diff options
Diffstat (limited to 'meta/recipes-devtools')
66 files changed, 11375 insertions, 2583 deletions
diff --git a/meta/recipes-devtools/binutils/binutils-2.36.inc b/meta/recipes-devtools/binutils/binutils-2.36.inc index 7d0824e060..fa28358c2d 100644 --- a/meta/recipes-devtools/binutils/binutils-2.36.inc +++ b/meta/recipes-devtools/binutils/binutils-2.36.inc @@ -24,7 +24,7 @@ BRANCH ?= "binutils-2_36-branch" UPSTREAM_CHECK_GITTAGREGEX = "binutils-(?P<pver>\d+_(\d_?)*)" -SRCREV ?= "7651a4871c225925ffdfda0a8c91a6ed370cd9a1" +SRCREV ?= "a281816c8aeb12619d34eec8959a43dfa5c6b4ec" BINUTILS_GIT_URI ?= "git://sourceware.org/git/binutils-gdb.git;branch=${BRANCH};protocol=git" SRC_URI = "\ ${BINUTILS_GIT_URI} \ @@ -41,10 +41,9 @@ SRC_URI = "\ file://0014-Fix-rpath-in-libtool-when-sysroot-is-enabled.patch \ file://0015-sync-with-OE-libtool-changes.patch \ file://0016-Check-for-clang-before-checking-gcc-version.patch \ - file://0001-CVE-2021-20197.patch \ - file://0002-CVE-2021-20197.patch \ - file://0003-CVE-2021-20197.patch \ file://0017-CVE-2021-3530.patch \ file://0018-CVE-2021-3530.patch \ + file://0001-CVE-2021-42574.patch \ + file://0001-CVE-2021-45078.patch \ " S = "${WORKDIR}/git" diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch deleted file mode 100644 index 2b4eaba26d..0000000000 --- a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-20197.patch +++ /dev/null @@ -1,201 +0,0 @@ -From 8e03235147a9e774d3ba084e93c2da1aa94d1cec Mon Sep 17 00:00:00 2001 -From: Siddhesh Poyarekar <siddhesh@gotplt.org> -Date: Mon, 22 Feb 2021 20:45:50 +0530 -Subject: [PATCH] binutils: Avoid renaming over existing files - -Renaming over existing files needs additional care to restore -permissions and ownership, which may not always succeed. -Additionally, other properties of the file such as extended attributes -may be lost, making the operation flaky. - -For predictable results, resort to rename() only if the file does not -exist, otherwise copy the file contents into the existing file. This -ensures that no additional tricks are needed to retain file -properties. - -This also allows dropping of the redundant set_times on the tmpfile in -objcopy/strip since now we no longer rename over existing files. - -binutils/ - - * ar.c (write_archive): Adjust call to SMART_RENAME. - * arsup.c (ar_save): Likewise. - * objcopy (strip_main): Don't set times on temporary file and - adjust call to SMART_RENAME. - (copy_main): Likewise. - * rename.c [!S_ISLNK]: Remove definitions. - (try_preserve_permissions): Remove function. - (smart_rename): Replace PRESERVE_DATES argument with - TARGET_STAT. Use rename system call only if TO does not exist. - * bucomm.h (smart_rename): Adjust declaration. - -(cherry picked from commit 3685de750e6a091663a0abe42528cad29e960e35) - -Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=8e03235147a9e774d3ba084e93c2da1aa94d1cec] -CVE: CVE-2021-20197 -Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com> ---- - binutils/ar.c | 2 +- - binutils/arsup.c | 2 +- - binutils/bucomm.h | 3 ++- - binutils/objcopy.c | 8 ++----- - binutils/rename.c | 55 +++++++++------------------------------------- - 6 files changed, 29 insertions(+), 54 deletions(-) - -diff --git a/binutils/ar.c b/binutils/ar.c -index 45a34e3a6cf..3a91708b51c 100644 ---- a/binutils/ar.c -+++ b/binutils/ar.c -@@ -1308,7 +1308,7 @@ write_archive (bfd *iarch) - /* We don't care if this fails; we might be creating the archive. */ - bfd_close (iarch); - -- if (smart_rename (new_name, old_name, 0) != 0) -+ if (smart_rename (new_name, old_name, NULL) != 0) - xexit (1); - free (old_name); - free (new_name); -diff --git a/binutils/arsup.c b/binutils/arsup.c -index 5403a0c5d74..0a1f63f6456 100644 ---- a/binutils/arsup.c -+++ b/binutils/arsup.c -@@ -351,7 +351,7 @@ ar_save (void) - - bfd_close (obfd); - -- smart_rename (ofilename, real_name, 0); -+ smart_rename (ofilename, real_name, NULL); - obfd = 0; - free (ofilename); - } -diff --git a/binutils/bucomm.h b/binutils/bucomm.h -index 91f6a5b228f..aa7e33d8cd1 100644 ---- a/binutils/bucomm.h -+++ b/binutils/bucomm.h -@@ -71,7 +71,8 @@ extern void print_version (const char *); - /* In rename.c. */ - extern void set_times (const char *, const struct stat *); - --extern int smart_rename (const char *, const char *, int); -+extern int smart_rename (const char *, const char *, struct stat *); -+ - - /* In libiberty. */ - void *xmalloc (size_t); -diff --git a/binutils/objcopy.c b/binutils/objcopy.c -index eab3b6db585..07a872b5a80 100644 ---- a/binutils/objcopy.c -+++ b/binutils/objcopy.c -@@ -4861,12 +4861,10 @@ strip_main (int argc, char *argv[]) - output_target, NULL); - if (status == 0) - { -- if (preserve_dates) -- set_times (tmpname, &statbuf); - if (output_file != tmpname) - status = (smart_rename (tmpname, - output_file ? output_file : argv[i], -- preserve_dates) != 0); -+ preserve_dates ? &statbuf : NULL) != 0); - if (status == 0) - status = hold_status; - } -@@ -5931,11 +5929,9 @@ copy_main (int argc, char *argv[]) - output_target, input_arch); - if (status == 0) - { -- if (preserve_dates) -- set_times (tmpname, &statbuf); - if (tmpname != output_filename) - status = (smart_rename (tmpname, input_filename, -- preserve_dates) != 0); -+ preserve_dates ? &statbuf : NULL) != 0); - } - else - unlink_if_ordinary (tmpname); -diff --git a/binutils/rename.c b/binutils/rename.c -index 65ad5bf52c4..f471b45fd3f 100644 ---- a/binutils/rename.c -+++ b/binutils/rename.c -@@ -122,20 +122,13 @@ set_times (const char *destination, const struct stat *statbuf) - non_fatal (_("%s: cannot set time: %s"), destination, strerror (errno)); - } - --#ifndef S_ISLNK --#ifdef S_IFLNK --#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK) --#else --#define S_ISLNK(m) 0 --#define lstat stat --#endif --#endif -- --/* Rename FROM to TO, copying if TO is a link. -- Return 0 if ok, -1 if error. */ -+/* Rename FROM to TO, copying if TO exists. TARGET_STAT has the file status -+ that, if non-NULL, is used to fix up timestamps after rename. Return 0 if -+ ok, -1 if error. */ - - int --smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNUSED) -+smart_rename (const char *from, const char *to, -+ struct stat *target_stat ATTRIBUTE_UNUSED) - { - bfd_boolean exists; - struct stat s; -@@ -158,38 +151,10 @@ smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNU - unlink (from); - } - #else -- /* Use rename only if TO is not a symbolic link and has -- only one hard link, and we have permission to write to it. */ -- if (! exists -- || (!S_ISLNK (s.st_mode) -- && S_ISREG (s.st_mode) -- && (s.st_mode & S_IWUSR) -- && s.st_nlink == 1) -- ) -+ /* Avoid a full copy and use rename if TO does not exist. */ -+ if (!exists) - { -- ret = rename (from, to); -- if (ret == 0) -- { -- if (exists) -- { -- /* Try to preserve the permission bits and ownership of -- TO. First get the mode right except for the setuid -- bit. Then change the ownership. Then fix the setuid -- bit. We do the chmod before the chown because if the -- chown succeeds, and we are a normal user, we won't be -- able to do the chmod afterward. We don't bother to -- fix the setuid bit first because that might introduce -- a fleeting security problem, and because the chown -- will clear the setuid bit anyhow. We only fix the -- setuid bit if the chown succeeds, because we don't -- want to introduce an unexpected setuid file owned by -- the user running objcopy. */ -- chmod (to, s.st_mode & 0777); -- if (chown (to, s.st_uid, s.st_gid) >= 0) -- chmod (to, s.st_mode & 07777); -- } -- } -- else -+ if ((ret = rename (from, to)) != 0) - { - /* We have to clean up here. */ - non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno)); -@@ -202,8 +167,8 @@ smart_rename (const char *from, const char *to, int preserve_dates ATTRIBUTE_UNU - if (ret != 0) - non_fatal (_("unable to copy file '%s'; reason: %s"), to, strerror (errno)); - -- if (preserve_dates) -- set_times (to, &s); -+ if (target_stat != NULL) -+ set_times (to, target_stat); - unlink (from); - } - #endif /* _WIN32 && !__CYGWIN32__ */ --- -2.31.1 - diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch new file mode 100644 index 0000000000..6adc438b5c --- /dev/null +++ b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-42574.patch @@ -0,0 +1,2006 @@ +From b3aa80b45c4f46029efeb204bb9f2d2c4278a0e5 Mon Sep 17 00:00:00 2001 +From: Nick Clifton <nickc@redhat.com> +Date: Tue, 9 Nov 2021 13:25:42 +0000 +Subject: [PATCH] Add --unicode option to control how unicode characters are + handled by display tools. + + * nm.c: Add --unicode option to control how unicode characters are + handled. + * objdump.c: Likewise. + * readelf.c: Likewise. + * strings.c: Likewise. + * binutils.texi: Document the new feature. + * NEWS: Document the new feature. + * testsuite/binutils-all/unicode.exp: New file. + * testsuite/binutils-all/nm.hex.unicode + * testsuite/binutils-all/strings.escape.unicode + * testsuite/binutils-all/objdump.highlight.unicode + * testsuite/binutils-all/readelf.invalid.unicode + +CVE: CVE-2021-42574 +Upstream-Status: Backport [https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=b3aa80b45c4f46029efeb204bb9f2d2c4278a0e5] + +Signed-off-by: pgowda <pgowda.cve@gmail.com> +--- + binutils/ChangeLog | 15 + + binutils/NEWS | 9 + + binutils/doc/binutils.texi | 78 ++++ + binutils/nm.c | 228 ++++++++++- + binutils/objdump.c | 235 ++++++++++-- + binutils/readelf.c | 190 +++++++++- + binutils/strings.c | 757 ++++++++++++++++++++++++++++++++++--- + 7 files changed, 1409 insertions(+), 103 deletions(-) + +diff --git a/binutils/ChangeLog b/binutils/ChangeLog +--- a/binutils/ChangeLog 2021-12-23 03:23:38.425843662 -0800 ++++ b/binutils/ChangeLog 2021-12-23 03:30:31.094968942 -0800 +@@ -1,3 +1,18 @@ ++2021-11-09 Nick Clifton <nickc@redhat.com> ++ ++ * nm.c: Add --unicode option to control how unicode characters are ++ handled. ++ * objdump.c: Likewise. ++ * readelf.c: Likewise. ++ * strings.c: Likewise. ++ * binutils.texi: Document the new feature. ++ * NEWS: Document the new feature. ++ * testsuite/binutils-all/unicode.exp: New file. ++ * testsuite/binutils-all/nm.hex.unicode ++ * testsuite/binutils-all/strings.escape.unicode ++ * testsuite/binutils-all/objdump.highlight.unicode ++ * testsuite/binutils-all/readelf.invalid.unicode ++ + 2021-04-15 Alan Modra <amodra@gmail.com> + + PR 27456 +diff --git a/binutils/doc/binutils.texi b/binutils/doc/binutils.texi +--- a/binutils/doc/binutils.texi 2021-12-23 03:23:38.441843395 -0800 ++++ b/binutils/doc/binutils.texi 2021-12-23 03:30:31.094968942 -0800 +@@ -805,6 +805,7 @@ nm [@option{-A}|@option{-o}|@option{--pr + [@option{-s}|@option{--print-armap}] [@option{-t} @var{radix}|@option{--radix=}@var{radix}] + [@option{-u}|@option{--undefined-only}] [@option{-V}|@option{--version}] + [@option{-X 32_64}] [@option{--defined-only}] [@option{--no-demangle}] ++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}] + [@option{--plugin} @var{name}] + [@option{--no-recurse-limit}|@option{--recurse-limit}]] + [@option{--size-sort}] [@option{--special-syms}] +@@ -1114,6 +1115,21 @@ Use @var{radix} as the radix for printin + @cindex undefined symbols + Display only undefined symbols (those external to each object file). + ++@item -U @var{[d|i|l|e|x|h]} ++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]} ++Controls the display of UTF-8 encoded mulibyte characters in strings. ++The default (@option{--unicode=default}) is to give them no special ++treatment. The @option{--unicode=locale} option displays the sequence ++in the current locale, which may or may not support them. The options ++@option{--unicode=hex} and @option{--unicode=invalid} display them as ++hex byte sequences enclosed by either angle brackets or curly braces. ++ ++The @option{--unicode=escape} option displays them as escape sequences ++(@var{\uxxxx}) and the @option{--unicode=highlight} option displays ++them as escape sequences highlighted in red (if supported by the ++output device). The colouring is intended to draw attention to the ++presence of unicode sequences where they might not be expected. ++ + @item -V + @itemx --version + Show the version number of @command{nm} and exit. +@@ -2210,6 +2226,7 @@ objdump [@option{-a}|@option{--archive-h + [@option{--prefix-strip=}@var{level}] + [@option{--insn-width=}@var{width}] + [@option{--visualize-jumps[=color|=extended-color|=off]} ++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}] + [@option{-V}|@option{--version}] + [@option{-H}|@option{--help}] + @var{objfile}@dots{} +@@ -2877,6 +2894,21 @@ When displaying symbols include those wh + special in some way and which would not normally be of interest to the + user. + ++@item -U @var{[d|i|l|e|x|h]} ++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]} ++Controls the display of UTF-8 encoded mulibyte characters in strings. ++The default (@option{--unicode=default}) is to give them no special ++treatment. The @option{--unicode=locale} option displays the sequence ++in the current locale, which may or may not support them. The options ++@option{--unicode=hex} and @option{--unicode=invalid} display them as ++hex byte sequences enclosed by either angle brackets or curly braces. ++ ++The @option{--unicode=escape} option displays them as escape sequences ++(@var{\uxxxx}) and the @option{--unicode=highlight} option displays ++them as escape sequences highlighted in red (if supported by the ++output device). The colouring is intended to draw attention to the ++presence of unicode sequences where they might not be expected. ++ + @item -V + @itemx --version + Print the version number of @command{objdump} and exit. +@@ -3153,6 +3185,7 @@ strings [@option{-afovV}] [@option{-}@va + [@option{-n} @var{min-len}] [@option{--bytes=}@var{min-len}] + [@option{-t} @var{radix}] [@option{--radix=}@var{radix}] + [@option{-e} @var{encoding}] [@option{--encoding=}@var{encoding}] ++ [@option{-U} @var{method}] [@option{--unicode=}@var{method}] + [@option{-}] [@option{--all}] [@option{--print-file-name}] + [@option{-T} @var{bfdname}] [@option{--target=}@var{bfdname}] + [@option{-w}] [@option{--include-all-whitespace}] +@@ -3244,6 +3277,28 @@ single-8-bit-byte characters, @samp{b} = + littleendian. Useful for finding wide character strings. (@samp{l} + and @samp{b} apply to, for example, Unicode UTF-16/UCS-2 encodings). + ++@item -U @var{[d|i|l|e|x|h]} ++@itemx --unicode=@var{[default|invalid|locale|escape|hex|highlight]} ++Controls the display of UTF-8 encoded mulibyte characters in strings. ++The default (@option{--unicode=default}) is to give them no special ++treatment, and instead rely upon the setting of the ++@option{--encoding} option. The other values for this option ++automatically enable @option{--encoding=S}. ++ ++The @option{--unicode=invalid} option treats them as non-graphic ++characters and hence not part of a valid string. All the remaining ++options treat them as valid string characters. ++ ++The @option{--unicode=locale} option displays them in the current ++locale, which may or may not support UTF-8 encoding. The ++@option{--unicode=hex} option displays them as hex byte sequences ++enclosed between @var{<>} characters. The @option{--unicode=escape} ++option displays them as escape sequences (@var{\uxxxx}) and the ++@option{--unicode=highlight} option displays them as escape sequences ++highlighted in red (if supported by the output device). The colouring ++is intended to draw attention to the presence of unicode sequences ++where they might not be expected. ++ + @item -T @var{bfdname} + @itemx --target=@var{bfdname} + @cindex object code format +@@ -4740,6 +4795,7 @@ readelf [@option{-a}|@option{--all}] + [@option{--dyn-syms}|@option{--lto-syms}] + [@option{--demangle@var{=style}}|@option{--no-demangle}] + [@option{--recurse-limit}|@option{--no-recurse-limit}] ++ [@option{-U} @var{method}|@option{--unicode=}@var{method}] + [@option{-n}|@option{--notes}] + [@option{-r}|@option{--relocs}] + [@option{-u}|@option{--unwind}] +@@ -4887,6 +4943,28 @@ necessary in order to demangle truly com + that if the recursion limit is disabled then stack exhaustion is + possible and any bug reports about such an event will be rejected. + ++@item -U @var{[d|i|l|e|x|h]} ++@itemx --unicode=[default|invalid|locale|escape|hex|highlight] ++Controls the display of non-ASCII characters in identifier names. ++The default (@option{--unicode=locale} or @option{--unicode=default}) is ++to treat them as multibyte characters and display them in the current ++locale. All other versions of this option treat the bytes as UTF-8 ++encoded values and attempt to interpret them. If they cannot be ++interpreted or if the @option{--unicode=invalid} option is used then ++they are displayed as a sequence of hex bytes, encloses in curly ++parethesis characters. ++ ++Using the @option{--unicode=escape} option will display the characters ++as as unicode escape sequences (@var{\uxxxx}). Using the ++@option{--unicode=hex} will display the characters as hex byte ++sequences enclosed between angle brackets. ++ ++Using the @option{--unicode=highlight} will display the characters as ++unicode escape sequences but it will also highlighted them in red, ++assuming that colouring is supported by the output device. The ++colouring is intended to draw attention to the presence of unicode ++sequences when they might not be expected. ++ + @item -e + @itemx --headers + Display all the headers in the file. Equivalent to @option{-h -l -S}. +diff --git a/binutils/NEWS b/binutils/NEWS +--- a/binutils/NEWS 2021-12-23 03:23:38.433843528 -0800 ++++ b/binutils/NEWS 2021-12-23 03:30:31.094968942 -0800 +@@ -1,5 +1,14 @@ + -*- text -*- + ++* Tools which display symbols or strings (readelf, strings, nm, objdump) ++ have a new command line option which controls how unicode characters are ++ handled. By default they are treated as normal for the tool. Using ++ --unicode=locale will display them according to the current locale. ++ Using --unicode=hex will display them as hex byte values, whilst ++ --unicode=escape will display them as escape sequences. In addition ++ using --unicode=highlight will display them as unicode escape sequences ++ highlighted in red (if supported by the output device). ++ + Changes in 2.36: + + * Update elfedit and readelf with LAM_U48 and LAM_U57 support. +diff --git a/binutils/nm.c b/binutils/nm.c +--- a/binutils/nm.c 2021-12-23 03:23:38.441843395 -0800 ++++ b/binutils/nm.c 2021-12-23 03:30:31.098968875 -0800 +@@ -38,6 +38,11 @@ + #include "bucomm.h" + #include "plugin-api.h" + #include "plugin.h" ++#include "safe-ctype.h" ++ ++#ifndef streq ++#define streq(a,b) (strcmp ((a),(b)) == 0) ++#endif + + /* When sorting by size, we use this structure to hold the size and a + pointer to the minisymbol. */ +@@ -192,6 +197,18 @@ static const char *plugin_target = NULL; + static bfd *lineno_cache_bfd; + static bfd *lineno_cache_rel_bfd; + ++typedef enum unicode_display_type ++{ ++ unicode_default = 0, ++ unicode_locale, ++ unicode_escape, ++ unicode_hex, ++ unicode_highlight, ++ unicode_invalid ++} unicode_display_type; ++ ++static unicode_display_type unicode_display = unicode_default; ++ + enum long_option_values + { + OPTION_TARGET = 200, +@@ -234,6 +251,7 @@ static struct option long_options[] = + {"target", required_argument, 0, OPTION_TARGET}, + {"defined-only", no_argument, &defined_only, 1}, + {"undefined-only", no_argument, &undefined_only, 1}, ++ {"unicode", required_argument, NULL, 'U'}, + {"version", no_argument, &show_version, 1}, + {"with-symbol-versions", no_argument, NULL, + OPTION_WITH_SYMBOL_VERSIONS}, +@@ -285,6 +303,8 @@ usage (FILE *stream, int status) + -t, --radix=RADIX Use RADIX for printing symbol values\n\ + --target=BFDNAME Specify the target object format as BFDNAME\n\ + -u, --undefined-only Display only undefined symbols\n\ ++ -U {d|s|i|x|e|h} Specify how to treat UTF-8 encoded unicode characters\n\ ++ --unicode={default|show|invalid|hex|escape|highlight}\n\ + --with-symbol-versions Display version strings after symbol names\n\ + -X 32_64 (ignored)\n\ + @FILE Read options from FILE\n\ +@@ -399,6 +419,188 @@ get_coff_symbol_type (const struct inter + fatal ("%s", xstrerror (errno)); + return bufp; + } ++ ++/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT. ++ The conversion format is controlled by the unicode_display variable. ++ Returns the number of characters added to OUT. ++ Returns the number of bytes consumed from IN in CONSUMED. ++ Always consumes at least one byte and displays at least one character. */ ++ ++static unsigned int ++display_utf8 (const unsigned char * in, char * out, unsigned int * consumed) ++{ ++ char * orig_out = out; ++ unsigned int nchars = 0; ++ unsigned int j; ++ ++ if (unicode_display == unicode_default) ++ goto invalid; ++ ++ if (in[0] < 0xc0) ++ goto invalid; ++ ++ if ((in[1] & 0xc0) != 0x80) ++ goto invalid; ++ ++ if ((in[0] & 0x20) == 0) ++ { ++ nchars = 2; ++ goto valid; ++ } ++ ++ if ((in[2] & 0xc0) != 0x80) ++ goto invalid; ++ ++ if ((in[0] & 0x10) == 0) ++ { ++ nchars = 3; ++ goto valid; ++ } ++ ++ if ((in[3] & 0xc0) != 0x80) ++ goto invalid; ++ ++ nchars = 4; ++ ++ valid: ++ switch (unicode_display) ++ { ++ case unicode_locale: ++ /* Copy the bytes into the output buffer as is. */ ++ memcpy (out, in, nchars); ++ out += nchars; ++ break; ++ ++ case unicode_invalid: ++ case unicode_hex: ++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{'); ++ out += sprintf (out, "0x"); ++ for (j = 0; j < nchars; j++) ++ out += sprintf (out, "%02x", in [j]); ++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}'); ++ break; ++ ++ case unicode_highlight: ++ if (isatty (1)) ++ out += sprintf (out, "\x1B[31;47m"); /* Red. */ ++ /* Fall through. */ ++ case unicode_escape: ++ switch (nchars) ++ { ++ case 2: ++ out += sprintf (out, "\\u%02x%02x", ++ ((in[0] & 0x1c) >> 2), ++ ((in[0] & 0x03) << 6) | (in[1] & 0x3f)); ++ break; ++ ++ case 3: ++ out += sprintf (out, "\\u%02x%02x", ++ ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2), ++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3f))); ++ break; ++ ++ case 4: ++ out += sprintf (out, "\\u%02x%02x%02x", ++ ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2), ++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2), ++ ((in[2] & 0x03) << 6) | ((in[3] & 0x3f))); ++ break; ++ default: ++ /* URG. */ ++ break; ++ } ++ ++ if (unicode_display == unicode_highlight && isatty (1)) ++ out += sprintf (out, "\033[0m"); /* Default colour. */ ++ break; ++ ++ default: ++ /* URG */ ++ break; ++ } ++ ++ * consumed = nchars; ++ return out - orig_out; ++ ++ invalid: ++ /* Not a valid UTF-8 sequence. */ ++ *out = *in; ++ * consumed = 1; ++ return 1; ++} ++ ++/* Convert any UTF-8 encoded characters in NAME into the form specified by ++ unicode_display. Also converts control characters. Returns a static ++ buffer if conversion was necessary. ++ Code stolen from objdump.c:sanitize_string(). */ ++ ++static const char * ++convert_utf8 (const char * in) ++{ ++ static char * buffer = NULL; ++ static size_t buffer_len = 0; ++ const char * original = in; ++ char * out; ++ ++ /* Paranoia. */ ++ if (in == NULL) ++ return ""; ++ ++ /* See if any conversion is necessary. ++ In the majority of cases it will not be needed. */ ++ do ++ { ++ unsigned char c = *in++; ++ ++ if (c == 0) ++ return original; ++ ++ if (ISCNTRL (c)) ++ break; ++ ++ if (unicode_display != unicode_default && c >= 0xc0) ++ break; ++ } ++ while (1); ++ ++ /* Copy the input, translating as needed. */ ++ in = original; ++ if (buffer_len < (strlen (in) * 9)) ++ { ++ free ((void *) buffer); ++ buffer_len = strlen (in) * 9; ++ buffer = xmalloc (buffer_len + 1); ++ } ++ ++ out = buffer; ++ do ++ { ++ unsigned char c = *in++; ++ ++ if (c == 0) ++ break; ++ ++ if (ISCNTRL (c)) ++ { ++ *out++ = '^'; ++ *out++ = c + 0x40; ++ } ++ else if (unicode_display != unicode_default && c >= 0xc0) ++ { ++ unsigned int num_consumed; ++ ++ out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed); ++ in += num_consumed - 1; ++ } ++ else ++ *out++ = c; ++ } ++ while (1); ++ ++ *out = 0; ++ return buffer; ++} ++ + + /* Print symbol name NAME, read from ABFD, with printf format FORM, + demangling it if requested. */ +@@ -418,6 +620,11 @@ print_symname (const char *form, struct + name = alloc; + } + ++ if (unicode_display != unicode_default) ++ { ++ name = convert_utf8 (name); ++ } ++ + if (info != NULL && info->elfinfo) + { + const char *version_string; +@@ -1738,7 +1945,7 @@ main (int argc, char **argv) + fatal (_("fatal error: libbfd ABI mismatch")); + set_default_bfd_target (); + +- while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uvVvX:", ++ while ((c = getopt_long (argc, argv, "aABCDef:gHhlnopPrSst:uU:vVvX:", + long_options, (int *) 0)) != EOF) + { + switch (c) +@@ -1828,6 +2035,24 @@ main (int argc, char **argv) + case 'u': + undefined_only = 1; + break; ++ ++ case 'U': ++ if (streq (optarg, "default") || streq (optarg, "d")) ++ unicode_display = unicode_default; ++ else if (streq (optarg, "locale") || streq (optarg, "l")) ++ unicode_display = unicode_locale; ++ else if (streq (optarg, "escape") || streq (optarg, "e")) ++ unicode_display = unicode_escape; ++ else if (streq (optarg, "invalid") || streq (optarg, "i")) ++ unicode_display = unicode_invalid; ++ else if (streq (optarg, "hex") || streq (optarg, "x")) ++ unicode_display = unicode_hex; ++ else if (streq (optarg, "highlight") || streq (optarg, "h")) ++ unicode_display = unicode_highlight; ++ else ++ fatal (_("invalid argument to -U/--unicode: %s"), optarg); ++ break; ++ + case 'V': + show_version = 1; + break; +diff --git a/binutils/objdump.c b/binutils/objdump.c +--- a/binutils/objdump.c 2021-12-23 03:23:38.445843329 -0800 ++++ b/binutils/objdump.c 2021-12-23 03:30:31.098968875 -0800 +@@ -205,6 +205,19 @@ static const struct objdump_private_desc + + /* The list of detected jumps inside a function. */ + static struct jump_info *detected_jumps = NULL; ++ ++typedef enum unicode_display_type ++{ ++ unicode_default = 0, ++ unicode_locale, ++ unicode_escape, ++ unicode_hex, ++ unicode_highlight, ++ unicode_invalid ++} unicode_display_type; ++ ++static unicode_display_type unicode_display = unicode_default; ++ + + static void usage (FILE *, int) ATTRIBUTE_NORETURN; + static void +@@ -274,6 +287,8 @@ usage (FILE *stream, int status) + --recurse-limit Enable a limit on recursion whilst demangling. [Default]\n\ + --no-recurse-limit Disable a limit on recursion whilst demangling\n\ + -w, --wide Format output for more than 80 columns\n\ ++ -U[d|l|i|x|e|h] Controls the display of UTF-8 unicode characters\n\ ++ --unicode=[default|locale|invalid|hex|escape|highlight]\n\ + -z, --disassemble-zeroes Do not skip blocks of zeroes when disassembling\n\ + --start-address=ADDR Only process data whose address is >= ADDR\n\ + --stop-address=ADDR Only process data whose address is < ADDR\n\ +@@ -348,17 +363,23 @@ static struct option long_options[]= + { + {"adjust-vma", required_argument, NULL, OPTION_ADJUST_VMA}, + {"all-headers", no_argument, NULL, 'x'}, +- {"private-headers", no_argument, NULL, 'p'}, +- {"private", required_argument, NULL, 'P'}, + {"architecture", required_argument, NULL, 'm'}, + {"archive-headers", no_argument, NULL, 'a'}, ++#ifdef ENABLE_LIBCTF ++ {"ctf", required_argument, NULL, OPTION_CTF}, ++ {"ctf-parent", required_argument, NULL, OPTION_CTF_PARENT}, ++#endif + {"debugging", no_argument, NULL, 'g'}, + {"debugging-tags", no_argument, NULL, 'e'}, + {"demangle", optional_argument, NULL, 'C'}, + {"disassemble", optional_argument, NULL, 'd'}, + {"disassemble-all", no_argument, NULL, 'D'}, +- {"disassembler-options", required_argument, NULL, 'M'}, + {"disassemble-zeroes", no_argument, NULL, 'z'}, ++ {"disassembler-options", required_argument, NULL, 'M'}, ++ {"dwarf", optional_argument, NULL, OPTION_DWARF}, ++ {"dwarf-check", no_argument, 0, OPTION_DWARF_CHECK}, ++ {"dwarf-depth", required_argument, 0, OPTION_DWARF_DEPTH}, ++ {"dwarf-start", required_argument, 0, OPTION_DWARF_START}, + {"dynamic-reloc", no_argument, NULL, 'R'}, + {"dynamic-syms", no_argument, NULL, 'T'}, + {"endian", required_argument, NULL, OPTION_ENDIAN}, +@@ -368,15 +389,22 @@ static struct option long_options[]= + {"full-contents", no_argument, NULL, 's'}, + {"headers", no_argument, NULL, 'h'}, + {"help", no_argument, NULL, 'H'}, ++ {"include", required_argument, NULL, 'I'}, + {"info", no_argument, NULL, 'i'}, ++ {"inlines", no_argument, 0, OPTION_INLINES}, ++ {"insn-width", required_argument, NULL, OPTION_INSN_WIDTH}, + {"line-numbers", no_argument, NULL, 'l'}, +- {"no-show-raw-insn", no_argument, &show_raw_insn, -1}, + {"no-addresses", no_argument, &no_addresses, 1}, ++ {"no-recurse-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT}, ++ {"no-recursion-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT}, ++ {"no-show-raw-insn", no_argument, &show_raw_insn, -1}, ++ {"prefix", required_argument, NULL, OPTION_PREFIX}, + {"prefix-addresses", no_argument, &prefix_addresses, 1}, ++ {"prefix-strip", required_argument, NULL, OPTION_PREFIX_STRIP}, ++ {"private", required_argument, NULL, 'P'}, ++ {"private-headers", no_argument, NULL, 'p'}, + {"recurse-limit", no_argument, NULL, OPTION_RECURSE_LIMIT}, + {"recursion-limit", no_argument, NULL, OPTION_RECURSE_LIMIT}, +- {"no-recurse-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT}, +- {"no-recursion-limit", no_argument, NULL, OPTION_NO_RECURSE_LIMIT}, + {"reloc", no_argument, NULL, 'r'}, + {"section", required_argument, NULL, 'j'}, + {"section-headers", no_argument, NULL, 'h'}, +@@ -384,28 +412,16 @@ static struct option long_options[]= + {"source", no_argument, NULL, 'S'}, + {"source-comment", optional_argument, NULL, OPTION_SOURCE_COMMENT}, + {"special-syms", no_argument, &dump_special_syms, 1}, +- {"include", required_argument, NULL, 'I'}, +- {"dwarf", optional_argument, NULL, OPTION_DWARF}, +-#ifdef ENABLE_LIBCTF +- {"ctf", required_argument, NULL, OPTION_CTF}, +- {"ctf-parent", required_argument, NULL, OPTION_CTF_PARENT}, +-#endif + {"stabs", no_argument, NULL, 'G'}, + {"start-address", required_argument, NULL, OPTION_START_ADDRESS}, + {"stop-address", required_argument, NULL, OPTION_STOP_ADDRESS}, + {"syms", no_argument, NULL, 't'}, + {"target", required_argument, NULL, 'b'}, ++ {"unicode", required_argument, NULL, 'U'}, + {"version", no_argument, NULL, 'V'}, +- {"wide", no_argument, NULL, 'w'}, +- {"prefix", required_argument, NULL, OPTION_PREFIX}, +- {"prefix-strip", required_argument, NULL, OPTION_PREFIX_STRIP}, +- {"insn-width", required_argument, NULL, OPTION_INSN_WIDTH}, +- {"dwarf-depth", required_argument, 0, OPTION_DWARF_DEPTH}, +- {"dwarf-start", required_argument, 0, OPTION_DWARF_START}, +- {"dwarf-check", no_argument, 0, OPTION_DWARF_CHECK}, +- {"inlines", no_argument, 0, OPTION_INLINES}, + {"visualize-jumps", optional_argument, 0, OPTION_VISUALIZE_JUMPS}, +- {0, no_argument, 0, 0} ++ {"wide", no_argument, NULL, 'w'}, ++ {NULL, no_argument, NULL, 0} + }; + + static void +@@ -415,9 +431,121 @@ nonfatal (const char *msg) + exit_status = 1; + } + ++/* Convert a potential UTF-8 encoded sequence in IN into characters in OUT. ++ The conversion format is controlled by the unicode_display variable. ++ Returns the number of characters added to OUT. ++ Returns the number of bytes consumed from IN in CONSUMED. ++ Always consumes at least one byte and displays at least one character. */ ++ ++static unsigned int ++display_utf8 (const unsigned char * in, char * out, unsigned int * consumed) ++{ ++ char * orig_out = out; ++ unsigned int nchars = 0; ++ unsigned int j; ++ ++ if (unicode_display == unicode_default) ++ goto invalid; ++ ++ if (in[0] < 0xc0) ++ goto invalid; ++ ++ if ((in[1] & 0xc0) != 0x80) ++ goto invalid; ++ ++ if ((in[0] & 0x20) == 0) ++ { ++ nchars = 2; ++ goto valid; ++ } ++ ++ if ((in[2] & 0xc0) != 0x80) ++ goto invalid; ++ ++ if ((in[0] & 0x10) == 0) ++ { ++ nchars = 3; ++ goto valid; ++ } ++ ++ if ((in[3] & 0xc0) != 0x80) ++ goto invalid; ++ ++ nchars = 4; ++ ++ valid: ++ switch (unicode_display) ++ { ++ case unicode_locale: ++ /* Copy the bytes into the output buffer as is. */ ++ memcpy (out, in, nchars); ++ out += nchars; ++ break; ++ ++ case unicode_invalid: ++ case unicode_hex: ++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '<' : '{'); ++ out += sprintf (out, "0x"); ++ for (j = 0; j < nchars; j++) ++ out += sprintf (out, "%02x", in [j]); ++ out += sprintf (out, "%c", unicode_display == unicode_hex ? '>' : '}'); ++ break; ++ ++ case unicode_highlight: ++ if (isatty (1)) ++ out += sprintf (out, "\x1B[31;47m"); /* Red. */ ++ /* Fall through. */ ++ case unicode_escape: ++ switch (nchars) ++ { ++ case 2: ++ out += sprintf (out, "\\u%02x%02x", ++ ((in[0] & 0x1c) >> 2), ++ ((in[0] & 0x03) << 6) | (in[1] & 0x3f)); ++ break; ++ ++ case 3: ++ out += sprintf (out, "\\u%02x%02x", ++ ((in[0] & 0x0f) << 4) | ((in[1] & 0x3c) >> 2), ++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3f))); ++ break; ++ ++ case 4: ++ out += sprintf (out, "\\u%02x%02x%02x", ++ ((in[0] & 0x07) << 6) | ((in[1] & 0x3c) >> 2), ++ ((in[1] & 0x03) << 6) | ((in[2] & 0x3c) >> 2), ++ ((in[2] & 0x03) << 6) | ((in[3] & 0x3f))); ++ break; ++ default: ++ /* URG. */ ++ break; ++ } ++ ++ if (unicode_display == unicode_highlight && isatty (1)) ++ out += sprintf (out, "\033[0m"); /* Default colour. */ ++ break; ++ ++ default: ++ /* URG */ ++ break; ++ } ++ ++ * consumed = nchars; ++ return out - orig_out; ++ ++ invalid: ++ /* Not a valid UTF-8 sequence. */ ++ *out = *in; ++ * consumed = 1; ++ return 1; ++} ++ + /* Returns a version of IN with any control characters + replaced by escape sequences. Uses a static buffer +- if necessary. */ ++ if necessary. ++ ++ If unicode display is enabled, then also handles the ++ conversion of unicode characters. */ + + static const char * + sanitize_string (const char * in) +@@ -435,40 +563,50 @@ sanitize_string (const char * in) + of cases it will not be needed. */ + do + { +- char c = *in++; ++ unsigned char c = *in++; + + if (c == 0) + return original; + + if (ISCNTRL (c)) + break; ++ ++ if (unicode_display != unicode_default && c >= 0xc0) ++ break; + } + while (1); + + /* Copy the input, translating as needed. */ + in = original; +- if (buffer_len < (strlen (in) * 2)) ++ if (buffer_len < (strlen (in) * 9)) + { + free ((void *) buffer); +- buffer_len = strlen (in) * 2; ++ buffer_len = strlen (in) * 9; + buffer = xmalloc (buffer_len + 1); + } + + out = buffer; + do + { +- char c = *in++; ++ unsigned char c = *in++; + + if (c == 0) + break; + +- if (!ISCNTRL (c)) +- *out++ = c; +- else ++ if (ISCNTRL (c)) + { + *out++ = '^'; + *out++ = c + 0x40; + } ++ else if (unicode_display != unicode_default && c >= 0xc0) ++ { ++ unsigned int num_consumed; ++ ++ out += display_utf8 ((const unsigned char *)(in - 1), out, & num_consumed); ++ in += num_consumed - 1; ++ } ++ else ++ *out++ = c; + } + while (1); + +@@ -4481,6 +4619,24 @@ dump_symbols (bfd *abfd ATTRIBUTE_UNUSED + free (alloc); + } + } ++ else if (unicode_display != unicode_default ++ && name != NULL && *name != '\0') ++ { ++ const char * sanitized_name; ++ ++ /* If we want to sanitize the name, we do it here, and ++ temporarily clobber it while calling bfd_print_symbol. ++ FIXME: This is a gross hack. */ ++ sanitized_name = sanitize_string (name); ++ if (sanitized_name != name) ++ (*current)->name = sanitized_name; ++ else ++ sanitized_name = NULL; ++ bfd_print_symbol (cur_bfd, stdout, *current, ++ bfd_print_symbol_all); ++ if (sanitized_name != NULL) ++ (*current)->name = name; ++ } + else + bfd_print_symbol (cur_bfd, stdout, *current, + bfd_print_symbol_all); +@@ -5162,7 +5318,7 @@ main (int argc, char **argv) + set_default_bfd_target (); + + while ((c = getopt_long (argc, argv, +- "pP:ib:m:M:VvCdDlfFaHhrRtTxsSI:j:wE:zgeGW::", ++ "pP:ib:m:U:M:VvCdDlfFaHhrRtTxsSI:j:wE:zgeGW::", + long_options, (int *) 0)) + != EOF) + { +@@ -5441,6 +5597,23 @@ main (int argc, char **argv) + seenflag = TRUE; + break; + ++ case 'U': ++ if (streq (optarg, "default") || streq (optarg, "d")) ++ unicode_display = unicode_default; ++ else if (streq (optarg, "locale") || streq (optarg, "l")) ++ unicode_display = unicode_locale; ++ else if (streq (optarg, "escape") || streq (optarg, "e")) ++ unicode_display = unicode_escape; ++ else if (streq (optarg, "invalid") || streq (optarg, "i")) ++ unicode_display = unicode_invalid; ++ else if (streq (optarg, "hex") || streq (optarg, "x")) ++ unicode_display = unicode_hex; ++ else if (streq (optarg, "highlight") || streq (optarg, "h")) ++ unicode_display = unicode_highlight; ++ else ++ fatal (_("invalid argument to -U/--unicode: %s"), optarg); ++ break; ++ + case 'H': + usage (stdout, 0); + /* No need to set seenflag or to break - usage() does not return. */ +diff --git a/binutils/readelf.c b/binutils/readelf.c +--- a/binutils/readelf.c 2021-12-23 03:23:42.065783023 -0800 ++++ b/binutils/readelf.c 2021-12-23 03:30:36.582877519 -0800 +@@ -321,6 +321,19 @@ typedef enum print_mode + } + print_mode; + ++typedef enum unicode_display_type ++{ ++ unicode_default = 0, ++ unicode_locale, ++ unicode_escape, ++ unicode_hex, ++ unicode_highlight, ++ unicode_invalid ++} unicode_display_type; ++ ++static unicode_display_type unicode_display = unicode_default; ++ ++ + /* Versioned symbol info. */ + enum versioned_symbol_info + { +@@ -613,11 +626,18 @@ print_symbol (signed int width, const ch + if (c == 0) + break; + +- /* Do not print control characters directly as they can affect terminal +- settings. Such characters usually appear in the names generated +- by the assembler for local labels. */ +- if (ISCNTRL (c)) ++ if (ISPRINT (c)) ++ { ++ putchar (c); ++ width_remaining --; ++ num_printed ++; ++ } ++ else if (ISCNTRL (c)) + { ++ /* Do not print control characters directly as they can affect terminal ++ settings. Such characters usually appear in the names generated ++ by the assembler for local labels. */ ++ + if (width_remaining < 2) + break; + +@@ -625,11 +645,137 @@ print_symbol (signed int width, const ch + width_remaining -= 2; + num_printed += 2; + } +- else if (ISPRINT (c)) ++ else if (c == 0x7f) + { +- putchar (c); +- width_remaining --; +- num_printed ++; ++ if (width_remaining < 5) ++ break; ++ printf ("<DEL>"); ++ width_remaining -= 5; ++ num_printed += 5; ++ } ++ else if (unicode_display != unicode_locale ++ && unicode_display != unicode_default) ++ { ++ /* Display unicode characters as something else. */ ++ unsigned char bytes[4]; ++ bfd_boolean is_utf8; ++ unsigned int nbytes; ++ ++ bytes[0] = c; ++ ++ if (bytes[0] < 0xc0) ++ { ++ nbytes = 1; ++ is_utf8 = FALSE; ++ } ++ else ++ { ++ bytes[1] = *symbol++; ++ ++ if ((bytes[1] & 0xc0) != 0x80) ++ { ++ is_utf8 = FALSE; ++ /* Do not consume this character. It may only ++ be the first byte in the sequence that was ++ corrupt. */ ++ --symbol; ++ nbytes = 1; ++ } ++ else if ((bytes[0] & 0x20) == 0) ++ { ++ is_utf8 = TRUE; ++ nbytes = 2; ++ } ++ else ++ { ++ bytes[2] = *symbol++; ++ ++ if ((bytes[2] & 0xc0) != 0x80) ++ { ++ is_utf8 = FALSE; ++ symbol -= 2; ++ nbytes = 1; ++ } ++ else if ((bytes[0] & 0x10) == 0) ++ { ++ is_utf8 = TRUE; ++ nbytes = 3; ++ } ++ else ++ { ++ bytes[3] = *symbol++; ++ ++ nbytes = 4; ++ ++ if ((bytes[3] & 0xc0) != 0x80) ++ { ++ is_utf8 = FALSE; ++ symbol -= 3; ++ nbytes = 1; ++ } ++ else ++ is_utf8 = TRUE; ++ } ++ } ++ } ++ ++ if (unicode_display == unicode_invalid) ++ is_utf8 = FALSE; ++ ++ if (unicode_display == unicode_hex || ! is_utf8) ++ { ++ unsigned int i; ++ ++ if (width_remaining < (nbytes * 2) + 2) ++ break; ++ ++ putchar (is_utf8 ? '<' : '{'); ++ printf ("0x"); ++ for (i = 0; i < nbytes; i++) ++ printf ("%02x", bytes[i]); ++ putchar (is_utf8 ? '>' : '}'); ++ } ++ else ++ { ++ if (unicode_display == unicode_highlight && isatty (1)) ++ printf ("\x1B[31;47m"); /* Red. */ ++ ++ switch (nbytes) ++ { ++ case 2: ++ if (width_remaining < 6) ++ break; ++ printf ("\\u%02x%02x", ++ (bytes[0] & 0x1c) >> 2, ++ ((bytes[0] & 0x03) << 6) | (bytes[1] & 0x3f)); ++ break; ++ case 3: ++ if (width_remaining < 6) ++ break; ++ printf ("\\u%02x%02x", ++ ((bytes[0] & 0x0f) << 4) | ((bytes[1] & 0x3c) >> 2), ++ ((bytes[1] & 0x03) << 6) | (bytes[2] & 0x3f)); ++ break; ++ case 4: ++ if (width_remaining < 8) ++ break; ++ printf ("\\u%02x%02x%02x", ++ ((bytes[0] & 0x07) << 6) | ((bytes[1] & 0x3c) >> 2), ++ ((bytes[1] & 0x03) << 6) | ((bytes[2] & 0x3c) >> 2), ++ ((bytes[2] & 0x03) << 6) | (bytes[3] & 0x3f)); ++ ++ break; ++ default: ++ /* URG. */ ++ break; ++ } ++ ++ if (unicode_display == unicode_highlight && isatty (1)) ++ printf ("\033[0m"); /* Default colour. */ ++ } ++ ++ if (bytes[nbytes - 1] == 0) ++ break; + } + else + { +@@ -4556,6 +4702,7 @@ static struct option options[] = + {"syms", no_argument, 0, 's'}, + {"silent-truncation",no_argument, 0, 'T'}, + {"section-details", no_argument, 0, 't'}, ++ {"unicode", required_argument, NULL, 'U'}, + {"unwind", no_argument, 0, 'u'}, + {"version-info", no_argument, 0, 'V'}, + {"version", no_argument, 0, 'v'}, +@@ -4609,6 +4756,11 @@ usage (FILE * stream) + --no-demangle Do not demangle low-level symbol names. (This is the default)\n\ + --recurse-limit Enable a demangling recursion limit. (This is the default)\n\ + --no-recurse-limit Disable a demangling recursion limit\n\ ++ -U[dlexhi] --unicode=[default|locale|escape|hex|highlight|invalid]\n\ ++ Display unicode characters as determined by the current locale\n\ ++ (default), escape sequences, \"<hex sequences>\", highlighted\n\ ++ escape sequences, or treat them as invalid and display as\n\ ++ \"{hex sequences}\"\n\ + -n --notes Display the core notes (if present)\n\ + -r --relocs Display the relocations (if present)\n\ + -u --unwind Display the unwind info (if present)\n\ +@@ -4749,7 +4901,7 @@ parse_args (struct dump_data *dumpdata, + usage (stderr); + + while ((c = getopt_long +- (argc, argv, "ACDHILNR:STVWacdeghi:lnp:rstuvw::x:z", options, NULL)) != EOF) ++ (argc, argv, "ACDHILNR:STU:VWacdeghi:lnp:rstuvw::x:z", options, NULL)) != EOF) + { + switch (c) + { +@@ -4943,6 +5095,24 @@ parse_args (struct dump_data *dumpdata, + case OPTION_WITH_SYMBOL_VERSIONS: + /* Ignored for backward compatibility. */ + break; ++ case 'U': ++ if (optarg == NULL) ++ error (_("Missing arg to -U/--unicode")); /* Can this happen ? */ ++ else if (streq (optarg, "default") || streq (optarg, "d")) ++ unicode_display = unicode_default; ++ else if (streq (optarg, "locale") || streq (optarg, "l")) ++ unicode_display = unicode_locale; ++ else if (streq (optarg, "escape") || streq (optarg, "e")) ++ unicode_display = unicode_escape; ++ else if (streq (optarg, "invalid") || streq (optarg, "i")) ++ unicode_display = unicode_invalid; ++ else if (streq (optarg, "hex") || streq (optarg, "x")) ++ unicode_display = unicode_hex; ++ else if (streq (optarg, "highlight") || streq (optarg, "h")) ++ unicode_display = unicode_highlight; ++ else ++ error (_("invalid argument to -U/--unicode: %s"), optarg); ++ break; + + default: + /* xgettext:c-format */ +diff --git a/binutils/strings.c b/binutils/strings.c +--- a/binutils/strings.c 2021-12-23 03:23:38.485842662 -0800 ++++ b/binutils/strings.c 2021-12-23 03:30:36.586877452 -0800 +@@ -55,6 +55,19 @@ + -T {bfdname} + Specify a non-default object file format. + ++ --unicode={default|locale|invalid|hex|escape|highlight} ++ -u {d|l|i|x|e|h} ++ Determine how to handle UTF-8 unicode characters. The default ++ is no special treatment. All other versions of this option ++ only apply if the encoding is valid and enabling the option ++ implies --encoding=S. ++ The 'locale' option displays the characters according to the ++ current locale. The 'invalid' option treats them as ++ non-string characters. The 'hex' option displays them as hex ++ byte sequences. The 'escape' option displays them as escape ++ sequences and the 'highlight' option displays them as ++ coloured escape sequences. ++ + --output-separator=sep_string + -s sep_string String used to separate parsed strings in output. + Default is newline. +@@ -76,6 +89,22 @@ + #include "safe-ctype.h" + #include "bucomm.h" + ++#ifndef streq ++#define streq(a,b) (strcmp ((a),(b)) == 0) ++#endif ++ ++typedef enum unicode_display_type ++{ ++ unicode_default = 0, ++ unicode_locale, ++ unicode_escape, ++ unicode_hex, ++ unicode_highlight, ++ unicode_invalid ++} unicode_display_type; ++ ++static unicode_display_type unicode_display = unicode_default; ++ + #define STRING_ISGRAPHIC(c) \ + ( (c) >= 0 \ + && (c) <= 255 \ +@@ -94,7 +123,7 @@ extern int errno; + static int address_radix; + + /* Minimum length of sequence of graphic chars to trigger output. */ +-static int string_min; ++static unsigned int string_min; + + /* Whether or not we include all whitespace as a graphic char. */ + static bfd_boolean include_all_whitespace; +@@ -121,21 +150,22 @@ static char *output_separator; + static struct option long_options[] = + { + {"all", no_argument, NULL, 'a'}, ++ {"bytes", required_argument, NULL, 'n'}, + {"data", no_argument, NULL, 'd'}, ++ {"encoding", required_argument, NULL, 'e'}, ++ {"help", no_argument, NULL, 'h'}, ++ {"include-all-whitespace", no_argument, NULL, 'w'}, ++ {"output-separator", required_argument, NULL, 's'}, + {"print-file-name", no_argument, NULL, 'f'}, +- {"bytes", required_argument, NULL, 'n'}, + {"radix", required_argument, NULL, 't'}, +- {"include-all-whitespace", no_argument, NULL, 'w'}, +- {"encoding", required_argument, NULL, 'e'}, + {"target", required_argument, NULL, 'T'}, +- {"output-separator", required_argument, NULL, 's'}, +- {"help", no_argument, NULL, 'h'}, ++ {"unicode", required_argument, NULL, 'U'}, + {"version", no_argument, NULL, 'v'}, + {NULL, 0, NULL, 0} + }; + + static bfd_boolean strings_file (char *); +-static void print_strings (const char *, FILE *, file_ptr, int, int, char *); ++static void print_strings (const char *, FILE *, file_ptr, int, char *); + static void usage (FILE *, int) ATTRIBUTE_NORETURN; + + int main (int, char **); +@@ -173,7 +203,7 @@ main (int argc, char **argv) + encoding = 's'; + output_separator = NULL; + +- while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:Vv0123456789", ++ while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:U:Vv0123456789", + long_options, (int *) 0)) != EOF) + { + switch (optc) +@@ -244,7 +274,24 @@ main (int argc, char **argv) + + case 's': + output_separator = optarg; +- break; ++ break; ++ ++ case 'U': ++ if (streq (optarg, "default") || streq (optarg, "d")) ++ unicode_display = unicode_default; ++ else if (streq (optarg, "locale") || streq (optarg, "l")) ++ unicode_display = unicode_locale; ++ else if (streq (optarg, "escape") || streq (optarg, "e")) ++ unicode_display = unicode_escape; ++ else if (streq (optarg, "invalid") || streq (optarg, "i")) ++ unicode_display = unicode_invalid; ++ else if (streq (optarg, "hex") || streq (optarg, "x")) ++ unicode_display = unicode_hex; ++ else if (streq (optarg, "highlight") || streq (optarg, "h")) ++ unicode_display = unicode_highlight; ++ else ++ fatal (_("invalid argument to -U/--unicode: %s"), optarg); ++ break; + + case 'V': + case 'v': +@@ -260,6 +307,9 @@ main (int argc, char **argv) + } + } + ++ if (unicode_display != unicode_default) ++ encoding = 'S'; ++ + if (numeric_opt != 0) + { + string_min = (int) strtoul (argv[numeric_opt - 1] + 1, &s, 0); +@@ -295,14 +345,14 @@ main (int argc, char **argv) + { + datasection_only = FALSE; + SET_BINARY (fileno (stdin)); +- print_strings ("{standard input}", stdin, 0, 0, 0, (char *) NULL); ++ print_strings ("{standard input}", stdin, 0, 0, (char *) NULL); + files_given = TRUE; + } + else + { + for (; optind < argc; ++optind) + { +- if (strcmp (argv[optind], "-") == 0) ++ if (streq (argv[optind], "-")) + datasection_only = FALSE; + else + { +@@ -344,7 +394,7 @@ strings_a_section (bfd *abfd, asection * + } + + *got_a_section = TRUE; +- print_strings (filename, NULL, sect->filepos, 0, sectsize, (char *) mem); ++ print_strings (filename, NULL, sect->filepos, sectsize, (char *) mem); + free (mem); + } + +@@ -429,7 +479,7 @@ strings_file (char *file) + return FALSE; + } + +- print_strings (file, stream, (file_ptr) 0, 0, 0, (char *) 0); ++ print_strings (file, stream, (file_ptr) 0, 0, (char *) NULL); + + if (fclose (stream) == EOF) + { +@@ -553,11 +603,632 @@ unget_part_char (long c, file_ptr *addre + } + } + } ++ ++ ++static void ++print_filename_and_address (const char * filename, file_ptr address) ++{ ++ if (print_filenames) ++ printf ("%s: ", filename); ++ ++ if (! print_addresses) ++ return; ++ ++ switch (address_radix) ++ { ++ case 8: ++ if (sizeof (address) > sizeof (long)) ++ { ++#ifndef __MSVCRT__ ++ printf ("%7llo ", (unsigned long long) address); ++#else ++ printf ("%7I64o ", (unsigned long long) address); ++#endif ++ } ++ else ++ printf ("%7lo ", (unsigned long) address); ++ break; ++ ++ case 10: ++ if (sizeof (address) > sizeof (long)) ++ { ++#ifndef __MSVCRT__ ++ printf ("%7llu ", (unsigned long long) address); ++#else ++ printf ("%7I64d ", (unsigned long long) address); ++#endif ++ } ++ else ++ printf ("%7ld ", (long) address); ++ break; ++ ++ case 16: ++ if (sizeof (address) > sizeof (long)) ++ { ++#ifndef __MSVCRT__ ++ printf ("%7llx ", (unsigned long long) address); ++#else ++ printf ("%7I64x ", (unsigned long long) address); ++#endif ++ } ++ else ++ printf ("%7lx ", (unsigned long) address); ++ break; ++ } ++} ++ ++/* Return non-zero if the bytes starting at BUFFER form a valid UTF-8 encoding. ++ If the encoding is valid then returns the number of bytes it uses. */ ++ ++static unsigned int ++is_valid_utf8 (const unsigned char * buffer, unsigned long buflen) ++{ ++ if (buffer[0] < 0xc0) ++ return 0; ++ ++ if (buflen < 2) ++ return 0; ++ ++ if ((buffer[1] & 0xc0) != 0x80) ++ return 0; ++ ++ if ((buffer[0] & 0x20) == 0) ++ return 2; ++ ++ if (buflen < 3) ++ return 0; ++ ++ if ((buffer[2] & 0xc0) != 0x80) ++ return 0; ++ ++ if ((buffer[0] & 0x10) == 0) ++ return 3; ++ ++ if (buflen < 4) ++ return 0; ++ ++ if ((buffer[3] & 0xc0) != 0x80) ++ return 0; ++ ++ return 4; ++} ++ ++/* Display a UTF-8 encoded character in BUFFER according to the setting ++ of unicode_display. The character is known to be valid. ++ Returns the number of bytes consumed. */ ++ ++static unsigned int ++display_utf8_char (const unsigned char * buffer) ++{ ++ unsigned int j; ++ unsigned int utf8_len; ++ ++ switch (buffer[0] & 0x30) ++ { ++ case 0x00: ++ case 0x10: ++ utf8_len = 2; ++ break; ++ case 0x20: ++ utf8_len = 3; ++ break; ++ default: ++ utf8_len = 4; ++ } ++ ++ switch (unicode_display) ++ { ++ default: ++ fprintf (stderr, "ICE: unexpected unicode display type\n"); ++ break; ++ ++ case unicode_escape: ++ case unicode_highlight: ++ if (unicode_display == unicode_highlight && isatty (1)) ++ printf ("\x1B[31;47m"); /* Red. */ ++ ++ switch (utf8_len) ++ { ++ case 2: ++ printf ("\\u%02x%02x", ++ ((buffer[0] & 0x1c) >> 2), ++ ((buffer[0] & 0x03) << 6) | (buffer[1] & 0x3f)); ++ break; ++ ++ case 3: ++ printf ("\\u%02x%02x", ++ ((buffer[0] & 0x0f) << 4) | ((buffer[1] & 0x3c) >> 2), ++ ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3f))); ++ break; ++ ++ case 4: ++ printf ("\\u%02x%02x%02x", ++ ((buffer[0] & 0x07) << 6) | ((buffer[1] & 0x3c) >> 2), ++ ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3c) >> 2), ++ ((buffer[2] & 0x03) << 6) | ((buffer[3] & 0x3f))); ++ break; ++ default: ++ /* URG. */ ++ break; ++ } ++ ++ if (unicode_display == unicode_highlight && isatty (1)) ++ printf ("\033[0m"); /* Default colour. */ ++ break; ++ ++ case unicode_hex: ++ putchar ('<'); ++ printf ("0x"); ++ for (j = 0; j < utf8_len; j++) ++ printf ("%02x", buffer [j]); ++ putchar ('>'); ++ break; ++ ++ case unicode_locale: ++ printf ("%.1s", buffer); ++ break; ++ } ++ ++ return utf8_len; ++} ++ ++/* Display strings in BUFFER. Treat any UTF-8 encoded characters encountered ++ according to the setting of the unicode_display variable. The buffer ++ contains BUFLEN bytes. ++ ++ Display the characters as if they started at ADDRESS and are contained in ++ FILENAME. */ ++ ++static void ++print_unicode_buffer (const char * filename, ++ file_ptr address, ++ const unsigned char * buffer, ++ unsigned long buflen) ++{ ++ /* Paranoia checks... */ ++ if (filename == NULL ++ || buffer == NULL ++ || unicode_display == unicode_default ++ || encoding != 'S' ++ || encoding_bytes != 1) ++ { ++ fprintf (stderr, "ICE: bad arguments to print_unicode_buffer\n"); ++ return; ++ } ++ ++ if (buflen == 0) ++ return; ++ ++ /* We must only display strings that are at least string_min *characters* ++ long. So we scan the buffer in two stages. First we locate the start ++ of a potential string. Then we walk along it until we have found ++ string_min characters. Then we go back to the start point and start ++ displaying characters according to the unicode_display setting. */ ++ ++ unsigned long start_point = 0; ++ unsigned long i = 0; ++ unsigned int char_len = 1; ++ unsigned int num_found = 0; ++ ++ for (i = 0; i < buflen; i += char_len) ++ { ++ int c = buffer[i]; ++ ++ char_len = 1; ++ ++ /* Find the first potential character of a string. */ ++ if (! STRING_ISGRAPHIC (c)) ++ { ++ num_found = 0; ++ continue; ++ } ++ ++ if (c > 126) ++ { ++ if (c < 0xc0) ++ { ++ num_found = 0; ++ continue; ++ } ++ ++ if ((char_len = is_valid_utf8 (buffer + i, buflen - i)) == 0) ++ { ++ char_len = 1; ++ num_found = 0; ++ continue; ++ } ++ ++ if (unicode_display == unicode_invalid) ++ { ++ /* We have found a valid UTF-8 character, but we treat it as non-graphic. */ ++ num_found = 0; ++ continue; ++ } ++ } ++ ++ if (num_found == 0) ++ /* We have found a potential starting point for a string. */ ++ start_point = i; ++ ++ ++ num_found; ++ ++ if (num_found >= string_min) ++ break; ++ } ++ ++ if (num_found < string_min) ++ return; ++ ++ print_filename_and_address (filename, address + start_point); ++ ++ /* We have found string_min characters. Display them and any ++ more that follow. */ ++ for (i = start_point; i < buflen; i += char_len) ++ { ++ int c = buffer[i]; ++ ++ char_len = 1; ++ ++ if (! STRING_ISGRAPHIC (c)) ++ break; ++ else if (c < 127) ++ putchar (c); ++ else if (! is_valid_utf8 (buffer + i, buflen - i)) ++ break; ++ else if (unicode_display == unicode_invalid) ++ break; ++ else ++ char_len = display_utf8_char (buffer + i); ++ } ++ ++ if (output_separator) ++ fputs (output_separator, stdout); ++ else ++ putchar ('\n'); ++ ++ /* FIXME: Using tail recursion here is lazy programming... */ ++ print_unicode_buffer (filename, address + i, buffer + i, buflen - i); ++} ++ ++static int ++get_unicode_byte (FILE * stream, ++ unsigned char * putback, ++ unsigned int * num_putback, ++ unsigned int * num_read) ++{ ++ if (* num_putback > 0) ++ { ++ * num_putback = * num_putback - 1; ++ return putback [* num_putback]; ++ } ++ ++ * num_read = * num_read + 1; ++ ++#if defined(HAVE_GETC_UNLOCKED) && HAVE_DECL_GETC_UNLOCKED ++ return getc_unlocked (stream); ++#else ++ return getc (stream); ++#endif ++} ++ ++/* Helper function for print_unicode_stream. */ ++ ++static void ++print_unicode_stream_body (const char * filename, ++ file_ptr address, ++ FILE * stream, ++ unsigned char * putback_buf, ++ unsigned int num_putback, ++ unsigned char * print_buf) ++{ ++ /* It would be nice if we could just read the stream into a buffer ++ and then process if with print_unicode_buffer. But the input ++ might be huge or it might time-locked (eg stdin). So instead ++ we go one byte at a time... */ ++ ++ file_ptr start_point = 0; ++ unsigned int num_read = 0; ++ unsigned int num_chars = 0; ++ unsigned int num_print = 0; ++ int c; ++ ++ /* Find a series of string_min characters. Put them into print_buf. */ ++ do ++ { ++ if (num_chars >= string_min) ++ break; ++ ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ ++ if (! STRING_ISGRAPHIC (c)) ++ { ++ num_chars = num_print = 0; ++ continue; ++ } ++ ++ if (num_chars == 0) ++ start_point = num_read - 1; ++ ++ if (c < 127) ++ { ++ print_buf[num_print] = c; ++ num_chars ++; ++ num_print ++; ++ continue; ++ } ++ ++ if (c < 0xc0) ++ { ++ num_chars = num_print = 0; ++ continue; ++ } ++ ++ /* We *might* have a UTF-8 sequence. Time to start peeking. */ ++ char utf8[4]; ++ ++ utf8[0] = c; ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[1] = c; ++ ++ if ((utf8[1] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[1]; ++ num_chars = num_print = 0; ++ continue; ++ } ++ else if ((utf8[0] & 0x20) == 0) ++ { ++ /* A valid 2-byte UTF-8 encoding. */ ++ if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[1]; ++ num_chars = num_print = 0; ++ } ++ else ++ { ++ print_buf[num_print ++] = utf8[0]; ++ print_buf[num_print ++] = utf8[1]; ++ num_chars ++; ++ } ++ continue; ++ } ++ ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[2] = c; ++ ++ if ((utf8[2] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ num_chars = num_print = 0; ++ continue; ++ } ++ else if ((utf8[0] & 0x10) == 0) ++ { ++ /* A valid 3-byte UTF-8 encoding. */ ++ if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ num_chars = num_print = 0; ++ } ++ else ++ { ++ print_buf[num_print ++] = utf8[0]; ++ print_buf[num_print ++] = utf8[1]; ++ print_buf[num_print ++] = utf8[2]; ++ num_chars ++; ++ } ++ continue; ++ } ++ ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[3] = c; ++ ++ if ((utf8[3] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[3]; ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ num_chars = num_print = 0; ++ } ++ /* We have a valid 4-byte UTF-8 encoding. */ ++ else if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[3]; ++ putback_buf[num_putback++] = utf8[1]; ++ putback_buf[num_putback++] = utf8[2]; ++ num_chars = num_print = 0; ++ } ++ else ++ { ++ print_buf[num_print ++] = utf8[0]; ++ print_buf[num_print ++] = utf8[1]; ++ print_buf[num_print ++] = utf8[2]; ++ print_buf[num_print ++] = utf8[3]; ++ num_chars ++; ++ } ++ } ++ while (1); ++ ++ if (num_chars >= string_min) ++ { ++ /* We know that we have string_min valid characters in print_buf, ++ and there may be more to come in the stream. Start displaying ++ them. */ ++ ++ print_filename_and_address (filename, address + start_point); ++ ++ unsigned int i; ++ for (i = 0; i < num_print;) ++ { ++ if (print_buf[i] < 127) ++ putchar (print_buf[i++]); ++ else ++ i += display_utf8_char (print_buf + i); ++ } ++ ++ /* OK so now we have to start read unchecked bytes. */ ++ ++ /* Find a series of string_min characters. Put them into print_buf. */ ++ do ++ { ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ ++ if (! STRING_ISGRAPHIC (c)) ++ break; ++ ++ if (c < 127) ++ { ++ putchar (c); ++ continue; ++ } ++ ++ if (c < 0xc0) ++ break; ++ ++ /* We *might* have a UTF-8 sequence. Time to start peeking. */ ++ unsigned char utf8[4]; ++ ++ utf8[0] = c; ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[1] = c; ++ ++ if ((utf8[1] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else if ((utf8[0] & 0x20) == 0) ++ { ++ /* Valid 2-byte UTF-8. */ ++ if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else ++ { ++ (void) display_utf8_char (utf8); ++ continue; ++ } ++ } ++ ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[2] = c; ++ ++ if ((utf8[2] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else if ((utf8[0] & 0x10) == 0) ++ { ++ /* Valid 3-byte UTF-8. */ ++ if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else ++ { ++ (void) display_utf8_char (utf8); ++ continue; ++ } ++ } ++ ++ c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read); ++ if (c == EOF) ++ break; ++ utf8[3] = c; ++ ++ if ((utf8[3] & 0xc0) != 0x80) ++ { ++ /* Invalid UTF-8. */ ++ putback_buf[num_putback++] = utf8[3]; ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else if (unicode_display == unicode_invalid) ++ { ++ putback_buf[num_putback++] = utf8[3]; ++ putback_buf[num_putback++] = utf8[2]; ++ putback_buf[num_putback++] = utf8[1]; ++ break; ++ } ++ else ++ /* A valid 4-byte UTF-8 encoding. */ ++ (void) display_utf8_char (utf8); ++ } ++ while (1); ++ ++ if (output_separator) ++ fputs (output_separator, stdout); ++ else ++ putchar ('\n'); ++ } ++ ++ if (c != EOF) ++ /* FIXME: Using tail recursion here is lazy, but it works. */ ++ print_unicode_stream_body (filename, address + num_read, stream, putback_buf, num_putback, print_buf); ++} ++ ++/* Display strings read in from STREAM. Treat any UTF-8 encoded characters ++ encountered according to the setting of the unicode_display variable. ++ The stream is positioned at ADDRESS and is attached to FILENAME. */ ++ ++static void ++print_unicode_stream (const char * filename, ++ file_ptr address, ++ FILE * stream) ++{ ++ /* Paranoia checks... */ ++ if (filename == NULL ++ || stream == NULL ++ || unicode_display == unicode_default ++ || encoding != 'S' ++ || encoding_bytes != 1) ++ { ++ fprintf (stderr, "ICE: bad arguments to print_unicode_stream\n"); ++ return; ++ } ++ ++ /* Allocate space for string_min 4-byte utf-8 characters. */ ++ unsigned char * print_buf = xmalloc ((4 * string_min) + 1); ++ /* We should never have to put back more than 4 bytes. */ ++ unsigned char putback_buf[5]; ++ unsigned int num_putback = 0; ++ ++ print_unicode_stream_body (filename, address, stream, putback_buf, num_putback, print_buf); ++ free (print_buf); ++} ++ + + /* Find the strings in file FILENAME, read from STREAM. + Assume that STREAM is positioned so that the next byte read + is at address ADDRESS in the file. +- Stop reading at address STOP_POINT in the file, if nonzero. + + If STREAM is NULL, do not read from it. + The caller can supply a buffer of characters +@@ -568,20 +1239,29 @@ unget_part_char (long c, file_ptr *addre + + static void + print_strings (const char *filename, FILE *stream, file_ptr address, +- int stop_point, int magiccount, char *magic) ++ int magiccount, char *magic) + { ++ if (unicode_display != unicode_default) ++ { ++ if (magic != NULL) ++ print_unicode_buffer (filename, address, ++ (const unsigned char *) magic, magiccount); ++ ++ if (stream != NULL) ++ print_unicode_stream (filename, address, stream); ++ return; ++ } ++ + char *buf = (char *) xmalloc (sizeof (char) * (string_min + 1)); + + while (1) + { + file_ptr start; +- int i; ++ unsigned int i; + long c; + + /* See if the next `string_min' chars are all graphic chars. */ + tryline: +- if (stop_point && address >= stop_point) +- break; + start = address; + for (i = 0; i < string_min; i++) + { +@@ -604,69 +1284,7 @@ print_strings (const char *filename, FIL + /* We found a run of `string_min' graphic characters. Print up + to the next non-graphic character. */ + +- if (print_filenames) +- printf ("%s: ", filename); +- if (print_addresses) +- switch (address_radix) +- { +- case 8: +-#ifdef HAVE_LONG_LONG +- if (sizeof (start) > sizeof (long)) +- { +-# ifndef __MSVCRT__ +- printf ("%7llo ", (unsigned long long) start); +-# else +- printf ("%7I64o ", (unsigned long long) start); +-# endif +- } +- else +-#elif !BFD_HOST_64BIT_LONG +- if (start != (unsigned long) start) +- printf ("++%7lo ", (unsigned long) start); +- else +-#endif +- printf ("%7lo ", (unsigned long) start); +- break; +- +- case 10: +-#ifdef HAVE_LONG_LONG +- if (sizeof (start) > sizeof (long)) +- { +-# ifndef __MSVCRT__ +- printf ("%7llu ", (unsigned long long) start); +-# else +- printf ("%7I64d ", (unsigned long long) start); +-# endif +- } +- else +-#elif !BFD_HOST_64BIT_LONG +- if (start != (unsigned long) start) +- printf ("++%7lu ", (unsigned long) start); +- else +-#endif +- printf ("%7ld ", (long) start); +- break; +- +- case 16: +-#ifdef HAVE_LONG_LONG +- if (sizeof (start) > sizeof (long)) +- { +-# ifndef __MSVCRT__ +- printf ("%7llx ", (unsigned long long) start); +-# else +- printf ("%7I64x ", (unsigned long long) start); +-# endif +- } +- else +-#elif !BFD_HOST_64BIT_LONG +- if (start != (unsigned long) start) +- printf ("%lx%8.8lx ", (unsigned long) (start >> 32), +- (unsigned long) (start & 0xffffffff)); +- else +-#endif +- printf ("%7lx ", (unsigned long) start); +- break; +- } ++ print_filename_and_address (filename, start); + + buf[i] = '\0'; + fputs (buf, stdout); +@@ -718,6 +1336,8 @@ usage (FILE *stream, int status) + -T --target=<BFDNAME> Specify the binary file format\n\ + -e --encoding={s,S,b,l,B,L} Select character size and endianness:\n\ + s = 7-bit, S = 8-bit, {b,l} = 16-bit, {B,L} = 32-bit\n\ ++ --unicode={default|show|invalid|hex|escape|highlight}\n\ ++ -u {d|s|i|x|e|h} Specify how to treat UTF-8 encoded unicode characters\n\ + -s --output-separator=<string> String used to separate strings in output.\n\ + @<file> Read options from <file>\n\ + -h --help Display this information\n\ diff --git a/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch new file mode 100644 index 0000000000..f118e2599b --- /dev/null +++ b/meta/recipes-devtools/binutils/binutils/0001-CVE-2021-45078.patch @@ -0,0 +1,255 @@ +From 161e87d12167b1e36193385485c1f6ce92f74f02 Mon Sep 17 00:00:00 2001 +From: Alan Modra <amodra@gmail.com> +Date: Wed, 15 Dec 2021 11:48:42 +1030 +Subject: [PATCH] PR28694, Out-of-bounds write in stab_xcoff_builtin_type + + PR 28694 + * stabs.c (stab_xcoff_builtin_type): Make typenum unsigned. + Negate typenum earlier, simplifying bounds checking. Correct + off-by-one indexing. Adjust switch cases. + + +CVE: CVE-2021-45078 +Upstream-Status: Backport [https://sourceware.org/git/?p=binutils-gdb.git;a=patch;h=161e87d12167b1e36193385485c1f6ce92f74f02] + +Signed-off-by: Sundeep KOKKONDA <sundeep.kokkonda@gmail.com> +--- + binutils/stabs.c | 87 ++++++++++++++++++++++++------------------------ + 1 file changed, 43 insertions(+), 44 deletions(-) + + +diff --git a/binutils/stabs.c b/binutils/stabs.c +index 274bfb0e7fa..83ee3ea5fa4 100644 +--- a/binutils/stabs.c ++++ b/binutils/stabs.c +@@ -202,7 +202,7 @@ static debug_type stab_find_type (void *, struct stab_handle *, const int *); + static bfd_boolean stab_record_type + (void *, struct stab_handle *, const int *, debug_type); + static debug_type stab_xcoff_builtin_type +- (void *, struct stab_handle *, int); ++ (void *, struct stab_handle *, unsigned int); + static debug_type stab_find_tagged_type + (void *, struct stab_handle *, const char *, int, enum debug_type_kind); + static debug_type *stab_demangle_argtypes +@@ -3496,166 +3496,167 @@ stab_record_type (void *dhandle ATTRIBUTE_UNUSED, struct stab_handle *info, + + static debug_type + stab_xcoff_builtin_type (void *dhandle, struct stab_handle *info, +- int typenum) ++ unsigned int typenum) + { + debug_type rettype; + const char *name; + +- if (typenum >= 0 || typenum < -XCOFF_TYPE_COUNT) ++ typenum = -typenum - 1; ++ if (typenum >= XCOFF_TYPE_COUNT) + { +- fprintf (stderr, _("Unrecognized XCOFF type %d\n"), typenum); ++ fprintf (stderr, _("Unrecognized XCOFF type %d\n"), -typenum - 1); + return DEBUG_TYPE_NULL; + } +- if (info->xcoff_types[-typenum] != NULL) +- return info->xcoff_types[-typenum]; ++ if (info->xcoff_types[typenum] != NULL) ++ return info->xcoff_types[typenum]; + +- switch (-typenum) ++ switch (typenum) + { +- case 1: ++ case 0: + /* The size of this and all the other types are fixed, defined + by the debugging format. */ + name = "int"; + rettype = debug_make_int_type (dhandle, 4, FALSE); + break; +- case 2: ++ case 1: + name = "char"; + rettype = debug_make_int_type (dhandle, 1, FALSE); + break; +- case 3: ++ case 2: + name = "short"; + rettype = debug_make_int_type (dhandle, 2, FALSE); + break; +- case 4: ++ case 3: + name = "long"; + rettype = debug_make_int_type (dhandle, 4, FALSE); + break; +- case 5: ++ case 4: + name = "unsigned char"; + rettype = debug_make_int_type (dhandle, 1, TRUE); + break; +- case 6: ++ case 5: + name = "signed char"; + rettype = debug_make_int_type (dhandle, 1, FALSE); + break; +- case 7: ++ case 6: + name = "unsigned short"; + rettype = debug_make_int_type (dhandle, 2, TRUE); + break; +- case 8: ++ case 7: + name = "unsigned int"; + rettype = debug_make_int_type (dhandle, 4, TRUE); + break; +- case 9: ++ case 8: + name = "unsigned"; + rettype = debug_make_int_type (dhandle, 4, TRUE); + break; +- case 10: ++ case 9: + name = "unsigned long"; + rettype = debug_make_int_type (dhandle, 4, TRUE); + break; +- case 11: ++ case 10: + name = "void"; + rettype = debug_make_void_type (dhandle); + break; +- case 12: ++ case 11: + /* IEEE single precision (32 bit). */ + name = "float"; + rettype = debug_make_float_type (dhandle, 4); + break; +- case 13: ++ case 12: + /* IEEE double precision (64 bit). */ + name = "double"; + rettype = debug_make_float_type (dhandle, 8); + break; +- case 14: ++ case 13: + /* This is an IEEE double on the RS/6000, and different machines + with different sizes for "long double" should use different + negative type numbers. See stabs.texinfo. */ + name = "long double"; + rettype = debug_make_float_type (dhandle, 8); + break; +- case 15: ++ case 14: + name = "integer"; + rettype = debug_make_int_type (dhandle, 4, FALSE); + break; +- case 16: ++ case 15: + name = "boolean"; + rettype = debug_make_bool_type (dhandle, 4); + break; +- case 17: ++ case 16: + name = "short real"; + rettype = debug_make_float_type (dhandle, 4); + break; +- case 18: ++ case 17: + name = "real"; + rettype = debug_make_float_type (dhandle, 8); + break; +- case 19: ++ case 18: + /* FIXME */ + name = "stringptr"; + rettype = NULL; + break; +- case 20: ++ case 19: + /* FIXME */ + name = "character"; + rettype = debug_make_int_type (dhandle, 1, TRUE); + break; +- case 21: ++ case 20: + name = "logical*1"; + rettype = debug_make_bool_type (dhandle, 1); + break; +- case 22: ++ case 21: + name = "logical*2"; + rettype = debug_make_bool_type (dhandle, 2); + break; +- case 23: ++ case 22: + name = "logical*4"; + rettype = debug_make_bool_type (dhandle, 4); + break; +- case 24: ++ case 23: + name = "logical"; + rettype = debug_make_bool_type (dhandle, 4); + break; +- case 25: ++ case 24: + /* Complex type consisting of two IEEE single precision values. */ + name = "complex"; + rettype = debug_make_complex_type (dhandle, 8); + break; +- case 26: ++ case 25: + /* Complex type consisting of two IEEE double precision values. */ + name = "double complex"; + rettype = debug_make_complex_type (dhandle, 16); + break; +- case 27: ++ case 26: + name = "integer*1"; + rettype = debug_make_int_type (dhandle, 1, FALSE); + break; +- case 28: ++ case 27: + name = "integer*2"; + rettype = debug_make_int_type (dhandle, 2, FALSE); + break; +- case 29: ++ case 28: + name = "integer*4"; + rettype = debug_make_int_type (dhandle, 4, FALSE); + break; +- case 30: ++ case 29: + /* FIXME */ + name = "wchar"; + rettype = debug_make_int_type (dhandle, 2, FALSE); + break; +- case 31: ++ case 30: + name = "long long"; + rettype = debug_make_int_type (dhandle, 8, FALSE); + break; +- case 32: ++ case 31: + name = "unsigned long long"; + rettype = debug_make_int_type (dhandle, 8, TRUE); + break; +- case 33: ++ case 32: + name = "logical*8"; + rettype = debug_make_bool_type (dhandle, 8); + break; +- case 34: ++ case 33: + name = "integer*8"; + rettype = debug_make_int_type (dhandle, 8, FALSE); + break; +@@ -3664,9 +3665,7 @@ stab_xcoff_builtin_type (void *dhandle, struct stab_handle *info, + } + + rettype = debug_name_type (dhandle, name, rettype); +- +- info->xcoff_types[-typenum] = rettype; +- ++ info->xcoff_types[typenum] = rettype; + return rettype; + } + +-- +2.27.0 + diff --git a/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch deleted file mode 100644 index 3771f571eb..0000000000 --- a/meta/recipes-devtools/binutils/binutils/0002-CVE-2021-20197.patch +++ /dev/null @@ -1,170 +0,0 @@ -From d3edaa91d4cf7202ec14342410194841e2f67f12 Mon Sep 17 00:00:00 2001 -From: Alan Modra <amodra@gmail.com> -Date: Fri, 26 Feb 2021 11:30:32 +1030 -Subject: [PATCH] Reinstate various pieces backed out from smart_rename changes - -In the interests of a stable release various last minute smart_rename -patches were backed out of the 2.36 branch. The main reason to -reinstate some of those backed out changes here is to make necessary -followup fixes to commit 8e03235147a9 simple cherry-picks from -mainline. A secondary reason is that ar -M support isn't fixed for -pr26945 without this patch. - - PR 26945 - * ar.c: Don't include libbfd.h. - (write_archive): Replace xmalloc+strcpy with xstrdup. - * arsup.c (temp_name, real_ofd): New static variables. - (ar_open): Use make_tempname and bfd_fdopenw. - (ar_save): Adjust to suit ar_open changes. - * objcopy.c: Don't include libbfd.h. - * rename.c: Rename and reorder variables. - -(cherry picked from commit 95b91a043aeaeb546d2fea556d84a2de1e917770) - -Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=d3edaa91d4cf7202ec14342410194841e2f67f12] -CVE: CVE-2021-20197 -Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com> ---- - binutils/ar.c | 4 +--- - binutils/arsup.c | 37 +++++++++++++++++++++++++------------ - binutils/objcopy.c | 1 - - binutils/rename.c | 6 +++--- - 5 files changed, 42 insertions(+), 19 deletions(-) - -diff --git a/binutils/ar.c b/binutils/ar.c -index 3a91708b51c..44df48c5c67 100644 ---- a/binutils/ar.c -+++ b/binutils/ar.c -@@ -25,7 +25,6 @@ - - #include "sysdep.h" - #include "bfd.h" --#include "libbfd.h" - #include "libiberty.h" - #include "progress.h" - #include "getopt.h" -@@ -1255,8 +1254,7 @@ write_archive (bfd *iarch) - bfd *contents_head = iarch->archive_next; - int ofd = -1; - -- old_name = (char *) xmalloc (strlen (bfd_get_filename (iarch)) + 1); -- strcpy (old_name, bfd_get_filename (iarch)); -+ old_name = xstrdup (bfd_get_filename (iarch)); - new_name = make_tempname (old_name, &ofd); - - if (new_name == NULL) -diff --git a/binutils/arsup.c b/binutils/arsup.c -index 0a1f63f6456..f7ce8f0bc82 100644 ---- a/binutils/arsup.c -+++ b/binutils/arsup.c -@@ -42,6 +42,8 @@ extern int deterministic; - - static bfd *obfd; - static char *real_name; -+static char *temp_name; -+static int real_ofd; - static FILE *outfile; - - static void -@@ -149,27 +151,24 @@ maybequit (void) - void - ar_open (char *name, int t) - { -- char *tname; -- const char *bname = lbasename (name); -- real_name = name; -+ real_name = xstrdup (name); -+ temp_name = make_tempname (real_name, &real_ofd); - -- /* Prepend tmp- to the beginning, to avoid file-name clashes after -- truncation on filesystems with limited namespaces (DOS). */ -- if (asprintf (&tname, "%.*stmp-%s", (int) (bname - name), name, bname) == -1) -+ if (temp_name == NULL) - { -- fprintf (stderr, _("%s: Can't allocate memory for temp name (%s)\n"), -+ fprintf (stderr, _("%s: Can't open temporary file (%s)\n"), - program_name, strerror(errno)); - maybequit (); - return; - } - -- obfd = bfd_openw (tname, NULL); -+ obfd = bfd_fdopenw (temp_name, NULL, real_ofd); - - if (!obfd) - { - fprintf (stderr, - _("%s: Can't open output archive %s\n"), -- program_name, tname); -+ program_name, temp_name); - - maybequit (); - } -@@ -344,16 +343,30 @@ ar_save (void) - } - else - { -- char *ofilename = xstrdup (bfd_get_filename (obfd)); -+ struct stat target_stat; - - if (deterministic > 0) - obfd->flags |= BFD_DETERMINISTIC_OUTPUT; - - bfd_close (obfd); - -- smart_rename (ofilename, real_name, NULL); -+ if (stat (real_name, &target_stat) != 0) -+ { -+ /* The temp file created in ar_open has mode 0600 as per mkstemp. -+ Create the real empty output file here so smart_rename will -+ update the mode according to the process umask. */ -+ obfd = bfd_openw (real_name, NULL); -+ if (obfd != NULL) -+ { -+ bfd_set_format (obfd, bfd_archive); -+ bfd_close (obfd); -+ } -+ } -+ -+ smart_rename (temp_name, real_name, NULL); - obfd = 0; -- free (ofilename); -+ free (temp_name); -+ free (real_name); - } - } - -diff --git a/binutils/objcopy.c b/binutils/objcopy.c -index 07a872b5a80..73aa8bc2514 100644 ---- a/binutils/objcopy.c -+++ b/binutils/objcopy.c -@@ -20,7 +20,6 @@ - - #include "sysdep.h" - #include "bfd.h" --#include "libbfd.h" - #include "progress.h" - #include "getopt.h" - #include "libiberty.h" -diff --git a/binutils/rename.c b/binutils/rename.c -index f471b45fd3f..2ff092ee22b 100644 ---- a/binutils/rename.c -+++ b/binutils/rename.c -@@ -130,11 +130,11 @@ int - smart_rename (const char *from, const char *to, - struct stat *target_stat ATTRIBUTE_UNUSED) - { -- bfd_boolean exists; -- struct stat s; - int ret = 0; -+ struct stat to_stat; -+ bfd_boolean exists; - -- exists = lstat (to, &s) == 0; -+ exists = lstat (to, &to_stat) == 0; - - #if defined (_WIN32) && !defined (__CYGWIN32__) - /* Win32, unlike unix, will not erase `to' in `rename(from, to)' but --- -2.31.1 - diff --git a/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch b/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch deleted file mode 100644 index 082b28b29c..0000000000 --- a/meta/recipes-devtools/binutils/binutils/0003-CVE-2021-20197.patch +++ /dev/null @@ -1,171 +0,0 @@ -From 8b69e61d4be276bb862698aaafddc3e779d23c8f Mon Sep 17 00:00:00 2001 -From: Alan Modra <amodra@gmail.com> -Date: Tue, 23 Feb 2021 09:37:39 +1030 -Subject: [PATCH] PR27456, lstat in rename.c on MinGW - - PR 27456 - * rename.c: Tidy throughout. - (smart_rename): Always copy. Remove windows specific code. - -(cherry picked from commit cca8873dd5a6015d5557ea44bc1ea9c252435a29) - -Upstream-Status: Backport [https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=8b69e61d4be276bb862698aaafddc3e779d23c8f] -CVE: CVE-2021-20197 -Signed-off-by: Vinay Kumar <vinay.m.engg@gmail.com> ---- - binutils/rename.c | 111 ++++++++++++++------------------------------- - 2 files changed, 40 insertions(+), 76 deletions(-) - -diff --git a/binutils/rename.c b/binutils/rename.c -index 2ff092ee22b..72a9323d72c 100644 ---- a/binutils/rename.c -+++ b/binutils/rename.c -@@ -24,14 +24,9 @@ - - #ifdef HAVE_GOOD_UTIME_H - #include <utime.h> --#else /* ! HAVE_GOOD_UTIME_H */ --#ifdef HAVE_UTIMES -+#elif defined HAVE_UTIMES - #include <sys/time.h> --#endif /* HAVE_UTIMES */ --#endif /* ! HAVE_GOOD_UTIME_H */ -- --#if ! defined (_WIN32) || defined (__CYGWIN32__) --static int simple_copy (const char *, const char *); -+#endif - - /* The number of bytes to copy at once. */ - #define COPY_BUF 8192 -@@ -82,7 +77,6 @@ simple_copy (const char *from, const char *to) - } - return 0; - } --#endif /* __CYGWIN32__ or not _WIN32 */ - - /* Set the times of the file DESTINATION to be the same as those in - STATBUF. */ -@@ -91,87 +85,52 @@ void - set_times (const char *destination, const struct stat *statbuf) - { - int result; -- -- { - #ifdef HAVE_GOOD_UTIME_H -- struct utimbuf tb; -- -- tb.actime = statbuf->st_atime; -- tb.modtime = statbuf->st_mtime; -- result = utime (destination, &tb); --#else /* ! HAVE_GOOD_UTIME_H */ --#ifndef HAVE_UTIMES -- long tb[2]; -- -- tb[0] = statbuf->st_atime; -- tb[1] = statbuf->st_mtime; -- result = utime (destination, tb); --#else /* HAVE_UTIMES */ -- struct timeval tv[2]; -- -- tv[0].tv_sec = statbuf->st_atime; -- tv[0].tv_usec = 0; -- tv[1].tv_sec = statbuf->st_mtime; -- tv[1].tv_usec = 0; -- result = utimes (destination, tv); --#endif /* HAVE_UTIMES */ --#endif /* ! HAVE_GOOD_UTIME_H */ -- } -+ struct utimbuf tb; -+ -+ tb.actime = statbuf->st_atime; -+ tb.modtime = statbuf->st_mtime; -+ result = utime (destination, &tb); -+#elif defined HAVE_UTIMES -+ struct timeval tv[2]; -+ -+ tv[0].tv_sec = statbuf->st_atime; -+ tv[0].tv_usec = 0; -+ tv[1].tv_sec = statbuf->st_mtime; -+ tv[1].tv_usec = 0; -+ result = utimes (destination, tv); -+#else -+ long tb[2]; -+ -+ tb[0] = statbuf->st_atime; -+ tb[1] = statbuf->st_mtime; -+ result = utime (destination, tb); -+#endif - - if (result != 0) - non_fatal (_("%s: cannot set time: %s"), destination, strerror (errno)); - } - --/* Rename FROM to TO, copying if TO exists. TARGET_STAT has the file status -- that, if non-NULL, is used to fix up timestamps after rename. Return 0 if -- ok, -1 if error. */ -+/* Copy FROM to TO. TARGET_STAT has the file status that, if non-NULL, -+ is used to fix up timestamps. Return 0 if ok, -1 if error. -+ At one time this function renamed files, but file permissions are -+ tricky to update given the number of different schemes used by -+ various systems. So now we just copy. */ - - int - smart_rename (const char *from, const char *to, -- struct stat *target_stat ATTRIBUTE_UNUSED) -+ struct stat *target_stat) - { -- int ret = 0; -- struct stat to_stat; -- bfd_boolean exists; -- -- exists = lstat (to, &to_stat) == 0; -- --#if defined (_WIN32) && !defined (__CYGWIN32__) -- /* Win32, unlike unix, will not erase `to' in `rename(from, to)' but -- fail instead. Also, chown is not present. */ -- -- if (exists) -- remove (to); -+ int ret; - -- ret = rename (from, to); -+ ret = simple_copy (from, to); - if (ret != 0) -- { -- /* We have to clean up here. */ -- non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno)); -- unlink (from); -- } --#else -- /* Avoid a full copy and use rename if TO does not exist. */ -- if (!exists) -- { -- if ((ret = rename (from, to)) != 0) -- { -- /* We have to clean up here. */ -- non_fatal (_("unable to rename '%s'; reason: %s"), to, strerror (errno)); -- unlink (from); -- } -- } -- else -- { -- ret = simple_copy (from, to); -- if (ret != 0) -- non_fatal (_("unable to copy file '%s'; reason: %s"), to, strerror (errno)); -+ non_fatal (_("unable to copy file '%s'; reason: %s"), -+ to, strerror (errno)); - -- if (target_stat != NULL) -- set_times (to, target_stat); -- unlink (from); -- } --#endif /* _WIN32 && !__CYGWIN32__ */ -+ if (target_stat != NULL) -+ set_times (to, target_stat); -+ unlink (from); - - return ret; - } --- -2.31.1 - diff --git a/meta/recipes-devtools/ccache/ccache_4.2.bb b/meta/recipes-devtools/ccache/ccache_4.2.1.bb index b76bf043f0..99bbe0eca2 100644 --- a/meta/recipes-devtools/ccache/ccache_4.2.bb +++ b/meta/recipes-devtools/ccache/ccache_4.2.1.bb @@ -7,14 +7,14 @@ HOMEPAGE = "http://ccache.samba.org" SECTION = "devel" LICENSE = "GPLv3+" -LIC_FILES_CHKSUM = "file://LICENSE.adoc;md5=28afb89f649f309e7ac1aab554564637" +LIC_FILES_CHKSUM = "file://LICENSE.adoc;md5=698a26b57e513d678e1e7727bf56395b" DEPENDS = "zstd" SRC_URI = "https://github.com/ccache/ccache/releases/download/v${PV}/${BP}.tar.gz" SRC_URI += "file://0001-CMake-make-build-of-documentation-optional-842.patch" -SRC_URI[sha256sum] = "dbf139ff32031b54cb47f2d7983269f328df14b5a427882f89f7721e5c411b7e" +SRC_URI[sha256sum] = "320d2b17d2f76393e5d4bb28c8dee5ca783248e9cd23dff0654694d60f8a4b62" UPSTREAM_CHECK_URI = "https://github.com/ccache/ccache/releases/" diff --git a/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc b/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc index fb02b2006e..1250a9b99c 100644 --- a/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc +++ b/meta/recipes-devtools/e2fsprogs/e2fsprogs.inc @@ -19,7 +19,8 @@ LIC_FILES_CHKSUM = "file://NOTICE;md5=d50be0580c0b0a7fbc7a4830bbe6c12b \ SECTION = "base" DEPENDS = "util-linux attr autoconf-archive" -SRC_URI = "git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git;branch=master" +SRC_URI = "git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git;branch=master \ + file://0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch" S = "${WORKDIR}/git" inherit autotools gettext texinfo pkgconfig multilib_header update-alternatives ptest diff --git a/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch b/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch new file mode 100644 index 0000000000..d679b25b1d --- /dev/null +++ b/meta/recipes-devtools/e2fsprogs/e2fsprogs/0001-e2fsck-fix-last-mount-write-time-when-e2fsck-is-forc.patch @@ -0,0 +1,66 @@ +From 2c69c94217b6db083d601d4fd62d6ab6c1628fee Mon Sep 17 00:00:00 2001 +From: Lukas Czerner <lczerner@redhat.com> +Date: Mon, 14 Jun 2021 15:27:25 +0200 +Subject: [PATCH] e2fsck: fix last mount/write time when e2fsck is forced + +With commit c52d930f e2fsck is no longer able to fix bad last +mount/write time by default because it is conditioned on s_checkinterval +not being zero, which it is by default. + +One place where it matters is when other e2fsprogs tools require to run +full file system check before a certain operation. If the last mount +time is for any reason in future, it will not allow it to run even if +full e2fsck is ran. + +Fix it by checking the last mount/write time when the e2fsck is forced, +except for the case where we know the system clock is broken. + +[ Reworked the conditionals so error messages claiming that the last + write/mount time were corrupted wouldn't be always printed when the + e2fsck was run with the -f option, thus causing 299 out of 372 + regression tests to fail. -- TYT ] + +Fixes: c52d930f ("e2fsck: don't check for future superblock times if checkinterval == 0") +Reported-by: Dusty Mabe <dustymabe@redhat.com> +Signed-off-by: Lukas Czerner <lczerner@redhat.com> +Signed-off-by: Theodore Ts'o <tytso@mit.edu> + +Upstream-Status: Backport [https://github.com/tytso/e2fsprogs/commit/2c69c94217b6db083d601d4fd62d6ab6c1628fee] +Signed-off-by: Changqing Li <changqing.li@windriver.com> +--- + e2fsck/super.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +diff --git a/e2fsck/super.c b/e2fsck/super.c +index e1c3f935..31e2ffb2 100644 +--- a/e2fsck/super.c ++++ b/e2fsck/super.c +@@ -1038,9 +1038,9 @@ void check_super_block(e2fsck_t ctx) + * Check to see if the superblock last mount time or last + * write time is in the future. + */ +- if (!broken_system_clock && fs->super->s_checkinterval && +- !(ctx->flags & E2F_FLAG_TIME_INSANE) && +- fs->super->s_mtime > (__u32) ctx->now) { ++ if (((ctx->options & E2F_OPT_FORCE) || fs->super->s_checkinterval) && ++ !broken_system_clock && !(ctx->flags & E2F_FLAG_TIME_INSANE) && ++ (fs->super->s_mtime > (__u32) ctx->now)) { + pctx.num = fs->super->s_mtime; + problem = PR_0_FUTURE_SB_LAST_MOUNT; + if (fs->super->s_mtime <= (__u32) ctx->now + ctx->time_fudge) +@@ -1050,9 +1050,9 @@ void check_super_block(e2fsck_t ctx) + fs->flags |= EXT2_FLAG_DIRTY; + } + } +- if (!broken_system_clock && fs->super->s_checkinterval && +- !(ctx->flags & E2F_FLAG_TIME_INSANE) && +- fs->super->s_wtime > (__u32) ctx->now) { ++ if (((ctx->options & E2F_OPT_FORCE) || fs->super->s_checkinterval) && ++ !broken_system_clock && !(ctx->flags & E2F_FLAG_TIME_INSANE) && ++ (fs->super->s_wtime > (__u32) ctx->now)) { + pctx.num = fs->super->s_wtime; + problem = PR_0_FUTURE_SB_LAST_WRITE; + if (fs->super->s_wtime <= (__u32) ctx->now + ctx->time_fudge) +-- +2.25.1 + diff --git a/meta/recipes-devtools/gcc/gcc-10.2.inc b/meta/recipes-devtools/gcc/gcc-10.3.inc index 248e002106..1fdfcced8e 100644 --- a/meta/recipes-devtools/gcc/gcc-10.2.inc +++ b/meta/recipes-devtools/gcc/gcc-10.3.inc @@ -2,11 +2,11 @@ require gcc-common.inc # Third digit in PV should be incremented after a minor release -PV = "10.2.0" +PV = "10.3.0" # BINV should be incremented to a revision after a minor gcc release -BINV = "10.2.0" +BINV = "10.3.0" FILESEXTRAPATHS =. "${FILE_DIRNAME}/gcc:${FILE_DIRNAME}/gcc/backport:" @@ -65,17 +65,18 @@ SRC_URI = "\ file://0035-gentypes-genmodes-Do-not-use-__LINE__-for-maintainin.patch \ file://0036-mingw32-Enable-operation_not_supported.patch \ file://0037-libatomic-Do-not-enforce-march-on-aarch64.patch \ - file://0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch \ - file://0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch \ - file://0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch \ - file://0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch \ file://0001-libatomic-libgomp-libitc-Fix-bootstrap-PR70454.patch \ file://0001-CVE-2021-35465.patch \ file://0002-CVE-2021-35465.patch \ file://0003-CVE-2021-35465.patch \ file://0004-CVE-2021-35465.patch \ + file://0001-CVE-2021-42574.patch \ + file://0002-CVE-2021-42574.patch \ + file://0003-CVE-2021-42574.patch \ + file://0004-CVE-2021-42574.patch \ + file://0005-CVE-2021-42574.patch \ " -SRC_URI[sha256sum] = "b8dd4368bb9c7f0b98188317ee0254dd8cc99d1e3a18d0ff146c855fe16c1d8c" +SRC_URI[sha256sum] = "64f404c1a650f27fc33da242e1f2df54952e3963a49e06e73f6940f3223ac344" S = "${TMPDIR}/work-shared/gcc-${PV}-${PR}/gcc-${PV}" # For dev release snapshotting @@ -122,3 +123,6 @@ EXTRA_OECONF_PATHS = "\ --with-sysroot=/not/exist \ --with-build-sysroot=${STAGING_DIR_TARGET} \ " + +# Is a binutils 2.26 issue, not gcc +CVE_CHECK_WHITELIST += "CVE-2021-37322" diff --git a/meta/recipes-devtools/gcc/gcc-cross-canadian_10.2.bb b/meta/recipes-devtools/gcc/gcc-cross-canadian_10.3.bb index bf53c5cd78..bf53c5cd78 100644 --- a/meta/recipes-devtools/gcc/gcc-cross-canadian_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-cross-canadian_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc-cross_10.2.bb b/meta/recipes-devtools/gcc/gcc-cross_10.3.bb index b43cca0c52..b43cca0c52 100644 --- a/meta/recipes-devtools/gcc/gcc-cross_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-cross_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc-crosssdk_10.2.bb b/meta/recipes-devtools/gcc/gcc-crosssdk_10.3.bb index 40a6c4feff..40a6c4feff 100644 --- a/meta/recipes-devtools/gcc/gcc-crosssdk_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-crosssdk_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc-runtime_10.2.bb b/meta/recipes-devtools/gcc/gcc-runtime_10.3.bb index dd430b57eb..dd430b57eb 100644 --- a/meta/recipes-devtools/gcc/gcc-runtime_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-runtime_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc-sanitizers_10.2.bb b/meta/recipes-devtools/gcc/gcc-sanitizers_10.3.bb index f3c7058114..f3c7058114 100644 --- a/meta/recipes-devtools/gcc/gcc-sanitizers_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-sanitizers_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc-source_10.2.bb b/meta/recipes-devtools/gcc/gcc-source_10.3.bb index b890fa33ea..b890fa33ea 100644 --- a/meta/recipes-devtools/gcc/gcc-source_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc-source_10.3.bb diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch index b9bca49dd8..4d7c7e3f18 100644 --- a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch +++ b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-35465.patch @@ -33,7 +33,7 @@ Signed-off-by: Pgowda <pgowda.cve@gmail.com> diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c --- a/gcc/config/arm/arm.c 2020-07-22 23:35:17.344384552 -0700 +++ b/gcc/config/arm/arm.c 2021-11-11 20:16:19.761241867 -0800 -@@ -3595,6 +3595,15 @@ arm_option_override (void) +@@ -3610,6 +3610,15 @@ arm_option_override (void) fix_cm3_ldrd = 0; } @@ -52,7 +52,7 @@ diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in --- a/gcc/config/arm/arm-cpus.in 2020-07-22 23:35:17.340384509 -0700 +++ b/gcc/config/arm/arm-cpus.in 2021-11-11 20:17:01.364573561 -0800 -@@ -190,6 +190,9 @@ define feature quirk_armv6kz +@@ -186,6 +186,9 @@ define feature quirk_armv6kz # Cortex-M3 LDRD quirk. define feature quirk_cm3_ldrd @@ -62,7 +62,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in # Don't use .cpu assembly directive define feature quirk_no_asmcpu -@@ -314,7 +317,7 @@ define fgroup DOTPROD NEON dotprod +@@ -322,7 +325,7 @@ define implied vfp_base MVE MVE_FP ALL_F # architectures. # xscale isn't really a 'quirk', but it isn't an architecture either and we # need to ignore it for matching purposes. @@ -71,7 +71,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in # Architecture entries # format: -@@ -1492,6 +1495,7 @@ begin cpu cortex-m33 +@@ -1524,6 +1527,7 @@ begin cpu cortex-m33 architecture armv8-m.main+dsp+fp option nofp remove ALL_FP option nodsp remove armv7em @@ -79,7 +79,7 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in costs v7m end cpu cortex-m33 -@@ -1501,6 +1505,7 @@ begin cpu cortex-m35p +@@ -1533,6 +1537,7 @@ begin cpu cortex-m35p architecture armv8-m.main+dsp+fp option nofp remove ALL_FP option nodsp remove armv7em @@ -87,10 +87,10 @@ diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in costs v7m end cpu cortex-m35p -@@ -1508,7 +1513,7 @@ begin cpu cortex-m55 - cname cortexm55 - tune flags LDSCHED - architecture armv8.1-m.main+mve.fp+fp.dp +@@ -1544,7 +1549,7 @@ begin cpu cortex-m55 + option nomve remove mve mve_float + option nofp remove ALL_FP mve_float + option nodsp remove MVE mve_float - isa quirk_no_asmcpu + isa quirk_no_asmcpu quirk_vlldm costs v7m @@ -113,7 +113,7 @@ diff --git a/gcc/config/arm/arm.opt b/gcc/config/arm/arm.opt diff -upr a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi --- a/gcc/doc/invoke.texi 2021-11-11 19:30:56.264523105 -0800 +++ b/gcc/doc/invoke.texi 2021-11-11 20:16:19.769241739 -0800 -@@ -773,6 +773,7 @@ Objective-C and Objective-C++ Dialects}. +@@ -774,6 +774,7 @@ Objective-C and Objective-C++ Dialects}. -mverbose-cost-dump @gol -mpure-code @gol -mcmse @gol @@ -121,7 +121,7 @@ diff -upr a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi -mfdpic} @emph{AVR Options} -@@ -21233,6 +21234,14 @@ Use multiply and add/subtract instructio +@@ -21266,6 +21267,14 @@ Use multiply and add/subtract instructio Do not use multiply and add/subtract instructions. diff --git a/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch new file mode 100644 index 0000000000..e0f4f7d32f --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0001-CVE-2021-42574.patch @@ -0,0 +1,2906 @@ +From 004bb936d6d5f177af26ad4905595e843d5665a5 Mon Sep 17 00:00:00 2001 +From: Lewis Hyatt <lhyatt@gmail.com> +Date: Tue, 14 Jul 2020 12:05:56 -0400 +Subject: [PATCH] diagnostics: Support conversion of tabs to spaces [PR49973] + [PR86904] + +Supports conversion of tabs to spaces when outputting diagnostics. Also +adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to +control how the column number is output, thereby resolving the two PRs. + +gcc/c-family/ChangeLog: + + PR other/86904 + * c-indentation.c (should_warn_for_misleading_indentation): Get + global tabstop from the new source. + * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which + is now a common option. + * c.opt: Likewise. + +gcc/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * common.opt: Handle -ftabstop here instead of in c-family + options. Add -fdiagnostics-column-unit= and + -fdiagnostics-column-origin= options. + * opts.c (common_handle_option): Handle the new options. + * diagnostic-format-json.cc (json_from_expanded_location): Add + diagnostic_context argument. Use it to convert column numbers as per + the new options. + (json_from_location_range): Likewise. + (json_from_fixit_hint): Likewise. + (json_end_diagnostic): Pass the new context argument to helper + functions above. Add "column-origin" field to the output. + (test_unknown_location): Add the new context argument to calls to + helper functions. + (test_bad_endpoints): Likewise. + * diagnostic-show-locus.c + (exploc_with_display_col::exploc_with_display_col): Support + tabstop parameter. + (layout_point::layout_point): Make use of class + exploc_with_display_col. + (layout_range::layout_range): Likewise. + (struct line_bounds): Clarify that the units are now always + display columns. Rename members accordingly. Add constructor. + (layout::print_source_line): Add support for tab expansion. + (make_range): Adapt to class layout_range changes. + (layout::maybe_add_location_range): Likewise. + (layout::layout): Adapt to class exploc_with_display_col changes. + (layout::calculate_x_offset_display): Support tabstop parameter. + (layout::print_annotation_line): Adapt to struct line_bounds changes. + (layout::print_line): Likewise. + (line_label::line_label): Add diagnostic_context argument. + (get_affected_range): Likewise. + (get_printed_columns): Likewise. + (layout::print_any_labels): Adapt to struct line_label changes. + (class correction): Add m_tabstop member. + (correction::correction): Add tabstop argument. + (correction::compute_display_cols): Use m_tabstop. + (class line_corrections): Add m_context member. + (line_corrections::line_corrections): Add diagnostic_context argument. + (line_corrections::add_hint): Use m_context to handle tabstops. + (layout::print_trailing_fixits): Adapt to class line_corrections + changes. + (test_layout_x_offset_display_utf8): Support tabstop parameter. + (test_layout_x_offset_display_tab): New selftest. + (test_one_liner_colorized_utf8): Likewise. + (test_tab_expansion): Likewise. + (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. + (diagnostic_show_locus_c_tests): Likewise. + (test_overlapped_fixit_printing): Adapt to helper class and + function changes. + (test_overlapped_fixit_printing_utf8): Likewise. + (test_overlapped_fixit_printing_2): Likewise. + * diagnostic.h (enum diagnostics_column_unit): New enum. + (struct diagnostic_context): Add members for the new options. + (diagnostic_converted_column): Declare. + (json_from_expanded_location): Add new context argument. + * diagnostic.c (diagnostic_initialize): Initialize new members. + (diagnostic_converted_column): New function. + (maybe_line_and_column): Be willing to output a column of 0. + (diagnostic_get_location_text): Convert column number as per the new + options. + (diagnostic_report_current_module): Likewise. + (assert_location_text): Add origin and column_unit arguments for + testing the new functionality. + (test_diagnostic_get_location_text): Test the new functionality. + * doc/invoke.texi: Document the new options and behavior. + * input.h (location_compute_display_column): Add tabstop argument. + * input.c (location_compute_display_column): Likewise. + (test_cpp_utf8): Add selftests for tab expansion. + * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the + new context argument to json_from_expanded_location(). + +libcpp/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, + which is now handled by diagnostic_context. + (class cpp_display_width_computation): New class. + (cpp_byte_column_to_display_column): Add optional tabstop argument. + (cpp_display_width): Likewise. + (cpp_display_column_to_byte_column): Likewise. + * charset.c + (cpp_display_width_computation::cpp_display_width_computation): New + function. + (cpp_display_width_computation::advance_display_cols): Likewise. + (compute_next_display_width): Removed and implemented this + functionality in a new function... + (cpp_display_width_computation::process_next_codepoint): ...here. + (cpp_byte_column_to_display_column): Added tabstop argument. + Reimplemented in terms of class cpp_display_width_computation. + (cpp_display_column_to_byte_column): Likewise. + * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now + handled by diagnostic_context. + +gcc/testsuite/ChangeLog: + + PR preprocessor/49973 + PR other/86904 + * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output + for new defaults. + * c-c++-common/Wmisleading-indentation.c: Likewise. + * c-c++-common/diagnostic-format-json-1.c: Likewise. + * c-c++-common/diagnostic-format-json-2.c: Likewise. + * c-c++-common/diagnostic-format-json-3.c: Likewise. + * c-c++-common/diagnostic-format-json-4.c: Likewise. + * c-c++-common/diagnostic-format-json-5.c: Likewise. + * c-c++-common/missing-close-symbol.c: Likewise. + * g++.dg/diagnostic/bad-binary-ops.C: Likewise. + * g++.dg/parse/error4.C: Likewise. + * g++.old-deja/g++.brendan/crash11.C: Likewise. + * g++.old-deja/g++.pt/overload2.C: Likewise. + * g++.old-deja/g++.robertl/eb109.C: Likewise. + * gcc.dg/analyzer/malloc-paths-9.c: Likewise. + * gcc.dg/bad-binary-ops.c: Likewise. + * gcc.dg/format/branch-1.c: Likewise. + * gcc.dg/format/pr79210.c: Likewise. + * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. + * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. + * gcc.dg/redecl-4.c: Likewise. + * gfortran.dg/diagnostic-format-json-1.F90: Likewise. + * gfortran.dg/diagnostic-format-json-2.F90: Likewise. + * gfortran.dg/diagnostic-format-json-3.F90: Likewise. + * go.dg/arrayclear.go: Add a comment explaining why adding a + comment was necessary to work around a dejagnu bug. + * c-c++-common/diagnostic-units-1.c: New test. + * c-c++-common/diagnostic-units-2.c: New test. + * c-c++-common/diagnostic-units-3.c: New test. + * c-c++-common/diagnostic-units-4.c: New test. + * c-c++-common/diagnostic-units-5.c: New test. + * c-c++-common/diagnostic-units-6.c: New test. + * c-c++-common/diagnostic-units-7.c: New test. + * c-c++-common/diagnostic-units-8.c: New test. + +CVE: CVE-2021-42574 +Upstream-Status: Backport [https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=004bb936d6d5f177af26ad4905595e843d5665a5] +Signed-off-by: Pgowda <pgowda.cve@gmail.com> +--- + gcc/c-family/c-indentation.c | 5 +- + gcc/c-family/c-opts.c | 6 - + gcc/c-family/c.opt | 4 - + gcc/common.opt | 21 + + gcc/diagnostic-format-json.cc | 55 +- + gcc/diagnostic-show-locus.c | 504 +++++++++++++----- + gcc/diagnostic.c | 113 +++- + gcc/diagnostic.h | 28 +- + gcc/doc/invoke.texi | 68 ++- + gcc/input.c | 72 ++- + gcc/input.h | 4 +- + gcc/opts.c | 14 + + .../c-c++-common/Wmisleading-indentation-3.c | 12 +- + .../c-c++-common/Wmisleading-indentation.c | 6 +- + .../c-c++-common/diagnostic-format-json-1.c | 5 + + .../c-c++-common/diagnostic-format-json-2.c | 5 + + .../c-c++-common/diagnostic-format-json-3.c | 5 + + .../c-c++-common/diagnostic-format-json-4.c | 9 + + .../c-c++-common/diagnostic-format-json-5.c | 9 + + .../c-c++-common/diagnostic-units-1.c | 28 + + .../c-c++-common/diagnostic-units-2.c | 28 + + .../c-c++-common/diagnostic-units-3.c | 28 + + .../c-c++-common/diagnostic-units-4.c | 28 + + .../c-c++-common/diagnostic-units-5.c | 28 + + .../c-c++-common/diagnostic-units-6.c | 28 + + .../c-c++-common/diagnostic-units-7.c | 28 + + .../c-c++-common/diagnostic-units-8.c | 28 + + .../c-c++-common/missing-close-symbol.c | 6 +- + .../g++.dg/diagnostic/bad-binary-ops.C | 8 +- + gcc/testsuite/g++.dg/parse/error4.C | 2 +- + .../g++.old-deja/g++.brendan/crash11.C | 4 +- + gcc/testsuite/g++.old-deja/g++.pt/overload2.C | 2 +- + .../g++.old-deja/g++.robertl/eb109.C | 4 +- + .../gcc.dg/analyzer/malloc-paths-9.c | 2 +- + gcc/testsuite/gcc.dg/bad-binary-ops.c | 8 +- + gcc/testsuite/gcc.dg/format/branch-1.c | 2 +- + gcc/testsuite/gcc.dg/format/pr79210.c | 2 +- + .../plugin/diagnostic-test-expressions-1.c | 16 +- + .../diagnostic-test-string-literals-1.c | 4 +- + gcc/testsuite/gcc.dg/redecl-4.c | 2 +- + .../gfortran.dg/diagnostic-format-json-1.F90 | 5 + + .../gfortran.dg/diagnostic-format-json-2.F90 | 5 + + .../gfortran.dg/diagnostic-format-json-3.F90 | 5 + + gcc/testsuite/go.dg/arrayclear.go | 3 + + gcc/tree-diagnostic-path.cc | 5 +- + libcpp/charset.c | 98 ++-- + libcpp/include/cpplib.h | 40 +- + libcpp/init.c | 1 - + 48 files changed, 1106 insertions(+), 287 deletions(-) + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-1.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-2.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-3.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-4.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-5.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-6.