summaryrefslogtreecommitdiffstats
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/Makefile.am6
-rw-r--r--src/Makefile.in7
-rw-r--r--src/common/common_w32res.rc5
-rw-r--r--src/common/mythread.h30
-rw-r--r--src/common/sysdefs.h18
-rw-r--r--src/common/tuklib_common.h27
-rw-r--r--src/common/tuklib_config.h2
-rw-r--r--src/common/tuklib_cpucores.c5
-rw-r--r--src/common/tuklib_cpucores.h5
-rw-r--r--src/common/tuklib_exit.c5
-rw-r--r--src/common/tuklib_exit.h9
-rw-r--r--src/common/tuklib_gettext.h5
-rw-r--r--src/common/tuklib_integer.h56
-rw-r--r--src/common/tuklib_mbstr.h5
-rw-r--r--src/common/tuklib_mbstr_fw.c5
-rw-r--r--src/common/tuklib_mbstr_width.c5
-rw-r--r--src/common/tuklib_open_stdxxx.c5
-rw-r--r--src/common/tuklib_open_stdxxx.h5
-rw-r--r--src/common/tuklib_physmem.c25
-rw-r--r--src/common/tuklib_physmem.h5
-rw-r--r--src/common/tuklib_progname.c5
-rw-r--r--src/common/tuklib_progname.h5
-rw-r--r--src/liblzma/Makefile.am8
-rw-r--r--src/liblzma/Makefile.in100
-rw-r--r--src/liblzma/api/Makefile.am25
-rw-r--r--src/liblzma/api/Makefile.in63
-rw-r--r--src/liblzma/api/lzma.h31
-rw-r--r--src/liblzma/api/lzma/base.h25
-rw-r--r--src/liblzma/api/lzma/bcj.h10
-rw-r--r--src/liblzma/api/lzma/block.h5
-rw-r--r--src/liblzma/api/lzma/check.h5
-rw-r--r--src/liblzma/api/lzma/container.h45
-rw-r--r--src/liblzma/api/lzma/delta.h5
-rw-r--r--src/liblzma/api/lzma/filter.h11
-rw-r--r--src/liblzma/api/lzma/hardware.h5
-rw-r--r--src/liblzma/api/lzma/index.h42
-rw-r--r--src/liblzma/api/lzma/index_hash.h5
-rw-r--r--src/liblzma/api/lzma/lzma12.h7
-rw-r--r--src/liblzma/api/lzma/stream_flags.h5
-rw-r--r--src/liblzma/api/lzma/version.h9
-rw-r--r--src/liblzma/api/lzma/vli.h10
-rw-r--r--src/liblzma/check/Makefile.inc15
-rw-r--r--src/liblzma/check/check.c5
-rw-r--r--src/liblzma/check/check.h5
-rw-r--r--src/liblzma/check/crc32_arm64.h122
-rw-r--r--src/liblzma/check/crc32_fast.c158
-rw-r--r--src/liblzma/check/crc32_small.c5
-rw-r--r--src/liblzma/check/crc32_table.c34
-rw-r--r--src/liblzma/check/crc32_table_be.h4
-rw-r--r--src/liblzma/check/crc32_table_le.h4
-rw-r--r--src/liblzma/check/crc32_tablegen.c23
-rw-r--r--src/liblzma/check/crc32_x86.S5
-rw-r--r--src/liblzma/check/crc64_fast.c446
-rw-r--r--src/liblzma/check/crc64_small.c5
-rw-r--r--src/liblzma/check/crc64_table.c16
-rw-r--r--src/liblzma/check/crc64_table_be.h4
-rw-r--r--src/liblzma/check/crc64_table_le.h4
-rw-r--r--src/liblzma/check/crc64_tablegen.c15
-rw-r--r--src/liblzma/check/crc64_x86.S5
-rw-r--r--src/liblzma/check/crc_common.h137
-rw-r--r--src/liblzma/check/crc_macros.h30
-rw-r--r--src/liblzma/check/crc_x86_clmul.h428
-rw-r--r--src/liblzma/check/sha256.c19
-rw-r--r--src/liblzma/common/Makefile.inc6
-rw-r--r--src/liblzma/common/alone_decoder.c5
-rw-r--r--src/liblzma/common/alone_decoder.h5
-rw-r--r--src/liblzma/common/alone_encoder.c5
-rw-r--r--src/liblzma/common/auto_decoder.c5
-rw-r--r--src/liblzma/common/block_buffer_decoder.c5
-rw-r--r--src/liblzma/common/block_buffer_encoder.c5
-rw-r--r--src/liblzma/common/block_buffer_encoder.h5
-rw-r--r--src/liblzma/common/block_decoder.c5
-rw-r--r--src/liblzma/common/block_decoder.h5
-rw-r--r--src/liblzma/common/block_encoder.c5
-rw-r--r--src/liblzma/common/block_encoder.h5
-rw-r--r--src/liblzma/common/block_header_decoder.c5
-rw-r--r--src/liblzma/common/block_header_encoder.c5
-rw-r--r--src/liblzma/common/block_util.c5
-rw-r--r--src/liblzma/common/common.c5
-rw-r--r--src/liblzma/common/common.h5
-rw-r--r--src/liblzma/common/easy_buffer_encoder.c5
-rw-r--r--src/liblzma/common/easy_decoder_memusage.c5
-rw-r--r--src/liblzma/common/easy_encoder.c5
-rw-r--r--src/liblzma/common/easy_encoder_memusage.c5
-rw-r--r--src/liblzma/common/easy_preset.c5
-rw-r--r--src/liblzma/common/easy_preset.h10
-rw-r--r--src/liblzma/common/file_info.c5
-rw-r--r--src/liblzma/common/filter_buffer_decoder.c7
-rw-r--r--src/liblzma/common/filter_buffer_encoder.c5
-rw-r--r--src/liblzma/common/filter_common.c16
-rw-r--r--src/liblzma/common/filter_common.h5
-rw-r--r--src/liblzma/common/filter_decoder.c28
-rw-r--r--src/liblzma/common/filter_decoder.h5
-rw-r--r--src/liblzma/common/filter_encoder.c54
-rw-r--r--src/liblzma/common/filter_encoder.h11
-rw-r--r--src/liblzma/common/filter_flags_decoder.c5
-rw-r--r--src/liblzma/common/filter_flags_encoder.c5
-rw-r--r--src/liblzma/common/hardware_cputhreads.c5
-rw-r--r--src/liblzma/common/hardware_physmem.c5
-rw-r--r--src/liblzma/common/index.c5
-rw-r--r--src/liblzma/common/index.h5
-rw-r--r--src/liblzma/common/index_decoder.c16
-rw-r--r--src/liblzma/common/index_decoder.h5
-rw-r--r--src/liblzma/common/index_encoder.c5
-rw-r--r--src/liblzma/common/index_encoder.h5
-rw-r--r--src/liblzma/common/index_hash.c5
-rw-r--r--src/liblzma/common/lzip_decoder.c5
-rw-r--r--src/liblzma/common/lzip_decoder.h5
-rw-r--r--src/liblzma/common/memcmplen.h37
-rw-r--r--src/liblzma/common/microlzma_decoder.c5
-rw-r--r--src/liblzma/common/microlzma_encoder.c5
-rw-r--r--src/liblzma/common/outqueue.c5
-rw-r--r--src/liblzma/common/outqueue.h10
-rw-r--r--src/liblzma/common/stream_buffer_decoder.c5
-rw-r--r--src/liblzma/common/stream_buffer_encoder.c5
-rw-r--r--src/liblzma/common/stream_decoder.c5
-rw-r--r--src/liblzma/common/stream_decoder.h5
-rw-r--r--src/liblzma/common/stream_decoder_mt.c5
-rw-r--r--src/liblzma/common/stream_encoder.c5
-rw-r--r--src/liblzma/common/stream_encoder_mt.c25
-rw-r--r--src/liblzma/common/stream_flags_common.c5
-rw-r--r--src/liblzma/common/stream_flags_common.h5
-rw-r--r--src/liblzma/common/stream_flags_decoder.c5
-rw-r--r--src/liblzma/common/stream_flags_encoder.c5
-rw-r--r--src/liblzma/common/string_conversion.c26
-rw-r--r--src/liblzma/common/vli_decoder.c5
-rw-r--r--src/liblzma/common/vli_encoder.c5
-rw-r--r--src/liblzma/common/vli_size.c5
-rw-r--r--src/liblzma/delta/Makefile.inc6
-rw-r--r--src/liblzma/delta/delta_common.c5
-rw-r--r--src/liblzma/delta/delta_common.h5
-rw-r--r--src/liblzma/delta/delta_decoder.c10
-rw-r--r--src/liblzma/delta/delta_decoder.h5
-rw-r--r--src/liblzma/delta/delta_encoder.c5
-rw-r--r--src/liblzma/delta/delta_encoder.h5
-rw-r--r--src/liblzma/delta/delta_private.h5
-rw-r--r--src/liblzma/liblzma.pc.in6
-rw-r--r--src/liblzma/liblzma_generic.map7
-rw-r--r--src/liblzma/liblzma_linux.map7
-rw-r--r--src/liblzma/liblzma_w32res.rc5
-rw-r--r--src/liblzma/lz/Makefile.inc6
-rw-r--r--src/liblzma/lz/lz_decoder.c48
-rw-r--r--src/liblzma/lz/lz_decoder.h116
-rw-r--r--src/liblzma/lz/lz_encoder.c13
-rw-r--r--src/liblzma/lz/lz_encoder.h21
-rw-r--r--src/liblzma/lz/lz_encoder_hash.h5
-rw-r--r--src/liblzma/lz/lz_encoder_hash_table.h4
-rw-r--r--src/liblzma/lz/lz_encoder_mf.c5
-rw-r--r--src/liblzma/lzma/Makefile.inc6
-rw-r--r--src/liblzma/lzma/fastpos.h5
-rw-r--r--src/liblzma/lzma/fastpos_table.c4
-rw-r--r--src/liblzma/lzma/fastpos_tablegen.c17
-rw-r--r--src/liblzma/lzma/lzma2_decoder.c5
-rw-r--r--src/liblzma/lzma/lzma2_decoder.h5
-rw-r--r--src/liblzma/lzma/lzma2_encoder.c8
-rw-r--r--src/liblzma/lzma/lzma2_encoder.h5
-rw-r--r--src/liblzma/lzma/lzma_common.h41
-rw-r--r--src/liblzma/lzma/lzma_decoder.c760
-rw-r--r--src/liblzma/lzma/lzma_decoder.h5
-rw-r--r--src/liblzma/lzma/lzma_encoder.c18
-rw-r--r--src/liblzma/lzma/lzma_encoder.h5
-rw-r--r--src/liblzma/lzma/lzma_encoder_optimum_fast.c5
-rw-r--r--src/liblzma/lzma/lzma_encoder_optimum_normal.c7
-rw-r--r--src/liblzma/lzma/lzma_encoder_presets.c5
-rw-r--r--src/liblzma/lzma/lzma_encoder_private.h9
-rw-r--r--src/liblzma/rangecoder/Makefile.inc6
-rw-r--r--src/liblzma/rangecoder/price.h5
-rw-r--r--src/liblzma/rangecoder/price_table.c4
-rw-r--r--src/liblzma/rangecoder/price_tablegen.c22
-rw-r--r--src/liblzma/rangecoder/range_common.h14
-rw-r--r--src/liblzma/rangecoder/range_decoder.h839
-rw-r--r--src/liblzma/rangecoder/range_encoder.h5
-rw-r--r--src/liblzma/simple/Makefile.inc10
-rw-r--r--src/liblzma/simple/arm.c5
-rw-r--r--src/liblzma/simple/arm64.c5
-rw-r--r--src/liblzma/simple/armthumb.c5
-rw-r--r--src/liblzma/simple/ia64.c5
-rw-r--r--src/liblzma/simple/powerpc.c5
-rw-r--r--src/liblzma/simple/riscv.c755
-rw-r--r--src/liblzma/simple/simple_coder.c5
-rw-r--r--src/liblzma/simple/simple_coder.h22
-rw-r--r--src/liblzma/simple/simple_decoder.c5
-rw-r--r--src/liblzma/simple/simple_decoder.h5
-rw-r--r--src/liblzma/simple/simple_encoder.c5
-rw-r--r--src/liblzma/simple/simple_encoder.h5
-rw-r--r--src/liblzma/simple/simple_private.h5
-rw-r--r--src/liblzma/simple/sparc.c5
-rw-r--r--src/liblzma/simple/x86.c16
-rw-r--r--src/liblzma/validate_map.sh6
-rw-r--r--src/lzmainfo/Makefile.am32
-rw-r--r--src/lzmainfo/Makefile.in60
-rw-r--r--src/lzmainfo/lzmainfo.14
-rw-r--r--src/lzmainfo/lzmainfo.c5
-rw-r--r--src/lzmainfo/lzmainfo_w32res.rc5
-rw-r--r--src/scripts/Makefile.am6
-rw-r--r--src/scripts/Makefile.in7
-rw-r--r--src/scripts/xzdiff.195
-rw-r--r--src/scripts/xzdiff.in19
-rw-r--r--src/scripts/xzgrep.1119
-rw-r--r--src/scripts/xzgrep.in8
-rw-r--r--src/scripts/xzless.112
-rw-r--r--src/scripts/xzless.in21
-rw-r--r--src/scripts/xzmore.178
-rw-r--r--src/scripts/xzmore.in3
-rw-r--r--src/xz/Makefile.am10
-rw-r--r--src/xz/Makefile.in57
-rw-r--r--src/xz/args.c186
-rw-r--r--src/xz/args.h8
-rw-r--r--src/xz/coder.c607
-rw-r--r--src/xz/coder.h42
-rw-r--r--src/xz/file_io.c144
-rw-r--r--src/xz/file_io.h21
-rw-r--r--src/xz/hardware.c11
-rw-r--r--src/xz/hardware.h5
-rw-r--r--src/xz/list.c31
-rw-r--r--src/xz/list.h5
-rw-r--r--src/xz/main.c91
-rw-r--r--src/xz/main.h5
-rw-r--r--src/xz/message.c94
-rw-r--r--src/xz/message.h16
-rw-r--r--src/xz/mytime.c105
-rw-r--r--src/xz/mytime.h11
-rw-r--r--src/xz/options.c7
-rw-r--r--src/xz/options.h5
-rw-r--r--src/xz/private.h26
-rw-r--r--src/xz/sandbox.c355
-rw-r--r--src/xz/sandbox.h43
-rw-r--r--src/xz/signals.c29
-rw-r--r--src/xz/signals.h5
-rw-r--r--src/xz/suffix.c17
-rw-r--r--src/xz/suffix.h5
-rw-r--r--src/xz/util.c36
-rw-r--r--src/xz/util.h19
-rw-r--r--src/xz/xz.1469
-rw-r--r--src/xz/xz_w32res.rc5
-rw-r--r--src/xzdec/Makefile.am6
-rw-r--r--src/xzdec/Makefile.in7
-rw-r--r--src/xzdec/lzmadec_w32res.rc5
-rw-r--r--src/xzdec/xzdec.16
-rw-r--r--src/xzdec/xzdec.c180
-rw-r--r--src/xzdec/xzdec_w32res.rc5
241 files changed, 6298 insertions, 2479 deletions
diff --git a/src/Makefile.am b/src/Makefile.am
index d199e85..1061323 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
SUBDIRS = liblzma xzdec
diff --git a/src/Makefile.in b/src/Makefile.in
index d9827e9..73e7a2a 100644
--- a/src/Makefile.in
+++ b/src/Makefile.in
@@ -92,8 +92,8 @@ host_triplet = @host@
@COND_SCRIPTS_TRUE@am__append_3 = scripts
subdir = src
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -206,7 +206,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -335,6 +334,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
diff --git a/src/common/common_w32res.rc b/src/common/common_w32res.rc
index d05d22e..97aa58a 100644
--- a/src/common/common_w32res.rc
+++ b/src/common/common_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#include <winresrc.h>
diff --git a/src/common/mythread.h b/src/common/mythread.h
index 4495e01..10ea2d4 100644
--- a/src/common/mythread.h
+++ b/src/common/mythread.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file mythread.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef MYTHREAD_H
@@ -112,6 +111,25 @@ mythread_sigmask(int how, const sigset_t *restrict set,
# include <sys/time.h>
#endif
+// MinGW-w64 with winpthreads:
+//
+// NOTE: Typical builds with MinGW-w64 don't use this code (MYTHREAD_POSIX).
+// Instead, native Windows threading APIs are used (MYTHREAD_VISTA or
+// MYTHREAD_WIN95).
+//
+// MinGW-w64 has _sigset_t (an integer type) in <sys/types.h>.
+// If _POSIX was #defined, the header would add the alias sigset_t too.
+// Let's keep this working even without _POSIX.
+//
+// There are no functions that actually do something with sigset_t
+// because signals barely exist on Windows. The sigfillset macro below
+// is just to silence warnings. There is no sigfillset() in MinGW-w64.
+#ifdef __MINGW32__
+# include <sys/types.h>
+# define sigset_t _sigset_t
+# define sigfillset(set_ptr) do { *(set_ptr) = 0; } while (0)
+#endif
+
#define MYTHREAD_RET_TYPE void *
#define MYTHREAD_RET_VALUE NULL
@@ -140,11 +158,13 @@ typedef struct timespec mythread_condtime;
// Use pthread_sigmask() to set the signal mask in multi-threaded programs.
// Do nothing on OpenVMS since it lacks pthread_sigmask().
+// Do nothing on MinGW-w64 too to silence warnings (its pthread_sigmask()
+// is #defined to 0 so it's a no-op).
static inline void
mythread_sigmask(int how, const sigset_t *restrict set,
sigset_t *restrict oset)
{
-#ifdef __VMS
+#if defined(__VMS) || defined(__MINGW32__)
(void)how;
(void)set;
(void)oset;
@@ -180,7 +200,7 @@ mythread_join(mythread thread)
}
-// Initiatlizes a mutex. Returns zero on success and non-zero on error.
+// Initializes a mutex. Returns zero on success and non-zero on error.
static inline int
mythread_mutex_init(mythread_mutex *mutex)
{
diff --git a/src/common/sysdefs.h b/src/common/sysdefs.h
index f04e45d..5f3785b 100644
--- a/src/common/sysdefs.h
+++ b/src/common/sysdefs.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file sysdefs.h
@@ -8,9 +10,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SYSDEFS_H
@@ -159,13 +158,16 @@ typedef unsigned char _Bool;
#include <string.h>
-// As of MSVC 2013, inline and restrict are supported with
-// non-standard keywords.
-#if defined(_WIN32) && defined(_MSC_VER)
-# ifndef inline
+// Visual Studio 2013 update 2 supports only __inline, not inline.
+// MSVC v19.0 / VS 2015 and newer support both.
+//
+// MSVC v19.27 (VS 2019 version 16.7) added support for restrict.
+// Older ones support only __restrict.
+#ifdef _MSC_VER
+# if _MSC_VER < 1900 && !defined(inline)
# define inline __inline
# endif
-# ifndef restrict
+# if _MSC_VER < 1927 && !defined(restrict)
# define restrict __restrict
# endif
#endif
diff --git a/src/common/tuklib_common.h b/src/common/tuklib_common.h
index b1f531e..7554dfc 100644
--- a/src/common/tuklib_common.h
+++ b/src/common/tuklib_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_common.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_COMMON_H
@@ -57,8 +56,28 @@
# define TUKLIB_GNUC_REQ(major, minor) 0
#endif
-#if TUKLIB_GNUC_REQ(2, 5)
+// tuklib_attr_noreturn attribute is used to mark functions as non-returning.
+// We cannot use "noreturn" as the macro name because then C23 code that
+// uses [[noreturn]] would break as it would expand to [[ [[noreturn]] ]].
+//
+// tuklib_attr_noreturn must be used at the beginning of function declaration
+// to work in all cases. The [[noreturn]] syntax is the most limiting, it
+// must be even before any GNU C's __attribute__ keywords:
+//
+// tuklib_attr_noreturn
+// __attribute__((nonnull(1)))
+// extern void foo(const char *s);
+//
+// FIXME: Update __STDC_VERSION__ for the final C23 version. 202000 is used
+// by GCC 13 and Clang 15 with -std=c2x.
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202000
+# define tuklib_attr_noreturn [[noreturn]]
+#elif defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112
+# define tuklib_attr_noreturn _Noreturn
+#elif TUKLIB_GNUC_REQ(2, 5)
# define tuklib_attr_noreturn __attribute__((__noreturn__))
+#elif defined(_MSC_VER)
+# define tuklib_attr_noreturn __declspec(noreturn)
#else
# define tuklib_attr_noreturn
#endif
diff --git a/src/common/tuklib_config.h b/src/common/tuklib_config.h
index 9d470ba..b27251d 100644
--- a/src/common/tuklib_config.h
+++ b/src/common/tuklib_config.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
// If config.h isn't available, assume that the headers required by
// tuklib_common.h are available. This is required by crc32_tablegen.c.
#ifdef HAVE_CONFIG_H
diff --git a/src/common/tuklib_cpucores.c b/src/common/tuklib_cpucores.c
index bb3f2f7..c4a781a 100644
--- a/src/common/tuklib_cpucores.c
+++ b/src/common/tuklib_cpucores.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_cpucores.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_cpucores.h"
diff --git a/src/common/tuklib_cpucores.h b/src/common/tuklib_cpucores.h
index be1ce1c..edff939 100644
--- a/src/common/tuklib_cpucores.h
+++ b/src/common/tuklib_cpucores.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_cpucores.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_CPUCORES_H
diff --git a/src/common/tuklib_exit.c b/src/common/tuklib_exit.c
index aa55620..c84e0f6 100644
--- a/src/common/tuklib_exit.c
+++ b/src/common/tuklib_exit.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_exit.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_common.h"
diff --git a/src/common/tuklib_exit.h b/src/common/tuklib_exit.h
index b11776f..d4e6b4a 100644
--- a/src/common/tuklib_exit.h
+++ b/src/common/tuklib_exit.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_exit.h
@@ -6,9 +8,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_EXIT_H
@@ -18,8 +17,8 @@
TUKLIB_DECLS_BEGIN
#define tuklib_exit TUKLIB_SYMBOL(tuklib_exit)
-extern void tuklib_exit(int status, int err_status, int show_error)
- tuklib_attr_noreturn;
+tuklib_attr_noreturn
+extern void tuklib_exit(int status, int err_status, int show_error);
TUKLIB_DECLS_END
#endif
diff --git a/src/common/tuklib_gettext.h b/src/common/tuklib_gettext.h
index ff18904..3ef5cb7 100644
--- a/src/common/tuklib_gettext.h
+++ b/src/common/tuklib_gettext.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_gettext.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_GETTEXT_H
diff --git a/src/common/tuklib_integer.h b/src/common/tuklib_integer.h
index e22aa8a..fbd5fb2 100644
--- a/src/common/tuklib_integer.h
+++ b/src/common/tuklib_integer.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_integer.h
@@ -14,7 +16,7 @@
///
/// Endianness-converting integer operations (these can be macros!)
/// (XX = 16, 32, or 64; Y = b or l):
-/// - Byte swapping: bswapXX(num)
+/// - Byte swapping: byteswapXX(num)
/// - Byte order conversions to/from native (byteswaps if Y isn't
/// the native endianness): convXXYe(num)
/// - Unaligned reads: readXXYe(ptr)
@@ -37,9 +39,6 @@
// Authors: Lasse Collin
// Joachim Henke
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_INTEGER_H
@@ -67,38 +66,41 @@
#if defined(HAVE___BUILTIN_BSWAPXX)
// GCC >= 4.8 and Clang
-# define bswap16(n) __builtin_bswap16(n)
-# define bswap32(n) __builtin_bswap32(n)
-# define bswap64(n) __builtin_bswap64(n)
+# define byteswap16(num) __builtin_bswap16(num)
+# define byteswap32(num) __builtin_bswap32(num)
+# define byteswap64(num) __builtin_bswap64(num)
#elif defined(HAVE_BYTESWAP_H)
// glibc, uClibc, dietlibc
# include <byteswap.h>
# ifdef HAVE_BSWAP_16
-# define bswap16(num) bswap_16(num)
+# define byteswap16(num) bswap_16(num)
# endif
# ifdef HAVE_BSWAP_32
-# define bswap32(num) bswap_32(num)
+# define byteswap32(num) bswap_32(num)
# endif
# ifdef HAVE_BSWAP_64
-# define bswap64(num) bswap_64(num)
+# define byteswap64(num) bswap_64(num)
# endif
#elif defined(HAVE_SYS_ENDIAN_H)
// *BSDs and Darwin
# include <sys/endian.h>
+# define byteswap16(num) bswap16(num)
+# define byteswap32(num) bswap32(num)
+# define byteswap64(num) bswap64(num)
#elif defined(HAVE_SYS_BYTEORDER_H)
// Solaris
# include <sys/byteorder.h>
# ifdef BSWAP_16
-# define bswap16(num) BSWAP_16(num)
+# define byteswap16(num) BSWAP_16(num)
# endif
# ifdef BSWAP_32
-# define bswap32(num) BSWAP_32(num)
+# define byteswap32(num) BSWAP_32(num)
# endif
# ifdef BSWAP_64
-# define bswap64(num) BSWAP_64(num)
+# define byteswap64(num) BSWAP_64(num)
# endif
# ifdef BE_16
# define conv16be(num) BE_16(num)
@@ -120,15 +122,15 @@
# endif
#endif
-#ifndef bswap16
-# define bswap16(n) (uint16_t)( \
+#ifndef byteswap16
+# define byteswap16(n) (uint16_t)( \
(((n) & 0x00FFU) << 8) \
| (((n) & 0xFF00U) >> 8) \
)
#endif
-#ifndef bswap32
-# define bswap32(n) (uint32_t)( \
+#ifndef byteswap32
+# define byteswap32(n) (uint32_t)( \
(((n) & UINT32_C(0x000000FF)) << 24) \
| (((n) & UINT32_C(0x0000FF00)) << 8) \
| (((n) & UINT32_C(0x00FF0000)) >> 8) \
@@ -136,8 +138,8 @@
)
#endif
-#ifndef bswap64
-# define bswap64(n) (uint64_t)( \
+#ifndef byteswap64
+# define byteswap64(n) (uint64_t)( \
(((n) & UINT64_C(0x00000000000000FF)) << 56) \
| (((n) & UINT64_C(0x000000000000FF00)) << 40) \
| (((n) & UINT64_C(0x0000000000FF0000)) << 24) \
@@ -161,23 +163,23 @@
# define conv64be(num) ((uint64_t)(num))
# endif
# ifndef conv16le
-# define conv16le(num) bswap16(num)
+# define conv16le(num) byteswap16(num)
# endif
# ifndef conv32le
-# define conv32le(num) bswap32(num)
+# define conv32le(num) byteswap32(num)
# endif
# ifndef conv64le
-# define conv64le(num) bswap64(num)
+# define conv64le(num) byteswap64(num)
# endif
#else
# ifndef conv16be
-# define conv16be(num) bswap16(num)
+# define conv16be(num) byteswap16(num)
# endif
# ifndef conv32be
-# define conv32be(num) bswap32(num)
+# define conv32be(num) byteswap32(num)
# endif
# ifndef conv64be
-# define conv64be(num) bswap64(num)
+# define conv64be(num) byteswap64(num)
# endif
# ifndef conv16le
# define conv16le(num) ((uint16_t)(num))
@@ -251,7 +253,7 @@
// was one instruction longer.
//
// Conclusion: At least in case of GCC and Clang, byte-by-byte code is
-// the best choise for strict-align archs to do unaligned access.
+// the best choice for strict-align archs to do unaligned access.
//
// See also: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111502
//
@@ -625,7 +627,7 @@ write64le(uint8_t *buf, uint64_t num)
// aligned but some compilers have language extensions to do that. With
// such language extensions the memcpy() method gives excellent results.
//
-// What to do on a strict-align system when no known language extentensions
+// What to do on a strict-align system when no known language extensions
// are available? Falling back to byte-by-byte access would be safe but ruin
// optimizations that have been made specifically with aligned access in mind.
// As a compromise, aligned reads will fall back to non-compliant type punning
diff --git a/src/common/tuklib_mbstr.h b/src/common/tuklib_mbstr.h
index dde9305..4c8eeb7 100644
--- a/src/common/tuklib_mbstr.h
+++ b/src/common/tuklib_mbstr.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_mbstr.h
@@ -10,9 +12,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_MBSTR_H
diff --git a/src/common/tuklib_mbstr_fw.c b/src/common/tuklib_mbstr_fw.c
index 64c9ad5..22d883b 100644
--- a/src/common/tuklib_mbstr_fw.c
+++ b/src/common/tuklib_mbstr_fw.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_mbstr_fw.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_mbstr.h"
diff --git a/src/common/tuklib_mbstr_width.c b/src/common/tuklib_mbstr_width.c
index 69d159e..7a8bf07 100644
--- a/src/common/tuklib_mbstr_width.c
+++ b/src/common/tuklib_mbstr_width.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_mbstr_width.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_mbstr.h"
diff --git a/src/common/tuklib_open_stdxxx.c b/src/common/tuklib_open_stdxxx.c
index 26702a6..b93e61d 100644
--- a/src/common/tuklib_open_stdxxx.c
+++ b/src/common/tuklib_open_stdxxx.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_open_stdxxx.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_open_stdxxx.h"
diff --git a/src/common/tuklib_open_stdxxx.h b/src/common/tuklib_open_stdxxx.h
index b911616..3ee3ade 100644
--- a/src/common/tuklib_open_stdxxx.h
+++ b/src/common/tuklib_open_stdxxx.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_open_stdxxx.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_OPEN_STDXXX_H
diff --git a/src/common/tuklib_physmem.c b/src/common/tuklib_physmem.c
index 69f6fd4..1009df1 100644
--- a/src/common/tuklib_physmem.c
+++ b/src/common/tuklib_physmem.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_physmem.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_physmem.h"
@@ -73,23 +72,20 @@
#endif
-// With GCC >= 8.1 with -Wextra and Clang >= 13 with -Wcast-function-type
-// will warn about the Windows-specific code.
-#if defined(__has_warning)
-# if __has_warning("-Wcast-function-type")
-# define CAN_DISABLE_WCAST_FUNCTION_TYPE 1
-# endif
-#elif TUKLIB_GNUC_REQ(8,1)
-# define CAN_DISABLE_WCAST_FUNCTION_TYPE 1
-#endif
-
-
extern uint64_t
tuklib_physmem(void)
{
uint64_t ret = 0;
#if defined(_WIN32) || defined(__CYGWIN__)
+ // This requires Windows 2000 or later.
+ MEMORYSTATUSEX meminfo;
+ meminfo.dwLength = sizeof(meminfo);
+ if (GlobalMemoryStatusEx(&meminfo))
+ ret = meminfo.ullTotalPhys;
+
+/*
+ // Old version that is compatible with even Win95:
if ((GetVersion() & 0xFF) >= 5) {
// Windows 2000 and later have GlobalMemoryStatusEx() which
// supports reporting values greater than 4 GiB. To keep the
@@ -125,6 +121,7 @@ tuklib_physmem(void)
GlobalMemoryStatus(&meminfo);
ret = meminfo.dwTotalPhys;
}
+*/
#elif defined(__OS2__)
unsigned long mem;
diff --git a/src/common/tuklib_physmem.h b/src/common/tuklib_physmem.h
index 09e2a51..f35bfba 100644
--- a/src/common/tuklib_physmem.h
+++ b/src/common/tuklib_physmem.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_physmem.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_PHYSMEM_H
diff --git a/src/common/tuklib_progname.c b/src/common/tuklib_progname.c
index e2ef4e5..959c127 100644
--- a/src/common/tuklib_progname.c
+++ b/src/common/tuklib_progname.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_progname.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "tuklib_progname.h"
diff --git a/src/common/tuklib_progname.h b/src/common/tuklib_progname.h
index bb80f25..a3d90cb 100644
--- a/src/common/tuklib_progname.h
+++ b/src/common/tuklib_progname.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file tuklib_progname.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef TUKLIB_PROGNAME_H
diff --git a/src/liblzma/Makefile.am b/src/liblzma/Makefile.am
index 23d524f..85b3a52 100644
--- a/src/liblzma/Makefile.am
+++ b/src/liblzma/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
SUBDIRS = api
@@ -24,7 +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 9:5:4
+liblzma_la_LDFLAGS = -no-undefined -version-info 11:2:6
EXTRA_DIST += liblzma_generic.map liblzma_linux.map validate_map.sh
if COND_SYMVERS_GENERIC
diff --git a/src/liblzma/Makefile.in b/src/liblzma/Makefile.in
index 2689fc4..45a8337 100644
--- a/src/liblzma/Makefile.in
+++ b/src/liblzma/Makefile.in
@@ -161,14 +161,14 @@ host_triplet = @host@
@COND_LZIP_DECODER_TRUE@@COND_MAIN_DECODER_TRUE@ common/lzip_decoder.c \
@COND_LZIP_DECODER_TRUE@@COND_MAIN_DECODER_TRUE@ common/lzip_decoder.h
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_TRUE@am__append_12 = check/crc32_small.c
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__append_13 = \
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@ check/crc32_table.c \
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@ check/crc32_table_le.h \
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@ check/crc32_table_be.h
-
-@COND_ASM_X86_TRUE@@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__append_14 = check/crc32_x86.S
-@COND_ASM_X86_FALSE@@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__append_15 = check/crc32_fast.c
+@COND_SMALL_TRUE@am__append_12 = check/crc32_small.c
+@COND_SMALL_FALSE@am__append_13 = \
+@COND_SMALL_FALSE@ check/crc32_table.c \
+@COND_SMALL_FALSE@ check/crc32_table_le.h \
+@COND_SMALL_FALSE@ check/crc32_table_be.h
+
+@COND_ASM_X86_TRUE@@COND_SMALL_FALSE@am__append_14 = check/crc32_x86.S
+@COND_ASM_X86_FALSE@@COND_SMALL_FALSE@am__append_15 = check/crc32_fast.c
@COND_CHECK_CRC64_TRUE@@COND_SMALL_TRUE@am__append_16 = check/crc64_small.c
@COND_CHECK_CRC64_TRUE@@COND_SMALL_FALSE@am__append_17 = \
@COND_CHECK_CRC64_TRUE@@COND_SMALL_FALSE@ check/crc64_table.c \
@@ -256,14 +256,15 @@ host_triplet = @host@
@COND_FILTER_ARMTHUMB_TRUE@@COND_FILTER_SIMPLE_TRUE@am__append_43 = simple/armthumb.c
@COND_FILTER_ARM64_TRUE@@COND_FILTER_SIMPLE_TRUE@am__append_44 = simple/arm64.c
@COND_FILTER_SIMPLE_TRUE@@COND_FILTER_SPARC_TRUE@am__append_45 = simple/sparc.c
-@COND_W32_TRUE@am__append_46 = liblzma.def liblzma.def.in empty.c
-@COND_W32_TRUE@am__append_47 = liblzma_w32res.rc
-@COND_W32_TRUE@am__append_48 = -Xlinker --output-def -Xlinker liblzma.def.in
-@COND_SHARED_TRUE@@COND_W32_TRUE@am__append_49 = liblzma.def
+@COND_FILTER_RISCV_TRUE@@COND_FILTER_SIMPLE_TRUE@am__append_46 = simple/riscv.c
+@COND_W32_TRUE@am__append_47 = liblzma.def liblzma.def.in empty.c
+@COND_W32_TRUE@am__append_48 = liblzma_w32res.rc
+@COND_W32_TRUE@am__append_49 = -Xlinker --output-def -Xlinker liblzma.def.in
+@COND_SHARED_TRUE@@COND_W32_TRUE@am__append_50 = liblzma.def
subdir = src/liblzma
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -349,10 +350,10 @@ am__liblzma_la_SOURCES_DIST = ../common/tuklib_physmem.c \
common/vli_decoder.c common/stream_decoder_mt.c \
common/microlzma_decoder.c common/lzip_decoder.c \
common/lzip_decoder.h check/check.c check/check.h \
- check/crc_macros.h check/crc32_small.c check/crc32_table.c \
- check/crc32_table_le.h check/crc32_table_be.h \
- check/crc32_x86.S check/crc32_fast.c check/crc64_small.c \
- check/crc64_table.c check/crc64_table_le.h \
+ check/crc_common.h check/crc_x86_clmul.h check/crc32_arm64.h \
+ check/crc32_small.c check/crc32_table.c check/crc32_table_le.h \
+ check/crc32_table_be.h check/crc32_x86.S check/crc32_fast.c \
+ check/crc64_small.c check/crc64_table.c check/crc64_table_le.h \
check/crc64_table_be.h check/crc64_x86.S check/crc64_fast.c \
check/sha256.c lz/lz_encoder.c lz/lz_encoder.h \
lz/lz_encoder_hash.h lz/lz_encoder_hash_table.h \
@@ -374,7 +375,7 @@ am__liblzma_la_SOURCES_DIST = ../common/tuklib_physmem.c \
simple/simple_encoder.h simple/simple_decoder.c \
simple/simple_decoder.h simple/x86.c simple/powerpc.c \
simple/ia64.c simple/arm.c simple/armthumb.c simple/arm64.c \
- simple/sparc.c liblzma_w32res.rc
+ simple/sparc.c simple/riscv.c liblzma_w32res.rc
@COND_THREADS_TRUE@am__objects_1 = liblzma_la-tuklib_cpucores.lo
@COND_THREADS_TRUE@am__objects_2 = liblzma_la-hardware_cputhreads.lo \
@COND_THREADS_TRUE@ liblzma_la-outqueue.lo
@@ -414,10 +415,11 @@ am__liblzma_la_SOURCES_DIST = ../common/tuklib_physmem.c \
@COND_MAIN_DECODER_TRUE@@COND_THREADS_TRUE@am__objects_7 = liblzma_la-stream_decoder_mt.lo
@COND_MAIN_DECODER_TRUE@@COND_MICROLZMA_TRUE@am__objects_8 = liblzma_la-microlzma_decoder.lo
@COND_LZIP_DECODER_TRUE@@COND_MAIN_DECODER_TRUE@am__objects_9 = liblzma_la-lzip_decoder.lo
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_TRUE@am__objects_10 = liblzma_la-crc32_small.lo
-@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__objects_11 = liblzma_la-crc32_table.lo
-@COND_ASM_X86_TRUE@@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__objects_12 = liblzma_la-crc32_x86.lo
-@COND_ASM_X86_FALSE@@COND_CHECK_CRC32_TRUE@@COND_SMALL_FALSE@am__objects_13 = liblzma_la-crc32_fast.lo
+@COND_SMALL_TRUE@am__objects_10 = liblzma_la-crc32_small.lo
+@COND_SMALL_FALSE@am__objects_11 = liblzma_la-crc32_table.lo
+@COND_ASM_X86_TRUE@@COND_SMALL_FALSE@am__objects_12 = \
+@COND_ASM_X86_TRUE@@COND_SMALL_FALSE@ liblzma_la-crc32_x86.lo
+@COND_ASM_X86_FALSE@@COND_SMALL_FALSE@am__objects_13 = liblzma_la-crc32_fast.lo
@COND_CHECK_CRC64_TRUE@@COND_SMALL_TRUE@am__objects_14 = liblzma_la-crc64_small.lo
@COND_CHECK_CRC64_TRUE@@COND_SMALL_FALSE@am__objects_15 = liblzma_la-crc64_table.lo
@COND_ASM_X86_TRUE@@COND_CHECK_CRC64_TRUE@@COND_SMALL_FALSE@am__objects_16 = liblzma_la-crc64_x86.lo
@@ -450,7 +452,8 @@ am__objects_27 =
@COND_FILTER_ARMTHUMB_TRUE@@COND_FILTER_SIMPLE_TRUE@am__objects_39 = liblzma_la-armthumb.lo
@COND_FILTER_ARM64_TRUE@@COND_FILTER_SIMPLE_TRUE@am__objects_40 = liblzma_la-arm64.lo
@COND_FILTER_SIMPLE_TRUE@@COND_FILTER_SPARC_TRUE@am__objects_41 = liblzma_la-sparc.lo
-@COND_W32_TRUE@am__objects_42 = liblzma_w32res.lo
+@COND_FILTER_RISCV_TRUE@@COND_FILTER_SIMPLE_TRUE@am__objects_42 = liblzma_la-riscv.lo
+@COND_W32_TRUE@am__objects_43 = liblzma_w32res.lo
am_liblzma_la_OBJECTS = liblzma_la-tuklib_physmem.lo $(am__objects_1) \
liblzma_la-common.lo liblzma_la-block_util.lo \
liblzma_la-easy_preset.lo liblzma_la-filter_common.lo \
@@ -471,7 +474,7 @@ am_liblzma_la_OBJECTS = liblzma_la-tuklib_physmem.lo $(am__objects_1) \
$(am__objects_33) $(am__objects_34) $(am__objects_35) \
$(am__objects_36) $(am__objects_37) $(am__objects_38) \
$(am__objects_39) $(am__objects_40) $(am__objects_41) \
- $(am__objects_42)
+ $(am__objects_42) $(am__objects_43)
liblzma_la_OBJECTS = $(am_liblzma_la_OBJECTS)
AM_V_lt = $(am__v_lt_@AM_V@)
am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@)
@@ -558,6 +561,7 @@ am__depfiles_remade = ./$(DEPDIR)/liblzma_la-alone_decoder.Plo \
./$(DEPDIR)/liblzma_la-outqueue.Plo \
./$(DEPDIR)/liblzma_la-powerpc.Plo \
./$(DEPDIR)/liblzma_la-price_table.Plo \
+ ./$(DEPDIR)/liblzma_la-riscv.Plo \
./$(DEPDIR)/liblzma_la-sha256.Plo \
./$(DEPDIR)/liblzma_la-simple_coder.Plo \
./$(DEPDIR)/liblzma_la-simple_decoder.Plo \
@@ -691,7 +695,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -820,6 +823,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
@@ -842,8 +847,8 @@ SUBDIRS = api
EXTRA_DIST = liblzma_generic.map liblzma_linux.map validate_map.sh \
check/crc32_tablegen.c check/crc64_tablegen.c $(am__append_23) \
liblzma.pc.in
-CLEANFILES = $(am__append_46)
-doc_DATA = $(am__append_49)
+CLEANFILES = $(am__append_47)
+doc_DATA = $(am__append_50)
lib_LTLIBRARIES = liblzma.la
liblzma_la_SOURCES = ../common/tuklib_physmem.c $(am__append_3) \
common/common.c common/common.h common/memcmplen.h \
@@ -855,18 +860,19 @@ liblzma_la_SOURCES = ../common/tuklib_physmem.c $(am__append_3) \
$(am__append_5) $(am__append_6) $(am__append_7) \
$(am__append_8) $(am__append_9) $(am__append_10) \
$(am__append_11) check/check.c check/check.h \
- check/crc_macros.h $(am__append_12) $(am__append_13) \
- $(am__append_14) $(am__append_15) $(am__append_16) \
- $(am__append_17) $(am__append_18) $(am__append_19) \
- $(am__append_20) $(am__append_21) $(am__append_22) \
- $(am__append_24) $(am__append_25) $(am__append_26) \
- $(am__append_27) $(am__append_28) $(am__append_29) \
- $(am__append_30) $(am__append_31) $(am__append_32) \
- $(am__append_33) $(am__append_34) $(am__append_35) \
- $(am__append_36) $(am__append_37) $(am__append_38) \
- $(am__append_39) $(am__append_40) $(am__append_41) \
- $(am__append_42) $(am__append_43) $(am__append_44) \
- $(am__append_45) $(am__append_47)
+ check/crc_common.h check/crc_x86_clmul.h check/crc32_arm64.h \
+ $(am__append_12) $(am__append_13) $(am__append_14) \
+ $(am__append_15) $(am__append_16) $(am__append_17) \
+ $(am__append_18) $(am__append_19) $(am__append_20) \
+ $(am__append_21) $(am__append_22) $(am__append_24) \
+ $(am__append_25) $(am__append_26) $(am__append_27) \
+ $(am__append_28) $(am__append_29) $(am__append_30) \
+ $(am__append_31) $(am__append_32) $(am__append_33) \
+ $(am__append_34) $(am__append_35) $(am__append_36) \
+ $(am__append_37) $(am__append_38) $(am__append_39) \
+ $(am__append_40) $(am__append_41) $(am__append_42) \
+ $(am__append_43) $(am__append_44) $(am__append_45) \
+ $(am__append_46) $(am__append_48)
liblzma_la_CPPFLAGS = \
-I$(top_srcdir)/src/liblzma/api \
-I$(top_srcdir)/src/liblzma/common \
@@ -879,8 +885,8 @@ liblzma_la_CPPFLAGS = \
-I$(top_srcdir)/src/common \
-DTUKLIB_SYMBOL_PREFIX=lzma_
-liblzma_la_LDFLAGS = -no-undefined -version-info 9:5:4 $(am__append_1) \
- $(am__append_2) $(am__append_48)
+liblzma_la_LDFLAGS = -no-undefined -version-info 11:2:6 \
+ $(am__append_1) $(am__append_2) $(am__append_49)
pkgconfigdir = $(libdir)/pkgconfig
pkgconfig_DATA = liblzma.pc
pc_verbose = $(pc_verbose_@AM_V@)
@@ -1028,6 +1034,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-outqueue.Plo@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-powerpc.Plo@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-price_table.Plo@am__quote@ # am--include-marker
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-riscv.Plo@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-sha256.Plo@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-simple_coder.Plo@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/liblzma_la-simple_decoder.Plo@am__quote@ # am--include-marker
@@ -1686,6 +1693,13 @@ liblzma_la-sparc.lo: simple/sparc.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(liblzma_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o liblzma_la-sparc.lo `test -f 'simple/sparc.c' || echo '$(srcdir)/'`simple/sparc.c
+liblzma_la-riscv.lo: simple/riscv.c
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(liblzma_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT liblzma_la-riscv.lo -MD -MP -MF $(DEPDIR)/liblzma_la-riscv.Tpo -c -o liblzma_la-riscv.lo `test -f 'simple/riscv.c' || echo '$(srcdir)/'`simple/riscv.c
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/liblzma_la-riscv.Tpo $(DEPDIR)/liblzma_la-riscv.Plo
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='simple/riscv.c' object='liblzma_la-riscv.lo' libtool=yes @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(liblzma_la_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o liblzma_la-riscv.lo `test -f 'simple/riscv.c' || echo '$(srcdir)/'`simple/riscv.c
+
mostlyclean-libtool:
-rm -f *.lo
@@ -1998,6 +2012,7 @@ distclean: distclean-recursive
-rm -f ./$(DEPDIR)/liblzma_la-outqueue.Plo
-rm -f ./$(DEPDIR)/liblzma_la-powerpc.Plo
-rm -f ./$(DEPDIR)/liblzma_la-price_table.Plo
+ -rm -f ./$(DEPDIR)/liblzma_la-riscv.Plo
-rm -f ./$(DEPDIR)/liblzma_la-sha256.Plo
-rm -f ./$(DEPDIR)/liblzma_la-simple_coder.Plo
-rm -f ./$(DEPDIR)/liblzma_la-simple_decoder.Plo
@@ -2127,6 +2142,7 @@ maintainer-clean: maintainer-clean-recursive
-rm -f ./$(DEPDIR)/liblzma_la-outqueue.Plo
-rm -f ./$(DEPDIR)/liblzma_la-powerpc.Plo
-rm -f ./$(DEPDIR)/liblzma_la-price_table.Plo
+ -rm -f ./$(DEPDIR)/liblzma_la-riscv.Plo
-rm -f ./$(DEPDIR)/liblzma_la-sha256.Plo
-rm -f ./$(DEPDIR)/liblzma_la-simple_coder.Plo
-rm -f ./$(DEPDIR)/liblzma_la-simple_decoder.Plo
diff --git a/src/liblzma/api/Makefile.am b/src/liblzma/api/Makefile.am
index db24600..4f91c77 100644
--- a/src/liblzma/api/Makefile.am
+++ b/src/liblzma/api/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
nobase_include_HEADERS = \
lzma.h \
@@ -21,3 +17,22 @@ nobase_include_HEADERS = \
lzma/stream_flags.h \
lzma/version.h \
lzma/vli.h
+
+if COND_DOXYGEN
+$(top_builddir)/doc/api/index.html: $(top_srcdir)/doxygen/update-doxygen $(top_srcdir)/doxygen/Doxyfile $(nobase_include_HEADERS)
+ $(MKDIR_P) "$(top_builddir)/doc"
+ "$(top_srcdir)/doxygen/update-doxygen" api \
+ "$(top_srcdir)" "$(top_builddir)/doc"
+
+all-local: $(top_builddir)/doc/api/index.html
+
+install-data-local:
+ $(MKDIR_P) "$(DESTDIR)$(docdir)/api"
+ $(INSTALL_DATA) "$(top_builddir)"/doc/api/* "$(DESTDIR)$(docdir)/api"
+
+uninstall-local:
+ rm -rf "$(DESTDIR)$(docdir)/api"
+
+clean-local:
+ rm -rf "$(top_builddir)/doc/api"
+endif
diff --git a/src/liblzma/api/Makefile.in b/src/liblzma/api/Makefile.in
index ea5cfd6..e973884 100644
--- a/src/liblzma/api/Makefile.in
+++ b/src/liblzma/api/Makefile.in
@@ -90,8 +90,8 @@ build_triplet = @build@
host_triplet = @host@
subdir = src/liblzma/api
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -192,7 +192,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -321,6 +320,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
@@ -505,7 +506,8 @@ distdir-am: $(DISTFILES)
done
check-am: all-am
check: check-am
-all-am: Makefile $(HEADERS)
+@COND_DOXYGEN_FALSE@all-local:
+all-am: Makefile $(HEADERS) all-local
installdirs:
for dir in "$(DESTDIR)$(includedir)"; do \
test -z "$$dir" || $(MKDIR_P) "$$dir"; \
@@ -540,9 +542,12 @@ distclean-generic:
maintainer-clean-generic:
@echo "This command is intended for maintainers to use"
@echo "it deletes files that may require special tools to rebuild."
+@COND_DOXYGEN_FALSE@clean-local:
+@COND_DOXYGEN_FALSE@install-data-local:
+@COND_DOXYGEN_FALSE@uninstall-local:
clean: clean-am
-clean-am: clean-generic clean-libtool mostlyclean-am
+clean-am: clean-generic clean-libtool clean-local mostlyclean-am
distclean: distclean-am
-rm -f Makefile
@@ -560,7 +565,7 @@ info: info-am
info-am:
-install-data-am: install-nobase_includeHEADERS
+install-data-am: install-data-local install-nobase_includeHEADERS
install-dvi: install-dvi-am
@@ -604,27 +609,45 @@ ps: ps-am
ps-am:
-uninstall-am: uninstall-nobase_includeHEADERS
+uninstall-am: uninstall-local uninstall-nobase_includeHEADERS
.MAKE: install-am install-strip
-.PHONY: CTAGS GTAGS TAGS all all-am check check-am clean clean-generic \
- clean-libtool cscopelist-am ctags ctags-am distclean \
- distclean-generic distclean-libtool distclean-tags distdir 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-nobase_includeHEADERS install-pdf install-pdf-am \
- install-ps install-ps-am install-strip installcheck \
- installcheck-am installdirs maintainer-clean \
- maintainer-clean-generic mostlyclean mostlyclean-generic \
- mostlyclean-libtool pdf pdf-am ps ps-am tags tags-am uninstall \
- uninstall-am uninstall-nobase_includeHEADERS
+.PHONY: CTAGS GTAGS TAGS all all-am all-local check check-am clean \
+ clean-generic clean-libtool clean-local cscopelist-am ctags \
+ ctags-am distclean distclean-generic distclean-libtool \
+ distclean-tags distdir dvi dvi-am html html-am info info-am \
+ install install-am install-data install-data-am \
+ install-data-local install-dvi install-dvi-am install-exec \
+ install-exec-am install-html install-html-am install-info \
+ install-info-am install-man install-nobase_includeHEADERS \
+ install-pdf install-pdf-am install-ps install-ps-am \
+ install-strip installcheck installcheck-am installdirs \
+ maintainer-clean maintainer-clean-generic mostlyclean \
+ mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
+ tags tags-am uninstall uninstall-am uninstall-local \
+ uninstall-nobase_includeHEADERS
.PRECIOUS: Makefile
+@COND_DOXYGEN_TRUE@$(top_builddir)/doc/api/index.html: $(top_srcdir)/doxygen/update-doxygen $(top_srcdir)/doxygen/Doxyfile $(nobase_include_HEADERS)
+@COND_DOXYGEN_TRUE@ $(MKDIR_P) "$(top_builddir)/doc"
+@COND_DOXYGEN_TRUE@ "$(top_srcdir)/doxygen/update-doxygen" api \
+@COND_DOXYGEN_TRUE@ "$(top_srcdir)" "$(top_builddir)/doc"
+
+@COND_DOXYGEN_TRUE@all-local: $(top_builddir)/doc/api/index.html
+
+@COND_DOXYGEN_TRUE@install-data-local:
+@COND_DOXYGEN_TRUE@ $(MKDIR_P) "$(DESTDIR)$(docdir)/api"
+@COND_DOXYGEN_TRUE@ $(INSTALL_DATA) "$(top_builddir)"/doc/api/* "$(DESTDIR)$(docdir)/api"
+
+@COND_DOXYGEN_TRUE@uninstall-local:
+@COND_DOXYGEN_TRUE@ rm -rf "$(DESTDIR)$(docdir)/api"
+
+@COND_DOXYGEN_TRUE@clean-local:
+@COND_DOXYGEN_TRUE@ rm -rf "$(top_builddir)/doc/api"
+
# 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/liblzma/api/lzma.h b/src/liblzma/api/lzma.h
index de12f22..6ca6e50 100644
--- a/src/liblzma/api/lzma.h
+++ b/src/liblzma/api/lzma.h
@@ -1,31 +1,30 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file api/lzma.h
* \brief The public API of liblzma data compression library
* \mainpage
*
- * liblzma is a public domain general-purpose data compression library with
- * a zlib-like API. The native file format is .xz, but also the old .lzma
- * format and raw (no headers) streams are supported. Multiple compression
- * algorithms (filters) are supported. Currently LZMA2 is the primary filter.
+ * liblzma is a general-purpose data compression library with a zlib-like API.
+ * The native file format is .xz, but also the old .lzma format and raw (no
+ * headers) streams are supported. Multiple compression algorithms (filters)
+ * are supported. Currently LZMA2 is the primary filter.
+ *
+ * liblzma is part of XZ Utils <https://tukaani.org/xz/>. XZ Utils
+ * includes a gzip-like command line tool named xz and some other tools.
+ * XZ Utils is developed and maintained by Lasse Collin.
*
- * liblzma is part of XZ Utils <https://tukaani.org/xz/>. XZ Utils includes
- * a gzip-like command line tool named xz and some other tools. XZ Utils
- * is developed and maintained by Lasse Collin and Jia Tan.
+ * Major parts of liblzma are based on code written by Igor Pavlov,
+ * specifically the LZMA SDK <https://7-zip.org/sdk.html>.
*
- * Major parts of liblzma are based on Igor Pavlov's public domain LZMA SDK
- * <https://7-zip.org/sdk.html>.
+ * The SHA-256 implementation in liblzma is based on code written by
+ * Wei Dai in Crypto++ Library <https://www.cryptopp.com/>.
*
- * The SHA-256 implementation is based on the public domain code found from
- * 7-Zip <https://7-zip.org/>, which has a modified version of the public
- * domain SHA-256 code found from Crypto++ <https://www.cryptopp.com/>.
- * The SHA-256 code in Crypto++ was written by Kevin Springle and Wei Dai.
+ * liblzma is distributed under the BSD Zero Clause License (0BSD).
*/
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H
diff --git a/src/liblzma/api/lzma/base.h b/src/liblzma/api/lzma/base.h
index 75cdd72..590e1d2 100644
--- a/src/liblzma/api/lzma/base.h
+++ b/src/liblzma/api/lzma/base.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/base.h
* \brief Data types and functions used in many places in liblzma API
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -21,8 +20,8 @@
*
* This is here because C89 doesn't have stdbool.h. To set a value for
* variables having type lzma_bool, you can use
- * - C99's `true' and `false' from stdbool.h;
- * - C++'s internal `true' and `false'; or
+ * - C99's 'true' and 'false' from stdbool.h;
+ * - C++'s internal 'true' and 'false'; or
* - integers one (true) and zero (false).
*/
typedef unsigned char lzma_bool;
@@ -258,7 +257,7 @@ typedef enum {
*/
/*
- * These eumerations may be used internally by liblzma
+ * These enumerations may be used internally by liblzma
* but they will never be returned to applications.
*/
LZMA_RET_INTERNAL1 = 101,
@@ -273,13 +272,13 @@ typedef enum {
/**
- * \brief The `action' argument for lzma_code()
+ * \brief The 'action' argument for lzma_code()
*
* After the first use of LZMA_SYNC_FLUSH, LZMA_FULL_FLUSH, LZMA_FULL_BARRIER,
- * or LZMA_FINISH, the same `action' must be used until lzma_code() returns
+ * or LZMA_FINISH, the same 'action' must be used until lzma_code() returns
* LZMA_STREAM_END. Also, the amount of input (that is, strm->avail_in) must
* not be modified by the application until lzma_code() returns
- * LZMA_STREAM_END. Changing the `action' or modifying the amount of input
+ * LZMA_STREAM_END. Changing the 'action' or modifying the amount of input
* will make lzma_code() return LZMA_PROG_ERROR.
*/
typedef enum {
@@ -393,8 +392,8 @@ typedef enum {
* Single-threaded mode only: liblzma doesn't make an internal copy of
* lzma_allocator. Thus, it is OK to change these function pointers in
* the middle of the coding process, but obviously it must be done
- * carefully to make sure that the replacement `free' can deallocate
- * memory allocated by the earlier `alloc' function(s).
+ * carefully to make sure that the replacement 'free' can deallocate
+ * memory allocated by the earlier 'alloc' function(s).
*
* Multithreaded mode: liblzma might internally store pointers to the
* lzma_allocator given via the lzma_stream structure. The application
@@ -422,7 +421,7 @@ typedef struct {
* liblzma never sets this to zero.
*
* \return Pointer to the beginning of a memory block of
- * `size' bytes, or NULL if allocation fails
+ * 'size' bytes, or NULL if allocation fails
* for some reason. When allocation fails, functions
* of liblzma return LZMA_MEM_ERROR.
*
@@ -622,7 +621,7 @@ typedef struct {
* to and get output from liblzma.
*
* See the description of the coder-specific initialization function to find
- * out what `action' values are supported by the coder.
+ * out what 'action' values are supported by the coder.
*
* \param strm Pointer to lzma_stream that is at least initialized
* with LZMA_STREAM_INIT.
diff --git a/src/liblzma/api/lzma/bcj.h b/src/liblzma/api/lzma/bcj.h
index 0c84e0c..7f6611f 100644
--- a/src/liblzma/api/lzma/bcj.h
+++ b/src/liblzma/api/lzma/bcj.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/bcj.h
* \brief Branch/Call/Jump conversion filters
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -53,6 +52,11 @@
*/
#define LZMA_FILTER_ARM64 LZMA_VLI_C(0x0A)
+/**
+ * \brief Filter for RISC-V binaries
+ */
+#define LZMA_FILTER_RISCV LZMA_VLI_C(0x0B)
+
/**
* \brief Options for BCJ filters
diff --git a/src/liblzma/api/lzma/block.h b/src/liblzma/api/lzma/block.h
index ec5e77a..05b77e5 100644
--- a/src/liblzma/api/lzma/block.h
+++ b/src/liblzma/api/lzma/block.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/block.h
* \brief .xz Block handling
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/check.h b/src/liblzma/api/lzma/check.h
index b37197d..e7a50ed 100644
--- a/src/liblzma/api/lzma/check.h
+++ b/src/liblzma/api/lzma/check.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/check.h
* \brief Integrity checks
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/container.h b/src/liblzma/api/lzma/container.h
index 2849fbf..8e4af42 100644
--- a/src/liblzma/api/lzma/container.h
+++ b/src/liblzma/api/lzma/container.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/container.h
* \brief File formats
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -297,7 +296,7 @@ extern LZMA_API(uint64_t) lzma_easy_decoder_memusage(uint32_t preset)
* to call lzma_end() after failed initialization.
