Docs: Simplify SECURITY.md.

This does the previous commit with CMake.

AC_EGREP_CPP uses AC_REQUIRE so the outermost if-commands must
be changed to AS_IF to ensure that things wont break some day.
See 5a5bd7f871.

.github/SECURITY.md

@@ -16,13 +16,7 @@ the chance that the exploit will be used before a patch is released.
 You may submit a report by emailing us at
 [xz@tukaani.org](mailto:xz@tukaani.org), or through
 [Security Advisories](https://github.com/tukaani-project/xz/security/advisories/new).
-While both options are available, we prefer email. In any case, please
-provide a clear description of the vulnerability including:
-
-- Affected versions of XZ Utils
-- Estimated severity (low, moderate, high, critical)
-- Steps to recreate the vulnerability
-- All relevant files (core dumps, build logs, input files, etc.)
+While both options are available, we prefer email.
 
 This project is maintained by a team of volunteers on a reasonable-effort
 basis. As such, please give us 90 days to work on a fix before

.gitignore

@@ -67,6 +67,7 @@ coverage
 /tests/test_index
 /tests/test_index_hash
 /tests/test_lzip_decoder
+/tests/test_microlzma
 /tests/test_memlimit
 /tests/test_stream_flags
 /tests/test_vli

CMakeLists.txt

@@ -273,14 +273,48 @@ endif()
 # Translation support requires CMake 3.20 because it added the Intl::Intl
 # target so we don't need to play with the individual variables.
 #
-# The defintion ENABLE_NLS is added only to those targets that use it, thus
+# The definition ENABLE_NLS is added only to those targets that use it, thus
 # it's not done here. (xz has translations, xzdec doesn't.)
 if(CMAKE_VERSION VERSION_GREATER_EQUAL "3.20")
     find_package(Intl)
     find_package(Gettext)
+
     if(Intl_FOUND)
         option(ENABLE_NLS "Native Language Support (translated messages)" ON)
 
+        # If translation support is enabled but neither gettext tools or
+        # pre-generated .gmo files exist, translation support cannot be
+        # enabled.
+        #
+        # The detection of pre-generated .gmo files is done by only
+        # checking for the existence of a single .gmo file; Ukrainian
+        # is one of many translations that gets regular updates.
+        if(ENABLE_NLS AND NOT GETTEXT_FOUND AND
+                NOT EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/po/uk.gmo")
+            # This only sets the variable, not the cache variable!
+            set(ENABLE_NLS OFF)
+
+            # This message is shown only when new enough CMake is used and
+            # library support for translations was found. The assumptions is
+            # that in this situation the user might have interest in the
+            # translations. This also keeps this code simpler.
+            message(WARNING "Native language support (NLS) has been disabled. "
+                            "NLS support requires either gettext tools or "
+                            "pre-generated .gmo files. The latter are only "
+                            "available in distribution tarballs. "
+                            "To avoid this warning, NLS can be explicitly "
+                            "disabled by passing -DENABLE_NLS=OFF to cmake.")
+        endif()
+
+        # Warn if NLS is enabled but translated man pages are missing.
+        if(UNIX AND ENABLE_NLS AND
+                NOT EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/po4a/man")
+            message(WARNING "Native language support (NLS) has been enabled "
+                            "but pre-generated translated man pages "
+                            "were not found and thus they won't be installed. "
+                            "Run 'po4a/update-po' to generate them.")
+        endif()
+
         # The *installed* name of the translation files is "xz.mo".
         set(TRANSLATION_DOMAIN "xz")
     endif()
@@ -299,6 +333,69 @@ endif()
 
 option(BUILD_SHARED_LIBS "Build liblzma as a shared library instead of static")
 
