[lld] 330268b - [Support/Hash functions] Change the `final()` and `result()` of the hashing functions to return an array of bytes
Argyrios Kyrtzidis via llvm-commits
llvm-commits at lists.llvm.org
Tue Apr 5 21:38:13 PDT 2022
Author: Argyrios Kyrtzidis
Date: 2022-04-05T21:38:06-07:00
New Revision: 330268ba346b679af786879d8f696c8c412a40eb
URL: https://github.com/llvm/llvm-project/commit/330268ba346b679af786879d8f696c8c412a40eb
DIFF: https://github.com/llvm/llvm-project/commit/330268ba346b679af786879d8f696c8c412a40eb.diff
LOG: [Support/Hash functions] Change the `final()` and `result()` of the hashing functions to return an array of bytes
Returning `std::array<uint8_t, N>` is better ergonomics for the hashing functions usage, instead of a `StringRef`:
* When returning `StringRef`, client code is "jumping through hoops" to do string manipulations instead of dealing with fixed array of bytes directly, which is more natural
* Returning `std::array<uint8_t, N>` avoids the need for the hasher classes to keep a field just for the purpose of wrapping it and returning it as a `StringRef`
As part of this patch also:
* Introduce `TruncatedBLAKE3` which is useful for using BLAKE3 as the hasher type for `HashBuilder` with non-default hash sizes.
* Make `MD5Result` inherit from `std::array<uint8_t, 16>` which improves & simplifies its API.
Differential Revision: https://reviews.llvm.org/D123100
Added:
Modified:
bolt/lib/Core/DebugData.cpp
clang/include/clang/Basic/Module.h
clang/lib/Serialization/ASTWriter.cpp
lld/MachO/SyntheticSections.cpp
llvm/include/llvm/Support/BLAKE3.h
llvm/include/llvm/Support/HashBuilder.h
llvm/include/llvm/Support/MD5.h
llvm/include/llvm/Support/SHA1.h
llvm/include/llvm/Support/SHA256.h
llvm/include/llvm/Support/raw_sha1_ostream.h
llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp
llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
llvm/lib/MC/MCDwarf.cpp
llvm/lib/MC/MCParser/AsmParser.cpp
llvm/lib/MC/MCParser/MasmParser.cpp
llvm/lib/ObjCopy/MachO/MachOWriter.cpp
llvm/lib/Support/BLAKE3/README.md
llvm/lib/Support/MD5.cpp
llvm/lib/Support/SHA1.cpp
llvm/lib/Support/SHA256.cpp
llvm/unittests/Support/BLAKE3Test.cpp
llvm/unittests/Support/HashBuilderTest.cpp
llvm/unittests/Support/MD5Test.cpp
llvm/unittests/Support/SHA256.cpp
llvm/unittests/Support/raw_sha1_ostream_test.cpp
mlir/lib/Pass/IRPrinting.cpp
Removed:
################################################################################
diff --git a/bolt/lib/Core/DebugData.cpp b/bolt/lib/Core/DebugData.cpp
index ba6a653cb88be..2ebd2c03838dd 100644
--- a/bolt/lib/Core/DebugData.cpp
+++ b/bolt/lib/Core/DebugData.cpp
@@ -820,7 +820,8 @@ void DebugAbbrevWriter::addUnitAbbreviations(DWARFUnit &Unit) {
auto hashAndAddAbbrev = [&](StringRef AbbrevData) -> bool {
llvm::SHA1 Hasher;
Hasher.update(AbbrevData);
- StringRef Key = Hasher.final();
+ std::array<uint8_t, 20> 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
index af96038ba4aa8..45c23d5b7988e 100644
--- a/clang/include/clang/Basic/Module.h
+++ b/clang/include/clang/Basic/Module.h
@@ -71,8 +71,8 @@ struct ASTFileSignature : std::array<uint8_t, 20> {
return Value;
}
- static ASTFileSignature create(StringRef Bytes) {
- return create(Bytes.bytes_begin(), Bytes.bytes_end());
+ static ASTFileSignature create(std::array<uint8_t, 20> Bytes) {
+ return ASTFileSignature(std::move(Bytes));
}
static ASTFileSignature createDISentinel() {
