* [PATCH] gcc: upgrade 11.2 -> current 12 snapshot
@ 2022-04-07 12:26 Bernhard Rosenkränzer
2022-04-07 12:32 ` [OE-core] " Richard Purdie
0 siblings, 1 reply; 4+ messages in thread
From: Bernhard Rosenkränzer @ 2022-04-07 12:26 UTC (permalink / raw)
To: openembedded-core; +Cc: raj.khem, Bernhard Rosenkränzer
gcc 12 is expected to be released this month or early next month.
Update so we're prepared.
This keeps/ports all patches currently applied to 11.2 that haven't
landed upstream yet.
Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com>
---
.../gcc/{gcc-11.2.inc => gcc-12.0.inc} | 29 +-
...ian_11.2.bb => gcc-cross-canadian_12.0.bb} | 0
meta/recipes-devtools/gcc/gcc-cross.inc | 9 +
.../{gcc-cross_11.2.bb => gcc-cross_12.0.bb} | 0
...-crosssdk_11.2.bb => gcc-crosssdk_12.0.bb} | 0
meta/recipes-devtools/gcc/gcc-runtime.inc | 2 +-
...cc-runtime_11.2.bb => gcc-runtime_12.0.bb} | 0
...itizers_11.2.bb => gcc-sanitizers_12.0.bb} | 0
...{gcc-source_11.2.bb => gcc-source_12.0.bb} | 0
.../gcc/gcc/0001-CVE-2021-35465.patch | 138 -
.../gcc/gcc/0001-CVE-2021-42574.patch | 2282 -----------------
.../gcc/gcc/0001-CVE-2021-46195.patch | 128 -
...0001-gcc-4.3.1-ARCH_FLAGS_FOR_TARGET.patch | 9 +-
.../gcc/gcc/0002-CVE-2021-35465.patch | 39 -
.../gcc/gcc/0002-CVE-2021-42574.patch | 1765 -------------
.../0002-gcc-poison-system-directories.patch | 17 +-
.../gcc/gcc/0003-CVE-2021-35465.patch | 103 -
.../gcc/gcc/0003-CVE-2021-42574.patch | 142 -
.../gcc/gcc/0004-CVE-2021-35465.patch | 304 ---
.../gcc/gcc/0004-CVE-2021-42574.patch | 573 -----
.../gcc/gcc/0009-cpp-honor-sysroot.patch | 9 +-
...gcc-Fix-argument-list-too-long-error.patch | 38 -
.../gcc/gcc/0018-export-CPP.patch | 199 --
| 8 +-
...le-sysroot-support-for-nativesdk-gcc.patch | 41 +-
...sroot-gcc-version-specific-dirs-with.patch | 9 +-
...027-nios2-Define-MUSL_DYNAMIC_LINKER.patch | 31 -
...using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch | 26 -
.../0030-sync-gcc-stddef.h-with-musl.patch | 88 -
...as-for-__cpu_indicator_init-instead-.patch | 13 +-
...s-Do-not-use-__LINE__-for-maintainin.patch | 71 +-
...prefix-maps-before-checksumming-DIEs.patch | 95 -
.../gcc/0042-Fix-thread-stack-size-init.patch | 23 -
.../gcc/{gcc_11.2.bb => gcc_12.0.bb} | 0
...initial_11.2.bb => libgcc-initial_12.0.bb} | 0
.../gcc/{libgcc_11.2.bb => libgcc_12.0.bb} | 0
...ibgfortran_11.2.bb => libgfortran_12.0.bb} | 0
37 files changed, 110 insertions(+), 6081 deletions(-)
rename meta/recipes-devtools/gcc/{gcc-11.2.inc => gcc-12.0.inc} (77%)
rename meta/recipes-devtools/gcc/{gcc-cross-canadian_11.2.bb => gcc-cross-canadian_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{gcc-cross_11.2.bb => gcc-cross_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{gcc-crosssdk_11.2.bb => gcc-crosssdk_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{gcc-runtime_11.2.bb => gcc-runtime_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{gcc-sanitizers_11.2.bb => gcc-sanitizers_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{gcc-source_11.2.bb => gcc-source_12.0.bb} (100%)
delete mode 100644 meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0001-CVE-2021-46195.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0002-CVE-2021-35465.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0003-CVE-2021-35465.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0004-CVE-2021-35465.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0018-export-CPP.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0027-nios2-Define-MUSL_DYNAMIC_LINKER.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0029-Link-libgcc-using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0030-sync-gcc-stddef.h-with-musl.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0041-apply-debug-prefix-maps-before-checksumming-DIEs.patch
delete mode 100644 meta/recipes-devtools/gcc/gcc/0042-Fix-thread-stack-size-init.patch
rename meta/recipes-devtools/gcc/{gcc_11.2.bb => gcc_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{libgcc-initial_11.2.bb => libgcc-initial_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{libgcc_11.2.bb => libgcc_12.0.bb} (100%)
rename meta/recipes-devtools/gcc/{libgfortran_11.2.bb => libgfortran_12.0.bb} (100%)
diff --git a/meta/recipes-devtools/gcc/gcc-11.2.inc b/meta/recipes-devtools/gcc/gcc-12.0.inc
similarity index 77%
rename from meta/recipes-devtools/gcc/gcc-11.2.inc
rename to meta/recipes-devtools/gcc/gcc-12.0.inc
index 68e0d203fc..3b7adf5cb7 100644
--- a/meta/recipes-devtools/gcc/gcc-11.2.inc
+++ b/meta/recipes-devtools/gcc/gcc-12.0.inc
@@ -2,11 +2,14 @@ require gcc-common.inc
# Third digit in PV should be incremented after a minor release
-PV = "11.2.0"
+PV = "12.0.1"
# BINV should be incremented to a revision after a minor gcc release
-BINV = "11.2.0"
+BINV = "12.0.1"
+
+MAJOR = "12"
+SNAPSHOT = "20220313"
FILESEXTRAPATHS =. "${FILE_DIRNAME}/gcc:${FILE_DIRNAME}/gcc/backport:"
@@ -26,7 +29,7 @@ LIC_FILES_CHKSUM = "\
#RELEASE ?= "5b2ac9b40c325e9209c0bd55955db84aad4a0cc5"
#BASEURI ?= "https://github.com/gcc-mirror/gcc/archive/${RELEASE}.zip;downloadfilename=gcc-${PV}-${RELEASE}.zip"
-BASEURI ?= "${GNU_MIRROR}/gcc/gcc-${PV}/gcc-${PV}.tar.xz \
+BASEURI ?= "https://mirror.koddos.net/gcc/snapshots/${MAJOR}-${SNAPSHOT}/gcc-${MAJOR}-${SNAPSHOT}.tar.xz \
"
SRC_URI = "\
${BASEURI} \
@@ -36,43 +39,27 @@ SRC_URI = "\
file://0007-Use-the-defaults.h-in-B-instead-of-S-and-t-oe-in-B.patch \
file://0009-cpp-honor-sysroot.patch \
file://0011-Define-GLIBC_DYNAMIC_LINKER-and-UCLIBC_DYNAMIC_LINKE.patch \
- file://0012-gcc-Fix-argument-list-too-long-error.patch \
file://0014-libtool.patch \
file://0015-gcc-armv4-pass-fix-v4bx-to-linker-to-support-EABI.patch \
file://0016-Use-the-multilib-config-files-from-B-instead-of-usin.patch \
file://0017-Avoid-using-libdir-from-.la-which-usually-points-to-.patch \
- file://0018-export-CPP.patch \
file://0019-Ensure-target-gcc-headers-can-be-included.patch \
file://0020-Don-t-search-host-directory-during-relink-if-inst_pr.patch \
file://0023-libcc1-fix-libcc1-s-install-path-and-rpath.patch \
file://0024-handle-sysroot-support-for-nativesdk-gcc.patch \
file://0025-Search-target-sysroot-gcc-version-specific-dirs-with.patch \
- file://0027-nios2-Define-MUSL_DYNAMIC_LINKER.patch \
file://0028-Add-ssp_nonshared-to-link-commandline-for-musl-targe.patch \
- file://0029-Link-libgcc-using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch \
- file://0030-sync-gcc-stddef.h-with-musl.patch \
file://0033-Re-introduce-spe-commandline-options.patch \
file://0034-libgcc_s-Use-alias-for-__cpu_indicator_init-instead-.patch \
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://0041-apply-debug-prefix-maps-before-checksumming-DIEs.patch \
file://0006-If-CXXFLAGS-contains-something-unsupported-by-the-bu.patch \
file://0001-Fix-install-path-of-linux64.h.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://0001-CVE-2021-46195.patch \
- file://0042-Fix-thread-stack-size-init.patch \
"
-SRC_URI[sha256sum] = "d08edc536b54c372a1010ff6619dd274c0f1603aa49212ba20f7aa2cda36fa8b"
+SRC_URI[sha256sum] = "979d8cbe9b2ed2ab4434f52097754e004a207cf6541aea3e167c5d0f74957633"
-S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${PV}"
+S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${MAJOR}-${SNAPSHOT}"
# For dev release snapshotting
#S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${RELEASE}"
diff --git a/meta/recipes-devtools/gcc/gcc-cross-canadian_11.2.bb b/meta/recipes-devtools/gcc/gcc-cross-canadian_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-cross-canadian_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-cross-canadian_12.0.bb
diff --git a/meta/recipes-devtools/gcc/gcc-cross.inc b/meta/recipes-devtools/gcc/gcc-cross.inc
index 3ffa1f0c46..0e8119384b 100644
--- a/meta/recipes-devtools/gcc/gcc-cross.inc
+++ b/meta/recipes-devtools/gcc/gcc-cross.inc
@@ -47,6 +47,15 @@ ARCH_FLAGS_FOR_TARGET += "-isystem${STAGING_DIR_TARGET}${target_includedir}"
do_configure:prepend () {
install -d ${RECIPE_SYSROOT}${target_includedir}
touch ${RECIPE_SYSROOT}${target_includedir}/limits.h
+
+ if ! echo ${@d.getVar("TARGET_OS")} | grep -qi linux; then
+ # Building Zephyr with DWARF-5 is problematic because
+ # its kernel tests use pyelftools, which has incomplete
+ # DWARF-5 support (even after applying preliminary
+ # support patches). Use DWARF-4 on Zephyr and FreeRTOS
+ # for the time being.
+ sed -i -e 's,Var(dwarf_version) Init(5),Var(dwarf_version) Init(4),' ${S}/gcc/common.opt
+ fi
}
do_compile () {
diff --git a/meta/recipes-devtools/gcc/gcc-cross_11.2.bb b/meta/recipes-devtools/gcc/gcc-cross_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-cross_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-cross_12.0.bb
diff --git a/meta/recipes-devtools/gcc/gcc-crosssdk_11.2.bb b/meta/recipes-devtools/gcc/gcc-crosssdk_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-crosssdk_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-crosssdk_12.0.bb
diff --git a/meta/recipes-devtools/gcc/gcc-runtime.inc b/meta/recipes-devtools/gcc/gcc-runtime.inc
index e9f2cf16e8..c39a0caf8a 100644
--- a/meta/recipes-devtools/gcc/gcc-runtime.inc
+++ b/meta/recipes-devtools/gcc/gcc-runtime.inc
@@ -2,7 +2,7 @@ require gcc-configure-common.inc
SUMMARY = "Runtime libraries from GCC"
-# Over-ride the LICENSE set by gcc-${PV}.inc to remove "& GPL-3.0-only"
+# Over-ride the LICENSE set by gcc-${PV}.inc to remove "& GPLv3"
# All gcc-runtime packages are now covered by the runtime exception.
LICENSE = "GPL-3.0-with-GCC-exception"
diff --git a/meta/recipes-devtools/gcc/gcc-runtime_11.2.bb b/meta/recipes-devtools/gcc/gcc-runtime_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-runtime_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-runtime_12.0.bb
diff --git a/meta/recipes-devtools/gcc/gcc-sanitizers_11.2.bb b/meta/recipes-devtools/gcc/gcc-sanitizers_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-sanitizers_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-sanitizers_12.0.bb
diff --git a/meta/recipes-devtools/gcc/gcc-source_11.2.bb b/meta/recipes-devtools/gcc/gcc-source_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc-source_11.2.bb
rename to meta/recipes-devtools/gcc/gcc-source_12.0.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
deleted file mode 100644
index e4aee10e37..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch
+++ /dev/null
@@ -1,138 +0,0 @@
-From 3929bca9ca95de9d35e82ae8828b188029e3eb70 Mon Sep 17 00:00:00 2001
-From: Richard Earnshaw <rearnsha@arm.com>
-Date: Fri, 11 Jun 2021 16:02:05 +0100
-Subject: [PATCH] arm: Add command-line option for enabling CVE-2021-35465
- mitigation [PR102035]
-
-Add a new option, -mfix-cmse-cve-2021-35465 and document it. Enable it
-automatically for cortex-m33, cortex-m35p and cortex-m55.
-
-gcc:
- PR target/102035
- * config/arm/arm.opt (mfix-cmse-cve-2021-35465): New option.
- * doc/invoke.texi (Arm Options): Document it.
- * config/arm/arm-cpus.in (quirk_vlldm): New feature bit.
- (ALL_QUIRKS): Add quirk_vlldm.
- (cortex-m33): Add quirk_vlldm.
- (cortex-m35p, cortex-m55): Likewise.
- * config/arm/arm.c (arm_option_override): Enable fix_vlldm if
- targetting an affected CPU and not explicitly controlled on
- the command line.
-
-CVE: CVE-2021-35465
-Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=3929bca9ca95de9d35e82ae8828b188029e3eb70]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- gcc/config/arm/arm-cpus.in | 9 +++++++--
- gcc/config/arm/arm.c | 9 +++++++++
- gcc/config/arm/arm.opt | 4 ++++
- gcc/doc/invoke.texi | 9 +++++++++
- 4 files changed, 29 insertions(+), 2 deletions(-)
-
-diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
---- a/gcc/config/arm/arm.c 2021-11-15 02:13:11.100579812 -0800
-+++ b/gcc/config/arm/arm.c 2021-11-15 02:17:36.988237692 -0800
-@@ -3610,6 +3610,15 @@ arm_option_override (void)
- fix_cm3_ldrd = 0;
- }
-
-+ /* Enable fix_vlldm by default if required. */
-+ if (fix_vlldm == 2)
-+ {
-+ if (bitmap_bit_p (arm_active_target.isa, isa_bit_quirk_vlldm))
-+ fix_vlldm = 1;
-+ else
-+ fix_vlldm = 0;
-+ }
-+
- /* Hot/Cold partitioning is not currently supported, since we can't
- handle literal pool placement in that case. */
- if (flag_reorder_blocks_and_partition)
-diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
---- a/gcc/config/arm/arm-cpus.in 2021-11-15 02:13:11.104579747 -0800
-+++ b/gcc/config/arm/arm-cpus.in 2021-11-15 02:17:36.984237757 -0800
-@@ -186,6 +186,9 @@ define feature quirk_armv6kz
- # Cortex-M3 LDRD quirk.
- define feature quirk_cm3_ldrd
-
-+# v8-m/v8.1-m VLLDM errata.
-+define feature quirk_vlldm
-+
- # Don't use .cpu assembly directive
- define feature quirk_no_asmcpu
-
-@@ -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.
--define fgroup ALL_QUIRKS quirk_no_volatile_ce quirk_armv6kz quirk_cm3_ldrd xscale quirk_no_asmcpu
-+define fgroup ALL_QUIRKS quirk_no_volatile_ce quirk_armv6kz quirk_cm3_ldrd quirk_vlldm xscale quirk_no_asmcpu
-
- define fgroup IGNORE_FOR_MULTILIB cdecp0 cdecp1 cdecp2 cdecp3 cdecp4 cdecp5 cdecp6 cdecp7
-
-@@ -1570,6 +1573,7 @@ begin cpu cortex-m33
- architecture armv8-m.main+dsp+fp
- option nofp remove ALL_FP
- option nodsp remove armv7em
-+ isa quirk_vlldm
- costs v7m
- end cpu cortex-m33
-
-@@ -1579,6 +1583,7 @@ begin cpu cortex-m35p
- architecture armv8-m.main+dsp+fp
- option nofp remove ALL_FP
- option nodsp remove armv7em
-+ isa quirk_vlldm
- costs v7m
- end cpu cortex-m35p
-
-@@ -1590,7 +1595,7 @@ 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
- vendor 41
- end cpu cortex-m55
-diff --git a/gcc/config/arm/arm.opt b/gcc/config/arm/arm.opt
---- a/gcc/config/arm/arm.opt 2021-11-15 02:13:11.104579747 -0800
-+++ b/gcc/config/arm/arm.opt 2021-11-15 02:17:36.988237692 -0800
-@@ -268,6 +268,10 @@ Target Var(fix_cm3_ldrd) Init(2)
- Avoid overlapping destination and address registers on LDRD instructions
- that may trigger Cortex-M3 errata.
-
-+mfix-cmse-cve-2021-35465
-+Target Var(fix_vlldm) Init(2)
-+Mitigate issues with VLLDM on some M-profile devices (CVE-2021-35465).
-+
- munaligned-access
- Target Var(unaligned_access) Init(2) Save
- Enable unaligned word and halfword accesses to packed data.
-diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
---- a/gcc/doc/invoke.texi 2021-11-15 02:13:11.112579616 -0800
-+++ b/gcc/doc/invoke.texi 2021-11-15 02:17:36.996237562 -0800
-@@ -804,6 +804,7 @@ Objective-C and Objective-C++ Dialects}.
- -mverbose-cost-dump @gol
- -mpure-code @gol
- -mcmse @gol
-+-mfix-cmse-cve-2021-35465 @gol
- -mfdpic}
-
- @emph{AVR Options}
-@@ -20487,6 +20488,14 @@ Generate secure code as per the "ARMv8-M
- Development Tools Engineering Specification", which can be found on
- @url{https://developer.arm.com/documentation/ecm0359818/latest/}.
-
-+@item -mfix-cmse-cve-2021-35465
-+@opindex mfix-cmse-cve-2021-35465
-+Mitigate against a potential security issue with the @code{VLLDM} instruction
-+in some M-profile devices when using CMSE (CVE-2021-365465). This option is
-+enabled by default when the option @option{-mcpu=} is used with
-+@code{cortex-m33}, @code{cortex-m35p} or @code{cortex-m55}. The option
-+@option{-mno-fix-cmse-cve-2021-35465} can be used to disable the mitigation.
-+
- @item -mfdpic
- @itemx -mno-fdpic
- @opindex mfdpic
diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch
deleted file mode 100644
index 4d680ccc8f..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch
+++ /dev/null
@@ -1,2282 +0,0 @@
-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 2021-07-27 23:55:06.980283060 -0700
-+++ b/gcc/c-family/c-lex.c 2021-12-14 01:16:01.541943272 -0800
-@@ -603,7 +603,11 @@ 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 2021-12-13 22:08:44.939137107 -0800
-+++ b/gcc/common.opt 2021-12-14 01:16:01.541943272 -0800
-@@ -1348,6 +1348,10 @@ 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
-@@ -1362,6 +1366,15 @@ 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 2021-07-27 23:55:07.232286576 -0700
-+++ b/gcc/diagnostic.c 2021-12-14 01:16:01.545943202 -0800
-@@ -230,6 +230,7 @@ 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;
-@@ -382,7 +383,10 @@ convert_column_unit (enum diagnostics_co
- gcc_unreachable ();
-
- case DIAGNOSTICS_COLUMN_UNIT_DISPLAY:
-- return location_compute_display_column (s, tabstop);
-+ {
-+ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
-+ return location_compute_display_column (s, policy);
-+ }
-
- case DIAGNOSTICS_COLUMN_UNIT_BYTE:
- return s.column;
-@@ -2275,8 +2279,8 @@ 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 2021-07-27 23:55:07.232286576 -0700
-+++ b/gcc/diagnostic-format-json.cc 2021-12-14 01:16:01.541943272 -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 2021-07-27 23:55:07.236286632 -0700
-+++ b/gcc/diagnostic.h 2021-12-14 01:16:01.545943202 -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
-@@ -320,6 +334,10 @@ 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 2021-07-27 23:55:07.232286576 -0700
-+++ b/gcc/diagnostic-show-locus.c 2021-12-14 01:16:01.545943202 -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);
- }
-
-@@ -959,6 +1012,164 @@ 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.
-@@ -975,8 +1186,10 @@ 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),
-@@ -986,7 +1199,8 @@ 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++)
- {
-@@ -1072,10 +1286,13 @@ 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
-@@ -1409,7 +1626,7 @@ 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)
- {
-@@ -1488,7 +1705,7 @@ 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
-@@ -1536,7 +1753,8 @@ 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
-@@ -1545,15 +1763,6 @@ 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. */
-@@ -1565,7 +1774,8 @@ 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;
-@@ -1664,14 +1874,14 @@ 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. */
-@@ -1731,7 +1941,7 @@ 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));
- }
- }
-
-@@ -2011,7 +2221,7 @@ 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 ());
-@@ -2022,13 +2232,11 @@ 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
- {
-@@ -2041,12 +2249,13 @@ 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 ())
- {
-@@ -2056,8 +2265,7 @@ 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));
- }
-@@ -2075,13 +2283,13 @@ 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 ();
-@@ -2099,7 +2307,7 @@ 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)
-@@ -2127,7 +2335,7 @@ 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;
- };
-
-@@ -2163,15 +2371,16 @@ 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;
-@@ -2217,10 +2426,10 @@ 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 ())
-@@ -2289,7 +2498,7 @@ 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.
-@@ -2303,7 +2512,7 @@ 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];
-@@ -2646,6 +2855,59 @@ 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,
-@@ -2715,10 +2977,10 @@ 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));
-
-@@ -2866,12 +3128,13 @@ 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. */
-@@ -4003,6 +4266,43 @@ 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
-@@ -4057,9 +4357,9 @@ 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 ();
-@@ -4445,30 +4745,31 @@ 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);
-@@ -4660,30 +4961,31 @@ 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);
-@@ -4877,15 +5179,16 @@ 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);
-@@ -5152,10 +5455,11 @@ 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_);
-@@ -5198,6 +5502,114 @@ 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"). */
-@@ -5254,6 +5666,8 @@ 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);
-
-@@ -5274,6 +5688,8 @@ 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 2021-12-13 23:23:05.764437151 -0800
-+++ b/gcc/doc/invoke.texi 2021-12-14 01:16:01.553943061 -0800
-@@ -312,7 +312,8 @@ 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}.
-@@ -5083,6 +5084,38 @@ 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.