*
* If initialization succeeds, use lzma_code() to do the actual encoding.
- * Valid values for `action' (the second argument of lzma_code()) are
+ * Valid values for 'action' (the second argument of lzma_code()) are
* LZMA_RUN, LZMA_SYNC_FLUSH, LZMA_FULL_FLUSH, and LZMA_FINISH. In future,
* there may be compression levels or flags that don't support LZMA_SYNC_FLUSH.
*
@@ -436,6 +435,34 @@ extern LZMA_API(lzma_ret) lzma_stream_encoder_mt(
/**
+ * \brief Calculate recommended Block size for multithreaded .xz encoder
+ *
+ * This calculates a recommended Block size for multithreaded encoding given
+ * a filter chain. This is used internally by lzma_stream_encoder_mt() to
+ * determine the Block size if the block_size member is not set to the
+ * special value of 0 in the lzma_mt options struct.
+ *
+ * If one wishes to change the filters between Blocks, this function is
+ * helpful to set the block_size member of the lzma_mt struct before calling
+ * lzma_stream_encoder_mt(). Since the block_size member represents the
+ * maximum possible Block size for the multithreaded .xz encoder, one can
+ * use this function to find the maximum recommended Block size based on
+ * all planned filter chains. Otherwise, the multithreaded encoder will
+ * base its maximum Block size on the first filter chain used (if the
+ * block_size member is not set), which may unnecessarily limit the Block
+ * size for a later filter chain.
+ *
+ * \param filters Array of filters terminated with
+ * .id == LZMA_VLI_UNKNOWN.
+ *
+ * \return Recommended Block size in bytes, or UINT64_MAX if
+ * an error occurred.
+ */
+extern LZMA_API(uint64_t) lzma_mt_block_size(const lzma_filter *filters)
+ lzma_nothrow;
+
+
+/**
* \brief Initialize .lzma encoder (legacy file format)
*
* The .lzma format is sometimes called the LZMA_Alone format, which is the
@@ -651,13 +678,13 @@ extern LZMA_API(lzma_ret) lzma_microlzma_encoder(
* supported by liblzma, only the .xz and .lz formats allow concatenated
* files. Concatenated files are not allowed with the legacy .lzma format.
*
- * This flag also affects the usage of the `action' argument for lzma_code().
+ * This flag also affects the usage of the 'action' argument for lzma_code().
* When LZMA_CONCATENATED is used, lzma_code() won't return LZMA_STREAM_END
- * unless LZMA_FINISH is used as `action'. Thus, the application has to set
+ * unless LZMA_FINISH is used as 'action'. Thus, the application has to set
* LZMA_FINISH in the same way as it does when encoding.
*
* If LZMA_CONCATENATED is not used, the decoders still accept LZMA_FINISH
- * as `action' for lzma_code(), but the usage of LZMA_FINISH isn't required.
+ * as 'action' for lzma_code(), but the usage of LZMA_FINISH isn't required.
*/
#define LZMA_CONCATENATED UINT32_C(0x08)
@@ -765,7 +792,7 @@ extern LZMA_API(lzma_ret) lzma_stream_decoder_mt(
* as it doesn't support any decoder flags. It will return LZMA_STREAM_END
* after one .lzma stream.)
*
- * \param strm Pointer to lzma_stream that is at least initialized
+ * \param strm Pointer to lzma_stream that is at least initialized
* with LZMA_STREAM_INIT.
* \param memlimit Memory usage limit as bytes. Use UINT64_MAX
* to effectively disable the limiter. liblzma
@@ -791,7 +818,7 @@ extern LZMA_API(lzma_ret) lzma_auto_decoder(
/**
* \brief Initialize .lzma decoder (legacy file format)
*
- * Valid `action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * Valid 'action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
* There is no need to use LZMA_FINISH, but it's allowed because it may
* simplify certain types of applications.
*
diff --git a/src/liblzma/api/lzma/delta.h b/src/liblzma/api/lzma/delta.h
index 7a725bc..5ebacef 100644
--- a/src/liblzma/api/lzma/delta.h
+++ b/src/liblzma/api/lzma/delta.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/delta.h
* \brief Delta filter
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/filter.h b/src/liblzma/api/lzma/filter.h
index 1d887b4..e86809c 100644
--- a/src/liblzma/api/lzma/filter.h
+++ b/src/liblzma/api/lzma/filter.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/filter.h
* \brief Common filter related types and functions
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -43,7 +42,7 @@ typedef struct {
/**
* \brief Filter ID
*
- * Use constants whose name begin with `LZMA_FILTER_' to specify
+ * Use constants whose name begin with 'LZMA_FILTER_' to specify
* different filters. In an array of lzma_filter structures, use
* LZMA_VLI_UNKNOWN to indicate end of filters.
*
@@ -199,7 +198,7 @@ extern LZMA_API(uint64_t) lzma_raw_decoder_memusage(const lzma_filter *filters)
*
* This function may be useful when implementing custom file formats.
*
- * The `action' with lzma_code() can be LZMA_RUN, LZMA_SYNC_FLUSH (if the
+ * The 'action' with lzma_code() can be LZMA_RUN, LZMA_SYNC_FLUSH (if the
* filter chain supports it), or LZMA_FINISH.
*
* \param strm Pointer to lzma_stream that is at least
@@ -223,7 +222,7 @@ extern LZMA_API(lzma_ret) lzma_raw_encoder(
*
* The initialization of raw decoder goes similarly to raw encoder.
*
- * The `action' with lzma_code() can be LZMA_RUN or LZMA_FINISH. Using
+ * The 'action' with lzma_code() can be LZMA_RUN or LZMA_FINISH. Using
* LZMA_FINISH is not required, it is supported just for convenience.
*
* \param strm Pointer to lzma_stream that is at least
diff --git a/src/liblzma/api/lzma/hardware.h b/src/liblzma/api/lzma/hardware.h
index f34897d..7a1a84f 100644
--- a/src/liblzma/api/lzma/hardware.h
+++ b/src/liblzma/api/lzma/hardware.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/hardware.h
* \brief Hardware information
@@ -23,9 +25,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/index.h b/src/liblzma/api/lzma/index.h
index 6eee4d6..b17025e 100644
--- a/src/liblzma/api/lzma/index.h
+++ b/src/liblzma/api/lzma/index.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/index.h
* \brief Handling of .xz Index and related information
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -234,7 +233,7 @@ typedef struct {
} block;
/**
- * \private Internal struct.
+ * \private Internal data
*
* Internal data which is used to store the state of the iterator.
* The exact format may vary between liblzma versions, so don't
@@ -302,6 +301,28 @@ typedef enum {
/**
+ * \brief Mask for return value from lzma_index_checks() for check none
+ *
+ * \note This and the other CHECK_MASK macros were added in 5.5.1alpha.
+ */
+#define LZMA_INDEX_CHECK_MASK_NONE (UINT32_C(1) << LZMA_CHECK_NONE)
+
+/**
+ * \brief Mask for return value from lzma_index_checks() for check CRC32
+ */
+#define LZMA_INDEX_CHECK_MASK_CRC32 (UINT32_C(1) << LZMA_CHECK_CRC32)
+
+/**
+ * \brief Mask for return value from lzma_index_checks() for check CRC64
+ */
+#define LZMA_INDEX_CHECK_MASK_CRC64 (UINT32_C(1) << LZMA_CHECK_CRC64)
+
+/**
+ * \brief Mask for return value from lzma_index_checks() for check SHA256
+ */
+#define LZMA_INDEX_CHECK_MASK_SHA256 (UINT32_C(1) << LZMA_CHECK_SHA256)
+
+/**
* \brief Calculate memory usage of lzma_index
*
* On disk, the size of the Index field depends on both the number of Records
@@ -431,6 +452,7 @@ extern LZMA_API(lzma_ret) lzma_index_stream_flags(
* showing the Check types to the user.
*
* The bitmask is 1 << check_id, e.g. CRC32 is 1 << 1 and SHA-256 is 1 << 10.
+ * These masks are defined for convenience as LZMA_INDEX_CHECK_MASK_XXX
*
* \param i Pointer to lzma_index structure
*
@@ -651,7 +673,7 @@ extern LZMA_API(lzma_bool) lzma_index_iter_locate(
* function succeeds, the memory allocated for src
* is freed or moved to be part of dest, and all
* iterators pointing to src will become invalid.
-* \param allocator lzma_allocator for custom allocator functions.
+ * \param allocator lzma_allocator for custom allocator functions.
* Set to NULL to use malloc() and free().
*
* \return Possible lzma_ret values:
@@ -686,7 +708,7 @@ extern LZMA_API(lzma_index *) lzma_index_dup(
* \param strm Pointer to properly prepared lzma_stream
* \param i Pointer to lzma_index which should be encoded.
*
- * The valid `action' values for lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * The valid 'action' values for lzma_code() are LZMA_RUN and LZMA_FINISH.
* It is enough to use only one of them (you can choose freely).
*
* \return Possible lzma_ret values:
@@ -715,7 +737,7 @@ extern LZMA_API(lzma_ret) lzma_index_encoder(
* don't allow 0 here and return LZMA_PROG_ERROR;
* later versions treat 0 as if 1 had been specified.
*
- * Valid `action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * Valid 'action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
* There is no need to use LZMA_FINISH, but it's allowed because it may
* simplify certain types of applications.
*
@@ -771,7 +793,7 @@ extern LZMA_API(lzma_ret) lzma_index_buffer_encode(const lzma_index *i,
* lzma_index is allowed to require. The value
* pointed by this pointer is modified if and only
* if LZMA_MEMLIMIT_ERROR is returned.
- * \param allocator lzma_allocator for custom allocator functions.
+ * \param allocator lzma_allocator for custom allocator functions.
* Set to NULL to use malloc() and free().
* \param in Beginning of the input buffer
* \param in_pos The next byte will be read from in[*in_pos].
@@ -819,10 +841,10 @@ extern LZMA_API(lzma_ret) lzma_index_buffer_decode(lzma_index **i,
* expect to see the same exact value for the same file if you change the
* input buffer size or switch to a different liblzma version.
*
- * Valid `action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
+ * Valid 'action' arguments to lzma_code() are LZMA_RUN and LZMA_FINISH.
* You only need to use LZMA_RUN; LZMA_FINISH is only supported because it
* might be convenient for some applications. If you use LZMA_FINISH and if
- * lzma_code() asks the application to seek, remember to reset `action' back
+ * lzma_code() asks the application to seek, remember to reset 'action' back
* to LZMA_RUN unless you hit the end of the file again.
*
* Possible return values from lzma_code():
diff --git a/src/liblzma/api/lzma/index_hash.h b/src/liblzma/api/lzma/index_hash.h
index a2d4c48..68f9024 100644
--- a/src/liblzma/api/lzma/index_hash.h
+++ b/src/liblzma/api/lzma/index_hash.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/index_hash.h
* \brief Validate Index by using a hash function
@@ -9,9 +11,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/lzma12.h b/src/liblzma/api/lzma/lzma12.h
index 8ef6ea5..05f5b66 100644
--- a/src/liblzma/api/lzma/lzma12.h
+++ b/src/liblzma/api/lzma/lzma12.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/lzma12.h
* \brief LZMA1 and LZMA2 filters
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -289,7 +288,7 @@ typedef struct {
* \brief Number of literal context bits
*
* How many of the highest bits of the previous uncompressed
- * eight-bit byte (also known as `literal') are taken into
+ * eight-bit byte (also known as 'literal') are taken into
* account when predicting the bits of the next literal.
*
* E.g. in typical English text, an upper-case letter is
diff --git a/src/liblzma/api/lzma/stream_flags.h b/src/liblzma/api/lzma/stream_flags.h
index 7622a62..a33fe46 100644
--- a/src/liblzma/api/lzma/stream_flags.h
+++ b/src/liblzma/api/lzma/stream_flags.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/stream_flags.h
* \brief .xz Stream Header and Stream Footer encoder and decoder
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
diff --git a/src/liblzma/api/lzma/version.h b/src/liblzma/api/lzma/version.h
index 8dac382..53526b9 100644
--- a/src/liblzma/api/lzma/version.h
+++ b/src/liblzma/api/lzma/version.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/version.h
* \brief Version number
@@ -6,9 +8,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -20,10 +19,10 @@
#define LZMA_VERSION_MAJOR 5
/** \brief Minor version number of the liblzma release. */
-#define LZMA_VERSION_MINOR 4
+#define LZMA_VERSION_MINOR 6
/** \brief Patch version number of the liblzma release. */
-#define LZMA_VERSION_PATCH 5
+#define LZMA_VERSION_PATCH 2
/**
* \brief Version stability marker
diff --git a/src/liblzma/api/lzma/vli.h b/src/liblzma/api/lzma/vli.h
index f9ad155..6b04902 100644
--- a/src/liblzma/api/lzma/vli.h
+++ b/src/liblzma/api/lzma/vli.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/**
* \file lzma/vli.h
* \brief Variable-length integer handling
@@ -17,9 +19,6 @@
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#ifndef LZMA_H_INTERNAL
@@ -68,9 +67,8 @@ typedef uint64_t lzma_vli;
* This is useful to test that application has given acceptable values
* for example in the uncompressed_size and compressed_size variables.
*
- * \return True if the integer is representable as VLI or if it
- * indicates unknown value. False if the integer cannot be
- * represented as VLI.
+ * \return True if the integer is representable as a VLI or if it
+ * indicates an unknown value. False otherwise.
*/
#define lzma_vli_is_valid(vli) \
((vli) <= LZMA_VLI_MAX || (vli) == LZMA_VLI_UNKNOWN)
diff --git a/src/liblzma/check/Makefile.inc b/src/liblzma/check/Makefile.inc
index dc011a3..04cf1ff 100644
--- a/src/liblzma/check/Makefile.inc
+++ b/src/liblzma/check/Makefile.inc
@@ -1,9 +1,8 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
+
+## Note: There is no check for COND_CHECK_CRC32 because
+## currently crc32 is always enabled.
EXTRA_DIST += \
check/crc32_tablegen.c \
@@ -12,9 +11,10 @@ EXTRA_DIST += \
liblzma_la_SOURCES += \
check/check.c \
check/check.h \
- check/crc_macros.h
+ check/crc_common.h \
+ check/crc_x86_clmul.h \
+ check/crc32_arm64.h
-if COND_CHECK_CRC32
if COND_SMALL
liblzma_la_SOURCES += check/crc32_small.c
else
@@ -28,7 +28,6 @@ else
liblzma_la_SOURCES += check/crc32_fast.c
endif
endif
-endif
if COND_CHECK_CRC64
if COND_SMALL
diff --git a/src/liblzma/check/check.c b/src/liblzma/check/check.c
index 428ddae..7734ace 100644
--- a/src/liblzma/check/check.c
+++ b/src/liblzma/check/check.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file check.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
diff --git a/src/liblzma/check/check.h b/src/liblzma/check/check.h
index 8ae95d5..f0eb117 100644
--- a/src/liblzma/check/check.h
+++ b/src/liblzma/check/check.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file check.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_CHECK_H
diff --git a/src/liblzma/check/crc32_arm64.h b/src/liblzma/check/crc32_arm64.h
new file mode 100644
index 0000000..39c1c63
--- /dev/null
+++ b/src/liblzma/check/crc32_arm64.h
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file crc32_arm64.h
+/// \brief CRC32 calculation with ARM64 optimization
+//
+// Authors: Chenxi Mao
+// Jia Tan
+// Hans Jansen
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef LZMA_CRC32_ARM64_H
+#define LZMA_CRC32_ARM64_H
+
+// MSVC always has the CRC intrinsics available when building for ARM64
+// there is no need to include any header files.
+#ifndef _MSC_VER
+# include <arm_acle.h>
+#endif
+
+// If both versions are going to be built, we need runtime detection
+// to check if the instructions are supported.
+#if defined(CRC32_GENERIC) && defined(CRC32_ARCH_OPTIMIZED)
+# if defined(HAVE_GETAUXVAL) || defined(HAVE_ELF_AUX_INFO)
+# include <sys/auxv.h>
+# elif defined(_WIN32)
+# include <processthreadsapi.h>
+# elif defined(__APPLE__) && defined(HAVE_SYSCTLBYNAME)
+# include <sys/sysctl.h>
+# endif
+#endif
+
+// Some EDG-based compilers support ARM64 and define __GNUC__
+// (such as Nvidia's nvcc), but do not support function attributes.
+//
+// NOTE: Build systems check for this too, keep them in sync with this.
+#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
+# define crc_attr_target __attribute__((__target__("+crc")))
+#else
+# define crc_attr_target
+#endif
+
+
+crc_attr_target
+static uint32_t
+crc32_arch_optimized(const uint8_t *buf, size_t size, uint32_t crc)
+{
+ crc = ~crc;
+
+ // Align the input buffer because this was shown to be
+ // significantly faster than unaligned accesses.
+ const size_t align_amount = my_min(size, (0U - (uintptr_t)buf) & 7);
+
+ for (const uint8_t *limit = buf + align_amount; buf < limit; ++buf)
+ crc = __crc32b(crc, *buf);
+
+ size -= align_amount;
+
+ // Process 8 bytes at a time. The end point is determined by
+ // ignoring the least significant three bits of size to ensure
+ // we do not process past the bounds of the buffer. This guarantees
+ // that limit is a multiple of 8 and is strictly less than size.
+ for (const uint8_t *limit = buf + (size & ~(size_t)7);
+ buf < limit; buf += 8)
+ crc = __crc32d(crc, aligned_read64le(buf));
+
+ // Process the remaining bytes that are not 8 byte aligned.
+ for (const uint8_t *limit = buf + (size & 7); buf < limit; ++buf)
+ crc = __crc32b(crc, *buf);
+
+ return ~crc;
+}
+
+
+#if defined(CRC32_GENERIC) && defined(CRC32_ARCH_OPTIMIZED)
+static inline bool
+is_arch_extension_supported(void)
+{
+#if defined(HAVE_GETAUXVAL)
+ return (getauxval(AT_HWCAP) & HWCAP_CRC32) != 0;
+
+#elif defined(HAVE_ELF_AUX_INFO)
+ unsigned long feature_flags;
+
+ if (elf_aux_info(AT_HWCAP, &feature_flags, sizeof(feature_flags)) != 0)
+ return false;
+
+ return (feature_flags & HWCAP_CRC32) != 0;
+
+#elif defined(_WIN32)
+ return IsProcessorFeaturePresent(
+ PF_ARM_V8_CRC32_INSTRUCTIONS_AVAILABLE);
+
+#elif defined(__APPLE__) && defined(HAVE_SYSCTLBYNAME)
+ int has_crc32 = 0;
+ size_t size = sizeof(has_crc32);
+
+ // The sysctlbyname() function requires a string identifier for the
+ // CPU feature it tests. The Apple documentation lists the string
+ // "hw.optional.armv8_crc32", which can be found here:
+ // https://developer.apple.com/documentation/kernel/1387446-sysctlbyname/determining_instruction_set_characteristics#3915619
+ if (sysctlbyname("hw.optional.armv8_crc32", &has_crc32,
+ &size, NULL, 0) != 0)
+ return false;
+
+ return has_crc32;
+
+#else
+ // If a runtime detection method cannot be found, then this must
+ // be a compile time error. The checks in crc_common.h should ensure
+ // a runtime detection method is always found if this function is
+ // built. It would be possible to just return false here, but this
+ // is inefficient for binary size and runtime since only the generic
+ // method could ever be used.
+# error Runtime detection method unavailable.
+#endif
+}
+#endif
+
+#endif // LZMA_CRC32_ARM64_H
diff --git a/src/liblzma/check/crc32_fast.c b/src/liblzma/check/crc32_fast.c
index eed7350..16dbb74 100644
--- a/src/liblzma/check/crc32_fast.c
+++ b/src/liblzma/check/crc32_fast.c
@@ -1,35 +1,40 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc32.c
/// \brief CRC32 calculation
-///
-/// Calculate the CRC32 using the slice-by-eight algorithm.
-/// It is explained in this document:
-/// http://www.intel.com/technology/comms/perfnet/download/CRC_generators.pdf
-/// The code in this file is not the same as in Intel's paper, but
-/// the basic principle is identical.
-//
-// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Ilya Kurdyukov
+// Hans Jansen
//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
-#include "crc_macros.h"
+#include "crc_common.h"
+
+#if defined(CRC_X86_CLMUL)
+# define BUILDING_CRC32_CLMUL
+# include "crc_x86_clmul.h"
+#elif defined(CRC32_ARM64)
+# include "crc32_arm64.h"
+#endif
-// If you make any changes, do some benchmarking! Seemingly unrelated
-// changes can very easily ruin the performance (and very probably is
-// very compiler dependent).
-extern LZMA_API(uint32_t)
-lzma_crc32(const uint8_t *buf, size_t size, uint32_t crc)
+#ifdef CRC32_GENERIC
+
+///////////////////
+// Generic CRC32 //
+///////////////////
+
+static uint32_t
+crc32_generic(const uint8_t *buf, size_t size, uint32_t crc)
{
crc = ~crc;
#ifdef WORDS_BIGENDIAN
- crc = bswap32(crc);
+ crc = byteswap32(crc);
#endif
if (size > 8) {
@@ -75,8 +80,125 @@ lzma_crc32(const uint8_t *buf, size_t size, uint32_t crc)
crc = lzma_crc32_table[0][*buf++ ^ A(crc)] ^ S8(crc);
#ifdef WORDS_BIGENDIAN
- crc = bswap32(crc);
+ crc = byteswap32(crc);
#endif
return ~crc;
}
+#endif
+
+
+#if defined(CRC32_GENERIC) && defined(CRC32_ARCH_OPTIMIZED)
+
+//////////////////////////
+// Function dispatching //
+//////////////////////////
+
+// If both the generic and arch-optimized implementations are built, then
+// the function to use is selected at runtime because the system running
+// the binary might not have the arch-specific instruction set extension(s)
+// available. The dispatch methods in order of priority:
+//
+// 1. Constructor. This method uses __attribute__((__constructor__)) to
+// set crc32_func at load time. This avoids extra computation (and any
+// unlikely threading bugs) on the first call to lzma_crc32() to decide
+// which implementation should be used.
+//
+// 2. First Call Resolution. On the very first call to lzma_crc32(), the
+// call will be directed to crc32_dispatch() instead. This will set the
+// appropriate implementation function and will not be called again.
+// This method does not use any kind of locking but is safe because if
+// multiple threads run the dispatcher simultaneously then they will all
+// set crc32_func to the same value.
+
+typedef uint32_t (*crc32_func_type)(
+ const uint8_t *buf, size_t size, uint32_t crc);
+
+// This resolver is shared between all dispatch methods.
+static crc32_func_type
+crc32_resolve(void)
+{
+ return is_arch_extension_supported()
+ ? &crc32_arch_optimized : &crc32_generic;
+}
+
+
+#ifdef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
+// Constructor method.
+# define CRC32_SET_FUNC_ATTR __attribute__((__constructor__))
+static crc32_func_type crc32_func;
+#else
+// First Call Resolution method.
+# define CRC32_SET_FUNC_ATTR
+static uint32_t crc32_dispatch(const uint8_t *buf, size_t size, uint32_t crc);
+static crc32_func_type crc32_func = &crc32_dispatch;
+#endif
+
+CRC32_SET_FUNC_ATTR
+static void
+crc32_set_func(void)
+{
+ crc32_func = crc32_resolve();
+ return;
+}
+
+#ifndef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
+static uint32_t
+crc32_dispatch(const uint8_t *buf, size_t size, uint32_t crc)
+{
+ // When __attribute__((__constructor__)) isn't supported, set the
+ // function pointer without any locking. If multiple threads run
+ // the detection code in parallel, they will all end up setting
+ // the pointer to the same value. This avoids the use of
+ // mythread_once() on every call to lzma_crc32() but this likely
+ // isn't strictly standards compliant. Let's change it if it breaks.
+ crc32_set_func();
+ return crc32_func(buf, size, crc);
+}
+
+#endif
+#endif
+
+
+extern LZMA_API(uint32_t)
+lzma_crc32(const uint8_t *buf, size_t size, uint32_t crc)
+{
+#if defined(CRC32_GENERIC) && defined(CRC32_ARCH_OPTIMIZED)
+ // On x86-64, if CLMUL is available, it is the best for non-tiny
+ // inputs, being over twice as fast as the generic slice-by-four
+ // version. However, for size <= 16 it's different. In the extreme
+ // case of size == 1 the generic version can be five times faster.
+ // At size >= 8 the CLMUL starts to become reasonable. It
+ // varies depending on the alignment of buf too.
+ //
+ // The above doesn't include the overhead of mythread_once().
+ // At least on x86-64 GNU/Linux, pthread_once() is very fast but
+ // it still makes lzma_crc32(buf, 1, crc) 50-100 % slower. When
+ // size reaches 12-16 bytes the overhead becomes negligible.
+ //
+ // So using the generic version for size <= 16 may give better
+ // performance with tiny inputs but if such inputs happen rarely
+ // it's not so obvious because then the lookup table of the
+ // generic version may not be in the processor cache.
+#ifdef CRC_USE_GENERIC_FOR_SMALL_INPUTS
+ if (size <= 16)
+ return crc32_generic(buf, size, crc);
+#endif
+
+/*
+#ifndef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
+ // See crc32_dispatch(). This would be the alternative which uses
+ // locking and doesn't use crc32_dispatch(). Note that on Windows
+ // this method needs Vista threads.
+ mythread_once(crc64_set_func);
+#endif
+*/
+ return crc32_func(buf, size, crc);
+
+#elif defined(CRC32_ARCH_OPTIMIZED)
+ return crc32_arch_optimized(buf, size, crc);
+
+#else
+ return crc32_generic(buf, size, crc);
+#endif
+}
diff --git a/src/liblzma/check/crc32_small.c b/src/liblzma/check/crc32_small.c
index 186966e..6a1bd66 100644
--- a/src/liblzma/check/crc32_small.c
+++ b/src/liblzma/check/crc32_small.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc32_small.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
diff --git a/src/liblzma/check/crc32_table.c b/src/liblzma/check/crc32_table.c
index b11762a..c141cef 100644
--- a/src/liblzma/check/crc32_table.c
+++ b/src/liblzma/check/crc32_table.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc32_table.c
@@ -5,18 +7,36 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
+
+// FIXME: Compared to crc_common.h this has to check for __x86_64__ too
+// so that in 32-bit builds crc32_x86.S won't break due to a missing table.
+#if defined(HAVE_USABLE_CLMUL) && ((defined(__x86_64__) && defined(__SSSE3__) \
+ && defined(__SSE4_1__) && defined(__PCLMUL__)) \
+ || (defined(__e2k__) && __iset__ >= 6))
+# define NO_CRC32_TABLE
+
+#elif defined(HAVE_ARM64_CRC32) \
+ && !defined(WORDS_BIGENDIAN) \
+ && defined(__ARM_FEATURE_CRC32)
+# define NO_CRC32_TABLE
+#endif
+
+
+#if !defined(HAVE_ENCODERS) && defined(NO_CRC32_TABLE)
+// No table needed. Use a typedef to avoid an empty translation unit.
+typedef void lzma_crc32_dummy;
+
+#else
// Having the declaration here silences clang -Wmissing-variable-declarations.
extern const uint32_t lzma_crc32_table[8][256];
-#ifdef WORDS_BIGENDIAN
-# include "crc32_table_be.h"
-#else
-# include "crc32_table_le.h"
+# ifdef WORDS_BIGENDIAN
+# include "crc32_table_be.h"
+# else
+# include "crc32_table_le.h"
+# endif
#endif
diff --git a/src/liblzma/check/crc32_table_be.h b/src/liblzma/check/crc32_table_be.h
index c483cb6..505c230 100644
--- a/src/liblzma/check/crc32_table_be.h
+++ b/src/liblzma/check/crc32_table_be.h
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by crc32_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by crc32_tablegen.c.
const uint32_t lzma_crc32_table[8][256] = {
{
diff --git a/src/liblzma/check/crc32_table_le.h b/src/liblzma/check/crc32_table_le.h
index 25f4fc4..e89c21a 100644
--- a/src/liblzma/check/crc32_table_le.h
+++ b/src/liblzma/check/crc32_table_le.h
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by crc32_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by crc32_tablegen.c.
const uint32_t lzma_crc32_table[8][256] = {
{
diff --git a/src/liblzma/check/crc32_tablegen.c b/src/liblzma/check/crc32_tablegen.c
index 31a4d27..b8cf459 100644
--- a/src/liblzma/check/crc32_tablegen.c
+++ b/src/liblzma/check/crc32_tablegen.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc32_tablegen.c
@@ -9,9 +11,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include <stdio.h>
@@ -44,7 +43,7 @@ init_crc32_table(void)
#ifdef WORDS_BIGENDIAN
for (size_t s = 0; s < 8; ++s)
for (size_t b = 0; b < 256; ++b)
- crc32_table[s][b] = bswap32(crc32_table[s][b]);
+ crc32_table[s][b] = byteswap32(crc32_table[s][b]);
#endif
return;
@@ -54,9 +53,11 @@ init_crc32_table(void)
static void
print_crc32_table(void)
{
- printf("/* This file has been automatically generated by "
- "crc32_tablegen.c. */\n\n"
- "const uint32_t lzma_crc32_table[8][256] = {\n\t{");
+ // Split the SPDX string so that it won't accidentally match
+ // when tools search for the string.
+ printf("// SPDX" "-License-Identifier" ": 0BSD\n\n"
+ "// This file has been generated by crc32_tablegen.c.\n\n"
+ "const uint32_t lzma_crc32_table[8][256] = {\n\t{");
for (size_t s = 0; s < 8; ++s) {
for (size_t b = 0; b < 256; ++b) {
@@ -82,9 +83,11 @@ print_crc32_table(void)
static void
print_lz_table(void)
{
- printf("/* This file has been automatically generated by "
- "crc32_tablegen.c. */\n\n"
- "const uint32_t lzma_lz_hash_table[256] = {");
+ // Split the SPDX string so that it won't accidentally match
+ // when tools search for the string.
+ printf("// SPDX" "-License-Identifier" ": 0BSD\n\n"
+ "// This file has been generated by crc32_tablegen.c.\n\n"
+ "const uint32_t lzma_lz_hash_table[256] = {");
for (size_t b = 0; b < 256; ++b) {
if ((b % 4) == 0)
diff --git a/src/liblzma/check/crc32_x86.S b/src/liblzma/check/crc32_x86.S
index 4f395df..ddc3cee 100644
--- a/src/liblzma/check/crc32_x86.S
+++ b/src/liblzma/check/crc32_x86.S
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Speed-optimized CRC32 using slicing-by-eight algorithm
*
@@ -11,9 +13,6 @@
* Authors: Igor Pavlov (original version)
* Lasse Collin (AT&T syntax, PIC support, better portability)
*
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
- *
* This code needs lzma_crc32_table, which can be created using the
* following C code:
diff --git a/src/liblzma/check/crc64_fast.c b/src/liblzma/check/crc64_fast.c
index 0c8622a..0ce83fe 100644
--- a/src/liblzma/check/crc64_fast.c
+++ b/src/liblzma/check/crc64_fast.c
@@ -1,85 +1,30 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc64.c
/// \brief CRC64 calculation
-///
-/// There are two methods in this file. crc64_generic uses the
-/// the slice-by-four algorithm. This is the same idea that is
-/// used in crc32_fast.c, but for CRC64 we use only four tables
-/// instead of eight to avoid increasing CPU cache usage.
-///
-/// crc64_clmul uses 32/64-bit x86 SSSE3, SSE4.1, and CLMUL instructions.
-/// It was derived from
-/// https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
-/// and the public domain code from https://github.com/rawrunprotected/crc
-/// (URLs were checked on 2022-11-07).
-///
-/// FIXME: Builds for 32-bit x86 use crc64_x86.S by default instead
-/// of this file and thus CLMUL version isn't available on 32-bit x86
-/// unless configured with --disable-assembler. Even then the lookup table
-/// isn't omitted in crc64_table.c since it doesn't know that assembly
-/// code has been disabled.
//
// Authors: Lasse Collin
// Ilya Kurdyukov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
+#include "crc_common.h"
-#undef CRC_GENERIC
-#undef CRC_CLMUL
-#undef CRC_USE_GENERIC_FOR_SMALL_INPUTS
-
-// If CLMUL cannot be used then only the generic slice-by-four is built.
-#if !defined(HAVE_USABLE_CLMUL)
-# define CRC_GENERIC 1
-
-// If CLMUL is allowed unconditionally in the compiler options then the
-// generic version can be omitted. Note that this doesn't work with MSVC
-// as I don't know how to detect the features here.
-//
-// NOTE: Keep this this in sync with crc64_table.c.
-#elif (defined(__SSSE3__) && defined(__SSE4_1__) && defined(__PCLMUL__)) \
- || (defined(__e2k__) && __iset__ >= 6)
-# define CRC_CLMUL 1
-
-// Otherwise build both and detect at runtime which version to use.
-#else
-# define CRC_GENERIC 1
-# define CRC_CLMUL 1
-
-/*
- // The generic code is much faster with 1-8-byte inputs and has
- // similar performance up to 16 bytes at least in microbenchmarks
- // (it depends on input buffer alignment too). If both versions are
- // built, this #define will use the generic version for inputs up to
- // 16 bytes and CLMUL for bigger inputs. It saves a little in code
- // size since the special cases for 0-16-byte inputs will be omitted
- // from the CLMUL code.
-# define CRC_USE_GENERIC_FOR_SMALL_INPUTS 1
-*/
-
-# if defined(_MSC_VER)
-# include <intrin.h>
-# elif defined(HAVE_CPUID_H)
-# include <cpuid.h>
-# endif
+#if defined(CRC_X86_CLMUL)
+# define BUILDING_CRC64_CLMUL
+# include "crc_x86_clmul.h"
#endif
+#ifdef CRC64_GENERIC
+
/////////////////////////////////
// Generic slice-by-four CRC64 //
/////////////////////////////////
-#ifdef CRC_GENERIC
-
-#include "crc_macros.h"
-
-
#ifdef WORDS_BIGENDIAN
# define A1(x) ((x) >> 56)
#else
@@ -94,7 +39,7 @@ crc64_generic(const uint8_t *buf, size_t size, uint64_t crc)
crc = ~crc;
#ifdef WORDS_BIGENDIAN
- crc = bswap64(crc);
+ crc = byteswap64(crc);
#endif
if (size > 4) {
@@ -128,7 +73,7 @@ crc64_generic(const uint8_t *buf, size_t size, uint64_t crc)
crc = lzma_crc64_table[0][*buf++ ^ A1(crc)] ^ S8(crc);
#ifdef WORDS_BIGENDIAN
- crc = bswap64(crc);
+ crc = byteswap64(crc);
#endif
return ~crc;
@@ -136,336 +81,40 @@ crc64_generic(const uint8_t *buf, size_t size, uint64_t crc)
#endif
-/////////////////////
-// x86 CLMUL CRC64 //
-/////////////////////
-
-#ifdef CRC_CLMUL
-
-#include <immintrin.h>
-
-
-/*
-// These functions were used to generate the constants
-// at the top of crc64_clmul().
-static uint64_t
-calc_lo(uint64_t poly)
-{
- uint64_t a = poly;
- uint64_t b = 0;
-
- for (unsigned i = 0; i < 64; ++i) {
- b = (b >> 1) | (a << 63);
- a = (a >> 1) ^ (a & 1 ? poly : 0);
- }
-
- return b;
-}
-
-static uint64_t
-calc_hi(uint64_t poly, uint64_t a)
-{
- for (unsigned i = 0; i < 64; ++i)
- a = (a >> 1) ^ (a & 1 ? poly : 0);
-
- return a;
-}
-*/
-
-
-#define MASK_L(in, mask, r) \
- r = _mm_shuffle_epi8(in, mask)
-
-#define MASK_H(in, mask, r) \
- r = _mm_shuffle_epi8(in, _mm_xor_si128(mask, vsign))
-
-#define MASK_LH(in, mask, low, high) \
- MASK_L(in, mask, low); \
- MASK_H(in, mask, high)
-
-
-// MSVC (VS2015 - VS2022) produces bad 32-bit x86 code from the CLMUL CRC
-// code when optimizations are enabled (release build). According to the bug
-// report, the ebx register is corrupted and the calculated result is wrong.
-// Trying to workaround the problem with "__asm mov ebx, ebx" didn't help.
-// The following pragma works and performance is still good. x86-64 builds
-// aren't affected by this problem.
-//
-// NOTE: Another pragma after the function restores the optimizations.
-// If the #if condition here is updated, the other one must be updated too.
-#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
- && defined(_M_IX86)
-# pragma optimize("g", off)
-#endif
-
-// EDG-based compilers (Intel's classic compiler and compiler for E2K) can
-// define __GNUC__ but the attribute must not be used with them.
-// The new Clang-based ICX needs the attribute.
-//
-// NOTE: Build systems check for this too, keep them in sync with this.
-#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
-__attribute__((__target__("ssse3,sse4.1,pclmul")))
-#endif
-// The intrinsics use 16-byte-aligned reads from buf, thus they may read
-// up to 15 bytes before or after the buffer (depending on the alignment
-// of the buf argument). The values of the extra bytes are ignored.
-// This unavoidably trips -fsanitize=address so address sanitizier has
-// to be disabled for this function.
-#if lzma_has_attribute(__no_sanitize_address__)
-__attribute__((__no_sanitize_address__))
-#endif
-static uint64_t
-crc64_clmul(const uint8_t *buf, size_t size, uint64_t crc)
-{
- // The prototypes of the intrinsics use signed types while most of
- // the values are treated as unsigned here. These warnings in this
- // function have been checked and found to be harmless so silence them.
-#if TUKLIB_GNUC_REQ(4, 6) || defined(__clang__)
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Wsign-conversion"
-# pragma GCC diagnostic ignored "-Wconversion"
-#endif
-
-#ifndef CRC_USE_GENERIC_FOR_SMALL_INPUTS
- // The code assumes that there is at least one byte of input.
- if (size == 0)
- return crc;
-#endif
-
- // const uint64_t poly = 0xc96c5795d7870f42; // CRC polynomial
- const uint64_t p = 0x92d8af2baf0e1e85; // (poly << 1) | 1
- const uint64_t mu = 0x9c3e466c172963d5; // (calc_lo(poly) << 1) | 1
- const uint64_t k2 = 0xdabe95afc7875f40; // calc_hi(poly, 1)
- const uint64_t k1 = 0xe05dd497ca393ae4; // calc_hi(poly, k2)
- const __m128i vfold0 = _mm_set_epi64x(p, mu);
- const __m128i vfold1 = _mm_set_epi64x(k2, k1);
-
- // Create a vector with 8-bit values 0 to 15. This is used to
- // construct control masks for _mm_blendv_epi8 and _mm_shuffle_epi8.
- const __m128i vramp = _mm_setr_epi32(
- 0x03020100, 0x07060504, 0x0b0a0908, 0x0f0e0d0c);
-
- // This is used to inverse the control mask of _mm_shuffle_epi8
- // so that bytes that wouldn't be picked with the original mask
- // will be picked and vice versa.
- const __m128i vsign = _mm_set1_epi8(0x80);
-
- // Memory addresses A to D and the distances between them:
- //
- // A B C D
- // [skip_start][size][skip_end]
- // [ size2 ]
- //
- // A and D are 16-byte aligned. B and C are 1-byte aligned.
- // skip_start and skip_end are 0-15 bytes. size is at least 1 byte.
- //
- // A = aligned_buf will initially point to this address.
- // B = The address pointed by the caller-supplied buf.
- // C = buf + size == aligned_buf + size2
- // D = buf + size + skip_end == aligned_buf + size2 + skip_end
- const size_t skip_start = (size_t)((uintptr_t)buf & 15);
- const size_t skip_end = (size_t)((0U - (uintptr_t)(buf + size)) & 15);
- const __m128i *aligned_buf = (const __m128i *)(
- (uintptr_t)buf & ~(uintptr_t)15);
-
- // If size2 <= 16 then the whole input fits into a single 16-byte
- // vector. If size2 > 16 then at least two 16-byte vectors must
- // be processed. If size2 > 16 && size <= 16 then there is only
- // one 16-byte vector's worth of input but it is unaligned in memory.
- //
- // NOTE: There is no integer overflow here if the arguments are valid.
- // If this overflowed, buf + size would too.
- size_t size2 = skip_start + size;
-
- // Masks to be used with _mm_blendv_epi8 and _mm_shuffle_epi8:
- // The first skip_start or skip_end bytes in the vectors will have
- // the high bit (0x80) set. _mm_blendv_epi8 and _mm_shuffle_epi8
- // will produce zeros for these positions. (Bitwise-xor of these
- // masks with vsign will produce the opposite behavior.)
- const __m128i mask_start
- = _mm_sub_epi8(vramp, _mm_set1_epi8(skip_start));
- const __m128i mask_end = _mm_sub_epi8(vramp, _mm_set1_epi8(skip_end));
-
- // Get the first 1-16 bytes into data0. If loading less than 16 bytes,
- // the bytes are loaded to the high bits of the vector and the least
- // significant positions are filled with zeros.
- const __m128i data0 = _mm_blendv_epi8(_mm_load_si128(aligned_buf),
- _mm_setzero_si128(), mask_start);
- ++aligned_buf;
-
-#if defined(__i386__) || defined(_M_IX86)
- const __m128i initial_crc = _mm_set_epi64x(0, ~crc);
-#else
- // GCC and Clang would produce good code with _mm_set_epi64x
- // but MSVC needs _mm_cvtsi64_si128 on x86-64.
- const __m128i initial_crc = _mm_cvtsi64_si128(~crc);
-#endif
+#if defined(CRC64_GENERIC) && defined(CRC64_ARCH_OPTIMIZED)
- __m128i v0, v1, v2, v3;
-
-#ifndef CRC_USE_GENERIC_FOR_SMALL_INPUTS
- if (size <= 16) {
- // Right-shift initial_crc by 1-16 bytes based on "size"
- // and store the result in v1 (high bytes) and v0 (low bytes).
- //
- // NOTE: The highest 8 bytes of initial_crc are zeros so
- // v1 will be filled with zeros if size >= 8. The highest 8
- // bytes of v1 will always become zeros.
- //
- // [ v1 ][ v0 ]
- // [ initial_crc ] size == 1
- // [ initial_crc ] size == 2
- // [ initial_crc ] size == 15
- // [ initial_crc ] size == 16 (all in v0)
- const __m128i mask_low = _mm_add_epi8(
- vramp, _mm_set1_epi8(size - 16));
- MASK_LH(initial_crc, mask_low, v0, v1);
-
- if (size2 <= 16) {
- // There are 1-16 bytes of input and it is all
- // in data0. Copy the input bytes to v3. If there
- // are fewer than 16 bytes, the low bytes in v3
- // will be filled with zeros. That is, the input
- // bytes are stored to the same position as
- // (part of) initial_crc is in v0.
- MASK_L(data0, mask_end, v3);
- } else {
- // There are 2-16 bytes of input but not all bytes
- // are in data0.
- const __m128i data1 = _mm_load_si128(aligned_buf);
-
- // Collect the 2-16 input bytes from data0 and data1
- // to v2 and v3, and bitwise-xor them with the
- // low bits of initial_crc in v0. Note that the
- // the second xor is below this else-block as it
- // is shared with the other branch.
- MASK_H(data0, mask_end, v2);
- MASK_L(data1, mask_end, v3);
- v0 = _mm_xor_si128(v0, v2);
- }
+//////////////////////////
+// Function dispatching //
+//////////////////////////
- v0 = _mm_xor_si128(v0, v3);
- v1 = _mm_alignr_epi8(v1, v0, 8);
- } else
-#endif
- {
- const __m128i data1 = _mm_load_si128(aligned_buf);
- MASK_LH(initial_crc, mask_start, v0, v1);
- v0 = _mm_xor_si128(v0, data0);
- v1 = _mm_xor_si128(v1, data1);
-
-#define FOLD \
- v1 = _mm_xor_si128(v1, _mm_clmulepi64_si128(v0, vfold1, 0x00)); \
- v0 = _mm_xor_si128(v1, _mm_clmulepi64_si128(v0, vfold1, 0x11));
-
- while (size2 > 32) {
- ++aligned_buf;
- size2 -= 16;
- FOLD
- v1 = _mm_load_si128(aligned_buf);
- }
-
- if (size2 < 32) {
- MASK_H(v0, mask_end, v2);
- MASK_L(v0, mask_end, v0);
- MASK_L(v1, mask_end, v3);
- v1 = _mm_or_si128(v2, v3);
- }
-
- FOLD
- v1 = _mm_srli_si128(v0, 8);
-#undef FOLD
- }
+// If both the generic and arch-optimized implementations are usable, then
+// the function that is used is selected at runtime. See crc32_fast.c.
- v1 = _mm_xor_si128(_mm_clmulepi64_si128(v0, vfold1, 0x10), v1);
- v0 = _mm_clmulepi64_si128(v1, vfold0, 0x00);
- v2 = _mm_clmulepi64_si128(v0, vfold0, 0x10);
- v0 = _mm_xor_si128(_mm_xor_si128(v2, _mm_slli_si128(v0, 8)), v1);
+typedef uint64_t (*crc64_func_type)(
+ const uint8_t *buf, size_t size, uint64_t crc);
-#if defined(__i386__) || defined(_M_IX86)
- return ~(((uint64_t)(uint32_t)_mm_extract_epi32(v0, 3) << 32) |
- (uint64_t)(uint32_t)_mm_extract_epi32(v0, 2));
-#else
- return ~(uint64_t)_mm_extract_epi64(v0, 1);
-#endif
-
-#if TUKLIB_GNUC_REQ(4, 6) || defined(__clang__)
-# pragma GCC diagnostic pop
-#endif
-}
-#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
- && defined(_M_IX86)
-# pragma optimize("", on)
-#endif
-#endif
-
-
-////////////////////////
-// Detect CPU support //
-////////////////////////
-
-#if defined(CRC_GENERIC) && defined(CRC_CLMUL)
-static inline bool
-is_clmul_supported(void)
+static crc64_func_type
+crc64_resolve(void)
{
- int success = 1;
- uint32_t r[4]; // eax, ebx, ecx, edx
-
-#if defined(_MSC_VER)
- // This needs <intrin.h> with MSVC. ICC has it as a built-in
- // on all platforms.
- __cpuid(r, 1);
-#elif defined(HAVE_CPUID_H)
- // Compared to just using __asm__ to run CPUID, this also checks
- // that CPUID is supported and saves and restores ebx as that is
- // needed with GCC < 5 with position-independent code (PIC).
- success = __get_cpuid(1, &r[0], &r[1], &r[2], &r[3]);
-#else
- // Just a fallback that shouldn't be needed.
- __asm__("cpuid\n\t"
- : "=a"(r[0]), "=b"(r[1]), "=c"(r[2]), "=d"(r[3])
- : "a"(1), "c"(0));
-#endif
-
- // Returns true if these are supported:
- // CLMUL (bit 1 in ecx)
- // SSSE3 (bit 9 in ecx)
- // SSE4.1 (bit 19 in ecx)
- const uint32_t ecx_mask = (1 << 1) | (1 << 9) | (1 << 19);
- return success && (r[2] & ecx_mask) == ecx_mask;
-
- // Alternative methods that weren't used:
- // - ICC's _may_i_use_cpu_feature: the other methods should work too.
- // - GCC >= 6 / Clang / ICX __builtin_cpu_supports("pclmul")
- //
- // CPUID decding is needed with MSVC anyway and older GCC. This keeps
- // the feature checks in the build system simpler too. The nice thing
- // about __builtin_cpu_supports would be that it generates very short
- // code as is it only reads a variable set at startup but a few bytes
- // doesn't matter here.
+ return is_arch_extension_supported()
+ ? &crc64_arch_optimized : &crc64_generic;
}
-
#ifdef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
-# define CRC64_FUNC_INIT
# define CRC64_SET_FUNC_ATTR __attribute__((__constructor__))
+static crc64_func_type crc64_func;
#else
-# define CRC64_FUNC_INIT = &crc64_dispatch
# define CRC64_SET_FUNC_ATTR
static uint64_t crc64_dispatch(const uint8_t *buf, size_t size, uint64_t crc);
+static crc64_func_type crc64_func = &crc64_dispatch;
#endif
-// Pointer to the the selected CRC64 method.
-static uint64_t (*crc64_func)(const uint8_t *buf, size_t size, uint64_t crc)
- CRC64_FUNC_INIT;
-
-
CRC64_SET_FUNC_ATTR
static void
crc64_set_func(void)
{
- crc64_func = is_clmul_supported() ? &crc64_clmul : &crc64_generic;
+ crc64_func = crc64_resolve();
return;
}
@@ -474,12 +123,6 @@ crc64_set_func(void)
static uint64_t
crc64_dispatch(const uint8_t *buf, size_t size, uint64_t crc)
{
- // When __attribute__((__constructor__)) isn't supported, set the
- // function pointer without any locking. If multiple threads run
- // the detection code in parallel, they will all end up setting
- // the pointer to the same value. This avoids the use of
- // mythread_once() on every call to lzma_crc64() but this likely
- // isn't strictly standards compliant. Let's change it if it breaks.
crc64_set_func();
return crc64_func(buf, size, crc);
}
@@ -490,47 +133,22 @@ crc64_dispatch(const uint8_t *buf, size_t size, uint64_t crc)
extern LZMA_API(uint64_t)
lzma_crc64(const uint8_t *buf, size_t size, uint64_t crc)
{
-#if defined(CRC_GENERIC) && defined(CRC_CLMUL)
- // If CLMUL is available, it is the best for non-tiny inputs,
- // being over twice as fast as the generic slice-by-four version.
- // However, for size <= 16 it's different. In the extreme case
- // of size == 1 the generic version can be five times faster.
- // At size >= 8 the CLMUL starts to become reasonable. It
- // varies depending on the alignment of buf too.
- //
- // The above doesn't include the overhead of mythread_once().
- // At least on x86-64 GNU/Linux, pthread_once() is very fast but
- // it still makes lzma_crc64(buf, 1, crc) 50-100 % slower. When
- // size reaches 12-16 bytes the overhead becomes negligible.
- //
- // So using the generic version for size <= 16 may give better
- // performance with tiny inputs but if such inputs happen rarely
- // it's not so obvious because then the lookup table of the
- // generic version may not be in the processor cache.
+#if defined(CRC64_GENERIC) && defined(CRC64_ARCH_OPTIMIZED)
+
#ifdef CRC_USE_GENERIC_FOR_SMALL_INPUTS
if (size <= 16)
return crc64_generic(buf, size, crc);
#endif
-
-/*
-#ifndef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
- // See crc64_dispatch(). This would be the alternative which uses
- // locking and doesn't use crc64_dispatch(). Note that on Windows
- // this method needs Vista threads.
- mythread_once(crc64_set_func);
-#endif
-*/
-
return crc64_func(buf, size, crc);
-#elif defined(CRC_CLMUL)
- // If CLMUL is used unconditionally without runtime CPU detection
- // then omitting the generic version and its 8 KiB lookup table
- // makes the library smaller.
+#elif defined(CRC64_ARCH_OPTIMIZED)
+ // If arch-optimized version is used unconditionally without runtime
+ // CPU detection then omitting the generic version and its 8 KiB
+ // lookup table makes the library smaller.
//
// FIXME: Lookup table isn't currently omitted on 32-bit x86,
// see crc64_table.c.
- return crc64_clmul(buf, size, crc);
+ return crc64_arch_optimized(buf, size, crc);
#else
return crc64_generic(buf, size, crc);
diff --git a/src/liblzma/check/crc64_small.c b/src/liblzma/check/crc64_small.c
index 420f7cf..ee4ea26 100644
--- a/src/liblzma/check/crc64_small.c
+++ b/src/liblzma/check/crc64_small.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc64_small.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
diff --git a/src/liblzma/check/crc64_table.c b/src/liblzma/check/crc64_table.c
index 688e527..78e4275 100644
--- a/src/liblzma/check/crc64_table.c
+++ b/src/liblzma/check/crc64_table.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc64_table.c
@@ -5,19 +7,21 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
-// FIXME: Compared to crc64_fast.c this has to check for __x86_64__ too
+// FIXME: Compared to crc_common.h this has to check for __x86_64__ too
// so that in 32-bit builds crc64_x86.S won't break due to a missing table.
-#if (defined(__x86_64__) && defined(__SSSE3__) \
+#if defined(HAVE_USABLE_CLMUL) && ((defined(__x86_64__) && defined(__SSSE3__) \
&& defined(__SSE4_1__) && defined(__PCLMUL__)) \
- || (defined(__e2k__) && __iset__ >= 6)
+ || (defined(__e2k__) && __iset__ >= 6))
+# define NO_CRC64_TABLE
+#endif
+
+
+#ifdef NO_CRC64_TABLE
// No table needed. Use a typedef to avoid an empty translation unit.
typedef void lzma_crc64_dummy;
diff --git a/src/liblzma/check/crc64_table_be.h b/src/liblzma/check/crc64_table_be.h
index ea074f3..db76cc7 100644
--- a/src/liblzma/check/crc64_table_be.h
+++ b/src/liblzma/check/crc64_table_be.h
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by crc64_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by crc64_tablegen.c.
const uint64_t lzma_crc64_table[4][256] = {
{
diff --git a/src/liblzma/check/crc64_table_le.h b/src/liblzma/check/crc64_table_le.h
index 1196b31..e40a8c8 100644
--- a/src/liblzma/check/crc64_table_le.h
+++ b/src/liblzma/check/crc64_table_le.h
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by crc64_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by crc64_tablegen.c.
const uint64_t lzma_crc64_table[4][256] = {
{
diff --git a/src/liblzma/check/crc64_tablegen.c b/src/liblzma/check/crc64_tablegen.c
index fddaa7e..2035127 100644
--- a/src/liblzma/check/crc64_tablegen.c
+++ b/src/liblzma/check/crc64_tablegen.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file crc64_tablegen.c
@@ -8,9 +10,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include <stdio.h>
@@ -43,7 +42,7 @@ init_crc64_table(void)
#ifdef WORDS_BIGENDIAN
for (size_t s = 0; s < 4; ++s)
for (size_t b = 0; b < 256; ++b)
- crc64_table[s][b] = bswap64(crc64_table[s][b]);
+ crc64_table[s][b] = byteswap64(crc64_table[s][b]);
#endif
return;
@@ -53,9 +52,11 @@ init_crc64_table(void)
static void
print_crc64_table(void)
{
- printf("/* This file has been automatically generated by "
- "crc64_tablegen.c. */\n\n"
- "const uint64_t lzma_crc64_table[4][256] = {\n\t{");
+ // Split the SPDX string so that it won't accidentally match
+ // when tools search for the string.
+ printf("// SPDX" "-License-Identifier" ": 0BSD\n\n"
+ "// This file has been generated by crc64_tablegen.c.\n\n"
+ "const uint64_t lzma_crc64_table[4][256] = {\n\t{");
for (size_t s = 0; s < 4; ++s) {
for (size_t b = 0; b < 256; ++b) {
diff --git a/src/liblzma/check/crc64_x86.S b/src/liblzma/check/crc64_x86.S
index 9aecf58..47f6081 100644
--- a/src/liblzma/check/crc64_x86.S
+++ b/src/liblzma/check/crc64_x86.S
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Speed-optimized CRC64 using slicing-by-four algorithm
*
@@ -7,9 +9,6 @@
* Authors: Igor Pavlov (original CRC32 assembly code)
* Lasse Collin (CRC64 adaptation of the modified CRC32 code)
*
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
- *
* This code needs lzma_crc64_table, which can be created using the
* following C code:
diff --git a/src/liblzma/check/crc_common.h b/src/liblzma/check/crc_common.h
new file mode 100644
index 0000000..63a7b5c
--- /dev/null
+++ b/src/liblzma/check/crc_common.h
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file crc_common.h
+/// \brief Some functions and macros for CRC32 and CRC64
+//
+// Authors: Lasse Collin
+// Ilya Kurdyukov
+// Hans Jansen
+// Jia Tan
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef LZMA_CRC_COMMON_H
+#define LZMA_CRC_COMMON_H
+
+#include "common.h"
+
+
+#ifdef WORDS_BIGENDIAN
+# define A(x) ((x) >> 24)
+# define B(x) (((x) >> 16) & 0xFF)
+# define C(x) (((x) >> 8) & 0xFF)
+# define D(x) ((x) & 0xFF)
+
+# define S8(x) ((x) << 8)
+# define S32(x) ((x) << 32)
+
+#else
+# define A(x) ((x) & 0xFF)
+# define B(x) (((x) >> 8) & 0xFF)
+# define C(x) (((x) >> 16) & 0xFF)
+# define D(x) ((x) >> 24)
+
+# define S8(x) ((x) >> 8)
+# define S32(x) ((x) >> 32)
+#endif
+
+
+// CRC CLMUL code needs this because accessing input buffers that aren't
+// aligned to the vector size will inherently trip the address sanitizer.
+#if lzma_has_attribute(__no_sanitize_address__)
+# define crc_attr_no_sanitize_address \
+ __attribute__((__no_sanitize_address__))
+#else
+# define crc_attr_no_sanitize_address
+#endif
+
+// Keep this in sync with changes to crc32_arm64.h
+#if defined(_WIN32) || defined(HAVE_GETAUXVAL) \
+ || defined(HAVE_ELF_AUX_INFO) \
+ || (defined(__APPLE__) && defined(HAVE_SYSCTLBYNAME))
+# define ARM64_RUNTIME_DETECTION 1
+#endif
+
+
+#undef CRC32_GENERIC
+#undef CRC64_GENERIC
+
+#undef CRC32_ARCH_OPTIMIZED
+#undef CRC64_ARCH_OPTIMIZED
+
+// The x86 CLMUL is used for both CRC32 and CRC64.
+#undef CRC_X86_CLMUL
+
+#undef CRC32_ARM64
+#undef CRC64_ARM64_CLMUL
+
+#undef CRC_USE_GENERIC_FOR_SMALL_INPUTS
+
+// ARM64 CRC32 instruction is only useful for CRC32. Currently, only
+// little endian is supported since we were unable to test on a big
+// endian machine.
+//
+// NOTE: Keep this and the next check in sync with the macro
+// NO_CRC32_TABLE in crc32_table.c
+#if defined(HAVE_ARM64_CRC32) && !defined(WORDS_BIGENDIAN)
+// Allow ARM64 CRC32 instruction without a runtime check if
+// __ARM_FEATURE_CRC32 is defined. GCC and Clang only define this if the
+// proper compiler options are used.
+# if defined(__ARM_FEATURE_CRC32)
+# define CRC32_ARCH_OPTIMIZED 1
+# define CRC32_ARM64 1
+# elif defined(ARM64_RUNTIME_DETECTION)
+# define CRC32_ARCH_OPTIMIZED 1
+# define CRC32_ARM64 1
+# define CRC32_GENERIC 1
+# endif
+#endif
+
+#if defined(HAVE_USABLE_CLMUL)
+// If CLMUL is allowed unconditionally in the compiler options then the
+// generic version can be omitted. Note that this doesn't work with MSVC
+// as I don't know how to detect the features here.