diff --git a/clang/lib/Serialization/ASTWriter.cpp b/clang/lib/Serialization/ASTWriter.cpp
index b6860619470d9..5fd4e8fb27cf8 100644
--- a/clang/lib/Serialization/ASTWriter.cpp
+++ b/clang/lib/Serialization/ASTWriter.cpp
@@ -1117,8 +1117,7 @@ std::pair<ASTFileSignature, ASTFileSignature>
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 @@ ASTWriter::createSignature(StringRef AllBytes, StringRef ASTBlockBytes) {
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/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
index e47c7e325a343..a4de385e04f00 100644
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -1202,7 +1202,7 @@ void CodeSignatureSection::writeHashes(uint8_t *buf) const {
std::min(codeEnd - code, static_cast<ssize_t>(blockSize)));
SHA256 hasher;
hasher.update(block);
- StringRef hash = hasher.final();
+ std::array<uint8_t, 32> 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
index ade5201904655..7b30dbccd1734 100644
--- a/llvm/include/llvm/Support/BLAKE3.h
+++ b/llvm/include/llvm/Support/BLAKE3.h
@@ -34,7 +34,7 @@ namespace llvm {
template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
using BLAKE3Result = std::array<uint8_t, NumBytes>;
-/// A class that wrap the BLAKE3 algorithm.
+/// A class that wraps the BLAKE3 algorithm.
class BLAKE3 {
public:
BLAKE3() { init(); }
@@ -70,6 +70,17 @@ class BLAKE3 {
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
+ //
diff erence for the BLAKE3 hash function.
+ template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
+ BLAKE3Result<NumBytes> result() {
+ return final<NumBytes>();
+ }
+
/// Returns a BLAKE3 hash for the given data.
template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
static BLAKE3Result<NumBytes> hash(ArrayRef<uint8_t> Data) {
@@ -82,6 +93,32 @@ class BLAKE3 {
llvm_blake3_hasher Hasher;
};
+/// Like \p BLAKE3 but using a class-level template parameter for specifying the
+/// hash size of the \p final() and \p result() functions.
+///
+/// This is useful for using BLAKE3 as the hasher type for \p HashBuilder with
+/// non-default hash sizes.
+template <size_t NumBytes> class TruncatedBLAKE3 : public BLAKE3 {
+public:
+ /// 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.
+ void final(BLAKE3Result<NumBytes> &Result) { return BLAKE3::final(Result); }
+
+ /// 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.
+ BLAKE3Result<NumBytes> final() { return BLAKE3::final<NumBytes>(); }
+
+ /// 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
+ //
diff erence for the BLAKE3 hash function.
+ BLAKE3Result<NumBytes> result() { return BLAKE3::result<NumBytes>(); }
+};
+
} // namespace llvm
#endif
diff --git a/llvm/include/llvm/Support/HashBuilder.h b/llvm/include/llvm/Support/HashBuilder.h
index bf93a0d22da73..9d7680d2b6677 100644
--- a/llvm/include/llvm/Support/HashBuilder.h
+++ b/llvm/include/llvm/Support/HashBuilder.h
@@ -39,6 +39,9 @@ struct IsHashableData
/// Declares the hasher member, and functions forwarding directly to the hasher.
template <typename HasherT> class HashBuilderBase {
public:
+ template <typename HasherT_ = HasherT>
+ using HashResultTy = decltype(std::declval<HasherT_ &>().final());
+
HasherT &getHasher() { return Hasher; }
/// Forward to `HasherT::update(ArrayRef<uint8_t>)`.
@@ -59,12 +62,12 @@ template <typename HasherT> class HashBuilderBase {
}
/// Forward to `HasherT::final()` if available.
