From dc03fde77244fda3efa43d6dbeeb3cb6e6f7b972 Mon Sep 17 00:00:00 2001
From: CentOS Sources <bugs@centos.org>
Date: May 10 2022 07:18:55 +0000
Subject: import gcc-8.5.0-10.el8


---

diff --git a/SOURCES/gcc8-Wbidi-chars.patch b/SOURCES/gcc8-Wbidi-chars.patch
new file mode 100644
index 0000000..988defe
--- /dev/null
+++ b/SOURCES/gcc8-Wbidi-chars.patch
@@ -0,0 +1,1644 @@
+commit 51c500269bf53749b107807d84271385fad35628
+Author: Marek Polacek <polacek@redhat.com>
+Date:   Wed Oct 6 14:33:59 2021 -0400
+
+    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.
+
+diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
+index f591b39be5a..cf922812198 100644
+--- a/gcc/c-family/c.opt
++++ b/gcc/c-family/c.opt
+@@ -334,6 +334,30 @@ 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 78ca7738df2..cc85c53aede 100644
+--- a/gcc/doc/invoke.texi
++++ b/gcc/doc/invoke.texi
+@@ -264,7 +264,8 @@ Objective-C and Objective-C++ Dialects}.
+ -Walloc-zero  -Walloc-size-larger-than=@var{n}
+ -Walloca  -Walloca-larger-than=@var{n} @gol
+ -Wno-aggressive-loop-optimizations  -Warray-bounds  -Warray-bounds=@var{n} @gol
+--Wno-attributes  -Wbool-compare  -Wbool-operation @gol
++-Wno-attributes  -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
+ -Wc++-compat  -Wc++11-compat  -Wc++14-compat  @gol
+@@ -5606,6 +5607,23 @@ Warn about declarations using the @code{alias} and similar attributes whose
+ target is incompatible with the type of the alias.  @xref{Function Attributes,
+ ,Declaring Attributes of Functions}.
+ 
++@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-1.c b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c
+new file mode 100644
+index 00000000000..34f5ac19271
+--- /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;
++    /*‮ } ⁦if (isAdmin)⁩ ⁦ begin admins only */
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++        __builtin_printf("You are an admin.\n");
++    /* end admins only ‮ { ⁦*/
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++    return 0;
++}
+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..3f851b69e65
+--- /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.  */
++
++/* RLE‫ LRI⁦ PDF‬ PDI⁩*/
++/* { 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..44d044d82de
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
+@@ -0,0 +1,9 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test that we warn when mixing UCN and UTF-8.  */
++
++const char *s1 = "LRE_‪_PDF_\u202c";
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++const char *s2 = "LRE_\u202a_PDF_‬";
++/* { 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 LRO‭ 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 PDI⁩ 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 --git a/gcc/testsuite/c-c++-common/Wbidi-chars-13.c b/gcc/testsuite/c-c++-common/Wbidi-chars-13.c
+new file mode 100644
+index 00000000000..b2dd9fde752
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-13.c
+@@ -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 RLE‫ 1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s3 = R"(a b c LRO‭ 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_⁦_LRI_⁦_RLE_‫_RLE_‫_RLE_‫_PDI_⁩*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// LRI_⁦_RLE_‫_RLE_‫_RLE_‫_PDI_⁩
++// LRI_⁦_RLO_‮_RLE_‫_RLE_‫_PDI_⁩
++// LRI_⁦_RLO_‮_RLE_‫_PDI_⁩
++// FSI_⁨_RLO_‮_PDI_⁩
++// FSI_⁨_FSI_⁨_RLO_‮_PDI_⁩
++/* { 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 } */
++/*
++ * RLE‫ end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * LRO‭ end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * RLO‮ 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 } */
++/* LRE‪
++   PDF‬ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/* FSI⁨
++   PDI⁩ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++
++/* LRE<‪>
++ *
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-3 } */
++
++/*
++ * LRE<‪>
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++
++/*
++ *
++ * LRE<‪> */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++/* RLI<⁧> */ /* PDI<⁩> */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRE<‪> */ /* PDF<‬> */
++/* { 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<‎> */
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++// LTR<‎>
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++/* RTL<‏> */
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++// RTL<‏>
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++
++const char *s1 = "LTR<‎>";
++/* { 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<‏>";
++/* { 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<‎> */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// LTR<‎>
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* RTL<‏> */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// RTL<‏>
++/* { 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<‎>";
++/* { 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<‏>";
++/* { 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-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; newline⁧/*/ 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, "user‮ ⁦// Check if admin⁩ ⁦")) {
++/* { 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..49f856b9bfe
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
+@@ -0,0 +1,172 @@
++/* 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 LRO‭ 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 LRO‭ 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 PDI⁩ 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 PDI⁩ 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 PDI⁩ 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 PDI⁩ 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 PDI⁩ 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 LRO‭ 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 PDI⁩ 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 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..f5776806c79
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
+@@ -0,0 +1,172 @@
++/* 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 LRO‭ 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 LRO‭ 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 PDI⁩ x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c PDF‬ x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c PDI⁩ 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 PDI⁩ x y z
++   */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* a b c PDF‬ x y z
++   */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* first
++   a b c PDI⁩ 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 PDI⁩ 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 LRO‭ 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 PDI⁩ 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 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..a65d6faf60e
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
+@@ -0,0 +1,130 @@
++/* 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 RLE‫ 1 2 3 PDI⁩ x y  z*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c LRO‭ 1 2 3 PDI⁩ x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLO‮ 1 2 3 PDI⁩ 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 RLE‫ 1 2 3 PDI⁩ x y  z*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c LRO‭ 1 2 3 PDI⁩ x y z 
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLO‮ 1 2 3 PDI⁩ 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 } */
++
++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 RLE‫ 1 2 3 PDI⁩ 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 LRO‭ 1 2 3 PDI⁩ 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 RLO‮ 1 2 3 PDI⁩ 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 LRE‪";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++  const char *s16 = "PDF\u202c LRE\u202a";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++  const char *s17 = "LRE‪ PDF‬";
++  const char *s18 = "LRE\u202a PDF\u202c";
++  const char *s19 = "LRE‪ LRE‪ PDF‬ PDF‬";
++  const char *s20 = "LRE\u202a LRE\u202a PDF\u202c PDF\u202c";
++  const char *s21 = "PDF‬ LRE‪ PDF‬";
++  const char *s22 = "PDF\u202c LRE\u202a PDF\u202c";
++  const char *s23 = "LRE‪ LRE‪ PDF‬";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++  const char *s24 = "LRE\u202a LRE\u202a PDF\u202c";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++  const char *s25 = "PDF‬ LRE‪";
++/* { 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 LRE‪";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++}
++
++int A\u202aB\u2069C;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202bB\u2069c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202db\u2069c2;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202eb\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u2066b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u2067b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u2068b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int A\u202aB\u202c;
++int A\u202aA\u202aB\u202cB\u202c;
++int a_\u202C_\u202a_\u202c;
++int a_\u202a_\u202c_\u202a_\u202c_;
++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 ->‪<- */ int pdf_\u202c_1;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLE ->‫<- */ int pdf_\u202c_2;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRO ->‭<- */ int pdf_\u202c_3;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLO ->‮<- */ int pdf_\u202c_4;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRI ->⁦<-*/ int pdi_\u2069_1;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLI ->⁧<- */ int pdi_\u2069_12;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* FSI ->⁨<- */ int pdi_\u2069_3;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++const char *s1 = "LRE\u202a"; /* PDF ->‬<- */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRE ->‪<- */ 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 3ad52d5e01e..e0dcb7f0529 100644
+--- a/libcpp/include/cpplib.h
++++ b/libcpp/include/cpplib.h
+@@ -305,6 +305,17 @@ enum cpp_normalize_level {
+   normalized_none
+ };
+ 
++/* 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
+@@ -506,6 +517,10 @@ 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
+   {
+@@ -1063,7 +1078,8 @@ enum {
+   CPP_W_PEDANTIC,
+   CPP_W_C90_C99_COMPAT,
+   CPP_W_CXX11_COMPAT,
+-  CPP_W_EXPANSION_TO_DEFINED
++  CPP_W_EXPANSION_TO_DEFINED,
++  CPP_W_BIDIRECTIONAL
+ };
+ 
+ /* Output a diagnostic of some kind.  */
+diff --git a/libcpp/init.c b/libcpp/init.c
+index ca3fbaa5c05..5c15da82ff8 100644
+--- a/libcpp/init.c
++++ b/libcpp/init.c
+@@ -208,6 +208,7 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
+       = 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 4f74f995cec..53b4c0f4af7 100644
+--- a/libcpp/internal.h
++++ b/libcpp/internal.h
+@@ -576,6 +576,13 @@ struct cpp_reader
+   /* If non-null, the lexer will use this location for the next token
+      instead of getting a location from the linemap.  */
+   source_location *forced_token_location_p;
++
++  /* 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 a408f912c5c..ea7f75e842e 100644
+--- a/libcpp/lex.c
++++ b/libcpp/lex.c
+@@ -1164,6 +1164,324 @@ _cpp_process_line_notes (cpp_reader *pfile, int in_comment)
+     }
+ }
+ 
++namespace bidi {
++  enum kind {
++    NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI, LTR, RTL
++  };
++
++  /* All the UTF-8 encodings of bidi characters start with E2.  */
++  const 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) ? PDF : PDI;
++  }
++
++  /* Return which context is currently opened.  */
++  kind current_ctx ()
++  {
++    unsigned int len = vec.count ();
++    if (len == 0)
++      return 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 LRE:
++      case RLE:
++      case LRO:
++      case RLO:
++	vec.push (ucn_p ? 3u : 1u);
++	break;
++      case LRI:
++      case RLI:
++      case 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 PDF:
++	if (current_ctx () == 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 PDI:
++	for (int i = vec.count () - 1; i >= 0; --i)
++	  if (ctx_at (i) == PDI)
++	    {
++	      vec.truncate (i);
++	      break;
++	    }
++	break;
++      case LTR:
++      case RTL:
++	/* These aren't popped by a PDF/PDI.  */
++	break;
++      [[likely]] case NONE:
++	break;
++      default:
++	abort ();
++      }
++  }
++
++  /* Return a descriptive string for K.  */
++  const char *to_str (kind k)
++  {
++    switch (k)
++      {
++      case LRE:
++	return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
++      case RLE:
++	return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
++      case LRO:
++	return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
++      case RLO:
++	return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
++      case LRI:
++	return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
++      case RLI:
++	return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
++      case FSI:
++	return "U+2068 (FIRST STRONG ISOLATE)";
++      case PDF:
++	return "U+202C (POP DIRECTIONAL FORMATTING)";
++      case PDI:
++	return "U+2069 (POP DIRECTIONAL ISOLATE)";
++      case LTR:
++	return "U+200E (LEFT-TO-RIGHT MARK)";
++      case 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::LRE;
++      case 0xab:
++	return bidi::RLE;
++      case 0xac:
++	return bidi::PDF;
++      case 0xad:
++	return bidi::LRO;
++      case 0xae:
++	return bidi::RLO;
++      case 0x8e:
++	return bidi::LTR;
++      case 0x8f:
++	return bidi::RTL;
++      default:
++	break;
++      }
++  else if (p[1] == 0x81)
++    switch (p[2])
++      {
++      case 0xa6:
++	return bidi::LRI;
++      case 0xa7:
++	return bidi::RLI;
++      case 0xa8:
++	return bidi::FSI;
++      case 0xa9:
++	return bidi::PDI;
++      default:
++	break;
++      }
++
++  return bidi::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::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::NONE;
++  else if (p[2] == '2')
++    switch (p[3])
++      {
++      case 'a':
++      case 'A':
++	return bidi::LRE;
++      case 'b':
++      case 'B':
++	return bidi::RLE;
++      case 'c':
++      case 'C':
++	return bidi::PDF;
++      case 'd':
++      case 'D':
++	return bidi::LRO;
++      case 'e':
++      case 'E':
++	return bidi::RLO;
++      default:
++	break;
++      }
++  else if (p[2] == '6')
++    switch (p[3])
++      {
++      case '6':
++	return bidi::LRI;
++      case '7':
++	return bidi::RLI;
++      case '8':
++	return bidi::FSI;
++      case '9':
++	return bidi::PDI;
++      default:
++	break;
++      }
++  else if (p[2] == '0')
++    switch (p[3])
++      {
++      case 'e':
++      case 'E':
++	return bidi::LTR;
++      case 'f':
++      case 'F':
++	return bidi::RTL;
++      default:
++	break;
++      }
++
++  return bidi::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 source_location 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::NONE, 1))
++    return;
++
++  const unsigned char warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
++
++  if (warn_bidi != bidirectional_none)
++    {
++      const source_location 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::PDF || kind == bidi::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 *pfile)
+   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 *pfile)
+       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 *pfile)
+ 	{
+ 	  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 *pfile)
+ 
+ 	  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;
+   source_location 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;
+@@ -1315,11 +1669,13 @@ warn_about_normalization (cpp_reader *pfile,
+ 
+ /* Returns TRUE if the sequence starting at buffer->cur is invalid 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 == '$')
+     {
+@@ -1343,6 +1699,12 @@ forms_identifier_p (cpp_reader *pfile, int first,
+     {
+       cppchar_t s;
+       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;
+@@ -1450,6 +1812,7 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
+   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)
+@@ -1472,6 +1835,8 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
+ 	    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);
+@@ -1673,6 +2038,7 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
+   _cpp_buff *first_buff = NULL, *last_buff = NULL;
+   size_t raw_prefix_start;
+   _cpp_line_note *note = &pfile->buffer->notes[pfile->buffer->cur_note];
++  const bool warn_bidi_p = pfile->warn_bidi_p ();
+ 
+   type = (*base == 'L' ? CPP_WSTRING :
+ 	  *base == 'U' ? CPP_STRING32 :
+@@ -1909,8 +2275,15 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
+ 	  cur = 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, cur - 1, get_bidi_utf8 (cur - 1),
++				 /*ucn_p=*/false);
+     }
+ 
++  if (warn_bidi_p)
++    maybe_warn_bidi_on_close (pfile, cur);
++
+   if (CPP_OPTION (pfile, user_literals))
+     {
+       /* If a string format macro, say from inttypes.h, is placed touching
+@@ -2005,15 +2378,27 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
+   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--;
+@@ -2030,6 +2415,11 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
+ 	}
+       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/SOURCES/gcc8-aarch64-mtune-neoverse-512tvb.patch b/SOURCES/gcc8-aarch64-mtune-neoverse-512tvb.patch
new file mode 100644
index 0000000..af0a049
--- /dev/null
+++ b/SOURCES/gcc8-aarch64-mtune-neoverse-512tvb.patch
@@ -0,0 +1,105 @@
+From 9c108bb84d3a2447dac730c455df658be0a2c751 Mon Sep 17 00:00:00 2001
+From: Richard Sandiford <richard.sandiford@arm.com>
+Date: Tue, 17 Aug 2021 15:15:27 +0100
+Subject: [PATCH] aarch64: Add -mtune=neoverse-512tvb
+To: gcc-patches@gcc.gnu.org
+
+This patch adds an option to tune for Neoverse cores that have
+a total vector bandwidth of 512 bits (4x128 for Advanced SIMD
+and a vector-length-dependent equivalent for SVE).  This is intended
+to be a compromise between tuning aggressively for a single core like
+Neoverse V1 (which can be too narrow) and tuning for AArch64 cores
+in general (which can be too wide).
