From 7599715ae66f17ff00e745925e3775b72cbca2fd Mon Sep 17 00:00:00 2001 From: Pete Batard Date: Mon, 29 Dec 2014 20:34:41 +0000 Subject: [PATCH] [cmp] add decompression support * Adds .Z, .gz, .lzma, .xz and .bz2 decompression support for DD images using the Bled library (https://github.com/pbatard/bled). * Closes #269 --- .gitattributes | 1 + .gitignore | 6 + configure | 19 +- configure.ac | 7 +- rufus.sln | 11 +- src/.msvc/rufus.vcxproj | 5 +- src/.msvc/rufus.vcxproj.filters | 6 +- src/.msvc/rufus_sources | 3 +- src/Makefile.am | 4 +- src/Makefile.in | 6 +- src/bled/.msvc/bled.vcxproj | 176 ++++ src/bled/.msvc/bled.vcxproj.filters | 114 +++ src/bled/.msvc/bled_sources | 20 + src/bled/Makefile.am | 8 + src/bled/Makefile.in | 642 +++++++++++++ src/bled/bb_archive.h | 262 ++++++ src/bled/bled.c | 139 +++ src/bled/bled.h | 41 + src/bled/crc32.c | 257 ++++++ src/bled/data_align.c | 15 + src/bled/data_extract_all.c | 213 +++++ src/bled/data_skip.c | 12 + src/bled/decompress_bunzip2.c | 829 +++++++++++++++++ src/bled/decompress_gunzip.c | 1271 ++++++++++++++++++++++++++ src/bled/decompress_uncompress.c | 315 +++++++ src/bled/decompress_unlzma.c | 468 ++++++++++ src/bled/decompress_unxz.c | 131 +++ src/bled/filter_accept_all.c | 17 + src/bled/filter_accept_list.c | 19 + src/bled/filter_accept_reject_list.c | 38 + src/bled/find_list_entry.c | 54 ++ src/bled/header_list.c | 12 + src/bled/header_skip.c | 10 + src/bled/header_verbose_list.c | 69 ++ src/bled/init_handle.c | 22 + src/bled/libbb.h | 233 +++++ src/bled/open_transformer.c | 351 +++++++ src/bled/platform.h | 621 +++++++++++++ src/bled/seek_by_jump.c | 19 + src/bled/seek_by_read.c | 16 + src/bled/xz.h | 282 ++++++ src/bled/xz_config.h | 123 +++ src/bled/xz_dec_bcj.c | 580 ++++++++++++ src/bled/xz_dec_lzma2.c | 1174 ++++++++++++++++++++++++ src/bled/xz_dec_stream.c | 822 +++++++++++++++++ src/bled/xz_lzma2.h | 204 +++++ src/bled/xz_private.h | 159 ++++ src/bled/xz_stream.h | 62 ++ src/format.c | 131 +-- src/msapi_utf8.h | 12 +- src/msvc-missing/stdbool.h | 16 + src/rufus.c | 2 + src/rufus.h | 2 + src/rufus.rc | 16 +- src/vhd.c | 45 +- wdk_build.cmd | 17 +- 56 files changed, 10020 insertions(+), 89 deletions(-) create mode 100644 src/bled/.msvc/bled.vcxproj create mode 100644 src/bled/.msvc/bled.vcxproj.filters create mode 100644 src/bled/.msvc/bled_sources create mode 100644 src/bled/Makefile.am create mode 100644 src/bled/Makefile.in create mode 100644 src/bled/bb_archive.h create mode 100644 src/bled/bled.c create mode 100644 src/bled/bled.h create mode 100644 src/bled/crc32.c create mode 100644 src/bled/data_align.c create mode 100644 src/bled/data_extract_all.c create mode 100644 src/bled/data_skip.c create mode 100644 src/bled/decompress_bunzip2.c create mode 100644 src/bled/decompress_gunzip.c create mode 100644 src/bled/decompress_uncompress.c create mode 100644 src/bled/decompress_unlzma.c create mode 100644 src/bled/decompress_unxz.c create mode 100644 src/bled/filter_accept_all.c create mode 100644 src/bled/filter_accept_list.c create mode 100644 src/bled/filter_accept_reject_list.c create mode 100644 src/bled/find_list_entry.c create mode 100644 src/bled/header_list.c create mode 100644 src/bled/header_skip.c create mode 100644 src/bled/header_verbose_list.c create mode 100644 src/bled/init_handle.c create mode 100644 src/bled/libbb.h create mode 100644 src/bled/open_transformer.c create mode 100644 src/bled/platform.h create mode 100644 src/bled/seek_by_jump.c create mode 100644 src/bled/seek_by_read.c create mode 100644 src/bled/xz.h create mode 100644 src/bled/xz_config.h create mode 100644 src/bled/xz_dec_bcj.c create mode 100644 src/bled/xz_dec_lzma2.c create mode 100644 src/bled/xz_dec_stream.c create mode 100644 src/bled/xz_lzma2.h create mode 100644 src/bled/xz_private.h create mode 100644 src/bled/xz_stream.h create mode 100644 src/msvc-missing/stdbool.h diff --git a/.gitattributes b/.gitattributes index 224d7139..4a2d2938 100644 --- a/.gitattributes +++ b/.gitattributes @@ -12,6 +12,7 @@ install-sh eol=lf *.txt eol=crlf *.loc eol=crlf *.sh export-ignore +*.cmd export-ignore .gitattributes export-ignore .gitignore export-ignore *.creole export-ignore diff --git a/.gitignore b/.gitignore index e2892de5..8f38e494 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,4 @@ +*.a *.aps *.dep *.exe @@ -16,11 +17,16 @@ *.pdb *.plg *.res +*.sdf *.suo *.swp +*.tlog *.user +*.opensdf +*.o_manifest .deps .libs +Makefile x86_32 x86_64 autom4te.cache diff --git a/configure b/configure index d2d21a39..69c78809 100644 --- a/configure +++ b/configure @@ -3797,11 +3797,7 @@ ac_config_files="$ac_config_files Makefile" ac_config_files="$ac_config_files src/Makefile" -ac_config_files="$ac_config_files src/ms-sys/Makefile" - -ac_config_files="$ac_config_files src/syslinux/libfat/Makefile" - -ac_config_files="$ac_config_files src/syslinux/libinstaller/Makefile" +ac_config_files="$ac_config_files src/bled/Makefile" ac_config_files="$ac_config_files src/libcdio/iso9660/Makefile" @@ -3811,6 +3807,12 @@ ac_config_files="$ac_config_files src/libcdio/driver/Makefile" ac_config_files="$ac_config_files res/localization/Makefile" +ac_config_files="$ac_config_files src/ms-sys/Makefile" + +ac_config_files="$ac_config_files src/syslinux/libfat/Makefile" + +ac_config_files="$ac_config_files src/syslinux/libinstaller/Makefile" + cat >confcache <<\_ACEOF # This file is a shell script that caches the results of configure # tests run on this system so they can be shared between configure @@ -4538,13 +4540,14 @@ do case $ac_config_target in "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;; "src/Makefile") CONFIG_FILES="$CONFIG_FILES src/Makefile" ;; - "src/ms-sys/Makefile") CONFIG_FILES="$CONFIG_FILES src/ms-sys/Makefile" ;; - "src/syslinux/libfat/Makefile") CONFIG_FILES="$CONFIG_FILES src/syslinux/libfat/Makefile" ;; - "src/syslinux/libinstaller/Makefile") CONFIG_FILES="$CONFIG_FILES src/syslinux/libinstaller/Makefile" ;; + "src/bled/Makefile") CONFIG_FILES="$CONFIG_FILES src/bled/Makefile" ;; "src/libcdio/iso9660/Makefile") CONFIG_FILES="$CONFIG_FILES src/libcdio/iso9660/Makefile" ;; "src/libcdio/udf/Makefile") CONFIG_FILES="$CONFIG_FILES src/libcdio/udf/Makefile" ;; "src/libcdio/driver/Makefile") CONFIG_FILES="$CONFIG_FILES src/libcdio/driver/Makefile" ;; "res/localization/Makefile") CONFIG_FILES="$CONFIG_FILES res/localization/Makefile" ;; + "src/ms-sys/Makefile") CONFIG_FILES="$CONFIG_FILES src/ms-sys/Makefile" ;; + "src/syslinux/libfat/Makefile") CONFIG_FILES="$CONFIG_FILES src/syslinux/libfat/Makefile" ;; + "src/syslinux/libinstaller/Makefile") CONFIG_FILES="$CONFIG_FILES src/syslinux/libinstaller/Makefile" ;; *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;; esac diff --git a/configure.ac b/configure.ac index a6afb1e9..8fd607ad 100644 --- a/configure.ac +++ b/configure.ac @@ -63,11 +63,12 @@ AC_SUBST([SUFFIX]) AC_CONFIG_FILES([Makefile]) AC_CONFIG_FILES([src/Makefile]) -AC_CONFIG_FILES([src/ms-sys/Makefile]) -AC_CONFIG_FILES([src/syslinux/libfat/Makefile]) -AC_CONFIG_FILES([src/syslinux/libinstaller/Makefile]) +AC_CONFIG_FILES([src/bled/Makefile]) AC_CONFIG_FILES([src/libcdio/iso9660/Makefile]) AC_CONFIG_FILES([src/libcdio/udf/Makefile]) AC_CONFIG_FILES([src/libcdio/driver/Makefile]) AC_CONFIG_FILES([res/localization/Makefile]) +AC_CONFIG_FILES([src/ms-sys/Makefile]) +AC_CONFIG_FILES([src/syslinux/libfat/Makefile]) +AC_CONFIG_FILES([src/syslinux/libinstaller/Makefile]) AC_OUTPUT diff --git a/rufus.sln b/rufus.sln index 22b7b80c..d44f53dd 100644 --- a/rufus.sln +++ b/rufus.sln @@ -1,4 +1,3 @@ - Microsoft Visual Studio Solution File, Format Version 12.00 # Visual Studio 2013 VisualStudioVersion = 12.0.31101.0 @@ -19,6 +18,8 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "libcdio-driver", "src\libcd EndProject Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "getopt", "src\getopt\.msvc\getopt.vcxproj", "{AE83E1B4-CE06-47EE-B7A3-C3A1D7C2D71E}" EndProject +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bled", "src\bled\.msvc\bled.vcxproj", "{FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}" +EndProject Global GlobalSection(SolutionConfigurationPlatforms) = preSolution Debug|Win32 = Debug|Win32 @@ -91,6 +92,14 @@ Global {AE83E1B4-CE06-47EE-B7A3-C3A1D7C2D71E}.Release|Win32.Build.0 = Release|Win32 {AE83E1B4-CE06-47EE-B7A3-C3A1D7C2D71E}.Release|x64.ActiveCfg = Release|x64 {AE83E1B4-CE06-47EE-B7A3-C3A1D7C2D71E}.Release|x64.Build.0 = Release|x64 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Debug|Win32.ActiveCfg = Debug|Win32 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Debug|Win32.Build.0 = Debug|Win32 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Debug|x64.ActiveCfg = Debug|x64 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Debug|x64.Build.0 = Debug|x64 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Release|Win32.ActiveCfg = Release|Win32 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Release|Win32.Build.0 = Release|Win32 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Release|x64.ActiveCfg = Release|x64 + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D}.Release|x64.Build.0 = Release|x64 EndGlobalSection GlobalSection(SolutionProperties) = preSolution HideSolutionNode = FALSE diff --git a/src/.msvc/rufus.vcxproj b/src/.msvc/rufus.vcxproj index 387814de..64360b8b 100644 --- a/src/.msvc/rufus.vcxproj +++ b/src/.msvc/rufus.vcxproj @@ -199,12 +199,12 @@ + - @@ -231,6 +231,9 @@ + + {fb6d52d4-a2f8-c358-db85-bbcaecfddd7d} + {ae83e1b4-ce06-47ee-b7a3-c3a1d7c2d71e} diff --git a/src/.msvc/rufus.vcxproj.filters b/src/.msvc/rufus.vcxproj.filters index 9ed84c82..7da8b596 100644 --- a/src/.msvc/rufus.vcxproj.filters +++ b/src/.msvc/rufus.vcxproj.filters @@ -98,9 +98,6 @@ Header Files - - Header Files - Header Files @@ -128,6 +125,9 @@ Header Files + + Header Files + diff --git a/src/.msvc/rufus_sources b/src/.msvc/rufus_sources index 6c33871c..8d57cc9d 100644 --- a/src/.msvc/rufus_sources +++ b/src/.msvc/rufus_sources @@ -3,7 +3,7 @@ TARGETTYPE=PROGRAM UMTYPE=windows UMENTRY=winmain -INCLUDES=$(DDK_INC_PATH);.\ms-sys\inc;.\syslinux\libfat;.\syslinux\libinstaller;.\msvc-missing;.\libcdio;.\getopt +INCLUDES=$(DDK_INC_PATH);.\ms-sys\inc;.\syslinux\libfat;.\syslinux\libinstaller;.\msvc-missing;.\libcdio;.\getopt;.\bled C_DEFINES = $(C_DEFINES) /DDDKBUILD /DUNICODE /D_UNICODE /DRUFUS_LOC /DISOLATION_AWARE_ENABLED !IFNDEF MSC_WARNING_LEVEL @@ -19,6 +19,7 @@ TARGETLIBS=$(SDK_LIB_PATH)\kernel32.lib \ $(SDK_LIB_PATH)\shell32.lib \ $(SDK_LIB_PATH)\wininet.lib \ $(SDK_LIB_PATH)\shlwapi.lib \ + .\bled\bled.lib \ .\ms-sys\ms-sys.lib \ .\syslinux\libfat\libfat.lib \ .\syslinux\libinstaller\libinstaller.lib \ diff --git a/src/Makefile.am b/src/Makefile.am index ec6f107c..1ac4b773 100644 --- a/src/Makefile.am +++ b/src/Makefile.am @@ -1,4 +1,4 @@ -SUBDIRS = ms-sys syslinux/libfat syslinux/libinstaller libcdio/iso9660 libcdio/udf libcdio/driver ../res/localization +SUBDIRS = bled ms-sys syslinux/libfat syslinux/libinstaller libcdio/iso9660 libcdio/udf libcdio/driver ../res/localization noinst_PROGRAMS = rufus @@ -13,5 +13,5 @@ AM_V_WINDRES = $(AM_V_WINDRES_$(V)) rufus_SOURCES = drive.c icon.c parser.c localization.c iso.c net.c dos.c dos_locale.c badblocks.c syslinux.c usb.c vhd.c format.c smart.c stdio.c stdfn.c stdlg.c rufus.c rufus_CFLAGS = -I./ms-sys/inc -I./syslinux/libfat -I./syslinux/libinstaller -I./libcdio $(AM_CFLAGS) rufus_LDFLAGS = $(AM_LDFLAGS) -mwindows -rufus_LDADD = rufus_rc.o ms-sys/libmssys.a syslinux/libfat/libfat.a syslinux/libinstaller/libinstaller.a \ +rufus_LDADD = rufus_rc.o bled/libbled.a ms-sys/libmssys.a syslinux/libfat/libfat.a syslinux/libinstaller/libinstaller.a \ libcdio/iso9660/libiso9660.a libcdio/udf/libudf.a libcdio/driver/libdriver.a -lsetupapi -lole32 -lgdi32 -lwininet -lshlwapi diff --git a/src/Makefile.in b/src/Makefile.in index 26d4e82d..e7bfa043 100644 --- a/src/Makefile.in +++ b/src/Makefile.in @@ -97,7 +97,7 @@ am_rufus_OBJECTS = rufus-drive.$(OBJEXT) rufus-icon.$(OBJEXT) \ rufus-stdfn.$(OBJEXT) rufus-stdlg.$(OBJEXT) \ rufus-rufus.$(OBJEXT) rufus_OBJECTS = $(am_rufus_OBJECTS) -rufus_DEPENDENCIES = rufus_rc.o ms-sys/libmssys.a \ +rufus_DEPENDENCIES = rufus_rc.o bled/libbled.a ms-sys/libmssys.a \ syslinux/libfat/libfat.a syslinux/libinstaller/libinstaller.a \ libcdio/iso9660/libiso9660.a libcdio/udf/libudf.a \ libcdio/driver/libdriver.a @@ -263,7 +263,7 @@ target_alias = @target_alias@ top_build_prefix = @top_build_prefix@ top_builddir = @top_builddir@ top_srcdir = @top_srcdir@ -SUBDIRS = ms-sys syslinux/libfat syslinux/libinstaller libcdio/iso9660 libcdio/udf libcdio/driver ../res/localization +SUBDIRS = bled ms-sys syslinux/libfat syslinux/libinstaller libcdio/iso9660 libcdio/udf libcdio/driver ../res/localization AM_V_WINDRES_0 = @echo " RC $@";$(WINDRES) AM_V_WINDRES_1 = $(WINDRES) AM_V_WINDRES_ = $(AM_V_WINDRES_$(AM_DEFAULT_VERBOSITY)) @@ -271,7 +271,7 @@ AM_V_WINDRES = $(AM_V_WINDRES_$(V)) rufus_SOURCES = drive.c icon.c parser.c localization.c iso.c net.c dos.c dos_locale.c badblocks.c syslinux.c usb.c vhd.c format.c smart.c stdio.c stdfn.c stdlg.c rufus.c rufus_CFLAGS = -I./ms-sys/inc -I./syslinux/libfat -I./syslinux/libinstaller -I./libcdio $(AM_CFLAGS) rufus_LDFLAGS = $(AM_LDFLAGS) -mwindows -rufus_LDADD = rufus_rc.o ms-sys/libmssys.a syslinux/libfat/libfat.a syslinux/libinstaller/libinstaller.a \ +rufus_LDADD = rufus_rc.o bled/libbled.a ms-sys/libmssys.a syslinux/libfat/libfat.a syslinux/libinstaller/libinstaller.a \ libcdio/iso9660/libiso9660.a libcdio/udf/libudf.a libcdio/driver/libdriver.a -lsetupapi -lole32 -lgdi32 -lwininet -lshlwapi all: all-recursive diff --git a/src/bled/.msvc/bled.vcxproj b/src/bled/.msvc/bled.vcxproj new file mode 100644 index 00000000..4fa303d0 --- /dev/null +++ b/src/bled/.msvc/bled.vcxproj @@ -0,0 +1,176 @@ + + + + + Debug + Win32 + + + Debug + x64 + + + Release + Win32 + + + Release + x64 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + bled + {FB6D52D4-A2F8-C358-DB85-BBCAECFDDD7D} + bled + + + + StaticLibrary + Unicode + v120 + + + StaticLibrary + Unicode + v120 + + + StaticLibrary + Unicode + v120 + + + StaticLibrary + Unicode + v120 + + + + + + <_ProjectFileVersion>10.0.30319.1 + $(SolutionDir)x86_32\$(Configuration)\ + $(SolutionDir)x86_32\$(Configuration)\$(ProjectName)\ + $(SolutionDir)x86_32\$(Configuration)\ + $(SolutionDir)x86_32\$(Configuration)\$(ProjectName)\ + $(SolutionDir)x86_64\$(Configuration)\ + $(SolutionDir)x86_64\$(Configuration)\$(ProjectName)\ + $(SolutionDir)x86_64\$(Configuration)\ + $(SolutionDir)x86_64\$(Configuration)\$(ProjectName)\ + false + false + false + false + + + + Level3 + ProgramDatabase + true + Disabled + _OFF_T_DEFINED;_off_t=__int64;off_t=_off_t;_FILE_OFFSET_BITS=64;_CRTDBG_MAP_ALLOC;%(PreprocessorDefinitions) + MultiThreadedDebug + ..\.. + + + true + true + true + $(OutDir)$(TargetName)$(TargetExt) + odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + + + + + Level3 + ProgramDatabase + EnableFastChecks + Disabled + _OFF_T_DEFINED;_off_t=__int64;off_t=_off_t;_FILE_OFFSET_BITS=64;_CRTDBG_MAP_ALLOC;%(PreprocessorDefinitions) + MultiThreadedDebug + ..\.. + + + true + true + true + $(OutDir)$(TargetName)$(TargetExt) + odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + + + + + Level3 + true + _OFF_T_DEFINED;_off_t=__int64;off_t=_off_t;_FILE_OFFSET_BITS=64;%(PreprocessorDefinitions) + MultiThreaded + ..\.. + + + true + true + $(OutDir)$(TargetName)$(TargetExt) + odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + + + true + + + + + Level3 + true + _OFF_T_DEFINED;_off_t=__int64;off_t=_off_t;_FILE_OFFSET_BITS=64;%(PreprocessorDefinitions) + MultiThreaded + ..\.. + + + true + true + $(OutDir)$(TargetName)$(TargetExt) + odbc32.lib;odbccp32.lib;%(AdditionalDependencies) + .\7z.def + + + true + + + + \ No newline at end of file diff --git a/src/bled/.msvc/bled.vcxproj.filters b/src/bled/.msvc/bled.vcxproj.filters new file mode 100644 index 00000000..26bfc876 --- /dev/null +++ b/src/bled/.msvc/bled.vcxproj.filters @@ -0,0 +1,114 @@ + + + + + {396df203-84ec-49b8-ae11-074c50a020f0} + + + {0147b833-dc8f-4666-be99-77dfae5e6679} + + + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + Source Files + + + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + Header Files + + + \ No newline at end of file diff --git a/src/bled/.msvc/bled_sources b/src/bled/.msvc/bled_sources new file mode 100644 index 00000000..36cb75fe --- /dev/null +++ b/src/bled/.msvc/bled_sources @@ -0,0 +1,20 @@ +TARGETNAME=bled +TARGETTYPE=LIBRARY + +INCLUDES=$(DDK_INC_PATH);.;..;..\msvc-missing +BLED_DEFINES = /D_OFF_T_DEFINED /D_off_t=__int64 /Doff_t=_off_t /D_FILE_OFFSET_BITS=64 +C_DEFINES=$(C_DEFINES) $(BLED_DEFINES) /DDDKBUILD /DUNICODE /D_UNICODE /DISOLATION_AWARE_ENABLED + +!IFNDEF MSC_WARNING_LEVEL +MSC_WARNING_LEVEL=/W3 +!ENDIF +USE_MSVCRT=1 + +TARGETLIBS=$(SDK_LIB_PATH)\kernel32.lib \ + $(SDK_LIB_PATH)\user32.lib + +SOURCES=bled.c crc32.c data_align.c data_extract_all.c data_skip.c decompress_bunzip2.c \ + decompress_gunzip.c decompress_uncompress.c decompress_unlzma.c decompress_unxz.c \ + filter_accept_all.c filter_accept_list.c filter_accept_reject_list.c find_list_entry.c \ + header_list.c header_skip.c header_verbose_list.c init_handle.c open_transformer.c \ + seek_by_jump.c seek_by_read.c xz_dec_bcj.c xz_dec_lzma2.c xz_dec_stream.c diff --git a/src/bled/Makefile.am b/src/bled/Makefile.am new file mode 100644 index 00000000..b0e5c984 --- /dev/null +++ b/src/bled/Makefile.am @@ -0,0 +1,8 @@ +noinst_LIBRARIES = libbled.a + +libbled_a_SOURCES = bled.c crc32.c data_align.c data_extract_all.c data_skip.c decompress_bunzip2.c \ + decompress_gunzip.c decompress_uncompress.c decompress_unlzma.c decompress_unxz.c \ + filter_accept_all.c filter_accept_list.c filter_accept_reject_list.c find_list_entry.c \ + header_list.c header_skip.c header_verbose_list.c init_handle.c open_transformer.c \ + seek_by_jump.c seek_by_read.c xz_dec_bcj.c xz_dec_lzma2.c xz_dec_stream.c +libbled_a_CFLAGS = $(AM_CFLAGS) -I.. -Wno-undef -Wno-strict-aliasing \ No newline at end of file diff --git a/src/bled/Makefile.in b/src/bled/Makefile.in new file mode 100644 index 00000000..bc08a7a1 --- /dev/null +++ b/src/bled/Makefile.in @@ -0,0 +1,642 @@ +# Makefile.in generated by automake 1.14.1 from Makefile.am. +# @configure_input@ + +# Copyright (C) 1994-2013 Free Software Foundation, Inc. + +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +@SET_MAKE@ + +VPATH = @srcdir@ +am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__make_running_with_option = \ + case $${target_option-} in \ + ?) ;; \ + *) echo "am__make_running_with_option: internal error: invalid" \ + "target option '$${target_option-}' specified" >&2; \ + exit 1;; \ + esac; \ + has_opt=no; \ + sane_makeflags=$$MAKEFLAGS; \ + if $(am__is_gnu_make); then \ + sane_makeflags=$$MFLAGS; \ + else \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + bs=\\; \ + sane_makeflags=`printf '%s\n' "$$MAKEFLAGS" \ + | sed "s/$$bs$$bs[$$bs $$bs ]*//g"`;; \ + esac; \ + fi; \ + skip_next=no; \ + strip_trailopt () \ + { \ + flg=`printf '%s\n' "$$flg" | sed "s/$$1.*$$//"`; \ + }; \ + for flg in $$sane_makeflags; do \ + test $$skip_next = yes && { skip_next=no; continue; }; \ + case $$flg in \ + *=*|--*) continue;; \ + -*I) strip_trailopt 'I'; skip_next=yes;; \ + -*I?*) strip_trailopt 'I';; \ + -*O) strip_trailopt 'O'; skip_next=yes;; \ + -*O?*) strip_trailopt 'O';; \ + -*l) strip_trailopt 'l'; skip_next=yes;; \ + -*l?*) strip_trailopt 'l';; \ + -[dEDm]) skip_next=yes;; \ + -[JT]) skip_next=yes;; \ + esac; \ + case $$flg in \ + *$$target_option*) has_opt=yes; break;; \ + esac; \ + done; \ + test $$has_opt = yes +am__make_dryrun = (target_option=n; $(am__make_running_with_option)) +am__make_keepgoing = (target_option=k; $(am__make_running_with_option)) +pkgdatadir = $(datadir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkglibexecdir = $(libexecdir)/@PACKAGE@ +am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd +install_sh_DATA = $(install_sh) -c -m 644 +install_sh_PROGRAM = $(install_sh) -c +install_sh_SCRIPT = $(install_sh) -c +INSTALL_HEADER = $(INSTALL_DATA) +transform = $(program_transform_name) +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +subdir = src/bled +DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am +ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 +am__aclocal_m4_deps = $(top_srcdir)/configure.ac +am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ + $(ACLOCAL_M4) +mkinstalldirs = $(install_sh) -d +CONFIG_CLEAN_FILES = +CONFIG_CLEAN_VPATH_FILES = +LIBRARIES = $(noinst_LIBRARIES) +AR = ar +ARFLAGS = cru +AM_V_AR = $(am__v_AR_@AM_V@) +am__v_AR_ = $(am__v_AR_@AM_DEFAULT_V@) +am__v_AR_0 = @echo " AR " $@; +am__v_AR_1 = +libbled_a_AR = $(AR) $(ARFLAGS) +libbled_a_LIBADD = +am_libbled_a_OBJECTS = libbled_a-bled.$(OBJEXT) \ + libbled_a-crc32.$(OBJEXT) libbled_a-data_align.$(OBJEXT) \ + libbled_a-data_extract_all.$(OBJEXT) \ + libbled_a-data_skip.$(OBJEXT) \ + libbled_a-decompress_bunzip2.$(OBJEXT) \ + libbled_a-decompress_gunzip.$(OBJEXT) \ + libbled_a-decompress_uncompress.$(OBJEXT) \ + libbled_a-decompress_unlzma.$(OBJEXT) \ + libbled_a-decompress_unxz.$(OBJEXT) \ + libbled_a-filter_accept_all.$(OBJEXT) \ + libbled_a-filter_accept_list.$(OBJEXT) \ + libbled_a-filter_accept_reject_list.$(OBJEXT) \ + libbled_a-find_list_entry.$(OBJEXT) \ + libbled_a-header_list.$(OBJEXT) \ + libbled_a-header_skip.$(OBJEXT) \ + libbled_a-header_verbose_list.$(OBJEXT) \ + libbled_a-init_handle.$(OBJEXT) \ + libbled_a-open_transformer.$(OBJEXT) \ + libbled_a-seek_by_jump.$(OBJEXT) \ + libbled_a-seek_by_read.$(OBJEXT) \ + libbled_a-xz_dec_bcj.$(OBJEXT) \ + libbled_a-xz_dec_lzma2.$(OBJEXT) \ + libbled_a-xz_dec_stream.$(OBJEXT) +libbled_a_OBJECTS = $(am_libbled_a_OBJECTS) +AM_V_P = $(am__v_P_@AM_V@) +am__v_P_ = $(am__v_P_@AM_DEFAULT_V@) +am__v_P_0 = false +am__v_P_1 = : +AM_V_GEN = $(am__v_GEN_@AM_V@) +am__v_GEN_ = $(am__v_GEN_@AM_DEFAULT_V@) +am__v_GEN_0 = @echo " GEN " $@; +am__v_GEN_1 = +AM_V_at = $(am__v_at_@AM_V@) +am__v_at_ = $(am__v_at_@AM_DEFAULT_V@) +am__v_at_0 = @ +am__v_at_1 = +DEFAULT_INCLUDES = -I.@am__isrc@ +depcomp = +am__depfiles_maybe = +AM_V_lt = $(am__v_lt_@AM_V@) +am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@) +am__v_lt_0 = --silent +am__v_lt_1 = +COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \ + $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) +AM_V_CC = $(am__v_CC_@AM_V@) +am__v_CC_ = $(am__v_CC_@AM_DEFAULT_V@) +am__v_CC_0 = @echo " CC " $@; +am__v_CC_1 = +CCLD = $(CC) +LINK = $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) $(LDFLAGS) -o $@ +AM_V_CCLD = $(am__v_CCLD_@AM_V@) +am__v_CCLD_ = $(am__v_CCLD_@AM_DEFAULT_V@) +am__v_CCLD_0 = @echo " CCLD " $@; +am__v_CCLD_1 = +SOURCES = $(libbled_a_SOURCES) +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac +am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +# Read a list of newline-separated strings from the standard input, +# and print each of them once, without duplicates. Input order is +# *not* preserved. +am__uniquify_input = $(AWK) '\ + BEGIN { nonempty = 0; } \ + { items[$$0] = 1; nonempty = 1; } \ + END { if (nonempty) { for (i in items) print i; }; } \ +' +# Make sure the list of sources is unique. This is necessary because, +# e.g., the same source file might be shared among _SOURCES variables +# for different programs/libraries. +am__define_uniq_tagged_files = \ + list='$(am__tagged_files)'; \ + unique=`for i in $$list; do \ + if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \ + done | $(am__uniquify_input)` +ETAGS = etags +CTAGS = ctags +ACLOCAL = @ACLOCAL@ +AMTAR = @AMTAR@ +AM_CFLAGS = @AM_CFLAGS@ +AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@ +AM_LDFLAGS = @AM_LDFLAGS@ +AUTOCONF = @AUTOCONF@ +AUTOHEADER = @AUTOHEADER@ +AUTOMAKE = @AUTOMAKE@ +AWK = @AWK@ +CC = @CC@ +CFLAGS = @CFLAGS@ +CPPFLAGS = @CPPFLAGS@ +CYGPATH_W = @CYGPATH_W@ +DEFS = @DEFS@ +ECHO_C = @ECHO_C@ +ECHO_N = @ECHO_N@ +ECHO_T = @ECHO_T@ +EXEEXT = @EXEEXT@ +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ +LDFLAGS = @LDFLAGS@ +LIBOBJS = @LIBOBJS@ +LIBS = @LIBS@ +LTLIBOBJS = @LTLIBOBJS@ +MAKEINFO = @MAKEINFO@ +MKDIR_P = @MKDIR_P@ +OBJEXT = @OBJEXT@ +PACKAGE = @PACKAGE@ +PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@ +PACKAGE_NAME = @PACKAGE_NAME@ +PACKAGE_STRING = @PACKAGE_STRING@ +PACKAGE_TARNAME = @PACKAGE_TARNAME@ +PACKAGE_URL = @PACKAGE_URL@ +PACKAGE_VERSION = @PACKAGE_VERSION@ +PATH_SEPARATOR = @PATH_SEPARATOR@ +RANLIB = @RANLIB@ +RM = @RM@ +SED = @SED@ +SET_MAKE = @SET_MAKE@ +SHELL = @SHELL@ +STRIP = @STRIP@ +SUFFIX = @SUFFIX@ +VERSION = @VERSION@ +VISIBILITY_CFLAGS = @VISIBILITY_CFLAGS@ +WINDRES = @WINDRES@ +abs_builddir = @abs_builddir@ +abs_srcdir = @abs_srcdir@ +abs_top_builddir = @abs_top_builddir@ +abs_top_srcdir = @abs_top_srcdir@ +ac_ct_CC = @ac_ct_CC@ +am__leading_dot = @am__leading_dot@ +am__tar = @am__tar@ +am__untar = @am__untar@ +bindir = @bindir@ +build_alias = @build_alias@ +builddir = @builddir@ +datadir = @datadir@ +datarootdir = @datarootdir@ +docdir = @docdir@ +dvidir = @dvidir@ +exec_prefix = @exec_prefix@ +host_alias = @host_alias@ +htmldir = @htmldir@ +includedir = @includedir@ +infodir = @infodir@ +install_sh = @install_sh@ +libdir = @libdir@ +libexecdir = @libexecdir@ +localedir = @localedir@ +localstatedir = @localstatedir@ +mandir = @mandir@ +mkdir_p = @mkdir_p@ +oldincludedir = @oldincludedir@ +pdfdir = @pdfdir@ +prefix = @prefix@ +program_transform_name = @program_transform_name@ +psdir = @psdir@ +sbindir = @sbindir@ +sharedstatedir = @sharedstatedir@ +srcdir = @srcdir@ +sysconfdir = @sysconfdir@ +target_alias = @target_alias@ +top_build_prefix = @top_build_prefix@ +top_builddir = @top_builddir@ +top_srcdir = @top_srcdir@ +noinst_LIBRARIES = libbled.a +libbled_a_SOURCES = bled.c crc32.c data_align.c data_extract_all.c data_skip.c decompress_bunzip2.c \ + decompress_gunzip.c decompress_uncompress.c decompress_unlzma.c decompress_unxz.c \ + filter_accept_all.c filter_accept_list.c filter_accept_reject_list.c find_list_entry.c \ + header_list.c header_skip.c header_verbose_list.c init_handle.c open_transformer.c \ + seek_by_jump.c seek_by_read.c xz_dec_bcj.c xz_dec_lzma2.c xz_dec_stream.c + +libbled_a_CFLAGS = $(AM_CFLAGS) -I.. -Wno-undef -Wno-strict-aliasing +all: all-am + +.SUFFIXES: +.SUFFIXES: .c .o .obj +$(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) + @for dep in $?; do \ + case '$(am__configure_deps)' in \ + *$$dep*) \ + ( cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh ) \ + && { if test -f $@; then exit 0; else break; fi; }; \ + exit 1;; \ + esac; \ + done; \ + echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign --ignore-deps src/bled/Makefile'; \ + $(am__cd) $(top_srcdir) && \ + $(AUTOMAKE) --foreign --ignore-deps src/bled/Makefile +.PRECIOUS: Makefile +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + @case '$?' in \ + *config.status*) \ + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \ + *) \ + echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \ + cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \ + esac; + +$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh + +$(top_srcdir)/configure: $(am__configure_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(ACLOCAL_M4): $(am__aclocal_m4_deps) + cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh +$(am__aclocal_m4_deps): + +clean-noinstLIBRARIES: + -test -z "$(noinst_LIBRARIES)" || rm -f $(noinst_LIBRARIES) + +libbled.a: $(libbled_a_OBJECTS) $(libbled_a_DEPENDENCIES) $(EXTRA_libbled_a_DEPENDENCIES) + $(AM_V_at)-rm -f libbled.a + $(AM_V_AR)$(libbled_a_AR) libbled.a $(libbled_a_OBJECTS) $(libbled_a_LIBADD) + $(AM_V_at)$(RANLIB) libbled.a + +mostlyclean-compile: + -rm -f *.$(OBJEXT) + +distclean-compile: + -rm -f *.tab.c + +.c.o: + $(AM_V_CC)$(COMPILE) -c -o $@ $< + +.c.obj: + $(AM_V_CC)$(COMPILE) -c -o $@ `$(CYGPATH_W) '$<'` + +libbled_a-bled.o: bled.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-bled.o `test -f 'bled.c' || echo '$(srcdir)/'`bled.c + +libbled_a-bled.obj: bled.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-bled.obj `if test -f 'bled.c'; then $(CYGPATH_W) 'bled.c'; else $(CYGPATH_W) '$(srcdir)/bled.c'; fi` + +libbled_a-crc32.o: crc32.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-crc32.o `test -f 'crc32.c' || echo '$(srcdir)/'`crc32.c + +libbled_a-crc32.obj: crc32.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-crc32.obj `if test -f 'crc32.c'; then $(CYGPATH_W) 'crc32.c'; else $(CYGPATH_W) '$(srcdir)/crc32.c'; fi` + +libbled_a-data_align.o: data_align.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_align.o `test -f 'data_align.c' || echo '$(srcdir)/'`data_align.c + +libbled_a-data_align.obj: data_align.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_align.obj `if test -f 'data_align.c'; then $(CYGPATH_W) 'data_align.c'; else $(CYGPATH_W) '$(srcdir)/data_align.c'; fi` + +libbled_a-data_extract_all.o: data_extract_all.