- template <typename HasherT_ = HasherT> StringRef final() {
+ template <typename HasherT_ = HasherT> HashResultTy<HasherT_> final() {
return this->getHasher().final();
}
/// Forward to `HasherT::result()` if available.
- template <typename HasherT_ = HasherT> StringRef result() {
+ template <typename HasherT_ = HasherT> HashResultTy<HasherT_> result() {
return this->getHasher().result();
}
diff --git a/llvm/include/llvm/Support/MD5.h b/llvm/include/llvm/Support/MD5.h
index 70d0466013461..fa2f477261dd9 100644
--- a/llvm/include/llvm/Support/MD5.h
+++ b/llvm/include/llvm/Support/MD5.h
@@ -40,26 +40,19 @@ template <typename T> class ArrayRef;
class MD5 {
public:
- struct MD5Result {
- std::array<uint8_t, 16> Bytes;
-
- operator std::array<uint8_t, 16>() const { return Bytes; }
-
- const uint8_t &operator[](size_t I) const { return Bytes[I]; }
- uint8_t &operator[](size_t I) { return Bytes[I]; }
-
+ struct MD5Result : public std::array<uint8_t, 16> {
SmallString<32> digest() const;
uint64_t low() const {
// Our MD5 implementation returns the result in little endian, so the low
// word is first.
using namespace support;
- return endian::read<uint64_t, little, unaligned>(Bytes.data());
+ return endian::read<uint64_t, little, unaligned>(data());
}
uint64_t high() const {
using namespace support;
- return endian::read<uint64_t, little, unaligned>(Bytes.data() + 8);
+ return endian::read<uint64_t, little, unaligned>(data() + 8);
}
std::pair<uint64_t, uint64_t> words() const {
using namespace support;
@@ -78,20 +71,20 @@ class MD5 {
/// 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.
+ MD5Result 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();
+ MD5Result result();
/// Translates the bytes in \p Res to a hex string that is
/// deposited into \p Str. The result will be of length 32.
static void stringifyResult(MD5Result &Result, SmallVectorImpl<char> &Str);
/// Computes the hash for a given bytes.
- static std::array<uint8_t, 16> hash(ArrayRef<uint8_t> Data);
+ static MD5Result hash(ArrayRef<uint8_t> Data);
private:
// Any 32-bit or wider unsigned integer data type will do.
@@ -109,15 +102,9 @@ class MD5 {
MD5_u32plus block[16];
} InternalState;
- MD5Result Result;
-
const uint8_t *body(ArrayRef<uint8_t> Data);
};
-inline bool operator==(const MD5::MD5Result &LHS, const MD5::MD5Result &RHS) {
- return LHS.Bytes == RHS.Bytes;
-}
-
/// Helper to compute and return lower 64 bits of the given string's MD5 hash.
inline uint64_t MD5Hash(StringRef Str) {
using namespace support;
diff --git a/llvm/include/llvm/Support/SHA1.h b/llvm/include/llvm/Support/SHA1.h
index efd8513cc201f..ae6d62aed723a 100644
--- a/llvm/include/llvm/Support/SHA1.h
+++ b/llvm/include/llvm/Support/SHA1.h
@@ -36,17 +36,17 @@ class SHA1 {
/// 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<uint8_t, 20> 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<uint8_t, 20> result();
/// Returns a raw 160-bit SHA1 hash for the given data.
static std::array<uint8_t, 20> hash(ArrayRef<uint8_t> Data);
@@ -68,14 +68,13 @@ class SHA1 {
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<uint32_t, HASH_LENGTH / 4> &HashResult);
};
} // end llvm namespace
diff --git a/llvm/include/llvm/Support/SHA256.h b/llvm/include/llvm/Support/SHA256.h
index 9e295b0b9fae5..68b32c7b48348 100644
--- a/llvm/include/llvm/Support/SHA256.h
+++ b/llvm/include/llvm/Support/SHA256.h
@@ -43,17 +43,17 @@ class SHA256 {
/// 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<uint8_t, 32> 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<uint8_t, 32> result();
/// Returns a raw 256-bit SHA256 hash for the given data.
