-/*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 reads repeatedly from /dev/lguest to run the Guest.
+/*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 <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 <sys/uio.h>
#include <termios.h>
#include <getopt.h>
-#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
- * want to draw attention to the use of kernel-style types.
+#include <limits.h>
+#include <stddef.h>
+#include <signal.h>
+#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_rng.h"
+#include "linux/virtio_ring.h"
+#include "asm/bootparam.h"
+/*L:110
+ * We can ignore the 42 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 */
-#define NET_PEERNUM 1
#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 fits nicely in a single 4096-byte page. */
-#define VIRTQUEUE_NUM 127
+/* 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)
/*:*/
-/* The pipe to send commands to the waker process */
-static int waker_fd;
/* 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;
-/* This is our list of devices. */
-struct device_list
-{
- /* Summary information about the devices in our list: ready to pass to
- * select() to ask which need servicing.*/
- fd_set infds;
- int max_infd;
+/* 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;
/* The descriptor page for the devices. */
u8 *descpage;
- /* The tail of the last descriptor. */
- unsigned int desc_used;
-
/* A single linked list of devices. */
struct device *dev;
- /* ... And an end pointer so we can easily append new devices */
- struct device **lastdev;
+ /* 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
-{
+struct device {
/* The linked-list pointer. */
struct device *next;
- /* The this device's descriptor, as mapped into the Guest. */
+ /* 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;
- /* If handle_input is set, it wants to be called when this file
- * descriptor is ready. */
- int fd;
- bool (*handle_input)(int fd, struct device *me);
-
/* Any queues attached to this device */
struct virtqueue *vq;
+ /* Is it operational */
+ bool running;
+
+ /* Does Guest want an intrrupt on empty? */
+ bool irq_on_empty;
+
/* Device-specific data. */
void *priv;
};
/* The virtqueue structure describes a queue attached to a device. */
-struct virtqueue
-{
+struct virtqueue {
struct virtqueue *next;
/* Which device owns me. */
/* Last available index we saw. */
u16 last_avail_idx;
- /* The routine to call when the Guest pings us. */
- void (*handle_output)(int fd, struct virtqueue *me);
+ /* 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;
};
-/* Since guest is UP and we don't run at the same time, we don't need barriers.
- * But I include them in the code in case others copy it. */
-#define wmb()
+/* Remember the arguments to the program so we can "reboot" */
+static char **main_args;
-/* Convert an iovec element to the given type.
+/* 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. */
+ * 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))
return iov->iov_base;
}
-/* 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. */
+/* 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(v32) (v64)
+#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.
+/*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)
- err(1, "Mmaping %u pages of /dev/zero", num);
+ err(1, "Mmapping %u pages of /dev/zero", num);
+
+ /*
+ * One neat mmap feature is that you can close the fd, and it
+ * stays mapped.
+ */
+ close(fd);
return addr;
}
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 isn't loadable. */
+ /*
+ * 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)
{
- u8 hdr[1024];
+ 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) */
+ /*
+ * 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, hdr, sizeof(hdr));
+ read(fd, &boot, sizeof(boot));
- /* At offset 0x202, we expect the magic "HdrS" */
- if (memcmp(hdr + 0x202, "HdrS", 4) != 0)
+ /* 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");
- /* The byte at 0x1F1 tells us how many extra sectors of
- * header: skip over them all. */
- lseek(fd, (unsigned long)(hdr[0x1F1]+1) * 512, SEEK_SET);
+ /* 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, 0x214 tells us where to start the kernel. */
- return *(unsigned long *)&hdr[0x214];
+ /* 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. */
+/*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;
if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0)
return map_elf(fd, &hdr);
- /* Otherwise we assume it's a bzImage, and try to unpack it */
+ /* 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
+/*
+ * 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);
/* We return the initrd size. */
return len;
}
+/*:*/
-/* Once we know how much memory we have, we can construct simple linear page
- * tables which set virtual == physical which will get the Guest far enough
- * into the boot to create its own.
- *
- * We lay them out of the way, just below the initrd (which is why we need to
- * know its size). */
-static unsigned long setup_pagetables(unsigned long mem,
- unsigned long initrd_size)
-{
- unsigned long *pgdir, *linear;
- unsigned int mapped_pages, i, linear_pages;
- unsigned int ptes_per_page = getpagesize()/sizeof(void *);
-
- mapped_pages = mem/getpagesize();
-
- /* Each PTE page can map ptes_per_page pages: how many do we need? */
- linear_pages = (mapped_pages + ptes_per_page-1)/ptes_per_page;
-
- /* We put the toplevel page directory page at the top of memory. */
- pgdir = from_guest_phys(mem) - initrd_size - getpagesize();
-
- /* Now we use the next linear_pages pages as pte pages */
- linear = (void *)pgdir - linear_pages*getpagesize();
-
- /* Linear mapping is easy: put every page's address into the mapping in
- * order. PAGE_PRESENT contains the flags Present, Writable and
- * Executable. */
- for (i = 0; i < mapped_pages; i++)
- linear[i] = ((i * getpagesize()) | PAGE_PRESENT);
-
- /* The top level points to the linear page table pages above. */
- for (i = 0; i < mapped_pages; i += ptes_per_page) {
- pgdir[i/ptes_per_page]
- = ((to_guest_phys(linear) + i*sizeof(void *))
- | PAGE_PRESENT);
- }
-
- verbose("Linear mapping of %u pages in %u pte pages at %#lx\n",
- mapped_pages, linear_pages, to_guest_phys(linear));
-
- /* We return the top level (guest-physical) address: the kernel needs
- * to know where it is. */
- return to_guest_phys(pgdir);
-}
-
-/* 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;
for (i = 0; args[i]; i++) {
+ if (i) {
+ strcat(dst+len, " ");
+ len++;
+ }
strcpy(dst+len, args[i]);
- strcat(dst+len, " ");
- len += strlen(args[i]) + 1;
+ len += strlen(args[i]);
}
/* In case it's empty. */
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
- * top level pagetable and the entry point for the Guest. */
-static int tell_kernel(unsigned long pgdir, unsigned long start)
+/*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(), pgdir, start };
- int fd;
-
+ guest_limit / getpagesize(), start };
verbose("Guest: %p - %p (%#lx)\n",
guest_base, guest_base + guest_limit, guest_limit);
- fd = open_or_die("/dev/lguest", O_RDWR);
- if (write(fd, args, sizeof(args)) < 0)
+ lguest_fd = open_or_die("/dev/lguest", O_RDWR);
+ if (write(lguest_fd, args, sizeof(args)) < 0)
err(1, "Writing to /dev/lguest");
-
- /* We return the /dev/lguest file descriptor to control this Guest */
- return fd;
}
/*:*/
-static void add_device_fd(int fd)
-{
- FD_SET(fd, &devices.infds);
- if (fd > devices.max_infd)
- devices.max_infd = fd;
-}
-
/*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.
- *
- * 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
- * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
- * the LHREQ_BREAK and wake us up again.
- *
- * This, of course, is merely a different *kind* of icky.
- */
-static void wake_parent(int pipefd, int lguest_fd)
-{
- /* Add the pipe from the Launcher to the fdset in the device_list, so
- * we watch it, too. */
- add_device_fd(pipefd);
-
- for (;;) {
- fd_set rfds = devices.infds;
- unsigned long args[] = { LHREQ_BREAK, 1 };
-
- /* Wait until input is ready from one of the devices. */
- select(devices.max_infd+1, &rfds, NULL, NULL, NULL);
- /* Is it a message from the Launcher? */
- if (FD_ISSET(pipefd, &rfds)) {
- int fd;
- /* If read() returns 0, it means the Launcher has
- * exited. We silently follow. */
- if (read(pipefd, &fd, sizeof(fd)) == 0)
- exit(0);
- /* Otherwise it's telling us to change what file
- * descriptors we're to listen to. */
- 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));
- }
-}
-
-/* This routine just sets up a pipe to the Waker process. */
-static int setup_waker(int lguest_fd)
-{
- int pipefd[2], child;
-
- /* 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();
- if (child == -1)
- err(1, "forking");
-
- if (child == 0) {
- /* Close the "writing" end of our copy of the pipe */
- close(pipefd[1]);
- wake_parent(pipefd[0], lguest_fd);
- }
- /* Close the reading end of our copy of the pipe. */
- close(pipefd[0]);
-
- /* Here is the fd used to talk to the waker. */
- 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,
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__)
-/* This function returns the next descriptor in the chain, or vq->vring.num. */
-static unsigned next_desc(struct virtqueue *vq, unsigned int i)
+/*
+ * 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 (!(vq->vring.desc[i].flags & VRING_DESC_F_NEXT))
- return vq->vring.num;
+ if (!(desc[i].flags & VRING_DESC_F_NEXT))
+ return max;
/* Check they're not leading us off end of descriptors. */
- next = vq->vring.desc[i].next;
+ next = desc[i].next;
/* Make sure compiler knows to grab that: we don't want it changing! */
wmb();
- if (next >= vq->vring.num)
+ if (next >= max)
errx(1, "Desc next is %u", next);
return next;
}
-/* This looks in the virtqueue and for the first available buffer, and converts
+/*
+ * 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) {
+ /* ... unless they've asked us to force one on empty. */
+ if (!vq->dev->irq_on_empty
+ || lg_last_avail(vq) != vq->vring.avail->idx)
+ 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 returns the descriptor number found, or vq->vring.num (which
- * is never a valid descriptor number) if none was found. */
-static unsigned get_vq_desc(struct virtqueue *vq,
- struct iovec iov[],
- unsigned int *out_num, unsigned int *in_num)
+ * 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;
+ 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 - vq->last_avail_idx) > vq->vring.num)
+ if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
errx(1, "Guest moved used index from %u to %u",
- vq->last_avail_idx, vq->vring.avail->idx);
+ last_avail, vq->vring.avail->idx);
- /* If there's nothing new since last we looked, return invalid. */
- if (vq->vring.avail->idx == vq->last_avail_idx)
- return vq->vring.num;
-
- /* Grab the next descriptor number they're advertising, and increment
- * the index we've seen. */
- head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num];
+ /*
+ * 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)
/* 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 = vq->vring.desc[i].len;
+ iov[*out_num + *in_num].iov_len = desc[i].len;
iov[*out_num + *in_num].iov_base
- = check_pointer(vq->vring.desc[i].addr,
- vq->vring.desc[i].len);
+ = check_pointer(desc[i].addr, desc[i].len);
/* If this is an input descriptor, increment that count. */
- if (vq->vring.desc[i].flags & VRING_DESC_F_WRITE)
+ 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)++;
}
/* If we've got too many, that implies a descriptor loop. */
- if (*out_num + *in_num > vq->vring.num)
+ if (*out_num + *in_num > max)
errx(1, "Looped descriptor");
- } while ((i = next_desc(vq, i)) != vq->vring.num);
+ } while ((i = next_desc(desc, i, max)) != max);
return head;
}
-/* Once 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 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;
- /* 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;
/* Make sure buffer is written before we update index. */
wmb();
vq->vring.used->idx++;
-}
-
-/* This actually sends the interrupt for this virtqueue */
-static void trigger_irq(int fd, struct virtqueue *vq)
-{
- unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
-
- if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
- return;
-
- /* Send the Guest an interrupt tell them we used something up. */
- if (write(fd, buf, sizeof(buf)) != 0)
- err(1, "Triggering irq %i", vq->config.irq);
+ vq->pending_used++;
}
/* And here's the combo meal deal. Supersize me! */
-static void add_used_and_trigger(int fd, struct virtqueue *vq,
- unsigned int head, int len)
+static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
{
add_used(vq, head, len);
- 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. */
-static struct termios orig_term;
-static void restore_term(void)
-{
- tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+ trigger_irq(vq);
}
-/* We associate some data with the console for our exit hack. */
-struct console_abort
-{
+/*
+ * 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? */
};
/* This is the routine which handles console input (ie. stdin). */
-static bool handle_console_input(int fd, struct device *dev)
+static void console_input(struct virtqueue *vq)
{
int len;
unsigned int head, in_num, out_num;
- struct iovec iov[dev->vq->vring.num];
- struct console_abort *abort = dev->priv;
-
- /* First we need a console buffer from the Guests's input virtqueue. */
- head = get_vq_desc(dev->vq, iov, &out_num, &in_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;
+ 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?");
- /* This is why we convert to iovecs: the readv() call uses them, and so
- * it reads straight into the Guest's buffer. */
- len = readv(dev->fd, iov, in_num);
+ /* Read into it. This is where we usually wait. */
+ len = readv(STDIN_FILENO, iov, in_num);
if (len <= 0) {
- /* This implies that the console is closed, is /dev/null, or
- * something went terribly wrong. */
+ /* Ran out of input? */
warnx("Failed to get console input, ignoring console.");
- /* 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;
+ /*
+ * For simplicity, dying threads kill the whole Launcher. So
+ * just nap here.