+//
+// NOTE: Keep this in sync with the NO_CRC32_TABLE macro in crc32_table.c
+// and NO_CRC64_TABLE in crc64_table.c.
+# if (defined(__SSSE3__) && defined(__SSE4_1__) && defined(__PCLMUL__)) \
+ || (defined(__e2k__) && __iset__ >= 6)
+# define CRC32_ARCH_OPTIMIZED 1
+# define CRC64_ARCH_OPTIMIZED 1
+# define CRC_X86_CLMUL 1
+# else
+# define CRC32_GENERIC 1
+# define CRC64_GENERIC 1
+# define CRC32_ARCH_OPTIMIZED 1
+# define CRC64_ARCH_OPTIMIZED 1
+# define CRC_X86_CLMUL 1
+
+/*
+ // The generic code is much faster with 1-8-byte inputs and
+ // has similar performance up to 16 bytes at least in
+ // microbenchmarks (it depends on input buffer alignment
+ // too). If both versions are built, this #define will use
+ // the generic version for inputs up to 16 bytes and CLMUL
+ // for bigger inputs. It saves a little in code size since
+ // the special cases for 0-16-byte inputs will be omitted
+ // from the CLMUL code.
+# define CRC_USE_GENERIC_FOR_SMALL_INPUTS 1
+*/
+# endif
+#endif
+
+// For CRC32 use the generic slice-by-eight implementation if no optimized
+// version is available.
+#if !defined(CRC32_ARCH_OPTIMIZED) && !defined(CRC32_GENERIC)
+# define CRC32_GENERIC 1
+#endif
+
+// For CRC64 use the generic slice-by-four implementation if no optimized
+// version is available.
+#if !defined(CRC64_ARCH_OPTIMIZED) && !defined(CRC64_GENERIC)
+# define CRC64_GENERIC 1
+#endif
+
+#endif
diff --git a/src/liblzma/check/crc_macros.h b/src/liblzma/check/crc_macros.h
deleted file mode 100644
index a7c21b7..0000000
--- a/src/liblzma/check/crc_macros.h
+++ /dev/null
@@ -1,30 +0,0 @@
-///////////////////////////////////////////////////////////////////////////////
-//
-/// \file crc_macros.h
-/// \brief Some endian-dependent macros for CRC32 and CRC64
-//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
-///////////////////////////////////////////////////////////////////////////////
-
-#ifdef WORDS_BIGENDIAN
-# define A(x) ((x) >> 24)
-# define B(x) (((x) >> 16) & 0xFF)
-# define C(x) (((x) >> 8) & 0xFF)
-# define D(x) ((x) & 0xFF)
-
-# define S8(x) ((x) << 8)
-# define S32(x) ((x) << 32)
-
-#else
-# define A(x) ((x) & 0xFF)
-# define B(x) (((x) >> 8) & 0xFF)
-# define C(x) (((x) >> 16) & 0xFF)
-# define D(x) ((x) >> 24)
-
-# define S8(x) ((x) >> 8)
-# define S32(x) ((x) >> 32)
-#endif
diff --git a/src/liblzma/check/crc_x86_clmul.h b/src/liblzma/check/crc_x86_clmul.h
new file mode 100644
index 0000000..f1254ec
--- /dev/null
+++ b/src/liblzma/check/crc_x86_clmul.h
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file crc_x86_clmul.h
+/// \brief CRC32 and CRC64 implementations using CLMUL instructions.
+///
+/// The CRC32 and CRC64 implementations use 32/64-bit x86 SSSE3, SSE4.1, and
+/// CLMUL instructions. This is compatible with Elbrus 2000 (E2K) too.
+///
+/// They were derived from
+/// https://www.researchgate.net/publication/263424619_Fast_CRC_computation
+/// and the public domain code from https://github.com/rawrunprotected/crc
+/// (URLs were checked on 2023-10-14).
+///
+/// While this file has both CRC32 and CRC64 implementations, only one
+/// should be built at a time to ensure that crc_simd_body() is inlined
+/// even with compilers with which lzma_always_inline expands to plain inline.
+/// The version to build is selected by defining BUILDING_CRC32_CLMUL or
+/// BUILDING_CRC64_CLMUL before including this file.
+///
+/// FIXME: Builds for 32-bit x86 use the assembly .S files by default
+/// unless configured with --disable-assembler. Even then the lookup table
+/// isn't omitted in crc64_table.c since it doesn't know that assembly
+/// code has been disabled.
+//
+// Authors: Ilya Kurdyukov
+// Hans Jansen
+// Lasse Collin
+// Jia Tan
+//
+///////////////////////////////////////////////////////////////////////////////
+
+// This file must not be included more than once.
+#ifdef LZMA_CRC_X86_CLMUL_H
+# error crc_x86_clmul.h was included twice.
+#endif
+#define LZMA_CRC_X86_CLMUL_H
+
+#include <immintrin.h>
+
+#if defined(_MSC_VER)
+# include <intrin.h>
+#elif defined(HAVE_CPUID_H)
+# include <cpuid.h>
+#endif
+
+
+// EDG-based compilers (Intel's classic compiler and compiler for E2K) can
+// define __GNUC__ but the attribute must not be used with them.
+// The new Clang-based ICX needs the attribute.
+//
+// NOTE: Build systems check for this too, keep them in sync with this.
+#if (defined(__GNUC__) || defined(__clang__)) && !defined(__EDG__)
+# define crc_attr_target \
+ __attribute__((__target__("ssse3,sse4.1,pclmul")))
+#else
+# define crc_attr_target
+#endif
+
+
+#define MASK_L(in, mask, r) r = _mm_shuffle_epi8(in, mask)
+
+#define MASK_H(in, mask, r) \
+ r = _mm_shuffle_epi8(in, _mm_xor_si128(mask, vsign))
+
+#define MASK_LH(in, mask, low, high) \
+ MASK_L(in, mask, low); \
+ MASK_H(in, mask, high)
+
+
+crc_attr_target
+crc_attr_no_sanitize_address
+static lzma_always_inline void
+crc_simd_body(const uint8_t *buf, const size_t size, __m128i *v0, __m128i *v1,
+ const __m128i vfold16, const __m128i initial_crc)
+{
+ // Create a vector with 8-bit values 0 to 15. This is used to
+ // construct control masks for _mm_blendv_epi8 and _mm_shuffle_epi8.
+ const __m128i vramp = _mm_setr_epi32(
+ 0x03020100, 0x07060504, 0x0b0a0908, 0x0f0e0d0c);
+
+ // This is used to inverse the control mask of _mm_shuffle_epi8
+ // so that bytes that wouldn't be picked with the original mask
+ // will be picked and vice versa.
+ const __m128i vsign = _mm_set1_epi8(-0x80);
+
+ // Memory addresses A to D and the distances between them:
+ //
+ // A B C D
+ // [skip_start][size][skip_end]
+ // [ size2 ]
+ //
+ // A and D are 16-byte aligned. B and C are 1-byte aligned.
+ // skip_start and skip_end are 0-15 bytes. size is at least 1 byte.
+ //
+ // A = aligned_buf will initially point to this address.
+ // B = The address pointed by the caller-supplied buf.
+ // C = buf + size == aligned_buf + size2
+ // D = buf + size + skip_end == aligned_buf + size2 + skip_end
+ const size_t skip_start = (size_t)((uintptr_t)buf & 15);
+ const size_t skip_end = (size_t)((0U - (uintptr_t)(buf + size)) & 15);
+ const __m128i *aligned_buf = (const __m128i *)(
+ (uintptr_t)buf & ~(uintptr_t)15);
+
+ // If size2 <= 16 then the whole input fits into a single 16-byte
+ // vector. If size2 > 16 then at least two 16-byte vectors must
+ // be processed. If size2 > 16 && size <= 16 then there is only
+ // one 16-byte vector's worth of input but it is unaligned in memory.
+ //
+ // NOTE: There is no integer overflow here if the arguments
+ // are valid. If this overflowed, buf + size would too.
+ const size_t size2 = skip_start + size;
+
+ // Masks to be used with _mm_blendv_epi8 and _mm_shuffle_epi8:
+ // The first skip_start or skip_end bytes in the vectors will have
+ // the high bit (0x80) set. _mm_blendv_epi8 and _mm_shuffle_epi8
+ // will produce zeros for these positions. (Bitwise-xor of these
+ // masks with vsign will produce the opposite behavior.)
+ const __m128i mask_start
+ = _mm_sub_epi8(vramp, _mm_set1_epi8((char)skip_start));
+ const __m128i mask_end
+ = _mm_sub_epi8(vramp, _mm_set1_epi8((char)skip_end));
+
+ // Get the first 1-16 bytes into data0. If loading less than 16
+ // bytes, the bytes are loaded to the high bits of the vector and
+ // the least significant positions are filled with zeros.
+ const __m128i data0 = _mm_blendv_epi8(_mm_load_si128(aligned_buf),
+ _mm_setzero_si128(), mask_start);
+ aligned_buf++;
+
+ __m128i v2, v3;
+
+#ifndef CRC_USE_GENERIC_FOR_SMALL_INPUTS
+ if (size <= 16) {
+ // Right-shift initial_crc by 1-16 bytes based on "size"
+ // and store the result in v1 (high bytes) and v0 (low bytes).
+ //
+ // NOTE: The highest 8 bytes of initial_crc are zeros so
+ // v1 will be filled with zeros if size >= 8. The highest
+ // 8 bytes of v1 will always become zeros.
+ //
+ // [ v1 ][ v0 ]
+ // [ initial_crc ] size == 1
+ // [ initial_crc ] size == 2
+ // [ initial_crc ] size == 15
+ // [ initial_crc ] size == 16 (all in v0)
+ const __m128i mask_low = _mm_add_epi8(
+ vramp, _mm_set1_epi8((char)(size - 16)));
+ MASK_LH(initial_crc, mask_low, *v0, *v1);
+
+ if (size2 <= 16) {
+ // There are 1-16 bytes of input and it is all
+ // in data0. Copy the input bytes to v3. If there
+ // are fewer than 16 bytes, the low bytes in v3
+ // will be filled with zeros. That is, the input
+ // bytes are stored to the same position as
+ // (part of) initial_crc is in v0.
+ MASK_L(data0, mask_end, v3);
+ } else {
+ // There are 2-16 bytes of input but not all bytes
+ // are in data0.
+ const __m128i data1 = _mm_load_si128(aligned_buf);
+
+ // Collect the 2-16 input bytes from data0 and data1
+ // to v2 and v3, and bitwise-xor them with the
+ // low bits of initial_crc in v0. Note that the
+ // the second xor is below this else-block as it
+ // is shared with the other branch.
+ MASK_H(data0, mask_end, v2);
+ MASK_L(data1, mask_end, v3);
+ *v0 = _mm_xor_si128(*v0, v2);
+ }
+
+ *v0 = _mm_xor_si128(*v0, v3);
+ *v1 = _mm_alignr_epi8(*v1, *v0, 8);
+ } else
+#endif
+ {
+ // There is more than 16 bytes of input.
+ const __m128i data1 = _mm_load_si128(aligned_buf);
+ const __m128i *end = (const __m128i*)(
+ (const char *)aligned_buf - 16 + size2);
+ aligned_buf++;
+
+ MASK_LH(initial_crc, mask_start, *v0, *v1);
+ *v0 = _mm_xor_si128(*v0, data0);
+ *v1 = _mm_xor_si128(*v1, data1);
+
+ while (aligned_buf < end) {
+ *v1 = _mm_xor_si128(*v1, _mm_clmulepi64_si128(
+ *v0, vfold16, 0x00));
+ *v0 = _mm_xor_si128(*v1, _mm_clmulepi64_si128(
+ *v0, vfold16, 0x11));
+ *v1 = _mm_load_si128(aligned_buf++);
+ }
+
+ if (aligned_buf != end) {
+ MASK_H(*v0, mask_end, v2);
+ MASK_L(*v0, mask_end, *v0);
+ MASK_L(*v1, mask_end, v3);
+ *v1 = _mm_or_si128(v2, v3);
+ }
+
+ *v1 = _mm_xor_si128(*v1, _mm_clmulepi64_si128(
+ *v0, vfold16, 0x00));
+ *v0 = _mm_xor_si128(*v1, _mm_clmulepi64_si128(
+ *v0, vfold16, 0x11));
+ *v1 = _mm_srli_si128(*v0, 8);
+ }
+}
+
+
+/////////////////////
+// x86 CLMUL CRC32 //
+/////////////////////
+
+/*
+// These functions were used to generate the constants
+// at the top of crc32_arch_optimized().
+static uint64_t
+calc_lo(uint64_t p, uint64_t a, int n)
+{
+ uint64_t b = 0; int i;
+ for (i = 0; i < n; i++) {
+ b = b >> 1 | (a & 1) << (n - 1);
+ a = (a >> 1) ^ ((0 - (a & 1)) & p);
+ }
+ return b;
+}
+
+// same as ~crc(&a, sizeof(a), ~0)
+static uint64_t
+calc_hi(uint64_t p, uint64_t a, int n)
+{
+ int i;
+ for (i = 0; i < n; i++)
+ a = (a >> 1) ^ ((0 - (a & 1)) & p);
+ return a;
+}
+*/
+
+#ifdef BUILDING_CRC32_CLMUL
+
+crc_attr_target
+crc_attr_no_sanitize_address
+static uint32_t
+crc32_arch_optimized(const uint8_t *buf, size_t size, uint32_t crc)
+{
+#ifndef CRC_USE_GENERIC_FOR_SMALL_INPUTS
+ // The code assumes that there is at least one byte of input.
+ if (size == 0)
+ return crc;
+#endif
+
+ // uint32_t poly = 0xedb88320;
+ const int64_t p = 0x1db710640; // p << 1
+ const int64_t mu = 0x1f7011641; // calc_lo(p, p, 32) << 1 | 1
+ const int64_t k5 = 0x163cd6124; // calc_hi(p, p, 32) << 1
+ const int64_t k4 = 0x0ccaa009e; // calc_hi(p, p, 64) << 1
+ const int64_t k3 = 0x1751997d0; // calc_hi(p, p, 128) << 1
+
+ const __m128i vfold4 = _mm_set_epi64x(mu, p);
+ const __m128i vfold8 = _mm_set_epi64x(0, k5);
+ const __m128i vfold16 = _mm_set_epi64x(k4, k3);
+
+ __m128i v0, v1, v2;
+
+ crc_simd_body(buf, size, &v0, &v1, vfold16,
+ _mm_cvtsi32_si128((int32_t)~crc));
+
+ v1 = _mm_xor_si128(
+ _mm_clmulepi64_si128(v0, vfold16, 0x10), v1); // xxx0
+ v2 = _mm_shuffle_epi32(v1, 0xe7); // 0xx0
+ v0 = _mm_slli_epi64(v1, 32); // [0]
+ v0 = _mm_clmulepi64_si128(v0, vfold8, 0x00);
+ v0 = _mm_xor_si128(v0, v2); // [1] [2]
+ v2 = _mm_clmulepi64_si128(v0, vfold4, 0x10);
+ v2 = _mm_clmulepi64_si128(v2, vfold4, 0x00);
+ v0 = _mm_xor_si128(v0, v2); // [2]
+ return ~(uint32_t)_mm_extract_epi32(v0, 2);
+}
+#endif // BUILDING_CRC32_CLMUL
+
+
+/////////////////////
+// x86 CLMUL CRC64 //
+/////////////////////
+
+/*
+// These functions were used to generate the constants
+// at the top of crc64_arch_optimized().
+static uint64_t
+calc_lo(uint64_t poly)
+{
+ uint64_t a = poly;
+ uint64_t b = 0;
+
+ for (unsigned i = 0; i < 64; ++i) {
+ b = (b >> 1) | (a << 63);
+ a = (a >> 1) ^ (a & 1 ? poly : 0);
+ }
+
+ return b;
+}
+
+static uint64_t
+calc_hi(uint64_t poly, uint64_t a)
+{
+ for (unsigned i = 0; i < 64; ++i)
+ a = (a >> 1) ^ (a & 1 ? poly : 0);
+
+ return a;
+}
+*/
+
+#ifdef BUILDING_CRC64_CLMUL
+
+// MSVC (VS2015 - VS2022) produces bad 32-bit x86 code from the CLMUL CRC
+// code when optimizations are enabled (release build). According to the bug
+// report, the ebx register is corrupted and the calculated result is wrong.
+// Trying to workaround the problem with "__asm mov ebx, ebx" didn't help.
+// The following pragma works and performance is still good. x86-64 builds
+// and CRC32 CLMUL aren't affected by this problem. The problem does not
+// happen in crc_simd_body() either (which is shared with CRC32 CLMUL anyway).
+//
+// NOTE: Another pragma after crc64_arch_optimized() restores
+// the optimizations. If the #if condition here is updated,
+// the other one must be updated too.
+#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
+ && defined(_M_IX86)
+# pragma optimize("g", off)
+#endif
+
+crc_attr_target
+crc_attr_no_sanitize_address
+static uint64_t
+crc64_arch_optimized(const uint8_t *buf, size_t size, uint64_t crc)
+{
+#ifndef CRC_USE_GENERIC_FOR_SMALL_INPUTS
+ // The code assumes that there is at least one byte of input.
+ if (size == 0)
+ return crc;
+#endif
+
+ // const uint64_t poly = 0xc96c5795d7870f42; // CRC polynomial
+ const uint64_t p = 0x92d8af2baf0e1e85; // (poly << 1) | 1
+ const uint64_t mu = 0x9c3e466c172963d5; // (calc_lo(poly) << 1) | 1
+ const uint64_t k2 = 0xdabe95afc7875f40; // calc_hi(poly, 1)
+ const uint64_t k1 = 0xe05dd497ca393ae4; // calc_hi(poly, k2)
+
+ const __m128i vfold8 = _mm_set_epi64x((int64_t)p, (int64_t)mu);
+ const __m128i vfold16 = _mm_set_epi64x((int64_t)k2, (int64_t)k1);
+
+ __m128i v0, v1, v2;
+
+#if defined(__i386__) || defined(_M_IX86)
+ crc_simd_body(buf, size, &v0, &v1, vfold16,
+ _mm_set_epi64x(0, (int64_t)~crc));
+#else
+ // GCC and Clang would produce good code with _mm_set_epi64x
+ // but MSVC needs _mm_cvtsi64_si128 on x86-64.
+ crc_simd_body(buf, size, &v0, &v1, vfold16,
+ _mm_cvtsi64_si128((int64_t)~crc));
+#endif
+
+ v1 = _mm_xor_si128(_mm_clmulepi64_si128(v0, vfold16, 0x10), v1);
+ v0 = _mm_clmulepi64_si128(v1, vfold8, 0x00);
+ v2 = _mm_clmulepi64_si128(v0, vfold8, 0x10);
+ v0 = _mm_xor_si128(_mm_xor_si128(v1, _mm_slli_si128(v0, 8)), v2);
+
+#if defined(__i386__) || defined(_M_IX86)
+ return ~(((uint64_t)(uint32_t)_mm_extract_epi32(v0, 3) << 32) |
+ (uint64_t)(uint32_t)_mm_extract_epi32(v0, 2));
+#else
+ return ~(uint64_t)_mm_extract_epi64(v0, 1);
+#endif
+}
+
+#if defined(_MSC_VER) && !defined(__INTEL_COMPILER) && !defined(__clang__) \
+ && defined(_M_IX86)
+# pragma optimize("", on)
+#endif
+
+#endif // BUILDING_CRC64_CLMUL
+
+
+// Inlining this function duplicates the function body in crc32_resolve() and
+// crc64_resolve(), but this is acceptable because this is a tiny function.
+static inline bool
+is_arch_extension_supported(void)
+{
+ int success = 1;
+ uint32_t r[4]; // eax, ebx, ecx, edx
+
+#if defined(_MSC_VER)
+ // This needs <intrin.h> with MSVC. ICC has it as a built-in
+ // on all platforms.
+ __cpuid(r, 1);
+#elif defined(HAVE_CPUID_H)
+ // Compared to just using __asm__ to run CPUID, this also checks
+ // that CPUID is supported and saves and restores ebx as that is
+ // needed with GCC < 5 with position-independent code (PIC).
+ success = __get_cpuid(1, &r[0], &r[1], &r[2], &r[3]);
+#else
+ // Just a fallback that shouldn't be needed.
+ __asm__("cpuid\n\t"
+ : "=a"(r[0]), "=b"(r[1]), "=c"(r[2]), "=d"(r[3])
+ : "a"(1), "c"(0));
+#endif
+
+ // Returns true if these are supported:
+ // CLMUL (bit 1 in ecx)
+ // SSSE3 (bit 9 in ecx)
+ // SSE4.1 (bit 19 in ecx)
+ const uint32_t ecx_mask = (1 << 1) | (1 << 9) | (1 << 19);
+ return success && (r[2] & ecx_mask) == ecx_mask;
+
+ // Alternative methods that weren't used:
+ // - ICC's _may_i_use_cpu_feature: the other methods should work too.
+ // - GCC >= 6 / Clang / ICX __builtin_cpu_supports("pclmul")
+ //
+ // CPUID decding is needed with MSVC anyway and older GCC. This keeps
+ // the feature checks in the build system simpler too. The nice thing
+ // about __builtin_cpu_supports would be that it generates very short
+ // code as is it only reads a variable set at startup but a few bytes
+ // doesn't matter here.
+}
diff --git a/src/liblzma/check/sha256.c b/src/liblzma/check/sha256.c
index 6feb342..bd0d280 100644
--- a/src/liblzma/check/sha256.c
+++ b/src/liblzma/check/sha256.c
@@ -1,24 +1,17 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file sha256.c
/// \brief SHA-256
-///
-/// \todo Crypto++ has x86 ASM optimizations. They use SSE so if they
-/// are imported to liblzma, SSE instructions need to be used
-/// conditionally to keep the code working on older boxes.
//
-// This code is based on the code found from 7-Zip, which has a modified
-// version of the SHA-256 found from Crypto++ <https://www.cryptopp.com/>.
-// The code was modified a little to fit into liblzma.
+// The C code is based on the public domain SHA-256 code found from
+// Crypto++ Library 5.5.1 released in 2007: https://www.cryptopp.com/
+// A few minor tweaks have been made in liblzma.
//
-// Authors: Kevin Springle
-// Wei Dai
-// Igor Pavlov
+// Authors: Wei Dai
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "check.h"
diff --git a/src/liblzma/common/Makefile.inc b/src/liblzma/common/Makefile.inc
index f0276a2..51b1aae 100644
--- a/src/liblzma/common/Makefile.inc
+++ b/src/liblzma/common/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
liblzma_la_SOURCES += \
common/common.c \
diff --git a/src/liblzma/common/alone_decoder.c b/src/liblzma/common/alone_decoder.c
index 1dc85ba..78af651 100644
--- a/src/liblzma/common/alone_decoder.c
+++ b/src/liblzma/common/alone_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "alone_decoder.h"
diff --git a/src/liblzma/common/alone_decoder.h b/src/liblzma/common/alone_decoder.h
index dfa031a..61ee24d 100644
--- a/src/liblzma/common/alone_decoder.h
+++ b/src/liblzma/common/alone_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_ALONE_DECODER_H
diff --git a/src/liblzma/common/alone_encoder.c b/src/liblzma/common/alone_encoder.c
index 7d3812f..21b0395 100644
--- a/src/liblzma/common/alone_encoder.c
+++ b/src/liblzma/common/alone_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file alone_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/auto_decoder.c b/src/liblzma/common/auto_decoder.c
index 2a5c089..fdd520f 100644
--- a/src/liblzma/common/auto_decoder.c
+++ b/src/liblzma/common/auto_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file auto_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_decoder.h"
diff --git a/src/liblzma/common/block_buffer_decoder.c b/src/liblzma/common/block_buffer_decoder.c
index b0ded90..55566cd 100644
--- a/src/liblzma/common/block_buffer_decoder.c
+++ b/src/liblzma/common/block_buffer_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_buffer_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "block_decoder.h"
diff --git a/src/liblzma/common/block_buffer_encoder.c b/src/liblzma/common/block_buffer_encoder.c
index fdef02d..df3b90e 100644
--- a/src/liblzma/common/block_buffer_encoder.c
+++ b/src/liblzma/common/block_buffer_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_buffer_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "block_buffer_encoder.h"
diff --git a/src/liblzma/common/block_buffer_encoder.h b/src/liblzma/common/block_buffer_encoder.h
index 653207f..5274ac4 100644
--- a/src/liblzma/common/block_buffer_encoder.h
+++ b/src/liblzma/common/block_buffer_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_buffer_encoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_BLOCK_BUFFER_ENCODER_H
diff --git a/src/liblzma/common/block_decoder.c b/src/liblzma/common/block_decoder.c
index be647d4..2e369d3 100644
--- a/src/liblzma/common/block_decoder.c
+++ b/src/liblzma/common/block_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "block_decoder.h"
diff --git a/src/liblzma/common/block_decoder.h b/src/liblzma/common/block_decoder.h
index 718c5ce..2cbf9ba 100644
--- a/src/liblzma/common/block_decoder.h
+++ b/src/liblzma/common/block_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_BLOCK_DECODER_H
diff --git a/src/liblzma/common/block_encoder.c b/src/liblzma/common/block_encoder.c
index 4a136ef..ce8c1de 100644
--- a/src/liblzma/common/block_encoder.c
+++ b/src/liblzma/common/block_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "block_encoder.h"
diff --git a/src/liblzma/common/block_encoder.h b/src/liblzma/common/block_encoder.h
index bd97c18..b7dfe9a 100644
--- a/src/liblzma/common/block_encoder.h
+++ b/src/liblzma/common/block_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_encoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_BLOCK_ENCODER_H
diff --git a/src/liblzma/common/block_header_decoder.c b/src/liblzma/common/block_header_decoder.c
index c4935dc..f0b2fbe 100644
--- a/src/liblzma/common/block_header_decoder.c
+++ b/src/liblzma/common/block_header_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_header_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/block_header_encoder.c b/src/liblzma/common/block_header_encoder.c
index 160425d..45e57a2 100644
--- a/src/liblzma/common/block_header_encoder.c
+++ b/src/liblzma/common/block_header_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_header_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/block_util.c b/src/liblzma/common/block_util.c
index acb3111..191f6d4 100644
--- a/src/liblzma/common/block_util.c
+++ b/src/liblzma/common/block_util.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file block_util.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/common.c b/src/liblzma/common/common.c
index adb50d7..cc0e06a 100644
--- a/src/liblzma/common/common.c
+++ b/src/liblzma/common/common.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file common.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/common.h b/src/liblzma/common/common.h
index 378923e..20af32f 100644
--- a/src/liblzma/common/common.h
+++ b/src/liblzma/common/common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file common.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_COMMON_H
diff --git a/src/liblzma/common/easy_buffer_encoder.c b/src/liblzma/common/easy_buffer_encoder.c
index 48eb56f..da610ce 100644
--- a/src/liblzma/common/easy_buffer_encoder.c
+++ b/src/liblzma/common/easy_buffer_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_buffer_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "easy_preset.h"
diff --git a/src/liblzma/common/easy_decoder_memusage.c b/src/liblzma/common/easy_decoder_memusage.c
index 20bcd5b..0c76f10 100644
--- a/src/liblzma/common/easy_decoder_memusage.c
+++ b/src/liblzma/common/easy_decoder_memusage.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_decoder_memusage.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "easy_preset.h"
diff --git a/src/liblzma/common/easy_encoder.c b/src/liblzma/common/easy_encoder.c
index 5cb492d..8dfe296 100644
--- a/src/liblzma/common/easy_encoder.c
+++ b/src/liblzma/common/easy_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "easy_preset.h"
diff --git a/src/liblzma/common/easy_encoder_memusage.c b/src/liblzma/common/easy_encoder_memusage.c
index e910575..1184ac6 100644
--- a/src/liblzma/common/easy_encoder_memusage.c
+++ b/src/liblzma/common/easy_encoder_memusage.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_encoder_memusage.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "easy_preset.h"
diff --git a/src/liblzma/common/easy_preset.c b/src/liblzma/common/easy_preset.c
index 2f98598..7908a2b 100644
--- a/src/liblzma/common/easy_preset.c
+++ b/src/liblzma/common/easy_preset.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_preset.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "easy_preset.h"
diff --git a/src/liblzma/common/easy_preset.h b/src/liblzma/common/easy_preset.h
index 382ade8..4ef6d04 100644
--- a/src/liblzma/common/easy_preset.h
+++ b/src/liblzma/common/easy_preset.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file easy_preset.h
@@ -5,11 +7,11 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
+#ifndef LZMA_EASY_PRESET_H
+#define LZMA_EASY_PRESET_H
+
#include "common.h"
@@ -30,3 +32,5 @@ typedef struct {
/// Set *easy to the settings given by the preset. Returns true on error,
/// false on success.
extern bool lzma_easy_preset(lzma_options_easy *easy, uint32_t preset);
+
+#endif
diff --git a/src/liblzma/common/file_info.c b/src/liblzma/common/file_info.c
index 799bb02..7c85084 100644
--- a/src/liblzma/common/file_info.c
+++ b/src/liblzma/common/file_info.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file file_info.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "index_decoder.h"
diff --git a/src/liblzma/common/filter_buffer_decoder.c b/src/liblzma/common/filter_buffer_decoder.c
index 6620986..cc0d88c 100644
--- a/src/liblzma/common/filter_buffer_decoder.c
+++ b/src/liblzma/common/filter_buffer_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_buffer_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_decoder.h"
@@ -24,7 +23,7 @@ lzma_raw_buffer_decode(
|| out_pos == NULL || *out_pos > out_size)
return LZMA_PROG_ERROR;
- // Initialize the decoer.
+ // Initialize the decoder.
lzma_next_coder next = LZMA_NEXT_CODER_INIT;
return_if_error(lzma_raw_decoder_init(&next, allocator, filters));
diff --git a/src/liblzma/common/filter_buffer_encoder.c b/src/liblzma/common/filter_buffer_encoder.c
index dda18e3..7fb8922 100644
--- a/src/liblzma/common/filter_buffer_encoder.c
+++ b/src/liblzma/common/filter_buffer_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_buffer_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_encoder.h"
diff --git a/src/liblzma/common/filter_common.c b/src/liblzma/common/filter_common.c
index fa0927c..d15d9cc 100644
--- a/src/liblzma/common/filter_common.c
+++ b/src/liblzma/common/filter_common.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_common.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_common.h"
@@ -122,6 +121,15 @@ static const struct {
.changes_size = false,
},
#endif
+#if defined(HAVE_ENCODER_RISCV) || defined(HAVE_DECODER_RISCV)
+ {
+ .id = LZMA_FILTER_RISCV,
+ .options_size = sizeof(lzma_options_bcj),
+ .non_last_ok = true,
+ .last_ok = false,
+ .changes_size = false,
+ },
+#endif
#if defined(HAVE_ENCODER_DELTA) || defined(HAVE_DECODER_DELTA)
{
.id = LZMA_FILTER_DELTA,
@@ -145,7 +153,7 @@ lzma_filters_copy(const lzma_filter *src, lzma_filter *real_dest,
return LZMA_PROG_ERROR;
// Use a temporary destination so that the real destination
- // will never be modied if an error occurs.
+ // will never be modified if an error occurs.
lzma_filter dest[LZMA_FILTERS_MAX + 1];
lzma_ret ret;
diff --git a/src/liblzma/common/filter_common.h b/src/liblzma/common/filter_common.h
index 2e47bb6..95f9fe2 100644
--- a/src/liblzma/common/filter_common.h
+++ b/src/liblzma/common/filter_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_common.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_FILTER_COMMON_H
diff --git a/src/liblzma/common/filter_decoder.c b/src/liblzma/common/filter_decoder.c
index fa53f5b..cbdeb58 100644
--- a/src/liblzma/common/filter_decoder.c
+++ b/src/liblzma/common/filter_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_decoder.h"
@@ -121,6 +120,14 @@ static const lzma_filter_decoder decoders[] = {
.props_decode = &lzma_simple_props_decode,
},
#endif
+#ifdef HAVE_DECODER_RISCV
+ {
+ .id = LZMA_FILTER_RISCV,
+ .init = &lzma_simple_riscv_decoder_init,
+ .memusage = NULL,
+ .props_decode = &lzma_simple_props_decode,
+ },
+#endif
#ifdef HAVE_DECODER_DELTA
{
.id = LZMA_FILTER_DELTA,
@@ -143,6 +150,16 @@ decoder_find(lzma_vli id)
}
+// lzma_filter_coder begins with the same members as lzma_filter_decoder.
+// This function is a wrapper with a type that is compatible with the
+// typedef of lzma_filter_find in filter_common.h.
+static const lzma_filter_coder *
+coder_find(lzma_vli id)
+{
+ return (const lzma_filter_coder *)decoder_find(id);
+}
+
+
extern LZMA_API(lzma_bool)
lzma_filter_decoder_is_supported(lzma_vli id)
{
@@ -155,7 +172,7 @@ lzma_raw_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter *options)
{
return lzma_raw_coder_init(next, allocator,
- options, (lzma_filter_find)(&decoder_find), false);
+ options, &coder_find, false);
}
@@ -174,8 +191,7 @@ lzma_raw_decoder(lzma_stream *strm, const lzma_filter *options)
extern LZMA_API(uint64_t)
lzma_raw_decoder_memusage(const lzma_filter *filters)
{
- return lzma_raw_coder_memusage(
- (lzma_filter_find)(&decoder_find), filters);
+ return lzma_raw_coder_memusage(&coder_find, filters);
}
diff --git a/src/liblzma/common/filter_decoder.h b/src/liblzma/common/filter_decoder.h
index 2dac602..e610bc1 100644
--- a/src/liblzma/common/filter_decoder.h
+++ b/src/liblzma/common/filter_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_FILTER_DECODER_H
diff --git a/src/liblzma/common/filter_encoder.c b/src/liblzma/common/filter_encoder.c
index 46fe8af..bc39444 100644
--- a/src/liblzma/common/filter_encoder.c
+++ b/src/liblzma/common/filter_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_encoder.h"
@@ -33,7 +32,8 @@ typedef struct {
/// Calculates the recommended Uncompressed Size for .xz Blocks to
/// which the input data can be split to make multithreaded
/// encoding possible. If this is NULL, it is assumed that
- /// the encoder is fast enough with single thread.
+ /// the encoder is fast enough with single thread. If the options
+ /// are invalid, UINT64_MAX is returned.
uint64_t (*block_size)(const void *options);
/// Tells the size of the Filter Properties field. If options are
@@ -158,6 +158,16 @@ static const lzma_filter_encoder encoders[] = {
.props_encode = &lzma_simple_props_encode,
},
#endif
+#ifdef HAVE_ENCODER_RISCV
+ {
+ .id = LZMA_FILTER_RISCV,
+ .init = &lzma_simple_riscv_encoder_init,
+ .memusage = NULL,
+ .block_size = NULL,
+ .props_size_get = &lzma_simple_props_size,
+ .props_encode = &lzma_simple_props_encode,
+ },
+#endif
#ifdef HAVE_ENCODER_DELTA
{
.id = LZMA_FILTER_DELTA,
@@ -183,6 +193,16 @@ encoder_find(lzma_vli id)
}
+// lzma_filter_coder begins with the same members as lzma_filter_encoder.
+// This function is a wrapper with a type that is compatible with the
+// typedef of lzma_filter_find in filter_common.h.
+static const lzma_filter_coder *
+coder_find(lzma_vli id)
+{
+ return (const lzma_filter_coder *)encoder_find(id);
+}
+
+
extern LZMA_API(lzma_bool)
lzma_filter_encoder_is_supported(lzma_vli id)
{
@@ -219,18 +239,18 @@ lzma_filters_update(lzma_stream *strm, const lzma_filter *filters)
extern lzma_ret
lzma_raw_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
- const lzma_filter *options)
+ const lzma_filter *filters)
{
return lzma_raw_coder_init(next, allocator,
- options, (lzma_filter_find)(&encoder_find), true);
+ filters, &coder_find, true);
}
extern LZMA_API(lzma_ret)
-lzma_raw_encoder(lzma_stream *strm, const lzma_filter *options)
+lzma_raw_encoder(lzma_stream *strm, const lzma_filter *filters)
{
- lzma_next_strm_init(lzma_raw_coder_init, strm, options,
- (lzma_filter_find)(&encoder_find), true);
+ lzma_next_strm_init(lzma_raw_coder_init, strm, filters,
+ &coder_find, true);
strm->internal->supported_actions[LZMA_RUN] = true;
strm->internal->supported_actions[LZMA_SYNC_FLUSH] = true;
@@ -243,31 +263,33 @@ lzma_raw_encoder(lzma_stream *strm, const lzma_filter *options)
extern LZMA_API(uint64_t)
lzma_raw_encoder_memusage(const lzma_filter *filters)
{
- return lzma_raw_coder_memusage(
- (lzma_filter_find)(&encoder_find), filters);
+ return lzma_raw_coder_memusage(&coder_find, filters);
}
-extern uint64_t
+extern LZMA_API(uint64_t)
lzma_mt_block_size(const lzma_filter *filters)
{
+ if (filters == NULL)
+ return UINT64_MAX;
+
uint64_t max = 0;
for (size_t i = 0; filters[i].id != LZMA_VLI_UNKNOWN; ++i) {
const lzma_filter_encoder *const fe
= encoder_find(filters[i].id);
+ if (fe == NULL)
+ return UINT64_MAX;
+
if (fe->block_size != NULL) {
const uint64_t size
= fe->block_size(filters[i].options);
- if (size == 0)
- return 0;
-
if (size > max)
max = size;
}
}
- return max;
+ return max == 0 ? UINT64_MAX : max;
}
diff --git a/src/liblzma/common/filter_encoder.h b/src/liblzma/common/filter_encoder.h
index f1d5683..88f2daf 100644
--- a/src/liblzma/common/filter_encoder.h
+++ b/src/liblzma/common/filter_encoder.h
@@ -1,13 +1,12 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
-/// \file filter_encoder.c
+/// \file filter_encoder.h
/// \brief Filter ID mapping to filter-specific functions
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_FILTER_ENCODER_H
@@ -16,10 +15,6 @@
#include "common.h"
-// FIXME: Might become a part of the public API.
-extern uint64_t lzma_mt_block_size(const lzma_filter *filters);
-
-
extern lzma_ret lzma_raw_encoder_init(
lzma_next_coder *next, const lzma_allocator *allocator,
const lzma_filter *filters);
diff --git a/src/liblzma/common/filter_flags_decoder.c b/src/liblzma/common/filter_flags_decoder.c
index ddfb085..0f5d204 100644
--- a/src/liblzma/common/filter_flags_decoder.c
+++ b/src/liblzma/common/filter_flags_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_flags_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_decoder.h"
diff --git a/src/liblzma/common/filter_flags_encoder.c b/src/liblzma/common/filter_flags_encoder.c
index b57b9fd..e1d6588 100644
--- a/src/liblzma/common/filter_flags_encoder.c
+++ b/src/liblzma/common/filter_flags_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file filter_flags_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_encoder.h"
diff --git a/src/liblzma/common/hardware_cputhreads.c b/src/liblzma/common/hardware_cputhreads.c
index 5d246d2..4ce852b 100644
--- a/src/liblzma/common/hardware_cputhreads.c
+++ b/src/liblzma/common/hardware_cputhreads.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file hardware_cputhreads.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/hardware_physmem.c b/src/liblzma/common/hardware_physmem.c
index a2bbbe2..1bc3486 100644
--- a/src/liblzma/common/hardware_physmem.c
+++ b/src/liblzma/common/hardware_physmem.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file hardware_physmem.c
@@ -5,9 +7,6 @@
//
// Author: Jonathan Nieder
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/index.c b/src/liblzma/common/index.c
index 8a35f43..6add6a6 100644
--- a/src/liblzma/common/index.c
+++ b/src/liblzma/common/index.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/index.h b/src/liblzma/common/index.h
index 7b27d70..007e118 100644
--- a/src/liblzma/common/index.h
+++ b/src/liblzma/common/index.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index.h
@@ -12,9 +14,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_INDEX_H
diff --git a/src/liblzma/common/index_decoder.c b/src/liblzma/common/index_decoder.c
index 19a31b3..4bcb306 100644
--- a/src/liblzma/common/index_decoder.c
+++ b/src/liblzma/common/index_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "index_decoder.h"
@@ -306,6 +305,12 @@ lzma_index_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
extern LZMA_API(lzma_ret)
lzma_index_decoder(lzma_stream *strm, lzma_index **i, uint64_t memlimit)
{
+ // If i isn't NULL, *i must always be initialized due to
+ // the wording in the API docs. This way it is initialized
+ // if we return LZMA_PROG_ERROR due to strm == NULL.
+ if (i != NULL)
+ *i = NULL;
+
lzma_next_strm_init(lzma_index_decoder_init, strm, i, memlimit);
strm->internal->supported_actions[LZMA_RUN] = true;
@@ -320,6 +325,11 @@ lzma_index_buffer_decode(lzma_index **i, uint64_t *memlimit,
const lzma_allocator *allocator,
const uint8_t *in, size_t *in_pos, size_t in_size)
{
+ // If i isn't NULL, *i must always be initialized due to
+ // the wording in the API docs.
+ if (i != NULL)
+ *i = NULL;
+
// Sanity checks
if (i == NULL || memlimit == NULL
|| in == NULL || in_pos == NULL || *in_pos > in_size)
diff --git a/src/liblzma/common/index_decoder.h b/src/liblzma/common/index_decoder.h
index 3fec483..5351d2f 100644
--- a/src/liblzma/common/index_decoder.h
+++ b/src/liblzma/common/index_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_INDEX_DECODER_H
diff --git a/src/liblzma/common/index_encoder.c b/src/liblzma/common/index_encoder.c
index 204490c..ecc299c 100644
--- a/src/liblzma/common/index_encoder.c
+++ b/src/liblzma/common/index_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "index_encoder.h"
diff --git a/src/liblzma/common/index_encoder.h b/src/liblzma/common/index_encoder.h
index 4d55cd1..29ba110 100644
--- a/src/liblzma/common/index_encoder.h
+++ b/src/liblzma/common/index_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index_encoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_INDEX_ENCODER_H
diff --git a/src/liblzma/common/index_hash.c b/src/liblzma/common/index_hash.c
index 52c3d65..caa5967 100644
--- a/src/liblzma/common/index_hash.c
+++ b/src/liblzma/common/index_hash.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file index_hash.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/lzip_decoder.c b/src/liblzma/common/lzip_decoder.c
index 88cc7ff..651a0ae 100644
--- a/src/liblzma/common/lzip_decoder.c
+++ b/src/liblzma/common/lzip_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzip_decoder.c
@@ -6,9 +8,6 @@
// Author: Michał Górny
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzip_decoder.h"
diff --git a/src/liblzma/common/lzip_decoder.h b/src/liblzma/common/lzip_decoder.h
index 33a01c3..0e1f7be 100644
--- a/src/liblzma/common/lzip_decoder.h
+++ b/src/liblzma/common/lzip_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzip_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Michał Górny
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZIP_DECODER_H
diff --git a/src/liblzma/common/memcmplen.h b/src/liblzma/common/memcmplen.h
index 99d9c51..394a485 100644
--- a/src/liblzma/common/memcmplen.h
+++ b/src/liblzma/common/memcmplen.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file memcmplen.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_MEMCMPLEN_H
@@ -24,7 +23,8 @@
// can use the intrinsics without the header file.
#if defined(TUKLIB_FAST_UNALIGNED_ACCESS) \
&& defined(_MSC_VER) \
- && defined(_M_X64) \
+ && (defined(_M_X64) \
+ || defined(_M_ARM64) || defined(_M_ARM64EC)) \
&& !defined(__INTEL_COMPILER)
# include <intrin.h>
#endif
@@ -57,20 +57,35 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2,
assert(limit <= UINT32_MAX / 2);
#if defined(TUKLIB_FAST_UNALIGNED_ACCESS) \
- && ((TUKLIB_GNUC_REQ(3, 4) && defined(__x86_64__)) \
+ && (((TUKLIB_GNUC_REQ(3, 4) || defined(__clang__)) \
+ && (defined(__x86_64__) \
+ || defined(__aarch64__))) \
|| (defined(__INTEL_COMPILER) && defined(__x86_64__)) \
|| (defined(__INTEL_COMPILER) && defined(_M_X64)) \
- || (defined(_MSC_VER) && defined(_M_X64)))
- // I keep this x86-64 only for now since that's where I know this
- // to be a good method. This may be fine on other 64-bit CPUs too.
- // On big endian one should use xor instead of subtraction and switch
- // to __builtin_clzll().
+ || (defined(_MSC_VER) && (defined(_M_X64) \
+ || defined(_M_ARM64) || defined(_M_ARM64EC))))
+ // 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);
if (x != 0) {
// MSVC or Intel C compiler on Windows
-# if (defined(_MSC_VER) || defined(__INTEL_COMPILER)) && defined(_M_X64)
+# if defined(_MSC_VER) || defined(__INTEL_COMPILER)
unsigned long tmp;
_BitScanForward64(&tmp, x);
len += (uint32_t)tmp >> 3;
diff --git a/src/liblzma/common/microlzma_decoder.c b/src/liblzma/common/microlzma_decoder.c
index e473373..882cb2c 100644
--- a/src/liblzma/common/microlzma_decoder.c
+++ b/src/liblzma/common/microlzma_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file microlzma_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma_decoder.h"
diff --git a/src/liblzma/common/microlzma_encoder.c b/src/liblzma/common/microlzma_encoder.c
index a787ca2..45ec0b1 100644
--- a/src/liblzma/common/microlzma_encoder.c
+++ b/src/liblzma/common/microlzma_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file microlzma_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma_encoder.h"
diff --git a/src/liblzma/common/outqueue.c b/src/liblzma/common/outqueue.c
index 71e8648..eb018eb 100644
--- a/src/liblzma/common/outqueue.c
+++ b/src/liblzma/common/outqueue.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file outqueue.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "outqueue.h"
diff --git a/src/liblzma/common/outqueue.h b/src/liblzma/common/outqueue.h
index 596911e..25f0719 100644
--- a/src/liblzma/common/outqueue.h
+++ b/src/liblzma/common/outqueue.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file outqueue.h
@@ -5,11 +7,11 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
+#ifndef LZMA_OUTQUEUE_H
+#define LZMA_OUTQUEUE_H
+
#include "common.h"
@@ -252,3 +254,5 @@ lzma_outq_outbuf_memusage(size_t buf_size)
assert(buf_size <= SIZE_MAX - sizeof(lzma_outbuf));
return sizeof(lzma_outbuf) + buf_size;
}
+
+#endif
diff --git a/src/liblzma/common/stream_buffer_decoder.c b/src/liblzma/common/stream_buffer_decoder.c
index b9745b5..c4f91fb 100644
--- a/src/liblzma/common/stream_buffer_decoder.c
+++ b/src/liblzma/common/stream_buffer_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_buffer_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_decoder.h"
diff --git a/src/liblzma/common/stream_buffer_encoder.c b/src/liblzma/common/stream_buffer_encoder.c
index 7315759..04d5869 100644
--- a/src/liblzma/common/stream_buffer_encoder.c
+++ b/src/liblzma/common/stream_buffer_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_buffer_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/stream_decoder.c b/src/liblzma/common/stream_decoder.c
index 6428381..7f42684 100644
--- a/src/liblzma/common/stream_decoder.c
+++ b/src/liblzma/common/stream_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_decoder.h"
diff --git a/src/liblzma/common/stream_decoder.h b/src/liblzma/common/stream_decoder.h
index c13c6ba..5803715 100644
--- a/src/liblzma/common/stream_decoder.h
+++ b/src/liblzma/common/stream_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_STREAM_DECODER_H
diff --git a/src/liblzma/common/stream_decoder_mt.c b/src/liblzma/common/stream_decoder_mt.c
index 76212b4..244624a 100644
--- a/src/liblzma/common/stream_decoder_mt.c
+++ b/src/liblzma/common/stream_decoder_mt.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_decoder_mt.c
@@ -6,9 +8,6 @@
// Authors: Sebastian Andrzej Siewior
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/stream_encoder.c b/src/liblzma/common/stream_encoder.c
index ee92046..e7e5b3f 100644
--- a/src/liblzma/common/stream_encoder.c
+++ b/src/liblzma/common/stream_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "block_encoder.h"
diff --git a/src/liblzma/common/stream_encoder_mt.c b/src/liblzma/common/stream_encoder_mt.c
index f64de9b..f0fef15 100644
--- a/src/liblzma/common/stream_encoder_mt.c
+++ b/src/liblzma/common/stream_encoder_mt.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_encoder_mt.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_encoder.h"
@@ -979,20 +978,18 @@ get_options(const lzma_mt *options, lzma_options_easy *opt_easy,
*filters = opt_easy->filters;
}
- // Block size
- if (options->block_size > 0) {
- if (options->block_size > BLOCK_SIZE_MAX)
- return LZMA_OPTIONS_ERROR;
-
+ // If the Block size is not set, determine it from the filter chain.
+ if (options->block_size > 0)
*block_size = options->block_size;
- } else {
- // Determine the Block size from the filter chain.
+ else
*block_size = lzma_mt_block_size(*filters);
- if (*block_size == 0)
- return LZMA_OPTIONS_ERROR;
- assert(*block_size <= BLOCK_SIZE_MAX);
- }
+ // UINT64_MAX > BLOCK_SIZE_MAX, so the second condition
+ // should be optimized out by any reasonable compiler.
+ // The second condition should be there in the unlikely event that
+ // the macros change and UINT64_MAX < BLOCK_SIZE_MAX.
+ if (*block_size > BLOCK_SIZE_MAX || *block_size == UINT64_MAX)
+ return LZMA_OPTIONS_ERROR;
// Calculate the maximum amount output that a single output buffer
// may need to hold. This is the same as the maximum total size of
diff --git a/src/liblzma/common/stream_flags_common.c b/src/liblzma/common/stream_flags_common.c
index fbe8eb8..41b8dcb 100644
--- a/src/liblzma/common/stream_flags_common.c
+++ b/src/liblzma/common/stream_flags_common.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_flags_common.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_flags_common.h"
diff --git a/src/liblzma/common/stream_flags_common.h b/src/liblzma/common/stream_flags_common.h
index 84e96ba..28729db 100644
--- a/src/liblzma/common/stream_flags_common.h
+++ b/src/liblzma/common/stream_flags_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_flags_common.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_STREAM_FLAGS_COMMON_H
diff --git a/src/liblzma/common/stream_flags_decoder.c b/src/liblzma/common/stream_flags_decoder.c
index b8d263b..522c98b 100644
--- a/src/liblzma/common/stream_flags_decoder.c
+++ b/src/liblzma/common/stream_flags_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_flags_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_flags_common.h"
diff --git a/src/liblzma/common/stream_flags_encoder.c b/src/liblzma/common/stream_flags_encoder.c
index b98ab17..f94b5cd 100644
--- a/src/liblzma/common/stream_flags_encoder.c
+++ b/src/liblzma/common/stream_flags_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file stream_flags_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "stream_flags_common.h"
diff --git a/src/liblzma/common/string_conversion.c b/src/liblzma/common/string_conversion.c
index d2c1e80..c899783 100644
--- a/src/liblzma/common/string_conversion.c
+++ b/src/liblzma/common/string_conversion.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file string_conversion.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "filter_common.h"
@@ -218,12 +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;
@@ -250,7 +251,9 @@ static const char *parse_options(const char **const str, const char *str_end,
|| defined(HAVE_ENCODER_IA64) \
|| defined(HAVE_DECODER_IA64) \
|| defined(HAVE_ENCODER_SPARC) \
- || defined(HAVE_DECODER_SPARC)
+ || defined(HAVE_DECODER_SPARC) \
+ || defined(HAVE_ENCODER_RISCV) \
+ || defined(HAVE_DECODER_RISCV)
static const option_map bcj_optmap[] = {
{
.name = "start",
@@ -509,6 +512,11 @@ static const struct {
&parse_bcj, bcj_optmap, 1, 1, true },
#endif
+#if defined(HAVE_ENCODER_RISCV) || defined(HAVE_DECODER_RISCV)
+ { "riscv", sizeof(lzma_options_bcj), LZMA_FILTER_RISCV,
+ &parse_bcj, bcj_optmap, 1, 1, true },
+#endif
+
#if defined(HAVE_ENCODER_POWERPC) || defined(HAVE_DECODER_POWERPC)
{ "powerpc", sizeof(lzma_options_bcj), LZMA_FILTER_POWERPC,
&parse_bcj, bcj_optmap, 1, 1, true },
@@ -994,6 +1002,12 @@ extern LZMA_API(const char *)
lzma_str_to_filters(const char *str, int *error_pos, lzma_filter *filters,
uint32_t flags, const lzma_allocator *allocator)
{
+ // If error_pos isn't NULL, *error_pos must always be set.
+ // liblzma <= 5.4.6 and <= 5.6.1 have a bug and don't do this
+ // when str == NULL or filters == NULL or flags are unsupported.
+ if (error_pos != NULL)
+ *error_pos = 0;
+
if (str == NULL || filters == NULL)
return "Unexpected NULL pointer argument(s) "
"to lzma_str_to_filters()";
diff --git a/src/liblzma/common/vli_decoder.c b/src/liblzma/common/vli_decoder.c
index af2799d..3254ccc 100644
--- a/src/liblzma/common/vli_decoder.c
+++ b/src/liblzma/common/vli_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file vli_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/vli_encoder.c b/src/liblzma/common/vli_encoder.c
index f864269..3859006 100644
--- a/src/liblzma/common/vli_encoder.c
+++ b/src/liblzma/common/vli_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file vli_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/common/vli_size.c b/src/liblzma/common/vli_size.c
index ec1b4fa..c8cb2ec 100644
--- a/src/liblzma/common/vli_size.c
+++ b/src/liblzma/common/vli_size.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file vli_size.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/delta/Makefile.inc b/src/liblzma/delta/Makefile.inc
index c7739b4..e5b919e 100644
--- a/src/liblzma/delta/Makefile.inc
+++ b/src/liblzma/delta/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
liblzma_la_SOURCES += \
delta/delta_common.c \
diff --git a/src/liblzma/delta/delta_common.c b/src/liblzma/delta/delta_common.c
index 4768201..5dbe253 100644
--- a/src/liblzma/delta/delta_common.c
+++ b/src/liblzma/delta/delta_common.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_common.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "delta_common.h"
diff --git a/src/liblzma/delta/delta_common.h b/src/liblzma/delta/delta_common.h
index 7e7e1ba..bd09127 100644
--- a/src/liblzma/delta/delta_common.h
+++ b/src/liblzma/delta/delta_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_common.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_DELTA_COMMON_H
diff --git a/src/liblzma/delta/delta_decoder.c b/src/liblzma/delta/delta_decoder.c
index 77cf65c..9f0d49c 100644
--- a/src/liblzma/delta/delta_decoder.c
+++ b/src/liblzma/delta/delta_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "delta_decoder.h"
@@ -26,6 +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,
diff --git a/src/liblzma/delta/delta_decoder.h b/src/liblzma/delta/delta_decoder.h
index ad89cc6..e2268ed 100644
--- a/src/liblzma/delta/delta_decoder.h
+++ b/src/liblzma/delta/delta_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_DELTA_DECODER_H
diff --git a/src/liblzma/delta/delta_encoder.c b/src/liblzma/delta/delta_encoder.c
index 056bf74..ba4a50b 100644
--- a/src/liblzma/delta/delta_encoder.c
+++ b/src/liblzma/delta/delta_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "delta_encoder.h"
diff --git a/src/liblzma/delta/delta_encoder.h b/src/liblzma/delta/delta_encoder.h
index 4ab9847..735f0ed 100644
--- a/src/liblzma/delta/delta_encoder.h
+++ b/src/liblzma/delta/delta_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_encoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_DELTA_ENCODER_H
diff --git a/src/liblzma/delta/delta_private.h b/src/liblzma/delta/delta_private.h
index 0d6cb38..e54721a 100644
--- a/src/liblzma/delta/delta_private.h
+++ b/src/liblzma/delta/delta_private.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file delta_private.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_DELTA_PRIVATE_H
diff --git a/src/liblzma/liblzma.pc.in b/src/liblzma/liblzma.pc.in
index d077cb7..a432992 100644
--- a/src/liblzma/liblzma.pc.in
+++ b/src/liblzma/liblzma.pc.in
@@ -1,9 +1,5 @@
-#
+# SPDX-License-Identifier: 0BSD
# Author: Lasse Collin
-#
-# This file has been put into the public domain.
-# You can do whatever you want with this file.
-#
prefix=@prefix@
exec_prefix=@exec_prefix@
diff --git a/src/liblzma/liblzma_generic.map b/src/liblzma/liblzma_generic.map
index bb82167..f74c154 100644
--- a/src/liblzma/liblzma_generic.map
+++ b/src/liblzma/liblzma_generic.map
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
XZ_5.0 {
global:
lzma_alone_decoder;
@@ -119,3 +121,8 @@ global:
lzma_str_list_filters;
lzma_str_to_filters;
} XZ_5.2;
+
+XZ_5.6.0 {
+global:
+ lzma_mt_block_size;
+} XZ_5.4;
diff --git a/src/liblzma/liblzma_linux.map b/src/liblzma/liblzma_linux.map
index 449f5fd..7e4b25e 100644
--- a/src/liblzma/liblzma_linux.map
+++ b/src/liblzma/liblzma_linux.map
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: 0BSD */
+
XZ_5.0 {
global:
lzma_alone_decoder;
@@ -134,3 +136,8 @@ global:
lzma_str_list_filters;
lzma_str_to_filters;
} XZ_5.2;
+
+XZ_5.6.0 {
+global:
+ lzma_mt_block_size;
+} XZ_5.4;
diff --git a/src/liblzma/liblzma_w32res.rc b/src/liblzma/liblzma_w32res.rc
index d4d8159..e225b19 100644
--- a/src/liblzma/liblzma_w32res.rc
+++ b/src/liblzma/liblzma_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#define MY_TYPE VFT_DLL
diff --git a/src/liblzma/lz/Makefile.inc b/src/liblzma/lz/Makefile.inc
index 75742a8..15235d7 100644
--- a/src/liblzma/lz/Makefile.inc
+++ b/src/liblzma/lz/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
if COND_ENCODER_LZ
liblzma_la_SOURCES += \
diff --git a/src/liblzma/lz/lz_decoder.c b/src/liblzma/lz/lz_decoder.c
index 06c95c1..92913f2 100644
--- a/src/liblzma/lz/lz_decoder.c
+++ b/src/liblzma/lz/lz_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_decoder.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
// liblzma supports multiple LZ77-based filters. The LZ part is shared
@@ -54,9 +53,10 @@ typedef struct {
static void
lz_decoder_reset(lzma_coder *coder)
{
- coder->dict.pos = 0;
+ coder->dict.pos = 2 * LZ_DICT_REPEAT_MAX;
coder->dict.full = 0;
- coder->dict.buf[coder->dict.size - 1] = '\0';
+ coder->dict.buf[2 * LZ_DICT_REPEAT_MAX - 1] = '\0';
+ coder->dict.has_wrapped = false;
coder->dict.need_reset = false;
return;
}
@@ -70,8 +70,15 @@ decode_buffer(lzma_coder *coder,
{
while (true) {
// Wrap the dictionary if needed.
- if (coder->dict.pos == coder->dict.size)
- coder->dict.pos = 0;
+ if (coder->dict.pos == coder->dict.size) {
+ // See the comment of #define LZ_DICT_REPEAT_MAX.
+ coder->dict.pos = LZ_DICT_REPEAT_MAX;
+ coder->dict.has_wrapped = true;
+ memcpy(coder->dict.buf, coder->dict.buf
+ + coder->dict.size
+ - LZ_DICT_REPEAT_MAX,
+ LZ_DICT_REPEAT_MAX);
+ }
// Store the current dictionary position. It is needed to know
// where to start copying to the out[] buffer.
