From bcc4b36559e38e30afe6030c42ea4f369df94989 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Sun, 22 Mar 2009 13:12:47 +0200 Subject: Initial commit --- linux/Documentation/xz.txt | 84 ++++ linux/include/linux/xz.h | 199 ++++++++ linux/lib/xz/Kconfig | 7 + linux/lib/xz/Makefile | 2 + linux/lib/xz/xz_boot.c | 180 +++++++ linux/lib/xz/xz_crc32.c | 51 ++ linux/lib/xz/xz_dec_lzma2.c | 1124 ++++++++++++++++++++++++++++++++++++++++++ linux/lib/xz/xz_dec_stream.c | 758 ++++++++++++++++++++++++++++ linux/lib/xz/xz_dec_syms.c | 26 + linux/lib/xz/xz_lzma2.h | 204 ++++++++ linux/lib/xz/xz_private.h | 86 ++++ linux/lib/xz/xz_stream.h | 43 ++ 12 files changed, 2764 insertions(+) create mode 100644 linux/Documentation/xz.txt create mode 100644 linux/include/linux/xz.h create mode 100644 linux/lib/xz/Kconfig create mode 100644 linux/lib/xz/Makefile create mode 100644 linux/lib/xz/xz_boot.c create mode 100644 linux/lib/xz/xz_crc32.c create mode 100644 linux/lib/xz/xz_dec_lzma2.c create mode 100644 linux/lib/xz/xz_dec_stream.c create mode 100644 linux/lib/xz/xz_dec_syms.c create mode 100644 linux/lib/xz/xz_lzma2.h create mode 100644 linux/lib/xz/xz_private.h create mode 100644 linux/lib/xz/xz_stream.h (limited to 'linux') diff --git a/linux/Documentation/xz.txt b/linux/Documentation/xz.txt new file mode 100644 index 0000000..d0f91b2 --- /dev/null +++ b/linux/Documentation/xz.txt @@ -0,0 +1,84 @@ + +XZ data compression in Linux +============================ + + The xz_dec module provides XZ decoder which supports the LZMA2 + filter and CRC32 for integrity checking. The usage of the xz_dec + module is documented in include/linux/xz.h. + +Userspace tools + + XZ Utils include a zlib-like compression library and a gzip-like + command line tool. XZ Utils can be downloaded from + . From the same webiste, you can also + find latest development versions of the XZ code used in Linux, + and information how to use that code outside the Linux kernel too. + +Notes on compression options + + Since the XZ implementation in the kernel supports only streams with + no integrity check or CRC32, make sure that you don't use some other + integrity check type when encoding files that are supposed to be + decoded by the kernel. In liblzma, you need to use either + LZMA_CHECK_NONE or LZMA_CHECK_CRC32 when encoding. In the xz command + line tool, use --check=none or --check=crc32 (-Cnone and -Ccrc32 are + the short option counterparts). + + Using CRC32 is strongly recommended unless there is some other layer + which will verify the integrity of the uncompressed data anyway. + Double checking the integrity would probably be waste of CPU cycles, + so feel free to use LZMA_CHECK_NONE or --check=none. Note that the + headers will always have a CRC32 which will be validated by the + decoder; you can only change the integrity check type (or disable it) + for the actual uncompressed data. + + In userspace, LZMA2 is typically used with dictionary sizes of several + megabytes. The decoder needs to have the dictionary in RAM, thus big + dictionaries cannot be used for files that are intended to be decoded + by the kernel. 1 MiB is probably the maximum reasonable dictionary + size for in-kernel use. The presets in XZ Utils may not be optimal + when creating files for the kernel, so don't hesitate to use custom + settings. Example: + + xz --check=crc32 --lzma2=dict=128KiB,nice=273,depth=512 inputfile + + An exception to above dictionary size limitation is when the decoder + is used in single-call mode. Compressing the kernel itself and + initramfs are examples of this situation. In this case the memory + usage doesn't depend on the dictionary size, and it is perfectly fine + to use a big dictionary: for maximum compression, the dictionary + should be at least as big as the uncompressed data itself. + +Future plans + + Add support for BCJ (Branch/Call/Jump) filters for different + instruction sets. This could be useful both at boot