diff options
| -rw-r--r-- | archival/Config.in | 22 | ||||
| -rw-r--r-- | archival/Kbuild | 19 | ||||
| -rw-r--r-- | archival/bbunzip.c | 33 | ||||
| -rw-r--r-- | archival/libunarchive/Kbuild | 1 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/README | 136 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz.h | 212 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_config.h | 119 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_dec_bcj.c | 560 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_dec_lzma2.c | 1157 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_dec_stream.c | 787 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_lzma2.h | 204 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_private.h | 120 | ||||
| -rw-r--r-- | archival/libunarchive/unxz/xz_stream.h | 46 | ||||
| -rw-r--r-- | include/applets.h | 3 | ||||
| -rw-r--r-- | include/unarchive.h | 1 | ||||
| -rw-r--r-- | include/usage.h | 22 |
16 files changed, 3433 insertions, 9 deletions
diff --git a/archival/Config.in b/archival/Config.in index 028fce32f..4f762e860 100644 --- a/archival/Config.in +++ b/archival/Config.in @@ -5,6 +5,12 @@ menu "Archival Utilities" +config FEATURE_SEAMLESS_XZ + bool "Make tar, rpm, modprobe etc understand .xz data" + default n + help + Make tar, rpm, modprobe etc understand .xz data. + config FEATURE_SEAMLESS_LZMA bool "Make tar, rpm, modprobe etc understand .lzma data" default n @@ -225,7 +231,7 @@ config FEATURE_TAR_CREATE config FEATURE_TAR_AUTODETECT bool "Autodetect compressed tarballs" default n - depends on TAR && (FEATURE_SEAMLESS_Z || FEATURE_SEAMLESS_GZ || FEATURE_SEAMLESS_BZ2 || FEATURE_SEAMLESS_LZMA) + depends on TAR && (FEATURE_SEAMLESS_Z || FEATURE_SEAMLESS_GZ || FEATURE_SEAMLESS_BZ2 || FEATURE_SEAMLESS_LZMA || FEATURE_SEAMLESS_XZ) help With this option tar can automatically detect compressed tarballs. Currently it works only on files (not pipes etc). @@ -335,6 +341,20 @@ config LZMA Enable this option if you want commands like "lzma -d" to work. IOW: you'll get lzma applet, but it will always require -d option. +config UNXZ + bool "unxz" + default n + help + unxz is a unlzma successor. + +config XZ + bool "Provide xz alias which supports only unpacking" + default n + depends on UNXZ + help + Enable this option if you want commands like "xz -d" to work. + IOW: you'll get xz applet, but it will always require -d option. + config UNZIP bool "unzip" default n diff --git a/archival/Kbuild b/archival/Kbuild index 53bd7e21e..3300ea90f 100644 --- a/archival/Kbuild +++ b/archival/Kbuild @@ -8,18 +8,21 @@ libs-y += libunarchive/ lib-y:= lib-$(CONFIG_AR) += ar.o -lib-$(CONFIG_BUNZIP2) += bbunzip.o -lib-$(CONFIG_BZIP2) += bzip2.o bbunzip.o -lib-$(CONFIG_UNLZMA) += bbunzip.o lib-$(CONFIG_CPIO) += cpio.o lib-$(CONFIG_DPKG) += dpkg.o lib-$(CONFIG_DPKG_DEB) += dpkg_deb.o -lib-$(CONFIG_GUNZIP) += bbunzip.o -lib-$(CONFIG_GZIP) += gzip.o bbunzip.o -lib-$(CONFIG_LZOP) += lzop.o lzo1x_1.o lzo1x_1o.o lzo1x_d.o bbunzip.o -lib-$(CONFIG_LZOP_COMPR_HIGH) += lzo1x_9x.o lib-$(CONFIG_RPM2CPIO) += rpm2cpio.o lib-$(CONFIG_RPM) += rpm.o lib-$(CONFIG_TAR) += tar.o -lib-$(CONFIG_UNCOMPRESS) += bbunzip.o lib-$(CONFIG_UNZIP) += unzip.o + +lib-$(CONFIG_LZOP) += lzop.o lzo1x_1.o lzo1x_1o.o lzo1x_d.o bbunzip.o +lib-$(CONFIG_LZOP_COMPR_HIGH) += lzo1x_9x.o +lib-$(CONFIG_GZIP) += gzip.o bbunzip.o +lib-$(CONFIG_BZIP2) += bzip2.o bbunzip.o + +lib-$(CONFIG_UNXZ) += bbunzip.o +lib-$(CONFIG_UNLZMA) += bbunzip.o +lib-$(CONFIG_BUNZIP2) += bbunzip.o +lib-$(CONFIG_GUNZIP) += bbunzip.o +lib-$(CONFIG_UNCOMPRESS) += bbunzip.o diff --git a/archival/bbunzip.c b/archival/bbunzip.c index 178dc63be..824b0027f 100644 --- a/archival/bbunzip.c +++ b/archival/bbunzip.c @@ -387,3 +387,36 @@ int uncompress_main(int argc UNUSED_PARAM, char **argv) } #endif + +#if ENABLE_UNXZ + +static +char* make_new_name_unxz(char *filename) +{ + return make_new_name_generic(filename, "xz"); +} + +static +IF_DESKTOP(long long) int unpack_unxz(unpack_info_t *info UNUSED_PARAM) +{ + return unpack_xz_stream_stdin(); +} + +int unxz_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE; +int unxz_main(int argc UNUSED_PARAM, char **argv) +{ + int opts = getopt32(argv, "cfvdt"); +# if ENABLE_XZ + /* xz without -d or -t? */ + if (applet_name[2] == '\0' && !