# HG changeset patch # User Christopher Rogers # Date 1292363109 0 # Node ID 1bea914df3b9a06ddb7eed14bdd2b28f471b3289 # Parent 13e4d4e6fcc194a9e044fdde4b5d45c6b5bcbde3 Add squashfs+xz to kernel. This allows for greater compressing then lzma and it will work without cause a kernel opps. As long as the custom code for freeing lzma initramfs stays with lzma initramfs. diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/receipt --- a/linux/receipt Tue Dec 14 21:34:46 2010 +0000 +++ b/linux/receipt Tue Dec 14 21:45:09 2010 +0000 @@ -26,13 +26,13 @@ TARBALL=$SOURCES_REPOSITORY/$AUFSDIR.tar.gz if [ -f $TARBALL ]; then tar xzf $TARBALL - cd $AUFSDIR && git checkout origin/aufs2 + cd $AUFSDIR && git checkout origin/aufs2.1-36 cd $WOK/$PACKAGE else # Aufs2 from git repository git clone http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-standalone.git $AUFSDIR tar czf $TARBALL $AUFSDIR - cd $AUFSDIR && git checkout origin/aufs2 + cd $AUFSDIR && git checkout origin/aufs2.1-36 cd $WOK/$PACKAGE fi cp -a $AUFSDIR/Documentation $AUFSDIR/fs $AUFSDIR/include $src @@ -64,8 +64,11 @@ $PACKAGE-freeinitrd-$VERSION.u aufs2-base.patch aufs2-standalone.patch -aufs2-module-2.6.36.patch -aufs2-2.6.36-fix.patch +001-squashfs-decompressors-add-xz-decompressor-module.patch +002-squashfs-decompressors-add-boot-time-xz-support.patch +003-squashfs-x86-support-xz-compressed-kernel.patch +004-squashfs-add-xz-compression-support.patch +005-squashfs-add-xz-compression-configuration-option.patch EOT make mrproper cd Documentation/lguest diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/001-squashfs-decompressors-add-xz-decompressor-module.patch --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/linux/stuff/001-squashfs-decompressors-add-xz-decompressor-module.patch Tue Dec 14 21:45:09 2010 +0000 @@ -0,0 +1,3934 @@ +From: Lasse Collin +Date: Thu, 2 Dec 2010 19:14:19 +0000 (+0200) +Subject: Decompressors: Add XZ decompressor module +X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Fpkl%2Fsquashfs-xz.git;a=commitdiff_plain;h=3dbc3fe7878e53b43064a12d4ab31ca4c18ce85f + +Decompressors: Add XZ decompressor module + +In userspace, the .lzma format has become mostly a legacy +file format that got superseded by the .xz format. Similarly, +LZMA Utils was superseded by XZ Utils. + +These patches add support for XZ decompression into +the kernel. Most of the code is as is from XZ Embedded +. It was written for +the Linux kernel but is usable in other projects too. + +Advantages of XZ over the current LZMA code in the kernel: + - Nice API that can be used by other kernel modules; it's + not limited to kernel, initramfs, and initrd decompression. + - Integrity check support (CRC32) + - BCJ filters improve compression of executable code on + certain architectures. These together with LZMA2 can + produce a few percent smaller kernel or Squashfs images + than plain LZMA without making the decompression slower. + +This patch: Add the main decompression code (xz_dec), testing +module (xz_dec_test), wrapper script (xz_wrap.sh) for the xz +command line tool, and documentation. The xz_dec module is +enough to have a usable XZ decompressor e.g. for Squashfs. + +Signed-off-by: Lasse Collin +--- + +diff --git a/Documentation/xz.txt b/Documentation/xz.txt +new file mode 100644 +index 0000000..68329ac +--- /dev/null ++++ b/Documentation/xz.txt +@@ -0,0 +1,122 @@ ++ ++XZ data compression in Linux ++============================ ++ ++Introduction ++ ++ XZ is a general purpose data compression format with high compression ++ ratio and relatively fast decompression. The primary compression ++ algorithm (filter) is LZMA2. Additional filters can be used to improve ++ compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters ++ improve compression ratio of executable data. ++ ++ The XZ decompressor in Linux is called XZ Embedded. It supports ++ the LZMA2 filter and optionally also BCJ filters. CRC32 is supported ++ for integrity checking. The home page of XZ Embedded is at ++ , where you can find the ++ latest version and also information about using the code outside ++ the Linux kernel. ++ ++ For userspace, XZ Utils provide a zlib-like compression library ++ and a gzip-like command line tool. XZ Utils can be downloaded from ++ . ++ ++XZ related components in the kernel ++ ++ The xz_dec module provides XZ decompressor with single-call (buffer ++ to buffer) and multi-call (stateful) APIs. The usage of the xz_dec ++ module is documented in include/linux/xz.h. ++ ++ The xz_dec_test module is for testing xz_dec. xz_dec_test is not ++ useful unless you are hacking the XZ decompressor. xz_dec_test ++ allocates a char device major dynamically to which one can write ++ .xz files from userspace. The decompressed output is thrown away. ++ Keep an eye on dmesg to see diagnostics printed by xz_dec_test. ++ See the xz_dec_test source code for the details. ++ ++ For decompressing the kernel image, initramfs, and initrd, there ++ is a wrapper function in lib/decompress_unxz.c. Its API is the ++ same as in other decompress_*.c files, which is defined in ++ include/linux/decompress/generic.h. ++ ++ scripts/xz_wrap.sh is a wrapper for the xz command line tool found ++ from XZ Utils. The wrapper sets compression options to values suitable ++ for compressing the kernel image. ++ ++ For kernel makefiles, two commands are provided for use with ++ $(call if_needed). The kernel image should be compressed with ++ $(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2 ++ dictionary. It will also append a four-byte trailer containing the ++ uncompressed size of the file, which is needed by the boot code. ++ Other things should be compressed with $(call if_needed,xzmisc) ++ which will use no BCJ filter and 1 MiB LZMA2 dictionary. ++ ++Notes on compression options ++ ++ Since the XZ Embedded supports only streams with no integrity check or ++ CRC32, make sure that you don't use some other integrity check type ++ when encoding files that are supposed to be decoded by the kernel. With ++ liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32 ++ when encoding. With the xz command line tool, use --check=none or ++ --check=crc32. ++ ++ Using CRC32 is strongly recommended unless there is some other layer ++ which will verify the integrity of the uncompressed data anyway. ++ Double checking the integrity would probably be waste of CPU cycles. ++ Note that the headers will always have a CRC32 which will be validated ++ by the decoder; you can only change the integrity check type (or ++ disable it) for the actual uncompressed data. ++ ++ In userspace, LZMA2 is typically used with dictionary sizes of several ++ megabytes. The decoder needs to have the dictionary in RAM, thus big ++ dictionaries cannot be used for files that are intended to be decoded ++ by the kernel. 