[PATCH] D41423: [Lex] Avoid out-of-bounds dereference in LexAngledStringLiteral.

[Volodymyr Sapsai via Phabricator via cfe-commits]

vsapsai created this revision.
vsapsai added reviewers: arphaman, kcc.

Fix makes the loop in LexAngledStringLiteral more like the loops in
LexStringLiteral, LexCharConstant. When we skip a character after
backslash, we need to check if we reached the end of the file instead of
reading the next character unconditionally.

Discovered by OSS-Fuzz:
https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=3832

rdar://problem/35572754


https://reviews.llvm.org/D41423

Files:
  clang/lib/Lex/Lexer.cpp
  clang/unittests/Lex/LexerTest.cpp


Index: clang/unittests/Lex/LexerTest.cpp
===================================================================
--- clang/unittests/Lex/LexerTest.cpp
+++ clang/unittests/Lex/LexerTest.cpp
@@ -474,8 +474,10 @@
 }
 
 TEST_F(LexerTest, AvoidPastEndOfStringDereference) {
-  std::vector<Token> LexedTokens = Lex("  //  \\\n");
-  EXPECT_TRUE(LexedTokens.empty());
+  EXPECT_TRUE(Lex("  //  \\\n").empty());
+  // rdar://problem/35572754
+  EXPECT_TRUE(Lex("#include <\\\\").empty());
+  EXPECT_TRUE(Lex("#include <\\\\\n").empty());
 }
 
 TEST_F(LexerTest, StringizingRasString) {
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -2009,18 +2009,21 @@
   const char *AfterLessPos = CurPtr;
   char C = getAndAdvanceChar(CurPtr, Result);
   while (C != '>') {
-    // Skip escaped characters.
-    if (C == '\\' && CurPtr < BufferEnd) {
-      // Skip the escaped character.
-      getAndAdvanceChar(CurPtr, Result);
-    } else if (C == '\n' || C == '\r' ||             // Newline.
-               (C == 0 && (CurPtr-1 == BufferEnd ||  // End of file.
-                           isCodeCompletionPoint(CurPtr-1)))) {
+    // Skip escaped characters.  Escaped newlines will already be processed by
+    // getAndAdvanceChar.
+    if (C == '\\')
+      C = getAndAdvanceChar(CurPtr, Result);
+
+    if (C == '\n' || C == '\r' ||             // Newline.
+        (C == 0 && (CurPtr-1 == BufferEnd ||  // End of file.
+                    isCodeCompletionPoint(CurPtr-1)))) {
       // If the filename is unterminated, then it must just be a lone <
       // character.  Return this as such.
       FormTokenWithChars(Result, AfterLessPos, tok::less);
       return true;
-    } else if (C == 0) {
+    }
+
+    if (C == 0) {
       NulCharacter = CurPtr-1;
     }
     C = getAndAdvanceChar(CurPtr, Result);



Index: clang/unittests/Lex/LexerTest.cpp
===================================================================
--- clang/unittests/Lex/LexerTest.cpp
+++ clang/unittests/Lex/LexerTest.cpp
@@ -474,8 +474,10 @@
 }
 
 TEST_F(LexerTest, AvoidPastEndOfStringDereference) {
-  std::vector<Token> LexedTokens = Lex("  //  \\\n");
-  EXPECT_TRUE(LexedTokens.empty());
+  EXPECT_TRUE(Lex("  //  \\\n").empty());
+  // rdar://problem/35572754
+  EXPECT_TRUE(Lex("#include <\\\\").empty());
+  EXPECT_TRUE(Lex("#include <\\\\\n").empty());
 }
 
 TEST_F(LexerTest, StringizingRasString) {
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -2009,18 +2009,21 @@
   const char *AfterLessPos = CurPtr;
   char C = getAndAdvanceChar(CurPtr, Result);
   while (C != '>') {
-    // Skip escaped characters.
-    if (C == '\\' && CurPtr < BufferEnd) {
-      // Skip the escaped character.
-      getAndAdvanceChar(CurPtr, Result);
-    } else if (C == '\n' || C == '\r' ||             // Newline.
-               (C == 0 && (CurPtr-1 == BufferEnd ||  // End of file.
-                           isCodeCompletionPoint(CurPtr-1)))) {
+    // Skip escaped characters.  Escaped newlines will already be processed by
+    // getAndAdvanceChar.
+    if (C == '\\')
+      C = getAndAdvanceChar(CurPtr, Result);
+
+    if (C == '\n' || C == '\r' ||             // Newline.
+        (C == 0 && (CurPtr-1 == BufferEnd ||  // End of file.
+                    isCodeCompletionPoint(CurPtr-1)))) {
       // If the filename is unterminated, then it must just be a lone <
       // character.  Return this as such.
       FormTokenWithChars(Result, AfterLessPos, tok::less);
       return true;
-    } else if (C == 0) {
+    }
+
+    if (C == 0) {
       NulCharacter = CurPtr-1;
     }
     C = getAndAdvanceChar(CurPtr, Result);

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits