diff options
author | Juergen Gross <jgross@suse.com> | 2017-08-16 19:31:57 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2017-08-24 09:57:28 +0200 |
commit | ecda85e70277ef24e44a1f6bc00243cebd19f985 (patch) | |
tree | cd094195d6ab0ed476ad093236880c8ce145e8e4 /tools | |
parent | edcb5cf84f05e5d2e2af25422a72ccde359fcca9 (diff) |
x86/lguest: Remove lguest support
Lguest seems to be rather unused these days. It has seen only patches
ensuring it still builds the last two years and its official state is
"Odd Fixes".
Remove it in order to be able to clean up the paravirt code.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: boris.ostrovsky@oracle.com
Cc: lguest@lists.ozlabs.org
Cc: rusty@rustcorp.com.au
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20170816173157.8633-3-jgross@suse.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/Makefile | 11 | ||||
-rw-r--r-- | tools/lguest/.gitignore | 2 | ||||
-rw-r--r-- | tools/lguest/Makefile | 14 | ||||
-rw-r--r-- | tools/lguest/extract | 58 | ||||
-rw-r--r-- | tools/lguest/lguest.c | 3420 | ||||
-rw-r--r-- | tools/lguest/lguest.txt | 125 |
6 files changed, 5 insertions, 3625 deletions
diff --git a/tools/Makefile b/tools/Makefile index 221e1ce78b06..a19b176b914b 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -18,7 +18,6 @@ help: @echo ' iio - IIO tools' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' - @echo ' lguest - a minimal 32-bit x86 hypervisor' @echo ' liblockdep - user-space wrapper for kernel locking-validator' @echo ' net - misc networking tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -90,7 +89,7 @@ freefall: FORCE kvm_stat: FORCE $(call descend,kvm/$@) -all: acpi cgroup cpupower gpio hv firewire lguest liblockdep \ +all: acpi cgroup cpupower gpio hv firewire liblockdep \ perf selftests turbostat usb \ virtio vm net x86_energy_perf_policy \ tmon freefall objtool kvm_stat @@ -101,7 +100,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install: +cgroup_install firewire_install gpio_install hv_install perf_install usb_install virtio_install vm_install net_install objtool_install: $(call descend,$(@:_install=),install) liblockdep_install: @@ -123,7 +122,7 @@ kvm_stat_install: $(call descend,kvm/$(@:_install=),install) install: acpi_install cgroup_install cpupower_install gpio_install \ - hv_install firewire_install lguest_install liblockdep_install \ + hv_install firewire_install liblockdep_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install net_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install @@ -134,7 +133,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: +cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean: @@ -168,7 +167,7 @@ freefall_clean: build_clean: $(call descend,build,clean) -clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \ +clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore deleted file mode 100644 index 8d9a8383a52e..000000000000 --- a/tools/lguest/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -lguest -include diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile deleted file mode 100644 index d04599a79802..000000000000 --- a/tools/lguest/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude - -all: lguest - -include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h - mkdir -p include/linux 2>&1 || true - ln -sf ../../../../include/uapi/linux/virtio_types.h $@ - -lguest: include/linux/virtio_types.h - -clean: - rm -f lguest - rm -rf include diff --git a/tools/lguest/extract b/tools/lguest/extract deleted file mode 100644 index 7730bb6e4b94..000000000000 --- a/tools/lguest/extract +++ /dev/null @@ -1,58 +0,0 @@ -#! /bin/sh - -set -e - -PREFIX=$1 -shift - -trap 'rm -r $TMPDIR' 0 -TMPDIR=`mktemp -d` - -exec 3>/dev/null -for f; do - while IFS=" -" read -r LINE; do - case "$LINE" in - *$PREFIX:[0-9]*:\**) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 - ;; - *$PREFIX:[0-9]*) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 - ;; - *:\**) - /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 - echo >&3 - exec 3>/dev/null - ;; - *) - /bin/echo "$LINE" >&3 - ;; - esac - done < $f - echo >&3 - exec 3>/dev/null -done - -LASTFILE="" -for f in $TMPDIR/*; do - if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then - LASTFILE=$(cat $TMPDIR/.