aboutsummaryrefslogtreecommitdiffstats
path: root/meta
diff options
context:
space:
mode:
Diffstat (limited to 'meta')
-rw-r--r--meta/classes/buildhistory.bbclass30
-rw-r--r--meta/classes/cve-check.bbclass2
-rw-r--r--meta/classes/populate_sdk_base.bbclass11
-rw-r--r--meta/classes/rootfs-postcommands.bbclass2
-rw-r--r--meta/classes/sanity.bbclass2
-rw-r--r--meta/classes/sstate.bbclass16
-rw-r--r--meta/classes/uboot-sign.bbclass16
-rw-r--r--meta/classes/uninative.bbclass2
-rw-r--r--meta/conf/distro/include/cve-extra-exclusions.inc9
-rw-r--r--meta/conf/distro/include/default-distrovars.inc2
-rw-r--r--meta/conf/distro/include/maintainers.inc2
-rw-r--r--meta/conf/distro/include/yocto-uninative.inc11
-rw-r--r--meta/conf/machine/include/arm/arch-armv8-5a.inc19
-rw-r--r--meta/conf/machine/include/arm/armv9a/tune-neoversen2.inc22
-rw-r--r--meta/conf/machine/include/tune-cortexa72.inc12
-rw-r--r--meta/files/toolchain-shar-relocate.sh2
-rw-r--r--meta/lib/oe/patch.py21
-rw-r--r--meta/lib/oe/reproducible.py2
-rw-r--r--meta/lib/oe/sdk.py4
-rw-r--r--meta/lib/oeqa/runtime/cases/parselogs.py14
-rw-r--r--meta/lib/oeqa/selftest/cases/bbtests.py31
-rw-r--r--meta/lib/oeqa/selftest/cases/devtool.py5
-rw-r--r--meta/lib/oeqa/selftest/cases/recipetool.py2
-rw-r--r--meta/lib/oeqa/selftest/cases/reproducible.py10
-rw-r--r--meta/lib/oeqa/selftest/cases/runtime_test.py7
-rw-r--r--meta/recipes-bsp/grub/files/CVE-2021-3981-grub-mkconfig-Restore-umask-for-the-grub.cfg.patch49
-rw-r--r--meta/recipes-bsp/grub/grub2.inc1
-rw-r--r--meta/recipes-connectivity/mobile-broadband-provider-info/mobile-broadband-provider-info_git.bb7
-rw-r--r--meta/recipes-connectivity/openssl/openssl/reproducibility.patch22
-rw-r--r--meta/recipes-connectivity/openssl/openssl_1.1.1n.bb (renamed from meta/recipes-connectivity/openssl/openssl_1.1.1l.bb)4
-rw-r--r--meta/recipes-connectivity/socat/socat_1.7.4.1.bb2
-rw-r--r--meta/recipes-core/busybox/busybox-inittab_1.33.2.bb (renamed from meta/recipes-core/busybox/busybox-inittab_1.33.0.bb)0
-rw-r--r--meta/recipes-core/busybox/busybox/0001-awk-fix-CVEs.patch3266
-rw-r--r--meta/recipes-core/busybox/busybox/0002-man-fix-segfault-in-man-1.patch30
-rw-r--r--meta/recipes-core/busybox/busybox_1.33.2.bb (renamed from meta/recipes-core/busybox/busybox_1.33.1.bb)4
-rw-r--r--meta/recipes-core/expat/expat/CVE-2021-45960.patch65
-rw-r--r--meta/recipes-core/expat/expat/CVE-2021-46143.patch49
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-22822-27.patch257
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-23852.patch33
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-23990.patch49
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-25235.patch261
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-25236-1.patch116
-rw-r--r--meta/recipes-core/expat/expat/CVE-2022-25236-2.patch232
-rw-r--r--meta/recipes-core/expat/expat_2.2.10.bb14
-rw-r--r--meta/recipes-core/glibc/glibc-version.inc2
-rw-r--r--meta/recipes-core/glibc/glibc_2.33.bb2
-rw-r--r--meta/recipes-core/images/build-appliance-image_15.0.0.bb2
-rwxr-xr-xmeta/recipes-core/initrdscripts/initramfs-framework/finish12
-rw-r--r--meta/recipes-core/libxml/libxml2/CVE-2022-23308-fix-regression.patch99
-rw-r--r--meta/recipes-core/libxml/libxml2/CVE-2022-23308.patch209
-rw-r--r--meta/recipes-core/libxml/libxml2_2.9.10.bb2
-rw-r--r--meta/recipes-core/os-release/os-release.bb4
-rw-r--r--meta/recipes-core/zlib/zlib/CVE-2018-25032.patch347
-rw-r--r--meta/recipes-core/zlib/zlib_1.2.11.bb1
-rw-r--r--meta/recipes-devtools/binutils/binutils-2.36.inc7
-rw-r--r--meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch201
-rw-r--r--meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch2006
-rw-r--r--meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch255
-rw-r--r--meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch170
-rw-r--r--meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch171
-rw-r--r--meta/recipes-devtools/ccache/ccache_4.2.1.bb (renamed from meta/recipes-devtools/ccache/ccache_4.2.bb)4
-rw-r--r--meta/recipes-devtools/e2fsprogs/e2fsprogs.inc3
-rw-r--r--meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch66
-rw-r--r--meta/recipes-devtools/gcc/gcc-10.3.inc (renamed from meta/recipes-devtools/gcc/gcc-10.2.inc)18
-rw-r--r--meta/recipes-devtools/gcc/gcc-cross-canadian_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-cross-canadian_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc-cross_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-cross_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc-crosssdk_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-crosssdk_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc-runtime_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-runtime_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc-sanitizers_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-sanitizers_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc-source_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc-source_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch22
-rw-r--r--meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch2906
-rw-r--r--meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch66
-rw-r--r--meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch202
-rw-r--r--meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch2270
-rw-r--r--meta/recipes-devtools/gcc/gcc/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch607
-rw-r--r--meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch1724
-rw-r--r--meta/recipes-devtools/gcc/gcc/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch658
-rw-r--r--meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch138
-rw-r--r--meta/recipes-devtools/gcc/gcc/0005-CVE-2021-42574.patch575
-rw-r--r--meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch5
-rw-r--r--meta/recipes-devtools/gcc/gcc/0033-Re-introduce-spe-commandline-options.patch2
-rw-r--r--meta/recipes-devtools/gcc/gcc/0036-mingw32-Enable-operation_not_supported.patch4
-rw-r--r--meta/recipes-devtools/gcc/gcc_10.3.bb (renamed from meta/recipes-devtools/gcc/gcc_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/libgcc-initial_10.3.bb (renamed from meta/recipes-devtools/gcc/libgcc-initial_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/libgcc_10.3.bb (renamed from meta/recipes-devtools/gcc/libgcc_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gcc/libgfortran_10.3.bb (renamed from meta/recipes-devtools/gcc/libgfortran_10.2.bb)0
-rw-r--r--meta/recipes-devtools/gnu-config/gnu-config_git.bb2
-rw-r--r--meta/recipes-devtools/go/go-1.16.15.inc (renamed from meta/recipes-devtools/go/go-1.16.8.inc)6
-rw-r--r--meta/recipes-devtools/go/go-binary-native_1.16.15.bb (renamed from meta/recipes-devtools/go/go-binary-native_1.16.8.bb)4
-rw-r--r--meta/recipes-devtools/go/go-cross-canadian_1.16.15.bb (renamed from meta/recipes-devtools/go/go-cross-canadian_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/go/go-cross_1.16.15.bb (renamed from meta/recipes-devtools/go/go-cross_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/go/go-crosssdk_1.16.15.bb (renamed from meta/recipes-devtools/go/go-crosssdk_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/go/go-native_1.16.15.bb (renamed from meta/recipes-devtools/go/go-native_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/go/go-runtime_1.16.15.bb (renamed from meta/recipes-devtools/go/go-runtime_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/go/go_1.16.15.bb (renamed from meta/recipes-devtools/go/go_1.16.8.bb)0
-rw-r--r--meta/recipes-devtools/patchelf/patchelf/0001-merge-from-PR243.patch47
-rw-r--r--meta/recipes-devtools/patchelf/patchelf_0.12.bb1
-rw-r--r--meta/recipes-devtools/python-numpy/files/CVE-2021-41496.patch64
-rw-r--r--meta/recipes-devtools/python-numpy/python3-numpy_1.20.1.bb1
-rw-r--r--meta/recipes-devtools/python/python3-pyelftools_0.27.bb2
-rw-r--r--meta/recipes-devtools/python/python3/0001-Makefile-fix-Issue36464-parallel-build-race-problem.patch34
-rw-r--r--meta/recipes-devtools/python/python3/0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch20
-rw-r--r--meta/recipes-devtools/python/python3_3.9.9.bb (renamed from meta/recipes-devtools/python/python3_3.9.5.bb)3
-rw-r--r--meta/recipes-devtools/qemu/qemu.inc5
-rw-r--r--meta/recipes-devtools/qemu/qemu/CVE-2021-20196_1.patch54
-rw-r--r--meta/recipes-devtools/qemu/qemu/CVE-2021-20196_2.patch67
-rw-r--r--meta/recipes-devtools/qemu/qemu/CVE-2021-3713.patch68
-rw-r--r--meta/recipes-devtools/qemu/qemu/CVE-2021-3748.patch127
-rw-r--r--meta/recipes-devtools/qemu/qemu/CVE-2021-3930.patch53
-rw-r--r--meta/recipes-devtools/ruby/ruby/CVE-2021-31799.patch57
-rw-r--r--meta/recipes-devtools/ruby/ruby/CVE-2021-31810.patch258
-rw-r--r--meta/recipes-devtools/ruby/ruby/CVE-2021-32066.patch102
-rw-r--r--meta/recipes-devtools/ruby/ruby_3.0.3.bb (renamed from meta/recipes-devtools/ruby/ruby_3.0.1.bb)7
-rw-r--r--meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-1.patch135
-rw-r--r--meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-2.patch109
-rw-r--r--meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-3.patch330
-rw-r--r--meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072.patch316
-rw-r--r--meta/recipes-devtools/squashfs-tools/squashfs-tools_git.bb4
-rw-r--r--meta/recipes-devtools/unfs3/unfs3_git.bb2
-rw-r--r--meta/recipes-extended/asciidoc/asciidoc_9.1.0.bb2
-rw-r--r--meta/recipes-extended/cups/cups.inc2
-rw-r--r--meta/recipes-extended/ghostscript/ghostscript/CVE-2021-45949.patch65
-rw-r--r--meta/recipes-extended/ghostscript/ghostscript/check-stack-limits-after-function-evalution.patch51
-rw-r--r--meta/recipes-extended/ghostscript/ghostscript_9.53.3.bb2
-rw-r--r--meta/recipes-extended/libarchive/libarchive_3.5.3.bb (renamed from meta/recipes-extended/libarchive/libarchive_3.5.1.bb)2
-rw-r--r--meta/recipes-extended/lighttpd/lighttpd/0001-mod_extforward-fix-out-of-bounds-OOB-write-fixes-313.patch97
-rw-r--r--meta/recipes-extended/lighttpd/lighttpd_1.4.59.bb1
-rw-r--r--meta/recipes-extended/mc/files/0001-Ticket-4200-fix-FTBFS-with-ncurses-build-with-disabl.patch87
-rw-r--r--meta/recipes-extended/mc/mc_4.8.26.bb5
-rw-r--r--meta/recipes-extended/pigz/files/0001-Fix-bug-when-combining-l-with-d.patch50
-rw-r--r--meta/recipes-extended/pigz/pigz_2.6.bb3
-rw-r--r--meta/recipes-extended/zip/zip-3.0/0001-configure-use-correct-CPP.patch47
-rw-r--r--meta/recipes-extended/zip/zip-3.0/0002-configure-support-PIC-code-build.patch34
-rw-r--r--meta/recipes-extended/zip/zip_3.0.bb2
-rw-r--r--meta/recipes-gnome/epiphany/epiphany_3.38.2.bb1
-rw-r--r--meta/recipes-gnome/epiphany/files/encode-untrusted-data.patch707
-rw-r--r--meta/recipes-graphics/virglrenderer/virglrenderer/cve-2022-0135.patch117
-rw-r--r--meta/recipes-graphics/virglrenderer/virglrenderer/cve-2022-0175.patch112
-rw-r--r--meta/recipes-graphics/virglrenderer/virglrenderer_0.8.2.bb4
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg.inc10
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg/CVE-2021-4008.patch59
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg/CVE-2021-4009.patch50
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg/CVE-2021-4010.patch39
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg/CVE-2021-4011.patch40
-rw-r--r--meta/recipes-graphics/xorg-xserver/xserver-xorg_1.20.10.bb4
-rw-r--r--meta/recipes-kernel/linux-firmware/linux-firmware_20220310.bb (renamed from meta/recipes-kernel/linux-firmware/linux-firmware_20211027.bb)7
-rw-r--r--meta/recipes-kernel/linux/linux-yocto-rt_5.10.bb6
-rw-r--r--meta/recipes-kernel/linux/linux-yocto-rt_5.4.bb6
-rw-r--r--meta/recipes-kernel/linux/linux-yocto-tiny_5.10.bb8
-rw-r--r--meta/recipes-kernel/linux/linux-yocto-tiny_5.4.bb8
-rw-r--r--meta/recipes-kernel/linux/linux-yocto_5.10.bb26
-rw-r--r--meta/recipes-kernel/linux/linux-yocto_5.4.bb22
-rw-r--r--meta/recipes-kernel/lttng/lttng-modules_2.12.8.bb (renamed from meta/recipes-kernel/lttng/lttng-modules_2.12.6.bb)2
-rw-r--r--meta/recipes-kernel/wireless-regdb/wireless-regdb_2022.02.18.bb (renamed from meta/recipes-kernel/wireless-regdb/wireless-regdb_2021.08.28.bb)2
-rw-r--r--meta/recipes-multimedia/flac/flac/CVE-2021-0561.patch41
-rw-r--r--meta/recipes-multimedia/flac/flac_1.3.3.bb1
-rw-r--r--meta/recipes-multimedia/gstreamer/gst-devtools_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gst-devtools_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gst-examples_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gst-examples_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-libav_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-libav_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-omx_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-omx_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-bad_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-bad_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-base_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-base_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-good/0002-rtpjitterbuffer-Fix-parsing-of-the-mediaclk-direct-f.patch33
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-good_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-good_1.18.4.bb)3
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-ugly_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-plugins-ugly_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-python_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-python_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-rtsp-server_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-rtsp-server_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0-vaapi_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0-vaapi_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0/0002-Remove-unused-valgrind-detection.patch14
-rw-r--r--meta/recipes-multimedia/gstreamer/gstreamer1.0_1.18.6.bb (renamed from meta/recipes-multimedia/gstreamer/gstreamer1.0_1.18.4.bb)2
-rw-r--r--meta/recipes-multimedia/libsndfile/libsndfile1/CVE-2021-4156.patch32
-rw-r--r--meta/recipes-multimedia/libsndfile/libsndfile1_1.0.28.bb1
-rw-r--r--meta/recipes-multimedia/speex/speex/CVE-2020-23903.patch30
-rw-r--r--meta/recipes-multimedia/speex/speex_1.2.0.bb4
-rw-r--r--meta/recipes-sato/webkit/webkitgtk/CVE-2021-42762.patch468
-rw-r--r--meta/recipes-sato/webkit/webkitgtk/reproducibility.patch22
-rw-r--r--meta/recipes-sato/webkit/webkitgtk_2.30.6.bb (renamed from meta/recipes-sato/webkit/webkitgtk_2.30.5.bb)4
-rw-r--r--meta/recipes-support/curl/curl/CVE-2021-22945.patch35
-rw-r--r--meta/recipes-support/curl/curl/CVE-2021-22946.patch333
-rw-r--r--meta/recipes-support/curl/curl/CVE-2021-22947.patch357
-rw-r--r--meta/recipes-support/curl/curl_7.75.0.bb8
-rw-r--r--meta/recipes-support/gmp/gmp/cve-2021-43618.patch27
-rw-r--r--meta/recipes-support/gmp/gmp_6.2.1.bb1
-rw-r--r--meta/recipes-support/libgcrypt/libgcrypt_1.9.4.bb (renamed from meta/recipes-support/libgcrypt/libgcrypt_1.9.3.bb)2
-rw-r--r--meta/recipes-support/libpcre/libpcre2_10.36.bb4
-rw-r--r--meta/recipes-support/libpcre/libpcre_8.44.bb2
-rw-r--r--meta/recipes-support/libusb/libusb1_1.0.24.bb6
-rw-r--r--meta/recipes-support/vim/files/0001-src-Makefile-improve-reproducibility.patch13
-rw-r--r--meta/recipes-support/vim/files/CVE-2021-3778.patch34
-rw-r--r--meta/recipes-support/vim/files/CVE-2021-3872.patch57
-rw-r--r--meta/recipes-support/vim/files/b7081e135a16091c93f6f5f7525a5c58fb7ca9f9.patch207
-rw-r--r--meta/recipes-support/vim/files/disable_acl_header_check.patch15
-rw-r--r--meta/recipes-support/vim/files/no-path-adjust.patch8
-rw-r--r--meta/recipes-support/vim/files/racefix.patch6
-rw-r--r--meta/recipes-support/vim/files/vim-add-knob-whether-elf.h-are-checked.patch13
-rw-r--r--meta/recipes-support/vim/vim.inc15
197 files changed, 19752 insertions, 3101 deletions
diff --git a/meta/classes/buildhistory.bbclass b/meta/classes/buildhistory.bbclass
index 49af61c9c5..b2cf9aa28a 100644
--- a/meta/classes/buildhistory.bbclass
+++ b/meta/classes/buildhistory.bbclass
@@ -960,23 +960,19 @@ def write_latest_srcrev(d, pkghistdir):
value = value.replace('"', '').strip()
old_tag_srcrevs[key] = value
with open(srcrevfile, 'w') as f:
- orig_srcrev = d.getVar('SRCREV', False) or 'INVALID'
- if orig_srcrev != 'INVALID':
- f.write('# SRCREV = "%s"\n' % orig_srcrev)
- if len(srcrevs) > 1:
- for name, srcrev in sorted(srcrevs.items()):
- orig_srcrev = d.getVar('SRCREV_%s' % name, False)
- if orig_srcrev:
- f.write('# SRCREV_%s = "%s"\n' % (name, orig_srcrev))
- f.write('SRCREV_%s = "%s"\n' % (name, srcrev))
- else:
- f.write('SRCREV = "%s"\n' % next(iter(srcrevs.values())))
- if len(tag_srcrevs) > 0:
- for name, srcrev in sorted(tag_srcrevs.items()):
- f.write('# tag_%s = "%s"\n' % (name, srcrev))
- if name in old_tag_srcrevs and old_tag_srcrevs[name] != srcrev:
- pkg = d.getVar('PN')
- bb.warn("Revision for tag %s in package %s was changed since last build (from %s to %s)" % (name, pkg, old_tag_srcrevs[name], srcrev))
+ for name, srcrev in sorted(srcrevs.items()):
+ suffix = "_" + name
+ if name == "default":
+ suffix = ""
+ orig_srcrev = d.getVar('SRCREV%s' % suffix, False)
+ if orig_srcrev:
+ f.write('# SRCREV%s = "%s"\n' % (suffix, orig_srcrev))
+ f.write('SRCREV%s = "%s"\n' % (suffix, srcrev))
+ for name, srcrev in sorted(tag_srcrevs.items()):
+ f.write('# tag_%s = "%s"\n' % (name, srcrev))
+ if name in old_tag_srcrevs and old_tag_srcrevs[name] != srcrev:
+ pkg = d.getVar('PN')
+ bb.warn("Revision for tag %s in package %s was changed since last build (from %s to %s)" % (name, pkg, old_tag_srcrevs[name], srcrev))
else:
if os.path.exists(srcrevfile):
diff --git a/meta/classes/cve-check.bbclass b/meta/classes/cve-check.bbclass
index 4fa1a64f85..a95e810605 100644
--- a/meta/classes/cve-check.bbclass
+++ b/meta/classes/cve-check.bbclass
@@ -110,6 +110,7 @@ python do_cve_check () {
}
addtask cve_check before do_build after do_fetch
+do_cve_check[lockfiles] += "${CVE_CHECK_DB_FILE_LOCK}"
do_cve_check[depends] = "cve-update-db-native:do_fetch"
do_cve_check[nostamp] = "1"
@@ -142,6 +143,7 @@ python cve_check_write_rootfs_manifest () {
manifest_name = d.getVar("CVE_CHECK_MANIFEST")
cve_tmp_file = d.getVar("CVE_CHECK_TMP_FILE")
+ bb.utils.mkdirhier(os.path.dirname(manifest_name))
shutil.copyfile(cve_tmp_file, manifest_name)
if manifest_name and os.path.exists(manifest_name):
diff --git a/meta/classes/populate_sdk_base.bbclass b/meta/classes/populate_sdk_base.bbclass
index 2d33611ddd..76757a3a9d 100644
--- a/meta/classes/populate_sdk_base.bbclass
+++ b/meta/classes/populate_sdk_base.bbclass
@@ -90,6 +90,8 @@ SDK_HOST_MANIFEST = "${SDKDEPLOYDIR}/${TOOLCHAIN_OUTPUTNAME}.host.manifest"
SDK_EXT_TARGET_MANIFEST = "${SDK_DEPLOY}/${TOOLCHAINEXT_OUTPUTNAME}.target.manifest"
SDK_EXT_HOST_MANIFEST = "${SDK_DEPLOY}/${TOOLCHAINEXT_OUTPUTNAME}.host.manifest"
+SDK_PRUNE_SYSROOT_DIRS ?= "/dev"
+
python write_target_sdk_manifest () {
from oe.sdk import sdk_list_installed_packages
from oe.utils import format_pkg_list
@@ -101,6 +103,12 @@ python write_target_sdk_manifest () {
output.write(format_pkg_list(pkgs, 'ver'))
}
+sdk_prune_dirs () {
+ for d in ${SDK_PRUNE_SYSROOT_DIRS}; do
+ rm -rf ${SDK_OUTPUT}${SDKTARGETSYSROOT}$d
+ done
+}
+
python write_sdk_test_data() {
from oe.data import export2json
testdata = "%s/%s.testdata.json" % (d.getVar('SDKDEPLOYDIR'), d.getVar('TOOLCHAIN_OUTPUTNAME'))
@@ -120,8 +128,9 @@ python write_host_sdk_manifest () {
}
POPULATE_SDK_POST_TARGET_COMMAND_append = " write_sdk_test_data ; "
-POPULATE_SDK_POST_TARGET_COMMAND_append_task-populate-sdk = " write_target_sdk_manifest ; "
+POPULATE_SDK_POST_TARGET_COMMAND_append_task-populate-sdk = " write_target_sdk_manifest; sdk_prune_dirs; "
POPULATE_SDK_POST_HOST_COMMAND_append_task-populate-sdk = " write_host_sdk_manifest; "
+
SDK_PACKAGING_COMMAND = "${@'${SDK_PACKAGING_FUNC};' if '${SDK_PACKAGING_FUNC}' else ''}"
SDK_POSTPROCESS_COMMAND = " create_sdk_files; check_sdk_sysroots; archive_sdk; ${SDK_PACKAGING_COMMAND} "
diff --git a/meta/classes/rootfs-postcommands.bbclass b/meta/classes/rootfs-postcommands.bbclass
index e66ed5938b..87b5751e24 100644
--- a/meta/classes/rootfs-postcommands.bbclass
+++ b/meta/classes/rootfs-postcommands.bbclass
@@ -60,7 +60,7 @@ python () {
}
systemd_create_users () {
- for conffile in ${IMAGE_ROOTFS}/usr/lib/sysusers.d/systemd.conf ${IMAGE_ROOTFS}/usr/lib/sysusers.d/systemd-remote.conf; do
+ for conffile in ${IMAGE_ROOTFS}/usr/lib/sysusers.d/*.conf; do
[ -e $conffile ] || continue
grep -v "^#" $conffile | sed -e '/^$/d' | while read type name id comment; do
if [ "$type" = "u" ]; then
diff --git a/meta/classes/sanity.bbclass b/meta/classes/sanity.bbclass
index a2ac4eeb80..c8a42dc8bf 100644
--- a/meta/classes/sanity.bbclass
+++ b/meta/classes/sanity.bbclass
@@ -395,7 +395,7 @@ def check_connectivity(d):
msg += " Please ensure your host's network is configured correctly.\n"
msg += " If your ISP or network is blocking the above URL,\n"
msg += " try with another domain name, for example by setting:\n"
- msg += " CONNECTIVITY_CHECK_URIS = \"https://www.yoctoproject.org/\""
+ msg += " CONNECTIVITY_CHECK_URIS = \"https://www.example.com/\""
msg += " You could also set BB_NO_NETWORK = \"1\" to disable network\n"
msg += " access if all required sources are on local disk.\n"
retval = msg
diff --git a/meta/classes/sstate.bbclass b/meta/classes/sstate.bbclass
index da29225983..de6e7fa960 100644
--- a/meta/classes/sstate.bbclass
+++ b/meta/classes/sstate.bbclass
@@ -827,14 +827,18 @@ sstate_create_package () {
fi
chmod 0664 $TFILE
# Skip if it was already created by some other process
- if [ ! -e ${SSTATE_PKG} ]; then
+ if [ -h ${SSTATE_PKG} ] && [ ! -e ${SSTATE_PKG} ]; then
+ # There is a symbolic link, but it links to nothing.
+ # Forcefully replace it with the new file.
+ ln -f $TFILE ${SSTATE_PKG} || true
+ elif [ ! -e ${SSTATE_PKG} ]; then
# Move into place using ln to attempt an atomic op.
# Abort if it already exists
- ln $TFILE ${SSTATE_PKG} && rm $TFILE
+ ln $TFILE ${SSTATE_PKG} || true
else
- rm $TFILE
+ touch ${SSTATE_PKG} 2>/dev/null || true
fi
- touch ${SSTATE_PKG} 2>/dev/null || true
+ rm $TFILE
}
python sstate_sign_package () {
@@ -864,7 +868,7 @@ python sstate_report_unihash() {
sstate_unpack_package () {
tar -xvzf ${SSTATE_PKG}
# update .siginfo atime on local/NFS mirror if it is a symbolic link
- [ ! -h ${SSTATE_PKG}.siginfo ] || touch -a ${SSTATE_PKG}.siginfo 2>/dev/null || true
+ [ ! -h ${SSTATE_PKG}.siginfo ] || [ ! -e ${SSTATE_PKG}.siginfo ] || touch -a ${SSTATE_PKG}.siginfo 2>/dev/null || true
# update each symbolic link instead of any referenced file
touch --no-dereference ${SSTATE_PKG} 2>/dev/null || true
[ ! -e ${SSTATE_PKG}.sig ] || touch --no-dereference ${SSTATE_PKG}.sig 2>/dev/null || true
@@ -946,7 +950,7 @@ def sstate_checkhashes(sq_data, d, siginfo=False, currentcount=0, summary=True,
localdata2 = bb.data.createCopy(localdata)
srcuri = "file://" + sstatefile
- localdata.setVar('SRC_URI', srcuri)
+ localdata2.setVar('SRC_URI', srcuri)
bb.debug(2, "SState: Attempting to fetch %s" % srcuri)
try:
diff --git a/meta/classes/uboot-sign.bbclass b/meta/classes/uboot-sign.bbclass
index ba48f24b10..fca9de2934 100644
--- a/meta/classes/uboot-sign.bbclass
+++ b/meta/classes/uboot-sign.bbclass
@@ -131,6 +131,20 @@ concat_dtb_helper() {
elif [ -e "${DEPLOYDIR}/${UBOOT_NODTB_IMAGE}" -a -e "$deployed_uboot_dtb_binary" ]; then
cd ${DEPLOYDIR}
cat ${UBOOT_NODTB_IMAGE} $deployed_uboot_dtb_binary | tee ${B}/${CONFIG_B_PATH}/${UBOOT_BINARY} > ${UBOOT_IMAGE}
+
+ if [ -n "${UBOOT_CONFIG}" ]
+ then
+ for config in ${UBOOT_MACHINE}; do
+ i=$(expr $i + 1);
+ for type in ${UBOOT_CONFIG}; do
+ j=$(expr $j + 1);
+ if [ $j -eq $i ]
+ then
+ cp ${UBOOT_IMAGE} ${B}/${CONFIG_B_PATH}/u-boot-$type.${UBOOT_SUFFIX}
+ fi
+ done
+ done
+ fi
else
bbwarn "Failure while adding public key to u-boot binary. Verified boot won't be available."
fi
@@ -205,7 +219,7 @@ install_helper() {
fi
}
-# Install SPL dtb and u-boot nodtb to datadir,
+# Install SPL dtb and u-boot nodtb to datadir,
install_spl_helper() {
if [ -f "${SPL_DIR}/${SPL_DTB_BINARY}" ]; then
install -Dm 0644 ${SPL_DIR}/${SPL_DTB_BINARY} ${D}${datadir}/${SPL_DTB_IMAGE}
diff --git a/meta/classes/uninative.bbclass b/meta/classes/uninative.bbclass
index 3c7ccd66f4..4412d7c567 100644
--- a/meta/classes/uninative.bbclass
+++ b/meta/classes/uninative.bbclass
@@ -2,7 +2,7 @@ UNINATIVE_LOADER ?= "${UNINATIVE_STAGING_DIR}-uninative/${BUILD_ARCH}-linux/lib/
UNINATIVE_STAGING_DIR ?= "${STAGING_DIR}"
UNINATIVE_URL ?= "unset"
-UNINATIVE_TARBALL ?= "${BUILD_ARCH}-nativesdk-libc.tar.xz"
+UNINATIVE_TARBALL ?= "${BUILD_ARCH}-nativesdk-libc-${UNINATIVE_VERSION}.tar.xz"
# Example checksums
#UNINATIVE_CHECKSUM[aarch64] = "dead"
#UNINATIVE_CHECKSUM[i686] = "dead"
diff --git a/meta/conf/distro/include/cve-extra-exclusions.inc b/meta/conf/distro/include/cve-extra-exclusions.inc
index 561386b706..0b8bec312b 100644
--- a/meta/conf/distro/include/cve-extra-exclusions.inc
+++ b/meta/conf/distro/include/cve-extra-exclusions.inc
@@ -43,3 +43,12 @@ CVE_CHECK_WHITELIST += "CVE-2010-4756"
# CVE applies to a netapp product as well as flagging a general issue. We don't ship anything
# exposing this interface in an exploitable way
CVE_CHECK_WHITELIST += "CVE-2020-29509 CVE-2020-29511"
+
+# db
+# Since Oracle relicensed bdb, the open source community is slowly but surely replacing bdb with
+# supported and open source friendly alternatives. As a result these CVEs are unlikely to ever be fixed.
+CVE_CHECK_WHITELIST += "CVE-2015-2583 CVE-2015-2624 CVE-2015-2626 CVE-2015-2640 CVE-2015-2654 \
+CVE-2015-2656 CVE-2015-4754 CVE-2015-4764 CVE-2015-4774 CVE-2015-4775 CVE-2015-4776 CVE-2015-4777 \
+CVE-2015-4778 CVE-2015-4779 CVE-2015-4780 CVE-2015-4781 CVE-2015-4782 CVE-2015-4783 CVE-2015-4784 \
+CVE-2015-4785 CVE-2015-4786 CVE-2015-4787 CVE-2015-4788 CVE-2015-4789 CVE-2015-4790 CVE-2016-0682 \
+CVE-2016-0689 CVE-2016-0692 CVE-2016-0694 CVE-2016-3418 CVE-2020-2981"
diff --git a/meta/conf/distro/include/default-distrovars.inc b/meta/conf/distro/include/default-distrovars.inc
index 0240589c81..038acc1504 100644
--- a/meta/conf/distro/include/default-distrovars.inc
+++ b/meta/conf/distro/include/default-distrovars.inc
@@ -48,4 +48,4 @@ KERNEL_IMAGETYPES ??= "${KERNEL_IMAGETYPE}"
# fetch from the network (and warn you if not). To disable the test set
# the variable to be empty.
# Git example url: git://git.yoctoproject.org/yocto-firewall-test;protocol=git;rev=master;branch=master
-CONNECTIVITY_CHECK_URIS ?= "https://www.example.com/"
+CONNECTIVITY_CHECK_URIS ?= "https://yoctoproject.org/connectivity.html"
diff --git a/meta/conf/distro/include/maintainers.inc b/meta/conf/distro/include/maintainers.inc
index 5d453a6fcd..5064ee6b79 100644
--- a/meta/conf/distro/include/maintainers.inc
+++ b/meta/conf/distro/include/maintainers.inc
@@ -191,7 +191,7 @@ RECIPE_MAINTAINER_pn-gcc-cross-canadian-${TRANSLATED_TARGET_ARCH} = "Khem Raj <r
RECIPE_MAINTAINER_pn-gcc-crosssdk-${SDK_SYS} = "Khem Raj <raj.khem@gmail.com>"
RECIPE_MAINTAINER_pn-gcc-runtime = "Khem Raj <raj.khem@gmail.com>"
RECIPE_MAINTAINER_pn-gcc-sanitizers = "Khem Raj <raj.khem@gmail.com>"
-RECIPE_MAINTAINER_pn-gcc-source-10.2.0 = "Khem Raj <raj.khem@gmail.com>"
+RECIPE_MAINTAINER_pn-gcc-source-10.3.0 = "Khem Raj <raj.khem@gmail.com>"
RECIPE_MAINTAINER_pn-gconf = "Ross Burton <ross.burton@arm.com>"
RECIPE_MAINTAINER_pn-gcr = "Alexander Kanavin <alex.kanavin@gmail.com>"
RECIPE_MAINTAINER_pn-gdb = "Khem Raj <raj.khem@gmail.com>"
diff --git a/meta/conf/distro/include/yocto-uninative.inc b/meta/conf/distro/include/yocto-uninative.inc
index 3165fc93b8..bfe05ce1eb 100644
--- a/meta/conf/distro/include/yocto-uninative.inc
+++ b/meta/conf/distro/include/yocto-uninative.inc
@@ -6,9 +6,10 @@
# to the distro running on the build machine.
#
-UNINATIVE_MAXGLIBCVERSION = "2.34"
+UNINATIVE_MAXGLIBCVERSION = "2.35"
+UNINATIVE_VERSION = "3.5"
-UNINATIVE_URL ?= "http://downloads.yoctoproject.org/releases/uninative/3.4/"
-UNINATIVE_CHECKSUM[aarch64] ?= "3013cdda8f0dc6639ce1c80f33eabce66f06b890bd5b58739a6d7a92a0bb7100"
-UNINATIVE_CHECKSUM[i686] ?= "abed500de584aad63ec237546db20cdd0c69d8870a6f8e94ac31721ace64b376"
-UNINATIVE_CHECKSUM[x86_64] ?= "126f4f7f6f21084ee140dac3eb4c536b963837826b7c38599db0b512c3377ba2"
+UNINATIVE_URL ?= "http://downloads.yoctoproject.org/releases/uninative/${UNINATIVE_VERSION}/"
+UNINATIVE_CHECKSUM[aarch64] ?= "6de0771bd21e0fcb5e80388e5b561a8023b24083bcbf46e056a089982aff75d7"
+UNINATIVE_CHECKSUM[i686] ?= "8c8745becbfa1c341bae839c7eab56ddf17ce36c303bcd73d3b2f2f788b631c2"
+UNINATIVE_CHECKSUM[x86_64] ?= "e8047a5748e6f266165da141eb6d08b23674f30e477b0e5505b6403d50fbc4b2"
diff --git a/meta/conf/machine/include/arm/arch-armv8-5a.inc b/meta/conf/machine/include/arm/arch-armv8-5a.inc
new file mode 100644
index 0000000000..44c3b5bd22
--- /dev/null
+++ b/meta/conf/machine/include/arm/arch-armv8-5a.inc
@@ -0,0 +1,19 @@
+DEFAULTTUNE ?= "armv8-5a"
+
+TUNEVALID[armv8-5a] = "Enable instructions for ARMv8.5-a"
+TUNE_CCARGS .= "${@bb.utils.contains('TUNE_FEATURES', 'armv8-5a', ' -march=armv8.5-a', '', d)}"
+# TUNE crypto will be handled by arch-armv8a.inc below
+MACHINEOVERRIDES =. "${@bb.utils.contains('TUNE_FEATURES', 'armv8-5a', 'armv8-5a:', '', d)}"
+
+require conf/machine/include/arm/arch-armv8a.inc
+
+# Little Endian base configs
+AVAILTUNES += "armv8-5a armv8-5a-crypto"
+ARMPKGARCH_tune-armv8-5a ?= "armv8-5a"
+ARMPKGARCH_tune-armv8-5a-crypto ?= "armv8-5a"
+TUNE_FEATURES_tune-armv8-5a = "aarch64 armv8-5a"
+TUNE_FEATURES_tune-armv8-5a-crypto = "${TUNE_FEATURES_tune-armv8-5a} crypto"
+PACKAGE_EXTRA_ARCHS_tune-armv8-5a = "${PACKAGE_EXTRA_ARCHS_tune-armv8a} armv8-5a"
+PACKAGE_EXTRA_ARCHS_tune-armv8-5a-crypto = "${PACKAGE_EXTRA_ARCHS_tune-armv8-5a} armv8-5a-crypto"
+BASE_LIB_tune-armv8-5a = "lib64"
+BASE_LIB_tune-armv8-5a-crypto = "lib64"
diff --git a/meta/conf/machine/include/arm/armv9a/tune-neoversen2.inc b/meta/conf/machine/include/arm/armv9a/tune-neoversen2.inc
new file mode 100644
index 0000000000..dedabcf46e
--- /dev/null
+++ b/meta/conf/machine/include/arm/armv9a/tune-neoversen2.inc
@@ -0,0 +1,22 @@
+#
+# Tune Settings for Neoverse-N2
+#
+DEFAULTTUNE ?= "neoversen2"
+
+TUNEVALID[neoversen2] = "Enable Neoverse-N2 specific processor optimizations"
+TUNE_CCARGS .= "${@bb.utils.contains('TUNE_FEATURES', 'neoversen2', ' -mcpu=neoverse-n2', '', d)}"
+
+# Even though the Neoverse N2 core implemnts the Arm v9.0-A architecture,
+# but the support of it in GCC is based on the Arm v8.5-A architecture.
+require conf/machine/include/arm/arch-armv8-5a.inc
+
+# Little Endian base configs
+AVAILTUNES += "neoversen2 neoversen2-crypto"
+ARMPKGARCH_tune-neoversen2 = "neoversen2"
+ARMPKGARCH_tune-neoversen2-crypto = "neoversen2-crypto"
+TUNE_FEATURES_tune-neoversen2 = "${TUNE_FEATURES_tune-armv8-5a} neoversen2"
+TUNE_FEATURES_tune-neoversen2-crypto = "${TUNE_FEATURES_tune-neoversen2} crypto"
+PACKAGE_EXTRA_ARCHS_tune-neoversen2 = "${PACKAGE_EXTRA_ARCHS_tune-armv8-5a} neoversen2"
+PACKAGE_EXTRA_ARCHS_tune-neoversen2-crypto = "${PACKAGE_EXTRA_ARCHS_tune-armv8-5a-crypto} neoversen2 neoversen2-crypto"
+BASE_LIB_tune-neoversen2 = "lib64"
+BASE_LIB_tune-neoversen2-crypto = "lib64"
diff --git a/meta/conf/machine/include/tune-cortexa72.inc b/meta/conf/machine/include/tune-cortexa72.inc
index b3f68ab6e3..efb71ee0a1 100644
--- a/meta/conf/machine/include/tune-cortexa72.inc
+++ b/meta/conf/machine/include/tune-cortexa72.inc
@@ -6,8 +6,12 @@ TUNE_CCARGS .= "${@bb.utils.contains('TUNE_FEATURES', 'cortexa72', ' -mcpu=corte
require conf/machine/include/arm/arch-armv8a.inc
# Little Endian base configs
-AVAILTUNES += "cortexa72"
+AVAILTUNES += "cortexa72 cortexa72-crypto"
ARMPKGARCH_tune-cortexa72 = "cortexa72"
-TUNE_FEATURES_tune-cortexa72 = "${TUNE_FEATURES_tune-armv8a-crc-crypto} cortexa72"
-PACKAGE_EXTRA_ARCHS_tune-cortexa72 = "${PACKAGE_EXTRA_ARCHS_tune-armv8a-crc-crypto} cortexa72"
-BASE_LIB_tune-cortexa72 = "lib64"
+ARMPKGARCH_tune-cortexa72-crypto = "cortexa72"
+TUNE_FEATURES_tune-cortexa72 = "${TUNE_FEATURES_tune-armv8a-crc} cortexa72"
+TUNE_FEATURES_tune-cortexa72-crypto = "${TUNE_FEATURES_tune-cortexa72} crypto"
+PACKAGE_EXTRA_ARCHS_tune-cortexa72 = "${PACKAGE_EXTRA_ARCHS_tune-armv8-crc} cortexa72"
+PACKAGE_EXTRA_ARCHS_tune-cortexa72-crypto = "${PACKAGE_EXTRA_ARCHS_tune-armv8a-crc-crypto} cortexa72 cortexa72-crypto"
+BASE_LIB_tune-cortexa72 = "lib64"
+BASE_LIB_tune-cortexa72-crypto = "lib64"
diff --git a/meta/files/toolchain-shar-relocate.sh b/meta/files/toolchain-shar-relocate.sh
index 3ece04db0a..cee9adbf39 100644
--- a/meta/files/toolchain-shar-relocate.sh
+++ b/meta/files/toolchain-shar-relocate.sh
@@ -5,7 +5,7 @@ fi
# fix dynamic loader paths in all ELF SDK binaries
native_sysroot=$($SUDO_EXEC cat $env_setup_script |grep 'OECORE_NATIVE_SYSROOT='|cut -d'=' -f2|tr -d '"')
-dl_path=$($SUDO_EXEC find $native_sysroot/lib -name "ld-linux*")
+dl_path=$($SUDO_EXEC find $native_sysroot/lib -maxdepth 1 -name "ld-linux*")
if [ "$dl_path" = "" ] ; then
echo "SDK could not be set up. Relocate script unable to find ld-linux.so. Abort!"
exit 1
diff --git a/meta/lib/oe/patch.py b/meta/lib/oe/patch.py
index fccbedb519..9034fcae03 100644
--- a/meta/lib/oe/patch.py
+++ b/meta/lib/oe/patch.py
@@ -4,6 +4,7 @@
import oe.path
import oe.types
+import subprocess
class NotFoundError(bb.BBHandledException):
def __init__(self, path):
@@ -25,7 +26,6 @@ class CmdError(bb.BBHandledException):
def runcmd(args, dir = None):
import pipes
- import subprocess
if dir:
olddir = os.path.abspath(os.curdir)
@@ -56,6 +56,7 @@ def runcmd(args, dir = None):
if dir:
os.chdir(olddir)
+
class PatchError(Exception):
def __init__(self, msg):
self.msg = msg
@@ -298,6 +299,24 @@ class GitApplyTree(PatchTree):
PatchTree.__init__(self, dir, d)
self.commituser = d.getVar('PATCH_GIT_USER_NAME')
self.commitemail = d.getVar('PATCH_GIT_USER_EMAIL')
+ if not self._isInitialized():
+ self._initRepo()
+
+ def _isInitialized(self):
+ cmd = "git rev-parse --show-toplevel"
+ try:
+ output = runcmd(cmd.split(), self.dir).strip()
+ except CmdError as err:
+ ## runcmd returned non-zero which most likely means 128
+ ## Not a git directory
+ return False
+ ## Make sure repo is in builddir to not break top-level git repos
+ return os.path.samefile(output, self.dir)
+
+ def _initRepo(self):
+ runcmd("git init".split(), self.dir)
+ runcmd("git add .".split(), self.dir)
+ runcmd("git commit -a --allow-empty -m bitbake_patching_started".split(), self.dir)
@staticmethod
def extractPatchHeader(patchfile):
diff --git a/meta/lib/oe/reproducible.py b/meta/lib/oe/reproducible.py
index 204b9bd734..0938e4cb39 100644
--- a/meta/lib/oe/reproducible.py
+++ b/meta/lib/oe/reproducible.py
@@ -41,7 +41,7 @@ def find_git_folder(d, sourcedir):
for root, dirs, files in os.walk(workdir, topdown=True):
dirs[:] = [d for d in dirs if d not in exclude]
if '.git' in dirs:
- return root
+ return os.path.join(root, ".git")
bb.warn("Failed to find a git repository in WORKDIR: %s" % workdir)
return None
diff --git a/meta/lib/oe/sdk.py b/meta/lib/oe/sdk.py
index 37b59afd1a..27347667e8 100644
--- a/meta/lib/oe/sdk.py
+++ b/meta/lib/oe/sdk.py
@@ -115,6 +115,10 @@ def sdk_list_installed_packages(d, target, rootfs_dir=None):
rootfs_dir = [sdk_output, os.path.join(sdk_output, target_path)][target is True]
+ if target is False:
+ ipkgconf_sdk_target = d.getVar("IPKGCONF_SDK")
+ d.setVar("IPKGCONF_TARGET", ipkgconf_sdk_target)
+
img_type = d.getVar('IMAGE_PKGTYPE')
import importlib
cls = importlib.import_module('oe.package_manager.' + img_type)
diff --git a/meta/lib/oeqa/runtime/cases/parselogs.py b/meta/lib/oeqa/runtime/cases/parselogs.py
index 01b633d89e..c842f95c34 100644
--- a/meta/lib/oeqa/runtime/cases/parselogs.py
+++ b/meta/lib/oeqa/runtime/cases/parselogs.py
@@ -302,7 +302,7 @@ class ParseLogsTest(OERuntimeTestCase):
grepcmd = 'grep '
grepcmd += '-Ei "'
for error in errors:
- grepcmd += '\<' + error + '\>' + '|'
+ grepcmd += r'\<' + error + r'\>' + '|'
grepcmd = grepcmd[:-1]
grepcmd += '" ' + str(log) + " | grep -Eiv \'"
@@ -313,13 +313,13 @@ class ParseLogsTest(OERuntimeTestCase):
errorlist = ignore_errors['default']
for ignore_error in errorlist:
- ignore_error = ignore_error.replace('(', '\(')
- ignore_error = ignore_error.replace(')', '\)')
+ ignore_error = ignore_error.replace('(', r'\(')
+ ignore_error = ignore_error.replace(')', r'\)')
ignore_error = ignore_error.replace("'", '.')
- ignore_error = ignore_error.replace('?', '\?')
- ignore_error = ignore_error.replace('[', '\[')
- ignore_error = ignore_error.replace(']', '\]')
- ignore_error = ignore_error.replace('*', '\*')
+ ignore_error = ignore_error.replace('?', r'\?')
+ ignore_error = ignore_error.replace('[', r'\[')
+ ignore_error = ignore_error.replace(']', r'\]')
+ ignore_error = ignore_error.replace('*', r'\*')
ignore_error = ignore_error.replace('0-9', '[0-9]')
grepcmd += ignore_error + '|'
grepcmd = grepcmd[:-1]
diff --git a/meta/lib/oeqa/selftest/cases/bbtests.py b/meta/lib/oeqa/selftest/cases/bbtests.py
index b932d5276b..4187cb840a 100644
--- a/meta/lib/oeqa/selftest/cases/bbtests.py
+++ b/meta/lib/oeqa/selftest/cases/bbtests.py
@@ -163,7 +163,7 @@ SSTATE_DIR = \"${TOPDIR}/download-selftest\"
""")
self.track_for_cleanup(os.path.join(self.builddir, "download-selftest"))
- data = 'SRC_URI = "${GNU_MIRROR}/aspell/aspell-${PV}.tar.gz;downloadfilename=test-aspell.tar.gz"'
+ data = 'SRC_URI = "https://downloads.yoctoproject.org/mirror/sources/aspell-${PV}.tar.gz;downloadfilename=test-aspell.tar.gz"'
self.write_recipeinc('aspell', data)
result = bitbake('-f -c fetch aspell', ignore_status=True)
self.delete_recipeinc('aspell')
@@ -300,3 +300,32 @@ INHERIT_remove = \"report-error\"
test_recipe_summary_after = get_bb_var('SUMMARY', test_recipe)
self.assertEqual(expected_recipe_summary, test_recipe_summary_after)
+
+ def test_git_patchtool(self):
+ """ PATCHTOOL=git should work with non-git sources like tarballs
+ test recipe for the test must NOT containt git:// repository in SRC_URI
+ """
+ test_recipe = "man-db"
+ self.write_recipeinc(test_recipe, 'PATCHTOOL=\"git\"')
+ src = get_bb_var("SRC_URI",test_recipe)
+ gitscm = re.search("git://", src)
+ self.assertFalse(gitscm, "test_git_patchtool pre-condition failed: {} test recipe contains git repo!".format(test_recipe))
+ result = bitbake('{} -c patch'.format(test_recipe), ignore_status=False)
+ fatal = re.search("fatal: not a git repository (or any of the parent directories)", result.output)
+ self.assertFalse(fatal, "Failed to patch using PATCHTOOL=\"git\"")
+ self.delete_recipeinc(test_recipe)
+ bitbake('-cclean {}'.format(test_recipe))
+
+ def test_git_patchtool2(self):
+ """ Test if PATCHTOOL=git works with git repo and doesn't reinitialize it
+ """
+ test_recipe = "gitrepotest"
+ src = get_bb_var("SRC_URI",test_recipe)
+ gitscm = re.search("git://", src)
+ self.assertTrue(gitscm, "test_git_patchtool pre-condition failed: {} test recipe doesn't contains git repo!".format(test_recipe))
+ result = bitbake('{} -c patch'.format(test_recipe), ignore_status=False)
+ srcdir = get_bb_var('S', test_recipe)
+ result = runCmd("git log", cwd = srcdir)
+ self.assertFalse("bitbake_patching_started" in result.output, msg = "Repository has been reinitialized. {}".format(srcdir))
+ self.delete_recipeinc(test_recipe)
+ bitbake('-cclean {}'.format(test_recipe))
diff --git a/meta/lib/oeqa/selftest/cases/devtool.py b/meta/lib/oeqa/selftest/cases/devtool.py
index 66e326253e..7ac1fcfbeb 100644
--- a/meta/lib/oeqa/selftest/cases/devtool.py
+++ b/meta/lib/oeqa/selftest/cases/devtool.py
@@ -442,6 +442,7 @@ class DevtoolAddTests(DevtoolBase):
tempdir = tempfile.mkdtemp(prefix='devtoolqa')
self.track_for_cleanup(tempdir)
url = 'gitsm://git.yoctoproject.org/mraa'
+ url_branch = '%s;branch=master' % url
checkrev = 'ae127b19a50aa54255e4330ccfdd9a5d058e581d'
testrecipe = 'mraa'
srcdir = os.path.join(tempdir, testrecipe)
@@ -462,7 +463,7 @@ class DevtoolAddTests(DevtoolBase):
checkvars = {}
checkvars['S'] = '${WORKDIR}/git'
checkvars['PV'] = '1.0+git${SRCPV}'
- checkvars['SRC_URI'] = url
+ checkvars['SRC_URI'] = url_branch
checkvars['SRCREV'] = '${AUTOREV}'
self._test_recipe_contents(recipefile, checkvars, [])
# Try with revision and version specified
@@ -481,7 +482,7 @@ class DevtoolAddTests(DevtoolBase):
checkvars = {}
checkvars['S'] = '${WORKDIR}/git'
checkvars['PV'] = '1.5+git${SRCPV}'
- checkvars['SRC_URI'] = url
+ checkvars['SRC_URI'] = url_branch
checkvars['SRCREV'] = checkrev
self._test_recipe_contents(recipefile, checkvars, [])
diff --git a/meta/lib/oeqa/selftest/cases/recipetool.py b/meta/lib/oeqa/selftest/cases/recipetool.py
index 3621492998..4f283cdc03 100644
--- a/meta/lib/oeqa/selftest/cases/recipetool.py
+++ b/meta/lib/oeqa/selftest/cases/recipetool.py
@@ -375,7 +375,7 @@ class RecipetoolTests(RecipetoolBase):
temprecipe = os.path.join(self.tempdir, 'recipe')
os.makedirs(temprecipe)
pv = '1.7.3.0'
- srcuri = 'http://www.dest-unreach.org/socat/download/socat-%s.tar.bz2' % pv
+ srcuri = 'http://www.dest-unreach.org/socat/download/Archive/socat-%s.tar.bz2' % pv
result = runCmd('recipetool create %s -o %s' % (srcuri, temprecipe))
dirlist = os.listdir(temprecipe)
if len(dirlist) > 1:
diff --git a/meta/lib/oeqa/selftest/cases/reproducible.py b/meta/lib/oeqa/selftest/cases/reproducible.py
index a62757399b..546dc91120 100644
--- a/meta/lib/oeqa/selftest/cases/reproducible.py
+++ b/meta/lib/oeqa/selftest/cases/reproducible.py
@@ -114,8 +114,9 @@ def compare_file(reference, test, diffutils_sysroot):
result.status = SAME
return result
-def run_diffoscope(a_dir, b_dir, html_dir, **kwargs):
- return runCmd(['diffoscope', '--no-default-limits', '--exclude-directory-metadata', 'yes', '--html-dir', html_dir, a_dir, b_dir],
+def run_diffoscope(a_dir, b_dir, html_dir, max_report_size=0, **kwargs):
+ return runCmd(['diffoscope', '--no-default-limits', '--max-report-size', str(max_report_size),
+ '--exclude-directory-metadata', 'yes', '--html-dir', html_dir, a_dir, b_dir],
**kwargs)
class DiffoscopeTests(OESelftestTestCase):
@@ -145,6 +146,9 @@ class ReproducibleTests(OESelftestTestCase):
package_classes = ['deb', 'ipk', 'rpm']
+ # Maximum report size, in bytes
+ max_report_size = 250 * 1024 * 1024
+
# targets are the things we want to test the reproducibility of
targets = ['core-image-minimal', 'core-image-sato', 'core-image-full-cmdline', 'core-image-weston', 'world']
# sstate targets are things to pull from sstate to potentially cut build/debugging time
@@ -321,7 +325,7 @@ class ReproducibleTests(OESelftestTestCase):
# Copy jquery to improve the diffoscope output usability
self.copy_file(os.path.join(jquery_sysroot, 'usr/share/javascript/jquery/jquery.min.js'), os.path.join(package_html_dir, 'jquery.js'))
- run_diffoscope('reproducibleA', 'reproducibleB', package_html_dir,
+ run_diffoscope('reproducibleA', 'reproducibleB', package_html_dir, max_report_size=self.max_report_size,
native_sysroot=diffoscope_sysroot, ignore_status=True, cwd=package_dir)
if fails:
diff --git a/meta/lib/oeqa/selftest/cases/runtime_test.py b/meta/lib/oeqa/selftest/cases/runtime_test.py
index b20c5b427b..f9649339e5 100644
--- a/meta/lib/oeqa/selftest/cases/runtime_test.py
+++ b/meta/lib/oeqa/selftest/cases/runtime_test.py
@@ -185,6 +185,10 @@ class TestImage(OESelftestTestCase):
self.skipTest('virgl isn\'t working with Debian 9')
if distro and distro == 'centos-7':
self.skipTest('virgl isn\'t working with Centos 7')
+ if distro and distro == 'centos-8':
+ self.skipTest('virgl isn\'t working with Centos 8')
+ if distro and distro == 'fedora-34':
+ self.skipTest('virgl isn\'t working with Fedora 34')
if distro and distro == 'opensuseleap-15.0':
self.skipTest('virgl isn\'t working with Opensuse 15.0')
@@ -228,6 +232,9 @@ class TestImage(OESelftestTestCase):
dripath = subprocess.check_output("pkg-config --variable=dridriverdir dri", shell=True)
except subprocess.CalledProcessError as e:
self.skipTest("Could not determine the path to dri drivers on the host via pkg-config.\nPlease install Mesa development files (particularly, dri.pc) on the host machine.")
+ distro = oe.lsb.distro_identifier()
+ if distro and distro == 'fedora-34':
+ self.skipTest('virgl isn\'t working with Fedora 34')
qemu_distrofeatures = get_bb_var('DISTRO_FEATURES', 'qemu-system-native')
features = 'INHERIT += "testimage"\n'
if 'opengl' not in qemu_distrofeatures:
diff --git a/meta/recipes-bsp/grub/files/CVE-2021-3981-grub-mkconfig-Restore-umask-for-the-grub.cfg.patch b/meta/recipes-bsp/grub/files/CVE-2021-3981-grub-mkconfig-Restore-umask-for-the-grub.cfg.patch
new file mode 100644
index 0000000000..dae26fd8bb
--- /dev/null
+++ b/meta/recipes-bsp/grub/files/CVE-2021-3981-grub-mkconfig-Restore-umask-for-the-grub.cfg.patch
@@ -0,0 +1,49 @@
+From 0adec29674561034771c13e446069b41ef41e4d4 Mon Sep 17 00:00:00 2001
+From: Michael Chang <mchang@suse.com>
+Date: Fri, 3 Dec 2021 16:13:28 +0800
+Subject: [PATCH] grub-mkconfig: Restore umask for the grub.cfg
+
+The commit ab2e53c8a (grub-mkconfig: Honor a symlink when generating
+configuration by grub-mkconfig) has inadvertently discarded umask for
+creating grub.cfg in the process of running grub-mkconfig. The resulting
+wrong permission (0644) would allow unprivileged users to read GRUB
+configuration file content. This presents a low confidentiality risk
+as grub.cfg may contain non-secured plain-text passwords.
+
+This patch restores the missing umask and sets the creation file mode
+to 0600 preventing unprivileged access.
+
+Fixes: CVE-2021-3981
+
+Signed-off-by: Michael Chang <mchang@suse.com>
+Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com>
+
+Upstream-Status: Backport
+CVE: CVE-2021-3981
+
+Reference to upstream patch:
+https://git.savannah.gnu.org/cgit/grub.git/commit/?id=0adec29674561034771c13e446069b41ef41e4d4
+
+Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com>
+---
+ util/grub-mkconfig.in | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/util/grub-mkconfig.in b/util/grub-mkconfig.in
+index c3ea7612e..62335d027 100644
+--- a/util/grub-mkconfig.in
++++ b/util/grub-mkconfig.in
+@@ -301,7 +301,10 @@ and /etc/grub.d/* files or please file a bug report with
+ exit 1
+ else
+ # none of the children aborted with error, install the new grub.cfg
++ oldumask=$(umask)
++ umask 077
+ cat ${grub_cfg}.new > ${grub_cfg}
++ umask $oldumask
+ rm -f ${grub_cfg}.new
+ fi
+ fi
+--
+2.31.1
+
diff --git a/meta/recipes-bsp/grub/grub2.inc b/meta/recipes-bsp/grub/grub2.inc
index 3c6b434c2d..a70754e346 100644
--- a/meta/recipes-bsp/grub/grub2.inc
+++ b/meta/recipes-bsp/grub/grub2.inc
@@ -20,6 +20,7 @@ SRC_URI = "https://alpha.gnu.org/gnu/grub/grub-${REALPV}.tar.xz \
file://0001-grub.d-10_linux.in-add-oe-s-kernel-name.patch \
file://determinism.patch \
file://0001-RISC-V-Restore-the-typcast-to-long.patch \
+ file://CVE-2021-3981-grub-mkconfig-Restore-umask-for-the-grub.cfg.patch \
"
SRC_URI[sha256sum] = "2c87f1f21e2ab50043e6cd9163c08f1b6c3a6171556bf23ff9ed65b074145484"
diff --git a/meta/recipes-connectivity/mobile-broadband-provider-info/mobile-broadband-provider-info_git.bb b/meta/recipes-connectivity/mobile-broadband-provider-info/mobile-broadband-provider-info_git.bb
index b4cbc1a76c..781b9216c5 100644
--- a/meta/recipes-connectivity/mobile-broadband-provider-info/mobile-broadband-provider-info_git.bb
+++ b/meta/recipes-connectivity/mobile-broadband-provider-info/mobile-broadband-provider-info_git.bb
@@ -4,11 +4,12 @@ DESCRIPTION = "Mobile Broadband Service Provider Database stores service provide
SECTION = "network"
LICENSE = "PD"
LIC_FILES_CHKSUM = "file://COPYING;md5=87964579b2a8ece4bc6744d2dc9a8b04"
-SRCREV = "90f3fe28aa25135b7e4a54a7816388913bfd4a2a"
-PV = "20201225"
+
+SRCREV = "4cbb44a9fe26aa6f0b28beb79f9488b37c097b5e"
+PV = "20220315"
PE = "1"
-SRC_URI = "git://gitlab.gnome.org/GNOME/mobile-broadband-provider-info.git;protocol=https;branch=master"
+SRC_URI = "git://gitlab.gnome.org/GNOME/mobile-broadband-provider-info.git;protocol=https;branch=main"
S = "${WORKDIR}/git"
inherit autotools
diff --git a/meta/recipes-connectivity/openssl/openssl/reproducibility.patch b/meta/recipes-connectivity/openssl/openssl/reproducibility.patch
new file mode 100644
index 0000000000..8accbc9df2
--- /dev/null
+++ b/meta/recipes-connectivity/openssl/openssl/reproducibility.patch
@@ -0,0 +1,22 @@
+Using localtime() means the output can depend on the timezone of the build machine.
+Using gmtime() is safer. For complete reproducibility use SOURCE_DATE_EPOCH if set.
+
+Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
+Upstream-Status: Pending [should be suitable]
+
+Index: openssl-3.0.1/apps/progs.pl
+===================================================================
+--- openssl-3.0.1.orig/apps/progs.pl
++++ openssl-3.0.1/apps/progs.pl
+@@ -21,7 +21,10 @@ die "Unrecognised option, must be -C or
+ my %commands = ();
+ my $cmdre = qr/^\s*int\s+([a-z_][a-z0-9_]*)_main\(\s*int\s+argc\s*,/;
+ my $apps_openssl = shift @ARGV;
+-my $YEAR = [localtime()]->[5] + 1900;
++my $YEAR = [gmtime()]->[5] + 1900;
++if (defined($ENV{SOURCE_DATE_EPOCH}) && $ENV{SOURCE_DATE_EPOCH} !~ /\D/) {
++ $YEAR = [gmtime($ENV{SOURCE_DATE_EPOCH})]->[5] + 1900;
++}
+
+ # because the program apps/openssl has object files as sources, and
+ # they then have the corresponding C files as source, we need to chain
diff --git a/meta/recipes-connectivity/openssl/openssl_1.1.1l.bb b/meta/recipes-connectivity/openssl/openssl_1.1.1n.bb
index 9ea5c4c81f..df13abf54e 100644
--- a/meta/recipes-connectivity/openssl/openssl_1.1.1l.bb
+++ b/meta/recipes-connectivity/openssl/openssl_1.1.1n.bb
@@ -17,6 +17,7 @@ SRC_URI = "http://www.openssl.org/source/openssl-${PV}.tar.gz \
file://0001-buildinfo-strip-sysroot-and-debug-prefix-map-from-co.patch \
file://afalg.patch \
file://reproducible.patch \
+ file://reproducibility.patch \
"
SRC_URI_append_class-nativesdk = " \
@@ -28,7 +29,7 @@ SRC_URI_append_riscv32 = " \
file://0004-Fixup-support-for-io_pgetevents_time64-syscall.patch \
"
-SRC_URI[sha256sum] = "0b7a3e5e59c34827fe0c3a74b7ec8baef302b98fa80088d7f9153aa16fa76bd1"
+SRC_URI[sha256sum] = "40dceb51a4f6a5275bde0e6bf20ef4b91bfc32ed57c0552e2e8e15463372b17a"
inherit lib_package multilib_header multilib_script ptest
MULTILIB_SCRIPTS = "${PN}-bin:${bindir}/c_rehash"
@@ -203,6 +204,7 @@ do_install_ptest () {
install -m755 ${B}/apps/CA.pl ${D}${PTEST_PATH}/apps
install -d ${D}${PTEST_PATH}/engines
+ install -m755 ${B}/engines/dasync.so ${D}${PTEST_PATH}/engines
install -m755 ${B}/engines/ossltest.so ${D}${PTEST_PATH}/engines
# seems to be needed with perl 5.32.1
diff --git a/meta/recipes-connectivity/socat/socat_1.7.4.1.bb b/meta/recipes-connectivity/socat/socat_1.7.4.1.bb
index 5a13af91bc..0a1b65a8ca 100644
--- a/meta/recipes-connectivity/socat/socat_1.7.4.1.bb
+++ b/meta/recipes-connectivity/socat/socat_1.7.4.1.bb
@@ -9,7 +9,7 @@ LICENSE = "GPL-2.0-with-OpenSSL-exception"
LIC_FILES_CHKSUM = "file://COPYING;md5=b234ee4d69f5fce4486a80fdaf4a4263 \
file://README;beginline=257;endline=287;md5=82520b052f322ac2b5b3dfdc7c7eea86"
-SRC_URI = "http://www.dest-unreach.org/socat/download/socat-${PV}.tar.bz2 \
+SRC_URI = "http://www.dest-unreach.org/socat/download/Archive/socat-${PV}.tar.bz2 \
"
SRC_URI[md5sum] = "36cad050ecf4981ab044c3fbd75c643f"
diff --git a/meta/recipes-core/busybox/busybox-inittab_1.33.0.bb b/meta/recipes-core/busybox/busybox-inittab_1.33.2.bb
index 3804f4f7b2..3804f4f7b2 100644
--- a/meta/recipes-core/busybox/busybox-inittab_1.33.0.bb
+++ b/meta/recipes-core/busybox/busybox-inittab_1.33.2.bb
diff --git a/meta/recipes-core/busybox/busybox/0001-awk-fix-CVEs.patch b/meta/recipes-core/busybox/busybox/0001-awk-fix-CVEs.patch
new file mode 100644
index 0000000000..c07b53ebfd
--- /dev/null
+++ b/meta/recipes-core/busybox/busybox/0001-awk-fix-CVEs.patch
@@ -0,0 +1,3266 @@
+From cf542caeed195af05fa6205341f829ccee53f8c2 Mon Sep 17 00:00:00 2001
+From: Chen Qi <Qi.Chen@windriver.com>
+Date: Tue, 4 Jan 2022 17:48:03 -0800
+Subject: [PATCH] awk: fix CVEs
+
+The awk CVEs is hard to be separated, thus we use the following method
+to format the current patch.
+git rev-list --reverse 1_33_2..1_34_1 -- editors/awk.c | xargs git cherry-pick
+git reset HEAD~66 && git add . && git commit
+
+CVE: CVE-2021-42378
+CVE: CVE-2021-42379
+CVE: CVE-2021-42380
+CVE: CVE-2021-42381
+CVE: CVE-2021-42382
+CVE: CVE-2021-42383
+CVE: CVE-2021-42384
+CVE: CVE-2021-42385
+CVE: CVE-2021-42386
+
+Upstream-Status: Backport
+
+Signed-off-by: Chen Qi <Qi.Chen@windriver.com>
+---
+ editors/awk.c | 2060 +++++++++++++++++++++++-----------------
+ testsuite/awk.tests | 62 +-
+ testsuite/printf.tests | 5 +
+ 3 files changed, 1264 insertions(+), 863 deletions(-)
+
+diff --git a/editors/awk.c b/editors/awk.c
+index 2c15f9e4e..f6314ac72 100644
+--- a/editors/awk.c
++++ b/editors/awk.c
+@@ -66,6 +66,8 @@
+ #endif
+ #ifndef debug_printf_parse
+ # define debug_printf_parse(...) (fprintf(stderr, __VA_ARGS__))
++#else
++# define debug_parse_print_tc(...) ((void)0)
+ #endif
+
+
+@@ -91,7 +93,6 @@ enum {
+ };
+
+ #define MAXVARFMT 240
+-#define MINNVBLOCK 64
+
+ /* variable flags */
+ #define VF_NUMBER 0x0001 /* 1 = primary type is number */
+@@ -101,7 +102,7 @@ enum {
+ #define VF_USER 0x0200 /* 1 = user input (may be numeric string) */
+ #define VF_SPECIAL 0x0400 /* 1 = requires extra handling when changed */
+ #define VF_WALK 0x0800 /* 1 = variable has alloc'd x.walker list */
+-#define VF_FSTR 0x1000 /* 1 = var::string points to fstring buffer */
++#define VF_FSTR 0x1000 /* 1 = don't free() var::string (not malloced, or is owned by something else) */
+ #define VF_CHILD 0x2000 /* 1 = function arg; x.parent points to source */
+ #define VF_DIRTY 0x4000 /* 1 = variable was set explicitly */
+
+@@ -118,8 +119,8 @@ typedef struct walker_list {
+ /* Variable */
+ typedef struct var_s {
+ unsigned type; /* flags */
+- double number;
+ char *string;
++ double number;
+ union {
+ int aidx; /* func arg idx (for compilation stage) */
+ struct xhash_s *array; /* array ptr */
+@@ -138,6 +139,7 @@ typedef struct chain_s {
+ /* Function */
+ typedef struct func_s {
+ unsigned nargs;
++ smallint defined;
+ struct chain_s body;
+ } func;
+
+@@ -177,7 +179,7 @@ typedef struct node_s {
+ struct node_s *n;
+ var *v;
+ int aidx;
+- char *new_progname;
++ const char *new_progname;
+ regex_t *re;
+ } l;
+ union {
+@@ -190,91 +192,120 @@ typedef struct node_s {
+ } a;
+ } node;
+
+-/* Block of temporary variables */
+-typedef struct nvblock_s {
+- int size;
+- var *pos;
+- struct nvblock_s *prev;
+- struct nvblock_s *next;
+- var nv[];
+-} nvblock;
+-
+ typedef struct tsplitter_s {
+ node n;
+ regex_t re[2];
+ } tsplitter;
+
+ /* simple token classes */
+-/* Order and hex values are very important!!! See next_token() */
+-#define TC_SEQSTART (1 << 0) /* ( */
+-#define TC_SEQTERM (1 << 1) /* ) */
+-#define TC_REGEXP (1 << 2) /* /.../ */
+-#define TC_OUTRDR (1 << 3) /* | > >> */
+-#define TC_UOPPOST (1 << 4) /* unary postfix operator */
+-#define TC_UOPPRE1 (1 << 5) /* unary prefix operator */
+-#define TC_BINOPX (1 << 6) /* two-opnd operator */
+-#define TC_IN (1 << 7)
+-#define TC_COMMA (1 << 8)
+-#define TC_PIPE (1 << 9) /* input redirection pipe */
+-#define TC_UOPPRE2 (1 << 10) /* unary prefix operator */
+-#define TC_ARRTERM (1 << 11) /* ] */
+-#define TC_GRPSTART (1 << 12) /* { */
+-#define TC_GRPTERM (1 << 13) /* } */
+-#define TC_SEMICOL (1 << 14)
+-#define TC_NEWLINE (1 << 15)
+-#define TC_STATX (1 << 16) /* ctl statement (for, next...) */
+-#define TC_WHILE (1 << 17)
+-#define TC_ELSE (1 << 18)
+-#define TC_BUILTIN (1 << 19)
++/* order and hex values are very important!!! See next_token() */
++#define TC_LPAREN (1 << 0) /* ( */
++#define TC_RPAREN (1 << 1) /* ) */
++#define TC_REGEXP (1 << 2) /* /.../ */
++#define TC_OUTRDR (1 << 3) /* | > >> */
++#define TC_UOPPOST (1 << 4) /* unary postfix operator ++ -- */
++#define TC_UOPPRE1 (1 << 5) /* unary prefix operator ++ -- $ */
++#define TC_BINOPX (1 << 6) /* two-opnd operator */
++#define TC_IN (1 << 7) /* 'in' */
++#define TC_COMMA (1 << 8) /* , */
++#define TC_PIPE (1 << 9) /* input redirection pipe | */
++#define TC_UOPPRE2 (1 << 10) /* unary prefix operator + - ! */
++#define TC_ARRTERM (1 << 11) /* ] */
++#define TC_LBRACE (1 << 12) /* { */
++#define TC_RBRACE (1 << 13) /* } */
++#define TC_SEMICOL (1 << 14) /* ; */
++#define TC_NEWLINE (1 << 15)
++#define TC_STATX (1 << 16) /* ctl statement (for, next...) */
++#define TC_WHILE (1 << 17) /* 'while' */
++#define TC_ELSE (1 << 18) /* 'else' */
++#define TC_BUILTIN (1 << 19)
+ /* This costs ~50 bytes of code.
