Merge #17398: build: Update leveldb to 1.22+

677fb8e92380d4deb6a3753047c01f7cf7b5af91 test: Add ubsan surpression for crc32c (Wladimir J. van der Laan)
8e68bb1ddeca504bedd40aee8492b5478a88c1e5 build: Disable msvc warning 4722 for leveldb build (Aaron Clauson)
be23949765e1b2e050574c6c2a136658a89dee5d build: MSVC changes for leveldb update (Aaron Clauson)
9ebdf047578f0da7e6578d0c51c32f55e84ac157 build: CRC32C build system integration (Wladimir J. van der Laan)
402252a8081e25f22aa1a5c60708714cf1d84ec4 build: Add LCOV exception for crc32c (Wladimir J. van der Laan)
3a037d0067c2c12a1c2c800fb85613a0a2911253 test: Add crc32c exception to various linters and generation scripts (Wladimir J. van der Laan)
84ff1b2076ef91ce688930d0aa0a7f4078ef3e1d test: Add crc32c to subtree check linter (Wladimir J. van der Laan)
7cf13a513409c18d18dff2f6203b3630937b487d doc: Add crc32c subtree to developer notes (Wladimir J. van der Laan)
24d02a9ac00a82d172b171f73554a882df264c80 build: Update build system for new leveldb (Wladimir J. van der Laan)
2e1819311a59fb5cb26e3ca50a510bfe01358350 Squashed 'src/crc32c/' content from commit 224988680f7673cd7c769963d4035cb315aa3388 (Wladimir J. van der Laan)
66480821b36c839ab7615cb9309850015bceadb0 Squashed 'src/leveldb/' changes from f545dfabff4c2e9836efed094dba99a34fbc6b88..f8ae182c1e5176d12e816fb2217ae33a5472fdd7 (Wladimir J. van der Laan)

Pull request description:

  This updates leveldb to currently newest upstream commit https://github.com/bitcoin-core/leveldb/commit/0c40829872a9f00f38e11dc370ff8adb3e19f25b:

  - CRC32C hardware acceleration is now an external library [crc32c](https://github.com/google/crc32c). This adds acceleration on ARM, and should be faster on x86 because of using prefetch. It also makes it easy to support similar instruction sets on other platforms in the future.
  - Thread handling uses C++11, instead of platform specific code.
  - Native windows environment was added. No need to maintain our own hacky one, anymore.
  - Upstream now builds using CMake. This doesn't mean we need to use that (phew), but internal configuration changed to a a series of checks, instead of OS profiles. This means the blanket error "Cannot build leveldb for $host. Please file a bug report' is removed.

  All changes: https://github.com/google/leveldb/compare/a53934a3ae1244679f812d998a4f16f2c7f309a6...0c40829872a9f00f38e11dc370ff8adb3e19f25b

  Pretty much all our changes have been subsumed by upstream, so we figured it was cleaner to start over with a new branch from upstream with the still-relevant patches applied: https://github.com/bitcoin-core/leveldb/tree/bitcoin-fork-new

  There's quite some testing to be done (see below). See https://github.com/bitcoin-core/leveldb/issues/25 and https://github.com/bitcoin-core/leveldb/pull/26 for more history and context.

  TODO:
  - [x] Subtree `crc32c`
  - [x] Make linters happy about crc32 subtree
  - [x] Integrate `crc32c` library into build system
  - [x] MSVC build system

ACKs for top commit:
  sipa:
    ACK 677fb8e92380d4deb6a3753047c01f7cf7b5af91

Tree-SHA512: 37ee92a750e053e924bc4626b12bb3fd81faa9f8c5ebaa343931fee810c45ba05aa6051fdea82535fa351bf2be7297801b98af9469865fc5ead771650a5d6240

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;