@@ -253,21 +260,31 @@ lzma_lz_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
// dictionary to the output buffer, since applications are
// recommended to give aligned buffers to liblzma.
//
+ // Reserve 2 * LZ_DICT_REPEAT_MAX bytes of extra space which is
+ // needed for alloc_size.
+ //
// Avoid integer overflow.
- if (lz_options.dict_size > SIZE_MAX - 15)
+ if (lz_options.dict_size > SIZE_MAX - 15 - 2 * LZ_DICT_REPEAT_MAX)
return LZMA_MEM_ERROR;
lz_options.dict_size = (lz_options.dict_size + 15) & ~((size_t)(15));
+ // Reserve extra space as explained in the comment
+ // of #define LZ_DICT_REPEAT_MAX.
+ const size_t alloc_size
+ = lz_options.dict_size + 2 * LZ_DICT_REPEAT_MAX;
+
// Allocate and initialize the dictionary.
- if (coder->dict.size != lz_options.dict_size) {
+ if (coder->dict.size != alloc_size) {
lzma_free(coder->dict.buf, allocator);
- coder->dict.buf
- = lzma_alloc(lz_options.dict_size, allocator);
+ coder->dict.buf = lzma_alloc(alloc_size, allocator);
if (coder->dict.buf == NULL)
return LZMA_MEM_ERROR;
- coder->dict.size = lz_options.dict_size;
+ // NOTE: Yes, alloc_size, not lz_options.dict_size. The way
+ // coder->dict.full is updated will take care that we will
+ // still reject distances larger than lz_options.dict_size.
+ coder->dict.size = alloc_size;
}
lz_decoder_reset(next->coder);
@@ -280,9 +297,12 @@ lzma_lz_decoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
const size_t copy_size = my_min(lz_options.preset_dict_size,
lz_options.dict_size);
const size_t offset = lz_options.preset_dict_size - copy_size;
- memcpy(coder->dict.buf, lz_options.preset_dict + offset,
+ memcpy(coder->dict.buf + coder->dict.pos,
+ lz_options.preset_dict + offset,
copy_size);
- coder->dict.pos = copy_size;
+
+ // dict.pos isn't zero after lz_decoder_reset().
+ coder->dict.pos += copy_size;
coder->dict.full = copy_size;
}
diff --git a/src/liblzma/lz/lz_decoder.h b/src/liblzma/lz/lz_decoder.h
index ad80d4d..cb61b6e 100644
--- a/src/liblzma/lz/lz_decoder.h
+++ b/src/liblzma/lz/lz_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_decoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZ_DECODER_H
@@ -17,10 +16,28 @@
#include "common.h"
+/// Maximum length of a match rounded up to a nice power of 2 which is
+/// a good size for aligned memcpy(). The allocated dictionary buffer will
+/// be 2 * LZ_DICT_REPEAT_MAX bytes larger than the actual dictionary size:
+///
+/// (1) Every time the decoder reaches the end of the dictionary buffer,
+/// the last LZ_DICT_REPEAT_MAX bytes will be copied to the beginning.
+/// This way dict_repeat() will only need to copy from one place,
+/// never from both the end and beginning of the buffer.
+///
+/// (2) The other LZ_DICT_REPEAT_MAX bytes is kept as a buffer between
+/// the oldest byte still in the dictionary and the current write
+/// position. This way dict_repeat(dict, dict->size - 1, &len)
+/// won't need memmove() as the copying cannot overlap.
+///
+/// Note that memcpy() still cannot be used if distance < len.
+///
+/// LZMA's longest match length is 273 so pick a multiple of 16 above that.
+#define LZ_DICT_REPEAT_MAX 288
+
+
typedef struct {
- /// Pointer to the dictionary buffer. It can be an allocated buffer
- /// internal to liblzma, or it can a be a buffer given by the
- /// application when in single-call mode (not implemented yet).
+ /// Pointer to the dictionary buffer.
uint8_t *buf;
/// Write position in dictionary. The next byte will be written to
@@ -35,9 +52,16 @@ typedef struct {
/// Write limit
size_t limit;
- /// Size of the dictionary
+ /// Allocated size of buf. This is 2 * LZ_DICT_REPEAT_MAX bytes
+ /// larger than the actual dictionary size. This is enforced by
+ /// how the value for "full" is set; it can be at most
+ /// "size - 2 * LZ_DICT_REPEAT_MAX".
size_t size;
+ /// True once the dictionary has become full and the writing position
+ /// has been wrapped in decode_buffer() in lz_decoder.c.
+ bool has_wrapped;
+
/// True when dictionary should be reset before decoding more data.
bool need_reset;
@@ -103,7 +127,16 @@ static inline uint8_t
dict_get(const lzma_dict *const dict, const uint32_t distance)
{
return dict->buf[dict->pos - distance - 1
- + (distance < dict->pos ? 0 : dict->size)];
+ + (distance < dict->pos
+ ? 0 : dict->size - LZ_DICT_REPEAT_MAX)];
+}
+
+
+/// Optimized version of dict_get(dict, 0)
+static inline uint8_t
+dict_get0(const lzma_dict *const dict)
+{
+ return dict->buf[dict->pos - 1];
}
@@ -132,68 +165,51 @@ dict_repeat(lzma_dict *dict, uint32_t distance, uint32_t *len)
uint32_t left = my_min(dict_avail, *len);
*len -= left;
+ size_t back = dict->pos - distance - 1;
+ if (distance >= dict->pos)
+ back += dict->size - LZ_DICT_REPEAT_MAX;
+
// Repeat a block of data from the history. Because memcpy() is faster
// than copying byte by byte in a loop, the copying process gets split
- // into three cases.
+ // into two cases.
if (distance < left) {
// Source and target areas overlap, thus we can't use
// memcpy() nor even memmove() safely.
do {
- dict->buf[dict->pos] = dict_get(dict, distance);
- ++dict->pos;
+ dict->buf[dict->pos++] = dict->buf[back++];
} while (--left > 0);
-
- } else if (distance < dict->pos) {
- // The easiest and fastest case
- memcpy(dict->buf + dict->pos,
- dict->buf + dict->pos - distance - 1,
- left);
- dict->pos += left;
-
} else {
- // The bigger the dictionary, the more rare this
- // case occurs. We need to "wrap" the dict, thus
- // we might need two memcpy() to copy all the data.
- assert(dict->full == dict->size);
- const uint32_t copy_pos
- = dict->pos - distance - 1 + dict->size;
- uint32_t copy_size = dict->size - copy_pos;
-
- if (copy_size < left) {
- memmove(dict->buf + dict->pos, dict->buf + copy_pos,
- copy_size);
- dict->pos += copy_size;
- copy_size = left - copy_size;
- memcpy(dict->buf + dict->pos, dict->buf, copy_size);
- dict->pos += copy_size;
- } else {
- memmove(dict->buf + dict->pos, dict->buf + copy_pos,
- left);
- dict->pos += left;
- }
+ memcpy(dict->buf + dict->pos, dict->buf + back, left);
+ dict->pos += left;
}
// Update how full the dictionary is.
- if (dict->full < dict->pos)
- dict->full = dict->pos;
+ if (!dict->has_wrapped)
+ dict->full = dict->pos - 2 * LZ_DICT_REPEAT_MAX;
- return unlikely(*len != 0);
+ return *len != 0;
+}
+
+
+static inline void
+dict_put(lzma_dict *dict, uint8_t byte)
+{
+ dict->buf[dict->pos++] = byte;
+
+ if (!dict->has_wrapped)
+ dict->full = dict->pos - 2 * LZ_DICT_REPEAT_MAX;
}
/// Puts one byte into the dictionary. Returns true if the dictionary was
/// already full and the byte couldn't be added.
static inline bool
-dict_put(lzma_dict *dict, uint8_t byte)
+dict_put_safe(lzma_dict *dict, uint8_t byte)
{
if (unlikely(dict->pos == dict->limit))
return true;
- dict->buf[dict->pos++] = byte;
-
- if (dict->pos > dict->full)
- dict->full = dict->pos;
-
+ dict_put(dict, byte);
return false;
}
@@ -217,8 +233,8 @@ dict_write(lzma_dict *restrict dict, const uint8_t *restrict in,
*left -= lzma_bufcpy(in, in_pos, in_size,
dict->buf, &dict->pos, dict->limit);
- if (dict->pos > dict->full)
- dict->full = dict->pos;
+ if (!dict->has_wrapped)
+ dict->full = dict->pos - 2 * LZ_DICT_REPEAT_MAX;
return;
}
diff --git a/src/liblzma/lz/lz_encoder.c b/src/liblzma/lz/lz_encoder.c
index 5489085..4af23e1 100644
--- a/src/liblzma/lz/lz_encoder.c
+++ b/src/liblzma/lz/lz_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_encoder.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lz_encoder.h"
@@ -196,9 +195,7 @@ lz_encoder_prepare(lzma_mf *mf, const lzma_allocator *allocator,
// For now, the dictionary size is limited to 1.5 GiB. This may grow
// in the future if needed, but it needs a little more work than just
// changing this check.
- if (lz_options->dict_size < LZMA_DICT_SIZE_MIN
- || lz_options->dict_size
- > (UINT32_C(1) << 30) + (UINT32_C(1) << 29)
+ if (!IS_ENC_DICT_SIZE_VALID(lz_options->dict_size)
|| lz_options->nice_len > lz_options->match_len_max)
return true;
@@ -549,7 +546,7 @@ lzma_lz_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
lzma_lz_options *lz_options))
{
#if defined(HAVE_SMALL) && !defined(HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR)
- // We need that the CRC32 table has been initialized.
+ // The CRC32 table must be initialized.
lzma_crc32_init();
#endif
@@ -569,6 +566,8 @@ lzma_lz_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
coder->lz.coder = NULL;
coder->lz.code = NULL;
coder->lz.end = NULL;
+ coder->lz.options_update = NULL;
+ coder->lz.set_out_limit = NULL;
// mf.size is initialized to silence Valgrind
// when used on optimized binaries (GCC may reorder
diff --git a/src/liblzma/lz/lz_encoder.h b/src/liblzma/lz/lz_encoder.h
index ffcba02..eb197c6 100644
--- a/src/liblzma/lz/lz_encoder.h
+++ b/src/liblzma/lz/lz_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_encoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZ_ENCODER_H
@@ -17,6 +16,14 @@
#include "common.h"
+// For now, the dictionary size is limited to 1.5 GiB. This may grow
+// in the future if needed, but it needs a little more work than just
+// changing this check.
+#define IS_ENC_DICT_SIZE_VALID(size) \
+ ((size) >= LZMA_DICT_SIZE_MIN \
+ && (size) <= (UINT32_C(1) << 30) + (UINT32_C(1) << 29))
+
+
/// A table of these is used by the LZ-based encoder to hold
/// the length-distance pairs found by the match finder.
typedef struct {
@@ -153,9 +160,13 @@ typedef struct {
/// Maximum search depth
uint32_t depth;
- /// TODO: Comment
+ /// Initial dictionary for the match finder to search.
const uint8_t *preset_dict;
+ /// If the preset dictionary is NULL, this value is ignored.
+ /// Otherwise this member must indicate the preset dictionary's
+ /// buffer size. If this size is larger than dict_size, then only
+ /// the dict_size sized tail of the preset_dict will be used.
uint32_t preset_dict_size;
} lzma_lz_options;
@@ -217,7 +228,7 @@ typedef struct {
// 3. The literals and matches are encoded using e.g. LZMA.
//
// The bytes that have been ran through the match finder, but not encoded yet,
-// are called `read ahead'.
+// are called 'read ahead'.
/// Get how many bytes the match finder hashes in its initial step.
diff --git a/src/liblzma/lz/lz_encoder_hash.h b/src/liblzma/lz/lz_encoder_hash.h
index 4d9971a..8ace82b 100644
--- a/src/liblzma/lz/lz_encoder_hash.h
+++ b/src/liblzma/lz/lz_encoder_hash.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_encoder_hash.h
@@ -5,9 +7,6 @@
//
// Author: Igor Pavlov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZ_ENCODER_HASH_H
diff --git a/src/liblzma/lz/lz_encoder_hash_table.h b/src/liblzma/lz/lz_encoder_hash_table.h
index 8c51717..2b3a60e 100644
--- a/src/liblzma/lz/lz_encoder_hash_table.h
+++ b/src/liblzma/lz/lz_encoder_hash_table.h
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by crc32_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by crc32_tablegen.c.
const uint32_t lzma_lz_hash_table[256] = {
0x00000000, 0x77073096, 0xEE0E612C, 0x990951BA,
diff --git a/src/liblzma/lz/lz_encoder_mf.c b/src/liblzma/lz/lz_encoder_mf.c
index 1fdc2d7..557c261 100644
--- a/src/liblzma/lz/lz_encoder_mf.c
+++ b/src/liblzma/lz/lz_encoder_mf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lz_encoder_mf.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lz_encoder.h"
diff --git a/src/liblzma/lzma/Makefile.inc b/src/liblzma/lzma/Makefile.inc
index 25440d8..dca6b76 100644
--- a/src/liblzma/lzma/Makefile.inc
+++ b/src/liblzma/lzma/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
EXTRA_DIST += lzma/fastpos_tablegen.c
diff --git a/src/liblzma/lzma/fastpos.h b/src/liblzma/lzma/fastpos.h
index dbeb16f..d3969a7 100644
--- a/src/liblzma/lzma/fastpos.h
+++ b/src/liblzma/lzma/fastpos.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file fastpos.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_FASTPOS_H
diff --git a/src/liblzma/lzma/fastpos_table.c b/src/liblzma/lzma/fastpos_table.c
index 6a3ceac..4e10e37 100644
--- a/src/liblzma/lzma/fastpos_table.c
+++ b/src/liblzma/lzma/fastpos_table.c
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by fastpos_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by fastpos_tablegen.c.
#include "common.h"
#include "fastpos.h"
diff --git a/src/liblzma/lzma/fastpos_tablegen.c b/src/liblzma/lzma/fastpos_tablegen.c
index 57ed150..957ccb7 100644
--- a/src/liblzma/lzma/fastpos_tablegen.c
+++ b/src/liblzma/lzma/fastpos_tablegen.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file fastpos_tablegen.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include <inttypes.h>
@@ -35,11 +34,13 @@ main(void)
fastpos[c] = slot_fast;
}
- printf("/* This file has been automatically generated "
- "by fastpos_tablegen.c. */\n\n"
- "#include \"common.h\"\n"
- "#include \"fastpos.h\"\n\n"
- "const uint8_t lzma_fastpos[1 << FASTPOS_BITS] = {");
+ // Split the SPDX string so that it won't accidentally match
+ // when tools search for the string.
+ printf("// SPDX" "-License-Identifier" ": 0BSD\n\n"
+ "// This file has been generated by fastpos_tablegen.c.\n\n"
+ "#include \"common.h\"\n"
+ "#include \"fastpos.h\"\n\n"
+ "const uint8_t lzma_fastpos[1 << FASTPOS_BITS] = {");
for (size_t i = 0; i < (1 << FASTPOS_BITS); ++i) {
if (i % 16 == 0)
diff --git a/src/liblzma/lzma/lzma2_decoder.c b/src/liblzma/lzma/lzma2_decoder.c
index 567df49..37ab253 100644
--- a/src/liblzma/lzma/lzma2_decoder.c
+++ b/src/liblzma/lzma/lzma2_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma2_decoder.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma2_decoder.h"
diff --git a/src/liblzma/lzma/lzma2_decoder.h b/src/liblzma/lzma/lzma2_decoder.h
index ef2dcbf..cdd8b46 100644
--- a/src/liblzma/lzma/lzma2_decoder.h
+++ b/src/liblzma/lzma/lzma2_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma2_decoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA2_DECODER_H
diff --git a/src/liblzma/lzma/lzma2_encoder.c b/src/liblzma/lzma/lzma2_encoder.c
index 4b6b231..e20b75b 100644
--- a/src/liblzma/lzma/lzma2_encoder.c
+++ b/src/liblzma/lzma/lzma2_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma2_encoder.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lz_encoder.h"
@@ -409,6 +408,9 @@ lzma_lzma2_block_size(const void *options)
{
const lzma_options_lzma *const opt = options;
+ if (!IS_ENC_DICT_SIZE_VALID(opt->dict_size))
+ return UINT64_MAX;
+
// Use at least 1 MiB to keep compression ratio better.
return my_max((uint64_t)(opt->dict_size) * 3, UINT64_C(1) << 20);
}
diff --git a/src/liblzma/lzma/lzma2_encoder.h b/src/liblzma/lzma/lzma2_encoder.h
index 515f183..29966a6 100644
--- a/src/liblzma/lzma/lzma2_encoder.h
+++ b/src/liblzma/lzma/lzma2_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma2_encoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA2_ENCODER_H
diff --git a/src/liblzma/lzma/lzma_common.h b/src/liblzma/lzma/lzma_common.h
index 9d040d9..c3c587f 100644
--- a/src/liblzma/lzma/lzma_common.h
+++ b/src/liblzma/lzma/lzma_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_common.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA_COMMON_H
@@ -84,6 +83,20 @@ typedef enum {
? (state) - 3 \
: (state) - 6))
+/// Like update_literal(state) but when it is already known that
+/// is_literal_state(state) is true.
+#define update_literal_normal(state) \
+ state = ((state) <= STATE_SHORTREP_LIT_LIT \
+ ? STATE_LIT_LIT \
+ : (state) - 3);
+
+/// Like update_literal(state) but when it is already known that
+/// is_literal_state(state) is false.
+#define update_literal_matched(state) \
+ state = ((state) <= STATE_LIT_SHORTREP \
+ ? (state) - 3 \
+ : (state) - 6);
+
/// Indicate that the latest state was a match.
#define update_match(state) \
state = ((state) < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH)
@@ -112,31 +125,33 @@ typedef enum {
///
/// 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
+#define LITERAL_CODER_SIZE UINT32_C(0x300)
/// Maximum number of literal coders
#define LITERAL_CODERS_MAX (1 << LZMA_LCLP_MAX)
+/// Calculates the literal_mask that literal_subcoder() needs.
+#define literal_mask_calc(lc, lp) \
+ ((UINT32_C(0x100) << (lp)) - (UINT32_C(0x100) >> (lc)))
+
/// Locate the literal coder for the next literal byte. The choice depends on
/// - the lowest literal_pos_bits bits of the position of the current
/// byte; and
/// - the highest literal_context_bits bits of the previous byte.
-#define literal_subcoder(probs, lc, lp_mask, pos, prev_byte) \
- ((probs)[(((pos) & (lp_mask)) << (lc)) \
- + ((uint32_t)(prev_byte) >> (8U - (lc)))])
+#define literal_subcoder(probs, lc, literal_mask, pos, prev_byte) \
+ ((probs) + UINT32_C(3) * \
+ (((((pos) << 8) + (prev_byte)) & (literal_mask)) << (lc)))
static inline void
-literal_init(probability (*probs)[LITERAL_CODER_SIZE],
- uint32_t lc, uint32_t lp)
+literal_init(probability *probs, uint32_t lc, uint32_t lp)
{
assert(lc + lp <= LZMA_LCLP_MAX);
- const uint32_t coders = 1U << (lc + lp);
+ const size_t coders = LITERAL_CODER_SIZE << (lc + lp);
- for (uint32_t i = 0; i < coders; ++i)
- for (uint32_t j = 0; j < LITERAL_CODER_SIZE; ++j)
- bit_reset(probs[i][j]);
+ for (size_t i = 0; i < coders; ++i)
+ bit_reset(probs[i]);
return;
}
diff --git a/src/liblzma/lzma/lzma_decoder.c b/src/liblzma/lzma/lzma_decoder.c
index 26c148a..0abed02 100644
--- a/src/liblzma/lzma/lzma_decoder.c
+++ b/src/liblzma/lzma/lzma_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_decoder.c
@@ -5,9 +7,7 @@
///
// Authors: Igor Pavlov
// Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
@@ -22,25 +22,20 @@
# pragma GCC diagnostic ignored "-Wimplicit-fallthrough"
#endif
+// Minimum number of input bytes 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 20 bytes of input.
+#define LZMA_IN_REQUIRED 20
-#ifdef HAVE_SMALL
// Macros for (somewhat) size-optimized code.
-#define seq_4(seq) seq
-
-#define seq_6(seq) seq
-
-#define seq_8(seq) seq
-
-#define seq_len(seq) \
- seq ## _CHOICE, \
- seq ## _CHOICE2, \
- seq ## _BITTREE
-
+// This is used to decode the match length (how many bytes must be repeated
+// from the dictionary). This version is used in the Resumable mode and
+// does not unroll any loops.
#define len_decode(target, ld, pos_state, seq) \
do { \
case seq ## _CHOICE: \
- rc_if_0(ld.choice, seq ## _CHOICE) { \
+ rc_if_0_safe(ld.choice, seq ## _CHOICE) { \
rc_update_0(ld.choice); \
probs = ld.low[pos_state];\
limit = LEN_LOW_SYMBOLS; \
@@ -48,7 +43,7 @@ case seq ## _CHOICE: \
} else { \
rc_update_1(ld.choice); \
case seq ## _CHOICE2: \
- rc_if_0(ld.choice2, seq ## _CHOICE2) { \
+ rc_if_0_safe(ld.choice2, seq ## _CHOICE2) { \
rc_update_0(ld.choice2); \
probs = ld.mid[pos_state]; \
limit = LEN_MID_SYMBOLS; \
@@ -64,98 +59,39 @@ case seq ## _CHOICE2: \
symbol = 1; \
case seq ## _BITTREE: \
do { \
- rc_bit(probs[symbol], , , seq ## _BITTREE); \
+ rc_bit_safe(probs[symbol], , , seq ## _BITTREE); \
} while (symbol < limit); \
target += symbol - limit; \
} while (0)
-#else // HAVE_SMALL
-
-// Unrolled versions
-#define seq_4(seq) \
- seq ## 0, \
- seq ## 1, \
- seq ## 2, \
- seq ## 3
-
-#define seq_6(seq) \
- seq ## 0, \
- seq ## 1, \
- seq ## 2, \
- seq ## 3, \
- seq ## 4, \
- seq ## 5
-
-#define seq_8(seq) \
- seq ## 0, \
- seq ## 1, \
- seq ## 2, \
- seq ## 3, \
- seq ## 4, \
- seq ## 5, \
- seq ## 6, \
- seq ## 7
-
-#define seq_len(seq) \
- seq ## _CHOICE, \
- seq ## _LOW0, \
- seq ## _LOW1, \
- seq ## _LOW2, \
- seq ## _CHOICE2, \
- seq ## _MID0, \
- seq ## _MID1, \
- seq ## _MID2, \
- seq ## _HIGH0, \
- seq ## _HIGH1, \
- seq ## _HIGH2, \
- seq ## _HIGH3, \
- seq ## _HIGH4, \
- seq ## _HIGH5, \
- seq ## _HIGH6, \
- seq ## _HIGH7
-#define len_decode(target, ld, pos_state, seq) \
+// This is the faster version of the match length decoder that does not
+// worry about being resumable. It unrolls the bittree decoding loop.
+#define len_decode_fast(target, ld, pos_state) \
do { \
symbol = 1; \
-case seq ## _CHOICE: \
- rc_if_0(ld.choice, seq ## _CHOICE) { \
+ rc_if_0(ld.choice) { \
rc_update_0(ld.choice); \
- rc_bit_case(ld.low[pos_state][symbol], , , seq ## _LOW0); \
- rc_bit_case(ld.low[pos_state][symbol], , , seq ## _LOW1); \
- rc_bit_case(ld.low[pos_state][symbol], , , seq ## _LOW2); \
- target = symbol - LEN_LOW_SYMBOLS + MATCH_LEN_MIN; \
+ rc_bittree3(ld.low[pos_state], \
+ -LEN_LOW_SYMBOLS + MATCH_LEN_MIN); \
+ target = symbol; \
} else { \
rc_update_1(ld.choice); \
-case seq ## _CHOICE2: \
- rc_if_0(ld.choice2, seq ## _CHOICE2) { \
+ rc_if_0(ld.choice2) { \
rc_update_0(ld.choice2); \
- rc_bit_case(ld.mid[pos_state][symbol], , , \
- seq ## _MID0); \
- rc_bit_case(ld.mid[pos_state][symbol], , , \
- seq ## _MID1); \
- rc_bit_case(ld.mid[pos_state][symbol], , , \
- seq ## _MID2); \
- target = symbol - LEN_MID_SYMBOLS \
- + MATCH_LEN_MIN + LEN_LOW_SYMBOLS; \
+ rc_bittree3(ld.mid[pos_state], -LEN_MID_SYMBOLS \
+ + MATCH_LEN_MIN + LEN_LOW_SYMBOLS); \
+ target = symbol; \
} else { \
rc_update_1(ld.choice2); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH0); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH1); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH2); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH3); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH4); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH5); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH6); \
- rc_bit_case(ld.high[symbol], , , seq ## _HIGH7); \
- target = symbol - LEN_HIGH_SYMBOLS \
+ rc_bittree8(ld.high, -LEN_HIGH_SYMBOLS \
+ MATCH_LEN_MIN \
- + LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS; \
+ + LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS); \
+ target = symbol; \
} \
} \
} while (0)
-#endif // HAVE_SMALL
-
/// Length decoder probabilities; see comments in lzma_common.h.
typedef struct {
@@ -173,7 +109,7 @@ typedef struct {
///////////////////
/// Literals; see comments in lzma_common.h.
- probability literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE];
+ probability literal[LITERAL_CODERS_MAX * LITERAL_CODER_SIZE];
/// If 1, it's a match. Otherwise it's a single 8-bit literal.
probability is_match[STATES][POS_STATES_MAX];
@@ -232,7 +168,7 @@ typedef struct {
uint32_t pos_mask; // (1U << pb) - 1
uint32_t literal_context_bits;
- uint32_t literal_pos_mask;
+ uint32_t literal_mask;
/// Uncompressed size as bytes, or LZMA_VLI_UNKNOWN if end of
/// payload marker is expected.
@@ -251,22 +187,26 @@ typedef struct {
enum {
SEQ_NORMALIZE,
SEQ_IS_MATCH,
- seq_8(SEQ_LITERAL),
- seq_8(SEQ_LITERAL_MATCHED),
+ SEQ_LITERAL,
+ SEQ_LITERAL_MATCHED,
SEQ_LITERAL_WRITE,
SEQ_IS_REP,
- seq_len(SEQ_MATCH_LEN),
- seq_6(SEQ_DIST_SLOT),
+ SEQ_MATCH_LEN_CHOICE,
+ SEQ_MATCH_LEN_CHOICE2,
+ SEQ_MATCH_LEN_BITTREE,
+ SEQ_DIST_SLOT,
SEQ_DIST_MODEL,
SEQ_DIRECT,
- seq_4(SEQ_ALIGN),
+ SEQ_ALIGN,
SEQ_EOPM,
SEQ_IS_REP0,
SEQ_SHORTREP,
SEQ_IS_REP0_LONG,
SEQ_IS_REP1,
SEQ_IS_REP2,
- seq_len(SEQ_REP_LEN),
+ SEQ_REP_LEN_CHOICE,
+ SEQ_REP_LEN_CHOICE2,
+ SEQ_REP_LEN_BITTREE,
SEQ_COPY,
} sequence;
@@ -321,7 +261,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
const size_t dict_start = dict.pos;
// Range decoder
- rc_to_local(coder->rc, *in_pos);
+ rc_to_local(coder->rc, *in_pos, LZMA_IN_REQUIRED);
// State
uint32_t state = coder->state;
@@ -340,7 +280,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
uint32_t offset = coder->offset;
uint32_t len = coder->len;
- const uint32_t literal_pos_mask = coder->literal_pos_mask;
+ const uint32_t literal_mask = coder->literal_mask;
const uint32_t literal_context_bits = coder->literal_context_bits;
// Temporary variables
@@ -367,8 +307,24 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
might_finish_without_eopm = true;
}
- // The main decoder loop. The "switch" is used to restart the decoder at
- // correct location. Once restarted, the "switch" is no longer used.
+ // The main decoder loop. The "switch" is used to resume the decoder at
+ // correct location. Once resumed, the "switch" is no longer used.
+ // The decoder loops is split into two modes:
+ //
+ // 1 - Non-resumable mode (fast). This is used when it is guaranteed
+ // there is enough input to decode the next symbol. If the output
+ // limit is reached, then the decoder loop will save the place
+ // for the resumable mode to continue. This mode is not used if
+ // HAVE_SMALL is defined. This is faster than Resumable mode
+ // because it reduces the number of branches needed and allows
+ // for more compiler optimizations.
+ //
+ // 2 - Resumable mode (slow). This is used when a previous decoder
+ // loop did not have enough space in the input or output buffers
+ // to complete. It uses sequence enum values to set remind
+ // coder->sequence where to resume in the decoder loop. This
+ // is the only mode used when HAVE_SMALL is defined.
+
switch (coder->sequence)
while (true) {
// Calculate new pos_state. This is skipped on the first loop
@@ -376,13 +332,339 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
// variables.
pos_state = dict.pos & pos_mask;
+#ifndef HAVE_SMALL
+
+ ///////////////////////////////
+ // Non-resumable Mode (fast) //
+ ///////////////////////////////
+
+ // Go to Resumable mode (1) if there is not enough input to
+ // safely decode any possible LZMA symbol or (2) if the
+ // dictionary is full, which may need special checks that
+ // are only done in the Resumable mode.
+ if (unlikely(!rc_is_fast_allowed()
+ || dict.pos == dict.limit))
+ goto slow;
+
+ // Decode the first bit from the next LZMA symbol.
+ // If the bit is a 0, then we handle it as a literal.
+ // If the bit is a 1, then it is a match of previously
+ // decoded data.
+ rc_if_0(coder->is_match[state][pos_state]) {
+ /////////////////////
+ // Decode literal. //
+ /////////////////////
+
+ // Update the RC that we have decoded a 0.
+ rc_update_0(coder->is_match[state][pos_state]);
+
+ // Get the correct probability array from lp and
+ // lc params.
+ probs = literal_subcoder(coder->literal,
+ literal_context_bits, literal_mask,
+ dict.pos, dict_get0(&dict));
+
+ if (is_literal_state(state)) {
+ update_literal_normal(state);
+
+ // Decode literal without match byte.
+ rc_bittree8(probs, 0);
+ } else {
+ update_literal_matched(state);
+
+ // Decode literal with match byte.
+ rc_matched_literal(probs,
+ dict_get(&dict, rep0));
+ }
+
+ // Write decoded literal to dictionary
+ dict_put(&dict, symbol);
+ continue;
+ }
+
+ ///////////////////
+ // Decode match. //
+ ///////////////////
+
+ // Instead of a new byte we are going to decode a
+ // distance-length pair. The distance represents how far
+ // back in the dictionary to begin copying. The length
+ // represents how many bytes to copy.
+
+ rc_update_1(coder->is_match[state][pos_state]);
+
+ rc_if_0(coder->is_rep[state]) {
+ ///////////////////
+ // Simple match. //
+ ///////////////////
+
+ // Not a repeated match. In this case,
+ // the length (how many bytes to copy) must be
+ // decoded first. Then, the distance (where to
+ // start copying) is decoded.
+ //
+ // This is also how we know when we are done
+ // decoding. If the distance decodes to UINT32_MAX,
+ // then we know to stop decoding (end of payload
+ // marker).
+
+ rc_update_0(coder->is_rep[state]);
+ update_match(state);
+
+ // The latest three match distances are kept in
+ // memory in case there are repeated matches.
+ rep3 = rep2;
+ rep2 = rep1;
+ rep1 = rep0;
+
+ // Decode the length of the match.
+ len_decode_fast(len, coder->match_len_decoder,
+ pos_state);
+
+ // Next, decode the distance into rep0.
+
+ // The next 6 bits determine how to decode the
+ // rest of the distance.
+ probs = coder->dist_slot[get_dist_state(len)];
+
+ rc_bittree6(probs, -DIST_SLOTS);
+ assert(symbol <= 63);
+
+ if (symbol < DIST_MODEL_START) {
+ // If the decoded symbol is < DIST_MODEL_START
+ // then we use its value directly as the
+ // match distance. No other bits are needed.
+ // The only possible distance values
+ // are [0, 3].
+ rep0 = symbol;
+ } else {
+ // Use the first two bits of symbol as the
+ // highest bits of the match distance.
+
+ // "limit" represents the number of low bits
+ // to decode.
+ limit = (symbol >> 1) - 1;
+ assert(limit >= 1 && limit <= 30);
+ rep0 = 2 + (symbol & 1);
+
+ if (symbol < DIST_MODEL_END) {
+ // When symbol is > DIST_MODEL_START,
+ // but symbol < DIST_MODEL_END, then
+ // it can decode distances between
+ // [4, 127].
+ assert(limit <= 5);
+ rep0 <<= limit;
+ assert(rep0 <= 96);
+
+ // -1 is fine, because we start
+ // decoding at probs[1], not probs[0].
+ // NOTE: This violates the C standard,
+ // since we are doing pointer
+ // arithmetic past the beginning of
+ // the array.
+ assert((int32_t)(rep0 - symbol - 1)
+ >= -1);
+ assert((int32_t)(rep0 - symbol - 1)
+ <= 82);
+ probs = coder->pos_special + rep0
+ - symbol - 1;
+ symbol = 1;
+ offset = 1;
+
+ // Variable number (1-5) of bits
+ // from a reverse bittree. This
+ // isn't worth manual unrolling.
+ //
+ // NOTE: Making one or many of the
+ // variables (probs, symbol, offset,
+ // or limit) local here (instead of
+ // using those declared outside the
+ // main loop) can affect code size
+ // and performance which isn't a
+ // surprise but it's not so clear
+ // what is the best.
+ do {
+ rc_bit_add_if_1(probs,
+ rep0, offset);
+ offset <<= 1;
+ } while (--limit > 0);
+ } else {
+ // The distance is >= 128. Decode the
+ // lower bits without probabilities
+ // except the lowest four bits.
+ assert(symbol >= 14);
+ assert(limit >= 6);
+
+ limit -= ALIGN_BITS;
+ assert(limit >= 2);
+
+ rc_direct(rep0, limit);
+
+ // Decode the lowest four bits using
+ // probabilities.
+ rep0 <<= ALIGN_BITS;
+ rc_bittree_rev4(coder->pos_align);
+ rep0 += symbol;
+
+ // If the end of payload marker (EOPM)
+ // is detected, jump to the safe code.
+ // The EOPM handling isn't speed
+ // critical at all.
+ //
+ // A final normalization is needed
+ // after the EOPM (there can be a
+ // dummy byte to read in some cases).
+ // If the normalization was done here
+ // in the fast code, it would need to
+ // be taken into account in the value
+ // of LZMA_IN_REQUIRED. Using the
+ // safe code allows keeping
+ // LZMA_IN_REQUIRED as 20 instead of
+ // 21.
+ if (rep0 == UINT32_MAX)
+ goto eopm;
+ }
+ }
+
+ // Validate the distance we just decoded.
+ if (unlikely(!dict_is_distance_valid(&dict, rep0))) {
+ ret = LZMA_DATA_ERROR;
+ goto out;
+ }
+
+ } else {
+ rc_update_1(coder->is_rep[state]);
+
+ /////////////////////
+ // Repeated match. //
+ /////////////////////
+
+ // The match distance is a value that we have decoded
+ // recently. The latest four match distances are
+ // available as rep0, rep1, rep2 and rep3. We will
+ // now decode which of them is the new distance.
+ //
+ // There cannot be a match if we haven't produced
+ // any output, so check that first.
+ if (unlikely(!dict_is_distance_valid(&dict, 0))) {
+ ret = LZMA_DATA_ERROR;
+ goto out;
+ }
+
+ rc_if_0(coder->is_rep0[state]) {
+ rc_update_0(coder->is_rep0[state]);
+ // The distance is rep0.
+
+ // Decode the next bit to determine if 1 byte
+ // should be copied from rep0 distance or
+ // if the number of bytes needs to be decoded.
+
+ // If the next bit is 0, then it is a
+ // "Short Rep Match" and only 1 bit is copied.
+ // Otherwise, the length of the match is
+ // decoded after the "else" statement.
+ rc_if_0(coder->is_rep0_long[state][pos_state]) {
+ rc_update_0(coder->is_rep0_long[
+ state][pos_state]);
+
+ update_short_rep(state);
+ dict_put(&dict, dict_get(&dict, rep0));
+ continue;
+ }
+
+ // Repeating more than one byte at
+ // distance of rep0.
+ rc_update_1(coder->is_rep0_long[
+ state][pos_state]);
+
+ } else {
+ rc_update_1(coder->is_rep0[state]);
+
+ // The distance is rep1, rep2 or rep3. Once
+ // we find out which one of these three, it
+ // is stored to rep0 and rep1, rep2 and rep3
+ // are updated accordingly. There is no
+ // "Short Rep Match" option, so the length
+ // of the match must always be decoded next.
+ rc_if_0(coder->is_rep1[state]) {
+ // The distance is rep1.
+ rc_update_0(coder->is_rep1[state]);
+
+ const uint32_t distance = rep1;
+ rep1 = rep0;
+ rep0 = distance;
+
+ } else {
+ rc_update_1(coder->is_rep1[state]);
+
+ rc_if_0(coder->is_rep2[state]) {
+ // The distance is rep2.
+ rc_update_0(coder->is_rep2[
+ state]);
+
+ const uint32_t distance = rep2;
+ rep2 = rep1;
+ rep1 = rep0;
+ rep0 = distance;
+
+ } else {
+ // The distance is rep3.
+ rc_update_1(coder->is_rep2[
+ state]);
+
+ const uint32_t distance = rep3;
+ rep3 = rep2;
+ rep2 = rep1;
+ rep1 = rep0;
+ rep0 = distance;
+ }
+ }
+ }
+
+ update_long_rep(state);
+
+ // Decode the length of the repeated match.
+ len_decode_fast(len, coder->rep_len_decoder,
+ pos_state);
+ }
+
+ /////////////////////////////////
+ // Repeat from history buffer. //
+ /////////////////////////////////
+
+ // The length is always between these limits. There is no way
+ // to trigger the algorithm to set len outside this range.
+ assert(len >= MATCH_LEN_MIN);
+ assert(len <= MATCH_LEN_MAX);
+
+ // Repeat len bytes from distance of rep0.
+ if (unlikely(dict_repeat(&dict, rep0, &len))) {
+ coder->sequence = SEQ_COPY;
+ goto out;
+ }
+
+ continue;
+
+slow:
+#endif
+ ///////////////////////////
+ // Resumable Mode (slow) //
+ ///////////////////////////
+
+ // This is very similar to Non-resumable Mode, so most of the
+ // comments are not repeated. The main differences are:
+ // - case labels are used to resume at the correct location.
+ // - Loops are not unrolled.
+ // - Range coder macros take an extra sequence argument
+ // so they can save to coder->sequence the location to
+ // resume in case there is not enough input.
case SEQ_NORMALIZE:
case SEQ_IS_MATCH:
if (unlikely(might_finish_without_eopm
&& dict.pos == dict.limit)) {
// In rare cases there is a useless byte that needs
// to be read anyway.
- rc_normalize(SEQ_NORMALIZE);
+ rc_normalize_safe(SEQ_NORMALIZE);
// If the range decoder state is such that we can
// be at the end of the LZMA stream, then the
@@ -405,49 +687,37 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
eopm_is_valid = true;
}
- rc_if_0(coder->is_match[state][pos_state], SEQ_IS_MATCH) {
- rc_update_0(coder->is_match[state][pos_state]);
+ rc_if_0_safe(coder->is_match[state][pos_state], SEQ_IS_MATCH) {
+ /////////////////////
+ // Decode literal. //
+ /////////////////////
- // It's a literal i.e. a single 8-bit byte.
+ rc_update_0(coder->is_match[state][pos_state]);
probs = literal_subcoder(coder->literal,
- literal_context_bits, literal_pos_mask,
- dict.pos, dict_get(&dict, 0));
+ literal_context_bits, literal_mask,
+ dict.pos, dict_get0(&dict));
symbol = 1;
if (is_literal_state(state)) {
+ update_literal_normal(state);
+
// Decode literal without match byte.
-#ifdef HAVE_SMALL
+ // The "slow" version does not unroll
+ // the loop.
case SEQ_LITERAL:
do {
- rc_bit(probs[symbol], , , SEQ_LITERAL);
+ rc_bit_safe(probs[symbol], , ,
+ SEQ_LITERAL);
} while (symbol < (1 << 8));
-#else
- rc_bit_case(probs[symbol], , , SEQ_LITERAL0);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL1);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL2);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL3);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL4);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL5);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL6);
- rc_bit_case(probs[symbol], , , SEQ_LITERAL7);
-#endif
} else {
+ update_literal_matched(state);
+
// Decode literal with match byte.
- //
- // We store the byte we compare against
- // ("match byte") to "len" to minimize the
- // number of variables we need to store
- // between decoder calls.
len = (uint32_t)(dict_get(&dict, rep0)) << 1;
- // The usage of "offset" allows omitting some
- // branches, which should give tiny speed
- // improvement on some CPUs. "offset" gets
- // set to zero if match_bit didn't match.
offset = 0x100;
-#ifdef HAVE_SMALL
case SEQ_LITERAL_MATCHED:
do {
const uint32_t match_bit
@@ -456,7 +726,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
= offset + match_bit
+ symbol;
- rc_bit(probs[subcoder_index],
+ rc_bit_safe(probs[subcoder_index],
offset &= ~match_bit,
offset &= match_bit,
SEQ_LITERAL_MATCHED);
@@ -469,61 +739,10 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
len <<= 1;
} while (symbol < (1 << 8));
-#else
- // Unroll the loop.
- uint32_t match_bit;
- uint32_t subcoder_index;
-
-# define d(seq) \
- case seq: \
- match_bit = len & offset; \
- subcoder_index = offset + match_bit + symbol; \
- rc_bit(probs[subcoder_index], \
- offset &= ~match_bit, \
- offset &= match_bit, \
- seq)
-
- d(SEQ_LITERAL_MATCHED0);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED1);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED2);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED3);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED4);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED5);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED6);
- len <<= 1;
- d(SEQ_LITERAL_MATCHED7);
-# undef d
-#endif
}
- //update_literal(state);
- // Use a lookup table to update to literal state,
- // since compared to other state updates, this would
- // need two branches.
- static const lzma_lzma_state next_state[] = {
- STATE_LIT_LIT,
- STATE_LIT_LIT,
- STATE_LIT_LIT,
- 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_MATCH_LIT,
- STATE_REP_LIT
- };
- state = next_state[state];
-
case SEQ_LITERAL_WRITE:
- if (unlikely(dict_put(&dict, symbol))) {
+ if (dict_put_safe(&dict, symbol)) {
coder->sequence = SEQ_LITERAL_WRITE;
goto out;
}
@@ -531,64 +750,47 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
continue;
}
- // Instead of a new byte we are going to get a byte range
- // (distance and length) which will be repeated from our
- // output history.
+ ///////////////////
+ // Decode match. //
+ ///////////////////
rc_update_1(coder->is_match[state][pos_state]);
case SEQ_IS_REP:
- rc_if_0(coder->is_rep[state], SEQ_IS_REP) {
- // Not a repeated match
+ rc_if_0_safe(coder->is_rep[state], SEQ_IS_REP) {
+ ///////////////////
+ // Simple match. //
+ ///////////////////
+
rc_update_0(coder->is_rep[state]);
update_match(state);
- // The latest three match distances are kept in
- // memory in case there are repeated matches.
rep3 = rep2;
rep2 = rep1;
rep1 = rep0;
- // Decode the length of the match.
len_decode(len, coder->match_len_decoder,
pos_state, SEQ_MATCH_LEN);
- // Prepare to decode the highest two bits of the
- // match distance.
probs = coder->dist_slot[get_dist_state(len)];
symbol = 1;
-#ifdef HAVE_SMALL
case SEQ_DIST_SLOT:
do {
- rc_bit(probs[symbol], , , SEQ_DIST_SLOT);
+ rc_bit_safe(probs[symbol], , , SEQ_DIST_SLOT);
} while (symbol < DIST_SLOTS);
-#else
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT0);
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT1);
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT2);
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT3);
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT4);
- rc_bit_case(probs[symbol], , , SEQ_DIST_SLOT5);
-#endif
- // Get rid of the highest bit that was needed for
- // indexing of the probability array.
+
symbol -= DIST_SLOTS;
assert(symbol <= 63);
if (symbol < DIST_MODEL_START) {
- // Match distances [0, 3] have only two bits.
rep0 = symbol;
} else {
- // Decode the lowest [1, 29] bits of
- // the match distance.
limit = (symbol >> 1) - 1;
assert(limit >= 1 && limit <= 30);
rep0 = 2 + (symbol & 1);
if (symbol < DIST_MODEL_END) {
- // Prepare to decode the low bits for
- // a distance of [4, 127].
assert(limit <= 5);
rep0 <<= limit;
assert(rep0 <= 96);
@@ -607,95 +809,36 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
symbol = 1;
offset = 0;
case SEQ_DIST_MODEL:
-#ifdef HAVE_SMALL
do {
- rc_bit(probs[symbol], ,
+ rc_bit_safe(probs[symbol], ,
rep0 += 1U << offset,
SEQ_DIST_MODEL);
} while (++offset < limit);
-#else
- switch (limit) {
- case 5:
- assert(offset == 0);
- rc_bit(probs[symbol], ,
- rep0 += 1U,
- SEQ_DIST_MODEL);
- ++offset;
- --limit;
- case 4:
- rc_bit(probs[symbol], ,
- rep0 += 1U << offset,
- SEQ_DIST_MODEL);
- ++offset;
- --limit;
- case 3:
- rc_bit(probs[symbol], ,
- rep0 += 1U << offset,
- SEQ_DIST_MODEL);
- ++offset;
- --limit;
- case 2:
- rc_bit(probs[symbol], ,
- rep0 += 1U << offset,
- SEQ_DIST_MODEL);
- ++offset;
- --limit;
- case 1:
- // We need "symbol" only for
- // indexing the probability
- // array, thus we can use
- // rc_bit_last() here to omit
- // the unneeded updating of
- // "symbol".
- rc_bit_last(probs[symbol], ,
- rep0 += 1U << offset,
- SEQ_DIST_MODEL);
- }
-#endif
} else {
- // The distance is >= 128. Decode the
- // lower bits without probabilities
- // except the lowest four bits.
assert(symbol >= 14);
assert(limit >= 6);
limit -= ALIGN_BITS;
assert(limit >= 2);
case SEQ_DIRECT:
- // Not worth manual unrolling
- do {
- rc_direct(rep0, SEQ_DIRECT);
- } while (--limit > 0);
+ rc_direct_safe(rep0, limit,
+ SEQ_DIRECT);
- // Decode the lowest four bits using
- // probabilities.
rep0 <<= ALIGN_BITS;
- symbol = 1;
-#ifdef HAVE_SMALL
- offset = 0;
+ symbol = 0;
+ offset = 1;
case SEQ_ALIGN:
do {
- rc_bit(coder->pos_align[
- symbol], ,
- rep0 += 1U << offset,
+ rc_bit_last_safe(
+ coder->pos_align[
+ offset
+ + symbol],
+ ,
+ symbol += offset,
SEQ_ALIGN);
- } while (++offset < ALIGN_BITS);
-#else
- case SEQ_ALIGN0:
- rc_bit(coder->pos_align[symbol], ,
- rep0 += 1, SEQ_ALIGN0);
- case SEQ_ALIGN1:
- rc_bit(coder->pos_align[symbol], ,
- rep0 += 2, SEQ_ALIGN1);
- case SEQ_ALIGN2:
- rc_bit(coder->pos_align[symbol], ,
- rep0 += 4, SEQ_ALIGN2);
- case SEQ_ALIGN3:
- // Like in SEQ_DIST_MODEL, we don't
- // need "symbol" for anything else
- // than indexing the probability array.
- rc_bit_last(coder->pos_align[symbol], ,
- rep0 += 8, SEQ_ALIGN3);
-#endif
+ offset <<= 1;
+ } while (offset < ALIGN_SIZE);
+
+ rep0 += symbol;
if (rep0 == UINT32_MAX) {
// End of payload marker was
@@ -710,6 +853,9 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
// that EOPM might be used
// (it's not allowed in
// LZMA2).
+#ifndef HAVE_SMALL
+eopm:
+#endif
if (!eopm_is_valid) {
ret = LZMA_DATA_ERROR;
goto out;
@@ -718,7 +864,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
case SEQ_EOPM:
// LZMA1 stream with
// end-of-payload marker.
- rc_normalize(SEQ_EOPM);
+ rc_normalize_safe(SEQ_EOPM);
ret = rc_is_finished(rc)
? LZMA_STREAM_END
: LZMA_DATA_ERROR;
@@ -727,36 +873,30 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
}
}
- // Validate the distance we just decoded.
if (unlikely(!dict_is_distance_valid(&dict, rep0))) {
ret = LZMA_DATA_ERROR;
goto out;
}
} else {
+ /////////////////////
+ // Repeated match. //
+ /////////////////////
+
rc_update_1(coder->is_rep[state]);
- // Repeated match
- //
- // The match distance is a value that we have had
- // earlier. The latest four match distances are
- // available as rep0, rep1, rep2 and rep3. We will
- // now decode which of them is the new distance.
- //
- // There cannot be a match if we haven't produced
- // any output, so check that first.
if (unlikely(!dict_is_distance_valid(&dict, 0))) {
ret = LZMA_DATA_ERROR;
goto out;
}
case SEQ_IS_REP0:
- rc_if_0(coder->is_rep0[state], SEQ_IS_REP0) {
+ rc_if_0_safe(coder->is_rep0[state], SEQ_IS_REP0) {
rc_update_0(coder->is_rep0[state]);
- // The distance is rep0.
case SEQ_IS_REP0_LONG:
- rc_if_0(coder->is_rep0_long[state][pos_state],
+ rc_if_0_safe(coder->is_rep0_long
+ [state][pos_state],
SEQ_IS_REP0_LONG) {
rc_update_0(coder->is_rep0_long[
state][pos_state]);
@@ -764,8 +904,9 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
update_short_rep(state);
case SEQ_SHORTREP:
- if (unlikely(dict_put(&dict, dict_get(
- &dict, rep0)))) {
+ if (dict_put_safe(&dict,
+ dict_get(&dict,
+ rep0))) {
coder->sequence = SEQ_SHORTREP;
goto out;
}
@@ -773,8 +914,6 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
continue;
}
- // Repeating more than one byte at
- // distance of rep0.
rc_update_1(coder->is_rep0_long[
state][pos_state]);
@@ -782,11 +921,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
rc_update_1(coder->is_rep0[state]);
case SEQ_IS_REP1:
- // The distance is rep1, rep2 or rep3. Once
- // we find out which one of these three, it
- // is stored to rep0 and rep1, rep2 and rep3
- // are updated accordingly.
- rc_if_0(coder->is_rep1[state], SEQ_IS_REP1) {
+ rc_if_0_safe(coder->is_rep1[state], SEQ_IS_REP1) {
rc_update_0(coder->is_rep1[state]);
const uint32_t distance = rep1;
@@ -796,7 +931,7 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
} else {
rc_update_1(coder->is_rep1[state]);
case SEQ_IS_REP2:
- rc_if_0(coder->is_rep2[state],
+ rc_if_0_safe(coder->is_rep2[state],
SEQ_IS_REP2) {
rc_update_0(coder->is_rep2[
state]);
@@ -821,7 +956,6 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
update_long_rep(state);
- // Decode the length of the repeated match.
len_decode(len, coder->rep_len_decoder,
pos_state, SEQ_REP_LEN);
}
@@ -830,13 +964,10 @@ lzma_decode(void *coder_ptr, lzma_dict *restrict dictptr,
// Repeat from history buffer. //
/////////////////////////////////
- // The length is always between these limits. There is no way
- // to trigger the algorithm to set len outside this range.
assert(len >= MATCH_LEN_MIN);
assert(len <= MATCH_LEN_MAX);
case SEQ_COPY:
- // Repeat len bytes from distance of rep0.
if (unlikely(dict_repeat(&dict, rep0, &len))) {
coder->sequence = SEQ_COPY;
goto out;
@@ -890,7 +1021,6 @@ out:
}
-
static void
lzma_decoder_uncompressed(void *coder_ptr, lzma_vli uncompressed_size,
bool allow_eopm)
@@ -917,7 +1047,7 @@ lzma_decoder_reset(void *coder_ptr, const void *opt)
literal_init(coder->literal, options->lc, options->lp);
coder->literal_context_bits = options->lc;
- coder->literal_pos_mask = (1U << options->lp) - 1;
+ coder->literal_mask = literal_mask_calc(options->lc, options->lp);
// State
coder->state = STATE_LIT_LIT;
diff --git a/src/liblzma/lzma/lzma_decoder.h b/src/liblzma/lzma/lzma_decoder.h
index 1427bc2..9730f56 100644
--- a/src/liblzma/lzma/lzma_decoder.h
+++ b/src/liblzma/lzma/lzma_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_decoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA_DECODER_H
diff --git a/src/liblzma/lzma/lzma_encoder.c b/src/liblzma/lzma/lzma_encoder.c
index 559c63e..543ca32 100644
--- a/src/liblzma/lzma/lzma_encoder.c
+++ b/src/liblzma/lzma/lzma_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma2_encoder.h"
@@ -49,24 +48,24 @@ literal(lzma_lzma1_encoder *coder, lzma_mf *mf, uint32_t position)
const uint8_t cur_byte = mf->buffer[
mf->read_pos - mf->read_ahead];
probability *subcoder = literal_subcoder(coder->literal,
- coder->literal_context_bits, coder->literal_pos_mask,
+ coder->literal_context_bits, coder->literal_mask,
position, mf->buffer[mf->read_pos - mf->read_ahead - 1]);
if (is_literal_state(coder->state)) {
// Previous LZMA-symbol was a literal. Encode a normal
// literal without a match byte.
+ update_literal_normal(coder->state);
rc_bittree(&coder->rc, subcoder, 8, cur_byte);
} else {
// Previous LZMA-symbol was a match. Use the last byte of
// the match as a "match byte". That is, compare the bits
// of the current literal and the match byte.
+ update_literal_matched(coder->state);
const uint8_t match_byte = mf->buffer[
mf->read_pos - coder->reps[0] - 1
- mf->read_ahead];
literal_matched(&coder->rc, subcoder, match_byte, cur_byte);
}
-
- update_literal(coder->state);
}
@@ -283,7 +282,7 @@ encode_init(lzma_lzma1_encoder *coder, lzma_mf *mf)
mf_skip(mf, 1);
mf->read_ahead = 0;
rc_bit(&coder->rc, &coder->is_match[0][0], 0);
- rc_bittree(&coder->rc, coder->literal[0], 8, mf->buffer[0]);
+ rc_bittree(&coder->rc, coder->literal + 0, 8, mf->buffer[0]);
++coder->uncomp_size;
}
@@ -535,7 +534,7 @@ lzma_lzma_encoder_reset(lzma_lzma1_encoder *coder,
coder->pos_mask = (1U << options->pb) - 1;
coder->literal_context_bits = options->lc;
- coder->literal_pos_mask = (1U << options->lp) - 1;
+ coder->literal_mask = literal_mask_calc(options->lc, options->lp);
// Range coder
rc_reset(&coder->rc);
@@ -712,6 +711,9 @@ static lzma_ret
lzma_encoder_init(lzma_lz_encoder *lz, const lzma_allocator *allocator,
lzma_vli id, const void *options, lzma_lz_options *lz_options)
{
+ if (options == NULL)
+ return LZMA_PROG_ERROR;
+
lz->code = &lzma_encode;
lz->set_out_limit = &lzma_lzma_set_out_limit;
return lzma_lzma_encoder_create(
diff --git a/src/liblzma/lzma/lzma_encoder.h b/src/liblzma/lzma/lzma_encoder.h
index 84d8c91..e8ae807 100644
--- a/src/liblzma/lzma/lzma_encoder.h
+++ b/src/liblzma/lzma/lzma_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA_ENCODER_H
diff --git a/src/liblzma/lzma/lzma_encoder_optimum_fast.c b/src/liblzma/lzma/lzma_encoder_optimum_fast.c
index 6c53d2b..0f063d5 100644
--- a/src/liblzma/lzma/lzma_encoder_optimum_fast.c
+++ b/src/liblzma/lzma/lzma_encoder_optimum_fast.c
@@ -1,12 +1,11 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder_optimum_fast.c
//
// Author: Igor Pavlov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma_encoder_private.h"
diff --git a/src/liblzma/lzma/lzma_encoder_optimum_normal.c b/src/liblzma/lzma/lzma_encoder_optimum_normal.c
index 101c8d4..a6c0398 100644
--- a/src/liblzma/lzma/lzma_encoder_optimum_normal.c
+++ b/src/liblzma/lzma/lzma_encoder_optimum_normal.c
@@ -1,12 +1,11 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder_optimum_normal.c
//
// Author: Igor Pavlov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "lzma_encoder_private.h"
@@ -24,7 +23,7 @@ get_literal_price(const lzma_lzma1_encoder *const coder, const uint32_t pos,
uint32_t match_byte, uint32_t symbol)
{
const probability *const subcoder = literal_subcoder(coder->literal,
- coder->literal_context_bits, coder->literal_pos_mask,
+ coder->literal_context_bits, coder->literal_mask,
pos, prev_byte);
uint32_t price = 0;
diff --git a/src/liblzma/lzma/lzma_encoder_presets.c b/src/liblzma/lzma/lzma_encoder_presets.c
index 711df02..e53483f 100644
--- a/src/liblzma/lzma/lzma_encoder_presets.c
+++ b/src/liblzma/lzma/lzma_encoder_presets.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder_presets.c
@@ -6,9 +8,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "common.h"
diff --git a/src/liblzma/lzma/lzma_encoder_private.h b/src/liblzma/lzma/lzma_encoder_private.h
index b228c57..eeea5e9 100644
--- a/src/liblzma/lzma/lzma_encoder_private.h
+++ b/src/liblzma/lzma/lzma_encoder_private.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzma_encoder_private.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_LZMA_ENCODER_PRIVATE_H
@@ -116,10 +115,10 @@ struct lzma_lzma1_encoder_s {
uint32_t pos_mask; ///< (1 << pos_bits) - 1
uint32_t literal_context_bits;
- uint32_t literal_pos_mask;
+ uint32_t literal_mask;
// These are the same as in lzma_decoder.c. See comments there.
- probability literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE];
+ probability literal[LITERAL_CODERS_MAX * LITERAL_CODER_SIZE];
probability is_match[STATES][POS_STATES_MAX];
probability is_rep[STATES];
probability is_rep0[STATES];
diff --git a/src/liblzma/rangecoder/Makefile.inc b/src/liblzma/rangecoder/Makefile.inc
index d8a597a..9a00e6e 100644
--- a/src/liblzma/rangecoder/Makefile.inc
+++ b/src/liblzma/rangecoder/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
EXTRA_DIST += rangecoder/price_tablegen.c
diff --git a/src/liblzma/rangecoder/price.h b/src/liblzma/rangecoder/price.h
index 45dbbbb..cce6bda 100644
--- a/src/liblzma/rangecoder/price.h
+++ b/src/liblzma/rangecoder/price.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file price.h
@@ -5,9 +7,6 @@
//
// Author: Igor Pavlov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_PRICE_H
diff --git a/src/liblzma/rangecoder/price_table.c b/src/liblzma/rangecoder/price_table.c
index ac64bf6..c33433f 100644
--- a/src/liblzma/rangecoder/price_table.c
+++ b/src/liblzma/rangecoder/price_table.c
@@ -1,4 +1,6 @@
-/* This file has been automatically generated by price_tablegen.c. */
+// SPDX-License-Identifier: 0BSD
+
+// This file has been generated by price_tablegen.c.
