Author: Aaron Ballman Date: 2024-08-08T07:32:39-04:00 New Revision: 8f0c865d1024a9ff7f3f1b0d3e47a6c9f5f672c2
URL: https://github.com/llvm/llvm-project/commit/8f0c865d1024a9ff7f3f1b0d3e47a6c9f5f672c2 DIFF: https://github.com/llvm/llvm-project/commit/8f0c865d1024a9ff7f3f1b0d3e47a6c9f5f672c2.diff LOG: Fix a crash with empty escape sequences when lexing (#102339) The utilities we use for lexing string and character literals can be run in a mode where we pass a null pointer for the diagnostics engine. This mode is used by the format string checkers, for example. However, there were two places that failed to account for a null diagnostic engine pointer: `\o{}` and `\x{}`. This patch adds a check for a null pointer and correctly handles fallback behavior. Fixes #102218 Added: Modified: clang/docs/ReleaseNotes.rst clang/lib/Lex/LiteralSupport.cpp clang/test/Lexer/char-escapes-delimited.c Removed: ################################################################################ diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index ffdb5f8f5af3ed..a355b8db11faf0 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -175,6 +175,8 @@ Bug Fixes in This Version be used in C++. - Fixed a failed assertion when checking required literal types in C context. (#GH101304). - Fixed a crash when trying to transform a dependent address space type. Fixes #GH101685. +- Fixed a crash when diagnosing format strings and encountering an empty + delimited escape sequence (e.g., ``"\o{}"``). #GH102218 Bug Fixes to Compiler Builtins ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/clang/lib/Lex/LiteralSupport.cpp b/clang/lib/Lex/LiteralSupport.cpp index 9d2720af5dbd92..225a6c2d15baaa 100644 --- a/clang/lib/Lex/LiteralSupport.cpp +++ b/clang/lib/Lex/LiteralSupport.cpp @@ -190,9 +190,10 @@ static unsigned ProcessCharEscape(const char *ThisTokBegin, Delimited = true; ThisTokBuf++; if (*ThisTokBuf == '}') { - Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf, - diag::err_delimited_escape_empty); - return ResultChar; + HadError = true; + if (Diags) + Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf, + diag::err_delimited_escape_empty); } } else if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) { if (Diags) @@ -283,9 +284,10 @@ static unsigned ProcessCharEscape(const char *ThisTokBegin, Delimited = true; ++ThisTokBuf; if (*ThisTokBuf == '}') { - Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf, - diag::err_delimited_escape_empty); - return ResultChar; + HadError = true; + if (Diags) + Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf, + diag::err_delimited_escape_empty); } while (ThisTokBuf != ThisTokEnd) { diff --git a/clang/test/Lexer/char-escapes-delimited.c b/clang/test/Lexer/char-escapes-delimited.c index 5327ef700b0e25..7a8986bc5f8679 100644 --- a/clang/test/Lexer/char-escapes-delimited.c +++ b/clang/test/Lexer/char-escapes-delimited.c @@ -123,3 +123,16 @@ void separators(void) { static_assert('\N??<DOLLAR SIGN??>' == '$'); // expected-warning 2{{trigraph converted}} \ // ext-warning {{extension}} cxx23-warning {{C++23}} #endif + +void GH102218(void) { + // The format specifier checking code runs the lexer with diagnostics + // disabled. This used to crash Clang for malformed \o and \x because the + // lexer missed a null pointer check for the diagnostics engine in that case. + extern int printf(const char *, ...); + printf("\o{}"); // expected-error {{delimited escape sequence cannot be empty}} + printf("\x{}"); // expected-error {{delimited escape sequence cannot be empty}} + + // These cases always worked but are here for completeness. + printf("\u{}"); // expected-error {{delimited escape sequence cannot be empty}} + printf("\N{}"); // expected-error {{delimited escape sequence cannot be empty}} +} _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