+if(NOT WIN32)
+    # Symbol versioning only affects ELF shared libraries. The option is
+    # ignored for static libraries.
+    #
+    # Determine the default value so that it's always set with
+    # shared libraries in mind which helps if the build dir is reconfigured
+    # from static to shared libs without resetting the cache variables.
+    set(SYMBOL_VERSIONING_DEFAULT OFF)
+
+    if(CMAKE_SYSTEM_NAME STREQUAL "Linux" AND
+            (CMAKE_SYSTEM_PROCESSOR MATCHES "[Mm]icro[Bb]laze" OR
+             CMAKE_C_COMPILER_ID STREQUAL "NVHPC"))
+        # As a special case, GNU/Linux on MicroBlaze gets the generic
+        # symbol versioning because GCC 12 doesn't support the __symver__
+        # attribute on MicroBlaze. On Linux, CMAKE_SYSTEM_PROCESSOR comes
+        # from "uname -m" for native builds (should be "microblaze") or from
+        # the CMake toolchain file (not perfectly standardized but it very
+        # likely has "microblaze" in lower case or mixed case somewhere in
+        # the string).
+        #
+        # NVIDIA HPC Compiler doesn't support symbol versioning but
+        # it uses the linked from the system so the linker script
+        # can still be used to get the generic symbol versioning.
+        set(SYMBOL_VERSIONING_DEFAULT "generic")
+
+    elseif(CMAKE_SYSTEM_NAME STREQUAL "Linux")
+        # GNU/Linux-specific symbol versioning for shared liblzma.
+        # This includes a few extra compatibility symbols for RHEL/CentOS 7
+        # which are pointless on non-glibc non-Linux systems.
+        #
+        # Avoid symvers on Linux with non-glibc like musl and uClibc.
+        # In Autoconf it's enough to check that $host_os equals linux-gnu
+        # instead of, for example, linux-musl. CMake doesn't provide such
+        # a method.
+        #
+        # This check is here for now since it's not strictly required
+        # by anything else.
+        check_c_source_compiles(
+                "#include <features.h>
+                #if defined(__GLIBC__) && !defined(__UCLIBC__)
+                int main(void) { return 0; }
+                #else
+                compile error
+                #endif
+            "
+            IS_LINUX_WITH_GLIBC)
+
+        if(IS_LINUX_WITH_GLIBC)
+            set(SYMBOL_VERSIONING_DEFAULT "linux")
+        endif()
+
+    elseif(CMAKE_SYSTEM_NAME STREQUAL "FreeBSD")
+        set(SYMBOL_VERSIONING_DEFAULT "generic")
+    endif()
+
+    set(SYMBOL_VERSIONING "${SYMBOL_VERSIONING_DEFAULT}" CACHE STRING
+        "Enable ELF shared library symbol versioning (OFF, generic, linux)")
+
+    # Show a dropdown menu in CMake GUI:
+    set_property(CACHE SYMBOL_VERSIONING PROPERTY STRINGS "OFF;generic;linux")
+endif()
+
+
 add_library(liblzma
     src/common/mythread.h
     src/common/sysdefs.h
@@ -819,10 +916,6 @@ if(MICROLZMA_DECODER)
     target_sources(liblzma PRIVATE src/liblzma/common/microlzma_decoder.c)
 endif()
 
-if (MICROLZMA_ENCODER OR MICROLZMA_DECODER)
-    add_compile_definitions(HAVE_MICROLZMA)
-endif()
-
 
 #############################
 # lzip (.lz) format support #
@@ -901,10 +994,29 @@ endif()
 
 # Sandboxing: Landlock
 if(NOT SANDBOX_FOUND AND ENABLE_SANDBOX MATCHES "^ON$|^landlock$")
-    check_include_file(linux/landlock.h HAVE_LINUX_LANDLOCK_H)
+    # A compile check is done here because some systems have
+    # linux/landlock.h, but do not have the syscalls defined
+    # in order to actually use Linux Landlock.
+    check_c_source_compiles("
+        #include <linux/landlock.h>
+        #include <sys/syscall.h>
+        #include <sys/prctl.h>
+.
+        void my_sandbox(void)
+        {
+            (void)prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+            (void)SYS_landlock_create_ruleset;
+            (void)SYS_landlock_restrict_self;
+            (void)LANDLOCK_CREATE_RULESET_VERSION;
+            return;
+        }
 
-    if(HAVE_LINUX_LANDLOCK_H)
-        set(SANDBOX_COMPILE_DEFINITION "HAVE_LINUX_LANDLOCK_H")
+        int main(void) { return 0; }
+        "
+    HAVE_LINUX_LANDLOCK)
+
+    if(HAVE_LINUX_LANDLOCK)
+        set(SANDBOX_COMPILE_DEFINITION "HAVE_LINUX_LANDLOCK")
         set(SANDBOX_FOUND ON)
 
         # Of our three sandbox methods, only Landlock is incompatible
@@ -1029,6 +1141,13 @@ if(USE_ATTR_IFUNC STREQUAL "auto")
             #endif
 
