Use xz-embedded for b64xz

build.py

@@ -300,11 +300,11 @@ def gen_update_binary():
 	binary = os.path.join('native', 'out', 'armeabi-v7a', 'busybox')
 	with open(binary, 'rb') as busybox:
 		update_bin.append('\'\nBB_ARM=')
-		update_bin.append(base64.b64encode(lzma.compress(busybox.read(), preset=9)).decode('ascii'))
+		update_bin.append(base64.b64encode(lzma.compress(busybox.read(), preset=9, check=lzma.CHECK_NONE)).decode('ascii'))
 	binary = os.path.join('native', 'out', 'x86', 'busybox')
 	with open(binary, 'rb') as busybox:
 		update_bin.append('\nBB_X86=')
-		update_bin.append(base64.b64encode(lzma.compress(busybox.read(), preset=9)).decode('ascii'))
+		update_bin.append(base64.b64encode(lzma.compress(busybox.read(), preset=9, check=lzma.CHECK_NONE)).decode('ascii'))
 		update_bin.append('\n')
 	with open(os.path.join('scripts', 'update_binary.sh'), 'r') as script:
 		update_bin.append(script.read())

native/build.gradle

@@ -14,7 +14,7 @@ android {
         externalNativeBuild {
             ndkBuild {
                 // Pass arguments to ndk-build.
-                arguments('B_MAGISK=1', 'B_INIT=1', 'B_BOOT=1', 'MAGISK_VERSION=debug',
+                arguments('B_MAGISK=1', 'B_INIT=1', 'B_BOOT=1', 'B_BXZ=1', 'MAGISK_VERSION=debug',
                         'MAGISK_VER_CODE=99999', 'MAGISK_DEBUG=-DMAGISK_DEBUG')
             }
         }

native/jni/Android.mk

@@ -73,8 +73,7 @@ LOCAL_C_INCLUDES := \
 	jni/magiskpolicy \
 	out \
 	out/$(TARGET_ARCH_ABI) \
-	$(LIBSEPOL) \
+	$(LIBSEPOL)
-	$(LIBLZMA)
 
 LOCAL_SRC_FILES := \
 	core/magiskinit.c \
@@ -126,8 +125,8 @@ ifdef B_BXZ
 # b64xz
 include $(CLEAR_VARS)
 LOCAL_MODULE := b64xz
-LOCAL_STATIC_LIBRARIES := liblzma
+LOCAL_STATIC_LIBRARIES := libxz
-LOCAL_C_INCLUDES := $(LIBLZMA)
+LOCAL_C_INCLUDES := $(EXT_PATH)/include
 LOCAL_SRC_FILES := b64xz.c
 LOCAL_LDFLAGS := -static
 include $(BUILD_EXECUTABLE)

native/jni/b64xz.c

@@ -1,21 +1,17 @@
 /* b64xz.c - Base64-XZ Extractor
  *
- * This program expects data from stdin. The data should be compressed with xz and
+ * This program converts data from stdin to stdout.
- * then encoded into base64 format. What b64xz does is basically the reverse of the
+ * The input should be compressed with xz (integrity check only support CRC32 or none) and then
- * mentioned process: decode base64 to uint8_ts, decompress xz, then dump to stdout
+ * encoded into base64 format. What b64xz does is basically the reverse of the
+ * mentioned process: decode base64 to bytes, decompress xz, then dump to stdout
  *
  * The compiled binary will be hex-dumped into update-binary
  * Busybox will be xz-compressed, base64 encoded and dumped into update-binary
  * This program is to recover busybox for Magisk installation environment
- *
- * I intentionally removed stdio. This will result in a smaller binary size because
- * all I/O are handled by system calls (read/write) instead of libc wrappers
  */
 
 #include <unistd.h>
-#include <lzma.h>
+#include <xz.h>
-
-#define BUFSIZE 8192
 
 static const char trans_tbl[] =
 		"|$$$}rstuvwxyz{$$$$$$$>?@ABCDEFGHIJKLMNOPQRSTUVW$$$$$$XYZ[\\]^_`abcdefghijklmnopq";
@@ -26,37 +22,39 @@ static void decodeblock(uint8_t* in, uint8_t* out) {
 	out[2] = (uint8_t)(((in[2] << 6) & 0xc0) | in[3]);
 }
 
-static int unxz(lzma_stream *strm, void *buf, size_t size) {
+static int unxz(struct xz_dec *dec, void *buf, unsigned size) {
-	lzma_ret ret = 0;
+	uint8_t out[8192];
-	uint8_t out[BUFSIZE];
+	struct xz_buf b = {
-	strm->next_in = buf;
+			.in = buf,
-	strm->avail_in = size;
+			.in_pos = 0,
+			.in_size = size,
+			.out = out,
+			.out_pos = 0,
+			.out_size = sizeof(out)
+	};
+	enum xz_ret ret;
 	do {
-		strm->next_out = out;
+		ret = xz_dec_run(dec, &b);
-		strm->avail_out = sizeof(out);
+		if (ret != XZ_OK && ret != XZ_STREAM_END)
-		ret = lzma_code(strm, LZMA_RUN);
+			return 1;
-		write(STDOUT_FILENO, out, sizeof(out) - strm->avail_out);
+		write(STDOUT_FILENO, out, b.out_pos);
-	} while (strm->avail_out == 0 && ret == LZMA_OK);
+		b.out_pos = 0;
-
+	} while (b.in_pos != size);
-	if (ret != LZMA_OK && ret != LZMA_STREAM_END)
+	return 0;
-		write(STDERR_FILENO, "LZMA error!\n", 13);
-	return ret;
 }
 
 int main(int argc, char const* argv[]) {
 	if (argc > 1)
 		return 0;
 
-	uint8_t in[4], buf[BUFSIZE];
+	uint8_t in[4], buf[6144];
-	int len = 0, pos = 0;
+	unsigned len = 0, pos = 0;
 	char c;
 
-	// Setup lzma stream
+	xz_crc32_init();
-	lzma_stream strm = LZMA_STREAM_INIT;
+	struct xz_dec *dec = xz_dec_init(XZ_DYNALLOC, 1 << 26);
-	if (lzma_auto_decoder(&strm, UINT64_MAX, 0) != LZMA_OK) {
+	if (dec == NULL)
-		write(STDERR_FILENO, "Unable to init lzma stream\n", 28);
 		return 1;
-	}
 
 	while (read(STDIN_FILENO, &c, sizeof(c)) == 1) {
 		c = ((c < 43 || c > 122) ? -1 : (trans_tbl[c - 43] == '$' ? -1 : trans_tbl[c - 43] - 62));
@@ -67,17 +65,14 @@ int main(int argc, char const* argv[]) {
 		len = 0;
 		decodeblock(in, buf + pos);
 		pos += 3;
-		if (pos > sizeof(buf) - 3) {
+		if (pos == sizeof(buf)) {
-			// Buffer is full, unxz
+			if (unxz(dec, buf, pos))
-			if (unxz(&strm, buf, pos))
 				return 1;
 			pos = 0;
 		}
 	}
-	if (pos) {
+	if (pos && unxz(dec, buf, pos))
-		if (unxz(&strm, buf, pos))
+		return 1;
-			return 1;
+	xz_dec_end(dec);
-	}
-	lzma_end(&strm);
 	return 0;
 }

native/jni/external/Android.mk

@@ -14,6 +14,16 @@ LOCAL_C_INCLUDES := $(LIBSELINUX)
 LOCAL_SRC_FILES := stubs/selinux_stub.c
 include $(BUILD_SHARED_LIBRARY)
 