-@@ -5150,9 +5183,11 @@ 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{}
-@@ -5239,6 +5274,7 @@ of the expression, which have labels. I
- "label": "T @{aka struct t@}"
- @}
- ],
-+ "escape-source": false,
- "message": "invalid operands to binary + @dots{}"
- @}
- @end smallexample
-@@ -5292,6 +5328,7 @@ might be printed in JSON form as:
- @}
- @}
- ],
-+ "escape-source": false,
- "message": "\u2018struct s\u2019 has no member named @dots{}"
- @}
- @end smallexample
-@@ -5349,6 +5386,10 @@ 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 2021-07-27 23:55:07.328287915 -0700
-+++ b/gcc/input.c 2021-12-14 01:16:01.553943061 -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
-@@ -3611,43 +3612,50 @@ 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,
-@@ -3660,13 +3668,13 @@ 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,
-@@ -3680,25 +3688,25 @@ 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 2021-07-27 23:55:07.328287915 -0700
-+++ b/gcc/input.h 2021-12-14 01:16:01.553943061 -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 2021-07-27 23:55:07.364288417 -0700
-+++ b/gcc/opts.c 2021-12-14 01:16:01.553943061 -0800
-@@ -2573,6 +2573,10 @@ 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 2021-07-27 23:55:07.500290315 -0700
-+++ b/gcc/selftest.c 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.500290315 -0700
-+++ b/gcc/selftest.h 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.596291654 -0700
-+++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.596291654 -0700
-+++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.596291654 -0700
-+++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.596291654 -0700
-+++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:07.596291654 -0700
-+++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-14 01:16:01.557942991 -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 2021-12-14 01:16:01.557942991 -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 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:08.472303878 -0700
-+++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:08.472303878 -0700
-+++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:08.472303878 -0700
-+++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-14 01:16:01.557942991 -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 2021-07-27 23:55:08.712307227 -0700
-+++ b/libcpp/charset.c 2021-12-14 01:16:01.557942991 -0800
-@@ -1552,12 +1552,14 @@ 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);
- }
- }
-
-@@ -2280,14 +2282,16 @@ 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);
- }
-
-
-@@ -2299,19 +2303,28 @@ 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)
-@@ -2321,14 +2334,24 @@ 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;
- }
-@@ -2344,7 +2367,7 @@ 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;
- }
-
-@@ -2352,29 +2375,33 @@ 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 2021-07-27 23:55:08.712307227 -0700
-+++ b/libcpp/errors.c 2021-12-14 01:16:01.557942991 -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 2021-12-13 23:23:05.768437079 -0800
-+++ b/libcpp/include/cpplib.h 2021-12-14 01:20:16.189507386 -0800
-@@ -1275,6 +1275,14 @@ 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,
-@@ -1435,42 +1443,95 @@ 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 2021-07-27 23:55:08.716307283 -0700
-+++ b/libcpp/include/line-map.h 2021-12-14 01:16:01.557942991 -0800
-@@ -1781,6 +1781,18 @@ 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 ();
-@@ -1807,6 +1819,7 @@ 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 2021-12-13 23:23:05.768437079 -0800
-+++ b/libcpp/internal.h 2021-12-14 01:16:01.557942991 -0800
-@@ -776,6 +776,9 @@ extern void _cpp_do_file_change (cpp_rea
- extern void _cpp_pop_buffer (cpp_reader *);
- extern char *_cpp_bracket_include (cpp_reader *);
-
-+/* 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 *);
-@@ -942,6 +945,26 @@ 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 2021-12-14 01:14:48.435225968 -0800
-+++ b/libcpp/lex.c 2021-12-14 01:24:37.220995816 -0800
-@@ -1774,7 +1774,11 @@ 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--;
- }
-@@ -1803,6 +1807,28 @@ 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 line notes to process. */
-+ && (!(pfile->buffer->cur
-+ >= pfile->buffer->notes[pfile->buffer->cur_note].pos
-+ && !pfile->overlaid_buffer)))
-+ {
-+ source_range tok_range;
-+ tok_range.m_start = loc;
-+ tok_range.m_finish
-+ = linemap_position_for_column (pfile->line_table,
-+ CPP_BUF_COLUMN (pfile->buffer,
-+ pfile->buffer->cur));
-+ loc = COMBINE_LOCATION_DATA (pfile->line_table,
-+ loc, tok_range, NULL);
-+ }
-+
-+ encoding_rich_location rich_loc (pfile, loc);
-+
- /* Make sure that the token is printed using UCNs, even
- if we'd otherwise happily print UTF-8. */
- unsigned char *buf = XNEWVEC (unsigned char, cpp_token_len (token));
-@@ -1810,11 +1836,11 @@ warn_about_normalization (cpp_reader *pf
-
- sz = cpp_spell_token (pfile, token, buf, false) - buf;
- if (NORMALIZE_STATE_RESULT (s) == normalized_C)
-- cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
-- "`%.*s' is not in NFKC", (int) sz, buf);
-+ cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
-+ "`%.*s' is not in NFKC", (int) sz, buf);
- else
-- cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
-- "`%.*s' is not in NFC", (int) sz, buf);
-+ cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
-+ "`%.*s' is not in NFC", (int) sz, buf);
- free (buf);
- }
- }
-diff --git a/libcpp/line-map.c b/libcpp/line-map.c
---- a/libcpp/line-map.c 2021-07-27 23:55:08.716307283 -0700
-+++ b/libcpp/line-map.c 2021-12-14 01:16:01.561942921 -0800
-@@ -2086,7 +2086,8 @@ rich_location::rich_location (line_maps
- m_fixit_hints (),
- m_seen_impossible_fixit (false),
- m_fixits_cannot_be_auto_applied (false),
-- m_path (NULL)
-+ m_path (NULL),
-+ m_escape_on_output (false)
- {
- add_range (loc, SHOW_RANGE_WITH_CARET, label);
- }
diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-46195.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-46195.patch
deleted file mode 100644
index 7b3651c73e..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-46195.patch
+++ /dev/null
@@ -1,128 +0,0 @@
-From f10bec5ffa487ad3033ed5f38cfd0fc7d696deab Mon Sep 17 00:00:00 2001
-From: Nick Clifton <nickc@redhat.com>
-Date: Mon, 31 Jan 2022 14:28:42 +0000
-Subject: [PATCH] libiberty: Fix infinite recursion in rust demangler.
-
-libiberty/
- PR demangler/98886
- PR demangler/99935
- * rust-demangle.c (struct rust_demangler): Add a recursion
- counter.
- (demangle_path): Increment/decrement the recursion counter upon
- entry and exit. Fail if the counter exceeds a fixed limit.
- (demangle_type): Likewise.
- (rust_demangle_callback): Initialise the recursion counter,
- disabling if requested by the option flags.
-
-CVE: CVE-2021-46195
-Upstream-Status: Backport
-[https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=f10bec5ffa487ad3033ed5f38cfd0fc7d696deab]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
----
- libiberty/rust-demangle.c | 47 ++++++++++++++++++++++++++++++++++-----
- 1 file changed, 41 insertions(+), 6 deletions(-)
-
-diff --git a/libiberty/rust-demangle.c b/libiberty/rust-demangle.c
-index 18c760491bd..3b24d63892a 100644
---- a/libiberty/rust-demangle.c
-+++ b/libiberty/rust-demangle.c
-@@ -74,6 +74,12 @@ struct rust_demangler
- /* Rust mangling version, with legacy mangling being -1. */
- int version;
-
-+ /* Recursion depth. */
-+ unsigned int recursion;
-+ /* Maximum number of times demangle_path may be called recursively. */
-+#define RUST_MAX_RECURSION_COUNT 1024
-+#define RUST_NO_RECURSION_LIMIT ((unsigned int) -1)
-+
- uint64_t bound_lifetime_depth;
- };
-
-@@ -671,6 +677,15 @@ demangle_path (struct rust_demangler *rdm, int in_value)
- if (rdm->errored)
- return;
-
-+ if (rdm->recursion != RUST_NO_RECURSION_LIMIT)
-+ {
-+ ++ rdm->recursion;
-+ if (rdm->recursion > RUST_MAX_RECURSION_COUNT)
-+ /* FIXME: There ought to be a way to report
-+ that the recursion limit has been reached. */
-+ goto fail_return;
-+ }
-+
- switch (tag = next (rdm))
- {
- case 'C':
-@@ -688,10 +703,7 @@ demangle_path (struct rust_demangler *rdm, int in_value)
- case 'N':
- ns = next (rdm);
- if (!ISLOWER (ns) && !ISUPPER (ns))
-- {
-- rdm->errored = 1;
-- return;
-- }
-+ goto fail_return;
-
- demangle_path (rdm, in_value);
-
-@@ -776,9 +788,15 @@ demangle_path (struct rust_demangler *rdm, int in_value)
- }
- break;
- default:
-- rdm->errored = 1;
-- return;
-+ goto fail_return;
- }
-+ goto pass_return;
-+
-+ fail_return:
-+ rdm->errored = 1;
-+ pass_return:
-+ if (rdm->recursion != RUST_NO_RECURSION_LIMIT)
-+ -- rdm->recursion;
- }
-
- static void
-@@ -870,6 +888,19 @@ demangle_type (struct rust_demangler *rdm)
- return;
- }
-
-+ if (rdm->recursion != RUST_NO_RECURSION_LIMIT)
-+ {
-+ ++ rdm->recursion;
-+ if (rdm->recursion > RUST_MAX_RECURSION_COUNT)
-+ /* FIXME: There ought to be a way to report
-+ that the recursion limit has been reached. */
-+ {
-+ rdm->errored = 1;
-+ -- rdm->recursion;
-+ return;
-+ }
-+ }
-+
- switch (tag)
- {
- case 'R':
-@@ -1030,6 +1061,9 @@ demangle_type (struct rust_demangler *rdm)
- rdm->next--;
- demangle_path (rdm, 0);
- }
-+
-+ if (rdm->recursion != RUST_NO_RECURSION_LIMIT)
-+ -- rdm->recursion;
- }
-
- /* A trait in a trait object may have some "existential projections"
-@@ -1320,6 +1354,7 @@ rust_demangle_callback (const char *mangled, int options,
- rdm.skipping_printing = 0;
- rdm.verbose = (options & DMGL_VERBOSE) != 0;
- rdm.version = 0;
-+ rdm.recursion = (options & DMGL_NO_RECURSE_LIMIT) ? RUST_NO_RECURSION_LIMIT : 0;
- rdm.bound_lifetime_depth = 0;
-
- /* Rust symbols always start with _R (v0) or _ZN (legacy). */
---
-2.27.0
-
diff --git a/meta/recipes-devtools/gcc/gcc/0001-gcc-4.3.1-ARCH_FLAGS_FOR_TARGET.patch b/meta/recipes-devtools/gcc/gcc/0001-gcc-4.3.1-ARCH_FLAGS_FOR_TARGET.patch
index 0a108ee51b..3069161bef 100644
--- a/meta/recipes-devtools/gcc/gcc/0001-gcc-4.3.1-ARCH_FLAGS_FOR_TARGET.patch
+++ b/meta/recipes-devtools/gcc/gcc/0001-gcc-4.3.1-ARCH_FLAGS_FOR_TARGET.patch
@@ -4,6 +4,7 @@ Date: Fri, 29 Mar 2013 08:37:11 +0400
Subject: [PATCH] gcc-4.3.1: ARCH_FLAGS_FOR_TARGET
Signed-off-by: Khem Raj <raj.khem@gmail.com>
+Signed-off-by: Bernhard Rosenkraenzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
Upstream-Status: Inappropriate [embedded specific]
---
@@ -12,10 +13,10 @@ Upstream-Status: Inappropriate [embedded specific]
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/configure b/configure
-index 504f6410274..bcebad264ec 100755
+index f7e0fa46c9c..ce1f596e4ca 100755
--- a/configure
+++ b/configure
-@@ -9728,7 +9728,7 @@ fi
+@@ -10177,7 +10177,7 @@ fi
# for target_alias and gcc doesn't manage it consistently.
target_configargs="--cache-file=./config.cache ${target_configargs}"
@@ -25,10 +26,10 @@ index 504f6410274..bcebad264ec 100755
*" newlib "*)
case " $target_configargs " in
diff --git a/configure.ac b/configure.ac
-index 088e735c5db..1289fe08760 100644
+index 434b1a267a4..a139a3c80ad 100644
--- a/configure.ac
+++ b/configure.ac
-@@ -3240,7 +3240,7 @@ fi
+@@ -3348,7 +3348,7 @@ fi
# for target_alias and gcc doesn't manage it consistently.
target_configargs="--cache-file=./config.cache ${target_configargs}"
diff --git a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-35465.patch b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-35465.patch
deleted file mode 100644
index e09818fecf..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-35465.patch
+++ /dev/null
@@ -1,39 +0,0 @@
-From 574e7950bd6b34e9e2cacce18c802b45505d1d0a Mon Sep 17 00:00:00 2001
-From: Richard Earnshaw <rearnsha@arm.com>
-Date: Fri, 18 Jun 2021 17:16:25 +0100
-Subject: [PATCH] arm: add erratum mitigation to __gnu_cmse_nonsecure_call
- [PR102035]
-
-Add the recommended erratum mitigation sequence to
-__gnu_cmse_nonsecure_call for use on Armv8-m.main devices. Since this
-is in the library code we cannot know in advance whether the core we
-are running on will be affected by this, so always enable it.
-
-libgcc:
- PR target/102035
- * config/arm/cmse_nonsecure_call.S (__gnu_cmse_nonsecure_call):
- Add vlldm erratum work-around.
-
-CVE: CVE-2021-35465
-Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=574e7950bd6b34e9e2cacce18c802b45505d1d0a]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- libgcc/config/arm/cmse_nonsecure_call.S | 5 +++++
- 1 file changed, 5 insertions(+)
-
-diff --git a/libgcc/config/arm/cmse_nonsecure_call.S b/libgcc/config/arm/cmse_nonsecure_call.S
---- a/libgcc/config/arm/cmse_nonsecure_call.S
-+++ b/libgcc/config/arm/cmse_nonsecure_call.S
-@@ -102,6 +102,11 @@ blxns r4
- #ifdef __ARM_PCS_VFP
- vpop.f64 {d8-d15}
- #else
-+/* VLLDM erratum mitigation sequence. */
-+mrs r5, control
-+tst r5, #8 /* CONTROL_S.SFPA */
-+it ne
-+.inst.w 0xeeb00a40 /* vmovne s0, s0 */
- vlldm sp /* Lazy restore of d0-d16 and FPSCR. */
- add sp, sp, #0x88 /* Free space used to save floating point registers. */
- #endif /* __ARM_PCS_VFP */
diff --git a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch
deleted file mode 100644
index 9bad81d4d0..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch
+++ /dev/null
@@ -1,1765 +0,0 @@
-From 51c500269bf53749b107807d84271385fad35628 Mon Sep 17 00:00:00 2001
-From: Marek Polacek <polacek@redhat.com>
-Date: Wed, 6 Oct 2021 14:33:59 -0400
-Subject: [PATCH] libcpp: Implement -Wbidi-chars for CVE-2021-42574 [PR103026]
-
-From a link below:
-"An issue was discovered in the Bidirectional Algorithm in the Unicode
-Specification through 14.0. It permits the visual reordering of
-characters via control sequences, which can be used to craft source code
-that renders different logic than the logical ordering of tokens
-ingested by compilers and interpreters. Adversaries can leverage this to
-encode source code for compilers accepting Unicode such that targeted
-vulnerabilities are introduced invisibly to human reviewers."
-
-More info:
-https://nvd.nist.gov/vuln/detail/CVE-2021-42574
-https://trojansource.codes/
-
-This is not a compiler bug. However, to mitigate the problem, this patch
-implements -Wbidi-chars=[none|unpaired|any] to warn about possibly
-misleading Unicode bidirectional control characters the preprocessor may
-encounter.
-
-The default is =unpaired, which warns about improperly terminated
-bidirectional control characters; e.g. a LRE without its corresponding PDF.
-The level =any warns about any use of bidirectional control characters.
-
-This patch handles both UCNs and UTF-8 characters. UCNs designating
-bidi characters in identifiers are accepted since r204886. Then r217144
-enabled -fextended-identifiers by default. Extended characters in C/C++
-identifiers have been accepted since r275979. However, this patch still
-warns about mixing UTF-8 and UCN bidi characters; there seems to be no
-good reason to allow mixing them.
-
-We warn in different contexts: comments (both C and C++-style), string
-literals, character constants, and identifiers. Expectedly, UCNs are ignored
-in comments and raw string literals. The bidirectional control characters
-can nest so this patch handles that as well.
-
-I have not included nor tested this at all with Fortran (which also has
-string literals and line comments).
-
-Dave M. posted patches improving diagnostic involving Unicode characters.
-This patch does not make use of this new infrastructure yet.
-
- PR preprocessor/103026
-
-gcc/c-family/ChangeLog:
-
- * c.opt (Wbidi-chars, Wbidi-chars=): New option.
-
-gcc/ChangeLog:
-
- * doc/invoke.texi: Document -Wbidi-chars.
-
-libcpp/ChangeLog:
-
- * include/cpplib.h (enum cpp_bidirectional_level): New.
- (struct cpp_options): Add cpp_warn_bidirectional.
- (enum cpp_warning_reason): Add CPP_W_BIDIRECTIONAL.
- * internal.h (struct cpp_reader): Add warn_bidi_p member
- function.
- * init.c (cpp_create_reader): Set cpp_warn_bidirectional.
- * lex.c (bidi): New namespace.
- (get_bidi_utf8): New function.
- (get_bidi_ucn): Likewise.
- (maybe_warn_bidi_on_close): Likewise.
- (maybe_warn_bidi_on_char): Likewise.
- (_cpp_skip_block_comment): Implement warning about bidirectional
- control characters.
- (skip_line_comment): Likewise.
- (forms_identifier_p): Likewise.
- (lex_identifier): Likewise.
- (lex_string): Likewise.
- (lex_raw_string): Likewise.
-
-gcc/testsuite/ChangeLog:
-
- * c-c++-common/Wbidi-chars-1.c: New test.
- * c-c++-common/Wbidi-chars-2.c: New test.
- * c-c++-common/Wbidi-chars-3.c: New test.
- * c-c++-common/Wbidi-chars-4.c: New test.
- * c-c++-common/Wbidi-chars-5.c: New test.
- * c-c++-common/Wbidi-chars-6.c: New test.
- * c-c++-common/Wbidi-chars-7.c: New test.
- * c-c++-common/Wbidi-chars-8.c: New test.
- * c-c++-common/Wbidi-chars-9.c: New test.
- * c-c++-common/Wbidi-chars-10.c: New test.
- * c-c++-common/Wbidi-chars-11.c: New test.
- * c-c++-common/Wbidi-chars-12.c: New test.
- * c-c++-common/Wbidi-chars-13.c: New test.
- * c-c++-common/Wbidi-chars-14.c: New test.
- * c-c++-common/Wbidi-chars-15.c: New test.
- * c-c++-common/Wbidi-chars-16.c: New test.
- * c-c++-common/Wbidi-chars-17.c: New test.
-
-CVE: CVE-2021-42574
-Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=51c500269bf53749b107807d84271385fad35628]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- gcc/c-family/c.opt | 24 ++
- gcc/doc/invoke.texi | 21 +-
- gcc/testsuite/c-c++-common/Wbidi-chars-1.c | 12 +
- gcc/testsuite/c-c++-common/Wbidi-chars-10.c | 27 ++
- gcc/testsuite/c-c++-common/Wbidi-chars-11.c | 13 +
- gcc/testsuite/c-c++-common/Wbidi-chars-12.c | 19 +
- gcc/testsuite/c-c++-common/Wbidi-chars-13.c | 17 +
- gcc/testsuite/c-c++-common/Wbidi-chars-14.c | 38 ++
- gcc/testsuite/c-c++-common/Wbidi-chars-15.c | 59 +++
- gcc/testsuite/c-c++-common/Wbidi-chars-16.c | 26 ++
- gcc/testsuite/c-c++-common/Wbidi-chars-17.c | 30 ++
- gcc/testsuite/c-c++-common/Wbidi-chars-2.c | 9 +
- gcc/testsuite/c-c++-common/Wbidi-chars-3.c | 11 +
- gcc/testsuite/c-c++-common/Wbidi-chars-4.c | 188 +++++++++
- gcc/testsuite/c-c++-common/Wbidi-chars-5.c | 188 +++++++++
- gcc/testsuite/c-c++-common/Wbidi-chars-6.c | 155 ++++++++
- gcc/testsuite/c-c++-common/Wbidi-chars-7.c | 9 +
- gcc/testsuite/c-c++-common/Wbidi-chars-8.c | 13 +
- gcc/testsuite/c-c++-common/Wbidi-chars-9.c | 29 ++
- libcpp/include/cpplib.h | 18 +-
- libcpp/init.c | 1 +
- libcpp/internal.h | 7 +
- libcpp/lex.c | 408 +++++++++++++++++++-
- 23 files changed, 1315 insertions(+), 7 deletions(-)
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-1.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-10.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-11.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-12.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-13.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-14.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-15.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-16.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-17.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-2.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-3.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-4.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-5.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-6.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-7.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-8.c
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-9.c
-
-diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
-index 8a4cd634f77..3976fc368db 100644
---- a/gcc/c-family/c.opt
-+++ b/gcc/c-family/c.opt
-@@ -370,6 +370,30 @@ Wbad-function-cast
- C ObjC Var(warn_bad_function_cast) Warning
- Warn about casting functions to incompatible types.
-
-+Wbidi-chars
-+C ObjC C++ ObjC++ Warning Alias(Wbidi-chars=,any,none)
-+;
-+
-+Wbidi-chars=
-+C ObjC C++ ObjC++ RejectNegative Joined Warning CPP(cpp_warn_bidirectional) CppReason(CPP_W_BIDIRECTIONAL) Var(warn_bidirectional) Init(bidirectional_unpaired) Enum(cpp_bidirectional_level)
-+-Wbidi-chars=[none|unpaired|any] Warn about UTF-8 bidirectional control characters.
-+
-+; Required for these enum values.
-+SourceInclude
-+cpplib.h
-+
-+Enum
-+Name(cpp_bidirectional_level) Type(int) UnknownError(argument %qs to %<-Wbidi-chars%> not recognized)
-+
-+EnumValue
-+Enum(cpp_bidirectional_level) String(none) Value(bidirectional_none)
-+
-+EnumValue
-+Enum(cpp_bidirectional_level) String(unpaired) Value(bidirectional_unpaired)
-+
-+EnumValue
-+Enum(cpp_bidirectional_level) String(any) Value(bidirectional_any)
-+
- Wbool-compare
- C ObjC C++ ObjC++ Var(warn_bool_compare) Warning LangEnabledBy(C ObjC C++ ObjC++,Wall)
- Warn about boolean expression compared with an integer value different from true/false.
-diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
-index 6070288856c..a22758d18ee 100644
---- a/gcc/doc/invoke.texi
-+++ b/gcc/doc/invoke.texi
-@@ -326,7 +326,9 @@ Objective-C and Objective-C++ Dialects}.
- -Warith-conversion @gol
- -Warray-bounds -Warray-bounds=@var{n} @gol
- -Wno-attributes -Wattribute-alias=@var{n} -Wno-attribute-alias @gol
---Wno-attribute-warning -Wbool-compare -Wbool-operation @gol
-+-Wno-attribute-warning @gol
-+-Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]} @gol
-+-Wbool-compare -Wbool-operation @gol
- -Wno-builtin-declaration-mismatch @gol
- -Wno-builtin-macro-redefined -Wc90-c99-compat -Wc99-c11-compat @gol
- -Wc11-c2x-compat @gol
-@@ -7559,6 +7561,23 @@ Attributes considered include @code{allo
- This is the default. You can disable these warnings with either
- @option{-Wno-attribute-alias} or @option{-Wattribute-alias=0}.
-
-+@item -Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]}
-+@opindex Wbidi-chars=
-+@opindex Wbidi-chars
-+@opindex Wno-bidi-chars
-+Warn about possibly misleading UTF-8 bidirectional control characters in
-+comments, string literals, character constants, and identifiers. Such
-+characters can change left-to-right writing direction into right-to-left
-+(and vice versa), which can cause confusion between the logical order and
-+visual order. This may be dangerous; for instance, it may seem that a piece
-+of code is not commented out, whereas it in fact is.
-+
-+There are three levels of warning supported by GCC@. The default is
-+@option{-Wbidi-chars=unpaired}, which warns about improperly terminated
-+bidi contexts. @option{-Wbidi-chars=none} turns the warning off.
-+@option{-Wbidi-chars=any} warns about any use of bidirectional control
-+characters.
