From 9613c86f0427be88ee43bddb7ae7cde74c1157ac Mon Sep 17 00:00:00 2001
From: serge-sans-paille <sguelton@redhat.com>
Date: Thu, 4 Nov 2021 11:11:53 +0100
Subject: [PATCH 2/3] Misleading bidirectional detection
Differential Revision: https://reviews.llvm.org/D112913
---
clang-tools-extra/clang-tidy/misc/CMakeLists.txt | 1 +
.../clang-tidy/misc/MiscTidyModule.cpp | 3 +
.../clang-tidy/misc/MisleadingBidirectional.cpp | 131 +++++++++++++++++++++
.../clang-tidy/misc/MisleadingBidirectional.h | 38 ++++++
clang-tools-extra/docs/ReleaseNotes.rst | 5 +
clang-tools-extra/docs/clang-tidy/checks/list.rst | 3 +-
.../checks/misc-misleading-bidirectional.rst | 21 ++++
.../checkers/misc-misleading-bidirectional.cpp | 31 +++++
8 files changed, 232 insertions(+), 1 deletion(-)
create mode 100644 clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.cpp
create mode 100644 clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.h
create mode 100644 clang-tools-extra/docs/clang-tidy/checks/misc-misleading-bidirectional.rst
create mode 100644 clang-tools-extra/test/clang-tidy/checkers/misc-misleading-bidirectional.cpp
diff --git a/clang-tools-extra/clang-tidy/misc/CMakeLists.txt b/clang-tools-extra/clang-tidy/misc/CMakeLists.txt
index d438a47..d6bb718 100644
--- a/clang-tools-extra/clang-tidy/misc/CMakeLists.txt
+++ b/clang-tools-extra/clang-tidy/misc/CMakeLists.txt
@@ -11,6 +11,7 @@ add_clang_library(clangTidyMiscModule
DefinitionsInHeadersCheck.cpp
Homoglyph.cpp
MiscTidyModule.cpp
+ MisleadingBidirectional.cpp
MisplacedConstCheck.cpp
NewDeleteOverloadsCheck.cpp
NoRecursionCheck.cpp
diff --git a/clang-tools-extra/clang-tidy/misc/MiscTidyModule.cpp b/clang-tools-extra/clang-tidy/misc/MiscTidyModule.cpp
index 5c7bd0c..bb5fde2 100644
--- a/clang-tools-extra/clang-tidy/misc/MiscTidyModule.cpp
+++ b/clang-tools-extra/clang-tidy/misc/MiscTidyModule.cpp
@@ -11,6 +11,7 @@
#include "../ClangTidyModuleRegistry.h"
#include "DefinitionsInHeadersCheck.h"
#include "Homoglyph.h"
+#include "MisleadingBidirectional.h"
#include "MisplacedConstCheck.h"
#include "NewDeleteOverloadsCheck.h"
#include "NoRecursionCheck.h"
@@ -35,6 +36,8 @@ public:
CheckFactories.registerCheck<DefinitionsInHeadersCheck>(
"misc-definitions-in-headers");
CheckFactories.registerCheck<Homoglyph>("misc-homoglyph");
+ CheckFactories.registerCheck<MisleadingBidirectionalCheck>(
+ "misc-misleading-bidirectional");
CheckFactories.registerCheck<MisplacedConstCheck>("misc-misplaced-const");
CheckFactories.registerCheck<NewDeleteOverloadsCheck>(
"misc-new-delete-overloads");
diff --git a/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.cpp b/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.cpp
new file mode 100644
index 0000000..7a2f06b
--- /dev/null
+++ b/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.cpp
@@ -0,0 +1,131 @@
+//===--- MisleadingBidirectional.cpp - clang-tidy -------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "MisleadingBidirectional.h"
+
+#include "clang/Frontend/CompilerInstance.h"
+#include "clang/Lex/Preprocessor.h"
+#include "llvm/Support/ConvertUTF.h"
+
+using namespace clang;
+
+static bool containsMisleadingBidi(StringRef Buffer,
+ bool HonorLineBreaks = true) {
+ const char *CurPtr = Buffer.begin();
+ unsigned EmbeddingOverride = 0, Isolate = 0;
+ unsigned i = 0;
+
+ enum {
+ LS = 0x2028,
+ PS = 0x2029,
+ RLO = 0x202E,
+ RLE = 0x202B,
+ LRO = 0x202D,
+ LRE = 0x202A,
+ PDF = 0x202C,
+ RLI = 0x2067,
+ LRI = 0x2066,
+ FSI = 0x2068,
+ PDI = 0x2069
+ };
+
+ // Scan each character while maintaining a count of opened bidi context.
+ // RLO/RLE/LRO/LRE all are closed by PDF while RLI LRI and FSI are closed by
+ // PDI. New lines reset the context count. Extra PDF / PDI are ignored.
+ //
+ // Warn if we end up with an unclosed context.
