mirror of
https://github.com/bitcoin/bitcoin.git
synced 2025-01-11 20:32:35 -03:00
1884ce2f4c
6544ea5035
refactor: Block unsafe fs::path std::string conversion calls (Russell Yanofsky)b39a477ec6
refactor: Add fs::PathToString, fs::PathFromString, u8string, u8path functions (Russell Yanofsky) Pull request description: The `fs::path` class has a `std::string` constructor which will implicitly convert from strings. Implicit conversions like this are not great in general because they can hide complexity and inefficiencies in the code, but this case is especially bad, because after the transition from `boost::filesystem` to `std::filesystem` in #20744 the behavior of this constructor on windows will be more complicated and can mangle path strings. The `fs::path` class also has a `.string()` method which is inverse of the constructor and has the same problems. Fix this by replacing the unsafe method calls with `PathToString` and `PathFromString` function calls, and by forbidding unsafe method calls in the future. ACKs for top commit: kiminuo: ACK6544ea5035
laanwj: Code review ACK6544ea5035
hebasto: re-ACK6544ea5035
, only added `fsbridge_stem` test case, updated comment, and rebased since my [previous](https://github.com/bitcoin/bitcoin/pull/22937#pullrequestreview-765503126) review. Verified with the following command: Tree-SHA512: c36324740eb4ee55151146626166c00d5ccc4b6f3df777e75c112bcb4d1db436c1d9cc8c29a1e7fb96051457d317961ab42e6c380c3be2771d135771b2b49fa0
259 lines
8.9 KiB
C++
259 lines
8.9 KiB
C++
// Copyright (c) 2012-2019 The Bitcoin Core developers
|
|
// Distributed under the MIT software license, see the accompanying
|
|
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
|
|
|
#include <dbwrapper.h>
|
|
|
|
#include <memory>
|
|
#include <random.h>
|
|
|
|
#include <leveldb/cache.h>
|
|
#include <leveldb/env.h>
|
|
#include <leveldb/filter_policy.h>
|
|
#include <memenv.h>
|
|
#include <stdint.h>
|
|
#include <algorithm>
|
|
|
|
class CBitcoinLevelDBLogger : public leveldb::Logger {
|
|
public:
|
|
// This code is adapted from posix_logger.h, which is why it is using vsprintf.
|
|
// Please do not do this in normal code
|
|
void Logv(const char * format, va_list ap) override {
|
|
if (!LogAcceptCategory(BCLog::LEVELDB)) {
|
|
return;
|
|
}
|
|
char buffer[500];
|
|
for (int iter = 0; iter < 2; iter++) {
|
|
char* base;
|
|
int bufsize;
|
|
if (iter == 0) {
|
|
bufsize = sizeof(buffer);
|
|
base = buffer;
|
|
}
|
|
else {
|
|
bufsize = 30000;
|
|
base = new char[bufsize];
|
|
}
|
|
char* p = base;
|
|
char* limit = base + bufsize;
|
|
|
|
// Print the message
|
|
if (p < limit) {
|
|
va_list backup_ap;
|
|
va_copy(backup_ap, ap);
|
|
// Do not use vsnprintf elsewhere in bitcoin source code, see above.
|
|
p += vsnprintf(p, limit - p, format, backup_ap);
|
|
va_end(backup_ap);
|
|
}
|
|
|
|
// Truncate to available space if necessary
|
|
if (p >= limit) {
|
|
if (iter == 0) {
|
|
continue; // Try again with larger buffer
|
|
}
|
|
else {
|
|
p = limit - 1;
|
|
}
|
|
}
|
|
|
|
// Add newline if necessary
|
|
if (p == base || p[-1] != '\n') {
|
|
*p++ = '\n';
|
|
}
|
|
|
|
assert(p <= limit);
|
|
base[std::min(bufsize - 1, (int)(p - base))] = '\0';
|
|
LogPrintf("leveldb: %s", base); /* Continued */
|
|
if (base != buffer) {
|
|
delete[] base;
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
};
|
|
|
|
static void SetMaxOpenFiles(leveldb::Options *options) {
|
|
// On most platforms the default setting of max_open_files (which is 1000)
|
|
// is optimal. On Windows using a large file count is OK because the handles
|
|
// do not interfere with select() loops. On 64-bit Unix hosts this value is
|
|
// also OK, because up to that amount LevelDB will use an mmap
|
|
// implementation that does not use extra file descriptors (the fds are
|
|
// closed after being mmap'ed).
