* [PATCH] support for xz compression
@ 2010-04-08 21:55 Szymon Janc
2010-04-11 19:30 ` Szymon Janc
2010-09-05 16:50 ` Vladimir 'φ-coder/phcoder' Serbinenko
0 siblings, 2 replies; 4+ messages in thread
From: Szymon Janc @ 2010-04-08 21:55 UTC (permalink / raw)
To: grub-devel
[-- Attachment #1: Type: Text/Plain, Size: 272 bytes --]
Hello,
New version with various fixes, most noticable : seek support, respect not
easly seekable flag, BCJ support.
This patch depends on 04_transparentio.diff from previous post.
Commenst and testing are welcome.
--
Szymon K. Janc
szymon@janc.net.pl // GG: 1383435
[-- Attachment #2: 05_gcrycrc32.diff --]
[-- Type: text/x-patch, Size: 887 bytes --]
=== modified file 'include/grub/crypto.h'
--- include/grub/crypto.h 2009-12-23 16:33:35 +0000
+++ include/grub/crypto.h 2010-04-06 21:02:23 +0000
@@ -243,10 +243,12 @@
extern gcry_md_spec_t _gcry_digest_spec_sha1;
extern gcry_md_spec_t _gcry_digest_spec_sha256;
extern gcry_md_spec_t _gcry_digest_spec_sha512;
+extern gcry_md_spec_t _gcry_digest_spec_crc32;
#define GRUB_MD_MD5 ((const gcry_md_spec_t *) &_gcry_digest_spec_md5)
#define GRUB_MD_SHA1 ((const gcry_md_spec_t *) &_gcry_digest_spec_sha1)
#define GRUB_MD_SHA256 ((const gcry_md_spec_t *) &_gcry_digest_spec_sha256)
#define GRUB_MD_SHA512 ((const gcry_md_spec_t *) &_gcry_digest_spec_sha512)
+#define GRUB_MD_CRC32 ((const gcry_md_spec_t *) &_gcry_digest_spec_crc32)
/* Implement PKCS#5 PBKDF2 as per RFC 2898. The PRF to use is HMAC variant
of digest supplied by MD. Inputs are the password P of length PLEN,
[-- Attachment #3: 06_posixwrap.diff --]
[-- Type: text/x-patch, Size: 526 bytes --]
=== modified file 'lib/posix_wrap/sys/types.h'
--- lib/posix_wrap/sys/types.h 2010-03-28 19:43:42 +0000
+++ lib/posix_wrap/sys/types.h 2010-04-06 22:04:30 +0000
@@ -23,10 +23,15 @@
typedef grub_size_t size_t;
typedef int bool;
-static const bool true = 1;
-static const bool false = 0;
+#define true 1
+#define false 0
#define ULONG_MAX GRUB_ULONG_MAX
#define UCHAR_MAX 0xff
+typedef grub_uint8_t uint8_t;
+typedef grub_uint16_t uint16_t;
+typedef grub_uint32_t uint32_t;
+typedef grub_uint64_t uint64_t;
+
#endif
[-- Attachment #4: 07_xzio.diff --]
[-- Type: text/x-patch, Size: 102017 bytes --]
=== modified file 'conf/common.rmk'
--- conf/common.rmk 2010-03-28 20:20:32 +0000
+++ conf/common.rmk 2010-04-06 20:48:49 +0000
@@ -727,7 +727,7 @@
# Misc.
-pkglib_MODULES += gzio.mod elf.mod
+pkglib_MODULES += gzio.mod xzio.mod elf.mod
# For elf.mod.
elf_mod_SOURCES = kern/elf.c
@@ -739,6 +739,11 @@
gzio_mod_CFLAGS = $(COMMON_CFLAGS)
gzio_mod_LDFLAGS = $(COMMON_LDFLAGS)
+# For xzio.mod.
+xzio_mod_SOURCES = io/xzio.c lib/xzembed/xz_dec_bcj.c lib/xzembed/xz_dec_lzma2.c lib/xzembed/xz_dec_stream.c
+xzio_mod_CFLAGS = $(COMMON_CFLAGS) -I$(srcdir)/lib/posix_wrap -I$(srcdir)/lib/xzembed
+xzio_mod_LDFLAGS = $(COMMON_LDFLAGS)
+
# On Yeeloong it's part of kernel
ifneq ($(platform), yeeloong)
# For bufio.mod.
=== modified file 'include/grub/file.h'
--- include/grub/file.h 2010-03-31 20:52:17 +0000
+++ include/grub/file.h 2010-04-06 21:55:17 +0000
@@ -55,7 +55,8 @@
/* IO filter priorities. */
typedef enum
{
- GRUB_IOFILTER_PRIO_GZIO = 0
+ GRUB_IOFILTER_PRIO_GZIO = 0,
+ GRUB_IOFILTER_PRIO_XZIO = 1
}
grub_io_filter_prio_t;
=== added file 'io/xzio.c'
--- io/xzio.c 1970-01-01 00:00:00 +0000
+++ io/xzio.c 2010-04-08 21:42:11 +0000
@@ -0,0 +1,373 @@
+/* xzio.c - decompression support for xz */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <grub/err.h>
+#include <grub/mm.h>
+#include <grub/misc.h>
+#include <grub/file.h>
+#include <grub/fs.h>
+#include <grub/dl.h>
+
+#include "xz.h"
+#include "xz_stream.h"
+
+#define XZBUFSIZ 0x2000
+#define VLI_MAX_DIGITS 9
+#define XZ_STREAM_FOOTER_SIZE 12
+
+struct grub_xzio
+{
+ grub_file_t file;
+ struct xz_buf buf;
+ struct xz_dec *dec;
+ grub_uint8_t inbuf[XZBUFSIZ];
+ grub_uint8_t outbuf[XZBUFSIZ];
+ grub_off_t saved_offset;
+};
+
+typedef struct grub_xzio *grub_xzio_t;
+static struct grub_fs grub_xzio_fs;
+
+static grub_size_t
+decode_vli (const grub_uint8_t buf[], grub_size_t size_max,
+ grub_uint64_t * num)
+{
+ if (size_max == 0)
+ return 0;
+
+ if (size_max > VLI_MAX_DIGITS)
+ size_max = VLI_MAX_DIGITS;
+
+ *num = buf[0] & 0x7F;
+ grub_size_t i = 0;
+
+ while (buf[i++] & 0x80)
+ {
+ if (i >= size_max || buf[i] == 0x00)
+ return 0;
+
+ *num |= (uint64_t) (buf[i] & 0x7F) << (i * 7);
+ }
+
+ return i;
+}
+
+static grub_ssize_t
+read_vli (grub_file_t file, grub_uint64_t * num)
+{
+ grub_uint8_t buf[VLI_MAX_DIGITS];
+ grub_ssize_t read;
+ grub_size_t dec;
+
+ read = grub_file_read (file, buf, VLI_MAX_DIGITS);
+ if (read < 0)
+ return -1;
+
+ dec = decode_vli (buf, read, num);
+ grub_file_seek (file, file->offset - (read - dec));
+ return dec;
+}
+
+/* Function xz_dec_run() should consume header and ask for more (XZ_OK)
+ * else file is corrupted (or options not supported) or not xz. */
+static int
+test_header (grub_file_t file)
+{
+ grub_xzio_t xzio = file->data;
+ xzio->buf.in_size = grub_file_read (xzio->file, xzio->inbuf,
+ STREAM_HEADER_SIZE);
+
+ if (xzio->buf.in_size != STREAM_HEADER_SIZE)
+ {
+ grub_error (GRUB_ERR_BAD_FILE_TYPE, "no xz magic found");
+ return 0;
+ }
+
+ enum xz_ret ret = xz_dec_run (xzio->dec, &xzio->buf);
+
+ if (ret == XZ_FORMAT_ERROR)
+ {
+ grub_error (GRUB_ERR_BAD_FILE_TYPE, "no xz magic found");
+ return 0;
+ }
+
+ if (ret != XZ_OK)
+ {
+ grub_error (GRUB_ERR_BAD_IOFILTER_DATA, "not supported xz options");
+ return 0;
+ }
+
+ return 1;
+}
+
+/* Try to find out size of uncompressed data,
+ * also do some footer sanity checks. */
+static int
+test_footer (grub_file_t file)
+{
+ grub_xzio_t xzio = file->data;
+ grub_uint8_t footer[FOOTER_MAGIC_SIZE];
+ grub_uint32_t backsize;
+ grub_uint8_t imarker;
+ grub_uint64_t uncompressed_size_total = 0;
+ grub_uint64_t uncompressed_size;
+ grub_uint64_t records;
+
+ grub_file_seek (xzio->file, xzio->file->size - FOOTER_MAGIC_SIZE);
+ if (grub_file_read (xzio->file, footer, FOOTER_MAGIC_SIZE) !=
+ FOOTER_MAGIC_SIZE
+ || grub_memcmp (footer, FOOTER_MAGIC, FOOTER_MAGIC_SIZE) != 0)
+ goto ERROR;
+
+ grub_file_seek (xzio->file, xzio->file->size - 8);
+ if (grub_file_read (xzio->file, &backsize, sizeof (backsize))
+ != sizeof (backsize))
+ goto ERROR;
+
+ /* Calculate real backward size. */
+ backsize = (grub_le_to_cpu32 (backsize) + 1) * 4;
+
+ /* Set file to the beginning of stream index. */
+ grub_file_seek (xzio->file,
+ xzio->file->size - XZ_STREAM_FOOTER_SIZE - backsize);
+
+ /* Test index marker. */
+ if (grub_file_read (xzio->file, &imarker, sizeof (imarker)) !=
+ sizeof (imarker) && imarker != 0x00)
+ goto ERROR;
+
+ if (read_vli (xzio->file, &records) <= 0)
+ goto ERROR;
+
+ for (; records != 0; records--)
+ {
+ if (read_vli (xzio->file, &uncompressed_size) <= 0) /* Ignore unpadded. */
+ goto ERROR;
+ if (read_vli (xzio->file, &uncompressed_size) <= 0) /* Uncompressed. */
+ goto ERROR;
+
+ uncompressed_size_total += uncompressed_size;
+ }
+
+ file->size = uncompressed_size_total;
+ grub_file_seek (xzio->file, STREAM_HEADER_SIZE);
+ return 1;
+
+ERROR:
+ grub_error (GRUB_ERR_BAD_IOFILTER_DATA, "bad footer magic");
+ return 0;
+}
+
+static grub_file_t
+grub_xzio_open (grub_file_t io)
+{
+ grub_file_t file;
+ grub_xzio_t xzio;
+
+ file = (grub_file_t) grub_zalloc (sizeof (*file));
+ if (!file)
+ return 0;
+
+ xzio = grub_zalloc (sizeof (*xzio));
+ if (!xzio)
+ {
+ grub_free (file);
+ return 0;
+ }
+
+ xzio->file = io;
+ xzio->saved_offset = 0;
+
+ file->device = io->device;
+ file->offset = 0;
+ file->data = xzio;
+ file->read_hook = 0;
+ file->fs = &grub_xzio_fs;
+ file->size = (grub_uint32_t) (-1);
+ file->not_easly_seekable = 1;
+
+ if (grub_file_tell (xzio->file) != 0)
+ grub_file_seek (xzio->file, 0);
+
+ /* Allocated 64KiB for dictionary.