(opts & (OPT_DECOMPRESS|OPT_TEST))) + bb_show_usage(); +# endif + /* xzcat? */ + if (applet_name[2] == 'c') + option_mask32 |= OPT_STDOUT; + + argv += optind; + return bbunpack(argv, make_new_name_unxz, unpack_unxz); +} + +#endif diff --git a/archival/libunarchive/Kbuild b/archival/libunarchive/Kbuild index 11d23b25f..ed8e85793 100644 --- a/archival/libunarchive/Kbuild +++ b/archival/libunarchive/Kbuild @@ -49,6 +49,7 @@ lib-$(CONFIG_FEATURE_SEAMLESS_Z) += open_transformer.o decompress_uncompr lib-$(CONFIG_FEATURE_SEAMLESS_GZ) += open_transformer.o decompress_unzip.o get_header_tar_gz.o lib-$(CONFIG_FEATURE_SEAMLESS_BZ2) += open_transformer.o decompress_bunzip2.o get_header_tar_bz2.o lib-$(CONFIG_FEATURE_SEAMLESS_LZMA) += open_transformer.o decompress_unlzma.o get_header_tar_lzma.o +lib-$(CONFIG_FEATURE_SEAMLESS_XZ) += open_transformer.o decompress_unxz.o lib-$(CONFIG_FEATURE_COMPRESS_USAGE) += decompress_bunzip2.o ifneq ($(lib-y),) diff --git a/archival/libunarchive/unxz/README b/archival/libunarchive/unxz/README new file mode 100644 index 000000000..f79b0a404 --- /dev/null +++ b/archival/libunarchive/unxz/README @@ -0,0 +1,136 @@ + +XZ Embedded +=========== + + XZ Embedded is a relatively small, limited implementation of the .xz + file format. Currently only decoding is implemented. + + XZ Embedded was written for use in the Linux kernel, but the code can + be easily used in other environments too, including regular userspace + applications. + + This README contains information that is useful only when the copy + of XZ Embedded isn't part of the Linux kernel tree. You should also + read linux/Documentation/xz.txt even if you aren't using XZ Embedded + as part of Linux; information in that file is not repeated in this + README. + +Compiling the Linux kernel module + + The xz_dec module depends on crc32 module, so make sure that you have + it enabled (CONFIG_CRC32). + + Building the xz_dec and xz_dec_test modules without support for BCJ + filters: + + cd linux/lib/xz + make -C /path/to/kernel/source \ + KCPPFLAGS=-I"$(pwd)/../../include" M="$(pwd)" \ + CONFIG_XZ_DEC=m CONFIG_XZ_DEC_TEST=m + + Building the xz_dec and xz_dec_test modules with support for BCJ + filters: + + cd linux/lib/xz + make -C /path/to/kernel/source \ + KCPPFLAGS=-I"$(pwd)/../../include" M="$(pwd)" \ + CONFIG_XZ_DEC=m CONFIG_XZ_DEC_TEST=m CONFIG_XZ_DEC_BCJ=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 + + If you want only one or a few of the BCJ filters, omit the appropriate + variables. CONFIG_XZ_DEC_BCJ=y is always required to build the support + code shared between all BCJ filters. + + Most people don't need the xz_dec_test module. You can skip building + it by omitting CONFIG_XZ_DEC_TEST=m from the make command line. + +Compiler requirements + + XZ Embedded should compile as either GNU-C89 (used in the Linux + kernel) or with any C99 compiler. Getting the code to compile with + non-GNU C89 compiler or a C++ compiler should be quite easy as + long as there is a data type for unsigned 64-bit integer (or the + code is modified not to support large files, which needs some more + care than just using 32-bit integer instead of 64-bit). + + If you use GCC, try to use a recent version. For example, on x86, + xz_dec_lzma2.c compiled with GCC 3.3.6 is 15-25 % slower than when + compiled with GCC 4.3.3. + +Embedding into userspace applications + + To embed the XZ decoder, copy the following files into a single + directory in your source code tree: + + linux/include/linux/xz.h + linux/lib/xz/xz_crc32.c + linux/lib/xz/xz_dec_lzma2.c + linux/lib/xz/xz_dec_stream.c + linux/lib/xz/xz_lzma2.h + linux/lib/xz/xz_private.h + linux/lib/xz/xz_stream.h + userspace/xz_config.h + + Alternatively, xz.h may be placed into a different directory but then + that directory must be in the compiler include path when compiling + the .c files. + + Your code should use only the functions declared in xz.h. The rest of + the .h files are meant only for internal use in XZ Embedded. + + You may want to modify xz_config.h