Merge pull request #4133 from akyrtzi/stable-cherry-blake3

[stable/20211026] Cherry-pick the `BLAKE3` hashing function implementation

Author: akyrtzi

llvm/include/llvm-c/blake3.h

@@ -0,0 +1,79 @@
+/*===-- llvm-c/blake3.h - BLAKE3 C Interface ----------------------*- C -*-===*\
+|*                                                                            *|
+|* Released into the public domain with CC0 1.0                               *|
+|* See 'llvm/lib/Support/BLAKE3/LICENSE' for info.                            *|
+|* SPDX-License-Identifier: CC0-1.0                                           *|
+|*                                                                            *|
+|*===----------------------------------------------------------------------===*|
+|*                                                                            *|
+|* This header declares the C interface to LLVM's BLAKE3 implementation.      *|
+|* Original BLAKE3 C API: https://github.com/BLAKE3-team/BLAKE3/tree/1.3.1/c  *|
+|*                                                                            *|
+|* Symbols are prefixed with 'llvm' to avoid a potential conflict with        *|
+|* another BLAKE3 version within the same program.                            *|
+|*                                                                            *|
+\*===----------------------------------------------------------------------===*/
+
+#ifndef LLVM_C_BLAKE3_H
+#define LLVM_C_BLAKE3_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define LLVM_BLAKE3_VERSION_STRING "1.3.1"
+#define LLVM_BLAKE3_KEY_LEN 32
+#define LLVM_BLAKE3_OUT_LEN 32
+#define LLVM_BLAKE3_BLOCK_LEN 64
+#define LLVM_BLAKE3_CHUNK_LEN 1024
+#define LLVM_BLAKE3_MAX_DEPTH 54
+
+// This struct is a private implementation detail. It has to be here because
+// it's part of llvm_blake3_hasher below.
+typedef struct {
+  uint32_t cv[8];
+  uint64_t chunk_counter;
+  uint8_t buf[LLVM_BLAKE3_BLOCK_LEN];
+  uint8_t buf_len;
+  uint8_t blocks_compressed;
+  uint8_t flags;
+} llvm_blake3_chunk_state;
+
+typedef struct {
+  uint32_t key[8];
+  llvm_blake3_chunk_state chunk;
+  uint8_t cv_stack_len;
+  // The stack size is MAX_DEPTH + 1 because we do lazy merging. For example,
+  // with 7 chunks, we have 3 entries in the stack. Adding an 8th chunk
+  // requires a 4th entry, rather than merging everything down to 1, because we
+  // don't know whether more input is coming. This is different from how the
+  // reference implementation does things.
+  uint8_t cv_stack[(LLVM_BLAKE3_MAX_DEPTH + 1) * LLVM_BLAKE3_OUT_LEN];
+} llvm_blake3_hasher;
+
+const char *llvm_blake3_version(void);
+void llvm_blake3_hasher_init(llvm_blake3_hasher *self);
+void llvm_blake3_hasher_init_keyed(llvm_blake3_hasher *self,
+                                   const uint8_t key[LLVM_BLAKE3_KEY_LEN]);
+void llvm_blake3_hasher_init_derive_key(llvm_blake3_hasher *self,
+                                        const char *context);
+void llvm_blake3_hasher_init_derive_key_raw(llvm_blake3_hasher *self,
+                                            const void *context,
+                                            size_t context_len);
+void llvm_blake3_hasher_update(llvm_blake3_hasher *self, const void *input,
+                               size_t input_len);
+void llvm_blake3_hasher_finalize(const llvm_blake3_hasher *self, uint8_t *out,
+                                 size_t out_len);
+void llvm_blake3_hasher_finalize_seek(const llvm_blake3_hasher *self,
+                                      uint64_t seek, uint8_t *out,
+                                      size_t out_len);
+void llvm_blake3_hasher_reset(llvm_blake3_hasher *self);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* LLVM_C_BLAKE3_H */