             static void func(void) { return; }
+
+            /*
+            * The attribute __no_profile_instrument_function__ is
+            * needed with GCC to prevent improper instrumentation in
+            * the ifunc resolver.
+            */
+            __attribute__((__no_profile_instrument_function__))
             static void (*resolve_func(void)) (void) { return func; }
             void func_ifunc(void)
                     __attribute__((__ifunc__(\"resolve_func\")));
@@ -1220,22 +1339,7 @@ if(WIN32)
         # Disable __declspec(dllimport) when linking against static liblzma.
         target_compile_definitions(liblzma INTERFACE LZMA_API_STATIC)
     endif()
-elseif(BUILD_SHARED_LIBS AND CMAKE_SYSTEM_NAME STREQUAL "Linux" AND
-       NOT CMAKE_SYSTEM_PROCESSOR MATCHES "[Mm]icro[Bb]laze")
-    # GNU/Linux-specific symbol versioning for shared liblzma.
-    # This includes a few extra compatibility symbols for RHEL/CentOS 7
-    # which are pointless on non-glibc non-Linux systems.
-    #
-    # As a special case, GNU/Linux on MicroBlaze gets the generic
-    # symbol versioning because GCC 12 doesn't support the __symver__
-    # attribute on MicroBlaze. On Linux, CMAKE_SYSTEM_PROCESSOR comes
-    # from "uname -m" for native builds (should be "microblaze") or from
-    # the CMake toolchain file (not perfectly standardized but it very
-    # likely has "microblaze" in lower case or mixed case somewhere in
-    # the string).
-    #
-    # FIXME? Avoid symvers on Linux with non-glibc like musl?
-    #
+elseif(BUILD_SHARED_LIBS AND SYMBOL_VERSIONING STREQUAL "linux")
     # Note that adding link options doesn't affect static builds
     # but HAVE_SYMBOL_VERSIONS_LINUX must not be used with static builds
     # because it would put symbol versions into the static library which
@@ -1251,10 +1355,7 @@ elseif(BUILD_SHARED_LIBS AND CMAKE_SYSTEM_NAME STREQUAL "Linux" AND
     set_target_properties(liblzma PROPERTIES
         LINK_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/liblzma/liblzma_linux.map"
     )
-elseif(BUILD_SHARED_LIBS AND (CMAKE_SYSTEM_NAME STREQUAL "FreeBSD" OR
-                              CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-    # Generic symbol versioning for shared liblzma is used on FreeBSD and
-    # also on GNU/Linux on MicroBlaze.
+elseif(BUILD_SHARED_LIBS AND SYMBOL_VERSIONING STREQUAL "generic")
     target_link_options(liblzma PRIVATE
         "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/src/liblzma/liblzma_generic.map"
     )
@@ -1988,6 +2089,16 @@ if(BUILD_TESTING)
         test_vli
     )
 
+    # MicroLZMA encoder is needed for both encoder and decoder tests.
+    # If MicroLZMA decoder is not configured but LZMA1 decoder is, then
+    # test_microlzma will fail to compile because this configuration is
+    # not possible in the Autotools build, so the test was not made to
+    # support it since it would have required additional changes.
+    if (MICROLZMA_ENCODER AND (MICROLZMA_DECODER
+            OR NOT "lzma1" IN_LIST DECODERS))
+        list(APPEND LIBLZMA_TESTS test_microlzma)
+    endif()
+
     foreach(TEST IN LISTS LIBLZMA_TESTS)
         add_executable("${TEST}" "tests/${TEST}.c")
 

INSTALL

@@ -561,10 +561,45 @@ XZ Utils Installation
                                 sandboxing. If no Landlock support
                                 is found, configure will give an error.
 
-    --enable-symbol-versions
-                Use symbol versioning for liblzma. This is enabled by
-                default on GNU/Linux, other GNU-based systems, and
-                FreeBSD.
+    --enable-symbol-versions[=VARIANT]
+                Use symbol versioning for liblzma shared library.
+                This is enabled by default on GNU/Linux (glibc only),
+                other GNU-based systems, and FreeBSD.
+
+                Symbol versioning is never used for static liblzma. This
+                option is ignored when not building a shared library.
+
+                Supported VARIANTs:
+
+                        no      Disable symbol versioning. This is the
+                                same as using --disable-symbol-versions.
+
+                        auto    Autodetect between "no", "linux",
+                                and "generic".
+
+                        yes     Autodetect between "linux" and
+                                "generic". This forces symbol
+                                versioning to be used when
+                                building a shared library.
+
+                        generic Generic version is the default for
+                                FreeBSD and GNU/Linux on MicroBlaze.
+
+                                This is also used on GNU/Linux when
+                                building with NVIDIA HPC Compiler
+                                because the compiler doesn't support
+                                the features required for the "linux"
+                                variant below.
+
+                        linux   Special version for GNU/Linux (glibc
+                                only). This adds a few extra symbol
+                                versions for compatibility with binaries
+                                that have been linked against a liblzma
+                                version that has been patched with
+                                "xz-5.2.2-compat-libs.patch" from
+                                RHEL/CentOS 7. That patch was used
+                                by some build tools outside of
+                                RHEL/CentOS 7 too.
 