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_extract_all.o `test -f 'data_extract_all.c' || echo '$(srcdir)/'`data_extract_all.c + +libbled_a-data_extract_all.obj: data_extract_all.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_extract_all.obj `if test -f 'data_extract_all.c'; then $(CYGPATH_W) 'data_extract_all.c'; else $(CYGPATH_W) '$(srcdir)/data_extract_all.c'; fi` + +libbled_a-data_skip.o: data_skip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_skip.o `test -f 'data_skip.c' || echo '$(srcdir)/'`data_skip.c + +libbled_a-data_skip.obj: data_skip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-data_skip.obj `if test -f 'data_skip.c'; then $(CYGPATH_W) 'data_skip.c'; else $(CYGPATH_W) '$(srcdir)/data_skip.c'; fi` + +libbled_a-decompress_bunzip2.o: decompress_bunzip2.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_bunzip2.o `test -f 'decompress_bunzip2.c' || echo '$(srcdir)/'`decompress_bunzip2.c + +libbled_a-decompress_bunzip2.obj: decompress_bunzip2.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_bunzip2.obj `if test -f 'decompress_bunzip2.c'; then $(CYGPATH_W) 'decompress_bunzip2.c'; else $(CYGPATH_W) '$(srcdir)/decompress_bunzip2.c'; fi` + +libbled_a-decompress_gunzip.o: decompress_gunzip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_gunzip.o `test -f 'decompress_gunzip.c' || echo '$(srcdir)/'`decompress_gunzip.c + +libbled_a-decompress_gunzip.obj: decompress_gunzip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_gunzip.obj `if test -f 'decompress_gunzip.c'; then $(CYGPATH_W) 'decompress_gunzip.c'; else $(CYGPATH_W) '$(srcdir)/decompress_gunzip.c'; fi` + +libbled_a-decompress_uncompress.o: decompress_uncompress.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_uncompress.o `test -f 'decompress_uncompress.c' || echo '$(srcdir)/'`decompress_uncompress.c + +libbled_a-decompress_uncompress.obj: decompress_uncompress.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_uncompress.obj `if test -f 'decompress_uncompress.c'; then $(CYGPATH_W) 'decompress_uncompress.c'; else $(CYGPATH_W) '$(srcdir)/decompress_uncompress.c'; fi` + +libbled_a-decompress_unlzma.o: decompress_unlzma.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_unlzma.o `test -f 'decompress_unlzma.c' || echo '$(srcdir)/'`decompress_unlzma.c + +libbled_a-decompress_unlzma.obj: decompress_unlzma.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_unlzma.obj `if test -f 'decompress_unlzma.c'; then $(CYGPATH_W) 'decompress_unlzma.c'; else $(CYGPATH_W) '$(srcdir)/decompress_unlzma.c'; fi` + +libbled_a-decompress_unxz.o: decompress_unxz.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_unxz.o `test -f 'decompress_unxz.c' || echo '$(srcdir)/'`decompress_unxz.c + +libbled_a-decompress_unxz.obj: decompress_unxz.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-decompress_unxz.obj `if test -f 'decompress_unxz.c'; then $(CYGPATH_W) 'decompress_unxz.c'; else $(CYGPATH_W) '$(srcdir)/decompress_unxz.c'; fi` + +libbled_a-filter_accept_all.o: filter_accept_all.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_all.o `test -f 'filter_accept_all.c' || echo '$(srcdir)/'`filter_accept_all.c + +libbled_a-filter_accept_all.obj: filter_accept_all.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_all.obj `if test -f 'filter_accept_all.c'; then $(CYGPATH_W) 'filter_accept_all.c'; else $(CYGPATH_W) '$(srcdir)/filter_accept_all.c'; fi` + +libbled_a-filter_accept_list.o: filter_accept_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_list.o `test -f 'filter_accept_list.c' || echo '$(srcdir)/'`filter_accept_list.c + +libbled_a-filter_accept_list.obj: filter_accept_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_list.obj `if test -f 'filter_accept_list.c'; then $(CYGPATH_W) 'filter_accept_list.c'; else $(CYGPATH_W) '$(srcdir)/filter_accept_list.c'; fi` + +libbled_a-filter_accept_reject_list.o: filter_accept_reject_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_reject_list.o `test -f 'filter_accept_reject_list.c' || echo '$(srcdir)/'`filter_accept_reject_list.c + +libbled_a-filter_accept_reject_list.obj: filter_accept_reject_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-filter_accept_reject_list.obj `if test -f 'filter_accept_reject_list.c'; then $(CYGPATH_W) 'filter_accept_reject_list.c'; else $(CYGPATH_W) '$(srcdir)/filter_accept_reject_list.c'; fi` + +libbled_a-find_list_entry.o: find_list_entry.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-find_list_entry.o `test -f 'find_list_entry.c' || echo '$(srcdir)/'`find_list_entry.c + +libbled_a-find_list_entry.obj: find_list_entry.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-find_list_entry.obj `if test -f 'find_list_entry.c'; then $(CYGPATH_W) 'find_list_entry.c'; else $(CYGPATH_W) '$(srcdir)/find_list_entry.c'; fi` + +libbled_a-header_list.o: header_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_list.o `test -f 'header_list.c' || echo '$(srcdir)/'`header_list.c + +libbled_a-header_list.obj: header_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_list.obj `if test -f 'header_list.c'; then $(CYGPATH_W) 'header_list.c'; else $(CYGPATH_W) '$(srcdir)/header_list.c'; fi` + +libbled_a-header_skip.o: header_skip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_skip.o `test -f 'header_skip.c' || echo '$(srcdir)/'`header_skip.c + +libbled_a-header_skip.obj: header_skip.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_skip.obj `if test -f 'header_skip.c'; then $(CYGPATH_W) 'header_skip.c'; else $(CYGPATH_W) '$(srcdir)/header_skip.c'; fi` + +libbled_a-header_verbose_list.o: header_verbose_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_verbose_list.o `test -f 'header_verbose_list.c' || echo '$(srcdir)/'`header_verbose_list.c + +libbled_a-header_verbose_list.obj: header_verbose_list.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-header_verbose_list.obj `if test -f 'header_verbose_list.c'; then $(CYGPATH_W) 'header_verbose_list.c'; else $(CYGPATH_W) '$(srcdir)/header_verbose_list.c'; fi` + +libbled_a-init_handle.o: init_handle.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-init_handle.o `test -f 'init_handle.c' || echo '$(srcdir)/'`init_handle.c + +libbled_a-init_handle.obj: init_handle.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-init_handle.obj `if test -f 'init_handle.c'; then $(CYGPATH_W) 'init_handle.c'; else $(CYGPATH_W) '$(srcdir)/init_handle.c'; fi` + +libbled_a-open_transformer.o: open_transformer.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-open_transformer.o `test -f 'open_transformer.c' || echo '$(srcdir)/'`open_transformer.c + +libbled_a-open_transformer.obj: open_transformer.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-open_transformer.obj `if test -f 'open_transformer.c'; then $(CYGPATH_W) 'open_transformer.c'; else $(CYGPATH_W) '$(srcdir)/open_transformer.c'; fi` + +libbled_a-seek_by_jump.o: seek_by_jump.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-seek_by_jump.o `test -f 'seek_by_jump.c' || echo '$(srcdir)/'`seek_by_jump.c + +libbled_a-seek_by_jump.obj: seek_by_jump.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-seek_by_jump.obj `if test -f 'seek_by_jump.c'; then $(CYGPATH_W) 'seek_by_jump.c'; else $(CYGPATH_W) '$(srcdir)/seek_by_jump.c'; fi` + +libbled_a-seek_by_read.o: seek_by_read.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-seek_by_read.o `test -f 'seek_by_read.c' || echo '$(srcdir)/'`seek_by_read.c + +libbled_a-seek_by_read.obj: seek_by_read.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-seek_by_read.obj `if test -f 'seek_by_read.c'; then $(CYGPATH_W) 'seek_by_read.c'; else $(CYGPATH_W) '$(srcdir)/seek_by_read.c'; fi` + +libbled_a-xz_dec_bcj.o: xz_dec_bcj.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_bcj.o `test -f 'xz_dec_bcj.c' || echo '$(srcdir)/'`xz_dec_bcj.c + +libbled_a-xz_dec_bcj.obj: xz_dec_bcj.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_bcj.obj `if test -f 'xz_dec_bcj.c'; then $(CYGPATH_W) 'xz_dec_bcj.c'; else $(CYGPATH_W) '$(srcdir)/xz_dec_bcj.c'; fi` + +libbled_a-xz_dec_lzma2.o: xz_dec_lzma2.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_lzma2.o `test -f 'xz_dec_lzma2.c' || echo '$(srcdir)/'`xz_dec_lzma2.c + +libbled_a-xz_dec_lzma2.obj: xz_dec_lzma2.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_lzma2.obj `if test -f 'xz_dec_lzma2.c'; then $(CYGPATH_W) 'xz_dec_lzma2.c'; else $(CYGPATH_W) '$(srcdir)/xz_dec_lzma2.c'; fi` + +libbled_a-xz_dec_stream.o: xz_dec_stream.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_stream.o `test -f 'xz_dec_stream.c' || echo '$(srcdir)/'`xz_dec_stream.c + +libbled_a-xz_dec_stream.obj: xz_dec_stream.c + $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(libbled_a_CFLAGS) $(CFLAGS) -c -o libbled_a-xz_dec_stream.obj `if test -f 'xz_dec_stream.c'; then $(CYGPATH_W) 'xz_dec_stream.c'; else $(CYGPATH_W) '$(srcdir)/xz_dec_stream.c'; fi` + +ID: $(am__tagged_files) + $(am__define_uniq_tagged_files); mkid -fID $$unique +tags: tags-am +TAGS: tags + +tags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files) + set x; \ + here=`pwd`; \ + $(am__define_uniq_tagged_files); \ + shift; \ + if test -z "$(ETAGS_ARGS)$$*$$unique"; then :; else \ + test -n "$$unique" || unique=$$empty_fix; \ + if test $$# -gt 0; then \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + "$$@" $$unique; \ + else \ + $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \ + $$unique; \ + fi; \ + fi +ctags: ctags-am + +CTAGS: ctags +ctags-am: $(TAGS_DEPENDENCIES) $(am__tagged_files) + $(am__define_uniq_tagged_files); \ + test -z "$(CTAGS_ARGS)$$unique" \ + || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \ + $$unique + +GTAGS: + here=`$(am__cd) $(top_builddir) && pwd` \ + && $(am__cd) $(top_srcdir) \ + && gtags -i $(GTAGS_ARGS) "$$here" +cscopelist: cscopelist-am + +cscopelist-am: $(am__tagged_files) + list='$(am__tagged_files)'; \ + case "$(srcdir)" in \ + [\\/]* | ?:[\\/]*) sdir="$(srcdir)" ;; \ + *) sdir=$(subdir)/$(srcdir) ;; \ + esac; \ + for i in $$list; do \ + if test -f "$$i"; then \ + echo "$(subdir)/$$i"; \ + else \ + echo "$$sdir/$$i"; \ + fi; \ + done >> $(top_builddir)/cscope.files + +distclean-tags: + -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags +check-am: all-am +check: check-am +all-am: Makefile $(LIBRARIES) +installdirs: +install: install-am +install-exec: install-exec-am +install-data: install-data-am +uninstall: uninstall-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am + +installcheck: installcheck-am +install-strip: + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi +mostlyclean-generic: + +clean-generic: + +distclean-generic: + -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES) + -test . = "$(srcdir)" || test -z "$(CONFIG_CLEAN_VPATH_FILES)" || rm -f $(CONFIG_CLEAN_VPATH_FILES) + +maintainer-clean-generic: + @echo "This command is intended for maintainers to use" + @echo "it deletes files that may require special tools to rebuild." +clean: clean-am + +clean-am: clean-generic clean-noinstLIBRARIES mostlyclean-am + +distclean: distclean-am + -rm -f Makefile +distclean-am: clean-am distclean-compile distclean-generic \ + distclean-tags + +dvi: dvi-am + +dvi-am: + +html: html-am + +html-am: + +info: info-am + +info-am: + +install-data-am: + +install-dvi: install-dvi-am + +install-dvi-am: + +install-exec-am: + +install-html: install-html-am + +install-html-am: + +install-info: install-info-am + +install-info-am: + +install-man: + +install-pdf: install-pdf-am + +install-pdf-am: + +install-ps: install-ps-am + +install-ps-am: + +installcheck-am: + +maintainer-clean: maintainer-clean-am + -rm -f Makefile +maintainer-clean-am: distclean-am maintainer-clean-generic + +mostlyclean: mostlyclean-am + +mostlyclean-am: mostlyclean-compile mostlyclean-generic + +pdf: pdf-am + +pdf-am: + +ps: ps-am + +ps-am: + +uninstall-am: + +.MAKE: install-am install-strip + +.PHONY: CTAGS GTAGS TAGS all all-am check check-am clean clean-generic \ + clean-noinstLIBRARIES cscopelist-am ctags ctags-am distclean \ + distclean-compile distclean-generic distclean-tags dvi dvi-am \ + html html-am info info-am install install-am install-data \ + install-data-am install-dvi install-dvi-am install-exec \ + install-exec-am install-html install-html-am install-info \ + install-info-am install-man install-pdf install-pdf-am \ + install-ps install-ps-am install-strip installcheck \ + installcheck-am installdirs maintainer-clean \ + maintainer-clean-generic mostlyclean mostlyclean-compile \ + mostlyclean-generic pdf pdf-am ps ps-am tags tags-am uninstall \ + uninstall-am + + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/src/bled/bb_archive.h b/src/bled/bb_archive.h new file mode 100644 index 00000000..a6b166fe --- /dev/null +++ b/src/bled/bb_archive.h @@ -0,0 +1,262 @@ +/* vi: set sw=4 ts=4: */ +#ifndef UNARCHIVE_H +#define UNARCHIVE_H 1 + +PUSH_AND_SET_FUNCTION_VISIBILITY_TO_HIDDEN + +enum { +#if BB_BIG_ENDIAN + COMPRESS_MAGIC = 0x1f9d, + GZIP_MAGIC = 0x1f8b, + BZIP2_MAGIC = 256 * 'B' + 'Z', + /* .xz signature: 0xfd, '7', 'z', 'X', 'Z', 0x00 */ + /* More info at: http://tukaani.org/xz/xz-file-format.txt */ + XZ_MAGIC1 = 256 * 0xfd + '7', + XZ_MAGIC2 = 256 * (unsigned)(256 * (256 * 'z' + 'X') + 'Z') + 0, + /* Different form: 32 bits, then 16 bits: */ + /* (unsigned) cast suppresses "integer overflow in expression" warning */ + XZ_MAGIC1a = 256 * (unsigned)(256 * (256 * 0xfd + '7') + 'z') + 'X', + XZ_MAGIC2a = 256 * 'Z' + 0, +#else + COMPRESS_MAGIC = 0x9d1f, + GZIP_MAGIC = 0x8b1f, + BZIP2_MAGIC = 'B' + 'Z' * 256, + XZ_MAGIC1 = 0xfd + '7' * 256, + XZ_MAGIC2 = 'z' + ('X' + ('Z' + 0 * 256) * 256) * 256, + XZ_MAGIC1a = 0xfd + ('7' + ('z' + 'X' * 256) * 256) * 256, + XZ_MAGIC2a = 'Z' + 0 * 256, +#endif +}; + +typedef struct file_header_t { + char *name; + char *link_target; +#if ENABLE_FEATURE_TAR_UNAME_GNAME + char *tar__uname; + char *tar__gname; +#endif + off_t size; + uid_t uid; + gid_t gid; + mode_t mode; + time_t mtime; + dev_t device; +} file_header_t; + +struct hardlinks_t; + +typedef struct archive_handle_t { + /* Flags. 1st since it is most used member */ + unsigned ah_flags; + + /* The raw stream as read from disk or stdin */ + int src_fd; + + /* Define if the header and data component should be processed */ + char FAST_FUNC (*filter)(struct archive_handle_t *); + /* List of files that have been accepted */ + llist_t *accept; + /* List of files that have been rejected */ + llist_t *reject; + /* List of files that have successfully been worked on */ + llist_t *passed; + + /* Currently processed file's header */ + file_header_t *file_header; + + /* Process the header component, e.g. tar -t */ + void FAST_FUNC (*action_header)(const file_header_t *); + + /* Process the data component, e.g. extract to filesystem */ + void FAST_FUNC (*action_data)(struct archive_handle_t *); + + /* Function that skips data */ + void FAST_FUNC (*seek)(int fd, off_t amount); + + /* Count processed bytes */ + off_t offset; + + /* Archiver specific. Can make it a union if it ever gets big */ +#define PAX_NEXT_FILE 0 +#define PAX_GLOBAL 1 +#if ENABLE_TAR || ENABLE_DPKG || ENABLE_DPKG_DEB + smallint tar__end; +# if ENABLE_FEATURE_TAR_GNU_EXTENSIONS + char* tar__longname; + char* tar__linkname; +# endif +# if ENABLE_FEATURE_TAR_TO_COMMAND + char* tar__to_command; + const char* tar__to_command_shell; +# endif +# if ENABLE_FEATURE_TAR_SELINUX + char* tar__sctx[2]; +# endif +#endif +#if ENABLE_CPIO || ENABLE_RPM2CPIO || ENABLE_RPM + uoff_t cpio__blocks; + struct hardlinks_t *cpio__hardlinks_to_create; + struct hardlinks_t *cpio__created_hardlinks; +#endif +#if ENABLE_DPKG || ENABLE_DPKG_DEB + /* Temporary storage */ + char *dpkg__buffer; + /* How to process any sub archive, e.g. get_header_tar_gz */ + char FAST_FUNC (*dpkg__action_data_subarchive)(struct archive_handle_t *); + /* Contains the handle to a sub archive */ + struct archive_handle_t *dpkg__sub_archive; +#endif +#if ENABLE_FEATURE_AR_CREATE + const char *ar__name; + struct archive_handle_t *ar__out; +#endif +} archive_handle_t; +/* bits in ah_flags */ +#define ARCHIVE_RESTORE_DATE (1 << 0) +#define ARCHIVE_CREATE_LEADING_DIRS (1 << 1) +#define ARCHIVE_UNLINK_OLD (1 << 2) +#define ARCHIVE_EXTRACT_QUIET (1 << 3) +#define ARCHIVE_EXTRACT_NEWER (1 << 4) +#define ARCHIVE_DONT_RESTORE_OWNER (1 << 5) +#define ARCHIVE_DONT_RESTORE_PERM (1 << 6) +#define ARCHIVE_NUMERIC_OWNER (1 << 7) +#define ARCHIVE_O_TRUNC (1 << 8) +#define ARCHIVE_REMEMBER_NAMES (1 << 9) +#if ENABLE_RPM +#define ARCHIVE_REPLACE_VIA_RENAME (1 << 10) +#endif + + +/* POSIX tar Header Block, from POSIX 1003.1-1990 */ +#define TAR_BLOCK_SIZE 512 +#define NAME_SIZE 100 +#define NAME_SIZE_STR "100" +typedef struct tar_header_t { /* byte offset */ + char name[NAME_SIZE]; /* 0-99 */ + char mode[8]; /* 100-107 */ + char uid[8]; /* 108-115 */ + char gid[8]; /* 116-123 */ + char size[12]; /* 124-135 */ + char mtime[12]; /* 136-147 */ + char chksum[8]; /* 148-155 */ + char typeflag; /* 156-156 */ + char linkname[NAME_SIZE]; /* 157-256 */ + /* POSIX: "ustar" NUL "00" */ + /* GNU tar: "ustar " NUL */ + /* Normally it's defined as magic[6] followed by + * version[2], but we put them together to save code. + */ + char magic[8]; /* 257-264 */ + char uname[32]; /* 265-296 */ + char gname[32]; /* 297-328 */ + char devmajor[8]; /* 329-336 */ + char devminor[8]; /* 337-344 */ + char prefix[155]; /* 345-499 */ + char padding[12]; /* 500-512 (pad to exactly TAR_BLOCK_SIZE) */ +} tar_header_t; +struct BUG_tar_header { + char c[sizeof(tar_header_t) == TAR_BLOCK_SIZE ? 1 : -1]; +}; + + + +archive_handle_t *init_handle(void) FAST_FUNC; + +char filter_accept_all(archive_handle_t *archive_handle) FAST_FUNC; +char filter_accept_list(archive_handle_t *archive_handle) FAST_FUNC; +char filter_accept_list_reassign(archive_handle_t *archive_handle) FAST_FUNC; +char filter_accept_reject_list(archive_handle_t *archive_handle) FAST_FUNC; + +void unpack_ar_archive(archive_handle_t *ar_archive) FAST_FUNC; + +void data_skip(archive_handle_t *archive_handle) FAST_FUNC; +void data_extract_all(archive_handle_t *archive_handle) FAST_FUNC; +void data_extract_to_stdout(archive_handle_t *archive_handle) FAST_FUNC; +void data_extract_to_command(archive_handle_t *archive_handle) FAST_FUNC; + +void header_skip(const file_header_t *file_header) FAST_FUNC; +void header_list(const file_header_t *file_header) FAST_FUNC; +void header_verbose_list(const file_header_t *file_header) FAST_FUNC; + +char get_header_ar(archive_handle_t *archive_handle) FAST_FUNC; +char get_header_cpio(archive_handle_t *archive_handle) FAST_FUNC; +char get_header_tar(archive_handle_t *archive_handle) FAST_FUNC; +char get_header_tar_gz(archive_handle_t *archive_handle) FAST_FUNC; +char get_header_tar_bz2(archive_handle_t *archive_handle) FAST_FUNC; +char get_header_tar_lzma(archive_handle_t *archive_handle) FAST_FUNC; + +void seek_by_jump(int fd, off_t amount) FAST_FUNC; +void seek_by_read(int fd, off_t amount) FAST_FUNC; + +const char *strip_unsafe_prefix(const char *str) FAST_FUNC; + +void data_align(archive_handle_t *archive_handle, unsigned boundary) FAST_FUNC; +const llist_t *find_list_entry(const llist_t *list, const char *filename) FAST_FUNC; +const llist_t *find_list_entry2(const llist_t *list, const char *filename) FAST_FUNC; + +/* A bit of bunzip2 internals are exposed for compressed help support: */ +typedef struct bunzip_data bunzip_data; +int start_bunzip(bunzip_data **bdp, int in_fd, const void *inbuf, int len) FAST_FUNC; +/* NB: read_bunzip returns < 0 on error, or the number of *unfilled* bytes + * in outbuf. IOW: on EOF returns len ("all bytes are not filled"), not 0: */ +int read_bunzip(bunzip_data *bd, char *outbuf, int len) FAST_FUNC; +void dealloc_bunzip(bunzip_data *bd) FAST_FUNC; + +/* Meaning and direction (input/output) of the fields are transformer-specific */ +typedef struct transformer_state_t { + smallint check_signature; /* most often referenced member */ + + IF_DESKTOP(long long) int FAST_FUNC (*xformer)(struct transformer_state_t *xstate); + USE_FOR_NOMMU(const char *xformer_prog;) + + /* Source */ + int src_fd; + /* Output */ + int dst_fd; + size_t mem_output_size_max; /* if non-zero, decompress to RAM instead of fd */ + size_t mem_output_size; + char *mem_output_buf; + + off_t bytes_out; + off_t bytes_in; /* used in unzip code only: needs to know packed size */ + uint32_t crc32; + time_t mtime; /* gunzip code may set this on exit */ +} transformer_state_t; + +void init_transformer_state(transformer_state_t *xstate) FAST_FUNC; +ssize_t transformer_write(transformer_state_t *xstate, const void *buf, size_t bufsize) FAST_FUNC; +ssize_t xtransformer_write(transformer_state_t *xstate, const void *buf, size_t bufsize) FAST_FUNC; +int check_signature16(transformer_state_t *xstate, unsigned magic16) FAST_FUNC; + +IF_DESKTOP(long long) int inflate_unzip(transformer_state_t *xstate) FAST_FUNC; +IF_DESKTOP(long long) int unpack_Z_stream(transformer_state_t *xstate) FAST_FUNC; +IF_DESKTOP(long long) int unpack_gz_stream(transformer_state_t *xstate) FAST_FUNC; +IF_DESKTOP(long long) int unpack_bz2_stream(transformer_state_t *xstate) FAST_FUNC; +IF_DESKTOP(long long) int unpack_lzma_stream(transformer_state_t *xstate) FAST_FUNC; +IF_DESKTOP(long long) int unpack_xz_stream(transformer_state_t *xstate) FAST_FUNC; + +char* append_ext(char *filename, const char *expected_ext) FAST_FUNC; +int bbunpack(char **argv, + IF_DESKTOP(long long) int FAST_FUNC (*unpacker)(transformer_state_t *xstate), + char* FAST_FUNC (*make_new_name)(char *filename, const char *expected_ext), + const char *expected_ext +) FAST_FUNC; + +void check_errors_in_children(int signo); +#if BB_MMU +void fork_transformer(int fd, + int check_signature, + IF_DESKTOP(long long) int FAST_FUNC (*transformer)(transformer_state_t *xstate) +) FAST_FUNC; +#define fork_transformer_with_sig(fd, transformer, transform_prog) fork_transformer((fd), 1, (transformer)) +#define fork_transformer_with_no_sig(fd, transformer) fork_transformer((fd), 0, (transformer)) +#else +void fork_transformer(int fd, const char *transform_prog) FAST_FUNC; +#define fork_transformer_with_sig(fd, transformer, transform_prog) fork_transformer((fd), (transform_prog)) +/* fork_transformer_with_no_sig() does not exist on NOMMU */ +#endif + + +POP_SAVED_FUNCTION_VISIBILITY + +#endif diff --git a/src/bled/bled.c b/src/bled/bled.c new file mode 100644 index 00000000..66dbc067 --- /dev/null +++ b/src/bled/bled.c @@ -0,0 +1,139 @@ +/* + * Bled (Busybox Library for Easy Decompression) + * + * Copyright © 2014 Pete Batard + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#ifdef _CRTDBG_MAP_ALLOC +#include +#include +#endif + +#include "libbb.h" +#include "bb_archive.h" +#include "bled.h" + +typedef long long int(*unpacker_t)(transformer_state_t *xstate); + +/* Globals */ +smallint bb_got_signal; +uint64_t bb_total_rb; +printf_t bled_printf = NULL; +progress_t bled_progress = NULL; +static bool bled_initialized = 0; + +static long long int unpack_none(transformer_state_t *xstate) +{ + bb_printf("BLED_COMPRESSION_NONE is not supported"); + return -1; +} + +unpacker_t unpacker[BLED_COMPRESSION_MAX] = { + unpack_none, + inflate_unzip, + unpack_Z_stream, + unpack_gz_stream, + unpack_lzma_stream, + unpack_bz2_stream, + unpack_xz_stream +}; + +/* Uncompress file 'src', compressed using 'type', to file 'dst' */ +int64_t bled_uncompress(const char* src, const char* dst, int type) +{ + transformer_state_t xstate; + int64_t ret; + + if (!bled_initialized) + return -1; + + bb_total_rb = 0; + init_transformer_state(&xstate); + xstate.src_fd = -1; + xstate.dst_fd = -1; + xstate.check_signature = 1; + + xstate.src_fd = _openU(src, _O_RDONLY | _O_BINARY, 0); + if (xstate.src_fd < 0) { + bb_printf("Could not open '%s' (errno: %d)", src, errno); + goto err; + } + + xstate.dst_fd = _openU(dst, _O_WRONLY | _O_CREAT | _O_TRUNC | _O_BINARY, _S_IREAD | _S_IWRITE); + if (xstate.dst_fd < 0) { + bb_printf("Could not open '%s' (errno: %d)", dst, errno); + goto err; + } + + if ((type < 0) || (type >= BLED_COMPRESSION_MAX)) { + bb_printf("unsupported compression format"); + goto err; + } + + ret = unpacker[type](&xstate); + _close(xstate.src_fd); + _close(xstate.dst_fd); + return ret; + +err: + if (xstate.src_fd > 0) + _close(xstate.src_fd); + if (xstate.dst_fd > 0) + _close(xstate.dst_fd); + return -1; +} + +/* Uncompress using Windows handles */ +int64_t bled_uncompress_with_handles(HANDLE hSrc, HANDLE hDst, int type) +{ + transformer_state_t xstate; + + if (!bled_initialized) + return -1; + + bb_total_rb = 0; + init_transformer_state(&xstate); + xstate.src_fd = -1; + xstate.dst_fd = -1; + xstate.check_signature = 1; + + xstate.src_fd = _open_osfhandle((intptr_t)hSrc, _O_RDONLY); + if (xstate.src_fd < 0) { + bb_printf("Could not get source descriptor (errno: %d)", errno); + return -1; + } + + xstate.dst_fd = _open_osfhandle((intptr_t)hDst, 0); + if (xstate.dst_fd < 0) { + bb_printf("Could not get target descriptor (errno: %d)", errno); + return -1; + } + + if ((type < 0) || (type >= BLED_COMPRESSION_MAX)) { + bb_printf("unsupported compression format"); + return -1; + } + + return unpacker[type](&xstate); +} + +int bled_init(printf_t print_function, progress_t progress_function) +{ + if (bled_initialized) + return -1; + bled_initialized = true; + bled_printf = print_function; + bled_progress = progress_function; + return 0; +} + +void bled_exit(void) +{ + bled_printf = NULL; + bled_progress = NULL; + if (global_crc32_table) + free(global_crc32_table); + bled_initialized = false; +} diff --git a/src/bled/bled.h b/src/bled/bled.h new file mode 100644 index 00000000..99562238 --- /dev/null +++ b/src/bled/bled.h @@ -0,0 +1,41 @@ +/* + * Bled (Busybox Library for Easy Decompression) + * + * Copyright © 2014 Pete Batard + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include +#include + +#pragma once + +#ifndef ARRAYSIZE +#define ARRAYSIZE(A) (sizeof(A)/sizeof((A)[0])) +#endif + +typedef void (*printf_t) (const char* format, ...); +typedef void (*progress_t) (const uint64_t processed_bytes); + +typedef enum { + BLED_COMPRESSION_NONE = 0, + BLED_COMPRESSION_ZIP, // .zip + BLED_COMPRESSION_LZW, // .Z + BLED_COMPRESSION_GZIP, // .gz + BLED_COMPRESSION_LZMA, // .lzma + BLED_COMPRESSION_BZIP2, // .bz2 + BLED_COMPRESSION_XZ, // .xz +// BLED_COMPRESSION_7ZIP // .7z + BLED_COMPRESSION_MAX +} bled_compression_type; + +/* Uncompress file 'src', compressed using 'type', to file 'dst' */ +int64_t bled_uncompress(const char* src, const char* dst, int type); + +int64_t bled_uncompress_with_handles(HANDLE hSrc, HANDLE hDst, int type); + +/* Initialize the library */ +int bled_init(printf_t print_function, progress_t progress_function); + +void bled_exit(void); diff --git a/src/bled/crc32.c b/src/bled/crc32.c new file mode 100644 index 00000000..8ff13f88 --- /dev/null +++ b/src/bled/crc32.c @@ -0,0 +1,257 @@ +/* + * GPLv2+ CRC32 implementation for busybox + * + * Based on crc32.c from util-linux v2.17's partx v2.17 - Public Domain + * Adjusted for busybox' by Pete Batard + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" + +#if __GNUC__ >= 3 /* 2.x has "attribute", but only 3.0 has "pure */ +#define attribute(x) __attribute__(x) +#else +#define attribute(x) +#endif + +/* Do NOT alter these */ +#define CRC_LE_BITS 8 +#define CRC_BE_BITS 8 + +/* + * There are multiple 16-bit CRC polynomials in common use, but this is + * *the* standard CRC-32 polynomial, first popularized by Ethernet. + * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 + */ +#define CRCPOLY_LE 0xedb88320 +#define CRCPOLY_BE 0x04c11db7 + +/* This needs to be defined somewhere */ +uint32_t *global_crc32_table; + +static void crc32init_le(uint32_t *crc32table_le) +{ + unsigned i, j; + uint32_t crc = 1; + + crc32table_le[0] = 0; + + for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) { + crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + for (j = 0; j < 1 << CRC_LE_BITS; j += 2 * i) + crc32table_le[i + j] = crc ^ crc32table_le[j]; + } +} + +/** + * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +uint32_t attribute((pure)) crc32_le(uint32_t crc, unsigned char const *p, size_t len, uint32_t *crc32table_le) +{ + while (len--) { +# if CRC_LE_BITS == 8 + crc = (crc >> 8) ^ crc32table_le[(crc ^ *p++) & 255]; +# elif CRC_LE_BITS == 4 + crc ^= *p++; + crc = (crc >> 4) ^ crc32table_le[crc & 15]; + crc = (crc >> 4) ^ crc32table_le[crc & 15]; +# elif CRC_LE_BITS == 2 + crc ^= *p++; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; + crc = (crc >> 2) ^ crc32table_le[crc & 3]; +# endif + } + return crc; +} + +/** + * crc32init_be() - allocate and initialize BE table data + */ +static void crc32init_be(uint32_t *crc32table_be) +{ + unsigned i, j; + uint32_t crc = 0x80000000; + + for (i = 1; i < 1 << CRC_BE_BITS; i <<= 1) { + crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0); + for (j = 0; j < i; j++) + crc32table_be[i + j] = crc ^ crc32table_be[j]; + } +} + +/** + * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 + * @crc - seed value for computation. ~0 for Ethernet, sometimes 0 for + * other uses, or the previous crc32 value if computing incrementally. + * @p - pointer to buffer over which CRC is run + * @len - length of buffer @p + * + */ +uint32_t attribute((pure)) crc32_be(uint32_t crc, unsigned char const *p, size_t len, uint32_t *crc32table_be) +{ + while (len--) { +# if CRC_BE_BITS == 8 + crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++]; +# elif CRC_BE_BITS == 4 + crc ^= *p++ << 24; + crc = (crc << 4) ^ crc32table_be[crc >> 28]; + crc = (crc << 4) ^ crc32table_be[crc >> 28]; +# elif CRC_BE_BITS == 2 + crc ^= *p++ << 24; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; + crc = (crc << 2) ^ crc32table_be[crc >> 30]; +# endif + } + return crc; +} + +uint32_t* crc32_filltable(uint32_t *crc_table, int endian) +{ + /* Expects the caller to do the cleanup */ + if (!crc_table) + crc_table = malloc((1 << CRC_LE_BITS) * sizeof(uint32_t)); + if (crc_table) { + if (endian) + crc32init_be(crc_table); + else + crc32init_le(crc_table); + } + return crc_table; +} + +/* + * A brief CRC tutorial. + * + * A CRC is a long-division remainder. You add the CRC to the message, + * and the whole thing (message+CRC) is a multiple of the given + * CRC polynomial. To check the CRC, you can either check that the + * CRC matches the recomputed value, *or* you can check that the + * remainder computed on the message+CRC is 0. This latter approach + * is used by a lot of hardware implementations, and is why so many + * protocols put the end-of-frame flag after the CRC. + * + * It's actually the same long division you learned in school, except that + * - We're working in binary, so the digits are only 0 and 1, and + * - When dividing polynomials, there are no carries. Rather than add and + * subtract, we just xor. Thus, we tend to get a bit sloppy about + * the difference between adding and subtracting. + * + * A 32-bit CRC polynomial is actually 33 bits long. But since it's + * 33 bits long, bit 32 is always going to be set, so usually the CRC + * is written in hex with the most significant bit omitted. (If you're + * familiar with the IEEE 754 floating-point format, it's the same idea.) + * + * Note that a CRC is computed over a string of *bits*, so you have + * to decide on the endianness of the bits within each byte. To get + * the best error-detecting properties, this should correspond to the + * order they're actually sent. For example, standard RS-232 serial is + * little-endian; the most significant bit (sometimes used for parity) + * is sent last. And when appending a CRC word to a message, you should + * do it in the right order, matching the endianness. + * + * Just like with ordinary division, the remainder is always smaller than + * the divisor (the CRC polynomial) you're dividing by. Each step of the + * division, you take one more digit (bit) of the dividend and append it + * to the current remainder. Then you figure out the appropriate multiple + * of the divisor to subtract to being the remainder back into range. + * In binary, it's easy - it has to be either 0 or 1, and to make the + * XOR cancel, it's just a copy of bit 32 of the remainder. + * + * When computing a CRC, we don't care about the quotient, so we can + * throw the quotient bit away, but subtract the appropriate multiple of + * the polynomial from the remainder and we're back to where we started, + * ready to process the next bit. + * + * A big-endian CRC written this way would be coded like: + * for (i = 0; i < input_bits; i++) { + * multiple = remainder & 0x80000000 ? CRCPOLY : 0; + * remainder = (remainder << 1 | next_input_bit()) ^ multiple; + * } + * Notice how, to get at bit 32 of the shifted remainder, we look + * at bit 31 of the remainder *before* shifting it. + * + * But also notice how the next_input_bit() bits we're shifting into + * the remainder don't actually affect any decision-making until + * 32 bits later. Thus, the first 32 cycles of this are pretty boring. + * Also, to add the CRC to a message, we need a 32-bit-long hole for it at + * the end, so we have to add 32 extra cycles shifting in zeros at the + * end of every message, + * + * So the standard trick is to rearrage merging in the next_input_bit() + * until the moment it's needed. Then the first 32 cycles can be precomputed, + * and merging in the final 32 zero bits to make room for the CRC can be + * skipped entirely. + * This changes the code to: + * for (i = 0; i < input_bits; i++) { + * remainder ^= next_input_bit() << 31; + * multiple = (remainder & 0x80000000) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * With this optimization, the little-endian code is simpler: + * for (i = 0; i < input_bits; i++) { + * remainder ^= next_input_bit(); + * multiple = (remainder & 1) ? CRCPOLY : 0; + * remainder = (remainder >> 1) ^ multiple; + * } + * + * Note that the other details of endianness have been hidden in CRCPOLY + * (which must be bit-reversed) and next_input_bit(). + * + * However, as long as next_input_bit is returning the bits in a sensible + * order, we can actually do the merging 8 or more bits at a time rather + * than one bit at a time: + * for (i = 0; i < input_bytes; i++) { + * remainder ^= next_input_byte() << 24; + * for (j = 0; j < 8; j++) { + * multiple = (remainder & 0x80000000) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * } + * Or in little-endian: + * for (i = 0; i < input_bytes; i++) { + * remainder ^= next_input_byte(); + * for (j = 0; j < 8; j++) { + * multiple = (remainder & 1) ? CRCPOLY : 0; + * remainder = (remainder << 1) ^ multiple; + * } + * } + * If the input is a multiple of 32 bits, you can even XOR in a 32-bit + * word at a time and increase the inner loop count to 32. + * + * You can also mix and match the two loop styles, for example doing the + * bulk of a message byte-at-a-time and adding bit-at-a-time processing + * for any fractional bytes at the end. + * + * The only remaining optimization is to the byte-at-a-time table method. + * Here, rather than just shifting one bit of the remainder to decide + * in the correct multiple to subtract, we can shift a byte at a time. + * This produces a 40-bit (rather than a 33-bit) intermediate remainder, + * but again the multiple of the polynomial to subtract depends only on + * the high bits, the high 8 bits in this case. + * + * The multile we need in that case is the low 32 bits of a 40-bit + * value whose high 8 bits are given, and which is a multiple of the + * generator polynomial. This is simply the CRC-32 of the given + * one-byte message. + * + * Two more details: normally, appending zero bits to a message which + * is already a multiple of a polynomial produces a larger multiple of that + * polynomial. To enable a CRC to detect this condition, it's common to + * invert the CRC before appending it. This makes the remainder of the + * message+crc come out not as zero, but some fixed non-zero value. + * + * The same problem applies to zero bits prepended to the message, and + * a similar solution is used. Instead of starting with a remainder of + * 0, an initial remainder of all ones is used. As long as you start + * the same way on decoding, it doesn't make a difference. + */ diff --git a/src/bled/data_align.c b/src/bled/data_align.c new file mode 100644 index 00000000..a6b84a44 --- /dev/null +++ b/src/bled/data_align.c @@ -0,0 +1,15 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC data_align(archive_handle_t *archive_handle, unsigned boundary) +{ + unsigned skip_amount = (boundary - (archive_handle->offset % boundary)) % boundary; + + archive_handle->seek(archive_handle->src_fd, skip_amount); + archive_handle->offset += skip_amount; +} diff --git a/src/bled/data_extract_all.c b/src/bled/data_extract_all.c new file mode 100644 index 00000000..45776dcb --- /dev/null +++ b/src/bled/data_extract_all.c @@ -0,0 +1,213 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC data_extract_all(archive_handle_t *archive_handle) +{ + file_header_t *file_header = archive_handle->file_header; + int dst_fd; + int res; + +#if ENABLE_FEATURE_TAR_SELINUX + char *sctx = archive_handle->tar__sctx[PAX_NEXT_FILE]; + if (!sctx) + sctx = archive_handle->tar__sctx[PAX_GLOBAL]; + if (sctx) { /* setfscreatecon is 4 syscalls, avoid if possible */ + setfscreatecon(sctx); + free(archive_handle->tar__sctx[PAX_NEXT_FILE]); + archive_handle->tar__sctx[PAX_NEXT_FILE] = NULL; + } +#endif + + if (archive_handle->ah_flags & ARCHIVE_CREATE_LEADING_DIRS) { + char *slash = strrchr(file_header->name, '/'); + if (slash) { + *slash = '\0'; + bb_make_directory(file_header->name, -1, FILEUTILS_RECUR); + *slash = '/'; + } + } + + if (archive_handle->ah_flags & ARCHIVE_UNLINK_OLD) { + /* Remove the entry if it exists */ + if (!S_ISDIR(file_header->mode)) { + /* Is it hardlink? + * We encode hard links as regular files of size 0 with a symlink */ + if (S_ISREG(file_header->mode) + && file_header->link_target + && file_header->size == 0 + ) { + /* Ugly special case: + * tar cf t.tar hardlink1 hardlink2 hardlink1 + * results in this tarball structure: + * hardlink1 + * hardlink2 -> hardlink1 + * hardlink1 -> hardlink1 <== !!! + */ + if (strcmp(file_header->link_target, file_header->name) == 0) + goto ret; + } + /* Proceed with deleting */ + if (unlink(file_header->name) == -1 + && errno != ENOENT + ) { + bb_perror_msg_and_die("can't remove old file %s", + file_header->name); + } + } + } + else if (archive_handle->ah_flags & ARCHIVE_EXTRACT_NEWER) { + /* Remove the existing entry if its older than the extracted entry */ + struct stat existing_sb; + if (lstat(file_header->name, &existing_sb) == -1) { + if (errno != ENOENT) { + bb_perror_msg_and_die("can't stat old file"); + } + } + else if (existing_sb.st_mtime >= file_header->mtime) { + if (!(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET) + && !S_ISDIR(file_header->mode) + ) { + bb_error_msg("%s not created: newer or " + "same age file exists", file_header->name); + } + data_skip(archive_handle); + goto ret; + } + else if ((unlink(file_header->name) == -1) && (errno != EISDIR)) { + bb_perror_msg_and_die("can't remove old file %s", + file_header->name); + } + } + + /* Handle hard links separately + * We encode hard links as regular files of size 0 with a symlink */ + if (S_ISREG(file_header->mode) + && file_header->link_target + && file_header->size == 0 + ) { + /* hard link */ + res = link(file_header->link_target, file_header->name); + if ((res == -1) && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET)) { + bb_perror_msg("can't create %slink " + "from %s to %s", "hard", + file_header->name, + file_header->link_target); + } + /* Hardlinks have no separate mode/ownership, skip chown/chmod */ + goto ret; + } + + /* Create the filesystem entry */ + switch (file_header->mode & S_IFMT) { + case S_IFREG: { + /* Regular file */ + char *dst_name; + int flags = O_WRONLY | O_CREAT | O_EXCL; + if (archive_handle->ah_flags & ARCHIVE_O_TRUNC) + flags = O_WRONLY | O_CREAT | O_TRUNC; + dst_name = file_header->name; +#ifdef ARCHIVE_REPLACE_VIA_RENAME + if (archive_handle->ah_flags & ARCHIVE_REPLACE_VIA_RENAME) + /* rpm-style temp file name */ + dst_name = xasprintf("%s;%x", dst_name, (int)getpid()); +#endif + dst_fd = xopen3(dst_name, + flags, + file_header->mode + ); + bb_copyfd_exact_size(archive_handle->src_fd, dst_fd, file_header->size); + close(dst_fd); +#ifdef ARCHIVE_REPLACE_VIA_RENAME + if (archive_handle->ah_flags & ARCHIVE_REPLACE_VIA_RENAME) { + xrename(dst_name, file_header->name); + free(dst_name); + } +#endif + break; + } + case S_IFDIR: + res = mkdir(file_header->name, file_header->mode); + if ((res == -1) + && (errno != EISDIR) /* btw, Linux doesn't return this */ + && (errno != EEXIST) + && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET) + ) { + bb_perror_msg("can't make dir %s", file_header->name); + } + break; + case S_IFLNK: + /* Symlink */ +//TODO: what if file_header->link_target == NULL (say, corrupted tarball?) + res = symlink(file_header->link_target, file_header->name); + if ((res == -1) + && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET) + ) { + bb_perror_msg("can't create %slink " + "from %s to %s", "sym", + file_header->name, + file_header->link_target); + } + break; + case S_IFSOCK: + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + res = mknod(file_header->name, file_header->mode, file_header->device); + if ((res == -1) + && !(archive_handle->ah_flags & ARCHIVE_EXTRACT_QUIET) + ) { + bb_perror_msg("can't create node %s", file_header->name); + } + break; + default: + bb_error_msg_and_die("unrecognized file type"); + } + + if (!S_ISLNK(file_header->mode)) { + if (!(archive_handle->ah_flags & ARCHIVE_DONT_RESTORE_OWNER)) { + uid_t uid = file_header->uid; + gid_t gid = file_header->gid; +#if ENABLE_FEATURE_TAR_UNAME_GNAME + if (!(archive_handle->ah_flags & ARCHIVE_NUMERIC_OWNER)) { + if (file_header->tar__uname) { +//TODO: cache last name/id pair? + struct passwd *pwd = getpwnam(file_header->tar__uname); + if (pwd) uid = pwd->pw_uid; + } + if (file_header->tar__gname) { + struct group *grp = getgrnam(file_header->tar__gname); + if (grp) gid = grp->gr_gid; + } + } +#endif + /* GNU tar 1.15.1 uses chown, not lchown */ + chown(file_header->name, uid, gid); + } + /* uclibc has no lchmod, glibc is even stranger - + * it has lchmod which seems to do nothing! + * so we use chmod... */ + if (!(archive_handle->ah_flags & ARCHIVE_DONT_RESTORE_PERM)) { + chmod(file_header->name, file_header->mode); + } + if (archive_handle->ah_flags & ARCHIVE_RESTORE_DATE) { + struct timeval t[2]; + + t[1].tv_sec = t[0].tv_sec = file_header->mtime; + t[1].tv_usec = t[0].tv_usec = 0; + utimes(file_header->name, t); + } + } + + ret: ; +#if ENABLE_FEATURE_TAR_SELINUX + if (sctx) { + /* reset the context after creating an entry */ + setfscreatecon(NULL); + } +#endif +} diff --git a/src/bled/data_skip.c b/src/bled/data_skip.c new file mode 100644 index 00000000..588167f0 --- /dev/null +++ b/src/bled/data_skip.c @@ -0,0 +1,12 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC data_skip(archive_handle_t *archive_handle) +{ + archive_handle->seek(archive_handle->src_fd, archive_handle->file_header->size); +} diff --git a/src/bled/decompress_bunzip2.c b/src/bled/decompress_bunzip2.c new file mode 100644 index 00000000..24fa03cf --- /dev/null +++ b/src/bled/decompress_bunzip2.c @@ -0,0 +1,829 @@ +/* vi: set sw=4 ts=4: */ +/* Small bzip2 deflate implementation, by Rob Landley (rob@landley.net). + + Based on bzip2 decompression code by Julian R Seward (jseward@acm.org), + which also acknowledges contributions by Mike Burrows, David Wheeler, + Peter Fenwick, Alistair Moffat, Radford Neal, Ian H. Witten, + Robert Sedgewick, and Jon L. Bentley. + + Licensed under GPLv2 or later, see file LICENSE in this source tree. +*/ + +/* + Size and speed optimizations by Manuel Novoa III (mjn3@codepoet.org). + + More efficient reading of Huffman codes, a streamlined read_bunzip() + function, and various other tweaks. In (limited) tests, approximately + 20% faster than bzcat on x86 and about 10% faster on arm. + + Note that about 2/3 of the time is spent in read_bunzip() reversing + the Burrows-Wheeler transformation. Much of that time is delay + resulting from cache misses. + + (2010 update by vda: profiled "bzcat <84mbyte.bz2 >/dev/null" + on x86-64 CPU with L2 > 1M: get_next_block is hotter than read_bunzip: + %time seconds calls function + 71.01 12.69 444 get_next_block + 28.65 5.12 93065 read_bunzip + 00.22 0.04 7736490 get_bits + 00.11 0.02 47 dealloc_bunzip + 00.00 0.00 93018 full_write + ...) + + + I would ask that anyone benefiting from this work, especially those + using it in commercial products, consider making a donation to my local + non-profit hospice organization (www.hospiceacadiana.com) in the name of + the woman I loved, Toni W. Hagan, who passed away Feb. 12, 2003. + + Manuel + */ + +#include "libbb.h" +#include "bb_archive.h" + +#if 0 +# define dbg(...) bb_error_msg(__VA_ARGS__) +#else +# define dbg(...) ((void)0) +#endif + +/* Constants for Huffman coding */ +#define MAX_GROUPS 6 +#define GROUP_SIZE 50 /* 64 would have been more efficient */ +#define MAX_HUFCODE_BITS 20 /* Longest Huffman code allowed */ +#define MAX_SYMBOLS 258 /* 256 literals + RUNA + RUNB */ +#define SYMBOL_RUNA 0 +#define SYMBOL_RUNB 1 + +/* Status return values */ +#define RETVAL_OK 0 +#define RETVAL_LAST_BLOCK (dbg("%d", __LINE__), -1) +#define RETVAL_NOT_BZIP_DATA (dbg("%d", __LINE__), -2) +#define RETVAL_UNEXPECTED_INPUT_EOF (dbg("%d", __LINE__), -3) +#define RETVAL_SHORT_WRITE (dbg("%d", __LINE__), -4) +#define RETVAL_DATA_ERROR (dbg("%d", __LINE__), -5) +#define RETVAL_OUT_OF_MEMORY (dbg("%d", __LINE__), -6) +#define RETVAL_OBSOLETE_INPUT (dbg("%d", __LINE__), -7) + +/* Other housekeeping constants */ +#define IOBUF_SIZE 4096 + +/* This is what we know about each Huffman coding group */ +struct group_data { + /* We have an extra slot at the end of limit[] for a sentinel value. */ + int limit[MAX_HUFCODE_BITS+1], base[MAX_HUFCODE_BITS], permute[MAX_SYMBOLS]; + int minLen, maxLen; +}; + +/* Structure holding all the housekeeping data, including IO buffers and + * memory that persists between calls to bunzip + * Found the most used member: + * cat this_file.c | sed -e 's/"/ /g' -e "s/'/ /g" | xargs -n1 \ + * | grep 'bd->' | sed 's/^.*bd->/bd->/' | sort | $PAGER + * and moved it (inbufBitCount) to offset 0. + */ +struct bunzip_data { + /* I/O tracking data (file handles, buffers, positions, etc.) */ + unsigned inbufBitCount, inbufBits; + int in_fd, out_fd, inbufCount, inbufPos /*, outbufPos*/; + uint8_t *inbuf /*,*outbuf*/; + + /* State for interrupting output loop */ + int writeCopies, writePos, writeRunCountdown, writeCount; + int writeCurrent; /* actually a uint8_t */ + + /* The CRC values stored in the block header and calculated from the data */ + uint32_t headerCRC, totalCRC, writeCRC; + + /* Intermediate buffer and its size (in bytes) */ + uint32_t *dbuf; + unsigned dbufSize; + + /* For I/O error handling */ + jmp_buf jmpbuf; + + /* Big things go last (register-relative addressing can be larger for big offsets) */ + uint32_t crc32Table[256]; + uint8_t selectors[32768]; /* nSelectors=15 bits */ + struct group_data groups[MAX_GROUPS]; /* Huffman coding tables */ +}; +/* typedef struct bunzip_data bunzip_data; -- done in .h file */ + + +/* Return the next nnn bits of input. All reads from the compressed input + are done through this function. All reads are big endian */ +static unsigned get_bits(bunzip_data *bd, int bits_wanted) +{ + unsigned bits = 0; + /* Cache bd->inbufBitCount in a CPU register (hopefully): */ + int bit_count = bd->inbufBitCount; + + /* If we need to get more data from the byte buffer, do so. (Loop getting + one byte at a time to enforce endianness and avoid unaligned access.) */ + while (bit_count < bits_wanted) { + + /* If we need to read more data from file into byte buffer, do so */ + if (bd->inbufPos == bd->inbufCount) { + /* if "no input fd" case: in_fd == -1, read fails, we jump */ + bd->inbufCount = safe_read(bd->in_fd, bd->inbuf, IOBUF_SIZE); + if (bd->inbufCount <= 0) + longjmp(bd->jmpbuf, RETVAL_UNEXPECTED_INPUT_EOF); + bd->inbufPos = 0; + } + + /* Avoid 32-bit overflow (dump bit buffer to top of output) */ + if (bit_count >= 24) { + bits = bd->inbufBits & ((1 << bit_count) - 1); + bits_wanted -= bit_count; + bits <<= bits_wanted; + bit_count = 0; + } + + /* Grab next 8 bits of input from buffer. */ + bd->inbufBits = (bd->inbufBits << 8) | bd->inbuf[bd->inbufPos++]; + bit_count += 8; + } + + /* Calculate result */ + bit_count -= bits_wanted; + bd->inbufBitCount = bit_count; + bits |= (bd->inbufBits >> bit_count) & ((1 << bits_wanted) - 1); + + return bits; +} + +/* Unpacks the next block and sets up for the inverse Burrows-Wheeler step. */ +static int get_next_block(bunzip_data *bd) +{ + struct group_data *hufGroup; + int dbufCount, dbufSize, groupCount, *base, *limit, selector, + i, j, t, runPos, symCount, symTotal, nSelectors, byteCount[256]; + int runCnt; + uint8_t uc, symToByte[256], mtfSymbol[256], *selectors; + uint32_t *dbuf; + unsigned origPtr; + + dbuf = bd->dbuf; + dbufSize = bd->dbufSize; + selectors = bd->selectors; + +/* In bbox, we are ok with aborting through setjmp which is set up in start_bunzip */ +#if 0 + /* Reset longjmp I/O error handling */ + i = setjmp(bd->jmpbuf); + if (i) return i; +#endif + + /* Read in header signature and CRC, then validate signature. + (last block signature means CRC is for whole file, return now) */ + i = get_bits(bd, 24); + j = get_bits(bd, 24); + bd->headerCRC = get_bits(bd, 32); + if ((i == 0x177245) && (j == 0x385090)) return RETVAL_LAST_BLOCK; + if ((i != 0x314159) || (j != 0x265359)) return RETVAL_NOT_BZIP_DATA; + + /* We can add support for blockRandomised if anybody complains. There was + some code for this in busybox 1.0.0-pre3, but nobody ever noticed that + it didn't actually work. */ + if (get_bits(bd, 1)) return RETVAL_OBSOLETE_INPUT; + origPtr = get_bits(bd, 24); + if ((int)origPtr > dbufSize) return RETVAL_DATA_ERROR; + + /* mapping table: if some byte values are never used (encoding things + like ascii text), the compression code removes the gaps to have fewer + symbols to deal with, and writes a sparse bitfield indicating which + values were present. We make a translation table to convert the symbols + back to the corresponding bytes. */ + symTotal = 0; + i = 0; + t = get_bits(bd, 16); + do { + if (t & (1 << 15)) { + unsigned inner_map = get_bits(bd, 16); + do { + if (inner_map & (1 << 15)) + symToByte[symTotal++] = i; + inner_map <<= 1; + i++; + } while (i & 15); + i -= 16; + } + t <<= 1; + i += 16; + } while (i < 256); + + /* How many different Huffman coding groups does this block use? */ + groupCount = get_bits(bd, 3); + if (groupCount < 2 || groupCount > MAX_GROUPS) + return RETVAL_DATA_ERROR; + + /* nSelectors: Every GROUP_SIZE many symbols we select a new Huffman coding + group. Read in the group selector list, which is stored as MTF encoded + bit runs. (MTF=Move To Front, as each value is used it's moved to the + start of the list.) */ + for (i = 0; i < groupCount; i++) + mtfSymbol[i] = i; + nSelectors = get_bits(bd, 15); + if (!nSelectors) + return RETVAL_DATA_ERROR; + for (i = 0; i < nSelectors; i++) { + uint8_t tmp_byte; + /* Get next value */ + int n = 0; + while (get_bits(bd, 1)) { + if (n >= groupCount) return RETVAL_DATA_ERROR; + n++; + } + /* Decode MTF to get the next selector */ + tmp_byte = mtfSymbol[n]; + while (--n >= 0) + mtfSymbol[n + 1] = mtfSymbol[n]; + mtfSymbol[0] = selectors[i] = tmp_byte; + } + + /* Read the Huffman coding tables for each group, which code for symTotal + literal symbols, plus two run symbols (RUNA, RUNB) */ + symCount = symTotal + 2; + for (j = 0; j < groupCount; j++) { + uint8_t length[MAX_SYMBOLS]; + /* 8 bits is ALMOST enough for temp[], see below */ + unsigned temp[MAX_HUFCODE_BITS+1]; + int minLen, maxLen, pp, len_m1; + + /* Read Huffman code lengths for each symbol. They're stored in + a way similar to mtf; record a starting value for the first symbol, + and an offset from the previous value for every symbol after that. + (Subtracting 1 before the loop and then adding it back at the end is + an optimization that makes the test inside the loop simpler: symbol + length 0 becomes negative, so an unsigned inequality catches it.) */ + len_m1 = get_bits(bd, 5) - 1; + for (i = 0; i < symCount; i++) { + for (;;) { + int two_bits; + if ((unsigned)len_m1 > (MAX_HUFCODE_BITS-1)) + return RETVAL_DATA_ERROR; + + /* If first bit is 0, stop. Else second bit indicates whether + to increment or decrement the value. Optimization: grab 2 + bits and unget the second if the first was 0. */ + two_bits = get_bits(bd, 2); + if (two_bits < 2) { + bd->inbufBitCount++; + break; + } + + /* Add one if second bit 1, else subtract 1. Avoids if/else */ + len_m1 += (((two_bits+1) & 2) - 1); + } + + /* Correct for the initial -1, to get the final symbol length */ + length[i] = len_m1 + 1; + } + + /* Find largest and smallest lengths in this group */ + minLen = maxLen = length[0]; + for (i = 1; i < symCount; i++) { + if (length[i] > maxLen) maxLen = length[i]; + else if (length[i] < minLen) minLen = length[i]; + } + + /* Calculate permute[], base[], and limit[] tables from length[]. + * + * permute[] is the lookup table for converting Huffman coded symbols + * into decoded symbols. base[] is the amount to subtract from the + * value of a Huffman symbol of a given length when using permute[]. + * + * limit[] indicates the largest numerical value a symbol with a given + * number of bits can have. This is how the Huffman codes can vary in + * length: each code with a value>limit[length] needs another bit. + */ + hufGroup = bd->groups + j; + hufGroup->minLen = minLen; + hufGroup->maxLen = maxLen; + + /* Note that minLen can't be smaller than 1, so we adjust the base + and limit array pointers so we're not always wasting the first + entry. We do this again when using them (during symbol decoding). */ + base = hufGroup->base - 1; + limit = hufGroup->limit - 1; + + /* Calculate permute[]. Concurently, initialize temp[] and limit[]. */ + pp = 0; + for (i = minLen; i <= maxLen; i++) { + int k; + temp[i] = limit[i] = 0; + for (k = 0; k < symCount; k++) + if (length[k] == i) + hufGroup->permute[pp++] = k; + } + + /* Count symbols coded for at each bit length */ + /* NB: in pathological cases, temp[8] can end ip being 256. + * That's why uint8_t is too small for temp[]. */ + for (i = 0; i < symCount; i++) temp[length[i]]++; + + /* Calculate limit[] (the largest symbol-coding value at each bit + * length, which is (previous limit<<1)+symbols at this level), and + * base[] (number of symbols to ignore at each bit length, which is + * limit minus the cumulative count of symbols coded for already). */ + pp = t = 0; + for (i = minLen; i < maxLen;) { + unsigned temp_i = temp[i]; + + pp += temp_i; + + /* We read the largest possible symbol size and then unget bits + after determining how many we need, and those extra bits could + be set to anything. (They're noise from future symbols.) At + each level we're really only interested in the first few bits, + so here we set all the trailing to-be-ignored bits to 1 so they + don't affect the value>limit[length] comparison. */ + limit[i] = (pp << (maxLen - i)) - 1; + pp <<= 1; + t += temp_i; + base[++i] = pp - t; + } + limit[maxLen] = pp + temp[maxLen] - 1; + limit[maxLen+1] = INT_MAX; /* Sentinel value for reading next sym. */ + base[minLen] = 0; + } + + /* We've finished reading and digesting the block header. Now read this + block's Huffman coded symbols from the file and undo the Huffman coding + and run length encoding, saving the result into dbuf[dbufCount++] = uc */ + + /* Initialize symbol occurrence counters and symbol Move To Front table */ + /*memset(byteCount, 0, sizeof(byteCount)); - smaller, but slower */ + for (i = 0; i < 256; i++) { + byteCount[i] = 0; + mtfSymbol[i] = (uint8_t)i; + } + + /* Loop through compressed symbols. */ + + runPos = dbufCount = selector = 0; + for (;;) { + int nextSym; + + /* Fetch next Huffman coding group from list. */ + symCount = GROUP_SIZE - 1; + if (selector >= nSelectors) return RETVAL_DATA_ERROR; + hufGroup = bd->groups + selectors[selector++]; + base = hufGroup->base - 1; + limit = hufGroup->limit - 1; + + continue_this_group: + /* Read next Huffman-coded symbol. */ + + /* Note: It is far cheaper to read maxLen bits and back up than it is + to read minLen bits and then add additional bit at a time, testing + as we go. Because there is a trailing last block (with file CRC), + there is no danger of the overread causing an unexpected EOF for a + valid compressed file. + */ + if (1) { + /* As a further optimization, we do the read inline + (falling back to a call to get_bits if the buffer runs dry). + */ + int new_cnt; + while ((new_cnt = bd->inbufBitCount - hufGroup->maxLen) < 0) { + /* bd->inbufBitCount < hufGroup->maxLen */ + if (bd->inbufPos == bd->inbufCount) { + nextSym = get_bits(bd, hufGroup->maxLen); + goto got_huff_bits; + } + bd->inbufBits = (bd->inbufBits << 8) | bd->inbuf[bd->inbufPos++]; + bd->inbufBitCount += 8; + }; + bd->inbufBitCount = new_cnt; /* "bd->inbufBitCount -= hufGroup->maxLen;" */ + nextSym = (bd->inbufBits >> new_cnt) & ((1 << hufGroup->maxLen) - 1); + got_huff_bits: ; + } else { /* unoptimized equivalent */ + nextSym = get_bits(bd, hufGroup->maxLen); + } + /* Figure how many bits are in next symbol and unget extras */ + i = hufGroup->minLen; + while (nextSym > limit[i]) ++i; + j = hufGroup->maxLen - i; + if (j < 0) + return RETVAL_DATA_ERROR; + bd->inbufBitCount += j; + + /* Huffman decode value to get nextSym (with bounds checking) */ + nextSym = (nextSym >> j) - base[i]; + if ((unsigned)nextSym >= MAX_SYMBOLS) + return RETVAL_DATA_ERROR; + nextSym = hufGroup->permute[nextSym]; + + /* We have now decoded the symbol, which indicates either a new literal + byte, or a repeated run of the most recent literal byte. First, + check if nextSym indicates a repeated run, and if so loop collecting + how many times to repeat the last literal. */ + if ((unsigned)nextSym <= SYMBOL_RUNB) { /* RUNA or RUNB */ + + /* If this is the start of a new run, zero out counter */ + if (runPos == 0) { + runPos = 1; + runCnt = 0; + } + + /* Neat trick that saves 1 symbol: instead of or-ing 0 or 1 at + each bit position, add 1 or 2 instead. For example, + 1011 is 1<<0 + 1<<1 + 2<<2. 