+
+-mcpu=neoverse-512tvb is equivalent to -mcpu=neoverse-v1
+-mtune=neoverse-512tvb.
+
+gcc/
+	* doc/invoke.texi: Document -mtune=neoverse-512tvb and
+	-mcpu=neoverse-512tvb.
+	* config/aarch64/aarch64-cores.def (neoverse-512tvb): New entry.
+	* config/aarch64/aarch64-tune.md: Regenerate.
+
+(cherry picked from commit 048039c49b96875144f67e7789fdea54abf7710b)
+---
+ gcc/config/aarch64/aarch64-cores.def |  1 +
+ gcc/config/aarch64/aarch64-tune.md   |  2 +-
+ gcc/doc/invoke.texi                  | 25 ++++++++++++++++++++++---
+ 3 files changed, 24 insertions(+), 4 deletions(-)
+
+diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
+index dfb839c01cc..f348d31e22e 100644
+--- a/gcc/config/aarch64/aarch64-cores.def
++++ b/gcc/config/aarch64/aarch64-cores.def
+@@ -99,6 +99,7 @@ AARCH64_CORE("saphira",     saphira,    falkor,    8_3A,  AARCH64_FL_FOR_ARCH8_3
+ /* ARM ('A') cores. */
+ AARCH64_CORE("zeus", zeus, cortexa57, 8_4A,  AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -1)
+ AARCH64_CORE("neoverse-v1", neoversev1, cortexa57, 8_4A,  AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -1)
++AARCH64_CORE("neoverse-512tvb", neoverse512tvb, cortexa57, 8_4A,  AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversev1, INVALID_IMP, INVALID_CORE, -1)
+ 
+ /* Armv8.5-A Architecture Processors.  */
+ AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, 8_4A,  AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_F16 | AARCH64_FL_SVE | AARCH64_FL_RNG, neoversen2, 0x41, 0xd49, -1)
+diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
+index 2d7c9aa4740..09b76480f0b 100644
+--- a/gcc/config/aarch64/aarch64-tune.md
++++ b/gcc/config/aarch64/aarch64-tune.md
+@@ -1,5 +1,5 @@
+ ;; -*- buffer-read-only: t -*-
+ ;; Generated automatically by gentune.sh from aarch64-cores.def
+ (define_attr "tune"
+-	"cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,ares,neoversen1,saphira,zeus,neoversev1,neoversen2,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55"
++	"cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,ares,neoversen1,saphira,zeus,neoversev1,neoverse512tvb,neoversen2,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55"
+ 	(const (symbol_ref "((enum attr_tune) aarch64_tune)")))
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+index 78ca7738df2..68fda03281a 100644
+--- a/gcc/doc/invoke.texi
++++ b/gcc/doc/invoke.texi
+@@ -14772,9 +14772,9 @@ performance of the code.  Permissible values for this option are:
+ @samp{generic}, @samp{cortex-a35}, @samp{cortex-a53}, @samp{cortex-a55},
+ @samp{cortex-a57}, @samp{cortex-a72}, @samp{cortex-a73}, @samp{cortex-a75},
+ @samp{cortex-a76}, @samp{ares}, @samp{neoverse-n1}, @samp{neoverse-n2},
+-@samp{neoverse-v1}, @samp{zeus}, @samp{exynos-m1}, @samp{falkor},
+-@samp{qdf24xx}, @samp{saphira}, @samp{xgene1}, @samp{vulcan}, @samp{thunderx},
+-@samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},
++@samp{neoverse-v1}, @samp{zeus}, @samp{neoverse-512tvb}, @samp{exynos-m1},
++@samp{falkor}, @samp{qdf24xx}, @samp{saphira}, @samp{xgene1}, @samp{vulcan},
++@samp{thunderx}, @samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},
+ @samp{thunderxt83}, @samp{thunderx2t99}, @samp{cortex-a57.cortex-a53},
+ @samp{cortex-a72.cortex-a53}, @samp{cortex-a73.cortex-a35},
+ @samp{cortex-a73.cortex-a53}, @samp{cortex-a75.cortex-a55},
+@@ -14785,6 +14785,15 @@ The values @samp{cortex-a57.cortex-a53}, @samp{cortex-a72.cortex-a53},
+ @samp{cortex-a75.cortex-a55} specify that GCC should tune for a
+ big.LITTLE system.
+ 
++The value @samp{neoverse-512tvb} specifies that GCC should tune
++for Neoverse cores that (a) implement SVE and (b) have a total vector
++bandwidth of 512 bits per cycle.  In other words, the option tells GCC to
++tune for Neoverse cores that can execute 4 128-bit Advanced SIMD arithmetic
++instructions a cycle and that can execute an equivalent number of SVE
++arithmetic instructions per cycle (2 for 256-bit SVE, 4 for 128-bit SVE).
++This is more general than tuning for a specific core like Neoverse V1
++but is more specific than the default tuning described below.
++
+ Additionally on native AArch64 GNU/Linux systems the value
+ @samp{native} tunes performance to the host system.  This option has no effect
+ if the compiler is unable to recognize the processor of the host system.
+@@ -14814,6 +14823,16 @@ by @option{-mtune}).  Where this option is used in conjunction
+ with @option{-march} or @option{-mtune}, those options take precedence
+ over the appropriate part of this option.
+ 
++@option{-mcpu=neoverse-512tvb} is special in that it does not refer
++to a specific core, but instead refers to all Neoverse cores that
++(a) implement SVE and (b) have a total vector bandwidth of 512 bits
++a cycle.  Unless overridden by @option{-march},
++@option{-mcpu=neoverse-512tvb} generates code that can run on a
++Neoverse V1 core, since Neoverse V1 is the first Neoverse core with
++these properties.  Unless overridden by @option{-mtune},
++@option{-mcpu=neoverse-512tvb} tunes code in the same way as for
++@option{-mtune=neoverse-512tvb}.
++
+ @item -moverride=@var{string}
+ @opindex moverride
+ Override tuning decisions made by the back-end in response to a
+-- 
+2.25.1
+
diff --git a/SOURCES/gcc8-add-Wbidirectional.patch b/SOURCES/gcc8-add-Wbidirectional.patch
deleted file mode 100644
index b907335..0000000
--- a/SOURCES/gcc8-add-Wbidirectional.patch
+++ /dev/null
@@ -1,1263 +0,0 @@
-diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
-index f591b39be5a..3e9a97f4ae2 100644
---- a/gcc/c-family/c.opt
-+++ b/gcc/c-family/c.opt
-@@ -334,6 +334,30 @@ Wbad-function-cast
- C ObjC Var(warn_bad_function_cast) Warning
- Warn about casting functions to incompatible types.
- 
-+Wbidirectional
-+C ObjC C++ ObjC++ Warning Alias(Wbidirectional=,any,none)
-+;
-+
-+Wbidirectional=
-+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)
-+-Wbidirectional=[none|unpaired|any] Warn about UTF-8 bidirectional characters.
-+
-+; Required for these enum values.
-+SourceInclude
-+cpplib.h
-+
-+Enum
-+Name(cpp_bidirectional_level) Type(int) UnknownError(argument %qs to %<-Wbidirectional%> 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 78ca7738df2..7342dd2e142 100644
---- a/gcc/doc/invoke.texi
-+++ b/gcc/doc/invoke.texi
-@@ -264,7 +264,9 @@ Objective-C and Objective-C++ Dialects}.
- -Walloc-zero  -Walloc-size-larger-than=@var{n}
- -Walloca  -Walloca-larger-than=@var{n} @gol
- -Wno-aggressive-loop-optimizations  -Warray-bounds  -Warray-bounds=@var{n} @gol
---Wno-attributes  -Wbool-compare  -Wbool-operation @gol
-+-Wno-attributes  @gol
-+-Wbidirectional=@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
- -Wc++-compat  -Wc++11-compat  -Wc++14-compat  @gol
-@@ -5606,6 +5608,21 @@ Warn about declarations using the @code{alias} and similar attributes whose
- target is incompatible with the type of the alias.  @xref{Function Attributes,
- ,Declaring Attributes of Functions}.
- 
-+@item -Wbidirectional=@r{[}none@r{|}unpaired@r{|}any@r{]}
-+@opindex Wbidirectional=
-+@opindex Wbidirectional
-+@opindex Wno-bidirectional
-+Warn about UTF-8 bidirectional characters.  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{-Wbidirectional=unpaired}, which warns about improperly terminated
-+bidi contexts.  @option{-Wbidirectional=none} turns the warning off.
-+@option{-Wbidirectional=any} warns about any use of bidirectional characters.