and with + compressed file systems that store executables. BCJ filters are + small and improve the compression ratio a little, and have minimal + effect on performance. + + Creating a limited XZ encoder may be considered if people think it is + useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at + the fastest settings, so it isn't clear if LZMA2 encoder is wanted + into the kernel. + +Conformance to the .xz file format specification + + There are a couple of corner cases where things have been simplified + at expense of detecting errors as early as possible. These should not + matter in practice all, since they don't cause security issues. But + it is good to know this if testing the code e.g. with the test files + from XZ Utils. + +Reporting bugs + + Report bugs to or (preferably) visit + #tukaani on Freenode and talk to Larhzu. I don't actively read + LKML or other kernel-related mailing lists, so if there's something + I should know, you must email to me personally or use IRC. + + Don't bother Igor Pavlov with questions about the XZ implementation + in the kernel or about XZ Utils. While these two implementations + include essential code that is directly based on Igor Pavlov's code, + these implementations aren't maintained nor supported by him. + diff --git a/linux/include/linux/xz.h b/linux/include/linux/xz.h new file mode 100644 index 0000000..f851bde --- /dev/null +++ b/linux/include/linux/xz.h @@ -0,0 +1,199 @@ +/* + * XZ decompressor + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_H +#define XZ_H + +#ifdef __KERNEL__ +# include +# include +#else +# include +# include +#endif + +/* In Linux, this is used to 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. + */ +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. + */ +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. + */ +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. + */ +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. + */ +extern void XZ_FUNC xz_crc32_init(void); + +/* + * Update CRC32 value using the polynomial from IEEE-802.3. To start a new + * calculation, the third argument must be zero. To continue the calculation, + * the previously returned value is passed as the third argument. + */ +extern uint32_t XZ_FUNC xz_crc32( + const uint8_t *buf, size_t size, uint32_t crc); +#endif +#endif diff --git a/linux/lib/xz/Kconfig b/linux/lib/xz/Kconfig new file mode 100644 index 0000000..be2e2fa --- /dev/null +++ b/linux/lib/xz/Kconfig @@ -0,0 +1,7 @@ +config XZ_DEC + tristate "XZ decompression support" + select CRC32 + help + Currently this supports the LZMA2 compression algorithm and + CRC32 for integrity checking. Other algorithms may be added + later. See Documentation/xz.txt for more information. diff --git a/linux/lib/xz/Makefile b/linux/lib/xz/Makefile new file mode 100644 index 0000000..a9e358f --- /dev/null +++ b/linux/lib/xz/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_XZ_DEC) += xz_dec.o +xz_dec-objs := xz_dec_stream.o xz_dec_lzma2.o xz_dec_syms.o diff --git a/linux/lib/xz/xz_boot.c b/linux/lib/xz/xz_boot.c new file mode 100644 index 0000000..9a1adfb --- /dev/null +++ b/linux/lib/xz/xz_boot.c @@ -0,0 +1,180 @@ +/* + * XZ decoder as a single file for uncompressing the kernel and initramfs + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +/* + * Before #including this file, void error(char *) or void error(const char *) + * must have been declared. It is called from xz_dec_buf() if an error + * occurs; if error() returns, xz_dec_buf() will return false. On success, + * xz_dec_buf() returns true, but if error() would never return, there's no + * need to check the return value of xz_dec_buf(). + * + * In the early phase of boot where kmalloc, memmove, and friends are not + * available, you need to #define XZ_MEM_FUNCS before #including this file. + * Before calling xz_dec_buf, set malloc_buf to the beginning of a workspace + * buffer, and malloc_avail to the size