-+
- @item -Wbool-compare
- @opindex Wno-bool-compare
- @opindex Wbool-compare
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-10.c b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
-new file mode 100644
-index 00000000000..34f5ac19271
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
-@@ -0,0 +1,27 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* More nesting testing. */
-+
-+/* RLEâ« LRI⦠PDF⬠PDIâ©*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int LRE_\u202a_PDF_\u202c;
-+int LRE_\u202a_PDF_\u202c_LRE_\u202a_PDF_\u202c;
-+int LRE_\u202a_LRI_\u2066_PDF_\u202c_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLE_\u202b_RLI_\u2067_PDF_\u202c_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLE_\u202b_RLI_\u2067_PDI_\u2069_PDF_\u202c;
-+int FSI_\u2068_LRO_\u202d_PDI_\u2069_PDF_\u202c;
-+int FSI_\u2068;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int FSI_\u2068_PDI_\u2069;
-+int FSI_\u2068_FSI_\u2068_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
-+int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDF_\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_FSI_\u2068_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
-new file mode 100644
-index 00000000000..270ce2368a9
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
-@@ -0,0 +1,13 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test that we warn when mixing UCN and UTF-8. */
-+
-+int LRE_âª_PDF_\u202c;
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+int LRE_\u202a_PDF_â¬_;
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+const char *s1 = "LRE_âª_PDF_\u202c";
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+const char *s2 = "LRE_\u202a_PDF_â¬";
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-12.c b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c
-new file mode 100644
-index 00000000000..b07eec1da91
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c
-@@ -0,0 +1,19 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile { target { c || c++11 } } } */
-+/* { dg-options "-Wbidi-chars=any" } */
-+/* Test raw strings. */
-+
-+const char *s1 = R"(a b c LRE⪠1 2 3 PDF⬠x y z)";
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+const char *s2 = R"(a b c RLE⫠1 2 3 PDF⬠x y z)";
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+const char *s3 = R"(a b c LROâ 1 2 3 PDF⬠x y z)";
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+const char *s4 = R"(a b c RLO⮠1 2 3 PDF⬠x y z)";
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+const char *s7 = R"(a b c FSI⨠1 2 3 PDI⩠x y) z";
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+const char *s8 = R"(a b c PDIâ© x y )z";
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+const char *s9 = R"(a b c PDF⬠x y z)";
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-diff -uprN '-x*.orig' '-x*.rej' del/gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c
---- del/gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 1969-12-31 16:00:00.000000000 -0800
-+++ gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 2021-12-13 23:11:22.328439287 -0800
-@@ -0,0 +1,17 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile { target { c || c++11 } } } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test raw strings. */
-+
-+const char *s1 = R"(a b c LRE⪠1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s2 = R"(a b c RLEâ« 1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s3 = R"(a b c LROâ 1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s4 = R"(a b c FSI⨠1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s5 = R"(a b c LRI⦠1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s6 = R"(a b c RLI⧠1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
-new file mode 100644
-index 00000000000..ba5f75d9553
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
-@@ -0,0 +1,38 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test PDI handling, which also pops any subsequent LREs, RLEs, LROs,
-+ or RLOs. */
-+
-+/* LRI_â¦_LRI_â¦_RLE_â«_RLE_â«_RLE_â«_PDI_â©*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// LRI_â¦_RLE_â«_RLE_â«_RLE_â«_PDI_â©
-+// LRI_â¦_RLO_â®_RLE_â«_RLE_â«_PDI_â©
-+// LRI_â¦_RLO_â®_RLE_â«_PDI_â©
-+// FSI_â¨_RLO_â®_PDI_â©
-+// FSI_â¨_FSI_â¨_RLO_â®_PDI_â©
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069;
-+int LRI_\u2066_LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int PDI_\u2069;
-+int LRI_\u2066_PDI_\u2069;
-+int RLI_\u2067_PDI_\u2069;
-+int LRE_\u202a_LRI_\u2066_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int LRI_\u2066_LRE_\u202a_PDF_\u202c_PDI_\u2069;
-+int LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
-+int RLI_\u2067_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int FSI_\u2068_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLO_\u202e_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int RLI_\u2067_PDI_\u2069_RLI_\u2067;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int FSI_\u2068_PDF_\u202c_PDI_\u2069;
-+int FSI_\u2068_FSI_\u2068_PDF_\u202c_PDI_\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-15.c b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c
-new file mode 100644
-index 00000000000..a0ce8ff5e2c
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c
-@@ -0,0 +1,59 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test unpaired bidi control chars in multiline comments. */
-+
-+/*
-+ * LRE⪠end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * RLEâ« end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * LROâ end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * RLOâ® end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * LRI⦠end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * RLI⧠end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/*
-+ * FSI⨠end
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/* LREâª
-+ PDF⬠*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+/* FSIâ¨
-+ PDIâ© */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+
-+/* LRE<âª>
-+ *
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-3 } */
-+
-+/*
-+ * LRE<âª>
-+ */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+
-+/*
-+ *
-+ * LRE<âª> */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+/* RLI<â§> */ /* PDI<â©> */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRE<âª> */ /* PDF<â¬> */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
-new file mode 100644
-index 00000000000..baa0159861c
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
-@@ -0,0 +1,26 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=any" } */
-+/* Test LTR/RTL chars. */
-+
-+/* LTR<â> */
-+/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
-+// LTR<â>
-+/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
-+/* RTL<â> */
-+/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
-+// RTL<â>
-+/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
-+
-+const char *s1 = "LTR<â>";
-+/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
-+const char *s2 = "LTR\u200e";
-+/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
-+const char *s3 = "LTR\u200E";
-+/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
-+const char *s4 = "RTL<â>";
-+/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
-+const char *s5 = "RTL\u200f";
-+/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
-+const char *s6 = "RTL\u200F";
-+/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
-new file mode 100644
-index 00000000000..07cb4321f96
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
-@@ -0,0 +1,30 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test LTR/RTL chars. */
-+
-+/* LTR<â> */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// LTR<â>
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* RTL<â> */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// RTL<â>
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int ltr_\u200e;
-+/* { dg-error "universal character " "" { target *-*-* } .-1 } */
-+int rtl_\u200f;
-+/* { dg-error "universal character " "" { target *-*-* } .-1 } */
-+
-+const char *s1 = "LTR<â>";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+const char *s2 = "LTR\u200e";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+const char *s3 = "LTR\u200E";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+const char *s4 = "RTL<â>";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+const char *s5 = "RTL\u200f";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+const char *s6 = "RTL\u200F";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-1.c b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c
-new file mode 100644
-index 00000000000..2340374f276
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c
-@@ -0,0 +1,12 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+
-+int main() {
-+ int isAdmin = 0;
-+ /*â® } â¦if (isAdmin)⩠⦠begin admins only */
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+ __builtin_printf("You are an admin.\n");
-+ /* end admins only â® { â¦*/
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+ return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-2.c b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c
-new file mode 100644
-index 00000000000..2340374f276
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c
-@@ -0,0 +1,9 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+
-+int main() {
-+ /* Say hello; newlineâ§/*/ return 0 ;
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+ __builtin_printf("Hello world.\n");
-+ return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-3.c b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c
-new file mode 100644
-index 00000000000..9dc7edb6e64
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c
-@@ -0,0 +1,11 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+
-+int main() {
-+ const char* access_level = "user";
-+ if (__builtin_strcmp(access_level, "userâ® â¦// Check if adminâ© â¦")) {
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+ __builtin_printf("You are an admin.\n");
-+ }
-+ return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
-new file mode 100644
-index 00000000000..639e5c62e88
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
-@@ -0,0 +1,188 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=any -Wno-multichar -Wno-overflow" } */
-+/* Test all bidi chars in various contexts (identifiers, comments,
-+ string literals, character constants), both UCN and UTF-8. The bidi
-+ chars here are properly terminated, except for the character constants. */
-+
-+/* a b c LRE⪠1 2 3 PDF⬠x y z */
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+/* a b c RLE⫠1 2 3 PDF⬠x y z */
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+/* a b c LROâ 1 2 3 PDF⬠x y z */
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+/* a b c RLO⮠1 2 3 PDF⬠x y z */
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+/* a b c LRI⦠1 2 3 PDI⩠x y z */
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+/* a b c RLI⧠1 2 3 PDI⩠x y */
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+/* a b c FSI⨠1 2 3 PDI⩠x y z */
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+
-+/* Same but C++ comments instead. */
-+// a b c LRE⪠1 2 3 PDF⬠x y z
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+// a b c RLE⫠1 2 3 PDF⬠x y z
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+// a b c LROâ 1 2 3 PDF⬠x y z
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+// a b c RLO⮠1 2 3 PDF⬠x y z
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+// a b c LRI⦠1 2 3 PDI⩠x y z
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+// a b c RLI⧠1 2 3 PDI⩠x y
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+// a b c FSI⨠1 2 3 PDI⩠x y z
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+
-+/* Here we're closing an unopened context, warn when =any. */
-+/* a b c PDIâ© x y z */
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+/* a b c PDF⬠x y z */
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+// a b c PDIâ© x y z
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+// a b c PDF⬠x y z
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+
-+/* Multiline comments. */
-+/* a b c PDIâ© x y z
-+ */
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */
-+/* a b c PDF⬠x y z
-+ */
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDIâ© x y z
-+ */
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDF⬠x y z
-+ */
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDIâ© x y z */
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+/* first
-+ a b c PDF⬠x y z */
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+
-+void
-+g1 ()
-+{
-+ const char *s1 = "a b c LRE⪠1 2 3 PDF⬠x y z";
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+ const char *s2 = "a b c RLE⫠1 2 3 PDF⬠x y z";
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+ const char *s3 = "a b c LROâ 1 2 3 PDF⬠x y z";
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+ const char *s4 = "a b c RLO⮠1 2 3 PDF⬠x y z";
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+ const char *s5 = "a b c LRI⦠1 2 3 PDI⩠x y z";
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+ const char *s6 = "a b c RLI⧠1 2 3 PDI⩠x y z";
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+ const char *s7 = "a b c FSI⨠1 2 3 PDI⩠x y z";
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+ const char *s8 = "a b c PDIâ© x y z";
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+ const char *s9 = "a b c PDF⬠x y z";
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+
-+ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+}
-+
-+void
-+g2 ()
-+{
-+ const char c1 = '\u202a';
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+ const char c2 = '\u202A';
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+ const char c3 = '\u202b';
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+ const char c4 = '\u202B';
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+ const char c5 = '\u202d';
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+ const char c6 = '\u202D';
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+ const char c7 = '\u202e';
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+ const char c8 = '\u202E';
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+ const char c9 = '\u2066';
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+ const char c10 = '\u2067';
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+ const char c11 = '\u2068';
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+}
-+
-+int aâªbâ¬c;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int aâ«bâ¬c;
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+int aâbâ¬c;
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+int aâ®bâ¬c;
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+int aâ¦bâ©c;
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+int aâ§bâ©c;
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+int aâ¨bâ©c;
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+int Aâ¬X;
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+int A\u202cY;
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+int A\u202CY2;
-+/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
-+
-+int d\u202ae\u202cf;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int d\u202Ae\u202cf2;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int d\u202be\u202cf;
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+int d\u202Be\u202cf2;
-+/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
-+int d\u202de\u202cf;
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+int d\u202De\u202cf2;
-+/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
-+int d\u202ee\u202cf;
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+int d\u202Ee\u202cf2;
-+/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
-+int d\u2066e\u2069f;
-+/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
-+int d\u2067e\u2069f;
-+/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
-+int d\u2068e\u2069f;
-+/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
-+int X\u2069;
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-5.c b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
-new file mode 100644
-index 00000000000..68cb053144b
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
-@@ -0,0 +1,188 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired -Wno-multichar -Wno-overflow" } */
-+/* Test all bidi chars in various contexts (identifiers, comments,
-+ string literals, character constants), both UCN and UTF-8. The bidi
-+ chars here are properly terminated, except for the character constants. */
-+
-+/* a b c LRE⪠1 2 3 PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLE⫠1 2 3 PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c LROâ 1 2 3 PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLO⮠1 2 3 PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c LRI⦠1 2 3 PDI⩠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLI⧠1 2 3 PDI⩠x y */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c FSI⨠1 2 3 PDI⩠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+/* Same but C++ comments instead. */
-+// a b c LRE⪠1 2 3 PDF⬠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLE⫠1 2 3 PDF⬠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c LROâ 1 2 3 PDF⬠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLO⮠1 2 3 PDF⬠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c LRI⦠1 2 3 PDI⩠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLI⧠1 2 3 PDI⩠x y
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c FSI⨠1 2 3 PDI⩠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+/* Here we're closing an unopened context, warn when =any. */
-+/* a b c PDIâ© x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c PDIâ© x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c PDF⬠x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+/* Multiline comments. */
-+/* a b c PDIâ© x y z
-+ */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
-+/* a b c PDF⬠x y z
-+ */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDIâ© x y z
-+ */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDF⬠x y z
-+ */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
-+/* first
-+ a b c PDIâ© x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* first
-+ a b c PDF⬠x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+void
-+g1 ()
-+{
-+ const char *s1 = "a b c LRE⪠1 2 3 PDF⬠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s2 = "a b c RLE⫠1 2 3 PDF⬠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s3 = "a b c LROâ 1 2 3 PDF⬠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s4 = "a b c RLO⮠1 2 3 PDF⬠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s5 = "a b c LRI⦠1 2 3 PDI⩠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s6 = "a b c RLI⧠1 2 3 PDI⩠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s7 = "a b c FSI⨠1 2 3 PDI⩠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s8 = "a b c PDIâ© x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s9 = "a b c PDF⬠x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z";
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+}
-+
-+void
-+g2 ()
-+{
-+ const char c1 = '\u202a';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c2 = '\u202A';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c3 = '\u202b';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c4 = '\u202B';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c5 = '\u202d';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c6 = '\u202D';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c7 = '\u202e';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c8 = '\u202E';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c9 = '\u2066';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c10 = '\u2067';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char c11 = '\u2068';
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+}
-+
-+int aâªbâ¬c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâ«bâ¬c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâbâ¬c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâ®bâ¬c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâ¦bâ©c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâ§bâ©c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int aâ¨bâ©c;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int Aâ¬X;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int A\u202cY;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int A\u202CY2;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+
-+int d\u202ae\u202cf;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202Ae\u202cf2;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202be\u202cf;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202Be\u202cf2;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202de\u202cf;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202De\u202cf2;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202ee\u202cf;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u202Ee\u202cf2;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u2066e\u2069f;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u2067e\u2069f;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int d\u2068e\u2069f;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+int X\u2069;
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-6.c b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
-new file mode 100644
-index 00000000000..0ce6fff2dee
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
-@@ -0,0 +1,155 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test nesting of bidi chars in various contexts. */
-+
-+/* Terminated by the wrong char: */
-+/* a b c LRE⪠1 2 3 PDI⩠x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLEâ« 1 2 3 PDIâ© x y z*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c LROâ 1 2 3 PDIâ© x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLOâ® 1 2 3 PDIâ© x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c LRI⦠1 2 3 PDF⬠x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLI⧠1 2 3 PDF⬠x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c FSI⨠1 2 3 PDF⬠x y z*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+/* LRE⪠PDF⬠*/
-+/* LRE⪠LRE⪠PDF⬠PDF⬠*/
-+/* PDF⬠LRE⪠PDF⬠*/
-+/* LRE⪠PDF⬠LRE⪠PDF⬠*/
-+/* LRE⪠LRE⪠PDF⬠*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* PDF⬠LRE⪠*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+// a b c LRE⪠1 2 3 PDI⩠x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLEâ« 1 2 3 PDIâ© x y z*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c LROâ 1 2 3 PDIâ© x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLOâ® 1 2 3 PDIâ© x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c LRI⦠1 2 3 PDF⬠x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLI⧠1 2 3 PDF⬠x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c FSI⨠1 2 3 PDF⬠x y z
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+// LRE⪠PDFâ¬
-+// LRE⪠LRE⪠PDF⬠PDFâ¬
-+// PDF⬠LRE⪠PDFâ¬
-+// LRE⪠PDF⬠LRE⪠PDFâ¬
-+// LRE⪠LRE⪠PDFâ¬
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// PDF⬠LREâª
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+void
-+g1 ()
-+{
-+ const char *s1 = "a b c LRE⪠1 2 3 PDI⩠x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s2 = "a b c LRE\u202a 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s3 = "a b c RLEâ« 1 2 3 PDIâ© x y ";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s4 = "a b c RLE\u202b 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s5 = "a b c LROâ 1 2 3 PDIâ© x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s6 = "a b c LRO\u202d 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s7 = "a b c RLOâ® 1 2 3 PDIâ© x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s8 = "a b c RLO\u202e 1 2 3 PDI\u2069 x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s9 = "a b c LRI⦠1 2 3 PDF⬠x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s10 = "a b c LRI\u2066 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s11 = "a b c RLI⧠1 2 3 PDF⬠x y z\
-+ ";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+ const char *s12 = "a b c RLI\u2067 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s13 = "a b c FSI⨠1 2 3 PDF⬠x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s14 = "a b c FSI\u2068 1 2 3 PDF\u202c x y z";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s15 = "PDF⬠LREâª";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s16 = "PDF\u202c LRE\u202a";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s17 = "LRE⪠PDFâ¬";
-+ const char *s18 = "LRE\u202a PDF\u202c";
-+ const char *s19 = "LRE⪠LRE⪠PDF⬠PDFâ¬";
-+ const char *s20 = "LRE\u202a LRE\u202a PDF\u202c PDF\u202c";
-+ const char *s21 = "PDF⬠LRE⪠PDFâ¬";
-+ const char *s22 = "PDF\u202c LRE\u202a PDF\u202c";
-+ const char *s23 = "LRE⪠LRE⪠PDFâ¬";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s24 = "LRE\u202a LRE\u202a PDF\u202c";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s25 = "PDF⬠LREâª";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s26 = "PDF\u202c LRE\u202a";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s27 = "PDF⬠LRE\u202a";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+ const char *s28 = "PDF\u202c LREâª";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+}
-+
-+int aLREâªbPDIâ©;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int A\u202aB\u2069C;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aRLEâ«bPDIâ©;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202bB\u2069c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aLROâbPDIâ©;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202db\u2069c2;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aRLOâ®bPDIâ©;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202eb\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aLRIâ¦bPDFâ¬;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u2066b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aRLIâ§bPDFâ¬c
-+;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
-+int a\u2067b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aFSIâ¨bPDFâ¬;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u2068b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aFSIâ¨bPD\u202C;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aFSI\u2068bPDFâ¬_;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int aLREâªbPDFâ¬b;
-+int A\u202aB\u202c;
-+int a_LREâª_LREâª_b_PDFâ¬_PDFâ¬;
-+int A\u202aA\u202aB\u202cB\u202c;
-+int aPDFâ¬bLREadPDFâ¬;
-+int a_\u202C_\u202a_\u202c;
-+int a_LREâª_b_PDFâ¬_c_LREâª_PDFâ¬;
-+int a_\u202a_\u202c_\u202a_\u202c_;
-+int a_LREâª_b_PDFâ¬_c_LREâª;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a_\u202a_\u202c_\u202a_;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-7.c b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
-new file mode 100644
-index 00000000000..d012d420ec0
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
-@@ -0,0 +1,9 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=any" } */
-+/* Test we ignore UCNs in comments. */
-+
-+// a b c \u202a 1 2 3
-+// a b c \u202A 1 2 3
-+/* a b c \u202a 1 2 3 */
-+/* a b c \u202A 1 2 3 */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-8.c b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
-new file mode 100644
-index 00000000000..4f54c5092ec
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
-@@ -0,0 +1,13 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=any" } */
-+/* Test \u vs \U. */
-+
-+int a_\u202A;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int a_\u202a_2;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int a_\U0000202A_3;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-+int a_\U0000202a_4;
-+/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-9.c b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
-new file mode 100644
-index 00000000000..e2af1b1ca97
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
-@@ -0,0 +1,29 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired" } */
-+/* Test that we properly separate bidi contexts (comment/identifier/character
-+ constant/string literal). */
-+
-+/* LRE ->âª<- */ int pdf_\u202c_1;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLE ->â«<- */ int pdf_\u202c_2;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRO ->â<- */ int pdf_\u202c_3;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLO ->â®<- */ int pdf_\u202c_4;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRI ->â¦<-*/ int pdi_\u2069_1;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLI ->â§<- */ int pdi_\u2069_12;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* FSI ->â¨<- */ int pdi_\u2069_3;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+const char *s1 = "LRE\u202a"; /* PDF ->â¬<- */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRE ->âª<- */ const char *s2 = "PDF\u202c";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s3 = "LRE\u202a"; int pdf_\u202c_5;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int lre_\u202a; const char *s4 = "PDF\u202c";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
-index 176f8c5bbce..112b9c24751 100644
---- a/libcpp/include/cpplib.h
-+++ b/libcpp/include/cpplib.h
-@@ -318,6 +318,17 @@ enum cpp_main_search
- CMS_system, /* Search the system INCLUDE path. */
- };
-
-+/* The possible bidirectional control characters checking levels, from least
-+ restrictive to most. */
-+enum cpp_bidirectional_level {
-+ /* No checking. */
-+ bidirectional_none,
-+ /* Only detect unpaired uses of bidirectional control characters. */
-+ bidirectional_unpaired,
-+ /* Detect any use of bidirectional control characters. */
-+ bidirectional_any
-+};
-+
- /* This structure is nested inside struct cpp_reader, and
- carries all the options visible to the command line. */
- struct cpp_options
-@@ -531,6 +542,10 @@ struct cpp_options
- /* True if warn about differences between C++98 and C++11. */
- bool cpp_warn_cxx11_compat;
-
-+ /* Nonzero if bidirectional control characters checking is on. See enum
-+ cpp_bidirectional_level. */
-+ unsigned char cpp_warn_bidirectional;
-+
- /* Dependency generation. */
- struct
- {
-@@ -635,7 +650,8 @@ enum cpp_warning_reason {
- CPP_W_C90_C99_COMPAT,
- CPP_W_C11_C2X_COMPAT,
- CPP_W_CXX11_COMPAT,
-- CPP_W_EXPANSION_TO_DEFINED
-+ CPP_W_EXPANSION_TO_DEFINED,
-+ CPP_W_BIDIRECTIONAL
- };
-
- /* Callback for header lookup for HEADER, which is the name of a
-diff --git a/libcpp/init.c b/libcpp/init.c
-index 5a424e23553..f9a8f5f088f 100644
---- a/libcpp/init.c
-+++ b/libcpp/init.c
-@@ -219,6 +219,7 @@ cpp_create_reader (enum c_lang lang, cpp
- = ENABLE_CANONICAL_SYSTEM_HEADERS;
- CPP_OPTION (pfile, ext_numeric_literals) = 1;
- CPP_OPTION (pfile, warn_date_time) = 0;
-+ CPP_OPTION (pfile, cpp_warn_bidirectional) = bidirectional_unpaired;
-
- /* Default CPP arithmetic to something sensible for the host for the
- benefit of dumb users like fix-header. */
-diff --git a/libcpp/internal.h b/libcpp/internal.h
-index 8577cab6c83..0ce0246c5a2 100644
---- a/libcpp/internal.h
-+++ b/libcpp/internal.h
-@@ -597,6 +597,13 @@ struct cpp_reader
- /* Location identifying the main source file -- intended to be line
- zero of said file. */
- location_t main_loc;
-+
-+ /* Returns true iff we should warn about UTF-8 bidirectional control
-+ characters. */
-+ bool warn_bidi_p () const
-+ {
-+ return CPP_OPTION (this, cpp_warn_bidirectional) != bidirectional_none;
-+ }
- };
-
- /* Character classes. Based on the more primitive macros in safe-ctype.h.
