Index: llvm/include/llvm/Object/ELF.h =================================================================== --- llvm/include/llvm/Object/ELF.h +++ llvm/include/llvm/Object/ELF.h @@ -1237,15 +1237,12 @@ /// Name of the API remains consistent as specified in the libelf /// REF : http://www.sco.com/developers/gabi/latest/ch5.dynamic.html#hash inline unsigned hashSysV(StringRef SymbolName) { - unsigned h = 0, g; - for (char C : SymbolName) { - h = (h << 4) + C; - g = h & 0xf0000000L; - if (g != 0) - h ^= g >> 24; - h &= ~g; + uint32_t H = 0; + for (uint8_t C : SymbolName) { + H = (H << 4) + C; + H ^= (H >> 24) & 0xf0; } - return h; + return H & 0xfffffff; } /// This function returns the hash value for a symbol in the .dynsym section Index: llvm/unittests/Object/ELFTest.cpp =================================================================== --- llvm/unittests/Object/ELFTest.cpp +++ llvm/unittests/Object/ELFTest.cpp @@ -271,3 +271,19 @@ EXPECT_THAT_ERROR(Region[3].takeError(), FailedWithMessage(ErrMsg2)); EXPECT_THAT_ERROR(Region[4].takeError(), FailedWithMessage(ErrMsg2)); } + +// Test the sysV and the gnu hash functions, particularly with utf8 unicode +TEST(ELFTest, Hash) { + // Symbols long enough to have feedback, we have to explicitly encode the utf8 + // to avoid encoding transliterations. + EXPECT_EQ(hashSysV("FooBarBazToto"), 0x5ec3e8fU); + EXPECT_EQ(hashGnu("FooBarBazToto"), 0x5478be61U); + // boom💥pants + EXPECT_EQ(hashSysV("boom\xf0\x9f\x92\xa5pants"), 0x5a0cf53U); + EXPECT_EQ(hashGnu("boom\xf0\x9f\x92\xa5pants"), 0xf5dda2deU); + // woot!🧙 💑 🌈 + EXPECT_EQ(hashSysV("woot!\xf0\x9f\xa7\x99 \xf0\x9f\x92\x91 " + "\xf0\x9f\x8c\x88"), 0x3522e38U); + EXPECT_EQ(hashGnu("woot!\xf0\x9f\xa7\x99 \xf0\x9f\x92\x91 " + "\xf0\x9f\x8c\x88"), 0xf7603f3U); +}