#include "range_encoder.h"
diff --git a/src/liblzma/rangecoder/price_tablegen.c b/src/liblzma/rangecoder/price_tablegen.c
index bf08ce3..4b6ca37 100644
--- a/src/liblzma/rangecoder/price_tablegen.c
+++ b/src/liblzma/rangecoder/price_tablegen.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file price_tablegen.c
@@ -8,13 +10,15 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include <inttypes.h>
#include <stdio.h>
+
+// Make it compile without common.h.
+#define BUILDING_PRICE_TABLEGEN
+#define lzma_attr_visibility_hidden
+
#include "range_common.h"
#include "price.h"
@@ -54,11 +58,13 @@ init_price_table(void)
static void
print_price_table(void)
{
- printf("/* This file has been automatically generated by "
- "price_tablegen.c. */\n\n"
- "#include \"range_encoder.h\"\n\n"
- "const uint8_t lzma_rc_prices["
- "RC_PRICE_TABLE_SIZE] = {");
+ // Split the SPDX string so that it won't accidentally match
+ // when tools search for the string.
+ printf("// SPDX" "-License-Identifier" ": 0BSD\n\n"
+ "// This file has been generated by price_tablegen.c.\n\n"
+ "#include \"range_encoder.h\"\n\n"
+ "const uint8_t lzma_rc_prices["
+ "RC_PRICE_TABLE_SIZE] = {");
const size_t array_size = sizeof(lzma_rc_prices)
/ sizeof(lzma_rc_prices[0]);
diff --git a/src/liblzma/rangecoder/range_common.h b/src/liblzma/rangecoder/range_common.h
index 2c74dc1..ac4dbe1 100644
--- a/src/liblzma/rangecoder/range_common.h
+++ b/src/liblzma/rangecoder/range_common.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file range_common.h
@@ -6,15 +8,15 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_RANGE_COMMON_H
#define LZMA_RANGE_COMMON_H
-#include "common.h"
+// Skip common.h if building price_tablegen.c.
+#ifndef BUILDING_PRICE_TABLEGEN
+# include "common.h"
+#endif
///////////////
@@ -66,6 +68,10 @@
///
/// I will be sticking to uint16_t unless some specific architectures
/// are *much* faster (20-50 %) with uint32_t.
+///
+/// Update in 2024: The branchless C and x86-64 assembly was written so that
+/// probability is assumed to be uint16_t. (In contrast, LZMA SDK 23.01
+/// assembly supports both types.)
typedef uint16_t probability;
#endif
diff --git a/src/liblzma/rangecoder/range_decoder.h b/src/liblzma/rangecoder/range_decoder.h
index e0b051f..31a58d1 100644
--- a/src/liblzma/rangecoder/range_decoder.h
+++ b/src/liblzma/rangecoder/range_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file range_decoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_RANGE_DECODER_H
@@ -17,6 +16,55 @@
#include "range_common.h"
+// Choose the range decoder variants to use using a bitmask.
+// If no bits are set, only the basic version is used.
+// If more than one version is selected for the same feature,
+// the last one on the list below is used.
+//
+// Bitwise-or of the following enable branchless C versions:
+// 0x01 normal bittrees
+// 0x02 fixed-sized reverse bittrees
+// 0x04 variable-sized reverse bittrees (not faster)
+// 0x08 matched literal (not faster)
+//
+// GCC & Clang compatible x86-64 inline assembly:
+// 0x010 normal bittrees
+// 0x020 fixed-sized reverse bittrees
+// 0x040 variable-sized reverse bittrees
+// 0x080 matched literal
+// 0x100 direct bits
+//
+// The default can be overridden at build time by defining
+// LZMA_RANGE_DECODER_CONFIG to the desired mask.
+//
+// 2024-02-22: Feedback from benchmarks:
+// - Brancless C (0x003) can be better than basic on x86-64 but often it's
+// slightly worse on other archs. Since asm is much better on x86-64,
+// branchless C is not used at all.
+// - With x86-64 asm, there are slight differences between GCC and Clang
+// 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
+# define LZMA_RANGE_DECODER_CONFIG 0
+# endif
+#endif
+
+
+// Negative RC_BIT_MODEL_TOTAL but the lowest RC_MOVE_BITS are flipped.
+// This is useful for updating probability variables in branchless decoding:
+//
+// uint32_t decoded_bit = ...;
+// probability tmp = RC_BIT_MODEL_OFFSET;
+// tmp &= decoded_bit - 1;
+// prob -= (prob + tmp) >> RC_MOVE_BITS;
+#define RC_BIT_MODEL_OFFSET \
+ ((UINT32_C(1) << RC_MOVE_BITS) - 1 - RC_BIT_MODEL_TOTAL)
+
+
typedef struct {
uint32_t range;
uint32_t code;
@@ -50,18 +98,28 @@ rc_read_init(lzma_range_decoder *rc, const uint8_t *restrict in,
/// Makes local copies of range decoder and *in_pos variables. Doing this
/// improves speed significantly. The range decoder macros expect also
-/// variables `in' and `in_size' to be defined.
-#define rc_to_local(range_decoder, in_pos) \
+/// variables 'in' and 'in_size' to be defined.
+#define rc_to_local(range_decoder, in_pos, fast_mode_in_required) \
lzma_range_decoder rc = range_decoder; \
- size_t rc_in_pos = (in_pos); \
+ const uint8_t *rc_in_ptr = in + (in_pos); \
+ const uint8_t *rc_in_end = in + in_size; \
+ const uint8_t *rc_in_fast_end \
+ = (rc_in_end - rc_in_ptr) <= (fast_mode_in_required) \
+ ? rc_in_ptr \
+ : rc_in_end - (fast_mode_in_required); \
+ (void)rc_in_fast_end; /* Silence a warning with HAVE_SMALL. */ \
uint32_t rc_bound
+/// Evaluates to true if there is enough input remaining to use fast mode.
+#define rc_is_fast_allowed() (rc_in_ptr < rc_in_fast_end)
+
+
/// Stores the local copes back to the range decoder structure.
#define rc_from_local(range_decoder, in_pos) \
do { \
range_decoder = rc; \
- in_pos = rc_in_pos; \
+ in_pos = (size_t)(rc_in_ptr - in); \
} while (0)
@@ -81,18 +139,30 @@ do { \
((range_decoder).code == 0)
-/// Read the next input byte if needed. If more input is needed but there is
+// Read the next input byte if needed.
+#define rc_normalize() \
+do { \
+ if (rc.range < RC_TOP_VALUE) { \
+ rc.range <<= RC_SHIFT_BITS; \
+ rc.code = (rc.code << RC_SHIFT_BITS) | *rc_in_ptr++; \
+ } \
+} while (0)
+
+
+/// If more input is needed but there is
/// no more input available, "goto out" is used to jump out of the main
-/// decoder loop.
-#define rc_normalize(seq) \
+/// decoder loop. The "_safe" macros are used in the Resumable decoder
+/// mode in order to save the sequence to continue decoding from that
+/// point later.
+#define rc_normalize_safe(seq) \
do { \
if (rc.range < RC_TOP_VALUE) { \
- if (unlikely(rc_in_pos == in_size)) { \
+ if (rc_in_ptr == rc_in_end) { \
coder->sequence = seq; \
goto out; \
} \
rc.range <<= RC_SHIFT_BITS; \
- rc.code = (rc.code << RC_SHIFT_BITS) | in[rc_in_pos++]; \
+ rc.code = (rc.code << RC_SHIFT_BITS) | *rc_in_ptr++; \
} \
} while (0)
@@ -100,7 +170,7 @@ do { \
/// Start decoding a bit. This must be used together with rc_update_0()
/// and rc_update_1():
///
-/// rc_if_0(prob, seq) {
+/// rc_if_0(prob) {
/// rc_update_0(prob);
/// // Do something
/// } else {
@@ -108,18 +178,28 @@ do { \
/// // Do something else
/// }
///
-#define rc_if_0(prob, seq) \
- rc_normalize(seq); \
+#define rc_if_0(prob) \
+ rc_normalize(); \
+ rc_bound = (rc.range >> RC_BIT_MODEL_TOTAL_BITS) * (prob); \
+ if (rc.code < rc_bound)
+
+
+#define rc_if_0_safe(prob, seq) \
+ rc_normalize_safe(seq); \
rc_bound = (rc.range >> RC_BIT_MODEL_TOTAL_BITS) * (prob); \
if (rc.code < rc_bound)
/// Update the range decoder state and the used probability variable to
/// match a decoded bit of 0.
+///
+/// The x86-64 assembly uses the commented method but it seems that,
+/// at least on x86-64, the first version is slightly faster as C code.
#define rc_update_0(prob) \
do { \
rc.range = rc_bound; \
prob += (RC_BIT_MODEL_TOTAL - (prob)) >> RC_MOVE_BITS; \
+ /* prob -= ((prob) + RC_BIT_MODEL_OFFSET) >> RC_MOVE_BITS; */ \
} while (0)
@@ -137,9 +217,21 @@ do { \
/// This macro is used as the last step in bittree reverse decoders since
/// those don't use "symbol" for anything else than indexing the probability
/// arrays.
-#define rc_bit_last(prob, action0, action1, seq) \
+#define rc_bit_last(prob, action0, action1) \
+do { \
+ rc_if_0(prob) { \
+ rc_update_0(prob); \
+ action0; \
+ } else { \
+ rc_update_1(prob); \
+ action1; \
+ } \
+} while (0)
+
+
+#define rc_bit_last_safe(prob, action0, action1, seq) \
do { \
- rc_if_0(prob, seq) { \
+ rc_if_0_safe(prob, seq) { \
rc_update_0(prob); \
action0; \
} else { \
@@ -151,35 +243,724 @@ do { \
/// Decodes one bit, updates "symbol", and runs action0 or action1 depending
/// on the decoded bit.
-#define rc_bit(prob, action0, action1, seq) \
+#define rc_bit(prob, action0, action1) \
rc_bit_last(prob, \
symbol <<= 1; action0, \
+ symbol = (symbol << 1) + 1; action1);
+
+
+#define rc_bit_safe(prob, action0, action1, seq) \
+ rc_bit_last_safe(prob, \
+ symbol <<= 1; action0, \
symbol = (symbol << 1) + 1; action1, \
seq);
+// Unroll fixed-sized bittree decoding.
+//
+// A compile-time constant in final_add can be used to get rid of the high bit
+// from symbol that is used for the array indexing (1U << bittree_bits).
+// final_add may also be used to add offset to the result (LZMA length
+// decoder does that).
+//
+// The reason to have final_add here is that in the asm code the addition
+// can be done for free: in x86-64 there is SBB instruction with -1 as
+// the immediate value, and final_add is combined with that value.
+#define rc_bittree_bit(prob) \
+ rc_bit(prob, , )
+
+#define rc_bittree3(probs, final_add) \
+do { \
+ symbol = 1; \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ symbol += (uint32_t)(final_add); \
+} while (0)
-/// Like rc_bit() but add "case seq:" as a prefix. This makes the unrolled
-/// loops more readable because the code isn't littered with "case"
-/// statements. On the other hand this also makes it less readable, since
-/// spotting the places where the decoder loop may be restarted is less
-/// obvious.
-#define rc_bit_case(prob, action0, action1, seq) \
- case seq: rc_bit(prob, action0, action1, seq)
+#define rc_bittree6(probs, final_add) \
+do { \
+ symbol = 1; \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ symbol += (uint32_t)(final_add); \
+} while (0)
+
+#define rc_bittree8(probs, final_add) \
+do { \
+ symbol = 1; \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ rc_bittree_bit(probs[symbol]); \
+ symbol += (uint32_t)(final_add); \
+} while (0)
+
+
+// Fixed-sized reverse bittree
+#define rc_bittree_rev4(probs) \
+do { \
+ symbol = 0; \
+ rc_bit_last(probs[symbol + 1], , symbol += 1); \
+ rc_bit_last(probs[symbol + 2], , symbol += 2); \
+ rc_bit_last(probs[symbol + 4], , symbol += 4); \
+ rc_bit_last(probs[symbol + 8], , symbol += 8); \
+} while (0)
+
+
+// Decode one bit from variable-sized reverse bittree. The loop is done
+// in the code that uses this macro. This could be changed if the assembly
+// version benefited from having the loop done in assembly but it didn't
+// seem so in early 2024.
+//
+// Also, if the loop was done here, the loop counter would likely be local
+// to the macro so that it wouldn't modify yet another input variable.
+// If a _safe version of a macro with a loop was done then a modifiable
+// input variable couldn't be avoided though.
+#define rc_bit_add_if_1(probs, dest, value_to_add_if_1) \
+ rc_bit(probs[symbol], \
+ , \
+ dest += value_to_add_if_1);
+
+
+// Matched literal
+#define decode_with_match_bit \
+ t_match_byte <<= 1; \
+ t_match_bit = t_match_byte & t_offset; \
+ t_subcoder_index = t_offset + t_match_bit + symbol; \
+ rc_bit(probs[t_subcoder_index], \
+ t_offset &= ~t_match_bit, \
+ t_offset &= t_match_bit)
+
+#define rc_matched_literal(probs_base_var, match_byte) \
+do { \
+ uint32_t t_match_byte = (match_byte); \
+ uint32_t t_match_bit; \
+ uint32_t t_subcoder_index; \
+ uint32_t t_offset = 0x100; \
+ symbol = 1; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+ decode_with_match_bit; \
+} while (0)
/// Decode a bit without using a probability.
-#define rc_direct(dest, seq) \
+//
+// NOTE: GCC 13 and Clang/LLVM 16 can, at least on x86-64, optimize the bound
+// calculation to use an arithmetic right shift so there's no need to provide
+// the alternative code which, according to C99/C11/C23 6.3.1.3-p3 isn't
+// perfectly portable: rc_bound = (uint32_t)((int32_t)rc.code >> 31);
+#define rc_direct(dest, count_var) \
do { \
- rc_normalize(seq); \
+ dest = (dest << 1) + 1; \
+ rc_normalize(); \
+ rc.range >>= 1; \
+ rc.code -= rc.range; \
+ rc_bound = UINT32_C(0) - (rc.code >> 31); \
+ dest += rc_bound; \
+ rc.code += rc.range & rc_bound; \
+} while (--count_var > 0)
+
+
+
+#define rc_direct_safe(dest, count_var, seq) \
+do { \
+ rc_normalize_safe(seq); \
rc.range >>= 1; \
rc.code -= rc.range; \
rc_bound = UINT32_C(0) - (rc.code >> 31); \
rc.code += rc.range & rc_bound; \
dest = (dest << 1) + (rc_bound + 1); \
+} while (--count_var > 0)
+
+
+//////////////////
+// Branchless C //
+//////////////////
+
+/// Decode a bit using a branchless method. This reduces the number of
+/// mispredicted branches and thus can improve speed.
+#define rc_c_bit(prob, action_bit, action_neg) \
+do { \
+ probability *p = &(prob); \
+ rc_normalize(); \
+ rc_bound = (rc.range >> RC_BIT_MODEL_TOTAL_BITS) * *p; \
+ uint32_t rc_mask = rc.code >= rc_bound; /* rc_mask = decoded bit */ \
+ action_bit; /* action when rc_mask is 0 or 1 */ \
+ /* rc_mask becomes 0 if bit is 0 and 0xFFFFFFFF if bit is 1: */ \
+ rc_mask = 0U - rc_mask; \
+ rc.range &= rc_mask; /* If bit 0: set rc.range = 0 */ \
+ rc_bound ^= rc_mask; \
+ rc_bound -= rc_mask; /* If bit 1: rc_bound = 0U - rc_bound */ \
+ rc.range += rc_bound; \
+ rc_bound &= rc_mask; \
+ rc.code += rc_bound; \
+ action_neg; /* action when rc_mask is 0 or 0xFFFFFFFF */ \
+ rc_mask = ~rc_mask; /* If bit 0: all bits are set in rc_mask */ \
+ rc_mask &= RC_BIT_MODEL_OFFSET; \
+ *p -= (*p + rc_mask) >> RC_MOVE_BITS; \
} while (0)
-// NOTE: No macros are provided for bittree decoding. It seems to be simpler
-// to just write them open in the code.
+// Testing on x86-64 give an impression that only the normal bittrees and
+// the fixed-sized reverse bittrees are worth the branchless C code.
+// It should be tested on other archs for which there isn't assembly code
+// in this file.
+
+// Using addition in "(symbol << 1) + rc_mask" allows use of x86 LEA
+// or RISC-V SH1ADD instructions. Compilers might infer it from
+// "(symbol << 1) | rc_mask" too if they see that mask is 0 or 1 but
+// the use of addition doesn't require such analysis from compilers.
+#if LZMA_RANGE_DECODER_CONFIG & 0x01
+#undef rc_bittree_bit
+#define rc_bittree_bit(prob) \
+ rc_c_bit(prob, \
+ symbol = (symbol << 1) + rc_mask, \
+ )
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x01
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x02
+#undef rc_bittree_rev4
+#define rc_bittree_rev4(probs) \
+do { \
+ symbol = 0; \
+ rc_c_bit(probs[symbol + 1], symbol += rc_mask, ); \
+ rc_c_bit(probs[symbol + 2], symbol += rc_mask << 1, ); \
+ rc_c_bit(probs[symbol + 4], symbol += rc_mask << 2, ); \
+ rc_c_bit(probs[symbol + 8], symbol += rc_mask << 3, ); \
+} while (0)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x02
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x04
+#undef rc_bit_add_if_1
+#define rc_bit_add_if_1(probs, dest, value_to_add_if_1) \
+ rc_c_bit(probs[symbol], \
+ symbol = (symbol << 1) + rc_mask, \
+ dest += (value_to_add_if_1) & rc_mask)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x04
+
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x08
+#undef decode_with_match_bit
+#define decode_with_match_bit \
+ t_match_byte <<= 1; \
+ t_match_bit = t_match_byte & t_offset; \
+ t_subcoder_index = t_offset + t_match_bit + symbol; \
+ rc_c_bit(probs[t_subcoder_index], \
+ symbol = (symbol << 1) + rc_mask, \
+ t_offset &= ~t_match_bit ^ rc_mask)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x08
+
+
+////////////
+// x86-64 //
+////////////
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x1F0
+
+// rc_asm_y and rc_asm_n are used as arguments to macros to control which
+// strings to include or omit.
+#define rc_asm_y(str) str
+#define rc_asm_n(str)
+
+// There are a few possible variations for normalization.
+// This is the smallest variant which is also used by LZMA SDK.
+//
+// - This has partial register write (the MOV from (%[in_ptr])).
+//
+// - INC saves one byte in code size over ADD. False dependency on
+// partial flags from INC shouldn't become a problem on any processor
+// because the instructions after normalization don't read the flags
+// until SUB which sets all flags.
+//
+#define rc_asm_normalize \
+ "cmp %[top_value], %[range]\n\t" \
+ "jae 1f\n\t" \
+ "shl %[shift_bits], %[code]\n\t" \
+ "mov (%[in_ptr]), %b[code]\n\t" \
+ "shl %[shift_bits], %[range]\n\t" \
+ "inc %[in_ptr]\n" \
+ "1:\n"
+
+// rc_asm_calc(prob) is roughly equivalent to the C version of rc_if_0(prob)...
+//
+// rc_bound = (rc.range >> RC_BIT_MODEL_TOTAL_BITS) * (prob);
+// if (rc.code < rc_bound)
+//
+// ...but the bound is stored in "range":
+//
+// t0 = range;
+// range = (range >> RC_BIT_MODEL_TOTAL_BITS) * (prob);
+// t0 -= range;
+// t1 = code;
+// code -= range;
+//
+// The carry flag (CF) from the last subtraction holds the negation of
+// the decoded bit (if CF==0 then the decoded bit is 1).
+// The values in t0 and t1 are needed for rc_update_0(prob) and
+// rc_update_1(prob). If the bit is 0, rc_update_0(prob)...
+//
+// rc.range = rc_bound;
+//
+// ...has already been done but the "code -= range" has to be reverted using
+// the old value stored in t1. (Also, prob needs to be updated.)
+//
+// If the bit is 1, rc_update_1(prob)...
+//
+// rc.range -= rc_bound;
+// rc.code -= rc_bound;
+//
+// ...is already done for "code" but the value for "range" needs to be taken
+// from t0. (Also, prob needs to be updated here as well.)
+//
+// The assignments from t0 and t1 can be done in a branchless manner with CMOV
+// after the instructions from this macro. The CF from SUB tells which moves
+// are needed.
+#define rc_asm_calc(prob) \
+ "mov %[range], %[t0]\n\t" \
+ "shr %[bit_model_total_bits], %[range]\n\t" \
+ "imul %[" prob "], %[range]\n\t" \
+ "sub %[range], %[t0]\n\t" \
+ "mov %[code], %[t1]\n\t" \
+ "sub %[range], %[code]\n\t"
+
+// Also, prob needs to be updated: The update math depends on the decoded bit.
+// It can be expressed in a few slightly different ways but this is fairly
+// convenient here:
+//
+// prob -= (prob + (bit ? 0 : RC_BIT_MODEL_OFFSET)) >> RC_MOVE_BITS;
+//
+// To do it in branchless way when the negation of the decoded bit is in CF,
+// both "prob" and "prob + RC_BIT_MODEL_OFFSET" are needed. Then the desired
+// value can be picked with CMOV. The addition can be done using LEA without
+// affecting CF.
+//
+// (This prob update method is a tiny bit different from LZMA SDK 23.01.
+// In the LZMA SDK a single register is reserved solely for a constant to
+// be used with CMOV when updating prob. That is fine since there are enough
+// free registers to do so. The method used here uses one fewer register,
+// which is valuable with inline assembly.)
+//
+// * * *
+//
+// In bittree decoding, each (unrolled) loop iteration decodes one bit
+// and needs one prob variable. To make it faster, the prob variable of
+// the iteration N+1 is loaded during iteration N. There are two possible
+// prob variables to choose from for N+1. Both are loaded from memory and
+// the correct one is chosen with CMOV using the same CF as is used for
+// other things described above.
+//
+// This preloading/prefetching requires an extra register. To avoid
+// useless moves from "preloaded prob register" to "current prob register",
+// the macros swap between the two registers for odd and even iterations.
+//
+// * * *
+//
+// Finally, the decoded bit has to be stored in "symbol". Since the negation
+// of the bit is in CF, this can be done with SBB: symbol -= CF - 1. That is,
+// if the decoded bit is 0 (CF==1) the operation is a no-op "symbol -= 0"
+// and when bit is 1 (CF==0) the operation is "symbol -= 0 - 1" which is
+// the same as "symbol += 1".
+//
+// The instructions for all things are intertwined for a few reasons:
+// - freeing temporary registers for new use
+// - not modifying CF too early
+// - instruction scheduling
+//
+// The first and last iterations can cheat a little. For example,
+// on the first iteration "symbol" is known to start from 1 so it
+// doesn't need to be read; it can even be immediately initialized
+// to 2 to prepare for the second iteration of the loop.
+//
+// * * *
+//
+// a = number of the current prob variable (0 or 1)
+// b = number of the next prob variable (1 or 0)
+// *_only = rc_asm_y or _n to include or exclude code marked with them
+#define rc_asm_bittree(a, b, first_only, middle_only, last_only) \
+ first_only( \
+ "movzw 2(%[probs_base]), %[prob" #a "]\n\t" \
+ "mov $2, %[symbol]\n\t" \
+ "movzw 4(%[probs_base]), %[prob" #b "]\n\t" \
+ ) \
+ middle_only( \
+ /* Note the scaling of 4 instead of 2: */ \
+ "movzw (%[probs_base], %q[symbol], 4), %[prob" #b "]\n\t" \
+ ) \
+ last_only( \
+ "add %[symbol], %[symbol]\n\t" \
+ ) \
+ \
+ rc_asm_normalize \
+ rc_asm_calc("prob" #a) \
+ \
+ "cmovae %[t0], %[range]\n\t" \
+ \
+ first_only( \
+ "movzw 6(%[probs_base]), %[t0]\n\t" \
+ "cmovae %[t0], %[prob" #b "]\n\t" \
+ ) \
+ middle_only( \
+ "movzw 2(%[probs_base], %q[symbol], 4), %[t0]\n\t" \
+ "lea (%q[symbol], %q[symbol]), %[symbol]\n\t" \
+ "cmovae %[t0], %[prob" #b "]\n\t" \
+ ) \
+ \
+ "lea %c[bit_model_offset](%q[prob" #a "]), %[t0]\n\t" \
+ "cmovb %[t1], %[code]\n\t" \
+ "mov %[symbol], %[t1]\n\t" \
+ "cmovae %[prob" #a "], %[t0]\n\t" \
+ \
+ first_only( \
+ "sbb $-1, %[symbol]\n\t" \
+ ) \
+ middle_only( \
+ "sbb $-1, %[symbol]\n\t" \
+ ) \
+ last_only( \
+ "sbb %[last_sbb], %[symbol]\n\t" \
+ ) \
+ \
+ "shr %[move_bits], %[t0]\n\t" \
+ "sub %[t0], %[prob" #a "]\n\t" \
+ /* Scaling of 1 instead of 2 because symbol <<= 1. */ \
+ "mov %w[prob" #a "], (%[probs_base], %q[t1], 1)\n\t"
+
+// NOTE: The order of variables in __asm__ can affect speed and code size.
+#define rc_asm_bittree_n(probs_base_var, final_add, asm_str) \
+do { \
+ uint32_t t0; \
+ uint32_t t1; \
+ uint32_t t_prob0; \
+ uint32_t t_prob1; \
+ \
+ __asm__( \
+ asm_str \
+ : \
+ [range] "+&r"(rc.range), \
+ [code] "+&r"(rc.code), \
+ [t0] "=&r"(t0), \
+ [t1] "=&r"(t1), \
+ [prob0] "=&r"(t_prob0), \
+ [prob1] "=&r"(t_prob1), \
+ [symbol] "=&r"(symbol), \
+ [in_ptr] "+&r"(rc_in_ptr) \
+ : \
+ [probs_base] "r"(probs_base_var), \
+ [last_sbb] "n"(-1 - (final_add)), \
+ [top_value] "n"(RC_TOP_VALUE), \
+ [shift_bits] "n"(RC_SHIFT_BITS), \
+ [bit_model_total_bits] "n"(RC_BIT_MODEL_TOTAL_BITS), \
+ [bit_model_offset] "n"(RC_BIT_MODEL_OFFSET), \
+ [move_bits] "n"(RC_MOVE_BITS) \
+ : \
+ "cc", "memory"); \
+} while (0)
+
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x010
+#undef rc_bittree3
+#define rc_bittree3(probs_base_var, final_add) \
+ rc_asm_bittree_n(probs_base_var, final_add, \
+ rc_asm_bittree(0, 1, rc_asm_y, rc_asm_n, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_n, rc_asm_y) \
+ )
+
+#undef rc_bittree6
+#define rc_bittree6(probs_base_var, final_add) \
+ rc_asm_bittree_n(probs_base_var, final_add, \
+ rc_asm_bittree(0, 1, rc_asm_y, rc_asm_n, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_n, rc_asm_y) \
+ )
+
+#undef rc_bittree8
+#define rc_bittree8(probs_base_var, final_add) \
+ rc_asm_bittree_n(probs_base_var, final_add, \
+ rc_asm_bittree(0, 1, rc_asm_y, rc_asm_n, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(0, 1, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree(1, 0, rc_asm_n, rc_asm_n, rc_asm_y) \
+ )
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x010
+
+
+// Fixed-sized reverse bittree
+//
+// This uses the indexing that constructs the final value in symbol directly.
+// add = 1, 2, 4, 8
+// dcur = -, 4, 8, 16
+// dnext0 = 4, 8, 16, -
+// dnext0 = 6, 12, 24, -
+#define rc_asm_bittree_rev(a, b, add, dcur, dnext0, dnext1, \
+ first_only, middle_only, last_only) \
+ first_only( \
+ "movzw 2(%[probs_base]), %[prob" #a "]\n\t" \
+ "xor %[symbol], %[symbol]\n\t" \
+ "movzw 4(%[probs_base]), %[prob" #b "]\n\t" \
+ ) \
+ middle_only( \
+ "movzw " #dnext0 "(%[probs_base], %q[symbol], 2), " \
+ "%[prob" #b "]\n\t" \
+ ) \
+ \
+ rc_asm_normalize \
+ rc_asm_calc("prob" #a) \
+ \
+ "cmovae %[t0], %[range]\n\t" \
+ \
+ first_only( \
+ "movzw 6(%[probs_base]), %[t0]\n\t" \
+ "cmovae %[t0], %[prob" #b "]\n\t" \
+ ) \
+ middle_only( \
+ "movzw " #dnext1 "(%[probs_base], %q[symbol], 2), %[t0]\n\t" \
+ "cmovae %[t0], %[prob" #b "]\n\t" \
+ ) \
+ \
+ "lea " #add "(%q[symbol]), %[t0]\n\t" \
+ "cmovb %[t1], %[code]\n\t" \
+ middle_only( \
+ "mov %[symbol], %[t1]\n\t" \
+ ) \
+ last_only( \
+ "mov %[symbol], %[t1]\n\t" \
+ ) \
+ "cmovae %[t0], %[symbol]\n\t" \
+ "lea %c[bit_model_offset](%q[prob" #a "]), %[t0]\n\t" \
+ "cmovae %[prob" #a "], %[t0]\n\t" \
+ \
+ "shr %[move_bits], %[t0]\n\t" \
+ "sub %[t0], %[prob" #a "]\n\t" \
+ first_only( \
+ "mov %w[prob" #a "], 2(%[probs_base])\n\t" \
+ ) \
+ middle_only( \
+ "mov %w[prob" #a "], " \
+ #dcur "(%[probs_base], %q[t1], 2)\n\t" \
+ ) \
+ last_only( \
+ "mov %w[prob" #a "], " \
+ #dcur "(%[probs_base], %q[t1], 2)\n\t" \
+ )
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x020
+#undef rc_bittree_rev4
+#define rc_bittree_rev4(probs_base_var) \
+rc_asm_bittree_n(probs_base_var, 4, \
+ rc_asm_bittree_rev(0, 1, 1, -, 4, 6, rc_asm_y, rc_asm_n, rc_asm_n) \
+ rc_asm_bittree_rev(1, 0, 2, 4, 8, 12, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree_rev(0, 1, 4, 8, 16, 24, rc_asm_n, rc_asm_y, rc_asm_n) \
+ rc_asm_bittree_rev(1, 0, 8, 16, -, -, rc_asm_n, rc_asm_n, rc_asm_y) \
+)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x020
+
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x040
+#undef rc_bit_add_if_1
+#define rc_bit_add_if_1(probs_base_var, dest_var, value_to_add_if_1) \
+do { \
+ uint32_t t0; \
+ uint32_t t1; \
+ uint32_t t2 = (value_to_add_if_1); \
+ uint32_t t_prob; \
+ uint32_t t_index; \
+ \
+ __asm__( \
+ "movzw (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
+ "mov %[symbol], %[index]\n\t" \
+ \
+ "add %[dest], %[t2]\n\t" \
+ "add %[symbol], %[symbol]\n\t" \
+ \
+ rc_asm_normalize \
+ rc_asm_calc("prob") \
+ \
+ "cmovae %[t0], %[range]\n\t" \
+ "lea %c[bit_model_offset](%q[prob]), %[t0]\n\t" \
+ "cmovb %[t1], %[code]\n\t" \
+ "cmovae %[prob], %[t0]\n\t" \
+ \
+ "cmovae %[t2], %[dest]\n\t" \
+ "sbb $-1, %[symbol]\n\t" \
+ \
+ "sar %[move_bits], %[t0]\n\t" \
+ "sub %[t0], %[prob]\n\t" \
+ "mov %w[prob], (%[probs_base], %q[index], 2)" \
+ : \
+ [range] "+&r"(rc.range), \
+ [code] "+&r"(rc.code), \
+ [t0] "=&r"(t0), \
+ [t1] "=&r"(t1), \
+ [prob] "=&r"(t_prob), \
+ [index] "=&r"(t_index), \
+ [symbol] "+&r"(symbol), \
+ [t2] "+&r"(t2), \
+ [dest] "+&r"(dest_var), \
+ [in_ptr] "+&r"(rc_in_ptr) \
+ : \
+ [probs_base] "r"(probs_base_var), \
+ [top_value] "n"(RC_TOP_VALUE), \
+ [shift_bits] "n"(RC_SHIFT_BITS), \
+ [bit_model_total_bits] "n"(RC_BIT_MODEL_TOTAL_BITS), \
+ [bit_model_offset] "n"(RC_BIT_MODEL_OFFSET), \
+ [move_bits] "n"(RC_MOVE_BITS) \
+ : \
+ "cc", "memory"); \
+} while (0)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x040
+
+
+// Literal decoding uses a normal 8-bit bittree but literal with match byte
+// is more complex in picking the probability variable from the correct
+// subtree. This doesn't use preloading/prefetching of the next prob because
+// there are four choices instead of two.
+//
+// FIXME? The first iteration starts with symbol = 1 so it could be optimized
+// by a tiny amount.
+#define rc_asm_matched_literal(nonlast_only) \
+ "add %[offset], %[symbol]\n\t" \
+ "and %[offset], %[match_bit]\n\t" \
+ "add %[match_bit], %[symbol]\n\t" \
+ \
+ "movzw (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
+ \
+ "add %[symbol], %[symbol]\n\t" \
+ \
+ nonlast_only( \
+ "xor %[match_bit], %[offset]\n\t" \
+ "add %[match_byte], %[match_byte]\n\t" \
+ ) \
+ \
+ rc_asm_normalize \
+ rc_asm_calc("prob") \
+ \
+ "cmovae %[t0], %[range]\n\t" \
+ "lea %c[bit_model_offset](%q[prob]), %[t0]\n\t" \
+ "cmovb %[t1], %[code]\n\t" \
+ "mov %[symbol], %[t1]\n\t" \
+ "cmovae %[prob], %[t0]\n\t" \
+ \
+ nonlast_only( \
+ "cmovae %[match_bit], %[offset]\n\t" \
+ "mov %[match_byte], %[match_bit]\n\t" \
+ ) \
+ \
+ "sbb $-1, %[symbol]\n\t" \
+ \
+ "shr %[move_bits], %[t0]\n\t" \
+ /* Undo symbol += match_bit + offset: */ \
+ "and $0x1FF, %[symbol]\n\t" \
+ "sub %[t0], %[prob]\n\t" \
+ \
+ /* Scaling of 1 instead of 2 because symbol <<= 1. */ \
+ "mov %w[prob], (%[probs_base], %q[t1], 1)\n\t"
+
+
+#if LZMA_RANGE_DECODER_CONFIG & 0x080
+#undef rc_matched_literal
+#define rc_matched_literal(probs_base_var, match_byte_value) \
+do { \
+ uint32_t t0; \
+ uint32_t t1; \
+ uint32_t t_prob; \
+ uint32_t t_match_byte = (uint32_t)(match_byte_value) << 1; \
+ uint32_t t_match_bit = t_match_byte; \
+ uint32_t t_offset = 0x100; \
+ symbol = 1; \
+ \
+ __asm__( \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_y) \
+ rc_asm_matched_literal(rc_asm_n) \
+ : \
+ [range] "+&r"(rc.range), \
+ [code] "+&r"(rc.code), \
+ [t0] "=&r"(t0), \
+ [t1] "=&r"(t1), \
+ [prob] "=&r"(t_prob), \
+ [match_bit] "+&r"(t_match_bit), \
+ [symbol] "+&r"(symbol), \
+ [match_byte] "+&r"(t_match_byte), \
+ [offset] "+&r"(t_offset), \
+ [in_ptr] "+&r"(rc_in_ptr) \
+ : \
+ [probs_base] "r"(probs_base_var), \
+ [top_value] "n"(RC_TOP_VALUE), \
+ [shift_bits] "n"(RC_SHIFT_BITS), \
+ [bit_model_total_bits] "n"(RC_BIT_MODEL_TOTAL_BITS), \
+ [bit_model_offset] "n"(RC_BIT_MODEL_OFFSET), \
+ [move_bits] "n"(RC_MOVE_BITS) \
+ : \
+ "cc", "memory"); \
+} while (0)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x080
+
+
+// Doing the loop in asm instead of C seems to help a little.
+#if LZMA_RANGE_DECODER_CONFIG & 0x100
+#undef rc_direct
+#define rc_direct(dest_var, count_var) \
+do { \
+ uint32_t t0; \
+ uint32_t t1; \
+ \
+ __asm__( \
+ "2:\n\t" \
+ "add %[dest], %[dest]\n\t" \
+ "lea 1(%q[dest]), %[t1]\n\t" \
+ \
+ rc_asm_normalize \
+ \
+ "shr $1, %[range]\n\t" \
+ "mov %[code], %[t0]\n\t" \
+ "sub %[range], %[code]\n\t" \
+ "cmovns %[t1], %[dest]\n\t" \
+ "cmovs %[t0], %[code]\n\t" \
+ "dec %[count]\n\t" \
+ "jnz 2b\n\t" \
+ : \
+ [range] "+&r"(rc.range), \
+ [code] "+&r"(rc.code), \
+ [t0] "=&r"(t0), \
+ [t1] "=&r"(t1), \
+ [dest] "+&r"(dest_var), \
+ [count] "+&r"(count_var), \
+ [in_ptr] "+&r"(rc_in_ptr) \
+ : \
+ [top_value] "n"(RC_TOP_VALUE), \
+ [shift_bits] "n"(RC_SHIFT_BITS) \
+ : \
+ "cc", "memory"); \
+} while (0)
+#endif // LZMA_RANGE_DECODER_CONFIG & 0x100
+
+#endif // x86_64
#endif
diff --git a/src/liblzma/rangecoder/range_encoder.h b/src/liblzma/rangecoder/range_encoder.h
index d794eab..8f62a47 100644
--- a/src/liblzma/rangecoder/range_encoder.h
+++ b/src/liblzma/rangecoder/range_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file range_encoder.h
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_RANGE_ENCODER_H
diff --git a/src/liblzma/simple/Makefile.inc b/src/liblzma/simple/Makefile.inc
index dc092f9..f42ad1b 100644
--- a/src/liblzma/simple/Makefile.inc
+++ b/src/liblzma/simple/Makefile.inc
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
liblzma_la_SOURCES += \
simple/simple_coder.c \
@@ -49,3 +45,7 @@ endif
if COND_FILTER_SPARC
liblzma_la_SOURCES += simple/sparc.c
endif
+
+if COND_FILTER_RISCV
+liblzma_la_SOURCES += simple/riscv.c
+endif
diff --git a/src/liblzma/simple/arm.c b/src/liblzma/simple/arm.c
index 6e53970..58acb2d 100644
--- a/src/liblzma/simple/arm.c
+++ b/src/liblzma/simple/arm.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file arm.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/arm64.c b/src/liblzma/simple/arm64.c
index 0fe0824..0a73f6c 100644
--- a/src/liblzma/simple/arm64.c
+++ b/src/liblzma/simple/arm64.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file arm64.c
@@ -16,9 +18,6 @@
// Jia Tan
// Igor Pavlov
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/armthumb.c b/src/liblzma/simple/armthumb.c
index 25d8dbd..f1eeca9 100644
--- a/src/liblzma/simple/armthumb.c
+++ b/src/liblzma/simple/armthumb.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file armthumb.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/ia64.c b/src/liblzma/simple/ia64.c
index 692b0a2..5025014 100644
--- a/src/liblzma/simple/ia64.c
+++ b/src/liblzma/simple/ia64.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file ia64.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/powerpc.c b/src/liblzma/simple/powerpc.c
index 3a340fd..ba6cfbe 100644
--- a/src/liblzma/simple/powerpc.c
+++ b/src/liblzma/simple/powerpc.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file powerpc.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/riscv.c b/src/liblzma/simple/riscv.c
new file mode 100644
index 0000000..b18df8b
--- /dev/null
+++ b/src/liblzma/simple/riscv.c
@@ -0,0 +1,755 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file riscv.c
+/// \brief Filter for 32-bit/64-bit little/big endian RISC-V binaries
+///
+/// This converts program counter relative addresses in function calls
+/// (JAL, AUIPC+JALR), address calculation of functions and global
+/// variables (AUIPC+ADDI), loads (AUIPC+load), and stores (AUIPC+store).
+///
+/// For AUIPC+inst2 pairs, the paired instruction checking is fairly relaxed.
+/// The paired instruction opcode must only have its lowest two bits set,
+/// meaning it will convert any paired instruction that is not a 16-bit
+/// compressed instruction. This was shown to be enough to keep the number
+/// of false matches low while improving code size and speed.
+//
+// Authors: Lasse Collin
+// Jia Tan
+//
+// Special thanks:
+//
+// - Chien Wong <m@xv97.com> provided a few early versions of RISC-V
+// filter variants along with test files and benchmark results.
+//
+// - Igor Pavlov helped a lot in the filter design, getting it both
+// faster and smaller. The implementation here is still independently
+// written, not based on LZMA SDK.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+/*
+
+RISC-V filtering
+================
+
+ RV32I and RV64I, possibly combined with extensions C, Zfh, F, D,
+ and Q, are identical enough that the same filter works for both.
+
+ The instruction encoding is always little endian, even on systems
+ with big endian data access. Thus the same filter works for both
+ endiannesses.
+
+ The following instructions have program counter relative
+ (pc-relative) behavior:
+
+JAL
+---
+
+ JAL is used for function calls (including tail calls) and
+ unconditional jumps within functions. Jumps within functions
+ aren't useful to filter because the absolute addresses often
+ appear only once or at most a few times. Tail calls and jumps
+ within functions look the same to a simple filter so neither
+ are filtered, that is, JAL x0 is ignored (the ABI name of the
+ register x0 is "zero").
+
+ Almost all calls store the return address to register x1 (ra)
+ or x5 (t0). To reduce false matches when the filter is applied
+ to non-code data, only the JAL instructions that use x1 or x5
+ are converted. JAL has pc-relative range of +/-1 MiB so longer
+ calls and jumps need another method (AUIPC+JALR).
+
+C.J and C.JAL
+-------------
+
+ C.J and C.JAL have pc-relative range of +/-2 KiB.
+
+ C.J is for tail calls and jumps within functions and isn't
+ filtered for the reasons mentioned for JAL x0.
+
+ C.JAL is an RV32C-only instruction. Its encoding overlaps with
+ RV64C-only C.ADDIW which is a common instruction. So if filtering
+ C.JAL was useful (it wasn't tested) then a separate filter would
+ be needed for RV32 and RV64. Also, false positives would be a
+ significant problem when the filter is applied to non-code data
+ because C.JAL needs only five bits to match. Thus, this filter
+ doesn't modify C.JAL instructions.
+
+BEQ, BNE, BLT, BGE, BLTU, BGEU, C.BEQZ, and C.BNEZ
+--------------------------------------------------
+
+ These are conditional branches with pc-relative range
+ of +/-4 KiB (+/-256 B for C.*). The absolute addresses often
+ appear only once and very short distances are the most common,
+ so filtering these instructions would make compression worse.
+
+AUIPC with rd != x0
+-------------------
+
+ AUIPC is paired with a second instruction (inst2) to do
+ pc-relative jumps, calls, loads, stores, and for taking
+ an address of a symbol. AUIPC has a 20-bit immediate and
+ the possible inst2 choices have a 12-bit immediate.
+
+ AUIPC stores pc + 20-bit signed immediate to a register.
+ The immediate encodes a multiple of 4 KiB so AUIPC itself
+ has a pc-relative range of +/-2 GiB. AUIPC does *NOT* set
+ the lowest 12 bits of the result to zero! This means that
+ the 12-bit immediate in inst2 cannot just include the lowest
+ 12 bits of the absolute address as is; the immediate has to
+ compensate for the lowest 12 bits that AUIPC copies from the
+ program counter. This means that a good filter has to convert
+ not only AUIPC but also the paired inst2.
+
+ A strict filter would focus on filtering the following
+ AUIPC+inst2 pairs:
+
+ - AUIPC+JALR: Function calls, including tail calls.
+
+ - AUIPC+ADDI: Calculating the address of a function
+ or a global variable.
+
+ - AUIPC+load/store from the base instruction sets
+ (RV32I, RV64I) or from the floating point extensions
+ Zfh, F, D, and Q:
+ * RV32I: LB, LH, LW, LBU, LHU, SB, SH, SW
+ * RV64I has also: LD, LWU, SD
+ * Zfh: FLH, FSH
+ * F: FLW, FSW
+ * D: FLD, FSD
+ * Q: FLQ, FSQ
+
+ NOTE: AUIPC+inst2 can only be a pair if AUIPC's rd specifies
+ the same register as inst2's rs1.
+
+ Instead of strictly accepting only the above instructions as inst2,
+ this filter uses a much simpler condition: the lowest two bits of
+ inst2 must be set, that is, inst2 must not be a 16-bit compressed
+ instruction. So this will accept all 32-bit and possible future
+ extended instructions as a pair to AUIPC if the bits in AUIPC's
+ rd [11:7] match the bits [19:15] in inst2 (the bits that I-type and
+ S-type instructions use for rs1). Testing showed that this relaxed
+ condition for inst2 did not consistently or significantly affect
+ compression ratio but it reduced code size and improved speed.
+
+ Additionally, the paired instruction is always treated as an I-type
+ instruction. The S-type instructions used by stores (SB, SH, SW,
+ etc.) place the lowest 5 bits of the immediate in a different
+ location than I-type instructions. AUIPC+store pairs are less
+ common than other pairs, and testing showed that the extra
+ code required to handle S-type instructions was not worth the
+ compression ratio gained.
+
+ AUIPC+inst2 don't necessarily appear sequentially next to each
+ other although very often they do. Especially AUIPC+JALR are
+ sequential as that may allow instruction fusion in processors
+ (and perhaps help branch prediction as a fused AUIPC+JALR is
+ a direct branch while JALR alone is an indirect branch).
+
+ Clang 16 can generate code where AUIPC+inst2 is split:
+
+ - AUIPC is outside a loop and inst2 (load/store) is inside
+ the loop. This way the AUIPC instruction needs to be
+ executed only once.
+
+ - Load-modify-store may have AUIPC for the load and the same
+ AUIPC-result is used for the store too. This may get combined
+ with AUIPC being outside the loop.
+
+ - AUIPC is before a conditional branch and inst2 is hundreds
+ of bytes away at the branch target.
+
+ - Inner and outer pair:
+
+ auipc a1,0x2f
+ auipc a2,0x3d
+ ld a2,-500(a2)
+ addi a1,a1,-233
+
+ - Many split pairs with an untaken conditional branch between:
+
+ auipc s9,0x1613 # Pair 1
+ auipc s4,0x1613 # Pair 2
+ auipc s6,0x1613 # Pair 3
+ auipc s10,0x1613 # Pair 4
+ beqz a5,a3baae
+ ld a0,0(a6)
+ ld a6,246(s9) # Pair 1
+ ld a1,250(s4) # Pair 2
+ ld a3,254(s6) # Pair 3
+ ld a4,258(s10) # Pair 4
+
+ It's not possible to find all split pairs in a filter like this.
+ At least in 2024, simple sequential pairs are 99 % of AUIPC uses
+ so filtering only such pairs gives good results and makes the
+ filter simpler. However, it's possible that future compilers will
+ produce different code where sequential pairs aren't as common.
+
+ This filter doesn't convert AUIPC instructions alone because:
+
+ (1) The conversion would be off-by-one (or off-by-4096) half the
+ time because the lowest 12 bits from inst2 (inst2_imm12)
+ aren't known. We only know that the absolute address is
+ pc + AUIPC_imm20 + [-2048, +2047] but there is no way to
+ know the exact 4096-byte multiple (or 4096 * n + 2048):
+ there are always two possibilities because AUIPC copies
+ the 12 lowest bits from pc instead of zeroing them.
+
+ NOTE: The sign-extension of inst2_imm12 adds a tiny bit
+ of extra complexity to AUIPC math in general but it's not
+ the reason for this problem. The sign-extension only changes
+ the relative position of the pc-relative 4096-byte window.
+
+ (2) Matching AUIPC instruction alone requires only seven bits.
+ When the filter is applied to non-code data, that leads
+ to many false positives which make compression worse.
+ As long as most AUIPC+inst2 pairs appear as two consecutive
+ instructions, converting only such pairs gives better results.
+
+ In assembly, AUIPC+inst2 tend to look like this:
+
+ # Call:
+ auipc ra, 0x12345
+ jalr ra, -42(ra)
+
+ # Tail call:
+ auipc t1, 0x12345
+ jalr zero, -42(t1)
+
+ # Getting the absolute address:
+ auipc a0, 0x12345
+ addi a0, a0, -42
+
+ # rd of inst2 isn't necessarily the same as rs1 even
+ # in cases where there is no reason to preserve rs1.
+ auipc a0, 0x12345
+ addi a1, a0, -42
+
+ As of 2024, 16-bit instructions from the C extension don't
+ appear as inst2. The RISC-V psABI doesn't list AUIPC+C.* as
+ a linker relaxation type explicitly but it's not disallowed
+ either. Usefulness is limited as most of the time the lowest
+ 12 bits won't fit in a C instruction. This filter doesn't
+ support AUIPC+C.* combinations because this makes the filter
+ simpler, there are no test files, and it hopefully will never
+ be needed anyway.
+
+ (Compare AUIPC to ARM64 where ADRP does set the lowest 12 bits
+ to zero. The paired instruction has the lowest 12 bits of the
+ absolute address as is in a zero-extended immediate. Thus the
+ ARM64 filter doesn't need to care about the instructions that
+ are paired with ADRP. An off-by-4096 issue can still occur if
+ the code section isn't aligned with the filter's start offset.
+ It's not a problem with standalone ELF files but Windows PE
+ files need start_offset=3072 for best results. Also, a .tar
+ stores files with 512-byte alignment so most of the time it
+ won't be the best for ARM64.)
+
+AUIPC with rd == x0
+-------------------
+
+ AUIPC instructions with rd=x0 are reserved for HINTs in the base
+ instruction set. Such AUIPC instructions are never filtered.
+
+ As of January 2024, it seems likely that AUIPC with rd=x0 will
+ be used for landing pads (pseudoinstruction LPAD). LPAD is used
+ to mark valid targets for indirect jumps (for JALR), for example,
+ beginnings of functions. The 20-bit immediate in LPAD instruction
+ is a label, not a pc-relative address. Thus it would be
+ counterproductive to convert AUIPC instructions with rd=x0.
+
+ Often the next instruction after LPAD won't have rs1=x0 and thus
+ the filtering would be skipped for that reason alone. However,
+ it's not good to rely on this. For example, consider a function
+ that begins like this:
+
+ int foo(int i)
+ {
+ if (i <= 234) {
+ ...
+ }
+
+ A compiler may generate something like this:
+
+ lpad 0x54321
+ li a5, 234
+ bgt a0, a5, .L2
+
+ Converting the pseudoinstructions to raw instructions:
+
+ auipc x0, 0x54321
+ addi x15, x0, 234
+ blt x15, x10, .L2
+
+ In this case the filter would undesirably convert the AUIPC+ADDI
+ pair if the filter didn't explicitly skip AUIPC instructions
+ that have rd=x0.
+
+*/
+
+
+#include "simple_private.h"
+
+
+// This checks two conditions at once:
+// - AUIPC rd == inst2 rs1.
+// - inst2 opcode has the lowest two bits set.
+//
+// The 8 bit left shift aligns the rd of AUIPC with the rs1 of inst2.
+// By XORing the registers, any non-zero value in those bits indicates the
+// registers are not equal and thus not an AUIPC pair. Subtracting 3 from
+// inst2 will zero out the first two opcode bits only when they are set.
+// The mask tests if any of the register or opcode bits are set (and thus
+// not an AUIPC pair).
+//
+// Alternative expression: (((((auipc) << 8) ^ (inst2)) & 0xF8003) != 3)
+#define NOT_AUIPC_PAIR(auipc, inst2) \
+ ((((auipc) << 8) ^ ((inst2) - 3)) & 0xF8003)
+
+// This macro checks multiple conditions:
+// (1) AUIPC rd [11:7] == x2 (special rd value).
+// (2) AUIPC bits 12 and 13 set (the lowest two opcode bits of packed inst2).
+// (3) inst2_rs1 doesn't equal x0 or x2 because the opposite
+// conversion is only done when
+// auipc_rd != x0 &&
+// auipc_rd != x2 &&
+// auipc_rd == inst2_rs1.
+//
+// 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 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 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
+// ensures that any non-zero result will be larger than any possible result
+// from the right-hand side of the comparison. The cast ensures that the
+// left-hand side didn't get promoted to a larger type than uint32_t.
+//
+// On the right-hand side, inst2_rs1 & 0x1D will be non-zero as long as
+// inst2_rs1 is not x0 or x2.
+//
+// The final '>=' comparison will make the expression true if:
+// - The subtraction caused any bits to be set (special AUIPC rd value not
+// used or inst2 opcode bits not set). (non-zero >= non-zero or 0)
+// - The subtraction did not cause any bits to be set but inst2_rs1 was
+// x0 or x2. (0 >= 0)
+#define NOT_SPECIAL_AUIPC(auipc, inst2_rs1) \
+ ((uint32_t)(((auipc) - 0x3117) << 18) >= ((inst2_rs1) & 0x1D))
+
+
+// The encode and decode functions are split for this filter because of the
+// AUIPC+inst2 filtering. This filter design allows a decoder-only
+// implementation to be smaller than alternative designs.
+
+#ifdef HAVE_ENCODER_RISCV
+static size_t
+riscv_encode(void *simple lzma_attribute((__unused__)),
+ uint32_t now_pos,
+ bool is_encoder lzma_attribute((__unused__)),
+ uint8_t *buffer, size_t size)
+{
+ // Avoid using i + 8 <= size in the loop condition.
+ //
+ // NOTE: If there is a JAL in the last six bytes of the stream, it
+ // won't be converted. This is intentional to keep the code simpler.
+ if (size < 8)
+ return 0;
+
+ size -= 8;
+
+ size_t i;
+
+ // The loop is advanced by 2 bytes every iteration since the
+ // instruction stream may include 16-bit instructions (C extension).
+ for (i = 0; i <= size; i += 2) {
+ uint32_t inst = buffer[i];
+
+ if (inst == 0xEF) {
+ // JAL
+ const uint32_t b1 = buffer[i + 1];
+
+ // Only filter rd=x1(ra) and rd=x5(t0).
+ if ((b1 & 0x0D) != 0)
+ continue;
+
+ // The 20-bit immediate is in four pieces.
+ // The encoder stores it in big endian form
+ // since it improves compression slightly.
+ const uint32_t b2 = buffer[i + 2];
+ const uint32_t b3 = buffer[i + 3];
+ const uint32_t pc = now_pos + (uint32_t)i;
+
+// The following chart shows the highest three bytes of JAL, focusing on
+// the 20-bit immediate field [31:12]. The first row of numbers is the
+// bit position in a 32-bit little endian instruction. The second row of
+// numbers shows the order of the immediate field in a J-type instruction.
+// The last row is the bit number in each byte.
+//
+// To determine the amount to shift each bit, subtract the value in
+// the last row from the value in the second last row. If the number
+// is positive, shift left. If negative, shift right.
+//
+// For example, at the rightmost side of the chart, the bit 4 in b1 is
+// the bit 12 of the address. Thus that bit needs to be shifted left
+// by 12 - 4 = 8 bits to put it in the right place in the addr variable.
+//
+// NOTE: The immediate of a J-type instruction holds bits [20:1] of
+// the address. The bit [0] is always 0 and not part of the immediate.
+//
+// | b3 | b2 | b1 |
+// | 31 30 29 28 27 26 25 24 | 23 22 21 20 19 18 17 16 | 15 14 13 12 x x x x |
+// | 20 10 9 8 7 6 5 4 | 3 2 1 11 19 18 17 16 | 15 14 13 12 x x x x |
+// | 7 6 5 4 3 2 1 0 | 7 6 5 4 3 2 1 0 | 7 6 5 4 x x x x |
+
+ uint32_t addr = ((b1 & 0xF0) << 8)
+ | ((b2 & 0x0F) << 16)
+ | ((b2 & 0x10) << 7)
+ | ((b2 & 0xE0) >> 4)
+ | ((b3 & 0x7F) << 4)
+ | ((b3 & 0x80) << 13);
+
+ addr += pc;
+
+ buffer[i + 1] = (uint8_t)((b1 & 0x0F)
+ | ((addr >> 13) & 0xF0));
+
+ buffer[i + 2] = (uint8_t)(addr >> 9);
+ buffer[i + 3] = (uint8_t)(addr >> 1);
+
+ // The "-2" is included because the for-loop will
+ // always increment by 2. In this case, we want to
+ // skip an extra 2 bytes since we used 4 bytes
+ // of input.
+ i += 4 - 2;
+
+ } else if ((inst & 0x7F) == 0x17) {
+ // AUIPC
+ inst |= (uint32_t)buffer[i + 1] << 8;
+ inst |= (uint32_t)buffer[i + 2] << 16;
+ inst |= (uint32_t)buffer[i + 3] << 24;
+
+ // Branch based on AUIPC's rd. The bitmask test does
+ // the same thing as this:
+ //
+ // const uint32_t auipc_rd = (inst >> 7) & 0x1F;
+ // if (auipc_rd != 0 && auipc_rd != 2) {
+ if (inst & 0xE80) {
+ // AUIPC's rd doesn't equal x0 or x2.
+
+ // Check if AUIPC+inst2 are a pair.
+ uint32_t inst2 = read32le(buffer + i + 4);
+
+ if (NOT_AUIPC_PAIR(inst, inst2)) {
+ // The NOT_AUIPC_PAIR macro allows
+ // a false AUIPC+AUIPC pair if the
+ // bits [19:15] (where rs1 would be)
+ // in the second AUIPC match the rd
+ // of the first AUIPC.
+ //
+ // We must skip enough forward so
+ // that the first two bytes of the
+ // second AUIPC cannot get converted.
+ // Such a conversion could make the
+ // current pair become a valid pair
+ // which would desync the decoder.
+ //
+ // Skipping six bytes is enough even
+ // though the above condition looks
+ // at the lowest four bits of the
+ // buffer[i + 6] too. This is safe
+ // because this filter never changes
+ // those bits if a conversion at
+ // that position is done.
+ i += 6 - 2;
+ continue;
+ }
+
+ // Convert AUIPC+inst2 to a special format:
+ //
+ // - The lowest 7 bits [6:0] retain the
+ // AUIPC opcode.
+ //
+ // - The rd [11:7] is set to x2(sp). x2 is
+ // used as the stack pointer so AUIPC with
+ // rd=x2 should be very rare in real-world
+ // executables.
+ //
+ // - The remaining 20 bits [31:12] (that
+ // normally hold the pc-relative immediate)
+ // are used to store the lowest 20 bits of
+ // inst2. That is, the 12-bit immediate of
+ // inst2 is not included.
+ //
+ // - The location of the original inst2 is
+ // used to store the 32-bit absolute
+ // address in big endian format. Compared
+ // to the 20+12-bit split encoding, this
+ // results in a longer uninterrupted
+ // sequence of identical common bytes
+ // when the same address is referred
+ // with different instruction pairs
+ // (like AUIPC+LD vs. AUIPC+ADDI) or
+ // when the occurrences of the same
+ // pair use different registers. When
+ // referring to adjacent memory locations
+ // (like function calls that go via the
+ // ELF PLT), in big endian order only the
+ // last 1-2 bytes differ; in little endian
+ // the differing 1-2 bytes would be in the
+ // middle of the 8-byte sequence.
+ //
+ // When reversing the transformation, the
+ // original rd of AUIPC can be restored
+ // from inst2's rs1 as they are required to
+ // be the same.
+
+ // Arithmetic right shift makes sign extension
+ // trivial but (1) it's implementation-defined
+ // behavior (C99/C11/C23 6.5.7-p5) and so is
+ // (2) casting unsigned to signed (6.3.1.3-p3).
+ //
+ // One can check for (1) with
+ //
+ // if ((-1 >> 1) == -1) ...
+ //
+ // but (2) has to be checked from the
+ // compiler docs. GCC promises that (1)
+ // and (2) behave in the common expected
+ // way and thus
+ //
+ // addr += (uint32_t)(
+ // (int32_t)inst2 >> 20);
+ //
+ // does the same as the code below. But since
+ // the 100 % portable way is only a few bytes
+ // bigger code and there is no real speed
+ // difference, let's just use that, especially
+ // since the decoder doesn't need this at all.
+ uint32_t addr = inst & 0xFFFFF000;
+ addr += (inst2 >> 20)
+ - ((inst2 >> 19) & 0x1000);
+
+ addr += now_pos + (uint32_t)i;
+
+ // Construct the first 32 bits:
+ // [6:0] AUIPC opcode
+ // [11:7] Special AUIPC rd = x2
+ // [31:12] The lowest 20 bits of inst2
+ inst = 0x17 | (2 << 7) | (inst2 << 12);
+
+ write32le(buffer + i, inst);
+
+ // The second 32 bits store the absolute
+ // address in big endian order.
+ write32be(buffer + i + 4, addr);
+ } else {
+ // AUIPC's rd equals x0 or x2.
+ //
+ // x0 indicates a landing pad (LPAD).
+ // It's always skipped.
+ //
+ // AUIPC with rd == x2 is used for the special
+ // format as explained above. When the input
+ // contains a byte sequence that matches the
+ // special format, "fake" decoding must be
+ // done to keep the filter bijective (that
+ // is, safe to apply on arbitrary data).
+ //
+ // See the "x0 or x2" section in riscv_decode()
+ // for how the "real" decoding is done. The
+ // "fake" decoding is a simplified version
+ // of "real" decoding with the following
+ // differences (these reduce code size of
+ // the decoder):
+ // (1) The lowest 12 bits aren't sign-extended.
+ // (2) No address conversion is done.
+ // (3) Big endian format isn't used (the fake
+ // address is in little endian order).
+
+ // Check if inst matches the special format.
+ const uint32_t fake_rs1 = inst >> 27;
+
+ if (NOT_SPECIAL_AUIPC(inst, fake_rs1)) {
+ i += 4 - 2;
+ continue;
+ }
+
+ const uint32_t fake_addr =
+ read32le(buffer + i + 4);
+
+ // Construct the second 32 bits:
+ // [19:0] Upper 20 bits from AUIPC
+ // [31:20] The lowest 12 bits of fake_addr
+ const uint32_t fake_inst2 = (inst >> 12)
+ | (fake_addr << 20);
+
+ // Construct new first 32 bits from:
+ // [6:0] AUIPC opcode
+ // [11:7] Fake AUIPC rd = fake_rs1
+ // [31:12] The highest 20 bits of fake_addr
+ inst = 0x17 | (fake_rs1 << 7)
+ | (fake_addr & 0xFFFFF000);
+
+ write32le(buffer + i, inst);
+ write32le(buffer + i + 4, fake_inst2);
+ }
+
+ i += 8 - 2;
+ }
+ }
+
+ return i;
+}
+
+
+extern lzma_ret
+lzma_simple_riscv_encoder_init(lzma_next_coder *next,
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters)
+{
+ return lzma_simple_coder_init(next, allocator, filters,
+ &riscv_encode, 0, 8, 2, true);
+}
+#endif
+
+
+#ifdef HAVE_DECODER_RISCV
+static size_t
+riscv_decode(void *simple lzma_attribute((__unused__)),
+ uint32_t now_pos,
+ bool is_encoder lzma_attribute((__unused__)),
+ uint8_t *buffer, size_t size)
+{
+ if (size < 8)
+ return 0;
+
+ size -= 8;
+
+ size_t i;
+ for (i = 0; i <= size; i += 2) {
+ uint32_t inst = buffer[i];
+
+ if (inst == 0xEF) {
+ // JAL
+ const uint32_t b1 = buffer[i + 1];
+
+ // Only filter rd=x1(ra) and rd=x5(t0).
+ if ((b1 & 0x0D) != 0)
+ continue;
+
+ const uint32_t b2 = buffer[i + 2];
+ const uint32_t b3 = buffer[i + 3];
+ const uint32_t pc = now_pos + (uint32_t)i;
+
+// | b3 | b2 | b1 |
+// | 31 30 29 28 27 26 25 24 | 23 22 21 20 19 18 17 16 | 15 14 13 12 x x x x |
+// | 20 10 9 8 7 6 5 4 | 3 2 1 11 19 18 17 16 | 15 14 13 12 x x x x |
+// | 7 6 5 4 3 2 1 0 | 7 6 5 4 3 2 1 0 | 7 6 5 4 x x x x |
+
+ uint32_t addr = ((b1 & 0xF0) << 13)
+ | (b2 << 9) | (b3 << 1);
+
+ addr -= pc;
+
+ buffer[i + 1] = (uint8_t)((b1 & 0x0F)
+ | ((addr >> 8) & 0xF0));
+
+ buffer[i + 2] = (uint8_t)(((addr >> 16) & 0x0F)
+ | ((addr >> 7) & 0x10)
+ | ((addr << 4) & 0xE0));
+
+ buffer[i + 3] = (uint8_t)(((addr >> 4) & 0x7F)
+ | ((addr >> 13) & 0x80));
+
+ i += 4 - 2;
+
+ } else if ((inst & 0x7F) == 0x17) {
+ // AUIPC
+ uint32_t inst2;
+
+ inst |= (uint32_t)buffer[i + 1] << 8;
+ inst |= (uint32_t)buffer[i + 2] << 16;
+ inst |= (uint32_t)buffer[i + 3] << 24;
+
+ if (inst & 0xE80) {
+ // AUIPC's rd doesn't equal x0 or x2.
+
+ // Check if it is a "fake" AUIPC+inst2 pair.
+ inst2 = read32le(buffer + i + 4);
+
+ if (NOT_AUIPC_PAIR(inst, inst2)) {
+ i += 6 - 2;
+ continue;
+ }
+
+ // Decode (or more like re-encode) the "fake"
+ // pair. The "fake" format doesn't do
+ // sign-extension, address conversion, or
+ // use big endian. (The use of little endian
+ // allows sharing the write32le() calls in
+ // the decoder to reduce code size when
+ // unaligned access isn't supported.)
+ uint32_t addr = inst & 0xFFFFF000;
+ addr += inst2 >> 20;
+
+ inst = 0x17 | (2 << 7) | (inst2 << 12);
+ inst2 = addr;
+ } else {
+ // AUIPC's rd equals x0 or x2.
+
+ // Check if inst matches the special format
+ // used by the encoder.
+ const uint32_t inst2_rs1 = inst >> 27;
+
+ if (NOT_SPECIAL_AUIPC(inst, inst2_rs1)) {
+ i += 4 - 2;
+ continue;
+ }
+
+ // Decode the "real" pair.
+ uint32_t addr = read32be(buffer + i + 4);
+
+ addr -= now_pos + (uint32_t)i;
+
+ // The second instruction:
+ // - Get the lowest 20 bits from inst.
+ // - Add the lowest 12 bits of the address
+ // as the immediate field.
+ inst2 = (inst >> 12) | (addr << 20);
+
+ // AUIPC:
+ // - rd is the same as inst2_rs1.
+ // - The sign extension of the lowest 12 bits
+ // must be taken into account.
+ inst = 0x17 | (inst2_rs1 << 7)
+ | ((addr + 0x800) & 0xFFFFF000);
+ }
+
+ // Both decoder branches write in little endian order.
+ write32le(buffer + i, inst);
+ write32le(buffer + i + 4, inst2);
+
+ i += 8 - 2;
+ }
+ }
+
+ return i;
+}
+
+
+extern lzma_ret
+lzma_simple_riscv_decoder_init(lzma_next_coder *next,
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters)
+{
+ return lzma_simple_coder_init(next, allocator, filters,
+ &riscv_decode, 0, 8, 2, false);
+}
+#endif
diff --git a/src/liblzma/simple/simple_coder.c b/src/liblzma/simple/simple_coder.c
index ed2d7fb..5cbfa82 100644
--- a/src/liblzma/simple/simple_coder.c
+++ b/src/liblzma/simple/simple_coder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_coder.c
@@ -8,9 +10,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/simple_coder.h b/src/liblzma/simple/simple_coder.h
index 668a509..2b762d5 100644
--- a/src/liblzma/simple/simple_coder.h
+++ b/src/liblzma/simple/simple_coder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_coder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SIMPLE_CODER_H
@@ -62,12 +61,12 @@ extern lzma_ret lzma_simple_armthumb_decoder_init(lzma_next_coder *next,
extern lzma_ret lzma_simple_arm64_encoder_init(lzma_next_coder *next,
- const lzma_allocator *allocator,
- const lzma_filter_info *filters);
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters);
extern lzma_ret lzma_simple_arm64_decoder_init(lzma_next_coder *next,
- const lzma_allocator *allocator,
- const lzma_filter_info *filters);
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters);
extern lzma_ret lzma_simple_sparc_encoder_init(lzma_next_coder *next,
@@ -78,4 +77,13 @@ extern lzma_ret lzma_simple_sparc_decoder_init(lzma_next_coder *next,
const lzma_allocator *allocator,
const lzma_filter_info *filters);
+
+extern lzma_ret lzma_simple_riscv_encoder_init(lzma_next_coder *next,
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters);
+
+extern lzma_ret lzma_simple_riscv_decoder_init(lzma_next_coder *next,
+ const lzma_allocator *allocator,
+ const lzma_filter_info *filters);
+
#endif
diff --git a/src/liblzma/simple/simple_decoder.c b/src/liblzma/simple/simple_decoder.c
index dc4d241..d9820ee 100644
--- a/src/liblzma/simple/simple_decoder.c
+++ b/src/liblzma/simple/simple_decoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_decoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_decoder.h"
diff --git a/src/liblzma/simple/simple_decoder.h b/src/liblzma/simple/simple_decoder.h
index bed8d37..2ae87bb 100644
--- a/src/liblzma/simple/simple_decoder.h
+++ b/src/liblzma/simple/simple_decoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_decoder.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SIMPLE_DECODER_H
diff --git a/src/liblzma/simple/simple_encoder.c b/src/liblzma/simple/simple_encoder.c
index d2cc03e..d1f3509 100644
--- a/src/liblzma/simple/simple_encoder.c
+++ b/src/liblzma/simple/simple_encoder.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_encoder.h"
diff --git a/src/liblzma/simple/simple_encoder.h b/src/liblzma/simple/simple_encoder.h
index 1cee482..bf5edbb 100644
--- a/src/liblzma/simple/simple_encoder.h
+++ b/src/liblzma/simple/simple_encoder.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_encoder.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SIMPLE_ENCODER_H
diff --git a/src/liblzma/simple/simple_private.h b/src/liblzma/simple/simple_private.h
index 9d2c0fd..7aa360f 100644
--- a/src/liblzma/simple/simple_private.h
+++ b/src/liblzma/simple/simple_private.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file simple_private.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#ifndef LZMA_SIMPLE_PRIVATE_H
diff --git a/src/liblzma/simple/sparc.c b/src/liblzma/simple/sparc.c
index bad8492..e8ad285 100644
--- a/src/liblzma/simple/sparc.c
+++ b/src/liblzma/simple/sparc.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file sparc.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
diff --git a/src/liblzma/simple/x86.c b/src/liblzma/simple/x86.c
index 232b295..f216231 100644
--- a/src/liblzma/simple/x86.c
+++ b/src/liblzma/simple/x86.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file x86.c
@@ -6,9 +8,6 @@
// Authors: Igor Pavlov
// Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "simple_private.h"
@@ -27,11 +26,7 @@ static size_t
x86_code(void *simple_ptr, uint32_t now_pos, bool is_encoder,
uint8_t *buffer, size_t size)
{
- static const bool MASK_TO_ALLOWED_STATUS[8]
- = { true, true, true, false, true, false, false, false };
-
- static const uint32_t MASK_TO_BIT_NUMBER[8]
- = { 0, 1, 2, 2, 3, 3, 3, 3 };
+ static const uint32_t MASK_TO_BIT_NUMBER[5] = { 0, 1, 2, 2, 3 };
lzma_simple_x86 *simple = simple_ptr;
uint32_t prev_mask = simple->prev_mask;
@@ -68,9 +63,8 @@ x86_code(void *simple_ptr, uint32_t now_pos, bool is_encoder,
b = buffer[buffer_pos + 4];
- if (Test86MSByte(b)
- && MASK_TO_ALLOWED_STATUS[(prev_mask >> 1) & 0x7]
- && (prev_mask >> 1) < 0x10) {
+ if (Test86MSByte(b) && (prev_mask >> 1) <= 4
+ && (prev_mask >> 1) != 3) {
uint32_t src = ((uint32_t)(b) << 24)
| ((uint32_t)(buffer[buffer_pos + 3]) << 16)
diff --git a/src/liblzma/validate_map.sh b/src/liblzma/validate_map.sh
index 2bf6f8b..dd1589d 100644
--- a/src/liblzma/validate_map.sh
+++ b/src/liblzma/validate_map.sh
@@ -1,4 +1,5 @@
#!/bin/sh
+# SPDX-License-Identifier: 0BSD
###############################################################################
#
@@ -78,9 +79,6 @@
#
# Author: Lasse Collin
#
-# This file has been put into the public domain.
-# You can do whatever you want with this file.
-#
###############################################################################
LC_ALL=C
@@ -124,7 +122,7 @@ DUPS=$(sort liblzma_generic.map | sed '/^$/d;/^global:$/d' | uniq -d)
# ignored (@XZ_5.1.2alpha or @XZ_5.2.2 won't be added at all when
# the #define HAVE_SYMBOL_VERSIONS_LINUX isn't used).
IN_SYNC=
-if ! sed '109,123d' liblzma_linux.map \
+if ! sed '111,125d' liblzma_linux.map \
| cmp -s - liblzma_generic.map; then
IN_SYNC=no
fi
diff --git a/src/lzmainfo/Makefile.am b/src/lzmainfo/Makefile.am
index ff7172b..9a5bc68 100644
--- a/src/lzmainfo/Makefile.am
+++ b/src/lzmainfo/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
bin_PROGRAMS = lzmainfo
@@ -37,3 +33,29 @@ dist_man_MANS = lzmainfo.1
.rc.o:
$(RC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \
$(lzmainfo_CPPFLAGS) $(CPPFLAGS) $(RCFLAGS) -i $< -o $@
+
+# The installation of translated man pages abuses Automake internals
+# by calling "install-man" with redefined dist_man_MANS and man_MANS.
+# If this breaks some day, don't blame Automake developers.
+install-data-hook:
+ languages= ; \
+ if test "$(USE_NLS)" = yes && test -d "$(top_srcdir)/po4a/man"; then \
+ languages=`ls "$(top_srcdir)/po4a/man"`; \
+ fi; \
+ for lang in . $$languages; do \
+ man="$(top_srcdir)/po4a/man/$$lang/lzmainfo.1" ; \
+ if test -f "$$man"; then \
+ $(MAKE) dist_man_MANS="$$man" man_MANS= \
+ mandir="$(mandir)/$$lang" install-man; \
+ fi; \
+ done
+
+uninstall-hook:
+ languages= ; \
+ if test "$(USE_NLS)" = yes && test -d "$(top_srcdir)/po4a/man"; then \
+ languages=`ls "$(top_srcdir)/po4a/man"`; \
+ fi; \
+ for lang in . $$languages; do \
+ name=`echo lzmainfo | sed '$(transform)'` && \
+ rm -f "$(DESTDIR)$(mandir)/$$lang/man1/$$name.1"; \
+ done
diff --git a/src/lzmainfo/Makefile.in b/src/lzmainfo/Makefile.in
index 0a18942..feea983 100644
--- a/src/lzmainfo/Makefile.in
+++ b/src/lzmainfo/Makefile.in
@@ -93,8 +93,8 @@ bin_PROGRAMS = lzmainfo$(EXEEXT)
@COND_GNULIB_TRUE@am__append_2 = $(top_builddir)/lib/libgnu.a
subdir = src/lzmainfo
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -237,7 +237,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -366,6 +365,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
@@ -756,7 +757,8 @@ info: info-am
info-am:
install-data-am: install-man
-
+ @$(NORMAL_INSTALL)
+ $(MAKE) $(AM_MAKEFLAGS) install-data-hook
install-dvi: install-dvi-am
install-dvi-am:
@@ -804,25 +806,27 @@ ps: ps-am
ps-am:
uninstall-am: uninstall-binPROGRAMS uninstall-man
-
+ @$(NORMAL_INSTALL)
+ $(MAKE) $(AM_MAKEFLAGS) uninstall-hook
uninstall-man: uninstall-man1
-.MAKE: install-am install-strip
+.MAKE: install-am install-data-am install-strip uninstall-am
.PHONY: CTAGS GTAGS TAGS all all-am am--depfiles check check-am clean \
clean-binPROGRAMS clean-generic clean-libtool cscopelist-am \
ctags ctags-am distclean distclean-compile distclean-generic \
distclean-libtool distclean-tags distdir dvi dvi-am html \
html-am info info-am install install-am install-binPROGRAMS \
- 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-man1 \
- 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 mostlyclean-libtool \
- pdf pdf-am ps ps-am tags tags-am uninstall uninstall-am \
- uninstall-binPROGRAMS uninstall-man uninstall-man1
+ install-data install-data-am install-data-hook install-dvi \
+ install-dvi-am install-exec install-exec-am install-html \
+ install-html-am install-info install-info-am install-man \
+ install-man1 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 \
+ mostlyclean-libtool pdf pdf-am ps ps-am tags tags-am uninstall \
+ uninstall-am uninstall-binPROGRAMS uninstall-hook \
+ uninstall-man uninstall-man1
.PRECIOUS: Makefile
@@ -832,6 +836,32 @@ uninstall-man: uninstall-man1
$(RC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \
$(lzmainfo_CPPFLAGS) $(CPPFLAGS) $(RCFLAGS) -i $< -o $@
+# The installation of translated man pages abuses Automake internals
+# by calling "install-man" with redefined dist_man_MANS and man_MANS.
+# If this breaks some day, don't blame Automake developers.
+install-data-hook:
+ languages= ; \
+ if test "$(USE_NLS)" = yes && test -d "$(top_srcdir)/po4a/man"; then \
+ languages=`ls "$(top_srcdir)/po4a/man"`; \
+ fi; \
+ for lang in . $$languages; do \
+ man="$(top_srcdir)/po4a/man/$$lang/lzmainfo.1" ; \
+ if test -f "$$man"; then \
+ $(MAKE) dist_man_MANS="$$man" man_MANS= \
+ mandir="$(mandir)/$$lang" install-man; \
+ fi; \
+ done
+
+uninstall-hook:
+ languages= ; \
+ if test "$(USE_NLS)" = yes && test -d "$(top_srcdir)/po4a/man"; then \
+ languages=`ls "$(top_srcdir)/po4a/man"`; \
+ fi; \
+ for lang in . $$languages; do \
+ name=`echo lzmainfo | sed '$(transform)'` && \
+ rm -f "$(DESTDIR)$(mandir)/$$lang/man1/$$name.1"; \
+ done
+
# 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/lzmainfo/lzmainfo.1 b/src/lzmainfo/lzmainfo.1
index ce38eee..114e0f3 100644
--- a/src/lzmainfo/lzmainfo.1
+++ b/src/lzmainfo/lzmainfo.1
@@ -1,9 +1,7 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
.\" Author: Lasse Collin
.\"
-.\" This file has been put into the public domain.
-.\" You can do whatever you want with this file.
-.\"
.TH LZMAINFO 1 "2013-06-30" "Tukaani" "XZ Utils"
.SH NAME
lzmainfo \- show information stored in the .lzma file header
diff --git a/src/lzmainfo/lzmainfo.c b/src/lzmainfo/lzmainfo.c
index 71e6295..2550b1f 100644
--- a/src/lzmainfo/lzmainfo.c
+++ b/src/lzmainfo/lzmainfo.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file lzmainfo.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "sysdefs.h"
diff --git a/src/lzmainfo/lzmainfo_w32res.rc b/src/lzmainfo/lzmainfo_w32res.rc
index 378fbe6..f2ec288 100644
--- a/src/lzmainfo/lzmainfo_w32res.rc
+++ b/src/lzmainfo/lzmainfo_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#define MY_TYPE VFT_APP
diff --git a/src/scripts/Makefile.am b/src/scripts/Makefile.am
index fe5742d..29c561c 100644
--- a/src/scripts/Makefile.am
+++ b/src/scripts/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
nodist_bin_SCRIPTS = xzdiff xzgrep xzmore xzless
dist_man_MANS = xzdiff.1 xzgrep.1 xzmore.1 xzless.1
diff --git a/src/scripts/Makefile.in b/src/scripts/Makefile.in
index 42dbfff..5cd5dbd 100644
--- a/src/scripts/Makefile.in
+++ b/src/scripts/Makefile.in
@@ -99,8 +99,8 @@ host_triplet = @host@
subdir = src/scripts
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -189,7 +189,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -318,6 +317,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
diff --git a/src/scripts/xzdiff.1 b/src/scripts/xzdiff.1
index 24fed68..8f473ed 100644
--- a/src/scripts/xzdiff.1
+++ b/src/scripts/xzdiff.1
@@ -1,67 +1,90 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
-.\" Original zdiff.1 for gzip: Jean-loup Gailly
+.\" Authors: Lasse Collin
+.\" Jia Tan
.\"
-.\" Modifications for XZ Utils: Lasse Collin
-.\" Andrew Dudman
+.\" (Note that this file is not based on gzip's zdiff.1.)
.\"
-.\" License: GNU GPLv2+
-.\"
-.TH XZDIFF 1 "2021-06-04" "Tukaani" "XZ Utils"
+.TH XZDIFF 1 "2024-02-13" "Tukaani" "XZ Utils"
.SH NAME
xzcmp, xzdiff, lzcmp, lzdiff \- compare compressed files
+.
.SH SYNOPSIS
.B xzcmp
-.RI [ cmp_options "] " file1 " [" file2 ]
+.RI [ option... ]
+.I file1
+.RI [ file2 ]
.br
.B xzdiff
-.RI [ diff_options "] " file1 " [" file2 ]
+\&...
.br
.B lzcmp
-.RI [ cmp_options "] " file1 " [" file2 ]
+\&...
.br
.B lzdiff
-.RI [ diff_options "] " file1 " [" file2 ]
+\&...
+.
.SH DESCRIPTION
.B xzcmp
and
.B xzdiff
-invoke
+compare uncompressed contents of two files.
+Uncompressed data and options are passed to
.BR cmp (1)
or
.BR diff (1)
-on files compressed with
+unless
+.B \-\-help
+or
+.B \-\-version
+is specified.
+.PP
+If both
+.I file1
+and
+.I file2
+are specified, they can be uncompressed files or files in formats that
.BR xz (1),
-.BR lzma (1),
.BR gzip (1),
.BR bzip2 (1),
.BR lzop (1),
+.BR zstd (1),
or
-.BR zstd (1).
-All options specified are passed directly to
-.BR cmp (1)
-or
-.BR diff (1).
-If only one file is specified, then the files compared are
+.BR lz4 (1)
+can decompress.
+The required decompression commands are determined from
+the filename suffixes of
.I file1
-(which must have a suffix of a supported compression format) and
+and
+.IR file2 .
+A file with an unknown suffix is assumed to be either uncompressed
+or in a format that
+.BR xz (1)
+can decompress.
+.PP
+If only one filename is provided,
.I file1
-from which the compression format suffix has been stripped.
-If two files are specified,
-then they are uncompressed if necessary and fed to
-.BR cmp (1)
-or
-.BR diff (1).
-The exit status from
-.BR cmp (1)
-or
-.BR diff (1)
-is preserved unless a decompression error occurs; then exit status is 2.
+must have a suffix of a supported compression format and the name for
+.I file2
+is assumed to be
+.I file1
+with the compression format suffix removed.
.PP
-The names
+The commands
.B lzcmp
and
.B lzdiff
are provided for backward compatibility with LZMA Utils.
+.
+.SH EXIT STATUS
+If a decompression error occurs, the exit status is
+.BR 2 .
+Otherwise the exit status of
+.BR cmp (1)
+or
+.BR diff (1)
+is used.
+.
.SH "SEE ALSO"
.BR cmp (1),
.BR diff (1),
@@ -70,10 +93,4 @@ are provided for backward compatibility with LZMA Utils.
.BR bzip2 (1),
.BR lzop (1),
.BR zstd (1),
-.BR zdiff (1)
-.SH BUGS
-Messages from the
-.BR cmp (1)
-or
-.BR diff (1)
-programs refer to temporary filenames instead of those specified.
+.BR lz4 (1)
diff --git a/src/scripts/xzdiff.in b/src/scripts/xzdiff.in
index c17d78b..179218d 100644
--- a/src/scripts/xzdiff.in
+++ b/src/scripts/xzdiff.in
@@ -1,4 +1,5 @@
#!@POSIX_SHELL@
+# SPDX-License-Identifier: GPL-2.0-or-later
# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
# Copyright (C) 1993 Jean-loup Gailly
@@ -30,7 +31,7 @@ case ${0##*/} in
*) prog=xzdiff; cmp=${DIFF:-diff};;
esac
-version="$prog (@PACKAGE_NAME@) @VERSION@"
+version="$prog (@PACKAGE_NAME@) @PACKAGE_VERSION@"
usage="Usage: ${0##*/} [OPTION]... FILE1 [FILE2]
Compare FILE1 to FILE2, using their uncompressed contents if they are
@@ -83,13 +84,15 @@ if test $# -eq 1; then
xz1=lzop;;
*[-.]zst | *.tzst)
xz1='zstd -q';;
+ *[-.]lz4)
+ xz1=lz4;;
*)
printf '%s\n' "$0: $1: Unknown compressed file name suffix" >&2
exit 2;;
esac
case $1 in
- *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *[-.]lzo | *[-.]zst)
- FILE=`expr "X$1" : 'X\(.*\)[-.][abglmostxzZ2]*$'`;;
+ *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *[-.]lzo | *[-.]zst | *[-.]lz4)
+ FILE=`expr "X$1" : 'X\(.*\)[-.][abglmostxzZ24]*$'`;;
*.t[abglx]z)
FILE=`expr "X$1" : 'X\(.*[-.]t\)[abglx]z$'`ar;;
*.tbz2)
@@ -109,17 +112,19 @@ elif test $# -eq 2; then
*[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz1=gzip;;
*[-.]lzo | *.tzo) xz1=lzop;;
*[-.]zst | *.tzst) xz1='zstd -q';;
+ *[-.]lz4) xz1=lz4;;
esac
case $2 in
*[-.]bz2 | *.tbz | *.tbz2) xz2=bzip2;;
*[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz2=gzip;;
*[-.]lzo | *.tzo) xz2=lzop;;
*[-.]zst | *.tzst) xz2='zstd -q';;
+ *[-.]lz4) xz2=lz4;;
esac
case $1 in
- *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+ *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | *[-.]lz4 | -)
case "$2" in
- *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+ *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | *[-.]lz4 | -)
if test "$1$2" = --; then
xz_status=$(
exec 4>&1
@@ -183,7 +188,7 @@ elif test $# -eq 2; then
esac;;
*)
case "$2" in
- *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+ *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | *[-.]lz4 | -)
xz_status=$(
exec 4>&1
($xz2 -cdf -- "$2" 4>&-; echo $? >&4) 3>&- |
@@ -194,7 +199,7 @@ elif test $# -eq 2; then
esac;;
esac
else
- printf '%s\n' "$0: Invalid number of operands; try \`${0##*/} --help' for help" >&2
+ printf '%s\n' "$0: Invalid number of operands; try '${0##*/} --help' for help" >&2
exit 2
fi
diff --git a/src/scripts/xzgrep.1 b/src/scripts/xzgrep.1
index e0514b8..63f012c 100644
--- a/src/scripts/xzgrep.1
+++ b/src/scripts/xzgrep.1
@@ -1,19 +1,18 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
-.\" Original zgrep.1 for gzip: Jean-loup Gailly
-.\" Charles Levert <charles@comm.polymtl.ca>
+.\" Authors: Lasse Collin
+.\" Jia Tan
.\"
-.\" Modifications for XZ Utils: Lasse Collin
+.\" (Note that this file is not based on gzip's zgrep.1.)
.\"
-.\" License: GNU GPLv2+
-.\"
-.TH XZGREP 1 "2022-07-19" "Tukaani" "XZ Utils"
+.TH XZGREP 1 "2024-02-13" "Tukaani" "XZ Utils"
.SH NAME
-xzgrep \- search compressed files for a regular expression
+xzgrep \- search possibly-compressed files for patterns
+.
.SH SYNOPSIS
.B xzgrep
-.RI [ grep_options ]
-.RB [ \-e ]
-.I pattern
+.RI [ option... ]
+.RI [ pattern_list ]
.RI [ file... ]
.br
.B xzegrep
@@ -30,54 +29,84 @@ xzgrep \- search compressed files for a regular expression
.br
.B lzfgrep
\&...
+.
.SH DESCRIPTION
.B xzgrep
invokes
.BR grep (1)
-on
+on uncompressed contents of files.
+The formats of the
.I files
-which may be either uncompressed or compressed with
+are determined from the filename suffixes.
+Any
+.I file
+with a suffix supported by
.BR xz (1),
-.BR lzma (1),
.BR gzip (1),
.BR bzip2 (1),
.BR lzop (1),
+.BR zstd (1),
or
-.BR zstd (1).
-All options specified are passed directly to
-.BR grep (1).
+.BR lz4 (1)
+will be decompressed;
+all other files are assumed to be uncompressed.
.PP
If no
+.I files
+are specified or
.I file
-is specified, then standard input is decompressed if necessary
-and fed to
-.BR grep (1).
-When reading from standard input,
-.BR gzip (1),
-.BR bzip2 (1),
-.BR lzop (1),
-and
-.BR zstd (1)
-compressed files are not supported.
+is
+.B \-
+then standard input is read.
+When reading from standard input, only files supported by
+.BR xz (1)
+are decompressed.
+Other files are assumed to be in uncompressed form already.
+.PP
+Most
+.I options
+of
+.BR grep (1)
+are supported.
+However, the following options are not supported:
+.IP "" 4
+.BR \-r ,
+.B \-\-recursive
+.IP "" 4
+.BR \-R ,
+.B \-\-dereference\-recursive
+.IP "" 4
+.BR \-d ,
+.BI \-\-directories= action
+.IP "" 4
+.BR \-Z ,
+.B \-\-null
+.IP "" 4
+.BR \-z ,
+.B \-\-null\-data
+.IP "" 4
+.BI \-\-include= glob
+.IP "" 4
+.BI \-\-exclude= glob
+.IP "" 4
+.BI \-\-exclude\-from= file
+.IP "" 4
+.BI \-\-exclude\-dir= glob
.PP
-If
-.B xzgrep
-is invoked as
.B xzegrep
-or
+is an alias for
+.BR "xzgrep \-E" .
.B xzfgrep
-then
-.B grep \-E
-or
-.B grep \-F
-is used instead of
-.BR grep (1).
-The same applies to names
+is an alias for
+.BR "xzgrep \-F" .
+.PP
+The commands
.BR lzgrep ,
.BR lzegrep ,
and
-.BR lzfgrep ,
-which are provided for backward compatibility with LZMA Utils.
+.B lzfgrep
+are provided for backward compatibility with LZMA Utils.
+.
.SH EXIT STATUS
.TP
0
@@ -91,18 +120,19 @@ No errors occurred.
>1
One or more errors occurred.
It is unknown if matches were found.
+.
.SH ENVIRONMENT
.TP
.B GREP
-If the
+If
.B GREP
-environment variable is set,
-.B xzgrep
-uses it instead of
-.BR grep (1),
+is set to a non-empty value,
+it is used instead of
+.BR "grep" ,
.BR "grep \-E" ,
or
.BR "grep \-F" .
+.
.SH "SEE ALSO"
.BR grep (1),
.BR xz (1),
@@ -110,4 +140,5 @@ or
.BR bzip2 (1),
.BR lzop (1),
.BR zstd (1),
+.BR lz4 (1),
.BR zgrep (1)
diff --git a/src/scripts/xzgrep.in b/src/scripts/xzgrep.in
index 490e47d..c9cd02d 100644
--- a/src/scripts/xzgrep.in
+++ b/src/scripts/xzgrep.in
@@ -1,4 +1,5 @@
#!@POSIX_SHELL@
+# SPDX-License-Identifier: GPL-2.0-or-later
# xzgrep -- a wrapper around a grep program that decompresses files as needed
# Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
@@ -34,7 +35,7 @@ case ${0##*/} in
*) prog=xzgrep; grep=${GREP:-grep};;
esac
-version="$prog (@PACKAGE_NAME@) @VERSION@"
+version="$prog (@PACKAGE_NAME@) @PACKAGE_VERSION@"
usage="Usage: ${0##*/} [OPTION]... [-e] PATTERN [FILE]...
Look for instances of PATTERN in the input FILEs, using their
@@ -156,7 +157,7 @@ done
eval "set -- $operands "'${1+"$@"}'
if test $have_pat -eq 0; then
- case ${1?"Missing pattern; try \`${0##*/} --help' for help"} in
+ case ${1?"Missing pattern; try '${0##*/} --help' for help"} in
(*\'*)
grep="$grep -e '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
(*)
@@ -180,6 +181,7 @@ for i; do
*[-.]bz2 | *[-.]tbz | *.tbz2) uncompress="bzip2 -cdf";;
*[-.]lzo | *[-.]tzo) uncompress="lzop -cdf";;
*[-.]zst | *[-.]tzst) uncompress="zstd -cdfq";; # zstd needs -q.
+ *[-.]lz4) uncompress="lz4 -cdf";;
*) uncompress="$xz -cdfqQ";; # -qQ to ignore warnings like unsupp. check.
esac
# xz_status will hold the decompressor's exit status.
@@ -275,7 +277,7 @@ for i; do
test "$(kill -l "$xz_status" 2> /dev/null)" != "PIPE" && exit "$xz_status"
elif test "$xz_status" -gt 0; then
# Decompression failed but we will continue with the remaining
- # files anwyway. Set exit status to at least 2 to indicate an error.
+ # files anyway. Set exit status to at least 2 to indicate an error.
test "$r" -lt 2 && r=2
fi
diff --git a/src/scripts/xzless.1 b/src/scripts/xzless.1
index 2d05459..570e601 100644
--- a/src/scripts/xzless.1
+++ b/src/scripts/xzless.1
@@ -1,13 +1,11 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
.\" Authors: Andrew Dudman
.\" Lasse Collin
.\"
-.\" This file has been put into the public domain.
-.\" You can do whatever you want with this file.
-.\"
.\" (Note that this file is not based on gzip's zless.1.)
.\"
-.TH XZLESS 1 "2010-09-27" "Tukaani" "XZ Utils"
+.TH XZLESS 1 "2024-02-12" "Tukaani" "XZ Utils"
.SH NAME
xzless, lzless \- view xz or lzma compressed (text) files
.SH SYNOPSIS
@@ -19,10 +17,10 @@ xzless, lzless \- view xz or lzma compressed (text) files
.SH DESCRIPTION
.B xzless
is a filter that displays text from compressed files to a terminal.
-It works on files compressed with
+Files supported by
.BR xz (1)
-or
-.BR lzma (1).
+are decompressed;
+other files are assumed to be in uncompressed form already.
If no
.I files
are given,
diff --git a/src/scripts/xzless.in b/src/scripts/xzless.in
index 79a849e..6346966 100644
--- a/src/scripts/xzless.in
+++ b/src/scripts/xzless.in
@@ -1,4 +1,5 @@
#!@POSIX_SHELL@
+# SPDX-License-Identifier: GPL-2.0-or-later
# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
@@ -23,7 +24,7 @@
# specified via XZ_OPT.
xz='@xz@ --format=auto'
-version='xzless (@PACKAGE_NAME@) @VERSION@'
+version='xzless (@PACKAGE_NAME@) @PACKAGE_VERSION@'
usage="Usage: ${0##*/} [OPTION]... [FILE]...
Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
@@ -47,13 +48,27 @@ if test "${LESSMETACHARS+set}" != set; then
LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
fi
-if test "$(less -V | { read _ ver _ && echo ${ver%%.*}; })" -ge 429; then
+VER=$(less -V | { read _ ver _ && echo ${ver%%.*}; })
+if test "$VER" -ge 451; then
+ # less 451 or later: If the compressed file is valid but has
+ # zero bytes of uncompressed data, using two vertical bars ||- makes
+ # "less" check the exit status of xz and if it is zero then display
+ # an empty file. With a single vertical bar |- and no output from xz,
+ # "less" would attempt to display the raw input file instead.
+ LESSOPEN="||-$xz -cdfqQ -- %s"
+elif test "$VER" -ge 429; then
# less 429 or later: LESSOPEN pipe will be used on
# standard input if $LESSOPEN begins with |-.
LESSOPEN="|-$xz -cdfqQ -- %s"
else
LESSOPEN="|$xz -cdfqQ -- %s"
fi
+
+SHOW_PREPROC_ERRORS=
+if test "$VER" -ge 632; then
+ SHOW_PREPROC_ERRORS=--show-preproc-errors
+fi
+
export LESSMETACHARS LESSOPEN
-exec less "$@"
+exec less $SHOW_PREPROC_ERRORS "$@"
diff --git a/src/scripts/xzmore.1 b/src/scripts/xzmore.1
index 9613974..afe89b8 100644
--- a/src/scripts/xzmore.1
+++ b/src/scripts/xzmore.1
@@ -1,53 +1,63 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
-.\" Original zdiff.1 for gzip: Jean-loup Gailly
-.\" Modifications for XZ Utils: Lasse Collin
+.\" Authors: Andrew Dudman
+.\" Lasse Collin
.\"
-.\" License: GNU GPLv2+
+.\" (Note that this file is based on xzless.1 instead of gzip's zmore.1.)
.\"
-.TH XZMORE 1 "2013-06-30" "Tukaani" "XZ Utils"
+.TH XZMORE 1 "2024-02-12" "Tukaani" "XZ Utils"
.SH NAME
xzmore, lzmore \- view xz or lzma compressed (text) files
+.
.SH SYNOPSIS
.B xzmore
-.RI [ file... ]
+.RI [ file ...]
.br
.B lzmore
-.RI [ file... ]
+.RI [ file ...]
+.
.SH DESCRIPTION
-.B xzmore
-is a filter which allows examination of
+.B xzmore
+displays text from compressed files to a terminal using
+.BR more (1).
+Files supported by
.BR xz (1)
-or
-.BR lzma (1)
-compressed text files one screenful at a time
-on a soft-copy terminal.
+are decompressed;
+other files are assumed to be in uncompressed form already.
+If no
+.I files
+are given,
+.B xzmore
+reads from standard input.
+See the
+.BR more (1)
+manual for the keyboard commands.
.PP
-To use a pager other than the default
-.B more,
-set environment variable
-.B PAGER
-to the name of the desired program.
-The name
+Note that scrolling backwards might not be possible
+depending on the implementation of
+.BR more (1).
+This is because
+.B xzmore
+uses a pipe to pass the decompressed data to
+.BR more (1).
+.BR xzless (1)
+uses
+.BR less (1)
+which provides more advanced features.
+.PP
+The command
.B lzmore
is provided for backward compatibility with LZMA Utils.
+.
+.SH ENVIRONMENT
.TP
-.BR e " or " q
-When the prompt \-\-More\-\-(Next file:
-.IR file )
-is printed, this command causes
-.B xzmore
-to exit.
-.TP
-.B s
-When the prompt \-\-More\-\-(Next file:
-.IR file )
-is printed, this command causes
-.B xzmore
-to skip the next file and continue.
-.PP
-For list of keyboard commands supported while actually viewing the
-content of a file, refer to manual of the pager you use, usually
+.B PAGER
+If
+.B PAGER
+is set,
+its value is used as the pager instead of
.BR more (1).
+.
.SH "SEE ALSO"
.BR more (1),
.BR xz (1),
diff --git a/src/scripts/xzmore.in b/src/scripts/xzmore.in
index 5188fda..c571913 100644
--- a/src/scripts/xzmore.in
+++ b/src/scripts/xzmore.in
@@ -1,4 +1,5 @@
#!@POSIX_SHELL@
+# SPDX-License-Identifier: GPL-2.0-or-later
# Copyright (C) 2001, 2002, 2007 Free Software Foundation
# Copyright (C) 1992, 1993 Jean-loup Gailly
@@ -23,7 +24,7 @@
# specified via XZ_OPT.
xz='@xz@ --format=auto'
-version='xzmore (@PACKAGE_NAME@) @VERSION@'
+version='xzmore (@PACKAGE_NAME@) @PACKAGE_VERSION@'
usage="Usage: ${0##*/} [OPTION]... [FILE]...
Like 'more', but operate on the uncompressed contents of xz compressed FILEs.
diff --git a/src/xz/Makefile.am b/src/xz/Makefile.am
index 4bc64f3..4ff061f 100644
--- a/src/xz/Makefile.am
+++ b/src/xz/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
bin_PROGRAMS = xz
@@ -25,6 +21,8 @@ xz_SOURCES = \
options.c \
options.h \
private.h \
+ sandbox.c \
+ sandbox.h \
signals.c \
signals.h \
suffix.c \
@@ -53,7 +51,7 @@ xz_CPPFLAGS = \
-I$(top_srcdir)/src/liblzma/api \
-I$(top_builddir)/lib
-xz_LDADD = $(top_builddir)/src/liblzma/liblzma.la $(CAPSICUM_LIB)
+xz_LDADD = $(top_builddir)/src/liblzma/liblzma.la
if COND_GNULIB
xz_LDADD += $(top_builddir)/lib/libgnu.a
diff --git a/src/xz/Makefile.in b/src/xz/Makefile.in
index e6422c5..18e0151 100644
--- a/src/xz/Makefile.in
+++ b/src/xz/Makefile.in
@@ -98,8 +98,8 @@ bin_PROGRAMS = xz$(EXEEXT)
@COND_LZMALINKS_TRUE@am__append_4 = lzma unlzma lzcat
subdir = src/xz
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -127,23 +127,25 @@ PROGRAMS = $(bin_PROGRAMS)
am__xz_SOURCES_DIST = args.c args.h coder.c coder.h file_io.c \
file_io.h hardware.c hardware.h main.c main.h message.c \
message.h mytime.c mytime.h options.c options.h private.h \
- signals.c signals.h suffix.c suffix.h util.c util.h \
- ../common/tuklib_open_stdxxx.c ../common/tuklib_progname.c \
- ../common/tuklib_exit.c ../common/tuklib_mbstr_width.c \
- ../common/tuklib_mbstr_fw.c list.c list.h xz_w32res.rc
+ sandbox.c sandbox.h signals.c signals.h suffix.c suffix.h \
+ util.c util.h ../common/tuklib_open_stdxxx.c \
+ ../common/tuklib_progname.c ../common/tuklib_exit.c \
+ ../common/tuklib_mbstr_width.c ../common/tuklib_mbstr_fw.c \
+ list.c list.h xz_w32res.rc
@COND_MAIN_DECODER_TRUE@am__objects_1 = xz-list.$(OBJEXT)
@COND_W32_TRUE@am__objects_2 = xz_w32res.$(OBJEXT)
am_xz_OBJECTS = xz-args.$(OBJEXT) xz-coder.$(OBJEXT) \
xz-file_io.$(OBJEXT) xz-hardware.$(OBJEXT) xz-main.$(OBJEXT) \
xz-message.$(OBJEXT) xz-mytime.$(OBJEXT) xz-options.$(OBJEXT) \
- xz-signals.$(OBJEXT) xz-suffix.$(OBJEXT) xz-util.$(OBJEXT) \
- xz-tuklib_open_stdxxx.$(OBJEXT) xz-tuklib_progname.$(OBJEXT) \
- xz-tuklib_exit.$(OBJEXT) xz-tuklib_mbstr_width.$(OBJEXT) \
- xz-tuklib_mbstr_fw.$(OBJEXT) $(am__objects_1) $(am__objects_2)
+ xz-sandbox.$(OBJEXT) xz-signals.$(OBJEXT) xz-suffix.$(OBJEXT) \
+ xz-util.$(OBJEXT) xz-tuklib_open_stdxxx.$(OBJEXT) \
+ xz-tuklib_progname.$(OBJEXT) xz-tuklib_exit.$(OBJEXT) \
+ xz-tuklib_mbstr_width.$(OBJEXT) xz-tuklib_mbstr_fw.$(OBJEXT) \
+ $(am__objects_1) $(am__objects_2)
xz_OBJECTS = $(am_xz_OBJECTS)
am__DEPENDENCIES_1 =
xz_DEPENDENCIES = $(top_builddir)/src/liblzma/liblzma.la \
- $(am__DEPENDENCIES_1) $(am__append_3) $(am__DEPENDENCIES_1)
+ $(am__append_3) $(am__DEPENDENCIES_1)
AM_V_lt = $(am__v_lt_@AM_V@)
am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@)
am__v_lt_0 = --silent
@@ -167,8 +169,9 @@ am__depfiles_remade = ./$(DEPDIR)/xz-args.Po ./$(DEPDIR)/xz-coder.Po \
./$(DEPDIR)/xz-file_io.Po ./$(DEPDIR)/xz-hardware.Po \
./$(DEPDIR)/xz-list.Po ./$(DEPDIR)/xz-main.Po \
./$(DEPDIR)/xz-message.Po ./$(DEPDIR)/xz-mytime.Po \
- ./$(DEPDIR)/xz-options.Po ./$(DEPDIR)/xz-signals.Po \
- ./$(DEPDIR)/xz-suffix.Po ./$(DEPDIR)/xz-tuklib_exit.Po \
+ ./$(DEPDIR)/xz-options.Po ./$(DEPDIR)/xz-sandbox.Po \
+ ./$(DEPDIR)/xz-signals.Po ./$(DEPDIR)/xz-suffix.Po \
+ ./$(DEPDIR)/xz-tuklib_exit.Po \
./$(DEPDIR)/xz-tuklib_mbstr_fw.Po \
./$(DEPDIR)/xz-tuklib_mbstr_width.Po \
./$(DEPDIR)/xz-tuklib_open_stdxxx.Po \
@@ -259,7 +262,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -388,6 +390,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
@@ -408,8 +412,8 @@ top_srcdir = @top_srcdir@
xz = @xz@
xz_SOURCES = args.c args.h coder.c coder.h file_io.c file_io.h \
hardware.c hardware.h main.c main.h message.c message.h \
- mytime.c mytime.h options.c options.h private.h signals.c \
- signals.h suffix.c suffix.h util.c util.h \
+ mytime.c mytime.h options.c options.h private.h sandbox.c \
+ sandbox.h signals.c signals.h suffix.c suffix.h util.c util.h \
../common/tuklib_open_stdxxx.c ../common/tuklib_progname.c \
../common/tuklib_exit.c ../common/tuklib_mbstr_width.c \
../common/tuklib_mbstr_fw.c $(am__append_1) $(am__append_2)
@@ -421,8 +425,8 @@ xz_CPPFLAGS = \
# libgnu.a may need these libs, so this must be after libgnu.a.
-xz_LDADD = $(top_builddir)/src/liblzma/liblzma.la $(CAPSICUM_LIB) \
- $(am__append_3) $(LTLIBINTL)
+xz_LDADD = $(top_builddir)/src/liblzma/liblzma.la $(am__append_3) \
+ $(LTLIBINTL)
dist_man_MANS = xz.1
xzlinks = unxz xzcat $(am__append_4)
all: all-am
@@ -527,6 +531,7 @@ distclean-compile:
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-message.Po@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-mytime.Po@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-options.Po@am__quote@ # am--include-marker
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-sandbox.Po@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-signals.Po@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-suffix.Po@am__quote@ # am--include-marker
@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/xz-tuklib_exit.Po@am__quote@ # am--include-marker
@@ -675,6 +680,20 @@ xz-options.obj: options.c
@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o xz-options.obj `if test -f 'options.c'; then $(CYGPATH_W) 'options.c'; else $(CYGPATH_W) '$(srcdir)/options.c'; fi`
+xz-sandbox.o: sandbox.c
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT xz-sandbox.o -MD -MP -MF $(DEPDIR)/xz-sandbox.Tpo -c -o xz-sandbox.o `test -f 'sandbox.c' || echo '$(srcdir)/'`sandbox.c
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/xz-sandbox.Tpo $(DEPDIR)/xz-sandbox.Po
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='sandbox.c' object='xz-sandbox.o' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o xz-sandbox.o `test -f 'sandbox.c' || echo '$(srcdir)/'`sandbox.c
+
+xz-sandbox.obj: sandbox.c
+@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT xz-sandbox.obj -MD -MP -MF $(DEPDIR)/xz-sandbox.Tpo -c -o xz-sandbox.obj `if test -f 'sandbox.c'; then $(CYGPATH_W) 'sandbox.c'; else $(CYGPATH_W) '$(srcdir)/sandbox.c'; fi`
+@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/xz-sandbox.Tpo $(DEPDIR)/xz-sandbox.Po
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ $(AM_V_CC)source='sandbox.c' object='xz-sandbox.obj' libtool=no @AMDEPBACKSLASH@
+@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@
+@am__fastdepCC_FALSE@ $(AM_V_CC@am__nodep@)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o xz-sandbox.obj `if test -f 'sandbox.c'; then $(CYGPATH_W) 'sandbox.c'; else $(CYGPATH_W) '$(srcdir)/sandbox.c'; fi`
+
xz-signals.o: signals.c
@am__fastdepCC_TRUE@ $(AM_V_CC)$(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(xz_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT xz-signals.o -MD -MP -MF $(DEPDIR)/xz-signals.Tpo -c -o xz-signals.o `test -f 'signals.c' || echo '$(srcdir)/'`signals.c
@am__fastdepCC_TRUE@ $(AM_V_at)$(am__mv) $(DEPDIR)/xz-signals.Tpo $(DEPDIR)/xz-signals.Po
@@ -985,6 +1004,7 @@ distclean: distclean-am
-rm -f ./$(DEPDIR)/xz-message.Po
-rm -f ./$(DEPDIR)/xz-mytime.Po
-rm -f ./$(DEPDIR)/xz-options.Po
+ -rm -f ./$(DEPDIR)/xz-sandbox.Po
-rm -f ./$(DEPDIR)/xz-signals.Po
-rm -f ./$(DEPDIR)/xz-suffix.Po
-rm -f ./$(DEPDIR)/xz-tuklib_exit.Po
@@ -1049,6 +1069,7 @@ maintainer-clean: maintainer-clean-am
-rm -f ./$(DEPDIR)/xz-message.Po
-rm -f ./$(DEPDIR)/xz-mytime.Po
-rm -f ./$(DEPDIR)/xz-options.Po
+ -rm -f ./$(DEPDIR)/xz-sandbox.Po
-rm -f ./$(DEPDIR)/xz-signals.Po
-rm -f ./$(DEPDIR)/xz-suffix.Po
-rm -f ./$(DEPDIR)/xz-tuklib_exit.Po
diff --git a/src/xz/args.c b/src/xz/args.c
index 17e778c..eba1b97 100644
--- a/src/xz/args.c
+++ b/src/xz/args.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file args.c
@@ -5,10 +7,8 @@
///
/// \note Filter-specific options parsing is in options.c.
//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
@@ -83,14 +83,20 @@ parse_block_list(const char *str_const)
++count;
// Prevent an unlikely integer overflow.
- if (count > SIZE_MAX / sizeof(uint64_t) - 1)
+ if (count > SIZE_MAX / sizeof(block_list_entry) - 1)
message_fatal(_("%s: Too many arguments to --block-list"),
str);
// Allocate memory to hold all the sizes specified.
// If --block-list was specified already, its value is forgotten.
free(opt_block_list);
- opt_block_list = xmalloc((count + 1) * sizeof(uint64_t));
+ opt_block_list = xmalloc((count + 1) * sizeof(block_list_entry));
+
+ // Clear the bitmask of filter chains in use.
+ block_list_chain_mask = 0;
+
+ // Reset the largest Block size found in --block-list.
+ block_list_largest = 0;
for (size_t i = 0; i < count; ++i) {
// Locate the next comma and replace it with \0.
@@ -98,6 +104,43 @@ parse_block_list(const char *str_const)
if (p != NULL)
*p = '\0';
+ // Use the default filter chain unless overridden.
+ opt_block_list[i].chain_num = 0;
+
+ // To specify a filter chain, the block list entry may be
+ // prepended with "[filter-chain-number]:". The size is
+ // still required for every block.
+ // For instance:
+ // --block-list=2:10MiB,1:5MiB,,8MiB,0:0
+ //
+ // Translates to:
+ // 1. Block of 10 MiB using filter chain 2
+ // 2. Block of 5 MiB using filter chain 1
+ // 3. Block of 5 MiB using filter chain 1
+ // 4. Block of 8 MiB using the default filter chain
+ // 5. The last block uses the default filter chain
+ //
+ // The block list:
+ // --block-list=2:MiB,1:,0
+ //
+ // Is not allowed because the second block does not specify
+ // the block size, only the filter chain.
+ if (str[0] >= '0' && str[0] <= '9' && str[1] == ':') {
+ if (str[2] == '\0')
+ message_fatal(_("In --block-list, block "
+ "size is missing after "
+ "filter chain number '%c:'"),
+ str[0]);
+
+ const unsigned chain_num = (unsigned)(str[0] - '0');
+ opt_block_list[i].chain_num = chain_num;
+ block_list_chain_mask |= 1U << chain_num;
+ str += 2;
+ } else {
+ // This Block uses the default filter chain.
+ block_list_chain_mask |= 1U << 0;
+ }
+
if (str[0] == '\0') {
// There is no string, that is, a comma follows
// another comma. Use the previous value.
@@ -107,25 +150,39 @@ parse_block_list(const char *str_const)
assert(i > 0);
opt_block_list[i] = opt_block_list[i - 1];
} else {
- opt_block_list[i] = str_to_uint64("block-list", str,
- 0, UINT64_MAX);
+ opt_block_list[i].size = str_to_uint64("block-list",
+ str, 0, UINT64_MAX);
// Zero indicates no more new Blocks.
- if (opt_block_list[i] == 0) {
+ if (opt_block_list[i].size == 0) {
if (i + 1 != count)
message_fatal(_("0 can only be used "
"as the last element "
"in --block-list"));
- opt_block_list[i] = UINT64_MAX;
+ opt_block_list[i].size = UINT64_MAX;
}
+
+ // Remember the largest Block size in the list.
+ //
+ // NOTE: Do this after handling the special value 0
+ // because when 0 is used, we don't want to reduce
+ // the Block size of the multithreaded encoder.
+ if (block_list_largest < opt_block_list[i].size)
+ block_list_largest = opt_block_list[i].size;
}
- str = p + 1;
+ // Be standards compliant: p + 1 is undefined behavior
+ // if p == NULL. That occurs on the last iteration of
+ // the loop when we won't care about the value of str
+ // anymore anyway. That is, this is done conditionally
+ // solely for standard conformance reasons.
+ if (p != NULL)
+ str = p + 1;
}
// Terminate the array.
- opt_block_list[count] = 0;
+ opt_block_list[count].size = 0;
free(str_start);
return;
@@ -136,13 +193,26 @@ static void
parse_real(args_info *args, int argc, char **argv)
{
enum {
- OPT_X86 = INT_MIN,
+ OPT_FILTERS = INT_MIN,
+ OPT_FILTERS1,
+ OPT_FILTERS2,
+ OPT_FILTERS3,
+ OPT_FILTERS4,
+ OPT_FILTERS5,
+ OPT_FILTERS6,
+ OPT_FILTERS7,
+ OPT_FILTERS8,
+ OPT_FILTERS9,
+ OPT_FILTERS_HELP,
+
+ OPT_X86,
OPT_POWERPC,
OPT_IA64,
OPT_ARM,
OPT_ARMTHUMB,
OPT_ARM64,
OPT_SPARC,
+ OPT_RISCV,
OPT_DELTA,
OPT_LZMA1,
OPT_LZMA2,
@@ -191,7 +261,7 @@ parse_real(args_info *args, int argc, char **argv)
{ "check", required_argument, NULL, 'C' },
{ "ignore-check", no_argument, NULL, OPT_IGNORE_CHECK },
{ "block-size", required_argument, NULL, OPT_BLOCK_SIZE },
- { "block-list", required_argument, NULL, OPT_BLOCK_LIST },
+ { "block-list", required_argument, NULL, OPT_BLOCK_LIST },
{ "memlimit-compress", required_argument, NULL, OPT_MEM_COMPRESS },
{ "memlimit-decompress", required_argument, NULL, OPT_MEM_DECOMPRESS },
{ "memlimit-mt-decompress", required_argument, NULL, OPT_MEM_MT_DECOMPRESS },
@@ -206,6 +276,18 @@ parse_real(args_info *args, int argc, char **argv)
{ "best", no_argument, NULL, '9' },
// Filters
+ { "filters", optional_argument, NULL, OPT_FILTERS},
+ { "filters1", optional_argument, NULL, OPT_FILTERS1},
+ { "filters2", optional_argument, NULL, OPT_FILTERS2},
+ { "filters3", optional_argument, NULL, OPT_FILTERS3},
+ { "filters4", optional_argument, NULL, OPT_FILTERS4},
+ { "filters5", optional_argument, NULL, OPT_FILTERS5},
+ { "filters6", optional_argument, NULL, OPT_FILTERS6},
+ { "filters7", optional_argument, NULL, OPT_FILTERS7},
+ { "filters8", optional_argument, NULL, OPT_FILTERS8},
+ { "filters9", optional_argument, NULL, OPT_FILTERS9},
+ { "filters-help", optional_argument, NULL, OPT_FILTERS_HELP},
+
{ "lzma1", optional_argument, NULL, OPT_LZMA1 },
{ "lzma2", optional_argument, NULL, OPT_LZMA2 },
{ "x86", optional_argument, NULL, OPT_X86 },
@@ -215,6 +297,7 @@ parse_real(args_info *args, int argc, char **argv)
{ "armthumb", optional_argument, NULL, OPT_ARMTHUMB },
{ "arm64", optional_argument, NULL, OPT_ARM64 },
{ "sparc", optional_argument, NULL, OPT_SPARC },
+ { "riscv", optional_argument, NULL, OPT_RISCV },
{ "delta", optional_argument, NULL, OPT_DELTA },
// Other options
@@ -372,7 +455,30 @@ parse_real(args_info *args, int argc, char **argv)
opt_mode = MODE_COMPRESS;
break;
- // Filter setup
+ // --filters
+ case OPT_FILTERS:
+ coder_add_filters_from_str(optarg);
+ break;
+
+ // --filters1...--filters9
+ case OPT_FILTERS1:
+ case OPT_FILTERS2:
+ case OPT_FILTERS3:
+ case OPT_FILTERS4:
+ case OPT_FILTERS5:
+ case OPT_FILTERS6:
+ case OPT_FILTERS7:
+ case OPT_FILTERS8:
+ case OPT_FILTERS9:
+ coder_add_block_filters(optarg,
+ (size_t)(c - OPT_FILTERS));
+ break;
+
+ // --filters-help
+ case OPT_FILTERS_HELP:
+ // This doesn't return.
+ message_filters_help();
+ break;
case OPT_X86:
coder_add_filter(LZMA_FILTER_X86,
@@ -409,6 +515,11 @@ parse_real(args_info *args, int argc, char **argv)
options_bcj(optarg));
break;
+ case OPT_RISCV:
+ coder_add_filter(LZMA_FILTER_RISCV,
+ options_bcj(optarg));
+ break;
+
case OPT_DELTA:
coder_add_filter(LZMA_FILTER_DELTA,
options_delta(optarg));
@@ -516,8 +627,8 @@ parse_real(args_info *args, int argc, char **argv)
case OPT_FILES0:
if (args->files_name != NULL)
message_fatal(_("Only one file can be "
- "specified with `--files' "
- "or `--files0'."));
+ "specified with '--files' "
+ "or '--files0'."));
if (optarg == NULL) {
args->files_name = stdin_filename;
@@ -718,6 +829,39 @@ args_parse(args_info *args, int argc, char **argv)
if (opt_mode == MODE_COMPRESS && opt_format == FORMAT_AUTO)
opt_format = FORMAT_XZ;
+ // Set opt_block_list to NULL if we are not compressing to the .xz
+ // format. This option cannot be used outside of this case, and
+ // simplifies the implementation later.
+ if ((opt_mode != MODE_COMPRESS || opt_format != FORMAT_XZ)
+ && opt_block_list != NULL) {
+ message(V_WARNING, _("--block-list is ignored unless "
+ "compressing to the .xz format"));
+ free(opt_block_list);
+ opt_block_list = NULL;
+ }
+
+ // If raw format is used and a custom suffix is not provided,
+ // then only stdout mode can be used when compressing or
+ // decompressing.
+ if (opt_format == FORMAT_RAW && !suffix_is_set() && !opt_stdout
+ && (opt_mode == MODE_COMPRESS
+ || opt_mode == MODE_DECOMPRESS)) {
+ if (args->files_name != NULL)
+ message_fatal(_("With --format=raw, "
+ "--suffix=.SUF is required "
+ "unless writing to stdout"));
+
+ // If all of the filenames provided are "-" (more than one
+ // "-" could be specified) or no filenames are provided,
+ // then we are only going to be writing to standard out.
+ for (int i = optind; i < argc; i++) {
+ if (strcmp(argv[i], "-") != 0)
+ message_fatal(_("With --format=raw, "
+ "--suffix=.SUF is required "
+ "unless writing to stdout"));
+ }
+ }
+
// Compression settings need to be validated (options themselves and
// their memory usage) when compressing to any file format. It has to
// be done also when uncompressing raw data, since for raw decoding
@@ -727,14 +871,6 @@ args_parse(args_info *args, int argc, char **argv)
&& opt_mode != MODE_LIST))
coder_set_compression_settings();
- // If raw format is used and a custom suffix is not provided,
- // then only stdout mode can be used when compressing or decompressing.
- if (opt_format == FORMAT_RAW && !suffix_is_set() && !opt_stdout
- && (opt_mode == MODE_COMPRESS
- || opt_mode == MODE_DECOMPRESS))
- message_fatal(_("With --format=raw, --suffix=.SUF is "
- "required unless writing to stdout"));
-
// If no filenames are given, use stdin.
if (argv[optind] == NULL && args->files_name == NULL) {
// We don't modify or free() the "-" constant. The caller
diff --git a/src/xz/args.h b/src/xz/args.h
index a1a5930..e693ecd 100644
--- a/src/xz/args.h
+++ b/src/xz/args.h
@@ -1,12 +1,12 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file args.h
/// \brief Argument parsing
//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
diff --git a/src/xz/coder.c b/src/xz/coder.c
index 91d40ed..5e41f0d 100644
--- a/src/xz/coder.c
+++ b/src/xz/coder.c
@@ -1,16 +1,17 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file coder.c
/// \brief Compresses or uncompresses a file
//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
+#include "tuklib_integer.h"
/// Return value type for coder_init().
@@ -26,25 +27,47 @@ enum format_type opt_format = FORMAT_AUTO;
bool opt_auto_adjust = true;
bool opt_single_stream = false;
uint64_t opt_block_size = 0;
-uint64_t *opt_block_list = NULL;
-
+block_list_entry *opt_block_list = NULL;
+uint64_t block_list_largest;
+uint32_t block_list_chain_mask;
/// Stream used to communicate with liblzma
static lzma_stream strm = LZMA_STREAM_INIT;
-/// Filters needed for all encoding all formats, and also decoding in raw data
-static lzma_filter filters[LZMA_FILTERS_MAX + 1];
+/// Maximum number of filter chains. The first filter chain is the default,
+/// and 9 other filter chains can be specified with --filtersX.
+#define NUM_FILTER_CHAIN_MAX 10
+
+/// The default filter chain is in chains[0]. It is used for encoding
+/// in all supported formats and also for decdoing raw streams. The other
+/// filter chains are set by --filtersX to support changing filters with
+/// the --block-list option.
+static lzma_filter chains[NUM_FILTER_CHAIN_MAX][LZMA_FILTERS_MAX + 1];
+
+/// Bitmask indicating which filter chains are actually used when encoding
+/// in the .xz format. This is needed since the filter chains specified using
+/// --filtersX (or the default filter chain) might in reality be unneeded
+/// if they are never used in --block-list. When --block-list isn't
+/// specified, only the default filter chain is used, thus the initial
+/// value of this variable is 1U << 0 (the number of the default chain is 0).
+static uint32_t chains_used_mask = 1U << 0;
/// Input and output buffers
static io_buf in_buf;
static io_buf out_buf;
-/// Number of filters. Zero indicates that we are using a preset.
+/// Number of filters in the default filter chain. Zero indicates that
+/// we are using a preset.
static uint32_t filters_count = 0;
/// Number of the preset (0-9)
static uint32_t preset_number = LZMA_PRESET_DEFAULT;
+/// True if the current default filter chain was set using the --filters
+/// option. The filter chain is reset if a preset option (like -9) or an
+/// old-style filter option (like --lzma2) is used after a --filters option.
+static bool string_to_filter_used = false;
+
/// Integrity check type
static lzma_check check;
@@ -60,7 +83,6 @@ static bool allow_trailing_input;
static lzma_mt mt_options = {
.flags = 0,
.timeout = 300,
- .filters = filters,
};
#endif
@@ -77,14 +99,14 @@ coder_set_check(lzma_check new_check)
static void
forget_filter_chain(void)
{
- // Setting a preset makes us forget a possibly defined custom
- // filter chain.
- while (filters_count > 0) {
- --filters_count;
- free(filters[filters_count].options);
- filters[filters_count].options = NULL;
+ // Setting a preset or using --filters makes us forget
+ // the earlier custom filter chain (if any).
+ if (filters_count > 0) {
+ lzma_filters_free(chains[0], NULL);
+ filters_count = 0;
}
+ string_to_filter_used = false;
return;
}
@@ -114,9 +136,15 @@ coder_add_filter(lzma_vli id, void *options)
if (filters_count == LZMA_FILTERS_MAX)
message_fatal(_("Maximum number of filters is four"));
- filters[filters_count].id = id;
- filters[filters_count].options = options;
- ++filters_count;
+ if (string_to_filter_used)
+ forget_filter_chain();
+
+ chains[0][filters_count].id = id;
+ chains[0][filters_count].options = options;
+
+ // Terminate the filter chain with LZMA_VLI_UNKNOWN to simplify
+ // implementation of forget_filter_chain().
+ chains[0][++filters_count].id = LZMA_VLI_UNKNOWN;
// Setting a custom filter chain makes us forget the preset options.
// This makes a difference if one specifies e.g. "xz -9 --lzma2 -e"
@@ -128,6 +156,69 @@ coder_add_filter(lzma_vli id, void *options)
}
+static void
+str_to_filters(const char *str, uint32_t index, uint32_t flags)
+{
+ int error_pos;
+ const char *err = lzma_str_to_filters(str, &error_pos,
+ chains[index], flags, NULL);
+
+ if (err != NULL) {
+ char filter_num[2] = "";
+ if (index > 0)
+ filter_num[0] = '0' + index;
+
+ // FIXME? The message in err isn't translated.
+ // Including the translations in the xz translations is
+ // slightly ugly but possible. Creating a new domain for
+ // liblzma might not be worth it especially since on some
+ // OSes it adds extra dependencies to translation libraries.
+ message(V_ERROR, _("Error in --filters%s=FILTERS option:"),
+ filter_num);
+ message(V_ERROR, "%s", str);
+ message(V_ERROR, "%*s^", error_pos, "");
+ message_fatal("%s", err);
+ }
+}
+
+
+extern void
+coder_add_filters_from_str(const char *filter_str)
+{
+ // Forget presets and previously defined filter chain. See
+ // coder_add_filter() above for why preset_number must be reset too.
+ forget_filter_chain();
+ preset_number = LZMA_PRESET_DEFAULT;
+
+ string_to_filter_used = true;
+
+ // Include LZMA_STR_ALL_FILTERS so this can be used with --format=raw.
+ str_to_filters(filter_str, 0, LZMA_STR_ALL_FILTERS);
+
+ // Set the filters_count to be the number of filters converted from
+ // the string.
+ for (filters_count = 0; chains[0][filters_count].id
+ != LZMA_VLI_UNKNOWN;
+ ++filters_count) ;
+
+ assert(filters_count > 0);
+ return;
+}
+
+
+extern void
+coder_add_block_filters(const char *str, size_t slot)
+{
+ // Free old filters first, if they were previously allocated.
+ if (chains_used_mask & (1U << slot))
+ lzma_filters_free(chains[slot], NULL);
+
+ str_to_filters(str, slot, 0);
+
+ chains_used_mask |= 1U << slot;
+}
+
+
tuklib_attr_noreturn
static void
memlimit_too_small(uint64_t memory_usage)
@@ -139,6 +230,67 @@ memlimit_too_small(uint64_t memory_usage)
}
+#ifdef HAVE_ENCODERS
+/// \brief Calculate the memory usage of each filter chain.
+///
+/// \param chains_memusages If non-NULL, the memusage of the encoder
+/// or decoder for each chain is stored in
+/// this array.
+/// \param mt If non-NULL, calculate memory usage of
+/// multithreaded encoder.
+/// \param encode Whether to calculate encoder or decoder
+/// memory usage. This must be true if
+/// mt != NULL.
+///
+/// \return Return the highest memory usage of all of the filter chains.
+static uint64_t
+get_chains_memusage(uint64_t *chains_memusages, const lzma_mt *mt, bool encode)
+{
+ uint64_t max_memusage = 0;
+
+#ifdef MYTHREAD_ENABLED
+ // Copy multithreading options to a temporary struct since the
+ // "filters" member needs to be changed.
+ lzma_mt mt_local;
+ if (mt != NULL)
+ mt_local = *mt;
+#else
+ (void)mt;
+#endif
+
+ for (uint32_t i = 0; i < ARRAY_SIZE(chains); i++) {
+ if (!(chains_used_mask & (1U << i)))
+ continue;
+
+ uint64_t memusage = UINT64_MAX;
+#ifdef MYTHREAD_ENABLED
+ if (mt != NULL) {
+ assert(encode);
+ mt_local.filters = chains[i];
+ memusage = lzma_stream_encoder_mt_memusage(&mt_local);
+ } else
+#endif
+ if (encode) {
+ memusage = lzma_raw_encoder_memusage(chains[i]);
+ }
+#ifdef HAVE_DECODERS
+ else {
+ memusage = lzma_raw_decoder_memusage(chains[i]);
+ }
+#endif
+
+ if (chains_memusages != NULL)
+ chains_memusages[i] = memusage;
+
+ if (memusage > max_memusage)
+ max_memusage = memusage;
+ }
+
+ return max_memusage;
+}
+#endif
+
+
extern void
coder_set_compression_settings(void)
{
@@ -156,10 +308,56 @@ coder_set_compression_settings(void)
check = LZMA_CHECK_CRC32;
}
+#ifdef HAVE_ENCODERS
+ if (opt_block_list != NULL) {
+ // args.c ensures these.
+ assert(opt_mode == MODE_COMPRESS);
+ assert(opt_format == FORMAT_XZ);
+
+ // Find out if block_list_chain_mask has a bit set that
+ // isn't set in chains_used_mask.
+ const uint32_t missing_chains_mask
+ = (block_list_chain_mask ^ chains_used_mask)
+ & block_list_chain_mask;
+
+ // If a filter chain was specified in --block-list but no
+ // matching --filtersX option was used, exit with an error.
+ if (missing_chains_mask != 0) {
+ // Get the number of the first missing filter chain
+ // and show it in the error message.
+ const unsigned first_missing
+ = (unsigned)ctz32(missing_chains_mask);
+
+ message_fatal(_("filter chain %u used by "
+ "--block-list but not specified "
+ "with --filters%u="),
+ first_missing, first_missing);
+ }
+
+ // Omit the unused filter chains from mask of used chains.
+ //
+ // (FIXME? When built with debugging, coder_free() will free()
+ // the filter chains (except the default chain) which makes
+ // Valgrind show fewer reachable allocations. But coder_free()
+ // uses this mask to determine which chains to free. Thus it
+ // won't free the ones that are cleared here from the mask.
+ // In practice this doesn't matter.)
+ chains_used_mask &= block_list_chain_mask;
+ } else {
+ // Reset filters used mask in case --block-list is not
+ // used, but --filtersX is used.
+ chains_used_mask = 1U << 0;
+ }
+#endif
+
// Options for LZMA1 or LZMA2 in case we are using a preset.
static lzma_options_lzma opt_lzma;
- if (filters_count == 0) {
+ // The first filter in the chains[] array is for the default
+ // filter chain.
+ lzma_filter *default_filters = chains[0];
+
+ if (filters_count == 0 && chains_used_mask & 1) {
// We are using a preset. This is not a good idea in raw mode
// except when playing around with things. Different versions
// of this software may use different options in presets, and
@@ -179,46 +377,61 @@ coder_set_compression_settings(void)
message_bug();
// Use LZMA2 except with --format=lzma we use LZMA1.
- filters[0].id = opt_format == FORMAT_LZMA
+ default_filters[0].id = opt_format == FORMAT_LZMA
? LZMA_FILTER_LZMA1 : LZMA_FILTER_LZMA2;
- filters[0].options = &opt_lzma;
+ default_filters[0].options = &opt_lzma;
+
filters_count = 1;
- }
- // Terminate the filter options array.
- filters[filters_count].id = LZMA_VLI_UNKNOWN;
+ // Terminate the filter options array.
+ default_filters[1].id = LZMA_VLI_UNKNOWN;
+ }
// If we are using the .lzma format, allow exactly one filter
- // which has to be LZMA1.
+ // which has to be LZMA1. There is no need to check if the default
+ // filter chain is being used since it can only be disabled if
+ // --block-list is used, which is incompatible with FORMAT_LZMA.
if (opt_format == FORMAT_LZMA && (filters_count != 1
- || filters[0].id != LZMA_FILTER_LZMA1))
+ || default_filters[0].id != LZMA_FILTER_LZMA1))
message_fatal(_("The .lzma format supports only "
"the LZMA1 filter"));
// If we are using the .xz format, make sure that there is no LZMA1
- // filter to prevent LZMA_PROG_ERROR.
- if (opt_format == FORMAT_XZ)
+ // filter to prevent LZMA_PROG_ERROR. With the chains from --filtersX
+ // we have already ensured this by calling lzma_str_to_filters()
+ // without setting the flags that would allow non-.xz filters.
+ if (opt_format == FORMAT_XZ && chains_used_mask & 1)
for (size_t i = 0; i < filters_count; ++i)
- if (filters[i].id == LZMA_FILTER_LZMA1)
+ if (default_filters[i].id == LZMA_FILTER_LZMA1)
message_fatal(_("LZMA1 cannot be used "
"with the .xz format"));
- // Print the selected filter chain.
- message_filters_show(V_DEBUG, filters);
+ if (chains_used_mask & 1) {
+ // Print the selected default filter chain.
+ message_filters_show(V_DEBUG, default_filters);
+ }
// The --flush-timeout option requires LZMA_SYNC_FLUSH support
- // from the filter chain. Currently threaded encoder doesn't support
- // LZMA_SYNC_FLUSH so single-threaded mode must be used.
+ // from the filter chain. Currently the threaded encoder doesn't
+ // support LZMA_SYNC_FLUSH so single-threaded mode must be used.
if (opt_mode == MODE_COMPRESS && opt_flush_timeout != 0) {
- for (size_t i = 0; i < filters_count; ++i) {
- switch (filters[i].id) {
- case LZMA_FILTER_LZMA2:
- case LZMA_FILTER_DELTA:
- break;
+ for (unsigned i = 0; i < ARRAY_SIZE(chains); ++i) {
+ if (!(chains_used_mask & (1U << i)))
+ continue;
+
+ const lzma_filter *fc = chains[i];
+ for (size_t j = 0; fc[j].id != LZMA_VLI_UNKNOWN; j++) {
+ switch (fc[j].id) {
+ case LZMA_FILTER_LZMA2:
+ case LZMA_FILTER_DELTA:
+ break;
- default:
- message_fatal(_("The filter chain is "
- "incompatible with --flush-timeout"));
+ default:
+ message_fatal(_("Filter chain %u is "
+ "incompatible with "
+ "--flush-timeout"),
+ i);
+ }
}
}
@@ -229,23 +442,72 @@ coder_set_compression_settings(void)
}
}
- // Get the memory usage. Note that if --format=raw was used,
- // we can be decompressing.
+ // Get memory limit and the memory usage of the used filter chains.
+ // Note that if --format=raw was used, we can be decompressing
+ // using the default filter chain.
//
- // If multithreaded .xz compression is done, this value will be
- // replaced.
+ // If multithreaded .xz compression is done, the memory limit
+ // will be replaced.
uint64_t memory_limit = hardware_memlimit_get(opt_mode);
uint64_t memory_usage = UINT64_MAX;
+
+#ifdef HAVE_ENCODERS
+ // Memory usage for each encoder filter chain (default
+ // or --filtersX). The encoder options may need to be
+ // scaled down depending on the memory usage limit.
+ uint64_t encoder_memusages[ARRAY_SIZE(chains)];
+#endif
+
if (opt_mode == MODE_COMPRESS) {
#ifdef HAVE_ENCODERS
# ifdef MYTHREAD_ENABLED
if (opt_format == FORMAT_XZ && hardware_threads_is_mt()) {
memory_limit = hardware_memlimit_mtenc_get();
mt_options.threads = hardware_threads_get();
- mt_options.block_size = opt_block_size;
+
+ uint64_t block_size = opt_block_size;
+
+ // If opt_block_size is not set, find the maximum
+ // recommended Block size based on the filter chains
+ if (block_size == 0) {
+ for (unsigned i = 0; i < ARRAY_SIZE(chains);
+ i++) {
+ if (!(chains_used_mask & (1U << i)))
+ continue;
+
+ uint64_t size = lzma_mt_block_size(
+ chains[i]);
+
+ // If this returns an error, then one
+ // of the filter chains in use is
+ // invalid, so there is no point in
+ // progressing further.
+ if (size == UINT64_MAX)
+ message_fatal(_("Unsupported "
+ "options in filter "
+ "chain %u"), i);
+
+ if (size > block_size)
+ block_size = size;
+ }
+
+ // If --block-list was used and our current
+ // Block size exceeds the largest size
+ // in --block-list, reduce the Block size of
+ // the multithreaded encoder. The extra size
+ // would only be a waste of RAM. With a
+ // smaller Block size we might even be able
+ // to use more threads in some cases.
+ if (block_list_largest > 0 && block_size
+ > block_list_largest)
+ block_size = block_list_largest;
+ }
+
+ mt_options.block_size = block_size;
mt_options.check = check;
- memory_usage = lzma_stream_encoder_mt_memusage(
- &mt_options);
+
+ memory_usage = get_chains_memusage(encoder_memusages,
+ &mt_options, true);
if (memory_usage != UINT64_MAX)
message(V_DEBUG, _("Using up to %" PRIu32
" threads."),
@@ -253,12 +515,13 @@ coder_set_compression_settings(void)
} else
# endif
{
- memory_usage = lzma_raw_encoder_memusage(filters);
+ memory_usage = get_chains_memusage(encoder_memusages,
+ NULL, true);
}
#endif
} else {
#ifdef HAVE_DECODERS
- memory_usage = lzma_raw_decoder_memusage(filters);
+ memory_usage = lzma_raw_decoder_memusage(default_filters);
#endif
}
@@ -268,12 +531,13 @@ coder_set_compression_settings(void)
// Print memory usage info before possible dictionary
// size auto-adjusting.
//
- // NOTE: If only encoder support was built, we cannot show the
+ // NOTE: If only encoder support was built, we cannot show
// what the decoder memory usage will be.
message_mem_needed(V_DEBUG, memory_usage);
-#ifdef HAVE_DECODERS
- if (opt_mode == MODE_COMPRESS) {
- const uint64_t decmem = lzma_raw_decoder_memusage(filters);
+
+#if defined(HAVE_ENCODERS) && defined(HAVE_DECODERS)
+ if (opt_mode == MODE_COMPRESS && message_verbosity_get() >= V_DEBUG) {
+ const uint64_t decmem = get_chains_memusage(NULL, NULL, false);
if (decmem != UINT64_MAX)
message(V_DEBUG, _("Decompression will need "
"%s MiB of memory."), uint64_to_str(
@@ -300,14 +564,21 @@ coder_set_compression_settings(void)
// Reduce the number of threads by one and check
// the memory usage.
--mt_options.threads;
- memory_usage = lzma_stream_encoder_mt_memusage(
- &mt_options);
+ memory_usage = get_chains_memusage(encoder_memusages,
+ &mt_options, true);
if (memory_usage == UINT64_MAX)
message_bug();
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(
@@ -326,8 +597,11 @@ 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. "
@@ -353,7 +627,8 @@ coder_set_compression_settings(void)
// the multithreaded mode but the output
// is also different.
hardware_threads_set(1);
- memory_usage = lzma_raw_encoder_memusage(filters);
+ memory_usage = get_chains_memusage(encoder_memusages,
+ NULL, true);
message(V_WARNING, _("Switching to single-threaded mode "
"to not exceed the memory usage limit of %s MiB"),
uint64_to_str(round_up_to_mib(memory_limit), 0));
@@ -368,55 +643,85 @@ coder_set_compression_settings(void)
if (!opt_auto_adjust)
memlimit_too_small(memory_usage);
- // Look for the last filter if it is LZMA2 or LZMA1, so we can make
- // it use less RAM. With other filters we don't know what to do.
- size_t i = 0;
- while (filters[i].id != LZMA_FILTER_LZMA2
- && filters[i].id != LZMA_FILTER_LZMA1) {
- if (filters[i].id == LZMA_VLI_UNKNOWN)
- memlimit_too_small(memory_usage);
+ // Adjust each filter chain that is exceeding the memory usage limit.
+ for (unsigned i = 0; i < ARRAY_SIZE(chains); i++) {
+ // Skip unused chains.
+ if (!(chains_used_mask & (1U << i)))
+ continue;
+
+ // Skip chains that already meet the memory usage limit.
+ if (encoder_memusages[i] <= memory_limit)
+ continue;
+
+ // Look for the last filter if it is LZMA2 or LZMA1, so we
+ // can make it use less RAM. We cannot adjust other filters.
+ unsigned j = 0;
+ while (chains[i][j].id != LZMA_FILTER_LZMA2
+ && chains[i][j].id != LZMA_FILTER_LZMA1) {
+ // NOTE: This displays the too high limit of this
+ // particular filter chain. If multiple chains are
+ // specified and another one would need more then
+ // this message could be confusing. As long as LZMA2
+ // is the only memory hungry filter in .xz this
+ // doesn't matter at all in practice.
+ //
+ // FIXME? However, it's sort of odd still if we had
+ // switched from multithreaded mode to single-threaded
+ // mode because single-threaded produces different
+ // output. So the messages could perhaps be clearer.
+ // Another case of this is a few lines below.
+ if (chains[i][j].id == LZMA_VLI_UNKNOWN)
+ memlimit_too_small(encoder_memusages[i]);
+
+ ++j;
+ }
- ++i;
- }
+ // Decrease the dictionary size until we meet the memory
+ // usage limit. First round down to full mebibytes.
+ lzma_options_lzma *opt = chains[i][j].options;
+ const uint32_t orig_dict_size = opt->dict_size;
+ opt->dict_size &= ~((UINT32_C(1) << 20) - 1);
- // Decrease the dictionary size until we meet the memory
- // usage limit. First round down to full mebibytes.
- lzma_options_lzma *opt = filters[i].options;
- const uint32_t orig_dict_size = opt->dict_size;
- opt->dict_size &= ~((UINT32_C(1) << 20) - 1);
- while (true) {
- // If it is below 1 MiB, auto-adjusting failed. We could be
- // more sophisticated and scale it down even more, but let's
- // see if many complain about this version.
- //
- // FIXME: Displays the scaled memory usage instead
- // of the original.
- if (opt->dict_size < (UINT32_C(1) << 20))
- memlimit_too_small(memory_usage);
+ while (true) {
+ // If it is below 1 MiB, auto-adjusting failed.
+ //
+ // FIXME? See the FIXME a few lines above.
+ if (opt->dict_size < (UINT32_C(1) << 20))
+ memlimit_too_small(encoder_memusages[i]);
- memory_usage = lzma_raw_encoder_memusage(filters);
- if (memory_usage == UINT64_MAX)
- message_bug();
+ encoder_memusages[i]
+ = lzma_raw_encoder_memusage(chains[i]);
+ if (encoder_memusages[i] == UINT64_MAX)
+ message_bug();
- // Accept it if it is low enough.
- if (memory_usage <= memory_limit)
- break;
+ // Accept it if it is low enough.
+ if (encoder_memusages[i] <= memory_limit)
+ break;
- // Otherwise 1 MiB down and try again. I hope this
- // isn't too slow method for cases where the original
- // dict_size is very big.
- opt->dict_size -= UINT32_C(1) << 20;
- }
+ // Otherwise adjust it 1 MiB down and try again.
+ opt->dict_size -= UINT32_C(1) << 20;
+ }
- // Tell the user that we decreased the dictionary size.
- message(V_WARNING, _("Adjusted LZMA%c dictionary size "
- "from %s MiB to %s MiB to not exceed "
- "the memory usage limit of %s MiB"),
- filters[i].id == LZMA_FILTER_LZMA2
- ? '2' : '1',
- uint64_to_str(orig_dict_size >> 20, 0),
- uint64_to_str(opt->dict_size >> 20, 1),
- uint64_to_str(round_up_to_mib(memory_limit), 2));
+ // Tell the user that we decreased the dictionary size.
+ // The message is slightly different between the default
+ // filter chain (0) or and chains from --filtersX.
+ const char lzma_num = chains[i][j].id == LZMA_FILTER_LZMA2
+ ? '2' : '1';
+ const char *from_size = uint64_to_str(orig_dict_size >> 20, 0);
+ const char *to_size = uint64_to_str(opt->dict_size >> 20, 1);
+ const char *limit_size = uint64_to_str(round_up_to_mib(
+ memory_limit), 2);
+ if (i == 0)
+ message(V_WARNING, _("Adjusted LZMA%c dictionary "
+ "size from %s MiB to %s MiB to not exceed the "
+ "memory usage limit of %s MiB"),
+ lzma_num, from_size, to_size, limit_size);
+ else
+ message(V_WARNING, _("Adjusted LZMA%c dictionary size "
+ "for --filters%u from %s MiB to %s MiB to not "
+ "exceed the memory usage limit of %s MiB"),
+ lzma_num, i, from_size, to_size, limit_size);
+ }
#endif
return;
@@ -512,6 +817,13 @@ coder_init(file_pair *pair)
// These will be handled later in this function.
allow_trailing_input = false;
+ // Set the first filter chain. If the --block-list option is not
+ // used then use the default filter chain (chains[0]).
+ // Otherwise, use first filter chain from the block list.
+ lzma_filter *active_filters = opt_block_list == NULL
+ ? chains[0]
+ : chains[opt_block_list[0].chain_num];
+
if (opt_mode == MODE_COMPRESS) {
#ifdef HAVE_ENCODERS
switch (opt_format) {
@@ -522,17 +834,19 @@ coder_init(file_pair *pair)
case FORMAT_XZ:
# ifdef MYTHREAD_ENABLED
+ mt_options.filters = active_filters;
if (hardware_threads_is_mt())
ret = lzma_stream_encoder_mt(
&strm, &mt_options);
else
# endif
ret = lzma_stream_encoder(
- &strm, filters, check);
+ &strm, active_filters, check);
break;
case FORMAT_LZMA:
- ret = lzma_alone_encoder(&strm, filters[0].options);
+ ret = lzma_alone_encoder(&strm,
+ active_filters[0].options);
break;
# ifdef HAVE_LZIP_DECODER
@@ -544,7 +858,7 @@ coder_init(file_pair *pair)
# endif
case FORMAT_RAW:
- ret = lzma_raw_encoder(&strm, filters);
+ ret = lzma_raw_encoder(&strm, active_filters);
break;
}
#endif
@@ -668,7 +982,7 @@ coder_init(file_pair *pair)
case FORMAT_RAW:
// Memory usage has already been checked in
// coder_set_compression_settings().
- ret = lzma_raw_decoder(&strm, filters);
+ ret = lzma_raw_decoder(&strm, active_filters);
break;
}
@@ -716,6 +1030,7 @@ coder_init(file_pair *pair)
}
+#ifdef HAVE_ENCODERS
/// Resolve conflicts between opt_block_size and opt_block_list in single
/// threaded mode. We want to default to opt_block_list, except when it is
/// larger than opt_block_size. If this is the case for the current Block
@@ -746,12 +1061,39 @@ split_block(uint64_t *block_remaining,
} else {
// The Block at *list_pos has been finished. Go to the next
- // entry in the list. If the end of the list has been reached,
- // reuse the size of the last Block.
- if (opt_block_list[*list_pos + 1] != 0)
+ // entry in the list. If the end of the list has been
+ // reached, reuse the size and filters of the last Block.
+ if (opt_block_list[*list_pos + 1].size != 0) {
++*list_pos;
- *block_remaining = opt_block_list[*list_pos];
+ // Update the filters if needed.
+ if (opt_block_list[*list_pos - 1].chain_num
+ != opt_block_list[*list_pos].chain_num) {
+ const unsigned chain_num
+ = opt_block_list[*list_pos].chain_num;
+ const lzma_filter *next = chains[chain_num];
+ const lzma_ret ret = lzma_filters_update(
+ &strm, next);
+
+ if (ret != LZMA_OK) {
+ // This message is only possible if
+ // the filter chain has unsupported
+ // options since the filter chain is
+ // validated using
+ // lzma_raw_encoder_memusage() or
+ // lzma_stream_encoder_mt_memusage().
+ // Some options are not validated until
+ // the encoders are initialized.
+ message_fatal(
+ _("Error changing to "
+ "filter chain %u: %s"),
+ chain_num,
+ message_strm(ret));
+ }
+ }
+ }
+
+ *block_remaining = opt_block_list[*list_pos].size;
// If in single-threaded mode, split up the Block if needed.
// This is not needed in multi-threaded mode because liblzma
@@ -764,6 +1106,7 @@ split_block(uint64_t *block_remaining,
}
}
}
+#endif
static bool
@@ -796,6 +1139,7 @@ coder_normal(file_pair *pair)
// Assume that something goes wrong.
bool success = false;
+#ifdef HAVE_ENCODERS
// block_remaining indicates how many input bytes to encode before
// finishing the current .xz Block. The Block size is set with
// --block-size=SIZE and --block-list. They have an effect only when
@@ -829,15 +1173,18 @@ coder_normal(file_pair *pair)
// output is still not identical because in single-threaded
// mode the size info isn't written into Block Headers.
if (opt_block_list != NULL) {
- if (block_remaining < opt_block_list[list_pos]) {
+ if (block_remaining < opt_block_list[list_pos].size) {
assert(!hardware_threads_is_mt());
- next_block_remaining = opt_block_list[list_pos]
+ next_block_remaining =
+ opt_block_list[list_pos].size
- block_remaining;
} else {
- block_remaining = opt_block_list[list_pos];
+ block_remaining =
+ opt_block_list[list_pos].size;
}
}
}
+#endif
strm.next_out = out_buf.u8;
strm.avail_out = IO_BUFFER_SIZE;
@@ -847,17 +1194,22 @@ coder_normal(file_pair *pair)
// flushing or finishing.
if (strm.avail_in == 0 && action == LZMA_RUN) {
strm.next_in = in_buf.u8;
- strm.avail_in = io_read(pair, &in_buf,
- my_min(block_remaining,
- IO_BUFFER_SIZE));
+#ifdef HAVE_ENCODERS
+ const size_t read_size = my_min(block_remaining,
+ IO_BUFFER_SIZE);
+#else
+ const size_t read_size = IO_BUFFER_SIZE;
+#endif
+ strm.avail_in = io_read(pair, &in_buf, read_size);
if (strm.avail_in == SIZE_MAX)
break;
if (pair->src_eof) {
action = LZMA_FINISH;
-
- } else if (block_remaining != UINT64_MAX) {
+ }
+#ifdef HAVE_ENCODERS
+ else if (block_remaining != UINT64_MAX) {
// Start a new Block after every
// opt_block_size bytes of input.
block_remaining -= strm.avail_in;
@@ -867,6 +1219,7 @@ coder_normal(file_pair *pair)
if (action == LZMA_RUN && pair->flush_needed)
action = LZMA_SYNC_FLUSH;
+#endif
}
// Let liblzma do the actual work.
@@ -878,6 +1231,7 @@ coder_normal(file_pair *pair)
break;
}
+#ifdef HAVE_ENCODERS
if (ret == LZMA_STREAM_END && (action == LZMA_SYNC_FLUSH
|| action == LZMA_FULL_BARRIER)) {
if (action == LZMA_SYNC_FLUSH) {
@@ -907,8 +1261,9 @@ coder_normal(file_pair *pair)
// Start a new Block after LZMA_FULL_FLUSH or continue
// the same block after LZMA_SYNC_FLUSH.
action = LZMA_RUN;
-
- } else if (ret != LZMA_OK) {
+ } else
+#endif
+ if (ret != LZMA_OK) {
// Determine if the return value indicates that we
// won't continue coding. LZMA_NO_CHECK would be
// here too if LZMA_TELL_ANY_CHECK was used.
@@ -1103,6 +1458,16 @@ coder_run(const char *filename)
extern void
coder_free(void)
{
+ // Free starting from the second filter chain since the default
+ // filter chain may have its options set from a static variable
+ // in coder_set_compression_settings(). Since this is only run in
+ // debug mode and will be freed when the process ends anyway, we
+ // don't worry about freeing it.
+ for (uint32_t i = 1; i < ARRAY_SIZE(chains); i++) {
+ if (chains_used_mask & (1U << i))
+ lzma_filters_free(chains[i], NULL);
+ }
+
lzma_end(&strm);
return;
}
diff --git a/src/xz/coder.h b/src/xz/coder.h
index b4f43a2..96755f3 100644
--- a/src/xz/coder.h
+++ b/src/xz/coder.h
@@ -1,12 +1,12 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file coder.h
/// \brief Compresses or uncompresses a file
//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
@@ -30,6 +30,16 @@ enum format_type {
};
+/// Array of these hold the entries specified with --block-list.
+typedef struct {
+ /// Uncompressed size of the Block
+ uint64_t size;
+
+ /// Filter chain to use for this Block (chains[chain_num])
+ unsigned chain_num;
+} block_list_entry;
+
+
/// Operation mode of the command line tool. This is set in args.c and read
/// in several files.
extern enum operation_mode opt_mode;
@@ -50,9 +60,21 @@ extern bool opt_single_stream;
/// of input. This has an effect only when compressing to the .xz format.
extern uint64_t opt_block_size;
-/// This is non-NULL if --block-list was used. This contains the Block sizes
-/// as an array that is terminated with 0.
-extern uint64_t *opt_block_list;
+/// List of block size and filter chain pointer pairs.
+extern block_list_entry *opt_block_list;
+
+/// Size of the largest Block that was specified in --block-list.
+/// This is used to limit the block_size option of multithreaded encoder.
+/// It's waste of memory to specify a too large block_size and reducing
+/// it might even allow using more threads in some cases.
+///
+/// NOTE: If the last entry in --block-list is the special value of 0
+/// (which gets converted to UINT64_MAX), it counts here as UINT64_MAX too.
+/// This way the multithreaded encoder's Block size won't be reduced.
+extern uint64_t block_list_largest;
+
+/// Bitmask indicating which filter chains we specified in --block-list.
+extern uint32_t block_list_chain_mask;
/// Set the integrity check type used when compressing
extern void coder_set_check(lzma_check check);
@@ -77,3 +99,9 @@ extern void coder_run(const char *filename);
/// Free the memory allocated for the coder and kill the worker threads.
extern void coder_free(void);
#endif
+
+/// Create filter chain from string
+extern void coder_add_filters_from_str(const char *filter_str);
+
+/// Add or overwrite a filter that can be used by the block-list.
+extern void coder_add_block_filters(const char *str, size_t slot);
diff --git a/src/xz/file_io.c b/src/xz/file_io.c
index 2828029..678a9a5 100644
--- a/src/xz/file_io.c
+++ b/src/xz/file_io.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file file_io.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -29,15 +28,33 @@ static bool warn_fchown;
# include <utime.h>
#endif
-#ifdef HAVE_CAPSICUM
-# ifdef HAVE_SYS_CAPSICUM_H
-# include <sys/capsicum.h>
+#include "tuklib_open_stdxxx.h"
+
+#ifdef _MSC_VER
+# ifdef _WIN64
+ typedef __int64 ssize_t;
# else
-# include <sys/capability.h>
+ typedef int ssize_t;
# endif
-#endif
-#include "tuklib_open_stdxxx.h"
+ typedef int mode_t;
+# define S_IRUSR _S_IREAD
+# define S_IWUSR _S_IWRITE
+
+# define setmode _setmode
+# define open _open
+# define close _close
+# define lseek _lseeki64
+# define unlink _unlink
+
+ // The casts are to silence warnings.
+ // The sizes are known to be small enough.
+# define read(fd, buf, size) _read(fd, buf, (unsigned int)(size))
+# define write(fd, buf, size) _write(fd, buf, (unsigned int)(size))
+
+# define S_ISDIR(m) (((m) & _S_IFMT) == _S_IFDIR)
+# define S_ISREG(m) (((m) & _S_IFMT) == _S_IFREG)
+#endif
#ifndef O_BINARY
# define O_BINARY 0
@@ -66,11 +83,6 @@ typedef enum {
/// If true, try to create sparse files when decompressing.
static bool try_sparse = true;
-#ifdef ENABLE_SANDBOX
-/// True if the conditions for sandboxing (described in main()) have been met.
-static bool sandbox_allowed = false;
-#endif
-
#ifndef TUKLIB_DOSLIKE
/// File status flags of standard input. This is used by io_open_src()
/// and io_close_src().
@@ -155,105 +167,6 @@ io_no_sparse(void)
}
-#ifdef ENABLE_SANDBOX
-extern void
-io_allow_sandbox(void)
-{
- sandbox_allowed = true;
- return;
-}
-
-
-/// Enables operating-system-specific sandbox if it is possible.
-/// src_fd is the file descriptor of the input file.
-static void
-io_sandbox_enter(int src_fd)
-{
- if (!sandbox_allowed) {
- // This message is more often annoying than useful so
- // it's commented out. It can be useful when developing
- // the sandboxing code.
- //message(V_DEBUG, _("Sandbox is disabled due "
- // "to incompatible command line arguments"));
- return;
- }
-
- const char dummy_str[] = "x";
-
- // Try to ensure that both libc and xz locale files have been
- // loaded when NLS is enabled.
- snprintf(NULL, 0, "%s%s", _(dummy_str), strerror(EINVAL));
-
- // Try to ensure that iconv data files needed for handling multibyte
- // characters have been loaded. This is needed at least with glibc.
- tuklib_mbstr_width(dummy_str, NULL);
-
-#ifdef HAVE_CAPSICUM
- // Capsicum needs FreeBSD 10.0 or later.
- cap_rights_t rights;
-
- if (cap_enter())
- goto error;
-
- if (cap_rights_limit(src_fd, cap_rights_init(&rights,
- CAP_EVENT, CAP_FCNTL, CAP_LOOKUP, CAP_READ, CAP_SEEK)))
- goto error;
-
- if (src_fd != STDIN_FILENO && cap_rights_limit(
- STDIN_FILENO, cap_rights_clear(&rights)))
- goto error;
-
- if (cap_rights_limit(STDOUT_FILENO, cap_rights_init(&rights,
- CAP_EVENT, CAP_FCNTL, CAP_FSTAT, CAP_LOOKUP,
- CAP_WRITE, CAP_SEEK)))
- goto error;
-
- if (cap_rights_limit(STDERR_FILENO, cap_rights_init(&rights,
- CAP_WRITE)))
- goto error;
-
- if (cap_rights_limit(user_abort_pipe[0], cap_rights_init(&rights,
- CAP_EVENT)))
- goto error;
-
- if (cap_rights_limit(user_abort_pipe[1], cap_rights_init(&rights,
- CAP_WRITE)))
- goto error;
-
-#elif defined(HAVE_PLEDGE)
- // pledge() was introduced in OpenBSD 5.9.
- //
- // main() unconditionally calls pledge() with fairly relaxed
- // promises which work in all situations. Here we make the
- // sandbox more strict.
- if (pledge("stdio", ""))
- goto error;
-
- (void)src_fd;
-
-#else
-# error ENABLE_SANDBOX is defined but no sandboxing method was found.
-#endif
-
- // This message is annoying in xz -lvv.
- //message(V_DEBUG, _("Sandbox was successfully enabled"));
- return;
-
-error:
-#ifdef HAVE_CAPSICUM
- // If a kernel is configured without capability mode support or
- // used in an emulator that does not implement the capability
- // system calls, then the Capsicum system calls will fail and set
- // errno to ENOSYS. In that case xz will silently run without
- // the sandbox.
- if (errno == ENOSYS)
- return;
-#endif
- message_fatal(_("Failed to enable the sandbox"));
-}
-#endif // ENABLE_SANDBOX
-
-
#ifndef TUKLIB_DOSLIKE
/// \brief Waits for input or output to become available or for a signal
///
@@ -407,7 +320,7 @@ io_copy_attrs(const file_pair *pair)
message_warning(_("%s: Cannot set the file group: %s"),
pair->dest_name, strerror(errno));
// We can still safely copy some additional permissions:
- // `group' must be at least as strict as `other' and
+ // 'group' must be at least as strict as 'other' and
// also vice versa.
//
// NOTE: After this, the owner of the source file may
@@ -809,7 +722,8 @@ io_open_src(const char *src_name)
#ifdef ENABLE_SANDBOX
if (!error)
- io_sandbox_enter(pair.src_fd);
+ sandbox_enable_strict_if_allowed(pair.src_fd,
+ user_abort_pipe[0], user_abort_pipe[1]);
#endif
return error ? NULL : &pair;
diff --git a/src/xz/file_io.h b/src/xz/file_io.h
index 6992efa..ae7e2f3 100644
--- a/src/xz/file_io.h
+++ b/src/xz/file_io.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file file_io.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
// Some systems have suboptimal BUFSIZ. Use a bit bigger value on them.
@@ -18,6 +17,16 @@
# define IO_BUFFER_SIZE (BUFSIZ & ~7U)
#endif
+#ifdef _MSC_VER
+ // The first one renames both "struct stat" -> "struct _stat64"
+ // and stat() -> _stat64(). The documentation mentions only
+ // "struct __stat64", not "struct _stat64", but the latter
+ // works too.
+# define stat _stat64
+# define fstat _fstat64
+# define off_t __int64
+#endif
+
/// is_sparse() accesses the buffer as uint64_t for maximum speed.
/// The u32 and u64 members must only be access through this union
@@ -90,12 +99,6 @@ extern void io_write_to_user_abort_pipe(void);
extern void io_no_sparse(void);
-#ifdef ENABLE_SANDBOX
-/// \brief main() calls this if conditions for sandboxing have been met.
-extern void io_allow_sandbox(void);
-#endif
-
-
/// \brief Open the source file
extern file_pair *io_open_src(const char *src_name);
diff --git a/src/xz/hardware.c b/src/xz/hardware.c
index c694882..952652f 100644
--- a/src/xz/hardware.c
+++ b/src/xz/hardware.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file hardware.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -15,7 +14,7 @@
/// Maximum number of worker threads. This can be set with
/// the --threads=NUM command line option.
-static uint32_t threads_max = 1;
+static uint32_t threads_max;
/// True when the number of threads is automatically determined based
/// on the available hardware threads.
@@ -334,5 +333,9 @@ hardware_init(void)
memlimit_mt_default = mem_ceiling;
#endif
+ // Enable threaded mode by default. xz 5.4.x and older
+ // used single-threaded mode by default.
+ hardware_threads_set(0);
+
return;
}
diff --git a/src/xz/hardware.h b/src/xz/hardware.h
index a67b26e..25b351e 100644
--- a/src/xz/hardware.h
+++ b/src/xz/hardware.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file hardware.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// Initialize some hardware-specific variables, which are needed by other
diff --git a/src/xz/list.c b/src/xz/list.c
index 86c3a76..ca9cf03 100644
--- a/src/xz/list.c
+++ b/src/xz/list.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file list.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -544,11 +543,21 @@ parse_block_header(file_pair *pair, const lzma_index_iter *iter,
xfi->memusage_max = bhi->memusage;
// Determine the minimum XZ Utils version that supports this Block.
+ // - RISC-V filter needs 5.6.0.
//
// - ARM64 filter needs 5.4.0.
//
// - 5.0.0 doesn't support empty LZMA2 streams and thus empty
// Blocks that use LZMA2. This decoder bug was fixed in 5.0.2.
+ if (xfi->min_version < 50060002U) {
+ for (size_t i = 0; filters[i].id != LZMA_VLI_UNKNOWN; ++i) {
+ if (filters[i].id == LZMA_FILTER_RISCV) {
+ xfi->min_version = 50060002U;
+ break;
+ }
+ }
+ }
+
if (xfi->min_version < 50040002U) {
for (size_t i = 0; filters[i].id != LZMA_VLI_UNKNOWN; ++i) {
if (filters[i].id == LZMA_FILTER_ARM64) {
@@ -1266,10 +1275,22 @@ list_totals(void)
extern void
list_file(const char *filename)
{
- if (opt_format != FORMAT_XZ && opt_format != FORMAT_AUTO)
- message_fatal(_("--list works only on .xz files "
+ if (opt_format != FORMAT_XZ && opt_format != FORMAT_AUTO) {
+ // The 'lzmainfo' message is printed only when --format=lzma
+ // is used (it is implied if using "lzma" as the command
+ // name). Thus instead of using message_fatal(), print
+ // the messages separately and then call tuklib_exit()
+ // like message_fatal() does.
+ message(V_ERROR, _("--list works only on .xz files "
"(--format=xz or --format=auto)"));
+ if (opt_format == FORMAT_LZMA)
+ message(V_ERROR,
+ _("Try 'lzmainfo' with .lzma files."));
+
+ tuklib_exit(E_ERROR, E_ERROR, false);
+ }
+
message_filename(filename);
if (filename == stdin_filename) {
diff --git a/src/xz/list.h b/src/xz/list.h
index a4c6ec7..805880d 100644
--- a/src/xz/list.h
+++ b/src/xz/list.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file list.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// \brief List information about the given .xz file
diff --git a/src/xz/main.c b/src/xz/main.c
index c9c3dec..71b5ef7 100644
--- a/src/xz/main.c
+++ b/src/xz/main.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file main.c
@@ -5,14 +7,12 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
#include <ctype.h>
+
/// Exit status to use. This can be changed with set_exit_status().
static enum exit_status_type exit_status = E_SUCCESS;
@@ -119,8 +119,8 @@ read_name(const args_info *args)
// newlines.
message_error(_("%s: Null character found when "
"reading filenames; maybe you meant "
- "to use `--files0' instead "
- "of `--files'?"), args->files_name);
+ "to use '--files0' instead "
+ "of '--files'?"), args->files_name);
return NULL;
}
@@ -142,35 +142,38 @@ read_name(const args_info *args)
int
main(int argc, char **argv)
{
-#ifdef HAVE_PLEDGE
- // OpenBSD's pledge(2) sandbox
- //
- // Unconditionally enable sandboxing with fairly relaxed promises.
- // This is still way better than having no sandbox at all. :-)
- // More strict promises will be made later in file_io.c if possible.
- if (pledge("stdio rpath wpath cpath fattr", "")) {
- // Don't translate the string or use message_fatal() as
- // those haven't been initialized yet.
- fprintf(stderr, "%s: Failed to enable the sandbox\n", argv[0]);
- return E_ERROR;
- }
-#endif
-
#if defined(_WIN32) && !defined(__CYGWIN__)
InitializeCriticalSection(&exit_status_cs);
#endif
- // Set up the progname variable.
+ // Set up the progname variable needed for messages.
tuklib_progname_init(argv);
// Initialize the file I/O. This makes sure that
// stdin, stdout, and stderr are something valid.
+ // This must be done before we might open any files
+ // even indirectly like locale and gettext initializations.
io_init();
+#ifdef ENABLE_SANDBOX
+ // Enable such sandboxing that can always be enabled.
+ // This requires that progname has been set up.
+ // It's also good that io_init() has been called because it
+ // might need to do things that the initial sandbox won't allow.
+ // Otherwise this should be called as early as possible.
+ //
+ // NOTE: Calling this before tuklib_gettext_init() means that
+ // translated error message won't be available if sandbox
+ // initialization fails. However, sandbox_init() shouldn't
+ // fail and this order simply feels better.
+ sandbox_init();
+#endif
+
// Set up the locale and message translations.
tuklib_gettext_init(PACKAGE, LOCALEDIR);
- // Initialize handling of error/warning/other messages.
+ // Initialize progress message handling. It's not always needed
+ // but it's simpler to do this unconditionally.
message_init();
// Set hardware-dependent default values. These can be overridden
@@ -220,21 +223,41 @@ main(int argc, char **argv)
signals_init();
#ifdef ENABLE_SANDBOX
- // Set a flag that sandboxing is allowed if all these are true:
- // - --files or --files0 wasn't used.
- // - There is exactly one input file or we are reading from stdin.
- // - We won't create any files: output goes to stdout or --test
- // or --list was used. Note that --test implies opt_stdout = true
- // but --list doesn't.
+ // Read-only sandbox can be enabled if we won't create or delete
+ // any files:
//
- // This is obviously not ideal but it was easy to implement and
- // it covers the most common use cases.
+ // - --stdout, --test, or --list was used. Note that --test
+ // implies opt_stdout = true but --list doesn't.
//
- // TODO: Make sandboxing work for other situations too.
- if (args.files_name == NULL && args.arg_count == 1
- && (opt_stdout || strcmp("-", args.arg_names[0]) == 0
- || opt_mode == MODE_LIST))
- io_allow_sandbox();
+ // - Output goes to stdout because --files or --files0 wasn't used
+ // and no arguments were given on the command line or the
+ // arguments are all "-" (indicating standard input).
+ bool to_stdout_only = opt_stdout || opt_mode == MODE_LIST;
+ if (!to_stdout_only && args.files_name == NULL) {
+ // If all of the filenames provided are "-" (more than one
+ // "-" could be specified), then we are only going to be
+ // writing to standard output. Note that if no filename args
+ // were provided, args.c puts a single "-" in arg_names[0].
+ to_stdout_only = true;
+
+ for (unsigned i = 0; i < args.arg_count; ++i) {
+ if (strcmp("-", args.arg_names[i]) != 0) {
+ to_stdout_only = false;
+ break;
+ }
+ }
+ }
+
+ if (to_stdout_only) {
+ sandbox_enable_read_only();
+
+ // Allow strict sandboxing if we are processing exactly one
+ // file to standard output. This requires that --files or
+ // --files0 wasn't specified (an unknown number of filenames
+ // could be provided that way).
+ if (args.files_name == NULL && args.arg_count == 1)
+ sandbox_allow_strict();
+ }
#endif
// coder_run() handles compression, decompression, and testing.
diff --git a/src/xz/main.h b/src/xz/main.h
index 323f2f7..a8a1b45 100644
--- a/src/xz/main.h
+++ b/src/xz/main.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file main.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// Possible exit status values. These are the same as used by gzip and bzip2.
diff --git a/src/xz/message.c b/src/xz/message.c
index abf30ad..deafdb4 100644
--- a/src/xz/message.c
+++ b/src/xz/message.c
@@ -1,12 +1,12 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file message.c
/// \brief Printing messages
//
-// Author: Lasse Collin
-//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
+// Authors: Lasse Collin
+// Jia Tan
//
///////////////////////////////////////////////////////////////////////////////
@@ -42,7 +42,7 @@ static bool current_filename_printed = false;
/// True if we should print progress indicator and update it automatically
/// if also verbose >= V_VERBOSE.
-static bool progress_automatic;
+static bool progress_automatic = false;
/// True if message_progress_start() has been called but
/// message_progress_end() hasn't been called yet.
@@ -119,26 +119,7 @@ message_init(void)
// exception, even if --verbose was not used, user can send SIGALRM
// to make us print progress information once without automatic
// updating.
- progress_automatic = isatty(STDERR_FILENO);
-
- // Commented out because COLUMNS is rarely exported to environment.
- // Most users have at least 80 columns anyway, let's think something
- // fancy here if enough people complain.
-/*
- if (progress_automatic) {
- // stderr is a terminal. Check the COLUMNS environment
- // variable to see if the terminal is wide enough. If COLUMNS
- // doesn't exist or it has some unparsable value, we assume
- // that the terminal is wide enough.
- const char *columns_str = getenv("COLUMNS");
- if (columns_str != NULL) {
- char *endptr;
- const long columns = strtol(columns_str, &endptr, 10);
- if (*endptr != '\0' || columns < 80)
- progress_automatic = false;
- }
- }
-*/
+ progress_automatic = is_tty(STDERR_FILENO);
#ifdef SIGALRM
// Establish the signal handlers which set a flag to tell us that
@@ -932,7 +913,7 @@ message_try_help(void)
{
// Print this with V_WARNING instead of V_ERROR to prevent it from
// showing up when --quiet has been specified.
- message(V_WARNING, _("Try `%s --help' for more information."),
+ message(V_WARNING, _("Try '%s --help' for more information."),
progname);
return;
}
@@ -994,7 +975,7 @@ message_help(bool long_help)
" ignore possible remaining input data"));
puts(_(
" --no-sparse do not create sparse files when decompressing\n"
-" -S, --suffix=.SUF use the suffix `.SUF' on compressed files\n"
+" -S, --suffix=.SUF use the suffix '.SUF' on compressed files\n"
" --files[=FILE] read filenames to process from FILE; if FILE is\n"
" omitted, filenames are read from the standard input;\n"
" filenames must be terminated with the newline character\n"
@@ -1005,9 +986,9 @@ message_help(bool long_help)
puts(_("\n Basic file format and compression options:\n"));
puts(_(
" -F, --format=FMT file format to encode or decode; possible values are\n"
-" `auto' (default), `xz', `lzma', `lzip', and `raw'\n"
-" -C, --check=CHECK integrity check type: `none' (use with caution),\n"
-" `crc32', `crc64' (default), or `sha256'"));
+" 'auto' (default), 'xz', 'lzma', 'lzip', and 'raw'\n"
+" -C, --check=CHECK integrity check type: 'none' (use with caution),\n"
+" 'crc32', 'crc64' (default), or 'sha256'"));
puts(_(
" --ignore-check don't verify the integrity check when decompressing"));
}
@@ -1021,8 +1002,8 @@ message_help(bool long_help)
" does not affect decompressor memory requirements"));
puts(_(
-" -T, --threads=NUM use at most NUM threads; the default is 1; set to 0\n"
-" to use as many threads as there are processor cores"));
+" -T, --threads=NUM use at most NUM threads; the default is 0 which uses\n"
+" as many threads as there are processor cores"));
if (long_help) {
puts(_(
@@ -1030,9 +1011,11 @@ message_help(bool long_help)
" start a new .xz block after every SIZE bytes of input;\n"
" use this to set the block size for threaded compression"));
puts(_(
-" --block-list=SIZES\n"
+" --block-list=BLOCKS\n"
" start a new .xz block after the given comma-separated\n"
-" intervals of uncompressed data"));
+" intervals of uncompressed data; optionally, specify a\n"
+" filter chain number (0-9) followed by a ':' before the\n"
+" uncompressed data size"));
puts(_(
" --flush-timeout=TIMEOUT\n"
" when compressing, if more than TIMEOUT milliseconds has\n"
@@ -1057,6 +1040,23 @@ message_help(bool long_help)
puts(_(
"\n Custom filter chain for compression (alternative for using presets):"));
+ puts(_(
+"\n"
+" --filters=FILTERS set the filter chain using the liblzma filter string\n"
+" syntax; use --filters-help for more information"
+ ));
+
+ puts(_(
+" --filters1=FILTERS ... --filters9=FILTERS\n"
+" set additional filter chains using the liblzma filter\n"
+" string syntax to use with --block-list"
+ ));
+
+ puts(_(
+" --filters-help display more information about the liblzma filter string\n"
+" syntax and exit."
+ ));
+
#if defined(HAVE_ENCODER_LZMA1) || defined(HAVE_DECODER_LZMA1) \
|| defined(HAVE_ENCODER_LZMA2) || defined(HAVE_DECODER_LZMA2)
// TRANSLATORS: The word "literal" in "literal context bits"
@@ -1087,6 +1087,7 @@ message_help(bool long_help)
" --powerpc[=OPTS] PowerPC BCJ filter (big endian only)\n"
" --ia64[=OPTS] IA-64 (Itanium) BCJ filter\n"
" --sparc[=OPTS] SPARC BCJ filter\n"
+" --riscv[=OPTS] RISC-V BCJ filter\n"
" Valid OPTS for all BCJ filters:\n"
" start=NUM start offset for conversions (default=0)"));
@@ -1144,3 +1145,28 @@ message_help(bool long_help)
tuklib_exit(E_SUCCESS, E_ERROR, verbosity != V_SILENT);
}
+
+
+extern void
+message_filters_help(void)
+{
+ char *encoder_options;
+ if (lzma_str_list_filters(&encoder_options, LZMA_VLI_UNKNOWN,
+ LZMA_STR_ENCODER, NULL) != LZMA_OK)
+ message_bug();
+
+ if (!opt_robot) {
+ puts(_(
+"Filter chains are set using the --filters=FILTERS or\n"
+"--filters1=FILTERS ... --filters9=FILTERS options. Each filter in the chain\n"
+"can be separated by spaces or '--'. Alternatively a preset <0-9>[e] can be\n"
+"specified instead of a filter chain.\n"
+ ));
+
+ puts(_("The supported filters and their options are:"));
+ }
+
+ puts(encoder_options);
+
+ tuklib_exit(E_SUCCESS, E_ERROR, verbosity != V_SILENT);
+}
diff --git a/src/xz/message.h b/src/xz/message.h
index f608ec7..3f6e183 100644
--- a/src/xz/message.h
+++ b/src/xz/message.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file message.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// Verbosity levels
@@ -24,7 +23,10 @@ enum message_verbosity {
extern const int message_progress_sigs[];
-/// \brief Initializes the message functions
+/// \brief Initializes the progress message functions
+///
+/// message_fatal() and such can be called even before message_init()
+/// has been called.
///
/// If an error occurs, this function doesn't return.
///
@@ -111,6 +113,12 @@ tuklib_attr_noreturn
extern void message_help(bool long_help);
+/// Prints a help message specifically for using the --filters and
+/// --filtersX command line options.
+tuklib_attr_noreturn
+extern void message_filters_help(void);
+
+
/// \brief Set the total number of files to be processed
///
/// Standard input is counted as a file here. This is used when printing
diff --git a/src/xz/mytime.c b/src/xz/mytime.c
index 7e8a074..7d9a27d 100644
--- a/src/xz/mytime.c
+++ b/src/xz/mytime.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file mytime.c
@@ -5,14 +7,14 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
-#if defined(HAVE_CLOCK_GETTIME) && defined(HAVE_CLOCK_MONOTONIC)
+#if defined(MYTHREAD_VISTA) || defined(_MSC_VER)
+ // Nothing
+#elif defined(HAVE_CLOCK_GETTIME) \
+ && (!defined(__MINGW32__) || defined(MYTHREAD_POSIX))
# include <time.h>
#else
# include <sys/time.h>
@@ -20,7 +22,22 @@
uint64_t opt_flush_timeout = 0;
+// start_time holds the time when the (de)compression was started.
+// It's from mytime_now() and thus only useful for calculating relative
+// time differences (elapsed time). start_time is initialized by calling
+// mytime_set_start_time() and modified by mytime_sigtstp_handler().
+//
+// When mytime_sigtstp_handler() is used, start_time is made volatile.
+// I'm not sure if that is really required since access to it is guarded
+// by signals_block()/signals_unblock() since accessing an uint64_t isn't
+// atomic on all systems. But since the variable isn't accessed very
+// frequently making it volatile doesn't hurt.
+#ifdef USE_SIGTSTP_HANDLER
+static volatile uint64_t start_time;
+#else
static uint64_t start_time;
+#endif
+
static uint64_t next_flush;
@@ -30,16 +47,41 @@ static uint64_t next_flush;
static uint64_t
mytime_now(void)
{
-#if defined(HAVE_CLOCK_GETTIME) && defined(HAVE_CLOCK_MONOTONIC)
+#if defined(MYTHREAD_VISTA) || defined(_MSC_VER)
+ // Since there is no SIGALRM on Windows, this function gets
+ // called frequently when the progress indicator is in use.
+ // Progress indicator doesn't need high-resolution time.
+ // GetTickCount64() has very low overhead but needs at least WinVista.
+ //
+ // MinGW-w64 provides the POSIX functions clock_gettime() and
+ // gettimeofday() in a manner that allow xz to run on older
+ // than WinVista. If the threading method needs WinVista anyway,
+ // there's no reason to avoid a WinVista API here either.
+ return GetTickCount64();
+
+#elif defined(HAVE_CLOCK_GETTIME) \
+ && (!defined(__MINGW32__) || defined(MYTHREAD_POSIX))
+ // MinGW-w64: clock_gettime() is defined in winpthreads but we need
+ // nothing else from winpthreads (unless, for some odd reason, POSIX
+ // threading has been selected). By avoiding clock_gettime(), we
+ // avoid the dependency on libwinpthread-1.dll or the need to link
+ // against the static version. The downside is that the fallback
+ // method, gettimeofday(), doesn't provide monotonic time.
+ struct timespec tv;
+
+# ifdef HAVE_CLOCK_MONOTONIC
// If CLOCK_MONOTONIC was available at compile time but for some
// reason isn't at runtime, fallback to CLOCK_REALTIME which
// according to POSIX is mandatory for all implementations.
static clockid_t clk_id = CLOCK_MONOTONIC;
- struct timespec tv;
while (clock_gettime(clk_id, &tv))
clk_id = CLOCK_REALTIME;
+# else
+ clock_gettime(CLOCK_REALTIME, &tv);
+# endif
return (uint64_t)tv.tv_sec * 1000 + (uint64_t)(tv.tv_nsec / 1000000);
+
#else
struct timeval tv;
gettimeofday(&tv, NULL);
@@ -48,10 +90,49 @@ mytime_now(void)
}
+#ifdef USE_SIGTSTP_HANDLER
+extern void
+mytime_sigtstp_handler(int sig lzma_attribute((__unused__)))
+{
+ // Measure how long the process stays in the stopped state and add
+ // that amount to start_time. This way the the progress indicator
+ // won't count the stopped time as elapsed time and the estimated
+ // remaining time won't be confused by the time spent in the
+ // stopped state.
+ //
+ // FIXME? Is raising SIGSTOP the correct thing to do? POSIX.1-2017
+ // says that orphan processes shouldn't stop on SIGTSTP. So perhaps
+ // the most correct thing to do could be to revert to the default
+ // handler for SIGTSTP, unblock SIGTSTP, and then raise(SIGTSTP).
+ // It's quite a bit more complicated than just raising SIGSTOP though.
+ //
+ // The difference between raising SIGTSTP vs. SIGSTOP can be seen on
+ // the shell command line too by running "echo $?" after stopping
+ // a process but perhaps that doesn't matter.
+ const uint64_t t = mytime_now();
+ raise(SIGSTOP);
+ start_time += mytime_now() - t;
+ return;
+}
+#endif
+
+
extern void
mytime_set_start_time(void)
{
+#ifdef USE_SIGTSTP_HANDLER
+ // Block the signals when accessing start_time so that we cannot
+ // end up with a garbage value. start_time is volatile but access
+ // to it isn't atomic at least on 32-bit systems.
+ signals_block();
+#endif
+
start_time = mytime_now();
+
+#ifdef USE_SIGTSTP_HANDLER
+ signals_unblock();
+#endif
+
return;
}
@@ -59,7 +140,17 @@ mytime_set_start_time(void)
extern uint64_t
mytime_get_elapsed(void)
{
- return mytime_now() - start_time;
+#ifdef USE_SIGTSTP_HANDLER
+ signals_block();
+#endif
+
+ const uint64_t t = mytime_now() - start_time;
+
+#ifdef USE_SIGTSTP_HANDLER
+ signals_unblock();
+#endif
+
+ return t;
}
diff --git a/src/xz/mytime.h b/src/xz/mytime.h
index a7be2aa..6dfaeae 100644
--- a/src/xz/mytime.h
+++ b/src/xz/mytime.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file mytime.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
@@ -21,6 +20,12 @@
extern uint64_t opt_flush_timeout;
+#ifdef USE_SIGTSTP_HANDLER
+/// \brief Signal handler for SIGTSTP
+extern void mytime_sigtstp_handler(int sig);
+#endif
+
+
/// \brief Store the time when (de)compression was started
///
/// The start time is also stored as the time of the first flush.
diff --git a/src/xz/options.c b/src/xz/options.c
index 4d5e899..bc8bc1a 100644
--- a/src/xz/options.c
+++ b/src/xz/options.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file options.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -83,7 +82,7 @@ parse_options(const char *str, const option_map *opts,
*value++ = '\0';
if (value == NULL || value[0] == '\0')
- message_fatal(_("%s: Options must be `name=value' "
+ message_fatal(_("%s: Options must be 'name=value' "
"pairs separated with commas"), str);
// Look for the option name from the option map.
diff --git a/src/xz/options.h b/src/xz/options.h
index 61ec8d5..4a1314d 100644
--- a/src/xz/options.h
+++ b/src/xz/options.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file options.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// \brief Parser for Delta options
diff --git a/src/xz/private.h b/src/xz/private.h
index 6414bdb..b370472 100644
--- a/src/xz/private.h
+++ b/src/xz/private.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file private.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "sysdefs.h"
@@ -21,7 +20,10 @@
#include <signal.h>
#include <locale.h>
#include <stdio.h>
-#include <unistd.h>
+
+#ifndef _MSC_VER
+# include <unistd.h>
+#endif
#include "tuklib_gettext.h"
#include "tuklib_progname.h"
@@ -33,6 +35,10 @@
# include <windows.h>
#endif
+#ifdef _MSC_VER
+# define fileno _fileno
+#endif
+
#ifndef STDIN_FILENO
# define STDIN_FILENO (fileno(stdin))
#endif
@@ -45,8 +51,15 @@
# define STDERR_FILENO (fileno(stderr))
#endif
-#if defined(HAVE_CAPSICUM) || defined(HAVE_PLEDGE)
-# define ENABLE_SANDBOX 1
+// Handling SIGTSTP keeps time-keeping for progress indicator correct
+// if xz is stopped. It requires use of clock_gettime() as that is
+// async-signal safe in POSIX. Require also SIGALRM support since
+// on systems where SIGALRM isn't available, progress indicator code
+// polls the time and the SIGTSTP handling adds slight overhead to
+// that code. Most (all?) systems that have SIGTSTP also have SIGALRM
+// so this requirement won't exclude many systems.
+#if defined(HAVE_CLOCK_GETTIME) && defined(SIGTSTP) && defined(SIGALRM)
+# define USE_SIGTSTP_HANDLER 1
#endif
#include "main.h"
@@ -57,6 +70,7 @@
#include "hardware.h"
#include "file_io.h"
#include "options.h"
+#include "sandbox.h"
#include "signals.h"
#include "suffix.h"
#include "util.h"
diff --git a/src/xz/sandbox.c b/src/xz/sandbox.c
new file mode 100644
index 0000000..5bd2273
--- /dev/null
+++ b/src/xz/sandbox.c
@@ -0,0 +1,355 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file sandbox.c
+/// \brief Sandbox support
+//
+// Author: Lasse Collin
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "private.h"
+
+
+#ifndef ENABLE_SANDBOX
+
+// Prevent an empty translation unit when no sandboxing is supported.
+typedef int dummy;
+
+#else
+
+/// If the conditions for strict sandboxing (described in main())
+/// have been met, sandbox_allow_strict() can be called to set this
+/// variable to true.
+static bool strict_sandbox_allowed = false;
+
+
+extern void
+sandbox_allow_strict(void)
+{
+ strict_sandbox_allowed = true;
+ return;
+}
+
+
+// Strict sandboxing prevents opening any files. This *tries* to ensure
+// that any auxiliary files that might be required are already open.
+//
+// Returns true if strict sandboxing is allowed, false otherwise.
+static bool
+prepare_for_strict_sandbox(void)
+{
+ if (!strict_sandbox_allowed)
+ return false;
+
+ const char dummy_str[] = "x";
+
+ // Try to ensure that both libc and xz locale files have been
+ // loaded when NLS is enabled.
+ snprintf(NULL, 0, "%s%s", _(dummy_str), strerror(EINVAL));
+
+ // Try to ensure that iconv data files needed for handling multibyte
+ // characters have been loaded. This is needed at least with glibc.
+ tuklib_mbstr_width(dummy_str, NULL);
+
+ return true;
+}
+
+#endif
+
+
+#if defined(HAVE_PLEDGE)
+
+///////////////
+// pledge(2) //
+///////////////
+
+#include <unistd.h>
+
+
+extern void
+sandbox_init(void)
+{
+ if (pledge("stdio rpath wpath cpath fattr", "")) {
+ // gettext hasn't been initialized yet so
+ // there's no point to call it here.
+ message_fatal("Failed to enable the sandbox");
+ }
+
+ return;
+}
+
+
+extern void
+sandbox_enable_read_only(void)
+{
+ // We will be opening files for reading but
+ // won't create or remove any files.
+ if (pledge("stdio rpath", ""))
+ message_fatal(_("Failed to enable the sandbox"));
+
+ return;
+}
+
+
+extern void
+sandbox_enable_strict_if_allowed(int src_fd lzma_attribute((__unused__)),
+ int pipe_event_fd lzma_attribute((__unused__)),
+ int pipe_write_fd lzma_attribute((__unused__)))
+{
+ if (!prepare_for_strict_sandbox())
+ return;
+
+ // All files that need to be opened have already been opened.
+ if (pledge("stdio", ""))
+ message_fatal(_("Failed to enable the sandbox"));
+
+ return;
+}
+
+
+#elif defined(HAVE_LINUX_LANDLOCK)
+
+//////////////
+// Landlock //
+//////////////
+
+#include <linux/landlock.h>
+#include <sys/syscall.h>
+#include <sys/prctl.h>
+
+
+// Highest Landlock ABI version supported by this file:
+// - For ABI versions 1-3 we don't need anything from <linux/landlock.h>
+// that isn't part of version 1.
+// - For ABI version 4 we need the larger struct landlock_ruleset_attr
+// with the handled_access_net member. That is bundled with the macros
+// LANDLOCK_ACCESS_NET_BIND_TCP and LANDLOCK_ACCESS_NET_CONNECT_TCP.
+#ifdef LANDLOCK_ACCESS_NET_BIND_TCP
+# define LANDLOCK_ABI_MAX 4
+#else
+# define LANDLOCK_ABI_MAX 3
+#endif
+
+
+/// Landlock ABI version supported by the kernel
+static int landlock_abi;
+
+
+// The required_rights should have those bits set that must not be restricted.
+// This function will then bitwise-and ~required_rights with a mask matching
+// the Landlock ABI version, leaving only those bits set that are supported
+// by the ABI and allowed to be restricted by the function argument.
+static void
+enable_landlock(uint64_t required_rights)
+{
+ assert(landlock_abi <= LANDLOCK_ABI_MAX);
+
+ if (landlock_abi <= 0)
+ return;
+
+ // We want to set all supported flags in handled_access_fs.
+ // This way the ruleset will initially forbid access to all
+ // actions that the available Landlock ABI version supports.
+ // Exceptions can be added using landlock_add_rule(2) to
+ // allow certain actions on certain files or directories.
+ //
+ // The same flag values are used on all archs. ABI v2 and v3
+ // both add one new flag.
+ //
+ // First in ABI v1: LANDLOCK_ACCESS_FS_EXECUTE = 1ULL << 0
+ // Last in ABI v1: LANDLOCK_ACCESS_FS_MAKE_SYM = 1ULL << 12
+ // Last in ABI v2: LANDLOCK_ACCESS_FS_REFER = 1ULL << 13
+ // Last in ABI v3: LANDLOCK_ACCESS_FS_TRUNCATE = 1ULL << 14
+ //
+ // This makes it simple to set the mask based on the ABI
+ // version and we don't need to care which flags are #defined
+ // in the installed <linux/landlock.h> for ABI versions 1-3.
+ const struct landlock_ruleset_attr attr = {
+ .handled_access_fs = ~required_rights
+ & ((1ULL << (12 + my_min(3, landlock_abi))) - 1),
+#if LANDLOCK_ABI_MAX >= 4
+ .handled_access_net = landlock_abi < 4 ? 0 :
+ (LANDLOCK_ACCESS_NET_BIND_TCP
+ | LANDLOCK_ACCESS_NET_CONNECT_TCP),
+#endif
+ };
+
+ const int ruleset_fd = syscall(SYS_landlock_create_ruleset,
+ &attr, sizeof(attr), 0U);
+ if (ruleset_fd < 0)
+ message_fatal(_("Failed to enable the sandbox"));
+
+ // All files we need should have already been opened. Thus,
+ // we don't need to add any rules using landlock_add_rule(2)
+ // before activating the sandbox.
+ //
+ // NOTE: It's possible that the hack prepare_for_strict_sandbox()
+ // isn't be good enough. It tries to get translations and
+ // libc-specific files loaded but if it's not good enough
+ // then perhaps a Landlock rule to allow reading from /usr
+ // and/or the xz installation prefix would be needed.
+ //
+ // prctl(PR_SET_NO_NEW_PRIVS, ...) was already called in
+ // sandbox_init() so we don't do it here again.
+ if (syscall(SYS_landlock_restrict_self, ruleset_fd, 0U) != 0)
+ message_fatal(_("Failed to enable the sandbox"));
+
+ return;
+}
+
+
+extern void
+sandbox_init(void)
+{
+ // Prevent the process from gaining new privileges. This must be done
+ // before landlock_restrict_self(2) but since we will never need new
+ // privileges, this call can be done here already.
+ //
+ // This is supported since Linux 3.5. Ignore the return value to
+ // keep compatibility with old kernels. landlock_restrict_self(2)
+ // will fail if the no_new_privs attribute isn't set, thus if prctl()
+ // fails here the error will still be detected when it matters.
+ (void)prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+
+ // Get the highest Landlock ABI version supported by the kernel.
+ landlock_abi = syscall(SYS_landlock_create_ruleset,
+ (void *)NULL, 0, LANDLOCK_CREATE_RULESET_VERSION);
+
+ // The kernel might support a newer ABI than this file.
+ if (landlock_abi > LANDLOCK_ABI_MAX)
+ landlock_abi = LANDLOCK_ABI_MAX;
+
+ // These are all in ABI version 1 already. We don't need truncate
+ // rights because files are created with open() using O_EXCL and
+ // without O_TRUNC.
+ //
+ // LANDLOCK_ACCESS_FS_READ_DIR is included here to get a clear error
+ // message if xz is given a directory name. Without this permission
+ // the message would be "Permission denied" but with this permission
+ // it's "Is a directory, skipping". It could be worked around with
+ // stat()/lstat() but just giving this permission is simpler and
+ // shouldn't make the sandbox much weaker in practice.
+ const uint64_t required_rights
+ = LANDLOCK_ACCESS_FS_WRITE_FILE
+ | LANDLOCK_ACCESS_FS_READ_FILE
+ | LANDLOCK_ACCESS_FS_READ_DIR
+ | LANDLOCK_ACCESS_FS_REMOVE_FILE
+ | LANDLOCK_ACCESS_FS_MAKE_REG;
+
+ enable_landlock(required_rights);
+ return;
+}
+
+
+extern void
+sandbox_enable_read_only(void)
+{
+ // We will be opening files for reading but
+ // won't create or remove any files.
+ const uint64_t required_rights
+ = LANDLOCK_ACCESS_FS_READ_FILE
+ | LANDLOCK_ACCESS_FS_READ_DIR;
+ enable_landlock(required_rights);
+ return;
+}
+
+
+extern void
+sandbox_enable_strict_if_allowed(int src_fd lzma_attribute((__unused__)),
+ int pipe_event_fd lzma_attribute((__unused__)),
+ int pipe_write_fd lzma_attribute((__unused__)))
+{
+ if (!prepare_for_strict_sandbox())
+ return;
+
+ // Allow all restrictions that the kernel supports with the
+ // highest Landlock ABI version that the kernel or xz supports.
+ //
+ // NOTE: LANDLOCK_ACCESS_FS_READ_DIR isn't needed here because
+ // the only input file has already been opened.
+ enable_landlock(0);
+ return;
+}
+
+
+#elif defined(HAVE_CAP_RIGHTS_LIMIT)
+
+//////////////
+// Capsicum //
+//////////////
+
+#include <sys/capsicum.h>
+
+
+extern void
+sandbox_init(void)
+{
+ // Nothing to do.
+ return;
+}
+
+
+extern void
+sandbox_enable_read_only(void)
+{
+ // Nothing to do.
+ return;
+}
+
+
+extern void
+sandbox_enable_strict_if_allowed(
+ int src_fd, int pipe_event_fd, int pipe_write_fd)
+{
+ if (!prepare_for_strict_sandbox())
+ return;
+
+ // Capsicum needs FreeBSD 10.2 or later.
+ cap_rights_t rights;
+
+ if (cap_enter())
+ goto error;
+
+ if (cap_rights_limit(src_fd, cap_rights_init(&rights,
+ CAP_EVENT, CAP_FCNTL, CAP_LOOKUP, CAP_READ, CAP_SEEK)))
+ goto error;
+
+ // If not reading from stdin, remove all capabilities from it.
+ if (src_fd != STDIN_FILENO && cap_rights_limit(
+ STDIN_FILENO, cap_rights_clear(&rights)))
+ goto error;
+
+ if (cap_rights_limit(STDOUT_FILENO, cap_rights_init(&rights,
+ CAP_EVENT, CAP_FCNTL, CAP_FSTAT, CAP_LOOKUP,
+ CAP_WRITE, CAP_SEEK)))
+ goto error;
+
+ if (cap_rights_limit(STDERR_FILENO, cap_rights_init(&rights,
+ CAP_WRITE)))
+ goto error;
+
+ if (cap_rights_limit(pipe_event_fd, cap_rights_init(&rights,
+ CAP_EVENT)))
+ goto error;
+
+ if (cap_rights_limit(pipe_write_fd, cap_rights_init(&rights,
+ CAP_WRITE)))
+ goto error;
+
+ return;
+
+error:
+ // If a kernel is configured without capability mode support or
+ // used in an emulator that does not implement the capability
+ // system calls, then the Capsicum system calls will fail and set
+ // errno to ENOSYS. In that case xz will silently run without
+ // the sandbox.
+ if (errno == ENOSYS)
+ return;
+
+ message_fatal(_("Failed to enable the sandbox"));
+}
+
+#endif
diff --git a/src/xz/sandbox.h b/src/xz/sandbox.h
new file mode 100644
index 0000000..98b9862
--- /dev/null
+++ b/src/xz/sandbox.h
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: 0BSD
+
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file sandbox.h
+/// \brief Sandbox support
+//
+// Author: Lasse Collin
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#if defined(HAVE_PLEDGE) || defined(HAVE_LINUX_LANDLOCK) \
+ || defined(HAVE_CAP_RIGHTS_LIMIT)
+# define ENABLE_SANDBOX 1
+#endif
+
+
+/// \brief Enables early sandboxing that can always be enabled
+///
+/// This requires that tuklib_progname() and io_init() have been called.
+extern void sandbox_init(void);
+
+
+/// \brief Enable sandboxing that only allows opening files for reading
+extern void sandbox_enable_read_only(void);
+
+
+/// \brief Tell sandboxing code that strict sandboxing can be used
+///
+/// This function only sets a flag which will be read by
+/// sandbox_enable_strict_if_allowed().
+extern void sandbox_allow_strict(void);
+
+
+/// \brief Enable sandboxing that allows reading from one file
+///
+/// This does nothing if sandbox_allow_strict() hasn't been called.
+///
+/// \param src_fd File descriptor open for reading
+/// \param pipe_event_fd user_abort_pipe[0] from file_io.c
+/// \param pipe_write_fd user_abort_pipe[1] from file_io.c
+extern void sandbox_enable_strict_if_allowed(
+ int src_fd, int pipe_event_fd, int pipe_write_fd);
diff --git a/src/xz/signals.c b/src/xz/signals.c
index 7aef463..20f03be 100644
--- a/src/xz/signals.c
+++ b/src/xz/signals.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file signals.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -50,6 +49,10 @@ signal_handler(int sig)
}
+#ifdef __APPLE__
+# pragma GCC diagnostic push
+# pragma GCC diagnostic ignored "-Wsign-conversion"
+#endif
extern void
signals_init(void)
{
@@ -82,6 +85,11 @@ signals_init(void)
sigaddset(&hooked_signals, message_progress_sigs[i]);
#endif
+#ifdef USE_SIGTSTP_HANDLER
+ // Add the SIGTSTP handler from mytime.c to hooked_signals.
+ sigaddset(&hooked_signals, SIGTSTP);
+#endif
+
// Using "my_sa" because "sa" may conflict with a sockaddr variable
// from system headers on Solaris.
struct sigaction my_sa;
@@ -96,10 +104,11 @@ signals_init(void)
my_sa.sa_flags = 0;
my_sa.sa_handler = &signal_handler;
+ struct sigaction old;
+
for (size_t i = 0; i < ARRAY_SIZE(sigs); ++i) {
// If the parent process has left some signals ignored,
// we don't unignore them.
- struct sigaction old;
if (sigaction(sigs[i], NULL, &old) == 0
&& old.sa_handler == SIG_IGN)
continue;
@@ -109,10 +118,22 @@ signals_init(void)
message_signal_handler();
}
+#ifdef USE_SIGTSTP_HANDLER
+ if (!(sigaction(SIGTSTP, NULL, &old) == 0
+ && old.sa_handler == SIG_IGN)) {
+ my_sa.sa_handler = &mytime_sigtstp_handler;
+ if (sigaction(SIGTSTP, &my_sa, NULL))
+ message_signal_handler();
+ }
+#endif
+
signals_are_initialized = true;
return;
}
+#ifdef __APPLE__
+# pragma GCC diagnostic pop
+#endif
#ifndef __VMS
diff --git a/src/xz/signals.h b/src/xz/signals.h
index 5b125e0..629335d 100644
--- a/src/xz/signals.h
+++ b/src/xz/signals.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file signals.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// If this is true, we will clean up the possibly incomplete output file,
diff --git a/src/xz/suffix.c b/src/xz/suffix.c
index 6ce9787..1d548e4 100644
--- a/src/xz/suffix.c
+++ b/src/xz/suffix.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file suffix.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -21,7 +20,13 @@
# ifdef HAVE_STRINGS_H
# include <strings.h>
# endif
-# define strcmp strcasecmp
+# ifdef _MSC_VER
+# define suffix_strcmp _stricmp
+# else
+# define suffix_strcmp strcasecmp
+# endif
+#else
+# define suffix_strcmp strcmp
#endif
@@ -98,7 +103,7 @@ test_suffix(const char *suffix, const char *src_name, size_t src_len)
|| is_dir_sep(src_name[src_len - suffix_len - 1]))
return 0;
- if (strcmp(suffix, src_name + src_len - suffix_len) == 0)
+ if (suffix_strcmp(suffix, src_name + src_len - suffix_len) == 0)
return src_len - suffix_len;
return 0;
@@ -178,7 +183,7 @@ uncompressed_name(const char *src_name, const size_t src_len)
static void
msg_suffix(const char *src_name, const char *suffix)
{
- message_warning(_("%s: File already has `%s' suffix, skipping"),
+ message_warning(_("%s: File already has '%s' suffix, skipping"),
src_name, suffix);
return;
}
diff --git a/src/xz/suffix.h b/src/xz/suffix.h
index 135e905..f59e312 100644
--- a/src/xz/suffix.h
+++ b/src/xz/suffix.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file suffix.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// \brief Get the name of the destination file
diff --git a/src/xz/util.c b/src/xz/util.c
index 6ab4c2d..0d339ae 100644
--- a/src/xz/util.c
+++ b/src/xz/util.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file util.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "private.h"
@@ -148,8 +147,8 @@ str_to_uint64(const char *name, const char *value, uint64_t min, uint64_t max)
if (multiplier == 0) {
message(V_ERROR, _("%s: Invalid multiplier suffix"),
value - 1);
- message_fatal(_("Valid suffixes are `KiB' (2^10), "
- "`MiB' (2^20), and `GiB' (2^30)."));
+ message_fatal(_("Valid suffixes are 'KiB' (2^10), "
+ "'MiB' (2^20), and 'GiB' (2^30)."));
}
// Don't overflow here either.
@@ -165,7 +164,7 @@ str_to_uint64(const char *name, const char *value, uint64_t min, uint64_t max)
return result;
error:
- message_fatal(_("Value of the option `%s' must be in the range "
+ message_fatal(_("Value of the option '%s' must be in the range "
"[%" PRIu64 ", %" PRIu64 "]"),
name, min, max);
}
@@ -262,9 +261,30 @@ my_snprintf(char **pos, size_t *left, const char *fmt, ...)
extern bool
+is_tty(int fd)
+{
+#if defined(_WIN32) && !defined(__CYGWIN__)
+ // There is no need to check if handle == INVALID_HANDLE_VALUE
+ // because it will return false anyway when used in GetConsoleMode().
+ // The resulting HANDLE is owned by the file descriptor.
+ // The HANDLE must not be closed here.
+ intptr_t handle = _get_osfhandle(fd);
+ DWORD mode;
+
+ // GetConsoleMode() is an easy way to tell if the HANDLE is a
+ // console or not. We do not care about the value of mode since we
+ // do not plan to use any further Windows console functions.
+ return GetConsoleMode((HANDLE)handle, &mode);
+#else
+ return isatty(fd);
+#endif
+}
+
+
+extern bool
is_tty_stdin(void)
{
- const bool ret = isatty(STDIN_FILENO);
+ const bool ret = is_tty(STDIN_FILENO);
if (ret)
message_error(_("Compressed data cannot be read from "
@@ -277,7 +297,7 @@ is_tty_stdin(void)
extern bool
is_tty_stdout(void)
{
- const bool ret = isatty(STDOUT_FILENO);
+ const bool ret = is_tty(STDOUT_FILENO);
if (ret)
message_error(_("Compressed data cannot be written to "
diff --git a/src/xz/util.h b/src/xz/util.h
index 6d7e148..a2fdd05 100644
--- a/src/xz/util.h
+++ b/src/xz/util.h
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file util.h
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
/// \brief Safe malloc() that never returns NULL
@@ -105,6 +104,20 @@ lzma_attribute((__format__(__printf__, 3, 4)))
extern void my_snprintf(char **pos, size_t *left, const char *fmt, ...);
+/// \brief Test if file descriptor is a terminal
+///
+/// For POSIX systems, this is a simple wrapper around isatty(). However on
+/// Windows, isatty() returns true for all character devices, not just
+/// terminals.
+///
+/// \param fd File descriptor to test
+///
+/// \return bool:
+/// - true if file descriptor is a terminal
+/// - false otherwise
+extern bool is_tty(int fd);
+
+
/// \brief Test if stdin is a terminal
///
/// If stdin is a terminal, an error message is printed and exit status set
diff --git a/src/xz/xz.1 b/src/xz/xz.1
index 73ca6ef..5b880e8 100644
--- a/src/xz/xz.1
+++ b/src/xz/xz.1
@@ -1,12 +1,10 @@
'\" t
+.\" SPDX-License-Identifier: 0BSD
.\"
.\" Authors: Lasse Collin
.\" Jia Tan
.\"
-.\" This file has been put into the public domain.
-.\" You can do whatever you want with this file.
-.\"
-.TH XZ 1 "2023-07-17" "Tukaani" "XZ Utils"
+.TH XZ 1 "2024-04-08" "Tukaani" "XZ Utils"
.
.SH NAME
xz, unxz, xzcat, lzma, unlzma, lzcat \- Compress or decompress .xz and .lzma files
@@ -801,8 +799,6 @@ in the single-threaded mode.
It may vary slightly between
.B xz
versions.
-Memory requirements of some of the future multithreaded modes may
-be dramatically higher than that of the single-threaded mode.
.IP \(bu 3
DecMem contains the decompressor memory requirements.
That is, the compression settings determine
@@ -811,6 +807,15 @@ The exact decompressor memory usage is slightly more than
the LZMA2 dictionary size, but the values in the table
have been rounded up to the next full MiB.
.RE
+.IP ""
+Memory requirements of the multi-threaded mode are
+significantly higher than that of the single-threaded mode.
+With the default value of
+.BR \-\-block\-size ,
+each thread needs 3*3*DictSize plus CompMem or DecMem.
+For example, four threads with preset
+.B \-6
+needs 660\(en670\ MiB of memory.
.TP
.BR \-e ", " \-\-extreme
Use a slower variant of the selected compression preset level
@@ -902,50 +907,90 @@ Using
.I size
less than the LZMA2 dictionary size is waste of RAM
because then the LZMA2 dictionary buffer will never get fully used.
-The sizes of the blocks are stored in the block headers,
-which a future version of
-.B xz
-will use for multi-threaded decompression.
+In multi-threaded mode,
+the sizes of the blocks are stored in the block headers.
+This size information is required for multi-threaded decompression.
.IP ""
In single-threaded mode no block splitting is done by default.
Setting this option doesn't affect memory usage.
No size information is stored in block headers,
thus files created in single-threaded mode
won't be identical to files created in multi-threaded mode.
-The lack of size information also means that a future version of
+The lack of size information also means that
.B xz
won't be able decompress the files in multi-threaded mode.
.TP
-.BI \-\-block\-list= sizes
+.BI \-\-block\-list= items
When compressing to the
.B .xz
-format, start a new block after
+format, start a new block with an optional custom filter chain after
the given intervals of uncompressed data.
.IP ""
-The uncompressed
-.I sizes
-of the blocks are specified as a comma-separated list.
-Omitting a size (two or more consecutive commas) is a shorthand
-to use the size of the previous block.
+The
+.I items
+are a comma-separated list.
+Each item consists of an optional filter chain number
+between 0 and 9 followed by a colon
+.RB ( : )
+and a required size of uncompressed data.
+Omitting an item (two or more consecutive commas) is a
+shorthand to use the size and filters of the previous item.
.IP ""
If the input file is bigger than the sum of
-.IR sizes ,
-the last value in
-.I sizes
-is repeated until the end of the file.
+the sizes in
+.IR items ,
+the last item is repeated until the end of the file.
A special value of
.B 0
-may be used as the last value to indicate that
+may be used as the last size to indicate that
the rest of the file should be encoded as a single block.
.IP ""
-If one specifies
-.I sizes
-that exceed the encoder's block size
+An alternative filter chain for each block can be
+specified in combination with the
+.BI \-\-filters1= filters
+\&...\&
+.BI \-\-filters9= filters
+options.
+These options define filter chains with an identifier
+between 1\(en9.
+Filter chain 0 can be used to refer to the default filter chain,
+which is the same as not specifying a filter chain.
+The filter chain identifier can be used before the uncompressed
+size, followed by a colon
+.RB ( : ).
+For example, if one specifies
+.B \-\-block\-list=1:2MiB,3:2MiB,2:4MiB,,2MiB,0:4MiB
+then blocks will be created using:
+.RS
+.IP \(bu 3
+The filter chain specified by
+.B \-\-filters1
+and 2 MiB input
+.IP \(bu 3
+The filter chain specified by
+.B \-\-filters3
+and 2 MiB input
+.IP \(bu 3
+The filter chain specified by
+.B \-\-filters2
+and 4 MiB input
+.IP \(bu 3
+The filter chain specified by
+.B \-\-filters2
+and 4 MiB input
+.IP \(bu 3
+The default filter chain and 2 MiB input
+.IP \(bu 3
+The default filter chain and 4 MiB input for every block until
+end of input.
+.RE
+.IP ""
+If one specifies a size that exceeds the encoder's block size
(either the default value in threaded mode or
the value specified with \fB\-\-block\-size=\fIsize\fR),
the encoder will create additional blocks while
keeping the boundaries specified in
-.IR sizes .
+.IR items .
For example, if one specifies
.B \-\-block\-size=10MiB
.B \-\-block\-list=5MiB,10MiB,8MiB,12MiB,24MiB
@@ -1262,6 +1307,15 @@ meet this condition,
but files compressed in single-threaded mode don't even if
.BI \-\-block\-size= size
has been used.
+.IP ""
+The default value for
+.I threads
+is
+.BR 0 .
+In
+.B xz
+5.4.x and older the default is
+.BR 1 .
.
.SS "Custom compressor filter chains"
A custom filter chain allows specifying
@@ -1295,22 +1349,37 @@ in the chain.
Depending on the filter, this limitation is either inherent to
the filter design or exists to prevent security issues.
.PP
-A custom filter chain is specified by using one or more
-filter options in the order they are wanted in the filter chain.
-That is, the order of filter options is significant!
+A custom filter chain can be specified in two different ways.
+The options
+.BI \-\-filters= filters
+and
+.BI \-\-filters1= filters
+\&...\&
+.BI \-\-filters9= filters
+allow specifying an entire filter chain in one option using the
+liblzma filter string syntax.
+Alternatively, a filter chain can be specified by using one or more
+individual filter options in the order they are wanted in the filter chain.
+That is, the order of the individual filter options is significant!
When decoding raw streams
.RB ( \-\-format=raw ),
-the filter chain is specified in the same order as
+the filter chain must be specified in the same order as
it was specified when compressing.
-.PP
-Filters take filter-specific
+Any individual filter or preset options specified before the full
+chain option
+(\fB\-\-filters=\fIfilters\fR)
+will be forgotten.
+Individual filters specified after the full chain option will reset the
+filter chain.
+.PP
+Both the full and individual filter options take filter-specific
.I options
as a comma-separated list.
Extra commas in
.I options
are ignored.
-Every option has a default value, so you need to
-specify only those you want to change.
+Every option has a default value, so
+specify those you want to change.
.PP
To see the whole filter chain and
.IR options ,
@@ -1321,6 +1390,45 @@ use
twice).
This works also for viewing the filter chain options used by presets.
.TP
+.BI \-\-filters= filters
+Specify the full filter chain or a preset in a single option.
+Each filter can be separated by spaces or two dashes
+.RB ( \-\- ).
+.I filters
+may need to be quoted on the shell command line so it is
+parsed as a single option.
+To denote
+.IR options ,
+use
+.B :
+or
+.BR = .
+A preset can be prefixed with a
+.B \-
+and followed with zero or more flags.
+The only supported flag is
+.B e
+to apply the same options as
+.BR \-\-extreme .
+.TP
+\fB\-\-filters1\fR=\fIfilters\fR ... \fB\-\-filters9\fR=\fIfilters
+Specify up to nine additional filter chains that can be used with
+.BR \-\-block\-list .
+.IP ""
+For example, when compressing an archive with executable files
+followed by text files, the executable part could use a filter
+chain with a BCJ filter and the text part only the LZMA2 filter.
+.TP
+.B \-\-filters-help
+Display a help message describing how to specify presets and
+custom filter chains in the
+.B \-\-filters
+and
+.BI \-\-filters1= filters
+\&...\&
+.BI \-\-filters9= filters
+options, and exit successfully.
+.TP
\fB\-\-lzma1\fR[\fB=\fIoptions\fR]
.PD 0
.TP
@@ -1704,6 +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
@@ -1762,6 +1872,7 @@ ARM64;4;4096-byte alignment is best
PowerPC;4;Big endian only
IA-64;16;Itanium
SPARC;4;
+RISC-V;2;
.TE
.RE
.RE
@@ -1770,14 +1881,38 @@ Since the BCJ-filtered data is usually compressed with LZMA2,
the compression ratio may be improved slightly if
the LZMA2 options are set to match the
alignment of the selected BCJ filter.
-For example, with the IA-64 filter, it's good to set
-.B pb=4
-or even
+Examples:
+.RS
+.IP \(bu 3
+IA-64 filter has 16-byte alignment so
.B pb=4,lp=4,lc=0
+is good
with LZMA2 (2^4=16).
-The x86 filter is an exception;
-it's usually good to stick to LZMA2's default
-four-byte alignment when compressing x86 executables.
+.IP \(bu 3
+RISC-V code has 2-byte or 4-byte alignment
+depending on whether the file contains
+16-bit compressed instructions (the C extension).
+When 16-bit instructions are used,
+.B pb=2,lp=1,lc=3
+or
+.B pb=1,lp=1,lc=3
+is good.
+When 16-bit instructions aren't present,
+.B pb=2,lp=2,lc=2
+is the best.
+.B readelf \-h
+can be used to check if "RVC"
+appears on the "Flags" line.
+.IP \(bu 3
+ARM64 is always 4-byte aligned so
+.B pb=2,lp=2,lc=2
+is the best.
+.IP \(bu 3
+The x86 filter is an exception.
+It's usually good to stick to LZMA2's defaults
+.RB ( pb=2,lp=0,lc=3 )
+when compressing x86 executables.
+.RE
.IP ""
All BCJ filters support the same
.IR options :
@@ -1954,107 +2089,14 @@ easier to parse by other programs.
Currently
.B \-\-robot
is supported only together with
-.BR \-\-version ,
+.BR \-\-list ,
+.BR \-\-filters\-help ,
.BR \-\-info\-memory ,
and
-.BR \-\-list .
+.BR \-\-version .
It will be supported for compression and
decompression in the future.
.
-.SS Version
-.B "xz \-\-robot \-\-version"
-prints the version number of
-.B xz
-and liblzma in the following format:
-.PP
-.BI XZ_VERSION= XYYYZZZS
-.br
-.BI LIBLZMA_VERSION= XYYYZZZS
-.TP
-.I X
-Major version.
-.TP
-.I YYY
-Minor version.
-Even numbers are stable.
-Odd numbers are alpha or beta versions.
-.TP
-.I ZZZ
-Patch level for stable releases or
-just a counter for development releases.
-.TP
-.I S
-Stability.
-0 is alpha, 1 is beta, and 2 is stable.
-.I S
-should be always 2 when
-.I YYY
-is even.
-.PP
-.I XYYYZZZS
-are the same on both lines if
-.B xz
-and liblzma are from the same XZ Utils release.
-.PP
-Examples: 4.999.9beta is
-.B 49990091
-and
-5.0.0 is
-.BR 50000002 .
-.
-.SS "Memory limit information"
-.B "xz \-\-robot \-\-info\-memory"
-prints a single line with multiple tab-separated columns:
-.IP 1. 4
-Total amount of physical memory (RAM) in bytes.
-.IP 2. 4
-Memory usage limit for compression in bytes
-.RB ( \-\-memlimit\-compress ).
-A special value of
-.B 0
-indicates the default setting
-which for single-threaded mode is the same as no limit.
-.IP 3. 4
-Memory usage limit for decompression in bytes
-.RB ( \-\-memlimit\-decompress ).
-A special value of
-.B 0
-indicates the default setting
-which for single-threaded mode is the same as no limit.
-.IP 4. 4
-Since
-.B xz
-5.3.4alpha:
-Memory usage for multi-threaded decompression in bytes
-.RB ( \-\-memlimit\-mt\-decompress ).
-This is never zero because a system-specific default value
-shown in the column 5
-is used if no limit has been specified explicitly.
-This is also never greater than the value in the column 3
-even if a larger value has been specified with
-.BR \-\-memlimit\-mt\-decompress .
-.IP 5. 4
-Since
-.B xz
-5.3.4alpha:
-A system-specific default memory usage limit
-that is used to limit the number of threads
-when compressing with an automatic number of threads
-.RB ( \-\-threads=0 )
-and no memory usage limit has been specified
-.RB ( \-\-memlimit\-compress ).
-This is also used as the default value for
-.BR \-\-memlimit\-mt\-decompress .
-.IP 6. 4
-Since
-.B xz
-5.3.4alpha:
-Number of available processor threads.
-.PP
-In the future, the output of
-.B "xz \-\-robot \-\-info\-memory"
-may have more columns, but never more than a single line.
-.
.SS "List mode"
.B "xz \-\-robot \-\-list"
uses tab-separated output.
@@ -2339,6 +2381,127 @@ Future versions may add new line types and
new columns can be added to the existing line types,
but the existing columns won't be changed.
.
+.SS "Filters help"
+.B "xz \-\-robot \-\-filters-help"
+prints the supported filters in the following format:
+.PP
+\fIfilter\fB:\fIoption\fB=<\fIvalue\fB>,\fIoption\fB=<\fIvalue\fB>\fR...
+.TP
+.I filter
+Name of the filter
+.TP
+.I option
+Name of a filter specific option
+.TP
+.I value
+Numeric
+.I value
+ranges appear as
+\fB<\fImin\fB\-\fImax\fB>\fR.
+String
+.I value
+choices are shown within
+.B "< >"
+and separated by a
+.B |
+character.
+.PP
+Each filter is printed on its own line.
+.
+.SS "Memory limit information"
+.B "xz \-\-robot \-\-info\-memory"
+prints a single line with multiple tab-separated columns:
+.IP 1. 4
+Total amount of physical memory (RAM) in bytes.
+.IP 2. 4
+Memory usage limit for compression in bytes
+.RB ( \-\-memlimit\-compress ).
+A special value of
+.B 0
+indicates the default setting
+which for single-threaded mode is the same as no limit.
+.IP 3. 4
+Memory usage limit for decompression in bytes
+.RB ( \-\-memlimit\-decompress ).
+A special value of
+.B 0
+indicates the default setting
+which for single-threaded mode is the same as no limit.
+.IP 4. 4
+Since
+.B xz
+5.3.4alpha:
+Memory usage for multi-threaded decompression in bytes
+.RB ( \-\-memlimit\-mt\-decompress ).
+This is never zero because a system-specific default value
+shown in the column 5
+is used if no limit has been specified explicitly.
+This is also never greater than the value in the column 3
+even if a larger value has been specified with
+.BR \-\-memlimit\-mt\-decompress .
+.IP 5. 4
+Since
+.B xz
+5.3.4alpha:
+A system-specific default memory usage limit
+that is used to limit the number of threads
+when compressing with an automatic number of threads
+.RB ( \-\-threads=0 )
+and no memory usage limit has been specified
+.RB ( \-\-memlimit\-compress ).
+This is also used as the default value for
+.BR \-\-memlimit\-mt\-decompress .
+.IP 6. 4
+Since
+.B xz
+5.3.4alpha:
+Number of available processor threads.
+.PP
+In the future, the output of
+.B "xz \-\-robot \-\-info\-memory"
+may have more columns, but never more than a single line.
+.
+.SS Version
+.B "xz \-\-robot \-\-version"
+prints the version number of
+.B xz
+and liblzma in the following format:
+.PP
+.BI XZ_VERSION= XYYYZZZS
+.br
+.BI LIBLZMA_VERSION= XYYYZZZS
+.TP
+.I X
+Major version.
+.TP
+.I YYY
+Minor version.
+Even numbers are stable.
+Odd numbers are alpha or beta versions.
+.TP
+.I ZZZ
+Patch level for stable releases or
+just a counter for development releases.
+.TP
+.I S
+Stability.
+0 is alpha, 1 is beta, and 2 is stable.
+.I S
+should be always 2 when
+.I YYY
+is even.
+.PP
+.I XYYYZZZS
+are the same on both lines if
+.B xz
+and liblzma are from the same XZ Utils release.
+.PP
+Examples: 4.999.9beta is
+.B 49990091
+and
+5.0.0 is
+.BR 50000002 .
+.
.SH "EXIT STATUS"
.TP
.B 0
@@ -2391,7 +2554,7 @@ is run by a script or tool, for example, GNU
.RS
.PP
.nf
-.ft CW
+.ft CR
XZ_OPT=\-2v tar caf foo.tar.xz foo
.ft R
.fi
@@ -2411,7 +2574,7 @@ scripts one may use something like this:
.RS
.PP
.nf
-.ft CW
+.ft CR
XZ_OPT=${XZ_OPT\-"\-7e"}
export XZ_OPT
.ft R
@@ -2669,7 +2832,7 @@ if compression is successful:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz foo
.ft R
.fi
@@ -2685,7 +2848,7 @@ even if decompression is successful:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-dk bar.xz
.ft R
.fi
@@ -2703,7 +2866,7 @@ and 5\ MiB, respectively):
.RS
.PP
.nf
-.ft CW
+.ft CR
tar cf \- baz | xz \-4e > baz.tar.xz
.ft R
.fi
@@ -2714,7 +2877,7 @@ to standard output with a single command:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-dcf a.txt b.txt.xz c.txt d.txt.lzma > abcd.txt
.ft R
.fi
@@ -2729,7 +2892,7 @@ can be used to parallelize compression of many files:
.RS
.PP
.nf
-.ft CW
+.ft CR
find . \-type f \e! \-name '*.xz' \-print0 \e
| xargs \-0r \-P4 \-n16 xz \-T1
.ft R
@@ -2769,7 +2932,7 @@ after compressing multiple files:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-robot \-\-list *.xz | awk '/^totals/{print $5\-$4}'
.ft R
.fi
@@ -2789,7 +2952,7 @@ option:
.RS
.PP
.nf
-.ft CW
+.ft CR
if ! eval "$(xz \-\-robot \-\-version 2> /dev/null)" ||
[ "$XZ_VERSION" \-lt 50000002 ]; then
echo "Your xz is too old."
@@ -2805,7 +2968,7 @@ but if a limit has already been set, don't increase it:
.RS
.PP
.nf
-.ft CW
+.ft CR
NEWLIM=$((123 << 20))\ \ # 123 MiB
OLDLIM=$(xz \-\-robot \-\-info\-memory | cut \-f3)
if [ $OLDLIM \-eq 0 \-o $OLDLIM \-gt $NEWLIM ]; then
@@ -2858,7 +3021,7 @@ can be modified to use a bigger dictionary:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-lzma2=preset=1,dict=32MiB foo.tar
.ft R
.fi
@@ -2886,7 +3049,7 @@ would use:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-vv \-\-lzma2=dict=192MiB big_foo.tar
.ft R
.fi
@@ -2916,7 +3079,7 @@ using about 100\ KiB of memory.
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-check=crc32 \-\-lzma2=preset=6e,dict=64KiB foo
.ft R
.fi
@@ -2944,7 +3107,7 @@ slightly (like 0.1\ %) smaller file than
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-lzma2=preset=6e,pb=0,lc=4 source_code.tar
.ft R
.fi
@@ -2957,7 +3120,7 @@ using the x86 BCJ filter:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-x86 \-\-lzma2 libfoo.so
.ft R
.fi
@@ -2992,7 +3155,7 @@ to LZMA2 to accommodate the three-byte alignment:
.RS
.PP
.nf
-.ft CW
+.ft CR
xz \-\-delta=dist=3 \-\-lzma2=pb=0 foo.tiff
.ft R
.fi
diff --git a/src/xz/xz_w32res.rc b/src/xz/xz_w32res.rc
index bad3020..e80903e 100644
--- a/src/xz/xz_w32res.rc
+++ b/src/xz/xz_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#define MY_TYPE VFT_APP
diff --git a/src/xzdec/Makefile.am b/src/xzdec/Makefile.am
index 90f1e92..31a6508 100644
--- a/src/xzdec/Makefile.am
+++ b/src/xzdec/Makefile.am
@@ -1,9 +1,5 @@
-##
+## SPDX-License-Identifier: 0BSD
## Author: Lasse Collin
-##
-## This file has been put into the public domain.
-## You can do whatever you want with this file.
-##
# Windows resource compiler support. It's fine to use xz_CPPFLAGS
# also for lzmadec.
diff --git a/src/xzdec/Makefile.in b/src/xzdec/Makefile.in
index b05cff1..7d44f9b 100644
--- a/src/xzdec/Makefile.in
+++ b/src/xzdec/Makefile.in
@@ -103,8 +103,8 @@ bin_PROGRAMS = $(am__EXEEXT_1) $(am__EXEEXT_2)
@COND_LZMADEC_TRUE@@COND_XZDEC_TRUE@am__append_6 = lzmadec
subdir = src/xzdec
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/ax_check_capsicum.m4 \
- $(top_srcdir)/m4/ax_pthread.m4 $(top_srcdir)/m4/getopt.m4 \
+am__aclocal_m4_deps = $(top_srcdir)/m4/ax_pthread.m4 \
+ $(top_srcdir)/m4/build-to-host.m4 $(top_srcdir)/m4/getopt.m4 \
$(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/host-cpu-c-abi.m4 \
$(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \
$(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \
@@ -264,7 +264,6 @@ AUTOCONF = @AUTOCONF@
AUTOHEADER = @AUTOHEADER@
AUTOMAKE = @AUTOMAKE@
AWK = @AWK@
-CAPSICUM_LIB = @CAPSICUM_LIB@
CC = @CC@
CCAS = @CCAS@
CCASDEPMODE = @CCASDEPMODE@
@@ -393,6 +392,8 @@ install_sh = @install_sh@
libdir = @libdir@
libexecdir = @libexecdir@
localedir = @localedir@
+localedir_c = @localedir_c@
+localedir_c_make = @localedir_c_make@
localstatedir = @localstatedir@
mandir = @mandir@
mkdir_p = @mkdir_p@
diff --git a/src/xzdec/lzmadec_w32res.rc b/src/xzdec/lzmadec_w32res.rc
index b85962d..b4b89b1 100644
--- a/src/xzdec/lzmadec_w32res.rc
+++ b/src/xzdec/lzmadec_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#define MY_TYPE VFT_APP
diff --git a/src/xzdec/xzdec.1 b/src/xzdec/xzdec.1
index 78bc9b4..5198efb 100644
--- a/src/xzdec/xzdec.1
+++ b/src/xzdec/xzdec.1
@@ -1,10 +1,8 @@
+.\" SPDX-License-Identifier: 0BSD
.\"
.\" Author: Lasse Collin
.\"
-.\" This file has been put into the public domain.
-.\" You can do whatever you want with this file.
-.\"
-.TH XZDEC 1 "2017-04-19" "Tukaani" "XZ Utils"
+.TH XZDEC 1 "2024-04-08" "Tukaani" "XZ Utils"
.SH NAME
xzdec, lzmadec \- Small .xz and .lzma decompressors
.SH SYNOPSIS
diff --git a/src/xzdec/xzdec.c b/src/xzdec/xzdec.c
index 556c548..4d88174 100644
--- a/src/xzdec/xzdec.c
+++ b/src/xzdec/xzdec.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: 0BSD
+
///////////////////////////////////////////////////////////////////////////////
//
/// \file xzdec.c
@@ -5,9 +7,6 @@
//
// Author: Lasse Collin
//
-// This file has been put into the public domain.
-// You can do whatever you want with this file.
-//
///////////////////////////////////////////////////////////////////////////////
#include "sysdefs.h"
@@ -16,7 +15,30 @@
#include <stdarg.h>
#include <errno.h>
#include <stdio.h>
-#include <unistd.h>
+
+#ifndef _MSC_VER
+# include <unistd.h>
+#endif
+
+#ifdef HAVE_CAP_RIGHTS_LIMIT
+# include <sys/capsicum.h>
+#endif
+
+#ifdef HAVE_LINUX_LANDLOCK
+# include <linux/landlock.h>
+# include <sys/prctl.h>
+# include <sys/syscall.h>
+# ifdef LANDLOCK_ACCESS_NET_BIND_TCP
+# define LANDLOCK_ABI_MAX 4
+# else
+# define LANDLOCK_ABI_MAX 3
+# endif
+#endif
+
+#if defined(HAVE_CAP_RIGHTS_LIMIT) || defined(HAVE_PLEDGE) \
+ || defined(HAVE_LINUX_LANDLOCK)
+# define ENABLE_SANDBOX 1
+#endif
#include "getopt.h"
#include "tuklib_progname.h"
@@ -25,6 +47,10 @@
#ifdef TUKLIB_DOSLIKE
# include <fcntl.h>
# include <io.h>
+# ifdef _MSC_VER
+# define fileno _fileno
+# define setmode _setmode
+# endif
#endif
@@ -273,9 +299,123 @@ uncompress(lzma_stream *strm, FILE *file, const char *filename)
}
+#ifdef ENABLE_SANDBOX
+static void
+sandbox_enter(int src_fd)
+{
+#if defined(HAVE_CAP_RIGHTS_LIMIT)
+ // Capsicum needs FreeBSD 10.2 or later.
+ cap_rights_t rights;
+
+ if (cap_enter())
+ goto error;
+
+ if (cap_rights_limit(src_fd, cap_rights_init(&rights, CAP_READ)))
+ goto error;
+
+ // If not reading from stdin, remove all capabilities from it.
+ if (src_fd != STDIN_FILENO && cap_rights_limit(
+ STDIN_FILENO, cap_rights_clear(&rights)))
+ goto error;
+
+ if (cap_rights_limit(STDOUT_FILENO, cap_rights_init(&rights,
+ CAP_WRITE)))
+ goto error;
+
+ if (cap_rights_limit(STDERR_FILENO, cap_rights_init(&rights,
+ CAP_WRITE)))
+ goto error;
+
+#elif defined(HAVE_PLEDGE)
+ // pledge() was introduced in OpenBSD 5.9.
+ if (pledge("stdio", ""))
+ goto error;
+
+ (void)src_fd;
+
+#elif defined(HAVE_LINUX_LANDLOCK)
+ int landlock_abi = syscall(SYS_landlock_create_ruleset,
+ (void *)NULL, 0, LANDLOCK_CREATE_RULESET_VERSION);
+
+ if (landlock_abi > 0) {
+ if (landlock_abi > LANDLOCK_ABI_MAX)
+ landlock_abi = LANDLOCK_ABI_MAX;
+
+ const struct landlock_ruleset_attr attr = {
+ .handled_access_fs = (1ULL
+ << (12 + my_min(3, landlock_abi))) - 1,
+# if LANDLOCK_ABI_MAX >= 4
+ .handled_access_net = landlock_abi < 4 ? 0 :
+ (LANDLOCK_ACCESS_NET_BIND_TCP
+ | LANDLOCK_ACCESS_NET_CONNECT_TCP),
+# endif
+ };
+
+ const int ruleset_fd = syscall(SYS_landlock_create_ruleset,
+ &attr, sizeof(attr), 0U);
+ if (ruleset_fd < 0)
+ goto error;
+
+ // All files we need should have already been opened. Thus,
+ // we don't need to add any rules using landlock_add_rule(2)
+ // before activating the sandbox.
+ if (syscall(SYS_landlock_restrict_self, ruleset_fd, 0U) != 0)
+ goto error;
+ }
+
+ (void)src_fd;
+
+#else
+# error ENABLE_SANDBOX is defined but no sandboxing method was found.
+#endif
+
+ return;
+
+error:
+#ifdef HAVE_CAP_RIGHTS_LIMIT
+ // If a kernel is configured without capability mode support or
+ // used in an emulator that does not implement the capability
+ // system calls, then the Capsicum system calls will fail and set
+ // errno to ENOSYS. In that case xzdec will silently run without
+ // the sandbox.
+ if (errno == ENOSYS)
+ return;
+#endif
+
+ my_errorf("Failed to enable the sandbox");
+ exit(EXIT_FAILURE);
+}
+#endif
+
+
int
main(int argc, char **argv)
{
+#ifdef HAVE_PLEDGE
+ // OpenBSD's pledge(2) sandbox.
+ // Initially enable the sandbox slightly more relaxed so that
+ // the process can still open files. This allows the sandbox to
+ // be enabled when parsing command line arguments and decompressing
+ // all files (the more strict sandbox only restricts the last file
+ // that is decompressed).
+ if (pledge("stdio rpath", "")) {
+ my_errorf("Failed to enable the sandbox");
+ exit(EXIT_FAILURE);
+ }
+#endif
+
+#ifdef HAVE_LINUX_LANDLOCK
+ // Prevent the process from gaining new privileges. This must be done
+ // before landlock_restrict_self(2) but since we will never need new
+ // privileges, this call can be done here already.
+ //
+ // This is supported since Linux 3.5. Ignore the return value to
+ // keep compatibility with old kernels. landlock_restrict_self(2)
+ // will fail if the no_new_privs attribute isn't set, thus if prctl()
+ // fails here the error will still be detected when it matters.
+ (void)prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+#endif
+
// Initialize progname which we will be used in error messages.
tuklib_progname_init(argv);
@@ -295,24 +435,42 @@ main(int argc, char **argv)
if (optind == argc) {
// No filenames given, decode from stdin.
+#ifdef ENABLE_SANDBOX
+ sandbox_enter(STDIN_FILENO);
+#endif
uncompress(&strm, stdin, "(stdin)");
} else {
// Loop through the filenames given on the command line.
do {
+ FILE *src_file;
+ const char *src_name;
+
// "-" indicates stdin.
if (strcmp(argv[optind], "-") == 0) {
- uncompress(&strm, stdin, "(stdin)");
+ src_file = stdin;
+ src_name = "(stdin)";
} else {
- FILE *file = fopen(argv[optind], "rb");
- if (file == NULL) {
- my_errorf("%s: %s", argv[optind],
+ src_name = argv[optind];
+ src_file = fopen(src_name, "rb");
+ if (src_file == NULL) {
+ my_errorf("%s: %s", src_name,
strerror(errno));
exit(EXIT_FAILURE);
}
-
- uncompress(&strm, file, argv[optind]);
- fclose(file);
}
+#ifdef ENABLE_SANDBOX
+ // Enable the strict sandbox for the last file.
+ // Then the process can no longer open additional
+ // files. The typical xzdec use case is to decompress
+ // a single file so this way the strictest sandboxing
+ // is used in most cases.
+ if (optind == argc - 1)
+ sandbox_enter(fileno(src_file));
+#endif
+ uncompress(&strm, src_file, src_name);
+
+ if (src_file != stdin)
+ (void)fclose(src_file);
} while (++optind < argc);
}
diff --git a/src/xzdec/xzdec_w32res.rc b/src/xzdec/xzdec_w32res.rc
index 0e26a22..fdbb102 100644
--- a/src/xzdec/xzdec_w32res.rc
+++ b/src/xzdec/xzdec_w32res.rc
@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: 0BSD */
+
/*
* Author: Lasse Collin
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
*/
#define MY_TYPE VFT_APP