sneak/vaultik
1
0
Fork 0
Code Issues 14 Pull Requests 2 Actions 1 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/vaultik:a99f9877d6197180306ffec743a7f12a64c4ffbf
Branches Tags
sneak/vaultik:main sneak/vaultik:issue-177-complete-after-export sneak/vaultik:next sneak/vaultik:feature/daemon-mode
..
compare: sneak/vaultik:next
Branches Tags
sneak/vaultik:issue-177-complete-after-export sneak/vaultik:next sneak/vaultik:main sneak/vaultik:feature/daemon-mode
33 Commits
a99f9877d6 .. next
Author SHA1 Message Date
clawbot 1548c0f933 Correct the security claims in docs and comments, and record the accepted risks (closes #171)
check / check (pull_request) Successful in 1m58s
Details
check / check (push) Successful in 2m49s
Details 
Docs and comments only; no behaviour change. Corrects ten overclaims the security review found: snapshot names are hashed but the hash uses no secret, so a guessed hostname and name can be confirmed; a blob is named by hex(SHA256(SHA256(uncompressed contents))), stated once in docs/REPOSTRUCTURE.md and referenced elsewhere; double hashing does not hide known content (blob packing does); age uses ChaCha20-Poly1305, not XChaCha20; encryption is required, not optional; a snapshot is marked complete before its metadata is uploaded; the export comment now matches its only caller; deep verify detects corruption, not authorship; adding a recipient does not reach existing data; restore examples target a user-owned directory.

Adds an Accepted Risks subsection under Security Considerations with the seven documented risks, cross-referenced from the README.

Model: opus-4-8
 2026-09-22 19:28:31 +02:00
clawbot c3bec7d3aa Reject a metadata database truncated to the age header and nonce (closes #152)
check / check (push) Successful in 2m5s
Details
check / check (pull_request) Successful in 2m28s
Details 
An object holding just the age header and its 16-byte nonce decrypts without error: the truncated read surfaces as io.ErrUnexpectedEOF at the age layer, which the zstd decoder maps to a clean EOF at frame start. blobgen then reported zero bytes and no error, so a truncated stream was indistinguishable from a valid empty one, and the metadata database export slipped through -- restore built a fresh schema on the empty file and reported success.

blobgen.Reader.Read now, on EOF, reads once more from the age reader and surfaces io.ErrUnexpectedEOF unless that read is (0, io.EOF), the state a genuine end leaves. downloadSnapshotDB additionally rejects a zero-length decrypted database before any schema is built.

Model: opus-4-8
 2026-09-22 18:11:57 +02:00
clawbot 1244c9e48d Bound download expansion and escape control chars on the terminal (closes #164)
check / check (pull_request) Successful in 1m47s
Details
check / check (push) Successful in 3m11s
Details 
Objects fetched from the store are untrusted; several decode paths let one expand or print without limit.

- blobgen.LimitReader errors past a byte cap (not io.LimitReader silent EOF). DecodeManifest reads through caps on both compressed input and decompressed output, far above any real manifest, so json.Decode cannot buffer a compressible bomb. FetchAndDecryptBlob bounds decompression to the blob recorded uncompressed_size (not the restoring host blob_size_limit).
- downloadSnapshotDB streams straight from storage to its temp file with io.Copy, replacing two ReadAll calls that held the whole database twice.
- FetchBlob drops the per-blob Stat round-trip, its expectedSize parameter and returned size, all of which only fed a debug log.
- TTYHandler and ui.Writer escape control characters in messages, attribute keys/values, and rendered identifiers/paths before colour codes are applied, so a crafted value cannot drive the terminal.

Model: opus-4-8
 2026-09-22 17:00:35 +02:00
clawbot 82c51a5337 Validate blob hashes, offsets and lengths from the destination (closes #155)
check / check (pull_request) Successful in 1m22s
Details
check / check (push) Successful in 3m30s
Details 
A blob hash read back from the downloaded snapshot database or the store listing was trusted unchecked. A hostile remote could set a hash such as "aa/../../etc" and have a decrypted blob written outside the cache directory, or feed a short or negative value that panicked a command.

blobDiskCache.path now refuses any key with a path separator, and ReadAt rejects a negative offset or length, bounding so a sum cannot overflow past the check. A new isBlobHash helper gates FetchBlob, shallow and deep verify, and restore: buildBlobIndexes rejects every hash from the snapshot database before any fetch. The blobs/ and metadata/ listings skip a non-conforming name, and short-hash prefixes in log and error text go through a panic-safe shortHash helper.

Model: opus-4-8
 2026-09-22 16:11:28 +02:00
clawbot d88ed64489 Parse the age identity key once and accept every identity in it (closes #165)
check / check (pull_request) Successful in 2m41s
Details
check / check (push) Successful in 2m56s
Details 
Restore and verify --deep now parse the configured age secret key a single time through a new helper that uses age.ParseIdentities and hands every identity to age.Decrypt. A key file with several identities (a whole age-keygen file) is fully accepted, so a blob encrypted to any of its recipients decrypts, not just the first.

The helper is the first step of both commands, so a missing or unparseable key fails before anything is downloaded. Its error names the config source and never echoes the key value. config.extractAgeSecretKey and its silent fallback are removed; the key is stored raw and parsed only where decryption happens. README, the restore help, and the missing-key error now read the key from a file with \$(cat ...) rather than typed literally, keeping it out of shell history.

Model: opus-4-8
 2026-09-22 15:45:27 +02:00
clawbot bd9656dbd4 Reject a decrypted snapshot database that is not the requested one (closes #156)
check / check (push) Successful in 1m26s
Details
check / check (pull_request) Successful in 2m51s
Details 
Restore and deep verify downloaded and decrypted metadata/<key>/db.zst.age by object name alone. age decryption proves the database is readable, not that it is the snapshot that was asked for: an attacker who swaps in another valid db.zst.age could redirect the operation, and deep verify with a swapped database plus an empty manifest reported success with zero blobs verified.

After the database is opened, both paths now confirm its identity: an exported per-snapshot database holds one snapshot row, and a snapshot remote key derives from that row ID, so the database is the requested one exactly when its sole snapshot hashes back to the remote key fetched. The shared check lives in verifySnapshotDBIdentity, backed by a new SnapshotRepository.GetOnlySnapshot.

Model: opus-4-8
 2026-09-22 15:01:02 +02:00
clawbot 7e611b95db Check blob sizes and the database in shallow verify (closes #169)
check / check (push) Successful in 1m21s
Details
check / check (pull_request) Successful in 2m37s
Details 
Shallow snapshot verify only checked that each blob object existed and then reported "All blobs verified", overstating what it did.

It now compares each blob stored size against the manifest compressed_size, using the same comparison as the deep path, and checks that the snapshot encrypted database (db.zst.age) is present. A blob of the wrong size no longer counts as verified. The final line reports only what was checked: presence and size, not contents.

The README verify description and the CLI short/long text are corrected to match. Removed the now-unused resolveAndDownloadManifest helper and errBlobsMissing sentinel.

Model: opus-4-8
 2026-09-22 14:28:44 +02:00
clawbot 4f27608560 Add negative and boundary tests for blobgen and types (closes #170)
check / check (push) Successful in 1m22s
Details
check / check (pull_request) Successful in 1m18s
Details 
Test-only. internal/blobgen and internal/types had no negative or boundary coverage. Adds, in package blobgen_test: Writer-to-Reader round trips at the 64 KiB age-segment edges for random and compressible data, checking plaintext, byte counts and the reader/writer hashes by decrypting; a wrong-identity open; truncation and single-byte corruption of a multi-segment blob at every region; trailing bytes, empty input and garbage; rejected and accepted compression levels; nil, empty and invalid recipients; and a failing destination. In package types_test: Value/Scan round trips, NULL, wrong-type and malformed Scan, Parse and IsZero for FileID and BlobID.

The "cut right after the age header and nonce" truncation is excluded: it reads as valid and empty today and belongs to #152.

Model: opus-4-8
 2026-09-22 14:28:34 +02:00
clawbot ae6aaaa388 Wait for the interrupted operation to clean up before exit (closes #159)
check / check (pull_request) Successful in 1m22s
Details
check / check (push) Successful in 3m13s
Details 
On SIGINT/SIGTERM the process could exit before the interrupted command cleanup defers ran, leaving decrypted data in the temp directory (the blob cache and the decrypted snapshot database).

RunApp now mirrors fx run sequence: start, block on app.Wait(), then app.Stop(), returning only after Stop completes. fx delivers both an OS interrupt and the finished operation Shutdowner.Shutdown() on one channel. Stop runs the OnStop hooks; the operation hook cancels the command and waits for its goroutine to return (bounded by shutdownTimeout) before exit. The old code returned as soon as app.Done fired, without Stop, so a real interrupt unwound to os.Exit while cleanup still ran. Restore loops check the context between chunks and blobs so the wait ends promptly. A cli test drives RunApp through the OnStop hook.

Model: opus-4-8
 2026-09-22 14:00:49 +02:00
clawbot f788668287 Remove the unused crypto path and write the blob-ID hash step once (closes #151)
check / check (push) Successful in 1m21s
Details
check / check (pull_request) Successful in 2m39s
Details 
Production encryption and decryption already run through blobgen; the crypto package (Encryptor, Decryptor, UpdateRecipients, the fx Module) and Vaultik.GetEncryptor/GetDecryptor had no production caller. Delete crypto and route verify --deep through the same blobgen reader restore uses, parsing the age key once.

The second blob-ID hash step is now one exported blobgen.DoubleSHA256; Writer.Sum256 (the double hash) becomes Writer.ContentID so it no longer collides with Reader.Sum256 (the single plaintext hash). Also delete the never-adopted internal/types newtypes and the uncalled CleanupIncompleteSnapshots and its now-dead deleteSnapshot caller, and correct ARCHITECTURE.md. No production behavior changes.

Model: opus-4-8
 2026-09-22 13:46:02 +02:00
clawbot 238ce3985f Scrub example config of real credentials and internal hosts (closes #172)
check / check (push) Successful in 1m20s
Details
check / check (pull_request) Successful in 2m41s
Details 
config.example.yml carried a real-looking 20-char S3 access key id and 40-char secret, a private-address http:// endpoint, and a storage_url naming an internal rclone remote and pool path. Replace them with the same neutral placeholders the config init template uses: YOUR_ACCESS_KEY / YOUR_SECRET_KEY, a https://s3.example.com endpoint, a mybucket bucket, and rclone://myremote/path/to/backups. No behavior or other keys change.

The credentials live in the commented-out s3 block, which the loader never parses, so the new test reads the file raw text to assert the placeholders are present and no http:// endpoint remains, and also loads it to confirm the active storage_url still parses.

Model: opus-4-8
 2026-09-22 13:45:52 +02:00
clawbot 548a7ae156 Give the local index and its export copy an explicit 0600 mode (closes #168)
check / check (pull_request) Successful in 1m23s
Details
check / check (push) Successful in 2m57s
Details 
The local index lists every backed-up path and chunk hash, but its file mode was left to the SQLite driver and the umask, so under a typical 022 umask a fresh index (and its -wal/-shm side files) landed world-readable. The snapshot export copied the index to snapshot.db with a permissive create as well.

provideDatabase now calls ensureIndexFileMode before opening the driver: it creates the index 0600 if missing and chmods an existing one to 0600. Doing this before the driver opens the file matters because SQLite gives its -wal and -shm files the mode of the main database file. The export copy is now created 0600. Tests under umask 022 cover a fresh index, an existing 0644 index, and the export copy.

Model: opus-4-8
 2026-09-22 13:12:07 +02:00
clawbot 3a58377127 Parse age_recipients at config load and never echo the entry (closes #153)
check / check (push) Successful in 1m23s
Details
check / check (pull_request) Successful in 1m18s
Details 
Config.Validate now parses every age_recipients entry with age.ParseX25519Recipient, so a bad recipient fails at config load instead of deep in a backup after the snapshot row and tree walk. On failure the error names the position (age_recipients[N]) and never the value: a recipient string can itself be a secret key an operator pasted by mistake, and age's own error quotes its input. An entry starting with AGE-SECRET-KEY- gets a specific message.

The remaining parse sites (blobgen.NewWriter, crypto NewEncryptor and UpdateRecipients), reachable by callers that skip config.Load, likewise drop the value and age's wrapped error, naming only the position.

Model: opus-4-8
 2026-09-22 13:01:00 +02:00
clawbot a6434de57f Open the downloaded snapshot database read-only, on a private temp dir (closes #162)
check / check (pull_request) Successful in 1m21s
Details
check / check (push) Successful in 3m4s
Details 
Restore and deep verify used to open the decrypted snapshot database read-write through the local-index constructor, which applied migrations against whatever the file carried, and left the decrypted file in the shared temp directory. A forged file could redefine what restore queries return, and an interrupted open left decrypted metadata on disk.

Add database.OpenReadOnly: opens the file read-only (mode=ro) with query_only and trusted_schema=OFF, never applies schema files, and refuses a file whose schema carries a trigger, view or virtual table or lacks an expected table. Restore and deep verify now both use it, each inside its own private (0700) temp directory removed on every return path. pickNextDownload returns (FileID, bool) so a genuine nil-UUID file is not mistaken for "nothing left".

Model: opus-4-8
 2026-09-22 12:45:53 +02:00
clawbot b4654f8e52 Abort the run when packing fails, even under --skip-errors (closes #161)
check / check (push) Successful in 1m22s
Details
check / check (pull_request) Successful in 3m2s
Details 
A chunk is registered as pending (known, scanner-pending, packer pending-row) before it is packed. Under --skip-errors the scanner skipped a file on any processing error, including a failure inside addChunkToPacker (packing, database, encryption, upload). The pending chunk then stayed queued and a later blob finalize inserted it into the chunks table with no blob_chunks row, so a snapshot could complete holding a file whose chunk is in no blob and cannot be restored.

Errors from addChunkToPacker are now marked and abort the run regardless of --skip-errors; only open and read errors are skipped. The bookkeeping order is unchanged. Flag help and comments now say only unreadable files are skipped.

Model: opus-4-8
 2026-09-22 12:28:44 +02:00
clawbot 39aef1c47c Stop config set echoing secrets; reject credential-bearing storage URLs (closes #166)
check / check (push) Successful in 1m21s
Details
check / check (pull_request) Successful in 1m18s
Details 
config set now prints only the key name after a write, never the value: a value may be a secret such as s3.secret_access_key, and echoing it leaks into captured stdout and pasted terminals. The set logic moves into writeConfigSet so this is testable.

config set also tightens a pre-existing group- or world-readable config to 0600 after writing; the previous stat-and-preserve-mode block had no effect (os.WriteFile does not change an existing file mode) and is removed.

ParseStorageURL now rejects s3:// and rclone:// URLs that carry credentials in the userinfo or an unknown query parameter, naming s3.access_key_id and s3.secret_access_key as where credentials belong. On a url.Parse failure only the inner cause is wrapped, so the raw URL is not echoed. file:// is unchanged.

Model: opus-4-8
 2026-09-22 12:28:32 +02:00
clawbot 96ebcd40d7 Reconcile purge against remote by hashed key, not human ID (closes #160)
check / check (pull_request) Successful in 1m20s
Details
check / check (push) Successful in 2m51s
Details 
syncWithRemote compared human snapshot IDs against the hashed metadata/<key>/ directory names, which never match, so it deleted every local snapshot record; the purge that followed then found nothing to remove remotely. Reconcile via listAllRemoteSnapshotKeys and RemoteSnapshotKey(id), matching CleanupLocalSnapshots, so a row still backed by remote metadata is kept.

The purge tests only passed because their stubs used the human-ID layout production never writes; they now write metadata under the hashed remote key. New tests prove remotely-backed local rows survive the reconcile and that a purge removes the local row and remote metadata together.

Model: opus-4-8
 2026-09-22 12:11:49 +02:00
clawbot d9f0220f94 Restore files at 0600 and make the blob hash check unskippable (closes #163)
check / check (pull_request) Successful in 1m21s
Details
check / check (push) Successful in 2m42s
Details 
Regular files are now created with O_EXCL at mode 0600 and given their stored mode only after the content is written and closed, so a file whose stored mode is restrictive is never briefly readable by other local users mid-restore. A file whose write or close fails is removed rather than left partial, and a chmod failure is a user-visible warning instead of a debug line.

hashVerifyReader.Close now errors when closed before EOF, so a short read or early close can never obtain a blob whose hash was not verified; downloadBlobToCache drops the cache entry on any such failure.

verifyFile (--verify) now rejects a restored file with bytes past its last chunk. Tests cover each behaviour under umask 022.

Model: opus-4-8
 2026-09-22 11:45:52 +02:00
clawbot 4c83e82543 Reject a blob_size_limit below the largest possible chunk (closes #167)
check / check (push) Successful in 1m20s
Details
check / check (pull_request) Successful in 1m16s
Details 
Validate only rejected blob_size_limit below chunk_size, but the chunker can emit chunks up to chunk_size times the FastCDC size spread (four times), and the packer puts a single chunk of any size into an otherwise empty blob. A limit between one and four times chunk_size therefore let a blob reach four times the configured maximum, with most blobs holding a single chunk and so exposing individual chunk lengths to anyone who can list the destination.

Validate now rejects blob_size_limit below chunk_size times the spread, reusing the chunker's one constant (now exported as ChunkSizeSpread) instead of a second literal. The rule is stated in the error text, the Validate comment, the README config table, config.example.yml, and the generated config template.

Model: opus-4-8
 2026-09-22 11:45:41 +02:00
clawbot 86361c8b50 Fail closed on unreadable manifests instead of losing blobs (closes #157)
check / check (pull_request) Successful in 1m20s
Details
check / check (push) Successful in 2m42s
Details 
Prune learned which blobs are in use by reading every snapshot's manifest, but merely logged and skipped one it could not download or decode. Blobs referenced only by that snapshot then looked unreferenced and were deleted, with a zero exit -- and snapshot create --prune runs this unattended. collectReferencedBlobs now errors, naming the remote key, so prune deletes nothing and exits non-zero.

Manifest generation likewise skipped a blob whose lookup failed or was missing, yielding a manifest short of what the snapshot needs; it now fails. Deep verify only warned when the manifest omitted a database blob; it now fails on any divergence. Docs corrected.

Model: opus-4-8
 2026-09-22 11:45:30 +02:00
clawbot d77663d039 Default a scheme-less s3.* endpoint to TLS (closes #158)
check / check (pull_request) Successful in 1m19s
Details
check / check (push) Successful in 3m15s
Details 
With the s3.* config form and an endpoint written without a scheme, use_ssl being omitted built an http:// endpoint, while config.example.yml documented use_ssl as defaulting to true. Over plain HTTP a network observer sees manifests, object names, sizes and the access key id, and can alter responses.

use_ssl is now *bool: omitted (nil) means the default, TLS; only an explicit use_ssl: false forces plain HTTP. This matches the s3:// URL form, which already defaults to TLS. The config init template dropped its misleading use_ssl line from the s3:// block (that key is never read for URLs; ?ssl=false controls TLS there) and points at ?ssl=false instead.

Model: opus-4-8
 2026-09-22 11:11:34 +02:00
clawbot 3abe9cbd9e Scope the PID lock to mutating commands (closes #150)
check / check (push) Successful in 1m19s
Details
check / check (pull_request) Successful in 1m16s
Details 
RunWithApp took the process-wide PID lock for every fx-backed command, so read-only commands (info, snapshot list, snapshot verify, remote info) failed with "already running" while a backup held it.

AppOptions now carries a lockMode declared at each call site: only mutating commands (snapshot create, snapshot purge, snapshot remove, prune, remote nuke) acquire the lock; read-only ones run without it. snapshot restore is classified read-only -- it writes only to its target directory, not the local index or remote store. The decision moves to a small acquireLockIfMutating helper, with a test that a read-only command runs while the lock is held and two mutators still exclude. The README locking section is rewritten to match.

Model: opus-4-8
 2026-09-22 11:01:29 +02:00
clawbot 76a6917a35 Keep restore writes inside the target directory (closes #154)
check / check (pull_request) Successful in 1m21s
Details
check / check (push) Successful in 2m51s
Details 
restoreFile and verifyRestoredFiles joined the stored path onto the target with no containment check, so a ".." segment or an absolute path escaped the target, and a restored symlink could redirect a later child write anywhere on disk. Since age decryption proves a snapshot is readable but not honest, and restore usually runs as root, a forged snapshot became an arbitrary file write.

Both call sites now go through containedRestorePath: it rejects a stored path unless filepath.IsLocal accepts it with the leading separator removed (barring "..", absolute, and empty paths), then Lstats each existing ancestor below the target and refuses to descend through a symlink. The target directory itself may be a symlink, and honest symlinks pointing outside the tree are still written verbatim.

Model: opus-4-8
 2026-09-22 11:01:01 +02:00
clawbot 38ebfd843a Trust only uploaded blobs for deduplication (closes #148)
check / check (pull_request) Successful in 1m23s
Details
check / check (push) Successful in 3m10s
Details 
An interrupted blob upload left the blob's chunks, blob_chunks, and blobs rows committed before the upload was attempted, so a later run deduplicated against data that never reached storage and produced a snapshot that reported success but could not be restored.

Fix (issue option b): a chunk counts as known only when a blob holding it has uploaded_ts set, and each run drops un-uploaded blob rows and the chunks they orphan at startup, so the affected data is re-chunked and re-uploaded. A blob recorded with no remote backend is marked uploaded so the invariant holds uniformly.

The reproduction is the interrupted-upload test from #72: its t.Skip is removed and it passes against this fix, and this branch's earlier duplicate copy is dropped. The interrupted metadata-export case is split to #177.

Model: opus-4-8
 2026-09-22 10:29:21 +02:00
clawbot 6b7517a4dc Add fault-injection tests for interruption and corruption (closes #72)
check / check (push) Successful in 1m22s
Details
check / check (pull_request) Successful in 2m42s
Details 
Adds internal/storage/faultstore, a storage.Storer wrapper that injects faults through the storage seam without patching production code: an upload that dies mid-stream, a backend reporting success while storing nothing, and reads returning corrupt or truncated bytes. Covers all six scenarios from the issue, each asserting the observable end state (index, destination, and what the user is told), not merely that an error returned. Scenario 1b (retry after an interrupted upload) exposed a real dedup defect and is skipped with a pointer to #148, which also owns the half-exported-state repair. Tests run serially because each calls log.Initialize on the global logger. No production behavior changes.

Model: opus-4-8
 2026-09-22 09:46:46 +02:00
clawbot 994e5de613 Quiet only the stdout UI under --json, not the log level (closes #112)
check / check (push) Successful in 2m23s
Details
check / check (pull_request) Successful in 1m24s
Details 
Per the decision on the issue (option 1), --json no longer implies Quiet. Folding --json into Quiet pinned the stderr log level to WARN, so prune --json gave a machine consumer no record of the local index rows it deleted. The two effects are now split: a JSON field on log.Options drives only the stdout UI-quiet in setupGlobals, keeping the JSON document clean, while the stderr log level follows --verbose/--debug again (diagnostics have gone to stderr since #82). The same coupling is removed for snapshot verify, snapshot remove and remote info; snapshot list was already decoupled.

Model: opus-4-8
 2026-09-22 09:05:52 +02:00
clawbot 42f4e648d7 Reconcile docs with code across the accuracy-sweep items (closes #74)
check / check (pull_request) Successful in 2m38s
Details
check / check (push) Successful in 4m22s
Details 
Docs-only sweep of the accuracy items. Corrected ARCHITECTURE.md chunk sizes and the fx config type; documented the ls/rm aliases, the CPU/MEM profile env vars, the age_secret_key threat-model caveat, the four zstd presets, and a new locking section for the process-wide PID lock. Narrowed the internal/ui output claim to what holds today (refactor deferred to #149); lock-scoping deferred to #150. Added the missing ARCHITECTURE.md and config.example.yml README links. Every claim re-verified against the tree.

Disclosure: a pre-existing gomodguard linter deprecation surfaced during the gate; unrelated.

Model: opus-4-8
 2026-09-22 09:05:36 +02:00
clawbot 343129f891 Accept a remote key for restore and verify, and document it (closes #124)
check / check (push) Failing after 1s
Details
check / check (pull_request) Failing after 1s
Details 
A machine restoring after the original is gone has no local index and cannot know a snapshot's human ID; snapshot list shows such snapshots only by their remote key, but restore and verify accepted only the human ID, so recovery could not be done as documented.

Restore and verify now also accept a remote key, or an unambiguous leading part of it as snapshot list prints it, resolved against the store's metadata listing. Human IDs are never pure hex, which tells the two forms apart. Deep verify reads the single snapshot in the downloaded per-snapshot database. A new README section walks the recovery end to end; a test backs up, then lists, restores and deep-verifies with an empty index, another hostname and no age_recipients.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
 2026-09-22 01:01:25 +02:00
clawbot a50e3fa038 Add tests for internal/storage: URL parsing, backends, shared conformance suite (closes #66)
check / check (push) Failing after 1s
Details
check / check (pull_request) Successful in 3m25s
Details 
internal/storage, the package that parses store URLs and selects the backend, had no tests.

Adds table-driven tests for URL parsing (each scheme, query parameters, malformed input, unknown scheme, backend type chosen); one shared conformance suite for the Storer interface, run against the file backend in a temp directory and the s3 backend on the in-process harness internal/s3 already uses, so a new backend inherits it; and rclone construction and argument tests using its in-process local backend. A comment records that rclone data operations need a configured remote and are not unit-tested. No production code changed and no defect surfaced.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
 2026-09-22 00:58:27 +02:00
clawbot 6fcd8e1668 Stamp Docker image version from the host; flush profiles on error exit (closes #75)
check / check (push) Failing after 1s
Details
check / check (pull_request) Failing after 1s
Details 
Docker images reported commit unknown because the build ran git inside the container while .dockerignore excludes .git, and VERSION was never overridden. script/docker and script/cibuild now compute version, commit and date on the host and pass them as build args; the Dockerfile runs no git and falls back to dev and unknown, never empty, on a bare docker build.

Profiling a failing command gave a truncated or missing profile: Entry and each command goroutine called os.Exit(1), skipping the deferred profile writers in main. Entry now returns a status that main exits with after its defers run, and command goroutines report failure through one RunOperation helper, which also restores PID-lock release and graceful shutdown on failure.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)

Co-authored-by: clawbot <clawbot@noreply.example.org>
 2026-09-21 22:01:05 +02:00
clawbot aab6a87f8c Reconcile the schema/migration docs with the code (closes #68)
check / check (pull_request) Failing after 1s
Details
check / check (push) Successful in 2m46s
Details 
Four documents told different stories about the database schema. docs/DATAMODEL.md now owns the explanation and separates two things: the policy, which is unchanged (no supported upgrade path between versions; delete the local index with vaultik database delete and back up again), and the schema bootstrap that does exist (numbered files in internal/database/schema applied to a fresh database and recorded in schema_migrations).

README.md and AGENTS.md are reworded to match and link there. AGENTS.md names the real file to edit, internal/database/schema/001.sql, and notes that the pre-1.0 disposability clause expires on tagging. No code changed.

Judgement call: REPO_POLICIES.md still names a different schema file; it is cross-project policy and was left alone.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
 2026-09-21 21:58:37 +02:00
clawbot c355ef4d25 Report a prune count that could not be read as unknown, not 0 (closes #96)
check / check (pull_request) Failing after 1s
Details
check / check (push) Successful in 2m46s
Details 
Prune read table row counts before and after to report how many orphaned files, chunks and blobs it removed, and discarded the error from every read. A failed query therefore reported as a count of 0, and the summary showed plausible wrong numbers.

A count that cannot be read is now logged as a warning (on stderr, also under --json) and shown as "unknown"; a difference computed from an unknown count is itself unknown. 0 still means the table was empty. No --json document carries these counts, so none can show a false 0.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
 2026-09-21 21:41:57 +02:00
clawbot 5927e1aa3d Write file:// blobs atomically via temp file and rename (closes #130)
check / check (push) Failing after 0s
Details
check / check (pull_request) Failing after 0s
Details 
The file:// backend streamed each object straight to its final key, so an upload cut off mid-stream left a truncated object there. The next backup saw that Stat succeeded, recorded the blob as complete, and produced a snapshot that reported success but could not be restored.