     --enable-debug
                 This enables the assert() macro and possibly some other

NEWS

@@ -2,6 +2,32 @@
 XZ Utils Release Notes
 ======================
 
+5.6.1 (2024-03-09)
+
+    * liblzma: Fixed two bugs relating to GNU indirect function (IFUNC)
+      with GCC. The more serious bug caused a program linked with
+      liblzma to crash on start up if the flag -fprofile-generate was
+      used to build liblzma. The second bug caused liblzma to falsely
+      report an invalid write to Valgrind when loading liblzma.
+
+    * xz: Changed the messages for thread reduction due to memory
+      constraints to only appear under the highest verbosity level.
+
+    * Build:
+
+        - Fixed a build issue when the header file <linux/landlock.h>
+          was present on the system but the Landlock system calls were
+          not defined in <sys/syscall.h>.
+
+        - The CMake build now warns and disables NLS if both gettext
+          tools and pre-created .gmo files are missing. Previously,
+          this caused the CMake build to fail.
+
+    * Minor improvements to man pages.
+
+    * Minor improvements to tests.
+
+
 5.6.0 (2024-02-24)
 
     This bumps the minor version of liblzma because new features were
@@ -23,7 +49,7 @@ XZ Utils Release Notes
     * Sandboxing support in xz:
 
         - Landlock is now used even when xz needs to create files.
-          In this case the sandbox is has to be more permissive than
+          In this case the sandbox has to be more permissive than
           when no files need to be created. A similar thing was
           already in use with pledge(2) since 5.3.4alpha.
 

THANKS

@@ -76,6 +76,7 @@ has been important. :-) In alphabetical order:
   - Richard Koch
   - Anton Kochkov
   - Ville Koskinen
+  - Sergey Kosukhin
   - Marcin Kowalczyk
   - Jan Kratochvil
   - Christian Kujau
@@ -152,9 +153,9 @@ has been important. :-) In alphabetical order:
   - Dan Stromberg
   - Jia Tan
   - Vincent Torri
+  - Alexey Tourbin
   - Paul Townsend
   - Mohammed Adnène Trojette
-  - Alexey Tourbin
   - Taiki Tsunekawa
   - Maksym Vatsyk
   - Loganaden Velvindron
@@ -171,6 +172,7 @@ has been important. :-) In alphabetical order:
   - Charles Wilson
   - Lars Wirzenius
   - Pilorz Wojciech
+  - Chien Wong
   - Ryan Young
   - Andreas Zieringer
 

configure.ac

@@ -304,13 +304,8 @@ AC_ARG_ENABLE([microlzma], AS_HELP_STRING([--disable-microlzma],
 		for example, erofs-utils.]),
 	[], [enable_microlzma=yes])
 case $enable_microlzma in
-	yes)
-		AC_DEFINE([HAVE_MICROLZMA], [1],
-			[Define to 1 if MicroLZMA support is enabled.])
-		AC_MSG_RESULT([yes])
-		;;
-	no)
-		AC_MSG_RESULT([no])
+	yes | no)
+		AC_MSG_RESULT([$enable_microlzma])
 		;;
 	*)
 		AC_MSG_RESULT([])
@@ -714,23 +709,44 @@ fi
 # --with-pic and --without-pic though. As long as neither --with-pic nor
 # --without-pic is used then we can use #ifdef PIC to detect if the file is
 # being built for a shared library.
-if test "x$enable_symbol_versions" = xno ; then
+AS_IF([test "x$enable_symbol_versions" = xno], [
 	enable_symbol_versions=no
 	AC_MSG_RESULT([no])
-elif test "x$enable_shared" = xno ; then
+], [test "x$enable_shared" = xno], [
 	enable_symbol_versions=no
 	AC_MSG_RESULT([no (not building a shared library)])
-else
+], [
+	# "yes" means that symbol version are to be used but we need to
+	# autodetect which variant to use.
+	if test "x$enable_symbol_versions" = xyes ; then
 		case "$host_cpu-$host_os" in
 			microblaze*)
-			# GCC 12 on MicroBlaze doesn't support __symver__
-			# attribute. It's simplest and safest to use the
-			# generic version on that platform since then only
-			# the linker script is needed. The RHEL/CentOS 7
-			# compatibility symbols don't matter on MicroBlaze.
+				# GCC 12 on MicroBlaze doesn't support
+				# __symver__ attribute. It's simplest and
+				# safest to use the generic version on that
+				# platform since then only the linker script
+				# is needed. The RHEL/CentOS 7 compatibility
+				# symbols don't matter on MicroBlaze.
 				enable_symbol_versions=generic
 				;;
 			*-linux*)
+				# NVIDIA HPC Compiler doesn't support symbol
+				# versioning but the linker script can still
+				# be used.
+				AC_EGREP_CPP([use_generic_symbol_versioning],
+					[#ifdef __NVCOMPILER
+					use_generic_symbol_versioning
+					#endif],
+					[enable_symbol_versions=generic],
+					[enable_symbol_versions=linux])
+				;;
+			*)
+				enable_symbol_versions=generic
+				;;
+		esac
+	fi
+
+	if test "x$enable_symbol_versions" = xlinux ; then
 		case "$pic_mode-$enable_static" in
 			default-*)
 				# Use symvers if PIC is defined.
@@ -751,7 +767,6 @@ else
     possibly picking only src/liblzma/.libs/liblzma.a from the static build.])
 				;;
 		esac
-			enable_symbol_versions=linux
 		AC_DEFINE_UNQUOTED([HAVE_SYMBOL_VERSIONS_LINUX],
 			[$have_symbol_versions_linux],
 			[Define to 1 to if GNU/Linux-specific details
@@ -762,13 +777,12 @@ else
 			time with Libtool if neither --with-pic nor
 			--without-pic is used). This define must be
 			used together with liblzma_linux.map.])
-			;;
-		*)
-			enable_symbol_versions=generic
-			;;
-	esac
+	elif test "x$enable_symbol_versions" != xgeneric ; then
+		AC_MSG_RESULT([])
+		AC_MSG_ERROR([unknown symbol versioning variant '$enable_symbol_versions'])
+	fi
 	AC_MSG_RESULT([yes ($enable_symbol_versions)])
-fi
+])
 