of the workspace buffer. malloc_buf + * must be aligned to a multiple of 8 bytes. About 30 KiB of space is + * currently needed, but to be future-proof, having 40-50 KiB of space would + * be good. + * + * Example: + * + * static void error(const char *message); + * #define XZ_MEM_FUNCS + * #include "../../../../lib/xz/xz_boot.c" + * ... + * struct xz_buf b; + * b.in = (const uint8_t *)in_buf; + * b.in_pos = 0; + * b.in_size = in_buf_size; + * b.out = (uint8_t *)out_buf; + * b.out_pos = 0; + * b.out_size = out_buf_size_max; + * malloc_buf = (uint8_t *)free_mem_begin; + * malloc_avail = free_mem_avail; + * if (!xz_dec_buf(&b)) + * goto error_handler; + * + * If xz_dec_buf() succeeded (it returned true), the amount if input consumed + * is in b.in_pos and the amount of output used is in b.out_pos. + */ + +#if !defined(XZ_FUNC) && defined(INIT) +# define XZ_FUNC INIT +#endif +#define XZ_INTERNAL_CRC32 +#include "xz_private.h" + +#ifdef XZ_MEM_FUNCS +/* + * Very simple malloc, which just picks big enough chunk from a preallocated + * buffer. There's no free(), because the decoder is (at least for now) used + * only once per compilation unit. Thus, free() would be just waste of space. + */ +static uint8_t *malloc_buf; +static size_t malloc_avail; + +static void * XZ_FUNC malloc(size_t size) +{ + void *ptr = malloc_buf; + size = (size + 7) & ~(size_t)7; + if (size > malloc_avail) + return NULL; + + malloc_buf += size; + malloc_avail -= size; + return ptr; +} + +/* + * memeq and memzero are not used much and any remotely sane implementation + * is fast enough. memcpy/memmove speed matters in multi-call mode, but + * xz_dec_buf() uses only the single-call mode, in which only memcpy speed + * can matter and only if there is a lot of uncompressible data (LZMA2 stores + * uncompressible chunks in uncompressed form). Thus, the functions below + * should just be kept small; it's probably not worth optimizing for speed. + */ +static bool XZ_FUNC memeq(const void *a, const void *b, size_t size) +{ + const uint8_t *x = a; + const uint8_t *y = b; + size_t i; + + for (i = 0; i < size; ++i) + if (x[i] != y[i]) + return false; + + return true; +} + +static void XZ_FUNC memzero(void *buf, size_t size) +{ + uint8_t *b = buf; + uint8_t *e = b + size; + while (b != e) + *b++ = '\0'; +} + +static void * XZ_FUNC memmove(void *dest, const void *src, size_t size) +{ + uint8_t *d = dest; + const uint8_t *s = src; + size_t i; + + if (d < s) { + for (i = 0; i < size; ++i) + d[i] = s[i]; + } else if (d > s) { + i = size; + while (i-- > 0) + d[i] = s[i]; + } + + return dest; +} + +/* Since we need memmove anyway, use it as memcpy too. */ +#define memcpy memmove +#endif + +#include "xz_crc32.c" +#include "xz_dec_stream.c" +#include "xz_dec_lzma2.c" + +/** + * xz_dec_buf() - Single-call XZ decoder + * @b: Input and output buffers + * + * On success, true is returned. On error, error() is called and false is + * returned in case error() returns. + */ +static bool XZ_FUNC xz_dec_buf(struct xz_buf *b) +{ + struct xz_dec *s; + enum xz_ret ret; + + xz_crc32_init(); + + s = xz_dec_init(0); + if (s == NULL) { + error("XZ decoder ran out of memory"); + return false; + } + + ret = xz_dec_run(s, b); + xz_dec_end(s); + + switch (ret) { + case XZ_STREAM_END: + return true; + + case XZ_FORMAT_ERROR: + error("Input is not in the XZ format (wrong magic bytes)"); + break; + + case XZ_OPTIONS_ERROR: + error("Input was encoded with settings that are not " + "supported by this XZ decoder"); + break; + + case XZ_DATA_ERROR: + error("XZ-compressed data is corrupt"); + break; + + case XZ_BUF_ERROR: + error("Output buffer is too small or the " + "XZ-compressed data is corrupt"); + break; + + default: + error("Bug in the XZ decoder"); + break; + } + + return false; +} diff --git a/linux/lib/xz/xz_crc32.c b/linux/lib/xz/xz_crc32.c new file mode 100644 index 0000000..83d15fb --- /dev/null +++ b/linux/lib/xz/xz_crc32.c @@ -0,0 +1,51 @@ +/* + * CRC32 