+# libxz.a
+include $(CLEAR_VARS)
+LOCAL_MODULE:= libxz
+LOCAL_C_INCLUDES := $(EXT_PATH)/include
+LOCAL_SRC_FILES := \
+	xz-embedded/xz_crc32.c \
+	xz-embedded/xz_dec_lzma2.c \
+	xz-embedded/xz_dec_stream.c
+include $(BUILD_STATIC_LIBRARY)
+
 # libmincrypt.a
 include $(CLEAR_VARS)
 LOCAL_MODULE:= libmincrypt

native/jni/external/include/xz.h

@@ -0,0 +1,304 @@
+/*
+ * 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 {
+	XZ_SINGLE,
+	XZ_PREALLOC,
+	XZ_DYNALLOC
+};
+
+/**
+ * enum xz_ret - Return codes
+ * @XZ_OK:                  Everything is OK so far. More input or more
+ *                          output space is required to continue. This
+ *                          return code is possible only in multi-call mode
+ *                          (XZ_PREALLOC or XZ_DYNALLOC).
+ * @XZ_STREAM_END:          Operation finished successfully.
+ * @XZ_UNSUPPORTED_CHECK:   Integrity check type is not supported. Decoding
+ *                          is still possible in multi-call mode by simply
+ *                          calling xz_dec_run() again.
+ *                          Note that this return value is used only if
+ *                          XZ_DEC_ANY_CHECK was defined at build time,
+ *                          which is not used in the kernel. Unsupported
+ *                          check types return XZ_OPTIONS_ERROR if
+ *                          XZ_DEC_ANY_CHECK was not defined at build time.
+ * @XZ_MEM_ERROR:           Allocating memory failed. This return code is
+ *                          possible only if the decoder was initialized
+ *                          with XZ_DYNALLOC. The amount of memory that was
+ *                          tried to be allocated was no more than the
+ *                          dict_max argument given to xz_dec_init().
+ * @XZ_MEMLIMIT_ERROR:      A bigger LZMA2 dictionary would be needed than
+ *                          allowed by the dict_max argument given to
+ *                          xz_dec_init(). This return value is possible
+ *                          only in multi-call mode (XZ_PREALLOC or
+ *                          XZ_DYNALLOC); the single-call mode (XZ_SINGLE)
+ *                          ignores the dict_max argument.
+ * @XZ_FORMAT_ERROR:        File format was not recognized (wrong magic
+ *                          bytes).
+ * @XZ_OPTIONS_ERROR:       This implementation doesn't support the requested
+ *                          compression options. In the decoder this means
+ *                          that the header CRC32 matches, but the header
+ *                          itself specifies something that we don't support.
+ * @XZ_DATA_ERROR:          Compressed data is corrupt.
+ * @XZ_BUF_ERROR:           Cannot make any progress. Details are slightly
+ *                          different between multi-call and single-call
+ *                          mode; more information below.
+ *
+ * In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls
+ * to XZ code cannot consume any input and cannot produce any new output.
+ * This happens when there is no new input available, or the output buffer
+ * is full while at least one output byte is still pending. Assuming your
+ * code is not buggy, you can get this error only when decoding a compressed
+ * stream that is truncated or otherwise corrupt.
+ *
+ * In single-call mode, XZ_BUF_ERROR is returned only when the output buffer
+ * is too small or the compressed input is corrupt in a way that makes the
+ * decoder produce more output than the caller expected. When it is
+ * (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR
+ * is used instead of XZ_BUF_ERROR.
+ */
+enum xz_ret {
+	XZ_OK,
+	XZ_STREAM_END,
+	XZ_UNSUPPORTED_CHECK,
+	XZ_MEM_ERROR,
+	XZ_MEMLIMIT_ERROR,
+	XZ_FORMAT_ERROR,
+	XZ_OPTIONS_ERROR,
+	XZ_DATA_ERROR,
+	XZ_BUF_ERROR
+};
+
+/**
+ * struct xz_buf - Passing input and output buffers to XZ code
+ * @in:         Beginning of the input buffer. This may be NULL if and only
+ *              if in_pos is equal to in_size.
+ * @in_pos:     Current position in the input buffer. This must not exceed
+ *              in_size.
+ * @in_size:    Size of the input buffer
+ * @out:        Beginning of the output buffer. This may be NULL if and only
+ *              if out_pos is equal to out_size.
+ * @out_pos:    Current position in the output buffer. This must not exceed
+ *              out_size.
+ * @out_size:   Size of the output buffer
+ *
+ * Only the contents of the output buffer from out[out_pos] onward, and
+ * the variables in_pos and out_pos are modified by the XZ code.
+ */
+struct xz_buf {
+	const uint8_t *in;
+	size_t in_pos;
+	size_t in_size;
+
+	uint8_t *out;
+	size_t out_pos;
+	size_t out_size;
+};
+
+/**
+ * struct xz_dec - Opaque type to hold the XZ decoder state
+ */
+struct xz_dec;
+
+/**
+ * xz_dec_init() - Allocate and initialize a XZ decoder state
+ * @mode:       Operation mode
+ * @dict_max:   Maximum size of the LZMA2 dictionary (history buffer) for
+ *              multi-call decoding. This is ignored in single-call mode
+ *              (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes
+ *              or 2^n + 2^(n-1) bytes (the latter sizes are less common
+ *              in practice), so other values for dict_max don't make sense.
+ *              In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB,
+ *              512 KiB, and 1 MiB are probably the only reasonable values,
+ *              except for kernel and initramfs images where a bigger
+ *              dictionary can be fine and useful.
+ *
+ * Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at
+ * once. The caller must provide enough output space or the decoding will
+ * fail. The output space is used as the dictionary buffer, which is why
+ * there is no need to allocate the dictionary as part of the decoder's
+ * internal state.
+ *
+ * Because the output buffer is used as the workspace, streams encoded using
+ * a big dictionary are not a problem in single-call mode. It is enough that
+ * the output buffer is big enough to hold the actual uncompressed data; it
+ * can be smaller than the dictionary size stored in the stream headers.
+ *
+ * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes
+ * of memory is preallocated for the LZMA2 dictionary. This way there is no
+ * risk that xz_dec_run() could run out of memory, since xz_dec_run() will
+ * never allocate any memory. Instead, if the preallocated dictionary is too
+ * small for decoding the given input stream, xz_dec_run() will return
+ * XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be
+ * decoded to avoid allocating excessive amount of memory for the dictionary.
+ *
+ * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC):
+ * dict_max specifies the maximum allowed dictionary size that xz_dec_run()
+ * may allocate once it has parsed the dictionary size from the stream
+ * headers. This way excessive allocations can be avoided while still
+ * limiting the maximum memory usage to a sane value to prevent running the
+ * system out of memory when decompressing streams from untrusted sources.
+ *
+ * On success, xz_dec_init() returns a pointer to struct xz_dec, which is
+ * ready to be used with xz_dec_run(). If memory allocation fails,
+ * xz_dec_init() returns NULL.
+ */
+XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max);
+
+/**
+ * xz_dec_run() - Run the XZ decoder
+ * @s:          Decoder state allocated using xz_dec_init()
+ * @b:          Input and output buffers
+ *
+ * The possible return values depend on build options and operation mode.
+ * See enum xz_ret for details.
+ *
+ * Note that if an error occurs in single-call mode (return value is not
+ * XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the
+ * contents of the output buffer from b->out[b->out_pos] onward are
+ * undefined. This is true even after XZ_BUF_ERROR, because with some filter
+ * chains, there may be a second pass over the output buffer, and this pass
+ * cannot be properly done if the output buffer is truncated. Thus, you
+ * cannot give the single-call decoder a too small buffer and then expect to
+ * get that amount valid data from the beginning of the stream. You must use
+ * the multi-call decoder if you don't want to uncompress the whole stream.
+ */
+XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b);
+
+/**
+ * xz_dec_reset() - Reset an already allocated decoder state
+ * @s:          Decoder state allocated using xz_dec_init()
+ *
+ * This function can be used to reset the multi-call decoder state without
+ * freeing and reallocating memory with xz_dec_end() and xz_dec_init().
+ *
+ * In single-call mode, xz_dec_reset() is always called in the beginning of
+ * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in
+ * multi-call mode.
+ */
+XZ_EXTERN void xz_dec_reset(struct xz_dec *s);
+
+/**
+ * xz_dec_end() - Free the memory allocated for the decoder state
+ * @s:          Decoder state allocated using xz_dec_init(). If s is NULL,
+ *              this function does nothing.
+ */
+XZ_EXTERN void xz_dec_end(struct xz_dec *s);
+
+/*
+ * Standalone build (userspace build or in-kernel build for boot time use)
+ * needs a CRC32 implementation. For normal in-kernel use, kernel's own
+ * CRC32 module is used instead, and users of this module don't need to
+ * care about the functions below.
+ */
+#ifndef XZ_INTERNAL_CRC32
+#	ifdef __KERNEL__
+#		define XZ_INTERNAL_CRC32 0
+#	else
+#		define XZ_INTERNAL_CRC32 1
+#	endif
+#endif
+
+/*
+ * If 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