-+
- @item -Wbool-compare
- @opindex Wno-bool-compare
- @opindex Wbool-compare
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-1.c b/gcc/testsuite/c-c++-common/Wbidirectional-1.c
-new file mode 100644
-index 00000000000..750de81fdd8
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-1.c
-@@ -0,0 +1,11 @@
-+/* { dg-do compile } */
-+
-+int main() {
-+    int isAdmin = 0;
-+    /*‮ } ⁦if (isAdmin)⁩ ⁦ begin admins only */
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+        __builtin_printf("You are an admin.\n");
-+    /* end admins only ‮ { ⁦*/
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+    return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-10.c b/gcc/testsuite/c-c++-common/Wbidirectional-10.c
-new file mode 100644
-index 00000000000..cd4abeeefbd
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-10.c
-@@ -0,0 +1,27 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=unpaired" } */
-+/* More nesting testing.  */
-+
-+/* RLE‫ LRI⁦ PDF‬ PDI⁩*/
-+/* { 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;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+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/Wbidirectional-11.c b/gcc/testsuite/c-c++-common/Wbidirectional-11.c
-new file mode 100644
-index 00000000000..89ed6e8affc
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-11.c
-@@ -0,0 +1,8 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=unpaired" } */
-+/* Test that we warn when mixing UCN and UTF-8.  */
-+
-+const char *s1 = "LRE_‪_PDF_\u202c";
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-+const char *s2 = "LRE_\u202a_PDF_‬";
-+/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-12.c b/gcc/testsuite/c-c++-common/Wbidirectional-12.c
-new file mode 100644
-index 00000000000..20d1566401a
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-12.c
-@@ -0,0 +1,18 @@
-+/* { dg-do compile { target { c || c++11 } } } */
-+/* { dg-options "-Wbidirectional=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 LRO‭ 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 PDI⁩ 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 --git a/gcc/testsuite/c-c++-common/Wbidirectional-13.c b/gcc/testsuite/c-c++-common/Wbidirectional-13.c
-new file mode 100644
-index 00000000000..08010e3b37b
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-13.c
-@@ -0,0 +1,16 @@
-+/* { dg-do compile { target { c || c++11 } } } */
-+/* { dg-options "-Wbidirectional=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 RLE‫ 1 2 3)";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+const char *s3 = R"(a b c LRO‭ 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/Wbidirectional-2.c b/gcc/testsuite/c-c++-common/Wbidirectional-2.c
-new file mode 100644
-index 00000000000..4e04202e058
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-2.c
-@@ -0,0 +1,8 @@
-+/* { dg-do compile } */
-+
-+int main() {
-+    /* Say hello; newline⁧/*/ return 0 ;
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+    __builtin_printf("Hello world.\n");
-+    return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-3.c b/gcc/testsuite/c-c++-common/Wbidirectional-3.c
-new file mode 100644
-index 00000000000..921300e94e0
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-3.c
-@@ -0,0 +1,10 @@
-+/* { dg-do compile } */
-+
-+int main() {
-+    const char* access_level = "user";
-+    if (__builtin_strcmp(access_level, "user‮ ⁦// Check if admin⁩ ⁦")) {
-+/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
-+        __builtin_printf("You are an admin.\n");
-+    }
-+    return 0;
-+}
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-4.c b/gcc/testsuite/c-c++-common/Wbidirectional-4.c
-new file mode 100644
-index 00000000000..bdf334d9986
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-4.c
-@@ -0,0 +1,149 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=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 LRO‭ 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 LRO‭ 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 PDI⁩ 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 PDI⁩ x y z
-+/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
-+// 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 LRO‭ 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 PDI⁩ 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 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/Wbidirectional-5.c b/gcc/testsuite/c-c++-common/Wbidirectional-5.c
-new file mode 100644
-index 00000000000..08b373a1bda
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-5.c
-@@ -0,0 +1,149 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=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 LRO‭ 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 LRO‭ 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 PDI⁩ x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c PDF‬ x y z */
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// a b c PDI⁩ x y z
-+/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
-+// 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 LRO‭ 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 PDI⁩ 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 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/Wbidirectional-6.c b/gcc/testsuite/c-c++-common/Wbidirectional-6.c
-new file mode 100644
-index 00000000000..c0b37c3a130
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-6.c
-@@ -0,0 +1,129 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=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 RLE‫ 1 2 3 PDI⁩ x y  z*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c LRO‭ 1 2 3 PDI⁩ x y z */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* a b c RLO‮ 1 2 3 PDI⁩ 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 RLE‫ 1 2 3 PDI⁩ x y  z*/
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c LRO‭ 1 2 3 PDI⁩ x y z 
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+// a b c RLO‮ 1 2 3 PDI⁩ 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 } */
-+
-+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 RLE‫ 1 2 3 PDI⁩ 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 LRO‭ 1 2 3 PDI⁩ 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 RLO‮ 1 2 3 PDI⁩ 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 LRE‪";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+  const char *s16 = "PDF\u202c LRE\u202a";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+  const char *s17 = "LRE‪ PDF‬";
-+  const char *s18 = "LRE\u202a PDF\u202c";
-+  const char *s19 = "LRE‪ LRE‪ PDF‬ PDF‬";
-+  const char *s20 = "LRE\u202a LRE\u202a PDF\u202c PDF\u202c";
-+  const char *s21 = "PDF‬ LRE‪ PDF‬";
-+  const char *s22 = "PDF\u202c LRE\u202a PDF\u202c";
-+  const char *s23 = "LRE‪ LRE‪ PDF‬";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+  const char *s24 = "LRE\u202a LRE\u202a PDF\u202c";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+  const char *s25 = "PDF‬ LRE‪";
-+/* { 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 LRE‪";
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+}
-+
-+int A\u202aB\u2069C;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202bB\u2069c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202db\u2069c2;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u202eb\u2069;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u2066b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u2067b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int a\u2068b\u202c;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+int A\u202aB\u202c;
-+int A\u202aA\u202aB\u202cB\u202c;
-+int a_\u202C_\u202a_\u202c;
-+int a_\u202a_\u202c_\u202a_\u202c_;
-+int a_\u202a_\u202c_\u202a_;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-diff --git a/gcc/testsuite/c-c++-common/Wbidirectional-7.c b/gcc/testsuite/c-c++-common/Wbidirectional-7.c
-new file mode 100644
-index 00000000000..f0f7b3ca14a
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-7.c
-@@ -0,0 +1,8 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=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/Wbidirectional-8.c b/gcc/testsuite/c-c++-common/Wbidirectional-8.c
-new file mode 100644
-index 00000000000..c7d02193131
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-8.c
-@@ -0,0 +1,12 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=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/Wbidirectional-9.c b/gcc/testsuite/c-c++-common/Wbidirectional-9.c
-new file mode 100644
-index 00000000000..d029209babb
---- /dev/null
-+++ b/gcc/testsuite/c-c++-common/Wbidirectional-9.c
-@@ -0,0 +1,28 @@
-+/* { dg-do compile } */
-+/* { dg-options "-Wbidirectional=unpaired" } */
-+/* Test that we properly separate bidi contexts (comment/identifier/character
-+   constant/string literal).  */
-+
-+/* LRE ->‪<- */ int pdf_\u202c_1;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLE ->‫<- */ int pdf_\u202c_2;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRO ->‭<- */ int pdf_\u202c_3;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLO ->‮<- */ int pdf_\u202c_4;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRI ->⁦<-*/ int pdi_\u2069_1;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* RLI ->⁧<- */ int pdi_\u2069_12;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* FSI ->⁨<- */ int pdi_\u2069_3;
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+
-+const char *s1 = "LRE\u202a"; /* PDF ->‬<- */
-+/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
-+/* LRE ->‪<- */ 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 3ad52d5e01e..cecbefd59d4 100644
---- a/libcpp/include/cpplib.h
-+++ b/libcpp/include/cpplib.h
-@@ -305,6 +305,17 @@ enum cpp_normalize_level {
-   normalized_none
- };
- 
-+/* The possible bidirectional characters checking levels, from least
-+   restrictive to most.  */
-+enum cpp_bidirectional_level {
-+  /* No checking.  */
-+  bidirectional_none,
-+  /* Only detect unpaired uses of bidirectional characters.  */
-+  bidirectional_unpaired,
-+  /* Detect any use of bidirectional characters.  */
-+  bidirectional_any
-+};
-+
- /* This structure is nested inside struct cpp_reader, and
-    carries all the options visible to the command line.  */
- struct cpp_options
-@@ -506,6 +517,10 @@ struct cpp_options
-   /* True if warn about differences between C++98 and C++11.  */
-   bool cpp_warn_cxx11_compat;
- 
-+  /* Nonzero of bidirectional characters checking is on.  See enum
-+     cpp_bidirectional_level.  */
-+  unsigned char cpp_warn_bidirectional;
-+
-   /* Dependency generation.  */
-   struct
-   {
-@@ -1063,7 +1078,8 @@ enum {
-   CPP_W_PEDANTIC,
-   CPP_W_C90_C99_COMPAT,
-   CPP_W_CXX11_COMPAT,
--  CPP_W_EXPANSION_TO_DEFINED
-+  CPP_W_EXPANSION_TO_DEFINED,
-+  CPP_W_BIDIRECTIONAL
- };
- 
- /* Output a diagnostic of some kind.  */
-diff --git a/libcpp/init.c b/libcpp/init.c
-index ca3fbaa5c05..5c15da82ff8 100644
---- a/libcpp/init.c
-+++ b/libcpp/init.c
-@@ -208,6 +208,7 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
-       = 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/lex.c b/libcpp/lex.c
-index a408f912c5c..3ba0a7ba818 100644
---- a/libcpp/lex.c
-+++ b/libcpp/lex.c
-@@ -1164,6 +1164,284 @@ _cpp_process_line_notes (cpp_reader *pfile, int in_comment)
-     }
- }
- 
-+namespace bidi {
-+  enum kind {
-+    NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI
-+  };
-+
-+  /* All the UTF-8 encodings of bidi characters start with E2.  */
-+  const 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 which context is currently opened.  */
-+  kind current_ctx ()
-+  {
-+    unsigned int len = vec.count ();
-+    if (len == 0)
-+      return NONE;
-+    return (vec[len - 1] & 1) ? PDF : PDI;
-+  }
-+
-+  /* 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 LRE:
-+      case RLE:
-+      case LRO:
-+      case RLO:
-+	vec.push (ucn_p ? 3u : 1u);
-+	break;
-+      case LRI:
-+      case RLI:
-+      case FSI:
-+	vec.push (ucn_p ? 2u : 0u);
-+	break;
-+      case PDF:
-+	if (current_ctx () == PDF)
-+	  pop ();
-+	break;
-+      case PDI:
-+	if (current_ctx () == PDI)
-+	  pop ();
-+	break;
-+      [[likely]] case NONE:
-+	break;
-+      default:
-+	abort ();
-+      }
-+  }
-+
-+  /* Return a descriptive string for K.  */
-+  const char *to_str (kind k)
-+  {
-+    switch (k)
-+      {
-+      case LRE:
-+	return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
-+      case RLE:
-+	return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
-+      case LRO:
-+	return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
-+      case RLO:
-+	return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
-+      case LRI:
-+	return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
-+      case RLI:
-+	return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
-+      case FSI:
-+	return "U+2068 (FIRST STRONG ISOLATE)";
-+      case PDF:
-+	return "U+202C (POP DIRECTIONAL FORMATTING)";
-+      case PDI:
-+	return "U+2069 (POP DIRECTIONAL ISOLATE)";
-+      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::LRE;
-+      case 0xab:
-+	return bidi::RLE;
-+      case 0xac:
-+	return bidi::PDF;
-+      case 0xad:
-+	return bidi::LRO;
-+      case 0xae:
-+	return bidi::RLO;
-+      default:
-+	break;
-+      }
-+  else if (p[1] == 0x81)
-+    switch (p[2])
-+      {
-+      case 0xa6:
-+	return bidi::LRI;
-+      case 0xa7:
-+	return bidi::RLI;
-+      case 0xa8:
-+	return bidi::FSI;
-+      case 0xa9:
-+	return bidi::PDI;
-+      default:
-+	break;
-+      }
-+
-+  return bidi::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::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::NONE;
-+  else if (p[2] == '2')
-+    switch (p[3])
-+      {
-+      case 'a':
-+      case 'A':
-+	return bidi::LRE;
-+      case 'b':
-+      case 'B':
-+	return bidi::RLE;
-+      case 'c':
-+      case 'C':
-+	return bidi::PDF;
-+      case 'd':
-+      case 'D':
-+	return bidi::LRO;
-+      case 'e':
-+      case 'E':
-+	return bidi::RLO;
-+      default:
-+	break;
-+      }
-+  else if (p[2] == '6')
-+    switch (p[3])
-+      {
-+      case '6':
-+	return bidi::LRI;
-+      case '7':
-+	return bidi::RLI;
-+      case '8':
-+	return bidi::FSI;
-+      case '9':
-+	return bidi::PDI;
-+      default:
-+	break;
-+      }
-+
-+  return bidi::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 source_location 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 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::NONE, 1))
-+    return;
-+
-+  const unsigned char warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
-+
-+  if (warn_bidi != bidirectional_none)
-+    {
-+      const source_location 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::PDF || kind == bidi::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.