using the polynomial from IEEE-802.3 + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +/* + * This is not the fastest implementation, but it is pretty compact. + * The fastest versions of xz_crc32() on modern CPUs without hardware + * accelerated CRC instruction are 3-5 times as fast as this version, + * but they are bigger and use more memory for the lookup table. + */ + +#include "xz_private.h" + +static uint32_t xz_crc32_table[256]; + +void XZ_FUNC xz_crc32_init(void) +{ + const uint32_t poly = 0xEDB88320; + + uint32_t i; + uint32_t j; + uint32_t r; + + for (i = 0; i < 256; ++i) { + r = i; + for (j = 0; j < 8; ++j) + r = (r >> 1) ^ (poly & ~((r & 1) - 1)); + + xz_crc32_table[i] = r; + } + + return; +} + +uint32_t XZ_FUNC xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) +{ + crc = ~crc; + + while (size != 0) { + crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8); + --size; + } + + return ~crc; +} diff --git a/linux/lib/xz/xz_dec_lzma2.c b/linux/lib/xz/xz_dec_lzma2.c new file mode 100644 index 0000000..8cfa596 --- /dev/null +++ b/linux/lib/xz/xz_dec_lzma2.c @@ -0,0 +1,1124 @@ +/* + * LZMA2 decoder + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include "xz_private.h" +#include "xz_lzma2.h" + +/* + * Range decoder initialization eats the first five bytes of each LZMA chunk. + */ +#define RC_INIT_BYTES 5 + +/* + * Minimum number of usable input buffer to safely decode one LZMA symbol. + * The worst case is that we decode 22 bits using probabilities and 26 + * direct bits. This may decode at maximum of 20 bytes of input. However, + * lzma_main() does an extra normalization before returning, thus we + * need to put 21 here. + */ +#define LZMA_IN_REQUIRED 21 + +/* + * Dictionary (history buffer) + * + * These are always true: + * start <= pos <= full <= end + * pos <= limit <= end + * + * In multi-call mode, also these are true: + * end == size + * size <= 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 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 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 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 = props / (9 * 5); + props -= s->lzma.pos_mask * 9 * 5; + s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1; + + s->lzma.literal_pos_mask = props / 9; + s->lzma.lc = props - s->lzma.literal_pos_mask * 9; + + 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) { + 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. + */ +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; +} + +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; +} + +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) + return XZ_OPTIONS_ERROR; + + s->dict.size = 2 + (props & 1); + s->dict.size <<= props / 2 + 11; + + if (s->dict.allocated > 0 && s->dict.allocated < s->dict.size) + return XZ_MEMLIMIT_ERROR; + + 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; +} + + +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/linux/lib/xz/xz_dec_stream.c b/linux/lib/xz/xz_dec_stream.c new file mode 100644 index 0000000..cdc0d67 --- /dev/null +++ b/linux/lib/xz/xz_dec_stream.c @@ -0,0 +1,758 @@ +/* + * .xz Stream decoder + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include "xz_private.h" +#include "xz_stream.h" + +#ifdef __KERNEL__ +# include +# define read_le32(buf) le32_to_cpup((const uint32_t *)(buf)) +#else +static uint32_t XZ_FUNC read_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 + +/* 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_COUNT, + SEQ_INDEX_UNPADDED, + SEQ_INDEX_UNCOMPRESSED, + 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 */ + bool has_crc32; + + /* 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; + +#ifdef XZ_DEC_BCJ + /* Type of the BCJ filter */ + enum xz_bcj_type bcj_type; +#endif + } 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 { + /* 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; +#endif +}; + +/* Call the raw filter decoder chain. */ +static enum xz_ret XZ_FUNC xz_dec_raw(struct xz_dec *s, struct xz_buf *b) +{ +#ifdef XZ_DEC_BCJ + if (s->block_header.bcj_type != XZ_BCJ_NONE) + return xz_dec_bcj_run(s, b); +#endif + + return xz_dec_lzma2_run(s->lzma2, b); +} + +/* + * 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 |= (uint64_t)(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; + } + + if (s->pos >= 56) + return XZ_DATA_ERROR; + + s->pos += 7; + } + + return XZ_OK; +} + +/* 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(b->in + s->in_start, in_used, s->crc32); +} + +/* + * 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->temp.buf + HEADER_MAGIC_SIZE, 2, 0) + != read_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) + return XZ_OPTIONS_ERROR; + + s->has_crc32 = 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->temp.buf + 4, 6, 0) != read_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 / 4 != read_le32(s->temp.buf + 4)) + return XZ_DATA_ERROR; + + if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->has_crc32) + 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->temp.buf, s->temp.size, 0) + != read_le32(s->temp.buf + s->temp.size)) + return XZ_DATA_ERROR; + + s->temp.pos = 2; + + /* + * Catch unsupported Block Flags. We support only one or two filters + * in the chain, so we catch that with the same test. + */ +#ifdef XZ_DEC_BCJ + if (s->temp.buf[1] & 0x3E) +#else + if (s->temp.buf[1] & 0x3F) +#endif + return XZ_OPTIONS_ERROR; + + /* Compressed Size */ + if (s->temp.buf[1] & 0x40) { + if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) + != XZ_STREAM_END) + return XZ_DATA_ERROR; + + s->block_header.compressed = s->vli; + } else { + s->block_header.compressed = VLI_UNKNOWN; + } + + /* Uncompressed Size */ + if (s->temp.buf[1] & 0x80) { + if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) + != XZ_STREAM_END) + return XZ_DATA_ERROR; + + s->block_header.uncompressed = s->vli; + } else { + s->block_header.uncompressed = VLI_UNKNOWN; + } + +#ifdef XZ_DEC_BCJ + /* If there are two filters, the first one must be a BCJ filter. */ + if (s->temp.buf[1] & 0x01) { + if (s->temp.size - s->temp.pos < 2) + return XZ_OPTIONS_ERROR; + + switch (s->temp.buf[s->temp.pos]) { +#ifdef XZ_DEC_BCJ_X86 + case XZ_BCJ_X86: +#endif +#ifdef XZ_DEC_BCJ_POWERPC + case XZ_BCJ_POWERPC: +#endif +#ifdef XZ_DEC_BCJ_IA64 + case XZ_BCJ_IA64: +#endif +#ifdef XZ_DEC_BCJ_ARM + case XZ_BCJ_ARM: +#endif +#ifdef XZ_DEC_BCJ_ARMTHUMB + case XZ_BCJ_ARMTHUMB: +#endif +#ifdef XZ_DEC_BCJ_SPARC + case XZ_BCJ_SPARC: +#endif + break; + + default: + return XZ_OPTIONS_ERROR; + } + + s->block_header.bcj_type = s->temp.buf[s->temp.pos++]; + + /* + * We don't support custom start offset, + * so Size of Properties must be zero. + */ + if (s->temp.buf[s->temp.pos++] != 0x00) + return XZ_OPTIONS_ERROR; + + xz_dec_bcj_reset(s); + } else { + s->bcj.type = XZ_BCJ_NONE; + } +#endif + + /* Valid Filter Flags always take at least two bytes. */ + if (s->temp.size - s->temp.pos < 2) + return XZ_DATA_ERROR; + + /* Filter ID = LZMA2 */ + if (s->temp.buf[s->temp.pos++] != 0x21) + return XZ_OPTIONS_ERROR; + + /* Size of Properties = 1-byte Filter Properties */ + if (s->temp.buf[s->temp.pos++] != 0x01) + return XZ_OPTIONS_ERROR; + + /* Filter Properties contains LZMA2 dictionary size. */ + if (s->temp.size - s->temp.pos < 1) + return XZ_DATA_ERROR; + + ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]); + if (ret != XZ_OK) + return ret; + + /* The rest must be Header Padding. */ + while (s->temp.pos < s->temp.size) + if (s->temp.buf[s->temp.pos++] != 0x00) + return XZ_OPTIONS_ERROR; + + s->temp.pos = 0; + s->block.compressed = 0; + s->block.uncompressed = 0; + + return XZ_OK; +} + +static enum xz_ret 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 still 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_COUNT; + 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: + s->in_start = b->in_pos; + s->out_start = b->out_pos; + + ret = xz_dec_raw(s, b); + + s->block.compressed += b->in_pos - s->in_start; + s->block.uncompressed += b->out_pos - s->out_start; + + if (s->block.compressed > s->block_header.compressed + || s->block.uncompressed + > s->block_header.uncompressed) + return XZ_DATA_ERROR; + + if (s->has_crc32) + s->crc32 = xz_crc32(b->out + s->out_start, + b->out_pos - s->out_start, s->crc32); + + if (ret != XZ_STREAM_END) + return ret; + + /* + * If sizes were stored in Block Header, they must match + * the observed sizes now. + */ + 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; + + /* + * Update the hash and count, which are used for + * Index validation. + */ + s->block.hash.unpadded += s->block_header.size + + s->block.compressed; + if (s->has_crc32) + s->block.hash.unpadded += 4; + + s->block.hash.uncompressed += s->block.uncompressed; + s->block.hash.crc32 = xz_crc32( + (const uint8_t *)&s->block.hash, + sizeof(s->block.hash), s->block.hash.crc32); + + ++s->block.count; + 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->d->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->has_crc32) { + ret = crc32_validate(s, b); + if (ret != XZ_STREAM_END) + return ret; + } + + s->sequence = SEQ_BLOCK_START; + break; + + case SEQ_INDEX_COUNT: + case SEQ_INDEX_UNPADDED: + case SEQ_INDEX_UNCOMPRESSED: + 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->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->sequence = SEQ_INDEX_UNPADDED; + break; + + case SEQ_INDEX_UNPADDED: + s->index.hash.unpadded += s->vli; + s->sequence = SEQ_INDEX_UNCOMPRESSED; + break; + + case SEQ_INDEX_UNCOMPRESSED: + s->index.hash.uncompressed += s->vli; + s->index.hash.crc32 = xz_crc32( + (const uint8_t *)&s->index.hash, + sizeof(s->index.hash), + s->index.hash.crc32); + --s->index.count; + s->sequence = SEQ_INDEX_UNPADDED; + break; + + default: + /* Silence compiler warnings */ + break; + } + } while (s->index.count > 0); + + 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). + */ +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; +} + +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->lzma2 = xz_dec_lzma2_create(dict_max); + if (s->lzma2 == NULL) { + kfree(s); + return NULL; + } + + s->single_call = dict_max == 0; + xz_dec_reset(s); + return s; +} + +void XZ_FUNC xz_dec_reset(struct xz_dec *s) +{ + if (s != NULL) { + s->sequence = SEQ_STREAM_HEADER; + s->allow_buf_error = false; + s->pos = 0; + s->crc32 = 0; + + s->block.count = 0; + memzero(&s->block.hash, sizeof(s->block.hash)); + + s->index.size = 0; + memzero(&s->index.hash, sizeof(s->index.hash)); + + s->temp.pos = 0; + s->temp.size = STREAM_HEADER_SIZE; + } +} + +void XZ_FUNC xz_dec_end(struct xz_dec *s) +{ + if (s != NULL) { + xz_dec_lzma2_end(s->lzma2); + kfree(s); + } +} diff --git a/linux/lib/xz/xz_dec_syms.c b/linux/lib/xz/xz_dec_syms.c new file mode 100644 index 0000000..b9fefad --- /dev/null +++ b/linux/lib/xz/xz_dec_syms.c @@ -0,0 +1,26 @@ +/* + * XZ decoder module information + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include +#include + +EXPORT_SYMBOL(xz_dec_init); +EXPORT_SYMBOL(xz_dec_reset); +EXPORT_SYMBOL(xz_dec_run); +EXPORT_SYMBOL(xz_dec_end); + +MODULE_DESCRIPTION("XZ decompressor"); +MODULE_VERSION("0.1"); +MODULE_AUTHOR("Lasse Collin and Igor Pavlov"); + +/* + * This code is in the public domain, but in Linux it's simplest to just + * say it's GPL and consider the authors as the copyright holders. + */ +MODULE_LICENSE("GPL"); diff --git a/linux/lib/xz/xz_lzma2.h b/linux/lib/xz/xz_lzma2.h new file mode 100644 index 0000000..47f21af --- /dev/null +++ b/linux/lib/xz/xz_lzma2.h @@ -0,0 +1,204 @@ +/* + * LZMA2 definitions + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_LZMA2_H +#define XZ_LZMA2_H + +/* Range coder constants */ +#define RC_SHIFT_BITS 8 +#define RC_TOP_BITS 24 +#define RC_TOP_VALUE (1 << RC_TOP_BITS) +#define RC_BIT_MODEL_TOTAL_BITS 11 +#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS) +#define