From 415e6b0a686989d0000a82ba8404d4ab9cd1e6b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Fabian=20Silva=20Delgado?= Date: Tue, 21 Feb 2012 11:39:38 -0200 Subject: kernels/xe-guest-utilities --- kernels/xen/09_xen | 123 ++ kernels/xen/24341.patch | 11 + kernels/xen/24344.patch | 33 + kernels/xen/24345.patch | 31 + kernels/xen/PKGBUILD | 99 + kernels/xen/dom0_xz_decompression.patch | 3528 +++++++++++++++++++++++++++++++ kernels/xen/parabolainit.patch | 423 ++++ kernels/xen/xen.patch | 21 + 8 files changed, 4269 insertions(+) create mode 100755 kernels/xen/09_xen create mode 100644 kernels/xen/24341.patch create mode 100644 kernels/xen/24344.patch create mode 100644 kernels/xen/24345.patch create mode 100644 kernels/xen/PKGBUILD create mode 100644 kernels/xen/dom0_xz_decompression.patch create mode 100644 kernels/xen/parabolainit.patch create mode 100644 kernels/xen/xen.patch (limited to 'kernels/xen') diff --git a/kernels/xen/09_xen b/kernels/xen/09_xen new file mode 100755 index 000000000..094b7f427 --- /dev/null +++ b/kernels/xen/09_xen @@ -0,0 +1,123 @@ +#! /bin/sh -e + +if [ -f /usr/lib/grub/grub-mkconfig_lib ]; then + . /usr/lib/grub/grub-mkconfig_lib +else + # no grub file, so we notify and exit gracefully + echo "Cannot find grub config file, exiting." >&2 + exit 0 +fi + +XEN_HYPERVISOR_CMDLINE= +XEN_LINUX_CMDLINE="console=tty0" +[ -r /etc/xen/grub.conf ] && . /etc/xen/grub.conf + +CLASS="--class gnu-linux --class gnu --class os" + +if [ "x${GRUB_DISTRIBUTOR}" = "x" ] ; then + OS=GNU/Linux +else + OS="${GRUB_DISTRIBUTOR}" + CLASS="--class $(echo ${GRUB_DISTRIBUTOR} | tr '[A-Z]' '[a-z]' | cut -d' ' -f1) ${CLASS}" +fi + +# loop-AES arranges things so that /dev/loop/X can be our root device, but +# the initrds that Linux uses don't like that. +case ${GRUB_DEVICE} in + /dev/loop/*|/dev/loop[0-9]) + GRUB_DEVICE=`losetup ${GRUB_DEVICE} | sed -e "s/^[^(]*(\([^)]\+\)).*/\1/"` + ;; +esac + +if [ "x${GRUB_DEVICE_UUID}" = "x" ] || [ "x${GRUB_DISABLE_LINUX_UUID}" = "xtrue" ] \ + || ! test -e "/dev/disk/by-uuid/${GRUB_DEVICE_UUID}" \ + || [ "`grub-probe -t abstraction --device ${GRUB_DEVICE} | sed -e 's,.*\(lvm\).*,\1,'`" = "lvm" ] ; then + LINUX_ROOT_DEVICE=${GRUB_DEVICE} +else + LINUX_ROOT_DEVICE=UUID=${GRUB_DEVICE_UUID} +fi + +xen_entry () +{ + os="$1" + xen_version="$2" + version="$3" + xen_args="$4" + args="$5" + printf "menuentry 'Xen %s / %s, with Linux %s' --class xen ${CLASS} {\n" "${xen_version}" "${os}" "${version}" + save_default_entry | sed -e "s/^/\t/" + + if [ -z "${prepare_boot_cache}" ]; then + prepare_boot_cache="$(prepare_grub_to_access_device ${GRUB_DEVICE_BOOT} | sed -e "s/^/\t/")" + fi + printf '%s\n' "${prepare_boot_cache}" + cat << EOF + echo '$(printf "Loading Xen %s ..." ${xen_version})' + multiboot ${rel_dirname}/${xen_basename} ${rel_dirname}/${xen_basename} ${xen_args} + echo $(printf "$(gettext "Loading Linux %s ...")" ${version}) + module ${rel_dirname}/${basename} ${rel_dirname}/${basename} root=${linux_root_device_thisversion} ro ${args} +EOF + if test -n "${initrd}" ; then + cat << EOF + echo "Loading initial ramdisk ..." + module ${rel_dirname}/${initrd} +EOF + fi + cat << EOF +} +EOF +} + +xen_list=`for i in /boot/xen-*.gz /xen-*.gz ; do + if grub_file_is_not_garbage "$i" ; then echo -n "$i "; fi +done` +prepare_boot_cache= + +while [ "x$xen_list" != "x" ] ; do + xen=`version_find_latest $xen_list` + echo "Found Xen hypervisor image: $xen" >&2 + xen_basename=`basename $xen` + xen_dirname=`dirname $xen` + rel_xen_dirname=`make_system_path_relative_to_its_root $xen_dirname` + xen_version=`echo $xen_basename | sed -e "s,^[^0-9]*-,,g" | sed -e "s,.gz,,g"` + alt_xen_version=`echo $xen_version | sed -e "s,\.old$,,g"` + + xen_configfiles=`grep -l 'CONFIG_XEN_PRIVILEGED_GUEST=y' /boot/config-*` + + list="/boot/vmlinuz-linux-libre"; + + while [ "x$list" != "x" ] ; do + linux=`version_find_latest $list` + echo -e "\tFound linux image: $linux" >&2 + basename=`basename $linux` + dirname=`dirname $linux` + rel_dirname=`make_system_path_relative_to_its_root $dirname` + version=`echo $basename | sed -e "s,^[^0-9]*-,,g"` + base_init=`echo $basename | sed -e "s,vmlinuz,initramfs,g"` + alt_version="${base_init}-fallback" + linux_root_device_thisversion="${LINUX_ROOT_DEVICE}" + initrd= + + for i in "${base_init}.img"; do + if test -e "${dirname}/${i}" ; then + initrd="$i" + break + fi + done + if test -n "${initrd}" ; then + echo -e "\tFound initrd image: ${dirname}/${initrd}" >&2 + else + # "UUID=" magic is parsed by initrds. Since there's no initrd, it can't work here. + linux_root_device_thisversion=${GRUB_DEVICE} + fi + + xen_entry "${OS}" "${xen_version}" "${version}" \ + "${XEN_HYPERVISOR_CMDLINE}" \ + "${XEN_LINUX_CMDLINE}" + + list=`echo $list | tr ' ' '\n' | grep -vx $linux | tr '\n' ' '` + done + + xen_list=`echo $xen_list | tr ' ' '\n' | grep -vx $xen | tr '\n' ' '` +done + diff --git a/kernels/xen/24341.patch b/kernels/xen/24341.patch new file mode 100644 index 000000000..5554004d3 --- /dev/null +++ b/kernels/xen/24341.patch @@ -0,0 +1,11 @@ +--- a/xen/arch/x86/x86_64/mmconfig_64.c 2011-10-20 15:05:49.000000000 -0200 ++++ b/xen/arch/x86/x86_64/mmconfig_64.c 2012-02-14 23:45:47.481729733 -0200 +@@ -23,7 +23,7 @@ + char __iomem *virt; + }; + static struct mmcfg_virt *pci_mmcfg_virt; +-static int __initdata mmcfg_pci_segment_shift; ++static unsigned int mmcfg_pci_segment_shift; + + static char __iomem *get_virt(unsigned int seg, unsigned bus) + { diff --git a/kernels/xen/24344.patch b/kernels/xen/24344.patch new file mode 100644 index 000000000..642b90867 --- /dev/null +++ b/kernels/xen/24344.patch @@ -0,0 +1,33 @@ +--- a/tools/libxc/xc_cpuid_x86.c 2011-10-20 15:05:42.000000000 -0200 ++++ b/tools/libxc/xc_cpuid_x86.c 2012-02-15 00:01:46.307514813 -0200 +@@ -42,23 +42,23 @@ + static void cpuid(const unsigned int *input, unsigned int *regs) + { + unsigned int count = (input[1] == XEN_CPUID_INPUT_UNUSED) ? 0 : input[1]; +- asm ( + #ifdef __i386__ ++/* Use the stack to avoid reg constraint failures with some gcc flags */ ++ asm ( + "push %%ebx; push %%edx\n\t" +-#else +- "push %%rbx; push %%rdx\n\t" +-#endif + "cpuid\n\t" + "mov %%ebx,4(%4)\n\t" + "mov %%edx,12(%4)\n\t" +-#ifdef __i386__ + "pop %%edx; pop %%ebx\n\t" ++ : "=a" (regs[0]), "=c" (regs[2]) ++ : "0" (input[0]), "1" (count), "S" (regs) ++ : "memory" ); + #else +- "pop %%rdx; pop %%rbx\n\t" ++ asm ( ++ "cpuid" ++ : "=a" (regs[0]), "=b" (regs[1]), "=c" (regs[2]), "=d" (regs[3]) ++ : "0" (input[0]), "2" (count) ); + #endif +- : "=a" (regs[0]), "=c" (regs[2]) +- : "0" (input[0]), "1" (count), "S" (regs) +- : "memory" ); + } diff --git a/kernels/xen/24345.patch b/kernels/xen/24345.patch new file mode 100644 index 000000000..e75a1b38c --- /dev/null +++ b/kernels/xen/24345.patch @@ -0,0 +1,31 @@ +--- a/tools/misc/xen-detect.c 2011-10-20 15:05:43.000000000 -0200 ++++ b/tools/misc/xen-detect.c 2012-02-15 00:05:55.524455578 -0200 +@@ -35,18 +35,21 @@ + + static void cpuid(uint32_t idx, uint32_t *regs, int pv_context) + { +- asm volatile ( + #ifdef __i386__ +-#define R(x) "%%e"#x"x" +-#else +-#define R(x) "%%r"#x"x" +-#endif +- "push "R(a)"; push "R(b)"; push "R(c)"; push "R(d)"\n\t" ++/* Use the stack to avoid reg constraint failures with some gcc flags */ ++ asm volatile ( ++ "push %%eax; push %%ebx; push %%ecx; push %%edx\n\t" + "test %1,%1 ; jz 1f ; ud2a ; .ascii \"xen\" ; 1: cpuid\n\t" + "mov %%eax,(%2); mov %%ebx,4(%2)\n\t" + "mov %%ecx,8(%2); mov %%edx,12(%2)\n\t" +- "pop "R(d)"; pop "R(c)"; pop "R(b)"; pop "R(a)"\n\t" ++ "pop %%edx; pop %%ecx; pop %%ebx; pop %%eax\n\t" + : : "a" (idx), "c" (pv_context), "S" (regs) : "memory" ); ++#else ++ asm volatile ( ++ "test %5,%5 ; jz 1f ; ud2a ; .ascii \"xen\" ; 1: cpuid\n\t" ++ : "=a" (regs[0]), "=b" (regs[1]), "=c" (regs[2]), "=d" (regs[3]) ++ : "0" (idx), "1" (pv_context), "2" (0) ); ++#endif + } + + static int check_for_xen(int pv_context) diff --git a/kernels/xen/PKGBUILD b/kernels/xen/PKGBUILD new file mode 100644 index 000000000..e1796106a --- /dev/null +++ b/kernels/xen/PKGBUILD @@ -0,0 +1,99 @@ +#Mantainer M0Rf30 +#Contributor WaxyMouthfeel +# Contributor (Parabola): André Silva +pkgname=xen +pkgver=4.1.2 +pkgrel=2 +pkgdesc="Xen 4 (hypervisor and tools)" +arch=(i686 x86_64) +url="http://xen.org/" +license="GPL" +depends=('xz-utils' 'bzip2' 'iproute' 'bridge-utils' 'python2' 'sdl' 'zlib' 'e2fsprogs' 'pkgconfig' 'gnutls' 'lzo2' 'glibc') +[ "$CARCH" == "x86_64" ] && depends=(${depends} 'lib32-glibc') +optdepends=('xen-docs: Xen Official Documentation') +makedepends=('dev86' 'bin86' 'ocaml-findlib' 'iasl') +conflicts=('xen4' 'xen3' 'xen-hv-tools' 'libxen4') +provides=('xen') +backup=('etc/xen/xend-config.sxp' 'etc/xen/xend-pci-permissive.sxp' 'etc/xen/xend-pci-quirks.sxp') +options=(!strip) +optional=(xen-docs) +source=(http://bits.xensource.com/oss-xen/release/${pkgver}/xen-${pkgver}.tar.gz + 09_xen + xen.patch + parabolainit.patch + dom0_xz_decompression.patch + 24341.patch + 24344.patch + 24345.patch) + +build() { + + + cd $srcdir/xen-${pkgver} + + patch -p1 -i ../xen.patch + patch -p1 -i ../parabolainit.patch + patch -p1 -i ../dom0_xz_decompression.patch + patch -p1 -i ../24341.patch + patch -p1 -i ../24344.patch + patch -p1 -i ../24345.patch + +unset CFLAGS LDFLAGS + +make PYTHON=python2 DESTDIR=$pkgdir install-xen +make PYTHON=python2 DESTDIR=$pkgdir install-tools +#make PYTHON=python2 DESTDIR=$pkgdir install-stubdom + + sed -i 's#XENDOM_CONFIG=/etc/sysconfig/xendomains#XENDOM_CONFIG=/etc/conf.d/xendomains#' $pkgdir/etc/init.d/xendomains + sed -i "s#touch /var/lock/subsys/xend#mkdir -p /var/lock/subsys\n touch /var/lock/subsys/xend#" $pkgdir/etc/init.d/xend + + [ -d $pkgdir/usr/lib64 ] && ( cd $pkgdir/usr && cp -R lib64/* lib/ && rm -R lib64 ) + ( cd $pkgdir/etc && mv init.d rc.d ) || return 1 + rm -f $pkgdir/usr/share/man/man1/qemu-img.1* \ + $pkgdir/usr/share/man/man1/qemu.1* + # First experiment to generate grub2.cfg entry + mkdir -p $pkgdir/etc/grub.d + chmod +x $srcdir/09_xen + cp $srcdir/09_xen $pkgdir/etc/grub.d + + ############ kill unwanted stuff ############ + +# stubdom: newlib +rm -rf $pkgdir/usr/*-xen-elf + +# hypervisor symlinks +rm -rf $pkgdir/boot/xen-4.1.gz +rm -rf $pkgdir/boot/xen-4.gz +rm -rf $pkgdir/boot/xen.gz + +# silly doc dir fun +rm -fr $pkgdir/usr/share/doc/xen +rm -rf $pkgdir/usr/share/doc/qemu + +# Pointless helper +rm -f $pkgdir/usr/sbin/xen-python-path + +# qemu stuff (unused or available from upstream) +rm -rf $pkgdir/usr/share/xen/man +rm -rf $pkgdir/usr/bin/qemu-*-xen +for file in bios.bin openbios-sparc32 openbios-sparc64 ppc_rom.bin \ + pxe-e1000.bin pxe-ne2k_pci.bin pxe-pcnet.bin pxe-rtl8139.bin \ + vgabios.bin vgabios-cirrus.bin video.x openbios-ppc bamboo.dtb +do + rm -f $pkgdir/usr/share/xen/qemu/$file +done + +# adhere to Static Library Packaging Guidelines +rm -rf $pkgdir/usr/lib/*.a + + +} + +md5sums=('73561faf3c1b5e36ec5c089b5db848ad' + '8d50beba46ffd89a3b959176245b676e' + 'f149bae1a6b420e49c51b9f3a74338a4' + '7a1ed81ecc828037724bb3280058c9fc' + '4aebccf16b578ed97aa8bab945011f35' + '1b0c05a555bc99fc8416dd52b6c6ae95' + 'b6225be5bec3fe462f9166f9fde9c347' + 'd282946a2873a78b2b2c3944571eb2fe') diff --git a/kernels/xen/dom0_xz_decompression.patch b/kernels/xen/dom0_xz_decompression.patch new file mode 100644 index 000000000..277ebcfd2 --- /dev/null +++ b/kernels/xen/dom0_xz_decompression.patch @@ -0,0 +1,3528 @@ +diff --git a/xen/common/Makefile b/xen/common/Makefile +--- a/xen/common/Makefile ++++ b/xen/common/Makefile +@@ -43,7 +43,7 @@ + obj-y += rbtree.o + obj-y += lzo.o + +-obj-$(CONFIG_X86) += decompress.o bunzip2.o unlzma.o unlzo.o ++obj-$(CONFIG_X86) += decompress.o bunzip2.o unxz.o unlzma.o unlzo.o + + obj-$(perfc) += perfc.o + obj-$(crash_debug) += gdbstub.o +diff --git a/xen/common/decompress.c b/xen/common/decompress.c +--- a/xen/common/decompress.c ++++ b/xen/common/decompress.c +@@ -20,6 +20,9 @@ + if ( len >= 3 && !memcmp(inbuf, "\x42\x5a\x68", 3) ) + return bunzip2(inbuf, len, NULL, NULL, outbuf, NULL, error); + ++ if ( len >= 6 && !memcmp(inbuf, "\3757zXZ", 6) ) ++ return unxz(inbuf, len, NULL, NULL, outbuf, NULL, error); ++ + if ( len >= 2 && !memcmp(inbuf, "\135\000", 2) ) + return unlzma(inbuf, len, NULL, NULL, outbuf, NULL, error); + +diff --git a/xen/common/decompress.h b/xen/common/decompress.h +--- a/xen/common/decompress.h ++++ b/xen/common/decompress.h +@@ -8,6 +8,7 @@ + + #define STATIC + #define INIT __init ++#define INITDATA __initdata + + static void(*__initdata error)(const char *); + #define set_error_fn(x) error = x; +diff --git a/xen/common/unxz.c b/xen/common/unxz.c +new file mode 100644 +--- /dev/null ++++ b/xen/common/unxz.c +@@ -0,0 +1,306 @@ ++/* ++ * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++/* ++ * Important notes about in-place decompression ++ * ++ * At least on x86, the kernel is decompressed in place: the compressed data ++ * is placed to the end of the output buffer, and the decompressor overwrites ++ * most of the compressed data. There must be enough safety margin to ++ * guarantee that the write position is always behind the read position. ++ * ++ * The safety margin for XZ with LZMA2 or BCJ+LZMA2 is calculated below. ++ * Note that the margin with XZ is bigger than with Deflate (gzip)! ++ * ++ * The worst case for in-place decompression is that the beginning of ++ * the file is compressed extremely well, and the rest of the file is ++ * uncompressible. Thus, we must look for worst-case expansion when the ++ * compressor is encoding uncompressible data. ++ * ++ * The structure of the .xz file in case of a compresed kernel is as follows. ++ * Sizes (as bytes) of the fields are in parenthesis. ++ * ++ * Stream Header (12) ++ * Block Header: ++ * Block Header (8-12) ++ * Compressed Data (N) ++ * Block Padding (0-3) ++ * CRC32 (4) ++ * Index (8-20) ++ * Stream Footer (12) ++ * ++ * Normally there is exactly one Block, but let's assume that there are ++ * 2-4 Blocks just in case. Because Stream Header and also Block Header ++ * of the first Block don't make the decompressor produce any uncompressed ++ * data, we can ignore them from our calculations. Block Headers of possible ++ * additional Blocks have to be taken into account still. With these ++ * assumptions, it is safe to assume that the total header overhead is ++ * less than 128 bytes. ++ * ++ * Compressed Data contains LZMA2 or BCJ+LZMA2 encoded data. Since BCJ ++ * doesn't change the size of the data, it is enough to calculate the ++ * safety margin for LZMA2. ++ * ++ * LZMA2 stores the data in chunks. Each chunk has a