|
|
//
|
|
// Increasing the value beyond the default is dangerous because LevelDB will
|
|
// fall back to a non-mmap implementation when the file count is too large.
|
|
// On 32-bit Unix host we should decrease the value because the handles use
|
|
// up real fds, and we want to avoid fd exhaustion issues.
|
|
//
|
|
// See PR #12495 for further discussion.
|
|
|
|
int default_open_files = options->max_open_files;
|
|
#ifndef WIN32
|
|
if (sizeof(void*) < 8) {
|
|
options->max_open_files = 64;
|
|
}
|
|
#endif
|
|
LogPrint(BCLog::LEVELDB, "LevelDB using max_open_files=%d (default=%d)\n",
|
|
options->max_open_files, default_open_files);
|
|
}
|
|
|
|
static leveldb::Options GetOptions(size_t nCacheSize)
|
|
{
|
|
leveldb::Options options;
|
|
options.block_cache = leveldb::NewLRUCache(nCacheSize / 2);
|
|
options.write_buffer_size = nCacheSize / 4; // up to two write buffers may be held in memory simultaneously
|
|
options.filter_policy = leveldb::NewBloomFilterPolicy(10);
|
|
options.compression = leveldb::kNoCompression;
|
|
options.info_log = new CBitcoinLevelDBLogger();
|
|
if (leveldb::kMajorVersion > 1 || (leveldb::kMajorVersion == 1 && leveldb::kMinorVersion >= 16)) {
|
|
// LevelDB versions before 1.16 consider short writes to be corruption. Only trigger error
|
|
// on corruption in later versions.
|
|
options.paranoid_checks = true;
|
|
}
|
|
SetMaxOpenFiles(&options);
|
|
return options;
|
|
}
|
|
|
|
CDBWrapper::CDBWrapper(const fs::path& path, size_t nCacheSize, bool fMemory, bool fWipe, bool obfuscate)
|
|
: m_name{fs::PathToString(path.stem())}
|
|
{
|
|
penv = nullptr;
|
|
readoptions.verify_checksums = true;
|
|
iteroptions.verify_checksums = true;
|
|
iteroptions.fill_cache = false;
|
|
syncoptions.sync = true;
|
|
options = GetOptions(nCacheSize);
|
|
options.create_if_missing = true;
|
|
if (fMemory) {
|
|
penv = leveldb::NewMemEnv(leveldb::Env::Default());
|
|
options.env = penv;
|
|
} else {
|
|
if (fWipe) {
|
|
LogPrintf("Wiping LevelDB in %s\n", fs::PathToString(path));
|
|
leveldb::Status result = leveldb::DestroyDB(fs::PathToString(path), options);
|
|
dbwrapper_private::HandleError(result);
|
|
}
|
|
TryCreateDirectories(path);
|
|
LogPrintf("Opening LevelDB in %s\n", fs::PathToString(path));
|
|
}
|
|
leveldb::Status status = leveldb::DB::Open(options, fs::PathToString(path), &pdb);
|
|
dbwrapper_private::HandleError(status);
|
|
LogPrintf("Opened LevelDB successfully\n");
|
|
|
|
if (gArgs.GetBoolArg("-forcecompactdb", false)) {
|
|
LogPrintf("Starting database compaction of %s\n", fs::PathToString(path));
|
|
pdb->CompactRange(nullptr, nullptr);
|
|
LogPrintf("Finished database compaction of %s\n", fs::PathToString(path));
|
|
}
|
|
|
|
// The base-case obfuscation key, which is a noop.
|
|
obfuscate_key = std::vector<unsigned char>(OBFUSCATE_KEY_NUM_BYTES, '\000');
|
|
|
|
bool key_exists = Read(OBFUSCATE_KEY_KEY, obfuscate_key);
|
|
|
|
if (!key_exists && obfuscate && IsEmpty()) {
|
|
// Initialize non-degenerate obfuscation if it won't upset
|
|
// existing, non-obfuscated data.