Writes now go to a temporary file with a .partial suffix in the destination directory, are synced, then renamed onto the key. List and ListStream skip .partial files, so a leftover is never trusted as a blob and is overwritten when the key is written again. S3 PutObject is already atomic.

Disclosure: the containing directory is not synced after the rename, so a host crash right after it could still lose the object on some filesystems.

model: claude-opus-4-8 (implementation, review); claude-fable-5-1 (merge)
 2026-09-21 21:24:42 +02:00
103 changed files with 8643 additions and 1757 deletions
Expand all files Collapse all files
AGENTS.md
+8 -3
View File
@@ -104,7 +104,12 @@ Version: 2025-06-08
13. Pre-1.0: NEVER write database migrations. There are no live databases
anywhere — every user's local index can be rebuilt from a fresh full
backup. When the schema changes, just change `schema.sql` (and any code
that touches the affected tables). The local index is disposable until
1.0 ships and is tagged.
backup. To change the schema, edit `internal/database/schema/001.sql`
(and any code that touches the affected tables) directly; do not add new
numbered schema files. Those numbered files and the `schema_migrations`
table they populate only bootstrap a fresh database — they are not an
upgrade path. The local index is disposable until 1.0 ships and is
tagged; once 1.0 is tagged that clause expires and the question of
upgrading existing indexes returns. See [`docs/DATAMODEL.md`](docs/DATAMODEL.md)
for the full explanation.
ARCHITECTURE.md
+8 -9
View File
@@ -63,7 +63,7 @@ A content-addressed unit of data. Files are split into variable-size chunks usin
- `ChunkHash`: SHA256 hash of chunk content (primary key)
- `Size`: Chunk size in bytes
Chunk sizes vary between `avgChunkSize/4` and `avgChunkSize*4` (typically 16KB-256KB for 64KB average).
Chunk sizes vary between `avgChunkSize/4` and `avgChunkSize*4` (2.5MB-40MB for the 10MB default average).
#### FileChunk (`database.FileChunk`)
Maps files to their constituent chunks:
@@ -74,16 +74,16 @@ Maps files to their constituent chunks:
#### Blob (`database.Blob`)
The final storage unit uploaded to S3. Contains many compressed and encrypted chunks:
- `ID`: UUID assigned at creation
- `Hash`: SHA256 of final compressed+encrypted content
- `Hash`: `hex(SHA256(SHA256(uncompressed blob contents)))`, computed before compression and encryption (see [docs/REPOSTRUCTURE.md](docs/REPOSTRUCTURE.md#blobs-directory-blobs))
- `UncompressedSize`: Total raw chunk data before compression
- `CompressedSize`: Size after zstd compression and age encryption
- `CreatedTS`, `FinishedTS`, `UploadedTS`: Lifecycle timestamps
Blob creation process:
1. Chunks are accumulated (up to MaxBlobSize, typically 10GB)
2. Compressed with zstd
3. Encrypted with age (recipients configured in config)
4. SHA256 hash computed → becomes filename in S3
2. As each chunk is added, its uncompressed bytes are fed to a running SHA-256
3. Concurrently, the same bytes are compressed with zstd, then encrypted with age (recipients configured in config), and streamed to storage
4. On finalize, the blob's name is the double SHA-256 of the uncompressed contents — `hex(SHA256(SHA256(...)))` — not a hash of the compressed, encrypted bytes
5. Uploaded to `blobs/{hash[0:2]}/{hash[2:4]}/{hash}`
#### BlobChunk (`database.BlobChunk`)
@@ -120,7 +120,7 @@ The CLI uses fx for dependency injection. Here's the instantiation order:
```go
// cli/app.go: NewApp()
fx.New(
fx.Supply(config.ConfigPath(opts.ConfigPath)), // 1. Config path
fx.Supply(config.Path(opts.ConfigPath)), // 1. Config path
fx.Supply(opts.LogOptions), // 2. Log options
fx.Provide(globals.New), // 3. Globals
fx.Provide(log.New), // 4. Logger config
@@ -193,7 +193,7 @@ scanner := v.ScannerFactory(snapshot.ScannerParams{
- **Created by**: `chunker.NewChunker(avgChunkSize)`
- **When**: Inside `snapshot.NewScanner()`
- **Configuration**:
- `avgChunkSize`: From config (typically 64KB)
- `avgChunkSize`: From config (default 10MB)
- `minChunkSize`: avgChunkSize / 4
- `maxChunkSize`: avgChunkSize * 4
@@ -286,7 +286,6 @@ Key methods:
- `CreateSnapshot(ctx, hostname, version, commit)` → Create snapshot record
- `CompleteSnapshot(ctx, snapshotID)` → Mark snapshot complete
- `ExportSnapshotMetadata(ctx, dbPath, snapshotID)` → Export to S3
- `CleanupIncompleteSnapshots(ctx, hostname)` → Remove failed snapshots
### `internal/database`
SQLite database for local index. Single-writer mode for thread safety.
@@ -307,7 +306,7 @@ Repository interfaces:
```
CreateSnapshot(opts)
│
├─► CleanupIncompleteSnapshots() // Critical: avoid dedup errors
├─► PruneDatabase() // Critical: avoid dedup errors
│
├─► SnapshotManager.CreateSnapshot() // Create DB record
│
README.md
+146 -34
View File
@@ -38,7 +38,7 @@ vaultik snapshot list
Features:
* modern encryption ([age](https://age-encryption.org/), X25519 + XChaCha20-Poly1305)
* modern encryption ([age](https://age-encryption.org/), X25519 + ChaCha20-Poly1305)
* content-defined chunking with deduplication (FastCDC)
* incremental backups (only changed files are re-chunked)
* multithreaded zstd compression at configurable levels
@@ -71,19 +71,80 @@ Requirements that no existing tool meets:
## daily use
```sh
# verify a snapshot (shallow: checks all blobs exist)
# verify a snapshot (shallow: checks all blobs are present with the listed size)
vaultik snapshot verify <snapshot-id>
# deep verify (downloads and cryptographically verifies every blob)
VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...' vaultik snapshot verify --deep <snapshot-id>
# put the private key file in the environment (reading it from the file
# keeps the key out of your shell history); the whole age-keygen file,
# with one or more identities, is accepted
export VAULTIK_AGE_SECRET_KEY="$(cat vaultik_backup_private_key.txt)"
# restore (requires the private key)
VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...' vaultik snapshot restore <snapshot-id> /tmp/restored
# deep verify (downloads every blob, decrypts it, and re-hashes it to
# detect corruption — this checks integrity, not who wrote the blob)
vaultik snapshot verify --deep <snapshot-id>
# restore (requires the private key). Restore into a new directory you own,
# writable only by you — not a shared location like /tmp
vaultik snapshot restore <snapshot-id> ~/vaultik-restore
# daily cron job: back up, keep a 4-week rolling window of snapshots
# 0 3 * * * vaultik snapshot create --cron --prune --keep-newer-than 4w
```
## restoring on another machine
Restoring on a host that never ran the backup — a replacement machine
after the original is gone — is the case vaultik is built for. That host
needs only three things: the `vaultik` binary, the age **private** key,
and the storage credentials for the destination. It does **not** need the
local index, the original config file, or the original hostname.
```sh
# install
go install sneak.berlin/go/vaultik/cmd/vaultik@latest
# create a config and point it at the ORIGINAL backup destination
vaultik config init
vaultik config set storage_url "s3://bucket/prefix?endpoint=https://s3.example.com"
vaultik config set s3.access_key_id "..."
vaultik config set s3.secret_access_key "..."
# see what is on the destination store
vaultik snapshot list
```
`snapshot list` reads the destination store without the private key. A
snapshot that is not in this host's (empty) local index is shown as
remote-only: its row is identified by `<remote only:...>` rather than by
a `hostname_name_timestamp` name, because the name lives only in the
local index and the encrypted database and cannot be recovered from the
store. Its timestamp and compressed size are real. (See the `snapshot
list` description under [command details](#command-details) for the full
explanation.)
Use that remote key — the hex printed inside `<remote only:...>`, or the
full `remote_key` from `snapshot list --json` — to restore and verify:
```sh
# put the private key file in the environment (reading it from the file
# keeps the key out of your shell history)
export VAULTIK_AGE_SECRET_KEY="$(cat vaultik_backup_private_key.txt)"
# restore everything to a new directory you own (writable only by you, not a
# shared location like /tmp), then check every restored file's chunk hashes
vaultik snapshot restore --verify <remote-key> ~/vaultik-restore
# optionally, deep-verify the snapshot against the store (downloads every
# blob, decrypts it, and re-hashes it to detect corruption — this checks
# integrity, not who wrote the blob)
vaultik snapshot verify --deep <remote-key>
```
`age_recipients` (the public key) is not needed to restore — only the
private key in `VAULTIK_AGE_SECRET_KEY`. Both the abbreviated key printed
in the table and the full 64-character key from `--json` are accepted; a
leading part of the key is enough as long as it is unambiguous.
---
## cli
@@ -96,10 +157,10 @@ vaultik [--config <path>] config edit
vaultik [--config <path>] config get <key>
vaultik [--config <path>] config set <key> <value>
vaultik [--config <path>] snapshot create [snapshot-names...] [--cron] [--prune] [--keep-newer-than <duration>]
vaultik [--config <path>] snapshot list [--json]
vaultik [--config <path>] snapshot list [--json] # alias: ls
vaultik [--config <path>] snapshot verify <snapshot-id> [--deep] [--json]
vaultik [--config <path>] snapshot purge [--keep-latest | --older-than <duration>] [--snapshot <name>...] [--force]
vaultik [--config <path>] snapshot remove <snapshot-id> [--dry-run] [--force] [--local-only] [--json]
vaultik [--config <path>] snapshot remove <snapshot-id> [--dry-run] [--force] [--local-only] [--json] # alias: rm
vaultik [--config <path>] snapshot restore <snapshot-id> <target-dir> [paths...] [--verify]
vaultik [--config <path>] prune [--force] [--json]
vaultik [--config <path>] info
@@ -116,7 +177,24 @@ vaultik version
* `--verbose`, `-v`: Enable verbose output (on stderr — see below)
* `--debug`: Enable debug output (on stderr — see below)
* `--quiet`, `-q`: Suppress non-error output (also suppresses startup banner)
* `--skip-errors`: Continue past per-file errors instead of aborting (applies to `snapshot create` and `restore`)
* `--skip-errors`: Skip files that cannot be read when creating a snapshot, or that cannot be restored when restoring, instead of aborting. Packing and storage errors (which would leave a chunk recorded but not stored) still abort the run.
### locking
Commands that write persistent state — `snapshot create`, `snapshot
purge`, `snapshot remove`, `prune`, and `remote nuke` — take a
process-wide lock at `$XDG_DATA_HOME/vaultik/vaultik.pid`
(`~/.local/share/vaultik/vaultik.pid` on Linux) for the whole run. Only
one of them runs at a time: a second one exits immediately with an
"already running" error rather than waiting, so two writers can never
corrupt the local index or the destination store.
Read-only commands — `info`, `snapshot list`, `snapshot verify`, and
`remote info` — do not take the lock and are never blocked, so they run
even while a backup is in progress. `snapshot restore` does not take the
lock either: it writes only to the target directory you name, not the
local index or the destination store. `config`, `database delete`,
`completion`, and `version` do not take the lock.
### stdout and stderr
@@ -149,9 +227,11 @@ and `vaultik prune --json | jq .` both work as written.
### environment variables
* `VAULTIK_AGE_SECRET_KEY`: Age private key for decryption (required for `snapshot restore` and `snapshot verify --deep`)
* `VAULTIK_AGE_SECRET_KEY`: Age private key for decryption (required for `snapshot restore` and `snapshot verify --deep`). May hold the whole `age-keygen` file — comments and every identity in it are accepted. Set it from the file, e.g. `export VAULTIK_AGE_SECRET_KEY="$(cat vaultik_backup_private_key.txt)"`, so the key is not typed into your shell history.
* `VAULTIK_CONFIG`: Path to config file (overridden by `--config`)
* `VAULTIK_INDEX_PATH`: Override local SQLite index path
* `VAULTIK_CPUPROFILE`: Write a CPU profile to this path for the duration of the run (development/debugging)
* `VAULTIK_MEMPROFILE`: Write a heap profile to this path when the run exits (development/debugging)
### shell completion
@@ -242,9 +322,13 @@ local index alone, and still exits zero.
logger, so stdout stays a single parseable document.
**`snapshot verify`**: Verify snapshot integrity.
* Default (shallow): checks that all blobs referenced in the manifest exist in storage
* Default (shallow): checks that every blob the manifest lists is present in
storage with the size the manifest records, and that the encrypted database is
present. It does not read blob contents.
* `--deep`: Downloads and decrypts each blob, verifies chunk hashes against the
encrypted metadata database
* Accepts the same identifiers as `snapshot restore`: a snapshot ID, or a
remote-only snapshot's remote key (or an unambiguous leading part of it)
* `--json`: Output results as JSON
**`snapshot purge`**: Remove old snapshots based on criteria. Retention is
@@ -275,6 +359,10 @@ on the destination in one go, use `vaultik remote nuke --force`.
**`snapshot restore`**: Restore files from a backup snapshot.
* Requires `VAULTIK_AGE_SECRET_KEY` environment variable
* Accepts a snapshot ID, or — for a snapshot only on the destination
store — its remote key (or an unambiguous leading part of it) as shown
by `snapshot list`. See
[restoring on another machine](#restoring-on-another-machine).
* Optional path arguments to restore specific files/directories (default: all)
* Preserves file permissions, timestamps, ownership (ownership requires root),
symlinks, and empty directories
@@ -338,6 +426,10 @@ both are set.
## architecture
For an implementation-level view of the internals — the data model, the
`fx` dependency-injection wiring, and the scanner — see
[`ARCHITECTURE.md`](ARCHITECTURE.md).
### remote storage layout
```
@@ -360,14 +452,19 @@ Snapshot IDs follow the human-readable format
`<hostname>_<snapshot-name>_<RFC3339-timestamp>` (e.g.
`server1_home_2025-06-01T12:00:00Z`), but this ID is never written to the
destination store in plaintext. Each snapshot's metadata directory is named
with its `<remote-key>`, a one-way double SHA-256 hash of the ID, so a listing
of the store reveals no hostname or snapshot name. The backup time is not
hidden: manifest.json.zst carries a plaintext timestamp, and object
with its `<remote-key>`, a one-way double SHA-256 hash of the ID, so a plain
listing of the store shows no hostname or snapshot name. The hash uses no
secret, though, so an observer who guesses a candidate hostname and snapshot
name can hash it and confirm the snapshot is present; the remote key keeps
names out of a listing but does not hide them from a guess. The backup time is
not hidden either: manifest.json.zst carries a plaintext timestamp, and object
modification times are visible at the storage layer regardless. For example,
`server1_home_2025-06-01T12:00:00Z` is stored under
`metadata/17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa/`.
See [docs/REPOSTRUCTURE.md](docs/REPOSTRUCTURE.md#remote-key-derivation) for the
derivation.
derivation, and [Security Considerations](docs/REPOSTRUCTURE.md#security-considerations)
(including [Accepted Risks](docs/REPOSTRUCTURE.md#accepted-risks)) for what the
format does and does not protect.
### data flow
@@ -408,32 +505,37 @@ derivation.
### encryption
* Asymmetric encryption using age (X25519 + XChaCha20-Poly1305)
* Asymmetric encryption using age (X25519 + ChaCha20-Poly1305)
* Only the public key is needed on the source host
* Each blob and each metadata database is encrypted independently
* Multiple recipients supported (encrypt to multiple keys)
### compression
* zstd compression at configurable level (1-19, default 3)
* zstd compression at configurable level (1-19, default 3). The level is
accepted as 1-19 but maps onto zstd's four internal speed presets:
1-2 fastest, 3-5 default, 6-9 better, 10-19 best. Levels within the
same band compress identically.
* Applied before encryption at the blob level
---
## configuration reference
Run `vaultik config init` to generate a fully commented config file.
Key fields:
Run `vaultik config init` to generate a fully commented config file; a
complete annotated example also lives in
[`config.example.yml`](config.example.yml). Key fields:
| Field | Default | Description |
|-------|---------|-------------|
| `age_recipients` | (required) | Age public keys for encryption |
| `age_secret_key` | (unset) | Age private key for decryption (`snapshot restore`, `snapshot verify --deep`). Setting it in the config file places the private key on the backed-up host, defeating the public-key-only design (see "why" above). Prefer the `VAULTIK_AGE_SECRET_KEY` environment variable, supplied only on the machine you restore from. |
| `snapshots` | (required) | Named snapshot definitions with paths and excludes |
| `storage_url` | | Storage backend URL (`s3://`, `file://`, `rclone://`) |
| `s3.*` | | Legacy S3 configuration (endpoint, bucket, credentials) |
| `exclude` | | Global exclude patterns (applied to all snapshots) |
| `chunk_size` | `10MB` | Average chunk size for content-defined chunking |
| `blob_size_limit` | `10GB` | Maximum blob size before splitting |
| `blob_size_limit` | `10GB` | Maximum blob size before splitting. Must be at least four times `chunk_size` (the largest chunk the chunker can emit), otherwise a single-chunk blob could exceed the limit |
| `compression_level` | `3` | zstd compression level (1-19) |
| `hostname` | system hostname | Hostname used in snapshot IDs |
| `index_path` | platform data dir | Local SQLite index path |
@@ -457,9 +559,13 @@ Key fields:
sequentially. Restore speed is bound by single-stream throughput.
* **Device nodes, named pipes, and sockets are silently skipped.** Only
regular files, directories, and symlinks are backed up.
* **No database migrations.** If the local SQLite schema changes between
versions, delete the local database (`vaultik database delete`) and run
a full backup. Remote storage is unaffected.
* **No upgrade path between versions.** There is no supported way to carry
an existing local index across a schema change; if the local SQLite
schema changes between versions, delete the local database (`vaultik
database delete`) and run a full backup. Remote storage is unaffected.
(The binary does embed numbered schema files and a `schema_migrations`
table to bootstrap a fresh database — see [`docs/DATAMODEL.md`](docs/DATAMODEL.md)
— but that is not an upgrade path.)
* **Files that change during backup may be inconsistent.** There is no
filesystem snapshot or freeze. If a file is modified between the scan
and chunk phases, the backed-up copy may reflect a partial write.
@@ -525,14 +631,12 @@ priority.
### infrastructure
* **Cross-machine restore documentation.** The "restore from
another host" workflow works but isn't documented as a
first-class operation in this README. Worth a dedicated section
once it's settled.
* **Schema migrations.** Currently nonexistent — pre-1.0 schema
changes are handled by `vaultik database delete` plus a full
re-scan. Post-1.0 we'll need a migration story to keep existing
index databases usable across upgrades.
* **Cross-version schema upgrades.** There is no upgrade path between
released versions — pre-1.0 schema changes are handled by `vaultik
database delete` plus a full re-scan (see
[`docs/DATAMODEL.md`](docs/DATAMODEL.md)). Post-1.0 we'll need a
migration story to keep existing index databases usable across
upgrades.
* **Storage backend coverage tests.** S3, file://, and rclone://
all share the Storer interface but the rclone path is the least
exercised in CI.
@@ -541,9 +645,17 @@ priority.
## output style
All user-facing output goes through helpers in `internal/ui` and conforms
to a uniform style. Color is enabled when stdout is a TTY and the
`NO_COLOR` environment variable is unset (https://no-color.org/).
The operational narration of the long-running commands — the Begin,
Complete, Progress, and status lines of `snapshot create`, `prune`,
`snapshot restore`, and the like — goes through helpers in `internal/ui`
and conforms to the uniform style below. Some commands instead write
plain text straight to stdout (`version`, `info`, `config`, the
`database delete` prompt, and the `snapshot list` table); that output is
unstyled and does not honor `--quiet`. Routing it through `internal/ui`
is tracked in
[issue #149](https://git.eeqj.de/sneak/vaultik/issues/149). Color is
enabled when stdout is a TTY and the `NO_COLOR` environment variable is
unset (https://no-color.org/).
`internal/ui` writes to stdout; it is the output the user asked for.
Structured log records are a different thing and go through
TODO.md
+70 -1
View File
@@ -25,6 +25,76 @@ release" is exactly the contradiction
# Completed Steps
- 2026-09-22: Validated blob hashes, offsets and lengths read back from
the destination before using them
([issue #155](https://git.eeqj.de/sneak/vaultik/issues/155)). A blob
hash taken from the downloaded database or the store listing was
trusted unchecked, so a hostile remote could drive a decrypted blob to
be written outside the cache directory (a hash like `aa/../../etc`) or
crash a command with a short or negative value. `blobDiskCache.path`
now refuses any key containing a path separator, and `ReadAt` rejects a
negative offset or length and bounds with `length > size-offset` so a
sum cannot overflow past the check. A new `isBlobHash` helper (a plain
function, not a method — the packer stores `temp-placeholder-{uuid}` as
a hash) gates `FetchBlob`, shallow and deep verify; the `blobs/` and
`metadata/` listings skip a non-conforming name with a warning; and
short-hash prefixes in log and error text go through a `shortHash`
helper that cannot panic. `verify`'s chunk reader also rejects a
negative `blob_chunks` length and streams the chunk instead of
allocating a database-supplied size. `restore.go` and
`internal/database` were left untouched to avoid colliding with the
in-flight [issue #156](https://git.eeqj.de/sneak/vaultik/issues/156)
work; the cache-path and `FetchBlob` guards already stop the unsafe
write and fetch, so restore's own `buildBlobIndexes` early check is
deferred as fail-fast defense in depth.
- 2026-09-21: Stopped an interrupted blob upload from making a later
backup deduplicate against data that was never stored
([issue #148](https://git.eeqj.de/sneak/vaultik/issues/148)). The
packer commits a blob's `chunks`, `blob_chunks`, and `blobs` rows
before the upload is attempted, so a failed upload left chunk rows
behind and the next run skipped re-uploading them, producing a
snapshot that reported success but could not be restored. A run now
deduplicates only against chunks held by a blob whose `uploaded_ts` is
set, and at startup drops any un-uploaded blob rows (and the chunks
they orphan) so the affected data is re-chunked and re-uploaded. Blobs
recorded with no remote backend are marked uploaded so this invariant
holds uniformly.
- 2026-09-22: Made restore refuse any snapshot path that would write
outside the target directory
([issue #154](https://git.eeqj.de/sneak/vaultik/issues/154)).
`restoreFile` and `verifyRestoredFiles` joined the stored path onto the
target with no containment check, so a `..` segment or an absolute path
escaped the target and a restored symlink could redirect a later child
write anywhere on disk. Every stored path is now rejected unless
`filepath.IsLocal` accepts it with the leading separator removed, and
each existing ancestor directory below the target is `Lstat`ed to refuse
descending through a symlink; honest symlinks pointing outside the tree
are still written verbatim. age decryption proves a snapshot is
readable, not honest, and restore usually runs as root.
- 2026-09-21: Stopped `--json` from silencing stderr diagnostics
([issue #112](https://git.eeqj.de/sneak/vaultik/issues/112)). `--json`
used to be folded into `Quiet`, which pinned the log level to `WARN`,
so `prune --json` gave a machine consumer no record of the local index
rows it deleted even under `--verbose`. `--json` now quiets only the
stdout UI (the JSON document must stay clean, per
[issue #108](https://git.eeqj.de/sneak/vaultik/issues/108)); the stderr
log level follows `--verbose`/`--debug` again. The coupling was
removed the same way for `snapshot verify`, `snapshot remove`, and
`remote info`, which carried it for the same outdated reason.
- 2026-09-21: Stopped `prune` from reporting a failed row count as 0
([issue #96](https://git.eeqj.de/sneak/vaultik/issues/96)). The seven
`getTableCount` reads in `PruneDatabase` discarded their error, so a
query that could not run became a plausible `0` and the before/after
delta computed from it looked like real work. Each read now logs at
warn on failure and renders as `unknown`, never `0`, so an empty table
is distinguishable from one that could not be queried. The counts have
no `--json` representation — under `--json` the summary is suppressed
entirely — so nothing there can show a false `0`.
- 2026-09-21: Made the s3 storage backend report a missing object as
`storage.ErrNotFound`, like the `file` and `rclone` backends and as the
`Storer` interface documents. `S3Storer.Get` and `Stat` returned the raw
@@ -33,7 +103,6 @@ release" is exactly the contradiction
helper (reused by `HeadObject`) and a test that a missing key maps to
`ErrNotFound`
([issue #129](https://git.eeqj.de/sneak/vaultik/issues/129)).
- 2026-09-21: Fixed `verify --deep` reporting healthy snapshots as
corrupt. Its final blob-integrity check hashed the encrypted
downloaded bytes with a single SHA256 and compared that to the blob
config.example.yml
+10 -5
View File
@@ -257,16 +257,16 @@ exclude:
# Storage URL - use either this OR the s3 section below
# Supports: s3://bucket/prefix, file:///path, rclone://remote/path
storage_url: "rclone://las1stor1//srv/pool.2024.04/backups/heraklion"
storage_url: "rclone://myremote/path/to/backups"
# S3-compatible storage configuration
#s3:
# # S3-compatible endpoint URL
# # Examples: https://s3.amazonaws.com, https://storage.googleapis.com
# endpoint: http://10.100.205.122:8333
# endpoint: https://s3.example.com
#
# # Bucket name where backups will be stored
# bucket: testbucket
# bucket: mybucket
#
# # Prefix (folder) within the bucket for this host's backups
# # Useful for organizing backups from multiple hosts
@@ -274,8 +274,8 @@ storage_url: "rclone://las1stor1//srv/pool.2024.04/backups/heraklion"
# #prefix: "hosts/myserver/"
#
# # S3 access credentials
# access_key_id: Z9GT22M9YFU08WRMC5D4
# secret_access_key: Pi0tPKjFbN4rZlRhcA4zBtEkib04yy2WcIzI+AXk
# access_key_id: YOUR_ACCESS_KEY
# secret_access_key: YOUR_SECRET_KEY
#
# # S3 region
# # Default: us-east-1
@@ -304,6 +304,11 @@ storage_url: "rclone://las1stor1//srv/pool.2024.04/backups/heraklion"
# Maximum blob size
# Multiple chunks are packed into blobs up to this size
# Must be at least four times chunk_size (the largest chunk the chunker can
# emit); a smaller limit would let a single-chunk blob exceed it.
# Chunking uses no secret (the FastCDC parameters are fixed and public). At a
# large limit a blob holds hundreds of chunks, so individual chunk lengths are
# not visible in its size; lowering the limit toward chunk_size exposes them.
# Supports: 1GB, 10G, 500MB, 1GiB, etc.
# Default: 10GB
#blob_size_limit: 10GB
docs/DATAMODEL.md
+26 -7
View File
@@ -5,11 +5,30 @@
Vaultik uses a local SQLite database to track file metadata, chunk mappings, and blob associations during the backup process. This database serves as an index for incremental backups and enables efficient deduplication.