header whose size is ++ * a maximum of 6 bytes, but to get round 2^n numbers, let's assume that ++ * the maximum chunk header size is 8 bytes. After the chunk header, there ++ * may be up to 64 KiB of actual payload in the chunk. Often the payload is ++ * quite a bit smaller though; to be safe, let's assume that an average ++ * chunk has only 32 KiB of payload. ++ * ++ * The maximum uncompressed size of the payload is 2 MiB. The minimum ++ * uncompressed size of the payload is in practice never less than the ++ * payload size itself. The LZMA2 format would allow uncompressed size ++ * to be less than the payload size, but no sane compressor creates such ++ * files. LZMA2 supports storing uncompressible data in uncompressed form, ++ * so there's never a need to create payloads whose uncompressed size is ++ * smaller than the compressed size. ++ * ++ * The assumption, that the uncompressed size of the payload is never ++ * smaller than the payload itself, is valid only when talking about ++ * the payload as a whole. It is possible that the payload has parts where ++ * the decompressor consumes more input than it produces output. Calculating ++ * the worst case for this would be tricky. Instead of trying to do that, ++ * let's simply make sure that the decompressor never overwrites any bytes ++ * of the payload which it is currently reading. ++ * ++ * Now we have enough information to calculate the safety margin. We need ++ * - 128 bytes for the .xz file format headers; ++ * - 8 bytes per every 32 KiB of uncompressed size (one LZMA2 chunk header ++ * per chunk, each chunk having average payload size of 32 KiB); and ++ * - 64 KiB (biggest possible LZMA2 chunk payload size) to make sure that ++ * the decompressor never overwrites anything from the LZMA2 chunk ++ * payload it is currently reading. ++ * ++ * We get the following formula: ++ * ++ * safety_margin = 128 + uncompressed_size * 8 / 32768 + 65536 ++ * = 128 + (uncompressed_size >> 12) + 65536 ++ * ++ * For comparision, according to arch/x86/boot/compressed/misc.c, the ++ * equivalent formula for Deflate is this: ++ * ++ * safety_margin = 18 + (uncompressed_size >> 12) + 32768 ++ * ++ * Thus, when updating Deflate-only in-place kernel decompressor to ++ * support XZ, the fixed overhead has to be increased from 18+32768 bytes ++ * to 128+65536 bytes. ++ */ ++ ++#include "decompress.h" ++ ++#define XZ_EXTERN STATIC ++ ++/* ++ * For boot time use, we enable only the BCJ filter of the current ++ * architecture or none if no BCJ filter is available for the architecture. ++ */ ++#ifdef CONFIG_X86 ++# define XZ_DEC_X86 ++#endif ++#ifdef CONFIG_PPC ++# define XZ_DEC_POWERPC ++#endif ++#ifdef CONFIG_ARM ++# define XZ_DEC_ARM ++#endif ++#ifdef CONFIG_IA64 ++# define XZ_DEC_IA64 ++#endif ++#ifdef CONFIG_SPARC ++# define XZ_DEC_SPARC ++#endif ++ ++/* ++ * This will get the basic headers so that memeq() and others ++ * can be defined. ++ */ ++#include "xz/private.h" ++ ++/* ++ * memeq and memzero are not used much and any remotely sane implementation ++ * is fast enough. memcpy/memmove speed matters in multi-call mode, but ++ * the kernel image is decompressed in single-call mode, in which only ++ * memcpy speed can matter and only if there is a lot of uncompressible data ++ * (LZMA2 stores uncompressible chunks in uncompressed form). Thus, the ++ * functions below should just be kept small; it's probably not worth ++ * optimizing for speed. ++ */ ++ ++#ifndef memeq ++#define memeq(p1, p2, sz) (memcmp(p1, p2, sz) == 0) ++#endif ++ ++#ifndef memzero ++#define memzero(p, sz) memset(p, 0, sz) ++#endif ++ ++#include "xz/crc32.c" ++#include "xz/dec_stream.c" ++#include "xz/dec_lzma2.c" ++#include "xz/dec_bcj.c" ++ ++/* Size of the input and output buffers in multi-call mode */ ++#define XZ_IOBUF_SIZE 4096 ++ ++/* ++ * This function implements the API defined in . ++ * ++ * This wrapper will automatically choose single-call or multi-call mode ++ * of the native XZ decoder API. The single-call mode can be used only when ++ * both input and output buffers are available as a single chunk, i.e. when ++ * fill() and flush() won't be used. ++ */ ++STATIC int INIT unxz(unsigned char *in, unsigned int in_size, ++ int (*fill)(void *dest, unsigned int size), ++ int (*flush)(void *src, unsigned int size), ++ unsigned char *out, unsigned int *in_used, ++ void (*error_fn)(const char *x)) ++{ ++ struct xz_buf b; ++ struct xz_dec *s; ++ enum xz_ret ret; ++ bool_t must_free_in = false; ++ ++ set_error_fn(error_fn); ++ ++ xz_crc32_init(); ++ ++ if (in_used != NULL) ++ *in_used = 0; ++ ++ if (fill == NULL && flush == NULL) ++ s = xz_dec_init(XZ_SINGLE, 0); ++ else ++ s = xz_dec_init(XZ_DYNALLOC, (uint32_t)-1); ++ ++ if (s == NULL) ++ goto error_alloc_state; ++ ++ if (flush == NULL) { ++ b.out = out; ++ b.out_size = (size_t)-1; ++ } else { ++ b.out_size = XZ_IOBUF_SIZE; ++ b.out = malloc(XZ_IOBUF_SIZE); ++ if (b.out == NULL) ++ goto error_alloc_out; ++ } ++ ++ if (in == NULL) { ++ must_free_in = true; ++ in = malloc(XZ_IOBUF_SIZE); ++ if (in == NULL) ++ goto error_alloc_in; ++ } ++ ++ b.in = in; ++ b.in_pos = 0; ++ b.in_size = in_size; ++ b.out_pos = 0; ++ ++ if (fill == NULL && flush == NULL) { ++ ret = xz_dec_run(s, &b); ++ } else { ++ do { ++ if (b.in_pos == b.in_size && fill != NULL) { ++ if (in_used != NULL) ++ *in_used += b.in_pos; ++ ++ b.in_pos = 0; ++ ++ in_size = fill(in, XZ_IOBUF_SIZE); ++ if (in_size < 0) { ++ /* ++ * This isn't an optimal error code ++ * but it probably isn't worth making ++ * a new one either. ++ */ ++ ret = XZ_BUF_ERROR; ++ break; ++ } ++ ++ b.in_size = in_size; ++ } ++ ++ ret = xz_dec_run(s, &b); ++ ++ if (flush != NULL && (b.out_pos == b.out_size ++ || (ret != XZ_OK && b.out_pos > 0))) { ++ /* ++ * Setting ret here may hide an error ++ * returned by xz_dec_run(), but probably ++ * it's not too bad. ++ */ ++ if (flush(b.out, b.out_pos) != (int)b.out_pos) ++ ret = XZ_BUF_ERROR; ++ ++ b.out_pos = 0; ++ } ++ } while (ret == XZ_OK); ++ ++ if (must_free_in) ++ free(in); ++ ++ if (flush != NULL) ++ free(b.out); ++ } ++ ++ if (in_used != NULL) ++ *in_used += b.in_pos; ++ ++ xz_dec_end(s); ++ ++ switch (ret) { ++ case XZ_STREAM_END: ++ return 0; ++ ++ case XZ_MEM_ERROR: ++ /* This can occur only in multi-call mode. */ ++ error("XZ decompressor ran out of memory"); ++ break; ++ ++ case XZ_FORMAT_ERROR: ++ error("Input is not in the XZ format (wrong magic bytes)"); ++ break; ++ ++ case XZ_OPTIONS_ERROR: ++ error("Input was encoded with settings that are not " ++ "supported by this XZ decoder"); ++ break; ++ ++ case XZ_DATA_ERROR: ++ case XZ_BUF_ERROR: ++ error("XZ-compressed data is corrupt"); ++ break; ++ ++ default: ++ error("Bug in the XZ decompressor"); ++ break; ++ } ++ ++ return -1; ++ ++error_alloc_in: ++ if (flush != NULL) ++ free(b.out); ++ ++error_alloc_out: ++ xz_dec_end(s); ++ ++error_alloc_state: ++ error("XZ decompressor ran out of memory"); ++ return -1; ++} ++ ++/* ++ * This macro is used by architecture-specific files to decompress ++ * the kernel image. ++ */ ++#define decompress unxz +diff --git a/xen/common/xz/crc32.c b/xen/common/xz/crc32.c +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/crc32.c +@@ -0,0 +1,51 @@ ++/* ++ * CRC32 using the polynomial from IEEE-802.3 ++ * ++ * Authors: Lasse Collin ++ * Igor Pavlov ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++/* ++ * This is not the fastest implementation, but it is pretty compact. ++ * The fastest versions of xz_crc32() on modern CPUs without hardware ++ * accelerated CRC instruction are 3-5 times as fast as this version, ++ * but they are bigger and use more memory for the lookup table. ++ */ ++ ++#include "private.h" ++ ++XZ_EXTERN uint32_t INITDATA xz_crc32_table[256]; ++ ++XZ_EXTERN void INIT xz_crc32_init(void) ++{ ++ const uint32_t poly = 0xEDB88320; ++ ++ uint32_t i; ++ uint32_t j; ++ uint32_t r; ++ ++ for (i = 0; i < 256; ++i) { ++ r = i; ++ for (j = 0; j < 8; ++j) ++ r = (r >> 1) ^ (poly & ~((r & 1) - 1)); ++ ++ xz_crc32_table[i] = r; ++ } ++ ++ return; ++} ++ ++XZ_EXTERN uint32_t INIT xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) ++{ ++ crc = ~crc; ++ ++ while (size != 0) { ++ crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8); ++ --size; ++ } ++ ++ return ~crc; ++} +diff --git a/xen/common/xz/dec_bcj.c b/xen/common/xz/dec_bcj.c +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/dec_bcj.c +@@ -0,0 +1,562 @@ ++/* ++ * Branch/Call/Jump (BCJ) filter decoders ++ * ++ * Authors: Lasse Collin ++ * Igor Pavlov ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#include "private.h" ++ ++/* ++ * The rest of the file is inside this ifdef. It makes things a little more ++ * convenient when building without support for any BCJ filters. ++ */ ++#ifdef XZ_DEC_BCJ ++ ++struct xz_dec_bcj { ++ /* Type of the BCJ filter being used */ ++ enum { ++ BCJ_X86 = 4, /* x86 or x86-64 */ ++ BCJ_POWERPC = 5, /* Big endian only */ ++ BCJ_IA64 = 6, /* Big or little endian */ ++ BCJ_ARM = 7, /* Little endian only */ ++ BCJ_ARMTHUMB = 8, /* Little endian only */ ++ BCJ_SPARC = 9 /* Big or little endian */ ++ } type; ++ ++ /* ++ * Return value of the next filter in the chain. We need to preserve ++ * this information across calls, because we must not call the next ++ * filter anymore once it has returned XZ_STREAM_END. ++ */ ++ enum xz_ret ret; ++ ++ /* True if we are operating in single-call mode. */ ++ bool_t single_call; ++ ++ /* ++ * Absolute position relative to the beginning of the uncompressed ++ * data (in a single .xz Block). We care only about the lowest 32 ++ * bits so this doesn't need to be uint64_t even with big files. ++ */ ++ uint32_t pos; ++ ++ /* x86 filter state */ ++ uint32_t x86_prev_mask; ++ ++ /* Temporary space to hold the variables from struct xz_buf */ ++ uint8_t *out; ++ size_t out_pos; ++ size_t out_size; ++ ++ struct { ++ /* Amount of already filtered data in the beginning of buf */ ++ size_t filtered; ++ ++ /* Total amount of data currently stored in buf */ ++ size_t size; ++ ++ /* ++ * Buffer to hold a mix of filtered and unfiltered data. This ++ * needs to be big enough to hold Alignment + 2 * Look-ahead: ++ * ++ * Type Alignment Look-ahead ++ * x86 1 4 ++ * PowerPC 4 0 ++ * IA-64 16 0 ++ * ARM 4 0 ++ * ARM-Thumb 2 2 ++ * SPARC 4 0 ++ */ ++ uint8_t buf[16]; ++ } temp; ++}; ++ ++#ifdef XZ_DEC_X86 ++/* ++ * This is used to test the most significant byte of a memory address ++ * in an x86 instruction. ++ */ ++static inline int INIT bcj_x86_test_msbyte(uint8_t b) ++{ ++ return b == 0x00 || b == 0xFF; ++} ++ ++static size_t INIT bcj_x86(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ static /*const*/ bool_t INITDATA mask_to_allowed_status[8] ++ = { true, true, true, false, true, false, false, false }; ++ ++ static /*const*/ uint8_t INITDATA mask_to_bit_num[8] ++ = { 0, 1, 2, 2, 3, 3, 3, 3 }; ++ ++ size_t i; ++ size_t prev_pos = (size_t)-1; ++ uint32_t prev_mask = s->x86_prev_mask; ++ uint32_t src; ++ uint32_t dest; ++ uint32_t j; ++ uint8_t b; ++ ++ if (size <= 4) ++ return 0; ++ ++ size -= 4; ++ for (i = 0; i < size; ++i) { ++ if ((buf[i] & 0xFE) != 0xE8) ++ continue; ++ ++ prev_pos = i - prev_pos; ++ if (prev_pos > 3) { ++ prev_mask = 0; ++ } else { ++ prev_mask = (prev_mask << (prev_pos - 1)) & 7; ++ if (prev_mask != 0) { ++ b = buf[i + 4 - mask_to_bit_num[prev_mask]]; ++ if (!mask_to_allowed_status[prev_mask] ++ || bcj_x86_test_msbyte(b)) { ++ prev_pos = i; ++ prev_mask = (prev_mask << 1) | 1; ++ continue; ++ } ++ } ++ } ++ ++ prev_pos = i; ++ ++ if (bcj_x86_test_msbyte(buf[i + 4])) { ++ src = get_unaligned_le32(buf + i + 1); ++ while (true) { ++ dest = src - (s->pos + (uint32_t)i + 5); ++ if (prev_mask == 0) ++ break; ++ ++ j = mask_to_bit_num[prev_mask] * 8; ++ b = (uint8_t)(dest >> (24 - j)); ++ if (!bcj_x86_test_msbyte(b)) ++ break; ++ ++ src = dest ^ (((uint32_t)1 << (32 - j)) - 1); ++ } ++ ++ dest &= 0x01FFFFFF; ++ dest |= (uint32_t)0 - (dest & 0x01000000); ++ put_unaligned_le32(dest, buf + i + 1); ++ i += 4; ++ } else { ++ prev_mask = (prev_mask << 1) | 1; ++ } ++ } ++ ++ prev_pos = i - prev_pos; ++ s->x86_prev_mask = prev_pos > 3 ? 0 : prev_mask << (prev_pos - 1); ++ return i; ++} ++#endif ++ ++#ifdef XZ_DEC_POWERPC ++static size_t INIT bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ size_t i; ++ uint32_t instr; ++ ++ for (i = 0; i + 4 <= size; i += 4) { ++ instr = get_unaligned_be32(buf + i); ++ if ((instr & 0xFC000003) == 0x48000001) { ++ instr &= 0x03FFFFFC; ++ instr -= s->pos + (uint32_t)i; ++ instr &= 0x03FFFFFC; ++ instr |= 0x48000001; ++ put_unaligned_be32(instr, buf + i); ++ } ++ } ++ ++ return i; ++} ++#endif ++ ++#ifdef XZ_DEC_IA64 ++static size_t INIT bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ static const uint8_t branch_table[32] = { ++ 0, 0, 0, 0, 0, 0, 0, 0, ++ 0, 0, 0, 0, 0, 0, 0, 0, ++ 4, 4, 6, 6, 0, 0, 7, 7, ++ 4, 4, 0, 0, 4, 4, 0, 0 ++ }; ++ ++ /* ++ * The local variables take a little bit stack space, but it's less ++ * than what LZMA2 decoder takes, so it doesn't make sense to reduce ++ * stack usage here without doing that for the LZMA2 decoder too. ++ */ ++ ++ /* Loop counters */ ++ size_t i; ++ size_t j; ++ ++ /* Instruction slot (0, 1, or 2) in the 128-bit instruction word */ ++ uint32_t slot; ++ ++ /* Bitwise offset of the instruction indicated by slot */ ++ uint32_t bit_pos; ++ ++ /* bit_pos split into byte and bit parts */ ++ uint32_t byte_pos; ++ uint32_t bit_res; ++ ++ /* Address part of an instruction */ ++ uint32_t addr; ++ ++ /* Mask used to detect which instructions to convert */ ++ uint32_t mask; ++ ++ /* 41-bit instruction stored somewhere in the lowest 48 bits */ ++ uint64_t instr; ++ ++ /* Instruction normalized with bit_res for easier manipulation */ ++ uint64_t norm; ++ ++ for (i = 0; i + 16 <= size; i += 16) { ++ mask = branch_table[buf[i] & 0x1F]; ++ for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) { ++ if (((mask >> slot) & 1) == 0) ++ continue; ++ ++ byte_pos = bit_pos >> 3; ++ bit_res = bit_pos & 7; ++ instr = 0; ++ for (j = 0; j < 6; ++j) ++ instr |= (uint64_t)(buf[i + j + byte_pos]) ++ << (8 * j); ++ ++ norm = instr >> bit_res; ++ ++ if (((norm >> 37) & 0x0F) == 0x05 ++ && ((norm >> 9) & 0x07) == 0) { ++ addr = (norm >> 13) & 0x0FFFFF; ++ addr |= ((uint32_t)(norm >> 36) & 1) << 20; ++ addr <<= 4; ++ addr -= s->pos + (uint32_t)i; ++ addr >>= 4; ++ ++ norm &= ~((uint64_t)0x8FFFFF << 13); ++ norm |= (uint64_t)(addr & 0x0FFFFF) << 13; ++ norm |= (uint64_t)(addr & 0x100000) ++ << (36 - 20); ++ ++ instr &= (1 << bit_res) - 1; ++ instr |= norm << bit_res; ++ ++ for (j = 0; j < 6; j++) ++ buf[i + j + byte_pos] ++ = (uint8_t)(instr >> (8 * j)); ++ } ++ } ++ } ++ ++ return i; ++} ++#endif ++ ++#ifdef XZ_DEC_ARM ++static size_t INIT bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ size_t i; ++ uint32_t addr; ++ ++ for (i = 0; i + 4 <= size; i += 4) { ++ if (buf[i + 3] == 0xEB) { ++ addr = (uint32_t)buf[i] | ((uint32_t)buf[i + 1] << 8) ++ | ((uint32_t)buf[i + 2] << 16); ++ addr <<= 2; ++ addr -= s->pos + (uint32_t)i + 8; ++ addr >>= 2; ++ buf[i] = (uint8_t)addr; ++ buf[i + 1] = (uint8_t)(addr >> 8); ++ buf[i + 2] = (uint8_t)(addr >> 16); ++ } ++ } ++ ++ return i; ++} ++#endif ++ ++#ifdef XZ_DEC_ARMTHUMB ++static size_t INIT bcj_armthumb(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ size_t i; ++ uint32_t addr; ++ ++ for (i = 0; i + 4 <= size; i += 2) { ++ if ((buf[i + 1] & 0xF8) == 0xF0 ++ && (buf[i + 3] & 0xF8) == 0xF8) { ++ addr = (((uint32_t)buf[i + 1] & 0x07) << 19) ++ | ((uint32_t)buf[i] << 11) ++ | (((uint32_t)buf[i + 3] & 0x07) << 8) ++ | (uint32_t)buf[i + 2]; ++ addr <<= 1; ++ addr -= s->pos + (uint32_t)i + 4; ++ addr >>= 1; ++ buf[i + 1] = (uint8_t)(0xF0 | ((addr >> 19) & 0x07)); ++ buf[i] = (uint8_t)(addr >> 11); ++ buf[i + 3] = (uint8_t)(0xF8 | ((addr >> 8) & 0x07)); ++ buf[i + 2] = (uint8_t)addr; ++ i += 2; ++ } ++ } ++ ++ return i; ++} ++#endif ++ ++#ifdef XZ_DEC_SPARC ++static size_t INIT bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ size_t i; ++ uint32_t instr; ++ ++ for (i = 0; i + 4 <= size; i += 4) { ++ instr = get_unaligned_be32(buf + i); ++ if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) { ++ instr <<= 2; ++ instr -= s->pos + (uint32_t)i; ++ instr >>= 2; ++ instr = ((uint32_t)0x40000000 - (instr & 0x400000)) ++ | 0x40000000 | (instr & 0x3FFFFF); ++ put_unaligned_be32(instr, buf + i); ++ } ++ } ++ ++ return i; ++} ++#endif ++ ++/* ++ * Apply the selected BCJ filter. Update *pos and s->pos to match the amount ++ * of data that got filtered. ++ * ++ * NOTE: This is implemented as a switch statement to avoid using function ++ * pointers, which could be problematic in the kernel boot code, which must ++ * avoid pointers to static data (at least on x86). ++ */ ++static void INIT bcj_apply(struct xz_dec_bcj *s, ++ uint8_t *buf, size_t *pos, size_t size) ++{ ++ size_t filtered; ++ ++ buf += *pos; ++ size -= *pos; ++ ++ switch (s->type) { ++#ifdef XZ_DEC_X86 ++ case BCJ_X86: ++ filtered = bcj_x86(s, buf, size); ++ break; ++#endif ++#ifdef XZ_DEC_POWERPC ++ case BCJ_POWERPC: ++ filtered = bcj_powerpc(s, buf, size); ++ break; ++#endif ++#ifdef XZ_DEC_IA64 ++ case BCJ_IA64: ++ filtered = bcj_ia64(s, buf, size); ++ break; ++#endif ++#ifdef XZ_DEC_ARM ++ case BCJ_ARM: ++ filtered = bcj_arm(s, buf, size); ++ break; ++#endif ++#ifdef XZ_DEC_ARMTHUMB ++ case BCJ_ARMTHUMB: ++ filtered = bcj_armthumb(s, buf, size); ++ break; ++#endif ++#ifdef XZ_DEC_SPARC ++ case BCJ_SPARC: ++ filtered = bcj_sparc(s, buf, size); ++ break; ++#endif ++ default: ++ /* Never reached but silence compiler warnings. */ ++ filtered = 0; ++ break; ++ } ++ ++ *pos += filtered; ++ s->pos += filtered; ++} ++ ++/* ++ * Flush pending filtered data from temp to the output buffer. ++ * Move the remaining mixture of possibly filtered and unfiltered ++ * data to the beginning of temp. ++ */ ++static void INIT bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b) ++{ ++ size_t copy_size; ++ ++ copy_size = min_t(size_t, s->temp.filtered, b->out_size - b->out_pos); ++ memcpy(b->out + b->out_pos, s->temp.buf, copy_size); ++ b->out_pos += copy_size; ++ ++ s->temp.filtered -= copy_size; ++ s->temp.size -= copy_size; ++ memmove(s->temp.buf, s->temp.buf + copy_size, s->temp.size); ++} ++ ++/* ++ * The BCJ filter functions are primitive in sense that they process the ++ * data in chunks of 1-16 bytes. To hide this issue, this function does ++ * some buffering. ++ */ ++XZ_EXTERN enum xz_ret INIT xz_dec_bcj_run(struct xz_dec_bcj *s, ++ struct xz_dec_lzma2 *lzma2, ++ struct xz_buf *b) ++{ ++ size_t out_start; ++ ++ /* ++ * Flush pending already filtered data to the output buffer. Return ++ * immediatelly if we couldn't flush everything, or if the next ++ * filter in the chain had already returned XZ_STREAM_END. ++ */ ++ if (s->temp.filtered > 0) { ++ bcj_flush(s, b); ++ if (s->temp.filtered > 0) ++ return XZ_OK; ++ ++ if (s->ret == XZ_STREAM_END) ++ return XZ_STREAM_END; ++ } ++ ++ /* ++ * If we have more output space than what is currently pending in ++ * temp, copy the unfiltered data from temp to the output buffer ++ * and try to fill the output buffer by decoding more data from the ++ * next filter in the chain. Apply the BCJ filter on the new data ++ * in the output buffer. If everything cannot be filtered, copy it ++ * to temp and rewind the output buffer position accordingly. ++ */ ++ if (s->temp.size < b->out_size - b->out_pos) { ++ out_start = b->out_pos; ++ memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size); ++ b->out_pos += s->temp.size; ++ ++ s->ret = xz_dec_lzma2_run(lzma2, b); ++ if (s->ret != XZ_STREAM_END ++ && (s->ret != XZ_OK || s->single_call)) ++ return s->ret; ++ ++ bcj_apply(s, b->out, &out_start, b->out_pos); ++ ++ /* ++ * As an exception, if the next filter returned XZ_STREAM_END, ++ * we can do that too, since the last few bytes that remain ++ * unfiltered are meant to remain unfiltered. ++ */ ++ if (s->ret == XZ_STREAM_END) ++ return XZ_STREAM_END; ++ ++ s->temp.size = b->out_pos - out_start; ++ b->out_pos -= s->temp.size; ++ memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size); ++ } ++ ++ /* ++ * If we have unfiltered data in temp, try to fill by decoding more ++ * data from the next filter. Apply the BCJ filter on temp. Then we ++ * hopefully can fill the actual output buffer by copying filtered ++ * data from temp. A mix of filtered and unfiltered data may be left ++ * in temp; it will be taken care on the next call to this function. ++ */ ++ if (s->temp.size > 0) { ++ /* Make b->out{,_pos,_size} temporarily point to s->temp. */ ++ s->out = b->out; ++ s->out_pos = b->out_pos; ++ s->out_size = b->out_size; ++ b->out = s->temp.buf; ++ b->out_pos = s->temp.size; ++ b->out_size = sizeof(s->temp.buf); ++ ++ s->ret = xz_dec_lzma2_run(lzma2, b); ++ ++ s->temp.size = b->out_pos; ++ b->out = s->out; ++ b->out_pos = s->out_pos; ++ b->out_size = s->out_size; ++ ++ if (s->ret != XZ_OK && s->ret != XZ_STREAM_END) ++ return s->ret; ++ ++ bcj_apply(s, s->temp.buf, &s->temp.filtered, s->temp.size); ++ ++ /* ++ * If the next filter returned XZ_STREAM_END, we mark that ++ * everything is filtered, since the last unfiltered bytes ++ * of the stream are meant to be left as is. ++ */ ++ if (s->ret == XZ_STREAM_END) ++ s->temp.filtered = s->temp.size; ++ ++ bcj_flush(s, b); ++ if (s->temp.filtered > 0) ++ return XZ_OK; ++ } ++ ++ return s->ret; ++} ++ ++XZ_EXTERN struct xz_dec_bcj *INIT xz_dec_bcj_create(bool_t single_call) ++{ ++ struct xz_dec_bcj *s = malloc(sizeof(*s)); ++ if (s != NULL) ++ s->single_call = single_call; ++ ++ return s; ++} ++ ++XZ_EXTERN enum xz_ret INIT xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) ++{ ++ switch (id) { ++#ifdef XZ_DEC_X86 ++ case BCJ_X86: ++#endif ++#ifdef XZ_DEC_POWERPC ++ case BCJ_POWERPC: ++#endif ++#ifdef XZ_DEC_IA64 ++ case BCJ_IA64: ++#endif ++#ifdef XZ_DEC_ARM ++ case BCJ_ARM: ++#endif ++#ifdef XZ_DEC_ARMTHUMB ++ case BCJ_ARMTHUMB: ++#endif ++#ifdef XZ_DEC_SPARC ++ case BCJ_SPARC: ++#endif ++ break; ++ ++ default: ++ /* Unsupported Filter ID */ ++ return XZ_OPTIONS_ERROR; ++ } ++ ++ s->type = id; ++ s->ret = XZ_OK; ++ s->pos = 0; ++ s->x86_prev_mask = 0; ++ s->temp.filtered = 0; ++ s->temp.size = 0; ++ ++ return XZ_OK; ++} ++ ++#endif +diff --git a/xen/common/xz/dec_lzma2.c b/xen/common/xz/dec_lzma2.c +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/dec_lzma2.c +@@ -0,0 +1,1171 @@ ++/* ++ * LZMA2 decoder ++ * ++ * Authors: Lasse Collin ++ * Igor Pavlov ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#include "private.h" ++#include "lzma2.h" ++ ++/* ++ * Range decoder initialization eats the first five bytes of each LZMA chunk. ++ */ ++#define RC_INIT_BYTES 5 ++ ++/* ++ * Minimum number of usable input buffer to safely decode one LZMA symbol. ++ * The worst case is that we decode 22 bits using probabilities and 26 ++ * direct bits. This may decode at maximum of 20 bytes of input. However, ++ * lzma_main() does an extra normalization before returning, thus we ++ * need to put 21 here. ++ */ ++#define LZMA_IN_REQUIRED 21 ++ ++/* ++ * Dictionary (history buffer) ++ * ++ * These are always true: ++ * start <= pos <= full <= end ++ * pos <= limit <= end ++ * ++ * In multi-call mode, also these are true: ++ * end == size ++ * size <= size_max ++ * allocated <= size ++ * ++ * Most of these variables are size_t to support single-call mode, ++ * in which the dictionary variables address the actual output ++ * buffer directly. ++ */ ++struct dictionary { ++ /* Beginning of the history buffer */ ++ uint8_t *buf; ++ ++ /* Old position in buf (before decoding more data) */ ++ size_t start; ++ ++ /* Position in buf */ ++ size_t pos; ++ ++ /* ++ * How full dictionary is. This is used to detect corrupt input that ++ * would read beyond the beginning of the uncompressed stream. ++ */ ++ size_t full; ++ ++ /* Write limit; we don't write to buf[limit] or later bytes. */ ++ size_t limit; ++ ++ /* ++ * End of the dictionary buffer. In multi-call mode, this is ++ * the same as the dictionary size. In single-call mode, this ++ * indicates the size of the output buffer. ++ */ ++ size_t end; ++ ++ /* ++ * Size of the dictionary as specified in Block Header. This is used ++ * together with "full" to detect corrupt input that would make us ++ * read beyond the beginning of the uncompressed stream. ++ */ ++ uint32_t size; ++ ++ /* ++ * Maximum allowed dictionary size in multi-call mode. ++ * This is ignored in single-call mode. ++ */ ++ uint32_t size_max; ++ ++ /* ++ * Amount of memory currently allocated for the dictionary. ++ * This is used only with XZ_DYNALLOC. (With XZ_PREALLOC, ++ * size_max is always the same as the allocated size.) ++ */ ++ uint32_t allocated; ++ ++ /* Operation mode */ ++ enum xz_mode mode; ++}; ++ ++/* Range decoder */ ++struct rc_dec { ++ uint32_t range; ++ uint32_t code; ++ ++ /* ++ * Number of initializing bytes remaining to be read ++ * by rc_read_init(). ++ */ ++ uint32_t init_bytes_left; ++ ++ /* ++ * Buffer from which we read our input. It can be either ++ * temp.buf or the caller-provided input buffer. ++ */ ++ const uint8_t *in; ++ size_t in_pos; ++ size_t in_limit; ++}; ++ ++/* Probabilities for a length decoder. */ ++struct lzma_len_dec { ++ /* Probability of match length being at least 10 */ ++ uint16_t choice; ++ ++ /* Probability of match length being at least 18 */ ++ uint16_t choice2; ++ ++ /* Probabilities for match lengths 2-9 */ ++ uint16_t low[POS_STATES_MAX][LEN_LOW_SYMBOLS]; ++ ++ /* Probabilities for match lengths 10-17 */ ++ uint16_t mid[POS_STATES_MAX][LEN_MID_SYMBOLS]; ++ ++ /* Probabilities for match lengths 18-273 */ ++ uint16_t high[LEN_HIGH_SYMBOLS]; ++}; ++ ++struct lzma_dec { ++ /* Distances of latest four matches */ ++ uint32_t rep0; ++ uint32_t rep1; ++ uint32_t rep2; ++ uint32_t rep3; ++ ++ /* Types of the most recently seen LZMA symbols */ ++ enum lzma_state state; ++ ++ /* ++ * Length of a match. This is updated so that dict_repeat can ++ * be called again to finish repeating the whole match. ++ */ ++ uint32_t len; ++ ++ /* ++ * LZMA properties or related bit masks (number of literal ++ * context bits, a mask dervied from the number of literal ++ * position bits, and a mask dervied from the number ++ * position bits) ++ */ ++ uint32_t lc; ++ uint32_t literal_pos_mask; /* (1 << lp) - 1 */ ++ uint32_t pos_mask; /* (1 << pb) - 1 */ ++ ++ /* If 1, it's a match. Otherwise it's a single 8-bit literal. */ ++ uint16_t is_match[STATES][POS_STATES_MAX]; ++ ++ /* If 1, it's a repeated match. The distance is one of rep0 .. rep3. */ ++ uint16_t is_rep[STATES]; ++ ++ /* ++ * If 0, distance of a repeated match is rep0. ++ * Otherwise check is_rep1. ++ */ ++ uint16_t is_rep0[STATES]; ++ ++ /* ++ * If 0, distance of a repeated match is rep1. ++ * Otherwise check is_rep2. ++ */ ++ uint16_t is_rep1[STATES]; ++ ++ /* If 0, distance of a repeated match is rep2. Otherwise it is rep3. */ ++ uint16_t is_rep2[STATES]; ++ ++ /* ++ * If 1, the repeated match has length of one byte. Otherwise ++ * the length is decoded from rep_len_decoder. ++ */ ++ uint16_t is_rep0_long[STATES][POS_STATES_MAX]; ++ ++ /* ++ * Probability tree for the highest two bits of the match ++ * distance. There is a separate probability tree for match ++ * lengths of 2 (i.e. MATCH_LEN_MIN), 3, 4, and [5, 273]. ++ */ ++ uint16_t dist_slot[DIST_STATES][DIST_SLOTS]; ++ ++ /* ++ * Probility trees for additional bits for match distance ++ * when the distance is in the range [4, 127]. ++ */ ++ uint16_t dist_special[FULL_DISTANCES - DIST_MODEL_END]; ++ ++ /* ++ * Probability tree for the lowest four bits of a match ++ * distance that is equal to or greater than 128. ++ */ ++ uint16_t dist_align[ALIGN_SIZE]; ++ ++ /* Length of a normal match */ ++ struct lzma_len_dec match_len_dec; ++ ++ /* Length of a repeated match */ ++ struct lzma_len_dec rep_len_dec; ++ ++ /* Probabilities of literals */ ++ uint16_t literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE]; ++}; ++ ++struct lzma2_dec { ++ /* Position in xz_dec_lzma2_run(). */ ++ enum lzma2_seq { ++ SEQ_CONTROL, ++ SEQ_UNCOMPRESSED_1, ++ SEQ_UNCOMPRESSED_2, ++ SEQ_COMPRESSED_0, ++ SEQ_COMPRESSED_1, ++ SEQ_PROPERTIES, ++ SEQ_LZMA_PREPARE, ++ SEQ_LZMA_RUN, ++ SEQ_COPY ++ } sequence; ++ ++ /* Next position after decoding the compressed size of the chunk. */ ++ enum lzma2_seq next_sequence; ++ ++ /* Uncompressed size of LZMA chunk (2 MiB at maximum) */ ++ uint32_t uncompressed; ++ ++ /* ++ * Compressed size of LZMA chunk or compressed/uncompressed ++ * size of uncompressed chunk (64 KiB at maximum) ++ */ ++ uint32_t compressed; ++ ++ /* ++ * True if dictionary reset is needed. This is false before ++ * the first chunk (LZMA or uncompressed). ++ */ ++ bool_t need_dict_reset; ++ ++ /* ++ * True if new LZMA properties are needed. This is false ++ * before the first LZMA chunk. ++ */ ++ bool_t need_props; ++}; ++ ++struct xz_dec_lzma2 { ++ /* ++ * The order below is important on x86 to reduce code size and ++ * it shouldn't hurt on other platforms. Everything up to and ++ * including lzma.pos_mask are in the first 128 bytes on x86-32, ++ * which allows using smaller