@@ -63,6 +63,10 @@ SRC_URI = "\
file://0002-CVE-2021-35465.patch \
file://0003-CVE-2021-35465.patch \
file://0004-CVE-2021-35465.patch \
+ file://0001-CVE-2021-42574.patch \
+ file://0002-CVE-2021-42574.patch \
+ file://0003-CVE-2021-42574.patch \
+ file://0004-CVE-2021-42574.patch \
"
SRC_URI[sha256sum] = "d08edc536b54c372a1010ff6619dd274c0f1603aa49212ba20f7aa2cda36fa8b"
new file mode 100644
@@ -0,0 +1,2282 @@
+From bd5e882cf6e0def3dd1bc106075d59a303fe0d1e Mon Sep 17 00:00:00 2001
+From: David Malcolm <dmalcolm@redhat.com>
+Date: Mon, 18 Oct 2021 18:55:31 -0400
+Subject: [PATCH] diagnostics: escape non-ASCII source bytes for certain
+ diagnostics
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf8
+Content-Transfer-Encoding: 8bit
+
+This patch adds support to GCC's diagnostic subsystem for escaping certain
+bytes and Unicode characters when quoting source code.
+
+Specifically, this patch adds a new flag rich_location::m_escape_on_output
+which is a hint from a diagnostic that non-ASCII bytes in the pertinent
+lines of the user's source code should be escaped when printed.
+
+The patch sets this for the following diagnostics:
+- when complaining about stray bytes in the program (when these
+are non-printable)
+- when complaining about "null character(s) ignored");
+- for -Wnormalized= (and generate source ranges for such warnings)
+
+The escaping is controlled by a new option:
+ -fdiagnostics-escape-format=[unicode|bytes]
+
+For example, consider a diagnostic involing a source line containing the
+string "before" followed by the Unicode character U+03C0 ("GREEK SMALL
+LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF
+(a stray UTF-8 trailing byte), followed by the string "after", where the
+diagnostic highlights the U+03C0 character.
+
+By default, this line will be printed verbatim to the user when
+reporting a diagnostic at it, as:
+
+ beforeÏXafter
+ ^
+
+(using X for the stray byte to avoid putting invalid UTF-8 in this
+commit message)
+
+If the diagnostic sets the "escape" flag, it will be printed as:
+
+ before<U+03C0><BF>after
+ ^~~~~~~~
+
+with -fdiagnostics-escape-format=unicode (the default), or as:
+
+ before<CF><80><BF>after
+ ^~~~~~~~
+
+if the user supplies -fdiagnostics-escape-format=bytes.
+
+This only affects how the source is printed; it does not affect
+how column numbers that are printed (as per -fdiagnostics-column-unit=
+and -fdiagnostics-column-origin=).
+
+gcc/c-family/ChangeLog:
+ * c-lex.c (c_lex_with_flags): When complaining about non-printable
+ CPP_OTHER tokens, set the "escape on output" flag.
+
+gcc/ChangeLog:
+ * common.opt (fdiagnostics-escape-format=): New.
+ (diagnostics_escape_format): New enum.
+ (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value.
+ (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise.
+ * diagnostic-format-json.cc (json_end_diagnostic): Add
+ "escape-source" attribute.
+ * diagnostic-show-locus.c
+ (exploc_with_display_col::exploc_with_display_col): Replace
+ "tabstop" param with a cpp_char_column_policy and add an "aspect"
+ param. Use these to compute m_display_col accordingly.
+ (struct char_display_policy): New struct.
+ (layout::m_policy): New field.
+ (layout::m_escape_on_output): New field.
+ (def_policy): New function.
+ (make_range): Update for changes to exploc_with_display_col ctor.
+ (default_print_decoded_ch): New.
+ (width_per_escaped_byte): New.
+ (escape_as_bytes_width): New.
+ (escape_as_bytes_print): New.
+ (escape_as_unicode_width): New.
+ (escape_as_unicode_print): New.
+ (make_policy): New.
+ (layout::layout): Initialize new fields. Update m_exploc ctor
+ call for above change to ctor.
+ (layout::maybe_add_location_range): Update for changes to
+ exploc_with_display_col ctor.
+ (layout::calculate_x_offset_display): Update for change to
+ cpp_display_width.
+ (layout::print_source_line): Pass policy
+ to cpp_display_width_computation. Capture cpp_decoded_char when
+ calling process_next_codepoint. Move printing of source code to
+ m_policy.m_print_cb.
+ (line_label::line_label): Pass in policy rather than context.
+ (layout::print_any_labels): Update for change to line_label ctor.
+ (get_affected_range): Pass in policy rather than context, updating
+ calls to location_compute_display_column accordingly.
+ (get_printed_columns): Likewise, also for cpp_display_width.
+ (correction::correction): Pass in policy rather than tabstop.
+ (correction::compute_display_cols): Pass m_policy rather than
+ m_tabstop to cpp_display_width.
+ (correction::m_tabstop): Replace with...
+ (correction::m_policy): ...this.
+ (line_corrections::line_corrections): Pass in policy rather than
+ context.
+ (line_corrections::m_context): Replace with...
+ (line_corrections::m_policy): ...this.
+ (line_corrections::add_hint): Update to use m_policy rather than
+ m_context.
+ (line_corrections::add_hint): Likewise.
+ (layout::print_trailing_fixits): Likewise.
+ (selftest::test_display_widths): New.
+ (selftest::test_layout_x_offset_display_utf8): Update to use
+ policy rather than tabstop.
+ (selftest::test_one_liner_labels_utf8): Add test of escaping
+ source lines.
+ (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to
+ use policy rather than tabstop.
+ (selftest::test_overlapped_fixit_printing): Likewise.
+ (selftest::test_overlapped_fixit_printing_utf8): Likewise.
+ (selftest::test_overlapped_fixit_printing_2): Likewise.
+ (selftest::test_tab_expansion): Likewise.
+ (selftest::test_escaping_bytes_1): New.
+ (selftest::test_escaping_bytes_2): New.
+ (selftest::diagnostic_show_locus_c_tests): Call the new tests.
+ * diagnostic.c (diagnostic_initialize): Initialize
+ context->escape_format.
+ (convert_column_unit): Update to use default character width policy.
+ (selftest::test_diagnostic_get_location_text): Likewise.
+ * diagnostic.h (enum diagnostics_escape_format): New enum.
+ (diagnostic_context::escape_format): New field.
+ * doc/invoke.texi (-fdiagnostics-escape-format=): New option.
+ (-fdiagnostics-format=): Add "escape-source" attribute to examples
+ of JSON output, and document it.
+ * input.c (location_compute_display_column): Pass in "policy"
+ rather than "tabstop", passing to
+ cpp_byte_column_to_display_column.
+ (selftest::test_cpp_utf8): Update to use cpp_char_column_policy.
+ * input.h (class cpp_char_column_policy): New forward decl.
+ (location_compute_display_column): Pass in "policy" rather than
+ "tabstop".
+ * opts.c (common_handle_option): Handle
+ OPT_fdiagnostics_escape_format_.
+ * selftest.c (temp_source_file::temp_source_file): New ctor
+ overload taking a size_t.
+ * selftest.h (temp_source_file::temp_source_file): Likewise.
+
+gcc/testsuite/ChangeLog:
+ * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume
+ "escape-source" attribute.
+ * c-c++-common/diagnostic-format-json-2.c: Likewise.
+ * c-c++-common/diagnostic-format-json-3.c: Likewise.
+ * c-c++-common/diagnostic-format-json-4.c: Likewise, twice.
+ * c-c++-common/diagnostic-format-json-5.c: Likewise.
+ * gcc.dg/cpp/warn-normalized-4-bytes.c: New test.
+ * gcc.dg/cpp/warn-normalized-4-unicode.c: New test.
+ * gcc.dg/encoding-issues-bytes.c: New test.
+ * gcc.dg/encoding-issues-unicode.c: New test.
+ * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume
+ "escape-source" attribute.
+ * gfortran.dg/diagnostic-format-json-2.F90: Likewise.
+ * gfortran.dg/diagnostic-format-json-3.F90: Likewise.
+
+libcpp/ChangeLog:
+ * charset.c (convert_escape): Use encoding_rich_location when
+ complaining about nonprintable unknown escape sequences.
+ (cpp_display_width_computation::::cpp_display_width_computation):
+ Pass in policy rather than tabstop.
+ (cpp_display_width_computation::process_next_codepoint): Add "out"
+ param and populate *out if non-NULL.
+ (cpp_display_width_computation::advance_display_cols): Pass NULL
+ to process_next_codepoint.
+ (cpp_byte_column_to_display_column): Pass in policy rather than
+ tabstop. Pass NULL to process_next_codepoint.
+ (cpp_display_column_to_byte_column): Pass in policy rather than
+ tabstop.
+ * errors.c (cpp_diagnostic_get_current_location): New function,
+ splitting out the logic from...
+ (cpp_diagnostic): ...here.
+ (cpp_warning_at): New function.
+ (cpp_pedwarning_at): New function.
+ * include/cpplib.h (cpp_warning_at): New decl for rich_location.
+ (cpp_pedwarning_at): Likewise.
+ (struct cpp_decoded_char): New.
+ (struct cpp_char_column_policy): New.
+ (cpp_display_width_computation::cpp_display_width_computation):
+ Replace "tabstop" param with "policy".
+ (cpp_display_width_computation::process_next_codepoint): Add "out"
+ param.
+ (cpp_display_width_computation::m_tabstop): Replace with...
+ (cpp_display_width_computation::m_policy): ...this.
+ (cpp_byte_column_to_display_column): Replace "tabstop" param with
+ "policy".
+ (cpp_display_width): Likewise.
+ (cpp_display_column_to_byte_column): Likewise.
+ * include/line-map.h (rich_location::escape_on_output_p): New.
+ (rich_location::set_escape_on_output): New.
+ (rich_location::m_escape_on_output): New.
+ * internal.h (cpp_diagnostic_get_current_location): New decl.
+ (class encoding_rich_location): New.
+ * lex.c (skip_whitespace): Use encoding_rich_location when
+ complaining about null characters.
+ (warn_about_normalization): Generate a source range when
+ complaining about improperly normalized tokens, rather than just a
+ point, and use encoding_rich_location so that the source code
+ is escaped on printing.
+ * line-map.c (rich_location::rich_location): Initialize
+ m_escape_on_output.
+
+Signed-off-by: David Malcolm <dmalcolm@redhat.com>
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bd5e882cf6e0def3dd1bc106075d59a303fe0d1e]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+
+---
+ gcc/c-family/c-lex.c | 6 +-
+ gcc/common.opt | 13 +
+ gcc/diagnostic-format-json.cc | 3 +
+ gcc/diagnostic-show-locus.c | 580 +++++++++++++++---
+ gcc/diagnostic.c | 10 +-
+ gcc/diagnostic.h | 18 +
+ gcc/doc/invoke.texi | 43 +-
+ gcc/input.c | 62 +-
+ gcc/input.h | 7 +-
+ gcc/opts.c | 4 +
+ gcc/selftest.c | 15 +
+ gcc/selftest.h | 2 +
+ .../c-c++-common/diagnostic-format-json-1.c | 1 +
+ .../c-c++-common/diagnostic-format-json-2.c | 1 +
+ .../c-c++-common/diagnostic-format-json-3.c | 1 +
+ .../c-c++-common/diagnostic-format-json-4.c | 2 +
+ .../c-c++-common/diagnostic-format-json-5.c | 1 +
+ .../gcc.dg/cpp/warn-normalized-4-bytes.c | 21 +
+ .../gcc.dg/cpp/warn-normalized-4-unicode.c | 19 +
+ gcc/testsuite/gcc.dg/encoding-issues-bytes.c | Bin 0 -> 595 bytes
+ .../gcc.dg/encoding-issues-unicode.c | Bin 0 -> 613 bytes
+ .../gfortran.dg/diagnostic-format-json-1.F90 | 1 +
+ .../gfortran.dg/diagnostic-format-json-2.F90 | 1 +
+ .../gfortran.dg/diagnostic-format-json-3.F90 | 1 +
+ libcpp/charset.c | 63 +-
+ libcpp/errors.c | 82 ++-
+ libcpp/include/cpplib.h | 76 ++-
+ libcpp/include/line-map.h | 13 +
+ libcpp/internal.h | 23 +
+ libcpp/lex.c | 38 +-
+ libcpp/line-map.c | 3 +-
+ 31 files changed, 942 insertions(+), 168 deletions(-)
+ create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c
+ create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c
+ create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-bytes.c
+ create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-unicode.c
+
+diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
+--- a/gcc/c-family/c-lex.c 2021-07-27 23:55:06.980283060 -0700
++++ b/gcc/c-family/c-lex.c 2021-12-14 01:16:01.541943272 -0800
+@@ -603,7 +603,11 @@ c_lex_with_flags (tree *value, location_
+ else if (ISGRAPH (c))
+ error_at (*loc, "stray %qc in program", (int) c);
+ else
+- error_at (*loc, "stray %<\\%o%> in program", (int) c);
++ {
++ rich_location rich_loc (line_table, *loc);
++ rich_loc.set_escape_on_output (true);
++ error_at (&rich_loc, "stray %<\\%o%> in program", (int) c);
++ }
+ }
+ goto retry;
+
+diff --git a/gcc/common.opt b/gcc/common.opt
+--- a/gcc/common.opt 2021-12-13 22:08:44.939137107 -0800
++++ b/gcc/common.opt 2021-12-14 01:16:01.541943272 -0800
+@@ -1348,6 +1348,10 @@ fdiagnostics-format=
+ Common Joined RejectNegative Enum(diagnostics_output_format)
+ -fdiagnostics-format=[text|json] Select output format.
+
++fdiagnostics-escape-format=
++Common Joined RejectNegative Enum(diagnostics_escape_format)
++-fdiagnostics-escape-format=[unicode|bytes] Select how to escape non-printable-ASCII bytes in the source for diagnostics that suggest it.
++
+ ; Required for these enum values.
+ SourceInclude
+ diagnostic.h
+@@ -1362,6 +1366,15 @@ EnumValue
+ Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE)
+
+ Enum
++Name(diagnostics_escape_format) Type(int)
++
++EnumValue
++Enum(diagnostics_escape_format) String(unicode) Value(DIAGNOSTICS_ESCAPE_FORMAT_UNICODE)
++
++EnumValue
++Enum(diagnostics_escape_format) String(bytes) Value(DIAGNOSTICS_ESCAPE_FORMAT_BYTES)
++
++Enum
+ Name(diagnostics_output_format) Type(int)
+
+ EnumValue
+diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c
+--- a/gcc/diagnostic.c 2021-07-27 23:55:07.232286576 -0700
++++ b/gcc/diagnostic.c 2021-12-14 01:16:01.545943202 -0800
+@@ -230,6 +230,7 @@ diagnostic_initialize (diagnostic_contex
+ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY;
+ context->column_origin = 1;
+ context->tabstop = 8;
++ context->escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
+ context->edit_context_ptr = NULL;
+ context->diagnostic_group_nesting_depth = 0;
+ context->diagnostic_group_emission_count = 0;
+@@ -382,7 +383,10 @@ convert_column_unit (enum diagnostics_co
+ gcc_unreachable ();
+
+ case DIAGNOSTICS_COLUMN_UNIT_DISPLAY:
+- return location_compute_display_column (s, tabstop);
++ {
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
++ return location_compute_display_column (s, policy);
++ }
+
+ case DIAGNOSTICS_COLUMN_UNIT_BYTE:
+ return s.column;
+@@ -2275,8 +2279,8 @@ test_diagnostic_get_location_text ()
+ const char *const content = "smile \xf0\x9f\x98\x82\n";
+ const int line_bytes = strlen (content) - 1;
+ const int def_tabstop = 8;
+- const int display_width = cpp_display_width (content, line_bytes,
+- def_tabstop);
++ const cpp_char_column_policy policy (def_tabstop, cpp_wcwidth);
++ const int display_width = cpp_display_width (content, line_bytes, policy);
+ ASSERT_EQ (line_bytes - 2, display_width);
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ const char *const fname = tmp.get_filename ();
+diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc
+--- a/gcc/diagnostic-format-json.cc 2021-07-27 23:55:07.232286576 -0700
++++ b/gcc/diagnostic-format-json.cc 2021-12-14 01:16:01.541943272 -0800
+@@ -264,6 +264,9 @@ json_end_diagnostic (diagnostic_context
+ json::value *path_value = context->make_json_for_path (context, path);
+ diag_obj->set ("path", path_value);
+ }
++
++ diag_obj->set ("escape-source",
++ new json::literal (richloc->escape_on_output_p ()));
+ }
+
+ /* No-op implementation of "begin_group_cb" for JSON output. */
+diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h
+--- a/gcc/diagnostic.h 2021-07-27 23:55:07.236286632 -0700
++++ b/gcc/diagnostic.h 2021-12-14 01:16:01.545943202 -0800
+@@ -38,6 +38,20 @@ enum diagnostics_column_unit
+ DIAGNOSTICS_COLUMN_UNIT_BYTE
+ };
+
++/* An enum for controlling how to print non-ASCII characters/bytes when
++ a diagnostic suggests escaping the source code on output. */
++
++enum diagnostics_escape_format
++{
++ /* Escape non-ASCII Unicode characters in the form <U+XXXX> and
++ non-UTF-8 bytes in the form <XX>. */
++ DIAGNOSTICS_ESCAPE_FORMAT_UNICODE,
++
++ /* Escape non-ASCII bytes in the form <XX> (thus showing the underlying
++ encoding of non-ASCII Unicode characters). */
++ DIAGNOSTICS_ESCAPE_FORMAT_BYTES
++};
++
+ /* Enum for overriding the standard output format. */
+
+ enum diagnostics_output_format
+@@ -320,6 +334,10 @@ struct diagnostic_context
+ /* The size of the tabstop for tab expansion. */
+ int tabstop;
+
++ /* How should non-ASCII/non-printable bytes be escaped when
++ a diagnostic suggests escaping the source code on output. */
++ enum diagnostics_escape_format escape_format;
++
+ /* If non-NULL, an edit_context to which fix-it hints should be
+ applied, for generating patches. */
+ edit_context *edit_context_ptr;
+diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c
+--- a/gcc/diagnostic-show-locus.c 2021-07-27 23:55:07.232286576 -0700
++++ b/gcc/diagnostic-show-locus.c 2021-12-14 01:16:01.545943202 -0800
+@@ -175,10 +175,26 @@ enum column_unit {
+ class exploc_with_display_col : public expanded_location
+ {
+ public:
+- exploc_with_display_col (const expanded_location &exploc, int tabstop)
+- : expanded_location (exploc),
+- m_display_col (location_compute_display_column (exploc, tabstop))
+- {}
++ exploc_with_display_col (const expanded_location &exploc,
++ const cpp_char_column_policy &policy,
++ enum location_aspect aspect)
++ : expanded_location (exploc),
++ m_display_col (location_compute_display_column (exploc, policy))
++ {
++ if (exploc.column > 0)
++ {
++ /* m_display_col is now the final column of the byte.
++ If escaping has happened, we may want the first column instead. */
++ if (aspect != LOCATION_ASPECT_FINISH)
++ {
++ expanded_location prev_exploc (exploc);
++ prev_exploc.column--;
++ int prev_display_col
++ = (location_compute_display_column (prev_exploc, policy));
++ m_display_col = prev_display_col + 1;
++ }
++ }
++ }
+
+ int m_display_col;
+ };
+@@ -313,6 +329,31 @@ test_line_span ()
+
+ #endif /* #if CHECKING_P */
+
++/* A bundle of information containing how to print unicode
++ characters and bytes when quoting source code.
++
++ Provides a unified place to support escaping some subset
++ of characters to some format.