-diff --git a/libcpp/lex.c b/libcpp/lex.c
-index fa2253d41c3..6a4fbce6030 100644
---- a/libcpp/lex.c
-+++ b/libcpp/lex.c
-@@ -1164,6 +1164,324 @@ _cpp_process_line_notes (cpp_reader *pfi
- }
- }
-
-+namespace bidi {
-+ enum class kind {
-+ NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI, LTR, RTL
-+ };
-+
-+ /* All the UTF-8 encodings of bidi characters start with E2. */
-+ constexpr uchar utf8_start = 0xe2;
-+
-+ /* A vector holding currently open bidi contexts. We use a char for
-+ each context, its LSB is 1 if it represents a PDF context, 0 if it
-+ represents a PDI context. The next bit is 1 if this context was open
-+ by a bidi character written as a UCN, and 0 when it was UTF-8. */
-+ semi_embedded_vec <unsigned char, 16> vec;
-+
-+ /* Close the whole comment/identifier/string literal/character constant
-+ context. */
-+ void on_close ()
-+ {
-+ vec.truncate (0);
-+ }
-+
-+ /* Pop the last element in the vector. */
-+ void pop ()
-+ {
-+ unsigned int len = vec.count ();
-+ gcc_checking_assert (len > 0);
-+ vec.truncate (len - 1);
-+ }
-+
-+ /* Return the context of the Ith element. */
-+ kind ctx_at (unsigned int i)
-+ {
-+ return (vec[i] & 1) ? kind::PDF : kind::PDI;
-+ }
-+
-+ /* Return which context is currently opened. */
-+ kind current_ctx ()
-+ {
-+ unsigned int len = vec.count ();
-+ if (len == 0)
-+ return kind::NONE;
-+ return ctx_at (len - 1);
-+ }
-+
-+ /* Return true if the current context comes from a UCN origin, that is,
-+ the bidi char which started this bidi context was written as a UCN. */
-+ bool current_ctx_ucn_p ()
-+ {
-+ unsigned int len = vec.count ();
-+ gcc_checking_assert (len > 0);
-+ return (vec[len - 1] >> 1) & 1;
-+ }
-+
-+ /* We've read a bidi char, update the current vector as necessary. */
-+ void on_char (kind k, bool ucn_p)
-+ {
-+ switch (k)
-+ {
-+ case kind::LRE:
-+ case kind::RLE:
-+ case kind::LRO:
-+ case kind::RLO:
-+ vec.push (ucn_p ? 3u : 1u);
-+ break;
-+ case kind::LRI:
-+ case kind::RLI:
-+ case kind::FSI:
-+ vec.push (ucn_p ? 2u : 0u);
-+ break;
-+ /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
-+ whose scope has not yet been terminated. */
-+ case kind::PDF:
-+ if (current_ctx () == kind::PDF)
-+ pop ();
-+ break;
-+ /* PDI terminates the scope of the last LRI, RLI, or FSI whose
-+ scope has not yet been terminated, as well as the scopes of
-+ any subsequent LREs, RLEs, LROs, or RLOs whose scopes have not
-+ yet been terminated. */
-+ case kind::PDI:
-+ for (int i = vec.count () - 1; i >= 0; --i)
-+ if (ctx_at (i) == kind::PDI)
-+ {
-+ vec.truncate (i);
-+ break;
-+ }
-+ break;
-+ case kind::LTR:
-+ case kind::RTL:
-+ /* These aren't popped by a PDF/PDI. */
-+ break;
-+ [[likely]] case kind::NONE:
-+ break;
-+ default:
-+ abort ();
-+ }
-+ }
-+
-+ /* Return a descriptive string for K. */
-+ const char *to_str (kind k)
-+ {
-+ switch (k)
-+ {
-+ case kind::LRE:
-+ return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
-+ case kind::RLE:
-+ return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
-+ case kind::LRO:
-+ return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
-+ case kind::RLO:
-+ return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
-+ case kind::LRI:
-+ return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
-+ case kind::RLI:
-+ return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
-+ case kind::FSI:
-+ return "U+2068 (FIRST STRONG ISOLATE)";
-+ case kind::PDF:
-+ return "U+202C (POP DIRECTIONAL FORMATTING)";
-+ case kind::PDI:
-+ return "U+2069 (POP DIRECTIONAL ISOLATE)";
-+ case kind::LTR:
-+ return "U+200E (LEFT-TO-RIGHT MARK)";
-+ case kind::RTL:
-+ return "U+200F (RIGHT-TO-LEFT MARK)";
-+ default:
-+ abort ();
-+ }
-+ }
-+}
-+
-+/* Parse a sequence of 3 bytes starting with P and return its bidi code. */
-+
-+static bidi::kind
-+get_bidi_utf8 (const unsigned char *const p)
-+{
-+ gcc_checking_assert (p[0] == bidi::utf8_start);
-+
-+ if (p[1] == 0x80)
-+ switch (p[2])
-+ {
-+ case 0xaa:
-+ return bidi::kind::LRE;
-+ case 0xab:
-+ return bidi::kind::RLE;
-+ case 0xac:
-+ return bidi::kind::PDF;
-+ case 0xad:
-+ return bidi::kind::LRO;
-+ case 0xae:
-+ return bidi::kind::RLO;
-+ case 0x8e:
-+ return bidi::kind::LTR;
-+ case 0x8f:
-+ return bidi::kind::RTL;
-+ default:
-+ break;
-+ }
-+ else if (p[1] == 0x81)
-+ switch (p[2])
-+ {
-+ case 0xa6:
-+ return bidi::kind::LRI;
-+ case 0xa7:
-+ return bidi::kind::RLI;
-+ case 0xa8:
-+ return bidi::kind::FSI;
-+ case 0xa9:
-+ return bidi::kind::PDI;
-+ default:
-+ break;
-+ }
-+
-+ return bidi::kind::NONE;
-+}
-+
-+/* Parse a UCN where P points just past \u or \U and return its bidi code. */
-+
-+static bidi::kind
-+get_bidi_ucn (const unsigned char *p, bool is_U)
-+{
-+ /* 6.4.3 Universal Character Names
-+ \u hex-quad
-+ \U hex-quad hex-quad
-+ where \unnnn means \U0000nnnn. */
-+
-+ if (is_U)
-+ {
-+ if (p[0] != '0' || p[1] != '0' || p[2] != '0' || p[3] != '0')
-+ return bidi::kind::NONE;
-+ /* Skip 4B so we can treat \u and \U the same below. */
-+ p += 4;
-+ }
-+
-+ /* All code points we are looking for start with 20xx. */
-+ if (p[0] != '2' || p[1] != '0')
-+ return bidi::kind::NONE;
-+ else if (p[2] == '2')
-+ switch (p[3])
-+ {
-+ case 'a':
-+ case 'A':
-+ return bidi::kind::LRE;
-+ case 'b':
-+ case 'B':
-+ return bidi::kind::RLE;
-+ case 'c':
-+ case 'C':
-+ return bidi::kind::PDF;
-+ case 'd':
-+ case 'D':
-+ return bidi::kind::LRO;
-+ case 'e':
-+ case 'E':
-+ return bidi::kind::RLO;
-+ default:
-+ break;
-+ }
-+ else if (p[2] == '6')
-+ switch (p[3])
-+ {
-+ case '6':
-+ return bidi::kind::LRI;
-+ case '7':
-+ return bidi::kind::RLI;
-+ case '8':
-+ return bidi::kind::FSI;
-+ case '9':
-+ return bidi::kind::PDI;
-+ default:
-+ break;
-+ }
-+ else if (p[2] == '0')
-+ switch (p[3])
-+ {
-+ case 'e':
-+ case 'E':
-+ return bidi::kind::LTR;
-+ case 'f':
-+ case 'F':
-+ return bidi::kind::RTL;
-+ default:
-+ break;
-+ }
-+
-+ return bidi::kind::NONE;
-+}
-+
-+/* We're closing a bidi context, that is, we've encountered a newline,
-+ are closing a C-style comment, or are at the end of a string literal,
-+ character constant, or identifier. Warn if this context was not
-+ properly terminated by a PDI or PDF. P points to the last character
-+ in this context. */
-+
-+static void
-+maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
-+{
-+ if (CPP_OPTION (pfile, cpp_warn_bidirectional) == bidirectional_unpaired
-+ && bidi::vec.count () > 0)
-+ {
-+ const location_t loc
-+ = linemap_position_for_column (pfile->line_table,
-+ CPP_BUF_COLUMN (pfile->buffer, p));
-+ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-+ "unpaired UTF-8 bidirectional control character "
-+ "detected");
-+ }
-+ /* We're done with this context. */
-+ bidi::on_close ();
-+}
-+
-+/* We're at the beginning or in the middle of an identifier/comment/string
-+ literal/character constant. Warn if we've encountered a bidi character.
-+ KIND says which bidi character it was; P points to it in the character
-+ stream. UCN_P is true iff this bidi character was written as a UCN. */
-+
-+static void
-+maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
-+ bool ucn_p)
-+{
-+ if (__builtin_expect (kind == bidi::kind::NONE, 1))
-+ return;
-+
-+ const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
-+
-+ if (warn_bidi != bidirectional_none)
-+ {
-+ const location_t loc
-+ = linemap_position_for_column (pfile->line_table,
-+ CPP_BUF_COLUMN (pfile->buffer, p));
-+ /* It seems excessive to warn about a PDI/PDF that is closing
-+ an opened context because we've already warned about the
-+ opening character. Except warn when we have a UCN x UTF-8
-+ mismatch. */
-+ if (kind == bidi::current_ctx ())
-+ {
-+ if (warn_bidi == bidirectional_unpaired
-+ && bidi::current_ctx_ucn_p () != ucn_p)
-+ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-+ "UTF-8 vs UCN mismatch when closing "
-+ "a context by \"%s\"", bidi::to_str (kind));
-+ }
-+ else if (warn_bidi == bidirectional_any)
-+ {
-+ if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
-+ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-+ "\"%s\" is closing an unopened context",
-+ bidi::to_str (kind));
-+ else
-+ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-+ "found problematic Unicode character \"%s\"",
-+ bidi::to_str (kind));
-+ }
-+ }
-+ /* We're done with this context. */
-+ bidi::on_char (kind, ucn_p);
-+}
-+
- /* Skip a C-style block comment. We find the end of the comment by
- seeing if an asterisk is before every '/' we encounter. Returns
- nonzero if comment terminated by EOF, zero otherwise.
-@@ -1175,6 +1493,7 @@ _cpp_skip_block_comment (cpp_reader *pfi
- cpp_buffer *buffer = pfile->buffer;
- const uchar *cur = buffer->cur;
- uchar c;
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
-
- cur++;
- if (*cur == '/')
-@@ -1189,7 +1508,11 @@ _cpp_skip_block_comment (cpp_reader *pfi
- if (c == '/')
- {
- if (cur[-2] == '*')
-- break;
-+ {
-+ if (warn_bidi_p)
-+ maybe_warn_bidi_on_close (pfile, cur);
-+ break;
-+ }
-
- /* Warn about potential nested comments, but not if the '/'
- comes immediately before the true comment delimiter.
-@@ -1208,6 +1531,8 @@ _cpp_skip_block_comment (cpp_reader *pfi
- {
- unsigned int cols;
- buffer->cur = cur - 1;
-+ if (warn_bidi_p)
-+ maybe_warn_bidi_on_close (pfile, cur);
- _cpp_process_line_notes (pfile, true);
- if (buffer->next_line >= buffer->rlimit)
- return true;
-@@ -1218,6 +1543,13 @@ _cpp_skip_block_comment (cpp_reader *pfi
-
- cur = buffer->cur;
- }
-+ /* If this is a beginning of a UTF-8 encoding, it might be
-+ a bidirectional control character. */
-+ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
-+ {
-+ bidi::kind kind = get_bidi_utf8 (cur - 1);
-+ maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/false);
-+ }
- }
-
- buffer->cur = cur;
-@@ -1233,9 +1565,31 @@ skip_line_comment (cpp_reader *pfile)
- {
- cpp_buffer *buffer = pfile->buffer;
- location_t orig_line = pfile->line_table->highest_line;
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
-
-- while (*buffer->cur != '\n')
-- buffer->cur++;
-+ if (!warn_bidi_p)
-+ while (*buffer->cur != '\n')
-+ buffer->cur++;
-+ else
-+ {
-+ while (*buffer->cur != '\n'
-+ && *buffer->cur != bidi::utf8_start)
-+ buffer->cur++;
-+ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
-+ {
-+ while (*buffer->cur != '\n')
-+ {
-+ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
-+ {
-+ bidi::kind kind = get_bidi_utf8 (buffer->cur);
-+ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-+ /*ucn_p=*/false);
-+ }
-+ buffer->cur++;
-+ }
-+ maybe_warn_bidi_on_close (pfile, buffer->cur);
-+ }
-+ }
-
- _cpp_process_line_notes (pfile, true);
- return orig_line != pfile->line_table->highest_line;
-@@ -1317,11 +1671,13 @@ static const cppchar_t utf8_signifier =
-
- /* Returns TRUE if the sequence starting at buffer->cur is valid in
- an identifier. FIRST is TRUE if this starts an identifier. */
-+
- static bool
- forms_identifier_p (cpp_reader *pfile, int first,
- struct normalize_state *state)
- {
- cpp_buffer *buffer = pfile->buffer;
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
-
- if (*buffer->cur == '$')
- {
-@@ -1344,6 +1700,13 @@ forms_identifier_p (cpp_reader *pfile, i
- cppchar_t s;
- if (*buffer->cur >= utf8_signifier)
- {
-+ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
-+ && warn_bidi_p)
-+ {
-+ bidi::kind kind = get_bidi_utf8 (buffer->cur);
-+ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-+ /*ucn_p=*/false);
-+ }
- if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
- state, &s))
- return true;
-@@ -1352,6 +1715,13 @@ forms_identifier_p (cpp_reader *pfile, i
- && (buffer->cur[1] == 'u' || buffer->cur[1] == 'U'))
- {
- buffer->cur += 2;
-+ if (warn_bidi_p)
-+ {
-+ bidi::kind kind = get_bidi_ucn (buffer->cur,
-+ buffer->cur[-1] == 'U');
-+ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-+ /*ucn_p=*/true);
-+ }
- if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
- state, &s, NULL, NULL))
- return true;
-@@ -1460,6 +1830,7 @@ lex_identifier (cpp_reader *pfile, const
- const uchar *cur;
- unsigned int len;
- unsigned int hash = HT_HASHSTEP (0, *base);
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
-
- cur = pfile->buffer->cur;
- if (! starts_ucn)
-@@ -1483,6 +1854,8 @@ lex_identifier (cpp_reader *pfile, const
- pfile->buffer->cur++;
- }
- } while (forms_identifier_p (pfile, false, nst));
-+ if (warn_bidi_p)
-+ maybe_warn_bidi_on_close (pfile, pfile->buffer->cur);
- result = _cpp_interpret_identifier (pfile, base,
- pfile->buffer->cur - base);
- *spelling = cpp_lookup (pfile, base, pfile->buffer->cur - base);
-@@ -1719,6 +2092,7 @@ static void
- lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
- {
- const uchar *pos = base;
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
-
- /* 'tis a pity this information isn't passed down from the lexer's
- initial categorization of the token. */
-@@ -1955,8 +2329,15 @@ lex_raw_string (cpp_reader *pfile, cpp_t
- pos = base = pfile->buffer->cur;
- note = &pfile->buffer->notes[pfile->buffer->cur_note];
- }
-+ else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0)
-+ && warn_bidi_p)
-+ maybe_warn_bidi_on_char (pfile, pos - 1, get_bidi_utf8 (pos - 1),
-+ /*ucn_p=*/false);
- }
-
-+ if (warn_bidi_p)
-+ maybe_warn_bidi_on_close (pfile, pos);
-+
- if (CPP_OPTION (pfile, user_literals))
- {
- /* If a string format macro, say from inttypes.h, is placed touching
-@@ -2051,15 +2432,27 @@ lex_string (cpp_reader *pfile, cpp_token
- else
- terminator = '>', type = CPP_HEADER_NAME;
-
-+ const bool warn_bidi_p = pfile->warn_bidi_p ();
- for (;;)
- {
- cppchar_t c = *cur++;
-
- /* In #include-style directives, terminators are not escapable. */
- if (c == '\\' && !pfile->state.angled_headers && *cur != '\n')
-- cur++;
-+ {
-+ if ((cur[0] == 'u' || cur[0] == 'U') && warn_bidi_p)
-+ {
-+ bidi::kind kind = get_bidi_ucn (cur + 1, cur[0] == 'U');
-+ maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/true);
-+ }
-+ cur++;
-+ }
- else if (c == terminator)
-- break;
-+ {
-+ if (warn_bidi_p)
-+ maybe_warn_bidi_on_close (pfile, cur - 1);
-+ break;
-+ }
- else if (c == '\n')
- {
- cur--;
-@@ -2076,6 +2469,11 @@ lex_string (cpp_reader *pfile, cpp_token
- }
- else if (c == '\0')
- saw_NUL = true;
-+ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
-+ {
-+ bidi::kind kind = get_bidi_utf8 (cur - 1);
-+ maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false);
-+ }
- }
-
- if (saw_NUL && !pfile->state.skipping)
diff --git a/meta/recipes-devtools/gcc/gcc/0002-gcc-poison-system-directories.patch b/meta/recipes-devtools/gcc/gcc/0002-gcc-poison-system-directories.patch
index 18a9fb8701..b85f7ed2c7 100644
--- a/meta/recipes-devtools/gcc/gcc/0002-gcc-poison-system-directories.patch
+++ b/meta/recipes-devtools/gcc/gcc/0002-gcc-poison-system-directories.patch
@@ -14,14 +14,15 @@ wants this to be a failure, they can add "-Werror=poison-system-directories".
Upstream-Status: Pending
Signed-off-by: Mark Hatle <mark.hatle@windriver.com>
Signed-off-by: Khem Raj <raj.khem@gmail.com>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
---
gcc/common.opt | 4 ++++
gcc/config.in | 10 ++++++++++
gcc/configure | 19 +++++++++++++++++++
gcc/configure.ac | 16 ++++++++++++++++
gcc/doc/invoke.texi | 9 +++++++++
- gcc/gcc.c | 9 +++++++--
- gcc/incpath.c | 21 +++++++++++++++++++++
+ gcc/gcc.cc | 9 +++++++--
+ gcc/incpath.cc | 21 +++++++++++++++++++++
7 files changed, 86 insertions(+), 2 deletions(-)
diff --git a/gcc/common.opt b/gcc/common.opt
@@ -158,10 +159,10 @@ index 7a368959e5e..6659a903bf0 100644
@item -Wfloat-equal
@opindex Wfloat-equal
@opindex Wno-float-equal
-diff --git a/gcc/gcc.c b/gcc/gcc.c
+diff --git a/gcc/gcc.cc b/gcc/gcc.cc
index 7837553958b..19c75b6e20d 100644
---- a/gcc/gcc.c
-+++ b/gcc/gcc.c
+--- a/gcc/gcc.cc
++++ b/gcc/gcc.cc
@@ -1152,6 +1152,8 @@ proper position among the other output files. */
"%{fuse-ld=*:-fuse-ld=%*} " LINK_COMPRESS_DEBUG_SPEC \
"%X %{o*} %{e*} %{N} %{n} %{r}\
@@ -185,10 +186,10 @@ index 7837553958b..19c75b6e20d 100644
/* Pass -d* flags, possibly modifying -dumpdir, -dumpbase et al.
-diff --git a/gcc/incpath.c b/gcc/incpath.c
+diff --git a/gcc/incpath.cc b/gcc/incpath.cc
index 446d280321d..fbfc0ce03b8 100644
---- a/gcc/incpath.c
-+++ b/gcc/incpath.c
+--- a/gcc/incpath.cc
++++ b/gcc/incpath.cc
@@ -26,6 +26,7 @@
#include "intl.h"
#include "incpath.h"
diff --git a/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-35465.patch b/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-35465.patch
deleted file mode 100644
index c7a7c76bf8..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-35465.patch
+++ /dev/null
@@ -1,103 +0,0 @@
-From 30461cf8dba3d3adb15a125e4da48800eb2b9b8f Mon Sep 17 00:00:00 2001
-From: Richard Earnshaw <rearnsha@arm.com>
-Date: Fri, 18 Jun 2021 17:18:37 +0100
-Subject: [PATCH] arm: fix vlldm erratum for Armv8.1-m [PR102035]
-
-For Armv8.1-m we generate code that emits VLLDM directly and do not
-rely on support code in the library, so emit the mitigation directly
-as well, when required. In this case, we can use the compiler options
-to determine when to apply the fix and when it is safe to omit it.
-
-gcc:
- PR target/102035
- * config/arm/arm.md (attribute arch): Add fix_vlldm.
- (arch_enabled): Use it.
- * config/arm/vfp.md (lazy_store_multiple_insn): Add alternative to
- use when erratum mitigation is needed.
-
-CVE: CVE-2021-35465
-Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=30461cf8dba3d3adb15a125e4da48800eb2b9b8f]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- gcc/config/arm/arm.md | 11 +++++++++--
- gcc/config/arm/vfp.md | 10 +++++++---
- 2 files changed, 16 insertions(+), 5 deletions(-)
-
-diff -upr a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
---- a/gcc/config/arm/arm.md 2020-07-22 23:35:17.344384552 -0700
-+++ b/gcc/config/arm/arm.md 2021-11-11 20:33:58.431543947 -0800
-@@ -132,9 +132,12 @@
- ; TARGET_32BIT, "t1" or "t2" to specify a specific Thumb mode. "v6"
- ; for ARM or Thumb-2 with arm_arch6, and nov6 for ARM without
- ; arm_arch6. "v6t2" for Thumb-2 with arm_arch6 and "v8mb" for ARMv8-M
--; Baseline. This attribute is used to compute attribute "enabled",
-+; Baseline. "fix_vlldm" is for fixing the v8-m/v8.1-m VLLDM erratum.
-+; This attribute is used to compute attribute "enabled",
- ; use type "any" to enable an alternative in all cases.
--(define_attr "arch" "any,a,t,32,t1,t2,v6,nov6,v6t2,v8mb,iwmmxt,iwmmxt2,armv6_or_vfpv3,neon,mve"
-+(define_attr "arch" "any, a, t, 32, t1, t2, v6,nov6, v6t2, \
-+ v8mb, fix_vlldm, iwmmxt, iwmmxt2, armv6_or_vfpv3, \
-+ neon, mve"
- (const_string "any"))
-
- (define_attr "arch_enabled" "no,yes"
-@@ -177,6 +180,10 @@
- (match_test "TARGET_THUMB1 && arm_arch8"))
- (const_string "yes")
-
-+ (and (eq_attr "arch" "fix_vlldm")
-+ (match_test "fix_vlldm"))
-+ (const_string "yes")
-+
- (and (eq_attr "arch" "iwmmxt2")
- (match_test "TARGET_REALLY_IWMMXT2"))
- (const_string "yes")
-diff -upr a/gcc/config/arm/vfp.md b/gcc/config/arm/vfp.md
---- a/gcc/config/arm/vfp.md 2020-07-22 23:35:17.356384684 -0700
-+++ b/gcc/config/arm/vfp.md 2021-11-11 20:33:58.431543947 -0800
-@@ -1703,12 +1703,15 @@
- (set_attr "type" "mov_reg")]
- )
-
-+;; Both this and the next instruction are treated by GCC in the same
-+;; way as a blockage pattern. That's perhaps stronger than it needs
-+;; to be, but we do not want accesses to the VFP register bank to be
-+;; moved across either instruction.