instructions to access those ++ * variables. On x86-64, fewer variables fit into the first 128 ++ * bytes, but this is still the best order without sacrificing ++ * the readability by splitting the structures. ++ */ ++ struct rc_dec rc; ++ struct dictionary dict; ++ struct lzma2_dec lzma2; ++ struct lzma_dec lzma; ++ ++ /* ++ * Temporary buffer which holds small number of input bytes between ++ * decoder calls. See lzma2_lzma() for details. ++ */ ++ struct { ++ uint32_t size; ++ uint8_t buf[3 * LZMA_IN_REQUIRED]; ++ } temp; ++}; ++ ++/************** ++ * Dictionary * ++ **************/ ++ ++/* ++ * Reset the dictionary state. When in single-call mode, set up the beginning ++ * of the dictionary to point to the actual output buffer. ++ */ ++static void INIT dict_reset(struct dictionary *dict, struct xz_buf *b) ++{ ++ if (DEC_IS_SINGLE(dict->mode)) { ++ dict->buf = b->out + b->out_pos; ++ dict->end = b->out_size - b->out_pos; ++ } ++ ++ dict->start = 0; ++ dict->pos = 0; ++ dict->limit = 0; ++ dict->full = 0; ++} ++ ++/* Set dictionary write limit */ ++static void INIT dict_limit(struct dictionary *dict, size_t out_max) ++{ ++ if (dict->end - dict->pos <= out_max) ++ dict->limit = dict->end; ++ else ++ dict->limit = dict->pos + out_max; ++} ++ ++/* Return true if at least one byte can be written into the dictionary. */ ++static inline bool_t INIT dict_has_space(const struct dictionary *dict) ++{ ++ return dict->pos < dict->limit; ++} ++ ++/* ++ * Get a byte from the dictionary at the given distance. The distance is ++ * assumed to valid, or as a special case, zero when the dictionary is ++ * still empty. This special case is needed for single-call decoding to ++ * avoid writing a '\0' to the end of the destination buffer. ++ */ ++static inline uint32_t INIT dict_get(const struct dictionary *dict, uint32_t dist) ++{ ++ size_t offset = dict->pos - dist - 1; ++ ++ if (dist >= dict->pos) ++ offset += dict->end; ++ ++ return dict->full > 0 ? dict->buf[offset] : 0; ++} ++ ++/* ++ * Put one byte into the dictionary. It is assumed that there is space for it. ++ */ ++static inline void INIT dict_put(struct dictionary *dict, uint8_t byte) ++{ ++ dict->buf[dict->pos++] = byte; ++ ++ if (dict->full < dict->pos) ++ dict->full = dict->pos; ++} ++ ++/* ++ * Repeat given number of bytes from the given distance. If the distance is ++ * invalid, false is returned. On success, true is returned and *len is ++ * updated to indicate how many bytes were left to be repeated. ++ */ ++static bool_t INIT dict_repeat(struct dictionary *dict, uint32_t *len, uint32_t dist) ++{ ++ size_t back; ++ uint32_t left; ++ ++ if (dist >= dict->full || dist >= dict->size) ++ return false; ++ ++ left = min_t(size_t, dict->limit - dict->pos, *len); ++ *len -= left; ++ ++ back = dict->pos - dist - 1; ++ if (dist >= dict->pos) ++ back += dict->end; ++ ++ do { ++ dict->buf[dict->pos++] = dict->buf[back++]; ++ if (back == dict->end) ++ back = 0; ++ } while (--left > 0); ++ ++ if (dict->full < dict->pos) ++ dict->full = dict->pos; ++ ++ return true; ++} ++ ++/* Copy uncompressed data as is from input to dictionary and output buffers. */ ++static void INIT dict_uncompressed(struct dictionary *dict, struct xz_buf *b, ++ uint32_t *left) ++{ ++ size_t copy_size; ++ ++ while (*left > 0 && b->in_pos < b->in_size ++ && b->out_pos < b->out_size) { ++ copy_size = min(b->in_size - b->in_pos, ++ b->out_size - b->out_pos); ++ if (copy_size > dict->end - dict->pos) ++ copy_size = dict->end - dict->pos; ++ if (copy_size > *left) ++ copy_size = *left; ++ ++ *left -= copy_size; ++ ++ memcpy(dict->buf + dict->pos, b->in + b->in_pos, copy_size); ++ dict->pos += copy_size; ++ ++ if (dict->full < dict->pos) ++ dict->full = dict->pos; ++ ++ if (DEC_IS_MULTI(dict->mode)) { ++ if (dict->pos == dict->end) ++ dict->pos = 0; ++ ++ memcpy(b->out + b->out_pos, b->in + b->in_pos, ++ copy_size); ++ } ++ ++ dict->start = dict->pos; ++ ++ b->out_pos += copy_size; ++ b->in_pos += copy_size; ++ } ++} ++ ++/* ++ * Flush pending data from dictionary to b->out. It is assumed that there is ++ * enough space in b->out. This is guaranteed because caller uses dict_limit() ++ * before decoding data into the dictionary. ++ */ ++static uint32_t INIT dict_flush(struct dictionary *dict, struct xz_buf *b) ++{ ++ size_t copy_size = dict->pos - dict->start; ++ ++ if (DEC_IS_MULTI(dict->mode)) { ++ if (dict->pos == dict->end) ++ dict->pos = 0; ++ ++ memcpy(b->out + b->out_pos, dict->buf + dict->start, ++ copy_size); ++ } ++ ++ dict->start = dict->pos; ++ b->out_pos += copy_size; ++ return copy_size; ++} ++ ++/***************** ++ * Range decoder * ++ *****************/ ++ ++/* Reset the range decoder. */ ++static void INIT rc_reset(struct rc_dec *rc) ++{ ++ rc->range = (uint32_t)-1; ++ rc->code = 0; ++ rc->init_bytes_left = RC_INIT_BYTES; ++} ++ ++/* ++ * Read the first five initial bytes into rc->code if they haven't been ++ * read already. (Yes, the first byte gets completely ignored.) ++ */ ++static bool_t INIT rc_read_init(struct rc_dec *rc, struct xz_buf *b) ++{ ++ while (rc->init_bytes_left > 0) { ++ if (b->in_pos == b->in_size) ++ return false; ++ ++ rc->code = (rc->code << 8) + b->in[b->in_pos++]; ++ --rc->init_bytes_left; ++ } ++ ++ return true; ++} ++ ++/* Return true if there may not be enough input for the next decoding loop. */ ++static inline bool_t INIT rc_limit_exceeded(const struct rc_dec *rc) ++{ ++ return rc->in_pos > rc->in_limit; ++} ++ ++/* ++ * Return true if it is possible (from point of view of range decoder) that ++ * we have reached the end of the LZMA chunk. ++ */ ++static inline bool_t INIT rc_is_finished(const struct rc_dec *rc) ++{ ++ return rc->code == 0; ++} ++ ++/* Read the next input byte if needed. */ ++static always_inline void rc_normalize(struct rc_dec *rc) ++{ ++ if (rc->range < RC_TOP_VALUE) { ++ rc->range <<= RC_SHIFT_BITS; ++ rc->code = (rc->code << RC_SHIFT_BITS) + rc->in[rc->in_pos++]; ++ } ++} ++ ++/* ++ * Decode one bit. In some versions, this function has been splitted in three ++ * functions so that the compiler is supposed to be able to more easily avoid ++ * an extra branch. In this particular version of the LZMA decoder, this ++ * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3 ++ * on x86). Using a non-splitted version results in nicer looking code too. ++ * ++ * NOTE: This must return an int. Do not make it return a bool or the speed ++ * of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care, ++ * and it generates 10-20 % faster code than GCC 3.x from this file anyway.) ++ */ ++static always_inline int rc_bit(struct rc_dec *rc, uint16_t *prob) ++{ ++ uint32_t bound; ++ int bit; ++ ++ rc_normalize(rc); ++ bound = (rc->range >> RC_BIT_MODEL_TOTAL_BITS) * *prob; ++ if (rc->code < bound) { ++ rc->range = bound; ++ *prob += (RC_BIT_MODEL_TOTAL - *prob) >> RC_MOVE_BITS; ++ bit = 0; ++ } else { ++ rc->range -= bound; ++ rc->code -= bound; ++ *prob -= *prob >> RC_MOVE_BITS; ++ bit = 1; ++ } ++ ++ return bit; ++} ++ ++/* Decode a bittree starting from the most significant bit. */ ++static always_inline uint32_t rc_bittree(struct rc_dec *rc, ++ uint16_t *probs, uint32_t limit) ++{ ++ uint32_t symbol = 1; ++ ++ do { ++ if (rc_bit(rc, &probs[symbol])) ++ symbol = (symbol << 1) + 1; ++ else ++ symbol <<= 1; ++ } while (symbol < limit); ++ ++ return symbol; ++} ++ ++/* Decode a bittree starting from the least significant bit. */ ++static always_inline void rc_bittree_reverse(struct rc_dec *rc, ++ uint16_t *probs, ++ uint32_t *dest, uint32_t limit) ++{ ++ uint32_t symbol = 1; ++ uint32_t i = 0; ++ ++ do { ++ if (rc_bit(rc, &probs[symbol])) { ++ symbol = (symbol << 1) + 1; ++ *dest += 1 << i; ++ } else { ++ symbol <<= 1; ++ } ++ } while (++i < limit); ++} ++ ++/* Decode direct bits (fixed fifty-fifty probability) */ ++static inline void INIT rc_direct(struct rc_dec *rc, uint32_t *dest, uint32_t limit) ++{ ++ uint32_t mask; ++ ++ do { ++ rc_normalize(rc); ++ rc->range >>= 1; ++ rc->code -= rc->range; ++ mask = (uint32_t)0 - (rc->code >> 31); ++ rc->code += rc->range & mask; ++ *dest = (*dest << 1) + (mask + 1); ++ } while (--limit > 0); ++} ++ ++/******** ++ * LZMA * ++ ********/ ++ ++/* Get pointer to literal coder probability array. */ ++static uint16_t *INIT lzma_literal_probs(struct xz_dec_lzma2 *s) ++{ ++ uint32_t prev_byte = dict_get(&s->dict, 0); ++ uint32_t low = prev_byte >> (8 - s->lzma.lc); ++ uint32_t high = (s->dict.pos & s->lzma.literal_pos_mask) << s->lzma.lc; ++ return s->lzma.literal[low + high]; ++} ++ ++/* Decode a literal (one 8-bit byte) */ ++static void INIT lzma_literal(struct xz_dec_lzma2 *s) ++{ ++ uint16_t *probs; ++ uint32_t symbol; ++ uint32_t match_byte; ++ uint32_t match_bit; ++ uint32_t offset; ++ uint32_t i; ++ ++ probs = lzma_literal_probs(s); ++ ++ if (lzma_state_is_literal(s->lzma.state)) { ++ symbol = rc_bittree(&s->rc, probs, 0x100); ++ } else { ++ symbol = 1; ++ match_byte = dict_get(&s->dict, s->lzma.rep0) << 1; ++ offset = 0x100; ++ ++ do { ++ match_bit = match_byte & offset; ++ match_byte <<= 1; ++ i = offset + match_bit + symbol; ++ ++ if (rc_bit(&s->rc, &probs[i])) { ++ symbol = (symbol << 1) + 1; ++ offset &= match_bit; ++ } else { ++ symbol <<= 1; ++ offset &= ~match_bit; ++ } ++ } while (symbol < 0x100); ++ } ++ ++ dict_put(&s->dict, (uint8_t)symbol); ++ lzma_state_literal(&s->lzma.state); ++} ++ ++/* Decode the length of the match into s->lzma.len. */ ++static void INIT lzma_len(struct xz_dec_lzma2 *s, struct lzma_len_dec *l, ++ uint32_t pos_state) ++{ ++ uint16_t *probs; ++ uint32_t limit; ++ ++ if (!rc_bit(&s->rc, &l->choice)) { ++ probs = l->low[pos_state]; ++ limit = LEN_LOW_SYMBOLS; ++ s->lzma.len = MATCH_LEN_MIN; ++ } else { ++ if (!rc_bit(&s->rc, &l->choice2)) { ++ probs = l->mid[pos_state]; ++ limit = LEN_MID_SYMBOLS; ++ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS; ++ } else { ++ probs = l->high; ++ limit = LEN_HIGH_SYMBOLS; ++ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS ++ + LEN_MID_SYMBOLS; ++ } ++ } ++ ++ s->lzma.len += rc_bittree(&s->rc, probs, limit) - limit; ++} ++ ++/* Decode a match. The distance will be stored in s->lzma.rep0. */ ++static void INIT lzma_match(struct xz_dec_lzma2 *s, uint32_t pos_state) ++{ ++ uint16_t *probs; ++ uint32_t dist_slot; ++ uint32_t limit; ++ ++ lzma_state_match(&s->lzma.state); ++ ++ s->lzma.rep3 = s->lzma.rep2; ++ s->lzma.rep2 = s->lzma.rep1; ++ s->lzma.rep1 = s->lzma.rep0; ++ ++ lzma_len(s, &s->lzma.match_len_dec, pos_state); ++ ++ probs = s->lzma.dist_slot[lzma_get_dist_state(s->lzma.len)]; ++ dist_slot = rc_bittree(&s->rc, probs, DIST_SLOTS) - DIST_SLOTS; ++ ++ if (dist_slot < DIST_MODEL_START) { ++ s->lzma.rep0 = dist_slot; ++ } else { ++ limit = (dist_slot >> 1) - 1; ++ s->lzma.rep0 = 2 + (dist_slot & 1); ++ ++ if (dist_slot < DIST_MODEL_END) { ++ s->lzma.rep0 <<= limit; ++ probs = s->lzma.dist_special + s->lzma.rep0 ++ - dist_slot - 1; ++ rc_bittree_reverse(&s->rc, probs, ++ &s->lzma.rep0, limit); ++ } else { ++ rc_direct(&s->rc, &s->lzma.rep0, limit - ALIGN_BITS); ++ s->lzma.rep0 <<= ALIGN_BITS; ++ rc_bittree_reverse(&s->rc, s->lzma.dist_align, ++ &s->lzma.rep0, ALIGN_BITS); ++ } ++ } ++} ++ ++/* ++ * Decode a repeated match. The distance is one of the four most recently ++ * seen matches. The distance will be stored in s->lzma.rep0. ++ */ ++static void INIT lzma_rep_match(struct xz_dec_lzma2 *s, uint32_t pos_state) ++{ ++ uint32_t tmp; ++ ++ if (!rc_bit(&s->rc, &s->lzma.is_rep0[s->lzma.state])) { ++ if (!rc_bit(&s->rc, &s->lzma.is_rep0_long[ ++ s->lzma.state][pos_state])) { ++ lzma_state_short_rep(&s->lzma.state); ++ s->lzma.len = 1; ++ return; ++ } ++ } else { ++ if (!rc_bit(&s->rc, &s->lzma.is_rep1[s->lzma.state])) { ++ tmp = s->lzma.rep1; ++ } else { ++ if (!rc_bit(&s->rc, &s->lzma.is_rep2[s->lzma.state])) { ++ tmp = s->lzma.rep2; ++ } else { ++ tmp = s->lzma.rep3; ++ s->lzma.rep3 = s->lzma.rep2; ++ } ++ ++ s->lzma.rep2 = s->lzma.rep1; ++ } ++ ++ s->lzma.rep1 = s->lzma.rep0; ++ s->lzma.rep0 = tmp; ++ } ++ ++ lzma_state_long_rep(&s->lzma.state); ++ lzma_len(s, &s->lzma.rep_len_dec, pos_state); ++} ++ ++/* LZMA decoder core */ ++static bool_t INIT lzma_main(struct xz_dec_lzma2 *s) ++{ ++ uint32_t pos_state; ++ ++ /* ++ * If the dictionary was reached during the previous call, try to ++ * finish the possibly pending repeat in the dictionary. ++ */ ++ if (dict_has_space(&s->dict) && s->lzma.len > 0) ++ dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0); ++ ++ /* ++ * Decode more LZMA symbols. One iteration may consume up to ++ * LZMA_IN_REQUIRED - 1 bytes. ++ */ ++ while (dict_has_space(&s->dict) && !rc_limit_exceeded(&s->rc)) { ++ pos_state = s->dict.pos & s->lzma.pos_mask; ++ ++ if (!rc_bit(&s->rc, &s->lzma.is_match[ ++ s->lzma.state][pos_state])) { ++ lzma_literal(s); ++ } else { ++ if (rc_bit(&s->rc, &s->lzma.is_rep[s->lzma.state])) ++ lzma_rep_match(s, pos_state); ++ else ++ lzma_match(s, pos_state); ++ ++ if (!dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0)) ++ return false; ++ } ++ } ++ ++ /* ++ * Having the range decoder always normalized when we are outside ++ * this function makes it easier to correctly handle end of the chunk. ++ */ ++ rc_normalize(&s->rc); ++ ++ return true; ++} ++ ++/* ++ * Reset the LZMA decoder and range decoder state. Dictionary is nore reset ++ * here, because LZMA state may be reset without resetting the dictionary. ++ */ ++static void INIT lzma_reset(struct xz_dec_lzma2 *s) ++{ ++ uint16_t *probs; ++ size_t i; ++ ++ s->lzma.state = STATE_LIT_LIT; ++ s->lzma.rep0 = 0; ++ s->lzma.rep1 = 0; ++ s->lzma.rep2 = 0; ++ s->lzma.rep3 = 0; ++ ++ /* ++ * All probabilities are initialized to the same value. This hack ++ * makes the code smaller by avoiding a separate loop for each ++ * probability array. ++ * ++ * This could be optimized so that only that part of literal ++ * probabilities that are actually required. In the common case ++ * we would write 12 KiB less. ++ */ ++ probs = s->lzma.is_match[0]; ++ for (i = 0; i < PROBS_TOTAL; ++i) ++ probs[i] = RC_BIT_MODEL_TOTAL / 2; ++ ++ rc_reset(&s->rc); ++} ++ ++/* ++ * Decode and validate LZMA properties (lc/lp/pb) and calculate the bit masks ++ * from the decoded lp and pb values. On success, the LZMA decoder state is ++ * reset and true is returned. ++ */ ++static bool_t INIT lzma_props(struct xz_dec_lzma2 *s, uint8_t props) ++{ ++ if (props > (4 * 5 + 4) * 9 + 8) ++ return false; ++ ++ s->lzma.pos_mask = 0; ++ while (props >= 9 * 5) { ++ props -= 9 * 5; ++ ++s->lzma.pos_mask; ++ } ++ ++ s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1; ++ ++ s->lzma.literal_pos_mask = 0; ++ while (props >= 9) { ++ props -= 9; ++ ++s->lzma.literal_pos_mask; ++ } ++ ++ s->lzma.lc = props; ++ ++ if (s->lzma.lc + s->lzma.literal_pos_mask > 4) ++ return false; ++ ++ s->lzma.literal_pos_mask = (1 << s->lzma.literal_pos_mask) - 1; ++ ++ lzma_reset(s); ++ ++ return true; ++} ++ ++/********* ++ * LZMA2 * ++ *********/ ++ ++/* ++ * The LZMA decoder assumes that if the input limit (s->rc.in_limit) hasn't ++ * been exceeded, it is safe to read up to LZMA_IN_REQUIRED bytes. This ++ * wrapper function takes care of making the LZMA decoder's assumption safe. ++ * ++ * As long as there is plenty of input left to be decoded in the current LZMA ++ * chunk, we decode directly from the caller-supplied input buffer until ++ * there's LZMA_IN_REQUIRED bytes left. Those remaining bytes are copied into ++ * s->temp.buf, which (hopefully) gets filled on the next call to this ++ * function. We decode a few bytes from the temporary buffer so that we can ++ * continue decoding from the caller-supplied input buffer again. ++ */ ++static bool_t INIT lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b) ++{ ++ size_t in_avail; ++ uint32_t tmp; ++ ++ in_avail = b->in_size - b->in_pos; ++ if (s->temp.size > 0 || s->lzma2.compressed == 0) { ++ tmp = 2 * LZMA_IN_REQUIRED - s->temp.size; ++ if (tmp > s->lzma2.compressed - s->temp.size) ++ tmp = s->lzma2.compressed - s->temp.size; ++ if (tmp > in_avail) ++ tmp = in_avail; ++ ++ memcpy(s->temp.buf + s->temp.size, b->in + b->in_pos, tmp); ++ ++ if (s->temp.size + tmp == s->lzma2.compressed) { ++ memzero(s->temp.buf + s->temp.size + tmp, ++ sizeof(s->temp.buf) ++ - s->temp.size - tmp); ++ s->rc.in_limit = s->temp.size + tmp; ++ } else if (s->temp.size + tmp < LZMA_IN_REQUIRED) { ++ s->temp.size += tmp; ++ b->in_pos += tmp; ++ return true; ++ } else { ++ s->rc.in_limit = s->temp.size + tmp - LZMA_IN_REQUIRED; ++ } ++ ++ s->rc.in = s->temp.buf; ++ s->rc.in_pos = 0; ++ ++ if (!lzma_main(s) || s->rc.in_pos > s->temp.size + tmp) ++ return false; ++ ++ s->lzma2.compressed -= s->rc.in_pos; ++ ++ if (s->rc.in_pos < s->temp.size) { ++ s->temp.size -= s->rc.in_pos; ++ memmove(s->temp.buf, s->temp.buf + s->rc.in_pos, ++ s->temp.size); ++ return true; ++ } ++ ++ b->in_pos += s->rc.in_pos - s->temp.size; ++ s->temp.size = 0; ++ } ++ ++ in_avail = b->in_size - b->in_pos; ++ if (in_avail >= LZMA_IN_REQUIRED) { ++ s->rc.in = b->in; ++ s->rc.in_pos = b->in_pos; ++ ++ if (in_avail >= s->lzma2.compressed + LZMA_IN_REQUIRED) ++ s->rc.in_limit = b->in_pos + s->lzma2.compressed; ++ else ++ s->rc.in_limit = b->in_size - LZMA_IN_REQUIRED; ++ ++ if (!lzma_main(s)) ++ return false; ++ ++ in_avail = s->rc.in_pos - b->in_pos; ++ if (in_avail > s->lzma2.compressed) ++ return false; ++ ++ s->lzma2.compressed -= in_avail; ++ b->in_pos = s->rc.in_pos; ++ } ++ ++ in_avail = b->in_size - b->in_pos; ++ if (in_avail < LZMA_IN_REQUIRED) { ++ if (in_avail > s->lzma2.compressed) ++ in_avail = s->lzma2.compressed; ++ ++ memcpy(s->temp.buf, b->in + b->in_pos, in_avail); ++ s->temp.size = in_avail; ++ b->in_pos += in_avail; ++ } ++ ++ return true; ++} ++ ++/* ++ * Take care of the LZMA2 control layer, and forward the job of actual LZMA ++ * decoding or copying of uncompressed chunks to other functions. ++ */ ++XZ_EXTERN enum xz_ret INIT xz_dec_lzma2_run(struct xz_dec_lzma2 *s, ++ struct xz_buf *b) ++{ ++ uint32_t tmp; ++ ++ while (b->in_pos < b->in_size || s->lzma2.sequence == SEQ_LZMA_RUN) { ++ switch (s->lzma2.sequence) { ++ case SEQ_CONTROL: ++ /* ++ * LZMA2 control byte ++ * ++ * Exact values: ++ * 0x00 End marker ++ * 0x01 Dictionary reset followed by ++ * an uncompressed chunk ++ * 0x02 Uncompressed chunk (no dictionary reset) ++ * ++ * Highest three bits (s->control & 0xE0): ++ * 0xE0 Dictionary reset, new properties and state ++ * reset, followed by LZMA compressed chunk ++ * 0xC0 New properties and state reset, followed ++ * by LZMA compressed chunk (no dictionary ++ * reset) ++ * 0xA0 State reset using old properties, ++ * followed by LZMA compressed chunk (no ++ * dictionary reset) ++ * 0x80 LZMA chunk (no dictionary or state reset) ++ * ++ * For LZMA compressed chunks, the lowest five bits ++ * (s->control & 1F) are the highest bits of the ++ * uncompressed size (bits 16-20). ++ * ++ * A new LZMA2 stream must begin with a dictionary ++ * reset. The first LZMA chunk must set new ++ * properties and reset the LZMA state. ++ * ++ * Values that don't match anything described above ++ * are invalid and we return XZ_DATA_ERROR. ++ */ ++ tmp = b->in[b->in_pos++]; ++ ++ if (tmp >= 0xE0 || tmp == 0x01) { ++ s->lzma2.need_props = true; ++ s->lzma2.need_dict_reset = false; ++ dict_reset(&s->dict, b); ++ } else if (s->lzma2.need_dict_reset) { ++ return XZ_DATA_ERROR; ++ } ++ ++ if (tmp >= 0x80) { ++ s->lzma2.uncompressed = (tmp & 0x1F) << 16; ++ s->lzma2.sequence = SEQ_UNCOMPRESSED_1; ++ ++ if (tmp >= 0xC0) { ++ /* ++ * When there are new properties, ++ * state reset is done at ++ * SEQ_PROPERTIES. ++ */ ++ s->lzma2.need_props = false; ++ s->lzma2.next_sequence ++ = SEQ_PROPERTIES; ++ ++ } else if (s->lzma2.need_props) { ++ return XZ_DATA_ERROR; ++ ++ } else { ++ s->lzma2.next_sequence ++ = SEQ_LZMA_PREPARE; ++ if (tmp >= 0xA0) ++ lzma_reset(s); ++ } ++ } else { ++ if (tmp == 0x00) ++ return XZ_STREAM_END; ++ ++ if (tmp > 0x02) ++ return XZ_DATA_ERROR; ++ ++ s->lzma2.sequence = SEQ_COMPRESSED_0; ++ s->lzma2.next_sequence = SEQ_COPY; ++ } ++ ++ break; ++ ++ case SEQ_UNCOMPRESSED_1: ++ s->lzma2.uncompressed ++ += (uint32_t)b->in[b->in_pos++] << 8; ++ s->lzma2.sequence = SEQ_UNCOMPRESSED_2; ++ break; ++ ++ case SEQ_UNCOMPRESSED_2: ++ s->lzma2.uncompressed ++ += (uint32_t)b->in[b->in_pos++] + 1; ++ s->lzma2.sequence = SEQ_COMPRESSED_0; ++ break; ++ ++ case SEQ_COMPRESSED_0: ++ s->lzma2.compressed ++ = (uint32_t)b->in[b->in_pos++] << 8; ++ s->lzma2.sequence = SEQ_COMPRESSED_1; ++ break; ++ ++ case SEQ_COMPRESSED_1: ++ s->lzma2.compressed ++ += (uint32_t)b->in[b->in_pos++] + 1; ++ s->lzma2.sequence = s->lzma2.next_sequence; ++ break; ++ ++ case SEQ_PROPERTIES: ++ if (!lzma_props(s, b->in[b->in_pos++])) ++ return XZ_DATA_ERROR; ++ ++ s->lzma2.sequence = SEQ_LZMA_PREPARE; ++ ++ case SEQ_LZMA_PREPARE: ++ if (s->lzma2.compressed < RC_INIT_BYTES) ++ return XZ_DATA_ERROR; ++ ++ if (!rc_read_init(&s->rc, b)) ++ return XZ_OK; ++ ++ s->lzma2.compressed -= RC_INIT_BYTES; ++ s->lzma2.sequence = SEQ_LZMA_RUN; ++ ++ case SEQ_LZMA_RUN: ++ /* ++ * Set dictionary limit to indicate how much we want ++ * to be encoded at maximum. Decode new data into the ++ * dictionary. Flush the new data from dictionary to ++ * b->out. Check if we finished decoding this chunk. ++ * In case the dictionary got full but we didn't fill ++ * the output buffer yet, we may run this loop ++ * multiple times without changing s->lzma2.sequence. ++ */ ++ dict_limit(&s->dict, min_t(size_t, ++ b->out_size - b->out_pos, ++ s->lzma2.uncompressed)); ++ if (!lzma2_lzma(s, b)) ++ return XZ_DATA_ERROR; ++ ++ s->lzma2.uncompressed -= dict_flush(&s->dict, b); ++ ++ if (s->lzma2.uncompressed == 0) { ++ if (s->lzma2.compressed > 0 || s->lzma.len > 0 ++ || !rc_is_finished(&s->rc)) ++ return XZ_DATA_ERROR; ++ ++ rc_reset(&s->rc); ++ s->lzma2.sequence = SEQ_CONTROL; ++ ++ } else if (b->out_pos == b->out_size ++ || (b->in_pos == b->in_size ++ && s->temp.size ++ < s->lzma2.compressed)) { ++ return XZ_OK; ++ } ++ ++ break; ++ ++ case SEQ_COPY: ++ dict_uncompressed(&s->dict, b, &s->lzma2.compressed); ++ if (s->lzma2.compressed > 0) ++ return XZ_OK; ++ ++ s->lzma2.sequence = SEQ_CONTROL; ++ break; ++ } ++ } ++ ++ return XZ_OK; ++} ++ ++XZ_EXTERN struct xz_dec_lzma2 *INIT xz_dec_lzma2_create(enum xz_mode mode, ++ uint32_t dict_max) ++{ ++ struct xz_dec_lzma2 *s = malloc(sizeof(*s)); ++ if (s == NULL) ++ return NULL; ++ ++ s->dict.mode = mode; ++ s->dict.size_max = dict_max; ++ ++ if (DEC_IS_PREALLOC(mode)) { ++ s->dict.buf = large_malloc(dict_max); ++ if (s->dict.buf == NULL) { ++ free(s); ++ return NULL; ++ } ++ } else if (DEC_IS_DYNALLOC(mode)) { ++ s->dict.buf = NULL; ++ s->dict.allocated = 0; ++ } ++ ++ return s; ++} ++ ++XZ_EXTERN enum xz_ret INIT xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) ++{ ++ /* This limits dictionary size to 3 GiB to keep parsing simpler. */ ++ if (props > 39) ++ return XZ_OPTIONS_ERROR; ++ ++ s->dict.size = 2 + (props & 1); ++ s->dict.size <<= (props >> 1) + 11; ++ ++ if (DEC_IS_MULTI(s->dict.mode)) { ++ if (s->dict.size > s->dict.size_max) ++ return XZ_MEMLIMIT_ERROR; ++ ++ s->dict.end = s->dict.size; ++ ++ if (DEC_IS_DYNALLOC(s->dict.mode)) { ++ if (s->dict.allocated < s->dict.size) { ++ large_free(s->dict.buf); ++ s->dict.buf = large_malloc(s->dict.size); ++ if (s->dict.buf == NULL) { ++ s->dict.allocated = 0; ++ return XZ_MEM_ERROR; ++ } ++ } ++ } ++ } ++ ++ s->lzma.len = 0; ++ ++ s->lzma2.sequence = SEQ_CONTROL; ++ s->lzma2.need_dict_reset = true; ++ ++ s->temp.size = 0; ++ ++ return XZ_OK; ++} ++ ++XZ_EXTERN void INIT xz_dec_lzma2_end(struct xz_dec_lzma2 *s) ++{ ++ if (DEC_IS_MULTI(s->dict.mode)) ++ large_free(s->dict.buf); ++ ++ free(s); ++} +diff --git a/xen/common/xz/dec_stream.c b/xen/common/xz/dec_stream.c +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/dec_stream.c +@@ -0,0 +1,821 @@ ++/* ++ * .xz Stream decoder ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#include "private.h" ++#include "stream.h" ++ ++/* Hash used to validate the Index field */ ++struct xz_dec_hash { ++ vli_type unpadded; ++ vli_type uncompressed; ++ uint32_t crc32; ++}; ++ ++struct xz_dec { ++ /* Position in dec_main() */ ++ enum { ++ SEQ_STREAM_HEADER, ++ SEQ_BLOCK_START, ++ SEQ_BLOCK_HEADER, ++ SEQ_BLOCK_UNCOMPRESS, ++ SEQ_BLOCK_PADDING, ++ SEQ_BLOCK_CHECK, ++ SEQ_INDEX, ++ SEQ_INDEX_PADDING, ++ SEQ_INDEX_CRC32, ++ SEQ_STREAM_FOOTER ++ } sequence; ++ ++ /* Position in variable-length integers and Check fields */ ++ uint32_t pos; ++ ++ /* Variable-length integer decoded by dec_vli() */ ++ vli_type vli; ++ ++ /* Saved in_pos and out_pos */ ++ size_t in_start; ++ size_t out_start; ++ ++ /* CRC32 value in Block or Index */ ++ uint32_t crc32; ++ ++ /* Type of the integrity check calculated from uncompressed data */ ++ enum xz_check check_type; ++ ++ /* Operation mode */ ++ enum xz_mode mode; ++ ++ /* ++ * True if the next call to xz_dec_run() is allowed to return ++ * XZ_BUF_ERROR. ++ */ ++ bool_t allow_buf_error; ++ ++ /* Information stored in Block Header */ ++ struct { ++ /* ++ * Value stored in the Compressed Size field, or ++ * VLI_UNKNOWN if Compressed Size is not present. ++ */ ++ vli_type compressed; ++ ++ /* ++ * Value stored in the Uncompressed Size field, or ++ * VLI_UNKNOWN if Uncompressed Size is not present. ++ */ ++ vli_type uncompressed; ++ ++ /* Size of the Block Header field */ ++ uint32_t size; ++ } block_header; ++ ++ /* Information collected when decoding Blocks */ ++ struct { ++ /* Observed compressed size of the current Block */ ++ vli_type compressed; ++ ++ /* Observed uncompressed size of the current Block */ ++ vli_type uncompressed; ++ ++ /* Number of Blocks decoded so far */ ++ vli_type count; ++ ++ /* ++ * Hash calculated from the Block sizes. This is used to ++ * validate the Index field. ++ */ ++ struct xz_dec_hash hash; ++ } block; ++ ++ /* Variables needed when verifying the Index field */ ++ struct { ++ /* Position in dec_index() */ ++ enum { ++ SEQ_INDEX_COUNT, ++ SEQ_INDEX_UNPADDED, ++ SEQ_INDEX_UNCOMPRESSED ++ } sequence; ++ ++ /* Size of the Index in bytes */ ++ vli_type size; ++ ++ /* Number of Records (matches block.count in valid files) */ ++ vli_type count; ++ ++ /* ++ * Hash calculated from the Records (matches block.hash in ++ * valid files). ++ */ ++ struct xz_dec_hash hash; ++ } index; ++ ++ /* ++ * Temporary buffer needed to hold Stream Header, Block Header, ++ * and Stream Footer. The Block Header is the biggest (1 KiB) ++ * so we reserve space according to that. buf[] has to be aligned ++ * to a multiple of four bytes; the size_t variables before it ++ * should guarantee this. ++ */ ++ struct { ++ size_t pos; ++ size_t size; ++ uint8_t buf[1024]; ++ } temp; ++ ++ struct xz_dec_lzma2 *lzma2; ++ ++#ifdef XZ_DEC_BCJ ++ struct xz_dec_bcj *bcj; ++ bool_t bcj_active; ++#endif ++}; ++ ++#ifdef XZ_DEC_ANY_CHECK ++/* Sizes of the Check field with different Check IDs */ ++static const uint8_t check_sizes[16] = { ++ 0, ++ 4, 4, 4, ++ 8, 8, 8, ++ 16, 16, 16, ++ 32, 32, 32, ++ 64, 64, 64 ++}; ++#endif ++ ++/* ++ * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller ++ * must have set s->temp.pos to indicate how much data we are supposed ++ * to copy into s->temp.buf. Return true once s->temp.pos has reached ++ * s->temp.size. ++ */ ++static bool_t INIT fill_temp(struct xz_dec *s, struct xz_buf *b) ++{ ++ size_t copy_size = min_t(size_t, ++ b->in_size - b->in_pos, s->temp.size - s->temp.pos); ++ ++ memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size); ++ b->in_pos += copy_size; ++ s->temp.pos += copy_size; ++ ++ if (s->temp.pos == s->temp.size) { ++ s->temp.pos = 0; ++ return true; ++ } ++ ++ return false; ++} ++ ++/* Decode a variable-length integer (little-endian base-128 encoding) */ ++static enum xz_ret INIT dec_vli(struct xz_dec *s, const uint8_t *in, ++ size_t *in_pos, size_t in_size) ++{ ++ uint8_t byte; ++ ++ if (s->pos == 0) ++ s->vli = 0; ++ ++ while (*in_pos < in_size) { ++ byte = in[*in_pos]; ++ ++*in_pos; ++ ++ s->vli |= (vli_type)(byte & 0x7F) << s->pos; ++ ++ if ((byte & 0x80) == 0) { ++ /* Don't allow non-minimal encodings. */ ++ if (byte == 0 && s->pos != 0) ++ return XZ_DATA_ERROR; ++ ++ s->pos = 0; ++ return XZ_STREAM_END; ++ } ++ ++ s->pos += 7; ++ if (s->pos == 7 * VLI_BYTES_MAX) ++ return XZ_DATA_ERROR; ++ } ++ ++ return XZ_OK; ++} ++ ++/* ++ * Decode the Compressed Data field from a Block. Update and validate ++ * the observed compressed and uncompressed sizes of the Block so that ++ * they don't exceed the values possibly stored in the Block Header ++ * (validation assumes that no integer overflow occurs, since vli_type ++ * is normally uint64_t). Update the CRC32 if presence of the CRC32 ++ * field was indicated in Stream Header. ++ * ++ * Once the decoding is finished, validate that the observed sizes match ++ * the sizes possibly stored in the Block Header. Update the hash and ++ * Block count, which are later used to validate the Index field. ++ */ ++static enum xz_ret INIT dec_block(struct xz_dec *s, struct xz_buf *b) ++{ ++ enum xz_ret ret; ++ ++ s->in_start = b->in_pos; ++ s->out_start = b->out_pos; ++ ++#ifdef XZ_DEC_BCJ ++ if (s->bcj_active) ++ ret = xz_dec_bcj_run(s->bcj, s->lzma2, b); ++ else ++#endif ++ ret = xz_dec_lzma2_run(s->lzma2, b); ++ ++ s->block.compressed += b->in_pos - s->in_start; ++ s->block.uncompressed += b->out_pos - s->out_start; ++ ++ /* ++ * There is no need to separately check for VLI_UNKNOWN, since ++ * the observed sizes are always smaller than VLI_UNKNOWN. ++ */ ++ if (s->block.compressed > s->block_header.compressed ++ || s->block.uncompressed ++ > s->block_header.uncompressed) ++ return XZ_DATA_ERROR; ++ ++ if (s->check_type == XZ_CHECK_CRC32) ++ s->crc32 = xz_crc32(b->out + s->out_start, ++ b->out_pos - s->out_start, s->crc32); ++ ++ if (ret == XZ_STREAM_END) { ++ if (s->block_header.compressed != VLI_UNKNOWN ++ && s->block_header.compressed ++ != s->block.compressed) ++ return XZ_DATA_ERROR; ++ ++ if (s->block_header.uncompressed != VLI_UNKNOWN ++ && s->block_header.uncompressed ++ != s->block.uncompressed) ++ return XZ_DATA_ERROR; ++ ++ s->block.hash.unpadded += s->block_header.size ++ + s->block.compressed; ++ ++#ifdef XZ_DEC_ANY_CHECK ++ s->block.hash.unpadded += check_sizes[s->check_type]; ++#else ++ if (s->check_type == XZ_CHECK_CRC32) ++ s->block.hash.unpadded += 4; ++#endif ++ ++ s->block.hash.uncompressed += s->block.uncompressed; ++ s->block.hash.crc32 = xz_crc32( ++ (const uint8_t *)&s->block.hash, ++ sizeof(s->block.hash), s->block.hash.crc32); ++ ++ ++s->block.count; ++ } ++ ++ return ret; ++} ++ ++/* Update the Index size and the CRC32 value. */ ++static void INIT index_update(struct xz_dec *s, const struct xz_buf *b) ++{ ++ size_t in_used = b->in_pos - s->in_start; ++ s->index.size += in_used; ++ s->crc32 = xz_crc32(b->in + s->in_start, in_used, s->crc32); ++} ++ ++/* ++ * Decode the Number of Records, Unpadded Size, and Uncompressed Size ++ * fields from the Index field. That is, Index Padding and CRC32 are not ++ * decoded by this function. ++ * ++ * This can return XZ_OK (more input needed), XZ_STREAM_END (everything ++ * successfully decoded), or XZ_DATA_ERROR (input is corrupt). ++ */ ++static enum xz_ret INIT dec_index(struct xz_dec *s, struct xz_buf *b) ++{ ++ enum xz_ret ret; ++ ++ do { ++ ret = dec_vli(s, b->in, &b->in_pos, b->in_size); ++ if (ret != XZ_STREAM_END) { ++ index_update(s, b); ++ return ret; ++ } ++ ++ switch (s->index.sequence) { ++ case SEQ_INDEX_COUNT: ++ s->index.count = s->vli; ++ ++ /* ++ * Validate that the Number of Records field ++ * indicates the same number of Records as ++ * there were Blocks in the Stream. ++ */ ++ if (s->index.count != s->block.count) ++ return XZ_DATA_ERROR; ++ ++ s->index.sequence = SEQ_INDEX_UNPADDED; ++ break; ++ ++ case SEQ_INDEX_UNPADDED: ++ s->index.hash.unpadded += s->vli; ++ s->index.sequence = SEQ_INDEX_UNCOMPRESSED; ++ break; ++ ++ case SEQ_INDEX_UNCOMPRESSED: ++ s->index.hash.uncompressed += s->vli; ++ s->index.hash.crc32 = xz_crc32( ++ (const uint8_t *)&s->index.hash, ++ sizeof(s->index.hash), ++ s->index.hash.crc32); ++ --s->index.count; ++ s->index.sequence = SEQ_INDEX_UNPADDED; ++ break; ++ } ++ } while (s->index.count > 0); ++ ++ return XZ_STREAM_END; ++} ++ ++/* ++ * Validate that the next four input bytes match the value of s->crc32. ++ * s->pos must be zero when starting to validate the first byte. ++ */ ++static enum xz_ret INIT crc32_validate(struct xz_dec *s, struct xz_buf *b) ++{ ++ do { ++ if (b->in_pos == b->in_size) ++ return XZ_OK; ++ ++ if (((s->crc32 >> s->pos) & 0xFF) != b->in[b->in_pos++]) ++ return XZ_DATA_ERROR; ++ ++ s->pos += 8; ++ ++ } while (s->pos < 32); ++ ++ s->crc32 = 0; ++ s->pos = 0; ++ ++ return XZ_STREAM_END; ++} ++ ++#ifdef XZ_DEC_ANY_CHECK ++/* ++ * Skip over the Check field when the Check ID is not supported. ++ * Returns true once the whole Check field has been skipped over. ++ */ ++static bool_t INIT check_skip(struct xz_dec *s, struct xz_buf *b) ++{ ++ while (s->pos < check_sizes[s->check_type]) { ++ if (b->in_pos == b->in_size) ++ return false; ++ ++ ++b->in_pos; ++ ++s->pos; ++ } ++ ++ s->pos = 0; ++ ++ return true; ++} ++#endif ++ ++/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */ ++static enum xz_ret INIT dec_stream_header(struct xz_dec *s) ++{ ++ if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE)) ++ return XZ_FORMAT_ERROR; ++ ++ if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0) ++ != get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2)) ++ return XZ_DATA_ERROR; ++ ++ if (s->temp.buf[HEADER_MAGIC_SIZE] != 0) ++ return XZ_OPTIONS_ERROR; ++ ++ /* ++ * Of integrity checks, we support only none (Check ID = 0) and ++ * CRC32 (Check ID = 1). However, if XZ_DEC_ANY_CHECK is defined, ++ * we will accept other check types too, but then the check won't ++ * be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given. ++ */ ++ s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1]; ++ ++#ifdef XZ_DEC_ANY_CHECK ++ if (s->check_type > XZ_CHECK_MAX) ++ return XZ_OPTIONS_ERROR; ++ ++ if (s->check_type > XZ_CHECK_CRC32) ++ return XZ_UNSUPPORTED_CHECK; ++#else ++ if (s->check_type > XZ_CHECK_CRC32) ++ return XZ_OPTIONS_ERROR; ++#endif ++ ++ return XZ_OK; ++} ++ ++/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */ ++static enum xz_ret INIT dec_stream_footer(struct xz_dec *s) ++{ ++ if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE)) ++ return XZ_DATA_ERROR; ++ ++ if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf)) ++ return XZ_DATA_ERROR; ++ ++ /* ++ * Validate Backward Size. Note that we never added the size of the ++ * Index CRC32 field to s->index.size, thus we use s->index.size / 4 ++ * instead of s->index.size / 4 - 1. ++ */ ++ if ((s->index.size >> 2) != get_le32(s->temp.buf + 4)) ++ return XZ_DATA_ERROR; ++ ++ if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type) ++ return XZ_DATA_ERROR; ++ ++ /* ++ * Use XZ_STREAM_END instead of XZ_OK to be more convenient ++ * for the caller. ++ */ ++ return XZ_STREAM_END; ++} ++ ++/* Decode the Block Header and initialize the filter chain. */ ++static enum xz_ret INIT dec_block_header(struct xz_dec *s) ++{ ++ enum xz_ret ret; ++ ++ /* ++ * Validate the CRC32. We know that the temp buffer is at least ++ * eight bytes so this is safe. ++ */ ++ s->temp.size -= 4; ++ if (xz_crc32(s->temp.buf, s->temp.size, 0) ++ != get_le32(s->temp.buf + s->temp.size)) ++ return XZ_DATA_ERROR; ++ ++ s->temp.pos = 2; ++ ++ /* ++ * Catch unsupported Block Flags. We support only one or two filters ++ * in the chain, so we catch that with the same test. ++ */ ++#ifdef XZ_DEC_BCJ ++ if (s->temp.buf[1] & 0x3E) ++#else ++ if (s->temp.buf[1] & 0x3F) ++#endif ++ return XZ_OPTIONS_ERROR; ++ ++ /* Compressed Size */ ++ if (s->temp.buf[1] & 0x40) { ++ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) ++ != XZ_STREAM_END) ++ return XZ_DATA_ERROR; ++ ++ s->block_header.compressed = s->vli; ++ } else { ++ s->block_header.compressed = VLI_UNKNOWN; ++ } ++ ++ /* Uncompressed Size */ ++ if (s->temp.buf[1] & 0x80) { ++ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) ++ != XZ_STREAM_END) ++ return XZ_DATA_ERROR; ++ ++ s->block_header.uncompressed = s->vli; ++ } else { ++ s->block_header.uncompressed = VLI_UNKNOWN; ++ } ++ ++#ifdef XZ_DEC_BCJ ++ /* If there are two filters, the first one must be a BCJ filter. */ ++ s->bcj_active = s->temp.buf[1] & 0x01; ++ if (s->bcj_active) { ++ if (s->temp.size - s->temp.pos < 2) ++ return XZ_OPTIONS_ERROR; ++ ++ ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]); ++ if (ret != XZ_OK) ++ return ret; ++ ++ /* ++ * We don't support custom start offset, ++ * so Size of Properties must be zero. ++ */ ++ if (s->temp.buf[s->temp.pos++] != 0x00) ++ return XZ_OPTIONS_ERROR; ++ } ++#endif ++ ++ /* Valid Filter Flags always take at least two bytes. */ ++ if (s->temp.size - s->temp.pos < 2) ++ return XZ_DATA_ERROR; ++ ++ /* Filter ID = LZMA2 */ ++ if (s->temp.buf[s->temp.pos++] != 0x21) ++ return XZ_OPTIONS_ERROR; ++ ++ /* Size of Properties = 1-byte Filter Properties */ ++ if (s->temp.buf[s->temp.pos++] != 0x01) ++ return XZ_OPTIONS_ERROR; ++ ++ /* Filter Properties contains LZMA2 dictionary size. */ ++ if (s->temp.size - s->temp.pos < 1) ++ return XZ_DATA_ERROR; ++ ++ ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]); ++ if (ret != XZ_OK) ++ return ret; ++ ++ /* The rest must be Header Padding. */ ++ while (s->temp.pos < s->temp.size) ++ if (s->temp.buf[s->temp.pos++] != 0x00) ++ return XZ_OPTIONS_ERROR; ++ ++ s->temp.pos = 0; ++ s->block.compressed = 0; ++ s->block.uncompressed = 0; ++ ++ return XZ_OK; ++} ++ ++static enum xz_ret INIT dec_main(struct xz_dec *s, struct xz_buf *b) ++{ ++ enum xz_ret ret; ++ ++ /* ++ * Store the start position for the case when we are in the middle ++ * of the Index field. ++ */ ++ s->in_start = b->in_pos; ++ ++ while (true) { ++ switch (s->sequence) { ++ case SEQ_STREAM_HEADER: ++ /* ++ * Stream Header is copied to s->temp, and then ++ * decoded from there. This way if the caller ++ * gives us only little input at a time, we can ++ * still keep the Stream Header decoding code ++ * simple. Similar approach is used in many places ++ * in this file. ++ */ ++ if (!fill_temp(s, b)) ++ return XZ_OK; ++ ++ /* ++ * If dec_stream_header() returns ++ * XZ_UNSUPPORTED_CHECK, it is still possible ++ * to continue decoding if working in multi-call ++ * mode. Thus, update s->sequence before calling ++ * dec_stream_header(). ++ */ ++ s->sequence = SEQ_BLOCK_START; ++ ++ ret = dec_stream_header(s); ++ if (ret != XZ_OK) ++ return ret; ++ ++ case SEQ_BLOCK_START: ++ /* We need one byte of input to continue. */ ++ if (b->in_pos == b->in_size) ++ return XZ_OK; ++ ++ /* See if this is the beginning of the Index field. */ ++ if (b->in[b->in_pos] == 0) { ++ s->in_start = b->in_pos++; ++ s->sequence = SEQ_INDEX; ++ break; ++ } ++ ++ /* ++ * Calculate the size of the Block Header and ++ * prepare to decode it. ++ */ ++ s->block_header.size ++ = ((uint32_t)b->in[b->in_pos] + 1) * 4; ++ ++ s->temp.size = s->block_header.size; ++ s->temp.pos = 0; ++ s->sequence = SEQ_BLOCK_HEADER; ++ ++ case SEQ_BLOCK_HEADER: ++ if (!fill_temp(s, b)) ++ return XZ_OK; ++ ++ ret = dec_block_header(s); ++ if (ret != XZ_OK) ++ return ret; ++ ++ s->sequence = SEQ_BLOCK_UNCOMPRESS; ++ ++ case SEQ_BLOCK_UNCOMPRESS: ++ ret = dec_block(s, b); ++ if (ret != XZ_STREAM_END) ++ return ret; ++ ++ s->sequence = SEQ_BLOCK_PADDING; ++ ++ case SEQ_BLOCK_PADDING: ++ /* ++ * Size of Compressed Data + Block Padding ++ * must be a multiple of four. We don't need ++ * s->block.compressed for anything else ++ * anymore, so we use it here to test the size ++ * of the Block Padding field. ++ */ ++ while (s->block.compressed & 3) { ++ if (b->in_pos == b->in_size) ++ return XZ_OK; ++ ++ if (b->in[b->in_pos++] != 0) ++ return XZ_DATA_ERROR; ++ ++ ++s->block.compressed; ++ } ++ ++ s->sequence = SEQ_BLOCK_CHECK; ++ ++ case SEQ_BLOCK_CHECK: ++ if (s->check_type == XZ_CHECK_CRC32) { ++ ret = crc32_validate(s, b); ++ if (ret != XZ_STREAM_END) ++ return ret; ++ } ++#ifdef XZ_DEC_ANY_CHECK ++ else if (!check_skip(s, b)) { ++ return XZ_OK; ++ } ++#endif ++ ++ s->sequence = SEQ_BLOCK_START; ++ break; ++ ++ case SEQ_INDEX: ++ ret = dec_index(s, b); ++ if (ret != XZ_STREAM_END) ++ return ret; ++ ++ s->sequence = SEQ_INDEX_PADDING; ++ ++ case SEQ_INDEX_PADDING: ++ while ((s->index.size + (b->in_pos - s->in_start)) ++ & 3) { ++ if (b->in_pos == b->in_size) { ++ index_update(s, b); ++ return XZ_OK; ++ } ++ ++ if (b->in[b->in_pos++] != 0) ++ return XZ_DATA_ERROR; ++ } ++ ++ /* Finish the CRC32 value and Index size. */ ++ index_update(s, b); ++ ++ /* Compare the hashes to validate the Index field. */ ++ if (!memeq(&s->block.hash, &s->index.hash, ++ sizeof(s->block.hash))) ++ return XZ_DATA_ERROR; ++ ++ s->sequence = SEQ_INDEX_CRC32; ++ ++ case SEQ_INDEX_CRC32: ++ ret = crc32_validate(s, b); ++ if (ret != XZ_STREAM_END) ++ return ret; ++ ++ s->temp.size = STREAM_HEADER_SIZE; ++ s->sequence = SEQ_STREAM_FOOTER; ++ ++ case SEQ_STREAM_FOOTER: ++ if (!fill_temp(s, b)) ++ return XZ_OK; ++ ++ return dec_stream_footer(s); ++ } ++ } ++ ++ /* Never reached */ ++} ++ ++XZ_EXTERN void INIT xz_dec_reset(struct xz_dec *s) ++{ ++ s->sequence = SEQ_STREAM_HEADER; ++ s->allow_buf_error = false; ++ s->pos = 0; ++ s->crc32 = 0; ++ memzero(&s->block, sizeof(s->block)); ++ memzero(&s->index, sizeof(s->index)); ++ s->temp.pos = 0; ++ s->temp.size = STREAM_HEADER_SIZE; ++} ++ ++/* ++ * xz_dec_run() is a wrapper for dec_main() to handle some special cases in ++ * multi-call and single-call decoding. ++ * ++ * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we ++ * are not going to make any progress anymore. This is to prevent the caller ++ * from calling us infinitely when the input file is truncated or otherwise ++ * corrupt. Since zlib-style API allows that the caller fills the input buffer ++ * only when the decoder doesn't produce any new output, we have to be careful ++ * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only ++ * after the second consecutive call to xz_dec_run() that makes no progress. ++ * ++ * In single-call mode, if we couldn't decode everything and no error ++ * occurred, either the input is truncated or the output buffer is too small. ++ * Since we know that the last input byte never produces any output, we know ++ * that if all the input was consumed and decoding wasn't finished, the file ++ * must be corrupt. Otherwise the output buffer has to be too small or the ++ * file is corrupt in a way that decoding it produces too big output. ++ * ++ * If single-call decoding fails, we reset b->in_pos and b->out_pos back to ++ * their original values. This is because with some filter chains there won't ++ * be any valid uncompressed data in the output buffer unless the decoding ++ * actually succeeds (that's the price to pay of using the output buffer as ++ * the workspace). ++ */ ++XZ_EXTERN enum xz_ret INIT xz_dec_run(struct xz_dec *s, struct xz_buf *b) ++{ ++ size_t in_start; ++ size_t out_start; ++ enum xz_ret ret; ++ ++ if (DEC_IS_SINGLE(s->mode)) ++ xz_dec_reset(s); ++ ++ in_start = b->in_pos; ++ out_start = b->out_pos; ++ ret = dec_main(s, b); ++ ++ if (DEC_IS_SINGLE(s->mode)) { ++ if (ret == XZ_OK) ++ ret = b->in_pos == b->in_size ++ ? XZ_DATA_ERROR : XZ_BUF_ERROR; ++ ++ if (ret != XZ_STREAM_END) { ++ b->in_pos = in_start; ++ b->out_pos = out_start; ++ } ++ ++ } else if (ret == XZ_OK && in_start == b->in_pos ++ && out_start == b->out_pos) { ++ if (s->allow_buf_error) ++ ret = XZ_BUF_ERROR; ++ ++ s->allow_buf_error = true; ++ } else { ++ s->allow_buf_error = false; ++ } ++ ++ return ret; ++} ++ ++XZ_EXTERN struct xz_dec *INIT xz_dec_init(enum