++
++ Extends char_column_policy; printing is split out to avoid
++ libcpp having to know about pretty_printer. */
++
++struct char_display_policy : public cpp_char_column_policy
++{
++ public:
++ char_display_policy (int tabstop,
++ int (*width_cb) (cppchar_t c),
++ void (*print_cb) (pretty_printer *pp,
++ const cpp_decoded_char &cp))
++ : cpp_char_column_policy (tabstop, width_cb),
++ m_print_cb (print_cb)
++ {
++ }
++
++ void (*m_print_cb) (pretty_printer *pp,
++ const cpp_decoded_char &cp);
++};
++
+ /* A class to control the overall layout when printing a diagnostic.
+
+ The layout is determined within the constructor.
+@@ -345,6 +386,8 @@ class layout
+
+ void print_line (linenum_type row);
+
++ void on_bad_codepoint (const char *ptr, cppchar_t ch, size_t ch_sz);
++
+ private:
+ bool will_show_line_p (linenum_type row) const;
+ void print_leading_fixits (linenum_type row);
+@@ -386,6 +429,7 @@ class layout
+ private:
+ diagnostic_context *m_context;
+ pretty_printer *m_pp;
++ char_display_policy m_policy;
+ location_t m_primary_loc;
+ exploc_with_display_col m_exploc;
+ colorizer m_colorizer;
+@@ -398,6 +442,7 @@ class layout
+ auto_vec <line_span> m_line_spans;
+ int m_linenum_width;
+ int m_x_offset_display;
++ bool m_escape_on_output;
+ };
+
+ /* Implementation of "class colorizer". */
+@@ -646,6 +691,11 @@ layout_range::intersects_line_p (linenum
+ /* Default for when we don't care what the tab expansion is set to. */
+ static const int def_tabstop = 8;
+
++static cpp_char_column_policy def_policy ()
++{
++ return cpp_char_column_policy (8, cpp_wcwidth);
++}
++
+ /* Create some expanded locations for testing layout_range. The filename
+ member of the explocs is set to the empty string. This member will only be
+ inspected by the calls to location_compute_display_column() made from the
+@@ -662,10 +712,13 @@ make_range (int start_line, int start_co
+ = {"", start_line, start_col, NULL, false};
+ const expanded_location finish_exploc
+ = {"", end_line, end_col, NULL, false};
+- return layout_range (exploc_with_display_col (start_exploc, def_tabstop),
+- exploc_with_display_col (finish_exploc, def_tabstop),
++ return layout_range (exploc_with_display_col (start_exploc, def_policy (),
++ LOCATION_ASPECT_START),
++ exploc_with_display_col (finish_exploc, def_policy (),
++ LOCATION_ASPECT_FINISH),
+ SHOW_RANGE_WITHOUT_CARET,
+- exploc_with_display_col (start_exploc, def_tabstop),
++ exploc_with_display_col (start_exploc, def_policy (),
++ LOCATION_ASPECT_CARET),
+ 0, NULL);
+ }
+
+@@ -959,6 +1012,164 @@ fixit_cmp (const void *p_a, const void *
+ return hint_a->get_start_loc () - hint_b->get_start_loc ();
+ }
+
++/* Callbacks for use when not escaping the source. */
++
++/* The default callback for char_column_policy::m_width_cb is cpp_wcwidth. */
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when not escaping the source. */
++
++static void
++default_print_decoded_ch (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ for (const char *ptr = decoded_ch.m_start_byte;
++ ptr != decoded_ch.m_next_byte; ptr++)
++ {
++ if (*ptr == '\0' || *ptr == '\r')
++ {
++ pp_space (pp);
++ continue;
++ }
++
++ pp_character (pp, *ptr);
++ }
++}
++
++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static const int width_per_escaped_byte = 4;
++
++/* Callback for char_column_policy::m_width_cb for determining the
++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static int
++escape_as_bytes_width (cppchar_t ch)
++{
++ if (ch < 0x80 && ISPRINT (ch))
++ return cpp_wcwidth (ch);
++ else
++ {
++ if (ch <= 0x7F) return 1 * width_per_escaped_byte;
++ if (ch <= 0x7FF) return 2 * width_per_escaped_byte;
++ if (ch <= 0xFFFF) return 3 * width_per_escaped_byte;
++ return 4 * width_per_escaped_byte;
++ }
++}
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */
++
++static void
++escape_as_bytes_print (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ if (!decoded_ch.m_valid_ch)
++ {
++ for (const char *iter = decoded_ch.m_start_byte;
++ iter != decoded_ch.m_next_byte; ++iter)
++ {
++ char buf[16];
++ sprintf (buf, "<%02x>", (unsigned char)*iter);
++ pp_string (pp, buf);
++ }
++ return;
++ }
++
++ cppchar_t ch = decoded_ch.m_ch;
++ if (ch < 0x80 && ISPRINT (ch))
++ pp_character (pp, ch);
++ else
++ {
++ for (const char *iter = decoded_ch.m_start_byte;
++ iter < decoded_ch.m_next_byte; ++iter)
++ {
++ char buf[16];
++ sprintf (buf, "<%02x>", (unsigned char)*iter);
++ pp_string (pp, buf);
++ }
++ }
++}
++
++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++/* Callback for char_column_policy::m_width_cb for determining the
++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++static int
++escape_as_unicode_width (cppchar_t ch)
++{
++ if (ch < 0x80 && ISPRINT (ch))
++ return cpp_wcwidth (ch);
++ else
++ {
++ // Width of "<U+%04x>"
++ if (ch > 0xfffff)
++ return 10;
++ else if (ch > 0xffff)
++ return 9;
++ else
++ return 8;
++ }
++}
++
++/* Callback for char_display_policy::m_print_cb for printing source chars
++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */
++
++static void
++escape_as_unicode_print (pretty_printer *pp,
++ const cpp_decoded_char &decoded_ch)
++{
++ if (!decoded_ch.m_valid_ch)
++ {
++ escape_as_bytes_print (pp, decoded_ch);
++ return;
++ }
++
++ cppchar_t ch = decoded_ch.m_ch;
++ if (ch < 0x80 && ISPRINT (ch))
++ pp_character (pp, ch);
++ else
++ {
++ char buf[16];
++ sprintf (buf, "<U+%04X>", ch);
++ pp_string (pp, buf);
++ }
++}
++
++/* Populate a char_display_policy based on DC and RICHLOC. */
++
++static char_display_policy
++make_policy (const diagnostic_context &dc,
++ const rich_location &richloc)
++{
++ /* The default is to not escape non-ASCII bytes. */
++ char_display_policy result
++ (dc.tabstop, cpp_wcwidth, default_print_decoded_ch);
++
++ /* If the diagnostic suggests escaping non-ASCII bytes, then
++ use policy from user-supplied options. */
++ if (richloc.escape_on_output_p ())
++ {
++ result.m_undecoded_byte_width = width_per_escaped_byte;
++ switch (dc.escape_format)
++ {
++ default:
++ gcc_unreachable ();
++ case DIAGNOSTICS_ESCAPE_FORMAT_UNICODE:
++ result.m_width_cb = escape_as_unicode_width;
++ result.m_print_cb = escape_as_unicode_print;
++ break;
++ case DIAGNOSTICS_ESCAPE_FORMAT_BYTES:
++ result.m_width_cb = escape_as_bytes_width;
++ result.m_print_cb = escape_as_bytes_print;
++ break;
++ }
++ }
++
++ return result;
++}
++
+ /* Implementation of class layout. */
+
+ /* Constructor for class layout.
+@@ -975,8 +1186,10 @@ layout::layout (diagnostic_context * con
+ diagnostic_t diagnostic_kind)
+ : m_context (context),
+ m_pp (context->printer),
++ m_policy (make_policy (*context, *richloc)),
+ m_primary_loc (richloc->get_range (0)->m_loc),
+- m_exploc (richloc->get_expanded_location (0), context->tabstop),
++ m_exploc (richloc->get_expanded_location (0), m_policy,
++ LOCATION_ASPECT_CARET),
+ m_colorizer (context, diagnostic_kind),
+ m_colorize_source_p (context->colorize_source_p),
+ m_show_labels_p (context->show_labels_p),
+@@ -986,7 +1199,8 @@ layout::layout (diagnostic_context * con
+ m_fixit_hints (richloc->get_num_fixit_hints ()),
+ m_line_spans (1 + richloc->get_num_locations ()),
+ m_linenum_width (0),
+- m_x_offset_display (0)
++ m_x_offset_display (0),
++ m_escape_on_output (richloc->escape_on_output_p ())
+ {
+ for (unsigned int idx = 0; idx < richloc->get_num_locations (); idx++)
+ {
+@@ -1072,10 +1286,13 @@ layout::maybe_add_location_range (const
+
+ /* Everything is now known to be in the correct source file,
+ but it may require further sanitization. */
+- layout_range ri (exploc_with_display_col (start, m_context->tabstop),
+- exploc_with_display_col (finish, m_context->tabstop),
++ layout_range ri (exploc_with_display_col (start, m_policy,
++ LOCATION_ASPECT_START),
++ exploc_with_display_col (finish, m_policy,
++ LOCATION_ASPECT_FINISH),
+ loc_range->m_range_display_kind,
+- exploc_with_display_col (caret, m_context->tabstop),
++ exploc_with_display_col (caret, m_policy,
++ LOCATION_ASPECT_CARET),
+ original_idx, loc_range->m_label);
+
+ /* If we have a range that finishes before it starts (perhaps
+@@ -1409,7 +1626,7 @@ layout::calculate_x_offset_display ()
+ = get_line_bytes_without_trailing_whitespace (line.get_buffer (),
+ line.length ());
+ int eol_display_column
+- = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop);
++ = cpp_display_width (line.get_buffer (), line_bytes, m_policy);
+ if (caret_display_column > eol_display_column
+ || !caret_display_column)
+ {
+@@ -1488,7 +1705,7 @@ layout::print_source_line (linenum_type
+ /* This object helps to keep track of which display column we are at, which is
+ necessary for computing the line bounds in display units, for doing
+ tab expansion, and for implementing m_x_offset_display. */
+- cpp_display_width_computation dw (line, line_bytes, m_context->tabstop);
++ cpp_display_width_computation dw (line, line_bytes, m_policy);
+
+ /* Skip the first m_x_offset_display display columns. In case the leading
+ portion that will be skipped ends with a character with wcwidth > 1, then
+@@ -1536,7 +1753,8 @@ layout::print_source_line (linenum_type
+ tabs and replacing some control bytes with spaces as necessary. */
+ const char *c = dw.next_byte ();
+ const int start_disp_col = dw.display_cols_processed () + 1;
+- const int this_display_width = dw.process_next_codepoint ();
++ cpp_decoded_char cp;
++ const int this_display_width = dw.process_next_codepoint (&cp);
+ if (*c == '\t')
+ {
+ /* The returned display width is the number of spaces into which the
+@@ -1545,15 +1763,6 @@ layout::print_source_line (linenum_type
+ pp_space (m_pp);
+ continue;
+ }
+- if (*c == '\0' || *c == '\r')
+- {
+- /* cpp_wcwidth() promises to return 1 for all control bytes, and we
+- want to output these as a single space too, so this case is
+- actually the same as the '\t' case. */
+- gcc_assert (this_display_width == 1);
+- pp_space (m_pp);
+- continue;
+- }
+
+ /* We have a (possibly multibyte) character to output; update the line
+ bounds if it is not whitespace. */
+@@ -1565,7 +1774,8 @@ layout::print_source_line (linenum_type
+ }
+
+ /* Output the character. */
+- while (c != dw.next_byte ()) pp_character (m_pp, *c++);
++ m_policy.m_print_cb (m_pp, cp);
++ c = dw.next_byte ();
+ }
+ print_newline ();
+ return lbounds;
+@@ -1664,14 +1874,14 @@ layout::print_annotation_line (linenum_t
+ class line_label
+ {
+ public:
+- line_label (diagnostic_context *context, int state_idx, int column,
++ line_label (const cpp_char_column_policy &policy,
++ int state_idx, int column,
+ label_text text)
+ : m_state_idx (state_idx), m_column (column),
+ m_text (text), m_label_line (0), m_has_vbar (true)
+ {
+ const int bytes = strlen (text.m_buffer);
+- m_display_width
+- = cpp_display_width (text.m_buffer, bytes, context->tabstop);
++ m_display_width = cpp_display_width (text.m_buffer, bytes, policy);
+ }
+
+ /* Sorting is primarily by column, then by state index. */
+@@ -1731,7 +1941,7 @@ layout::print_any_labels (linenum_type r
+ if (text.m_buffer == NULL)
+ continue;
+
+- labels.safe_push (line_label (m_context, i, disp_col, text));
++ labels.safe_push (line_label (m_policy, i, disp_col, text));
+ }
+ }
+
+@@ -2011,7 +2221,7 @@ public:
+
+ /* Get the range of bytes or display columns that HINT would affect. */
+ static column_range
+-get_affected_range (diagnostic_context *context,
++get_affected_range (const cpp_char_column_policy &policy,
+ const fixit_hint *hint, enum column_unit col_unit)
+ {
+ expanded_location exploc_start = expand_location (hint->get_start_loc ());
+@@ -2022,13 +2232,11 @@ get_affected_range (diagnostic_context *
+ int finish_column;
+ if (col_unit == CU_DISPLAY_COLS)
+ {
+- start_column
+- = location_compute_display_column (exploc_start, context->tabstop);
++ start_column = location_compute_display_column (exploc_start, policy);
+ if (hint->insertion_p ())
+ finish_column = start_column - 1;
+ else
+- finish_column
+- = location_compute_display_column (exploc_finish, context->tabstop);
++ finish_column = location_compute_display_column (exploc_finish, policy);
+ }
+ else
+ {
+@@ -2041,12 +2249,13 @@ get_affected_range (diagnostic_context *
+ /* Get the range of display columns that would be printed for HINT. */
+
+ static column_range
+-get_printed_columns (diagnostic_context *context, const fixit_hint *hint)
++get_printed_columns (const cpp_char_column_policy &policy,
++ const fixit_hint *hint)
+ {
+ expanded_location exploc = expand_location (hint->get_start_loc ());
+- int start_column = location_compute_display_column (exploc, context->tabstop);
++ int start_column = location_compute_display_column (exploc, policy);
+ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (),
+- context->tabstop);
++ policy);
+ int final_hint_column = start_column + hint_width - 1;
+ if (hint->insertion_p ())
+ {
+@@ -2056,8 +2265,7 @@ get_printed_columns (diagnostic_context
+ {
+ exploc = expand_location (hint->get_next_loc ());
+ --exploc.column;
+- int finish_column
+- = location_compute_display_column (exploc, context->tabstop);
++ int finish_column = location_compute_display_column (exploc, policy);
+ return column_range (start_column,
+ MAX (finish_column, final_hint_column));
+ }
+@@ -2075,13 +2283,13 @@ public:
+ column_range affected_columns,
+ column_range printed_columns,
+ const char *new_text, size_t new_text_len,
+- int tabstop)
++ const cpp_char_column_policy &policy)
+ : m_affected_bytes (affected_bytes),
+ m_affected_columns (affected_columns),
+ m_printed_columns (printed_columns),
+ m_text (xstrdup (new_text)),
+ m_byte_length (new_text_len),
+- m_tabstop (tabstop),
++ m_policy (policy),
+ m_alloc_sz (new_text_len + 1)
+ {
+ compute_display_cols ();
+@@ -2099,7 +2307,7 @@ public:
+
+ void compute_display_cols ()
+ {
+- m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop);
++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_policy);
+ }
+
+ void overwrite (int dst_offset, const char_span &src_span)
+@@ -2127,7 +2335,7 @@ public:
+ char *m_text;
+ size_t m_byte_length; /* Not including null-terminator. */
+ int m_display_cols;
+- int m_tabstop;
++ const cpp_char_column_policy &m_policy;
+ size_t m_alloc_sz;
+ };
+
+@@ -2163,15 +2371,16 @@ correction::ensure_terminated ()
+ class line_corrections
+ {
+ public:
+- line_corrections (diagnostic_context *context, const char *filename,
++ line_corrections (const char_display_policy &policy,
++ const char *filename,
+ linenum_type row)
+- : m_context (context), m_filename (filename), m_row (row)
++ : m_policy (policy), m_filename (filename), m_row (row)
+ {}
+ ~line_corrections ();
+
+ void add_hint (const fixit_hint *hint);
+
+- diagnostic_context *m_context;
++ const char_display_policy &m_policy;
+ const char *m_filename;
+ linenum_type m_row;
+ auto_vec <correction *> m_corrections;
+@@ -2217,10 +2426,10 @@ source_line::source_line (const char *fi
+ void
+ line_corrections::add_hint (const fixit_hint *hint)
+ {
+- column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES);
+- column_range affected_columns = get_affected_range (m_context, hint,
++ column_range affected_bytes = get_affected_range (m_policy, hint, CU_BYTES);
++ column_range affected_columns = get_affected_range (m_policy, hint,
+ CU_DISPLAY_COLS);
+- column_range printed_columns = get_printed_columns (m_context, hint);
++ column_range printed_columns = get_printed_columns (m_policy, hint);
+
+ /* Potentially consolidate. */
+ if (!m_corrections.is_empty ())
+@@ -2289,7 +2498,7 @@ line_corrections::add_hint (const fixit_
+ printed_columns,
+ hint->get_string (),
+ hint->get_length (),
+- m_context->tabstop));
++ m_policy));
+ }
+
+ /* If there are any fixit hints on source line ROW, print them.