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-7.c + create mode 100644 gcc/testsuite/c-c++-common/diagnostic-units-8.c + +diff --git a/gcc/c-family/c-indentation.c b/gcc/c-family/c-indentation.c +--- a/gcc/c-family/c-indentation.c 2020-07-22 23:35:17.296384022 -0700 ++++ b/gcc/c-family/c-indentation.c 2021-12-25 01:20:53.475636694 -0800 +@@ -24,8 +24,7 @@ along with GCC; see the file COPYING3. + #include "c-common.h" + #include "c-indentation.h" + #include "selftest.h" +- +-extern cpp_options *cpp_opts; ++#include "diagnostic.h" + + /* Round up VIS_COLUMN to nearest tab stop. */ + +@@ -294,7 +293,7 @@ should_warn_for_misleading_indentation ( + expanded_location next_stmt_exploc = expand_location (next_stmt_loc); + expanded_location guard_exploc = expand_location (guard_loc); + +- const unsigned int tab_width = cpp_opts->tabstop; ++ const unsigned int tab_width = global_dc->tabstop; + + /* They must be in the same file. */ + if (next_stmt_exploc.file != body_exploc.file) +diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt +--- a/gcc/c-family/c.opt 2021-12-24 20:23:42.816809230 -0800 ++++ b/gcc/c-family/c.opt 2021-12-25 01:20:53.475636694 -0800 +@@ -1876,10 +1876,6 @@ Enum(strong_eval_order) String(some) Val + EnumValue + Enum(strong_eval_order) String(all) Value(2) + +-ftabstop= +-C ObjC C++ ObjC++ Joined RejectNegative UInteger +--ftabstop=<number> Distance between tab stops for column reporting. +- + ftemplate-backtrace-limit= + C++ ObjC++ Joined RejectNegative UInteger Var(template_backtrace_limit) Init(10) + Set the maximum number of template instantiation notes for a single warning or error. +diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c +--- a/gcc/c-family/c-opts.c 2021-12-24 20:23:44.824774786 -0800 ++++ b/gcc/c-family/c-opts.c 2021-12-25 01:20:53.475636694 -0800 +@@ -504,12 +504,6 @@ c_common_handle_option (size_t scode, co + cpp_opts->track_macro_expansion = 2; + break; + +- case OPT_ftabstop_: +- /* It is documented that we silently ignore silly values. */ +- if (value >= 1 && value <= 100) +- cpp_opts->tabstop = value; +- break; +- + case OPT_fexec_charset_: + cpp_opts->narrow_charset = arg; + break; +diff --git a/gcc/common.opt b/gcc/common.opt +--- a/gcc/common.opt 2021-12-24 20:23:42.480814993 -0800 ++++ b/gcc/common.opt 2021-12-25 01:20:53.475636694 -0800 +@@ -1325,6 +1325,14 @@ Enum(diagnostic_url_rule) String(always) + EnumValue + Enum(diagnostic_url_rule) String(auto) Value(DIAGNOSTICS_URL_AUTO) + ++fdiagnostics-column-unit= ++Common Joined RejectNegative Enum(diagnostics_column_unit) ++-fdiagnostics-column-unit=[display|byte] Select whether column numbers are output as display columns (default) or raw bytes. ++ ++fdiagnostics-column-origin= ++Common Joined RejectNegative UInteger ++-fdiagnostics-column-origin=<number> Set the number of the first column. The default is 1-based as per GNU style, but some utilities may expect 0-based, for example. ++ + fdiagnostics-format= + Common Joined RejectNegative Enum(diagnostics_output_format) + -fdiagnostics-format=[text|json] Select output format. +@@ -1334,6 +1342,15 @@ SourceInclude + diagnostic.h + + Enum ++Name(diagnostics_column_unit) Type(int) ++ ++EnumValue ++Enum(diagnostics_column_unit) String(display) Value(DIAGNOSTICS_COLUMN_UNIT_DISPLAY) ++ ++EnumValue ++Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE) ++ ++Enum + Name(diagnostics_output_format) Type(int) + + EnumValue +@@ -1362,6 +1379,10 @@ fdiagnostics-path-format= + Common Joined RejectNegative Var(flag_diagnostics_path_format) Enum(diagnostic_path_format) Init(DPF_INLINE_EVENTS) + Specify how to print any control-flow path associated with a diagnostic. + ++ftabstop= ++Common Joined RejectNegative UInteger ++-ftabstop=<number> Distance between tab stops for column reporting. ++ + Enum + Name(diagnostic_path_format) Type(int) + +diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c +--- a/gcc/diagnostic.c 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic.c 2021-12-25 01:23:41.300841207 -0800 +@@ -38,6 +38,7 @@ along with GCC; see the file COPYING3. + #include "selftest.h" + #include "selftest-diagnostic.h" + #include "opts.h" ++#include "cpplib.h" + + #ifdef HAVE_TERMIOS_H + # include <termios.h> +@@ -219,6 +220,9 @@ diagnostic_initialize (diagnostic_contex + context->min_margin_width = 0; + context->show_ruler_p = false; + context->parseable_fixits_p = false; ++ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY; ++ context->column_origin = 1; ++ context->tabstop = 8; + context->edit_context_ptr = NULL; + context->diagnostic_group_nesting_depth = 0; + context->diagnostic_group_emission_count = 0; +@@ -353,8 +357,51 @@ diagnostic_get_color_for_kind (diagnosti + return diagnostic_kind_color[kind]; + } + ++/* Given an expanded_location, convert the column (which is in 1-based bytes) ++ to the requested units, without converting the origin. ++ Return -1 if the column is invalid (<= 0). */ ++ ++static int ++convert_column_unit (enum diagnostics_column_unit column_unit, ++ int tabstop, ++ expanded_location s) ++{ ++ if (s.column <= 0) ++ return -1; ++ ++ switch (column_unit) ++ { ++ default: ++ gcc_unreachable (); ++ ++ case DIAGNOSTICS_COLUMN_UNIT_DISPLAY: ++ { ++ cpp_char_column_policy policy (tabstop, cpp_wcwidth); ++ return location_compute_display_column (s, policy); ++ } ++ ++ case DIAGNOSTICS_COLUMN_UNIT_BYTE: ++ return s.column; ++ } ++} ++ ++/* Given an expanded_location, convert the column (which is in 1-based bytes) ++ to the requested units and origin. Return -1 if the column is ++ invalid (<= 0). */ ++int ++diagnostic_converted_column (diagnostic_context *context, expanded_location s) ++{ ++ int one_based_col ++ = convert_column_unit (context->column_unit, context->tabstop, s); ++ if (one_based_col <= 0) ++ return -1; ++ return one_based_col + (context->column_origin - 1); ++} ++ + /* Return a formatted line and column ':%line:%column'. Elided if +- zero. The result is a statically allocated buffer. */ ++ line == 0 or col < 0. (A column of 0 may be valid due to the ++ -fdiagnostics-column-origin option.) ++ The result is a statically allocated buffer. */ + + static const char * + maybe_line_and_column (int line, int col) +@@ -363,8 +410,9 @@ maybe_line_and_column (int line, int col + + if (line) + { +- size_t l = snprintf (result, sizeof (result), +- col ? ":%d:%d" : ":%d", line, col); ++ size_t l ++ = snprintf (result, sizeof (result), ++ col >= 0 ? ":%d:%d" : ":%d", line, col); + gcc_checking_assert (l < sizeof (result)); + } + else +@@ -383,8 +431,14 @@ diagnostic_get_location_text (diagnostic + const char *locus_cs = colorize_start (pp_show_color (pp), "locus"); + const char *locus_ce = colorize_stop (pp_show_color (pp)); + const char *file = s.file ? s.file : progname; +- int line = strcmp (file, N_("<built-in>")) ? s.line : 0; +- int col = context->show_column ? s.column : 0; ++ int line = 0; ++ int col = -1; ++ if (strcmp (file, N_("<built-in>"))) ++ { ++ line = s.line; ++ if (context->show_column) ++ col = diagnostic_converted_column (context, s); ++ } + + const char *line_col = maybe_line_and_column (line, col); + return build_message_string ("%s%s%s:%s", locus_cs, file, +@@ -650,14 +704,20 @@ diagnostic_report_current_module (diagno + if (! MAIN_FILE_P (map)) + { + bool first = true; ++ expanded_location s = {}; + do + { + where = linemap_included_from (map); + map = linemap_included_from_linemap (line_table, map); +- const char *line_col +- = maybe_line_and_column (SOURCE_LINE (map, where), +- first && context->show_column +- ? SOURCE_COLUMN (map, where) : 0); ++ s.file = LINEMAP_FILE (map); ++ s.line = SOURCE_LINE (map, where); ++ int col = -1; ++ if (first && context->show_column) ++ { ++ s.column = SOURCE_COLUMN (map, where); ++ col = diagnostic_converted_column (context, s); ++ } ++ const char *line_col = maybe_line_and_column (s.line, col); + static const char *const msgs[] = + { + N_("In file included from"), +@@ -666,7 +726,7 @@ diagnostic_report_current_module (diagno + unsigned index = !first; + pp_verbatim (context->printer, "%s%s %r%s%s%R", + first ? "" : ",\n", _(msgs[index]), +- "locus", LINEMAP_FILE (map), line_col); ++ "locus", s.file, line_col); + first = false; + } + while (! MAIN_FILE_P (map)); +@@ -2042,10 +2102,15 @@ test_print_parseable_fixits_replace () + static void + assert_location_text (const char *expected_loc_text, + const char *filename, int line, int column, +- bool show_column) ++ bool show_column, ++ int origin = 1, ++ enum diagnostics_column_unit column_unit ++ = DIAGNOSTICS_COLUMN_UNIT_BYTE) + { + test_diagnostic_context dc; + dc.show_column = show_column; ++ dc.column_unit = column_unit; ++ dc.column_origin = origin; + + expanded_location xloc; + xloc.file = filename; +@@ -2069,7 +2134,10 @@ test_diagnostic_get_location_text () + assert_location_text ("PROGNAME:", NULL, 0, 0, true); + assert_location_text ("<built-in>:", "<built-in>", 42, 10, true); + assert_location_text ("foo.c:42:10:", "foo.c", 42, 10, true); +- assert_location_text ("foo.c:42:", "foo.c", 42, 0, true); ++ assert_location_text ("foo.c:42:9:", "foo.c", 42, 10, true, 0); ++ assert_location_text ("foo.c:42:1010:", "foo.c", 42, 10, true, 1001); ++ for (int origin = 0; origin != 2; ++origin) ++ assert_location_text ("foo.c:42:", "foo.c", 42, 0, true, origin); + assert_location_text ("foo.c:", "foo.c", 0, 10, true); + assert_location_text ("foo.c:42:", "foo.c", 42, 10, false); + assert_location_text ("foo.c:", "foo.c", 0, 10, false); +@@ -2077,6 +2145,41 @@ test_diagnostic_get_location_text () + maybe_line_and_column (INT_MAX, INT_MAX); + maybe_line_and_column (INT_MIN, INT_MIN); + ++ { ++ /* In order to test display columns vs byte columns, we need to create a ++ file for location_get_source_line() to read. */ ++ ++ const char *const content = "smile \xf0\x9f\x98\x82\n"; ++ const int line_bytes = strlen (content) - 1; ++ const int def_tabstop = 8; ++ const int display_width = cpp_display_width (content, line_bytes, ++ def_tabstop); ++ ASSERT_EQ (line_bytes - 2, display_width); ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ const char *const fname = tmp.get_filename (); ++ const int buf_len = strlen (fname) + 16; ++ char *const expected = XNEWVEC (char, buf_len); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 1, DIAGNOSTICS_COLUMN_UNIT_BYTE); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes - 1); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 0, DIAGNOSTICS_COLUMN_UNIT_BYTE); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 1, DIAGNOSTICS_COLUMN_UNIT_DISPLAY); ++ ++ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width - 1); ++ assert_location_text (expected, fname, 1, line_bytes, true, ++ 0, DIAGNOSTICS_COLUMN_UNIT_DISPLAY); ++ ++ XDELETEVEC (expected); ++ } ++ ++ + progname = old_progname; + } + +diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc +--- a/gcc/diagnostic-format-json.cc 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic-format-json.cc 2021-12-25 01:20:53.475636694 -0800 +@@ -23,6 +23,7 @@ along with GCC; see the file COPYING3. + #include "system.h" + #include "coretypes.h" + #include "diagnostic.h" ++#include "selftest-diagnostic.h" + #include "diagnostic-metadata.h" + #include "json.h" + #include "selftest.h" +@@ -43,21 +44,43 @@ static json::array *cur_children_array; + /* Generate a JSON object for LOC. */ + + json::value * +-json_from_expanded_location (location_t loc) ++json_from_expanded_location (diagnostic_context *context, location_t loc) + { + expanded_location exploc = expand_location (loc); + json::object *result = new json::object (); + if (exploc.file) + result->set ("file", new json::string (exploc.file)); + result->set ("line", new json::integer_number (exploc.line)); +- result->set ("column", new json::integer_number (exploc.column)); ++ ++ const enum diagnostics_column_unit orig_unit = context->column_unit; ++ struct ++ { ++ const char *name; ++ enum diagnostics_column_unit unit; ++ } column_fields[] = { ++ {"display-column", DIAGNOSTICS_COLUMN_UNIT_DISPLAY}, ++ {"byte-column", DIAGNOSTICS_COLUMN_UNIT_BYTE} ++ }; ++ int the_column = INT_MIN; ++ for (int i = 0; i != sizeof column_fields / sizeof (*column_fields); ++i) ++ { ++ context->column_unit = column_fields[i].unit; ++ const int col = diagnostic_converted_column (context, exploc); ++ result->set (column_fields[i].name, new json::integer_number (col)); ++ if (column_fields[i].unit == orig_unit) ++ the_column = col; ++ } ++ gcc_assert (the_column != INT_MIN); ++ result->set ("column", new json::integer_number (the_column)); ++ context->column_unit = orig_unit; + return result; + } + + /* Generate a JSON object for LOC_RANGE. */ + + static json::object * +-json_from_location_range (const location_range *loc_range, unsigned range_idx) ++json_from_location_range (diagnostic_context *context, ++ const location_range *loc_range, unsigned range_idx) + { + location_t caret_loc = get_pure_location (loc_range->m_loc); + +@@ -68,13 +91,13 @@ json_from_location_range (const location + location_t finish_loc = get_finish (loc_range->m_loc); + + json::object *result = new json::object (); +- result->set ("caret", json_from_expanded_location (caret_loc)); ++ result->set ("caret", json_from_expanded_location (context, caret_loc)); + if (start_loc != caret_loc + && start_loc != UNKNOWN_LOCATION) +- result->set ("start", json_from_expanded_location (start_loc)); ++ result->set ("start", json_from_expanded_location (context, start_loc)); + if (finish_loc != caret_loc + && finish_loc != UNKNOWN_LOCATION) +- result->set ("finish", json_from_expanded_location (finish_loc)); ++ result->set ("finish", json_from_expanded_location (context, finish_loc)); + + if (loc_range->m_label) + { +@@ -91,14 +114,14 @@ json_from_location_range (const location + /* Generate a JSON object for HINT. */ + + static json::object * +-json_from_fixit_hint (const fixit_hint *hint) ++json_from_fixit_hint (diagnostic_context *context, const fixit_hint *hint) + { + json::object *fixit_obj = new json::object (); + + location_t start_loc = hint->get_start_loc (); +- fixit_obj->set ("start", json_from_expanded_location (start_loc)); ++ fixit_obj->set ("start", json_from_expanded_location (context, start_loc)); + location_t next_loc = hint->get_next_loc (); +- fixit_obj->set ("next", json_from_expanded_location (next_loc)); ++ fixit_obj->set ("next", json_from_expanded_location (context, next_loc)); + fixit_obj->set ("string", new json::string (hint->get_string ())); + + return fixit_obj; +@@ -190,11 +213,13 @@ json_end_diagnostic (diagnostic_context + else + { + /* Otherwise, make diag_obj be the top-level object within the group; +- add a "children" array. */ ++ add a "children" array and record the column origin. */ + toplevel_array->append (diag_obj); + cur_group = diag_obj; + cur_children_array = new json::array (); + diag_obj->set ("children", cur_children_array); ++ diag_obj->set ("column-origin", ++ new json::integer_number (context->column_origin)); + } + + const rich_location *richloc = diagnostic->richloc; +@@ -205,7 +230,7 @@ json_end_diagnostic (diagnostic_context + for (unsigned int i = 0; i < richloc->get_num_locations (); i++) + { + const location_range *loc_range = richloc->get_range (i); +- json::object *loc_obj = json_from_location_range (loc_range, i); ++ json::object *loc_obj = json_from_location_range (context, loc_range, i); + if (loc_obj) + loc_array->append (loc_obj); + } +@@ -217,7 +242,7 @@ json_end_diagnostic (diagnostic_context + for (unsigned int i = 0; i < richloc->get_num_fixit_hints (); i++) + { + const fixit_hint *hint = richloc->get_fixit_hint (i); +- json::object *fixit_obj = json_from_fixit_hint (hint); ++ json::object *fixit_obj = json_from_fixit_hint (context, hint); + fixit_array->append (fixit_obj); + } + } +@@ -320,7 +345,8 @@ namespace selftest { + static void + test_unknown_location () + { +- delete json_from_expanded_location (UNKNOWN_LOCATION); ++ test_diagnostic_context dc; ++ delete json_from_expanded_location (&dc, UNKNOWN_LOCATION); + } + + /* Verify that we gracefully handle attempts to serialize bad +@@ -338,7 +364,8 @@ test_bad_endpoints () + loc_range.m_range_display_kind = SHOW_RANGE_WITH_CARET; + loc_range.m_label = NULL; + +- json::object *obj = json_from_location_range (&loc_range, 0); ++ test_diagnostic_context dc; ++ json::object *obj = json_from_location_range (&dc, &loc_range, 0); + /* We should have a "caret" value, but no "start" or "finish" values. */ + ASSERT_TRUE (obj != NULL); + ASSERT_TRUE (obj->get ("caret") != NULL); +diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h +--- a/gcc/diagnostic.h 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic.h 2021-12-25 01:20:53.479636627 -0800 +@@ -24,6 +24,20 @@ along with GCC; see the file COPYING3. + #include "pretty-print.h" + #include "diagnostic-core.h" + ++/* An enum for controlling what units to use for the column number ++ when diagnostics are output, used by the -fdiagnostics-column-unit option. ++ Tabs will be expanded or not according to the value of -ftabstop. The origin ++ (default 1) is controlled by -fdiagnostics-column-origin. */ ++ ++enum diagnostics_column_unit ++{ ++ /* The default from GCC 11 onwards: display columns. */ ++ DIAGNOSTICS_COLUMN_UNIT_DISPLAY, ++ ++ /* The behavior in GCC 10 and earlier: simple bytes. */ ++ DIAGNOSTICS_COLUMN_UNIT_BYTE ++}; ++ + /* Enum for overriding the standard output format. */ + + enum diagnostics_output_format +@@ -280,6 +294,15 @@ struct diagnostic_context + rest of the diagnostic. */ + bool parseable_fixits_p; + ++ /* What units to use when outputting the column number. */ ++ enum diagnostics_column_unit column_unit; ++ ++ /* The origin for the column number (1-based or 0-based typically). */ ++ int column_origin; ++ ++ /* The size of the tabstop for tab expansion. */ ++ int tabstop; ++ + /* If non-NULL, an edit_context to which fix-it hints should be + applied, for generating patches. */ + edit_context *edit_context_ptr; +@@ -458,6 +481,8 @@ diagnostic_same_line (const diagnostic_c + } + + extern const char *diagnostic_get_color_for_kind (diagnostic_t kind); ++extern int diagnostic_converted_column (diagnostic_context *context, ++ expanded_location s); + + /* Pure text formatting support functions. */ + extern char *file_name_as_prefix (diagnostic_context *, const char *); +@@ -470,6 +495,7 @@ extern void diagnostic_output_format_ini + /* Compute the number of digits in the decimal representation of an integer. */ + extern int num_digits (int); + +-extern json::value *json_from_expanded_location (location_t loc); ++extern json::value *json_from_expanded_location (diagnostic_context *context, ++ location_t loc); + + #endif /* ! GCC_DIAGNOSTIC_H */ +diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c +--- a/gcc/diagnostic-show-locus.c 2020-07-22 23:35:17.556386887 -0700 ++++ b/gcc/diagnostic-show-locus.c 2021-12-25 01:20:53.479636627 -0800 +@@ -175,9 +175,10 @@ enum column_unit { + class exploc_with_display_col : public expanded_location + { + public: +- exploc_with_display_col (const expanded_location &exploc) ++ exploc_with_display_col (const expanded_location &exploc, int tabstop) + : expanded_location (exploc), +- m_display_col (location_compute_display_column (exploc)) {} ++ m_display_col (location_compute_display_column (exploc, tabstop)) ++ {} + + int m_display_col; + }; +@@ -189,11 +190,11 @@ class exploc_with_display_col : public e + class layout_point + { + public: +- layout_point (const expanded_location &exploc) ++ layout_point (const exploc_with_display_col &exploc) + : m_line (exploc.line) + { + m_columns[CU_BYTES] = exploc.column; +- m_columns[CU_DISPLAY_COLS] = location_compute_display_column (exploc); ++ m_columns[CU_DISPLAY_COLS] = exploc.m_display_col; + } + + linenum_type m_line; +@@ -205,10 +206,10 @@ class layout_point + class layout_range + { + public: +- layout_range (const expanded_location *start_exploc, +- const expanded_location *finish_exploc, ++ layout_range (const exploc_with_display_col &start_exploc, ++ const exploc_with_display_col &finish_exploc, + enum range_display_kind range_display_kind, +- const expanded_location *caret_exploc, ++ const exploc_with_display_col &caret_exploc, + unsigned original_idx, + const range_label *label); + +@@ -226,22 +227,18 @@ class layout_range + + /* A struct for use by layout::print_source_line for telling + layout::print_annotation_line the extents of the source line that +- it printed, so that underlines can be clipped appropriately. */ ++ it printed, so that underlines can be clipped appropriately. Units ++ are 1-based display columns. */ + + struct line_bounds + { +- int m_first_non_ws; +- int m_last_non_ws; ++ int m_first_non_ws_disp_col; ++ int m_last_non_ws_disp_col; + +- void convert_to_display_cols (char_span line) ++ line_bounds () + { +- m_first_non_ws = cpp_byte_column_to_display_column (line.get_buffer (), +- line.length (), +- m_first_non_ws); +- +- m_last_non_ws = cpp_byte_column_to_display_column (line.get_buffer (), +- line.length (), +- m_last_non_ws); ++ m_first_non_ws_disp_col = INT_MAX; ++ m_last_non_ws_disp_col = 0; + } + }; + +@@ -351,8 +348,8 @@ class layout + private: + bool will_show_line_p (linenum_type row) const; + void print_leading_fixits (linenum_type row); +- void print_source_line (linenum_type row, const char *line, int line_bytes, +- line_bounds *lbounds_out); ++ line_bounds print_source_line (linenum_type row, const char *line, ++ int line_bytes); + bool should_print_annotation_line_p (linenum_type row) const; + void start_annotation_line (char margin_char = ' ') const; + void print_annotation_line (linenum_type row, const line_bounds lbounds); +@@ -513,16 +510,16 @@ colorizer::get_color_by_name (const char + Initialize various layout_point fields from expanded_location + equivalents; we've already filtered on file. */ + +-layout_range::layout_range (const expanded_location *start_exploc, +- const expanded_location *finish_exploc, ++layout_range::layout_range (const exploc_with_display_col &start_exploc, ++ const exploc_with_display_col &finish_exploc, + enum range_display_kind range_display_kind, +- const expanded_location *caret_exploc, ++ const exploc_with_display_col &caret_exploc, + unsigned original_idx, + const range_label *label) +-: m_start (*start_exploc), +- m_finish (*finish_exploc), ++: m_start (start_exploc), ++ m_finish (finish_exploc), + m_range_display_kind (range_display_kind), +- m_caret (*caret_exploc), ++ m_caret (caret_exploc), + m_original_idx (original_idx), + m_label (label) + { +@@ -646,6 +643,9 @@ layout_range::intersects_line_p (linenum + + #if CHECKING_P + ++/* Default for when we don't care what the tab expansion is set to. */ ++static const int def_tabstop = 8; ++ + /* Create some expanded locations for testing layout_range. The filename + member of the explocs is set to the empty string. This member will only be + inspected by the calls to location_compute_display_column() made from the +@@ -662,8 +662,11 @@ make_range (int start_line, int start_co + = {"", start_line, start_col, NULL, false}; + const expanded_location finish_exploc + = {"", end_line, end_col, NULL, false}; +- return layout_range (&start_exploc, &finish_exploc, SHOW_RANGE_WITHOUT_CARET, +- &start_exploc, 0, NULL); ++ return layout_range (exploc_with_display_col (start_exploc, def_tabstop), ++ exploc_with_display_col (finish_exploc, def_tabstop), ++ SHOW_RANGE_WITHOUT_CARET, ++ exploc_with_display_col (start_exploc, def_tabstop), ++ 0, NULL); + } + + /* Selftests for layout_range::contains_point and +@@ -964,7 +967,7 @@ layout::layout (diagnostic_context * con + : m_context (context), + m_pp (context->printer), + m_primary_loc (richloc->get_range (0)->m_loc), +- m_exploc (richloc->get_expanded_location (0)), ++ m_exploc (richloc->get_expanded_location (0), context->tabstop), + m_colorizer (context, diagnostic_kind), + m_colorize_source_p (context->colorize_source_p), + m_show_labels_p (context->show_labels_p), +@@ -1060,7 +1063,10 @@ layout::maybe_add_location_range (const + + /* Everything is now known to be in the correct source file, + but it may require further sanitization. */ +- layout_range ri (&start, &finish, loc_range->m_range_display_kind, &caret, ++ layout_range ri (exploc_with_display_col (start, m_context->tabstop), ++ exploc_with_display_col (finish, m_context->tabstop), ++ loc_range->m_range_display_kind, ++ exploc_with_display_col (caret, m_context->tabstop), + original_idx, loc_range->m_label); + + /* If we have a range that finishes before it starts (perhaps +@@ -1394,7 +1400,7 @@ layout::calculate_x_offset_display () + = get_line_bytes_without_trailing_whitespace (line.get_buffer (), + line.length ()); + int eol_display_column +- = cpp_display_width (line.get_buffer (), line_bytes); ++ = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop); + if (caret_display_column > eol_display_column + || !caret_display_column) + { +@@ -1445,16 +1451,13 @@ layout::calculate_x_offset_display () + } + + /* Print line ROW of source code, potentially colorized at any ranges, and +- populate *LBOUNDS_OUT. +- LINE is the source line (not necessarily 0-terminated) and LINE_BYTES +- is its length in bytes. +- This function deals only with byte offsets, not display columns, so +- m_x_offset_display must be converted from display to byte units. In +- particular, LINE_BYTES and LBOUNDS_OUT are in bytes. */ ++ return the line bounds. LINE is the source line (not necessarily ++ 0-terminated) and LINE_BYTES is its length in bytes. In order to handle both ++ colorization and tab expansion, this function tracks the line position in ++ both byte and display column units. */ + +-void +-layout::print_source_line (linenum_type row, const char *line, int line_bytes, +- line_bounds *lbounds_out) ++line_bounds ++layout::print_source_line (linenum_type row, const char *line, int line_bytes) + { + m_colorizer.set_normal_text (); + +@@ -1469,30 +1472,29 @@ layout::print_source_line (linenum_type + else + pp_space (m_pp); + +- /* We will stop printing the source line at any trailing whitespace, and start +- printing it as per m_x_offset_display. */ ++ /* We will stop printing the source line at any trailing whitespace. */ + line_bytes = get_line_bytes_without_trailing_whitespace (line, + line_bytes); +- int x_offset_bytes = 0; +- if (m_x_offset_display) +- { +- x_offset_bytes = cpp_display_column_to_byte_column (line, line_bytes, +- m_x_offset_display); +- /* In case the leading portion of the line that will be skipped over ends +- with a character with wcwidth > 1, then it is possible we skipped too +- much, so account for that by padding with spaces. */ +- const int overage +- = cpp_byte_column_to_display_column (line, line_bytes, x_offset_bytes) +- - m_x_offset_display; +- for (int column = 0; column < overage; ++column) +- pp_space (m_pp); +- line += x_offset_bytes; +- } + +- /* Print the line. */ +- int first_non_ws = INT_MAX; +- int last_non_ws = 0; +- for (int col_byte = 1 + x_offset_bytes; col_byte <= line_bytes; col_byte++) ++ /* This object helps to keep track of which display column we are at, which is ++ necessary for computing the line bounds in display units, for doing ++ tab expansion, and for implementing m_x_offset_display. */ ++ cpp_display_width_computation dw (line, line_bytes, m_context->tabstop); ++ ++ /* Skip the first m_x_offset_display display columns. In case the leading ++ portion that will be skipped ends with a character with wcwidth > 1, then ++ it is possible we skipped too much, so account for that by padding with ++ spaces. Note that this does the right thing too in case a tab was the last ++ character to be skipped over; the tab is effectively replaced by the ++ correct number of trailing spaces needed to offset by the desired number of ++ display columns. */ ++ for (int skipped_display_cols = dw.advance_display_cols (m_x_offset_display); ++ skipped_display_cols > m_x_offset_display; --skipped_display_cols) ++ pp_space (m_pp); ++ ++ /* Print the line and compute the line_bounds. */ ++ line_bounds lbounds; ++ while (!dw.done ()) + { + /* Assuming colorization is enabled for the caret and underline + characters, we may also colorize the associated characters +@@ -1510,7 +1512,8 @@ layout::print_source_line (linenum_type + { + bool in_range_p; + point_state state; +- in_range_p = get_state_at_point (row, col_byte, ++ const int start_byte_col = dw.bytes_processed () + 1; ++ in_range_p = get_state_at_point (row, start_byte_col, + 0, INT_MAX, + CU_BYTES, + &state); +@@ -1519,22 +1522,44 @@ layout::print_source_line (linenum_type + else + m_colorizer.set_normal_text (); + } +- char c = *line; +- if (c == '\0' || c == '\t' || c == '\r') +- c = ' '; +- if (c != ' ') ++ ++ /* Get the display width of the next character to be output, expanding ++ tabs and replacing some control bytes with spaces as necessary. */ ++ const char *c = dw.next_byte (); ++ const int start_disp_col = dw.display_cols_processed () + 1; ++ const int this_display_width = dw.process_next_codepoint (); ++ if (*c == '\t') ++ { ++ /* The returned display width is the number of spaces into which the ++ tab should be expanded. */ ++ for (int i = 0; i != this_display_width; ++i) ++ pp_space (m_pp); ++ continue; ++ } ++ if (*c == '\0' || *c == '\r') + { +- last_non_ws = col_byte; +- if (first_non_ws == INT_MAX) +- first_non_ws = col_byte; ++ /* cpp_wcwidth() promises to return 1 for all control bytes, and we ++ want to output these as a single space too, so this case is ++ actually the same as the '\t' case. */ ++ gcc_assert (this_display_width == 1); ++ pp_space (m_pp); ++ continue; + } +- pp_character (m_pp, c); +- line++; ++ ++ /* We have a (possibly multibyte) character to output; update the line ++ bounds if it is not whitespace. */ ++ if (*c != ' ') ++ { ++ lbounds.m_last_non_ws_disp_col = dw.display_cols_processed (); ++ if (lbounds.m_first_non_ws_disp_col == INT_MAX) ++ lbounds.m_first_non_ws_disp_col = start_disp_col; ++ } ++ ++ /* Output the character. */ ++ while (c != dw.next_byte ()) pp_character (m_pp, *c++); + } + print_newline (); +- +- lbounds_out->m_first_non_ws = first_non_ws; +- lbounds_out->m_last_non_ws = last_non_ws; ++ return lbounds; + } + + /* Determine if we should print an annotation line for ROW. +@@ -1576,14 +1601,13 @@ layout::start_annotation_line (char marg + } + + /* Print a line consisting of the caret/underlines for the given +- source line. This function works with display columns, rather than byte +- counts; in particular, LBOUNDS should be in display column units. */ ++ source line. */ + + void + layout::print_annotation_line (linenum_type row, const line_bounds lbounds) + { + int x_bound = get_x_bound_for_row (row, m_exploc.m_display_col, +- lbounds.m_last_non_ws); ++ lbounds.m_last_non_ws_disp_col); + + start_annotation_line (); + pp_space (m_pp); +@@ -1593,8 +1617,8 @@ layout::print_annotation_line (linenum_t + bool in_range_p; + point_state state; + in_range_p = get_state_at_point (row, column, +- lbounds.m_first_non_ws, +- lbounds.m_last_non_ws, ++ lbounds.m_first_non_ws_disp_col, ++ lbounds.m_last_non_ws_disp_col, + CU_DISPLAY_COLS, + &state); + if (in_range_p) +@@ -1631,12 +1655,14 @@ layout::print_annotation_line (linenum_t + class line_label + { + public: +- line_label (int state_idx, int column, label_text text) ++ line_label (diagnostic_context *context, int state_idx, int column, ++ label_text text) + : m_state_idx (state_idx), m_column (column), + m_text (text), m_label_line (0), m_has_vbar (true) + { + const int bytes = strlen (text.m_buffer); +- m_display_width = cpp_display_width (text.m_buffer, bytes); ++ m_display_width ++ = cpp_display_width (text.m_buffer, bytes, context->tabstop); + } + + /* Sorting is primarily by column, then by state index. */ +@@ -1696,7 +1722,7 @@ layout::print_any_labels (linenum_type r + if (text.m_buffer == NULL) + continue; + +- labels.safe_push (line_label (i, disp_col, text)); ++ labels.safe_push (line_label (m_context, i, disp_col, text)); + } + } + +@@ -1976,7 +2002,8 @@ public: + + /* Get the range of bytes or display columns that HINT would affect. */ + static column_range +-get_affected_range (const fixit_hint *hint, enum column_unit col_unit) ++get_affected_range (diagnostic_context *context, ++ const fixit_hint *hint, enum column_unit col_unit) + { + expanded_location exploc_start = expand_location (hint->get_start_loc ()); + expanded_location exploc_finish = expand_location (hint->get_next_loc ()); +@@ -1986,11 +2013,13 @@ get_affected_range (const fixit_hint *hi + int finish_column; + if (col_unit == CU_DISPLAY_COLS) + { +- start_column = location_compute_display_column (exploc_start); ++ start_column ++ = location_compute_display_column (exploc_start, context->tabstop); + if (hint->insertion_p ()) + finish_column = start_column - 1; + else +- finish_column = location_compute_display_column (exploc_finish); ++ finish_column ++ = location_compute_display_column (exploc_finish, context->tabstop); + } + else + { +@@ -2003,12 +2032,12 @@ get_affected_range (const fixit_hint *hi + /* Get the range of display columns that would be printed for HINT. */ + + static column_range +-get_printed_columns (const fixit_hint *hint) ++get_printed_columns (diagnostic_context *context, const fixit_hint *hint) + { + expanded_location exploc = expand_location (hint->get_start_loc ()); +- int start_column = location_compute_display_column (exploc); +- int hint_width = cpp_display_width (hint->get_string (), +- hint->get_length ()); ++ int start_column = location_compute_display_column (exploc, context->tabstop); ++ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (), ++ context->tabstop); + int final_hint_column = start_column + hint_width - 1; + if (hint->insertion_p ()) + { +@@ -2018,7 +2047,8 @@ get_printed_columns (const fixit_hint *h + { + exploc = expand_location (hint->get_next_loc ()); + --exploc.column; +- int finish_column = location_compute_display_column (exploc); ++ int finish_column ++ = location_compute_display_column (exploc, context->tabstop); + return column_range (start_column, + MAX (finish_column, final_hint_column)); + } +@@ -2035,12 +2065,14 @@ public: + correction (column_range affected_bytes, + column_range affected_columns, + column_range printed_columns, +- const char *new_text, size_t new_text_len) ++ const char *new_text, size_t new_text_len, ++ int tabstop) + : m_affected_bytes (affected_bytes), + m_affected_columns (affected_columns), + m_printed_columns (printed_columns), + m_text (xstrdup (new_text)), + m_byte_length (new_text_len), ++ m_tabstop (tabstop), + m_alloc_sz (new_text_len + 1) + { + compute_display_cols (); +@@ -2058,7 +2090,7 @@ public: + + void compute_display_cols () + { +- m_display_cols = cpp_display_width (m_text, m_byte_length); ++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop); + } + + void overwrite (int dst_offset, const char_span &src_span) +@@ -2086,6 +2118,7 @@ public: + char *m_text; + size_t m_byte_length; /* Not including null-terminator. */ + int m_display_cols; ++ int m_tabstop; + size_t m_alloc_sz; + }; + +@@ -2121,13 +2154,15 @@ correction::ensure_terminated () + class line_corrections + { + public: +- line_corrections (const char *filename, linenum_type row) +- : m_filename (filename), m_row (row) ++ line_corrections (diagnostic_context *context, const char *filename, ++ linenum_type row) ++ : m_context (context), m_filename (filename), m_row (row) + {} + ~line_corrections (); + + void add_hint (const fixit_hint *hint); + ++ diagnostic_context *m_context; + const char *m_filename; + linenum_type m_row; + auto_vec <correction *> m_corrections; +@@ -2173,9 +2208,10 @@ source_line::source_line (const char *fi + void + line_corrections::add_hint (const fixit_hint *hint) + { +- column_range affected_bytes = get_affected_range (hint, CU_BYTES); +- column_range affected_columns = get_affected_range (hint, CU_DISPLAY_COLS); +- column_range printed_columns = get_printed_columns (hint); ++ column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES); ++ column_range affected_columns = get_affected_range (m_context, hint, ++ CU_DISPLAY_COLS); ++ column_range printed_columns = get_printed_columns (m_context, hint); + + /* Potentially consolidate. */ + if (!m_corrections.is_empty ()) +@@ -2243,7 +2279,8 @@ line_corrections::add_hint (const fixit_ + affected_columns, + printed_columns, + hint->get_string (), +- hint->get_length ())); ++ hint->get_length (), ++ m_context->tabstop)); + } + + /* If there are any fixit hints on source line ROW, print them. +@@ -2257,7 +2294,7 @@ layout::print_trailing_fixits (linenum_t + { + /* Build a list of correction instances for the line, + potentially consolidating hints (for the sake of readability). */ +- line_corrections corrections (m_exploc.file, row); ++ line_corrections corrections (m_context, m_exploc.file, row); + for (unsigned int i = 0; i < m_fixit_hints.length (); i++) + { + const fixit_hint *hint = m_fixit_hints[i]; +@@ -2499,15 +2536,11 @@ layout::print_line (linenum_type row) + if (!line) + return; + +- line_bounds lbounds; + print_leading_fixits (row); +- print_source_line (row, line.get_buffer (), line.length (), &lbounds); ++ const line_bounds lbounds ++ = print_source_line (row, line.get_buffer (), line.length ()); + if (should_print_annotation_line_p (row)) +- { +- if (lbounds.m_first_non_ws != INT_MAX) +- lbounds.convert_to_display_cols (line); +- print_annotation_line (row, lbounds); +- } ++ print_annotation_line (row, lbounds); + if (m_show_labels_p) + print_any_labels (row); + print_trailing_fixits (row); +@@ -2670,9 +2703,11 @@ test_layout_x_offset_display_utf8 (const + + char_span lspan = location_get_source_line (tmp.get_filename (), 1); + ASSERT_EQ (line_display_cols, +- cpp_display_width (lspan.get_buffer (), lspan.length ())); ++ cpp_display_width (lspan.get_buffer (), lspan.length (), ++ def_tabstop)); + ASSERT_EQ (line_display_cols, +- location_compute_display_column (expand_location (line_end))); ++ location_compute_display_column (expand_location (line_end), ++ def_tabstop)); + ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1), + "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8)); + +@@ -2774,6 +2809,111 @@ test_layout_x_offset_display_utf8 (const + + } + ++static void ++test_layout_x_offset_display_tab (const line_table_case &case_) ++{ ++ const char *content ++ = "This line is very long, so that we can use it to test the logic for " ++ "clipping long lines. Also this: `\t' is a tab that occupies 1 byte and " ++ "a variable number of display columns, starting at column #103.\n"; ++ ++ /* Number of bytes in the line, subtracting one to remove the newline. */ ++ const int line_bytes = strlen (content) - 1; ++ ++ /* The column where the tab begins. Byte or display is the same as there are ++ no multibyte characters earlier on the line. */ ++ const int tab_col = 103; ++ ++ /* Effective extra size of the tab beyond what a single space would have taken ++ up, indexed by tabstop. */ ++ static const int num_tabstops = 11; ++ int extra_width[num_tabstops]; ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ const int this_tab_size = tabstop - (tab_col - 1) % tabstop; ++ extra_width[tabstop] = this_tab_size - 1; ++ } ++ /* Example of this calculation: if tabstop is 10, the tab starting at column ++ #103 has to expand into 8 spaces, covering columns 103-110, so that the ++ next character is at column #111. So it takes up 7 more columns than ++ a space would have taken up. */ ++ ASSERT_EQ (7, extra_width[10]); ++ ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ line_table_test ltt (case_); ++ ++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1); ++ ++ location_t line_end = linemap_position_for_column (line_table, line_bytes); ++ ++ /* Don't attempt to run the tests if column data might be unavailable. */ ++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Check that cpp_display_width handles the tabs as expected. */ ++ char_span lspan = location_get_source_line (tmp.get_filename (), 1); ++ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1))); ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ ASSERT_EQ (line_bytes + extra_width[tabstop], ++ cpp_display_width (lspan.get_buffer (), lspan.length (), ++ tabstop)); ++ ASSERT_EQ (line_bytes + extra_width[tabstop], ++ location_compute_display_column (expand_location (line_end), ++ tabstop)); ++ } ++ ++ /* Check that the tab is expanded to the expected number of spaces. */ ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ tab_col + 1)); ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ const char *out = pp_formatted_text (dc.printer); ++ ASSERT_EQ (NULL, strchr (out, '\t')); ++ const char *left_quote = strchr (out, '`'); ++ const char *right_quote = strchr (out, '\''); ++ ASSERT_NE (NULL, left_quote); ++ ASSERT_NE (NULL, right_quote); ++ ASSERT_EQ (right_quote - left_quote, extra_width[tabstop] + 2); ++ } ++ ++ /* Check that the line is offset properly and that the tab is broken up ++ into the expected number of spaces when it is the last character skipped ++ over. */ ++ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ static const int small_width = 24; ++ dc.caret_max_width = small_width - 4; ++ dc.min_margin_width = test_left_margin - test_linenum_sep + 1; ++ dc.show_line_numbers_p = true; ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ++ /* We have arranged things so that two columns will be printed before ++ the caret. If the tab results in more than one space, this should ++ produce two spaces in the output; otherwise, it will be a single space ++ preceded by the opening quote before the tab character. */ ++ const char *output1 ++ = " 1 | ' is a tab that occupies 1 byte and a variable number of " ++ "display columns, starting at column #103.\n" ++ " | ^\n\n"; ++ const char *output2 ++ = " 1 | ` ' is a tab that occupies 1 byte and a variable number of " ++ "display columns, starting at column #103.\n" ++ " | ^\n\n"; ++ const char *expected_output = (extra_width[tabstop] ? output1 : output2); ++ ASSERT_STREQ (expected_output, pp_formatted_text (dc.printer)); ++ } ++} ++ ++ + /* Verify that diagnostic_show_locus works sanely on UNKNOWN_LOCATION. */ + + static void +@@ -3854,6 +3994,27 @@ test_one_liner_labels_utf8 () + } + } + ++/* Make sure that colorization codes don't interrupt a multibyte ++ sequence, which would corrupt it. */ ++static void ++test_one_liner_colorized_utf8 () ++{ ++ test_diagnostic_context dc; ++ dc.colorize_source_p = true; ++ diagnostic_color_init (&dc, DIAGNOSTICS_COLOR_YES); ++ const location_t pi = linemap_position_for_column (line_table, 12); ++ rich_location richloc (line_table, pi); ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ++ /* In order to avoid having the test depend on exactly how the colorization ++ was effected, just confirm there are two pi characters in the output. */ ++ const char *result = pp_formatted_text (dc.printer); ++ const char *null_term = result + strlen (result); ++ const char *first_pi = strstr (result, "\xcf\x80"); ++ ASSERT_TRUE (first_pi && first_pi <= null_term - 2); ++ ASSERT_STR_CONTAINS (first_pi + 2, "\xcf\x80"); ++} ++ + /* Run the various one-liner tests. */ + + static void +@@ -3884,8 +4045,10 @@ test_diagnostic_show_locus_one_liner_utf + ASSERT_EQ (31, LOCATION_COLUMN (line_end)); + + char_span lspan = location_get_source_line (tmp.get_filename (), 1); +- ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length ())); +- ASSERT_EQ (25, location_compute_display_column (expand_location (line_end))); ++ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (), ++ def_tabstop)); ++ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end), ++ def_tabstop)); + + test_one_liner_simple_caret_utf8 (); + test_one_liner_caret_and_range_utf8 (); +@@ -3900,6 +4063,7 @@ test_diagnostic_show_locus_one_liner_utf + test_one_liner_many_fixits_1_utf8 (); + test_one_liner_many_fixits_2_utf8 (); + test_one_liner_labels_utf8 (); ++ test_one_liner_colorized_utf8 (); + } + + /* Verify that gcc_rich_location::add_location_if_nearby works. */ +@@ -4272,25 +4436,28 @@ test_overlapped_fixit_printing (const li + /* Unit-test the line_corrections machinery. */ + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (12, 12), get_affected_range (hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0)); ++ get_affected_range (&dc, hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (12, 12), ++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (18, 18), get_affected_range (hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1)); ++ get_affected_range (&dc, hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (18, 18), ++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); +- ASSERT_EQ (column_range (29, 28), get_affected_range (hint_2, CU_BYTES)); + ASSERT_EQ (column_range (29, 28), +- get_affected_range (hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (29, 29), get_printed_columns (hint_2)); ++ get_affected_range (&dc, hint_2, CU_BYTES)); ++ ASSERT_EQ (column_range (29, 28), ++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (tmp.get_filename (), 1); ++ line_corrections lc (&dc, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4484,25 +4651,28 @@ test_overlapped_fixit_printing_utf8 (con + /* Unit-test the line_corrections machinery. */ + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (14, 14), get_affected_range (hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (14, 14), ++ get_affected_range (&dc, hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0)); ++ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (22, 22), get_affected_range (hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (22, 22), ++ get_affected_range (&dc, hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1)); ++ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); +- ASSERT_EQ (column_range (35, 34), get_affected_range (hint_2, CU_BYTES)); ++ ASSERT_EQ (column_range (35, 34), ++ get_affected_range (&dc, hint_2, CU_BYTES)); + ASSERT_EQ (column_range (30, 29), +- get_affected_range (hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (30, 30), get_printed_columns (hint_2)); ++ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (tmp.get_filename (), 1); ++ line_corrections lc (&dc, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4689,6 +4859,8 @@ test_overlapped_fixit_printing_2 (const + + /* Two insertions, in the wrong order. */ + { ++ test_diagnostic_context dc; ++ + rich_location richloc (line_table, col_20); + richloc.add_fixit_insert_before (col_23, "{"); + richloc.add_fixit_insert_before (col_21, "}"); +@@ -4696,14 +4868,15 @@ test_overlapped_fixit_printing_2 (const + /* These fixits should be accepted; they can't be consolidated. */ + ASSERT_EQ (2, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); +- ASSERT_EQ (column_range (23, 22), get_affected_range (hint_0, CU_BYTES)); +- ASSERT_EQ (column_range (23, 23), get_printed_columns (hint_0)); ++ ASSERT_EQ (column_range (23, 22), ++ get_affected_range (&dc, hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); +- ASSERT_EQ (column_range (21, 20), get_affected_range (hint_1, CU_BYTES)); +- ASSERT_EQ (column_range (21, 21), get_printed_columns (hint_1)); ++ ASSERT_EQ (column_range (21, 20), ++ get_affected_range (&dc, hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1)); + + /* Verify that they're printed correctly. */ +- test_diagnostic_context dc; + diagnostic_show_locus (&dc, &richloc, DK_ERROR); + ASSERT_STREQ (" int a5[][0][0] = { 1, 2 };\n" + " ^\n" +@@ -4955,6 +5128,65 @@ test_fixit_deletion_affecting_newline (c + pp_formatted_text (dc.printer)); + } + ++static void ++test_tab_expansion (const line_table_case &case_) ++{ ++ /* Create a tempfile and write some text to it. This example uses a tabstop ++ of 8, as the column numbers attempt to indicate: ++ ++ .....................000.01111111111.22222333333 display ++ .....................123.90123456789.56789012345 columns */ ++ const char *content = " \t This: `\t' is a tab.\n"; ++ /* ....................000 00000011111 11111222222 byte ++ ....................123 45678901234 56789012345 columns */ ++ ++ const int tabstop = 8; ++ const int first_non_ws_byte_col = 7; ++ const int right_quote_byte_col = 15; ++ const int last_byte_col = 25; ++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop)); ++ ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content); ++ line_table_test ltt (case_); ++ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1); ++ ++ /* Don't attempt to run the tests if column data might be unavailable. */ ++ location_t line_end = linemap_position_for_column (line_table, last_byte_col); ++ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Check that the leading whitespace with mixed tabs and spaces is expanded ++ into 11 spaces. Recall that print_line() also puts one space before ++ everything too. */ ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ first_non_ws_byte_col)); ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ASSERT_STREQ (" This: ` ' is a tab.\n" ++ " ^\n", ++ pp_formatted_text (dc.printer)); ++ } ++ ++ /* Confirm the display width was tracked correctly across the internal tab ++ as well. */ ++ { ++ test_diagnostic_context dc; ++ dc.tabstop = tabstop; ++ rich_location richloc (line_table, ++ linemap_position_for_column (line_table, ++ right_quote_byte_col)); ++ layout test_layout (&dc, &richloc, DK_ERROR); ++ test_layout.print_line (1); ++ ASSERT_STREQ (" This: ` ' is a tab.\n" ++ " ^\n", ++ pp_formatted_text (dc.printer)); ++ } ++} ++ + /* Verify that line numbers are correctly printed for the case of + a multiline range in which the width of the line numbers changes + (e.g. from "9" to "10"). */ +@@ -5012,6 +5244,7 @@ diagnostic_show_locus_c_tests () + test_layout_range_for_multiple_lines (); + + for_each_line_table_case (test_layout_x_offset_display_utf8); ++ for_each_line_table_case (test_layout_x_offset_display_tab); + + test_get_line_bytes_without_trailing_whitespace (); + +@@ -5029,6 +5262,7 @@ diagnostic_show_locus_c_tests () + for_each_line_table_case (test_fixit_insert_containing_newline_2); + for_each_line_table_case (test_fixit_replace_containing_newline); + for_each_line_table_case (test_fixit_deletion_affecting_newline); ++ for_each_line_table_case (test_tab_expansion); + + test_line_numbers_multiline_range (); + } +diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi +--- a/gcc/doc/invoke.texi 2021-12-24 20:23:46.876739587 -0800 ++++ b/gcc/doc/invoke.texi 2021-12-25 01:20:53.487636494 -0800 +@@ -293,7 +293,9 @@ Objective-C and Objective-C++ Dialects}. + -fdiagnostics-show-template-tree -fno-elide-type @gol + -fdiagnostics-path-format=@r{[}none@r{|}separate-events@r{|}inline-events@r{]} @gol + -fdiagnostics-show-path-depths @gol +--fno-show-column} ++-fno-show-column @gol ++-fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol ++-fdiagnostics-column-origin=@var{origin}} + + @item Warning Options + @xref{Warning Options,,Options to Request or Suppress Warnings}. +@@ -4424,6 +4426,31 @@ Do not print column numbers in diagnosti + diagnostics are being scanned by a program that does not understand the + column numbers, such as @command{dejagnu}. + ++@item -fdiagnostics-column-unit=@var{UNIT} ++@opindex fdiagnostics-column-unit ++Select the units for the column number. This affects traditional diagnostics ++(in the absence of @option{-fno-show-column}), as well as JSON format ++diagnostics if requested. ++ ++The default @var{UNIT}, @samp{display}, considers the number of display ++columns occupied by each character. This may be larger than the number ++of bytes required to encode the character, in the case of tab ++characters, or it may be smaller, in the case of multibyte characters. ++For example, the character ``GREEK SMALL LETTER PI (U+03C0)'' occupies one ++display column, and its UTF-8 encoding requires two bytes; the character ++``SLIGHTLY SMILING FACE (U+1F642)'' occupies two display columns, and ++its UTF-8 encoding requires four bytes. ++ ++Setting @var{UNIT} to @samp{byte} changes the column number to the raw byte ++count in all cases, as was traditionally output by GCC prior to version 11.1.0. ++ ++@item -fdiagnostics-column-origin=@var{ORIGIN} ++@opindex fdiagnostics-column-origin ++Select the origin for column numbers, i.e. the column number assigned to the ++first column. The default value of 1 corresponds to traditional GCC ++behavior and to the GNU style guide. Some utilities may perform better with an ++origin of 0; any non-negative value may be specified. ++ + @item -fdiagnostics-format=@var{FORMAT} + @opindex fdiagnostics-format + Select a different format for printing diagnostics. +@@ -4459,11 +4486,15 @@ might be printed in JSON form (after for + "locations": [ + @{ + "caret": @{ ++ "display-column": 3, ++ "byte-column": 3, + "column": 3, + "file": "misleading-indentation.c", + "line": 15 + @}, + "finish": @{ ++ "display-column": 4, ++ "byte-column": 4, + "column": 4, + "file": "misleading-indentation.c", + "line": 15 +@@ -4479,6 +4510,8 @@ might be printed in JSON form (after for + "locations": [ + @{ + "caret": @{ ++ "display-column": 5, ++ "byte-column": 5, + "column": 5, + "file": "misleading-indentation.c", + "line": 17 +@@ -4488,6 +4521,7 @@ might be printed in JSON form (after for + "message": "...this statement, but the latter is @dots{}" + @} + ] ++ "column-origin": 1, + @}, + @dots{} + ] +@@ -4500,10 +4534,34 @@ A diagnostic has a @code{kind}. If this + an @code{option} key describing the command-line option controlling the + warning. + +-A diagnostic can contain zero or more locations. Each location has up +-to three positions within it: a @code{caret} position and optional +-@code{start} and @code{finish} positions. A location can also have +-an optional @code{label} string. For example, this error: ++A diagnostic can contain zero or more locations. Each location has an ++optional @code{label} string and up to three positions within it: a ++@code{caret} position and optional @code{start} and @code{finish} positions. ++A position is described by a @code{file} name, a @code{line} number, and ++three numbers indicating a column position: ++@itemize @bullet ++ ++@item ++@code{display-column} counts display columns, accounting for tabs and ++multibyte characters. ++ ++@item ++@code{byte-column} counts raw bytes. ++ ++@item ++@code{column} is equal to one of ++the previous two, as dictated by the @option{-fdiagnostics-column-unit} ++option. ++ ++@end itemize ++All three columns are relative to the origin specified by ++@option{-fdiagnostics-column-origin}, which is typically equal to 1 but may ++be set, for instance, to 0 for compatibility with other utilities that ++number columns from 0. The column origin is recorded in the JSON output in ++the @code{column-origin} tag. In the remaining examples below, the extra ++column number outputs have been omitted for brevity. ++ ++For example, this error: + + @smallexample + bad-binary-ops.c:64:23: error: invalid operands to binary + (have 'S' @{aka +diff --git a/gcc/input.c b/gcc/input.c +--- a/gcc/input.c 2020-07-22 23:35:17.664388078 -0700 ++++ b/gcc/input.c 2021-12-25 01:20:53.487636494 -0800 +@@ -913,7 +913,7 @@ make_location (location_t caret, source_ + source line in order to calculate the display width. If that cannot be done + for any reason, then returns the byte column as a fallback. */ + int +-location_compute_display_column (expanded_location exploc) ++location_compute_display_column (expanded_location exploc, int tabstop) + { + if (!(exploc.file && *exploc.file && exploc.line && exploc.column)) + return exploc.column; +@@ -921,7 +921,7 @@ location_compute_display_column (expande + /* If line is NULL, this function returns exploc.column which is the + desired fallback. */ + return cpp_byte_column_to_display_column (line.get_buffer (), line.length (), +- exploc.column); ++ exploc.column, tabstop); + } + + /* Dump statistics to stderr about the memory usage of the line_table +@@ -3608,33 +3608,46 @@ test_line_offset_overflow () + + void test_cpp_utf8 () + { ++ const int def_tabstop = 8; + /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */ + { +- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8); ++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop); + ASSERT_EQ (8, w_bad); +- int w_ctrl = cpp_display_width ("\r\t\n\v\0\1", 6); +- ASSERT_EQ (6, w_ctrl); ++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop); ++ ASSERT_EQ (5, w_ctrl); + } + + /* Verify that wcwidth of valid UTF-8 is as expected. */ + { +- const int w_pi = cpp_display_width ("\xcf\x80", 2); ++ const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop); + ASSERT_EQ (1, w_pi); +- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4); ++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop); + ASSERT_EQ (2, w_emoji); +- const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2); ++ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2, ++ def_tabstop); + ASSERT_EQ (1, w_umlaut_precomposed); +- const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3); ++ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3, ++ def_tabstop); + ASSERT_EQ (1, w_umlaut_combining); +- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3); ++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop); + ASSERT_EQ (2, w_han); +- const int w_ascii = cpp_display_width ("GCC", 3); ++ const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop); + ASSERT_EQ (3, w_ascii); + const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82" +- "\x9f! \xe4\xb8\xba y\xcc\x88", 24); ++ "\x9f! \xe4\xb8\xba y\xcc\x88", ++ 24, def_tabstop); + ASSERT_EQ (18, w_mixed); + } + ++ /* Verify that display width properly expands tabs. */ ++ { ++ const char *tstr = "\tabc\td"; ++ ASSERT_EQ (6, cpp_display_width (tstr, 6, 1)); ++ ASSERT_EQ (10, cpp_display_width (tstr, 6, 3)); ++ ASSERT_EQ (17, cpp_display_width (tstr, 6, 8)); ++ ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8)); ++ } ++ + /* Verify that cpp_byte_column_to_display_column can go past the end, + and similar edge cases. */ + { +@@ -3645,10 +3658,13 @@ void test_cpp_utf8 () + /* 111122223456 + Byte columns. */ + +- ASSERT_EQ (5, cpp_display_width (str, 6)); +- ASSERT_EQ (105, cpp_byte_column_to_display_column (str, 6, 106)); +- ASSERT_EQ (10000, cpp_byte_column_to_display_column (NULL, 0, 10000)); +- ASSERT_EQ (0, cpp_byte_column_to_display_column (NULL, 10000, 0)); ++ ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop)); ++ ASSERT_EQ (105, ++ cpp_byte_column_to_display_column (str, 6, 106, def_tabstop)); ++ ASSERT_EQ (10000, ++ cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop)); ++ ASSERT_EQ (0, ++ cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop)); + } + + /* Verify that cpp_display_column_to_byte_column can go past the end, +@@ -3662,21 +3678,25 @@ void test_cpp_utf8 () + /* 000000000000000000000000000000000111111 + 111122223333444456666777788889999012345 + Byte columns. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2)); +- ASSERT_EQ (15, cpp_display_column_to_byte_column (str, 15, 11)); +- ASSERT_EQ (115, cpp_display_column_to_byte_column (str, 15, 111)); +- ASSERT_EQ (10000, cpp_display_column_to_byte_column (NULL, 0, 10000)); +- ASSERT_EQ (0, cpp_display_column_to_byte_column (NULL, 10000, 0)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop)); ++ ASSERT_EQ (15, ++ cpp_display_column_to_byte_column (str, 15, 11, def_tabstop)); ++ ASSERT_EQ (115, ++ cpp_display_column_to_byte_column (str, 15, 111, def_tabstop)); ++ ASSERT_EQ (10000, ++ cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop)); ++ ASSERT_EQ (0, ++ cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop)); + + /* Verify that we do not interrupt a UTF-8 sequence. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop)); + + for (int byte_col = 1; byte_col <= 15; ++byte_col) + { +- const int disp_col = cpp_byte_column_to_display_column (str, 15, +- byte_col); +- const int byte_col2 = cpp_display_column_to_byte_column (str, 15, +- disp_col); ++ const int disp_col ++ = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop); ++ const int byte_col2 ++ = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop); + + /* If we ask for the display column in the middle of a UTF-8 + sequence, it will return the length of the partial sequence, +diff --git a/gcc/input.h b/gcc/input.h +--- a/gcc/input.h 2020-07-22 23:35:17.664388078 -0700 ++++ b/gcc/input.h 2021-12-25 01:20:53.487636494 -0800 +@@ -38,7 +38,9 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER + + extern bool is_location_from_builtin_token (location_t); + extern expanded_location expand_location (location_t); +-extern int location_compute_display_column (expanded_location); ++ ++extern int location_compute_display_column (expanded_location exploc, ++ int tabstop); + + /* A class capturing the bounds of a buffer, to allow for run-time + bounds-checking in a checked build. */ +diff --git a/gcc/opts.c b/gcc/opts.c +--- a/gcc/opts.c 2020-07-22 23:35:17.708388562 -0700 ++++ b/gcc/opts.c 2021-12-25 01:20:53.487636494 -0800 +@@ -2439,6 +2439,14 @@ common_handle_option (struct gcc_options + dc->parseable_fixits_p = value; + break; + ++ case OPT_fdiagnostics_column_unit_: ++ dc->column_unit = (enum diagnostics_column_unit)value; ++ break; ++ ++ case OPT_fdiagnostics_column_origin_: ++ dc->column_origin = value; ++ break; ++ + case OPT_fdiagnostics_show_cwe: + dc->show_cwe = value; + break; +@@ -2825,6 +2833,12 @@ common_handle_option (struct gcc_options + check_alignment_argument (loc, arg, "functions"); + break; + ++ case OPT_ftabstop_: ++ /* It is documented that we silently ignore silly values. */ ++ if (value >= 1 && value <= 100) ++ dc->tabstop = value; ++ break; ++ + default: + /* If the flag was handled in a standard way, assume the lack of + processing here is intentional. */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,17 +8,22 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#error message\"" } */ + + /* { dg-regexp "\"caret\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 6" } */ ++/* { dg-regexp "\"display-column\": 6" } */ ++/* { dg-regexp "\"byte-column\": 6" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,6 +8,7 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"warning\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Wcpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +@@ -16,11 +17,15 @@ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 8" } */ ++/* { dg-regexp "\"display-column\": 8" } */ ++/* { dg-regexp "\"byte-column\": 8" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -8,6 +8,7 @@ + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +@@ -16,11 +17,15 @@ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 2" } */ ++/* { dg-regexp "\"display-column\": 2" } */ ++/* { dg-regexp "\"byte-column\": 2" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */ + /* { dg-regexp "\"line\": 4" } */ + /* { dg-regexp "\"column\": 8" } */ ++/* { dg-regexp "\"display-column\": 8" } */ ++/* { dg-regexp "\"byte-column\": 8" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:20:53.487636494 -0800 +@@ -24,15 +24,20 @@ int test (void) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 5" } */ ++/* { dg-regexp "\"display-column\": 5" } */ ++/* { dg-regexp "\"byte-column\": 5" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 10" } */ ++/* { dg-regexp "\"display-column\": 10" } */ ++/* { dg-regexp "\"byte-column\": 10" } */ + + /* The outer diagnostic. */ + + /* { dg-regexp "\"kind\": \"warning\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */ + /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */ +@@ -41,11 +46,15 @@ int test (void) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 6" } */ + /* { dg-regexp "\"column\": 3" } */ ++/* { dg-regexp "\"display-column\": 3" } */ ++/* { dg-regexp "\"byte-column\": 3" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ + /* { dg-regexp "\"line\": 6" } */ + /* { dg-regexp "\"column\": 4" } */ ++/* { dg-regexp "\"display-column\": 4" } */ ++/* { dg-regexp "\"byte-column\": 4" } */ + + /* More from the nested diagnostic (we can't guarantee what order the + "file" keys are consumed). */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2020-07-22 23:35:17.908390765 -0700 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:20:53.487636494 -0800 +@@ -13,6 +13,7 @@ int test (struct s *ptr) + We can't rely on any ordering of the keys. */ + + /* { dg-regexp "\"kind\": \"error\"" } */ ++/* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \".*\"" } */ + + /* Verify fix-it hints. */ +@@ -23,11 +24,15 @@ int test (struct s *ptr) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 15" } */ ++/* { dg-regexp "\"display-column\": 15" } */ ++/* { dg-regexp "\"byte-column\": 15" } */ + + /* { dg-regexp "\"next\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 21" } */ ++/* { dg-regexp "\"display-column\": 21" } */ ++/* { dg-regexp "\"byte-column\": 21" } */ + + /* { dg-regexp "\"fixits\": \[\[\{\}, \]*\]" } */ + +@@ -35,11 +40,15 @@ int test (struct s *ptr) + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 15" } */ ++/* { dg-regexp "\"display-column\": 15" } */ ++/* { dg-regexp "\"byte-column\": 15" } */ + + /* { dg-regexp "\"finish\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */ + /* { dg-regexp "\"line\": 8" } */ + /* { dg-regexp "\"column\": 20" } */ ++/* { dg-regexp "\"display-column\": 20" } */ ++/* { dg-regexp "\"byte-column\": 20" } */ + + /* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */ + /* { dg-regexp "\"children\": \[\[\]\[\]\]" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-1.c b/gcc/testsuite/c-c++-common/diagnostic-units-1.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-1.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-1.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via default) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-2.c b/gcc/testsuite/c-c++-common/diagnostic-units-2.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-2.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-2.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -Wmultichar" } */ ++ ++/* column units: display (via arg) ++ column origin: 1 (via default) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "25: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-3.c b/gcc/testsuite/c-c++-common/diagnostic-units-3.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-3.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=200 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via fallback from overly large argument) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-4.c b/gcc/testsuite/c-c++-common/diagnostic-units-4.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-4.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-4.c 2021-12-25 01:20:53.487636494 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 0 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "10: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "18: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-5.c b/gcc/testsuite/c-c++-common/diagnostic-units-5.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-5.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-5.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */ ++ ++/* column units: display (via arg) ++ column origin: 0 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "24: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-6.c b/gcc/testsuite/c-c++-common/diagnostic-units-6.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-6.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-6.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=100 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 100 (via arg) ++ tabstop: 8 (via default) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "110: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "117: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "118: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-7.c b/gcc/testsuite/c-c++-common/diagnostic-units-7.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-7.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-7.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */ ++ ++/* column units: bytes (via arg) ++ column origin: 1 (via default) ++ tabstop: 9 (via arg) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "20: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-units-8.c b/gcc/testsuite/c-c++-common/diagnostic-units-8.c +--- a/gcc/testsuite/c-c++-common/diagnostic-units-8.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-units-8.c 2021-12-25 01:20:53.491636427 -0800 +@@ -0,0 +1,28 @@ ++/* { dg-do compile } */ ++/* { dg-additional-options "-fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */ ++ ++/* column units: display (via default) ++ column origin: 1 (via default) ++ tabstop: 9 (via arg) */ ++ ++/* This line starts with a tab. */ ++ int c1 = 'c1'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c1 = 'c1'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces. */ ++ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c2 = 'c2'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ ++ ++/* This line starts with <tabstop> spaces and has an internal tab after ++ a space. */ ++ int c3 = 'c3'; /* { dg-warning "28: multi-character character constant" } */ ++/* { dg-begin-multiline-output "" } ++ int c3 = 'c3'; ++ ^~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/c-c++-common/missing-close-symbol.c b/gcc/testsuite/c-c++-common/missing-close-symbol.c +--- a/gcc/testsuite/c-c++-common/missing-close-symbol.c 2020-07-22 23:35:17.912390810 -0700 ++++ b/gcc/testsuite/c-c++-common/missing-close-symbol.c 2021-12-25 01:20:53.491636427 -0800 +@@ -24,9 +24,9 @@ void test_static_assert_different_line ( + _Static_assert(sizeof(int) >= sizeof(char), /* { dg-message "to match this '\\('" } */ + "msg"; /* { dg-error "expected '\\)' before ';' token" } */ + /* { dg-begin-multiline-output "" } +- "msg"; +- ^ +- ) ++ "msg"; ++ ^ ++ ) + { dg-end-multiline-output "" } */ + /* { dg-begin-multiline-output "" } + _Static_assert(sizeof(int) >= sizeof(char), +diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c +--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2020-07-22 23:35:17.904390722 -0700 ++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation-3.c 2021-12-25 01:20:53.487636494 -0800 +@@ -36,20 +36,20 @@ int fn_6 (int a, int b, int c) + /* ... */ + if ((err = foo (a)) != 0) + goto fail; +- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */ ++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */ + goto fail; +- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + if ((err = foo (c)) != 0) + goto fail; + /* ... */ + + /* { dg-begin-multiline-output "" } +- if ((err = foo (b)) != 0) +- ^~ ++ if ((err = foo (b)) != 0) ++ ^~ + { dg-end-multiline-output "" } */ + /* { dg-begin-multiline-output "" } +- goto fail; +- ^~~~ ++ goto fail; ++ ^~~~ + { dg-end-multiline-output "" } */ + + fail: +diff --git a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c +--- a/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2020-07-22 23:35:17.904390722 -0700 ++++ b/gcc/testsuite/c-c++-common/Wmisleading-indentation.c 2021-12-25 01:20:53.487636494 -0800 +@@ -65,9 +65,9 @@ int fn_6 (int a, int b, int c) + /* ... */ + if ((err = foo (a)) != 0) + goto fail; +- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */ ++ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */ + goto fail; +- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + if ((err = foo (c)) != 0) + goto fail; + /* ... */ +@@ -178,7 +178,7 @@ void fn_16_tabs (void) + while (flagA) + if (flagB) /* { dg-message "7: this 'if' clause does not guard..." } */ + foo (0); +- foo (1);/* { dg-message "2: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ ++ foo (1);/* { dg-message "9: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */ + } + + void fn_17_spaces (void) +diff --git a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c +--- a/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2020-07-22 23:35:18.124393144 -0700 ++++ b/gcc/testsuite/gcc.dg/analyzer/malloc-paths-9.c 2021-12-25 01:20:53.491636427 -0800 +@@ -288,7 +288,7 @@ int test_3 (int x, int y) + | | ~~~~~~~~~~ + | | | + | | (4) ...to here +- | NN | to dereference it above ++ | NN | to dereference it above + | NN | return *ptr; + | | ~~~~ + | | | +diff --git a/gcc/testsuite/gcc.dg/bad-binary-ops.c b/gcc/testsuite/gcc.dg/bad-binary-ops.c +--- a/gcc/testsuite/gcc.dg/bad-binary-ops.c 2020-07-22 23:35:18.128393190 -0700 ++++ b/gcc/testsuite/gcc.dg/bad-binary-ops.c 2021-12-25 01:20:53.491636427 -0800 +@@ -35,10 +35,10 @@ int test_2 (void) + ~~~~~~~~~~~~~~~~ + | + struct s +- + some_other_function ()); +- ^ ~~~~~~~~~~~~~~~~~~~~~~ +- | +- struct t ++ + some_other_function ()); ++ ^ ~~~~~~~~~~~~~~~~~~~~~~ ++ | ++ struct t + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/gcc.dg/format/branch-1.c b/gcc/testsuite/gcc.dg/format/branch-1.c +--- a/gcc/testsuite/gcc.dg/format/branch-1.c 2020-07-22 23:35:18.152393454 -0700 ++++ b/gcc/testsuite/gcc.dg/format/branch-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -10,7 +10,7 @@ foo (long l, int nfoo) + { + printf ((nfoo > 1) ? "%d foos" : "%d foo", nfoo); + printf ((l > 1) ? "%d foos" /* { dg-warning "23:int" "wrong type in conditional expr" } */ +- : "%d foo", l); /* { dg-warning "16:int" "wrong type in conditional expr" } */ ++ : "%d foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */ + printf ((l > 1) ? "%ld foos" : "%d foo", l); /* { dg-warning "36:int" "wrong type in conditional expr" } */ + printf ((l > 1) ? "%d foos" : "%ld foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */ + /* Should allow one case to have extra arguments. */ +diff --git a/gcc/testsuite/gcc.dg/format/pr79210.c b/gcc/testsuite/gcc.dg/format/pr79210.c +--- a/gcc/testsuite/gcc.dg/format/pr79210.c 2020-07-22 23:35:18.152393454 -0700 ++++ b/gcc/testsuite/gcc.dg/format/pr79210.c 2021-12-25 01:20:53.491636427 -0800 +@@ -20,4 +20,4 @@ LPFC_VPORT_ATTR_R(peer_port_login, + "Allow peer ports on the same physical port to login to each " + "other."); + +-/* { dg-warning "6: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */ ++/* { dg-warning "20: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */ +diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c +--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2020-07-22 23:35:18.172393674 -0700 ++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-expressions-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -540,15 +540,15 @@ void test_builtin_types_compatible_p (un + __emit_expression_range (0, + f (i) + __builtin_types_compatible_p (long, int)); /* { dg-warning "range" } */ + /* { dg-begin-multiline-output "" } +- f (i) + __builtin_types_compatible_p (long, int)); +- ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ++ f (i) + __builtin_types_compatible_p (long, int)); ++ ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + { dg-end-multiline-output "" } */ + + __emit_expression_range (0, + __builtin_types_compatible_p (long, int) + f (i)); /* { dg-warning "range" } */ + /* { dg-begin-multiline-output "" } +- __builtin_types_compatible_p (long, int) + f (i)); +- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~ ++ __builtin_types_compatible_p (long, int) + f (i)); ++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~ + { dg-end-multiline-output "" } */ + } + +@@ -671,8 +671,8 @@ void test_multiple_ordinary_maps (void) + /* { dg-begin-multiline-output "" } + __emit_expression_range (0, foo (0, + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +- "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789")); +- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ++ "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789")); ++ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + { dg-end-multiline-output "" } */ + + /* Another expression that transitions between ordinary maps; this +@@ -685,8 +685,8 @@ void test_multiple_ordinary_maps (void) + /* { dg-begin-multiline-output "" } + __emit_expression_range (0, foo (0, "01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789", + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +- 0)); +- ~~ ++ 0)); ++ ~~ + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c +--- a/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2020-07-22 23:35:18.172393674 -0700 ++++ b/gcc/testsuite/gcc.dg/plugin/diagnostic-test-string-literals-1.c 2021-12-25 01:20:53.491636427 -0800 +@@ -335,11 +335,11 @@ pr87652 (const char *stem, int counter) + /* { dg-error "unable to read substring location: unable to read source line" "" { target c } 329 } */ + /* { dg-error "unable to read substring location: failed to get ordinary maps" "" { target c++ } 329 } */ + /* { dg-begin-multiline-output "" } +- __emit_string_literal_range(__FILE__":%5d: " format, \ ++ __emit_string_literal_range(__FILE__":%5d: " format, \ + ^~~~~~~~ + { dg-end-multiline-output "" { target c } } */ + /* { dg-begin-multiline-output "" } +- __emit_string_literal_range(__FILE__":%5d: " format, \ ++ __emit_string_literal_range(__FILE__":%5d: " format, \ + ^ + { dg-end-multiline-output "" { target c++ } } */ + +diff --git a/gcc/testsuite/gcc.dg/redecl-4.c b/gcc/testsuite/gcc.dg/redecl-4.c +--- a/gcc/testsuite/gcc.dg/redecl-4.c 2020-07-22 23:35:18.192393895 -0700 ++++ b/gcc/testsuite/gcc.dg/redecl-4.c 2021-12-25 01:20:53.491636427 -0800 +@@ -15,7 +15,7 @@ f (void) + /* Should get format warnings even though the built-in declaration + isn't "visible". */ + printf ( +- "%s", 1); /* { dg-warning "8:format" } */ ++ "%s", 1); /* { dg-warning "15:format" } */ + /* The type of strcmp here should have no prototype. */ + if (0) + strcmp (1); +diff --git a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C +--- a/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2020-07-22 23:35:17.972391472 -0700 ++++ b/gcc/testsuite/g++.dg/diagnostic/bad-binary-ops.C 2021-12-25 01:20:53.491636427 -0800 +@@ -33,10 +33,10 @@ int test_2 (void) + ~~~~~~~~~~~~~~~~ + | + s +- + some_other_function ()); +- ^ ~~~~~~~~~~~~~~~~~~~~~~ +- | +- t ++ + some_other_function ()); ++ ^ ~~~~~~~~~~~~~~~~~~~~~~ ++ | ++ t + { dg-end-multiline-output "" } */ + } + +diff --git a/gcc/testsuite/g++.dg/parse/error4.C b/gcc/testsuite/g++.dg/parse/error4.C +--- a/gcc/testsuite/g++.dg/parse/error4.C 2020-07-22 23:35:18.012391910 -0700 ++++ b/gcc/testsuite/g++.dg/parse/error4.C 2021-12-25 01:20:53.491636427 -0800 +@@ -7,4 +7,4 @@ struct X { + int); + }; + +-// { dg-error "4:'itn' has not been declared" "" { target *-*-* } 6 } ++// { dg-error "18:'itn' has not been declared" "" { target *-*-* } 6 } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,17 +8,22 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"error\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#error message\"" } + + ! { dg-regexp "\"caret\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 6" } ++! { dg-regexp "\"display-column\": 6" } ++! { dg-regexp "\"byte-column\": 6" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,6 +8,7 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"warning\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Wcpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +@@ -16,11 +17,15 @@ + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 8" } ++! { dg-regexp "\"display-column\": 8" } ++! { dg-regexp "\"byte-column\": 8" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2020-07-22 23:35:18.512397420 -0700 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:20:53.491636427 -0800 +@@ -8,6 +8,7 @@ + ! We can't rely on any ordering of the keys. + + ! { dg-regexp "\"kind\": \"error\"" } ++! { dg-regexp "\"column-origin\": 1" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Werror=cpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +@@ -16,11 +17,15 @@ + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 2" } ++! { dg-regexp "\"display-column\": 2" } ++! { dg-regexp "\"byte-column\": 2" } + + ! { dg-regexp "\"finish\": \{" } + ! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" } + ! { dg-regexp "\"line\": 4" } + ! { dg-regexp "\"column\": 8" } ++! { dg-regexp "\"display-column\": 8" } ++! { dg-regexp "\"byte-column\": 8" } + + ! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } + ! { dg-regexp "\"children\": \[\[\]\[\]\]" } +diff --git a/gcc/testsuite/go.dg/arrayclear.go b/gcc/testsuite/go.dg/arrayclear.go +--- a/gcc/testsuite/go.dg/arrayclear.go 2020-07-22 23:35:18.588398257 -0700 ++++ b/gcc/testsuite/go.dg/arrayclear.go 2021-12-25 01:20:53.491636427 -0800 +@@ -1,5 +1,8 @@ + // { dg-do compile } + // { dg-options "-fgo-debug-optimization" } ++// This comment is necessary to work around a dejagnu bug. Otherwise, the ++// column of the second error message would equal the row of the first one, and ++// since the errors are also identical, dejagnu is not able to distinguish them. + + package p + +diff --git a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C +--- a/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2020-07-22 23:35:18.048392308 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.brendan/crash11.C 2021-12-25 01:20:53.491636427 -0800 +@@ -9,13 +9,13 @@ class A { + int h; + A() { i=10; j=20; } + virtual void f1() { printf("i=%d j=%d\n",i,j); } +- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" } ++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" } + }; + + class B : public A { + public: + virtual void f1() { printf("i=%d j=%d\n",i,j); }// { dg-error "" } member.*// ERROR - member.* +- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" } ++ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" } + // { dg-error "private" "" { target *-*-* } .-1 } + }; + +diff --git a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C +--- a/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2020-07-22 23:35:18.072392572 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.pt/overload2.C 2021-12-25 01:20:53.491636427 -0800 +@@ -12,5 +12,5 @@ int + main() + { + C<char*> c; +- char* p = Z(c.O); //{ dg-error "13:'Z' was not declared" } ambiguous c.O ++ char* p = Z(c.O); //{ dg-error "29:'Z' was not declared" } ambiguous c.O + } +diff --git a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C +--- a/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2020-07-22 23:35:18.076392617 -0700 ++++ b/gcc/testsuite/g++.old-deja/g++.robertl/eb109.C 2021-12-25 01:20:53.491636427 -0800 +@@ -48,8 +48,8 @@ ostream& operator<<(ostream& os, Graph<V + + // The compiler does not like this line!!!!!! + typename Graph<VertexType, EdgeType>::Successor::iterator +- startN = G[i].second.begin(), // { dg-error "14:no match" } no index operator +- endN = G[i].second.end(); // { dg-error "14:no match" } no index operator ++ startN = G[i].second.begin(), // { dg-error "21:no match" } no index operator ++ endN = G[i].second.end(); // { dg-error "21:no match" } no index operator + + while(startN != endN) + { +diff --git a/gcc/tree-diagnostic-path.cc b/gcc/tree-diagnostic-path.cc +--- a/gcc/tree-diagnostic-path.cc 2020-07-22 23:35:18.628398698 -0700 ++++ b/gcc/tree-diagnostic-path.cc 2021-12-25 01:20:53.491636427 -0800 +@@ -493,7 +493,7 @@ default_tree_diagnostic_path_printer (di + doesn't have access to trees (for m_fndecl). */ + + json::value * +-default_tree_make_json_for_path (diagnostic_context *, ++default_tree_make_json_for_path (diagnostic_context *context, + const diagnostic_path *path) + { + json::array *path_array = new json::array (); +@@ -504,7 +504,8 @@ default_tree_make_json_for_path (diagnos + json::object *event_obj = new json::object (); + if (event.get_location ()) + event_obj->set ("location", +- json_from_expanded_location (event.get_location ())); ++ json_from_expanded_location (context, ++ event.get_location ())); + label_text event_text (event.get_desc (false)); + event_obj->set ("description", new json::string (event_text.m_buffer)); + event_text.maybe_free (); +diff --git a/libcpp/charset.c b/libcpp/charset.c +--- a/libcpp/charset.c 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/charset.c 2021-12-25 01:20:53.491636427 -0800 +@@ -2276,49 +2276,90 @@ cpp_string_location_reader::get_next () + return result; + } + +-/* Helper for cpp_byte_column_to_display_column and its inverse. Given a +- pointer to a UTF-8-encoded character, compute its display width. *INBUFP +- points on entry to the start of the UTF-8 encoding of the character, and +- is updated to point just after the last byte of the encoding. *INBYTESLEFTP +- contains on entry the remaining size of the buffer into which *INBUFP +- points, and this is also updated accordingly. If *INBUFP does not ++cpp_display_width_computation:: ++cpp_display_width_computation (const char *data, int data_length, int tabstop) : ++ m_begin (data), ++ m_next (m_begin), ++ m_bytes_left (data_length), ++ m_tabstop (tabstop), ++ m_display_cols (0) ++{ ++ gcc_assert (m_tabstop > 0); ++} ++ ++ ++/* The main implementation function for class cpp_display_width_computation. ++ m_next points on entry to the start of the UTF-8 encoding of the next ++ character, and is updated to point just after the last byte of the encoding. ++ m_bytes_left contains on entry the remaining size of the buffer into which ++ m_next points, and this is also updated accordingly. If m_next does not + point to a valid UTF-8-encoded sequence, then it will be treated as a single +- byte with display width 1. */ ++ byte with display width 1. m_cur_display_col is the current display column, ++ relative to which tab stops should be expanded. Returns the display width of ++ the codepoint just processed. */ + +-static inline int +-compute_next_display_width (const uchar **inbufp, size_t *inbytesleftp) ++int ++cpp_display_width_computation::process_next_codepoint () + { + cppchar_t c; +- if (one_utf8_to_cppchar (inbufp, inbytesleftp, &c) != 0) ++ int next_width; ++ ++ if (*m_next == '\t') ++ { ++ ++m_next; ++ --m_bytes_left; ++ next_width = m_tabstop - (m_display_cols % m_tabstop); ++ } ++ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c) ++ != 0) + { + /* Input is not convertible to UTF-8. This could be fine, e.g. in a + string literal, so don't complain. Just treat it as if it has a width + of one. */ +- ++*inbufp; +- --*inbytesleftp; +- return 1; ++ ++m_next; ++ --m_bytes_left; ++ next_width = 1; ++ } ++ else ++ { ++ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */ ++ next_width = cpp_wcwidth (c); + } + +- /* one_utf8_to_cppchar() has updated inbufp and inbytesleftp for us. */ +- return cpp_wcwidth (c); ++ m_display_cols += next_width; ++ return next_width; ++} ++ ++/* Utility to advance the byte stream by the minimum amount needed to consume ++ N display columns. Returns the number of display columns that were ++ actually skipped. This could be less than N, if there was not enough data, ++ or more than N, if the last character to be skipped had a sufficiently large ++ display width. */ ++int ++cpp_display_width_computation::advance_display_cols (int n) ++{ ++ const int start = m_display_cols; ++ const int target = start + n; ++ while (m_display_cols < target && !done ()) ++ process_next_codepoint (); ++ return m_display_cols - start; + } + + /* For the string of length DATA_LENGTH bytes that begins at DATA, compute + how many display columns are occupied by the first COLUMN bytes. COLUMN + may exceed DATA_LENGTH, in which case the phantom bytes at the end are +- treated as if they have display width 1. */ ++ treated as if they have display width 1. Tabs are expanded to the next tab ++ stop, relative to the start of DATA. */ + + int + cpp_byte_column_to_display_column (const char *data, int data_length, +- int column) ++ int column, int tabstop) + { +- int display_col = 0; +- const uchar *udata = (const uchar *) data; + const int offset = MAX (0, column - data_length); +- size_t inbytesleft = column - offset; +- while (inbytesleft) +- display_col += compute_next_display_width (&udata, &inbytesleft); +- return display_col + offset; ++ cpp_display_width_computation dw (data, column - offset, tabstop); ++ while (!dw.done ()) ++ dw.process_next_codepoint (); ++ return dw.display_cols_processed () + offset; + } + + /* For the string of length DATA_LENGTH bytes that begins at DATA, compute +@@ -2328,14 +2369,11 @@ cpp_byte_column_to_display_column (const + + int + cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col) ++ int display_col, int tabstop) + { +- int column = 0; +- const uchar *udata = (const uchar *) data; +- size_t inbytesleft = data_length; +- while (column < display_col && inbytesleft) +- column += compute_next_display_width (&udata, &inbytesleft); +- return data_length - inbytesleft + MAX (0, display_col - column); ++ cpp_display_width_computation dw (data, data_length, tabstop); ++ const int avail_display = dw.advance_display_cols (display_col); ++ return dw.bytes_processed () + MAX (0, display_col - avail_display); + } + + /* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc, +diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h +--- a/libcpp/include/cpplib.h 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/include/cpplib.h 2021-12-25 01:20:53.491636427 -0800 +@@ -312,9 +312,6 @@ enum cpp_normalize_level { + carries all the options visible to the command line. */ + struct cpp_options + { +- /* Characters between tab stops. */ +- unsigned int tabstop; +- + /* The language we're preprocessing. */ + enum c_lang lang; + +@@ -1322,14 +1319,43 @@ extern const char * cpp_get_userdef_suff + (const cpp_token *); + + /* In charset.c */ ++ ++/* A class to manage the state while converting a UTF-8 sequence to cppchar_t ++ and computing the display width one character at a time. */ ++class cpp_display_width_computation { ++ public: ++ cpp_display_width_computation (const char *data, int data_length, ++ int tabstop); ++ const char *next_byte () const { return m_next; } ++ int bytes_processed () const { return m_next - m_begin; } ++ int bytes_left () const { return m_bytes_left; } ++ bool done () const { return !bytes_left (); } ++ int display_cols_processed () const { return m_display_cols; } ++ ++ int process_next_codepoint (); ++ int advance_display_cols (int n); ++ ++ private: ++ const char *const m_begin; ++ const char *m_next; ++ size_t m_bytes_left; ++ const int m_tabstop; ++ int m_display_cols; ++}; ++ ++/* Convenience functions that are simple use cases for class ++ cpp_display_width_computation. Tab characters will be expanded to spaces ++ as determined by TABSTOP. */ + int cpp_byte_column_to_display_column (const char *data, int data_length, +- int column); +-inline int cpp_display_width (const char *data, int data_length) ++ int column, int tabstop); ++inline int cpp_display_width (const char *data, int data_length, ++ int tabstop) + { +- return cpp_byte_column_to_display_column (data, data_length, data_length); ++ return cpp_byte_column_to_display_column (data, data_length, data_length, ++ tabstop); + } + int cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col); ++ int display_col, int tabstop); + int cpp_wcwidth (cppchar_t c); + + #endif /* ! LIBCPP_CPPLIB_H */ +diff --git a/libcpp/init.c b/libcpp/init.c +--- a/libcpp/init.c 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/init.c 2021-12-25 01:20:53.491636427 -0800 +@@ -190,7 +190,6 @@ cpp_create_reader (enum c_lang lang, cpp + CPP_OPTION (pfile, discard_comments) = 1; + CPP_OPTION (pfile, discard_comments_in_macro_exp) = 1; + CPP_OPTION (pfile, max_include_depth) = 200; +- CPP_OPTION (pfile, tabstop) = 8; + CPP_OPTION (pfile, operator_names) = 1; + CPP_OPTION (pfile, warn_trigraphs) = 2; + CPP_OPTION (pfile, warn_endif_labels) = 1; diff --git a/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch b/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch deleted file mode 100644 index c060accd99..0000000000 --- a/meta/recipes-devtools/gcc/gcc/0001-aarch64-Fix-up-__aarch64_cas16_acq_rel-fallback.patch +++ /dev/null @@ -1,66 +0,0 @@ -Upstream-Status: Backport -Signed-off-by: Ross Burton <ross.burton@arm.com> - -From fd2ec4542fd2975e6d3f2f1c1a2639945a84f9e1 Mon Sep 17 00:00:00 2001 -From: Jakub Jelinek <jakub@redhat.com> -Date: Mon, 3 Aug 2020 22:55:28 +0200 -Subject: [PATCH] aarch64: Fix up __aarch64_cas16_acq_rel fallback - -As mentioned in the PR, the fallback path when LSE is unavailable writes -incorrect registers to the memory if the previous content compares equal -to x0, x1 - it writes copy of x0, x1 from the start of function, but it -should write x2, x3. - -2020-08-03 Jakub Jelinek <jakub@redhat.com> - - PR target/96402 - * config/aarch64/lse.S (__aarch64_cas16_acq_rel): Use x2, x3 instead - of x(tmp0), x(tmp1) in STXP arguments. - - * gcc.target/aarch64/pr96402.c: New test. - -(cherry picked from commit 90b43856fdff7d96d93d22970eca8a86c56e0ddc) ---- - gcc/testsuite/gcc.target/aarch64/pr96402.c | 16 ++++++++++++++++ - libgcc/config/aarch64/lse.S | 2 +- - 2 files changed, 17 insertions(+), 1 deletion(-) - create mode 100644 gcc/testsuite/gcc.target/aarch64/pr96402.c - -diff --git a/gcc/testsuite/gcc.target/aarch64/pr96402.c b/gcc/testsuite/gcc.target/aarch64/pr96402.c -new file mode 100644 -index 00000000000..fa2dddfac15 ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/pr96402.c -@@ -0,0 +1,16 @@ -+/* PR target/96402 */ -+/* { dg-do run { target int128 } } */ -+/* { dg-options "-moutline-atomics" } */ -+ -+int -+main () -+{ -+ __int128 a = 0; -+ __sync_val_compare_and_swap (&a, (__int128) 0, (__int128) 1); -+ if (a != 1) -+ __builtin_abort (); -+ __sync_val_compare_and_swap (&a, (__int128) 1, (((__int128) 0xdeadbeeffeedbac1ULL) << 64) | 0xabadcafe00c0ffeeULL); -+ if (a != ((((__int128) 0xdeadbeeffeedbac1ULL) << 64) | 0xabadcafe00c0ffeeULL)) -+ __builtin_abort (); -+ return 0; -+} -diff --git a/libgcc/config/aarch64/lse.S b/libgcc/config/aarch64/lse.S -index 64691c601c1..c8fbfbce4fd 100644 ---- a/libgcc/config/aarch64/lse.S -+++ b/libgcc/config/aarch64/lse.S -@@ -203,7 +203,7 @@ STARTFN NAME(cas) - cmp x0, x(tmp0) - ccmp x1, x(tmp1), #0, eq - bne 1f -- STXP w(tmp2), x(tmp0), x(tmp1), [x4] -+ STXP w(tmp2), x2, x3, [x4] - cbnz w(tmp2), 0b - 1: ret - --- -2.26.2 - diff --git a/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch b/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch deleted file mode 100644 index 73de4c7590..0000000000 --- a/meta/recipes-devtools/gcc/gcc/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch +++ /dev/null @@ -1,202 +0,0 @@ -CVE: CVE-2020-13844 -Upstream-Status: Backport -Signed-off-by: Ross Burton <ross.burton@arm.com> - -From 1ff243934ac443b5f58cd02a5012ce58ecc31fb2 Mon Sep 17 00:00:00 2001 -From: Matthew Malcomson <matthew.malcomson@arm.com> -Date: Thu, 9 Jul 2020 09:11:58 +0100 -Subject: [PATCH 1/3] aarch64: New Straight Line Speculation (SLS) mitigation - flags - -Here we introduce the flags that will be used for straight line speculation. - -The new flag introduced is `-mharden-sls=`. -This flag can take arguments of `none`, `all`, or a comma seperated list of one -or more of `retbr` or `blr`. -`none` indicates no special mitigation of the straight line speculation -vulnerability. -`all` requests all mitigations currently implemented. -`retbr` requests that the RET and BR instructions have a speculation barrier -inserted after them. -`blr` requests that BLR instructions are replaced by a BL to a function stub -using a BR with a speculation barrier after it. - -Setting this on a per-function basis using attributes or the like is not -enabled, but may be in the future. - -gcc/ChangeLog: - -2020-06-02 Matthew Malcomson <matthew.malcomson@arm.com> - - * config/aarch64/aarch64-protos.h (aarch64_harden_sls_retbr_p): - New. - (aarch64_harden_sls_blr_p): New. - * config/aarch64/aarch64.c (enum aarch64_sls_hardening_type): - New. - (aarch64_harden_sls_retbr_p): New. - (aarch64_harden_sls_blr_p): New. - (aarch64_validate_sls_mitigation): New. - (aarch64_override_options): Parse options for SLS mitigation. - * config/aarch64/aarch64.opt (-mharden-sls): New option. - * doc/invoke.texi: Document new option. ---- - gcc/config/aarch64/aarch64-protos.h | 3 ++ - gcc/config/aarch64/aarch64.c | 76 +++++++++++++++++++++++++++++++++++++ - gcc/config/aarch64/aarch64.opt | 4 ++ - gcc/doc/invoke.texi | 12 ++++++ - 4 files changed, 95 insertions(+) - -diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h -index 723d9ba..eb5f4b4 100644 ---- a/gcc/config/aarch64/aarch64-protos.h -+++ b/gcc/config/aarch64/aarch64-protos.h -@@ -781,4 +781,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names; - - tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *); - -+extern bool aarch64_harden_sls_retbr_p (void); -+extern bool aarch64_harden_sls_blr_p (void); -+ - #endif /* GCC_AARCH64_PROTOS_H */ -diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c -index b86434a..437a9cf 100644 ---- a/gcc/config/aarch64/aarch64.c -+++ b/gcc/config/aarch64/aarch64.c -@@ -14494,6 +14494,79 @@ aarch64_validate_mcpu (const char *str, const struct processor **res, - return false; - } - -+/* Straight line speculation indicators. */ -+enum aarch64_sls_hardening_type -+{ -+ SLS_NONE = 0, -+ SLS_RETBR = 1, -+ SLS_BLR = 2, -+ SLS_ALL = 3, -+}; -+static enum aarch64_sls_hardening_type aarch64_sls_hardening; -+ -+/* Return whether we should mitigatate Straight Line Speculation for the RET -+ and BR instructions. */ -+bool -+aarch64_harden_sls_retbr_p (void) -+{ -+ return aarch64_sls_hardening & SLS_RETBR; -+} -+ -+/* Return whether we should mitigatate Straight Line Speculation for the BLR -+ instruction. */ -+bool -+aarch64_harden_sls_blr_p (void) -+{ -+ return aarch64_sls_hardening & SLS_BLR; -+} -+ -+/* As of yet we only allow setting these options globally, in the future we may -+ allow setting them per function. */ -+static void -+aarch64_validate_sls_mitigation (const char *const_str) -+{ -+ char *token_save = NULL; -+ char *str = NULL; -+ -+ if (strcmp (const_str, "none") == 0) -+ { -+ aarch64_sls_hardening = SLS_NONE; -+ return; -+ } -+ if (strcmp (const_str, "all") == 0) -+ { -+ aarch64_sls_hardening = SLS_ALL; -+ return; -+ } -+ -+ char *str_root = xstrdup (const_str); -+ str = strtok_r (str_root, ",", &token_save); -+ if (!str) -+ error ("invalid argument given to %<-mharden-sls=%>"); -+ -+ int temp = SLS_NONE; -+ while (str) -+ { -+ if (strcmp (str, "blr") == 0) -+ temp |= SLS_BLR; -+ else if (strcmp (str, "retbr") == 0) -+ temp |= SLS_RETBR; -+ else if (strcmp (str, "none") == 0 || strcmp (str, "all") == 0) -+ { -+ error ("%<%s%> must be by itself for %<-mharden-sls=%>", str); -+ break; -+ } -+ else -+ { -+ error ("invalid argument %<%s%> for %<-mharden-sls=%>", str); -+ break; -+ } -+ str = strtok_r (NULL, ",", &token_save); -+ } -+ aarch64_sls_hardening = (aarch64_sls_hardening_type) temp; -+ free (str_root); -+} -+ - /* Parses CONST_STR for branch protection features specified in - aarch64_branch_protect_types, and set any global variables required. Returns - the parsing result and assigns LAST_STR to the last processed token from -@@ -14738,6 +14811,9 @@ aarch64_override_options (void) - selected_arch = NULL; - selected_tune = NULL; - -+ if (aarch64_harden_sls_string) -+ aarch64_validate_sls_mitigation (aarch64_harden_sls_string); -+ - if (aarch64_branch_protection_string) - aarch64_validate_mbranch_protection (aarch64_branch_protection_string); - -diff --git a/gcc/config/aarch64/aarch64.opt b/gcc/config/aarch64/aarch64.opt -index d99d14c..5170361 100644 ---- a/gcc/config/aarch64/aarch64.opt -+++ b/gcc/config/aarch64/aarch64.opt -@@ -71,6 +71,10 @@ mgeneral-regs-only - Target Report RejectNegative Mask(GENERAL_REGS_ONLY) Save - Generate code which uses only the general registers. - -+mharden-sls= -+Target RejectNegative Joined Var(aarch64_harden_sls_string) -+Generate code to mitigate against straight line speculation. -+ - mfix-cortex-a53-835769 - Target Report Var(aarch64_fix_a53_err835769) Init(2) Save - Workaround for ARM Cortex-A53 Erratum number 835769. -diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi -index a2794a6..bd5b77a 100644 ---- a/gcc/doc/invoke.texi -+++ b/gcc/doc/invoke.texi -@@ -696,6 +696,7 @@ Objective-C and Objective-C++ Dialects}. - -msign-return-address=@var{scope} @gol - -mbranch-protection=@var{none}|@var{standard}|@var{pac-ret}[+@var{leaf} - +@var{b-key}]|@var{bti} @gol -+-mharden-sls=@var{opts} @gol - -march=@var{name} -mcpu=@var{name} -mtune=@var{name} @gol - -moverride=@var{string} -mverbose-cost-dump @gol - -mstack-protector-guard=@var{guard} -mstack-protector-guard-reg=@var{sysreg} @gol -@@ -17065,6 +17066,17 @@ functions. The optional argument @samp{b-key} can be used to sign the functions - with the B-key instead of the A-key. - @samp{bti} turns on branch target identification mechanism. - -+@item -mharden-sls=@var{opts} -+@opindex mharden-sls -+Enable compiler hardening against straight line speculation (SLS). -+@var{opts} is a comma-separated list of the following options: -+@table @samp -+@item retbr -+@item blr -+@end table -+In addition, @samp{-mharden-sls=all} enables all SLS hardening while -+@samp{-mharden-sls=none} disables all SLS hardening. -+ - @item -msve-vector-bits=@var{bits} - @opindex msve-vector-bits - Specify the number of bits in an SVE vector register. This option only has --- -2.7.4 - diff --git a/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch new file mode 100644 index 0000000000..5b1896ed69 --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0002-CVE-2021-42574.patch @@ -0,0 +1,2270 @@ +From bd5e882cf6e0def3dd1bc106075d59a303fe0d1e Mon Sep 17 00:00:00 2001 +From: David Malcolm <dmalcolm@redhat.com> +Date: Mon, 18 Oct 2021 18:55:31 -0400 +Subject: [PATCH] diagnostics: escape non-ASCII source bytes for certain + diagnostics +MIME-Version: 1.0 +Content-Type: text/plain; charset=utf8 +Content-Transfer-Encoding: 8bit + +This patch adds support to GCC's diagnostic subsystem for escaping certain +bytes and Unicode characters when quoting source code. + +Specifically, this patch adds a new flag rich_location::m_escape_on_output +which is a hint from a diagnostic that non-ASCII bytes in the pertinent +lines of the user's source code should be escaped when printed. + +The patch sets this for the following diagnostics: +- when complaining about stray bytes in the program (when these +are non-printable) +- when complaining about "null character(s) ignored"); +- for -Wnormalized= (and generate source ranges for such warnings) + +The escaping is controlled by a new option: + -fdiagnostics-escape-format=[unicode|bytes] + +For example, consider a diagnostic involing a source line containing the +string "before" followed by the Unicode character U+03C0 ("GREEK SMALL +LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF +(a stray UTF-8 trailing byte), followed by the string "after", where the +diagnostic highlights the U+03C0 character. + +By default, this line will be printed verbatim to the user when +reporting a diagnostic at it, as: + + beforeÏXafter + ^ + +(using X for the stray byte to avoid putting invalid UTF-8 in this +commit message) + +If the diagnostic sets the "escape" flag, it will be printed as: + + before<U+03C0><BF>after + ^~~~~~~~ + +with -fdiagnostics-escape-format=unicode (the default), or as: + + before<CF><80><BF>after + ^~~~~~~~ + +if the user supplies -fdiagnostics-escape-format=bytes. + +This only affects how the source is printed; it does not affect +how column numbers that are printed (as per -fdiagnostics-column-unit= +and -fdiagnostics-column-origin=). + +gcc/c-family/ChangeLog: + * c-lex.c (c_lex_with_flags): When complaining about non-printable + CPP_OTHER tokens, set the "escape on output" flag. + +gcc/ChangeLog: + * common.opt (fdiagnostics-escape-format=): New. + (diagnostics_escape_format): New enum. + (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. + (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. + * diagnostic-format-json.cc (json_end_diagnostic): Add + "escape-source" attribute. + * diagnostic-show-locus.c + (exploc_with_display_col::exploc_with_display_col): Replace + "tabstop" param with a cpp_char_column_policy and add an "aspect" + param. Use these to compute m_display_col accordingly. + (struct char_display_policy): New struct. + (layout::m_policy): New field. + (layout::m_escape_on_output): New field. + (def_policy): New function. + (make_range): Update for changes to exploc_with_display_col ctor. + (default_print_decoded_ch): New. + (width_per_escaped_byte): New. + (escape_as_bytes_width): New. + (escape_as_bytes_print): New. + (escape_as_unicode_width): New. + (escape_as_unicode_print): New. + (make_policy): New. + (layout::layout): Initialize new fields. Update m_exploc ctor + call for above change to ctor. + (layout::maybe_add_location_range): Update for changes to + exploc_with_display_col ctor. + (layout::calculate_x_offset_display): Update for change to + cpp_display_width. + (layout::print_source_line): Pass policy + to cpp_display_width_computation. Capture cpp_decoded_char when + calling process_next_codepoint. Move printing of source code to + m_policy.m_print_cb. + (line_label::line_label): Pass in policy rather than context. + (layout::print_any_labels): Update for change to line_label ctor. + (get_affected_range): Pass in policy rather than context, updating + calls to location_compute_display_column accordingly. + (get_printed_columns): Likewise, also for cpp_display_width. + (correction::correction): Pass in policy rather than tabstop. + (correction::compute_display_cols): Pass m_policy rather than + m_tabstop to cpp_display_width. + (correction::m_tabstop): Replace with... + (correction::m_policy): ...this. + (line_corrections::line_corrections): Pass in policy rather than + context. + (line_corrections::m_context): Replace with... + (line_corrections::m_policy): ...this. + (line_corrections::add_hint): Update to use m_policy rather than + m_context. + (line_corrections::add_hint): Likewise. + (layout::print_trailing_fixits): Likewise. + (selftest::test_display_widths): New. + (selftest::test_layout_x_offset_display_utf8): Update to use + policy rather than tabstop. + (selftest::test_one_liner_labels_utf8): Add test of escaping + source lines. + (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to + use policy rather than tabstop. + (selftest::test_overlapped_fixit_printing): Likewise. + (selftest::test_overlapped_fixit_printing_utf8): Likewise. + (selftest::test_overlapped_fixit_printing_2): Likewise. + (selftest::test_tab_expansion): Likewise. + (selftest::test_escaping_bytes_1): New. + (selftest::test_escaping_bytes_2): New. + (selftest::diagnostic_show_locus_c_tests): Call the new tests. + * diagnostic.c (diagnostic_initialize): Initialize + context->escape_format. + (convert_column_unit): Update to use default character width policy. + (selftest::test_diagnostic_get_location_text): Likewise. + * diagnostic.h (enum diagnostics_escape_format): New enum. + (diagnostic_context::escape_format): New field. + * doc/invoke.texi (-fdiagnostics-escape-format=): New option. + (-fdiagnostics-format=): Add "escape-source" attribute to examples + of JSON output, and document it. + * input.c (location_compute_display_column): Pass in "policy" + rather than "tabstop", passing to + cpp_byte_column_to_display_column. + (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. + * input.h (class cpp_char_column_policy): New forward decl. + (location_compute_display_column): Pass in "policy" rather than + "tabstop". + * opts.c (common_handle_option): Handle + OPT_fdiagnostics_escape_format_. + * selftest.c (temp_source_file::temp_source_file): New ctor + overload taking a size_t. + * selftest.h (temp_source_file::temp_source_file): Likewise. + +gcc/testsuite/ChangeLog: + * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume + "escape-source" attribute. + * c-c++-common/diagnostic-format-json-2.c: Likewise. + * c-c++-common/diagnostic-format-json-3.c: Likewise. + * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. + * c-c++-common/diagnostic-format-json-5.c: Likewise. + * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. + * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. + * gcc.dg/encoding-issues-bytes.c: New test. + * gcc.dg/encoding-issues-unicode.c: New test. + * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume + "escape-source" attribute. + * gfortran.dg/diagnostic-format-json-2.F90: Likewise. + * gfortran.dg/diagnostic-format-json-3.F90: Likewise. + +libcpp/ChangeLog: + * charset.c (convert_escape): Use encoding_rich_location when + complaining about nonprintable unknown escape sequences. + (cpp_display_width_computation::::cpp_display_width_computation): + Pass in policy rather than tabstop. + (cpp_display_width_computation::process_next_codepoint): Add "out" + param and populate *out if non-NULL. + (cpp_display_width_computation::advance_display_cols): Pass NULL + to process_next_codepoint. + (cpp_byte_column_to_display_column): Pass in policy rather than + tabstop. Pass NULL to process_next_codepoint. + (cpp_display_column_to_byte_column): Pass in policy rather than + tabstop. + * errors.c (cpp_diagnostic_get_current_location): New function, + splitting out the logic from... + (cpp_diagnostic): ...here. + (cpp_warning_at): New function. + (cpp_pedwarning_at): New function. + * include/cpplib.h (cpp_warning_at): New decl for rich_location. + (cpp_pedwarning_at): Likewise. + (struct cpp_decoded_char): New. + (struct cpp_char_column_policy): New. + (cpp_display_width_computation::cpp_display_width_computation): + Replace "tabstop" param with "policy". + (cpp_display_width_computation::process_next_codepoint): Add "out" + param. + (cpp_display_width_computation::m_tabstop): Replace with... + (cpp_display_width_computation::m_policy): ...this. + (cpp_byte_column_to_display_column): Replace "tabstop" param with + "policy". + (cpp_display_width): Likewise. + (cpp_display_column_to_byte_column): Likewise. + * include/line-map.h (rich_location::escape_on_output_p): New. + (rich_location::set_escape_on_output): New. + (rich_location::m_escape_on_output): New. + * internal.h (cpp_diagnostic_get_current_location): New decl. + (class encoding_rich_location): New. + * lex.c (skip_whitespace): Use encoding_rich_location when + complaining about null characters. + (warn_about_normalization): Generate a source range when + complaining about improperly normalized tokens, rather than just a + point, and use encoding_rich_location so that the source code + is escaped on printing. + * line-map.c (rich_location::rich_location): Initialize + m_escape_on_output. + +Signed-off-by: David Malcolm <dmalcolm@redhat.com> + +CVE: CVE-2021-42574 +Upstream-Status: Backport [https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=bd5e882cf6e0def3dd1bc106075d59a303fe0d1e] +Signed-off-by: Pgowda <pgowda.cve@gmail.com> + +--- + gcc/c-family/c-lex.c | 6 +- + gcc/common.opt | 13 + + gcc/diagnostic-format-json.cc | 3 + + gcc/diagnostic-show-locus.c | 580 +++++++++++++++--- + gcc/diagnostic.c | 10 +- + gcc/diagnostic.h | 18 + + gcc/doc/invoke.texi | 43 +- + gcc/input.c | 62 +- + gcc/input.h | 7 +- + gcc/opts.c | 4 + + gcc/selftest.c | 15 + + gcc/selftest.h | 2 + + .../c-c++-common/diagnostic-format-json-1.c | 1 + + .../c-c++-common/diagnostic-format-json-2.c | 1 + + .../c-c++-common/diagnostic-format-json-3.c | 1 + + .../c-c++-common/diagnostic-format-json-4.c | 2 + + .../c-c++-common/diagnostic-format-json-5.c | 1 + + .../gcc.dg/cpp/warn-normalized-4-bytes.c | 21 + + .../gcc.dg/cpp/warn-normalized-4-unicode.c | 19 + + gcc/testsuite/gcc.dg/encoding-issues-bytes.c | Bin 0 -> 595 bytes + .../gcc.dg/encoding-issues-unicode.c | Bin 0 -> 613 bytes + .../gfortran.dg/diagnostic-format-json-1.F90 | 1 + + .../gfortran.dg/diagnostic-format-json-2.F90 | 1 + + .../gfortran.dg/diagnostic-format-json-3.F90 | 1 + + libcpp/charset.c | 63 +- + libcpp/errors.c | 82 ++- + libcpp/include/cpplib.h | 76 ++- + libcpp/include/line-map.h | 13 + + libcpp/internal.h | 23 + + libcpp/lex.c | 38 +- + libcpp/line-map.c | 3 +- + 31 files changed, 942 insertions(+), 168 deletions(-) + create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c + create mode 100644 gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c + create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-bytes.c + create mode 100644 gcc/testsuite/gcc.dg/encoding-issues-unicode.c + +diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c +--- a/gcc/c-family/c-lex.c 2020-07-22 23:35:17.296384022 -0700 ++++ b/gcc/c-family/c-lex.c 2021-12-25 01:30:50.669689023 -0800 +@@ -587,7 +587,11 @@ c_lex_with_flags (tree *value, location_ + else if (ISGRAPH (c)) + error_at (*loc, "stray %qc in program", (int) c); + else +- error_at (*loc, "stray %<\\%o%> in program", (int) c); ++ { ++ rich_location rich_loc (line_table, *loc); ++ rich_loc.set_escape_on_output (true); ++ error_at (&rich_loc, "stray %<\\%o%> in program", (int) c); ++ } + } + goto retry; + +diff --git a/gcc/common.opt b/gcc/common.opt +--- a/gcc/common.opt 2021-12-25 01:29:12.915317374 -0800 ++++ b/gcc/common.opt 2021-12-25 01:30:50.669689023 -0800 +@@ -1337,6 +1337,10 @@ fdiagnostics-format= + Common Joined RejectNegative Enum(diagnostics_output_format) + -fdiagnostics-format=[text|json] Select output format. + ++fdiagnostics-escape-format= ++Common Joined RejectNegative Enum(diagnostics_escape_format) ++-fdiagnostics-escape-format=[unicode|bytes] Select how to escape non-printable-ASCII bytes in the source for diagnostics that suggest it. ++ + ; Required for these enum values. + SourceInclude + diagnostic.h +@@ -1351,6 +1355,15 @@ EnumValue + Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE) + + Enum ++Name(diagnostics_escape_format) Type(int) ++ ++EnumValue ++Enum(diagnostics_escape_format) String(unicode) Value(DIAGNOSTICS_ESCAPE_FORMAT_UNICODE) ++ ++EnumValue ++Enum(diagnostics_escape_format) String(bytes) Value(DIAGNOSTICS_ESCAPE_FORMAT_BYTES) ++ ++Enum + Name(diagnostics_output_format) Type(int) + + EnumValue +diff --git a/gcc/diagnostic.c b/gcc/diagnostic.c +--- a/gcc/diagnostic.c 2021-12-25 01:29:12.915317374 -0800 ++++ b/gcc/diagnostic.c 2021-12-25 01:30:50.669689023 -0800 +@@ -223,6 +223,7 @@ diagnostic_initialize (diagnostic_contex + context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY; + context->column_origin = 1; + context->tabstop = 8; ++ context->escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE; + context->edit_context_ptr = NULL; + context->diagnostic_group_nesting_depth = 0; + context->diagnostic_group_emission_count = 0; +@@ -2152,8 +2153,8 @@ test_diagnostic_get_location_text () + const char *const content = "smile \xf0\x9f\x98\x82\n"; + const int line_bytes = strlen (content) - 1; + const int def_tabstop = 8; +- const int display_width = cpp_display_width (content, line_bytes, +- def_tabstop); ++ const cpp_char_column_policy policy (def_tabstop, cpp_wcwidth); ++ const int display_width = cpp_display_width (content, line_bytes, policy); + ASSERT_EQ (line_bytes - 2, display_width); + temp_source_file tmp (SELFTEST_LOCATION, ".c", content); + const char *const fname = tmp.get_filename (); +diff --git a/gcc/diagnostic-format-json.cc b/gcc/diagnostic-format-json.cc +--- a/gcc/diagnostic-format-json.cc 2021-12-25 01:29:12.915317374 -0800 ++++ b/gcc/diagnostic-format-json.cc 2021-12-25 01:30:50.669689023 -0800 +@@ -264,6 +264,9 @@ json_end_diagnostic (diagnostic_context + json::value *path_value = context->make_json_for_path (context, path); + diag_obj->set ("path", path_value); + } ++ ++ diag_obj->set ("escape-source", ++ new json::literal (richloc->escape_on_output_p ())); + } + + /* No-op implementation of "begin_group_cb" for JSON output. */ +diff --git a/gcc/diagnostic.h b/gcc/diagnostic.h +--- a/gcc/diagnostic.h 2021-12-25 01:29:12.919317307 -0800 ++++ b/gcc/diagnostic.h 2021-12-25 01:30:50.669689023 -0800 +@@ -38,6 +38,20 @@ enum diagnostics_column_unit + DIAGNOSTICS_COLUMN_UNIT_BYTE + }; + ++/* An enum for controlling how to print non-ASCII characters/bytes when ++ a diagnostic suggests escaping the source code on output. */ ++ ++enum diagnostics_escape_format ++{ ++ /* Escape non-ASCII Unicode characters in the form <U+XXXX> and ++ non-UTF-8 bytes in the form <XX>. */ ++ DIAGNOSTICS_ESCAPE_FORMAT_UNICODE, ++ ++ /* Escape non-ASCII bytes in the form <XX> (thus showing the underlying ++ encoding of non-ASCII Unicode characters). */ ++ DIAGNOSTICS_ESCAPE_FORMAT_BYTES ++}; ++ + /* Enum for overriding the standard output format. */ + + enum diagnostics_output_format +@@ -303,6 +317,10 @@ struct diagnostic_context + /* The size of the tabstop for tab expansion. */ + int tabstop; + ++ /* How should non-ASCII/non-printable bytes be escaped when ++ a diagnostic suggests escaping the source code on output. */ ++ enum diagnostics_escape_format escape_format; ++ + /* If non-NULL, an edit_context to which fix-it hints should be + applied, for generating patches. */ + edit_context *edit_context_ptr; +diff --git a/gcc/diagnostic-show-locus.c b/gcc/diagnostic-show-locus.c +--- a/gcc/diagnostic-show-locus.c 2021-12-25 01:29:12.919317307 -0800 ++++ b/gcc/diagnostic-show-locus.c 2021-12-25 01:30:50.673688956 -0800 +@@ -175,10 +175,26 @@ enum column_unit { + class exploc_with_display_col : public expanded_location + { + public: +- exploc_with_display_col (const expanded_location &exploc, int tabstop) +- : expanded_location (exploc), +- m_display_col (location_compute_display_column (exploc, tabstop)) +- {} ++ exploc_with_display_col (const expanded_location &exploc, ++ const cpp_char_column_policy &policy, ++ enum location_aspect aspect) ++ : expanded_location (exploc), ++ m_display_col (location_compute_display_column (exploc, policy)) ++ { ++ if (exploc.column > 0) ++ { ++ /* m_display_col is now the final column of the byte. ++ If escaping has happened, we may want the first column instead. */ ++ if (aspect != LOCATION_ASPECT_FINISH) ++ { ++ expanded_location prev_exploc (exploc); ++ prev_exploc.column--; ++ int prev_display_col ++ = (location_compute_display_column (prev_exploc, policy)); ++ m_display_col = prev_display_col + 1; ++ } ++ } ++ } + + int m_display_col; + }; +@@ -313,6 +329,31 @@ test_line_span () + + #endif /* #if CHECKING_P */ + ++/* A bundle of information containing how to print unicode ++ characters and bytes when quoting source code. ++ ++ Provides a unified place to support escaping some subset ++ of characters to some format. ++ ++ Extends char_column_policy; printing is split out to avoid ++ libcpp having to know about pretty_printer. */ ++ ++struct char_display_policy : public cpp_char_column_policy ++{ ++ public: ++ char_display_policy (int tabstop, ++ int (*width_cb) (cppchar_t c), ++ void (*print_cb) (pretty_printer *pp, ++ const cpp_decoded_char &cp)) ++ : cpp_char_column_policy (tabstop, width_cb), ++ m_print_cb (print_cb) ++ { ++ } ++ ++ void (*m_print_cb) (pretty_printer *pp, ++ const cpp_decoded_char &cp); ++}; ++ + /* A class to control the overall layout when printing a diagnostic. + + The layout is determined within the constructor. +@@ -345,6 +386,8 @@ class layout + + void print_line (linenum_type row); + ++ void on_bad_codepoint (const char *ptr, cppchar_t ch, size_t ch_sz); ++ + private: + bool will_show_line_p (linenum_type row) const; + void print_leading_fixits (linenum_type row); +@@ -386,6 +429,7 @@ class layout + private: + diagnostic_context *m_context; + pretty_printer *m_pp; ++ char_display_policy m_policy; + location_t m_primary_loc; + exploc_with_display_col m_exploc; + colorizer m_colorizer; +@@ -398,6 +442,7 @@ class layout + auto_vec <line_span> m_line_spans; + int m_linenum_width; + int m_x_offset_display; ++ bool m_escape_on_output; + }; + + /* Implementation of "class colorizer". */ +@@ -646,6 +691,11 @@ layout_range::intersects_line_p (linenum + /* Default for when we don't care what the tab expansion is set to. */ + static const int def_tabstop = 8; + ++static cpp_char_column_policy def_policy () ++{ ++ return cpp_char_column_policy (8, cpp_wcwidth); ++} ++ + /* Create some expanded locations for testing layout_range. The filename + member of the explocs is set to the empty string. This member will only be + inspected by the calls to location_compute_display_column() made from the +@@ -662,10 +712,13 @@ make_range (int start_line, int start_co + = {"", start_line, start_col, NULL, false}; + const expanded_location finish_exploc + = {"", end_line, end_col, NULL, false}; +- return layout_range (exploc_with_display_col (start_exploc, def_tabstop), +- exploc_with_display_col (finish_exploc, def_tabstop), ++ return layout_range (exploc_with_display_col (start_exploc, def_policy (), ++ LOCATION_ASPECT_START), ++ exploc_with_display_col (finish_exploc, def_policy (), ++ LOCATION_ASPECT_FINISH), + SHOW_RANGE_WITHOUT_CARET, +- exploc_with_display_col (start_exploc, def_tabstop), ++ exploc_with_display_col (start_exploc, def_policy (), ++ LOCATION_ASPECT_CARET), + 0, NULL); + } + +@@ -950,6 +1003,164 @@ fixit_cmp (const void *p_a, const void * + return hint_a->get_start_loc () - hint_b->get_start_loc (); + } + ++/* Callbacks for use when not escaping the source. */ ++ ++/* The default callback for char_column_policy::m_width_cb is cpp_wcwidth. */ ++ ++/* Callback for char_display_policy::m_print_cb for printing source chars ++ when not escaping the source. */ ++ ++static void ++default_print_decoded_ch (pretty_printer *pp, ++ const cpp_decoded_char &decoded_ch) ++{ ++ for (const char *ptr = decoded_ch.m_start_byte; ++ ptr != decoded_ch.m_next_byte; ptr++) ++ { ++ if (*ptr == '\0' || *ptr == '\r') ++ { ++ pp_space (pp); ++ continue; ++ } ++ ++ pp_character (pp, *ptr); ++ } ++} ++ ++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */ ++ ++static const int width_per_escaped_byte = 4; ++ ++/* Callback for char_column_policy::m_width_cb for determining the ++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */ ++ ++static int ++escape_as_bytes_width (cppchar_t ch) ++{ ++ if (ch < 0x80 && ISPRINT (ch)) ++ return cpp_wcwidth (ch); ++ else ++ { ++ if (ch <= 0x7F) return 1 * width_per_escaped_byte; ++ if (ch <= 0x7FF) return 2 * width_per_escaped_byte; ++ if (ch <= 0xFFFF) return 3 * width_per_escaped_byte; ++ return 4 * width_per_escaped_byte; ++ } ++} ++ ++/* Callback for char_display_policy::m_print_cb for printing source chars ++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_BYTES. */ ++ ++static void ++escape_as_bytes_print (pretty_printer *pp, ++ const cpp_decoded_char &decoded_ch) ++{ ++ if (!decoded_ch.m_valid_ch) ++ { ++ for (const char *iter = decoded_ch.m_start_byte; ++ iter != decoded_ch.m_next_byte; ++iter) ++ { ++ char buf[16]; ++ sprintf (buf, "<%02x>", (unsigned char)*iter); ++ pp_string (pp, buf); ++ } ++ return; ++ } ++ ++ cppchar_t ch = decoded_ch.m_ch; ++ if (ch < 0x80 && ISPRINT (ch)) ++ pp_character (pp, ch); ++ else ++ { ++ for (const char *iter = decoded_ch.m_start_byte; ++ iter < decoded_ch.m_next_byte; ++iter) ++ { ++ char buf[16]; ++ sprintf (buf, "<%02x>", (unsigned char)*iter); ++ pp_string (pp, buf); ++ } ++ } ++} ++ ++/* Callbacks for use with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */ ++ ++/* Callback for char_column_policy::m_width_cb for determining the ++ display width when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */ ++ ++static int ++escape_as_unicode_width (cppchar_t ch) ++{ ++ if (ch < 0x80 && ISPRINT (ch)) ++ return cpp_wcwidth (ch); ++ else ++ { ++ // Width of "<U+%04x>" ++ if (ch > 0xfffff) ++ return 10; ++ else if (ch > 0xffff) ++ return 9; ++ else ++ return 8; ++ } ++} ++ ++/* Callback for char_display_policy::m_print_cb for printing source chars ++ when escaping with DIAGNOSTICS_ESCAPE_FORMAT_UNICODE. */ ++ ++static void ++escape_as_unicode_print (pretty_printer *pp, ++ const cpp_decoded_char &decoded_ch) ++{ ++ if (!decoded_ch.m_valid_ch) ++ { ++ escape_as_bytes_print (pp, decoded_ch); ++ return; ++ } ++ ++ cppchar_t ch = decoded_ch.m_ch; ++ if (ch < 0x80 && ISPRINT (ch)) ++ pp_character (pp, ch); ++ else ++ { ++ char buf[16]; ++ sprintf (buf, "<U+%04X>", ch); ++ pp_string (pp, buf); ++ } ++} ++ ++/* Populate a char_display_policy based on DC and RICHLOC. */ ++ ++static char_display_policy ++make_policy (const diagnostic_context &dc, ++ const rich_location &richloc) ++{ ++ /* The default is to not escape non-ASCII bytes. */ ++ char_display_policy result ++ (dc.tabstop, cpp_wcwidth, default_print_decoded_ch); ++ ++ /* If the diagnostic suggests escaping non-ASCII bytes, then ++ use policy from user-supplied options. */ ++ if (richloc.escape_on_output_p ()) ++ { ++ result.m_undecoded_byte_width = width_per_escaped_byte; ++ switch (dc.escape_format) ++ { ++ default: ++ gcc_unreachable (); ++ case DIAGNOSTICS_ESCAPE_FORMAT_UNICODE: ++ result.m_width_cb = escape_as_unicode_width; ++ result.m_print_cb = escape_as_unicode_print; ++ break; ++ case DIAGNOSTICS_ESCAPE_FORMAT_BYTES: ++ result.m_width_cb = escape_as_bytes_width; ++ result.m_print_cb = escape_as_bytes_print; ++ break; ++ } ++ } ++ ++ return result; ++} ++ + /* Implementation of class layout. */ + + /* Constructor for class layout. +@@ -966,8 +1177,10 @@ layout::layout (diagnostic_context * con + diagnostic_t diagnostic_kind) + : m_context (context), + m_pp (context->printer), ++ m_policy (make_policy (*context, *richloc)), + m_primary_loc (richloc->get_range (0)->m_loc), +- m_exploc (richloc->get_expanded_location (0), context->tabstop), ++ m_exploc (richloc->get_expanded_location (0), m_policy, ++ LOCATION_ASPECT_CARET), + m_colorizer (context, diagnostic_kind), + m_colorize_source_p (context->colorize_source_p), + m_show_labels_p (context->show_labels_p), +@@ -977,7 +1190,8 @@ layout::layout (diagnostic_context * con + m_fixit_hints (richloc->get_num_fixit_hints ()), + m_line_spans (1 + richloc->get_num_locations ()), + m_linenum_width (0), +- m_x_offset_display (0) ++ m_x_offset_display (0), ++ m_escape_on_output (richloc->escape_on_output_p ()) + { + for (unsigned int idx = 0; idx < richloc->get_num_locations (); idx++) + { +@@ -1063,10 +1277,13 @@ layout::maybe_add_location_range (const + + /* Everything is now known to be in the correct source file, + but it may require further sanitization. */ +- layout_range ri (exploc_with_display_col (start, m_context->tabstop), +- exploc_with_display_col (finish, m_context->tabstop), ++ layout_range ri (exploc_with_display_col (start, m_policy, ++ LOCATION_ASPECT_START), ++ exploc_with_display_col (finish, m_policy, ++ LOCATION_ASPECT_FINISH), + loc_range->m_range_display_kind, +- exploc_with_display_col (caret, m_context->tabstop), ++ exploc_with_display_col (caret, m_policy, ++ LOCATION_ASPECT_CARET), + original_idx, loc_range->m_label); + + /* If we have a range that finishes before it starts (perhaps +@@ -1400,7 +1617,7 @@ layout::calculate_x_offset_display () + = get_line_bytes_without_trailing_whitespace (line.get_buffer (), + line.length ()); + int eol_display_column +- = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop); ++ = cpp_display_width (line.get_buffer (), line_bytes, m_policy); + if (caret_display_column > eol_display_column + || !caret_display_column) + { +@@ -1479,7 +1696,7 @@ layout::print_source_line (linenum_type + /* This object helps to keep track of which display column we are at, which is + necessary for computing the line bounds in display units, for doing + tab expansion, and for implementing m_x_offset_display. */ +- cpp_display_width_computation dw (line, line_bytes, m_context->tabstop); ++ cpp_display_width_computation dw (line, line_bytes, m_policy); + + /* Skip the first m_x_offset_display display columns. In case the leading + portion that will be skipped ends with a character with wcwidth > 1, then +@@ -1527,7 +1744,8 @@ layout::print_source_line (linenum_type + tabs and replacing some control bytes with spaces as necessary. */ + const char *c = dw.next_byte (); + const int start_disp_col = dw.display_cols_processed () + 1; +- const int this_display_width = dw.process_next_codepoint (); ++ cpp_decoded_char cp; ++ const int this_display_width = dw.process_next_codepoint (&cp); + if (*c == '\t') + { + /* The returned display width is the number of spaces into which the +@@ -1536,15 +1754,6 @@ layout::print_source_line (linenum_type + pp_space (m_pp); + continue; + } +- if (*c == '\0' || *c == '\r') +- { +- /* cpp_wcwidth() promises to return 1 for all control bytes, and we +- want to output these as a single space too, so this case is +- actually the same as the '\t' case. */ +- gcc_assert (this_display_width == 1); +- pp_space (m_pp); +- continue; +- } + + /* We have a (possibly multibyte) character to output; update the line + bounds if it is not whitespace. */ +@@ -1556,7 +1765,8 @@ layout::print_source_line (linenum_type + } + + /* Output the character. */ +- while (c != dw.next_byte ()) pp_character (m_pp, *c++); ++ m_policy.m_print_cb (m_pp, cp); ++ c = dw.next_byte (); + } + print_newline (); + return lbounds; +@@ -1655,14 +1865,14 @@ layout::print_annotation_line (linenum_t + class line_label + { + public: +- line_label (diagnostic_context *context, int state_idx, int column, ++ line_label (const cpp_char_column_policy &policy, ++ int state_idx, int column, + label_text text) + : m_state_idx (state_idx), m_column (column), + m_text (text), m_label_line (0), m_has_vbar (true) + { + const int bytes = strlen (text.m_buffer); +- m_display_width +- = cpp_display_width (text.m_buffer, bytes, context->tabstop); ++ m_display_width = cpp_display_width (text.m_buffer, bytes, policy); + } + + /* Sorting is primarily by column, then by state index. */ +@@ -1722,7 +1932,7 @@ layout::print_any_labels (linenum_type r + if (text.m_buffer == NULL) + continue; + +- labels.safe_push (line_label (m_context, i, disp_col, text)); ++ labels.safe_push (line_label (m_policy, i, disp_col, text)); + } + } + +@@ -2002,7 +2212,7 @@ public: + + /* Get the range of bytes or display columns that HINT would affect. */ + static column_range +-get_affected_range (diagnostic_context *context, ++get_affected_range (const cpp_char_column_policy &policy, + const fixit_hint *hint, enum column_unit col_unit) + { + expanded_location exploc_start = expand_location (hint->get_start_loc ()); +@@ -2013,13 +2223,11 @@ get_affected_range (diagnostic_context * + int finish_column; + if (col_unit == CU_DISPLAY_COLS) + { +- start_column +- = location_compute_display_column (exploc_start, context->tabstop); ++ start_column = location_compute_display_column (exploc_start, policy); + if (hint->insertion_p ()) + finish_column = start_column - 1; + else +- finish_column +- = location_compute_display_column (exploc_finish, context->tabstop); ++ finish_column = location_compute_display_column (exploc_finish, policy); + } + else + { +@@ -2032,12 +2240,13 @@ get_affected_range (diagnostic_context * + /* Get the range of display columns that would be printed for HINT. */ + + static column_range +-get_printed_columns (diagnostic_context *context, const fixit_hint *hint) ++get_printed_columns (const cpp_char_column_policy &policy, ++ const fixit_hint *hint) + { + expanded_location exploc = expand_location (hint->get_start_loc ()); +- int start_column = location_compute_display_column (exploc, context->tabstop); ++ int start_column = location_compute_display_column (exploc, policy); + int hint_width = cpp_display_width (hint->get_string (), hint->get_length (), +- context->tabstop); ++ policy); + int final_hint_column = start_column + hint_width - 1; + if (hint->insertion_p ()) + { +@@ -2047,8 +2256,7 @@ get_printed_columns (diagnostic_context + { + exploc = expand_location (hint->get_next_loc ()); + --exploc.column; +- int finish_column +- = location_compute_display_column (exploc, context->tabstop); ++ int finish_column = location_compute_display_column (exploc, policy); + return column_range (start_column, + MAX (finish_column, final_hint_column)); + } +@@ -2066,13 +2274,13 @@ public: + column_range affected_columns, + column_range printed_columns, + const char *new_text, size_t new_text_len, +- int tabstop) ++ const cpp_char_column_policy &policy) + : m_affected_bytes (affected_bytes), + m_affected_columns (affected_columns), + m_printed_columns (printed_columns), + m_text (xstrdup (new_text)), + m_byte_length (new_text_len), +- m_tabstop (tabstop), ++ m_policy (policy), + m_alloc_sz (new_text_len + 1) + { + compute_display_cols (); +@@ -2090,7 +2298,7 @@ public: + + void compute_display_cols () + { +- m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop); ++ m_display_cols = cpp_display_width (m_text, m_byte_length, m_policy); + } + + void overwrite (int dst_offset, const char_span &src_span) +@@ -2118,7 +2326,7 @@ public: + char *m_text; + size_t m_byte_length; /* Not including null-terminator. */ + int m_display_cols; +- int m_tabstop; ++ const cpp_char_column_policy &m_policy; + size_t m_alloc_sz; + }; + +@@ -2154,15 +2362,16 @@ correction::ensure_terminated () + class line_corrections + { + public: +- line_corrections (diagnostic_context *context, const char *filename, ++ line_corrections (const char_display_policy &policy, ++ const char *filename, + linenum_type row) +- : m_context (context), m_filename (filename), m_row (row) ++ : m_policy (policy), m_filename (filename), m_row (row) + {} + ~line_corrections (); + + void add_hint (const fixit_hint *hint); + +- diagnostic_context *m_context; ++ const char_display_policy &m_policy; + const char *m_filename; + linenum_type m_row; + auto_vec <correction *> m_corrections; +@@ -2208,10 +2417,10 @@ source_line::source_line (const char *fi + void + line_corrections::add_hint (const fixit_hint *hint) + { +- column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES); +- column_range affected_columns = get_affected_range (m_context, hint, ++ column_range affected_bytes = get_affected_range (m_policy, hint, CU_BYTES); ++ column_range affected_columns = get_affected_range (m_policy, hint, + CU_DISPLAY_COLS); +- column_range printed_columns = get_printed_columns (m_context, hint); ++ column_range printed_columns = get_printed_columns (m_policy, hint); + + /* Potentially consolidate. */ + if (!m_corrections.is_empty ()) +@@ -2280,7 +2489,7 @@ line_corrections::add_hint (const fixit_ + printed_columns, + hint->get_string (), + hint->get_length (), +- m_context->tabstop)); ++ m_policy)); + } + + /* If there are any fixit hints on source line ROW, print them. +@@ -2294,7 +2503,7 @@ layout::print_trailing_fixits (linenum_t + { + /* Build a list of correction instances for the line, + potentially consolidating hints (for the sake of readability). */ +- line_corrections corrections (m_context, m_exploc.file, row); ++ line_corrections corrections (m_policy, m_exploc.file, row); + for (unsigned int i = 0; i < m_fixit_hints.length (); i++) + { + const fixit_hint *hint = m_fixit_hints[i]; +@@ -2635,6 +2844,59 @@ namespace selftest { + + /* Selftests for diagnostic_show_locus. */ + ++/* Verify that cpp_display_width correctly handles escaping. */ ++ ++static void ++test_display_widths () ++{ ++ gcc_rich_location richloc (UNKNOWN_LOCATION); ++ ++ /* U+03C0 "GREEK SMALL LETTER PI". */ ++ const char *pi = "\xCF\x80"; ++ /* U+1F642 "SLIGHTLY SMILING FACE". */ ++ const char *emoji = "\xF0\x9F\x99\x82"; ++ /* Stray trailing byte of a UTF-8 character. */ ++ const char *stray = "\xBF"; ++ /* U+10FFFF. */ ++ const char *max_codepoint = "\xF4\x8F\xBF\xBF"; ++ ++ /* No escaping. */ ++ { ++ test_diagnostic_context dc; ++ char_display_policy policy (make_policy (dc, richloc)); ++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 1); ++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 2); ++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 1); ++ /* Don't check width of U+10FFFF; it's in a private use plane. */ ++ } ++ ++ richloc.set_escape_on_output (true); ++ ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE; ++ char_display_policy policy (make_policy (dc, richloc)); ++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8); ++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 9); ++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4); ++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint), ++ policy), ++ strlen ("<U+10FFFF>")); ++ } ++ ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES; ++ char_display_policy policy (make_policy (dc, richloc)); ++ ASSERT_EQ (cpp_display_width (pi, strlen (pi), policy), 8); ++ ASSERT_EQ (cpp_display_width (emoji, strlen (emoji), policy), 16); ++ ASSERT_EQ (cpp_display_width (stray, strlen (stray), policy), 4); ++ ASSERT_EQ (cpp_display_width (max_codepoint, strlen (max_codepoint), ++ policy), ++ 16); ++ } ++} ++ + /* For precise tests of the layout, make clear where the source line will + start. test_left_margin sets the total byte count from the left side of the + screen to the start of source lines, after the line number and the separator, +@@ -2704,10 +2966,10 @@ test_layout_x_offset_display_utf8 (const + char_span lspan = location_get_source_line (tmp.get_filename (), 1); + ASSERT_EQ (line_display_cols, + cpp_display_width (lspan.get_buffer (), lspan.length (), +- def_tabstop)); ++ def_policy ())); + ASSERT_EQ (line_display_cols, + location_compute_display_column (expand_location (line_end), +- def_tabstop)); ++ def_policy ())); + ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1), + "\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8)); + +@@ -2855,12 +3117,13 @@ test_layout_x_offset_display_tab (const + ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1))); + for (int tabstop = 1; tabstop != num_tabstops; ++tabstop) + { ++ cpp_char_column_policy policy (tabstop, cpp_wcwidth); + ASSERT_EQ (line_bytes + extra_width[tabstop], + cpp_display_width (lspan.get_buffer (), lspan.length (), +- tabstop)); ++ policy)); + ASSERT_EQ (line_bytes + extra_width[tabstop], + location_compute_display_column (expand_location (line_end), +- tabstop)); ++ policy)); + } + + /* Check that the tab is expanded to the expected number of spaces. */ +@@ -3992,6 +4255,43 @@ test_one_liner_labels_utf8 () + " bb\xf0\x9f\x98\x82\xf0\x9f\x98\x82\n", + pp_formatted_text (dc.printer)); + } ++ ++ /* Example of escaping the source lines. */ ++ { ++ text_range_label label0 ("label 0\xf0\x9f\x98\x82"); ++ text_range_label label1 ("label 1\xcf\x80"); ++ text_range_label label2 ("label 2\xcf\x80"); ++ gcc_rich_location richloc (foo, &label0); ++ richloc.add_range (bar, SHOW_RANGE_WITHOUT_CARET, &label1); ++ richloc.add_range (field, SHOW_RANGE_WITHOUT_CARET, &label2); ++ richloc.set_escape_on_output (true); ++ ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" <U+1F602>_foo = <U+03C0>_bar.<U+1F602>_field<U+03C0>;\n" ++ " ^~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~\n" ++ " | | |\n" ++ " | | label 2\xcf\x80\n" ++ " | label 1\xcf\x80\n" ++ " label 0\xf0\x9f\x98\x82\n", ++ pp_formatted_text (dc.printer)); ++ } ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ ++ (" <f0><9f><98><82>_foo = <cf><80>_bar.<f0><9f><98><82>_field<cf><80>;\n" ++ " ^~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" ++ " | | |\n" ++ " | | label 2\xcf\x80\n" ++ " | label 1\xcf\x80\n" ++ " label 0\xf0\x9f\x98\x82\n", ++ pp_formatted_text (dc.printer)); ++ } ++ } + } + + /* Make sure that colorization codes don't interrupt a multibyte +@@ -4046,9 +4346,9 @@ test_diagnostic_show_locus_one_liner_utf + + char_span lspan = location_get_source_line (tmp.get_filename (), 1); + ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (), +- def_tabstop)); ++ def_policy ())); + ASSERT_EQ (25, location_compute_display_column (expand_location (line_end), +- def_tabstop)); ++ def_policy ())); + + test_one_liner_simple_caret_utf8 (); + test_one_liner_caret_and_range_utf8 (); +@@ -4434,30 +4734,31 @@ test_overlapped_fixit_printing (const li + pp_formatted_text (dc.printer)); + + /* Unit-test the line_corrections machinery. */ ++ char_display_policy policy (make_policy (dc, richloc)); + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (&dc, hint_0, CU_BYTES)); ++ get_affected_range (policy, hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); ++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (&dc, hint_1, CU_BYTES)); ++ get_affected_range (policy, hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); ++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); + ASSERT_EQ (column_range (29, 28), +- get_affected_range (&dc, hint_2, CU_BYTES)); ++ get_affected_range (policy, hint_2, CU_BYTES)); + ASSERT_EQ (column_range (29, 28), +- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2)); ++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (29, 29), get_printed_columns (policy, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (&dc, tmp.get_filename (), 1); ++ line_corrections lc (policy, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4649,30 +4950,31 @@ test_overlapped_fixit_printing_utf8 (con + pp_formatted_text (dc.printer)); + + /* Unit-test the line_corrections machinery. */ ++ char_display_policy policy (make_policy (dc, richloc)); + ASSERT_EQ (3, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); + ASSERT_EQ (column_range (14, 14), +- get_affected_range (&dc, hint_0, CU_BYTES)); ++ get_affected_range (policy, hint_0, CU_BYTES)); + ASSERT_EQ (column_range (12, 12), +- get_affected_range (&dc, hint_0, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0)); ++ get_affected_range (policy, hint_0, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (12, 22), get_printed_columns (policy, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); + ASSERT_EQ (column_range (22, 22), +- get_affected_range (&dc, hint_1, CU_BYTES)); ++ get_affected_range (policy, hint_1, CU_BYTES)); + ASSERT_EQ (column_range (18, 18), +- get_affected_range (&dc, hint_1, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1)); ++ get_affected_range (policy, hint_1, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (18, 20), get_printed_columns (policy, hint_1)); + const fixit_hint *hint_2 = richloc.get_fixit_hint (2); + ASSERT_EQ (column_range (35, 34), +- get_affected_range (&dc, hint_2, CU_BYTES)); ++ get_affected_range (policy, hint_2, CU_BYTES)); + ASSERT_EQ (column_range (30, 29), +- get_affected_range (&dc, hint_2, CU_DISPLAY_COLS)); +- ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2)); ++ get_affected_range (policy, hint_2, CU_DISPLAY_COLS)); ++ ASSERT_EQ (column_range (30, 30), get_printed_columns (policy, hint_2)); + + /* Add each hint in turn to a line_corrections instance, + and verify that they are consolidated into one correction instance + as expected. */ +- line_corrections lc (&dc, tmp.get_filename (), 1); ++ line_corrections lc (policy, tmp.get_filename (), 1); + + /* The first replace hint by itself. */ + lc.add_hint (hint_0); +@@ -4866,15 +5168,16 @@ test_overlapped_fixit_printing_2 (const + richloc.add_fixit_insert_before (col_21, "}"); + + /* These fixits should be accepted; they can't be consolidated. */ ++ char_display_policy policy (make_policy (dc, richloc)); + ASSERT_EQ (2, richloc.get_num_fixit_hints ()); + const fixit_hint *hint_0 = richloc.get_fixit_hint (0); + ASSERT_EQ (column_range (23, 22), +- get_affected_range (&dc, hint_0, CU_BYTES)); +- ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0)); ++ get_affected_range (policy, hint_0, CU_BYTES)); ++ ASSERT_EQ (column_range (23, 23), get_printed_columns (policy, hint_0)); + const fixit_hint *hint_1 = richloc.get_fixit_hint (1); + ASSERT_EQ (column_range (21, 20), +- get_affected_range (&dc, hint_1, CU_BYTES)); +- ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1)); ++ get_affected_range (policy, hint_1, CU_BYTES)); ++ ASSERT_EQ (column_range (21, 21), get_printed_columns (policy, hint_1)); + + /* Verify that they're printed correctly. */ + diagnostic_show_locus (&dc, &richloc, DK_ERROR); +@@ -5141,10 +5444,11 @@ test_tab_expansion (const line_table_cas + ....................123 45678901234 56789012345 columns */ + + const int tabstop = 8; ++ cpp_char_column_policy policy (tabstop, cpp_wcwidth); + const int first_non_ws_byte_col = 7; + const int right_quote_byte_col = 15; + const int last_byte_col = 25; +- ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop)); ++ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, policy)); + + temp_source_file tmp (SELFTEST_LOCATION, ".c", content); + line_table_test ltt (case_); +@@ -5187,6 +5491,114 @@ test_tab_expansion (const line_table_cas + } + } + ++/* Verify that the escaping machinery can cope with a variety of different ++ invalid bytes. */ ++ ++static void ++test_escaping_bytes_1 (const line_table_case &case_) ++{ ++ const char content[] = "before\0\1\2\3\r\x80\xff""after\n"; ++ const size_t sz = sizeof (content); ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz); ++ line_table_test ltt (case_); ++ const line_map_ordinary *ord_map = linemap_check_ordinary ++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0)); ++ linemap_line_start (line_table, 1, 100); ++ ++ location_t finish ++ = linemap_position_for_line_and_column (line_table, ord_map, 1, ++ strlen (content)); ++ ++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Locations of the NUL and \r bytes. */ ++ location_t nul_loc ++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 7); ++ location_t r_loc ++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 11); ++ gcc_rich_location richloc (nul_loc); ++ richloc.add_range (r_loc); ++ ++ { ++ test_diagnostic_context dc; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" before \1\2\3 \x80\xff""after\n" ++ " ^ ~\n", ++ pp_formatted_text (dc.printer)); ++ } ++ richloc.set_escape_on_output (true); ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ ++ (" before<U+0000><U+0001><U+0002><U+0003><U+000D><80><ff>after\n" ++ " ^~~~~~~~ ~~~~~~~~\n", ++ pp_formatted_text (dc.printer)); ++ } ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" before<00><01><02><03><0d><80><ff>after\n" ++ " ^~~~ ~~~~\n", ++ pp_formatted_text (dc.printer)); ++ } ++} ++ ++/* As above, but verify that we handle the initial byte of a line ++ correctly. */ ++ ++static void ++test_escaping_bytes_2 (const line_table_case &case_) ++{ ++ const char content[] = "\0after\n"; ++ const size_t sz = sizeof (content); ++ temp_source_file tmp (SELFTEST_LOCATION, ".c", content, sz); ++ line_table_test ltt (case_); ++ const line_map_ordinary *ord_map = linemap_check_ordinary ++ (linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 0)); ++ linemap_line_start (line_table, 1, 100); ++ ++ location_t finish ++ = linemap_position_for_line_and_column (line_table, ord_map, 1, ++ strlen (content)); ++ ++ if (finish > LINE_MAP_MAX_LOCATION_WITH_COLS) ++ return; ++ ++ /* Location of the NUL byte. */ ++ location_t nul_loc ++ = linemap_position_for_line_and_column (line_table, ord_map, 1, 1); ++ gcc_rich_location richloc (nul_loc); ++ ++ { ++ test_diagnostic_context dc; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" after\n" ++ " ^\n", ++ pp_formatted_text (dc.printer)); ++ } ++ richloc.set_escape_on_output (true); ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_UNICODE; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" <U+0000>after\n" ++ " ^~~~~~~~\n", ++ pp_formatted_text (dc.printer)); ++ } ++ { ++ test_diagnostic_context dc; ++ dc.escape_format = DIAGNOSTICS_ESCAPE_FORMAT_BYTES; ++ diagnostic_show_locus (&dc, &richloc, DK_ERROR); ++ ASSERT_STREQ (" <00>after\n" ++ " ^~~~\n", ++ pp_formatted_text (dc.printer)); ++ } ++} ++ + /* Verify that line numbers are correctly printed for the case of + a multiline range in which the width of the line numbers changes + (e.g. from "9" to "10"). */ +@@ -5243,6 +5655,8 @@ diagnostic_show_locus_c_tests () + test_layout_range_for_single_line (); + test_layout_range_for_multiple_lines (); + ++ test_display_widths (); ++ + for_each_line_table_case (test_layout_x_offset_display_utf8); + for_each_line_table_case (test_layout_x_offset_display_tab); + +@@ -5263,6 +5677,8 @@ diagnostic_show_locus_c_tests () + for_each_line_table_case (test_fixit_replace_containing_newline); + for_each_line_table_case (test_fixit_deletion_affecting_newline); + for_each_line_table_case (test_tab_expansion); ++ for_each_line_table_case (test_escaping_bytes_1); ++ for_each_line_table_case (test_escaping_bytes_2); + + test_line_numbers_multiline_range (); + } +diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi +--- a/gcc/doc/invoke.texi 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/doc/invoke.texi 2021-12-25 01:30:50.681688823 -0800 +@@ -295,7 +295,8 @@ Objective-C and Objective-C++ Dialects}. + -fdiagnostics-show-path-depths @gol + -fno-show-column @gol + -fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol +--fdiagnostics-column-origin=@var{origin}} ++-fdiagnostics-column-origin=@var{origin} @gol ++-fdiagnostics-escape-format=@r{[}unicode@r{|}bytes@r{]}} + + @item Warning Options + @xref{Warning Options,,Options to Request or Suppress Warnings}. +@@ -4451,6 +4452,38 @@ first column. The default value of 1 co + behavior and to the GNU style guide. Some utilities may perform better with an + origin of 0; any non-negative value may be specified. + ++@item -fdiagnostics-escape-format=@var{FORMAT} ++@opindex fdiagnostics-escape-format ++When GCC prints pertinent source lines for a diagnostic it normally attempts ++to print the source bytes directly. However, some diagnostics relate to encoding ++issues in the source file, such as malformed UTF-8, or issues with Unicode ++normalization. These diagnostics are flagged so that GCC will escape bytes ++that are not printable ASCII when printing their pertinent source lines. ++ ++This option controls how such bytes should be escaped. ++ ++The default @var{FORMAT}, @samp{unicode} displays Unicode characters that ++are not printable ASCII in the form @samp{<U+XXXX>}, and bytes that do not ++correspond to a Unicode character validly-encoded in UTF-8-encoded will be ++displayed as hexadecimal in the form @samp{<XX>}. ++ ++For example, a source line containing the string @samp{before} followed by the ++Unicode character U+03C0 (``GREEK SMALL LETTER PI'', with UTF-8 encoding ++0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by ++the string @samp{after} will be printed for such a diagnostic as: ++ ++@smallexample ++ before<U+03C0><BF>after ++@end smallexample ++ ++Setting @var{FORMAT} to @samp{bytes} will display all non-printable-ASCII bytes ++in the form @samp{<XX>}, thus showing the underlying encoding of non-ASCII ++Unicode characters. For the example above, the following will be printed: ++ ++@smallexample ++ before<CF><80><BF>after ++@end smallexample ++ + @item -fdiagnostics-format=@var{FORMAT} + @opindex fdiagnostics-format + Select a different format for printing diagnostics. +@@ -4518,9 +4551,11 @@ might be printed in JSON form (after for + @} + @} + ], ++ "escape-source": false, + "message": "...this statement, but the latter is @dots{}" + @} + ] ++ "escape-source": false, + "column-origin": 1, + @}, + @dots{} +@@ -4607,6 +4642,7 @@ of the expression, which have labels. I + "label": "T @{aka struct t@}" + @} + ], ++ "escape-source": false, + "message": "invalid operands to binary + @dots{}" + @} + @end smallexample +@@ -4660,6 +4696,7 @@ might be printed in JSON form as: + @} + @} + ], ++ "escape-source": false, + "message": "\u2018struct s\u2019 has no member named @dots{}" + @} + @end smallexample +@@ -4717,6 +4754,10 @@ For example, the intraprocedural example + ] + @end smallexample + ++Diagnostics have a boolean attribute @code{escape-source}, hinting whether ++non-ASCII bytes should be escaped when printing the pertinent lines of ++source code (@code{true} for diagnostics involving source encoding issues). ++ + @end table + + @node Warning Options +diff --git a/gcc/input.c b/gcc/input.c +--- a/gcc/input.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/input.c 2021-12-25 01:30:50.681688823 -0800 +@@ -913,7 +913,8 @@ make_location (location_t caret, source_ + source line in order to calculate the display width. If that cannot be done + for any reason, then returns the byte column as a fallback. */ + int +-location_compute_display_column (expanded_location exploc, int tabstop) ++location_compute_display_column (expanded_location exploc, ++ const cpp_char_column_policy &policy) + { + if (!(exploc.file && *exploc.file && exploc.line && exploc.column)) + return exploc.column; +@@ -921,7 +922,7 @@ location_compute_display_column (expande + /* If line is NULL, this function returns exploc.column which is the + desired fallback. */ + return cpp_byte_column_to_display_column (line.get_buffer (), line.length (), +- exploc.column, tabstop); ++ exploc.column, policy); + } + + /* Dump statistics to stderr about the memory usage of the line_table +@@ -3609,43 +3610,50 @@ test_line_offset_overflow () + void test_cpp_utf8 () + { + const int def_tabstop = 8; ++ cpp_char_column_policy policy (def_tabstop, cpp_wcwidth); ++ + /* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */ + { +- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop); ++ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, policy); + ASSERT_EQ (8, w_bad); +- int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop); ++ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, policy); + ASSERT_EQ (5, w_ctrl); + } + + /* Verify that wcwidth of valid UTF-8 is as expected. */ + { +- const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop); ++ const int w_pi = cpp_display_width ("\xcf\x80", 2, policy); + ASSERT_EQ (1, w_pi); +- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop); ++ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, policy); + ASSERT_EQ (2, w_emoji); + const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2, +- def_tabstop); ++ policy); + ASSERT_EQ (1, w_umlaut_precomposed); + const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3, +- def_tabstop); ++ policy); + ASSERT_EQ (1, w_umlaut_combining); +- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop); ++ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, policy); + ASSERT_EQ (2, w_han); +- const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop); ++ const int w_ascii = cpp_display_width ("GCC", 3, policy); + ASSERT_EQ (3, w_ascii); + const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82" + "\x9f! \xe4\xb8\xba y\xcc\x88", +- 24, def_tabstop); ++ 24, policy); + ASSERT_EQ (18, w_mixed); + } + + /* Verify that display width properly expands tabs. */ + { + const char *tstr = "\tabc\td"; +- ASSERT_EQ (6, cpp_display_width (tstr, 6, 1)); +- ASSERT_EQ (10, cpp_display_width (tstr, 6, 3)); +- ASSERT_EQ (17, cpp_display_width (tstr, 6, 8)); +- ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8)); ++ ASSERT_EQ (6, cpp_display_width (tstr, 6, ++ cpp_char_column_policy (1, cpp_wcwidth))); ++ ASSERT_EQ (10, cpp_display_width (tstr, 6, ++ cpp_char_column_policy (3, cpp_wcwidth))); ++ ASSERT_EQ (17, cpp_display_width (tstr, 6, ++ cpp_char_column_policy (8, cpp_wcwidth))); ++ ASSERT_EQ (1, ++ cpp_display_column_to_byte_column ++ (tstr, 6, 7, cpp_char_column_policy (8, cpp_wcwidth))); + } + + /* Verify that cpp_byte_column_to_display_column can go past the end, +@@ -3658,13 +3666,13 @@ void test_cpp_utf8 () + /* 111122223456 + Byte columns. */ + +- ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop)); ++ ASSERT_EQ (5, cpp_display_width (str, 6, policy)); + ASSERT_EQ (105, +- cpp_byte_column_to_display_column (str, 6, 106, def_tabstop)); ++ cpp_byte_column_to_display_column (str, 6, 106, policy)); + ASSERT_EQ (10000, +- cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop)); ++ cpp_byte_column_to_display_column (NULL, 0, 10000, policy)); + ASSERT_EQ (0, +- cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop)); ++ cpp_byte_column_to_display_column (NULL, 10000, 0, policy)); + } + + /* Verify that cpp_display_column_to_byte_column can go past the end, +@@ -3678,25 +3686,25 @@ void test_cpp_utf8 () + /* 000000000000000000000000000000000111111 + 111122223333444456666777788889999012345 + Byte columns. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, policy)); + ASSERT_EQ (15, +- cpp_display_column_to_byte_column (str, 15, 11, def_tabstop)); ++ cpp_display_column_to_byte_column (str, 15, 11, policy)); + ASSERT_EQ (115, +- cpp_display_column_to_byte_column (str, 15, 111, def_tabstop)); ++ cpp_display_column_to_byte_column (str, 15, 111, policy)); + ASSERT_EQ (10000, +- cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop)); ++ cpp_display_column_to_byte_column (NULL, 0, 10000, policy)); + ASSERT_EQ (0, +- cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop)); ++ cpp_display_column_to_byte_column (NULL, 10000, 0, policy)); + + /* Verify that we do not interrupt a UTF-8 sequence. */ +- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop)); ++ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, policy)); + + for (int byte_col = 1; byte_col <= 15; ++byte_col) + { + const int disp_col +- = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop); ++ = cpp_byte_column_to_display_column (str, 15, byte_col, policy); + const int byte_col2 +- = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop); ++ = cpp_display_column_to_byte_column (str, 15, disp_col, policy); + + /* If we ask for the display column in the middle of a UTF-8 + sequence, it will return the length of the partial sequence, +diff --git a/gcc/input.h b/gcc/input.h +--- a/gcc/input.h 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/input.h 2021-12-25 01:30:50.681688823 -0800 +@@ -39,8 +39,11 @@ STATIC_ASSERT (BUILTINS_LOCATION < RESER + extern bool is_location_from_builtin_token (location_t); + extern expanded_location expand_location (location_t); + +-extern int location_compute_display_column (expanded_location exploc, +- int tabstop); ++class cpp_char_column_policy; ++ ++extern int ++location_compute_display_column (expanded_location exploc, ++ const cpp_char_column_policy &policy); + + /* A class capturing the bounds of a buffer, to allow for run-time + bounds-checking in a checked build. */ +diff --git a/gcc/opts.c b/gcc/opts.c +--- a/gcc/opts.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/opts.c 2021-12-25 01:30:50.681688823 -0800 +@@ -2447,6 +2447,10 @@ common_handle_option (struct gcc_options + dc->column_origin = value; + break; + ++ case OPT_fdiagnostics_escape_format_: ++ dc->escape_format = (enum diagnostics_escape_format)value; ++ break; ++ + case OPT_fdiagnostics_show_cwe: + dc->show_cwe = value; + break; +diff --git a/gcc/selftest.c b/gcc/selftest.c +--- a/gcc/selftest.c 2020-07-22 23:35:17.820389797 -0700 ++++ b/gcc/selftest.c 2021-12-25 01:30:50.681688823 -0800 +@@ -193,6 +193,21 @@ temp_source_file::temp_source_file (cons + fclose (out); + } + ++/* As above, but with a size, to allow for NUL bytes in CONTENT. */ ++ ++temp_source_file::temp_source_file (const location &loc, ++ const char *suffix, ++ const char *content, ++ size_t sz) ++: named_temp_file (suffix) ++{ ++ FILE *out = fopen (get_filename (), "w"); ++ if (!out) ++ fail_formatted (loc, "unable to open tempfile: %s", get_filename ()); ++ fwrite (content, sz, 1, out); ++ fclose (out); ++} ++ + /* Avoid introducing locale-specific differences in the results + by hardcoding open_quote and close_quote. */ + +diff --git a/gcc/selftest.h b/gcc/selftest.h +--- a/gcc/selftest.h 2020-07-22 23:35:17.820389797 -0700 ++++ b/gcc/selftest.h 2021-12-25 01:30:50.681688823 -0800 +@@ -112,6 +112,8 @@ class temp_source_file : public named_te + public: + temp_source_file (const location &loc, const char *suffix, + const char *content); ++ temp_source_file (const location &loc, const char *suffix, ++ const char *content, size_t sz); + }; + + /* RAII-style class for avoiding introducing locale-specific differences +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-1.c 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + /* { dg-regexp "\"kind\": \"error\"" } */ + /* { dg-regexp "\"column-origin\": 1" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + /* { dg-regexp "\"message\": \"#error message\"" } */ + + /* { dg-regexp "\"caret\": \{" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-2.c 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + /* { dg-regexp "\"kind\": \"warning\"" } */ + /* { dg-regexp "\"column-origin\": 1" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Wcpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-3.c 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + /* { dg-regexp "\"kind\": \"error\"" } */ + /* { dg-regexp "\"column-origin\": 1" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + /* { dg-regexp "\"message\": \"#warning message\"" } */ + /* { dg-regexp "\"option\": \"-Werror=cpp\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */ +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-4.c 2021-12-25 01:30:50.681688823 -0800 +@@ -19,6 +19,7 @@ int test (void) + + /* { dg-regexp "\"kind\": \"note\"" } */ + /* { dg-regexp "\"message\": \"...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'\"" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + + /* { dg-regexp "\"caret\": \{" } */ + /* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */ +@@ -39,6 +40,7 @@ int test (void) + /* { dg-regexp "\"kind\": \"warning\"" } */ + /* { dg-regexp "\"column-origin\": 1" } */ + /* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + /* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */ + /* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */ + +diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c +--- a/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:29:12.927317174 -0800 ++++ b/gcc/testsuite/c-c++-common/diagnostic-format-json-5.c 2021-12-25 01:30:50.681688823 -0800 +@@ -14,6 +14,7 @@ int test (struct s *ptr) + + /* { dg-regexp "\"kind\": \"error\"" } */ + /* { dg-regexp "\"column-origin\": 1" } */ ++/* { dg-regexp "\"escape-source\": false" } */ + /* { dg-regexp "\"message\": \".*\"" } */ + + /* Verify fix-it hints. */ +diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c +--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-bytes.c 2021-12-25 01:30:50.681688823 -0800 +@@ -0,0 +1,21 @@ ++// { dg-do preprocess } ++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=bytes" } ++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */ ++ ++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e. ++ U+0F42 TIBETAN LETTER GA: འ++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ ++ ++ The UTF-8 encoding of U+0F43 TIBETAN LETTER GHA is: E0 BD 83. */ ++ ++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." } ++/* { dg-begin-multiline-output "" } ++ foo before_\u0F43_after bar ++ ^~~~~~~~~~~~~~~~~~~ ++ { dg-end-multiline-output "" } */ ++ ++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." } ++/* { dg-begin-multiline-output "" } ++ foo before_<e0><bd><83>_after bar ++ ^~~~~~~~~~~~~~~~~~~~~~~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c +--- a/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/gcc.dg/cpp/warn-normalized-4-unicode.c 2021-12-25 01:30:50.681688823 -0800 +@@ -0,0 +1,19 @@ ++// { dg-do preprocess } ++// { dg-options "-std=gnu99 -Werror=normalized=nfc -fdiagnostics-show-caret -fdiagnostics-escape-format=unicode" } ++/* { dg-message "some warnings being treated as errors" "" {target "*-*-*"} 0 } */ ++ ++/* འ= U+0F43 TIBETAN LETTER GHA, which has decomposition "0F42 0FB7" i.e. ++ U+0F42 TIBETAN LETTER GA: འ++ U+0FB7 TIBETAN SUBJOINED LETTER HA: ྷ */ ++ ++foo before_\u0F43_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." } ++/* { dg-begin-multiline-output "" } ++ foo before_\u0F43_after bar ++ ^~~~~~~~~~~~~~~~~~~ ++ { dg-end-multiline-output "" } */ ++ ++foo before_à½_after bar // { dg-error "`before_.U00000f43_after' is not in NFC .-Werror=normalized=." } ++/* { dg-begin-multiline-output "" } ++ foo before_<U+0F43>_after bar ++ ^~~~~~~~~~~~~~~~~~~~~ ++ { dg-end-multiline-output "" } */ +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:29:12.931317107 -0800 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-1.F90 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + ! { dg-regexp "\"kind\": \"error\"" } + ! { dg-regexp "\"column-origin\": 1" } ++! { dg-regexp "\"escape-source\": false" } + ! { dg-regexp "\"message\": \"#error message\"" } + + ! { dg-regexp "\"caret\": \{" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:29:12.931317107 -0800 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-2.F90 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + ! { dg-regexp "\"kind\": \"warning\"" } + ! { dg-regexp "\"column-origin\": 1" } ++! { dg-regexp "\"escape-source\": false" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Wcpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +diff --git a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 +--- a/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:29:12.931317107 -0800 ++++ b/gcc/testsuite/gfortran.dg/diagnostic-format-json-3.F90 2021-12-25 01:30:50.681688823 -0800 +@@ -9,6 +9,7 @@ + + ! { dg-regexp "\"kind\": \"error\"" } + ! { dg-regexp "\"column-origin\": 1" } ++! { dg-regexp "\"escape-source\": false" } + ! { dg-regexp "\"message\": \"#warning message\"" } + ! { dg-regexp "\"option\": \"-Werror=cpp\"" } + ! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" } +diff --git a/libcpp/charset.c b/libcpp/charset.c +--- a/libcpp/charset.c 2021-12-25 01:29:12.931317107 -0800 ++++ b/libcpp/charset.c 2021-12-25 01:30:50.681688823 -0800 +@@ -1549,12 +1549,14 @@ convert_escape (cpp_reader *pfile, const + "unknown escape sequence: '\\%c'", (int) c); + else + { ++ encoding_rich_location rich_loc (pfile); ++ + /* diagnostic.c does not support "%03o". When it does, this + code can use %03o directly in the diagnostic again. */ + char buf[32]; + sprintf(buf, "%03o", (int) c); +- cpp_error (pfile, CPP_DL_PEDWARN, +- "unknown escape sequence: '\\%s'", buf); ++ cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc, ++ "unknown escape sequence: '\\%s'", buf); + } + } + +@@ -2277,14 +2279,16 @@ cpp_string_location_reader::get_next () + } + + cpp_display_width_computation:: +-cpp_display_width_computation (const char *data, int data_length, int tabstop) : ++cpp_display_width_computation (const char *data, int data_length, ++ const cpp_char_column_policy &policy) : + m_begin (data), + m_next (m_begin), + m_bytes_left (data_length), +- m_tabstop (tabstop), ++ m_policy (policy), + m_display_cols (0) + { +- gcc_assert (m_tabstop > 0); ++ gcc_assert (policy.m_tabstop > 0); ++ gcc_assert (policy.m_width_cb); + } + + +@@ -2296,19 +2300,28 @@ cpp_display_width_computation (const cha + point to a valid UTF-8-encoded sequence, then it will be treated as a single + byte with display width 1. m_cur_display_col is the current display column, + relative to which tab stops should be expanded. Returns the display width of +- the codepoint just processed. */ ++ the codepoint just processed. ++ If OUT is non-NULL, it is populated. */ + + int +-cpp_display_width_computation::process_next_codepoint () ++cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out) + { + cppchar_t c; + int next_width; + ++ if (out) ++ out->m_start_byte = m_next; ++ + if (*m_next == '\t') + { + ++m_next; + --m_bytes_left; +- next_width = m_tabstop - (m_display_cols % m_tabstop); ++ next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop); ++ if (out) ++ { ++ out->m_ch = '\t'; ++ out->m_valid_ch = true; ++ } + } + else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c) + != 0) +@@ -2318,14 +2331,24 @@ cpp_display_width_computation::process_n + of one. */ + ++m_next; + --m_bytes_left; +- next_width = 1; ++ next_width = m_policy.m_undecoded_byte_width; ++ if (out) ++ out->m_valid_ch = false; + } + else + { + /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */ +- next_width = cpp_wcwidth (c); ++ next_width = m_policy.m_width_cb (c); ++ if (out) ++ { ++ out->m_ch = c; ++ out->m_valid_ch = true; ++ } + } + ++ if (out) ++ out->m_next_byte = m_next; ++ + m_display_cols += next_width; + return next_width; + } +@@ -2341,7 +2364,7 @@ cpp_display_width_computation::advance_d + const int start = m_display_cols; + const int target = start + n; + while (m_display_cols < target && !done ()) +- process_next_codepoint (); ++ process_next_codepoint (NULL); + return m_display_cols - start; + } + +@@ -2349,29 +2372,33 @@ cpp_display_width_computation::advance_d + how many display columns are occupied by the first COLUMN bytes. COLUMN + may exceed DATA_LENGTH, in which case the phantom bytes at the end are + treated as if they have display width 1. Tabs are expanded to the next tab +- stop, relative to the start of DATA. */ ++ stop, relative to the start of DATA, and non-printable-ASCII characters ++ will be escaped as per POLICY. */ + + int + cpp_byte_column_to_display_column (const char *data, int data_length, +- int column, int tabstop) ++ int column, ++ const cpp_char_column_policy &policy) + { + const int offset = MAX (0, column - data_length); +- cpp_display_width_computation dw (data, column - offset, tabstop); ++ cpp_display_width_computation dw (data, column - offset, policy); + while (!dw.done ()) +- dw.process_next_codepoint (); ++ dw.process_next_codepoint (NULL); + return dw.display_cols_processed () + offset; + } + + /* For the string of length DATA_LENGTH bytes that begins at DATA, compute + the least number of bytes that will result in at least DISPLAY_COL display + columns. The return value may exceed DATA_LENGTH if the entire string does +- not occupy enough display columns. */ ++ not occupy enough display columns. Non-printable-ASCII characters ++ will be escaped as per POLICY. */ + + int + cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col, int tabstop) ++ int display_col, ++ const cpp_char_column_policy &policy) + { +- cpp_display_width_computation dw (data, data_length, tabstop); ++ cpp_display_width_computation dw (data, data_length, policy); + const int avail_display = dw.advance_display_cols (display_col); + return dw.bytes_processed () + MAX (0, display_col - avail_display); + } +diff --git a/libcpp/errors.c b/libcpp/errors.c +--- a/libcpp/errors.c 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/errors.c 2021-12-25 01:30:50.681688823 -0800 +@@ -27,6 +27,31 @@ along with this program; see the file CO + #include "cpplib.h" + #include "internal.h" + ++/* Get a location_t for the current location in PFILE, ++ generally that of the previously lexed token. */ ++ ++location_t ++cpp_diagnostic_get_current_location (cpp_reader *pfile) ++{ ++ if (CPP_OPTION (pfile, traditional)) ++ { ++ if (pfile->state.in_directive) ++ return pfile->directive_line; ++ else ++ return pfile->line_table->highest_line; ++ } ++ /* We don't want to refer to a token before the beginning of the ++ current run -- that is invalid. */ ++ else if (pfile->cur_token == pfile->cur_run->base) ++ { ++ return 0; ++ } ++ else ++ { ++ return pfile->cur_token[-1].src_loc; ++ } ++} ++ + /* Print a diagnostic at the given location. */ + + ATTRIBUTE_FPTR_PRINTF(5,0) +@@ -52,25 +77,7 @@ cpp_diagnostic (cpp_reader * pfile, enum + enum cpp_warning_reason reason, + const char *msgid, va_list *ap) + { +- location_t src_loc; +- +- if (CPP_OPTION (pfile, traditional)) +- { +- if (pfile->state.in_directive) +- src_loc = pfile->directive_line; +- else +- src_loc = pfile->line_table->highest_line; +- } +- /* We don't want to refer to a token before the beginning of the +- current run -- that is invalid. */ +- else if (pfile->cur_token == pfile->cur_run->base) +- { +- src_loc = 0; +- } +- else +- { +- src_loc = pfile->cur_token[-1].src_loc; +- } ++ location_t src_loc = cpp_diagnostic_get_current_location (pfile); + rich_location richloc (pfile->line_table, src_loc); + return cpp_diagnostic_at (pfile, level, reason, &richloc, msgid, ap); + } +@@ -142,6 +149,43 @@ cpp_warning_syshdr (cpp_reader * pfile, + + va_end (ap); + return ret; ++} ++ ++/* As cpp_warning above, but use RICHLOC as the location of the diagnostic. */ ++ ++bool cpp_warning_at (cpp_reader *pfile, enum cpp_warning_reason reason, ++ rich_location *richloc, const char *msgid, ...) ++{ ++ va_list ap; ++ bool ret; ++ ++ va_start (ap, msgid); ++ ++ ret = cpp_diagnostic_at (pfile, CPP_DL_WARNING, reason, richloc, ++ msgid, &ap); ++ ++ va_end (ap); ++ return ret; ++ ++} ++ ++/* As cpp_pedwarning above, but use RICHLOC as the location of the ++ diagnostic. */ ++ ++bool ++cpp_pedwarning_at (cpp_reader * pfile, enum cpp_warning_reason reason, ++ rich_location *richloc, const char *msgid, ...) ++{ ++ va_list ap; ++ bool ret; ++ ++ va_start (ap, msgid); ++ ++ ret = cpp_diagnostic_at (pfile, CPP_DL_PEDWARN, reason, richloc, ++ msgid, &ap); ++ ++ va_end (ap); ++ return ret; + } + + /* Print a diagnostic at a specific location. */ +diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h +--- a/libcpp/include/cpplib.h 2021-12-25 01:29:12.931317107 -0800 ++++ b/libcpp/include/cpplib.h 2021-12-25 01:30:50.685688757 -0800 +@@ -1176,6 +1176,14 @@ extern bool cpp_warning_syshdr (cpp_read + const char *msgid, ...) + ATTRIBUTE_PRINTF_3; + ++/* As their counterparts above, but use RICHLOC. */ ++extern bool cpp_warning_at (cpp_reader *, enum cpp_warning_reason, ++ rich_location *richloc, const char *msgid, ...) ++ ATTRIBUTE_PRINTF_4; ++extern bool cpp_pedwarning_at (cpp_reader *, enum cpp_warning_reason, ++ rich_location *richloc, const char *msgid, ...) ++ ATTRIBUTE_PRINTF_4; ++ + /* Output a diagnostic with "MSGID: " preceding the + error string of errno. No location is printed. */ + extern bool cpp_errno (cpp_reader *, enum cpp_diagnostic_level, +@@ -1320,42 +1328,95 @@ extern const char * cpp_get_userdef_suff + + /* In charset.c */ + ++/* The result of attempting to decode a run of UTF-8 bytes. */ ++ ++struct cpp_decoded_char ++{ ++ const char *m_start_byte; ++ const char *m_next_byte; ++ ++ bool m_valid_ch; ++ cppchar_t m_ch; ++}; ++ ++/* Information for mapping between code points and display columns. ++ ++ This is a tabstop value, along with a callback for getting the ++ widths of characters. Normally this callback is cpp_wcwidth, but we ++ support other schemes for escaping non-ASCII unicode as a series of ++ ASCII chars when printing the user's source code in diagnostic-show-locus.c ++ ++ For example, consider: ++ - the Unicode character U+03C0 "GREEK SMALL LETTER PI" (UTF-8: 0xCF 0x80) ++ - the Unicode character U+1F642 "SLIGHTLY SMILING FACE" ++ (UTF-8: 0xF0 0x9F 0x99 0x82) ++ - the byte 0xBF (a stray trailing byte of a UTF-8 character) ++ Normally U+03C0 would occupy one display column, U+1F642 ++ would occupy two display columns, and the stray byte would be ++ printed verbatim as one display column. ++ ++ However when escaping them as unicode code points as "<U+03C0>" ++ and "<U+1F642>" they occupy 8 and 9 display columns respectively, ++ and when escaping them as bytes as "<CF><80>" and "<F0><9F><99><82>" ++ they occupy 8 and 16 display columns respectively. In both cases ++ the stray byte is escaped to <BF> as 4 display columns. */ ++ ++struct cpp_char_column_policy ++{ ++ cpp_char_column_policy (int tabstop, ++ int (*width_cb) (cppchar_t c)) ++ : m_tabstop (tabstop), ++ m_undecoded_byte_width (1), ++ m_width_cb (width_cb) ++ {} ++ ++ int m_tabstop; ++ /* Width in display columns of a stray byte that isn't decodable ++ as UTF-8. */ ++ int m_undecoded_byte_width; ++ int (*m_width_cb) (cppchar_t c); ++}; ++ + /* A class to manage the state while converting a UTF-8 sequence to cppchar_t + and computing the display width one character at a time. */ + class cpp_display_width_computation { + public: + cpp_display_width_computation (const char *data, int data_length, +- int tabstop); ++ const cpp_char_column_policy &policy); + const char *next_byte () const { return m_next; } + int bytes_processed () const { return m_next - m_begin; } + int bytes_left () const { return m_bytes_left; } + bool done () const { return !bytes_left (); } + int display_cols_processed () const { return m_display_cols; } + +- int process_next_codepoint (); ++ int process_next_codepoint (cpp_decoded_char *out); + int advance_display_cols (int n); + + private: + const char *const m_begin; + const char *m_next; + size_t m_bytes_left; +- const int m_tabstop; ++ const cpp_char_column_policy &m_policy; + int m_display_cols; + }; + + /* Convenience functions that are simple use cases for class + cpp_display_width_computation. Tab characters will be expanded to spaces +- as determined by TABSTOP. */ ++ as determined by POLICY.m_tabstop, and non-printable-ASCII characters ++ will be escaped as per POLICY. */ ++ + int cpp_byte_column_to_display_column (const char *data, int data_length, +- int column, int tabstop); ++ int column, ++ const cpp_char_column_policy &policy); + inline int cpp_display_width (const char *data, int data_length, +- int tabstop) ++ const cpp_char_column_policy &policy) + { + return cpp_byte_column_to_display_column (data, data_length, data_length, +- tabstop); ++ policy); + } + int cpp_display_column_to_byte_column (const char *data, int data_length, +- int display_col, int tabstop); ++ int display_col, ++ const cpp_char_column_policy &policy); + int cpp_wcwidth (cppchar_t c); + + #endif /* ! LIBCPP_CPPLIB_H */ +diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h +--- a/libcpp/include/line-map.h 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/include/line-map.h 2021-12-25 01:30:50.685688757 -0800 +@@ -1732,6 +1732,18 @@ class rich_location + const diagnostic_path *get_path () const { return m_path; } + void set_path (const diagnostic_path *path) { m_path = path; } + ++ /* A flag for hinting that the diagnostic involves character encoding ++ issues, and thus that it will be helpful to the user if we show some ++ representation of how the characters in the pertinent source lines ++ are encoded. ++ The default is false (i.e. do not escape). ++ When set to true, non-ASCII bytes in the pertinent source lines will ++ be escaped in a manner controlled by the user-supplied option ++ -fdiagnostics-escape-format=, so that the user can better understand ++ what's going on with the encoding in their source file. */ ++ bool escape_on_output_p () const { return m_escape_on_output; } ++ void set_escape_on_output (bool flag) { m_escape_on_output = flag; } ++ + private: + bool reject_impossible_fixit (location_t where); + void stop_supporting_fixits (); +@@ -1758,6 +1770,7 @@ protected: + bool m_fixits_cannot_be_auto_applied; + + const diagnostic_path *m_path; ++ bool m_escape_on_output; + }; + + /* A struct for the result of range_label::get_text: a NUL-terminated buffer +diff --git a/libcpp/internal.h b/libcpp/internal.h +--- a/libcpp/internal.h 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/internal.h 2021-12-25 01:30:50.685688757 -0800 +@@ -758,6 +758,9 @@ struct _cpp_dir_only_callbacks + extern void _cpp_preprocess_dir_only (cpp_reader *, + const struct _cpp_dir_only_callbacks *); + ++/* In errors.c */ ++extern location_t cpp_diagnostic_get_current_location (cpp_reader *); ++ + /* In traditional.c. */ + extern bool _cpp_scan_out_logical_line (cpp_reader *, cpp_macro *, bool); + extern bool _cpp_read_logical_line_trad (cpp_reader *); +@@ -946,6 +949,26 @@ int linemap_get_expansion_line (class li + const char* linemap_get_expansion_filename (class line_maps *, + location_t); + ++/* A subclass of rich_location for emitting a diagnostic ++ at the current location of the reader, but flagging ++ it with set_escape_on_output (true). */ ++class encoding_rich_location : public rich_location ++{ ++ public: ++ encoding_rich_location (cpp_reader *pfile) ++ : rich_location (pfile->line_table, ++ cpp_diagnostic_get_current_location (pfile)) ++ { ++ set_escape_on_output (true); ++ } ++ ++ encoding_rich_location (cpp_reader *pfile, location_t loc) ++ : rich_location (pfile->line_table, loc) ++ { ++ set_escape_on_output (true); ++ } ++}; ++ + #ifdef __cplusplus + } + #endif +diff --git a/libcpp/lex.c b/libcpp/lex.c +--- a/libcpp/lex.c 2021-12-24 20:23:45.568762024 -0800 ++++ b/libcpp/lex.c 2021-12-25 01:30:50.685688757 -0800 +@@ -1268,7 +1268,11 @@ skip_whitespace (cpp_reader *pfile, cppc + while (is_nvspace (c)); + + if (saw_NUL) +- cpp_error (pfile, CPP_DL_WARNING, "null character(s) ignored"); ++ { ++ encoding_rich_location rich_loc (pfile); ++ cpp_error_at (pfile, CPP_DL_WARNING, &rich_loc, ++ "null character(s) ignored"); ++ } + + buffer->cur--; + } +@@ -1297,6 +1301,28 @@ warn_about_normalization (cpp_reader *pf + if (CPP_OPTION (pfile, warn_normalize) < NORMALIZE_STATE_RESULT (s) + && !pfile->state.skipping) + { ++ location_t loc = token->src_loc; ++ ++ /* If possible, create a location range for the token. */ ++ if (loc >= RESERVED_LOCATION_COUNT ++ && token->type != CPP_EOF ++ /* There must be no 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)); +@@ -1304,11 +1330,11 @@ 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 2020-07-22 23:35:18.712399623 -0700 ++++ b/libcpp/line-map.c 2021-12-25 01:30:50.685688757 -0800 +@@ -2007,7 +2007,8 @@ rich_location::rich_location (line_maps + m_fixit_hints (), + m_seen_impossible_fixit (false), + m_fixits_cannot_be_auto_applied (false), +- m_path (NULL) ++ m_path (NULL), ++ m_escape_on_output (false) + { + add_range (loc, SHOW_RANGE_WITH_CARET, label); + } diff --git a/meta/recipes-devtools/gcc/gcc/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch b/meta/recipes-devtools/gcc/gcc/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch deleted file mode 100644 index 823cc8b668..0000000000 --- a/meta/recipes-devtools/gcc/gcc/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch +++ /dev/null @@ -1,607 +0,0 @@ -Upstream-Status: Backport -Signed-off-by: Ross Burton <ross.burton@arm.com> - -From b1204d16e1ec96a4aa89e44de8990e2499ffdb22 Mon Sep 17 00:00:00 2001 -From: Matthew Malcomson <matthew.malcomson@arm.com> -Date: Thu, 9 Jul 2020 09:11:59 +0100 -Subject: [PATCH 2/3] aarch64: Introduce SLS mitigation for RET and BR - instructions - -Instructions following RET or BR are not necessarily executed. In order -to avoid speculation past RET and BR we can simply append a speculation -barrier. - -Since these speculation barriers will not be architecturally executed, -they are not expected to add a high performance penalty. - -The speculation barrier is to be SB when targeting architectures which -have this enabled, and DSB SY + ISB otherwise. - -We add tests for each of the cases where such an instruction was seen. - -This is implemented by modifying each machine description pattern that -emits either a RET or a BR instruction. We choose not to use something -like `TARGET_ASM_FUNCTION_EPILOGUE` since it does not affect the -`indirect_jump`, `jump`, `sibcall_insn` and `sibcall_value_insn` -patterns and we find it preferable to implement the functionality in the -same way for every pattern. - -There is one particular case which is slightly tricky. The -implementation of TARGET_ASM_TRAMPOLINE_TEMPLATE uses a BR which needs -to be mitigated against. The trampoline template is used *once* per -compilation unit, and the TRAMPOLINE_SIZE is exposed to the user via the -builtin macro __LIBGCC_TRAMPOLINE_SIZE__. -In the future we may implement function specific attributes to turn on -and off hardening on a per-function basis. -The fixed nature of the trampoline described above implies it will be -safer to ensure this speculation barrier is always used. - -Testing: - Bootstrap and regtest done on aarch64-none-linux - Used a temporary hack(1) to use these options on every test in the - testsuite and a script to check that the output never emitted an - unmitigated RET or BR. - -1) Temporary hack was a change to the testsuite to always use -`-save-temps` and run a script on the assembly output of those -compilations which produced one to ensure every RET or BR is immediately -followed by a speculation barrier. - -gcc/ChangeLog: - - * config/aarch64/aarch64-protos.h (aarch64_sls_barrier): New. - * config/aarch64/aarch64.c (aarch64_output_casesi): Emit - speculation barrier after BR instruction if needs be. - (aarch64_trampoline_init): Handle ptr_mode value & adjust size - of code copied. - (aarch64_sls_barrier): New. - (aarch64_asm_trampoline_template): Add needed barriers. - * config/aarch64/aarch64.h (AARCH64_ISA_SB): New. - (TARGET_SB): New. - (TRAMPOLINE_SIZE): Account for barrier. - * config/aarch64/aarch64.md (indirect_jump, *casesi_dispatch, - simple_return, *do_return, *sibcall_insn, *sibcall_value_insn): - Emit barrier if needs be, also account for possible barrier using - "sls_length" attribute. - (sls_length): New attribute. - (length): Determine default using any non-default sls_length - value. - -gcc/testsuite/ChangeLog: - - * gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c: New test. - * gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c: - New test. - * gcc.target/aarch64/sls-mitigation/sls-mitigation.exp: New file. - * lib/target-supports.exp (check_effective_target_aarch64_asm_sb_ok): - New proc. ---- - gcc/config/aarch64/aarch64-protos.h | 1 + - gcc/config/aarch64/aarch64.c | 41 ++++++- - gcc/config/aarch64/aarch64.h | 10 +- - gcc/config/aarch64/aarch64.md | 76 +++++++++---- - .../aarch64/sls-mitigation/sls-miti-retbr-pacret.c | 21 ++++ - .../aarch64/sls-mitigation/sls-miti-retbr.c | 119 +++++++++++++++++++++ - .../aarch64/sls-mitigation/sls-mitigation.exp | 73 +++++++++++++ - gcc/testsuite/lib/target-supports.exp | 2 +- - 8 files changed, 318 insertions(+), 25 deletions(-) - create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c - create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c - create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp - -diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h -index eb5f4b4..ee0ffde 100644 ---- a/gcc/config/aarch64/aarch64-protos.h -+++ b/gcc/config/aarch64/aarch64-protos.h -@@ -781,6 +781,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names; - - tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *); - -+const char *aarch64_sls_barrier (int); - extern bool aarch64_harden_sls_retbr_p (void); - extern bool aarch64_harden_sls_blr_p (void); - -diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c -index 437a9cf..44e3d1f 100644 ---- a/gcc/config/aarch64/aarch64.c -+++ b/gcc/config/aarch64/aarch64.c -@@ -10852,8 +10852,8 @@ aarch64_return_addr (int count, rtx frame ATTRIBUTE_UNUSED) - static void - aarch64_asm_trampoline_template (FILE *f) - { -- int offset1 = 16; -- int offset2 = 20; -+ int offset1 = 24; -+ int offset2 = 28; - - if (aarch64_bti_enabled ()) - { -@@ -10876,6 +10876,17 @@ aarch64_asm_trampoline_template (FILE *f) - } - asm_fprintf (f, "\tbr\t%s\n", reg_names [IP1_REGNUM]); - -+ /* We always emit a speculation barrier. -+ This is because the same trampoline template is used for every nested -+ function. Since nested functions are not particularly common or -+ performant we don't worry too much about the extra instructions to copy -+ around. -+ This is not yet a problem, since we have not yet implemented function -+ specific attributes to choose between hardening against straight line -+ speculation or not, but such function specific attributes are likely to -+ happen in the future. */ -+ asm_fprintf (f, "\tdsb\tsy\n\tisb\n"); -+ - /* The trampoline needs an extra padding instruction. In case if BTI is - enabled the padding instruction is replaced by the BTI instruction at - the beginning. */ -@@ -10890,10 +10901,14 @@ static void - aarch64_trampoline_init (rtx m_tramp, tree fndecl, rtx chain_value) - { - rtx fnaddr, mem, a_tramp; -- const int tramp_code_sz = 16; -+ const int tramp_code_sz = 24; - - /* Don't need to copy the trailing D-words, we fill those in below. */ -- emit_block_move (m_tramp, assemble_trampoline_template (), -+ /* We create our own memory address in Pmode so that `emit_block_move` can -+ use parts of the backend which expect Pmode addresses. */ -+ rtx temp = convert_memory_address (Pmode, XEXP (m_tramp, 0)); -+ emit_block_move (gen_rtx_MEM (BLKmode, temp), -+ assemble_trampoline_template (), - GEN_INT (tramp_code_sz), BLOCK_OP_NORMAL); - mem = adjust_address (m_tramp, ptr_mode, tramp_code_sz); - fnaddr = XEXP (DECL_RTL (fndecl), 0); -@@ -11084,6 +11099,8 @@ aarch64_output_casesi (rtx *operands) - output_asm_insn (buf, operands); - output_asm_insn (patterns[index][1], operands); - output_asm_insn ("br\t%3", operands); -+ output_asm_insn (aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()), -+ operands); - assemble_label (asm_out_file, label); - return ""; - } -@@ -22924,6 +22941,22 @@ aarch64_file_end_indicate_exec_stack () - #undef GNU_PROPERTY_AARCH64_FEATURE_1_BTI - #undef GNU_PROPERTY_AARCH64_FEATURE_1_AND - -+/* Helper function for straight line speculation. -+ Return what barrier should be emitted for straight line speculation -+ mitigation. -+ When not mitigating against straight line speculation this function returns -+ an empty string. -+ When mitigating against straight line speculation, use: -+ * SB when the v8.5-A SB extension is enabled. -+ * DSB+ISB otherwise. */ -+const char * -+aarch64_sls_barrier (int mitigation_required) -+{ -+ return mitigation_required -+ ? (TARGET_SB ? "sb" : "dsb\tsy\n\tisb") -+ : ""; -+} -+ - /* Target-specific selftests. */ - - #if CHECKING_P -diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h -index 1ce23c6..c21015f 100644 ---- a/gcc/config/aarch64/aarch64.h -+++ b/gcc/config/aarch64/aarch64.h -@@ -281,6 +281,7 @@ extern unsigned aarch64_architecture_version; - #define AARCH64_ISA_F32MM (aarch64_isa_flags & AARCH64_FL_F32MM) - #define AARCH64_ISA_F64MM (aarch64_isa_flags & AARCH64_FL_F64MM) - #define AARCH64_ISA_BF16 (aarch64_isa_flags & AARCH64_FL_BF16) -+#define AARCH64_ISA_SB (aarch64_isa_flags & AARCH64_FL_SB) - - /* Crypto is an optional extension to AdvSIMD. */ - #define TARGET_CRYPTO (TARGET_SIMD && AARCH64_ISA_CRYPTO) -@@ -378,6 +379,9 @@ extern unsigned aarch64_architecture_version; - #define TARGET_FIX_ERR_A53_835769_DEFAULT 1 - #endif - -+/* SB instruction is enabled through +sb. */ -+#define TARGET_SB (AARCH64_ISA_SB) -+ - /* Apply the workaround for Cortex-A53 erratum 835769. */ - #define TARGET_FIX_ERR_A53_835769 \ - ((aarch64_fix_a53_err835769 == 2) \ -@@ -1058,8 +1062,10 @@ typedef struct - - #define RETURN_ADDR_RTX aarch64_return_addr - --/* BTI c + 3 insns + 2 pointer-sized entries. */ --#define TRAMPOLINE_SIZE (TARGET_ILP32 ? 24 : 32) -+/* BTI c + 3 insns -+ + sls barrier of DSB + ISB. -+ + 2 pointer-sized entries. */ -+#define TRAMPOLINE_SIZE (24 + (TARGET_ILP32 ? 8 : 16)) - - /* Trampolines contain dwords, so must be dword aligned. */ - #define TRAMPOLINE_ALIGNMENT 64 -diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md -index 8c8be3c..dda04ee 100644 ---- a/gcc/config/aarch64/aarch64.md -+++ b/gcc/config/aarch64/aarch64.md -@@ -407,10 +407,25 @@ - ;; Attribute that specifies whether the alternative uses MOVPRFX. - (define_attr "movprfx" "no,yes" (const_string "no")) - -+;; Attribute to specify that an alternative has the length of a single -+;; instruction plus a speculation barrier. -+(define_attr "sls_length" "none,retbr,casesi" (const_string "none")) -+ - (define_attr "length" "" - (cond [(eq_attr "movprfx" "yes") - (const_int 8) -- ] (const_int 4))) -+ -+ (eq_attr "sls_length" "retbr") -+ (cond [(match_test "!aarch64_harden_sls_retbr_p ()") (const_int 4) -+ (match_test "TARGET_SB") (const_int 8)] -+ (const_int 12)) -+ -+ (eq_attr "sls_length" "casesi") -+ (cond [(match_test "!aarch64_harden_sls_retbr_p ()") (const_int 16) -+ (match_test "TARGET_SB") (const_int 20)] -+ (const_int 24)) -+ ] -+ (const_int 4))) - - ;; Strictly for compatibility with AArch32 in pipeline models, since AArch64 has - ;; no predicated insns. -@@ -447,8 +462,12 @@ - (define_insn "indirect_jump" - [(set (pc) (match_operand:DI 0 "register_operand" "r"))] - "" -- "br\\t%0" -- [(set_attr "type" "branch")] -+ { -+ output_asm_insn ("br\\t%0", operands); -+ return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()); -+ } -+ [(set_attr "type" "branch") -+ (set_attr "sls_length" "retbr")] - ) - - (define_insn "jump" -@@ -765,7 +784,7 @@ - "* - return aarch64_output_casesi (operands); - " -- [(set_attr "length" "16") -+ [(set_attr "sls_length" "casesi") - (set_attr "type" "branch")] - ) - -@@ -844,18 +863,23 @@ - [(return)] - "" - { -+ const char *ret = NULL; - if (aarch64_return_address_signing_enabled () - && TARGET_ARMV8_3 - && !crtl->calls_eh_return) - { - if (aarch64_ra_sign_key == AARCH64_KEY_B) -- return "retab"; -+ ret = "retab"; - else -- return "retaa"; -+ ret = "retaa"; - } -- return "ret"; -+ else -+ ret = "ret"; -+ output_asm_insn (ret, operands); -+ return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()); - } -- [(set_attr "type" "branch")] -+ [(set_attr "type" "branch") -+ (set_attr "sls_length" "retbr")] - ) - - (define_expand "return" -@@ -867,8 +891,12 @@ - (define_insn "simple_return" - [(simple_return)] - "" -- "ret" -- [(set_attr "type" "branch")] -+ { -+ output_asm_insn ("ret", operands); -+ return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()); -+ } -+ [(set_attr "type" "branch") -+ (set_attr "sls_length" "retbr")] - ) - - (define_insn "*cb<optab><mode>1" -@@ -1066,10 +1094,16 @@ - (unspec:DI [(match_operand:DI 2 "const_int_operand")] UNSPEC_CALLEE_ABI) - (return)] - "SIBLING_CALL_P (insn)" -- "@ -- br\\t%0 -- b\\t%c0" -- [(set_attr "type" "branch, branch")] -+ { -+ if (which_alternative == 0) -+ { -+ output_asm_insn ("br\\t%0", operands); -+ return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()); -+ } -+ return "b\\t%c0"; -+ } -+ [(set_attr "type" "branch, branch") -+ (set_attr "sls_length" "retbr,none")] - ) - - (define_insn "*sibcall_value_insn" -@@ -1080,10 +1114,16 @@ - (unspec:DI [(match_operand:DI 3 "const_int_operand")] UNSPEC_CALLEE_ABI) - (return)] - "SIBLING_CALL_P (insn)" -- "@ -- br\\t%1 -- b\\t%c1" -- [(set_attr "type" "branch, branch")] -+ { -+ if (which_alternative == 0) -+ { -+ output_asm_insn ("br\\t%1", operands); -+ return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()); -+ } -+ return "b\\t%c1"; -+ } -+ [(set_attr "type" "branch, branch") -+ (set_attr "sls_length" "retbr,none")] - ) - - ;; Call subroutine returning any type. -diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c -new file mode 100644 -index 0000000..fa1887a ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c -@@ -0,0 +1,21 @@ -+/* Avoid ILP32 since pacret is only available for LP64 */ -+/* { dg-do compile { target { ! ilp32 } } } */ -+/* { dg-additional-options "-mharden-sls=retbr -mbranch-protection=pac-ret -march=armv8.3-a" } */ -+ -+/* Testing the do_return pattern for retaa and retab. */ -+long retbr_subcall(void); -+long retbr_do_return_retaa(void) -+{ -+ return retbr_subcall()+1; -+} -+ -+__attribute__((target("branch-protection=pac-ret+b-key"))) -+long retbr_do_return_retab(void) -+{ -+ return retbr_subcall()+1; -+} -+ -+/* Ensure there are no BR or RET instructions which are not directly followed -+ by a speculation barrier. */ -+/* { dg-final { scan-assembler-not {\t(br|ret|retaa|retab)\tx[0-9][0-9]?\n\t(?!dsb\tsy\n\tisb)} } } */ -+/* { dg-final { scan-assembler-not {ret\t} } } */ -diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c -new file mode 100644 -index 0000000..76b8d03 ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c -@@ -0,0 +1,119 @@ -+/* We ensure that -Wpedantic is off since it complains about the trampolines -+ we explicitly want to test. */ -+/* { dg-additional-options "-mharden-sls=retbr -Wno-pedantic " } */ -+/* -+ Ensure that the SLS hardening of RET and BR leaves no unprotected RET/BR -+ instructions. -+ */ -+typedef int (foo) (int, int); -+typedef void (bar) (int, int); -+struct sls_testclass { -+ foo *x; -+ bar *y; -+ int left; -+ int right; -+}; -+ -+int -+retbr_sibcall_value_insn (struct sls_testclass x) -+{ -+ return x.x(x.left, x.right); -+} -+ -+void -+retbr_sibcall_insn (struct sls_testclass x) -+{ -+ x.y(x.left, x.right); -+} -+ -+/* Aim to test two different returns. -+ One that introduces a tail call in the middle of the function, and one that -+ has a normal return. */ -+int -+retbr_multiple_returns (struct sls_testclass x) -+{ -+ int temp; -+ if (x.left % 10) -+ return x.x(x.left, 100); -+ else if (x.right % 20) -+ { -+ return x.x(x.left * x.right, 100); -+ } -+ temp = x.left % x.right; -+ temp *= 100; -+ temp /= 2; -+ return temp % 3; -+} -+ -+void -+retbr_multiple_returns_void (struct sls_testclass x) -+{ -+ if (x.left % 10) -+ { -+ x.y(x.left, 100); -+ } -+ else if (x.right % 20) -+ { -+ x.y(x.left * x.right, 100); -+ } -+ return; -+} -+ -+/* Testing the casesi jump via register. */ -+__attribute__ ((optimize ("Os"))) -+int -+retbr_casesi_dispatch (struct sls_testclass x) -+{ -+ switch (x.left) -+ { -+ case -5: -+ return -2; -+ case -3: -+ return -1; -+ case 0: -+ return 0; -+ case 3: -+ return 1; -+ case 5: -+ break; -+ default: -+ __builtin_unreachable (); -+ } -+ return x.right; -+} -+ -+/* Testing the BR in trampolines is mitigated against. */ -+void f1 (void *); -+void f3 (void *, void (*)(void *)); -+void f2 (void *); -+ -+int -+retbr_trampolines (void *a, int b) -+{ -+ if (!b) -+ { -+ f1 (a); -+ return 1; -+ } -+ if (b) -+ { -+ void retbr_tramp_internal (void *c) -+ { -+ if (c == a) -+ f2 (c); -+ } -+ f3 (a, retbr_tramp_internal); -+ } -+ return 0; -+} -+ -+/* Testing the indirect_jump pattern. */ -+void -+retbr_indirect_jump (int *buf) -+{ -+ __builtin_longjmp(buf, 1); -+} -+ -+/* Ensure there are no BR or RET instructions which are not directly followed -+ by a speculation barrier. */ -+/* { dg-final { scan-assembler-not {\t(br|ret|retaa|retab)\tx[0-9][0-9]?\n\t(?!dsb\tsy\n\tisb|sb)} } } */ -diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp -new file mode 100644 -index 0000000..8122503 ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp -@@ -0,0 +1,73 @@ -+# Regression driver for SLS mitigation on AArch64. -+# Copyright (C) 2020 Free Software Foundation, Inc. -+# Contributed by ARM Ltd. -+# -+# This file is part of GCC. -+# -+# GCC is free software; you can redistribute it and/or modify it -+# under the terms of the GNU General Public License as published by -+# the Free Software Foundation; either version 3, or (at your option) -+# any later version. -+# -+# GCC is distributed in the hope that it will be useful, but -+# WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -+# General Public License for more details. -+# -+# You should have received a copy of the GNU General Public License -+# along with GCC; see the file COPYING3. If not see -+# <http://www.gnu.org/licenses/>. */ -+ -+# Exit immediately if this isn't an AArch64 target. -+if {![istarget aarch64*-*-*] } then { -+ return -+} -+ -+# Load support procs. -+load_lib gcc-dg.exp -+load_lib torture-options.exp -+ -+# If a testcase doesn't have special options, use these. -+global DEFAULT_CFLAGS -+if ![info exists DEFAULT_CFLAGS] then { -+ set DEFAULT_CFLAGS " " -+} -+ -+# Initialize `dg'. -+dg-init -+torture-init -+ -+# Use different architectures as well as the normal optimisation options. -+# (i.e. use both SB and DSB+ISB barriers). -+ -+set save-dg-do-what-default ${dg-do-what-default} -+# Main loop. -+# Run with torture tests (i.e. a bunch of different optimisation levels) just -+# to increase test coverage. -+set dg-do-what-default assemble -+gcc-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.\[cCS\]]] \ -+ "-save-temps" $DEFAULT_CFLAGS -+ -+# Run the same tests but this time with SB extension. -+# Since not all supported assemblers will support that extension we decide -+# whether to assemble or just compile based on whether the extension is -+# supported for the available assembler. -+ -+set templist {} -+foreach x $DG_TORTURE_OPTIONS { -+ lappend templist "$x -march=armv8.3-a+sb " -+ lappend templist "$x -march=armv8-a+sb " -+} -+set-torture-options $templist -+if { [check_effective_target_aarch64_asm_sb_ok] } { -+ set dg-do-what-default assemble -+} else { -+ set dg-do-what-default compile -+} -+gcc-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.\[cCS\]]] \ -+ "-save-temps" $DEFAULT_CFLAGS -+set dg-do-what-default ${save-dg-do-what-default} -+ -+# All done. -+torture-finish -+dg-finish -diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp -index 8a186dd..9d2e093 100644 ---- a/gcc/testsuite/lib/target-supports.exp -+++ b/gcc/testsuite/lib/target-supports.exp -@@ -9432,7 +9432,7 @@ proc check_effective_target_aarch64_tiny { } { - # various architecture extensions via the .arch_extension pseudo-op. - - foreach { aarch64_ext } { "fp" "simd" "crypto" "crc" "lse" "dotprod" "sve" -- "i8mm" "f32mm" "f64mm" "bf16" } { -+ "i8mm" "f32mm" "f64mm" "bf16" "sb" } { - eval [string map [list FUNC $aarch64_ext] { - proc check_effective_target_aarch64_asm_FUNC_ok { } { - if { [istarget aarch64*-*-*] } { --- -2.7.4 - diff --git a/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch new file mode 100644 index 0000000000..6bfaf8402d --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0003-CVE-2021-42574.patch @@ -0,0 +1,1724 @@ +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 +--- a/gcc/c-family/c.opt 2021-12-25 01:29:12.915317374 -0800 ++++ b/gcc/c-family/c.opt 2021-12-25 01:36:22.040018701 -0800 +@@ -350,6 +350,30 @@ 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 +--- a/gcc/doc/invoke.texi 2021-12-25 01:35:33.284883488 -0800 ++++ b/gcc/doc/invoke.texi 2021-12-25 01:36:22.048018559 -0800 +@@ -310,7 +310,9 @@ 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 +@@ -6860,6 +6862,23 @@ 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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-10.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-10.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,27 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=unpaired" } */ ++/* More nesting testing. */ ++ ++/* RLE LRI PDF PDI*/ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int LRE_\u202a_PDF_\u202c; ++int LRE_\u202a_PDF_\u202c_LRE_\u202a_PDF_\u202c; ++int LRE_\u202a_LRI_\u2066_PDF_\u202c_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLE_\u202b_RLI_\u2067_PDF_\u202c_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLE_\u202b_RLI_\u2067_PDI_\u2069_PDF_\u202c; ++int FSI_\u2068_LRO_\u202d_PDI_\u2069_PDF_\u202c; ++int FSI_\u2068; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int FSI_\u2068_PDI_\u2069; ++int FSI_\u2068_FSI_\u2068_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069; ++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDF_\u202c; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLI_\u2067_RLI_\u2067_RLI_\u2067_RLI_\u2067_FSI_\u2068_PDI_\u2069_PDI_\u2069_PDI_\u2069_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-11.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-11.c 2021-12-25 01:36:22.048018559 -0800 +@@ -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__PDF_\u202c; ++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */ ++int LRE_\u202a_PDF__; ++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */ ++const char *s1 = "LRE__PDF_\u202c"; ++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */ ++const char *s2 = "LRE_\u202a_PDF_"; ++/* { dg-warning "mismatch" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-12.c b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-12.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-12.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,19 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile { target { c || c++11 } } } */ ++/* { dg-options "-Wbidi-chars=any" } */ ++/* Test raw strings. */ ++ ++const char *s1 = R"(a b c LRE 1 2 3 PDF x y z)"; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++const char *s2 = R"(a b c RLE 1 2 3 PDF x y z)"; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++const char *s3 = R"(a b c LRO 1 2 3 PDF x y z)"; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++const char *s4 = R"(a b c RLO 1 2 3 PDF x y z)"; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++const char *s7 = R"(a b c FSI 1 2 3 PDI x y) z"; ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++const char *s8 = R"(a b c PDI x y )z"; ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */ ++const char *s9 = R"(a b c PDF x y z)"; ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-13.c b/gcc/testsuite/c-c++-common/Wbidi-chars-13.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-13.c 2021-12-25 01:36:22.048018559 -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 RLE 1 2 3)"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++const char *s3 = R"(a b c LRO 1 2 3)"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++const char *s4 = R"(a b c FSI 1 2 3)"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++const char *s5 = R"(a b c LRI 1 2 3)"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++const char *s6 = R"(a b c RLI 1 2 3)"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-14.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-14.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,38 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=unpaired" } */ ++/* Test PDI handling, which also pops any subsequent LREs, RLEs, LROs, ++ or RLOs. */ ++ ++/* LRI__LRI__RLE__RLE__RLE__PDI_*/ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// LRI__RLE__RLE__RLE__PDI_ ++// LRI__RLO__RLE__RLE__PDI_ ++// LRI__RLO__RLE__PDI_ ++// FSI__RLO__PDI_ ++// FSI__FSI__RLO__PDI_ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069; ++int LRI_\u2066_LRI_\u2066_LRI_\u2066_LRE_\u202a_LRE_\u202a_LRE_\u202a_PDI_\u2069_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int PDI_\u2069; ++int LRI_\u2066_PDI_\u2069; ++int RLI_\u2067_PDI_\u2069; ++int LRE_\u202a_LRI_\u2066_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int LRI_\u2066_LRE_\u202a_PDF_\u202c_PDI_\u2069; ++int LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069; ++int RLI_\u2067_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int FSI_\u2068_LRI_\u2066_LRE_\u202a_LRE_\u202a_PDF_\u202c_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLO_\u202e_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int RLI_\u2067_PDI_\u2069_RLI_\u2067; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int FSI_\u2068_PDF_\u202c_PDI_\u2069; ++int FSI_\u2068_FSI_\u2068_PDF_\u202c_PDI_\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-15.c b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-15.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-15.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,59 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=unpaired" } */ ++/* Test unpaired bidi control chars in multiline comments. */ ++ ++/* ++ * LRE end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * RLE end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * LRO end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * RLO end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * LRI end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * RLI end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* ++ * FSI end ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* LRE ++ PDF */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++/* FSI ++ PDI */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++ ++/* LRE<> ++ * ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-3 } */ ++ ++/* ++ * LRE<> ++ */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++ ++/* ++ * ++ * LRE<> */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++/* RLI<> */ /* PDI<> */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* LRE<> */ /* PDF<> */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-16.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-16.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,26 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=any" } */ ++/* Test LTR/RTL chars. */ ++ ++/* LTR<> */ ++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */ ++// LTR<> ++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */ ++/* RTL<> */ ++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */ ++// RTL<> ++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */ ++ ++const char *s1 = "LTR<>"; ++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */ ++const char *s2 = "LTR\u200e"; ++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */ ++const char *s3 = "LTR\u200E"; ++/* { dg-warning "U\\+200E" "" { target *-*-* } .-1 } */ ++const char *s4 = "RTL<>"; ++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */ ++const char *s5 = "RTL\u200f"; ++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */ ++const char *s6 = "RTL\u200F"; ++/* { dg-warning "U\\+200F" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-17.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-17.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,30 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=unpaired" } */ ++/* Test LTR/RTL chars. */ ++ ++/* LTR<> */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// LTR<> ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* RTL<> */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// RTL<> ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int ltr_\u200e; ++/* { dg-error "universal character " "" { target *-*-* } .-1 } */ ++int rtl_\u200f; ++/* { dg-error "universal character " "" { target *-*-* } .-1 } */ ++ ++const char *s1 = "LTR<>"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++const char *s2 = "LTR\u200e"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++const char *s3 = "LTR\u200E"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++const char *s4 = "RTL<>"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++const char *s5 = "RTL\u200f"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++const char *s6 = "RTL\u200F"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-1.c b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-1.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-1.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,12 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++ ++int main() { ++ int isAdmin = 0; ++ /* } if (isAdmin) begin admins only */ ++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */ ++ __builtin_printf("You are an admin.\n"); ++ /* end admins only { */ ++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */ ++ return 0; ++} +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-2.c b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-2.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-2.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,9 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++ ++int main() { ++ /* Say hello; newline/*/ return 0 ; ++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */ ++ __builtin_printf("Hello world.\n"); ++ return 0; ++} +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-3.c b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-3.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-3.c 2021-12-25 01:36:22.048018559 -0800 +@@ -0,0 +1,11 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++ ++int main() { ++ const char* access_level = "user"; ++ if (__builtin_strcmp(access_level, "user // Check if admin ")) { ++/* { dg-warning "bidirectional" "" { target *-*-* } .-1 } */ ++ __builtin_printf("You are an admin.\n"); ++ } ++ return 0; ++} +diff --git a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-4.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-4.c 2021-12-25 01:36:22.048018559 -0800 +@@ -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 LRO 1 2 3 PDF x y z */ ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++/* a b c RLO 1 2 3 PDF x y z */ ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++/* a b c LRI 1 2 3 PDI x y z */ ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++/* a b c RLI 1 2 3 PDI x y */ ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++/* a b c FSI 1 2 3 PDI x y z */ ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++ ++/* Same but C++ comments instead. */ ++// a b c LRE 1 2 3 PDF x y z ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++// a b c RLE 1 2 3 PDF x y z ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++// a b c LRO 1 2 3 PDF x y z ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++// a b c RLO 1 2 3 PDF x y z ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++// a b c LRI 1 2 3 PDI x y z ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++// a b c RLI 1 2 3 PDI x y ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++// a b c FSI 1 2 3 PDI x y z ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++ ++/* Here we're closing an unopened context, warn when =any. */ ++/* a b c PDI x y z */ ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */ ++/* a b c PDF x y z */ ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */ ++// a b c PDI x y z ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */ ++// a b c PDF x y z ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */ ++ ++/* Multiline comments. */ ++/* a b c PDI x y z ++ */ ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */ ++/* a b c PDF x y z ++ */ ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDI x y z ++ */ ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDF x y z ++ */ ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDI x y z */ ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */ ++/* first ++ a b c PDF x y z */ ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */ ++ ++void ++g1 () ++{ ++ const char *s1 = "a b c LRE 1 2 3 PDF x y z"; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++ const char *s2 = "a b c RLE 1 2 3 PDF x y z"; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++ const char *s3 = "a b c LRO 1 2 3 PDF x y z"; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++ const char *s4 = "a b c RLO 1 2 3 PDF x y z"; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++ const char *s5 = "a b c LRI 1 2 3 PDI x y z"; ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++ const char *s6 = "a b c RLI 1 2 3 PDI x y z"; ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++ const char *s7 = "a b c FSI 1 2 3 PDI x y z"; ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++ const char *s8 = "a b c PDI x y z"; ++/* { dg-warning "U\\+2069" "" { target *-*-* } .-1 } */ ++ const char *s9 = "a b c PDF x y z"; ++/* { dg-warning "U\\+202C" "" { target *-*-* } .-1 } */ ++ ++ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++} ++ ++void ++g2 () ++{ ++ const char c1 = '\u202a'; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++ const char c2 = '\u202A'; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++ const char c3 = '\u202b'; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++ const char c4 = '\u202B'; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++ const char c5 = '\u202d'; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++ const char c6 = '\u202D'; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++ const char c7 = '\u202e'; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++ const char c8 = '\u202E'; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++ const char c9 = '\u2066'; ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++ const char c10 = '\u2067'; ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++ const char c11 = '\u2068'; ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++} ++ ++int abc; ++/* { dg-warning "U\\+202A" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+202B" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+202D" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+202E" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+2066" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+2067" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-warning "U\\+2068" "" { target *-*-* } .-1 } */ ++int AX; ++/* { 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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-5.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-5.c 2021-12-25 01:36:22.048018559 -0800 +@@ -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 LRO 1 2 3 PDF x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c RLO 1 2 3 PDF x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c LRI 1 2 3 PDI x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c RLI 1 2 3 PDI x y */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c FSI 1 2 3 PDI x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ ++/* Same but C++ comments instead. */ ++// a b c LRE 1 2 3 PDF x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLE 1 2 3 PDF x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c LRO 1 2 3 PDF x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLO 1 2 3 PDF x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c LRI 1 2 3 PDI x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLI 1 2 3 PDI x y ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c FSI 1 2 3 PDI x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ ++/* Here we're closing an unopened context, warn when =any. */ ++/* a b c PDI x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c PDF x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c PDI x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++// a b c PDF x y z ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ ++/* Multiline comments. */ ++/* a b c PDI x y z ++ */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */ ++/* a b c PDF x y z ++ */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDI x y z ++ */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDF x y z ++ */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-2 } */ ++/* first ++ a b c PDI x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++/* first ++ a b c PDF x y z */ ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ ++void ++g1 () ++{ ++ const char *s1 = "a b c LRE 1 2 3 PDF x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s2 = "a b c RLE 1 2 3 PDF x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s3 = "a b c LRO 1 2 3 PDF x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s4 = "a b c RLO 1 2 3 PDF x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s5 = "a b c LRI 1 2 3 PDI x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s6 = "a b c RLI 1 2 3 PDI x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s7 = "a b c FSI 1 2 3 PDI x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s8 = "a b c PDI x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s9 = "a b c PDF x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ ++ const char *s10 = "a b c LRE\u202a 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s11 = "a b c LRE\u202A 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s12 = "a b c RLE\u202b 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s13 = "a b c RLE\u202B 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s14 = "a b c LRO\u202d 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s15 = "a b c LRO\u202D 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s16 = "a b c RLO\u202e 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s17 = "a b c RLO\u202E 1 2 3 PDF\u202c x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s18 = "a b c LRI\u2066 1 2 3 PDI\u2069 x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s19 = "a b c RLI\u2067 1 2 3 PDI\u2069 x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s20 = "a b c FSI\u2068 1 2 3 PDI\u2069 x y z"; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++} ++ ++void ++g2 () ++{ ++ const char c1 = '\u202a'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c2 = '\u202A'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c3 = '\u202b'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c4 = '\u202B'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c5 = '\u202d'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c6 = '\u202D'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c7 = '\u202e'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c8 = '\u202E'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c9 = '\u2066'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c10 = '\u2067'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char c11 = '\u2068'; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++} ++ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int abc; ++/* { dg-bogus "unpaired" "" { target *-*-* } .-1 } */ ++int AX; ++/* { 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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-6.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-6.c 2021-12-25 01:36:22.052018489 -0800 +@@ -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 RLE 1 2 3 PDI x y z*/ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c LRO 1 2 3 PDI x y z */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c RLO 1 2 3 PDI x y z */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c LRI 1 2 3 PDF x y z */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c RLI 1 2 3 PDF x y z */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* a b c FSI 1 2 3 PDF x y z*/ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++/* LRE PDF */ ++/* LRE LRE PDF PDF */ ++/* PDF LRE PDF */ ++/* LRE PDF LRE PDF */ ++/* LRE LRE PDF */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* PDF LRE */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++// a b c LRE 1 2 3 PDI x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLE 1 2 3 PDI x y z*/ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c LRO 1 2 3 PDI x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLO 1 2 3 PDI x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c LRI 1 2 3 PDF x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c RLI 1 2 3 PDF x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// a b c FSI 1 2 3 PDF x y z ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++// LRE PDF ++// LRE LRE PDF PDF ++// PDF LRE PDF ++// LRE PDF LRE PDF ++// LRE LRE PDF ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++// PDF LRE ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++void ++g1 () ++{ ++ const char *s1 = "a b c LRE 1 2 3 PDI x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s2 = "a b c LRE\u202a 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s3 = "a b c RLE 1 2 3 PDI x y "; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s4 = "a b c RLE\u202b 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s5 = "a b c LRO 1 2 3 PDI x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s6 = "a b c LRO\u202d 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s7 = "a b c RLO 1 2 3 PDI x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s8 = "a b c RLO\u202e 1 2 3 PDI\u2069 x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s9 = "a b c LRI 1 2 3 PDF x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s10 = "a b c LRI\u2066 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s11 = "a b c RLI 1 2 3 PDF x y z\ ++ "; ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++ const char *s12 = "a b c RLI\u2067 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s13 = "a b c FSI 1 2 3 PDF x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s14 = "a b c FSI\u2068 1 2 3 PDF\u202c x y z"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s15 = "PDF LRE"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s16 = "PDF\u202c LRE\u202a"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s17 = "LRE PDF"; ++ const char *s18 = "LRE\u202a PDF\u202c"; ++ const char *s19 = "LRE LRE PDF PDF"; ++ const char *s20 = "LRE\u202a LRE\u202a PDF\u202c PDF\u202c"; ++ const char *s21 = "PDF LRE PDF"; ++ const char *s22 = "PDF\u202c LRE\u202a PDF\u202c"; ++ const char *s23 = "LRE LRE PDF"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s24 = "LRE\u202a LRE\u202a PDF\u202c"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s25 = "PDF LRE"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s26 = "PDF\u202c LRE\u202a"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s27 = "PDF LRE\u202a"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ const char *s28 = "PDF\u202c LRE"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++} ++ ++int aLREbPDI; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int A\u202aB\u2069C; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aRLEbPDI; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int a\u202bB\u2069c; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aLRObPDI; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int a\u202db\u2069c2; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aRLObPDI; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int a\u202eb\u2069; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aLRIbPDF; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int a\u2066b\u202c; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aRLIbPDFc ++; ++/* { dg-warning "unpaired" "" { target *-*-* } .