native/jni/external/xz-embedded/xz_config.h

@@ -0,0 +1,124 @@
+/*
+ * 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 to enable CRC64 support. */
+/* #define XZ_USE_CRC64 */
+
+/* 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 */
+
+/*
+ * MSVC doesn't support modern C but XZ Embedded is mostly C89
+ * so these are enough.
+ */
+#ifdef _MSC_VER
+typedef unsigned char bool;
+#	define true 1
+#	define false 0
+#	define inline __inline
+#else
+#	include <stdbool.h>
+#endif
+
+#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)
+
+#ifndef min
+#	define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#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, 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
+
+/* Inline functions to access unaligned unsigned 32-bit integers */
+#ifndef get_unaligned_le32
+static inline uint32_t 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 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 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 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.
+ */
+#ifndef get_le32
+#	define get_le32 get_unaligned_le32
+#endif
+
+#endif

native/jni/external/xz-embedded/xz_crc32.c

@@ -0,0 +1,59 @@
+/*
+ * CRC32 using the polynomial from IEEE-802.3
+ *
+ * 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.
+ */
+
+/*
+ * This is not the fastest implementation, but it is pretty compact.
+ * The fastest versions of xz_crc32() on modern CPUs without hardware
+ * accelerated CRC instruction are 3-5 times as fast as this version,
+ * but they are bigger and use more memory for the lookup table.
+ */
+
+#include "xz_private.h"
+
+/*
+ * STATIC_RW_DATA is used in the pre-boot environment on some architectures.
+ * See <linux/decompress/mm.h> for details.
+ */
+#ifndef STATIC_RW_DATA
+#	define STATIC_RW_DATA static
+#endif
+
+STATIC_RW_DATA uint32_t xz_crc32_table[256];
+
+XZ_EXTERN void xz_crc32_init(void)
+{
+	const uint32_t poly = 0xEDB88320;
+
+	uint32_t i;
+	uint32_t j;
+	uint32_t r;
+
+	for (i = 0; i < 256; ++i) {
+		r = i;
+		for (j = 0; j < 8; ++j)
+			r = (r >> 1) ^ (poly & ~((r & 1) - 1));
+
+		xz_crc32_table[i] = r;
+	}
+
+	return;
+}
+
+XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc)
+{
+	crc = ~crc;
+
+	while (size != 0) {
+		crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
+		--size;
+	}
+
+	return ~crc;
+}