+ while (CurPtr < Buffer.end()) {
+ ++i;
+ unsigned char C = *CurPtr;
+ if (isASCII(C)) {
+ ++CurPtr;
+ // Line break: https://www.unicode.org/reports/tr14/tr14-32.html
+ if (C == '\n' || C == '\r' || C == '\f' || C == '\v' ||
+ C == 0x85 /*next line*/)
+ EmbeddingOverride = Isolate = 0;
+ continue;
+ }
+ llvm::UTF32 CodePoint;
+ llvm::ConversionResult Result = llvm::convertUTF8Sequence(
+ (const llvm::UTF8 **)&CurPtr, (const llvm::UTF8 *)Buffer.end(),
+ &CodePoint, llvm::strictConversion);
+
+ // If conversion fails, utf-8 is designed so that we can just try next char.
+ if (Result != llvm::conversionOK) {
+ ++CurPtr;
+ continue;
+ }
+
+ if (CodePoint == RLO || CodePoint == RLE || CodePoint == LRO ||
+ CodePoint == LRE)
+ EmbeddingOverride += 1;
+ else if (CodePoint == PDF)
+ EmbeddingOverride = std::min(EmbeddingOverride - 1, EmbeddingOverride);
+ else if (CodePoint == RLI || CodePoint == LRI || CodePoint == FSI)
+ Isolate += 1;
+ else if (CodePoint == PDI)
+ Isolate = std::min(Isolate - 1, Isolate);
+ // Line break: https://www.unicode.org/reports/tr14/tr14-32.html
+ else if (CodePoint == LS || CodePoint == PS)
+ EmbeddingOverride = Isolate = 0;
+ }
+ return EmbeddingOverride != 0 || Isolate != 0;
+}
+
+class clang::tidy::misc::MisleadingBidirectionalCheck::
+ MisleadingBidirectionalHandler : public CommentHandler {
+public:
+ MisleadingBidirectionalHandler(MisleadingBidirectionalCheck &Check,
+ llvm::Optional<std::string> User)
+ : Check(Check) {}
+
+ bool HandleComment(Preprocessor &PP, SourceRange Range) override {
+ // FIXME: check that we are in a /* */ comment
+ StringRef Text =
+ Lexer::getSourceText(CharSourceRange::getCharRange(Range),
+ PP.getSourceManager(), PP.getLangOpts());
+
+ if (containsMisleadingBidi(Text, true))
+ Check.diag(
+ Range.getBegin(),
+ "comment contains misleading bidirectional Unicode characters");
+ return false;
+ }
+
+private:
+ MisleadingBidirectionalCheck &Check;
+};
+
+clang::tidy::misc::MisleadingBidirectionalCheck::MisleadingBidirectionalCheck(
+ StringRef Name, ClangTidyContext *Context)
+ : ClangTidyCheck(Name, Context),
+ Handler(std::make_unique<MisleadingBidirectionalHandler>(
+ *this, Context->getOptions().User)) {}
+
+clang::tidy::misc::MisleadingBidirectionalCheck::
+ ~MisleadingBidirectionalCheck() = default;
+
+void clang::tidy::misc::MisleadingBidirectionalCheck::registerPPCallbacks(
+ const SourceManager &SM, Preprocessor *PP, Preprocessor *ModuleExpanderPP) {
+ PP->addCommentHandler(Handler.get());
+}
+
+void clang::tidy::misc::MisleadingBidirectionalCheck::check(
+ const ast_matchers::MatchFinder::MatchResult &Result) {
+ if (const auto *SL = Result.Nodes.getNodeAs<StringLiteral>("strlit")) {
+ StringRef Literal = SL->getBytes();
+ if (containsMisleadingBidi(Literal, false))
+ diag(SL->getBeginLoc(), "string literal contains misleading "
+ "bidirectional Unicode characters");
+ }
+}
+
+void clang::tidy::misc::MisleadingBidirectionalCheck::registerMatchers(
+ ast_matchers::MatchFinder *Finder) {
+ Finder->addMatcher(ast_matchers::stringLiteral().bind("strlit"), this);
+}
diff --git a/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.h b/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.h
new file mode 100644
index 0000000..18e7060
--- /dev/null
+++ b/clang-tools-extra/clang-tidy/misc/MisleadingBidirectional.h
@@ -0,0 +1,38 @@
+//===--- MisleadingBidirectionalCheck.h - clang-tidy ------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MISC_MISLEADINGBIDIRECTIONALCHECK_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MISC_MISLEADINGBIDIRECTIONALCHECK_H
+
+#include "../ClangTidyCheck.h"
+
+namespace clang {
+namespace tidy {
+namespace misc {
+
+class MisleadingBidirectionalCheck : public ClangTidyCheck {
+public:
+ MisleadingBidirectionalCheck(StringRef Name, ClangTidyContext *Context);
+ ~MisleadingBidirectionalCheck();
+
+ void registerPPCallbacks(const SourceManager &SM, Preprocessor *PP,
+ Preprocessor *ModuleExpanderPP) override;
+
+ void registerMatchers(ast_matchers::MatchFinder *Finder) override;
+ void check(const ast_matchers::MatchFinder::MatchResult &Result) override;
+
+private:
+ class MisleadingBidirectionalHandler;
+ std::unique_ptr<MisleadingBidirectionalHandler> Handler;
+};
+
+} // namespace misc
+} // namespace tidy
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANG_TIDY_MISC_MISLEADINGBIDIRECTIONALCHECK_H
diff --git a/clang-tools-extra/docs/ReleaseNotes.rst b/clang-tools-extra/docs/ReleaseNotes.rst
index e4ad7b9..546d544 100644
--- a/clang-tools-extra/docs/ReleaseNotes.rst
+++ b/clang-tools-extra/docs/ReleaseNotes.rst
@@ -326,6 +326,11 @@ New checks
Detects confusable unicode identifiers.
+- New :doc:`misc-misleading-bidirectional <clang-tidy/checks/misc-misleading-bidirectional>` check.
+
+ Inspect string literal and comments for unterminated bidirectional Unicode
+ characters.
+
New check aliases
^^^^^^^^^^^^^^^^^
diff --git a/clang-tools-extra/docs/clang-tidy/checks/list.rst b/clang-tools-extra/docs/clang-tidy/checks/list.rst
index 47ff5b7..977867d 100644
--- a/clang-tools-extra/docs/clang-tidy/checks/list.rst
+++ b/clang-tools-extra/docs/clang-tidy/checks/list.rst
@@ -202,7 +202,8 @@ Clang-Tidy Checks
`llvmlibc-implementation-in-namespace <llvmlibc-implementation-in-namespace.html>`_,
`llvmlibc-restrict-system-libc-headers <llvmlibc-restrict-system-libc-headers.html>`_, "Yes"
`misc-definitions-in-headers <misc-definitions-in-headers.html>`_, "Yes"
- `misc-homoglyph <misc-homoglyph.html>`_, "Yes"
+ `misc-homoglyph <misc-homoglyph.html>`_,
+ `misc-misleading-bidirectional <misc-misleading-bidirectional.html>`_,
`misc-misplaced-const <misc-misplaced-const.html>`_,
`misc-new-delete-overloads <misc-new-delete-overloads.html>`_,
`misc-no-recursion <misc-no-recursion.html>`_,
diff --git a/clang-tools-extra/docs/clang-tidy/checks/misc-misleading-bidirectional.rst b/clang-tools-extra/docs/clang-tidy/checks/misc-misleading-bidirectional.rst
new file mode 100644
index 0000000..16ffc97
--- /dev/null
+++ b/clang-tools-extra/docs/clang-tidy/checks/misc-misleading-bidirectional.rst
@@ -0,0 +1,21 @@
+.. title:: clang-tidy - misc-misleading-bidirectional
+
+misc-misleading-bidirectional
+=============================
+
+Warn about unterminated bidirectional unicode sequence, detecting potential attack
+as described in the `Trojan Source <https://www.trojansource.codes>`_ attack.
+
+Example:
+
+.. code-block:: c++
+
+ #include <iostream>
+
+ int main() {
+ bool isAdmin = false;
+ /* } if (isAdmin) begin admins only */
+ std::cout << "You are an admin.\n";
+ /* end admins only { */
+ return 0;
+ }
diff --git a/clang-tools-extra/test/clang-tidy/checkers/misc-misleading-bidirectional.cpp b/clang-tools-extra/test/clang-tidy/checkers/misc-misleading-bidirectional.cpp
new file mode 100644
index 0000000..12fdf63
--- /dev/null
+++ b/clang-tools-extra/test/clang-tidy/checkers/misc-misleading-bidirectional.cpp
@@ -0,0 +1,31 @@
+// RUN: %check_clang_tidy %s misc-misleading-bidirectional %t
+
+void func(void) {
+ int admin = 0;
+ /* }if(admin) begin*/
+ // CHECK-MESSAGES: :[[@LINE-1]]:3: warning: comment contains misleading bidirectional Unicode characters [misc-misleading-bidirectional]
+ const char msg[] = "if(admin) tes";
+ // CHECK-MESSAGES: :[[@LINE-1]]:22: warning: string literal contains misleading bidirectional Unicode characters [misc-misleading-bidirectional]
+}
+
+void all_fine(void) {
+ char valid[] = "somevalidsequence";
+ /* EOL ends bidi sequence
+ * end it's fine to do so.
+ * EOL ends isolate too
+ */
+}
+
+int invalid_utf_8(void) {
+ bool isAdmin = false;
+
+ // the comment below contains an invalid utf8 character, but should still be
+ // processed.
+
+ // CHECK-MESSAGES: :[[@LINE+1]]:3: warning: comment contains misleading bidirectional Unicode characters [misc-misleading-bidirectional]
+ /* } if (isAdmin) begin admins only */
+ return 1;
+ /* end admins only { */
+ // CHECK-MESSAGES: :[[@LINE-1]]:3: warning: comment contains misleading bidirectional Unicode characters [misc-misleading-bidirectional]
+ return 0;
+}
--
1.8.3.1