+ * A separate class to support deprecated "length" form. If we don't need that
+ * (i.e. if we demand that only "length()" with () is valid), then TC_LENGTH
+ * can be merged with TC_BUILTIN:
+ */
+-#define TC_LENGTH (1 << 20)
+-#define TC_GETLINE (1 << 21)
+-#define TC_FUNCDECL (1 << 22) /* 'function' 'func' */
+-#define TC_BEGIN (1 << 23)
+-#define TC_END (1 << 24)
+-#define TC_EOF (1 << 25)
+-#define TC_VARIABLE (1 << 26)
+-#define TC_ARRAY (1 << 27)
+-#define TC_FUNCTION (1 << 28)
+-#define TC_STRING (1 << 29)
+-#define TC_NUMBER (1 << 30)
+-
+-#define TC_UOPPRE (TC_UOPPRE1 | TC_UOPPRE2)
+-
+-/* combined token classes */
+-#define TC_BINOP (TC_BINOPX | TC_COMMA | TC_PIPE | TC_IN)
+-//#define TC_UNARYOP (TC_UOPPRE | TC_UOPPOST)
+-#define TC_OPERAND (TC_VARIABLE | TC_ARRAY | TC_FUNCTION \
+- | TC_BUILTIN | TC_LENGTH | TC_GETLINE \
+- | TC_SEQSTART | TC_STRING | TC_NUMBER)
+-
+-#define TC_STATEMNT (TC_STATX | TC_WHILE)
+-#define TC_OPTERM (TC_SEMICOL | TC_NEWLINE)
++#define TC_LENGTH (1 << 20) /* 'length' */
++#define TC_GETLINE (1 << 21) /* 'getline' */
++#define TC_FUNCDECL (1 << 22) /* 'function' 'func' */
++#define TC_BEGIN (1 << 23) /* 'BEGIN' */
++#define TC_END (1 << 24) /* 'END' */
++#define TC_EOF (1 << 25)
++#define TC_VARIABLE (1 << 26) /* name */
++#define TC_ARRAY (1 << 27) /* name[ */
++#define TC_FUNCTION (1 << 28) /* name( */
++#define TC_STRING (1 << 29) /* "..." */
++#define TC_NUMBER (1 << 30)
++
++#ifndef debug_parse_print_tc
++static void debug_parse_print_tc(uint32_t n)
++{
++ if (n & TC_LPAREN ) debug_printf_parse(" LPAREN" );
++ if (n & TC_RPAREN ) debug_printf_parse(" RPAREN" );
++ if (n & TC_REGEXP ) debug_printf_parse(" REGEXP" );
++ if (n & TC_OUTRDR ) debug_printf_parse(" OUTRDR" );
++ if (n & TC_UOPPOST ) debug_printf_parse(" UOPPOST" );
++ if (n & TC_UOPPRE1 ) debug_printf_parse(" UOPPRE1" );
++ if (n & TC_BINOPX ) debug_printf_parse(" BINOPX" );
++ if (n & TC_IN ) debug_printf_parse(" IN" );
++ if (n & TC_COMMA ) debug_printf_parse(" COMMA" );
++ if (n & TC_PIPE ) debug_printf_parse(" PIPE" );
++ if (n & TC_UOPPRE2 ) debug_printf_parse(" UOPPRE2" );
++ if (n & TC_ARRTERM ) debug_printf_parse(" ARRTERM" );
++ if (n & TC_LBRACE ) debug_printf_parse(" LBRACE" );
++ if (n & TC_RBRACE ) debug_printf_parse(" RBRACE" );
++ if (n & TC_SEMICOL ) debug_printf_parse(" SEMICOL" );
++ if (n & TC_NEWLINE ) debug_printf_parse(" NEWLINE" );
++ if (n & TC_STATX ) debug_printf_parse(" STATX" );
++ if (n & TC_WHILE ) debug_printf_parse(" WHILE" );
++ if (n & TC_ELSE ) debug_printf_parse(" ELSE" );
++ if (n & TC_BUILTIN ) debug_printf_parse(" BUILTIN" );
++ if (n & TC_LENGTH ) debug_printf_parse(" LENGTH" );
++ if (n & TC_GETLINE ) debug_printf_parse(" GETLINE" );
++ if (n & TC_FUNCDECL) debug_printf_parse(" FUNCDECL");
++ if (n & TC_BEGIN ) debug_printf_parse(" BEGIN" );
++ if (n & TC_END ) debug_printf_parse(" END" );
++ if (n & TC_EOF ) debug_printf_parse(" EOF" );
++ if (n & TC_VARIABLE) debug_printf_parse(" VARIABLE");
++ if (n & TC_ARRAY ) debug_printf_parse(" ARRAY" );
++ if (n & TC_FUNCTION) debug_printf_parse(" FUNCTION");
++ if (n & TC_STRING ) debug_printf_parse(" STRING" );
++ if (n & TC_NUMBER ) debug_printf_parse(" NUMBER" );
++}
++#endif
++
++/* combined token classes ("token [class] sets") */
++#define TS_UOPPRE (TC_UOPPRE1 | TC_UOPPRE2)
++
++#define TS_BINOP (TC_BINOPX | TC_COMMA | TC_PIPE | TC_IN)
++//#define TS_UNARYOP (TS_UOPPRE | TC_UOPPOST)
++#define TS_OPERAND (TC_VARIABLE | TC_ARRAY | TC_FUNCTION \
++ | TC_BUILTIN | TC_LENGTH | TC_GETLINE \
++ | TC_LPAREN | TC_STRING | TC_NUMBER)
++
++#define TS_LVALUE (TC_VARIABLE | TC_ARRAY)
++#define TS_STATEMNT (TC_STATX | TC_WHILE)
+
+ /* word tokens, cannot mean something else if not expected */
+-#define TC_WORD (TC_IN | TC_STATEMNT | TC_ELSE \
+- | TC_BUILTIN | TC_LENGTH | TC_GETLINE \
+- | TC_FUNCDECL | TC_BEGIN | TC_END)
++#define TS_WORD (TC_IN | TS_STATEMNT | TC_ELSE \
++ | TC_BUILTIN | TC_LENGTH | TC_GETLINE \
++ | TC_FUNCDECL | TC_BEGIN | TC_END)
+
+ /* discard newlines after these */
+-#define TC_NOTERM (TC_COMMA | TC_GRPSTART | TC_GRPTERM \
+- | TC_BINOP | TC_OPTERM)
++#define TS_NOTERM (TS_BINOP | TC_COMMA | TC_LBRACE | TC_RBRACE \
++ | TC_SEMICOL | TC_NEWLINE)
+
+ /* what can expression begin with */
+-#define TC_OPSEQ (TC_OPERAND | TC_UOPPRE | TC_REGEXP)
++#define TS_OPSEQ (TS_OPERAND | TS_UOPPRE | TC_REGEXP)
+ /* what can group begin with */
+-#define TC_GRPSEQ (TC_OPSEQ | TC_OPTERM | TC_STATEMNT | TC_GRPSTART)
++#define TS_GRPSEQ (TS_OPSEQ | TS_STATEMNT \
++ | TC_SEMICOL | TC_NEWLINE | TC_LBRACE)
+
+-/* if previous token class is CONCAT1 and next is CONCAT2, concatenation */
++/* if previous token class is CONCAT_L and next is CONCAT_R, concatenation */
+ /* operator is inserted between them */
+-#define TC_CONCAT1 (TC_VARIABLE | TC_ARRTERM | TC_SEQTERM \
++#define TS_CONCAT_L (TC_VARIABLE | TC_ARRTERM | TC_RPAREN \
+ | TC_STRING | TC_NUMBER | TC_UOPPOST \
+ | TC_LENGTH)
+-#define TC_CONCAT2 (TC_OPERAND | TC_UOPPRE)
++#define TS_CONCAT_R (TS_OPERAND | TS_UOPPRE)
+
+ #define OF_RES1 0x010000
+ #define OF_RES2 0x020000
+@@ -284,13 +315,12 @@ typedef struct tsplitter_s {
+ #define OF_CHECKED 0x200000
+ #define OF_REQUIRED 0x400000
+
+-
+ /* combined operator flags */
+ #define xx 0
+ #define xV OF_RES2
+ #define xS (OF_RES2 | OF_STR2)
+ #define Vx OF_RES1
+-#define Rx (OF_RES1 | OF_NUM1 | OF_REQUIRED)
++#define Rx OF_REQUIRED
+ #define VV (OF_RES1 | OF_RES2)
+ #define Nx (OF_RES1 | OF_NUM1)
+ #define NV (OF_RES1 | OF_NUM1 | OF_RES2)
+@@ -302,8 +332,7 @@ typedef struct tsplitter_s {
+ #define OPNMASK 0x007F
+
+ /* operator priority is a highest byte (even: r->l, odd: l->r grouping)
+- * For builtins it has different meaning: n n s3 s2 s1 v3 v2 v1,
+- * n - min. number of args, vN - resolve Nth arg to var, sN - resolve to string
++ * (for builtins it has different meaning)
+ */
+ #undef P
+ #undef PRIMASK
+@@ -313,10 +342,8 @@ typedef struct tsplitter_s {
+ #define PRIMASK2 0x7E000000
+
+ /* Operation classes */
+-
+ #define SHIFT_TIL_THIS 0x0600
+ #define RECUR_FROM_THIS 0x1000
+-
+ enum {
+ OC_DELETE = 0x0100, OC_EXEC = 0x0200, OC_NEWSOURCE = 0x0300,
+ OC_PRINT = 0x0400, OC_PRINTF = 0x0500, OC_WALKINIT = 0x0600,
+@@ -358,8 +385,8 @@ enum {
+ #define NTCC '\377'
+
+ static const char tokenlist[] ALIGN1 =
+- "\1(" NTC /* TC_SEQSTART */
+- "\1)" NTC /* TC_SEQTERM */
++ "\1(" NTC /* TC_LPAREN */
++ "\1)" NTC /* TC_RPAREN */
+ "\1/" NTC /* TC_REGEXP */
+ "\2>>" "\1>" "\1|" NTC /* TC_OUTRDR */
+ "\2++" "\2--" NTC /* TC_UOPPOST */
+@@ -376,8 +403,8 @@ static const char tokenlist[] ALIGN1 =
+ "\1|" NTC /* TC_PIPE */
+ "\1+" "\1-" "\1!" NTC /* TC_UOPPRE2 */
+ "\1]" NTC /* TC_ARRTERM */
+- "\1{" NTC /* TC_GRPSTART */
+- "\1}" NTC /* TC_GRPTERM */
++ "\1{" NTC /* TC_LBRACE */
++ "\1}" NTC /* TC_RBRACE */
+ "\1;" NTC /* TC_SEMICOL */
+ "\1\n" NTC /* TC_NEWLINE */
+ "\2if" "\2do" "\3for" "\5break" /* TC_STATX */
+@@ -391,7 +418,7 @@ static const char tokenlist[] ALIGN1 =
+ "\5close" "\6system" "\6fflush" "\5atan2"
+ "\3cos" "\3exp" "\3int" "\3log"
+ "\4rand" "\3sin" "\4sqrt" "\5srand"
+- "\6gensub" "\4gsub" "\5index" /* "\6length" was here */
++ "\6gensub" "\4gsub" "\5index" /* "\6length" was here */
+ "\5match" "\5split" "\7sprintf" "\3sub"
+ "\6substr" "\7systime" "\10strftime" "\6mktime"
+ "\7tolower" "\7toupper" NTC
+@@ -403,25 +430,32 @@ static const char tokenlist[] ALIGN1 =
+ /* compiler adds trailing "\0" */
+ ;
+
+-#define OC_B OC_BUILTIN
+-
+ static const uint32_t tokeninfo[] ALIGN4 = {
+ 0,
+ 0,
+- OC_REGEXP,
++#define TI_REGEXP OC_REGEXP
++ TI_REGEXP,
+ xS|'a', xS|'w', xS|'|',
+ OC_UNARY|xV|P(9)|'p', OC_UNARY|xV|P(9)|'m',
+- OC_UNARY|xV|P(9)|'P', OC_UNARY|xV|P(9)|'M', OC_FIELD|xV|P(5),
++#define TI_PREINC (OC_UNARY|xV|P(9)|'P')
++#define TI_PREDEC (OC_UNARY|xV|P(9)|'M')
++ TI_PREINC, TI_PREDEC, OC_FIELD|xV|P(5),
+ OC_COMPARE|VV|P(39)|5, OC_MOVE|VV|P(74), OC_REPLACE|NV|P(74)|'+', OC_REPLACE|NV|P(74)|'-',
+ OC_REPLACE|NV|P(74)|'*', OC_REPLACE|NV|P(74)|'/', OC_REPLACE|NV|P(74)|'%', OC_REPLACE|NV|P(74)|'&',
+ OC_BINARY|NV|P(29)|'+', OC_BINARY|NV|P(29)|'-', OC_REPLACE|NV|P(74)|'&', OC_BINARY|NV|P(15)|'&',
+ OC_BINARY|NV|P(25)|'/', OC_BINARY|NV|P(25)|'%', OC_BINARY|NV|P(15)|'&', OC_BINARY|NV|P(25)|'*',
+ OC_COMPARE|VV|P(39)|4, OC_COMPARE|VV|P(39)|3, OC_COMPARE|VV|P(39)|0, OC_COMPARE|VV|P(39)|1,
+- OC_COMPARE|VV|P(39)|2, OC_MATCH|Sx|P(45)|'!', OC_MATCH|Sx|P(45)|'~', OC_LAND|Vx|P(55),
+- OC_LOR|Vx|P(59), OC_TERNARY|Vx|P(64)|'?', OC_COLON|xx|P(67)|':',
+- OC_IN|SV|P(49), /* TC_IN */
+- OC_COMMA|SS|P(80),
+- OC_PGETLINE|SV|P(37),
++#define TI_LESS (OC_COMPARE|VV|P(39)|2)
++ TI_LESS, OC_MATCH|Sx|P(45)|'!', OC_MATCH|Sx|P(45)|'~', OC_LAND|Vx|P(55),
++#define TI_TERNARY (OC_TERNARY|Vx|P(64)|'?')
++#define TI_COLON (OC_COLON|xx|P(67)|':')
++ OC_LOR|Vx|P(59), TI_TERNARY, TI_COLON,
++#define TI_IN (OC_IN|SV|P(49))
++ TI_IN,
++#define TI_COMMA (OC_COMMA|SS|P(80))
++ TI_COMMA,
++#define TI_PGETLINE (OC_PGETLINE|SV|P(37))
++ TI_PGETLINE,
+ OC_UNARY|xV|P(19)|'+', OC_UNARY|xV|P(19)|'-', OC_UNARY|xV|P(19)|'!',
+ 0, /* ] */
+ 0,
+@@ -434,20 +468,45 @@ static const uint32_t tokeninfo[] ALIGN4 = {
+ OC_RETURN|Vx, OC_EXIT|Nx,
+ ST_WHILE,
+ 0, /* else */
+- OC_B|B_an|P(0x83), OC_B|B_co|P(0x41), OC_B|B_ls|P(0x83), OC_B|B_or|P(0x83),
+- OC_B|B_rs|P(0x83), OC_B|B_xo|P(0x83),
+- OC_FBLTIN|Sx|F_cl, OC_FBLTIN|Sx|F_sy, OC_FBLTIN|Sx|F_ff, OC_B|B_a2|P(0x83),
+- OC_FBLTIN|Nx|F_co, OC_FBLTIN|Nx|F_ex, OC_FBLTIN|Nx|F_in, OC_FBLTIN|Nx|F_lg,
+- OC_FBLTIN|F_rn, OC_FBLTIN|Nx|F_si, OC_FBLTIN|Nx|F_sq, OC_FBLTIN|Nx|F_sr,
+- OC_B|B_ge|P(0xd6), OC_B|B_gs|P(0xb6), OC_B|B_ix|P(0x9b), /* OC_FBLTIN|Sx|F_le, was here */
+- OC_B|B_ma|P(0x89), OC_B|B_sp|P(0x8b), OC_SPRINTF, OC_B|B_su|P(0xb6),
+- OC_B|B_ss|P(0x8f), OC_FBLTIN|F_ti, OC_B|B_ti|P(0x0b), OC_B|B_mt|P(0x0b),
+- OC_B|B_lo|P(0x49), OC_B|B_up|P(0x49),
+- OC_FBLTIN|Sx|F_le, /* TC_LENGTH */
+- OC_GETLINE|SV|P(0),
+- 0, 0,
+- 0,
+- 0 /* TC_END */
++// OC_B's are builtins with enforced minimum number of arguments (two upper bits).
++// Highest byte bit pattern: nn s3s2s1 v3v2v1
++// nn - min. number of args, sN - resolve Nth arg to string, vN - resolve to var
++// OC_F's are builtins with zero or one argument.
++// |Rx| enforces that arg is present for: system, close, cos, sin, exp, int, log, sqrt
++// Check for no args is present in builtins' code (not in this table): rand, systime
++// Have one _optional_ arg: fflush, srand, length
++#define OC_B OC_BUILTIN
++#define OC_F OC_FBLTIN
++#define A1 P(0x40) /*one arg*/
++#define A2 P(0x80) /*two args*/
++#define A3 P(0xc0) /*three args*/
++#define __v P(1)
++#define _vv P(3)
++#define __s__v P(9)
++#define __s_vv P(0x0b)
++#define __svvv P(0x0f)
++#define _ss_vv P(0x1b)
++#define _s_vv_ P(0x16)
++#define ss_vv_ P(0x36)
++ OC_B|B_an|_vv|A2, OC_B|B_co|__v|A1, OC_B|B_ls|_vv|A2, OC_B|B_or|_vv|A2, // and compl lshift or
++ OC_B|B_rs|_vv|A2, OC_B|B_xo|_vv|A2, // rshift xor
++ OC_F|F_cl|Sx|Rx, OC_F|F_sy|Sx|Rx, OC_F|F_ff|Sx, OC_B|B_a2|_vv|A2, // close system fflush atan2
++ OC_F|F_co|Nx|Rx, OC_F|F_ex|Nx|Rx, OC_F|F_in|Nx|Rx, OC_F|F_lg|Nx|Rx, // cos exp int log
++ OC_F|F_rn, OC_F|F_si|Nx|Rx, OC_F|F_sq|Nx|Rx, OC_F|F_sr|Nx, // rand sin sqrt srand
++ OC_B|B_ge|_s_vv_|A3,OC_B|B_gs|ss_vv_|A2,OC_B|B_ix|_ss_vv|A2, // gensub gsub index /*length was here*/
++ OC_B|B_ma|__s__v|A2,OC_B|B_sp|__s_vv|A2,OC_SPRINTF, OC_B|B_su|ss_vv_|A2,// match split sprintf sub
++ OC_B|B_ss|__svvv|A2,OC_F|F_ti, OC_B|B_ti|__s_vv, OC_B|B_mt|__s_vv, // substr systime strftime mktime
++ OC_B|B_lo|__s__v|A1,OC_B|B_up|__s__v|A1, // tolower toupper
++ OC_F|F_le|Sx, // length
++ OC_GETLINE|SV, // getline
++ 0, 0, // func function
++ 0, // BEGIN
++ 0 // END
++#undef A1
++#undef A2
++#undef A3
++#undef OC_B
++#undef OC_F
+ };
+
+ /* internal variable names and their initial values */
+@@ -488,21 +547,29 @@ struct globals {
+ chain *seq;
+ node *break_ptr, *continue_ptr;
+ rstream *iF;
+- xhash *vhash, *ahash, *fdhash, *fnhash;
++ xhash *ahash; /* argument names, used only while parsing function bodies */
++ xhash *fnhash; /* function names, used only in parsing stage */
++ xhash *vhash; /* variables and arrays */
++ //xhash *fdhash; /* file objects, used only in execution stage */
++ //we are reusing ahash as fdhash, via define (see later)
+ const char *g_progname;
+ int g_lineno;
+ int nfields;
+ int maxfields; /* used in fsrealloc() only */
+ var *Fields;
+- nvblock *g_cb;
+ char *g_pos;
+- char *g_buf;
++ char g_saved_ch;
+ smallint icase;
+ smallint exiting;
+ smallint nextrec;
+ smallint nextfile;
+ smallint is_f0_split;
+ smallint t_rollback;
++
++ /* former statics from various functions */
++ smallint next_token__concat_inserted;
++ uint32_t next_token__save_tclass;
++ uint32_t next_token__save_info;
+ };
+ struct globals2 {
+ uint32_t t_info; /* often used */
+@@ -515,32 +582,35 @@ struct globals2 {
+ /* former statics from various functions */
+ char *split_f0__fstrings;
+
+- uint32_t next_token__save_tclass;
+- uint32_t next_token__save_info;
+- uint32_t next_token__ltclass;
+- smallint next_token__concat_inserted;
+-
+- smallint next_input_file__files_happen;
+ rstream next_input_file__rsm;
++ smallint next_input_file__files_happen;
++
++ smalluint exitcode;
+
+- var *evaluate__fnargs;
+ unsigned evaluate__seed;
++ var *evaluate__fnargs;
+ regex_t evaluate__sreg;
+
+- var ptest__v;
++ var ptest__tmpvar;
++ var awk_printf__tmpvar;
++ var as_regex__tmpvar;
++ var exit__tmpvar;
++ var main__tmpvar;
+
+ tsplitter exec_builtin__tspl;
+
+ /* biggest and least used members go last */
+ tsplitter fsplitter, rsplitter;
++
++ char g_buf[MAXVARFMT + 1];
+ };
+ #define G1 (ptr_to_globals[-1])
+ #define G (*(struct globals2 *)ptr_to_globals)
+ /* For debug. nm --size-sort awk.o | grep -vi ' [tr] ' */
+-/*char G1size[sizeof(G1)]; - 0x74 */
+-/*char Gsize[sizeof(G)]; - 0x1c4 */
++//char G1size[sizeof(G1)]; // 0x70
++//char Gsize[sizeof(G)]; // 0x2f8
+ /* Trying to keep most of members accessible with short offsets: */
+-/*char Gofs_seed[offsetof(struct globals2, evaluate__seed)]; - 0x90 */
++//char Gofs_seed[offsetof(struct globals2, evaluate__seed)]; // 0x7c
+ #define t_double (G1.t_double )
+ #define beginseq (G1.beginseq )
+ #define mainseq (G1.mainseq )
+@@ -549,18 +619,20 @@ struct globals2 {
+ #define break_ptr (G1.break_ptr )
+ #define continue_ptr (G1.continue_ptr)
+ #define iF (G1.iF )
+-#define vhash (G1.vhash )
+ #define ahash (G1.ahash )
+-#define fdhash (G1.fdhash )
+ #define fnhash (G1.fnhash )
++#define vhash (G1.vhash )
++#define fdhash ahash
++//^^^^^^^^^^^^^^^^^^ ahash is cleared after every function parsing,
++// and ends up empty after parsing phase. Thus, we can simply reuse it
++// for fdhash in execution stage.
+ #define g_progname (G1.g_progname )
+ #define g_lineno (G1.g_lineno )
+ #define nfields (G1.nfields )
+ #define maxfields (G1.maxfields )
+ #define Fields (G1.Fields )
+-#define g_cb (G1.g_cb )
+ #define g_pos (G1.g_pos )
+-#define g_buf (G1.g_buf )
++#define g_saved_ch (G1.g_saved_ch )
+ #define icase (G1.icase )
+ #define exiting (G1.exiting )
+ #define nextrec (G1.nextrec )
+@@ -574,25 +646,13 @@ struct globals2 {
+ #define intvar (G.intvar )
+ #define fsplitter (G.fsplitter )
+ #define rsplitter (G.rsplitter )
++#define g_buf (G.g_buf )
+ #define INIT_G() do { \
+ SET_PTR_TO_GLOBALS((char*)xzalloc(sizeof(G1)+sizeof(G)) + sizeof(G1)); \
+- G.next_token__ltclass = TC_OPTERM; \
++ t_tclass = TC_NEWLINE; \
+ G.evaluate__seed = 1; \
+ } while (0)
+
+-
+-/* function prototypes */
+-static void handle_special(var *);
+-static node *parse_expr(uint32_t);
+-static void chain_group(void);
+-static var *evaluate(node *, var *);
+-static rstream *next_input_file(void);
+-static int fmt_num(char *, int, const char *, double, int);
+-static int awk_exit(int) NORETURN;
+-
+-/* ---- error handling ---- */
+-
+-static const char EMSG_INTERNAL_ERROR[] ALIGN1 = "Internal error";
+ static const char EMSG_UNEXP_EOS[] ALIGN1 = "Unexpected end of string";
+ static const char EMSG_UNEXP_TOKEN[] ALIGN1 = "Unexpected token";
+ static const char EMSG_DIV_BY_ZERO[] ALIGN1 = "Division by zero";
+@@ -604,10 +664,7 @@ static const char EMSG_UNDEF_FUNC[] ALIGN1 = "Call to undefined function";
+ static const char EMSG_NO_MATH[] ALIGN1 = "Math support is not compiled in";
+ static const char EMSG_NEGATIVE_FIELD[] ALIGN1 = "Access to negative field";
+
+-static void zero_out_var(var *vp)
+-{
+- memset(vp, 0, sizeof(*vp));
+-}
++static int awk_exit(void) NORETURN;
+
+ static void syntax_error(const char *message) NORETURN;
+ static void syntax_error(const char *message)
+@@ -638,12 +695,40 @@ static xhash *hash_init(void)
+ return newhash;
+ }
+
++static void hash_clear(xhash *hash)
++{
++ unsigned i;
++ hash_item *hi, *thi;
++
++ for (i = 0; i < hash->csize; i++) {
++ hi = hash->items[i];
++ while (hi) {
++ thi = hi;
++ hi = hi->next;
++//FIXME: this assumes that it's a hash of *variables*:
++ free(thi->data.v.string);
++ free(thi);
++ }
++ hash->items[i] = NULL;
++ }
++ hash->glen = hash->nel = 0;
++}
++
++#if 0 //UNUSED
++static void hash_free(xhash *hash)
++{
++ hash_clear(hash);
++ free(hash->items);
++ free(hash);
++}
++#endif
++
+ /* find item in hash, return ptr to data, NULL if not found */
+-static void *hash_search(xhash *hash, const char *name)
++static NOINLINE void *hash_search3(xhash *hash, const char *name, unsigned idx)
+ {
+ hash_item *hi;
+
+- hi = hash->items[hashidx(name) % hash->csize];
++ hi = hash->items[idx % hash->csize];
+ while (hi) {
+ if (strcmp(hi->name, name) == 0)
+ return &hi->data;
+@@ -652,6 +737,11 @@ static void *hash_search(xhash *hash, const char *name)
+ return NULL;
+ }
+
++static void *hash_search(xhash *hash, const char *name)
++{
++ return hash_search3(hash, name, hashidx(name));
++}
++
+ /* grow hash if it becomes too big */
+ static void hash_rebuild(xhash *hash)
+ {
+@@ -687,16 +777,17 @@ static void *hash_find(xhash *hash, const char *name)
+ unsigned idx;
+ int l;
+
+- hi = hash_search(hash, name);
++ idx = hashidx(name);
++ hi = hash_search3(hash, name, idx);
+ if (!hi) {
+- if (++hash->nel / hash->csize > 10)
++ if (++hash->nel > hash->csize * 8)
+ hash_rebuild(hash);
+
+ l = strlen(name) + 1;
+ hi = xzalloc(sizeof(*hi) + l);
+ strcpy(hi->name, name);
+
+- idx = hashidx(name) % hash->csize;
++ idx = idx % hash->csize;
+ hi->next = hash->items[idx];
+ hash->items[idx] = hi;
+ hash->glen += l;
+@@ -731,7 +822,7 @@ static void hash_remove(xhash *hash, const char *name)
+
+ static char *skip_spaces(char *p)
+ {
+- while (1) {
++ for (;;) {
+ if (*p == '\\' && p[1] == '\n') {
+ p++;
+ t_lineno++;
+@@ -747,8 +838,10 @@ static char *skip_spaces(char *p)
+ static char *nextword(char **s)
+ {
+ char *p = *s;
+- while (*(*s)++ != '\0')
++ char *q = p;
++ while (*q++ != '\0')
+ continue;
++ *s = q;
+ return p;
+ }
+
+@@ -811,10 +904,27 @@ static double my_strtod(char **pp)
+
+ /* -------- working with variables (set/get/copy/etc) -------- */
+
+-static xhash *iamarray(var *v)
++static void fmt_num(const char *format, double n)
+ {
+- var *a = v;
++ if (n == (long long)n) {
++ snprintf(g_buf, MAXVARFMT, "%lld", (long long)n);
++ } else {
++ const char *s = format;
++ char c;
++
++ do { c = *s; } while (c && *++s);
++ if (strchr("diouxX", c)) {
++ snprintf(g_buf, MAXVARFMT, format, (int)n);
++ } else if (strchr("eEfFgGaA", c)) {
++ snprintf(g_buf, MAXVARFMT, format, n);
++ } else {
++ syntax_error(EMSG_INV_FMT);
++ }
++ }
++}
+
++static xhash *iamarray(var *a)
++{
+ while (a->type & VF_CHILD)
+ a = a->x.parent;
+
+@@ -825,23 +935,7 @@ static xhash *iamarray(var *v)
+ return a->x.array;
+ }
+
+-static void clear_array(xhash *array)
+-{
+- unsigned i;
+- hash_item *hi, *thi;
+-
+- for (i = 0; i < array->csize; i++) {
+- hi = array->items[i];
+- while (hi) {
+- thi = hi;
+- hi = hi->next;
+- free(thi->data.v.string);
+- free(thi);
+- }
+- array->items[i] = NULL;
+- }
+- array->glen = array->nel = 0;
+-}
++#define clear_array(array) hash_clear(array)
+
+ /* clear a variable */
+ static var *clrvar(var *v)
+@@ -855,6 +949,8 @@ static var *clrvar(var *v)
+ return v;
+ }
+
++static void handle_special(var *);
++
+ /* assign string value to variable */
+ static var *setvar_p(var *v, char *value)
+ {
+@@ -901,7 +997,7 @@ static const char *getvar_s(var *v)
+ {
+ /* if v is numeric and has no cached string, convert it to string */
+ if ((v->type & (VF_NUMBER | VF_CACHED)) == VF_NUMBER) {
+- fmt_num(g_buf, MAXVARFMT, getvar_s(intvar[CONVFMT]), v->number, TRUE);
++ fmt_num(getvar_s(intvar[CONVFMT]), v->number);
+ v->string = xstrdup(g_buf);
+ v->type |= VF_CACHED;
+ }
+@@ -920,6 +1016,7 @@ static double getvar_i(var *v)
+ v->number = my_strtod(&s);
+ debug_printf_eval("%f (s:'%s')\n", v->number, s);
+ if (v->type & VF_USER) {
++//TODO: skip_spaces() also skips backslash+newline, is it intended here?
+ s = skip_spaces(s);
+ if (*s != '\0')
+ v->type &= ~VF_USER;
+@@ -981,94 +1078,28 @@ static int istrue(var *v)
+ return (v->string && v->string[0]);
+ }
+
+-/* temporary variables allocator. Last allocated should be first freed */
+-static var *nvalloc(int n)
+-{
+- nvblock *pb = NULL;
+- var *v, *r;
+- int size;
+-
+- while (g_cb) {
+- pb = g_cb;
+- if ((g_cb->pos - g_cb->nv) + n <= g_cb->size)
+- break;
+- g_cb = g_cb->next;
+- }
+-
+- if (!g_cb) {
+- size = (n <= MINNVBLOCK) ? MINNVBLOCK : n;
+- g_cb = xzalloc(sizeof(nvblock) + size * sizeof(var));
+- g_cb->size = size;
+- g_cb->pos = g_cb->nv;
+- g_cb->prev = pb;
+- /*g_cb->next = NULL; - xzalloc did it */
+- if (pb)
+- pb->next = g_cb;
+- }
+-
+- v = r = g_cb->pos;
+- g_cb->pos += n;
+-
+- while (v < g_cb->pos) {
+- v->type = 0;
+- v->string = NULL;
+- v++;
+- }
+-
+- return r;
+-}
+-
+-static void nvfree(var *v)
+-{
+- var *p;
+-
+- if (v < g_cb->nv || v >= g_cb->pos)
+- syntax_error(EMSG_INTERNAL_ERROR);
+-
+- for (p = v; p < g_cb->pos; p++) {
+- if ((p->type & (VF_ARRAY | VF_CHILD)) == VF_ARRAY) {
+- clear_array(iamarray(p));
+- free(p->x.array->items);
+- free(p->x.array);
+- }
+- if (p->type & VF_WALK) {
+- walker_list *n;
+- walker_list *w = p->x.walker;
+- debug_printf_walker("nvfree: freeing walker @%p\n", &p->x.walker);
+- p->x.walker = NULL;
+- while (w) {
+- n = w->prev;
+- debug_printf_walker(" free(%p)\n", w);
+- free(w);
+- w = n;
+- }
+- }
+- clrvar(p);
+- }
+-
+- g_cb->pos = v;
+- while (g_cb->prev && g_cb->pos == g_cb->nv) {
+- g_cb = g_cb->prev;
+- }
+-}
+-
+ /* ------- awk program text parsing ------- */
+
+-/* Parse next token pointed by global pos, place results into global ttt.
+- * If token isn't expected, give away. Return token class
++/* Parse next token pointed by global pos, place results into global t_XYZ variables.
++ * If token isn't expected, print error message and die.
++ * Return token class (also store it in t_tclass).
+ */
+ static uint32_t next_token(uint32_t expected)
+ {
+-#define concat_inserted (G.next_token__concat_inserted)
+-#define save_tclass (G.next_token__save_tclass)
+-#define save_info (G.next_token__save_info)
+-/* Initialized to TC_OPTERM: */
+-#define ltclass (G.next_token__ltclass)
++#define concat_inserted (G1.next_token__concat_inserted)
++#define save_tclass (G1.next_token__save_tclass)
++#define save_info (G1.next_token__save_info)
+
+- char *p, *s;
++ char *p;
+ const char *tl;
+- uint32_t tc;
+ const uint32_t *ti;
++ uint32_t tc, last_token_class;
++
++ last_token_class = t_tclass; /* t_tclass is initialized to TC_NEWLINE */
++
++ debug_printf_parse("%s() expected(%x):", __func__, expected);
++ debug_parse_print_tc(expected);
++ debug_printf_parse("\n");
+
+ if (t_rollback) {
+ debug_printf_parse("%s: using rolled-back token\n", __func__);
+@@ -1080,6 +1111,10 @@ static uint32_t next_token(uint32_t expected)
+ t_info = save_info;
+ } else {
+ p = g_pos;
++ if (g_saved_ch != '\0') {
++ *p = g_saved_ch;
++ g_saved_ch = '\0';
++ }
+ readnext:
+ p = skip_spaces(p);
+ g_lineno = t_lineno;
+@@ -1087,15 +1122,12 @@ static uint32_t next_token(uint32_t expected)
+ while (*p != '\n' && *p != '\0')
+ p++;
+
+- if (*p == '\n')
+- t_lineno++;
+-
+ if (*p == '\0') {
+ tc = TC_EOF;
+ debug_printf_parse("%s: token found: TC_EOF\n", __func__);
+ } else if (*p == '\"') {
+ /* it's a string */
+- t_string = s = ++p;
++ char *s = t_string = ++p;
+ while (*p != '\"') {
+ char *pp;
+ if (*p == '\0' || *p == '\n')
+@@ -1110,7 +1142,7 @@ static uint32_t next_token(uint32_t expected)
+ debug_printf_parse("%s: token found:'%s' TC_STRING\n", __func__, t_string);
+ } else if ((expected & TC_REGEXP) && *p == '/') {
+ /* it's regexp */
+- t_string = s = ++p;
++ char *s = t_string = ++p;
+ while (*p != '/') {
+ if (*p == '\0' || *p == '\n')
+ syntax_error(EMSG_UNEXP_EOS);
+@@ -1141,6 +1173,11 @@ static uint32_t next_token(uint32_t expected)
+ tc = TC_NUMBER;
+ debug_printf_parse("%s: token found:%f TC_NUMBER\n", __func__, t_double);
+ } else {
++ char *end_of_name;
++
++ if (*p == '\n')
++ t_lineno++;
++
+ /* search for something known */
+ tl = tokenlist;
+ tc = 0x00000001;
+@@ -1155,9 +1192,9 @@ static uint32_t next_token(uint32_t expected)
+ * token matches,
+ * and it's not a longer word,
+ */
+- if ((tc & (expected | TC_WORD | TC_NEWLINE))
++ if ((tc & (expected | TS_WORD | TC_NEWLINE))
+ && strncmp(p, tl, l) == 0
+- && !((tc & TC_WORD) && isalnum_(p[l]))
++ && !((tc & TS_WORD) && isalnum_(p[l]))
+ ) {
+ /* then this is what we are looking for */
+ t_info = *ti;
+@@ -1174,67 +1211,94 @@ static uint32_t next_token(uint32_t expected)
+ if (!isalnum_(*p))
+ syntax_error(EMSG_UNEXP_TOKEN); /* no */
+ /* yes */
+- t_string = --p;
+- while (isalnum_(*++p)) {
+- p[-1] = *p;
+- }
+- p[-1] = '\0';
+- tc = TC_VARIABLE;
+- /* also consume whitespace between functionname and bracket */
+- if (!(expected & TC_VARIABLE) || (expected & TC_ARRAY))
++ t_string = p;
++ while (isalnum_(*p))
++ p++;
++ end_of_name = p;
++
++ if (last_token_class == TC_FUNCDECL)
++ /* eat space in "function FUNC (...) {...}" declaration */
+ p = skip_spaces(p);
++ else if (expected & TC_ARRAY) {
++ /* eat space between array name and [ */
++ char *s = skip_spaces(p);
++ if (*s == '[') /* array ref, not just a name? */
++ p = s;
++ }
++ /* else: do NOT consume whitespace after variable name!
++ * gawk allows definition "function FUNC (p) {...}" - note space,
++ * but disallows the call "FUNC (p)" because it isn't one -
++ * expression "v (a)" should NOT be parsed as TC_FUNCTION:
++ * it is a valid concatenation if "v" is a variable,
++ * not a function name (and type of name is not known at parse time).
++ */
++
+ if (*p == '(') {
++ p++;
+ tc = TC_FUNCTION;
+ debug_printf_parse("%s: token found:'%s' TC_FUNCTION\n", __func__, t_string);
++ } else if (*p == '[') {
++ p++;
++ tc = TC_ARRAY;
++ debug_printf_parse("%s: token found:'%s' TC_ARRAY\n", __func__, t_string);
+ } else {
+- if (*p == '[') {
+- p++;
+- tc = TC_ARRAY;
+- debug_printf_parse("%s: token found:'%s' TC_ARRAY\n", __func__, t_string);
+- } else
+- debug_printf_parse("%s: token found:'%s' TC_VARIABLE\n", __func__, t_string);
++ tc = TC_VARIABLE;
++ debug_printf_parse("%s: token found:'%s' TC_VARIABLE\n", __func__, t_string);
++ if (end_of_name == p) {
++ /* there is no space for trailing NUL in t_string!
++ * We need to save the char we are going to NUL.
++ * (we'll use it in future call to next_token())
++ */
++ g_saved_ch = *end_of_name;
++// especially pathological example is V="abc"; V.2 - it's V concatenated to .2
++// (it evaluates to "abc0.2"). Because of this case, we can't simply cache
++// '.' and analyze it later: we also have to *store it back* in next
++// next_token(), in order to give my_strtod() the undamaged ".2" string.
++ }
+ }
++ *end_of_name = '\0'; /* terminate t_string */
+ }
+ token_found:
+ g_pos = p;
+
+ /* skipping newlines in some cases */
+- if ((ltclass & TC_NOTERM) && (tc & TC_NEWLINE))
++ if ((last_token_class & TS_NOTERM) && (tc & TC_NEWLINE))
+ goto readnext;
+
+ /* insert concatenation operator when needed */
+- debug_printf_parse("%s: %x %x %x concat_inserted?\n", __func__,
+- (ltclass & TC_CONCAT1), (tc & TC_CONCAT2), (expected & TC_BINOP));
+- if ((ltclass & TC_CONCAT1) && (tc & TC_CONCAT2) && (expected & TC_BINOP)
+- && !(ltclass == TC_LENGTH && tc == TC_SEQSTART) /* but not for "length(..." */
++ debug_printf_parse("%s: concat_inserted if all nonzero: %x %x %x %x\n", __func__,
++ (last_token_class & TS_CONCAT_L), (tc & TS_CONCAT_R), (expected & TS_BINOP),
++ !(last_token_class == TC_LENGTH && tc == TC_LPAREN));
++ if ((last_token_class & TS_CONCAT_L) && (tc & TS_CONCAT_R) && (expected & TS_BINOP)
++ && !(last_token_class == TC_LENGTH && tc == TC_LPAREN) /* but not for "length(..." */
+ ) {
+ concat_inserted = TRUE;
+ save_tclass = tc;
+ save_info = t_info;
+- tc = TC_BINOP;
++ tc = TC_BINOPX;
+ t_info = OC_CONCAT | SS | P(35);
+ }
+
+- debug_printf_parse("%s: t_tclass=tc=%x\n", __func__, t_tclass);
+ t_tclass = tc;
++ debug_printf_parse("%s: t_tclass=tc=%x\n", __func__, tc);
+ }
+- ltclass = t_tclass;
+-
+ /* Are we ready for this? */
+- if (!(ltclass & expected)) {
+- syntax_error((ltclass & (TC_NEWLINE | TC_EOF)) ?
++ if (!(t_tclass & expected)) {
++ syntax_error((last_token_class & (TC_NEWLINE | TC_EOF)) ?
+ EMSG_UNEXP_EOS : EMSG_UNEXP_TOKEN);
+ }
+
+- debug_printf_parse("%s: returning, ltclass:%x t_double:%f\n", __func__, ltclass, t_double);
+- return ltclass;
++ debug_printf_parse("%s: returning, t_double:%f t_tclass:", __func__, t_double);
++ debug_parse_print_tc(t_tclass);
++ debug_printf_parse("\n");
++
++ return t_tclass;
+ #undef concat_inserted
+ #undef save_tclass
+ #undef save_info
+-#undef ltclass
+ }
+
+-static void rollback_token(void)
++static ALWAYS_INLINE void rollback_token(void)
+ {
+ t_rollback = TRUE;
+ }
+@@ -1251,169 +1315,188 @@ static node *new_node(uint32_t info)
+
+ static void mk_re_node(const char *s, node *n, regex_t *re)
+ {
+- n->info = OC_REGEXP;
++ n->info = TI_REGEXP;
+ n->l.re = re;
+ n->r.ire = re + 1;
+ xregcomp(re, s, REG_EXTENDED);
+ xregcomp(re + 1, s, REG_EXTENDED | REG_ICASE);
+ }
+
+-static node *condition(void)
++static node *parse_expr(uint32_t);
++
++static node *parse_lrparen_list(void)
+ {
+- next_token(TC_SEQSTART);
+- return parse_expr(TC_SEQTERM);
++ next_token(TC_LPAREN);
++ return parse_expr(TC_RPAREN);
+ }
+
+ /* parse expression terminated by given argument, return ptr
+ * to built subtree. Terminator is eaten by parse_expr */
+-static node *parse_expr(uint32_t iexp)
++static node *parse_expr(uint32_t term_tc)
+ {
+ node sn;
+ node *cn = &sn;
+ node *vn, *glptr;
+- uint32_t tc, xtc;
++ uint32_t tc, expected_tc;
+ var *v;
+
+- debug_printf_parse("%s(%x)\n", __func__, iexp);
++ debug_printf_parse("%s() term_tc(%x):", __func__, term_tc);
++ debug_parse_print_tc(term_tc);
++ debug_printf_parse("\n");
+
+ sn.info = PRIMASK;
+ sn.r.n = sn.a.n = glptr = NULL;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_REGEXP | iexp;
++ expected_tc = TS_OPERAND | TS_UOPPRE | TC_REGEXP | term_tc;
+
+- while (!((tc = next_token(xtc)) & iexp)) {
++ while (!((tc = next_token(expected_tc)) & term_tc)) {
+
+- if (glptr && (t_info == (OC_COMPARE | VV | P(39) | 2))) {
++ if (glptr && (t_info == TI_LESS)) {
+ /* input redirection (<) attached to glptr node */
+ debug_printf_parse("%s: input redir\n", __func__);
+ cn = glptr->l.n = new_node(OC_CONCAT | SS | P(37));
+ cn->a.n = glptr;
+- xtc = TC_OPERAND | TC_UOPPRE;
++ expected_tc = TS_OPERAND | TS_UOPPRE;
+ glptr = NULL;
+-
+- } else if (tc & (TC_BINOP | TC_UOPPOST)) {
+- debug_printf_parse("%s: TC_BINOP | TC_UOPPOST tc:%x\n", __func__, tc);
++ continue;
++ }
++ if (tc & (TS_BINOP | TC_UOPPOST)) {
++ debug_printf_parse("%s: TS_BINOP | TC_UOPPOST tc:%x\n", __func__, tc);
+ /* for binary and postfix-unary operators, jump back over
+ * previous operators with higher priority */
+ vn = cn;
+ while (((t_info & PRIMASK) > (vn->a.n->info & PRIMASK2))
+- || ((t_info == vn->info) && ((t_info & OPCLSMASK) == OC_COLON))
++ || ((t_info == vn->info) && t_info == TI_COLON)
+ ) {
+ vn = vn->a.n;
+ if (!vn->a.n) syntax_error(EMSG_UNEXP_TOKEN);
+ }
+- if ((t_info & OPCLSMASK) == OC_TERNARY)
++ if (t_info == TI_TERNARY)
++//TODO: why?
+ t_info += P(6);
+ cn = vn->a.n->r.n = new_node(t_info);
+ cn->a.n = vn->a.n;
+- if (tc & TC_BINOP) {
++ if (tc & TS_BINOP) {
+ cn->l.n = vn;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_REGEXP;
+- if ((t_info & OPCLSMASK) == OC_PGETLINE) {
++//FIXME: this is the place to detect and reject assignments to non-lvalues.
++//Currently we allow "assignments" to consts and temporaries, nonsense like this:
++// awk 'BEGIN { "qwe" = 1 }'
++// awk 'BEGIN { 7 *= 7 }'
++// awk 'BEGIN { length("qwe") = 1 }'
++// awk 'BEGIN { (1+1) += 3 }'
++ expected_tc = TS_OPERAND | TS_UOPPRE | TC_REGEXP;
++ if (t_info == TI_PGETLINE) {
+ /* it's a pipe */
+ next_token(TC_GETLINE);
+ /* give maximum priority to this pipe */
+ cn->info &= ~PRIMASK;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_BINOP | iexp;
++ expected_tc = TS_OPERAND | TS_UOPPRE | TS_BINOP | term_tc;
+ }
+ } else {
+ cn->r.n = vn;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_BINOP | iexp;
++ expected_tc = TS_OPERAND | TS_UOPPRE | TS_BINOP | term_tc;
+ }
+ vn->a.n = cn;
++ continue;
++ }
+
+- } else {
+- debug_printf_parse("%s: other\n", __func__);
+- /* for operands and prefix-unary operators, attach them
+- * to last node */
+- vn = cn;
+- cn = vn->r.n = new_node(t_info);
+- cn->a.n = vn;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_REGEXP;
+- if (tc & (TC_OPERAND | TC_REGEXP)) {
+- debug_printf_parse("%s: TC_OPERAND | TC_REGEXP\n", __func__);
+- xtc = TC_UOPPRE | TC_UOPPOST | TC_BINOP | TC_OPERAND | iexp;
+- /* one should be very careful with switch on tclass -
+- * only simple tclasses should be used! */
+- switch (tc) {
+- case TC_VARIABLE:
+- case TC_ARRAY:
+- debug_printf_parse("%s: TC_VARIABLE | TC_ARRAY\n", __func__);
+- cn->info = OC_VAR;
+- v = hash_search(ahash, t_string);
+- if (v != NULL) {
+- cn->info = OC_FNARG;
+- cn->l.aidx = v->x.aidx;
+- } else {
+- cn->l.v = newvar(t_string);
+- }
+- if (tc & TC_ARRAY) {
+- cn->info |= xS;
+- cn->r.n = parse_expr(TC_ARRTERM);
+- }
+- break;
++ debug_printf_parse("%s: other, t_info:%x\n", __func__, t_info);
++ /* for operands and prefix-unary operators, attach them
++ * to last node */
++ vn = cn;
++ cn = vn->r.n = new_node(t_info);
++ cn->a.n = vn;
+
+- case TC_NUMBER:
+- case TC_STRING:
+- debug_printf_parse("%s: TC_NUMBER | TC_STRING\n", __func__);
+- cn->info = OC_VAR;
+- v = cn->l.v = xzalloc(sizeof(var));
+- if (tc & TC_NUMBER)
+- setvar_i(v, t_double);
+- else {
+- setvar_s(v, t_string);
+- xtc &= ~TC_UOPPOST; /* "str"++ is not allowed */
+- }
+- break;
++ expected_tc = TS_OPERAND | TS_UOPPRE | TC_REGEXP;
++ if (t_info == TI_PREINC || t_info == TI_PREDEC)
++ expected_tc = TS_LVALUE | TC_UOPPRE1;
+
+- case TC_REGEXP:
+- debug_printf_parse("%s: TC_REGEXP\n", __func__);
+- mk_re_node(t_string, cn, xzalloc(sizeof(regex_t)*2));
+- break;
++ if (!(tc & (TS_OPERAND | TC_REGEXP)))
++ continue;
+
+- case TC_FUNCTION:
+- debug_printf_parse("%s: TC_FUNCTION\n", __func__);
+- cn->info = OC_FUNC;
+- cn->r.f = newfunc(t_string);
+- cn->l.n = condition();
+- break;
++ debug_printf_parse("%s: TS_OPERAND | TC_REGEXP\n", __func__);
++ expected_tc = TS_UOPPRE | TC_UOPPOST | TS_BINOP | TS_OPERAND | term_tc;
++ /* one should be very careful with switch on tclass -
++ * only simple tclasses should be used (TC_xyz, not TS_xyz) */
++ switch (tc) {
++ case TC_VARIABLE:
++ case TC_ARRAY:
++ debug_printf_parse("%s: TC_VARIABLE | TC_ARRAY\n", __func__);
++ cn->info = OC_VAR;
++ v = hash_search(ahash, t_string);
++ if (v != NULL) {
++ cn->info = OC_FNARG;
++ cn->l.aidx = v->x.aidx;
++ } else {
++ cn->l.v = newvar(t_string);
++ }
++ if (tc & TC_ARRAY) {
++ cn->info |= xS;
++ cn->r.n = parse_expr(TC_ARRTERM);
++ }
++ break;
+
+- case TC_SEQSTART:
+- debug_printf_parse("%s: TC_SEQSTART\n", __func__);
+- cn = vn->r.n = parse_expr(TC_SEQTERM);
+- if (!cn)
+- syntax_error("Empty sequence");
+- cn->a.n = vn;
+- break;
++ case TC_NUMBER:
++ case TC_STRING:
++ debug_printf_parse("%s: TC_NUMBER | TC_STRING\n", __func__);
++ cn->info = OC_VAR;
++ v = cn->l.v = xzalloc(sizeof(var));
++ if (tc & TC_NUMBER)
++ setvar_i(v, t_double);
++ else {
++ setvar_s(v, t_string);
++ expected_tc &= ~TC_UOPPOST; /* "str"++ is not allowed */
++ }
++ break;
+
+- case TC_GETLINE:
+- debug_printf_parse("%s: TC_GETLINE\n", __func__);
+- glptr = cn;
+- xtc = TC_OPERAND | TC_UOPPRE | TC_BINOP | iexp;
+- break;
++ case TC_REGEXP:
++ debug_printf_parse("%s: TC_REGEXP\n", __func__);
++ mk_re_node(t_string, cn, xzalloc(sizeof(regex_t)*2));
++ break;
+
+- case TC_BUILTIN:
+- debug_printf_parse("%s: TC_BUILTIN\n", __func__);
+- cn->l.n = condition();
+- break;
++ case TC_FUNCTION:
++ debug_printf_parse("%s: TC_FUNCTION\n", __func__);
++ cn->info = OC_FUNC;
++ cn->r.f = newfunc(t_string);
++ cn->l.n = parse_expr(TC_RPAREN);
++ break;
+
+- case TC_LENGTH:
+- debug_printf_parse("%s: TC_LENGTH\n", __func__);
+- next_token(TC_SEQSTART /* length(...) */
+- | TC_OPTERM /* length; (or newline)*/
+- | TC_GRPTERM /* length } */
+- | TC_BINOPX /* length <op> NUM */
+- | TC_COMMA /* print length, 1 */
+- );
+- rollback_token();
+- if (t_tclass & TC_SEQSTART) {
+- /* It was a "(" token. Handle just like TC_BUILTIN */
+- cn->l.n = condition();
+- }
+- break;
+- }
++ case TC_LPAREN:
++ debug_printf_parse("%s: TC_LPAREN\n", __func__);
++ cn = vn->r.n = parse_expr(TC_RPAREN);
++ if (!cn)
++ syntax_error("Empty sequence");
++ cn->a.n = vn;
++ break;
++
++ case TC_GETLINE:
++ debug_printf_parse("%s: TC_GETLINE\n", __func__);
++ glptr = cn;
++ expected_tc = TS_OPERAND | TS_UOPPRE | TS_BINOP | term_tc;
++ break;
++
++ case TC_BUILTIN:
++ debug_printf_parse("%s: TC_BUILTIN\n", __func__);
++ cn->l.n = parse_lrparen_list();
++ break;
++
++ case TC_LENGTH:
++ debug_printf_parse("%s: TC_LENGTH\n", __func__);
++ tc = next_token(TC_LPAREN /* length(...) */
++ | TC_SEMICOL /* length; */
++ | TC_NEWLINE /* length<newline> */
++ | TC_RBRACE /* length } */
++ | TC_BINOPX /* length <op> NUM */
++ | TC_COMMA /* print length, 1 */
++ );
++ if (tc != TC_LPAREN)
++ rollback_token();
++ else {
++ /* It was a "(" token. Handle just like TC_BUILTIN */
++ cn->l.n = parse_expr(TC_RPAREN);
+ }
++ break;
+ }
+- }
++ } /* while() */
+
+ debug_printf_parse("%s() returns %p\n", __func__, sn.r.n);
+ return sn.r.n;
+@@ -1430,7 +1513,7 @@ static node *chain_node(uint32_t info)
+ if (seq->programname != g_progname) {
+ seq->programname = g_progname;
+ n = chain_node(OC_NEWSOURCE);
+- n->l.new_progname = xstrdup(g_progname);
++ n->l.new_progname = g_progname;
+ }
+
+ n = seq->last;
+@@ -1446,14 +1529,16 @@ static void chain_expr(uint32_t info)
+
+ n = chain_node(info);
+
+- n->l.n = parse_expr(TC_OPTERM | TC_GRPTERM);
++ n->l.n = parse_expr(TC_SEMICOL | TC_NEWLINE | TC_RBRACE);
+ if ((info & OF_REQUIRED) && !n->l.n)
+ syntax_error(EMSG_TOO_FEW_ARGS);
+
+- if (t_tclass & TC_GRPTERM)
++ if (t_tclass & TC_RBRACE)
+ rollback_token();
+ }
+
++static void chain_group(void);
++
+ static node *chain_loop(node *nn)
+ {
+ node *n, *n2, *save_brk, *save_cont;
+@@ -1477,207 +1562,284 @@ static node *chain_loop(node *nn)
+ return n;
+ }
+
++static void chain_until_rbrace(void)
++{
++ uint32_t tc;
++ while ((tc = next_token(TS_GRPSEQ | TC_RBRACE)) != TC_RBRACE) {
++ debug_printf_parse("%s: !TC_RBRACE\n", __func__);
++ if (tc == TC_NEWLINE)
++ continue;
++ rollback_token();
++ chain_group();
++ }
++ debug_printf_parse("%s: TC_RBRACE\n", __func__);
++}
++
+ /* parse group and attach it to chain */
+ static void chain_group(void)
+ {
+- uint32_t c;
++ uint32_t tc;
+ node *n, *n2, *n3;
+
+ do {
+- c = next_token(TC_GRPSEQ);
+- } while (c & TC_NEWLINE);
+-
+- if (c & TC_GRPSTART) {
+- debug_printf_parse("%s: TC_GRPSTART\n", __func__);
+- while (next_token(TC_GRPSEQ | TC_GRPTERM) != TC_GRPTERM) {
+- debug_printf_parse("%s: !TC_GRPTERM\n", __func__);
+- if (t_tclass & TC_NEWLINE)
+- continue;
+- rollback_token();
+- chain_group();
+- }
+- debug_printf_parse("%s: TC_GRPTERM\n", __func__);
+- } else if (c & (TC_OPSEQ | TC_OPTERM)) {
+- debug_printf_parse("%s: TC_OPSEQ | TC_OPTERM\n", __func__);
++ tc = next_token(TS_GRPSEQ);
++ } while (tc == TC_NEWLINE);
++
++ if (tc == TC_LBRACE) {
++ debug_printf_parse("%s: TC_LBRACE\n", __func__);
++ chain_until_rbrace();
++ return;
++ }
++ if (tc & (TS_OPSEQ | TC_SEMICOL)) {
++ debug_printf_parse("%s: TS_OPSEQ | TC_SEMICOL\n", __func__);
+ rollback_token();
+ chain_expr(OC_EXEC | Vx);
+- } else {
+- /* TC_STATEMNT */
+- debug_printf_parse("%s: TC_STATEMNT(?)\n", __func__);
+- switch (t_info & OPCLSMASK) {
+- case ST_IF:
+- debug_printf_parse("%s: ST_IF\n", __func__);
+- n = chain_node(OC_BR | Vx);
+- n->l.n = condition();
++ return;
++ }
++
++ /* TS_STATEMNT */
++ debug_printf_parse("%s: TS_STATEMNT(?)\n", __func__);
++ switch (t_info & OPCLSMASK) {
++ case ST_IF:
++ debug_printf_parse("%s: ST_IF\n", __func__);
++ n = chain_node(OC_BR | Vx);
++ n->l.n = parse_lrparen_list();
++ chain_group();
++ n2 = chain_node(OC_EXEC);
++ n->r.n = seq->last;
++ if (next_token(TS_GRPSEQ | TC_RBRACE | TC_ELSE) == TC_ELSE) {
+ chain_group();
+- n2 = chain_node(OC_EXEC);
+- n->r.n = seq->last;
+- if (next_token(TC_GRPSEQ | TC_GRPTERM | TC_ELSE) == TC_ELSE) {
+- chain_group();
+- n2->a.n = seq->last;
+- } else {
+- rollback_token();
+- }
+- break;
++ n2->a.n = seq->last;
++ } else {
++ rollback_token();
++ }
++ break;
+
+- case ST_WHILE:
+- debug_printf_parse("%s: ST_WHILE\n", __func__);
+- n2 = condition();
+- n = chain_loop(NULL);
+- n->l.n = n2;
+- break;
++ case ST_WHILE:
++ debug_printf_parse("%s: ST_WHILE\n", __func__);
++ n2 = parse_lrparen_list();
++ n = chain_loop(NULL);
++ n->l.n = n2;
++ break;
+
+- case ST_DO:
+- debug_printf_parse("%s: ST_DO\n", __func__);
+- n2 = chain_node(OC_EXEC);
+- n = chain_loop(NULL);
+- n2->a.n = n->a.n;
+- next_token(TC_WHILE);
+- n->l.n = condition();
+- break;
++ case ST_DO:
++ debug_printf_parse("%s: ST_DO\n", __func__);
++ n2 = chain_node(OC_EXEC);
++ n = chain_loop(NULL);
++ n2->a.n = n->a.n;
++ next_token(TC_WHILE);
++ n->l.n = parse_lrparen_list();
++ break;
+
+- case ST_FOR:
+- debug_printf_parse("%s: ST_FOR\n", __func__);
+- next_token(TC_SEQSTART);
+- n2 = parse_expr(TC_SEMICOL | TC_SEQTERM);
+- if (t_tclass & TC_SEQTERM) { /* for-in */
+- if (!n2 || (n2->info & OPCLSMASK) != OC_IN)
+- syntax_error(EMSG_UNEXP_TOKEN);
+- n = chain_node(OC_WALKINIT | VV);
+- n->l.n = n2->l.n;
+- n->r.n = n2->r.n;
+- n = chain_loop(NULL);
+- n->info = OC_WALKNEXT | Vx;
+- n->l.n = n2->l.n;
+- } else { /* for (;;) */
+- n = chain_node(OC_EXEC | Vx);
+- n->l.n = n2;
+- n2 = parse_expr(TC_SEMICOL);
+- n3 = parse_expr(TC_SEQTERM);
+- n = chain_loop(n3);
+- n->l.n = n2;
+- if (!n2)
+- n->info = OC_EXEC;
+- }
+- break;
++ case ST_FOR:
++ debug_printf_parse("%s: ST_FOR\n", __func__);
++ next_token(TC_LPAREN);
++ n2 = parse_expr(TC_SEMICOL | TC_RPAREN);
++ if (t_tclass & TC_RPAREN) { /* for (I in ARRAY) */
++ if (!n2 || n2->info != TI_IN)
++ syntax_error(EMSG_UNEXP_TOKEN);
++ n = chain_node(OC_WALKINIT | VV);
++ n->l.n = n2->l.n;
++ n->r.n = n2->r.n;
++ n = chain_loop(NULL);
++ n->info = OC_WALKNEXT | Vx;
++ n->l.n = n2->l.n;
++ } else { /* for (;;) */
++ n = chain_node(OC_EXEC | Vx);
++ n->l.n = n2;
++ n2 = parse_expr(TC_SEMICOL);
++ n3 = parse_expr(TC_RPAREN);
++ n = chain_loop(n3);
++ n->l.n = n2;
++ if (!n2)
++ n->info = OC_EXEC;
++ }
++ break;
+
+- case OC_PRINT:
+- case OC_PRINTF:
+- debug_printf_parse("%s: OC_PRINT[F]\n", __func__);
+- n = chain_node(t_info);
+- n->l.n = parse_expr(TC_OPTERM | TC_OUTRDR | TC_GRPTERM);
+- if (t_tclass & TC_OUTRDR) {
+- n->info |= t_info;
+- n->r.n = parse_expr(TC_OPTERM | TC_GRPTERM);
+- }
+- if (t_tclass & TC_GRPTERM)
+- rollback_token();
+- break;
++ case OC_PRINT:
++ case OC_PRINTF:
++ debug_printf_parse("%s: OC_PRINT[F]\n", __func__);
++ n = chain_node(t_info);
++ n->l.n = parse_expr(TC_SEMICOL | TC_NEWLINE | TC_OUTRDR | TC_RBRACE);
++ if (t_tclass & TC_OUTRDR) {
++ n->info |= t_info;
++ n->r.n = parse_expr(TC_SEMICOL | TC_NEWLINE | TC_RBRACE);
++ }
++ if (t_tclass & TC_RBRACE)
++ rollback_token();
++ break;
+
+- case OC_BREAK:
+- debug_printf_parse("%s: OC_BREAK\n", __func__);
+- n = chain_node(OC_EXEC);
+- n->a.n = break_ptr;
+- chain_expr(t_info);
+- break;
++ case OC_BREAK:
++ debug_printf_parse("%s: OC_BREAK\n", __func__);
++ n = chain_node(OC_EXEC);
++ if (!break_ptr)
++ syntax_error("'break' not in a loop");
++ n->a.n = break_ptr;
++ chain_expr(t_info);
++ break;
+
+- case OC_CONTINUE:
+- debug_printf_parse("%s: OC_CONTINUE\n", __func__);
+- n = chain_node(OC_EXEC);
+- n->a.n = continue_ptr;
+- chain_expr(t_info);
+- break;
++ case OC_CONTINUE:
++ debug_printf_parse("%s: OC_CONTINUE\n", __func__);
++ n = chain_node(OC_EXEC);
++ if (!continue_ptr)
++ syntax_error("'continue' not in a loop");
++ n->a.n = continue_ptr;
++ chain_expr(t_info);
++ break;
+
+- /* delete, next, nextfile, return, exit */
+- default:
+- debug_printf_parse("%s: default\n", __func__);
+- chain_expr(t_info);
+- }
++ /* delete, next, nextfile, return, exit */
++ default:
++ debug_printf_parse("%s: default\n", __func__);
++ chain_expr(t_info);
+ }
+ }
+
+ static void parse_program(char *p)
+ {
+- uint32_t tclass;
+- node *cn;
+- func *f;
+- var *v;
++ debug_printf_parse("%s()\n", __func__);
+
+ g_pos = p;
+ t_lineno = 1;
+- while ((tclass = next_token(TC_EOF | TC_OPSEQ | TC_GRPSTART |
+- TC_OPTERM | TC_BEGIN | TC_END | TC_FUNCDECL)) != TC_EOF) {
++ for (;;) {
++ uint32_t tclass;
+
+- if (tclass & TC_OPTERM) {
+- debug_printf_parse("%s: TC_OPTERM\n", __func__);
++ tclass = next_token(TS_OPSEQ | TC_LBRACE | TC_BEGIN | TC_END | TC_FUNCDECL
++ | TC_EOF | TC_NEWLINE /* but not TC_SEMICOL */);
++ got_tok:
++ if (tclass == TC_EOF) {
++ debug_printf_parse("%s: TC_EOF\n", __func__);
++ break;
++ }
++ if (tclass == TC_NEWLINE) {
++ debug_printf_parse("%s: TC_NEWLINE\n", __func__);
+ continue;
+ }
+-
+- seq = &mainseq;
+- if (tclass & TC_BEGIN) {
++ if (tclass == TC_BEGIN) {
+ debug_printf_parse("%s: TC_BEGIN\n", __func__);
+ seq = &beginseq;
+- chain_group();
+- } else if (tclass & TC_END) {
++ /* ensure there is no newline between BEGIN and { */
++ next_token(TC_LBRACE);
++ chain_until_rbrace();
++ goto next_tok;
++ }
++ if (tclass == TC_END) {
+ debug_printf_parse("%s: TC_END\n", __func__);
+ seq = &endseq;
+- chain_group();
+- } else if (tclass & TC_FUNCDECL) {
++ /* ensure there is no newline between END and { */
++ next_token(TC_LBRACE);
++ chain_until_rbrace();
++ goto next_tok;
++ }
++ if (tclass == TC_FUNCDECL) {
++ func *f;
++
+ debug_printf_parse("%s: TC_FUNCDECL\n", __func__);
+ next_token(TC_FUNCTION);
+- g_pos++;
+ f = newfunc(t_string);
+- f->body.first = NULL;
+- f->nargs = 0;
+- /* Match func arg list: a comma sep list of >= 0 args, and a close paren */
+- while (next_token(TC_VARIABLE | TC_SEQTERM | TC_COMMA)) {
+- /* Either an empty arg list, or trailing comma from prev iter
+- * must be followed by an arg */
+- if (f->nargs == 0 && t_tclass == TC_SEQTERM)
+- break;
+-
+- /* TC_SEQSTART/TC_COMMA must be followed by TC_VARIABLE */
+- if (t_tclass != TC_VARIABLE)
++ if (f->defined)
++ syntax_error("Duplicate function");
++ f->defined = 1;
++ //f->body.first = NULL; - already is
++ //f->nargs = 0; - already is
++ /* func arg list: comma sep list of args, and a close paren */
++ for (;;) {
++ var *v;
++ if (next_token(TC_VARIABLE | TC_RPAREN) == TC_RPAREN) {
++ if (f->nargs == 0)
++ break; /* func() is ok */
++ /* func(a,) is not ok */
+ syntax_error(EMSG_UNEXP_TOKEN);
+-
++ }
+ v = findvar(ahash, t_string);
+ v->x.aidx = f->nargs++;
+-
+ /* Arg followed either by end of arg list or 1 comma */
+- if (next_token(TC_COMMA | TC_SEQTERM) & TC_SEQTERM)
++ if (next_token(TC_COMMA | TC_RPAREN) == TC_RPAREN)
+ break;
+- if (t_tclass != TC_COMMA)
+- syntax_error(EMSG_UNEXP_TOKEN);
++ /* it was a comma, we ate it */
+ }
+ seq = &f->body;
+- chain_group();
+- clear_array(ahash);
+- } else if (tclass & TC_OPSEQ) {
+- debug_printf_parse("%s: TC_OPSEQ\n", __func__);
++ /* ensure there is { after "func F(...)" - but newlines are allowed */
++ while (next_token(TC_LBRACE | TC_NEWLINE) == TC_NEWLINE)
++ continue;
++ chain_until_rbrace();
++ hash_clear(ahash);
++ goto next_tok;
++ }
++ seq = &mainseq;
++ if (tclass & TS_OPSEQ) {
++ node *cn;
++
++ debug_printf_parse("%s: TS_OPSEQ\n", __func__);
+ rollback_token();
+ cn = chain_node(OC_TEST);
+- cn->l.n = parse_expr(TC_OPTERM | TC_EOF | TC_GRPSTART);
+- if (t_tclass & TC_GRPSTART) {
+- debug_printf_parse("%s: TC_GRPSTART\n", __func__);
+- rollback_token();
+- chain_group();
++ cn->l.n = parse_expr(TC_SEMICOL | TC_NEWLINE | TC_EOF | TC_LBRACE);
++ if (t_tclass == TC_LBRACE) {
++ debug_printf_parse("%s: TC_LBRACE\n", __func__);
++ chain_until_rbrace();
+ } else {
+- debug_printf_parse("%s: !TC_GRPSTART\n", __func__);
++ /* no action, assume default "{ print }" */
++ debug_printf_parse("%s: !TC_LBRACE\n", __func__);
+ chain_node(OC_PRINT);
+ }
+ cn->r.n = mainseq.last;
+- } else /* if (tclass & TC_GRPSTART) */ {
+- debug_printf_parse("%s: TC_GRPSTART(?)\n", __func__);
+- rollback_token();
+- chain_group();
++ goto next_tok;
+ }
+- }
+- debug_printf_parse("%s: TC_EOF\n", __func__);
++ /* tclass == TC_LBRACE */
++ debug_printf_parse("%s: TC_LBRACE(?)\n", __func__);
++ chain_until_rbrace();
++ next_tok:
++ /* Same as next_token() at the top of the loop, + TC_SEMICOL */
++ tclass = next_token(TS_OPSEQ | TC_LBRACE | TC_BEGIN | TC_END | TC_FUNCDECL
++ | TC_EOF | TC_NEWLINE | TC_SEMICOL);
++ /* gawk allows many newlines, but does not allow more than one semicolon:
++ * BEGIN {...}<newline>;<newline>;
++ * would complain "each rule must have a pattern or an action part".
++ * Same message for
++ * ; BEGIN {...}
++ */
++ if (tclass != TC_SEMICOL)
++ goto got_tok; /* use this token */
++ /* else: loop back - ate the semicolon, get and use _next_ token */
++ } /* for (;;) */
+ }
+
+-
+ /* -------- program execution part -------- */
+
++/* temporary variables allocator */
++static var *nvalloc(int sz)
++{
++ return xzalloc(sz * sizeof(var));
++}
++
++static void nvfree(var *v, int sz)
++{
++ var *p = v;
++
++ while (--sz >= 0) {
++ if ((p->type & (VF_ARRAY | VF_CHILD)) == VF_ARRAY) {
++ clear_array(iamarray(p));
++ free(p->x.array->items);
++ free(p->x.array);
++ }
++ if (p->type & VF_WALK) {
++ walker_list *n;
++ walker_list *w = p->x.walker;
++ debug_printf_walker("nvfree: freeing walker @%p\n", &p->x.walker);
++ p->x.walker = NULL;
++ while (w) {
++ n = w->prev;
++ debug_printf_walker(" free(%p)\n", w);
++ free(w);
++ w = n;
++ }
++ }
++ clrvar(p);
++ p++;
++ }
++
++ free(v);
++}
++
+ static node *mk_splitter(const char *s, tsplitter *spl)
+ {
+ regex_t *re, *ire;
+@@ -1686,7 +1848,7 @@ static node *mk_splitter(const char *s, tsplitter *spl)
+ re = &spl->re[0];
+ ire = &spl->re[1];
+ n = &spl->n;
+- if ((n->info & OPCLSMASK) == OC_REGEXP) {
++ if (n->info == TI_REGEXP) {
+ regfree(re);
+ regfree(ire); // TODO: nuke ire, use re+1?