+ */
+ for (;;)
+ pause();
}
- /* Tell the Guest about the new input. */
- add_used_and_trigger(fd, dev->vq, head, len);
+ /* Tell the Guest we used a buffer. */
+ 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. */
- if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
- if (!abort->count++)
- gettimeofday(&abort->start, NULL);
- else if (abort->count == 3) {
- struct timeval now;
- gettimeofday(&now, NULL);
- if (now.tv_sec <= abort->start.tv_sec+1) {
- unsigned long args[] = { LHREQ_BREAK, 0 };
- /* Close the fd so Waker will know it has to
- * exit. */
- close(waker_fd);
- /* Just in case waker is blocked in BREAK, send
- * unbreak now. */
- write(fd, args, sizeof(args));
- exit(2);
- }
- abort->count = 0;
- }
- } else
- /* Any other key resets the abort counter. */
+ * 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;
+ }
- /* Everything went OK! */
- return true;
+ 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;
+ }
}
-/* Handling output for console is simple: we just get all the output buffers
- * and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq)
+/* This is the routine which handles console output (ie. stdout). */
+static void console_output(struct virtqueue *vq)
{
unsigned int head, out, in;
- int len;
struct iovec iov[vq->vring.num];
- /* Keep getting output buffers from the Guest until we run out. */
- while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
- if (in)
- errx(1, "Input buffers in output queue?");
- len = writev(STDOUT_FILENO, iov, out);
- add_used_and_trigger(fd, vq, head, len);
+ /* 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)
+ err(1, "Write to stdout gave %i", len);
+ 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);
}
-/* 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)
+/*
+ * 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)
+ errx(1, "Write to tun failed?");
+
+ /*
+ * 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)
+ err(1, "Failed to read from tun.");
- /* Keep getting output buffers from the Guest until we run out. */
- 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). */
- (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);
+ /*
+ * 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)
+{
+ /*
+ * Create stack for thread. 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 };
+
+ /* Create a zero-initialized eventfd. */
+ vq->eventfd = eventfd(0, 0);
+ if (vq->eventfd < 0)
+ err(1, "Creating eventfd");
+ args[2] = vq->eventfd;
+
+ /*
+ * Attach an eventfd to this virtqueue: it will go off when the Guest
+ * does an LHCALL_NOTIFY for this vq.
+ */
+ if (write(lguest_fd, &args, sizeof(args)) != 0)
+ err(1, "Attaching eventfd");
+
+ /*
+ * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
+ * we get a signal if it dies.
+ */
+ vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
+ if (vq->thread == (pid_t)-1)
+ err(1, "Creating clone");
+
+ /* We close our local copy now the child has it. */
+ close(vq->eventfd);
}
-/* This is where we handle a packet coming in from the tun device to our
- * Guest. */
-static bool handle_tun_input(int fd, struct device *dev)
+static bool accepted_feature(struct device *dev, unsigned int bit)
{
- unsigned int head, in_num, out_num;
- int len;
- struct iovec iov[dev->vq->vring.num];
- struct virtio_net_hdr *hdr;
-
- /* First we need a network buffer from the Guests's recv virtqueue. */
- head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
- if (head == dev->vq->vring.num) {
- /* Now, it's expected that if we try to send a packet too
- * early, the Guest won't be ready yet. Wait until the device
- * status says it's ready. */
- /* FIXME: Actually want DRIVER_ACTIVE here. */
- if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
- warn("network: no dma buffer!");
- /* We'll turn this back on if input buffers are registered. */
+ const u8 *features = get_feature_bits(dev) + dev->feature_len;
+
+ if (dev->feature_len < bit / CHAR_BIT)
return false;
- } else if (out_num)
- errx(1, "Output buffers in network recv queue?");
+ return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
+}
- /* First element is the header: we set it to 0 (no features). */
- hdr = convert(&iov[0], struct virtio_net_hdr);
- hdr->flags = 0;
- hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+static void start_device(struct device *dev)
+{
+ unsigned int i;
+ struct virtqueue *vq;
- /* Read the packet from the device directly into the Guest's buffer. */
- len = readv(dev->fd, iov+1, in_num-1);
- if (len <= 0)
- err(1, "reading network");
+ verbose("Device %s OK: offered", dev->name);
+ for (i = 0; i < dev->feature_len; i++)
+ verbose(" %02x", get_feature_bits(dev)[i]);
+ verbose(", accepted");
+ for (i = 0; i < dev->feature_len; i++)
+ verbose(" %02x", get_feature_bits(dev)
+ [dev->feature_len+i]);
- /* Tell the Guest about the new packet. */
- add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);
+ dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
- verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
- ((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
- head != dev->vq->vring.num ? "sent" : "discarded");
+ for (vq = dev->vq; vq; vq = vq->next) {
+ if (vq->service)
+ create_thread(vq);
+ }
+ dev->running = true;
+}
- /* All good. */
- return true;
+static void cleanup_devices(void)
+{
+ struct device *dev;
+
+ for (dev = devices.dev; dev; dev = dev->next)
+ reset_device(dev);
+
+ /* If we saved off the original terminal settings, restore them now. */
+ if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
+ tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
}
-/* This callback 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)
+/* When the Guest tells us they updated the status field, we handle it. */
+static void update_device_status(struct device *dev)
{
- add_device_fd(vq->dev->fd);
- /* Tell waker to listen to it again */
- write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+ /* A zero status is a reset, otherwise it's a set of flags. */
+ if (dev->desc->status == 0)
+ reset_device(dev);
+ else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
+ warnx("Device %s configuration FAILED", dev->name);
+ if (dev->running)
+ reset_device(dev);
+ } else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
+ if (!dev->running)
+ start_device(dev);
+ }
}
-/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
-static void handle_output(int fd, unsigned long 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;
- struct virtqueue *vq;
- /* Check each virtqueue. */
+ /* 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 *can* be used before status is set to DRIVER_OK.
+ * The original plan was that they would never do this: they
+ * would always finish setting up their status bits before
+ * actually touching the virtqueues. In practice, we allowed
+ * them to, and they do (eg. the disk probes for partition
+ * tables as part of initialization).
+ *
+ * If we see this, we start the device: once it's running, we
+ * expect the device to catch all the notifications.
+ */
for (vq = i->vq; vq; vq = vq->next) {
- if (vq->config.pfn == addr/getpagesize()
- && vq->handle_output) {
- verbose("Output to %s\n", vq->dev->name);
- vq->handle_output(fd, vq);
- return;
- }
+ if (addr != vq->config.pfn*getpagesize())
+ continue;
+ if (i->running)
+ errx(1, "Notification on running %s", i->name);
+ /* This just calls create_thread() for each virtqueue */
+ start_device(i);
+ return;
}
}
- /* 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);
strnlen(from_guest_phys(addr), guest_limit - addr));
}
-/* This is called when the waker wakes us up: check for incoming file
- * descriptors. */
-static void handle_input(int fd)
-{
- /* select() wants a zeroed timeval to mean "don't wait". */
- struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };
-
- for (;;) {
- struct device *i;
- fd_set fds = devices.infds;
-
- /* If nothing is ready, we're done. */
- if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0)
- break;
-
- /* Otherwise, call the device(s) which have readable
- * 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. 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));
- }
- }
- }
-}
-
/*L:190
* Device Setup
*
* All devices need a descriptor so the Guest knows it exists, and a "struct
* device" so the Launcher can keep track of it. We have common helper
- * routines to allocate them.
- *
- * This routine allocates a new "struct lguest_device_desc" from descriptor
- * table just above the Guest's normal memory. It returns a pointer to that
- * descriptor. */
-static struct lguest_device_desc *new_dev_desc(u16 type)
-{
- struct lguest_device_desc *d;
-
- /* We only have one page for all the descriptors. */
- if (devices.desc_used + sizeof(*d) > getpagesize())
- errx(1, "Too many devices");
-
- /* We don't need to set config_len or status: page is 0 already. */
- d = (void *)devices.descpage + devices.desc_used;
- d->type = type;
- devices.desc_used += sizeof(*d);
+ * routines to allocate and manage them.
+ */
- return d;
+/*
+ * 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.
+ */
+static u8 *device_config(const struct device *dev)
+{
+ return (void *)(dev->desc + 1)
+ + dev->num_vq * sizeof(struct lguest_vqconfig)
+ + dev->feature_len * 2;
}
-/* 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...].
- *
- * 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. */
-static void add_desc_field(struct device *dev, u8 type, u8 len, const void *c)
+/*
+ * 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.
+ */
+static struct lguest_device_desc *new_dev_desc(u16 type)
{
- /* This is the last descriptor, right? */
- assert(devices.descpage + devices.desc_used
- == (u8 *)(dev->desc + 1) + dev->desc->config_len);
+ struct lguest_device_desc d = { .type = type };
+ void *p;
- /* We only have one page of device descriptions. */
- if (devices.desc_used + 2 + len > getpagesize())
- errx(1, "Too many devices");
+ /* Figure out where the next device config is, based on the last one. */
+ if (devices.lastdev)
+ p = device_config(devices.lastdev)
+ + devices.lastdev->desc->config_len;
+ else
+ p = devices.descpage;
- /* Copy in the new config header: type then length. */
- devices.descpage[devices.desc_used++] = type;
- devices.descpage[devices.desc_used++] = len;
- memcpy(devices.descpage + devices.desc_used, c, len);
- devices.desc_used += len;
+ /* We only have one page for all the descriptors. */
+ if (p + sizeof(d) > (void *)devices.descpage + getpagesize())
+ errx(1, "Too many devices");
- /* Update the device descriptor length: two byte head then data. */
- dev->desc->config_len += 2 + len;
+ /* p might not be aligned, so we memcpy in. */
+ return memcpy(p, &d, sizeof(d));
}
-/* This routine adds a virtqueue to a device. 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 (*handle_output)(int fd, struct virtqueue *me))
+ void (*service)(struct virtqueue *))
{
unsigned int pages;
struct virtqueue **i, *vq = malloc(sizeof(*vq));
void *p;
- /* First we need some pages for this virtqueue. */
- pages = (vring_size(num_descs) + getpagesize() - 1) / getpagesize();
+ /* First we need some memory for this virtqueue. */
+ pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1)
+ / getpagesize();
p = get_pages(pages);
+ /* Initialize the virtqueue */
+ vq->next = NULL;
+ vq->last_avail_idx = 0;
+ vq->dev = dev;
+
+ /*
+ * This is the routine the service thread will run, and its Process ID
+ * once it's running.