**Important Notes:**
- **No Migration Support (pre-1.0)**: Vaultik does not support database schema
migrations. The local index is treated as disposable — if the schema changes,
delete the local SQLite database (`vaultik database delete`) and run a full
backup. The remote storage is unaffected; the new index will re-deduplicate
against existing remote blobs.
This section is the authoritative explanation of the schema/migration story;
other documents (the README and `AGENTS.md`) link here.
- **No upgrade path between versions (pre-1.0)**: Vaultik has no supported way to
carry an existing local index across a schema change. The index is disposable
— if the on-disk schema changes between versions, delete the local SQLite
database (`vaultik database delete`) and run a full backup. Remote storage is
unaffected; the new index re-deduplicates against existing remote blobs. This
is the standing project policy, and it is separate from the schema bootstrap
described next.
- **Schema bootstrap**: a fresh database is populated from numbered SQL files
embedded in the binary under `internal/database/schema/`. `000.sql` creates the
`schema_migrations` table; `001.sql` creates the application tables. On opening
a database the code applies each numbered file that has not yet run and records
its version in `schema_migrations`. This bootstraps a new database; it does not
upgrade an existing one between released versions.
- **Changing the schema (pre-1.0)**: edit `internal/database/schema/001.sql` (and
the code that touches the affected tables) directly. Do not add new numbered
files — there is no installed base to migrate.
- **Disposability expires at 1.0**: the index is treated as disposable only until
1.0 ships and is tagged. Once 1.0 is tagged that clause expires and the
question of upgrading existing indexes returns. It is deliberately left open
here.
- **Version Compatibility**: In rare cases, you may need to use the same version
of Vaultik to restore a backup as was used to create it. This ensures
compatibility with the metadata format stored in S3.
@@ -71,7 +90,7 @@ Stores information about packed, compressed, and encrypted blob files.
**Columns:**
- `id` (TEXT PRIMARY KEY) - UUID assigned when blob creation starts
- `blob_hash` (TEXT UNIQUE) - SHA256 hash of final blob (NULL until finalized)
- `blob_hash` (TEXT UNIQUE) - `hex(SHA256(SHA256(uncompressed blob contents)))`, computed before compression and encryption (NULL until finalized); see [REPOSTRUCTURE.md](REPOSTRUCTURE.md#blobs-directory-blobs)
- `created_ts` (INTEGER NOT NULL) - Creation timestamp
- `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress)
- `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before compression
@@ -197,7 +216,7 @@ After a snapshot is completed:
5. Upload to S3 as `metadata/{remote-key}/db.zst.age`
6. Generate blob manifest and upload as `metadata/{remote-key}/manifest.json.zst`
The `{remote-key}` directory name is a one-way hash of the human snapshot ID, so the ID is never written to the store in plaintext; see [REPOSTRUCTURE.md](REPOSTRUCTURE.md#remote-key-derivation).
The `{remote-key}` directory name is a one-way hash of the human snapshot ID, so the ID is never written to the store in plaintext. The hash uses no secret, so a guessed hostname and snapshot name can still be confirmed against a listing; see [REPOSTRUCTURE.md](REPOSTRUCTURE.md#remote-key-derivation) and its [Accepted Risks](REPOSTRUCTURE.md#accepted-risks).
### 4. Restore Process
docs/REPOSTRUCTURE.md
+21 -8
View File
@@ -35,7 +35,7 @@ The metadata subdirectory is named with the **remote key**, a one-way hash of th
- **What it contains**: Packed collections of content-defined chunks from files
- **Format**: Zstandard compressed, then Age encrypted
- **Encryption**: Always encrypted with Age using the configured recipients
- **Naming**: Content-addressed using SHA256 hash of the encrypted blob
- **Naming**: Content-addressed. The blob's name is `hex(SHA256(SHA256(uncompressed blob contents)))` — the double SHA-256 of the concatenated chunk data, computed before compression and encryption, not a hash of the stored (compressed, encrypted) bytes. One consequence: only a holder of the age private key can check a stored blob's integrity, because matching a blob to its name means decrypting and decompressing it first — which is what `restore` and `verify --deep` do. Implemented in `internal/blobgen` (`DoubleSHA256`). This is the canonical description of blob naming; other documents and comments point here.
### Why Encrypted
Blobs contain the actual file data from backups and must be encrypted for security. The content-addressing ensures deduplication while the encryption ensures privacy.
@@ -59,14 +59,14 @@ This ID reveals the hostname, the configured snapshot name, and the backup time,
### Remote Key Derivation
The remote key is `hex(SHA256(SHA256("vaultik|" + snapshot-id)))`: a double SHA-256 over the snapshot ID, with a `vaultik|` domain-separation prefix. The result is a 64-character hex string with no structure a remote observer can reverse. Implemented in `internal/snapshot/remotekey.go`.
The remote key is `hex(SHA256(SHA256("vaultik|" + snapshot-id)))`: a double SHA-256 over the snapshot ID, with a `vaultik|` domain-separation prefix. The result is a 64-character hex string. The hash is not reversible, but it uses no secret: an observer who guesses a candidate hostname and snapshot name can hash it the same way and confirm whether that snapshot is present. The remote key keeps names out of a plain listing; it does not hide them from a guess. Implemented in `internal/snapshot/remotekey.go`.
Worked example:
- Snapshot ID: `server1_home_2025-06-01T12:00:00Z`
- Remote key: `17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa`
- Directory: `metadata/17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa/`
Because the hash is one-way, a listing of the destination store reveals neither the hostname nor the snapshot name of any backup. The same remote key is stored in the manifest's `snapshot_id` field.
A plain listing of the destination store therefore shows only these hashes, not the hostname or snapshot name of any backup — but because the hash uses no secret, a guessed hostname and snapshot name can be hashed and confirmed against the listing. The same remote key is stored in the manifest's `snapshot_id` field.
### Files in Each Snapshot Directory
@@ -124,31 +124,44 @@ From the unencrypted data, an observer of the destination store can determine:
- **When each backup was taken** — not from the directory name, which is a one-way hash, but from the plaintext `timestamp` field in manifest.json.zst, which is published in the clear
- How many blobs each snapshot references, and the total compressed size
- The compressed size of each blob, and which blobs are shared between snapshots (deduplication patterns)
- **Whether a guessed hostname and snapshot name are present** — the remote key is an unkeyed hash, so an observer holding candidate names can hash each one and match it against the directory listing. The human ID is never published, so it cannot be read off directly, but it can be confirmed by guessing.
Together these give an observer a timing-and-size profile of every snapshot. This is an accepted, documented property of the format, not a defect: the manifest is unencrypted so that pruning can run without the private key, and the timing channel could not be closed by encrypting it anyway — object creation times and per-object sizes stay visible at the storage layer on both `s3://` and `file://` destinations regardless.
An observer cannot determine:
- The hostname or snapshot name of any backup (the directory name and the manifest `snapshot_id` are one-way hashes of the human ID)
- The hostname or snapshot name of any backup by reading it off the store — the directory name and the manifest `snapshot_id` are unkeyed hashes of the human ID, so the text is never published (though a guessed name can be confirmed, as above)
- File names or paths
- File contents
- File permissions or ownership
- Directory structure
- Which chunks belong to which files
### Accepted Risks
These are known, deliberate properties of the format and the tooling, recorded so an operator can weigh them rather than discover them.
1. **No proof of authorship.** Restore and `verify --deep` prove that data decrypts with the age private key and matches its unkeyed content hashes. They do not prove who wrote it: anyone who knows a recipient public key and can replace objects on the destination can substitute a snapshot they built. The recipient string is not stored at the destination, but a compromised backed-up host has it. Defences live on the destination side — bucket versioning or object lock, credentials for the source host that cannot delete or overwrite existing versions, and pruning from a trusted host. Note that S3 `PutObject` overwrites an existing key, so PUT permission alone is not append-only.
2. **Compression reveals sizes.** Blobs and `db.zst.age` are zstd-compressed then age-encrypted; the manifest is compressed only. age does not pad, so an object's size is the exact compressed length of its contents. All new chunks packed into one blob share a single zstd stream (8 MiB window, 4 MiB at compression levels 1-2), and a blob is closed at `blob_size_limit` and at the end of each configured path. Because a stored chunk is never packed again, someone who can write into a backed-up file and watch blob sizes learns something only when their controlled data and a secret land in the same chunk of a file that keeps changing. Advice: back up any outsider-writable directory as its own snapshot.
3. **Chunking uses no secret.** The FastCDC parameters are fixed and public. The default 10 MB average yields chunks between 2.5 MB and 40 MB, and any file of 2.5 MB or less is a single chunk. At the default 10 GB `blob_size_limit` a blob holds hundreds of chunks, so individual chunk lengths are not visible in the blob's size; lowering the limit toward the chunk size begins to expose them.
4. **Decrypted data on local disk.** Several commands stage plaintext under `$TMPDIR`: `snapshot restore` writes decrypted blobs under `vaultik-blobcache-*/` (no size cap) and the decrypted metadata database at `vaultik-restore-*/snapshot.db`; `verify --deep` writes that database at `vaultik-verify-*/snapshot.db`; `snapshot create` keeps a plaintext copy of the index at `vaultik-snapshot-*/snapshot.db`. These files are created `0600` and removed on success, but a `kill -9` or a power loss leaves them behind — delete any leftover `vaultik-*` directory under `$TMPDIR` by hand. `$TMPDIR` should be trusted to the same degree as the restore target.
5. **Store permissions differ per command.** The backed-up host needs only PUT to run `snapshot create`: it writes blobs and metadata and neither reads nor deletes them. Other commands need more — `snapshot verify`, `snapshot restore`, and `prune` list and read; `prune`, `snapshot purge`, `snapshot remove`, and `remote nuke` also delete. The recommended cron line uses `--prune`, which runs `prune` on the backed-up host, so granting that host `--prune` gives it credentials that can delete its own backups. To keep the source host to PUT only, prune from a separate trusted host instead.
6. **Changing recipients does not re-encrypt existing data.** Deduplicated chunks and same-named blobs already on the destination stay encrypted to the recipients in force when they were written. A new snapshot that reuses them cannot be restored with a newly added recipient's key alone, because those reused objects were never encrypted to it. To make everything readable by a new key, run `vaultik database delete` and take a full backup to a fresh destination or prefix.
7. **X25519 recipients only.** vaultik rejects age ssh and plugin recipients. Long-lived ciphertext held by a third party (the destination operator) has no fallback if X25519 is ever broken: there is no second recipient type and no post-quantum option.
## Consistency Guarantees
1. **Blobs are immutable** - Once written, a blob is never modified
2. **Blobs are written before metadata** - A snapshot's metadata is only written after all its blobs are successfully uploaded
3. **Metadata is written atomically** - Both db.zst.age and manifest.json.zst are written as complete files
4. **Snapshots are marked complete in local DB only after metadata upload** - Ensures consistency between local and remote state
4. **A snapshot is marked complete in the local DB before its metadata is uploaded, not after** - `CompleteSnapshot` runs first, then `ExportSnapshotMetadata` (see the backup data flow in [ARCHITECTURE.md](../ARCHITECTURE.md)). A crash between the two leaves a completed-looking row in the local index with no matching metadata on the destination store. `vaultik prune` reconciles this away: it drops any local snapshot whose remote metadata is missing.
## Pruning Safety
The prune operation is safe because:
1. It only deletes blobs not referenced in any manifest
1. It keeps every blob listed in any snapshot's manifest and deletes only blobs that no manifest references
2. Manifests are unencrypted and can be read without keys
3. The operation compares the latest local DB snapshot with the latest S3 snapshot to ensure consistency
4. Pruning will fail if these don't match, preventing accidental deletion of needed blobs
3. If any manifest cannot be downloaded or decoded, prune deletes nothing and exits with an error, rather than treating that snapshot's blobs as unreferenced
4. Prune requires exclusive access to the destination: running it during a concurrent backup can race a snapshot whose manifest is not yet written, so do not prune while a backup is in progress
## Restoration Requirements
internal/blob/packer.go
+9 -7
View File
@@ -1,14 +1,16 @@
// Package blob handles the creation of blobs - the final storage units for Vaultik.
// A blob is a large file (up to 10GB) containing many compressed and encrypted chunks
// from multiple source files. Blobs are content-addressed, meaning their filename
// is derived from the SHA256 hash of their compressed and encrypted content.
// from multiple source files. Blobs are content-addressed: a blob's filename is
// hex(SHA256(SHA256(uncompressed blob contents))), computed from the concatenated
// chunk data before compression and encryption, not from the stored bytes. See
// blobgen.DoubleSHA256 and docs/REPOSTRUCTURE.md.
//
// The blob creation process:
// 1. Chunks are accumulated from multiple files
// 2. The collection is compressed using zstd
// 3. The compressed data is encrypted using age
// 4. The encrypted blob is hashed to create its content-addressed name
// 5. The blob is uploaded to S3 using the hash as the filename
// 2. Each chunk's uncompressed bytes are fed to a running SHA-256 and, in the same
// pass, compressed with zstd and encrypted with age into the temp file
// 3. On finalize, the name is the double SHA-256 of that uncompressed content
// 4. The blob is uploaded to S3 using the name as the filename
//
// This design optimizes storage efficiency by batching many small chunks into
// larger blobs, reducing the number of S3 operations and associated costs.
@@ -487,7 +489,7 @@ func (p *Packer) closeBlobWriter() (string, int64, error) {
return "", 0, fmt.Errorf("seeking to start: %w", err)
}
finalHash := p.currentBlob.writer.Sum256()
finalHash := p.currentBlob.writer.ContentID()
return hex.EncodeToString(finalHash), finalSize, nil
}
internal/blobgen/compress.go
-89
View File
@@ -1,89 +0,0 @@
// Package blobgen implements the blob data pipeline: streaming zstd
// compression, age encryption, and SHA256 content hashing for blob
// creation, plus the matching decrypt/decompress/verify reader.
package blobgen
import (
"bytes"
"encoding/hex"
"fmt"
"io"
)
// CompressResult contains the results of compression
type CompressResult struct {
Data []byte
UncompressedSize int64
CompressedSize int64
SHA256 string
}
// CompressData compresses and encrypts data, returning the result with hash
func CompressData(
data []byte, compressionLevel int, recipients []string,
) (*CompressResult, error) {
var buf bytes.Buffer
// Create writer
w, err := NewWriter(&buf, compressionLevel, recipients)
if err != nil {
return nil, fmt.Errorf("creating writer: %w", err)
}
// Write data
_, err = w.Write(data)
if err != nil {
_ = w.Close()
return nil, fmt.Errorf("writing data: %w", err)
}
// Close to flush
err = w.Close()
if err != nil {
return nil, fmt.Errorf("closing writer: %w", err)
}
return &CompressResult{
Data: buf.Bytes(),
UncompressedSize: int64(len(data)),
CompressedSize: int64(buf.Len()),
SHA256: hex.EncodeToString(w.Sum256()),
}, nil
}
// CompressStream compresses and encrypts from reader to writer, returning
// the number of uncompressed bytes written and the content hash.
func CompressStream(
dst io.Writer, src io.Reader, compressionLevel int, recipients []string,
) (int64, string, error) {
// Create writer
w, err := NewWriter(dst, compressionLevel, recipients)
if err != nil {
return 0, "", fmt.Errorf("creating writer: %w", err)
}
closed := false
defer func() {
if !closed {
_ = w.Close()
}
}()
// Copy data
_, err = io.Copy(w, src)
if err != nil {
return 0, "", fmt.Errorf("copying data: %w", err)
}
// Close to flush
err = w.Close()
if err != nil {
return 0, "", fmt.Errorf("closing writer: %w", err)
}
closed = true
return w.BytesWritten(), hex.EncodeToString(w.Sum256()), nil
}
internal/blobgen/compress_test.go
-80
View File
@@ -1,80 +0,0 @@
package blobgen_test
import (
"bytes"
"crypto/rand"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// testRecipient is a static age recipient for tests.
const testRecipient = "age1cplgrwj77ta54dnmydvvmzn64ltk83ankxl5sww04mrtmu62kv3s89gmvv"
// TestCompressStreamNoDoubleClose is a regression test for issue #28.
// It verifies that CompressStream does not panic or return an error due to
// double-closing the underlying blobgen.Writer. Before the fix in PR #33,
// the explicit Close() on the happy path combined with defer Close() would
// cause a double close.
func TestCompressStreamNoDoubleClose(t *testing.T) {
t.Parallel()
input := []byte("regression test data for issue #28 double-close fix")
var buf bytes.Buffer
written, hash, err := blobgen.CompressStream(
&buf, bytes.NewReader(input), 3, []string{testRecipient})
require.NoError(t, err, "CompressStream should not return an error")
assert.Positive(t, written, "expected bytes written > 0")
assert.NotEmpty(t, hash, "expected non-empty hash")
assert.Positive(t, buf.Len(), "expected non-empty output")
}
// TestCompressStreamLargeInput exercises CompressStream with a larger payload
// to ensure no double-close issues surface under heavier I/O.
func TestCompressStreamLargeInput(t *testing.T) {
t.Parallel()
data := make([]byte, 512*1024) // 512 KB
_, err := rand.Read(data)
require.NoError(t, err)
var buf bytes.Buffer
written, hash, err := blobgen.CompressStream(
&buf, bytes.NewReader(data), 3, []string{testRecipient})
require.NoError(t, err)
assert.Positive(t, written)
assert.NotEmpty(t, hash)
}
// TestCompressStreamEmptyInput verifies CompressStream handles empty input
// without double-close issues.
func TestCompressStreamEmptyInput(t *testing.T) {
t.Parallel()
var buf bytes.Buffer
_, hash, err := blobgen.CompressStream(
&buf, strings.NewReader(""), 3, []string{testRecipient})
require.NoError(t, err)
assert.NotEmpty(t, hash)
}
// TestCompressDataNoDoubleClose mirrors the stream test for CompressData,
// ensuring the explicit Close + error-path Close pattern is also safe.
func TestCompressDataNoDoubleClose(t *testing.T) {
t.Parallel()
input := []byte("CompressData regression test for double-close")
result, err := blobgen.CompressData(input, 3, []string{testRecipient})
require.NoError(t, err)
assert.Positive(t, result.CompressedSize)
assert.Equal(t, result.UncompressedSize, int64(len(input)))
assert.NotEmpty(t, result.SHA256)
}
internal/blobgen/helpers_test.go
+119
View File
@@ -0,0 +1,119 @@
package blobgen_test
import (
"bytes"
"crypto/rand"
"errors"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// ageChunkSize is age's STREAM plaintext chunk size (64 KiB); each encrypted
// chunk adds a 16-byte ChaCha20-Poly1305 tag.
const (
ageChunkSize = 64 * 1024
ageChunkTagSize = 16
ageSegmentSize = ageChunkSize + ageChunkTagSize
ageNonceSize = 16
)
// makeIdentity returns a fresh X25519 identity and its recipient string.
func makeIdentity(t *testing.T) (*age.X25519Identity, string) {
t.Helper()
id, err := age.GenerateX25519Identity()
require.NoError(t, err)
return id, id.Recipient().String()
}
// randomBytes returns n cryptographically random bytes, which do not compress
// so the encrypted payload spans multiple age segments.
func randomBytes(t *testing.T, n int) []byte {
t.Helper()
b := make([]byte, n)
_, err := rand.Read(b)
require.NoError(t, err)
return b
}
// compressibleBytes returns n bytes of a repeating pattern, which zstd packs
// down to a small payload.
func compressibleBytes(n int) []byte {
pattern := bytes.Repeat([]byte("compressible-"), n/13+1)
return pattern[:n]
}
// encryptBlob compresses, encrypts and returns a blob for plaintext at
// compression level 1.
func encryptBlob(t *testing.T, plaintext []byte, recipients ...string) []byte {
t.Helper()
var buf bytes.Buffer
w, err := blobgen.NewWriter(&buf, 1, recipients)
require.NoError(t, err)
_, err = w.Write(plaintext)
require.NoError(t, err)
require.NoError(t, w.Close())
return buf.Bytes()
}
// ageHeaderLen returns the byte length of blob's age header, i.e. the offset
// of the 16-byte payload nonce that follows it. The header ends with a MAC
// line "--- <mac>\n"; the nonce begins right after that newline.
func ageHeaderLen(t *testing.T, blob []byte) int {
t.Helper()
i := bytes.Index(blob, []byte("\n--- "))
require.GreaterOrEqual(t, i, 0, "age MAC footer line not found")
nl := bytes.IndexByte(blob[i+1:], '\n')
require.GreaterOrEqual(t, nl, 0, "newline ending MAC line not found")
return i + 1 + nl + 1
}
// requireBlobUnreadable asserts that data never decrypts to a plaintext with a
// nil error: either NewReader fails, or reading it does.
func requireBlobUnreadable(t *testing.T, data []byte, id age.Identity) {
t.Helper()
r, err := blobgen.NewReader(bytes.NewReader(data), id)
if err != nil {
return
}
_, err = io.ReadAll(r)
_ = r.Close()
require.Error(t, err, "reading a damaged blob must fail")
}
// errFailWriter is returned by failAfterWriter once its byte limit is passed.
var errFailWriter = errors.New("destination write failed")
// failAfterWriter accepts writes until more than limit bytes have been sent,
// then fails every write. It models a destination that dies mid-blob.
type failAfterWriter struct {
limit int
written int
}
func (f *failAfterWriter) Write(p []byte) (int, error) {
f.written += len(p)
if f.written > f.limit {
return 0, errFailWriter
}
return len(p), nil
}
internal/blobgen/limit.go
+49
View File
@@ -0,0 +1,49 @@
package blobgen
import (
"errors"
"io"
)
// ErrOutputTooLarge is returned by a reader from LimitReader once it has
// been asked for more than its limit. It bounds how far an untrusted
// compressed stream may expand, so a small, highly compressible object
// from the store cannot decompress without limit.
var ErrOutputTooLarge = errors.New("output exceeds size limit")
// LimitReader returns a reader that yields at most limit bytes from r and
// then fails with ErrOutputTooLarge. Unlike io.LimitReader, which reports
// a silent io.EOF at the limit (indistinguishable from a stream that
// simply ended), this fails, so a caller decoding or copying the stream
// sees an error rather than a truncated value. A stream of exactly limit
// bytes reads back cleanly to EOF; the first byte beyond it is the error.
func LimitReader(r io.Reader, limit int64) io.Reader {
// remaining counts down from limit+1: the extra byte is the one that,
// if it ever arrives, proves the stream is longer than the limit.
return &limitReader{r: r, remaining: limit + 1}
}
type limitReader struct {
r io.Reader
remaining int64
}
func (l *limitReader) Read(p []byte) (int, error) {
if l.remaining <= 0 {
return 0, ErrOutputTooLarge
}
if int64(len(p)) > l.remaining {
p = p[:l.remaining]
}
n, err := l.r.Read(p)
l.remaining -= int64(n)
if l.remaining <= 0 {
// The (limit+1)th byte was just read: the stream is too long.
return n, ErrOutputTooLarge
}
return n, err
}
internal/blobgen/limit_test.go
+43
View File
@@ -0,0 +1,43 @@
package blobgen_test
import (
"bytes"
"io"
"testing"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestLimitReaderPassesExactSize checks that a stream of exactly the limit
// reads back cleanly to EOF: the bound must not reject a legitimate blob
// whose plaintext equals its recorded size.
func TestLimitReaderPassesExactSize(t *testing.T) {
t.Parallel()
const n = 1000
r := blobgen.LimitReader(bytes.NewReader(bytes.Repeat([]byte("a"), n)), n)
got, err := io.ReadAll(r)
require.NoError(t, err)
require.Len(t, got, n)
}
// TestLimitReaderFailsPastLimit feeds a large, highly compressible run of
// zeros — the decompressed output a zip bomb would produce — through a
// small limit and checks it fails within the bound rather than passing
// the whole stream through.
func TestLimitReaderFailsPastLimit(t *testing.T) {
t.Parallel()
const limit = 1000
r := blobgen.LimitReader(
bytes.NewReader(bytes.Repeat([]byte{0}, limit*1000)), limit)
n, err := io.Copy(io.Discard, r)
require.ErrorIs(t, err, blobgen.ErrOutputTooLarge)
require.LessOrEqual(t, n, int64(limit)+1,
"reader must stop within one byte of the limit")
}
internal/blobgen/negative_test.go
+190
View File
@@ -0,0 +1,190 @@
package blobgen_test
import (
"bytes"
"fmt"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestNewReaderWrongIdentity covers issue case 4: opening a blob with an
// identity other than the recipient reports no matching identity.
func TestNewReaderWrongIdentity(t *testing.T) {
t.Parallel()
_, recipient := makeIdentity(t)
other, _ := makeIdentity(t)
blob := encryptBlob(t, []byte("secret payload"), recipient)
_, err := blobgen.NewReader(bytes.NewReader(blob), other)
require.Error(t, err)
var noMatch *age.NoIdentityMatchError
assert.ErrorAs(t, err, &noMatch)
}
// TestNewReaderTruncated covers issue case 6: a multi-segment blob cut at
// several points must never read back as valid data. The point immediately
// after the header and nonce is intentionally excluded: it reads as a valid
// empty blob today and is the regression case for
// https://git.eeqj.de/sneak/vaultik/issues/152.
func TestNewReaderTruncated(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
blob := encryptBlob(t, randomBytes(t, 4*65536+123), recipient)
h := ageHeaderLen(t, blob)
require.Greater(t, len(blob), h+ageNonceSize+ageSegmentSize,
"test needs a blob of at least two age segments")
cases := []struct {
name string
size int
}{
{"inside header", h / 2},
{"inside nonce", h + 8},
{"inside first segment", h + ageNonceSize + 100},
{"end of first full segment", h + ageNonceSize + ageSegmentSize},
{"last byte removed", len(blob) - 1},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
requireBlobUnreadable(t, blob[:tc.size], id)
})
}
}
// TestNewReaderCorrupted covers issue case 7: one flipped byte in each region
// of a multi-segment blob makes it unreadable.
func TestNewReaderCorrupted(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
blob := encryptBlob(t, randomBytes(t, 4*65536+123), recipient)
h := ageHeaderLen(t, blob)
firstNL := bytes.IndexByte(blob, '\n')
require.Positive(t, firstNL, "header must have a version line")
cases := []struct {
name string
pos int
}{
{"header stanza", firstNL + 5},
{"header MAC line", h - 2},