to be more suitable for your build + environment. Probably you should at least skim through it even if the + default file works as is. + +BCJ filter support + + If you want support for one or more BCJ filters, you need to copy also + linux/lib/xz/xz_dec_bcj.c into your application, and use appropriate + #defines in xz_config.h or in compiler flags. You don't need these + #defines in the code that just uses XZ Embedded via xz.h, but having + them always #defined doesn't hurt either. + + #define Instruction set BCJ filter endianness + XZ_DEC_X86 x86 or x86-64 Little endian only + XZ_DEC_POWERPC PowerPC Big endian only + XZ_DEC_IA64 Itanium (IA-64) Big or little endian + XZ_DEC_ARM ARM Little endian only + XZ_DEC_ARMTHUMB ARM-Thumb Little endian only + XZ_DEC_SPARC SPARC Big or little endian + + While some architectures are (partially) bi-endian, the endianness + setting doesn't change the endianness of the instructions on all + architectures. That's why Itanium and SPARC filters work for both big + and little endian executables (Itanium has little endian instructions + and SPARC has big endian instructions). + + There currently is no filter for little endian PowerPC or big endian + ARM or ARM-Thumb. Implementing filters for them can be considered if + there is a need for such filters in real-world applications. + +Notes about shared libraries + + If you are including XZ Embedded into a shared library, you very + probably should rename the xz_* functions to prevent symbol + conflicts in case your library is linked against some other library + or application that also has XZ Embedded in it (which may even be + a different version of XZ Embedded). TODO: Provide an easy way + to do this. + + Please don't create a shared library of XZ Embedded itself unless + it is fine to rebuild everything depending on that shared library + everytime you upgrade to a newer version of XZ Embedded. There are + no API or ABI stability guarantees between different versions of + XZ Embedded. + +Specifying the calling convention + + XZ_FUNC macro was included to support declaring functions with __init + in Linux. Outside Linux, it can be used to specify the calling + convention on systems that support multiple calling conventions. + For example, on Windows, you may make all functions use the stdcall + calling convention by defining XZ_FUNC=__stdcall when building and + using the functions from XZ Embedded. + diff --git a/archival/libunarchive/unxz/xz.h b/archival/libunarchive/unxz/xz.h new file mode 100644 index 000000000..82f16ee22 --- /dev/null +++ b/archival/libunarchive/unxz/xz.h @@ -0,0 +1,212 @@ +/* + * XZ decompressor + * + * Authors: Lasse Collin <lasse.collin@tukaani.org> + * Igor Pavlov <http://7-zip.org/> + * + * 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 <linux/stddef.h> +# include <linux/types.h> +#else +# include <stddef.h> +# include <stdint.h> +#endif + +#ifndef XZ_DEBUG_MSG +# define XZ_DEBUG_MSG(...) ((void)0) +#endif + +/* In Linux, this is used to make extern functions static when needed. */ +#ifndef XZ_EXTERN +# define XZ_EXTERN extern +#endif + +/* In Linux, this is used to mark the functions with __init when needed. */ +#ifndef XZ_FUNC +# define XZ_FUNC +#endif + +/** + * enum xz_ret - Return codes + * @XZ_OK: Everything is OK so far. More input or more output + * space is required to continue. + * @XZ_STREAM_END: Operation finished successfully. + * @XZ_MEMLIMIT_ERROR: Not enough memory was preallocated at decoder + * initialization time. + * @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_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 + * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for + * multi-call decoding, or special value of zero to indicate + * single-call decoding mode. + * + * If dict_max > 0, the decoder is initialized to work in multi-call mode. + * dict_max number of 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. + * + * LZMA2 dictionary is always 2^n bytes or 2^n + 2^(n-1) bytes (the latter + * sizes are less common in practice). In the kernel, dictionary sizes of + * 64 KiB, 128 KiB, 256 KiB, 512 KiB, and 1 MiB are probably the only + * reasonable values. + * + * If dict_max == 0, the decoder is initialized to work in single-call mode. + * In single-call mode, 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. It is enough that the + * output buffer is is big enough to hold the actual uncompressed data; it + * can be smaller than the dictionary size stored in the stream headers. + * + * On success, xz_dec_init() returns a pointer to struct xz_dec, which is + * ready to be used with xz_dec_run(). On error, xz_dec_init() returns NULL. + */ +XZ_EXTERN struct xz_dec * XZ_FUNC xz_dec_init(uint32_t dict_max); + +/** + * xz_dec_run() - Run the XZ decoder + * @s: Decoder state allocated using xz_dec_init() + * @b: Input and output buffers + * + * In multi-call mode, this function may return any of the values listed in + * enum xz_ret. + * + * In single-call mode, this function never returns XZ_OK. 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. + * + * NOTE: In single-call mode, the contents of the output buffer are undefined + * also after XZ_BUF_ERROR. This is 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_FUNC 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_FUNC 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_FUNC 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. + */ +#if !defined(__KERNEL__) || defined(XZ_INTERNAL_CRC32) +/* + * This must be called before any other xz_* function to initialize + * the CRC32 lookup table. + */ +#ifndef xz_crc32_init +XZ_EXTERN void XZ_FUNC xz_crc32_init(uint32_t *crc32_table); +#endif + +/* + * 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. + */ +#ifndef xz_crc32 +XZ_EXTERN uint32_t XZ_FUNC xz_crc32(uint32_t *crc32_table, + const uint8_t *buf, size_t size, uint32_t crc); +#endif +#endif +#endif diff --git a/archival/libunarchive/unxz/xz_config.h b/archival/libunarchive/unxz/xz_config.h new file mode 100644 index 000000000..3259815f0 --- /dev/null +++ b/archival/libunarchive/unxz/xz_config.h @@ -0,0 +1,119 @@ +/* + * Private includes and definitions for userspace use of XZ Embedded + * + * Author: Lasse Collin <lasse.collin@tukaani.org> + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_CONFIG_H +#define XZ_CONFIG_H + +/* Uncomment as needed to enable BCJ filter decoders. */ +/* #define XZ_DEC_X86 */ +/* #define XZ_DEC_POWERPC */ +/* #define XZ_DEC_IA64 */ +/* #define XZ_DEC_ARM */ +/* #define XZ_DEC_ARMTHUMB */ +/* #define XZ_DEC_SPARC */ + +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> + +#include "xz.h" + +#define kmalloc(size, flags) malloc(size) +#define kfree(ptr) free(ptr) +#define vmalloc(size) malloc(size) +#define vfree(ptr) free(ptr) + +#define memeq(a, b, size) (memcmp(a, b, size) == 0) +#define memzero(buf, size) memset(buf, 0, size) + +#define min(x, y) ((x) < (y) ? (x) : (y)) +#define min_t(type, x, y) min(x, y) + +/* + * Some functions have been marked with __always_inline to keep the + * performance reasonable even when the compiler is optimizing for + * small code size. You may be able to save a few bytes by #defining + * __always_inline to plain inline, but don't complain if the code + * becomes slow. + * + * NOTE: System headers on GNU/Linux may #define this macro already, + * so if you want to change it, it you need to #undef it first. + */ +#ifndef __always_inline +# ifdef __GNUC__ +# define __always_inline \ + inline __attribute__((__always_inline__)) +# else +# define __always_inline inline +# endif +#endif + +/* + * Some functions are marked to never be inlined to reduce stack usage. + * If you don't care about stack usage, you may want to modify this so + * that noinline_for_stack is #defined to be empty even when using GCC. + * Doing so may save a few bytes in binary size. + */ +#ifndef noinline_for_stack +# ifdef __GNUC__ +# define noinline_for_stack __attribute__((__noinline__)) +# else +# define noinline_for_stack +# endif +#endif + +/* Inline functions to access unaligned unsigned 32-bit integers */ +#ifndef get_unaligned_le32 +static inline uint32_t XZ_FUNC get_unaligned_le32(const uint8_t *buf) +{ + return (uint32_t)buf[0] + | ((uint32_t)buf[1] << 8) + | ((uint32_t)buf[2] << 16) + | ((uint32_t)buf[3] << 