 AM_CONDITIONAL([COND_SYMVERS_LINUX],
 	[test "x$enable_symbol_versions" = xlinux])
@@ -915,6 +929,13 @@ if test "x$enable_ifunc" = xauto ; then
 		#endif
 
 		static void func(void) { return; }
+
+		/*
+		 * The attribute __no_profile_instrument_function__ is
+		 * needed with GCC to prevent improper instrumentation in
+		 * the ifunc resolver.
+		 */
+		__attribute__((__no_profile_instrument_function__))
 		static void (*resolve_func (void)) (void) { return func; }
 		void func_ifunc (void)
 				__attribute__((__ifunc__("resolve_func")));
@@ -1177,12 +1198,37 @@ AS_CASE([$enable_sandbox],
 )
 AS_CASE([$enable_sandbox],
 	[auto | landlock], [
-		AC_CHECK_HEADERS([linux/landlock.h], [
+		AC_MSG_CHECKING([if Linux Landlock is usable])
+
+		# A compile check is done here because some systems have
+		# linux/landlock.h, but do not have the syscalls defined
+		# in order to actually use Linux Landlock.
+		AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
+			#include <linux/landlock.h>
+			#include <sys/syscall.h>
+			#include <sys/prctl.h>
+
+			void my_sandbox(void)
+			{
+				(void)prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+				(void)SYS_landlock_create_ruleset;
+				(void)SYS_landlock_restrict_self;
+				(void)LANDLOCK_CREATE_RULESET_VERSION;
+				return;
+			}
+		]])], [
 			enable_sandbox=found
 
 			AS_CASE([$CFLAGS], [*-fsanitize=*], [AC_MSG_ERROR([
     CFLAGS contains '-fsanitize=' which is incompatible with the Landlock
     sandboxing. Use --disable-sandbox when using '-fsanitize'.])])
+
+			AC_DEFINE([HAVE_LINUX_LANDLOCK], [1],
+				[Define to 1 if Linux Landlock is supported.
+				See configure.ac for details.])
+			AC_MSG_RESULT([yes])
+		], [
+			AC_MSG_RESULT([no])
 		])
 	]
 )

src/liblzma/Makefile.am

@@ -20,7 +20,7 @@ liblzma_la_CPPFLAGS = \
 	-I$(top_srcdir)/src/liblzma/simple \
 	-I$(top_srcdir)/src/common \
 	-DTUKLIB_SYMBOL_PREFIX=lzma_
-liblzma_la_LDFLAGS = -no-undefined -version-info 10:99:5
+liblzma_la_LDFLAGS = -no-undefined -version-info 11:99:6
 
 EXTRA_DIST += liblzma_generic.map liblzma_linux.map validate_map.sh
 if COND_SYMVERS_GENERIC

src/liblzma/api/lzma/version.h

@@ -19,10 +19,10 @@
 #define LZMA_VERSION_MAJOR 5
 
 /** \brief Minor version number of the liblzma release. */
-#define LZMA_VERSION_MINOR 5
+#define LZMA_VERSION_MINOR 7
 
 /** \brief Patch version number of the liblzma release. */
-#define LZMA_VERSION_PATCH 2
+#define LZMA_VERSION_PATCH 0
 
 /**
  * \brief Version stability marker
@@ -32,7 +32,7 @@
  *   - LZMA_VERSION_STABILITY_BETA
  *   - LZMA_VERSION_STABILITY_STABLE
  */
-#define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_BETA
+#define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_ALPHA
 