static std::array<uint8_t, 32> hash(ArrayRef<uint8_t> Data);
@@ -75,14 +75,13 @@ class SHA256 {
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<uint32_t, HASH_LENGTH / 4> &HashResult);
};
} // namespace llvm
diff --git a/llvm/include/llvm/Support/raw_sha1_ostream.h b/llvm/include/llvm/Support/raw_sha1_ostream.h
index 3991691796b59..299f6e6b5e886 100644
--- a/llvm/include/llvm/Support/raw_sha1_ostream.h
+++ b/llvm/include/llvm/Support/raw_sha1_ostream.h
@@ -30,7 +30,7 @@ class raw_sha1_ostream : public raw_ostream {
public:
/// Return the current SHA1 hash for the content of the stream
- StringRef sha1() {
+ std::array<uint8_t, 20> sha1() {
flush();
return State.result();
}
diff --git a/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp b/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp
index fdb07cf282a93..f291827d7f6f3 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeAnalyzer.cpp
@@ -903,7 +903,7 @@ Error BitcodeAnalyzer::parseBlock(unsigned BlockID, unsigned IndentLevel,
else {
// Recompute the hash and compare it to the one in the bitcode
SHA1 Hasher;
- StringRef Hash;
+ std::array<uint8_t, 20> Hash;
Hasher.update(*CheckHash);
{
int BlockSize = (CurrentRecordPos / 8) - BlockEntryPos;
@@ -911,14 +911,14 @@ Error BitcodeAnalyzer::parseBlock(unsigned BlockID, unsigned IndentLevel,
Hasher.update(ArrayRef<uint8_t>(Ptr, BlockSize));
Hash = Hasher.result();
}
- std::array<char, 20> RecordedHash;
+ std::array<uint8_t, 20> 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
index 8a1652478aaed..c76294d5a6d9f 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -4387,7 +4387,7 @@ void ModuleBitcodeWriter::writeModuleHash(size_t BlockStartPos) {
uint32_t Vals[5];
Hasher.update(ArrayRef<uint8_t>((const uint8_t *)&(Buffer)[BlockStartPos],
Buffer.size() - BlockStartPos));
- StringRef Hash = Hasher.result();
+ std::array<uint8_t, 20> 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/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index 850a5e11f97dd..37ae84ad9bf17 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -3536,6 +3536,6 @@ Optional<MD5::MD5Result> DwarfDebug::getMD5AsBytes(const DIFile *File) const {
// An MD5 checksum is 16 bytes.