+@@ -2303,7 +2512,7 @@ layout::print_trailing_fixits (linenum_t
+ {
+ /* Build a list of correction instances for the line,
+ potentially consolidating hints (for the sake of readability). */
+- line_corrections corrections (m_context, m_exploc.file, row);
++ line_corrections corrections (m_policy, m_exploc.file, row);
+ for (unsigned int i = 0; i < m_fixit_hints.length (); i++)
+ {
+ const fixit_hint *hint = m_fixit_hints[i];
+@@ -2646,6 +2855,59 @@ namespace selftest {
+
+ /* Selftests for diagnostic_show_locus. */
+
++/* Verify that cpp_display_width correctly handles escaping. */
++
++static void
++test_display_widths ()
++{
++ gcc_rich_location richloc (UNKNOWN_LOCATION);
++
++ /* U+03C0 "GREEK SMALL LETTER PI". */
++ const char *pi = "\xCF\x80";
++ /* U+1F642 "SLIGHTLY SMILING FACE". */
++ const char *emoji = "\xF0\x9F\x99\x82";
++ /* Stray trailing byte of a UTF-8 character. */
++ const char *stray = "\xBF";
++ /* U+10FFFF. */
++ const char *max_codepoint = "\xF4\x8F\xBF\xBF";
++
++ /* No escaping. */
++ {
++ test_diagnostic_context dc;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 1);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 2);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 1);
++ /* Don't check width of U+10FFFF; it's in a private use plane. */
++ }
++
++ richloc.set_escape_on_output (true);
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 9);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4);
++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint),
++ policy),
++ strlen ("<U+10FFFF>"));
++ }
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ char_display_policy policy (make_policy (dc, richloc));
++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8);
++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 16);
++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4);
++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint),
++ policy),
++ 16);
++ }
++}
++
+ /* For precise tests of the layout, make clear where the source line will
+ start. test_left_margin sets the total byte count from the left side of the
+ screen to the start of source lines, after the line number and the separator,
+@@ -2715,10 +2977,10 @@ test_layout_x_offset_display_utf8 (const
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ (line_display_cols,
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (line_display_cols,
+ location_compute_display_column (expand_location (line_end),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1),
+ "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8));
+
+@@ -2866,12 +3128,13 @@ test_layout_x_offset_display_tab (const
+ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1)));
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+- tabstop));
++ policy));
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ location_compute_display_column (expand_location (line_end),
+- tabstop));
++ policy));
+ }
+
+ /* Check that the tab is expanded to the expected number of spaces. */
+@@ -4003,6 +4266,43 @@ test_one_liner_labels_utf8 ()
+ " bb\xf0\x9f\x98\x82\xf0\x9f\x98\x82\n",
+ pp_formatted_text (dc.printer));
+ }
++
++ /* Example of escaping the source lines. */
++ {
++ text_range_label label0 ("label 0\xf0\x9f\x98\x82");
++ text_range_label label1 ("label 1\xcf\x80");
++ text_range_label label2 ("label 2\xcf\x80");
++ gcc_rich_location richloc (foo, &label0);
++ richloc.add_range (bar, SHOW_RANGE_WITHOUT_CARET, &label1);
++ richloc.add_range (field, SHOW_RANGE_WITHOUT_CARET, &label2);
++ richloc.set_escape_on_output (true);
++
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <U+1F602>_foo = <U+03C0>_bar.<U+1F602>_field<U+03C0>;\n"
++ " ^~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~\n"
++ " | | |\n"
++ " | | label 2\xcf\x80\n"
++ " | label 1\xcf\x80\n"
++ " label 0\xf0\x9f\x98\x82\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ
++ (" <f0><9f><98><82>_foo = <cf><80>_bar.<f0><9f><98><82>_field<cf><80>;\n"
++ " ^~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n"
++ " | | |\n"
++ " | | label 2\xcf\x80\n"
++ " | label 1\xcf\x80\n"
++ " label 0\xf0\x9f\x98\x82\n",
++ pp_formatted_text (dc.printer));
++ }
++ }
+ }
+
+ /* Make sure that colorization codes don't interrupt a multibyte
+@@ -4057,9 +4357,9 @@ test_diagnostic_show_locus_one_liner_utf
+
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (),
+- def_tabstop));
++ def_policy ()));
+ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end),
+- def_tabstop));
++ def_policy ()));
+
+ test_one_liner_simple_caret_utf8 ();
+ test_one_liner_caret_and_range_utf8 ();
+@@ -4445,30 +4745,31 @@ test_overlapped_fixit_printing (const li
+ pp_formatted_text (dc.printer));
+
+ /* Unit-test the line_corrections machinery. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_BYTES));
++ get_affected_range (policy, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_BYTES));
++ get_affected_range (policy, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+ ASSERT_EQ (column_range (29, 28),
+- get_affected_range (&dc, hint_2, CU_BYTES));
++ get_affected_range (policy, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (29, 28),
+- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2));
++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (29, 29), get_printed_columns (policy, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (&dc, tmp.get_filename (), 1);
++ line_corrections lc (policy, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4660,30 +4961,31 @@ test_overlapped_fixit_printing_utf8 (con
+ pp_formatted_text (dc.printer));
+
+ /* Unit-test the line_corrections machinery. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (3, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (14, 14),
+- get_affected_range (&dc, hint_0, CU_BYTES));
++ get_affected_range (policy, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (22, 22),
+- get_affected_range (&dc, hint_1, CU_BYTES));
++ get_affected_range (policy, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1));
+ const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
+ ASSERT_EQ (column_range (35, 34),
+- get_affected_range (&dc, hint_2, CU_BYTES));
++ get_affected_range (policy, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (30, 29),
+- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+- ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2));
++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS));
++ ASSERT_EQ (column_range (30, 30), get_printed_columns (policy, hint_2));
+
+ /* Add each hint in turn to a line_corrections instance,
+ and verify that they are consolidated into one correction instance
+ as expected. */
+- line_corrections lc (&dc, tmp.get_filename (), 1);
++ line_corrections lc (policy, tmp.get_filename (), 1);
+
+ /* The first replace hint by itself. */
+ lc.add_hint (hint_0);
+@@ -4877,15 +5179,16 @@ test_overlapped_fixit_printing_2 (const
+ richloc.add_fixit_insert_before (col_21, "}");
+
+ /* These fixits should be accepted; they can't be consolidated. */
++ char_display_policy policy (make_policy (dc, richloc));
+ ASSERT_EQ (2, richloc.get_num_fixit_hints ());
+ const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
+ ASSERT_EQ (column_range (23, 22),
+- get_affected_range (&dc, hint_0, CU_BYTES));
+- ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0));
++ get_affected_range (policy, hint_0, CU_BYTES));
++ ASSERT_EQ (column_range (23, 23), get_printed_columns (policy, hint_0));
+ const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
+ ASSERT_EQ (column_range (21, 20),
+- get_affected_range (&dc, hint_1, CU_BYTES));
+- ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1));
++ get_affected_range (policy, hint_1, CU_BYTES));
++ ASSERT_EQ (column_range (21, 21), get_printed_columns (policy, hint_1));
+
+ /* Verify that they're printed correctly. */
+ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
+@@ -5152,10 +5455,11 @@ test_tab_expansion (const line_table_cas
+ ....................123 45678901234 56789012345 columns */
+
+ const int tabstop = 8;
++ cpp_char_column_policy policy (tabstop, cpp_wcwidth);
+ const int first_non_ws_byte_col = 7;
+ const int right_quote_byte_col = 15;
+ const int last_byte_col = 25;
+- ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop));
++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, policy));
+
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ line_table_test ltt (case_);
+@@ -5198,6 +5502,114 @@ test_tab_expansion (const line_table_cas
+ }
+ }
+
++/* Verify that the escaping machinery can cope with a variety of different
++ invalid bytes. */
++
++static void
++test_escaping_bytes_1 (const line_table_case &case_)
++{
++ const char content[] = "before\0\1\2\3\r\x80\xff""after\n";
++ const size_t sz = sizeof (content);
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz);
++ line_table_test ltt (case_);
++ const line_map_ordinary *ord_map = linemap_check_ordinary
++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0));
++ linemap_line_start (line_table, 1, 100);
++
++ location_t finish
++ = linemap_position_for_line_and_column (line_table, ord_map, 1,
++ strlen (content));
++
++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Locations of the NUL and \r bytes. */
++ location_t nul_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 7);
++ location_t r_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 11);
++ gcc_rich_location richloc (nul_loc);
++ richloc.add_range (r_loc);
++
++ {
++ test_diagnostic_context dc;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" before \1\2\3 \x80\xff""after\n"
++ " ^ ~\n",
++ pp_formatted_text (dc.printer));
++ }
++ richloc.set_escape_on_output (true);
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ
++ (" before<U+0000><U+0001><U+0002><U+0003><U+000D><80><ff>after\n"
++ " ^~~~~~~~ ~~~~~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" before<00><01><02><03><0d><80><ff>after\n"
++ " ^~~~ ~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++}
++
++/* As above, but verify that we handle the initial byte of a line
++ correctly. */
++
++static void
++test_escaping_bytes_2 (const line_table_case &case_)
++{
++ const char content[] = "\0after\n";
++ const size_t sz = sizeof (content);
++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz);
++ line_table_test ltt (case_);
++ const line_map_ordinary *ord_map = linemap_check_ordinary
++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0));
++ linemap_line_start (line_table, 1, 100);
++
++ location_t finish
++ = linemap_position_for_line_and_column (line_table, ord_map, 1,
++ strlen (content));
++
++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS)
++ return;
++
++ /* Location of the NUL byte. */
++ location_t nul_loc
++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 1);
++ gcc_rich_location richloc (nul_loc);
++
++ {
++ test_diagnostic_context dc;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" after\n"
++ " ^\n",
++ pp_formatted_text (dc.printer));
++ }
++ richloc.set_escape_on_output (true);
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <U+0000>after\n"
++ " ^~~~~~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++ {
++ test_diagnostic_context dc;
++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES;
++ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
++ ASSERT_STREQ (" <00>after\n"
++ " ^~~~\n",
++ pp_formatted_text (dc.printer));
++ }
++}
++
+ /* Verify that line numbers are correctly printed for the case of
+ a multiline range in which the width of the line numbers changes
+ (e.g. from "9" to "10"). */
+@@ -5254,6 +5666,8 @@ diagnostic_show_locus_c_tests ()
+ test_layout_range_for_single_line ();
+ test_layout_range_for_multiple_lines ();
+
++ test_display_widths ();
++
+ for_each_line_table_case (test_layout_x_offset_display_utf8);
+ for_each_line_table_case (test_layout_x_offset_display_tab);
+
+@@ -5274,6 +5688,8 @@ diagnostic_show_locus_c_tests ()
+ for_each_line_table_case (test_fixit_replace_containing_newline);
+ for_each_line_table_case (test_fixit_deletion_affecting_newline);
+ for_each_line_table_case (test_tab_expansion);
++ for_each_line_table_case (test_escaping_bytes_1);
++ for_each_line_table_case (test_escaping_bytes_2);
+
+ test_line_numbers_multiline_range ();
+ }
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+--- a/gcc/doc/invoke.texi 2021-12-13 23:23:05.764437151 -0800
++++ b/gcc/doc/invoke.texi 2021-12-14 01:16:01.553943061 -0800
+@@ -312,7 +312,8 @@ Objective-C and Objective-C++ Dialects}.
+ -fdiagnostics-show-path-depths @gol
+ -fno-show-column @gol
+ -fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol
+--fdiagnostics-column-origin=@var{origin}}
++-fdiagnostics-column-origin=@var{origin} @gol
++-fdiagnostics-escape-format=@r{[}unicode@r{|}bytes@r{]}}
+
+ @item Warning Options
+ @xref{Warning Options,,Options to Request or Suppress Warnings}.
+@@ -5083,6 +5084,38 @@ first column. The default value of 1 co
+ behavior and to the GNU style guide. Some utilities may perform better with an
+ origin of 0; any non-negative value may be specified.
+
++@item -fdiagnostics-escape-format=@var{FORMAT}
++@opindex fdiagnostics-escape-format
++When GCC prints pertinent source lines for a diagnostic it normally attempts
++to print the source bytes directly. However, some diagnostics relate to encoding
++issues in the source file, such as malformed UTF-8, or issues with Unicode
++normalization. These diagnostics are flagged so that GCC will escape bytes
++that are not printable ASCII when printing their pertinent source lines.
++
++This option controls how such bytes should be escaped.
++
++The default @var{FORMAT}, @samp{unicode} displays Unicode characters that
++are not printable ASCII in the form @samp{<U+XXXX>}, and bytes that do not
++correspond to a Unicode character validly-encoded in UTF-8-encoded will be
++displayed as hexadecimal in the form @samp{<XX>}.
++
++For example, a source line containing the string @samp{before} followed by the
++Unicode character U+03C0 (``GREEK SMALL LETTER PI'', with UTF-8 encoding
++0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by
++the string @samp{after} will be printed for such a diagnostic as:
++
++@smallexample
++ before<U+03C0><BF>after
++@end smallexample
++
++Setting @var{FORMAT} to @samp{bytes} will display all non-printable-ASCII bytes
++in the form @samp{<XX>}, thus showing the underlying encoding of non-ASCII
++Unicode characters. For the example above, the following will be printed:
++
++@smallexample
++ before<CF><80><BF>after
++@end smallexample
++
+ @item -fdiagnostics-format=@var{FORMAT}
+ @opindex fdiagnostics-format
+ Select a different format for printing diagnostics.
+@@ -5150,9 +5183,11 @@ might be printed in JSON form (after for
+ @}
+ @}
+ ],
++ "escape-source": false,
+ "message": "...this statement, but the latter is @dots{}"
+ @}
+ ]
++ "escape-source": false,
+ "column-origin": 1,
+ @},
+ @dots{}
+@@ -5239,6 +5274,7 @@ of the expression, which have labels. I
+ "label": "T @{aka struct t@}"
+ @}
+ ],
++ "escape-source": false,
+ "message": "invalid operands to binary + @dots{}"
+ @}
+ @end smallexample
+@@ -5292,6 +5328,7 @@ might be printed in JSON form as:
+ @}
+ @}
+ ],
++ "escape-source": false,
+ "message": "\u2018struct s\u2019 has no member named @dots{}"
+ @}
+ @end smallexample
+@@ -5349,6 +5386,10 @@ For example, the intraprocedural example
+ ]
+ @end smallexample
+
++Diagnostics have a boolean attribute @code{escape-source}, hinting whether
++non-ASCII bytes should be escaped when printing the pertinent lines of
++source code (@code{true} for diagnostics involving source encoding issues).
++
+ @end table
+
+ @node Warning Options
+diff --git a/gcc/input.c b/gcc/input.c
+--- a/gcc/input.c 2021-07-27 23:55:07.328287915 -0700
++++ b/gcc/input.c 2021-12-14 01:16:01.553943061 -0800
+@@ -913,7 +913,8 @@ make_location (location_t caret, source_
+ source line in order to calculate the display width. If that cannot be done
+ for any reason, then returns the byte column as a fallback. */
+ int
+-location_compute_display_column (expanded_location exploc, int tabstop)
++location_compute_display_column (expanded_location exploc,
++ const cpp_char_column_policy &policy)
+ {
+ if (!(exploc.file && *exploc.file && exploc.line && exploc.column))
+ return exploc.column;
+@@ -921,7 +922,7 @@ location_compute_display_column (expande
+ /* If line is NULL, this function returns exploc.column which is the
+ desired fallback. */
+ return cpp_byte_column_to_display_column (line.get_buffer (), line.length (),
+- exploc.column, tabstop);
++ exploc.column, policy);
+ }
+
+ /* Dump statistics to stderr about the memory usage of the line_table
+@@ -3611,43 +3612,50 @@ test_line_offset_overflow ()
+ void test_cpp_utf8 ()
+ {
+ const int def_tabstop = 8;
++ cpp_char_column_policy policy (def_tabstop, cpp_wcwidth);
++
+ /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */
+ {
+- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop);
++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, policy);
+ ASSERT_EQ (8, w_bad);
+- int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop);
++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, policy);
+ ASSERT_EQ (5, w_ctrl);
+ }
+
+ /* Verify that wcwidth of valid UTF-8 is as expected. */
+ {
+- const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop);
++ const int w_pi = cpp_display_width ("\xcf\x80", 2, policy);
+ ASSERT_EQ (1, w_pi);
+- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop);
++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, policy);
+ ASSERT_EQ (2, w_emoji);
+ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2,
+- def_tabstop);
++ policy);
+ ASSERT_EQ (1, w_umlaut_precomposed);
+ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3,
+- def_tabstop);
++ policy);
+ ASSERT_EQ (1, w_umlaut_combining);
+- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop);
++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, policy);
+ ASSERT_EQ (2, w_han);
+- const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop);
++ const int w_ascii = cpp_display_width ("GCC", 3, policy);
+ ASSERT_EQ (3, w_ascii);
+ const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82"
+ "\x9f! \xe4\xb8\xba y\xcc\x88",
+- 24, def_tabstop);
++ 24, policy);
+ ASSERT_EQ (18, w_mixed);
+ }
+
+ /* Verify that display width properly expands tabs. */
+ {
+ const char *tstr = "\tabc\td";
+- ASSERT_EQ (6, cpp_display_width (tstr, 6, 1));
+- ASSERT_EQ (10, cpp_display_width (tstr, 6, 3));
+- ASSERT_EQ (17, cpp_display_width (tstr, 6, 8));
+- ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8));
++ ASSERT_EQ (6, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (1, cpp_wcwidth)));
++ ASSERT_EQ (10, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (3, cpp_wcwidth)));
++ ASSERT_EQ (17, cpp_display_width (tstr, 6,
++ cpp_char_column_policy (8, cpp_wcwidth)));
++ ASSERT_EQ (1,
++ cpp_display_column_to_byte_column
++ (tstr, 6, 7, cpp_char_column_policy (8, cpp_wcwidth)));
+ }
+
+ /* Verify that cpp_byte_column_to_display_column can go past the end,
+@@ -3660,13 +3668,13 @@ void test_cpp_utf8 ()
+ /* 111122223456
+ Byte columns. */
+
+- ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop));
++ ASSERT_EQ (5, cpp_display_width (str, 6, policy));
+ ASSERT_EQ (105,
+- cpp_byte_column_to_display_column (str, 6, 106, def_tabstop));
++ cpp_byte_column_to_display_column (str, 6, 106, policy));
+ ASSERT_EQ (10000,
+- cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop));
++ cpp_byte_column_to_display_column (NULL, 0, 10000, policy));
+ ASSERT_EQ (0,
+- cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop));
++ cpp_byte_column_to_display_column (NULL, 10000, 0, policy));
+ }
+
+ /* Verify that cpp_display_column_to_byte_column can go past the end,
+@@ -3680,25 +3688,25 @@ void test_cpp_utf8 ()
+ /* 000000000000000000000000000000000111111
+ 111122223333444456666777788889999012345
+ Byte columns. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, policy));
+ ASSERT_EQ (15,
+- cpp_display_column_to_byte_column (str, 15, 11, def_tabstop));
++ cpp_display_column_to_byte_column (str, 15, 11, policy));
+ ASSERT_EQ (115,
+- cpp_display_column_to_byte_column (str, 15, 111, def_tabstop));
++ cpp_display_column_to_byte_column (str, 15, 111, policy));
+ ASSERT_EQ (10000,
+- cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop));
++ cpp_display_column_to_byte_column (NULL, 0, 10000, policy));
+ ASSERT_EQ (0,
+- cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop));
++ cpp_display_column_to_byte_column (NULL, 10000, 0, policy));
+
+ /* Verify that we do not interrupt a UTF-8 sequence. */
+- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop));
++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, policy));
+
+ for (int byte_col = 1; byte_col <= 15; ++byte_col)
+ {
+ const int disp_col
+- = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop);
++ = cpp_byte_column_to_display_column (str, 15, byte_col, policy);
+ const int byte_col2
+- = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop);
++ = cpp_display_column_to_byte_column (str, 15, disp_col, policy);
+
+ /* If we ask for the display column in the middle of a UTF-8
+ sequence, it will return the length of the partial sequence,
+diff --git a/gcc/input.h b/gcc/input.h
+--- a/gcc/input.h 2021-07-27 23:55:07.328287915 -0700
++++ b/gcc/input.h 2021-12-14 01:16:01.553943061 -0800
+@@ -39,8 +39,11 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER
+ extern bool is_location_from_builtin_token (location_t);
+ extern expanded_location expand_location (location_t);
+
+-extern int location_compute_display_column (expanded_location exploc,
+- int tabstop);
++class cpp_char_column_policy;
++
++extern int
++location_compute_display_column (expanded_location exploc,
++ const cpp_char_column_policy &policy);
+
+ /* A class capturing the bounds of a buffer, to allow for run-time
+ bounds-checking in a checked build. */
+diff --git a/gcc/opts.c b/gcc/opts.c
+--- a/gcc/opts.c 2021-07-27 23:55:07.364288417 -0700
++++ b/gcc/opts.c 2021-12-14 01:16:01.553943061 -0800
+@@ -2573,6 +2573,10 @@ common_handle_option (struct gcc_options
+ dc->column_origin = value;
+ break;
+
++ case OPT_fdiagnostics_escape_format_:
++ dc->escape_format = (enum diagnostics_escape_format)value;
++ break;
++
+ case OPT_fdiagnostics_show_cwe:
+ dc->show_cwe = value;
+ break;
+diff --git a/gcc/selftest.c b/gcc/selftest.c
+--- a/gcc/selftest.c 2021-07-27 23:55:07.500290315 -0700
++++ b/gcc/selftest.c 2021-12-14 01:16:01.557942991 -0800
+@@ -193,6 +193,21 @@ temp_source_file::temp_source_file (cons
+ fclose (out);
+ }
+
++/* As above, but with a size, to allow for NUL bytes in CONTENT. */
++
++temp_source_file::temp_source_file (const location &loc,
++ const char *suffix,
++ const char *content,
++ size_t sz)
++: named_temp_file (suffix)
++{
++ FILE *out = fopen (get_filename (), "w");
++ if (!out)
++ fail_formatted (loc, "unable to open tempfile: %s", get_filename ());
++ fwrite (content, sz, 1, out);
++ fclose (out);
++}
++
+ /* Avoid introducing locale-specific differences in the results
+ by hardcoding open_quote and close_quote. */
+
+diff --git a/gcc/selftest.h b/gcc/selftest.h
+--- a/gcc/selftest.h 2021-07-27 23:55:07.500290315 -0700
++++ b/gcc/selftest.h 2021-12-14 01:16:01.557942991 -0800
+@@ -112,6 +112,8 @@ class temp_source_file : public named_te
+ public:
+ temp_source_file (const location &loc, const char *suffix,
+ const char *content);
++ temp_source_file (const location &loc, const char *suffix,
++ const char *content, size_t sz);
+ };
+
+ /* RAII-style class for avoiding introducing locale-specific differences
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-07-27 23:55:07.596291654 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#error message\"" } */
+
+ /* { dg-regexp "\"caret\": \{" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-07-27 23:55:07.596291654 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"warning\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Wcpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-07-27 23:55:07.596291654 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \"#warning message\"" } */
+ /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-07-27 23:55:07.596291654 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-14 01:16:01.557942991 -0800
+@@ -19,6 +19,7 @@ int test (void)
+
+ /* { dg-regexp "\"kind\": \"note\"" } */
+ /* { dg-regexp "\"message\": \"...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'\"" } */
++/* { dg-regexp "\"escape-source\": false" } */
+
+ /* { dg-regexp "\"caret\": \{" } */
+ /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
+@@ -39,6 +40,7 @@ int test (void)
+ /* { dg-regexp "\"kind\": \"warning\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
+ /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */
+ /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */
+
+diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c
+--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-07-27 23:55:07.596291654 -0700
++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-14 01:16:01.557942991 -0800
+@@ -14,6 +14,7 @@ int test (struct s *ptr)
+
+ /* { dg-regexp "\"kind\": \"error\"" } */
+ /* { dg-regexp "\"column-origin\": 1" } */
++/* { dg-regexp "\"escape-source\": false" } */
+ /* { dg-regexp "\"message\": \".*\"" } */
+
+ /* Verify fix-it hints. */
+diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c
+--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 2021-12-14 01:16:01.557942991 -0800
+@@ -0,0 +1,21 @@
++// { dg-do preprocess }
++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=bytes" }
++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */
++
++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e.