$(basename $f) ) - echo "[ $LASTFILE ]" - fi - cat $f -done - diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c deleted file mode 100644 index 897cd6f3f687..000000000000 --- a/tools/lguest/lguest.c +++ /dev/null @@ -1,3420 +0,0 @@ -/*P:100 - * This is the Launcher code, a simple program which lays out the "physical" - * memory for the new Guest by mapping the kernel image and the virtual - * devices, then opens /dev/lguest to tell the kernel about the Guest and - * control it. -:*/ -#define _LARGEFILE64_SOURCE -#define _GNU_SOURCE -#include <stdio.h> -#include <string.h> -#include <unistd.h> -#include <err.h> -#include <stdint.h> -#include <stdlib.h> -#include <elf.h> -#include <sys/mman.h> -#include <sys/param.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/wait.h> -#include <sys/eventfd.h> -#include <fcntl.h> -#include <stdbool.h> -#include <errno.h> -#include <ctype.h> -#include <sys/socket.h> -#include <sys/ioctl.h> -#include <sys/time.h> -#include <time.h> -#include <netinet/in.h> -#include <net/if.h> -#include <linux/sockios.h> -#include <linux/if_tun.h> -#include <sys/uio.h> -#include <termios.h> -#include <getopt.h> -#include <assert.h> -#include <sched.h> -#include <limits.h> -#include <stddef.h> -#include <signal.h> -#include <pwd.h> -#include <grp.h> -#include <sys/user.h> -#include <linux/pci_regs.h> - -#ifndef VIRTIO_F_ANY_LAYOUT -#define VIRTIO_F_ANY_LAYOUT 27 -#endif - -/*L:110 - * We can ignore the 43 include files we need for this program, but I do want - * to draw attention to the use of kernel-style types. - * - * As Linus said, "C is a Spartan language, and so should your naming be." I - * like these abbreviations, so we define them here. Note that u64 is always - * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. - */ -typedef unsigned long long u64; -typedef uint32_t u32; -typedef uint16_t u16; -typedef uint8_t u8; -/*:*/ - -#define VIRTIO_CONFIG_NO_LEGACY -#define VIRTIO_PCI_NO_LEGACY -#define VIRTIO_BLK_NO_LEGACY -#define VIRTIO_NET_NO_LEGACY - -/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */ -#include "../../include/uapi/linux/virtio_config.h" -#include "../../include/uapi/linux/virtio_net.h" -#include "../../include/uapi/linux/virtio_blk.h" -#include "../../include/uapi/linux/virtio_console.h" -#include "../../include/uapi/linux/virtio_rng.h" -#include <linux/virtio_ring.h> -#include "../../include/uapi/linux/virtio_pci.h" -#include <asm/bootparam.h> -#include "../../include/linux/lguest_launcher.h" - -#define BRIDGE_PFX "bridge:" -#ifndef SIOCBRADDIF -#define SIOCBRADDIF 0x89a2 /* add interface to bridge */ -#endif -/* We can have up to 256 pages for devices. */ -#define DEVICE_PAGES 256 -/* This will occupy 3 pages: it must be a power of 2. */ -#define VIRTQUEUE_NUM 256 - -/*L:120 - * verbose is both a global flag and a macro. The C preprocessor allows - * this, and although I wouldn't recommend it, it works quite nicely here. - */ -static bool verbose; -#define verbose(args...) \ - do { if (verbose) printf(args); } while(0) -/*:*/ - -/* The pointer to the start of guest memory. */ -static void *guest_base; -/* The maximum guest physical address allowed, and maximum possible. */ -static unsigned long guest_limit, guest_max, guest_mmio; -/* The /dev/lguest file descriptor. */ -static int lguest_fd; - -/* a per-cpu variable indicating whose vcpu is currently running */ -static unsigned int __thread cpu_id; - -/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */ -#define MAX_PCI_DEVICES 32 - -/* This is our list of devices. */ -struct device_list { - /* Counter to assign interrupt numbers. */ - unsigned int next_irq; - - /* Counter to print out convenient device numbers. */ - unsigned int device_num; - - /* PCI devices. */ - struct device *pci[MAX_PCI_DEVICES]; -}; - -/* The list of Guest devices, based on command line arguments. */ -static struct device_list devices; - -/* - * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h, - * but uses a u32 explicitly for the data. - */ -struct virtio_pci_cfg_cap_u32 { - struct virtio_pci_cap cap; - u32 pci_cfg_data; /* Data for BAR access. */ -}; - -struct virtio_pci_mmio { - struct virtio_pci_common_cfg cfg; - u16 notify; - u8 