24); +} +#endif + +#ifndef get_unaligned_be32 +static inline uint32_t XZ_FUNC get_unaligned_be32(const uint8_t *buf) +{ + return (uint32_t)(buf[0] << 24) + | ((uint32_t)buf[1] << 16) + | ((uint32_t)buf[2] << 8) + | (uint32_t)buf[3]; +} +#endif + +#ifndef put_unaligned_le32 +static inline void XZ_FUNC put_unaligned_le32(uint32_t val, uint8_t *buf) +{ + buf[0] = (uint8_t)val; + buf[1] = (uint8_t)(val >> 8); + buf[2] = (uint8_t)(val >> 16); + buf[3] = (uint8_t)(val >> 24); +} +#endif + +#ifndef put_unaligned_be32 +static inline void XZ_FUNC put_unaligned_be32(uint32_t val, uint8_t *buf) +{ + buf[0] = (uint8_t)(val >> 24); + buf[1] = (uint8_t)(val >> 16); + buf[2] = (uint8_t)(val >> 8); + buf[3] = (uint8_t)val; +} +#endif + +/* + * Use get_unaligned_le32() also for aligned access for simplicity. On + * little endian systems, #define get_le32(ptr) (*(const uint32_t *)(ptr)) + * could save a few bytes in code size. + */ +#define get_le32 get_unaligned_le32 + +#endif diff --git a/archival/libunarchive/unxz/xz_dec_bcj.c b/archival/libunarchive/unxz/xz_dec_bcj.c new file mode 100644 index 000000000..d4b6ef751 --- /dev/null +++ b/archival/libunarchive/unxz/xz_dec_bcj.c @@ -0,0 +1,560 @@ +/* + * Branch/Call/Jump (BCJ) filter decoders + * + * Authors: Lasse Collin <lasse.collin@tukaani.org> + * Igor Pavlov <http://7-zip.org/> + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include "xz_private.h" + +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 macro used to test the most significant byte of a memory address + * in an x86 instruction. + */ +#define bcj_x86_test_msbyte(b) ((b) == 0x00 || (b) == 0xFF) + +static noinline_for_stack size_t XZ_FUNC 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 noinline_for_stack size_t XZ_FUNC 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 noinline_for_stack size_t XZ_FUNC 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 noinline_for_stack size_t XZ_FUNC 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 noinline_for_stack size_t XZ_FUNC 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 noinline_for_stack size_t XZ_FUNC 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 + +#ifdef XZ_DEC_BCJ +/* + * 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 XZ_FUNC 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; +} +#endif + +#ifdef XZ_DEC_BCJ +/* + * 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 XZ_FUNC 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_FUNC 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_FUNC 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_FUNC 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/archival/libunarchive/unxz/xz_dec_lzma2.c b/archival/libunarchive/unxz/xz_dec_lzma2.c new file mode 100644 index 000000000..890141b7c --- /dev/null +++ b/archival/libunarchive/unxz/xz_dec_lzma2.c @@ -0,0 +1,1157 @@ +/* + * LZMA2 decoder + * + * Authors: Lasse Collin <lasse.collin@tukaani.org> + * Igor Pavlov <http://7-zip.org/> + * + * 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 <= allocated + * + * 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; + + /* + * Amount of memory allocated for the dictionary. A special + * value of zero indicates that we are in single-call mode, + * where the output buffer works as the dictionary. + */ + uint32_t allocated; +}; + +/* 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 { + /* + * 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 */ + + /* Types of the most recently seen LZMA symbols */ + enum lzma_state state; + + /* Distances of latest four matches */ + uint32_t rep0; + uint32_t rep1; + uint32_t rep2; + uint32_t rep3; + + /* + * Length of a match. This is updated so that dict_repeat can + * be called again to finish repeating the whole match. + */ + uint32_t len; + + /* 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 xz_dec_lzma2 { + /* LZMA2 */ + struct { + /* 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; + } lzma2; + + /* + * 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; + + struct dictionary dict; + struct rc_dec rc; + struct lzma_dec lzma; +}; + +/************** + * 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 