xz_mode mode, uint32_t dict_max) ++{ ++ struct xz_dec *s = malloc(sizeof(*s)); ++ if (s == NULL) ++ return NULL; ++ ++ s->mode = mode; ++ ++#ifdef XZ_DEC_BCJ ++ s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode)); ++ if (s->bcj == NULL) ++ goto error_bcj; ++#endif ++ ++ s->lzma2 = xz_dec_lzma2_create(mode, dict_max); ++ if (s->lzma2 == NULL) ++ goto error_lzma2; ++ ++ xz_dec_reset(s); ++ return s; ++ ++error_lzma2: ++#ifdef XZ_DEC_BCJ ++ xz_dec_bcj_end(s->bcj); ++error_bcj: ++#endif ++ free(s); ++ return NULL; ++} ++ ++XZ_EXTERN void INIT xz_dec_end(struct xz_dec *s) ++{ ++ if (s != NULL) { ++ xz_dec_lzma2_end(s->lzma2); ++#ifdef XZ_DEC_BCJ ++ xz_dec_bcj_end(s->bcj); ++#endif ++ free(s); ++ } ++} +diff --git a/xen/common/xz/lzma2.h b/xen/common/xz/lzma2.h +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/lzma2.h +@@ -0,0 +1,204 @@ ++/* ++ * LZMA2 definitions ++ * ++ * Authors: Lasse Collin ++ * Igor Pavlov ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#ifndef XZ_LZMA2_H ++#define XZ_LZMA2_H ++ ++/* Range coder constants */ ++#define RC_SHIFT_BITS 8 ++#define RC_TOP_BITS 24 ++#define RC_TOP_VALUE (1 << RC_TOP_BITS) ++#define RC_BIT_MODEL_TOTAL_BITS 11 ++#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS) ++#define RC_MOVE_BITS 5 ++ ++/* ++ * Maximum number of position states. A position state is the lowest pb ++ * number of bits of the current uncompressed offset. In some places there ++ * are different sets of probabilities for different position states. ++ */ ++#define POS_STATES_MAX (1 << 4) ++ ++/* ++ * This enum is used to track which LZMA symbols have occurred most recently ++ * and in which order. This information is used to predict the next symbol. ++ * ++ * Symbols: ++ * - Literal: One 8-bit byte ++ * - Match: Repeat a chunk of data at some distance ++ * - Long repeat: Multi-byte match at a recently seen distance ++ * - Short repeat: One-byte repeat at a recently seen distance ++ * ++ * The symbol names are in from STATE_oldest_older_previous. REP means ++ * either short or long repeated match, and NONLIT means any non-literal. ++ */ ++enum lzma_state { ++ STATE_LIT_LIT, ++ STATE_MATCH_LIT_LIT, ++ STATE_REP_LIT_LIT, ++ STATE_SHORTREP_LIT_LIT, ++ STATE_MATCH_LIT, ++ STATE_REP_LIT, ++ STATE_SHORTREP_LIT, ++ STATE_LIT_MATCH, ++ STATE_LIT_LONGREP, ++ STATE_LIT_SHORTREP, ++ STATE_NONLIT_MATCH, ++ STATE_NONLIT_REP ++}; ++ ++/* Total number of states */ ++#define STATES 12 ++ ++/* The lowest 7 states indicate that the previous state was a literal. */ ++#define LIT_STATES 7 ++ ++/* Indicate that the latest symbol was a literal. */ ++static inline void INIT lzma_state_literal(enum lzma_state *state) ++{ ++ if (*state <= STATE_SHORTREP_LIT_LIT) ++ *state = STATE_LIT_LIT; ++ else if (*state <= STATE_LIT_SHORTREP) ++ *state -= 3; ++ else ++ *state -= 6; ++} ++ ++/* Indicate that the latest symbol was a match. */ ++static inline void INIT lzma_state_match(enum lzma_state *state) ++{ ++ *state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH; ++} ++ ++/* Indicate that the latest state was a long repeated match. */ ++static inline void INIT lzma_state_long_rep(enum lzma_state *state) ++{ ++ *state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP; ++} ++ ++/* Indicate that the latest symbol was a short match. */ ++static inline void INIT lzma_state_short_rep(enum lzma_state *state) ++{ ++ *state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP; ++} ++ ++/* Test if the previous symbol was a literal. */ ++static inline bool_t INIT lzma_state_is_literal(enum lzma_state state) ++{ ++ return state < LIT_STATES; ++} ++ ++/* Each literal coder is divided in three sections: ++ * - 0x001-0x0FF: Without match byte ++ * - 0x101-0x1FF: With match byte; match bit is 0 ++ * - 0x201-0x2FF: With match byte; match bit is 1 ++ * ++ * Match byte is used when the previous LZMA symbol was something else than ++ * a literal (that is, it was some kind of match). ++ */ ++#define LITERAL_CODER_SIZE 0x300 ++ ++/* Maximum number of literal coders */ ++#define LITERAL_CODERS_MAX (1 << 4) ++ ++/* Minimum length of a match is two bytes. */ ++#define MATCH_LEN_MIN 2 ++ ++/* Match length is encoded with 4, 5, or 10 bits. ++ * ++ * Length Bits ++ * 2-9 4 = Choice=0 + 3 bits ++ * 10-17 5 = Choice=1 + Choice2=0 + 3 bits ++ * 18-273 10 = Choice=1 + Choice2=1 + 8 bits ++ */ ++#define LEN_LOW_BITS 3 ++#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS) ++#define LEN_MID_BITS 3 ++#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS) ++#define LEN_HIGH_BITS 8 ++#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS) ++#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS) ++ ++/* ++ * Maximum length of a match is 273 which is a result of the encoding ++ * described above. ++ */ ++#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1) ++ ++/* ++ * Different sets of probabilities are used for match distances that have ++ * very short match length: Lengths of 2, 3, and 4 bytes have a separate ++ * set of probabilities for each length. The matches with longer length ++ * use a shared set of probabilities. ++ */ ++#define DIST_STATES 4 ++ ++/* ++ * Get the index of the appropriate probability array for decoding ++ * the distance slot. ++ */ ++static inline uint32_t INIT lzma_get_dist_state(uint32_t len) ++{ ++ return len < DIST_STATES + MATCH_LEN_MIN ++ ? len - MATCH_LEN_MIN : DIST_STATES - 1; ++} ++ ++/* ++ * The highest two bits of a 32-bit match distance are encoded using six bits. ++ * This six-bit value is called a distance slot. This way encoding a 32-bit ++ * value takes 6-36 bits, larger values taking more bits. ++ */ ++#define DIST_SLOT_BITS 6 ++#define DIST_SLOTS (1 << DIST_SLOT_BITS) ++ ++/* Match distances up to 127 are fully encoded using probabilities. Since ++ * the highest two bits (distance slot) are always encoded using six bits, ++ * the distances 0-3 don't need any additional bits to encode, since the ++ * distance slot itself is the same as the actual distance. DIST_MODEL_START ++ * indicates the first distance slot where at least one additional bit is ++ * needed. ++ */ ++#define DIST_MODEL_START 4 ++ ++/* ++ * Match distances greater than 127 are encoded in three pieces: ++ * - distance slot: the highest two bits ++ * - direct bits: 2-26 bits below the highest two bits ++ * - alignment bits: four lowest bits ++ * ++ * Direct bits don't use any probabilities. ++ * ++ * The distance slot value of 14 is for distances 128-191. ++ */ ++#define DIST_MODEL_END 14 ++ ++/* Distance slots that indicate a distance <= 127. */ ++#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2) ++#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS) ++ ++/* ++ * For match distances greater than 127, only the highest two bits and the ++ * lowest four bits (alignment) is encoded using probabilities. ++ */ ++#define ALIGN_BITS 4 ++#define ALIGN_SIZE (1 << ALIGN_BITS) ++#define ALIGN_MASK (ALIGN_SIZE - 1) ++ ++/* Total number of all probability variables */ ++#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE) ++ ++/* ++ * LZMA remembers the four most recent match distances. Reusing these ++ * distances tends to take less space than re-encoding the actual ++ * distance value. ++ */ ++#define REPS 4 ++ ++#endif +diff --git a/xen/common/xz/private.h b/xen/common/xz/private.h +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/private.h +@@ -0,0 +1,271 @@ ++/* ++ * Private includes and definitions ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#ifndef XZ_PRIVATE_H ++#define XZ_PRIVATE_H ++ ++#include ++#include ++#define get_le32(p) le32_to_cpup((const uint32_t *)(p)) ++ ++#if 1 /* ndef CONFIG_??? */ ++static inline u32 INIT get_unaligned_le32(void *p) ++{ ++ return le32_to_cpup(p); ++} ++ ++static inline void INIT put_unaligned_le32(u32 val, void *p) ++{ ++ *(__force __le32*)p = cpu_to_le32(val); ++} ++#else ++#include ++ ++static inline u32 INIT get_unaligned_le32(void *p) ++{ ++ return le32_to_cpu(__get_unaligned(p, 4)); ++} ++ ++static inline void INIT put_unaligned_le32(u32 val, void *p) ++{ ++ __put_unaligned(cpu_to_le32(val), p, 4); ++} ++#endif ++ ++#define false 0 ++#define true 1 ++ ++/** ++ * enum xz_mode - Operation mode ++ * ++ * @XZ_SINGLE: Single-call mode. This uses less RAM than ++ * than multi-call modes, because the LZMA2 ++ * dictionary doesn't need to be allocated as ++ * part of the decoder state. All required data ++ * structures are allocated at initialization, ++ * so xz_dec_run() cannot return XZ_MEM_ERROR. ++ * @XZ_PREALLOC: Multi-call mode with preallocated LZMA2 ++ * dictionary buffer. All data structures are ++ * allocated at initialization, so xz_dec_run() ++ * cannot return XZ_MEM_ERROR. ++ * @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is ++ * allocated once the required size has been ++ * parsed from the stream headers. If the ++ * allocation fails, xz_dec_run() will return ++ * XZ_MEM_ERROR. ++ * ++ * It is possible to enable support only for a subset of the above ++ * modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC, ++ * or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled ++ * with support for all operation modes, but the preboot code may ++ * be built with fewer features to minimize code size. ++ */ ++enum xz_mode { ++ XZ_SINGLE, ++ XZ_PREALLOC, ++ XZ_DYNALLOC ++}; ++ ++/** ++ * enum xz_ret - Return codes ++ * @XZ_OK: Everything is OK so far. More input or more ++ * output space is required to continue. This ++ * return code is possible only in multi-call mode ++ * (XZ_PREALLOC or XZ_DYNALLOC). ++ * @XZ_STREAM_END: Operation finished successfully. ++ * @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding ++ * is still possible in multi-call mode by simply ++ * calling xz_dec_run() again. ++ * Note that this return value is used only if ++ * XZ_DEC_ANY_CHECK was defined at build time, ++ * which is not used in the kernel. Unsupported ++ * check types return XZ_OPTIONS_ERROR if ++ * XZ_DEC_ANY_CHECK was not defined at build time. ++ * @XZ_MEM_ERROR: Allocating memory failed. This return code is ++ * possible only if the decoder was initialized ++ * with XZ_DYNALLOC. The amount of memory that was ++ * tried to be allocated was no more than the ++ * dict_max argument given to xz_dec_init(). ++ * @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than ++ * allowed by the dict_max argument given to ++ * xz_dec_init(). This return value is possible ++ * only in multi-call mode (XZ_PREALLOC or ++ * XZ_DYNALLOC); the single-call mode (XZ_SINGLE) ++ * ignores the dict_max argument. ++ * @XZ_FORMAT_ERROR: File format was not recognized (wrong magic ++ * bytes). ++ * @XZ_OPTIONS_ERROR: This implementation doesn't support the requested ++ * compression options. In the decoder this means ++ * that the header CRC32 matches, but the header ++ * itself specifies something that we don't support. ++ * @XZ_DATA_ERROR: Compressed data is corrupt. ++ * @XZ_BUF_ERROR: Cannot make any progress. Details are slightly ++ * different between multi-call and single-call ++ * mode; more information below. ++ * ++ * In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls ++ * to XZ code cannot consume any input and cannot produce any new output. ++ * This happens when there is no new input available, or the output buffer ++ * is full while at least one output byte is still pending. Assuming your ++ * code is not buggy, you can get this error only when decoding a compressed ++ * stream that is truncated or otherwise corrupt. ++ * ++ * In single-call mode, XZ_BUF_ERROR is returned only when the output buffer ++ * is too small or the compressed input is corrupt in a way that makes the ++ * decoder produce more output than the caller expected. When it is ++ * (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR ++ * is used instead of XZ_BUF_ERROR. ++ */ ++enum xz_ret { ++ XZ_OK, ++ XZ_STREAM_END, ++ XZ_UNSUPPORTED_CHECK, ++ XZ_MEM_ERROR, ++ XZ_MEMLIMIT_ERROR, ++ XZ_FORMAT_ERROR, ++ XZ_OPTIONS_ERROR, ++ XZ_DATA_ERROR, ++ XZ_BUF_ERROR ++}; ++ ++/** ++ * struct xz_buf - Passing input and output buffers to XZ code ++ * @in: Beginning of the input buffer. This may be NULL if and only ++ * if in_pos is equal to in_size. ++ * @in_pos: Current position in the input buffer. This must not exceed ++ * in_size. ++ * @in_size: Size of the input buffer ++ * @out: Beginning of the output buffer. This may be NULL if and only ++ * if out_pos is equal to out_size. ++ * @out_pos: Current position in the output buffer. This must not exceed ++ * out_size. ++ * @out_size: Size of the output buffer ++ * ++ * Only the contents of the output buffer from out[out_pos] onward, and ++ * the variables in_pos and out_pos are modified by the XZ code. ++ */ ++struct xz_buf { ++ const uint8_t *in; ++ size_t in_pos; ++ size_t in_size; ++ ++ uint8_t *out; ++ size_t out_pos; ++ size_t out_size; ++}; ++ ++/** ++ * struct xz_dec - Opaque type to hold the XZ decoder state ++ */ ++struct xz_dec; ++ ++/* If no specific decoding mode is requested, enable support for all modes. */ ++#if !defined(XZ_DEC_SINGLE) && !defined(XZ_DEC_PREALLOC) \ ++ && !defined(XZ_DEC_DYNALLOC) ++# define XZ_DEC_SINGLE ++# define XZ_DEC_PREALLOC ++# define XZ_DEC_DYNALLOC ++#endif ++ ++/* ++ * The DEC_IS_foo(mode) macros are used in "if" statements. If only some ++ * of the supported modes are enabled, these macros will evaluate to true or ++ * false at compile time and thus allow the compiler to omit unneeded code. ++ */ ++#ifdef XZ_DEC_SINGLE ++# define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE) ++#else ++# define DEC_IS_SINGLE(mode) (false) ++#endif ++ ++#ifdef XZ_DEC_PREALLOC ++# define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC) ++#else ++# define DEC_IS_PREALLOC(mode) (false) ++#endif ++ ++#ifdef XZ_DEC_DYNALLOC ++# define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC) ++#else ++# define DEC_IS_DYNALLOC(mode) (false) ++#endif ++ ++#if !defined(XZ_DEC_SINGLE) ++# define DEC_IS_MULTI(mode) (true) ++#elif defined(XZ_DEC_PREALLOC) || defined(XZ_DEC_DYNALLOC) ++# define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE) ++#else ++# define DEC_IS_MULTI(mode) (false) ++#endif ++ ++/* ++ * If any of the BCJ filter decoders are wanted, define XZ_DEC_BCJ. ++ * XZ_DEC_BCJ is used to enable generic support for BCJ decoders. ++ */ ++#ifndef XZ_DEC_BCJ ++# if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \ ++ || defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \ ++ || defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \ ++ || defined(XZ_DEC_SPARC) ++# define