-+
- (define_insn "lazy_store_multiple_insn"
-- [(set (match_operand:SI 0 "s_register_operand" "+&rk")
-- (post_dec:SI (match_dup 0)))
-- (unspec_volatile [(const_int 0)
-- (mem:SI (post_dec:SI (match_dup 0)))]
-- VUNSPEC_VLSTM)]
-+ [(unspec_volatile
-+ [(mem:BLK (match_operand:SI 0 "s_register_operand" "rk"))]
-+ VUNSPEC_VLSTM)]
- "use_cmse && reload_completed"
- "vlstm%?\\t%0"
- [(set_attr "predicable" "yes")
-@@ -1716,14 +1719,16 @@
- )
-
- (define_insn "lazy_load_multiple_insn"
-- [(set (match_operand:SI 0 "s_register_operand" "+&rk")
-- (post_inc:SI (match_dup 0)))
-- (unspec_volatile:SI [(const_int 0)
-- (mem:SI (match_dup 0))]
-- VUNSPEC_VLLDM)]
-+ [(unspec_volatile
-+ [(mem:BLK (match_operand:SI 0 "s_register_operand" "rk,rk"))]
-+ VUNSPEC_VLLDM)]
- "use_cmse && reload_completed"
-- "vlldm%?\\t%0"
-- [(set_attr "predicable" "yes")
-+ "@
-+ vscclrm\\t{vpr}\;vlldm\\t%0
-+ vlldm\\t%0"
-+ [(set_attr "arch" "fix_vlldm,*")
-+ (set_attr "predicable" "no")
-+ (set_attr "length" "8,4")
- (set_attr "type" "load_4")]
- )
-
diff --git a/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch
deleted file mode 100644
index 2995a6fc61..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch
+++ /dev/null
@@ -1,142 +0,0 @@
-From 1a7f2c0774129750fdf73e9f1b78f0ce983c9ab3 Mon Sep 17 00:00:00 2001
-From: David Malcolm <dmalcolm@redhat.com>
-Date: Tue, 2 Nov 2021 09:54:32 -0400
-Subject: [PATCH] libcpp: escape non-ASCII source bytes in -Wbidi-chars=
- [PR103026]
-MIME-Version: 1.0
-Content-Type: text/plain; charset=utf8
-Content-Transfer-Encoding: 8bit
-
-This flags rich_locations associated with -Wbidi-chars= so that
-non-ASCII bytes will be escaped when printing the source lines
-(using the diagnostics support I added in
-r12-4825-gbd5e882cf6e0def3dd1bc106075d59a303fe0d1e).
-
-In particular, this ensures that the printed source lines will
-be pure ASCII, and thus the visual ordering of the characters
-will be the same as the logical ordering.
-
-Before:
-
- Wbidi-chars-1.c: In function âmainâ:
- Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 6 | /*â® } â¦if (isAdmin)⩠⦠begin admins only */
- | ^
- Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 9 | /* end admins only â® { â¦*/
- | ^
-
- Wbidi-chars-11.c:6:15: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 6 | int LRE_âª_PDF_\u202c;
- | ^
- Wbidi-chars-11.c:8:19: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 8 | int LRE_\u202a_PDF_â¬_;
- | ^
- Wbidi-chars-11.c:10:28: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 10 | const char *s1 = "LRE_âª_PDF_\u202c";
- | ^
- Wbidi-chars-11.c:12:33: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 12 | const char *s2 = "LRE_\u202a_PDF_â¬";
- | ^
-
-After:
-
- Wbidi-chars-1.c: In function âmainâ:
- Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
- | ^
- Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 9 | /* end admins only <U+202E> { <U+2066>*/
- | ^
-
- Wbidi-chars-11.c:6:15: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 6 | int LRE_<U+202A>_PDF_\u202c;
- | ^
- Wbidi-chars-11.c:8:19: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 8 | int LRE_\u202a_PDF_<U+202C>_;
- | ^
- Wbidi-chars-11.c:10:28: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 10 | const char *s1 = "LRE_<U+202A>_PDF_\u202c";
- | ^
- Wbidi-chars-11.c:12:33: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
- 12 | const char *s2 = "LRE_\u202a_PDF_<U+202C>";
- | ^
-
-libcpp/ChangeLog:
- PR preprocessor/103026
- * lex.c (maybe_warn_bidi_on_close): Use a rich_location
- and call set_escape_on_output (true) on it.
- (maybe_warn_bidi_on_char): Likewise.
-
-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=1a7f2c0774129750fdf73e9f1b78f0ce983c9ab3]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- libcpp/lex.c | 29 +++++++++++++++++------------
- 1 file changed, 17 insertions(+), 12 deletions(-)
-
-diff --git a/libcpp/lex.c b/libcpp/lex.c
-index 8188e33b07d..2421d6c0f40 100644
---- a/libcpp/lex.c
-+++ b/libcpp/lex.c
-@@ -1427,9 +1427,11 @@ maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
- const location_t loc
- = linemap_position_for_column (pfile->line_table,
- CPP_BUF_COLUMN (pfile->buffer, p));
-- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-- "unpaired UTF-8 bidirectional control character "
-- "detected");
-+ rich_location rich_loc (pfile->line_table, loc);
-+ rich_loc.set_escape_on_output (true);
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "unpaired UTF-8 bidirectional control character "
-+ "detected");
- }
- /* We're done with this context. */
- bidi::on_close ();
-@@ -1454,6 +1456,9 @@ maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
- const location_t loc
- = linemap_position_for_column (pfile->line_table,
- CPP_BUF_COLUMN (pfile->buffer, p));
-+ rich_location rich_loc (pfile->line_table, loc);
-+ rich_loc.set_escape_on_output (true);
-+
- /* It seems excessive to warn about a PDI/PDF that is closing
- an opened context because we've already warned about the
- opening character. Except warn when we have a UCN x UTF-8
-@@ -1462,20 +1467,20 @@ maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
- {
- if (warn_bidi == bidirectional_unpaired
- && bidi::current_ctx_ucn_p () != ucn_p)
-- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-- "UTF-8 vs UCN mismatch when closing "
-- "a context by \"%s\"", bidi::to_str (kind));
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "UTF-8 vs UCN mismatch when closing "
-+ "a context by \"%s\"", bidi::to_str (kind));
- }
- else if (warn_bidi == bidirectional_any)
- {
- if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
-- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-- "\"%s\" is closing an unopened context",
-- bidi::to_str (kind));
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "\"%s\" is closing an unopened context",
-+ bidi::to_str (kind));
- else
-- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
-- "found problematic Unicode character \"%s\"",
-- bidi::to_str (kind));
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "found problematic Unicode character \"%s\"",
-+ bidi::to_str (kind));
- }
- }
- /* We're done with this context. */
---
-2.27.0
-
diff --git a/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-35465.patch b/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-35465.patch
deleted file mode 100644
index 9dd6a313c2..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-35465.patch
+++ /dev/null
@@ -1,304 +0,0 @@
-From 809330ab8450261e05919b472783bf15e4b000f7 Mon Sep 17 00:00:00 2001
-From: Richard Earnshaw <rearnsha@arm.com>
-Date: Tue, 6 Jul 2021 15:10:18 +0100
-Subject: [PATCH] arm: Add tests for VLLDM mitigation [PR102035]
-
-New tests for the erratum mitigation.
-
-gcc/testsuite:
- PR target/102035
- * gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c: New test.
- * gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c: Likewise.
- * gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c: Likewise.
-
-CVE: CVE-2021-35465
-Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=809330ab8450261e05919b472783bf15e4b000f7]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- .../arm/cmse/mainline/8_1m/soft/cmse-13a.c | 31 +++++++++++++++++++
- .../arm/cmse/mainline/8_1m/soft/cmse-7a.c | 28 +++++++++++++++++
- .../arm/cmse/mainline/8_1m/soft/cmse-8a.c | 30 ++++++++++++++++++
- .../cmse/mainline/8_1m/softfp-sp/cmse-7a.c | 27 ++++++++++++++++
- .../cmse/mainline/8_1m/softfp-sp/cmse-8a.c | 29 +++++++++++++++++
- .../arm/cmse/mainline/8_1m/softfp/cmse-13a.c | 30 ++++++++++++++++++
- .../arm/cmse/mainline/8_1m/softfp/cmse-7a.c | 27 ++++++++++++++++
- .../arm/cmse/mainline/8_1m/softfp/cmse-8a.c | 29 +++++++++++++++++
- 8 files changed, 231 insertions(+)
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c
- create mode 100644 gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c
-
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-13a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,31 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=soft -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=soft" } } */
-+
-+#include "../../../cmse-13.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[1,4-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[1,4-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r1, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[1,4-9\]|r10|fp|ip), ){9}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[1,4-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler-not "vmov" } } */
-+/* { dg-final { scan-assembler-not "vmsr" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-7a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,28 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=soft -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=soft" } } */
-+
-+#include "../../../cmse-7.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r0, )?(r1, )?(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[0-9\]|r10|fp|ip), ){12}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[0-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler-not "vmov" } } */
-+/* { dg-final { scan-assembler-not "vmsr" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/soft/cmse-8a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,30 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=soft -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=soft" } } */
-+
-+#include "../../../cmse-8.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[2-9\]|r10|fp|ip), ){10}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[2-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler-not "vmov" } } */
-+/* { dg-final { scan-assembler-not "vmsr" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-13a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,30 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-d16 -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=softfp" } } */
-+/* { dg-skip-if "Skip these if testing single precision" {*-*-*} {"-mfpu=*-sp-*"} {""} } */
-+
-+#include "../../../cmse-13.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[1,4-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[1,4-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr2, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr3, r4" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r1, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[1,4-9\]|r10|fp|ip), ){9}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[1,4-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-7a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,27 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-d16 -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=softfp" } } */
-+/* { dg-skip-if "Skip these if testing single precision" {*-*-*} {"-mfpu=*-sp-*"} {""} } */
-+
-+#include "../../../cmse-7.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r0, )?(r1, )?(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[0-9\]|r10|fp|ip), ){12}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[0-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp/cmse-8a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,29 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-d16 -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=softfp" } } */
-+/* { dg-skip-if "Skip these if testing single precision" {*-*-*} {"-mfpu=*-sp-*"} {""} } */
-+
-+#include "../../../cmse-8.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[2-9\]|r10|fp|ip), ){10}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[2-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-7a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,27 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-sp-d16 -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=softfp" } } */
-+/* { dg-skip-if "Skip these if testing double precision" {*-*-*} {"-mfpu=fpv[4-5]-d16"} {""} } */
-+
-+#include "../../../cmse-7.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[0-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r0, )?(r1, )?(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[0-9\]|r10|fp|ip), ){12}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[0-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
-diff --git a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c
---- a/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c 1969-12-31 16:00:00.000000000 -0800
-+++ b/gcc/testsuite/gcc.target/arm/cmse/mainline/8_1m/softfp-sp/cmse-8a.c 2021-11-15 02:30:37.210637445 -0800
-@@ -0,0 +1,29 @@
-+/* { dg-do compile } */
-+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-sp-d16 -mfix-cmse-cve-2021-35465" } */
-+/* { dg-skip-if "Incompatible float ABI" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=softfp" } } */
-+/* { dg-skip-if "Skip these if testing double precision" {*-*-*} {"-mfpu=fpv[4-5]-d16"} {""} } */
-+
-+#include "../../../cmse-8.x"
-+
-+/* Checks for saving and clearing prior to function call. */
-+/* Shift on the same register as blxns. */
-+/* { dg-final { scan-assembler "lsrs\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler "lsls\t(r\[2-9\]|r10|fp|ip), \\1, #1.*blxns\t\\1" } } */
-+/* { dg-final { scan-assembler-not "mov\tr0, r4" } } */
-+/* { dg-final { scan-assembler-not "mov\tr1, r4" } } */
-+/* { dg-final { scan-assembler "push\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+/* { dg-final { scan-assembler "vlstm\tsp" } } */
-+/* Check the right registers are cleared and none appears twice. */
-+/* { dg-final { scan-assembler "clrm\t\{(r2, )?(r3, )?(r4, )?(r5, )?(r6, )?(r7, )?(r8, )?(r9, )?(r10, )?(fp, )?(ip, )?APSR\}" } } */
-+/* Check that the right number of registers is cleared and thus only one
-+ register is missing. */
-+/* { dg-final { scan-assembler "clrm\t\{((r\[2-9\]|r10|fp|ip), ){10}APSR\}" } } */
-+/* Check that no cleared register is used for blxns. */
-+/* { dg-final { scan-assembler-not "clrm\t\{\[^\}\]\+(r\[2-9\]|r10|fp|ip),\[^\}\]\+\}.*blxns\t\\1" } } */
-+/* Check for v8.1-m variant of erratum work-around. */
-+/* { dg-final { scan-assembler "vscclrm\t\{vpr\}" } } */
-+/* { dg-final { scan-assembler "vlldm\tsp" } } */
-+/* { dg-final { scan-assembler "pop\t\{r4, r5, r6, r7, r8, r9, r10, fp\}" } } */
-+
-+/* Now we check that we use the correct intrinsic to call. */
-+/* { dg-final { scan-assembler "blxns" } } */
diff --git a/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch
deleted file mode 100644
index 4999c71b64..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch
+++ /dev/null
@@ -1,573 +0,0 @@
-From bef32d4a28595e933f24fef378cf052a30b674a7 Mon Sep 17 00:00:00 2001
-From: David Malcolm <dmalcolm@redhat.com>
-Date: Tue, 2 Nov 2021 15:45:22 -0400
-Subject: [PATCH] libcpp: capture and underline ranges in -Wbidi-chars=
- [PR103026]
-MIME-Version: 1.0
-Content-Type: text/plain; charset=utf8
-Content-Transfer-Encoding: 8bit
-
-This patch converts the bidi::vec to use a struct so that we can
-capture location_t values for the bidirectional control characters.
-
-Before:
-
- Wbidi-chars-1.c: In function âmainâ:
- Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
- | ^
- Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
- 9 | /* end admins only <U+202E> { <U+2066>*/
- | ^
-
-After:
-
- Wbidi-chars-1.c: In function âmainâ:
- Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
- 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
- | ~~~~~~~~ ~~~~~~~~ ^
- | | | |
- | | | end of bidirectional context
- | U+202E (RIGHT-TO-LEFT OVERRIDE) U+2066 (LEFT-TO-RIGHT ISOLATE)
- Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
- 9 | /* end admins only <U+202E> { <U+2066>*/
- | ~~~~~~~~ ~~~~~~~~ ^
- | | | |
- | | | end of bidirectional context
- | | U+2066 (LEFT-TO-RIGHT ISOLATE)
- | U+202E (RIGHT-TO-LEFT OVERRIDE)
-
-Signed-off-by: David Malcolm <dmalcolm@redhat.com>
-
-gcc/testsuite/ChangeLog:
- PR preprocessor/103026
- * c-c++-common/Wbidi-chars-ranges.c: New test.
-
-libcpp/ChangeLog:
- PR preprocessor/103026
- * lex.c (struct bidi::context): New.
- (bidi::vec): Convert to a vec of context rather than unsigned
- char.
- (bidi::ctx_at): Rename to...
- (bidi::pop_kind_at): ...this and reimplement for above change.
- (bidi::current_ctx): Update for change to vec.
- (bidi::current_ctx_ucn_p): Likewise.
- (bidi::current_ctx_loc): New.
- (bidi::on_char): Update for usage of context struct. Add "loc"
- param and pass it when pushing contexts.
- (get_location_for_byte_range_in_cur_line): New.
- (get_bidi_utf8): Rename to...
- (get_bidi_utf8_1): ...this, reintroducing...
- (get_bidi_utf8): ...as a wrapper, setting *OUT when the result is
- not NONE.
- (get_bidi_ucn): Rename to...
- (get_bidi_ucn_1): ...this, reintroducing...
- (get_bidi_ucn): ...as a wrapper, setting *OUT when the result is
- not NONE.
- (class unpaired_bidi_rich_location): New.
- (maybe_warn_bidi_on_close): Use unpaired_bidi_rich_location when
- reporting on unpaired bidi chars. Split into singular vs plural
- spellings.
- (maybe_warn_bidi_on_char): Pass in a location_t rather than a
- const uchar * and use it when emitting warnings, and when calling
- bidi::on_char.
- (_cpp_skip_block_comment): Capture location when kind is not NONE
- and pass it to maybe_warn_bidi_on_char.
- (skip_line_comment): Likewise.
- (forms_identifier_p): Likewise.
- (lex_raw_string): Likewise.
- (lex_string): Likewise.
-
-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=bef32d4a28595e933f24fef378cf052a30b674a7]
-Signed-off-by: Pgowda <pgowda.cve@gmail.com>
-
----
- .../c-c++-common/Wbidi-chars-ranges.c | 54 ++++
- libcpp/lex.c | 251 ++++++++++++++----
- 2 files changed, 257 insertions(+), 48 deletions(-)
- create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
-
-diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
-new file mode 100644
-index 00000000000..298750a2a64
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
-@@ -0,0 +1,54 @@
-+/* PR preprocessor/103026 */
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidi-chars=unpaired -fdiagnostics-show-caret" } */
-+/* Verify that we escape and underline pertinent bidirectional
-+ control characters when quoting the source. */
-+
-+int test_unpaired_bidi () {
-+ int isAdmin = 0;
-+ /*â® } â¦if (isAdmin)⩠⦠begin admins only */
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+#if 0
-+ { dg-begin-multiline-output "" }
-+ /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
-+ ~~~~~~~~ ~~~~~~~~ ^
-+ | | |
-+ | | end of bidirectional context
-+ U+202E (RIGHT-TO-LEFT OVERRIDE) U+2066 (LEFT-TO-RIGHT ISOLATE)
-+ { dg-end-multiline-output "" }
-+#endif
-+
-+ __builtin_printf("You are an admin.\n");
-+ /* end admins only â® { â¦*/
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+#if 0
-+ { dg-begin-multiline-output "" }
-+ /* end admins only <U+202E> { <U+2066>*/
-+ ~~~~~~~~ ~~~~~~~~ ^
-+ | | |
-+ | | end of bidirectional context
-+ | U+2066 (LEFT-TO-RIGHT ISOLATE)
-+ U+202E (RIGHT-TO-LEFT OVERRIDE)
-+ { dg-end-multiline-output "" }
-+#endif
-+
-+ return 0;
-+}
-+
-+int LRE_âª_PDF_\u202c;
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+#if 0
-+ { dg-begin-multiline-output "" }
-+ int LRE_<U+202A>_PDF_\u202c;
-+ ~~~~~~~~ ^~~~~~
-+ { dg-end-multiline-output "" }
-+#endif
-+
-+const char *s1 = "LRE_âª_PDF_\u202c";
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+#if 0
-+ { dg-begin-multiline-output "" }
-+ const char *s1 = "LRE_<U+202A>_PDF_\u202c";
-+ ~~~~~~~~ ^~~~~~
-+ { dg-end-multiline-output "" }
-+#endif
-diff --git a/libcpp/lex.c b/libcpp/lex.c
-index 2421d6c0f40..94c36f0d014 100644
---- a/libcpp/lex.c
-+++ b/libcpp/lex.c
-@@ -1172,11 +1172,34 @@ namespace bidi {
- /* All the UTF-8 encodings of bidi characters start with E2. */
- constexpr uchar utf8_start = 0xe2;
-
-+ struct context
-+ {
-+ context () {}
-+ context (location_t loc, kind k, bool pdf, bool ucn)
-+ : m_loc (loc), m_kind (k), m_pdf (pdf), m_ucn (ucn)
-+ {
-+ }
-+
-+ kind get_pop_kind () const
-+ {
-+ return m_pdf ? kind::PDF : kind::PDI;
-+ }
-+ bool ucn_p () const
-+ {
-+ return m_ucn;
-+ }
-+
-+ location_t m_loc;
-+ kind m_kind;
-+ unsigned m_pdf : 1;
-+ unsigned m_ucn : 1;
-+ };
-+
- /* A vector holding currently open bidi contexts. We use a char for
- each context, its LSB is 1 if it represents a PDF context, 0 if it
- represents a PDI context. The next bit is 1 if this context was open
- by a bidi character written as a UCN, and 0 when it was UTF-8. */
-- semi_embedded_vec <unsigned char, 16> vec;
-+ semi_embedded_vec <context, 16> vec;
-
- /* Close the whole comment/identifier/string literal/character constant
- context. */
-@@ -1193,19 +1216,19 @@ namespace bidi {
- vec.truncate (len - 1);
- }
-
-- /* Return the context of the Ith element. */
-- kind ctx_at (unsigned int i)
-+ /* Return the pop kind of the context of the Ith element. */
-+ kind pop_kind_at (unsigned int i)
- {
-- return (vec[i] & 1) ? kind::PDF : kind::PDI;
-+ return vec[i].get_pop_kind ();
- }
-
-- /* Return which context is currently opened. */
-+ /* Return the pop kind of the context that is currently opened. */
- kind current_ctx ()
- {
- unsigned int len = vec.count ();
- if (len == 0)
- return kind::NONE;
-- return ctx_at (len - 1);
-+ return vec[len - 1].get_pop_kind ();
- }
-
- /* Return true if the current context comes from a UCN origin, that is,
-@@ -1214,11 +1237,19 @@ namespace bidi {
- {
- unsigned int len = vec.count ();
- gcc_checking_assert (len > 0);
-- return (vec[len - 1] >> 1) & 1;
-+ return vec[len - 1].m_ucn;
- }
-
-- /* We've read a bidi char, update the current vector as necessary. */
-- void on_char (kind k, bool ucn_p)
-+ location_t current_ctx_loc ()
-+ {
-+ unsigned int len = vec.count ();
-+ gcc_checking_assert (len > 0);
-+ return vec[len - 1].m_loc;
-+ }
-+
-+ /* We've read a bidi char, update the current vector as necessary.
-+ LOC is only valid when K is not kind::NONE. */
-+ void on_char (kind k, bool ucn_p, location_t loc)
- {
- switch (k)
- {
-@@ -1226,12 +1257,12 @@ namespace bidi {
- case kind::RLE:
- case kind::LRO:
- case kind::RLO:
-- vec.push (ucn_p ? 3u : 1u);
-+ vec.push (context (loc, k, true, ucn_p));
- break;
- case kind::LRI:
- case kind::RLI:
- case kind::FSI:
-- vec.push (ucn_p ? 2u : 0u);
-+ vec.push (context (loc, k, false, ucn_p));
- break;
- /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
- whose scope has not yet been terminated. */
-@@ -1245,7 +1276,7 @@ namespace bidi {
- yet been terminated. */
- case kind::PDI:
- for (int i = vec.count () - 1; i >= 0; --i)
-- if (ctx_at (i) == kind::PDI)
-+ if (pop_kind_at (i) == kind::PDI)
- {
- vec.truncate (i);
- break;
-@@ -1295,10 +1326,47 @@ namespace bidi {
- }
- }
-
-+/* Get location_t for the range of bytes [START, START + NUM_BYTES)
-+ within the current line in FILE, with the caret at START. */
-+
-+static location_t
-+get_location_for_byte_range_in_cur_line (cpp_reader *pfile,
-+ const unsigned char *const start,
-+ size_t num_bytes)
-+{
-+ gcc_checking_assert (num_bytes > 0);
-+
-+ /* CPP_BUF_COLUMN and linemap_position_for_column both refer
-+ to offsets in bytes, but CPP_BUF_COLUMN is 0-based,
-+ whereas linemap_position_for_column is 1-based. */
-+
-+ /* Get 0-based offsets within the line. */
-+ size_t start_offset = CPP_BUF_COLUMN (pfile->buffer, start);
-+ size_t end_offset = start_offset + num_bytes - 1;
-+
-+ /* Now convert to location_t, where "columns" are 1-based byte offsets. */
-+ location_t start_loc = linemap_position_for_column (pfile->line_table,
-+ start_offset + 1);
-+ location_t end_loc = linemap_position_for_column (pfile->line_table,
-+ end_offset + 1);
-+
-+ if (start_loc == end_loc)
-+ return start_loc;
-+
-+ source_range src_range;
-+ src_range.m_start = start_loc;
-+ src_range.m_finish = end_loc;
-+ location_t combined_loc = COMBINE_LOCATION_DATA (pfile->line_table,
-+ start_loc,
-+ src_range,
-+ NULL);
-+ return combined_loc;
-+}
-+
- /* Parse a sequence of 3 bytes starting with P and return its bidi code. */
-
- static bidi::kind
--get_bidi_utf8 (const unsigned char *const p)
-+get_bidi_utf8_1 (const unsigned char *const p)
- {
- gcc_checking_assert (p[0] == bidi::utf8_start);
-
-@@ -1340,10 +1408,25 @@ get_bidi_utf8 (const unsigned char *cons
- return bidi::kind::NONE;
- }
-
-+/* Parse a sequence of 3 bytes starting with P and return its bidi code.