native/jni/external/xz-embedded/xz_dec_stream.c

@@ -0,0 +1,847 @@
+/*
+ * .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"
+
+#ifdef XZ_USE_CRC64
+#	define IS_CRC64(check_type) ((check_type) == XZ_CHECK_CRC64)
+#else
+#	define IS_CRC64(check_type) false
+#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,
+		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;
+
+#ifdef XZ_USE_CRC64
+	/* CRC32 or CRC64 value in Block or CRC32 value in Index */
+	uint64_t crc;
+#else
+	/* CRC32 value in Block or Index */
+	uint32_t crc;
+#endif
+
+	/* Type of the integrity check calculated from uncompressed data */
+	enum xz_check check_type;
+
+	/* Operation mode */
+	enum xz_mode mode;
+
+	/*
+	 * True if the next call to xz_dec_run() is allowed to return
+	 * XZ_BUF_ERROR.
+	 */
+	bool allow_buf_error;
+
+	/* Information stored in Block Header */
+	struct {
+		/*
+		 * Value stored in the Compressed Size field, or
+		 * VLI_UNKNOWN if Compressed Size is not present.
+		 */
+		vli_type compressed;
+
+		/*
+		 * Value stored in the Uncompressed Size field, or
+		 * VLI_UNKNOWN if Uncompressed Size is not present.
+		 */
+		vli_type uncompressed;
+
+		/* Size of the Block Header field */
+		uint32_t size;
+	} block_header;
+
+	/* Information collected when decoding Blocks */
+	struct {
+		/* Observed compressed size of the current Block */
+		vli_type compressed;
+
+		/* Observed uncompressed size of the current Block */
+		vli_type uncompressed;
+
+		/* Number of Blocks decoded so far */
+		vli_type count;
+
+		/*
+		 * Hash calculated from the Block sizes. This is used to
+		 * validate the Index field.
+		 */
+		struct xz_dec_hash hash;
+	} block;
+
+	/* Variables needed when verifying the Index field */
+	struct {
+		/* Position in dec_index() */
+		enum {
+			SEQ_INDEX_COUNT,
+			SEQ_INDEX_UNPADDED,
+			SEQ_INDEX_UNCOMPRESSED
+		} sequence;
+
+		/* Size of the Index in bytes */
+		vli_type size;
+
+		/* Number of Records (matches block.count in valid files) */
+		vli_type count;
+
+		/*
+		 * Hash calculated from the Records (matches block.hash in
+		 * valid files).
+		 */
+		struct xz_dec_hash hash;
+	} index;
+
+	/*
+	 * Temporary buffer needed to hold Stream Header, Block Header,
+	 * and Stream Footer. The Block Header is the biggest (1 KiB)
+	 * so we reserve space according to that. buf[] has to be aligned
+	 * to a multiple of four bytes; the size_t variables before it
+	 * should guarantee this.
+	 */
+	struct {
+		size_t pos;
+		size_t size;
+		uint8_t buf[1024];
+	} temp;
+
+	struct xz_dec_lzma2 *lzma2;
+
+#ifdef XZ_DEC_BCJ
+	struct xz_dec_bcj *bcj;
+	bool bcj_active;
+#endif
+};
+
+#ifdef XZ_DEC_ANY_CHECK
+/* Sizes of the Check field with different Check IDs */
+static const uint8_t check_sizes[16] = {
+	0,
+	4, 4, 4,
+	8, 8, 8,
+	16, 16, 16,
+	32, 32, 32,
+	64, 64, 64
+};
+#endif
+
+/*
+ * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller
+ * must have set s->temp.pos to indicate how much data we are supposed
+ * to copy into s->temp.buf. Return true once s->temp.pos has reached
+ * s->temp.size.
+ */
+static bool fill_temp(struct xz_dec *s, struct xz_buf *b)
+{
+	size_t copy_size = min_t(size_t,
+			b->in_size - b->in_pos, s->temp.size - s->temp.pos);
+
+	memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
+	b->in_pos += copy_size;
+	s->temp.pos += copy_size;
+
+	if (s->temp.pos == s->temp.size) {
+		s->temp.pos = 0;
+		return true;
+	}
+
+	return false;
+}
+
+/* Decode a variable-length integer (little-endian base-128 encoding) */
+static enum xz_ret dec_vli(struct xz_dec *s, const uint8_t *in,
+			   size_t *in_pos, size_t in_size)
+{
+	uint8_t byte;
+
+	if (s->pos == 0)
+		s->vli = 0;
+
+	while (*in_pos < in_size) {
+		byte = in[*in_pos];
+		++*in_pos;
+
+		s->vli |= (vli_type)(byte & 0x7F) << s->pos;
+
+		if ((byte & 0x80) == 0) {
+			/* Don't allow non-minimal encodings. */
+			if (byte == 0 && s->pos != 0)
+				return XZ_DATA_ERROR;
+
+			s->pos = 0;
+			return XZ_STREAM_END;
+		}
+
+		s->pos += 7;
+		if (s->pos == 7 * VLI_BYTES_MAX)
+			return XZ_DATA_ERROR;
+	}
+
+	return XZ_OK;
+}
+
+/*
+ * Decode the Compressed Data field from a Block. Update and validate
+ * the observed compressed and uncompressed sizes of the Block so that
+ * they don't exceed the values possibly stored in the Block Header
+ * (validation assumes that no integer overflow occurs, since vli_type
+ * is normally uint64_t). Update the CRC32 or CRC64 value if presence of
+ * the CRC32 or CRC64 field was indicated in Stream Header.
+ *
+ * Once the decoding is finished, validate that the observed sizes match
+ * the sizes possibly stored in the Block Header. Update the hash and
+ * Block count, which are later used to validate the Index field.
+ */
+static enum xz_ret dec_block(struct xz_dec *s, struct xz_buf *b)
+{
+	enum xz_ret ret;
+
+	s->in_start = b->in_pos;
+	s->out_start = b->out_pos;
+
+#ifdef XZ_DEC_BCJ
+	if (s->bcj_active)
+		ret = xz_dec_bcj_run(s->bcj, s->lzma2, b);
+	else
+#endif
+		ret = xz_dec_lzma2_run(s->lzma2, b);
+
+	s->block.compressed += b->in_pos - s->in_start;
+	s->block.uncompressed += b->out_pos - s->out_start;
+
+	/*
+	 * There is no need to separately check for VLI_UNKNOWN, since
+	 * the observed sizes are always smaller than VLI_UNKNOWN.
+	 */
+	if (s->block.compressed > s->block_header.compressed
+			|| s->block.uncompressed
+				> s->block_header.uncompressed)
+		return XZ_DATA_ERROR;
+
+	if (s->check_type == XZ_CHECK_CRC32)
+		s->crc = xz_crc32(b->out + s->out_start,
+				b->out_pos - s->out_start, s->crc);
+#ifdef XZ_USE_CRC64
+	else if (s->check_type == XZ_CHECK_CRC64)
+		s->crc = xz_crc64(b->out + s->out_start,
+				b->out_pos - s->out_start, s->crc);
+#endif
+
+	if (ret == XZ_STREAM_END) {
+		if (s->block_header.compressed != VLI_UNKNOWN
+				&& s->block_header.compressed
+					!= s->block.compressed)
+			return XZ_DATA_ERROR;
+
+		if (s->block_header.uncompressed != VLI_UNKNOWN
+				&& s->block_header.uncompressed
+					!= s->block.uncompressed)
+			return XZ_DATA_ERROR;
+
+		s->block.hash.unpadded += s->block_header.size
+				+ s->block.compressed;
+
+#ifdef XZ_DEC_ANY_CHECK
+		s->block.hash.unpadded += check_sizes[s->check_type];
+#else
+		if (s->check_type == XZ_CHECK_CRC32)
+			s->block.hash.unpadded += 4;
+		else if (IS_CRC64(s->check_type))
+			s->block.hash.unpadded += 8;
+#endif
+
+		s->block.hash.uncompressed += s->block.uncompressed;
+		s->block.hash.crc32 = xz_crc32(
+				(const uint8_t *)&s->block.hash,
+				sizeof(s->block.hash), s->block.hash.crc32);
+
+		++s->block.count;
+	}
+
+	return ret;
+}
+
+/* Update the Index size and the CRC32 value. */
+static void index_update(struct xz_dec *s, const struct xz_buf *b)
+{
+	size_t in_used = b->in_pos - s->in_start;
+	s->index.size += in_used;
+	s->crc = xz_crc32(b->in + s->in_start, in_used, s->crc);
+}
+
+/*