+ */
+ vq->service = service;
+ vq->thread = (pid_t)-1;
+
/* Initialize the configuration. */
vq->config.num = num_descs;
vq->config.irq = devices.next_irq++;
vq->config.pfn = to_guest_phys(p) / getpagesize();
/* Initialize the vring. */
- vring_init(&vq->vring, num_descs, p);
-
- /* Add the configuration information to this device's descriptor. */
- add_desc_field(dev, VIRTIO_CONFIG_F_VIRTQUEUE,
- sizeof(vq->config), &vq->config);
-
- /* Add to tail of list, so dev->vq is first vq, dev->vq->next is
- * second. */
+ vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
+
+ /*
+ * 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.
+ */
+ assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
+ memcpy(device_config(dev), &vq->config, sizeof(vq->config));
+ dev->num_vq++;
+ dev->desc->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.
+ */
for (i = &dev->vq; *i; i = &(*i)->next);
*i = vq;
+}
- /* Link virtqueue back to device. */
- vq->dev = dev;
+/*
+ * 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);
- /* Set up handler. */
- vq->handle_output = handle_output;
- if (!handle_output)
- vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
+ /* We can't extend the feature bits once we've added config bytes */
+ if (dev->desc->feature_len <= bit / CHAR_BIT) {
+ assert(dev->desc->config_len == 0);
+ dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1;
+ }
+
+ features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
}
-/* This routine does all the creation and setup of a new device, including
- * caling 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 *))
+/*
+ * 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.
+ */
+static void set_config(struct device *dev, unsigned len, const void *conf)
{
- struct device *dev = malloc(sizeof(*dev));
+ /* Check we haven't overflowed our single page. */
+ if (device_config(dev) + len > devices.descpage + getpagesize())
+ errx(1, "Too many devices");
- /* 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. */
- *devices.lastdev = dev;
- dev->next = NULL;
- devices.lastdev = &dev->next;
+ /* Copy in the config information, and store the length. */
+ memcpy(device_config(dev), conf, len);
+ dev->desc->config_len = len;
+
+ /* Size must fit in config_len field (8 bits)! */
+ assert(dev->desc->config_len == len);
+}
+
+/*
+ * This routine does all the creation and setup of a new device, including
+ * calling new_dev_desc() to allocate the descriptor and device memory. We
+ * don't actually start the service threads until later.
+ *
+ * See what I mean about userspace being boring?
+ */
+static struct device *new_device(const char *name, u16 type)
+{
+ struct device *dev = malloc(sizeof(*dev));
/* Now we populate the fields one at a time. */
- dev->fd = fd;
- /* If we have an input handler for this file descriptor, then we add it
- * to the device_list's fdset and maxfd. */
- if (handle_input)
- add_device_fd(dev->fd);
dev->desc = new_dev_desc(type);
- dev->handle_input = handle_input;
dev->name = name;
+ dev->vq = NULL;
+ dev->feature_len = 0;
+ dev->num_vq = 0;
+ dev->running = false;
+
+ /*
+ * 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.
+ */
+ if (devices.lastdev)
+ devices.lastdev->next = dev;
+ else
+ devices.dev = dev;
+ devices.lastdev = dev;
+
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);
- /* If we exit gracefully, the original settings will be
- * restored so the user can see what they're typing. */
- atexit(restore_term);
}
- dev = new_device("console", VIRTIO_ID_CONSOLE,
- STDIN_FILENO, handle_console_input);
+ dev = new_device("console", VIRTIO_ID_CONSOLE);
+
/* We store the console state in dev->priv, and initialize it. */
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. */
- add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
- add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);
+ * stdout.
+ */
+ add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
+ add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
- verbose("device %u: console\n", devices.device_num++);
+ verbose("device %u: console\n", ++devices.device_num);
}
/*:*/
-/*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)
{
- unsigned int byte[4];
+ unsigned int b[4];
+
+ if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
+ errx(1, "Failed to parse IP address '%s'", ipaddr);
+ return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
+}
- sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
- return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+static void str2mac(const char *macaddr, unsigned char mac[6])
+{
+ unsigned int m[6];
+ if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
+ &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
+ errx(1, "Failed to parse mac address '%s'", macaddr);
+ mac[0] = m[0];
+ mac[1] = m[1];
+ mac[2] = m[2];
+ mac[3] = m[3];
+ mac[4] = m[4];
+ 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;
errx(1, "interface %s does not exist!", if_name);
strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
+ ifr.ifr_name[IFNAMSIZ-1] = '\0';
ifr.ifr_ifindex = ifidx;
if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
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. */
-static void configure_device(int fd, const char *devname, u32 ipaddr,
- unsigned char hwaddr[6])
+ * pointer.
+ */
+static void configure_device(int fd, const char *tapif, u32 ipaddr)
{
struct ifreq ifr;
struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
- /* Don't read these incantations. Just cut & paste them like I did! */
memset(&ifr, 0, sizeof(ifr));
- strcpy(ifr.ifr_name, devname);
+ strcpy(ifr.ifr_name, tapif);
+
+ /* Don't read these incantations. Just cut & paste them like I did! */
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = htonl(ipaddr);
if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
- err(1, "Setting %s interface address", devname);
+ err(1, "Setting %s interface address", tapif);
ifr.ifr_flags = IFF_UP;
if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
- err(1, "Bringing interface %s up", devname);
-
- /* SIOC stands for Socket I/O Control. G means Get (vs S for Set
- * above). IF means Interface, and HWADDR is hardware address.