llvm/include/llvm/Support/BLAKE3.h

@@ -0,0 +1,87 @@
+//==- BLAKE3.h - BLAKE3 C++ wrapper for LLVM ---------------------*- C++ -*-==//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This is a C++ wrapper of the BLAKE3 C interface.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_BLAKE3_H
+#define LLVM_SUPPORT_BLAKE3_H
+
+#include "llvm-c/blake3.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/StringRef.h"
+
+namespace llvm {
+
+/// The constant \p LLVM_BLAKE3_OUT_LEN provides the default output length,
+/// 32 bytes, which is recommended for most callers.
+///
+/// Outputs shorter than the default length of 32 bytes (256 bits) provide
+/// less security. An N-bit BLAKE3 output is intended to provide N bits of
+/// first and second preimage resistance and N/2 bits of collision
+/// resistance, for any N up to 256. Longer outputs don't provide any
+/// additional security.
+///
+/// Shorter BLAKE3 outputs are prefixes of longer ones. Explicitly
+/// requesting a short output is equivalent to truncating the default-length
+/// output.
+template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
+using BLAKE3Result = std::array<uint8_t, NumBytes>;
+
+/// A class that wrap the BLAKE3 algorithm.
+class BLAKE3 {
+public:
+  BLAKE3() { init(); }
+
+  /// Reinitialize the internal state
+  void init() { llvm_blake3_hasher_init(&Hasher); }
+
+  /// Digest more data.
+  void update(ArrayRef<uint8_t> Data) {
+    llvm_blake3_hasher_update(&Hasher, Data.data(), Data.size());
+  }
+
+  /// Digest more data.
+  void update(StringRef Str) {
+    llvm_blake3_hasher_update(&Hasher, Str.data(), Str.size());
+  }
+
+  /// 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 <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
+  void final(BLAKE3Result<NumBytes> &Result) {
+    llvm_blake3_hasher_finalize(&Hasher, Result.data(), Result.size());
+  }
+
+  /// 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 <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
+  BLAKE3Result<NumBytes> final() {
+    BLAKE3Result<NumBytes> Result;
+    llvm_blake3_hasher_finalize(&Hasher, Result.data(), Result.size());
+    return Result;
+  }
+
+  /// Returns a BLAKE3 hash for the given data.
+  template <size_t NumBytes = LLVM_BLAKE3_OUT_LEN>
+  static BLAKE3Result<NumBytes> hash(ArrayRef<uint8_t> Data) {
+    BLAKE3 Hasher;
+    Hasher.update(Data);
+    return Hasher.final<NumBytes>();
+  }
+
+private:
+  llvm_blake3_hasher Hasher;
+};
+
+} // namespace llvm
+
+#endif

llvm/lib/Support/BLAKE3/.clang-format

@@ -0,0 +1,2 @@
+DisableFormat: true
+SortIncludes: Never

llvm/lib/Support/BLAKE3/CMakeLists.txt

@@ -0,0 +1,56 @@
+set(LLVM_BLAKE3_FILES
+  blake3.c
+  blake3_dispatch.c
+  blake3_portable.c
+)
+
+# The BLAKE3 team recommends using the assembly versions, from the README:
+#
+# "For each of the x86 SIMD instruction sets, four versions are available:
+# three flavors of assembly (Unix, Windows MSVC, and Windows GNU) and one
+# version using C intrinsics. The assembly versions are generally
+# preferred. They perform better, they perform more consistently across
+# different compilers, and they build more quickly."
+
+if (MSVC)
+  check_symbol_exists(_M_X64 "" IS_X64)
+  check_symbol_exists(_M_ARM64 "" IS_ARM64)
+else()
+  check_symbol_exists(__x86_64__ "" IS_X64)
+  check_symbol_exists(__aarch64__ "" IS_ARM64)
+endif()
+
+if (IS_X64)
+  if (MSVC)
+    enable_language(ASM_MASM)
+    list(APPEND LLVM_BLAKE3_FILES
+      blake3_sse2_x86-64_windows_msvc.asm
+      blake3_sse41_x86-64_windows_msvc.asm
+      blake3_avx2_x86-64_windows_msvc.asm
+      blake3_avx512_x86-64_windows_msvc.asm
+    )
+  elseif(WIN32)
+    list(APPEND LLVM_BLAKE3_FILES
+      blake3_sse2_x86-64_windows_gnu.S
+      blake3_sse41_x86-64_windows_gnu.S
+      blake3_avx2_x86-64_windows_gnu.S
+      blake3_avx512_x86-64_windows_gnu.S
+    )
+  else()
+    list(APPEND LLVM_BLAKE3_FILES
+      blake3_sse2_x86-64_unix.S
+      blake3_sse41_x86-64_unix.S
+      blake3_avx2_x86-64_unix.S
+      blake3_avx512_x86-64_unix.S
+    )
+  endif()
+endif()
+
+if (IS_ARM64)
+  list(APPEND LLVM_BLAKE3_FILES
+    blake3_neon.c
+  )
+endif()
+
+add_library(LLVMSupportBlake3 OBJECT EXCLUDE_FROM_ALL ${LLVM_BLAKE3_FILES})
+llvm_update_compile_flags(LLVMSupportBlake3)