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
+While both options are available, we prefer email.
-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.)
 
 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

CMakeLists.txt

@@ -333,6 +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
@@ -1276,22 +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
+elseif(BUILD_SHARED_LIBS AND SYMBOL_VERSIONING STREQUAL "linux")
-       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?
-    #
     # 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
@@ -1307,10 +1355,7 @@ elseif(BUILD_SHARED_LIBS AND CMAKE_SYSTEM_NAME STREQUAL "Linux" AND
     set_target_properties(liblzma PROPERTIES
         LINK_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/liblzma/liblzma_linux.map"
     )
-elseif(BUILD_SHARED_LIBS AND (CMAKE_SYSTEM_NAME STREQUAL "FreeBSD" OR
+elseif(BUILD_SHARED_LIBS AND SYMBOL_VERSIONING STREQUAL "generic")
-                              CMAKE_SYSTEM_NAME STREQUAL "Linux"))
-    # Generic symbol versioning for shared liblzma is used on FreeBSD and
-    # also on GNU/Linux on MicroBlaze.
     target_link_options(liblzma PRIVATE
         "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/src/liblzma/liblzma_generic.map"
     )

INSTALL

@@ -561,10 +561,45 @@ XZ Utils Installation
                                 sandboxing. If no Landlock support
                                 is found, configure will give an error.
 
-    --enable-symbol-versions
+    --enable-symbol-versions[=VARIANT]
-                Use symbol versioning for liblzma. This is enabled by
+                Use symbol versioning for liblzma shared library.
-                default on GNU/Linux, other GNU-based systems, and
+                This is enabled by default on GNU/Linux (glibc only),
-                FreeBSD.
+                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

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

configure.ac

@@ -709,61 +709,80 @@ 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
+], [
-	case "$host_cpu-$host_os" in
+	# "yes" means that symbol version are to be used but we need to
-		microblaze*)
+	# autodetect which variant to use.
-			# GCC 12 on MicroBlaze doesn't support __symver__
+	if test "x$enable_symbol_versions" = xyes ; then
-			# attribute. It's simplest and safest to use the
+		case "$host_cpu-$host_os" in
-			# generic version on that platform since then only
+			microblaze*)
-			# the linker script is needed. The RHEL/CentOS 7
+				# GCC 12 on MicroBlaze doesn't support
-			# compatibility symbols don't matter on MicroBlaze.
+				# __symver__ attribute. It's simplest and
-			enable_symbol_versions=generic
+				# safest to use the generic version on that
-			;;
+				# platform since then only the linker script
-		*-linux*)
+				# is needed. The RHEL/CentOS 7 compatibility
-			case "$pic_mode-$enable_static" in
+				# symbols don't matter on MicroBlaze.
-				default-*)
+				enable_symbol_versions=generic
-					# Use symvers if PIC is defined.
+				;;
-					have_symbol_versions_linux=2
+			*-linux*)
-					;;
+				# NVIDIA HPC Compiler doesn't support symbol
-				*-no)
+				# versioning but the linker script can still
-					# Not building static library.
+				# be used.
-					# Use symvers unconditionally.
+				AC_EGREP_CPP([use_generic_symbol_versioning],
-					have_symbol_versions_linux=1
+					[#ifdef __NVCOMPILER
-					;;
+					use_generic_symbol_versioning
-				*)
+					#endif],
-					AC_MSG_RESULT([])
+					[enable_symbol_versions=generic],
-					AC_MSG_ERROR([
+					[enable_symbol_versions=linux])
+				;;
+			*)
+				enable_symbol_versions=generic
+				;;
+		esac
+	fi
+
+	if test "x$enable_symbol_versions" = xlinux ; then
+		case "$pic_mode-$enable_static" in
+			default-*)
+				# Use symvers if PIC is defined.
+				have_symbol_versions_linux=2
+				;;
+			*-no)
+				# Not building static library.
+				# Use symvers unconditionally.
+				have_symbol_versions_linux=1
+				;;
+			*)
+				AC_MSG_RESULT([])
+				AC_MSG_ERROR([
     On GNU/Linux, building both shared and static library at the same time
     is not supported if --with-pic or --without-pic is used.
     Use either --disable-shared or --disable-static to build one type
     of library at a time. If both types are needed, build one at a time,
     possibly picking only src/liblzma/.libs/liblzma.a from the static build.])
-					;;
+				;;
-			esac
+		esac
-			enable_symbol_versions=linux
+		AC_DEFINE_UNQUOTED([HAVE_SYMBOL_VERSIONS_LINUX],
-			AC_DEFINE_UNQUOTED([HAVE_SYMBOL_VERSIONS_LINUX],
+			[$have_symbol_versions_linux],
-				[$have_symbol_versions_linux],
+			[Define to 1 to if GNU/Linux-specific details
-				[Define to 1 to if GNU/Linux-specific details
+			are unconditionally wanted for symbol
-				are unconditionally wanted for symbol
+			versioning. Define to 2 to if these are wanted
-				versioning. Define to 2 to if these are wanted
+			only if also PIC is defined (allows building
-				only if also PIC is defined (allows building
+			both shared and static liblzma at the same
-				both shared and static liblzma at the same
+			time with Libtool if neither --with-pic nor
-				time with Libtool if neither --with-pic nor
+			--without-pic is used). This define must be
-				--without-pic is used). This define must be
+			used together with liblzma_linux.map.])
-				used together with liblzma_linux.map.])
+	elif test "x$enable_symbol_versions" != xgeneric ; then
-			;;
+		AC_MSG_RESULT([])
-		*)
+		AC_MSG_ERROR([unknown symbol versioning variant '$enable_symbol_versions'])
-			enable_symbol_versions=generic
+	fi
-			;;
-	esac
 	AC_MSG_RESULT([yes ($enable_symbol_versions)])
-fi
+])
 
 AM_CONDITIONAL([COND_SYMVERS_LINUX],
 	[test "x$enable_symbol_versions" = xlinux])

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 11:1:6
+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 6
+#define LZMA_VERSION_MINOR 7
 
 /** \brief Patch version number of the liblzma release. */
-#define LZMA_VERSION_PATCH 1
+#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_STABLE
+#define LZMA_VERSION_STABILITY LZMA_VERSION_STABILITY_ALPHA
 
 /** \brief Commit version number of the liblzma release */
 #ifndef LZMA_VERSION_COMMIT

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/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