 /** \brief Commit version number of the liblzma release */
 #ifndef LZMA_VERSION_COMMIT

src/liblzma/check/crc32_fast.c

@@ -135,6 +135,8 @@ typedef uint32_t (*crc32_func_type)(
 // This resolver is shared between all three dispatch methods. It serves as
 // the ifunc resolver if ifunc is supported, otherwise it is called as a
 // regular function by the constructor or first call resolution methods.
+// The function attributes are needed for safe IFUNC resolver usage with GCC.
+lzma_resolver_attributes
 static crc32_func_type
 crc32_resolve(void)
 {

src/liblzma/check/crc64_fast.c

@@ -98,6 +98,7 @@ typedef uint64_t (*crc64_func_type)(
 #	pragma GCC diagnostic ignored "-Wunused-function"
 #endif
 
+lzma_resolver_attributes
 static crc64_func_type
 crc64_resolve(void)
 {

src/liblzma/check/crc_common.h

@@ -128,6 +128,31 @@
 #	endif
 #endif
 
+#ifdef CRC_USE_IFUNC
+// Two function attributes are needed to make IFUNC safe with GCC.
+//
+// no-omit-frame-pointer prevents false Valgrind issues when combined with
+// a few other compiler flags. The optimize attribute is supported on
+// GCC >= 4.4 and is not supported with Clang.
+#	if TUKLIB_GNUC_REQ(4,4) && !defined(__clang__)
+#		define no_omit_frame_pointer \
+			__attribute__((optimize("no-omit-frame-pointer")))
+#	else
+#		define no_omit_frame_pointer
+#	endif
+
+// The __no_profile_instrument_function__ attribute support is checked when
+// determining if ifunc can be used, so it is safe to use unconditionally.
+// This attribute is needed because GCC can add profiling to the IFUNC
+// resolver, which calls functions that have not yet been relocated leading
+// to a crash on liblzma start up.
+#	define lzma_resolver_attributes \
+		__attribute__((__no_profile_instrument_function__)) \
+		no_omit_frame_pointer
+#else
+#	define lzma_resolver_attributes
+#endif
+
 // For CRC32 use the generic slice-by-eight implementation if no optimized
 // version is available.
 #if !defined(CRC32_ARCH_OPTIMIZED) && !defined(CRC32_GENERIC)

src/liblzma/common/memcmplen.h

@@ -67,6 +67,19 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2,
 	// This is only for x86-64 and ARM64 for now. This might be fine on
 	// other 64-bit processors too. On big endian one should use xor
 	// instead of subtraction and switch to __builtin_clzll().
+	//
+	// Reasons to use subtraction instead of xor:
+	//
+	//   - On some x86-64 processors (Intel Sandy Bridge to Tiger Lake),
+	//     sub+jz and sub+jnz can be fused but xor+jz or xor+jnz cannot.
+	//     Thus using subtraction has potential to be a tiny amount faster
+	//     since the code checks if the quotient is non-zero.
+	//
+	//   - Some processors (Intel Pentium 4) used to have more ALU
+	//     resources for add/sub instructions than and/or/xor.
+	//
+	// The processor info is based on Agner Fog's microarchitecture.pdf
+	// version 2023-05-26. https://www.agner.org/optimize/
 #define LZMA_MEMCMPLEN_EXTRA 8
 	while (len < limit) {
 		const uint64_t x = read64ne(buf1 + len) - read64ne(buf2 + len);

src/liblzma/common/string_conversion.c

@@ -217,12 +217,14 @@ typedef struct {
 	uint16_t offset;
 
 	union {
+		// NVHPC has problems with unions that contain pointers that
+		// are not the first members, so keep "map" at the top.
+		const name_value_map *map;
+
 		struct {
 			uint32_t min;
 			uint32_t max;
 		} range;
-
-		const name_value_map *map;
 	} u;
 } option_map;
 

src/liblzma/delta/delta_decoder.c

@@ -25,6 +25,11 @@ decode_buffer(lzma_delta_coder *coder, uint8_t *buffer, size_t size)
 }
 
 
+// For an unknown reason NVIDIA HPC Compiler needs this pragma
+// to produce working code.
+#ifdef __NVCOMPILER
+#	pragma routine novector
+#endif
 static lzma_ret
 delta_decode(void *coder_ptr, const lzma_allocator *allocator,
 		const uint8_t *restrict in, size_t *restrict in_pos,

src/liblzma/liblzma_generic.map

@@ -122,7 +122,7 @@ global:
 	lzma_str_to_filters;
 } XZ_5.2;
 
-XZ_5.5.2beta {
+XZ_5.6.0 {
 global:
 	lzma_mt_block_size;
 } XZ_5.4;

src/liblzma/liblzma_linux.map

@@ -137,7 +137,7 @@ global:
 	lzma_str_to_filters;
 } XZ_5.2;
 