std::string ChecksumString = fromHex(Checksum->Value);
MD5::MD5Result CKMem;
- std::copy(ChecksumString.begin(), ChecksumString.end(), CKMem.Bytes.data());
+ std::copy(ChecksumString.begin(), ChecksumString.end(), CKMem.data());
return CKMem;
}
diff --git a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
index 2dbc11a84f0b0..fc85d8186eaad 100644
--- a/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
+++ b/llvm/lib/DebugInfo/CodeView/TypeHashing.cpp
@@ -76,5 +76,6 @@ GloballyHashedType::hashType(ArrayRef<uint8_t> RecordData,
auto TrailingBytes = RecordData.drop_front(Off);
S.update(TrailingBytes);
- return {S.final().take_back(8)};
+ std::array<uint8_t, 20> Hash = S.final();
+ return {ArrayRef<uint8_t>(Hash).take_back(8)};
}
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
index 3df22c0ec2395..81394e2b24b74 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
@@ -341,7 +341,7 @@ parseV5DirFileTables(const DWARFDataExtractor &DebugLineData,
errc::invalid_argument,
"failed to parse file entry because the MD5 hash is invalid");
std::uninitialized_copy_n(Value.getAsBlock().getValue().begin(), 16,
- FileEntry.Checksum.Bytes.begin());
+ FileEntry.Checksum.begin());
break;
default:
break;
diff --git a/llvm/lib/MC/MCDwarf.cpp b/llvm/lib/MC/MCDwarf.cpp
index 2cb5a000f88a7..f2e92fe007a8a 100644
--- a/llvm/lib/MC/MCDwarf.cpp
+++ b/llvm/lib/MC/MCDwarf.cpp
@@ -387,8 +387,7 @@ static void emitOneV5FileEntry(MCStreamer *MCOS, const MCDwarfFile &DwarfFile,
if (EmitMD5) {
const MD5::MD5Result &Cksum = *DwarfFile.Checksum;
MCOS->emitBinaryData(
- StringRef(reinterpret_cast<const char *>(Cksum.Bytes.data()),
- Cksum.Bytes.size()));
+ StringRef(reinterpret_cast<const char *>(Cksum.data()), Cksum.size()));
}
if (HasSource) {
if (LineStr)
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 9632f00379bfd..defc86e06aa60 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -3573,8 +3573,8 @@ bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
if (HasMD5) {
MD5::MD5Result Sum;
for (unsigned i = 0; i != 8; ++i) {
- Sum.Bytes[i] = uint8_t(MD5Hi >> ((7 - i) * 8));
- Sum.Bytes[i + 8] = uint8_t(MD5Lo >> ((7 - i) * 8));
+ Sum[i] = uint8_t(MD5Hi >> ((7 - i) * 8));
+ Sum[i + 8] = uint8_t(MD5Lo >> ((7 - i) * 8));
}
CKMem = Sum;
}
diff --git a/llvm/lib/MC/MCParser/MasmParser.cpp b/llvm/lib/MC/MCParser/MasmParser.cpp
index aa4cc0271b97a..be478e2fac5d8 100644
--- a/llvm/lib/MC/MCParser/MasmParser.cpp
+++ b/llvm/lib/MC/MCParser/MasmParser.cpp
@@ -4907,8 +4907,8 @@ bool MasmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
if (HasMD5) {
MD5::MD5Result Sum;
for (unsigned i = 0; i != 8; ++i) {
- Sum.Bytes[i] = uint8_t(MD5Hi >> ((7 - i) * 8));
- Sum.Bytes[i + 8] = uint8_t(MD5Lo >> ((7 - i) * 8));
+ Sum[i] = uint8_t(MD5Hi >> ((7 - i) * 8));
+ Sum[i + 8] = uint8_t(MD5Lo >> ((7 - i) * 8));
}
CKMem = Sum;
}
diff --git a/llvm/lib/ObjCopy/MachO/MachOWriter.cpp b/llvm/lib/ObjCopy/MachO/MachOWriter.cpp
index 2a2eda45db390..d5d7c0275d351 100644
--- a/llvm/lib/ObjCopy/MachO/MachOWriter.cpp
+++ b/llvm/lib/ObjCopy/MachO/MachOWriter.cpp
@@ -570,7 +570,7 @@ void MachOWriter::writeCodeSignatureData() {
static_cast<ssize_t>(CodeSignature.BlockSize)));
SHA256 Hasher;