-+ If the kind is not NONE, write the location to *OUT.*/
-+
-+static bidi::kind
-+get_bidi_utf8 (cpp_reader *pfile, const unsigned char *const p, location_t *out)
-+{
-+ bidi::kind result = get_bidi_utf8_1 (p);
-+ if (result != bidi::kind::NONE)
-+ {
-+ /* We have a sequence of 3 bytes starting at P. */
-+ *out = get_location_for_byte_range_in_cur_line (pfile, p, 3);
-+ }
-+ return result;
-+}
-+
- /* Parse a UCN where P points just past \u or \U and return its bidi code. */
-
- static bidi::kind
--get_bidi_ucn (const unsigned char *p, bool is_U)
-+get_bidi_ucn_1 (const unsigned char *p, bool is_U)
- {
- /* 6.4.3 Universal Character Names
- \u hex-quad
-@@ -1412,6 +1495,62 @@ get_bidi_ucn (const unsigned char *p, bo
- return bidi::kind::NONE;
- }
-
-+/* Parse a UCN where P points just past \u or \U and return its bidi code.
-+ If the kind is not NONE, write the location to *OUT.*/
-+
-+static bidi::kind
-+get_bidi_ucn (cpp_reader *pfile, const unsigned char *p, bool is_U,
-+ location_t *out)
-+{
-+ bidi::kind result = get_bidi_ucn_1 (p, is_U);
-+ if (result != bidi::kind::NONE)
-+ {
-+ const unsigned char *start = p - 2;
-+ size_t num_bytes = 2 + (is_U ? 8 : 4);
-+ *out = get_location_for_byte_range_in_cur_line (pfile, start, num_bytes);
-+ }
-+ return result;
-+}
-+
-+/* Subclass of rich_location for reporting on unpaired UTF-8
-+ bidirectional control character(s).
-+ Escape the source lines on output, and show all unclosed
-+ bidi context, labelling everything. */
-+
-+class unpaired_bidi_rich_location : public rich_location
-+{
-+ public:
-+ class custom_range_label : public range_label
-+ {
-+ public:
-+ label_text get_text (unsigned range_idx) const FINAL OVERRIDE
-+ {
-+ /* range 0 is the primary location; each subsequent range i + 1
-+ is for bidi::vec[i]. */
-+ if (range_idx > 0)
-+ {
-+ const bidi::context &ctxt (bidi::vec[range_idx - 1]);
-+ return label_text::borrow (bidi::to_str (ctxt.m_kind));
-+ }
-+ else
-+ return label_text::borrow (_("end of bidirectional context"));
-+ }
-+ };
-+
-+ unpaired_bidi_rich_location (cpp_reader *pfile, location_t loc)
-+ : rich_location (pfile->line_table, loc, &m_custom_label)
-+ {
-+ set_escape_on_output (true);
-+ for (unsigned i = 0; i < bidi::vec.count (); i++)
-+ add_range (bidi::vec[i].m_loc,
-+ SHOW_RANGE_WITHOUT_CARET,
-+ &m_custom_label);
-+ }
-+
-+ private:
-+ custom_range_label m_custom_label;
-+};
-+
- /* We're closing a bidi context, that is, we've encountered a newline,
- are closing a C-style comment, or are at the end of a string literal,
- character constant, or identifier. Warn if this context was not
-@@ -1427,11 +1566,17 @@ maybe_warn_bidi_on_close (cpp_reader *pf
- const location_t loc
- = linemap_position_for_column (pfile->line_table,
- CPP_BUF_COLUMN (pfile->buffer, p));
-- rich_location rich_loc (pfile->line_table, loc);
-- rich_loc.set_escape_on_output (true);
-- cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-- "unpaired UTF-8 bidirectional control character "
-- "detected");
-+ unpaired_bidi_rich_location rich_loc (pfile, loc);
-+ /* cpp_callbacks doesn't yet have a way to handle singular vs plural
-+ forms of a diagnostic, so fake it for now. */
-+ if (bidi::vec.count () > 1)
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "unpaired UTF-8 bidirectional control characters "
-+ "detected");
-+ else
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "unpaired UTF-8 bidirectional control character "
-+ "detected");
- }
- /* We're done with this context. */
- bidi::on_close ();
-@@ -1439,12 +1584,13 @@ maybe_warn_bidi_on_close (cpp_reader *pf
-
- /* We're at the beginning or in the middle of an identifier/comment/string
- literal/character constant. Warn if we've encountered a bidi character.
-- KIND says which bidi character it was; P points to it in the character
-- stream. UCN_P is true iff this bidi character was written as a UCN. */
-+ KIND says which bidi control character it was; UCN_P is true iff this bidi
-+ control character was written as a UCN. LOC is the location of the
-+ character, but is only valid if KIND != bidi::kind::NONE. */
-
- static void
--maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
-- bool ucn_p)
-+maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
-+ bool ucn_p, location_t loc)
- {
- if (__builtin_expect (kind == bidi::kind::NONE, 1))
- return;
-@@ -1453,9 +1599,6 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
-
- if (warn_bidi != bidirectional_none)
- {
-- const location_t loc
-- = linemap_position_for_column (pfile->line_table,
-- CPP_BUF_COLUMN (pfile->buffer, p));
- rich_location rich_loc (pfile->line_table, loc);
- rich_loc.set_escape_on_output (true);
-
-@@ -1467,9 +1610,12 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
- {
- if (warn_bidi == bidirectional_unpaired
- && bidi::current_ctx_ucn_p () != ucn_p)
-- cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-- "UTF-8 vs UCN mismatch when closing "
-- "a context by \"%s\"", bidi::to_str (kind));
-+ {
-+ rich_loc.add_range (bidi::current_ctx_loc ());
-+ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
-+ "UTF-8 vs UCN mismatch when closing "
-+ "a context by \"%s\"", bidi::to_str (kind));
-+ }
- }
- else if (warn_bidi == bidirectional_any)
- {
-@@ -1484,7 +1630,7 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
- }
- }
- /* We're done with this context. */
-- bidi::on_char (kind, ucn_p);
-+ bidi::on_char (kind, ucn_p, loc);
- }
-
- /* Skip a C-style block comment. We find the end of the comment by
-@@ -1552,8 +1698,9 @@ _cpp_skip_block_comment (cpp_reader *pfi
- a bidirectional control character. */
- else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
- {
-- bidi::kind kind = get_bidi_utf8 (cur - 1);
-- maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/false);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
- }
- }
-
-@@ -1586,9 +1733,9 @@ skip_line_comment (cpp_reader *pfile)
- {
- if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
- {
-- bidi::kind kind = get_bidi_utf8 (buffer->cur);
-- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-- /*ucn_p=*/false);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
- }
- buffer->cur++;
- }
-@@ -1708,9 +1855,9 @@ forms_identifier_p (cpp_reader *pfile, i
- if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
- && warn_bidi_p)
- {
-- bidi::kind kind = get_bidi_utf8 (buffer->cur);
-- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-- /*ucn_p=*/false);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
- }
- if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
- state, &s))
-@@ -1722,10 +1869,12 @@ forms_identifier_p (cpp_reader *pfile, i
- buffer->cur += 2;
- if (warn_bidi_p)
- {
-- bidi::kind kind = get_bidi_ucn (buffer->cur,
-- buffer->cur[-1] == 'U');
-- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
-- /*ucn_p=*/true);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_ucn (pfile,
-+ buffer->cur,
-+ buffer->cur[-1] == 'U',
-+ &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
- }
- if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
- state, &s, NULL, NULL))
-@@ -2336,8 +2485,11 @@ lex_raw_string (cpp_reader *pfile, cpp_t
- }
- else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0)
- && warn_bidi_p)
-- maybe_warn_bidi_on_char (pfile, pos - 1, get_bidi_utf8 (pos - 1),
-- /*ucn_p=*/false);
-+ {
-+ location_t loc;
-+ bidi::kind kind = get_bidi_utf8 (pfile, pos - 1, &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
-+ }
- }
-
- if (warn_bidi_p)
-@@ -2447,8 +2599,10 @@ lex_string (cpp_reader *pfile, cpp_token
- {
- if ((cur[0] == 'u' || cur[0] == 'U') && warn_bidi_p)
- {
-- bidi::kind kind = get_bidi_ucn (cur + 1, cur[0] == 'U');
-- maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/true);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_ucn (pfile, cur + 1, cur[0] == 'U',
-+ &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
- }
- cur++;
- }
-@@ -2476,8 +2630,9 @@ lex_string (cpp_reader *pfile, cpp_token
- saw_NUL = true;
- else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
- {
-- bidi::kind kind = get_bidi_utf8 (cur - 1);
-- maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false);
-+ location_t loc;
-+ bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
-+ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
- }
- }
-
diff --git a/meta/recipes-devtools/gcc/gcc/0009-cpp-honor-sysroot.patch b/meta/recipes-devtools/gcc/gcc/0009-cpp-honor-sysroot.patch
index 37f26f0728..1c0f381859 100644
--- a/meta/recipes-devtools/gcc/gcc/0009-cpp-honor-sysroot.patch
+++ b/meta/recipes-devtools/gcc/gcc/0009-cpp-honor-sysroot.patch
@@ -22,13 +22,14 @@ gcc/ChangeLog:
* gcc.c: Pass sysroot options to cpp for preprocessed source
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
[YOCTO #2074]
Upstream-Status: Submitted [https://gcc.gnu.org/pipermail/gcc-patches/2021-October/582725.html]
---
gcc/cp/lang-specs.h | 2 +-
- gcc/gcc.c | 2 +-
+ gcc/gcc.cc | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
Index: gcc-11.2.0/gcc/cp/lang-specs.h
@@ -44,10 +45,10 @@ Index: gcc-11.2.0/gcc/cp/lang-specs.h
" %{!fsyntax-only:"
" %{fmodule-only:%{!S:-o %g.s%V}}"
" %{!fmodule-only:%{!fmodule-header*:%(invoke_as)}}}"
-Index: gcc-11.2.0/gcc/gcc.c
+Index: gcc-11.2.0/gcc/gcc.cc
===================================================================
---- gcc-11.2.0.orig/gcc/gcc.c
-+++ gcc-11.2.0/gcc/gcc.c
+--- gcc-11.2.0.orig/gcc/gcc.cc
++++ gcc-11.2.0/gcc/gcc.cc
@@ -1470,7 +1470,7 @@ static const struct compiler default_com
%W{o*:--output-pch=%*}}%V}}}}}}}", 0, 0, 0},
{".i", "@cpp-output", 0, 0, 0},
diff --git a/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch b/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch
deleted file mode 100644
index ebee30bbd6..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch
+++ /dev/null
@@ -1,38 +0,0 @@
-From: Richard Purdie <richard.purdie@linuxfoundation.org>
-Subject: [PATCH 2/5] gcc: Fix "argument list too long" from install-plugins
-
-When building in longer build paths (200+ characters), the
-"echo $(PLUGIN_HEADERS)" from the install-plugins target would cause an
-"argument list too long error" on some systems.
-
-Avoid this by calling make's sort function on the list which removes
-duplicates and stops the overflow from reaching the echo command.
-The original sort is left to handle the the .h and .def files.
-
-2021-10-26 Richard Purdie <richard.purdie@linuxfoundation.org>
-
-gcc/ChangeLog:
-
- * Makefile.in: Fix "argument list too long" from install-plugins
-
-Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
-
-Submitted [https://gcc.gnu.org/pipermail/gcc-patches/2021-October/582722.html]
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=66e157188bd2f789809e17e85f917534c9381599]
----
- gcc/Makefile.in | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-Index: gcc-11.2.0/gcc/Makefile.in
-===================================================================
---- gcc-11.2.0.orig/gcc/Makefile.in
-+++ gcc-11.2.0/gcc/Makefile.in
-@@ -3678,7 +3678,7 @@ install-plugin: installdirs lang.install
- # We keep the directory structure for files in config, common/config or
- # c-family and .def files. All other files are flattened to a single directory.
- $(mkinstalldirs) $(DESTDIR)$(plugin_includedir)
-- headers=`echo $(PLUGIN_HEADERS) $$(cd $(srcdir); echo *.h *.def) | tr ' ' '\012' | sort -u`; \
-+ headers=`echo $(sort $(PLUGIN_HEADERS)) $$(cd $(srcdir); echo *.h *.def) | tr ' ' '\012' | sort -u`; \
- srcdirstrip=`echo "$(srcdir)" | sed 's/[].[^$$\\*|]/\\\\&/g'`; \
- for file in $$headers; do \
- if [ -f $$file ] ; then \
diff --git a/meta/recipes-devtools/gcc/gcc/0018-export-CPP.patch b/meta/recipes-devtools/gcc/gcc/0018-export-CPP.patch
deleted file mode 100644
index 86ab6574c7..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0018-export-CPP.patch
+++ /dev/null
@@ -1,199 +0,0 @@
-From: Richard Purdie <richard.purdie@linuxfoundation.org>
-Subject: [PATCH 1/5] Makefile.in: Ensure build CPP/CPPFLAGS is used for build targets
-
-During cross compiling, CPP is being set to the target compiler even for
-build targets. As an example, when building a cross compiler targetting
-mingw, the config.log for libiberty in
-build.x86_64-pokysdk-mingw32.i586-poky-linux/build-x86_64-linux/libiberty/config.log
-shows:
-
-configure:3786: checking how to run the C preprocessor
-configure:3856: result: x86_64-pokysdk-mingw32-gcc -E --sysroot=[sysroot]/x86_64-nativesdk-mingw32-pokysdk-mingw32
-configure:3876: x86_64-pokysdk-mingw32-gcc -E --sysroot=[sysroot]/x86_64-nativesdk-mingw32-pokysdk-mingw32 conftest.c
-configure:3876: $? = 0
-
-This is libiberty being built for the build environment, not the target one
-(i.e. in build-x86_64-linux). As such it should be using the build environment's
-gcc and not the target one. In the mingw case the system headers are quite
-different leading to build failures related to not being able to include a
-process.h file for pem-unix.c.
-
-Further analysis shows the same issue occuring for CPPFLAGS too.
-
-Fix this by adding support for CPP_FOR_BUILD and CPPFLAGS_FOR_BUILD which
-for example, avoids mixing the mingw headers for host binaries on linux
-systems.
-
-2021-10-27 Richard Purdie <richard.purdie@linuxfoundation.org>
-
-ChangeLog:
-
- * Makefile.tpl: Add CPP_FOR_BUILD and CPPFLAGS_FOR_BUILD support
- * Makefile.in: Regenerate.
- * configure: Regenerate.
- * configure.ac: Add CPP_FOR_BUILD and CPPFLAGS_FOR_BUILD support
-
-gcc/ChangeLog:
-
- * configure: Regenerate.
- * configure.ac: Use CPPFLAGS_FOR_BUILD for GMPINC
-
-Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
-
-Submitted [https://gcc.gnu.org/pipermail/gcc-patches/2021-October/582727.html]
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commitdiff;h=84401ce5fb4ecab55decb472b168100e7593e01f]
----
- Makefile.in | 6 ++++++
- Makefile.tpl | 6 ++++++
- configure | 4 ++++
- configure.ac | 4 ++++
- gcc/configure | 2 +-
- gcc/configure.ac | 2 +-
- 6 files changed, 22 insertions(+), 2 deletions(-)
-
-Index: gcc-11.2.0/Makefile.in
-===================================================================
---- gcc-11.2.0.orig/Makefile.in
-+++ gcc-11.2.0/Makefile.in
-@@ -151,6 +151,8 @@ BUILD_EXPORTS = \
- CC="$(CC_FOR_BUILD)"; export CC; \
- CFLAGS="$(CFLAGS_FOR_BUILD)"; export CFLAGS; \
- CONFIG_SHELL="$(SHELL)"; export CONFIG_SHELL; \
-+ CPP="$(CPP_FOR_BUILD)"; export CPP; \
-+ CPPFLAGS="$(CPPFLAGS_FOR_BUILD)"; export CPPFLAGS; \
- CXX="$(CXX_FOR_BUILD)"; export CXX; \
- CXXFLAGS="$(CXXFLAGS_FOR_BUILD)"; export CXXFLAGS; \
- GFORTRAN="$(GFORTRAN_FOR_BUILD)"; export GFORTRAN; \
-@@ -198,6 +200,8 @@ HOST_EXPORTS = \
- AR="$(AR)"; export AR; \
- AS="$(AS)"; export AS; \
- CC_FOR_BUILD="$(CC_FOR_BUILD)"; export CC_FOR_BUILD; \
-+ CPP_FOR_BUILD="$(CPP_FOR_BUILD)"; export CPP_FOR_BUILD; \
-+ CPPFLAGS_FOR_BUILD="$(CPPFLAGS_FOR_BUILD)"; export CPPFLAGS_FOR_BUILD; \
- CXX_FOR_BUILD="$(CXX_FOR_BUILD)"; export CXX_FOR_BUILD; \
- DLLTOOL="$(DLLTOOL)"; export DLLTOOL; \
- LD="$(LD)"; export LD; \
-@@ -353,6 +357,8 @@ AR_FOR_BUILD = @AR_FOR_BUILD@
- AS_FOR_BUILD = @AS_FOR_BUILD@
- CC_FOR_BUILD = @CC_FOR_BUILD@
- CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@
-+CPP_FOR_BUILD = @CPP_FOR_BUILD@
-+CPPFLAGS_FOR_BUILD = @CPPFLAGS_FOR_BUILD@
- CXXFLAGS_FOR_BUILD = @CXXFLAGS_FOR_BUILD@
- CXX_FOR_BUILD = @CXX_FOR_BUILD@
- DLLTOOL_FOR_BUILD = @DLLTOOL_FOR_BUILD@
-Index: gcc-11.2.0/Makefile.tpl
-===================================================================
---- gcc-11.2.0.orig/Makefile.tpl
-+++ gcc-11.2.0/Makefile.tpl
-@@ -154,6 +154,8 @@ BUILD_EXPORTS = \
- CC="$(CC_FOR_BUILD)"; export CC; \
- CFLAGS="$(CFLAGS_FOR_BUILD)"; export CFLAGS; \
- CONFIG_SHELL="$(SHELL)"; export CONFIG_SHELL; \
-+ CPP="$(CPP_FOR_BUILD)"; export CPP; \
-+ CPPFLAGS="$(CPPFLAGS_FOR_BUILD)"; export CPPFLAGS; \
- CXX="$(CXX_FOR_BUILD)"; export CXX; \
- CXXFLAGS="$(CXXFLAGS_FOR_BUILD)"; export CXXFLAGS; \
- GFORTRAN="$(GFORTRAN_FOR_BUILD)"; export GFORTRAN; \
-@@ -201,6 +203,8 @@ HOST_EXPORTS = \
- AR="$(AR)"; export AR; \
- AS="$(AS)"; export AS; \
- CC_FOR_BUILD="$(CC_FOR_BUILD)"; export CC_FOR_BUILD; \
-+ CPP_FOR_BUILD="$(CPP_FOR_BUILD)"; export CPP_FOR_BUILD; \
-+ CPPFLAGS_FOR_BUILD="$(CPPFLAGS_FOR_BUILD)"; export CPPFLAGS_FOR_BUILD; \
- CXX_FOR_BUILD="$(CXX_FOR_BUILD)"; export CXX_FOR_BUILD; \
- DLLTOOL="$(DLLTOOL)"; export DLLTOOL; \
- LD="$(LD)"; export LD; \
-@@ -356,6 +360,8 @@ AR_FOR_BUILD = @AR_FOR_BUILD@
- AS_FOR_BUILD = @AS_FOR_BUILD@
- CC_FOR_BUILD = @CC_FOR_BUILD@
- CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@
-+CPP_FOR_BUILD = @CPP_FOR_BUILD@
-+CPPFLAGS_FOR_BUILD = @CPPFLAGS_FOR_BUILD@
- CXXFLAGS_FOR_BUILD = @CXXFLAGS_FOR_BUILD@
- CXX_FOR_BUILD = @CXX_FOR_BUILD@
- DLLTOOL_FOR_BUILD = @DLLTOOL_FOR_BUILD@
-Index: gcc-11.2.0/configure
-===================================================================
---- gcc-11.2.0.orig/configure
-+++ gcc-11.2.0/configure
-@@ -652,6 +652,8 @@ GFORTRAN_FOR_BUILD
- DLLTOOL_FOR_BUILD
- CXX_FOR_BUILD
- CXXFLAGS_FOR_BUILD
-+CPPFLAGS_FOR_BUILD
-+CPP_FOR_BUILD
- CFLAGS_FOR_BUILD
- CC_FOR_BUILD
- AS_FOR_BUILD
-@@ -4092,6 +4094,7 @@ if test "${build}" != "${host}" ; then
- AR_FOR_BUILD=${AR_FOR_BUILD-ar}
- AS_FOR_BUILD=${AS_FOR_BUILD-as}
- CC_FOR_BUILD=${CC_FOR_BUILD-gcc}
-+ CPP_FOR_BUILD="${CPP_FOR_BUILD-\$(CPP)}"
- CXX_FOR_BUILD=${CXX_FOR_BUILD-g++}
- GFORTRAN_FOR_BUILD=${GFORTRAN_FOR_BUILD-gfortran}
- GOC_FOR_BUILD=${GOC_FOR_BUILD-gccgo}
-@@ -9809,6 +9812,7 @@ esac
- # our build compiler if desired.
- if test x"${build}" = x"${host}" ; then
- CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD-${CFLAGS}}
-+ CPPFLAGS_FOR_BUILD=${CPPFLAGS_FOR_BUILD-${CPPFLAGS}}
- CXXFLAGS_FOR_BUILD=${CXXFLAGS_FOR_BUILD-${CXXFLAGS}}
- LDFLAGS_FOR_BUILD=${LDFLAGS_FOR_BUILD-${LDFLAGS}}
- fi
-Index: gcc-11.2.0/configure.ac
-===================================================================
---- gcc-11.2.0.orig/configure.ac
-+++ gcc-11.2.0/configure.ac
-@@ -1347,6 +1347,7 @@ if test "${build}" != "${host}" ; then
- AR_FOR_BUILD=${AR_FOR_BUILD-ar}
- AS_FOR_BUILD=${AS_FOR_BUILD-as}
- CC_FOR_BUILD=${CC_FOR_BUILD-gcc}
-+ CPP_FOR_BUILD="${CPP_FOR_BUILD-\$(CPP)}"
- CXX_FOR_BUILD=${CXX_FOR_BUILD-g++}
- GFORTRAN_FOR_BUILD=${GFORTRAN_FOR_BUILD-gfortran}
- GOC_FOR_BUILD=${GOC_FOR_BUILD-gccgo}
-@@ -3321,6 +3322,7 @@ esac
- # our build compiler if desired.