+ * Decoder will relocate if bigger is needed. */
+ xzio->dec = xz_dec_init (1 << 16);
+ if (!xzio->dec)
+ {
+ grub_free (file);
+ grub_free (xzio);
+ return 0;
+ }
+
+ xzio->buf.in = xzio->inbuf;
+ xzio->buf.in_pos = 0;
+ xzio->buf.in_size = 0;
+ xzio->buf.out = xzio->outbuf;
+ xzio->buf.out_pos = 0;
+ xzio->buf.out_size = XZBUFSIZ;
+
+ if (!test_header (file) || !(grub_file_seekable (io) && test_footer (file)))
+ {
+ grub_file_seek (io, 0);
+ xz_dec_end (xzio->dec);
+ grub_free (xzio);
+ grub_free (file);
+
+ return 0;
+ }
+
+ return file;
+}
+
+static grub_ssize_t
+grub_xzio_read (grub_file_t file, char *buf, grub_size_t len)
+{
+ grub_ssize_t ret = 0;
+ grub_ssize_t readret;
+ enum xz_ret xzret;
+ grub_xzio_t xzio = file->data;
+ int offset_lock;
+ grub_uint8_t current_offset;
+
+ xzio->buf.out_size = len >= XZBUFSIZ ? XZBUFSIZ : len;
+
+ /* If seek backward need to reset decoder and start from beginning of file.
+ TODO Possible improvement by jumping blocks. */
+ if (file->offset < xzio->saved_offset)
+ {
+ xz_dec_reset (xzio->dec);
+ xzio->saved_offset = 0;
+ xzio->buf.out_pos = 0;
+ xzio->buf.in_pos = 0;
+ xzio->buf.in_size = 0;
+ grub_file_seek (xzio->file, 0);
+ }
+
+ offset_lock = (file->offset == xzio->saved_offset) ? 1 : 0;
+ current_offset = xzio->saved_offset;
+
+ while (len >= xzio->buf.out_size)
+ {
+ /* Feed input. */
+ if (xzio->buf.in_pos == xzio->buf.in_size)
+ {
+ readret = grub_file_read (xzio->file, xzio->inbuf, XZBUFSIZ);
+ if (readret < 0)
+ return -1;
+
+ xzio->buf.in_size = readret;
+ xzio->buf.in_pos = 0;
+ }
+
+ xzret = xz_dec_run (xzio->dec, &xzio->buf);
+ switch (xzret)
+ {
+ case XZ_MEMLIMIT_ERROR:
+ case XZ_FORMAT_ERROR:
+ case XZ_OPTIONS_ERROR:
+ case XZ_DATA_ERROR:
+ case XZ_BUF_ERROR:
+ grub_error (GRUB_ERR_BAD_IOFILTER_DATA,
+ "file corrupted or unsupported block options");
+ return -1;
+ default:
+ break;
+ }
+
+ if (offset_lock)
+ {
+ grub_memmove (buf, xzio->buf.out, xzio->buf.out_pos);
+ len -= xzio->buf.out_pos;
+ buf += xzio->buf.out_pos;
+ ret += xzio->buf.out_pos;
+ }
+ else
+ {
+ grub_uint8_t new_offset = current_offset + xzio->buf.out_pos;
+
+ if (file->offset > new_offset)
+ current_offset = new_offset;
+ else
+ /* Store first chunk of data in buffer. */
+ {
+ grub_uint8_t delta = new_offset - file->offset;
+ grub_memmove (buf, xzio->buf.out + delta,
+ xzio->buf.out_pos - delta);
+ len -= delta;
+ buf += delta;
+ ret += delta;
+ offset_lock = 1;
+ }
+ }
+ xzio->buf.out_pos = 0;
+
+ if (xzret == XZ_STREAM_END) /* Stream end, EOF. */
+ break;
+ }
+
+ if (ret >= 0)
+ xzio->saved_offset = file->offset + ret;
+
+ return ret;
+}
+
+/* Release everything, including the underlying file object. */
+static grub_err_t
+grub_xzio_close (grub_file_t file)
+{
+ grub_xzio_t xzio = file->data;
+
+ xz_dec_end (xzio->dec);
+
+ grub_file_close (xzio->file);
+ grub_free (xzio);
+
+ /* Device must not be closed twice. */
+ file->device = 0;
+ return grub_errno;
+}
+
+static struct grub_fs grub_xzio_fs = {
+ .name = "xzio",
+ .dir = 0,
+ .open = 0,
+ .read = grub_xzio_read,
+ .close = grub_xzio_close,
+ .label = 0,
+ .next = 0
+};
+
+static struct grub_io_filter grub_xzio_filter = {
+ .next = 0,
+ .name = "xzio",
+ .prio = GRUB_IOFILTER_PRIO_XZIO,
+ .active = 1,
+ .grub_io_open = grub_xzio_open
+};
+
+
+GRUB_MOD_INIT (xzio)
+{
+ grub_io_register (&grub_xzio_filter);
+}
+
+GRUB_MOD_FINI (xzio)
+{
+ grub_io_unregister (&grub_xzio_filter);
+}
=== added directory 'lib/xzembed'
=== added file 'lib/xzembed/xz.h'
--- lib/xzembed/xz.h 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz.h 2010-04-06 22:04:03 +0000
@@ -0,0 +1,180 @@
+/* xz.h - XZ decompressor */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#ifndef XZ_H
+#define XZ_H
+
+#include <stdint.h>
+
+/**
+ * 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.
+ */
+struct xz_dec * 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.
+ */
+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.
+ */
+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.
+ */
+void xz_dec_end(struct xz_dec *s);
+
+#endif
=== added file 'lib/xzembed/xz_config.h'
--- lib/xzembed/xz_config.h 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_config.h 2010-04-08 12:47:22 +0000
@@ -0,0 +1,141 @@
+/* xz_config.h - Private includes and definitions for userspace use */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#ifndef XZ_CONFIG_H
+#define XZ_CONFIG_H
+
+/* Enable BCJ filter decoders. */
+
+#if defined(__i386__) || defined(__x86_64__)
+ #define XZ_DEC_X86
+#endif
+
+#ifdef __powerpc__
+ #define XZ_DEC_POWERPC
+#endif
+
+#ifdef __ia64__
+ #define XZ_DEC_IA64
+#endif
+
+#ifdef __arm__
+ #define XZ_DEC_ARM
+#endif
+
+#ifdef __thumb__
+ #define XZ_DEC_ARMTHUMB
+#endif
+
+#ifdef __sparc__
+ #define XZ_DEC_SPARC
+#endif
+
+
+#include "xz.h"
+#include <stdlib.h>
+
+#define kmalloc(size, flags) malloc(size)
+#define kfree(ptr) free(ptr)
+#define vmalloc(size) malloc(size)
+#define vfree(ptr) free(ptr)
+
+#define memeq(a, b, size) (memcmp(a, b, size) == 0)
+#define memzero(buf, size) memset(buf, 0, size)
+
+#define min(x, y) ((x) < (y) ? (x) : (y))
+#define min_t(type, x, y) min(x, y)
+
+/*
+ * Some functions have been marked with __always_inline to keep the
+ * performance reasonable even when the compiler is optimizing for
+ * small code size. You may be able to save a few bytes by #defining
+ * __always_inline to plain inline, but don't complain if the code
+ * becomes slow.
+ *
+ * NOTE: System headers on GNU/Linux may #define this macro already,
+ * so if you want to change it, it you need to #undef it first.
+ */
+#ifndef __always_inline
+# ifdef __GNUC__
+# define __always_inline \
+ inline __attribute__((__always_inline__))
+# else
+# define __always_inline inline
+# endif
+#endif
+
+/*
+ * Some functions are marked to never be inlined to reduce stack usage.
+ * If you don't care about stack usage, you may want to modify this so
+ * that noinline_for_stack is #defined to be empty even when using GCC.
+ * Doing so may save a few bytes in binary size.
+ */
+#ifndef noinline_for_stack
+# ifdef __GNUC__
+# define noinline_for_stack __attribute__((__noinline__))
+# else
+# define noinline_for_stack
+# endif
+#endif
+
+/* Inline functions to access unaligned unsigned 32-bit integers */
+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);
+}
+
+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];
+}
+
+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);
+}
+
+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;
+}
+
+/*
+ * Use get_unaligned_le32() also for aligned access for simplicity. On
+ * little endian systems, #define get_le32(ptr) (*(const uint32_t *)(ptr))
+ * could save a few bytes in code size.
+ */
+#define get_le32 get_unaligned_le32
+
+#endif
=== added file 'lib/xzembed/xz_dec_bcj.c'
--- lib/xzembed/xz_dec_bcj.c 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_dec_bcj.c 2010-02-02 00:34:34 +0000
@@ -0,0 +1,569 @@
+/* xz_dec_bcj.c - Branch/Call/Jump (BCJ) filter decoders */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#include "xz_private.h"
+
+struct xz_dec_bcj {
+ /* Type of the BCJ filter being used */
+ enum {
+ BCJ_X86 = 4, /* x86 or x86-64 */
+ BCJ_POWERPC = 5, /* Big endian only */
+ BCJ_IA64 = 6, /* Big or little endian */
+ BCJ_ARM = 7, /* Little endian only */
+ BCJ_ARMTHUMB = 8, /* Little endian only */
+ BCJ_SPARC = 9 /* Big or little endian */
+ } type;
+
+ /*
+ * Return value of the next filter in the chain. We need to preserve
+ * this information across calls, because we must not call the next
+ * filter anymore once it has returned XZ_STREAM_END.
+ */
+ enum xz_ret ret;
+
+ /* True if we are operating in single-call mode. */
+ bool single_call;
+
+ /*
+ * Absolute position relative to the beginning of the uncompressed
+ * data (in a single .xz Block). We care only about the lowest 32
+ * bits so this doesn't need to be uint64_t even with big files.
+ */
+ uint32_t pos;
+
+ /* x86 filter state */
+ uint32_t x86_prev_mask;
+
+ /* Temporary space to hold the variables from struct xz_buf */
+ uint8_t *out;
+ size_t out_pos;
+ size_t out_size;
+
+ struct {
+ /* Amount of already filtered data in the beginning of buf */
+ size_t filtered;
+
+ /* Total amount of data currently stored in buf */
+ size_t size;
+
+ /*
+ * Buffer to hold a mix of filtered and unfiltered data. This
+ * needs to be big enough to hold Alignment + 2 * Look-ahead:
+ *
+ * Type Alignment Look-ahead
+ * x86 1 4
+ * PowerPC 4 0
+ * IA-64 16 0
+ * ARM 4 0
+ * ARM-Thumb 2 2
+ * SPARC 4 0
+ */
+ uint8_t buf[16];
+ } temp;
+};
+
+#ifdef XZ_DEC_X86
+/*
+ * This is macro used to test the most significant byte of a memory address
+ * in an x86 instruction.