-XZ_5.5.2beta {
+XZ_5.6.0 {
 global:
 	lzma_mt_block_size;
 } XZ_5.4;

src/liblzma/rangecoder/range_decoder.h

@@ -45,6 +45,7 @@
 //     and different processors. Overall 0x1F0 seems to be the best choice.
 #ifndef LZMA_RANGE_DECODER_CONFIG
 #	if defined(__x86_64__) && !defined(__ILP32__) \
+			&& !defined(__NVCOMPILER) \
 			&& (defined(__GNUC__) || defined(__clang__))
 #		define LZMA_RANGE_DECODER_CONFIG 0x1F0
 #	else

src/liblzma/simple/riscv.c

@@ -116,7 +116,7 @@ AUIPC with rd != x0
         Zfh, F, D, and Q:
           * RV32I: LB, LH, LW, LBU, LHU, SB, SH, SW
           * RV64I has also: LD, LWU, SD
-          * Zhf: FLH, FSH
+          * Zfh: FLH, FSH
           * F: FLW, FSW
           * D: FLD, FSD
           * Q: FLQ, FSQ
@@ -320,11 +320,11 @@ AUIPC with rd == x0
 // The left-hand side takes care of (1) and (2).
 //   (a) The lowest 7 bits are already known to be AUIPC so subtracting 0x17
 //       makes those bits zeros.
-//   (b) If AUIPC rd equals x2, subtracting 0x10 makes bits [11:7] zeros.
+//   (b) If AUIPC rd equals x2, subtracting 0x100 makes bits [11:7] zeros.
 //       If rd doesn't equal x2, then there will be at least one non-zero bit
 //       and the next step (c) is irrelevant.
 //   (c) If the lowest two opcode bits of the packed inst2 are set in [13:12],
-//       then subtracting 0x300 will make those bits zeros. Otherwise there
+//       then subtracting 0x3000 will make those bits zeros. Otherwise there
 //       will be at least one non-zero bit.
 //
 // The shift by 18 removes the high bits from the final '>=' comparison and

src/xz/coder.c

@@ -581,7 +581,14 @@ coder_set_compression_settings(void)
 
 			if (memory_usage <= memory_limit) {
 				// The memory usage is now low enough.
-				message(V_WARNING, _("Reduced the number of "
+				//
+				// Since 5.6.1: This is only shown at
+				// V_DEBUG instead of V_WARNING because
+				// changing the number of threads doesn't
+				// affect the output. On some systems this
+				// message would be too common now that
+				// multithreaded compression is the default.
+				message(V_DEBUG, _("Reduced the number of "
 					"threads from %s to %s to not exceed "
 					"the memory usage limit of %s MiB"),
 					uint64_to_str(
@@ -600,8 +607,11 @@ coder_set_compression_settings(void)
 		// way -T0 won't use insane amount of memory but at the same
 		// time the soft limit will never make xz fail and never make
 		// xz change settings that would affect the compressed output.
+		//
+		// Since 5.6.1: Like above, this is now shown at V_DEBUG
+		// instead of V_WARNING.
 		if (hardware_memlimit_mtenc_is_default()) {
-			message(V_WARNING, _("Reduced the number of threads "
+			message(V_DEBUG, _("Reduced the number of threads "
 				"from %s to one. The automatic memory usage "
 				"limit of %s MiB is still being exceeded. "
 				"%s MiB of memory is required. "

src/xz/sandbox.c

@@ -109,7 +109,7 @@ sandbox_enable_strict_if_allowed(int src_fd lzma_attribute((__unused__)),
 }
 
 
-#elif defined(HAVE_LINUX_LANDLOCK_H)
+#elif defined(HAVE_LINUX_LANDLOCK)
 
 //////////////
 // Landlock //

src/xz/sandbox.h

@@ -9,7 +9,7 @@
 //
 ///////////////////////////////////////////////////////////////////////////////
 
-#if defined(HAVE_PLEDGE) || defined(HAVE_LINUX_LANDLOCK_H) \
+#if defined(HAVE_PLEDGE) || defined(HAVE_LINUX_LANDLOCK) \
 		|| defined(HAVE_CAP_RIGHTS_LIMIT)
 #	define ENABLE_SANDBOX 1
 #endif

src/xz/xz.1

@@ -4,7 +4,7 @@
 .\" Authors: Lasse Collin
 .\"          Jia Tan
 .\"
-.TH XZ 1 "2024-02-13" "Tukaani" "XZ Utils"
+.TH XZ 1 "2024-02-25" "Tukaani" "XZ Utils"
 .
 .SH NAME
 xz, unxz, xzcat, lzma, unlzma, lzcat \- Compress or decompress .xz and .lzma files
@@ -1812,6 +1812,8 @@ and
 \fB\-\-ia64\fR[\fB=\fIoptions\fR]
 .TP
 \fB\-\-sparc\fR[\fB=\fIoptions\fR]
+.TP
+\fB\-\-riscv\fR[\fB=\fIoptions\fR]
 .PD
 Add a branch/call/jump (BCJ) filter to the filter chain.
 These filters can be used only as a non-last filter

src/xzdec/xzdec.c

@@ -24,14 +24,14 @@
 #	include <sys/capsicum.h>
 #endif
 
-#ifdef HAVE_LINUX_LANDLOCK_H
+#ifdef HAVE_LINUX_LANDLOCK
 #	include <linux/landlock.h>
 #	include <sys/prctl.h>
 #	include <sys/syscall.h>
 #endif
 