- if test x"${build}" = x"${host}" ; then
- CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD-${CFLAGS}}
-+ CPPFLAGS_FOR_BUILD=${CPPFLAGS_FOR_BUILD-${CPPFLAGS}}
- CXXFLAGS_FOR_BUILD=${CXXFLAGS_FOR_BUILD-${CXXFLAGS}}
- LDFLAGS_FOR_BUILD=${LDFLAGS_FOR_BUILD-${LDFLAGS}}
- fi
-@@ -3387,6 +3389,8 @@ AC_SUBST(AR_FOR_BUILD)
- AC_SUBST(AS_FOR_BUILD)
- AC_SUBST(CC_FOR_BUILD)
- AC_SUBST(CFLAGS_FOR_BUILD)
-+AC_SUBST(CPP_FOR_BUILD)
-+AC_SUBST(CPPFLAGS_FOR_BUILD)
- AC_SUBST(CXXFLAGS_FOR_BUILD)
- AC_SUBST(CXX_FOR_BUILD)
- AC_SUBST(DLLTOOL_FOR_BUILD)
-Index: gcc-11.2.0/gcc/configure
-===================================================================
---- gcc-11.2.0.orig/gcc/configure
-+++ gcc-11.2.0/gcc/configure
-@@ -12699,7 +12699,7 @@ else
- CC="${CC_FOR_BUILD}" CFLAGS="${CFLAGS_FOR_BUILD}" \
- CXX="${CXX_FOR_BUILD}" CXXFLAGS="${CXXFLAGS_FOR_BUILD}" \
- LD="${LD_FOR_BUILD}" LDFLAGS="${LDFLAGS_FOR_BUILD}" \
-- GMPINC="" CPPFLAGS="${CPPFLAGS} -DGENERATOR_FILE" \
-+ GMPINC="" CPPFLAGS="${CPPFLAGS_FOR_BUILD} -DGENERATOR_FILE" \
- ${realsrcdir}/configure \
- --enable-languages=${enable_languages-all} \
- ${enable_obsolete+--enable-obsolete="$enable_obsolete"} \
-Index: gcc-11.2.0/gcc/configure.ac
-===================================================================
---- gcc-11.2.0.orig/gcc/configure.ac
-+++ gcc-11.2.0/gcc/configure.ac
-@@ -2023,7 +2023,7 @@ else
- CC="${CC_FOR_BUILD}" CFLAGS="${CFLAGS_FOR_BUILD}" \
- CXX="${CXX_FOR_BUILD}" CXXFLAGS="${CXXFLAGS_FOR_BUILD}" \
- LD="${LD_FOR_BUILD}" LDFLAGS="${LDFLAGS_FOR_BUILD}" \
-- GMPINC="" CPPFLAGS="${CPPFLAGS} -DGENERATOR_FILE" \
-+ GMPINC="" CPPFLAGS="${CPPFLAGS_FOR_BUILD} -DGENERATOR_FILE" \
- ${realsrcdir}/configure \
- --enable-languages=${enable_languages-all} \
- ${enable_obsolete+--enable-obsolete="$enable_obsolete"} \
diff --git a/meta/recipes-devtools/gcc/gcc/0019-Ensure-target-gcc-headers-can-be-included.patch b/meta/recipes-devtools/gcc/gcc/0019-Ensure-target-gcc-headers-can-be-included.patch
index 120d5a29b2..f8d1861bc0 100644
--- a/meta/recipes-devtools/gcc/gcc/0019-Ensure-target-gcc-headers-can-be-included.patch
+++ b/meta/recipes-devtools/gcc/gcc/0019-Ensure-target-gcc-headers-can-be-included.patch
@@ -21,7 +21,7 @@ Signed-off-by: Khem Raj <raj.khem@gmail.com>
gcc/Makefile.in | 2 ++
gcc/config/linux.h | 8 ++++++++
gcc/config/rs6000/sysv4.h | 8 ++++++++
- gcc/cppdefault.c | 4 ++++
+ gcc/cppdefault.cc | 4 ++++
4 files changed, 22 insertions(+)
diff --git a/gcc/Makefile.in b/gcc/Makefile.in
@@ -96,10 +96,10 @@ index 510abe169c5..0c2bba5ea32 100644
INCLUDE_DEFAULTS_MUSL_NATIVE \
{ GCC_INCLUDE_DIR, "GCC", 0, 1, 0, 0 }, \
{ 0, 0, 0, 0, 0, 0 } \
-diff --git a/gcc/cppdefault.c b/gcc/cppdefault.c
+diff --git a/gcc/cppdefault.cc b/gcc/cppdefault.cc
index c503d14fc3f..d54d6ce0076 100644
---- a/gcc/cppdefault.c
-+++ b/gcc/cppdefault.c
+--- a/gcc/cppdefault.cc
++++ b/gcc/cppdefault.cc
@@ -64,6 +64,10 @@ const struct default_include cpp_include_defaults[]
/* This is the dir for gcc's private headers. */
{ GCC_INCLUDE_DIR, "GCC", 0, 0, 0, 0 },
diff --git a/meta/recipes-devtools/gcc/gcc/0024-handle-sysroot-support-for-nativesdk-gcc.patch b/meta/recipes-devtools/gcc/gcc/0024-handle-sysroot-support-for-nativesdk-gcc.patch
index b1054fa749..aa005532ad 100644
--- a/meta/recipes-devtools/gcc/gcc/0024-handle-sysroot-support-for-nativesdk-gcc.patch
+++ b/meta/recipes-devtools/gcc/gcc/0024-handle-sysroot-support-for-nativesdk-gcc.patch
@@ -34,21 +34,22 @@ if the executable is moved. (These paths were missed in the original
implementation.)
Signed-off-by: Mark Hatle <mark.hatle@kernel.crashing.org>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
---
- gcc/c-family/c-opts.c | 4 +--
+ gcc/c-family/c-opts.cc | 4 +--
gcc/config/linux.h | 24 +++++++--------
gcc/config/rs6000/sysv4.h | 24 +++++++--------
- gcc/cppdefault.c | 63 ++++++++++++++++++++++++---------------
+ gcc/cppdefault.cc | 63 ++++++++++++++++++++++++---------------
gcc/cppdefault.h | 13 ++++----
- gcc/gcc.c | 20 +++++++++----
- gcc/incpath.c | 12 ++++----
- gcc/prefix.c | 6 ++--
+ gcc/gcc.cc | 20 +++++++++----
+ gcc/incpath.cc | 12 ++++----
+ gcc/prefix.cc | 6 ++--
8 files changed, 94 insertions(+), 72 deletions(-)
-diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c
+diff --git a/gcc/c-family/c-opts.cc b/gcc/c-family/c-opts.cc
index 89e05a4c551..5577383665d 100644
---- a/gcc/c-family/c-opts.c
-+++ b/gcc/c-family/c-opts.c
+--- a/gcc/c-family/c-opts.cc
++++ b/gcc/c-family/c-opts.cc
@@ -1436,8 +1436,8 @@ add_prefixed_path (const char *suffix, incpath_kind chain)
size_t prefix_len, suffix_len;
@@ -216,10 +217,10 @@ index 0c2bba5ea32..313a8de4417 100644
{ 0, 0, 0, 0, 0, 0 } \
}
#endif
-diff --git a/gcc/cppdefault.c b/gcc/cppdefault.c
+diff --git a/gcc/cppdefault.cc b/gcc/cppdefault.cc
index d54d6ce0076..784a92a0c24 100644
---- a/gcc/cppdefault.c
-+++ b/gcc/cppdefault.c
+--- a/gcc/cppdefault.cc
++++ b/gcc/cppdefault.cc
@@ -35,6 +35,30 @@
# undef CROSS_INCLUDE_DIR
#endif
@@ -377,10 +378,10 @@ index fd3c655db1c..20669ac427d 100644
/* The run-time execution prefix. This is typically the lib/gcc
subdirectory of the actual installation. */
extern const char *gcc_exec_prefix;
-diff --git a/gcc/gcc.c b/gcc/gcc.c
+diff --git a/gcc/gcc.cc b/gcc/gcc.cc
index 8737bae5353..aa6fbe43965 100644
---- a/gcc/gcc.c
-+++ b/gcc/gcc.c
+--- a/gcc/gcc.cc
++++ b/gcc/gcc.cc
@@ -252,6 +252,8 @@ FILE *report_times_to_file = NULL;
#endif
static const char *target_system_root = DEFAULT_TARGET_SYSTEM_ROOT;
@@ -437,10 +438,10 @@ index 8737bae5353..aa6fbe43965 100644
case 'S':
value = do_spec_1 (startfile_spec, 0, NULL);
if (value != 0)
-diff --git a/gcc/incpath.c b/gcc/incpath.c
+diff --git a/gcc/incpath.cc b/gcc/incpath.cc
index fbfc0ce03b8..a82e543428b 100644
---- a/gcc/incpath.c
-+++ b/gcc/incpath.c
+--- a/gcc/incpath.cc
++++ b/gcc/incpath.cc
@@ -131,7 +131,7 @@ add_standard_paths (const char *sysroot, const char *iprefix,
int relocated = cpp_relocated ();
size_t len;
@@ -484,10 +485,10 @@ index fbfc0ce03b8..a82e543428b 100644
NULL);
str = update_path (ostr, p->component);
free (ostr);
-diff --git a/gcc/prefix.c b/gcc/prefix.c
+diff --git a/gcc/prefix.cc b/gcc/prefix.cc
index 747c09de638..f728638dc65 100644
---- a/gcc/prefix.c
-+++ b/gcc/prefix.c
+--- a/gcc/prefix.cc
++++ b/gcc/prefix.cc
@@ -72,7 +72,9 @@ License along with GCC; see the file COPYING3. If not see
#include "prefix.h"
#include "common/common-target.h"
diff --git a/meta/recipes-devtools/gcc/gcc/0025-Search-target-sysroot-gcc-version-specific-dirs-with.patch b/meta/recipes-devtools/gcc/gcc/0025-Search-target-sysroot-gcc-version-specific-dirs-with.patch
index ff622b1056..d27e3011ed 100644
--- a/meta/recipes-devtools/gcc/gcc/0025-Search-target-sysroot-gcc-version-specific-dirs-with.patch
+++ b/meta/recipes-devtools/gcc/gcc/0025-Search-target-sysroot-gcc-version-specific-dirs-with.patch
@@ -46,14 +46,15 @@ Upstream-Status: Pending
RP 2015/7/31
Signed-off-by: Khem Raj <raj.khem@gmail.com>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
---
- gcc/gcc.c | 29 ++++++++++++++++++++++++++++-
+ gcc/gcc.cc | 29 ++++++++++++++++++++++++++++-
1 file changed, 28 insertions(+), 1 deletion(-)
-diff --git a/gcc/gcc.c b/gcc/gcc.c
+diff --git a/gcc/gcc.cc b/gcc/gcc.cc
index aa6fbe43965..f8a71a13826 100644
---- a/gcc/gcc.c
-+++ b/gcc/gcc.c
+--- a/gcc/gcc.cc
++++ b/gcc/gcc.cc
@@ -2811,7 +2811,7 @@ for_each_path (const struct path_prefix *paths,
if (path == NULL)
{
diff --git a/meta/recipes-devtools/gcc/gcc/0027-nios2-Define-MUSL_DYNAMIC_LINKER.patch b/meta/recipes-devtools/gcc/gcc/0027-nios2-Define-MUSL_DYNAMIC_LINKER.patch
deleted file mode 100644
index 97c271373b..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0027-nios2-Define-MUSL_DYNAMIC_LINKER.patch
+++ /dev/null
@@ -1,31 +0,0 @@
-From: Richard Purdie <richard.purdie@linuxfoundation.org>
-Subject: [PATCH 4/5] gcc/nios2: Define the musl linker
-
-Add a definition of the musl linker used on the nios2 platform.
-
-2021-10-26 Richard Purdie <richard.purdie@linuxfoundation.org>
-
-gcc/ChangeLog:
-
- * config/nios2/linux.h (MUSL_DYNAMIC_LINKER): Add musl linker
-
-Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
-
-Submitted [https://gcc.gnu.org/pipermail/gcc-patches/2021-October/582723.html]
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commitdiff;h=e5ddbbf992b909d8e38851bd3179d29389e6ac97]
----
- gcc/config/nios2/linux.h | 1 +
- 1 file changed, 1 insertion(+)
-
-Index: gcc-11.2.0/gcc/config/nios2/linux.h
-===================================================================
---- gcc-11.2.0.orig/gcc/config/nios2/linux.h
-+++ gcc-11.2.0/gcc/config/nios2/linux.h
-@@ -30,6 +30,7 @@
- #define CPP_SPEC "%{posix:-D_POSIX_SOURCE} %{pthread:-D_REENTRANT}"
-
- #define GLIBC_DYNAMIC_LINKER "/lib/ld-linux-nios2.so.1"
-+#define MUSL_DYNAMIC_LINKER "/lib/ld-musl-nios2.so.1"
-
- #undef LINK_SPEC
- #define LINK_SPEC LINK_SPEC_ENDIAN \
diff --git a/meta/recipes-devtools/gcc/gcc/0029-Link-libgcc-using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch b/meta/recipes-devtools/gcc/gcc/0029-Link-libgcc-using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch
deleted file mode 100644
index b74aeb8bb6..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0029-Link-libgcc-using-LDFLAGS-not-just-SHLIB_LDFLAGS.patch
+++ /dev/null
@@ -1,26 +0,0 @@
-From 695adb4dffb23c6f5cbc757e05cf4187a2bd6528 Mon Sep 17 00:00:00 2001
-From: Khem Raj <raj.khem@gmail.com>
-Date: Wed, 4 May 2016 21:11:34 -0700
-Subject: [PATCH] Link libgcc using LDFLAGS, not just SHLIB_LDFLAGS
-
-Upstream-Status: Pending
-
-Signed-off-by: Christopher Larson <chris_larson@mentor.com>
-Signed-off-by: Khem Raj <raj.khem@gmail.com>
----
- libgcc/config/t-slibgcc | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/libgcc/config/t-slibgcc b/libgcc/config/t-slibgcc
-index c59b43b7b69..ca4c141f526 100644
---- a/libgcc/config/t-slibgcc
-+++ b/libgcc/config/t-slibgcc
-@@ -32,7 +32,7 @@ SHLIB_INSTALL_SOLINK = $(LN_S) $(SHLIB_SONAME) \
- $(DESTDIR)$(slibdir)$(SHLIB_SLIBDIR_QUAL)/$(SHLIB_SOLINK)
-
- SHLIB_LINK = $(CC) $(LIBGCC2_CFLAGS) -shared -nodefaultlibs \
-- $(SHLIB_LDFLAGS) \
-+ $(LDFLAGS) $(SHLIB_LDFLAGS) \
- -o $(SHLIB_DIR)/$(SHLIB_SONAME).tmp @multilib_flags@ \
- $(SHLIB_OBJS) $(SHLIB_LC) && \
- rm -f $(SHLIB_DIR)/$(SHLIB_SOLINK) && \
diff --git a/meta/recipes-devtools/gcc/gcc/0030-sync-gcc-stddef.h-with-musl.patch b/meta/recipes-devtools/gcc/gcc/0030-sync-gcc-stddef.h-with-musl.patch
deleted file mode 100644
index fd7d604e98..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0030-sync-gcc-stddef.h-with-musl.patch
+++ /dev/null
@@ -1,88 +0,0 @@
-From a9173429ae256c4b4a3ab4d758a6adf42f8c4239 Mon Sep 17 00:00:00 2001
-From: Khem Raj <raj.khem@gmail.com>
-Date: Fri, 3 Feb 2017 12:56:00 -0800
-Subject: [PATCH] sync gcc stddef.h with musl
-
-musl defines ptrdiff_t size_t and wchar_t
-so dont define them here if musl is definining them
-
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=85a438fc78dd12249ca854a3e5c577fefeb1a5cd]
-
-Signed-off-by: Khem Raj <raj.khem@gmail.com>
----
- gcc/ginclude/stddef.h | 9 +++++++++
- 1 file changed, 9 insertions(+)
-
-diff --git a/gcc/ginclude/stddef.h b/gcc/ginclude/stddef.h
-index 66619fe43b1..3f843d6f365 100644
---- a/gcc/ginclude/stddef.h
-+++ b/gcc/ginclude/stddef.h
-@@ -128,6 +128,7 @@ _TYPE_wchar_t;
- #ifndef ___int_ptrdiff_t_h
- #ifndef _GCC_PTRDIFF_T
- #ifndef _PTRDIFF_T_DECLARED /* DragonFly */
-+#ifndef __DEFINED_ptrdiff_t /* musl */
- #define _PTRDIFF_T
- #define _T_PTRDIFF_
- #define _T_PTRDIFF
-@@ -137,10 +138,12 @@ _TYPE_wchar_t;
- #define ___int_ptrdiff_t_h
- #define _GCC_PTRDIFF_T
- #define _PTRDIFF_T_DECLARED
-+#define __DEFINED_ptrdiff_t /* musl */
- #ifndef __PTRDIFF_TYPE__
- #define __PTRDIFF_TYPE__ long int
- #endif
- typedef __PTRDIFF_TYPE__ ptrdiff_t;
-+#endif /* __DEFINED_ptrdiff_t */
- #endif /* _PTRDIFF_T_DECLARED */
- #endif /* _GCC_PTRDIFF_T */
- #endif /* ___int_ptrdiff_t_h */
-@@ -178,6 +181,7 @@ typedef __PTRDIFF_TYPE__ ptrdiff_t;
- #ifndef _GCC_SIZE_T
- #ifndef _SIZET_
- #ifndef __size_t
-+#ifndef __DEFINED_size_t /* musl */
- #define __size_t__ /* BeOS */
- #define __SIZE_T__ /* Cray Unicos/Mk */
- #define _SIZE_T
-@@ -194,6 +198,7 @@ typedef __PTRDIFF_TYPE__ ptrdiff_t;
- #define ___int_size_t_h
- #define _GCC_SIZE_T
- #define _SIZET_
-+#define __DEFINED_size_t /* musl */
- #if defined (__FreeBSD__) \
- || defined(__DragonFly__) \
- || defined(__FreeBSD_kernel__) \
-@@ -228,6 +233,7 @@ typedef long ssize_t;
- #endif /* _SIZE_T */
- #endif /* __SIZE_T__ */
- #endif /* __size_t__ */
-+#endif /* __DEFINED_size_t */
- #undef __need_size_t
- #endif /* _STDDEF_H or __need_size_t. */
-
-@@ -257,6 +263,7 @@ typedef long ssize_t;
- #ifndef ___int_wchar_t_h
- #ifndef __INT_WCHAR_T_H
- #ifndef _GCC_WCHAR_T
-+#ifndef __DEFINED_wchar_t /* musl */
- #define __wchar_t__ /* BeOS */
- #define __WCHAR_T__ /* Cray Unicos/Mk */
- #define _WCHAR_T
-@@ -272,6 +279,7 @@ typedef long ssize_t;
- #define __INT_WCHAR_T_H
- #define _GCC_WCHAR_T
- #define _WCHAR_T_DECLARED
-+#define __DEFINED_wchar_t /* musl */
-
- /* On BSD/386 1.1, at least, machine/ansi.h defines _BSD_WCHAR_T_
- instead of _WCHAR_T_, and _BSD_RUNE_T_ (which, unlike the other
-@@ -337,6 +345,7 @@ typedef __WCHAR_TYPE__ wchar_t;
- #endif
- #endif /* __WCHAR_T__ */
- #endif /* __wchar_t__ */
-+#endif /* __DEFINED_wchar_t musl */
- #undef __need_wchar_t
- #endif /* _STDDEF_H or __need_wchar_t. */
-
diff --git a/meta/recipes-devtools/gcc/gcc/0034-libgcc_s-Use-alias-for-__cpu_indicator_init-instead-.patch b/meta/recipes-devtools/gcc/gcc/0034-libgcc_s-Use-alias-for-__cpu_indicator_init-instead-.patch
index 3f666dc7bd..5970c2fcbd 100644
--- a/meta/recipes-devtools/gcc/gcc/0034-libgcc_s-Use-alias-for-__cpu_indicator_init-instead-.patch
+++ b/meta/recipes-devtools/gcc/gcc/0034-libgcc_s-Use-alias-for-__cpu_indicator_init-instead-.patch
@@ -32,16 +32,17 @@ gcc/Changelog:
Upstream-Status: Pending
Signed-off-by: Khem Raj <raj.khem@gmail.com>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
---
- gcc/config/i386/i386-expand.c | 4 ++--
- libgcc/config/i386/cpuinfo.c | 6 +++---
- libgcc/config/i386/t-linux | 2 +-
+ gcc/config/i386/i386-expand.cc | 4 ++--
+ libgcc/config/i386/cpuinfo.c | 6 +++---
+ libgcc/config/i386/t-linux | 2 +-
3 files changed, 6 insertions(+), 6 deletions(-)
-diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
+diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index ac69eed4d32..ffaa44a16fc 100644
---- a/gcc/config/i386/i386-expand.c
-+++ b/gcc/config/i386/i386-expand.c
+--- a/gcc/config/i386/i386-expand.cc
++++ b/gcc/config/i386/i386-expand.cc
@@ -11038,10 +11038,10 @@ ix86_expand_builtin (tree exp, rtx target, rtx subtarget,
{
case IX86_BUILTIN_CPU_INIT:
diff --git a/meta/recipes-devtools/gcc/gcc/0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch b/meta/recipes-devtools/gcc/gcc/0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch
index 874cd7798d..579bd91251 100644
--- a/meta/recipes-devtools/gcc/gcc/0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch
+++ b/meta/recipes-devtools/gcc/gcc/0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch
@@ -11,16 +11,17 @@ Upstream-Status: Inappropriate [OE Reproducibility specific]
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Signed-off-by: Khem Raj <raj.khem@gmail.com>
+Signed-off-by: Bernhard Rosenkränzer <bernhard.rosenkraenzer.ext@huawei.com> [ported to gcc 12]
---
- gcc/gengtype.c | 6 +++---
- gcc/genmodes.c | 32 ++++++++++++++++----------------
+ gcc/gengtype.cc | 6 +++---
+ gcc/genmodes.cc | 32 ++++++++++++++++----------------
2 files changed, 19 insertions(+), 19 deletions(-)
-diff --git a/gcc/gengtype.c b/gcc/gengtype.c
-index 5f50242e857..cbaca9b8cd0 100644
---- a/gcc/gengtype.c
-+++ b/gcc/gengtype.c
-@@ -991,7 +991,7 @@ create_field_at (pair_p next, type_p type, const char *name, options_p opt,
+diff --git a/gcc/gengtype.cc b/gcc/gengtype.cc
+index 386ae1b0506..9762e914296 100644
+--- a/gcc/gengtype.cc
++++ b/gcc/gengtype.cc
+@@ -1006,7 +1006,7 @@ create_field_at (pair_p next, type_p type, const char *name, options_p opt,
/* Create a fake field with the given type and name. NEXT is the next
field in the chain. */
#define create_field(next,type,name) \
@@ -29,7 +30,7 @@ index 5f50242e857..cbaca9b8cd0 100644
/* Like create_field, but the field is only valid when condition COND
is true. */
-@@ -1024,7 +1024,7 @@ create_optional_field_ (pair_p next, type_p type, const char *name,
+@@ -1039,7 +1039,7 @@ create_optional_field_ (pair_p next, type_p type, const char *name,
}
#define create_optional_field(next,type,name,cond) \
@@ -38,7 +39,7 @@ index 5f50242e857..cbaca9b8cd0 100644
/* Reverse a linked list of 'struct pair's in place. */
pair_p
-@@ -5189,7 +5189,7 @@ main (int argc, char **argv)
+@@ -5238,7 +5238,7 @@ main (int argc, char **argv)
/* These types are set up with #define or else outside of where
we can see them. We should initialize them before calling
read_input_list. */
@@ -47,11 +48,11 @@ index 5f50242e857..cbaca9b8cd0 100644
Call;} while (0)
POS_HERE (do_scalar_typedef ("CUMULATIVE_ARGS", &pos));
POS_HERE (do_scalar_typedef ("REAL_VALUE_TYPE", &pos));
-diff --git a/gcc/genmodes.c b/gcc/genmodes.c
-index c268ebc4c6e..4361f3f1563 100644
---- a/gcc/genmodes.c
-+++ b/gcc/genmodes.c
-@@ -438,7 +438,7 @@ complete_all_modes (void)
+diff --git a/gcc/genmodes.cc b/gcc/genmodes.cc
+index 59850bb070a..e187f8542a1 100644
+--- a/gcc/genmodes.cc
++++ b/gcc/genmodes.cc
+@@ -440,7 +440,7 @@ complete_all_modes (void)
}
/* For each mode in class CLASS, construct a corresponding complex mode. */
@@ -60,7 +61,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void
make_complex_modes (enum mode_class cl,
const char *file, unsigned int line)
-@@ -497,7 +497,7 @@ make_complex_modes (enum mode_class cl,
+@@ -499,7 +499,7 @@ make_complex_modes (enum mode_class cl,
having as many components as necessary. ORDER is the sorting order
of the mode, with smaller numbers indicating a higher priority. */
