Each device descriptor is followed by some configuration information.
- * The first byte is a "status" byte for the Guest to report what's happening.
- * After that are fields: u8 type, u8 len, [... len bytes...].
+ * Each configuration field looks like: u8 type, u8 len, [... len bytes...].
*
* This routine adds a new field to an existing device's descriptor. It only
* works for the last device, but that's OK because that's how we use it. */
/* Link virtqueue back to device. */
vq->dev = dev;
- /* Set up handler. */
+ /* Set the routine to call when the Guest does something to this
+ * virtqueue. */
vq->handle_output = handle_output;
+
+ /* Set the "Don't Notify Me" flag if we don't have a handler */
if (!handle_output)
vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
}
/* This routine does all the creation and setup of a new device, including
- * caling new_dev_desc() to allocate the descriptor and device memory. */
+ * calling new_dev_desc() to allocate the descriptor and device memory. */
static struct device *new_device(const char *name, u16 type, int fd,
bool (*handle_input)(int, struct device *))
{
/* 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/lgba, etc. */
+ * is eth0, the first block device /dev/vda, etc. */
*devices.lastdev = dev;
dev->next = NULL;
devices.lastdev = &dev->next;
dev->priv = malloc(sizeof(struct console_abort));
((struct console_abort *)dev->priv)->count = 0;
- /* The console needs two virtqueues: the input then the output. We
- * don't care when they refill the input queue, since we don't hold
- * data waiting for them. That's why the input queue's callback is
- * NULL. */
- add_virtqueue(dev, VIRTQUEUE_NUM, NULL);
+ /* 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. */
+ add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);
verbose("device %u: console\n", devices.device_num++);
/* First we create a new network device. */
dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
- /* Network devices need a receive and a send queue. */
- add_virtqueue(dev, VIRTQUEUE_NUM, NULL);
+ /* Network devices need a receive and a send queue, just like
+ * console. */
+ add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
/* We need a socket to perform the magic network ioctls to bring up the
verbose("attached to bridge: %s\n", br_name);
}
-
-/*
- * Block device.
- *
- * Serving a block device is really easy: the Guest asks for a block number and
- * we read or write that position in the file.
+/* 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.
*
- * Unfortunately, this is amazingly slow: the Guest waits until the read is
- * finished before running anything else, even if it could be 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.
+ * 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. */
-/* This hangs off device->priv, with the data. */
+/* This hangs off device->priv. */
struct vblk_info
{
/* The size of the file. */
* Launcher triggers interrupt to Guest. */
int done_fd;
};
+/*:*/
-/* This is the core of the I/O thread. It returns true if it did something. */
+/*L:210
+ * The Disk
+ *
+ * Remember that the block device is handled by a separate I/O thread. We head
+ * straight into the core of that thread here:
+ */
static bool service_io(struct device *dev)
{
struct vblk_info *vblk = dev->priv;
struct iovec iov[dev->vq->vring.num];
off64_t off;
+ /* See if there's a request waiting. If not, nothing to do. */
head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
if (head == dev->vq->vring.num)
return false;
+ /* 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). */
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], struct virtio_blk_inhdr);
off = out->sector * 512;
- /* This is how we implement barriers. Pretty poor, no? */
+ /* 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? */
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. */
if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
fprintf(stderr, "Scsi commands unsupported\n");
in->status = VIRTIO_BLK_S_UNSUPP;
/* When this read fails, it means Launcher died, so we follow. */
while (read(vblk->workpipe[0], &c, 1) == 1) {
- /* We acknowledge each request immediately, to reduce latency,
+ /* We acknowledge each request immediately to reduce latency,
* rather than waiting until we've done them all. I haven't