1010 is 2<<0 + 2<<1 + 1<<2. + You can make any bit pattern that way using 1 less symbol than + the basic or 0/1 method (except all bits 0, which would use no + symbols, but a run of length 0 doesn't mean anything in this + context). Thus space is saved. */ + runCnt += (runPos << nextSym); /* +runPos if RUNA; +2*runPos if RUNB */ + if (runPos < dbufSize) runPos <<= 1; + goto end_of_huffman_loop; + } + + /* When we hit the first non-run symbol after a run, we now know + how many times to repeat the last literal, so append that many + copies to our buffer of decoded symbols (dbuf) now. (The last + literal used is the one at the head of the mtfSymbol array.) */ + if (runPos != 0) { + uint8_t tmp_byte; + if (dbufCount + runCnt > dbufSize) { + dbg("dbufCount:%d+runCnt:%d %d > dbufSize:%d RETVAL_DATA_ERROR", + dbufCount, runCnt, dbufCount + runCnt, dbufSize); + return RETVAL_DATA_ERROR; + } + tmp_byte = symToByte[mtfSymbol[0]]; + byteCount[tmp_byte] += runCnt; + while (--runCnt >= 0) dbuf[dbufCount++] = (uint32_t)tmp_byte; + runPos = 0; + } + + /* Is this the terminating symbol? */ + if (nextSym > symTotal) break; + + /* At this point, nextSym indicates a new literal character. Subtract + one to get the position in the MTF array at which this literal is + currently to be found. (Note that the result can't be -1 or 0, + because 0 and 1 are RUNA and RUNB. But another instance of the + first symbol in the mtf array, position 0, would have been handled + as part of a run above. Therefore 1 unused mtf position minus + 2 non-literal nextSym values equals -1.) */ + if (dbufCount >= dbufSize) return RETVAL_DATA_ERROR; + i = nextSym - 1; + uc = mtfSymbol[i]; + + /* Adjust the MTF array. Since we typically expect to move only a + * small number of symbols, and are bound by 256 in any case, using + * memmove here would typically be bigger and slower due to function + * call overhead and other assorted setup costs. */ + do { + mtfSymbol[i] = mtfSymbol[i-1]; + } while (--i); + mtfSymbol[0] = uc; + uc = symToByte[uc]; + + /* We have our literal byte. Save it into dbuf. */ + byteCount[uc]++; + dbuf[dbufCount++] = (uint32_t)uc; + + /* Skip group initialization if we're not done with this group. Done + * this way to avoid compiler warning. */ + end_of_huffman_loop: + if (--symCount >= 0) goto continue_this_group; + } + + /* At this point, we've read all the Huffman-coded symbols (and repeated + runs) for this block from the input stream, and decoded them into the + intermediate buffer. There are dbufCount many decoded bytes in dbuf[]. + Now undo the Burrows-Wheeler transform on dbuf. + See http://dogma.net/markn/articles/bwt/bwt.htm + */ + + /* Turn byteCount into cumulative occurrence counts of 0 to n-1. */ + j = 0; + for (i = 0; i < 256; i++) { + int tmp_count = j + byteCount[i]; + byteCount[i] = j; + j = tmp_count; + } + + /* Figure out what order dbuf would be in if we sorted it. */ + for (i = 0; i < dbufCount; i++) { + uint8_t tmp_byte = (uint8_t)dbuf[i]; + int tmp_count = byteCount[tmp_byte]; + dbuf[tmp_count] |= (i << 8); + byteCount[tmp_byte] = tmp_count + 1; + } + + /* Decode first byte by hand to initialize "previous" byte. Note that it + doesn't get output, and if the first three characters are identical + it doesn't qualify as a run (hence writeRunCountdown=5). */ + if (dbufCount) { + uint32_t tmp; + if ((int)origPtr >= dbufCount) return RETVAL_DATA_ERROR; + tmp = dbuf[origPtr]; + bd->writeCurrent = (uint8_t)tmp; + bd->writePos = (tmp >> 8); + bd->writeRunCountdown = 5; + } + bd->writeCount = dbufCount; + + return RETVAL_OK; +} + +/* Undo Burrows-Wheeler transform on intermediate buffer to produce output. + If start_bunzip was initialized with out_fd=-1, then up to len bytes of + data are written to outbuf. Return value is number of bytes written or + error (all errors are negative numbers). If out_fd!=-1, outbuf and len + are ignored, data is written to out_fd and return is RETVAL_OK or error. + + NB: read_bunzip returns < 0 on error, or the number of *unfilled* bytes + in outbuf. IOW: on EOF returns len ("all bytes are not filled"), not 0. + (Why? This allows to get rid of one local variable) +*/ +int FAST_FUNC read_bunzip(bunzip_data *bd, char *outbuf, int len) +{ + const uint32_t *dbuf; + int pos, current, previous; + uint32_t CRC; + + /* If we already have error/end indicator, return it */ + if (bd->writeCount < 0) + return bd->writeCount; + + dbuf = bd->dbuf; + + /* Register-cached state (hopefully): */ + pos = bd->writePos; + current = bd->writeCurrent; + CRC = bd->writeCRC; /* small loss on x86-32 (not enough regs), win on x86-64 */ + + /* We will always have pending decoded data to write into the output + buffer unless this is the very first call (in which case we haven't + Huffman-decoded a block into the intermediate buffer yet). */ + if (bd->writeCopies) { + + dec_writeCopies: + /* Inside the loop, writeCopies means extra copies (beyond 1) */ + --bd->writeCopies; + + /* Loop outputting bytes */ + for (;;) { + + /* If the output buffer is full, save cached state and return */ + if (--len < 0) { + /* Unlikely branch. + * Use of "goto" instead of keeping code here + * helps compiler to realize this. */ + goto outbuf_full; + } + + /* Write next byte into output buffer, updating CRC */ + *outbuf++ = current; + CRC = (CRC << 8) ^ bd->crc32Table[(CRC >> 24) ^ current]; + + /* Loop now if we're outputting multiple copies of this byte */ + if (bd->writeCopies) { + /* Unlikely branch */ + /*--bd->writeCopies;*/ + /*continue;*/ + /* Same, but (ab)using other existing --writeCopies operation + * (and this if() compiles into just test+branch pair): */ + goto dec_writeCopies; + } + decode_next_byte: + if (--bd->writeCount < 0) + break; /* input block is fully consumed, need next one */ + + /* Follow sequence vector to undo Burrows-Wheeler transform */ + previous = current; + pos = dbuf[pos]; + current = (uint8_t)pos; + pos >>= 8; + + /* After 3 consecutive copies of the same byte, the 4th + * is a repeat count. We count down from 4 instead + * of counting up because testing for non-zero is faster */ + if (--bd->writeRunCountdown != 0) { + if (current != previous) + bd->writeRunCountdown = 4; + } else { + /* Unlikely branch */ + /* We have a repeated run, this byte indicates the count */ + bd->writeCopies = current; + current = previous; + bd->writeRunCountdown = 5; + + /* Sometimes there are just 3 bytes (run length 0) */ + if (!bd->writeCopies) goto decode_next_byte; + + /* Subtract the 1 copy we'd output anyway to get extras */ + --bd->writeCopies; + } + } /* for(;;) */ + + /* Decompression of this input block completed successfully */ + bd->writeCRC = CRC = ~CRC; + bd->totalCRC = ((bd->totalCRC << 1) | (bd->totalCRC >> 31)) ^ CRC; + + /* If this block had a CRC error, force file level CRC error */ + if (CRC != bd->headerCRC) { + bd->totalCRC = bd->headerCRC + 1; + return RETVAL_LAST_BLOCK; + } + } + + /* Refill the intermediate buffer by Huffman-decoding next block of input */ + { + int r = get_next_block(bd); + if (r) { /* error/end */ + bd->writeCount = r; + return (r != RETVAL_LAST_BLOCK) ? r : len; + } + } + + CRC = ~0; + pos = bd->writePos; + current = bd->writeCurrent; + goto decode_next_byte; + + outbuf_full: + /* Output buffer is full, save cached state and return */ + bd->writePos = pos; + bd->writeCurrent = current; + bd->writeCRC = CRC; + + bd->writeCopies++; + + return 0; +} + +/* Allocate the structure, read file header. If in_fd==-1, inbuf must contain + a complete bunzip file (len bytes long). If in_fd!=-1, inbuf and len are + ignored, and data is read from file handle into temporary buffer. */ + +/* Because bunzip2 is used for help text unpacking, and because bb_show_usage() + should work for NOFORK applets too, we must be extremely careful to not leak + any allocations! */ +int FAST_FUNC start_bunzip(bunzip_data **bdp, int in_fd, + const void *inbuf, int len) +{ + bunzip_data *bd; + unsigned i; + enum { + BZh0 = ('B' << 24) + ('Z' << 16) + ('h' << 8) + '0', + h0 = ('h' << 8) + '0', + }; + + /* Figure out how much data to allocate */ + i = sizeof(bunzip_data); + if (in_fd != -1) i += IOBUF_SIZE; + + /* Allocate bunzip_data. Most fields initialize to zero. */ + bd = *bdp = xzalloc(i); + + /* Setup input buffer */ + bd->in_fd = in_fd; + if (-1 == in_fd) { + /* in this case, bd->inbuf is read-only */ + bd->inbuf = (void*)inbuf; /* cast away const-ness */ + } else { + bd->inbuf = (uint8_t*)(bd + 1); + memcpy(bd->inbuf, inbuf, len); + } + bd->inbufCount = len; + + /* Init the CRC32 table (big endian) */ + crc32_filltable(bd->crc32Table, 1); + + /* Setup for I/O error handling via longjmp */ + i = setjmp(bd->jmpbuf); + if (i) return i; + + /* Ensure that file starts with "BZh['1'-'9']." */ + /* Update: now caller verifies 1st two bytes, makes .gz/.bz2 + * integration easier */ + /* was: */ + /* i = get_bits(bd, 32); */ + /* if ((unsigned)(i - BZh0 - 1) >= 9) return RETVAL_NOT_BZIP_DATA; */ + i = get_bits(bd, 16); + if ((unsigned)(i - h0 - 1) >= 9) return RETVAL_NOT_BZIP_DATA; + + /* Fourth byte (ascii '1'-'9') indicates block size in units of 100k of + uncompressed data. Allocate intermediate buffer for block. */ + /* bd->dbufSize = 100000 * (i - BZh0); */ + bd->dbufSize = 100000 * (i - h0); + + /* Cannot use xmalloc - may leak bd in NOFORK case! */ + bd->dbuf = malloc_or_warn(bd->dbufSize * sizeof(bd->dbuf[0])); + if (!bd->dbuf) { + free(bd); + xfunc_die(); + } + return RETVAL_OK; +} + +void FAST_FUNC dealloc_bunzip(bunzip_data *bd) +{ + free(bd->dbuf); + free(bd); +} + + +/* Decompress src_fd to dst_fd. Stops at end of bzip data, not end of file. */ +IF_DESKTOP(long long) int FAST_FUNC +unpack_bz2_stream(transformer_state_t *xstate) +{ + IF_DESKTOP(long long total_written = 0;) + bunzip_data *bd; + char *outbuf; + int i; + unsigned len; + + if (check_signature16(xstate, BZIP2_MAGIC)) + return -1; + + outbuf = xmalloc(IOBUF_SIZE); + len = 0; + while (1) { /* "Process one BZ... stream" loop */ + + i = start_bunzip(&bd, xstate->src_fd, outbuf + 2, len); + + if (i == 0) { + while (1) { /* "Produce some output bytes" loop */ + i = read_bunzip(bd, outbuf, IOBUF_SIZE); + if (i < 0) /* error? */ + break; + i = IOBUF_SIZE - i; /* number of bytes produced */ + if (i == 0) /* EOF? */ + break; + if (i != transformer_write(xstate, outbuf, i)) { + i = RETVAL_SHORT_WRITE; + goto release_mem; + } + IF_DESKTOP(total_written += i;) + } + } + + if (i != RETVAL_LAST_BLOCK + /* Observed case when i == RETVAL_OK: + * "bzcat z.bz2", where "z.bz2" is a bzipped zero-length file + * (to be exact, z.bz2 is exactly these 14 bytes: + * 42 5a 68 39 17 72 45 38 50 90 00 00 00 00). + */ + && i != RETVAL_OK + ) { + bb_error_msg("bunzip error %d", i); + break; + } + if (bd->headerCRC != bd->totalCRC) { + bb_error_msg("CRC error"); + break; + } + + /* Successfully unpacked one BZ stream */ + i = RETVAL_OK; + + /* Do we have "BZ..." after last processed byte? + * pbzip2 (parallelized bzip2) produces such files. + */ + len = bd->inbufCount - bd->inbufPos; + memcpy(outbuf, &bd->inbuf[bd->inbufPos], len); + if (len < 2) { + if (safe_read(xstate->src_fd, outbuf + len, 2 - len) != 2 - len) + break; + len = 2; + } + if (*(uint16_t*)outbuf != BZIP2_MAGIC) /* "BZ"? */ + break; + dealloc_bunzip(bd); + len -= 2; + } + + release_mem: + dealloc_bunzip(bd); + free(outbuf); + + return i ? i : IF_DESKTOP(total_written) + 0; +} + +#ifdef TESTING + +static char *const bunzip_errors[] = { + NULL, "Bad file checksum", "Not bzip data", + "Unexpected input EOF", "Unexpected output EOF", "Data error", + "Out of memory", "Obsolete (pre 0.9.5) bzip format not supported" +}; + +/* Dumb little test thing, decompress stdin to stdout */ +int main(int argc, char **argv) +{ + char c; + + int i = unpack_bz2_stream(0, 1); + if (i < 0) + fprintf(stderr, "%s\n", bunzip_errors[-i]); + else if (read(STDIN_FILENO, &c, 1)) + fprintf(stderr, "Trailing garbage ignored\n"); + return -i; +} +#endif diff --git a/src/bled/decompress_gunzip.c b/src/bled/decompress_gunzip.c new file mode 100644 index 00000000..d1b4f7f0 --- /dev/null +++ b/src/bled/decompress_gunzip.c @@ -0,0 +1,1271 @@ +/* vi: set sw=4 ts=4: */ +/* + * gunzip implementation for busybox + * + * Based on GNU gzip v1.2.4 Copyright (C) 1992-1993 Jean-loup Gailly. + * + * Originally adjusted for busybox by Sven Rudolph + * based on gzip sources + * + * Adjusted further by Erik Andersen to support + * files as well as stdin/stdout, and to generally behave itself wrt + * command line handling. + * + * General cleanup to better adhere to the style guide and make use of standard + * busybox functions by Glenn McGrath + * + * read_gz interface + associated hacking by Laurence Anderson + * + * Fixed huft_build() so decoding end-of-block code does not grab more bits + * than necessary (this is required by unzip applet), added inflate_cleanup() + * to free leaked bytebuffer memory (used in unzip.c), and some minor style + * guide cleanups by Ed Clark + * + * gzip (GNU zip) -- compress files with zip algorithm and 'compress' interface + * Copyright (C) 1992-1993 Jean-loup Gailly + * The unzip code was written and put in the public domain by Mark Adler. + * Portions of the lzw code are derived from the public domain 'compress' + * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies, + * Ken Turkowski, Dave Mack and Peter Jannesen. + * + * See the file algorithm.doc for the compression algorithms and file formats. + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include +#include "libbb.h" +#include "bb_archive.h" + +typedef struct huft_t { + unsigned char e; /* number of extra bits or operation */ + unsigned char b; /* number of bits in this code or subcode */ + union { + unsigned short n; /* literal, length base, or distance base */ + struct huft_t *t; /* pointer to next level of table */ + } v; +} huft_t; + +enum { + /* gunzip_window size--must be a power of two, and + * at least 32K for zip's deflate method */ + GUNZIP_WSIZE = 0x8000, + /* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ + BMAX = 16, /* maximum bit length of any code (16 for explode) */ + N_MAX = 288, /* maximum number of codes in any set */ +}; + + +/* This is somewhat complex-looking arrangement, but it allows + * to place decompressor state either in bss or in + * malloc'ed space simply by changing #defines below. + * Sizes on i386: + * text data bss dec hex + * 5256 0 108 5364 14f4 - bss + * 4915 0 0 4915 1333 - malloc + */ +#define STATE_IN_BSS 0 +#define STATE_IN_MALLOC 1 + + +typedef struct state_t { + off_t gunzip_bytes_out; /* number of output bytes */ + uint32_t gunzip_crc; + + int gunzip_src_fd; + unsigned gunzip_outbuf_count; /* bytes in output buffer */ + + unsigned char *gunzip_window; + + uint32_t *gunzip_crc_table; + + /* bitbuffer */ + unsigned gunzip_bb; /* bit buffer */ + unsigned char gunzip_bk; /* bits in bit buffer */ + + /* input (compressed) data */ + unsigned char *bytebuffer; /* buffer itself */ + off_t to_read; /* compressed bytes to read (unzip only, -1 for gunzip) */ +// unsigned bytebuffer_max; /* buffer size */ + unsigned bytebuffer_offset; /* buffer position */ + unsigned bytebuffer_size; /* how much data is there (size <= max) */ + + /* private data of inflate_codes() */ + unsigned inflate_codes_ml; /* masks for bl and bd bits */ + unsigned inflate_codes_md; /* masks for bl and bd bits */ + unsigned inflate_codes_bb; /* bit buffer */ + unsigned inflate_codes_k; /* number of bits in bit buffer */ + unsigned inflate_codes_w; /* current gunzip_window position */ + huft_t *inflate_codes_tl; + huft_t *inflate_codes_td; + unsigned inflate_codes_bl; + unsigned inflate_codes_bd; + unsigned inflate_codes_nn; /* length and index for copy */ + unsigned inflate_codes_dd; + + smallint resume_copy; + + /* private data of inflate_get_next_window() */ + smallint method; /* method == -1 for stored, -2 for codes */ + smallint need_another_block; + smallint end_reached; + + /* private data of inflate_stored() */ + unsigned inflate_stored_n; + unsigned inflate_stored_b; + unsigned inflate_stored_k; + unsigned inflate_stored_w; + + const char *error_msg; + jmp_buf error_jmp; +} state_t; +#define gunzip_bytes_out (S()gunzip_bytes_out ) +#define gunzip_crc (S()gunzip_crc ) +#define gunzip_src_fd (S()gunzip_src_fd ) +#define gunzip_outbuf_count (S()gunzip_outbuf_count) +#define gunzip_window (S()gunzip_window ) +#define gunzip_crc_table (S()gunzip_crc_table ) +#define gunzip_bb (S()gunzip_bb ) +#define gunzip_bk (S()gunzip_bk ) +#define to_read (S()to_read ) +// #define bytebuffer_max (S()bytebuffer_max ) +// Both gunzip and unzip can use constant buffer size now (16k): +#define bytebuffer_max 0x4000 +#define bytebuffer (S()bytebuffer ) +#define bytebuffer_offset (S()bytebuffer_offset ) +#define bytebuffer_size (S()bytebuffer_size ) +#define inflate_codes_ml (S()inflate_codes_ml ) +#define inflate_codes_md (S()inflate_codes_md ) +#define inflate_codes_bb (S()inflate_codes_bb ) +#define inflate_codes_k (S()inflate_codes_k ) +#define inflate_codes_w (S()inflate_codes_w ) +#define inflate_codes_tl (S()inflate_codes_tl ) +#define inflate_codes_td (S()inflate_codes_td ) +#define inflate_codes_bl (S()inflate_codes_bl ) +#define inflate_codes_bd (S()inflate_codes_bd ) +#define inflate_codes_nn (S()inflate_codes_nn ) +#define inflate_codes_dd (S()inflate_codes_dd ) +#define resume_copy (S()resume_copy ) +#define method (S()method ) +#define need_another_block (S()need_another_block ) +#define end_reached (S()end_reached ) +#define inflate_stored_n (S()inflate_stored_n ) +#define inflate_stored_b (S()inflate_stored_b ) +#define inflate_stored_k (S()inflate_stored_k ) +#define inflate_stored_w (S()inflate_stored_w ) +#define error_msg (S()error_msg ) +#define error_jmp (S()error_jmp ) + +/* This is a generic part */ +#if STATE_IN_BSS /* Use global data segment */ +#define DECLARE_STATE /*nothing*/ +#define ALLOC_STATE /*nothing*/ +#define DEALLOC_STATE ((void)0) +#define S() state. +#define PASS_STATE /*nothing*/ +#define PASS_STATE_ONLY /*nothing*/ +#define STATE_PARAM /*nothing*/ +#define STATE_PARAM_ONLY void +static state_t state; +#endif + +#if STATE_IN_MALLOC /* Use malloc space */ +#define DECLARE_STATE state_t *state +#define ALLOC_STATE (state = xzalloc(sizeof(*state))) +#define DEALLOC_STATE free(state) +#define S() state-> +#define PASS_STATE state, +#define PASS_STATE_ONLY state +#define STATE_PARAM state_t *state, +#define STATE_PARAM_ONLY state_t *state +#endif + + +static const uint16_t mask_bits[] ALIGN2 = { + 0x0000, 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + +/* Copy lengths for literal codes 257..285 */ +static const uint16_t cplens[] ALIGN2 = { + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, 35, 43, 51, 59, + 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0 +}; + +/* note: see note #13 above about the 258 in this list. */ +/* Extra bits for literal codes 257..285 */ +static const uint8_t cplext[] ALIGN1 = { + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, + 5, 5, 5, 0, 99, 99 +}; /* 99 == invalid */ + +/* Copy offsets for distance codes 0..29 */ +static const uint16_t cpdist[] ALIGN2 = { + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, + 769, 1025, 1537, 2049, 3073, 4097, 6145, 8193, 12289, 16385, 24577 +}; + +/* Extra bits for distance codes */ +static const uint8_t cpdext[] ALIGN1 = { + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, + 11, 11, 12, 12, 13, 13 +}; + +/* Tables for deflate from PKZIP's appnote.txt. */ +/* Order of the bit length code lengths */ +static const uint8_t border[] ALIGN1 = { + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15 +}; + + +/* + * Free the malloc'ed tables built by huft_build(), which makes a linked + * list of the tables it made, with the links in a dummy first entry of + * each table. + * t: table to free + */ +static void huft_free(huft_t *p) +{ + huft_t *q; + + /* Go through linked list, freeing from the malloced (t[-1]) address. */ + while (p) { + q = (--p)->v.t; + free(p); + p = q; + } +} + +static void huft_free_all(STATE_PARAM_ONLY) +{ + huft_free(inflate_codes_tl); + huft_free(inflate_codes_td); + inflate_codes_tl = NULL; + inflate_codes_td = NULL; +} + +static void abort_unzip(STATE_PARAM_ONLY) NORETURN; +static void abort_unzip(STATE_PARAM_ONLY) +{ + huft_free_all(PASS_STATE_ONLY); + longjmp(error_jmp, 1); +} + +static unsigned fill_bitbuffer(STATE_PARAM unsigned bitbuffer, unsigned *current, const unsigned required) +{ + while (*current < required) { + if (bytebuffer_offset >= bytebuffer_size) { + unsigned sz = bytebuffer_max - 4; + if (to_read >= 0 && to_read < sz) /* unzip only */ + sz = to_read; + /* Leave the first 4 bytes empty so we can always unwind the bitbuffer + * to the front of the bytebuffer */ + bytebuffer_size = safe_read(gunzip_src_fd, &bytebuffer[4], sz); + if ((int)bytebuffer_size < 1) { + error_msg = "unexpected end of file"; + abort_unzip(PASS_STATE_ONLY); + } + if (to_read >= 0) /* unzip only */ + to_read -= bytebuffer_size; + bytebuffer_size += 4; + bytebuffer_offset = 4; + } + bitbuffer |= ((unsigned) bytebuffer[bytebuffer_offset]) << *current; + bytebuffer_offset++; + *current += 8; + } + return bitbuffer; +} + + +/* Given a list of code lengths and a maximum table size, make a set of + * tables to decode that set of codes. Return zero on success, one if + * the given code set is incomplete (the tables are still built in this + * case), two if the input is invalid (all zero length codes or an + * oversubscribed set of lengths) - in this case stores NULL in *t. + * + * b: code lengths in bits (all assumed <= BMAX) + * n: number of codes (assumed <= N_MAX) + * s: number of simple-valued codes (0..s-1) + * d: list of base values for non-simple codes + * e: list of extra bits for non-simple codes + * t: result: starting table + * m: maximum lookup bits, returns actual + */ +static int huft_build(const unsigned *b, const unsigned n, + const unsigned s, const unsigned short *d, + const unsigned char *e, huft_t **t, unsigned *m) +{ + unsigned a; /* counter for codes of length k */ + unsigned c[BMAX + 1]; /* bit length count table */ + unsigned eob_len; /* length of end-of-block code (value 256) */ + unsigned f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int htl; /* table level */ + unsigned i; /* counter, current code */ + unsigned j; /* counter */ + int k; /* number of bits in current code */ + unsigned *p; /* pointer into c[], b[], or v[] */ + huft_t *q; /* points to current table */ + huft_t r; /* table entry for structure assignment */ + huft_t *u[BMAX]; /* table stack */ + unsigned v[N_MAX]; /* values in order of bit length */ + int ws[BMAX + 1]; /* bits decoded stack */ + int w; /* bits decoded */ + unsigned x[BMAX + 1]; /* bit offsets, then code stack */ + unsigned *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + unsigned z; /* number of entries in current table */ + + /* Length of EOB code, if any */ + eob_len = n > 256 ? b[256] : BMAX; + + *t = NULL; + + /* Generate counts for each bit length */ + memset(c, 0, sizeof(c)); + p = (unsigned *) b; /* cast allows us to reuse p for pointing to b */ + i = n; + do { + c[*p]++; /* assume all entries <= BMAX */ + p++; /* can't combine with above line (Solaris bug) */ + } while (--i); + if (c[0] == n) { /* null input - all zero length codes */ + *m = 0; + return 2; + } + + /* Find minimum and maximum length, bound *m by those */ + for (j = 1; (j <= BMAX) && (c[j] == 0); j++) + continue; + k = j; /* minimum code length */ + for (i = BMAX; (c[i] == 0) && i; i--) + continue; + g = i; /* maximum code length */ + *m = (*m < j) ? j : ((*m > i) ? i : *m); + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) { + y -= c[j]; + if (y < 0) + return 2; /* bad input: more codes than bits */ + } + y -= c[i]; + if (y < 0) + return 2; + c[i] += y; + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; + xp = x + 2; + while (--i) { /* note that i == g from above */ + j += *p++; + *xp++ = j; + } + + /* Make a table of values in order of bit lengths */ + p = (unsigned *) b; + i = 0; + do { + j = *p++; + if (j != 0) { + v[x[j]++] = i; + } + } while (++i < n); + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + htl = -1; /* no tables yet--level -1 */ + w = ws[0] = 0; /* bits decoded */ + u[0] = NULL; /* just to keep compilers happy */ + q = NULL; /* ditto */ + z = 0; /* ditto */ + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) { + a = c[k]; + while (a--) { + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > ws[htl + 1]) { + w = ws[++htl]; + + /* compute minimum size table less than or equal to *m bits */ + z = g - w; + z = z > *m ? *m : z; /* upper limit on table size */ + j = k - w; + f = 1 << j; + if (f > a + 1) { /* try a k-w bit table */ + /* too few codes for k-w bit table */ + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + while (++j < z) { /* try smaller tables up to z bits */ + f <<= 1; + if (f <= *++xp) { + break; /* enough codes to use up j bits */ + } + f -= *xp; /* else deduct codes from patterns */ + } + } + j = ((w + j) > (int)eob_len && w < (int)eob_len) ? eob_len - w : j; /* make EOB code end at table */ + z = 1 << j; /* table entries for j-bit table */ + ws[htl+1] = w + j; /* set bits decoded in stack */ + + /* allocate and link in new table */ + q = xzalloc((z + 1) * sizeof(huft_t)); + *t = q + 1; /* link to list for huft_free() */ + t = &(q->v.t); + u[htl] = ++q; /* table starts after link */ + + /* connect to last table, if there is one */ + if (htl) { + x[htl] = i; /* save pattern for backing up */ + r.b = (unsigned char) (w - ws[htl - 1]); /* bits to dump before this table */ + r.e = (unsigned char) (16 + j); /* bits in this table */ + r.v.t = q; /* pointer to this table */ + j = (i & ((1 << w) - 1)) >> ws[htl - 1]; + u[htl - 1][j] = r; /* connect to last table */ + } + } + + /* set up table entry in r */ + r.b = (unsigned char) (k - w); + if (p >= v + n) { + r.e = 99; /* out of values--invalid code */ + } else if (*p < s) { + r.e = (unsigned char) (*p < 256 ? 