#define VECTOR_MODES_WITH_PREFIX(PREFIX, C, W, ORDER) \
@@ -69,16 +70,16 @@ index c268ebc4c6e..4361f3f1563 100644
#define VECTOR_MODES(C, W) VECTOR_MODES_WITH_PREFIX (V, C, W, 0)
static void ATTRIBUTE_UNUSED
make_vector_modes (enum mode_class cl, const char *prefix, unsigned int width,
-@@ -549,7 +549,7 @@ make_vector_modes (enum mode_class cl, const char *prefix, unsigned int width,
- /* Create a vector of booleans called NAME with COUNT elements and
+@@ -552,7 +552,7 @@ make_vector_modes (enum mode_class cl, const char *prefix, unsigned int width,
BYTESIZE bytes in total. */
- #define VECTOR_BOOL_MODE(NAME, COUNT, BYTESIZE) \
-- make_vector_bool_mode (#NAME, COUNT, BYTESIZE, __FILE__, __LINE__)
-+ make_vector_bool_mode (#NAME, COUNT, BYTESIZE, __FILE__, 0)
+ #define VECTOR_BOOL_MODE(NAME, COUNT, COMPONENT, BYTESIZE) \
+ make_vector_bool_mode (#NAME, COUNT, #COMPONENT, BYTESIZE, \
+- __FILE__, __LINE__)
++ __FILE__, 0)
static void ATTRIBUTE_UNUSED
make_vector_bool_mode (const char *name, unsigned int count,
- unsigned int bytesize, const char *file,
-@@ -571,7 +571,7 @@ make_vector_bool_mode (const char *name, unsigned int count,
+ const char *component, unsigned int bytesize,
+@@ -574,7 +574,7 @@ make_vector_bool_mode (const char *name, unsigned int count,
/* Input. */
#define _SPECIAL_MODE(C, N) \
@@ -87,7 +88,7 @@ index c268ebc4c6e..4361f3f1563 100644
#define RANDOM_MODE(N) _SPECIAL_MODE (RANDOM, N)
#define CC_MODE(N) _SPECIAL_MODE (CC, N)
-@@ -584,7 +584,7 @@ make_special_mode (enum mode_class cl, const char *name,
+@@ -587,7 +587,7 @@ make_special_mode (enum mode_class cl, const char *name,
#define INT_MODE(N, Y) FRACTIONAL_INT_MODE (N, -1U, Y)
#define FRACTIONAL_INT_MODE(N, B, Y) \
@@ -96,7 +97,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void
make_int_mode (const char *name,
-@@ -611,16 +611,16 @@ make_opaque_mode (const char *name,
+@@ -628,16 +628,16 @@ make_opaque_mode (const char *name,
}
#define FRACT_MODE(N, Y, F) \
@@ -117,7 +118,7 @@ index c268ebc4c6e..4361f3f1563 100644
/* Create a fixed-point mode by setting CL, NAME, BYTESIZE, IBIT, FBIT,
FILE, and LINE. */
-@@ -641,7 +641,7 @@ make_fixed_point_mode (enum mode_class cl,
+@@ -658,7 +658,7 @@ make_fixed_point_mode (enum mode_class cl,
#define FLOAT_MODE(N, Y, F) FRACTIONAL_FLOAT_MODE (N, -1U, Y, F)
#define FRACTIONAL_FLOAT_MODE(N, B, Y, F) \
@@ -126,7 +127,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void
make_float_mode (const char *name,
-@@ -658,7 +658,7 @@ make_float_mode (const char *name,
+@@ -675,7 +675,7 @@ make_float_mode (const char *name,
#define DECIMAL_FLOAT_MODE(N, Y, F) \
FRACTIONAL_DECIMAL_FLOAT_MODE (N, -1U, Y, F)
#define FRACTIONAL_DECIMAL_FLOAT_MODE(N, B, Y, F) \
@@ -135,7 +136,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void
make_decimal_float_mode (const char *name,
-@@ -673,7 +673,7 @@ make_decimal_float_mode (const char *name,
+@@ -690,7 +690,7 @@ make_decimal_float_mode (const char *name,
}
#define RESET_FLOAT_FORMAT(N, F) \
@@ -144,7 +145,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void ATTRIBUTE_UNUSED
reset_float_format (const char *name, const char *format,
const char *file, unsigned int line)
-@@ -694,7 +694,7 @@ reset_float_format (const char *name, const char *format,
+@@ -711,7 +711,7 @@ reset_float_format (const char *name, const char *format,
/* __intN support. */
#define INT_N(M,PREC) \
@@ -153,7 +154,7 @@ index c268ebc4c6e..4361f3f1563 100644
static void ATTRIBUTE_UNUSED
make_int_n (const char *m, int bitsize,
const char *file, unsigned int line)
-@@ -723,7 +723,7 @@ make_int_n (const char *m, int bitsize,
+@@ -740,7 +740,7 @@ make_int_n (const char *m, int bitsize,
/* Partial integer modes are specified by relation to a full integer
mode. */
#define PARTIAL_INT_MODE(M,PREC,NAME) \
@@ -162,16 +163,16 @@ index c268ebc4c6e..4361f3f1563 100644
static void ATTRIBUTE_UNUSED
make_partial_integer_mode (const char *base, const char *name,
unsigned int precision,
-@@ -750,7 +750,7 @@ make_partial_integer_mode (const char *base, const char *name,
+@@ -767,7 +767,7 @@ make_partial_integer_mode (const char *base, const char *name,
/* A single vector mode can be specified by naming its component
mode and the number of components. */
- #define VECTOR_MODE(C, M, N) \
-- make_vector_mode (MODE_##C, #M, N, __FILE__, __LINE__);
-+ make_vector_mode (MODE_##C, #M, N, __FILE__, 0);
+ #define VECTOR_MODE_WITH_PREFIX(PREFIX, C, M, N, ORDER) \
+- make_vector_mode (MODE_##C, #PREFIX, #M, N, ORDER, __FILE__, __LINE__);
++ make_vector_mode (MODE_##C, #PREFIX, #M, N, ORDER, __FILE__, 0);
+ #define VECTOR_MODE(C, M, N) VECTOR_MODE_WITH_PREFIX(V, C, M, N, 0);
static void ATTRIBUTE_UNUSED
make_vector_mode (enum mode_class bclass,
- const char *base,
-@@ -793,7 +793,7 @@ make_vector_mode (enum mode_class bclass,
+@@ -814,7 +814,7 @@ make_vector_mode (enum mode_class bclass,
/* Adjustability. */
#define _ADD_ADJUST(A, M, X, C1, C2) \
diff --git a/meta/recipes-devtools/gcc/gcc/0041-apply-debug-prefix-maps-before-checksumming-DIEs.patch b/meta/recipes-devtools/gcc/gcc/0041-apply-debug-prefix-maps-before-checksumming-DIEs.patch
deleted file mode 100644
index c8dcd74b9d..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0041-apply-debug-prefix-maps-before-checksumming-DIEs.patch
+++ /dev/null
@@ -1,95 +0,0 @@
-From 7cc2df084b7977653a9b59cbc34a9ad500ae619c Mon Sep 17 00:00:00 2001
-From: Richard Biener <rguenther@suse.de>
-Date: Tue, 20 Jul 2021 11:00:33 +0200
-Subject: [PATCH] debug/101473 - apply debug prefix maps before checksumming DIEs
-
-The following makes sure to apply the debug prefix maps to filenames
-before checksumming DIEs to create the global symbol for the CU DIE
-used by LTO to link the late debug to the early debug. This avoids
-binary differences (in said symbol) when compiling with toolchains
-installed under a different path and that compensated with appropriate
--fdebug-prefix-map options.
-
-The easiest and most scalable way is to record both the unmapped
-and the remapped filename in the dwarf_file_data so the remapping
-process takes place at a single point and only once (otherwise it
-creates GC garbage at each point doing that).
-
-2021-07-20 Richard Biener <rguenther@suse.de>
-
- PR debug/101473
- * dwarf2out.h (dwarf_file_data): Add key member.
- * dwarf2out.c (dwarf_file_hasher::equal): Compare key.
- (dwarf_file_hasher::hash): Hash key.
- (lookup_filename): Remap the filename and store it in the
- filename member of dwarf_file_data when creating a new
- dwarf_file_data.
- (file_name_acquire): Do not remap the filename again.
- (maybe_emit_file): Likewise.
-
-[YOCTO #14481]
-
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=7cc2df084b7977653a9b59cbc34a9ad500ae619c]
-
-The upstream patch was modified to compensate for the definition of
-"struct dwarf_file_data" being in dwarf2out.c rather than dwarf2out.h in
-this version of gcc.
-
-Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
----
-diff -urpN a/gcc/dwarf2out.c b/gcc/dwarf2out.c
---- a/gcc/dwarf2out.c 2021-04-27 06:00:13.000000000 -0400
-+++ b/gcc/dwarf2out.c 2021-07-23 16:40:06.141886167 -0400
-@@ -1283,6 +1283,7 @@ dwarf2out_switch_text_section (void)
-
- /* Data about a single source file. */
- struct GTY((for_user)) dwarf_file_data {
-+ const char * key;
- const char * filename;
- int emitted_number;
- };
-@@ -12334,7 +12335,7 @@ file_name_acquire (dwarf_file_data **slo
-
- fi = fnad->files + fnad->used_files++;
-
-- f = remap_debug_filename (d->filename);
-+ f = d->filename;
-
- /* Skip all leading "./". */
- while (f[0] == '.' && IS_DIR_SEPARATOR (f[1]))
-@@ -27231,13 +27232,13 @@ dwarf2out_ignore_block (const_tree block
- bool
- dwarf_file_hasher::equal (dwarf_file_data *p1, const char *p2)
- {
-- return filename_cmp (p1->filename, p2) == 0;
-+ return filename_cmp (p1->key, p2) == 0;
- }
-
- hashval_t
- dwarf_file_hasher::hash (dwarf_file_data *p)
- {
-- return htab_hash_string (p->filename);
-+ return htab_hash_string (p->key);
- }
-
- /* Lookup FILE_NAME (in the list of filenames that we know about here in
-@@ -27267,7 +27268,8 @@ lookup_filename (const char *file_name)
- return *slot;
-
- created = ggc_alloc<dwarf_file_data> ();
-- created->filename = file_name;
-+ created->key = file_name;
-+ created->filename = remap_debug_filename (file_name);
- created->emitted_number = 0;
- *slot = created;
- return created;
-@@ -27293,8 +27295,7 @@ maybe_emit_file (struct dwarf_file_data
- if (output_asm_line_debug_info ())
- {
- fprintf (asm_out_file, "\t.file %u ", fd->emitted_number);
-- output_quoted_string (asm_out_file,
-- remap_debug_filename (fd->filename));
-+ output_quoted_string (asm_out_file, fd->filename);
- fputc ('\n', asm_out_file);
- }
- }
diff --git a/meta/recipes-devtools/gcc/gcc/0042-Fix-thread-stack-size-init.patch b/meta/recipes-devtools/gcc/gcc/0042-Fix-thread-stack-size-init.patch
deleted file mode 100644
index 3fb9ee98de..0000000000
--- a/meta/recipes-devtools/gcc/gcc/0042-Fix-thread-stack-size-init.patch
+++ /dev/null
@@ -1,23 +0,0 @@
-The patch is needed in order to support recent glibc (2.34).
-
-Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=91f8a7a34cf29ae7c465603a801326767f1cc7e9]
-
-Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
-
----
---- a/libsanitizer/sanitizer_common/sanitizer_posix_libcdep.cpp 2022-03-15 07:59:54.515325204 -0700
-+++ b/libsanitizer/sanitizer_common/sanitizer_posix_libcdep.cpp 2022-03-15 08:01:45.919405931 -0700
-@@ -166,9 +166,10 @@
- #if !SANITIZER_GO
- // TODO(glider): different tools may require different altstack size.
- static uptr GetAltStackSize() {
-- // SIGSTKSZ is not enough.
-- static const uptr kAltStackSize = SIGSTKSZ * 4;
-- return kAltStackSize;
-+ // Note: since GLIBC_2.31, SIGSTKSZ may be a function call, so this may be
-+ // more costly that you think. However GetAltStackSize is only call 2-3 times
-+ // per thread so don't cache the evaluation.
-+ return SIGSTKSZ * 4;
- }
-
- void SetAlternateSignalStack() {
diff --git a/meta/recipes-devtools/gcc/gcc_11.2.bb b/meta/recipes-devtools/gcc/gcc_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/gcc_11.2.bb
rename to meta/recipes-devtools/gcc/gcc_12.0.bb
diff --git a/meta/recipes-devtools/gcc/libgcc-initial_11.2.bb b/meta/recipes-devtools/gcc/libgcc-initial_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/libgcc-initial_11.2.bb
rename to meta/recipes-devtools/gcc/libgcc-initial_12.0.bb
diff --git a/meta/recipes-devtools/gcc/libgcc_11.2.bb b/meta/recipes-devtools/gcc/libgcc_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/libgcc_11.2.bb
rename to meta/recipes-devtools/gcc/libgcc_12.0.bb
diff --git a/meta/recipes-devtools/gcc/libgfortran_11.2.bb b/meta/recipes-devtools/gcc/libgfortran_12.0.bb
similarity index 100%
rename from meta/recipes-devtools/gcc/libgfortran_11.2.bb
rename to meta/recipes-devtools/gcc/libgfortran_12.0.bb
--
2.35.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [OE-core] [PATCH] gcc: upgrade 11.2 -> current 12 snapshot
2022-04-07 12:26 [PATCH] gcc: upgrade 11.2 -> current 12 snapshot Bernhard Rosenkränzer
@ 2022-04-07 12:32 ` Richard Purdie
2022-04-07 13:29 ` Bernhard Rosenkränzer
0 siblings, 1 reply; 4+ messages in thread
From: Richard Purdie @ 2022-04-07 12:32 UTC (permalink / raw)
To: bernhard.rosenkraenzer.ext, openembedded-core; +Cc: raj.khem
On Thu, 2022-04-07 at 14:26 +0200, Bernhard Rosenkränzer via
lists.openembedded.org wrote:
> rename from meta/recipes-devtools/gcc/gcc-cross-canadian_11.2.bb
> rename to meta/recipes-devtools/gcc/gcc-cross-canadian_12.0.bb
> diff --git a/meta/recipes-devtools/gcc/gcc-cross.inc b/meta/recipes-devtools/gcc/gcc-cross.inc
> index 3ffa1f0c46..0e8119384b 100644
> --- a/meta/recipes-devtools/gcc/gcc-cross.inc
> +++ b/meta/recipes-devtools/gcc/gcc-cross.inc
> @@ -47,6 +47,15 @@ ARCH_FLAGS_FOR_TARGET += "-isystem${STAGING_DIR_TARGET}${target_includedir}"
> do_configure:prepend () {
> install -d ${RECIPE_SYSROOT}${target_includedir}
> touch ${RECIPE_SYSROOT}${target_includedir}/limits.h
> +
> + if ! echo ${@d.getVar("TARGET_OS")} | grep -qi linux; then
> + # Building Zephyr with DWARF-5 is problematic because
> + # its kernel tests use pyelftools, which has incomplete
> + # DWARF-5 support (even after applying preliminary
> + # support patches). Use DWARF-4 on Zephyr and FreeRTOS
> + # for the time being.
> + sed -i -e 's,Var(dwarf_version) Init(5),Var(dwarf_version) Init(4),' ${S}/gcc/common.opt
> + fi
> }
>
> do_compile () {
Unfortunately you can't do that. The gcc-cross is shared amongst all targets on
a given architecture. This will "kind of work" in that other sstate code will
clean it up and rebuild gcc but it isn't as designed and can't merge like that
I'm afraid.
Cheers,
Richard
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] gcc: upgrade 11.2 -> current 12 snapshot
2022-04-07 12:32 ` [OE-core] " Richard Purdie
@ 2022-04-07 13:29 ` Bernhard Rosenkränzer
2022-04-07 20:07 ` [OE-core] " Khem Raj
0 siblings, 1 reply; 4+ messages in thread
From: Bernhard Rosenkränzer @ 2022-04-07 13:29 UTC (permalink / raw)
To: openembedded-core
[-- Attachment #1: Type: text/plain, Size: 1712 bytes --]
On Thu, Apr 7, 2022 at 02:32 PM, Richard Purdie wrote:
>
> On Thu, 2022-04-07 at 14:26 +0200, Bernhard Rosenkränzer via
> lists.openembedded.org wrote:
>
>> rename from meta/recipes-devtools/gcc/gcc-cross-canadian_11.2.bb
>> rename to meta/recipes-devtools/gcc/gcc-cross-canadian_12.0.bb
>> diff --git a/meta/recipes-devtools/gcc/gcc-cross.inc
>> b/meta/recipes-devtools/gcc/gcc-cross.inc
>> index 3ffa1f0c46..0e8119384b 100644
>> --- a/meta/recipes-devtools/gcc/gcc-cross.inc
>> +++ b/meta/recipes-devtools/gcc/gcc-cross.inc
>> @@ -47,6 +47,15 @@ ARCH_FLAGS_FOR_TARGET +=
>> "-isystem${STAGING_DIR_TARGET}${target_includedir}"
>> do_configure:prepend () {
>> install -d ${RECIPE_SYSROOT}${target_includedir}
>> touch ${RECIPE_SYSROOT}${target_includedir}/limits.h
>> +
>> + if ! echo ${@d.getVar("TARGET_OS")} | grep -qi linux; then
>> + # Building Zephyr with DWARF-5 is problematic because
>> + # its kernel tests use pyelftools, which has incomplete
>> + # DWARF-5 support (even after applying preliminary
>> + # support patches). Use DWARF-4 on Zephyr and FreeRTOS
>> + # for the time being.
>> + sed -i -e 's,Var(dwarf_version) Init(5),Var(dwarf_version) Init(4),'
>> ${S}/gcc/common.opt
>> + fi
>> }
>>
>> do_compile () {
>
> Unfortunately you can't do that. The gcc-cross is shared amongst all
> targets on
> a given architecture. This will "kind of work" in that other sstate code
> will
> clean it up and rebuild gcc but it isn't as designed and can't merge like
> that
> I'm afraid.
True, didn't think of that. I've backed out this part and sent a new patch. Will address the zephyr problem with an added -gdwarf-4 flag in zephyr configs.
ttyl
bero
[-- Attachment #2: Type: text/html, Size: 1775 bytes --]
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [OE-core] [PATCH] gcc: upgrade 11.2 -> current 12 snapshot
2022-04-07 13:29 ` Bernhard Rosenkränzer
@ 2022-04-07 20:07 ` Khem Raj
0 siblings, 0 replies; 4+ messages in thread
From: Khem Raj @ 2022-04-07 20:07 UTC (permalink / raw)
To: Bernhard Rosenkränzer
Cc: Patches and discussions about the oe-core layer
I carry patches all OE patches in my gcc tree as well here
https://github.com/kraj/gcc/tree/oe/master
which would be good to seed the changes.
On Thu, Apr 7, 2022 at 9:29 AM Bernhard Rosenkränzer via
lists.openembedded.org
<bernhard.rosenkraenzer.ext=huawei.com@lists.openembedded.org> wrote:
>
> On Thu, Apr 7, 2022 at 02:32 PM, Richard Purdie wrote:
>
> On Thu, 2022-04-07 at 14:26 +0200, Bernhard Rosenkränzer via
> lists.openembedded.org wrote:
>
> rename from meta/recipes-devtools/gcc/gcc-cross-canadian_11.2.bb
> rename to meta/recipes-devtools/gcc/gcc-cross-canadian_12.0.bb
> diff --git a/meta/recipes-devtools/gcc/gcc-cross.inc b/meta/recipes-devtools/gcc/gcc-cross.inc
> index 3ffa1f0c46..0e8119384b 100644
> --- a/meta/recipes-devtools/gcc/gcc-cross.inc
> +++ b/meta/recipes-devtools/gcc/gcc-cross.inc
> @@ -47,6 +47,15 @@ ARCH_FLAGS_FOR_TARGET += "-isystem${STAGING_DIR_TARGET}${target_includedir}"
> do_configure:prepend () {
> install -d ${RECIPE_SYSROOT}${target_includedir}
> touch ${RECIPE_SYSROOT}${target_includedir}/limits.h
> +
> + if ! echo ${@d.getVar("TARGET_OS")} | grep -qi linux; then
> + # Building Zephyr with DWARF-5 is problematic because
> + # its kernel tests use pyelftools, which has incomplete
> + # DWARF-5 support (even after applying preliminary
> + # support patches). Use DWARF-4 on Zephyr and FreeRTOS
> + # for the time being.
> + sed -i -e 's,Var(dwarf_version) Init(5),Var(dwarf_version) Init(4),' ${S}/gcc/common.opt
> + fi
> }
>
> do_compile () {
>
> Unfortunately you can't do that. The gcc-cross is shared amongst all targets on
> a given architecture. This will "kind of work" in that other sstate code will
> clean it up and rebuild gcc but it isn't as designed and can't merge like that
> I'm afraid.
>
> True, didn't think of that. I've backed out this part and sent a new patch. Will address the zephyr problem with an added -gdwarf-4 flag in zephyr configs.
>
> ttyl
> bero
> -=-=-=-=-=-=-=-=-=-=-=-
> Links: You receive all messages sent to this group.
> View/Reply Online (#164108): https://lists.openembedded.org/g/openembedded-core/message/164108
> Mute This Topic: https://lists.openembedded.org/mt/90311375/1997914
> Group Owner: openembedded-core+owner@lists.openembedded.org
> Unsubscribe: https://lists.openembedded.org/g/openembedded-core/unsub [raj.khem@gmail.com]
> -=-=-=-=-=-=-=-=-=-=-=-
>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2022-04-07 20:36 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-04-07 12:26 [PATCH] gcc: upgrade 11.2 -> current 12 snapshot Bernhard Rosenkränzer
2022-04-07 12:32 ` [OE-core] " Richard Purdie
2022-04-07 13:29 ` Bernhard Rosenkränzer
2022-04-07 20:07 ` [OE-core] " Khem Raj
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox