diff options
Diffstat (limited to 'src/leveldb/util/coding.h')
-rw-r--r-- | src/leveldb/util/coding.h | 136 |
1 files changed, 98 insertions, 38 deletions
diff --git a/src/leveldb/util/coding.h b/src/leveldb/util/coding.h index 3993c4a755..1983ae7173 100644 --- a/src/leveldb/util/coding.h +++ b/src/leveldb/util/coding.h @@ -10,87 +10,147 @@ #ifndef STORAGE_LEVELDB_UTIL_CODING_H_ #define STORAGE_LEVELDB_UTIL_CODING_H_ -#include <stdint.h> -#include <string.h> +#include <cstdint> +#include <cstring> #include <string> + #include "leveldb/slice.h" #include "port/port.h" namespace leveldb { // Standard Put... routines append to a string -extern void PutFixed32(std::string* dst, uint32_t value); -extern void PutFixed64(std::string* dst, uint64_t value); -extern void PutVarint32(std::string* dst, uint32_t value); -extern void PutVarint64(std::string* dst, uint64_t value); -extern void PutLengthPrefixedSlice(std::string* dst, const Slice& value); +void PutFixed32(std::string* dst, uint32_t value); +void PutFixed64(std::string* dst, uint64_t value); +void PutVarint32(std::string* dst, uint32_t value); +void PutVarint64(std::string* dst, uint64_t value); +void PutLengthPrefixedSlice(std::string* dst, const Slice& value); // Standard Get... routines parse a value from the beginning of a Slice // and advance the slice past the parsed value. -extern bool GetVarint32(Slice* input, uint32_t* value); -extern bool GetVarint64(Slice* input, uint64_t* value); -extern bool GetLengthPrefixedSlice(Slice* input, Slice* result); +bool GetVarint32(Slice* input, uint32_t* value); +bool GetVarint64(Slice* input, uint64_t* value); +bool GetLengthPrefixedSlice(Slice* input, Slice* result); // Pointer-based variants of GetVarint... These either store a value // in *v and return a pointer just past the parsed value, or return -// NULL on error. These routines only look at bytes in the range +// nullptr on error. These routines only look at bytes in the range // [p..limit-1] -extern const char* GetVarint32Ptr(const char* p,const char* limit, uint32_t* v); -extern const char* GetVarint64Ptr(const char* p,const char* limit, uint64_t* v); +const char* GetVarint32Ptr(const char* p, const char* limit, uint32_t* v); +const char* GetVarint64Ptr(const char* p, const char* limit, uint64_t* v); // Returns the length of the varint32 or varint64 encoding of "v" -extern int VarintLength(uint64_t v); +int VarintLength(uint64_t v); // Lower-level versions of Put... that write directly into a character buffer +// and return a pointer just past the last byte written. // REQUIRES: dst has enough space for the value being written -extern void EncodeFixed32(char* dst, uint32_t value); -extern void EncodeFixed64(char* dst, uint64_t value); +char* EncodeVarint32(char* dst, uint32_t value); +char* EncodeVarint64(char* dst, uint64_t value); + +// TODO(costan): Remove port::kLittleEndian and the fast paths based on +// std::memcpy when clang learns to optimize the generic code, as +// described in https://bugs.llvm.org/show_bug.cgi?id=41761 +// +// The platform-independent code in DecodeFixed{32,64}() gets optimized to mov +// on x86 and ldr on ARM64, by both clang and gcc. However, only gcc optimizes +// the platform-independent code in EncodeFixed{32,64}() to mov / str. // Lower-level versions of Put... that write directly into a character buffer -// and return a pointer just past the last byte written. // REQUIRES: dst has enough space for the value being written -extern char* EncodeVarint32(char* dst, uint32_t value); -extern char* EncodeVarint64(char* dst, uint64_t value); + +inline void EncodeFixed32(char* dst, uint32_t value) { + uint8_t* const buffer = reinterpret_cast<uint8_t*>(dst); + + if (port::kLittleEndian) { + // Fast path for little-endian CPUs. All major compilers optimize this to a + // single mov (x86_64) / str (ARM) instruction. + std::memcpy(buffer, &value, sizeof(uint32_t)); + return; + } + + // Platform-independent