16 : 15); /* 256 is EOB code */ + r.v.n = (unsigned short) (*p++); /* simple code is just the value */ + } else { + r.e = (unsigned char) e[*p - s]; /* non-simple--look up in lists */ + r.v.n = d[*p++ - s]; + } + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) { + q[j] = r; + } + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) { + i ^= j; + } + i ^= j; + + /* backup over finished tables */ + while ((i & ((1 << w) - 1)) != x[htl]) { + w = ws[--htl]; + } + } + } + + /* return actual size of base table */ + *m = ws[1]; + + /* Return 1 if we were given an incomplete table */ + return y != 0 && g != 1; +} + + +/* + * inflate (decompress) the codes in a deflated (compressed) block. + * Return an error code or zero if it all goes ok. + * + * tl, td: literal/length and distance decoder tables + * bl, bd: number of bits decoded by tl[] and td[] + */ +/* called once from inflate_block */ + +/* map formerly local static variables to globals */ +#define ml inflate_codes_ml +#define md inflate_codes_md +#define bb inflate_codes_bb +#define k inflate_codes_k +#define w inflate_codes_w +#define tl inflate_codes_tl +#define td inflate_codes_td +#define bl inflate_codes_bl +#define bd inflate_codes_bd +#define nn inflate_codes_nn +#define dd inflate_codes_dd +static void inflate_codes_setup(STATE_PARAM unsigned my_bl, unsigned my_bd) +{ + bl = my_bl; + bd = my_bd; + /* make local copies of globals */ + bb = gunzip_bb; /* initialize bit buffer */ + k = gunzip_bk; + w = gunzip_outbuf_count; /* initialize gunzip_window position */ + /* inflate the coded data */ + ml = mask_bits[bl]; /* precompute masks for speed */ + md = mask_bits[bd]; +} +/* called once from inflate_get_next_window */ +static NOINLINE int inflate_codes(STATE_PARAM_ONLY) +{ + unsigned e; /* table entry flag/number of extra bits */ + huft_t *t; /* pointer to table entry */ + + if (resume_copy) + goto do_copy; + + while (1) { /* do until end of block */ + bb = fill_bitbuffer(PASS_STATE bb, &k, bl); + t = tl + ((unsigned) bb & ml); + e = t->e; + if (e > 16) + do { + if (e == 99) + abort_unzip(PASS_STATE_ONLY);; + bb >>= t->b; + k -= t->b; + e -= 16; + bb = fill_bitbuffer(PASS_STATE bb, &k, e); + t = t->v.t + ((unsigned) bb & mask_bits[e]); + e = t->e; + } while (e > 16); + bb >>= t->b; + k -= t->b; + if (e == 16) { /* then it's a literal */ + gunzip_window[w++] = (unsigned char) t->v.n; + if (w == GUNZIP_WSIZE) { + gunzip_outbuf_count = w; + //flush_gunzip_window(); + w = 0; + return 1; // We have a block to read + } + } else { /* it's an EOB or a length */ + /* exit if end of block */ + if (e == 15) { + break; + } + + /* get length of block to copy */ + bb = fill_bitbuffer(PASS_STATE bb, &k, e); + nn = t->v.n + ((unsigned) bb & mask_bits[e]); + bb >>= e; + k -= e; + + /* decode distance of block to copy */ + bb = fill_bitbuffer(PASS_STATE bb, &k, bd); + t = td + ((unsigned) bb & md); + e = t->e; + if (e > 16) + do { + if (e == 99) + abort_unzip(PASS_STATE_ONLY); + bb >>= t->b; + k -= t->b; + e -= 16; + bb = fill_bitbuffer(PASS_STATE bb, &k, e); + t = t->v.t + ((unsigned) bb & mask_bits[e]); + e = t->e; + } while (e > 16); + bb >>= t->b; + k -= t->b; + bb = fill_bitbuffer(PASS_STATE bb, &k, e); + dd = w - t->v.n - ((unsigned) bb & mask_bits[e]); + bb >>= e; + k -= e; + + /* do the copy */ + do_copy: + do { + /* Was: nn -= (e = (e = GUNZIP_WSIZE - ((dd &= GUNZIP_WSIZE - 1) > w ? dd : w)) > nn ? nn : e); */ + /* Who wrote THAT?? rewritten as: */ + unsigned delta; + + dd &= GUNZIP_WSIZE - 1; + e = GUNZIP_WSIZE - (dd > w ? dd : w); + delta = w > dd ? w - dd : dd - w; + if (e > nn) e = nn; + nn -= e; + + /* copy to new buffer to prevent possible overwrite */ + if (delta >= e) { + memcpy(gunzip_window + w, gunzip_window + dd, e); + w += e; + dd += e; + } else { + /* do it slow to avoid memcpy() overlap */ + /* !NOMEMCPY */ + do { + gunzip_window[w++] = gunzip_window[dd++]; + } while (--e); + } + if (w == GUNZIP_WSIZE) { + gunzip_outbuf_count = w; + resume_copy = (nn != 0); + //flush_gunzip_window(); + w = 0; + return 1; + } + } while (nn); + resume_copy = 0; + } + } + + /* restore the globals from the locals */ + gunzip_outbuf_count = w; /* restore global gunzip_window pointer */ + gunzip_bb = bb; /* restore global bit buffer */ + gunzip_bk = k; + + /* normally just after call to inflate_codes, but save code by putting it here */ + /* free the decoding tables (tl and td), return */ + huft_free_all(PASS_STATE_ONLY); + + /* done */ + return 0; +} +#undef ml +#undef md +#undef bb +#undef k +#undef w +#undef tl +#undef td +#undef bl +#undef bd +#undef nn +#undef dd + + +/* called once from inflate_block */ +static void inflate_stored_setup(STATE_PARAM int my_n, int my_b, int my_k) +{ + inflate_stored_n = my_n; + inflate_stored_b = my_b; + inflate_stored_k = my_k; + /* initialize gunzip_window position */ + inflate_stored_w = gunzip_outbuf_count; +} +/* called once from inflate_get_next_window */ +static int inflate_stored(STATE_PARAM_ONLY) +{ + /* read and output the compressed data */ + while (inflate_stored_n--) { + inflate_stored_b = fill_bitbuffer(PASS_STATE inflate_stored_b, &inflate_stored_k, 8); + gunzip_window[inflate_stored_w++] = (unsigned char) inflate_stored_b; + if (inflate_stored_w == GUNZIP_WSIZE) { + gunzip_outbuf_count = inflate_stored_w; + //flush_gunzip_window(); + inflate_stored_w = 0; + inflate_stored_b >>= 8; + inflate_stored_k -= 8; + return 1; /* We have a block */ + } + inflate_stored_b >>= 8; + inflate_stored_k -= 8; + } + + /* restore the globals from the locals */ + gunzip_outbuf_count = inflate_stored_w; /* restore global gunzip_window pointer */ + gunzip_bb = inflate_stored_b; /* restore global bit buffer */ + gunzip_bk = inflate_stored_k; + return 0; /* Finished */ +} + + +/* + * decompress an inflated block + * e: last block flag + * + * GLOBAL VARIABLES: bb, kk, + */ +/* Return values: -1 = inflate_stored, -2 = inflate_codes */ +/* One callsite in inflate_get_next_window */ +static int inflate_block(STATE_PARAM smallint *e) +{ + unsigned ll[286 + 30]; /* literal/length and distance code lengths */ + unsigned t; /* block type */ + unsigned b; /* bit buffer */ + unsigned k; /* number of bits in bit buffer */ + + /* make local bit buffer */ + + b = gunzip_bb; + k = gunzip_bk; + + /* read in last block bit */ + b = fill_bitbuffer(PASS_STATE b, &k, 1); + *e = b & 1; + b >>= 1; + k -= 1; + + /* read in block type */ + b = fill_bitbuffer(PASS_STATE b, &k, 2); + t = (unsigned) b & 3; + b >>= 2; + k -= 2; + + /* restore the global bit buffer */ + gunzip_bb = b; + gunzip_bk = k; + + /* Do we see block type 1 often? Yes! + * TODO: fix performance problem (see below) */ + //bb_error_msg("blktype %d", t); + + /* inflate that block type */ + switch (t) { + case 0: /* Inflate stored */ + { + unsigned n; /* number of bytes in block */ + unsigned b_stored; /* bit buffer */ + unsigned k_stored; /* number of bits in bit buffer */ + + /* make local copies of globals */ + b_stored = gunzip_bb; /* initialize bit buffer */ + k_stored = gunzip_bk; + + /* go to byte boundary */ + n = k_stored & 7; + b_stored >>= n; + k_stored -= n; + + /* get the length and its complement */ + b_stored = fill_bitbuffer(PASS_STATE b_stored, &k_stored, 16); + n = ((unsigned) b_stored & 0xffff); + b_stored >>= 16; + k_stored -= 16; + + b_stored = fill_bitbuffer(PASS_STATE b_stored, &k_stored, 16); + if (n != (unsigned) ((~b_stored) & 0xffff)) { + abort_unzip(PASS_STATE_ONLY); /* error in compressed data */ + } + b_stored >>= 16; + k_stored -= 16; + + inflate_stored_setup(PASS_STATE n, b_stored, k_stored); + + return -1; + } + case 1: + /* Inflate fixed + * decompress an inflated type 1 (fixed Huffman codes) block. We should + * either replace this with a custom decoder, or at least precompute the + * Huffman tables. TODO */ + { + int i; /* temporary variable */ + unsigned bl; /* lookup bits for tl */ + unsigned bd; /* lookup bits for td */ + /* gcc 4.2.1 is too dumb to reuse stackspace. Moved up... */ + //unsigned ll[288]; /* length list for huft_build */ + + /* set up literal table */ + for (i = 0; i < 144; i++) + ll[i] = 8; + for (; i < 256; i++) + ll[i] = 9; + for (; i < 280; i++) + ll[i] = 7; + for (; i < 288; i++) /* make a complete, but wrong code set */ + ll[i] = 8; + bl = 7; + huft_build(ll, 288, 257, cplens, cplext, &inflate_codes_tl, &bl); + /* huft_build() never return nonzero - we use known data */ + + /* set up distance table */ + for (i = 0; i < 30; i++) /* make an incomplete code set */ + ll[i] = 5; + bd = 5; + huft_build(ll, 30, 0, cpdist, cpdext, &inflate_codes_td, &bd); + + /* set up data for inflate_codes() */ + inflate_codes_setup(PASS_STATE bl, bd); + + /* huft_free code moved into inflate_codes */ + + return -2; + } + case 2: /* Inflate dynamic */ + { + enum { dbits = 6 }; /* bits in base distance lookup table */ + enum { lbits = 9 }; /* bits in base literal/length lookup table */ + + huft_t *td; /* distance code table */ + unsigned i; /* temporary variables */ + unsigned j; + unsigned l; /* last length */ + unsigned m; /* mask for bit lengths table */ + unsigned n; /* number of lengths to get */ + unsigned bl; /* lookup bits for tl */ + unsigned bd; /* lookup bits for td */ + unsigned nb; /* number of bit length codes */ + unsigned nl; /* number of literal/length codes */ + unsigned nd; /* number of distance codes */ + + //unsigned ll[286 + 30];/* literal/length and distance code lengths */ + unsigned b_dynamic; /* bit buffer */ + unsigned k_dynamic; /* number of bits in bit buffer */ + + /* make local bit buffer */ + b_dynamic = gunzip_bb; + k_dynamic = gunzip_bk; + + /* read in table lengths */ + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 5); + nl = 257 + ((unsigned) b_dynamic & 0x1f); /* number of literal/length codes */ + + b_dynamic >>= 5; + k_dynamic -= 5; + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 5); + nd = 1 + ((unsigned) b_dynamic & 0x1f); /* number of distance codes */ + + b_dynamic >>= 5; + k_dynamic -= 5; + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 4); + nb = 4 + ((unsigned) b_dynamic & 0xf); /* number of bit length codes */ + + b_dynamic >>= 4; + k_dynamic -= 4; + if (nl > 286 || nd > 30) + abort_unzip(PASS_STATE_ONLY); /* bad lengths */ + + /* read in bit-length-code lengths */ + for (j = 0; j < nb; j++) { + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 3); + ll[border[j]] = (unsigned) b_dynamic & 7; + b_dynamic >>= 3; + k_dynamic -= 3; + } + for (; j < 19; j++) + ll[border[j]] = 0; + + /* build decoding table for trees - single level, 7 bit lookup */ + bl = 7; + i = huft_build(ll, 19, 19, NULL, NULL, &inflate_codes_tl, &bl); + if (i != 0) { + abort_unzip(PASS_STATE_ONLY); //return i; /* incomplete code set */ + } + + /* read in literal and distance code lengths */ + n = nl + nd; + m = mask_bits[bl]; + i = l = 0; + while ((unsigned) i < n) { + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, (unsigned)bl); + td = inflate_codes_tl + ((unsigned) b_dynamic & m); + j = td->b; + b_dynamic >>= j; + k_dynamic -= j; + j = td->v.n; + if (j < 16) { /* length of code in bits (0..15) */ + ll[i++] = l = j; /* save last length in l */ + } else if (j == 16) { /* repeat last length 3 to 6 times */ + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 2); + j = 3 + ((unsigned) b_dynamic & 3); + b_dynamic >>= 2; + k_dynamic -= 2; + if ((unsigned) i + j > n) { + abort_unzip(PASS_STATE_ONLY); //return 1; + } + while (j--) { + ll[i++] = l; + } + } else if (j == 17) { /* 3 to 10 zero length codes */ + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 3); + j = 3 + ((unsigned) b_dynamic & 7); + b_dynamic >>= 3; + k_dynamic -= 3; + if ((unsigned) i + j > n) { + abort_unzip(PASS_STATE_ONLY); //return 1; + } + while (j--) { + ll[i++] = 0; + } + l = 0; + } else { /* j == 18: 11 to 138 zero length codes */ + b_dynamic = fill_bitbuffer(PASS_STATE b_dynamic, &k_dynamic, 7); + j = 11 + ((unsigned) b_dynamic & 0x7f); + b_dynamic >>= 7; + k_dynamic -= 7; + if ((unsigned) i + j > n) { + abort_unzip(PASS_STATE_ONLY); //return 1; + } + while (j--) { + ll[i++] = 0; + } + l = 0; + } + } + + /* free decoding table for trees */ + huft_free(inflate_codes_tl); + + /* restore the global bit buffer */ + gunzip_bb = b_dynamic; + gunzip_bk = k_dynamic; + + /* build the decoding tables for literal/length and distance codes */ + bl = lbits; + + i = huft_build(ll, nl, 257, cplens, cplext, &inflate_codes_tl, &bl); + if (i != 0) + abort_unzip(PASS_STATE_ONLY); + bd = dbits; + i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &inflate_codes_td, &bd); + if (i != 0) + abort_unzip(PASS_STATE_ONLY); + + /* set up data for inflate_codes() */ + inflate_codes_setup(PASS_STATE bl, bd); + + /* huft_free code moved into inflate_codes */ + + return -2; + } + default: + abort_unzip(PASS_STATE_ONLY); + } +} + +/* Two callsites, both in inflate_get_next_window */ +static void calculate_gunzip_crc(STATE_PARAM_ONLY) +{ + gunzip_crc = crc32_block_endian0(gunzip_crc, gunzip_window, gunzip_outbuf_count, gunzip_crc_table); + gunzip_bytes_out += gunzip_outbuf_count; +} + +/* One callsite in inflate_unzip_internal */ +static int inflate_get_next_window(STATE_PARAM_ONLY) +{ + gunzip_outbuf_count = 0; + + while (1) { + int ret = 0; + + if (need_another_block) { + if (end_reached) { + calculate_gunzip_crc(PASS_STATE_ONLY); + end_reached = 0; + /* NB: need_another_block is still set */ + return 0; /* Last block */ + } + method = inflate_block(PASS_STATE &end_reached); + need_another_block = 0; + } + + switch (method) { + case -1: + ret = inflate_stored(PASS_STATE_ONLY); + break; + case -2: + ret = inflate_codes(PASS_STATE_ONLY); + break; + default: /* cannot happen */ + abort_unzip(PASS_STATE_ONLY); + } + + if (ret == 1) { + calculate_gunzip_crc(PASS_STATE_ONLY); + return 1; /* more data left */ + } + need_another_block = 1; /* end of that block */ + } + /* Doesnt get here */ +} + + +/* Called from unpack_gz_stream() and inflate_unzip() */ +static IF_DESKTOP(long long) int +inflate_unzip_internal(STATE_PARAM transformer_state_t *xstate) +{ + IF_DESKTOP(long long) int n = 0; + ssize_t nwrote; + + /* Allocate all global buffers (for DYN_ALLOC option) */ + gunzip_window = xmalloc(GUNZIP_WSIZE); + gunzip_outbuf_count = 0; + gunzip_bytes_out = 0; + gunzip_src_fd = xstate->src_fd; + + /* (re) initialize state */ + method = -1; + need_another_block = 1; + resume_copy = 0; + gunzip_bk = 0; + gunzip_bb = 0; + + /* Create the crc table */ + gunzip_crc_table = crc32_filltable(NULL, 0); + gunzip_crc = ~0; + + error_msg = "corrupted data"; + if (setjmp(error_jmp)) { + /* Error from deep inside zip machinery */ + n = -1; + goto ret; + } + + while (1) { + int r = inflate_get_next_window(PASS_STATE_ONLY); + nwrote = transformer_write(xstate, gunzip_window, gunzip_outbuf_count); + if (nwrote == (ssize_t)-1) { + n = -1; + goto ret; + } + IF_DESKTOP(n += nwrote;) + if (r == 0) break; + } + + /* Store unused bytes in a global buffer so calling applets can access it */ + if (gunzip_bk >= 8) { + /* Undo too much lookahead. The next read will be byte aligned + * so we can discard unused bits in the last meaningful byte. */ + bytebuffer_offset--; + bytebuffer[bytebuffer_offset] = gunzip_bb & 0xff; + gunzip_bb >>= 8; + gunzip_bk -= 8; + } + ret: + /* Cleanup */ + free(gunzip_window); + free(gunzip_crc_table); + return n; +} + + +/* External entry points */ + +/* For unzip */ + +IF_DESKTOP(long long) int FAST_FUNC +inflate_unzip(transformer_state_t *xstate) +{ + IF_DESKTOP(long long) int n; + DECLARE_STATE; + + ALLOC_STATE; + + to_read = xstate->bytes_in; +// bytebuffer_max = 0x8000; + bytebuffer_offset = 4; + bytebuffer = xmalloc(bytebuffer_max); + n = inflate_unzip_internal(PASS_STATE xstate); + free(bytebuffer); + + xstate->crc32 = gunzip_crc; + xstate->bytes_out = gunzip_bytes_out; + DEALLOC_STATE; + return n; +} + + +/* For gunzip */ + +/* helpers first */ + +/* Top up the input buffer with at least n bytes. */ +static int top_up(STATE_PARAM unsigned n) +{ + int count = bytebuffer_size - bytebuffer_offset; + + if (count < (int)n) { + memmove(bytebuffer, &bytebuffer[bytebuffer_offset], count); + bytebuffer_offset = 0; + bytebuffer_size = full_read(gunzip_src_fd, &bytebuffer[count], bytebuffer_max - count); + if ((int)bytebuffer_size < 0) { + bb_error_msg(bb_msg_read_error); + return 0; + } + bytebuffer_size += count; + if (bytebuffer_size < n) + return 0; + } + return 1; +} + +static uint16_t buffer_read_le_u16(STATE_PARAM_ONLY) +{ + uint16_t res; +#if BB_LITTLE_ENDIAN + move_from_unaligned16(res, &bytebuffer[bytebuffer_offset]); +#else + res = bytebuffer[bytebuffer_offset]; + res |= bytebuffer[bytebuffer_offset + 1] << 8; +#endif + bytebuffer_offset += 2; + return res; +} + +static uint32_t buffer_read_le_u32(STATE_PARAM_ONLY) +{ + uint32_t res; +#if BB_LITTLE_ENDIAN + move_from_unaligned32(res, &bytebuffer[bytebuffer_offset]); +#else + res = bytebuffer[bytebuffer_offset]; + res |= bytebuffer[bytebuffer_offset + 1] << 8; + res |= bytebuffer[bytebuffer_offset + 2] << 16; + res |= bytebuffer[bytebuffer_offset + 3] << 24; +#endif + bytebuffer_offset += 4; + return res; +} + +static int check_header_gzip(STATE_PARAM transformer_state_t *xstate) +{ + PRAGMA_BEGIN_PACKED + union { + unsigned char raw[8]; + struct { + uint8_t gz_method; + uint8_t flags; + uint32_t mtime; + uint8_t xtra_flags_UNUSED; + uint8_t os_flags_UNUSED; + } PACKED formatted; + } header; + PRAGMA_END_PACKED + struct BUG_header { + char BUG_header[sizeof(header) == 8 ? 1 : -1]; + }; + + /* + * Rewind bytebuffer. We use the beginning because the header has 8 + * bytes, leaving enough for unwinding afterwards. + */ + bytebuffer_size -= bytebuffer_offset; + memmove(bytebuffer, &bytebuffer[bytebuffer_offset], bytebuffer_size); + bytebuffer_offset = 0; + + if (!top_up(PASS_STATE 8)) + return 0; + memcpy(header.raw, &bytebuffer[bytebuffer_offset], 8); + bytebuffer_offset += 8; + + /* Check the compression method */ + if (header.formatted.gz_method != 8) { + return 0; + } + + if (header.formatted.flags & 0x04) { + /* bit 2 set: extra field present */ + unsigned extra_short; + + if (!top_up(PASS_STATE 2)) + return 0; + extra_short = buffer_read_le_u16(PASS_STATE_ONLY); + if (!top_up(PASS_STATE extra_short)) + return 0; + /* Ignore extra field */ + bytebuffer_offset += extra_short; + } + + /* Discard original name and file comment if any */ + /* bit 3 set: original file name present */ + /* bit 4 set: file comment present */ + if (header.formatted.flags & 0x18) { + while (1) { + do { + if (!top_up(PASS_STATE 1)) + return 0; + } while (bytebuffer[bytebuffer_offset++] != 0); + if ((header.formatted.flags & 0x18) != 0x18) + break; + header.formatted.flags &= ~0x18; + } + } + + xstate->mtime = SWAP_LE32(header.formatted.mtime); + + /* Read the header checksum */ + if (header.formatted.flags & 0x02) { + if (!top_up(PASS_STATE 2)) + return 0; + bytebuffer_offset += 2; + } + return 1; +} + +IF_DESKTOP(long long) int FAST_FUNC +unpack_gz_stream(transformer_state_t *xstate) +{ + uint32_t v32; + IF_DESKTOP(long long) int total, n; + DECLARE_STATE; + +#if !ENABLE_FEATURE_SEAMLESS_Z + if (check_signature16(xstate, GZIP_MAGIC)) + return -1; +#else + if (xstate->check_signature) { + uint16_t magic2; + + if (full_read(xstate->src_fd, &magic2, 2) != 2) { + bad_magic: + bb_error_msg("invalid magic"); + return -1; + } + if (magic2 == COMPRESS_MAGIC) { + xstate->check_signature = 0; + return unpack_Z_stream(xstate); + } + if (magic2 != GZIP_MAGIC) + goto bad_magic; + } +#endif + + total = 0; + + ALLOC_STATE; + to_read = -1; +// bytebuffer_max = 0x8000; + bytebuffer = xmalloc(bytebuffer_max); + gunzip_src_fd = xstate->src_fd; + + again: + if (!check_header_gzip(PASS_STATE xstate)) { + bb_error_msg("corrupted data"); + total = -1; + goto ret; + } + + n = inflate_unzip_internal(PASS_STATE xstate); + if (n < 0) { + total = -1; + goto ret; + } + total += n; + + if (!top_up(PASS_STATE 8)) { + bb_error_msg("corrupted data"); + total = -1; + goto ret; + } + + /* Validate decompression - crc */ + v32 = buffer_read_le_u32(PASS_STATE_ONLY); + if ((~gunzip_crc) != v32) { + bb_error_msg("crc error"); + total = -1; + goto ret; + } + + /* Validate decompression - size */ + v32 = buffer_read_le_u32(PASS_STATE_ONLY); + if ((uint32_t)gunzip_bytes_out != v32) { + bb_error_msg("incorrect length"); + total = -1; + } + + if (!top_up(PASS_STATE 2)) + goto ret; /* EOF */ + + if (bytebuffer[bytebuffer_offset] == 0x1f + && bytebuffer[bytebuffer_offset + 1] == 0x8b + ) { + bytebuffer_offset += 2; + goto again; + } + /* GNU gzip says: */ + /*bb_error_msg("decompression OK, trailing garbage ignored");*/ + + ret: + free(bytebuffer); + DEALLOC_STATE; + return total; +} diff --git a/src/bled/decompress_uncompress.c b/src/bled/decompress_uncompress.c new file mode 100644 index 00000000..5330f5d1 --- /dev/null +++ b/src/bled/decompress_uncompress.c @@ -0,0 +1,315 @@ +/* vi: set sw=4 ts=4: */ +/* uncompress for busybox -- (c) 2002 Robert Griebl + * + * based on the original compress42.c source + * (see disclaimer below) + */ + +/* (N)compress42.c - File compression ala IEEE Computer, Mar 1992. + * + * Authors: + * Spencer W. Thomas (decvax!harpo!utah-cs!utah-gr!thomas) + * Jim McKie (decvax!mcvax!jim) + * Steve Davies (decvax!vax135!petsd!peora!srd) + * Ken Turkowski (decvax!decwrl!turtlevax!ken) + * James A. Woods (decvax!ihnp4!ames!jaw) + * Joe Orost (decvax!vax135!petsd!joe) + * Dave Mack (csu@alembic.acs.com) + * Peter Jannesen, Network Communication Systems + * (peter@ncs.nl) + * + * marc@suse.de : a small security fix for a buffer overflow + * + * [... History snipped ...] + * + */ + +#include "libbb.h" +#include "bb_archive.h" + + +/* Default input buffer size */ +#define IBUFSIZ 2048 + +/* Default output buffer size */ +#define OBUFSIZ 2048 + +/* Defines for third byte of header */ +#define BIT_MASK 0x1f /* Mask for 'number of compresssion bits' */ + /* Masks 0x20 and 0x40 are free. */ + /* I think 0x20 should mean that there is */ + /* a fourth header byte (for expansion). */ +#define BLOCK_MODE 0x80 /* Block compression if table is full and */ + /* compression rate is dropping flush tables */ + /* the next two codes should not be changed lightly, as they must not */ + /* lie within the contiguous general code space. */ +#define FIRST 257 /* first free entry */ +#define CLEAR 256 /* table clear output code */ + +#define INIT_BITS 9 /* initial number of bits/code */ + + +/* machine variants which require cc -Dmachine: pdp11, z8000, DOS */ +#define HBITS 17 /* 50% occupancy */ +#define HSIZE (1<src_fd, inbuf, 1) != 1) { + bb_error_msg("short read"); + goto err; + } + + maxbits = inbuf[0] & BIT_MASK; + block_mode = inbuf[0] & BLOCK_MODE; + maxmaxcode = MAXCODE(maxbits); + + if (maxbits > BITS) { + bb_error_msg("compressed with %d bits, can only handle " + BITS_STR" bits", maxbits); + goto err; + } + + n_bits = INIT_BITS; + maxcode = MAXCODE(INIT_BITS) - 1; + bitmask = (1 << INIT_BITS) - 1; + oldcode = -1; + finchar = 0; + outpos = 0; + posbits = 0 << 3; + + free_ent = ((block_mode) ? FIRST : 256); + + /* As above, initialize the first 256 entries in the table. */ + /*clear_tab_prefixof(); - done by xzalloc */ + + { + int i; + for (i = 255; i >= 0; --i) + tab_suffixof(i) = (unsigned char) i; + } + + do { + resetbuf: + { + int i; + int e; + int o; + + o = posbits >> 3; + e = insize - o; + + for (i = 0; i < e; ++i) + inbuf[i] = inbuf[i + o]; + + insize = e; + posbits = 0; + } + + if (insize < (int) (IBUFSIZ + 64) - IBUFSIZ) { + rsize = safe_read(xstate->src_fd, inbuf + insize, IBUFSIZ); + if (rsize < 0) + bb_error_msg_and_err(bb_msg_read_error); + insize += rsize; + } + + inbits = ((rsize > 0) ? (insize - insize % n_bits) << 3 : + (insize << 3) - (n_bits - 1)); + + while (inbits > posbits) { + long code; + + if (free_ent > maxcode) { + posbits = + ((posbits - 1) + + ((n_bits << 3) - + (posbits - 1 + (n_bits << 3)) % (n_bits << 3))); + ++n_bits; + if (n_bits == maxbits) { + maxcode = maxmaxcode; + } else { + maxcode = MAXCODE(n_bits) - 1; + } + bitmask = (1 << n_bits) - 1; + goto resetbuf; + } + { + unsigned char *p = &inbuf[posbits >> 3]; + code = ((p[0] + | ((long) (p[1]) << 8) + | ((long) (p[2]) << 16)) >> (posbits & 0x7)) & bitmask; + } + posbits += n_bits; + + if (oldcode == -1) { + if (code >= 256) + bb_error_msg_and_err("corrupted data"); /* %ld", code); */ + oldcode = code; + finchar = (int) oldcode; + outbuf[outpos++] = (unsigned char) finchar; + continue; + } + + if (code == CLEAR && block_mode) { + clear_tab_prefixof(); + free_ent = FIRST - 1; + posbits = + ((posbits - 1) + + ((n_bits << 3) - + (posbits - 1 + (n_bits << 3)) % (n_bits << 3))); + n_bits = INIT_BITS; + maxcode = MAXCODE(INIT_BITS) - 1; + bitmask = (1 << INIT_BITS) - 1; + goto resetbuf; + } + + incode = code; + stackp = de_stack; + + /* Special case for KwKwK string. */ + if (code >= free_ent) { + if (code > free_ent) { +/* + unsigned char *p; + + posbits -= n_bits; + p = &inbuf[posbits >> 3]; + bb_error_msg + ("insize:%d posbits:%d inbuf:%02X %02X %02X %02X %02X (%d)", + insize, posbits, p[-1], p[0], p[1], p[2], p[3], + (posbits & 07)); +*/ + bb_error_msg("corrupted data"); + goto err; + } + + *--stackp = (unsigned char) finchar; + code = oldcode; + } + + /* Generate output characters in reverse order */ + while (code >= 256) { + if (stackp <= &htabof(0)) + bb_error_msg_and_err("corrupted data"); + *--stackp = tab_suffixof(code); + code = tab_prefixof(code); + } + + finchar = tab_suffixof(code); + *--stackp = (unsigned char) finchar; + + /* And put them out in forward order */ + { + int i; + + i = de_stack - stackp; + if (outpos + i >= OBUFSIZ) { + do { + if (i > OBUFSIZ - outpos) { + i = OBUFSIZ - outpos; + } + + if (i > 0) { + memcpy(outbuf + outpos, stackp, i); + outpos += i; + } + + if (outpos >= OBUFSIZ) { + xtransformer_write(xstate, outbuf, outpos); + IF_DESKTOP(total_written += outpos;) + outpos = 0; + } + stackp += i; + i = de_stack - stackp; + } while (i > 0); + } else { + memcpy(outbuf + outpos, stackp, i); + outpos += i; + } + } + + /* Generate the new entry. */ + if (free_ent < maxmaxcode) { + tab_prefixof(free_ent) = (unsigned short) oldcode; + tab_suffixof(free_ent) = (unsigned char) finchar; + free_ent++; + } + + /* Remember previous code. */ + oldcode = incode; + } + + } while (rsize > 0); + + if (outpos > 0) { + xtransformer_write(xstate, outbuf, outpos); + IF_DESKTOP(total_written += outpos;) + } + + retval = IF_DESKTOP(total_written) + 0; + err: + free(inbuf); + free(outbuf); + free(htab); + free(codetab); + return retval; +} diff --git a/src/bled/decompress_unlzma.c b/src/bled/decompress_unlzma.c new file mode 100644 index 00000000..d1c5fa5d --- /dev/null +++ b/src/bled/decompress_unlzma.c @@ -0,0 +1,468 @@ +/* vi: set sw=4 ts=4: */ +/* + * Small lzma deflate implementation. + * Copyright (C) 2006 Aurelien Jacobs + * + * Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/) + * Copyright (C) 1999-2005 Igor Pavlov + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ +#include "libbb.h" +#include "bb_archive.h" + +#if ENABLE_FEATURE_LZMA_FAST +# define speed_inline ALWAYS_INLINE +# define size_inline +#else +# define speed_inline +# define size_inline ALWAYS_INLINE +#endif + + +typedef struct { + int fd; + uint8_t *ptr; + +/* Was keeping rc on stack in unlzma and separately allocating buffer, + * but with "buffer 'attached to' allocated rc" code is smaller: */ + /* uint8_t *buffer; */ +#define RC_BUFFER ((uint8_t*)(rc+1)) + + uint8_t *buffer_end; + +/* Had provisions for variable buffer, but we don't need it here */ + /* int buffer_size; */ +#define RC_BUFFER_SIZE 0x10000 + + uint32_t code; + uint32_t range; + uint32_t bound; +} rc_t; + +#define RC_TOP_BITS 24 +#define RC_MOVE_BITS 5 +#define RC_MODEL_TOTAL_BITS 11 + + +/* Called once in rc_do_normalize() */ +static void rc_read(rc_t *rc) +{ + int buffer_size = safe_read(rc->fd, RC_BUFFER, RC_BUFFER_SIZE); +//TODO: return -1 instead +//This will make unlzma delete broken unpacked file on unpack errors + if (buffer_size <= 0) + bb_error_msg_and_die("unexpected EOF"); + rc->buffer_end = RC_BUFFER + buffer_size; + rc->ptr = RC_BUFFER; +} + +/* Called twice, but one callsite is in speed_inline'd rc_is_bit_1() */ +static void rc_do_normalize(rc_t *rc) +{ + if (rc->ptr >= rc->buffer_end) + rc_read(rc); + rc->range <<= 8; + rc->code = (rc->code << 8) | *rc->ptr++; +} +static ALWAYS_INLINE void rc_normalize(rc_t *rc) +{ + if (rc->range < (1 << RC_TOP_BITS)) { + rc_do_normalize(rc); + } +} + +/* Called once */ +static ALWAYS_INLINE rc_t* rc_init(int fd) /*, int buffer_size) */ +{ + int i; + rc_t *rc; + + rc = xzalloc(sizeof(*rc) + RC_BUFFER_SIZE); + + rc->fd = fd; + /* rc->ptr = rc->buffer_end; */ + + for (i = 0; i < 5; i++) { + rc_do_normalize(rc); + } + rc->range = 0xffffffff; + return rc; +} + +/* Called once */ +static ALWAYS_INLINE void rc_free(rc_t *rc) +{ + free(rc); +} + +/* rc_is_bit_1 is called 9 times */ +static speed_inline int rc_is_bit_1(rc_t *rc, uint16_t *p) +{ + rc_normalize(rc); + rc->bound = *p * (rc->range >> RC_MODEL_TOTAL_BITS); + if (rc->code < rc->bound) { + rc->range = rc->bound; + *p += ((1 << RC_MODEL_TOTAL_BITS) - *p) >> RC_MOVE_BITS; + return 0; + } + rc->range -= rc->bound; + rc->code -= rc->bound; + *p -= *p >> RC_MOVE_BITS; + return 1; +} + +/* Called 4 times in unlzma loop */ +static ALWAYS_INLINE int rc_get_bit(rc_t *rc, uint16_t *p, int *symbol) +{ + int ret = rc_is_bit_1(rc, p); + *symbol = *symbol * 2 + ret; + return ret; +} + +/* Called once */ +static ALWAYS_INLINE int rc_direct_bit(rc_t *rc) +{ + rc_normalize(rc); + rc->range >>= 1; + if (rc->code >= rc->range) { + rc->code -= rc->range; + return 1; + } + return 0; +} + +/* Called twice */ +static speed_inline void +rc_bit_tree_decode(rc_t *rc, uint16_t *p, int num_levels, int *symbol) +{ + int i = num_levels; + + *symbol = 1; + while (i--) + rc_get_bit(rc, p + *symbol, symbol); + *symbol -= 1 << num_levels; +} + +PRAGMA_BEGIN_PACKED +typedef struct { + uint8_t pos; + uint32_t dict_size; + uint64_t dst_size; +} PACKED lzma_header_t; +PRAGMA_END_PACKED + + +/* #defines will force compiler to compute/optimize each one with each usage. + * Have heart and use enum instead. */ +enum { + LZMA_BASE_SIZE = 1846, + LZMA_LIT_SIZE = 768, + + LZMA_NUM_POS_BITS_MAX = 4, + + LZMA_LEN_NUM_LOW_BITS = 3, + LZMA_LEN_NUM_MID_BITS = 3, + LZMA_LEN_NUM_HIGH_BITS = 8, + + LZMA_LEN_CHOICE = 0, + LZMA_LEN_CHOICE_2 = (LZMA_LEN_CHOICE + 1), + LZMA_LEN_LOW = (LZMA_LEN_CHOICE_2 + 1), + LZMA_LEN_MID = (LZMA_LEN_LOW \ + + (1 << (LZMA_NUM_POS_BITS_MAX + LZMA_LEN_NUM_LOW_BITS))), + LZMA_LEN_HIGH = (LZMA_LEN_MID \ + + (1 << (LZMA_NUM_POS_BITS_MAX + LZMA_LEN_NUM_MID_BITS))), + LZMA_NUM_LEN_PROBS = (LZMA_LEN_HIGH + (1 << LZMA_LEN_NUM_HIGH_BITS)), + + LZMA_NUM_STATES = 12, + LZMA_NUM_LIT_STATES = 7, + + LZMA_START_POS_MODEL_INDEX = 4, + LZMA_END_POS_MODEL_INDEX = 14, + LZMA_NUM_FULL_DISTANCES = (1 << (LZMA_END_POS_MODEL_INDEX >> 1)), + + LZMA_NUM_POS_SLOT_BITS = 6, + LZMA_NUM_LEN_TO_POS_STATES = 4, + + LZMA_NUM_ALIGN_BITS = 4, + + LZMA_MATCH_MIN_LEN = 2, + + LZMA_IS_MATCH = 0, + LZMA_IS_REP = (LZMA_IS_MATCH + (LZMA_NUM_STATES << LZMA_NUM_POS_BITS_MAX)), + LZMA_IS_REP_G0 = (LZMA_IS_REP + LZMA_NUM_STATES), + LZMA_IS_REP_G1 = (LZMA_IS_REP_G0 + LZMA_NUM_STATES), + LZMA_IS_REP_G2 = (LZMA_IS_REP_G1 + LZMA_NUM_STATES), + LZMA_IS_REP_0_LONG = (LZMA_IS_REP_G2 + LZMA_NUM_STATES), + LZMA_POS_SLOT = (LZMA_IS_REP_0_LONG \ + + (LZMA_NUM_STATES << LZMA_NUM_POS_BITS_MAX)), + LZMA_SPEC_POS = (LZMA_POS_SLOT \ + + (LZMA_NUM_LEN_TO_POS_STATES << LZMA_NUM_POS_SLOT_BITS)), + LZMA_ALIGN = (LZMA_SPEC_POS \ + + LZMA_NUM_FULL_DISTANCES - LZMA_END_POS_MODEL_INDEX), + LZMA_LEN_CODER = (LZMA_ALIGN + (1 << LZMA_NUM_ALIGN_BITS)), + LZMA_REP_LEN_CODER = (LZMA_LEN_CODER + LZMA_NUM_LEN_PROBS), + LZMA_LITERAL = (LZMA_REP_LEN_CODER + LZMA_NUM_LEN_PROBS), +}; + + +IF_DESKTOP(long long) int FAST_FUNC +unpack_lzma_stream(transformer_state_t *xstate) +{ + IF_DESKTOP(long long total_written = 0;) + lzma_header_t header; + int lc, pb, lp; + uint32_t pos_state_mask; + uint32_t literal_pos_mask; + uint16_t *p; + rc_t *rc; + int i; + uint8_t *buffer; + uint8_t previous_byte = 0; + size_t buffer_pos = 0, global_pos = 0; + int len = 0; + int state = 0; + uint32_t rep0 = 1, rep1 = 1, rep2 = 1, rep3 = 1; + + if (full_read(xstate->src_fd, &header, sizeof(header)) != sizeof(header) + || header.pos >= (9 * 5 * 5) + ) { + bb_error_msg("bad lzma header"); + return -1; + } + + i = header.pos / 9; + lc = header.pos % 9; + pb = i / 5; + lp = i % 5; + pos_state_mask = (1 << pb) - 1; + literal_pos_mask = (1 << lp) - 1; + + /* Example values from linux-3.3.4.tar.lzma: + * dict_size: 64M, dst_size: 2^64-1 + */ + header.dict_size = SWAP_LE32(header.dict_size); + header.dst_size = SWAP_LE64(header.dst_size); + + if (header.dict_size == 0) + header.dict_size++; + + buffer = xmalloc(MIN(header.dst_size, header.dict_size)); + + { + int num_probs; + + num_probs = LZMA_BASE_SIZE + (LZMA_LIT_SIZE << (lc + lp)); + p = xmalloc(num_probs * sizeof(*p)); + num_probs += LZMA_LITERAL - LZMA_BASE_SIZE; + for (i = 0; i < num_probs; i++) + p[i] = (1 << RC_MODEL_TOTAL_BITS) >> 1; + } + + rc = rc_init(xstate->src_fd); /*, RC_BUFFER_SIZE); */ + + while (global_pos + buffer_pos < header.dst_size) { + int pos_state = (buffer_pos + global_pos) & pos_state_mask; + uint16_t *prob = p + LZMA_IS_MATCH + (state << LZMA_NUM_POS_BITS_MAX) + pos_state; + + if (!rc_is_bit_1(rc, prob)) { + static const char next_state[LZMA_NUM_STATES] = + { 0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5 }; + int mi = 1; + + prob = (p + LZMA_LITERAL + + (LZMA_LIT_SIZE * ((((buffer_pos + global_pos) & literal_pos_mask) << lc) + + (previous_byte >> (8 - lc)) + ) + ) + ); + + if (state >= LZMA_NUM_LIT_STATES) { + int match_byte; + uint32_t pos = buffer_pos - rep0; + + while (pos >= header.dict_size) + pos += header.dict_size; + match_byte = buffer[pos]; + do { + int bit; + + match_byte <<= 1; + bit = match_byte & 0x100; + bit ^= (rc_get_bit(rc, prob + 0x100 + bit + mi, &mi) << 8); /* 0x100 or 0 */ + if (bit) + break; + } while (mi < 0x100); + } + while (mi < 0x100) { + rc_get_bit(rc, prob + mi, &mi); + } + + state = next_state[state]; + + previous_byte = (uint8_t) mi; +#if ENABLE_FEATURE_LZMA_FAST + one_byte1: + buffer[buffer_pos++] = previous_byte; + if (buffer_pos == header.dict_size) { + buffer_pos = 0; + global_pos += header.dict_size; + if (transformer_write(xstate, buffer, header.dict_size) != (ssize_t)header.dict_size) + goto bad; + IF_DESKTOP(total_written += header.dict_size;) + } +#else + len = 1; + goto one_byte2; +#endif + } else { + int num_bits; + int offset; + uint16_t *prob2; +#define prob_len prob2 + + prob2 = p + LZMA_IS_REP + state; + if (!rc_is_bit_1(rc, prob2)) { + rep3 = rep2; + rep2 = rep1; + rep1 = rep0; + state = state < LZMA_NUM_LIT_STATES ? 0 : 3; + prob2 = p + LZMA_LEN_CODER; + } else { + prob2 += LZMA_IS_REP_G0 - LZMA_IS_REP; + if (!rc_is_bit_1(rc, prob2)) { + prob2 = (p + LZMA_IS_REP_0_LONG + + (state << LZMA_NUM_POS_BITS_MAX) + + pos_state + ); + if (!rc_is_bit_1(rc, prob2)) { +#if ENABLE_FEATURE_LZMA_FAST + uint32_t pos = buffer_pos - rep0; + state = state < LZMA_NUM_LIT_STATES ? 9 : 11; + while (pos >= header.dict_size) + pos += header.dict_size; + previous_byte = buffer[pos]; + goto one_byte1; +#else + state = state < LZMA_NUM_LIT_STATES ? 9 : 11; + len = 1; + goto string; +#endif + } + } else { + uint32_t distance; + + prob2 += LZMA_IS_REP_G1 - LZMA_IS_REP_G0; + distance = rep1; + if (rc_is_bit_1(rc, prob2)) { + prob2 += LZMA_IS_REP_G2 - LZMA_IS_REP_G1; + distance = rep2; + if (rc_is_bit_1(rc, prob2)) { + distance = rep3; + rep3 = rep2; + } + rep2 = rep1; + } + rep1 = rep0; + rep0 = distance; + } + state = state < LZMA_NUM_LIT_STATES ? 8 : 11; + prob2 = p + LZMA_REP_LEN_CODER; + } + + prob_len = prob2 + LZMA_LEN_CHOICE; + num_bits = LZMA_LEN_NUM_LOW_BITS; + if (!rc_is_bit_1(rc, prob_len)) { + prob_len += LZMA_LEN_LOW - LZMA_LEN_CHOICE + + (pos_state << LZMA_LEN_NUM_LOW_BITS); + offset = 0; + } else { + prob_len += LZMA_LEN_CHOICE_2 - LZMA_LEN_CHOICE; + if (!rc_is_bit_1(rc, prob_len)) { + prob_len += LZMA_LEN_MID - LZMA_LEN_CHOICE_2 + + (pos_state << LZMA_LEN_NUM_MID_BITS); + offset = 1 << LZMA_LEN_NUM_LOW_BITS; + num_bits += LZMA_LEN_NUM_MID_BITS - LZMA_LEN_NUM_LOW_BITS; + } else { + prob_len += LZMA_LEN_HIGH - LZMA_LEN_CHOICE_2; + offset = ((1 << LZMA_LEN_NUM_LOW_BITS) + + (1 << LZMA_LEN_NUM_MID_BITS)); + num_bits += LZMA_LEN_NUM_HIGH_BITS - LZMA_LEN_NUM_LOW_BITS; + } + } + rc_bit_tree_decode(rc, prob_len, num_bits, &len); + len += offset; + + if (state < 4) { + int pos_slot; + uint16_t *prob3; + + state += LZMA_NUM_LIT_STATES; + prob3 = p + LZMA_POS_SLOT + + ((len < LZMA_NUM_LEN_TO_POS_STATES ? len : + LZMA_NUM_LEN_TO_POS_STATES - 1) + << LZMA_NUM_POS_SLOT_BITS); + rc_bit_tree_decode(rc, prob3, + LZMA_NUM_POS_SLOT_BITS, &pos_slot); + rep0 = pos_slot; + if (pos_slot >= LZMA_START_POS_MODEL_INDEX) { + int i2, mi2, num_bits2 = (pos_slot >> 1) - 1; + rep0 = 2 | (pos_slot & 1); + if (pos_slot < LZMA_END_POS_MODEL_INDEX) { + rep0 <<= num_bits2; + prob3 = p + LZMA_SPEC_POS + rep0 - pos_slot - 1; + } else { + for (; num_bits2 != LZMA_NUM_ALIGN_BITS; num_bits2--) + rep0 = (rep0 << 1) | rc_direct_bit(rc); + rep0 <<= LZMA_NUM_ALIGN_BITS; + prob3 = p + LZMA_ALIGN; + } + i2 = 1; + mi2 = 1; + while (num_bits2--) { + if (rc_get_bit(rc, prob3 + mi2, &mi2)) + rep0 |= i2; + i2 <<= 1; + } + } + if (++rep0 == 0) + break; + } + + len += LZMA_MATCH_MIN_LEN; + IF_NOT_FEATURE_LZMA_FAST(string:) + do { + uint32_t pos = buffer_pos - rep0; + while (pos >= header.dict_size) + pos += header.dict_size; + previous_byte = buffer[pos]; + IF_NOT_FEATURE_LZMA_FAST(one_byte2:) + buffer[buffer_pos++] = previous_byte; + if (buffer_pos == header.dict_size) { + buffer_pos = 0; + global_pos += header.dict_size; + if (transformer_write(xstate, buffer, header.dict_size) != (ssize_t)header.dict_size) + goto bad; + IF_DESKTOP(total_written += header.dict_size;) + } + len--; + } while (len != 0 && buffer_pos < header.dst_size); + /* FIXME: ...........^^^^^ + * shouldn't it be "global_pos + buffer_pos < header.dst_size"? + */ + } + } + + { + IF_NOT_DESKTOP(int total_written = 0; /* success */) + IF_DESKTOP(total_written += buffer_pos;) + if (transformer_write(xstate, buffer, buffer_pos) != (ssize_t)buffer_pos) { + bad: + total_written = -1; /* failure */ + } + rc_free(rc); + free(p); + free(buffer); + return total_written; + } +} diff --git a/src/bled/decompress_unxz.c b/src/bled/decompress_unxz.c new file mode 100644 index 00000000..54d68889 --- /dev/null +++ b/src/bled/decompress_unxz.c @@ -0,0 +1,131 @@ +/* + * unxz implementation for busybox + * + * Based on xz-embedded (C) Lasse Collin - Public Domain + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +#define XZ_EXTERN static +// We get XZ_OPTIONS_ERROR in xz_dec_stream if this is not defined +#define XZ_DEC_ANY_CHECK + +#include "xz_dec_bcj.c" +#include "xz_dec_lzma2.c" +#include "xz_dec_stream.c" + +static void XZ_FUNC xz_crc32_init(void) +{ + if (!global_crc32_table) + global_crc32_table = crc32_filltable(NULL, 0); +} + +static uint32_t XZ_FUNC xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) +{ + // The XZ CRC32 is INVERTED! + return ~crc32_block_endian0(~crc, buf, size, global_crc32_table); +} + +IF_DESKTOP(long long) int FAST_FUNC unpack_xz_stream(transformer_state_t *xstate) +{ + IF_DESKTOP(long long) int n = 0; + struct xz_buf b; + struct xz_dec *s; + enum xz_ret ret = XZ_STREAM_END; + uint8_t *in = NULL, *out = NULL; + ssize_t nwrote; + + xz_crc32_init(); + + /* + * Support up to 64 MiB dictionary. The actually needed memory + * is allocated once the headers have been parsed. + */ + s = xz_dec_init(XZ_DYNALLOC, 1 << 26); + if (!s) + bb_error_msg_and_err("memory allocation failed"); + + // TODO: this is set very low on Windows... + in = xmalloc(BUFSIZ); + out = xmalloc(BUFSIZ); + + b.in = in; + b.in_pos = 0; + b.in_size = 0; + b.out = out; + b.out_pos = 0; + b.out_size = BUFSIZ; + + while (true) { + if (b.in_pos == b.in_size) { + b.in_size = safe_read(xstate->src_fd, in, BUFSIZ); + if ((int)b.in_size < 0) + bb_error_msg_and_err(bb_msg_read_error); + b.in_pos = 0; + } + ret = xz_dec_run(s, &b); + + if (b.out_pos == BUFSIZ) { + nwrote = transformer_write(xstate, b.out, b.out_pos); + if (nwrote == (ssize_t)-1) { + ret = XZ_DATA_ERROR; + bb_error_msg_and_err("write error"); + } + IF_DESKTOP(n += nwrote;) + b.out_pos = 0; + } + + if (ret == XZ_OK) + continue; + +#ifdef XZ_DEC_ANY_CHECK + if (ret == XZ_UNSUPPORTED_CHECK) { + bb_error_msg("unsupported check; not verifying file integrity"); + continue; + } +#endif + + nwrote = transformer_write(xstate, b.out, b.out_pos); + if (nwrote == (ssize_t)-1) { + ret = XZ_DATA_ERROR; + bb_error_msg_and_err("write error"); + } + IF_DESKTOP(n += nwrote;) + + switch (ret) { + case XZ_STREAM_END: + ret = XZ_OK; + goto out; + + case XZ_MEM_ERROR: + bb_error_msg_and_err("memory allocation failed"); + + case XZ_MEMLIMIT_ERROR: + bb_error_msg_and_err("memory usage limit reached"); + + case XZ_FORMAT_ERROR: + bb_error_msg_and_err("not a .xz file"); + + case XZ_OPTIONS_ERROR: + bb_error_msg_and_err("unsupported options in the .xz headers"); + + case XZ_DATA_ERROR: + bb_error_msg_and_err("file is corrupt"); + case XZ_BUF_ERROR: + bb_error_msg_and_err("buf is corrupt"); + + default: + bb_error_msg_and_err("bug!"); + } + } + +out: +err: + xz_dec_end(s); + free(in); + free(out); + return (ret == XZ_OK)?n:-ret; +} diff --git a/src/bled/filter_accept_all.c b/src/bled/filter_accept_all.c new file mode 100644 index 00000000..c33f7d3e --- /dev/null +++ b/src/bled/filter_accept_all.c @@ -0,0 +1,17 @@ +/* vi: set sw=4 ts=4: */ +/* + * Copyright (C) 2002 by Glenn McGrath + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +/* Accept any non-null name, its not really a filter at all */ +char FAST_FUNC filter_accept_all(archive_handle_t *archive_handle) +{ + if (archive_handle->file_header->name) + return EXIT_SUCCESS; + return EXIT_FAILURE; +} diff --git a/src/bled/filter_accept_list.c b/src/bled/filter_accept_list.c new file mode 100644 index 00000000..a2d4b23e --- /dev/null +++ b/src/bled/filter_accept_list.c @@ -0,0 +1,19 @@ +/* vi: set sw=4 ts=4: */ +/* + * Copyright (C) 2002 by Glenn McGrath + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +/* + * Accept names that are in the accept list, ignoring reject list. + */ +char FAST_FUNC filter_accept_list(archive_handle_t *archive_handle) +{ + if (find_list_entry(archive_handle->accept, archive_handle->file_header->name)) + return EXIT_SUCCESS; + return EXIT_FAILURE; +} diff --git a/src/bled/filter_accept_reject_list.c b/src/bled/filter_accept_reject_list.c new file mode 100644 index 00000000..24837494 --- /dev/null +++ b/src/bled/filter_accept_reject_list.c @@ -0,0 +1,38 @@ +/* vi: set sw=4 ts=4: */ +/* + * Copyright (C) 2002 by Glenn McGrath + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +/* + * Accept names that are in the accept list and not in the reject list + */ +char FAST_FUNC filter_accept_reject_list(archive_handle_t *archive_handle) +{ + const char *key; + const llist_t *reject_entry; + const llist_t *accept_entry; + + key = archive_handle->file_header->name; + + /* If the key is in a reject list fail */ + reject_entry = find_list_entry2(archive_handle->reject, key); + if (reject_entry) { + return EXIT_FAILURE; + } + + /* Fail if an accept list was specified and the key wasnt in there */ + if (archive_handle->accept) { + accept_entry = find_list_entry2(archive_handle->accept, key); + if (!accept_entry) { + return EXIT_FAILURE; + } + } + + /* Accepted */ + return EXIT_SUCCESS; +} diff --git a/src/bled/find_list_entry.c b/src/bled/find_list_entry.c new file mode 100644 index 00000000..21034dbf --- /dev/null +++ b/src/bled/find_list_entry.c @@ -0,0 +1,54 @@ +/* vi: set sw=4 ts=4: */ +/* + * Copyright (C) 2002 by Glenn McGrath + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +//#include +#include "libbb.h" +#include "bb_archive.h" + +/* Find a string in a shell pattern list */ +const llist_t* FAST_FUNC find_list_entry(const llist_t *list, const char *filename) +{ + while (list) { + if (fnmatch(list->data, filename, 0) == 0) { + return list; + } + list = list->link; + } + return NULL; +} + +/* Same, but compares only path components present in pattern + * (extra trailing path components in filename are assumed to match) + */ +const llist_t* FAST_FUNC find_list_entry2(const llist_t *list, const char *filename) +{ + char buf[PATH_MAX]; + int pattern_slash_cnt; + const char *c; + char *d; + + while (list) { + c = list->data; + pattern_slash_cnt = 0; + while (*c) + if (*c++ == '/') pattern_slash_cnt++; + c = filename; + d = buf; + /* paranoia is better than buffer overflows */ + while (*c && d != buf + sizeof(buf)-1) { + if (*c == '/' && --pattern_slash_cnt < 0) + break; + *d++ = *c++; + } + *d = '\0'; + if (fnmatch(list->data, buf, 0) == 0) { + return list; + } + list = list->link; + } + return NULL; +} diff --git a/src/bled/header_list.c b/src/bled/header_list.c new file mode 100644 index 00000000..0621aa40 --- /dev/null +++ b/src/bled/header_list.c @@ -0,0 +1,12 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC header_list(const file_header_t *file_header) +{ +//TODO: cpio -vp DIR should output "DIR/NAME", not just "NAME" */ + puts(file_header->name); +} diff --git a/src/bled/header_skip.c b/src/bled/header_skip.c new file mode 100644 index 00000000..f5987bfe --- /dev/null +++ b/src/bled/header_skip.c @@ -0,0 +1,10 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC header_skip(const file_header_t *file_header UNUSED_PARAM) +{ +} diff --git a/src/bled/header_verbose_list.c b/src/bled/header_verbose_list.c new file mode 100644 index 00000000..87dd8213 --- /dev/null +++ b/src/bled/header_verbose_list.c @@ -0,0 +1,69 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC header_verbose_list(const file_header_t *file_header) +{ + struct tm tm_time; + struct tm *ptm = &tm_time; //localtime(&file_header->mtime); + +#if ENABLE_FEATURE_TAR_UNAME_GNAME + char uid[sizeof(int)*3 + 2]; + /*char gid[sizeof(int)*3 + 2];*/ + char *user; + char *group; + + localtime_r(&file_header->mtime, ptm); + + user = file_header->tar__uname; + if (user == NULL) { + sprintf(uid, "%u", (unsigned)file_header->uid); + user = uid; + } + group = file_header->tar__gname; + if (group == NULL) { + /*sprintf(gid, "%u", (unsigned)file_header->gid);*/ + group = utoa(file_header->gid); + } + printf("%s %s/%s %9"OFF_FMT"u %4u-%02u-%02u %02u:%02u:%02u %s", + bb_mode_string(file_header->mode), + user, + group, + file_header->size, + 1900 + ptm->tm_year, + 1 + ptm->tm_mon, + ptm->tm_mday, + ptm->tm_hour, + ptm->tm_min, + ptm->tm_sec, + file_header->name); + +#else /* !FEATURE_TAR_UNAME_GNAME */ + + localtime_r(&file_header->mtime, ptm); + + printf("%s %u/%u %9"OFF_FMT"u %4u-%02u-%02u %02u:%02u:%02u %s", + bb_mode_string(file_header->mode), + (unsigned)file_header->uid, + (unsigned)file_header->gid, + file_header->size, + 1900 + ptm->tm_year, + 1 + ptm->tm_mon, + ptm->tm_mday, + ptm->tm_hour, + ptm->tm_min, + ptm->tm_sec, + file_header->name); + +#endif /* FEATURE_TAR_UNAME_GNAME */ + + /* NB: GNU tar shows "->" for symlinks and "link to" for hardlinks */ + if (file_header->link_target) { + printf(" -> %s", file_header->link_target); + } + bb_putchar('\n'); +} diff --git a/src/bled/init_handle.c b/src/bled/init_handle.c new file mode 100644 index 00000000..cbae06ac --- /dev/null +++ b/src/bled/init_handle.c @@ -0,0 +1,22 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +archive_handle_t* FAST_FUNC init_handle(void) +{ + archive_handle_t *archive_handle; + + /* Initialize default values */ + archive_handle = xzalloc(sizeof(archive_handle_t)); + archive_handle->file_header = xzalloc(sizeof(file_header_t)); + archive_handle->action_header = header_skip; + archive_handle->action_data = data_skip; + archive_handle->filter = filter_accept_all; + archive_handle->seek = seek_by_jump; + + return archive_handle; +} diff --git a/src/bled/libbb.h b/src/bled/libbb.h new file mode 100644 index 00000000..8f73266b --- /dev/null +++ b/src/bled/libbb.h @@ -0,0 +1,233 @@ +/* + * Library header for busybox + * + * Rewritten for Bled (Busybox Library for Easy Decompression) + * Copyright © 2014 Pete Batard + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +/* Memory leaks detection - define _CRTDBG_MAP_ALLOC as preprocessor macro */ +#ifdef _CRTDBG_MAP_ALLOC +#include +#include +#endif + +#ifndef LIBBB_H +#define LIBBB_H 1 + +#ifndef _WIN32 +#error Only Windows platforms are supported +#endif + +#if defined(_MSC_VER) +#pragma warning(disable: 4715) // not all control paths return a value +#pragma warning(disable: 4996) // Ignore deprecated +#if defined(DDKBUILD) +#pragma warning(disable: 4242) // "Conversion from x to y, possible loss of data" +#pragma warning(disable: 4244) +struct timeval { + long tv_sec; + long tv_usec; +}; +#endif +#endif + +#include "platform.h" +#include "msapi_utf8.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef BUFSIZ +#undef BUFSIZ +#endif +#define BUFSIZ 65536 + +#define IF_DESKTOP(x) x +#define IF_NOT_DESKTOP(x) +#define IF_NOT_FEATURE_LZMA_FAST(x) x + +#define uoff_t unsigned off_t +#define OFF_FMT "I64" + +#ifndef _MODE_T_ +#define _MODE_T_ +typedef unsigned short mode_t; +#endif + +#ifndef _PID_T_ +#define _PID_T_ +typedef int pid_t; +#endif + +#ifndef _GID_T_ +#define _GID_T_ +typedef unsigned int gid_t; +#endif + +#ifndef _UID_T_ +#define _UID_T_ +typedef unsigned int uid_t; +#endif + +#ifndef MIN +#define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif + +#ifndef MAX +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) +#endif + +#ifndef PATH_MAX +#define PATH_MAX MAX_PATH +#endif + +#ifndef get_le64 +#define get_le64(ptr) (*(const uint64_t *)(ptr)) +#endif + +#ifndef get_le32 +#define get_le32(ptr) (*(const uint32_t *)(ptr)) +#endif + +#ifndef get_le16 +#define get_le16(ptr) (*(const uint16_t *)(ptr)) +#endif + +extern smallint bb_got_signal; +extern uint32_t *global_crc32_table; + +uint32_t* crc32_filltable(uint32_t *crc_table, int endian); +uint32_t crc32_le(uint32_t crc, unsigned char const *p, size_t len, uint32_t *crc32table_le); +uint32_t crc32_be(uint32_t crc, unsigned char const *p, size_t len, uint32_t *crc32table_be); +#define crc32_block_endian0 crc32_le +#define crc32_block_endian1 crc32_be + +#if defined(_MSC_VER) +#if _FILE_OFFSET_BITS == 64 +#define stat _stat32i64 +#define lseek _lseeki64 +#else +#define stat _stat32 +#define lseek _lseek +#endif +#endif + +typedef struct _llist_t { + struct _llist_t *link; + char *data; +} llist_t; + +extern void (*bled_printf) (const char* format, ...); +extern void (*bled_progress) (const uint64_t processed_bytes); + +#define bb_printf(...) do { if (bled_printf != NULL) bled_printf(__VA_ARGS__); \ + else { printf(__VA_ARGS__); putchar('\n'); } } while(0) +#define bb_error_msg bb_printf +#define bb_error_msg_and_die(...) do {bb_printf(__VA_ARGS__); return;} while(0) +#define bb_error_msg_and_err(...) do {bb_printf(__VA_ARGS__); goto err;} while(0) +#define bb_perror_msg bb_error_msg +#define bb_perror_msg_and_die bb_error_msg_and_die +#define bb_putchar putchar + +static inline void *xrealloc(void *ptr, size_t size) { + void *ret = realloc(ptr, size); + if (!ret) + free(ptr); + return ret; +} + +#define bb_msg_read_error "read error" +#define bb_msg_write_error "write error" +#define bb_mode_string(mode) "[not implemented]" +#define bb_copyfd_exact_size(fd1, fd2, size) bb_printf("not implemented") +#define bb_make_directory(path, mode, flags) SHCreateDirectoryExU(NULL, path, NULL) + +static inline int link(const char *oldpath, const char *newpath) {errno = ENOSYS; return -1;} +static inline int symlink(const char *oldpath, const char *newpath) {errno = ENOSYS; return -1;} +static inline int chown(const char *path, uid_t owner, gid_t group) {errno = ENOSYS; return -1;} +static inline int mknod(const char *pathname, mode_t mode, dev_t dev) {errno = ENOSYS; return -1;} +static inline int utimes(const char *filename, const struct timeval times[2]) {errno = ENOSYS; return -1;} +static inline int fnmatch(const char *pattern, const char *string, int flags) {return PathMatchSpecA(string, pattern)?0:1;} +static inline pid_t wait(int* status) { *status = 4; return -1; } +#define wait_any_nohang wait + +/* This override enables the display of a progress based on the number of bytes read */ +extern uint64_t bb_total_rb; +static inline ssize_t full_read(int fd, void *buf, size_t count) { + ssize_t rb = _read(fd, buf, count); + if (rb > 0) { + bb_total_rb += rb; + if (bled_progress != NULL) + bled_progress(bb_total_rb); + } + return rb; +} + +#define full_write _write +#define safe_read full_read +#define lstat stat +#define xmalloc malloc +#define xzalloc(x) calloc(x, 1) +#define malloc_or_warn malloc +#define xopen3 open +#define xfunc_die() do { bb_printf("not implemented"); return -1; } while(0) +#define mkdir(x, y) _mkdirU(x) + +#if defined(_MSC_VER) +static inline struct tm *localtime_r(const time_t *timep, struct tm *result) { + result = localtime(timep); + return result; +} + +#define _S_IFBLK 0x3000 + +#define S_IFMT _S_IFMT +#define S_IFDIR _S_IFDIR +#define S_IFCHR _S_IFCHR +#define S_IFIFO _S_IFIFO +#define S_IFREG _S_IFREG +#define S_IREAD _S_IREAD +#define S_IWRITE _S_IWRITE +#define S_IEXEC _S_IEXEC +#define S_IFBLK _S_IFBLK + +#define S_ISDIR(m) (((m) & _S_IFMT) == _S_IFDIR) +#define S_ISFIFO(m) (((m) & _S_IFMT) == _S_IFIFO) +#define S_ISCHR(m) (((m) & _S_IFMT) == _S_IFCHR) +#define S_ISBLK(m) (((m) & _S_IFMT) == _S_IFBLK) +#define S_ISREG(m) (((m) & _S_IFMT) == _S_IFREG) + +#define O_RDONLY _O_RDONLY +#define O_WRONLY _O_WRONLY +#define O_RDWR _O_RDWR +#define O_APPEND _O_APPEND + +#define O_CREAT _O_CREAT +#define O_TRUNC _O_TRUNC +#define O_EXCL _O_EXCL +#endif + +/* MinGW doesn't know these */ +#define _S_IFLNK 0xA000 +#define _S_IFSOCK 0xC000 +#define S_IFLNK _S_IFLNK +#define S_IFSOCK _S_IFSOCK +#define S_ISLNK(m) (((m) & _S_IFMT) == _S_IFLNK) +#define S_ISSOCK(m) (((m) & _S_IFMT) == _S_IFSOCK) + +#endif diff --git a/src/bled/open_transformer.c b/src/bled/open_transformer.c new file mode 100644 index 00000000..deea54b5 --- /dev/null +++ b/src/bled/open_transformer.c @@ -0,0 +1,351 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC init_transformer_state(transformer_state_t *xstate) +{ + memset(xstate, 0, sizeof(*xstate)); +} + +int FAST_FUNC check_signature16(transformer_state_t *xstate, unsigned magic16) +{ + if (xstate->check_signature) { + uint16_t magic2; + if (full_read(xstate->src_fd, &magic2, 2) != 2 || magic2 != magic16) { + bb_error_msg("invalid magic"); +#if 0 /* possible future extension */ + if (xstate->check_signature > 1) + xfunc_die(); +#endif + return -1; + } + } + return 0; +} + +ssize_t FAST_FUNC transformer_write(transformer_state_t *xstate, const void *buf, size_t bufsize) +{ + ssize_t nwrote; + + if (xstate->mem_output_size_max != 0) { + size_t pos = xstate->mem_output_size; + size_t size; + + size = (xstate->mem_output_size += bufsize); + if (size > xstate->mem_output_size_max) { + free(xstate->mem_output_buf); + xstate->mem_output_buf = NULL; + bb_perror_msg("buffer %u too small", (unsigned)xstate->mem_output_size_max); + nwrote = -1; + goto ret; + } + xstate->mem_output_buf = xrealloc(xstate->mem_output_buf, size + 1); + memcpy(xstate->mem_output_buf + pos, buf, bufsize); + xstate->mem_output_buf[size] = '\0'; + nwrote = bufsize; + } else { + nwrote = full_write(xstate->dst_fd, buf, bufsize); + if (nwrote != (ssize_t)bufsize) { + bb_perror_msg("write"); + nwrote = -1; + goto ret; + } + } + ret: + return nwrote; +} + +ssize_t FAST_FUNC xtransformer_write(transformer_state_t *xstate, const void *buf, size_t bufsize) +{ + ssize_t nwrote = transformer_write(xstate, buf, bufsize); + if (nwrote != (ssize_t)bufsize) { + xfunc_die(); + } + return nwrote; +} + +void check_errors_in_children(int signo) +{ + int status; + + if (!signo) { + /* block waiting for any child */ + if (wait(&status) < 0) +//FIXME: check EINTR? + return; /* probably there are no children */ + goto check_status; + } + + /* Wait for any child without blocking */ + for (;;) { + if (wait_any_nohang(&status) < 0) +//FIXME: check EINTR? + /* wait failed?! I'm confused... */ + return; + check_status: + /*if (WIFEXITED(status) && WEXITSTATUS(status) == 0)*/ + /* On Linux, the above can be checked simply as: */ + if (status == 0) + /* this child exited with 0 */ + continue; + /* Cannot happen: + if (!WIFSIGNALED(status) && !WIFEXITED(status)) ???; + */ + bb_got_signal = 1; + } +} + +#if SEAMLESS_COMPRESSION + +/* transformer(), more than meets the eye */ +#if BB_MMU +void FAST_FUNC fork_transformer(int fd, + int check_signature, + IF_DESKTOP(long long) int FAST_FUNC (*transformer)(transformer_state_t *xstate) +) +#else +void FAST_FUNC fork_transformer(int fd, const char *transform_prog) +#endif +{ + struct fd_pair fd_pipe; + int pid; + + xpiped_pair(fd_pipe); + pid = BB_MMU ? xfork() : xvfork(); + if (pid == 0) { + /* Child */ + close(fd_pipe.rd); /* we don't want to read from the parent */ + // FIXME: error check? +#if BB_MMU + { + IF_DESKTOP(long long) int r; + transformer_state_t xstate; + init_transformer_state(&xstate); + xstate.check_signature = check_signature; + xstate.src_fd = fd; + xstate.dst_fd = fd_pipe.wr; + r = transformer(&xstate); + if (ENABLE_FEATURE_CLEAN_UP) { + close(fd_pipe.wr); /* send EOF */ + close(fd); + } + /* must be _exit! bug was actually seen here */ + _exit(/*error if:*/ r < 0); + } +#else + { + char *argv[4]; + xmove_fd(fd, 0); + xmove_fd(fd_pipe.wr, 1); + argv[0] = (char*)transform_prog; + argv[1] = (char*)"-cf"; + argv[2] = (char*)"-"; + argv[3] = NULL; + BB_EXECVP(transform_prog, argv); + bb_perror_msg_and_die("can't execute '%s'", transform_prog); + } +#endif + /* notreached */ + } + + /* parent process */ + close(fd_pipe.wr); /* don't want to write to the child */ + xmove_fd(fd_pipe.rd, fd); +} + +/* Used by e.g. rpm which gives us a fd without filename, + * thus we can't guess the format from filename's extension. + */ +static transformer_state_t *setup_transformer_on_fd(int fd, int fail_if_not_compressed) +{ + union { + uint8_t b[4]; + uint16_t b16[2]; + uint32_t b32[1]; + } magic; + int offset; + transformer_state_t *xstate; + + offset = -2; + xstate = xzalloc(sizeof(*xstate)); + xstate->src_fd = fd; + + /* .gz and .bz2 both have 2-byte signature, and their + * unpack_XXX_stream wants this header skipped. */ + xread(fd, magic.b16, sizeof(magic.b16[0])); + if (ENABLE_FEATURE_SEAMLESS_GZ + && magic.b16[0] == GZIP_MAGIC + ) { + xstate->xformer = unpack_gz_stream; + USE_FOR_NOMMU(xstate->xformer_prog = "gunzip";) + goto found_magic; + } + if (ENABLE_FEATURE_SEAMLESS_BZ2 + && magic.b16[0] == BZIP2_MAGIC + ) { + xstate->xformer = unpack_bz2_stream; + USE_FOR_NOMMU(xstate->xformer_prog = "bunzip2";) + goto found_magic; + } + if (ENABLE_FEATURE_SEAMLESS_XZ + && magic.b16[0] == XZ_MAGIC1 + ) { + offset = -6; + xread(fd, magic.b32, sizeof(magic.b32[0])); + if (magic.b32[0] == XZ_MAGIC2) { + xstate->xformer = unpack_xz_stream; + USE_FOR_NOMMU(xstate->xformer_prog = "unxz";) + goto found_magic; + } + } + + /* No known magic seen */ + if (fail_if_not_compressed) + bb_error_msg_and_die("no gzip" + IF_FEATURE_SEAMLESS_BZ2("/bzip2") + IF_FEATURE_SEAMLESS_XZ("/xz") + " magic"); + + /* Some callers expect this function to "consume" fd + * even if data is not compressed. In this case, + * we return a state with trivial transformer. + */ +// USE_FOR_MMU(xstate->xformer = copy_stream;) +// USE_FOR_NOMMU(xstate->xformer_prog = "cat";) + /* fall through to seeking bck over bytes we read earlier */ + + USE_FOR_NOMMU(found_magic:) + /* NOMMU version of fork_transformer execs + * an external unzipper that wants + * file position at the start of the file. + */ + xlseek(fd, offset, SEEK_CUR); + + USE_FOR_MMU(found_magic:) + /* In MMU case, if magic was found, seeking back is not necessary */ + + return xstate; +} + +/* Used by e.g. rpm which gives us a fd without filename, + * thus we can't guess the format from filename's extension. + */ +int FAST_FUNC setup_unzip_on_fd(int fd, int fail_if_not_compressed) +{ + transformer_state_t *xstate = setup_transformer_on_fd(fd, fail_if_not_compressed); + + if (!xstate || !xstate->xformer) { + free(xstate); + return 1; + } + +# if BB_MMU + fork_transformer_with_no_sig(xstate->src_fd, xstate->xformer); +# else + fork_transformer_with_sig(xstate->src_fd, xstate->xformer, xstate->xformer_prog); +# endif + free(xstate); + return 0; +} + +static transformer_state_t *open_transformer(const char *fname, int fail_if_not_compressed) +{ + transformer_state_t *xstate; + int fd; + + fd = open(fname, O_RDONLY); + if (fd < 0) + return NULL; + + if (ENABLE_FEATURE_SEAMLESS_LZMA) { + /* .lzma has no header/signature, can only detect it by extension */ + char *sfx = strrchr(fname, '.'); + if (sfx && strcmp(sfx+1, "lzma") == 0) { + xstate = xzalloc(sizeof(*xstate)); + xstate->src_fd = fd; + xstate->xformer = unpack_lzma_stream; + USE_FOR_NOMMU(xstate->xformer_prog = "unlzma";) + return xstate; + } + } + + xstate = setup_transformer_on_fd(fd, fail_if_not_compressed); + + return xstate; +} + +int FAST_FUNC open_zipped(const char *fname, int fail_if_not_compressed) +{ + int fd; + transformer_state_t *xstate; + + xstate = open_transformer(fname, fail_if_not_compressed); + if (!xstate) + return -1; + + fd = xstate->src_fd; + if (xstate->xformer) { +# if BB_MMU + fork_transformer_with_no_sig(xstate->src_fd, xstate->xformer); +# else + fork_transformer_with_sig(xstate->src_fd, xstate->xformer, xstate->xformer_prog); +# endif + } + /* else: the file is not compressed */ + + free(xstate); + return fd; +} + +void* FAST_FUNC xmalloc_open_zipped_read_close(const char *fname, size_t *maxsz_p) +{ +# if 1 + transformer_state_t *xstate; + char *image; + + xstate = open_transformer(fname, /*fail_if_not_compressed:*/ 0); + if (!xstate) /* file open error */ + return NULL; + + image = NULL; + if (xstate->xformer) { + /* In-memory decompression */ + xstate->mem_output_size_max = maxsz_p ? *maxsz_p : (size_t)(INT_MAX - 4095); + xstate->xformer(xstate); + if (xstate->mem_output_buf) { + image = xstate->mem_output_buf; + if (maxsz_p) + *maxsz_p = xstate->mem_output_size; + } + } else { + /* File is not compressed */ + image = xmalloc_read(xstate->src_fd, maxsz_p); + } + + if (!image) + bb_perror_msg("read error from '%s'", fname); + close(xstate->src_fd); + free(xstate); + return image; +# else + /* This version forks a subprocess - much more expensive */ + int fd; + char *image; + + fd = open_zipped(fname, /*fail_if_not_compressed:*/ 0); + if (fd < 0) + return NULL; + + image = xmalloc_read(fd, maxsz_p); + if (!image) + bb_perror_msg("read error from '%s'", fname); + close(fd); + return image; +# endif +} + +#endif /* SEAMLESS_COMPRESSION */ diff --git a/src/bled/platform.h b/src/bled/platform.h new file mode 100644 index 00000000..4dcc835e --- /dev/null +++ b/src/bled/platform.h @@ -0,0 +1,621 @@ +/* vi: set sw=4 ts=4: */ +/* + * Copyright 2006, Bernhard Reutner-Fischer + * + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ +#ifndef BB_PLATFORM_H +#define BB_PLATFORM_H 1 + + +/* Convenience macros to test the version of gcc. */ +#undef __GNUC_PREREQ +#if defined __GNUC__ && defined __GNUC_MINOR__ +# define __GNUC_PREREQ(maj, min) \ + ((__GNUC__ << 16) + __GNUC_MINOR__ >= ((maj) << 16) + (min)) +#else +# define __GNUC_PREREQ(maj, min) 0 +#endif + +/* __restrict is known in EGCS 1.2 and above. */ +#if !