++ U+0F42 TIBETAN LETTER GA: à½
++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ
++
++ The UTF-8 encoding of U+0F43 TIBETAN LETTER GHA is: E0 BD 83. */
++
++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_\u0F43_after bar
++ ^~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
++
++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_<e0><bd><83>_after bar
++ ^~~~~~~~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c
+--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 1969-12-31 16:00:00.000000000 -0800
++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 2021-12-14 01:16:01.557942991 -0800
+@@ -0,0 +1,19 @@
++// { dg-do preprocess }
++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=unicode" }
++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */
++
++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e.
++ U+0F42 TIBETAN LETTER GA: à½
++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ */
++
++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_\u0F43_after bar
++ ^~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
++
++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." }
++/* { dg-begin-multiline-output "" }
++ foo before_<U+0F43>_after bar
++ ^~~~~~~~~~~~~~~~~~~~~
++ { dg-end-multiline-output "" } */
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-07-27 23:55:08.472303878 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"error\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#error message\"" }
+
+ ! { dg-regexp "\"caret\": \{" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-07-27 23:55:08.472303878 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"warning\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Wcpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90
+--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-07-27 23:55:08.472303878 -0700
++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-14 01:16:01.557942991 -0800
+@@ -9,6 +9,7 @@
+
+ ! { dg-regexp "\"kind\": \"error\"" }
+ ! { dg-regexp "\"column-origin\": 1" }
++! { dg-regexp "\"escape-source\": false" }
+ ! { dg-regexp "\"message\": \"#warning message\"" }
+ ! { dg-regexp "\"option\": \"-Werror=cpp\"" }
+ ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
+diff --git a/libcpp/charset.c b/libcpp/charset.c
+--- a/libcpp/charset.c 2021-07-27 23:55:08.712307227 -0700
++++ b/libcpp/charset.c 2021-12-14 01:16:01.557942991 -0800
+@@ -1552,12 +1552,14 @@ convert_escape (cpp_reader *pfile, const
+ "unknown escape sequence: '\\%c'", (int) c);
+ else
+ {
++ encoding_rich_location rich_loc (pfile);
++
+ /* diagnostic.c does not support "%03o". When it does, this
+ code can use %03o directly in the diagnostic again. */
+ char buf[32];
+ sprintf(buf, "%03o", (int) c);
+- cpp_error (pfile, CPP_DL_PEDWARN,
+- "unknown escape sequence: '\\%s'", buf);
++ cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc,
++ "unknown escape sequence: '\\%s'", buf);
+ }
+ }
+
+@@ -2280,14 +2282,16 @@ cpp_string_location_reader::get_next ()
+ }
+
+ cpp_display_width_computation::
+-cpp_display_width_computation (const char *data, int data_length, int tabstop) :
++cpp_display_width_computation (const char *data, int data_length,
++ const cpp_char_column_policy &policy) :
+ m_begin (data),
+ m_next (m_begin),
+ m_bytes_left (data_length),
+- m_tabstop (tabstop),
++ m_policy (policy),
+ m_display_cols (0)
+ {
+- gcc_assert (m_tabstop > 0);
++ gcc_assert (policy.m_tabstop > 0);
++ gcc_assert (policy.m_width_cb);
+ }
+
+
+@@ -2299,19 +2303,28 @@ cpp_display_width_computation (const cha
+ point to a valid UTF-8-encoded sequence, then it will be treated as a single
+ byte with display width 1. m_cur_display_col is the current display column,
+ relative to which tab stops should be expanded. Returns the display width of
+- the codepoint just processed. */
++ the codepoint just processed.
++ If OUT is non-NULL, it is populated. */
+
+ int
+-cpp_display_width_computation::process_next_codepoint ()
++cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out)
+ {
+ cppchar_t c;
+ int next_width;
+
++ if (out)
++ out->m_start_byte = m_next;
++
+ if (*m_next == '\t')
+ {
+ ++m_next;
+ --m_bytes_left;
+- next_width = m_tabstop - (m_display_cols % m_tabstop);
++ next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop);
++ if (out)
++ {
++ out->m_ch = '\t';
++ out->m_valid_ch = true;
++ }
+ }
+ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
+ != 0)
+@@ -2321,14 +2334,24 @@ cpp_display_width_computation::process_n
+ of one. */
+ ++m_next;
+ --m_bytes_left;
+- next_width = 1;
++ next_width = m_policy.m_undecoded_byte_width;
++ if (out)
++ out->m_valid_ch = false;
+ }
+ else
+ {
+ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
+- next_width = cpp_wcwidth (c);
++ next_width = m_policy.m_width_cb (c);
++ if (out)
++ {
++ out->m_ch = c;
++ out->m_valid_ch = true;
++ }
+ }
+
++ if (out)
++ out->m_next_byte = m_next;
++
+ m_display_cols += next_width;
+ return next_width;
+ }
+@@ -2344,7 +2367,7 @@ cpp_display_width_computation::advance_d
+ const int start = m_display_cols;
+ const int target = start + n;
+ while (m_display_cols < target && !done ())
+- process_next_codepoint ();
++ process_next_codepoint (NULL);
+ return m_display_cols - start;
+ }
+
+@@ -2352,29 +2375,33 @@ cpp_display_width_computation::advance_d
+ how many display columns are occupied by the first COLUMN bytes. COLUMN
+ may exceed DATA_LENGTH, in which case the phantom bytes at the end are
+ treated as if they have display width 1. Tabs are expanded to the next tab
+- stop, relative to the start of DATA. */
++ stop, relative to the start of DATA, and non-printable-ASCII characters
++ will be escaped as per POLICY. */
+
+ int
+ cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column, int tabstop)
++ int column,
++ const cpp_char_column_policy &policy)
+ {
+ const int offset = MAX (0, column - data_length);
+- cpp_display_width_computation dw (data, column - offset, tabstop);
++ cpp_display_width_computation dw (data, column - offset, policy);
+ while (!dw.done ())
+- dw.process_next_codepoint ();
++ dw.process_next_codepoint (NULL);
+ return dw.display_cols_processed () + offset;
+ }
+
+ /* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+ the least number of bytes that will result in at least DISPLAY_COL display
+ columns. The return value may exceed DATA_LENGTH if the entire string does
+- not occupy enough display columns. */
++ not occupy enough display columns. Non-printable-ASCII characters
++ will be escaped as per POLICY. */
+
+ int
+ cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col, int tabstop)
++ int display_col,
++ const cpp_char_column_policy &policy)
+ {
+- cpp_display_width_computation dw (data, data_length, tabstop);
++ cpp_display_width_computation dw (data, data_length, policy);
+ const int avail_display = dw.advance_display_cols (display_col);
+ return dw.bytes_processed () + MAX (0, display_col - avail_display);
+ }
+diff --git a/libcpp/errors.c b/libcpp/errors.c
+--- a/libcpp/errors.c 2021-07-27 23:55:08.712307227 -0700
++++ b/libcpp/errors.c 2021-12-14 01:16:01.557942991 -0800
+@@ -27,6 +27,31 @@ along with this program; see the file CO
+ #include "cpplib.h"
+ #include "internal.h"
+
++/* Get a location_t for the current location in PFILE,
++ generally that of the previously lexed token. */
++
++location_t
++cpp_diagnostic_get_current_location (cpp_reader *pfile)
++{
++ if (CPP_OPTION (pfile, traditional))
++ {
++ if (pfile->state.in_directive)
++ return pfile->directive_line;
++ else
++ return pfile->line_table->highest_line;
++ }
++ /* We don't want to refer to a token before the beginning of the
++ current run -- that is invalid. */
++ else if (pfile->cur_token == pfile->cur_run->base)
++ {
++ return 0;
++ }
++ else
++ {
++ return pfile->cur_token[-1].src_loc;
++ }
++}
++
+ /* Print a diagnostic at the given location. */
+
+ ATTRIBUTE_FPTR_PRINTF(5,0)
+@@ -52,25 +77,7 @@ cpp_diagnostic (cpp_reader * pfile, enum
+ enum cpp_warning_reason reason,
+ const char *msgid, va_list *ap)
+ {
+- location_t src_loc;
+-
+- if (CPP_OPTION (pfile, traditional))
+- {
+- if (pfile->state.in_directive)
+- src_loc = pfile->directive_line;
+- else
+- src_loc = pfile->line_table->highest_line;
+- }
+- /* We don't want to refer to a token before the beginning of the
+- current run -- that is invalid. */
+- else if (pfile->cur_token == pfile->cur_run->base)
+- {
+- src_loc = 0;
+- }
+- else
+- {
+- src_loc = pfile->cur_token[-1].src_loc;
+- }
++ location_t src_loc = cpp_diagnostic_get_current_location (pfile);
+ rich_location richloc (pfile->line_table, src_loc);
+ return cpp_diagnostic_at (pfile, level, reason, &richloc, msgid, ap);
+ }
+@@ -142,6 +149,43 @@ cpp_warning_syshdr (cpp_reader * pfile,
+
+ va_end (ap);
+ return ret;
++}
++
++/* As cpp_warning above, but use RICHLOC as the location of the diagnostic. */
++
++bool cpp_warning_at (cpp_reader *pfile, enum cpp_warning_reason reason,
++ rich_location *richloc, const char *msgid, ...)
++{
++ va_list ap;
++ bool ret;
++
++ va_start (ap, msgid);
++
++ ret = cpp_diagnostic_at (pfile, CPP_DL_WARNING, reason, richloc,
++ msgid, &ap);
++
++ va_end (ap);
++ return ret;
++
++}
++
++/* As cpp_pedwarning above, but use RICHLOC as the location of the
++ diagnostic. */
++
++bool
++cpp_pedwarning_at (cpp_reader * pfile, enum cpp_warning_reason reason,
++ rich_location *richloc, const char *msgid, ...)
++{
++ va_list ap;
++ bool ret;
++
++ va_start (ap, msgid);
++
++ ret = cpp_diagnostic_at (pfile, CPP_DL_PEDWARN, reason, richloc,
++ msgid, &ap);
++
++ va_end (ap);
++ return ret;
+ }
+
+ /* Print a diagnostic at a specific location. */
+diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
+--- a/libcpp/include/cpplib.h 2021-12-13 23:23:05.768437079 -0800
++++ b/libcpp/include/cpplib.h 2021-12-14 01:20:16.189507386 -0800
+@@ -1275,6 +1275,14 @@ extern bool cpp_warning_syshdr (cpp_read
+ const char *msgid, ...)
+ ATTRIBUTE_PRINTF_3;
+
++/* As their counterparts above, but use RICHLOC. */
++extern bool cpp_warning_at (cpp_reader *, enum cpp_warning_reason,
++ rich_location *richloc, const char *msgid, ...)
++ ATTRIBUTE_PRINTF_4;
++extern bool cpp_pedwarning_at (cpp_reader *, enum cpp_warning_reason,
++ rich_location *richloc, const char *msgid, ...)
++ ATTRIBUTE_PRINTF_4;
++
+ /* Output a diagnostic with "MSGID: " preceding the
+ error string of errno. No location is printed. */
+ extern bool cpp_errno (cpp_reader *, enum cpp_diagnostic_level,
+@@ -1435,42 +1443,95 @@ extern const char * cpp_get_userdef_suff
+
+ /* In charset.c */
+
++/* The result of attempting to decode a run of UTF-8 bytes. */
++
++struct cpp_decoded_char
++{
++ const char *m_start_byte;
++ const char *m_next_byte;
++
++ bool m_valid_ch;
++ cppchar_t m_ch;
++};
++
++/* Information for mapping between code points and display columns.
++
++ This is a tabstop value, along with a callback for getting the
++ widths of characters. Normally this callback is cpp_wcwidth, but we
++ support other schemes for escaping non-ASCII unicode as a series of
++ ASCII chars when printing the user's source code in diagnostic-show-locus.c
++
++ For example, consider:
++ - the Unicode character U+03C0 "GREEK SMALL LETTER PI" (UTF-8: 0xCF 0x80)
++ - the Unicode character U+1F642 "SLIGHTLY SMILING FACE"
++ (UTF-8: 0xF0 0x9F 0x99 0x82)
++ - the byte 0xBF (a stray trailing byte of a UTF-8 character)
++ Normally U+03C0 would occupy one display column, U+1F642
++ would occupy two display columns, and the stray byte would be
++ printed verbatim as one display column.
++
++ However when escaping them as unicode code points as "<U+03C0>"
++ and "<U+1F642>" they occupy 8 and 9 display columns respectively,
++ and when escaping them as bytes as "<CF><80>" and "<F0><9F><99><82>"
++ they occupy 8 and 16 display columns respectively. In both cases
++ the stray byte is escaped to <BF> as 4 display columns. */
++
++struct cpp_char_column_policy
++{
++ cpp_char_column_policy (int tabstop,
++ int (*width_cb) (cppchar_t c))
++ : m_tabstop (tabstop),
++ m_undecoded_byte_width (1),
++ m_width_cb (width_cb)
++ {}
++
++ int m_tabstop;
++ /* Width in display columns of a stray byte that isn't decodable
++ as UTF-8. */
++ int m_undecoded_byte_width;
++ int (*m_width_cb) (cppchar_t c);
++};
++
+ /* A class to manage the state while converting a UTF-8 sequence to cppchar_t
+ and computing the display width one character at a time. */
+ class cpp_display_width_computation {
+ public:
+ cpp_display_width_computation (const char *data, int data_length,
+- int tabstop);
++ const cpp_char_column_policy &policy);
+ const char *next_byte () const { return m_next; }
+ int bytes_processed () const { return m_next - m_begin; }
+ int bytes_left () const { return m_bytes_left; }
+ bool done () const { return !bytes_left (); }
+ int display_cols_processed () const { return m_display_cols; }
+
+- int process_next_codepoint ();
++ int process_next_codepoint (cpp_decoded_char *out);
+ int advance_display_cols (int n);
+
+ private:
+ const char *const m_begin;
+ const char *m_next;
+ size_t m_bytes_left;
+- const int m_tabstop;
++ const cpp_char_column_policy &m_policy;
+ int m_display_cols;
+ };
+
+ /* Convenience functions that are simple use cases for class
+ cpp_display_width_computation. Tab characters will be expanded to spaces
+- as determined by TABSTOP. */
++ as determined by POLICY.m_tabstop, and non-printable-ASCII characters
++ will be escaped as per POLICY. */
++
+ int cpp_byte_column_to_display_column (const char *data, int data_length,
+- int column, int tabstop);
++ int column,
++ const cpp_char_column_policy &policy);
+ inline int cpp_display_width (const char *data, int data_length,
+- int tabstop)
++ const cpp_char_column_policy &policy)
+ {
+ return cpp_byte_column_to_display_column (data, data_length, data_length,
+- tabstop);
++ policy);
+ }
+ int cpp_display_column_to_byte_column (const char *data, int data_length,
+- int display_col, int tabstop);
++ int display_col,
++ const cpp_char_column_policy &policy);
+ int cpp_wcwidth (cppchar_t c);
+
+ #endif /* ! LIBCPP_CPPLIB_H */
+diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
+--- a/libcpp/include/line-map.h 2021-07-27 23:55:08.716307283 -0700
++++ b/libcpp/include/line-map.h 2021-12-14 01:16:01.557942991 -0800
+@@ -1781,6 +1781,18 @@ class rich_location
+ const diagnostic_path *get_path () const { return m_path; }
+ void set_path (const diagnostic_path *path) { m_path = path; }
+
++ /* A flag for hinting that the diagnostic involves character encoding
++ issues, and thus that it will be helpful to the user if we show some
++ representation of how the characters in the pertinent source lines
++ are encoded.
++ The default is false (i.e. do not escape).
++ When set to true, non-ASCII bytes in the pertinent source lines will
++ be escaped in a manner controlled by the user-supplied option
++ -fdiagnostics-escape-format=, so that the user can better understand
++ what's going on with the encoding in their source file. */
++ bool escape_on_output_p () const { return m_escape_on_output; }
++ void set_escape_on_output (bool flag) { m_escape_on_output = flag; }
++
+ private:
+ bool reject_impossible_fixit (location_t where);
+ void stop_supporting_fixits ();
+@@ -1807,6 +1819,7 @@ protected:
+ bool m_fixits_cannot_be_auto_applied;
+
+ const diagnostic_path *m_path;
++ bool m_escape_on_output;
+ };
+
+ /* A struct for the result of range_label::get_text: a NUL-terminated buffer
+diff --git a/libcpp/internal.h b/libcpp/internal.h
+--- a/libcpp/internal.h 2021-12-13 23:23:05.768437079 -0800
++++ b/libcpp/internal.h 2021-12-14 01:16:01.557942991 -0800
+@@ -776,6 +776,9 @@ extern void _cpp_do_file_change (cpp_rea
+ extern void _cpp_pop_buffer (cpp_reader *);
+ extern char *_cpp_bracket_include (cpp_reader *);
+
++/* In errors.c */
++extern location_t cpp_diagnostic_get_current_location (cpp_reader *);
++
+ /* In traditional.c. */
+ extern bool _cpp_scan_out_logical_line (cpp_reader *, cpp_macro *, bool);
+ extern bool _cpp_read_logical_line_trad (cpp_reader *);
+@@ -942,6 +945,26 @@ int linemap_get_expansion_line (class li
+ const char* linemap_get_expansion_filename (class line_maps *,
+ location_t);
+
++/* A subclass of rich_location for emitting a diagnostic
++ at the current location of the reader, but flagging
++ it with set_escape_on_output (true). */
++class encoding_rich_location : public rich_location
++{
++ public:
++ encoding_rich_location (cpp_reader *pfile)
++ : rich_location (pfile->line_table,
++ cpp_diagnostic_get_current_location (pfile))
++ {
++ set_escape_on_output (true);
++ }
++
++ encoding_rich_location (cpp_reader *pfile, location_t loc)
++ : rich_location (pfile->line_table, loc)
++ {
++ set_escape_on_output (true);
++ }
++};
++
+ #ifdef __cplusplus
+ }
+ #endif
+diff --git a/libcpp/lex.c b/libcpp/lex.c
+--- a/libcpp/lex.c 2021-12-14 01:14:48.435225968 -0800
++++ b/libcpp/lex.c 2021-12-14 01:24:37.220995816 -0800
+@@ -1774,7 +1774,11 @@ skip_whitespace (cpp_reader *pfile, cppc
+ while (is_nvspace (c));
+
+ if (saw_NUL)
+- cpp_error (pfile, CPP_DL_WARNING, "null character(s) ignored");
++ {
++ encoding_rich_location rich_loc (pfile);
++ cpp_error_at (pfile, CPP_DL_WARNING, &rich_loc,
++ "null character(s) ignored");
++ }
+
+ buffer->cur--;
+ }
+@@ -1803,6 +1807,28 @@ warn_about_normalization (cpp_reader *pf
+ if (CPP_OPTION (pfile, warn_normalize) < NORMALIZE_STATE_RESULT (s)
+ && !pfile->state.skipping)
+ {
++ location_t loc = token->src_loc;
++
++ /* If possible, create a location range for the token. */
++ if (loc >= RESERVED_LOCATION_COUNT
++ && token->type != CPP_EOF
++ /* There must be no line notes to process. */
++ && (!(pfile->buffer->cur
++ >= pfile->buffer->notes[pfile->buffer->cur_note].pos
++ && !pfile->overlaid_buffer)))
++ {
++ source_range tok_range;
++ tok_range.m_start = loc;
++ tok_range.m_finish
++ = linemap_position_for_column (pfile->line_table,
++ CPP_BUF_COLUMN (pfile->buffer,
++ pfile->buffer->cur));
++ loc = COMBINE_LOCATION_DATA (pfile->line_table,
++ loc, tok_range, NULL);
++ }
++
++ encoding_rich_location rich_loc (pfile, loc);
++
+ /* Make sure that the token is printed using UCNs, even
+ if we'd otherwise happily print UTF-8. */
+ unsigned char *buf = XNEWVEC (unsigned char, cpp_token_len (token));
+@@ -1810,11 +1836,11 @@ warn_about_normalization (cpp_reader *pf
+
+ sz = cpp_spell_token (pfile, token, buf, false) - buf;
+ if (NORMALIZE_STATE_RESULT (s) == normalized_C)
+- cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
+- "`%.*s' is not in NFKC", (int) sz, buf);
++ cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
++ "`%.*s' is not in NFKC", (int) sz, buf);
+ else
+- cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
+- "`%.*s' is not in NFC", (int) sz, buf);
++ cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
++ "`%.*s' is not in NFC", (int) sz, buf);
+ free (buf);
+ }
+ }
+diff --git a/libcpp/line-map.c b/libcpp/line-map.c
+--- a/libcpp/line-map.c 2021-07-27 23:55:08.716307283 -0700
++++ b/libcpp/line-map.c 2021-12-14 01:16:01.561942921 -0800
+@@ -2086,7 +2086,8 @@ rich_location::rich_location (line_maps
+ m_fixit_hints (),
+ m_seen_impossible_fixit (false),
+ m_fixits_cannot_be_auto_applied (false),
+- m_path (NULL)
++ m_path (NULL),
++ m_escape_on_output (false)
+ {
+ add_range (loc, SHOW_RANGE_WITH_CARET, label);
+ }
new file mode 100644
@@ -0,0 +1,1765 @@
+From 51c500269bf53749b107807d84271385fad35628 Mon Sep 17 00:00:00 2001
+From: Marek Polacek <polacek@redhat.com>
+Date: Wed, 6 Oct 2021 14:33:59 -0400
+Subject: [PATCH] libcpp: Implement -Wbidi-chars for CVE-2021-42574 [PR103026]
+
+From a link below:
+"An issue was discovered in the Bidirectional Algorithm in the Unicode
+Specification through 14.0. It permits the visual reordering of
+characters via control sequences, which can be used to craft source code
+that renders different logic than the logical ordering of tokens
+ingested by compilers and interpreters. Adversaries can leverage this to
+encode source code for compilers accepting Unicode such that targeted
+vulnerabilities are introduced invisibly to human reviewers."
+
+More info:
+https://nvd.nist.gov/vuln/detail/CVE-2021-42574
+https://trojansource.codes/
+
+This is not a compiler bug. However, to mitigate the problem, this patch
+implements -Wbidi-chars=[none|unpaired|any] to warn about possibly
+misleading Unicode bidirectional control characters the preprocessor may
+encounter.
+
+The default is =unpaired, which warns about improperly terminated
+bidirectional control characters; e.g. a LRE without its corresponding PDF.
+The level =any warns about any use of bidirectional control characters.
+
+This patch handles both UCNs and UTF-8 characters. UCNs designating
+bidi characters in identifiers are accepted since r204886. Then r217144
+enabled -fextended-identifiers by default. Extended characters in C/C++
+identifiers have been accepted since r275979. However, this patch still
+warns about mixing UTF-8 and UCN bidi characters; there seems to be no
+good reason to allow mixing them.
+
+We warn in different contexts: comments (both C and C++-style), string
+literals, character constants, and identifiers. Expectedly, UCNs are ignored
+in comments and raw string literals. The bidirectional control characters
+can nest so this patch handles that as well.
+
+I have not included nor tested this at all with Fortran (which also has
+string literals and line comments).
+
+Dave M. posted patches improving diagnostic involving Unicode characters.
+This patch does not make use of this new infrastructure yet.
+
+ PR preprocessor/103026
+
+gcc/c-family/ChangeLog:
+
+ * c.opt (Wbidi-chars, Wbidi-chars=): New option.
+
+gcc/ChangeLog:
+
+ * doc/invoke.texi: Document -Wbidi-chars.
+
+libcpp/ChangeLog:
+
+ * include/cpplib.h (enum cpp_bidirectional_level): New.
+ (struct cpp_options): Add cpp_warn_bidirectional.
+ (enum cpp_warning_reason): Add CPP_W_BIDIRECTIONAL.
+ * internal.h (struct cpp_reader): Add warn_bidi_p member
+ function.
+ * init.c (cpp_create_reader): Set cpp_warn_bidirectional.
+ * lex.c (bidi): New namespace.
+ (get_bidi_utf8): New function.
+ (get_bidi_ucn): Likewise.
+ (maybe_warn_bidi_on_close): Likewise.
+ (maybe_warn_bidi_on_char): Likewise.
+ (_cpp_skip_block_comment): Implement warning about bidirectional
+ control characters.
+ (skip_line_comment): Likewise.
+ (forms_identifier_p): Likewise.
+ (lex_identifier): Likewise.
+ (lex_string): Likewise.
+ (lex_raw_string): Likewise.
+
+gcc/testsuite/ChangeLog:
+
+ * c-c++-common/Wbidi-chars-1.c: New test.
+ * c-c++-common/Wbidi-chars-2.c: New test.
+ * c-c++-common/Wbidi-chars-3.c: New test.
+ * c-c++-common/Wbidi-chars-4.c: New test.
+ * c-c++-common/Wbidi-chars-5.c: New test.
+ * c-c++-common/Wbidi-chars-6.c: New test.
+ * c-c++-common/Wbidi-chars-7.c: New test.
+ * c-c++-common/Wbidi-chars-8.c: New test.
+ * c-c++-common/Wbidi-chars-9.c: New test.
+ * c-c++-common/Wbidi-chars-10.c: New test.
+ * c-c++-common/Wbidi-chars-11.c: New test.
+ * c-c++-common/Wbidi-chars-12.c: New test.
+ * c-c++-common/Wbidi-chars-13.c: New test.
+ * c-c++-common/Wbidi-chars-14.c: New test.
+ * c-c++-common/Wbidi-chars-15.c: New test.
+ * c-c++-common/Wbidi-chars-16.c: New test.
+ * c-c++-common/Wbidi-chars-17.c: New test.
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=51c500269bf53749b107807d84271385fad35628]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+
+---
+ gcc/c-family/c.opt | 24 ++
+ gcc/doc/invoke.texi | 21 +-
+ gcc/testsuite/c-c++-common/Wbidi-chars-1.c | 12 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-10.c | 27 ++
+ gcc/testsuite/c-c++-common/Wbidi-chars-11.c | 13 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-12.c | 19 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-13.c | 17 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-14.c | 38 ++
+ gcc/testsuite/c-c++-common/Wbidi-chars-15.c | 59 +++
+ gcc/testsuite/c-c++-common/Wbidi-chars-16.c | 26 ++
+ gcc/testsuite/c-c++-common/Wbidi-chars-17.c | 30 ++
+ gcc/testsuite/c-c++-common/Wbidi-chars-2.c | 9 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-3.c | 11 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-4.c | 188 +++++++++
+ gcc/testsuite/c-c++-common/Wbidi-chars-5.c | 188 +++++++++
+ gcc/testsuite/c-c++-common/Wbidi-chars-6.c | 155 ++++++++
+ gcc/testsuite/c-c++-common/Wbidi-chars-7.c | 9 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-8.c | 13 +
+ gcc/testsuite/c-c++-common/Wbidi-chars-9.c | 29 ++
+ libcpp/include/cpplib.h | 18 +-
+ libcpp/init.c | 1 +
+ libcpp/internal.h | 7 +
+ libcpp/lex.c | 408 +++++++++++++++++++-
+ 23 files changed, 1315 insertions(+), 7 deletions(-)
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-1.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-10.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-11.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-12.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-13.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-14.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-15.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-16.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-17.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-2.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-3.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-4.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-5.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-6.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-7.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-8.c
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-9.c
+
+diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
+index 8a4cd634f77..3976fc368db 100644
+--- a/gcc/c-family/c.opt
++++ b/gcc/c-family/c.opt
+@@ -370,6 +370,30 @@ Wbad-function-cast
+ C ObjC Var(warn_bad_function_cast) Warning
+ Warn about casting functions to incompatible types.
+
++Wbidi-chars
++C ObjC C++ ObjC++ Warning Alias(Wbidi-chars=,any,none)
++;
++
++Wbidi-chars=
++C ObjC C++ ObjC++ RejectNegative Joined Warning CPP(cpp_warn_bidirectional) CppReason(CPP_W_BIDIRECTIONAL) Var(warn_bidirectional) Init(bidirectional_unpaired) Enum(cpp_bidirectional_level)
++-Wbidi-chars=[none|unpaired|any] Warn about UTF-8 bidirectional control characters.
++
++; Required for these enum values.
++SourceInclude
++cpplib.h
++
++Enum
++Name(cpp_bidirectional_level) Type(int) UnknownError(argument %qs to %<-Wbidi-chars%> not recognized)
++
++EnumValue
++Enum(cpp_bidirectional_level) String(none) Value(bidirectional_none)
++
++EnumValue
++Enum(cpp_bidirectional_level) String(unpaired) Value(bidirectional_unpaired)
++
++EnumValue
++Enum(cpp_bidirectional_level) String(any) Value(bidirectional_any)
++
+ Wbool-compare
+ C ObjC C++ ObjC++ Var(warn_bool_compare) Warning LangEnabledBy(C ObjC C++ ObjC++,Wall)
+ Warn about boolean expression compared with an integer value different from true/false.
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+index 6070288856c..a22758d18ee 100644
+--- a/gcc/doc/invoke.texi
++++ b/gcc/doc/invoke.texi
+@@ -326,7 +326,9 @@ Objective-C and Objective-C++ Dialects}.
+ -Warith-conversion @gol
+ -Warray-bounds -Warray-bounds=@var{n} @gol
+ -Wno-attributes -Wattribute-alias=@var{n} -Wno-attribute-alias @gol
+--Wno-attribute-warning -Wbool-compare -Wbool-operation @gol
++-Wno-attribute-warning @gol
++-Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]} @gol
++-Wbool-compare -Wbool-operation @gol
+ -Wno-builtin-declaration-mismatch @gol
+ -Wno-builtin-macro-redefined -Wc90-c99-compat -Wc99-c11-compat @gol
+ -Wc11-c2x-compat @gol
+@@ -7559,6 +7561,23 @@ Attributes considered include @code{allo
+ This is the default. You can disable these warnings with either
+ @option{-Wno-attribute-alias} or @option{-Wattribute-alias=0}.
+
++@item -Wbidi-chars=@r{[}none@r{|}unpaired@r{|}any@r{]}
++@opindex Wbidi-chars=
++@opindex Wbidi-chars
++@opindex Wno-bidi-chars
++Warn about possibly misleading UTF-8 bidirectional control characters in
++comments, string literals, character constants, and identifiers. Such
++characters can change left-to-right writing direction into right-to-left
++(and vice versa), which can cause confusion between the logical order and
++visual order. This may be dangerous; for instance, it may seem that a piece
++of code is not commented out, whereas it in fact is.
++
++There are three levels of warning supported by GCC@. The default is
++@option{-Wbidi-chars=unpaired}, which warns about improperly terminated
++bidi contexts. @option{-Wbidi-chars=none} turns the warning off.
++@option{-Wbidi-chars=any} warns about any use of bidirectional control
++characters.
++
+ @item -Wbool-compare
+ @opindex Wno-bool-compare
+ @opindex Wbool-compare
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-10.c b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
+new file mode 100644
+index 00000000000..34f5ac19271
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c
+@@ -0,0 +1,27 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* More nesting testing. */
++
++/* RLEâ« LRI⦠PDF⬠PDIâ©*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int LRE_\u202a_PDF_\u202c;
++int LRE_\u202a_PDF_\u202c_LRE_\u202a_PDF_\u202c;
++int LRE_\u202a_LRI_\u2066_PDF_\u202c_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLE_\u202b_RLI_\u2067_PDF_\u202c_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLE_\u202b_RLI_\u2067_PDI_\u2069_PDF_\u202c;
++int FSI_\u2068_LRO_\u202d_PDI_\u2069_PDF_\u202c;
++int FSI_\u2068;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int FSI_\u2068_PDI_\u2069;
++int FSI_\u2068_FSI_\u2068_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDF_\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_FSI_\u2068_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
+new file mode 100644
+index 00000000000..270ce2368a9
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c
+@@ -0,0 +1,13 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test that we warn when mixing UCN and UTF-8. */
++
++int LRE_âª_PDF_\u202c;
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++int LRE_\u202a_PDF_â¬_;
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++const char *s1 = "LRE_âª_PDF_\u202c";
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++const char *s2 = "LRE_\u202a_PDF_â¬";
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-12.c b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c
+new file mode 100644
+index 00000000000..b07eec1da91
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c
+@@ -0,0 +1,19 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile { target { c || c++11 } } } */
++/* { dg-options "-Wbidi-chars=any" } */
++/* Test raw strings. */
++
++const char *s1 = R"(a b c LRE⪠1 2 3 PDF⬠x y z)";
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++const char *s2 = R"(a b c RLE⫠1 2 3 PDF⬠x y z)";
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++const char *s3 = R"(a b c LROâ 1 2 3 PDF⬠x y z)";
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++const char *s4 = R"(a b c RLO⮠1 2 3 PDF⬠x y z)";
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++const char *s7 = R"(a b c FSI⨠1 2 3 PDI⩠x y) z";
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++const char *s8 = R"(a b c PDIâ© x y )z";
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
++const char *s9 = R"(a b c PDF⬠x y z)";
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
+diff -uprN '-x*.orig' '-x*.rej' del/gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c
+--- del/gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 1969-12-31 16:00:00.000000000 -0800
++++ gcc-11.2.0/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 2021-12-13 23:11:22.328439287 -0800
+@@ -0,0 +1,17 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile { target { c || c++11 } } } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test raw strings. */
++
++const char *s1 = R"(a b c LRE⪠1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s2 = R"(a b c RLEâ« 1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s3 = R"(a b c LROâ 1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s4 = R"(a b c FSI⨠1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s5 = R"(a b c LRI⦠1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s6 = R"(a b c RLI⧠1 2 3)";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
+new file mode 100644
+index 00000000000..ba5f75d9553
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c
+@@ -0,0 +1,38 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test PDI handling, which also pops any subsequent LREs, RLEs, LROs,
++ or RLOs. */
++
++/* LRI_â¦_LRI_â¦_RLE_â«_RLE_â«_RLE_â«_PDI_â©*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// LRI_â¦_RLE_â«_RLE_â«_RLE_â«_PDI_â©
++// LRI_â¦_RLO_â®_RLE_â«_RLE_â«_PDI_â©
++// LRI_â¦_RLO_â®_RLE_â«_PDI_â©
++// FSI_â¨_RLO_â®_PDI_â©
++// FSI_â¨_FSI_â¨_RLO_â®_PDI_â©
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069;
++int LRI_\u2066_LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int PDI_\u2069;
++int LRI_\u2066_PDI_\u2069;
++int RLI_\u2067_PDI_\u2069;
++int LRE_\u202a_LRI_\u2066_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int LRI_\u2066_LRE_\u202a_PDF_\u202c_PDI_\u2069;
++int LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
++int RLI_\u2067_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int FSI_\u2068_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLO_\u202e_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int RLI_\u2067_PDI_\u2069_RLI_\u2067;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int FSI_\u2068_PDF_\u202c_PDI_\u2069;
++int FSI_\u2068_FSI_\u2068_PDF_\u202c_PDI_\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-15.c b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c
+new file mode 100644
+index 00000000000..a0ce8ff5e2c
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c
+@@ -0,0 +1,59 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test unpaired bidi control chars in multiline comments. */
++
++/*
++ * LRE⪠end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * RLEâ« end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * LROâ end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * RLOâ® end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * LRI⦠end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * RLI⧠end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/*
++ * FSI⨠end
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/* LREâª
++ PDF⬠*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++/* FSIâ¨
++ PDIâ© */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++
++/* LRE<âª>
++ *
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-3 } */
++
++/*
++ * LRE<âª>
++ */
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++
++/*
++ *
++ * LRE<âª> */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++/* RLI<â§> */ /* PDI<â©> */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRE<âª> */ /* PDF<â¬> */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
+new file mode 100644
+index 00000000000..baa0159861c
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c
+@@ -0,0 +1,26 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=any" } */
++/* Test LTR/RTL chars. */
++
++/* LTR<â> */
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++// LTR<â>
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++/* RTL<â> */
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++// RTL<â>
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++
++const char *s1 = "LTR<â>";
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++const char *s2 = "LTR\u200e";
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++const char *s3 = "LTR\u200E";
++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */
++const char *s4 = "RTL<â>";
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++const char *s5 = "RTL\u200f";
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
++const char *s6 = "RTL\u200F";
++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
+new file mode 100644
+index 00000000000..07cb4321f96
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c
+@@ -0,0 +1,30 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test LTR/RTL chars. */
++
++/* LTR<â> */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// LTR<â>
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* RTL<â> */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// RTL<â>
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int ltr_\u200e;
++/* { dg-error "universal character " "" { target *-*-* } .-1 } */
++int rtl_\u200f;
++/* { dg-error "universal character " "" { target *-*-* } .-1 } */
++
++const char *s1 = "LTR<â>";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++const char *s2 = "LTR\u200e";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++const char *s3 = "LTR\u200E";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++const char *s4 = "RTL<â>";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++const char *s5 = "RTL\u200f";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++const char *s6 = "RTL\u200F";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-1.c b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c
+new file mode 100644
+index 00000000000..2340374f276
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c
+@@ -0,0 +1,12 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++
++int main() {
++ int isAdmin = 0;
++ /*â® } â¦if (isAdmin)⩠⦠begin admins only */
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++ __builtin_printf("You are an admin.\n");
++ /* end admins only â® { â¦*/
