decompressors: add XZ decompressor module

In userspace, the .lzma format has become mostly a legacy file format that
got superseded by the .xz format.  Similarly, LZMA Utils was superseded by
XZ Utils.

These patches add support for XZ decompression into the kernel.  Most of
the code is as is from XZ Embedded <http://tukaani.org/xz/embedded.html>.
It was written for the Linux kernel but is usable in other projects too.

Advantages of XZ over the current LZMA code in the kernel:
  - Nice API that can be used by other kernel modules; it's
    not limited to kernel, initramfs, and initrd decompression.
  - Integrity check support (CRC32)
  - BCJ filters improve compression of executable code on
    certain architectures. These together with LZMA2 can
    produce a few percent smaller kernel or Squashfs images
    than plain LZMA without making the decompression slower.

This patch: Add the main decompression code (xz_dec), testing module
(xz_dec_test), wrapper script (xz_wrap.sh) for the xz command line tool,
and documentation.  The xz_dec module is enough to have a usable XZ
decompressor e.g.  for Squashfs.

Signed-off-by: Lasse Collin <lasse.collin@tukaani.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Alain Knaff <alain@knaff.lu>
Cc: Albin Tonnerre <albin.tonnerre@free-electrons.com>
Cc: Phillip Lougher <phillip@lougher.demon.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 156 insertions, 0 deletions

diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h
new file mode 100644
index 000000000000..a65633e06962
--- /dev/null
+++ b/lib/xz/xz_private.h
@@ -0,0 +1,156 @@
+/*
+ * Private includes and definitions
+ *
+ * Author: Lasse Collin <lasse.collin@tukaani.org>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_PRIVATE_H
+#define XZ_PRIVATE_H
+
+#ifdef __KERNEL__
+#       include <linux/xz.h>
+#       include <asm/byteorder.h>
+#       include <asm/unaligned.h>
+        /* XZ_PREBOOT may be defined only via decompress_unxz.c. */
+#       ifndef XZ_PREBOOT
+#               include <linux/slab.h>
+#               include <linux/vmalloc.h>
+#               include <linux/string.h>
+#               ifdef CONFIG_XZ_DEC_X86
+#                       define XZ_DEC_X86
+#               endif
+#               ifdef CONFIG_XZ_DEC_POWERPC
+#                       define XZ_DEC_POWERPC
+#               endif
+#               ifdef CONFIG_XZ_DEC_IA64
+#                       define XZ_DEC_IA64
+#               endif
+#               ifdef CONFIG_XZ_DEC_ARM
+#                       define XZ_DEC_ARM
+#               endif
+#               ifdef CONFIG_XZ_DEC_ARMTHUMB
+#                       define XZ_DEC_ARMTHUMB
+#               endif
+#               ifdef CONFIG_XZ_DEC_SPARC
+#                       define XZ_DEC_SPARC
+#               endif
+#               define memeq(a, b, size) (memcmp(a, b, size) == 0)
+#               define memzero(buf, size) memset(buf, 0, size)
+#       endif
+#       define get_le32(p) le32_to_cpup((const uint32_t *)(p))
+#else
+        /*
+         * For userspace builds, use a separate header to define the required
+         * macros and functions. This makes it easier to adapt the code into
+         * different environments and avoids clutter in the Linux kernel tree.
+         */
+#       include "xz_config.h"
+#endif
+
+/* If no specific decoding mode is requested, enable support for all modes. */
+#if !defined(XZ_DEC_SINGLE) && !defined(XZ_DEC_PREALLOC) \
+                && !defined(XZ_DEC_DYNALLOC)
+#       define XZ_DEC_SINGLE
+#       define XZ_DEC_PREALLOC
+#       define XZ_DEC_DYNALLOC
+#endif
+
+/*
+ * The DEC_IS_foo(mode) macros are used in "if" statements. If only some
+ * of the supported modes are enabled, these macros will evaluate to true or
+ * false at compile time and thus allow the compiler to omit unneeded code.
+ */
+#ifdef XZ_DEC_SINGLE
+#       define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
+#else
+#       define DEC_IS_SINGLE(mode) (false)
+#endif
+
+#ifdef XZ_DEC_PREALLOC
+#       define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC)
+#else
+#       define DEC_IS_PREALLOC(mode) (false)
+#endif
+
+#ifdef XZ_DEC_DYNALLOC
+#       define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC)
+#else
+#       define DEC_IS_DYNALLOC(mode) (false)
+#endif
+
+#if !defined(XZ_DEC_SINGLE)
+#       define DEC_IS_MULTI(mode) (true)
+#elif defined(XZ_DEC_PREALLOC) || defined(XZ_DEC_DYNALLOC)
+#       define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE)
+#else
+#       define DEC_IS_MULTI(mode) (false)
+#endif
+
+/*
+ * If any of the BCJ filter decoders are wanted, define XZ_DEC_BCJ.
+ * XZ_DEC_BCJ is used to enable generic support for BCJ decoders.
+ */
+#ifndef XZ_DEC_BCJ
+#       if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \
+                        || defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \
+                        || defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \
+                        || defined(XZ_DEC_SPARC)
+#               define XZ_DEC_BCJ
+#       endif
+#endif
+
+/*
+ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
+ * before calling xz_dec_lzma2_run().
+ */
+XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode,
+                                                   uint32_t dict_max);
+
+/*
+ * Decode the LZMA2 properties (one byte) and reset the decoder. Return
+ * XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not
+ * big enough, and XZ_OPTIONS_ERROR if props indicates something that this
+ * decoder doesn't support.
+ */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s,
+                                         uint8_t props);
+
+/* Decode raw LZMA2 stream from b->in to b->out. */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
+                                       struct xz_buf *b);
+
+/* Free the memory allocated for the LZMA2 decoder. */
+XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s);
+
+#ifdef XZ_DEC_BCJ
+/*
+ * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before
+ * calling xz_dec_bcj_run().
+ */
+XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call);
+
+/*
+ * Decode the Filter ID of a BCJ filter. This implementation doesn't
+ * support custom start offsets, so no decoding of Filter Properties
+ * is needed. Returns XZ_OK if the given Filter ID is supported.
+ * Otherwise XZ_OPTIONS_ERROR is returned.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id);
+
+/*
+ * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is
+ * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run()
+ * must be called directly.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
+                                     struct xz_dec_lzma2 *lzma2,
+                                     struct xz_buf *b);
+
+/* Free the memory allocated for the BCJ filters. */
+#define xz_dec_bcj_end(s) kfree(s)
+#endif
+
+#endif