+ }
+@@ -1699,21 +1861,28 @@ static node *mk_splitter(const char *s, tsplitter *spl)
+ return n;
+ }
+
+-/* use node as a regular expression. Supplied with node ptr and regex_t
++static var *evaluate(node *, var *);
++
++/* Use node as a regular expression. Supplied with node ptr and regex_t
+ * storage space. Return ptr to regex (if result points to preg, it should
+- * be later regfree'd manually
++ * be later regfree'd manually).
+ */
+ static regex_t *as_regex(node *op, regex_t *preg)
+ {
+ int cflags;
+- var *v;
+ const char *s;
+
+- if ((op->info & OPCLSMASK) == OC_REGEXP) {
++ if (op->info == TI_REGEXP) {
+ return icase ? op->r.ire : op->l.re;
+ }
+- v = nvalloc(1);
+- s = getvar_s(evaluate(op, v));
++
++ //tmpvar = nvalloc(1);
++#define TMPVAR (&G.as_regex__tmpvar)
++ // We use a single "static" tmpvar (instead of on-stack or malloced one)
++ // to decrease memory consumption in deeply-recursive awk programs.
++ // The rule to work safely is to never call evaluate() while our static
++ // TMPVAR's value is still needed.
++ s = getvar_s(evaluate(op, TMPVAR));
+
+ cflags = icase ? REG_EXTENDED | REG_ICASE : REG_EXTENDED;
+ /* Testcase where REG_EXTENDED fails (unpaired '{'):
+@@ -1725,7 +1894,8 @@ static regex_t *as_regex(node *op, regex_t *preg)
+ cflags &= ~REG_EXTENDED;
+ xregcomp(preg, s, cflags);
+ }
+- nvfree(v);
++ //nvfree(tmpvar, 1);
++#undef TMPVAR
+ return preg;
+ }
+
+@@ -1745,12 +1915,22 @@ static char* qrealloc(char *b, int n, int *size)
+ /* resize field storage space */
+ static void fsrealloc(int size)
+ {
+- int i;
++ int i, newsize;
+
+ if (size >= maxfields) {
++ /* Sanity cap, easier than catering for overflows */
++ if (size > 0xffffff)
++ bb_die_memory_exhausted();
++
+ i = maxfields;
+ maxfields = size + 16;
+- Fields = xrealloc(Fields, maxfields * sizeof(Fields[0]));
++
++ newsize = maxfields * sizeof(Fields[0]);
++ debug_printf_eval("fsrealloc: xrealloc(%p, %u)\n", Fields, newsize);
++ Fields = xrealloc(Fields, newsize);
++ debug_printf_eval("fsrealloc: Fields=%p..%p\n", Fields, (char*)Fields + newsize - 1);
++ /* ^^^ did Fields[] move? debug aid for L.v getting "upstaged" by R.v in evaluate() */
++
+ for (; i < maxfields; i++) {
+ Fields[i].type = VF_SPECIAL;
+ Fields[i].string = NULL;
+@@ -1802,13 +1982,13 @@ static int awk_split(const char *s, node *spl, char **slist)
+ c[2] = '\n';
+
+ n = 0;
+- if ((spl->info & OPCLSMASK) == OC_REGEXP) { /* regex split */
++ if (spl->info == TI_REGEXP) { /* regex split */
+ if (!*s)
+ return n; /* "": zero fields */
+ n++; /* at least one field will be there */
+ do {
+ int l;
+- regmatch_t pmatch[2]; // TODO: why [2]? [1] is enough...
++ regmatch_t pmatch[1];
+
+ l = strcspn(s, c+2); /* len till next NUL or \n */
+ if (regexec1_nonempty(icase ? spl->r.ire : spl->l.re, s, pmatch) == 0
+@@ -1969,7 +2149,7 @@ static node *nextarg(node **pn)
+ node *n;
+
+ n = *pn;
+- if (n && (n->info & OPCLSMASK) == OC_COMMA) {
++ if (n && n->info == TI_COMMA) {
+ *pn = n->r.n;
+ n = n->l.n;
+ } else {
+@@ -2000,8 +2180,7 @@ static void hashwalk_init(var *v, xhash *array)
+ for (i = 0; i < array->csize; i++) {
+ hi = array->items[i];
+ while (hi) {
+- strcpy(w->end, hi->name);
+- nextword(&w->end);
++ w->end = stpcpy(w->end, hi->name) + 1;
+ hi = hi->next;
+ }
+ }
+@@ -2027,15 +2206,18 @@ static int hashwalk_next(var *v)
+ /* evaluate node, return 1 when result is true, 0 otherwise */
+ static int ptest(node *pattern)
+ {
+- /* ptest__v is "static": to save stack space? */
+- return istrue(evaluate(pattern, &G.ptest__v));
++ // We use a single "static" tmpvar (instead of on-stack or malloced one)
++ // to decrease memory consumption in deeply-recursive awk programs.
++ // The rule to work safely is to never call evaluate() while our static
++ // TMPVAR's value is still needed.
++ return istrue(evaluate(pattern, &G.ptest__tmpvar));
+ }
+
+ /* read next record from stream rsm into a variable v */
+ static int awk_getline(rstream *rsm, var *v)
+ {
+ char *b;
+- regmatch_t pmatch[2]; // TODO: why [2]? [1] is enough...
++ regmatch_t pmatch[1];
+ int size, a, p, pp = 0;
+ int fd, so, eo, r, rp;
+ char c, *m, *s;
+@@ -2061,7 +2243,7 @@ static int awk_getline(rstream *rsm, var *v)
+ so = eo = p;
+ r = 1;
+ if (p > 0) {
+- if ((rsplitter.n.info & OPCLSMASK) == OC_REGEXP) {
++ if (rsplitter.n.info == TI_REGEXP) {
+ if (regexec(icase ? rsplitter.n.r.ire : rsplitter.n.l.re,
+ b, 1, pmatch, 0) == 0) {
+ so = pmatch[0].rm_so;
+@@ -2133,82 +2315,126 @@ static int awk_getline(rstream *rsm, var *v)
+ return r;
+ }
+
+-static int fmt_num(char *b, int size, const char *format, double n, int int_as_int)
+-{
+- int r = 0;
+- char c;
+- const char *s = format;
+-
+- if (int_as_int && n == (long long)n) {
+- r = snprintf(b, size, "%lld", (long long)n);
+- } else {
+- do { c = *s; } while (c && *++s);
+- if (strchr("diouxX", c)) {
+- r = snprintf(b, size, format, (int)n);
+- } else if (strchr("eEfgG", c)) {
+- r = snprintf(b, size, format, n);
+- } else {
+- syntax_error(EMSG_INV_FMT);
+- }
+- }
+- return r;
+-}
+-
+ /* formatted output into an allocated buffer, return ptr to buffer */
+-static char *awk_printf(node *n)
++#if !ENABLE_FEATURE_AWK_GNU_EXTENSIONS
++# define awk_printf(a, b) awk_printf(a)
++#endif
++static char *awk_printf(node *n, size_t *len)
+ {
+- char *b = NULL;
+- char *fmt, *s, *f;
+- const char *s1;
+- int i, j, incr, bsize;
+- char c, c1;
+- var *v, *arg;
+-
+- v = nvalloc(1);
+- fmt = f = xstrdup(getvar_s(evaluate(nextarg(&n), v)));
+-
++ char *b;
++ char *fmt, *f;
++ size_t i;
++
++ //tmpvar = nvalloc(1);
++#define TMPVAR (&G.awk_printf__tmpvar)
++ // We use a single "static" tmpvar (instead of on-stack or malloced one)
++ // to decrease memory consumption in deeply-recursive awk programs.
++ // The rule to work safely is to never call evaluate() while our static
++ // TMPVAR's value is still needed.
++ fmt = f = xstrdup(getvar_s(evaluate(nextarg(&n), TMPVAR)));
++ // ^^^^^^^^^ here we immediately strdup() the value, so the later call
++ // to evaluate() potentially recursing into another awk_printf() can't
++ // mangle the value.
++
++ b = NULL;
+ i = 0;
+- while (*f) {
++ while (1) { /* "print one format spec" loop */
++ char *s;
++ char c;
++ char sv;
++ var *arg;
++ size_t slen;
++
++ /* Find end of the next format spec, or end of line */
+ s = f;
+- while (*f && (*f != '%' || *++f == '%'))
+- f++;
+- while (*f && !isalpha(*f)) {
+- if (*f == '*')
+- syntax_error("%*x formats are not supported");
++ while (1) {
++ c = *f;
++ if (!c) /* no percent chars found at all */
++ goto nul;
+ f++;
++ if (c == '%')
++ break;
+ }
+-
+- incr = (f - s) + MAXVARFMT;
+- b = qrealloc(b, incr + i, &bsize);
++ /* we are past % in "....%..." */
+ c = *f;
+- if (c != '\0')
++ if (!c) /* "....%" */
++ goto nul;
++ if (c == '%') { /* "....%%...." */
++ slen = f - s;
++ s = xstrndup(s, slen);
+ f++;
+- c1 = *f;
++ goto append; /* print "....%" part verbatim */
++ }
++ while (1) {
++ if (isalpha(c))
++ break;
++ if (c == '*')
++ syntax_error("%*x formats are not supported");
++ c = *++f;
++ if (!c) { /* "....%...." and no letter found after % */
++ /* Example: awk 'BEGIN { printf "^^^%^^^\n"; }' */
++ nul:
++ slen = f - s;
++ goto tail; /* print remaining string, exit loop */
++ }
++ }
++ /* we are at A in "....%...A..." */
++
++ arg = evaluate(nextarg(&n), TMPVAR);
++
++ /* Result can be arbitrarily long. Example:
++ * printf "%99999s", "BOOM"
++ */
++ sv = *++f;
+ *f = '\0';
+- arg = evaluate(nextarg(&n), v);
+-
+- j = i;
+- if (c == 'c' || !c) {
+- i += sprintf(b+i, s, is_numeric(arg) ?
+- (char)getvar_i(arg) : *getvar_s(arg));
+- } else if (c == 's') {
+- s1 = getvar_s(arg);
+- b = qrealloc(b, incr+i+strlen(s1), &bsize);
+- i += sprintf(b+i, s, s1);
++ if (c == 'c') {
++ char cc = is_numeric(arg) ? getvar_i(arg) : *getvar_s(arg);
++ char *r = xasprintf(s, cc ? cc : '^' /* else strlen will be wrong */);
++ slen = strlen(r);
++ if (cc == '\0') /* if cc is NUL, re-format the string with it */
++ sprintf(r, s, cc);
++ s = r;
+ } else {
+- i += fmt_num(b+i, incr, s, getvar_i(arg), FALSE);
++ if (c == 's') {
++ s = xasprintf(s, getvar_s(arg));
++ } else {
++ double d = getvar_i(arg);
++ if (strchr("diouxX", c)) {
++//TODO: make it wider here (%x -> %llx etc)?
++ s = xasprintf(s, (int)d);
++ } else if (strchr("eEfFgGaA", c)) {
++ s = xasprintf(s, d);
++ } else {
++//TODO: GNU Awk 5.0.1: printf "%W" prints "%W", does not error out
++ syntax_error(EMSG_INV_FMT);
++ }
++ }
++ slen = strlen(s);
+ }
+- *f = c1;
+-
+- /* if there was an error while sprintf, return value is negative */
+- if (i < j)
+- i = j;
++ *f = sv;
++ append:
++ if (i == 0) {
++ b = s;
++ i = slen;
++ continue;
++ }
++ tail:
++ b = xrealloc(b, i + slen + 1);
++ strcpy(b + i, s);
++ i += slen;
++ if (!c) /* s is NOT allocated and this is the last part of string? */
++ break;
++ free(s);
+ }
+
+ free(fmt);
+- nvfree(v);
+- b = xrealloc(b, i + 1);
+- b[i] = '\0';
++ //nvfree(tmpvar, 1);
++#undef TMPVAR
++
++#if ENABLE_FEATURE_AWK_GNU_EXTENSIONS
++ if (len)
++ *len = i;
++#endif
+ return b;
+ }
+
+@@ -2338,33 +2564,59 @@ static NOINLINE int do_mktime(const char *ds)
+ return mktime(&then);
+ }
+
++/* Reduce stack usage in exec_builtin() by keeping match() code separate */
++static NOINLINE var *do_match(node *an1, const char *as0)
++{
++ regmatch_t pmatch[1];
++ regex_t sreg, *re;
++ int n, start, len;
++
++ re = as_regex(an1, &sreg);
++ n = regexec(re, as0, 1, pmatch, 0);
++ if (re == &sreg)
++ regfree(re);
++ start = 0;
++ len = -1;
++ if (n == 0) {
++ start = pmatch[0].rm_so + 1;
++ len = pmatch[0].rm_eo - pmatch[0].rm_so;
++ }
++ setvar_i(newvar("RLENGTH"), len);
++ return setvar_i(newvar("RSTART"), start);
++}
++
++/* Reduce stack usage in evaluate() by keeping builtins' code separate */
+ static NOINLINE var *exec_builtin(node *op, var *res)
+ {
+ #define tspl (G.exec_builtin__tspl)
+
+- var *tv;
++ var *tmpvars;
+ node *an[4];
+ var *av[4];
+ const char *as[4];
+- regmatch_t pmatch[2];
+- regex_t sreg, *re;
+ node *spl;
+ uint32_t isr, info;
+ int nargs;
+ time_t tt;
+ int i, l, ll, n;
+
+- tv = nvalloc(4);
++ tmpvars = nvalloc(4);
++#define TMPVAR0 (tmpvars)
++#define TMPVAR1 (tmpvars + 1)
++#define TMPVAR2 (tmpvars + 2)
++#define TMPVAR3 (tmpvars + 3)
++#define TMPVAR(i) (tmpvars + (i))
+ isr = info = op->info;
+ op = op->l.n;
+
+ av[2] = av[3] = NULL;
+ for (i = 0; i < 4 && op; i++) {
+ an[i] = nextarg(&op);
+- if (isr & 0x09000000)
+- av[i] = evaluate(an[i], &tv[i]);
+- if (isr & 0x08000000)
+- as[i] = getvar_s(av[i]);
++ if (isr & 0x09000000) {
++ av[i] = evaluate(an[i], TMPVAR(i));
++ if (isr & 0x08000000)
++ as[i] = getvar_s(av[i]);
++ }
+ isr >>= 1;
+ }
+
+@@ -2386,8 +2638,8 @@ static NOINLINE var *exec_builtin(node *op, var *res)
+ char *s, *s1;
+
+ if (nargs > 2) {
+- spl = (an[2]->info & OPCLSMASK) == OC_REGEXP ?
+- an[2] : mk_splitter(getvar_s(evaluate(an[2], &tv[2])), &tspl);
++ spl = (an[2]->info == TI_REGEXP) ? an[2]
++ : mk_splitter(getvar_s(evaluate(an[2], TMPVAR2)), &tspl);
+ } else {
+ spl = &fsplitter.n;
+ }
+@@ -2501,20 +2753,7 @@ static NOINLINE var *exec_builtin(node *op, var *res)
+ break;
+
+ case B_ma:
+- re = as_regex(an[1], &sreg);
+- n = regexec(re, as[0], 1, pmatch, 0);
+- if (n == 0) {
+- pmatch[0].rm_so++;
+- pmatch[0].rm_eo++;
+- } else {
+- pmatch[0].rm_so = 0;
+- pmatch[0].rm_eo = -1;
+- }
+- setvar_i(newvar("RSTART"), pmatch[0].rm_so);
+- setvar_i(newvar("RLENGTH"), pmatch[0].rm_eo - pmatch[0].rm_so);
+- setvar_i(res, pmatch[0].rm_so);
+- if (re == &sreg)
+- regfree(re);
++ res = do_match(an[1], as[0]);
+ break;
+
+ case B_ge:
+@@ -2530,14 +2769,79 @@ static NOINLINE var *exec_builtin(node *op, var *res)
+ break;
+ }
+
+- nvfree(tv);
++ nvfree(tmpvars, 4);
++#undef TMPVAR0
++#undef TMPVAR1
++#undef TMPVAR2
++#undef TMPVAR3
++#undef TMPVAR
++
+ return res;
+ #undef tspl
+ }
+
++/* if expr looks like "var=value", perform assignment and return 1,
++ * otherwise return 0 */
++static int is_assignment(const char *expr)
++{
++ char *exprc, *val;
++
++ val = (char*)endofname(expr);
++ if (val == (char*)expr || *val != '=') {
++ return FALSE;
++ }
++
++ exprc = xstrdup(expr);
++ val = exprc + (val - expr);
++ *val++ = '\0';
++
++ unescape_string_in_place(val);
++ setvar_u(newvar(exprc), val);
++ free(exprc);
++ return TRUE;
++}
++
++/* switch to next input file */
++static rstream *next_input_file(void)
++{
++#define rsm (G.next_input_file__rsm)
++#define files_happen (G.next_input_file__files_happen)
++
++ const char *fname, *ind;
++
++ if (rsm.F)
++ fclose(rsm.F);
++ rsm.F = NULL;
++ rsm.pos = rsm.adv = 0;
++
++ for (;;) {
++ if (getvar_i(intvar[ARGIND])+1 >= getvar_i(intvar[ARGC])) {
++ if (files_happen)
++ return NULL;
++ fname = "-";
++ rsm.F = stdin;
++ break;
++ }
++ ind = getvar_s(incvar(intvar[ARGIND]));
++ fname = getvar_s(findvar(iamarray(intvar[ARGV]), ind));
++ if (fname && *fname && !is_assignment(fname)) {
++ rsm.F = xfopen_stdin(fname);
++ break;
++ }
++ }
++
++ files_happen = TRUE;
++ setvar_s(intvar[FILENAME], fname);
++ return &rsm;
++#undef rsm
++#undef files_happen
++}
++
+ /*
+ * Evaluate node - the heart of the program. Supplied with subtree
+- * and place where to store result. returns ptr to result.
++ * and "res" variable to assign the result to if we evaluate an expression.
++ * If node refers to e.g. a variable or a field, no assignment happens.
++ * Return ptr to the result (which may or may not be the "res" variable!)
+ */
+ #define XC(n) ((n) >> 8)
+
+@@ -2549,14 +2853,16 @@ static var *evaluate(node *op, var *res)
+ #define seed (G.evaluate__seed)
+ #define sreg (G.evaluate__sreg)
+
+- var *v1;
++ var *tmpvars;
+
+ if (!op)
+ return setvar_s(res, NULL);
+
+ debug_printf_eval("entered %s()\n", __func__);
+
+- v1 = nvalloc(2);
++ tmpvars = nvalloc(2);
++#define TMPVAR0 (tmpvars)
++#define TMPVAR1 (tmpvars + 1)
+
+ while (op) {
+ struct {
+@@ -2578,48 +2884,35 @@ static var *evaluate(node *op, var *res)
+ op1 = op->l.n;
+ debug_printf_eval("opinfo:%08x opn:%08x\n", opinfo, opn);
+
+- /* "delete" is special:
+- * "delete array[var--]" must evaluate index expr only once,
+- * must not evaluate it in "execute inevitable things" part.
+- */
+- if (XC(opinfo & OPCLSMASK) == XC(OC_DELETE)) {
+- uint32_t info = op1->info & OPCLSMASK;
+- var *v;
+-
+- debug_printf_eval("DELETE\n");
+- if (info == OC_VAR) {
+- v = op1->l.v;
+- } else if (info == OC_FNARG) {
+- v = &fnargs[op1->l.aidx];
+- } else {
+- syntax_error(EMSG_NOT_ARRAY);
++ /* execute inevitable things */
++ if (opinfo & OF_RES1) {
++ if ((opinfo & OF_REQUIRED) && !op1)
++ syntax_error(EMSG_TOO_FEW_ARGS);
++ L.v = evaluate(op1, TMPVAR0);
++ if (opinfo & OF_STR1) {
++ L.s = getvar_s(L.v);
++ debug_printf_eval("L.s:'%s'\n", L.s);
+ }
+- if (op1->r.n) { /* array ref? */
+- const char *s;
+- s = getvar_s(evaluate(op1->r.n, v1));
+- hash_remove(iamarray(v), s);
+- } else {
+- clear_array(iamarray(v));
++ if (opinfo & OF_NUM1) {
++ L_d = getvar_i(L.v);
++ debug_printf_eval("L_d:%f\n", L_d);
+ }
+- goto next;
+ }
+-
+- /* execute inevitable things */
+- if (opinfo & OF_RES1)
+- L.v = evaluate(op1, v1);
+- if (opinfo & OF_RES2)
+- R.v = evaluate(op->r.n, v1+1);
+- if (opinfo & OF_STR1) {
+- L.s = getvar_s(L.v);
+- debug_printf_eval("L.s:'%s'\n", L.s);
+- }
+- if (opinfo & OF_STR2) {
+- R.s = getvar_s(R.v);
+- debug_printf_eval("R.s:'%s'\n", R.s);
+- }
+- if (opinfo & OF_NUM1) {
+- L_d = getvar_i(L.v);
+- debug_printf_eval("L_d:%f\n", L_d);
++ /* NB: Must get string/numeric values of L (done above)
++ * _before_ evaluate()'ing R.v: if both L and R are $NNNs,
++ * and right one is large, then L.v points to Fields[NNN1],
++ * second evaluate() reallocates and moves (!) Fields[],
++ * R.v points to Fields[NNN2] but L.v now points to freed mem!
++ * (Seen trying to evaluate "$444 $44444")
++ */
++ if (opinfo & OF_RES2) {
++ R.v = evaluate(op->r.n, TMPVAR1);
++ //TODO: L.v may be invalid now, set L.v to NULL to catch bugs?
++ //L.v = NULL;
++ if (opinfo & OF_STR2) {
++ R.s = getvar_s(R.v);
++ debug_printf_eval("R.s:'%s'\n", R.s);
++ }
+ }
+
+ debug_printf_eval("switch(0x%x)\n", XC(opinfo & OPCLSMASK));
+@@ -2629,7 +2922,8 @@ static var *evaluate(node *op, var *res)
+
+ /* test pattern */
+ case XC( OC_TEST ):
+- if ((op1->info & OPCLSMASK) == OC_COMMA) {
++ debug_printf_eval("TEST\n");
++ if (op1->info == TI_COMMA) {
+ /* it's range pattern */
+ if ((opinfo & OF_CHECKED) || ptest(op1->l.n)) {
+ op->info |= OF_CHECKED;
+@@ -2646,25 +2940,32 @@ static var *evaluate(node *op, var *res)
+
+ /* just evaluate an expression, also used as unconditional jump */
+ case XC( OC_EXEC ):
++ debug_printf_eval("EXEC\n");
+ break;
+
+ /* branch, used in if-else and various loops */
+ case XC( OC_BR ):
++ debug_printf_eval("BR\n");
+ op = istrue(L.v) ? op->a.n : op->r.n;
+ break;
+
+ /* initialize for-in loop */
+ case XC( OC_WALKINIT ):
++ debug_printf_eval("WALKINIT\n");
+ hashwalk_init(L.v, iamarray(R.v));
+ break;
+
+ /* get next array item */
+ case XC( OC_WALKNEXT ):
++ debug_printf_eval("WALKNEXT\n");
+ op = hashwalk_next(L.v) ? op->a.n : op->r.n;
+ break;
+
+ case XC( OC_PRINT ):
+- case XC( OC_PRINTF ): {
++ debug_printf_eval("PRINT /\n");
++ case XC( OC_PRINTF ):
++ debug_printf_eval("PRINTF\n");
++ {
+ FILE *F = stdout;
+
+ if (op->r.n) {
+@@ -2682,55 +2983,94 @@ static var *evaluate(node *op, var *res)
+ F = rsm->F;
+ }
+
++ /* Can't just check 'opinfo == OC_PRINT' here, parser ORs
++ * additional bits to opinfos of print/printf with redirects
++ */
+ if ((opinfo & OPCLSMASK) == OC_PRINT) {
+ if (!op1) {
+ fputs(getvar_s(intvar[F0]), F);
+ } else {
+- while (op1) {
+- var *v = evaluate(nextarg(&op1), v1);
++ for (;;) {
++ var *v = evaluate(nextarg(&op1), TMPVAR0);
+ if (v->type & VF_NUMBER) {
+- fmt_num(g_buf, MAXVARFMT, getvar_s(intvar[OFMT]),
+- getvar_i(v), TRUE);
++ fmt_num(getvar_s(intvar[OFMT]),
++ getvar_i(v));
+ fputs(g_buf, F);
+ } else {
+ fputs(getvar_s(v), F);
+ }
+-
+- if (op1)
+- fputs(getvar_s(intvar[OFS]), F);
++ if (!op1)
++ break;
++ fputs(getvar_s(intvar[OFS]), F);
+ }
+ }
+ fputs(getvar_s(intvar[ORS]), F);
+-
+- } else { /* OC_PRINTF */
+- char *s = awk_printf(op1);
++ } else { /* PRINTF */
++ IF_FEATURE_AWK_GNU_EXTENSIONS(size_t len;)
++ char *s = awk_printf(op1, &len);
++#if ENABLE_FEATURE_AWK_GNU_EXTENSIONS
++ fwrite(s, len, 1, F);
++#else
+ fputs(s, F);
++#endif
+ free(s);
+ }
+ fflush(F);
+ break;
+ }
+
+- /* case XC( OC_DELETE ): - moved to happen before arg evaluation */
++ case XC( OC_DELETE ):
++ debug_printf_eval("DELETE\n");
++ {
++ /* "delete" is special:
++ * "delete array[var--]" must evaluate index expr only once.
++ */
++ uint32_t info = op1->info & OPCLSMASK;
++ var *v;
++
++ if (info == OC_VAR) {
++ v = op1->l.v;
++ } else if (info == OC_FNARG) {
++ v = &fnargs[op1->l.aidx];
++ } else {
++ syntax_error(EMSG_NOT_ARRAY);
++ }
++ if (op1->r.n) { /* array ref? */
++ const char *s;
++ s = getvar_s(evaluate(op1->r.n, TMPVAR0));
++ hash_remove(iamarray(v), s);
++ } else {
++ clear_array(iamarray(v));
++ }
++ break;
++ }
+
+ case XC( OC_NEWSOURCE ):
++ debug_printf_eval("NEWSOURCE\n");
+ g_progname = op->l.new_progname;
+ break;
+
+ case XC( OC_RETURN ):
++ debug_printf_eval("RETURN\n");
+ copyvar(res, L.v);
+ break;
+
+ case XC( OC_NEXTFILE ):
++ debug_printf_eval("NEXTFILE\n");
+ nextfile = TRUE;
+ case XC( OC_NEXT ):
++ debug_printf_eval("NEXT\n");
+ nextrec = TRUE;
+ case XC( OC_DONE ):
++ debug_printf_eval("DONE\n");
+ clrvar(res);
+ break;
+
+ case XC( OC_EXIT ):
+- awk_exit(L_d);
++ debug_printf_eval("EXIT\n");
++ if (op1)
++ G.exitcode = (int)L_d;
++ awk_exit();
+
+ /* -- recursive node type -- */
+
+@@ -2749,15 +3089,18 @@ static var *evaluate(node *op, var *res)
+ break;
+
+ case XC( OC_IN ):
++ debug_printf_eval("IN\n");
+ setvar_i(res, hash_search(iamarray(R.v), L.s) ? 1 : 0);
+ break;
+
+ case XC( OC_REGEXP ):
++ debug_printf_eval("REGEXP\n");
+ op1 = op;
+ L.s = getvar_s(intvar[F0]);
+ goto re_cont;
+
+ case XC( OC_MATCH ):
++ debug_printf_eval("MATCH\n");
+ op1 = op->r.n;
+ re_cont:
+ {
+@@ -2772,61 +3115,80 @@ static var *evaluate(node *op, var *res)
+ case XC( OC_MOVE ):
+ debug_printf_eval("MOVE\n");
+ /* if source is a temporary string, jusk relink it to dest */
+-//Disabled: if R.v is numeric but happens to have cached R.v->string,
+-//then L.v ends up being a string, which is wrong
+-// if (R.v == v1+1 && R.v->string) {
+-// res = setvar_p(L.v, R.v->string);
+-// R.v->string = NULL;
+-// } else {
++ if (R.v == TMPVAR1
++ && !(R.v->type & VF_NUMBER)
++ /* Why check !NUMBER? if R.v is a number but has cached R.v->string,
++ * L.v ends up a string, which is wrong */
++ /*&& R.v->string - always not NULL (right?) */
++ ) {
++ res = setvar_p(L.v, R.v->string); /* avoids strdup */
++ R.v->string = NULL;
++ } else {
+ res = copyvar(L.v, R.v);
+-// }
++ }
+ break;
+
+ case XC( OC_TERNARY ):
+- if ((op->r.n->info & OPCLSMASK) != OC_COLON)
++ debug_printf_eval("TERNARY\n");
++ if (op->r.n->info != TI_COLON)
+ syntax_error(EMSG_POSSIBLE_ERROR);
+ res = evaluate(istrue(L.v) ? op->r.n->l.n : op->r.n->r.n, res);
+ break;
+
+ case XC( OC_FUNC ): {
+- var *vbeg, *v;
++ var *argvars, *sv_fnargs;
+ const char *sv_progname;
++ int nargs, i;
+
+- /* The body might be empty, still has to eval the args */
+- if (!op->r.n->info && !op->r.f->body.first)
++ debug_printf_eval("FUNC\n");
++
++ if (!op->r.f->defined)
+ syntax_error(EMSG_UNDEF_FUNC);
+
+- vbeg = v = nvalloc(op->r.f->nargs + 1);
++ /* The body might be empty, still has to eval the args */
++ nargs = op->r.f->nargs;
++ argvars = nvalloc(nargs);
++ i = 0;
+ while (op1) {
+- var *arg = evaluate(nextarg(&op1), v1);
+- copyvar(v, arg);
+- v->type |= VF_CHILD;
+- v->x.parent = arg;
+- if (++v - vbeg >= op->r.f->nargs)
+- break;
++ var *arg = evaluate(nextarg(&op1), TMPVAR0);
++ if (i == nargs) {
++ /* call with more arguments than function takes.
++ * (gawk warns: "warning: function 'f' called with more arguments than declared").
++ * They are still evaluated, but discarded: */
++ clrvar(arg);
++ continue;
++ }
++ copyvar(&argvars[i], arg);
++ argvars[i].type |= VF_CHILD;
++ argvars[i].x.parent = arg;
++ i++;
+ }
+
+- v = fnargs;
+- fnargs = vbeg;
++ sv_fnargs = fnargs;
+ sv_progname = g_progname;
+
++ fnargs = argvars;
+ res = evaluate(op->r.f->body.first, res);
++ nvfree(argvars, nargs);
+
+ g_progname = sv_progname;
+- nvfree(fnargs);
+- fnargs = v;
++ fnargs = sv_fnargs;
+
+ break;
+ }
+
+ case XC( OC_GETLINE ):
+- case XC( OC_PGETLINE ): {
++ debug_printf_eval("GETLINE /\n");
++ case XC( OC_PGETLINE ):
++ debug_printf_eval("PGETLINE\n");
++ {
+ rstream *rsm;
+ int i;
+
+ if (op1) {
+ rsm = newfile(L.s);
+ if (!rsm->F) {
++ /* NB: can't use "opinfo == TI_PGETLINE", would break "cmd" | getline */
+ if ((opinfo & OPCLSMASK) == OC_PGETLINE) {
+ rsm->F = popen(L.s, "r");
+ rsm->is_pipe = TRUE;
+@@ -2861,16 +3223,34 @@ static var *evaluate(node *op, var *res)
+ /* simple builtins */
+ case XC( OC_FBLTIN ): {
+ double R_d = R_d; /* for compiler */
++ debug_printf_eval("FBLTIN\n");
++
++ if (op1 && op1->info == TI_COMMA)
++ /* Simple builtins take one arg maximum */
++ syntax_error("Too many arguments");
+
+ switch (opn) {
+ case F_in:
+ R_d = (long long)L_d;
+ break;
+
+- case F_rn:
+- R_d = (double)rand() / (double)RAND_MAX;
++ case F_rn: /*rand*/
++ if (op1)
++ syntax_error("Too many arguments");
++ {
++#if RAND_MAX >= 0x7fffffff
++ uint32_t u = ((uint32_t)rand() << 16) ^ rand();
++ uint64_t v = ((uint64_t)rand() << 32) | u;
++ /* the above shift+or is optimized out on 32-bit arches */
++# if RAND_MAX > 0x7fffffff
++ v &= 0x7fffffffffffffffULL;
++# endif
++ R_d = (double)v / 0x8000000000000000ULL;
++#else
++# error Not implemented for this value of RAND_MAX
++#endif
+ break;
+-
++ }
+ case F_co:
+ if (ENABLE_FEATURE_AWK_LIBM) {
+ R_d = cos(L_d);
+@@ -2910,7 +3290,9 @@ static var *evaluate(node *op, var *res)
+ srand(seed);
+ break;
+
+- case F_ti:
++ case F_ti: /*systime*/
++ if (op1)
++ syntax_error("Too many arguments");
+ R_d = time(NULL);
+ break;
+
+@@ -2949,7 +3331,7 @@ static var *evaluate(node *op, var *res)
+ rstream *rsm;
+ int err = 0;
+ rsm = (rstream *)hash_search(fdhash, L.s);
+- debug_printf_eval("OC_FBLTIN F_cl rsm:%p\n", rsm);
++ debug_printf_eval("OC_FBLTIN close: op1:%p s:'%s' rsm:%p\n", op1, L.s, rsm);
+ if (rsm) {
+ debug_printf_eval("OC_FBLTIN F_cl "
+ "rsm->is_pipe:%d, ->F:%p\n",
+@@ -2960,6 +3342,11 @@ static var *evaluate(node *op, var *res)
+ */
+ if (rsm->F)
+ err = rsm->is_pipe ? pclose(rsm->F) : fclose(rsm->F);
++//TODO: fix this case:
++// $ awk 'BEGIN { print close(""); print ERRNO }'
++// -1
++// close of redirection that was never opened
++// (we print 0, 0)
+ free(rsm->buffer);
+ hash_remove(fdhash, L.s);
+ }
+@@ -2974,14 +3361,18 @@ static var *evaluate(node *op, var *res)
+ }
+
+ case XC( OC_BUILTIN ):
++ debug_printf_eval("BUILTIN\n");
+ res = exec_builtin(op, res);
+ break;
+
+ case XC( OC_SPRINTF ):
+- setvar_p(res, awk_printf(op1));
++ debug_printf_eval("SPRINTF\n");
++ setvar_p(res, awk_printf(op1, NULL));
+ break;
+
+- case XC( OC_UNARY ): {
++ case XC( OC_UNARY ):
++ debug_printf_eval("UNARY\n");
++ {
+ double Ld, R_d;
+
+ Ld = R_d = getvar_i(R.v);
+@@ -3011,7 +3402,9 @@ static var *evaluate(node *op, var *res)
+ break;
+ }
+
+- case XC( OC_FIELD ): {
++ case XC( OC_FIELD ):
++ debug_printf_eval("FIELD\n");
++ {
+ int i = (int)getvar_i(R.v);
+ if (i < 0)
+ syntax_error(EMSG_NEGATIVE_FIELD);
+@@ -3028,26 +3421,33 @@ static var *evaluate(node *op, var *res)
+
+ /* concatenation (" ") and index joining (",") */
+ case XC( OC_CONCAT ):
++ debug_printf_eval("CONCAT /\n");
+ case XC( OC_COMMA ): {
+ const char *sep = "";
+- if ((opinfo & OPCLSMASK) == OC_COMMA)
++ debug_printf_eval("COMMA\n");
++ if (opinfo == TI_COMMA)
+ sep = getvar_s(intvar[SUBSEP]);
+ setvar_p(res, xasprintf("%s%s%s", L.s, sep, R.s));
+ break;
+ }
+
+ case XC( OC_LAND ):
++ debug_printf_eval("LAND\n");
+ setvar_i(res, istrue(L.v) ? ptest(op->r.n) : 0);
+ break;
+
+ case XC( OC_LOR ):
++ debug_printf_eval("LOR\n");
+ setvar_i(res, istrue(L.v) ? 1 : ptest(op->r.n));
+ break;
+
+ case XC( OC_BINARY ):
+- case XC( OC_REPLACE ): {
++ debug_printf_eval("BINARY /\n");
++ case XC( OC_REPLACE ):
++ debug_printf_eval("REPLACE\n");
++ {
+ double R_d = getvar_i(R.v);
+- debug_printf_eval("BINARY/REPLACE: R_d:%f opn:%c\n", R_d, opn);
++ debug_printf_eval("R_d:%f opn:%c\n", R_d, opn);
+ switch (opn) {
+ case '+':
+ L_d += R_d;
+@@ -3083,6 +3483,7 @@ static var *evaluate(node *op, var *res)
+ case XC( OC_COMPARE ): {
+ int i = i; /* for compiler */
+ double Ld;
++ debug_printf_eval("COMPARE\n");
+
+ if (is_numeric(L.v) && is_numeric(R.v)) {
+ Ld = getvar_i(L.v) - getvar_i(R.v);
+@@ -3109,7 +3510,7 @@ static var *evaluate(node *op, var *res)
+ default:
+ syntax_error(EMSG_POSSIBLE_ERROR);
+ } /* switch */
+- next:
++
+ if ((opinfo & OPCLSMASK) <= SHIFT_TIL_THIS)
+ op = op->a.n;
+ if ((opinfo & OPCLSMASK) >= RECUR_FROM_THIS)
+@@ -3118,7 +3519,10 @@ static var *evaluate(node *op, var *res)
+ break;
+ } /* while (op) */
+
+- nvfree(v1);
++ nvfree(tmpvars, 2);
++#undef TMPVAR0
++#undef TMPVAR1
++
+ debug_printf_eval("returning from %s(): %p\n", __func__, res);
+ return res;
+ #undef fnargs
+@@ -3126,25 +3530,21 @@ static var *evaluate(node *op, var *res)
+ #undef sreg
+ }
+
+-
+ /* -------- main & co. -------- */
+
+-static int awk_exit(int r)
++static int awk_exit(void)
+ {
+- var tv;
+ unsigned i;
+- hash_item *hi;
+-
+- zero_out_var(&tv);
+
+ if (!exiting) {
+ exiting = TRUE;
+ nextrec = FALSE;
+- evaluate(endseq.first, &tv);
++ evaluate(endseq.first, &G.exit__tmpvar);
+ }
+
+ /* waiting for children */
+ for (i = 0; i < fdhash->csize; i++) {
++ hash_item *hi;
+ hi = fdhash->items[i];
+ while (hi) {
+ if (hi->data.rs.F && hi->data.rs.is_pipe)
+@@ -3153,65 +3553,7 @@ static int awk_exit(int r)
+ }
+ }
+
+- exit(r);
+-}
+-
+-/* if expr looks like "var=value", perform assignment and return 1,
+- * otherwise return 0 */
+-static int is_assignment(const char *expr)
+-{
+- char *exprc, *val;
+-
+- if (!isalnum_(*expr) || (val = strchr(expr, '=')) == NULL) {
+- return FALSE;
+- }
+-
+- exprc = xstrdup(expr);
+- val = exprc + (val - expr);
+- *val++ = '\0';
+-
+- unescape_string_in_place(val);
+- setvar_u(newvar(exprc), val);
+- free(exprc);
+- return TRUE;
+-}
+-
+-/* switch to next input file */
+-static rstream *next_input_file(void)
+-{
+-#define rsm (G.next_input_file__rsm)
+-#define files_happen (G.next_input_file__files_happen)
+-
+- FILE *F;
+- const char *fname, *ind;
+-
+- if (rsm.F)
+- fclose(rsm.F);
+- rsm.F = NULL;
+- rsm.pos = rsm.adv = 0;
+-
+- for (;;) {
+- if (getvar_i(intvar[ARGIND])+1 >= getvar_i(intvar[ARGC])) {
+- if (files_happen)
+- return NULL;
+- fname = "-";
+- F = stdin;
+- break;
+- }
+- ind = getvar_s(incvar(intvar[ARGIND]));
+- fname = getvar_s(findvar(iamarray(intvar[ARGV]), ind));
+- if (fname && *fname && !is_assignment(fname)) {
+- F = xfopen_stdin(fname);
+- break;
+- }
+- }
+-
+- files_happen = TRUE;
+- setvar_s(intvar[FILENAME], fname);
+- rsm.F = F;
+- return &rsm;
+-#undef rsm
+-#undef files_happen
++ exit(G.exitcode);
+ }
+
+ int awk_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
+@@ -3224,12 +3566,7 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ #if ENABLE_FEATURE_AWK_GNU_EXTENSIONS
+ llist_t *list_e = NULL;
+ #endif
+- int i, j;
+- var *v;
+- var tv;
+- char **envp;
+- char *vnames = (char *)vNames; /* cheat */
+- char *vvalues = (char *)vValues;
++ int i;
+
+ INIT_G();
+
+@@ -3238,48 +3575,43 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ if (ENABLE_LOCALE_SUPPORT)
+ setlocale(LC_NUMERIC, "C");
+
+- zero_out_var(&tv);
+-
+- /* allocate global buffer */
+- g_buf = xmalloc(MAXVARFMT + 1);
+-
+- vhash = hash_init();
+- ahash = hash_init();
+- fdhash = hash_init();
+- fnhash = hash_init();
+-
+ /* initialize variables */
+- for (i = 0; *vnames; i++) {
+- intvar[i] = v = newvar(nextword(&vnames));
+- if (*vvalues != '\377')
+- setvar_s(v, nextword(&vvalues));
+- else
+- setvar_i(v, 0);
+-
+- if (*vnames == '*') {
+- v->type |= VF_SPECIAL;
+- vnames++;
++ vhash = hash_init();
++ {
++ char *vnames = (char *)vNames; /* cheat */
++ char *vvalues = (char *)vValues;
++ for (i = 0; *vnames; i++) {
++ var *v;
++ intvar[i] = v = newvar(nextword(&vnames));
++ if (*vvalues != '\377')
++ setvar_s(v, nextword(&vvalues));
++ else
++ setvar_i(v, 0);
++
++ if (*vnames == '*') {
++ v->type |= VF_SPECIAL;
++ vnames++;
++ }
+ }
+ }
+
+ handle_special(intvar[FS]);
+ handle_special(intvar[RS]);
+
+- newfile("/dev/stdin")->F = stdin;
+- newfile("/dev/stdout")->F = stdout;
+- newfile("/dev/stderr")->F = stderr;
+-
+ /* Huh, people report that sometimes environ is NULL. Oh well. */
+- if (environ) for (envp = environ; *envp; envp++) {
+- /* environ is writable, thus we don't strdup it needlessly */
+- char *s = *envp;
+- char *s1 = strchr(s, '=');
+- if (s1) {
+- *s1 = '\0';
+- /* Both findvar and setvar_u take const char*
+- * as 2nd arg -> environment is not trashed */
+- setvar_u(findvar(iamarray(intvar[ENVIRON]), s), s1 + 1);
+- *s1 = '=';
++ if (environ) {
++ char **envp;
++ for (envp = environ; *envp; envp++) {
++ /* environ is writable, thus we don't strdup it needlessly */
++ char *s = *envp;
++ char *s1 = strchr(s, '=');
++ if (s1) {
++ *s1 = '\0';
++ /* Both findvar and setvar_u take const char*
++ * as 2nd arg -> environment is not trashed */
++ setvar_u(findvar(iamarray(intvar[ENVIRON]), s), s1 + 1);
++ *s1 = '=';
++ }
+ }
+ }
+ opt = getopt32(argv, OPTSTR_AWK, &opt_F, &list_v, &list_f, IF_FEATURE_AWK_GNU_EXTENSIONS(&list_e,) NULL);
+@@ -3295,20 +3627,19 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ if (!is_assignment(llist_pop(&list_v)))
+ bb_show_usage();
+ }
++
++ /* Parse all supplied programs */
++ fnhash = hash_init();
++ ahash = hash_init();
+ while (list_f) {
+- char *s = NULL;
+- FILE *from_file;
++ int fd;
++ char *s;
+
+ g_progname = llist_pop(&list_f);
+- from_file = xfopen_stdin(g_progname);
+- /* one byte is reserved for some trick in next_token */
+- for (i = j = 1; j > 0; i += j) {
+- s = xrealloc(s, i + 4096);
+- j = fread(s + i, 1, 4094, from_file);
+- }
+- s[i] = '\0';
+- fclose(from_file);
+- parse_program(s + 1);
++ fd = xopen_stdin(g_progname);
++ s = xmalloc_read(fd, NULL); /* it's NUL-terminated */
++ close(fd);
++ parse_program(s);
+ free(s);
+ }
+ g_progname = "cmd. line";
+@@ -3317,11 +3648,23 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ parse_program(llist_pop(&list_e));
+ }
+ #endif
++//FIXME: preserve order of -e and -f
++//TODO: implement -i LIBRARY and -E FILE too, they are easy-ish
+ if (!(opt & (OPT_f | OPT_e))) {
+ if (!*argv)
+ bb_show_usage();
+ parse_program(*argv++);
+ }
++ /* Free unused parse structures */
++ //hash_free(fnhash); // ~250 bytes when empty, used only for function names
++ //^^^^^^^^^^^^^^^^^ does not work, hash_clear() inside SEGVs
++ // (IOW: hash_clear() assumes it's a hash of variables. fnhash is not).
++ free(fnhash->items);
++ free(fnhash);
++ fnhash = NULL; // debug
++ //hash_free(ahash); // empty after parsing, will reuse as fdhash instead of freeing
++
++ /* Parsing done, on to executing */
+
+ /* fill in ARGV array */
+ setari_u(intvar[ARGV], 0, "awk");
+@@ -3330,9 +3673,14 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ setari_u(intvar[ARGV], ++i, *argv++);
+ setvar_i(intvar[ARGC], i + 1);
+
+- evaluate(beginseq.first, &tv);
++ //fdhash = ahash; // done via define
++ newfile("/dev/stdin")->F = stdin;
++ newfile("/dev/stdout")->F = stdout;
++ newfile("/dev/stderr")->F = stderr;
++
++ evaluate(beginseq.first, &G.main__tmpvar);
+ if (!mainseq.first && !endseq.first)
+- awk_exit(EXIT_SUCCESS);
++ awk_exit();
+
+ /* input file could already be opened in BEGIN block */
+ if (!iF)
+@@ -3347,7 +3695,7 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ nextrec = FALSE;
+ incvar(intvar[NR]);
+ incvar(intvar[FNR]);
+- evaluate(mainseq.first, &tv);
++ evaluate(mainseq.first, &G.main__tmpvar);
+
+ if (nextfile)
+ break;
+@@ -3359,6 +3707,6 @@ int awk_main(int argc UNUSED_PARAM, char **argv)
+ iF = next_input_file();
+ }
+
+- awk_exit(EXIT_SUCCESS);
++ awk_exit();
+ /*return 0;*/
+ }
+diff --git a/testsuite/awk.tests b/testsuite/awk.tests
+index 92c83d719..4a7a01245 100755
+--- a/testsuite/awk.tests
++++ b/testsuite/awk.tests
+@@ -44,6 +44,16 @@ testing "awk handles empty function f(arg){}" \
+ "L1\n\nL2\n\n" \
+ "" ""
+
++prg='
++function empty_fun(){}
++END {empty_fun()
++ print "Ok"
++}'
++testing "awk handles empty function f(){}" \
++ "awk '$prg'" \
++ "Ok\n" \
++ "" ""
++
+ prg='
+ function outer_fun() {
+ return 1
+@@ -71,6 +81,23 @@ testing "awk properly handles undefined function" \
+ "L1\n\nawk: cmd. line:5: Call to undefined function\n" \
+ "" ""
+
++prg='
++BEGIN {
++ v=1
++ a=2
++ print v (a)
++}'
++testing "awk 'v (a)' is not a function call, it is a concatenation" \
++ "awk '$prg' 2>&1" \
++ "12\n" \
++ "" ""
++
++prg='func f(){print"F"};func g(){print"G"};BEGIN{f(g(),g())}'
++testing "awk unused function args are evaluated" \
++ "awk '$prg' 2>&1" \
++ "G\nG\nF\n" \
++ "" ""
++
+
+ optional DESKTOP
+ testing "awk hex const 1" "awk '{ print or(0xffffffff,1) }'" "4294967295\n" "" "\n"
+@@ -352,19 +379,14 @@ testing "awk -e and ARGC" \
+ ""
+ SKIP=
+
+-# The examples are in fact not valid awk programs (break/continue
+-# can only be used inside loops).
+-# But we do accept them outside of loops.
+-# We had a bug with misparsing "break ; else" sequence.
+-# Test that *that* bug is fixed, using simplest possible scripts:
+ testing "awk break" \
+ "awk -f - 2>&1; echo \$?" \
+- "0\n" \
++ "awk: -:1: 'break' not in a loop\n1\n" \
+ "" \
+ 'BEGIN { if (1) break; else a = 1 }'
+ testing "awk continue" \
+ "awk -f - 2>&1; echo \$?" \
+- "0\n" \
++ "awk: -:1: 'continue' not in a loop\n1\n" \
+ "" \
+ 'BEGIN { if (1) continue; else a = 1 }'
+
+@@ -383,6 +405,11 @@ testing "awk errors on missing delete arg" \
+ "awk -e '{delete}' 2>&1" "awk: cmd. line:1: Too few arguments\n" "" ""
+ SKIP=
+
++optional FEATURE_AWK_GNU_EXTENSIONS
++testing "awk printf('%c') can output NUL" \
++ "awk '{printf(\"hello%c null\n\", 0)}'" "hello\0 null\n" "" "\n"
++SKIP=
++
+ # testing "description" "command" "result" "infile" "stdin"
+ testing 'awk negative field access' \
+ 'awk 2>&1 -- '\''{ $(-1) }'\' \
+@@ -413,4 +440,25 @@ testing 'awk $NF is empty' \
+ '' \
+ 'a=====123='
+
++testing "awk exit N propagates through END's exit" \
++ "awk 'BEGIN { exit 42 } END { exit }'; echo \$?" \
++ "42\n" \
++ '' ''
++
++testing "awk print + redirect" \
++ "awk 'BEGIN { print \"STDERR %s\" >\"/dev/stderr\" }' 2>&1" \
++ "STDERR %s\n" \
++ '' ''
++
++testing "awk \"cmd\" | getline" \
++ "awk 'BEGIN { \"echo HELLO\" | getline; print }'" \
++ "HELLO\n" \
++ '' ''
++
++# printf %% should print one % (had a bug where it didn't)
++testing 'awk printf %% prints one %' \
++ "awk 'BEGIN { printf \"%%\n\" }'" \
++ "%\n" \
++ '' ''
++
+ exit $FAILCOUNT
+diff --git a/testsuite/printf.tests b/testsuite/printf.tests
+index 34a65926e..050edef71 100755
+--- a/testsuite/printf.tests
++++ b/testsuite/printf.tests
+@@ -79,6 +79,11 @@ testing "printf understands %Ld" \
+ "-5\n""0\n" \
+ "" ""
+
++testing "printf understands %%" \
++ "${bb}printf '%%\n' 2>&1; echo \$?" \
++ "%\n""0\n" \
++ "" ""
++
+ testing "printf handles positive numbers for %d" \
+ "${bb}printf '%d\n' 3 +3 ' 3' ' +3' 2>&1; echo \$?" \
+ "3\n"\
+--
+2.33.0
+
diff --git a/meta/recipes-core/busybox/busybox/0002-man-fix-segfault-in-man-1.patch b/meta/recipes-core/busybox/busybox/0002-man-fix-segfault-in-man-1.patch
new file mode 100644
index 0000000000..4a930b7b6f
--- /dev/null
+++ b/meta/recipes-core/busybox/busybox/0002-man-fix-segfault-in-man-1.patch
@@ -0,0 +1,30 @@
+From 4975cace9bf96bfde174f8bb5cc4068d2ea294d4 Mon Sep 17 00:00:00 2001
+From: Denys Vlasenko <vda.linux@googlemail.com>
+Date: Tue, 15 Jun 2021 14:47:46 +0200
+Subject: [PATCH] man: fix segfault in "man 1"
+
+function old new delta
+man_main 942 954 +12
+
+Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
+
+Upstream-Status: Backport [4d4fc5ca5ee4f]
+CVE: CVE-2021-42373
+Signed-off-by: Chen Qi <Qi.Chen@windriver.com>
+---
+ miscutils/man.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/miscutils/man.c b/miscutils/man.c
+index 722f6641e..d319e8bba 100644
+--- a/miscutils/man.c
++++ b/miscutils/man.c
+@@ -324,7 +324,7 @@ int man_main(int argc UNUSED_PARAM, char **argv)
+
+ /* is 1st ARG a SECTION? */
+ sec_list = conf_sec_list;
+- if (is_section_name(conf_sec_list, *argv)) {
++ if (is_section_name(conf_sec_list, *argv) && argv[1]) {
+ /* yes */
+ sec_list = *argv++;
+ }
diff --git a/meta/recipes-core/busybox/busybox_1.33.1.bb b/meta/recipes-core/busybox/busybox_1.33.2.bb
index 4002d6a5c6..4a0d3b4556 100644
--- a/meta/recipes-core/busybox/busybox_1.33.1.bb
+++ b/meta/recipes-core/busybox/busybox_1.33.2.bb
@@ -48,7 +48,9 @@ SRC_URI = "https://busybox.net/downloads/busybox-${PV}.tar.bz2;name=tarball \
file://0001-sysctl-ignore-EIO-of-stable_secret-below-proc-sys-ne.patch \
file://0001-gen_build_files-Use-C-locale-when-calling-sed-on-glo.patch \
file://0001-mktemp-add-tmpdir-option.patch \
+ file://0001-awk-fix-CVEs.patch \
+ file://0002-man-fix-segfault-in-man-1.patch \
"
SRC_URI_append_libc-musl = " file://musl.cfg "
-SRC_URI[tarball.sha256sum] = "12cec6bd2b16d8a9446dd16130f2b92982f1819f6e1c5f5887b6db03f5660d28"
+SRC_URI[tarball.sha256sum] = "6843ba7977081e735fa0fdb05893e3c002c8c5ad7c9c80da206e603cc0ac47e7"
diff --git a/meta/recipes-core/expat/expat/CVE-2021-45960.patch b/meta/recipes-core/expat/expat/CVE-2021-45960.patch
new file mode 100644
index 0000000000..523449e22c
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2021-45960.patch
@@ -0,0 +1,65 @@
+From 0adcb34c49bee5b19bd29b16a578c510c23597ea Mon Sep 17 00:00:00 2001
+From: Sebastian Pipping <sebastian@pipping.org>
+Date: Mon, 27 Dec 2021 20:15:02 +0100
+Subject: [PATCH] lib: Detect and prevent troublesome left shifts in function
+ storeAtts (CVE-2021-45960)
+
+Upstream-Status: Backport:
+https://github.com/libexpat/libexpat/pull/534/commits/0adcb34c49bee5b19bd29b16a578c510c23597ea
+
+CVE: CVE-2021-45960
+Signed-off-by: Steve Sakoman <steve@sakoman.com>
+
+---
+ expat/lib/xmlparse.c | 31 +++++++++++++++++++++++++++++--
+ 1 file changed, 29 insertions(+), 2 deletions(-)
+
+diff --git a/expat/lib/xmlparse.c b/expat/lib/xmlparse.c
+index d730f41c3..b47c31b05 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -3414,7 +3414,13 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+ if (nPrefixes) {
+ int j; /* hash table index */
+ unsigned long version = parser->m_nsAttsVersion;
+- int nsAttsSize = (int)1 << parser->m_nsAttsPower;
++
++ /* Detect and prevent invalid shift */
++ if (parser->m_nsAttsPower >= sizeof(unsigned int) * 8 /* bits per byte */) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
++ unsigned int nsAttsSize = 1u << parser->m_nsAttsPower;
+ unsigned char oldNsAttsPower = parser->m_nsAttsPower;
+ /* size of hash table must be at least 2 * (# of prefixed attributes) */
+ if ((nPrefixes << 1)
+@@ -3425,7 +3431,28 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+ ;
+ if (parser->m_nsAttsPower < 3)
+ parser->m_nsAttsPower = 3;
+- nsAttsSize = (int)1 << parser->m_nsAttsPower;
++
++ /* Detect and prevent invalid shift */
++ if (parser->m_nsAttsPower >= sizeof(nsAttsSize) * 8 /* bits per byte */) {
++ /* Restore actual size of memory in m_nsAtts */
++ parser->m_nsAttsPower = oldNsAttsPower;
++ return XML_ERROR_NO_MEMORY;
++ }
++
++ nsAttsSize = 1u << parser->m_nsAttsPower;
++
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if (nsAttsSize > (size_t)(-1) / sizeof(NS_ATT)) {
++ /* Restore actual size of memory in m_nsAtts */
++ parser->m_nsAttsPower = oldNsAttsPower;
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts,
+ nsAttsSize * sizeof(NS_ATT));
+ if (! temp) {
diff --git a/meta/recipes-core/expat/expat/CVE-2021-46143.patch b/meta/recipes-core/expat/expat/CVE-2021-46143.patch
new file mode 100644
index 0000000000..b1a726d9a8
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2021-46143.patch
@@ -0,0 +1,49 @@
+From 85ae9a2d7d0e9358f356b33977b842df8ebaec2b Mon Sep 17 00:00:00 2001
+From: Sebastian Pipping <sebastian@pipping.org>
+Date: Sat, 25 Dec 2021 20:52:08 +0100
+Subject: [PATCH] lib: Prevent integer overflow on m_groupSize in function
+ doProlog (CVE-2021-46143)
+
+Upstream-Status: Backport:
+https://github.com/libexpat/libexpat/pull/538/commits/85ae9a2d7d0e9358f356b33977b842df8ebaec2b
+
+CVE: CVE-2021-46143
+
+Signed-off-by: Steve Sakoman <steve@sakoman.com>
+---
+ expat/lib/xmlparse.c | 15 +++++++++++++++
+ 1 file changed, 15 insertions(+)
+
+diff --git a/expat/lib/xmlparse.c b/expat/lib/xmlparse.c
+index b47c31b0..8f243126 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -5046,6 +5046,11 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end,
+ if (parser->m_prologState.level >= parser->m_groupSize) {
+ if (parser->m_groupSize) {
+ {
++ /* Detect and prevent integer overflow */
++ if (parser->m_groupSize > (unsigned int)(-1) / 2u) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
+ char *const new_connector = (char *)REALLOC(
+ parser, parser->m_groupConnector, parser->m_groupSize *= 2);
+ if (new_connector == NULL) {
+@@ -5056,6 +5061,16 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end,
+ }
+
+ if (dtd->scaffIndex) {
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if (parser->m_groupSize > (size_t)(-1) / sizeof(int)) {
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ int *const new_scaff_index = (int *)REALLOC(
+ parser, dtd->scaffIndex, parser->m_groupSize * sizeof(int));
+ if (new_scaff_index == NULL)
diff --git a/meta/recipes-core/expat/expat/CVE-2022-22822-27.patch b/meta/recipes-core/expat/expat/CVE-2022-22822-27.patch
new file mode 100644
index 0000000000..e569fbc7ab
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-22822-27.patch
@@ -0,0 +1,257 @@
+From 9f93e8036e842329863bf20395b8fb8f73834d9e Mon Sep 17 00:00:00 2001
+From: Sebastian Pipping <sebastian@pipping.org>
+Date: Thu, 30 Dec 2021 22:46:03 +0100
+Subject: [PATCH] lib: Prevent integer overflow at multiple places
+ (CVE-2022-22822 to CVE-2022-22827)
+
+The involved functions are:
+- addBinding (CVE-2022-22822)
+- build_model (CVE-2022-22823)
+- defineAttribute (CVE-2022-22824)
+- lookup (CVE-2022-22825)
+- nextScaffoldPart (CVE-2022-22826)
+- storeAtts (CVE-2022-22827)
+
+Upstream-Status: Backport:
+https://github.com/libexpat/libexpat/pull/539/commits/9f93e8036e842329863bf20395b8fb8f73834d9e
+
+CVE: CVE-2022-22822 CVE-2022-22823 CVE-2022-22824 CVE-2022-22825 CVE-2022-22826 CVE-2022-22827
+Signed-off-by: Steve Sakoman <steve@sakoman.com>
+
+---
+ expat/lib/xmlparse.c | 153 ++++++++++++++++++++++++++++++++++++++++++-
+ 1 file changed, 151 insertions(+), 2 deletions(-)
+
+diff --git a/expat/lib/xmlparse.c b/expat/lib/xmlparse.c
+index 8f243126..575e73ee 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -3261,13 +3261,38 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+
+ /* get the attributes from the tokenizer */
+ n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts);
++
++ /* Detect and prevent integer overflow */
++ if (n > INT_MAX - nDefaultAtts) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
+ if (n + nDefaultAtts > parser->m_attsSize) {
+ int oldAttsSize = parser->m_attsSize;
+ ATTRIBUTE *temp;
+ #ifdef XML_ATTR_INFO
+ XML_AttrInfo *temp2;
+ #endif
++
++ /* Detect and prevent integer overflow */
++ if ((nDefaultAtts > INT_MAX - INIT_ATTS_SIZE)
++ || (n > INT_MAX - (nDefaultAtts + INIT_ATTS_SIZE))) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
+ parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
++
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(ATTRIBUTE)) {
++ parser->m_attsSize = oldAttsSize;
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts,
+ parser->m_attsSize * sizeof(ATTRIBUTE));
+ if (temp == NULL) {
+@@ -3276,6 +3301,17 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+ }
+ parser->m_atts = temp;
+ #ifdef XML_ATTR_INFO
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++# if UINT_MAX >= SIZE_MAX
++ if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(XML_AttrInfo)) {
++ parser->m_attsSize = oldAttsSize;
++ return XML_ERROR_NO_MEMORY;
++ }
++# endif
++
+ temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo,
+ parser->m_attsSize * sizeof(XML_AttrInfo));
+ if (temp2 == NULL) {
+@@ -3610,9 +3646,31 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+ tagNamePtr->prefixLen = prefixLen;
+ for (i = 0; localPart[i++];)
+ ; /* i includes null terminator */
++
++ /* Detect and prevent integer overflow */
++ if (binding->uriLen > INT_MAX - prefixLen
++ || i > INT_MAX - (binding->uriLen + prefixLen)) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
+ n = i + binding->uriLen + prefixLen;
+ if (n > binding->uriAlloc) {
+ TAG *p;
++
++ /* Detect and prevent integer overflow */
++ if (n > INT_MAX - EXPAND_SPARE) {
++ return XML_ERROR_NO_MEMORY;
++ }
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if ((unsigned)(n + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char));
+ if (! uri)
+ return XML_ERROR_NO_MEMORY;
+@@ -3708,6 +3766,21 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
+ if (parser->m_freeBindingList) {
+ b = parser->m_freeBindingList;
+ if (len > b->uriAlloc) {
++ /* Detect and prevent integer overflow */
++ if (len > INT_MAX - EXPAND_SPARE) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ XML_Char *temp = (XML_Char *)REALLOC(
+ parser, b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE));
+ if (temp == NULL)
+@@ -3720,6 +3793,21 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
+ b = (BINDING *)MALLOC(parser, sizeof(BINDING));
+ if (! b)
+ return XML_ERROR_NO_MEMORY;
++
++ /* Detect and prevent integer overflow */
++ if (len > INT_MAX - EXPAND_SPARE) {
++ return XML_ERROR_NO_MEMORY;
++ }
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) {
++ return XML_ERROR_NO_MEMORY;
++ }
++#endif
++
+ b->uri
+ = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE));
+ if (! b->uri) {
+@@ -6141,7 +6229,24 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
+ }
+ } else {
+ DEFAULT_ATTRIBUTE *temp;
++
++ /* Detect and prevent integer overflow */
++ if (type->allocDefaultAtts > INT_MAX / 2) {
++ return 0;
++ }
++
+ int count = type->allocDefaultAtts * 2;
++
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if ((unsigned)count > (size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE)) {
++ return 0;
++ }
++#endif
++
+ temp = (DEFAULT_ATTRIBUTE *)REALLOC(parser, type->defaultAtts,
+ (count * sizeof(DEFAULT_ATTRIBUTE)));
+ if (temp == NULL)
+@@ -6792,8 +6897,20 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) {
+ /* check for overflow (table is half full) */
+ if (table->used >> (table->power - 1)) {
+ unsigned char newPower = table->power + 1;
++
++ /* Detect and prevent invalid shift */
++ if (newPower >= sizeof(unsigned long) * 8 /* bits per byte */) {
++ return NULL;
++ }
++
+ size_t newSize = (size_t)1 << newPower;
+ unsigned long newMask = (unsigned long)newSize - 1;
++
++ /* Detect and prevent integer overflow */
++ if (newSize > (size_t)(-1) / sizeof(NAMED *)) {
++ return NULL;
++ }
++
+ size_t tsize = newSize * sizeof(NAMED *);
+ NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize);
+ if (! newV)
+@@ -7143,6 +7260,20 @@ nextScaffoldPart(XML_Parser parser) {
+ if (dtd->scaffCount >= dtd->scaffSize) {
+ CONTENT_SCAFFOLD *temp;
+ if (dtd->scaffold) {
++ /* Detect and prevent integer overflow */
++ if (dtd->scaffSize > UINT_MAX / 2u) {
++ return -1;
++ }
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if (dtd->scaffSize > (size_t)(-1) / 2u / sizeof(CONTENT_SCAFFOLD)) {
++ return -1;
++ }
++#endif
++
+ temp = (CONTENT_SCAFFOLD *)REALLOC(
+ parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
+ if (temp == NULL)
+@@ -7212,8 +7343,26 @@ build_model(XML_Parser parser) {
+ XML_Content *ret;
+ XML_Content *cpos;
+ XML_Char *str;
+- int allocsize = (dtd->scaffCount * sizeof(XML_Content)
+- + (dtd->contentStringLen * sizeof(XML_Char)));
++
++ /* Detect and prevent integer overflow.
++ * The preprocessor guard addresses the "always false" warning
++ * from -Wtype-limits on platforms where
++ * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */
++#if UINT_MAX >= SIZE_MAX
++ if (dtd->scaffCount > (size_t)(-1) / sizeof(XML_Content)) {
++ return NULL;
++ }
++ if (dtd->contentStringLen > (size_t)(-1) / sizeof(XML_Char)) {
++ return NULL;
++ }
++#endif
++ if (dtd->scaffCount * sizeof(XML_Content)
++ > (size_t)(-1) - dtd->contentStringLen * sizeof(XML_Char)) {
++ return NULL;
++ }
++
++ const size_t allocsize = (dtd->scaffCount * sizeof(XML_Content)
++ + (dtd->contentStringLen * sizeof(XML_Char)));
+
+ ret = (XML_Content *)MALLOC(parser, allocsize);
+ if (! ret)
diff --git a/meta/recipes-core/expat/expat/CVE-2022-23852.patch b/meta/recipes-core/expat/expat/CVE-2022-23852.patch
new file mode 100644
index 0000000000..41425c108b
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-23852.patch
@@ -0,0 +1,33 @@
+From 847a645152f5ebc10ac63b74b604d0c1a79fae40 Mon Sep 17 00:00:00 2001
+From: Samanta Navarro <ferivoz@riseup.net>
+Date: Sat, 22 Jan 2022 17:48:00 +0100
+Subject: [PATCH] lib: Detect and prevent integer overflow in XML_GetBuffer
+ (CVE-2022-23852)
+
+Upstream-Status: Backport:
+https://github.com/libexpat/libexpat/commit/847a645152f5ebc10ac63b74b604d0c1a79fae40
+
+CVE: CVE-2022-23852
+
+Signed-off-by: Steve Sakoman <steve@sakoman.com>
+
+---
+ expat/lib/xmlparse.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/expat/lib/xmlparse.c b/expat/lib/xmlparse.c
+index d54af683..5ce31402 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -2067,6 +2067,11 @@ XML_GetBuffer(XML_Parser parser, int len) {
+ keep = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer);
+ if (keep > XML_CONTEXT_BYTES)
+ keep = XML_CONTEXT_BYTES;
++ /* Detect and prevent integer overflow */
++ if (keep > INT_MAX - neededSize) {
++ parser->m_errorCode = XML_ERROR_NO_MEMORY;
++ return NULL;
++ }
+ neededSize += keep;
+ #endif /* defined XML_CONTEXT_BYTES */
+ if (neededSize
diff --git a/meta/recipes-core/expat/expat/CVE-2022-23990.patch b/meta/recipes-core/expat/expat/CVE-2022-23990.patch
new file mode 100644
index 0000000000..c599517b3e
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-23990.patch
@@ -0,0 +1,49 @@
+From ede41d1e186ed2aba88a06e84cac839b770af3a1 Mon Sep 17 00:00:00 2001
+From: Sebastian Pipping <sebastian@pipping.org>
+Date: Wed, 26 Jan 2022 02:36:43 +0100
+Subject: [PATCH] lib: Prevent integer overflow in doProlog (CVE-2022-23990)
+
+The change from "int nameLen" to "size_t nameLen"
+addresses the overflow on "nameLen++" in code
+"for (; name[nameLen++];)" right above the second
+change in the patch.
+
+Upstream-Status: Backport:
+https://github.com/libexpat/libexpat/pull/551/commits/ede41d1e186ed2aba88a06e84cac839b770af3a1
+
+CVE: CVE-2022-23990
+
+Signed-off-by: Steve Sakoman <steve@sakoman.com>
+
+---
+ lib/xmlparse.c | 10 ++++++++--
+ 1 file changed, 8 insertions(+), 2 deletions(-)
+
+diff --git a/lib/xmlparse.c b/expat/lib/xmlparse.c
+index 5ce31402..d1d17005 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -5372,7 +5372,7 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end,
+ if (dtd->in_eldecl) {
+ ELEMENT_TYPE *el;
+ const XML_Char *name;
+- int nameLen;
++ size_t nameLen;
+ const char *nxt
+ = (quant == XML_CQUANT_NONE ? next : next - enc->minBytesPerChar);
+ int myindex = nextScaffoldPart(parser);
+@@ -5388,7 +5388,13 @@ doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end,
+ nameLen = 0;
+ for (; name[nameLen++];)
+ ;
+- dtd->contentStringLen += nameLen;
++
++ /* Detect and prevent integer overflow */
++ if (nameLen > UINT_MAX - dtd->contentStringLen) {
++ return XML_ERROR_NO_MEMORY;
++ }
++
++ dtd->contentStringLen += (unsigned)nameLen;
+ if (parser->m_elementDeclHandler)
+ handleDefault = XML_FALSE;
+ }
diff --git a/meta/recipes-core/expat/expat/CVE-2022-25235.patch b/meta/recipes-core/expat/expat/CVE-2022-25235.patch
new file mode 100644
index 0000000000..9febeae609
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-25235.patch
@@ -0,0 +1,261 @@
+Upstream-Status: Backport [https://github.com/libexpat/libexpat/commit/306b721]
+CVE: CVE-2022-25235
+
+The commit is a merge commit, and this patch is created by:
+
+$ git show -m -p --stat 306b72134f157bbfd1637b20a22cabf4acfa136a
+
+Remove modification for expat/Changes which fails to be applied.