-2 } */ ++int a\u2067b\u202c; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aFSIbPDF; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int a\u2068b\u202c; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aFSIbPD\u202C; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aFSI\u2068bPDF_; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int aLREbPDFb; ++int A\u202aB\u202c; ++int a_LRE_LRE_b_PDF_PDF; ++int A\u202aA\u202aB\u202cB\u202c; ++int aPDFbLREadPDF; ++int a_\u202C_\u202a_\u202c; ++int a_LRE_b_PDF_c_LRE_PDF; ++int a_\u202a_\u202c_\u202a_\u202c_; ++int a_LRE_b_PDF_c_LRE; ++/* { 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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-7.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-7.c 2021-12-25 01:36:22.052018489 -0800 +@@ -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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-8.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-8.c 2021-12-25 01:36:22.052018489 -0800 +@@ -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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-9.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-9.c 2021-12-25 01:36:22.052018489 -0800 +@@ -0,0 +1,29 @@ ++/* PR preprocessor/103026 */ ++/* { dg-do compile } */ ++/* { dg-options "-Wbidi-chars=unpaired" } */ ++/* Test that we properly separate bidi contexts (comment/identifier/character ++ constant/string literal). */ ++ ++/* LRE -><- */ int pdf_\u202c_1; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* RLE -><- */ int pdf_\u202c_2; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* LRO -><- */ int pdf_\u202c_3; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* RLO -><- */ int pdf_\u202c_4; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* LRI -><-*/ int pdi_\u2069_1; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* RLI -><- */ int pdi_\u2069_12; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* FSI -><- */ int pdi_\u2069_3; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++ ++const char *s1 = "LRE\u202a"; /* PDF -><- */ ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++/* LRE -><- */ const char *s2 = "PDF\u202c"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++const char *s3 = "LRE\u202a"; int pdf_\u202c_5; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ ++int lre_\u202a; const char *s4 = "PDF\u202c"; ++/* { dg-warning "unpaired" "" { target *-*-* } .-1 } */ +diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h +--- a/libcpp/include/cpplib.h 2021-12-25 01:35:33.288883417 -0800 ++++ b/libcpp/include/cpplib.h 2021-12-25 01:36:22.052018489 -0800 +@@ -308,6 +308,17 @@ enum cpp_normalize_level { + normalized_none + }; + ++/* The possible bidirectional control characters checking levels, from least ++ restrictive to most. */ ++enum cpp_bidirectional_level { ++ /* No checking. */ ++ bidirectional_none, ++ /* Only detect unpaired uses of bidirectional control characters. */ ++ bidirectional_unpaired, ++ /* Detect any use of bidirectional control characters. */ ++ bidirectional_any ++}; ++ + /* This structure is nested inside struct cpp_reader, and + carries all the options visible to the command line. */ + struct cpp_options +@@ -515,6 +526,10 @@ 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 + { +@@ -613,7 +628,8 @@ 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 +--- a/libcpp/init.c 2021-12-25 01:29:12.931317107 -0800 ++++ b/libcpp/init.c 2021-12-25 01:36:22.052018489 -0800 +@@ -215,6 +215,7 @@ 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 +--- a/libcpp/internal.h 2021-12-25 01:35:33.288883417 -0800 ++++ b/libcpp/internal.h 2021-12-25 01:36:22.052018489 -0800 +@@ -581,6 +581,10 @@ struct cpp_reader + /* If non-zero, the lexer will use this location for the next token + instead of getting a location from the linemap. */ + location_t forced_token_location; ++ 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 +--- a/libcpp/lex.c 2021-12-25 01:35:33.288883417 -0800 ++++ b/libcpp/lex.c 2021-12-25 01:36:22.052018489 -0800 +@@ -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; +@@ -1343,11 +1697,13 @@ 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 == '$') + { +@@ -1370,6 +1726,13 @@ 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; +@@ -1378,6 +1741,13 @@ 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; +@@ -1486,6 +1856,7 @@ 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) +@@ -1509,6 +1880,8 @@ 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); +@@ -1697,6 +2070,7 @@ lex_raw_string (cpp_reader *pfile, cpp_t + { + uchar raw_prefix[17]; + uchar temp_buffer[18]; ++ const bool warn_bidi_p = pfile->warn_bidi_p (); + const uchar *orig_base; + unsigned int raw_prefix_len = 0, raw_suffix_len = 0; + enum raw_str_phase { RAW_STR_PREFIX, RAW_STR, RAW_STR_SUFFIX }; +@@ -1946,8 +2320,15 @@ lex_raw_string (cpp_reader *pfile, cpp_t + cur = base = pfile->buffer->cur; + note = &pfile->buffer->notes[pfile->buffer->cur_note]; + } ++ else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0) ++ && warn_bidi_p) ++ maybe_warn_bidi_on_char (pfile, 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 +@@ -2042,15 +2423,27 @@ 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--; +@@ -2067,6 +2460,11 @@ lex_string (cpp_reader *pfile, cpp_token + } + else if (c == '\0') + saw_NUL = true; ++ else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p) ++ { ++ bidi::kind kind = get_bidi_utf8 (cur - 1); ++ maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false); ++ } + } + + if (saw_NUL && !pfile->state.skipping) diff --git a/meta/recipes-devtools/gcc/gcc/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch b/meta/recipes-devtools/gcc/gcc/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch deleted file mode 100644 index 716a367172..0000000000 --- a/meta/recipes-devtools/gcc/gcc/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch +++ /dev/null @@ -1,658 +0,0 @@ -Upstream-Status: Backport -Signed-off-by: Ross Burton <ross.burton@arm.com> - -From a5e7efc40ed841934c1d913f39476afa17d8e5f7 Mon Sep 17 00:00:00 2001 -From: Matthew Malcomson <matthew.malcomson@arm.com> -Date: Thu, 9 Jul 2020 09:11:59 +0100 -Subject: [PATCH 3/3] aarch64: Mitigate SLS for BLR instruction - -This patch introduces the mitigation for Straight Line Speculation past -the BLR instruction. - -This mitigation replaces BLR instructions with a BL to a stub which uses -a BR to jump to the original value. These function stubs are then -appended with a speculation barrier to ensure no straight line -speculation happens after these jumps. - -When optimising for speed we use a set of stubs for each function since -this should help the branch predictor make more accurate predictions -about where a stub should branch. - -When optimising for size we use one set of stubs for all functions. -This set of stubs can have human readable names, and we are using -`__call_indirect_x<N>` for register x<N>. - -When BTI branch protection is enabled the BLR instruction can jump to a -`BTI c` instruction using any register, while the BR instruction can -only jump to a `BTI c` instruction using the x16 or x17 registers. -Hence, in order to ensure this transformation is safe we mov the value -of the original register into x16 and use x16 for the BR. - -As an example when optimising for size: -a - BLR x0 -instruction would get transformed to something like - BL __call_indirect_x0 -where __call_indirect_x0 labels a thunk that contains -__call_indirect_x0: - MOV X16, X0 - BR X16 - <speculation barrier> - -The first version of this patch used local symbols specific to a -compilation unit to try and avoid relocations. -This was mistaken since functions coming from the same compilation unit -can still be in different sections, and the assembler will insert -relocations at jumps between sections. - -On any relocation the linker is permitted to emit a veneer to handle -jumps between symbols that are very far apart. The registers x16 and -x17 may be clobbered by these veneers. -Hence the function stubs cannot rely on the values of x16 and x17 being -the same as just before the function stub is called. - -Similar can be said for the hot/cold partitioning of single functions, -so function-local stubs have the same restriction. - -This updated version of the patch never emits function stubs for x16 and -x17, and instead forces other registers to be used. - -Given the above, there is now no benefit to local symbols (since they -are not enough to avoid dealing with linker intricacies). This patch -now uses global symbols with hidden visibility each stored in their own -COMDAT section. This means stubs can be shared between compilation -units while still avoiding the PLT indirection. - -This patch also removes the `__call_indirect_x30` stub (and -function-local equivalent) which would simply jump back to the original -location. - -The function-local stubs are emitted to the assembly output file in one -chunk, which means we need not add the speculation barrier directly -after each one. -This is because we know for certain that the instructions directly after -the BR in all but the last function stub will be from another one of -these stubs and hence will not contain a speculation gadget. -Instead we add a speculation barrier at the end of the sequence of -stubs. - -The global stubs are emitted in COMDAT/.linkonce sections by -themselves so that the linker can remove duplicates from multiple object -files. This means they are not emitted in one chunk, and each one must -include the speculation barrier. - -Another difference is that since the global stubs are shared across -compilation units we do not know that all functions will be targeting an -architecture supporting the SB instruction. -Rather than provide multiple stubs for each architecture, we provide a -stub that will work for all architectures -- using the DSB+ISB barrier. - -This mitigation does not apply for BLR instructions in the following -places: -- Some accesses to thread-local variables use a code sequence with a BLR - instruction. This code sequence is part of the binary interface between - compiler and linker. If this BLR instruction needs to be mitigated, it'd - probably be best to do so in the linker. It seems that the code sequence - for thread-local variable access is unlikely to lead to a Spectre Revalation - Gadget. -- PLT stubs are produced by the linker and each contain a BLR instruction. - It seems that at most only after the last PLT stub a Spectre Revalation - Gadget might appear. - -Testing: - Bootstrap and regtest on AArch64 - (with BOOT_CFLAGS="-mharden-sls=retbr,blr") - Used a temporary hack(1) in gcc-dg.exp to use these options on every - test in the testsuite, a slight modification to emit the speculation - barrier after every function stub, and a script to check that the - output never emitted a BLR, or unmitigated BR or RET instruction. - Similar on an aarch64-none-elf cross-compiler. - -1) Temporary hack emitted a speculation barrier at the end of every stub -function, and used a script to ensure that: - a) Every RET or BR is immediately followed by a speculation barrier. - b) No BLR instruction is emitted by compiler. - -gcc/ChangeLog: - - * config/aarch64/aarch64-protos.h (aarch64_indirect_call_asm): - New declaration. - * config/aarch64/aarch64.c (aarch64_regno_regclass): Handle new - stub registers class. - (aarch64_class_max_nregs): Likewise. - (aarch64_register_move_cost): Likewise. - (aarch64_sls_shared_thunks): Global array to store stub labels. - (aarch64_sls_emit_function_stub): New. - (aarch64_create_blr_label): New. - (aarch64_sls_emit_blr_function_thunks): New. - (aarch64_sls_emit_shared_blr_thunks): New. - (aarch64_asm_file_end): New. - (aarch64_indirect_call_asm): New. - (TARGET_ASM_FILE_END): Use aarch64_asm_file_end. - (TARGET_ASM_FUNCTION_EPILOGUE): Use - aarch64_sls_emit_blr_function_thunks. - * config/aarch64/aarch64.h (STB_REGNUM_P): New. - (enum reg_class): Add STUB_REGS class. - (machine_function): Introduce `call_via` array for - function-local stub labels. - * config/aarch64/aarch64.md (*call_insn, *call_value_insn): Use - aarch64_indirect_call_asm to emit code when hardening BLR - instructions. - * config/aarch64/constraints.md (Ucr): New constraint - representing registers for indirect calls. Is GENERAL_REGS - usually, and STUB_REGS when hardening BLR instruction against - SLS. - * config/aarch64/predicates.md (aarch64_general_reg): STUB_REGS class - is also a general register. - -gcc/testsuite/ChangeLog: - - * gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c: New test. - * gcc.target/aarch64/sls-mitigation/sls-miti-blr.c: New test. ---- - gcc/config/aarch64/aarch64-protos.h | 1 + - gcc/config/aarch64/aarch64.c | 225 ++++++++++++++++++++- - gcc/config/aarch64/aarch64.h | 15 ++ - gcc/config/aarch64/aarch64.md | 11 +- - gcc/config/aarch64/constraints.md | 9 + - gcc/config/aarch64/predicates.md | 3 +- - .../aarch64/sls-mitigation/sls-miti-blr-bti.c | 40 ++++ - .../aarch64/sls-mitigation/sls-miti-blr.c | 33 +++ - 8 files changed, 328 insertions(+), 9 deletions(-) - create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c - create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c - -diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h -index ee0ffde..839f801 100644 ---- a/gcc/config/aarch64/aarch64-protos.h -+++ b/gcc/config/aarch64/aarch64-protos.h -@@ -782,6 +782,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names; - tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *); - - const char *aarch64_sls_barrier (int); -+const char *aarch64_indirect_call_asm (rtx); - extern bool aarch64_harden_sls_retbr_p (void); - extern bool aarch64_harden_sls_blr_p (void); - -diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c -index 2389d49..0f7bba3 100644 ---- a/gcc/config/aarch64/aarch64.c -+++ b/gcc/config/aarch64/aarch64.c -@@ -10605,6 +10605,9 @@ aarch64_label_mentioned_p (rtx x) - enum reg_class - aarch64_regno_regclass (unsigned regno) - { -+ if (STUB_REGNUM_P (regno)) -+ return STUB_REGS; -+ - if (GP_REGNUM_P (regno)) - return GENERAL_REGS; - -@@ -10939,6 +10942,7 @@ aarch64_class_max_nregs (reg_class_t regclass, machine_mode mode) - unsigned int nregs, vec_flags; - switch (regclass) - { -+ case STUB_REGS: - case TAILCALL_ADDR_REGS: - case POINTER_REGS: - case GENERAL_REGS: -@@ -13155,10 +13159,12 @@ aarch64_register_move_cost (machine_mode mode, - = aarch64_tune_params.regmove_cost; - - /* Caller save and pointer regs are equivalent to GENERAL_REGS. */ -- if (to == TAILCALL_ADDR_REGS || to == POINTER_REGS) -+ if (to == TAILCALL_ADDR_REGS || to == POINTER_REGS -+ || to == STUB_REGS) - to = GENERAL_REGS; - -- if (from == TAILCALL_ADDR_REGS || from == POINTER_REGS) -+ if (from == TAILCALL_ADDR_REGS || from == POINTER_REGS -+ || from == STUB_REGS) - from = GENERAL_REGS; - - /* Make RDFFR very expensive. In particular, if we know that the FFR -@@ -22957,6 +22963,215 @@ aarch64_sls_barrier (int mitigation_required) - : ""; - } - -+static GTY (()) tree aarch64_sls_shared_thunks[30]; -+static GTY (()) bool aarch64_sls_shared_thunks_needed = false; -+const char *indirect_symbol_names[30] = { -+ "__call_indirect_x0", -+ "__call_indirect_x1", -+ "__call_indirect_x2", -+ "__call_indirect_x3", -+ "__call_indirect_x4", -+ "__call_indirect_x5", -+ "__call_indirect_x6", -+ "__call_indirect_x7", -+ "__call_indirect_x8", -+ "__call_indirect_x9", -+ "__call_indirect_x10", -+ "__call_indirect_x11", -+ "__call_indirect_x12", -+ "__call_indirect_x13", -+ "__call_indirect_x14", -+ "__call_indirect_x15", -+ "", /* "__call_indirect_x16", */ -+ "", /* "__call_indirect_x17", */ -+ "__call_indirect_x18", -+ "__call_indirect_x19", -+ "__call_indirect_x20", -+ "__call_indirect_x21", -+ "__call_indirect_x22", -+ "__call_indirect_x23", -+ "__call_indirect_x24", -+ "__call_indirect_x25", -+ "__call_indirect_x26", -+ "__call_indirect_x27", -+ "__call_indirect_x28", -+ "__call_indirect_x29", -+}; -+ -+/* Function to create a BLR thunk. This thunk is used to mitigate straight -+ line speculation. Instead of a simple BLR that can be speculated past, -+ we emit a BL to this thunk, and this thunk contains a BR to the relevant -+ register. These thunks have the relevant speculation barries put after -+ their indirect branch so that speculation is blocked. -+ -+ We use such a thunk so the speculation barriers are kept off the -+ architecturally executed path in order to reduce the performance overhead. -+ -+ When optimizing for size we use stubs shared by the linked object. -+ When optimizing for performance we emit stubs for each function in the hope -+ that the branch predictor can better train on jumps specific for a given -+ function. */ -+rtx -+aarch64_sls_create_blr_label (int regnum) -+{ -+ gcc_assert (STUB_REGNUM_P (regnum)); -+ if (optimize_function_for_size_p (cfun)) -+ { -+ /* For the thunks shared between different functions in this compilation -+ unit we use a named symbol -- this is just for users to more easily -+ understand the generated assembly. */ -+ aarch64_sls_shared_thunks_needed = true; -+ const char *thunk_name = indirect_symbol_names[regnum]; -+ if (aarch64_sls_shared_thunks[regnum] == NULL) -+ { -+ /* Build a decl representing this function stub and record it for -+ later. We build a decl here so we can use the GCC machinery for -+ handling sections automatically (through `get_named_section` and -+ `make_decl_one_only`). That saves us a lot of trouble handling -+ the specifics of different output file formats. */ -+ tree decl = build_decl (BUILTINS_LOCATION, FUNCTION_DECL, -+ get_identifier (thunk_name), -+ build_function_type_list (void_type_node, -+ NULL_TREE)); -+ DECL_RESULT (decl) = build_decl (BUILTINS_LOCATION, RESULT_DECL, -+ NULL_TREE, void_type_node); -+ TREE_PUBLIC (decl) = 1; -+ TREE_STATIC (decl) = 1; -+ DECL_IGNORED_P (decl) = 1; -+ DECL_ARTIFICIAL (decl) = 1; -+ make_decl_one_only (decl, DECL_ASSEMBLER_NAME (decl)); -+ resolve_unique_section (decl, 0, false); -+ aarch64_sls_shared_thunks[regnum] = decl; -+ } -+ -+ return gen_rtx_SYMBOL_REF (Pmode, thunk_name); -+ } -+ -+ if (cfun->machine->call_via[regnum] == NULL) -+ cfun->machine->call_via[regnum] -+ = gen_rtx_LABEL_REF (Pmode, gen_label_rtx ()); -+ return cfun->machine->call_via[regnum]; -+} -+ -+/* Helper function for aarch64_sls_emit_blr_function_thunks and -+ aarch64_sls_emit_shared_blr_thunks below. */ -+static void -+aarch64_sls_emit_function_stub (FILE *out_file, int regnum) -+{ -+ /* Save in x16 and branch to that function so this transformation does -+ not prevent jumping to `BTI c` instructions. */ -+ asm_fprintf (out_file, "\tmov\tx16, x%d\n", regnum); -+ asm_fprintf (out_file, "\tbr\tx16\n"); -+} -+ -+/* Emit all BLR stubs for this particular function. -+ Here we emit all the BLR stubs needed for the current function. Since we -+ emit these stubs in a consecutive block we know there will be no speculation -+ gadgets between each stub, and hence we only emit a speculation barrier at -+ the end of the stub sequences. -+ -+ This is called in the TARGET_ASM_FUNCTION_EPILOGUE hook. */ -+void -+aarch64_sls_emit_blr_function_thunks (FILE *out_file) -+{ -+ if (! aarch64_harden_sls_blr_p ()) -+ return; -+ -+ bool any_functions_emitted = false; -+ /* We must save and restore the current function section since this assembly -+ is emitted at the end of the function. This means it can be emitted *just -+ after* the cold section of a function. That cold part would be emitted in -+ a different section. That switch would trigger a `.cfi_endproc` directive -+ to be emitted in the original section and a `.cfi_startproc` directive to -+ be emitted in the new section. Switching to the original section without -+ restoring would mean that the `.cfi_endproc` emitted as a function ends -+ would happen in a different section -- leaving an unmatched -+ `.cfi_startproc` in the cold text section and an unmatched `.cfi_endproc` -+ in the standard text section. */ -+ section *save_text_section = in_section; -+ switch_to_section (function_section (current_function_decl)); -+ for (int regnum = 0; regnum < 30; ++regnum) -+ { -+ rtx specu_label = cfun->machine->call_via[regnum]; -+ if (specu_label == NULL) -+ continue; -+ -+ targetm.asm_out.print_operand (out_file, specu_label, 0); -+ asm_fprintf (out_file, ":\n"); -+ aarch64_sls_emit_function_stub (out_file, regnum); -+ any_functions_emitted = true; -+ } -+ if (any_functions_emitted) -+ /* Can use the SB if needs be here, since this stub will only be used -+ by the current function, and hence for the current target. */ -+ asm_fprintf (out_file, "\t%s\n", aarch64_sls_barrier (true)); -+ switch_to_section (save_text_section); -+} -+ -+/* Emit shared BLR stubs for the current compilation unit. -+ Over the course of compiling this unit we may have converted some BLR -+ instructions to a BL to a shared stub function. This is where we emit those -+ stub functions. -+ This function is for the stubs shared between different functions in this -+ compilation unit. We share when optimizing for size instead of speed. -+ -+ This function is called through the TARGET_ASM_FILE_END hook. */ -+void -+aarch64_sls_emit_shared_blr_thunks (FILE *out_file) -+{ -+ if (! aarch64_sls_shared_thunks_needed) -+ return; -+ -+ for (int regnum = 0; regnum < 30; ++regnum) -+ { -+ tree decl = aarch64_sls_shared_thunks[regnum]; -+ if (!decl) -+ continue; -+ -+ const char *name = indirect_symbol_names[regnum]; -+ switch_to_section (get_named_section (decl, NULL, 0)); -+ ASM_OUTPUT_ALIGN (out_file, 2); -+ targetm.asm_out.globalize_label (out_file, name); -+ /* Only emits if the compiler is configured for an assembler that can -+ handle visibility directives. */ -+ targetm.asm_out.assemble_visibility (decl, VISIBILITY_HIDDEN); -+ ASM_OUTPUT_TYPE_DIRECTIVE (out_file, name, "function"); -+ ASM_OUTPUT_LABEL (out_file, name); -+ aarch64_sls_emit_function_stub (out_file, regnum); -+ /* Use the most conservative target to ensure it can always be used by any -+ function in the translation unit. */ -+ asm_fprintf (out_file, "\tdsb\tsy\n\tisb\n"); -+ ASM_DECLARE_FUNCTION_SIZE (out_file, name, decl); -+ } -+} -+ -+/* Implement TARGET_ASM_FILE_END. */ -+void -+aarch64_asm_file_end () -+{ -+ aarch64_sls_emit_shared_blr_thunks (asm_out_file); -+ /* Since this function will be called for the ASM_FILE_END hook, we ensure -+ that what would be called otherwise (e.g. `file_end_indicate_exec_stack` -+ for FreeBSD) still gets called. */ -+#ifdef TARGET_ASM_FILE_END -+ TARGET_ASM_FILE_END (); -+#endif -+} -+ -+const char * -+aarch64_indirect_call_asm (rtx addr) -+{ -+ gcc_assert (REG_P (addr)); -+ if (aarch64_harden_sls_blr_p ()) -+ { -+ rtx stub_label = aarch64_sls_create_blr_label (REGNO (addr)); -+ output_asm_insn ("bl\t%0", &stub_label); -+ } -+ else -+ output_asm_insn ("blr\t%0", &addr); -+ return ""; -+} -+ - /* Target-specific selftests. */ - - #if CHECKING_P -@@ -23507,6 +23722,12 @@ aarch64_libgcc_floating_mode_supported_p - #undef TARGET_MD_ASM_ADJUST - #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust - -+#undef TARGET_ASM_FILE_END -+#define TARGET_ASM_FILE_END aarch64_asm_file_end -+ -+#undef TARGET_ASM_FUNCTION_EPILOGUE -+#define TARGET_ASM_FUNCTION_EPILOGUE aarch64_sls_emit_blr_function_thunks -+ - struct gcc_target targetm = TARGET_INITIALIZER; - - #include "gt-aarch64.h" -diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h -index 8e0fc37..7331450 100644 ---- a/gcc/config/aarch64/aarch64.h -+++ b/gcc/config/aarch64/aarch64.h -@@ -643,6 +643,16 @@ extern unsigned aarch64_architecture_version; - #define GP_REGNUM_P(REGNO) \ - (((unsigned) (REGNO - R0_REGNUM)) <= (R30_REGNUM - R0_REGNUM)) - -+/* Registers known to be preserved over a BL instruction. This consists of the -+ GENERAL_REGS without x16, x17, and x30. The x30 register is changed by the -+ BL instruction itself, while the x16 and x17 registers may be used by -+ veneers which can be inserted by the linker. */ -+#define STUB_REGNUM_P(REGNO) \ -+ (GP_REGNUM_P (REGNO) \ -+ && (REGNO) != R16_REGNUM \ -+ && (REGNO) != R17_REGNUM \ -+ && (REGNO) != R30_REGNUM) \ -+ - #define FP_REGNUM_P(REGNO) \ - (((unsigned) (REGNO - V0_REGNUM)) <= (V31_REGNUM - V0_REGNUM)) - -@@ -667,6 +677,7 @@ enum reg_class - { - NO_REGS, - TAILCALL_ADDR_REGS, -+ STUB_REGS, - GENERAL_REGS, - STACK_REG, - POINTER_REGS, -@@ -689,6 +700,7 @@ enum reg_class - { \ - "NO_REGS", \ - "TAILCALL_ADDR_REGS", \ -+ "STUB_REGS", \ - "GENERAL_REGS", \ - "STACK_REG", \ - "POINTER_REGS", \ -@@ -708,6 +720,7 @@ enum reg_class - { \ - { 0x00000000, 0x00000000, 0x00000000 }, /* NO_REGS */ \ - { 0x00030000, 0x00000000, 0x00000000 }, /* TAILCALL_ADDR_REGS */\ -+ { 0x3ffcffff, 0x00000000, 0x00000000 }, /* STUB_REGS */ \ - { 0x7fffffff, 0x00000000, 0x00000003 }, /* GENERAL_REGS */ \ - { 0x80000000, 0x00000000, 0x00000000 }, /* STACK_REG */ \ - { 0xffffffff, 0x00000000, 0x00000003 }, /* POINTER_REGS */ \ -@@ -862,6 +875,8 @@ typedef struct GTY (()) machine_function - struct aarch64_frame frame; - /* One entry for each hard register. */ - bool reg_is_wrapped_separately[LAST_SAVED_REGNUM]; -+ /* One entry for each general purpose register. */ -+ rtx call_via[SP_REGNUM]; - bool label_is_assembled; - } machine_function; - #endif -diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md -index dda04ee..43da754 100644 ---- a/gcc/config/aarch64/aarch64.md -+++ b/gcc/config/aarch64/aarch64.md -@@ -1022,16 +1022,15 @@ - ) - - (define_insn "*call_insn" -- [(call (mem:DI (match_operand:DI 0 "aarch64_call_insn_operand" "r, Usf")) -+ [(call (mem:DI (match_operand:DI 0 "aarch64_call_insn_operand" "Ucr, Usf")) - (match_operand 1 "" "")) - (unspec:DI [(match_operand:DI 2 "const_int_operand")] UNSPEC_CALLEE_ABI) - (clobber (reg:DI LR_REGNUM))] - "" - "@ -- blr\\t%0 -+ * return aarch64_indirect_call_asm (operands[0]); - bl\\t%c0" -- [(set_attr "type" "call, call")] --) -+ [(set_attr "type" "call, call")]) - - (define_expand "call_value" - [(parallel -@@ -1050,13 +1049,13 @@ - - (define_insn "*call_value_insn" - [(set (match_operand 0 "" "") -- (call (mem:DI (match_operand:DI 1 "aarch64_call_insn_operand" "r, Usf")) -+ (call (mem:DI (match_operand:DI 1 "aarch64_call_insn_operand" "Ucr, Usf")) - (match_operand 2 "" ""))) - (unspec:DI [(match_operand:DI 3 "const_int_operand")] UNSPEC_CALLEE_ABI) - (clobber (reg:DI LR_REGNUM))] - "" - "@ -- blr\\t%1 -+ * return aarch64_indirect_call_asm (operands[1]); - bl\\t%c1" - [(set_attr "type" "call, call")] - ) -diff --git a/gcc/config/aarch64/constraints.md b/gcc/config/aarch64/constraints.md -index d993268..8cc6f50 100644 ---- a/gcc/config/aarch64/constraints.md -+++ b/gcc/config/aarch64/constraints.md -@@ -24,6 +24,15 @@ - (define_register_constraint "Ucs" "TAILCALL_ADDR_REGS" - "@internal Registers suitable for an indirect tail call") - -+(define_register_constraint "Ucr" -+ "aarch64_harden_sls_blr_p () ? STUB_REGS : GENERAL_REGS" -+ "@internal Registers to be used for an indirect call. -+ This is usually the general registers, but when we are hardening against -+ Straight Line Speculation we disallow x16, x17, and x30 so we can use -+ indirection stubs. These indirection stubs cannot use the above registers -+ since they will be reached by a BL that may have to go through a linker -+ veneer.") -+ - (define_register_constraint "w" "FP_REGS" - "Floating point and SIMD vector registers.") - -diff --git a/gcc/config/aarch64/predicates.md b/gcc/config/aarch64/predicates.md -index 215fcec..1754b1e 100644 ---- a/gcc/config/aarch64/predicates.md -+++ b/gcc/config/aarch64/predicates.md -@@ -32,7 +32,8 @@ - - (define_predicate "aarch64_general_reg" - (and (match_operand 0 "register_operand") -- (match_test "REGNO_REG_CLASS (REGNO (op)) == GENERAL_REGS"))) -+ (match_test "REGNO_REG_CLASS (REGNO (op)) == STUB_REGS -+ || REGNO_REG_CLASS (REGNO (op)) == GENERAL_REGS"))) - - ;; Return true if OP a (const_int 0) operand. - (define_predicate "const0_operand" -diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c -new file mode 100644 -index 0000000..b1fb754 ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c -@@ -0,0 +1,40 @@ -+/* { dg-do compile } */ -+/* { dg-additional-options "-mharden-sls=blr -mbranch-protection=bti" } */ -+/* -+ Ensure that the SLS hardening of BLR leaves no BLR instructions. -+ Here we also check that there are no BR instructions with anything except an -+ x16 or x17 register. This is because a `BTI c` instruction can be branched -+ to using a BLR instruction using any register, but can only be branched to -+ with a BR using an x16 or x17 register. -+ */ -+typedef int (foo) (int, int); -+typedef void (bar) (int, int); -+struct sls_testclass { -+ foo *x; -+ bar *y; -+ int left; -+ int right; -+}; -+ -+/* We test both RTL patterns for a call which returns a value and a call which -+ does not. */ -+int blr_call_value (struct sls_testclass x) -+{ -+ int retval = x.x(x.left, x.right); -+ if (retval % 10) -+ return 100; -+ return 9; -+} -+ -+int blr_call (struct sls_testclass x) -+{ -+ x.y(x.left, x.right); -+ if (x.left % 10) -+ return 100; -+ return 9; -+} -+ -+/* { dg-final { scan-assembler-not {\tblr\t} } } */ -+/* { dg-final { scan-assembler-not {\tbr\tx(?!16|17)} } } */ -+/* { dg-final { scan-assembler {\tbr\tx(16|17)} } } */ -+ -diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c -new file mode 100644 -index 0000000..88bafff ---- /dev/null -+++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c -@@ -0,0 +1,33 @@ -+/* { dg-additional-options "-mharden-sls=blr -save-temps" } */ -+/* Ensure that the SLS hardening of BLR leaves no BLR instructions. -+ We only test that all BLR instructions have been removed, not that the -+ resulting code makes sense. */ -+typedef int (foo) (int, int); -+typedef void (bar) (int, int); -+struct sls_testclass { -+ foo *x; -+ bar *y; -+ int left; -+ int right; -+}; -+ -+/* We test both RTL patterns for a call which returns a value and a call which -+ does not. */ -+int blr_call_value (struct sls_testclass x) -+{ -+ int retval = x.x(x.left, x.right); -+ if (retval % 10) -+ return 100; -+ return 9; -+} -+ -+int blr_call (struct sls_testclass x) -+{ -+ x.y(x.left, x.right); -+ if (x.left % 10) -+ return 100; -+ return 9; -+} -+ -+/* { dg-final { scan-assembler-not {\tblr\t} } } */ -+/* { dg-final { scan-assembler {\tbr\tx[0-9][0-9]?} } } */ --- -2.7.4 - diff --git a/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch new file mode 100644 index 0000000000..877b8a6452 --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0004-CVE-2021-42574.patch @@ -0,0 +1,138 @@ +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 +--- a/libcpp/lex.c 2021-12-14 20:44:11.647815287 -0800 ++++ b/libcpp/lex.c 2021-12-14 20:43:38.008383220 -0800 +@@ -1427,9 +1427,11 @@ 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)); +- 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 *pfi + 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 *pfi + { + 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. */ diff --git a/meta/recipes-devtools/gcc/gcc/0005-CVE-2021-42574.patch b/meta/recipes-devtools/gcc/gcc/0005-CVE-2021-42574.patch new file mode 100644 index 0000000000..6e983a67b6 --- /dev/null +++ b/meta/recipes-devtools/gcc/gcc/0005-CVE-2021-42574.patch @@ -0,0 +1,575 @@ +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 +--- a/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c 1969-12-31 16:00:00.000000000 -0800 ++++ b/gcc/testsuite/c-c++-common/Wbidi-chars-ranges.c 2021-12-25 01:39:55.116281847 -0800 +@@ -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; ++ /* } 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 { */ ++/* { 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__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__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 +--- a/libcpp/lex.c 2021-12-25 01:41:16.522868808 -0800 ++++ b/libcpp/lex.c 2021-12-25 06:28:58.530680302 -0800 +@@ -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++; + } +@@ -1734,9 +1881,9 @@ 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)) +@@ -1748,10 +1895,12 @@ 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)) +@@ -2327,12 +2476,15 @@ 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, cur - 1, &loc); ++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc); ++ } + } + + if (warn_bidi_p) +- maybe_warn_bidi_on_close (pfile, pos); ++ maybe_warn_bidi_on_close (pfile, cur); + + if (CPP_OPTION (pfile, user_literals)) + { +@@ -2438,8 +2590,10 @@ 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++; + } +@@ -2467,8 +2621,9 @@ lex_string (cpp_reader *pfile, cpp_token + saw_NUL = true; + else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p) + { +- bidi::kind kind = get_bidi_utf8 (cur - 1); +- maybe_warn_bidi_on_char (pfile, cur - 1, kind, /*ucn_p=*/false); ++ location_t loc; ++ bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc); ++ maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc); + } + } + diff --git a/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch b/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch index 88e1715b5c..03d7a41633 100644 --- a/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch +++ b/meta/recipes-devtools/gcc/gcc/0012-gcc-Fix-argument-list-too-long-error.patch @@ -30,9 +30,8 @@ diff --git a/gcc/Makefile.in b/gcc/Makefile.in index a67d2cc18d6..480c9366418 100644 --- a/gcc/Makefile.in +++ b/gcc/Makefile.in -@@ -3606,7 +3606,7 @@ install-plugin: installdirs lang.install-plugin s-header-vars install-gengtype - # We keep the directory structure for files in config or c-family and .def - # files. All other files are flattened to a single directory. + # We keep the directory structure for files in config, common/config or + # c-family and .def files. All other files are flattened to a single directory. $(mkinstalldirs) $(DESTDIR)$(plugin_includedir) - headers=`echo $(PLUGIN_HEADERS) $$(cd $(srcdir); echo *.h *.def) | tr ' ' '\012' | sort -u`; \ + headers=`echo $(sort $(PLUGIN_HEADERS)) $$(cd $(srcdir); echo *.h *.def) | tr ' ' '\012' | sort -u`; \ diff --git a/meta/recipes-devtools/gcc/gcc/0033-Re-introduce-spe-commandline-options.patch b/meta/recipes-devtools/gcc/gcc/0033-Re-introduce-spe-commandline-options.patch index ba7c2b8fd5..43d881fa5e 100644 --- a/meta/recipes-devtools/gcc/gcc/0033-Re-introduce-spe-commandline-options.patch +++ b/meta/recipes-devtools/gcc/gcc/0033-Re-introduce-spe-commandline-options.patch @@ -33,6 +33,6 @@ index f95b8279270..0e52d51409d 100644 +Target RejectNegative Var(rs6000_spe_abi, 0) +Do not use the SPE ABI extensions. + + ; Altivec ABI mabi=altivec Target RejectNegative Var(rs6000_altivec_abi) Save - Use the AltiVec ABI extensions. diff --git a/meta/recipes-devtools/gcc/gcc/0036-mingw32-Enable-operation_not_supported.patch b/meta/recipes-devtools/gcc/gcc/0036-mingw32-Enable-operation_not_supported.patch index de82a3a539..4db3d15554 100644 --- a/meta/recipes-devtools/gcc/gcc/0036-mingw32-Enable-operation_not_supported.patch +++ b/meta/recipes-devtools/gcc/gcc/0036-mingw32-Enable-operation_not_supported.patch @@ -16,11 +16,11 @@ index 68ac72a78fb..71cd5815b81 100644 --- a/libstdc++-v3/config/os/mingw32/error_constants.h +++ b/libstdc++-v3/config/os/mingw32/error_constants.h @@ -107,7 +107,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION - #ifdef _GLIBCXX_HAVE_EPERM + #ifdef EPERM operation_not_permitted = EPERM, #endif -// operation_not_supported = EOPNOTSUPP, + operation_not_supported = EOPNOTSUPP, - #ifdef _GLIBCXX_HAVE_EWOULDBLOCK + #ifdef EWOULDBLOCK operation_would_block = EWOULDBLOCK, #endif diff --git a/meta/recipes-devtools/gcc/gcc_10.2.bb b/meta/recipes-devtools/gcc/gcc_10.3.bb index 7d93590588..7d93590588 100644 --- a/meta/recipes-devtools/gcc/gcc_10.2.bb +++ b/meta/recipes-devtools/gcc/gcc_10.3.bb diff --git a/meta/recipes-devtools/gcc/libgcc-initial_10.2.bb b/meta/recipes-devtools/gcc/libgcc-initial_10.3.bb index 0c698c26ec..0c698c26ec 100644 --- a/meta/recipes-devtools/gcc/libgcc-initial_10.2.bb +++ b/meta/recipes-devtools/gcc/libgcc-initial_10.3.bb diff --git a/meta/recipes-devtools/gcc/libgcc_10.2.bb b/meta/recipes-devtools/gcc/libgcc_10.3.bb index ea210a1130..ea210a1130 100644 --- a/meta/recipes-devtools/gcc/libgcc_10.2.bb +++ b/meta/recipes-devtools/gcc/libgcc_10.3.bb diff --git a/meta/recipes-devtools/gcc/libgfortran_10.2.bb b/meta/recipes-devtools/gcc/libgfortran_10.3.bb index 71dd8b4bdc..71dd8b4bdc 100644 --- a/meta/recipes-devtools/gcc/libgfortran_10.2.bb +++ b/meta/recipes-devtools/gcc/libgfortran_10.3.bb diff --git a/meta/recipes-devtools/gnu-config/gnu-config_git.bb b/meta/recipes-devtools/gnu-config/gnu-config_git.bb index ecbd60e72a..da52c943f5 100644 --- a/meta/recipes-devtools/gnu-config/gnu-config_git.bb +++ b/meta/recipes-devtools/gnu-config/gnu-config_git.bb @@ -12,7 +12,7 @@ INHIBIT_DEFAULT_DEPS = "1" SRCREV = "6faca61810d335c7837f320733fe8e15a1431fc2" PV = "20210125+git${SRCPV}" -SRC_URI = "git://git.savannah.gnu.org/config.git;branch=master \ +SRC_URI = "git://git.savannah.gnu.org/git/config.git;protocol=https;branch=master \ file://gnu-configize.in" S = "${WORKDIR}/git" UPSTREAM_CHECK_COMMITS = "1" diff --git a/meta/recipes-devtools/go/go-1.16.8.inc b/meta/recipes-devtools/go/go-1.16.15.inc index acc2300a28..8b1ad22bcc 100644 --- a/meta/recipes-devtools/go/go-1.16.8.inc +++ b/meta/recipes-devtools/go/go-1.16.15.inc @@ -1,8 +1,8 @@ require go-common.inc GO_BASEVERSION = "1.16" -PV = "1.16.8" -FILESEXTRAPATHS_prepend := "${FILE_DIRNAME}/go-${GO_BASEVERSION}:" +PV = "1.16.15" +FILESEXTRAPATHS:prepend := "${FILE_DIRNAME}/go-${GO_BASEVERSION}:" LIC_FILES_CHKSUM = "file://LICENSE;md5=5d4950ecb7b26d2c5e4e7b4e0dd74707" @@ -18,7 +18,7 @@ SRC_URI += "\ file://0009-Revert-cmd-go-make-sure-CC-and-CXX-are-absolute.patch \ file://0001-encoding-xml-handle-leading-trailing-or-double-colon.patch \ " -SRC_URI[main.sha256sum] = "8f2a8c24b793375b3243df82fdb0c8387486dcc8a892ca1c991aa99ace086b98" +SRC_URI[main.sha256sum] = "90a08c689279e35f3865ba510998c33a63255c36089b3ec206c912fc0568c3d3" # Upstream don't believe it is a signifiant real world issue and will only # fix in 1.17 onwards where we can drop this. diff --git a/meta/recipes-devtools/go/go-binary-native_1.16.8.bb b/meta/recipes-devtools/go/go-binary-native_1.16.15.bb index 926222089d..ba11ee5695 100644 --- a/meta/recipes-devtools/go/go-binary-native_1.16.8.bb +++ b/meta/recipes-devtools/go/go-binary-native_1.16.15.bb @@ -8,8 +8,8 @@ LIC_FILES_CHKSUM = "file://LICENSE;md5=5d4950ecb7b26d2c5e4e7b4e0dd74707" PROVIDES = "go-native" SRC_URI = "https://dl.google.com/go/go${PV}.${BUILD_GOOS}-${BUILD_GOARCH}.tar.gz;name=go_${BUILD_GOTUPLE}" -SRC_URI[go_linux_amd64.sha256sum] = "f32501aeb8b7b723bc7215f6c373abb6981bbc7e1c7b44e9f07317e1a300dce2" -SRC_URI[go_linux_arm64.sha256sum] = "430dbe185417204f6788913197ab3b189b6deae9c9b524f262858e53dab239c2" +SRC_URI[go_linux_amd64.sha256sum] = "77c782a633186d78c384f972fb113a43c24be0234c42fef22c2d8c4c4c8e7475" +SRC_URI[go_linux_arm64.sha256sum] = "c2f27f0ce5620a9bc2ff3446165d1974ef94e9b885ec12dbfa3c07e0e198b7ce" UPSTREAM_CHECK_URI = "https://golang.org/dl/" UPSTREAM_CHECK_REGEX = "go(?P<pver>\d+(\.\d+)+)\.linux" diff --git a/meta/recipes-devtools/go/go-cross-canadian_1.16.8.bb b/meta/recipes-devtools/go/go-cross-canadian_1.16.15.bb index 7ac9449e47..7ac9449e47 100644 --- a/meta/recipes-devtools/go/go-cross-canadian_1.16.8.bb +++ b/meta/recipes-devtools/go/go-cross-canadian_1.16.15.bb diff --git a/meta/recipes-devtools/go/go-cross_1.16.8.bb b/meta/recipes-devtools/go/go-cross_1.16.15.bb index 80b5a03f6c..80b5a03f6c 100644 --- a/meta/recipes-devtools/go/go-cross_1.16.8.bb +++ b/meta/recipes-devtools/go/go-cross_1.16.15.bb diff --git a/meta/recipes-devtools/go/go-crosssdk_1.16.8.bb b/meta/recipes-devtools/go/go-crosssdk_1.16.15.bb index 1857c8a577..1857c8a577 100644 --- a/meta/recipes-devtools/go/go-crosssdk_1.16.8.bb +++ b/meta/recipes-devtools/go/go-crosssdk_1.16.15.bb diff --git a/meta/recipes-devtools/go/go-native_1.16.8.bb b/meta/recipes-devtools/go/go-native_1.16.15.bb index f14892cdb0..f14892cdb0 100644 --- a/meta/recipes-devtools/go/go-native_1.16.8.bb +++ b/meta/recipes-devtools/go/go-native_1.16.15.bb diff --git a/meta/recipes-devtools/go/go-runtime_1.16.8.bb b/meta/recipes-devtools/go/go-runtime_1.16.15.bb index 63464a1501..63464a1501 100644 --- a/meta/recipes-devtools/go/go-runtime_1.16.8.bb +++ b/meta/recipes-devtools/go/go-runtime_1.16.15.bb diff --git a/meta/recipes-devtools/go/go_1.16.8.bb b/meta/recipes-devtools/go/go_1.16.15.bb index 4e9e0ebec8..4e9e0ebec8 100644 --- a/meta/recipes-devtools/go/go_1.16.8.bb +++ b/meta/recipes-devtools/go/go_1.16.15.bb diff --git a/meta/recipes-devtools/patchelf/patchelf/0001-merge-from-PR243.patch b/meta/recipes-devtools/patchelf/patchelf/0001-merge-from-PR243.patch new file mode 100644 index 0000000000..a5322f0375 --- /dev/null +++ b/meta/recipes-devtools/patchelf/patchelf/0001-merge-from-PR243.patch @@ -0,0 +1,47 @@ +From 6ac5c1350834b9da81ab90ab5ba4e5bf507c6c0d Mon Sep 17 00:00:00 2001 +From: Satadru Pramanik <satadru@gmail.com> +Date: Thu, 20 May 2021 16:52:21 -0400 +Subject: [PATCH] merge from PR243 + +Upstream-Status: Backport + +Reference to upstream patch: +https://github.com/NixOS/patchelf/commit/4efbce410d00c8cb43f134181d07b364bcf78022 + +[OP: tweak patch to apply to patchelf v0.10] +Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com> +[OP: tweak patch to apply to patchelf v0.12] +Signed-off-by: Chen Qi <Qi.Chen@windriver.com> +--- + src/patchelf.cc | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/src/patchelf.cc b/src/patchelf.cc +index 1854cfa..73a3a86 100644 +--- a/src/patchelf.cc ++++ b/src/patchelf.cc +@@ -774,12 +774,15 @@ void ElfFile<ElfFileParamNames>::rewriteSectionsLibrary() + PT_LOAD segment located directly after the last virtual address + page of other segments. */ + Elf_Addr startPage = 0; ++ Elf_Addr firstPage = 0; + for (unsigned int i = 0; i < phdrs.size(); ++i) { + Elf_Addr thisPage = roundUp(rdi(phdrs[i].p_vaddr) + rdi(phdrs[i].p_memsz), getPageSize()); + if (thisPage > startPage) startPage = thisPage; ++ if (rdi(phdrs[i].p_type) == PT_PHDR) firstPage = rdi(phdrs[i].p_vaddr) - rdi(phdrs[i].p_offset); + } + + debug("last page is 0x%llx\n", (unsigned long long) startPage); ++ debug("first page is 0x%llx\n", (unsigned long long) firstPage); + + /* When normalizing note segments we will in the worst case be adding + 1 program header for each SHT_NOTE section. */ +@@ -852,7 +855,7 @@ void ElfFile<ElfFileParamNames>::rewriteSectionsLibrary() + assert(curOff == startOffset + neededSpace); + + /* Write out the updated program and section headers */ +- rewriteHeaders(hdr->e_phoff); ++ rewriteHeaders(firstPage + hdr->e_phoff); + } + + diff --git a/meta/recipes-devtools/patchelf/patchelf_0.12.bb b/meta/recipes-devtools/patchelf/patchelf_0.12.bb index 390a8110da..007435a719 100644 --- a/meta/recipes-devtools/patchelf/patchelf_0.12.bb +++ b/meta/recipes-devtools/patchelf/patchelf_0.12.bb @@ -8,6 +8,7 @@ SRC_URI = "git://github.com/NixOS/patchelf;protocol=https;branch=master \ file://handle-read-only-files.patch \ file://6edec83653ce1b5fc201ff6db93b966394766814.patch \ file://alignmentfix.patch \ + file://0001-merge-from-PR243.patch \ " SRCREV = "8d3a16e97294e3c5521c61b4c8835499c9918264" diff --git a/meta/recipes-devtools/python-numpy/files/CVE-2021-41496.patch b/meta/recipes-devtools/python-numpy/files/CVE-2021-41496.patch new file mode 100644 index 0000000000..0afc79ae0d --- /dev/null +++ b/meta/recipes-devtools/python-numpy/files/CVE-2021-41496.patch @@ -0,0 +1,64 @@ +From 86d81322c5c0ab67f89d64f56f6e77d4fe185910 Mon Sep 17 00:00:00 2001 +From: Warren Weckesser <warren.weckesser@gmail.com> +Date: Tue, 29 Mar 2022 15:58:00 +0800 +Subject: [PATCH] BUG: f2py: Simplify creation of an exception message. Closes + gh-19000. + +CVE: CVE-2021-41496 + +Upstream-Status: Backport [https://github.com/numpy/numpy/commit/271010f1037150e95017f803f4214b8861e528f2] + +Signed-off-by: Mingli Yu <mingli.yu@windriver.com> +--- + numpy/f2py/src/fortranobject.c | 26 ++++++++++++-------------- + 1 file changed, 12 insertions(+), 14 deletions(-) + +diff --git a/numpy/f2py/src/fortranobject.c b/numpy/f2py/src/fortranobject.c +index 3275f90..85c9c7f 100644 +--- a/numpy/f2py/src/fortranobject.c ++++ b/numpy/f2py/src/fortranobject.c +@@ -637,14 +637,14 @@ static int check_and_fix_dimensions(const PyArrayObject* arr, + npy_intp *dims); + + static int +-count_negative_dimensions(const int rank, ++find_first_negative_dimension(const int rank, + const npy_intp *dims) { +- int i=0,r=0; +- while (i<rank) { +- if (dims[i] < 0) ++r; +- ++i; ++ for (int i = 0; i < rank; ++i) { ++ if (dims[i] < 0) { ++ return i; ++ } + } +- return r; ++ return -1; + } + + #ifdef DEBUG_COPY_ND_ARRAY +@@ -721,14 +721,12 @@ PyArrayObject* array_from_pyobj(const int type_num, + || ((intent & F2PY_OPTIONAL) && (obj==Py_None)) + ) { + /* intent(cache), optional, intent(hide) */ +- if (count_negative_dimensions(rank,dims) > 0) { +- int i; +- strcpy(mess, "failed to create intent(cache|hide)|optional array" +- "-- must have defined dimensions but got ("); +- for(i=0;i<rank;++i) +- sprintf(mess+strlen(mess),"%" NPY_INTP_FMT ",",dims[i]); +- strcat(mess, ")"); +- PyErr_SetString(PyExc_ValueError,mess); ++ int i = find_first_negative_dimension(rank, dims); ++ if (i >= 0) { ++ PyErr_Format(PyExc_ValueError, ++ "failed to create intent(cache|hide)|optional array" ++ " -- must have defined dimensions, but dims[%d] = %" ++ NPY_INTP_FMT, i, dims[i]); + return NULL; + } + arr = (PyArrayObject *) +-- +2.25.1 + diff --git a/meta/recipes-devtools/python-numpy/python3-numpy_1.20.1.bb b/meta/recipes-devtools/python-numpy/python3-numpy_1.20.1.bb index 6c3b886782..9e55e74d2c 100644 --- a/meta/recipes-devtools/python-numpy/python3-numpy_1.20.1.bb +++ b/meta/recipes-devtools/python-numpy/python3-numpy_1.20.1.bb @@ -10,6 +10,7 @@ SRCNAME = "numpy" SRC_URI = "https://github.com/${SRCNAME}/${SRCNAME}/releases/download/v${PV}/${SRCNAME}-${PV}.tar.gz \ file://0001-Don-t-search-usr-and-so-on-for-libraries-by-default-.patch \ file://0001-numpy-core-Define-RISCV-32-support.patch \ + file://CVE-2021-41496.patch \ file://run-ptest \ " SRC_URI[sha256sum] = "9bf51d69ebb4ca9239e55bedc2185fe2c0ec222da0adee7ece4125414676846d" diff --git a/meta/recipes-devtools/python/python3-pyelftools_0.27.bb b/meta/recipes-devtools/python/python3-pyelftools_0.27.bb index 0cfd99504b..f8b9d420a5 100644 --- a/meta/recipes-devtools/python/python3-pyelftools_0.27.bb +++ b/meta/recipes-devtools/python/python3-pyelftools_0.27.bb @@ -11,3 +11,5 @@ PYPI_PACKAGE = "pyelftools" inherit pypi setuptools3 BBCLASSEXTEND = "native" + +RDEPENDS_${PN} += "${PYTHON_PN}-debugger ${PYTHON_PN}-pprint" diff --git a/meta/recipes-devtools/python/python3/0001-Makefile-fix-Issue36464-parallel-build-race-problem.patch b/meta/recipes-devtools/python/python3/0001-Makefile-fix-Issue36464-parallel-build-race-problem.patch deleted file mode 100644 index 237645bc60..0000000000 --- a/meta/recipes-devtools/python/python3/0001-Makefile-fix-Issue36464-parallel-build-race-problem.patch +++ /dev/null @@ -1,34 +0,0 @@ -From 840fda32c82550259d02a7a56a78a9c05162b1a1 Mon Sep 17 00:00:00 2001 -From: Changqing Li <changqing.li@windriver.com> -Date: Wed, 8 May 2019 16:10:29 +0800 -Subject: [PATCH] Makefile: fix Issue36464 (parallel build race problem) - -When using make -j with the 'install' target, it's possible for altbininstall -(which normally creates BINDIR) and libainstall (which doesn't, though it -installs python-config there) to race, resulting in a failure due to -attempting to install python-config into a nonexistent BINDIR. Ensure it also -exists in the libainstall target. - -Upstream-Status: Submitted [https://github.com/python/cpython/pull/13186] - -Signed-off-by: Changqing Li <changqing.li@windriver.com> ---- - Makefile.pre.in | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -diff --git a/Makefile.pre.in b/Makefile.pre.in -index 15f3687..7e9f173 100644 ---- a/Makefile.pre.in -+++ b/Makefile.pre.in -@@ -1456,7 +1456,7 @@ LIBPL= @LIBPL@ - LIBPC= $(LIBDIR)/pkgconfig - - libainstall: @DEF_MAKE_RULE@ python-config -- @for i in $(LIBDIR) $(LIBPL) $(LIBPC); \ -+ @for i in $(LIBDIR) $(LIBPL) $(LIBPC) $(BINDIR); \ - do \ - if test ! -d $(DESTDIR)$$i; then \ - echo "Creating directory $$i"; \ --- -2.7.4 - diff --git a/meta/recipes-devtools/python/python3/0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch b/meta/recipes-devtools/python/python3/0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch index c4fae09a5b..99968b81de 100644 --- a/meta/recipes-devtools/python/python3/0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch +++ b/meta/recipes-devtools/python/python3/0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch @@ -1,7 +1,8 @@ -From 1ad771d86728ee2ed30e202e9768d8d825f96467 Mon Sep 17 00:00:00 2001 +From d9eb634b3d2e6ba831e864c50f6a37c48edfc4f3 Mon Sep 17 00:00:00 2001 From: Matthias Schoepfer <matthias.schoepfer@ithinx.io> Date: Fri, 31 May 2019 15:34:34 +0200 Subject: [PATCH] bpo-36852: proper detection of mips architecture for soft + float When (cross) compiling for softfloat mips, __mips_hard_float will not be @@ -13,18 +14,18 @@ to do this in a more autoconf/autotools manner. Upstream-Status: Submitted [https://github.com/python/cpython/pull/13196] Signed-off-by: Matthias Schoepfer <matthias.schoepfer@ithinx.io> -%% original patch: 0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch + --- configure.ac | 175 +++++++-------------------------------------------- 1 file changed, 21 insertions(+), 154 deletions(-) diff --git a/configure.ac b/configure.ac -index ede710e..bc81b0b 100644 +index e2979a8..337182d 100644 --- a/configure.ac +++ b/configure.ac -@@ -710,160 +710,27 @@ fi - MULTIARCH=$($CC --print-multiarch 2>/dev/null) - AC_SUBST(MULTIARCH) +@@ -728,160 +728,27 @@ then + fi + -AC_MSG_CHECKING([for the platform triplet based on compiler characteristics]) -cat >> conftest.c <<EOF @@ -202,8 +203,5 @@ index ede710e..bc81b0b 100644 + ;; +esac - if test x$PLATFORM_TRIPLET != x && test x$MULTIARCH != x; then - if test x$PLATFORM_TRIPLET != x$MULTIARCH; then --- -2.24.1 - + if test x$PLATFORM_TRIPLET != xdarwin; then + MULTIARCH=$($CC --print-multiarch 2>/dev/null) diff --git a/meta/recipes-devtools/python/python3_3.9.5.bb b/meta/recipes-devtools/python/python3_3.9.9.bb index 2b05bd530e..f41529833c 100644 --- a/meta/recipes-devtools/python/python3_3.9.5.bb +++ b/meta/recipes-devtools/python/python3_3.9.9.bb @@ -20,7 +20,6 @@ SRC_URI = "http://www.python.org/ftp/python/${PV}/Python-${PV}.tar.xz \ file://python-config.patch \ file://0001-Makefile.pre-use-qemu-wrapper-when-gathering-profile.patch \ file://0001-python3-use-cc_basename-to-replace-CC-for-checking-c.patch \ - file://0001-Makefile-fix-Issue36464-parallel-build-race-problem.patch \ file://0001-bpo-36852-proper-detection-of-mips-architecture-for-.patch \ file://crosspythonpath.patch \ file://0001-Use-FLAG_REF-always-for-interned-strings.patch \ @@ -39,7 +38,7 @@ SRC_URI_append_class-native = " \ file://12-distutils-prefix-is-inside-staging-area.patch \ file://0001-Don-t-search-system-for-headers-libraries.patch \ " -SRC_URI[sha256sum] = "0c5a140665436ec3dbfbb79e2dfb6d192655f26ef4a29aeffcb6d1820d716d83" +SRC_URI[sha256sum] = "06828c04a573c073a4e51c4292a27c1be4ae26621c3edc7cf9318418ce3b6d27" # exclude pre-releases for both python 2.x and 3.x UPSTREAM_CHECK_REGEX = "[Pp]ython-(?P<pver>\d+(\.\d+)+).tar" diff --git a/meta/recipes-devtools/qemu/qemu.inc b/meta/recipes-devtools/qemu/qemu.inc index 463339e42b..568ef1be94 100644 --- a/meta/recipes-devtools/qemu/qemu.inc +++ b/meta/recipes-devtools/qemu/qemu.inc @@ -70,6 +70,11 @@ SRC_URI = "https://download.qemu.org/${BPN}-${PV}.tar.xz \ file://CVE-2021-3607.patch \ file://CVE-2021-3608.patch \ file://CVE-2021-3682.patch \ + file://CVE-2021-3713.patch \ + file://CVE-2021-3748.patch \ + file://CVE-2021-3930.patch \ + file://CVE-2021-20196_1.patch \ + file://CVE-2021-20196_2.patch \ " UPSTREAM_CHECK_REGEX = "qemu-(?P<pver>\d+(\.\d+)+)\.tar" diff --git a/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_1.patch b/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_1.patch new file mode 100644 index 0000000000..8b1ad0423b --- /dev/null +++ b/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_1.patch @@ -0,0 +1,54 @@ +From e907ff3d4cb7fd20d402f45355059e67d0dc93e7 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= <philmd@redhat.com> +Date: Wed, 24 Nov 2021 17:15:34 +0100 +Subject: [PATCH 11/12] hw/block/fdc: Extract blk_create_empty_drive() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +We are going to re-use this code in the next commit, +so extract it as a new blk_create_empty_drive() function. + +Inspired-by: Hanna Reitz <hreitz@redhat.com> +Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> +Message-id: 20211124161536.631563-2-philmd@redhat.com +Signed-off-by: John Snow <jsnow@redhat.com> + +Upstream-Status: Backport [b154791e7b6d4ca5cdcd54443484d97360bd7ad2] +CVE: CVE-2021-20196 + +Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com> +--- + hw/block/fdc.