fs/erofs: add custom compression option with optional compress-hints file

Add another option for FS compression that allows fine-grained control using a
list of algorithms and optional compress-hints file. This way multiple
algorithms and pcluster sizes can be used for different files, fully exposing
EROFS compression abilities.

Signed-off-by: Jan Čermák <sairon@sairon.cz>
Signed-off-by: Arnout Vandecappelle <arnout@mind.be>

fs/erofs/Config.in

@@ -22,6 +22,10 @@ choice
 	  slower both in compression and decompression, and higher
 	  compression levels can have noticeable memory requirements.
 
+	  Custom compression allows for advanced configuration of the
+	  compression algorithms, and adds the possibility of
+	  finegrained per-file compression using compression hints.
+
 config BR2_TARGET_ROOTFS_EROFS_NONE
 	bool "no compression"
 
@@ -31,6 +35,9 @@ config BR2_TARGET_ROOTFS_EROFS_LZ4HC
 config BR2_TARGET_ROOTFS_EROFS_LZMA
 	bool "lzma"
 
+config BR2_TARGET_ROOTFS_EROFS_CUSTOM_COMPRESSION
+	bool "custom"
+
 endchoice
 
 if BR2_TARGET_ROOTFS_EROFS_LZ4HC
@@ -58,6 +65,35 @@ config BR2_TARGET_ROOTFS_EROFS_LZMA_LEVEL
 
 endif # BR2_TARGET_ROOTFS_EROFS_LZMA
 
+if BR2_TARGET_ROOTFS_EROFS_CUSTOM_COMPRESSION
+
+config BR2_TARGET_ROOTFS_EROFS_COMPRESSION_ALGORITHMS
+	string "compression algorithms"
+	default "lz4hc,12"
+	help
+	  Specify arbitrary compression option, useful in combination
+	  with compression hints. Individual algorithms are separated
+	  by colon with optional level, e.g. "lz4hc,12:lzma".
+	  See erofs-utils documentaion for detailed information.
+
+config BR2_TARGET_ROOTFS_EROFS_COMPRESSION_HINTS
+	string "path to compression hints file"
+	default ""
+	help
+	  Path to file containing compression hints. Each line in the
+	  file is defined by tokens separated by spaces in the
+	  following form. Optionally, instead of the given primary
+	  algorithm, algorithms can be specified with zero-based
+	  algorithm-index explicitly:
+
+	  <pcluster-size-in-bytes> [algorithm-index] <match-pattern>
+
+	  match-patterns are extended regular expressions, matched
+	  against absolute paths within the output filesystem, with no
+	  leading /.
+
+endif # BR2_TARGET_ROOTFS_EROFS_LZMA
+
 config BR2_TARGET_ROOTFS_EROFS_DEDUPE
 	bool "enable data deduplication"
 	depends on !BR2_TARGET_ROOTFS_EROFS_NONE

fs/erofs/erofs.mk

@@ -10,6 +10,11 @@ ifeq ($(BR2_TARGET_ROOTFS_EROFS_LZ4HC),y)
 ROOTFS_EROFS_ARGS += -zlz4hc,$(BR2_TARGET_ROOTFS_EROFS_LZ4HC_LEVEL)
 else ifeq ($(BR2_TARGET_ROOTFS_EROFS_LZMA),y)
 ROOTFS_EROFS_ARGS += -zlzma,$(BR2_TARGET_ROOTFS_EROFS_LZMA_LEVEL)
+else ifeq ($(BR2_TARGET_ROOTFS_EROFS_CUSTOM_COMPRESSION),y)
+ROOTFS_EROFS_ARGS += -z$(strip $(BR2_TARGET_ROOTFS_EROFS_COMPRESSION_ALGORITHMS))
+ifneq ($(strip $(BR2_TARGET_ROOTFS_EROFS_COMPRESSION_HINTS)),)
+ROOTFS_EROFS_ARGS += --compress-hints $(strip $(BR2_TARGET_ROOTFS_EROFS_COMPRESSION_HINTS))
+endif
 endif
 
 ifeq ($(BR2_REPRODUCIBLE),y)