XZ_FUNC dict_reset(struct dictionary *dict, struct xz_buf *b) +{ + if (dict->allocated == 0) { + 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 XZ_FUNC 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 __always_inline bool XZ_FUNC 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 __always_inline uint32_t XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 (dict->allocated != 0) { + 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 XZ_FUNC dict_flush(struct dictionary *dict, struct xz_buf *b) +{ + size_t copy_size = dict->pos - dict->start; + + if (dict->allocated != 0) { + 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 __always_inline void XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC rc_is_finished(const struct rc_dec *rc) +{ + return rc->code == 0; +} + +/* Read the next input byte if needed. */ +static __always_inline void XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 * XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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_FUNC 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_FUNC xz_dec_lzma2_create(uint32_t dict_max) +{ + struct xz_dec_lzma2 *s; + + /* Maximum supported dictionary by this implementation is 3 GiB. */ + if (dict_max > ((uint32_t)3 << 30)) + return NULL; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + if (dict_max > 0) { + s->dict.buf = vmalloc(dict_max); + if (s->dict.buf == NULL) { + kfree(s); + return NULL; + } + } + + s->dict.allocated = dict_max; + + return s; +} + +XZ_EXTERN enum xz_ret XZ_FUNC 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) { + XZ_DEBUG_MSG("props:%d", props); + return XZ_OPTIONS_ERROR; + } + + s->dict.size = 2 + (props & 1); + s->dict.size <<= (props >> 1) + 11; + + if (s->dict.allocated > 0 && s->dict.allocated < s->dict.size) { +#ifdef XZ_REALLOC_DICT_BUF + s->dict.buf = XZ_REALLOC_DICT_BUF(s->dict.buf, s->dict.size); + if (!s->dict.buf) + return XZ_MEMLIMIT_ERROR; + s->dict.allocated = s->dict.size; +#else + return XZ_MEMLIMIT_ERROR; +#endif + } + + s->dict.end = s->dict.size; + + 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_FUNC xz_dec_lzma2_end(struct xz_dec_lzma2 *s) +{ + if (s->dict.allocated > 0) + vfree(s->dict.buf); + + kfree(s); +} diff --git a/archival/libunarchive/unxz/xz_dec_stream.c b/archival/libunarchive/unxz/xz_dec_stream.c new file mode 100644 index 000000000..e10c9413d --- /dev/null +++ b/archival/libunarchive/unxz/xz_dec_stream.c @@ -0,0 +1,787 @@ +/* + * .xz Stream decoder + * + * Author: Lasse Collin <lasse.collin@tukaani.org> + * + * 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; + + /* True if CRC32 is calculated from uncompressed data */ + uint8_t crc_type; + + /* True if we are operating in single-call mode. */ + bool single_call; + + /* + * 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 + + uint32_t crc32_table[256]; +}; + +/* + * 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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->crc_type == 0x01) + s->crc32 = xz_crc32(s->crc32_table, + 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; + if (s->crc_type == 0x01) + s->block.hash.unpadded += 4; + if (s->crc_type == 0x04) /* CRC64 */ + s->block.hash.unpadded += 8; + if (s->crc_type == 0x0A) /* SHA-256 */ + s->block.hash.unpadded += 32; + + s->block.hash.uncompressed += s->block.uncompressed; + s->block.hash.crc32 = xz_crc32(s->crc32_table, + (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 XZ_FUNC 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(s->crc32_table, 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 XZ_FUNC 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(s->crc32_table, + (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 XZ_FUNC 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; +} + +/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */ +static enum xz_ret XZ_FUNC 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->crc32_table, s->temp.buf + HEADER_MAGIC_SIZE, 2, 0) + != get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2)) + return XZ_DATA_ERROR; + + /* + * Decode the Stream Flags field. Of