__GNUC_PREREQ(2,92) +# ifndef __restrict +# define __restrict +# endif +#endif + +#if !__GNUC_PREREQ(2,7) +# ifndef __attribute__ +# define __attribute__(x) +# endif +#endif + +#undef inline +#if defined(__STDC_VERSION__) && __STDC_VERSION__ > 199901L +/* it's a keyword */ +#elif __GNUC_PREREQ(2,7) +# define inline __inline__ +#elif defined(_MSC_VER) +#define inline __inline +#else +# define inline +#endif + +#ifndef __const +# define __const const +#endif + +#define UNUSED_PARAM __attribute__ ((__unused__)) +#define NORETURN __attribute__ ((__noreturn__)) +/* "The malloc attribute is used to tell the compiler that a function + * may be treated as if any non-NULL pointer it returns cannot alias + * any other pointer valid when the function returns. This will often + * improve optimization. Standard functions with this property include + * malloc and calloc. realloc-like functions have this property as long + * as the old pointer is never referred to (including comparing it + * to the new pointer) after the function returns a non-NULL value." + */ +#if defined(__GNUC__) +#define RETURNS_MALLOC __attribute__ ((malloc)) +#ifdef __MINGW32__ +#define PACKED __attribute__ ((packed, gcc_struct)) +#else +#define PACKED __attribute__ ((__packed__)) +#endif +#define ALIGNED(m) __attribute__ ((__aligned__(m))) +#define PRAGMA_BEGIN_PACKED +#define PRAGMA_END_PACKED +#elif defined(_MSC_VER) +#define RETURNS_MALLOC +#define PACKED +#define ALIGNED(m) __declspec(align(m)) +#define PRAGMA_BEGIN_PACKED __pragma(pack(push, 1)) +#define PRAGMA_END_PACKED __pragma(pack(pop)) +#endif + +/* __NO_INLINE__: some gcc's do not honor inlining! :( */ +#if __GNUC_PREREQ(3,0) && !defined(__NO_INLINE__) +# define ALWAYS_INLINE __attribute__ ((always_inline)) inline +/* I've seen a toolchain where I needed __noinline__ instead of noinline */ +# define NOINLINE __attribute__((__noinline__)) +# if !ENABLE_WERROR +# define DEPRECATED __attribute__ ((__deprecated__)) +# define UNUSED_PARAM_RESULT __attribute__ ((warn_unused_result)) +# else +# define DEPRECATED +# define UNUSED_PARAM_RESULT +# endif +#else +# define ALWAYS_INLINE inline +# define NOINLINE +# define DEPRECATED +# define UNUSED_PARAM_RESULT +#endif + +/* used by unit test machinery to run registration functions before calling main() */ +#define INIT_FUNC __attribute__ ((constructor)) + +/* -fwhole-program makes all symbols local. The attribute externally_visible + * forces a symbol global. */ +#if __GNUC_PREREQ(4,1) +# define EXTERNALLY_VISIBLE __attribute__(( visibility("default") )) +//__attribute__ ((__externally_visible__)) +#else +# define EXTERNALLY_VISIBLE +#endif + +/* At 4.4 gcc become much more anal about this, need to use "aliased" types */ +#if __GNUC_PREREQ(4,4) +# define FIX_ALIASING __attribute__((__may_alias__)) +#else +# define FIX_ALIASING +#endif + +/* We use __extension__ in some places to suppress -pedantic warnings + * about GCC extensions. This feature didn't work properly before + * gcc 2.8. */ +#if !__GNUC_PREREQ(2,8) +# ifndef __extension__ +# define __extension__ +# endif +#endif + +/* FAST_FUNC is a qualifier which (possibly) makes function call faster + * and/or smaller by using modified ABI. It is usually only needed + * on non-static, busybox internal functions. Recent versions of gcc + * optimize statics automatically. FAST_FUNC on static is required + * only if you need to match a function pointer's type */ +#if __GNUC_PREREQ(3,0) && !defined(__MINGW32__) && defined(i386) /* || defined(__x86_64__)? */ +/* stdcall makes callee to pop arguments from stack, not caller */ +# define FAST_FUNC __attribute__((regparm(3),stdcall)) +/* #elif ... - add your favorite arch today! */ +#else +# define FAST_FUNC +#endif + +/* Make all declarations hidden (-fvisibility flag only affects definitions) */ +/* (don't include system headers after this until corresponding pop!) */ +#if __GNUC_PREREQ(4,1) && !defined(__CYGWIN__) +# define PUSH_AND_SET_FUNCTION_VISIBILITY_TO_HIDDEN _Pragma("GCC visibility push(hidden)") +# define POP_SAVED_FUNCTION_VISIBILITY _Pragma("GCC visibility pop") +#else +# define PUSH_AND_SET_FUNCTION_VISIBILITY_TO_HIDDEN +# define POP_SAVED_FUNCTION_VISIBILITY +#endif + +/* gcc-2.95 had no va_copy but only __va_copy. */ +#if !__GNUC_PREREQ(3,0) +# include +# if !defined va_copy && defined __va_copy +# define va_copy(d,s) __va_copy((d),(s)) +# endif +#endif + + +/* ---- Endian Detection ------------------------------------ */ + +#include +#if defined(__digital__) && defined(__unix__) +# include +#elif defined(__FreeBSD__) || defined(__OpenBSD__) || defined(__NetBSD__) \ + || defined(__APPLE__) +# include /* rlimit */ +# include +# define bswap_64 __bswap64 +# define bswap_32 __bswap32 +# define bswap_16 __bswap16 +#elif defined(_MSC_VER) || defined(__MINGW32__) +#include +#ifndef bswap_16 +static __inline uint16_t bswap_16(uint16_t x) +{ + x = (x>>8) | (x<<8); + return x; +} +#endif + +#ifndef bswap_32 +static __inline uint32_t bswap_32(uint32_t x) +{ + x = ((x<<8)&0xFF00FF00) | ((x>>8)&0x00FF00FF); + x = (x>>16) | (x<<16); + return x; +} +#endif + +#ifndef bswap_64 +static __inline uint64_t bswap_64(uint64_t x) +{ + union { + uint64_t ll; + uint32_t l[2]; + } w, r; + w.ll = x; + r.l[0] = bswap_32(w.l[1]); + r.l[1] = bswap_32(w.l[0]); + return r.ll; +} +#endif + +#else +# include +# include +#endif + +#if defined(__BYTE_ORDER) && __BYTE_ORDER == __BIG_ENDIAN +# define BB_BIG_ENDIAN 1 +# define BB_LITTLE_ENDIAN 0 +#elif defined(__BYTE_ORDER) && __BYTE_ORDER == __LITTLE_ENDIAN +# define BB_BIG_ENDIAN 0 +# define BB_LITTLE_ENDIAN 1 +#elif defined(_BYTE_ORDER) && _BYTE_ORDER == _BIG_ENDIAN +# define BB_BIG_ENDIAN 1 +# define BB_LITTLE_ENDIAN 0 +#elif defined(_BYTE_ORDER) && _BYTE_ORDER == _LITTLE_ENDIAN +# define BB_BIG_ENDIAN 0 +# define BB_LITTLE_ENDIAN 1 +#elif defined(BYTE_ORDER) && BYTE_ORDER == BIG_ENDIAN +# define BB_BIG_ENDIAN 1 +# define BB_LITTLE_ENDIAN 0 +#elif defined(BYTE_ORDER) && BYTE_ORDER == LITTLE_ENDIAN +# define BB_BIG_ENDIAN 0 +# define BB_LITTLE_ENDIAN 1 +#elif defined(__386__) || defined(_M_IX86) || defined(_M_AMD64) +# define BB_BIG_ENDIAN 0 +# define BB_LITTLE_ENDIAN 1 +#else +# error "Can't determine endianness" +#endif + +#if ULONG_MAX > 0xffffffff +# define bb_bswap_64(x) bswap_64(x) +#endif + +/* SWAP_LEnn means "convert CPU<->little_endian by swapping bytes" */ +#if BB_BIG_ENDIAN +# define SWAP_BE16(x) (x) +# define SWAP_BE32(x) (x) +# define SWAP_BE64(x) (x) +# define SWAP_LE16(x) bswap_16(x) +# define SWAP_LE32(x) bswap_32(x) +# define SWAP_LE64(x) bb_bswap_64(x) +# define IF_BIG_ENDIAN(...) __VA_ARGS__ +# define IF_LITTLE_ENDIAN(...) +#else +# define SWAP_BE16(x) bswap_16(x) +# define SWAP_BE32(x) bswap_32(x) +# define SWAP_BE64(x) bb_bswap_64(x) +# define SWAP_LE16(x) (x) +# define SWAP_LE32(x) (x) +# define SWAP_LE64(x) (x) +# define IF_BIG_ENDIAN(...) +# define IF_LITTLE_ENDIAN(...) __VA_ARGS__ +#endif + + +/* ---- Unaligned access ------------------------------------ */ + +#include +typedef int bb__aliased_int FIX_ALIASING; +typedef long bb__aliased_long FIX_ALIASING; +typedef uint16_t bb__aliased_uint16_t FIX_ALIASING; +typedef uint32_t bb__aliased_uint32_t FIX_ALIASING; +typedef uint64_t bb__aliased_uint64_t FIX_ALIASING; + +/* NB: unaligned parameter should be a pointer, aligned one - + * a lvalue. This makes it more likely to not swap them by mistake + */ +#if defined(i386) || defined(__x86_64__) || defined(__powerpc__) +# define move_from_unaligned_int(v, intp) ((v) = *(bb__aliased_int*)(intp)) +# define move_from_unaligned_long(v, longp) ((v) = *(bb__aliased_long*)(longp)) +# define move_from_unaligned16(v, u16p) ((v) = *(bb__aliased_uint16_t*)(u16p)) +# define move_from_unaligned32(v, u32p) ((v) = *(bb__aliased_uint32_t*)(u32p)) +# define move_to_unaligned16(u16p, v) (*(bb__aliased_uint16_t*)(u16p) = (v)) +# define move_to_unaligned32(u32p, v) (*(bb__aliased_uint32_t*)(u32p) = (v)) +/* #elif ... - add your favorite arch today! */ +#else +/* performs reasonably well (gcc usually inlines memcpy here) */ +# define move_from_unaligned_int(v, intp) (memcpy(&(v), (intp), sizeof(int))) +# define move_from_unaligned_long(v, longp) (memcpy(&(v), (longp), sizeof(long))) +# define move_from_unaligned16(v, u16p) (memcpy(&(v), (u16p), 2)) +# define move_from_unaligned32(v, u32p) (memcpy(&(v), (u32p), 4)) +# define move_to_unaligned16(u16p, v) do { \ + uint16_t __t = (v); \ + memcpy((u16p), &__t, 2); \ +} while (0) +# define move_to_unaligned32(u32p, v) do { \ + uint32_t __t = (v); \ + memcpy((u32p), &__t, 4); \ +} while (0) +#endif + + +/* ---- Size-saving "small" ints (arch-dependent) ----------- */ + +#if defined(i386) || defined(__x86_64__) || defined(__mips__) || defined(__cris__) +/* add other arches which benefit from this... */ +typedef signed char smallint; +typedef unsigned char smalluint; +#else +/* for arches where byte accesses generate larger code: */ +typedef int smallint; +typedef unsigned smalluint; +#endif + +/* ISO C Standard: 7.16 Boolean type and values */ +#if (defined __digital__ && defined __unix__) +/* old system without (proper) C99 support */ +# define bool smalluint +#else +/* modern system, so use it */ +# include +#endif + + +/*----- Kernel versioning ------------------------------------*/ + +#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c)) + +#ifdef __UCLIBC__ +# define UCLIBC_VERSION KERNEL_VERSION(__UCLIBC_MAJOR__, __UCLIBC_MINOR__, __UCLIBC_SUBLEVEL__) +#else +# define UCLIBC_VERSION 0 +#endif + + +/* ---- Miscellaneous --------------------------------------- */ + +#if defined __GLIBC__ \ + || defined __UCLIBC__ \ + || defined __dietlibc__ \ + || defined __BIONIC__ \ + || defined _NEWLIB_VERSION +# include +#endif + +/* Define bb_setpgrp */ +#if defined(__digital__) && defined(__unix__) +/* use legacy setpgrp(pid_t, pid_t) for now. move to platform.c */ +# define bb_setpgrp() do { pid_t __me = getpid(); setpgrp(__me, __me); } while (0) +#else +# define bb_setpgrp() setpgrp() +#endif + +/* Useful for defeating gcc's alignment of "char message[]"-like data */ +#if !defined(__s390__) + /* on s390[x], non-word-aligned data accesses require larger code */ +# define ALIGN1 __attribute__((aligned(1))) +# define ALIGN2 __attribute__((aligned(2))) +# define ALIGN4 __attribute__((aligned(4))) +#else +/* Arches which MUST have 2 or 4 byte alignment for everything are here */ +# define ALIGN1 +# define ALIGN2 +# define ALIGN4 +#endif + +/* + * For 0.9.29 and svn, __ARCH_USE_MMU__ indicates no-mmu reliably. + * For earlier versions there is no reliable way to check if we are building + * for a mmu-less system. + */ +#if ENABLE_NOMMU || \ + (defined __UCLIBC__ && \ + UCLIBC_VERSION > KERNEL_VERSION(0, 9, 28) && \ + !defined __ARCH_USE_MMU__) +# define BB_MMU 0 +# define USE_FOR_NOMMU(...) __VA_ARGS__ +# define USE_FOR_MMU(...) +#else +# define BB_MMU 1 +# define USE_FOR_NOMMU(...) +# define USE_FOR_MMU(...) __VA_ARGS__ +#endif + +#if defined(__digital__) && defined(__unix__) +# include +# include +# define PRIu32 "u" +# if !defined ADJ_OFFSET_SINGLESHOT && defined MOD_CLKA && defined MOD_OFFSET +# define ADJ_OFFSET_SINGLESHOT (MOD_CLKA | MOD_OFFSET) +# endif +# if !defined ADJ_FREQUENCY && defined MOD_FREQUENCY +# define ADJ_FREQUENCY MOD_FREQUENCY +# endif +# if !defined ADJ_TIMECONST && defined MOD_TIMECONST +# define ADJ_TIMECONST MOD_TIMECONST +# endif +# if !defined ADJ_TICK && defined MOD_CLKB +# define ADJ_TICK MOD_CLKB +# endif +#endif + +#if defined(__CYGWIN__) +# define MAXSYMLINKS SYMLOOP_MAX +#endif + +#if defined(ANDROID) || defined(__ANDROID__) +# define BB_ADDITIONAL_PATH ":/system/sbin:/system/bin:/system/xbin" +# define SYS_ioprio_set __NR_ioprio_set +# define SYS_ioprio_get __NR_ioprio_get +#endif + + +/* ---- Who misses what? ------------------------------------ */ + +/* Assume all these functions and header files exist by default. + * Platforms where it is not true will #undef them below. + */ +#define HAVE_CLEARENV 1 +#define HAVE_FDATASYNC 1 +#define HAVE_DPRINTF 1 +#define HAVE_MEMRCHR 1 +#define HAVE_MKDTEMP 1 +#define HAVE_PTSNAME_R 1 +#define HAVE_SETBIT 1 +#define HAVE_SIGHANDLER_T 1 +#define HAVE_STPCPY 1 +#define HAVE_STRCASESTR 1 +#define HAVE_STRCHRNUL 1 +#define HAVE_STRSEP 1 +#define HAVE_STRSIGNAL 1 +#define HAVE_STRVERSCMP 1 +#define HAVE_VASPRINTF 1 +#define HAVE_USLEEP 1 +#define HAVE_UNLOCKED_STDIO 1 +#define HAVE_UNLOCKED_LINE_OPS 1 +#define HAVE_GETLINE 1 +#define HAVE_XTABS 1 +#define HAVE_MNTENT_H 1 +#define HAVE_NET_ETHERNET_H 1 +#define HAVE_SYS_STATFS_H 1 + +#if defined(__UCLIBC__) +# if UCLIBC_VERSION < KERNEL_VERSION(0, 9, 32) +# undef HAVE_STRVERSCMP +# endif +# if UCLIBC_VERSION >= KERNEL_VERSION(0, 9, 30) +# ifndef __UCLIBC_SUSV3_LEGACY__ +# undef HAVE_USLEEP +# endif +# endif +#endif + +#if defined(__WATCOMC__) +# undef HAVE_DPRINTF +# undef HAVE_GETLINE +# undef HAVE_MEMRCHR +# undef HAVE_MKDTEMP +# undef HAVE_SETBIT +# undef HAVE_STPCPY +# undef HAVE_STRCASESTR +# undef HAVE_STRCHRNUL +# undef HAVE_STRSEP +# undef HAVE_STRSIGNAL +# undef HAVE_STRVERSCMP +# undef HAVE_VASPRINTF +# undef HAVE_UNLOCKED_STDIO +# undef HAVE_UNLOCKED_LINE_OPS +# undef HAVE_NET_ETHERNET_H +#endif + +#if defined(_MSC_VER) +/* We need to define ssize_t before the getline declaration below (copy/paste from MinGW) */ +#ifndef _SSIZE_T_DEFINED +#define _SSIZE_T_DEFINED +#undef ssize_t +#ifdef _WIN64 + typedef __int64 ssize_t; +#else + typedef int ssize_t; +#endif +#endif +# undef HAVE_GETLINE +# undef HAVE_MEMRCHR +# undef HAVE_MKDTEMP +# undef HAVE_MNTENT_H +# undef HAVE_SETBIT +# undef HAVE_STPCPY +# undef HAVE_STRCASESTR +# undef HAVE_STRCHRNUL +# undef HAVE_STRSEP +# undef HAVE_STRSIGNAL +# undef HAVE_STRVERSCMP +# undef HAVE_SYS_STATFS_H +# undef HAVE_VASPRINTF +# undef HAVE_UNLOCKED_STDIO +# undef HAVE_UNLOCKED_LINE_OPS +# undef HAVE_NET_ETHERNET_H +#endif + +#if defined(__CYGWIN__) +# undef HAVE_CLEARENV +# undef HAVE_FDPRINTF +# undef HAVE_MEMRCHR +# undef HAVE_PTSNAME_R +# undef HAVE_STRVERSCMP +# undef HAVE_UNLOCKED_LINE_OPS +#endif + +/* These BSD-derived OSes share many similarities */ +#if (defined __digital__ && defined __unix__) \ + || defined __APPLE__ \ + || defined __OpenBSD__ || defined __NetBSD__ +# undef HAVE_CLEARENV +# undef HAVE_FDATASYNC +# undef HAVE_GETLINE +# undef HAVE_MNTENT_H +# undef HAVE_PTSNAME_R +# undef HAVE_SYS_STATFS_H +# undef HAVE_SIGHANDLER_T +# undef HAVE_STRVERSCMP +# undef HAVE_XTABS +# undef HAVE_DPRINTF +# undef HAVE_UNLOCKED_STDIO +# undef HAVE_UNLOCKED_LINE_OPS +#endif + +#if defined(__dietlibc__) +# undef HAVE_STRCHRNUL +#endif + +#if defined(__APPLE__) +# undef HAVE_STRCHRNUL +#endif + +#if defined(__FreeBSD__) +# undef HAVE_CLEARENV +# undef HAVE_FDATASYNC +# undef HAVE_MNTENT_H +# undef HAVE_PTSNAME_R +# undef HAVE_SYS_STATFS_H +# undef HAVE_SIGHANDLER_T +# undef HAVE_STRVERSCMP +# undef HAVE_XTABS +# undef HAVE_UNLOCKED_LINE_OPS +# include +# if __FreeBSD_version < 1000029 +# undef HAVE_STRCHRNUL /* FreeBSD added strchrnul() between 1000028 and 1000029 */ +# endif +#endif + +#if defined(__NetBSD__) +# define HAVE_GETLINE 1 /* Recent NetBSD versions have getline() */ +#endif + +#if defined(__digital__) && defined(__unix__) +# undef HAVE_STPCPY +#endif + +#if defined(ANDROID) || defined(__ANDROID__) +# undef HAVE_DPRINTF +# undef HAVE_GETLINE +# undef HAVE_STPCPY +# undef HAVE_STRCHRNUL +# undef HAVE_STRVERSCMP +# undef HAVE_UNLOCKED_LINE_OPS +# undef HAVE_NET_ETHERNET_H +#endif + +/* + * Now, define prototypes for all the functions defined in platform.c + * These must come after all the HAVE_* macros are defined (or not) + */ + +#ifndef HAVE_DPRINTF +extern int dprintf(int fd, const char *format, ...); +#endif + +#ifndef HAVE_MEMRCHR +extern void *memrchr(const void *s, int c, size_t n) FAST_FUNC; +#endif + +#ifndef HAVE_MKDTEMP +extern char *mkdtemp(char *template) FAST_FUNC; +#endif + +#ifndef HAVE_SETBIT +# define setbit(a, b) ((a)[(b) >> 3] |= 1 << ((b) & 7)) +# define clrbit(a, b) ((a)[(b) >> 3] &= ~(1 << ((b) & 7))) +#endif + +#ifndef HAVE_SIGHANDLER_T +typedef void (*sighandler_t)(int); +#endif + +#ifndef HAVE_STPCPY +extern char *stpcpy(char *p, const char *to_add) FAST_FUNC; +#endif + +#ifndef HAVE_STRCASESTR +extern char *strcasestr(const char *s, const char *pattern) FAST_FUNC; +#endif + +#ifndef HAVE_STRCHRNUL +extern char *strchrnul(const char *s, int c) FAST_FUNC; +#endif + +#ifndef HAVE_STRSEP +extern char *strsep(char **stringp, const char *delim) FAST_FUNC; +#endif + +#ifndef HAVE_STRSIGNAL +/* Not exactly the same: instead of "Stopped" it shows "STOP" etc */ +# define strsignal(sig) get_signame(sig) +#endif + +#ifndef HAVE_USLEEP +extern int usleep(unsigned) FAST_FUNC; +#endif + +#ifndef HAVE_VASPRINTF +extern int vasprintf(char **string_ptr, const char *format, va_list p) FAST_FUNC; +#endif + +#ifndef HAVE_GETLINE +# include /* for FILE */ +# include /* size_t */ +extern ssize_t getline(char **lineptr, size_t *n, FILE *stream) FAST_FUNC; +#endif + +#endif diff --git a/src/bled/seek_by_jump.c b/src/bled/seek_by_jump.c new file mode 100644 index 00000000..4fcd99ac --- /dev/null +++ b/src/bled/seek_by_jump.c @@ -0,0 +1,19 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +void FAST_FUNC seek_by_jump(int fd, off_t amount) +{ + if (amount + && lseek(fd, amount, SEEK_CUR) == (off_t) -1 + ) { + if (errno == ESPIPE) + seek_by_read(fd, amount); + else + bb_perror_msg_and_die("seek failure"); + } +} diff --git a/src/bled/seek_by_read.c b/src/bled/seek_by_read.c new file mode 100644 index 00000000..c0fde966 --- /dev/null +++ b/src/bled/seek_by_read.c @@ -0,0 +1,16 @@ +/* vi: set sw=4 ts=4: */ +/* + * Licensed under GPLv2 or later, see file LICENSE in this source tree. + */ + +#include "libbb.h" +#include "bb_archive.h" + +/* If we are reading through a pipe, or from stdin then we can't lseek, + * we must read and discard the data to skip over it. + */ +void FAST_FUNC seek_by_read(int fd, off_t amount) +{ + if (amount) + bb_copyfd_exact_size(fd, -1, amount); +} diff --git a/src/bled/xz.h b/src/bled/xz.h new file mode 100644 index 00000000..59ca88bb --- /dev/null +++ b/src/bled/xz.h @@ -0,0 +1,282 @@ +/* + * XZ decompressor + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_H +#define XZ_H + +#ifdef __KERNEL__ +# include +# include +#else +# include +# include +#endif + +#include "platform.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/* In Linux, this is used to make extern functions static when needed. */ +#ifndef XZ_EXTERN +# define XZ_EXTERN extern +#endif + +/* In Linux, this is used to mark the functions with __init when needed. */ +#ifndef XZ_FUNC +# define XZ_FUNC +#endif + +/** + * enum xz_mode - Operation mode + * + * @XZ_SINGLE: Single-call mode. This uses less RAM than + * than multi-call modes, because the LZMA2 + * dictionary doesn't need to be allocated as + * part of the decoder state. All required data + * structures are allocated at initialization, + * so xz_dec_run() cannot return XZ_MEM_ERROR. + * @XZ_PREALLOC: Multi-call mode with preallocated LZMA2 + * dictionary buffer. All data structures are + * allocated at initialization, so xz_dec_run() + * cannot return XZ_MEM_ERROR. + * @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is + * allocated once the required size has been + * parsed from the stream headers. If the + * allocation fails, xz_dec_run() will return + * XZ_MEM_ERROR. + * + * It is possible to enable support only for a subset of the above + * modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC, + * or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled + * with support for all operation modes, but the preboot code may + * be built with fewer features to minimize code size. + */ +enum xz_mode { + XZ_SINGLE, + XZ_PREALLOC, + XZ_DYNALLOC +}; + +/** + * enum xz_ret - Return codes + * @XZ_OK: Everything is OK so far. More input or more + * output space is required to continue. This + * return code is possible only in multi-call mode + * (XZ_PREALLOC or XZ_DYNALLOC). + * @XZ_STREAM_END: Operation finished successfully. + * @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding + * is still possible in multi-call mode by simply + * calling xz_dec_run() again. + * Note that this return value is used only if + * XZ_DEC_ANY_CHECK was defined at build time, + * which is not used in the kernel. Unsupported + * check types return XZ_OPTIONS_ERROR if + * XZ_DEC_ANY_CHECK was not defined at build time. + * @XZ_MEM_ERROR: Allocating memory failed. This return code is + * possible only if the decoder was initialized + * with XZ_DYNALLOC. The amount of memory that was + * tried to be allocated was no more than the + * dict_max argument given to xz_dec_init(). + * @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than + * allowed by the dict_max argument given to + * xz_dec_init(). This return value is possible + * only in multi-call mode (XZ_PREALLOC or + * XZ_DYNALLOC); the single-call mode (XZ_SINGLE) + * ignores the dict_max argument. + * @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_UNSUPPORTED_CHECK, + XZ_MEM_ERROR, + 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 + * @mode: Operation mode + * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for + * multi-call decoding. This is ignored in single-call mode + * (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes + * or 2^n + 2^(n-1) bytes (the latter sizes are less common + * in practice), so other values for dict_max don't make sense. + * In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB, + * 512 KiB, and 1 MiB are probably the only reasonable values, + * except for kernel and initramfs images where a bigger + * dictionary can be fine and useful. + * + * Single-call mode (XZ_SINGLE): 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 mode. It is enough that + * the output buffer is big enough to hold the actual uncompressed data; it + * can be smaller than the dictionary size stored in the stream headers. + * + * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max 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. + * + * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC): + * dict_max specifies the maximum allowed dictionary size that xz_dec_run() + * may allocate once it has parsed the dictionary size from the stream + * headers. This way excessive allocations can be avoided while still + * limiting the maximum memory usage to a sane value to prevent running the + * system out of memory when decompressing streams from untrusted sources. + * + * On success, xz_dec_init() returns a pointer to struct xz_dec, which is + * ready to be used with xz_dec_run(). If memory allocation fails, + * xz_dec_init() returns NULL. + */ +XZ_EXTERN struct xz_dec * XZ_FUNC xz_dec_init( + enum xz_mode mode, uint32_t dict_max); + +/** + * xz_dec_run() - Run the XZ decoder + * @s: Decoder state allocated using xz_dec_init() + * @b: Input and output buffers + * + * The possible return values depend on build options and operation mode. + * See enum xz_ret for details. + * + * Note that 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. This is true even after XZ_BUF_ERROR, 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. + */ +XZ_EXTERN enum xz_ret XZ_FUNC 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. + */ +XZ_EXTERN void XZ_FUNC 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. + */ +XZ_EXTERN void XZ_FUNC xz_dec_end(struct xz_dec *s); + +/* + * Standalone build (userspace build or in-kernel build for boot time use) + * needs a CRC32 implementation. For normal in-kernel use, kernel's own + * CRC32 module is used instead, and users of this module don't need to + * care about the functions below. + */ +#ifndef XZ_INTERNAL_CRC32 +# ifdef __KERNEL__ +# define XZ_INTERNAL_CRC32 0 +# else +# define XZ_INTERNAL_CRC32 1 +# endif +#endif + +#if XZ_INTERNAL_CRC32 +/* + * This must be called before any other xz_* function to initialize + * the CRC32 lookup table. + */ +XZ_EXTERN void XZ_FUNC xz_crc32_init(void); + +/* + * Update CRC32 value using the polynomial from IEEE-802.3. To start a new + * calculation, the third argument must be zero. To continue the calculation, + * the previously returned value is passed as the third argument. + */ +XZ_EXTERN uint32_t XZ_FUNC xz_crc32( + const uint8_t *buf, size_t size, uint32_t crc); +#endif + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/src/bled/xz_config.h b/src/bled/xz_config.h new file mode 100644 index 00000000..05d90af9 --- /dev/null +++ b/src/bled/xz_config.h @@ -0,0 +1,123 @@ +/* + * Private includes and definitions for userspace use of XZ Embedded + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_CONFIG_H +#define XZ_CONFIG_H + +/* Uncomment as needed to enable BCJ filter decoders. */ +#define XZ_DEC_X86 +/* #define XZ_DEC_POWERPC */ +/* #define XZ_DEC_IA64 */ +/* #define XZ_DEC_ARM */ +/* #define XZ_DEC_ARMTHUMB */ +/* #define XZ_DEC_SPARC */ + +#include +#include +#include + +#include "xz.