{"nonce", h + 4},
{"body segment", h + ageNonceSize + 50},
{"final tag", len(blob) - 1},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
corrupt := append([]byte(nil), blob...)
corrupt[tc.pos] ^= 0xff
requireBlobUnreadable(t, corrupt, id)
})
}
}
// TestNewReaderTrailingAndGarbage covers issue case 8: bytes appended after a
// valid blob, empty input, and random garbage each fail to read.
func TestNewReaderTrailingAndGarbage(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
valid := encryptBlob(t, []byte("small payload"), recipient)
appended := append(append([]byte(nil), valid...), []byte("trailing junk")...)
t.Run("appended bytes", func(t *testing.T) {
t.Parallel()
requireBlobUnreadable(t, appended, id)
})
t.Run("empty input", func(t *testing.T) {
t.Parallel()
requireBlobUnreadable(t, []byte{}, id)
})
t.Run("random garbage", func(t *testing.T) {
t.Parallel()
requireBlobUnreadable(t, randomBytes(t, 512), id)
})
}
// TestNewWriterInvalidLevel covers the rejected end of issue case 9: an
// out-of-range compression level errors and writes nothing to the destination.
func TestNewWriterInvalidLevel(t *testing.T) {
t.Parallel()
_, recipient := makeIdentity(t)
for _, level := range []int{0, -1, 20} {
t.Run(fmt.Sprintf("level%d", level), func(t *testing.T) {
t.Parallel()
var buf bytes.Buffer
w, err := blobgen.NewWriter(&buf, level, []string{recipient})
require.ErrorIs(t, err, blobgen.ErrInvalidCompressionLevel)
assert.Nil(t, w)
assert.Zero(t, buf.Len(), "nothing written on an invalid level")
})
}
}
// TestNewWriterInvalidRecipients covers issue case 10: nil and empty recipient
// lists and an unparsable recipient string each error.
func TestNewWriterInvalidRecipients(t *testing.T) {
t.Parallel()
cases := []struct {
name string
recipients []string
}{
{"nil list", nil},
{"empty list", []string{}},
{"invalid recipient string", []string{"not-a-recipient"}},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
var buf bytes.Buffer
w, err := blobgen.NewWriter(&buf, 1, tc.recipients)
require.Error(t, err)
assert.Nil(t, w)
})
}
}
// TestNewWriterFailingDestination covers issue case 11: a destination that
// fails mid-blob surfaces its error from Write or Close.
func TestNewWriterFailingDestination(t *testing.T) {
t.Parallel()
_, recipient := makeIdentity(t)
// The limit clears the age header and nonce so NewWriter succeeds, then
// trips once the compressed body starts flowing.
dst := &failAfterWriter{limit: 512}
w, err := blobgen.NewWriter(dst, 1, []string{recipient})
require.NoError(t, err)
_, writeErr := w.Write(randomBytes(t, 256*1024))
closeErr := w.Close()
assert.True(t, writeErr != nil || closeErr != nil,
"destination failure must surface from Write or Close")
}
internal/blobgen/reader.go
+25 -4
View File
@@ -2,6 +2,7 @@ package blobgen
import (
"crypto/sha256"
"errors"
"fmt"
"hash"
"io"
@@ -20,10 +21,12 @@ type Reader struct {
bytesRead int64
}
// NewReader creates a new Reader that decrypts, decompresses, and verifies data
func NewReader(r io.Reader, identity age.Identity) (*Reader, error) {
// NewReader creates a new Reader that decrypts, decompresses, and verifies
// data. Every supplied identity is offered to age.Decrypt, so a blob
// encrypted to any one of them can be read.
func NewReader(r io.Reader, identities ...age.Identity) (*Reader, error) {
// Create decryption reader
decReader, err := age.Decrypt(r, identity)
decReader, err := age.Decrypt(r, identities...)
if err != nil {
return nil, fmt.Errorf("creating decryption reader: %w", err)
}
@@ -54,6 +57,22 @@ func (r *Reader) Read(p []byte) (int, error) {
n, err := r.teeReader.Read(p)
r.bytesRead += int64(n)
// When the ciphertext is cut right after the age header plus its
// 16-byte nonce, the age reader's first read fails with
// io.ErrUnexpectedEOF, and the zstd decoder maps that to a clean
// io.EOF at frame start. That makes a truncated stream look like a
// valid empty one. Distinguish the two: on EOF, read once more from
// the age reader. A genuine end leaves it at (0, io.EOF); a truncated
// stream leaves its stored io.ErrUnexpectedEOF, which we surface.
if errors.Is(err, io.EOF) {
var probe [1]byte
m, ageErr := r.decryptor.Read(probe[:])
if m != 0 || !errors.Is(ageErr, io.EOF) {
return n, io.ErrUnexpectedEOF
}
}
return n, err
}
@@ -64,7 +83,9 @@ func (r *Reader) Close() error {
return nil
}
// Sum256 returns the SHA256 hash of all data read
// Sum256 returns the single SHA-256 of the plaintext read so far. This is the
// first hash only; the stored object name is its double hash, which callers
// obtain by passing this digest to DoubleSHA256.
func (r *Reader) Sum256() []byte {
return r.hasher.Sum(nil)
}
internal/blobgen/reader_test.go
+54
View File
@@ -0,0 +1,54 @@
package blobgen_test
import (
"bytes"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestMultipleRecipients verifies that data written for several recipients can
// be read back by each recipient's identity. Moved from internal/crypto, which
// held the only multi-recipient test; blobgen is now the sole encryption path.
func TestMultipleRecipients(t *testing.T) {
t.Parallel()
identities := make([]*age.X25519Identity, 3)
recipients := make([]string, 3)
for i := range identities {
identity, err := age.GenerateX25519Identity()
require.NoError(t, err)
identities[i] = identity
recipients[i] = identity.Recipient().String()
}
plaintext := []byte("Secret message for multiple recipients")
var encrypted bytes.Buffer
writer, err := blobgen.NewWriter(&encrypted, 3, recipients)
require.NoError(t, err)
_, err = writer.Write(plaintext)
require.NoError(t, err)
require.NoError(t, writer.Close())
// Every recipient's identity must recover the original plaintext.
for i, identity := range identities {
reader, err := blobgen.NewReader(
bytes.NewReader(encrypted.Bytes()), identity)
require.NoError(t, err, "recipient %d should open the reader", i+1)
got, err := io.ReadAll(reader)
require.NoError(t, err, "recipient %d should read the plaintext", i+1)
require.NoError(t, reader.Close())
assert.Equal(t, plaintext, got,
"recipient %d should recover the original plaintext", i+1)
}
}
internal/blobgen/roundtrip_test.go
+132
View File
@@ -0,0 +1,132 @@
package blobgen_test
import (
"bytes"
"crypto/sha256"
"fmt"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// checkRoundTrip writes input through a Writer, reads it back through a Reader,
// and verifies the plaintext, the byte counts, and the content hashes.
func checkRoundTrip(
t *testing.T, id *age.X25519Identity, recipient string,
level int, input []byte,
) {
t.Helper()
var buf bytes.Buffer
w, err := blobgen.NewWriter(&buf, level, []string{recipient})
require.NoError(t, err)
n, err := w.Write(input)
require.NoError(t, err)
assert.Equal(t, len(input), n)
require.NoError(t, w.Close())
require.Equal(t, int64(len(input)), w.BytesWritten())
r, err := blobgen.NewReader(bytes.NewReader(buf.Bytes()), id)
require.NoError(t, err)
got, err := io.ReadAll(r)
require.NoError(t, err)
require.NoError(t, r.Close())
assert.Equal(t, input, got, "decrypted output must equal input")
require.Equal(t, int64(len(input)), r.BytesRead())
// The hash values are checked by decrypting: the reader's single SHA-256
// is the hash of the plaintext, and hashing it once more (DoubleSHA256)
// gives the writer's ContentID.
single := sha256.Sum256(got)
assert.Equal(t, single[:], r.Sum256())
assert.Equal(t, blobgen.DoubleSHA256(r.Sum256()), w.ContentID())
}
// TestWriterReaderRoundTrip covers issue cases 1 and 2: every size round trips
// for both random and compressible data, and the reader hash, its double hash
// and the byte counts all agree.
func TestWriterReaderRoundTrip(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
// Sizes exercise the age segment boundary (64 KiB) from just below to a
// few segments above it, plus the empty and single-byte edges.
sizes := []int{0, 1, 65535, 65536, 65537, 4*65536 + 123}
kinds := []struct {
name string
fill func(*testing.T, int) []byte
}{
{"random", randomBytes},
{"compressible", func(_ *testing.T, n int) []byte {
return compressibleBytes(n)
}},
}
for _, k := range kinds {
for _, size := range sizes {
name := fmt.Sprintf("%s/%d", k.name, size)
t.Run(name, func(t *testing.T) {
t.Parallel()
checkRoundTrip(t, id, recipient, 1, k.fill(t, size))
})
}
}
}
// TestZeroLengthNoWrite covers issue case 3: a Writer closed with no Write at
// all produces the double hash of the empty input, and the blob reads back as
// empty with no error.
func TestZeroLengthNoWrite(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
var buf bytes.Buffer
w, err := blobgen.NewWriter(&buf, 1, []string{recipient})
require.NoError(t, err)
require.NoError(t, w.Close())
assert.Equal(t, int64(0), w.BytesWritten())
empty := sha256.Sum256(nil)
doubled := sha256.Sum256(empty[:])
assert.Equal(t, doubled[:], w.ContentID(),
"ContentID of empty input is SHA256(SHA256(\"\"))")
r, err := blobgen.NewReader(bytes.NewReader(buf.Bytes()), id)
require.NoError(t, err)
got, err := io.ReadAll(r)
require.NoError(t, err)
require.NoError(t, r.Close())
assert.Empty(t, got, "empty blob decrypts to empty output")
assert.Equal(t, int64(0), r.BytesRead())
assert.Equal(t, empty[:], r.Sum256())
}
// TestNewWriterValidLevelsRoundTrip covers the accepted end of issue case 9:
// the boundary compression levels 1 and 19 both round trip.
func TestNewWriterValidLevelsRoundTrip(t *testing.T) {
t.Parallel()
id, recipient := makeIdentity(t)
input := randomBytes(t, 4096)
for _, level := range []int{1, 19} {
t.Run(fmt.Sprintf("level%d", level), func(t *testing.T) {
t.Parallel()
checkRoundTrip(t, id, recipient, level, input)
})
}
}
internal/blobgen/truncation_test.go
+70
View File
@@ -0,0 +1,70 @@
package blobgen_test
import (
"bytes"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestReaderRejectsHeaderNonceTruncation guards against a stream cut right
// after the age header plus its 16-byte nonce. age.Decrypt still succeeds on
// such an object, and the zstd decoder maps the age reader's
// io.ErrUnexpectedEOF to a clean io.EOF at frame start, so without the extra
// check the truncated stream would read as a valid empty one. Reading it must
// now fail.
func TestReaderRejectsHeaderNonceTruncation(t *testing.T) {
t.Parallel()
identity, err := age.GenerateX25519Identity()
require.NoError(t, err)
// Encrypting empty plaintext yields header + nonce(16) + a single
// 16-byte final chunk tag. Dropping the trailing tag leaves exactly the
// age header plus its nonce — the truncation point that triggers the bug.
var full bytes.Buffer
w, err := age.Encrypt(&full, identity.Recipient())
require.NoError(t, err)
require.NoError(t, w.Close())
truncated := full.Bytes()[:full.Len()-16]
reader, err := blobgen.NewReader(bytes.NewReader(truncated), identity)
require.NoError(t, err)
defer func() { _ = reader.Close() }()
_, err = io.ReadAll(reader)
require.Error(t, err)
require.ErrorIs(t, err, io.ErrUnexpectedEOF)
}
// TestReaderReadsGenuinelyEmptyBlob confirms the truncation check does not
// reject a legitimately empty payload: a blob written with no data must round
// trip back to zero bytes with no error.
func TestReaderReadsGenuinelyEmptyBlob(t *testing.T) {
t.Parallel()
identity, err := age.GenerateX25519Identity()
require.NoError(t, err)
var encrypted bytes.Buffer
writer, err := blobgen.NewWriter(
&encrypted, 3, []string{identity.Recipient().String()})
require.NoError(t, err)
require.NoError(t, writer.Close())
reader, err := blobgen.NewReader(bytes.NewReader(encrypted.Bytes()), identity)
require.NoError(t, err)
defer func() { _ = reader.Close() }()
data, err := io.ReadAll(reader)
require.NoError(t, err)
require.Empty(t, data)
}
internal/blobgen/writer.go
+36 -13
View File
@@ -1,3 +1,6 @@
// Package blobgen implements the blob data pipeline: streaming zstd
// compression, age encryption, and SHA256 content hashing for blob
// creation, plus the matching decrypt/decompress/verify reader.
package blobgen
import (
@@ -12,6 +15,24 @@ import (
"github.com/klauspost/compress/zstd"
)
// DoubleSHA256 returns the double SHA-256 of content whose single SHA-256
// digest is sum: it hashes that digest once more. Stored objects — a blob, and
// the metadata database export — are named by this second hash.
//
// The second hash does not hide whether known content is stored: an attacker
// who can reproduce an object's entire plaintext computes the same name simply
// by hashing twice, exactly as this code does. What limits that is blob
// packing, not the double hash — a blob's name covers all of its concatenated
// chunk plaintext, so a name can be confirmed only by someone who can
// reproduce the whole blob (a snapshot made entirely of known content, or a
// known file large enough to fill blobs on its own). An ordinary file that
// shares a blob with other, unknown data cannot be confirmed this way.
func DoubleSHA256(sum []byte) []byte {
h := sha256.Sum256(sum)
return h[:]
}
// Zstd compression level bounds accepted by NewWriter.
const (
minCompressionLevel = 1
@@ -27,6 +48,11 @@ const reservedCompressionCPUs = 2
var ErrInvalidCompressionLevel = errors.New(
"invalid compression level: must be between 1 and 19")
// errInvalidRecipient is returned when a recipient string does not parse as
// an X25519 age1... public key. It omits the value, which can be sensitive.
var errInvalidRecipient = errors.New(
"not a valid X25519 age1... recipient")
// Writer wraps compression and encryption with SHA256 hashing.
// Data flows: input -> tee(hasher, compressor -> encryptor -> destination)
// The hash is computed on the uncompressed input for deterministic content-addressing.
@@ -57,10 +83,12 @@ func NewWriter(
// Parse recipients
var ageRecipients []age.Recipient
for _, recipient := range recipients {
for i, recipient := range recipients {
// The recipient string can be sensitive (e.g. a secret key pasted by
// mistake), so the error names its position, never its value.
r, err := age.ParseX25519Recipient(recipient)
if err != nil {
return nil, fmt.Errorf("parsing recipient %s: %w", recipient, err)
return nil, fmt.Errorf("%w: recipient %d", errInvalidRecipient, i)
}
ageRecipients = append(ageRecipients, r)
@@ -123,17 +151,12 @@ func (w *Writer) Close() error {
return nil
}
// Sum256 returns the double SHA256 hash of the uncompressed input data.
// Double hashing (SHA256(SHA256(data))) prevents information leakage about
// the plaintext - an attacker cannot confirm existence of known content
// by computing its hash and checking for a matching blob filename.
func (w *Writer) Sum256() []byte {
// First hash: SHA256(plaintext)
firstHash := w.hasher.Sum(nil)
// Second hash: SHA256(firstHash) - this is the blob ID
secondHash := sha256.Sum256(firstHash)
return secondHash[:]
// ContentID returns the double SHA-256 of the uncompressed input data: the
// name under which this content is stored. It is the second hash of the
// running SHA-256, via DoubleSHA256; see that function for what naming content
// this way does and does not hide.
func (w *Writer) ContentID() []byte {
return DoubleSHA256(w.hasher.Sum(nil))
}
// BytesWritten returns the number of uncompressed bytes written
internal/blobgen/writer_test.go
+27 -9
View File
@@ -12,9 +12,10 @@ import (
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestWriterHashIsDoubleHash verifies that Writer.Sum256() returns
// the double hash SHA256(SHA256(plaintext)) for security.
// Double hashing prevents attackers from confirming existence of known content.
// TestWriterHashIsDoubleHash verifies that Writer.ContentID() returns
// SHA256(SHA256(plaintext)). Stored objects are named by this second hash so a
// name is not the plaintext's own SHA-256; this does not stop someone who
// already holds the plaintext from confirming it.
func TestWriterHashIsDoubleHash(t *testing.T) {
t.Parallel()
@@ -43,7 +44,7 @@ func TestWriterHashIsDoubleHash(t *testing.T) {
require.NoError(t, err)
// Get the hash from the writer
writerHash := hex.EncodeToString(writer.Sum256())
writerHash := hex.EncodeToString(writer.ContentID())
// Calculate the expected double hash: SHA256(SHA256(plaintext))
firstHash := sha256.Sum256(testData)
@@ -60,11 +61,11 @@ func TestWriterHashIsDoubleHash(t *testing.T) {
// The writer hash should match the double hash
assert.Equal(t, expectedDoubleHash, writerHash,
"Writer.Sum256() should return SHA256(SHA256(plaintext)) for security")
"Writer.ContentID() must be SHA256(SHA256(plaintext))")
// Verify it's NOT the single hash (would leak information)
// It must be the second hash, not the plaintext's own SHA-256.
assert.NotEqual(t, singleHashStr, writerHash,
"Writer hash should not be single hash (would allow content confirmation attacks)")
"Writer hash must be the double hash, not the single SHA-256")
}
// TestWriterDeterministicHash verifies that the same input always produces
@@ -93,8 +94,8 @@ func TestWriterDeterministicHash(t *testing.T) {
require.NoError(t, err)
require.NoError(t, writer2.Close())
hash1 := hex.EncodeToString(writer1.Sum256())
hash2 := hex.EncodeToString(writer2.Sum256())
hash1 := hex.EncodeToString(writer1.ContentID())
hash2 := hex.EncodeToString(writer2.ContentID())
// Hashes should be identical (deterministic)
assert.Equal(t, hash1, hash2, "Same input should produce same hash")
@@ -108,3 +109,20 @@ func TestWriterDeterministicHash(t *testing.T) {
t.Logf("Encrypted size 1: %d bytes", buf1.Len())
t.Logf("Encrypted size 2: %d bytes", buf2.Len())
}
// TestNewWriterSecretKeyNotEchoed verifies that a secret key mistakenly passed
// as a recipient does not appear in the returned error. A recipient string can
// be sensitive, so the error must name only the position, not the value.
func TestNewWriterSecretKeyNotEchoed(t *testing.T) {
t.Parallel()
secretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GX" +
"VEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
var buf bytes.Buffer
_, err := blobgen.NewWriter(&buf, 3, []string{secretKey})
require.Error(t, err)
assert.NotContains(t, err.Error(), secretKey,
"error must not echo the recipient value")
}
internal/chunker/chunker.go
+5 -4
View File
@@ -33,9 +33,10 @@ type Chunker struct {
maxChunkSize int
}
// chunkSizeSpread is the FastCDC-recommended factor between the average
// ChunkSizeSpread is the FastCDC-recommended factor between the average
// chunk size and the minimum (avg/spread) and maximum (avg*spread) sizes.
const chunkSizeSpread = 4
// The largest chunk the chunker can emit is therefore avg*ChunkSizeSpread.
const ChunkSizeSpread = 4
// NewChunker creates a new chunker with the specified average chunk size.
// The actual chunk sizes will vary between avgChunkSize/4 and avgChunkSize*4
@@ -45,8 +46,8 @@ func NewChunker(avgChunkSize int64) *Chunker {
// FastCDC recommends min = avg/4 and max = avg*4
return &Chunker{
avgChunkSize: int(avgChunkSize),
minChunkSize: int(avgChunkSize / chunkSizeSpread),
maxChunkSize: int(avgChunkSize * chunkSizeSpread),
minChunkSize: int(avgChunkSize / ChunkSizeSpread),
maxChunkSize: int(avgChunkSize * ChunkSizeSpread),
}
}
internal/cli/app.go
+114 -77
View File
@@ -7,12 +7,9 @@ import (
"context"
"errors"
"fmt"
"os"
"os/signal"
"path/filepath"
"strings"
"sync"
"syscall"
"time"
"github.com/adrg/xdg"
@@ -33,14 +30,33 @@ import (
// may take before we give up.
const shutdownTimeout = 30 * time.Second
// AppOptions contains common options for creating the fx application.
// It includes the configuration file path, logging options, and additional
// fx modules and invocations that should be included in the application.
// lockMode says whether a command mutates persistent state — the local
// index database or the remote store — and so must hold the process-wide
// PID lock, or only reads that state and may run alongside a mutator.
type lockMode int
const (
// mutating commands (snapshot create, snapshot purge, snapshot remove,
// prune, remote nuke) write the local index or the remote store. They
// hold the PID lock so that at most one runs at a time.
mutating lockMode = iota
// readOnly commands (info, snapshot list, snapshot verify, remote info,
// snapshot restore) do not write the local index or the remote store,
// so they run without the lock and are never blocked by a running
// mutator. restore writes only to the target directory it is given.
readOnly
)
// AppOptions contains common options for creating and running the fx
// application: the configuration file path, logging options, additional fx
// modules and invocations, and whether the command mutates persistent
// state (which decides whether it takes the PID lock).
type AppOptions struct {
ConfigPath string
LogOptions log.Options
Modules []fx.Option
Invokes []fx.Option
Mode lockMode
}
// setupGlobals records the startup time and, when an output-suppression
@@ -49,6 +65,11 @@ type AppOptions struct {
// silenced — per the documented convention that --quiet suppresses
// non-error output only. The startup banner is printed by Entry
// before cobra parses arguments, gated by the same arg-level check.
//
// --json quiets the UI here too, because stdout then carries a JSON
// document and human narration would corrupt it. Unlike Quiet it does
// not lower the stderr log level (issue #112), so --verbose/--debug
// still surface diagnostics alongside the document.
func setupGlobals(
lc fx.Lifecycle, g *globals.Globals, v *vaultik.Vaultik, opts log.Options,
) {
@@ -56,7 +77,7 @@ func setupGlobals(
OnStart: func(_ context.Context) error {
g.StartTime = time.Now().UTC()
if opts.Cron || opts.Quiet {
if opts.Cron || opts.Quiet || opts.JSON {
v.UI.SetQuiet(true)
}
@@ -137,64 +158,45 @@ func cleanStartupError(err error) error {
return &startupError{msg: msg}
}
// RunApp starts and stops the fx application within the given context.
// It handles graceful shutdown on interrupt signals (SIGINT, SIGTERM) and
// ensures the application stops cleanly. The function blocks until the
// application completes or is interrupted. Returns an error if startup fails.
// RunApp starts the fx application, blocks until it is asked to stop, and
// then stops it. The app is asked to stop either by an OS interrupt
// (SIGINT/SIGTERM — fx installs its own handler when app.Wait is called) or,
// on normal completion, by the finished operation calling
// Shutdowner.Shutdown(); both arrive on the app.Wait channel.
//
// Stopping runs the fx OnStop hooks, and RunApp does not return until Stop
// returns. On an interrupt the operation's OnStop hook cancels the running
// command and waits for it to unwind — removing its decrypted scratch files —
// so the process cannot proceed to exit mid-cleanup (issue #159). Waiting for
// Stop before returning is what makes that hook effective: routing the
// interrupt through app.Stop and not returning until it completes is required,
// because fx also fires the app.Wait channel on the signal, and an earlier
// version returned on that alone — unwinding to os.Exit while the concurrent
// cleanup still ran. The stop is bounded by shutdownTimeout. Returns an error
// if startup fails.
func RunApp(ctx context.Context, app *fx.App) error {
// Set up signal handling for graceful shutdown
sigChan := make(chan os.Signal, 1)
signal.Notify(sigChan, os.Interrupt, syscall.SIGTERM)
// Create a context that will be cancelled on signal
ctx, cancel := context.WithCancel(ctx)
defer cancel()
// Start the app
err := app.Start(ctx)
if err != nil {
return cleanStartupError(err)
}
// Handle shutdown
shutdownComplete := make(chan struct{})
// Block until an interrupt or the finished operation's
// Shutdowner.Shutdown() arrives, then stop the app in this goroutine so we
// return only after its OnStop hooks — including the operation's cleanup
// wait — have run. Detach the stop from ctx's cancellation but keep its
// values, and bound it by shutdownTimeout.
<-app.Wait()
go func() {
defer close(shutdownComplete)
<-sigChan
log.Notice("Received interrupt signal, shutting down gracefully...")
// Create a timeout context for shutdown. The parent ctx is being
// cancelled, so detach from its cancellation but keep its values.
shutdownCtx, shutdownCancel := context.WithTimeout(
shutdownCtx, cancel := context.WithTimeout(
context.WithoutCancel(ctx), shutdownTimeout)
defer shutdownCancel()
defer cancel()
err := app.Stop(shutdownCtx)
err = app.Stop(shutdownCtx)
if err != nil {
log.Error("Error during shutdown", "error", err)
}
}()
// Wait for the signal handler to complete shutdown or the app to
// request shutdown.
select {
case <-shutdownComplete:
// Shutdown completed via signal
return nil
case <-ctx.Done():
// Context cancelled (shouldn't happen in normal operation)
err := app.Stop(context.WithoutCancel(ctx))
if err != nil {
log.Error("Error stopping app", "error", err)
}
return ctx.Err()
case <-app.Done():
// App finished running (e.g., backup completed)
return nil
}
}
// errReported marks a failure the operation has already shown the user
@@ -214,7 +216,10 @@ var errReported = errors.New("operation failed")
//
// op runs in a goroutine so OnStart returns promptly and an interrupt
// can still cancel through OnStop; when it finishes, success or failure,
// it triggers shutdown, which is what lets RunWithApp return. report is
// it triggers shutdown, which is what lets RunWithApp return. On an
// interrupt OnStop cancels op and waits for the goroutine to return, so
// op's cleanup (removing decrypted scratch files) runs before the
// process exits; the wait is bounded by shutdownTimeout. report is
// called with a non-canceled failure so the caller can log it (and
// suppress it under --json) before it becomes errReported. A context
// cancellation is the interrupt path, not a failure: it is neither
@@ -230,9 +235,11 @@ func RunOperation(
opts.Invokes = append(opts.Invokes,
fx.Invoke(func(v *vaultik.Vaultik, lc fx.Lifecycle) {
var stop func(context.Context) bool
lc.Append(fx.Hook{
OnStart: func(_ context.Context) error {
go func() {
stop = v.StartOperation(func() {
err := op(v)
if err != nil && !errors.Is(err, context.Canceled) {
report(err)
@@ -246,12 +253,20 @@ func RunOperation(
if stopErr != nil {
log.Error("Failed to shutdown", "error", stopErr)
}
}()
})
return nil
},
OnStop: func(_ context.Context) error {
v.Cancel()
// On an interrupt, cancel the operation and wait for it to
// unwind so its cleanup defers (which remove decrypted
// scratch files from the temp directory) run before the
// process exits. The wait is bounded by ctx, the existing
// shutdownTimeout.
OnStop: func(ctx context.Context) error {
if !stop(ctx) {
log.Warn("Shutdown timed out before the operation " +
"finished; decrypted temporary files may remain")
}
return nil
},
@@ -276,13 +291,15 @@ func RunOperation(
}
// runVaultikApp runs the standard single-operation command lifecycle
// shared by the list/purge/verify/remove/remote-info subcommands:
// shared by the snapshot list/purge/remove and remote nuke subcommands:
// resolve the config, then run op against the Vaultik instance through
// RunOperation, reporting a failure prefixed with failMsg (suppressed
// while suppressErrors is true, e.g. under --json). extraQuiet is OR-ed
// into LogOptions.Quiet (e.g. --json output modes).
// while suppressErrors is true, e.g. under --json). mode says whether the
// command takes the PID lock. jsonOutput marks a command whose stdout is a
// JSON document: it quiets the UI but, unlike Quiet, leaves the stderr log
// level alone.
func runVaultikApp(
cmd *cobra.Command, extraQuiet, suppressErrors bool,
cmd *cobra.Command, mode lockMode, jsonOutput, suppressErrors bool,
failMsg string, op func(v *vaultik.Vaultik) error,
) error {
configPath, err := ResolveConfigPath()
@@ -297,8 +314,10 @@ func runVaultikApp(
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet || extraQuiet,
Quiet: rootFlags.Quiet,