-@@ -1175,7 +1453,8 @@ _cpp_skip_block_comment (cpp_reader *pfile)
-   cpp_buffer *buffer = pfile->buffer;
-   const uchar *cur = buffer->cur;
-   uchar c;
--
-+  const bool warn_bidi_p = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
-   cur++;
-   if (*cur == '/')
-     cur++;
-@@ -1189,7 +1468,11 @@ _cpp_skip_block_comment (cpp_reader *pfile)
-       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 +1491,8 @@ _cpp_skip_block_comment (cpp_reader *pfile)
- 	{
- 	  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 +1503,13 @@ _cpp_skip_block_comment (cpp_reader *pfile)
- 
- 	  cur = buffer->cur;
- 	}
-+      /* If this is a beginning of a UTF-8 encoding, it might be
-+	 a bidirectional 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 +1525,32 @@ skip_line_comment (cpp_reader *pfile)
- {
-   cpp_buffer *buffer = pfile->buffer;
-   source_location orig_line = pfile->line_table->highest_line;
-+  const bool warn_bidi_p = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
- 
--  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;
-@@ -1315,11 +1630,14 @@ warn_about_normalization (cpp_reader *pfile,
- 
- /* Returns TRUE if the sequence starting at buffer->cur is invalid 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 = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
- 
-   if (*buffer->cur == '$')
-     {
-@@ -1343,6 +1661,12 @@ forms_identifier_p (cpp_reader *pfile, int first,
-     {
-       cppchar_t s;
-       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;
-@@ -1450,6 +1774,8 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
-   const uchar *cur;
-   unsigned int len;
-   unsigned int hash = HT_HASHSTEP (0, *base);
-+  const bool warn_bidi_p = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
- 
-   cur = pfile->buffer->cur;
-   if (! starts_ucn)
-@@ -1472,6 +1798,8 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
- 	    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);
-@@ -1673,6 +2001,8 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
-   _cpp_buff *first_buff = NULL, *last_buff = NULL;
-   size_t raw_prefix_start;
-   _cpp_line_note *note = &pfile->buffer->notes[pfile->buffer->cur_note];
-+  const bool warn_bidi_p = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
- 
-   type = (*base == 'L' ? CPP_WSTRING :
- 	  *base == 'U' ? CPP_STRING32 :
-@@ -1909,8 +2239,16 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
- 	  cur = 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, cur - 1,
-+				 get_bidi_utf8 (cur - 1),
-+				 /*ucn_p=*/false);
-     }
- 
-+  if (warn_bidi_p)
-+    maybe_warn_bidi_on_close (pfile, cur);
-+
-   if (CPP_OPTION (pfile, user_literals))
-     {
-       /* If a string format macro, say from inttypes.h, is placed touching
-@@ -2005,15 +2343,28 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
-   else
-     terminator = '>', type = CPP_HEADER_NAME;
- 
-+  const bool warn_bidi_p = (CPP_OPTION (pfile, cpp_warn_bidirectional)
-+			    != bidirectional_none);
-   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--;
-@@ -2030,6 +2381,11 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
- 	}
-       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/SOURCES/gcc8-pch-tweaks.patch b/SOURCES/gcc8-pch-tweaks.patch
new file mode 100644
index 0000000..6d25329
--- /dev/null
+++ b/SOURCES/gcc8-pch-tweaks.patch
@@ -0,0 +1,844 @@
+commit fe7c3ecff1f9c0520090a77fa824d8c5d9dbec12
+Author: Jakub Jelinek <jakub@redhat.com>
+Date:   Fri Dec 3 11:03:30 2021 +0100
+
+    pch: Add support for PCH for relocatable executables [PR71934]
+    
+    So, if we want to make PCH work for PIEs, I'd say we can:
+    1) add a new GTY option, say callback, which would act like
+       skip for non-PCH and for PCH would make us skip it but
+       remember for address bias translation
+    2) drop the skip for tree_translation_unit_decl::language
+    3) change get_unnamed_section to have const char * as
+       last argument instead of const void *, change
+       unnamed_section::data also to const char * and update
+       everything related to that
+    4) maybe add a host hook whether it is ok to support binaries
+       changing addresses (the only thing I'm worried is if
+       some host that uses function descriptors allocates them
+       dynamically instead of having them somewhere in the
+       executable)
+    5) maybe add a gengtype warning if it sees in GTY tracked
+       structure a function pointer without that new callback
+       option
+    
+    Here is 1), 2), 3) implemented.
+    
+    Note, on stdc++.h.gch/O2g.gch there are just those 10 relocations without
+    the second patch, with it a few more, but nothing huge.  And for non-PIEs
+    there isn't really any extra work on the load side except freading two scalar
+    values and fseek.
+    
+    2021-12-03  Jakub Jelinek  <jakub@redhat.com>
+    
+            PR pch/71934
+    gcc/
+            * ggc.h (gt_pch_note_callback): Declare.
+            * gengtype.h (enum typekind): Add TYPE_CALLBACK.
+            (callback_type): Declare.
+            * gengtype.c (dbgprint_count_type_at): Handle TYPE_CALLBACK.
+            (callback_type): New variable.
+            (process_gc_options): Add CALLBACK argument, handle callback
+            option.
+            (set_gc_used_type): Adjust process_gc_options caller, if callback,
+            set type to &callback_type.
+            (output_mangled_typename): Handle TYPE_CALLBACK.
+            (walk_type): Likewise.  Handle callback option.
+            (write_types_process_field): Handle TYPE_CALLBACK.
+            (write_types_local_user_process_field): Likewise.
+            (write_types_local_process_field): Likewise.
+            (write_root): Likewise.
+            (dump_typekind): Likewise.
+            (dump_type): Likewise.
+            * gengtype-state.c (type_lineloc): Handle TYPE_CALLBACK.
+            (state_writer::write_state_callback_type): New method.
+            (state_writer::write_state_type): Handle TYPE_CALLBACK.
+            (read_state_callback_type): New function.
+            (read_state_type): Handle TYPE_CALLBACK.
+            * ggc-common.c (callback_vec): New variable.
+            (gt_pch_note_callback): New function.
+            (gt_pch_save): Stream out gt_pch_save function address and relocation
+            table.
+            (gt_pch_restore): Stream in saved gt_pch_save function address and
+            relocation table and apply relocations if needed.
+            * doc/gty.texi (callback): Document new GTY option.
+            * varasm.c (get_unnamed_section): Change callback argument's type and
+            last argument's type from const void * to const char *.
+            (output_section_asm_op): Change argument's type from const void *
+            to const char *, remove unnecessary cast.
+            * tree-core.h (struct tree_translation_unit_decl): Drop GTY((skip))
+            from language member.
+            * output.h (unnamed_section_callback): Change argument type from
+            const void * to const char *.
+            (struct unnamed_section): Use GTY((callback)) instead of GTY((skip))
+            for callback member.  Change data member type from const void *
+            to const char *.
+            (struct noswitch_section): Use GTY((callback)) instead of GTY((skip))
+            for callback member.
+            (get_unnamed_section): Change callback argument's type and
+            last argument's type from const void * to const char *.
+            (output_section_asm_op): Change argument's type from const void *
+            to const char *.
+            * config/avr/avr.c (avr_output_progmem_section_asm_op): Likewise.
+            Remove unneeded cast.
+            * config/darwin.c (output_objc_section_asm_op): Change argument's type
+            from const void * to const char *.
+            * config/pa/pa.c (som_output_text_section_asm_op): Likewise.
+            (som_output_comdat_data_section_asm_op): Likewise.
+            * config/rs6000/rs6000.c (rs6000_elf_output_toc_section_asm_op):
+            Likewise.
+            (rs6000_xcoff_output_readonly_section_asm_op): Likewise.  Instead
+            of dereferencing directive hardcode variable names and decide based on
+            whether directive is NULL or not.
+            (rs6000_xcoff_output_readwrite_section_asm_op): Change argument's type
+            from const void * to const char *.
+            (rs6000_xcoff_output_tls_section_asm_op): Likewise.  Instead
+            of dereferencing directive hardcode variable names and decide based on
+            whether directive is NULL or not.
+            (rs6000_xcoff_output_toc_section_asm_op): Change argument's type
+            from const void * to const char *.
+            (rs6000_xcoff_asm_init_sections): Adjust get_unnamed_section callers.
+    gcc/c-family/
+            * c-pch.c (struct c_pch_validity): Remove pch_init member.
+            (pch_init): Don't initialize v.pch_init.
+            (c_common_valid_pch): Don't warn and punt if .text addresses change.
+    libcpp/
+            * include/line-map.h (class line_maps): Add GTY((callback)) to
+            reallocator and round_alloc_size members.
+
+commit 4dc6d19222581c77a174d44d97507d234fb7e39b
+Author: Jakub Jelinek <jakub@redhat.com>
+Date:   Mon Dec 6 11:18:58 2021 +0100
+
+    avr: Fix AVR build [PR71934]
+    
+    On Mon, Dec 06, 2021 at 11:00:30AM +0100, Martin Liška wrote:
+    > Jakub, I think the patch broke avr-linux target:
+    >
+    > g++  -fno-PIE -c   -g   -DIN_GCC  -DCROSS_DIRECTORY_STRUCTURE   -fno-exceptions -fno-rtti -fasynchronous-unwind-tables -W -Wall -Wno-narrowing -Wwrite-strings -Wcast-qual -Wno-erro
+    > /home/marxin/Programming/gcc/gcc/config/avr/avr.c: In function ‘void avr_output_data_section_asm_op(const void*)’:
+    > /home/marxin/Programming/gcc/gcc/config/avr/avr.c:10097:26: error: invalid conversion from ‘const void*’ to ‘const char*’ [-fpermissive]
+    
+    This patch fixes that.
+    
+    2021-12-06  Jakub Jelinek  <jakub@redhat.com>
+    
+            PR pch/71934
+            * config/avr/avr.c (avr_output_data_section_asm_op,
+            avr_output_bss_section_asm_op): Change argument type from const void *
+            to const char *.
+
+diff --git a/gcc/c-family/c-pch.c b/gcc/c-family/c-pch.c
+index 5da60423354..2cafa1387bb 100644
+--- a/gcc/c-family/c-pch.c
++++ b/gcc/c-family/c-pch.c
+@@ -58,7 +58,6 @@ struct c_pch_validity
+ {
+   unsigned char debug_info_type;
+   signed char match[MATCH_SIZE];
+-  void (*pch_init) (void);
+   size_t target_data_length;
+ };
+ 
+@@ -123,7 +122,6 @@ pch_init (void)
+ 	gcc_assert (v.match[i] == *pch_matching[i].flag_var);
+       }
+   }
+-  v.pch_init = &pch_init;
+   target_validity = targetm.get_pch_validity (&v.target_data_length);
+ 
+   if (fwrite (partial_pch, IDENT_LENGTH, 1, f) != 1
+@@ -287,20 +285,6 @@ c_common_valid_pch (cpp_reader *pfile, c
+ 	}
+   }
+ 
+-  /* If the text segment was not loaded at the same address as it was
+-     when the PCH file was created, function pointers loaded from the
+-     PCH will not be valid.  We could in theory remap all the function
+-     pointers, but no support for that exists at present.
+-     Since we have the same executable, it should only be necessary to
+-     check one function.  */
+-  if (v.pch_init != &pch_init)
+-    {
+-      if (cpp_get_options (pfile)->warn_invalid_pch)
+-	cpp_error (pfile, CPP_DL_WARNING,
+-		   "%s: had text segment at different address", name);
+-      return 2;
+-    }
+-
+   /* Check the target-specific validity data.  */
+   {
+     void *this_file_data = xmalloc (v.target_data_length);
+diff --git a/gcc/config/avr/avr.c b/gcc/config/avr/avr.c
+index 200701a583c..6ba038881d6 100644
+--- a/gcc/config/avr/avr.c
++++ b/gcc/config/avr/avr.c
+@@ -10114,10 +10114,9 @@ avr_output_bss_section_asm_op (const void *data)
+ /* Unnamed section callback for progmem*.data sections.  */
+ 
+ static void
+-avr_output_progmem_section_asm_op (const void *data)
++avr_output_progmem_section_asm_op (const char *data)
+ {
+-  fprintf (asm_out_file, "\t.section\t%s,\"a\",@progbits\n",
+-           (const char*) data);
++  fprintf (asm_out_file, "\t.section\t%s,\"a\",@progbits\n", data);
+ }
+ 
+ 
+diff --git a/gcc/config/darwin.c b/gcc/config/darwin.c
+index c5ba7927ce1..8ad5b26c980 100644
+--- a/gcc/config/darwin.c
++++ b/gcc/config/darwin.c
+@@ -134,7 +134,7 @@ int emit_aligned_common = false;
+    DIRECTIVE is as for output_section_asm_op.  */
+ 
+ static void
+-output_objc_section_asm_op (const void *directive)
++output_objc_section_asm_op (const char *directive)
+ {
+   static bool been_here = false;
+ 
+diff --git a/gcc/config/pa/pa.c b/gcc/config/pa/pa.c
+index f22d25a4066..2b10ef34061 100644
+--- a/gcc/config/pa/pa.c
++++ b/gcc/config/pa/pa.c
+@@ -10009,7 +10009,7 @@ pa_arg_partial_bytes (cumulative_args_t cum_v, const function_arg_info &arg)
+    to the default text subspace.  */
+ 
+ static void
+-som_output_text_section_asm_op (const void *data ATTRIBUTE_UNUSED)
++som_output_text_section_asm_op (const char *data ATTRIBUTE_UNUSED)
+ {
+   gcc_assert (TARGET_SOM);
+   if (TARGET_GAS)
+@@ -10053,7 +10053,7 @@ som_output_text_section_asm_op (const void *data ATTRIBUTE_UNUSED)
+    sections.  This function is only used with SOM.  */
+ 
+ static void
+-som_output_comdat_data_section_asm_op (const void *data)
++som_output_comdat_data_section_asm_op (const char *data)
+ {
+   in_section = NULL;
+   output_section_asm_op (data);
+diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
+index 945157b1c1a..34089743759 100644
+--- a/gcc/config/rs6000/rs6000.c
++++ b/gcc/config/rs6000/rs6000.c
+@@ -20599,7 +20599,7 @@ rs6000_ms_bitfield_layout_p (const_tree record_type)
+ /* A get_unnamed_section callback, used for switching to toc_section.  */
+ 
+ static void
+-rs6000_elf_output_toc_section_asm_op (const void *data ATTRIBUTE_UNUSED)
++rs6000_elf_output_toc_section_asm_op (const char *data ATTRIBUTE_UNUSED)
+ {
+   if ((DEFAULT_ABI == ABI_AIX || DEFAULT_ABI == ABI_ELFv2)
+       && TARGET_MINIMAL_TOC)
+@@ -21303,35 +21303,39 @@ rs6000_xcoff_asm_globalize_label (FILE *stream, const char *name)
+    points to the section string variable.  */
+ 
+ static void
+-rs6000_xcoff_output_readonly_section_asm_op (const void *directive)
++rs6000_xcoff_output_readonly_section_asm_op (const char *directive)
+ {
+   fprintf (asm_out_file, "\t.csect %s[RO],%s\n",
+-	   *(const char *const *) directive,
++	   directive
++	   ? xcoff_private_rodata_section_name
++	   : xcoff_read_only_section_name,
+ 	   XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
+ }
+ 
+ /* Likewise for read-write sections.  */
+ 
+ static void
+-rs6000_xcoff_output_readwrite_section_asm_op (const void *directive)
++rs6000_xcoff_output_readwrite_section_asm_op (const char *)
+ {
+   fprintf (asm_out_file, "\t.csect %s[RW],%s\n",
+-	   *(const char *const *) directive,
++	   xcoff_private_data_section_name,
+ 	   XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
+ }
+ 
+ static void
+-rs6000_xcoff_output_tls_section_asm_op (const void *directive)
++rs6000_xcoff_output_tls_section_asm_op (const char *directive)
+ {
+   fprintf (asm_out_file, "\t.csect %s[TL],%s\n",
+-	   *(const char *const *) directive,
++	   directive
++	   ? xcoff_private_data_section_name
++	   : xcoff_tls_data_section_name,
+ 	   XCOFF_CSECT_DEFAULT_ALIGNMENT_STR);
+ }
+ 
+ /* A get_unnamed_section callback, used for switching to toc_section.  */
+ 
+ static void
+-rs6000_xcoff_output_toc_section_asm_op (const void *data ATTRIBUTE_UNUSED)
++rs6000_xcoff_output_toc_section_asm_op (const char *data ATTRIBUTE_UNUSED)
+ {
+   if (TARGET_MINIMAL_TOC)
+     {
+@@ -21358,26 +21362,26 @@ rs6000_xcoff_asm_init_sections (void)
+ {
+   read_only_data_section
+     = get_unnamed_section (0, rs6000_xcoff_output_readonly_section_asm_op,
+-			   &xcoff_read_only_section_name);
++			   NULL);
+ 
+   private_data_section
+     = get_unnamed_section (SECTION_WRITE,
+ 			   rs6000_xcoff_output_readwrite_section_asm_op,
+-			   &xcoff_private_data_section_name);
++			   NULL);
+ 
+   read_only_private_data_section
+     = get_unnamed_section (0, rs6000_xcoff_output_readonly_section_asm_op,
+-			   &xcoff_private_rodata_section_name);
++			   "");
+ 
+   tls_data_section
+     = get_unnamed_section (SECTION_TLS,
+ 			   rs6000_xcoff_output_tls_section_asm_op,
+-			   &xcoff_tls_data_section_name);
++			   NULL);
+ 
+   tls_private_data_section
+     = get_unnamed_section (SECTION_TLS,
+ 			   rs6000_xcoff_output_tls_section_asm_op,
+-			   &xcoff_private_data_section_name);
++			   "");
+ 
+   toc_section
+     = get_unnamed_section (0, rs6000_xcoff_output_toc_section_asm_op, NULL);
+diff --git a/gcc/doc/gty.texi b/gcc/doc/gty.texi
+index b996ff2c44e..ca2c8404894 100644
+--- a/gcc/doc/gty.texi
++++ b/gcc/doc/gty.texi
+@@ -205,6 +205,15 @@ If @code{skip} is applied to a field, the type machinery will ignore it.
+ This is somewhat dangerous; the only safe use is in a union when one
+ field really isn't ever used.
+ 
++@findex callback
++@item callback
++
++@code{callback} should be applied to fields with pointer to function type
++and causes the field to be ignored similarly to @code{skip}, except when
++writing PCH and the field is non-NULL it will remember the field's address
++for relocation purposes if the process writing PCH has different load base
++from a process reading PCH.
++
+ @findex for_user
+ @item for_user
+ 
+diff --git a/gcc/gengtype-state.c b/gcc/gengtype-state.c
+index ac9d536963f..36a96e84574 100644
+--- a/gcc/gengtype-state.c
++++ b/gcc/gengtype-state.c
+@@ -57,6 +57,7 @@ type_lineloc (const_type_p ty)
+     case TYPE_STRING:
+     case TYPE_POINTER:
+     case TYPE_ARRAY:
++    case TYPE_CALLBACK:
+       return NULL;
+     default:
+       gcc_unreachable ();
+@@ -171,6 +172,7 @@ private:
+   void write_state_version (const char *version);
+   void write_state_scalar_type (type_p current);
+   void write_state_string_type (type_p current);
++  void write_state_callback_type (type_p current);
+   void write_state_undefined_type (type_p current);
+   void write_state_struct_union_type (type_p current, const char *kindstr);
+   void write_state_struct_type (type_p current);
+@@ -898,6 +900,20 @@ state_writer::write_state_string_type (type_p current)
+     fatal ("Unexpected type in write_state_string_type");
+ }
+ 
++/* Write the callback type.  There is only one such thing! */
++void
++state_writer::write_state_callback_type (type_p current)
++{
++  if (current == &callback_type)
++    {
++      write_any_indent (0);
++      fprintf (state_file, "callback ");
++      write_state_common_type_content (current);
++    }
++  else
++    fatal ("Unexpected type in write_state_callback_type");
++}
++
+ /* Write an undefined type.  */
+ void
+ state_writer::write_state_undefined_type (type_p current)
+@@ -1143,6 +1159,9 @@ state_writer::write_state_type (type_p current)
+ 	case TYPE_STRING:
+ 	  write_state_string_type (current);
+ 	  break;
++	case TYPE_CALLBACK:
++	  write_state_callback_type (current);
++	  break;
+ 	}
+     }
+ 
+@@ -1477,6 +1496,14 @@ read_state_string_type (type_p *type)
+   read_state_common_type_content (*type);
+ }
+ 
++/* Read the callback_type.  */
++static void
++read_state_callback_type (type_p *type)
++{
++  *type = &callback_type;
++  read_state_common_type_content (*type);
++}
++
+ 
+ /* Read a lang_bitmap representing a set of GCC front-end languages.  */
+ static void
+@@ -1834,6 +1861,11 @@ read_state_type (type_p *current)
+ 	      next_state_tokens (1);
+ 	      read_state_string_type (current);
+ 	    }
++	  else if (state_token_is_name (t0, "callback"))
++	    {
++	      next_state_tokens (1);
++	      read_state_callback_type (current);
++	    }
+ 	  else if (state_token_is_name (t0, "undefined"))
+ 	    {
+ 	      *current = XCNEW (struct type);
+diff --git a/gcc/gengtype.c b/gcc/gengtype.c
+index a77cfd92bfa..b9daaa43689 100644
+--- a/gcc/gengtype.c
++++ b/gcc/gengtype.c
+@@ -172,6 +172,7 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
+   int nb_struct = 0, nb_union = 0, nb_array = 0, nb_pointer = 0;
+   int nb_lang_struct = 0;
+   int nb_user_struct = 0, nb_undefined = 0;
++  int nb_callback = 0;
+   type_p p = NULL;
+   for (p = t; p; p = p->next)
+     {
+@@ -202,6 +203,9 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
+ 	case TYPE_ARRAY:
+ 	  nb_array++;
+ 	  break;
++	case TYPE_CALLBACK:
++	  nb_callback++;
++	  break;
+ 	case TYPE_LANG_STRUCT:
+ 	  nb_lang_struct++;
+ 	  break;
+@@ -217,6 +221,8 @@ dbgprint_count_type_at (const char *fil, int lin, const char *msg, type_p t)
+     fprintf (stderr, "@@%%@@ %d structs, %d unions\n", nb_struct, nb_union);
+   if (nb_pointer > 0 || nb_array > 0)
+     fprintf (stderr, "@@%%@@ %d pointers, %d arrays\n", nb_pointer, nb_array);
++  if (nb_callback > 0)
++    fprintf (stderr, "@@%%@@ %d callbacks\n", nb_callback);
+   if (nb_lang_struct > 0)
+     fprintf (stderr, "@@%%@@ %d lang_structs\n", nb_lang_struct);
+   if (nb_user_struct > 0)
+@@ -495,6 +501,10 @@ struct type scalar_char = {
+   TYPE_SCALAR, 0, 0, 0, GC_USED, {0}
+ };
+ 
++struct type callback_type = {
++  TYPE_CALLBACK, 0, 0, 0, GC_USED, {0}
++};
++
+ /* Lists of various things.  */
+ 
+ pair_p typedefs = NULL;
+@@ -1464,7 +1474,7 @@ static void set_gc_used (pair_p);
+ 
+ static void
+ process_gc_options (options_p opt, enum gc_used_enum level, int *maybe_undef,
+-		    int *length, int *skip, type_p *nested_ptr)
++		    int *length, int *skip, int *callback, type_p *nested_ptr)
+ {
+   options_p o;
+   for (o = opt; o; o = o->next)
+@@ -1478,6 +1488,8 @@ process_gc_options (options_p opt, enum gc_used_enum level, int *maybe_undef,
+       *length = 1;
+     else if (strcmp (o->name, "skip") == 0)
+       *skip = 1;
++    else if (strcmp (o->name, "callback") == 0)
++      *callback = 1;
+     else if (strcmp (o->name, "nested_ptr") == 0
+ 	     && o->kind == OPTION_NESTED)
+       *nested_ptr = ((const struct nested_ptr_data *) o->info.nested)->type;
+@@ -1526,7 +1538,7 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
+ 	type_p dummy2;
+ 	bool allow_undefined_field_types = (t->kind == TYPE_USER_STRUCT);
+ 
+-	process_gc_options (t->u.s.opt, level, &dummy, &dummy, &dummy,
++	process_gc_options (t->u.s.opt, level, &dummy, &dummy, &dummy, &dummy,
+ 			    &dummy2);
+ 
+ 	if (t->u.s.base_class)
+@@ -1542,9 +1554,10 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
+ 	    int maybe_undef = 0;
+ 	    int length = 0;
+ 	    int skip = 0;
++	    int callback = 0;
+ 	    type_p nested_ptr = NULL;
+ 	    process_gc_options (f->opt, level, &maybe_undef, &length, &skip,
+-				&nested_ptr);
++				&callback, &nested_ptr);
+ 
+ 	    if (nested_ptr && f->type->kind == TYPE_POINTER)
+ 	      set_gc_used_type (nested_ptr, GC_POINTED_TO);
+@@ -1554,6 +1567,8 @@ set_gc_used_type (type_p t, enum gc_used_enum level,
+ 	      set_gc_used_type (f->type->u.p, GC_MAYBE_POINTED_TO);
+ 	    else if (skip)
+ 	      ;			/* target type is not used through this field */
++	    else if (callback)
++	      f->type = &callback_type;
+ 	    else
+ 	      set_gc_used_type (f->type, GC_USED, allow_undefined_field_types);
+ 	  }
+@@ -2519,6 +2534,7 @@ output_mangled_typename (outf_p of, const_type_p t)
+       {
+       case TYPE_NONE:
+       case TYPE_UNDEFINED:
++      case TYPE_CALLBACK:
+ 	gcc_unreachable ();
+ 	break;
+       case TYPE_POINTER:
+@@ -2719,6 +2735,8 @@ walk_type (type_p t, struct walk_type_data *d)
+       ;
+     else if (strcmp (oo->name, "for_user") == 0)
+       ;
++    else if (strcmp (oo->name, "callback") == 0)
++      ;
+     else
+       error_at_line (d->line, "unknown option `%s'\n", oo->name);
+ 
+@@ -2744,6 +2762,7 @@ walk_type (type_p t, struct walk_type_data *d)
+     {
+     case TYPE_SCALAR:
+     case TYPE_STRING:
++    case TYPE_CALLBACK:
+       d->process_field (t, d);
+       break;
+ 
+@@ -3275,6 +3294,7 @@ write_types_process_field (type_p f, const struct walk_type_data *d)
+       break;
+ 
+     case TYPE_SCALAR:
++    case TYPE_CALLBACK:
+       break;
+ 
+     case TYPE_ARRAY:
+@@ -3820,6 +3840,7 @@ write_types_local_user_process_field (type_p f, const struct walk_type_data *d)
+       break;
+ 
+     case TYPE_SCALAR:
++    case TYPE_CALLBACK:
+       break;
+ 
+     case TYPE_ARRAY:
+@@ -3906,6 +3927,13 @@ write_types_local_process_field (type_p f, const struct walk_type_data *d)
+     case TYPE_SCALAR:
+       break;
+ 
++    case TYPE_CALLBACK:
++      oprintf (d->of, "%*sif ((void *)(%s) == this_obj)\n", d->indent, "",
++	       d->prev_val[3]);
++      oprintf (d->of, "%*s  gt_pch_note_callback (&(%s), this_obj);\n",
++	       d->indent, "", d->val);
++      break;
++
+     case TYPE_ARRAY:
+     case TYPE_NONE:
+     case TYPE_UNDEFINED:
+@@ -4434,6 +4462,7 @@ write_root (outf_p f, pair_p v, type_p type, const char *name, int has_length,
+     case TYPE_UNDEFINED:
+     case TYPE_UNION:
+     case TYPE_LANG_STRUCT:
++    case TYPE_CALLBACK:
+       error_at_line (line, "global `%s' is unimplemented type", name);
+     }
+ }
+@@ -4728,6 +4757,9 @@ dump_typekind (int indent, enum typekind kind)
+     case TYPE_ARRAY:
+       printf ("TYPE_ARRAY");
+       break;
++    case TYPE_CALLBACK:
++      printf ("TYPE_CALLBACK");
++      break;
+     case TYPE_LANG_STRUCT:
+       printf ("TYPE_LANG_STRUCT");
+       break;
+@@ -4894,6 +4926,7 @@ dump_type (int indent, type_p t)
+ 	      t->u.scalar_is_char ? "true" : "false");
+       break;
+     case TYPE_STRING:
++    case TYPE_CALLBACK:
+       break;
+     case TYPE_STRUCT:
+     case TYPE_UNION:
+diff --git a/gcc/gengtype.h b/gcc/gengtype.h
+index 8a7a54957ea..8fa7064ca85 100644
+--- a/gcc/gengtype.h
++++ b/gcc/gengtype.h
+@@ -154,6 +154,9 @@ enum typekind {
+   TYPE_UNION,           /* Type for GTY-ed discriminated unions.  */
+   TYPE_POINTER,         /* Pointer type to GTY-ed type.  */
+   TYPE_ARRAY,           /* Array of GTY-ed types.  */
++  TYPE_CALLBACK,	/* A function pointer that needs relocation if
++			   the executable has been loaded at a different
++			   address.  */
+   TYPE_LANG_STRUCT,     /* GCC front-end language specific structs.
+                            Various languages may have homonymous but
+                            different structs.  */
+@@ -331,6 +334,9 @@ extern struct type string_type;
+ extern struct type scalar_nonchar;
+ extern struct type scalar_char;
+ 
++/* The one and only TYPE_CALLBACK.  */
++extern struct type callback_type;
++
+ /* Test if a type is a union, either a plain one or a language
+    specific one.  */
+ #define UNION_P(x)					\
+diff --git a/gcc/ggc-common.c b/gcc/ggc-common.c
+index b6abed1d9a2..7c998e95473 100644
+--- a/gcc/ggc-common.c
++++ b/gcc/ggc-common.c
+@@ -256,6 +256,7 @@ saving_hasher::equal (const ptr_data *p1
+ }
+ 
+ static hash_table<saving_hasher> *saving_htab;
++static vec<void *> callback_vec;
+ 
+ /* Register an object in the hash table.  */
+ 
+@@ -288,6 +289,23 @@ gt_pch_note_object (void *obj, void *not
+   return 1;
+ }
+ 
++/* Register address of a callback pointer.  */
++void
++gt_pch_note_callback (void *obj, void *base)
++{
++  void *ptr;
++  memcpy (&ptr, obj, sizeof (void *));
++  if (ptr != NULL)
++    {
++      struct ptr_data *data
++	= (struct ptr_data *)
++	  saving_htab->find_with_hash (base, POINTER_HASH (base));
++      gcc_assert (data);
++      callback_vec.safe_push ((char *) data->new_addr
++			      + ((char *) obj - (char *) base));
++    }
++}
++
+ /* Register an object in the hash table.  */
+ 
+ void
+@@ -582,10 +600,20 @@ gt_pch_save (FILE *f)
+   ggc_pch_finish (state.d, state.f);
+   gt_pch_fixup_stringpool ();
+ 
++  unsigned num_callbacks = callback_vec.length ();
++  void (*pch_save) (FILE *) = &gt_pch_save;
++  if (fwrite (&pch_save, sizeof (pch_save), 1, f) != 1
++      || fwrite (&num_callbacks, sizeof (num_callbacks), 1, f) != 1
++      || (num_callbacks
++	  && fwrite (callback_vec.address (), sizeof (void *), num_callbacks,
++		     f) != num_callbacks))
++    fatal_error (input_location, "cannot write PCH file: %m");
++
+   XDELETE (state.ptrs);
+   XDELETE (this_object);
+   delete saving_htab;
+   saving_htab = NULL;
++  callback_vec.release ();
+ }
+ 
+ /* Read the state of the compiler back in from F.  */
+@@ -639,6 +667,30 @@ gt_pch_restore (FILE *f)
+   ggc_pch_read (f, mmi.preferred_base);
+ 
+   gt_pch_restore_stringpool ();
++
++  void (*pch_save) (FILE *);
++  unsigned num_callbacks;
++  if (fread (&pch_save, sizeof (pch_save), 1, f) != 1
++      || fread (&num_callbacks, sizeof (num_callbacks), 1, f) != 1)
++    fatal_error (input_location, "cannot read PCH file: %m");
++  if (pch_save != &gt_pch_save)
++    {
++      uintptr_t bias = (uintptr_t) &gt_pch_save - (uintptr_t) pch_save;
++      void **ptrs = XNEWVEC (void *, num_callbacks);
++      unsigned i;
++
++      if (fread (ptrs, sizeof (void *), num_callbacks, f) != num_callbacks)
++	fatal_error (input_location, "cannot read PCH file: %m");
++      for (i = 0; i < num_callbacks; ++i)
++	{
++	  memcpy (&pch_save, ptrs[i], sizeof (pch_save));
++	  pch_save = (void (*) (FILE *)) ((uintptr_t) pch_save + bias);
++	  memcpy (ptrs[i], &pch_save, sizeof (pch_save));
++	}
++      XDELETE (ptrs);
++    }
++  else if (fseek (f, num_callbacks * sizeof (void *), SEEK_CUR) != 0)
++    fatal_error (input_location, "cannot read PCH file: %m");
+ }
+ 
+ /* Default version of HOST_HOOKS_GT_PCH_GET_ADDRESS when mmap is not present.