+
+Signed-off-by: Kai Kang <kai.kang@windriver.com>
+
+commit 306b72134f157bbfd1637b20a22cabf4acfa136a (from 2cc97e875ef84da4bcf55156c83599116f7523b4)
+Merge: 2cc97e87 c16300f0
+Author: Sebastian Pipping <sebastian@pipping.org>
+Date: Fri Feb 18 20:12:32 2022 +0100
+
+ Merge pull request #562 from libexpat/utf8-security
+
+ [CVE-2022-25235] lib: Protect against malformed encoding (e.g. malformed UTF-8)
+---
+ expat/Changes | 7 ++++
+ expat/lib/xmltok.c | 5 ---
+ expat/lib/xmltok_impl.c | 18 ++++----
+ expat/tests/runtests.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++++
+ 4 files changed, 127 insertions(+), 12 deletions(-)
+
+diff --git a/lib/xmltok.c b/lib/xmltok.c
+index a72200e8..3bddf125 100644
+--- a/lib/xmltok.c
++++ b/lib/xmltok.c
+@@ -98,11 +98,6 @@
+ + ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \
+ & (1u << (((byte)[2]) & 0x1F)))
+
+-#define UTF8_GET_NAMING(pages, p, n) \
+- ((n) == 2 \
+- ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \
+- : ((n) == 3 ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) : 0))
+-
+ /* Detection of invalid UTF-8 sequences is based on Table 3.1B
+ of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/
+ with the additional restriction of not allowing the Unicode
+diff --git a/lib/xmltok_impl.c b/lib/xmltok_impl.c
+index 0430591b..84ff35f9 100644
+--- a/lib/xmltok_impl.c
++++ b/lib/xmltok_impl.c
+@@ -69,7 +69,7 @@
+ case BT_LEAD##n: \
+ if (end - ptr < n) \
+ return XML_TOK_PARTIAL_CHAR; \
+- if (! IS_NAME_CHAR(enc, ptr, n)) { \
++ if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NAME_CHAR(enc, ptr, n)) { \
+ *nextTokPtr = ptr; \
+ return XML_TOK_INVALID; \
+ } \
+@@ -98,7 +98,7 @@
+ case BT_LEAD##n: \
+ if (end - ptr < n) \
+ return XML_TOK_PARTIAL_CHAR; \
+- if (! IS_NMSTRT_CHAR(enc, ptr, n)) { \
++ if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NMSTRT_CHAR(enc, ptr, n)) { \
+ *nextTokPtr = ptr; \
+ return XML_TOK_INVALID; \
+ } \
+@@ -1142,6 +1142,10 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end,
+ case BT_LEAD##n: \
+ if (end - ptr < n) \
+ return XML_TOK_PARTIAL_CHAR; \
++ if (IS_INVALID_CHAR(enc, ptr, n)) { \
++ *nextTokPtr = ptr; \
++ return XML_TOK_INVALID; \
++ } \
+ if (IS_NMSTRT_CHAR(enc, ptr, n)) { \
+ ptr += n; \
+ tok = XML_TOK_NAME; \
+@@ -1270,7 +1274,7 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end,
+ switch (BYTE_TYPE(enc, ptr)) {
+ # define LEAD_CASE(n) \
+ case BT_LEAD##n: \
+- ptr += n; \
++ ptr += n; /* NOTE: The encoding has already been validated. */ \
+ break;
+ LEAD_CASE(2)
+ LEAD_CASE(3)
+@@ -1339,7 +1343,7 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end,
+ switch (BYTE_TYPE(enc, ptr)) {
+ # define LEAD_CASE(n) \
+ case BT_LEAD##n: \
+- ptr += n; \
++ ptr += n; /* NOTE: The encoding has already been validated. */ \
+ break;
+ LEAD_CASE(2)
+ LEAD_CASE(3)
+@@ -1518,7 +1522,7 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, int attsMax,
+ state = inName; \
+ }
+ # define LEAD_CASE(n) \
+- case BT_LEAD##n: \
++ case BT_LEAD##n: /* NOTE: The encoding has already been validated. */ \
+ START_NAME ptr += (n - MINBPC(enc)); \
+ break;
+ LEAD_CASE(2)
+@@ -1730,7 +1734,7 @@ PREFIX(nameLength)(const ENCODING *enc, const char *ptr) {
+ switch (BYTE_TYPE(enc, ptr)) {
+ # define LEAD_CASE(n) \
+ case BT_LEAD##n: \
+- ptr += n; \
++ ptr += n; /* NOTE: The encoding has already been validated. */ \
+ break;
+ LEAD_CASE(2)
+ LEAD_CASE(3)
+@@ -1775,7 +1779,7 @@ PREFIX(updatePosition)(const ENCODING *enc, const char *ptr, const char *end,
+ switch (BYTE_TYPE(enc, ptr)) {
+ # define LEAD_CASE(n) \
+ case BT_LEAD##n: \
+- ptr += n; \
++ ptr += n; /* NOTE: The encoding has already been validated. */ \
+ pos->columnNumber++; \
+ break;
+ LEAD_CASE(2)
+diff --git a/tests/runtests.c b/tests/runtests.c
+index bc5344b1..9b155b82 100644
+--- a/tests/runtests.c
++++ b/tests/runtests.c
+@@ -5998,6 +5998,105 @@ START_TEST(test_utf8_in_cdata_section_2) {
+ }
+ END_TEST
+
++START_TEST(test_utf8_in_start_tags) {
++ struct test_case {
++ bool goodName;
++ bool goodNameStart;
++ const char *tagName;
++ };
++
++ // The idea with the tests below is this:
++ // We want to cover 1-, 2- and 3-byte sequences, 4-byte sequences
++ // go to isNever and are hence not a concern.
++ //
++ // We start with a character that is a valid name character
++ // (or even name-start character, see XML 1.0r4 spec) and then we flip
++ // single bits at places where (1) the result leaves the UTF-8 encoding space
++ // and (2) we stay in the same n-byte sequence family.
++ //
++ // The flipped bits are highlighted in angle brackets in comments,
++ // e.g. "[<1>011 1001]" means we had [0011 1001] but we now flipped
++ // the most significant bit to 1 to leave UTF-8 encoding space.
++ struct test_case cases[] = {
++ // 1-byte UTF-8: [0xxx xxxx]
++ {true, true, "\x3A"}, // [0011 1010] = ASCII colon ':'
++ {false, false, "\xBA"}, // [<1>011 1010]
++ {true, false, "\x39"}, // [0011 1001] = ASCII nine '9'
++ {false, false, "\xB9"}, // [<1>011 1001]
++
++ // 2-byte UTF-8: [110x xxxx] [10xx xxxx]
++ {true, true, "\xDB\xA5"}, // [1101 1011] [1010 0101] =
++ // Arabic small waw U+06E5
++ {false, false, "\x9B\xA5"}, // [1<0>01 1011] [1010 0101]
++ {false, false, "\xDB\x25"}, // [1101 1011] [<0>010 0101]
++ {false, false, "\xDB\xE5"}, // [1101 1011] [1<1>10 0101]
++ {true, false, "\xCC\x81"}, // [1100 1100] [1000 0001] =
++ // combining char U+0301
++ {false, false, "\x8C\x81"}, // [1<0>00 1100] [1000 0001]
++ {false, false, "\xCC\x01"}, // [1100 1100] [<0>000 0001]
++ {false, false, "\xCC\xC1"}, // [1100 1100] [1<1>00 0001]
++
++ // 3-byte UTF-8: [1110 xxxx] [10xx xxxx] [10xxxxxx]
++ {true, true, "\xE0\xA4\x85"}, // [1110 0000] [1010 0100] [1000 0101] =
++ // Devanagari Letter A U+0905
++ {false, false, "\xA0\xA4\x85"}, // [1<0>10 0000] [1010 0100] [1000 0101]
++ {false, false, "\xE0\x24\x85"}, // [1110 0000] [<0>010 0100] [1000 0101]
++ {false, false, "\xE0\xE4\x85"}, // [1110 0000] [1<1>10 0100] [1000 0101]
++ {false, false, "\xE0\xA4\x05"}, // [1110 0000] [1010 0100] [<0>000 0101]
++ {false, false, "\xE0\xA4\xC5"}, // [1110 0000] [1010 0100] [1<1>00 0101]
++ {true, false, "\xE0\xA4\x81"}, // [1110 0000] [1010 0100] [1000 0001] =
++ // combining char U+0901
++ {false, false, "\xA0\xA4\x81"}, // [1<0>10 0000] [1010 0100] [1000 0001]
++ {false, false, "\xE0\x24\x81"}, // [1110 0000] [<0>010 0100] [1000 0001]
++ {false, false, "\xE0\xE4\x81"}, // [1110 0000] [1<1>10 0100] [1000 0001]
++ {false, false, "\xE0\xA4\x01"}, // [1110 0000] [1010 0100] [<0>000 0001]
++ {false, false, "\xE0\xA4\xC1"}, // [1110 0000] [1010 0100] [1<1>00 0001]
++ };
++ const bool atNameStart[] = {true, false};
++
++ size_t i = 0;
++ char doc[1024];
++ size_t failCount = 0;
++
++ for (; i < sizeof(cases) / sizeof(cases[0]); i++) {
++ size_t j = 0;
++ for (; j < sizeof(atNameStart) / sizeof(atNameStart[0]); j++) {
++ const bool expectedSuccess
++ = atNameStart[j] ? cases[i].goodNameStart : cases[i].goodName;
++ sprintf(doc, "<%s%s><!--", atNameStart[j] ? "" : "a", cases[i].tagName);
++ XML_Parser parser = XML_ParserCreate(NULL);
++
++ const enum XML_Status status
++ = XML_Parse(parser, doc, (int)strlen(doc), /*isFinal=*/XML_FALSE);
++
++ bool success = true;
++ if ((status == XML_STATUS_OK) != expectedSuccess) {
++ success = false;
++ }
++ if ((status == XML_STATUS_ERROR)
++ && (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)) {
++ success = false;
++ }
++
++ if (! success) {
++ fprintf(
++ stderr,
++ "FAIL case %2u (%sat name start, %u-byte sequence, error code %d)\n",
++ (unsigned)i + 1u, atNameStart[j] ? " " : "not ",
++ (unsigned)strlen(cases[i].tagName), XML_GetErrorCode(parser));
++ failCount++;
++ }
++
++ XML_ParserFree(parser);
++ }
++ }
++
++ if (failCount > 0) {
++ fail("UTF-8 regression detected");
++ }
++}
++END_TEST
++
+ /* Test trailing spaces in elements are accepted */
+ static void XMLCALL
+ record_element_end_handler(void *userData, const XML_Char *name) {
+@@ -6175,6 +6274,14 @@ START_TEST(test_bad_doctype) {
+ }
+ END_TEST
+
++START_TEST(test_bad_doctype_utf8) {
++ const char *text = "<!DOCTYPE \xDB\x25"
++ "doc><doc/>"; // [1101 1011] [<0>010 0101]
++ expect_failure(text, XML_ERROR_INVALID_TOKEN,
++ "Invalid UTF-8 in DOCTYPE not faulted");
++}
++END_TEST
++
+ START_TEST(test_bad_doctype_utf16) {
+ const char text[] =
+ /* <!DOCTYPE doc [ \x06f2 ]><doc/>
+@@ -11870,6 +11977,7 @@ make_suite(void) {
+ tcase_add_test(tc_basic, test_ext_entity_utf8_non_bom);
+ tcase_add_test(tc_basic, test_utf8_in_cdata_section);
+ tcase_add_test(tc_basic, test_utf8_in_cdata_section_2);
++ tcase_add_test(tc_basic, test_utf8_in_start_tags);
+ tcase_add_test(tc_basic, test_trailing_spaces_in_elements);
+ tcase_add_test(tc_basic, test_utf16_attribute);
+ tcase_add_test(tc_basic, test_utf16_second_attr);
+@@ -11878,6 +11986,7 @@ make_suite(void) {
+ tcase_add_test(tc_basic, test_bad_attr_desc_keyword);
+ tcase_add_test(tc_basic, test_bad_attr_desc_keyword_utf16);
+ tcase_add_test(tc_basic, test_bad_doctype);
++ tcase_add_test(tc_basic, test_bad_doctype_utf8);
+ tcase_add_test(tc_basic, test_bad_doctype_utf16);
+ tcase_add_test(tc_basic, test_bad_doctype_plus);
+ tcase_add_test(tc_basic, test_bad_doctype_star);
diff --git a/meta/recipes-core/expat/expat/CVE-2022-25236-1.patch b/meta/recipes-core/expat/expat/CVE-2022-25236-1.patch
new file mode 100644
index 0000000000..ab53d99c8f
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-25236-1.patch
@@ -0,0 +1,116 @@
+Upstream-Status: Backport [https://github.com/libexpat/libexpat/commit/2cc97e87]
+CVE: CVE-2022-25236
+
+The commit is a merge commit, and this patch is created by:
+
+$ git diff -p --stat 2cc97e87~ 2cc97e87
+
+Remove modification for expat/Changes which fails to be applied.
+
+Signed-off-by: Kai Kang <kai.kang@windriver.com>
+
+commit 2cc97e875ef84da4bcf55156c83599116f7523b4 (from d477fdd284468f2ab822024e75702f2c1b254f42)
+Merge: d477fdd2 e4d7e497
+Author: Sebastian Pipping <sebastian@pipping.org>
+Date: Fri Feb 18 18:01:27 2022 +0100
+
+ Merge pull request #561 from libexpat/namesep-security
+
+ [CVE-2022-25236] lib: Protect against insertion of namesep characters into namespace URIs
+
+---
+ expat/Changes | 16 ++++++++++++++++
+ expat/lib/xmlparse.c | 17 +++++++++++++----
+ expat/tests/runtests.c | 30 ++++++++++++++++++++++++++++++
+ 3 files changed, 59 insertions(+), 4 deletions(-)
+
+diff --git a/lib/xmlparse.c b/lib/xmlparse.c
+index 7376aab1..c98e2e9f 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -718,8 +718,7 @@ XML_ParserCreate(const XML_Char *encodingName) {
+
+ XML_Parser XMLCALL
+ XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) {
+- XML_Char tmp[2];
+- *tmp = nsSep;
++ XML_Char tmp[2] = {nsSep, 0};
+ return XML_ParserCreate_MM(encodingName, NULL, tmp);
+ }
+
+@@ -1344,8 +1343,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context,
+ would be otherwise.
+ */
+ if (parser->m_ns) {
+- XML_Char tmp[2];
+- *tmp = parser->m_namespaceSeparator;
++ XML_Char tmp[2] = {parser->m_namespaceSeparator, 0};
+ parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);
+ } else {
+ parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd);
+@@ -3761,6 +3759,17 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
+ if (! mustBeXML && isXMLNS
+ && (len > xmlnsLen || uri[len] != xmlnsNamespace[len]))
+ isXMLNS = XML_FALSE;
++
++ // NOTE: While Expat does not validate namespace URIs against RFC 3986,
++ // we have to at least make sure that the XML processor on top of
++ // Expat (that is splitting tag names by namespace separator into
++ // 2- or 3-tuples (uri-local or uri-local-prefix)) cannot be confused
++ // by an attacker putting additional namespace separator characters
++ // into namespace declarations. That would be ambiguous and not to
++ // be expected.
++ if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)) {
++ return XML_ERROR_SYNTAX;
++ }
+ }
+ isXML = isXML && len == xmlLen;
+ isXMLNS = isXMLNS && len == xmlnsLen;
+diff --git a/tests/runtests.c b/tests/runtests.c
+index d07203f2..bc5344b1 100644
+--- a/tests/runtests.c
++++ b/tests/runtests.c
+@@ -7220,6 +7220,35 @@ START_TEST(test_ns_double_colon_doctype) {
+ }
+ END_TEST
+
++START_TEST(test_ns_separator_in_uri) {
++ struct test_case {
++ enum XML_Status expectedStatus;
++ const char *doc;
++ };
++ struct test_case cases[] = {
++ {XML_STATUS_OK, "<doc xmlns='one_two' />"},
++ {XML_STATUS_ERROR, "<doc xmlns='one&#x0A;two' />"},
++ };
++
++ size_t i = 0;
++ size_t failCount = 0;
++ for (; i < sizeof(cases) / sizeof(cases[0]); i++) {
++ XML_Parser parser = XML_ParserCreateNS(NULL, '\n');
++ XML_SetElementHandler(parser, dummy_start_element, dummy_end_element);
++ if (XML_Parse(parser, cases[i].doc, (int)strlen(cases[i].doc),
++ /*isFinal*/ XML_TRUE)
++ != cases[i].expectedStatus) {
++ failCount++;
++ }
++ XML_ParserFree(parser);
++ }
++
++ if (failCount) {
++ fail("Namespace separator handling is broken");
++ }
++}
++END_TEST
++
+ /* Control variable; the number of times duff_allocator() will successfully
+ * allocate */
+ #define ALLOC_ALWAYS_SUCCEED (-1)
+@@ -11905,6 +11934,7 @@ make_suite(void) {
+ tcase_add_test(tc_namespace, test_ns_utf16_doctype);
+ tcase_add_test(tc_namespace, test_ns_invalid_doctype);
+ tcase_add_test(tc_namespace, test_ns_double_colon_doctype);
++ tcase_add_test(tc_namespace, test_ns_separator_in_uri);
+
+ suite_add_tcase(s, tc_misc);
+ tcase_add_checked_fixture(tc_misc, NULL, basic_teardown);
diff --git a/meta/recipes-core/expat/expat/CVE-2022-25236-2.patch b/meta/recipes-core/expat/expat/CVE-2022-25236-2.patch
new file mode 100644
index 0000000000..0f14c9631b
--- /dev/null
+++ b/meta/recipes-core/expat/expat/CVE-2022-25236-2.patch
@@ -0,0 +1,232 @@
+Upstream-Status: Backport [https://github.com/libexpat/libexpat/commit/f178826b]
+CVE: CVE-2022-25236
+
+The commit is a merge commit, and this patch is created by:
+
+$ git show -m -p --stat f178826b
+
+Remove changes for expat/Changes and reference.html which fail to be applied.
+
+Signed-off-by: Kai Kang <kai.kang@windriver.com>
+
+commit f178826bb1e9c8ee23202f1be55ad4ac7b649e84 (from c99e0e7f2b15b48848038992ecbb4480f957cfe9)
+Merge: c99e0e7f 9579f7ea
+Author: Sebastian Pipping <sebastian@pipping.org>
+Date: Fri Mar 4 18:43:39 2022 +0100
+
+ Merge pull request #577 from libexpat/namesep
+
+ lib: Relax fix to CVE-2022-25236 with regard to RFC 3986 URI characters (fixes #572)
+---
+ expat/Changes | 16 ++++++
+ expat/doc/reference.html | 8 +++
+ expat/lib/expat.h | 11 ++++
+ expat/lib/xmlparse.c | 139 ++++++++++++++++++++++++++++++++++++++++++++---
+ expat/tests/runtests.c | 8 ++-
+ 5 files changed, 171 insertions(+), 11 deletions(-)
+
+diff --git a/lib/expat.h b/lib/expat.h
+index 5ab493f7..181fc960 100644
+--- a/lib/expat.h
++++ b/lib/expat.h
+@@ -239,6 +239,17 @@ XML_ParserCreate(const XML_Char *encoding);
+ and the local part will be concatenated without any separator.
+ It is a programming error to use the separator '\0' with namespace
+ triplets (see XML_SetReturnNSTriplet).
++ If a namespace separator is chosen that can be part of a URI or
++ part of an XML name, splitting an expanded name back into its
++ 1, 2 or 3 original parts on application level in the element handler
++ may end up vulnerable, so these are advised against; sane choices for
++ a namespace separator are e.g. '\n' (line feed) and '|' (pipe).
++
++ Note that Expat does not validate namespace URIs (beyond encoding)
++ against RFC 3986 today (and is not required to do so with regard to
++ the XML 1.0 namespaces specification) but it may start doing that
++ in future releases. Before that, an application using Expat must
++ be ready to receive namespace URIs containing non-URI characters.
+ */
+ XMLPARSEAPI(XML_Parser)
+ XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
+diff --git a/lib/xmlparse.c b/lib/xmlparse.c
+index 59da19c8..6fe2cf1e 100644
+--- a/lib/xmlparse.c
++++ b/lib/xmlparse.c
+@@ -3705,6 +3705,117 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr,
+ return XML_ERROR_NONE;
+ }
+
++static XML_Bool
++is_rfc3986_uri_char(XML_Char candidate) {
++ // For the RFC 3986 ANBF grammar see
++ // https://datatracker.ietf.org/doc/html/rfc3986#appendix-A
++
++ switch (candidate) {
++ // From rule "ALPHA" (uppercase half)
++ case 'A':
++ case 'B':
++ case 'C':
++ case 'D':
++ case 'E':
++ case 'F':
++ case 'G':
++ case 'H':
++ case 'I':
++ case 'J':
++ case 'K':
++ case 'L':
++ case 'M':
++ case 'N':
++ case 'O':
++ case 'P':
++ case 'Q':
++ case 'R':
++ case 'S':
++ case 'T':
++ case 'U':
++ case 'V':
++ case 'W':
++ case 'X':
++ case 'Y':
++ case 'Z':
++
++ // From rule "ALPHA" (lowercase half)
++ case 'a':
++ case 'b':
++ case 'c':
++ case 'd':
++ case 'e':
++ case 'f':
++ case 'g':
++ case 'h':
++ case 'i':
++ case 'j':
++ case 'k':
++ case 'l':
++ case 'm':
++ case 'n':
++ case 'o':
++ case 'p':
++ case 'q':
++ case 'r':
++ case 's':
++ case 't':
++ case 'u':
++ case 'v':
++ case 'w':
++ case 'x':
++ case 'y':
++ case 'z':
++
++ // From rule "DIGIT"
++ case '0':
++ case '1':
++ case '2':
++ case '3':
++ case '4':
++ case '5':
++ case '6':
++ case '7':
++ case '8':
++ case '9':
++
++ // From rule "pct-encoded"
++ case '%':
++
++ // From rule "unreserved"
++ case '-':
++ case '.':
++ case '_':
++ case '~':
++
++ // From rule "gen-delims"
++ case ':':
++ case '/':
++ case '?':
++ case '#':
++ case '[':
++ case ']':
++ case '@':
++
++ // From rule "sub-delims"
++ case '!':
++ case '$':
++ case '&':
++ case '\'':
++ case '(':
++ case ')':
++ case '*':
++ case '+':
++ case ',':
++ case ';':
++ case '=':
++ return XML_TRUE;
++
++ default:
++ return XML_FALSE;
++ }
++}
++
+ /* addBinding() overwrites the value of prefix->binding without checking.
+ Therefore one must keep track of the old value outside of addBinding().
+ */
+@@ -3763,14 +3874,26 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
+ && (len > xmlnsLen || uri[len] != xmlnsNamespace[len]))
+ isXMLNS = XML_FALSE;
+
+- // NOTE: While Expat does not validate namespace URIs against RFC 3986,
+- // we have to at least make sure that the XML processor on top of
+- // Expat (that is splitting tag names by namespace separator into
+- // 2- or 3-tuples (uri-local or uri-local-prefix)) cannot be confused
+- // by an attacker putting additional namespace separator characters
+- // into namespace declarations. That would be ambiguous and not to
+- // be expected.
+- if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)) {
++ // NOTE: While Expat does not validate namespace URIs against RFC 3986
++ // today (and is not REQUIRED to do so with regard to the XML 1.0
++ // namespaces specification) we have to at least make sure, that
++ // the application on top of Expat (that is likely splitting expanded
++ // element names ("qualified names") of form
++ // "[uri sep] local [sep prefix] '\0'" back into 1, 2 or 3 pieces
++ // in its element handler code) cannot be confused by an attacker
++ // putting additional namespace separator characters into namespace
++ // declarations. That would be ambiguous and not to be expected.
++ //
++ // While the HTML API docs of function XML_ParserCreateNS have been
++ // advising against use of a namespace separator character that can
++ // appear in a URI for >20 years now, some widespread applications
++ // are using URI characters (':' (colon) in particular) for a
++ // namespace separator, in practice. To keep these applications
++ // functional, we only reject namespaces URIs containing the
++ // application-chosen namespace separator if the chosen separator
++ // is a non-URI character with regard to RFC 3986.
++ if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)
++ && ! is_rfc3986_uri_char(uri[len])) {
+ return XML_ERROR_SYNTAX;
+ }
+ }
+diff --git a/tests/runtests.c b/tests/runtests.c
+index 60da868e..712706c4 100644
+--- a/tests/runtests.c
++++ b/tests/runtests.c
+@@ -7406,16 +7406,18 @@ START_TEST(test_ns_separator_in_uri) {
+ struct test_case {
+ enum XML_Status expectedStatus;
+ const char *doc;
++ XML_Char namesep;
+ };
+ struct test_case cases[] = {
+- {XML_STATUS_OK, "<doc xmlns='one_two' />"},
+- {XML_STATUS_ERROR, "<doc xmlns='one&#x0A;two' />"},
++ {XML_STATUS_OK, "<doc xmlns='one_two' />", XCS('\n')},
++ {XML_STATUS_ERROR, "<doc xmlns='one&#x0A;two' />", XCS('\n')},
++ {XML_STATUS_OK, "<doc xmlns='one:two' />", XCS(':')},
+ };
+
+ size_t i = 0;
+ size_t failCount = 0;
+ for (; i < sizeof(cases) / sizeof(cases[0]); i++) {
+- XML_Parser parser = XML_ParserCreateNS(NULL, '\n');
++ XML_Parser parser = XML_ParserCreateNS(NULL, cases[i].namesep);
+ XML_SetElementHandler(parser, dummy_start_element, dummy_end_element);
+ if (XML_Parse(parser, cases[i].doc, (int)strlen(cases[i].doc),
+ /*isFinal*/ XML_TRUE)
diff --git a/meta/recipes-core/expat/expat_2.2.10.bb b/meta/recipes-core/expat/expat_2.2.10.bb
index 08e8ff1cea..f99fa7edb6 100644
--- a/meta/recipes-core/expat/expat_2.2.10.bb
+++ b/meta/recipes-core/expat/expat_2.2.10.bb
@@ -10,9 +10,17 @@ VERSION_TAG = "${@d.getVar('PV').replace('.', '_')}"
SRC_URI = "https://github.com/libexpat/libexpat/releases/download/R_${VERSION_TAG}/expat-${PV}.tar.bz2 \
file://libtool-tag.patch \
- file://run-ptest \
- file://0001-Add-output-of-tests-result.patch \
- "
+ file://run-ptest \
+ file://0001-Add-output-of-tests-result.patch \
+ file://CVE-2022-22822-27.patch \
+ file://CVE-2021-45960.patch \
+ file://CVE-2021-46143.patch \
+ file://CVE-2022-23852.patch \
+ file://CVE-2022-23990.patch \
+ file://CVE-2022-25235.patch \
+ file://CVE-2022-25236-1.patch \
+ file://CVE-2022-25236-2.patch \
+ "
UPSTREAM_CHECK_URI = "https://github.com/libexpat/libexpat/releases/"
diff --git a/meta/recipes-core/glibc/glibc-version.inc b/meta/recipes-core/glibc/glibc-version.inc
index 4d69187961..e1eefdee49 100644
--- a/meta/recipes-core/glibc/glibc-version.inc
+++ b/meta/recipes-core/glibc/glibc-version.inc
@@ -1,6 +1,6 @@
SRCBRANCH ?= "release/2.33/master"
PV = "2.33"
-SRCREV_glibc ?= "6090cf1330faf2deb17285758f327cb23b89ebf1"
+SRCREV_glibc ?= "3e2a15c666e40e5ee740e5079c56d83469280323"
SRCREV_localedef ?= "bd644c9e6f3e20c5504da1488448173c69c56c28"
GLIBC_GIT_URI ?= "git://sourceware.org/git/glibc.git"
diff --git a/meta/recipes-core/glibc/glibc_2.33.bb b/meta/recipes-core/glibc/glibc_2.33.bb
index ad5e2b8eb1..a1e9eb3a16 100644
--- a/meta/recipes-core/glibc/glibc_2.33.bb
+++ b/meta/recipes-core/glibc/glibc_2.33.bb
@@ -88,7 +88,7 @@ EXTRA_OECONF = "--enable-kernel=${OLDEST_KERNEL} \
EXTRA_OECONF += "${@get_libc_fpu_setting(bb, d)}"
-EXTRA_OECONF_append_x86 = " --enable-cet"
+EXTRA_OECONF_append_x86 = " ${@bb.utils.contains_any('TUNE_FEATURES', 'i586 c3', '--disable-cet', '--enable-cet', d)}"
EXTRA_OECONF_append_x86-64 = " --enable-cet"
PACKAGECONFIG ??= "nscd"
diff --git a/meta/recipes-core/images/build-appliance-image_15.0.0.bb b/meta/recipes-core/images/build-appliance-image_15.0.0.bb
index 455fe825c8..5631cd8ae6 100644
--- a/meta/recipes-core/images/build-appliance-image_15.0.0.bb
+++ b/meta/recipes-core/images/build-appliance-image_15.0.0.bb
@@ -24,7 +24,7 @@ IMAGE_FSTYPES = "wic.vmdk wic.vhd wic.vhdx"
inherit core-image setuptools3
-SRCREV ?= "ec3ac9d883d53ebbf3c6b9a80694df69c9e9ccc7"
+SRCREV ?= "2954fa87a4d325f1a3c722d6fb8bf13b17f9e7a0"
SRC_URI = "git://git.yoctoproject.org/poky;branch=hardknott \
file://Yocto_Build_Appliance.vmx \
file://Yocto_Build_Appliance.vmxf \
diff --git a/meta/recipes-core/initrdscripts/initramfs-framework/finish b/meta/recipes-core/initrdscripts/initramfs-framework/finish
index 717383ebac..f08a920867 100755
--- a/meta/recipes-core/initrdscripts/initramfs-framework/finish
+++ b/meta/recipes-core/initrdscripts/initramfs-framework/finish
@@ -12,6 +12,18 @@ finish_run() {
fatal "ERROR: There's no '/dev' on rootfs."
fi
+ # Unmount anything that was automounted by busybox via mdev-mount.sh.
+ # We're about to switch_root, and leaving anything mounted will prevent
+ # the next rootfs from modifying the block device. Ignore ROOT_DISK,
+ # if it was set by setup-live, because it'll be mounted over loopback
+ # to ROOTFS_DIR.
+ local dev
+ for dev in /run/media/*; do
+ if mountpoint -q "${dev}" && [ "${dev##*/}" != "${ROOT_DISK}" ]; then
+ umount -f "${dev}" || debug "Failed to unmount ${dev}"
+ fi
+ done
+
info "Switching root to '$ROOTFS_DIR'..."
debug "Moving /dev, /proc and /sys onto rootfs..."
diff --git a/meta/recipes-core/libxml/libxml2/CVE-2022-23308-fix-regression.patch b/meta/recipes-core/libxml/libxml2/CVE-2022-23308-fix-regression.patch
new file mode 100644
index 0000000000..eefecb9adb
--- /dev/null
+++ b/meta/recipes-core/libxml/libxml2/CVE-2022-23308-fix-regression.patch
@@ -0,0 +1,99 @@
+From 646fe48d1c8a74310c409ddf81fe7df6700052af Mon Sep 17 00:00:00 2001
+From: Nick Wellnhofer <wellnhofer@aevum.de>
+Date: Tue, 22 Feb 2022 11:51:08 +0100
+Subject: [PATCH] Fix --without-valid build
+
+Regressed in commit 652dd12a.
+---
+ valid.c | 58 ++++++++++++++++++++++++++++-----------------------------
+ 1 file changed, 29 insertions(+), 29 deletions(-)
+---
+
+From https://github.com/GNOME/libxml2.git
+ commit 646fe48d1c8a74310c409ddf81fe7df6700052af
+
+CVE: CVE-2022-23308
+Upstream-status: Backport
+
+Signed-off-by: Joe Slater <joe.slater@windriver.com>
+
+
+diff --git a/valid.c b/valid.c
+index 8e596f1d..9684683a 100644
+--- a/valid.c
++++ b/valid.c
+@@ -479,35 +479,6 @@ nodeVPop(xmlValidCtxtPtr ctxt)
+ return (ret);
+ }
+
+-/**
+- * xmlValidNormalizeString:
+- * @str: a string
+- *
+- * Normalize a string in-place.
+- */
+-static void
+-xmlValidNormalizeString(xmlChar *str) {
+- xmlChar *dst;
+- const xmlChar *src;
+-
+- if (str == NULL)
+- return;
+- src = str;
+- dst = str;
+-
+- while (*src == 0x20) src++;
+- while (*src != 0) {
+- if (*src == 0x20) {
+- while (*src == 0x20) src++;
+- if (*src != 0)
+- *dst++ = 0x20;
+- } else {
+- *dst++ = *src++;
+- }
+- }
+- *dst = 0;
+-}
+-
+ #ifdef DEBUG_VALID_ALGO
+ static void
+ xmlValidPrintNode(xmlNodePtr cur) {
+@@ -2636,6 +2607,35 @@ xmlDumpNotationTable(xmlBufferPtr buf, xmlNotationTablePtr table) {
+ (xmlDictOwns(dict, (const xmlChar *)(str)) == 0))) \
+ xmlFree((char *)(str));
+
++/**
++ * xmlValidNormalizeString:
++ * @str: a string
++ *
++ * Normalize a string in-place.
++ */
++static void
++xmlValidNormalizeString(xmlChar *str) {
++ xmlChar *dst;
++ const xmlChar *src;
++
++ if (str == NULL)
++ return;
++ src = str;
++ dst = str;
++
++ while (*src == 0x20) src++;
++ while (*src != 0) {
++ if (*src == 0x20) {
++ while (*src == 0x20) src++;
++ if (*src != 0)
++ *dst++ = 0x20;
++ } else {
++ *dst++ = *src++;
++ }
++ }
++ *dst = 0;
++}
++
+ static int
+ xmlIsStreaming(xmlValidCtxtPtr ctxt) {
+ xmlParserCtxtPtr pctxt;
+--
+2.35.1
+
diff --git a/meta/recipes-core/libxml/libxml2/CVE-2022-23308.patch b/meta/recipes-core/libxml/libxml2/CVE-2022-23308.patch
new file mode 100644
index 0000000000..708a98b45a
--- /dev/null
+++ b/meta/recipes-core/libxml/libxml2/CVE-2022-23308.patch
@@ -0,0 +1,209 @@
+From 652dd12a858989b14eed4e84e453059cd3ba340e Mon Sep 17 00:00:00 2001
+From: Nick Wellnhofer <wellnhofer@aevum.de>
+Date: Tue, 8 Feb 2022 03:29:24 +0100
+Subject: [PATCH] [CVE-2022-23308] Use-after-free of ID and IDREF attributes
+
+If a document is parsed with XML_PARSE_DTDVALID and without
+XML_PARSE_NOENT, the value of ID attributes has to be normalized after
+potentially expanding entities in xmlRemoveID. Otherwise, later calls
+to xmlGetID can return a pointer to previously freed memory.
+
+ID attributes which are empty or contain only whitespace after
+entity expansion are affected in a similar way. This is fixed by
+not storing such attributes in the ID table.
+
+The test to detect streaming mode when validating against a DTD was
+broken. In connection with the defects above, this could result in a
+use-after-free when using the xmlReader interface with validation.
+Fix detection of streaming mode to avoid similar issues. (This changes
+the expected result of a test case. But as far as I can tell, using the
+XML reader with XIncludes referencing the root document never worked
+properly, anyway.)
+
+All of these issues can result in denial of service. Using xmlReader
+with validation could result in disclosure of memory via the error
+channel, typically stderr. The security impact of xmlGetID returning
+a pointer to freed memory depends on the application. The typical use
+case of calling xmlGetID on an unmodified document is not affected.
+---
+ result/XInclude/ns1.xml.rdr | 2 +-
+ valid.c | 88 +++++++++++++++++++++++--------------
+ 2 files changed, 56 insertions(+), 34 deletions(-)
+ ---
+
+From https://github.com/GNOME/libxml2.git
+ commit 652dd12a858989b14eed4e84e453059cd3ba340e
+
+Remove patch to ns1.xml.rdr which does not exist in version 2.9.10.
+
+CVE: CVE-2022-23308
+Upstream-status: Backport
+
+Signed-off-by: Joe Slater <joe.slater@windriver.com>
+
+
+diff --git a/valid.c b/valid.c
+index 5ee391c0..8e596f1d 100644
+--- a/valid.c
++++ b/valid.c
+@@ -479,6 +479,35 @@ nodeVPop(xmlValidCtxtPtr ctxt)
+ return (ret);
+ }
+
++/**
++ * xmlValidNormalizeString:
++ * @str: a string
++ *
++ * Normalize a string in-place.
++ */
++static void
++xmlValidNormalizeString(xmlChar *str) {
++ xmlChar *dst;
++ const xmlChar *src;
++
++ if (str == NULL)
++ return;
++ src = str;
++ dst = str;
++
++ while (*src == 0x20) src++;
++ while (*src != 0) {
++ if (*src == 0x20) {
++ while (*src == 0x20) src++;
++ if (*src != 0)
++ *dst++ = 0x20;
++ } else {
++ *dst++ = *src++;
++ }
++ }
++ *dst = 0;
++}
++
+ #ifdef DEBUG_VALID_ALGO
+ static void
+ xmlValidPrintNode(xmlNodePtr cur) {
+@@ -2607,6 +2636,24 @@ xmlDumpNotationTable(xmlBufferPtr buf, xmlNotationTablePtr table) {
+ (xmlDictOwns(dict, (const xmlChar *)(str)) == 0))) \
+ xmlFree((char *)(str));
+
++static int
++xmlIsStreaming(xmlValidCtxtPtr ctxt) {
++ xmlParserCtxtPtr pctxt;
++
++ if (ctxt == NULL)
++ return(0);
++ /*
++ * These magic values are also abused to detect whether we're validating
++ * while parsing a document. In this case, userData points to the parser
++ * context.
++ */
++ if ((ctxt->finishDtd != XML_CTXT_FINISH_DTD_0) &&
++ (ctxt->finishDtd != XML_CTXT_FINISH_DTD_1))
++ return(0);
++ pctxt = ctxt->userData;
++ return(pctxt->parseMode == XML_PARSE_READER);
++}
++
+ /**
+ * xmlFreeID:
+ * @not: A id
+@@ -2650,7 +2697,7 @@ xmlAddID(xmlValidCtxtPtr ctxt, xmlDocPtr doc, const xmlChar *value,
+ if (doc == NULL) {
+ return(NULL);
+ }
+- if (value == NULL) {
++ if ((value == NULL) || (value[0] == 0)) {
+ return(NULL);
+ }
+ if (attr == NULL) {
+@@ -2681,7 +2728,7 @@ xmlAddID(xmlValidCtxtPtr ctxt, xmlDocPtr doc, const xmlChar *value,
+ */
+ ret->value = xmlStrdup(value);
+ ret->doc = doc;
+- if ((ctxt != NULL) && (ctxt->vstateNr != 0)) {
++ if (xmlIsStreaming(ctxt)) {
+ /*
+ * Operating in streaming mode, attr is gonna disappear
+ */
+@@ -2820,6 +2867,7 @@ xmlRemoveID(xmlDocPtr doc, xmlAttrPtr attr) {
+ ID = xmlNodeListGetString(doc, attr->children, 1);
+ if (ID == NULL)
+ return(-1);
++ xmlValidNormalizeString(ID);
+
+ id = xmlHashLookup(table, ID);
+ if (id == NULL || id->attr != attr) {
+@@ -3009,7 +3057,7 @@ xmlAddRef(xmlValidCtxtPtr ctxt, xmlDocPtr doc, const xmlChar *value,
+ * fill the structure.
+ */
+ ret->value = xmlStrdup(value);
+- if ((ctxt != NULL) && (ctxt->vstateNr != 0)) {
++ if (xmlIsStreaming(ctxt)) {
+ /*
+ * Operating in streaming mode, attr is gonna disappear
+ */
+@@ -4028,8 +4076,7 @@ xmlValidateAttributeValue2(xmlValidCtxtPtr ctxt, xmlDocPtr doc,
+ xmlChar *
+ xmlValidCtxtNormalizeAttributeValue(xmlValidCtxtPtr ctxt, xmlDocPtr doc,
+ xmlNodePtr elem, const xmlChar *name, const xmlChar *value) {
+- xmlChar *ret, *dst;
+- const xmlChar *src;
++ xmlChar *ret;
+ xmlAttributePtr attrDecl = NULL;
+ int extsubset = 0;
+
+@@ -4070,19 +4117,7 @@ xmlValidCtxtNormalizeAttributeValue(xmlValidCtxtPtr ctxt, xmlDocPtr doc,
+ ret = xmlStrdup(value);
+ if (ret == NULL)
+ return(NULL);
+- src = value;
+- dst = ret;
+- while (*src == 0x20) src++;
+- while (*src != 0) {
+- if (*src == 0x20) {
+- while (*src == 0x20) src++;
+- if (*src != 0)
+- *dst++ = 0x20;
+- } else {
+- *dst++ = *src++;
+- }
+- }
+- *dst = 0;
++ xmlValidNormalizeString(ret);
+ if ((doc->standalone) && (extsubset == 1) && (!xmlStrEqual(value, ret))) {
+ xmlErrValidNode(ctxt, elem, XML_DTD_NOT_STANDALONE,
+ "standalone: %s on %s value had to be normalized based on external subset declaration\n",
+@@ -4114,8 +4149,7 @@ xmlValidCtxtNormalizeAttributeValue(xmlValidCtxtPtr ctxt, xmlDocPtr doc,
+ xmlChar *
+ xmlValidNormalizeAttributeValue(xmlDocPtr doc, xmlNodePtr elem,
+ const xmlChar *name, const xmlChar *value) {
+- xmlChar *ret, *dst;
+- const xmlChar *src;
++ xmlChar *ret;
+ xmlAttributePtr attrDecl = NULL;
+
+ if (doc == NULL) return(NULL);
+@@ -4145,19 +4179,7 @@ xmlValidNormalizeAttributeValue(xmlDocPtr doc, xmlNodePtr elem,
+ ret = xmlStrdup(value);
+ if (ret == NULL)
+ return(NULL);
+- src = value;
+- dst = ret;
+- while (*src == 0x20) src++;
+- while (*src != 0) {
+- if (*src == 0x20) {
+- while (*src == 0x20) src++;
+- if (*src != 0)
+- *dst++ = 0x20;
+- } else {
+- *dst++ = *src++;
+- }
+- }
+- *dst = 0;
++ xmlValidNormalizeString(ret);
+ return(ret);
+ }
+
+--
+2.25.1
+
diff --git a/meta/recipes-core/libxml/libxml2_2.9.10.bb b/meta/recipes-core/libxml/libxml2_2.9.10.bb
index cabf911816..778312f662 100644
--- a/meta/recipes-core/libxml/libxml2_2.9.10.bb
+++ b/meta/recipes-core/libxml/libxml2_2.9.10.bb
@@ -30,6 +30,8 @@ SRC_URI = "http://www.xmlsoft.org/sources/libxml2-${PV}.tar.gz;name=libtar \
file://CVE-2021-3518-0002.patch \
file://CVE-2021-3537.patch \
file://CVE-2021-3541.patch \
+ file://CVE-2022-23308.patch \
+ file://CVE-2022-23308-fix-regression.patch \
"
SRC_URI[libtar.md5sum] = "10942a1dc23137a8aa07f0639cbfece5"
diff --git a/meta/recipes-core/os-release/os-release.bb b/meta/recipes-core/os-release/os-release.bb
index a29d678125..33f75e39b8 100644
--- a/meta/recipes-core/os-release/os-release.bb
+++ b/meta/recipes-core/os-release/os-release.bb
@@ -12,7 +12,9 @@ do_configure[noexec] = "1"
# Other valid fields: BUILD_ID ID_LIKE ANSI_COLOR CPE_NAME
# HOME_URL SUPPORT_URL BUG_REPORT_URL
-OS_RELEASE_FIELDS = "ID ID_LIKE NAME VERSION VERSION_ID PRETTY_NAME"
+OS_RELEASE_FIELDS = "\
+ ID ID_LIKE NAME VERSION VERSION_ID PRETTY_NAME DISTRO_CODENAME \
+"
OS_RELEASE_UNQUOTED_FIELDS = "ID VERSION_ID VARIANT_ID"
ID = "${DISTRO}"
diff --git a/meta/recipes-core/zlib/zlib/CVE-2018-25032.patch b/meta/recipes-core/zlib/zlib/CVE-2018-25032.patch
new file mode 100644
index 0000000000..5cb6183641
--- /dev/null
+++ b/meta/recipes-core/zlib/zlib/CVE-2018-25032.patch
@@ -0,0 +1,347 @@
+CVE: CVE-2018-25032
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@arm.com>
+
+From 5c44459c3b28a9bd3283aaceab7c615f8020c531 Mon Sep 17 00:00:00 2001
+From: Mark Adler <madler@alumni.caltech.edu>
+Date: Tue, 17 Apr 2018 22:09:22 -0700
+Subject: [PATCH] Fix a bug that can crash deflate on some input when using
+ Z_FIXED.
+
+This bug was reported by Danilo Ramos of Eideticom, Inc. It has
+lain in wait 13 years before being found! The bug was introduced
+in zlib 1.2.2.2, with the addition of the Z_FIXED option. That
+option forces the use of fixed Huffman codes. For rare inputs with
+a large number of distant matches, the pending buffer into which
+the compressed data is written can overwrite the distance symbol
+table which it overlays. That results in corrupted output due to
+invalid distances, and can result in out-of-bound accesses,
+crashing the application.
+
+The fix here combines the distance buffer and literal/length
+buffers into a single symbol buffer. Now three bytes of pending
+buffer space are opened up for each literal or length/distance
+pair consumed, instead of the previous two bytes. This assures
+that the pending buffer cannot overwrite the symbol table, since
+the maximum fixed code compressed length/distance is 31 bits, and
+since there are four bytes of pending space for every three bytes
+of symbol space.
+---
+ deflate.c | 74 ++++++++++++++++++++++++++++++++++++++++---------------
+ deflate.h | 25 +++++++++----------
+ trees.c | 50 +++++++++++--------------------------
+ 3 files changed, 79 insertions(+), 70 deletions(-)
+
+diff --git a/deflate.c b/deflate.c
+index 425babc00..19cba873a 100644
+--- a/deflate.c
++++ b/deflate.c
+@@ -255,11 +255,6 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+ int wrap = 1;
+ static const char my_version[] = ZLIB_VERSION;
+
+- ushf *overlay;
+- /* We overlay pending_buf and d_buf+l_buf. This works since the average
+- * output size for (length,distance) codes is <= 24 bits.
+- */
+-
+ if (version == Z_NULL || version[0] != my_version[0] ||
+ stream_size != sizeof(z_stream)) {
+ return Z_VERSION_ERROR;
+@@ -329,9 +324,47 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+
+ s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */
+
+- overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2);
+- s->pending_buf = (uchf *) overlay;
+- s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L);
++ /* We overlay pending_buf and sym_buf. This works since the average size
++ * for length/distance pairs over any compressed block is assured to be 31
++ * bits or less.
++ *
++ * Analysis: The longest fixed codes are a length code of 8 bits plus 5
++ * extra bits, for lengths 131 to 257. The longest fixed distance codes are
++ * 5 bits plus 13 extra bits, for distances 16385 to 32768. The longest
++ * possible fixed-codes length/distance pair is then 31 bits total.
++ *
++ * sym_buf starts one-fourth of the way into pending_buf. So there are
++ * three bytes in sym_buf for every four bytes in pending_buf. Each symbol
++ * in sym_buf is three bytes -- two for the distance and one for the
++ * literal/length. As each symbol is consumed, the pointer to the next
++ * sym_buf value to read moves forward three bytes. From that symbol, up to
++ * 31 bits are written to pending_buf. The closest the written pending_buf
++ * bits gets to the next sym_buf symbol to read is just before the last
++ * code is written. At that time, 31*(n-2) bits have been written, just
++ * after 24*(n-2) bits have been consumed from sym_buf. sym_buf starts at
++ * 8*n bits into pending_buf. (Note that the symbol buffer fills when n-1
++ * symbols are written.) The closest the writing gets to what is unread is
++ * then n+14 bits. Here n is lit_bufsize, which is 16384 by default, and
++ * can range from 128 to 32768.
++ *
++ * Therefore, at a minimum, there are 142 bits of space between what is
++ * written and what is read in the overlain buffers, so the symbols cannot
++ * be overwritten by the compressed data. That space is actually 139 bits,
++ * due to the three-bit fixed-code block header.
++ *
++ * That covers the case where either Z_FIXED is specified, forcing fixed
++ * codes, or when the use of fixed codes is chosen, because that choice
++ * results in a smaller compressed block than dynamic codes. That latter
++ * condition then assures that the above analysis also covers all dynamic
++ * blocks. A dynamic-code block will only be chosen to be emitted if it has
++ * fewer bits than a fixed-code block would for the same set of symbols.
++ * Therefore its average symbol length is assured to be less than 31. So
++ * the compressed data for a dynamic block also cannot overwrite the
++ * symbols from which it is being constructed.
++ */
++
++ s->pending_buf = (uchf *) ZALLOC(strm, s->lit_bufsize, 4);
++ s->pending_buf_size = (ulg)s->lit_bufsize * 4;
+
+ if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL ||
+ s->pending_buf == Z_NULL) {
+@@ -340,8 +373,12 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+ deflateEnd (strm);
+ return Z_MEM_ERROR;
+ }
+- s->d_buf = overlay + s->lit_bufsize/sizeof(ush);
+- s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize;
++ s->sym_buf = s->pending_buf + s->lit_bufsize;
++ s->sym_end = (s->lit_bufsize - 1) * 3;
++ /* We avoid equality with lit_bufsize*3 because of wraparound at 64K
++ * on 16 bit machines and because stored blocks are restricted to
++ * 64K-1 bytes.
++ */
+
+ s->level = level;
+ s->strategy = strategy;
+@@ -552,7 +589,7 @@ int ZEXPORT deflatePrime (strm, bits, value)
+
+ if (deflateStateCheck(strm)) return Z_STREAM_ERROR;
+ s = strm->state;
+- if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3))
++ if (s->sym_buf < s->pending_out + ((Buf_size + 7) >> 3))
+ return Z_BUF_ERROR;
+ do {
+ put = Buf_size - s->bi_valid;
+@@ -1113,7 +1150,6 @@ int ZEXPORT deflateCopy (dest, source)
+ #else
+ deflate_state *ds;
+ deflate_state *ss;
+- ushf *overlay;
+
+
+ if (deflateStateCheck(source) || dest == Z_NULL) {
+@@ -1133,8 +1169,7 @@ int ZEXPORT deflateCopy (dest, source)
+ ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte));
+ ds->prev = (Posf *) ZALLOC(dest, ds->w_size, sizeof(Pos));
+ ds->head = (Posf *) ZALLOC(dest, ds->hash_size, sizeof(Pos));
+- overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2);
+- ds->pending_buf = (uchf *) overlay;
++ ds->pending_buf = (uchf *) ZALLOC(dest, ds->lit_bufsize, 4);
+
+ if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL ||
+ ds->pending_buf == Z_NULL) {
+@@ -1148,8 +1183,7 @@ int ZEXPORT deflateCopy (dest, source)
+ zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size);
+
+ ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf);
+- ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush);
+- ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize;
++ ds->sym_buf = ds->pending_buf + ds->lit_bufsize;
+
+ ds->l_desc.dyn_tree = ds->dyn_ltree;
+ ds->d_desc.dyn_tree = ds->dyn_dtree;
+@@ -1925,7 +1959,7 @@ local block_state deflate_fast(s, flush)
+ FLUSH_BLOCK(s, 1);
+ return finish_done;
+ }
+- if (s->last_lit)
++ if (s->sym_next)
+ FLUSH_BLOCK(s, 0);
+ return block_done;
+ }
+@@ -2056,7 +2090,7 @@ local block_state deflate_slow(s, flush)
+ FLUSH_BLOCK(s, 1);
+ return finish_done;
+ }
+- if (s->last_lit)
++ if (s->sym_next)
+ FLUSH_BLOCK(s, 0);
+ return block_done;
+ }
+@@ -2131,7 +2165,7 @@ local block_state deflate_rle(s, flush)
+ FLUSH_BLOCK(s, 1);
+ return finish_done;
+ }
+- if (s->last_lit)
++ if (s->sym_next)
+ FLUSH_BLOCK(s, 0);
+ return block_done;
+ }
+@@ -2170,7 +2204,7 @@ local block_state deflate_huff(s, flush)
+ FLUSH_BLOCK(s, 1);
+ return finish_done;
+ }
+- if (s->last_lit)
++ if (s->sym_next)
+ FLUSH_BLOCK(s, 0);
+ return block_done;
+ }
+diff --git a/deflate.h b/deflate.h
+index 23ecdd312..d4cf1a98b 100644
+--- a/deflate.h
++++ b/deflate.h
+@@ -217,7 +217,7 @@ typedef struct internal_state {
+ /* Depth of each subtree used as tie breaker for trees of equal frequency
+ */
+
+- uchf *l_buf; /* buffer for literals or lengths */
++ uchf *sym_buf; /* buffer for distances and literals/lengths */
+
+ uInt lit_bufsize;
+ /* Size of match buffer for literals/lengths. There are 4 reasons for
+@@ -239,13 +239,8 @@ typedef struct internal_state {
+ * - I can't count above 4
+ */
+
+- uInt last_lit; /* running index in l_buf */
+-
+- ushf *d_buf;
+- /* Buffer for distances. To simplify the code, d_buf and l_buf have
+- * the same number of elements. To use different lengths, an extra flag
+- * array would be necessary.
+- */
++ uInt sym_next; /* running index in sym_buf */
++ uInt sym_end; /* symbol table full when sym_next reaches this */
+
+ ulg opt_len; /* bit length of current block with optimal trees */
+ ulg static_len; /* bit length of current block with static trees */
+@@ -325,20 +320,22 @@ void ZLIB_INTERNAL _tr_stored_block OF((deflate_state *s, charf *buf,
+
+ # define _tr_tally_lit(s, c, flush) \
+ { uch cc = (c); \
+- s->d_buf[s->last_lit] = 0; \
+- s->l_buf[s->last_lit++] = cc; \
++ s->sym_buf[s->sym_next++] = 0; \
++ s->sym_buf[s->sym_next++] = 0; \
++ s->sym_buf[s->sym_next++] = cc; \
+ s->dyn_ltree[cc].Freq++; \
+- flush = (s->last_lit == s->lit_bufsize-1); \
++ flush = (s->sym_next == s->sym_end); \
+ }
+ # define _tr_tally_dist(s, distance, length, flush) \
+ { uch len = (uch)(length); \
+ ush dist = (ush)(distance); \
+- s->d_buf[s->last_lit] = dist; \
+- s->l_buf[s->last_lit++] = len; \
++ s->sym_buf[s->sym_next++] = dist; \
++ s->sym_buf[s->sym_next++] = dist >> 8; \
++ s->sym_buf[s->sym_next++] = len; \
+ dist--; \
+ s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
+ s->dyn_dtree[d_code(dist)].Freq++; \
+- flush = (s->last_lit == s->lit_bufsize-1); \
++ flush = (s->sym_next == s->sym_end); \
+ }
+ #else
+ # define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c)
+diff --git a/trees.c b/trees.c
+index 4f4a65011..decaeb7c3 100644
+--- a/trees.c
++++ b/trees.c
+@@ -416,7 +416,7 @@ local void init_block(s)
+
+ s->dyn_ltree[END_BLOCK].Freq = 1;
+ s->opt_len = s->static_len = 0L;
+- s->last_lit = s->matches = 0;
++ s->sym_next = s->matches = 0;
+ }
+
+ #define SMALLEST 1
+@@ -948,7 +948,7 @@ void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
+
+ Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ",
+ opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len,
+- s->last_lit));
++ s->sym_next / 3));
+
+ if (static_lenb <= opt_lenb) opt_lenb = static_lenb;
+
+@@ -1017,8 +1017,9 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+ unsigned dist; /* distance of matched string */
+ unsigned lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */
+ {
+- s->d_buf[s->last_lit] = (ush)dist;
+- s->l_buf[s->last_lit++] = (uch)lc;
++ s->sym_buf[s->sym_next++] = dist;
++ s->sym_buf[s->sym_next++] = dist >> 8;
++ s->sym_buf[s->sym_next++] = lc;
+ if (dist == 0) {
+ /* lc is the unmatched char */
+ s->dyn_ltree[lc].Freq++;
+@@ -1033,30 +1034,7 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+ s->dyn_ltree[_length_code[lc]+LITERALS+1].Freq++;
+ s->dyn_dtree[d_code(dist)].Freq++;
+ }
+-
+-#ifdef TRUNCATE_BLOCK
+- /* Try to guess if it is profitable to stop the current block here */
+- if ((s->last_lit & 0x1fff) == 0 && s->level > 2) {
+- /* Compute an upper bound for the compressed length */
+- ulg out_length = (ulg)s->last_lit*8L;
+- ulg in_length = (ulg)((long)s->strstart - s->block_start);
+- int dcode;
+- for (dcode = 0; dcode < D_CODES; dcode++) {
+- out_length += (ulg)s->dyn_dtree[dcode].Freq *
+- (5L+extra_dbits[dcode]);
+- }
+- out_length >>= 3;
+- Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ",
+- s->last_lit, in_length, out_length,
+- 100L - out_length*100L/in_length));
+- if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1;
+- }
+-#endif
+- return (s->last_lit == s->lit_bufsize-1);
+- /* We avoid equality with lit_bufsize because of wraparound at 64K
+- * on 16 bit machines and because stored blocks are restricted to
+- * 64K-1 bytes.
+- */
++ return (s->sym_next == s->sym_end);
+ }
+
+ /* ===========================================================================
+@@ -1069,13 +1047,14 @@ local void compress_block(s, ltree, dtree)
+ {
+ unsigned dist; /* distance of matched string */
+ int lc; /* match length or unmatched char (if dist == 0) */
+- unsigned lx = 0; /* running index in l_buf */
++ unsigned sx = 0; /* running index in sym_buf */
+ unsigned code; /* the code to send */
+ int extra; /* number of extra bits to send */
+
+- if (s->last_lit != 0) do {
+- dist = s->d_buf[lx];
+- lc = s->l_buf[lx++];
++ if (s->sym_next != 0) do {
++ dist = s->sym_buf[sx++] & 0xff;
++ dist += (unsigned)(s->sym_buf[sx++] & 0xff) << 8;
++ lc = s->sym_buf[sx++];
+ if (dist == 0) {
+ send_code(s, lc, ltree); /* send a literal byte */
+ Tracecv(isgraph(lc), (stderr," '%c' ", lc));
+@@ -1100,11 +1079,10 @@ local void compress_block(s, ltree, dtree)
+ }
+ } /* literal or match pair ? */
+
+- /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */
+- Assert((uInt)(s->pending) < s->lit_bufsize + 2*lx,
+- "pendingBuf overflow");
++ /* Check that the overlay between pending_buf and sym_buf is ok: */
++ Assert(s->pending < s->lit_bufsize + sx, "pendingBuf overflow");
+
+- } while (lx < s->last_lit);
++ } while (sx < s->sym_next);
+
+ send_code(s, END_BLOCK, ltree);
+ }
diff --git a/meta/recipes-core/zlib/zlib_1.2.11.bb b/meta/recipes-core/zlib/zlib_1.2.11.bb
index ef9431ae47..bc42cd64e9 100644
--- a/meta/recipes-core/zlib/zlib_1.2.11.bb
+++ b/meta/recipes-core/zlib/zlib_1.2.11.bb
@@ -8,6 +8,7 @@ LIC_FILES_CHKSUM = "file://zlib.h;beginline=6;endline=23;md5=5377232268e952e9ef6
SRC_URI = "${SOURCEFORGE_MIRROR}/libpng/${BPN}/${PV}/${BPN}-${PV}.tar.xz \
file://ldflags-tests.patch \
+ file://CVE-2018-25032.patch \
file://run-ptest \
"
UPSTREAM_CHECK_URI = "http://zlib.net/"
diff --git a/meta/recipes-devtools/binutils/binutils-2.36.inc b/meta/recipes-devtools/binutils/binutils-2.36.inc
index 7d0824e060..fa28358c2d 100644
--- a/meta/recipes-devtools/binutils/binutils-2.36.inc
+++ b/meta/recipes-devtools/binutils/binutils-2.36.inc
@@ -24,7 +24,7 @@ BRANCH ?= "binutils-2_36-branch"
UPSTREAM_CHECK_GITTAGREGEX = "binutils-(?P<pver>\d+_(\d_?)*)"
-SRCREV ?= "7651a4871c225925ffdfda0a8c91a6ed370cd9a1"
+SRCREV ?= "a281816c8aeb12619d34eec8959a43dfa5c6b4ec"
BINUTILS_GIT_URI ?= "git://sourceware.org/git/binutils-gdb.git;branch=${BRANCH};protocol=git"
SRC_URI = "\
${BINUTILS_GIT_URI} \
@@ -41,10 +41,9 @@ SRC_URI = "\
file://0014-Fix-rpath-in-libtool-when-sysroot-is-enabled.patch \
file://0015-sync-with-OE-libtool-changes.patch \
file://0016-Check-for-clang-before-checking-gcc-version.patch \
- file://0001-CVE-2021-20197.patch \
- file://0002-CVE-2021-20197.patch \
- file://0003-CVE-2021-20197.patch \
file://0017-CVE-2021-3530.patch \
file://0018-CVE-2021-3530.patch \
+ file://0001-CVE-2021-42574.patch \
+ file://0001-CVE-2021-45078.patch \
"
S = "${WORKDIR}/git"
diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch
deleted file mode 100644
index 2b4eaba26d..0000000000
--- a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch
+++ /dev/null
@@ -1,201 +0,0 @@
-From 8e03235147a9e774d3ba084e93c2da1aa94d1cec Mon Sep 17 00:00:00 2001
-From: Siddhesh Poyarekar <siddhesh@gotplt.org>
-Date: Mon, 22 Feb 2021 20:45:50 +0530
-Subject: [PATCH] binutils: Avoid renaming over existing files
-
-Renaming over existing files needs additional care to restore
-permissions and ownership, which may not always succeed.
-Additionally, other properties of the file such as extended attributes
-may be lost, making the operation flaky.
-
-For predictable results, resort to rename() only if the file does not
-exist, otherwise copy the file contents into the existing file. This
-ensures that no additional tricks are needed to retain file
-properties.
-
-This also allows dropping of the redundant set_times on the tmpfile in
-objcopy/strip since now we no longer rename over existing files.
-
-binutils/
-
- * ar.c (write_archive): Adjust call to SMART_RENAME.
- * arsup.c (ar_save): Likewise.
- * objcopy (strip_main): Don't set times on temporary file and
- adjust call to SMART_RENAME.
- (copy_main): Likewise.
- * rename.c [!S_ISLNK]: Remove definitions.
- (try_preserve_permissions): Remove function.
- (smart_rename): Replace PRESERVE_DATES argument with
- TARGET_STAT. Use rename system call only if TO does not exist.
- * bucomm.h (smart_rename): Adjust declaration.
-
-(cherry picked from commit 3685de750e6a091663a0abe42528cad29e960e35)
-
-Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=8e03235147a9e774d3ba084e93c2da1aa94d1cec]
-CVE: CVE-2021-20197
-Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com>
----
- binutils/ar.c | 2 +-
- binutils/arsup.c | 2 +-
- binutils/bucomm.h | 3 ++-
- binutils/objcopy.c | 8 ++-----
- binutils/rename.c | 55 +++++++++-------------------------------------
- 6 files changed, 29 insertions(+), 54 deletions(-)
-
-diff --git a/binutils/ar.c b/binutils/ar.c
-index 45a34e3a6cf..3a91708b51c 100644
---- a/binutils/ar.c
-+++ b/binutils/ar.c
-@@ -1308,7 +1308,7 @@ write_archive (bfd *iarch)
- /* We don't care if this fails; we might be creating the archive. */
- bfd_close (iarch);
-
-- if (smart_rename (new_name, old_name, 0) != 0)
-+ if (smart_rename (new_name, old_name, NULL) != 0)
- xexit (1);
- free (old_name);
- free (new_name);
-diff --git a/binutils/arsup.c b/binutils/arsup.c
-index 5403a0c5d74..0a1f63f6456 100644
---- a/binutils/arsup.c
-+++ b/binutils/arsup.c
-@@ -351,7 +351,7 @@ ar_save (void)
-
- bfd_close (obfd);
-
-- smart_rename (ofilename, real_name, 0);
-+ smart_rename (ofilename, real_name, NULL);
- obfd = 0;
- free (ofilename);
- }
-diff --git a/binutils/bucomm.h b/binutils/bucomm.h
-index 91f6a5b228f..aa7e33d8cd1 100644
---- a/binutils/bucomm.h
-+++ b/binutils/bucomm.h
-@@ -71,7 +71,8 @@ extern void print_version (const char *);
- /* In rename.c. */
- extern void set_times (const char *, const struct stat *);
-
--extern int smart_rename (const char *, const char *, int);
-+extern int smart_rename (const char *, const char *, struct stat *);
-+
-
- /* In libiberty. */
- void *xmalloc (size_t);
-diff --git a/binutils/objcopy.c b/binutils/objcopy.c
-index eab3b6db585..07a872b5a80 100644
---- a/binutils/objcopy.c
-+++ b/binutils/objcopy.c
-@@ -4861,12 +4861,10 @@ strip_main (int argc, char *argv[])
- output_target, NULL);
- if (status == 0)
- {
-- if (preserve_dates)
-- set_times (tmpname, &statbuf);
- if (output_file != tmpname)
- status = (smart_rename (tmpname,
- output_file ? output_file : argv[i],
-- preserve_dates) != 0);
-+ preserve_dates ? &statbuf : NULL) != 0);
- if (status == 0)
- status = hold_status;
- }
-@@ -5931,11 +5929,9 @@ copy_main (int argc, char *argv[])
- output_target, input_arch);
- if (status == 0)
- {
-- if (preserve_dates)
-- set_times (tmpname, &statbuf);
- if (tmpname != output_filename)
- status = (smart_rename (tmpname, input_filename,
-- preserve_dates) != 0);
-+ preserve_dates ? &statbuf : NULL) != 0);
- }
- else
- unlink_if_ordinary (tmpname);
-diff --git a/binutils/rename.c b/binutils/rename.c
-index 65ad5bf52c4..f471b45fd3f 100644
---- a/binutils/rename.c
-+++ b/binutils/rename.c
-@@ -122,20 +122,13 @@ set_times (const char *destination, const struct stat *statbuf)
- non_fatal (_("%s: cannot set time: %s"), destination, strerror (errno));
- }
-
--#ifndef S_ISLNK
--#ifdef S_IFLNK
--#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK)
--#else
--#define S_ISLNK(m) 0
--#define lstat stat
--#endif
--#endif
--
--/* Rename FROM to TO, copying if TO is a link.
-- Return 0 if ok, -1 if error. */
-+/* Rename FROM to TO, copying if TO exists. TARGET_STAT has the file status
-+ that, if non-NULL, is used to fix up timestamps after rename. Return 0 if
-+ ok, -1 if error. */
-
- int
--smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNUSED)
-+smart_rename (const char *from, const char *to,
-+ struct stat *target_stat ATTRIBUTE_UNUSED)
- {
- bfd_boolean exists;
- struct stat s;
-@@ -158,38 +151,10 @@ smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNU
- unlink (from);
- }
- #else
-- /* Use rename only if TO is not a symbolic link and has
-- only one hard link, and we have permission to write to it. */
-- if (! exists
-- || (!S_ISLNK (s.st_mode)
-- && S_ISREG (s.st_mode)
-- && (s.st_mode & S_IWUSR)
-- && s.st_nlink == 1)
-- )
-+ /* Avoid a full copy and use rename if TO does not exist. */
-+ if (!exists)
- {
-- ret = rename (from, to);
-- if (ret == 0)
-- {
-- if (exists)
-- {
-- /* Try to preserve the permission bits and ownership of
-- TO. First get the mode right except for the setuid
-- bit. Then change the ownership. Then fix the setuid
-- bit. We do the chmod before the chown because if the
-- chown succeeds, and we are a normal user, we won't be
-- able to do the chmod afterward. We don't bother to
-- fix the setuid bit first because that might introduce
-- a fleeting security problem, and because the chown
-- will clear the setuid bit anyhow. We only fix the
-- setuid bit if the chown succeeds, because we don't
-- want to introduce an unexpected setuid file owned by
-- the user running objcopy. */
-- chmod (to, s.st_mode & 0777);
-- if (chown (to, s.st_uid, s.st_gid) >= 0)
-- chmod (to, s.st_mode & 07777);
-- }
-- }
-- else
-+ if ((ret = rename (from, to)) != 0)
- {
- /* We have to clean up here. */
- non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno));
-@@ -202,8 +167,8 @@ smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNU
- if (ret != 0)
- non_fatal (_("unable to copy file '%s'; reason: %s"), to, strerror (errno));
-
-- if (preserve_dates)
-- set_times (to, &s);
-+ if (target_stat != NULL)
-+ set_times (to, target_stat);
- unlink (from);
- }
- #endif /* _WIN32 && !__CYGWIN32__ */
---
-2.31.1
-
diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch
new file mode 100644
index 0000000000..6adc438b5c
--- /dev/null
+++ b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch
@@ -0,0 +1,2006 @@
+From b3aa80b45c4f46029efeb204bb9f2d2c4278a0e5 Mon Sep 17 00:00:00 2001
+From: Nick Clifton <nickc@redhat.com>
+Date: Tue, 9 Nov 2021 13:25:42 +0000
+Subject: [PATCH] Add --unicode option to control how unicode characters are
+ handled by display tools.
+
+ * nm.c: Add --unicode option to control how unicode characters are
+ handled.
+ * objdump.c: Likewise.
+ * readelf.c: Likewise.
+ * strings.c: Likewise.
+ * binutils.texi: Document the new feature.
+ * NEWS: Document the new feature.
+ * testsuite/binutils-all/unicode.exp: New file.
+ * testsuite/binutils-all/nm.hex.unicode
+ * testsuite/binutils-all/strings.escape.unicode
+ * testsuite/binutils-all/objdump.highlight.unicode
+ * testsuite/binutils-all/readelf.invalid.unicode
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=b3aa80b45c4f46029efeb204bb9f2d2c4278a0e5]
+
+Signed-off-by: pgowda <pgowda.cve@gmail.com>
+---
+ binutils/ChangeLog | 15 +
+ binutils/NEWS | 9 +
+ binutils/doc/binutils.texi | 78 ++++
+ binutils/nm.c | 228 ++++++++++-
+ binutils/objdump.c | 235 ++++++++++--
+ binutils/readelf.c | 190 +++++++++-
+ binutils/strings.c | 757 ++++++++++++++++++++++++++++++++++---
+ 7 files changed, 1409 insertions(+), 103 deletions(-)
+
+diff --git a/binutils/ChangeLog b/binutils/ChangeLog
+--- a/binutils/ChangeLog 2021-12-23 03:23:38.425843662 -0800
++++ b/binutils/ChangeLog 2021-12-23 03:30:31.094968942 -0800
+@@ -1,3 +1,18 @@
++2021-11-09 Nick Clifton <nickc@redhat.com>
++
++ * nm.c: Add --unicode option to control how unicode characters are
++ handled.
++ * objdump.c: Likewise.
++ * readelf.c: Likewise.
++ * strings.c: Likewise.
++ * binutils.texi: Document the new feature.
++ * NEWS: Document the new feature.
++ * testsuite/binutils-all/unicode.exp: New file.
++ * testsuite/binutils-all/nm.hex.unicode
++ * testsuite/binutils-all/strings.escape.unicode
++ * testsuite/binutils-all/objdump.highlight.unicode
++ * testsuite/binutils-all/readelf.invalid.unicode
++
+ 2021-04-15 Alan Modra <amodra@gmail.com>
+
+ PR 27456
+diff --git a/binutils/doc/binutils.texi b/binutils/doc/binutils.texi
+--- a/binutils/doc/binutils.texi 2021-12-23 03:23:38.441843395 -0800
++++ b/binutils/doc/binutils.texi 2021-12-23 03:30:31.094968942 -0800
+@@ -805,6 +805,7 @@ nm [@option{-A}|@option{-o}|@option{--pr
+ [@option{-s}|@option{--print-armap}] [@option{-t} @var{radix}|@option{--radix=}@var{radix}]
+ [@option{-u}|@option{--undefined-only}] [@option{-V}|@option{--version}]
+ [@option{-X 32_64}] [@option{--defined-only}] [@option{--no-demangle}]
++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}]
+ [@option{--plugin} @var{name}]
+ [@option{--no-recurse-limit}|@option{--recurse-limit}]]
+ [@option{--size-sort}] [@option{--special-syms}]
+@@ -1114,6 +1115,21 @@ Use @var{radix} as the radix for printin
+ @cindex undefined symbols
+ Display only undefined symbols (those external to each object file).
+
++@item -U @var{[d|i|l|e|x|h]}
++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}
++Controls the display of UTF-8 encoded mulibyte characters in strings.
++The default (@option{--unicode=default}) is to give them no special
++treatment. The @option{--unicode=locale} option displays the sequence
++in the current locale, which may or may not support them. The options
++@option{--unicode=hex} and @option{--unicode=invalid} display them as
++hex byte sequences enclosed by either angle brackets or curly braces.