isr; - u8 padding; - /* Device-specific configuration follows this. */ -}; - -/* This is the layout (little-endian) of the PCI config space. */ -struct pci_config { - u16 vendor_id, device_id; - u16 command, status; - u8 revid, prog_if, subclass, class; - u8 cacheline_size, lat_timer, header_type, bist; - u32 bar[6]; - u32 cardbus_cis_ptr; - u16 subsystem_vendor_id, subsystem_device_id; - u32 expansion_rom_addr; - u8 capabilities, reserved1[3]; - u32 reserved2; - u8 irq_line, irq_pin, min_grant, max_latency; - - /* Now, this is the linked capability list. */ - struct virtio_pci_cap common; - struct virtio_pci_notify_cap notify; - struct virtio_pci_cap isr; - struct virtio_pci_cap device; - struct virtio_pci_cfg_cap_u32 cfg_access; -}; - -/* The device structure describes a single device. */ -struct device { - /* The name of this device, for --verbose. */ - const char *name; - - /* Any queues attached to this device */ - struct virtqueue *vq; - - /* Is it operational */ - bool running; - - /* Has it written FEATURES_OK but not re-checked it? */ - bool wrote_features_ok; - - /* PCI configuration */ - union { - struct pci_config config; - u32 config_words[sizeof(struct pci_config) / sizeof(u32)]; - }; - - /* Features we offer, and those accepted. */ - u64 features, features_accepted; - - /* Device-specific config hangs off the end of this. */ - struct virtio_pci_mmio *mmio; - - /* PCI MMIO resources (all in BAR0) */ - size_t mmio_size; - u32 mmio_addr; - - /* Device-specific data. */ - void *priv; -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue { - struct virtqueue *next; - - /* Which device owns me. */ - struct device *dev; - - /* Name for printing errors. */ - const char *name; - - /* The actual ring of buffers. */ - struct vring vring; - - /* The information about this virtqueue (we only use queue_size on) */ - struct virtio_pci_common_cfg pci_config; - - /* Last available index we saw. */ - u16 last_avail_idx; - - /* How many are used since we sent last irq? */ - unsigned int pending_used; - - /* Eventfd where Guest notifications arrive. */ - int eventfd; - - /* Function for the thread which is servicing this virtqueue. */ - void (*service)(struct virtqueue *vq); - pid_t thread; -}; - -/* Remember the arguments to the program so we can "reboot" */ -static char **main_args; - -/* The original tty settings to restore on exit. */ -static struct termios orig_term; - -/* - * We have to be careful with barriers: our devices are all run in separate - * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. - */ -#define wmb() __asm__ __volatile__("" : : : "memory") -#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") -#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") - -/* Wrapper for the last available index. Makes it easier to change. */ -#define lg_last_avail(vq) ((vq)->last_avail_idx) - -/* - * The virtio configuration space is defined to be little-endian. x86 is - * little-endian too, but it's nice to be explicit so we have these helpers. - */ -#define cpu_to_le16(v16) (v16) -#define cpu_to_le32(v32) (v32) -#define cpu_to_le64(v64) (v64) -#define le16_to_cpu(v16) (v16) -#define le32_to_cpu(v32) (v32) -#define le64_to_cpu(v64) (v64) - -/* - * A real device would ignore weird/non-compliant driver behaviour. We - * stop and flag it, to help debugging Linux problems. - */ -#define bad_driver(d, fmt, ...) \ - errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__) -#define bad_driver_vq(vq, fmt, ...) \ - errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \ - vq->name, ## __VA_ARGS__) - -/* 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 device *d, - struct iovec iov[], unsigned num_iov, - void *dest, 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; - if (dest) { - memcpy(dest, iov[i].iov_base, used); - dest += used; - } - iov[i].iov_base += used; - iov[i].iov_len -= used; - len -= used; - } - if (len != 0) - bad_driver(d, "iovec too short!"); -} - -/*L:100 - * The Launcher code itself takes us out into userspace, that scary place where - * pointers run wild and free! Unfortunately, like most userspace programs, - * it's quite boring (which is why everyone likes to hack on the kernel!). - * Perhaps if you make up an Lguest Drinking Game