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) + +#undef min +#undef min_t +#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, 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 */ +#ifndef get_unaligned_le32 +static inline uint32_t XZ_FUNC 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); +} +#endif + +#ifndef get_unaligned_be32 +static inline uint32_t XZ_FUNC 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]; +} +#endif + +#ifndef put_unaligned_le32 +static inline void XZ_FUNC 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); +} +#endif + +#ifndef put_unaligned_be32 +static inline void XZ_FUNC 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; +} +#endif + +/* + * 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. + */ +#ifndef get_le32 +# define get_le32 get_unaligned_le32 +#endif + +#endif diff --git a/src/bled/xz_dec_bcj.c b/src/bled/xz_dec_bcj.c new file mode 100644 index 00000000..e0f913a9 --- /dev/null +++ b/src/bled/xz_dec_bcj.c @@ -0,0 +1,580 @@ +/* + * Branch/Call/Jump (BCJ) filter decoders + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include "xz_private.h" + +/* + * The rest of the file is inside this ifdef. It makes things a little more + * convenient when building without support for any BCJ filters. + */ +#ifdef XZ_DEC_BCJ + +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 used to test the most significant byte of a memory address + * in an x86 instruction. + */ +static inline int bcj_x86_test_msbyte(uint8_t b) +{ + return b == 0x00 || b == 0xFF; +} + +static noinline_for_stack size_t XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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. + */ +XZ_EXTERN enum xz_ret XZ_FUNC 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. + * + * This needs to be always run when temp.size == 0 to handle a special + * case where the output buffer is full and the next filter has no + * more output coming but hasn't returned XZ_STREAM_END yet. + */ + if (s->temp.size < b->out_size - b->out_pos || s->temp.size == 0) { + 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 there wasn't enough input to the next filter to fill + * the output buffer with unfiltered data, there's no point + * to try decoding more data to temp. + */ + if (b->out_pos + s->temp.size < b->out_size) + return XZ_OK; + } + + /* + * We have unfiltered data in temp. If the output buffer isn't full + * yet, try to fill the temp buffer 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 (b->out_pos < b->out_size) { + /* 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; +} + +XZ_EXTERN struct xz_dec_bcj * XZ_FUNC 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; +} + +XZ_EXTERN enum xz_ret XZ_FUNC 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; +} + +#endif diff --git a/src/bled/xz_dec_lzma2.c b/src/bled/xz_dec_lzma2.c new file mode 100644 index 00000000..3c2dc88b --- /dev/null +++ b/src/bled/xz_dec_lzma2.c @@ -0,0 +1,1174 @@ +/* + * LZMA2 decoder + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#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 <= size_max + * allocated <= size + * + * 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; + + /* + * Maximum allowed dictionary size in multi-call mode. + * This is ignored in single-call mode. + */ + uint32_t size_max; + + /* + * Amount of memory currently allocated for the dictionary. + * This is used only with XZ_DYNALLOC. (With XZ_PREALLOC, + * size_max is always the same as the allocated size.) + */ + uint32_t allocated; + + /* Operation mode */ + enum xz_mode mode; +}; + +/* 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 { + /* Distances of latest four matches */ + uint32_t rep0; + uint32_t rep1; + uint32_t rep2; + uint32_t rep3; + + /* Types of the most recently seen LZMA symbols */ + enum lzma_state state; + + /* + * Length of a match. This is updated so that dict_repeat can + * be called again to finish repeating the whole match. + */ + uint32_t len; + + /* + * 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 */ + + /* 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 lzma2_dec { + /* 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; +}; + +struct xz_dec_lzma2 { + /* + * The order below is important on x86 to reduce code size and + * it shouldn't hurt on other platforms. Everything up to and + * including lzma.pos_mask are in the first 128 bytes on x86-32, + * which allows using smaller instructions to access those + * variables. On x86-64, fewer variables fit into the first 128 + * bytes, but this is still the best order without sacrificing + * the readability by splitting the structures. + */ + struct rc_dec rc; + struct dictionary dict; + struct lzma2_dec lzma2; + struct lzma_dec lzma; + + /* + * 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; +}; + +/************** + * 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 XZ_FUNC dict_reset(struct dictionary *dict, struct xz_buf *b) +{ + if (DEC_IS_SINGLE(dict->mode)) { + 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 XZ_FUNC 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 __always_inline bool XZ_FUNC 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 __always_inline uint32_t XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 (DEC_IS_MULTI(dict->mode)) { + 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 XZ_FUNC dict_flush(struct dictionary *dict, struct xz_buf *b) +{ + size_t copy_size = dict->pos - dict->start; + + if (DEC_IS_MULTI(dict->mode)) { + 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC rc_is_finished(const struct rc_dec *rc) +{ + return rc->code == 0; +} + +/* Read the next input byte if needed. */ +static __always_inline void XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 * XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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. + */ +XZ_EXTERN NOINLINE enum xz_ret XZ_FUNC 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 == 0x00) + return XZ_STREAM_END; + + 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 > 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; +} + +XZ_EXTERN struct xz_dec_lzma2 * XZ_FUNC xz_dec_lzma2_create( + enum xz_mode mode, uint32_t dict_max) +{ + struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + s->dict.mode = mode; + s->dict.size_max = dict_max; + + if (DEC_IS_PREALLOC(mode)) { + s->dict.buf = vmalloc(dict_max); + if (s->dict.buf == NULL) { + kfree(s); + return NULL; + } + } else if (DEC_IS_DYNALLOC(mode)) { + s->dict.buf = NULL; + s->dict.allocated = 0; + } + + return s; +} + +XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_lzma2_reset( + struct xz_dec_lzma2 *s, uint8_t props) +{ + /* This limits dictionary size to 3 GiB to keep parsing simpler. */ + if (props > 39) + return XZ_OPTIONS_ERROR; + + s->dict.size = 2 + (props & 1); + s->dict.size <<= (props >> 1) + 11; + + if (DEC_IS_MULTI(s->dict.mode)) { + if (s->dict.size > s->dict.size_max) + return XZ_MEMLIMIT_ERROR; + + s->dict.end = s->dict.size; + + if (DEC_IS_DYNALLOC(s->dict.mode)) { + if (s->dict.allocated < s->dict.size) { + vfree(s->dict.buf); + s->dict.buf = vmalloc(s->dict.size); + if (s->dict.buf == NULL) { + s->dict.allocated = 0; + return XZ_MEM_ERROR; + } + } + } + } + + s->lzma.len = 0; + + s->lzma2.sequence = SEQ_CONTROL; + s->lzma2.need_dict_reset = true; + + s->temp.size = 0; + + return XZ_OK; +} + +XZ_EXTERN void XZ_FUNC xz_dec_lzma2_end(struct xz_dec_lzma2 *s) +{ + if (DEC_IS_MULTI(s->dict.mode)) + vfree(s->dict.buf); + + kfree(s); +} diff --git a/src/bled/xz_dec_stream.c b/src/bled/xz_dec_stream.c new file mode 100644 index 00000000..bdcbf1ba --- /dev/null +++ b/src/bled/xz_dec_stream.c @@ -0,0 +1,822 @@ +/* + * .xz Stream decoder + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#include "xz_private.h" +#include "xz_stream.h" + +/* Hash used to validate the Index field */ +struct xz_dec_hash { + vli_type unpadded; + vli_type uncompressed; + uint32_t crc32; +}; + +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; + + /* Type of the integrity check calculated from uncompressed data */ + enum xz_check check_type; + + /* Operation mode */ + enum xz_mode mode; + + /* + * 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 +}; + +#ifdef XZ_DEC_ANY_CHECK +/* Sizes of the Check field with different Check IDs */ +static const uint8_t check_sizes[16] = { + 0, + 4, 4, 4, + 8, 8, 8, + 16, 16, 16, + 32, 32, 32, + 64, 64, 64 +}; +#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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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->check_type == XZ_CHECK_CRC32) + s->crc32 = xz_crc32(b->out + s->out_start, + b->out_pos - s->out_start, s->crc32); + + 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; + +#ifdef XZ_DEC_ANY_CHECK + s->block.hash.unpadded += check_sizes[s->check_type]; +#else + if (s->check_type == XZ_CHECK_CRC32) + s->block.hash.unpadded += 4; +#endif + + s->block.hash.uncompressed += s->block.uncompressed; + s->block.hash.crc32 = xz_crc32( + (const uint8_t *)&s->block.hash, + sizeof(s->block.hash), s->block.hash.crc32); + + ++s->block.count; + } + + return ret; +} + +/* Update the Index size and the CRC32 value. */ +static void XZ_FUNC 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; + s->crc32 = xz_crc32(b->in + s->in_start, in_used, s->crc32); +} + +/* + * 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 XZ_FUNC 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; + s->index.hash.crc32 = xz_crc32( + (const uint8_t *)&s->index.hash, + sizeof(s->index.hash), + s->index.hash.crc32); + --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 XZ_FUNC crc32_validate(struct xz_dec *s, struct xz_buf *b) +{ + do { + if (b->in_pos == b->in_size) + return XZ_OK; + + if (((s->crc32 >> s->pos) & 0xFF) != b->in[b->in_pos++]) + return XZ_DATA_ERROR; + + s->pos += 8; + + } while (s->pos < 32); + + s->crc32 = 0; + s->pos = 0; + + return XZ_STREAM_END; +} + +#ifdef XZ_DEC_ANY_CHECK +/* + * Skip over the Check field when the Check ID is not supported. + * Returns true once the whole Check field has been skipped over. + */ +static bool XZ_FUNC check_skip(struct xz_dec *s, struct xz_buf *b) +{ + while (s->pos < check_sizes[s->check_type]) { + if (b->in_pos == b->in_size) + return false; + + ++b->in_pos; + ++s->pos; + } + + s->pos = 0; + + return true; +} +#endif + +/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */ +static enum xz_ret XZ_FUNC dec_stream_header(struct xz_dec *s) +{ + if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE)) + return XZ_FORMAT_ERROR; + + if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0) + != get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2)) + return XZ_DATA_ERROR; + + if (s->temp.buf[HEADER_MAGIC_SIZE] != 0) + return XZ_OPTIONS_ERROR; + + /* + * Of integrity checks, we support only none (Check ID = 0) and + * CRC32 (Check ID = 1). However, if XZ_DEC_ANY_CHECK is defined, + * we will accept other check types too, but then the check won't + * be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given. + */ + s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1]; + +#ifdef XZ_DEC_ANY_CHECK + if (s->check_type > XZ_CHECK_MAX) + return XZ_OPTIONS_ERROR; + + if (s->check_type > XZ_CHECK_CRC32) + return XZ_UNSUPPORTED_CHECK; +#else + if (s->check_type > XZ_CHECK_CRC32) + return XZ_OPTIONS_ERROR; +#endif + + return XZ_OK; +} + +/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */ +static enum xz_ret XZ_FUNC dec_stream_footer(struct xz_dec *s) +{ + if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE)) + return XZ_DATA_ERROR; + + if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf)) + 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->check_type) + 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 XZ_FUNC 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; + if (xz_crc32(s->temp.buf, s->temp.size, 0) + != get_le32(s->temp.buf + s->temp.size)) + 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 XZ_FUNC 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; + + /* + * If dec_stream_header() returns + * XZ_UNSUPPORTED_CHECK, it is still possible + * to continue decoding if working in multi-call + * mode. Thus, update s->sequence before calling + * dec_stream_header(). + */ + s->sequence = SEQ_BLOCK_START; + + ret = dec_stream_header(s); + if (ret != XZ_OK) + return ret; + + 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->check_type == XZ_CHECK_CRC32) { + ret = crc32_validate(s, b); + if (ret != XZ_STREAM_END) + return ret; + } +#ifdef XZ_DEC_ANY_CHECK + else if (!check_skip(s, b)) { + return XZ_OK; + } +#endif + + 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). + */ +XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_run(struct xz_dec *s, struct xz_buf *b) +{ + size_t in_start; + size_t out_start; + enum xz_ret ret; + + if (DEC_IS_SINGLE(s->mode)) + xz_dec_reset(s); + + in_start = b->in_pos; + out_start = b->out_pos; + ret = dec_main(s, b); + + if (DEC_IS_SINGLE(s->mode)) { + 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; +} + +XZ_EXTERN struct xz_dec * XZ_FUNC xz_dec_init( + enum xz_mode mode, uint32_t dict_max) +{ + struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + s->mode = mode; + +#ifdef XZ_DEC_BCJ + s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode)); + if (s->bcj == NULL) + goto error_bcj; +#endif + + s->lzma2 = xz_dec_lzma2_create(mode, 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; +} + +XZ_EXTERN void XZ_FUNC xz_dec_reset(struct xz_dec *s) +{ + s->sequence = SEQ_STREAM_HEADER; + s->allow_buf_error = false; + s->pos = 0; + s->crc32 = 0; + memzero(&s->block, sizeof(s->block)); + memzero(&s->index, sizeof(s->index)); + s->temp.pos = 0; + s->temp.size = STREAM_HEADER_SIZE; +} + +XZ_EXTERN void XZ_FUNC 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); + } +} diff --git a/src/bled/xz_lzma2.h b/src/bled/xz_lzma2.h new file mode 100644 index 00000000..47f21afb --- /dev/null +++ b/src/bled/xz_lzma2.h @@ -0,0 +1,204 @@ +/* + * LZMA2 definitions + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_LZMA2_H +#define XZ_LZMA2_H + +/* 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 XZ_FUNC 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 diff --git a/src/bled/xz_private.h b/src/bled/xz_private.h new file mode 100644 index 00000000..145649a8 --- /dev/null +++ b/src/bled/xz_private.h @@ -0,0 +1,159 @@ +/* + * Private includes and definitions + * + * Author: Lasse Collin + * + * 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__ + /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ +# ifndef XZ_PREBOOT +# include +# include +# include +# define memeq(a, b, size) (memcmp(a, b, size) == 0) +# define memzero(buf, size) memset(buf, 0, size) +# endif +# include +# include +# define get_le32(p) le32_to_cpup((const uint32_t *)(p)) + /* XZ_IGNORE_KCONFIG may be defined only via decompress_unxz.c. */ +# ifndef XZ_IGNORE_KCONFIG +# 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 +# endif +# include +#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_FUNC 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_FUNC 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_FUNC 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_FUNC 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_FUNC 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_FUNC 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_FUNC 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 diff --git a/src/bled/xz_stream.h b/src/bled/xz_stream.h new file mode 100644 index 00000000..6dc9d1f9 --- /dev/null +++ b/src/bled/xz_stream.h @@ -0,0 +1,62 @@ +/* + * Definitions for handling the .xz file format + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_STREAM_H +#define XZ_STREAM_H + +#if defined(__KERNEL__) && !XZ_INTERNAL_CRC32 +# include +# undef crc32 +# define xz_crc32(buf, size, crc) \ + (~crc32_le(~(uint32_t)(crc), buf, size)) +#endif + +/* + * 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 "\xFD" "7zXZ" +#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 indicating that the value is unknown. + * + * Experimental: vli_type can be defined to uint32_t to save a few bytes + * in code size (no effect on speed). Doing so limits the uncompressed and + * compressed size of the file to less than 256 MiB and may also weaken + * error detection slightly. + */ +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) + +/* Integrity Check types */ +enum xz_check { + XZ_CHECK_NONE = 0, + XZ_CHECK_CRC32 = 1, + XZ_CHECK_CRC64 = 4, + XZ_CHECK_SHA256 = 10 +}; + +/* Maximum possible Check ID */ +#define XZ_CHECK_MAX 15 + +#endif diff --git a/src/format.c b/src/format.c index 4161a8b1..031cfb4c 100644 --- a/src/format.c +++ b/src/format.c @@ -45,11 +45,12 @@ #include "format.h" #include "badblocks.h" #include "localization.h" +#include "bled/bled.h" /* * Globals */ -DWORD FormatStatus; +DWORD FormatStatus, LastRefresh; badblocks_report report; static float format_percent = 0.0f; static int task_number = 0; @@ -374,7 +375,7 @@ static DWORD GetFATSizeSectors(DWORD DskSize, DWORD ReservedSecCnt, DWORD SecPer static BOOL FormatFAT32(DWORD DriveIndex) { BOOL r = FALSE; - DWORD i, LastRefresh = 0; + DWORD i; HANDLE hLogicalVolume; DWORD cbRet; DISK_GEOMETRY dgDrive; @@ -412,6 +413,7 @@ static BOOL FormatFAT32(DWORD DriveIndex) ULONGLONG FatNeeded, ClusterCount; PrintStatus(0, TRUE, MSG_222, "Large FAT32"); + LastRefresh = 0; VolumeId = GetVolumeID(); // Open the drive and lock it @@ -1256,6 +1258,16 @@ DWORD WINAPI CloseFormatPromptThread(LPVOID param) { ExitThread(0); } +void update_progress(const uint64_t processed_bytes) +{ + if (GetTickCount() > LastRefresh + 25) { + LastRefresh = GetTickCount(); + format_percent = (100.0f*processed_bytes)/(1.0f*iso_report.projected_size); + PrintStatus(0, FALSE, MSG_261, format_percent); + UpdateProgress(OP_FORMAT, format_percent); + } +} + /* * Standalone thread for the formatting operation * According to http://msdn.microsoft.com/en-us/library/windows/desktop/aa364562.aspx @@ -1273,7 +1285,7 @@ DWORD WINAPI FormatThread(void* param) int i, r, pt, bt, fs, dt; BOOL s, ret, use_large_fat32, add_uefi_togo; const DWORD SectorSize = SelectedDrive.Geometry.BytesPerSector; - DWORD rSize, wSize, BufSize, LastRefresh = 0, DriveIndex = (DWORD)(uintptr_t)param; + DWORD rSize, wSize, BufSize, DriveIndex = (DWORD)(uintptr_t)param; HANDLE hPhysicalDrive = INVALID_HANDLE_VALUE; HANDLE hLogicalVolume = INVALID_HANDLE_VALUE; HANDLE hSourceImage = INVALID_HANDLE_VALUE; @@ -1454,63 +1466,71 @@ DWORD WINAPI FormatThread(void* param) FormatStatus = ERROR_SEVERITY_ERROR|FAC(FACILITY_STORAGE)|ERROR_OPEN_FAILED; goto out; } + LastRefresh = 0; - uprintf("Writing Image..."); - // Our buffer size must be a multiple of the sector size - BufSize = ((DD_BUFFER_SIZE + SectorSize - 1) / SectorSize) * SectorSize; - buffer = (uint8_t*)malloc(BufSize + SectorSize); // +1 sector for align - if (buffer == NULL) { - FormatStatus = ERROR_SEVERITY_ERROR|FAC(FACILITY_STORAGE)|ERROR_NOT_ENOUGH_MEMORY; - uprintf("could not allocate DD buffer"); - goto out; - } - // http://msdn.microsoft.com/en-us/library/windows/desktop/aa365747.aspx does buffer sector alignment - aligned_buffer = ((void *) ((((uintptr_t)(buffer)) + (SectorSize) - 1) & (~(((uintptr_t)(SectorSize)) - 1)))); - - // Don't bother trying for something clever, using double buffering overlapped and whatnot: - // With Windows' default optimizations, sync read + sync write for sequential operations - // will be as fast, if not faster, than whatever async scheme you can come up with. - for (wb = 0, wSize = 0; ; wb += wSize) { - s = ReadFile(hSourceImage, aligned_buffer, BufSize, &rSize, NULL); - if (!s) { - FormatStatus = ERROR_SEVERITY_ERROR|FAC(FACILITY_STORAGE)|ERROR_READ_FAULT; - uprintf("read error: %s", WindowsErrorString()); + if (iso_report.compression_type != BLED_COMPRESSION_NONE) { + uprintf("Writing Compressed Image..."); + bled_init(_uprintf, update_progress); + bled_uncompress_with_handles(hSourceImage, hPhysicalDrive, iso_report.compression_type); + bled_exit(); + } else { + uprintf("Writing Image..."); + // Our buffer size must be a multiple of the sector size + BufSize = ((DD_BUFFER_SIZE + SectorSize - 1) / SectorSize) * SectorSize; + buffer = (uint8_t*)malloc(BufSize + SectorSize); // +1 sector for align + if (buffer == NULL) { + FormatStatus = ERROR_SEVERITY_ERROR|FAC(FACILITY_STORAGE)|ERROR_NOT_ENOUGH_MEMORY; + uprintf("could not allocate DD buffer"); goto out; } - if (rSize == 0) - break; - if (GetTickCount() > LastRefresh + 25) { - LastRefresh = GetTickCount(); - format_percent = (100.0f*wb)/(1.0f*iso_report.projected_size); - PrintStatus(0, FALSE, MSG_261, format_percent); - UpdateProgress(OP_FORMAT, format_percent); - } - // Don't overflow our projected size (mostly for VHDs) - if (wb + rSize > iso_report.projected_size) { - rSize = (DWORD)(iso_report.projected_size - wb); - } - // WriteFile fails unless the size is a multiple of sector size - if (rSize % SectorSize != 0) - rSize = ((rSize + SectorSize -1) / SectorSize) * SectorSize; - for (i=0; i LastRefresh + 25) { + LastRefresh = GetTickCount(); + format_percent = (100.0f*wb)/(1.0f*iso_report.projected_size); + PrintStatus(0, FALSE, MSG_261, format_percent); + UpdateProgress(OP_FORMAT, format_percent); + } + // Don't overflow our projected size (mostly for VHDs) + if (wb + rSize > iso_report.projected_size) { + rSize = (DWORD)(iso_report.projected_size - wb); + } + // WriteFile fails unless the size is a multiple of sector size + if (rSize % SectorSize != 0) + rSize = ((rSize + SectorSize -1) / SectorSize) * SectorSize; + for (i=0; i= WRITE_RETRIES) goto out; } - if (i >= WRITE_RETRIES) goto out; } // If the image contains a partition we might be able to access, try to re-mount it @@ -1739,7 +1759,7 @@ out: DWORD WINAPI SaveImageThread(void* param) { BOOL s; - DWORD rSize, wSize, LastRefresh = 0, DriveIndex = (DWORD)(uintptr_t)param; + DWORD rSize, wSize, DriveIndex = (DWORD)(uintptr_t)param; HANDLE hPhysicalDrive = INVALID_HANDLE_VALUE; HANDLE hDestImage = INVALID_HANDLE_VALUE; LARGE_INTEGER li; @@ -1748,6 +1768,7 @@ DWORD WINAPI SaveImageThread(void* param) int i; PrintStatus(0, TRUE, MSG_225); + LastRefresh = 0; hPhysicalDrive = GetPhysicalHandle(DriveIndex, FALSE, TRUE); if (hPhysicalDrive == INVALID_HANDLE_VALUE) { FormatStatus = ERROR_SEVERITY_ERROR|FAC(FACILITY_STORAGE)|ERROR_OPEN_FAILED; diff --git a/src/msapi_utf8.h b/src/msapi_utf8.h index aec92faa..704d08c6 100644 --- a/src/msapi_utf8.h +++ b/src/msapi_utf8.h @@ -3,7 +3,7 @@ * Compensating for what Microsoft should have done a long long time ago. * Also see http://utf8everywhere.org/ * - * Copyright © 2010-2013 Pete Batard + * Copyright © 2010-2014 Pete Batard * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -28,6 +28,7 @@ #include #include #include +#include #pragma once #if defined(_MSC_VER) @@ -721,6 +722,15 @@ static __inline FILE* fopenU(const char* filename, const char* mode) return ret; } +static __inline int _openU(const char *filename, int oflag , int pmode) +{ + int ret = -1; + wconvert(filename); + ret = _wopen(wfilename, oflag, pmode); + wfree(filename); + return ret; +} + // returned UTF-8 string must be freed static __inline char* getenvU(const char* varname) { diff --git a/src/msvc-missing/stdbool.h b/src/msvc-missing/stdbool.h new file mode 100644 index 00000000..ab4eccc3 --- /dev/null +++ b/src/msvc-missing/stdbool.h @@ -0,0 +1,16 @@ +/* Workaround stdbool.h for WDK compilers - Public Domain */ + +#include + +#ifndef _STDBOOL +#define _STDBOOL + +#ifndef __cplusplus + +#define bool BOOL +#define false FALSE +#define true TRUE + +#endif + +#endif diff --git a/src/rufus.c b/src/rufus.c index 1550057e..cb656f80 100644 --- a/src/rufus.c +++ b/src/rufus.c @@ -41,6 +41,7 @@ #include "drive.h" #include "registry.h" #include "localization.h" +#include "bled/bled.h" /* Redefinitions for WDK and MinGW */ // TODO: these would be better in a 'missing.h' file @@ -1637,6 +1638,7 @@ void SetBoot(int fs, int bt) /* * Main dialog callback */ +extern int uncompress(const char* src, const char* dst, int type); static INT_PTR CALLBACK MainCallback(HWND hDlg, UINT message, WPARAM wParam, LPARAM lParam) { DRAWITEMSTRUCT* pDI; diff --git a/src/rufus.h b/src/rufus.h index 9a723cfd..e4021275 100644 --- a/src/rufus.h +++ b/src/rufus.h @@ -240,6 +240,7 @@ typedef struct { char cfg_path[128]; /* path to the ISO's isolinux.cfg */ char reactos_path[128]; /* path to the ISO's freeldr.sys or setupldr.sys */ uint64_t projected_size; + uint64_t src_size; // TODO: use a bitmask and #define tests for the following uint8_t winpe; BOOL has_4GB_file; @@ -257,6 +258,7 @@ typedef struct { BOOL has_kolibrios; BOOL uses_minint; BOOL is_bootable_img; + BOOL compression_type; BOOL is_vhd; uint16_t sl_version; // Syslinux/Isolinux version char sl_version_str[12]; diff --git a/src/rufus.rc b/src/rufus.rc index c05a50dd..e516f85a 100644 --- a/src/rufus.rc +++ b/src/rufus.rc @@ -32,7 +32,7 @@ LANGUAGE LANG_NEUTRAL, SUBLANG_NEUTRAL IDD_DIALOG DIALOGEX 12, 12, 242, 329 STYLE DS_SETFONT | DS_MODALFRAME | DS_CENTER | WS_MINIMIZEBOX | WS_POPUP | WS_CAPTION | WS_SYSMENU -CAPTION "Rufus 1.5.0.562" +CAPTION "Rufus 1.5.0.563" FONT 8, "Segoe UI", 400, 0, 0x1 BEGIN DEFPUSHBUTTON "Start",IDC_START,127,291,50,14 @@ -164,7 +164,7 @@ END IDD_DIALOG_XP DIALOGEX 12, 12, 242, 329 STYLE DS_SETFONT | DS_MODALFRAME | DS_CENTER | WS_MINIMIZEBOX | WS_POPUP | WS_CAPTION | WS_SYSMENU -CAPTION "Rufus 1.5.0.562" +CAPTION "Rufus 1.5.0.563" FONT 8, "MS Shell Dlg", 400, 0, 0x1 BEGIN DEFPUSHBUTTON "Start",IDC_START,127,291,50,14 @@ -297,7 +297,7 @@ END IDD_DIALOG_RTL DIALOGEX 12, 12, 242, 329 STYLE DS_SETFONT | DS_MODALFRAME | DS_CENTER | WS_MINIMIZEBOX | WS_POPUP | WS_CAPTION | WS_SYSMENU EXSTYLE WS_EX_RTLREADING | WS_EX_APPWINDOW | WS_EX_LAYOUTRTL -CAPTION "Rufus 1.5.0.562" +CAPTION "Rufus 1.5.0.563" FONT 8, "Segoe UI", 400, 0, 0x1 BEGIN DEFPUSHBUTTON "Start",IDC_START,127,291,50,14 @@ -437,7 +437,7 @@ END IDD_DIALOG_RTL_XP DIALOGEX 12, 12, 242, 329 STYLE DS_SETFONT | DS_MODALFRAME | DS_CENTER | WS_MINIMIZEBOX | WS_POPUP | WS_CAPTION | WS_SYSMENU EXSTYLE WS_EX_RTLREADING | WS_EX_APPWINDOW | WS_EX_LAYOUTRTL -CAPTION "Rufus 1.5.0.562" +CAPTION "Rufus 1.5.0.563" FONT 8, "MS Shell Dlg", 400, 0, 0x1 BEGIN DEFPUSHBUTTON "Start",IDC_START,127,291,50,14 @@ -703,8 +703,8 @@ END // VS_VERSION_INFO VERSIONINFO - FILEVERSION 1,5,0,562 - PRODUCTVERSION 1,5,0,562 + FILEVERSION 1,5,0,563 + PRODUCTVERSION 1,5,0,563 FILEFLAGSMASK 0x3fL #ifdef _DEBUG FILEFLAGS 0x1L @@ -721,13 +721,13 @@ BEGIN BEGIN VALUE "CompanyName", "Akeo Consulting (http://akeo.ie)" VALUE "FileDescription", "Rufus" - VALUE "FileVersion", "1.5.0.562" + VALUE "FileVersion", "1.5.0.563" VALUE "InternalName", "Rufus" VALUE "LegalCopyright", "© 2011-2014 Pete Batard (GPL v3)" VALUE "LegalTrademarks", "http://www.gnu.org/copyleft/gpl.html" VALUE "OriginalFilename", "rufus.exe" VALUE "ProductName", "Rufus" - VALUE "ProductVersion", "1.5.0.562" + VALUE "ProductVersion", "1.5.0.563" END END BLOCK "VarFileInfo" diff --git a/src/vhd.c b/src/vhd.c index afe68ab5..31c2925e 100644 --- a/src/vhd.c +++ b/src/vhd.c @@ -27,6 +27,7 @@ #include "msapi_utf8.h" #include "drive.h" #include "registry.h" +#include "bled/bled.h" #if defined(_MSC_VER) #define bswap_uint64 _byteswap_uint64 @@ -211,6 +212,43 @@ out: return r; } +typedef struct { + const char* ext; + bled_compression_type type; +} comp_assoc; + +static comp_assoc blah[] = { + { ".xz", BLED_COMPRESSION_XZ }, + { ".gz", BLED_COMPRESSION_GZIP }, + { ".lzma", BLED_COMPRESSION_LZMA }, + { ".bz2", BLED_COMPRESSION_BZIP2 }, + { ".Z", BLED_COMPRESSION_LZW }, +}; + +// For now we consider that an image that matches a known extension is bootable +// TODO: uncompress header and check for bootable flag +BOOL IsCompressedBootableImage(const char* path) +{ + char* p; + int i; + + iso_report.compression_type = BLED_COMPRESSION_NONE; + for (p = (char*)&path[strlen(path)-1]; (*p != '.') && (p != path); p--); + + if (p == path) + return FALSE; + + for (i = 0; i= (512 + size)) { + if ((iso_report.compression_type == BLED_COMPRESSION_NONE) && (iso_report.projected_size >= (512 + size))) { footer = (vhd_footer*)malloc(size); ptr.QuadPart = iso_report.projected_size - size; if ( (footer == NULL) || (!SetFilePointerEx(handle, ptr, NULL, FILE_BEGIN)) || diff --git a/wdk_build.cmd b/wdk_build.cmd index c0be8453..6beb863b 100644 --- a/wdk_build.cmd +++ b/wdk_build.cmd @@ -10,8 +10,23 @@ set PWD=%~dp0 set ARCH_DIR=%_BUILDARCH% if /I Test%_BUILDARCH%==Testx86 set ARCH_DIR=i386 +::# Bled Library +cd src\bled +if EXIST Makefile ren Makefile Makefile.hide + +copy .msvc\bled_sources sources >NUL 2>&1 + +@echo on +%BUILD_CMD% +@echo off +if errorlevel 1 goto builderror +copy obj%BUILD_ALT_DIR%\%ARCH_DIR%\bled.lib . >NUL 2>&1 + +if EXIST Makefile.hide ren Makefile.hide Makefile +if EXIST sources del sources >NUL 2>&1 + ::# MS-SYS Library -cd src\ms-sys +cd ..\ms-sys if EXIST Makefile ren Makefile Makefile.hide copy .msvc\ms-sys_sources sources >NUL 2>&1