1 MiB is probably the maximum reasonable dictionary ++ size for in-kernel use (maybe more is OK for initramfs). The presets ++ in XZ Utils may not be optimal when creating files for the kernel, ++ so don't hesitate to use custom settings. Example: ++ ++ xz --check=crc32 --lzma2=dict=512KiB inputfile ++ ++ An exception to above dictionary size limitation is when the decoder ++ is used in single-call mode. Decompressing the kernel itself is an ++ example of this situation. In single-call mode, the memory usage ++ doesn't depend on the dictionary size, and it is perfectly fine to ++ use a big dictionary: for maximum compression, the dictionary should ++ be at least as big as the uncompressed data itself. ++ ++Future plans ++ ++ Creating a limited XZ encoder may be considered if people think it is ++ useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at ++ the fastest settings, so it isn't clear if LZMA2 encoder is wanted ++ into the kernel. ++ ++ Support for limited random-access reading is planned for the ++ decompression code. I don't know if it could have any use in the ++ kernel, but I know that it would be useful in some embedded projects ++ outside the Linux kernel. ++ ++Conformance to the .xz file format specification ++ ++ There are a couple of corner cases where things have been simplified ++ at expense of detecting errors as early as possible. These should not ++ matter in practice all, since they don't cause security issues. But ++ it is good to know this if testing the code e.g. with the test files ++ from XZ Utils. ++ ++Reporting bugs ++ ++ Before reporting a bug, please check that it's not fixed already ++ at upstream. See to get the ++ latest code. ++ ++ Report bugs to or visit #tukaani on ++ Freenode and talk to Larhzu. I don't actively read LKML or other ++ kernel-related mailing lists, so if there's something I should know, ++ you should email to me personally or use IRC. ++ ++ Don't bother Igor Pavlov with questions about the XZ implementation ++ in the kernel or about XZ Utils. While these two implementations ++ include essential code that is directly based on Igor Pavlov's code, ++ these implementations aren't maintained nor supported by him. ++ +diff --git a/include/linux/xz.h b/include/linux/xz.h +new file mode 100644 +index 0000000..64cffa6 +--- /dev/null ++++ b/include/linux/xz.h +@@ -0,0 +1,264 @@ ++/* ++ * XZ decompressor ++ * ++ * 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_H ++#define XZ_H ++ ++#ifdef __KERNEL__ ++# include ++# include ++#else ++# include ++# include ++#endif ++ ++/* In Linux, this is used to make extern functions static when needed. */ ++#ifndef XZ_EXTERN ++# define XZ_EXTERN extern ++#endif ++ ++/** ++ * 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; ++ ++/** ++ * xz_dec_init() - Allocate and initialize a XZ decoder state ++ * @mode: Operation mode ++ * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for ++ * multi-call decoding. This is ignored in single-call mode ++ * (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes ++ * or 2^n + 2^(n-1) bytes (the latter sizes are less common ++ * in practice), so other values for dict_max don't make sense. ++ * In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB, ++ * 512 KiB, and 1 MiB are probably the only reasonable values, ++ * except for kernel and initramfs images where a bigger ++ * dictionary can be fine and useful. ++ * ++ * Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at ++ * once. The caller must provide enough output space or the decoding will ++ * fail. The output space is used as the dictionary buffer, which is why ++ * there is no need to allocate the dictionary as part of the decoder's ++ * internal state. ++ * ++ * Because the output buffer is used as the workspace, streams encoded using ++ * a big dictionary are not a problem in single-call mode. It is enough that ++ * the output buffer is big enough to hold the actual uncompressed data; it ++ * can be smaller than the dictionary size stored in the stream headers. ++ * ++ * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes ++ * of memory is preallocated for the LZMA2 dictionary. This way there is no ++ * risk that xz_dec_run() could run out of memory, since xz_dec_run() will ++ * never allocate any memory. Instead, if the preallocated dictionary is too ++ * small for decoding the given input stream, xz_dec_run() will return ++ * XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be ++ * decoded to avoid allocating excessive amount of memory for the dictionary. ++ * ++ * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC): ++ * dict_max specifies the maximum allowed dictionary size that xz_dec_run() ++ * may allocate once it has parsed the dictionary size from the stream ++ * headers. This way excessive allocations can be avoided while still ++ * limiting the maximum memory usage to a sane value to prevent running the ++ * system out of memory when decompressing streams from untrusted sources. ++ * ++ * On success, xz_dec_init() returns a pointer to struct xz_dec, which is ++ * ready to be used with xz_dec_run(). If memory allocation fails, ++ * xz_dec_init() returns NULL. ++ */ ++XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); ++ ++/** ++ * xz_dec_run() - Run the XZ decoder ++ * @s: Decoder state allocated using xz_dec_init() ++ * @b: Input and output buffers ++ * ++ * The possible return values depend on build options and operation mode. ++ * See enum xz_ret for details. ++ * ++ * Note that if an error occurs in single-call mode (return value is not ++ * XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the ++ * contents of the output buffer from b->out[b->out_pos] onward are ++ * undefined. This is true even after XZ_BUF_ERROR, because with some filter ++ * chains, there may be a second pass over the output buffer, and this pass ++ * cannot be properly done if the output buffer is truncated. Thus, you ++ * cannot give the single-call decoder a too small buffer and then expect to ++ * get that amount valid data from the beginning of the stream. You must use ++ * the multi-call decoder if you don't want to uncompress the whole stream. ++ */ ++XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); ++ ++/** ++ * xz_dec_reset() - Reset an already allocated decoder state ++ * @s: Decoder state allocated using xz_dec_init() ++ * ++ * This function can be used to reset the multi-call decoder state without ++ * freeing and reallocating memory with xz_dec_end() and xz_dec_init(). ++ * ++ * In single-call mode, xz_dec_reset() is always called in the beginning of ++ * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in ++ * multi-call mode. ++ */ ++XZ_EXTERN void xz_dec_reset(struct xz_dec *s); ++ ++/** ++ * xz_dec_end() - Free the memory allocated for the decoder state ++ * @s: Decoder state allocated using xz_dec_init(). If s is NULL, ++ * this function does nothing. ++ */ ++XZ_EXTERN void xz_dec_end(struct xz_dec *s); ++ ++/* ++ * Standalone build (userspace build or in-kernel build for boot time use) ++ * needs a CRC32 implementation. For normal in-kernel use, kernel's own ++ * CRC32 module is used instead, and users of this module don't need to ++ * care about the functions below. ++ */ ++#ifndef XZ_INTERNAL_CRC32 ++# ifdef __KERNEL__ ++# define XZ_INTERNAL_CRC32 0 ++# else ++# define XZ_INTERNAL_CRC32 1 ++# endif ++#endif ++ ++#if XZ_INTERNAL_CRC32 ++/* ++ * This must be called before any other xz_* function to initialize ++ * the CRC32 lookup table. ++ */ ++XZ_EXTERN void xz_crc32_init(void); ++ ++/* ++ * Update CRC32 value using the polynomial from IEEE-802.3. To start a new ++ * calculation, the third argument must be zero. To continue the calculation, ++ * the previously returned value is passed as the third argument. ++ */ ++XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); ++#endif ++#endif +diff --git a/lib/Kconfig b/lib/Kconfig +index fa9bf2c..6090314 100644 +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -106,6 +106,8 @@ config LZO_COMPRESS + config LZO_DECOMPRESS + tristate + ++source "lib/xz/Kconfig" ++ + # + # These all provide a common interface (hence the apparent duplication with + # ZLIB_INFLATE; DECOMPRESS_GZIP is just a wrapper.) +diff --git a/lib/Makefile b/lib/Makefile +index e6a3763..f2f98dd 100644 +--- a/lib/Makefile ++++ b/lib/Makefile +@@ -69,6 +69,7 @@ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/ + obj-$(CONFIG_REED_SOLOMON) += reed_solomon/ + obj-$(CONFIG_LZO_COMPRESS) += lzo/ + obj-$(CONFIG_LZO_DECOMPRESS) += lzo/ ++obj-$(CONFIG_XZ_DEC) += xz/ + obj-$(CONFIG_RAID6_PQ) += raid6/ + + lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o +diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig +new file mode 100644 +index 0000000..e3b6e18 +--- /dev/null ++++ b/lib/xz/Kconfig +@@ -0,0 +1,59 @@ ++config XZ_DEC ++ tristate "XZ decompression support" ++ select CRC32 ++ help ++ LZMA2 compression algorithm and BCJ filters are supported using ++ the .xz file format as the container. For integrity checking, ++ CRC32 is supported. See Documentation/xz.txt for more information. ++ ++config XZ_DEC_X86 ++ bool "x86 BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_POWERPC ++ bool "PowerPC BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_IA64 ++ bool "IA-64 BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_ARM ++ bool "ARM BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_ARMTHUMB ++ bool "ARM-Thumb BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_SPARC ++ bool "SPARC BCJ filter decoder" if EMBEDDED ++ default y ++ depends on XZ_DEC ++ select XZ_DEC_BCJ ++ ++config XZ_DEC_BCJ ++ bool ++ default n ++ ++config XZ_DEC_TEST ++ tristate "XZ decompressor tester" ++ default n ++ depends on XZ_DEC ++ help ++ This allows passing .xz files to the in-kernel XZ decoder via ++ a character special file. It calculates CRC32 of the decompressed ++ data and writes diagnostics to the system log. ++ ++ Unless you are developing the XZ decoder, you don't need this ++ and should say N. +diff --git a/lib/xz/Makefile b/lib/xz/Makefile +new file mode 100644 +index 0000000..a7fa769 +--- /dev/null ++++ b/lib/xz/Makefile +@@ -0,0 +1,5 @@ ++obj-$(CONFIG_XZ_DEC) += xz_dec.o ++xz_dec-y := xz_dec_syms.o xz_dec_stream.o xz_dec_lzma2.o ++xz_dec-$(CONFIG_XZ_DEC_BCJ) += xz_dec_bcj.o ++ ++obj-$(CONFIG_XZ_DEC_TEST) += xz_dec_test.o +diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c +new file mode 100644 +index 0000000..34532d1 +--- /dev/null ++++ b/lib/xz/xz_crc32.c +@@ -0,0 +1,59 @@ ++/* ++ * 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 "xz_private.h" ++ ++/* ++ * STATIC_RW_DATA is used in the pre-boot environment on some architectures. ++ * See for details. ++ */ ++#ifndef STATIC_RW_DATA ++# define STATIC_RW_DATA static ++#endif ++ ++STATIC_RW_DATA uint32_t xz_crc32_table[256]; ++ ++XZ_EXTERN void 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 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/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c +new file mode 100644 +index 0000000..e51e255 +--- /dev/null ++++ b/lib/xz/xz_dec_bcj.c +@@ -0,0 +1,561 @@ ++/* ++ * 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 "xz_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 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 bcj_x86_test_msbyte(uint8_t b) ++{ ++ return b == 0x00 || b == 0xFF; ++} ++ ++static size_t bcj_x86(struct xz_dec_bcj *s, uint8_t *buf, size_t size) ++{ ++ static const bool mask_to_allowed_status[8] ++ = { true, true, true, false, true, false, false, false }; ++ ++ static const uint8_t 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 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 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 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 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 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 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 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 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 *xz_dec_bcj_create(bool single_call) ++{ ++ struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL); ++ if (s != NULL) ++ s->single_call = single_call; ++ ++ return s; ++} ++ ++XZ_EXTERN enum xz_ret 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/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c +new file mode 100644 +index 0000000..ea5fa4f +--- /dev/null ++++ b/lib/xz/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 "xz_private.h" ++#include "xz_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 need_dict_reset; ++ ++ /* ++ * True if new LZMA properties are needed. This is false ++ * before the first LZMA chunk. ++ */ ++ bool 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 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 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 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 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 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 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 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 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 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 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 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 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 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 *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 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 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 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 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 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 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 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 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 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 *xz_dec_lzma2_create(enum xz_mode mode, ++ uint32_t dict_max) ++{ ++ struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL); ++ if (s == NULL) ++ return NULL; ++ ++ s->dict.mode = mode; ++ s->dict.size_max = dict_max; ++ ++ if (DEC_IS_PREALLOC(mode)) { ++ s->dict.buf = vmalloc(dict_max); ++ if (s->dict.buf == NULL) { ++ kfree(s); ++ return NULL; ++ } ++ } else if (DEC_IS_DYNALLOC(mode)) { ++ s->dict.buf = NULL; ++ s->dict.allocated = 0; ++ } ++ ++ return s; ++} ++ ++XZ_EXTERN enum xz_ret 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) { ++ vfree(s->dict.buf); ++ s->dict.buf = vmalloc(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 xz_dec_lzma2_end(struct xz_dec_lzma2 *s) ++{ ++ if (DEC_IS_MULTI(s->dict.mode)) ++ vfree(s->dict.buf); ++ ++ kfree(s); ++} +diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c +new file mode 100644 +index 0000000..ac809b1 +--- /dev/null ++++ b/lib/xz/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 "xz_private.h" ++#include "xz_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 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 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 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 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 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 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 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 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 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 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 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 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 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_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 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 *xz_dec_init(enum xz_mode mode, uint32_t dict_max) ++{ ++ struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); ++ 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 ++ kfree(s); ++ return NULL; ++} ++ ++XZ_EXTERN void 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_EXTERN void 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 ++ kfree(s); ++ } ++} +diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c +new file mode 100644 +index 0000000..32eb3c0 +--- /dev/null ++++ b/lib/xz/xz_dec_syms.c +@@ -0,0 +1,26 @@ ++/* ++ * XZ decoder module information ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#include ++#include ++ ++EXPORT_SYMBOL(xz_dec_init); ++EXPORT_SYMBOL(xz_dec_reset); ++EXPORT_SYMBOL(xz_dec_run); ++EXPORT_SYMBOL(xz_dec_end); ++ ++MODULE_DESCRIPTION("XZ decompressor"); ++MODULE_VERSION("1.0"); ++MODULE_AUTHOR("Lasse Collin and Igor Pavlov"); ++ ++/* ++ * This code is in the public domain, but in Linux it's simplest to just ++ * say it's GPL and consider the authors as the copyright holders. ++ */ ++MODULE_LICENSE("GPL"); +diff --git a/lib/xz/xz_dec_test.c b/lib/xz/xz_dec_test.c +new file mode 100644 +index 0000000..da28a19 +--- /dev/null ++++ b/lib/xz/xz_dec_test.c +@@ -0,0 +1,220 @@ ++/* ++ * XZ decoder tester ++ * ++ * Author: Lasse Collin ++ * ++ * This file has been put into the public domain. ++ * You can do whatever you want with this file. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++/* Maximum supported dictionary size */ ++#define DICT_MAX (1 << 20) ++ ++/* Device name to pass to register_chrdev(). */ ++#define DEVICE_NAME "xz_dec_test" ++ ++/* Dynamically allocated device major number */ ++static int device_major; ++ ++/* ++ * We reuse the same decoder state, and thus can decode only one ++ * file at a time. ++ */ ++static bool device_is_open; ++ ++/* XZ decoder state */ ++static struct xz_dec *state; ++ ++/* ++ * Return value of xz_dec_run(). We need to avoid calling xz_dec_run() after ++ * it has returned XZ_STREAM_END, so we make this static. ++ */ ++static enum xz_ret ret; ++ ++/* ++ * Input and output buffers. The input buffer is used as a temporary safe ++ * place for the data coming from the userspace. ++ */ ++static uint8_t buffer_in[1024]; ++static uint8_t buffer_out[1024]; ++ ++/* ++ * Structure to pass the input and output buffers to the XZ decoder. ++ * A few of the fields are never modified so we initialize them here. ++ */ ++static struct xz_buf buffers = { ++ .in = buffer_in, ++ .out = buffer_out, ++ .out_size = sizeof(buffer_out) ++}; ++ ++/* ++ * CRC32 of uncompressed data. This is used to give the user a simple way ++ * to check that the decoder produces correct output. ++ */ ++static uint32_t crc; ++ ++static int xz_dec_test_open(struct inode *i, struct file *f) ++{ ++ if (device_is_open) ++ return -EBUSY; ++ ++ device_is_open = true; ++ ++ xz_dec_reset(state); ++ ret = XZ_OK; ++ crc = 0xFFFFFFFF; ++ ++ buffers.in_pos = 0; ++ buffers.in_size = 0; ++ buffers.out_pos = 0; ++ ++ printk(KERN_INFO DEVICE_NAME ": opened\n"); ++ return 0; ++} ++ ++static int xz_dec_test_release(struct inode *i, struct file *f) ++{ ++ device_is_open = false; ++ ++ if (ret == XZ_OK) ++ printk(KERN_INFO DEVICE_NAME ": input was truncated\n"); ++ ++ printk(KERN_INFO DEVICE_NAME ": closed\n"); ++ return 0; ++} ++ ++/* ++ * Decode the data given to us from the userspace. CRC32 of the uncompressed ++ * data is calculated and is printed at the end of successful decoding. The ++ * uncompressed data isn't stored anywhere for further use. ++ * ++ * The .xz file must have exactly one Stream and no Stream Padding. The data ++ * after the first Stream is considered to be garbage. ++ */ ++static ssize_t xz_dec_test_write(struct file *file, const char __user *buf, ++ size_t size, loff_t *pos) ++{ ++ size_t remaining; ++ ++ if (ret != XZ_OK) { ++ if (size > 0) ++ printk(KERN_INFO DEVICE_NAME ": %zu bytes of " ++ "garbage at the end of the file\n", ++ size); ++ ++ return -ENOSPC; ++ } ++ ++ printk(KERN_INFO DEVICE_NAME ": decoding %zu bytes of input\n", ++ size); ++ ++ remaining = size; ++ while ((remaining > 0 || buffers.out_pos == buffers.out_size) ++ && ret == XZ_OK) { ++ if (buffers.in_pos == buffers.in_size) { ++ buffers.in_pos = 0; ++ buffers.in_size = min(remaining, sizeof(buffer_in)); ++ if (copy_from_user(buffer_in, buf, buffers.in_size)) ++ return -EFAULT; ++ ++ buf += buffers.in_size; ++ remaining -= buffers.in_size; ++ } ++ ++ buffers.out_pos = 0; ++ ret = xz_dec_run(state, &buffers); ++ crc = crc32(crc, buffer_out, buffers.out_pos); ++ } ++ ++ switch (ret) { ++ case XZ_OK: ++ printk(KERN_INFO DEVICE_NAME ": XZ_OK\n"); ++ return size; ++ ++ case XZ_STREAM_END: ++ printk(KERN_INFO DEVICE_NAME ": XZ_STREAM_END, " ++ "CRC32 = 0x%08X\n", ~crc); ++ return size - remaining - (buffers.in_size - buffers.in_pos); ++ ++ case XZ_MEMLIMIT_ERROR: ++ printk(KERN_INFO DEVICE_NAME ": XZ_MEMLIMIT_ERROR\n"); ++ break; ++ ++ case XZ_FORMAT_ERROR: ++ printk(KERN_INFO DEVICE_NAME ": XZ_FORMAT_ERROR\n"); ++ break; ++ ++ case XZ_OPTIONS_ERROR: ++ printk(KERN_INFO DEVICE_NAME ": XZ_OPTIONS_ERROR\n"); ++ break; ++ ++ case XZ_DATA_ERROR: ++ printk(KERN_INFO DEVICE_NAME ": XZ_DATA_ERROR\n"); ++ break; ++ ++ case XZ_BUF_ERROR: ++ printk(KERN_INFO DEVICE_NAME ": XZ_BUF_ERROR\n"); ++ break; ++ ++ default: ++ printk(KERN_INFO DEVICE_NAME ": Bug detected!\n"); ++ break; ++ } ++ ++ return -EIO; ++} ++ ++/* Allocate the XZ decoder state and register the character device. */ ++static int __init xz_dec_test_init(void) ++{ ++ static const struct file_operations fileops = { ++ .owner = THIS_MODULE, ++ .open = &xz_dec_test_open, ++ .release = &xz_dec_test_release, ++ .write = &xz_dec_test_write ++ }; ++ ++ state = xz_dec_init(XZ_PREALLOC, DICT_MAX); ++ if (state == NULL) ++ return -ENOMEM; ++ ++ device_major = register_chrdev(0, DEVICE_NAME, &fileops); ++ if (device_major < 0) { ++ xz_dec_end(state); ++ return device_major; ++ } ++ ++ printk(KERN_INFO DEVICE_NAME ": module loaded\n"); ++ printk(KERN_INFO DEVICE_NAME ": Create a device node with " ++ "'mknod " DEVICE_NAME " c %d 0' and write .xz files " ++ "to it.\n", device_major); ++ return 0; ++} ++ ++static void __exit xz_dec_test_exit(void) ++{ ++ unregister_chrdev(device_major, DEVICE_NAME); ++ xz_dec_end(state); ++ printk(KERN_INFO DEVICE_NAME ": module unloaded\n"); ++} ++ ++module_init(xz_dec_test_init); ++module_exit(xz_dec_test_exit); ++ ++MODULE_DESCRIPTION("XZ decompressor tester"); ++MODULE_VERSION("1.0"); ++MODULE_AUTHOR("Lasse Collin "); ++ ++/* ++ * This code is in the public domain, but in Linux it's simplest to just ++ * say it's GPL and consider the authors as the copyright holders. ++ */ ++MODULE_LICENSE("GPL"); +diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h +new file mode 100644 +index 0000000..071d67b +--- /dev/null ++++ b/lib/xz/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 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 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 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 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 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 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/lib/xz/xz_private.h b/lib/xz/xz_private.h +new file mode 100644 +index 0000000..a65633e +--- /dev/null ++++ b/lib/xz/xz_private.h +@@ -0,0 +1,156 @@ ++/* ++ * 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 ++ ++#ifdef __KERNEL__ ++# include ++# include ++# include ++ /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ ++# ifndef XZ_PREBOOT ++# include ++# include ++# include ++# ifdef CONFIG_XZ_DEC_X86 ++# define XZ_DEC_X86 ++# endif ++# ifdef CONFIG_XZ_DEC_POWERPC ++# define XZ_DEC_POWERPC ++# endif ++# ifdef CONFIG_XZ_DEC_IA64 ++# define XZ_DEC_IA64 ++# endif ++# ifdef CONFIG_XZ_DEC_ARM ++# define XZ_DEC_ARM ++# endif ++# ifdef CONFIG_XZ_DEC_ARMTHUMB ++# define XZ_DEC_ARMTHUMB ++# endif ++# ifdef CONFIG_XZ_DEC_SPARC ++# define XZ_DEC_SPARC ++# endif ++# define memeq(a, b, size) (memcmp(a, b, size) == 0) ++# define memzero(buf, size) memset(buf, 0, size) ++# endif ++# define get_le32(p) le32_to_cpup((const uint32_t *)(p)) ++#else ++ /* ++ * For userspace builds, use a separate header to define the required ++ * macros and functions. This makes it easier to adapt the code into ++ * different environments and avoids clutter in the Linux kernel tree. ++ */ ++# include "xz_config.h" ++#endif ++ ++/* 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 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) kfree(s) ++#endif ++ ++#endif +diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h +new file mode 100644 +index 0000000..66cb5a7 +--- /dev/null ++++ b/lib/xz/xz_stream.h +@@ -0,0 +1,62 @@ ++/* ++ * 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 ++ ++#if defined(__KERNEL__) && !XZ_INTERNAL_CRC32 ++# include ++# undef crc32 ++# define xz_crc32(buf, size, crc) \ ++ (~crc32_le(~(uint32_t)(crc), buf, size)) ++#endif ++ ++/* ++ * 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/scripts/Makefile.lib b/scripts/Makefile.lib +index 54fd1b7..b862007 100644 +--- a/scripts/Makefile.lib ++++ b/scripts/Makefile.lib +@@ -246,6 +246,34 @@ cmd_lzo = (cat $(filter-out FORCE,$^) | \ + lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \ + (rm -f $@ ; false) + ++# XZ ++# --------------------------------------------------------------------------- ++# Use xzkern to compress the kernel image and xzmisc to compress other things. ++# ++# xzkern uses a big LZMA2 dictionary since it doesn't increase memory usage ++# of the kernel decompressor. A BCJ filter is used if it is available for ++# the target architecture. xzkern also appends uncompressed size of the data ++# using size_append. The .xz format has the size information available at ++# the end of the file too, but it's in more complex format and it's good to ++# avoid changing the part of the boot code that reads the uncompressed size. ++# Note that the bytes added by size_append will make the xz tool think that ++# the file is corrupt. This is expected. ++# ++# xzmisc doesn't use size_append, so it can be used to create normal .xz ++# files. xzmisc uses smaller LZMA2 dictionary than xzkern, because a very ++# big dictionary would increase the memory usage too much in the multi-call ++# decompression mode. A BCJ filter isn't used either. ++quiet_cmd_xzkern = XZKERN $@ ++cmd_xzkern = (cat $(filter-out FORCE,$^) | \ ++ sh $(srctree)/scripts/xz_wrap.sh && \ ++ $(call size_append, $(filter-out FORCE,$^))) > $@ || \ ++ (rm -f $@ ; false) ++ ++quiet_cmd_xzmisc = XZMISC $@ ++cmd_xzmisc = (cat $(filter-out FORCE,$^) | \ ++ xz --check=crc32 --lzma2=dict=1MiB) > $@ || \ ++ (rm -f $@ ; false) ++ + # misc stuff + # --------------------------------------------------------------------------- + quote:=" +diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh +new file mode 100644 +index 0000000..17a5798 +--- /dev/null ++++ b/scripts/xz_wrap.sh +@@ -0,0 +1,23 @@ ++#!/bin/sh ++# ++# This is a wrapper for xz to compress the kernel image using appropriate ++# compression options depending on the architecture. ++# ++# Author: Lasse Collin ++# ++# This file has been put into the public domain. ++# You can do whatever you want with this file. ++# ++ ++BCJ= ++LZMA2OPTS= ++ ++case $ARCH in ++ x86|x86_64) BCJ=--x86 ;; ++ powerpc) BCJ=--powerpc ;; ++ ia64) BCJ=--ia64; LZMA2OPTS=pb=4 ;; ++ arm) BCJ=--arm ;; ++ sparc) BCJ=--sparc ;; ++esac ++ ++exec xz --check=crc32 $BCJ --lzma2=$LZMA2OPTS,dict=32MiB diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/002-squashfs-decompressors-add-boot-time-xz-support.patch --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/linux/stuff/002-squashfs-decompressors-add-boot-time-xz-support.patch Tue Dec 14 21:45:09 2010 +0000 @@ -0,0 +1,638 @@ +From: Lasse Collin +Date: Thu, 2 Dec 2010 19:14:37 +0000 (+0200) +Subject: Decompressors: Add boot-time XZ support +X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Fpkl%2Fsquashfs-xz.git;a=commitdiff_plain;h=c64bc9a229b46db75d7761601dd8ca25385a7780 + +Decompressors: Add boot-time XZ support + +This implements the API defined in +which is used for kernel, initramfs, and initrd decompression. +This patch together with the first patch is enough for +XZ-compressed initramfs and initrd; XZ-compressed kernel will +need arch-specific changes. + +In contrast to other initramfs compression methods, support for +XZ-compressed initramfs is not enabled by default in usr/Kconfig. +This is primarily due to the Kconfig options of the xz_dec +module. It can be good to require that xz_dec is enabled +separately so the user can select only the BCJ filters he needs +when EMBEDDED=y. + +The buffering requirements described in decompress_unxz.c are +stricter than with gzip, so the relevant changes should be done +to the arch-specific code when adding support for XZ-compressed +kernel. Similarly, the heap size in arch-specific pre-boot code +may need to be increased (30 KiB is enough). + +The XZ decompressor needs memmove(), memeq() (memcmp() == 0), +and memzero() (memset(ptr, 0, size)), which aren't available in +all arch-specific pre-boot environments. I'm including simple +versions in decompress_unxz.c, but a cleaner solution would +naturally be nicer. + +Signed-off-by: Lasse Collin +--- + +diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h +new file mode 100644 +index 0000000..41728fc +--- /dev/null ++++ b/include/linux/decompress/unxz.h +@@ -0,0 +1,19 @@ ++/* ++ * 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. ++ */ ++ ++#ifndef DECOMPRESS_UNXZ_H ++#define DECOMPRESS_UNXZ_H ++ ++int unxz(unsigned char *in, int in_size, ++ int (*fill)(void *dest, unsigned int size), ++ int (*flush)(void *src, unsigned int size), ++ unsigned char *out, int *in_used, ++ void (*error)(char *x)); ++ ++#endif +diff --git a/init/Kconfig b/init/Kconfig +index 2de5b1c..d9fbb0f 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -123,13 +123,16 @@ config HAVE_KERNEL_BZIP2 + config HAVE_KERNEL_LZMA + bool + ++config HAVE_KERNEL_XZ ++ bool ++ + config HAVE_KERNEL_LZO + bool + + choice + prompt "Kernel compression mode" + default KERNEL_GZIP +- depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_LZO ++ depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO + help + The linux kernel is a kind of self-extracting executable. + Several compression algorithms are available, which differ +@@ -174,6 +177,21 @@ config KERNEL_LZMA + two. Compression is slowest. The kernel size is about 33% + smaller with LZMA in comparison to gzip. + ++config KERNEL_XZ ++ bool "XZ" ++ depends on HAVE_KERNEL_XZ ++ help ++ XZ uses the LZMA2 algorithm and instruction set specific ++ BCJ filters which can improve compression ratio of executable ++ code. The size of the kernel is about 30% smaller with XZ in ++ comparison to gzip. On architectures for which there is a BCJ ++ filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ ++ will create a few percent smaller kernel than plain LZMA. ++ ++ The speed is about the same as with LZMA: The decompression ++ speed of XZ is better than that of bzip2 but worse than gzip ++ and LZO. Compression is slow. ++ + config KERNEL_LZO + bool "LZO" + depends on HAVE_KERNEL_LZO +diff --git a/lib/Kconfig b/lib/Kconfig +index 6090314..45960e1 100644 +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -122,6 +122,9 @@ config DECOMPRESS_BZIP2 + config DECOMPRESS_LZMA + tristate + ++config DECOMPRESS_XZ ++ tristate ++ + config DECOMPRESS_LZO + select LZO_DECOMPRESS + tristate +diff --git a/lib/Makefile b/lib/Makefile +index f2f98dd..06e3d8a 100644 +--- a/lib/Makefile ++++ b/lib/Makefile +@@ -75,6 +75,7 @@ obj-$(CONFIG_RAID6_PQ) += raid6/ + lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o + lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o + lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o ++lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o + lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o + + obj-$(CONFIG_TEXTSEARCH) += textsearch.o +diff --git a/lib/decompress.c b/lib/decompress.c +index a760681..3d766b7 100644 +--- a/lib/decompress.c ++++ b/lib/decompress.c +@@ -8,6 +8,7 @@ + + #include + #include ++#include + #include + #include + +@@ -23,6 +24,9 @@ + #ifndef CONFIG_DECOMPRESS_LZMA + # define unlzma NULL + #endif ++#ifndef CONFIG_DECOMPRESS_XZ ++# define unxz NULL ++#endif + #ifndef CONFIG_DECOMPRESS_LZO + # define unlzo NULL + #endif +@@ -36,6 +40,7 @@ static const struct compress_format { + { {037, 0236}, "gzip", gunzip }, + { {0x42, 0x5a}, "bzip2", bunzip2 }, + { {0x5d, 0x00}, "lzma", unlzma }, ++ { {0xfd, 0x37}, "xz", unxz }, + { {0x89, 0x4c}, "lzo", unlzo }, + { {0, 0}, NULL, NULL } + }; +diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c +new file mode 100644 +index 0000000..cecd23d +--- /dev/null ++++ b/lib/decompress_unxz.c +@@ -0,0 +1,397 @@ ++/* ++ * 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. ++ */ ++ ++/* ++ * STATIC is defined to "static" if we are being built for kernel ++ * decompression (pre-boot code). will define ++ * STATIC to empty if it wasn't already defined. Since we will need to ++ * know later if we are being used for kernel decompression, we define ++ * XZ_PREBOOT here. ++ */ ++#ifdef STATIC ++# define XZ_PREBOOT ++#endif ++#ifdef __KERNEL__ ++# include ++#endif ++#define XZ_EXTERN STATIC ++ ++#ifndef XZ_PREBOOT ++# include ++# include ++#else ++/* ++ * Use the internal CRC32 code instead of kernel's CRC32 module, which ++ * is not available in early phase of booting. ++ */ ++#define XZ_INTERNAL_CRC32 1 ++ ++/* ++ * 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/xz_private.h" ++ ++/* ++ * Replace the normal allocation functions with the versions from ++ * . vfree() needs to support vfree(NULL) ++ * when XZ_DYNALLOC is used, but the pre-boot free() doesn't support it. ++ * Workaround it here because the other decompressors don't need it. ++ */ ++#undef kmalloc ++#undef kfree ++#undef vmalloc ++#undef vfree ++#define kmalloc(size, flags) malloc(size) ++#define kfree(ptr) free(ptr) ++#define vmalloc(size) malloc(size) ++#define vfree(ptr) do { if (ptr != NULL) free(ptr); } while (0) ++ ++/* ++ * FIXME: Not all basic memory functions are provided in architecture-specific ++ * files (yet). We define our own versions here for now, but this should be ++ * only a temporary solution. ++ * ++ * 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 ++static bool memeq(const void *a, const void *b, size_t size) ++{ ++ const uint8_t *x = a; ++ const uint8_t *y = b; ++ size_t i; ++ ++ for (i = 0; i < size; ++i) ++ if (x[i] != y[i]) ++ return false; ++ ++ return true; ++} ++#endif ++ ++#ifndef memzero ++static void memzero(void *buf, size_t size) ++{ ++ uint8_t *b = buf; ++ uint8_t *e = b + size; ++ ++ while (b != e) ++ *b++ = '\0'; ++} ++#endif ++ ++#ifndef memmove ++/* Not static to avoid a conflict with the prototype in the Linux headers. */ ++void *memmove(void *dest, const void *src, size_t size) ++{ ++ uint8_t *d = dest; ++ const uint8_t *s = src; ++ size_t i; ++ ++ if (d < s) { ++ for (i = 0; i < size; ++i) ++ d[i] = s[i]; ++ } else if (d > s) { ++ i = size; ++ while (i-- > 0) ++ d[i] = s[i]; ++ } ++ ++ return dest; ++} ++#endif ++ ++/* ++ * Since we need memmove anyway, would use it as memcpy too. ++ * Commented out for now to avoid breaking things. ++ */ ++/* ++#ifndef memcpy ++# define memcpy memmove ++#endif ++*/ ++ ++#include "xz/xz_crc32.c" ++#include "xz/xz_dec_stream.c" ++#include "xz/xz_dec_lzma2.c" ++#include "xz/xz_dec_bcj.c" ++ ++#endif /* XZ_PREBOOT */ ++ ++/* 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, int in_size, ++ int (*fill)(void *dest, unsigned int size), ++ int (*flush)(void *src, unsigned int size), ++ unsigned char *out, int *in_used, ++ void (*error)(char *x)) ++{ ++ struct xz_buf b; ++ struct xz_dec *s; ++ enum xz_ret ret; ++ bool must_free_in = false; ++ ++#if XZ_INTERNAL_CRC32 ++ xz_crc32_init(); ++#endif ++ ++ 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/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh +index 5958fff..55caecd 100644 +--- a/scripts/gen_initramfs_list.sh ++++ b/scripts/gen_initramfs_list.sh +@@ -243,6 +243,8 @@ case "$arg" in + echo "$output_file" | grep -q "\.gz$" && compr="gzip -9 -f" + echo "$output_file" | grep -q "\.bz2$" && compr="bzip2 -9 -f" + echo "$output_file" | grep -q "\.lzma$" && compr="lzma -9 -f" ++ echo "$output_file" | grep -q "\.xz$" && \ ++ compr="xz --check=crc32 --lzma2=dict=1MiB" + echo "$output_file" | grep -q "\.lzo$" && compr="lzop -9 -f" + echo "$output_file" | grep -q "\.cpio$" && compr="cat" + shift +diff --git a/usr/Kconfig b/usr/Kconfig +index e2721f5..9f51a29 100644 +--- a/usr/Kconfig ++++ b/usr/Kconfig +@@ -72,6 +72,18 @@ config RD_LZMA + Support loading of a LZMA encoded initial ramdisk or cpio buffer + If unsure, say N. + ++config RD_XZ ++ bool "Support initial ramdisks compressed using XZ" ++ depends on BLK_DEV_INITRD && XZ_DEC=y ++ select DECOMPRESS_XZ ++ help ++ Support loading of a XZ encoded initial ramdisk or cpio buffer. ++ ++ If this option is inactive, say Y to "XZ decompression support" ++ under "Library routines" first. ++ ++ If unsure, say N. ++ + config RD_LZO + bool "Support initial ramdisks compressed using LZO" if EMBEDDED + default !EMBEDDED +@@ -139,6 +151,15 @@ config INITRAMFS_COMPRESSION_LZMA + three. Compression is slowest. The initramfs size is about 33% + smaller with LZMA in comparison to gzip. + ++config INITRAMFS_COMPRESSION_XZ ++ bool "XZ" ++ depends on RD_XZ ++ help ++ XZ uses the LZMA2 algorithm. The initramfs size is about 30% ++ smaller with XZ in comparison to gzip. Decompression speed ++ is better than that of bzip2 but worse than gzip and LZO. ++ Compression is slow. ++ + config INITRAMFS_COMPRESSION_LZO + bool "LZO" + depends on RD_LZO +diff --git a/usr/Makefile b/usr/Makefile +index 6b4b6da..5845a13 100644 +--- a/usr/Makefile ++++ b/usr/Makefile +@@ -15,6 +15,9 @@ suffix_$(CONFIG_INITRAMFS_COMPRESSION_BZIP2) = .bz2 + # Lzma + suffix_$(CONFIG_INITRAMFS_COMPRESSION_LZMA) = .lzma + ++# XZ ++suffix_$(CONFIG_INITRAMFS_COMPRESSION_XZ) = .xz ++ + # Lzo + suffix_$(CONFIG_INITRAMFS_COMPRESSION_LZO) = .lzo + +@@ -48,7 +51,7 @@ endif + quiet_cmd_initfs = GEN $@ + cmd_initfs = $(initramfs) -o $@ $(ramfs-args) $(ramfs-input) + +-targets := initramfs_data.cpio.gz initramfs_data.cpio.bz2 initramfs_data.cpio.lzma initramfs_data.cpio.lzo initramfs_data.cpio ++targets := initramfs_data.cpio.gz initramfs_data.cpio.bz2 initramfs_data.cpio.lzma initramfs_data.cpio.xz initramfs_data.cpio.lzo initramfs_data.cpio + # do not try to update files included in initramfs + $(deps_initramfs): ; + diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/003-squashfs-x86-support-xz-compressed-kernel.patch --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/linux/stuff/003-squashfs-x86-support-xz-compressed-kernel.patch Tue Dec 14 21:45:09 2010 +0000 @@ -0,0 +1,128 @@ +From: Lasse Collin +Date: Thu, 2 Dec 2010 19:14:57 +0000 (+0200) +Subject: x86: Support