JSON: jsonOutput,
},
Mode: mode,
}, op, func(err error) {
if suppressErrors {
return
@@ -312,28 +331,46 @@ func runVaultikApp(
// RunWithApp is a helper that creates and runs an fx app with the given options.
// It combines NewApp and RunApp into a single convenient function. This is the
// preferred way to run CLI commands that need the full application context.
// It acquires a PID lock before starting to prevent concurrent instances.
// A mutating command takes the process-wide PID lock before starting so that
// only one runs at a time; a read-only command runs without it and is not
// blocked while a mutator holds the lock (opts.Mode).
func RunWithApp(ctx context.Context, opts AppOptions) error {
// Acquire PID lock to prevent concurrent instances
lockDir := filepath.Join(xdg.DataHome, "vaultik")
lock, err := pidlock.Acquire(lockDir)
release, err := acquireLockIfMutating(opts.Mode,
filepath.Join(xdg.DataHome, "vaultik"))
if err != nil {
if errors.Is(err, pidlock.ErrAlreadyRunning) {
return fmt.Errorf("cannot start: %w", err)
return err
}
return fmt.Errorf("failed to acquire lock: %w", err)
}
defer func() {
err := lock.Release()
if err != nil {
log.Warn("Failed to release PID lock", "error", err)
}
}()
defer release()
app := NewApp(opts)
return RunApp(ctx, app)
}
// acquireLockIfMutating takes the process-wide PID lock in lockDir for a
// mutating command and returns a function that releases it. A read-only
// command takes no lock, so it returns a no-op release and is never blocked
// while a mutator holds the lock. ErrAlreadyRunning (another mutator holds
// the lock) is surfaced as a "cannot start" error.
func acquireLockIfMutating(mode lockMode, lockDir string) (func(), error) {
if mode != mutating {
return func() {}, nil
}
lock, err := pidlock.Acquire(lockDir)
if err != nil {
if errors.Is(err, pidlock.ErrAlreadyRunning) {
return nil, fmt.Errorf("cannot start: %w", err)
}
return nil, fmt.Errorf("failed to acquire lock: %w", err)
}
return func() {
err := lock.Release()
if err != nil {
log.Warn("Failed to release PID lock", "error", err)
}
}, nil
}
internal/cli/app_test.go
+42
View File
@@ -2,7 +2,10 @@ package cli //nolint:testpackage // needs access to unexported cleanStartupError
import (
"errors"
"path/filepath"
"testing"
"sneak.berlin/go/vaultik/internal/pidlock"
)
func TestCleanStartupError(t *testing.T) {
@@ -53,3 +56,42 @@ func TestCleanStartupError(t *testing.T) {
})
}
}
// TestLockScopedToMutatingCommands proves the partition the PID lock now
// enforces: a read-only command runs while a mutator holds the lock, and
// two mutating commands still mutually exclude.
func TestLockScopedToMutatingCommands(t *testing.T) {
t.Parallel()
lockDir := filepath.Join(t.TempDir(), "vaultik")
// A mutating command takes the process-wide lock.
releaseMutator, err := acquireLockIfMutating(mutating, lockDir)
if err != nil {
t.Fatalf("mutating command could not acquire lock: %v", err)
}
// A read-only command runs to completion even while the lock is held.
releaseReader, err := acquireLockIfMutating(readOnly, lockDir)
if err != nil {
t.Fatalf("read-only command was blocked by held lock: %v", err)
}
releaseReader()
// A second mutating command is refused while the first holds the lock.
_, err = acquireLockIfMutating(mutating, lockDir)
if !errors.Is(err, pidlock.ErrAlreadyRunning) {
t.Fatalf("second mutating command was not excluded, got: %v", err)
}
// Once the first mutator releases, another mutating command may run.
releaseMutator()
release, err := acquireLockIfMutating(mutating, lockDir)
if err != nil {
t.Fatalf("mutating command could not acquire released lock: %v", err)
}
release()
}
internal/cli/config.go
+34 -15
View File
@@ -4,6 +4,7 @@ import (
"bytes"
"errors"
"fmt"
"io"
"os"
"os/exec"
"path/filepath"
@@ -45,8 +46,11 @@ const defaultConfigTemplate = `# vaultik configuration
# ─── REQUIRED ────────────────────────────────────────────────────────────────
# Age recipient public keys for encryption.
# Backups are encrypted to ALL listed recipients. Any one of the corresponding
# private keys can decrypt. Generate a keypair with:
# Backups are encrypted to ALL listed recipients; any one of the corresponding
# private keys can decrypt. Adding a recipient later does not re-encrypt data
# already stored: deduplicated chunks and existing blobs stay encrypted to the
# earlier recipients, so a newly added key cannot restore them on its own (see
# docs/REPOSTRUCTURE.md, Accepted Risks). Generate a keypair with:
# age-keygen -o vaultik_backup_private_key.txt
# grep 'public key' vaultik_backup_private_key.txt
age_recipients:
@@ -192,8 +196,8 @@ storage_url: ""
# access_key_id: YOUR_ACCESS_KEY
# secret_access_key: YOUR_SECRET_KEY
# # region: us-east-1 # Default: us-east-1
# # use_ssl: true # Default: true
# # part_size: 5MB # Multipart upload part size. Default: 5MB
# # For the s3:// form, disable TLS with ?ssl=false in the URL, not use_ssl.
# ─── OPTIONAL ────────────────────────────────────────────────────────────────
@@ -212,6 +216,8 @@ storage_url: ""
# chunk_size: 10MB
# Maximum blob size before splitting into a new blob.
# Must be at least four times chunk_size (the largest chunk the chunker can
# emit); a smaller limit would let a single-chunk blob exceed it.
# Accepts: 1GB, 10G, 500MB, etc.
# Default: 10GB
# blob_size_limit: 10GB
@@ -377,12 +383,23 @@ Examples:
return err
}
return writeConfigSet(os.Stdout, path, args[0], args[1])
},
}
}
// writeConfigSet applies key=value to the config at path, writes it back
// owner-only, and confirms the write by printing just the key name to w.
// The value is never echoed: it may be a secret such as
// s3.secret_access_key, and captured stdout or a pasted terminal would
// then leak it.
func writeConfigSet(w io.Writer, path, key, value string) error {
root, err := loadYAMLFile(path)
if err != nil {
return err
}
err = yamlPathSet(root, strings.Split(args[0], "."), args[1])
err = yamlPathSet(root, strings.Split(key, "."), value)
if err != nil {
return err
}
@@ -392,23 +409,25 @@ Examples:
return fmt.Errorf("marshaling config: %w", err)
}
mode := os.FileMode(configFileMode)
info, statErr := os.Stat(path)
if statErr == nil {
mode = info.Mode().Perm()
}
err = os.WriteFile(path, out, mode)
err = os.WriteFile(path, out, configFileMode)
if err != nil {
return fmt.Errorf("writing config file: %w", err)
}
_, _ = fmt.Fprintf(os.Stdout, "%s = %s\n", args[0], args[1])
// os.WriteFile does not change the mode of a file that already exists,
// so a config that was group- or world-readable stays that way. As it
// may hold S3 credentials, tighten it to owner-only after writing.
info, statErr := os.Stat(path)
if statErr == nil && info.Mode().Perm()&0o044 != 0 {
err = os.Chmod(path, configFileMode)
if err != nil {
return fmt.Errorf("tightening config file permissions: %w", err)
}
}
_, _ = fmt.Fprintln(w, key)
return nil
},
}
}
// marshalConfigYAML renders a config document tree with 2-space indentation,
internal/cli/config_test.go
+65
View File
@@ -1,6 +1,9 @@
package cli //nolint:testpackage // exercises unexported yamlPathGet/yamlPathSet
import (
"bytes"
"os"
"path/filepath"
"strings"
"testing"
@@ -229,6 +232,68 @@ func TestConfigSetPreservesFormatting(t *testing.T) {
}
}
// TestWriteConfigSetHidesSecret checks that setting a secret key prints
// only the key name, never the value, to the confirmation output.
func TestWriteConfigSetHidesSecret(t *testing.T) {
t.Parallel()
const secret = "SUPERSECRETVALUE"
path := filepath.Join(t.TempDir(), "config.yaml")
err := os.WriteFile(path, []byte("version: 1\n"), 0o600)
if err != nil {
t.Fatalf("seed config: %v", err)
}
var out bytes.Buffer
err = writeConfigSet(&out, path, "s3.secret_access_key", secret)
if err != nil {
t.Fatalf("writeConfigSet: %v", err)
}
if strings.Contains(out.String(), secret) {
t.Errorf("output echoed the secret value: %q", out.String())
}
if !strings.Contains(out.String(), "s3.secret_access_key") {
t.Errorf("output did not confirm the key name: %q", out.String())
}
}
// TestWriteConfigSetTightensMode checks that a pre-existing group- or
// world-readable config is tightened to owner-only after a set, since
// os.WriteFile leaves an existing file's mode untouched.
func TestWriteConfigSetTightensMode(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yaml")
// Seed a world-readable config; the loose mode is the condition under
// test, so gosec's G306 is expected here.
err := os.WriteFile(path, []byte("version: 1\n"), 0o644) //nolint:gosec // G306
if err != nil {
t.Fatalf("seed config: %v", err)
}
var out bytes.Buffer
err = writeConfigSet(&out, path, "compression_level", "9")
if err != nil {
t.Fatalf("writeConfigSet: %v", err)
}
info, err := os.Stat(path)
if err != nil {
t.Fatalf("stat config: %v", err)
}
if info.Mode().Perm() != 0o600 {
t.Errorf("config mode = %04o, want 0600", info.Mode().Perm())
}
}
func splitPath(s string) []string {
return strings.Split(s, ".")
}
internal/cli/entry_prune_json_stderr_test.go
+140
View File
@@ -0,0 +1,140 @@
package cli //nolint:testpackage // shares the prune fixtures and capture helpers
import (
"bytes"
"io"
"os"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// staleRecordLogMessage is the local-cleanup audit line CleanupLocalSnapshots
// logs for each stale record. It is exactly the signal issue #112 says a
// machine consumer lost under --json: gated off stdout, and pinned below
// the log level on stderr because --json used to force Quiet.
const staleRecordLogMessage = "Removing stale local snapshot record"
// TestEntryPruneJSONStderrHonoursVerbosity is the end-to-end regression
// guard for issue #112. Under --json the log level must still follow
// --verbose/--debug rather than being pinned to WARN, so the
// local-cleanup records reach stderr under --verbose while stdout stays
// exactly one JSON document; without --verbose they stay below the
// level, as they do without --json.
//
// Both halves are asserted together on the same run, because the fix has
// to keep the document clean (issue #108) while freeing stderr.
//
// Not parallel: it replaces os.Args, os.Stdout, os.Stderr and the xdg
// globals.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntryPruneJSONStderrHonoursVerbosity(t *testing.T) {
for _, testCase := range []struct {
name string
verbose bool
wantOnStderr bool
}{
{
name: "verbose json surfaces the cleanup record on stderr",
verbose: true,
wantOnStderr: true,
},
{
name: "json alone keeps the cleanup record below the level",
verbose: false,
wantOnStderr: false,
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath := writeHermeticPruneConfig(t, true)
previousArgs := os.Args
t.Cleanup(func() {
os.Args = previousArgs
rootFlags = RootFlags{}
})
args := []string{
programName, flagConfig, configPath, cmdPrune, flagJSON,
}
if testCase.verbose {
args = append(args, "--verbose")
}
os.Args = args
stdout, stderr := captureProcessStdoutAndStderr(t,
func() { _ = Entry() })
// The document stays clean in both cases: freeing stderr must
// not regress issue #108.
requireExactlyOneJSONDocument(t, stdout)
if testCase.wantOnStderr {
assert.Contains(t, stderr, staleRecordLogMessage,
"--verbose --json must emit the cleanup record on stderr")
assert.Contains(t, stderr, stalePruneSnapshotID,
"the record must name the snapshot it removed")
} else {
assert.NotContains(t, stderr, staleRecordLogMessage,
"without --verbose the record stays below the log level")
}
})
}
}
// captureProcessStdoutAndStderr redirects both of the process's own
// standard streams to pipes for the duration of fn and returns what was
// written to each. The redirection is at the file-descriptor level
// because the logger binds os.Stderr when it initializes inside fn, and
// the JSON document reaches os.Stdout independently; the point is to see
// where each actually lands.
//
// Not parallel-safe: os.Stdout and os.Stderr are process-global.
func captureProcessStdoutAndStderr(t *testing.T, fn func()) (string, string) {
t.Helper()
outReader, outWriter, err := os.Pipe()
require.NoError(t, err)
errReader, errWriter, err := os.Pipe()
require.NoError(t, err)
previousOut, previousErr := os.Stdout, os.Stderr
os.Stdout, os.Stderr = outWriter, errWriter
capturedOut := drain(outReader)
capturedErr := drain(errReader)
fn()
os.Stdout, os.Stderr = previousOut, previousErr
require.NoError(t, outWriter.Close())
require.NoError(t, errWriter.Close())
out, errOut := <-capturedOut, <-capturedErr
require.NoError(t, outReader.Close())
require.NoError(t, errReader.Close())
return out, errOut
}
// drain copies a reader to a string on a goroutine and delivers the
// result once the writer end is closed.
func drain(reader io.Reader) <-chan string {
captured := make(chan string, 1)
go func() {
var buf bytes.Buffer
_, _ = io.Copy(&buf, reader)
captured <- buf.String()
}()
return captured
}
internal/cli/info.go
+1
View File
@@ -35,6 +35,7 @@ func NewInfoCommand() *cobra.Command {
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
},
Mode: readOnly,
}, func(v *vaultik.Vaultik) error {
return v.ShowInfo()
}, func(err error) {
internal/cli/prune.go
+3 -1
View File
@@ -41,8 +41,10 @@ work (e.g. after a crashed backup or to reclaim storage).`,
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet || opts.JSON,
Quiet: rootFlags.Quiet,
JSON: opts.JSON,
},
Mode: mutating,
}, func(v *vaultik.Vaultik) error {
return v.Prune(opts)
}, func(err error) {
internal/cli/remote.go
+4 -2
View File
@@ -45,7 +45,7 @@ This is destructive and irreversible. Requires --force.`,
return errNukeNeedsForce
}
return runVaultikApp(cmd, false, false, "Remote nuke failed",
return runVaultikApp(cmd, mutating, false, false, "Remote nuke failed",
func(v *vaultik.Vaultik) error {
return v.NukeRemote(true)
})
@@ -85,8 +85,10 @@ func newRemoteInfoCommand() *cobra.Command {
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet || jsonOutput,
Quiet: rootFlags.Quiet,
JSON: jsonOutput,
},
Mode: readOnly,
}, func(v *vaultik.Vaultik) error {
return v.RemoteInfo(jsonOutput)
}, func(err error) {
internal/cli/root.go
+3 -2
View File
@@ -57,8 +57,9 @@ on the source system.`,
cmd.PersistentFlags().BoolVarP(&rootFlags.Quiet, "quiet", "q", false,
"Suppress non-error output")
cmd.PersistentFlags().BoolVar(&rootFlags.SkipErrors, "skip-errors", false,
"Continue past per-file errors instead of aborting "+
"(applies to snapshot create and restore)")
"Skip files that cannot be read when creating a snapshot, or "+
"that cannot be restored when restoring, instead of aborting "+
"(packing and storage errors still abort)")
// Add subcommands
cmd.AddCommand(
internal/cli/runapp_interrupt_test.go
+97
View File
@@ -0,0 +1,97 @@
package cli_test
import (
"context"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/require"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/cli"
)
// TestRunAppWaitsForOperationCleanupOnShutdown drives RunApp with an fx app
// wired the way RunOperation wires a command: a single lifecycle hook whose
// OnStart launches the operation in its own goroutine and whose OnStop cancels
// it and blocks until that goroutine returns. The operation stands in for a
// restore blocked mid-download — it holds a decrypted "scratch" file and only
// removes it as it unwinds on cancellation.
//
// The app is asked to stop once the operation is running (standing in for an
// OS interrupt; fx delivers a real signal and Shutdowner.Shutdown() on the
// same app.Wait channel, so both drive the identical shutdown path). RunApp
// must not return until app.Stop has run the OnStop hook, so the scratch file
// must be gone by the time RunApp returns. Before the fix RunApp returned as
// soon as the app.Wait/Done channel fired, without running app.Stop, so the
// cleanup never ran and this file would still be on disk (issue #159).
func TestRunAppWaitsForOperationCleanupOnShutdown(t *testing.T) {
t.Parallel()
scratch := filepath.Join(t.TempDir(), "decrypted-scratch")
require.NoError(t, os.WriteFile(scratch, []byte("secret"), 0o600))
// Cancel and reap the operation even if RunApp returns without doing so
// (the buggy path), so the goroutine cannot leak past the test.
opCtx, opCancel := context.WithCancel(context.Background())
t.Cleanup(opCancel)
var stop func(context.Context) bool
app := fx.New(
fx.NopLogger,
fx.Invoke(func(lc fx.Lifecycle, sh fx.Shutdowner) {
lc.Append(fx.Hook{
OnStart: func(_ context.Context) error {
done := make(chan struct{})
go func() {
defer close(done)
// Blocked mid-operation until cancelled, then run the
// cleanup an interrupted restore would run.
<-opCtx.Done()
_ = os.Remove(scratch)
}()
stop = func(ctx context.Context) bool {
opCancel()
select {
case <-done:
return true
case <-ctx.Done():
return false
}
}
// Ask the app to stop now that the operation is running.
go func() { _ = sh.Shutdown() }()
return nil
},
OnStop: func(ctx context.Context) error {
stop(ctx)
return nil
},
})
}),
)
done := make(chan error, 1)
go func() { done <- cli.RunApp(context.Background(), app) }()
select {
case err := <-done:
require.NoError(t, err)
case <-time.After(30 * time.Second):
t.Fatal("RunApp did not return after shutdown was requested")
}
_, err := os.Stat(scratch)
require.True(t, os.IsNotExist(err),
"RunApp returned before the operation removed its decrypted scratch file")
}
internal/cli/snapshot.go
+16 -6
View File
@@ -92,6 +92,7 @@ specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
Cron: opts.Cron,
Quiet: rootFlags.Quiet,
},
Mode: mutating,
}, func(v *vaultik.Vaultik) error {
return v.CreateSnapshot(opts)
}, func(err error) {
@@ -125,7 +126,7 @@ func newSnapshotListCommand() *cobra.Command {
Long: "Lists all snapshots with their ID, timestamp, and compressed size",
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error {
return runVaultikApp(cmd, false, false,
return runVaultikApp(cmd, readOnly, false, false,
"Failed to list snapshots",
func(v *vaultik.Vaultik) error {
return v.ListSnapshots(jsonOutput)
@@ -161,7 +162,7 @@ restrict the operation to specific snapshot names.`,
return errPurgeCriteriaBoth
}
return runVaultikApp(cmd, false, false,
return runVaultikApp(cmd, mutating, false, false,
"Failed to purge snapshots",
func(v *vaultik.Vaultik) error {
return v.PurgeSnapshotsWithOptions(opts)
@@ -187,8 +188,15 @@ func newSnapshotVerifyCommand() *cobra.Command {
cmd := &cobra.Command{
Use: "verify <snapshot-id>",
Short: "Verify snapshot integrity",
Long: "Verifies that all blobs referenced in a snapshot exist",
Short: "Check a snapshot's blobs are present with the listed size",
Long: "Checks that every blob the snapshot's manifest lists is present\n" +
"in storage with the size the manifest records, and that the\n" +
"snapshot's encrypted database is present. It does not read blob\n" +
"contents; use --deep to download, decrypt, and re-hash every blob\n" +
"to detect corruption -- integrity, not who wrote it.\n\n" +
"The snapshot may be named by its ID or, on a host with no local\n" +
"index, by the remote key that 'snapshot list' prints for a\n" +
"remote-only snapshot (an unambiguous leading part is enough).",
Args: requireSnapshotIDArg,
RunE: func(cmd *cobra.Command, args []string) error {
snapshotID := args[0]
@@ -206,8 +214,10 @@ func newSnapshotVerifyCommand() *cobra.Command {
LogOptions: log.Options{
Verbose: rootFlags.Verbose,
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet || opts.JSON,
Quiet: rootFlags.Quiet,
JSON: opts.JSON,
},
Mode: readOnly,
}, func(v *vaultik.Vaultik) error {
return v.VerifySnapshotWithOptions(snapshotID, opts)
}, func(err error) {
@@ -255,7 +265,7 @@ To wipe the entire destination store and start over, use 'vaultik remote
nuke --force' — it is the single supported entry point for that.`,
Args: requireSnapshotIDArg,
RunE: func(cmd *cobra.Command, args []string) error {
return runVaultikApp(cmd, opts.JSON, opts.JSON,
return runVaultikApp(cmd, mutating, opts.JSON, opts.JSON,
"Failed to remove snapshot",
func(v *vaultik.Vaultik) error {
_, err := v.RemoveSnapshot(args[0], opts)
internal/cli/snapshot_restore.go
+11 -2
View File
@@ -31,8 +31,16 @@ target directory.
If no paths are specified, all files are restored.
If paths are specified, only matching files/directories are restored.
Requires the VAULTIK_AGE_SECRET_KEY environment variable to be set with
the age private key.
The snapshot may be named by its ID or, when restoring on a host with no
local index, by the remote key that 'snapshot list' prints for a
remote-only snapshot (an unambiguous leading part is enough).
Requires the age private key in the VAULTIK_AGE_SECRET_KEY environment
variable. The variable may hold the whole age-keygen file (comments and
all of its identities are accepted); read it from the file rather than
typing the key, so it does not land in your shell history:
export VAULTIK_AGE_SECRET_KEY="$(cat vaultik_backup_private_key.txt)"
Examples:
# Restore entire snapshot
@@ -84,6 +92,7 @@ func runRestore(cmd *cobra.Command, args []string, opts *RestoreOptions) error {
Debug: rootFlags.Debug,
Quiet: rootFlags.Quiet,
},
Mode: readOnly,
}, func(v *vaultik.Vaultik) error {
return v.Restore(&vaultik.RestoreOptions{
SnapshotID: snapshotID,
internal/cli/snapshot_restore_test.go
+37
View File
@@ -0,0 +1,37 @@
package cli //nolint:testpackage // exercises the unexported command constructor
import (
"strings"
"testing"
"github.com/spf13/pflag"
)
// TestRestoreCommandDoesNotTakeKeyAsArgument guards the fix for the age
// key being echoed on the command line: restore must take the key only
// from the environment, never as a flag value, and its help must show the
// file-based form rather than a literal key that would land in shell
// history.
func TestRestoreCommandDoesNotTakeKeyAsArgument(t *testing.T) {
t.Parallel()
cmd := newSnapshotRestoreCommand()
cmd.Flags().VisitAll(func(f *pflag.Flag) {
lower := strings.ToLower(f.Name)
for _, banned := range []string{"key", "secret", "age", "identity"} {
if strings.Contains(lower, banned) {
t.Errorf("restore must not accept the key as a flag; found --%s", f.Name)
}
}
})
help := cmd.Long
if strings.Contains(help, "AGE-SECRET-KEY-") {
t.Error("restore help must not show a literal age private key to type")
}
if !strings.Contains(help, "$(cat ") {
t.Error("restore help should read the key from a file, e.g. $(cat ...)")
}
}
internal/config/config.go
+97 -26
View File
@@ -16,11 +16,19 @@ import (
"github.com/adrg/xdg"
"go.uber.org/fx"
"gopkg.in/yaml.v3"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
)
const appName = "vaultik"
// secretKeyPrefix marks an age secret (private) key. It is compared
// case-insensitively so a recipient entry that is actually a private key is
// caught and never passed to age or echoed back.
//
//nolint:gosec // G101: marker for detecting a pasted secret key, not a credential
const secretKeyPrefix = "AGE-SECRET-KEY-"
// Defaults and validation bounds for tunable settings.
const (
defaultBlobSizeLimit = Size(10 * 1024 * 1024 * 1024) // 10GB
@@ -37,11 +45,17 @@ var (
errNoConfigPath = errors.New("config path not provided")
errNoAgeRecipients = errors.New(
"at least one age_recipient is required (generate with: age-keygen)")
errRecipientIsSecretKey = errors.New(
"an age secret key was given where a public key (age1...) belongs")
errRecipientNotX25519 = errors.New(
"not a valid recipient; only X25519 age1... public keys are supported")
errNoSnapshots = errors.New(
"at least one snapshot must be configured (see config.example.yml)")
errSnapshotNoPaths = errors.New("snapshot must have at least one path")
errChunkSizeTooSmall = errors.New("chunk_size must be at least 1MB")
errBlobSizeTooSmall = errors.New("blob_size_limit must be at least chunk_size")
errBlobSizeTooSmall = errors.New(
"blob_size_limit must be at least the largest chunk the chunker can " +
"emit (chunk_size times the FastCDC size spread)")
errBadCompression = errors.New("compression_level must be between 1 and 19")
errBadStorageScheme = errors.New(
"storage_url must start with s3://, file://, or rclone://")
@@ -121,6 +135,26 @@ func (c *Config) SnapshotNames() []string {
return names
}
// Names of the two places the age secret key can be configured, used by
// AgeSecretKeySourceName for error messages that must not echo the value.
//
//nolint:gosec // G101: these are the names of the config sources, not a key
const (
ageSecretKeySourceEnv = "VAULTIK_AGE_SECRET_KEY"
ageSecretKeySourceConfig = "age_secret_key"
)
// AgeSecretKeySourceName returns the human name of where AgeSecretKey was
// configured. A Config built directly (as in tests) has no recorded
// source, so it reports the config-file field name.
func (c *Config) AgeSecretKeySourceName() string {
if c.AgeSecretKeySource != "" {
return c.AgeSecretKeySource
}
return ageSecretKeySourceConfig
}
// Config represents the application configuration for Vaultik.
// It defines all settings for backup operations, including source directories,
// encryption recipients, storage configuration, and performance tuning parameters.
@@ -130,6 +164,11 @@ func (c *Config) SnapshotNames() []string {
type Config struct {
AgeRecipients []string `yaml:"age_recipients"`
AgeSecretKey string `yaml:"age_secret_key"`
// AgeSecretKeySource names where AgeSecretKey was configured
// ("VAULTIK_AGE_SECRET_KEY" or "age_secret_key") so a later parse
// failure can name the source without echoing the secret value. It is
// set by Load and never read from or written to the config file.
AgeSecretKeySource string `yaml:"-"`
BlobSizeLimit Size `yaml:"blob_size_limit"`
ChunkSize Size `yaml:"chunk_size"`
// Exclude holds global excludes applied to all snapshots.
@@ -162,7 +201,9 @@ type S3Config struct {
AccessKeyID string `yaml:"access_key_id"`
SecretAccessKey string `yaml:"secret_access_key"`
Region string `yaml:"region"`
UseSSL bool `yaml:"use_ssl"`
// UseSSL selects HTTPS for a scheme-less endpoint. Omitted (nil) means
// the default, TLS; set it to false only to force plain HTTP.
UseSSL *bool `yaml:"use_ssl"`
PartSize Size `yaml:"part_size"`
}
@@ -238,10 +279,7 @@ func Load(path string) (*Config, error) {
cfg.IndexPath = expandTilde(envIndexPath)
}
// Check for environment variable override for AgeSecretKey
if envAgeSecretKey := os.Getenv("VAULTIK_AGE_SECRET_KEY"); envAgeSecretKey != "" {
cfg.AgeSecretKey = extractAgeSecretKey(envAgeSecretKey)
}
cfg.setAgeSecretKey()
// Get hostname if not set
if cfg.Hostname == "" {
@@ -285,18 +323,30 @@ func Load(path string) (*Config, error) {
// Validate checks if the configuration is valid and complete.
// It ensures all required fields are present and have valid values:
// - At least one age recipient must be specified
// - At least one age recipient must be specified, and every recipient must
// parse as an X25519 age1... public key (so a bad entry fails at load, not
// mid-backup); errors name the position, never the value
// - At least one snapshot must be configured with at least one path
// - Storage must be configured (either storage_url or s3.* fields)
// - Chunk size must be at least 1MB
// - Blob size limit must be at least the chunk size
// - Blob size limit must be at least the largest chunk the chunker can emit
// (chunk_size times chunker.ChunkSizeSpread), so a single-chunk blob never
// exceeds the configured limit
// - Compression level must be between 1 and 19
//
// Returns an error describing the first validation failure encountered.
func (c *Config) Validate() error {
if len(c.AgeRecipients) == 0 {
return errNoAgeRecipients
}
for i, recipient := range c.AgeRecipients {
err := validateAgeRecipient(recipient)
if err != nil {
return fmt.Errorf("age_recipients[%d]: %w", i, err)
}
}
if len(c.Snapshots) == 0 {
return errNoSnapshots
}
@@ -317,8 +367,13 @@ func (c *Config) Validate() error {
return errChunkSizeTooSmall
}
if c.BlobSizeLimit.Int64() < c.ChunkSize.Int64() {
return errBlobSizeTooSmall
// The chunker can emit chunks up to chunk_size * ChunkSizeSpread, and the
// packer places a single such chunk into an otherwise empty blob. A limit
// below that bound would let a blob exceed it, so reject it.
largestChunk := c.ChunkSize.Int64() * chunker.ChunkSizeSpread
if c.BlobSizeLimit.Int64() < largestChunk {
return fmt.Errorf("%w: need at least %d bytes",
errBlobSizeTooSmall, largestChunk)
}
if c.CompressionLevel < minCompressionLevel ||
@@ -329,6 +384,38 @@ func (c *Config) Validate() error {
return nil
}
// validateAgeRecipient parses one age_recipients entry with the age library
// and returns a value-free error on failure. A recipient string can be
// sensitive (an operator may paste a secret key by mistake), so neither the
// entry nor age's own error (which quotes its input) is ever included.
func validateAgeRecipient(recipient string) error {
if strings.HasPrefix(strings.ToUpper(recipient), secretKeyPrefix) {
return errRecipientIsSecretKey
}
_, err := age.ParseX25519Recipient(recipient)
if err != nil {
return errRecipientNotX25519
}
return nil
}
// setAgeSecretKey records the age secret key and where it came from. The
// value is stored raw and parsed only where decryption happens
// (internal/vaultik), so backup, list and prune keep working whatever the
// field holds. The environment variable overrides the config-file field.
func (c *Config) setAgeSecretKey() {
if c.AgeSecretKey != "" {
c.AgeSecretKeySource = ageSecretKeySourceConfig
}
if env := os.Getenv("VAULTIK_AGE_SECRET_KEY"); env != "" {
c.AgeSecretKey = env
c.AgeSecretKeySource = ageSecretKeySourceEnv
}
}
// validateStorage validates storage configuration.
// If StorageURL is set, it takes precedence. S3 URLs require credentials.
// File URLs don't require any S3 configuration.
@@ -385,22 +472,6 @@ func (c *Config) validateStorageURL() error {
}
}
// extractAgeSecretKey extracts the AGE-SECRET-KEY from the input using
// the age library's parser, which handles comments and whitespace.
func extractAgeSecretKey(input string) string {
identities, err := age.ParseIdentities(strings.NewReader(input))
if err != nil || len(identities) == 0 {
// Fall back to trimmed input if parsing fails
return strings.TrimSpace(input)
}
// Return the string representation of the first identity
if id, ok := identities[0].(*age.X25519Identity); ok {
return id.String()
}
return strings.TrimSpace(input)
}
// Module exports the config module for fx dependency injection.
// It provides the Config type to other modules in the application.
//
internal/config/config_test.go
+212 -38
View File
@@ -1,9 +1,13 @@
package config //nolint:testpackage // exercises unexported extractAgeSecretKey
package config //nolint:testpackage // exercises unexported source constants
import (
"errors"
"os"
"path/filepath"
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/chunker"
)
const (
@@ -83,6 +87,48 @@ func TestConfigLoad(t *testing.T) {
}
}
// TestExampleConfigIsScrubbedAndLoads checks that the shipped
// config.example.yml carries only neutral placeholders (no real credentials,
// private addresses, or internal host names) and still parses.
func TestExampleConfigIsScrubbedAndLoads(t *testing.T) {
t.Parallel()
examplePath := filepath.Join("..", "..", "config.example.yml")
cfg, err := Load(examplePath)
if err != nil {
t.Fatalf("Failed to load config.example.yml: %v", err)
}
if cfg.StorageURL != "rclone://myremote/path/to/backups" {
t.Errorf("Expected neutral storage_url, got '%s'", cfg.StorageURL)
}
//nolint:gosec // G304: examplePath is a fixed in-repo path, not user input
raw, err := os.ReadFile(examplePath)
if err != nil {
t.Fatalf("Failed to read config.example.yml: %v", err)
}
text := string(raw)
wantSubstrings := []string{
"YOUR_ACCESS_KEY",
"YOUR_SECRET_KEY",
"endpoint: https://",
}
for _, want := range wantSubstrings {
if !strings.Contains(text, want) {
t.Errorf("Expected config.example.yml to contain %q", want)
}
}
// A raw "http://" scheme would mean a plaintext, likely private endpoint.
if strings.Contains(text, "http://") {
t.Error("config.example.yml should not contain an http:// endpoint")
}
}
// TestConfigFromEnv tests loading config path from environment variable
func TestConfigFromEnv(t *testing.T) {
t.Parallel()
@@ -101,53 +147,57 @@ func TestConfigFromEnv(t *testing.T) {
}
}
// TestExtractAgeSecretKey tests extraction of AGE-SECRET-KEY from various inputs
func TestExtractAgeSecretKey(t *testing.T) {
// TestValidateBlobSizeLimit checks the blob_size_limit boundary: it must be at
// least the largest chunk the chunker can emit (chunk_size times
// chunker.ChunkSizeSpread), because the packer places a single such chunk into
// an otherwise empty blob. A limit between chunk_size and that bound is rejected.
func TestValidateBlobSizeLimit(t *testing.T) {
t.Parallel()
const chunkSize = Size(10 * 1024 * 1024) // 10MB
largestChunk := chunkSize.Int64() * chunker.ChunkSizeSpread
newConfig := func(blobLimit Size) *Config {
return &Config{
AgeRecipients: []string{testSneakAgePublicKey},
Snapshots: map[string]SnapshotConfig{"test": {Paths: []string{"/tmp/src"}}},
StorageURL: "file:///tmp/vaultik-test-store",
ChunkSize: chunkSize,
BlobSizeLimit: blobLimit,
CompressionLevel: 3,
}
}
tests := []struct {
name string
input string
expected string
blobLimit Size
wantErr bool
}{
{
name: "plain key",
input: testIntegrationAgePrivateKey,
expected: testIntegrationAgePrivateKey,
name: "at chunk_size but below largest chunk is rejected",
blobLimit: chunkSize,
wantErr: true,
},
{
name: "key with trailing newline",
input: testIntegrationAgePrivateKey + "\n",
expected: testIntegrationAgePrivateKey,
name: "between chunk_size and largest chunk is rejected",
blobLimit: Size(chunkSize.Int64() * 2),
wantErr: true,
},
{
name: "full age-keygen output",
input: "# created: 2025-01-14T12:00:00Z\n" +
"# public key: " + testIntegrationAgePublicKey + "\n" +
testIntegrationAgePrivateKey + "\n",
expected: testIntegrationAgePrivateKey,
name: "one byte below largest chunk is rejected",
blobLimit: Size(largestChunk - 1),
wantErr: true,
},
{
name: "age-keygen output with extra blank lines",
input: "# created: 2025-01-14T12:00:00Z\n" +
"# public key: " + testIntegrationAgePublicKey + "\n\n" +
testIntegrationAgePrivateKey + "\n\n",
expected: testIntegrationAgePrivateKey,
name: "exactly at largest chunk is accepted",
blobLimit: Size(largestChunk),
wantErr: false,
},
{
name: "key with leading whitespace",
input: " " + testIntegrationAgePrivateKey + " ",
expected: testIntegrationAgePrivateKey,
},
{
name: "empty input",
input: "",
expected: "",
},
{
name: "only comments",
input: "# this is a comment\n# another comment",
expected: "# this is a comment\n# another comment",
name: "above largest chunk is accepted",
blobLimit: Size(largestChunk * 100),
wantErr: false,
},
}
@@ -155,10 +205,134 @@ func TestExtractAgeSecretKey(t *testing.T) {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
result := extractAgeSecretKey(tt.input)
if result != tt.expected {
t.Errorf("extractAgeSecretKey(%q) = %q, want %q",
tt.input, result, tt.expected)
err := newConfig(tt.blobLimit).Validate()
if tt.wantErr {
if !errors.Is(err, errBlobSizeTooSmall) {
t.Fatalf("Validate() error = %v, want errBlobSizeTooSmall", err)
}
return
}
if err != nil {
t.Fatalf("Validate() unexpected error: %v", err)
}
})
}
}
// TestValidateAgeRecipients checks that recipients are parsed at config load
// (a bad entry fails immediately, not mid-backup) and that no invalid entry —
// least of all a pasted secret key — is echoed in the error.
func TestValidateAgeRecipients(t *testing.T) {
t.Parallel()
baseConfig := func(recipients []string) *Config {
return &Config{
AgeRecipients: recipients,
Snapshots: map[string]SnapshotConfig{"test": {Paths: []string{"/tmp/src"}}},
StorageURL: "file:///tmp/vaultik-test-store",
ChunkSize: Size(10 * 1024 * 1024),
BlobSizeLimit: Size(10 * 1024 * 1024 * 1024),
CompressionLevel: 3,
}
}
tests := []struct {
name string
recipients []string
wantErr bool
}{
{
name: "config init placeholder is rejected",
recipients: []string{"age1REPLACE_WITH_YOUR_PUBLIC_KEY"},
wantErr: true,
},
{
name: "ssh-ed25519 recipient is rejected",
recipients: []string{"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIexamplekeydata"},
wantErr: true,
},
{
name: "truncated age1 string is rejected",
recipients: []string{"age1short"},
wantErr: true,
},
{
name: "secret key passed as recipient is rejected",
recipients: []string{testIntegrationAgePrivateKey},
wantErr: true,
},
{
name: "two valid recipients are accepted",
recipients: []string{testSneakAgePublicKey, testIntegrationAgePublicKey},
wantErr: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
err := baseConfig(tt.recipients).Validate()
if !tt.wantErr {
if err != nil {
t.Fatalf("Validate() unexpected error: %v", err)
}
return
}
if err == nil {
t.Fatal("Validate() returned nil, want error")
}
// The entry itself must never appear in the error, since a
// recipient string can be a secret key.
for _, recipient := range tt.recipients {
if strings.Contains(err.Error(), recipient) {
t.Fatalf("Validate() error echoed the recipient value: %v", err)
}
}
})
}
}
// TestAgeSecretKeySourceName checks the name reported for the configured
// age secret key: the recorded source when Load set one, and the
// config-file field name for a Config built directly (as in tests).
func TestAgeSecretKeySourceName(t *testing.T) {
t.Parallel()
tests := []struct {
name string
source string
want string
}{
{
name: "unset defaults to config field",
source: "",
want: ageSecretKeySourceConfig,
},
{
name: "environment source",
source: ageSecretKeySourceEnv,
want: ageSecretKeySourceEnv,
},
{
name: "config-file source",
source: ageSecretKeySourceConfig,
want: ageSecretKeySourceConfig,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
cfg := &Config{AgeSecretKeySource: tt.source}
if got := cfg.AgeSecretKeySourceName(); got != tt.want {
t.Errorf("AgeSecretKeySourceName() = %q, want %q", got, tt.want)
}
})
}
internal/crypto/encryption.go
-224
View File
@@ -1,224 +0,0 @@
// Package crypto provides thread-safe age encryption and decryption
// helpers used to protect blob and metadata content.
package crypto //nolint:revive,nolintlint // stdlib crypto unused; see #76
import (
"bytes"
"errors"
"fmt"
"io"
"sync"
"filippo.io/age"
"go.uber.org/fx"
)
// ErrNoRecipients is returned when an encryptor is created or updated
// without any recipient public keys.
var ErrNoRecipients = errors.New("at least one recipient is required")
// Encryptor provides thread-safe encryption using the age encryption library.
// It supports encrypting data for multiple recipients simultaneously, allowing
// any of the corresponding private keys to decrypt the data. This is useful
// for backup scenarios where multiple parties should be able to decrypt the data.
type Encryptor struct {
recipients []age.Recipient
mu sync.RWMutex
}
// NewEncryptor creates a new encryptor with the given age public keys.
// Each public key should be a valid age X25519 recipient string (e.g., "age1...")
// At least one recipient must be provided. Returns an error if any of the
// public keys are invalid or if no recipients are specified.
func NewEncryptor(publicKeys []string) (*Encryptor, error) {
if len(publicKeys) == 0 {
return nil, ErrNoRecipients
}
recipients := make([]age.Recipient, 0, len(publicKeys))
for _, key := range publicKeys {
recipient, err := age.ParseX25519Recipient(key)
if err != nil {
return nil, fmt.Errorf("parsing age recipient %s: %w", key, err)
}
recipients = append(recipients, recipient)
}
return &Encryptor{
recipients: recipients,
}, nil
}
// Encrypt encrypts data using age encryption for all configured recipients.
// The encrypted data can be decrypted by any of the corresponding private keys.
// This method is suitable for small to medium amounts of data that fit in memory.
// For large data streams, use EncryptStream or EncryptWriter instead.
func (e *Encryptor) Encrypt(data []byte) ([]byte, error) {
e.mu.RLock()
recipients := e.recipients
e.mu.RUnlock()
var buf bytes.Buffer
// Create encrypted writer for all recipients
w, err := age.Encrypt(&buf, recipients...)
if err != nil {
return nil, fmt.Errorf("creating encrypted writer: %w", err)
}
// Write data
_, err = w.Write(data)
if err != nil {
return nil, fmt.Errorf("writing encrypted data: %w", err)
}
// Close to flush
err = w.Close()
if err != nil {
return nil, fmt.Errorf("closing encrypted writer: %w", err)
}
return buf.Bytes(), nil
}
// EncryptStream encrypts data from reader to writer using age encryption.
// This method is suitable for encrypting large files or streams as it processes
// data in a streaming fashion without loading everything into memory.
// The encrypted data is written directly to the destination writer.
func (e *Encryptor) EncryptStream(dst io.Writer, src io.Reader) error {
e.mu.RLock()
recipients := e.recipients
e.mu.RUnlock()
// Create encrypted writer for all recipients
w, err := age.Encrypt(dst, recipients...)
if err != nil {
return fmt.Errorf("creating encrypted writer: %w", err)
}
// Copy data
_, err = io.Copy(w, src)
if err != nil {
return fmt.Errorf("copying encrypted data: %w", err)
}
// Close to flush
err = w.Close()
if err != nil {
return fmt.Errorf("closing encrypted writer: %w", err)
}
return nil
}
// EncryptWriter creates a writer that encrypts data written to it.
// All data written to the returned WriteCloser will be encrypted and written
// to the destination writer. The caller must call Close() on the returned
// writer to ensure all encrypted data is properly flushed and finalized.
// This is useful for integrating encryption into existing writer-based pipelines.
func (e *Encryptor) EncryptWriter(dst io.Writer) (io.WriteCloser, error) {
e.mu.RLock()
recipients := e.recipients
e.mu.RUnlock()
// Create encrypted writer for all recipients
w, err := age.Encrypt(dst, recipients...)
if err != nil {
return nil, fmt.Errorf("creating encrypted writer: %w", err)
}
return w, nil
}
// UpdateRecipients updates the recipients for future encryption operations.
// This method is thread-safe and can be called while other encryption operations
// are in progress. Existing encryption operations will continue with the old
// recipients. At least one recipient must be provided. Returns an error if any
// of the public keys are invalid or if no recipients are specified.
func (e *Encryptor) UpdateRecipients(publicKeys []string) error {
if len(publicKeys) == 0 {
return ErrNoRecipients
}
recipients := make([]age.Recipient, 0, len(publicKeys))
for _, key := range publicKeys {
recipient, err := age.ParseX25519Recipient(key)
if err != nil {
return fmt.Errorf("parsing age recipient %s: %w", key, err)
}
recipients = append(recipients, recipient)
}
e.mu.Lock()
e.recipients = recipients
e.mu.Unlock()
return nil
}
// Decryptor provides thread-safe decryption using the age encryption library.
// It uses a private key to decrypt data that was encrypted for the corresponding
// public key.
type Decryptor struct {
identity age.Identity
mu sync.RWMutex
}
// NewDecryptor creates a new decryptor with the given age private key.
// The private key should be a valid age X25519 identity string.
// Returns an error if the private key is invalid.
func NewDecryptor(privateKey string) (*Decryptor, error) {
identity, err := age.ParseX25519Identity(privateKey)
if err != nil {
return nil, fmt.Errorf("parsing age identity: %w", err)
}
return &Decryptor{
identity: identity,
}, nil
}
// Decrypt decrypts data using age decryption.
// This method is suitable for small to medium amounts of data that fit in memory.
// For large data streams, use DecryptStream instead.
func (d *Decryptor) Decrypt(data []byte) ([]byte, error) {
d.mu.RLock()
identity := d.identity
d.mu.RUnlock()
r, err := age.Decrypt(bytes.NewReader(data), identity)
if err != nil {
return nil, fmt.Errorf("creating decrypted reader: %w", err)
}
decrypted, err := io.ReadAll(r)
if err != nil {
return nil, fmt.Errorf("reading decrypted data: %w", err)
}
return decrypted, nil
}
// DecryptStream returns a reader that decrypts data from the provided reader.
// This method is suitable for decrypting large files or streams as it processes
// data in a streaming fashion without loading everything into memory.
// The caller should close the input reader when done.
func (d *Decryptor) DecryptStream(src io.Reader) (io.Reader, error) {
d.mu.RLock()
identity := d.identity
d.mu.RUnlock()
r, err := age.Decrypt(src, identity)
if err != nil {
return nil, fmt.Errorf("creating decrypted reader: %w", err)
}
return r, nil
}
// Module exports the crypto module for fx dependency injection.
//
//nolint:gochecknoglobals // fx module definitions are package globals
var Module = fx.Module("crypto")
internal/crypto/encryption_test.go
-178
View File
@@ -1,178 +0,0 @@
package crypto_test
import (
"bytes"
"testing"
"filippo.io/age"
"sneak.berlin/go/vaultik/internal/crypto"
)
func TestEncryptor(t *testing.T) {
t.Parallel()
// Generate a test key pair
identity, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("failed to generate identity: %v", err)
}
publicKey := identity.Recipient().String()
// Create encryptor
enc, err := crypto.NewEncryptor([]string{publicKey})
if err != nil {
t.Fatalf("failed to create encryptor: %v", err)
}
// Test data
plaintext := []byte("Hello, World! This is a test message.")
// Encrypt
ciphertext, err := enc.Encrypt(plaintext)
if err != nil {
t.Fatalf("failed to encrypt: %v", err)
}
// Verify it's actually encrypted (should be larger and different)
if bytes.Equal(plaintext, ciphertext) {
t.Error("ciphertext equals plaintext")
}
// Decrypt to verify
r, err := age.Decrypt(bytes.NewReader(ciphertext), identity)
if err != nil {
t.Fatalf("failed to decrypt: %v", err)
}
var decrypted bytes.Buffer
_, err = decrypted.ReadFrom(r)
if err != nil {
t.Fatalf("failed to read decrypted data: %v", err)
}
if !bytes.Equal(plaintext, decrypted.Bytes()) {
t.Error("decrypted data doesn't match original")
}
}
func TestEncryptorMultipleRecipients(t *testing.T) {
t.Parallel()
// Generate three test key pairs
identity1, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("failed to generate identity1: %v", err)
}
identity2, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("failed to generate identity2: %v", err)
}
identity3, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("failed to generate identity3: %v", err)
}
publicKeys := []string{
identity1.Recipient().String(),
identity2.Recipient().String(),
identity3.Recipient().String(),
}
// Create encryptor with multiple recipients
enc, err := crypto.NewEncryptor(publicKeys)
if err != nil {
t.Fatalf("failed to create encryptor: %v", err)
}
// Test data
plaintext := []byte("Secret message for multiple recipients")
// Encrypt
ciphertext, err := enc.Encrypt(plaintext)
if err != nil {
t.Fatalf("failed to encrypt: %v", err)
}
// Verify each recipient can decrypt
identities := []age.Identity{identity1, identity2, identity3}
for i, identity := range identities {
r, err := age.Decrypt(bytes.NewReader(ciphertext), identity)
if err != nil {
t.Fatalf("recipient %d failed to decrypt: %v", i+1, err)
}
var decrypted bytes.Buffer
_, err = decrypted.ReadFrom(r)
if err != nil {
t.Fatalf("recipient %d failed to read decrypted data: %v", i+1, err)
}
if !bytes.Equal(plaintext, decrypted.Bytes()) {
t.Errorf("recipient %d: decrypted data doesn't match original", i+1)
}
}
}
func TestEncryptorUpdateRecipients(t *testing.T) {
t.Parallel()
// Generate two identities
identity1, _ := age.GenerateX25519Identity()
identity2, _ := age.GenerateX25519Identity()
publicKey1 := identity1.Recipient().String()
publicKey2 := identity2.Recipient().String()
// Create encryptor with first key
enc, err := crypto.NewEncryptor([]string{publicKey1})
if err != nil {
t.Fatalf("failed to create encryptor: %v", err)
}
// Encrypt with first key
plaintext := []byte("test data")
ciphertext1, err := enc.Encrypt(plaintext)
if err != nil {
t.Fatalf("failed to encrypt: %v", err)
}
// Update to second key
err = enc.UpdateRecipients([]string{publicKey2})
if err != nil {
t.Fatalf("failed to update recipients: %v", err)
}
// Encrypt with second key
ciphertext2, err := enc.Encrypt(plaintext)
if err != nil {
t.Fatalf("failed to encrypt: %v", err)
}
// First ciphertext should only decrypt with first identity
_, err = age.Decrypt(bytes.NewReader(ciphertext1), identity1)
if err != nil {
t.Error("failed to decrypt with identity1")
}
_, err = age.Decrypt(bytes.NewReader(ciphertext1), identity2)
if err == nil {
t.Error("should not decrypt with identity2")
}
// Second ciphertext should only decrypt with second identity
_, err = age.Decrypt(bytes.NewReader(ciphertext2), identity2)
if err != nil {
t.Error("failed to decrypt with identity2")
}
_, err = age.Decrypt(bytes.NewReader(ciphertext2), identity1)
if err == nil {
t.Error("should not decrypt with identity1")
}
}
internal/database/blobs.go
+24
View File
@@ -208,6 +208,30 @@ func (r *BlobRepository) DeleteOrphaned(ctx context.Context) error {
return nil
}
// DeleteUnuploaded deletes blob rows whose upload never completed
// (uploaded_ts IS NULL) and returns how many were removed. Their
// blob_chunks rows are removed by the ON DELETE CASCADE foreign key.
// A blob is only ever attached to a snapshot once its upload has been
// recorded, so an un-uploaded blob is never referenced by a completed
// snapshot: dropping it discards chunk rows that point at data which
// was never stored remotely, so the affected content is re-chunked and
// re-uploaded on the next run.
func (r *BlobRepository) DeleteUnuploaded(ctx context.Context) (int64, error) {
query := `DELETE FROM blobs WHERE uploaded_ts IS NULL`
result, err := r.db.ExecWithLog(ctx, query)
if err != nil {
return 0, fmt.Errorf("deleting un-uploaded blobs: %w", err)
}
rowsAffected, _ := result.RowsAffected()
if rowsAffected > 0 {
log.Debug("Deleted un-uploaded blobs", "count", rowsAffected)
}
return rowsAffected, nil
}
// getOne fetches a single blob row matched on the given column, or
// (nil, nil) when no row matches.
func (r *BlobRepository) getOne(
internal/database/chunks_ext.go
+22 -2
View File
@@ -7,12 +7,32 @@ import (
// List returns every chunk in the index, ordered by chunk hash.
func (r *ChunkRepository) List(ctx context.Context) ([]*Chunk, error) {
query := `
return r.list(ctx, `
SELECT chunk_hash, size
FROM chunks
ORDER BY chunk_hash
`
`)
}
// ListInUploadedBlobs returns the chunks that are stored in a blob whose
// upload has completed (uploaded_ts set), ordered by chunk hash. These
// are the only chunks a backup may safely deduplicate against: a chunk
// recorded solely in a blob that was never uploaded refers to data that
// is not in remote storage, so trusting it would silently drop that data
// from later snapshots.
func (r *ChunkRepository) ListInUploadedBlobs(ctx context.Context) ([]*Chunk, error) {
return r.list(ctx, `
SELECT DISTINCT c.chunk_hash, c.size
FROM chunks c
JOIN blob_chunks bc ON c.chunk_hash = bc.chunk_hash
JOIN blobs b ON bc.blob_id = b.id
WHERE b.uploaded_ts IS NOT NULL
ORDER BY c.chunk_hash
`)
}
// list runs a chunk-selecting query and scans the (chunk_hash, size) rows.
func (r *ChunkRepository) list(ctx context.Context, query string) ([]*Chunk, error) {
rows, err := r.db.conn.QueryContext(ctx, query)
if err != nil {
return nil, fmt.Errorf("querying chunks: %w", err)
internal/database/database.go
+134 -2
View File
@@ -3,8 +3,10 @@
//
// Blobs in Vaultik are the final storage units uploaded to S3. Each blob is a
// large (up to 10GB) file containing many compressed and encrypted chunks from
// multiple source files. Blobs are content-addressed, meaning their filename
// is derived from their SHA256 hash after compression and encryption.
// multiple source files. Blobs are content-addressed: the filename in S3 is
// hex(SHA256(SHA256(uncompressed blob contents))), computed from the chunk data
// before compression and encryption (not from the stored bytes). See
// blobgen.DoubleSHA256 and docs/REPOSTRUCTURE.md.
//
// Schema is managed via numbered SQL migrations embedded in the schema/
// directory. Migration 000.sql bootstraps the schema_migrations tracking
@@ -17,6 +19,7 @@ import (
"embed"
"errors"
"fmt"
"net/url"
"os"
"path/filepath"
"sort"
@@ -219,6 +222,135 @@ func openWithRecovery(ctx context.Context, path string) (*DB, error) {
return db, nil
}
// errUntrustedSnapshotSchema is returned when a downloaded snapshot
// database carries schema objects the real schema never defines, or is
// missing a table the restore and deep-verify queries read.
var errUntrustedSnapshotSchema = errors.New(
"downloaded snapshot database has an untrusted schema")
// snapshotReadOnlyDSN builds the driver DSN that opens a materialized
// snapshot database file read-only. mode=ro opens the file read-only at
// the OS level, query_only rejects any write the engine is asked to make,
// and trusted_schema=OFF refuses to run application code named in the
// schema. The file: URI form is required for the driver to honour the
// mode parameter.
func snapshotReadOnlyDSN(path string) string {
u := url.URL{
Scheme: "file",
Path: path,
RawQuery: "mode=ro&_pragma=query_only(true)&_pragma=trusted_schema(false)",
}
return u.String()
}
// OpenReadOnly opens an already-materialized SQLite file for read-only
// querying of a snapshot database downloaded from the store, used by
// restore and deep verify. Unlike New it never applies schema migrations
// and never writes: the connection is opened read-only with query_only
// and trusted_schema=OFF. It refuses any file whose schema carries a
// trigger, view or virtual table, or lacks an expected table, so a forged
// file cannot redefine what the restore queries return. The caller owns
// the file and must remove it.
func OpenReadOnly(ctx context.Context, path string) (*DB, error) {
conn, err := sql.Open("sqlite", snapshotReadOnlyDSN(path))
if err != nil {
return nil, fmt.Errorf("opening read-only database: %w", err)
}
configureConnPool(conn)
err = conn.PingContext(ctx)
if err != nil {
_ = conn.Close()
return nil, fmt.Errorf("opening read-only database: %w", err)
}
err = verifySnapshotSchema(ctx, conn)
if err != nil {
_ = conn.Close()
return nil, err
}
return &DB{conn: conn, path: path}, nil
}
// verifySnapshotSchema rejects a downloaded database whose schema is not
// the plain table set the real schema defines. Any trigger, view or
// virtual table, or a missing expected table, fails the open.
func verifySnapshotSchema(ctx context.Context, conn *sql.DB) error {
// expectedSnapshotTables are the tables the restore and deep-verify
// queries read. A downloaded database missing any of them is not a
// genuine snapshot database and is refused.
expectedSnapshotTables := []string{
"blob_chunks",
"blobs",
"chunks",
"file_chunks",
"files",
}
rows, err := conn.QueryContext(
ctx, "SELECT type, name, sql FROM sqlite_master")
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
defer func() { _ = rows.Close() }()
present := make(map[string]struct{})
for rows.Next() {
var objType, name string
var objSQL sql.NullString
err = rows.Scan(&objType, &name, &objSQL)
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
switch objType {
case "trigger", "view":
return fmt.Errorf(
"%w: unexpected %s %q", errUntrustedSnapshotSchema, objType, name)
case "table":
if isVirtualTableSQL(objSQL.String) {
return fmt.Errorf(
"%w: unexpected virtual table %q",
errUntrustedSnapshotSchema, name)
}
present[name] = struct{}{}
}
}
err = rows.Err()
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
for _, table := range expectedSnapshotTables {
if _, ok := present[table]; !ok {
return fmt.Errorf(
"%w: missing table %q", errUntrustedSnapshotSchema, table)
}
}
return nil
}