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/hw/block/fdc.c b/hw/block/fdc.c +index 4c2c35e22..854b4f172 100644 +--- a/hw/block/fdc.c ++++ b/hw/block/fdc.c +@@ -61,6 +61,12 @@ + } while (0) + + ++/* Anonymous BlockBackend for empty drive */ ++static BlockBackend *blk_create_empty_drive(void) ++{ ++ return blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL); ++} ++ + /********************************************************/ + /* qdev floppy bus */ + +@@ -543,8 +549,7 @@ static void floppy_drive_realize(DeviceState *qdev, Error **errp) + } + + if (!dev->conf.blk) { +- /* Anonymous BlockBackend for an empty drive */ +- dev->conf.blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL); ++ dev->conf.blk = blk_create_empty_drive(); + ret = blk_attach_dev(dev->conf.blk, qdev); + assert(ret == 0); + +-- +2.31.1 + diff --git a/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_2.patch b/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_2.patch new file mode 100644 index 0000000000..dd442ccb8f --- /dev/null +++ b/meta/recipes-devtools/qemu/qemu/CVE-2021-20196_2.patch @@ -0,0 +1,67 @@ +From 1d48445a951fd5504190a38abeda70ea9372cf77 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= <philmd@redhat.com> +Date: Wed, 24 Nov 2021 17:15:35 +0100 +Subject: [PATCH 12/12] hw/block/fdc: Kludge missing floppy drive to fix + CVE-2021-20196 +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +Guest might select another drive on the bus by setting the +DRIVE_SEL bit of the DIGITAL OUTPUT REGISTER (DOR). +The current controller model doesn't expect a BlockBackend +to be NULL. A simple way to fix CVE-2021-20196 is to create +an empty BlockBackend when it is missing. All further +accesses will be safely handled, and the controller state +machines keep behaving correctly. + +Cc: qemu-stable@nongnu.org +Fixes: CVE-2021-20196 +Reported-by: Gaoning Pan (Ant Security Light-Year Lab) <pgn@zju.edu.cn> +Reviewed-by: Darren Kenny <darren.kenny@oracle.com> +Reviewed-by: Hanna Reitz <hreitz@redhat.com> +Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> +Message-id: 20211124161536.631563-3-philmd@redhat.com +BugLink: https://bugs.launchpad.net/qemu/+bug/1912780 +Resolves: https://gitlab.com/qemu-project/qemu/-/issues/338 +Reviewed-by: Darren Kenny <darren.kenny@oracle.com> +Reviewed-by: Hanna Reitz <hreitz@redhat.com> +Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> +Signed-off-by: John Snow <jsnow@redhat.com> + +Upstream-Status: Backport [1ab95af033a419e7a64e2d58e67dd96b20af5233] +CVE: CVE-2021-20196 + +Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com> +--- + hw/block/fdc.c | 14 +++++++++++++- + 1 file changed, 13 insertions(+), 1 deletion(-) + +diff --git a/hw/block/fdc.c b/hw/block/fdc.c +index 854b4f172..a736c4d14 100644 +--- a/hw/block/fdc.c ++++ b/hw/block/fdc.c +@@ -1365,7 +1365,19 @@ static FDrive *get_drv(FDCtrl *fdctrl, int unit) + + static FDrive *get_cur_drv(FDCtrl *fdctrl) + { +- return get_drv(fdctrl, fdctrl->cur_drv); ++ FDrive *cur_drv = get_drv(fdctrl, fdctrl->cur_drv); ++ ++ if (!cur_drv->blk) { ++ /* ++ * Kludge: empty drive line selected. Create an anonymous ++ * BlockBackend to avoid NULL deref with various BlockBackend ++ * API calls within this model (CVE-2021-20196). ++ * Due to the controller QOM model limitations, we don't ++ * attach the created to the controller device. ++ */ ++ cur_drv->blk = blk_create_empty_drive(); ++ } ++ return cur_drv; + } + + /* Status A register : 0x00 (read-only) */ +-- +2.31.1 + diff --git a/meta/recipes-devtools/qemu/qemu/CVE-2021-3713.patch b/meta/recipes-devtools/qemu/qemu/CVE-2021-3713.patch new file mode 100644 index 0000000000..33fca66d3d --- /dev/null +++ b/meta/recipes-devtools/qemu/qemu/CVE-2021-3713.patch @@ -0,0 +1,68 @@ +From 9a8f71ec660e67c51cc5905dd9d2a12ff78ce743 Mon Sep 17 00:00:00 2001 +From: Gerd Hoffmann <kraxel@redhat.com> +Date: Wed, 18 Aug 2021 14:05:05 +0200 +Subject: [PATCH 08/12] uas: add stream number sanity checks. +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +The device uses the guest-supplied stream number unchecked, which can +lead to guest-triggered out-of-band access to the UASDevice->data3 and +UASDevice->status3 fields. Add the missing checks. + +Fixes: CVE-2021-3713 +Signed-off-by: Gerd Hoffmann <kraxel@redhat.com> +Reported-by: Chen Zhe <chenzhe@huawei.com> +Reported-by: Tan Jingguo <tanjingguo@huawei.com> +Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> +Message-Id: <20210818120505.1258262-2-kraxel@redhat.com> +(cherry picked from commit 13b250b12ad3c59114a6a17d59caf073ce45b33a) +Signed-off-by: Michael Roth <michael.roth@amd.com> + +Upstream-Status: Backport [36403e8788a264dc96174f52584681ebcb4f54b1] +CVE: CVE-2021-3713 + +Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com> +--- + hw/usb/dev-uas.c | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +diff --git a/hw/usb/dev-uas.c b/hw/usb/dev-uas.c +index cec071d96..157734eb0 100644 +--- a/hw/usb/dev-uas.c ++++ b/hw/usb/dev-uas.c +@@ -831,6 +831,9 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) + } + break; + case UAS_PIPE_ID_STATUS: ++ if (p->stream > UAS_MAX_STREAMS) { ++ goto err_stream; ++ } + if (p->stream) { + QTAILQ_FOREACH(st, &uas->results, next) { + if (st->stream == p->stream) { +@@ -858,6 +861,9 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) + break; + case UAS_PIPE_ID_DATA_IN: + case UAS_PIPE_ID_DATA_OUT: ++ if (p->stream > UAS_MAX_STREAMS) { ++ goto err_stream; ++ } + if (p->stream) { + req = usb_uas_find_request(uas, p->stream); + } else { +@@ -893,6 +899,11 @@ static void usb_uas_handle_data(USBDevice *dev, USBPacket *p) + p->status = USB_RET_STALL; + break; + } ++ ++err_stream: ++ error_report("%s: invalid stream %d", __func__, p->stream); ++ p->status = USB_RET_STALL; ++ return; + } + + static void usb_uas_unrealize(USBDevice *dev) +-- +2.31.1 + diff --git a/meta/recipes-devtools/qemu/qemu/CVE-2021-3748.patch b/meta/recipes-devtools/qemu/qemu/CVE-2021-3748.patch new file mode 100644 index 0000000000..4765f24739 --- /dev/null +++ b/meta/recipes-devtools/qemu/qemu/CVE-2021-3748.patch @@ -0,0 +1,127 @@ +From bacc200f623647632258f7efc0f098ac30dd4225 Mon Sep 17 00:00:00 2001 +From: Jason Wang <jasowang@redhat.com> +Date: Thu, 2 Sep 2021 13:44:12 +0800 +Subject: [PATCH 09/12] virtio-net: fix use after unmap/free for sg + +When mergeable buffer is enabled, we try to set the num_buffers after +the virtqueue elem has been unmapped. This will lead several issues, +E.g a use after free when the descriptor has an address which belongs +to the non direct access region. In this case we use bounce buffer +that is allocated during address_space_map() and freed during +address_space_unmap(). + +Fixing this by storing the elems temporarily in an array and delay the +unmap after we set the the num_buffers. + +This addresses CVE-2021-3748. + +Reported-by: Alexander Bulekov <alxndr@bu.edu> +Fixes: fbe78f4f55c6 ("virtio-net support") +Cc: qemu-stable@nongnu.org +Signed-off-by: Jason Wang <jasowang@redhat.com> + +Upstream-Status: Backport [bedd7e93d01961fcb16a97ae45d93acf357e11f6] +CVE: CVE-2021-3748 + +Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com> +--- + hw/net/virtio-net.c | 39 ++++++++++++++++++++++++++++++++------- + 1 file changed, 32 insertions(+), 7 deletions(-) + +diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c +index 9179013ac..df1d30e2c 100644 +--- a/hw/net/virtio-net.c ++++ b/hw/net/virtio-net.c +@@ -1665,10 +1665,13 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + VirtIONet *n = qemu_get_nic_opaque(nc); + VirtIONetQueue *q = virtio_net_get_subqueue(nc); + VirtIODevice *vdev = VIRTIO_DEVICE(n); ++ VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE]; ++ size_t lens[VIRTQUEUE_MAX_SIZE]; + struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE]; + struct virtio_net_hdr_mrg_rxbuf mhdr; + unsigned mhdr_cnt = 0; +- size_t offset, i, guest_offset; ++ size_t offset, i, guest_offset, j; ++ ssize_t err; + + if (!virtio_net_can_receive(nc)) { + return -1; +@@ -1699,6 +1702,12 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + + total = 0; + ++ if (i == VIRTQUEUE_MAX_SIZE) { ++ virtio_error(vdev, "virtio-net unexpected long buffer chain"); ++ err = size; ++ goto err; ++ } ++ + elem = virtqueue_pop(q->rx_vq, sizeof(VirtQueueElement)); + if (!elem) { + if (i) { +@@ -1710,7 +1719,8 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + n->guest_hdr_len, n->host_hdr_len, + vdev->guest_features); + } +- return -1; ++ err = -1; ++ goto err; + } + + if (elem->in_num < 1) { +@@ -1718,7 +1728,8 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + "virtio-net receive queue contains no in buffers"); + virtqueue_detach_element(q->rx_vq, elem, 0); + g_free(elem); +- return -1; ++ err = -1; ++ goto err; + } + + sg = elem->in_sg; +@@ -1755,12 +1766,13 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + if (!n->mergeable_rx_bufs && offset < size) { + virtqueue_unpop(q->rx_vq, elem, total); + g_free(elem); +- return size; ++ err = size; ++ goto err; + } + +- /* signal other side */ +- virtqueue_fill(q->rx_vq, elem, total, i++); +- g_free(elem); ++ elems[i] = elem; ++ lens[i] = total; ++ i++; + } + + if (mhdr_cnt) { +@@ -1770,10 +1782,23 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + &mhdr.num_buffers, sizeof mhdr.num_buffers); + } + ++ for (j = 0; j < i; j++) { ++ /* signal other side */ ++ virtqueue_fill(q->rx_vq, elems[j], lens[j], j); ++ g_free(elems[j]); ++ } ++ + virtqueue_flush(q->rx_vq, i); + virtio_notify(vdev, q->rx_vq); + + return size; ++ ++err: ++ for (j = 0; j < i; j++) { ++ g_free(elems[j]); ++ } ++ ++ return err; + } + + static ssize_t virtio_net_do_receive(NetClientState *nc, const uint8_t *buf, +-- +2.31.1 + diff --git a/meta/recipes-devtools/qemu/qemu/CVE-2021-3930.patch b/meta/recipes-devtools/qemu/qemu/CVE-2021-3930.patch new file mode 100644 index 0000000000..bfbe5cee33 --- /dev/null +++ b/meta/recipes-devtools/qemu/qemu/CVE-2021-3930.patch @@ -0,0 +1,53 @@ +From cdca50eff9c38367be54f92839734ab490c8b0f7 Mon Sep 17 00:00:00 2001 +From: Mauro Matteo Cascella <mcascell@redhat.com> +Date: Thu, 4 Nov 2021 17:31:38 +0100 +Subject: [PATCH 10/12] hw/scsi/scsi-disk: MODE_PAGE_ALLS not allowed in MODE + SELECT commands + +This avoids an off-by-one read of 'mode_sense_valid' buffer in +hw/scsi/scsi-disk.c:mode_sense_page(). + +Fixes: CVE-2021-3930 +Cc: qemu-stable@nongnu.org +Reported-by: Alexander Bulekov <alxndr@bu.edu> +Fixes: a8f4bbe2900 ("scsi-disk: store valid mode pages in a table") +Fixes: #546 +Reported-by: Qiuhao Li <Qiuhao.Li@outlook.com> +Signed-off-by: Mauro Matteo Cascella <mcascell@redhat.com> +Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> + +Upstream-Status: Backport [b3af7fdf9cc537f8f0dd3e2423d83f5c99a457e8] +CVE: CVE-2021-3930 + +Signed-off-by: Sakib Sajal <sakib.sajal@windriver.com> +--- + hw/scsi/scsi-disk.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c +index 90841ad79..5b44ed7d8 100644 +--- a/hw/scsi/scsi-disk.c ++++ b/hw/scsi/scsi-disk.c +@@ -1100,6 +1100,7 @@ static int mode_sense_page(SCSIDiskState *s, int page, uint8_t **p_outbuf, + uint8_t *p = *p_outbuf + 2; + int length; + ++ assert(page < ARRAY_SIZE(mode_sense_valid)); + if ((mode_sense_valid[page] & (1 << s->qdev.type)) == 0) { + return -1; + } +@@ -1441,6 +1442,11 @@ static int scsi_disk_check_mode_select(SCSIDiskState *s, int page, + return -1; + } + ++ /* MODE_PAGE_ALLS is only valid for MODE SENSE commands */ ++ if (page == MODE_PAGE_ALLS) { ++ return -1; ++ } ++ + p = mode_current; + memset(mode_current, 0, inlen + 2); + len = mode_sense_page(s, page, &p, 0); +-- +2.31.1 + diff --git a/meta/recipes-devtools/ruby/ruby/CVE-2021-31799.patch b/meta/recipes-devtools/ruby/ruby/CVE-2021-31799.patch deleted file mode 100644 index 83064e85ab..0000000000 --- a/meta/recipes-devtools/ruby/ruby/CVE-2021-31799.patch +++ /dev/null @@ -1,57 +0,0 @@ -From b1c73f239fe9af97de837331849f55d67c27561e Mon Sep 17 00:00:00 2001 -From: aycabta <aycabta@gmail.com> -Date: Sun, 2 May 2021 20:52:23 +0900 -Subject: [PATCH] [ruby/rdoc] Use File.open to fix the OS Command Injection - vulnerability in CVE-2021-31799 - -https://github.com/ruby/rdoc/commit/a7f5d6ab88 - -CVE: CVE-2021-31799 - -Upstream-Status: Backport[https://github.com/ruby/ruby/commit/b1c73f239fe9af97de837331849f55d67c27561e] - -Signed-off-by: Mingli Yu <mingli.yu@windriver.com> ---- - lib/rdoc/rdoc.rb | 2 +- - test/rdoc/test_rdoc_rdoc.rb | 12 ++++++++++++ - 2 files changed, 13 insertions(+), 1 deletion(-) - -diff --git a/lib/rdoc/rdoc.rb b/lib/rdoc/rdoc.rb -index 680a8612f7..904625f105 100644 ---- a/lib/rdoc/rdoc.rb -+++ b/lib/rdoc/rdoc.rb -@@ -444,7 +444,7 @@ def remove_unparseable files - files.reject do |file, *| - file =~ /\.(?:class|eps|erb|scpt\.txt|svg|ttf|yml)$/i or - (file =~ /tags$/i and -- open(file, 'rb') { |io| -+ File.open(file, 'rb') { |io| - io.read(100) =~ /\A(\f\n[^,]+,\d+$|!_TAG_)/ - }) - end -diff --git a/test/rdoc/test_rdoc_rdoc.rb b/test/rdoc/test_rdoc_rdoc.rb -index 3910dd4656..a83d5a1b88 100644 ---- a/test/rdoc/test_rdoc_rdoc.rb -+++ b/test/rdoc/test_rdoc_rdoc.rb -@@ -456,6 +456,18 @@ def test_remove_unparseable_tags_vim - end - end - -+ def test_remove_unparseable_CVE_2021_31799 -+ temp_dir do -+ file_list = ['| touch evil.txt && echo tags'] -+ file_list.each do |f| -+ FileUtils.touch f -+ end -+ -+ assert_equal file_list, @rdoc.remove_unparseable(file_list) -+ assert_equal file_list, Dir.children('.') -+ end -+ end -+ - def test_setup_output_dir - Dir.mktmpdir {|d| - path = File.join d, 'testdir' --- -2.17.1 - diff --git a/meta/recipes-devtools/ruby/ruby/CVE-2021-31810.patch b/meta/recipes-devtools/ruby/ruby/CVE-2021-31810.patch deleted file mode 100644 index 69d774e0b7..0000000000 --- a/meta/recipes-devtools/ruby/ruby/CVE-2021-31810.patch +++ /dev/null @@ -1,258 +0,0 @@ -From 8cebc092cd18f4cfb669f66018ea8ffc6f408584 Mon Sep 17 00:00:00 2001 -From: Yusuke Endoh <mame@ruby-lang.org> -Date: Wed, 7 Jul 2021 11:57:15 +0900 -Subject: [PATCH] Ignore IP addresses in PASV responses by default, and add new - option use_pasv_ip - -This fixes CVE-2021-31810. -Reported by Alexandr Savca. - -Co-authored-by: Shugo Maeda <shugo@ruby-lang.org> - -CVE: CVE-2021-31810 - -Upstream-Status: Backport -[https://github.com/ruby/ruby/commit/bf4d05173c7cf04d8892e4b64508ecf7902717cd] - -Signed-off-by: Yi Zhao <yi.zhao@windriver.com> ---- - lib/net/ftp.rb | 15 +++- - test/net/ftp/test_ftp.rb | 159 ++++++++++++++++++++++++++++++++++++++- - 2 files changed, 170 insertions(+), 4 deletions(-) - -diff --git a/lib/net/ftp.rb b/lib/net/ftp.rb -index 88e8655..d6f5cc3 100644 ---- a/lib/net/ftp.rb -+++ b/lib/net/ftp.rb -@@ -98,6 +98,10 @@ module Net - # When +true+, the connection is in passive mode. Default: +true+. - attr_accessor :passive - -+ # When +true+, use the IP address in PASV responses. Otherwise, it uses -+ # the same IP address for the control connection. Default: +false+. -+ attr_accessor :use_pasv_ip -+ - # When +true+, all traffic to and from the server is written - # to +$stdout+. Default: +false+. - attr_accessor :debug_mode -@@ -206,6 +210,9 @@ module Net - # handshake. - # See Net::FTP#ssl_handshake_timeout for - # details. Default: +nil+. -+ # use_pasv_ip:: When +true+, use the IP address in PASV responses. -+ # Otherwise, it uses the same IP address for the control -+ # connection. Default: +false+. - # debug_mode:: When +true+, all traffic to and from the server is - # written to +$stdout+. Default: +false+. - # -@@ -266,6 +273,7 @@ module Net - @open_timeout = options[:open_timeout] - @ssl_handshake_timeout = options[:ssl_handshake_timeout] - @read_timeout = options[:read_timeout] || 60 -+ @use_pasv_ip = options[:use_pasv_ip] || false - if host - connect(host, options[:port] || FTP_PORT) - if options[:username] -@@ -1371,7 +1379,12 @@ module Net - raise FTPReplyError, resp - end - if m = /\((?<host>\d+(?:,\d+){3}),(?<port>\d+,\d+)\)/.match(resp) -- return parse_pasv_ipv4_host(m["host"]), parse_pasv_port(m["port"]) -+ if @use_pasv_ip -+ host = parse_pasv_ipv4_host(m["host"]) -+ else -+ host = @bare_sock.remote_address.ip_address -+ end -+ return host, parse_pasv_port(m["port"]) - else - raise FTPProtoError, resp - end -diff --git a/test/net/ftp/test_ftp.rb b/test/net/ftp/test_ftp.rb -index 023e794..243d4ad 100644 ---- a/test/net/ftp/test_ftp.rb -+++ b/test/net/ftp/test_ftp.rb -@@ -61,7 +61,7 @@ class FTPTest < Test::Unit::TestCase - end - - def test_parse227 -- ftp = Net::FTP.new -+ ftp = Net::FTP.new(nil, use_pasv_ip: true) - host, port = ftp.send(:parse227, "227 Entering Passive Mode (192,168,0,1,12,34)") - assert_equal("192.168.0.1", host) - assert_equal(3106, port) -@@ -80,6 +80,14 @@ class FTPTest < Test::Unit::TestCase - assert_raise(Net::FTPProtoError) do - ftp.send(:parse227, "227 ) foo bar (") - end -+ -+ ftp = Net::FTP.new -+ sock = OpenStruct.new -+ sock.remote_address = OpenStruct.new -+ sock.remote_address.ip_address = "10.0.0.1" -+ ftp.instance_variable_set(:@bare_sock, sock) -+ host, port = ftp.send(:parse227, "227 Entering Passive Mode (192,168,0,1,12,34)") -+ assert_equal("10.0.0.1", host) - end - - def test_parse228 -@@ -2474,10 +2482,155 @@ EOF - end - end - -+ def test_ignore_pasv_ip -+ commands = [] -+ binary_data = (0..0xff).map {|i| i.chr}.join * 4 * 3 -+ server = create_ftp_server(nil, "127.0.0.1") { |sock| -+ sock.print("220 (test_ftp).\r\n") -+ commands.push(sock.gets) -+ sock.print("331 Please specify the password.\r\n") -+ commands.push(sock.gets) -+ sock.print("230 Login successful.\r\n") -+ commands.push(sock.gets) -+ sock.print("200 Switching to Binary mode.\r\n") -+ line = sock.gets -+ commands.push(line) -+ data_server = TCPServer.new("127.0.0.1", 0) -+ port = data_server.local_address.ip_port -+ sock.printf("227 Entering Passive Mode (999,0,0,1,%s).\r\n", -+ port.divmod(256).join(",")) -+ commands.push(sock.gets) -+ sock.print("150 Opening BINARY mode data connection for foo (#{binary_data.size} bytes)\r\n") -+ conn = data_server.accept -+ binary_data.scan(/.{1,1024}/nm) do |s| -+ conn.print(s) -+ end -+ conn.shutdown(Socket::SHUT_WR) -+ conn.read -+ conn.close -+ data_server.close -+ sock.print("226 Transfer complete.\r\n") -+ } -+ begin -+ begin -+ ftp = Net::FTP.new -+ ftp.passive = true -+ ftp.read_timeout *= 5 if defined?(RubyVM::MJIT) && RubyVM::MJIT.enabled? # for --jit-wait -+ ftp.connect("127.0.0.1", server.port) -+ ftp.login -+ assert_match(/\AUSER /, commands.shift) -+ assert_match(/\APASS /, commands.shift) -+ assert_equal("TYPE I\r\n", commands.shift) -+ buf = ftp.getbinaryfile("foo", nil) -+ assert_equal(binary_data, buf) -+ assert_equal(Encoding::ASCII_8BIT, buf.encoding) -+ assert_equal("PASV\r\n", commands.shift) -+ assert_equal("RETR foo\r\n", commands.shift) -+ assert_equal(nil, commands.shift) -+ ensure -+ ftp.close if ftp -+ end -+ ensure -+ server.close -+ end -+ end -+ -+ def test_use_pasv_ip -+ commands = [] -+ binary_data = (0..0xff).map {|i| i.chr}.join * 4 * 3 -+ server = create_ftp_server(nil, "127.0.0.1") { |sock| -+ sock.print("220 (test_ftp).\r\n") -+ commands.push(sock.gets) -+ sock.print("331 Please specify the password.\r\n") -+ commands.push(sock.gets) -+ sock.print("230 Login successful.\r\n") -+ commands.push(sock.gets) -+ sock.print("200 Switching to Binary mode.\r\n") -+ line = sock.gets -+ commands.push(line) -+ data_server = TCPServer.new("127.0.0.1", 0) -+ port = data_server.local_address.ip_port -+ sock.printf("227 Entering Passive Mode (127,0,0,1,%s).\r\n", -+ port.divmod(256).join(",")) -+ commands.push(sock.gets) -+ sock.print("150 Opening BINARY mode data connection for foo (#{binary_data.size} bytes)\r\n") -+ conn = data_server.accept -+ binary_data.scan(/.{1,1024}/nm) do |s| -+ conn.print(s) -+ end -+ conn.shutdown(Socket::SHUT_WR) -+ conn.read -+ conn.close -+ data_server.close -+ sock.print("226 Transfer complete.\r\n") -+ } -+ begin -+ begin -+ ftp = Net::FTP.new -+ ftp.passive = true -+ ftp.use_pasv_ip = true -+ ftp.read_timeout *= 5 if defined?(RubyVM::MJIT) && RubyVM::MJIT.enabled? # for --jit-wait -+ ftp.connect("127.0.0.1", server.port) -+ ftp.login -+ assert_match(/\AUSER /, commands.shift) -+ assert_match(/\APASS /, commands.shift) -+ assert_equal("TYPE I\r\n", commands.shift) -+ buf = ftp.getbinaryfile("foo", nil) -+ assert_equal(binary_data, buf) -+ assert_equal(Encoding::ASCII_8BIT, buf.encoding) -+ assert_equal("PASV\r\n", commands.shift) -+ assert_equal("RETR foo\r\n", commands.shift) -+ assert_equal(nil, commands.shift) -+ ensure -+ ftp.close if ftp -+ end -+ ensure -+ server.close -+ end -+ end -+ -+ def test_use_pasv_invalid_ip -+ commands = [] -+ binary_data = (0..0xff).map {|i| i.chr}.join * 4 * 3 -+ server = create_ftp_server(nil, "127.0.0.1") { |sock| -+ sock.print("220 (test_ftp).\r\n") -+ commands.push(sock.gets) -+ sock.print("331 Please specify the password.\r\n") -+ commands.push(sock.gets) -+ sock.print("230 Login successful.\r\n") -+ commands.push(sock.gets) -+ sock.print("200 Switching to Binary mode.\r\n") -+ line = sock.gets -+ commands.push(line) -+ sock.print("227 Entering Passive Mode (999,0,0,1,48,57).\r\n") -+ commands.push(sock.gets) -+ } -+ begin -+ begin -+ ftp = Net::FTP.new -+ ftp.passive = true -+ ftp.use_pasv_ip = true -+ ftp.read_timeout *= 5 if defined?(RubyVM::MJIT) && RubyVM::MJIT.enabled? # for --jit-wait -+ ftp.connect("127.0.0.1", server.port) -+ ftp.login -+ assert_match(/\AUSER /, commands.shift) -+ assert_match(/\APASS /, commands.shift) -+ assert_equal("TYPE I\r\n", commands.shift) -+ assert_raise(SocketError) do -+ ftp.getbinaryfile("foo", nil) -+ end -+ ensure -+ ftp.close if ftp -+ end -+ ensure -+ server.close -+ end -+ end -+ - private - -- def create_ftp_server(sleep_time = nil) -- server = TCPServer.new(SERVER_ADDR, 0) -+ def create_ftp_server(sleep_time = nil, addr = SERVER_ADDR) -+ server = TCPServer.new(addr, 0) - @thread = Thread.start do - if sleep_time - sleep(sleep_time) --- -2.17.1 - diff --git a/meta/recipes-devtools/ruby/ruby/CVE-2021-32066.patch b/meta/recipes-devtools/ruby/ruby/CVE-2021-32066.patch deleted file mode 100644 index b78a74a4b5..0000000000 --- a/meta/recipes-devtools/ruby/ruby/CVE-2021-32066.patch +++ /dev/null @@ -1,102 +0,0 @@ -From e2ac25d0eb66de99f098d6669cf4f06796aa6256 Mon Sep 17 00:00:00 2001 -From: Shugo Maeda <shugo@ruby-lang.org> -Date: Tue, 11 May 2021 10:31:27 +0900 -Subject: [PATCH] Fix StartTLS stripping vulnerability - -This fixes CVE-2021-32066. -Reported by Alexandr Savca in <https://hackerone.com/reports/1178562>. - -CVE: CVE-2021-32066 - -Upstream-Status: Backport -[https://github.com/ruby/ruby/commit/e2ac25d0eb66de99f098d6669cf4f06796aa6256] - -Signed-off-by: Yi Zhao <yi.zhao@windriver.com> ---- - lib/net/imap.rb | 8 +++++++- - test/net/imap/test_imap.rb | 31 +++++++++++++++++++++++++++++++ - 2 files changed, 38 insertions(+), 1 deletion(-) - -diff --git a/lib/net/imap.rb b/lib/net/imap.rb -index 505b4c8950..d45304f289 100644 ---- a/lib/net/imap.rb -+++ b/lib/net/imap.rb -@@ -1218,12 +1218,14 @@ def get_tagged_response(tag, cmd) - end - resp = @tagged_responses.delete(tag) - case resp.name -+ when /\A(?:OK)\z/ni -+ return resp - when /\A(?:NO)\z/ni - raise NoResponseError, resp - when /\A(?:BAD)\z/ni - raise BadResponseError, resp - else -- return resp -+ raise UnknownResponseError, resp - end - end - -@@ -3719,6 +3721,10 @@ class BadResponseError < ResponseError - class ByeResponseError < ResponseError - end - -+ # Error raised upon an unknown response from the server. -+ class UnknownResponseError < ResponseError -+ end -+ - RESPONSE_ERRORS = Hash.new(ResponseError) - RESPONSE_ERRORS["NO"] = NoResponseError - RESPONSE_ERRORS["BAD"] = BadResponseError -diff --git a/test/net/imap/test_imap.rb b/test/net/imap/test_imap.rb -index 8b924b524e..85fb71d440 100644 ---- a/test/net/imap/test_imap.rb -+++ b/test/net/imap/test_imap.rb -@@ -127,6 +127,16 @@ def test_starttls - imap.disconnect - end - end -+ -+ def test_starttls_stripping -+ starttls_stripping_test do |port| -+ imap = Net::IMAP.new("localhost", :port => port) -+ assert_raise(Net::IMAP::UnknownResponseError) do -+ imap.starttls(:ca_file => CA_FILE) -+ end -+ imap -+ end -+ end - end - - def start_server -@@ -834,6 +844,27 @@ def starttls_test - end - end - -+ def starttls_stripping_test -+ server = create_tcp_server -+ port = server.addr[1] -+ start_server do -+ sock = server.accept -+ begin -+ sock.print("* OK test server\r\n") -+ sock.gets -+ sock.print("RUBY0001 BUG unhandled command\r\n") -+ ensure -+ sock.close -+ server.close -+ end -+ end -+ begin -+ imap = yield(port) -+ ensure -+ imap.disconnect if imap && !imap.disconnected? -+ end -+ end -+ - def create_tcp_server - return TCPServer.new(server_addr, 0) - end --- -2.25.1 - diff --git a/meta/recipes-devtools/ruby/ruby_3.0.1.bb b/meta/recipes-devtools/ruby/ruby_3.0.3.bb index a348946972..a781f69534 100644 --- a/meta/recipes-devtools/ruby/ruby_3.0.1.bb +++ b/meta/recipes-devtools/ruby/ruby_3.0.3.bb @@ -6,16 +6,13 @@ SRC_URI += " \ file://remove_has_include_macros.patch \ file://run-ptest \ file://0001-template-Makefile.in-do-not-write-host-cross-cc-item.patch \ - file://CVE-2021-31810.patch \ - file://CVE-2021-32066.patch \ - file://CVE-2021-31799.patch \ file://0003-rdoc-build-reproducible-documentation.patch \ file://0004-lib-mkmf.rb-sort-list-of-object-files-in-generated-M.patch \ file://0005-Mark-Gemspec-reproducible-change-fixing-784225-too.patch \ file://0006-Make-gemspecs-reproducible.patch \ " -SRC_URI[sha256sum] = "369825db2199f6aeef16b408df6a04ebaddb664fb9af0ec8c686b0ce7ab77727" +SRC_URI[sha256sum] = "3586861cb2df56970287f0fd83f274bd92058872d830d15570b36def7f1a92ac" PACKAGECONFIG ??= "" PACKAGECONFIG += "${@bb.utils.filter('DISTRO_FEATURES', 'ipv6', d)}" @@ -81,8 +78,6 @@ do_install_ptest () { -i ${D}${PTEST_PATH}/test/erb/test_erb_command.rb cp -r ${S}/include ${D}/${libdir}/ruby/ - test_case_rb=`grep rubygems/test_case.rb ${B}/.installed.list` - sed -i -e 's:../../../test/:../../../ptest/test/:g' ${D}/$test_case_rb } PACKAGES =+ "${PN}-ri-docs ${PN}-rdoc" diff --git a/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-1.patch b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-1.patch new file mode 100644 index 0000000000..d01b5c6871 --- /dev/null +++ b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-1.patch @@ -0,0 +1,135 @@ +The commit is required by the fix for CVE-2021-41072. + +Upstream-Status: Backport [https://github.com/plougher/squashfs-tools/commit/80b8441] + +Signed-off-by: Kai Kang <kai.kang@windriver.com> + +From 80b8441a37fcf8bf07dacf24d9d6c6459a0f6e36 Mon Sep 17 00:00:00 2001 +From: Phillip Lougher <phillip@squashfs.org.uk> +Date: Sun, 12 Sep 2021 19:58:19 +0100 +Subject: [PATCH] unsquashfs: use squashfs_closedir() to delete directory + +Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> +--- + squashfs-tools/unsquash-1.c | 3 +-- + squashfs-tools/unsquash-1234.c | 11 +++++++++-- + squashfs-tools/unsquash-2.c | 3 +-- + squashfs-tools/unsquash-3.c | 3 +-- + squashfs-tools/unsquash-4.c | 3 +-- + squashfs-tools/unsquashfs.c | 7 ------- + squashfs-tools/unsquashfs.h | 1 + + 7 files changed, 14 insertions(+), 17 deletions(-) + +diff --git a/squashfs-tools/unsquash-1.c b/squashfs-tools/unsquash-1.c +index acba821..7598499 100644 +--- a/squashfs-tools/unsquash-1.c ++++ b/squashfs-tools/unsquash-1.c +@@ -373,8 +373,7 @@ static struct dir *squashfs_opendir(unsigned int block_start, unsigned int offse + return dir; + + corrupted: +- free(dir->dirs); +- free(dir); ++ squashfs_closedir(dir); + return NULL; + } + +diff --git a/squashfs-tools/unsquash-1234.c b/squashfs-tools/unsquash-1234.c +index c2d4f42..0c8dfbb 100644 +--- a/squashfs-tools/unsquash-1234.c ++++ b/squashfs-tools/unsquash-1234.c +@@ -25,8 +25,8 @@ + * unsquash-4. + */ + +-#define TRUE 1 +-#define FALSE 0 ++#include "unsquashfs.h" ++ + /* + * Check name for validity, name should not + * - be ".", "./", or +@@ -56,3 +56,10 @@ int check_name(char *name, int size) + + return TRUE; + } ++ ++ ++void squashfs_closedir(struct dir *dir) ++{ ++ free(dir->dirs); ++ free(dir); ++} +diff --git a/squashfs-tools/unsquash-2.c b/squashfs-tools/unsquash-2.c +index 0746b3d..86f62ba 100644 +--- a/squashfs-tools/unsquash-2.c ++++ b/squashfs-tools/unsquash-2.c +@@ -465,8 +465,7 @@ static struct dir *squashfs_opendir(unsigned int block_start, unsigned int offse + return dir; + + corrupted: +- free(dir->dirs); +- free(dir); ++ squashfs_closedir(dir); + return NULL; + } + +diff --git a/squashfs-tools/unsquash-3.c b/squashfs-tools/unsquash-3.c +index 094caaa..c04aa9e 100644 +--- a/squashfs-tools/unsquash-3.c ++++ b/squashfs-tools/unsquash-3.c +@@ -499,8 +499,7 @@ static struct dir *squashfs_opendir(unsigned int block_start, unsigned int offse + return dir; + + corrupted: +- free(dir->dirs); +- free(dir); ++ squashfs_closedir(dir); + return NULL; + } + +diff --git a/squashfs-tools/unsquash-4.c b/squashfs-tools/unsquash-4.c +index 3a1b9e1..ff62dcc 100644 +--- a/squashfs-tools/unsquash-4.c ++++ b/squashfs-tools/unsquash-4.c +@@ -436,8 +436,7 @@ static struct dir *squashfs_opendir(unsigned int block_start, unsigned int offse + return dir; + + corrupted: +- free(dir->dirs); +- free(dir); ++ squashfs_closedir(dir); + return NULL; + } + +diff --git a/squashfs-tools/unsquashfs.c b/squashfs-tools/unsquashfs.c +index 7b590bd..04be53c 100644 +--- a/squashfs-tools/unsquashfs.c ++++ b/squashfs-tools/unsquashfs.c +@@ -1350,13 +1350,6 @@ unsigned int *offset, unsigned int *type) + } + + +-void squashfs_closedir(struct dir *dir) +-{ +- free(dir->dirs); +- free(dir); +-} +- +- + char *get_component(char *target, char **targname) + { + char *start; +diff --git a/squashfs-tools/unsquashfs.h b/squashfs-tools/unsquashfs.h +index 2e9201c..5ecb2ab 100644 +--- a/squashfs-tools/unsquashfs.h ++++ b/squashfs-tools/unsquashfs.h +@@ -291,4 +291,5 @@ extern long long *alloc_index_table(int); + + /* unsquash-1234.c */ + extern int check_name(char *, int); ++extern void squashfs_closedir(struct dir *); + #endif +-- +2.17.1 + diff --git a/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-2.patch b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-2.patch new file mode 100644 index 0000000000..0b80d07b3b --- /dev/null +++ b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-2.patch @@ -0,0 +1,109 @@ +The commit is required by the fix for CVE-2021-41072. Update context for +version 4.4. + +Upstream-Status: Backport [https://github.com/plougher/squashfs-tools/commit/1993a4e] + +Signed-off-by: Kai Kang <kai.kang@windriver.com> + +From 1993a4e7aeda04962bf26e84c15fba8b58837e10 Mon Sep 17 00:00:00 2001 +From: Phillip Lougher <phillip@squashfs.org.uk> +Date: Sun, 12 Sep 2021 20:09:13 +0100 +Subject: [PATCH] unsquashfs: dynamically allocate name + +Dynamically allocate name rather than store it +directly in structure. + +Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> +--- + squashfs-tools/unsquash-1.c | 2 +- + squashfs-tools/unsquash-1234.c | 5 +++++ + squashfs-tools/unsquash-2.c | 2 +- + squashfs-tools/unsquash-3.c | 2 +- + squashfs-tools/unsquash-4.c | 2 +- + squashfs-tools/unsquashfs.h | 2 +- + 6 files changed, 10 insertions(+), 5 deletions(-) + +diff --git a/squashfs-tools/unsquash-1.c b/squashfs-tools/unsquash-1.c +index 7598499..d0121c6 100644 +--- a/squashfs-tools/unsquash-1.c ++++ b/squashfs-tools/unsquash-1.c +@@ -303,7 +303,7 @@ static struct dir *squashfs_opendir(unsi + "realloc failed!\n"); + dir->dirs = new_dir; + } +- strcpy(dir->dirs[dir->dir_count].name, dire->name); ++ dir->dirs[dir->dir_count].name = strdup(dire->name); + dir->dirs[dir->dir_count].start_block = + dirh.start_block; + dir->dirs[dir->dir_count].offset = dire->offset; +diff --git a/squashfs-tools/unsquash-1234.c b/squashfs-tools/unsquash-1234.c +index 0c8dfbb..ac46d9d 100644 +--- a/squashfs-tools/unsquash-1234.c ++++ b/squashfs-tools/unsquash-1234.c +@@ -60,6 +60,11 @@ int check_name(char *name, int size) + + void squashfs_closedir(struct dir *dir) + { ++ int i; ++ ++ for(i = 0; i < dir->dir_count; i++) ++ free(dir->dirs[i].name); ++ + free(dir->dirs); + free(dir); + } +diff --git a/squashfs-tools/unsquash-2.c b/squashfs-tools/unsquash-2.c +index 86f62ba..e847980 100644 +--- a/squashfs-tools/unsquash-2.c ++++ b/squashfs-tools/unsquash-2.c +@@ -404,7 +404,7 @@ static struct dir *squashfs_opendir(unsi + "realloc failed!\n"); + dir->dirs = new_dir; + } +- strcpy(dir->dirs[dir->dir_count].name, dire->name); ++ dir->dirs[dir->dir_count].name = strdup(dire->name); + dir->dirs[dir->dir_count].start_block = + dirh.start_block; + dir->dirs[dir->dir_count].offset = dire->offset; +diff --git a/squashfs-tools/unsquash-3.c b/squashfs-tools/unsquash-3.c +index c04aa9e..8223f27 100644 +--- a/squashfs-tools/unsquash-3.c ++++ b/squashfs-tools/unsquash-3.c +@@ -431,7 +431,7 @@ static struct dir *squashfs_opendir(unsi + "realloc failed!\n"); + dir->dirs = new_dir; + } +- strcpy(dir->dirs[dir->dir_count].name, dire->name); ++ dir->dirs[dir->dir_count].name = strdup(dire->name); + dir->dirs[dir->dir_count].start_block = + dirh.start_block; + dir->dirs[dir->dir_count].offset = dire->offset; +diff --git a/squashfs-tools/unsquash-4.c b/squashfs-tools/unsquash-4.c +index ff62dcc..1e199a7 100644 +--- a/squashfs-tools/unsquash-4.c ++++ b/squashfs-tools/unsquash-4.c +@@ -367,7 +367,7 @@ static struct dir *squashfs_opendir(unsi + "realloc failed!\n"); + dir->dirs = new_dir; + } +- strcpy(dir->dirs[dir->dir_count].name, dire->name); ++ dir->dirs[dir->dir_count].name = strdup(dire->name); + dir->dirs[dir->dir_count].start_block = + dirh.start_block; + dir->dirs[dir->dir_count].offset = dire->offset; +diff --git a/squashfs-tools/unsquashfs.h b/squashfs-tools/unsquashfs.h +index 5ecb2ab..583fbe4 100644 +--- a/squashfs-tools/unsquashfs.h ++++ b/squashfs-tools/unsquashfs.h +@@ -165,7 +165,7 @@ struct queue { + #define DIR_ENT_SIZE 16 + + struct dir_ent { +- char name[SQUASHFS_NAME_LEN + 1]; ++ char *name; + unsigned int start_block; + unsigned int offset; + unsigned int type; +-- +2.17.1 + diff --git a/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-3.patch b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-3.patch new file mode 100644 index 0000000000..fad5898f13 --- /dev/null +++ b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072-requisite-3.patch @@ -0,0 +1,330 @@ +The commit is required by the fix for CVE-2021-41072. Update context for +version 4.4. + +Upstream-Status: Backport [https://github.com/plougher/squashfs-tools/commit/9938154] + +Signed-off-by: Kai Kang <kai.kang@windriver.com> + +From 9938154174756ee48a94ea0b076397a2944b028d Mon Sep 17 00:00:00 2001 +From: Phillip Lougher <phillip@squashfs.org.uk> +Date: Sun, 12 Sep 2021 22:58:11 +0100 +Subject: [PATCH] unsquashfs: use linked list to store directory names + +This should bring higher performance, and it allows sorting +if necessary (1.x and 2.0 filesystems). + +Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> +--- + squashfs-tools/unsquash-1.c | 30 +++++++++++++++--------------- + squashfs-tools/unsquash-1234.c | 12 ++++++++---- + squashfs-tools/unsquash-2.c | 29 +++++++++++++++-------------- + squashfs-tools/unsquash-3.c | 29 +++++++++++++++-------------- + squashfs-tools/unsquash-4.c | 29 +++++++++++++++-------------- + squashfs-tools/unsquashfs.c | 16 ++++++++++------ + squashfs-tools/unsquashfs.h | 3 ++- + 7 files changed, 80 insertions(+), 68 deletions(-) + +diff --git a/squashfs-tools/unsquash-1.c b/squashfs-tools/unsquash-1.c +index d0121c6..b604434 100644 +--- a/squashfs-tools/unsquash-1.c ++++ b/squashfs-tools/unsquash-1.c +@@ -207,7 +207,7 @@ static struct dir *squashfs_opendir(unsi + long long start; + int bytes; + int dir_count, size; +- struct dir_ent *new_dir; ++ struct dir_ent *ent, *cur_ent = NULL; + struct dir *dir; + + TRACE("squashfs_opendir: inode start block %d, offset %d\n", +@@ -220,7 +220,7 @@ static struct dir *squashfs_opendir(unsi + EXIT_UNSQUASH("squashfs_opendir: malloc failed!\n"); + + dir->dir_count = 0; +- dir->cur_entry = 0; ++ dir->cur_entry = NULL; + dir->mode = (*i)->mode; + dir->uid = (*i)->uid; + dir->guid = (*i)->gid; +@@ -295,19 +295,20 @@ static struct dir *squashfs_opendir(unsi + TRACE("squashfs_opendir: directory entry %s, inode " + "%d:%d, type %d\n", dire->name, + dirh.start_block, dire->offset, dire->type); +- if((dir->dir_count % DIR_ENT_SIZE) == 0) { +- new_dir = realloc(dir->dirs, (dir->dir_count + +- DIR_ENT_SIZE) * sizeof(struct dir_ent)); +- if(new_dir == NULL) +- EXIT_UNSQUASH("squashfs_opendir: " +- "realloc failed!\n"); +- dir->dirs = new_dir; +- } +- dir->dirs[dir->dir_count].name = strdup(dire->name); +- dir->dirs[dir->dir_count].start_block = +- dirh.start_block; +- dir->dirs[dir->dir_count].offset = dire->offset; +- dir->dirs[dir->dir_count].type = dire->type; ++ ent = malloc(sizeof(struct dir_ent)); ++ if(ent == NULL) ++ MEM_ERROR(); ++ ++ ent->name = strdup(dire->name); ++ ent->start_block = dirh.start_block; ++ ent->offset = dire->offset; ++ ent->type = dire->type; ++ ent->next = NULL; ++ if(cur_ent == NULL) ++ dir->dirs = ent; ++ else ++ cur_ent->next = ent; ++ cur_ent = ent; + dir->dir_count ++; + bytes += dire->size + 1; + } +diff --git a/squashfs-tools/unsquash-1234.c b/squashfs-tools/unsquash-1234.c +index ac46d9d..e389f8d 100644 +--- a/squashfs-tools/unsquash-1234.c ++++ b/squashfs-tools/unsquash-1234.c +@@ -60,11 +60,15 @@ int check_name(char *name, int size) + + void squashfs_closedir(struct dir *dir) + { +- int i; ++ struct dir_ent *ent = dir->dirs; + +- for(i = 0; i < dir->dir_count; i++) +- free(dir->dirs[i].name); ++ while(ent) { ++ struct dir_ent *tmp = ent; ++ ++ ent = ent->next; ++ free(tmp->name); ++ free(tmp); ++ } + +- free(dir->dirs); + free(dir); + } +diff --git a/squashfs-tools/unsquash-2.c b/squashfs-tools/unsquash-2.c +index e847980..956f96f 100644 +--- a/squashfs-tools/unsquash-2.c ++++ b/squashfs-tools/unsquash-2.c +@@ -308,7 +308,7 @@ static struct dir *squashfs_opendir(unsi + long long start; + int bytes; + int dir_count, size; +- struct dir_ent *new_dir; ++ struct dir_ent *ent, *cur_ent = NULL; + struct dir *dir; + + TRACE("squashfs_opendir: inode start block %d, offset %d\n", +@@ -321,7 +321,7 @@ static struct dir *squashfs_opendir(unsi + EXIT_UNSQUASH("squashfs_opendir: malloc failed!\n"); + + dir->dir_count = 0; +- dir->cur_entry = 0; ++ dir->cur_entry = NULL; + dir->mode = (*i)->mode; + dir->uid = (*i)->uid; + dir->guid = (*i)->gid; +@@ -396,19 +396,20 @@ static struct dir *squashfs_opendir(unsi + TRACE("squashfs_opendir: directory entry %s, inode " + "%d:%d, type %d\n", dire->name, + dirh.start_block, dire->offset, dire->type); +- if((dir->dir_count % DIR_ENT_SIZE) == 0) { +- new_dir = realloc(dir->dirs, (dir->dir_count + +- DIR_ENT_SIZE) * sizeof(struct dir_ent)); +- if(new_dir == NULL) +- EXIT_UNSQUASH("squashfs_opendir: " +- "realloc failed!\n"); +- dir->dirs = new_dir; +- } +- dir->dirs[dir->dir_count].name = strdup(dire->name); +- dir->dirs[dir->dir_count].start_block = +- dirh.start_block; +- dir->dirs[dir->dir_count].offset = dire->offset; +- dir->dirs[dir->dir_count].type = dire->type; ++ ent = malloc(sizeof(struct dir_ent)); ++ if(ent == NULL) ++ MEM_ERROR(); ++ ++ ent->name = strdup(dire->name); ++ ent->start_block = dirh.start_block; ++ ent->offset = dire->offset; ++ ent->type = dire->type; ++ ent->next = NULL; ++ if(cur_ent == NULL) ++ dir->dirs = ent; ++ else ++ cur_ent->next = ent; ++ cur_ent = ent; + dir->dir_count ++; + bytes += dire->size + 1; + } +diff --git a/squashfs-tools/unsquash-3.c b/squashfs-tools/unsquash-3.c +index 8223f27..835a574 100644 +--- a/squashfs-tools/unsquash-3.c ++++ b/squashfs-tools/unsquash-3.c +@@ -334,7 +334,7 @@ static struct dir *squashfs_opendir(unsi + long long start; + int bytes; + int dir_count, size; +- struct dir_ent *new_dir; ++ struct dir_ent *ent, *cur_ent = NULL; + struct dir *dir; + + TRACE("squashfs_opendir: inode start block %d, offset %d\n", +@@ -347,7 +347,7 @@ static struct dir *squashfs_opendir(unsi + EXIT_UNSQUASH("squashfs_opendir: malloc failed!\n"); + + dir->dir_count = 0; +- dir->cur_entry = 0; ++ dir->cur_entry = NULL; + dir->mode = (*i)->mode; + dir->uid = (*i)->uid; + dir->guid = (*i)->gid; +@@ -423,19 +423,20 @@ static struct dir *squashfs_opendir(unsi + TRACE("squashfs_opendir: directory entry %s, inode " + "%d:%d, type %d\n", dire->name, + dirh.start_block, dire->offset, dire->type); +- if((dir->dir_count % DIR_ENT_SIZE) == 0) { +- new_dir = realloc(dir->dirs, (dir->dir_count + +- DIR_ENT_SIZE) * sizeof(struct dir_ent)); +- if(new_dir == NULL) +- EXIT_UNSQUASH("squashfs_opendir: " +- "realloc failed!\n"); +- dir->dirs = new_dir; +- } +- dir->dirs[dir->dir_count].name = strdup(dire->name); +- dir->dirs[dir->dir_count].start_block = +- dirh.start_block; +- dir->dirs[dir->dir_count].offset = dire->offset; +- dir->dirs[dir->dir_count].type = dire->type; ++ ent = malloc(sizeof(struct dir_ent)); ++ if(ent == NULL) ++ MEM_ERROR(); ++ ++ ent->name = strdup(dire->name); ++ ent->start_block = dirh.start_block; ++ ent->offset = dire->offset; ++ ent->type = dire->type; ++ ent->next = NULL; ++ if(cur_ent == NULL) ++ dir->dirs = ent; ++ else ++ cur_ent->next = ent; ++ cur_ent = ent; + dir->dir_count ++; + bytes += dire->size + 1; + } +diff --git a/squashfs-tools/unsquash-4.c b/squashfs-tools/unsquash-4.c +index 1e199a7..694783d 100644 +--- a/squashfs-tools/unsquash-4.c ++++ b/squashfs-tools/unsquash-4.c +@@ -281,7 +281,7 @@ static struct dir *squashfs_opendir(unsi + long long start; + long long bytes; + int dir_count, size; +- struct dir_ent *new_dir; ++ struct dir_ent *ent, *cur_ent = NULL; + struct dir *dir; + + TRACE("squashfs_opendir: inode start block %d, offset %d\n", +@@ -294,7 +294,7 @@ static struct dir *squashfs_opendir(unsi + EXIT_UNSQUASH("squashfs_opendir: malloc failed!\n"); + + dir->dir_count = 0; +- dir->cur_entry = 0; ++ dir->cur_entry = NULL; + dir->mode = (*i)->mode; + dir->uid = (*i)->uid; + dir->guid = (*i)->gid; +@@ -359,19 +359,20 @@ static struct dir *squashfs_opendir(unsi + TRACE("squashfs_opendir: directory entry %s, inode " + "%d:%d, type %d\n", dire->name, + dirh.start_block, dire->offset, dire->type); +- if((dir->dir_count % DIR_ENT_SIZE) == 0) { +- new_dir = realloc(dir->dirs, (dir->dir_count + +- DIR_ENT_SIZE) * sizeof(struct dir_ent)); +- if(new_dir == NULL) +- EXIT_UNSQUASH("squashfs_opendir: " +- "realloc failed!\n"); +- dir->dirs = new_dir; +- } +- dir->dirs[dir->dir_count].name = strdup(dire->name); +- dir->dirs[dir->dir_count].start_block = +- dirh.start_block; +- dir->dirs[dir->dir_count].offset = dire->offset; +- dir->dirs[dir->dir_count].type = dire->type; ++ ent = malloc(sizeof(struct dir_ent)); ++ if(ent == NULL) ++ MEM_ERROR(); ++ ++ ent->name = strdup(dire->name); ++ ent->start_block = dirh.start_block; ++ ent->offset = dire->offset; ++ ent->type = dire->type; ++ ent->next = NULL; ++ if(cur_ent == NULL) ++ dir->dirs = ent; ++ else ++ cur_ent->next = ent; ++ cur_ent = ent; + dir->dir_count ++; + bytes += dire->size + 1; + } +diff --git a/squashfs-tools/unsquashfs.c b/squashfs-tools/unsquashfs.c +index 04be53c..fee28ec 100644 +--- a/squashfs-tools/unsquashfs.c ++++ b/squashfs-tools/unsquashfs.c +@@ -1277,14 +1277,18 @@ failed: + int squashfs_readdir(struct dir *dir, char **name, unsigned int *start_block, + unsigned int *offset, unsigned int *type) + { +- if(dir->cur_entry == dir->dir_count) ++ if(dir->cur_entry == NULL) ++ dir->cur_entry = dir->dirs; ++ else ++ dir->cur_entry = dir->cur_entry->next; ++ ++ if(dir->cur_entry == NULL) + return FALSE; + +- *name = dir->dirs[dir->cur_entry].name; +- *start_block = dir->dirs[dir->cur_entry].start_block; +- *offset = dir->dirs[dir->cur_entry].offset; +- *type = dir->dirs[dir->cur_entry].type; +- dir->cur_entry ++; ++ *name = dir->cur_entry->name; ++ *start_block = dir->cur_entry->start_block; ++ *offset = dir->cur_entry->offset; ++ *type = dir->cur_entry->type; + + return TRUE; + } +diff --git a/squashfs-tools/unsquashfs.h b/squashfs-tools/unsquashfs.h +index 583fbe4..f8cf78c 100644 +--- a/squashfs-tools/unsquashfs.h ++++ b/squashfs-tools/unsquashfs.h +@@ -169,17 +169,18 @@ struct dir_ent { + unsigned int start_block; + unsigned int offset; + unsigned int type; ++ struct dir_ent *next; + }; + + struct dir { + int dir_count; +- int cur_entry; + unsigned int mode; + uid_t uid; + gid_t guid; + unsigned int mtime; + unsigned int xattr; + struct dir_ent *dirs; ++ struct dir_ent *cur_entry; + }; + + struct file_entry { +-- +2.17.1 + diff --git a/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072.patch b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072.patch new file mode 100644 index 0000000000..29ec3bbeab --- /dev/null +++ b/meta/recipes-devtools/squashfs-tools/files/CVE-2021-41072.patch @@ -0,0 +1,316 @@ +CVE: CVE-2021-41072 +Upstream-Status: Backport [https://github.com/plougher/squashfs-tools/commit/e048580] + +Backport commit to fix CVE-2021-41072. And squash a follow-up fix for +CVE-2021-41072 from upstream: +https://github.com/plougher/squashfs-tools/commit/19fcc93 + +Update context for version 4.4. + +Signed-off-by: Kai Kang <kai.kang@windriver.com> + +From e0485802ec72996c20026da320650d8362f555bd Mon Sep 17 00:00:00 2001 +From: Phillip Lougher <phillip@squashfs.org.uk> +Date: Sun, 12 Sep 2021 23:50:06 +0100 +Subject: [PATCH] Unsquashfs: additional write outside destination directory + exploit fix + +An issue on github (https://github.com/plougher/squashfs-tools/issues/72) +showed how some specially crafted Squashfs filesystems containing +invalid file names (with '/' and '..') can cause Unsquashfs to write +files outside of the destination directory. + +Since then it has been shown that specially crafted Squashfs filesystems +that contain a symbolic link pointing outside of the destination directory, +coupled with an identically named file within the same directory, can +cause Unsquashfs to write files outside of the destination directory. + +Specifically the symbolic link produces a pathname pointing outside +of the destination directory, which is then followed when writing the +duplicate identically named file within the directory. + +This commit fixes this exploit by explictly checking for duplicate +filenames within a directory. As directories in v2.1, v3.x, and v4.0 +filesystems are sorted, this is achieved by checking for consecutively +identical filenames. Additionally directories are checked to +ensure they are sorted, to avoid attempts to evade the duplicate +check. + +Version 1.x and 2.0 filesystems (where the directories were unsorted) +are sorted and then the above duplicate filename check is applied. + +Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> +--- + squashfs-tools/Makefile | 6 +- + squashfs-tools/unsquash-1.c | 6 ++ + squashfs-tools/unsquash-12.c | 110 +++++++++++++++++++++++++++++++++ + squashfs-tools/unsquash-1234.c | 21 +++++++ + squashfs-tools/unsquash-2.c | 16 +++++ + squashfs-tools/unsquash-3.c | 6 ++ + squashfs-tools/unsquash-4.c | 6 ++ + squashfs-tools/unsquashfs.h | 4 ++ + 8 files changed, 173 insertions(+), 2 deletions(-) + create mode 100644 squashfs-tools/unsquash-12.c + +diff --git a/squashfs-tools/Makefile b/squashfs-tools/Makefile +index 7262a2e..1b544ed 100755 +--- a/squashfs-tools/Makefile ++++ b/squashfs-tools/Makefile +@@ -156,8 +156,8 @@ MKSQUASHFS_OBJS = mksquashfs.o read_fs.o + caches-queues-lists.o + + UNSQUASHFS_OBJS = unsquashfs.o unsquash-1.o unsquash-2.o unsquash-3.o \ +- unsquash-4.o unsquash-123.o unsquash-34.o unsquash-1234.o swap.o \ +- compressor.o unsquashfs_info.o ++ unsquash-4.o unsquash-123.o unsquash-34.o unsquash-1234.o unsquash-12.o \ ++ swap.o compressor.o unsquashfs_info.o + + CFLAGS ?= -O2 + CFLAGS += $(EXTRA_CFLAGS) $(INCLUDEDIR) -D_FILE_OFFSET_BITS=64 \ +@@ -353,6 +353,8 @@ unsquash-34.o: unsquashfs.h unsquash-34.c unsquashfs_error.h + + unsquash-1234.o: unsquash-1234.c + ++unsquash-12.o: unsquash-12.c unsquashfs.h ++ + unsquashfs_xattr.o: unsquashfs_xattr.c unsquashfs.h squashfs_fs.h xattr.h + + unsquashfs_info.o: unsquashfs.h squashfs_fs.h +--- a/squashfs-tools/unsquash-1.c ++++ b/squashfs-tools/unsquash-1.c +@@ -314,6 +314,12 @@ static struct dir *squashfs_opendir(unsi + } + } + ++ /* check directory for duplicate names. Need to sort directory first */ ++ sort_directory(dir); ++ if(check_directory(dir) == FALSE) { ++ ERROR("File system corrupted: directory has duplicate names\n"); ++ goto corrupted; ++ } + return dir; + + corrupted: +diff --git a/squashfs-tools/unsquash-12.c b/squashfs-tools/unsquash-12.c +new file mode 100644 +index 0000000..61bf128 +--- /dev/null ++++ b/squashfs-tools/unsquash-12.c +@@ -0,0 +1,110 @@ ++/* ++ * Unsquash a squashfs filesystem. This is a highly compressed read only ++ * filesystem. ++ * ++ * Copyright (c) 2021 ++ * Phillip Lougher <phillip@squashfs.org.uk> ++ * ++ * This program is free software; you can redistribute it and/or ++ * modify it under the terms of the GNU General Public License ++ * as published by the Free Software Foundation; either version 2, ++ * or (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program; if not, write to the Free Software ++ * Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. ++ * ++ * unsquash-12.c ++ * ++ * Helper functions used by unsquash-1 and unsquash-2. ++ */ ++ ++#include "unsquashfs.h" ++ ++/* ++ * Bottom up linked list merge sort. ++ * ++ */ ++void sort_directory(struct dir *dir) ++{ ++ struct dir_ent *cur, *l1, *l2, *next; ++ int len1, len2, stride = 1; ++ ++ if(dir->dir_count < 2) ++ return; ++ ++ /* ++ * We can consider our linked-list to be made up of stride length ++ * sublists. Eacn iteration around this loop merges adjacent ++ * stride length sublists into larger 2*stride sublists. We stop ++ * when stride becomes equal to the entire list. ++ * ++ * Initially stride = 1 (by definition a sublist of 1 is sorted), and ++ * these 1 element sublists are merged into 2 element sublists, which ++ * are then merged into 4 element sublists and so on. ++ */ ++ do { ++ l2 = dir->dirs; /* head of current linked list */ ++ cur = NULL; /* empty output list */ ++ ++ /* ++ * Iterate through the linked list, merging adjacent sublists. ++ * On each interation l2 points to the next sublist pair to be ++ * merged (if there's only one sublist left this is simply added ++ * to the output list) ++ */ ++ while(l2) { ++ l1 = l2; ++ for(len1 = 0; l2 && len1 < stride; len1 ++, l2 = l2->next); ++ len2 = stride; ++ ++ /* ++ * l1 points to first sublist. ++ * l2 points to second sublist. ++ * Merge them onto the output list ++ */ ++ while(len1 && l2 && len2) { ++ if(strcmp(l1->name, l2->name) <= 0) { ++ next = l1; ++ l1 = l1->next; ++ len1 --; ++ } else { ++ next = l2; ++ l2 = l2->next; ++ len2 --; ++ } ++ ++ if(cur) { ++ cur->next = next; ++ cur = next; ++ } else ++ dir->dirs = cur = next; ++ } ++ /* ++ * One sublist is now empty, copy the other one onto the ++ * output list ++ */ ++ for(; len1; len1 --, l1 = l1->next) { ++ if(cur) { ++ cur->next = l1; ++ cur = l1; ++ } else ++ dir->dirs = cur = l1; ++ } ++ for(; l2 && len2; len2 --, l2 = l2->next) { ++ if(cur) { ++ cur->next = l2; ++ cur = l2; ++ } else ++ dir->dirs = cur = l2; ++ } ++ } ++ cur->next = NULL; ++ stride = stride << 1; ++ } while(stride < dir->dir_count); ++} +diff --git a/squashfs-tools/unsquash-1234.c b/squashfs-tools/unsquash-1234.c +index e389f8d..98a81ed 100644 +--- a/squashfs-tools/unsquash-1234.c ++++ b/squashfs-tools/unsquash-1234.c +@@ -72,3 +72,24 @@ void squashfs_closedir(struct dir *dir) + + free(dir); + } ++ ++ ++/* ++ * Check directory for duplicate names. As the directory should be sorted, ++ * duplicates will be consecutive. Obviously we also need to check if the ++ * directory has been deliberately unsorted, to evade this check. ++ */ ++int check_directory(struct dir *dir) ++{ ++ int i; ++ struct dir_ent *ent; ++ ++ if(dir->dir_count < 2) ++ return TRUE; ++ ++ for(ent = dir->dirs, i = 0; i < dir->dir_count - 1; ent = ent->next, i++) ++ if(strcmp(ent->name, ent->next->name) >= 0) ++ return FALSE; ++ ++ return TRUE; ++} +diff --git a/squashfs-tools/unsquash-2.c b/squashfs-tools/unsquash-2.c +index 956f96f..0e36f7d 100644 +--- a/squashfs-tools/unsquash-2.c ++++ b/squashfs-tools/unsquash-2.c +@@ -29,6 +29,7 @@ static squashfs_fragment_entry_2 *fragme + static unsigned int *uid_table, *guid_table; + static char *inode_table, *directory_table; + static squashfs_operations ops; ++static int needs_sorting = FALSE; + + static void read_block_list(unsigned int *block_list, char *block_ptr, int blocks) + { +@@ -415,6 +416,17 @@ static struct dir *squashfs_opendir(unsi + } + } + ++ if(needs_sorting) ++ sort_directory(dir); ++ ++ /* check directory for duplicate names and sorting */ ++ if(check_directory(dir) == FALSE) { ++ if(needs_sorting) ++ ERROR("File system corrupted: directory has duplicate names\n"); ++ else ++ ERROR("File system corrupted: directory has duplicate names or is unsorted\n"); ++ goto corrupted; ++ } + return dir; + + corrupted: +--- a/squashfs-tools/unsquash-3.c ++++ b/squashfs-tools/unsquash-3.c +@@ -442,6 +442,12 @@ static struct dir *squashfs_opendir(unsi + } + } + ++ /* check directory for duplicate names and sorting */ ++ if(check_directory(dir) == FALSE) { ++ ERROR("File system corrupted: directory has duplicate names or is unsorted\n"); ++ goto corrupted; ++ } ++ + return dir; + + corrupted: +diff --git a/squashfs-tools/unsquash-4.c b/squashfs-tools/unsquash-4.c +index 694783d..c615bb8 100644 +--- a/squashfs-tools/unsquash-4.c ++++ b/squashfs-tools/unsquash-4.c +@@ -378,6 +378,12 @@ static struct dir *squashfs_opendir(unsi + } + } + ++ /* check directory for duplicate names and sorting */ ++ if(check_directory(dir) == FALSE) { ++ ERROR("File system corrupted: directory has duplicate names or is unsorted\n"); ++ goto corrupted; ++ } ++ + return dir; + + corrupted: +diff --git a/squashfs-tools/unsquashfs.h b/squashfs-tools/unsquashfs.h +index f8cf78c..bf2a80d 100644 +--- a/squashfs-tools/unsquashfs.h ++++ b/squashfs-tools/unsquashfs.h +@@ -266,4 +266,8 @@ extern long long *alloc_index_table(int) + /* unsquash-1234.c */ + extern int check_name(char *, int); + extern void squashfs_closedir(struct dir *); ++extern int check_directory(struct dir *); ++ ++/* unsquash-12.c */ ++extern void sort_directory(struct dir *); + #endif +-- +2.17.1 + diff --git a/meta/recipes-devtools/squashfs-tools/squashfs-tools_git.bb b/meta/recipes-devtools/squashfs-tools/squashfs-tools_git.bb index 5d754b20b3..caa5417ed0 100644 --- a/meta/recipes-devtools/squashfs-tools/squashfs-tools_git.bb +++ b/meta/recipes-devtools/squashfs-tools/squashfs-tools_git.bb @@ -12,6 +12,10 @@ SRCREV = "52eb4c279cd283ed9802dd1ceb686560b22ffb67" SRC_URI = "git://github.com/plougher/squashfs-tools.git;protocol=https;branch=master \ file://0001-squashfs-tools-fix-build-failure-against-gcc-10.patch;striplevel=2 \ file://CVE-2021-40153.patch;striplevel=2 \ + file://CVE-2021-41072-requisite-1.patch;striplevel=2 \ + file://CVE-2021-41072-requisite-2.patch;striplevel=2 \ + file://CVE-2021-41072-requisite-3.patch;striplevel=2 \ + file://CVE-2021-41072.patch;striplevel=2 \ " S = "${WORKDIR}/git/squashfs-tools" diff --git a/meta/recipes-devtools/unfs3/unfs3_git.bb b/meta/recipes-devtools/unfs3/unfs3_git.bb index bcaa4e2822..06148005cf 100644 --- a/meta/recipes-devtools/unfs3/unfs3_git.bb +++ b/meta/recipes-devtools/unfs3/unfs3_git.bb @@ -37,7 +37,7 @@ BBCLASSEXTEND = "native nativesdk" inherit autotools EXTRA_OECONF_append_class-native = " --sbindir=${bindir}" CFLAGS_append = " -I${STAGING_INCDIR}/tirpc" -LDFLAGS_append = " -ltirpc" +EXTRA_OECONF_append = " LIBS=-ltirpc" # Turn off these header detects else the inode search # will walk entire file systems and this is a real problem |