+ */
+#define bcj_x86_test_msbyte(b) ((b) == 0x00 || (b) == 0xFF)
+
+static noinline_for_stack size_t bcj_x86(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ static const bool mask_to_allowed_status[8]
+ = { true, true, true, false, true, false, false, false };
+
+ static const uint8_t mask_to_bit_num[8] = { 0, 1, 2, 2, 3, 3, 3, 3 };
+
+ size_t i;
+ size_t prev_pos = (size_t)-1;
+ uint32_t prev_mask = s->x86_prev_mask;
+ uint32_t src;
+ uint32_t dest;
+ uint32_t j;
+ uint8_t b;
+
+ if (size <= 4)
+ return 0;
+
+ size -= 4;
+ for (i = 0; i < size; ++i) {
+ if ((buf[i] & 0xFE) != 0xE8)
+ continue;
+
+ prev_pos = i - prev_pos;
+ if (prev_pos > 3) {
+ prev_mask = 0;
+ } else {
+ prev_mask = (prev_mask << (prev_pos - 1)) & 7;
+ if (prev_mask != 0) {
+ b = buf[i + 4 - mask_to_bit_num[prev_mask]];
+ if (!mask_to_allowed_status[prev_mask]
+ || bcj_x86_test_msbyte(b)) {
+ prev_pos = i;
+ prev_mask = (prev_mask << 1) | 1;
+ continue;
+ }
+ }
+ }
+
+ prev_pos = i;
+
+ if (bcj_x86_test_msbyte(buf[i + 4])) {
+ src = get_unaligned_le32(buf + i + 1);
+ while (true) {
+ dest = src - (s->pos + (uint32_t)i + 5);
+ if (prev_mask == 0)
+ break;
+
+ j = mask_to_bit_num[prev_mask] * 8;
+ b = (uint8_t)(dest >> (24 - j));
+ if (!bcj_x86_test_msbyte(b))
+ break;
+
+ src = dest ^ (((uint32_t)1 << (32 - j)) - 1);
+ }
+
+ dest &= 0x01FFFFFF;
+ dest |= (uint32_t)0 - (dest & 0x01000000);
+ put_unaligned_le32(dest, buf + i + 1);
+ i += 4;
+ } else {
+ prev_mask = (prev_mask << 1) | 1;
+ }
+ }
+
+ prev_pos = i - prev_pos;
+ s->x86_prev_mask = prev_pos > 3 ? 0 : prev_mask << (prev_pos - 1);
+ return i;
+}
+#endif
+
+#ifdef XZ_DEC_POWERPC
+static noinline_for_stack size_t bcj_powerpc(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ size_t i;
+ uint32_t instr;
+
+ for (i = 0; i + 4 <= size; i += 4) {
+ instr = get_unaligned_be32(buf + i);
+ if ((instr & 0xFC000003) == 0x48000001) {
+ instr &= 0x03FFFFFC;
+ instr -= s->pos + (uint32_t)i;
+ instr &= 0x03FFFFFC;
+ instr |= 0x48000001;
+ put_unaligned_be32(instr, buf + i);
+ }
+ }
+
+ return i;
+}
+#endif
+
+#ifdef XZ_DEC_IA64
+static noinline_for_stack size_t bcj_ia64(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ static const uint8_t branch_table[32] = {
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 4, 4, 6, 6, 0, 0, 7, 7,
+ 4, 4, 0, 0, 4, 4, 0, 0
+ };
+
+ /*
+ * The local variables take a little bit stack space, but it's less
+ * than what LZMA2 decoder takes, so it doesn't make sense to reduce
+ * stack usage here without doing that for the LZMA2 decoder too.
+ */
+
+ /* Loop counters */
+ size_t i;
+ size_t j;
+
+ /* Instruction slot (0, 1, or 2) in the 128-bit instruction word */
+ uint32_t slot;
+
+ /* Bitwise offset of the instruction indicated by slot */
+ uint32_t bit_pos;
+
+ /* bit_pos split into byte and bit parts */
+ uint32_t byte_pos;
+ uint32_t bit_res;
+
+ /* Address part of an instruction */
+ uint32_t addr;
+
+ /* Mask used to detect which instructions to convert */
+ uint32_t mask;
+
+ /* 41-bit instruction stored somewhere in the lowest 48 bits */
+ uint64_t instr;
+
+ /* Instruction normalized with bit_res for easier manipulation */
+ uint64_t norm;
+
+ for (i = 0; i + 16 <= size; i += 16) {
+ mask = branch_table[buf[i] & 0x1F];
+ for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) {
+ if (((mask >> slot) & 1) == 0)
+ continue;
+
+ byte_pos = bit_pos >> 3;
+ bit_res = bit_pos & 7;
+ instr = 0;
+ for (j = 0; j < 6; ++j)
+ instr |= (uint64_t)(buf[i + j + byte_pos])
+ << (8 * j);
+
+ norm = instr >> bit_res;
+
+ if (((norm >> 37) & 0x0F) == 0x05
+ && ((norm >> 9) & 0x07) == 0) {
+ addr = (norm >> 13) & 0x0FFFFF;
+ addr |= ((uint32_t)(norm >> 36) & 1) << 20;
+ addr <<= 4;
+ addr -= s->pos + (uint32_t)i;
+ addr >>= 4;
+
+ norm &= ~((uint64_t)0x8FFFFF << 13);
+ norm |= (uint64_t)(addr & 0x0FFFFF) << 13;
+ norm |= (uint64_t)(addr & 0x100000)
+ << (36 - 20);
+
+ instr &= (1 << bit_res) - 1;
+ instr |= norm << bit_res;
+
+ for (j = 0; j < 6; j++)
+ buf[i + j + byte_pos]
+ = (uint8_t)(instr >> (8 * j));
+ }
+ }
+ }
+
+ return i;
+}
+#endif
+
+#ifdef XZ_DEC_ARM
+static noinline_for_stack size_t bcj_arm(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ size_t i;
+ uint32_t addr;
+
+ for (i = 0; i + 4 <= size; i += 4) {
+ if (buf[i + 3] == 0xEB) {
+ addr = (uint32_t)buf[i] | ((uint32_t)buf[i + 1] << 8)
+ | ((uint32_t)buf[i + 2] << 16);
+ addr <<= 2;
+ addr -= s->pos + (uint32_t)i + 8;
+ addr >>= 2;
+ buf[i] = (uint8_t)addr;
+ buf[i + 1] = (uint8_t)(addr >> 8);
+ buf[i + 2] = (uint8_t)(addr >> 16);
+ }
+ }
+
+ return i;
+}
+#endif
+
+#ifdef XZ_DEC_ARMTHUMB
+static noinline_for_stack size_t bcj_armthumb(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ size_t i;
+ uint32_t addr;
+
+ for (i = 0; i + 4 <= size; i += 2) {
+ if ((buf[i + 1] & 0xF8) == 0xF0
+ && (buf[i + 3] & 0xF8) == 0xF8) {
+ addr = (((uint32_t)buf[i + 1] & 0x07) << 19)
+ | ((uint32_t)buf[i] << 11)
+ | (((uint32_t)buf[i + 3] & 0x07) << 8)
+ | (uint32_t)buf[i + 2];
+ addr <<= 1;
+ addr -= s->pos + (uint32_t)i + 4;
+ addr >>= 1;
+ buf[i + 1] = (uint8_t)(0xF0 | ((addr >> 19) & 0x07));
+ buf[i] = (uint8_t)(addr >> 11);
+ buf[i + 3] = (uint8_t)(0xF8 | ((addr >> 8) & 0x07));
+ buf[i + 2] = (uint8_t)addr;
+ i += 2;
+ }
+ }
+
+ return i;
+}
+#endif
+
+#ifdef XZ_DEC_SPARC
+static noinline_for_stack size_t bcj_sparc(
+ struct xz_dec_bcj *s, uint8_t *buf, size_t size)
+{
+ size_t i;
+ uint32_t instr;
+
+ for (i = 0; i + 4 <= size; i += 4) {
+ instr = get_unaligned_be32(buf + i);
+ if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) {
+ instr <<= 2;
+ instr -= s->pos + (uint32_t)i;
+ instr >>= 2;
+ instr = ((uint32_t)0x40000000 - (instr & 0x400000))
+ | 0x40000000 | (instr & 0x3FFFFF);
+ put_unaligned_be32(instr, buf + i);
+ }
+ }
+
+ return i;
+}
+#endif
+
+/*
+ * Apply the selected BCJ filter. Update *pos and s->pos to match the amount
+ * of data that got filtered.
+ *
+ * NOTE: This is implemented as a switch statement to avoid using function
+ * pointers, which could be problematic in the kernel boot code, which must
+ * avoid pointers to static data (at least on x86).
+ */
+static void bcj_apply(struct xz_dec_bcj *s,
+ uint8_t *buf, size_t *pos, size_t size)
+{
+ size_t filtered;
+
+ buf += *pos;
+ size -= *pos;
+
+ switch (s->type) {
+#ifdef XZ_DEC_X86
+ case BCJ_X86:
+ filtered = bcj_x86(s, buf, size);
+ break;
+#endif
+#ifdef XZ_DEC_POWERPC
+ case BCJ_POWERPC:
+ filtered = bcj_powerpc(s, buf, size);
+ break;
+#endif
+#ifdef XZ_DEC_IA64
+ case BCJ_IA64:
+ filtered = bcj_ia64(s, buf, size);
+ break;
+#endif
+#ifdef XZ_DEC_ARM
+ case BCJ_ARM:
+ filtered = bcj_arm(s, buf, size);
+ break;
+#endif
+#ifdef XZ_DEC_ARMTHUMB
+ case BCJ_ARMTHUMB:
+ filtered = bcj_armthumb(s, buf, size);
+ break;
+#endif
+#ifdef XZ_DEC_SPARC
+ case BCJ_SPARC:
+ filtered = bcj_sparc(s, buf, size);
+ break;
+#endif
+ default:
+ /* Never reached but silence compiler warnings. */
+ filtered = 0;
+ break;
+ }
+
+ *pos += filtered;
+ s->pos += filtered;
+}
+
+/*
+ * Flush pending filtered data from temp to the output buffer.
+ * Move the remaining mixture of possibly filtered and unfiltered
+ * data to the beginning of temp.
+ */
+static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b)
+{
+ size_t copy_size;
+
+ copy_size = min_t(size_t, s->temp.filtered, b->out_size - b->out_pos);
+ memcpy(b->out + b->out_pos, s->temp.buf, copy_size);
+ b->out_pos += copy_size;
+
+ s->temp.filtered -= copy_size;
+ s->temp.size -= copy_size;
+ memmove(s->temp.buf, s->temp.buf + copy_size, s->temp.size);
+}
+
+/*
+ * The BCJ filter functions are primitive in sense that they process the
+ * data in chunks of 1-16 bytes. To hide this issue, this function does
+ * some buffering.
+ */
+enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
+ struct xz_dec_lzma2 *lzma2, struct xz_buf *b)
+{
+ size_t out_start;
+
+ /*
+ * Flush pending already filtered data to the output buffer. Return
+ * immediatelly if we couldn't flush everything, or if the next
+ * filter in the chain had already returned XZ_STREAM_END.
+ */
+ if (s->temp.filtered > 0) {
+ bcj_flush(s, b);
+ if (s->temp.filtered > 0)
+ return XZ_OK;
+
+ if (s->ret == XZ_STREAM_END)
+ return XZ_STREAM_END;
+ }
+
+ /*
+ * If we have more output space than what is currently pending in
+ * temp, copy the unfiltered data from temp to the output buffer
+ * and try to fill the output buffer by decoding more data from the
+ * next filter in the chain. Apply the BCJ filter on the new data
+ * in the output buffer. If everything cannot be filtered, copy it
+ * to temp and rewind the output buffer position accordingly.