- * Simple! */
- if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
- err(1, "getting hw address for %s", devname);
- memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
+ err(1, "Bringing interface %s up", tapif);
}
-/*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. */
-static void setup_tun_net(const char *arg)
+static int get_tun_device(char tapif[IFNAMSIZ])
{
- struct device *dev;
struct ifreq ifr;
- int netfd, ipfd;
- u32 ip;
- const char *br_name = NULL;
- u8 hwaddr[6];
+ int netfd;
+
+ /* 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);
- memset(&ifr, 0, sizeof(ifr));
- ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
strcpy(ifr.ifr_name, "tap%d");
if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
err(1, "configuring /dev/net/tun");
- /* We don't need checksums calculated for packets coming in this
- * device: trust us! */
+
+ if (ioctl(netfd, TUNSETOFFLOAD,
+ 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!
+ */
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
+ * 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.
+ */
+static void setup_tun_net(char *arg)
+{
+ struct device *dev;
+ struct net_info *net_info = malloc(sizeof(*net_info));
+ int ipfd;
+ u32 ip = INADDR_ANY;
+ bool bridging = false;
+ char tapif[IFNAMSIZ], *p;
+ struct virtio_net_config conf;
+
+ net_info->tunfd = get_tun_device(tapif);
+
/* First we create a new network device. */
- dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
+ dev = new_device("net", VIRTIO_ID_NET);
+ dev->priv = net_info;
- /* 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);
+ /* 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");
/* If the command line was --tunnet=bridge:<name> do bridging. */
if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
- ip = INADDR_ANY;
- br_name = arg + strlen(BRIDGE_PFX);
- add_to_bridge(ipfd, ifr.ifr_name, br_name);
- } else /* It is an IP address to set up the device with */
- ip = str2ip(arg);
+ arg += strlen(BRIDGE_PFX);
+ bridging = true;
+ }
- /* Set up the tun device, and get the mac address for the interface. */
- configure_device(ipfd, ifr.ifr_name, ip, hwaddr);
+ /* A mac address may follow the bridge name or IP address */
+ p = strchr(arg, ':');
+ if (p) {
+ str2mac(p+1, conf.mac);
+ add_feature(dev, VIRTIO_NET_F_MAC);
+ *p = '\0';
+ }
- /* Tell Guest what MAC address to use. */
- add_desc_field(dev, VIRTIO_CONFIG_NET_MAC_F, sizeof(hwaddr), hwaddr);
+ /* arg is now either an IP address or a bridge name */
+ if (bridging)
+ add_to_bridge(ipfd, tapif, arg);
+ else
+ ip = str2ip(arg);
- /* We don't seed the socket any more; setup is done. */
+ /* Set up the tun device. */
+ configure_device(ipfd, tapif, ip);
+
+ add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
+ /* Expect Guest to handle everything except UFO */
+ add_feature(dev, VIRTIO_NET_F_CSUM);
+ add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
+ add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
+ add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
+ add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
+ add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
+ add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
+ add_feature(dev, VIRTIO_NET_F_HOST_ECN);
+ /* We handle indirect ring entries */
+ add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
+ set_config(dev, sizeof(conf), &conf);
+
+ /* We don't need the socket any more; setup is done. */
close(ipfd);
- verbose("device %u: tun net %u.%u.%u.%u\n",
- devices.device_num++,
- (u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
- if (br_name)
- verbose("attached to bridge: %s\n", br_name);
-}
-
+ devices.device_num++;
-/*
- * 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.
- *
- * 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.
- *
- * So we farm the I/O out to thread, and communicate with it via a pipe. */
+ if (bridging)
+ verbose("device %u: tun %s attached to bridge: %s\n",
+ devices.device_num, tapif, arg);
+ else
+ verbose("device %u: tun %s: %s\n",
+ devices.device_num, tapif, arg);
+}
+/*:*/
-/* This hangs off device->priv, with the data. */
-struct vblk_info
-{
+/* This hangs off device->priv. */
+struct vblk_info {
/* The size of the file. */
off64_t len;
/* The file descriptor for the file. */
int fd;
- /* IO thread listens on this file descriptor [0]. */
- int workpipe[2];
-
- /* IO thread writes to this file descriptor to mark it done, then
- * Launcher triggers interrupt to Guest. */
- int done_fd;
};
-/* This is the core of the I/O thread. It returns true if it did something. */
-static bool service_io(struct device *dev)
+/*L:210
+ * The Disk
+ *
+ * The disk only has one virtqueue, so it only has one thread. It is really
+ * simple: the Guest asks for a block number and we read or write that position
+ * in the file.
+ *
+ * Before we serviced each virtqueue in a separate thread, that was unacceptably
+ * slow: the Guest waits until the read is finished before running anything
+ * else, even if it could have been doing useful work.
+ *
+ * We could have used 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.
+ */
+static void blk_request(struct virtqueue *vq)
{
- struct vblk_info *vblk = dev->priv;
+ struct vblk_info *vblk = vq->dev->priv;
unsigned int head, out_num, in_num, wlen;
int ret;
- struct virtio_blk_inhdr *in;
+ u8 *in;
struct virtio_blk_outhdr *out;
- struct iovec iov[dev->vq->vring.num];
+ struct iovec iov[vq->vring.num];
off64_t off;
- head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
- if (head == dev->vq->vring.num)
- return false;
-
+ /*
+ * Get the next request, where we normally wait. It triggers the
+ * interrupt to acknowledge previously serviced requests (if any).
+ */
+ head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
+
+ /*
+ * 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);
out = convert(&iov[0], struct virtio_blk_outhdr);
- in = convert(&iov[out_num+in_num-1], struct virtio_blk_inhdr);
+ in = convert(&iov[out_num+in_num-1], u8);
+ /*
+ * For historical reasons, block operations are expressed in 512 byte
+ * "sectors".