integrity checks, we support + * only none (Check ID = 0) and CRC32 (Check ID = 1). + */ + if (s->temp.buf[HEADER_MAGIC_SIZE] != 0 + || (s->temp.buf[HEADER_MAGIC_SIZE + 1] > 1 + && s->temp.buf[HEADER_MAGIC_SIZE + 1] != 0x04 + && s->temp.buf[HEADER_MAGIC_SIZE + 1] != 0x0A + ) + ) { + XZ_DEBUG_MSG("unsupported stream flags %x:%x", + s->temp.buf[HEADER_MAGIC_SIZE], + s->temp.buf[HEADER_MAGIC_SIZE+1]); + return XZ_OPTIONS_ERROR; + } + + s->crc_type = s->temp.buf[HEADER_MAGIC_SIZE + 1]; + + return XZ_OK; +} + +/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */ +static enum xz_ret XZ_FUNC 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->crc32_table, 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->crc_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 XZ_FUNC 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->crc32_table, 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 + { + XZ_DEBUG_MSG("s->temp.buf[1] & 0x3E/3F != 0"); + 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) { + XZ_DEBUG_MSG("temp.size - 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) { + XZ_DEBUG_MSG("size of properties != 0"); + 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) { + XZ_DEBUG_MSG("filter ID != 0x21"); + return XZ_OPTIONS_ERROR; + } + + /* Size of Properties = 1-byte Filter Properties */ + if (s->temp.buf[s->temp.pos++] != 0x01) { + XZ_DEBUG_MSG("size of properties != 1"); + 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) { + XZ_DEBUG_MSG("padding is not zero-filled"); + return XZ_OPTIONS_ERROR; + } + + s->temp.pos = 0; + s->block.compressed = 0; + s->block.uncompressed = 0; + + return XZ_OK; +} + +static enum xz_ret XZ_FUNC 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; + + ret = dec_stream_header(s); + if (ret != XZ_OK) + return ret; + + s->sequence = SEQ_BLOCK_START; + + 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->crc_type == 0x01) { + ret = crc32_validate(s, b); + if (ret != XZ_STREAM_END) + return ret; + } + + 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_FUNC xz_dec_run(struct xz_dec *s, struct xz_buf *b) +{ + size_t in_start; + size_t out_start; + enum xz_ret ret; + + if (s->single_call) + xz_dec_reset(s); + + in_start = b->in_pos; + out_start = b->out_pos; + ret = dec_main(s, b); + + if (s->single_call) { + 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_FUNC xz_dec_init(uint32_t dict_max) +{ + struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + s->single_call = dict_max == 0; + +#ifdef XZ_DEC_BCJ + s->bcj = xz_dec_bcj_create(s->single_call); + if (s->bcj == NULL) + goto error_bcj; +#endif + + s->lzma2 = xz_dec_lzma2_create(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_FUNC 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_FUNC 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/archival/libunarchive/unxz/xz_lzma2.h b/archival/libunarchive/unxz/xz_lzma2.h new file mode 100644 index 000000000..47f21afbc --- /dev/null +++ b/archival/libunarchive/unxz/xz_lzma2.h @@ -0,0 +1,204 @@ +/* + * LZMA2 definitions + * + * Authors: Lasse Collin <lasse.collin@tukaani.org> + * Igor Pavlov <http://7-zip.org/> + * + * 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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/archival/libunarchive/unxz/xz_private.h b/archival/libunarchive/unxz/xz_private.h new file mode 100644 index 000000000..9da8d7061 --- /dev/null +++ b/archival/libunarchive/unxz/xz_private.h @@ -0,0 +1,120 @@ +/* + * Private includes and definitions + * + * Author: Lasse Collin <lasse.collin@tukaani.org> + * + * 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__ + /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ +# ifndef XZ_PREBOOT +# include <linux/slab.h> +# include <linux/vmalloc.h> +# include <linux/string.h> +# define memeq(a, b, size) (memcmp(a, b, size) == 0) +# define memzero(buf, size) memset(buf, 0, size) +# endif +# include <asm/byteorder.h> +# include <asm/unaligned.h> +# define get_le32(p) le32_to_cpup((const uint32_t *)(p)) + /* XZ_IGNORE_KCONFIG may be defined only via decompress_unxz.c. */ +# ifndef XZ_IGNORE_KCONFIG +# 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 +# endif +# include <linux/xz.h> +#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 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_FUNC xz_dec_lzma2_create( + 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_FUNC 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_FUNC 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_FUNC 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_FUNC 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_FUNC 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_FUNC xz_dec_bcj_run(struct xz_dec_bcj *s, + struct xz_dec_lzma2 *lzma2, struct xz_buf *b); +#endif + +/* Free the memory allocated for the BCJ filters. */ +#define xz_dec_bcj_end(s) kfree(s) + +#endif diff --git a/archival/libunarchive/unxz/xz_stream.h b/archival/libunarchive/unxz/xz_stream.h new file mode 100644 index 000000000..efbe75ae3 --- /dev/null +++ b/archival/libunarchive/unxz/xz_stream.h @@ -0,0 +1,46 @@ +/* + * Definitions for handling the .xz file format + * + * Author: Lasse Collin <lasse.collin@tukaani.org> + * + * 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__) && !defined(XZ_INTERNAL_CRC32) +# include <linux/crc32.h> +# undef crc32 +# define xz_crc32(crc32_table, 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\0" +#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 to indicate that the value is unknown. + */ +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) + +#endif diff --git a/include/applets.h b/include/applets.h index a171c5449..d8a706b44 100644 --- a/include/applets.h +++ b/include/applets.h @@ -419,6 +419,7 @@ IF_UNCOMPRESS(APPLET(uncompress, _BB_DIR_BIN, _BB_SUID_DROP)) IF_UNEXPAND(APPLET_ODDNAME(unexpand, expand, _BB_DIR_USR_BIN, _BB_SUID_DROP, unexpand)) IF_UNIQ(APPLET(uniq, _BB_DIR_USR_BIN, _BB_SUID_DROP)) IF_UNIX2DOS(APPLET_ODDNAME(unix2dos, dos2unix, _BB_DIR_USR_BIN, _BB_SUID_DROP, unix2dos)) +IF_UNXZ(APPLET(unxz, _BB_DIR_USR_BIN, _BB_SUID_DROP)) IF_UNLZMA(APPLET(unlzma, _BB_DIR_USR_BIN, _BB_SUID_DROP)) IF_LZOP(APPLET_ODDNAME(unlzop, lzop, _BB_DIR_USR_BIN, _BB_SUID_DROP, unlzop)) IF_UNZIP(APPLET(unzip, _BB_DIR_USR_BIN, _BB_SUID_DROP)) @@ -439,6 +440,8 @@ IF_WHICH(APPLET(which, _BB_DIR_USR_BIN, _BB_SUID_DROP)) IF_WHO(APPLET(who, _BB_DIR_USR_BIN, _BB_SUID_DROP)) IF_WHOAMI(APPLET_NOFORK(whoami, whoami, _BB_DIR_USR_BIN, _BB_SUID_DROP, whoami)) IF_XARGS(APPLET_NOEXEC(xargs, xargs, _BB_DIR_USR_BIN, _BB_SUID_DROP, xargs)) +IF_UNXZ(APPLET_ODDNAME(xzcat, unxz, _BB_DIR_USR_BIN, _BB_SUID_DROP, xzcat)) +IF_XZ(APPLET_ODDNAME(xz, unxz, _BB_DIR_USR_BIN, _BB_SUID_DROP, xz)) IF_YES(APPLET_NOFORK(yes, yes, _BB_DIR_USR_BIN, _BB_SUID_DROP, yes)) IF_GUNZIP(APPLET_ODDNAME(zcat, gunzip, _BB_DIR_BIN, _BB_SUID_DROP, zcat)) IF_ZCIP(APPLET(zcip, _BB_DIR_SBIN, _BB_SUID_DROP)) diff --git a/include/unarchive.h b/include/unarchive.h index a834816ba..14cd98e24 100644 --- a/include/unarchive.h +++ b/include/unarchive.h @@ -143,6 +143,7 @@ typedef struct inflate_unzip_result { } inflate_unzip_result; IF_DESKTOP(long long) int inflate_unzip(inflate_unzip_result *res, off_t compr_size, int src_fd, int dst_fd) FAST_FUNC; +IF_DESKTOP(long long) int unpack_xz_stream_stdin(void) FAST_FUNC; /* lzma unpacker takes .lzma stream from offset 0 */ IF_DESKTOP(long long) int unpack_lzma_stream(int src_fd, int dst_fd) FAST_FUNC; /* the rest wants 2 first bytes already skipped by the caller */ diff --git a/include/usage.h b/include/usage.h index 3aa980cdc..a9c4c4294 100644 --- a/include/usage.h +++ b/include/usage.h @@ -269,6 +269,28 @@ #define lzcat_full_usage "\n\n" \ "Decompress to stdout" +#define unxz_trivial_usage \ + "[OPTIONS] [FILE]..." +#define unxz_full_usage "\n\n" \ + "Decompress FILE (or stdin)\n" \ + "\nOptions:" \ + "\n -c Write to stdout" \ + "\n -f Force" \ + +#define xz_trivial_usage \ + "-d [OPTIONS] [FILE]..." +#define xz_full_usage "\n\n" \ + "Decompress FILE (or stdin)\n" \ + "\nOptions:" \ + "\n -d Decompress" \ + "\n -c Write to stdout" \ + "\n -f Force" \ + +#define xzcat_trivial_usage \ + "FILE" +#define xzcat_full_usage "\n\n" \ + "Decompress to stdout" + #define cal_trivial_usage \ "[-jy] [[MONTH] YEAR]" #define cal_full_usage "\n\n" \ |