+ */
+ if (s->temp.size < b->out_size - b->out_pos) {
+ out_start = b->out_pos;
+ memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size);
+ b->out_pos += s->temp.size;
+
+ s->ret = xz_dec_lzma2_run(lzma2, b);
+ if (s->ret != XZ_STREAM_END
+ && (s->ret != XZ_OK || s->single_call))
+ return s->ret;
+
+ bcj_apply(s, b->out, &out_start, b->out_pos);
+
+ /*
+ * As an exception, if the next filter returned XZ_STREAM_END,
+ * we can do that too, since the last few bytes that remain
+ * unfiltered are meant to remain unfiltered.
+ */
+ if (s->ret == XZ_STREAM_END)
+ return XZ_STREAM_END;
+
+ s->temp.size = b->out_pos - out_start;
+ b->out_pos -= s->temp.size;
+ memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size);
+ }
+
+ /*
+ * If we have unfiltered data in temp, try to fill by decoding more
+ * data from the next filter. Apply the BCJ filter on temp. Then we
+ * hopefully can fill the actual output buffer by copying filtered
+ * data from temp. A mix of filtered and unfiltered data may be left
+ * in temp; it will be taken care on the next call to this function.
+ */
+ if (s->temp.size > 0) {
+ /* Make b->out{,_pos,_size} temporarily point to s->temp. */
+ s->out = b->out;
+ s->out_pos = b->out_pos;
+ s->out_size = b->out_size;
+ b->out = s->temp.buf;
+ b->out_pos = s->temp.size;
+ b->out_size = sizeof(s->temp.buf);
+
+ s->ret = xz_dec_lzma2_run(lzma2, b);
+
+ s->temp.size = b->out_pos;
+ b->out = s->out;
+ b->out_pos = s->out_pos;
+ b->out_size = s->out_size;
+
+ if (s->ret != XZ_OK && s->ret != XZ_STREAM_END)
+ return s->ret;
+
+ bcj_apply(s, s->temp.buf, &s->temp.filtered, s->temp.size);
+
+ /*
+ * If the next filter returned XZ_STREAM_END, we mark that
+ * everything is filtered, since the last unfiltered bytes
+ * of the stream are meant to be left as is.
+ */
+ if (s->ret == XZ_STREAM_END)
+ s->temp.filtered = s->temp.size;
+
+ bcj_flush(s, b);
+ if (s->temp.filtered > 0)
+ return XZ_OK;
+ }
+
+ return s->ret;
+}
+
+struct xz_dec_bcj * xz_dec_bcj_create(bool single_call)
+{
+ struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s != NULL)
+ s->single_call = single_call;
+
+ return s;
+}
+
+enum xz_ret xz_dec_bcj_reset(
+ struct xz_dec_bcj *s, uint8_t id)
+{
+ switch (id) {
+#ifdef XZ_DEC_X86
+ case BCJ_X86:
+#endif
+#ifdef XZ_DEC_POWERPC
+ case BCJ_POWERPC:
+#endif
+#ifdef XZ_DEC_IA64
+ case BCJ_IA64:
+#endif
+#ifdef XZ_DEC_ARM
+ case BCJ_ARM:
+#endif
+#ifdef XZ_DEC_ARMTHUMB
+ case BCJ_ARMTHUMB:
+#endif
+#ifdef XZ_DEC_SPARC
+ case BCJ_SPARC:
+#endif
+ break;
+
+ default:
+ /* Unsupported Filter ID */
+ return XZ_OPTIONS_ERROR;
+ }
+
+ s->type = id;
+ s->ret = XZ_OK;
+ s->pos = 0;
+ s->x86_prev_mask = 0;
+ s->temp.filtered = 0;
+ s->temp.size = 0;
+
+ return XZ_OK;
+}
=== added file 'lib/xzembed/xz_dec_lzma2.c'
--- lib/xzembed/xz_dec_lzma2.c 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_dec_lzma2.c 2010-02-04 18:07:48 +0000
@@ -0,0 +1,1168 @@
+/* xz_dec_lzma2.c - LZMA2 decoder */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#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 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 dict_limit(struct dictionary *dict, size_t out_max)
+{
+ if (dict->end - dict->pos <= out_max)
+ dict->limit = dict->end;
+ else
+ dict->limit = dict->pos + out_max;
+}
+
+/* Return true if at least one byte can be written into the dictionary. */
+static inline bool dict_has_space(const struct dictionary *dict)
+{
+ return dict->pos < dict->limit;
+}
+
+/*
+ * Get a byte from the dictionary at the given distance. The distance is
+ * assumed to valid, or as a special case, zero when the dictionary is
+ * still empty. This special case is needed for single-call decoding to
+ * avoid writing a '\0' to the end of the destination buffer.
+ */
+static inline uint32_t dict_get(
+ const struct dictionary *dict, uint32_t dist)
+{
+ size_t offset = dict->pos - dist - 1;
+
+ if (dist >= dict->pos)
+ offset += dict->end;
+
+ return dict->full > 0 ? dict->buf[offset] : 0;
+}
+
+/*
+ * Put one byte into the dictionary. It is assumed that there is space for it.
+ */
+static inline void dict_put(struct dictionary *dict, uint8_t byte)
+{
+ dict->buf[dict->pos++] = byte;
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+}
+
+/*
+ * Repeat given number of bytes from the given distance. If the distance is
+ * invalid, false is returned. On success, true is returned and *len is
+ * updated to indicate how many bytes were left to be repeated.
+ */
+static bool dict_repeat(
+ struct dictionary *dict, uint32_t *len, uint32_t dist)
+{
+ size_t back;
+ uint32_t left;
+
+ if (dist >= dict->full || dist >= dict->size)
+ return false;
+
+ left = min_t(size_t, dict->limit - dict->pos, *len);
+ *len -= left;
+
+ back = dict->pos - dist - 1;
+ if (dist >= dict->pos)
+ back += dict->end;
+
+ do {
+ dict->buf[dict->pos++] = dict->buf[back++];
+ if (back == dict->end)
+ back = 0;
+ } while (--left > 0);
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+
+ return true;
+}
+
+/* Copy uncompressed data as is from input to dictionary and output buffers. */
+static void dict_uncompressed(
+ struct dictionary *dict, struct xz_buf *b, uint32_t *left)
+{
+ size_t copy_size;
+
+ while (*left > 0 && b->in_pos < b->in_size
+ && b->out_pos < b->out_size) {
+ copy_size = min(b->in_size - b->in_pos,
+ b->out_size - b->out_pos);
+ if (copy_size > dict->end - dict->pos)
+ copy_size = dict->end - dict->pos;
+ if (copy_size > *left)
+ copy_size = *left;
+
+ *left -= copy_size;
+
+ memcpy(dict->buf + dict->pos, b->in + b->in_pos, copy_size);
+ dict->pos += copy_size;
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+
+ if (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 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 rc_reset(struct rc_dec *rc)
+{
+ rc->range = (uint32_t)-1;
+ rc->code = 0;
+ rc->init_bytes_left = RC_INIT_BYTES;
+}
+
+/*
+ * Read the first five initial bytes into rc->code if they haven't been
+ * read already. (Yes, the first byte gets completely ignored.)
+ */
+static bool rc_read_init(struct rc_dec *rc, struct xz_buf *b)
+{
+ while (rc->init_bytes_left > 0) {
+ if (b->in_pos == b->in_size)
+ return false;
+
+ rc->code = (rc->code << 8) + b->in[b->in_pos++];
+ --rc->init_bytes_left;
+ }
+
+ return true;
+}
+
+/* Return true if there may not be enough input for the next decoding loop. */
+static inline bool rc_limit_exceeded(const struct rc_dec *rc)
+{
+ return rc->in_pos > rc->in_limit;
+}
+
+/*
+ * Return true if it is possible (from point of view of range decoder) that
+ * we have reached the end of the LZMA chunk.
+ */
+static inline bool rc_is_finished(const struct rc_dec *rc)
+{
+ return rc->code == 0;
+}
+
+/* Read the next input byte if needed. */
+static __always_inline void rc_normalize(struct rc_dec *rc)
+{
+ if (rc->range < RC_TOP_VALUE) {
+ rc->range <<= RC_SHIFT_BITS;
+ rc->code = (rc->code << RC_SHIFT_BITS) + rc->in[rc->in_pos++];
+ }
+}
+
+/*
+ * Decode one bit. In some versions, this function has been splitted in three
+ * functions so that the compiler is supposed to be able to more easily avoid
+ * an extra branch. In this particular version of the LZMA decoder, this
+ * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3
+ * on x86). Using a non-splitted version results in nicer looking code too.
+ *
+ * NOTE: This must return an int. Do not make it return a bool or the speed
+ * of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care,
+ * and it generates 10-20 % faster code than GCC 3.x from this file anyway.)
+ */
+static __always_inline int rc_bit(struct rc_dec *rc, uint16_t *prob)
+{
+ uint32_t bound;
+ int bit;
+
+ rc_normalize(rc);
+ bound = (rc->range >> RC_BIT_MODEL_TOTAL_BITS) * *prob;
+ if (rc->code < bound) {
+ rc->range = bound;
+ *prob += (RC_BIT_MODEL_TOTAL - *prob) >> RC_MOVE_BITS;
+ bit = 0;
+ } else {
+ rc->range -= bound;
+ rc->code -= bound;
+ *prob -= *prob >> RC_MOVE_BITS;
+ bit = 1;
+ }
+
+ return bit;
+}
+
+/* Decode a bittree starting from the most significant bit. */
+static __always_inline uint32_t rc_bittree(
+ struct rc_dec *rc, uint16_t *probs, uint32_t limit)
+{
+ uint32_t symbol = 1;
+
+ do {
+ if (rc_bit(rc, &probs[symbol]))
+ symbol = (symbol << 1) + 1;
+ else
+ symbol <<= 1;
+ } while (symbol < limit);
+
+ return symbol;
+}
+
+/* Decode a bittree starting from the least significant bit. */
+static __always_inline void rc_bittree_reverse(struct rc_dec *rc,
+ uint16_t *probs, uint32_t *dest, uint32_t limit)
+{
+ uint32_t symbol = 1;
+ uint32_t i = 0;
+
+ do {
+ if (rc_bit(rc, &probs[symbol])) {
+ symbol = (symbol << 1) + 1;
+ *dest += 1 << i;
+ } else {
+ symbol <<= 1;
+ }
+ } while (++i < limit);
+}
+
+/* Decode direct bits (fixed fifty-fifty probability) */
+static inline void rc_direct(
+ struct rc_dec *rc, uint32_t *dest, uint32_t limit)
+{
+ uint32_t mask;
+
+ do {
+ rc_normalize(rc);
+ rc->range >>= 1;
+ rc->code -= rc->range;
+ mask = (uint32_t)0 - (rc->code >> 31);
+ rc->code += rc->range & mask;
+ *dest = (*dest << 1) + (mask + 1);
+ } while (--limit > 0);
+}
+
+/********
+ * LZMA *
+ ********/
+
+/* Get pointer to literal coder probability array. */
+static uint16_t * lzma_literal_probs(struct xz_dec_lzma2 *s)
+{
+ uint32_t prev_byte = dict_get(&s->dict, 0);
+ uint32_t low = prev_byte >> (8 - s->lzma.lc);
+ uint32_t high = (s->dict.pos & s->lzma.literal_pos_mask) << s->lzma.lc;
+ return s->lzma.literal[low + high];
+}
+
+/* Decode a literal (one 8-bit byte) */
+static void lzma_literal(struct xz_dec_lzma2 *s)
+{
+ uint16_t *probs;
+ uint32_t symbol;
+ uint32_t match_byte;
+ uint32_t match_bit;
+ uint32_t offset;
+ uint32_t i;
+
+ probs = lzma_literal_probs(s);
+
+ if (lzma_state_is_literal(s->lzma.state)) {
+ symbol = rc_bittree(&s->rc, probs, 0x100);
+ } else {
+ symbol = 1;
+ match_byte = dict_get(&s->dict, s->lzma.rep0) << 1;
+ offset = 0x100;
+
+ do {
+ match_bit = match_byte & offset;
+ match_byte <<= 1;
+ i = offset + match_bit + symbol;
+
+ if (rc_bit(&s->rc, &probs[i])) {
+ symbol = (symbol << 1) + 1;
+ offset &= match_bit;
+ } else {
+ symbol <<= 1;
+ offset &= ~match_bit;
+ }
+ } while (symbol < 0x100);
+ }
+
+ dict_put(&s->dict, (uint8_t)symbol);
+ lzma_state_literal(&s->lzma.state);
+}
+
+/* Decode the length of the match into s->lzma.len. */
+static void lzma_len(struct xz_dec_lzma2 *s, struct lzma_len_dec *l,
+ uint32_t pos_state)
+{
+ uint16_t *probs;
+ uint32_t limit;
+
+ if (!rc_bit(&s->rc, &l->choice)) {
+ probs = l->low[pos_state];
+ limit = LEN_LOW_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN;
+ } else {
+ if (!rc_bit(&s->rc, &l->choice2)) {
+ probs = l->mid[pos_state];
+ limit = LEN_MID_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS;
+ } else {
+ probs = l->high;
+ limit = LEN_HIGH_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS
+ + LEN_MID_SYMBOLS;
+ }
+ }
+
+ s->lzma.len += rc_bittree(&s->rc, probs, limit) - limit;
+}
+
+/* Decode a match. The distance will be stored in s->lzma.rep0. */
+static void lzma_match(struct xz_dec_lzma2 *s, uint32_t pos_state)
+{
+ uint16_t *probs;
+ uint32_t dist_slot;
+ uint32_t limit;
+
+ lzma_state_match(&s->lzma.state);
+
+ s->lzma.rep3 = s->lzma.rep2;
+ s->lzma.rep2 = s->lzma.rep1;
+ s->lzma.rep1 = s->lzma.rep0;
+
+ lzma_len(s, &s->lzma.match_len_dec, pos_state);
+
+ probs = s->lzma.dist_slot[lzma_get_dist_state(s->lzma.len)];
+ dist_slot = rc_bittree(&s->rc, probs, DIST_SLOTS) - DIST_SLOTS;
+
+ if (dist_slot < DIST_MODEL_START) {
+ s->lzma.rep0 = dist_slot;
+ } else {
+ limit = (dist_slot >> 1) - 1;
+ s->lzma.rep0 = 2 + (dist_slot & 1);
+
+ if (dist_slot < DIST_MODEL_END) {
+ s->lzma.rep0 <<= limit;
+ probs = s->lzma.dist_special + s->lzma.rep0
+ - dist_slot - 1;
+ rc_bittree_reverse(&s->rc, probs,
+ &s->lzma.rep0, limit);
+ } else {
+ rc_direct(&s->rc, &s->lzma.rep0, limit - ALIGN_BITS);
+ s->lzma.rep0 <<= ALIGN_BITS;
+ rc_bittree_reverse(&s->rc, s->lzma.dist_align,
+ &s->lzma.rep0, ALIGN_BITS);
+ }
+ }
+}
+
+/*
+ * Decode a repeated match. The distance is one of the four most recently
+ * seen matches. The distance will be stored in s->lzma.rep0.
+ */
+static void lzma_rep_match(struct xz_dec_lzma2 *s, uint32_t pos_state)
+{
+ uint32_t tmp;
+
+ if (!rc_bit(&s->rc, &s->lzma.is_rep0[s->lzma.state])) {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep0_long[
+ s->lzma.state][pos_state])) {
+ lzma_state_short_rep(&s->lzma.state);
+ s->lzma.len = 1;
+ return;
+ }
+ } else {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep1[s->lzma.state])) {
+ tmp = s->lzma.rep1;
+ } else {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep2[s->lzma.state])) {
+ tmp = s->lzma.rep2;
+ } else {
+ tmp = s->lzma.rep3;
+ s->lzma.rep3 = s->lzma.rep2;
+ }
+
+ s->lzma.rep2 = s->lzma.rep1;
+ }
+
+ s->lzma.rep1 = s->lzma.rep0;
+ s->lzma.rep0 = tmp;
+ }
+
+ lzma_state_long_rep(&s->lzma.state);
+ lzma_len(s, &s->lzma.rep_len_dec, pos_state);
+}
+
+/* LZMA decoder core */
+static bool lzma_main(struct xz_dec_lzma2 *s)
+{
+ uint32_t pos_state;
+
+ /*
+ * If the dictionary was reached during the previous call, try to
+ * finish the possibly pending repeat in the dictionary.
+ */
+ if (dict_has_space(&s->dict) && s->lzma.len > 0)
+ dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0);
+
+ /*
+ * Decode more LZMA symbols. One iteration may consume up to
+ * LZMA_IN_REQUIRED - 1 bytes.
+ */
+ while (dict_has_space(&s->dict) && !rc_limit_exceeded(&s->rc)) {
+ pos_state = s->dict.pos & s->lzma.pos_mask;
+
+ if (!rc_bit(&s->rc, &s->lzma.is_match[
+ s->lzma.state][pos_state])) {
+ lzma_literal(s);
+ } else {
+ if (rc_bit(&s->rc, &s->lzma.is_rep[s->lzma.state]))
+ lzma_rep_match(s, pos_state);
+ else
+ lzma_match(s, pos_state);
+
+ if (!dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0))
+ return false;
+ }
+ }
+
+ /*
+ * Having the range decoder always normalized when we are outside
+ * this function makes it easier to correctly handle end of the chunk.
+ */
+ rc_normalize(&s->rc);
+
+ return true;
+}
+
+/*
+ * Reset the LZMA decoder and range decoder state. Dictionary is nore reset
+ * here, because LZMA state may be reset without resetting the dictionary.
+ */
+static void lzma_reset(struct xz_dec_lzma2 *s)
+{
+ uint16_t *probs;
+ size_t i;
+
+ s->lzma.state = STATE_LIT_LIT;
+ s->lzma.rep0 = 0;
+ s->lzma.rep1 = 0;
+ s->lzma.rep2 = 0;
+ s->lzma.rep3 = 0;
+
+ /*
+ * All probabilities are initialized to the same value. This hack
+ * makes the code smaller by avoiding a separate loop for each
+ * probability array.
+ *
+ * This could be optimized so that only that part of literal
+ * probabilities that are actually required. In the common case
+ * we would write 12 KiB less.
+ */
+ probs = s->lzma.is_match[0];
+ for (i = 0; i < PROBS_TOTAL; ++i)
+ probs[i] = RC_BIT_MODEL_TOTAL / 2;
+
+ rc_reset(&s->rc);
+}
+
+/*
+ * Decode and validate LZMA properties (lc/lp/pb) and calculate the bit masks
+ * from the decoded lp and pb values. On success, the LZMA decoder state is
+ * reset and true is returned.
+ */
+static bool lzma_props(struct xz_dec_lzma2 *s, uint8_t props)
+{
+ if (props > (4 * 5 + 4) * 9 + 8)
+ return false;
+
+ s->lzma.pos_mask = 0;
+ while (props >= 9 * 5) {
+ props -= 9 * 5;
+ ++s->lzma.pos_mask;
+ }
+
+ s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1;
+
+ s->lzma.literal_pos_mask = 0;
+ while (props >= 9) {
+ props -= 9;
+ ++s->lzma.literal_pos_mask;
+ }
+
+ s->lzma.lc = props;
+
+ if (s->lzma.lc + s->lzma.literal_pos_mask > 4)
+ return false;
+
+ s->lzma.literal_pos_mask = (1 << s->lzma.literal_pos_mask) - 1;
+
+ lzma_reset(s);
+
+ return true;
+}
+
+/*********
+ * LZMA2 *
+ *********/
+
+/*
+ * The LZMA decoder assumes that if the input limit (s->rc.in_limit) hasn't
+ * been exceeded, it is safe to read up to LZMA_IN_REQUIRED bytes. This
+ * wrapper function takes care of making the LZMA decoder's assumption safe.
+ *
+ * As long as there is plenty of input left to be decoded in the current LZMA
+ * chunk, we decode directly from the caller-supplied input buffer until
+ * there's LZMA_IN_REQUIRED bytes left. Those remaining bytes are copied into
+ * s->temp.buf, which (hopefully) gets filled on the next call to this
+ * function. We decode a few bytes from the temporary buffer so that we can
+ * continue decoding from the caller-supplied input buffer again.
+ */
+static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b)
+{
+ size_t in_avail;
+ uint32_t tmp;
+
+ in_avail = b->in_size - b->in_pos;
+ if (s->temp.size > 0 || s->lzma2.compressed == 0) {
+ tmp = 2 * LZMA_IN_REQUIRED - s->temp.size;
+ if (tmp > s->lzma2.compressed - s->temp.size)
+ tmp = s->lzma2.compressed - s->temp.size;
+ if (tmp > in_avail)
+ tmp = in_avail;
+
+ memcpy(s->temp.buf + s->temp.size, b->in + b->in_pos, tmp);
+
+ if (s->temp.size + tmp == s->lzma2.compressed) {
+ memzero(s->temp.buf + s->temp.size + tmp,
+ sizeof(s->temp.buf)
+ - s->temp.size - tmp);
+ s->rc.in_limit = s->temp.size + tmp;
+ } else if (s->temp.size + tmp < LZMA_IN_REQUIRED) {
+ s->temp.size += tmp;
+ b->in_pos += tmp;
+ return true;
+ } else {
+ s->rc.in_limit = s->temp.size + tmp - LZMA_IN_REQUIRED;
+ }
+
+ s->rc.in = s->temp.buf;
+ s->rc.in_pos = 0;
+
+ if (!lzma_main(s) || s->rc.in_pos > s->temp.size + tmp)
+ return false;
+
+ s->lzma2.compressed -= s->rc.in_pos;
+
+ if (s->rc.in_pos < s->temp.size) {
+ s->temp.size -= s->rc.in_pos;
+ memmove(s->temp.buf, s->temp.buf + s->rc.in_pos,
+ s->temp.size);
+ return true;
+ }
+
+ b->in_pos += s->rc.in_pos - s->temp.size;
+ s->temp.size = 0;
+ }
+
+ in_avail = b->in_size - b->in_pos;
+ if (in_avail >= LZMA_IN_REQUIRED) {
+ s->rc.in = b->in;
+ s->rc.in_pos = b->in_pos;
+
+ if (in_avail >= s->lzma2.compressed + LZMA_IN_REQUIRED)
+ s->rc.in_limit = b->in_pos + s->lzma2.compressed;
+ else
+ s->rc.in_limit = b->in_size - LZMA_IN_REQUIRED;
+
+ if (!lzma_main(s))
+ return false;
+
+ in_avail = s->rc.in_pos - b->in_pos;
+ if (in_avail > s->lzma2.compressed)
+ return false;
+
+ s->lzma2.compressed -= in_avail;
+ b->in_pos = s->rc.in_pos;
+ }
+
+ in_avail = b->in_size - b->in_pos;
+ if (in_avail < LZMA_IN_REQUIRED) {
+ if (in_avail > s->lzma2.compressed)
+ in_avail = s->lzma2.compressed;
+
+ memcpy(s->temp.buf, b->in + b->in_pos, in_avail);
+ s->temp.size = in_avail;
+ b->in_pos += in_avail;
+ }
+
+ return true;
+}
+
+/*
+ * Take care of the LZMA2 control layer, and forward the job of actual LZMA
+ * decoding or copying of uncompressed chunks to other functions.