code. + // Currently, only gcc optimizes this to a single mov / str instruction. + buffer[0] = static_cast<uint8_t>(value); + buffer[1] = static_cast<uint8_t>(value >> 8); + buffer[2] = static_cast<uint8_t>(value >> 16); + buffer[3] = static_cast<uint8_t>(value >> 24); +} + +inline void EncodeFixed64(char* dst, uint64_t value) { + uint8_t* const buffer = reinterpret_cast<uint8_t*>(dst); + + if (port::kLittleEndian) { + // Fast path for little-endian CPUs. All major compilers optimize this to a + // single mov (x86_64) / str (ARM) instruction. + std::memcpy(buffer, &value, sizeof(uint64_t)); + return; + } + + // Platform-independent code. + // Currently, only gcc optimizes this to a single mov / str instruction. + buffer[0] = static_cast<uint8_t>(value); + buffer[1] = static_cast<uint8_t>(value >> 8); + buffer[2] = static_cast<uint8_t>(value >> 16); + buffer[3] = static_cast<uint8_t>(value >> 24); + buffer[4] = static_cast<uint8_t>(value >> 32); + buffer[5] = static_cast<uint8_t>(value >> 40); + buffer[6] = static_cast<uint8_t>(value >> 48); + buffer[7] = static_cast<uint8_t>(value >> 56); +} // Lower-level versions of Get... that read directly from a character buffer // without any bounds checking. inline uint32_t DecodeFixed32(const char* ptr) { + const uint8_t* const buffer = reinterpret_cast<const uint8_t*>(ptr); + if (port::kLittleEndian) { - // Load the raw bytes + // Fast path for little-endian CPUs. All major compilers optimize this to a + // single mov (x86_64) / ldr (ARM) instruction. uint32_t result; - memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load + std::memcpy(&result, buffer, sizeof(uint32_t)); return result; - } else { - return ((static_cast<uint32_t>(static_cast<unsigned char>(ptr[0]))) - | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[1])) << 8) - | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[2])) << 16) - | (static_cast<uint32_t>(static_cast<unsigned char>(ptr[3])) << 24)); } + + // Platform-independent code. + // Clang and gcc optimize this to a single mov / ldr instruction. + return (static_cast<uint32_t>(buffer[0])) | + (static_cast<uint32_t>(buffer[1]) << 8) | + (static_cast<uint32_t>(buffer[2]) << 16) | + (static_cast<uint32_t>(buffer[3]) << 24); } inline uint64_t DecodeFixed64(const char* ptr) { + const uint8_t* const buffer = reinterpret_cast<const uint8_t*>(ptr); + if (port::kLittleEndian) { - // Load the raw bytes + // Fast path for little-endian CPUs. All major compilers optimize this to a + // single mov (x86_64) / ldr (ARM) instruction. uint64_t result; - memcpy(&result, ptr, sizeof(result)); // gcc optimizes this to a plain load + std::memcpy(&result, buffer, sizeof(uint64_t)); return result; - } else { - uint64_t lo = DecodeFixed32(ptr); - uint64_t hi = DecodeFixed32(ptr + 4); - return (hi << 32) | lo; } + + // Platform-independent code. + // Clang and gcc optimize this to a single mov / ldr instruction. + return (static_cast<uint64_t>(buffer[0])) | + (static_cast<uint64_t>(buffer[1]) << 8) | + (static_cast<uint64_t>(buffer[2]) << 16) | + (static_cast<uint64_t>(buffer[3]) << 24) | + (static_cast<uint64_t>(buffer[4]) << 32) | + (static_cast<uint64_t>(buffer[5]) << 40) | + (static_cast<uint64_t>(buffer[6]) << 48) | + (static_cast<uint64_t>(buffer[7]) << 56); } // Internal routine for use by fallback path of GetVarint32Ptr -extern const char* GetVarint32PtrFallback(const char* p, - const char* limit, - uint32_t* value); -inline const char* GetVarint32Ptr(const char* p, - const char* limit, +const char* GetVarint32PtrFallback(const char* p, const char* limit, + uint32_t* value); +inline const char* GetVarint32Ptr(const char* p, const char* limit, uint32_t* value) { if (p < limit) { - uint32_t result = *(reinterpret_cast<const unsigned char*>(p)); + uint32_t result = *(reinterpret_cast<const uint8_t*>(p)); if ((result & 128) == 0) { *value = result; return p + 1; |