From 85cd3d98686c47d015dbcc17f1f7d0714b00e172 Mon Sep 17 00:00:00 2001 From: Richard Smith Date: Wed, 13 Aug 2025 12:39:25 -0700 Subject: Work around documented Linux mmap bug. (#152595) On Linux, mmap doesn't always zero-fill slack bytes ([man page]), despite being required to do so by POSIX. If the final page of a file is in the page cache and the bytes past the end of the file get overwritten by some process, those bytes then remain non-zero until the page falls out of the cache or another process overwrites them. Stop trusting that mmap behaves properly and instead check whether the buffer was indeed properly terminated. If not, fall back to using `read` to read the file contents. This fixes an obscure clang crash bug that can occur if another program (such as an editor) mmap's a source file and writes past the end of the mmap'd region shortly before clang or clangd attempts to parse the file. [man page]: https://man7.org/linux/man-pages/man2/mmap.2.html#BUGS --- llvm/lib/Support/MemoryBuffer.cpp | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'llvm/lib') diff --git a/llvm/lib/Support/MemoryBuffer.cpp b/llvm/lib/Support/MemoryBuffer.cpp index 601f11f..1c4645a 100644 --- a/llvm/lib/Support/MemoryBuffer.cpp +++ b/llvm/lib/Support/MemoryBuffer.cpp @@ -501,8 +501,14 @@ getOpenFileImpl(sys::fs::file_t FD, const Twine &Filename, uint64_t FileSize, std::unique_ptr Result( new (NamedBufferAlloc(Filename)) MemoryBufferMMapFile( RequiresNullTerminator, FD, MapSize, Offset, EC)); - if (!EC) - return std::move(Result); + if (!EC) { + // On at least Linux, and possibly on other systems, mmap may return pages + // from the page cache that are not properly filled with trailing zeroes, + // if some prior user of the page wrote non-zero bytes. Detect this and + // don't use mmap in that case. + if (!RequiresNullTerminator || *Result->getBufferEnd() == '\0') + return std::move(Result); + } } #ifdef __MVS__ -- cgit v1.1