+ */
+enum xz_ret xz_dec_lzma2_run(
+ struct xz_dec_lzma2 *s, struct xz_buf *b)
+{
+ uint32_t tmp;
+
+ while (b->in_pos < b->in_size || s->lzma2.sequence == SEQ_LZMA_RUN) {
+ switch (s->lzma2.sequence) {
+ case SEQ_CONTROL:
+ /*
+ * LZMA2 control byte
+ *
+ * Exact values:
+ * 0x00 End marker
+ * 0x01 Dictionary reset followed by
+ * an uncompressed chunk
+ * 0x02 Uncompressed chunk (no dictionary reset)
+ *
+ * Highest three bits (s->control & 0xE0):
+ * 0xE0 Dictionary reset, new properties and state
+ * reset, followed by LZMA compressed chunk
+ * 0xC0 New properties and state reset, followed
+ * by LZMA compressed chunk (no dictionary
+ * reset)
+ * 0xA0 State reset using old properties,
+ * followed by LZMA compressed chunk (no
+ * dictionary reset)
+ * 0x80 LZMA chunk (no dictionary or state reset)
+ *
+ * For LZMA compressed chunks, the lowest five bits
+ * (s->control & 1F) are the highest bits of the
+ * uncompressed size (bits 16-20).
+ *
+ * A new LZMA2 stream must begin with a dictionary
+ * reset. The first LZMA chunk must set new
+ * properties and reset the LZMA state.
+ *
+ * Values that don't match anything described above
+ * are invalid and we return XZ_DATA_ERROR.
+ */
+ tmp = b->in[b->in_pos++];
+
+ if (tmp >= 0xE0 || tmp == 0x01) {
+ s->lzma2.need_props = true;
+ s->lzma2.need_dict_reset = false;
+ dict_reset(&s->dict, b);
+ } else if (s->lzma2.need_dict_reset) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (tmp >= 0x80) {
+ s->lzma2.uncompressed = (tmp & 0x1F) << 16;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_1;
+
+ if (tmp >= 0xC0) {
+ /*
+ * When there are new properties,
+ * state reset is done at
+ * SEQ_PROPERTIES.
+ */
+ s->lzma2.need_props = false;
+ s->lzma2.next_sequence
+ = SEQ_PROPERTIES;
+
+ } else if (s->lzma2.need_props) {
+ return XZ_DATA_ERROR;
+
+ } else {
+ s->lzma2.next_sequence
+ = SEQ_LZMA_PREPARE;
+ if (tmp >= 0xA0)
+ lzma_reset(s);
+ }
+ } else {
+ if (tmp == 0x00)
+ return XZ_STREAM_END;
+
+ if (tmp > 0x02)
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ s->lzma2.next_sequence = SEQ_COPY;
+ }
+
+ break;
+
+ case SEQ_UNCOMPRESSED_1:
+ s->lzma2.uncompressed
+ += (uint32_t)b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_2;
+ break;
+
+ case SEQ_UNCOMPRESSED_2:
+ s->lzma2.uncompressed
+ += (uint32_t)b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ break;
+
+ case SEQ_COMPRESSED_0:
+ s->lzma2.compressed
+ = (uint32_t)b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_COMPRESSED_1;
+ break;
+
+ case SEQ_COMPRESSED_1:
+ s->lzma2.compressed
+ += (uint32_t)b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = s->lzma2.next_sequence;
+ break;
+
+ case SEQ_PROPERTIES:
+ if (!lzma_props(s, b->in[b->in_pos++]))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_LZMA_PREPARE;
+
+ case SEQ_LZMA_PREPARE:
+ if (s->lzma2.compressed < RC_INIT_BYTES)
+ return XZ_DATA_ERROR;
+
+ if (!rc_read_init(&s->rc, b))
+ return XZ_OK;
+
+ s->lzma2.compressed -= RC_INIT_BYTES;
+ s->lzma2.sequence = SEQ_LZMA_RUN;
+
+ case SEQ_LZMA_RUN:
+ /*
+ * Set dictionary limit to indicate how much we want
+ * to be encoded at maximum. Decode new data into the
+ * dictionary. Flush the new data from dictionary to
+ * b->out. Check if we finished decoding this chunk.
+ * In case the dictionary got full but we didn't fill
+ * the output buffer yet, we may run this loop
+ * multiple times without changing s->lzma2.sequence.
+ */
+ dict_limit(&s->dict, min_t(size_t,
+ b->out_size - b->out_pos,
+ s->lzma2.uncompressed));
+ if (!lzma2_lzma(s, b))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.uncompressed -= dict_flush(&s->dict, b);
+
+ if (s->lzma2.uncompressed == 0) {
+ if (s->lzma2.compressed > 0 || s->lzma.len > 0
+ || !rc_is_finished(&s->rc))
+ return XZ_DATA_ERROR;
+
+ rc_reset(&s->rc);
+ s->lzma2.sequence = SEQ_CONTROL;
+
+ } else if (b->out_pos == b->out_size
+ || (b->in_pos == b->in_size
+ && s->temp.size
+ < s->lzma2.compressed)) {
+ return XZ_OK;
+ }
+
+ break;
+
+ case SEQ_COPY:
+ dict_uncompressed(&s->dict, b, &s->lzma2.compressed);
+ if (s->lzma2.compressed > 0)
+ return XZ_OK;
+
+ s->lzma2.sequence = SEQ_CONTROL;
+ break;
+ }
+ }
+
+ return XZ_OK;
+}
+
+struct xz_dec_lzma2 * 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_dec_lzma2_reset(
+ struct xz_dec_lzma2 *s, uint8_t props)
+{
+ /* This limits dictionary size to 3 GiB (39) to keep parsing simpler. */
+ if (props > ( min (DICT_BIT_SIZE,39)) )
+ return XZ_OPTIONS_ERROR;
+
+ s->dict.size = 2 + (props & 1);
+ s->dict.size <<= (props >> 1) + 11;
+
+ if (s->dict.allocated > 0 && s->dict.allocated < s->dict.size)
+ {
+ /* enlarge dictionary buffer */
+ uint8_t * newdict = realloc(s->dict.buf,s->dict.size);
+
+ if (! newdict)
+ return XZ_MEMLIMIT_ERROR;
+
+ s->dict.buf = newdict;
+ s->dict.allocated = s->dict.size;
+ }
+
+ 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_dec_lzma2_end(struct xz_dec_lzma2 *s)
+{
+ if (s->dict.allocated > 0)
+ vfree(s->dict.buf);
+
+ kfree(s);
+}
=== added file 'lib/xzembed/xz_dec_stream.c'
--- lib/xzembed/xz_dec_stream.c 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_dec_stream.c 2010-03-07 00:39:29 +0000
@@ -0,0 +1,854 @@
+/* xz_dec_stream.c - .xz Stream decoder */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#include "xz_config.h"
+#include "xz_private.h"
+#include "xz_stream.h"
+
+#include <grub/crypto.h>
+
+/* Hash used to validate the Index field */
+struct xz_dec_hash {
+ vli_type unpadded;
+ vli_type uncompressed;
+ uint8_t *crc32_context;
+};
+
+struct xz_dec {
+ /* Position in dec_main() */
+ enum {
+ SEQ_STREAM_HEADER,
+ SEQ_BLOCK_START,
+ SEQ_BLOCK_HEADER,
+ SEQ_BLOCK_UNCOMPRESS,
+ SEQ_BLOCK_PADDING,
+ SEQ_BLOCK_CHECK,
+ SEQ_INDEX,
+ SEQ_INDEX_PADDING,
+ SEQ_INDEX_CRC32,
+ SEQ_STREAM_FOOTER
+ } sequence;
+
+ /* Position in variable-length integers and Check fields */
+ uint32_t pos;
+
+ /* Variable-length integer decoded by dec_vli() */
+ vli_type vli;
+
+ /* Saved in_pos and out_pos */
+ size_t in_start;
+ size_t out_start;
+
+ /* CRC32 value in Block or Index */
+ uint32_t crc32_temp; /* need for crc32_validate*/
+ uint8_t *crc32_context;
+
+ /* 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;
+ } 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
+};
+
+/*
+ * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller
+ * must have set s->temp.pos to indicate how much data we are supposed
+ * to copy into s->temp.buf. Return true once s->temp.pos has reached
+ * s->temp.size.
+ */
+static bool fill_temp(struct xz_dec *s, struct xz_buf *b)
+{
+ size_t copy_size = min_t(size_t,
+ b->in_size - b->in_pos, s->temp.size - s->temp.pos);
+
+ memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
+ b->in_pos += copy_size;
+ s->temp.pos += copy_size;
+
+ if (s->temp.pos == s->temp.size) {
+ s->temp.pos = 0;
+ return true;
+ }
+
+ return false;
+}
+
+/* Decode a variable-length integer (little-endian base-128 encoding) */
+static enum xz_ret dec_vli(struct xz_dec *s,
+ const uint8_t *in, size_t *in_pos, size_t in_size)
+{
+ uint8_t byte;
+
+ if (s->pos == 0)
+ s->vli = 0;
+
+ while (*in_pos < in_size) {
+ byte = in[*in_pos];
+ ++*in_pos;
+
+ s->vli |= (vli_type)(byte & 0x7F) << s->pos;
+
+ if ((byte & 0x80) == 0) {
+ /* Don't allow non-minimal encodings. */
+ if (byte == 0 && s->pos != 0)
+ return XZ_DATA_ERROR;
+
+ s->pos = 0;
+ return XZ_STREAM_END;
+ }
+
+ s->pos += 7;
+ if (s->pos == 7 * VLI_BYTES_MAX)
+ return XZ_DATA_ERROR;
+ }
+
+ return XZ_OK;
+}
+
+/*
+ * Decode the Compressed Data field from a Block. Update and validate
+ * the observed compressed and uncompressed sizes of the Block so that
+ * they don't exceed the values possibly stored in the Block Header
+ * (validation assumes that no integer overflow occurs, since vli_type
+ * is normally uint64_t). Update the CRC32 if presence of the CRC32
+ * field was indicated in Stream Header.
+ *
+ * Once the decoding is finished, validate that the observed sizes match
+ * the sizes possibly stored in the Block Header. Update the hash and
+ * Block count, which are later used to validate the Index field.
+ */
+static enum xz_ret dec_block(struct xz_dec *s, struct xz_buf *b)
+{
+ enum xz_ret ret;
+
+ s->in_start = b->in_pos;
+ s->out_start = b->out_pos;
+
+#ifdef XZ_DEC_BCJ
+ if (s->bcj_active)
+ ret = xz_dec_bcj_run(s->bcj, s->lzma2, b);
+ else
+#endif
+ ret = xz_dec_lzma2_run(s->lzma2, b);
+
+ s->block.compressed += b->in_pos - s->in_start;
+ s->block.uncompressed += b->out_pos - s->out_start;
+
+ /*
+ * There is no need to separately check for VLI_UNKNOWN, since
+ * the observed sizes are always smaller than VLI_UNKNOWN.
+ */
+ if (s->block.compressed > s->block_header.compressed
+ || s->block.uncompressed
+ > s->block_header.uncompressed)
+ return XZ_DATA_ERROR;
+
+ if (s->has_crc32)
+ GRUB_MD_CRC32->write(s->crc32_context,b->out + s->out_start,
+ b->out_pos - s->out_start);
+
+ if (ret == XZ_STREAM_END) {
+ if (s->block_header.compressed != VLI_UNKNOWN
+ && s->block_header.compressed
+ != s->block.compressed)
+ return XZ_DATA_ERROR;
+
+ if (s->block_header.uncompressed != VLI_UNKNOWN
+ && s->block_header.uncompressed
+ != s->block.uncompressed)
+ return XZ_DATA_ERROR;
+
+ s->block.hash.unpadded += s->block_header.size
+ + s->block.compressed;
+ if (s->has_crc32)
+ s->block.hash.unpadded += 4;
+
+ s->block.hash.uncompressed += s->block.uncompressed;
+
+ GRUB_MD_CRC32->write(s->block.hash.crc32_context,
+ (const uint8_t *)&s->block.hash, sizeof(s->block.hash));
+
+ ++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;
+ GRUB_MD_CRC32->write(s->crc32_context,b->in + s->in_start, in_used);
+}
+
+/*
+ * 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;
+
+ GRUB_MD_CRC32->write(s->index.hash.crc32_context,
+ (const uint8_t *)&s->index.hash,
+ sizeof(s->index.hash));
+
+ --s->index.count;
+ s->index.sequence = SEQ_INDEX_UNPADDED;
+ break;
+ }
+ } while (s->index.count > 0);
+
+ return XZ_STREAM_END;
+}
+
+/*
+ * Validate that the next four input bytes match the value of s->crc32.
+ * s->pos must be zero when starting to validate the first byte.
+ */
+static enum xz_ret crc32_validate(struct xz_dec *s, struct xz_buf *b)
+{
+ if(s->crc32_temp == 0)
+ {
+ GRUB_MD_CRC32->final(s->crc32_context);
+ s->crc32_temp = get_unaligned_be32(GRUB_MD_CRC32->read(s->crc32_context));
+ }
+
+ do {
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ if (((s->crc32_temp >> s->pos) & 0xFF) != b->in[b->in_pos++])
+ return XZ_DATA_ERROR;
+
+ s->pos += 8;
+
+ } while (s->pos < 32);
+
+ GRUB_MD_CRC32->init(s->crc32_context);
+ s->crc32_temp = 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 dec_stream_header(struct xz_dec *s)
+{
+ if (! memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE))
+ return XZ_FORMAT_ERROR;
+
+ uint8_t crc32_context[GRUB_MD_CRC32->contextsize];
+
+ GRUB_MD_CRC32->init(crc32_context);
+ GRUB_MD_CRC32->write(crc32_context,s->temp.buf + HEADER_MAGIC_SIZE, 2);
+ GRUB_MD_CRC32->final(crc32_context);
+
+ uint32_t resultcrc = get_unaligned_be32(GRUB_MD_CRC32->read(crc32_context));
+ uint32_t readcrc = get_unaligned_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2);
+
+ if(resultcrc != readcrc)
+ 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 dec_stream_footer(struct xz_dec *s)
+{
+ if (! memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE))
+ return XZ_DATA_ERROR;
+
+ uint8_t crc32_context[GRUB_MD_CRC32->contextsize];
+
+ GRUB_MD_CRC32->init(crc32_context);
+ GRUB_MD_CRC32->write(crc32_context, s->temp.buf + 4, 6);
+ GRUB_MD_CRC32->final(crc32_context);
+
+ uint32_t resultcrc = get_unaligned_be32(GRUB_MD_CRC32->read(crc32_context));
+ uint32_t readcrc = get_unaligned_le32(s->temp.buf);
+
+ if(resultcrc != readcrc)
+ 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->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 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;
+
+ uint8_t crc32_context[GRUB_MD_CRC32->contextsize];
+
+ GRUB_MD_CRC32->init(crc32_context);
+ GRUB_MD_CRC32->write(crc32_context, s->temp.buf, s->temp.size);
+ GRUB_MD_CRC32->final(crc32_context);
+
+ uint32_t resultcrc = get_unaligned_be32(GRUB_MD_CRC32->read(crc32_context));
+ uint32_t readcrc = get_unaligned_le32(s->temp.buf + s->temp.size);
+
+ if (resultcrc != readcrc)
+ 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;
+
+ ret = dec_stream_header(s);
+ if (ret != XZ_OK)
+ return ret;
+
+ s->sequence = SEQ_BLOCK_START;
+
+ case SEQ_BLOCK_START:
+ /* We need one byte of input to continue. */
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ /* See if this is the beginning of the Index field. */
+ if (b->in[b->in_pos] == 0) {
+ s->in_start = b->in_pos++;
+ s->sequence = SEQ_INDEX;
+ break;
+ }
+
+ /*
+ * Calculate the size of the Block Header and
+ * prepare to decode it.
+ */
+ s->block_header.size
+ = ((uint32_t)b->in[b->in_pos] + 1) * 4;
+
+ s->temp.size = s->block_header.size;
+ s->temp.pos = 0;
+ s->sequence = SEQ_BLOCK_HEADER;
+
+ case SEQ_BLOCK_HEADER:
+ if (!fill_temp(s, b))
+ return XZ_OK;
+
+ ret = dec_block_header(s);
+ if (ret != XZ_OK)
+ return ret;
+
+ s->sequence = SEQ_BLOCK_UNCOMPRESS;
+
+ case SEQ_BLOCK_UNCOMPRESS:
+ ret = dec_block(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->sequence = SEQ_BLOCK_PADDING;
+
+ case SEQ_BLOCK_PADDING:
+ /*
+ * Size of Compressed Data + Block Padding
+ * must be a multiple of four. We don't need
+ * s->block.compressed for anything else
+ * anymore, so we use it here to test the size
+ * of the Block Padding field.
+ */
+ while (s->block.compressed & 3) {
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ if (b->in[b->in_pos++] != 0)
+ return XZ_DATA_ERROR;
+
+ ++s->block.compressed;
+ }
+
+ s->sequence = SEQ_BLOCK_CHECK;
+
+ case SEQ_BLOCK_CHECK:
+ if (s->has_crc32) {
+ ret = crc32_validate(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+ }
+
+ s->sequence = SEQ_BLOCK_START;
+ break;
+
+ case SEQ_INDEX:
+ ret = dec_index(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->sequence = SEQ_INDEX_PADDING;
+
+ case SEQ_INDEX_PADDING:
+ while ((s->index.size + (b->in_pos - s->in_start))
+ & 3) {
+ if (b->in_pos == b->in_size) {
+ index_update(s, b);
+ return XZ_OK;
+ }
+
+ if (b->in[b->in_pos++] != 0)
+ return XZ_DATA_ERROR;
+ }
+
+ /* Finish the CRC32 value and Index size. */
+ index_update(s, b);
+
+ /* Compare the hashes to validate the Index field. */
+ if (! memeq(&s->block.hash, &s->index.hash, sizeof(s->block.hash)))
+ return XZ_DATA_ERROR;
+
+ s->sequence = SEQ_INDEX_CRC32;
+
+ case SEQ_INDEX_CRC32:
+ ret = crc32_validate(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->temp.size = STREAM_HEADER_SIZE;
+ s->sequence = SEQ_STREAM_FOOTER;
+
+ case SEQ_STREAM_FOOTER:
+ if (!fill_temp(s, b))
+ return XZ_OK;
+
+ return dec_stream_footer(s);
+ }
+ }
+
+ /* Never reached */
+}
+
+/*
+ * xz_dec_run() is a wrapper for dec_main() to handle some special cases in
+ * multi-call and single-call decoding.
+ *
+ * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we
+ * are not going to make any progress anymore. This is to prevent the caller
+ * from calling us infinitely when the input file is truncated or otherwise
+ * corrupt. Since zlib-style API allows that the caller fills the input buffer
+ * only when the decoder doesn't produce any new output, we have to be careful
+ * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only
+ * after the second consecutive call to xz_dec_run() that makes no progress.
+ *
+ * In single-call mode, if we couldn't decode everything and no error
+ * occurred, either the input is truncated or the output buffer is too small.
+ * Since we know that the last input byte never produces any output, we know
+ * that if all the input was consumed and decoding wasn't finished, the file
+ * must be corrupt. Otherwise the output buffer has to be too small or the
+ * file is corrupt in a way that decoding it produces too big output.
+ *
+ * If single-call decoding fails, we reset b->in_pos and b->out_pos back to
+ * their original values. This is because with some filter chains there won't
+ * be any valid uncompressed data in the output buffer unless the decoding
+ * actually succeeds (that's the price to pay of using the output buffer as
+ * the workspace).