+diff --git a/gcc/ggc.h b/gcc/ggc.h
+index 5e921d957fd..c005f7e0412 100644
+--- a/gcc/ggc.h
++++ b/gcc/ggc.h
+@@ -46,6 +46,10 @@ typedef void (*gt_handle_reorder) (void *, void *, gt_pointer_operator,
+ /* Used by the gt_pch_n_* routines.  Register an object in the hash table.  */
+ extern int gt_pch_note_object (void *, void *, gt_note_pointers);
+ 
++/* Used by the gt_pch_p_* routines.  Register address of a callback
++   pointer.  */
++extern void gt_pch_note_callback (void *, void *);
++
+ /* Used by the gt_pch_n_* routines.  Register that an object has a reorder
+    function.  */
+ extern void gt_pch_note_reorder (void *, void *, gt_handle_reorder);
+diff --git a/gcc/output.h b/gcc/output.h
+index 8f6f15308f4..4a23795bf7e 100644
+--- a/gcc/output.h
++++ b/gcc/output.h
+@@ -456,7 +456,7 @@ struct GTY(()) named_section {
+ 
+ /* A callback that writes the assembly code for switching to an unnamed
+    section.  The argument provides callback-specific data.  */
+-typedef void (*unnamed_section_callback) (const void *);
++typedef void (*unnamed_section_callback) (const char *);
+ 
+ /* Information about a SECTION_UNNAMED section.  */
+ struct GTY(()) unnamed_section {
+@@ -464,8 +464,8 @@ struct GTY(()) unnamed_section {
+ 
+   /* The callback used to switch to the section, and the data that
+      should be passed to the callback.  */
+-  unnamed_section_callback GTY ((skip)) callback;
+-  const void *GTY ((skip)) data;
++  unnamed_section_callback GTY ((callback)) callback;
++  const char *data;
+ 
+   /* The next entry in the chain of unnamed sections.  */
+   section *next;
+@@ -489,7 +489,7 @@ struct GTY(()) noswitch_section {
+   struct section_common common;
+ 
+   /* The callback used to assemble decls in this section.  */
+-  noswitch_section_callback GTY ((skip)) callback;
++  noswitch_section_callback GTY ((callback)) callback;
+ };
+ 
+ /* Information about a section, which may be named or unnamed.  */
+@@ -524,8 +524,8 @@ extern GTY(()) section *bss_noswitch_sec
+ extern GTY(()) section *in_section;
+ extern GTY(()) bool in_cold_section_p;
+ 
+-extern section *get_unnamed_section (unsigned int, void (*) (const void *),
+-				     const void *);
++extern section *get_unnamed_section (unsigned int, void (*) (const char *),
++				     const char *);
+ extern section *get_section (const char *, unsigned int, tree);
+ extern section *get_named_section (tree, const char *, int);
+ extern section *get_variable_section (tree, bool);
+@@ -546,7 +546,7 @@ extern section *get_cdtor_priority_secti
+ 
+ extern bool unlikely_text_section_p (section *);
+ extern void switch_to_section (section *);
+-extern void output_section_asm_op (const void *);
++extern void output_section_asm_op (const char *);
+ 
+ extern void record_tm_clone_pair (tree, tree);
+ extern void finish_tm_clone_pairs (void);
+diff --git a/gcc/tree-core.h b/gcc/tree-core.h
+index 8ab119dc9a2..91ae5237d7e 100644
+--- a/gcc/tree-core.h
++++ b/gcc/tree-core.h
+@@ -1961,7 +1961,7 @@ struct GTY(()) tree_function_decl {
+ struct GTY(()) tree_translation_unit_decl {
+   struct tree_decl_common common;
+   /* Source language of this translation unit.  Used for DWARF output.  */
+-  const char * GTY((skip(""))) language;
++  const char *language;
+   /* TODO: Non-optimization used to build this translation unit.  */
+   /* TODO: Root of a partial DWARF tree for global types and decls.  */
+ };
+diff --git a/gcc/varasm.c b/gcc/varasm.c
+index 9315e2c6936..aff93ca5de9 100644
+--- a/gcc/varasm.c
++++ b/gcc/varasm.c
+@@ -250,8 +250,8 @@ object_block_hasher::hash (object_block *old)
+ /* Return a new unnamed section with the given fields.  */
+ 
+ section *
+-get_unnamed_section (unsigned int flags, void (*callback) (const void *),
+-		     const void *data)
++get_unnamed_section (unsigned int flags, void (*callback) (const char *),
++		     const char *data)
+ {
+   section *sect;
+ 
+@@ -7778,9 +7778,9 @@ file_end_indicate_split_stack (void)
+    a get_unnamed_section callback.  */
+ 
+ void
+-output_section_asm_op (const void *directive)
++output_section_asm_op (const char *directive)
+ {
+-  fprintf (asm_out_file, "%s\n", (const char *) directive);
++  fprintf (asm_out_file, "%s\n", directive);
+ }
+ 
+ /* Emit assembly code to switch to section NEW_SECTION.  Do nothing if
+diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
+index 8b5e2f82982..bc40e333579 100644
+--- a/libcpp/include/line-map.h
++++ b/libcpp/include/line-map.h
+@@ -758,11 +758,11 @@ struct GTY(()) line_maps {
+ 
+   /* If non-null, the allocator to use when resizing 'maps'.  If null,
+      xrealloc is used.  */
+-  line_map_realloc reallocator;
++  line_map_realloc GTY((callback)) reallocator;
+ 
+   /* The allocators' function used to know the actual size it
+      allocated, for a certain allocation size requested.  */
+-  line_map_round_alloc_size_func round_alloc_size;
++  line_map_round_alloc_size_func GTY((callback)) round_alloc_size;
+ 
+   struct location_adhoc_data_map location_adhoc_data_map;
+ 
+diff --git a/gcc/config/avr/avr.c b/gcc/config/avr/avr.c
+index 6ba038881d6..1c2f7d564e7 100644
+--- a/gcc/config/avr/avr.c
++++ b/gcc/config/avr/avr.c
+@@ -10089,7 +10089,7 @@ avr_asm_asm_output_aligned_bss (FILE *file, tree decl, const char *name,
+    to track need of __do_copy_data.  */
+ 
+ static void
+-avr_output_data_section_asm_op (const void *data)
++avr_output_data_section_asm_op (const char *data)
+ {
+   avr_need_copy_data_p = true;
+ 
+@@ -10102,7 +10102,7 @@ avr_output_data_section_asm_op (const void *data)
+    to track need of __do_clear_bss.  */
+ 
+ static void
+-avr_output_bss_section_asm_op (const void *data)
++avr_output_bss_section_asm_op (const char *data)
+ {
+   avr_need_clear_bss_p = true;
+ 
diff --git a/SOURCES/gcc8-pr96796.patch b/SOURCES/gcc8-pr96796.patch
new file mode 100644
index 0000000..46d1d2c
--- /dev/null
+++ b/SOURCES/gcc8-pr96796.patch
@@ -0,0 +1,254 @@
+commit 6001db79c477b03eacc7e7049560921fb54b7845
+Author: Richard Sandiford <richard.sandiford@arm.com>
+Date:   Mon Sep 7 20:15:36 2020 +0100
+
+    lra: Avoid cycling on certain subreg reloads [PR96796]
+    
+    This PR is about LRA cycling for a reload of the form:
+    
+    ----------------------------------------------------------------------------
+    Changing pseudo 196 in operand 1 of insn 103 on equiv [r105:DI*0x8+r140:DI]
+          Creating newreg=287, assigning class ALL_REGS to slow/invalid mem r287
+          Creating newreg=288, assigning class ALL_REGS to slow/invalid mem r288
+      103: r203:SI=r288:SI<<0x1+r196:DI#0
+          REG_DEAD r196:DI
+        Inserting slow/invalid mem reload before:
+      316: r287:DI=[r105:DI*0x8+r140:DI]
+      317: r288:SI=r287:DI#0
+    ----------------------------------------------------------------------------
+    
+    The problem is with r287.  We rightly give it a broad starting class of
+    POINTER_AND_FP_REGS (reduced from ALL_REGS by preferred_reload_class).
+    However, we never make forward progress towards narrowing it down to
+    a specific choice of class (POINTER_REGS or FP_REGS).
+    
+    I think in practice we rely on two things to narrow a reload pseudo's
+    class down to a specific choice:
+    
+    (1) a restricted class is specified when the pseudo is created
+    
+        This happens for input address reloads, where the class is taken
+        from the target's chosen base register class.  It also happens
+        for simple REG reloads, where the class is taken from the chosen
+        alternative's constraints.
+    
+    (2) uses of the reload pseudo as a direct input operand
+    
+        In this case get_reload_reg tries to reuse the existing register
+        and narrow its class, instead of creating a new reload pseudo.
+    
+    However, neither occurs here.  As described above, r287 rightly
+    starts out with a wide choice of class, ultimately derived from
+    ALL_REGS, so we don't get (1).  And as the comments in the PR
+    explain, r287 is never used as an input reload, only the subreg is,
+    so we don't get (2):
+    
+    ----------------------------------------------------------------------------
+             Choosing alt 13 in insn 317:  (0) r  (1) w {*movsi_aarch64}
+          Creating newreg=291, assigning class FP_REGS to r291
+      317: r288:SI=r291:SI
+        Inserting insn reload before:
+      320: r291:SI=r287:DI#0
+    ----------------------------------------------------------------------------
+    
+    IMO, in this case we should rely on the reload of r316 to narrow
+    down the class of r278.  Currently we do:
+    
+    ----------------------------------------------------------------------------
+             Choosing alt 7 in insn 316:  (0) r  (1) m {*movdi_aarch64}
+          Creating newreg=289 from oldreg=287, assigning class GENERAL_REGS to r289
+      316: r289:DI=[r105:DI*0x8+r140:DI]
+        Inserting insn reload after:
+      318: r287:DI=r289:DI
+    ---------------------------------------------------
+    
+    i.e. we create a new pseudo register r289 and give *that* pseudo
+    GENERAL_REGS instead.  This is because get_reload_reg only narrows
+    down the existing class for OP_IN and OP_INOUT, not OP_OUT.
+    
+    But if we have a reload pseudo in a reload instruction and have chosen
+    a specific class for the reload pseudo, I think we should simply install
+    it for OP_OUT reloads too, if the class is a subset of the existing class.
+    We will need to pick such a register whatever happens (for r289 in the
+    example above).  And as explained in the PR, doing this actually avoids
+    an unnecessary move via the FP registers too.
+    
+    The patch is quite aggressive in that it does this for all reload
+    pseudos in all reload instructions.  I wondered about reusing the
+    condition for a reload move in in_class_p:
+    
+              INSN_UID (curr_insn) >= new_insn_uid_start
+              && curr_insn_set != NULL
+              && ((OBJECT_P (SET_SRC (curr_insn_set))
+                   && ! CONSTANT_P (SET_SRC (curr_insn_set)))
+                  || (GET_CODE (SET_SRC (curr_insn_set)) == SUBREG
+                      && OBJECT_P (SUBREG_REG (SET_SRC (curr_insn_set)))
+                      && ! CONSTANT_P (SUBREG_REG (SET_SRC (curr_insn_set)))))))
+    
+    but I can't really justify that on first principles.  I think we
+    should apply the rule consistently until we have a specific reason
+    for doing otherwise.
+    
+    gcc/
+            PR rtl-optimization/96796
+            * lra-constraints.c (in_class_p): Add a default-false
+            allow_all_reload_class_changes_p parameter.  Do not treat
+            reload moves specially when the parameter is true.
+            (get_reload_reg): Try to narrow the class of an existing OP_OUT
+            reload if we're reloading a reload pseudo in a reload instruction.
+    
+    gcc/testsuite/
+            PR rtl-optimization/96796
+            * gcc.c-torture/compile/pr96796.c: New test.
+
+diff --git a/gcc/lra-constraints.c b/gcc/lra-constraints.c
+index 580da9c3ed6..161b721efb1 100644
+--- a/gcc/lra-constraints.c
++++ b/gcc/lra-constraints.c
+@@ -236,12 +236,17 @@ get_reg_class (int regno)
+    CL.  Use elimination first if REG is a hard register.  If REG is a
+    reload pseudo created by this constraints pass, assume that it will
+    be allocated a hard register from its allocno class, but allow that
+-   class to be narrowed to CL if it is currently a superset of CL.
++   class to be narrowed to CL if it is currently a superset of CL and
++   if either:
++
++   - ALLOW_ALL_RELOAD_CLASS_CHANGES_P is true or
++   - the instruction we're processing is not a reload move.
+ 
+    If NEW_CLASS is nonnull, set *NEW_CLASS to the new allocno class of
+    REGNO (reg), or NO_REGS if no change in its class was needed.  */
+ static bool
+-in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class)
++in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class,
++	    bool allow_all_reload_class_changes_p = false)
+ {
+   enum reg_class rclass, common_class;
+   machine_mode reg_mode;
+@@ -266,7 +271,8 @@ in_class_p (rtx reg, enum reg_class cl, enum reg_class *new_class)
+ 	 typically moves that have many alternatives, and restricting
+ 	 reload pseudos for one alternative may lead to situations
+ 	 where other reload pseudos are no longer allocatable.  */
+-      || (INSN_UID (curr_insn) >= new_insn_uid_start
++      || (!allow_all_reload_class_changes_p
++	  && INSN_UID (curr_insn) >= new_insn_uid_start
+ 	  && curr_insn_set != NULL
+ 	  && ((OBJECT_P (SET_SRC (curr_insn_set))
+ 	       && ! CONSTANT_P (SET_SRC (curr_insn_set)))
+@@ -551,13 +557,12 @@ init_curr_insn_input_reloads (void)
+   curr_insn_input_reloads_num = 0;
+ }
+ 
+-/* Create a new pseudo using MODE, RCLASS, ORIGINAL or reuse already
+-   created input reload pseudo (only if TYPE is not OP_OUT).  Don't
+-   reuse pseudo if IN_SUBREG_P is true and the reused pseudo should be
+-   wrapped up in SUBREG.  The result pseudo is returned through
+-   RESULT_REG.  Return TRUE if we created a new pseudo, FALSE if we
+-   reused the already created input reload pseudo.  Use TITLE to
+-   describe new registers for debug purposes.  */
++/* Create a new pseudo using MODE, RCLASS, ORIGINAL or reuse an existing
++   reload pseudo.  Don't reuse an existing reload pseudo if IN_SUBREG_P
++   is true and the reused pseudo should be wrapped up in a SUBREG.
++   The result pseudo is returned through RESULT_REG.  Return TRUE if we
++   created a new pseudo, FALSE if we reused an existing reload pseudo.
++   Use TITLE to describe new registers for debug purposes.  */
+ static bool
+ get_reload_reg (enum op_type type, machine_mode mode, rtx original,
+ 		enum reg_class rclass, bool in_subreg_p,
+@@ -616,6 +621,35 @@ get_reload_reg (enum op_type type, machine_mode mode, rtx original,
+ 
+   if (type == OP_OUT)
+     {
++      /* Output reload registers tend to start out with a conservative
++	 choice of register class.  Usually this is ALL_REGS, although
++	 a target might narrow it (for performance reasons) through
++	 targetm.preferred_reload_class.  It's therefore quite common
++	 for a reload instruction to require a more restrictive class
++	 than the class that was originally assigned to the reload register.
++
++	 In these situations, it's more efficient to refine the choice
++	 of register class rather than create a second reload register.