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++ return 0;
++}
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-2.c b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c
+new file mode 100644
+index 00000000000..2340374f276
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c
+@@ -0,0 +1,9 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++
++int main() {
++ /* Say hello; newlineâ§/*/ return 0 ;
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++ __builtin_printf("Hello world.\n");
++ return 0;
++}
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-3.c b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c
+new file mode 100644
+index 00000000000..9dc7edb6e64
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c
+@@ -0,0 +1,11 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++
++int main() {
++ const char* access_level = "user";
++ if (__builtin_strcmp(access_level, "userâ® â¦// Check if adminâ© â¦")) {
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++ __builtin_printf("You are an admin.\n");
++ }
++ return 0;
++}
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
+new file mode 100644
+index 00000000000..639e5c62e88
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c
+@@ -0,0 +1,188 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=any -Wno-multichar -Wno-overflow" } */
++/* Test all bidi chars in various contexts (identifiers, comments,
++ string literals, character constants), both UCN and UTF-8. The bidi
++ chars here are properly terminated, except for the character constants. */
++
++/* a b c LRE⪠1 2 3 PDF⬠x y z */
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++/* a b c RLE⫠1 2 3 PDF⬠x y z */
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++/* a b c LROâ 1 2 3 PDF⬠x y z */
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++/* a b c RLO⮠1 2 3 PDF⬠x y z */
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++/* a b c LRI⦠1 2 3 PDI⩠x y z */
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++/* a b c RLI⧠1 2 3 PDI⩠x y */
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++/* a b c FSI⨠1 2 3 PDI⩠x y z */
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++
++/* Same but C++ comments instead. */
++// a b c LRE⪠1 2 3 PDF⬠x y z
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++// a b c RLE⫠1 2 3 PDF⬠x y z
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++// a b c LROâ 1 2 3 PDF⬠x y z
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++// a b c RLO⮠1 2 3 PDF⬠x y z
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++// a b c LRI⦠1 2 3 PDI⩠x y z
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++// a b c RLI⧠1 2 3 PDI⩠x y
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++// a b c FSI⨠1 2 3 PDI⩠x y z
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++
++/* Here we're closing an unopened context, warn when =any. */
++/* a b c PDIâ© x y z */
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
++/* a b c PDF⬠x y z */
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++// a b c PDIâ© x y z
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
++// a b c PDF⬠x y z
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++
++/* Multiline comments. */
++/* a b c PDIâ© x y z
++ */
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */
++/* a b c PDF⬠x y z
++ */
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDIâ© x y z
++ */
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDF⬠x y z
++ */
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDIâ© x y z */
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
++/* first
++ a b c PDF⬠x y z */
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++
++void
++g1 ()
++{
++ const char *s1 = "a b c LRE⪠1 2 3 PDF⬠x y z";
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++ const char *s2 = "a b c RLE⫠1 2 3 PDF⬠x y z";
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++ const char *s3 = "a b c LROâ 1 2 3 PDF⬠x y z";
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++ const char *s4 = "a b c RLO⮠1 2 3 PDF⬠x y z";
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++ const char *s5 = "a b c LRI⦠1 2 3 PDI⩠x y z";
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++ const char *s6 = "a b c RLI⧠1 2 3 PDI⩠x y z";
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++ const char *s7 = "a b c FSI⨠1 2 3 PDI⩠x y z";
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++ const char *s8 = "a b c PDIâ© x y z";
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
++ const char *s9 = "a b c PDF⬠x y z";
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++
++ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z";
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++}
++
++void
++g2 ()
++{
++ const char c1 = '\u202a';
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++ const char c2 = '\u202A';
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++ const char c3 = '\u202b';
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++ const char c4 = '\u202B';
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++ const char c5 = '\u202d';
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++ const char c6 = '\u202D';
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++ const char c7 = '\u202e';
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++ const char c8 = '\u202E';
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++ const char c9 = '\u2066';
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++ const char c10 = '\u2067';
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++ const char c11 = '\u2068';
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++}
++
++int aâªbâ¬c;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int aâ«bâ¬c;
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++int aâbâ¬c;
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++int aâ®bâ¬c;
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++int aâ¦bâ©c;
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++int aâ§bâ©c;
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++int aâ¨bâ©c;
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++int Aâ¬X;
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++int A\u202cY;
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++int A\u202CY2;
++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */
++
++int d\u202ae\u202cf;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int d\u202Ae\u202cf2;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int d\u202be\u202cf;
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++int d\u202Be\u202cf2;
++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */
++int d\u202de\u202cf;
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++int d\u202De\u202cf2;
++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */
++int d\u202ee\u202cf;
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++int d\u202Ee\u202cf2;
++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */
++int d\u2066e\u2069f;
++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */
++int d\u2067e\u2069f;
++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */
++int d\u2068e\u2069f;
++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */
++int X\u2069;
++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-5.c b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
+new file mode 100644
+index 00000000000..68cb053144b
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c
+@@ -0,0 +1,188 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired -Wno-multichar -Wno-overflow" } */
++/* Test all bidi chars in various contexts (identifiers, comments,
++ string literals, character constants), both UCN and UTF-8. The bidi
++ chars here are properly terminated, except for the character constants. */
++
++/* a b c LRE⪠1 2 3 PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLE⫠1 2 3 PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c LROâ 1 2 3 PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLO⮠1 2 3 PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c LRI⦠1 2 3 PDI⩠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLI⧠1 2 3 PDI⩠x y */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c FSI⨠1 2 3 PDI⩠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++/* Same but C++ comments instead. */
++// a b c LRE⪠1 2 3 PDF⬠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLE⫠1 2 3 PDF⬠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c LROâ 1 2 3 PDF⬠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLO⮠1 2 3 PDF⬠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c LRI⦠1 2 3 PDI⩠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLI⧠1 2 3 PDI⩠x y
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c FSI⨠1 2 3 PDI⩠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++/* Here we're closing an unopened context, warn when =any. */
++/* a b c PDIâ© x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* a b c PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c PDIâ© x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++// a b c PDF⬠x y z
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++/* Multiline comments. */
++/* a b c PDIâ© x y z
++ */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* a b c PDF⬠x y z
++ */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDIâ© x y z
++ */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDF⬠x y z
++ */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */
++/* first
++ a b c PDIâ© x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++/* first
++ a b c PDF⬠x y z */
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++void
++g1 ()
++{
++ const char *s1 = "a b c LRE⪠1 2 3 PDF⬠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s2 = "a b c RLE⫠1 2 3 PDF⬠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s3 = "a b c LROâ 1 2 3 PDF⬠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s4 = "a b c RLO⮠1 2 3 PDF⬠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s5 = "a b c LRI⦠1 2 3 PDI⩠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s6 = "a b c RLI⧠1 2 3 PDI⩠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s7 = "a b c FSI⨠1 2 3 PDI⩠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s8 = "a b c PDIâ© x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s9 = "a b c PDF⬠x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z";
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++}
++
++void
++g2 ()
++{
++ const char c1 = '\u202a';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c2 = '\u202A';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c3 = '\u202b';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c4 = '\u202B';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c5 = '\u202d';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c6 = '\u202D';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c7 = '\u202e';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c8 = '\u202E';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c9 = '\u2066';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c10 = '\u2067';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char c11 = '\u2068';
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++}
++
++int aâªbâ¬c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâ«bâ¬c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâbâ¬c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâ®bâ¬c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâ¦bâ©c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâ§bâ©c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int aâ¨bâ©c;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int Aâ¬X;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int A\u202cY;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int A\u202CY2;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++
++int d\u202ae\u202cf;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202Ae\u202cf2;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202be\u202cf;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202Be\u202cf2;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202de\u202cf;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202De\u202cf2;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202ee\u202cf;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u202Ee\u202cf2;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u2066e\u2069f;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u2067e\u2069f;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int d\u2068e\u2069f;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
++int X\u2069;
++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-6.c b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
+new file mode 100644
+index 00000000000..0ce6fff2dee
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c
+@@ -0,0 +1,155 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test nesting of bidi chars in various contexts. */
++
++/* Terminated by the wrong char: */
++/* a b c LRE⪠1 2 3 PDI⩠x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLEâ« 1 2 3 PDIâ© x y z*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c LROâ 1 2 3 PDIâ© x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLOâ® 1 2 3 PDIâ© x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c LRI⦠1 2 3 PDF⬠x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c RLI⧠1 2 3 PDF⬠x y z */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* a b c FSI⨠1 2 3 PDF⬠x y z*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++/* LRE⪠PDF⬠*/
++/* LRE⪠LRE⪠PDF⬠PDF⬠*/
++/* PDF⬠LRE⪠PDF⬠*/
++/* LRE⪠PDF⬠LRE⪠PDF⬠*/
++/* LRE⪠LRE⪠PDF⬠*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* PDF⬠LRE⪠*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++// a b c LRE⪠1 2 3 PDI⩠x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLEâ« 1 2 3 PDIâ© x y z*/
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c LROâ 1 2 3 PDIâ© x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLOâ® 1 2 3 PDIâ© x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c LRI⦠1 2 3 PDF⬠x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c RLI⧠1 2 3 PDF⬠x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// a b c FSI⨠1 2 3 PDF⬠x y z
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++// LRE⪠PDFâ¬
++// LRE⪠LRE⪠PDF⬠PDFâ¬
++// PDF⬠LRE⪠PDFâ¬
++// LRE⪠PDF⬠LRE⪠PDFâ¬
++// LRE⪠LRE⪠PDFâ¬
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++// PDF⬠LREâª
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++void
++g1 ()
++{
++ const char *s1 = "a b c LRE⪠1 2 3 PDI⩠x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s2 = "a b c LRE\u202a 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s3 = "a b c RLEâ« 1 2 3 PDIâ© x y ";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s4 = "a b c RLE\u202b 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s5 = "a b c LROâ 1 2 3 PDIâ© x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s6 = "a b c LRO\u202d 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s7 = "a b c RLOâ® 1 2 3 PDIâ© x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s8 = "a b c RLO\u202e 1 2 3 PDI\u2069 x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s9 = "a b c LRI⦠1 2 3 PDF⬠x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s10 = "a b c LRI\u2066 1 2 3 PDF\u202c x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s11 = "a b c RLI⧠1 2 3 PDF⬠x y z\
++ ";
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++ const char *s12 = "a b c RLI\u2067 1 2 3 PDF\u202c x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s13 = "a b c FSI⨠1 2 3 PDF⬠x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s14 = "a b c FSI\u2068 1 2 3 PDF\u202c x y z";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s15 = "PDF⬠LREâª";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s16 = "PDF\u202c LRE\u202a";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s17 = "LRE⪠PDFâ¬";
++ const char *s18 = "LRE\u202a PDF\u202c";
++ const char *s19 = "LRE⪠LRE⪠PDF⬠PDFâ¬";
++ const char *s20 = "LRE\u202a LRE\u202a PDF\u202c PDF\u202c";
++ const char *s21 = "PDF⬠LRE⪠PDFâ¬";
++ const char *s22 = "PDF\u202c LRE\u202a PDF\u202c";
++ const char *s23 = "LRE⪠LRE⪠PDFâ¬";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s24 = "LRE\u202a LRE\u202a PDF\u202c";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s25 = "PDF⬠LREâª";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s26 = "PDF\u202c LRE\u202a";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s27 = "PDF⬠LRE\u202a";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++ const char *s28 = "PDF\u202c LREâª";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++}
++
++int aLREâªbPDIâ©;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int A\u202aB\u2069C;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aRLEâ«bPDIâ©;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202bB\u2069c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aLROâbPDIâ©;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202db\u2069c2;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aRLOâ®bPDIâ©;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u202eb\u2069;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aLRIâ¦bPDFâ¬;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u2066b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aRLIâ§bPDFâ¬c
++;
++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */
++int a\u2067b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aFSIâ¨bPDFâ¬;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a\u2068b\u202c;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aFSIâ¨bPD\u202C;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aFSI\u2068bPDFâ¬_;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int aLREâªbPDFâ¬b;
++int A\u202aB\u202c;
++int a_LREâª_LREâª_b_PDFâ¬_PDFâ¬;
++int A\u202aA\u202aB\u202cB\u202c;
++int aPDFâ¬bLREadPDFâ¬;
++int a_\u202C_\u202a_\u202c;
++int a_LREâª_b_PDFâ¬_c_LREâª_PDFâ¬;
++int a_\u202a_\u202c_\u202a_\u202c_;
++int a_LREâª_b_PDFâ¬_c_LREâª;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int a_\u202a_\u202c_\u202a_;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-7.c b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
+new file mode 100644
+index 00000000000..d012d420ec0
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c
+@@ -0,0 +1,9 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=any" } */
++/* Test we ignore UCNs in comments. */
++
++// a b c \u202a 1 2 3
++// a b c \u202A 1 2 3
++/* a b c \u202a 1 2 3 */
++/* a b c \u202A 1 2 3 */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-8.c b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
+new file mode 100644
+index 00000000000..4f54c5092ec
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c
+@@ -0,0 +1,13 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=any" } */
++/* Test \u vs \U. */
++
++int a_\u202A;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int a_\u202a_2;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int a_\U0000202A_3;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
++int a_\U0000202a_4;
++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-9.c b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
+new file mode 100644
+index 00000000000..e2af1b1ca97
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c
+@@ -0,0 +1,29 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired" } */
++/* Test that we properly separate bidi contexts (comment/identifier/character
++ constant/string literal). */
++
++/* LRE ->âª<- */ int pdf_\u202c_1;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLE ->â«<- */ int pdf_\u202c_2;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRO ->â<- */ int pdf_\u202c_3;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLO ->â®<- */ int pdf_\u202c_4;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRI ->â¦<-*/ int pdi_\u2069_1;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* RLI ->â§<- */ int pdi_\u2069_12;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* FSI ->â¨<- */ int pdi_\u2069_3;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++
++const char *s1 = "LRE\u202a"; /* PDF ->â¬<- */
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++/* LRE ->âª<- */ const char *s2 = "PDF\u202c";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++const char *s3 = "LRE\u202a"; int pdf_\u202c_5;
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
++int lre_\u202a; const char *s4 = "PDF\u202c";
++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */
+diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
+index 176f8c5bbce..112b9c24751 100644
+--- a/libcpp/include/cpplib.h
++++ b/libcpp/include/cpplib.h
+@@ -318,6 +318,17 @@ enum cpp_main_search
+ CMS_system, /* Search the system INCLUDE path. */
+ };
+
++/* The possible bidirectional control characters checking levels, from least
++ restrictive to most. */
++enum cpp_bidirectional_level {
++ /* No checking. */
++ bidirectional_none,
++ /* Only detect unpaired uses of bidirectional control characters. */
++ bidirectional_unpaired,
++ /* Detect any use of bidirectional control characters. */
++ bidirectional_any
++};
++
+ /* This structure is nested inside struct cpp_reader, and
+ carries all the options visible to the command line. */
+ struct cpp_options
+@@ -531,6 +542,10 @@ struct cpp_options
+ /* True if warn about differences between C++98 and C++11. */
+ bool cpp_warn_cxx11_compat;
+
++ /* Nonzero if bidirectional control characters checking is on. See enum
++ cpp_bidirectional_level. */
++ unsigned char cpp_warn_bidirectional;
++
+ /* Dependency generation. */
+ struct
+ {
+@@ -635,7 +650,8 @@ enum cpp_warning_reason {
+ CPP_W_C90_C99_COMPAT,
+ CPP_W_C11_C2X_COMPAT,
+ CPP_W_CXX11_COMPAT,
+- CPP_W_EXPANSION_TO_DEFINED
++ CPP_W_EXPANSION_TO_DEFINED,
++ CPP_W_BIDIRECTIONAL
+ };
+
+ /* Callback for header lookup for HEADER, which is the name of a
+diff --git a/libcpp/init.c b/libcpp/init.c
+index 5a424e23553..f9a8f5f088f 100644
+--- a/libcpp/init.c
++++ b/libcpp/init.c
+@@ -219,6 +219,7 @@ cpp_create_reader (enum c_lang lang, cpp
+ = ENABLE_CANONICAL_SYSTEM_HEADERS;
+ CPP_OPTION (pfile, ext_numeric_literals) = 1;
+ CPP_OPTION (pfile, warn_date_time) = 0;
++ CPP_OPTION (pfile, cpp_warn_bidirectional) = bidirectional_unpaired;
+
+ /* Default CPP arithmetic to something sensible for the host for the
+ benefit of dumb users like fix-header. */
+diff --git a/libcpp/internal.h b/libcpp/internal.h
+index 8577cab6c83..0ce0246c5a2 100644
+--- a/libcpp/internal.h
++++ b/libcpp/internal.h
+@@ -597,6 +597,13 @@ struct cpp_reader
+ /* Location identifying the main source file -- intended to be line
+ zero of said file. */
+ location_t main_loc;
++
++ /* Returns true iff we should warn about UTF-8 bidirectional control
++ characters. */
++ bool warn_bidi_p () const
++ {
++ return CPP_OPTION (this, cpp_warn_bidirectional) != bidirectional_none;
++ }
+ };
+
+ /* Character classes. Based on the more primitive macros in safe-ctype.h.