++
++The @option{--unicode=escape} option displays them as escape sequences
++(@var{\uxxxx}) and the @option{--unicode=highlight} option displays
++them as escape sequences highlighted in red (if supported by the
++output device). The colouring is intended to draw attention to the
++presence of unicode sequences where they might not be expected.
++
+ @item -V
+ @itemx --version
+ Show the version number of @command{nm} and exit.
+@@ -2210,6 +2226,7 @@ objdump [@option{-a}|@option{--archive-h
+ [@option{--prefix-strip=}@var{level}]
+ [@option{--insn-width=}@var{width}]
+ [@option{--visualize-jumps[=color|=extended-color|=off]}
++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}]
+ [@option{-V}|@option{--version}]
+ [@option{-H}|@option{--help}]
+ @var{objfile}@dots{}
+@@ -2877,6 +2894,21 @@ When displaying symbols include those wh
+ special in some way and which would not normally be of interest to the
+ user.
+
++@item -U @var{[d|i|l|e|x|h]}
++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}
++Controls the display of UTF-8 encoded mulibyte characters in strings.
++The default (@option{--unicode=default}) is to give them no special
++treatment. The @option{--unicode=locale} option displays the sequence
++in the current locale, which may or may not support them. The options
++@option{--unicode=hex} and @option{--unicode=invalid} display them as
++hex byte sequences enclosed by either angle brackets or curly braces.
++
++The @option{--unicode=escape} option displays them as escape sequences
++(@var{\uxxxx}) and the @option{--unicode=highlight} option displays
++them as escape sequences highlighted in red (if supported by the
++output device). The colouring is intended to draw attention to the
++presence of unicode sequences where they might not be expected.
++
+ @item -V
+ @itemx --version
+ Print the version number of @command{objdump} and exit.
+@@ -3153,6 +3185,7 @@ strings [@option{-afovV}] [@option{-}@va
+ [@option{-n} @var{min-len}] [@option{--bytes=}@var{min-len}]
+ [@option{-t} @var{radix}] [@option{--radix=}@var{radix}]
+ [@option{-e} @var{encoding}] [@option{--encoding=}@var{encoding}]
++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}]
+ [@option{-}] [@option{--all}] [@option{--print-file-name}]
+ [@option{-T} @var{bfdname}] [@option{--target=}@var{bfdname}]
+ [@option{-w}] [@option{--include-all-whitespace}]
+@@ -3244,6 +3277,28 @@ single-8-bit-byte characters, @samp{b} =
+ littleendian. Useful for finding wide character strings. (@samp{l}
+ and @samp{b} apply to, for example, Unicode UTF-16/UCS-2 encodings).
+
++@item -U @var{[d|i|l|e|x|h]}
++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]}
++Controls the display of UTF-8 encoded mulibyte characters in strings.
++The default (@option{--unicode=default}) is to give them no special
++treatment, and instead rely upon the setting of the
++@option{--encoding} option. The other values for this option
++automatically enable @option{--encoding=S}.
++
++The @option{--unicode=invalid} option treats them as non-graphic
++characters and hence not part of a valid string. All the remaining
++options treat them as valid string characters.
++
++The @option{--unicode=locale} option displays them in the current
++locale, which may or may not support UTF-8 encoding. The
++@option{--unicode=hex} option displays them as hex byte sequences
++enclosed between @var{<>} characters. The @option{--unicode=escape}
++option displays them as escape sequences (@var{\uxxxx}) and the
++@option{--unicode=highlight} option displays them as escape sequences
++highlighted in red (if supported by the output device). The colouring
++is intended to draw attention to the presence of unicode sequences
++where they might not be expected.
++
+ @item -T @var{bfdname}
+ @itemx --target=@var{bfdname}
+ @cindex object code format
+@@ -4740,6 +4795,7 @@ readelf [@option{-a}|@option{--all}]
+ [@option{--dyn-syms}|@option{--lto-syms}]
+ [@option{--demangle@var{=style}}|@option{--no-demangle}]
+ [@option{--recurse-limit}|@option{--no-recurse-limit}]
++ [@option{-U} @var{method}|@option{--unicode=}@var{method}]
+ [@option{-n}|@option{--notes}]
+ [@option{-r}|@option{--relocs}]
+ [@option{-u}|@option{--unwind}]
+@@ -4887,6 +4943,28 @@ necessary in order to demangle truly com
+ that if the recursion limit is disabled then stack exhaustion is
+ possible and any bug reports about such an event will be rejected.
+
++@item -U @var{[d|i|l|e|x|h]}
++@itemx --unicode=[default|invalid|locale|escape|hex|highlight]
++Controls the display of non-ASCII characters in identifier names.
++The default (@option{--unicode=locale} or @option{--unicode=default}) is
++to treat them as multibyte characters and display them in the current
++locale. All other versions of this option treat the bytes as UTF-8
++encoded values and attempt to interpret them. If they cannot be
++interpreted or if the @option{--unicode=invalid} option is used then
++they are displayed as a sequence of hex bytes, encloses in curly
++parethesis characters.
++
++Using the @option{--unicode=escape} option will display the characters
++as as unicode escape sequences (@var{\uxxxx}). Using the
++@option{--unicode=hex} will display the characters as hex byte
++sequences enclosed between angle brackets.
++
++Using the @option{--unicode=highlight} will display the characters as
++unicode escape sequences but it will also highlighted them in red,
++assuming that colouring is supported by the output device. The
++colouring is intended to draw attention to the presence of unicode
++sequences when they might not be expected.
++
+ @item -e
+ @itemx --headers
+ Display all the headers in the file. Equivalent to @option{-h -l -S}.
+diff --git a/binutils/NEWS b/binutils/NEWS
+--- a/binutils/NEWS 2021-12-23 03:23:38.433843528 -0800
++++ b/binutils/NEWS 2021-12-23 03:30:31.094968942 -0800
+@@ -1,5 +1,14 @@
+ -*- text -*-
+
++* Tools which display symbols or strings (readelf, strings, nm, objdump)
++ have a new command line option which controls how unicode characters are
++ handled. By default they are treated as normal for the tool. Using
++ --unicode=locale will display them according to the current locale.
++ Using --unicode=hex will display them as hex byte values, whilst
++ --unicode=escape will display them as escape sequences. In addition
++ using --unicode=highlight will display them as unicode escape sequences
++ highlighted in red (if supported by the output device).
++
+ Changes in 2.36:
+
+ * Update elfedit and readelf with LAM_U48 and LAM_U57 support.
+diff --git a/binutils/nm.c b/binutils/nm.c
+--- a/binutils/nm.c 2021-12-23 03:23:38.441843395 -0800
++++ b/binutils/nm.c 2021-12-23 03:30:31.098968875 -0800
+@@ -38,6 +38,11 @@
+ #include "bucomm.h"
+ #include "plugin-api.h"
+ #include "plugin.h"
++#include "safe-ctype.h"
++
++#ifndef streq
++#define streq(a,b) (strcmp ((a),(b)) == 0)
++#endif
+
+ /* When sorting by size, we use this structure to hold the size and a
+ pointer to the minisymbol. */
+@@ -192,6 +197,18 @@ static const char *plugin_target = NULL;
+ static bfd *lineno_cache_bfd;
+ static bfd *lineno_cache_rel_bfd;
+
++typedef enum unicode_display_type
++{
++ unicode_default = 0,
++ unicode_locale,
++ unicode_escape,
++ unicode_hex,
++ unicode_highlight,
++ unicode_invalid
++} unicode_display_type;
++
++static unicode_display_type unicode_display = unicode_default;
++
+ enum long_option_values
+ {
+ OPTION_TARGET = 200,
+@@ -234,6 +251,7 @@ static struct option long_options[] =
+ {"target", required_argument, 0, OPTION_TARGET},
+ {"defined-only", no_argument, &defined_only, 1},
+ {"undefined-only", no_argument, &undefined_only, 1},
++ {"unicode", required_argument, NULL, 'U'},
+ {"version", no_argument, &show_version, 1},
+ {"with-symbol-versions", no_argument, NULL,
+ OPTION_WITH_SYMBOL_VERSIONS},
+@@ -285,6 +303,8 @@ usage (FILE *stream, int status)
+ -t, --radix=RADIX Use RADIX for printing symbol values\n\
+ --target=BFDNAME Specify the target object format as BFDNAME\n\
+ -u, --undefined-only Display only undefined symbols\n\
++ -U {d|s|i|x|e|h} Specify how to treat UTF-8 encoded unicode characters\n\
++ --unicode={default|show|invalid|hex|escape|highlight}\n\
+ --with-symbol-versions Display version strings after symbol names\n\
+ -X 32_64 (ignored)\n\
+ @FILE Read options from FILE\n\
+@@ -399,6 +419,188 @@ get_coff_symbol_type (const struct inter
+ fatal ("%s", xstrerror (errno));
+ return bufp;
+ }
++
++/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT.
++ The conversion format is controlled by the unicode_display variable.
++ Returns the number of characters added to OUT.
++ Returns the number of bytes consumed from IN in CONSUMED.
++ Always consumes at least one byte and displays at least one character. */
++
++static unsigned int
++display_utf8 (const unsigned char * in, char * out, unsigned int * consumed)
++{
++ char * orig_out = out;
++ unsigned int nchars = 0;
++ unsigned int j;
++
++ if (unicode_display == unicode_default)
++ goto invalid;
++
++ if (in[0] < 0xc0)
++ goto invalid;
++
++ if ((in[1] & 0xc0) != 0x80)
++ goto invalid;
++
++ if ((in[0] & 0x20) == 0)
++ {
++ nchars = 2;
++ goto valid;
++ }
++
++ if ((in[2] & 0xc0) != 0x80)
++ goto invalid;
++
++ if ((in[0] & 0x10) == 0)
++ {
++ nchars = 3;
++ goto valid;
++ }
++
++ if ((in[3] & 0xc0) != 0x80)
++ goto invalid;
++
++ nchars = 4;
++
++ valid:
++ switch (unicode_display)
++ {
++ case unicode_locale:
++ /* Copy the bytes into the output buffer as is. */
++ memcpy (out, in, nchars);
++ out += nchars;
++ break;
++
++ case unicode_invalid:
++ case unicode_hex:
++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{');
++ out += sprintf (out, "0x");
++ for (j = 0; j < nchars; j++)
++ out += sprintf (out, "%02x", in [j]);
++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}');
++ break;
++
++ case unicode_highlight:
++ if (isatty (1))
++ out += sprintf (out, "\x1B[31;47m"); /* Red. */
++ /* Fall through. */
++ case unicode_escape:
++ switch (nchars)
++ {
++ case 2:
++ out += sprintf (out, "\\u%02x%02x",
++ ((in[0] & 0x1c) >> 2),
++ ((in[0] & 0x03) << 6) | (in[1] & 0x3f));
++ break;
++
++ case 3:
++ out += sprintf (out, "\\u%02x%02x",
++ ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2),
++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3f)));
++ break;
++
++ case 4:
++ out += sprintf (out, "\\u%02x%02x%02x",
++ ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2),
++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2),
++ ((in[2] & 0x03) << 6) | ((in[3] & 0x3f)));
++ break;
++ default:
++ /* URG. */
++ break;
++ }
++
++ if (unicode_display == unicode_highlight && isatty (1))
++ out += sprintf (out, "\033[0m"); /* Default colour. */
++ break;
++
++ default:
++ /* URG */
++ break;
++ }
++
++ * consumed = nchars;
++ return out - orig_out;
++
++ invalid:
++ /* Not a valid UTF-8 sequence. */
++ *out = *in;
++ * consumed = 1;
++ return 1;
++}
++
++/* Convert any UTF-8 encoded characters in NAME into the form specified by
++ unicode_display. Also converts control characters. Returns a static
++ buffer if conversion was necessary.
++ Code stolen from objdump.c:sanitize_string(). */
++
++static const char *
++convert_utf8 (const char * in)
++{
++ static char * buffer = NULL;
++ static size_t buffer_len = 0;
++ const char * original = in;
++ char * out;
++
++ /* Paranoia. */
++ if (in == NULL)
++ return "";
++
++ /* See if any conversion is necessary.
++ In the majority of cases it will not be needed. */
++ do
++ {
++ unsigned char c = *in++;
++
++ if (c == 0)
++ return original;
++
++ if (ISCNTRL (c))
++ break;
++
++ if (unicode_display != unicode_default && c >= 0xc0)
++ break;
++ }
++ while (1);
++
++ /* Copy the input, translating as needed. */
++ in = original;
++ if (buffer_len < (strlen (in) * 9))
++ {
++ free ((void *) buffer);
++ buffer_len = strlen (in) * 9;
++ buffer = xmalloc (buffer_len + 1);
++ }
++
++ out = buffer;
++ do
++ {
++ unsigned char c = *in++;
++
++ if (c == 0)
++ break;
++
++ if (ISCNTRL (c))
++ {
++ *out++ = '^';
++ *out++ = c + 0x40;
++ }
++ else if (unicode_display != unicode_default && c >= 0xc0)
++ {
++ unsigned int num_consumed;
++
++ out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed);
++ in += num_consumed - 1;
++ }
++ else
++ *out++ = c;
++ }
++ while (1);
++
++ *out = 0;
++ return buffer;
++}
++
+
+ /* Print symbol name NAME, read from ABFD, with printf format FORM,
+ demangling it if requested. */
+@@ -418,6 +620,11 @@ print_symname (const char *form, struct
+ name = alloc;
+ }
+
++ if (unicode_display != unicode_default)
++ {
++ name = convert_utf8 (name);
++ }
++
+ if (info != NULL && info->elfinfo)
+ {
+ const char *version_string;
+@@ -1738,7 +1945,7 @@ main (int argc, char **argv)
+ fatal (_("fatal error: libbfd ABI mismatch"));
+ set_default_bfd_target ();
+
+- while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uvVvX:",
++ while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uU:vVvX:",
+ long_options, (int *) 0)) != EOF)
+ {
+ switch (c)
+@@ -1828,6 +2035,24 @@ main (int argc, char **argv)
+ case 'u':
+ undefined_only = 1;
+ break;
++
++ case 'U':
++ if (streq (optarg, "default") || streq (optarg, "d"))
++ unicode_display = unicode_default;
++ else if (streq (optarg, "locale") || streq (optarg, "l"))
++ unicode_display = unicode_locale;
++ else if (streq (optarg, "escape") || streq (optarg, "e"))
++ unicode_display = unicode_escape;
++ else if (streq (optarg, "invalid") || streq (optarg, "i"))
++ unicode_display = unicode_invalid;
++ else if (streq (optarg, "hex") || streq (optarg, "x"))
++ unicode_display = unicode_hex;
++ else if (streq (optarg, "highlight") || streq (optarg, "h"))
++ unicode_display = unicode_highlight;
++ else
++ fatal (_("invalid argument to -U/--unicode: %s"), optarg);
++ break;
++
+ case 'V':
+ show_version = 1;
+ break;
+diff --git a/binutils/objdump.c b/binutils/objdump.c
+--- a/binutils/objdump.c 2021-12-23 03:23:38.445843329 -0800
++++ b/binutils/objdump.c 2021-12-23 03:30:31.098968875 -0800
+@@ -205,6 +205,19 @@ static const struct objdump_private_desc
+
+ /* The list of detected jumps inside a function. */
+ static struct jump_info *detected_jumps = NULL;
++
++typedef enum unicode_display_type
++{
++ unicode_default = 0,
++ unicode_locale,
++ unicode_escape,
++ unicode_hex,
++ unicode_highlight,
++ unicode_invalid
++} unicode_display_type;
++
++static unicode_display_type unicode_display = unicode_default;
++
+
+ static void usage (FILE *, int) ATTRIBUTE_NORETURN;
+ static void
+@@ -274,6 +287,8 @@ usage (FILE *stream, int status)
+ --recurse-limit Enable a limit on recursion whilst demangling. [Default]\n\
+ --no-recurse-limit Disable a limit on recursion whilst demangling\n\
+ -w, --wide Format output for more than 80 columns\n\
++ -U[d|l|i|x|e|h] Controls the display of UTF-8 unicode characters\n\
++ --unicode=[default|locale|invalid|hex|escape|highlight]\n\
+ -z, --disassemble-zeroes Do not skip blocks of zeroes when disassembling\n\
+ --start-address=ADDR Only process data whose address is >= ADDR\n\
+ --stop-address=ADDR Only process data whose address is < ADDR\n\
+@@ -348,17 +363,23 @@ static struct option long_options[]=
+ {
+ {"adjust-vma", required_argument, NULL, OPTION_ADJUST_VMA},
+ {"all-headers", no_argument, NULL, 'x'},
+- {"private-headers", no_argument, NULL, 'p'},
+- {"private", required_argument, NULL, 'P'},
+ {"architecture", required_argument, NULL, 'm'},
+ {"archive-headers", no_argument, NULL, 'a'},
++#ifdef ENABLE_LIBCTF
++ {"ctf", required_argument, NULL, OPTION_CTF},
++ {"ctf-parent", required_argument, NULL, OPTION_CTF_PARENT},
++#endif
+ {"debugging", no_argument, NULL, 'g'},
+ {"debugging-tags", no_argument, NULL, 'e'},
+ {"demangle", optional_argument, NULL, 'C'},
+ {"disassemble", optional_argument, NULL, 'd'},
+ {"disassemble-all", no_argument, NULL, 'D'},
+- {"disassembler-options", required_argument, NULL, 'M'},
+ {"disassemble-zeroes", no_argument, NULL, 'z'},
++ {"disassembler-options", required_argument, NULL, 'M'},
++ {"dwarf", optional_argument, NULL, OPTION_DWARF},
++ {"dwarf-check", no_argument, 0, OPTION_DWARF_CHECK},
++ {"dwarf-depth", required_argument, 0, OPTION_DWARF_DEPTH},
++ {"dwarf-start", required_argument, 0, OPTION_DWARF_START},
+ {"dynamic-reloc", no_argument, NULL, 'R'},
+ {"dynamic-syms", no_argument, NULL, 'T'},
+ {"endian", required_argument, NULL, OPTION_ENDIAN},
+@@ -368,15 +389,22 @@ static struct option long_options[]=
+ {"full-contents", no_argument, NULL, 's'},
+ {"headers", no_argument, NULL, 'h'},
+ {"help", no_argument, NULL, 'H'},
++ {"include", required_argument, NULL, 'I'},
+ {"info", no_argument, NULL, 'i'},
++ {"inlines", no_argument, 0, OPTION_INLINES},
++ {"insn-width", required_argument, NULL, OPTION_INSN_WIDTH},
+ {"line-numbers", no_argument, NULL, 'l'},
+- {"no-show-raw-insn", no_argument, &show_raw_insn, -1},
+ {"no-addresses", no_argument, &no_addresses, 1},
++ {"no-recurse-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT},
++ {"no-recursion-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT},
++ {"no-show-raw-insn", no_argument, &show_raw_insn, -1},
++ {"prefix", required_argument, NULL, OPTION_PREFIX},
+ {"prefix-addresses", no_argument, &prefix_addresses, 1},
++ {"prefix-strip", required_argument, NULL, OPTION_PREFIX_STRIP},
++ {"private", required_argument, NULL, 'P'},
++ {"private-headers", no_argument, NULL, 'p'},
+ {"recurse-limit", no_argument, NULL, OPTION_RECURSE_LIMIT},
+ {"recursion-limit", no_argument, NULL, OPTION_RECURSE_LIMIT},
+- {"no-recurse-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT},
+- {"no-recursion-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT},
+ {"reloc", no_argument, NULL, 'r'},
+ {"section", required_argument, NULL, 'j'},
+ {"section-headers", no_argument, NULL, 'h'},
+@@ -384,28 +412,16 @@ static struct option long_options[]=
+ {"source", no_argument, NULL, 'S'},
+ {"source-comment", optional_argument, NULL, OPTION_SOURCE_COMMENT},
+ {"special-syms", no_argument, &dump_special_syms, 1},
+- {"include", required_argument, NULL, 'I'},
+- {"dwarf", optional_argument, NULL, OPTION_DWARF},
+-#ifdef ENABLE_LIBCTF
+- {"ctf", required_argument, NULL, OPTION_CTF},
+- {"ctf-parent", required_argument, NULL, OPTION_CTF_PARENT},
+-#endif
+ {"stabs", no_argument, NULL, 'G'},
+ {"start-address", required_argument, NULL, OPTION_START_ADDRESS},
+ {"stop-address", required_argument, NULL, OPTION_STOP_ADDRESS},
+ {"syms", no_argument, NULL, 't'},
+ {"target", required_argument, NULL, 'b'},
++ {"unicode", required_argument, NULL, 'U'},
+ {"version", no_argument, NULL, 'V'},
+- {"wide", no_argument, NULL, 'w'},
+- {"prefix", required_argument, NULL, OPTION_PREFIX},
+- {"prefix-strip", required_argument, NULL, OPTION_PREFIX_STRIP},
+- {"insn-width", required_argument, NULL, OPTION_INSN_WIDTH},
+- {"dwarf-depth", required_argument, 0, OPTION_DWARF_DEPTH},
+- {"dwarf-start", required_argument, 0, OPTION_DWARF_START},
+- {"dwarf-check", no_argument, 0, OPTION_DWARF_CHECK},
+- {"inlines", no_argument, 0, OPTION_INLINES},
+ {"visualize-jumps", optional_argument, 0, OPTION_VISUALIZE_JUMPS},
+- {0, no_argument, 0, 0}
++ {"wide", no_argument, NULL, 'w'},
++ {NULL, no_argument, NULL, 0}
+ };
+
+ static void
+@@ -415,9 +431,121 @@ nonfatal (const char *msg)
+ exit_status = 1;
+ }
+
++/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT.
++ The conversion format is controlled by the unicode_display variable.
++ Returns the number of characters added to OUT.
++ Returns the number of bytes consumed from IN in CONSUMED.
++ Always consumes at least one byte and displays at least one character. */
++
++static unsigned int
++display_utf8 (const unsigned char * in, char * out, unsigned int * consumed)
++{
++ char * orig_out = out;
++ unsigned int nchars = 0;
++ unsigned int j;
++
++ if (unicode_display == unicode_default)
++ goto invalid;
++
++ if (in[0] < 0xc0)
++ goto invalid;
++
++ if ((in[1] & 0xc0) != 0x80)
++ goto invalid;
++
++ if ((in[0] & 0x20) == 0)
++ {
++ nchars = 2;
++ goto valid;
++ }
++
++ if ((in[2] & 0xc0) != 0x80)
++ goto invalid;
++
++ if ((in[0] & 0x10) == 0)
++ {
++ nchars = 3;
++ goto valid;
++ }
++
++ if ((in[3] & 0xc0) != 0x80)
++ goto invalid;
++
++ nchars = 4;
++
++ valid:
++ switch (unicode_display)
++ {
++ case unicode_locale:
++ /* Copy the bytes into the output buffer as is. */
++ memcpy (out, in, nchars);
++ out += nchars;
++ break;
++
++ case unicode_invalid:
++ case unicode_hex:
++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{');
++ out += sprintf (out, "0x");
++ for (j = 0; j < nchars; j++)
++ out += sprintf (out, "%02x", in [j]);
++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}');
++ break;
++
++ case unicode_highlight:
++ if (isatty (1))
++ out += sprintf (out, "\x1B[31;47m"); /* Red. */
++ /* Fall through. */
++ case unicode_escape:
++ switch (nchars)
++ {
++ case 2:
++ out += sprintf (out, "\\u%02x%02x",
++ ((in[0] & 0x1c) >> 2),
++ ((in[0] & 0x03) << 6) | (in[1] & 0x3f));
++ break;
++
++ case 3:
++ out += sprintf (out, "\\u%02x%02x",
++ ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2),
++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3f)));
++ break;
++
++ case 4:
++ out += sprintf (out, "\\u%02x%02x%02x",
++ ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2),
++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2),
++ ((in[2] & 0x03) << 6) | ((in[3] & 0x3f)));
++ break;
++ default:
++ /* URG. */
++ break;
++ }
++
++ if (unicode_display == unicode_highlight && isatty (1))
++ out += sprintf (out, "\033[0m"); /* Default colour. */
++ break;
++
++ default:
++ /* URG */
++ break;
++ }
++
++ * consumed = nchars;
++ return out - orig_out;
++
++ invalid:
++ /* Not a valid UTF-8 sequence. */
++ *out = *in;
++ * consumed = 1;
++ return 1;
++}
++
+ /* Returns a version of IN with any control characters
+ replaced by escape sequences. Uses a static buffer
+- if necessary. */
++ if necessary.
++
++ If unicode display is enabled, then also handles the
++ conversion of unicode characters. */
+
+ static const char *
+ sanitize_string (const char * in)
+@@ -435,40 +563,50 @@ sanitize_string (const char * in)
+ of cases it will not be needed. */
+ do
+ {
+- char c = *in++;
++ unsigned char c = *in++;
+
+ if (c == 0)
+ return original;
+
+ if (ISCNTRL (c))
+ break;
++
++ if (unicode_display != unicode_default && c >= 0xc0)
++ break;
+ }
+ while (1);
+
+ /* Copy the input, translating as needed. */
+ in = original;
+- if (buffer_len < (strlen (in) * 2))
++ if (buffer_len < (strlen (in) * 9))
+ {
+ free ((void *) buffer);
+- buffer_len = strlen (in) * 2;
++ buffer_len = strlen (in) * 9;
+ buffer = xmalloc (buffer_len + 1);
+ }
+
+ out = buffer;
+ do
+ {
+- char c = *in++;
++ unsigned char c = *in++;
+
+ if (c == 0)
+ break;
+
+- if (!ISCNTRL (c))
+- *out++ = c;
+- else
++ if (ISCNTRL (c))
+ {
+ *out++ = '^';
+ *out++ = c + 0x40;
+ }
++ else if (unicode_display != unicode_default && c >= 0xc0)
++ {
++ unsigned int num_consumed;
++
++ out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed);
++ in += num_consumed - 1;
++ }
++ else
++ *out++ = c;
+ }
+ while (1);
+
+@@ -4481,6 +4619,24 @@ dump_symbols (bfd *abfd ATTRIBUTE_UNUSED
+ free (alloc);
+ }
+ }
++ else if (unicode_display != unicode_default
++ && name != NULL && *name != '\0')
++ {
++ const char * sanitized_name;
++
++ /* If we want to sanitize the name, we do it here, and
++ temporarily clobber it while calling bfd_print_symbol.
++ FIXME: This is a gross hack. */
++ sanitized_name = sanitize_string (name);
++ if (sanitized_name != name)
++ (*current)->name = sanitized_name;
++ else
++ sanitized_name = NULL;
++ bfd_print_symbol (cur_bfd, stdout, *current,
++ bfd_print_symbol_all);
++ if (sanitized_name != NULL)
++ (*current)->name = name;
++ }
+ else
+ bfd_print_symbol (cur_bfd, stdout, *current,
+ bfd_print_symbol_all);
+@@ -5162,7 +5318,7 @@ main (int argc, char **argv)
+ set_default_bfd_target ();
+
+ while ((c = getopt_long (argc, argv,
+- "pP:ib:m:M:VvCdDlfFaHhrRtTxsSI:j:wE:zgeGW::",
++ "pP:ib:m:U:M:VvCdDlfFaHhrRtTxsSI:j:wE:zgeGW::",
+ long_options, (int *) 0))
+ != EOF)
+ {
+@@ -5441,6 +5597,23 @@ main (int argc, char **argv)
+ seenflag = TRUE;
+ break;
+
++ case 'U':
++ if (streq (optarg, "default") || streq (optarg, "d"))
++ unicode_display = unicode_default;
++ else if (streq (optarg, "locale") || streq (optarg, "l"))
++ unicode_display = unicode_locale;
++ else if (streq (optarg, "escape") || streq (optarg, "e"))
++ unicode_display = unicode_escape;
++ else if (streq (optarg, "invalid") || streq (optarg, "i"))
++ unicode_display = unicode_invalid;
++ else if (streq (optarg, "hex") || streq (optarg, "x"))
++ unicode_display = unicode_hex;
++ else if (streq (optarg, "highlight") || streq (optarg, "h"))
++ unicode_display = unicode_highlight;
++ else
++ fatal (_("invalid argument to -U/--unicode: %s"), optarg);
++ break;
++
+ case 'H':
+ usage (stdout, 0);
+ /* No need to set seenflag or to break - usage() does not return. */
+diff --git a/binutils/readelf.c b/binutils/readelf.c
+--- a/binutils/readelf.c 2021-12-23 03:23:42.065783023 -0800
++++ b/binutils/readelf.c 2021-12-23 03:30:36.582877519 -0800
+@@ -321,6 +321,19 @@ typedef enum print_mode
+ }
+ print_mode;
+
++typedef enum unicode_display_type
++{
++ unicode_default = 0,
++ unicode_locale,
++ unicode_escape,
++ unicode_hex,
++ unicode_highlight,
++ unicode_invalid
++} unicode_display_type;
++
++static unicode_display_type unicode_display = unicode_default;
++
++
+ /* Versioned symbol info. */
+ enum versioned_symbol_info
+ {
+@@ -613,11 +626,18 @@ print_symbol (signed int width, const ch
+ if (c == 0)
+ break;
+
+- /* Do not print control characters directly as they can affect terminal
+- settings. Such characters usually appear in the names generated
+- by the assembler for local labels. */
+- if (ISCNTRL (c))
++ if (ISPRINT (c))
++ {
++ putchar (c);
++ width_remaining --;
++ num_printed ++;
++ }
++ else if (ISCNTRL (c))
+ {
++ /* Do not print control characters directly as they can affect terminal
++ settings. Such characters usually appear in the names generated
++ by the assembler for local labels. */
++
+ if (width_remaining < 2)
+ break;
+
+@@ -625,11 +645,137 @@ print_symbol (signed int width, const ch
+ width_remaining -= 2;
+ num_printed += 2;
+ }
+- else if (ISPRINT (c))
++ else if (c == 0x7f)
+ {
+- putchar (c);
+- width_remaining --;
+- num_printed ++;
++ if (width_remaining < 5)
++ break;
++ printf ("<DEL>");
++ width_remaining -= 5;
++ num_printed += 5;
++ }
++ else if (unicode_display != unicode_locale
++ && unicode_display != unicode_default)
++ {
++ /* Display unicode characters as something else. */
++ unsigned char bytes[4];
++ bfd_boolean is_utf8;
++ unsigned int nbytes;
++
++ bytes[0] = c;
++
++ if (bytes[0] < 0xc0)
++ {
++ nbytes = 1;
++ is_utf8 = FALSE;
++ }
++ else
++ {
++ bytes[1] = *symbol++;
++
++ if ((bytes[1] & 0xc0) != 0x80)
++ {
++ is_utf8 = FALSE;
++ /* Do not consume this character. It may only
++ be the first byte in the sequence that was
++ corrupt. */
++ --symbol;
++ nbytes = 1;
++ }
++ else if ((bytes[0] & 0x20) == 0)
++ {
++ is_utf8 = TRUE;
++ nbytes = 2;
++ }
++ else
++ {
++ bytes[2] = *symbol++;
++
++ if ((bytes[2] & 0xc0) != 0x80)
++ {
++ is_utf8 = FALSE;
++ symbol -= 2;
++ nbytes = 1;
++ }
++ else if ((bytes[0] & 0x10) == 0)
++ {
++ is_utf8 = TRUE;
++ nbytes = 3;
++ }
++ else
++ {
++ bytes[3] = *symbol++;
++
++ nbytes = 4;
++
++ if ((bytes[3] & 0xc0) != 0x80)
++ {
++ is_utf8 = FALSE;
++ symbol -= 3;
++ nbytes = 1;
++ }
++ else
++ is_utf8 = TRUE;
++ }
++ }
++ }
++
++ if (unicode_display == unicode_invalid)
++ is_utf8 = FALSE;
++
++ if (unicode_display == unicode_hex || ! is_utf8)
++ {
++ unsigned int i;
++
++ if (width_remaining < (nbytes * 2) + 2)
++ break;
++
++ putchar (is_utf8 ? '<' : '{');
++ printf ("0x");
++ for (i = 0; i < nbytes; i++)
++ printf ("%02x", bytes[i]);
++ putchar (is_utf8 ? '>' : '}');
++ }
++ else
++ {
++ if (unicode_display == unicode_highlight && isatty (1))
++ printf ("\x1B[31;47m"); /* Red. */
++
++ switch (nbytes)
++ {
++ case 2:
++ if (width_remaining < 6)
++ break;
++ printf ("\\u%02x%02x",
++ (bytes[0] & 0x1c) >> 2,
++ ((bytes[0] & 0x03) << 6) | (bytes[1] & 0x3f));
++ break;
++ case 3:
++ if (width_remaining < 6)
++ break;
++ printf ("\\u%02x%02x",
++ ((bytes[0] & 0x0f) << 4) | ((bytes[1] & 0x3c) >> 2),
++ ((bytes[1] & 0x03) << 6) | (bytes[2] & 0x3f));
++ break;
++ case 4:
++ if (width_remaining < 8)
++ break;
++ printf ("\\u%02x%02x%02x",
++ ((bytes[0] & 0x07) << 6) | ((bytes[1] & 0x3c) >> 2),
++ ((bytes[1] & 0x03) << 6) | ((bytes[2] & 0x3c) >> 2),
++ ((bytes[2] & 0x03) << 6) | (bytes[3] & 0x3f));
++
++ break;
++ default:
++ /* URG. */
++ break;
++ }
++
++ if (unicode_display == unicode_highlight && isatty (1))
++ printf ("\033[0m"); /* Default colour. */
++ }
++
++ if (bytes[nbytes - 1] == 0)
++ break;
+ }
+ else
+ {
+@@ -4556,6 +4702,7 @@ static struct option options[] =
+ {"syms", no_argument, 0, 's'},
+ {"silent-truncation",no_argument, 0, 'T'},
+ {"section-details", no_argument, 0, 't'},
++ {"unicode", required_argument, NULL, 'U'},
+ {"unwind", no_argument, 0, 'u'},
+ {"version-info", no_argument, 0, 'V'},
+ {"version", no_argument, 0, 'v'},
+@@ -4609,6 +4756,11 @@ usage (FILE * stream)
+ --no-demangle Do not demangle low-level symbol names. (This is the default)\n\
+ --recurse-limit Enable a demangling recursion limit. (This is the default)\n\
+ --no-recurse-limit Disable a demangling recursion limit\n\
++ -U[dlexhi] --unicode=[default|locale|escape|hex|highlight|invalid]\n\
++ Display unicode characters as determined by the current locale\n\
++ (default), escape sequences, \"<hex sequences>\", highlighted\n\
++ escape sequences, or treat them as invalid and display as\n\
++ \"{hex sequences}\"\n\
+ -n --notes Display the core notes (if present)\n\
+ -r --relocs Display the relocations (if present)\n\
+ -u --unwind Display the unwind info (if present)\n\
+@@ -4749,7 +4901,7 @@ parse_args (struct dump_data *dumpdata,
+ usage (stderr);
+
+ while ((c = getopt_long
+- (argc, argv, "ACDHILNR:STVWacdeghi:lnp:rstuvw::x:z", options, NULL)) != EOF)
++ (argc, argv, "ACDHILNR:STU:VWacdeghi:lnp:rstuvw::x:z", options, NULL)) != EOF)
+ {
+ switch (c)
+ {
+@@ -4943,6 +5095,24 @@ parse_args (struct dump_data *dumpdata,
+ case OPTION_WITH_SYMBOL_VERSIONS:
+ /* Ignored for backward compatibility. */
+ break;
++ case 'U':
++ if (optarg == NULL)
++ error (_("Missing arg to -U/--unicode")); /* Can this happen ? */
++ else if (streq (optarg, "default") || streq (optarg, "d"))
++ unicode_display = unicode_default;
++ else if (streq (optarg, "locale") || streq (optarg, "l"))
++ unicode_display = unicode_locale;
++ else if (streq (optarg, "escape") || streq (optarg, "e"))
++ unicode_display = unicode_escape;
++ else if (streq (optarg, "invalid") || streq (optarg, "i"))
++ unicode_display = unicode_invalid;
++ else if (streq (optarg, "hex") || streq (optarg, "x"))
++ unicode_display = unicode_hex;
++ else if (streq (optarg, "highlight") || streq (optarg, "h"))
++ unicode_display = unicode_highlight;
++ else
++ error (_("invalid argument to -U/--unicode: %s"), optarg);
++ break;
+
+ default:
+ /* xgettext:c-format */
+diff --git a/binutils/strings.c b/binutils/strings.c
+--- a/binutils/strings.c 2021-12-23 03:23:38.485842662 -0800
++++ b/binutils/strings.c 2021-12-23 03:30:36.586877452 -0800
+@@ -55,6 +55,19 @@
+ -T {bfdname}
+ Specify a non-default object file format.
+
++ --unicode={default|locale|invalid|hex|escape|highlight}
++ -u {d|l|i|x|e|h}
++ Determine how to handle UTF-8 unicode characters. The default
++ is no special treatment. All other versions of this option
++ only apply if the encoding is valid and enabling the option
++ implies --encoding=S.
++ The 'locale' option displays the characters according to the
++ current locale. The 'invalid' option treats them as
++ non-string characters. The 'hex' option displays them as hex
++ byte sequences. The 'escape' option displays them as escape
++ sequences and the 'highlight' option displays them as
++ coloured escape sequences.
++
+ --output-separator=sep_string
+ -s sep_string String used to separate parsed strings in output.
+ Default is newline.
+@@ -76,6 +89,22 @@
+ #include "safe-ctype.h"
+ #include "bucomm.h"
+
++#ifndef streq
++#define streq(a,b) (strcmp ((a),(b)) == 0)
++#endif
++
++typedef enum unicode_display_type
++{
++ unicode_default = 0,
++ unicode_locale,
++ unicode_escape,
++ unicode_hex,
++ unicode_highlight,
++ unicode_invalid
++} unicode_display_type;
++
++static unicode_display_type unicode_display = unicode_default;
++
+ #define STRING_ISGRAPHIC(c) \
+ ( (c) >= 0 \
+ && (c) <= 255 \
+@@ -94,7 +123,7 @@ extern int errno;
+ static int address_radix;
+
+ /* Minimum length of sequence of graphic chars to trigger output. */
+-static int string_min;
++static unsigned int string_min;
+
+ /* Whether or not we include all whitespace as a graphic char. */
+ static bfd_boolean include_all_whitespace;
+@@ -121,21 +150,22 @@ static char *output_separator;
+ static struct option long_options[] =
+ {
+ {"all", no_argument, NULL, 'a'},
++ {"bytes", required_argument, NULL, 'n'},
+ {"data", no_argument, NULL, 'd'},
++ {"encoding", required_argument, NULL, 'e'},
++ {"help", no_argument, NULL, 'h'},
++ {"include-all-whitespace", no_argument, NULL, 'w'},
++ {"output-separator", required_argument, NULL, 's'},
+ {"print-file-name", no_argument, NULL, 'f'},
+- {"bytes", required_argument, NULL, 'n'},
+ {"radix", required_argument, NULL, 't'},
+- {"include-all-whitespace", no_argument, NULL, 'w'},
+- {"encoding", required_argument, NULL, 'e'},
+ {"target", required_argument, NULL, 'T'},
+- {"output-separator", required_argument, NULL, 's'},
+- {"help", no_argument, NULL, 'h'},
++ {"unicode", required_argument, NULL, 'U'},
+ {"version", no_argument, NULL, 'v'},
+ {NULL, 0, NULL, 0}
+ };
+
+ static bfd_boolean strings_file (char *);
+-static void print_strings (const char *, FILE *, file_ptr, int, int, char *);
++static void print_strings (const char *, FILE *, file_ptr, int, char *);
+ static void usage (FILE *, int) ATTRIBUTE_NORETURN;
+
+ int main (int, char **);
+@@ -173,7 +203,7 @@ main (int argc, char **argv)
+ encoding = 's';
+ output_separator = NULL;
+
+- while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:Vv0123456789",
++ while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:U:Vv0123456789",
+ long_options, (int *) 0)) != EOF)
+ {
+ switch (optc)
+@@ -244,7 +274,24 @@ main (int argc, char **argv)
+
+ case 's':
+ output_separator = optarg;
+- break;
++ break;
++
++ case 'U':
++ if (streq (optarg, "default") || streq (optarg, "d"))
++ unicode_display = unicode_default;
++ else if (streq (optarg, "locale") || streq (optarg, "l"))
++ unicode_display = unicode_locale;
++ else if (streq (optarg, "escape") || streq (optarg, "e"))
++ unicode_display = unicode_escape;
++ else if (streq (optarg, "invalid") || streq (optarg, "i"))
++ unicode_display = unicode_invalid;
++ else if (streq (optarg, "hex") || streq (optarg, "x"))
++ unicode_display = unicode_hex;
++ else if (streq (optarg, "highlight") || streq (optarg, "h"))
++ unicode_display = unicode_highlight;
++ else
++ fatal (_("invalid argument to -U/--unicode: %s"), optarg);
++ break;
+
+ case 'V':
+ case 'v':
+@@ -260,6 +307,9 @@ main (int argc, char **argv)
+ }
+ }
+
++ if (unicode_display != unicode_default)
++ encoding = 'S';
++
+ if (numeric_opt != 0)
+ {
+ string_min = (int) strtoul (argv[numeric_opt - 1] + 1, &s, 0);
+@@ -295,14 +345,14 @@ main (int argc, char **argv)
+ {
+ datasection_only = FALSE;
+ SET_BINARY (fileno (stdin));
+- print_strings ("{standard input}", stdin, 0, 0, 0, (char *) NULL);
++ print_strings ("{standard input}", stdin, 0, 0, (char *) NULL);
+ files_given = TRUE;
+ }
+ else
+ {
+ for (; optind < argc; ++optind)
+ {
+- if (strcmp (argv[optind], "-") == 0)
++ if (streq (argv[optind], "-"))
+ datasection_only = FALSE;
+ else
+ {
+@@ -344,7 +394,7 @@ strings_a_section (bfd *abfd, asection *
+ }
+
+ *got_a_section = TRUE;
+- print_strings (filename, NULL, sect->filepos, 0, sectsize, (char *) mem);
++ print_strings (filename, NULL, sect->filepos, sectsize, (char *) mem);
+ free (mem);
+ }
+
+@@ -429,7 +479,7 @@ strings_file (char *file)
+ return FALSE;
+ }
+
+- print_strings (file, stream, (file_ptr) 0, 0, 0, (char *) 0);
++ print_strings (file, stream, (file_ptr) 0, 0, (char *) NULL);
+
+ if (fclose (stream) == EOF)
+ {
+@@ -553,11 +603,632 @@ unget_part_char (long c, file_ptr *addre
+ }
+ }
+ }
++
++
++static void
++print_filename_and_address (const char * filename, file_ptr address)
++{
++ if (print_filenames)
++ printf ("%s: ", filename);
++
++ if (! print_addresses)
++ return;
++
++ switch (address_radix)
++ {
++ case 8:
++ if (sizeof (address) > sizeof (long))
++ {
++#ifndef __MSVCRT__
++ printf ("%7llo ", (unsigned long long) address);
++#else
++ printf ("%7I64o ", (unsigned long long) address);
++#endif
++ }
++ else
++ printf ("%7lo ", (unsigned long) address);
++ break;
++
++ case 10:
++ if (sizeof (address) > sizeof (long))
++ {
++#ifndef __MSVCRT__
++ printf ("%7llu ", (unsigned long long) address);
++#else
++ printf ("%7I64d ", (unsigned long long) address);
++#endif
++ }
++ else
++ printf ("%7ld ", (long) address);
++ break;
++
++ case 16:
++ if (sizeof (address) > sizeof (long))
++ {
++#ifndef __MSVCRT__
++ printf ("%7llx ", (unsigned long long) address);
++#else
++ printf ("%7I64x ", (unsigned long long) address);
++#endif
++ }
++ else
++ printf ("%7lx ", (unsigned long) address);
++ break;
++ }
++}
++
++/* Return non-zero if the bytes starting at BUFFER form a valid UTF-8 encoding.
++ If the encoding is valid then returns the number of bytes it uses. */
++
++static unsigned int
++is_valid_utf8 (const unsigned char * buffer, unsigned long buflen)
++{
++ if (buffer[0] < 0xc0)
++ return 0;
++
++ if (buflen < 2)
++ return 0;
++
++ if ((buffer[1] & 0xc0) != 0x80)
++ return 0;
++
++ if ((buffer[0] & 0x20) == 0)
++ return 2;
++
++ if (buflen < 3)
++ return 0;
++
++ if ((buffer[2] & 0xc0) != 0x80)
++ return 0;
++
++ if ((buffer[0] & 0x10) == 0)
++ return 3;
++
++ if (buflen < 4)
++ return 0;
++
++ if ((buffer[3] & 0xc0) != 0x80)
++ return 0;
++
++ return 4;
++}
++
++/* Display a UTF-8 encoded character in BUFFER according to the setting
++ of unicode_display. The character is known to be valid.
++ Returns the number of bytes consumed. */
++
++static unsigned int
++display_utf8_char (const unsigned char * buffer)
++{
++ unsigned int j;
++ unsigned int utf8_len;
++
++ switch (buffer[0] & 0x30)
++ {
++ case 0x00:
++ case 0x10:
++ utf8_len = 2;
++ break;
++ case 0x20:
++ utf8_len = 3;
++ break;
++ default:
++ utf8_len = 4;
++ }
++
++ switch (unicode_display)
++ {
++ default:
++ fprintf (stderr, "ICE: unexpected unicode display type\n");
++ break;
++
++ case unicode_escape:
++ case unicode_highlight:
++ if (unicode_display == unicode_highlight && isatty (1))
++ printf ("\x1B[31;47m"); /* Red. */
++
++ switch (utf8_len)
++ {
++ case 2:
++ printf ("\\u%02x%02x",
++ ((buffer[0] & 0x1c) >> 2),
++ ((buffer[0] & 0x03) << 6) | (buffer[1] & 0x3f));
++ break;
++
++ case 3:
++ printf ("\\u%02x%02x",
++ ((buffer[0] & 0x0f) << 4) | ((buffer[1] & 0x3c) >> 2),
++ ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3f)));
++ break;
++
++ case 4:
++ printf ("\\u%02x%02x%02x",
++ ((buffer[0] & 0x07) << 6) | ((buffer[1] & 0x3c) >> 2),
++ ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3c) >> 2),
++ ((buffer[2] & 0x03) << 6) | ((buffer[3] & 0x3f)));
++ break;
++ default:
++ /* URG. */
++ break;
++ }
++
++ if (unicode_display == unicode_highlight && isatty (1))
++ printf ("\033[0m"); /* Default colour. */
++ break;
++
++ case unicode_hex:
++ putchar ('<');
++ printf ("0x");
++ for (j = 0; j < utf8_len; j++)
++ printf ("%02x", buffer [j]);
++ putchar ('>');
++ break;
++
++ case unicode_locale:
++ printf ("%.1s", buffer);
++ break;
++ }
++
++ return utf8_len;
++}
++
++/* Display strings in BUFFER. Treat any UTF-8 encoded characters encountered
++ according to the setting of the unicode_display variable. The buffer
++ contains BUFLEN bytes.
++
++ Display the characters as if they started at ADDRESS and are contained in
++ FILENAME. */
++
++static void
++print_unicode_buffer (const char * filename,
++ file_ptr address,
++ const unsigned char * buffer,
++ unsigned long buflen)
++{
++ /* Paranoia checks... */
++ if (filename == NULL
++ || buffer == NULL
++ || unicode_display == unicode_default
++ || encoding != 'S'
++ || encoding_bytes != 1)
++ {
++ fprintf (stderr, "ICE: bad arguments to print_unicode_buffer\n");
++ return;
++ }
++
++ if (buflen == 0)
++ return;
++
++ /* We must only display strings that are at least string_min *characters*
++ long. So we scan the buffer in two stages. First we locate the start
++ of a potential string. Then we walk along it until we have found
++ string_min characters. Then we go back to the start point and start
++ displaying characters according to the unicode_display setting. */
++
++ unsigned long start_point = 0;
++ unsigned long i = 0;
++ unsigned int char_len = 1;
++ unsigned int num_found = 0;
++
++ for (i = 0; i < buflen; i += char_len)
++ {
++ int c = buffer[i];
++
++ char_len = 1;
++
++ /* Find the first potential character of a string. */
++ if (! STRING_ISGRAPHIC (c))
++ {
++ num_found = 0;
++ continue;
++ }
++
++ if (c > 126)
++ {
++ if (c < 0xc0)
++ {
++ num_found = 0;
++ continue;
++ }
++
++ if ((char_len = is_valid_utf8 (buffer + i, buflen - i)) == 0)
++ {
++ char_len = 1;
++ num_found = 0;
++ continue;
++ }
++
++ if (unicode_display == unicode_invalid)
++ {
++ /* We have found a valid UTF-8 character, but we treat it as non-graphic. */
++ num_found = 0;
++ continue;
++ }
++ }
++
++ if (num_found == 0)
++ /* We have found a potential starting point for a string. */
++ start_point = i;
++
++ ++ num_found;
++
++ if (num_found >= string_min)
++ break;
++ }
++
++ if (num_found < string_min)
++ return;
++
++ print_filename_and_address (filename, address + start_point);
++
++ /* We have found string_min characters. Display them and any
++ more that follow. */
++ for (i = start_point; i < buflen; i += char_len)
++ {
++ int c = buffer[i];
++
++ char_len = 1;
++
++ if (! STRING_ISGRAPHIC (c))
++ break;
++ else if (c < 127)
++ putchar (c);
++ else if (! is_valid_utf8 (buffer + i, buflen - i))
++ break;
++ else if (unicode_display == unicode_invalid)
++ break;
++ else
++ char_len = display_utf8_char (buffer + i);
++ }
++
++ if (output_separator)
++ fputs (output_separator, stdout);
++ else
++ putchar ('\n');
++
++ /* FIXME: Using tail recursion here is lazy programming... */
++ print_unicode_buffer (filename, address + i, buffer + i, buflen - i);
++}
++
++static int
++get_unicode_byte (FILE * stream,
++ unsigned char * putback,
++ unsigned int * num_putback,
++ unsigned int * num_read)
++{
++ if (* num_putback > 0)
++ {
++ * num_putback = * num_putback - 1;
++ return putback [* num_putback];
++ }
++
++ * num_read = * num_read + 1;
++
++#if defined(HAVE_GETC_UNLOCKED) && HAVE_DECL_GETC_UNLOCKED
++ return getc_unlocked (stream);
++#else
++ return getc (stream);
++#endif
++}
++
++/* Helper function for print_unicode_stream. */
++
++static void
++print_unicode_stream_body (const char * filename,
++ file_ptr address,
++ FILE * stream,
++ unsigned char * putback_buf,
++ unsigned int num_putback,
++ unsigned char * print_buf)
++{
++ /* It would be nice if we could just read the stream into a buffer
++ and then process if with print_unicode_buffer. But the input
++ might be huge or it might time-locked (eg stdin). So instead
++ we go one byte at a time... */
++
++ file_ptr start_point = 0;
++ unsigned int num_read = 0;
++ unsigned int num_chars = 0;
++ unsigned int num_print = 0;
++ int c;
++
++ /* Find a series of string_min characters. Put them into print_buf. */
++ do
++ {
++ if (num_chars >= string_min)
++ break;
++
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++
++ if (! STRING_ISGRAPHIC (c))
++ {
++ num_chars = num_print = 0;
++ continue;
++ }
++
++ if (num_chars == 0)
++ start_point = num_read - 1;
++
++ if (c < 127)
++ {
++ print_buf[num_print] = c;
++ num_chars ++;
++ num_print ++;
++ continue;
++ }
++
++ if (c < 0xc0)
++ {
++ num_chars = num_print = 0;
++ continue;
++ }
++
++ /* We *might* have a UTF-8 sequence. Time to start peeking. */
++ char utf8[4];
++
++ utf8[0] = c;
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[1] = c;
++
++ if ((utf8[1] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[1];
++ num_chars = num_print = 0;
++ continue;
++ }
++ else if ((utf8[0] & 0x20) == 0)
++ {
++ /* A valid 2-byte UTF-8 encoding. */
++ if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[1];
++ num_chars = num_print = 0;
++ }
++ else
++ {
++ print_buf[num_print ++] = utf8[0];
++ print_buf[num_print ++] = utf8[1];
++ num_chars ++;
++ }
++ continue;
++ }
++
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[2] = c;
++
++ if ((utf8[2] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ num_chars = num_print = 0;
++ continue;
++ }
++ else if ((utf8[0] & 0x10) == 0)
++ {
++ /* A valid 3-byte UTF-8 encoding. */
++ if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ num_chars = num_print = 0;
++ }
++ else
++ {
++ print_buf[num_print ++] = utf8[0];
++ print_buf[num_print ++] = utf8[1];
++ print_buf[num_print ++] = utf8[2];
++ num_chars ++;
++ }
++ continue;
++ }
++
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[3] = c;
++
++ if ((utf8[3] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[3];
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ num_chars = num_print = 0;
++ }
++ /* We have a valid 4-byte UTF-8 encoding. */
++ else if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[3];
++ putback_buf[num_putback++] = utf8[1];
++ putback_buf[num_putback++] = utf8[2];
++ num_chars = num_print = 0;
++ }
++ else
++ {
++ print_buf[num_print ++] = utf8[0];
++ print_buf[num_print ++] = utf8[1];
++ print_buf[num_print ++] = utf8[2];
++ print_buf[num_print ++] = utf8[3];
++ num_chars ++;
++ }
++ }
++ while (1);
++
++ if (num_chars >= string_min)
++ {
++ /* We know that we have string_min valid characters in print_buf,
++ and there may be more to come in the stream. Start displaying
++ them. */
++
++ print_filename_and_address (filename, address + start_point);
++
++ unsigned int i;
++ for (i = 0; i < num_print;)
++ {
++ if (print_buf[i] < 127)
++ putchar (print_buf[i++]);
++ else
++ i += display_utf8_char (print_buf + i);
++ }
++
++ /* OK so now we have to start read unchecked bytes. */
++
++ /* Find a series of string_min characters. Put them into print_buf. */
++ do
++ {
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++
++ if (! STRING_ISGRAPHIC (c))
++ break;
++
++ if (c < 127)
++ {
++ putchar (c);
++ continue;
++ }
++
++ if (c < 0xc0)
++ break;
++
++ /* We *might* have a UTF-8 sequence. Time to start peeking. */
++ unsigned char utf8[4];
++
++ utf8[0] = c;
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[1] = c;
++
++ if ((utf8[1] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else if ((utf8[0] & 0x20) == 0)
++ {
++ /* Valid 2-byte UTF-8. */
++ if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else
++ {
++ (void) display_utf8_char (utf8);
++ continue;
++ }
++ }
++
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[2] = c;
++
++ if ((utf8[2] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else if ((utf8[0] & 0x10) == 0)
++ {
++ /* Valid 3-byte UTF-8. */
++ if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else
++ {
++ (void) display_utf8_char (utf8);
++ continue;
++ }
++ }
++
++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
++ if (c == EOF)
++ break;
++ utf8[3] = c;
++
++ if ((utf8[3] & 0xc0) != 0x80)
++ {
++ /* Invalid UTF-8. */
++ putback_buf[num_putback++] = utf8[3];
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else if (unicode_display == unicode_invalid)
++ {
++ putback_buf[num_putback++] = utf8[3];
++ putback_buf[num_putback++] = utf8[2];
++ putback_buf[num_putback++] = utf8[1];
++ break;
++ }
++ else
++ /* A valid 4-byte UTF-8 encoding. */
++ (void) display_utf8_char (utf8);
++ }
++ while (1);
++
++ if (output_separator)
++ fputs (output_separator, stdout);
++ else
++ putchar ('\n');
++ }
++
++ if (c != EOF)
++ /* FIXME: Using tail recursion here is lazy, but it works. */
++ print_unicode_stream_body (filename, address + num_read, stream, putback_buf, num_putback, print_buf);
++}
++
++/* Display strings read in from STREAM. Treat any UTF-8 encoded characters
++ encountered according to the setting of the unicode_display variable.
++ The stream is positioned at ADDRESS and is attached to FILENAME. */
++
++static void
++print_unicode_stream (const char * filename,
++ file_ptr address,
++ FILE * stream)
++{
++ /* Paranoia checks... */
++ if (filename == NULL
++ || stream == NULL
++ || unicode_display == unicode_default
++ || encoding != 'S'
++ || encoding_bytes != 1)
++ {
++ fprintf (stderr, "ICE: bad arguments to print_unicode_stream\n");
++ return;
++ }
++
++ /* Allocate space for string_min 4-byte utf-8 characters. */
++ unsigned char * print_buf = xmalloc ((4 * string_min) + 1);
++ /* We should never have to put back more than 4 bytes. */
++ unsigned char putback_buf[5];
++ unsigned int num_putback = 0;
++
++ print_unicode_stream_body (filename, address, stream, putback_buf, num_putback, print_buf);
++ free (print_buf);
++}
++
+
+ /* Find the strings in file FILENAME, read from STREAM.
+ Assume that STREAM is positioned so that the next byte read
+ is at address ADDRESS in the file.
+- Stop reading at address STOP_POINT in the file, if nonzero.
+
+ If STREAM is NULL, do not read from it.
+ The caller can supply a buffer of characters
+@@ -568,20 +1239,29 @@ unget_part_char (long c, file_ptr *addre
+
+ static void
+ print_strings (const char *filename, FILE *stream, file_ptr address,
+- int stop_point, int magiccount, char *magic)
++ int magiccount, char *magic)
+ {
++ if (unicode_display != unicode_default)
++ {
++ if (magic != NULL)
++ print_unicode_buffer (filename, address,
++ (const unsigned char *) magic, magiccount);
++
++ if (stream != NULL)
++ print_unicode_stream (filename, address, stream);
++ return;
++ }
++
+ char *buf = (char *) xmalloc (sizeof (char) * (string_min + 1));
+
+ while (1)
+ {
+ file_ptr start;
+- int i;
++ unsigned int i;
+ long c;
+
+ /* See if the next `string_min' chars are all graphic chars. */
+ tryline:
+- if (stop_point && address >= stop_point)
+- break;
+ start = address;
+ for (i = 0; i < string_min; i++)
+ {
+@@ -604,69 +1284,7 @@ print_strings (const char *filename, FIL
+ /* We found a run of `string_min' graphic characters. Print up
+ to the next non-graphic character. */
+
+- if (print_filenames)
+- printf ("%s: ", filename);
+- if (print_addresses)
+- switch (address_radix)
+- {
+- case 8:
+-#ifdef HAVE_LONG_LONG
+- if (sizeof (start) > sizeof (long))
+- {
+-# ifndef __MSVCRT__
+- printf ("%7llo ", (unsigned long long) start);
+-# else
+- printf ("%7I64o ", (unsigned long long) start);
+-# endif
+- }
+- else
+-#elif !BFD_HOST_64BIT_LONG
+- if (start != (unsigned long) start)
+- printf ("++%7lo ", (unsigned long) start);
+- else
+-#endif
+- printf ("%7lo ", (unsigned long) start);
+- break;
+-
+- case 10:
+-#ifdef HAVE_LONG_LONG
+- if (sizeof (start) > sizeof (long))
+- {
+-# ifndef __MSVCRT__
+- printf ("%7llu ", (unsigned long long) start);
+-# else
+- printf ("%7I64d ", (unsigned long long) start);
+-# endif
+- }
+- else
+-#elif !BFD_HOST_64BIT_LONG
+- if (start != (unsigned long) start)
+- printf ("++%7lu ", (unsigned long) start);
+- else
+-#endif
+- printf ("%7ld ", (long) start);
+- break;
+-
+- case 16:
+-#ifdef HAVE_LONG_LONG
+- if (sizeof (start) > sizeof (long))
+- {
+-# ifndef __MSVCRT__
+- printf ("%7llx ", (unsigned long long) start);
+-# else
+- printf ("%7I64x ", (unsigned long long) start);
+-# endif
+- }
+- else
+-#elif !BFD_HOST_64BIT_LONG
+- if (start != (unsigned long) start)
+- printf ("%lx%8.8lx ", (unsigned long) (start >> 32),
+- (unsigned long) (start & 0xffffffff));
+- else
+-#endif
+- printf ("%7lx ", (unsigned long) start);
+- break;
+- }
++ print_filename_and_address (filename, start);
+
+ buf[i] = '\0';
+ fputs (buf, stdout);
+@@ -718,6 +1336,8 @@ usage (FILE *stream, int status)
+ -T --target=<BFDNAME> Specify the binary file format\n\
+ -e --encoding={s,S,b,l,B,L} Select character size and endianness:\n\
+ s = 7-bit, S = 8-bit, {b,l} = 16-bit, {B,L} = 32-bit\n\
++ --unicode={default|show|invalid|hex|escape|highlight}\n\
++ -u {d|s|i|x|e|h} Specify how to treat UTF-8 encoded unicode characters\n\
+ -s --output-separator=<string> String used to separate strings in output.\n\
+ @<file> Read options from <file>\n\
+ -h --help Display this information\n\
diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch
new file mode 100644
index 0000000000..f118e2599b
--- /dev/null
+++ b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch
@@ -0,0 +1,255 @@
+From 161e87d12167b1e36193385485c1f6ce92f74f02 Mon Sep 17 00:00:00 2001
+From: Alan Modra <amodra@gmail.com>
+Date: Wed, 15 Dec 2021 11:48:42 +1030
+Subject: [PATCH] PR28694, Out-of-bounds write in stab_xcoff_builtin_type
+
+ PR 28694
+ * stabs.c (stab_xcoff_builtin_type): Make typenum unsigned.
+ Negate typenum earlier, simplifying bounds checking. Correct
+ off-by-one indexing. Adjust switch cases.
+
+
+CVE: CVE-2021-45078
+Upstream-Status: Backport [https://sourceware.org/git/?p=binutils-gdb.git;a=patch;h=161e87d12167b1e36193385485c1f6ce92f74f02]
+
+Signed-off-by: Sundeep KOKKONDA <sundeep.kokkonda@gmail.com>
+---
+ binutils/stabs.c | 87 ++++++++++++++++++++++++------------------------
+ 1 file changed, 43 insertions(+), 44 deletions(-)
+
+
+diff --git a/binutils/stabs.c b/binutils/stabs.c
+index 274bfb0e7fa..83ee3ea5fa4 100644
+--- a/binutils/stabs.c
++++ b/binutils/stabs.c
+@@ -202,7 +202,7 @@ static debug_type stab_find_type (void *, struct stab_handle *, const int *);
+ static bfd_boolean stab_record_type
+ (void *, struct stab_handle *, const int *, debug_type);
+ static debug_type stab_xcoff_builtin_type
+- (void *, struct stab_handle *, int);
++ (void *, struct stab_handle *, unsigned int);
+ static debug_type stab_find_tagged_type
+ (void *, struct stab_handle *, const char *, int, enum debug_type_kind);
+ static debug_type *stab_demangle_argtypes
+@@ -3496,166 +3496,167 @@ stab_record_type (void *dhandle ATTRIBUTE_UNUSED, struct stab_handle *info,
+
+ static debug_type
+ stab_xcoff_builtin_type (void *dhandle, struct stab_handle *info,
+- int typenum)
++ unsigned int typenum)
+ {
+ debug_type rettype;
+ const char *name;
+
+- if (typenum >= 0 || typenum < -XCOFF_TYPE_COUNT)
++ typenum = -typenum - 1;
++ if (typenum >= XCOFF_TYPE_COUNT)
+ {
+- fprintf (stderr, _("Unrecognized XCOFF type %d\n"), typenum);
++ fprintf (stderr, _("Unrecognized XCOFF type %d\n"), -typenum - 1);
+ return DEBUG_TYPE_NULL;
+ }
+- if (info->xcoff_types[-typenum] != NULL)
+- return info->xcoff_types[-typenum];
++ if (info->xcoff_types[typenum] != NULL)
++ return info->xcoff_types[typenum];
+
+- switch (-typenum)
++ switch (typenum)
+ {
+- case 1:
++ case 0:
+ /* The size of this and all the other types are fixed, defined
+ by the debugging format. */
+ name = "int";
+ rettype = debug_make_int_type (dhandle, 4, FALSE);
+ break;
+- case 2:
++ case 1:
+ name = "char";
+ rettype = debug_make_int_type (dhandle, 1, FALSE);
+ break;
+- case 3:
++ case 2:
+ name = "short";
+ rettype = debug_make_int_type (dhandle, 2, FALSE);
+ break;
+- case 4:
++ case 3:
+ name = "long";
+ rettype = debug_make_int_type (dhandle, 4, FALSE);
+ break;
+- case 5:
++ case 4:
+ name = "unsigned char";
+ rettype = debug_make_int_type (dhandle, 1, TRUE);
+ break;
+- case 6:
++ case 5:
+ name = "signed char";
+ rettype = debug_make_int_type (dhandle, 1, FALSE);
+ break;
+- case 7:
++ case 6:
+ name = "unsigned short";
+ rettype = debug_make_int_type (dhandle, 2, TRUE);
+ break;
+- case 8:
++ case 7:
+ name = "unsigned int";
+ rettype = debug_make_int_type (dhandle, 4, TRUE);
+ break;
+- case 9:
++ case 8:
+ name = "unsigned";
+ rettype = debug_make_int_type (dhandle, 4, TRUE);
+ break;
+- case 10:
++ case 9:
+ name = "unsigned long";
+ rettype = debug_make_int_type (dhandle, 4, TRUE);
+ break;
+- case 11:
++ case 10:
+ name = "void";
+ rettype = debug_make_void_type (dhandle);
+ break;
+- case 12:
++ case 11:
+ /* IEEE single precision (32 bit). */
+ name = "float";
+ rettype = debug_make_float_type (dhandle, 4);
+ break;
+- case 13:
++ case 12:
+ /* IEEE double precision (64 bit). */
+ name = "double";
+ rettype = debug_make_float_type (dhandle, 8);
+ break;
+- case 14:
++ case 13:
+ /* This is an IEEE double on the RS/6000, and different machines
+ with different sizes for "long double" should use different
+ negative type numbers. See stabs.texinfo. */
+ name = "long double";
+ rettype = debug_make_float_type (dhandle, 8);
+ break;
+- case 15:
++ case 14:
+ name = "integer";
+ rettype = debug_make_int_type (dhandle, 4, FALSE);
+ break;
+- case 16:
++ case 15:
+ name = "boolean";
+ rettype = debug_make_bool_type (dhandle, 4);
+ break;
+- case 17:
++ case 16:
+ name = "short real";
+ rettype = debug_make_float_type (dhandle, 4);
+ break;
+- case 18:
++ case 17:
+ name = "real";
+ rettype = debug_make_float_type (dhandle, 8);
+ break;
+- case 19:
++ case 18:
+ /* FIXME */
+ name = "stringptr";
+ rettype = NULL;
+ break;
+- case 20:
++ case 19:
+ /* FIXME */
+ name = "character";
+ rettype = debug_make_int_type (dhandle, 1, TRUE);
+ break;
+- case 21:
++ case 20:
+ name = "logical*1";
+ rettype = debug_make_bool_type (dhandle, 1);
+ break;
+- case 22:
++ case 21:
+ name = "logical*2";
+ rettype = debug_make_bool_type (dhandle, 2);
+ break;
+- case 23:
++ case 22:
+ name = "logical*4";
+ rettype = debug_make_bool_type (dhandle, 4);
+ break;
+- case 24:
++ case 23:
+ name = "logical";
+ rettype = debug_make_bool_type (dhandle, 4);
+ break;
+- case 25:
++ case 24:
+ /* Complex type consisting of two IEEE single precision values. */
+ name = "complex";
+ rettype = debug_make_complex_type (dhandle, 8);
+ break;
+- case 26:
++ case 25:
+ /* Complex type consisting of two IEEE double precision values. */
+ name = "double complex";
+ rettype = debug_make_complex_type (dhandle, 16);
+ break;
+- case 27:
++ case 26:
+ name = "integer*1";
+ rettype = debug_make_int_type (dhandle, 1, FALSE);
+ break;
+- case 28:
++ case 27:
+ name = "integer*2";
+ rettype = debug_make_int_type (dhandle, 2, FALSE);
+ break;
+- case 29:
++ case 28:
+ name = "integer*4";
+ rettype = debug_make_int_type (dhandle, 4, FALSE);
+ break;
+- case 30:
++ case 29:
+ /* FIXME */
+ name = "wchar";
+ rettype = debug_make_int_type (dhandle, 2, FALSE);
+ break;
+- case 31:
++ case 30:
+ name = "long long";
+ rettype = debug_make_int_type (dhandle, 8, FALSE);
+ break;
+- case 32:
++ case 31:
+ name = "unsigned long long";
+ rettype = debug_make_int_type (dhandle, 8, TRUE);
+ break;
+- case 33:
++ case 32:
+ name = "logical*8";
+ rettype = debug_make_bool_type (dhandle, 8);
+ break;
+- case 34:
++ case 33:
+ name = "integer*8";
+ rettype = debug_make_int_type (dhandle, 8, FALSE);
+ break;
+@@ -3664,9 +3665,7 @@ stab_xcoff_builtin_type (void *dhandle, struct stab_handle *info,
+ }
+
+ rettype = debug_name_type (dhandle, name, rettype);
+-
+- info->xcoff_types[-typenum] = rettype;
+-
++ info->xcoff_types[typenum] = rettype;
+ return rettype;
+ }
+
+--
+2.27.0
+
diff --git a/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch
deleted file mode 100644
index 3771f571eb..0000000000
--- a/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch
+++ /dev/null
@@ -1,170 +0,0 @@
-From d3edaa91d4cf7202ec14342410194841e2f67f12 Mon Sep 17 00:00:00 2001
-From: Alan Modra <amodra@gmail.com>
-Date: Fri, 26 Feb 2021 11:30:32 +1030
-Subject: [PATCH] Reinstate various pieces backed out from smart_rename changes
-
-In the interests of a stable release various last minute smart_rename
-patches were backed out of the 2.36 branch. The main reason to
-reinstate some of those backed out changes here is to make necessary
-followup fixes to commit 8e03235147a9 simple cherry-picks from
-mainline. A secondary reason is that ar -M support isn't fixed for
-pr26945 without this patch.
-
- PR 26945
- * ar.c: Don't include libbfd.h.
- (write_archive): Replace xmalloc+strcpy with xstrdup.
- * arsup.c (temp_name, real_ofd): New static variables.
- (ar_open): Use make_tempname and bfd_fdopenw.
- (ar_save): Adjust to suit ar_open changes.
- * objcopy.c: Don't include libbfd.h.
- * rename.c: Rename and reorder variables.
-
-(cherry picked from commit 95b91a043aeaeb546d2fea556d84a2de1e917770)
-
-Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=d3edaa91d4cf7202ec14342410194841e2f67f12]
-CVE: CVE-2021-20197
-Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com>
----
- binutils/ar.c | 4 +---
- binutils/arsup.c | 37 +++++++++++++++++++++++++------------
- binutils/objcopy.c | 1 -
- binutils/rename.c | 6 +++---
- 5 files changed, 42 insertions(+), 19 deletions(-)
-
-diff --git a/binutils/ar.c b/binutils/ar.c
-index 3a91708b51c..44df48c5c67 100644
---- a/binutils/ar.c
-+++ b/binutils/ar.c
-@@ -25,7 +25,6 @@
-
- #include "sysdep.h"
- #include "bfd.h"
--#include "libbfd.h"
- #include "libiberty.h"
- #include "progress.h"
- #include "getopt.h"
-@@ -1255,8 +1254,7 @@ write_archive (bfd *iarch)
- bfd *contents_head = iarch->archive_next;
- int ofd = -1;
-
-- old_name = (char *) xmalloc (strlen (bfd_get_filename (iarch)) + 1);
-- strcpy (old_name, bfd_get_filename (iarch));
-+ old_name = xstrdup (bfd_get_filename (iarch));
- new_name = make_tempname (old_name, &ofd);
-
- if (new_name == NULL)
-diff --git a/binutils/arsup.c b/binutils/arsup.c
-index 0a1f63f6456..f7ce8f0bc82 100644
---- a/binutils/arsup.c
-+++ b/binutils/arsup.c
-@@ -42,6 +42,8 @@ extern int deterministic;
-
- static bfd *obfd;
- static char *real_name;
-+static char *temp_name;
-+static int real_ofd;
- static FILE *outfile;
-
- static void
-@@ -149,27 +151,24 @@ maybequit (void)
- void
- ar_open (char *name, int t)
- {
-- char *tname;
-- const char *bname = lbasename (name);
-- real_name = name;
-+ real_name = xstrdup (name);
-+ temp_name = make_tempname (real_name, &real_ofd);
-
-- /* Prepend tmp- to the beginning, to avoid file-name clashes after
-- truncation on filesystems with limited namespaces (DOS). */
-- if (asprintf (&tname, "%.*stmp-%s", (int) (bname - name), name, bname) == -1)
-+ if (temp_name == NULL)
- {
-- fprintf (stderr, _("%s: Can't allocate memory for temp name (%s)\n"),
-+ fprintf (stderr, _("%s: Can't open temporary file (%s)\n"),
- program_name, strerror(errno));
- maybequit ();
- return;
- }
-
-- obfd = bfd_openw (tname, NULL);
-+ obfd = bfd_fdopenw (temp_name, NULL, real_ofd);
-
- if (!obfd)
- {
- fprintf (stderr,
- _("%s: Can't open output archive %s\n"),
-- program_name, tname);
-+ program_name, temp_name);
-
- maybequit ();
- }
-@@ -344,16 +343,30 @@ ar_save (void)
- }
- else
- {
-- char *ofilename = xstrdup (bfd_get_filename (obfd));
-+ struct stat target_stat;
-
- if (deterministic > 0)
- obfd->flags |= BFD_DETERMINISTIC_OUTPUT;
-
- bfd_close (obfd);
-
-- smart_rename (ofilename, real_name, NULL);
-+ if (stat (real_name, &target_stat) != 0)
-+ {
-+ /* The temp file created in ar_open has mode 0600 as per mkstemp.
-+ Create the real empty output file here so smart_rename will
-+ update the mode according to the process umask. */
-+ obfd = bfd_openw (real_name, NULL);
-+ if (obfd != NULL)
-+ {
-+ bfd_set_format (obfd, bfd_archive);
-+ bfd_close (obfd);
-+ }
-+ }
-+
-+ smart_rename (temp_name, real_name, NULL);
- obfd = 0;
-- free (ofilename);
-+ free (temp_name);
-+ free (real_name);
- }
- }
-
-diff --git a/binutils/objcopy.c b/binutils/objcopy.c
-index 07a872b5a80..73aa8bc2514 100644
---- a/binutils/objcopy.c
-+++ b/binutils/objcopy.c
-@@ -20,7 +20,6 @@
-
- #include "sysdep.h"
- #include "bfd.h"
--#include "libbfd.h"
- #include "progress.h"
- #include "getopt.h"
- #include "libiberty.h"
-diff --git a/binutils/rename.c b/binutils/rename.c
-index f471b45fd3f..2ff092ee22b 100644
---- a/binutils/rename.c
-+++ b/binutils/rename.c
-@@ -130,11 +130,11 @@ int
- smart_rename (const char *from, const char *to,
- struct stat *target_stat ATTRIBUTE_UNUSED)
- {
-- bfd_boolean exists;
-- struct stat s;
- int ret = 0;
-+ struct stat to_stat;
-+ bfd_boolean exists;
-
-- exists = lstat (to, &s) == 0;
-+ exists = lstat (to, &to_stat) == 0;
-
- #if defined (_WIN32) && !defined (__CYGWIN32__)
- /* Win32, unlike unix, will not erase `to' in `rename(from, to)' but
---
-2.31.1
-
diff --git a/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch
deleted file mode 100644
index 082b28b29c..0000000000
--- a/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch
+++ /dev/null
@@ -1,171 +0,0 @@
-From 8b69e61d4be276bb862698aaafddc3e779d23c8f Mon Sep 17 00:00:00 2001
-From: Alan Modra <amodra@gmail.com>
-Date: Tue, 23 Feb 2021 09:37:39 +1030
-Subject: [PATCH] PR27456, lstat in rename.c on MinGW
-
- PR 27456
- * rename.c: Tidy throughout.
- (smart_rename): Always copy. Remove windows specific code.
-
-(cherry picked from commit cca8873dd5a6015d5557ea44bc1ea9c252435a29)
-
-Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=8b69e61d4be276bb862698aaafddc3e779d23c8f]
-CVE: CVE-2021-20197
-Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com>
----
- binutils/rename.c | 111 ++++++++++++++-------------------------------
- 2 files changed, 40 insertions(+), 76 deletions(-)
-
-diff --git a/binutils/rename.c b/binutils/rename.c
-index 2ff092ee22b..72a9323d72c 100644
---- a/binutils/rename.c
-+++ b/binutils/rename.c
-@@ -24,14 +24,9 @@
-
- #ifdef HAVE_GOOD_UTIME_H
- #include <utime.h>
--#else /* ! HAVE_GOOD_UTIME_H */
--#ifdef HAVE_UTIMES
-+#elif defined HAVE_UTIMES
- #include <sys/time.h>
--#endif /* HAVE_UTIMES */
--#endif /* ! HAVE_GOOD_UTIME_H */
--
--#if ! defined (_WIN32) || defined (__CYGWIN32__)
--static int simple_copy (const char *, const char *);
-+#endif
-
- /* The number of bytes to copy at once. */
- #define COPY_BUF 8192
-@@ -82,7 +77,6 @@ simple_copy (const char *from, const char *to)
- }
- return 0;
- }
--#endif /* __CYGWIN32__ or not _WIN32 */
-
- /* Set the times of the file DESTINATION to be the same as those in
- STATBUF. */
-@@ -91,87 +85,52 @@ void
- set_times (const char *destination, const struct stat *statbuf)
- {
- int result;
--
-- {
- #ifdef HAVE_GOOD_UTIME_H
-- struct utimbuf tb;
--
-- tb.actime = statbuf->st_atime;
-- tb.modtime = statbuf->st_mtime;
-- result = utime (destination, &tb);
--#else /* ! HAVE_GOOD_UTIME_H */
--#ifndef HAVE_UTIMES
-- long tb[2];
--
-- tb[0] = statbuf->st_atime;
-- tb[1] = statbuf->st_mtime;
-- result = utime (destination, tb);
--#else /* HAVE_UTIMES */
-- struct timeval tv[2];
--
-- tv[0].tv_sec = statbuf->st_atime;
-- tv[0].tv_usec = 0;
-- tv[1].tv_sec = statbuf->st_mtime;
-- tv[1].tv_usec = 0;
-- result = utimes (destination, tv);
--#endif /* HAVE_UTIMES */
--#endif /* ! HAVE_GOOD_UTIME_H */
-- }
-+ struct utimbuf tb;
-+
-+ tb.actime = statbuf->st_atime;
-+ tb.modtime = statbuf->st_mtime;
-+ result = utime (destination, &tb);
-+#elif defined HAVE_UTIMES
-+ struct timeval tv[2];
-+
-+ tv[0].tv_sec = statbuf->st_atime;
-+ tv[0].tv_usec = 0;
-+ tv[1].tv_sec = statbuf->st_mtime;
-+ tv[1].tv_usec = 0;
-+ result = utimes (destination, tv);
-+#else
-+ long tb[2];
-+
-+ tb[0] = statbuf->st_atime;
-+ tb[1] = statbuf->st_mtime;
-+ result = utime (destination, tb);
-+#endif
-
- if (result != 0)
- non_fatal (_("%s: cannot set time: %s"), destination, strerror (errno));
- }
-
--/* Rename FROM to TO, copying if TO exists. TARGET_STAT has the file status
-- that, if non-NULL, is used to fix up timestamps after rename. Return 0 if
-- ok, -1 if error. */
-+/* Copy FROM to TO. TARGET_STAT has the file status that, if non-NULL,
-+ is used to fix up timestamps. Return 0 if ok, -1 if error.
-+ At one time this function renamed files, but file permissions are
-+ tricky to update given the number of different schemes used by
-+ various systems. So now we just copy. */
-
- int
- smart_rename (const char *from, const char *to,
-- struct stat *target_stat ATTRIBUTE_UNUSED)
-+ struct stat *target_stat)
- {
-- int ret = 0;
-- struct stat to_stat;
-- bfd_boolean exists;
--
-- exists = lstat (to, &to_stat) == 0;
--
--#if defined (_WIN32) && !defined (__CYGWIN32__)
-- /* Win32, unlike unix, will not erase `to' in `rename(from, to)' but
-- fail instead. Also, chown is not present. */
--
-- if (exists)
-- remove (to);
-+ int ret;
-
-- ret = rename (from, to);
-+ ret = simple_copy (from, to);
- if (ret != 0)
-- {
-- /* We have to clean up here. */
-- non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno));
-- unlink (from);
-- }
--#else
-- /* Avoid a full copy and use rename if TO does not exist. */
-- if (!exists)
-- {
-- if ((ret = rename (from, to)) != 0)
-- {
-- /* We have to clean up here. */
-- non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno));
-- unlink (from);
-- }
-- }
-- else
-- {
-- ret = simple_copy (from, to);
-- if (ret != 0)
-- non_fatal (_("unable to copy file '%s'; reason: %s"), to, strerror (errno));
-+ non_fatal (_("unable to copy file '%s'; reason: %s"),
-+ to, strerror (errno));
-
-- if (target_stat != NULL)
-- set_times (to, target_stat);
-- unlink (from);
-- }
--#endif /* _WIN32 && !__CYGWIN32__ */
-+ if (target_stat != NULL)
-+ set_times (to, target_stat);
-+ unlink (from);
-
- return ret;
- }
---
-2.31.1
-
diff --git a/meta/recipes-devtools/ccache/ccache_4.2.bb b/meta/recipes-devtools/ccache/ccache_4.2.1.bb
index b76bf043f0..99bbe0eca2 100644
--- a/meta/recipes-devtools/ccache/ccache_4.2.bb
+++ b/meta/recipes-devtools/ccache/ccache_4.2.1.bb
@@ -7,14 +7,14 @@ HOMEPAGE = "http://ccache.samba.org"
SECTION = "devel"
LICENSE = "GPLv3+"
-LIC_FILES_CHKSUM = "file://LICENSE.adoc;md5=28afb89f649f309e7ac1aab554564637"
+LIC_FILES_CHKSUM = "file://LICENSE.adoc;md5=698a26b57e513d678e1e7727bf56395b"
DEPENDS = "zstd"
SRC_URI = "https://github.com/ccache/ccache/releases/download/v${PV}/${BP}.tar.gz"
SRC_URI += "file://0001-CMake-make-build-of-documentation-optional-842.patch"
-SRC_URI[sha256sum] = "dbf139ff32031b54cb47f2d7983269f328df14b5a427882f89f7721e5c411b7e"
+SRC_URI[sha256sum] = "320d2b17d2f76393e5d4bb28c8dee5ca783248e9cd23dff0654694d60f8a4b62"
UPSTREAM_CHECK_URI = "https://github.com/ccache/ccache/releases/"
diff --git a/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc b/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc
index fb02b2006e..1250a9b99c 100644
--- a/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc
+++ b/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc
@@ -19,7 +19,8 @@ LIC_FILES_CHKSUM = "file://NOTICE;md5=d50be0580c0b0a7fbc7a4830bbe6c12b \
SECTION = "base"
DEPENDS = "util-linux attr autoconf-archive"
-SRC_URI = "git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git;branch=master"
+SRC_URI = "git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git;branch=master \
+ file://0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch"
S = "${WORKDIR}/git"
inherit autotools gettext texinfo pkgconfig multilib_header update-alternatives ptest
diff --git a/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch b/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch
new file mode 100644
index 0000000000..d679b25b1d
--- /dev/null
+++ b/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch
@@ -0,0 +1,66 @@
+From 2c69c94217b6db083d601d4fd62d6ab6c1628fee Mon Sep 17 00:00:00 2001
+From: Lukas Czerner <lczerner@redhat.com>
+Date: Mon, 14 Jun 2021 15:27:25 +0200
+Subject: [PATCH] e2fsck: fix last mount/write time when e2fsck is forced
+
+With commit c52d930f e2fsck is no longer able to fix bad last
+mount/write time by default because it is conditioned on s_checkinterval
+not being zero, which it is by default.
+
+One place where it matters is when other e2fsprogs tools require to run
+full file system check before a certain operation. If the last mount
+time is for any reason in future, it will not allow it to run even if
+full e2fsck is ran.
+
+Fix it by checking the last mount/write time when the e2fsck is forced,
+except for the case where we know the system clock is broken.
+
+[ Reworked the conditionals so error messages claiming that the last
+ write/mount time were corrupted wouldn't be always printed when the
+ e2fsck was run with the -f option, thus causing 299 out of 372
+ regression tests to fail. -- TYT ]
+
+Fixes: c52d930f ("e2fsck: don't check for future superblock times if checkinterval == 0")
+Reported-by: Dusty Mabe <dustymabe@redhat.com>
+Signed-off-by: Lukas Czerner <lczerner@redhat.com>
+Signed-off-by: Theodore Ts'o <tytso@mit.edu>
+
+Upstream-Status: Backport [https://github.com/tytso/e2fsprogs/commit/2c69c94217b6db083d601d4fd62d6ab6c1628fee]
+Signed-off-by: Changqing Li <changqing.li@windriver.com>
+---
+ e2fsck/super.c | 12 ++++++------
+ 1 file changed, 6 insertions(+), 6 deletions(-)
+
+diff --git a/e2fsck/super.c b/e2fsck/super.c
+index e1c3f935..31e2ffb2 100644
+--- a/e2fsck/super.c
++++ b/e2fsck/super.c
+@@ -1038,9 +1038,9 @@ void check_super_block(e2fsck_t ctx)
+ * Check to see if the superblock last mount time or last
+ * write time is in the future.
+ */
+- if (!broken_system_clock && fs->super->s_checkinterval &&
+- !(ctx->flags & E2F_FLAG_TIME_INSANE) &&
+- fs->super->s_mtime > (__u32) ctx->now) {
++ if (((ctx->options & E2F_OPT_FORCE) || fs->super->s_checkinterval) &&
++ !broken_system_clock && !(ctx->flags & E2F_FLAG_TIME_INSANE) &&
++ (fs->super->s_mtime > (__u32) ctx->now)) {
+ pctx.num = fs->super->s_mtime;
+ problem = PR_0_FUTURE_SB_LAST_MOUNT;
+ if (fs->super->s_mtime <= (__u32) ctx->now + ctx->time_fudge)
+@@ -1050,9 +1050,9 @@ void check_super_block(e2fsck_t ctx)
+ fs->flags |= EXT2_FLAG_DIRTY;
+ }
+ }
+- if (!broken_system_clock && fs->super->s_checkinterval &&
+- !(ctx->flags & E2F_FLAG_TIME_INSANE) &&
+- fs->super->s_wtime > (__u32) ctx->now) {
++ if (((ctx->options & E2F_OPT_FORCE) || fs->super->s_checkinterval) &&
++ !broken_system_clock && !(ctx->flags & E2F_FLAG_TIME_INSANE) &&
++ (fs->super->s_wtime > (__u32) ctx->now)) {
+ pctx.num = fs->super->s_wtime;
+ problem = PR_0_FUTURE_SB_LAST_WRITE;
+ if (fs->super->s_wtime <= (__u32) ctx->now + ctx->time_fudge)
+--
+2.25.1
+
diff --git a/meta/recipes-devtools/gcc/gcc-10.2.inc b/meta/recipes-devtools/gcc/gcc-10.3.inc
index 248e002106..1fdfcced8e 100644
--- a/meta/recipes-devtools/gcc/gcc-10.2.inc
+++ b/meta/recipes-devtools/gcc/gcc-10.3.inc
@@ -2,11 +2,11 @@ require gcc-common.inc
# Third digit in PV should be incremented after a minor release
-PV = "10.2.0"
+PV = "10.3.0"
# BINV should be incremented to a revision after a minor gcc release
-BINV = "10.2.0"
+BINV = "10.3.0"
FILESEXTRAPATHS =. "${FILE_DIRNAME}/gcc:${FILE_DIRNAME}/gcc/backport:"
@@ -65,17 +65,18 @@ SRC_URI = "\
file://0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch \
file://0036-mingw32-Enable-operation_not_supported.patch \
file://0037-libatomic-Do-not-enforce-march-on-aarch64.patch \
- file://0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch \
- file://0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch \
- file://0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch \
- file://0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch \
file://0001-libatomic-libgomp-libitc-Fix-bootstrap-PR70454.patch \
file://0001-CVE-2021-35465.patch \
file://0002-CVE-2021-35465.patch \
file://0003-CVE-2021-35465.patch \
file://0004-CVE-2021-35465.patch \
+ file://0001-CVE-2021-42574.patch \
+ file://0002-CVE-2021-42574.patch \
+ file://0003-CVE-2021-42574.patch \
+ file://0004-CVE-2021-42574.patch \
+ file://0005-CVE-2021-42574.patch \
"
-SRC_URI[sha256sum] = "b8dd4368bb9c7f0b98188317ee0254dd8cc99d1e3a18d0ff146c855fe16c1d8c"
+SRC_URI[sha256sum] = "64f404c1a650f27fc33da242e1f2df54952e3963a49e06e73f6940f3223ac344"
S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${PV}"
# For dev release snapshotting
@@ -122,3 +123,6 @@ EXTRA_OECONF_PATHS = "\
--with-sysroot=/not/exist \
--with-build-sysroot=${STAGING_DIR_TARGET} \
"
+
+# Is a binutils 2.26 issue, not gcc
+CVE_CHECK_WHITELIST += "CVE-2021-37322"
diff --git a/meta/recipes-devtools/gcc/gcc-cross-canadian_10.2.bb b/meta/recipes-devtools/gcc/gcc-cross-canadian_10.3.bb
index bf53c5cd78..bf53c5cd78 100644
--- a/meta/recipes-devtools/gcc/gcc-cross-canadian_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-cross-canadian_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc-cross_10.2.bb b/meta/recipes-devtools/gcc/gcc-cross_10.3.bb
index b43cca0c52..b43cca0c52 100644
--- a/meta/recipes-devtools/gcc/gcc-cross_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-cross_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc-crosssdk_10.2.bb b/meta/recipes-devtools/gcc/gcc-crosssdk_10.3.bb
index 40a6c4feff..40a6c4feff 100644
--- a/meta/recipes-devtools/gcc/gcc-crosssdk_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-crosssdk_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc-runtime_10.2.bb b/meta/recipes-devtools/gcc/gcc-runtime_10.3.bb
index dd430b57eb..dd430b57eb 100644
--- a/meta/recipes-devtools/gcc/gcc-runtime_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-runtime_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc-sanitizers_10.2.bb b/meta/recipes-devtools/gcc/gcc-sanitizers_10.3.bb
index f3c7058114..f3c7058114 100644
--- a/meta/recipes-devtools/gcc/gcc-sanitizers_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-sanitizers_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc-source_10.2.bb b/meta/recipes-devtools/gcc/gcc-source_10.3.bb
index b890fa33ea..b890fa33ea 100644
--- a/meta/recipes-devtools/gcc/gcc-source_10.2.bb
+++ b/meta/recipes-devtools/gcc/gcc-source_10.3.bb
diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch
index b9bca49dd8..4d7c7e3f18 100644
--- a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch
+++ b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch
@@ -33,7 +33,7 @@ Signed-off-by: Pgowda <pgowda.cve@gmail.com>
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
--- a/gcc/config/arm/arm.c 2020-07-22 23:35:17.344384552 -0700
+++ b/gcc/config/arm/arm.c 2021-11-11 20:16:19.761241867 -0800
-@@ -3595,6 +3595,15 @@ arm_option_override (void)
+@@ -3610,6 +3610,15 @@ arm_option_override (void)
fix_cm3_ldrd = 0;
}
@@ -52,7 +52,7 @@ diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
--- a/gcc/config/arm/arm-cpus.in 2020-07-22 23:35:17.340384509 -0700
+++ b/gcc/config/arm/arm-cpus.in 2021-11-11 20:17:01.364573561 -0800
-@@ -190,6 +190,9 @@ define feature quirk_armv6kz
+@@ -186,6 +186,9 @@ define feature quirk_armv6kz
# Cortex-M3 LDRD quirk.
define feature quirk_cm3_ldrd
@@ -62,7 +62,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
# Don't use .cpu assembly directive
define feature quirk_no_asmcpu
-@@ -314,7 +317,7 @@ define fgroup DOTPROD NEON dotprod
+@@ -322,7 +325,7 @@ define implied vfp_base MVE MVE_FP ALL_F
# architectures.
# xscale isn't really a 'quirk', but it isn't an architecture either and we
# need to ignore it for matching purposes.
@@ -71,7 +71,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
# Architecture entries
# format:
-@@ -1492,6 +1495,7 @@ begin cpu cortex-m33
+@@ -1524,6 +1527,7 @@ begin cpu cortex-m33
architecture armv8-m.main+dsp+fp
option nofp remove ALL_FP
option nodsp remove armv7em
@@ -79,7 +79,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
costs v7m
end cpu cortex-m33
-@@ -1501,6 +1505,7 @@ begin cpu cortex-m35p
+@@ -1533,6 +1537,7 @@ begin cpu cortex-m35p
architecture armv8-m.main+dsp+fp
option nofp remove ALL_FP
option nodsp remove armv7em
@@ -87,10 +87,10 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
costs v7m
end cpu cortex-m35p
-@@ -1508,7 +1513,7 @@ begin cpu cortex-m55
- cname cortexm55
- tune flags LDSCHED
- architecture armv8.1-m.main+mve.fp+fp.dp
+@@ -1544,7 +1549,7 @@ begin cpu cortex-m55
+ option nomve remove mve mve_float
+ option nofp remove ALL_FP mve_float
+ option nodsp remove MVE mve_float
- isa quirk_no_asmcpu
+ isa quirk_no_asmcpu quirk_vlldm
costs v7m
@@ -113,7 +113,7 @@ diff --git a/gcc/config/arm/arm.opt b/gcc/config/arm/arm.opt
diff -upr a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
--- a/gcc/doc/invoke.texi 2021-11-11 19:30:56.264523105 -0800
+++ b/gcc/doc/invoke.texi 2021-11-11 20:16:19.769241739 -0800
-@@ -773,6 +773,7 @@ Objective-C and Objective-C++ Dialects}.
+@@ -774,6 +774,7 @@ Objective-C and Objective-C++ Dialects}.
-mverbose-cost-dump @gol
-mpure-code @gol
-mcmse @gol
@@ -121,7 +121,7 @@ diff -upr a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
-mfdpic}
@emph{AVR Options}
-@@ -21233,6 +21234,14 @@ Use multiply and add/subtract instructio
+@@ -21266,6 +21267,14 @@ Use multiply and add/subtract instructio
Do not use multiply and add/subtract instructions.
diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch
new file mode 100644
index 0000000000..e0f4f7d32f
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch
@@ -0,0 +1,2906 @@
+From 004bb936d6d5f177af26ad4905595e843d5665a5 Mon Sep 17 00:00:00 2001
+From: Lewis Hyatt <lhyatt@gmail.com>
+Date: Tue, 14 Jul 2020 12:05:56 -0400
+Subject: [PATCH] diagnostics: Support conversion of tabs to spaces [PR49973]
+ [PR86904]
+
+Supports conversion of tabs to spaces when outputting diagnostics. Also
+adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to
+control how the column number is output, thereby resolving the two PRs.
+
+gcc/c-family/ChangeLog:
+
+ PR other/86904
+ * c-indentation.c (should_warn_for_misleading_indentation): Get
+ global tabstop from the new source.
+ * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which
+ is now a common option.
+ * c.opt: Likewise.
+
+gcc/ChangeLog:
+
+ PR preprocessor/49973
+ PR other/86904
+ * common.opt: Handle -ftabstop here instead of in c-family
+ options. Add -fdiagnostics-column-unit= and
+ -fdiagnostics-column-origin= options.
+ * opts.c (common_handle_option): Handle the new options.
+ * diagnostic-format-json.cc (json_from_expanded_location): Add
+ diagnostic_context argument. Use it to convert column numbers as per
+ the new options.
+ (json_from_location_range): Likewise.
+ (json_from_fixit_hint): Likewise.
+ (json_end_diagnostic): Pass the new context argument to helper
+ functions above. Add "column-origin" field to the output.
+ (test_unknown_location): Add the new context argument to calls to
+ helper functions.
+ (test_bad_endpoints): Likewise.
+ * diagnostic-show-locus.c
+ (exploc_with_display_col::exploc_with_display_col): Support
+ tabstop parameter.
+ (layout_point::layout_point): Make use of class
+ exploc_with_display_col.
+ (layout_range::layout_range): Likewise.
+ (struct line_bounds): Clarify that the units are now always
+ display columns. Rename members accordingly. Add constructor.
+ (layout::print_source_line): Add support for tab expansion.
+ (make_range): Adapt to class layout_range changes.
+ (layout::maybe_add_location_range): Likewise.
+ (layout::layout): Adapt to class exploc_with_display_col changes.
+ (layout::calculate_x_offset_display): Support tabstop parameter.
+ (layout::print_annotation_line): Adapt to struct line_bounds changes.
+ (layout::print_line): Likewise.
+ (line_label::line_label): Add diagnostic_context argument.
+ (get_affected_range): Likewise.
+ (get_printed_columns): Likewise.
+ (layout::print_any_labels): Adapt to struct line_label changes.
+ (class correction): Add m_tabstop member.
+ (correction::correction): Add tabstop argument.
+ (correction::compute_display_cols): Use m_tabstop.
+ (class line_corrections): Add m_context member.
+ (line_corrections::line_corrections): Add diagnostic_context argument.
+ (line_corrections::add_hint): Use m_context to handle tabstops.
+ (layout::print_trailing_fixits): Adapt to class line_corrections
+ changes.
+ (test_layout_x_offset_display_utf8): Support tabstop parameter.
+ (test_layout_x_offset_display_tab): New selftest.
+ (test_one_liner_colorized_utf8): Likewise.
+ (test_tab_expansion): Likewise.
+ (test_diagnostic_show_locus_one_liner_utf8): Call the new tests.
+ (diagnostic_show_locus_c_tests): Likewise.
+ (test_overlapped_fixit_printing): Adapt to helper class and
+ function changes.
+ (test_overlapped_fixit_printing_utf8): Likewise.
+ (test_overlapped_fixit_printing_2): Likewise.
+ * diagnostic.h (enum diagnostics_column_unit): New enum.
+ (struct diagnostic_context): Add members for the new options.
+ (diagnostic_converted_column): Declare.
+ (json_from_expanded_location): Add new context argument.
+ * diagnostic.c (diagnostic_initialize): Initialize new members.
+ (diagnostic_converted_column): New function.
+ (maybe_line_and_column): Be willing to output a column of 0.
+ (diagnostic_get_location_text): Convert column number as per the new
+ options.
+ (diagnostic_report_current_module): Likewise.
+ (assert_location_text): Add origin and column_unit arguments for
+ testing the new functionality.
+ (test_diagnostic_get_location_text): Test the new functionality.
+ * doc/invoke.texi: Document the new options and behavior.
+ * input.h (location_compute_display_column): Add tabstop argument.
+ * input.c (location_compute_display_column): Likewise.
+ (test_cpp_utf8): Add selftests for tab expansion.
+ * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the
+ new context argument to json_from_expanded_location().
+
+libcpp/ChangeLog:
+
+ PR preprocessor/49973
+ PR other/86904
+ * include/cpplib.h (struct cpp_options): Removed support for -ftabstop,
+ which is now handled by diagnostic_context.
+ (class cpp_display_width_computation): New class.
+ (cpp_byte_column_to_display_column): Add optional tabstop argument.
+ (cpp_display_width): Likewise.
+ (cpp_display_column_to_byte_column): Likewise.
+ * charset.c
+ (cpp_display_width_computation::cpp_display_width_computation): New
+ function.
+ (cpp_display_width_computation::advance_display_cols): Likewise.
+ (compute_next_display_width): Removed and implemented this
+ functionality in a new function...
+ (cpp_display_width_computation::process_next_codepoint): ...here.
+ (cpp_byte_column_to_display_column): Added tabstop argument.
+ Reimplemented in terms of class cpp_display_width_computation.
+ (cpp_display_column_to_byte_column): Likewise.
+ * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now
+ handled by diagnostic_context.
+
+gcc/testsuite/ChangeLog:
+
+ PR preprocessor/49973
+ PR other/86904
+ * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output
+ for new defaults.
+ * c-c++-common/Wmisleading-indentation.c: Likewise.
+ * c-c++-common/diagnostic-format-json-1.c: Likewise.
+ * c-c++-common/diagnostic-format-json-2.c: Likewise.
+ * c-c++-common/diagnostic-format-json-3.c: Likewise.
+ * c-c++-common/diagnostic-format-json-4.c: Likewise.
+ * c-c++-common/diagnostic-format-json-5.c: Likewise.
+ * c-c++-common/missing-close-symbol.c: Likewise.
+ * g++.dg/diagnostic/bad-binary-ops.C: Likewise.
+ * g++.dg/parse/error4.C: Likewise.
+ * g++.old-deja/g++.brendan/crash11.C: Likewise.
+ * g++.old-deja/g++.pt/overload2.C: Likewise.
+ * g++.old-deja/g++.robertl/eb109.C: Likewise.
+ * gcc.dg/analyzer/malloc-paths-9.c: Likewise.
+ * gcc.dg/bad-binary-ops.c: Likewise.
+ * gcc.dg/format/branch-1.c: Likewise.
+ * gcc.dg/format/pr79210.c: Likewise.
+ * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise.
+ * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise.
+ * gcc.dg/redecl-4.c: Likewise.
+ * gfortran.dg/diagnostic-format-json-1.F90: Likewise.
+ * gfortran.dg/diagnostic-format-json-2.F90: Likewise.
+ * gfortran.dg/diagnostic-format-json-3.F90: Likewise.
+ * go.dg/arrayclear.go: Add a comment explaining why adding a
+ comment was necessary to work around a dejagnu bug.
+ * c-c++-common/diagnostic-units-1.c: New test.
+ * c-c++-common/diagnostic-units-2.c: New test.
+ * c-c++-common/diagnostic-units-3.c: New test.
+ * c-c++-common/diagnostic-units-4.c: New test.
+ * c-c++-common/diagnostic-units-5.c: New test.
+ * c-c++-common/diagnostic-units-6.c: New test.
+ * c-c++-common/diagnostic-units-7.c: New test.
+ * c-c++-common/diagnostic-units-8.c: New test.
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=004bb936d6d5f177af26ad4905595e843d5665a5]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+---
+ gcc/c-family/c-indentation.c | 5 +-
+ gcc/c-family/c-opts.c | 6 -
+ gcc/c-family/c.opt | 4 -
+ gcc/common.opt | 21 +
+ gcc/diagnostic-format-json.cc | 55 +-
+ gcc/diagnostic-show-locus.c | 504 +++++++++++++-----
+ gcc/diagnostic.c | 113 +++-
+ gcc/diagnostic.h | 28 +-
+ gcc/doc/invoke.texi | 68 ++-
+ gcc/input.c | 72 ++-
+ gcc/input.h | 4 +-
+ gcc/opts.c | 14 +
+ .../c-c++-common/Wmisleading-indentation-3.c | 12 +-
+ .../c-c++-common/Wmisleading-indentation.c | 6 +-
+ .../c-c++-common/diagnostic-format-json-1.c | 5 +
+ .../c-c++-common/diagnostic-format-json-2.c | 5 +
+ .../c-c++-common/diagnostic-format-json-3.c | 5 +
+ .../c-c++-common/diagnostic-format-json-4.c | 9 +
+ .../c-c++-common/diagnostic-format-json-5.c | 9 +
+ .../c-c++-common/diagnostic-units-1.c | 28 +
+ .../c-c++-common/diagnostic-units-2.c | 28 +
+ .../c-c++-common/diagnostic-units-3.c | 28 +
+ .../c-c++-common/diagnostic-units-4.c | 28 +
+ .../c-c++-common/diagnostic-units-5.c | 28 +
+ .../c-c++-common/diagnostic-units-6.c | 28 +
+ .../c-c++-common/diagnostic-units-7.c | 28 +
+ .../c-c++-common/diagnostic-units-8.c | 28 +
+ .../c-c++-common/missing-close-symbol.c | 6 +-
+ .../g++.dg/diagnostic/bad-binary-ops.C | 8 +-
+ gcc/testsuite/g++.dg/parse/error4.C | 2 +-
+ .../g++.old-deja/g++.brendan/crash11.C | 4 +-
+ gcc/testsuite/g++.old-deja/g++.pt/overload2.C | 2 +-
+ .../g++.old-deja/g++.robertl/eb109.C | 4 +-
+ .../gcc.dg/analyzer/malloc-paths-9.c | 2 +-
+ gcc/testsuite/gcc.dg/bad-binary-ops.c | 8 +-
+ gcc/testsuite/gcc.dg/format/branch-1.c | 2 +-
+ gcc/testsuite/gcc.dg/format/pr79210.c | 2 +-
+ .../plugin/diagnostic-test-expressions-1.c | 16 +-
+ .../diagnostic-test-string-literals-1.c | 4 +-
+ gcc/testsuite/gcc.dg/redecl-4.c | 2 +-
+ .../gfortran.dg/diagnostic-format-json-1.F90 | 5 +
+ .../gfortran.dg/diagnostic-format-json-2.F90 | 5 +
+ .../gfortran.dg/diagnostic-format-json-3.F90 | 5 +
+ gcc/testsuite/go.dg/arrayclear.go | 3 +
+ gcc/tree-diagnostic-path.cc | 5 +-
+ libcpp/charset.c | 98 ++--
+ libcpp/include/cpplib.h | 40 +-
+ libcpp/init.c | 1 -
+ 48 files changed, 1106 insertions(+), 287 deletions(-)
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-1.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-2.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-3.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-4.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-5.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-6.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-7.c
+ create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-8.c
+
+diff --git a/gcc/c-family/c-indentation.c b/gcc/c-family/c-indentation.c
+--- a/gcc/c-family/c-indentation.c 2020-07-22 23:35:17.296384022 -0700
++++ b/gcc/c-family/c-indentation.c 2021-12-25 01:20:53.475636694 -0800
+@@ -24,8 +24,7 @@ along with GCC; see the file COPYING3.
+ #include "c-common.h"
+ #include "c-indentation.h"
+ #include "selftest.h"
+-
+-extern cpp_options *cpp_opts;
++#include "diagnostic.h"
+
+ /* Round up VIS_COLUMN to nearest tab stop. */
+
+@@ -294,7 +293,7 @@ should_warn_for_misleading_indentation (
+ expanded_location next_stmt_exploc = expand_location (next_stmt_loc);
+ expanded_location guard_exploc = expand_location (guard_loc);
+
+- const unsigned int tab_width = cpp_opts->tabstop;
++ const unsigned int tab_width = global_dc->tabstop;
+
+ /* They must be in the same file. */
+ if (next_stmt_exploc.file != body_exploc.file)
+diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
+--- a/gcc/c-family/c.opt 2021-12-24 20:23:42.816809230 -0800
++++ b/gcc/c-family/c.opt 2021-12-25 01:20:53.475636694 -0800
+@@ -1876,10 +1876,6 @@ Enum(strong_eval_order) String(some) Val
+ EnumValue
+ Enum(strong_eval_order) String(all) Value(2)
+
+-ftabstop=
+-C ObjC C++ ObjC++ Joined RejectNegative UInteger
+--ftabstop=<number> Distance between tab stops for column reporting.
+-
+ ftemplate-backtrace-limit=
+ C++ ObjC++ Joined RejectNegative UInteger Var(template_backtrace_limit) Init(10)
+ Set the maximum number of template instantiation notes for a single warning or error.
+diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c
+--- a/gcc/c-family/c-opts.c 2021-12-24 20:23:44.824774786 -0800
++++ b/gcc/c-family/c-opts.c 2021-12-25 01:20:53.475636694 -0800
+@@ -504,12 +504,6 @@ c_common_handle_option (size_t scode, co
+ cpp_opts->track_macro_expansion = 2;
+ break;
+
+- case OPT_ftabstop_:
+- /* It is documented that we silently ignore silly values. */
+- if (value >= 1 && value <= 100)
+- cpp_opts->tabstop = value;
+- break;
+-
+ case OPT_fexec_charset_:
+ cpp_opts->narrow_charset = arg;
+ break;
+diff --git a/gcc/common.opt b/gcc/common.opt
+--- a/gcc/common.opt 2021-12-24 20:23:42.480814993 -0800
++++ b/gcc/common.opt 2021-12-25 01:20:53.475636694 -0800
+@@ -1325,6 +1325,14 @@ Enum(diagnostic_url_rule) String(always)
+ EnumValue
+ Enum(diagnostic_url_rule) String(auto) Value(DIAGNOSTICS_URL_AUTO)
+
++fdiagnostics-column-unit=
++Common Joined RejectNegative Enum(diagnostics_column_unit)
++-fdiagnostics-column-unit=[display|byte] Select whether column numbers are output as display columns (default) or raw bytes.
++
++fdiagnostics-column-origin=
++Common Joined RejectNegative UInteger
++-fdiagnostics-column-origin=<number> Set the number of the first column. The default is 1-based as per GNU style, but some utilities may expect 0-based, for example.
++
+ fdiagnostics-format=
+ Common Joined RejectNegative Enum(diagnostics_output_format)
+ -fdiagnostics-format=[text|json] Select output format.
+@@ -1334,6 +1342,15 @@ SourceInclude
+ diagnostic.h
+
+ Enum
++Name(diagnostics_column_unit) Type(int)
++
++EnumValue
++Enum(diagnostics_column_unit) String(display) Value(DIAGNOSTICS_COLUMN_UNIT_DISPLAY)
++
++EnumValue
++Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE)
++
++Enum
+ Name(diagnostics_output_format) Type(int)
+
+ EnumValue
+@@ -1362,6 +1379,10 @@ fdiagnostics-path-format=
+ Common Joined RejectNegative Var(flag_diagnostics_path_format) Enum(diagnostic_path_format) Init(DPF_INLINE_EVENTS)
+ Specify how to print any control-flow path associated with a diagnostic.
+
++ftabstop=
++Common Joined RejectNegative UInteger
++-ftabstop=<number> Distance between tab stops for column reporting.
++
+ Enum
+ Name(diagnostic_path_format) Type(int)
+
+diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c
+--- a/gcc/diagnostic.c 2020-07-22 23:35:17.556386887 -0700
++++ b/gcc/diagnostic.c 2021-12-25 01:23:41.300841207 -0800
+@@ -38,6 +38,7 @@ along with GCC; see the file COPYING3.
+ #include "selftest.h"
+ #include "selftest-diagnostic.h"
+ #include "opts.h"
++#include "cpplib.h"
+
+ #ifdef HAVE_TERMIOS_H
+ # include <termios.h>
+@@ -219,6 +220,9 @@ diagnostic_initialize (diagnostic_contex
+ context->min_margin_width = 0;
+ context->show_ruler_p = false;
+ context->parseable_fixits_p = false;
++ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY;
++ context->column_origin = 1;
++ context->tabstop = 8;
+ context->edit_context_ptr = NULL;
+ context->diagnostic_group_nesting_depth = 0;
+ context->diagnostic_group_emission_count = 0;
+@@ -353,8 +357,51 @@ diagnostic_get_color_for_kind (diagnosti
+ return diagnostic_kind_color[kind];
+ }
+
++/* Given an expanded_location, convert the column (which is in 1-based bytes)
++ to the requested units, without converting the origin.
++ Return -1 if the column is invalid (<= 0). */
++
++static int
++convert_column_unit (enum diagnostics_column_unit column_unit,
++ int tabstop,
++ expanded_location s)
++{
++ if (s.column <= 0)
++ return -1;
++
++ switch (column_unit)
++ {
++ default:
++ gcc_unreachable ();
++
++ case DIAGNOSTICS_COLUMN_UNIT_DISPLAY:
++ {
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
++ return location_compute_display_column (s, policy);
++ }
++
++ case DIAGNOSTICS_COLUMN_UNIT_BYTE:
++ return s.column;
++ }
++}
++
++/* Given an expanded_location, convert the column (which is in 1-based bytes)
++ to the requested units and origin. Return -1 if the column is
++ invalid (<= 0). */
++int
++diagnostic_converted_column (diagnostic_context *context, expanded_location s)
++{
++ int one_based_col
++ = convert_column_unit (context->column_unit, context->tabstop, s);
++ if (one_based_col <= 0)
++ return -1;
++ return one_based_col + (context->column_origin - 1);
++}
++
+ /* Return a formatted line and column ':%line:%column'. Elided if
+- zero. The result is a statically allocated buffer. */
++ line == 0 or col < 0. (A column of 0 may be valid due to the
++ -fdiagnostics-column-origin option.)
++ The result is a statically allocated buffer. */
+
+ static const char *
+ maybe_line_and_column (int line, int col)
+@@ -363,8 +410,9 @@ maybe_line_and_column (int line, int col
+
+ if (line)
+ {
+- size_t l = snprintf (result, sizeof (result),
+- col ? ":%d:%d" : ":%d", line, col);
++ size_t l
++ = snprintf (result, sizeof (result),
++ col >= 0 ? ":%d:%d" : ":%d", line, col);
+ gcc_checking_assert (l < sizeof (result));
+ }
+ else
+@@ -383,8 +431,14 @@ diagnostic_get_location_text (diagnostic
+ const char *locus_cs = colorize_start (pp_show_color (pp), "locus");
+ const char *locus_ce = colorize_stop (pp_show_color (pp));
+ const char *file = s.file ? s.file : progname;
+- int line = strcmp (file, N_("<built-in>")) ? s.line : 0;
+- int col = context->show_column ? s.column : 0;
++ int line = 0;
++ int col = -1;
++ if (strcmp (file, N_("<built-in>")))
++ {
++ line = s.line;
++ if (context->show_column)
++ col = diagnostic_converted_column (context, s);
++ }
+
+ const char *line_col = maybe_line_and_column (line, col);
+ return build_message_string ("%s%s%s:%s", locus_cs, file,
+@@ -650,14 +704,20 @@ diagnostic_report_current_module (diagno
+ if (! MAIN_FILE_P (map))
+ {
+ bool first = true;
++ expanded_location s = {};
+ do
+ {
+ where = linemap_included_from (map);
+ map = linemap_included_from_linemap (line_table, map);
+- const char *line_col
+- = maybe_line_and_column (SOURCE_LINE (map, where),
+- first && context->show_column
+- ? SOURCE_COLUMN (map, where) : 0);
++ s.file = LINEMAP_FILE (map);
++ s.line = SOURCE_LINE (map, where);
++ int col = -1;
++ if (first && context->show_column)
++ {
++ s.column = SOURCE_COLUMN (map, where);
++ col = diagnostic_converted_column (context, s);
++ }
++ const char *line_col = maybe_line_and_column (s.line, col);
+ static const char *const msgs[] =
+ {
+ N_("In file included from"),
+@@ -666,7 +726,7 @@ diagnostic_report_current_module (diagno
+ unsigned index = !first;
+ pp_verbatim (context->printer, "%s%s %r%s%s%R",
+ first ? "" : ",\n", _(msgs[index]),
+- "locus", LINEMAP_FILE (map), line_col);
++ "locus", s.file, line_col);
+ first = false;
+ }
+ while (! MAIN_FILE_P (map));
+@@ -2042,10 +2102,15 @@ test_print_parseable_fixits_replace ()
+ static void
+ assert_location_text (const char *expected_loc_text,
+ const char *filename, int line, int column,
+- bool show_column)
++ bool show_column,
++ int origin = 1,
++ enum diagnostics_column_unit column_unit
++ = DIAGNOSTICS_COLUMN_UNIT_BYTE)
+ {
+ test_diagnostic_context dc;
+ dc.show_column = show_column;
++ dc.column_unit = column_unit;
++ dc.column_origin = origin;
+
+ expanded_location xloc;
+ xloc.file = filename;
+@@ -2069,7 +2134,10 @@ test_diagnostic_get_location_text ()
+ assert_location_text ("PROGNAME:", NULL, 0, 0, true);
+ assert_location_text ("<built-in>:", "<built-in>", 42, 10, true);
+ assert_location_text ("foo.c:42:10:", "foo.c", 42, 10, true);
+- assert_location_text ("foo.c:42:", "foo.c", 42, 0, true);
++ assert_location_text ("foo.c:42:9:", "foo.c", 42, 10, true, 0);
++ assert_location_text ("foo.c:42:1010:", "foo.c", 42, 10, true, 1001);
++ for (int origin = 0; origin != 2; ++origin)
++ assert_location_text ("foo.c:42:", "foo.c", 42, 0, true, origin);
+ assert_location_text ("foo.c:", "foo.c", 0, 10, true);
+ assert_location_text ("foo.c:42:", "foo.c", 42, 10, false);
+ assert_location_text ("foo.c:", "foo.c", 0, 10, false);
+@@ -2077,6 +2145,41 @@ test_diagnostic_get_location_text ()
+ maybe_line_and_column (INT_MAX, INT_MAX);
+ maybe_line_and_column (INT_MIN, INT_MIN);
+
++ {
++ /* In order to test display columns vs byte columns, we need to create a
++ file for location_get_source_line() to read. */
++
++ const char *const content = "smile \xf0\x9f\x98\x82\n";
++ const int line_bytes = strlen (content) - 1;
++ const int def_tabstop = 8;
++ const int display_width = cpp_display_width (content, line_bytes,
++ def_tabstop);
++ ASSERT_EQ (line_bytes - 2, display_width);
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
++ const char *const fname = tmp.get_filename ();
++ const int buf_len = strlen (fname) + 16;
++ char *const expected = XNEWVEC (char, buf_len);
++
++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes);
++ assert_location_text (expected, fname, 1, line_bytes, true,
++ 1, DIAGNOSTICS_COLUMN_UNIT_BYTE);
++
++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes - 1);
++ assert_location_text (expected, fname, 1, line_bytes, true,
++ 0, DIAGNOSTICS_COLUMN_UNIT_BYTE);
++
++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width);
++ assert_location_text (expected, fname, 1, line_bytes, true,
++ 1, DIAGNOSTICS_COLUMN_UNIT_DISPLAY);
++
++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width - 1);
++ assert_location_text (expected, fname, 1, line_bytes, true,
++ 0, DIAGNOSTICS_COLUMN_UNIT_DISPLAY);
++
++ XDELETEVEC (expected);
++ }
++
++
+ progname = old_progname;
+ }
+
+diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc
+--- a/gcc/diagnostic-format-json.cc 2020-07-22 23:35:17.556386887 -0700
++++ b/gcc/diagnostic-format-json.cc 2021-12-25 01:20:53.475636694 -0800
+@@ -23,6 +23,7 @@ along with GCC; see the file COPYING3.
+ #include "system.h"
+ #include "coretypes.h"
+ #include "diagnostic.h"
++#include "selftest-diagnostic.h"
+ #include "diagnostic-metadata.h"
+ #include "json.h"
+ #include "selftest.h"
+@@ -43,21 +44,43 @@ static json::array *cur_children_array;
+ /* Generate a JSON object for LOC. */
+
+ json::value *
+-json_from_expanded_location (location_t loc)
++json_from_expanded_location (diagnostic_context *context, location_t loc)
+ {
+ expanded_location exploc = expand_location (loc);
+ json::object *result = new json::object ();
+ if (exploc.file)
+ result->set ("file", new json::string (exploc.file));
+ result->set ("line", new json::integer_number (exploc.line));
+- result->set ("column", new json::integer_number (exploc.column));
++
++ const enum diagnostics_column_unit orig_unit = context->column_unit;
++ struct
++ {
++ const char *name;
++ enum diagnostics_column_unit unit;
++ } column_fields[] = {
++ {"display-column", DIAGNOSTICS_COLUMN_UNIT_DISPLAY},
++ {"byte-column", DIAGNOSTICS_COLUMN_UNIT_BYTE}
++ };
++ int the_column = INT_MIN;
++ for (int i = 0; i != sizeof column_fields / sizeof (*column_fields); ++i)
++ {
++ context->column_unit = column_fields[i].unit;
++ const int col = diagnostic_converted_column (context, exploc);
++ result->set (column_fields[i].name, new json::integer_number (col));
++ if (column_fields[i].unit == orig_unit)
++ the_column = col;
++ }
++ gcc_assert (the_column != INT_MIN);
++ result->set ("column", new json::integer_number (the_column));
++ context->column_unit = orig_unit;
+ return result;
+ }
+
+ /* Generate a JSON object for LOC_RANGE. */
+
+ static json::object *
+-json_from_location_range (const location_range *loc_range, unsigned range_idx)
++json_from_location_range (diagnostic_context *context,
++ const location_range *loc_range, unsigned range_idx)
+ {
+ location_t caret_loc = get_pure_location (loc_range->m_loc);
+
+@@ -68,13 +91,13 @@ json_from_location_range (const location
+ location_t finish_loc = get_finish (loc_range->m_loc);
+
+ json::object *result = new json::object ();
+- result->set ("caret", json_from_expanded_location (caret_loc));
++ result->set ("caret", json_from_expanded_location (context, caret_loc));
+ if (start_loc != caret_loc
+ && start_loc != UNKNOWN_LOCATION)
+- result->set ("start", json_from_expanded_location (start_loc));
++ result->set ("start", json_from_expanded_location (context, start_loc));
+ if (finish_loc != caret_loc
+ && finish_loc != UNKNOWN_LOCATION)
+- result->set ("finish", json_from_expanded_location (finish_loc));
++ result->set ("finish", json_from_expanded_location (context, finish_loc));
+
+ if (loc_range->m_label)
+ {
+@@ -91,14 +114,14 @@ json_from_location_range (const location
+ /* Generate a JSON object for HINT. */
+
+ static json::object *
+-json_from_fixit_hint (const fixit_hint *hint)
++json_from_fixit_hint (diagnostic_context *context, const fixit_hint *hint)
+ {
+ json::object *fixit_obj = new json::object ();
+
+ location_t start_loc = hint->get_start_loc ();
+- fixit_obj->set ("start", json_from_expanded_location (start_loc));
++ fixit_obj->set ("start", json_from_expanded_location (context, start_loc));
+ location_t next_loc = hint->get_next_loc ();
+- fixit_obj->set ("next", json_from_expanded_location (next_loc));
++ fixit_obj->set ("next", json_from_expanded_location (context, next_loc));
+ fixit_obj->set ("string", new json::string (hint->get_string ()));
+
+ return fixit_obj;
+@@ -190,11 +213,13 @@ json_end_diagnostic (diagnostic_context
+ else
+ {
+ /* Otherwise, make diag_obj be the top-level object within the group;
+- add a "children" array. */
++ add a "children" array and record the column origin. */
+ toplevel_array->append (diag_obj);
+ cur_group = diag_obj;
+ cur_children_array = new json::array ();
+ diag_obj->set ("children", cur_children_array);
++ diag_obj->set ("column-origin",
++ new json::integer_number (context->column_origin));
+ }
+
+ const rich_location *richloc = diagnostic->richloc;
+@@ -205,7 +230,7 @@ json_end_diagnostic (diagnostic_context
+ for (unsigned int i = 0; i < richloc->get_num_locations (); i++)
+ {
+ const location_range *loc_range = richloc->get_range (i);
+- json::object *loc_obj = json_from_location_range (loc_range, i);
++ json::object *loc_obj = json_from_location_range (context, loc_range, i);
+ if (loc_obj)
+ loc_array->append (loc_obj);
+ }
+@@ -217,7 +242,7 @@ json_end_diagnostic (diagnostic_context
+ for (unsigned int i = 0; i < richloc->get_num_fixit_hints (); i++)
+ {
+ const fixit_hint *hint = richloc->get_fixit_hint (i);
+- json::object *fixit_obj = json_from_fixit_hint (hint);
++ json::object *fixit_obj = json_from_fixit_hint (context, hint);
+ fixit_array->append (fixit_obj);
+ }
+ }
+@@ -320,7 +345,8 @@ namespace selftest {
+ static void
+ test_unknown_location ()
+ {
+- delete json_from_expanded_location (UNKNOWN_LOCATION);
++ test_diagnostic_context dc;
++ delete json_from_expanded_location (&dc, UNKNOWN_LOCATION);
+ }
+
+ /* Verify that we gracefully handle attempts to serialize bad
+@@ -338,7 +364,8 @@ test_bad_endpoints ()
+ loc_range.m_range_display_kind = SHOW_RANGE_WITH_CARET;
+ loc_range.m_label = NULL;
+
+- json::object *obj = json_from_location_range (&loc_range, 0);
++ test_diagnostic_context dc;
++ json::object *obj = json_from_location_range (&dc, &loc_range, 0);
+ /* We should have a "caret" value, but no "start" or "finish" values. */
+ ASSERT_TRUE (obj != NULL);
+ ASSERT_TRUE (obj->get ("caret") != NULL);
+diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h
+--- a/gcc/diagnostic.h 2020-07-22 23:35:17.556386887 -0700
++++ b/gcc/diagnostic.h 2021-12-25 01:20:53.479636627 -0800
+@@ -24,6 +24,20 @@ along with GCC; see the file COPYING3.
+ #include "pretty-print.h"
+ #include "diagnostic-core.h"
+
++/* An enum for controlling what units to use for the column number
++ when diagnostics are output, used by the -fdiagnostics-column-unit option.
++ Tabs will be expanded or not according to the value of -ftabstop. The origin
++ (default 1) is controlled by -fdiagnostics-column-origin. */
++
++enum diagnostics_column_unit
++{
++ /* The default from GCC 11 onwards: display columns. */
++ DIAGNOSTICS_COLUMN_UNIT_DISPLAY,
++
++ /* The behavior in GCC 10 and earlier: simple bytes. */
++ DIAGNOSTICS_COLUMN_UNIT_BYTE
++};
++
+ /* Enum for overriding the standard output format. */
+
+ enum diagnostics_output_format
+@@ -280,6 +294,15 @@ struct diagnostic_context
+ rest of the diagnostic. */
+ bool parseable_fixits_p;
+
++ /* What units to use when outputting the column number. */
++ enum diagnostics_column_unit column_unit;
++
++ /* The origin for the column number (1-based or 0-based typically). */
++ int column_origin;
++
++ /* The size of the tabstop for tab expansion. */
++ int tabstop;
++
+ /* If non-NULL, an edit_context to which fix-it hints should be
+ applied, for generating patches. */
+ edit_context *edit_context_ptr;
+@@ -458,6 +481,8 @@ diagnostic_same_line (const diagnostic_c
+ }
+
+ extern const char *diagnostic_get_color_for_kind (diagnostic_t kind);
++extern int diagnostic_converted_column (diagnostic_context *context,
++ expanded_location s);
+
+ /* Pure text formatting support functions. */
+ extern char *file_name_as_prefix (diagnostic_context *, const char *);
+@@ -470,6 +495,7 @@ extern void diagnostic_output_format_ini
+ /* Compute the number of digits in the decimal representation of an integer. */
+ extern int num_digits (int);
+
+-extern json::value *json_from_expanded_location (location_t loc);
++extern json::value *json_from_expanded_location (diagnostic_context *context,
++ location_t loc);
+
+ #endif /* ! GCC_DIAGNOSTIC_H */
+diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c
+--- a/gcc/diagnostic-show-locus.c 2020-07-22 23:35:17.556386887 -0700
++++ b/gcc/diagnostic-show-locus.c 2021-12-25 01:20:53.479636627 -0800
+@@ -175,9 +175,10 @@ enum column_unit {
+ class exploc_with_display_col : public expanded_location
+ {
+ public:
+- exploc_with_display_col (const expanded_location &exploc)
++ exploc_with_display_col (const expanded_location &exploc, int tabstop)
+ : expanded_location (exploc),
+- m_display_col (location_compute_display_column (exploc)) {}
++ m_display_col (location_compute_display_column (exploc, tabstop))
++ {}
+
+ int m_display_col;
+ };
+@@ -189,11 +190,11 @@ class exploc_with_display_col : public e
+ class layout_point
+ {
+ public:
+- layout_point (const expanded_location &exploc)
++ layout_point (const exploc_with_display_col &exploc)
+ : m_line (exploc.line)
+ {
+ m_columns[CU_BYTES] = exploc.column;
+- m_columns[CU_DISPLAY_COLS] = location_compute_display_column (exploc);
++ m_columns[CU_DISPLAY_COLS] = exploc.m_display_col;
+ }
+
+ linenum_type m_line;
+@@ -205,10 +206,10 @@ class layout_point
+ class layout_range
+ {
+ public:
+- layout_range (const expanded_location *start_exploc,
+- const expanded_location *finish_exploc,
++ layout_range (const exploc_with_display_col &start_exploc,
++ const exploc_with_display_col &finish_exploc,
+ enum range_display_kind range_display_kind,
+- const expanded_location *caret_exploc,
++ const exploc_with_display_col &caret_exploc,
+ unsigned original_idx,
+ const range_label *label);
+
+@@ -226,22 +227,18 @@ class layout_range
+
+ /* A struct for use by layout::print_source_line for telling
+ layout::print_annotation_line the extents of the source line that
+- it printed, so that underlines can be clipped appropriately. */
++ it printed, so that underlines can be clipped appropriately. Units
++ are 1-based display columns. */
+
+ struct line_bounds
+ {
+- int m_first_non_ws;
+- int m_last_non_ws;
++ int m_first_non_ws_disp_col;
++ int m_last_non_ws_disp_col;
+
+- void convert_to_display_cols (char_span line)
++ line_bounds ()
+ {
+- m_first_non_ws = cpp_byte_column_to_display_column (line.get_buffer (),
+- line.length (),
+- m_first_non_ws);
+-
+- m_last_non_ws = cpp_byte_column_to_display_column (line.get_buffer (),
+- line.length (),
+- m_last_non_ws);
++ m_first_non_ws_disp_col = INT_MAX;
++ m_last_non_ws_disp_col = 0;
+ }
+ };
+
+@@ -351,8 +348,8 @@ class layout
+ private:
+ bool will_show_line_p (linenum_type row) const;
+ void print_leading_fixits (linenum_type row);
+- void print_source_line (linenum_type row, const char *line, int line_bytes,
+- line_bounds *lbounds_out);
++ line_bounds print_source_line (linenum_type row, const char *line,
++ int line_bytes);
+ bool should_print_annotation_line_p (linenum_type row) const;
+ void start_annotation_line (char margin_char = ' ') const;
+ void print_annotation_line (linenum_type row, const line_bounds lbounds);
+@@ -513,16 +510,16 @@ colorizer::get_color_by_name (const char
+ Initialize various layout_point fields from expanded_location
+ equivalents; we've already filtered on file. */
+
+-layout_range::layout_range (const expanded_location *start_exploc,
+- const expanded_location *finish_exploc,
++layout_range::layout_range (const exploc_with_display_col &start_exploc,
++ const exploc_with_display_col &finish_exploc,
+ enum range_display_kind range_display_kind,
+- const expanded_location *caret_exploc,
++ const exploc_with_display_col &caret_exploc,
+ unsigned original_idx,
+ const range_label *label)
+-: m_start (*start_exploc),
+- m_finish (*finish_exploc),
++: m_start (start_exploc),
++ m_finish (finish_exploc),
+ m_range_display_kind (range_display_kind),
+- m_caret (*caret_exploc),
++ m_caret (caret_exploc),
+ m_original_idx (original_idx),
+ m_label (label)
+ {
+@@ -646,6 +643,9 @@ layout_range::intersects_line_p (linenum
+
+ #if CHECKING_P
+
++/* Default for when we don't care what the tab expansion is set to. */
++static const int def_tabstop = 8;
++
+ /* Create some expanded locations for testing layout_range. The filename
+ member of the explocs is set to the empty string. This member will only be
+ inspected by the calls to location_compute_display_column() made from the
+@@ -662,8 +662,11 @@ make_range (int start_line, int start_co
+ = {"", start_line, start_col, NULL, false};
+ const expanded_location finish_exploc
+ = {"", end_line, end_col, NULL, false};
+- return layout_range (&start_exploc, &finish_exploc, SHOW_RANGE_WITHOUT_CARET,
+- &start_exploc, 0, NULL);
++ return layout_range (exploc_with_display_col (start_exploc, def_tabstop),
++ exploc_with_display_col (finish_exploc, def_tabstop),
++ SHOW_RANGE_WITHOUT_CARET,
++ exploc_with_display_col (start_exploc, def_tabstop),
++ 0, NULL);
+ }
+
+ /* Selftests for layout_range::contains_point and
+@@ -964,7 +967,7 @@ layout::layout (diagnostic_context * con
+ : m_context (context),
+ m_pp (context->printer),
+ m_primary_loc (richloc->get_range (0)->m_loc),
+- m_exploc (richloc->get_expanded_location (0)),
++ m_exploc (richloc->get_expanded_location (0), context->tabstop),
+ m_colorizer (context, diagnostic_kind),
+ m_colorize_source_p (context->colorize_source_p),
+ m_show_labels_p (context->show_labels_p),
+@@ -1060,7 +1063,10 @@ layout::maybe_add_location_range (const
+
+ /* Everything is now known to be in the correct source file,
+ but it may require further sanitization. */
+- layout_range ri (&start, &finish, loc_range->m_range_display_kind, &caret,
++ layout_range ri (exploc_with_display_col (start, m_context->tabstop),
++ exploc_with_display_col (finish, m_context->tabstop),
++ loc_range->m_range_display_kind,
++ exploc_with_display_col (caret, m_context->tabstop),
+ original_idx, loc_range->m_label);
+
+ /* If we have a range that finishes before it starts (perhaps
+@@ -1394,7 +1400,7 @@ layout::calculate_x_offset_display ()
+ = get_line_bytes_without_trailing_whitespace (line.get_buffer (),
+ line.length ());
+ int eol_display_column
+- = cpp_display_width (line.get_buffer (), line_bytes);
++ = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop);
+ if (caret_display_column > eol_display_column
+ || !caret_display_column)
+ {
+@@ -1445,16 +1451,13 @@ layout::calculate_x_offset_display ()
+ }
+
+ /* Print line ROW of source code, potentially colorized at any ranges, and
+- populate *LBOUNDS_OUT.
+- LINE is the source line (not necessarily 0-terminated) and LINE_BYTES
+- is its length in bytes.
+- This function deals only with byte offsets, not display columns, so
+- m_x_offset_display must be converted from display to byte units. In
+- particular, LINE_BYTES and LBOUNDS_OUT are in bytes. */
++ return the line bounds. LINE is the source line (not necessarily
++ 0-terminated) and LINE_BYTES is its length in bytes. In order to handle both
++ colorization and tab expansion, this function tracks the line position in
++ both byte and display column units. */
+
+-void
+-layout::print_source_line (linenum_type row, const char *line, int line_bytes,
+- line_bounds *lbounds_out)
++line_bounds
++layout::print_source_line (linenum_type row, const char *line, int line_bytes)
+ {
+ m_colorizer.set_normal_text ();
+
+@@ -1469,30 +1472,29 @@ layout::print_source_line (linenum_type
+ else
+ pp_space (m_pp);
+
+- /* We will stop printing the source line at any trailing whitespace, and start
+- printing it as per m_x_offset_display. */
++ /* We will stop printing the source line at any trailing whitespace. */
+ line_bytes = get_line_bytes_without_trailing_whitespace (line,
+ line_bytes);
+- int x_offset_bytes = 0;
+- if (m_x_offset_display)
+- {
+- x_offset_bytes = cpp_display_column_to_byte_column (line, line_bytes,
+- m_x_offset_display);
+- /* In case the leading portion of the line that will be skipped over ends
+- with a character with wcwidth > 1, then it is possible we skipped too
+- much, so account for that by padding with spaces. */
+- const int overage
+- = cpp_byte_column_to_display_column (line, line_bytes, x_offset_bytes)
+- - m_x_offset_display;
+- for (int column = 0; column < overage; ++column)
+- pp_space (m_pp);
+- line += x_offset_bytes;
+- }
+
+- /* Print the line. */
+- int first_non_ws = INT_MAX;
+- int last_non_ws = 0;
+- for (int col_byte = 1 + x_offset_bytes; col_byte <= line_bytes; col_byte++)
++ /* This object helps to keep track of which display column we are at, which is
++ necessary for computing the line bounds in display units, for doing
++ tab expansion, and for implementing m_x_offset_display. */
++ cpp_display_width_computation dw (line, line_bytes, m_context->tabstop);
++
++ /* Skip the first m_x_offset_display display columns. In case the leading
++ portion that will be skipped ends with a character with wcwidth > 1, then
++ it is possible we skipped too much, so account for that by padding with
++ spaces. Note that this does the right thing too in case a tab was the last
++ character to be skipped over; the tab is effectively replaced by the
++ correct number of trailing spaces needed to offset by the desired number of
++ display columns. */
++ for (int skipped_display_cols = dw.advance_display_cols (m_x_offset_display);
++ skipped_display_cols > m_x_offset_display; --skipped_display_cols)
++ pp_space (m_pp);
++
++ /* Print the line and compute the line_bounds. */
++ line_bounds lbounds;
++ while (!dw.done ())
+ {
+ /* Assuming colorization is enabled for the caret and underline
+ characters, we may also colorize the associated characters
+@@ -1510,7 +1512,8 @@ layout::print_source_line (linenum_type
+ {
+ bool in_range_p;
+ point_state state;
+- in_range_p = get_state_at_point (row, col_byte,
++ const int start_byte_col = dw.bytes_processed () + 1;
++ in_range_p = get_state_at_point (row, start_byte_col,
+ 0, INT_MAX,
+ CU_BYTES,
+ &state);
+@@ -1519,22 +1522,44 @@ layout::print_source_line (linenum_type
+ else
+ m_colorizer.set_normal_text ();
+ }
+- char c = *line;
+- if (c == '\0' || c == '\t' || c == '\r')
+- c = ' ';
+- if (c != ' ')
++
++ /* Get the display width of the next character to be output, expanding
++ tabs and replacing some control bytes with spaces as necessary. */
++ const char *c = dw.next_byte ();
++ const int start_disp_col = dw.display_cols_processed () + 1;
++ const int this_display_width = dw.process_next_codepoint ();
++ if (*c == '\t')
++ {
++ /* The returned display width is the number of spaces into which the
++ tab should be expanded. */
++ for (int i = 0; i != this_display_width; ++i)
++ pp_space (m_pp);
++ continue;
++ }
++ if (*c == '\0' || *c == '\r')
+ {
+- last_non_ws = col_byte;
+- if (first_non_ws == INT_MAX)
+- first_non_ws = col_byte;
++ /* cpp_wcwidth() promises to return 1 for all control bytes, and we
++ want to output these as a single space too, so this case is
++ actually the same as the '\t' case. */
++ gcc_assert (this_display_width == 1);
++ pp_space (m_pp);
++ continue;
+ }
+- pp_character (m_pp, c);
+- line++;
++
++ /* We have a (possibly multibyte) character to output; update the line
++ bounds if it is not whitespace. */
++ if (*c != ' ')
++ {
++ lbounds.m_last_non_ws_disp_col = dw.display_cols_processed ();
++ if (lbounds.m_first_non_ws_disp_col == INT_MAX)
++ lbounds.m_first_non_ws_disp_col = start_disp_col;
++ }
++
++ /* Output the character. */
++ while (c != dw.next_byte ()) pp_character (m_pp, *c++);
+ }
+ print_newline ();
+-
+- lbounds_out->m_first_non_ws = first_non_ws;
+- lbounds_out->m_last_non_ws = last_non_ws;
++ return lbounds;
+ }
+
+ /* Determine if we should print an annotation line for ROW.
+@@ -1576,14 +1601,13 @@ layout::start_annotation_line (char marg
+ }
+
+ /* Print a line consisting of the caret/underlines for the given
+- source line. This function works with display columns, rather than byte
+- counts; in particular, LBOUNDS should be in display column units. */
++ source line. */
+
+ void
+ layout::print_annotation_line (linenum_type row, const line_bounds lbounds)
+ {
+ int x_bound = get_x_bound_for_row (row, m_exploc.m_display_col,
+- lbounds.m_last_non_ws);
++ lbounds.m_last_non_ws_disp_col);
+
+ start_annotation_line ();
+ pp_space (m_pp);
+@@ -1593,8 +1617,8 @@ layout::print_annotation_line (linenum_t
+ bool in_range_p;
+ point_state state;
+ in_range_p = get_state_at_point (row, column,
+- lbounds.m_first_non_ws,
+- lbounds.m_last_non_ws,
++ lbounds.m_first_non_ws_disp_col,
++ lbounds.m_last_non_ws_disp_col,
+ CU_DISPLAY_COLS,
+ &state);
+ if (in_range_p)
+@@ -1631,12 +1655,14 @@ layout::print_annotation_line (linenum_t
+ class line_label
+ {
+ public:
+- line_label (int state_idx, int column, label_text text)
++ line_label (diagnostic_context *context, int state_idx, int column,
++ label_text text)
+ : m_state_idx (state_idx), m_column (column),
+ m_text (text), m_label_line (0), m_has_vbar (true)
+ {
+ const int bytes = strlen (text.m_buffer);
+- m_display_width = cpp_display_width (text.m_buffer, bytes);
++ m_display_width
++ = cpp_display_width (text.m_buffer, bytes, context->tabstop);
+ }
+
+ /* Sorting is primarily by column, then by state index. */
+@@ -1696,7 +1722,7 @@ layout::print_any_labels (linenum_type r
+ if (text.m_buffer == NULL)
+ continue;
+
+- labels.safe_push (line_label (i, disp_col, text));
++ labels.safe_push (line_label (m_context, i, disp_col, text));
+ }
+ }
+
+@@ -1976,7 +2002,8 @@ public:
+
+ /* Get the range of bytes or display columns that HINT would affect. */
+ static column_range
+-get_affected_range (const fixit_hint *hint, enum column_unit col_unit)
++get_affected_range (diagnostic_context *context,
++ const fixit_hint *hint, enum column_unit col_unit)
+ {
+ expanded_location exploc_start = expand_location (hint->get_start_loc ());
+ expanded_location exploc_finish = expand_location (hint->get_next_loc ());
+@@ -1986,11 +2013,13 @@ get_affected_range (const fixit_hint *hi
+ int finish_column;
+ if (col_unit == CU_DISPLAY_COLS)
+ {
+- start_column = location_compute_display_column (exploc_start);
++ start_column
++ = location_compute_display_column (exploc_start, context->tabstop);
+ if (hint->insertion_p ())
+ finish_column = start_column - 1;
+ else
+- finish_column = location_compute_display_column (exploc_finish);
++ finish_column
++ = location_compute_display_column (exploc_finish, context->tabstop);
+ }
+ else
+ {
+@@ -2003,12 +2032,12 @@ get_affected_range (const fixit_hint *hi
+ /* Get the range of display columns that would be printed for HINT. */
+
+ static column_range
+-get_printed_columns (const fixit_hint *hint)
++get_printed_columns (diagnostic_context *context, const fixit_hint *hint)
+ {
+ expanded_location exploc = expand_location (hint->get_start_loc ());
+- int start_column = location_compute_display_column (exploc);
+- int hint_width = cpp_display_width (hint->get_string (),
+- hint->get_length ());
++ int start_column = location_compute_display_column (exploc, context->tabstop);
++ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (),
++ context->tabstop);
+ int final_hint_column = start_column + hint_width - 1;
+ if (hint->insertion_p ())
+ {
+@@ -2018,7 +2047,8 @@ get_printed_columns (const fixit_hint *h
+ {
+ exploc = expand_location (hint->get_next_loc ());
+ --exploc.column;
+- int finish_column = location_compute_display_column (exploc);
++ int finish_column
++ = location_compute_display_column (exploc, context->tabstop);
+ return column_range (start_column,
+ MAX (finish_column, final_hint_column));
+ }
+@@ -2035,12 +2065,14 @@ public:
+ correction (column_range affected_bytes,
+ column_range affected_columns,
+ column_range printed_columns,
+- const char *new_text, size_t new_text_len)
++ const char *new_text, size_t new_text_len,
++ int tabstop)
+ : m_affected_bytes (affected_bytes),
+ m_affected_columns (affected_columns),
+ m_printed_columns (printed_columns),
+ m_text (xstrdup (new_text)),
+ m_byte_length (new_text_len),
++ m_tabstop (tabstop),
+ m_alloc_sz (new_text_len + 1)
+ {
+ compute_display_cols ();
+@@ -2058,7 +2090,7 @@ public:
+
+ void compute_display_cols ()
+ {
+- m_display_cols = cpp_display_width (m_text, m_byte_length);
++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop);
+ }
+
+ void overwrite (int dst_offset, const char_span &src_span)
+@@ -2086,6 +2118,7 @@ public:
+ char *m_text;
+ size_t m_byte_length; /* Not including null-terminator. */
+ int m_display_cols;
++ int m_tabstop;
+ size_t m_alloc_sz;
+ };
+
+@@ -2121,13 +2154,15 @@ correction::ensure_terminated ()
+ class line_corrections
+ {
+ public:
+- line_corrections (const char *filename, linenum_type row)
+- : m_filename (filename), m_row (row)
++ line_corrections (diagnostic_context *context, const char *filename,
++ linenum_type row)
++ : m_context (context), m_filename (filename), m_row (row)
+ {}
+ ~line_corrections ();
+
+ void add_hint (const fixit_hint *hint);
+
++ diagnostic_context *m_context;
+ const char *m_filename;
+ linenum_type m_row;
+ auto_vec <correction *> m_corrections;
+@@ -2173,9 +2208,10 @@ source_line::source_line (const char *fi
+ void
+ line_corrections::add_hint (const fixit_hint *hint)
+ {
+- column_range affected_bytes = get_affected_range (hint, CU_BYTES);
+- column_range affected_columns = get_affected_range (hint, CU_DISPLAY_COLS);
+- column_range printed_columns = get_printed_columns (hint);
++ column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES);
++ column_range affected_columns = get_affected_range (m_context, hint,
++ CU_DISPLAY_COLS);
++ column_range printed_columns = get_printed_columns (m_context, hint);
+
+ /* Potentially consolidate. */
+ if (!m_corrections.is_empty ())
+@@ -2243,7 +2279,8 @@ line_corrections::add_hint (const fixit_
+ affected_columns,
+ printed_columns,
+ hint->get_string (),
+- hint->get_length ()));
++ hint->get_length (),
++ m_context->tabstop));
+ }
+
+ /* If there are any fixit hints on source line ROW, print them.