|
|
std::vector<unsigned char> new_key = CreateObfuscateKey();
|
|
|
|
// Write `new_key` so we don't obfuscate the key with itself
|
|
Write(OBFUSCATE_KEY_KEY, new_key);
|
|
obfuscate_key = new_key;
|
|
|
|
LogPrintf("Wrote new obfuscate key for %s: %s\n", fs::PathToString(path), HexStr(obfuscate_key));
|
|
}
|
|
|
|
LogPrintf("Using obfuscation key for %s: %s\n", fs::PathToString(path), HexStr(obfuscate_key));
|
|
}
|
|
|
|
CDBWrapper::~CDBWrapper()
|
|
{
|
|
delete pdb;
|
|
pdb = nullptr;
|
|
delete options.filter_policy;
|
|
options.filter_policy = nullptr;
|
|
delete options.info_log;
|
|
options.info_log = nullptr;
|
|
delete options.block_cache;
|
|
options.block_cache = nullptr;
|
|
delete penv;
|
|
options.env = nullptr;
|
|
}
|
|
|
|
bool CDBWrapper::WriteBatch(CDBBatch& batch, bool fSync)
|
|
{
|
|
const bool log_memory = LogAcceptCategory(BCLog::LEVELDB);
|
|
double mem_before = 0;
|
|
if (log_memory) {
|
|
mem_before = DynamicMemoryUsage() / 1024.0 / 1024;
|
|
}
|
|
leveldb::Status status = pdb->Write(fSync ? syncoptions : writeoptions, &batch.batch);
|
|
dbwrapper_private::HandleError(status);
|
|
if (log_memory) {
|
|
double mem_after = DynamicMemoryUsage() / 1024.0 / 1024;
|
|
LogPrint(BCLog::LEVELDB, "WriteBatch memory usage: db=%s, before=%.1fMiB, after=%.1fMiB\n",
|
|
m_name, mem_before, mem_after);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
size_t CDBWrapper::DynamicMemoryUsage() const
|
|
{
|
|
std::string memory;
|
|
std::optional<size_t> parsed;
|
|
if (!pdb->GetProperty("leveldb.approximate-memory-usage", &memory) || !(parsed = ToIntegral<size_t>(memory))) {
|
|
LogPrint(BCLog::LEVELDB, "Failed to get approximate-memory-usage property\n");
|
|
return 0;
|
|
}
|
|
return parsed.value();
|
|
}
|
|
|
|
// Prefixed with null character to avoid collisions with other keys
|
|
//
|
|
// We must use a string constructor which specifies length so that we copy
|
|
// past the null-terminator.
|
|
const std::string CDBWrapper::OBFUSCATE_KEY_KEY("\000obfuscate_key", 14);
|
|
|
|
const unsigned int CDBWrapper::OBFUSCATE_KEY_NUM_BYTES = 8;
|
|
|
|
/**
|
|
* Returns a string (consisting of 8 random bytes) suitable for use as an
|
|
* obfuscating XOR key.
|
|
*/
|
|
std::vector<unsigned char> CDBWrapper::CreateObfuscateKey() const
|
|
{
|
|
std::vector<uint8_t> ret(OBFUSCATE_KEY_NUM_BYTES);
|
|
GetRandBytes(ret.data(), OBFUSCATE_KEY_NUM_BYTES);
|
|
return ret;
|
|
}
|
|
|
|
bool CDBWrapper::IsEmpty()
|
|
{
|
|
std::unique_ptr<CDBIterator> it(NewIterator());
|
|
it->SeekToFirst();
|
|
return !(it->Valid());
|
|
}
|
|
|
|
CDBIterator::~CDBIterator() { delete piter; }
|
|
bool CDBIterator::Valid() const { return piter->Valid(); }
|
|
void CDBIterator::SeekToFirst() { piter->SeekToFirst(); }
|
|
void CDBIterator::Next() { piter->Next(); }
|
|
|
|
namespace dbwrapper_private {
|
|
|
|
void HandleError(const leveldb::Status& status)
|
|
{
|
|
if (status.ok())
|
|
return;
|
|
const std::string errmsg = "Fatal LevelDB error: " + status.ToString();
|
|
LogPrintf("%s\n", errmsg);
|
|
LogPrintf("You can use -debug=leveldb to get more complete diagnostic messages\n");
|
|
throw dbwrapper_error(errmsg);
|
|
}
|
|
|
|
const std::vector<unsigned char>& GetObfuscateKey(const CDBWrapper &w)
|
|
{
|
|
return w.obfuscate_key;
|
|
}
|
|
|
|
} // namespace dbwrapper_private
|