+ */
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;
- wlen = sizeof(in);
+ *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);
/* Die, bad Guest, die. */
errx(1, "Write past end %llu+%u", off, ret);
}
- wlen = sizeof(in);
- in->status = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+ 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);
ret = readv(vblk->fd, iov+1, in_num-1);
verbose("READ from sector %llu: %i\n", out->sector, ret);
if (ret >= 0) {
- wlen = sizeof(in) + ret;
- in->status = VIRTIO_BLK_S_OK;
+ wlen = sizeof(*in) + ret;
+ *in = VIRTIO_BLK_S_OK;
} else {
- wlen = sizeof(in);
- in->status = VIRTIO_BLK_S_IOERR;
+ wlen = sizeof(*in);
+ *in = VIRTIO_BLK_S_IOERR;
}
}
- /* We can't trigger an IRQ, because we're not the Launcher. It does
- * that when we tell it we're done. */
- add_used(dev->vq, head, wlen);
- return true;
-}
-
-/* This is the thread which actually services the I/O. */
-static int io_thread(void *_dev)
-{
- struct device *dev = _dev;
- struct vblk_info *vblk = dev->priv;
- char c;
-
- /* Close other side of workpipe so we get 0 read when main dies. */
- close(vblk->workpipe[1]);
- /* Close the other side of the done_fd pipe. */
- close(dev->fd);
-
- /* 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,
- * rather than waiting until we've done them all. I haven't
- * measured to see if it makes any difference. */
- while (service_io(dev))
- write(vblk->done_fd, &c, 1);
- }
- return 0;
-}
-
-/* When the thread says some I/O is done, we interrupt the Guest. */
-static bool handle_io_finish(int fd, struct device *dev)
-{
- char c;
-
- /* If child died, presumably it printed message. */
- if (read(dev->fd, &c, 1) != 1)
- exit(1);
-
- /* It did some work, so trigger the irq. */
- trigger_irq(fd, dev->vq);
- return true;
-}
-
-/* When the Guest submits some I/O, we wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq)
-{
- struct vblk_info *vblk = vq->dev->priv;
- char c = 0;
+ /*
+ * 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:
+ */
+ if (out->type & VIRTIO_BLK_T_BARRIER)
+ fdatasync(vblk->fd);
- /* Wake up I/O thread and tell it to go to work! */
- if (write(vblk->workpipe[1], &c, 1) != 1)
- /* Presumably it indicated why it died. */
- exit(1);
+ /* Finished that request. */
+ add_used(vq, head, wlen);
}
-/* 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];
struct device *dev;
struct vblk_info *vblk;
- void *stack;
- u64 cap;
- unsigned int val;
-
- /* This is the pipe the I/O thread will use to tell us I/O is done. */
- pipe(p);
+ struct virtio_blk_config conf;
- /* The device responds to return from I/O thread. */
- dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish);
+ /* Creat the device. */
+ dev = new_device("block", VIRTIO_ID_BLOCK);
- /* The device has a virtqueue. */
- add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output);
+ /* The device has one virtqueue, where the Guest places requests. */
+ add_virtqueue(dev, VIRTQUEUE_NUM, blk_request);
/* Allocate the room for our own bookkeeping */
vblk = dev->priv = malloc(sizeof(*vblk));
vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
vblk->len = lseek64(vblk->fd, 0, SEEK_END);
+ /* We support barriers. */
+ add_feature(dev, VIRTIO_BLK_F_BARRIER);
+
/* Tell Guest how many sectors this device has. */
- cap = cpu_to_le64(vblk->len / 512);
- add_desc_field(dev, VIRTIO_CONFIG_BLK_F_CAPACITY, sizeof(cap), &cap);
+ 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.
+ */
+ add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
+ conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
- /* Tell Guest not to put in too many descriptors at once: two are used
- * for the in and out elements. */
- val = cpu_to_le32(VIRTQUEUE_NUM - 2);
- add_desc_field(dev, VIRTIO_CONFIG_BLK_F_SEG_MAX, sizeof(val), &val);
+ /* Don't try to put whole struct: we have 8 bit limit. */
+ set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf);
- /* The I/O thread writes to this end of the pipe when done. */
- vblk->done_fd = p[1];
+ verbose("device %u: virtblock %llu sectors\n",
+ ++devices.device_num, le64_to_cpu(conf.capacity));
+}
- /* This is how we tell the I/O thread about more work. */
- pipe(vblk->workpipe);
+/*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.
+ */
+struct rng_info {
+ int rfd;
+};
- /* Create stack for thread and run it */
- stack = malloc(32768);
- if (clone(io_thread, stack + 32768, CLONE_VM, dev) == -1)
- err(1, "Creating clone");
+static void rng_input(struct virtqueue *vq)
+{
+ int len;
+ unsigned int head, in_num, out_num, totlen = 0;
+ struct rng_info *rng_info = vq->dev->priv;
+ struct iovec iov[vq->vring.num];
- /* We don't need to keep the I/O thread's end of the pipes open. */
- close(vblk->done_fd);
- close(vblk->workpipe[0]);
+ /* First we need a buffer from the Guests's virtqueue. */
+ head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
+ if (out_num)
+ errx(1, "Output buffers in rng?");
+
+ /*
+ * Just like the console write, we loop to cover the whole iovec.
+ * In this case, short reads actually happen quite a bit.
+ */
+ while (!iov_empty(iov, in_num)) {
+ len = readv(rng_info->rfd, iov, in_num);
+ if (len <= 0)
+ err(1, "Read from /dev/random gave %i", len);
+ iov_consume(iov, in_num, len);
+ totlen += len;
+ }
- verbose("device %u: virtblock %llu sectors\n",
- devices.device_num, cap);
+ /* Tell the Guest about the new input. */
+ add_used(vq, head, totlen);
+}
+
+/*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);
+
+ /* Create the new device. */
+ dev = new_device("rng", VIRTIO_ID_RNG);
+ dev->priv = rng_info;
+
+ /* The device has one virtqueue, where the Guest places inbufs. */
+ add_virtqueue(dev, VIRTQUEUE_NUM, rng_input);
+
+ verbose("device %u: rng\n", devices.device_num++);
}
/* That's the end of device setup. */
-/*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(int lguest_fd)
+/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
+static void __attribute__((noreturn)) restart_guest(void)
+{
+ unsigned int i;
+
+ /*
+ * Since we don't track all open fds, we simply close everything beyond
+ * stderr.