Hasher.update(Block);
- StringRef Hash = Hasher.final();
+ std::array<uint8_t, 32> 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
index c4a87c7806410..319a7514e8b50 100644
--- a/llvm/lib/Support/BLAKE3/README.md
+++ b/llvm/lib/Support/BLAKE3/README.md
@@ -152,7 +152,7 @@ template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
void BLAKE3::final(BLAKE3Result<NumBytes> &Result);
template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
-BLAKE3Result<NumBytes> final();
+BLAKE3Result<NumBytes> BLAKE3::final();
```
```c
void llvm_blake3_hasher_finalize(
diff --git a/llvm/lib/Support/MD5.cpp b/llvm/lib/Support/MD5.cpp
index caadde3895043..fdcf34d70ad97 100644
--- a/llvm/lib/Support/MD5.cpp
+++ b/llvm/lib/Support/MD5.cpp
@@ -261,13 +261,13 @@ void MD5::final(MD5Result &Result) {
support::endian::write32le(&Result[12], InternalState.d);
}
-StringRef MD5::final() {
+MD5::MD5Result MD5::final() {
+ MD5Result Result;
final(Result);
- return StringRef(reinterpret_cast<char *>(Result.Bytes.data()),
- Result.Bytes.size());
+ return Result;
}
-StringRef MD5::result() {
+MD5::MD5Result MD5::result() {
auto StateToRestore = InternalState;
auto Hash = final();
@@ -280,15 +280,15 @@ StringRef MD5::result() {
SmallString<32> MD5::MD5Result::digest() const {
SmallString<32> Str;
- toHex(Bytes, /*LowerCase*/ true, Str);
+ toHex(*this, /*LowerCase*/ true, Str);
return Str;
}
void MD5::stringifyResult(MD5Result &Result, SmallVectorImpl<char> &Str) {
- toHex(Result.Bytes, /*LowerCase*/ true, Str);
+ toHex(Result, /*LowerCase*/ true, Str);
}
-std::array<uint8_t, 16> MD5::hash(ArrayRef<uint8_t> Data) {
+MD5::MD5Result MD5::hash(ArrayRef<uint8_t> Data) {
MD5 Hash;
Hash.update(Data);
MD5::MD5Result Res;
diff --git a/llvm/lib/Support/SHA1.cpp b/llvm/lib/Support/SHA1.cpp
index 5dce44af9ecd8..52bae700350d6 100644
--- a/llvm/lib/Support/SHA1.cpp
+++ b/llvm/lib/Support/SHA1.cpp
@@ -263,7 +263,7 @@ void SHA1::pad() {
addUncounted(InternalState.ByteCount << 3);
}
-StringRef SHA1::final() {
+void SHA1::final(std::array<uint32_t, HASH_LENGTH / 4> &HashResult) {
// Pad to complete the last block
pad();
@@ -281,12 +281,19 @@ StringRef SHA1::final() {
(((InternalState.State[i]) >> 24) & 0x000000ff);
}
#endif
+}
- // Return pointer to hash (20 characters)
- return StringRef((char *)HashResult, HASH_LENGTH);
+std::array<uint8_t, 20> SHA1::final() {
+ union {
+ std::array<uint32_t, HASH_LENGTH / 4> HashResult;
+ std::array<uint8_t, HASH_LENGTH> ReturnResult;
+ };
+ static_assert(sizeof(HashResult) == sizeof(ReturnResult), "");
+ final(HashResult);
+ return ReturnResult;
}
-StringRef SHA1::result() {
+std::array<uint8_t, 20> SHA1::result() {
auto StateToRestore = InternalState;
auto Hash = final();
@@ -301,9 +308,5 @@ StringRef SHA1::result() {
std::array<uint8_t, 20> SHA1::hash(ArrayRef<uint8_t> Data) {
SHA1 Hash;
Hash.update(Data);
- StringRef S = Hash.final();
-
- std::array<uint8_t, 20> 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
index 3b81506847ec8..81d897fb41874 100644
--- a/llvm/lib/Support/SHA256.cpp
+++ b/llvm/lib/Support/SHA256.cpp
@@ -243,7 +243,7 @@ void SHA256::pad() {
addUncounted(len);
}
-StringRef SHA256::final() {
