2018-08-09 22:37:38 +02:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* In Linux, this is used to make extern functions static when needed. */
|
|
|
|
#ifndef XZ_EXTERN
|
|
|
|
# define XZ_EXTERN extern
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/**
|
|
|
|
* enum xz_mode - Operation mode
|
|
|
|
*
|
|
|
|
* @XZ_SINGLE: Single-call mode. This uses less RAM than
|
|
|
|
* than multi-call modes, because the LZMA2
|
|
|
|
* dictionary doesn't need to be allocated as
|
|
|
|
* part of the decoder state. All required data
|
|
|
|
* structures are allocated at initialization,
|
|
|
|
* so xz_dec_run() cannot return XZ_MEM_ERROR.
|
|
|
|
* @XZ_PREALLOC: Multi-call mode with preallocated LZMA2
|
|
|
|
* dictionary buffer. All data structures are
|
|
|
|
* allocated at initialization, so xz_dec_run()
|
|
|
|
* cannot return XZ_MEM_ERROR.
|
|
|
|
* @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is
|
|
|
|
* allocated once the required size has been
|
|
|
|
* parsed from the stream headers. If the
|
|
|
|
* allocation fails, xz_dec_run() will return
|
|
|
|
* XZ_MEM_ERROR.
|
|
|
|
*
|
|
|
|
* It is possible to enable support only for a subset of the above
|
|
|
|
* modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC,
|
|
|
|
* or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled
|
|
|
|
* with support for all operation modes, but the preboot code may
|
|
|
|
* be built with fewer features to minimize code size.
|
|
|
|
*/
|
|
|
|
enum xz_mode {
|
2020-12-31 07:11:24 +01:00
|
|
|
XZ_SINGLE,
|
|
|
|
XZ_PREALLOC,
|
|
|
|
XZ_DYNALLOC
|
2018-08-09 22:37:38 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* enum xz_ret - Return codes
|
|
|
|
* @XZ_OK: Everything is OK so far. More input or more
|
|
|
|
* output space is required to continue. This
|
|
|
|
* return code is possible only in multi-call mode
|
|
|
|
* (XZ_PREALLOC or XZ_DYNALLOC).
|
|
|
|
* @XZ_STREAM_END: Operation finished successfully.
|
|
|
|
* @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding
|
|
|
|
* is still possible in multi-call mode by simply
|
|
|
|
* calling xz_dec_run() again.
|
|
|
|
* Note that this return value is used only if
|
|
|
|
* XZ_DEC_ANY_CHECK was defined at build time,
|
|
|
|
* which is not used in the kernel. Unsupported
|
|
|
|
* check types return XZ_OPTIONS_ERROR if
|
|
|
|
* XZ_DEC_ANY_CHECK was not defined at build time.
|
|
|
|
* @XZ_MEM_ERROR: Allocating memory failed. This return code is
|
|
|
|
* possible only if the decoder was initialized
|
|
|
|
* with XZ_DYNALLOC. The amount of memory that was
|
|
|
|
* tried to be allocated was no more than the
|
|
|
|
* dict_max argument given to xz_dec_init().
|
|
|
|
* @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than
|
|
|
|
* allowed by the dict_max argument given to
|
|
|
|
* xz_dec_init(). This return value is possible
|
|
|
|
* only in multi-call mode (XZ_PREALLOC or
|
|
|
|
* XZ_DYNALLOC); the single-call mode (XZ_SINGLE)
|
|
|
|
* ignores the dict_max argument.
|
|
|
|
* @XZ_FORMAT_ERROR: File format was not recognized (wrong magic
|
|
|
|
* bytes).
|
|
|
|
* @XZ_OPTIONS_ERROR: This implementation doesn't support the requested
|
|
|
|
* compression options. In the decoder this means
|
|
|
|
* that the header CRC32 matches, but the header
|
|
|
|
* itself specifies something that we don't support.
|
|
|
|
* @XZ_DATA_ERROR: Compressed data is corrupt.
|
|
|
|
* @XZ_BUF_ERROR: Cannot make any progress. Details are slightly
|
|
|
|
* different between multi-call and single-call
|
|
|
|
* mode; more information below.
|
|
|
|
*
|
|
|
|
* In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls
|
|
|
|
* to XZ code cannot consume any input and cannot produce any new output.
