fix: close TOCTOU window between blob eviction commit and unlink
StoreSource now hashes content itself and holds the per-hash contentLock across the whole store (file write plus accounting row inserts); evictSourceBlob holds the same lock across its whole operation (row deletion transaction through file unlink). A concurrent store and eviction of identical content bytes can no longer interleave: either runs to completion before the other starts, so a fresh row can never be left pointing at a file the other side is mid-unlink on. ContentStorage gains StoreHashed for callers that need the hash before writing; Store is refactored to share the write-if-absent logic with it, with no change to its existing behavior or signature. internal/imgcache/eviction_test.go: TestEvictSourceBlobExcludesConcurrentStoreOfIdenticalContent proves it: pauses eviction (via evictSourceBlobTestHook) in the exact window between commit and unlink, asserts a concurrent StoreSource for identical content blocks rather than completing, then verifies no dangling reference and that the store's data survives once eviction releases the hash.
This commit is contained in:
@@ -65,24 +65,49 @@ func (s *ContentStorage) Store(r io.Reader) (hash ContentHash, size int64, err e
|
||||
hash = ContentHash(hex.EncodeToString(h[:]))
|
||||
size = int64(len(data))
|
||||
|
||||
if err := s.writeIfAbsent(hash, data); err != nil {
|
||||
return "", 0, err
|
||||
}
|
||||
|
||||
return hash, size, nil
|
||||
}
|
||||
|
||||
// StoreHashed writes pre-hashed content to storage at the path derived
|
||||
// from hash, without recomputing it. Callers that already know the
|
||||
// hash before writing (e.g. because they must hold a hash-keyed lock
|
||||
// across the whole store operation) use this instead of Store. Like
|
||||
// Store, it is idempotent: content already on disk at that path is
|
||||
// left untouched.
|
||||
func (s *ContentStorage) StoreHashed(hash ContentHash, data []byte) (size int64, err error) {
|
||||
if err := s.writeIfAbsent(hash, data); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
return int64(len(data)), nil
|
||||
}
|
||||
|
||||
// writeIfAbsent writes data to the path derived from hash, unless
|
||||
// content already exists there, via a temp-file-plus-rename so
|
||||
// concurrent readers never observe a partial file.
|
||||
func (s *ContentStorage) writeIfAbsent(hash ContentHash, data []byte) (err error) {
|
||||
// Build path: <basedir>/<ab>/<cd>/<hash>
|
||||
path := s.hashToPath(hash)
|
||||
|
||||
// Check if already exists
|
||||
if _, err := os.Stat(path); err == nil {
|
||||
return hash, size, nil
|
||||
if _, statErr := os.Stat(path); statErr == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Create directory structure
|
||||
dir := filepath.Dir(path)
|
||||
if err := os.MkdirAll(dir, StorageDirPerm); err != nil {
|
||||
return "", 0, fmt.Errorf("failed to create directory: %w", err)
|
||||
return fmt.Errorf("failed to create directory: %w", err)
|
||||
}
|
||||
|
||||
// Write to temp file first, then rename for atomicity
|
||||
tmpFile, err := os.CreateTemp(dir, ".tmp-*")
|
||||
if err != nil {
|
||||
return "", 0, fmt.Errorf("failed to create temp file: %w", err)
|
||||
return fmt.Errorf("failed to create temp file: %w", err)
|
||||
}
|
||||
tmpPath := tmpFile.Name()
|
||||
|
||||
@@ -95,20 +120,20 @@ func (s *ContentStorage) Store(r io.Reader) (hash ContentHash, size int64, err e
|
||||
if _, err := tmpFile.Write(data); err != nil {
|
||||
_ = tmpFile.Close()
|
||||
|
||||
return "", 0, fmt.Errorf("failed to write content: %w", err)
|
||||
return fmt.Errorf("failed to write content: %w", err)
|
||||
}
|
||||
|
||||
if err := tmpFile.Close(); err != nil {
|
||||
return "", 0, fmt.Errorf("failed to close temp file: %w", err)
|
||||
return fmt.Errorf("failed to close temp file: %w", err)
|
||||
}
|
||||
|
||||
// Atomic rename
|
||||
//nolint:gosec // G703: paths from internal SHA256 hashes
|
||||
if err := os.Rename(filepath.Clean(tmpPath), filepath.Clean(path)); err != nil {
|
||||
return "", 0, fmt.Errorf("failed to rename temp file: %w", err)
|
||||
return fmt.Errorf("failed to rename temp file: %w", err)
|
||||
}
|
||||
|
||||
return hash, size, nil
|
||||
return nil
|
||||
}
|
||||
|
||||
// Load returns a reader for the content with the given hash.
|
||||
|
||||
Reference in New Issue
Block a user