+void SHA256::final(std::array<uint32_t, HASH_LENGTH / 4> &HashResult) {
// Pad to complete the last block
pad();
@@ -261,12 +261,19 @@ StringRef SHA256::final() {
(((InternalState.State[i]) >> 24) & 0x000000ff);
}
#endif
+}
- // Return pointer to hash (32 characters)
- return StringRef((char *)HashResult, HASH_LENGTH);
+std::array<uint8_t, 32> SHA256::final() {
+ union {
+ std::array<uint32_t, HASH_LENGTH / 4> HashResult;
+ std::array<uint8_t, HASH_LENGTH> ReturnResult;
+ };
+ static_assert(sizeof(HashResult) == sizeof(ReturnResult), "");
+ final(HashResult);
+ return ReturnResult;
}
-StringRef SHA256::result() {
+std::array<uint8_t, 32> SHA256::result() {
auto StateToRestore = InternalState;
auto Hash = final();
@@ -281,11 +288,7 @@ StringRef SHA256::result() {
std::array<uint8_t, 32> SHA256::hash(ArrayRef<uint8_t> Data) {
SHA256 Hash;
Hash.update(Data);
- StringRef S = Hash.final();
-
- std::array<uint8_t, 32> 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
index 197271a12804d..a729524112e32 100644
--- 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;
@@ -59,6 +60,14 @@ TEST(BLAKE3Test, BLAKE3) {
auto hashStr = toHex(hash);
EXPECT_EQ(hashStr,
"616F575A1B58D4C9797D4217B9730AE5E6EB319D76EDEF6549B46F4EFE31FF8B");
+
+ // Using generic HashBuilder.
+ HashBuilder<BLAKE3, support::endianness::native> HashBuilder;
+ HashBuilder.update(std::get<0>(testvectors[2]));
+ BLAKE3Result<> HBHash1 = HashBuilder.final();
+ BLAKE3Result<> HBHash2 = HashBuilder.result();
+ EXPECT_EQ(std::get<1>(testvectors[2]), toHex(HBHash1));
+ EXPECT_EQ(std::get<1>(testvectors[2]), toHex(HBHash2));
}
TEST(BLAKE3Test, SmallerHashSize) {
@@ -73,6 +82,14 @@ TEST(BLAKE3Test, SmallerHashSize) {
auto hashStr2 = toHex(hash2);
EXPECT_EQ(hashStr1, hashStr2);
EXPECT_EQ(hashStr1, "6437B3AC38465133FFB63B75273A8DB5");
+
+ // Using generic HashBuilder.
+ HashBuilder<TruncatedBLAKE3<16>, support::endianness::native> HashBuilder;
+ HashBuilder.update(Input);
+ BLAKE3Result<16> hash3 = HashBuilder.final();
+ BLAKE3Result<16> 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
index d644107bbcf18..26007442a3394 100644
--- a/llvm/unittests/Support/HashBuilderTest.cpp
+++ b/llvm/unittests/Support/HashBuilderTest.cpp
@@ -44,13 +44,15 @@ using HashBuilder = llvm::HashBuilder<typename HasherTAndEndianness::HasherT,
HasherTAndEndianness::Endianness>;
template <typename HasherTAndEndianness, typename... Ts>
-static std::string hashWithBuilder(const Ts &...Args) {
- return HashBuilder<HasherTAndEndianness>().add(Args...).final().str();
+static typename HashBuilder<HasherTAndEndianness>::template HashResultTy<>
+hashWithBuilder(const Ts &...Args) {
+ return HashBuilder<HasherTAndEndianness>().add(Args...).final();
}
template <typename HasherTAndEndianness, typename... Ts>
-static std::string hashRangeWithBuilder(const Ts &...Args) {
- return HashBuilder<HasherTAndEndianness>().addRange(Args...).final().str();
+static typename HashBuilder<HasherTAndEndianness>::template HashResultTy<>
+hashRangeWithBuilder(const Ts &...Args) {
+ return HashBuilder<HasherTAndEndianness>().addRange(Args...).final();
}
// All the test infrastructure relies on the variadic helpers. Test them first.
@@ -102,7 +104,7 @@ TYPED_TEST(HashBuilderTest, AddHashableData) {
auto SwappedData = llvm::support::endian::byte_swap(Data, E);
Hasher.update(llvm::makeArrayRef(
reinterpret_cast<const uint8_t *>(&SwappedData), sizeof(Data)));
- return static_cast<std::string>(Hasher.final());
+ return Hasher.final();
};
char C = 'c';
diff --git a/llvm/unittests/Support/MD5Test.cpp b/llvm/unittests/Support/MD5Test.cpp
index 8eb4d3422cb62..83c556cbc5bd9 100644
--- a/llvm/unittests/Support/MD5Test.cpp
+++ b/llvm/unittests/Support/MD5Test.cpp
@@ -62,7 +62,7 @@ TEST(MD5HashTest, MD5) {
std::array<uint8_t, 16> Vec = MD5::hash(Input);
MD5::MD5Result MD5Res;
SmallString<32> Res;
- memcpy(MD5Res.Bytes.data(), Vec.data(), Vec.size());
+ memcpy(MD5Res.data(), Vec.data(), Vec.size());
MD5::stringifyResult(MD5Res, Res);
EXPECT_EQ(Res, "c3fcd3d76192e4007dfb496cca67e13b");
EXPECT_EQ(0x3be167ca6c49fb7dULL, MD5Res.high());
@@ -79,10 +79,7 @@ TEST(MD5Test, FinalAndResultHelpers) {
ReferenceHash.update("abcd");
MD5::MD5Result ReferenceResult;
ReferenceHash.final(ReferenceResult);
- StringRef ExpectedResult =
- StringRef(reinterpret_cast<char *>(ReferenceResult.Bytes.data()),
- ReferenceResult.Bytes.size());
- EXPECT_EQ(Hash.result(), ExpectedResult);
+ EXPECT_EQ(Hash.result(), ReferenceResult);
}
Hash.update("xyz");
@@ -93,10 +90,7 @@ TEST(MD5Test, FinalAndResultHelpers) {
ReferenceHash.update("xyz");
MD5::MD5Result ReferenceResult;
ReferenceHash.final(ReferenceResult);
- StringRef ExpectedResult =
- StringRef(reinterpret_cast<char *>(ReferenceResult.Bytes.data()),
- ReferenceResult.Bytes.size());
- EXPECT_EQ(Hash.final(), ExpectedResult);
+ EXPECT_EQ(Hash.final(), ReferenceResult);
}
}
} // namespace
diff --git a/llvm/unittests/Support/SHA256.cpp b/llvm/unittests/Support/SHA256.cpp
index 82359a7177b9b..a50ce7ba64cd2 100644
--- a/llvm/unittests/Support/SHA256.cpp
+++ b/llvm/unittests/Support/SHA256.cpp
@@ -20,7 +20,7 @@ using namespace llvm;
namespace {
-static std::string toHex(StringRef Input) {
+static std::string toHex(ArrayRef<uint8_t> 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
index 3238d0d0e88ff..a3cb6f58d3e29 100644
--- 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<uint8_t> Input) {
static const char *const LUT = "0123456789ABCDEF";
size_t Length = Input.size();
@@ -39,7 +39,7 @@ TEST(raw_sha1_ostreamTest, Basic) {
TEST(sha1_hash_test, Basic) {
ArrayRef<uint8_t> Input((const uint8_t *)"Hello World!", 12);
std::array<uint8_t, 20> 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
index 30d5a8e1a7798..c6bfa941a8632 100644
--- a/mlir/lib/Pass/IRPrinting.cpp
+++ b/mlir/lib/Pass/IRPrinting.cpp
@@ -66,7 +66,7 @@ class OperationFingerPrint {
ArrayRef<uint8_t>(reinterpret_cast<const uint8_t *>(&data), sizeof(T)));
}
- SmallString<20> hash;
+ std::array<uint8_t, 20> hash;
};
//===----------------------------------------------------------------------===//
More information about the llvm-commits
mailing list