diff --git a/bolt/lib/Core/DebugData.cpp b/bolt/lib/Core/DebugData.cpp --- a/bolt/lib/Core/DebugData.cpp +++ b/bolt/lib/Core/DebugData.cpp @@ -820,7 +820,8 @@ auto hashAndAddAbbrev = [&](StringRef AbbrevData) -> bool { llvm::SHA1 Hasher; Hasher.update(AbbrevData); - StringRef Key = Hasher.final(); + auto Hash = Hasher.final(); + StringRef Key((const char *)Hash.data(), Hash.size()); auto Iter = AbbrevDataCache.find(Key); if (Iter != AbbrevDataCache.end()) { UnitsAbbrevData[&Unit] = Iter->second.get(); diff --git a/clang/include/clang/Basic/Module.h b/clang/include/clang/Basic/Module.h --- a/clang/include/clang/Basic/Module.h +++ b/clang/include/clang/Basic/Module.h @@ -71,8 +71,8 @@ return Value; } - static ASTFileSignature create(StringRef Bytes) { - return create(Bytes.bytes_begin(), Bytes.bytes_end()); + static ASTFileSignature create(std::array Bytes) { + return ASTFileSignature(std::move(Bytes)); } static ASTFileSignature createDISentinel() { diff --git a/clang/lib/Serialization/ASTWriter.cpp b/clang/lib/Serialization/ASTWriter.cpp --- a/clang/lib/Serialization/ASTWriter.cpp +++ b/clang/lib/Serialization/ASTWriter.cpp @@ -1117,8 +1117,7 @@ ASTWriter::createSignature(StringRef AllBytes, StringRef ASTBlockBytes) { llvm::SHA1 Hasher; Hasher.update(ASTBlockBytes); - auto Hash = Hasher.result(); - ASTFileSignature ASTBlockHash = ASTFileSignature::create(Hash); + ASTFileSignature ASTBlockHash = ASTFileSignature::create(Hasher.result()); // Add the remaining bytes (i.e. bytes before the unhashed control block that // are not part of the AST block). @@ -1126,8 +1125,7 @@ AllBytes.take_front(ASTBlockBytes.bytes_end() - AllBytes.bytes_begin())); Hasher.update( AllBytes.take_back(AllBytes.bytes_end() - ASTBlockBytes.bytes_end())); - Hash = Hasher.result(); - ASTFileSignature Signature = ASTFileSignature::create(Hash); + ASTFileSignature Signature = ASTFileSignature::create(Hasher.result()); return std::make_pair(ASTBlockHash, Signature); } diff --git a/lld/ELF/Writer.cpp b/lld/ELF/Writer.cpp --- a/lld/ELF/Writer.cpp +++ b/lld/ELF/Writer.cpp @@ -2944,12 +2944,12 @@ break; case BuildIdKind::Md5: computeHash(output, input, [&](uint8_t *dest, ArrayRef arr) { - memcpy(dest, BLAKE3::hash<16>(arr).data(), hashSize); + memcpy(dest, BLAKE3<16>::hash(arr).data(), hashSize); }); break; case BuildIdKind::Sha1: computeHash(output, input, [&](uint8_t *dest, ArrayRef arr) { - memcpy(dest, BLAKE3::hash<20>(arr).data(), hashSize); + memcpy(dest, BLAKE3<20>::hash(arr).data(), hashSize); }); break; case BuildIdKind::Uuid: diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp --- a/lld/MachO/SyntheticSections.cpp +++ b/lld/MachO/SyntheticSections.cpp @@ -1202,7 +1202,7 @@ std::min(codeEnd - code, static_cast(blockSize))); SHA256 hasher; hasher.update(block); - StringRef hash = hasher.final(); + auto hash = hasher.final(); assert(hash.size() == hashSize); memcpy(hashes, hash.data(), hashSize); code += blockSize; diff --git a/llvm/include/llvm/Support/BLAKE3.h b/llvm/include/llvm/Support/BLAKE3.h --- a/llvm/include/llvm/Support/BLAKE3.h +++ b/llvm/include/llvm/Support/BLAKE3.h @@ -34,8 +34,8 @@ template using BLAKE3Result = std::array; -/// A class that wrap the BLAKE3 algorithm. -class BLAKE3 { +/// A class that wraps the BLAKE3 algorithm. +template class BLAKE3 { public: BLAKE3() { init(); } @@ -55,7 +55,6 @@ /// Finalize the hasher and put the result in \p Result. /// This doesn't modify the hasher itself, and it's possible to finalize again /// after adding more input. - template void final(BLAKE3Result &Result) { llvm_blake3_hasher_finalize(&Hasher, Result.data(), Result.size()); } @@ -63,19 +62,25 @@ /// Finalize the hasher and return an output of any length, given in bytes. /// This doesn't modify the hasher itself, and it's possible to finalize again /// after adding more input. - template BLAKE3Result final() { BLAKE3Result Result; llvm_blake3_hasher_finalize(&Hasher, Result.data(), Result.size()); return Result; } + /// Return the current output for the digested data since the last call to + /// init(). + /// + /// Other hash functions distinguish between \p result() and \p final(), with + /// \p result() allowing more calls into \p update(), but there's no + // difference for the BLAKE3 function. + BLAKE3Result result() { return final(); } + /// Returns a BLAKE3 hash for the given data. - template static BLAKE3Result hash(ArrayRef Data) { - BLAKE3 Hasher; + BLAKE3 Hasher; Hasher.update(Data); - return Hasher.final(); + return Hasher.final(); } private: diff --git a/llvm/include/llvm/Support/HashBuilder.h b/llvm/include/llvm/Support/HashBuilder.h --- a/llvm/include/llvm/Support/HashBuilder.h +++ b/llvm/include/llvm/Support/HashBuilder.h @@ -39,6 +39,9 @@ /// Declares the hasher member, and functions forwarding directly to the hasher. template class HashBuilderBase { public: + template + using HashResultTy = decltype(std::declval().final()); + HasherT &getHasher() { return Hasher; } /// Forward to `HasherT::update(ArrayRef)`. @@ -59,12 +62,12 @@ } /// Forward to `HasherT::final()` if available. - template StringRef final() { + template HashResultTy final() { return this->getHasher().final(); } /// Forward to `HasherT::result()` if available. - template StringRef result() { + template HashResultTy result() { return this->getHasher().result(); } diff --git a/llvm/include/llvm/Support/MD5.h b/llvm/include/llvm/Support/MD5.h --- a/llvm/include/llvm/Support/MD5.h +++ b/llvm/include/llvm/Support/MD5.h @@ -78,13 +78,13 @@ /// Finishes off the hash and puts the result in result. void final(MD5Result &Result); - /// Finishes off the hash, and returns a reference to the 16-byte hash data. - StringRef final(); + /// Finishes off the hash, and returns the 16-byte hash data. + std::array final(); - /// Finishes off the hash, and returns a reference to the 16-byte hash data. + /// Finishes off the hash, and returns the 16-byte hash data. /// This is suitable for getting the MD5 at any time without invalidating the /// internal state, so that more calls can be made into `update`. - StringRef result(); + std::array result(); /// Translates the bytes in \p Res to a hex string that is /// deposited into \p Str. The result will be of length 32. @@ -109,8 +109,6 @@ MD5_u32plus block[16]; } InternalState; - MD5Result Result; - const uint8_t *body(ArrayRef Data); }; diff --git a/llvm/include/llvm/Support/SHA1.h b/llvm/include/llvm/Support/SHA1.h --- a/llvm/include/llvm/Support/SHA1.h +++ b/llvm/include/llvm/Support/SHA1.h @@ -36,17 +36,17 @@ /// Digest more data. void update(StringRef Str); - /// Return a reference to the current raw 160-bits SHA1 for the digested