at this point, it will get - * you through this section. Or, maybe not. - * - * The Launcher sets up a big chunk of memory to be the Guest's "physical" - * memory and stores it in "guest_base". In other words, Guest physical == - * Launcher virtual with an offset. - * - * This can be tough to get your head around, but usually it just means that we - * use these trivial conversion functions when the Guest gives us its - * "physical" addresses: - */ -static void *from_guest_phys(unsigned long addr) -{ - return guest_base + addr; -} - -static unsigned long to_guest_phys(const void *addr) -{ - return (addr - guest_base); -} - -/*L:130 - * Loading the Kernel. - * - * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: - */ -static int open_or_die(const char *name, int flags) -{ - int fd = open(name, flags); - if (fd < 0) - err(1, "Failed to open %s", name); - return fd; -} - -/* map_zeroed_pages() takes a number of pages. */ -static void *map_zeroed_pages(unsigned int num) -{ - int fd = open_or_die("/dev/zero", O_RDONLY); - void *addr; - - /* - * We use a private mapping (ie. if we write to the page, it will be - * copied). We allocate an extra two pages PROT_NONE to act as guard - * pages against read/write attempts that exceed allocated space. - */ - addr = mmap(NULL, getpagesize() * (num+2), - PROT_NONE, MAP_PRIVATE, fd, 0); - - if (addr == MAP_FAILED) - err(1, "Mmapping %u pages of /dev/zero", num); - - if (mprotect(addr + getpagesize(), getpagesize() * num, - PROT_READ|PROT_WRITE) == -1) - err(1, "mprotect rw %u pages failed", num); - - /* - * One neat mmap feature is that you can close the fd, and it - * stays mapped. - */ - close(fd); - - /* Return address after PROT_NONE page */ - return addr + getpagesize(); -} - -/* Get some bytes which won't be mapped into the guest. */ -static unsigned long get_mmio_region(size_t size) -{ - unsigned long addr = guest_mmio; - size_t i; - - if (!size) - return addr; - - /* Size has to be a power of 2 (and multiple of 16) */ - for (i = 1; i < size; i <<= 1); - - guest_mmio += i; - - return addr; -} - -/* - * This routine is used to load the kernel or initrd. It tries mmap, but if - * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), - * it falls back to reading the memory in. - */ -static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) -{ - ssize_t r; - - /* - * We map writable even though for some segments are marked read-only. - * The kernel really wants to be writable: it patches its own - * instructions. - * - * MAP_PRIVATE means that the page won't be copied until a write is - * done to it. This allows us to share untouched memory between - * Guests. - */ - if (mmap(addr, len, PROT_READ|PROT_WRITE, - MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) - return; - - /* pread does a seek and a read in one shot: saves a few lines. */ - r = pread(fd, addr, len, offset); - if (r != len) - err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); -} - -/* - * This routine takes an open vmlinux image, which is in ELF, and maps it into - * the Guest memory. ELF = Embedded Linking Format, which is the format used - * by all modern binaries on Linux including the kernel. - * - * The ELF headers give *two* addresses: a physical address, and a virtual - * address. We use the physical address; the Guest will map itself to the - * virtual address. - * - * We return the starting address. - */ -static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) -{ - Elf32_Phdr phdr[ehdr->e_phnum]; - unsigned int i; - - /* - * Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. - */ - if (ehdr->e_type != ET_EXEC - || ehdr->e_machine != EM_386 - || ehdr->e_phentsize != sizeof(Elf32_Phdr) - || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) - errx(1, "Malformed elf header"); - - /* - * An ELF executable contains an ELF header and a number of "program" - * headers which indicate which parts ("segments") of the program to - * load where. - */ - - /* We read in all the program headers at once: */ - if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) - err(1, "Seeking to program headers"); - if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) - err(1, "Reading program headers"); - - /* - * Try all the headers: there are