++	 This also helps to avoid cycling for registers that are only
++	 used by reload instructions.  */
++      if (REG_P (original)
++	  && (int) REGNO (original) >= new_regno_start
++	  && INSN_UID (curr_insn) >= new_insn_uid_start
++	  && in_class_p (original, rclass, &new_class, true))
++	{
++	  unsigned int regno = REGNO (original);
++	  if (lra_dump_file != NULL)
++	    {
++	      fprintf (lra_dump_file, "	 Reuse r%d for output ", regno);
++	      dump_value_slim (lra_dump_file, original, 1);
++	    }
++	  if (new_class != lra_get_allocno_class (regno))
++	    lra_change_class (regno, new_class, ", change to", false);
++	  if (lra_dump_file != NULL)
++	    fprintf (lra_dump_file, "\n");
++	  *result_reg = original;
++	  return false;
++	}
+       *result_reg
+ 	= lra_create_new_reg_with_unique_value (mode, original, rclass, title);
+       return true;
+diff --git a/gcc/testsuite/gcc.c-torture/compile/pr96796.c b/gcc/testsuite/gcc.c-torture/compile/pr96796.c
+new file mode 100644
+index 00000000000..8808e62fe77
+--- /dev/null
++++ b/gcc/testsuite/gcc.c-torture/compile/pr96796.c
+@@ -0,0 +1,55 @@
++/* { dg-additional-options "-fcommon" } */
++
++struct S0 {
++  signed f0 : 8;
++  unsigned f1;
++  unsigned f4;
++};
++struct S1 {
++  long f3;
++  char f4;
++} g_3_4;
++
++int g_5, func_1_l_32, func_50___trans_tmp_31;
++static struct S0 g_144, g_834, g_1255, g_1261;
++
++int g_273[120] = {};
++int *g_555;
++char **g_979;
++static int g_1092_0;
++static int g_1193;
++int safe_mul_func_int16_t_s_s(int si1, int si2) { return si1 * si2; }
++static struct S0 *func_50();
++int func_1() { func_50(g_3_4, g_5, func_1_l_32, 8, 3); }
++void safe_div_func_int64_t_s_s(int *);
++void safe_mod_func_uint32_t_u_u(struct S0);
++struct S0 *func_50(int p_51, struct S0 p_52, struct S1 p_53, int p_54,
++                   int p_55) {
++  int __trans_tmp_30;
++  char __trans_tmp_22;
++  short __trans_tmp_19;
++  long l_985_1;
++  long l_1191[8];
++  safe_div_func_int64_t_s_s(g_273);
++  __builtin_printf((char*)g_1261.f4);
++  safe_mod_func_uint32_t_u_u(g_834);
++  g_144.f0 += 1;
++  for (;;) {
++    struct S1 l_1350 = {&l_1350};
++    for (; p_53.f3; p_53.f3 -= 1)
++      for (; g_1193 <= 2; g_1193 += 1) {
++        __trans_tmp_19 = safe_mul_func_int16_t_s_s(l_1191[l_985_1 + p_53.f3],
++                                                   p_55 % (**g_979 = 10));
++        __trans_tmp_22 = g_1255.f1 * p_53.f4;
++        __trans_tmp_30 = __trans_tmp_19 + __trans_tmp_22;
++        if (__trans_tmp_30)
++          g_1261.f0 = p_51;
++        else {
++          g_1255.f0 = p_53.f3;
++          int *l_1422 = g_834.f0 = g_144.f4 != (*l_1422)++ > 0 < 0 ^ 51;
++          g_555 = ~0;
++          g_1092_0 |= func_50___trans_tmp_31;
++        }
++      }
++  }
++}
diff --git a/SOURCES/gcc8-rh2028609.patch b/SOURCES/gcc8-rh2028609.patch
new file mode 100644
index 0000000..379153b
--- /dev/null
+++ b/SOURCES/gcc8-rh2028609.patch
@@ -0,0 +1,101 @@
+The cprop_hardreg pass is built around the assumption that accessing a
+register in a narrower mode is the same as accessing the lowpart of
+the register.  This unfortunately is not true for vector registers on
+IBM Z. This caused a miscompile of LLVM with GCC 8.5. The problem
+could not be reproduced with upstream GCC unfortunately but we have to
+assume that it is latent there. The right fix would require
+substantial changes to the cprop pass and is certainly something we
+would want for our platform. But since this would not be acceptable
+for older GCCs I'll go with what Vladimir proposed in the RedHat BZ
+and introduce a hopefully temporary and undocumented target hook to
+disable that specific transformation in regcprop.c.
+
+--- a/gcc/config/s390/s390.c
++++ b/gcc/config/s390/s390.c
+@@ -10488,6 +10488,18 @@ s390_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
+   return false;
+ }
+ 
++/* Implement TARGET_NARROW_MODE_REFERS_LOW_PART_P.  */
++
++static bool
++s390_narrow_mode_refers_low_part_p (unsigned int regno)
++{
++  if (reg_classes_intersect_p (VEC_REGS, REGNO_REG_CLASS (regno)))
++    return false;
++
++  return true;
++}
++
++
+ /* Implement TARGET_MODES_TIEABLE_P.  */
+ 
+ static bool
+@@ -16956,6 +16968,9 @@ s390_case_values_threshold (void)
+ #undef TARGET_CASE_VALUES_THRESHOLD
+ #define TARGET_CASE_VALUES_THRESHOLD s390_case_values_threshold
+ 
++#undef TARGET_NARROW_MODE_REFERS_LOW_PART_P
++#define TARGET_NARROW_MODE_REFERS_LOW_PART_P s390_narrow_mode_refers_low_part_p
++
+ struct gcc_target targetm = TARGET_INITIALIZER;
+ 
+ #include "gt-s390.h"
+--- a/gcc/regcprop.c
++++ b/gcc/regcprop.c
+@@ -426,7 +426,8 @@ maybe_mode_change (machine_mode orig_mode, machine_mode copy_mode,
+ 
+   if (orig_mode == new_mode)
+     return gen_raw_REG (new_mode, regno);
+-  else if (mode_change_ok (orig_mode, new_mode, regno))
++  else if (mode_change_ok (orig_mode, new_mode, regno)
++	   && targetm.narrow_mode_refers_low_part_p (copy_regno))
+     {
+       int copy_nregs = hard_regno_nregs (copy_regno, copy_mode);
+       int use_nregs = hard_regno_nregs (copy_regno, new_mode);
+--- a/gcc/target.def
++++ b/gcc/target.def
+@@ -5446,6 +5446,16 @@ value that the middle-end intended.",
+  bool, (machine_mode from, machine_mode to, reg_class_t rclass),
+  hook_bool_mode_mode_reg_class_t_true)
+ 
++/* This hook is used to work around a problem in regcprop. Hardcoded
++assumptions currently prevent it from working correctly for targets
++where the low part of a multi-word register doesn't align to accessing
++the register with a narrower mode.  */
++DEFHOOK_UNDOC
++(narrow_mode_refers_low_part_p,
++"",
++bool, (unsigned int regno),
++hook_bool_uint_true)
++
+ /* Change pseudo allocno class calculated by IRA.  */
+ DEFHOOK
+ (ira_change_pseudo_allocno_class,
+--- a/gcc/hooks.h
++++ b/gcc/hooks.h
+@@ -86,6 +86,7 @@ extern void hook_void_tree (tree);
+ extern void hook_void_tree_treeptr (tree, tree *);
+ extern void hook_void_int_int (int, int);
+ extern void hook_void_gcc_optionsp (struct gcc_options *);
++extern bool hook_bool_uint_true (unsigned int);
+ extern bool hook_bool_uint_uintp_false (unsigned int, unsigned int *);
+ 
+ extern int hook_int_uint_mode_1 (unsigned int, machine_mode);
+--- a/gcc/hooks.c
++++ b/gcc/hooks.c
+@@ -498,6 +498,14 @@ hook_void_gcc_optionsp (struct gcc_optio
+ {
+ }
+ 
++/* Generic hook that takes an unsigned int and returns true.  */
++
++bool
++hook_bool_uint_true (unsigned int)
++{
++  return true;
++}
++
+ /* Generic hook that takes an unsigned int, an unsigned int pointer and
+    returns false.  */
+ 
diff --git a/SPECS/gcc.spec b/SPECS/gcc.spec
index ea4f09c..e029f89 100644
--- a/SPECS/gcc.spec
+++ b/SPECS/gcc.spec
@@ -4,7 +4,7 @@
 %global gcc_major 8
 # Note, gcc_release must be integer, if you want to add suffixes to
 # %%{release}, append them after %%{gcc_release} on Release: line.
-%global gcc_release 4
+%global gcc_release 10
 %global nvptx_tools_gitrev c28050f60193b3b95a18866a96f03334e874e78f
 %global nvptx_newlib_gitrev aadc8eb0ec43b7cd0dd2dfb484bae63c8b05ef24
 %global _unpackaged_files_terminate_build 0
@@ -279,7 +279,11 @@ Patch18: gcc8-remove-old-demangle.patch
 Patch19: gcc8-rh1960701.patch
 Patch20: gcc8-pr100797.patch
 Patch21: gcc8-rh1981822.patch
-Patch22: gcc8-add-Wbidirectional.patch
+Patch22: gcc8-Wbidi-chars.patch
+Patch23: gcc8-pr96796.patch
+Patch24: gcc8-pch-tweaks.patch
+Patch25: gcc8-aarch64-mtune-neoverse-512tvb.patch
+Patch26: gcc8-rh2028609.patch
 
 Patch30: gcc8-rh1668903-1.patch
 Patch31: gcc8-rh1668903-2.patch
@@ -861,6 +865,10 @@ to NVidia PTX capable devices if available.
 %patch20 -p0 -b .pr100797~
 %patch21 -p0 -b .rh1981822~
 %patch22 -p1 -b .bidi~
+%patch23 -p1 -b .pr96796~
+%patch24 -p1 -b .pch-tweaks~
+%patch25 -p1 -b .neoverse~
+%patch26 -p1 -b .rh2028609~
 
 %patch30 -p0 -b .rh1668903-1~
 %patch31 -p0 -b .rh1668903-2~
@@ -1359,7 +1367,7 @@ mkdir -p %{buildroot}/%{_lib}
 mv -f %{buildroot}%{_prefix}/%{_lib}/libgcc_s.so.1 %{buildroot}/%{_lib}/libgcc_s-%{gcc_major}-%{DATE}.so.1
 chmod 755 %{buildroot}/%{_lib}/libgcc_s-%{gcc_major}-%{DATE}.so.1
 ln -sf libgcc_s-%{gcc_major}-%{DATE}.so.1 %{buildroot}/%{_lib}/libgcc_s.so.1
-%ifarch %{ix86} x86_64 ppc ppc64 ppc64p7 ppc64le %{arm}
+%ifarch %{ix86} x86_64 ppc ppc64 ppc64p7 ppc64le %{arm} aarch64
 rm -f $FULLPATH/libgcc_s.so
 echo '/* GNU ld script
    Use the shared library, but some functions are only in
@@ -3177,8 +3185,26 @@ fi
 %endif
 
 %changelog
-* Fri Oct 29 2021 Marek Polacek <polacek@redhat.com> 8.5.0-4
-- add -Wbidirectional patch (#2008391)
+* Thu Jan 27 2022 Marek Polacek <polacek@redhat.com> 8.5.0-10
+- fix typo in the cprop_hardreg patch (#2028609)
+
+* Mon Jan 24 2022 Marek Polacek <polacek@redhat.com> 8.5.0-9
+- apply cprop_hardreg fix for narrow mode != lowpart targets (#2028609)
+
+* Mon Jan 24 2022 Marek Polacek <polacek@redhat.com> 8.5.0-8
+- aarch64: Add -mtune=neoverse-512tvb (#1845932)
+
+* Fri Dec 10 2021 Marek Polacek <polacek@redhat.com> 8.5.0-7
+- backport PCH tweaks (#2030878)
+
+* Fri Dec  3 2021 Marek Polacek <polacek@redhat.com> 8.5.0-6
+- avoid cycling on certain subreg reloads (PR rtl-optimization/96796, #2028798)
+
+* Tue Nov 30 2021 Marek Polacek <polacek@redhat.com> 8.5.0-5
+- when linking against libgcc_s, link libgcc.a too (#2022588)
+
+* Thu Nov 18 2021 Marek Polacek <polacek@redhat.com> 8.5.0-4
+- add -Wbidi-chars patch (#2008392)
 
 * Tue Jul 13 2021 Marek Polacek <polacek@redhat.com> 8.5.0-3
 - fix mangling of lambdas in default args (PR c++/91241, #1981822)