+ */
+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 (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_dec_init(uint32_t dict_max)
+{
+ struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return NULL;
+
+ /* prepare CRC32 calculators */
+ if(GRUB_MD_CRC32 == NULL)
+ {
+ kfree(s);
+ return NULL;
+ }
+
+ s->crc32_context = kmalloc(GRUB_MD_CRC32->contextsize, GFP_KERNEL);
+ if (s->crc32_context == NULL)
+ {
+ kfree(s);
+ return NULL;
+ }
+
+ s->index.hash.crc32_context = kmalloc(GRUB_MD_CRC32->contextsize, GFP_KERNEL);
+ if (s->index.hash.crc32_context == NULL)
+ {
+ kfree(s->crc32_context);
+ kfree(s);
+ return NULL;
+ }
+
+ s->block.hash.crc32_context = kmalloc(GRUB_MD_CRC32->contextsize, GFP_KERNEL);
+ if (s->block.hash.crc32_context == NULL)
+ {
+ kfree(s->index.hash.crc32_context);
+ kfree(s->crc32_context);
+ kfree(s);
+ return NULL;
+ }
+
+
+ GRUB_MD_CRC32->init(s->crc32_context);
+ s->crc32_temp = 0;
+ GRUB_MD_CRC32->init(s->index.hash.crc32_context);
+ GRUB_MD_CRC32->init(s->block.hash.crc32_context);
+
+
+ s->single_call = dict_max == 0;
+
+#ifdef XZ_DEC_BCJ
+ s->bcj = xz_dec_bcj_create(s->single_call);
+ if (s->bcj == NULL)
+ goto error_bcj;
+#endif
+
+ s->lzma2 = xz_dec_lzma2_create(dict_max);
+ if (s->lzma2 == NULL)
+ goto error_lzma2;
+
+ xz_dec_reset(s);
+ return s;
+
+error_lzma2:
+#ifdef XZ_DEC_BCJ
+ xz_dec_bcj_end(s->bcj);
+error_bcj:
+#endif
+ kfree(s);
+ return NULL;
+}
+
+void xz_dec_reset(struct xz_dec *s)
+{
+ s->sequence = SEQ_STREAM_HEADER;
+ s->allow_buf_error = false;
+ s->pos = 0;
+
+ memzero(&s->block, sizeof(s->block));
+ memzero(&s->index, sizeof(s->index));
+ s->temp.pos = 0;
+ s->temp.size = STREAM_HEADER_SIZE;
+
+ GRUB_MD_CRC32->init(s->crc32_context);
+ s->crc32_temp = 0;
+ GRUB_MD_CRC32->init(s->index.hash.crc32_context);
+ GRUB_MD_CRC32->init(s->block.hash.crc32_context);
+
+}
+
+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);
+ }
+}
=== added file 'lib/xzembed/xz_lzma2.h'
--- lib/xzembed/xz_lzma2.h 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_lzma2.h 2010-04-06 21:16:23 +0000
@@ -0,0 +1,236 @@
+/* xz_lzma2.h - LZMA2 definitions */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#ifndef XZ_LZMA2_H
+#define XZ_LZMA2_H
+
+/* dictionary size hard limit
+ * actual size limit is calculated as shown in 5.3.1
+ * http://tukaani.org/xz/xz-file-format.txt
+ *
+ * if bits > 39 dictionary_size = UINT32_MAX
+ * else
+ * dictionary_size = 2 | (bits & 1);
+ * dictionary_size <<= bits / 2 + 11;
+ *
+ * i.e.
+ * 0 - 4 KiB
+ * 6 - 32 KiB
+ * 30 - 128MiB
+ * 39 - 3072 MiB
+ * 40 - 4096 MiB - 1 B
+ * note: implementation supports 39 at maximum
+ */
+#define DICT_BIT_SIZE 30
+
+/* 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
=== added file 'lib/xzembed/xz_private.h'
--- lib/xzembed/xz_private.h 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_private.h 2010-02-02 00:23:33 +0000
@@ -0,0 +1,96 @@
+/* xz_private.h - Private includes and definitions */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#ifndef XZ_PRIVATE_H
+#define XZ_PRIVATE_H
+
+/*
+ * 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"
+
+/*
+ * 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().
+ */
+struct xz_dec_lzma2 * 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.
+ */
+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. */
+enum xz_ret xz_dec_lzma2_run(
+ struct xz_dec_lzma2 *s, struct xz_buf *b);
+
+/* Free the memory allocated for the LZMA2 decoder. */
+void xz_dec_lzma2_end(struct xz_dec_lzma2 *s);
+
+/*
+ * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before
+ * calling xz_dec_bcj_run().
+ */
+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.
+ */
+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.
+ */
+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
=== added file 'lib/xzembed/xz_stream.h'
--- lib/xzembed/xz_stream.h 1970-01-01 00:00:00 +0000
+++ lib/xzembed/xz_stream.h 2010-04-06 21:16:45 +0000
@@ -0,0 +1,53 @@
+/* xz_stream.h - Definitions for handling the .xz file format */
+/*
+ * GRUB -- GRand Unified Bootloader
+ * Copyright (C) 2010 Free Software Foundation, Inc.
+ *
+ * GRUB is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GRUB is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GRUB. If not, see <http://www.gnu.org/licenses/>.
+ */
+/*
+ * This file is based on code from XZ embedded project
+ * http://tukaani.org/xz/embedded.html
+ */
+
+#ifndef XZ_STREAM_H
+#define XZ_STREAM_H
+
+/*
+ * See the .xz file format specification at
+ * http://tukaani.org/xz/xz-file-format.txt
+ * to understand the container format.
+ */
+
+#define STREAM_HEADER_SIZE 12
+
+#define HEADER_MAGIC "\3757zXZ\0"
+#define HEADER_MAGIC_SIZE 6
+
+#define FOOTER_MAGIC "YZ"
+#define FOOTER_MAGIC_SIZE 2
+
+/*
+ * Variable-length integer can hold a 63-bit unsigned integer, or a special
+ * value to indicate that the value is unknown.
+ */
+typedef uint64_t vli_type;
+
+#define VLI_MAX ((vli_type)-1 / 2)
+#define VLI_UNKNOWN ((vli_type)-1)
+
+/* Maximum encoded size of a VLI */
+#define VLI_BYTES_MAX (sizeof(vli_type) * 8 / 7)
+
+#endif
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] support for xz compression
2010-04-08 21:55 [PATCH] support for xz compression Szymon Janc
@ 2010-04-11 19:30 ` Szymon Janc
2010-04-15 18:43 ` Szymon Janc
2010-09-05 16:50 ` Vladimir 'φ-coder/phcoder' Serbinenko
1 sibling, 1 reply; 4+ messages in thread
From: Szymon Janc @ 2010-04-11 19:30 UTC (permalink / raw)
To: grub-devel
[-- Attachment #1: Type: Text/Plain, Size: 333 bytes --]
Dnia czwartek 08 kwiecień 2010 o 23:55:28 Szymon Janc napisał(a):
> Hello,
>
> New version with various fixes, most noticable : seek support, respect not
> easly seekable flag, BCJ support.
Attached is a small fix for xzio read to act in grub way, not posix like.
--
Szymon K. Janc
szymon@janc.net.pl // GG: 1383435
[-- Attachment #2: 07a_xzio_fix.diff --]
[-- Type: text/x-patch, Size: 1277 bytes --]
=== modified file 'io/xzio.c'
--- io/xzio.c 2010-04-08 21:44:23 +0000
+++ io/xzio.c 2010-04-10 22:46:52 +0000
@@ -245,8 +245,6 @@
int offset_lock;
grub_uint8_t current_offset;
- xzio->buf.out_size = len >= XZBUFSIZ ? XZBUFSIZ : len;
-
/* If seek backward need to reset decoder and start from beginning of file.
TODO Possible improvement by jumping blocks. */
if (file->offset < xzio->saved_offset)
@@ -259,18 +257,19 @@
grub_file_seek (xzio->file, 0);
}
- offset_lock = (file->offset == xzio->saved_offset) ? 1 : 0;
- current_offset = xzio->saved_offset;
-
- while (len >= xzio->buf.out_size)
+ while (len > 0)
{
+ xzio->buf.out_size = len >= XZBUFSIZ ? XZBUFSIZ : len;
+
+ offset_lock = (file->offset == xzio->saved_offset) ? 1 : 0;
+ current_offset = xzio->saved_offset;
+
/* Feed input. */
if (xzio->buf.in_pos == xzio->buf.in_size)
{
readret = grub_file_read (xzio->file, xzio->inbuf, XZBUFSIZ);
if (readret < 0)
return -1;
-
xzio->buf.in_size = readret;
xzio->buf.in_pos = 0;
}
@@ -317,7 +316,7 @@
}
xzio->buf.out_pos = 0;
- if (xzret == XZ_STREAM_END) /* Stream end, EOF. */
+ if (xzret == XZ_STREAM_END) /* Stream end, EOF. */
break;
}
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] support for xz compression
2010-04-11 19:30 ` Szymon Janc
@ 2010-04-15 18:43 ` Szymon Janc
0 siblings, 0 replies; 4+ messages in thread
From: Szymon Janc @ 2010-04-15 18:43 UTC (permalink / raw)
To: The development of GNU GRUB
[-- Attachment #1: Type: Text/Plain, Size: 346 bytes --]
Dnia niedziela 11 kwiecień 2010 o 21:30:17 Szymon Janc napisał(a):
> Attached is a small fix for xzio read to act in grub way, not posix like.
Attached patch fix a nasty seek bug introduced by previous fix.
If You are brave enough to test xzio don't forget to apply this fix.
--
Szymon K. Janc
szymon@janc.net.pl // GG: 1383435
[-- Attachment #2: 07b_xzio_fix2.diff --]
[-- Type: text/x-patch, Size: 1105 bytes --]
=== modified file 'io/xzio.c'
--- io/xzio.c 2010-04-10 22:47:20 +0000
+++ io/xzio.c 2010-04-15 18:35:28 +0000
@@ -243,7 +243,7 @@
enum xz_ret xzret;
grub_xzio_t xzio = file->data;
int offset_lock;
- grub_uint8_t current_offset;
+ grub_off_t current_offset;
/* If seek backward need to reset decoder and start from beginning of file.
TODO Possible improvement by jumping blocks. */
@@ -257,13 +257,13 @@
grub_file_seek (xzio->file, 0);
}
+ offset_lock = (file->offset == xzio->saved_offset) ? 1 : 0;
+ current_offset = xzio->saved_offset;
+
while (len > 0)
{
xzio->buf.out_size = len >= XZBUFSIZ ? XZBUFSIZ : len;
- offset_lock = (file->offset == xzio->saved_offset) ? 1 : 0;
- current_offset = xzio->saved_offset;
-
/* Feed input. */
if (xzio->buf.in_pos == xzio->buf.in_size)
{
@@ -298,7 +298,7 @@
}
else
{
- grub_uint8_t new_offset = current_offset + xzio->buf.out_pos;
+ grub_off_t new_offset = current_offset + xzio->buf.out_pos;
if (file->offset > new_offset)
current_offset = new_offset;
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] support for xz compression
2010-04-08 21:55 [PATCH] support for xz compression Szymon Janc
2010-04-11 19:30 ` Szymon Janc
@ 2010-09-05 16:50 ` Vladimir 'φ-coder/phcoder' Serbinenko
1 sibling, 0 replies; 4+ messages in thread
From: Vladimir 'φ-coder/phcoder' Serbinenko @ 2010-09-05 16:50 UTC (permalink / raw)
To: grub-devel
[-- Attachment #1: Type: text/plain, Size: 586 bytes --]
On 04/08/2010 11:55 PM, Szymon Janc wrote:
> Hello,
>
> New version with various fixes, most noticable : seek support, respect not
> easly seekable flag, BCJ support.
>
> This patch depends on 04_transparentio.diff from previous post.
>
> Commenst and testing are welcome.
>
>
Merged together with few followup patches and my bugfixing. Thanks
>
>
> _______________________________________________
> Grub-devel mailing list
> Grub-devel@gnu.org
> http://lists.gnu.org/mailman/listinfo/grub-devel
>
--
Regards
Vladimir 'φ-coder/phcoder' Serbinenko
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 294 bytes --]
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2010-09-05 16:50 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-04-08 21:55 [PATCH] support for xz compression Szymon Janc
2010-04-11 19:30 ` Szymon Janc
2010-04-15 18:43 ` Szymon Janc
2010-09-05 16:50 ` Vladimir 'φ-coder/phcoder' Serbinenko
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.