 #if defined(HAVE_CAP_RIGHTS_LIMIT) || defined(HAVE_PLEDGE) \
-		|| defined(HAVE_LINUX_LANDLOCK_H)
+		|| defined(HAVE_LINUX_LANDLOCK)
 #	define ENABLE_SANDBOX 1
 #endif
 
@@ -325,7 +325,7 @@ sandbox_enter(int src_fd)
 		goto error;
 
 	(void)src_fd;
-#elif defined(HAVE_LINUX_LANDLOCK_H)
+#elif defined(HAVE_LINUX_LANDLOCK)
 	int landlock_abi = syscall(SYS_landlock_create_ruleset,
 			(void *)NULL, 0, LANDLOCK_CREATE_RULESET_VERSION);
 
@@ -389,7 +389,7 @@ main(int argc, char **argv)
 	}
 #endif
 
-#ifdef HAVE_LINUX_LANDLOCK_H
+#ifdef HAVE_LINUX_LANDLOCK
 	// Prevent the process from gaining new privileges. The return
 	// is ignored to keep compatibility with old kernels.
 	(void)prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);

tests/Makefile.am

@@ -42,8 +42,7 @@ check_PROGRAMS = \
 	test_bcj_exact_size \
 	test_memlimit \
 	test_lzip_decoder \
-	test_vli \
-	test_microlzma
+	test_vli
 
 TESTS = \
 	test_check \
@@ -58,7 +57,6 @@ TESTS = \
 	test_memlimit \
 	test_lzip_decoder \
 	test_vli \
-	test_microlzma \
 	test_files.sh \
 	test_suffix.sh \
 	test_compress_prepared_bcj_sparc \
@@ -67,6 +65,11 @@ TESTS = \
 	test_compress_generated_random \
 	test_compress_generated_text
 
+if COND_MICROLZMA
+check_PROGRAMS += test_microlzma
+TESTS += test_microlzma
+endif
+
 if COND_SCRIPTS
 TESTS += test_scripts.sh
 endif

tests/test_files.sh

@@ -149,6 +149,17 @@ else
 	exit 1
 fi
 
+# Test that --single-stream can decompress bad-3-corrupt_lzma2.xz.
+# The first Stream in this file should decompress without errors.
+# This file cannot be decompressed with xzdec.
+I="$srcdir/files/bad-3-corrupt_lzma2.xz"
+if test -z "$XZ" || "$XZ" -dc --single-stream $NO_WARN "$I" > /dev/null; then
+	:
+else
+	echo "Good first Stream failed xz with --single-stream: $I"
+	exit 1
+fi
+
 
 #########
 # .lzma #

tests/test_microlzma.c

@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
 ///////////////////////////////////////////////////////////////////////////////
 //
 /// \file       test_microlzma.c
@@ -5,15 +7,10 @@
 //
 //  Author:     Jia Tan
 //
-//  This file has been put into the public domain.
-//  You can do whatever you want with this file.
-//
 ///////////////////////////////////////////////////////////////////////////////
 
 #include "tests.h"
 
-#ifdef HAVE_MICROLZMA
-
 #define BUFFER_SIZE 1024
 
 #ifdef HAVE_ENCODER_LZMA1
@@ -514,7 +511,6 @@ test_decode_bad_lzma_properties(void)
 	lzma_end(&strm);
 }
 #endif
-#endif
 
 
 extern int
@@ -522,17 +518,16 @@ main(int argc, char **argv)
 {
 	tuktest_start(argc, argv);
 
-#ifndef HAVE_MICROLZMA
-	tuktest_early_skip("MicroLZMA disabled");
+#ifndef HAVE_ENCODER_LZMA1
+	tuktest_early_skip("LZMA1 encoder disabled");
 #else
-#	ifdef HAVE_ENCODER_LZMA1
 	tuktest_run(test_encode_options);
 	tuktest_run(test_encode_basic);
 	tuktest_run(test_encode_small_out);
 	tuktest_run(test_encode_actions);
-#	endif
 
-#	if defined(HAVE_DECODER_LZMA1) && defined(HAVE_ENCODER_LZMA1)
+	// MicroLZMA decoder tests require the basic encoder functionality.
+#	ifdef HAVE_DECODER_LZMA1
 	goodbye_world_encoded_size = basic_microlzma_encode(goodbye_world,
 			ARRAY_SIZE(goodbye_world), &goodbye_world_encoded);