|
|
|
|
* This happens when there is no new input available, or the output buffer
|
|
|
|
* is full while at least one output byte is still pending. Assuming your
|
|
|
|
* code is not buggy, you can get this error only when decoding a compressed
|
|
|
|
* stream that is truncated or otherwise corrupt.
|
|
|
|
*
|
|
|
|
* In single-call mode, XZ_BUF_ERROR is returned only when the output buffer
|
|
|
|
* is too small or the compressed input is corrupt in a way that makes the
|
|
|
|
* decoder produce more output than the caller expected. When it is
|
|
|
|
* (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR
|
|
|
|
* is used instead of XZ_BUF_ERROR.
|
|
|
|
*/
|
|
|
|
enum xz_ret {
|
2020-12-31 07:11:24 +01:00
|
|
|
XZ_OK,
|
|
|
|
XZ_STREAM_END,
|
|
|
|
XZ_UNSUPPORTED_CHECK,
|
|
|
|
XZ_MEM_ERROR,
|
|
|
|
XZ_MEMLIMIT_ERROR,
|
|
|
|
XZ_FORMAT_ERROR,
|
|
|
|
XZ_OPTIONS_ERROR,
|
|
|
|
XZ_DATA_ERROR,
|
|
|
|
XZ_BUF_ERROR
|
2018-08-09 22:37:38 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* 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 {
|
2020-12-31 07:11:24 +01:00
|
|
|
const uint8_t *in;
|
|
|
|
size_t in_pos;
|
|
|
|
size_t in_size;
|
2018-08-09 22:37:38 +02:00
|
|
|
|
2020-12-31 07:11:24 +01:00
|
|
|
uint8_t *out;
|
|
|
|
size_t out_pos;
|
|
|
|
size_t out_size;
|
2018-08-09 22:37:38 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct xz_dec - Opaque type to hold the XZ decoder state
|
|
|
|
*/
|
|
|
|
struct xz_dec;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xz_dec_init() - Allocate and initialize a XZ decoder state
|
|
|
|
* @mode: Operation mode
|
|
|
|
* @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for
|
|
|
|
* multi-call decoding. This is ignored in single-call mode
|
|
|
|
* (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes
|
|
|
|
* or 2^n + 2^(n-1) bytes (the latter sizes are less common
|
|
|
|
* in practice), so other values for dict_max don't make sense.
|
|
|
|
* In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB,
|
|
|
|
* 512 KiB, and 1 MiB are probably the only reasonable values,
|
|
|
|
* except for kernel and initramfs images where a bigger
|
|
|
|
* dictionary can be fine and useful.
|
|
|
|
*
|
|
|
|
* Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at
|
|
|
|
* once. The caller must provide enough output space or the decoding will
|
|
|
|
* fail. The output space is used as the dictionary buffer, which is why
|
|
|
|
* there is no need to allocate the dictionary as part of the decoder's
|
|
|
|
* internal state.
|
|
|
|
*
|
|
|
|
* Because the output buffer is used as the workspace, streams encoded using
|
|
|
|
* a big dictionary are not a problem in single-call mode. It is enough that
|
|
|
|
* the output buffer is big enough to hold the actual uncompressed data; it
|
|
|
|
* can be smaller than the dictionary size stored in the stream headers.
|
|
|
|
*
|
|
|
|
* Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes
|
|
|
|
* of memory is preallocated for the LZMA2 dictionary. This way there is no
|
|
|
|
* risk that xz_dec_run() could run out of memory, since xz_dec_run() will
|
|
|
|
* never allocate any memory. Instead, if the preallocated dictionary is too
|
|
|
|
* small for decoding the given input stream, xz_dec_run() will return
|
|
|
|
* XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be
|
|
|
|
* decoded to avoid allocating excessive amount of memory for the dictionary.
|
|
|
|
*
|
|
|
|
* Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC):
|
|
|
|
* dict_max specifies the maximum allowed dictionary size that xz_dec_run()
|
|
|
|
* may allocate once it has parsed the dictionary size from the stream
|
|
|
|
* headers. This way excessive allocations can be avoided while still
|
|
|
|
* limiting the maximum memory usage to a sane value to prevent running the
|
|
|
|
* system out of memory when decompressing streams from untrusted sources.