usually only three. A read-only one, - * a read-write one, and a "note" section which we don't load. - */ - for (i = 0; i < ehdr->e_phnum; i++) { - /* If this isn't a loadable segment, we ignore it */ - if (phdr[i].p_type != PT_LOAD) - continue; - - verbose("Section %i: size %i addr %p\n", - i, phdr[i].p_memsz, (void *)phdr[i].p_paddr); - - /* We map this section of the file at its physical address. */ - map_at(elf_fd, from_guest_phys(phdr[i].p_paddr), - phdr[i].p_offset, phdr[i].p_filesz); - } - - /* The entry point is given in the ELF header. */ - return ehdr->e_entry; -} - -/*L:150 - * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed - * to jump into it and it will unpack itself. We used to have to perform some - * hairy magic because the unpacking code scared me. - * - * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote - * a small patch to jump over the tricky bits in the Guest, so now we just read - * the funky header so we know where in the file to load, and away we go! - */ -static unsigned long load_bzimage(int fd) -{ - struct boot_params boot; - int r; - /* Modern bzImages get loaded at 1M. */ - void *p = from_guest_phys(0x100000); - - /* - * Go back to the start of the file and read the header. It should be - * a Linux boot header (see Documentation/x86/boot.txt) - */ - lseek(fd, 0, SEEK_SET); - read(fd, &boot, sizeof(boot)); - - /* Inside the setup_hdr, we expect the magic "HdrS" */ - if (memcmp(&boot.hdr.header, "HdrS", 4) != 0) - errx(1, "This doesn't look like a bzImage to me"); - - /* Skip over the extra sectors of the header. */ - lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET); - - /* Now read everything into memory. in nice big chunks. */ - while ((r = read(fd, p, 65536)) > 0) - p += r; - - /* Finally, code32_start tells us where to enter the kernel. */ - return boot.hdr.code32_start; -} - -/*L:140 - * Loading the kernel is easy when it's a "vmlinux", but most kernels - * come wrapped up in the self-decompressing "bzImage" format. With a little - * work, we can load those, too. - */ -static unsigned long load_kernel(int fd) -{ - Elf32_Ehdr hdr; - - /* Read in the first few bytes. */ - if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - err(1, "Reading kernel"); - - /* If it's an ELF file, it starts with "\177ELF" */ - if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) - return map_elf(fd, &hdr); - - /* Otherwise we assume it's a bzImage, and try to load it. */ - return load_bzimage(fd); -} - -/* - * This is a trivial little helper to align pages. Andi Kleen hated it because - * it calls getpagesize() twice: "it's dumb code." - * - * Kernel guys get really het up about optimization, even when it's not - * necessary. I leave this code as a reaction against that. - */ -static inline unsigned long page_align(unsigned long addr) -{ - /* Add upwards and truncate downwards. */ - return ((addr + getpagesize()-1) & ~(getpagesize()-1)); -} - -/*L:180 - * An "initial ram disk" is a disk image loaded into memory along with the - * kernel which the kernel can use to boot from without needing any drivers. - * Most distributions now use this as standard: the initrd contains the code to - * load the appropriate driver modules for the current machine. - * - * Importantly, James Morris works for RedHat, and Fedora uses initrds for its - * kernels. He sent me this (and tells me when I break it). - */ -static unsigned long load_initrd(const char *name, unsigned long mem) -{ - int ifd; - struct stat st; - unsigned long len; - - ifd = open_or_die(name, O_RDONLY); - /* fstat() is needed to get the file size. */ - if (fstat(ifd, &st) < 0) - err(1, "fstat() on initrd '%s'", name); - - /* - * We map the initrd at the top of memory, but mmap wants it to be - * page-aligned, so we round the size up for that. - */ - len = page_align(st.st_size); - map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); - /* - * Once a file is mapped, you can close the file descriptor. It's a - * little odd, but quite useful. - */ - close(ifd); - verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); - - /* We return the initrd size. */ - return len; -} -/*:*/ - -/* - * Simple routine to roll all the commandline arguments together with spaces - * between