diff --git a/clang-tools-extra/clangd/index/Serialization.cpp b/clang-tools-extra/clangd/index/Serialization.cpp --- a/clang-tools-extra/clangd/index/Serialization.cpp +++ b/clang-tools-extra/clangd/index/Serialization.cpp @@ -21,6 +21,7 @@ #include "llvm/Support/Endian.h" #include "llvm/Support/Error.h" #include "llvm/Support/raw_ostream.h" +#include #include namespace clang { @@ -81,12 +82,17 @@ uint32_t consumeVar() { constexpr static uint8_t More = 1 << 7; - uint8_t B = consume8(); + + // Use a 32 bit unsigned here to prevent promotion to signed int (unless int + // is wider than 32 bits). + uint32_t B = consume8(); if (LLVM_LIKELY(!(B & More))) return B; uint32_t Val = B & ~More; for (int Shift = 7; B & More && Shift < 32; Shift += 7) { B = consume8(); + // 5th byte of a varint can only have lowest 4 bits set. + assert((Shift != 28 || B == (B & 0x0f)) && "Invalid varint encoding"); Val |= (B & ~More) << Shift; } return Val; diff --git a/clang-tools-extra/clangd/unittests/SerializationTests.cpp b/clang-tools-extra/clangd/unittests/SerializationTests.cpp --- a/clang-tools-extra/clangd/unittests/SerializationTests.cpp +++ b/clang-tools-extra/clangd/unittests/SerializationTests.cpp @@ -366,9 +366,9 @@ Pos += FileDigest.size(); // Varints are little-endian base-128 numbers, where the top-bit of each byte - // indicates whether there are more. 8fffffff7f -> 0xffffffff. + // indicates whether there are more. ffffffff0f -> 0xffffffff. std::string CorruptSrcs = - (Srcs->Data.take_front(Pos) + llvm::fromHex("8fffffff7f") + + (Srcs->Data.take_front(Pos) + llvm::fromHex("ffffffff0f") + "some_random_garbage") .str(); Srcs->Data = CorruptSrcs;