+@@ -2257,7 +2294,7 @@ layout::print_trailing_fixits (linenum_t
+ {
+ /* Build a list of correction instances for the line,
+ potentially consolidating hints (for the sake of readability). */
+- line_corrections corrections (m_exploc.file, row);
++ line_corrections corrections (m_context, m_exploc.file, row);
+ for (unsigned int i = 0; i < m_fixit_hints.length (); i++)
+ {
+ const fixit_hint *hint = m_fixit_hints[i];
+@@ -2499,15 +2536,11 @@ layout::print_line (linenum_type row)
+ if (!line)
+ return;
+
+- line_bounds lbounds;
+ print_leading_fixits (row);
+- print_source_line (row, line.get_buffer (), line.length (), &lbounds);
++ const line_bounds lbounds
++ = print_source_line (row, line.get_buffer (), line.length ());
+ if (should_print_annotation_line_p (row))
+- {
+- if (lbounds.m_first_non_ws != INT_MAX)
+- lbounds.convert_to_display_cols (line);
+- print_annotation_line (row, lbounds);
+- }
++ print_annotation_line (row, lbounds);
+ if (m_show_labels_p)
+ print_any_labels (row);
+ print_trailing_fixits (row);
+@@ -2670,9 +2703,11 @@ test_layout_x_offset_display_utf8 (const
+
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ (line_display_cols,
+- cpp_display_width (lspan.get_buffer (), lspan.length ()));
++ cpp_display_width (lspan.get_buffer (), lspan.length (),
++ def_tabstop));
+ ASSERT_EQ (line_display_cols,
+- location_compute_display_column (expand_location (line_end)));
++ location_compute_display_column (expand_location (line_end),
++ def_tabstop));
+ ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1),
+ "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8));
+
+@@ -2774,6 +2809,111 @@ test_layout_x_offset_display_utf8 (const
+
+ }
+
++static void
++test_layout_x_offset_display_tab (const line_table_case &case_)
++{
++ const char *content
++ = "This line is very long, so that we can use it to test the logic for "
++ "clipping long lines. Also this: `\t' is a tab that occupies 1 byte and "
++ "a variable number of display columns, starting at column #103.\n";
++
++ /* Number of bytes in the line, subtracting one to remove the newline. */
++ const int line_bytes = strlen (content) - 1;
++
++ /* The column where the tab begins. Byte or display is the same as there are
++ no multibyte characters earlier on the line. */
++ const int tab_col = 103;
++
++ /* Effective extra size of the tab beyond what a single space would have taken
++ up, indexed by tabstop. */
++ static const int num_tabstops = 11;
++ int extra_width[num_tabstops];
++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
++ {
++ const int this_tab_size = tabstop - (tab_col - 1) % tabstop;
++ extra_width[tabstop] = this_tab_size - 1;
++ }
++ /* Example of this calculation: if tabstop is 10, the tab starting at column
++ #103 has to expand into 8 spaces, covering columns 103-110, so that the
++ next character is at column #111. So it takes up 7 more columns than
++ a space would have taken up. */
++ ASSERT_EQ (7, extra_width[10]);
++
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
++ line_table_test ltt (case_);
++
++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1);
++
++ location_t line_end = linemap_position_for_column (line_table, line_bytes);
++
++ /* Don't attempt to run the tests if column data might be unavailable. */
++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Check that cpp_display_width handles the tabs as expected. */
++ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
++ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1)));
++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
++ {
++ ASSERT_EQ (line_bytes + extra_width[tabstop],
++ cpp_display_width (lspan.get_buffer (), lspan.length (),
++ tabstop));
++ ASSERT_EQ (line_bytes + extra_width[tabstop],
++ location_compute_display_column (expand_location (line_end),
++ tabstop));
++ }
++
++ /* Check that the tab is expanded to the expected number of spaces. */
++ rich_location richloc (line_table,
++ linemap_position_for_column (line_table,
++ tab_col + 1));
++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
++ {
++ test_diagnostic_context dc;
++ dc.tabstop = tabstop;
++ layout test_layout (&dc, &richloc, DK_ERROR);
++ test_layout.print_line (1);
++ const char *out = pp_formatted_text (dc.printer);
++ ASSERT_EQ (NULL, strchr (out, '\t'));
++ const char *left_quote = strchr (out, '`');
++ const char *right_quote = strchr (out, '\'');
++ ASSERT_NE (NULL, left_quote);
++ ASSERT_NE (NULL, right_quote);
++ ASSERT_EQ (right_quote - left_quote, extra_width[tabstop] + 2);
++ }
++
++ /* Check that the line is offset properly and that the tab is broken up
++ into the expected number of spaces when it is the last character skipped
++ over. */
++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
++ {
++ test_diagnostic_context dc;
++ dc.tabstop = tabstop;
++ static const int small_width = 24;
++ dc.caret_max_width = small_width - 4;
++ dc.min_margin_width = test_left_margin - test_linenum_sep + 1;
++ dc.show_line_numbers_p = true;
++ layout test_layout (&dc, &richloc, DK_ERROR);
++ test_layout.print_line (1);
++
++ /* We have arranged things so that two columns will be printed before
++ the caret. If the tab results in more than one space, this should
++ produce two spaces in the output; otherwise, it will be a single space
++ preceded by the opening quote before the tab character. */
++ const char *output1
++ = " 1 | ' is a tab that occupies 1 byte and a variable number of "
++ "display columns, starting at column #103.\n"
++ " | ^\n\n";
++ const char *output2
++ = " 1 | ` ' is a tab that occupies 1 byte and a variable number of "
++ "display columns, starting at column #103.\n"
++ " | ^\n\n";
++ const char *expected_output = (extra_width[tabstop] ? output1 : output2);
++ ASSERT_STREQ (expected_output, pp_formatted_text (dc.printer));
++ }
++}
++
++
+ /* Verify that diagnostic_show_locus works sanely on UNKNOWN_LOCATION. */
+
+ static void
+@@ -3854,6 +3994,27 @@ test_one_liner_labels_utf8 ()
+ }
+ }
+
++/* Make sure that colorization codes don't interrupt a multibyte
++ sequence, which would corrupt it. */
++static void
++test_one_liner_colorized_utf8 ()
++{
++ test_diagnostic_context dc;
++ dc.colorize_source_p = true;
++ diagnostic_color_init (&dc, DIAGNOSTICS_COLOR_YES);
++ const location_t pi = linemap_position_for_column (line_table, 12);
++ rich_location richloc (line_table, pi);
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++
++ /* In order to avoid having the test depend on exactly how the colorization
++ was effected, just confirm there are two pi characters in the output. */
++ const char *result = pp_formatted_text (dc.printer);
++ const char *null_term = result + strlen (result);
++ const char *first_pi = strstr (result, "\xcf\x80");
++ ASSERT_TRUE (first_pi && first_pi <= null_term - 2);
++ ASSERT_STR_CONTAINS (first_pi + 2, "\xcf\x80");
++}
++
+ /* Run the various one-liner tests. */
+
+ static void
+@@ -3884,8 +4045,10 @@ test_diagnostic_show_locus_one_liner_utf
+ ASSERT_EQ (31, LOCATION_COLUMN (line_end));
+
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+- ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length ()));
+- ASSERT_EQ (25, location_compute_display_column (expand_location (line_end)));
++ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (),
++ def_tabstop));
++ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end),
++ def_tabstop));
+
+ test_one_liner_simple_caret_utf8 ();
+ test_one_liner_caret_and_range_utf8 ();
+@@ -3900,6 +4063,7 @@ test_diagnostic_show_locus_one_liner_utf
+ test_one_liner_many_fixits_1_utf8 ();
+ test_one_liner_many_fixits_2_utf8 ();
+ test_one_liner_labels_utf8 ();
++ test_one_liner_colorized_utf8 ();
+ }
+
+ /* Verify that gcc_rich_location::add_location_if_nearby works. */
+@@ -4272,25 +4436,28 @@ test_overlapped_fixit_printing (const li
+ /* Unit-test the line_corrections machinery. */
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+- ASSERT_EQ (column_range (12, 12), get_affected_range (hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0));
++ get_affected_range (&dc, hint_0, CU_BYTES));
++ ASSERT_EQ (column_range (12, 12),
++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+- ASSERT_EQ (column_range (18, 18), get_affected_range (hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1));
++ get_affected_range (&dc, hint_1, CU_BYTES));
++ ASSERT_EQ (column_range (18, 18),
++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+- ASSERT_EQ (column_range (29, 28), get_affected_range (hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (29, 28),
+- get_affected_range (hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (29, 29), get_printed_columns (hint_2));
++ get_affected_range (&dc, hint_2, CU_BYTES));
++ ASSERT_EQ (column_range (29, 28),
++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (tmp.get_filename (), 1);
++ line_corrections lc (&dc, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4484,25 +4651,28 @@ test_overlapped_fixit_printing_utf8 (con
+ /* Unit-test the line_corrections machinery. */
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+- ASSERT_EQ (column_range (14, 14), get_affected_range (hint_0, CU_BYTES));
++ ASSERT_EQ (column_range (14, 14),
++ get_affected_range (&dc, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0));
++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+- ASSERT_EQ (column_range (22, 22), get_affected_range (hint_1, CU_BYTES));
++ ASSERT_EQ (column_range (22, 22),
++ get_affected_range (&dc, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1));
++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+- ASSERT_EQ (column_range (35, 34), get_affected_range (hint_2, CU_BYTES));
++ ASSERT_EQ (column_range (35, 34),
++ get_affected_range (&dc, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (30, 29),
+- get_affected_range (hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (30, 30), get_printed_columns (hint_2));
++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (tmp.get_filename (), 1);
++ line_corrections lc (&dc, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4689,6 +4859,8 @@ test_overlapped_fixit_printing_2 (const
+
+ /* Two insertions, in the wrong order. */
+ {
++ test_diagnostic_context dc;
++
+ rich_location richloc (line_table, col_20);
+ richloc.add_fixit_insert_before (col_23, "{");
+ richloc.add_fixit_insert_before (col_21, "}");
+@@ -4696,14 +4868,15 @@ test_overlapped_fixit_printing_2 (const
+ /* These fixits should be accepted; they can't be consolidated. */
+ ASSERT_EQ (2, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+- ASSERT_EQ (column_range (23, 22), get_affected_range (hint_0, CU_BYTES));
+- ASSERT_EQ (column_range (23, 23), get_printed_columns (hint_0));
++ ASSERT_EQ (column_range (23, 22),
++ get_affected_range (&dc, hint_0, CU_BYTES));
++ ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+- ASSERT_EQ (column_range (21, 20), get_affected_range (hint_1, CU_BYTES));
+- ASSERT_EQ (column_range (21, 21), get_printed_columns (hint_1));
++ ASSERT_EQ (column_range (21, 20),
++ get_affected_range (&dc, hint_1, CU_BYTES));
++ ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1));
+
+ /* Verify that they're printed correctly. */
+- test_diagnostic_context dc;
+ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
+ ASSERT_STREQ (" int a5[][0][0] = { 1, 2 };\n"
+ " ^\n"
+@@ -4955,6 +5128,65 @@ test_fixit_deletion_affecting_newline (c
+ pp_formatted_text (dc.printer));
+ }
+
++static void
++test_tab_expansion (const line_table_case &case_)
++{
++ /* Create a tempfile and write some text to it. This example uses a tabstop
++ of 8, as the column numbers attempt to indicate:
++
++ .....................000.01111111111.22222333333 display
++ .....................123.90123456789.56789012345 columns */
++ const char *content = " \t This: `\t' is a tab.\n";
++ /* ....................000 00000011111 11111222222 byte
++ ....................123 45678901234 56789012345 columns */
++
++ const int tabstop = 8;
++ const int first_non_ws_byte_col = 7;
++ const int right_quote_byte_col = 15;
++ const int last_byte_col = 25;
++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop));
++
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
++ line_table_test ltt (case_);
++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1);
++
++ /* Don't attempt to run the tests if column data might be unavailable. */
++ location_t line_end = linemap_position_for_column (line_table, last_byte_col);
++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Check that the leading whitespace with mixed tabs and spaces is expanded
++ into 11 spaces. Recall that print_line() also puts one space before
++ everything too. */
++ {
++ test_diagnostic_context dc;
++ dc.tabstop = tabstop;
++ rich_location richloc (line_table,
++ linemap_position_for_column (line_table,
++ first_non_ws_byte_col));
++ layout test_layout (&dc, &richloc, DK_ERROR);
++ test_layout.print_line (1);
++ ASSERT_STREQ (" This: ` ' is a tab.\n"
++ " ^\n",
++ pp_formatted_text (dc.printer));
++ }
++
++ /* Confirm the display width was tracked correctly across the internal tab
++ as well. */
++ {
++ test_diagnostic_context dc;
++ dc.tabstop = tabstop;
++ rich_location richloc (line_table,
++ linemap_position_for_column (line_table,
++ right_quote_byte_col));
++ layout test_layout (&dc, &richloc, DK_ERROR);
++ test_layout.print_line (1);
++ ASSERT_STREQ (" This: ` ' is a tab.\n"
++ " ^\n",
++ pp_formatted_text (dc.printer));
++ }
++}
++
+ /* Verify that line numbers are correctly printed for the case of
+ a multiline range in which the width of the line numbers changes
+ (e.g. from "9" to "10"). */
+@@ -5012,6 +5244,7 @@ diagnostic_show_locus_c_tests ()
+ test_layout_range_for_multiple_lines ();
+
+ for_each_line_table_case (test_layout_x_offset_display_utf8);
++ for_each_line_table_case (test_layout_x_offset_display_tab);
+
+ test_get_line_bytes_without_trailing_whitespace ();
+
+@@ -5029,6 +5262,7 @@ diagnostic_show_locus_c_tests ()
+ for_each_line_table_case (test_fixit_insert_containing_newline_2);
+ for_each_line_table_case (test_fixit_replace_containing_newline);
+ for_each_line_table_case (test_fixit_deletion_affecting_newline);
++ for_each_line_table_case (test_tab_expansion);
+
+ test_line_numbers_multiline_range ();
+ }
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+--- a/gcc/doc/invoke.texi 2021-12-24 20:23:46.876739587 -0800
++++ b/gcc/doc/invoke.texi 2021-12-25 01:20:53.487636494 -0800
+@@ -293,7 +293,9 @@ Objective-C and Objective-C++ Dialects}.
+ -fdiagnostics-show-template-tree -fno-elide-type @gol
+ -fdiagnostics-path-format=@r{[}none@r{|}separate-events@r{|}inline-events@r{]} @gol
+ -fdiagnostics-show-path-depths @gol
+--fno-show-column}
++-fno-show-column @gol
++-fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol
++-fdiagnostics-column-origin=@var{origin}}
+
+ @item Warning Options
+ @xref{Warning Options,,Options to Request or Suppress Warnings}.
+@@ -4424,6 +4426,31 @@ Do not print column numbers in diagnosti
+ diagnostics are being scanned by a program that does not understand the
+ column numbers, such as @command{dejagnu}.
+
++@item -fdiagnostics-column-unit=@var{UNIT}
++@opindex fdiagnostics-column-unit
++Select the units for the column number. This affects traditional diagnostics
++(in the absence of @option{-fno-show-column}), as well as JSON format
++diagnostics if requested.
++
++The default @var{UNIT}, @samp{display}, considers the number of display
++columns occupied by each character. This may be larger than the number
++of bytes required to encode the character, in the case of tab
++characters, or it may be smaller, in the case of multibyte characters.
++For example, the character ``GREEK SMALL LETTER PI (U+03C0)'' occupies one
++display column, and its UTF-8 encoding requires two bytes; the character
++``SLIGHTLY SMILING FACE (U+1F642)'' occupies two display columns, and
++its UTF-8 encoding requires four bytes.
++
++Setting @var{UNIT} to @samp{byte} changes the column number to the raw byte
++count in all cases, as was traditionally output by GCC prior to version 11.1.0.
++
++@item -fdiagnostics-column-origin=@var{ORIGIN}
++@opindex fdiagnostics-column-origin
++Select the origin for column numbers, i.e. the column number assigned to the
++first column. The default value of 1 corresponds to traditional GCC
++behavior and to the GNU style guide. Some utilities may perform better with an
++origin of 0; any non-negative value may be specified.
++
+ @item -fdiagnostics-format=@var{FORMAT}
+ @opindex fdiagnostics-format
+ Select a different format for printing diagnostics.
+@@ -4459,11 +4486,15 @@ might be printed in JSON form (after for
+ "locations": [
+ @{
+ "caret": @{
++ "display-column": 3,
++ "byte-column": 3,
+ "column": 3,
+ "file": "misleading-indentation.c",
+ "line": 15
+ @},
+ "finish": @{
++ "display-column": 4,
++ "byte-column": 4,
+ "column": 4,
+ "file": "misleading-indentation.c",
+ "line": 15
+@@ -4479,6 +4510,8 @@ might be printed in JSON form (after for
+ "locations": [
+ @{
+ "caret": @{
++ "display-column": 5,
++ "byte-column": 5,
+ "column": 5,
+ "file": "misleading-indentation.c",
+ "line": 17
+@@ -4488,6 +4521,7 @@ might be printed in JSON form (after for
+ "message": "...this statement, but the latter is @dots{}"
+ @}
+ ]
++ "column-origin": 1,
+ @},
+ @dots{}
+ ]
+@@ -4500,10 +4534,34 @@ A diagnostic has a @code{kind}. If this
+ an @code{option} key describing the command-line option controlling the
+ warning.
+
+-A diagnostic can contain zero or more locations. Each location has up
+-to three positions within it: a @code{caret} position and optional
+-@code{start} and @code{finish} positions. A location can also have
+-an optional @code{label} string. For example, this error:
++A diagnostic can contain zero or more locations. Each location has an
++optional @code{label} string and up to three positions within it: a
++@code{caret} position and optional @code{start} and @code{finish} positions.
++A position is described by a @code{file} name, a @code{line} number, and
++three numbers indicating a column position:
++@itemize @bullet
++
++@item
++@code{display-column} counts display columns, accounting for tabs and
++multibyte characters.
++
++@item
++@code{byte-column} counts raw bytes.
++
++@item
++@code{column} is equal to one of
++the previous two, as dictated by the @option{-fdiagnostics-column-unit}
++option.
++
++@end itemize
++All three columns are relative to the origin specified by
++@option{-fdiagnostics-column-origin}, which is typically equal to 1 but may
++be set, for instance, to 0 for compatibility with other utilities that
++number columns from 0. The column origin is recorded in the JSON output in
++the @code{column-origin} tag. In the remaining examples below, the extra
++column number outputs have been omitted for brevity.
++
++For example, this error:
+
+ @smallexample
+ bad-binary-ops.c:64:23: error: invalid operands to binary + (have 'S' @{aka
+diff --git a/gcc/input.c b/gcc/input.c
+--- a/gcc/input.c 2020-07-22 23:35:17.664388078 -0700
++++ b/gcc/input.c 2021-12-25 01:20:53.487636494 -0800
+@@ -913,7 +913,7 @@ make_location (location_t caret, source_
+ source line in order to calculate the display width. If that cannot be done
+ for any reason, then returns the byte column as a fallback. */
+ int
+-location_compute_display_column (expanded_location exploc)
++location_compute_display_column (expanded_location exploc, int tabstop)
+ {
+ if (!(exploc.file && *exploc.file && exploc.line && exploc.column))
+ return exploc.column;
+@@ -921,7 +921,7 @@ location_compute_display_column (expande
+ /* If line is NULL, this function returns exploc.column which is the
+ desired fallback. */
+ return cpp_byte_column_to_display_column (line.get_buffer (), line.length (),
+- exploc.column);
++ exploc.column, tabstop);
+ }
+
+ /* Dump statistics to stderr about the memory usage of the line_table
+@@ -3608,33 +3608,46 @@ test_line_offset_overflow ()
+
+ void test_cpp_utf8 ()
+ {
++ const int def_tabstop = 8;
+ /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */
+ {
+- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8);
++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop);
+ ASSERT_EQ (8, w_bad);
+- int w_ctrl = cpp_display_width ("\r\t\n\v\0\1", 6);
+- ASSERT_EQ (6, w_ctrl);
++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop);
++ ASSERT_EQ (5, w_ctrl);
+ }
+
+ /* Verify that wcwidth of valid UTF-8 is as expected. */
+ {
+- const int w_pi = cpp_display_width ("\xcf\x80", 2);
++ const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop);
+ ASSERT_EQ (1, w_pi);
+- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4);
++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop);
+ ASSERT_EQ (2, w_emoji);
+- const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2);
++ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2,
++ def_tabstop);
+ ASSERT_EQ (1, w_umlaut_precomposed);
+- const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3);
++ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3,
++ def_tabstop);
+ ASSERT_EQ (1, w_umlaut_combining);
+- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3);
++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop);
+ ASSERT_EQ (2, w_han);
+- const int w_ascii = cpp_display_width ("GCC", 3);
++ const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop);
+ ASSERT_EQ (3, w_ascii);
+ const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82"
+- "\x9f! \xe4\xb8\xba y\xcc\x88", 24);
++ "\x9f! \xe4\xb8\xba y\xcc\x88",
++ 24, def_tabstop);
+ ASSERT_EQ (18, w_mixed);
+ }
+
++ /* Verify that display width properly expands tabs. */
++ {
++ const char *tstr = "\tabc\td";
++ ASSERT_EQ (6, cpp_display_width (tstr, 6, 1));
++ ASSERT_EQ (10, cpp_display_width (tstr, 6, 3));
++ ASSERT_EQ (17, cpp_display_width (tstr, 6, 8));
++ ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8));
++ }
++
+ /* Verify that cpp_byte_column_to_display_column can go past the end,
+ and similar edge cases. */
+ {
+@@ -3645,10 +3658,13 @@ void test_cpp_utf8 ()
+ /* 111122223456
+ Byte columns. */
+
+- ASSERT_EQ (5, cpp_display_width (str, 6));
+- ASSERT_EQ (105, cpp_byte_column_to_display_column (str, 6, 106));
+- ASSERT_EQ (10000, cpp_byte_column_to_display_column (NULL, 0, 10000));
+- ASSERT_EQ (0, cpp_byte_column_to_display_column (NULL, 10000, 0));
++ ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop));
++ ASSERT_EQ (105,
++ cpp_byte_column_to_display_column (str, 6, 106, def_tabstop));
++ ASSERT_EQ (10000,
++ cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop));
++ ASSERT_EQ (0,
++ cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop));
+ }
+
+ /* Verify that cpp_display_column_to_byte_column can go past the end,
+@@ -3662,21 +3678,25 @@ void test_cpp_utf8 ()
+ /* 000000000000000000000000000000000111111
+ 111122223333444456666777788889999012345
+ Byte columns. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2));
+- ASSERT_EQ (15, cpp_display_column_to_byte_column (str, 15, 11));
+- ASSERT_EQ (115, cpp_display_column_to_byte_column (str, 15, 111));
+- ASSERT_EQ (10000, cpp_display_column_to_byte_column (NULL, 0, 10000));
+- ASSERT_EQ (0, cpp_display_column_to_byte_column (NULL, 10000, 0));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop));
++ ASSERT_EQ (15,
++ cpp_display_column_to_byte_column (str, 15, 11, def_tabstop));
++ ASSERT_EQ (115,
++ cpp_display_column_to_byte_column (str, 15, 111, def_tabstop));
++ ASSERT_EQ (10000,
++ cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop));
++ ASSERT_EQ (0,
++ cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop));
+
+ /* Verify that we do not interrupt a UTF-8 sequence. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop));
+
+ for (int byte_col = 1; byte_col <= 15; ++byte_col)
+ {
+- const int disp_col = cpp_byte_column_to_display_column (str, 15,
+- byte_col);
+- const int byte_col2 = cpp_display_column_to_byte_column (str, 15,
+- disp_col);
++ const int disp_col
++ = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop);
++ const int byte_col2
++ = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop);
+
+ /* If we ask for the display column in the middle of a UTF-8
+ sequence, it will return the length of the partial sequence,
+diff --git a/gcc/input.h b/gcc/input.h
+--- a/gcc/input.h 2020-07-22 23:35:17.664388078 -0700
++++ b/gcc/input.h 2021-12-25 01:20:53.487636494 -0800
+@@ -38,7 +38,9 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER
+
+ extern bool is_location_from_builtin_token (location_t);
+ extern expanded_location expand_location (location_t);
+-extern int location_compute_display_column (expanded_location);
++
++extern int location_compute_display_column (expanded_location exploc,
++ int tabstop);
+
+ /* A class capturing the bounds of a buffer, to allow for run-time
+ bounds-checking in a checked build. */
+diff --git a/gcc/opts.c b/gcc/opts.c
+--- a/gcc/opts.c 2020-07-22 23:35:17.708388562 -0700
++++ b/gcc/opts.c 2021-12-25 01:20:53.487636494 -0800
+@@ -2439,6 +2439,14 @@ common_handle_option (struct gcc_options
+ dc->parseable_fixits_p = value;
+ break;
+
++ case OPT_fdiagnostics_column_unit_:
++ dc->column_unit = (enum diagnostics_column_unit)value;
++ break;
++
++ case OPT_fdiagnostics_column_origin_:
++ dc->column_origin = value;
++ break;
++
+ case OPT_fdiagnostics_show_cwe:
+ dc->show_cwe = value;
+ break;
+@@ -2825,6 +2833,12 @@ common_handle_option (struct gcc_options
+ check_alignment_argument (loc, arg, "functions");
+ break;
+
++ case OPT_ftabstop_:
++ /* It is documented that we silently ignore silly values. */
++ if (value >= 1 && value <= 100)
++ dc->tabstop = value;
++ break;
++
+ default:
+ /* If the flag was handled in a standard way, assume the lack of
+ processing here is intentional. */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2020-07-22 23:35:17.908390765 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:20:53.487636494 -0800
+@@ -8,17 +8,22 @@
+ We can't rely on any ordering of the keys. */
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
++/* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"#error message\"" } */
+
+ /* { dg-regexp "\"caret\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 2" } */
++/* { dg-regexp "\"display-column\": 2" } */
++/* { dg-regexp "\"byte-column\": 2" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 6" } */
++/* { dg-regexp "\"display-column\": 6" } */
++/* { dg-regexp "\"byte-column\": 6" } */
+
+ /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
+ /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2020-07-22 23:35:17.908390765 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:20:53.487636494 -0800
+@@ -8,6 +8,7 @@
+ We can't rely on any ordering of the keys. */
+
+ /* { dg-regexp "\"kind\": \"warning\"" } */
++/* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Wcpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+@@ -16,11 +17,15 @@
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 2" } */
++/* { dg-regexp "\"display-column\": 2" } */
++/* { dg-regexp "\"byte-column\": 2" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 8" } */
++/* { dg-regexp "\"display-column\": 8" } */
++/* { dg-regexp "\"byte-column\": 8" } */
+
+ /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
+ /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2020-07-22 23:35:17.908390765 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:20:53.487636494 -0800
+@@ -8,6 +8,7 @@
+ We can't rely on any ordering of the keys. */
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
++/* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+@@ -16,11 +17,15 @@
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 2" } */
++/* { dg-regexp "\"display-column\": 2" } */
++/* { dg-regexp "\"byte-column\": 2" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */
+ /* { dg-regexp "\"line\": 4" } */
+ /* { dg-regexp "\"column\": 8" } */
++/* { dg-regexp "\"display-column\": 8" } */
++/* { dg-regexp "\"byte-column\": 8" } */
+
+ /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
+ /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2020-07-22 23:35:17.908390765 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:20:53.487636494 -0800
+@@ -24,15 +24,20 @@ int test (void)
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 5" } */
++/* { dg-regexp "\"display-column\": 5" } */
++/* { dg-regexp "\"byte-column\": 5" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 10" } */
++/* { dg-regexp "\"display-column\": 10" } */
++/* { dg-regexp "\"byte-column\": 10" } */
+
+ /* The outer diagnostic. */
+
+ /* { dg-regexp "\"kind\": \"warning\"" } */
++/* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */
+ /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */
+@@ -41,11 +46,15 @@ int test (void)
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+ /* { dg-regexp "\"line\": 6" } */
+ /* { dg-regexp "\"column\": 3" } */
++/* { dg-regexp "\"display-column\": 3" } */
++/* { dg-regexp "\"byte-column\": 3" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+ /* { dg-regexp "\"line\": 6" } */
+ /* { dg-regexp "\"column\": 4" } */
++/* { dg-regexp "\"display-column\": 4" } */
++/* { dg-regexp "\"byte-column\": 4" } */
+
+ /* More from the nested diagnostic (we can't guarantee what order the
+ "file" keys are consumed). */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2020-07-22 23:35:17.908390765 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:20:53.487636494 -0800
+@@ -13,6 +13,7 @@ int test (struct s *ptr)
+ We can't rely on any ordering of the keys. */
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
++/* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \".*\"" } */
+
+ /* Verify fix-it hints. */
+@@ -23,11 +24,15 @@ int test (struct s *ptr)
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 15" } */
++/* { dg-regexp "\"display-column\": 15" } */
++/* { dg-regexp "\"byte-column\": 15" } */
+
+ /* { dg-regexp "\"next\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 21" } */
++/* { dg-regexp "\"display-column\": 21" } */
++/* { dg-regexp "\"byte-column\": 21" } */
+
+ /* { dg-regexp "\"fixits\": \[\[\{\}, \]*\]" } */
+
+@@ -35,11 +40,15 @@ int test (struct s *ptr)
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 15" } */
++/* { dg-regexp "\"display-column\": 15" } */
++/* { dg-regexp "\"byte-column\": 15" } */
+
+ /* { dg-regexp "\"finish\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
+ /* { dg-regexp "\"line\": 8" } */
+ /* { dg-regexp "\"column\": 20" } */
++/* { dg-regexp "\"display-column\": 20" } */
++/* { dg-regexp "\"byte-column\": 20" } */
+
+ /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
+ /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-1.c b/gcc/testsuite/c-c++-common/diagnostic-units-1.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-1.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-1.c 2021-12-25 01:20:53.487636494 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -Wmultichar" } */
++
++/* column units: bytes (via arg)
++ column origin: 1 (via default)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-2.c b/gcc/testsuite/c-c++-common/diagnostic-units-2.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-2.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-2.c 2021-12-25 01:20:53.487636494 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -Wmultichar" } */
++
++/* column units: display (via arg)
++ column origin: 1 (via default)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "18: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "25: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-3.c b/gcc/testsuite/c-c++-common/diagnostic-units-3.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-3.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-3.c 2021-12-25 01:20:53.487636494 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=200 -Wmultichar" } */
++
++/* column units: bytes (via arg)
++ column origin: 1 (via fallback from overly large argument)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-4.c b/gcc/testsuite/c-c++-common/diagnostic-units-4.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-4.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-4.c 2021-12-25 01:20:53.487636494 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */
++
++/* column units: bytes (via arg)
++ column origin: 0 (via arg)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "10: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "18: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-5.c b/gcc/testsuite/c-c++-common/diagnostic-units-5.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-5.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-5.c 2021-12-25 01:20:53.491636427 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */
++
++/* column units: display (via arg)
++ column origin: 0 (via arg)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "17: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "24: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-6.c b/gcc/testsuite/c-c++-common/diagnostic-units-6.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-6.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-6.c 2021-12-25 01:20:53.491636427 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=100 -Wmultichar" } */
++
++/* column units: bytes (via arg)
++ column origin: 100 (via arg)
++ tabstop: 8 (via default) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "110: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "117: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "118: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-7.c b/gcc/testsuite/c-c++-common/diagnostic-units-7.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-7.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-7.c 2021-12-25 01:20:53.491636427 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */
++
++/* column units: bytes (via arg)
++ column origin: 1 (via default)
++ tabstop: 9 (via arg) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "20: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-8.c b/gcc/testsuite/c-c++-common/diagnostic-units-8.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-units-8.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-units-8.c 2021-12-25 01:20:53.491636427 -0800
+@@ -0,0 +1,28 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */
++
++/* column units: display (via default)
++ column origin: 1 (via default)
++ tabstop: 9 (via arg) */
++
++/* This line starts with a tab. */
++ int c1 = 'c1'; /* { dg-warning "19: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c1 = 'c1';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces. */
++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c2 = 'c2';
++ ^~~~
++ { dg-end-multiline-output "" } */
++
++/* This line starts with <tabstop> spaces and has an internal tab after
++ a space. */
++ int c3 = 'c3'; /* { dg-warning "28: multi-character character constant" } */
++/* { dg-begin-multiline-output "" }
++ int c3 = 'c3';
++ ^~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/c-c++-common/missing-close-symbol.c b/gcc/testsuite/c-c++-common/missing-close-symbol.c
+--- a/gcc/testsuite/c-c++-common/missing-close-symbol.c 2020-07-22 23:35:17.912390810 -0700
++++ b/gcc/testsuite/c-c++-common/missing-close-symbol.c 2021-12-25 01:20:53.491636427 -0800
+@@ -24,9 +24,9 @@ void test_static_assert_different_line (
+ _Static_assert(sizeof(int) >= sizeof(char), /* { dg-message "to match this '\\('" } */
+ "msg"; /* { dg-error "expected '\\)' before ';' token" } */
+ /* { dg-begin-multiline-output "" }
+- "msg";
+- ^
+- )
++ "msg";
++ ^
++ )
+ { dg-end-multiline-output "" } */
+ /* { dg-begin-multiline-output "" }
+ _Static_assert(sizeof(int) >= sizeof(char),
+diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c
+--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2020-07-22 23:35:17.904390722 -0700
++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2021-12-25 01:20:53.487636494 -0800
+@@ -36,20 +36,20 @@ int fn_6 (int a, int b, int c)
+ /* ... */
+ if ((err = foo (a)) != 0)
+ goto fail;
+- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */
++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */
+ goto fail;
+- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ if ((err = foo (c)) != 0)
+ goto fail;
+ /* ... */
+
+ /* { dg-begin-multiline-output "" }
+- if ((err = foo (b)) != 0)
+- ^~
++ if ((err = foo (b)) != 0)
++ ^~
+ { dg-end-multiline-output "" } */
+ /* { dg-begin-multiline-output "" }
+- goto fail;
+- ^~~~
++ goto fail;
++ ^~~~
+ { dg-end-multiline-output "" } */
+
+ fail:
+diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c
+--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2020-07-22 23:35:17.904390722 -0700
++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2021-12-25 01:20:53.487636494 -0800
+@@ -65,9 +65,9 @@ int fn_6 (int a, int b, int c)
+ /* ... */
+ if ((err = foo (a)) != 0)
+ goto fail;
+- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */
++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */
+ goto fail;
+- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ if ((err = foo (c)) != 0)
+ goto fail;
+ /* ... */
+@@ -178,7 +178,7 @@ void fn_16_tabs (void)
+ while (flagA)
+ if (flagB) /* { dg-message "7: this 'if' clause does not guard..." } */
+ foo (0);
+- foo (1);/* { dg-message "2: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
++ foo (1);/* { dg-message "9: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ }
+
+ void fn_17_spaces (void)
+diff --git a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c
+--- a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2020-07-22 23:35:18.124393144 -0700
++++ b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2021-12-25 01:20:53.491636427 -0800
+@@ -288,7 +288,7 @@ int test_3 (int x, int y)
+ | | ~~~~~~~~~~
+ | | |
+ | | (4) ...to here
+- | NN | to dereference it above
++ | NN | to dereference it above
+ | NN | return *ptr;
+ | | ~~~~
+ | | |
+diff --git a/gcc/testsuite/gcc.dg/bad-binary-ops.c b/gcc/testsuite/gcc.dg/bad-binary-ops.c
+--- a/gcc/testsuite/gcc.dg/bad-binary-ops.c 2020-07-22 23:35:18.128393190 -0700
++++ b/gcc/testsuite/gcc.dg/bad-binary-ops.c 2021-12-25 01:20:53.491636427 -0800
+@@ -35,10 +35,10 @@ int test_2 (void)
+ ~~~~~~~~~~~~~~~~
+ |
+ struct s
+- + some_other_function ());
+- ^ ~~~~~~~~~~~~~~~~~~~~~~
+- |
+- struct t
++ + some_other_function ());
++ ^ ~~~~~~~~~~~~~~~~~~~~~~
++ |
++ struct t
+ { dg-end-multiline-output "" } */
+ }
+
+diff --git a/gcc/testsuite/gcc.dg/format/branch-1.c b/gcc/testsuite/gcc.dg/format/branch-1.c
+--- a/gcc/testsuite/gcc.dg/format/branch-1.c 2020-07-22 23:35:18.152393454 -0700
++++ b/gcc/testsuite/gcc.dg/format/branch-1.c 2021-12-25 01:20:53.491636427 -0800
+@@ -10,7 +10,7 @@ foo (long l, int nfoo)
+ {
+ printf ((nfoo > 1) ? "%d foos" : "%d foo", nfoo);
+ printf ((l > 1) ? "%d foos" /* { dg-warning "23:int" "wrong type in conditional expr" } */
+- : "%d foo", l); /* { dg-warning "16:int" "wrong type in conditional expr" } */
++ : "%d foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */
+ printf ((l > 1) ? "%ld foos" : "%d foo", l); /* { dg-warning "36:int" "wrong type in conditional expr" } */
+ printf ((l > 1) ? "%d foos" : "%ld foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */
+ /* Should allow one case to have extra arguments. */
+diff --git a/gcc/testsuite/gcc.dg/format/pr79210.c b/gcc/testsuite/gcc.dg/format/pr79210.c
+--- a/gcc/testsuite/gcc.dg/format/pr79210.c 2020-07-22 23:35:18.152393454 -0700
++++ b/gcc/testsuite/gcc.dg/format/pr79210.c 2021-12-25 01:20:53.491636427 -0800
+@@ -20,4 +20,4 @@ LPFC_VPORT_ATTR_R(peer_port_login,
+ "Allow peer ports on the same physical port to login to each "
+ "other.");
+
+-/* { dg-warning "6: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */
++/* { dg-warning "20: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */
+diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c
+--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2020-07-22 23:35:18.172393674 -0700
++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2021-12-25 01:20:53.491636427 -0800
+@@ -540,15 +540,15 @@ void test_builtin_types_compatible_p (un
+ __emit_expression_range (0,
+ f (i) + __builtin_types_compatible_p (long, int)); /* { dg-warning "range" } */
+ /* { dg-begin-multiline-output "" }
+- f (i) + __builtin_types_compatible_p (long, int));
+- ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
++ f (i) + __builtin_types_compatible_p (long, int));
++ ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ { dg-end-multiline-output "" } */
+
+ __emit_expression_range (0,
+ __builtin_types_compatible_p (long, int) + f (i)); /* { dg-warning "range" } */
+ /* { dg-begin-multiline-output "" }
+- __builtin_types_compatible_p (long, int) + f (i));
+- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
++ __builtin_types_compatible_p (long, int) + f (i));
++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
+ { dg-end-multiline-output "" } */
+ }
+
+@@ -671,8 +671,8 @@ void test_multiple_ordinary_maps (void)
+ /* { dg-begin-multiline-output "" }
+ __emit_expression_range (0, foo (0,
+ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"));
+- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
++ "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"));
++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ { dg-end-multiline-output "" } */
+
+ /* Another expression that transitions between ordinary maps; this
+@@ -685,8 +685,8 @@ void test_multiple_ordinary_maps (void)
+ /* { dg-begin-multiline-output "" }
+ __emit_expression_range (0, foo (0, "01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789",
+ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- 0));
+- ~~
++ 0));
++ ~~
+ { dg-end-multiline-output "" } */
+ }
+
+diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c
+--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2020-07-22 23:35:18.172393674 -0700
++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2021-12-25 01:20:53.491636427 -0800
+@@ -335,11 +335,11 @@ pr87652 (const char *stem, int counter)
+ /* { dg-error "unable to read substring location: unable to read source line" "" { target c } 329 } */
+ /* { dg-error "unable to read substring location: failed to get ordinary maps" "" { target c++ } 329 } */
+ /* { dg-begin-multiline-output "" }
+- __emit_string_literal_range(__FILE__":%5d: " format, \
++ __emit_string_literal_range(__FILE__":%5d: " format, \
+ ^~~~~~~~
+ { dg-end-multiline-output "" { target c } } */
+ /* { dg-begin-multiline-output "" }
+- __emit_string_literal_range(__FILE__":%5d: " format, \
++ __emit_string_literal_range(__FILE__":%5d: " format, \
+ ^
+ { dg-end-multiline-output "" { target c++ } } */
+
+diff --git a/gcc/testsuite/gcc.dg/redecl-4.c b/gcc/testsuite/gcc.dg/redecl-4.c
+--- a/gcc/testsuite/gcc.dg/redecl-4.c 2020-07-22 23:35:18.192393895 -0700
++++ b/gcc/testsuite/gcc.dg/redecl-4.c 2021-12-25 01:20:53.491636427 -0800
+@@ -15,7 +15,7 @@ f (void)
+ /* Should get format warnings even though the built-in declaration
+ isn't "visible". */
+ printf (
+- "%s", 1); /* { dg-warning "8:format" } */
++ "%s", 1); /* { dg-warning "15:format" } */
+ /* The type of strcmp here should have no prototype. */
+ if (0)
+ strcmp (1);
+diff --git a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C
+--- a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2020-07-22 23:35:17.972391472 -0700
++++ b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2021-12-25 01:20:53.491636427 -0800
+@@ -33,10 +33,10 @@ int test_2 (void)
+ ~~~~~~~~~~~~~~~~
+ |
+ s
+- + some_other_function ());
+- ^ ~~~~~~~~~~~~~~~~~~~~~~
+- |
+- t
++ + some_other_function ());
++ ^ ~~~~~~~~~~~~~~~~~~~~~~
++ |
++ t
+ { dg-end-multiline-output "" } */
+ }
+
+diff --git a/gcc/testsuite/g++.dg/parse/error4.C b/gcc/testsuite/g++.dg/parse/error4.C
+--- a/gcc/testsuite/g++.dg/parse/error4.C 2020-07-22 23:35:18.012391910 -0700
++++ b/gcc/testsuite/g++.dg/parse/error4.C 2021-12-25 01:20:53.491636427 -0800
+@@ -7,4 +7,4 @@ struct X {
+ int);
+ };
+
+-// { dg-error "4:'itn' has not been declared" "" { target *-*-* } 6 }
++// { dg-error "18:'itn' has not been declared" "" { target *-*-* } 6 }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2020-07-22 23:35:18.512397420 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:20:53.491636427 -0800
+@@ -8,17 +8,22 @@
+ ! We can't rely on any ordering of the keys.
+
+ ! { dg-regexp "\"kind\": \"error\"" }
++! { dg-regexp "\"column-origin\": 1" }
+ ! { dg-regexp "\"message\": \"#error message\"" }
+
+ ! { dg-regexp "\"caret\": \{" }
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 2" }
++! { dg-regexp "\"display-column\": 2" }
++! { dg-regexp "\"byte-column\": 2" }
+
+ ! { dg-regexp "\"finish\": \{" }
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 6" }
++! { dg-regexp "\"display-column\": 6" }
++! { dg-regexp "\"byte-column\": 6" }
+
+ ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
+ ! { dg-regexp "\"children\": \[\[\]\[\]\]" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2020-07-22 23:35:18.512397420 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:20:53.491636427 -0800
+@@ -8,6 +8,7 @@
+ ! We can't rely on any ordering of the keys.
+
+ ! { dg-regexp "\"kind\": \"warning\"" }
++! { dg-regexp "\"column-origin\": 1" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Wcpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+@@ -16,11 +17,15 @@
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 2" }
++! { dg-regexp "\"display-column\": 2" }
++! { dg-regexp "\"byte-column\": 2" }
+
+ ! { dg-regexp "\"finish\": \{" }
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 8" }
++! { dg-regexp "\"display-column\": 8" }
++! { dg-regexp "\"byte-column\": 8" }
+
+ ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
+ ! { dg-regexp "\"children\": \[\[\]\[\]\]" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2020-07-22 23:35:18.512397420 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:20:53.491636427 -0800
+@@ -8,6 +8,7 @@
+ ! We can't rely on any ordering of the keys.
+
+ ! { dg-regexp "\"kind\": \"error\"" }
++! { dg-regexp "\"column-origin\": 1" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Werror=cpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+@@ -16,11 +17,15 @@
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 2" }
++! { dg-regexp "\"display-column\": 2" }
++! { dg-regexp "\"byte-column\": 2" }
+
+ ! { dg-regexp "\"finish\": \{" }
+ ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" }
+ ! { dg-regexp "\"line\": 4" }
+ ! { dg-regexp "\"column\": 8" }
++! { dg-regexp "\"display-column\": 8" }
++! { dg-regexp "\"byte-column\": 8" }
+
+ ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
+ ! { dg-regexp "\"children\": \[\[\]\[\]\]" }
+diff --git a/gcc/testsuite/go.dg/arrayclear.go b/gcc/testsuite/go.dg/arrayclear.go
+--- a/gcc/testsuite/go.dg/arrayclear.go 2020-07-22 23:35:18.588398257 -0700
++++ b/gcc/testsuite/go.dg/arrayclear.go 2021-12-25 01:20:53.491636427 -0800
+@@ -1,5 +1,8 @@
+ // { dg-do compile }
+ // { dg-options "-fgo-debug-optimization" }
++// This comment is necessary to work around a dejagnu bug. Otherwise, the
++// column of the second error message would equal the row of the first one, and
++// since the errors are also identical, dejagnu is not able to distinguish them.
+
+ package p
+
+diff --git a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C
+--- a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2020-07-22 23:35:18.048392308 -0700
++++ b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2021-12-25 01:20:53.491636427 -0800
+@@ -9,13 +9,13 @@ class A {
+ int h;
+ A() { i=10; j=20; }
+ virtual void f1() { printf("i=%d j=%d\n",i,j); }
+- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" }
++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" }
+ };
+
+ class B : public A {
+ public:
+ virtual void f1() { printf("i=%d j=%d\n",i,j); }// { dg-error "" } member.*// ERROR - member.*
+- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" }
++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" }
+ // { dg-error "private" "" { target *-*-* } .-1 }
+ };
+
+diff --git a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C
+--- a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2020-07-22 23:35:18.072392572 -0700
++++ b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2021-12-25 01:20:53.491636427 -0800
+@@ -12,5 +12,5 @@ int
+ main()
+ {
+ C<char*> c;
+- char* p = Z(c.O); //{ dg-error "13:'Z' was not declared" } ambiguous c.O
++ char* p = Z(c.O); //{ dg-error "29:'Z' was not declared" } ambiguous c.O
+ }
+diff --git a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C
+--- a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2020-07-22 23:35:18.076392617 -0700
++++ b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2021-12-25 01:20:53.491636427 -0800
+@@ -48,8 +48,8 @@ ostream& operator<<(ostream& os, Graph<V
+
+ // The compiler does not like this line!!!!!!
+ typename Graph<VertexType, EdgeType>::Successor::iterator
+- startN = G[i].second.begin(), // { dg-error "14:no match" } no index operator
+- endN = G[i].second.end(); // { dg-error "14:no match" } no index operator
++ startN = G[i].second.begin(), // { dg-error "21:no match" } no index operator
++ endN = G[i].second.end(); // { dg-error "21:no match" } no index operator
+
+ while(startN != endN)
+ {
+diff --git a/gcc/tree-diagnostic-path.cc b/gcc/tree-diagnostic-path.cc
+--- a/gcc/tree-diagnostic-path.cc 2020-07-22 23:35:18.628398698 -0700
++++ b/gcc/tree-diagnostic-path.cc 2021-12-25 01:20:53.491636427 -0800
+@@ -493,7 +493,7 @@ default_tree_diagnostic_path_printer (di
+ doesn't have access to trees (for m_fndecl). */
+
+ json::value *
+-default_tree_make_json_for_path (diagnostic_context *,
++default_tree_make_json_for_path (diagnostic_context *context,
+ const diagnostic_path *path)
+ {
+ json::array *path_array = new json::array ();
+@@ -504,7 +504,8 @@ default_tree_make_json_for_path (diagnos
+ json::object *event_obj = new json::object ();
+ if (event.get_location ())
+ event_obj->set ("location",
+- json_from_expanded_location (event.get_location ()));
++ json_from_expanded_location (context,
++ event.get_location ()));
+ label_text event_text (event.get_desc (false));
+ event_obj->set ("description", new json::string (event_text.m_buffer));
+ event_text.maybe_free ();
+diff --git a/libcpp/charset.c b/libcpp/charset.c
+--- a/libcpp/charset.c 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/charset.c 2021-12-25 01:20:53.491636427 -0800
+@@ -2276,49 +2276,90 @@ cpp_string_location_reader::get_next ()
+ return result;
+ }
+
+-/* Helper for cpp_byte_column_to_display_column and its inverse. Given a
+- pointer to a UTF-8-encoded character, compute its display width. *INBUFP
+- points on entry to the start of the UTF-8 encoding of the character, and
+- is updated to point just after the last byte of the encoding. *INBYTESLEFTP
+- contains on entry the remaining size of the buffer into which *INBUFP
+- points, and this is also updated accordingly. If *INBUFP does not
++cpp_display_width_computation::
++cpp_display_width_computation (const char *data, int data_length, int tabstop) :
++ m_begin (data),
++ m_next (m_begin),
++ m_bytes_left (data_length),
++ m_tabstop (tabstop),
++ m_display_cols (0)
++{
++ gcc_assert (m_tabstop > 0);
++}
++
++
++/* The main implementation function for class cpp_display_width_computation.
++ m_next points on entry to the start of the UTF-8 encoding of the next
++ character, and is updated to point just after the last byte of the encoding.
++ m_bytes_left contains on entry the remaining size of the buffer into which
++ m_next points, and this is also updated accordingly. If m_next does not
+ point to a valid UTF-8-encoded sequence, then it will be treated as a single
+- byte with display width 1. */
++ byte with display width 1. m_cur_display_col is the current display column,
++ relative to which tab stops should be expanded. Returns the display width of
++ the codepoint just processed. */
+
+-static inline int
+-compute_next_display_width (const uchar **inbufp, size_t *inbytesleftp)
++int
++cpp_display_width_computation::process_next_codepoint ()
+ {
+ cppchar_t c;
+- if (one_utf8_to_cppchar (inbufp, inbytesleftp, &c) != 0)
++ int next_width;
++
++ if (*m_next == '\t')
++ {
++ ++m_next;
++ --m_bytes_left;
++ next_width = m_tabstop - (m_display_cols % m_tabstop);
++ }
++ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
++ != 0)
+ {
+ /* Input is not convertible to UTF-8. This could be fine, e.g. in a
+ string literal, so don't complain. Just treat it as if it has a width
+ of one. */
+- ++*inbufp;
+- --*inbytesleftp;
+- return 1;
++ ++m_next;
++ --m_bytes_left;
++ next_width = 1;
++ }
++ else
++ {
++ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
++ next_width = cpp_wcwidth (c);
+ }
+
+- /* one_utf8_to_cppchar() has updated inbufp and inbytesleftp for us. */
+- return cpp_wcwidth (c);
++ m_display_cols += next_width;
++ return next_width;
++}
++
++/* Utility to advance the byte stream by the minimum amount needed to consume
++ N display columns. Returns the number of display columns that were
++ actually skipped. This could be less than N, if there was not enough data,
++ or more than N, if the last character to be skipped had a sufficiently large
++ display width. */
++int
++cpp_display_width_computation::advance_display_cols (int n)
++{
++ const int start = m_display_cols;
++ const int target = start + n;
++ while (m_display_cols < target && !done ())
++ process_next_codepoint ();
++ return m_display_cols - start;
+ }
+
+ /* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+ how many display columns are occupied by the first COLUMN bytes. COLUMN
+ may exceed DATA_LENGTH, in which case the phantom bytes at the end are
+- treated as if they have display width 1. */
++ treated as if they have display width 1. Tabs are expanded to the next tab
++ stop, relative to the start of DATA. */
+
+ int
+ cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column)
++ int column, int tabstop)
+ {
+- int display_col = 0;
+- const uchar *udata = (const uchar *) data;
+ const int offset = MAX (0, column - data_length);
+- size_t inbytesleft = column - offset;
+- while (inbytesleft)
+- display_col += compute_next_display_width (&udata, &inbytesleft);
+- return display_col + offset;
++ cpp_display_width_computation dw (data, column - offset, tabstop);
++ while (!dw.done ())
++ dw.process_next_codepoint ();
++ return dw.display_cols_processed () + offset;
+ }
+
+ /* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+@@ -2328,14 +2369,11 @@ cpp_byte_column_to_display_column (const
+
+ int
+ cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col)
++ int display_col, int tabstop)
+ {
+- int column = 0;
+- const uchar *udata = (const uchar *) data;
+- size_t inbytesleft = data_length;
+- while (column < display_col && inbytesleft)
+- column += compute_next_display_width (&udata, &inbytesleft);
+- return data_length - inbytesleft + MAX (0, display_col - column);
++ cpp_display_width_computation dw (data, data_length, tabstop);
++ const int avail_display = dw.advance_display_cols (display_col);
++ return dw.bytes_processed () + MAX (0, display_col - avail_display);
+ }
+
+ /* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc,
+diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
+--- a/libcpp/include/cpplib.h 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/include/cpplib.h 2021-12-25 01:20:53.491636427 -0800
+@@ -312,9 +312,6 @@ enum cpp_normalize_level {
+ carries all the options visible to the command line. */
+ struct cpp_options
+ {
+- /* Characters between tab stops. */
+- unsigned int tabstop;
+-
+ /* The language we're preprocessing. */
+ enum c_lang lang;
+
+@@ -1322,14 +1319,43 @@ extern const char * cpp_get_userdef_suff
+ (const cpp_token *);
+
+ /* In charset.c */
++
++/* A class to manage the state while converting a UTF-8 sequence to cppchar_t
++ and computing the display width one character at a time. */
++class cpp_display_width_computation {
++ public:
++ cpp_display_width_computation (const char *data, int data_length,
++ int tabstop);
++ const char *next_byte () const { return m_next; }
++ int bytes_processed () const { return m_next - m_begin; }
++ int bytes_left () const { return m_bytes_left; }
++ bool done () const { return !bytes_left (); }
++ int display_cols_processed () const { return m_display_cols; }
++
++ int process_next_codepoint ();
++ int advance_display_cols (int n);
++
++ private:
++ const char *const m_begin;
++ const char *m_next;
++ size_t m_bytes_left;
++ const int m_tabstop;
++ int m_display_cols;
++};
++
++/* Convenience functions that are simple use cases for class
++ cpp_display_width_computation. Tab characters will be expanded to spaces
++ as determined by TABSTOP. */
+ int cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column);
+-inline int cpp_display_width (const char *data, int data_length)
++ int column, int tabstop);
++inline int cpp_display_width (const char *data, int data_length,
++ int tabstop)
+ {
+- return cpp_byte_column_to_display_column (data, data_length, data_length);
++ return cpp_byte_column_to_display_column (data, data_length, data_length,
++ tabstop);
+ }
+ int cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col);
++ int display_col, int tabstop);
+ int cpp_wcwidth (cppchar_t c);
+
+ #endif /* ! LIBCPP_CPPLIB_H */
+diff --git a/libcpp/init.c b/libcpp/init.c
+--- a/libcpp/init.c 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/init.c 2021-12-25 01:20:53.491636427 -0800
+@@ -190,7 +190,6 @@ cpp_create_reader (enum c_lang lang, cpp
+ CPP_OPTION (pfile, discard_comments) = 1;
+ CPP_OPTION (pfile, discard_comments_in_macro_exp) = 1;
+ CPP_OPTION (pfile, max_include_depth) = 200;
+- CPP_OPTION (pfile, tabstop) = 8;
+ CPP_OPTION (pfile, operator_names) = 1;
+ CPP_OPTION (pfile, warn_trigraphs) = 2;
+ CPP_OPTION (pfile, warn_endif_labels) = 1;
diff --git a/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch b/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch
deleted file mode 100644
index c060accd99..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch
+++ /dev/null
@@ -1,66 +0,0 @@
-Upstream-Status: Backport
-Signed-off-by: Ross Burton <ross.burton@arm.com>
-
-From fd2ec4542fd2975e6d3f2f1c1a2639945a84f9e1 Mon Sep 17 00:00:00 2001
-From: Jakub Jelinek <jakub@redhat.com>
-Date: Mon, 3 Aug 2020 22:55:28 +0200
-Subject: [PATCH] aarch64: Fix up __aarch64_cas16_acq_rel fallback
-
-As mentioned in the PR, the fallback path when LSE is unavailable writes
-incorrect registers to the memory if the previous content compares equal
-to x0, x1 - it writes copy of x0, x1 from the start of function, but it
-should write x2, x3.
-
-2020-08-03 Jakub Jelinek <jakub@redhat.com>
-
- PR target/96402
- * config/aarch64/lse.S (__aarch64_cas16_acq_rel): Use x2, x3 instead
- of x(tmp0), x(tmp1) in STXP arguments.
-
- * gcc.target/aarch64/pr96402.c: New test.
-
-(cherry picked from commit 90b43856fdff7d96d93d22970eca8a86c56e0ddc)
----
- gcc/testsuite/gcc.target/aarch64/pr96402.c | 16 ++++++++++++++++
- libgcc/config/aarch64/lse.S | 2 +-
- 2 files changed, 17 insertions(+), 1 deletion(-)
- create mode 100644 gcc/testsuite/gcc.target/aarch64/pr96402.c
-
-diff --git a/gcc/testsuite/gcc.target/aarch64/pr96402.c b/gcc/testsuite/gcc.target/aarch64/pr96402.c
-new file mode 100644
-index 00000000000..fa2dddfac15
---- /dev/null
-+++ b/gcc/testsuite/gcc.target/aarch64/pr96402.c
-@@ -0,0 +1,16 @@
-+/* PR target/96402 */
-+/* { dg-do run { target int128 } } */
-+/* { dg-options "-moutline-atomics" } */
-+
-+int
-+main ()
-+{
-+ __int128 a = 0;
-+ __sync_val_compare_and_swap (&a, (__int128) 0, (__int128) 1);
-+ if (a != 1)
-+ __builtin_abort ();
-+ __sync_val_compare_and_swap (&a, (__int128) 1, (((__int128) 0xdeadbeeffeedbac1ULL) << 64) | 0xabadcafe00c0ffeeULL);
-+ if (a != ((((__int128) 0xdeadbeeffeedbac1ULL) << 64) | 0xabadcafe00c0ffeeULL))
-+ __builtin_abort ();
-+ return 0;
-+}
-diff --git a/libgcc/config/aarch64/lse.S b/libgcc/config/aarch64/lse.S
-index 64691c601c1..c8fbfbce4fd 100644
---- a/libgcc/config/aarch64/lse.S
-+++ b/libgcc/config/aarch64/lse.S
-@@ -203,7 +203,7 @@ STARTFN NAME(cas)
- cmp x0, x(tmp0)
- ccmp x1, x(tmp1), #0, eq
- bne 1f
-- STXP w(tmp2), x(tmp0), x(tmp1), [x4]
-+ STXP w(tmp2), x2, x3, [x4]
- cbnz w(tmp2), 0b
- 1: ret
-
---
-2.26.2
-
diff --git a/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch b/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch
deleted file mode 100644
index 73de4c7590..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch
+++ /dev/null
@@ -1,202 +0,0 @@
-CVE: CVE-2020-13844
-Upstream-Status: Backport
-Signed-off-by: Ross Burton <ross.burton@arm.com>
-
-From 1ff243934ac443b5f58cd02a5012ce58ecc31fb2 Mon Sep 17 00:00:00 2001
-From: Matthew Malcomson <matthew.malcomson@arm.com>
-Date: Thu, 9 Jul 2020 09:11:58 +0100
-Subject: [PATCH 1/3] aarch64: New Straight Line Speculation (SLS) mitigation
- flags
-
-Here we introduce the flags that will be used for straight line speculation.
-
-The new flag introduced is `-mharden-sls=`.
-This flag can take arguments of `none`, `all`, or a comma seperated list of one
-or more of `retbr` or `blr`.
-`none` indicates no special mitigation of the straight line speculation
-vulnerability.
-`all` requests all mitigations currently implemented.
-`retbr` requests that the RET and BR instructions have a speculation barrier
-inserted after them.
-`blr` requests that BLR instructions are replaced by a BL to a function stub
-using a BR with a speculation barrier after it.
-
-Setting this on a per-function basis using attributes or the like is not
-enabled, but may be in the future.
-
-gcc/ChangeLog:
-
-2020-06-02 Matthew Malcomson <matthew.malcomson@arm.com>
-
- * config/aarch64/aarch64-protos.h (aarch64_harden_sls_retbr_p):
- New.
- (aarch64_harden_sls_blr_p): New.
- * config/aarch64/aarch64.c (enum aarch64_sls_hardening_type):
- New.
- (aarch64_harden_sls_retbr_p): New.
- (aarch64_harden_sls_blr_p): New.
- (aarch64_validate_sls_mitigation): New.
- (aarch64_override_options): Parse options for SLS mitigation.
- * config/aarch64/aarch64.opt (-mharden-sls): New option.
- * doc/invoke.texi: Document new option.
----
- gcc/config/aarch64/aarch64-protos.h | 3 ++
- gcc/config/aarch64/aarch64.c | 76 +++++++++++++++++++++++++++++++++++++
- gcc/config/aarch64/aarch64.opt | 4 ++
- gcc/doc/invoke.texi | 12 ++++++
- 4 files changed, 95 insertions(+)
-
-diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
-index 723d9ba..eb5f4b4 100644
---- a/gcc/config/aarch64/aarch64-protos.h
-+++ b/gcc/config/aarch64/aarch64-protos.h
-@@ -781,4 +781,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names;
-
- tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *);
-
-+extern bool aarch64_harden_sls_retbr_p (void);
-+extern bool aarch64_harden_sls_blr_p (void);
-+
- #endif /* GCC_AARCH64_PROTOS_H */
-diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
-index b86434a..437a9cf 100644
---- a/gcc/config/aarch64/aarch64.c
-+++ b/gcc/config/aarch64/aarch64.c
-@@ -14494,6 +14494,79 @@ aarch64_validate_mcpu (const char *str, const struct processor **res,
- return false;
- }
-
-+/* Straight line speculation indicators. */
-+enum aarch64_sls_hardening_type
-+{
-+ SLS_NONE = 0,
-+ SLS_RETBR = 1,
-+ SLS_BLR = 2,
-+ SLS_ALL = 3,
-+};
-+static enum aarch64_sls_hardening_type aarch64_sls_hardening;
-+
-+/* Return whether we should mitigatate Straight Line Speculation for the RET
-+ and BR instructions. */
-+bool
-+aarch64_harden_sls_retbr_p (void)
-+{
-+ return aarch64_sls_hardening & SLS_RETBR;
-+}
-+
-+/* Return whether we should mitigatate Straight Line Speculation for the BLR
-+ instruction. */
-+bool
-+aarch64_harden_sls_blr_p (void)
-+{
-+ return aarch64_sls_hardening & SLS_BLR;
-+}
-+
-+/* As of yet we only allow setting these options globally, in the future we may
-+ allow setting them per function. */
-+static void
-+aarch64_validate_sls_mitigation (const char *const_str)
-+{
-+ char *token_save = NULL;
-+ char *str = NULL;
-+
-+ if (strcmp (const_str, "none") == 0)
-+ {
-+ aarch64_sls_hardening = SLS_NONE;
-+ return;
-+ }
-+ if (strcmp (const_str, "all") == 0)
-+ {
-+ aarch64_sls_hardening = SLS_ALL;
-+ return;
-+ }
-+
-+ char *str_root = xstrdup (const_str);
-+ str = strtok_r (str_root, ",", &token_save);
-+ if (!str)
-+ error ("invalid argument given to %<-mharden-sls=%>");
-+
-+ int temp = SLS_NONE;
-+ while (str)
-+ {
-+ if (strcmp (str, "blr") == 0)
-+ temp |= SLS_BLR;
-+ else if (strcmp (str, "retbr") == 0)
-+ temp |= SLS_RETBR;
-+ else if (strcmp (str, "none") == 0 || strcmp (str, "all") == 0)
-+ {
-+ error ("%<%s%> must be by itself for %<-mharden-sls=%>", str);
-+ break;
-+ }
-+ else
-+ {
-+ error ("invalid argument %<%s%> for %<-mharden-sls=%>", str);
-+ break;
-+ }
-+ str = strtok_r (NULL, ",", &token_save);
-+ }
-+ aarch64_sls_hardening = (aarch64_sls_hardening_type) temp;
-+ free (str_root);
-+}
-+
- /* Parses CONST_STR for branch protection features specified in
- aarch64_branch_protect_types, and set any global variables required. Returns
- the parsing result and assigns LAST_STR to the last processed token from
-@@ -14738,6 +14811,9 @@ aarch64_override_options (void)
- selected_arch = NULL;
- selected_tune = NULL;
-
-+ if (aarch64_harden_sls_string)
-+ aarch64_validate_sls_mitigation (aarch64_harden_sls_string);
-+
- if (aarch64_branch_protection_string)
- aarch64_validate_mbranch_protection (aarch64_branch_protection_string);
-
-diff --git a/gcc/config/aarch64/aarch64.opt b/gcc/config/aarch64/aarch64.opt
-index d99d14c..5170361 100644
---- a/gcc/config/aarch64/aarch64.opt
-+++ b/gcc/config/aarch64/aarch64.opt
-@@ -71,6 +71,10 @@ mgeneral-regs-only
- Target Report RejectNegative Mask(GENERAL_REGS_ONLY) Save
- Generate code which uses only the general registers.
-
-+mharden-sls=
-+Target RejectNegative Joined Var(aarch64_harden_sls_string)
-+Generate code to mitigate against straight line speculation.
-+
- mfix-cortex-a53-835769
- Target Report Var(aarch64_fix_a53_err835769) Init(2) Save
- Workaround for ARM Cortex-A53 Erratum number 835769.
-diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
-index a2794a6..bd5b77a 100644
---- a/gcc/doc/invoke.texi
-+++ b/gcc/doc/invoke.texi
-@@ -696,6 +696,7 @@ Objective-C and Objective-C++ Dialects}.
- -msign-return-address=@var{scope} @gol
- -mbranch-protection=@var{none}|@var{standard}|@var{pac-ret}[+@var{leaf}
- +@var{b-key}]|@var{bti} @gol
-+-mharden-sls=@var{opts} @gol
- -march=@var{name} -mcpu=@var{name} -mtune=@var{name} @gol
- -moverride=@var{string} -mverbose-cost-dump @gol
- -mstack-protector-guard=@var{guard} -mstack-protector-guard-reg=@var{sysreg} @gol
-@@ -17065,6 +17066,17 @@ functions. The optional argument @samp{b-key} can be used to sign the functions
- with the B-key instead of the A-key.
- @samp{bti} turns on branch target identification mechanism.
-
-+@item -mharden-sls=@var{opts}
-+@opindex mharden-sls
-+Enable compiler hardening against straight line speculation (SLS).
-+@var{opts} is a comma-separated list of the following options:
-+@table @samp
-+@item retbr
-+@item blr
-+@end table
-+In addition, @samp{-mharden-sls=all} enables all SLS hardening while
-+@samp{-mharden-sls=none} disables all SLS hardening.
-+
- @item -msve-vector-bits=@var{bits}
- @opindex msve-vector-bits
- Specify the number of bits in an SVE vector register. This option only has
---
-2.7.4
-
diff --git a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch
new file mode 100644
index 0000000000..5b1896ed69
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch
@@ -0,0 +1,2270 @@
+From bd5e882cf6e0def3dd1bc106075d59a303fe0d1e Mon Sep 17 00:00:00 2001
+From: David Malcolm <dmalcolm@redhat.com>
+Date: Mon, 18 Oct 2021 18:55:31 -0400
+Subject: [PATCH] diagnostics: escape non-ASCII source bytes for certain
+ diagnostics
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf8
+Content-Transfer-Encoding: 8bit
+
+This patch adds support to GCC's diagnostic subsystem for escaping certain
+bytes and Unicode characters when quoting source code.
+
+Specifically, this patch adds a new flag rich_location::m_escape_on_output
+which is a hint from a diagnostic that non-ASCII bytes in the pertinent
+lines of the user's source code should be escaped when printed.
+
+The patch sets this for the following diagnostics:
+- when complaining about stray bytes in the program (when these
+are non-printable)
+- when complaining about "null character(s) ignored");
+- for -Wnormalized= (and generate source ranges for such warnings)
+
+The escaping is controlled by a new option:
+ -fdiagnostics-escape-format=[unicode|bytes]
+
+For example, consider a diagnostic involing a source line containing the
+string "before" followed by the Unicode character U+03C0 ("GREEK SMALL
+LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF
+(a stray UTF-8 trailing byte), followed by the string "after", where the
+diagnostic highlights the U+03C0 character.
+
+By default, this line will be printed verbatim to the user when
+reporting a diagnostic at it, as:
+
+ beforeÏXafter
+ ^
+
+(using X for the stray byte to avoid putting invalid UTF-8 in this
+commit message)
+
+If the diagnostic sets the "escape" flag, it will be printed as:
+
+ before<U+03C0><BF>after
+ ^~~~~~~~
+
+with -fdiagnostics-escape-format=unicode (the default), or as:
+
+ before<CF><80><BF>after
+ ^~~~~~~~
+
+if the user supplies -fdiagnostics-escape-format=bytes.
+
+This only affects how the source is printed; it does not affect
+how column numbers that are printed (as per -fdiagnostics-column-unit=
+and -fdiagnostics-column-origin=).
+
+gcc/c-family/ChangeLog:
+ * c-lex.c (c_lex_with_flags): When complaining about non-printable
+ CPP_OTHER tokens, set the "escape on output" flag.
+
+gcc/ChangeLog:
+ * common.opt (fdiagnostics-escape-format=): New.
+ (diagnostics_escape_format): New enum.
+ (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value.
+ (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise.
+ * diagnostic-format-json.cc (json_end_diagnostic): Add
+ "escape-source" attribute.
+ * diagnostic-show-locus.c
+ (exploc_with_display_col::exploc_with_display_col): Replace
+ "tabstop" param with a cpp_char_column_policy and add an "aspect"
+ param. Use these to compute m_display_col accordingly.
+ (struct char_display_policy): New struct.
+ (layout::m_policy): New field.
+ (layout::m_escape_on_output): New field.
+ (def_policy): New function.
+ (make_range): Update for changes to exploc_with_display_col ctor.
+ (default_print_decoded_ch): New.
+ (width_per_escaped_byte): New.
+ (escape_as_bytes_width): New.
+ (escape_as_bytes_print): New.
+ (escape_as_unicode_width): New.
+ (escape_as_unicode_print): New.
+ (make_policy): New.
+ (layout::layout): Initialize new fields. Update m_exploc ctor
+ call for above change to ctor.
+ (layout::maybe_add_location_range): Update for changes to
+ exploc_with_display_col ctor.
