xz_wrap.sh: Adjust arch-specific options for better compression.

Use LZMA2 options that match the arch-specific alignment of instructions.
This change reduces compressed kernel size 0-2 % depending on the arch.
On 1-byte-aligned x86 it makes no difference and on 4-byte-aligned archs
it helps the most.

Use the ARM-Thumb filter for ARM-Thumb2 kernels. This reduces compressed
kernel size about 5 %. Previously such kernels were compressed using
the ARM filter which didn't do anything useful with ARM-Thumb2 code.

Add BCJ filter support for ARM64 and RISC-V. On ARM64 the compressed
kernel size is reduced about 5 % and on RISC-V by 7-8 %. These require
new enough version of the xz tool. With an old xz version a message is
printed to standard error and compression is done without the filter.

Update lib/decompress_unxz.c to match the changes to xz_wrap.sh.

Thanks to Jubin Zhong for pointing out that CONFIG_THUMB2_KERNEL
should be used to detect which BCJ filter is used on 32-bit ARM.

    https://lore.kernel.org/lkml/1637379771-39449-1-git-send-email-zhongjubin@huawei.com/

It never got merged into Linux. That patch sourced the whole auto.conf
file as a shell script instead of using grep like is done in this commit.

2 files changed, 148 insertions, 7 deletions

diff --git a/linux/lib/decompress_unxz.c b/linux/lib/decompress_unxz.c
index 46aa3be..cae0039 100644
--- a/linux/lib/decompress_unxz.c
+++ b/linux/lib/decompress_unxz.c
@@ -126,11 +126,21 @@
 #ifdef CONFIG_X86
 #	define XZ_DEC_X86
 #endif
-#ifdef CONFIG_PPC
+#if defined(CONFIG_PPC) && defined(CONFIG_CPU_BIG_ENDIAN)
 #	define XZ_DEC_POWERPC
 #endif
 #ifdef CONFIG_ARM
-#	define XZ_DEC_ARM
+#	ifdef CONFIG_THUMB2_KERNEL
+#		define XZ_DEC_ARMTHUMB
+#	else
+#		define XZ_DEC_ARM
+#	endif
+#endif
+#ifdef CONFIG_ARM64
+#	define XZ_DEC_ARM64
+#endif
+#ifdef CONFIG_RISCV
+#	define XZ_DEC_RISCV
 #endif
 #ifdef CONFIG_SPARC
 #	define XZ_DEC_SPARC
diff --git a/linux/scripts/xz_wrap.sh b/linux/scripts/xz_wrap.sh
index c8c3644..5bdf0c3 100755
--- a/linux/scripts/xz_wrap.sh
+++ b/linux/scripts/xz_wrap.sh
@@ -6,14 +6,145 @@
 #
 # Author: Lasse Collin <lasse.collin@tukaani.org>
 
+# This has specialized settings for the following archs. However,
+# XZ-compressed kernel isn't currently supported on every listed arch.
+#
+#   Arch        Align   Notes
+#   arm          2/4    ARM and ARM-Thumb2
+#   arm64         4
+#   csky          2
+#   loongarch     4
+#   mips         2/4    MicroMIPS is 2-byte aligned
+#   parisc        4
+#   powerpc       4     Uses its own wrapper for compressors instead of this.
+#   riscv        2/4
+#   s390          2
+#   sh            2
+#   sparc         4
+#   x86           1
+
+# A few archs use 2-byte or 4-byte aligned instructions depending on
+# the kernel config. This function is used to check if the relevant
+# config option is set to "y".
+is_enabled()
+{
+	grep -q "^$1=y$" include/config/auto.conf
+}
+
+# Set XZ_VERSION (and LIBLZMA_VERSION). This is needed to disable features
+# that aren't available in old XZ Utils versions.
+eval "$($XZ --robot --version)" || exit
+
+# Assume that no BCJ filter is available.
 BCJ=
-LZMA2OPTS=
 
+# Set the instruction alignment to 1, 2, or 4 bytes.
+#
+# Set the BCJ filter if one is available.
+# It must match the #ifdef usage in lib/decompress_unxz.c.
 case $SRCARCH in
-	x86)            BCJ=--x86 ;;
-	powerpc)        BCJ=--powerpc ;;
-	arm)            BCJ=--arm ;;
-	sparc)          BCJ=--sparc ;;
+	arm)
+		if is_enabled CONFIG_THUMB2_KERNEL; then
+			ALIGN=2
+			BCJ=--armthumb
+		else
+			ALIGN=4
+			BCJ=--arm
+		fi
+		;;
+
+	arm64)
+		ALIGN=4
+
+		# ARM64 filter was added in XZ Utils 5.4.0.
+		if [ "$XZ_VERSION" -ge 50040002 ]; then
+			BCJ=--arm64
+		else
+			echo "$0: Upgrading to xz >= 5.4.0" \
+				"would enable the ARM64 filter" \
+				"for better compression" >&2
+		fi
+		;;
+
+	csky)
+		ALIGN=2
+		;;
+
+	loongarch)
+		ALIGN=4
+		;;
+
+	mips)
+		if is_enabled CONFIG_CPU_MICROMIPS; then
+			ALIGN=2
+		else
+			ALIGN=4
+		fi
+		;;
+
+	parisc)
+		ALIGN=4
+		;;
+
+	powerpc)
+		ALIGN=4
+
+		# The filter is only for big endian instruction encoding.
+		if is_enabled CONFIG_CPU_BIG_ENDIAN; then
+			BCJ=--powerpc
+		fi
+		;;
+
+	riscv)
+		if is_enabled CONFIG_RISCV_ISA_C; then
+			ALIGN=2
+		else
+			ALIGN=4
+		fi
+
+		# RISC-V filter was added in XZ Utils 5.6.0.
+		if [ "$XZ_VERSION" -ge 50060002 ]; then
+			BCJ=--riscv
+		else
+			echo "$0: Upgrading to xz >= 5.6.0" \
+				"would enable the RISC-V filter" \
+				"for better compression" >&2
+		fi
+		;;
+
+	s390)
+		ALIGN=2
+		;;
+
+	sh)
+		ALIGN=2
+		;;
+
+	sparc)
+		ALIGN=4
+		BCJ=--sparc
+		;;
+
+	x86)
+		ALIGN=1
+		BCJ=--x86
+		;;
+
+	*)
+		echo "$0: Arch-specific tuning is missing for '$SRCARCH'" >&2
+
+		# Guess 2-byte-aligned instructions. Guessing too low
+		# should hurt less than guessing too high.
+		ALIGN=2
+		;;
+esac
+
+# Select the LZMA2 options matching the instruction alignment.
+case $ALIGN in
+	1)  LZMA2OPTS= ;;
+	2)  LZMA2OPTS=lp=1 ;;
+	4)  LZMA2OPTS=lp=2,lc=2 ;;
+	*)  echo "$0: ALIGN wrong or missing" >&2; exit 1 ;;
 esac
 
 # Use single-threaded mode because it compresses a little better