|
|
|
|
*
|
|
|
|
* On success, xz_dec_init() returns a pointer to struct xz_dec, which is
|
|
|
|
* ready to be used with xz_dec_run(). If memory allocation fails,
|
|
|
|
* xz_dec_init() returns NULL.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xz_dec_run() - Run the XZ decoder
|
|
|
|
* @s: Decoder state allocated using xz_dec_init()
|
|
|
|
* @b: Input and output buffers
|
|
|
|
*
|
|
|
|
* The possible return values depend on build options and operation mode.
|
|
|
|
* See enum xz_ret for details.
|
|
|
|
*
|
|
|
|
* Note that if an error occurs in single-call mode (return value is not
|
|
|
|
* XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the
|
|
|
|
* contents of the output buffer from b->out[b->out_pos] onward are
|
|
|
|
* undefined. This is true even after XZ_BUF_ERROR, because with some filter
|
|
|
|
* chains, there may be a second pass over the output buffer, and this pass
|
|
|
|
* cannot be properly done if the output buffer is truncated. Thus, you
|
|
|
|
* cannot give the single-call decoder a too small buffer and then expect to
|
|
|
|
* get that amount valid data from the beginning of the stream. You must use
|
|
|
|
* the multi-call decoder if you don't want to uncompress the whole stream.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xz_dec_reset() - Reset an already allocated decoder state
|
|
|
|
* @s: Decoder state allocated using xz_dec_init()
|
|
|
|
*
|
|
|
|
* This function can be used to reset the multi-call decoder state without
|
|
|
|
* freeing and reallocating memory with xz_dec_end() and xz_dec_init().
|
|
|
|
*
|
|
|
|
* In single-call mode, xz_dec_reset() is always called in the beginning of
|
|
|
|
* xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in
|
|
|
|
* multi-call mode.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN void xz_dec_reset(struct xz_dec *s);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xz_dec_end() - Free the memory allocated for the decoder state
|
|
|
|
* @s: Decoder state allocated using xz_dec_init(). If s is NULL,
|
|
|
|
* this function does nothing.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN void xz_dec_end(struct xz_dec *s);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Standalone build (userspace build or in-kernel build for boot time use)
|
|
|
|
* needs a CRC32 implementation. For normal in-kernel use, kernel's own
|
|
|
|
* CRC32 module is used instead, and users of this module don't need to
|
|
|
|
* care about the functions below.
|
|
|
|
*/
|
|
|
|
#ifndef XZ_INTERNAL_CRC32
|
|
|
|
# ifdef __KERNEL__
|
|
|
|
# define XZ_INTERNAL_CRC32 0
|
|
|
|
# else
|
|
|
|
# define XZ_INTERNAL_CRC32 1
|
|
|
|
# endif
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If CRC64 support has been enabled with XZ_USE_CRC64, a CRC64
|
|
|
|
* implementation is needed too.
|
|
|
|
*/
|
|
|
|
#ifndef XZ_USE_CRC64
|
|
|
|
# undef XZ_INTERNAL_CRC64
|
|
|
|
# define XZ_INTERNAL_CRC64 0
|
|
|
|
#endif
|
|
|
|
#ifndef XZ_INTERNAL_CRC64
|
|
|
|
# ifdef __KERNEL__
|
|
|
|
# error Using CRC64 in the kernel has not been implemented.
|
|
|
|
# else
|
|
|
|
# define XZ_INTERNAL_CRC64 1
|
|
|
|
# endif
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#if XZ_INTERNAL_CRC32
|
|
|
|
/*
|
|
|
|
* This must be called before any other xz_* function to initialize
|
|
|
|
* the CRC32 lookup table.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN void xz_crc32_init(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update CRC32 value using the polynomial from IEEE-802.3. To start a new
|
|
|
|
* calculation, the third argument must be zero. To continue the calculation,
|
|
|
|
* the previously returned value is passed as the third argument.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#if XZ_INTERNAL_CRC64
|
|
|
|
/*
|
|
|
|
* This must be called before any other xz_* function (except xz_crc32_init())
|
|
|
|
* to initialize the CRC64 lookup table.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN void xz_crc64_init(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update CRC64 value using the polynomial from ECMA-182. To start a new
|
|
|
|
* calculation, the third argument must be zero. To continue the calculation,
|
|
|
|
* the previously returned value is passed as the third argument.
|
|
|
|
*/
|
|
|
|
XZ_EXTERN uint64_t xz_crc64(const uint8_t *buf, size_t size, uint64_t crc);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#endif
|