them. - */ -static void concat(char *dst, char *args[]) -{ - unsigned int i, len = 0; - - for (i = 0; args[i]; i++) { - if (i) { - strcat(dst+len, " "); - len++; - } - strcpy(dst+len, args[i]); - len += strlen(args[i]); - } - /* In case it's empty. */ - dst[len] = '\0'; -} - -/*L:185 - * This is where we actually tell the kernel to initialize the Guest. We - * saw the arguments it expects when we looked at initialize() in lguest_user.c: - * the base of Guest "physical" memory, the top physical page to allow and the - * entry point for the Guest. - */ -static void tell_kernel(unsigned long start) -{ - unsigned long args[] = { LHREQ_INITIALIZE, - (unsigned long)guest_base, - guest_limit / getpagesize(), start, - (guest_mmio+getpagesize()-1) / getpagesize() }; - verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n", - guest_base, guest_base + guest_limit, - guest_limit, guest_mmio); - lguest_fd = open_or_die("/dev/lguest", O_RDWR); - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Writing to /dev/lguest"); -} -/*:*/ - -/*L:200 - * Device Handling. - * - * When the Guest gives us a buffer, it sends an array of addresses and sizes. - * We need to make sure it's not trying to reach into the Launcher itself, so - * we have a convenient routine which checks it and exits with an error message - * if something funny is going on: - */ -static void *_check_pointer(struct device *d, - unsigned long addr, unsigned int size, - unsigned int line) -{ - /* - * Check if the requested address and size exceeds the allocated memory, - * or addr + size wraps around. - */ - if ((addr + size) > guest_limit || (addr + size) < addr) - bad_driver(d, "%s:%i: Invalid address %#lx", - __FILE__, line, addr); - /* - * We return a pointer for the caller's convenience, now we know it's - * safe to use. - */ - return from_guest_phys(addr); -} -/* A macro which transparently hands the line number to the real function. */ -#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__) - -/* - * Each buffer in the virtqueues is actually a chain of descriptors. This - * function returns the next descriptor in the chain, or vq->vring.num if we're - * at the end. - */ -static unsigned next_desc(struct device *d, struct vring_desc *desc, - unsigned int i, unsigned int max) -{ - unsigned int next; - - /* If this descriptor says it doesn't chain, we're done. */ - if (!(desc[i].flags & VRING_DESC_F_NEXT)) - return max; - - /* Check they're not leading us off end of descriptors. */ - next = desc[i].next; - /* Make sure compiler knows to grab that: we don't want it changing! */ - wmb(); - - if (next >= max) - bad_driver(d, "Desc next is %u", next); - - return next; -} - -/* - * This actually sends the interrupt for this virtqueue, if we've used a - * buffer. - */ -static void trigger_irq(struct virtqueue *vq) -{ - unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line }; - - /* Don't inform them if nothing used. */ - if (!vq->pending_used) - return; - vq->pending_used = 0; - - /* - * 2.4.7.1: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * The driver MUST set flags to 0 or 1. - */ - if (vq->vring.avail->flags > 1) - bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags); - - /* - * 2.4.7.2: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * - * - The device MUST ignore the used_event value. - * - After the device writes a descriptor index into the used ring: - * - If flags is 1, the device SHOULD NOT send an interrupt. - * - If flags is 0, the device MUST send an interrupt. - */ - if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { - return; - } - - /* - * 4.1.4.5.1: - * - * If MSI-X capability is disabled, the device MUST set the Queue - * Interrupt bit in ISR status before sending a virtqueue notification - * to the driver. - */ - vq->dev->mmio->isr = 0x1; - - /* 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->dev->config.irq_line); -} - -/* - * This looks in the virtqueue for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function waits if necessary, and returns the descriptor number found. - */ -static unsigned wait_for_vq_desc(struct virtqueue *vq, - struct iovec iov[], - unsigned int *out_num, unsigned int *in_num) -{ - unsigned int i, head, max; - struct vring_desc *desc; - u16 