+ * Decode the Number of Records, Unpadded Size, and Uncompressed Size
+ * fields from the Index field. That is, Index Padding and CRC32 are not
+ * decoded by this function.
+ *
+ * This can return XZ_OK (more input needed), XZ_STREAM_END (everything
+ * successfully decoded), or XZ_DATA_ERROR (input is corrupt).
+ */
+static enum xz_ret dec_index(struct xz_dec *s, struct xz_buf *b)
+{
+	enum xz_ret ret;
+
+	do {
+		ret = dec_vli(s, b->in, &b->in_pos, b->in_size);
+		if (ret != XZ_STREAM_END) {
+			index_update(s, b);
+			return ret;
+		}
+
+		switch (s->index.sequence) {
+		case SEQ_INDEX_COUNT:
+			s->index.count = s->vli;
+
+			/*
+			 * Validate that the Number of Records field
+			 * indicates the same number of Records as
+			 * there were Blocks in the Stream.
+			 */
+			if (s->index.count != s->block.count)
+				return XZ_DATA_ERROR;
+
+			s->index.sequence = SEQ_INDEX_UNPADDED;
+			break;
+
+		case SEQ_INDEX_UNPADDED:
+			s->index.hash.unpadded += s->vli;
+			s->index.sequence = SEQ_INDEX_UNCOMPRESSED;
+			break;
+
+		case SEQ_INDEX_UNCOMPRESSED:
+			s->index.hash.uncompressed += s->vli;
+			s->index.hash.crc32 = xz_crc32(
+					(const uint8_t *)&s->index.hash,
+					sizeof(s->index.hash),
+					s->index.hash.crc32);
+			--s->index.count;
+			s->index.sequence = SEQ_INDEX_UNPADDED;
+			break;
+		}
+	} while (s->index.count > 0);
+
+	return XZ_STREAM_END;
+}
+
+/*
+ * Validate that the next four or eight input bytes match the value
+ * of s->crc. s->pos must be zero when starting to validate the first byte.
+ * The "bits" argument allows using the same code for both CRC32 and CRC64.
+ */
+static enum xz_ret crc_validate(struct xz_dec *s, struct xz_buf *b,
+				uint32_t bits)
+{
+	do {
+		if (b->in_pos == b->in_size)
+			return XZ_OK;
+
+		if (((s->crc >> s->pos) & 0xFF) != b->in[b->in_pos++])
+			return XZ_DATA_ERROR;
+
+		s->pos += 8;
+
+	} while (s->pos < bits);
+
+	s->crc = 0;
+	s->pos = 0;
+
+	return XZ_STREAM_END;
+}
+
+#ifdef XZ_DEC_ANY_CHECK
+/*
+ * Skip over the Check field when the Check ID is not supported.
+ * Returns true once the whole Check field has been skipped over.
+ */
+static bool check_skip(struct xz_dec *s, struct xz_buf *b)
+{
+	while (s->pos < check_sizes[s->check_type]) {
+		if (b->in_pos == b->in_size)
+			return false;
+
+		++b->in_pos;
+		++s->pos;
+	}
+
+	s->pos = 0;
+
+	return true;
+}
+#endif
+
+/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */
+static enum xz_ret dec_stream_header(struct xz_dec *s)
+{
+	if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE))
+		return XZ_FORMAT_ERROR;
+
+	if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0)
+			!= get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2))
+		return XZ_DATA_ERROR;
+
+	if (s->temp.buf[HEADER_MAGIC_SIZE] != 0)
+		return XZ_OPTIONS_ERROR;
+
+	/*
+	 * Of integrity checks, we support none (Check ID = 0),
+	 * CRC32 (Check ID = 1), and optionally CRC64 (Check ID = 4).
+	 * However, if XZ_DEC_ANY_CHECK is defined, we will accept other
+	 * check types too, but then the check won't be verified and
+	 * a warning (XZ_UNSUPPORTED_CHECK) will be given.
+	 */
+	s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1];
+
+#ifdef XZ_DEC_ANY_CHECK
+	if (s->check_type > XZ_CHECK_MAX)
+		return XZ_OPTIONS_ERROR;
+
+	if (s->check_type > XZ_CHECK_CRC32 && !IS_CRC64(s->check_type))
+		return XZ_UNSUPPORTED_CHECK;
+#else
+	if (s->check_type > XZ_CHECK_CRC32 && !IS_CRC64(s->check_type))
+		return XZ_OPTIONS_ERROR;
+#endif
+
+	return XZ_OK;
+}
+
+/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */
+static enum xz_ret dec_stream_footer(struct xz_dec *s)
+{
+	if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE))
+		return XZ_DATA_ERROR;
+
+	if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf))
+		return XZ_DATA_ERROR;
+
+	/*
+	 * Validate Backward Size. Note that we never added the size of the
+	 * Index CRC32 field to s->index.size, thus we use s->index.size / 4
+	 * instead of s->index.size / 4 - 1.
+	 */
+	if ((s->index.size >> 2) != get_le32(s->temp.buf + 4))
+		return XZ_DATA_ERROR;
+
+	if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type)
+		return XZ_DATA_ERROR;
+
+	/*
+	 * Use XZ_STREAM_END instead of XZ_OK to be more convenient
+	 * for the caller.
+	 */
+	return XZ_STREAM_END;
+}
+
+/* Decode the Block Header and initialize the filter chain. */
+static enum xz_ret dec_block_header(struct xz_dec *s)
+{
+	enum xz_ret ret;
+
+	/*
+	 * Validate the CRC32. We know that the temp buffer is at least
+	 * eight bytes so this is safe.
+	 */
+	s->temp.size -= 4;
+	if (xz_crc32(s->temp.buf, s->temp.size, 0)
+			!= get_le32(s->temp.buf + s->temp.size))
+		return XZ_DATA_ERROR;
+
+	s->temp.pos = 2;
+
+	/*
+	 * Catch unsupported Block Flags. We support only one or two filters
+	 * in the chain, so we catch that with the same test.
+	 */
+#ifdef XZ_DEC_BCJ
+	if (s->temp.buf[1] & 0x3E)
+#else
+	if (s->temp.buf[1] & 0x3F)
+#endif
+		return XZ_OPTIONS_ERROR;
+
+	/* Compressed Size */
+	if (s->temp.buf[1] & 0x40) {
+		if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
+					!= XZ_STREAM_END)
+			return XZ_DATA_ERROR;
+
+		s->block_header.compressed = s->vli;
+	} else {
+		s->block_header.compressed = VLI_UNKNOWN;
+	}
+
+	/* Uncompressed Size */
+	if (s->temp.buf[1] & 0x80) {
+		if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
+				!= XZ_STREAM_END)
+			return XZ_DATA_ERROR;
+
+		s->block_header.uncompressed = s->vli;
+	} else {
+		s->block_header.uncompressed = VLI_UNKNOWN;
+	}
+
+#ifdef XZ_DEC_BCJ
+	/* If there are two filters, the first one must be a BCJ filter. */
+	s->bcj_active = s->temp.buf[1] & 0x01;
+	if (s->bcj_active) {
+		if (s->temp.size - s->temp.pos < 2)
+			return XZ_OPTIONS_ERROR;
+
+		ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]);
+		if (ret != XZ_OK)
+			return ret;
+
+		/*
+		 * We don't support custom start offset,
+		 * so Size of Properties must be zero.
+		 */
+		if (s->temp.buf[s->temp.pos++] != 0x00)
+			return XZ_OPTIONS_ERROR;
+	}
+#endif
+
+	/* Valid Filter Flags always take at least two bytes. */
+	if (s->temp.size - s->temp.pos < 2)
+		return XZ_DATA_ERROR;
+
+	/* Filter ID = LZMA2 */
+	if (s->temp.buf[s->temp.pos++] != 0x21)
+		return XZ_OPTIONS_ERROR;
+
+	/* Size of Properties = 1-byte Filter Properties */
+	if (s->temp.buf[s->temp.pos++] != 0x01)
+		return XZ_OPTIONS_ERROR;
+
+	/* Filter Properties contains LZMA2 dictionary size. */
+	if (s->temp.size - s->temp.pos < 1)
+		return XZ_DATA_ERROR;
+
+	ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]);
+	if (ret != XZ_OK)
+		return ret;
+
+	/* The rest must be Header Padding. */
+	while (s->temp.pos < s->temp.size)
+		if (s->temp.buf[s->temp.pos++] != 0x00)
+			return XZ_OPTIONS_ERROR;
+
+	s->temp.pos = 0;
+	s->block.compressed = 0;
+	s->block.uncompressed = 0;
+
+	return XZ_OK;
+}
+
+static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
+{
+	enum xz_ret ret;
+
+	/*
+	 * Store the start position for the case when we are in the middle
+	 * of the Index field.
+	 */
+	s->in_start = b->in_pos;
+
+	while (true) {
+		switch (s->sequence) {
+		case SEQ_STREAM_HEADER:
+			/*
+			 * Stream Header is copied to s->temp, and then
+			 * decoded from there. This way if the caller
+			 * gives us only little input at a time, we can
+			 * still keep the Stream Header decoding code
+			 * simple. Similar approach is used in many places
+			 * in this file.
+			 */
+			if (!fill_temp(s, b))
+				return XZ_OK;
+
+			/*
+			 * If dec_stream_header() returns
+			 * XZ_UNSUPPORTED_CHECK, it is still possible
+			 * to continue decoding if working in multi-call
+			 * mode. Thus, update s->sequence before calling
+			 * dec_stream_header().
+			 */
+			s->sequence = SEQ_BLOCK_START;
+
+			ret = dec_stream_header(s);
+			if (ret != XZ_OK)
+				return ret;
+
+		case SEQ_BLOCK_START:
+			/* We need one byte of input to continue. */
+			if (b->in_pos == b->in_size)
+				return XZ_OK;
+
+			/* See if this is the beginning of the Index field. */
+			if (b->in[b->in_pos] == 0) {
+				s->in_start = b->in_pos++;
+				s->sequence = SEQ_INDEX;
+				break;
+			}
+
+			/*
+			 * Calculate the size of the Block Header and
+			 * prepare to decode it.
+			 */
+			s->block_header.size
+				= ((uint32_t)b->in[b->in_pos] + 1) * 4;
+
+			s->temp.size = s->block_header.size;
+			s->temp.pos = 0;
+			s->sequence = SEQ_BLOCK_HEADER;
+
+		case SEQ_BLOCK_HEADER:
+			if (!fill_temp(s, b))
+				return XZ_OK;
+
+			ret = dec_block_header(s);
+			if (ret != XZ_OK)
+				return ret;
+
+			s->sequence = SEQ_BLOCK_UNCOMPRESS;
+
+		case SEQ_BLOCK_UNCOMPRESS:
+			ret = dec_block(s, b);
+			if (ret != XZ_STREAM_END)
+				return ret;
+
+			s->sequence = SEQ_BLOCK_PADDING;
+
+		case SEQ_BLOCK_PADDING:
+			/*
+			 * Size of Compressed Data + Block Padding
+			 * must be a multiple of four. We don't need
+			 * s->block.compressed for anything else
+			 * anymore, so we use it here to test the size
+			 * of the Block Padding field.
+			 */
+			while (s->block.compressed & 3) {
+				if (b->in_pos == b->in_size)
+					return XZ_OK;
+
+				if (b->in[b->in_pos++] != 0)
+					return XZ_DATA_ERROR;
+
+				++s->block.compressed;
+			}
+
+			s->sequence = SEQ_BLOCK_CHECK;
+
+		case SEQ_BLOCK_CHECK:
+			if (s->check_type == XZ_CHECK_CRC32) {
+				ret = crc_validate(s, b, 32);
+				if (ret != XZ_STREAM_END)
+					return ret;
+			}
+			else if (IS_CRC64(s->check_type)) {
+				ret = crc_validate(s, b, 64);
+				if (ret != XZ_STREAM_END)
+					return ret;
+			}
+#ifdef XZ_DEC_ANY_CHECK
+			else if (!check_skip(s, b)) {
+				return XZ_OK;
+			}
+#endif
+
+			s->sequence = SEQ_BLOCK_START;
+			break;
+
+		case SEQ_INDEX:
+			ret = dec_index(s, b);
+			if (ret != XZ_STREAM_END)
+				return ret;
+
+			s->sequence = SEQ_INDEX_PADDING;
+
+		case SEQ_INDEX_PADDING:
+			while ((s->index.size + (b->in_pos - s->in_start))
+					& 3) {
+				if (b->in_pos == b->in_size) {
+					index_update(s, b);
+					return XZ_OK;
+				}
+
+				if (b->in[b->in_pos++] != 0)
+					return XZ_DATA_ERROR;
+			}
+
+			/* Finish the CRC32 value and Index size. */
+			index_update(s, b);
+
+			/* Compare the hashes to validate the Index field. */
+			if (!memeq(&s->block.hash, &s->index.hash,
+					sizeof(s->block.hash)))
+				return XZ_DATA_ERROR;
+
+			s->sequence = SEQ_INDEX_CRC32;
+
+		case SEQ_INDEX_CRC32:
+			ret = crc_validate(s, b, 32);
+			if (ret != XZ_STREAM_END)
+				return ret;
+
+			s->temp.size = STREAM_HEADER_SIZE;
+			s->sequence = SEQ_STREAM_FOOTER;
+
+		case SEQ_STREAM_FOOTER:
+			if (!fill_temp(s, b))
+				return XZ_OK;
+
+			return dec_stream_footer(s);
+		}
+	}
+
+	/* Never reached */
+}
+
+/*
+ * xz_dec_run() is a wrapper for dec_main() to handle some special cases in
+ * multi-call and single-call decoding.
+ *
+ * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we
+ * are not going to make any progress anymore. This is to prevent the caller
+ * from calling us infinitely when the input file is truncated or otherwise
+ * corrupt. Since zlib-style API allows that the caller fills the input buffer
+ * only when the decoder doesn't produce any new output, we have to be careful
+ * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only
+ * after the second consecutive call to xz_dec_run() that makes no progress.
+ *
+ * In single-call mode, if we couldn't decode everything and no error
+ * occurred, either the input is truncated or the output buffer is too small.
+ * Since we know that the last input byte never produces any output, we know
+ * that if all the input was consumed and decoding wasn't finished, the file
+ * must be corrupt. Otherwise the output buffer has to be too small or the
+ * file is corrupt in a way that decoding it produces too big output.
+ *
+ * If single-call decoding fails, we reset b->in_pos and b->out_pos back to
+ * their original values. This is because with some filter chains there won't
+ * be any valid uncompressed data in the output buffer unless the decoding
+ * actually succeeds (that's the price to pay of using the output buffer as
+ * the workspace).
+ */
+XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b)
+{
+	size_t in_start;
+	size_t out_start;
+	enum xz_ret ret;
+
+	if (DEC_IS_SINGLE(s->mode))
+		xz_dec_reset(s);
+
+	in_start = b->in_pos;
+	out_start = b->out_pos;
+	ret = dec_main(s, b);
+
+	if (DEC_IS_SINGLE(s->mode)) {
+		if (ret == XZ_OK)
+			ret = b->in_pos == b->in_size
+					? XZ_DATA_ERROR : XZ_BUF_ERROR;
+
+		if (ret != XZ_STREAM_END) {
+			b->in_pos = in_start;
+			b->out_pos = out_start;
+		}
+
+	} else if (ret == XZ_OK && in_start == b->in_pos
+			&& out_start == b->out_pos) {
+		if (s->allow_buf_error)
+			ret = XZ_BUF_ERROR;
+
+		s->allow_buf_error = true;
+	} else {
+		s->allow_buf_error = false;
+	}
+
+	return ret;
+}
+
+XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max)
+{
+	struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (s == NULL)
+		return NULL;
+
+	s->mode = mode;
+
+#ifdef XZ_DEC_BCJ
+	s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode));
+	if (s->bcj == NULL)
+		goto error_bcj;
+#endif
+
+	s->lzma2 = xz_dec_lzma2_create(mode, dict_max);
+	if (s->lzma2 == NULL)
+		goto error_lzma2;
+
+	xz_dec_reset(s);
+	return s;
+
+error_lzma2:
+#ifdef XZ_DEC_BCJ
+	xz_dec_bcj_end(s->bcj);
+error_bcj:
+#endif
+	kfree(s);
+	return NULL;
+}
+
+XZ_EXTERN void xz_dec_reset(struct xz_dec *s)
+{
+	s->sequence = SEQ_STREAM_HEADER;
+	s->allow_buf_error = false;
+	s->pos = 0;
+	s->crc = 0;
+	memzero(&s->block, sizeof(s->block));
+	memzero(&s->index, sizeof(s->index));
+	s->temp.pos = 0;
+	s->temp.size = STREAM_HEADER_SIZE;
+}
+
+XZ_EXTERN void xz_dec_end(struct xz_dec *s)
+{
+	if (s != NULL) {
+		xz_dec_lzma2_end(s->lzma2);
+#ifdef XZ_DEC_BCJ
+		xz_dec_bcj_end(s->bcj);
+#endif
+		kfree(s);
+	}
+}