+ */
+ for (i = 3; i < FD_SETSIZE; i++)
+ close(i);
+
+ /* Reset all the devices (kills all threads). */
+ cleanup_devices();
+
+ execv(main_args[0], main_args);
+ 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.
+ */
+static void __attribute__((noreturn)) run_guest(void)
{
for (;;) {
- unsigned long args[] = { LHREQ_BREAK, 0 };
unsigned long notify_addr;
int readval;
/* We read from the /dev/lguest device to run the Guest. */
- readval = read(lguest_fd, ¬ify_addr, sizeof(notify_addr));
+ readval = pread(lguest_fd, ¬ify_addr,
+ sizeof(notify_addr), cpu_id);
/* One unsigned long means the Guest did HCALL_NOTIFY */
if (readval == sizeof(notify_addr)) {
verbose("Notify on address %#lx\n", notify_addr);
- handle_output(lguest_fd, notify_addr);
- continue;
+ handle_output(notify_addr);
/* ENOENT means the Guest died. Reading tells us why. */
} else if (errno == ENOENT) {
char reason[1024] = { 0 };
- read(lguest_fd, reason, sizeof(reason)-1);
+ pread(lguest_fd, reason, sizeof(reason)-1, cpu_id);
errx(1, "%s", reason);
- /* EAGAIN means the waker wanted us to look at some input.
- * Anything else means a bug or incompatible change. */
- } else if (errno != EAGAIN)
+ /* ERESTART means that we need to reboot the guest */
+ } else if (errno == ERESTART) {
+ restart_guest();
+ /* Anything else means a bug or incompatible change. */
+ } else
err(1, "Running guest failed");
-
- /* Service input, then unset the BREAK which releases
- * 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.
+/*L:240
+ * 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' },
{ "tunnet", 1, NULL, 't' },
{ "block", 1, NULL, 'b' },
+ { "rng", 0, NULL, 'r' },
{ "initrd", 1, NULL, 'i' },
{ NULL },
};
static void usage(void)
{
errx(1, "Usage: lguest [--verbose] "
- "[--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
+ "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n"
"|--block=<filename>|--initrd=<filename>]...\n"
"<mem-in-mb> vmlinux [args...]");
}
/*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. */
- unsigned long mem = 0, pgdir, start, initrd_size = 0;
- /* A temporary and the /dev/lguest file descriptor. */
- int i, c, lguest_fd;
+ /* Memory, code startpoint and size of the (optional) initrd. */
+ unsigned long mem = 0, start, initrd_size = 0;
+ /* Two temporaries. */
+ int i, c;
/* 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;
- /* First we initialize the device list. Since console and network
- * device receive input from a file descriptor, we keep an fdset
- * (infds) and the maximum fd number (max_infd) with the head of the
- * list. We also keep a pointer to the last device, for easy appending
- * to the list. Finally, we keep the next interrupt number to hand out
- * (1: remember that 0 is used by the timer). */
- FD_ZERO(&devices.infds);
- devices.max_infd = -1;
- devices.lastdev = &devices.dev;
+ /* 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
+ * device, and the next interrupt number to use for devices (1:
+ * remember that 0 is used by the timer).
+ */
+ devices.lastdev = NULL;
devices.next_irq = 1;
- /* We need to know how much memory so we can set up the device
+ /* We're CPU 0. In fact, that's the only CPU possible right now. */
+ cpu_id = 0;
+
+ /*
+ * 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;
case 'b':
setup_block_file(optarg);
break;
+ case 'r':
+ setup_rng();
+ break;
case 'i':
initrd_name = optarg;
break;
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. */
- *(unsigned long *)(boot+0x218) = mem - initrd_size;
- *(unsigned long *)(boot+0x21c) = initrd_size;
+ /*
+ * 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. */
- *(unsigned char *)(boot+0x210) = 0xFF;
+ boot->hdr.type_of_loader = 0xFF;
}
- /* Set up the initial linear pagetables, starting below the initrd. */
- pgdir = setup_pagetables(mem, initrd_size);
-
- /* 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 });
- /* 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);
+ /*
+ * 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.
+ */
+ 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. */
- *(u16 *)(boot + 0x206) = 0x207;
+ boot->hdr.version = 0x207;
/* The hardware_subarch value of "1" tells the Guest it's an lguest. */
- *(u32 *)(boot + 0x23c) = 1;
+ boot->hdr.hardware_subarch = 1;
+
+ /* Tell the entry path not to try to reload segment registers. */
+ boot->hdr.loadflags |= KEEP_SEGMENTS;
- /* Set bit 6 of the loadflags (aka. KEEP_SEGMENTS) so the entry path
- * does not try to reload segment registers. */
- *(u8 *)(boot + 0x211) |= (1 << 6);
+ /*
+ * We tell the kernel to initialize the Guest: this returns the open
+ * /dev/lguest file descriptor.
+ */
+ tell_kernel(start);
- /* We tell the kernel to initialize the Guest: this returns the open
- * /dev/lguest file descriptor. */
- lguest_fd = tell_kernel(pgdir, start);
+ /* Ensure that we terminate if a device-servicing child dies. */
+ signal(SIGCHLD, kill_launcher);
- /* We fork off a child process, which wakes the Launcher whenever one
- * of the input file descriptors needs attention. Otherwise we would
- * run the Guest until it tries to output something. */
- waker_fd = setup_waker(lguest_fd);
+ /* If we exit via err(), this kills all the threads, restores tty. */
+ atexit(cleanup_devices);
/* Finally, run the Guest. This doesn't return. */
- run_guest(lguest_fd);
+ run_guest();
}
/*:*/