data + /// Return the current raw 160-bits SHA1 for the digested data /// since the last call to init(). This call will add data to the internal /// state and as such is not suited for getting an intermediate result /// (see result()). - StringRef final(); + std::array final(); - /// Return a reference to the current raw 160-bits SHA1 for the digested data + /// Return the current raw 160-bits SHA1 for the digested data /// since the last call to init(). This is suitable for getting the SHA1 at /// any time without invalidating the internal state so that more calls can be /// made into update. - StringRef result(); + std::array result(); /// Returns a raw 160-bit SHA1 hash for the given data. static std::array hash(ArrayRef Data); @@ -68,14 +68,13 @@ uint8_t BufferOffset; } InternalState; - // Internal copy of the hash, populated and accessed on calls to result() - uint32_t HashResult[HASH_LENGTH / 4]; - // Helper void writebyte(uint8_t data); void hashBlock(); void addUncounted(uint8_t data); void pad(); + + void final(std::array &HashResult); }; } // end llvm namespace diff --git a/llvm/include/llvm/Support/SHA256.h b/llvm/include/llvm/Support/SHA256.h --- a/llvm/include/llvm/Support/SHA256.h +++ b/llvm/include/llvm/Support/SHA256.h @@ -43,17 +43,17 @@ /// Digest more data. void update(StringRef Str); - /// Return a reference to the current raw 256-bits SHA256 for the digested + /// Return the current raw 256-bits SHA256 for the digested /// data since the last call to init(). This call will add data to the /// internal state and as such is not suited for getting an intermediate /// result (see result()). - StringRef final(); + std::array final(); - /// Return a reference to the current raw 256-bits SHA256 for the digested + /// Return the current raw 256-bits SHA256 for the digested /// data since the last call to init(). This is suitable for getting the /// SHA256 at any time without invalidating the internal state so that more /// calls can be made into update. - StringRef result(); + std::array result(); /// Returns a raw 256-bit SHA256 hash for the given data. static std::array hash(ArrayRef Data); @@ -75,14 +75,13 @@ uint8_t BufferOffset; } InternalState; - // Internal copy of the hash, populated and accessed on calls to result() - uint32_t HashResult[HASH_LENGTH / 4]; - // Helper void writebyte(uint8_t data); void hashBlock(); void addUncounted(uint8_t data); void pad(); + + void final(std::array &HashResult); }; } // namespace llvm diff --git a/llvm/include/llvm/Support/raw_sha1_ostream.h b/llvm/include/llvm/Support/raw_sha1_ostream.h --- a/llvm/include/llvm/Support/raw_sha1_ostream.h +++ b/llvm/include/llvm/Support/raw_sha1_ostream.h @@ -30,7 +30,7 @@ public: /// Return the current SHA1 hash for the content of the stream - StringRef sha1() { + std::array sha1() { flush(); return State.result(); } diff --git a/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp b/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp --- a/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp +++ b/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp @@ -903,7 +903,7 @@ else { // Recompute the hash and compare it to the one in the bitcode SHA1 Hasher; - StringRef Hash; + std::array Hash; Hasher.update(*CheckHash); { int BlockSize = (CurrentRecordPos / 8) - BlockEntryPos; @@ -911,14 +911,14 @@ Hasher.update(ArrayRef(Ptr, BlockSize)); Hash = Hasher.result(); } - std::array RecordedHash; + std::array RecordedHash; int Pos = 0; for (auto &Val : Record) { assert(!