XZ_DEC_BCJ ++# endif ++#endif ++ ++/* ++ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used ++ * before calling xz_dec_lzma2_run(). ++ */ ++XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, ++ uint32_t dict_max); ++ ++/* ++ * Decode the LZMA2 properties (one byte) and reset the decoder. Return ++ * XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not ++ * big enough, and XZ_OPTIONS_ERROR if props indicates something that this ++ * decoder doesn't support. ++ */ ++XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, ++ uint8_t props); ++ ++/* Decode raw LZMA2 stream from b->in to b->out. */ ++XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, ++ struct xz_buf *b); ++ ++/* Free the memory allocated for the LZMA2 decoder. */ ++XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s); ++ ++#ifdef XZ_DEC_BCJ ++/* ++ * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before ++ * calling xz_dec_bcj_run(). ++ */ ++XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool_t single_call); ++ ++/* ++ * Decode the Filter ID of a BCJ filter. This implementation doesn't ++ * support custom start offsets, so no decoding of Filter Properties ++ * is needed. Returns XZ_OK if the given Filter ID is supported. ++ * Otherwise XZ_OPTIONS_ERROR is returned. ++ */ ++XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id); ++ ++/* ++ * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is ++ * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run() ++ * must be called directly. ++ */ ++XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, ++ struct xz_dec_lzma2 *lzma2, ++ struct xz_buf *b); ++ ++/* Free the memory allocated for the BCJ filters. */ ++#define xz_dec_bcj_end(s) free(s) ++#endif ++ ++#endif +diff --git a/xen/common/xz/stream.h b/xen/common/xz/stream.h +new file mode 100644 +--- /dev/null ++++ b/xen/common/xz/stream.h +@@ -0,0 +1,55 @@ ++/* ++ * Definitions for handling the .xz file format ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#ifndef XZ_STREAM_H ++#define XZ_STREAM_H ++ ++/* ++ * See the .xz file format specification at ++ * http://tukaani.org/xz/xz-file-format.txt ++ * to understand the container format. ++ */ ++ ++#define STREAM_HEADER_SIZE 12 ++ ++#define HEADER_MAGIC "\3757zXZ" ++#define HEADER_MAGIC_SIZE 6 ++ ++#define FOOTER_MAGIC "YZ" ++#define FOOTER_MAGIC_SIZE 2 ++ ++/* ++ * Variable-length integer can hold a 63-bit unsigned integer or a special ++ * value indicating that the value is unknown. ++ * ++ * Experimental: vli_type can be defined to uint32_t to save a few bytes ++ * in code size (no effect on speed). Doing so limits the uncompressed and ++ * compressed size of the file to less than 256 MiB and may also weaken ++ * error detection slightly. ++ */ ++typedef uint64_t vli_type; ++ ++#define VLI_MAX ((vli_type)-1 / 2) ++#define VLI_UNKNOWN ((vli_type)-1) ++ ++/* Maximum encoded size of a VLI */ ++#define VLI_BYTES_MAX (sizeof(vli_type) * 8 / 7) ++ ++/* Integrity Check types */ ++enum xz_check { ++ XZ_CHECK_NONE = 0, ++ XZ_CHECK_CRC32 = 1, ++ XZ_CHECK_CRC64 = 4, ++ XZ_CHECK_SHA256 = 10 ++}; ++ ++/* Maximum possible Check ID */ ++#define XZ_CHECK_MAX 15 ++ ++#endif +diff --git a/xen/include/xen/decompress.h b/xen/include/xen/decompress.h +--- a/xen/include/xen/decompress.h ++++ b/xen/include/xen/decompress.h +@@ -31,7 +31,7 @@ + * dependent). + */ + +-decompress_fn bunzip2, unlzma, unlzo; ++decompress_fn bunzip2, unxz, unlzma, unlzo; + + int decompress(void *inbuf, unsigned int len, void *outbuf); \ No newline at end of file diff --git a/kernels/xen/parabolainit.patch b/kernels/xen/parabolainit.patch new file mode 100644 index 000000000..645a66edd --- /dev/null +++ b/kernels/xen/parabolainit.patch @@ -0,0 +1,423 @@ +diff -Naur orig.xen-4.1.1//tools/hotplug/Linux/init.d/xencommons xen-4.1.1//tools/hotplug/Linux/init.d/xencommons +--- orig.xen-4.1.1//tools/hotplug/Linux/init.d/xencommons 2011-07-03 03:08:44.953747064 -0700 ++++ xen-4.1.1//tools/hotplug/Linux/init.d/xencommons 2011-07-05 13:47:54.627029164 -0700 +@@ -18,6 +18,9 @@ + # Description: Starts and stops the daemons neeeded for xl/xend + ### END INIT INFO + ++. /etc/rc.conf ++. /etc/rc.d/functions ++ + if [ -d /etc/sysconfig ]; then + xencommons_config=/etc/sysconfig + else +@@ -26,7 +29,7 @@ + + test -f $xencommons_config/xencommons && . $xencommons_config/xencommons + +-XENCONSOLED_PIDFILE=/var/run/xenconsoled.pid ++XENCONSOLED_PIDFILE=/run/daemons/xenconsoled.pid + shopt -s extglob + + if test "x$1" = xstart && \ +@@ -51,8 +54,9 @@ + rm -f "$XENSTORED_ROOTDIR"/tdb* &>/dev/null + test -z "$XENSTORED_TRACE" || XENSTORED_ARGS=" -T /var/log/xen/xenstored-trace.log" + +- echo -n Starting xenstored... +- xenstored --pid-file=/var/run/xenstored.pid $XENSTORED_ARGS ++ #echo -n Starting xenstored... ++ stat_busy "Starting xenstored" ++ xenstored --pid-file=/run/daemons/xenstored.pid $XENSTORED_ARGS + + # Wait for xenstored to actually come up, timing out after 30 seconds + while [ $time -lt $timeout ] && ! `xenstore-read -s / >/dev/null 2>&1` ; do +@@ -60,33 +64,39 @@ + time=$(($time+1)) + sleep 1 + done +- echo +- + # Exit if we timed out + if ! [ $time -lt $timeout ] ; then +- echo Could not start xenstored ++ #echo Could not start xenstored ++ stat_fail + exit 1 + fi ++ stat_done + +- echo Setting domain 0 name... ++ stat_busy "Setting domain 0 name..." + xenstore-write "/local/domain/0/name" "Domain-0" ++ stat_done + fi + +- echo Starting xenconsoled... ++ #echo Starting xenconsoled... ++ stat_busy "Starting xenconsoled" + test -z "$XENCONSOLED_TRACE" || XENCONSOLED_ARGS=" --log=$XENCONSOLED_TRACE" + xenconsoled --pid-file=$XENCONSOLED_PIDFILE $XENCONSOLED_ARGS + test -z "$XENBACKENDD_DEBUG" || XENBACKENDD_ARGS="-d" + test "`uname`" != "NetBSD" || xenbackendd $XENBACKENDD_ARGS ++ stat_done ++ add_daemon xencommons + } + do_stop () { +- echo Stopping xenconsoled ++ stat_busy "Stopping xenconsoled" + if read 2>/dev/null <$XENCONSOLED_PIDFILE pid; then + kill $pid + while kill -9 $pid >/dev/null 2>&1; do sleep 0.1; done + rm -f $XENCONSOLED_PIDFILE + fi ++ stat_done + +- echo WARNING: Not stopping xenstored, as it cannot be restarted. ++ printhl "WARNING: Not stopping xenstored, as it cannot be restarted." ++ rm_daemon xencommons + } + + case "$1" in +diff -Naur orig.xen-4.1.1//tools/hotplug/Linux/init.d/xend xen-4.1.1//tools/hotplug/Linux/init.d/xend +--- orig.xen-4.1.1//tools/hotplug/Linux/init.d/xend 2011-07-03 03:08:44.953747064 -0700 ++++ xen-4.1.1//tools/hotplug/Linux/init.d/xend 2011-07-05 01:47:40.981951191 -0700 +@@ -18,6 +18,10 @@ + # Description: Starts and stops the Xen control daemon. + ### END INIT INFO + ++. /etc/rc.conf ++. /etc/rc.d/functions ++ ++ + shopt -s extglob + + # Wait for Xend to be up +@@ -37,23 +41,30 @@ + case "$1" in + start) + if [ -z "`ps -C xenconsoled -o pid=`" ]; then +- echo "xencommons should be started first." ++ printhl "xencommons should be started first." + exit 1 + fi + # mkdir shouldn't be needed as most distros have this already created. Default to using subsys. + # See docs/misc/distro_mapping.txt +- mkdir -p /var/lock +- if [ -d /var/lock/subsys ] ; then +- touch /var/lock/subsys/xend ++ if [ -d /run/lock/subsys ] ; then ++ touch /run/lock/subsys/xend + else +- touch /var/lock/xend ++ touch /run/lock/xend + fi ++ stat_busy "Starting xend" + xend start + await_daemons_up ++ stat_done ++ add_daemon xend + ;; ++ ++ + stop) ++ stat_busy "Stopping xend" + xend stop +- rm -f /var/lock/subsys/xend /var/lock/xend ++ rm -f /run/lock/xend /var/lock/xend ++ stat_done ++ rm_daemon xend + ;; + status) + xend status +@@ -62,8 +73,10 @@ + xend reload + ;; + restart|force-reload) ++ stat_busy "Restarting xend" + xend restart + await_daemons_up ++ stat_done + ;; + *) + # do not advertise unreasonable commands that there is no reason +diff -Naur orig.xen-4.1.1//tools/hotplug/Linux/init.d/xendomains xen-4.1.1//tools/hotplug/Linux/init.d/xendomains +--- orig.xen-4.1.1//tools/hotplug/Linux/init.d/xendomains 2011-07-03 03:08:44.953747064 -0700 ++++ xen-4.1.1//tools/hotplug/Linux/init.d/xendomains 2011-07-05 13:46:36.208222760 -0700 +@@ -26,6 +26,9 @@ + # Description: Start / stop domains automatically when domain 0 + # boots / shuts down. + ### END INIT INFO ++. /etc/rc.conf ++. /etc/rc.d/functions ++ + + CMD=xm + $CMD list &> /dev/null +@@ -46,93 +49,52 @@ + exit 0 + fi + +-# See docs/misc/distro_mapping.txt +-if [ -d /var/lock/subsys ]; then +- LOCKFILE=/var/lock/subsys/xendomains +-else +- LOCKFILE=/var/lock/xendomains +-fi +- +-if [ -d /etc/sysconfig ]; then +- XENDOM_CONFIG=/etc/sysconfig/xendomains +-else +- XENDOM_CONFIG=/etc/default/xendomains +-fi ++LOCKFILE=/run/lock/xendomains ++XENDOM_CONFIG=/etc/default/xendomains + +-test -r $XENDOM_CONFIG || { echo "$XENDOM_CONFIG not existing"; ++test -r $XENDOM_CONFIG || { ++ printhl "$XENDOM_CONFIG not existing"; + if [ "$1" = "stop" ]; then exit 0; + else exit 6; fi; } + + . $XENDOM_CONFIG + +-# Use the SUSE rc_ init script functions; +-# emulate them on LSB, RH and other systems +-if test -e /etc/rc.status; then +- # SUSE rc script library +- . /etc/rc.status +-else +- _cmd=$1 +- declare -a _SMSG +- if test "${_cmd}" = "status"; then ++_cmd=$1 ++declare -a _SMSG ++if test "${_cmd}" = "status"; then + _SMSG=(running dead dead unused unknown) + _RC_UNUSED=3 +- else ++else + _SMSG=(done failed failed missed failed skipped unused failed failed) + _RC_UNUSED=6 +- fi +- if test -e /etc/init.d/functions; then +- # REDHAT +- . /etc/init.d/functions +- echo_rc() +- { +- #echo -n " [${_SMSG[${_RC_RV}]}] " +- if test ${_RC_RV} = 0; then +- success " [${_SMSG[${_RC_RV}]}] " +- else +- failure " [${_SMSG[${_RC_RV}]}] " +- fi +- } +- elif test -e /lib/lsb/init-functions; then +- # LSB +- . /lib/lsb/init-functions +- if alias log_success_msg >/dev/null 2>/dev/null; then +- echo_rc() +- { +- echo " [${_SMSG[${_RC_RV}]}] " +- } +- else +- echo_rc() +- { +- if test ${_RC_RV} = 0; then +- log_success_msg " [${_SMSG[${_RC_RV}]}] " +- else +- log_failure_msg " [${_SMSG[${_RC_RV}]}] " +- fi +- } +- fi +- else +- # emulate it +- echo_rc() +- { +- echo " [${_SMSG[${_RC_RV}]}] " +- } +- fi +- rc_reset() { _RC_RV=0; } +- rc_failed() +- { ++fi ++ ++ ++ ++echo_rc() { ++ echo ++ printhl "Return Status: ${_SMSG[${_RC_RV}]}" ++} ++ ++ ++rc_reset() { _RC_RV=0; } ++ ++ ++rc_failed() { + if test -z "$1"; then +- _RC_RV=1; ++ _RC_RV=1; + elif test "$1" != "0"; then +- _RC_RV=$1; +- fi ++ _RC_RV=$1; ++ fi + return ${_RC_RV} +- } +- rc_check() +- { ++} ++ ++rc_check() { + return rc_failed $? +- } +- rc_status() +- { ++} ++ ++ ++rc_status() { + rc_failed $? + if test "$1" = "-r"; then _RC_RV=0; shift; fi + if test "$1" = "-s"; then rc_failed 5; echo_rc; rc_failed 3; shift; fi +@@ -140,26 +102,24 @@ + if test "$1" = "-v"; then echo_rc; shift; fi + if test "$1" = "-r"; then _RC_RV=0; shift; fi + return ${_RC_RV} +- } +- rc_exit() { exit ${_RC_RV}; } +- rc_active() +- { ++} ++ ++ ++rc_exit() { exit ${_RC_RV}; } ++ ++ ++rc_active() { + if test -z "$RUNLEVEL"; then read RUNLEVEL REST < <(/sbin/runlevel); fi + if test -e /etc/init.d/S[0-9][0-9]${1}; then return 0; fi + return 1 +- } +-fi ++} + +-if ! which usleep >&/dev/null +-then +- usleep() +- { +- if [ -n "$1" ] +- then +- sleep $(( $1 / 1000000 )) +- fi +- } +-fi ++usleep() { ++ if [ -n "$1" ] ++ then ++ sleep $(( $1 / 1000000 )) ++ fi ++} + + # Reset status of this service + rc_reset +@@ -235,10 +195,12 @@ + start() + { + if [ -f $LOCKFILE ]; then +- echo -e "xendomains already running (lockfile exists)" ++ stat_busy "xendomains already running (lockfile exists)" ++ stat_fail + return; + fi + ++ printhl "Starting Xen Domains" + saved_domains=" " + if [ "$XENDOMAINS_RESTORE" = "true" ] && + contains_something "$XENDOMAINS_SAVE" +@@ -299,6 +261,7 @@ + fi + done + fi ++ add_daemon xendomains + } + + all_zombies() +@@ -352,7 +315,7 @@ + if test "$XENDOMAINS_AUTO_ONLY" = "true"; then + rdnames + fi +- echo -n "Shutting down Xen domains:" ++ printhl "Shutting down Xen domains" + name=;id= + while read LN; do + parseln "$LN" || continue +@@ -465,6 +428,7 @@ + rm -f $LOCKFILE + + exec 2>&3 ++ rm_daemon xendomains + } + + check_domain_up() +diff -Naur orig.xen-4.1.1//tools/hotplug/Linux/init.d/xen-watchdog xen-4.1.1//tools/hotplug/Linux/init.d/xen-watchdog +--- orig.xen-4.1.1//tools/hotplug/Linux/init.d/xen-watchdog 2011-07-03 03:08:44.957080397 -0700 ++++ xen-4.1.1//tools/hotplug/Linux/init.d/xen-watchdog 2011-07-05 13:20:22.515289867 -0700 +@@ -17,49 +17,32 @@ + ### END INIT INFO + # + ++. /etc/rc.conf ++. /etc/rc.d/functions ++ + DAEMON=/usr/sbin/xenwatchdogd + base=$(basename $DAEMON) ++initname="xen-watchdog" + +-# Source function library. +-if [ -e /etc/init.d/functions ] ; then +- . /etc/init.d/functions +-elif [ -e /lib/lsb/init-functions ] ; then +- . /lib/lsb/init-functions +- success () { +- log_success_msg $* +- } +- failure () { +- log_failure_msg $* +- } +-else +- success () { +- echo $* +- } +- failure () { +- echo $* +- } +-fi + + start() { + local r +- echo -n $"Starting domain watchdog daemon: " ++ stat_busy "Starting domain watchdog daemon" + + $DAEMON 30 15 + r=$? +- [ "$r" -eq 0 ] && success $"$base startup" || failure $"$base startup" +- echo ++ [ "$r" -eq 0 ] && stat_done ; add_daemon $initname || stat_fail + + return $r + } + + stop() { + local r +- echo -n $"Stopping domain watchdog daemon: " ++ stat_busy "Stopping domain watchdog daemon" + + killall -USR1 $base 2>/dev/null + r=$? +- [ "$r" -eq 0 ] && success $"$base stop" || failure $"$base stop" +- echo ++ [ "$r" -eq 0 ] && stat_done ; rm_daemon $initname || stat_fail + + return $r + } diff --git a/kernels/xen/xen.patch b/kernels/xen/xen.patch new file mode 100644 index 000000000..8b1b5585d --- /dev/null +++ b/kernels/xen/xen.patch @@ -0,0 +1,21 @@ +--- xen-4.0.1.orig/Config.mk 2010-08-25 12:22:44.000000000 +0200 ++++ xen-4.0.1/Config.mk 2010-11-02 23:38:11.575000000 +0100 +@@ -187,4 +187,4 @@ + CONFIG_MINITERM ?= n + CONFIG_LOMOUNT ?= n + +--include $(XEN_ROOT)/.config ++#-include $(XEN_ROOT)/.config + +--- xen-4.0.1/Config.mk.orig 2010-08-25 11:22:44.000000000 +0100 ++++ xen-4.0.1/Config.mk 2011-01-29 17:40:43.000000000 +0000 +@@ -135,6 +135,8 @@ + + LDFLAGS += $(foreach i, $(EXTRA_LIB), -L$(i)) + CFLAGS += $(foreach i, $(EXTRA_INCLUDES), -I$(i)) ++# temporary compile fix for rawhide ++CFLAGS += -Wunused-but-set-variable -Wno-error=unused-but-set-variable -Wuninitialized -Wno-error=uninitialized + + EMBEDDED_EXTRA_CFLAGS := -nopie -fno-stack-protector -fno-stack-protector-all + EMBEDDED_EXTRA_CFLAGS += -fno-exceptions + -- cgit v1.2.3-2-g168b