+diff --git a/libcpp/lex.c b/libcpp/lex.c
+index fa2253d41c3..6a4fbce6030 100644
+--- a/libcpp/lex.c
++++ b/libcpp/lex.c
+@@ -1164,6 +1164,324 @@ _cpp_process_line_notes (cpp_reader *pfi
+ }
+ }
+
++namespace bidi {
++ enum class kind {
++ NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI, LTR, RTL
++ };
++
++ /* All the UTF-8 encodings of bidi characters start with E2. */
++ constexpr uchar utf8_start = 0xe2;
++
++ /* A vector holding currently open bidi contexts. We use a char for
++ each context, its LSB is 1 if it represents a PDF context, 0 if it
++ represents a PDI context. The next bit is 1 if this context was open
++ by a bidi character written as a UCN, and 0 when it was UTF-8. */
++ semi_embedded_vec <unsigned char, 16> vec;
++
++ /* Close the whole comment/identifier/string literal/character constant
++ context. */
++ void on_close ()
++ {
++ vec.truncate (0);
++ }
++
++ /* Pop the last element in the vector. */
++ void pop ()
++ {
++ unsigned int len = vec.count ();
++ gcc_checking_assert (len > 0);
++ vec.truncate (len - 1);
++ }
++
++ /* Return the context of the Ith element. */
++ kind ctx_at (unsigned int i)
++ {
++ return (vec[i] & 1) ? kind::PDF : kind::PDI;
++ }
++
++ /* Return which context is currently opened. */
++ kind current_ctx ()
++ {
++ unsigned int len = vec.count ();
++ if (len == 0)
++ return kind::NONE;
++ return ctx_at (len - 1);
++ }
++
++ /* Return true if the current context comes from a UCN origin, that is,
++ the bidi char which started this bidi context was written as a UCN. */
++ bool current_ctx_ucn_p ()
++ {
++ unsigned int len = vec.count ();
++ gcc_checking_assert (len > 0);
++ return (vec[len - 1] >> 1) & 1;
++ }
++
++ /* We've read a bidi char, update the current vector as necessary. */
++ void on_char (kind k, bool ucn_p)
++ {
++ switch (k)
++ {
++ case kind::LRE:
++ case kind::RLE:
++ case kind::LRO:
++ case kind::RLO:
++ vec.push (ucn_p ? 3u : 1u);
++ break;
++ case kind::LRI:
++ case kind::RLI:
++ case kind::FSI:
++ vec.push (ucn_p ? 2u : 0u);
++ break;
++ /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
++ whose scope has not yet been terminated. */
++ case kind::PDF:
++ if (current_ctx () == kind::PDF)
++ pop ();
++ break;
++ /* PDI terminates the scope of the last LRI, RLI, or FSI whose
++ scope has not yet been terminated, as well as the scopes of
++ any subsequent LREs, RLEs, LROs, or RLOs whose scopes have not
++ yet been terminated. */
++ case kind::PDI:
++ for (int i = vec.count () - 1; i >= 0; --i)
++ if (ctx_at (i) == kind::PDI)
++ {
++ vec.truncate (i);
++ break;
++ }
++ break;
++ case kind::LTR:
++ case kind::RTL:
++ /* These aren't popped by a PDF/PDI. */
++ break;
++ [[likely]] case kind::NONE:
++ break;
++ default:
++ abort ();
++ }
++ }
++
++ /* Return a descriptive string for K. */
++ const char *to_str (kind k)
++ {
++ switch (k)
++ {
++ case kind::LRE:
++ return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
++ case kind::RLE:
++ return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
++ case kind::LRO:
++ return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
++ case kind::RLO:
++ return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
++ case kind::LRI:
++ return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
++ case kind::RLI:
++ return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
++ case kind::FSI:
++ return "U+2068 (FIRST STRONG ISOLATE)";
++ case kind::PDF:
++ return "U+202C (POP DIRECTIONAL FORMATTING)";
++ case kind::PDI:
++ return "U+2069 (POP DIRECTIONAL ISOLATE)";
++ case kind::LTR:
++ return "U+200E (LEFT-TO-RIGHT MARK)";
++ case kind::RTL:
++ return "U+200F (RIGHT-TO-LEFT MARK)";
++ default:
++ abort ();
++ }
++ }
++}
++
++/* Parse a sequence of 3 bytes starting with P and return its bidi code. */
++
++static bidi::kind
++get_bidi_utf8 (const unsigned char *const p)
++{
++ gcc_checking_assert (p[0] == bidi::utf8_start);
++
++ if (p[1] == 0x80)
++ switch (p[2])
++ {
++ case 0xaa:
++ return bidi::kind::LRE;
++ case 0xab:
++ return bidi::kind::RLE;
++ case 0xac:
++ return bidi::kind::PDF;
++ case 0xad:
++ return bidi::kind::LRO;
++ case 0xae:
++ return bidi::kind::RLO;
++ case 0x8e:
++ return bidi::kind::LTR;
++ case 0x8f:
++ return bidi::kind::RTL;
++ default:
++ break;
++ }
++ else if (p[1] == 0x81)
++ switch (p[2])
++ {
++ case 0xa6:
++ return bidi::kind::LRI;
++ case 0xa7:
++ return bidi::kind::RLI;
++ case 0xa8:
++ return bidi::kind::FSI;
++ case 0xa9:
++ return bidi::kind::PDI;
++ default:
++ break;
++ }
++
++ return bidi::kind::NONE;
++}
++
++/* Parse a UCN where P points just past \u or \U and return its bidi code. */
++
++static bidi::kind
++get_bidi_ucn (const unsigned char *p, bool is_U)
++{
++ /* 6.4.3 Universal Character Names
++ \u hex-quad
++ \U hex-quad hex-quad
++ where \unnnn means \U0000nnnn. */
++
++ if (is_U)
++ {
++ if (p[0] != '0' || p[1] != '0' || p[2] != '0' || p[3] != '0')
++ return bidi::kind::NONE;
++ /* Skip 4B so we can treat \u and \U the same below. */
++ p += 4;
++ }
++
++ /* All code points we are looking for start with 20xx. */
++ if (p[0] != '2' || p[1] != '0')
++ return bidi::kind::NONE;
++ else if (p[2] == '2')
++ switch (p[3])
++ {
++ case 'a':
++ case 'A':
++ return bidi::kind::LRE;
++ case 'b':
++ case 'B':
++ return bidi::kind::RLE;
++ case 'c':
++ case 'C':
++ return bidi::kind::PDF;
++ case 'd':
++ case 'D':
++ return bidi::kind::LRO;
++ case 'e':
++ case 'E':
++ return bidi::kind::RLO;
++ default:
++ break;
++ }
++ else if (p[2] == '6')
++ switch (p[3])
++ {
++ case '6':
++ return bidi::kind::LRI;
++ case '7':
++ return bidi::kind::RLI;
++ case '8':
++ return bidi::kind::FSI;
++ case '9':
++ return bidi::kind::PDI;
++ default:
++ break;
++ }
++ else if (p[2] == '0')
++ switch (p[3])
++ {
++ case 'e':
++ case 'E':
++ return bidi::kind::LTR;
++ case 'f':
++ case 'F':
++ return bidi::kind::RTL;
++ default:
++ break;
++ }
++
++ return bidi::kind::NONE;
++}
++
++/* We're closing a bidi context, that is, we've encountered a newline,
++ are closing a C-style comment, or are at the end of a string literal,
++ character constant, or identifier. Warn if this context was not
++ properly terminated by a PDI or PDF. P points to the last character
++ in this context. */
++
++static void
++maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
++{
++ if (CPP_OPTION (pfile, cpp_warn_bidirectional) == bidirectional_unpaired
++ && bidi::vec.count () > 0)
++ {
++ const location_t loc
++ = linemap_position_for_column (pfile->line_table,
++ CPP_BUF_COLUMN (pfile->buffer, p));
++ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
++ "unpaired UTF-8 bidirectional control character "
++ "detected");
++ }
++ /* We're done with this context. */
++ bidi::on_close ();
++}
++
++/* We're at the beginning or in the middle of an identifier/comment/string
++ literal/character constant. Warn if we've encountered a bidi character.
++ KIND says which bidi character it was; P points to it in the character
++ stream. UCN_P is true iff this bidi character was written as a UCN. */
++
++static void
++maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
++ bool ucn_p)
++{
++ if (__builtin_expect (kind == bidi::kind::NONE, 1))
++ return;
++
++ const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
++
++ if (warn_bidi != bidirectional_none)
++ {
++ const location_t loc
++ = linemap_position_for_column (pfile->line_table,
++ CPP_BUF_COLUMN (pfile->buffer, p));
++ /* It seems excessive to warn about a PDI/PDF that is closing
++ an opened context because we've already warned about the
++ opening character. Except warn when we have a UCN x UTF-8
++ mismatch. */
++ if (kind == bidi::current_ctx ())
++ {
++ if (warn_bidi == bidirectional_unpaired
++ && bidi::current_ctx_ucn_p () != ucn_p)
++ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
++ "UTF-8 vs UCN mismatch when closing "
++ "a context by \"%s\"", bidi::to_str (kind));
++ }
++ else if (warn_bidi == bidirectional_any)
++ {
++ if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
++ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
++ "\"%s\" is closing an unopened context",
++ bidi::to_str (kind));
++ else
++ cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
++ "found problematic Unicode character \"%s\"",
++ bidi::to_str (kind));
++ }
++ }
++ /* We're done with this context. */
++ bidi::on_char (kind, ucn_p);
++}
++
+ /* Skip a C-style block comment. We find the end of the comment by
+ seeing if an asterisk is before every '/' we encounter. Returns
+ nonzero if comment terminated by EOF, zero otherwise.
+@@ -1175,6 +1493,7 @@ _cpp_skip_block_comment (cpp_reader *pfi
+ cpp_buffer *buffer = pfile->buffer;
+ const uchar *cur = buffer->cur;
+ uchar c;
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+
+ cur++;
+ if (*cur == '/')
+@@ -1189,7 +1508,11 @@ _cpp_skip_block_comment (cpp_reader *pfi
+ if (c == '/')
+ {
+ if (cur[-2] == '*')
+- break;
++ {
++ if (warn_bidi_p)
++ maybe_warn_bidi_on_close (pfile, cur);
++ break;
++ }
+
+ /* Warn about potential nested comments, but not if the '/'
+ comes immediately before the true comment delimiter.
+@@ -1208,6 +1531,8 @@ _cpp_skip_block_comment (cpp_reader *pfi
+ {
+ unsigned int cols;
+ buffer->cur = cur - 1;
++ if (warn_bidi_p)
++ maybe_warn_bidi_on_close (pfile, cur);
+ _cpp_process_line_notes (pfile, true);
+ if (buffer->next_line >= buffer->rlimit)
+ return true;
+@@ -1218,6 +1543,13 @@ _cpp_skip_block_comment (cpp_reader *pfi
+
+ cur = buffer->cur;
+ }
++ /* If this is a beginning of a UTF-8 encoding, it might be
++ a bidirectional control character. */
++ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
++ {
++ bidi::kind kind = get_bidi_utf8 (cur - 1);
++ maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/false);
++ }
+ }
+
+ buffer->cur = cur;
+@@ -1233,9 +1565,31 @@ skip_line_comment (cpp_reader *pfile)
+ {
+ cpp_buffer *buffer = pfile->buffer;
+ location_t orig_line = pfile->line_table->highest_line;
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+
+- while (*buffer->cur != '\n')
+- buffer->cur++;
++ if (!warn_bidi_p)
++ while (*buffer->cur != '\n')
++ buffer->cur++;
++ else
++ {
++ while (*buffer->cur != '\n'
++ && *buffer->cur != bidi::utf8_start)
++ buffer->cur++;
++ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
++ {
++ while (*buffer->cur != '\n')
++ {
++ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
++ {
++ bidi::kind kind = get_bidi_utf8 (buffer->cur);
++ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
++ /*ucn_p=*/false);
++ }
++ buffer->cur++;
++ }
++ maybe_warn_bidi_on_close (pfile, buffer->cur);
++ }
++ }
+
+ _cpp_process_line_notes (pfile, true);
+ return orig_line != pfile->line_table->highest_line;
+@@ -1317,11 +1671,13 @@ static const cppchar_t utf8_signifier =
+
+ /* Returns TRUE if the sequence starting at buffer->cur is valid in
+ an identifier. FIRST is TRUE if this starts an identifier. */
++
+ static bool
+ forms_identifier_p (cpp_reader *pfile, int first,
+ struct normalize_state *state)
+ {
+ cpp_buffer *buffer = pfile->buffer;
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+
+ if (*buffer->cur == '$')
+ {
+@@ -1344,6 +1700,13 @@ forms_identifier_p (cpp_reader *pfile, i
+ cppchar_t s;
+ if (*buffer->cur >= utf8_signifier)
+ {
++ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
++ && warn_bidi_p)
++ {
++ bidi::kind kind = get_bidi_utf8 (buffer->cur);
++ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
++ /*ucn_p=*/false);
++ }
+ if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
+ state, &s))
+ return true;
+@@ -1352,6 +1715,13 @@ forms_identifier_p (cpp_reader *pfile, i
+ && (buffer->cur[1] == 'u' || buffer->cur[1] == 'U'))
+ {
+ buffer->cur += 2;
++ if (warn_bidi_p)
++ {
++ bidi::kind kind = get_bidi_ucn (buffer->cur,
++ buffer->cur[-1] == 'U');
++ maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
++ /*ucn_p=*/true);
++ }
+ if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
+ state, &s, NULL, NULL))
+ return true;
+@@ -1460,6 +1830,7 @@ lex_identifier (cpp_reader *pfile, const
+ const uchar *cur;
+ unsigned int len;
+ unsigned int hash = HT_HASHSTEP (0, *base);
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+
+ cur = pfile->buffer->cur;
+ if (! starts_ucn)
+@@ -1483,6 +1854,8 @@ lex_identifier (cpp_reader *pfile, const
+ pfile->buffer->cur++;
+ }
+ } while (forms_identifier_p (pfile, false, nst));
++ if (warn_bidi_p)
++ maybe_warn_bidi_on_close (pfile, pfile->buffer->cur);
+ result = _cpp_interpret_identifier (pfile, base,
+ pfile->buffer->cur - base);
+ *spelling = cpp_lookup (pfile, base, pfile->buffer->cur - base);
+@@ -1719,6 +2092,7 @@ static void
+ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
+ {
+ const uchar *pos = base;
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+
+ /* 'tis a pity this information isn't passed down from the lexer's
+ initial categorization of the token. */
+@@ -1955,8 +2329,15 @@ lex_raw_string (cpp_reader *pfile, cpp_t
+ pos = base = pfile->buffer->cur;
+ note = &pfile->buffer->notes[pfile->buffer->cur_note];
+ }
++ else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0)
++ && warn_bidi_p)
++ maybe_warn_bidi_on_char (pfile, pos - 1, get_bidi_utf8 (pos - 1),
++ /*ucn_p=*/false);
+ }
+
++ if (warn_bidi_p)
++ maybe_warn_bidi_on_close (pfile, pos);
++
+ if (CPP_OPTION (pfile, user_literals))
+ {
+ /* If a string format macro, say from inttypes.h, is placed touching
+@@ -2051,15 +2432,27 @@ lex_string (cpp_reader *pfile, cpp_token
+ else
+ terminator = '>', type = CPP_HEADER_NAME;
+
++ const bool warn_bidi_p = pfile->warn_bidi_p ();
+ for (;;)
+ {
+ cppchar_t c = *cur++;
+
+ /* In #include-style directives, terminators are not escapable. */
+ if (c == '\\' && !pfile->state.angled_headers && *cur != '\n')
+- cur++;
++ {
++ if ((cur[0] == 'u' || cur[0] == 'U') && warn_bidi_p)
++ {
++ bidi::kind kind = get_bidi_ucn (cur + 1, cur[0] == 'U');
++ maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/true);
++ }
++ cur++;
++ }
+ else if (c == terminator)
+- break;
++ {
++ if (warn_bidi_p)
++ maybe_warn_bidi_on_close (pfile, cur - 1);
++ break;
++ }
+ else if (c == '\n')
+ {
+ cur--;
+@@ -2076,6 +2469,11 @@ lex_string (cpp_reader *pfile, cpp_token
+ }
+ else if (c == '\0')
+ saw_NUL = true;
++ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
++ {
++ bidi::kind kind = get_bidi_utf8 (cur - 1);
++ maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false);
++ }
+ }
+
+ if (saw_NUL && !pfile->state.skipping)
new file mode 100644
@@ -0,0 +1,142 @@
+From 1a7f2c0774129750fdf73e9f1b78f0ce983c9ab3 Mon Sep 17 00:00:00 2001
+From: David Malcolm <dmalcolm@redhat.com>
+Date: Tue, 2 Nov 2021 09:54:32 -0400
+Subject: [PATCH] libcpp: escape non-ASCII source bytes in -Wbidi-chars=
+ [PR103026]
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf8
+Content-Transfer-Encoding: 8bit
+
+This flags rich_locations associated with -Wbidi-chars= so that
+non-ASCII bytes will be escaped when printing the source lines
+(using the diagnostics support I added in
+r12-4825-gbd5e882cf6e0def3dd1bc106075d59a303fe0d1e).
+
+In particular, this ensures that the printed source lines will
+be pure ASCII, and thus the visual ordering of the characters
+will be the same as the logical ordering.
+
+Before:
+
+ Wbidi-chars-1.c: In function âmainâ:
+ Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 6 | /*â® } â¦if (isAdmin)⩠⦠begin admins only */
+ | ^
+ Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 9 | /* end admins only â® { â¦*/
+ | ^
+
+ Wbidi-chars-11.c:6:15: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 6 | int LRE_âª_PDF_\u202c;
+ | ^
+ Wbidi-chars-11.c:8:19: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 8 | int LRE_\u202a_PDF_â¬_;
+ | ^
+ Wbidi-chars-11.c:10:28: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 10 | const char *s1 = "LRE_âª_PDF_\u202c";
+ | ^
+ Wbidi-chars-11.c:12:33: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 12 | const char *s2 = "LRE_\u202a_PDF_â¬";
+ | ^
+
+After:
+
+ Wbidi-chars-1.c: In function âmainâ:
+ Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
+ | ^
+ Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 9 | /* end admins only <U+202E> { <U+2066>*/
+ | ^
+
+ Wbidi-chars-11.c:6:15: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 6 | int LRE_<U+202A>_PDF_\u202c;
+ | ^
+ Wbidi-chars-11.c:8:19: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 8 | int LRE_\u202a_PDF_<U+202C>_;
+ | ^
+ Wbidi-chars-11.c:10:28: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 10 | const char *s1 = "LRE_<U+202A>_PDF_\u202c";
+ | ^
+ Wbidi-chars-11.c:12:33: warning: UTF-8 vs UCN mismatch when closing a context by "U+202C (POP DIRECTIONAL FORMATTING)" [-Wbidi-chars=]
+ 12 | const char *s2 = "LRE_\u202a_PDF_<U+202C>";
+ | ^
+
+libcpp/ChangeLog:
+ PR preprocessor/103026
+ * lex.c (maybe_warn_bidi_on_close): Use a rich_location
+ and call set_escape_on_output (true) on it.
+ (maybe_warn_bidi_on_char): Likewise.
+
+Signed-off-by: David Malcolm <dmalcolm@redhat.com>
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=1a7f2c0774129750fdf73e9f1b78f0ce983c9ab3]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+
+---
+ libcpp/lex.c | 29 +++++++++++++++++------------
+ 1 file changed, 17 insertions(+), 12 deletions(-)
+
+diff --git a/libcpp/lex.c b/libcpp/lex.c
+index 8188e33b07d..2421d6c0f40 100644
+--- a/libcpp/lex.c
++++ b/libcpp/lex.c
+@@ -1427,9 +1427,11 @@ maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
+ const location_t loc
+ = linemap_position_for_column (pfile->line_table,
+ CPP_BUF_COLUMN (pfile->buffer, p));
+- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
+- "unpaired UTF-8 bidirectional control character "
+- "detected");
++ rich_location rich_loc (pfile->line_table, loc);
++ rich_loc.set_escape_on_output (true);
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "unpaired UTF-8 bidirectional control character "
++ "detected");
+ }
+ /* We're done with this context. */
+ bidi::on_close ();
+@@ -1454,6 +1456,9 @@ maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
+ const location_t loc
+ = linemap_position_for_column (pfile->line_table,
+ CPP_BUF_COLUMN (pfile->buffer, p));
++ rich_location rich_loc (pfile->line_table, loc);
++ rich_loc.set_escape_on_output (true);
++
+ /* It seems excessive to warn about a PDI/PDF that is closing
+ an opened context because we've already warned about the
+ opening character. Except warn when we have a UCN x UTF-8
+@@ -1462,20 +1467,20 @@ maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
+ {
+ if (warn_bidi == bidirectional_unpaired
+ && bidi::current_ctx_ucn_p () != ucn_p)
+- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
+- "UTF-8 vs UCN mismatch when closing "
+- "a context by \"%s\"", bidi::to_str (kind));
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "UTF-8 vs UCN mismatch when closing "
++ "a context by \"%s\"", bidi::to_str (kind));
+ }
+ else if (warn_bidi == bidirectional_any)
+ {
+ if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
+- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
+- "\"%s\" is closing an unopened context",
+- bidi::to_str (kind));
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "\"%s\" is closing an unopened context",
++ bidi::to_str (kind));
+ else
+- cpp_warning_with_line (pfile, CPP_W_BIDIRECTIONAL, loc, 0,
+- "found problematic Unicode character \"%s\"",
+- bidi::to_str (kind));
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "found problematic Unicode character \"%s\"",
++ bidi::to_str (kind));
+ }
+ }
+ /* We're done with this context. */
+--
+2.27.0
+
new file mode 100644
@@ -0,0 +1,573 @@
+From bef32d4a28595e933f24fef378cf052a30b674a7 Mon Sep 17 00:00:00 2001
+From: David Malcolm <dmalcolm@redhat.com>
+Date: Tue, 2 Nov 2021 15:45:22 -0400
+Subject: [PATCH] libcpp: capture and underline ranges in -Wbidi-chars=
+ [PR103026]
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf8
+Content-Transfer-Encoding: 8bit
+
+This patch converts the bidi::vec to use a struct so that we can
+capture location_t values for the bidirectional control characters.
+
+Before:
+
+ Wbidi-chars-1.c: In function âmainâ:
+ Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
+ | ^
+ Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control character detected [-Wbidi-chars=]
+ 9 | /* end admins only <U+202E> { <U+2066>*/
+ | ^
+
+After:
+
+ Wbidi-chars-1.c: In function âmainâ:
+ Wbidi-chars-1.c:6:43: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
+ 6 | /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
+ | ~~~~~~~~ ~~~~~~~~ ^
+ | | | |
+ | | | end of bidirectional context
+ | U+202E (RIGHT-TO-LEFT OVERRIDE) U+2066 (LEFT-TO-RIGHT ISOLATE)
+ Wbidi-chars-1.c:9:28: warning: unpaired UTF-8 bidirectional control characters detected [-Wbidi-chars=]
+ 9 | /* end admins only <U+202E> { <U+2066>*/
+ | ~~~~~~~~ ~~~~~~~~ ^
+ | | | |
+ | | | end of bidirectional context
+ | | U+2066 (LEFT-TO-RIGHT ISOLATE)
+ | U+202E (RIGHT-TO-LEFT OVERRIDE)
+
+Signed-off-by: David Malcolm <dmalcolm@redhat.com>
+
+gcc/testsuite/ChangeLog:
+ PR preprocessor/103026
+ * c-c++-common/Wbidi-chars-ranges.c: New test.
+
+libcpp/ChangeLog:
+ PR preprocessor/103026
+ * lex.c (struct bidi::context): New.
+ (bidi::vec): Convert to a vec of context rather than unsigned
+ char.
+ (bidi::ctx_at): Rename to...