+ (layout::calculate_x_offset_display): Update for change to
+ cpp_display_width.
+ (layout::print_source_line): Pass policy
+ to cpp_display_width_computation. Capture cpp_decoded_char when
+ calling process_next_codepoint. Move printing of source code to
+ m_policy.m_print_cb.
+ (line_label::line_label): Pass in policy rather than context.
+ (layout::print_any_labels): Update for change to line_label ctor.
+ (get_affected_range): Pass in policy rather than context, updating
+ calls to location_compute_display_column accordingly.
+ (get_printed_columns): Likewise, also for cpp_display_width.
+ (correction::correction): Pass in policy rather than tabstop.
+ (correction::compute_display_cols): Pass m_policy rather than
+ m_tabstop to cpp_display_width.
+ (correction::m_tabstop): Replace with...
+ (correction::m_policy): ...this.
+ (line_corrections::line_corrections): Pass in policy rather than
+ context.
+ (line_corrections::m_context): Replace with...
+ (line_corrections::m_policy): ...this.
+ (line_corrections::add_hint): Update to use m_policy rather than
+ m_context.
+ (line_corrections::add_hint): Likewise.
+ (layout::print_trailing_fixits): Likewise.
+ (selftest::test_display_widths): New.
+ (selftest::test_layout_x_offset_display_utf8): Update to use
+ policy rather than tabstop.
+ (selftest::test_one_liner_labels_utf8): Add test of escaping
+ source lines.
+ (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to
+ use policy rather than tabstop.
+ (selftest::test_overlapped_fixit_printing): Likewise.
+ (selftest::test_overlapped_fixit_printing_utf8): Likewise.
+ (selftest::test_overlapped_fixit_printing_2): Likewise.
+ (selftest::test_tab_expansion): Likewise.
+ (selftest::test_escaping_bytes_1): New.
+ (selftest::test_escaping_bytes_2): New.
+ (selftest::diagnostic_show_locus_c_tests): Call the new tests.
+ * diagnostic.c (diagnostic_initialize): Initialize
+ context->escape_format.
+ (convert_column_unit): Update to use default character width policy.
+ (selftest::test_diagnostic_get_location_text): Likewise.
+ * diagnostic.h (enum diagnostics_escape_format): New enum.
+ (diagnostic_context::escape_format): New field.
+ * doc/invoke.texi (-fdiagnostics-escape-format=): New option.
+ (-fdiagnostics-format=): Add "escape-source" attribute to examples
+ of JSON output, and document it.
+ * input.c (location_compute_display_column): Pass in "policy"
+ rather than "tabstop", passing to
+ cpp_byte_column_to_display_column.
+ (selftest::test_cpp_utf8): Update to use cpp_char_column_policy.
+ * input.h (class cpp_char_column_policy): New forward decl.
+ (location_compute_display_column): Pass in "policy" rather than
+ "tabstop".
+ * opts.c (common_handle_option): Handle
+ OPT_fdiagnostics_escape_format_.
+ * selftest.c (temp_source_file::temp_source_file): New ctor
+ overload taking a size_t.
+ * selftest.h (temp_source_file::temp_source_file): Likewise.
+
+gcc/testsuite/ChangeLog:
+ * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume
+ "escape-source" attribute.
+ * c-c++-common/diagnostic-format-json-2.c: Likewise.
+ * c-c++-common/diagnostic-format-json-3.c: Likewise.
+ * c-c++-common/diagnostic-format-json-4.c: Likewise, twice.
+ * c-c++-common/diagnostic-format-json-5.c: Likewise.
+ * gcc.dg/cpp/warn-normalized-4-bytes.c: New test.
+ * gcc.dg/cpp/warn-normalized-4-unicode.c: New test.
+ * gcc.dg/encoding-issues-bytes.c: New test.
+ * gcc.dg/encoding-issues-unicode.c: New test.
+ * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume
+ "escape-source" attribute.
+ * gfortran.dg/diagnostic-format-json-2.F90: Likewise.
+ * gfortran.dg/diagnostic-format-json-3.F90: Likewise.
+
+libcpp/ChangeLog:
+ * charset.c (convert_escape): Use encoding_rich_location when
+ complaining about nonprintable unknown escape sequences.
+ (cpp_display_width_computation::::cpp_display_width_computation):
+ Pass in policy rather than tabstop.
+ (cpp_display_width_computation::process_next_codepoint): Add "out"
+ param and populate *out if non-NULL.
+ (cpp_display_width_computation::advance_display_cols): Pass NULL
+ to process_next_codepoint.
+ (cpp_byte_column_to_display_column): Pass in policy rather than
+ tabstop. Pass NULL to process_next_codepoint.
+ (cpp_display_column_to_byte_column): Pass in policy rather than
+ tabstop.
+ * errors.c (cpp_diagnostic_get_current_location): New function,
+ splitting out the logic from...
+ (cpp_diagnostic): ...here.
+ (cpp_warning_at): New function.
+ (cpp_pedwarning_at): New function.
+ * include/cpplib.h (cpp_warning_at): New decl for rich_location.
+ (cpp_pedwarning_at): Likewise.
+ (struct cpp_decoded_char): New.
+ (struct cpp_char_column_policy): New.
+ (cpp_display_width_computation::cpp_display_width_computation):
+ Replace "tabstop" param with "policy".
+ (cpp_display_width_computation::process_next_codepoint): Add "out"
+ param.
+ (cpp_display_width_computation::m_tabstop): Replace with...
+ (cpp_display_width_computation::m_policy): ...this.
+ (cpp_byte_column_to_display_column): Replace "tabstop" param with
+ "policy".
+ (cpp_display_width): Likewise.
+ (cpp_display_column_to_byte_column): Likewise.
+ * include/line-map.h (rich_location::escape_on_output_p): New.
+ (rich_location::set_escape_on_output): New.
+ (rich_location::m_escape_on_output): New.
+ * internal.h (cpp_diagnostic_get_current_location): New decl.
+ (class encoding_rich_location): New.
+ * lex.c (skip_whitespace): Use encoding_rich_location when
+ complaining about null characters.
+ (warn_about_normalization): Generate a source range when
+ complaining about improperly normalized tokens, rather than just a
+ point, and use encoding_rich_location so that the source code
+ is escaped on printing.
+ * line-map.c (rich_location::rich_location): Initialize
+ m_escape_on_output.
+
+Signed-off-by: David Malcolm <dmalcolm@redhat.com>
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bd5e882cf6e0def3dd1bc106075d59a303fe0d1e]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+
+---
+ gcc/c-family/c-lex.c | 6 +-
+ gcc/common.opt | 13 +
+ gcc/diagnostic-format-json.cc | 3 +
+ gcc/diagnostic-show-locus.c | 580 +++++++++++++++---
+ gcc/diagnostic.c | 10 +-
+ gcc/diagnostic.h | 18 +
+ gcc/doc/invoke.texi | 43 +-
+ gcc/input.c | 62 +-
+ gcc/input.h | 7 +-
+ gcc/opts.c | 4 +
+ gcc/selftest.c | 15 +
+ gcc/selftest.h | 2 +
+ .../c-c++-common/diagnostic-format-json-1.c | 1 +
+ .../c-c++-common/diagnostic-format-json-2.c | 1 +
+ .../c-c++-common/diagnostic-format-json-3.c | 1 +
+ .../c-c++-common/diagnostic-format-json-4.c | 2 +
+ .../c-c++-common/diagnostic-format-json-5.c | 1 +
+ .../gcc.dg/cpp/warn-normalized-4-bytes.c | 21 +
+ .../gcc.dg/cpp/warn-normalized-4-unicode.c | 19 +
+ gcc/testsuite/gcc.dg/encoding-issues-bytes.c | Bin 0 -> 595 bytes
+ .../gcc.dg/encoding-issues-unicode.c | Bin 0 -> 613 bytes
+ .../gfortran.dg/diagnostic-format-json-1.F90 | 1 +
+ .../gfortran.dg/diagnostic-format-json-2.F90 | 1 +
+ .../gfortran.dg/diagnostic-format-json-3.F90 | 1 +
+ libcpp/charset.c | 63 +-
+ libcpp/errors.c | 82 ++-
+ libcpp/include/cpplib.h | 76 ++-
+ libcpp/include/line-map.h | 13 +
+ libcpp/internal.h | 23 +
+ libcpp/lex.c | 38 +-
+ libcpp/line-map.c | 3 +-
+ 31 files changed, 942 insertions(+), 168 deletions(-)
+ create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c
+ create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c
+ create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-bytes.c
+ create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-unicode.c
+
+diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
+--- a/gcc/c-family/c-lex.c 2020-07-22 23:35:17.296384022 -0700
++++ b/gcc/c-family/c-lex.c 2021-12-25 01:30:50.669689023 -0800
+@@ -587,7 +587,11 @@ c_lex_with_flags (tree *value, location_
+ else if (ISGRAPH (c))
+ error_at (*loc, "stray %qc in program", (int) c);
+ else
+- error_at (*loc, "stray %<\\%o%> in program", (int) c);
++ {
++ rich_location rich_loc (line_table, *loc);
++ rich_loc.set_escape_on_output (true);
++ error_at (&rich_loc, "stray %<\\%o%> in program", (int) c);
++ }
+ }
+ goto retry;
+
+diff --git a/gcc/common.opt b/gcc/common.opt
+--- a/gcc/common.opt 2021-12-25 01:29:12.915317374 -0800
++++ b/gcc/common.opt 2021-12-25 01:30:50.669689023 -0800
+@@ -1337,6 +1337,10 @@ fdiagnostics-format=
+ Common Joined RejectNegative Enum(diagnostics_output_format)
+ -fdiagnostics-format=[text|json] Select output format.
+
++fdiagnostics-escape-format=
++Common Joined RejectNegative Enum(diagnostics_escape_format)
++-fdiagnostics-escape-format=[unicode|bytes] Select how to escape non-printable-ASCII bytes in the source for diagnostics that suggest it.
++
+ ; Required for these enum values.
+ SourceInclude
+ diagnostic.h
+@@ -1351,6 +1355,15 @@ EnumValue
+ Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE)
+
+ Enum
++Name(diagnostics_escape_format) Type(int)
++
++EnumValue
++Enum(diagnostics_escape_format) String(unicode) Value(DIAGNOSTICS_ESCAPE_FORMAT_UNICODE)
++
++EnumValue
++Enum(diagnostics_escape_format) String(bytes) Value(DIAGNOSTICS_ESCAPE_FORMAT_BYTES)
++
++Enum
+ Name(diagnostics_output_format) Type(int)
+
+ EnumValue
+diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c
+--- a/gcc/diagnostic.c 2021-12-25 01:29:12.915317374 -0800
++++ b/gcc/diagnostic.c 2021-12-25 01:30:50.669689023 -0800
+@@ -223,6 +223,7 @@ diagnostic_initialize (diagnostic_contex
+ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY;
+ context->column_origin = 1;
+ context->tabstop = 8;
++ context->escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
+ context->edit_context_ptr = NULL;
+ context->diagnostic_group_nesting_depth = 0;
+ context->diagnostic_group_emission_count = 0;
+@@ -2152,8 +2153,8 @@ test_diagnostic_get_location_text ()
+ const char *const content = "smile \xf0\x9f\x98\x82\n";
+ const int line_bytes = strlen (content) - 1;
+ const int def_tabstop = 8;
+- const int display_width = cpp_display_width (content, line_bytes,
+- def_tabstop);
++ const cpp_char_column_policy policy (def_tabstop, cpp_wcwidth);
++ const int display_width = cpp_display_width (content, line_bytes, policy);
+ ASSERT_EQ (line_bytes - 2, display_width);
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ const char *const fname = tmp.get_filename ();
+diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc
+--- a/gcc/diagnostic-format-json.cc 2021-12-25 01:29:12.915317374 -0800
++++ b/gcc/diagnostic-format-json.cc 2021-12-25 01:30:50.669689023 -0800
+@@ -264,6 +264,9 @@ json_end_diagnostic (diagnostic_context
+ json::value *path_value = context->make_json_for_path (context, path);
+ diag_obj->set ("path", path_value);
+ }
++
++ diag_obj->set ("escape-source",
++ new json::literal (richloc->escape_on_output_p ()));
+ }
+
+ /* No-op implementation of "begin_group_cb" for JSON output. */
+diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h
+--- a/gcc/diagnostic.h 2021-12-25 01:29:12.919317307 -0800
++++ b/gcc/diagnostic.h 2021-12-25 01:30:50.669689023 -0800
+@@ -38,6 +38,20 @@ enum diagnostics_column_unit
+ DIAGNOSTICS_COLUMN_UNIT_BYTE
+ };
+
++/* An enum for controlling how to print non-ASCII characters/bytes when
++ a diagnostic suggests escaping the source code on output. */
++
++enum diagnostics_escape_format
++{
++ /* Escape non-ASCII Unicode characters in the form <U+XXXX> and
++ non-UTF-8 bytes in the form <XX>. */
++ DIAGNOSTICS_ESCAPE_FORMAT_UNICODE,
++
++ /* Escape non-ASCII bytes in the form <XX> (thus showing the underlying
++ encoding of non-ASCII Unicode characters). */
++ DIAGNOSTICS_ESCAPE_FORMAT_BYTES
++};
++
+ /* Enum for overriding the standard output format. */
+
+ enum diagnostics_output_format
+@@ -303,6 +317,10 @@ struct diagnostic_context
+ /* The size of the tabstop for tab expansion. */
+ int tabstop;
+
++ /* How should non-ASCII/non-printable bytes be escaped when
++ a diagnostic suggests escaping the source code on output. */
++ enum diagnostics_escape_format escape_format;
++
+ /* If non-NULL, an edit_context to which fix-it hints should be
+ applied, for generating patches. */
+ edit_context *edit_context_ptr;
+diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c
+--- a/gcc/diagnostic-show-locus.c 2021-12-25 01:29:12.919317307 -0800
++++ b/gcc/diagnostic-show-locus.c 2021-12-25 01:30:50.673688956 -0800
+@@ -175,10 +175,26 @@ enum column_unit {
+ class exploc_with_display_col : public expanded_location
+ {
+ public:
+- exploc_with_display_col (const expanded_location &exploc, int tabstop)
+- : expanded_location (exploc),
+- m_display_col (location_compute_display_column (exploc, tabstop))
+- {}
++ exploc_with_display_col (const expanded_location &exploc,
++ const cpp_char_column_policy &policy,
++ enum location_aspect aspect)
++ : expanded_location (exploc),
++ m_display_col (location_compute_display_column (exploc, policy))
++ {
++ if (exploc.column > 0)
++ {
++ /* m_display_col is now the final column of the byte.
++ If escaping has happened, we may want the first column instead. */
++ if (aspect != LOCATION_ASPECT_FINISH)
++ {
++ expanded_location prev_exploc (exploc);
++ prev_exploc.column--;
++ int prev_display_col
++ = (location_compute_display_column (prev_exploc, policy));
++ m_display_col = prev_display_col + 1;
++ }
++ }
++ }
+
+ int m_display_col;
+ };
+@@ -313,6 +329,31 @@ test_line_span ()
+
+ #endif /* #if CHECKING_P */
+
++/* A bundle of information containing how to print unicode
++ characters and bytes when quoting source code.
++
++ Provides a unified place to support escaping some subset
++ of characters to some format.
++
++ Extends char_column_policy; printing is split out to avoid
++ libcpp having to know about pretty_printer. */
++
++struct char_display_policy : public cpp_char_column_policy
++{
++ public:
++ char_display_policy (int tabstop,
++ int (*width_cb) (cppchar_t c),
++ void (*print_cb) (pretty_printer *pp,
++ const cpp_decoded_char &cp))
++ : cpp_char_column_policy (tabstop, width_cb),
++ m_print_cb (print_cb)
++ {
++ }
++
++ void (*m_print_cb) (pretty_printer *pp,
++ const cpp_decoded_char &cp);
++};
++
+ /* A class to control the overall layout when printing a diagnostic.
+
+ The layout is determined within the constructor.
+@@ -345,6 +386,8 @@ class layout
+
+ void print_line (linenum_type row);
+
++ void on_bad_codepoint (const char *ptr, cppchar_t ch, size_t ch_sz);
++
+ private:
+ bool will_show_line_p (linenum_type row) const;
+ void print_leading_fixits (linenum_type row);
+@@ -386,6 +429,7 @@ class layout
+ private:
+ diagnostic_context *m_context;
+ pretty_printer *m_pp;
++ char_display_policy m_policy;
+ location_t m_primary_loc;
+ exploc_with_display_col m_exploc;
+ colorizer m_colorizer;
+@@ -398,6 +442,7 @@ class layout
+ auto_vec <line_span> m_line_spans;
+ int m_linenum_width;
+ int m_x_offset_display;
++ bool m_escape_on_output;
+ };
+
+ /* Implementation of "class colorizer". */
+@@ -646,6 +691,11 @@ layout_range::intersects_line_p (linenum
+ /* Default for when we don't care what the tab expansion is set to. */
+ static const int def_tabstop = 8;
+
++static cpp_char_column_policy def_policy ()
++{
++ return cpp_char_column_policy (8, cpp_wcwidth);
++}
++
+ /* Create some expanded locations for testing layout_range. The filename
+ member of the explocs is set to the empty string. This member will only be
+ inspected by the calls to location_compute_display_column() made from the
+@@ -662,10 +712,13 @@ make_range (int start_line, int start_co
+ = {"", start_line, start_col, NULL, false};
+ const expanded_location finish_exploc
+ = {"", end_line, end_col, NULL, false};
+- return layout_range (exploc_with_display_col (start_exploc, def_tabstop),
+- exploc_with_display_col (finish_exploc, def_tabstop),
++ return layout_range (exploc_with_display_col (start_exploc, def_policy (),
++ LOCATION_ASPECT_START),
++ exploc_with_display_col (finish_exploc, def_policy (),
++ LOCATION_ASPECT_FINISH),
+ SHOW_RANGE_WITHOUT_CARET,
+- exploc_with_display_col (start_exploc, def_tabstop),
++ exploc_with_display_col (start_exploc, def_policy (),
++ LOCATION_ASPECT_CARET),
+ 0, NULL);
+ }
+
+@@ -950,6 +1003,164 @@ fixit_cmp (const void *p_a, const void *
+ return hint_a->get_start_loc () - hint_b->get_start_loc ();
+ }
+
++/* Callbacks for use when not escaping the source. */
++
++/* The default callback for char_column_policy::m_width_cb is cpp_wcwidth. */
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when not escaping the source. */
++
++static void
++default_print_decoded_ch (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ for (const char *ptr = decoded_ch.m_start_byte;
++ ptr != decoded_ch.m_next_byte; ptr++)
++ {
++ if (*ptr == '\0' || *ptr == '\r')
++ {
++ pp_space (pp);
++ continue;
++ }
++
++ pp_character (pp, *ptr);
++ }
++}
++
++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static const int width_per_escaped_byte = 4;
++
++/* Callback for char_column_policy::m_width_cb for determining the
++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static int
++escape_as_bytes_width (cppchar_t ch)
++{
++ if (ch < 0x80 && ISPRINT (ch))
++ return cpp_wcwidth (ch);
++ else
++ {
++ if (ch <= 0x7F) return 1 * width_per_escaped_byte;
++ if (ch <= 0x7FF) return 2 * width_per_escaped_byte;
++ if (ch <= 0xFFFF) return 3 * width_per_escaped_byte;
++ return 4 * width_per_escaped_byte;
++ }
++}
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static void
++escape_as_bytes_print (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ if (!decoded_ch.m_valid_ch)
++ {
++ for (const char *iter = decoded_ch.m_start_byte;
++ iter != decoded_ch.m_next_byte; ++iter)
++ {
++ char buf[16];
++ sprintf (buf, "<%02x>", (unsigned char)*iter);
++ pp_string (pp, buf);
++ }
++ return;
++ }
++
++ cppchar_t ch = decoded_ch.m_ch;
++ if (ch < 0x80 && ISPRINT (ch))
++ pp_character (pp, ch);
++ else
++ {
++ for (const char *iter = decoded_ch.m_start_byte;
++ iter < decoded_ch.m_next_byte; ++iter)
++ {
++ char buf[16];
++ sprintf (buf, "<%02x>", (unsigned char)*iter);
++ pp_string (pp, buf);
++ }
++ }
++}
++
++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++/* Callback for char_column_policy::m_width_cb for determining the
++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++static int
++escape_as_unicode_width (cppchar_t ch)
++{
++ if (ch < 0x80 && ISPRINT (ch))
++ return cpp_wcwidth (ch);
++ else
++ {
++ // Width of "<U+%04x>"
++ if (ch > 0xfffff)
++ return 10;
++ else if (ch > 0xffff)
++ return 9;
++ else
++ return 8;
++ }
++}
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++static void
++escape_as_unicode_print (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ if (!decoded_ch.m_valid_ch)
++ {
++ escape_as_bytes_print (pp, decoded_ch);
++ return;
++ }
++
++ cppchar_t ch = decoded_ch.m_ch;
++ if (ch < 0x80 && ISPRINT (ch))
++ pp_character (pp, ch);
++ else
++ {
++ char buf[16];
++ sprintf (buf, "<U+%04X>", ch);
++ pp_string (pp, buf);
++ }
++}
++
++/* Populate a char_display_policy based on DC and RICHLOC. */
++
++static char_display_policy
++make_policy (const diagnostic_context &dc,
++ const rich_location &richloc)
++{
++ /* The default is to not escape non-ASCII bytes. */
++ char_display_policy result
++ (dc.tabstop, cpp_wcwidth, default_print_decoded_ch);
++
++ /* If the diagnostic suggests escaping non-ASCII bytes, then
++ use policy from user-supplied options. */
++ if (richloc.escape_on_output_p ())
++ {
++ result.m_undecoded_byte_width = width_per_escaped_byte;
++ switch (dc.escape_format)
++ {
++ default:
++ gcc_unreachable ();
++ case DIAGNOSTICS_ESCAPE_FORMAT_UNICODE:
++ result.m_width_cb = escape_as_unicode_width;
++ result.m_print_cb = escape_as_unicode_print;
++ break;
++ case DIAGNOSTICS_ESCAPE_FORMAT_BYTES:
++ result.m_width_cb = escape_as_bytes_width;
++ result.m_print_cb = escape_as_bytes_print;
++ break;
++ }
++ }
++
++ return result;
++}
++
+ /* Implementation of class layout. */
+
+ /* Constructor for class layout.
+@@ -966,8 +1177,10 @@ layout::layout (diagnostic_context * con
+ diagnostic_t diagnostic_kind)
+ : m_context (context),
+ m_pp (context->printer),
++ m_policy (make_policy (*context, *richloc)),
+ m_primary_loc (richloc->get_range (0)->m_loc),
+- m_exploc (richloc->get_expanded_location (0), context->tabstop),
++ m_exploc (richloc->get_expanded_location (0), m_policy,
++ LOCATION_ASPECT_CARET),
+ m_colorizer (context, diagnostic_kind),
+ m_colorize_source_p (context->colorize_source_p),
+ m_show_labels_p (context->show_labels_p),
+@@ -977,7 +1190,8 @@ layout::layout (diagnostic_context * con
+ m_fixit_hints (richloc->get_num_fixit_hints ()),
+ m_line_spans (1 + richloc->get_num_locations ()),
+ m_linenum_width (0),
+- m_x_offset_display (0)
++ m_x_offset_display (0),
++ m_escape_on_output (richloc->escape_on_output_p ())
+ {
+ for (unsigned int idx = 0; idx < richloc->get_num_locations (); idx++)
+ {
+@@ -1063,10 +1277,13 @@ layout::maybe_add_location_range (const
+
+ /* Everything is now known to be in the correct source file,
+ but it may require further sanitization. */
+- layout_range ri (exploc_with_display_col (start, m_context->tabstop),
+- exploc_with_display_col (finish, m_context->tabstop),
++ layout_range ri (exploc_with_display_col (start, m_policy,
++ LOCATION_ASPECT_START),
++ exploc_with_display_col (finish, m_policy,
++ LOCATION_ASPECT_FINISH),
+ loc_range->m_range_display_kind,
+- exploc_with_display_col (caret, m_context->tabstop),
++ exploc_with_display_col (caret, m_policy,
++ LOCATION_ASPECT_CARET),
+ original_idx, loc_range->m_label);
+
+ /* If we have a range that finishes before it starts (perhaps
+@@ -1400,7 +1617,7 @@ layout::calculate_x_offset_display ()
+ = get_line_bytes_without_trailing_whitespace (line.get_buffer (),
+ line.length ());
+ int eol_display_column
+- = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop);
++ = cpp_display_width (line.get_buffer (), line_bytes, m_policy);
+ if (caret_display_column > eol_display_column
+ || !caret_display_column)
+ {
+@@ -1479,7 +1696,7 @@ layout::print_source_line (linenum_type
+ /* This object helps to keep track of which display column we are at, which is
+ necessary for computing the line bounds in display units, for doing
+ tab expansion, and for implementing m_x_offset_display. */
+- cpp_display_width_computation dw (line, line_bytes, m_context->tabstop);
++ cpp_display_width_computation dw (line, line_bytes, m_policy);
+
+ /* Skip the first m_x_offset_display display columns. In case the leading
+ portion that will be skipped ends with a character with wcwidth > 1, then
+@@ -1527,7 +1744,8 @@ layout::print_source_line (linenum_type
+ tabs and replacing some control bytes with spaces as necessary. */
+ const char *c = dw.next_byte ();
+ const int start_disp_col = dw.display_cols_processed () + 1;
+- const int this_display_width = dw.process_next_codepoint ();
++ cpp_decoded_char cp;
++ const int this_display_width = dw.process_next_codepoint (&cp);
+ if (*c == '\t')
+ {
+ /* The returned display width is the number of spaces into which the
+@@ -1536,15 +1754,6 @@ layout::print_source_line (linenum_type
+ pp_space (m_pp);
+ continue;
+ }
+- if (*c == '\0' || *c == '\r')
+- {
+- /* cpp_wcwidth() promises to return 1 for all control bytes, and we
+- want to output these as a single space too, so this case is
+- actually the same as the '\t' case. */
+- gcc_assert (this_display_width == 1);
+- pp_space (m_pp);
+- continue;
+- }
+
+ /* We have a (possibly multibyte) character to output; update the line
+ bounds if it is not whitespace. */
+@@ -1556,7 +1765,8 @@ layout::print_source_line (linenum_type
+ }
+
+ /* Output the character. */
+- while (c != dw.next_byte ()) pp_character (m_pp, *c++);
++ m_policy.m_print_cb (m_pp, cp);
++ c = dw.next_byte ();
+ }
+ print_newline ();
+ return lbounds;
+@@ -1655,14 +1865,14 @@ layout::print_annotation_line (linenum_t
+ class line_label
+ {
+ public:
+- line_label (diagnostic_context *context, int state_idx, int column,
++ line_label (const cpp_char_column_policy &policy,
++ int state_idx, int column,
+ label_text text)
+ : m_state_idx (state_idx), m_column (column),
+ m_text (text), m_label_line (0), m_has_vbar (true)
+ {
+ const int bytes = strlen (text.m_buffer);
+- m_display_width
+- = cpp_display_width (text.m_buffer, bytes, context->tabstop);
++ m_display_width = cpp_display_width (text.m_buffer, bytes, policy);
+ }
+
+ /* Sorting is primarily by column, then by state index. */
+@@ -1722,7 +1932,7 @@ layout::print_any_labels (linenum_type r
+ if (text.m_buffer == NULL)
+ continue;
+
+- labels.safe_push (line_label (m_context, i, disp_col, text));
++ labels.safe_push (line_label (m_policy, i, disp_col, text));
+ }
+ }
+
+@@ -2002,7 +2212,7 @@ public:
+
+ /* Get the range of bytes or display columns that HINT would affect. */
+ static column_range
+-get_affected_range (diagnostic_context *context,
++get_affected_range (const cpp_char_column_policy &policy,
+ const fixit_hint *hint, enum column_unit col_unit)
+ {
+ expanded_location exploc_start = expand_location (hint->get_start_loc ());
+@@ -2013,13 +2223,11 @@ get_affected_range (diagnostic_context *
+ int finish_column;
+ if (col_unit == CU_DISPLAY_COLS)
+ {
+- start_column
+- = location_compute_display_column (exploc_start, context->tabstop);
++ start_column = location_compute_display_column (exploc_start, policy);
+ if (hint->insertion_p ())
+ finish_column = start_column - 1;
+ else
+- finish_column
+- = location_compute_display_column (exploc_finish, context->tabstop);
++ finish_column = location_compute_display_column (exploc_finish, policy);
+ }
+ else
+ {
+@@ -2032,12 +2240,13 @@ get_affected_range (diagnostic_context *
+ /* Get the range of display columns that would be printed for HINT. */
+
+ static column_range
+-get_printed_columns (diagnostic_context *context, const fixit_hint *hint)
++get_printed_columns (const cpp_char_column_policy &policy,
++ const fixit_hint *hint)
+ {
+ expanded_location exploc = expand_location (hint->get_start_loc ());
+- int start_column = location_compute_display_column (exploc, context->tabstop);
++ int start_column = location_compute_display_column (exploc, policy);
+ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (),
+- context->tabstop);
++ policy);
+ int final_hint_column = start_column + hint_width - 1;
+ if (hint->insertion_p ())
+ {
+@@ -2047,8 +2256,7 @@ get_printed_columns (diagnostic_context
+ {
+ exploc = expand_location (hint->get_next_loc ());
+ --exploc.column;
+- int finish_column
+- = location_compute_display_column (exploc, context->tabstop);
++ int finish_column = location_compute_display_column (exploc, policy);
+ return column_range (start_column,
+ MAX (finish_column, final_hint_column));
+ }
+@@ -2066,13 +2274,13 @@ public:
+ column_range affected_columns,
+ column_range printed_columns,
+ const char *new_text, size_t new_text_len,
+- int tabstop)
++ const cpp_char_column_policy &policy)
+ : m_affected_bytes (affected_bytes),
+ m_affected_columns (affected_columns),
+ m_printed_columns (printed_columns),
+ m_text (xstrdup (new_text)),
+ m_byte_length (new_text_len),
+- m_tabstop (tabstop),
++ m_policy (policy),
+ m_alloc_sz (new_text_len + 1)
+ {
+ compute_display_cols ();
+@@ -2090,7 +2298,7 @@ public:
+
+ void compute_display_cols ()
+ {
+- m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop);
++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_policy);
+ }
+
+ void overwrite (int dst_offset, const char_span &src_span)
+@@ -2118,7 +2326,7 @@ public:
+ char *m_text;
+ size_t m_byte_length; /* Not including null-terminator. */
+ int m_display_cols;
+- int m_tabstop;
++ const cpp_char_column_policy &m_policy;
+ size_t m_alloc_sz;
+ };
+
+@@ -2154,15 +2362,16 @@ correction::ensure_terminated ()
+ class line_corrections
+ {
+ public:
+- line_corrections (diagnostic_context *context, const char *filename,
++ line_corrections (const char_display_policy &policy,
++ const char *filename,
+ linenum_type row)
+- : m_context (context), m_filename (filename), m_row (row)
++ : m_policy (policy), m_filename (filename), m_row (row)
+ {}
+ ~line_corrections ();
+
+ void add_hint (const fixit_hint *hint);
+
+- diagnostic_context *m_context;
++ const char_display_policy &m_policy;
+ const char *m_filename;
+ linenum_type m_row;
+ auto_vec <correction *> m_corrections;
+@@ -2208,10 +2417,10 @@ source_line::source_line (const char *fi
+ void
+ line_corrections::add_hint (const fixit_hint *hint)
+ {
+- column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES);
+- column_range affected_columns = get_affected_range (m_context, hint,
++ column_range affected_bytes = get_affected_range (m_policy, hint, CU_BYTES);
++ column_range affected_columns = get_affected_range (m_policy, hint,
+ CU_DISPLAY_COLS);
+- column_range printed_columns = get_printed_columns (m_context, hint);
++ column_range printed_columns = get_printed_columns (m_policy, hint);
+
+ /* Potentially consolidate. */
+ if (!m_corrections.is_empty ())
+@@ -2280,7 +2489,7 @@ line_corrections::add_hint (const fixit_
+ printed_columns,
+ hint->get_string (),
+ hint->get_length (),
+- m_context->tabstop));
++ m_policy));
+ }
+
+ /* If there are any fixit hints on source line ROW, print them.
+@@ -2294,7 +2503,7 @@ layout::print_trailing_fixits (linenum_t
+ {
+ /* Build a list of correction instances for the line,
+ potentially consolidating hints (for the sake of readability). */
+- line_corrections corrections (m_context, m_exploc.file, row);
++ line_corrections corrections (m_policy, m_exploc.file, row);
+ for (unsigned int i = 0; i < m_fixit_hints.length (); i++)
+ {
+ const fixit_hint *hint = m_fixit_hints[i];
+@@ -2635,6 +2844,59 @@ namespace selftest {
+
+ /* Selftests for diagnostic_show_locus. */
+
++/* Verify that cpp_display_width correctly handles escaping. */
++
++static void
++test_display_widths ()
++{
++ gcc_rich_location richloc (UNKNOWN_LOCATION);
++
++ /* U+03C0 "GREEK SMALL LETTER PI". */
++ const char *pi = "\xCF\x80";
++ /* U+1F642 "SLIGHTLY SMILING FACE". */
++ const char *emoji = "\xF0\x9F\x99\x82";
++ /* Stray trailing byte of a UTF-8 character. */
++ const char *stray = "\xBF";
++ /* U+10FFFF. */
++ const char *max_codepoint = "\xF4\x8F\xBF\xBF";
++
++ /* No escaping. */
++ {
++ test_diagnostic_context dc;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 1);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 2);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 1);
++ /* Don't check width of U+10FFFF; it's in a private use plane. */
++ }
++
++ richloc.set_escape_on_output (true);
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 9);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4);
++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint),
++ policy),
++ strlen ("<U+10FFFF>"));
++ }
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 16);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4);
++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint),
++ policy),
++ 16);
++ }
++}
++
+ /* For precise tests of the layout, make clear where the source line will
+ start. test_left_margin sets the total byte count from the left side of the
+ screen to the start of source lines, after the line number and the separator,
+@@ -2704,10 +2966,10 @@ test_layout_x_offset_display_utf8 (const
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ (line_display_cols,
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (line_display_cols,
+ location_compute_display_column (expand_location (line_end),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1),
+ "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8));
+
+@@ -2855,12 +3117,13 @@ test_layout_x_offset_display_tab (const
+ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1)));
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+- tabstop));
++ policy));
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ location_compute_display_column (expand_location (line_end),
+- tabstop));
++ policy));
+ }
+
+ /* Check that the tab is expanded to the expected number of spaces. */
+@@ -3992,6 +4255,43 @@ test_one_liner_labels_utf8 ()
+ " bb\xf0\x9f\x98\x82\xf0\x9f\x98\x82\n",
+ pp_formatted_text (dc.printer));
+ }
++
++ /* Example of escaping the source lines. */
++ {
++ text_range_label label0 ("label 0\xf0\x9f\x98\x82");
++ text_range_label label1 ("label 1\xcf\x80");
++ text_range_label label2 ("label 2\xcf\x80");
++ gcc_rich_location richloc (foo, &label0);
++ richloc.add_range (bar, SHOW_RANGE_WITHOUT_CARET, &label1);
++ richloc.add_range (field, SHOW_RANGE_WITHOUT_CARET, &label2);
++ richloc.set_escape_on_output (true);
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <U+1F602>_foo = <U+03C0>_bar.<U+1F602>_field<U+03C0>;\n"
++ " ^~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~\n"
++ " | | |\n"
++ " | | label 2\xcf\x80\n"
++ " | label 1\xcf\x80\n"
++ " label 0\xf0\x9f\x98\x82\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ
++ (" <f0><9f><98><82>_foo = <cf><80>_bar.<f0><9f><98><82>_field<cf><80>;\n"
++ " ^~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n"
++ " | | |\n"
++ " | | label 2\xcf\x80\n"
++ " | label 1\xcf\x80\n"
++ " label 0\xf0\x9f\x98\x82\n",
++ pp_formatted_text (dc.printer));
++ }
++ }
+ }
+
+ /* Make sure that colorization codes don't interrupt a multibyte
+@@ -4046,9 +4346,9 @@ test_diagnostic_show_locus_one_liner_utf
+
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end),
+- def_tabstop));
++ def_policy ()));
+
+ test_one_liner_simple_caret_utf8 ();
+ test_one_liner_caret_and_range_utf8 ();
+@@ -4434,30 +4734,31 @@ test_overlapped_fixit_printing (const li
+ pp_formatted_text (dc.printer));
+
+ /* Unit-test the line_corrections machinery. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_BYTES));
++ get_affected_range (policy, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_BYTES));
++ get_affected_range (policy, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+ ASSERT_EQ (column_range (29, 28),
+- get_affected_range (&dc, hint_2, CU_BYTES));
++ get_affected_range (policy, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (29, 28),
+- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2));
++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (29, 29), get_printed_columns (policy, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (&dc, tmp.get_filename (), 1);
++ line_corrections lc (policy, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4649,30 +4950,31 @@ test_overlapped_fixit_printing_utf8 (con
+ pp_formatted_text (dc.printer));
+
+ /* Unit-test the line_corrections machinery. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (14, 14),
+- get_affected_range (&dc, hint_0, CU_BYTES));
++ get_affected_range (policy, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (22, 22),
+- get_affected_range (&dc, hint_1, CU_BYTES));
++ get_affected_range (policy, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+ ASSERT_EQ (column_range (35, 34),
+- get_affected_range (&dc, hint_2, CU_BYTES));
++ get_affected_range (policy, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (30, 29),
+- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2));
++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (30, 30), get_printed_columns (policy, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (&dc, tmp.get_filename (), 1);
++ line_corrections lc (policy, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4866,15 +5168,16 @@ test_overlapped_fixit_printing_2 (const
+ richloc.add_fixit_insert_before (col_21, "}");
+
+ /* These fixits should be accepted; they can't be consolidated. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (2, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (23, 22),
+- get_affected_range (&dc, hint_0, CU_BYTES));
+- ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_BYTES));
++ ASSERT_EQ (column_range (23, 23), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (21, 20),
+- get_affected_range (&dc, hint_1, CU_BYTES));
+- ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_BYTES));
++ ASSERT_EQ (column_range (21, 21), get_printed_columns (policy, hint_1));
+
+ /* Verify that they're printed correctly. */
+ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
+@@ -5141,10 +5444,11 @@ test_tab_expansion (const line_table_cas
+ ....................123 45678901234 56789012345 columns */
+
+ const int tabstop = 8;
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
+ const int first_non_ws_byte_col = 7;
+ const int right_quote_byte_col = 15;
+ const int last_byte_col = 25;
+- ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop));
++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, policy));
+
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ line_table_test ltt (case_);
+@@ -5187,6 +5491,114 @@ test_tab_expansion (const line_table_cas
+ }
+ }
+
++/* Verify that the escaping machinery can cope with a variety of different
++ invalid bytes. */
++
++static void
++test_escaping_bytes_1 (const line_table_case &case_)
++{
++ const char content[] = "before\0\1\2\3\r\x80\xff""after\n";
++ const size_t sz = sizeof (content);
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz);
++ line_table_test ltt (case_);
++ const line_map_ordinary *ord_map = linemap_check_ordinary
++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0));
++ linemap_line_start (line_table, 1, 100);
++
++ location_t finish
++ = linemap_position_for_line_and_column (line_table, ord_map, 1,
++ strlen (content));
++
++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Locations of the NUL and \r bytes. */
++ location_t nul_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 7);
++ location_t r_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 11);
++ gcc_rich_location richloc (nul_loc);
++ richloc.add_range (r_loc);
++
++ {
++ test_diagnostic_context dc;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" before \1\2\3 \x80\xff""after\n"
++ " ^ ~\n",
++ pp_formatted_text (dc.printer));
++ }
++ richloc.set_escape_on_output (true);
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ
++ (" before<U+0000><U+0001><U+0002><U+0003><U+000D><80><ff>after\n"
++ " ^~~~~~~~ ~~~~~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" before<00><01><02><03><0d><80><ff>after\n"
++ " ^~~~ ~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++}
++
++/* As above, but verify that we handle the initial byte of a line
++ correctly. */
++
++static void
++test_escaping_bytes_2 (const line_table_case &case_)
++{
++ const char content[] = "\0after\n";
++ const size_t sz = sizeof (content);
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz);
++ line_table_test ltt (case_);
++ const line_map_ordinary *ord_map = linemap_check_ordinary
++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0));
++ linemap_line_start (line_table, 1, 100);
++
++ location_t finish
++ = linemap_position_for_line_and_column (line_table, ord_map, 1,
++ strlen (content));
++
++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Location of the NUL byte. */
++ location_t nul_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 1);
++ gcc_rich_location richloc (nul_loc);
++
++ {
++ test_diagnostic_context dc;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" after\n"
++ " ^\n",
++ pp_formatted_text (dc.printer));
++ }
++ richloc.set_escape_on_output (true);
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <U+0000>after\n"
++ " ^~~~~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <00>after\n"
++ " ^~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++}
++
+ /* Verify that line numbers are correctly printed for the case of
+ a multiline range in which the width of the line numbers changes
+ (e.g. from "9" to "10"). */
+@@ -5243,6 +5655,8 @@ diagnostic_show_locus_c_tests ()
+ test_layout_range_for_single_line ();
+ test_layout_range_for_multiple_lines ();
+
++ test_display_widths ();
++
+ for_each_line_table_case (test_layout_x_offset_display_utf8);
+ for_each_line_table_case (test_layout_x_offset_display_tab);
+
+@@ -5263,6 +5677,8 @@ diagnostic_show_locus_c_tests ()
+ for_each_line_table_case (test_fixit_replace_containing_newline);
+ for_each_line_table_case (test_fixit_deletion_affecting_newline);
+ for_each_line_table_case (test_tab_expansion);
++ for_each_line_table_case (test_escaping_bytes_1);
++ for_each_line_table_case (test_escaping_bytes_2);
+
+ test_line_numbers_multiline_range ();
+ }
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+--- a/gcc/doc/invoke.texi 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/doc/invoke.texi 2021-12-25 01:30:50.681688823 -0800
+@@ -295,7 +295,8 @@ Objective-C and Objective-C++ Dialects}.
+ -fdiagnostics-show-path-depths @gol
+ -fno-show-column @gol
+ -fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol
+--fdiagnostics-column-origin=@var{origin}}
++-fdiagnostics-column-origin=@var{origin} @gol
++-fdiagnostics-escape-format=@r{[}unicode@r{|}bytes@r{]}}
+
+ @item Warning Options
+ @xref{Warning Options,,Options to Request or Suppress Warnings}.
+@@ -4451,6 +4452,38 @@ first column. The default value of 1 co
+ behavior and to the GNU style guide. Some utilities may perform better with an
+ origin of 0; any non-negative value may be specified.
+
++@item -fdiagnostics-escape-format=@var{FORMAT}
++@opindex fdiagnostics-escape-format
++When GCC prints pertinent source lines for a diagnostic it normally attempts
++to print the source bytes directly. However, some diagnostics relate to encoding
++issues in the source file, such as malformed UTF-8, or issues with Unicode
++normalization. These diagnostics are flagged so that GCC will escape bytes
++that are not printable ASCII when printing their pertinent source lines.
++
++This option controls how such bytes should be escaped.
++
++The default @var{FORMAT}, @samp{unicode} displays Unicode characters that
++are not printable ASCII in the form @samp{<U+XXXX>}, and bytes that do not
++correspond to a Unicode character validly-encoded in UTF-8-encoded will be
++displayed as hexadecimal in the form @samp{<XX>}.
++
++For example, a source line containing the string @samp{before} followed by the
++Unicode character U+03C0 (``GREEK SMALL LETTER PI'', with UTF-8 encoding
++0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by
++the string @samp{after} will be printed for such a diagnostic as:
++
++@smallexample
++ before<U+03C0><BF>after
++@end smallexample
++
++Setting @var{FORMAT} to @samp{bytes} will display all non-printable-ASCII bytes
++in the form @samp{<XX>}, thus showing the underlying encoding of non-ASCII
++Unicode characters. For the example above, the following will be printed:
++
++@smallexample
++ before<CF><80><BF>after
++@end smallexample
++
+ @item -fdiagnostics-format=@var{FORMAT}
+ @opindex fdiagnostics-format
+ Select a different format for printing diagnostics.
+@@ -4518,9 +4551,11 @@ might be printed in JSON form (after for
+ @}
+ @}
+ ],
++ "escape-source": false,
+ "message": "...this statement, but the latter is @dots{}"
+ @}
+ ]
++ "escape-source": false,
+ "column-origin": 1,
+ @},
+ @dots{}
+@@ -4607,6 +4642,7 @@ of the expression, which have labels. I
+ "label": "T @{aka struct t@}"
+ @}
+ ],
++ "escape-source": false,
+ "message": "invalid operands to binary + @dots{}"
+ @}
+ @end smallexample
+@@ -4660,6 +4696,7 @@ might be printed in JSON form as:
+ @}
+ @}
+ ],
++ "escape-source": false,
+ "message": "\u2018struct s\u2019 has no member named @dots{}"
+ @}
+ @end smallexample
+@@ -4717,6 +4754,10 @@ For example, the intraprocedural example
+ ]
+ @end smallexample
+
++Diagnostics have a boolean attribute @code{escape-source}, hinting whether
++non-ASCII bytes should be escaped when printing the pertinent lines of
++source code (@code{true} for diagnostics involving source encoding issues).
++
+ @end table
+
+ @node Warning Options
+diff --git a/gcc/input.c b/gcc/input.c
+--- a/gcc/input.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/input.c 2021-12-25 01:30:50.681688823 -0800
+@@ -913,7 +913,8 @@ make_location (location_t caret, source_
+ source line in order to calculate the display width. If that cannot be done
+ for any reason, then returns the byte column as a fallback. */
+ int
+-location_compute_display_column (expanded_location exploc, int tabstop)
++location_compute_display_column (expanded_location exploc,
++ const cpp_char_column_policy &policy)
+ {
+ if (!(exploc.file && *exploc.file && exploc.line && exploc.column))
+ return exploc.column;
+@@ -921,7 +922,7 @@ location_compute_display_column (expande
+ /* If line is NULL, this function returns exploc.column which is the
+ desired fallback. */
+ return cpp_byte_column_to_display_column (line.get_buffer (), line.length (),
+- exploc.column, tabstop);
++ exploc.column, policy);
+ }
+
+ /* Dump statistics to stderr about the memory usage of the line_table
+@@ -3609,43 +3610,50 @@ test_line_offset_overflow ()
+ void test_cpp_utf8 ()
+ {
+ const int def_tabstop = 8;
++ cpp_char_column_policy policy (def_tabstop, cpp_wcwidth);
++
+ /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */
+ {
+- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop);
++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, policy);
+ ASSERT_EQ (8, w_bad);
+- int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop);
++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, policy);
+ ASSERT_EQ (5, w_ctrl);
+ }
+
+ /* Verify that wcwidth of valid UTF-8 is as expected. */
+ {
+- const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop);
++ const int w_pi = cpp_display_width ("\xcf\x80", 2, policy);
+ ASSERT_EQ (1, w_pi);
+- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop);
++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, policy);
+ ASSERT_EQ (2, w_emoji);
+ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2,
+- def_tabstop);
++ policy);
+ ASSERT_EQ (1, w_umlaut_precomposed);
+ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3,
+- def_tabstop);
++ policy);
+ ASSERT_EQ (1, w_umlaut_combining);
+- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop);
++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, policy);
+ ASSERT_EQ (2, w_han);
+- const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop);
++ const int w_ascii = cpp_display_width ("GCC", 3, policy);
+ ASSERT_EQ (3, w_ascii);
+ const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82"
+ "\x9f! \xe4\xb8\xba y\xcc\x88",
+- 24, def_tabstop);
++ 24, policy);
+ ASSERT_EQ (18, w_mixed);
+ }
+
+ /* Verify that display width properly expands tabs. */
+ {
+ const char *tstr = "\tabc\td";
+- ASSERT_EQ (6, cpp_display_width (tstr, 6, 1));
+- ASSERT_EQ (10, cpp_display_width (tstr, 6, 3));
+- ASSERT_EQ (17, cpp_display_width (tstr, 6, 8));
+- ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8));
++ ASSERT_EQ (6, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (1, cpp_wcwidth)));
++ ASSERT_EQ (10, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (3, cpp_wcwidth)));
++ ASSERT_EQ (17, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (8, cpp_wcwidth)));
++ ASSERT_EQ (1,
++ cpp_display_column_to_byte_column
++ (tstr, 6, 7, cpp_char_column_policy (8, cpp_wcwidth)));
+ }
+
+ /* Verify that cpp_byte_column_to_display_column can go past the end,
+@@ -3658,13 +3666,13 @@ void test_cpp_utf8 ()
+ /* 111122223456
+ Byte columns. */
+
+- ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop));
++ ASSERT_EQ (5, cpp_display_width (str, 6, policy));
+ ASSERT_EQ (105,
+- cpp_byte_column_to_display_column (str, 6, 106, def_tabstop));
++ cpp_byte_column_to_display_column (str, 6, 106, policy));
+ ASSERT_EQ (10000,
+- cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop));
++ cpp_byte_column_to_display_column (NULL, 0, 10000, policy));
+ ASSERT_EQ (0,
+- cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop));
++ cpp_byte_column_to_display_column (NULL, 10000, 0, policy));
+ }
+
+ /* Verify that cpp_display_column_to_byte_column can go past the end,
+@@ -3678,25 +3686,25 @@ void test_cpp_utf8 ()
+ /* 000000000000000000000000000000000111111
+ 111122223333444456666777788889999012345
+ Byte columns. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, policy));
+ ASSERT_EQ (15,
+- cpp_display_column_to_byte_column (str, 15, 11, def_tabstop));
++ cpp_display_column_to_byte_column (str, 15, 11, policy));
+ ASSERT_EQ (115,
+- cpp_display_column_to_byte_column (str, 15, 111, def_tabstop));
++ cpp_display_column_to_byte_column (str, 15, 111, policy));
+ ASSERT_EQ (10000,
+- cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop));
++ cpp_display_column_to_byte_column (NULL, 0, 10000, policy));
+ ASSERT_EQ (0,
+- cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop));
++ cpp_display_column_to_byte_column (NULL, 10000, 0, policy));
+
+ /* Verify that we do not interrupt a UTF-8 sequence. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, policy));
+
+ for (int byte_col = 1; byte_col <= 15; ++byte_col)
+ {
+ const int disp_col
+- = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop);
++ = cpp_byte_column_to_display_column (str, 15, byte_col, policy);
+ const int byte_col2
+- = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop);
++ = cpp_display_column_to_byte_column (str, 15, disp_col, policy);
+
+ /* If we ask for the display column in the middle of a UTF-8
+ sequence, it will return the length of the partial sequence,
+diff --git a/gcc/input.h b/gcc/input.h
+--- a/gcc/input.h 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/input.h 2021-12-25 01:30:50.681688823 -0800
+@@ -39,8 +39,11 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER
+ extern bool is_location_from_builtin_token (location_t);
+ extern expanded_location expand_location (location_t);
+
+-extern int location_compute_display_column (expanded_location exploc,
+- int tabstop);
++class cpp_char_column_policy;
++
++extern int
++location_compute_display_column (expanded_location exploc,
++ const cpp_char_column_policy &policy);
+
+ /* A class capturing the bounds of a buffer, to allow for run-time
+ bounds-checking in a checked build. */
+diff --git a/gcc/opts.c b/gcc/opts.c
+--- a/gcc/opts.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/opts.c 2021-12-25 01:30:50.681688823 -0800
+@@ -2447,6 +2447,10 @@ common_handle_option (struct gcc_options
+ dc->column_origin = value;
+ break;
+
++ case OPT_fdiagnostics_escape_format_:
++ dc->escape_format = (enum diagnostics_escape_format)value;
++ break;
++
+ case OPT_fdiagnostics_show_cwe:
+ dc->show_cwe = value;
+ break;
+diff --git a/gcc/selftest.c b/gcc/selftest.c
+--- a/gcc/selftest.c 2020-07-22 23:35:17.820389797 -0700
++++ b/gcc/selftest.c 2021-12-25 01:30:50.681688823 -0800
+@@ -193,6 +193,21 @@ temp_source_file::temp_source_file (cons
+ fclose (out);
+ }
+
++/* As above, but with a size, to allow for NUL bytes in CONTENT. */
++
++temp_source_file::temp_source_file (const location &loc,
++ const char *suffix,
++ const char *content,
++ size_t sz)
++: named_temp_file (suffix)
++{
++ FILE *out = fopen (get_filename (), "w");
++ if (!out)
++ fail_formatted (loc, "unable to open tempfile: %s", get_filename ());
++ fwrite (content, sz, 1, out);
++ fclose (out);
++}
++
+ /* Avoid introducing locale-specific differences in the results
+ by hardcoding open_quote and close_quote. */
+
+diff --git a/gcc/selftest.h b/gcc/selftest.h
+--- a/gcc/selftest.h 2020-07-22 23:35:17.820389797 -0700
++++ b/gcc/selftest.h 2021-12-25 01:30:50.681688823 -0800
+@@ -112,6 +112,8 @@ class temp_source_file : public named_te
+ public:
+ temp_source_file (const location &loc, const char *suffix,
+ const char *content);
++ temp_source_file (const location &loc, const char *suffix,
++ const char *content, size_t sz);
+ };
+
+ /* RAII-style class for avoiding introducing locale-specific differences
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#error message\"" } */
+
+ /* { dg-regexp "\"caret\": \{" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"warning\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Wcpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:30:50.681688823 -0800
+@@ -19,6 +19,7 @@ int test (void)
+
+ /* { dg-regexp "\"kind\": \"note\"" } */
+ /* { dg-regexp "\"message\": \"...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'\"" } */
++/* { dg-regexp "\"escape-source\": false" } */
+
+ /* { dg-regexp "\"caret\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+@@ -39,6 +40,7 @@ int test (void)
+ /* { dg-regexp "\"kind\": \"warning\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */
+
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:29:12.927317174 -0800
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:30:50.681688823 -0800
+@@ -14,6 +14,7 @@ int test (struct s *ptr)
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \".*\"" } */
+
+ /* Verify fix-it hints. */
+diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c
+--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 2021-12-25 01:30:50.681688823 -0800
+@@ -0,0 +1,21 @@
++// { dg-do preprocess }
++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=bytes" }
++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */
++
++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e.
++ U+0F42 TIBETAN LETTER GA: à½
++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ
++
++ The UTF-8 encoding of U+0F43 TIBETAN LETTER GHA is: E0 BD 83. */
++
++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_\u0F43_after bar
++ ^~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
++
++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_<e0><bd><83>_after bar
++ ^~~~~~~~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c
+--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 2021-12-25 01:30:50.681688823 -0800
+@@ -0,0 +1,19 @@
++// { dg-do preprocess }
++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=unicode" }
++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */
++
++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e.
++ U+0F42 TIBETAN LETTER GA: à½
++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ */
++
++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_\u0F43_after bar
++ ^~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
++
++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_<U+0F43>_after bar
++ ^~~~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:29:12.931317107 -0800
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"error\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#error message\"" }
+
+ ! { dg-regexp "\"caret\": \{" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:29:12.931317107 -0800
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"warning\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Wcpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:29:12.931317107 -0800
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:30:50.681688823 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"error\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Werror=cpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+diff --git a/libcpp/charset.c b/libcpp/charset.c
+--- a/libcpp/charset.c 2021-12-25 01:29:12.931317107 -0800
++++ b/libcpp/charset.c 2021-12-25 01:30:50.681688823 -0800
+@@ -1549,12 +1549,14 @@ convert_escape (cpp_reader *pfile, const
+ "unknown escape sequence: '\\%c'", (int) c);
+ else
+ {
++ encoding_rich_location rich_loc (pfile);
++
+ /* diagnostic.c does not support "%03o". When it does, this
+ code can use %03o directly in the diagnostic again. */
+ char buf[32];
+ sprintf(buf, "%03o", (int) c);
+- cpp_error (pfile, CPP_DL_PEDWARN,
+- "unknown escape sequence: '\\%s'", buf);
++ cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc,
++ "unknown escape sequence: '\\%s'", buf);
+ }
+ }
+
+@@ -2277,14 +2279,16 @@ cpp_string_location_reader::get_next ()
+ }
+
+ cpp_display_width_computation::
+-cpp_display_width_computation (const char *data, int data_length, int tabstop) :
++cpp_display_width_computation (const char *data, int data_length,
++ const cpp_char_column_policy &policy) :
+ m_begin (data),
+ m_next (m_begin),
+ m_bytes_left (data_length),
+- m_tabstop (tabstop),
++ m_policy (policy),
+ m_display_cols (0)
+ {
+- gcc_assert (m_tabstop > 0);
++ gcc_assert (policy.m_tabstop > 0);
++ gcc_assert (policy.m_width_cb);
+ }
+
+
+@@ -2296,19 +2300,28 @@ cpp_display_width_computation (const cha
+ point to a valid UTF-8-encoded sequence, then it will be treated as a single
+ byte with display width 1. m_cur_display_col is the current display column,
+ relative to which tab stops should be expanded. Returns the display width of
+- the codepoint just processed. */
++ the codepoint just processed.
++ If OUT is non-NULL, it is populated. */
+
+ int
+-cpp_display_width_computation::process_next_codepoint ()
++cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out)
+ {
+ cppchar_t c;
+ int next_width;
+
++ if (out)
++ out->m_start_byte = m_next;
++
+ if (*m_next == '\t')
+ {
+ ++m_next;
+ --m_bytes_left;
+- next_width = m_tabstop - (m_display_cols % m_tabstop);
++ next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop);
++ if (out)
++ {
++ out->m_ch = '\t';
++ out->m_valid_ch = true;
++ }
+ }
+ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
+ != 0)
+@@ -2318,14 +2331,24 @@ cpp_display_width_computation::process_n
+ of one. */
+ ++m_next;
+ --m_bytes_left;
+- next_width = 1;
++ next_width = m_policy.m_undecoded_byte_width;
++ if (out)
++ out->m_valid_ch = false;
+ }
+ else
+ {
+ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
+- next_width = cpp_wcwidth (c);
++ next_width = m_policy.m_width_cb (c);
++ if (out)
++ {
++ out->m_ch = c;
++ out->m_valid_ch = true;
++ }
+ }
+
++ if (out)
++ out->m_next_byte = m_next;
++
+ m_display_cols += next_width;
+ return next_width;
+ }
+@@ -2341,7 +2364,7 @@ cpp_display_width_computation::advance_d
+ const int start = m_display_cols;
+ const int target = start + n;
+ while (m_display_cols < target && !done ())
+- process_next_codepoint ();
++ process_next_codepoint (NULL);
+ return m_display_cols - start;
+ }
+
+@@ -2349,29 +2372,33 @@ cpp_display_width_computation::advance_d
+ how many display columns are occupied by the first COLUMN bytes. COLUMN
+ may exceed DATA_LENGTH, in which case the phantom bytes at the end are
+ treated as if they have display width 1. Tabs are expanded to the next tab
+- stop, relative to the start of DATA. */
++ stop, relative to the start of DATA, and non-printable-ASCII characters
++ will be escaped as per POLICY. */
+
+ int
+ cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column, int tabstop)
++ int column,
++ const cpp_char_column_policy &policy)
+ {
+ const int offset = MAX (0, column - data_length);
+- cpp_display_width_computation dw (data, column - offset, tabstop);
++ cpp_display_width_computation dw (data, column - offset, policy);
+ while (!dw.done ())
+- dw.process_next_codepoint ();
++ dw.process_next_codepoint (NULL);
+ return dw.display_cols_processed () + offset;
+ }
+
+ /* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+ the least number of bytes that will result in at least DISPLAY_COL display
+ columns. The return value may exceed DATA_LENGTH if the entire string does
+- not occupy enough display columns. */
++ not occupy enough display columns. Non-printable-ASCII characters
++ will be escaped as per POLICY. */
+
+ int
+ cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col, int tabstop)
++ int display_col,
++ const cpp_char_column_policy &policy)
+ {
+- cpp_display_width_computation dw (data, data_length, tabstop);
++ cpp_display_width_computation dw (data, data_length, policy);
+ const int avail_display = dw.advance_display_cols (display_col);
+ return dw.bytes_processed () + MAX (0, display_col - avail_display);
+ }
+diff --git a/libcpp/errors.c b/libcpp/errors.c
+--- a/libcpp/errors.c 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/errors.c 2021-12-25 01:30:50.681688823 -0800
+@@ -27,6 +27,31 @@ along with this program; see the file CO
+ #include "cpplib.h"
+ #include "internal.h"
+
++/* Get a location_t for the current location in PFILE,
++ generally that of the previously lexed token. */
++
++location_t
++cpp_diagnostic_get_current_location (cpp_reader *pfile)
++{
++ if (CPP_OPTION (pfile, traditional))
++ {
++ if (pfile->state.in_directive)
++ return pfile->directive_line;
++ else
++ return pfile->line_table->highest_line;
++ }
++ /* We don't want to refer to a token before the beginning of the
++ current run -- that is invalid. */
++ else if (pfile->cur_token == pfile->cur_run->base)
++ {
++ return 0;
++ }
++ else
++ {
++ return pfile->cur_token[-1].src_loc;
++ }
++}
++
+ /* Print a diagnostic at the given location. */
+
+ ATTRIBUTE_FPTR_PRINTF(5,0)
+@@ -52,25 +77,7 @@ cpp_diagnostic (cpp_reader * pfile, enum
+ enum cpp_warning_reason reason,
+ const char *msgid, va_list *ap)
+ {
+- location_t src_loc;
+-
+- if (CPP_OPTION (pfile, traditional))
+- {
+- if (pfile->state.in_directive)
+- src_loc = pfile->directive_line;
+- else
+- src_loc = pfile->line_table->highest_line;
+- }
+- /* We don't want to refer to a token before the beginning of the
+- current run -- that is invalid. */
+- else if (pfile->cur_token == pfile->cur_run->base)
+- {
+- src_loc = 0;
+- }
+- else
+- {
+- src_loc = pfile->cur_token[-1].src_loc;
+- }
++ location_t src_loc = cpp_diagnostic_get_current_location (pfile);
+ rich_location richloc (pfile->line_table, src_loc);
+ return cpp_diagnostic_at (pfile, level, reason, &richloc, msgid, ap);
+ }
+@@ -142,6 +149,43 @@ cpp_warning_syshdr (cpp_reader * pfile,
+
+ va_end (ap);
+ return ret;
++}
++
++/* As cpp_warning above, but use RICHLOC as the location of the diagnostic. */
++
++bool cpp_warning_at (cpp_reader *pfile, enum cpp_warning_reason reason,
++ rich_location *richloc, const char *msgid, ...)
++{
++ va_list ap;
++ bool ret;
++
++ va_start (ap, msgid);
++
++ ret = cpp_diagnostic_at (pfile, CPP_DL_WARNING, reason, richloc,
++ msgid, &ap);
++
++ va_end (ap);
++ return ret;
++
++}
++
++/* As cpp_pedwarning above, but use RICHLOC as the location of the
++ diagnostic. */
++
++bool
++cpp_pedwarning_at (cpp_reader * pfile, enum cpp_warning_reason reason,
++ rich_location *richloc, const char *msgid, ...)
++{
++ va_list ap;
++ bool ret;
++
++ va_start (ap, msgid);
++
++ ret = cpp_diagnostic_at (pfile, CPP_DL_PEDWARN, reason, richloc,
++ msgid, &ap);
++
++ va_end (ap);
++ return ret;
+ }
+
+ /* Print a diagnostic at a specific location. */
+diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
+--- a/libcpp/include/cpplib.h 2021-12-25 01:29:12.931317107 -0800
++++ b/libcpp/include/cpplib.h 2021-12-25 01:30:50.685688757 -0800
+@@ -1176,6 +1176,14 @@ extern bool cpp_warning_syshdr (cpp_read
+ const char *msgid, ...)
+ ATTRIBUTE_PRINTF_3;
+
++/* As their counterparts above, but use RICHLOC. */
++extern bool cpp_warning_at (cpp_reader *, enum cpp_warning_reason,
++ rich_location *richloc, const char *msgid, ...)
++ ATTRIBUTE_PRINTF_4;
++extern bool cpp_pedwarning_at (cpp_reader *, enum cpp_warning_reason,
++ rich_location *richloc, const char *msgid, ...)
++ ATTRIBUTE_PRINTF_4;
++
+ /* Output a diagnostic with "MSGID: " preceding the
+ error string of errno. No location is printed. */
+ extern bool cpp_errno (cpp_reader *, enum cpp_diagnostic_level,
+@@ -1320,42 +1328,95 @@ extern const char * cpp_get_userdef_suff
+
+ /* In charset.c */
+
++/* The result of attempting to decode a run of UTF-8 bytes. */
++
++struct cpp_decoded_char
++{
++ const char *m_start_byte;
++ const char *m_next_byte;
++
++ bool m_valid_ch;
++ cppchar_t m_ch;
++};
++
++/* Information for mapping between code points and display columns.
++
++ This is a tabstop value, along with a callback for getting the
++ widths of characters. Normally this callback is cpp_wcwidth, but we
++ support other schemes for escaping non-ASCII unicode as a series of
++ ASCII chars when printing the user's source code in diagnostic-show-locus.c
++
++ For example, consider:
++ - the Unicode character U+03C0 "GREEK SMALL LETTER PI" (UTF-8: 0xCF 0x80)
++ - the Unicode character U+1F642 "SLIGHTLY SMILING FACE"
++ (UTF-8: 0xF0 0x9F 0x99 0x82)
++ - the byte 0xBF (a stray trailing byte of a UTF-8 character)
++ Normally U+03C0 would occupy one display column, U+1F642
++ would occupy two display columns, and the stray byte would be
++ printed verbatim as one display column.
++
++ However when escaping them as unicode code points as "<U+03C0>"
++ and "<U+1F642>" they occupy 8 and 9 display columns respectively,
++ and when escaping them as bytes as "<CF><80>" and "<F0><9F><99><82>"
++ they occupy 8 and 16 display columns respectively. In both cases
++ the stray byte is escaped to <BF> as 4 display columns. */
++
++struct cpp_char_column_policy
++{
++ cpp_char_column_policy (int tabstop,
++ int (*width_cb) (cppchar_t c))
++ : m_tabstop (tabstop),
++ m_undecoded_byte_width (1),
++ m_width_cb (width_cb)
++ {}
++
++ int m_tabstop;
++ /* Width in display columns of a stray byte that isn't decodable
++ as UTF-8. */
++ int m_undecoded_byte_width;
++ int (*m_width_cb) (cppchar_t c);
++};
++
+ /* A class to manage the state while converting a UTF-8 sequence to cppchar_t
+ and computing the display width one character at a time. */
+ class cpp_display_width_computation {
+ public:
+ cpp_display_width_computation (const char *data, int data_length,
+- int tabstop);
++ const cpp_char_column_policy &policy);
+ const char *next_byte () const { return m_next; }
+ int bytes_processed () const { return m_next - m_begin; }
+ int bytes_left () const { return m_bytes_left; }
+ bool done () const { return !bytes_left (); }
+ int display_cols_processed () const { return m_display_cols; }
+
+- int process_next_codepoint ();
++ int process_next_codepoint (cpp_decoded_char *out);
+ int advance_display_cols (int n);
+
+ private:
+ const char *const m_begin;
+ const char *m_next;
+ size_t m_bytes_left;
+- const int m_tabstop;
++ const cpp_char_column_policy &m_policy;
+ int m_display_cols;
+ };
+
+ /* Convenience functions that are simple use cases for class
+ cpp_display_width_computation. Tab characters will be expanded to spaces
+- as determined by TABSTOP. */
++ as determined by POLICY.m_tabstop, and non-printable-ASCII characters
++ will be escaped as per POLICY. */
++
+ int cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column, int tabstop);
++ int column,
++ const cpp_char_column_policy &policy);
+ inline int cpp_display_width (const char *data, int data_length,
+- int tabstop)
++ const cpp_char_column_policy &policy)
+ {
+ return cpp_byte_column_to_display_column (data, data_length, data_length,
+- tabstop);
++ policy);
+ }
+ int cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col, int tabstop);
++ int display_col,
++ const cpp_char_column_policy &policy);
+ int cpp_wcwidth (cppchar_t c);
+
+ #endif /* ! LIBCPP_CPPLIB_H */
+diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
+--- a/libcpp/include/line-map.h 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/include/line-map.h 2021-12-25 01:30:50.685688757 -0800
+@@ -1732,6 +1732,18 @@ class rich_location
+ const diagnostic_path *get_path () const { return m_path; }
+ void set_path (const diagnostic_path *path) { m_path = path; }
+
++ /* A flag for hinting that the diagnostic involves character encoding
++ issues, and thus that it will be helpful to the user if we show some
++ representation of how the characters in the pertinent source lines
++ are encoded.
++ The default is false (i.e. do not escape).
++ When set to true, non-ASCII bytes in the pertinent source lines will
++ be escaped in a manner controlled by the user-supplied option
++ -fdiagnostics-escape-format=, so that the user can better understand
++ what's going on with the encoding in their source file. */
++ bool escape_on_output_p () const { return m_escape_on_output; }
++ void set_escape_on_output (bool flag) { m_escape_on_output = flag; }
++
+ private:
+ bool reject_impossible_fixit (location_t where);
+ void stop_supporting_fixits ();
+@@ -1758,6 +1770,7 @@ protected:
+ bool m_fixits_cannot_be_auto_applied;
+
+ const diagnostic_path *m_path;
++ bool m_escape_on_output;
+ };
+
+ /* A struct for the result of range_label::get_text: a NUL-terminated buffer
+diff --git a/libcpp/internal.h b/libcpp/internal.h
+--- a/libcpp/internal.h 2020-07-22 23:35:18.712399623 -0700
++++ b/libcpp/internal.h 2021-12-25 01:30:50.685688757 -0800
+@@ -758,6 +758,9 @@ struct _cpp_dir_only_callbacks
+ extern void _cpp_preprocess_dir_only (cpp_reader *,
+ const struct _cpp_dir_only_callbacks *);
+
++/* In errors.c */
++extern location_t cpp_diagnostic_get_current_location (cpp_reader *);
++
+ /* In traditional.c. */
+ extern bool _cpp_scan_out_logical_line (cpp_reader *, cpp_macro *, bool);
+ extern bool _cpp_read_logical_line_trad (cpp_reader *);
+@@ -946,6 +949,26 @@ int linemap_get_expansion_line (class li
+ const char* linemap_get_expansion_filename (class line_maps *,
+ location_t);
+
++/* A subclass of rich_location for emitting a diagnostic
++ at the current location of the reader, but flagging
++ it with set_escape_on_output (true). */
++class encoding_rich_location : public rich_location
++{
++ public:
++ encoding_rich_location (cpp_reader *pfile)
++ : rich_location (pfile->line_table,
++ cpp_diagnostic_get_current_location (pfile))
++ {
++ set_escape_on_output (true);
++ }
++
++ encoding_rich_location (cpp_reader *pfile, location_t loc)
++ : rich_location (pfile->line_table, loc)
++ {
++ set_escape_on_output (true);
++ }
++};
++
+ #ifdef __cplusplus
+ }
+ #endif
+diff --git a/libcpp/lex.c b/libcpp/lex.c
+--- a/libcpp/lex.c 2021-12-24 20:23:45.568762024 -0800
++++ b/libcpp/lex.c 2021-12-25 01:30:50.685688757 -0800
+@@ -1268,7 +1268,11 @@ skip_whitespace (cpp_reader *pfile, cppc
+ while (is_nvspace (c));
+
+ if (saw_NUL)
+- cpp_error (pfile, CPP_DL_WARNING, "null character(s) ignored");
++ {
++ encoding_rich_location rich_loc (pfile);
++ cpp_error_at (pfile, CPP_DL_WARNING, &rich_loc,
++ "null character(s) ignored");
++ }
+
+ buffer->cur--;
+ }
+@@ -1297,6 +1301,28 @@ warn_about_normalization (cpp_reader *pf
+ if (CPP_OPTION (pfile, warn_normalize) < NORMALIZE_STATE_RESULT (s)
+ && !pfile->state.skipping)
+ {
++ location_t loc = token->src_loc;
++
++ /* If possible, create a location range for the token. */
++ if (loc >= RESERVED_LOCATION_COUNT
++ && token->type != CPP_EOF
++ /* There must be no li