native/jni/external/xz-embedded/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 lzma_state_literal(enum lzma_state *state)
+{
+	if (*state <= STATE_SHORTREP_LIT_LIT)
+		*state = STATE_LIT_LIT;
+	else if (*state <= STATE_LIT_SHORTREP)
+		*state -= 3;
+	else
+		*state -= 6;
+}
+
+/* Indicate that the latest symbol was a match. */
+static inline void lzma_state_match(enum lzma_state *state)
+{
+	*state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH;
+}
+
+/* Indicate that the latest state was a long repeated match. */
+static inline void lzma_state_long_rep(enum lzma_state *state)
+{
+	*state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP;
+}
+
+/* Indicate that the latest symbol was a short match. */
+static inline void lzma_state_short_rep(enum lzma_state *state)
+{
+	*state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP;
+}
+
+/* Test if the previous symbol was a literal. */
+static inline bool lzma_state_is_literal(enum lzma_state state)
+{
+	return state < LIT_STATES;
+}
+
+/* Each literal coder is divided in three sections:
+ *   - 0x001-0x0FF: Without match byte
+ *   - 0x101-0x1FF: With match byte; match bit is 0
+ *   - 0x201-0x2FF: With match byte; match bit is 1
+ *
+ * Match byte is used when the previous LZMA symbol was something else than
+ * a literal (that is, it was some kind of match).
+ */
+#define LITERAL_CODER_SIZE 0x300
+
+/* Maximum number of literal coders */
+#define LITERAL_CODERS_MAX (1 << 4)
+
+/* Minimum length of a match is two bytes. */
+#define MATCH_LEN_MIN 2
+
+/* Match length is encoded with 4, 5, or 10 bits.
+ *
+ * Length   Bits
+ *  2-9      4 = Choice=0 + 3 bits
+ * 10-17     5 = Choice=1 + Choice2=0 + 3 bits
+ * 18-273   10 = Choice=1 + Choice2=1 + 8 bits
+ */
+#define LEN_LOW_BITS 3
+#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS)
+#define LEN_MID_BITS 3
+#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS)
+#define LEN_HIGH_BITS 8
+#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS)
+#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS)
+
+/*
+ * Maximum length of a match is 273 which is a result of the encoding
+ * described above.
+ */
+#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1)
+
+/*
+ * Different sets of probabilities are used for match distances that have
+ * very short match length: Lengths of 2, 3, and 4 bytes have a separate
+ * set of probabilities for each length. The matches with longer length
+ * use a shared set of probabilities.
+ */
+#define DIST_STATES 4
+
+/*
+ * Get the index of the appropriate probability array for decoding
+ * the distance slot.
+ */
+static inline uint32_t lzma_get_dist_state(uint32_t len)
+{
+	return len < DIST_STATES + MATCH_LEN_MIN
+			? len - MATCH_LEN_MIN : DIST_STATES - 1;
+}
+
+/*
+ * The highest two bits of a 32-bit match distance are encoded using six bits.
+ * This six-bit value is called a distance slot. This way encoding a 32-bit
+ * value takes 6-36 bits, larger values taking more bits.
+ */
+#define DIST_SLOT_BITS 6
+#define DIST_SLOTS (1 << DIST_SLOT_BITS)
+
+/* Match distances up to 127 are fully encoded using probabilities. Since
+ * the highest two bits (distance slot) are always encoded using six bits,
+ * the distances 0-3 don't need any additional bits to encode, since the
+ * distance slot itself is the same as the actual distance. DIST_MODEL_START
+ * indicates the first distance slot where at least one additional bit is
+ * needed.
+ */
+#define DIST_MODEL_START 4
+
+/*
+ * Match distances greater than 127 are encoded in three pieces:
+ *   - distance slot: the highest two bits
+ *   - direct bits: 2-26 bits below the highest two bits
+ *   - alignment bits: four lowest bits
+ *
+ * Direct bits don't use any probabilities.
+ *
+ * The distance slot value of 14 is for distances 128-191.
+ */
+#define DIST_MODEL_END 14
+
+/* Distance slots that indicate a distance <= 127. */
+#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2)
+#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS)
+
+/*
+ * For match distances greater than 127, only the highest two bits and the
+ * lowest four bits (alignment) is encoded using probabilities.
+ */
+#define ALIGN_BITS 4
+#define ALIGN_SIZE (1 << ALIGN_BITS)
+#define ALIGN_MASK (ALIGN_SIZE - 1)
+
+/* Total number of all probability variables */
+#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE)
+
+/*
+ * LZMA remembers the four most recent match distances. Reusing these
+ * distances tends to take less space than re-encoding the actual
+ * distance value.
+ */
+#define REPS 4
+
+#endif

native/jni/external/xz-embedded/xz_private.h

@@ -0,0 +1,156 @@
+/*
+ * 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__
+#	include <linux/xz.h>
+#	include <linux/kernel.h>
+#	include <asm/unaligned.h>
+	/* 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>
+#		ifdef CONFIG_XZ_DEC_X86
+#			define XZ_DEC_X86
+#		endif
+#		ifdef CONFIG_XZ_DEC_POWERPC
+#			define XZ_DEC_POWERPC
+#		endif
+#		ifdef CONFIG_XZ_DEC_IA64
+#			define XZ_DEC_IA64
+#		endif
+#		ifdef CONFIG_XZ_DEC_ARM
+#			define XZ_DEC_ARM
+#		endif
+#		ifdef CONFIG_XZ_DEC_ARMTHUMB
+#			define XZ_DEC_ARMTHUMB
+#		endif
+#		ifdef CONFIG_XZ_DEC_SPARC
+#			define XZ_DEC_SPARC
+#		endif
+#		define memeq(a, b, size) (memcmp(a, b, size) == 0)
+#		define memzero(buf, size) memset(buf, 0, size)
+#	endif
+#	define get_le32(p) le32_to_cpup((const uint32_t *)(p))
+#else
+	/*
+	 * For userspace builds, use a separate header to define the required
+	 * macros and functions. This makes it easier to adapt the code into
+	 * different environments and avoids clutter in the Linux kernel tree.
+	 */
+#	include "xz_config.h"
+#endif
+
+/* If no specific decoding mode is requested, enable support for all modes. */
+#if !defined(XZ_DEC_SINGLE) && !defined(XZ_DEC_PREALLOC) \
+		&& !defined(XZ_DEC_DYNALLOC)
+#	define XZ_DEC_SINGLE
+#	define XZ_DEC_PREALLOC
+#	define XZ_DEC_DYNALLOC
+#endif
+
+/*
+ * The DEC_IS_foo(mode) macros are used in "if" statements. If only some
+ * of the supported modes are enabled, these macros will evaluate to true or
+ * false at compile time and thus allow the compiler to omit unneeded code.
+ */
+#ifdef XZ_DEC_SINGLE
+#	define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
+#else
+#	define DEC_IS_SINGLE(mode) (false)
+#endif
+
+#ifdef XZ_DEC_PREALLOC
+#	define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC)
+#else
+#	define DEC_IS_PREALLOC(mode) (false)
+#endif
+
+#ifdef XZ_DEC_DYNALLOC
+#	define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC)
+#else
+#	define DEC_IS_DYNALLOC(mode) (false)
+#endif
+
+#if !defined(XZ_DEC_SINGLE)
+#	define DEC_IS_MULTI(mode) (true)
+#elif defined(XZ_DEC_PREALLOC) || defined(XZ_DEC_DYNALLOC)
+#	define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE)
+#else
+#	define DEC_IS_MULTI(mode) (false)
+#endif
+
+/*
+ * If any of the BCJ filter decoders are wanted, define XZ_DEC_BCJ.
+ * XZ_DEC_BCJ is used to enable generic support for BCJ decoders.
+ */
+#ifndef XZ_DEC_BCJ
+#	if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \
+			|| defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \
+			|| defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \
+			|| defined(XZ_DEC_SPARC)
+#		define XZ_DEC_BCJ
+#	endif
+#endif
+
+/*
+ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
+ * before calling xz_dec_lzma2_run().
+ */
+XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode,
+						   uint32_t dict_max);
+
+/*
+ * Decode the LZMA2 properties (one byte) and reset the decoder. Return
+ * XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not
+ * big enough, and XZ_OPTIONS_ERROR if props indicates something that this
+ * decoder doesn't support.
+ */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s,
+					 uint8_t props);
+
+/* Decode raw LZMA2 stream from b->in to b->out. */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
+				       struct xz_buf *b);
+
+/* Free the memory allocated for the LZMA2 decoder. */
+XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s);
+
+#ifdef XZ_DEC_BCJ
+/*
+ * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before
+ * calling xz_dec_bcj_run().
+ */
+XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call);
+
+/*
+ * Decode the Filter ID of a BCJ filter. This implementation doesn't
+ * support custom start offsets, so no decoding of Filter Properties
+ * is needed. Returns XZ_OK if the given Filter ID is supported.
+ * Otherwise XZ_OPTIONS_ERROR is returned.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id);
+
+/*
+ * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is
+ * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run()
+ * must be called directly.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
+				     struct xz_dec_lzma2 *lzma2,
+				     struct xz_buf *b);
+
+/* Free the memory allocated for the BCJ filters. */
+#define xz_dec_bcj_end(s) kfree(s)
+#endif
+
+#endif

native/jni/external/xz-embedded/xz_stream.h

@@ -0,0 +1,62 @@
+/*
+ * 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__) && !XZ_INTERNAL_CRC32
+#	include <linux/crc32.h>
+#	undef crc32
+#	define xz_crc32(buf, size, crc) \
+		(~crc32_le(~(uint32_t)(crc), buf, size))
+#endif
+
+/*
+ * See the .xz file format specification at
+ * http://tukaani.org/xz/xz-file-format.txt
+ * to understand the container format.
+ */
+
+#define STREAM_HEADER_SIZE 12
+
+#define HEADER_MAGIC "\3757zXZ"
+#define HEADER_MAGIC_SIZE 6
+
+#define FOOTER_MAGIC "YZ"
+#define FOOTER_MAGIC_SIZE 2
+
+/*
+ * Variable-length integer can hold a 63-bit unsigned integer or a special
+ * value indicating that the value is unknown.
+ *
+ * Experimental: vli_type can be defined to uint32_t to save a few bytes
+ * in code size (no effect on speed). Doing so limits the uncompressed and
+ * compressed size of the file to less than 256 MiB and may also weaken
+ * error detection slightly.
+ */
+typedef uint64_t vli_type;
+
+#define VLI_MAX ((vli_type)-1 / 2)
+#define VLI_UNKNOWN ((vli_type)-1)
+
+/* Maximum encoded size of a VLI */
+#define VLI_BYTES_MAX (sizeof(vli_type) * 8 / 7)
+
+/* Integrity Check types */
+enum xz_check {
+	XZ_CHECK_NONE = 0,
+	XZ_CHECK_CRC32 = 1,
+	XZ_CHECK_CRC64 = 4,
+	XZ_CHECK_SHA256 = 10
+};
+
+/* Maximum possible Check ID */
+#define XZ_CHECK_MAX 15
+
+#endif