XZ-compressed kernel +X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Fpkl%2Fsquashfs-xz.git;a=commitdiff_plain;h=d4ad78414e5312126127b1f88cdaf8584af3eef1 + +x86: Support XZ-compressed kernel + +This integrates the XZ decompression code to the x86 +pre-boot code. + +mkpiggy.c is updated to reserve about 32 KiB more buffer safety +margin for kernel decompression. It is done unconditionally for +all decompressors to keep the code simpler. + +The XZ decompressor needs around 30 KiB of heap, so the heap size +is increased to 32 KiB on both x86-32 and x86-64. + +Documentation/x86/boot.txt is updated to list the XZ magic number. + +With the x86 BCJ filter in XZ, XZ-compressed x86 kernel tends to be +a few percent smaller than the equivalent LZMA-compressed kernel. + +Signed-off-by: Lasse Collin +--- + +diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt +index 30b43e1..3988cde 100644 +--- a/Documentation/x86/boot.txt ++++ b/Documentation/x86/boot.txt +@@ -621,9 +621,9 @@ Protocol: 2.08+ + The payload may be compressed. The format of both the compressed and + uncompressed data should be determined using the standard magic + numbers. The currently supported compression formats are gzip +- (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A) and LZMA +- (magic number 5D 00). The uncompressed payload is currently always ELF +- (magic number 7F 45 4C 46). ++ (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A), LZMA ++ (magic number 5D 00), and XZ (magic number FD 37). The uncompressed ++ payload is currently always ELF (magic number 7F 45 4C 46). + + Field name: payload_length + Type: read +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index cea0cd9..f3db0d7 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -51,6 +51,7 @@ config X86 + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_LZMA ++ select HAVE_KERNEL_XZ + select HAVE_KERNEL_LZO + select HAVE_HW_BREAKPOINT + select HAVE_MIXED_BREAKPOINTS_REGS +diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile +index 0c22955..09664ef 100644 +--- a/arch/x86/boot/compressed/Makefile ++++ b/arch/x86/boot/compressed/Makefile +@@ -4,7 +4,7 @@ + # create a compressed vmlinux image from the original vmlinux + # + +-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o ++targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o + + KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 + KBUILD_CFLAGS += -fno-strict-aliasing -fPIC +@@ -49,12 +49,15 @@ $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE + $(call if_changed,bzip2) + $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lzma) ++$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE ++ $(call if_changed,xzkern) + $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lzo) + + suffix-$(CONFIG_KERNEL_GZIP) := gz + suffix-$(CONFIG_KERNEL_BZIP2) := bz2 + suffix-$(CONFIG_KERNEL_LZMA) := lzma ++suffix-$(CONFIG_KERNEL_XZ) := xz + suffix-$(CONFIG_KERNEL_LZO) := lzo + + quiet_cmd_mkpiggy = MKPIGGY $@ +diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c +index 8f7bef8..6d4cab7 100644 +--- a/arch/x86/boot/compressed/misc.c ++++ b/arch/x86/boot/compressed/misc.c +@@ -139,6 +139,10 @@ static int lines, cols; + #include "../../../../lib/decompress_unlzma.c" + #endif + ++#ifdef CONFIG_KERNEL_XZ ++#include "../../../../lib/decompress_unxz.c" ++#endif ++ + #ifdef CONFIG_KERNEL_LZO + #include "../../../../lib/decompress_unlzo.c" + #endif +diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c +index 5c22812..646aa78 100644 +--- a/arch/x86/boot/compressed/mkpiggy.c ++++ b/arch/x86/boot/compressed/mkpiggy.c +@@ -74,7 +74,7 @@ int main(int argc, char *argv[]) + + offs = (olen > ilen) ? olen - ilen : 0; + offs += olen >> 12; /* Add 8 bytes for each 32K block */ +- offs += 32*1024 + 18; /* Add 32K + 18 bytes slack */ ++ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ + offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + + printf(".section \".rodata..compressed\",\"a\",@progbits\n"); +diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h +index 3b62ab5..5e1a2ee 100644 +--- a/arch/x86/include/asm/boot.h ++++ b/arch/x86/include/asm/boot.h +@@ -32,11 +32,7 @@ + #define BOOT_HEAP_SIZE 0x400000 + #else /* !CONFIG_KERNEL_BZIP2 */ + +-#ifdef CONFIG_X86_64 +-#define BOOT_HEAP_SIZE 0x7000 +-#else +-#define BOOT_HEAP_SIZE 0x4000 +-#endif ++#define BOOT_HEAP_SIZE 0x8000 + + #endif /* !CONFIG_KERNEL_BZIP2 */ + diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/004-squashfs-add-xz-compression-support.patch --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/linux/stuff/004-squashfs-add-xz-compression-support.patch Tue Dec 14 21:45:09 2010 +0000 @@ -0,0 +1,183 @@ +From: Phillip Lougher +Date: Thu, 9 Dec 2010 02:02:29 +0000 (+0000) +Subject: Squashfs: add XZ compression support +X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Fpkl%2Fsquashfs-xz.git;a=commitdiff_plain;h=d3e6969b9ff1f3a3c6bf3da71433c77046aa80e4 + +Squashfs: add XZ compression support + +Add XZ decompressor wrapper code. + +Signed-off-by: Phillip Lougher +--- + +diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h +index c5137fc..39533fe 100644 +--- a/fs/squashfs/squashfs_fs.h ++++ b/fs/squashfs/squashfs_fs.h +@@ -238,6 +238,7 @@ struct meta_index { + #define ZLIB_COMPRESSION 1 + #define LZMA_COMPRESSION 2 + #define LZO_COMPRESSION 3 ++#define XZ_COMPRESSION 4 + + struct squashfs_super_block { + __le32 s_magic; +diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c +new file mode 100644 +index 0000000..053fe35 +--- /dev/null ++++ b/fs/squashfs/xz_wrapper.c +@@ -0,0 +1,153 @@ ++/* ++ * Squashfs - a compressed read only filesystem for Linux ++ * ++ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 ++ * Phillip Lougher ++ * ++ * This program is free software; you can redistribute it and/or ++ * modify it under the terms of the GNU General Public License ++ * as published by the Free Software Foundation; either version 2, ++ * or (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program; if not, write to the Free Software ++ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. ++ * ++ * xz_wrapper.c ++ */ ++ ++ ++#include ++#include ++#include ++#include ++ ++#include "squashfs_fs.h" ++#include "squashfs_fs_sb.h" ++#include "squashfs_fs_i.h" ++#include "squashfs.h" ++#include "decompressor.h" ++ ++struct squashfs_xz { ++ struct xz_dec *state; ++ struct xz_buf buf; ++}; ++ ++static void *squashfs_xz_init(struct squashfs_sb_info *msblk) ++{ ++ int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); ++ ++ struct squashfs_xz *stream = kmalloc(sizeof(*stream), GFP_KERNEL); ++ if (stream == NULL) ++ goto failed; ++ stream->state = xz_dec_init(XZ_PREALLOC, block_size); ++ if (stream->state == NULL) ++ goto failed; ++ ++ return stream; ++ ++failed: ++ ERROR("Failed to allocate xz workspace\n"); ++ kfree(stream); ++ return NULL; ++} ++ ++ ++static void squashfs_xz_free(void *strm) ++{ ++ struct squashfs_xz *stream = strm; ++ ++ if (stream) { ++ xz_dec_end(stream->state); ++ kfree(stream); ++ } ++} ++ ++ ++static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer, ++ struct buffer_head **bh, int b, int offset, int length, int srclength, ++ int pages) ++{ ++ enum xz_ret xz_err; ++ int avail, total = 0, k = 0, page = 0; ++ struct squashfs_xz *stream = msblk->stream; ++ ++ mutex_lock(&msblk->read_data_mutex); ++ ++ xz_dec_reset(stream->state); ++ stream->buf.in_pos = 0; ++ stream->buf.in_size = 0; ++ stream->buf.out_pos = 0; ++ stream->buf.out_size = PAGE_CACHE_SIZE; ++ stream->buf.out = buffer[page++]; ++ ++ do { ++ if (stream->buf.in_pos == stream->buf.in_size && k < b) { ++ avail = min(length, msblk->devblksize - offset); ++ length -= avail; ++ wait_on_buffer(bh[k]); ++ if (!buffer_uptodate(bh[k])) ++ goto release_mutex; ++ ++ if (avail == 0) { ++ offset = 0; ++ put_bh(bh[k++]); ++ continue; ++ } ++ ++ stream->buf.in = bh[k]->b_data + offset; ++ stream->buf.in_size = avail; ++ stream->buf.in_pos = 0; ++ offset = 0; ++ } ++ ++ if (stream->buf.out_pos == stream->buf.out_size ++ && page < pages) { ++ stream->buf.out = buffer[page++]; ++ stream->buf.out_pos = 0; ++ total += PAGE_CACHE_SIZE; ++ } ++ ++ xz_err = xz_dec_run(stream->state, &stream->buf); ++ ++ if (stream->buf.in_pos == stream->buf.in_size && k < b) ++ put_bh(bh[k++]); ++ } while (xz_err == XZ_OK); ++ ++ if (xz_err != XZ_STREAM_END) { ++ ERROR("xz_dec_run error, data probably corrupt\n"); ++ goto release_mutex; ++ } ++ ++ if (k < b) { ++ ERROR("xz_uncompress error, input remaining\n"); ++ goto release_mutex; ++ } ++ ++ total += stream->buf.out_pos; ++ mutex_unlock(&msblk->read_data_mutex); ++ return total; ++ ++release_mutex: ++ mutex_unlock(&msblk->read_data_mutex); ++ ++ for (; k < b; k++) ++ put_bh(bh[k]); ++ ++ return -EIO; ++} ++ ++const struct squashfs_decompressor squashfs_xz_comp_ops = { ++ .init = squashfs_xz_init, ++ .free = squashfs_xz_free, ++ .decompress = squashfs_xz_uncompress, ++ .id = XZ_COMPRESSION, ++ .name = "xz", ++ .supported = 1 ++}; ++ diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/005-squashfs-add-xz-compression-configuration-option.patch --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/linux/stuff/005-squashfs-add-xz-compression-configuration-option.patch Tue Dec 14 21:45:09 2010 +0000 @@ -0,0 +1,86 @@ +From: Phillip Lougher +Date: Thu, 9 Dec 2010 02:08:31 +0000 (+0000) +Subject: Squashfs: Add XZ compression configuration option +X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Fpkl%2Fsquashfs-xz.git;a=commitdiff_plain;h=e23d468968e608de27328888240de27d7582ad52 + +Squashfs: Add XZ compression configuration option + +Signed-off-by: Phillip Lougher +--- + +diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig +index e5f63da..e96d99a 100644 +--- a/fs/squashfs/Kconfig ++++ b/fs/squashfs/Kconfig +@@ -53,6 +53,22 @@ config SQUASHFS_LZO + + If unsure, say N. + ++config SQUASHFS_XZ ++ bool "Include support for XZ compressed file systems" ++ depends on SQUASHFS ++ default n ++ select XZ_DEC ++ help ++ Saying Y here includes support for reading Squashfs file systems ++ compressed with XZ compresssion. XZ gives better compression than ++ the default zlib compression, at the expense of greater CPU and ++ memory overhead. ++ ++ XZ is not the standard compression used in Squashfs and so most ++ file systems will be readable without selecting this option. ++ ++ If unsure, say N. ++ + config SQUASHFS_EMBEDDED + bool "Additional option for memory-constrained systems" + depends on SQUASHFS +diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile +index 7672bac..cecf2be 100644 +--- a/fs/squashfs/Makefile ++++ b/fs/squashfs/Makefile +@@ -7,3 +7,4 @@ squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o + squashfs-y += namei.o super.o symlink.o zlib_wrapper.o decompressor.o + squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o + squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o ++squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o +diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c +index 24af9ce..ac333b8 100644 +--- a/fs/squashfs/decompressor.c ++++ b/fs/squashfs/decompressor.c +@@ -46,6 +46,12 @@ static const struct squashfs_decompressor squashfs_lzo_unsupported_comp_ops = { + }; + #endif + ++#ifndef CONFIG_SQUASHFS_XZ ++static const struct squashfs_decompressor squashfs_xz_unsupported_comp_ops = { ++ NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 ++}; ++#endif ++ + static const struct squashfs_decompressor squashfs_unknown_comp_ops = { + NULL, NULL, NULL, 0, "unknown", 0 + }; +@@ -58,6 +64,11 @@ static const struct squashfs_decompressor *decompressor[] = { + #else + &squashfs_lzo_unsupported_comp_ops, + #endif ++#ifdef CONFIG_SQUASHFS_XZ ++ &squashfs_xz_comp_ops, ++#else ++ &squashfs_xz_unsupported_comp_ops, ++#endif + &squashfs_unknown_comp_ops + }; + +diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h +index 5d45569..1096e2e 100644 +--- a/fs/squashfs/squashfs.h ++++ b/fs/squashfs/squashfs.h +@@ -107,3 +107,6 @@ extern const struct squashfs_decompressor squashfs_zlib_comp_ops; + + /* lzo_wrapper.c */ + extern const struct squashfs_decompressor squashfs_lzo_comp_ops; ++ ++/* xz_wrapper.c */ ++extern const struct squashfs_decompressor squashfs_xz_comp_ops; diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/linux-2.6.36-slitaz.config --- a/linux/stuff/linux-2.6.36-slitaz.config Tue Dec 14 21:34:46 2010 +0000 +++ b/linux/stuff/linux-2.6.36-slitaz.config Tue Dec 14 21:45:09 2010 +0000 @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit # Linux kernel version: 2.6.36 -# Fri Nov 5 02:14:33 2010 +# Tue Dec 14 11:22:55 2010 # # CONFIG_64BIT is not set CONFIG_X86_32=y @@ -74,10 +74,12 @@ CONFIG_HAVE_KERNEL_GZIP=y CONFIG_HAVE_KERNEL_BZIP2=y CONFIG_HAVE_KERNEL_LZMA=y +CONFIG_HAVE_KERNEL_XZ=y CONFIG_HAVE_KERNEL_LZO=y # CONFIG_KERNEL_GZIP is not set # CONFIG_KERNEL_BZIP2 is not set CONFIG_KERNEL_LZMA=y +# CONFIG_KERNEL_XZ is not set # CONFIG_KERNEL_LZO is not set CONFIG_SWAP=y CONFIG_SYSVIPC=y @@ -116,6 +118,7 @@ CONFIG_RD_GZIP=y CONFIG_RD_BZIP2=y CONFIG_RD_LZMA=y +CONFIG_RD_XZ=y CONFIG_RD_LZO=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_SYSCTL=y @@ -837,7 +840,6 @@ CONFIG_ATM_BR2684=m # CONFIG_ATM_BR2684_IPFILTER is not set # CONFIG_L2TP is not set -# CONFIG_L2TP_V3 is not set CONFIG_STP=m CONFIG_BRIDGE=m # CONFIG_BRIDGE_IGMP_SNOOPING is not set @@ -1815,7 +1817,6 @@ CONFIG_PPP_MPPE=y CONFIG_PPPOE=y CONFIG_PPPOATM=m -# CONFIG_PPPOL2TP is not set # CONFIG_SLIP is not set CONFIG_SLHC=y # CONFIG_NET_FC is not set @@ -3268,6 +3269,7 @@ CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y # CONFIG_SQUASHFS_EMBEDDED is not set CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE=3 # CONFIG_VXFS_FS is not set @@ -3278,23 +3280,6 @@ # CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set -CONFIG_AUFS_FS=m -# CONFIG_AUFS_BRANCH_MAX_127 is not set -# CONFIG_AUFS_BRANCH_MAX_511 is not set -CONFIG_AUFS_BRANCH_MAX_1023=y -# CONFIG_AUFS_BRANCH_MAX_32767 is not set -CONFIG_AUFS_HNOTIFY=y -CONFIG_AUFS_HFSNOTIFY=y -# CONFIG_AUFS_HINOTIFY is not set -# CONFIG_AUFS_EXPORT is not set -# CONFIG_AUFS_RDU is not set -# CONFIG_AUFS_SP_IATTR is not set -CONFIG_AUFS_SHWH=y -CONFIG_AUFS_BR_RAMFS=y -# CONFIG_AUFS_BR_FUSE is not set -# CONFIG_AUFS_BR_HFSPLUS is not set -CONFIG_AUFS_BDEV_LOOP=y -# CONFIG_AUFS_DEBUG is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y @@ -3615,9 +3600,19 @@ CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y CONFIG_LZO_DECOMPRESS=y +CONFIG_XZ_DEC=y +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +CONFIG_XZ_DEC_BCJ=y +# CONFIG_XZ_DEC_TEST is not set CONFIG_DECOMPRESS_GZIP=y CONFIG_DECOMPRESS_BZIP2=y CONFIG_DECOMPRESS_LZMA=y +CONFIG_DECOMPRESS_XZ=y CONFIG_DECOMPRESS_LZO=y CONFIG_TEXTSEARCH=y CONFIG_TEXTSEARCH_KMP=m diff -r 13e4d4e6fcc1 -r 1bea914df3b9 linux/stuff/modules-2.6.36.list --- a/linux/stuff/modules-2.6.36.list Tue Dec 14 21:34:46 2010 +0000 +++ b/linux/stuff/modules-2.6.36.list Tue Dec 14 21:45:09 2010 +0000 @@ -128,6 +128,9 @@ net/llc/llc.ko.gz drivers/mmc/core/mmc_core.ko.gz net/rfkill/rfkill.ko.gz +net/sunrpc/auth_gss/auth_rpcgss.ko.gz +net/sunrpc/auth_gss/rpcsec_gss_krb5.ko.gz +net/netfilter/nf_conntrack.ko.gz drivers/input/gameport/gameport.ko.gz drivers/i2c/i2c-core.ko.gz sound/soundcore.ko.gz