last_avail = lg_last_avail(vq); - - /* - * 2.4.7.1: - * - * The driver MUST handle spurious interrupts from the device. - * - * That's why this is a while loop. - */ - - /* There's nothing available? */ - while (last_avail == vq->vring.avail->idx) { - u64 event; - - /* - * Since we're about to sleep, now is a good time to tell the - * Guest about what we've used up to now. - */ - trigger_irq(vq); - - /* OK, now we need to know about added descriptors. */ - vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - - /* - * They could have slipped one in as we were doing that: make - * sure it's written, then check again. - */ - mb(); - if (last_avail != vq->vring.avail->idx) { - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - break; - } - - /* Nothing new? Wait for eventfd to tell us they refilled. */ - if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) - errx(1, "Event read failed?"); - - /* We don't need to be notified again. */ - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - } - - /* Check it isn't doing very strange things with descriptor numbers. */ - if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) - bad_driver_vq(vq, "Guest moved used index from %u to %u", - last_avail, vq->vring.avail->idx); - - /* - * Make sure we read the descriptor number *after* we read the ring - * update; don't let the cpu or compiler change the order. - */ - rmb(); - - /* - * 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) - bad_driver_vq(vq, "Guest says index %u is available", head); - - /* When we start there are none of either input nor output. */ - *out_num = *in_num = 0; - - max = vq->vring.num; - desc = vq->vring.desc; - i = head; - - /* - * We have to read the descriptor after we read the descriptor number, - * but there's a data dependency there so the CPU shouldn't reorder - * that: no rmb() required. - */ - - do { - /* - * 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) { - /* 2.4.5.3.1: - * - * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT - * flag unless the VIRTIO_F_INDIRECT_DESC feature was - * negotiated. - */ - if (!(vq->dev->features_accepted & - (1<<VIRTIO_RING_F_INDIRECT_DESC))) - bad_driver_vq(vq, "vq indirect not negotiated"); - - /* - * 2.4.5.3.1: - * - * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT - * flag within an indirect descriptor (ie. only one - * table per descriptor). - */ - if (desc != vq->vring.desc) - bad_driver_vq(vq, "Indirect within indirect"); - - /* - * Proposed update VIRTIO-134 spells this out: - * - * A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT - * and VIRTQ_DESC_F_NEXT in flags. - */ - if (desc[i].flags & VRING_DESC_F_NEXT) - bad_driver_vq(vq, "indirect and next together"); - - if (desc[i].len % sizeof(struct vring_desc)) - bad_driver_vq(vq, - "Invalid size for indirect table"); - /* - * 2.4.5.3.2: - * - * The device MUST ignore the write-only flag - * (flags&VIRTQ_DESC_F_WRITE) in the descriptor that - * refers to an indirect table. - * - * We ignore it here: :) - */ - - max = desc[i].len / sizeof(struct vring_desc); - desc = check_pointer(vq->dev, desc[i].addr, desc[i].len); - i = 0; - - /* 2.4.5.3.1: - * - * A driver MUST NOT create a descriptor chain longer - * than the Queue Size of the device. - */ - if (max > vq->pci_config.queue_size) - bad_driver_vq(vq, - "indirect has too many entries"); - } - - /* Grab the first descriptor, and check it's OK. */ - iov[*out_num + *in_num].iov_len = desc[i].len; - iov[*out_num + *in_num].iov_base - = check_pointer(vq->dev, desc[i].addr, desc[i].len); - /* If this is an input descriptor, increment that count. */ - if (desc[i].flags & VRING_DESC_F_WRITE) - (*in_num)++; - else { - /* - * If it's an output descriptor, they're all supposed - * to come before any input descriptors. - */ - if (*in_num) - bad_driver_vq(vq, - "Descriptor has out after in"); - (*out_num)++; - } - - /* If we've got too many, that implies a descriptor loop. */ - if (*out_num + *in_num > max) - bad_driver_vq(vq, "Looped descriptor"); - } while ((i = next_desc(vq->dev, desc, i, max)) != max); - - return head; -} - -/* - * After we've used one of their buffers, we tell the Guest about it. Sometime - * later we'll want to send them an interrupt using trigger_irq() |