RC_MOVE_BITS 5 + +/* + * Maximum number of position states. A position state is the lowest pb + * number of bits of the current uncompressed offset. In some places there + * are different sets of probabilities for different position states. + */ +#define POS_STATES_MAX (1 << 4) + +/* + * This enum is used to track which LZMA symbols have occurred most recently + * and in which order. This information is used to predict the next symbol. + * + * Symbols: + * - Literal: One 8-bit byte + * - Match: Repeat a chunk of data at some distance + * - Long repeat: Multi-byte match at a recently seen distance + * - Short repeat: One-byte repeat at a recently seen distance + * + * The symbol names are in from STATE_oldest_older_previous. REP means + * either short or long repeated match, and NONLIT means any non-literal. + */ +enum lzma_state { + STATE_LIT_LIT, + STATE_MATCH_LIT_LIT, + STATE_REP_LIT_LIT, + STATE_SHORTREP_LIT_LIT, + STATE_MATCH_LIT, + STATE_REP_LIT, + STATE_SHORTREP_LIT, + STATE_LIT_MATCH, + STATE_LIT_LONGREP, + STATE_LIT_SHORTREP, + STATE_NONLIT_MATCH, + STATE_NONLIT_REP +}; + +/* Total number of states */ +#define STATES 12 + +/* The lowest 7 states indicate that the previous state was a literal. */ +#define LIT_STATES 7 + +/* Indicate that the latest symbol was a literal. */ +static inline void 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/linux/lib/xz/xz_private.h b/linux/lib/xz/xz_private.h new file mode 100644 index 0000000..bd47708 --- /dev/null +++ b/linux/lib/xz/xz_private.h @@ -0,0 +1,86 @@ +/* + * Private includes and definitions + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_PRIVATE_H +#define XZ_PRIVATE_H + +#ifdef __KERNEL__ +# ifndef XZ_MEM_FUNCS +# include +# include +# include +# endif +# include +#else +# ifndef XZ_MEM_FUNCS +# include +# include +# define kmalloc(size, flags) malloc(size) +# define kfree(ptr) free(ptr) +# define vmalloc(size) malloc(size) +# define vfree(ptr) free(ptr) +# endif +# include +# include "xz.h" +# define min(x, y) ((x) < (y) ? (x) : (y)) +# define min_t(type, x, y) min(x, y) +# ifndef __always_inline +# ifdef __GNUC__ +# define __always_inline \ + inline __attribute__((__always_inline__)) +# else +# define __always_inline inline +# endif +# endif +#endif + +#ifdef XZ_MEM_FUNCS +# define kmalloc(size, flags) malloc(size) +# define kfree(ptr) ((void)0) +# define vmalloc(size) malloc(size) +# define vfree(ptr) ((void)0) +#else +# define memeq(a, b, size) (memcmp(a, b, size) == 0) +# define memzero(buf, size) memset(buf, 0, size) +#endif + +/* + * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used + * before calling xz_dec_lzma2_run(). + */ +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. + */ +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. */ +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. */ +extern void XZ_FUNC xz_dec_lzma2_end(struct xz_dec_lzma2 *s); + +/* BCJ filter types (Branch/Jump/Call) */ +enum xz_bcj_type { + XZ_BCJ_NONE = 0, + XZ_BCJ_X86 = 4, + XZ_BCJ_POWERPC = 5, /* Big endian */ + XZ_BCJ_IA64 = 6, + XZ_BCJ_ARM = 7, /* Little endian */ + XZ_BCJ_ARMTHUMB = 8, /* Little endian */ + XZ_BCJ_SPARC = 9 +}; + +#endif diff --git a/linux/lib/xz/xz_stream.h b/linux/lib/xz/xz_stream.h new file mode 100644 index 0000000..de35e67 --- /dev/null +++ b/linux/lib/xz/xz_stream.h @@ -0,0 +1,43 @@ +/* + * Definitions for handling the .xz file format + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_STREAM_H +#define XZ_STREAM_H + +#if defined(__KERNEL__) && !defined(XZ_INTERNAL_CRC32) +# include +# undef crc32 +# define xz_crc32(buf, size, crc) \ + (~crc32_le(~(uint32_t)(crc), buf, size)) +#endif + +/* + * See the .xz file format specification at + * http://tukaani.org/xz/xz-file-format.txt + * to understand the container format. + */ + +#define STREAM_HEADER_SIZE 12 + +#define HEADER_MAGIC "\3757zXZ\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) + +#endif -- cgit v1.2.3