+ (bidi::pop_kind_at): ...this and reimplement for above change.
+ (bidi::current_ctx): Update for change to vec.
+ (bidi::current_ctx_ucn_p): Likewise.
+ (bidi::current_ctx_loc): New.
+ (bidi::on_char): Update for usage of context struct. Add "loc"
+ param and pass it when pushing contexts.
+ (get_location_for_byte_range_in_cur_line): New.
+ (get_bidi_utf8): Rename to...
+ (get_bidi_utf8_1): ...this, reintroducing...
+ (get_bidi_utf8): ...as a wrapper, setting *OUT when the result is
+ not NONE.
+ (get_bidi_ucn): Rename to...
+ (get_bidi_ucn_1): ...this, reintroducing...
+ (get_bidi_ucn): ...as a wrapper, setting *OUT when the result is
+ not NONE.
+ (class unpaired_bidi_rich_location): New.
+ (maybe_warn_bidi_on_close): Use unpaired_bidi_rich_location when
+ reporting on unpaired bidi chars. Split into singular vs plural
+ spellings.
+ (maybe_warn_bidi_on_char): Pass in a location_t rather than a
+ const uchar * and use it when emitting warnings, and when calling
+ bidi::on_char.
+ (_cpp_skip_block_comment): Capture location when kind is not NONE
+ and pass it to maybe_warn_bidi_on_char.
+ (skip_line_comment): Likewise.
+ (forms_identifier_p): Likewise.
+ (lex_raw_string): Likewise.
+ (lex_string): Likewise.
+
+Signed-off-by: David Malcolm <dmalcolm@redhat.com>
+
+CVE: CVE-2021-42574
+Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bef32d4a28595e933f24fef378cf052a30b674a7]
+Signed-off-by: Pgowda <pgowda.cve@gmail.com>
+
+---
+ .../c-c++-common/Wbidi-chars-ranges.c | 54 ++++
+ libcpp/lex.c | 251 ++++++++++++++----
+ 2 files changed, 257 insertions(+), 48 deletions(-)
+ create mode 100644 gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
+
+diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
+new file mode 100644
+index 00000000000..298750a2a64
+--- /dev/null
++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c
+@@ -0,0 +1,54 @@
++/* PR preprocessor/103026 */
++/* { dg-do compile } */
++/* { dg-options "-Wbidi-chars=unpaired -fdiagnostics-show-caret" } */
++/* Verify that we escape and underline pertinent bidirectional
++ control characters when quoting the source. */
++
++int test_unpaired_bidi () {
++ int isAdmin = 0;
++ /*â® } â¦if (isAdmin)⩠⦠begin admins only */
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++#if 0
++ { dg-begin-multiline-output "" }
++ /*<U+202E> } <U+2066>if (isAdmin)<U+2069> <U+2066> begin admins only */
++ ~~~~~~~~ ~~~~~~~~ ^
++ | | |
++ | | end of bidirectional context
++ U+202E (RIGHT-TO-LEFT OVERRIDE) U+2066 (LEFT-TO-RIGHT ISOLATE)
++ { dg-end-multiline-output "" }
++#endif
++
++ __builtin_printf("You are an admin.\n");
++ /* end admins only â® { â¦*/
++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */
++#if 0
++ { dg-begin-multiline-output "" }
++ /* end admins only <U+202E> { <U+2066>*/
++ ~~~~~~~~ ~~~~~~~~ ^
++ | | |
++ | | end of bidirectional context
++ | U+2066 (LEFT-TO-RIGHT ISOLATE)
++ U+202E (RIGHT-TO-LEFT OVERRIDE)
++ { dg-end-multiline-output "" }
++#endif
++
++ return 0;
++}
++
++int LRE_âª_PDF_\u202c;
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++#if 0
++ { dg-begin-multiline-output "" }
++ int LRE_<U+202A>_PDF_\u202c;
++ ~~~~~~~~ ^~~~~~
++ { dg-end-multiline-output "" }
++#endif
++
++const char *s1 = "LRE_âª_PDF_\u202c";
++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */
++#if 0
++ { dg-begin-multiline-output "" }
++ const char *s1 = "LRE_<U+202A>_PDF_\u202c";
++ ~~~~~~~~ ^~~~~~
++ { dg-end-multiline-output "" }
++#endif
+diff --git a/libcpp/lex.c b/libcpp/lex.c
+index 2421d6c0f40..94c36f0d014 100644
+--- a/libcpp/lex.c
++++ b/libcpp/lex.c
+@@ -1172,11 +1172,34 @@ namespace bidi {
+ /* All the UTF-8 encodings of bidi characters start with E2. */
+ constexpr uchar utf8_start = 0xe2;
+
++ struct context
++ {
++ context () {}
++ context (location_t loc, kind k, bool pdf, bool ucn)
++ : m_loc (loc), m_kind (k), m_pdf (pdf), m_ucn (ucn)
++ {
++ }
++
++ kind get_pop_kind () const
++ {
++ return m_pdf ? kind::PDF : kind::PDI;
++ }
++ bool ucn_p () const
++ {
++ return m_ucn;
++ }
++
++ location_t m_loc;
++ kind m_kind;
++ unsigned m_pdf : 1;
++ unsigned m_ucn : 1;
++ };
++
+ /* A vector holding currently open bidi contexts. We use a char for
+ each context, its LSB is 1 if it represents a PDF context, 0 if it
+ represents a PDI context. The next bit is 1 if this context was open
+ by a bidi character written as a UCN, and 0 when it was UTF-8. */
+- semi_embedded_vec <unsigned char, 16> vec;
++ semi_embedded_vec <context, 16> vec;
+
+ /* Close the whole comment/identifier/string literal/character constant
+ context. */
+@@ -1193,19 +1216,19 @@ namespace bidi {
+ vec.truncate (len - 1);
+ }
+
+- /* Return the context of the Ith element. */
+- kind ctx_at (unsigned int i)
++ /* Return the pop kind of the context of the Ith element. */
++ kind pop_kind_at (unsigned int i)
+ {
+- return (vec[i] & 1) ? kind::PDF : kind::PDI;
++ return vec[i].get_pop_kind ();
+ }
+
+- /* Return which context is currently opened. */
++ /* Return the pop kind of the context that is currently opened. */
+ kind current_ctx ()
+ {
+ unsigned int len = vec.count ();
+ if (len == 0)
+ return kind::NONE;
+- return ctx_at (len - 1);
++ return vec[len - 1].get_pop_kind ();
+ }
+
+ /* Return true if the current context comes from a UCN origin, that is,
+@@ -1214,11 +1237,19 @@ namespace bidi {
+ {
+ unsigned int len = vec.count ();
+ gcc_checking_assert (len > 0);
+- return (vec[len - 1] >> 1) & 1;
++ return vec[len - 1].m_ucn;
+ }
+
+- /* We've read a bidi char, update the current vector as necessary. */
+- void on_char (kind k, bool ucn_p)
++ location_t current_ctx_loc ()
++ {
++ unsigned int len = vec.count ();
++ gcc_checking_assert (len > 0);
++ return vec[len - 1].m_loc;
++ }
++
++ /* We've read a bidi char, update the current vector as necessary.
++ LOC is only valid when K is not kind::NONE. */
++ void on_char (kind k, bool ucn_p, location_t loc)
+ {
+ switch (k)
+ {
+@@ -1226,12 +1257,12 @@ namespace bidi {
+ case kind::RLE:
+ case kind::LRO:
+ case kind::RLO:
+- vec.push (ucn_p ? 3u : 1u);
++ vec.push (context (loc, k, true, ucn_p));
+ break;
+ case kind::LRI:
+ case kind::RLI:
+ case kind::FSI:
+- vec.push (ucn_p ? 2u : 0u);
++ vec.push (context (loc, k, false, ucn_p));
+ break;
+ /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
+ whose scope has not yet been terminated. */
+@@ -1245,7 +1276,7 @@ namespace bidi {
+ yet been terminated. */
+ case kind::PDI:
+ for (int i = vec.count () - 1; i >= 0; --i)
+- if (ctx_at (i) == kind::PDI)
++ if (pop_kind_at (i) == kind::PDI)
+ {
+ vec.truncate (i);
+ break;
+@@ -1295,10 +1326,47 @@ namespace bidi {
+ }
+ }
+
++/* Get location_t for the range of bytes [START, START + NUM_BYTES)
++ within the current line in FILE, with the caret at START. */
++
++static location_t
++get_location_for_byte_range_in_cur_line (cpp_reader *pfile,
++ const unsigned char *const start,
++ size_t num_bytes)
++{
++ gcc_checking_assert (num_bytes > 0);
++
++ /* CPP_BUF_COLUMN and linemap_position_for_column both refer
++ to offsets in bytes, but CPP_BUF_COLUMN is 0-based,
++ whereas linemap_position_for_column is 1-based. */
++
++ /* Get 0-based offsets within the line. */
++ size_t start_offset = CPP_BUF_COLUMN (pfile->buffer, start);
++ size_t end_offset = start_offset + num_bytes - 1;
++
++ /* Now convert to location_t, where "columns" are 1-based byte offsets. */
++ location_t start_loc = linemap_position_for_column (pfile->line_table,
++ start_offset + 1);
++ location_t end_loc = linemap_position_for_column (pfile->line_table,
++ end_offset + 1);
++
++ if (start_loc == end_loc)
++ return start_loc;
++
++ source_range src_range;
++ src_range.m_start = start_loc;
++ src_range.m_finish = end_loc;
++ location_t combined_loc = COMBINE_LOCATION_DATA (pfile->line_table,
++ start_loc,
++ src_range,
++ NULL);
++ return combined_loc;
++}
++
+ /* Parse a sequence of 3 bytes starting with P and return its bidi code. */
+
+ static bidi::kind
+-get_bidi_utf8 (const unsigned char *const p)
++get_bidi_utf8_1 (const unsigned char *const p)
+ {
+ gcc_checking_assert (p[0] == bidi::utf8_start);
+
+@@ -1340,10 +1408,25 @@ get_bidi_utf8 (const unsigned char *cons
+ return bidi::kind::NONE;
+ }
+
++/* Parse a sequence of 3 bytes starting with P and return its bidi code.
++ If the kind is not NONE, write the location to *OUT.*/
++
++static bidi::kind
++get_bidi_utf8 (cpp_reader *pfile, const unsigned char *const p, location_t *out)
++{
++ bidi::kind result = get_bidi_utf8_1 (p);
++ if (result != bidi::kind::NONE)
++ {
++ /* We have a sequence of 3 bytes starting at P. */
++ *out = get_location_for_byte_range_in_cur_line (pfile, p, 3);
++ }
++ return result;
++}
++
+ /* Parse a UCN where P points just past \u or \U and return its bidi code. */
+
+ static bidi::kind
+-get_bidi_ucn (const unsigned char *p, bool is_U)
++get_bidi_ucn_1 (const unsigned char *p, bool is_U)
+ {
+ /* 6.4.3 Universal Character Names
+ \u hex-quad
+@@ -1412,6 +1495,62 @@ get_bidi_ucn (const unsigned char *p, bo
+ return bidi::kind::NONE;
+ }
+
++/* Parse a UCN where P points just past \u or \U and return its bidi code.
++ If the kind is not NONE, write the location to *OUT.*/
++
++static bidi::kind
++get_bidi_ucn (cpp_reader *pfile, const unsigned char *p, bool is_U,
++ location_t *out)
++{
++ bidi::kind result = get_bidi_ucn_1 (p, is_U);
++ if (result != bidi::kind::NONE)
++ {
++ const unsigned char *start = p - 2;
++ size_t num_bytes = 2 + (is_U ? 8 : 4);
++ *out = get_location_for_byte_range_in_cur_line (pfile, start, num_bytes);
++ }
++ return result;
++}
++
++/* Subclass of rich_location for reporting on unpaired UTF-8
++ bidirectional control character(s).
++ Escape the source lines on output, and show all unclosed
++ bidi context, labelling everything. */
++
++class unpaired_bidi_rich_location : public rich_location
++{
++ public:
++ class custom_range_label : public range_label
++ {
++ public:
++ label_text get_text (unsigned range_idx) const FINAL OVERRIDE
++ {
++ /* range 0 is the primary location; each subsequent range i + 1
++ is for bidi::vec[i]. */
++ if (range_idx > 0)
++ {
++ const bidi::context &ctxt (bidi::vec[range_idx - 1]);
++ return label_text::borrow (bidi::to_str (ctxt.m_kind));
++ }
++ else
++ return label_text::borrow (_("end of bidirectional context"));
++ }
++ };
++
++ unpaired_bidi_rich_location (cpp_reader *pfile, location_t loc)
++ : rich_location (pfile->line_table, loc, &m_custom_label)
++ {
++ set_escape_on_output (true);
++ for (unsigned i = 0; i < bidi::vec.count (); i++)
++ add_range (bidi::vec[i].m_loc,
++ SHOW_RANGE_WITHOUT_CARET,
++ &m_custom_label);
++ }
++
++ private:
++ custom_range_label m_custom_label;
++};
++
+ /* We're closing a bidi context, that is, we've encountered a newline,
+ are closing a C-style comment, or are at the end of a string literal,
+ character constant, or identifier. Warn if this context was not
+@@ -1427,11 +1566,17 @@ maybe_warn_bidi_on_close (cpp_reader *pf
+ const location_t loc
+ = linemap_position_for_column (pfile->line_table,
+ CPP_BUF_COLUMN (pfile->buffer, p));
+- rich_location rich_loc (pfile->line_table, loc);
+- rich_loc.set_escape_on_output (true);
+- cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+- "unpaired UTF-8 bidirectional control character "
+- "detected");
++ unpaired_bidi_rich_location rich_loc (pfile, loc);
++ /* cpp_callbacks doesn't yet have a way to handle singular vs plural
++ forms of a diagnostic, so fake it for now. */
++ if (bidi::vec.count () > 1)
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "unpaired UTF-8 bidirectional control characters "
++ "detected");
++ else
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "unpaired UTF-8 bidirectional control character "
++ "detected");
+ }
+ /* We're done with this context. */
+ bidi::on_close ();
+@@ -1439,12 +1584,13 @@ maybe_warn_bidi_on_close (cpp_reader *pf
+
+ /* We're at the beginning or in the middle of an identifier/comment/string
+ literal/character constant. Warn if we've encountered a bidi character.
+- KIND says which bidi character it was; P points to it in the character
+- stream. UCN_P is true iff this bidi character was written as a UCN. */
++ KIND says which bidi control character it was; UCN_P is true iff this bidi
++ control character was written as a UCN. LOC is the location of the
++ character, but is only valid if KIND != bidi::kind::NONE. */
+
+ static void
+-maybe_warn_bidi_on_char (cpp_reader *pfile, const uchar *p, bidi::kind kind,
+- bool ucn_p)
++maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
++ bool ucn_p, location_t loc)
+ {
+ if (__builtin_expect (kind == bidi::kind::NONE, 1))
+ return;
+@@ -1453,9 +1599,6 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
+
+ if (warn_bidi != bidirectional_none)
+ {
+- const location_t loc
+- = linemap_position_for_column (pfile->line_table,
+- CPP_BUF_COLUMN (pfile->buffer, p));
+ rich_location rich_loc (pfile->line_table, loc);
+ rich_loc.set_escape_on_output (true);
+
+@@ -1467,9 +1610,12 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
+ {
+ if (warn_bidi == bidirectional_unpaired
+ && bidi::current_ctx_ucn_p () != ucn_p)
+- cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+- "UTF-8 vs UCN mismatch when closing "
+- "a context by \"%s\"", bidi::to_str (kind));
++ {
++ rich_loc.add_range (bidi::current_ctx_loc ());
++ cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
++ "UTF-8 vs UCN mismatch when closing "
++ "a context by \"%s\"", bidi::to_str (kind));
++ }
+ }
+ else if (warn_bidi == bidirectional_any)
+ {
+@@ -1484,7 +1630,7 @@ maybe_warn_bidi_on_char (cpp_reader *pfi
+ }
+ }
+ /* We're done with this context. */
+- bidi::on_char (kind, ucn_p);
++ bidi::on_char (kind, ucn_p, loc);
+ }
+
+ /* Skip a C-style block comment. We find the end of the comment by
+@@ -1552,8 +1698,9 @@ _cpp_skip_block_comment (cpp_reader *pfi
+ a bidirectional control character. */
+ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
+ {
+- bidi::kind kind = get_bidi_utf8 (cur - 1);
+- maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/false);
++ location_t loc;
++ bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+ }
+ }
+
+@@ -1586,9 +1733,9 @@ skip_line_comment (cpp_reader *pfile)
+ {
+ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
+ {
+- bidi::kind kind = get_bidi_utf8 (buffer->cur);
+- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
+- /*ucn_p=*/false);
++ location_t loc;
++ bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+ }
+ buffer->cur++;
+ }
+@@ -1708,9 +1855,9 @@ forms_identifier_p (cpp_reader *pfile, i
+ if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
+ && warn_bidi_p)
+ {
+- bidi::kind kind = get_bidi_utf8 (buffer->cur);
+- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
+- /*ucn_p=*/false);
++ location_t loc;
++ bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+ }
+ if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
+ state, &s))
+@@ -1722,10 +1869,12 @@ forms_identifier_p (cpp_reader *pfile, i
+ buffer->cur += 2;
+ if (warn_bidi_p)
+ {
+- bidi::kind kind = get_bidi_ucn (buffer->cur,
+- buffer->cur[-1] == 'U');
+- maybe_warn_bidi_on_char (pfile, buffer->cur, kind,
+- /*ucn_p=*/true);
++ location_t loc;
++ bidi::kind kind = get_bidi_ucn (pfile,
++ buffer->cur,
++ buffer->cur[-1] == 'U',
++ &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
+ }
+ if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
+ state, &s, NULL, NULL))
+@@ -2336,8 +2485,11 @@ lex_raw_string (cpp_reader *pfile, cpp_t
+ }
+ else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0)
+ && warn_bidi_p)
+- maybe_warn_bidi_on_char (pfile, pos - 1, get_bidi_utf8 (pos - 1),
+- /*ucn_p=*/false);
++ {
++ location_t loc;
++ bidi::kind kind = get_bidi_utf8 (pfile, pos - 1, &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
++ }
+ }
+
+ if (warn_bidi_p)
+@@ -2447,8 +2599,10 @@ lex_string (cpp_reader *pfile, cpp_token
+ {
+ if ((cur[0] == 'u' || cur[0] == 'U') && warn_bidi_p)
+ {
+- bidi::kind kind = get_bidi_ucn (cur + 1, cur[0] == 'U');
+- maybe_warn_bidi_on_char (pfile, cur, kind, /*ucn_p=*/true);
++ location_t loc;
++ bidi::kind kind = get_bidi_ucn (pfile, cur + 1, cur[0] == 'U',
++ &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
+ }
+ cur++;
+ }
+@@ -2476,8 +2630,9 @@ lex_string (cpp_reader *pfile, cpp_token
+ saw_NUL = true;
+ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
+ {
+- bidi::kind kind = get_bidi_utf8 (cur - 1);
+- maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false);
++ location_t loc;
++ bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+ }
+ }
+
Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bd5e882cf6e0def3dd1bc106075d59a303fe0d1e] Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=51c500269bf53749b107807d84271385fad35628] Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=1a7f2c0774129750fdf73e9f1b78f0ce983c9ab3] Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bef32d4a28595e933f24fef378cf052a30b674a7] Signed-off-by: pgowda <pgowda.cve@gmail.com> --- meta/recipes-devtools/gcc/gcc-11.2.inc | 4 + .../gcc/gcc/0001-CVE-2021-42574.patch | 2282 +++++++++++++++++ .../gcc/gcc/0002-CVE-2021-42574.patch | 1765 +++++++++++++ .../gcc/gcc/0003-CVE-2021-42574.patch | 142 + .../gcc/gcc/0004-CVE-2021-42574.patch | 573 +++++ 5 files changed, 4766 insertions(+) create mode 100644 meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch create mode 100644 meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch create mode 100644 meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch create mode 100644 meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch