decompressors: add boot-time XZ support

This implements the API defined in <linux/decompress/generic.h> which is
used for kernel, initramfs, and initrd decompression.  This patch together
with the first patch is enough for XZ-compressed initramfs and initrd;
XZ-compressed kernel will need arch-specific changes.

The buffering requirements described in decompress_unxz.c are stricter
than with gzip, so the relevant changes should be done to the
arch-specific code when adding support for XZ-compressed kernel.
Similarly, the heap size in arch-specific pre-boot code may need to be
increased (30 KiB is enough).

The XZ decompressor needs memmove(), memeq() (memcmp() == 0), and
memzero() (memset(ptr, 0, size)), which aren't available in all
arch-specific pre-boot environments.  I'm including simple versions in
decompress_unxz.c, but a cleaner solution would naturally be nicer.
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>

include/linux/decompress/unxz.h

+/*
+ * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd
+ *
+ * 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 DECOMPRESS_UNXZ_H
+#define DECOMPRESS_UNXZ_H
+
+int unxz(unsigned char *in, int in_size,
+	 int (*fill)(void *dest, unsigned int size),
+	 int (*flush)(void *src, unsigned int size),
+	 unsigned char *out, int *in_used,
+	 void (*error)(char *x));
+
+#endif

init/Kconfig

@@ -130,13 +130,16 @@ config HAVE_KERNEL_BZIP2
 config HAVE_KERNEL_LZMA
 	bool
 
+config HAVE_KERNEL_XZ
+	bool
+
 config HAVE_KERNEL_LZO
 	bool
 
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_LZO
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -181,6 +184,21 @@ config KERNEL_LZMA
 	  two. Compression is slowest.	The kernel size is about 33%
 	  smaller with LZMA in comparison to gzip.
 
+config KERNEL_XZ
+	bool "XZ"
+	depends on HAVE_KERNEL_XZ
+	help
+	  XZ uses the LZMA2 algorithm and instruction set specific
+	  BCJ filters which can improve compression ratio of executable
+	  code. The size of the kernel is about 30% smaller with XZ in
+	  comparison to gzip. On architectures for which there is a BCJ
+	  filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
+	  will create a few percent smaller kernel than plain LZMA.
+
+	  The speed is about the same as with LZMA: The decompression
+	  speed of XZ is better than that of bzip2 but worse than gzip
+	  and LZO. Compression is slow.
+
 config KERNEL_LZO
 	bool "LZO"
 	depends on HAVE_KERNEL_LZO

lib/Kconfig

@@ -122,6 +122,10 @@ config DECOMPRESS_BZIP2
 config DECOMPRESS_LZMA
 	tristate
 
+config DECOMPRESS_XZ
+	select XZ_DEC
+	tristate
+
 config DECOMPRESS_LZO
 	select LZO_DECOMPRESS
 	tristate

lib/Makefile

@@ -75,6 +75,7 @@ obj-$(CONFIG_RAID6_PQ) += raid6/
 lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
 lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o
 lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
+lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
 lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o

lib/decompress.c

@@ -8,6 +8,7 @@
 
 #include <linux/decompress/bunzip2.h>
 #include <linux/decompress/unlzma.h>
+#include <linux/decompress/unxz.h>
 #include <linux/decompress/inflate.h>
 #include <linux/decompress/unlzo.h>
 
@@ -23,6 +24,9 @@
 #ifndef CONFIG_DECOMPRESS_LZMA
 # define unlzma NULL
 #endif
+#ifndef CONFIG_DECOMPRESS_XZ
+# define unxz NULL
+#endif
 #ifndef CONFIG_DECOMPRESS_LZO
 # define unlzo NULL
 #endif
@@ -36,6 +40,7 @@ static const struct compress_format {
 	{ {037, 0236}, "gzip", gunzip },
 	{ {0x42, 0x5a}, "bzip2", bunzip2 },
 	{ {0x5d, 0x00}, "lzma", unlzma },
+	{ {0xfd, 0x37}, "xz", unxz },
 	{ {0x89, 0x4c}, "lzo", unlzo },
 	{ {0, 0}, NULL, NULL }
 };

scripts/gen_initramfs_list.sh

@@ -243,6 +243,8 @@ case "$arg" in
 		echo "$output_file" | grep -q "\.gz$" && compr="gzip -9 -f"
 		echo "$output_file" | grep -q "\.bz2$" && compr="bzip2 -9 -f"
 		echo "$output_file" | grep -q "\.lzma$" && compr="lzma -9 -f"
+		echo "$output_file" | grep -q "\.xz$" && \
+				compr="xz --check=crc32 --lzma2=dict=1MiB"
 		echo "$output_file" | grep -q "\.lzo$" && compr="lzop -9 -f"
 		echo "$output_file" | grep -q "\.cpio$" && compr="cat"
 		shift

usr/Kconfig

@@ -72,6 +72,15 @@ config RD_LZMA
 	  Support loading of a LZMA encoded initial ramdisk or cpio buffer
 	  If unsure, say N.
 
+config RD_XZ
+	bool "Support initial ramdisks compressed using XZ" if EMBEDDED
+	default !EMBEDDED
+	depends on BLK_DEV_INITRD
+	select DECOMPRESS_XZ
+	help
+	  Support loading of a XZ encoded initial ramdisk or cpio buffer.
+	  If unsure, say N.
+
 config RD_LZO
 	bool "Support initial ramdisks compressed using LZO" if EMBEDDED
 	default !EMBEDDED
@@ -139,6 +148,15 @@ config INITRAMFS_COMPRESSION_LZMA
 	  three. Compression is slowest. The initramfs size is about 33%
 	  smaller with LZMA in comparison to gzip.
 
+config INITRAMFS_COMPRESSION_XZ
+	bool "XZ"
+	depends on RD_XZ
+	help
+	  XZ uses the LZMA2 algorithm. The initramfs size is about 30%
+	  smaller with XZ in comparison to gzip. Decompression speed
+	  is better than that of bzip2 but worse than gzip and LZO.
+	  Compression is slow.
+
 config INITRAMFS_COMPRESSION_LZO
 	bool "LZO"
 	depends on RD_LZO

usr/Makefile

@@ -15,6 +15,9 @@ suffix_$(CONFIG_INITRAMFS_COMPRESSION_BZIP2)  = .bz2
 # Lzma
 suffix_$(CONFIG_INITRAMFS_COMPRESSION_LZMA)   = .lzma
 
+# XZ
+suffix_$(CONFIG_INITRAMFS_COMPRESSION_XZ)     = .xz
+
 # Lzo
 suffix_$(CONFIG_INITRAMFS_COMPRESSION_LZO)   = .lzo
 
@@ -50,7 +53,7 @@ endif
 quiet_cmd_initfs = GEN     $@
       cmd_initfs = $(initramfs) -o $@ $(ramfs-args) $(ramfs-input)
 
-targets := initramfs_data.cpio.gz initramfs_data.cpio.bz2 initramfs_data.cpio.lzma initramfs_data.cpio.lzo initramfs_data.cpio
+targets := initramfs_data.cpio.gz initramfs_data.cpio.bz2 initramfs_data.cpio.lzma initramfs_data.cpio.xz initramfs_data.cpio.lzo initramfs_data.cpio
 # do not try to update files included in initramfs
 $(deps_initramfs): ;