* measured to see if it makes any difference. */
while (service_io(dev))
return 0;
}
-/* When the thread says some I/O is done, we interrupt the Guest. */
+/* Now we've seen the I/O thread, we return to the Launcher to see what happens
+ * when the thread tells us it's completed some I/O. */
static bool handle_io_finish(int fd, struct device *dev)
{
char c;
- /* If child died, presumably it printed message. */
+ /* If the I/O thread died, presumably it printed the error, so we
+ * simply exit. */
if (read(dev->fd, &c, 1) != 1)
exit(1);
return true;
}
-/* When the Guest submits some I/O, we wake the I/O thread. */
+/* When the Guest submits some I/O, we just need to wake the I/O thread. */
static void handle_virtblk_output(int fd, struct virtqueue *vq)
{
struct vblk_info *vblk = vq->dev->priv;
exit(1);
}
-/* This creates a virtual block device. */
+/*L:198 This actually sets up a virtual block device. */
static void setup_block_file(const char *filename)
{
int p[2];
/* The device responds to return from I/O thread. */
dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish);
- /* The device has a virtqueue. */
+ /* The device has one virtqueue, where the Guest places requests. */
add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output);
/* Allocate the room for our own bookkeeping */
/* The I/O thread writes to this end of the pipe when done. */
vblk->done_fd = p[1];
- /* This is how we tell the I/O thread about more work. */
+ /* This is the second pipe, which is how we tell the I/O thread about
+ * more work. */
pipe(vblk->workpipe);
/* Create stack for thread and run it */
char reason[1024] = { 0 };
read(lguest_fd, reason, sizeof(reason)-1);
errx(1, "%s", reason);
- /* EAGAIN means the waker wanted us to look at some input.
+ /* EAGAIN means the Waker wanted us to look at some input.
* Anything else means a bug or incompatible change. */
} else if (errno != EAGAIN)
err(1, "Running guest failed");
- /* Service input, then unset the BREAK which releases
- * the Waker. */
+ /* Service input, then unset the BREAK to release the Waker. */
handle_input(lguest_fd);
if (write(lguest_fd, args, sizeof(args)) < 0)
err(1, "Resetting break");
}
}
/*
- * This is the end of the Launcher.
+ * This is the end of the Launcher. The good news: we are over halfway
+ * through! The bad news: the most fiendish part of the code still lies ahead
+ * of us.
*
- * But wait! We've seen I/O from the Launcher, and we've seen I/O from the
- * Drivers. If we were to see the Host kernel I/O code, our understanding
- * would be complete... :*/
+ * 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' },
/* Memory, top-level pagetable, code startpoint and size of the
* (optional) initrd. */
unsigned long mem = 0, pgdir, start, initrd_size = 0;
- /* A temporary and the /dev/lguest file descriptor. */
+ /* Two temporaries and the /dev/lguest file descriptor. */
int i, c, lguest_fd;
/* The boot information for the Guest. */
- void *boot;
+ struct boot_params *boot;
/* If they specify an initrd file to load. */
const char *initrd_name = NULL;
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. */
- *(unsigned long *)(boot+0x218) = mem - initrd_size;
- *(unsigned long *)(boot+0x21c) = initrd_size;
+ boot->hdr.ramdisk_image = mem - initrd_size;
+ boot->hdr.ramdisk_size = initrd_size;
/* The bootloader type 0xFF means "unknown"; that's OK. */
- *(unsigned char *)(boot+0x210) = 0xFF;
+ boot->hdr.type_of_loader = 0xFF;
}
/* Set up the initial linear pagetables, starting below the initrd. */
/* The Linux boot header contains an "E820" memory map: ours is a
* simple, single region. */
- *(char*)(boot+E820NR) = 1;
- *((struct e820entry *)(boot+E820MAP))
- = ((struct e820entry) { 0, mem, E820_RAM });
+ 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 (at address 4096) */
- *(u32 *)(boot + 0x228) = 4096;
- concat(boot + 4096, argv+optind+2);
+ * 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);
+
+ /* Boot protocol version: 2.07 supports the fields for lguest. */
+ boot->hdr.version = 0x207;
+
+ /* The hardware_subarch value of "1" tells the Guest it's an lguest. */
+ boot->hdr.hardware_subarch = 1;
- /* The guest type value of "1" tells the Guest it's under lguest. */
- *(int *)(boot + 0x23c) = 1;
+ /* 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. */