(Val >> 32) && "Unexpected high bits set"); support::endian::write32be(&RecordedHash[Pos], Val); Pos += 4; } - if (Hash == StringRef(RecordedHash.data(), RecordedHash.size())) + if (Hash == RecordedHash) O->OS << " (match)"; else O->OS << " (!mismatch!)"; diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp --- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp +++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp @@ -4387,7 +4387,7 @@ uint32_t Vals[5]; Hasher.update(ArrayRef((const uint8_t *)&(Buffer)[BlockStartPos], Buffer.size() - BlockStartPos)); - StringRef Hash = Hasher.result(); + auto Hash = Hasher.result(); for (int Pos = 0; Pos < 20; Pos += 4) { Vals[Pos / 4] = support::endian::read32be(Hash.data() + Pos); } diff --git a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp --- a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp +++ b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp @@ -76,5 +76,6 @@ auto TrailingBytes = RecordData.drop_front(Off); S.update(TrailingBytes); - return {S.final().take_back(8)}; + auto Hash = S.final(); + return {ArrayRef(Hash).take_back(8)}; } diff --git a/llvm/lib/ObjCopy/MachO/MachOWriter.cpp b/llvm/lib/ObjCopy/MachO/MachOWriter.cpp --- a/llvm/lib/ObjCopy/MachO/MachOWriter.cpp +++ b/llvm/lib/ObjCopy/MachO/MachOWriter.cpp @@ -570,7 +570,7 @@ static_cast(CodeSignature.BlockSize))); SHA256 Hasher; Hasher.update(Block); - StringRef Hash = Hasher.final(); + auto Hash = Hasher.final(); assert(Hash.size() == CodeSignature.HashSize); memcpy(CurrHashWritePosition, Hash.data(), CodeSignature.HashSize); CurrHashReadPosition += CodeSignature.BlockSize; diff --git a/llvm/lib/Support/BLAKE3/README.md b/llvm/lib/Support/BLAKE3/README.md --- a/llvm/lib/Support/BLAKE3/README.md +++ b/llvm/lib/Support/BLAKE3/README.md @@ -17,7 +17,7 @@ int main() { // Initialize the hasher. - llvm::BLAKE3 hasher; + llvm::BLAKE3<> hasher; // Read input bytes from stdin. char buf[65536]; @@ -92,6 +92,7 @@ ## The Class/Struct ```c++ +template class BLAKE3 { // API private: @@ -149,10 +150,10 @@ using BLAKE3Result = std::array; template -void BLAKE3::final(BLAKE3Result &Result); +void BLAKE3::final(BLAKE3Result &Result); template -BLAKE3Result final(); +BLAKE3Result BLAKE3::final(); ``` ```c void llvm_blake3_hasher_finalize( diff --git a/llvm/lib/Support/MD5.cpp b/llvm/lib/Support/MD5.cpp --- a/llvm/lib/Support/MD5.cpp +++ b/llvm/lib/Support/MD5.cpp @@ -261,13 +261,13 @@ support::endian::write32le(&Result[12], InternalState.d); } -StringRef MD5::final() { +std::array MD5::final() { + MD5Result Result; final(Result); - return StringRef(reinterpret_cast(Result.Bytes.data()), - Result.Bytes.size()); + return Result.Bytes; } -StringRef MD5::result() { +std::array MD5::result() { auto StateToRestore = InternalState; auto Hash = final(); diff --git a/llvm/lib/Support/SHA1.cpp b/llvm/lib/Support/SHA1.cpp --- a/llvm/lib/Support/SHA1.cpp +++ b/llvm/lib/Support/SHA1.cpp @@ -263,7 +263,7 @@ addUncounted(InternalState.ByteCount << 3); } -StringRef SHA1::final() { +void SHA1::final(std::array &HashResult) { // Pad to complete the last block pad(); @@ -281,12 +281,19 @@ (((InternalState.State[i]) >> 24) & 0x000000ff); } #endif +} - // Return pointer to hash (20 characters) - return StringRef((char *)HashResult, HASH_LENGTH); +std::array SHA1::final() { + union { + std::array HashResult; + std::array ReturnResult; + }; + static_assert(sizeof(HashResult) == sizeof(ReturnResult), ""); + final(HashResult); + return ReturnResult; } -StringRef SHA1::result() { +std::array SHA1::result() { auto StateToRestore = InternalState; auto Hash = final(); @@ -301,9 +308,5 @@ std::array SHA1::hash(ArrayRef Data) { SHA1 Hash; Hash.update(Data); - StringRef S = Hash.final(); - - std::array Arr; - memcpy(Arr.data(), S.data(), S.size()); - return Arr; + return Hash.final(); } diff --git a/llvm/lib/Support/SHA256.cpp b/llvm/lib/Support/SHA256.cpp --- a/llvm/lib/Support/SHA256.cpp +++ b/llvm/lib/Support/SHA256.cpp @@ -243,7 +243,7 @@ addUncounted(len); } -StringRef SHA256::final() { +void SHA256::final(std::array &HashResult) { // Pad to complete the last block pad(); @@ -261,12 +261,19 @@ (((InternalState.State[i]) >> 24) & 0x000000ff); } #endif +} - // Return pointer to hash (32 characters) - return StringRef((char *)HashResult, HASH_LENGTH); +std::array SHA256::final() { + union { + std::array HashResult; + std::array ReturnResult; + }; + static_assert(sizeof(HashResult) == sizeof(ReturnResult), ""); + final(HashResult); + return ReturnResult; } -StringRef SHA256::result() { +std::array SHA256::result() { auto StateToRestore = InternalState; auto Hash = final(); @@ -281,11 +288,7 @@ std::array SHA256::hash(ArrayRef Data) { SHA256 Hash; Hash.update(Data); - StringRef S = Hash.final(); - - std::array Arr; - memcpy(Arr.data(), S.data(), S.size()); - return Arr; + return Hash.final(); } } // namespace llvm diff --git a/llvm/unittests/Support/BLAKE3Test.cpp b/llvm/unittests/Support/BLAKE3Test.cpp --- a/llvm/unittests/Support/BLAKE3Test.cpp +++ b/llvm/unittests/Support/BLAKE3Test.cpp @@ -12,6 +12,7 @@ #include "llvm/Support/BLAKE3.h" #include "llvm/ADT/StringExtras.h" +#include "llvm/Support/HashBuilder.h" #include "gtest/gtest.h" using namespace llvm; @@ -20,7 +21,7 @@ /// Tests an arbitrary set of bytes passed as \p Input. void TestBLAKE3Sum(ArrayRef Input, StringRef Final) { - BLAKE3 Hash; + BLAKE3<> Hash; Hash.update(Input); auto hash = Hash.final(); auto hashStr = toHex(hash); @@ -51,7 +52,7 @@ } std::string rep(1000, 'a'); - BLAKE3 Hash; + BLAKE3<> Hash; for (int i = 0; i < 1000; ++i) { Hash.update({reinterpret_cast(rep.data()), rep.size()}); } @@ -65,14 +66,22 @@ const char *InputStr = "abc"; ArrayRef Input(reinterpret_cast(InputStr), strlen(InputStr)); - BLAKE3 Hash; + BLAKE3<16> Hash; Hash.update(Input); - auto hash1 = Hash.final<16>(); - auto hash2 = BLAKE3::hash<16>(Input); + auto hash1 = Hash.final(); + auto hash2 = BLAKE3<16>::hash(Input); auto hashStr1 = toHex(hash1); auto hashStr2 = toHex(hash2); EXPECT_EQ(hashStr1, hashStr2); EXPECT_EQ(hashStr1, "6437B3AC38465133FFB63B75273A8DB5"); + + // Using generic HashBuilder + HashBuilder, support::endianness::native> HashBuilder; + HashBuilder.update(Input); + auto hash3 = HashBuilder.final(); + auto hash4 = HashBuilder.result(); + EXPECT_EQ(hashStr1, toHex(hash3)); + EXPECT_EQ(hashStr1, toHex(hash4)); } } // namespace diff --git a/llvm/unittests/Support/HashBuilderTest.cpp b/llvm/unittests/Support/HashBuilderTest.cpp --- a/llvm/unittests/Support/HashBuilderTest.cpp +++ b/llvm/unittests/Support/HashBuilderTest.cpp @@ -44,13 +44,15 @@ HasherTAndEndianness::Endianness>; template -static std::string hashWithBuilder(const Ts &...Args) { - return HashBuilder().add(Args...).final().str(); +static typename HashBuilder::template HashResultTy<> +hashWithBuilder(const Ts &...Args) { + return HashBuilder().add(Args...).final(); } template -static std::string hashRangeWithBuilder(const Ts &...Args) { - return HashBuilder().addRange(Args...).final().str(); +static typename HashBuilder::template HashResultTy<> +hashRangeWithBuilder(const Ts &...Args) { + return HashBuilder().addRange(Args...).final(); } // All the test infrastructure relies on the variadic helpers. Test them first. @@ -102,7 +104,7 @@ auto SwappedData = llvm::support::endian::byte_swap(Data, E); Hasher.update(llvm::makeArrayRef( reinterpret_cast(&SwappedData), sizeof(Data))); - return static_cast(Hasher.final()); + return Hasher.final(); }; char C = 'c'; diff --git a/llvm/unittests/Support/MD5Test.cpp b/llvm/unittests/Support/MD5Test.cpp --- a/llvm/unittests/Support/MD5Test.cpp +++ b/llvm/unittests/Support/MD5Test.cpp @@ -79,10 +79,7 @@ ReferenceHash.update("abcd"); MD5::MD5Result ReferenceResult; ReferenceHash.final(ReferenceResult); - StringRef ExpectedResult = - StringRef(reinterpret_cast(ReferenceResult.Bytes.data()), - ReferenceResult.Bytes.size()); - EXPECT_EQ(Hash.result(), ExpectedResult); + EXPECT_EQ(Hash.result(), ReferenceResult.Bytes); } Hash.update("xyz"); @@ -93,10 +90,7 @@ ReferenceHash.update("xyz"); MD5::MD5Result ReferenceResult; ReferenceHash.final(ReferenceResult); - StringRef ExpectedResult = - StringRef(reinterpret_cast(ReferenceResult.Bytes.data()), - ReferenceResult.Bytes.size()); - EXPECT_EQ(Hash.final(), ExpectedResult); + EXPECT_EQ(Hash.final(), ReferenceResult.Bytes); } } } // namespace diff --git a/llvm/unittests/Support/SHA256.cpp b/llvm/unittests/Support/SHA256.cpp --- a/llvm/unittests/Support/SHA256.cpp +++ b/llvm/unittests/Support/SHA256.cpp @@ -20,7 +20,7 @@ namespace { -static std::string toHex(StringRef Input) { +static std::string toHex(ArrayRef Input) { static const char *const LUT = "0123456789abcdef"; size_t Length = Input.size(); diff --git a/llvm/unittests/Support/raw_sha1_ostream_test.cpp b/llvm/unittests/Support/raw_sha1_ostream_test.cpp --- a/llvm/unittests/Support/raw_sha1_ostream_test.cpp +++ b/llvm/unittests/Support/raw_sha1_ostream_test.cpp @@ -14,7 +14,7 @@ using namespace llvm; -static std::string toHex(StringRef Input) { +static std::string toHex(ArrayRef Input) { static const char *const LUT = "0123456789ABCDEF"; size_t Length = Input.size(); @@ -39,7 +39,7 @@ TEST(sha1_hash_test, Basic) { ArrayRef Input((const uint8_t *)"Hello World!", 12); std::array Vec = SHA1::hash(Input); - std::string Hash = toHex({(const char *)Vec.data(), 20}); + std::string Hash = toHex(Vec); ASSERT_EQ("2EF7BDE608CE5404E97D5F042F95F89F1C232871", Hash); } diff --git a/mlir/lib/Pass/IRPrinting.cpp b/mlir/lib/Pass/IRPrinting.cpp --- a/mlir/lib/Pass/IRPrinting.cpp +++ b/mlir/lib/Pass/IRPrinting.cpp @@ -66,7 +66,7 @@ ArrayRef(reinterpret_cast(&data), sizeof(T))); } - SmallString<20> hash; + std::array hash; }; //===----------------------------------------------------------------------===//