// isVirtualTableSQL reports whether a sqlite_master row's SQL defines a
// virtual table. Virtual tables are recorded with type 'table' but a
// "CREATE VIRTUAL TABLE" definition and can run module code, so they are
// refused alongside triggers and views.
func isVirtualTableSQL(createSQL string) bool {
return strings.HasPrefix(
strings.ToUpper(strings.TrimSpace(createSQL)), "CREATE VIRTUAL TABLE")
}
// NewTestDB creates an in-memory SQLite database for testing purposes.
// The database is automatically initialized with the schema and is ready
// for use. Each call creates a new independent database instance.
internal/database/models.go
+6 -6
View File
@@ -51,15 +51,15 @@ type Chunk struct {
// Blob represents a blob record in the database.
// A blob is Vaultik's final storage unit - a large file (up to 10GB) containing
// many compressed and encrypted chunks from multiple source files.
// Blobs are content-addressed, meaning their filename in S3 is derived from
// the SHA256 hash of their compressed and encrypted content.
// The blob creation process is: chunks are accumulated -> compressed with zstd
// -> encrypted with age -> hashed -> uploaded to S3 with the hash as filename.
// Blobs are content-addressed: the filename in S3 is
// hex(SHA256(SHA256(uncompressed blob contents))), computed from the chunk data
// before compression and encryption (not from the stored bytes). See
// blobgen.DoubleSHA256 and docs/REPOSTRUCTURE.md.
type Blob struct {
ID types.BlobID // UUID assigned when blob creation starts
// Hash is the SHA256 of the final compressed+encrypted content
// (empty until finalized).
// Hash is hex(SHA256(SHA256(uncompressed blob contents)))
// (empty until finalized); see the type comment above.
Hash types.BlobHash
CreatedTS time.Time // When blob creation started
FinishedTS *time.Time // When blob was finalized (nil if still packing)
internal/database/module.go
+44
View File
@@ -2,6 +2,7 @@ package database
import (
"context"
"errors"
"fmt"
"os"
"path/filepath"
@@ -15,6 +16,44 @@ import (
// the index describes the backed-up file tree and must stay private.
const indexDirPerm = 0o700
// indexFilePerm restricts the index file to the owning user; it lists every
// backed-up path and chunk hash and must stay private.
const indexFilePerm = 0o600
// ensureIndexFileMode makes the index file owner-only before the SQLite
// driver opens it: it creates the file 0600 if absent, or chmods an existing
// one to 0600. Doing this first matters because SQLite creates its -wal and
// -shm side files with the mode of the main database file, so a private main
// file yields private side files. The driver treats a zero-byte file as an
// empty database, so pre-creating it here is safe.
func ensureIndexFileMode(path string) error {
info, err := os.Stat(path)
switch {
case err == nil:
if info.Mode().Perm() == indexFilePerm {
return nil
}
err = os.Chmod(path, indexFilePerm)
if err != nil {
return fmt.Errorf("restricting index file permissions: %w", err)
}
return nil
case errors.Is(err, os.ErrNotExist):
//nolint:gosec // G304: the index path is operator-configured by design
f, err := os.OpenFile(path, os.O_CREATE|os.O_WRONLY, indexFilePerm)
if err != nil {
return fmt.Errorf("creating index file: %w", err)
}
return f.Close()
default:
return fmt.Errorf("checking index file: %w", err)
}
}
// Module provides database dependencies
//
//nolint:gochecknoglobals // fx module definitions are package globals by convention
@@ -34,6 +73,11 @@ func provideDatabase(lc fx.Lifecycle, cfg *config.Config) (*DB, error) {
return nil, fmt.Errorf("creating index directory: %w", err)
}
err = ensureIndexFileMode(cfg.IndexPath)
if err != nil {
return nil, err
}
db, err := New(context.Background(), cfg.IndexPath)
if err != nil {
return nil, fmt.Errorf("opening database: %w", err)
internal/database/module_internal_test.go
+100
View File
@@ -0,0 +1,100 @@
package database
import (
"os"
"path/filepath"
"syscall"
"testing"
"go.uber.org/fx/fxtest"
"sneak.berlin/go/vaultik/internal/config"
)
// TestProvideDatabaseFreshIndexMode verifies that provideDatabase creates a
// missing index file owner-only (0600), even under a lenient 022 umask that
// would otherwise leave a freshly created file world-readable.
//
//nolint:paralleltest // syscall.Umask is process-global; parallel tests would clash
func TestProvideDatabaseFreshIndexMode(t *testing.T) {
restore := syscall.Umask(0o022)
defer syscall.Umask(restore)
indexPath := filepath.Join(t.TempDir(), "index.sqlite")
openIndex(t, indexPath)
assertPerm(t, indexPath, 0o600)
}
// TestProvideDatabaseExistingIndexMode verifies that provideDatabase tightens
// an existing world-readable index (0644) in a group/other-readable directory
// down to owner-only (0600).
//
//nolint:paralleltest // syscall.Umask is process-global; parallel tests would clash
func TestProvideDatabaseExistingIndexMode(t *testing.T) {
restore := syscall.Umask(0o022)
defer syscall.Umask(restore)
dir := filepath.Join(t.TempDir(), "data")
//nolint:gosec // G301: the test intentionally uses a 0755 directory
err := os.MkdirAll(dir, 0o755)
if err != nil {
t.Fatalf("creating index directory: %v", err)
}
//nolint:gosec // G302: the test intentionally uses a 0755 directory
err = os.Chmod(dir, 0o755)
if err != nil {
t.Fatalf("relaxing index directory permissions: %v", err)
}
indexPath := filepath.Join(dir, "index.sqlite")
//nolint:gosec // G306: the test intentionally starts from a 0644 index
err = os.WriteFile(indexPath, nil, 0o644)
if err != nil {
t.Fatalf("creating pre-existing index: %v", err)
}
//nolint:gosec // G302: the test intentionally starts from a 0644 index
err = os.Chmod(indexPath, 0o644)
if err != nil {
t.Fatalf("relaxing pre-existing index permissions: %v", err)
}
openIndex(t, indexPath)
assertPerm(t, indexPath, 0o600)
}
// openIndex runs provideDatabase against indexPath and closes the resulting
// database before returning.
func openIndex(t *testing.T, indexPath string) {
t.Helper()
cfg := &config.Config{IndexPath: indexPath}
db, err := provideDatabase(fxtest.NewLifecycle(t), cfg)
if err != nil {
t.Fatalf("provideDatabase: %v", err)
}
err = db.Close()
if err != nil {
t.Fatalf("closing database: %v", err)
}
}
// assertPerm fails the test unless path has exactly the given permission bits.
func assertPerm(t *testing.T, path string, want os.FileMode) {
t.Helper()
info, err := os.Stat(path)
if err != nil {
t.Fatalf("stat %s: %v", path, err)
}
got := info.Mode().Perm()
if got != want {
t.Fatalf("permissions of %s = %#o, want %#o", path, got, want)
}
}
internal/database/read_only_test.go
+145
View File
@@ -0,0 +1,145 @@
//nolint:testpackage // exercises unexported read-only open internals
package database
import (
"context"
"database/sql"
"errors"
"path/filepath"
"testing"
)
// genuineSnapshotDB writes a real snapshot database (the full schema
// applied) to a fresh file and returns its path.
func genuineSnapshotDB(t *testing.T) string {
t.Helper()
path := filepath.Join(t.TempDir(), "snapshot.db")
db, err := New(context.Background(), path)
if err != nil {
t.Fatalf("creating snapshot database: %v", err)
}
err = db.Close()
if err != nil {
t.Fatalf("closing snapshot database: %v", err)
}
return path
}
// forgedDB creates an empty database file and runs the given statements
// against it read-write, so a test can plant schema objects the real
// schema never defines.
func forgedDB(t *testing.T, stmts ...string) string {
t.Helper()
path := filepath.Join(t.TempDir(), "forged.db")
db, err := sql.Open("sqlite", path)
if err != nil {
t.Fatalf("opening forged database: %v", err)
}
for _, stmt := range stmts {
_, err = db.ExecContext(context.Background(), stmt)
if err != nil {
t.Fatalf("executing %q: %v", stmt, err)
}
}
err = db.Close()
if err != nil {
t.Fatalf("closing forged database: %v", err)
}
return path
}
func TestOpenReadOnlyAcceptsGenuineSnapshot(t *testing.T) {
t.Parallel()
db, err := OpenReadOnly(context.Background(), genuineSnapshotDB(t))
if err != nil {
t.Fatalf("OpenReadOnly refused a genuine snapshot database: %v", err)
}
t.Cleanup(func() { _ = db.Close() })
}
func TestOpenReadOnlyRefusesWrites(t *testing.T) {
t.Parallel()
db, err := OpenReadOnly(context.Background(), genuineSnapshotDB(t))
if err != nil {
t.Fatalf("OpenReadOnly: %v", err)
}
t.Cleanup(func() { _ = db.Close() })
// A schema write depends on no table columns, so the only reason it
// can fail is that the database is open read-only.
_, err = db.Conn().ExecContext(context.Background(),
"CREATE TABLE probe_readonly (x)")
if err == nil {
t.Fatal("expected a write to a read-only snapshot database to fail")
}
}
func TestOpenReadOnlyRejectsView(t *testing.T) {
t.Parallel()
path := forgedDB(t, "CREATE VIEW files AS SELECT 1 AS path")
_, err := OpenReadOnly(context.Background(), path)
if !errors.Is(err, errUntrustedSnapshotSchema) {
t.Fatalf("expected a view named files to be refused, got %v", err)
}
}
func TestOpenReadOnlyRejectsTrigger(t *testing.T) {
t.Parallel()
path := forgedDB(t,
"CREATE TABLE files (path TEXT)",
"CREATE TRIGGER t AFTER INSERT ON files BEGIN SELECT 1; END")
_, err := OpenReadOnly(context.Background(), path)
if !errors.Is(err, errUntrustedSnapshotSchema) {
t.Fatalf("expected a trigger to be refused, got %v", err)
}
}
func TestOpenReadOnlyRejectsMissingTable(t *testing.T) {
t.Parallel()
// Only one of the expected tables is present.
path := forgedDB(t, "CREATE TABLE files (path TEXT)")
_, err := OpenReadOnly(context.Background(), path)
if !errors.Is(err, errUntrustedSnapshotSchema) {
t.Fatalf("expected a missing expected table to be refused, got %v", err)
}
}
func TestIsVirtualTableSQL(t *testing.T) {
t.Parallel()
cases := []struct {
sql string
want bool
}{
{"CREATE VIRTUAL TABLE t USING fts5(x)", true},
{" create virtual table t using fts5(x)", true},
{"CREATE TABLE t (x)", false},
{"CREATE VIEW t AS SELECT 1", false},
{"", false},
}
for _, c := range cases {
if got := isVirtualTableSQL(c.sql); got != c.want {
t.Errorf("isVirtualTableSQL(%q) = %v, want %v", c.sql, got, c.want)
}
}
}
internal/database/snapshots.go
+54
View File
@@ -11,6 +11,18 @@ import (
"sneak.berlin/go/vaultik/internal/types"
)
// Sentinel errors for the single-snapshot invariant that an exported
// per-snapshot metadata database must satisfy.
var (
// ErrNoSnapshotInDatabase means the metadata database has no snapshot
// row at all.
ErrNoSnapshotInDatabase = errors.New("database contains no snapshot")
// ErrMultipleSnapshotsInDatabase means the metadata database holds
// more than the single snapshot an export is supposed to contain.
ErrMultipleSnapshotsInDatabase = errors.New(
"database contains more than one snapshot")
)
// SnapshotRepository provides access to the snapshots table and its
// snapshot_files / snapshot_blobs association tables.
type SnapshotRepository struct {
@@ -206,6 +218,48 @@ func (r *SnapshotRepository) GetByID(
return &snapshot, nil
}
// GetOnlySnapshot returns the sole snapshot in an exported per-snapshot
// metadata database. The backup path writes each snapshot's database with
// exactly one snapshot row (see cleanSnapshotDB), so restore and deep
// verify expect exactly one. Zero rows return ErrNoSnapshotInDatabase and
// more than one returns ErrMultipleSnapshotsInDatabase; callers treat
// either as a failed identity check on the downloaded database.
func (r *SnapshotRepository) GetOnlySnapshot(ctx context.Context) (*Snapshot, error) {
query := `
SELECT id, hostname, vaultik_version, vaultik_git_revision,
started_at, completed_at, file_count, chunk_count, blob_count,
total_size, blob_size, compression_ratio
FROM snapshots
LIMIT 2
`
rows, err := r.db.conn.QueryContext(ctx, query)
if err != nil {
return nil, fmt.Errorf("querying snapshots: %w", err)
}
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
snapshots, err := r.scanSnapshotRows(rows)
if err != nil {
return nil, err
}
switch len(snapshots) {
case 1:
return snapshots[0], nil
case 0:
return nil, ErrNoSnapshotInDatabase
default:
return nil, ErrMultipleSnapshotsInDatabase
}
}
// ListRecent returns up to limit snapshots, most recently started first.
func (r *SnapshotRepository) ListRecent(
ctx context.Context, limit int,
internal/log/module.go
+15 -1
View File
@@ -14,8 +14,18 @@ var Module = fx.Module("log",
)
// New creates a new logger configuration from provided options.
//
// JSON is intentionally not carried into Config: a command emitting a
// JSON document on stdout must keep its stderr log level under
// --verbose/--debug, so --json must not lower it (issue #112). JSON
// silences the stdout UI in setupGlobals instead.
func New(opts Options) Config {
return Config(opts)
return Config{
Verbose: opts.Verbose,
Debug: opts.Debug,
Cron: opts.Cron,
Quiet: opts.Quiet,
}
}
// Options are provided by the CLI.
@@ -24,4 +34,8 @@ type Options struct {
Debug bool
Cron bool
Quiet bool
// JSON marks a command whose stdout carries a machine-readable
// document. It silences the human UI on stdout (see setupGlobals),
// but unlike Quiet it leaves the stderr log level alone.
JSON bool
}
internal/log/tty_escape_test.go
+39
View File
@@ -0,0 +1,39 @@
package log_test
import (
"bytes"
"log/slog"
"strings"
"testing"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
)
// TestTTYHandlerEscapesControlCharacters logs a message and an attribute
// value that each carry an ESC and a newline — the shape a crafted path or
// storage error from the destination would take — and checks neither raw
// byte reaches the output. The handler's own colour codes (ESC ... m) are
// stripped first; any ESC left after that came from the untrusted value.
func TestTTYHandlerEscapesControlCharacters(t *testing.T) {
t.Parallel()
var buf bytes.Buffer
logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions()))
logger.Info("start\x1b[31mZAP\nend", "target", "a\x1b[31mZAP\nb")
out := buf.String()
// The only newline is the line terminator; the injected ones were escaped.
require.Equal(t, 1, strings.Count(out, "\n"),
"a newline in the message or a value must be escaped, not emitted raw")
// After the handler's own colour codes are removed, no ESC survives.
stripped := ansiEscape.ReplaceAllString(out, "")
require.NotContains(t, stripped, "\x1b",
"a raw ESC from the message or a value must not reach the terminal")
// The escaped form is what appears instead.
require.Contains(t, out, `\x1b`)
}
internal/log/tty_handler.go
+29 -4
View File
@@ -5,9 +5,11 @@ import (
"fmt"
"io"
"log/slog"
"strconv"
"strings"
"sync"
"time"
"unicode"
)
// groupSeparator joins an open group path to an attribute key. This
@@ -116,11 +118,14 @@ func (h *TTYHandler) Handle(_ context.Context, r slog.Record) error {
levelColor = colorReset
}
// Print main message
// Print main message. The message is escaped before the colour codes
// are written around it: it can carry text from an untrusted source
// (a storage error, for one), and a raw control character would
// otherwise reach the terminal.
_, _ = fmt.Fprintf(h.out, "%s%s%s %s%s%s %s%s%s",
colorGray, timestamp, colorReset,
levelColor, level, colorReset,
colorBold, r.Message, colorReset)
colorBold, sanitize(r.Message), colorReset)
// Attributes carried by the handler come first, then the record's
// own. Handler attributes were qualified when they were added; the
@@ -260,9 +265,29 @@ func (h *TTYHandler) writeAttr(a slog.Attr) {
// Future kinds also use the plain string form.
}
// Escape the key and value before the colour codes are written around
// them. Both can carry text from an untrusted source — a manifest
// timestamp, a storage error, a path or symlink target read back from
// the snapshot database — so a control character in one of them must
// be rendered as an escape sequence rather than reaching the terminal,
// where it could move the cursor or inject its own colours.
_, _ = fmt.Fprintf(h.out, " %s%s%s=%s%s%s",
colorCyan, a.Key, colorReset,
colorBlue, value, colorReset)
colorCyan, sanitize(a.Key), colorReset,
colorBlue, sanitize(value), colorReset)
}
// sanitize returns s unchanged when every rune in it is printable, and a
// double-quoted, backslash-escaped form (\n, \x1b, …) otherwise. It is
// applied to untrusted text before any colour code is written, so a
// control character can never reach the terminal raw.
func sanitize(s string) string {
for _, r := range s {
if !unicode.IsPrint(r) {
return strconv.Quote(s)
}
}
return s
}
// formatDuration formats a duration in a human-readable way
internal/snapshot/export_perm_test.go
+49
View File
@@ -0,0 +1,49 @@
//nolint:testpackage // exercises the unexported copyFile helper
package snapshot
import (
"os"
"path/filepath"
"syscall"
"testing"
"github.com/spf13/afero"
)
// TestCopyFileExportCopyMode verifies that the exported snapshot database
// copy is created owner-only (0600), even under a lenient 022 umask that
// would otherwise leave a fresh file world-readable.
//
//nolint:paralleltest // syscall.Umask is process-global; parallel tests would clash
func TestCopyFileExportCopyMode(t *testing.T) {
restore := syscall.Umask(0o022)
defer syscall.Umask(restore)
dir := t.TempDir()
src := filepath.Join(dir, "index.sqlite")
err := os.WriteFile(src, []byte("index data"), 0o600)
if err != nil {
t.Fatalf("creating source index: %v", err)
}
dst := filepath.Join(dir, "snapshot.db")
sm := &SnapshotManager{fs: afero.NewOsFs()}
err = sm.copyFile(src, dst)
if err != nil {
t.Fatalf("copyFile: %v", err)
}
info, err := os.Stat(dst)
if err != nil {
t.Fatalf("stat export copy: %v", err)
}
got := info.Mode().Perm()
if got != 0o600 {
t.Fatalf("export copy permissions = %#o, want %#o", got, 0o600)
}
}
internal/snapshot/manifest.go
+30 -5
View File
@@ -7,6 +7,19 @@ import (
"io"
"github.com/klauspost/compress/zstd"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// Manifest size bounds. A manifest lists one small entry per blob, and
// blobs are large (the default target is 10 GB), so even a manifest for a
// petabyte-scale backup is a few megabytes. These caps are far above any
// manifest the writer can emit, yet stop a crafted, highly compressible
// manifest from expanding without limit when decoded: the manifest is
// fetched from the store, which is not trusted, and json.Decode buffers
// the whole value in memory.
const (
manifestMaxCompressed = 256 * 1024 * 1024 // 256 MiB
manifestMaxDecompressed = 1024 * 1024 * 1024 // 1 GiB
)
// Manifest represents the structure of a snapshot's blob manifest
@@ -28,19 +41,31 @@ type BlobInfo struct {
CompressedSize int64 `json:"compressed_size"`
}
// DecodeManifest decodes a manifest from a reader containing compressed JSON
// DecodeManifest decodes a manifest from a reader containing compressed
// JSON, reading through byte limits on both the compressed input and the
// decompressed output so an untrusted manifest cannot exhaust memory.
func DecodeManifest(r io.Reader) (*Manifest, error) {
// Decompress using zstd
zr, err := zstd.NewReader(r)
return decodeManifest(r, manifestMaxCompressed, manifestMaxDecompressed)
}
// decodeManifest is DecodeManifest with explicit limits, so tests can drive
// the bounds with small inputs instead of gigabyte-scale ones.
func decodeManifest(
r io.Reader, maxCompressed, maxDecompressed int64,
) (*Manifest, error) {
// Decompress using zstd, bounding how many compressed bytes are read.
zr, err := zstd.NewReader(blobgen.LimitReader(r, maxCompressed))
if err != nil {
return nil, fmt.Errorf("creating zstd reader: %w", err)
}
defer zr.Close()
// Decode JSON manifest
// Decode JSON manifest, bounding how far the compressed input may
// expand: json.Decode buffers the whole value, so without this a
// small, highly compressible manifest could expand to gigabytes.
var manifest Manifest
err = json.NewDecoder(zr).Decode(&manifest)
err = json.NewDecoder(blobgen.LimitReader(zr, maxDecompressed)).Decode(&manifest)
if err != nil {
return nil, fmt.Errorf("decoding manifest: %w", err)
}
internal/snapshot/manifest_bound_test.go
+79
View File
@@ -0,0 +1,79 @@
//nolint:testpackage // exercises the unexported decodeManifest bounds
package snapshot
import (
"bytes"
"strings"
"testing"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// testSnapshotID is a stand-in snapshot ID reused across the bound cases.
const testSnapshotID = "host_home_2026-01-01T00:00:00Z"
// TestDecodeManifestRoundTrip is the baseline: with generous bounds a
// manifest the writer produced decodes back unchanged.
func TestDecodeManifestRoundTrip(t *testing.T) {
t.Parallel()
want := &Manifest{
SnapshotID: testSnapshotID,
Timestamp: "2026-01-01T00:00:00Z",
BlobCount: 2,
TotalCompressedSize: 42,
Blobs: []BlobInfo{
{Hash: "aa", CompressedSize: 21},
{Hash: "bb", CompressedSize: 21},
},
}
compressed, err := EncodeManifest(want, 3)
require.NoError(t, err)
got, err := decodeManifest(
bytes.NewReader(compressed), manifestMaxCompressed, manifestMaxDecompressed)
require.NoError(t, err)
require.Equal(t, want, got)
}
// TestDecodeManifestBoundsDecompressedOutput feeds a valid but highly
// compressible manifest — one whose timestamp is a megabyte of the same
// character — through a small decompressed bound. The compressed form is
// tiny, so only the decompressed bound stops it; decoding must fail within
// that bound rather than expanding the value in memory.
func TestDecodeManifestBoundsDecompressedOutput(t *testing.T) {
t.Parallel()
bomb := &Manifest{
SnapshotID: testSnapshotID,
Timestamp: strings.Repeat("a", 1<<20),
}
compressed, err := EncodeManifest(bomb, 3)
require.NoError(t, err)
require.Less(t, len(compressed), 4096,
"the compressible manifest must be small compressed")
_, err = decodeManifest(bytes.NewReader(compressed), 1<<20, 4096)
require.ErrorIs(t, err, blobgen.ErrOutputTooLarge)
}
// TestDecodeManifestBoundsCompressedInput checks the compressed-input
// bound fires independently: a valid manifest with a generous decompressed
// bound but a tiny compressed bound still fails.
func TestDecodeManifestBoundsCompressedInput(t *testing.T) {
t.Parallel()
manifest := &Manifest{
SnapshotID: testSnapshotID,
Timestamp: strings.Repeat("a", 4096),
}
compressed, err := EncodeManifest(manifest, 3)
require.NoError(t, err)
_, err = decodeManifest(bytes.NewReader(compressed), 8, manifestMaxDecompressed)
require.Error(t, err)
}
internal/snapshot/manifest_gen_test.go
+64
View File
@@ -0,0 +1,64 @@
//nolint:testpackage // exercises the unexported generateBlobManifest
package snapshot
import (
"context"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
)
// TestGenerateBlobManifest_MissingBlobFails is the regression guard for
// issue #157: a blob the snapshot references but that is absent from the
// blobs table used to be logged and skipped, yielding a manifest with
// fewer blobs than the snapshot needs. Since prune trusts the manifest
// alone, that omitted blob would be deleted at the next prune. Manifest
// generation must fail instead.
func TestGenerateBlobManifest_MissingBlobFails(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
dbPath := filepath.Join(t.TempDir(), "snapshot.db")
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
// A real blob row satisfies the snapshot_blobs foreign key on
// blob_id; the snapshot then references a different, absent hash.
presentBlob := &database.Blob{
ID: types.NewBlobID(),
Hash: types.BlobHash("present-blob-hash"),
CreatedTS: time.Now().Truncate(time.Second),
}
require.NoError(t, repos.Blobs.Create(ctx, nil, presentBlob))
snap := &database.Snapshot{
ID: "testhost_home_2026-05-01T00:00:00Z",
Hostname: "testhost",
}
require.NoError(t, repos.Snapshots.Create(ctx, nil, snap))
require.NoError(t, repos.Snapshots.AddBlob(ctx, nil,
snap.ID.String(), presentBlob.ID, types.BlobHash("absent-blob-hash")))
require.NoError(t, db.Close())
sm := &SnapshotManager{
config: &config.Config{CompressionLevel: 3},
fs: afero.NewOsFs(),
}
_, err = sm.generateBlobManifest(ctx, dbPath, snap.ID.String())
require.Error(t, err, "manifest generation must fail on a missing blob")
assert.Contains(t, err.Error(), "absent-blob-hash")
}
internal/snapshot/scanner.go
+93 -10
View File
@@ -63,7 +63,9 @@ type Scanner struct {
exclude []string // Glob patterns for files/directories to exclude
compiledExclude []compiledPattern // Compiled glob patterns
progress *ProgressReporter
skipErrors bool // Skip file read errors (log loudly but continue)
// skipErrors skips files that cannot be opened or read (logged loudly);
// packer, database, encryption, and upload errors still abort the run.
skipErrors bool
// ui is the user-facing output; never nil (defaults to a discarding writer).
ui *ui.Writer
@@ -117,11 +119,13 @@ type ScannerConfig struct {
Storage storage.Storer
MaxBlobSize int64
CompressionLevel int
AgeRecipients []string // Optional, empty means no encryption
AgeRecipients []string // required; output is always encrypted
EnableProgress bool // Enable the live progress reporter (ETAs, throughput)
UI *ui.Writer // Where user-facing scanner messages go; nil = discard
Exclude []string // Glob patterns for files/directories to exclude
SkipErrors bool // Skip file read errors (log loudly but continue)
// SkipErrors skips files that cannot be opened or read (log loudly but
// continue); packer, database, encryption, and upload errors still abort.
SkipErrors bool
}
// ScanResult contains the results of a scan operation
@@ -220,7 +224,14 @@ func (s *Scanner) Scan(
defer s.progress.Stop()
}
// Phase 0: Load known files and chunks from database into memory for fast lookup
// Phase 0: Repair any state left by an interrupted previous run, then
// load known files and chunks from the database into memory for fast
// lookup.
err := s.repairInterruptedBlobs(ctx)
if err != nil {
return nil, err
}
knownFiles, err := s.loadDatabaseState(ctx, path)
if err != nil {
return nil, err
@@ -317,6 +328,38 @@ func (s *Scanner) loadDatabaseState(
return knownFiles, nil
}
// repairInterruptedBlobs discards blob rows left by a previous run whose
// upload never completed. Such a blob has its chunks, blob_chunks, and
// blobs rows committed to the local index before the upload is attempted,
// so a crash or dropped connection mid-upload leaves them behind while the
// data never reaches remote storage. Deduplicating against those chunks on
// a later run would produce a snapshot that reports success but cannot be
// restored. Dropping the un-uploaded blobs (their blob_chunks cascade) and
// then any chunks left unreferenced forces the affected data to be
// re-chunked and re-uploaded this run. A blob is attached to a snapshot
// only once its upload is recorded, so this never touches a completed
// snapshot's data.
func (s *Scanner) repairInterruptedBlobs(ctx context.Context) error {
removed, err := s.repos.Blobs.DeleteUnuploaded(ctx)
if err != nil {
return fmt.Errorf("removing un-uploaded blob records: %w", err)
}
if removed == 0 {
return nil
}
log.Warn("Discarded blob records from an interrupted previous run; "+
"their data will be re-uploaded", "blobs", removed)
err = s.repos.Chunks.DeleteOrphaned(ctx)
if err != nil {
return fmt.Errorf("removing orphaned chunks: %w", err)
}
return nil
}
// summarizeScanPhase calculates total size to process, updates progress tracking,
// and prints the scan phase summary with file counts and sizes
func (s *Scanner) summarizeScanPhase(
@@ -392,11 +435,14 @@ func (s *Scanner) loadKnownFiles(
return result, nil
}
// loadKnownChunks loads all known chunk hashes from the database into a
// map for fast lookup. This avoids per-chunk database queries during file
// processing.
// loadKnownChunks loads the chunk hashes safe to deduplicate against into
// an in-memory map for fast lookup, avoiding per-chunk database queries
// during file processing. Only chunks held by a blob whose upload
// completed are loaded: a chunk left behind by an interrupted upload
// refers to data that never reached remote storage, and deduplicating
// against it would silently produce an unrestorable snapshot.
func (s *Scanner) loadKnownChunks(ctx context.Context) error {
chunks, err := s.repos.Chunks.List(ctx)
chunks, err := s.repos.Chunks.ListInUploadedBlobs(ctx)
if err != nil {
return fmt.Errorf("listing chunks: %w", err)
}
@@ -1294,6 +1340,15 @@ func (s *Scanner) processFileWithErrorHandling(
) (bool, error) {
err := s.processFileStreaming(ctx, fileToProcess, result)
if err != nil {
// A packer/database/encryption/upload failure means the chunk's data
// may not have been stored. Skipping the file would let the snapshot
// record a file whose chunk is in no blob and cannot be restored, so
// abort the run even under --skip-errors. Only open and read errors
// are skipped below.
var pErr *packerError
if errors.As(err, &pErr) {
return false, fmt.Errorf("processing file %s: %w", fileToProcess.Path, err)
}
// Handle files that were deleted between scan and process phases
if errors.Is(err, os.ErrNotExist) {
log.Warn("File was deleted during backup, skipping",
@@ -1303,7 +1358,7 @@ func (s *Scanner) processFileWithErrorHandling(
return true, nil
}
// Skip file read errors if --skip-errors is enabled
// Skip open/read errors if --skip-errors is enabled
if s.skipErrors {
log.Error("Failed to process file (skipping due to --skip-errors)",
"path", fileToProcess.Path, "error", err)
@@ -1401,7 +1456,17 @@ func (s *Scanner) finalizeProcessPhase(ctx context.Context, result *ScanResult)
return fmt.Errorf("parsing blob ID: %w", err)
}
// With no remote backend the blob's lifecycle ends here, so
// mark it uploaded in the same transaction that attaches it to
// the snapshot. This keeps the invariant that any blob a
// snapshot references has uploaded_ts set, so deduplication and
// interrupted-run repair treat these blobs as trustworthy.
err = s.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
err := s.repos.Blobs.UpdateUploaded(ctx, tx, b.ID)
if err != nil {
return fmt.Errorf("marking blob uploaded: %w", err)
}
return s.repos.Snapshots.AddBlob(ctx, tx, s.snapshotID, blobID,
types.BlobHash(b.Hash))
})
@@ -1660,6 +1725,20 @@ type streamingChunkInfo struct {
size int64
}
// packerError marks an error that came from adding a chunk to the packer
// (packing, database, encryption, or upload). Such an error means the chunk's
// data may not have been stored, so the run must abort even under --skip-errors:
// skipping the file would leave the chunk recorded as backed up while it lives
// in no blob, and a later snapshot could record a file that cannot be restored.
// Only open and read errors are safe to skip.
type packerError struct {
err error
}
func (e *packerError) Error() string { return e.err.Error() }
func (e *packerError) Unwrap() error { return e.err }
// processFileStreaming processes a file by streaming chunks directly to the packer
func (s *Scanner) processFileStreaming(
ctx context.Context, fileToProcess *FileToProcess, result *ScanResult,
@@ -1710,7 +1789,11 @@ func (s *Scanner) processFileStreaming(
if !chunkExists {
err := s.addChunkToPacker(ctx, chunk)
if err != nil {
return err
// Mark as a packer error so --skip-errors cannot swallow it:
// the chunk was registered as pending before packing, so a
// skipped file here would be recorded as backed up while its
// data was never stored.
return &packerError{err: err}
}
}
internal/snapshot/skip_errors_test.go
+216
View File
@@ -0,0 +1,216 @@
package snapshot_test
import (
"context"
"errors"
"os"
"path/filepath"
"strings"
"sync"
"testing"
"time"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// errSimTempFail is the one-time temp-file creation failure blobTempFailFs
// injects, mirroring a full temp filesystem.
var errSimTempFail = errors.New("simulated temp-file creation failure")
// errSimRead is the read failure readFailFile injects for a file that opens
// but cannot be read.
var errSimRead = errors.New("simulated read failure")
// blobTempFailFs fails the first temp-file creation for a packer blob, then
// behaves normally, simulating a one-time failure to start a new blob.
type blobTempFailFs struct {
afero.Fs
mu sync.Mutex
failed bool
}
//nolint:ireturn // afero.Fs.OpenFile is defined to return the interface.
func (f *blobTempFailFs) OpenFile(
name string, flag int, perm os.FileMode,
) (afero.File, error) {
if strings.Contains(name, "vaultik-blob-") {
f.mu.Lock()
firstTime := !f.failed
f.failed = true
f.mu.Unlock()
if firstTime {
return nil, errSimTempFail
}
}
return f.Fs.OpenFile(name, flag, perm)
}
// readFailFile wraps an afero.File whose Read always fails.
type readFailFile struct {
afero.File
}
func (readFailFile) Read([]byte) (int, error) {
return 0, errSimRead
}
// readFailFs fails reads of one target path after a successful open.
type readFailFs struct {
afero.Fs
target string
}
//nolint:ireturn // afero.Fs.Open is defined to return the interface.
func (f *readFailFs) Open(name string) (afero.File, error) {
file, err := f.Fs.Open(name)
if err != nil {
return nil, err
}
if name == f.target {
return readFailFile{File: file}, nil
}
return file, nil
}
// writeSkipErrorTestFile writes one file into fs with a fixed mtime.
func writeSkipErrorTestFile(t *testing.T, fs afero.Fs, path, content string) {
t.Helper()
err := fs.MkdirAll(filepath.Dir(path), 0755)
if err != nil {
t.Fatalf("mkdir: %v", err)
}
err = afero.WriteFile(fs, path, []byte(content), 0644)
if err != nil {
t.Fatalf("write %s: %v", path, err)
}
when := time.Date(2024, 1, 1, 12, 0, 0, 0, time.UTC)
err = fs.Chtimes(path, when, when)
if err != nil {
t.Fatalf("chtimes %s: %v", path, err)
}
}
// runSkipErrorScan scans /source on fs with the given skip-errors setting and
// returns the repositories (for inspection) and the scan error.
func runSkipErrorScan(
t *testing.T, fs afero.Fs, skipErrors bool,
) (*database.Repositories, error) {
t.Helper()
db, err := database.NewTestDB()
if err != nil {
t.Fatalf("create test db: %v", err)
}
t.Cleanup(func() {
cerr := db.Close()
if cerr != nil {
t.Errorf("close db: %v", cerr)
}
})
repos := database.NewRepositories(db)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
ChunkSize: int64(1024 * 16),
Repositories: repos,
MaxBlobSize: int64(1024 * 1024),
CompressionLevel: 3,
AgeRecipients: []string{testAgePublicKey},
SkipErrors: skipErrors,
})
ctx := context.Background()
snapshotID := "test-snapshot-skip-errors"
createTestSnapshotRecord(ctx, t, repos, snapshotID)
_, err = scanner.Scan(ctx, "/source", snapshotID)
return repos, err
}
// TestScannerPackingFailureAbortsUnderSkipErrors checks that a failure to start
// a new blob aborts the run even with --skip-errors. Otherwise the file would
// be skipped while its chunk had already been registered as pending, letting a
// later blob record that chunk in the chunks table with no blob to back it —
// a snapshot that completes with a file that cannot be restored.
func TestScannerPackingFailureAbortsUnderSkipErrors(t *testing.T) {
t.Parallel()
// Two files with distinct content so each yields a distinct chunk: the
// first fails to start a blob, and without the fix the second's blob would
// commit the first's orphaned chunk row.
fs := &blobTempFailFs{Fs: afero.NewMemMapFs()}
writeSkipErrorTestFile(t, fs, "/source/file1.txt", "first file content")
writeSkipErrorTestFile(t, fs, "/source/file2.txt", "second file content")
repos, err := runSkipErrorScan(t, fs, true)
if err == nil {
t.Fatal("expected scan to abort on the packer error, got nil")
}
// ListUnpacked returns chunks recorded with no blob_chunks row: exactly the
// unrestorable state this fix prevents.
unpacked, err := repos.Chunks.ListUnpacked(context.Background(), 10)
if err != nil {
t.Fatalf("listing unpacked chunks: %v", err)
}
if len(unpacked) != 0 {
t.Fatalf("expected no chunk recorded without a blob, got %d", len(unpacked))
}
}
// TestScannerReadErrorAbortsWithoutSkipErrors checks that a file read error
// aborts the run when --skip-errors is not set.
func TestScannerReadErrorAbortsWithoutSkipErrors(t *testing.T) {
t.Parallel()
const target = "/source/unreadable.txt"
fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target}
writeSkipErrorTestFile(t, fs, target, "content that cannot be read")
_, err := runSkipErrorScan(t, fs, false)
if err == nil {
t.Fatal("expected scan to fail on the read error, got nil")
}
}
// TestScannerReadErrorSkippedWithSkipErrors checks that a file read error is
// skipped and the run completes when --skip-errors is set.
func TestScannerReadErrorSkippedWithSkipErrors(t *testing.T) {
t.Parallel()
const target = "/source/unreadable.txt"
fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target}
writeSkipErrorTestFile(t, fs, target, "content that cannot be read")
repos, err := runSkipErrorScan(t, fs, true)
if err != nil {
t.Fatalf("expected scan to complete with --skip-errors, got %v", err)
}
chunks, err := repos.FileChunks.GetByFile(context.Background(), target)
if err != nil {
t.Fatalf("getting file chunks: %v", err)
}
if len(chunks) != 0 {
t.Fatalf("expected unreadable file skipped, got %d chunks", len(chunks))
}
}
internal/snapshot/snapshot.go
+42 -122
View File
@@ -24,7 +24,7 @@ package snapshot
// 7. Close the temporary database
// 8. VACUUM the database to remove deleted data and compact (security critical)
// 9. Compress the binary database with zstd
// 10. Encrypt the compressed database with age (if encryption is enabled)
// 10. Encrypt the compressed database with age (always; recipients are required)
// 11. Upload to S3 as: metadata/{snapshot-id}/db.zst.age
// 12. Reopen the main database
//
@@ -44,6 +44,7 @@ import (
"errors"
"fmt"
"io"
"os"
"path/filepath"
"strings"
"time"
@@ -237,14 +238,12 @@ func (sm *SnapshotManager) CompleteSnapshot(
// 3. Cleans the copy to contain only current snapshot data
// 4. Dumps the cleaned database to SQL
// 5. Compresses the SQL dump with zstd
// 6. Encrypts the compressed data (if encryption is enabled)
// 6. Encrypts the compressed data with age (always; recipients are required)
// 7. Uploads to S3 at: snapshots/{snapshot-id}.sql.zst[.age]
//
// The caller is responsible for:
// - Ensuring the main database is closed before calling this method
// - Reopening the main database after this method returns
//
// This ensures database consistency during the copy operation.
// The only caller (finalizeSnapshotMetadata) does not close the main database
// before calling this method: the index is copied at dbPath while it is still
// open, and every step here operates on that copy, never on the live index.
func (sm *SnapshotManager) ExportSnapshotMetadata(
ctx context.Context, dbPath string, snapshotID string,
) error {
@@ -294,68 +293,6 @@ func (sm *SnapshotManager) ExportSnapshotMetadata(
return nil
}
// CleanupIncompleteSnapshots removes incomplete snapshots that don't have
// metadata in S3. This is critical for data safety: incomplete snapshots
// can cause deduplication to skip files that were never successfully
// backed up, resulting in data loss.
func (sm *SnapshotManager) CleanupIncompleteSnapshots(
ctx context.Context, hostname string,
) error {
log.Info("Checking for incomplete snapshots", "hostname", hostname)
// Get all incomplete snapshots for this hostname
incompleteSnapshots, err := sm.repos.Snapshots.GetIncompleteByHostname(ctx, hostname)
if err != nil {
return fmt.Errorf("getting incomplete snapshots: %w", err)
}
if len(incompleteSnapshots) == 0 {
log.Debug("No incomplete snapshots found")
return nil
}
log.Info("Found incomplete snapshots", "count", len(incompleteSnapshots))
// Check each incomplete snapshot for metadata in storage
for _, snapshot := range incompleteSnapshots {
// Check if metadata exists in storage (paths use the hashed
// remote key so we don't leak host info to the listing).
metadataKey := fmt.Sprintf("metadata/%s/db.zst",
RemoteSnapshotKey(snapshot.ID.String()))
_, err := sm.storage.Stat(ctx, metadataKey)
if err != nil {
// Metadata doesn't exist in S3 - this is an incomplete snapshot
log.Info("Cleaning up incomplete snapshot record",
"snapshot_id", snapshot.ID, "started_at", snapshot.StartedAt)
// Delete the snapshot and all its associations
err := sm.deleteSnapshot(ctx, snapshot.ID.String())
if err != nil {
return fmt.Errorf("deleting incomplete snapshot %s: %w",
snapshot.ID, err)
}
log.Info("Deleted incomplete snapshot record and associated data",
"snapshot_id", snapshot.ID)
} else {
// Metadata exists - this snapshot was completed but database wasn't updated
// This shouldn't happen in normal operation, but mark it complete
log.Warn("Found snapshot with remote metadata but incomplete in database",
"snapshot_id", snapshot.ID)
err := sm.repos.Snapshots.MarkComplete(ctx, nil, snapshot.ID.String())
if err != nil {
log.Error("Failed to mark snapshot as complete in database",
"snapshot_id", snapshot.ID, "error", err)
}
}
}
return nil
}
// CleanupOrphanedData removes files, chunks, and blobs that are no longer
// referenced by any snapshot. This should be called periodically to clean
// up data from deleted or incomplete snapshots.
@@ -476,9 +413,11 @@ func (sm *SnapshotManager) prepareExportDB(
// uploadSnapshotArtifacts uploads the database backup and blob manifest
// to remote storage at metadata/<remote-key>/, where remote-key is the
// double-SHA256 derivation of the snapshot ID (see RemoteSnapshotKey).
// We never write the human-readable snapshot ID into any unencrypted
// part of remote storage so a listing of the destination bucket leaks
// no host, configuration, or scheduling information.
// The human-readable snapshot ID is never written into an unencrypted part
// of remote storage, so a plain listing shows only the hashed key, not the
// hostname or snapshot name. The hash uses no secret, so a guessed hostname
// and snapshot name can still be confirmed against a listing, and the backup
// time is public: the manifest carries a plaintext timestamp.
func (sm *SnapshotManager) uploadSnapshotArtifacts(
ctx context.Context, snapshotID string, dbData, manifestData []byte,
) error {
@@ -758,12 +697,18 @@ func (sm *SnapshotManager) compressFile(inputPath, outputPath string) error {
writerClosed = true
log.Debug("Compression complete", "hash", hex.EncodeToString(writer.Sum256()))
log.Debug("Compression complete", "hash", hex.EncodeToString(writer.ContentID()))
return nil
}
// copyFile copies a file from src to dst
// exportCopyPerm restricts the exported snapshot database copy to the owning
// user; it holds the same private index data as the local index file.
const exportCopyPerm = 0o600
// copyFile copies a file from src to dst. The destination is the exported
// snapshot database, so it is created owner-only rather than with the
// umask-dependent default.
func (sm *SnapshotManager) copyFile(src, dst string) error {
log.Debug("Opening source file for copy", "path", src)
@@ -783,7 +728,9 @@ func (sm *SnapshotManager) copyFile(src, dst string) error {
log.Debug("Creating destination file", "path", dst)
destFile, err := sm.fs.Create(dst)
destFile, err := sm.fs.OpenFile(
dst, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, exportCopyPerm,
)
if err != nil {
return err
}
@@ -809,6 +756,11 @@ func (sm *SnapshotManager) copyFile(src, dst string) error {
return nil
}
// errBlobMissingFromDatabase means a snapshot references a blob that is
// absent from the blobs table, so a complete manifest cannot be built.
var errBlobMissingFromDatabase = errors.New(
"blob referenced by snapshot is not in the database")
// generateBlobManifest creates a compressed JSON list of all blobs in the snapshot
func (sm *SnapshotManager) generateBlobManifest(
ctx context.Context, dbPath string, snapshotID string,
@@ -839,27 +791,34 @@ func (sm *SnapshotManager) generateBlobManifest(
totalCompressedSize := int64(0)
for _, hash := range blobHashes {
// Every blob the snapshot references must appear in the manifest.
// Prune consults only the manifest to decide what is still in use,
// so silently dropping a blob here would let a later prune delete
// it while this snapshot still needs it. A lookup failure or a
// missing blob row therefore fails manifest generation.
blob, err := repos.Blobs.GetByHash(ctx, hash)
if err != nil {
log.Warn("Failed to get blob details", "hash", hash, "error", err)
return nil, fmt.Errorf("getting blob details for %s: %w", hash, err)
}
continue
if blob == nil {
return nil, fmt.Errorf("%w: blob %s, snapshot %s",
errBlobMissingFromDatabase, hash, snapshotID)
}
if blob != nil {
blobs = append(blobs, BlobInfo{
Hash: hash,
CompressedSize: blob.CompressedSize,
})
totalCompressedSize += blob.CompressedSize
}
}
// Create manifest. SnapshotID in the unencrypted manifest is the
// double-SHA256 remote key (see RemoteSnapshotKey), not the human ID,
// so neither this field nor the directory name reveals the hostname or
// snapshot name. Timestamp below is written in the clear, so the backup
// time is observable to anyone who can read the manifest.
// double-SHA256 remote key (see RemoteSnapshotKey), not the human ID, so
// neither this field nor the directory name spells out the hostname or
// snapshot name — but the key uses no secret, so a guessed hostname and
// snapshot name can be confirmed. Timestamp below is written in the clear,
// so the backup time is observable to anyone who can read the manifest.
manifest := &Manifest{
SnapshotID: RemoteSnapshotKey(snapshotID),
Timestamp: time.Now().UTC().Format(time.RFC3339),
@@ -913,45 +872,6 @@ type ExtendedBackupStats struct {
UploadDurationMs int64 // Total milliseconds spent uploading to S3
}
// deleteSnapshot removes a snapshot and all its associations from the database
func (sm *SnapshotManager) deleteSnapshot(
ctx context.Context, snapshotID string,
) error {
// Delete snapshot_files entries
err := sm.repos.Snapshots.DeleteSnapshotFiles(ctx, snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot files: %w", err)
}
// Delete snapshot_blobs entries
err = sm.repos.Snapshots.DeleteSnapshotBlobs(ctx, snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot blobs: %w", err)
}
// Delete uploads entries (has foreign key to snapshots without CASCADE)
err = sm.repos.Snapshots.DeleteSnapshotUploads(ctx, snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot uploads: %w", err)
}
// Delete the snapshot itself
err = sm.repos.Snapshots.Delete(ctx, snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot: %w", err)
}
// Clean up orphaned data
log.Debug("Cleaning up orphaned records in main database")
err = sm.CleanupOrphanedData(ctx)
if err != nil {
return fmt.Errorf("cleaning up orphaned data: %w", err)
}
return nil
}
// deleteOtherSnapshots deletes all snapshots except the current one
func (sm *SnapshotManager) deleteOtherSnapshots(
ctx context.Context, tx *sql.Tx, currentSnapshotID string,
internal/storage/conformance_test.go
+198
View File
@@ -0,0 +1,198 @@
package storage_test
import (
"bytes"
"context"
"errors"
"io"
"reflect"
"sort"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// runStorerConformance is the shared Storer contract. Every backend that
// can run in-process is expected to pass it: TestFileStorer runs it against
// file://, TestS3Storer against s3://. A new backend inherits this coverage
// by passing its own constructor, so the contract is defined once.
//
// It exercises the public Storer interface: round-trip, stat, list with
// prefix filtering, overwrite, delete, delete-of-missing, and not-found on
// Get and Stat. Each section takes its own fresh backend instance, so the
// order of sections never matters and no section sees another's objects.
func runStorerConformance(t *testing.T, newStorer func(*testing.T) storage.Storer) {
t.Helper()
conformanceRoundTrip(t, newStorer(t))
conformanceOverwrite(t, newStorer(t))
conformanceList(t, newStorer(t))
conformanceDelete(t, newStorer(t))
conformanceNotFound(t, newStorer(t))
}
// conformanceRoundTrip stores a nested key, then reads it back and stats it.
func conformanceRoundTrip(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "blobs/aa/bb/object.bin"
want := []byte("round-trip payload")
err := s.Put(ctx, key, bytes.NewReader(want))
if err != nil {
t.Fatalf("Put: %v", err)
}
got := getBytes(t, s, key)
if !bytes.Equal(got, want) {
t.Errorf("Get returned %q, want %q", got, want)
}
info, err := s.Stat(ctx, key)
if err != nil {
t.Fatalf("Stat: %v", err)
}
if info.Key != key {
t.Errorf("Stat key = %q, want %q", info.Key, key)
}
if info.Size != int64(len(want)) {
t.Errorf("Stat size = %d, want %d", info.Size, len(want))
}
}
// conformanceOverwrite checks that a second Put replaces the first.
func conformanceOverwrite(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "meta/snapshot.json"
err := s.Put(ctx, key, bytes.NewReader([]byte("first")))
if err != nil {
t.Fatalf("first Put: %v", err)
}
want := []byte("second and longer payload")
err = s.Put(ctx, key, bytes.NewReader(want))
if err != nil {
t.Fatalf("second Put: %v", err)
}
got := getBytes(t, s, key)
if !bytes.Equal(got, want) {
t.Errorf("after overwrite Get returned %q, want %q", got, want)
}
}
// conformanceList checks prefix filtering and the empty result for a
// prefix that matches nothing.
func conformanceList(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
keys := []string{"blobs/aa/one", "blobs/bb/two", "meta/three"}
for _, k := range keys {
err := s.Put(ctx, k, bytes.NewReader([]byte("data")))
if err != nil {
t.Fatalf("Put %q: %v", k, err)
}
}
if got := listSorted(t, s, ""); !reflect.DeepEqual(got, keys) {
t.Errorf("List(\"\") = %v, want %v", got, keys)
}
wantBlobs := []string{"blobs/aa/one", "blobs/bb/two"}
if got := listSorted(t, s, "blobs/"); !reflect.DeepEqual(got, wantBlobs) {
t.Errorf("List(\"blobs/\") = %v, want %v", got, wantBlobs)
}
if got := listSorted(t, s, "absent/"); len(got) != 0 {
t.Errorf("List(\"absent/\") = %v, want empty", got)
}
}
// conformanceDelete checks that Delete removes an object and that deleting
// a missing key is not an error.
func conformanceDelete(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "blobs/cc/gone.bin"
err := s.Put(ctx, key, bytes.NewReader([]byte("temporary")))
if err != nil {
t.Fatalf("Put: %v", err)
}
err = s.Delete(ctx, key)
if err != nil {
t.Fatalf("Delete: %v", err)
}
_, err = s.Get(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get after Delete error = %v, want ErrNotFound", err)
}
err = s.Delete(ctx, key)
if err != nil {
t.Errorf("Delete of missing key = %v, want nil", err)
}
}
// conformanceNotFound checks Get and Stat on an absent key.
func conformanceNotFound(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
key := "never/written"
_, err := s.Get(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get error = %v, want ErrNotFound", err)
}
_, err = s.Stat(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Stat error = %v, want ErrNotFound", err)
}
}
// getBytes reads a key fully and closes the reader.
func getBytes(t *testing.T, s storage.Storer, key string) []byte {
t.Helper()
rc, err := s.Get(context.Background(), key)
if err != nil {
t.Fatalf("Get %q: %v", key, err)
}
defer func() { _ = rc.Close() }()
data, err := io.ReadAll(rc)
if err != nil {
t.Fatalf("read %q: %v", key, err)
}
return data
}
// listSorted returns the keys under a prefix in a stable order.
func listSorted(t *testing.T, s storage.Storer, prefix string) []string {
t.Helper()
keys, err := s.List(context.Background(), prefix)
if err != nil {
t.Fatalf("List %q: %v", prefix, err)
}
sort.Strings(keys)
return keys
}
internal/storage/faultstore/faultstore.go
+209
View File
@@ -0,0 +1,209 @@
// Package faultstore provides a storage.Storer wrapper that injects
// faults on demand, so tests can reproduce the failure modes a real
// backend exhibits: an upload that fails partway, a backend that reports
// success while storing nothing, and reads that return corrupt or
// truncated bytes. It is the seam called for by the fault-injection
// tests (sneak/vaultik issue 72) and is meant to be reused by future
// tests rather than re-implemented per case.
//
// The wrapper delegates every method to the inner Storer. Two hooks
// change that: OnPut decides the fate of each write, and OnGet decides
// how each read's bytes are returned. Both are keyed by the object key,
// so a test can fault only blobs, only metadata, or a single object.
package faultstore
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"sneak.berlin/go/vaultik/internal/storage"
)
// ErrInjectedUpload is returned by a Put the OnPut hook chose to fail.
var ErrInjectedUpload = errors.New("faultstore: injected upload failure")
// PutAction is the disposition OnPut assigns to a write.
type PutAction int
const (
// PutNormal writes through to the inner Storer.
PutNormal PutAction = iota
// PutFail reads part of the stream, then fails without storing the
// object — a network upload that dies partway through.
PutFail
// PutSwallow reports success but stores nothing — a backend that
// lies about durability.
PutSwallow
)
// GetFault is how OnGet chooses to damage a read.
type GetFault int
const (
// GetNormal returns the stored bytes unchanged.
GetNormal GetFault = iota
// GetCorrupt flips a byte so the returned object no longer matches
// what was stored.
GetCorrupt
// GetTruncate returns a short read: the object's bytes cut off
// before the end.
GetTruncate
)
// Storer wraps an inner storage.Storer with fault-injection hooks. A
// zero-valued hook means "no fault": construct with New and set only the
// hook a test needs.
type Storer struct {
inner storage.Storer
// OnPut, when set, is consulted before every Put and
// PutWithProgress with the object key.
OnPut func(key string) PutAction
// OnGet, when set, is consulted for every Get with the object key
// and damages the returned bytes accordingly.
OnGet func(key string) GetFault
}
// New wraps inner. inner must be non-nil.
func New(inner storage.Storer) *Storer {
return &Storer{inner: inner}
}
// midStreamBytes is how far a PutFail reads before failing, enough to be
// past the start of any real blob without depending on the blob's size.
const midStreamBytes = 512
// Put stores data unless OnPut faults the write.
func (f *Storer) Put(ctx context.Context, key string, data io.Reader) error {
handled, err := f.injectPut(key, data)
if handled {
return err
}
return f.inner.Put(ctx, key, data)
}
// PutWithProgress stores data unless OnPut faults the write.
func (f *Storer) PutWithProgress(
ctx context.Context, key string, data io.Reader,
size int64, progress storage.ProgressCallback,
) error {
handled, err := f.injectPut(key, data)
if handled {
return err
}
return f.inner.PutWithProgress(ctx, key, data, size, progress)
}
// Get retrieves data, damaging it if OnGet faults the read.
func (f *Storer) Get(ctx context.Context, key string) (io.ReadCloser, error) {
rc, err := f.inner.Get(ctx, key)
if err != nil {
return nil, err
}
fault := GetNormal
if f.OnGet != nil {
fault = f.OnGet(key)
}
if fault == GetNormal {
return rc, nil
}
data, err := io.ReadAll(rc)
_ = rc.Close()
if err != nil {
return nil, err
}
return io.NopCloser(bytes.NewReader(damage(fault, data))), nil
}
// damage returns a faulted copy of the stored bytes. GetCorrupt flips a
// byte in the middle so decryption authentication fails; GetTruncate
// drops the final byte so the read ends short. Both are no-ops on empty
// input, which cannot be damaged into something distinguishable.
func damage(fault GetFault, data []byte) []byte {
out := make([]byte, len(data))
copy(out, data)
if len(out) == 0 {
return out
}
switch fault {
case GetCorrupt:
out[len(out)/2] ^= 0xff
case GetTruncate:
out = out[:len(out)-1]
case GetNormal:
}
return out
}
// Stat delegates unchanged.
func (f *Storer) Stat(ctx context.Context, key string) (*storage.ObjectInfo, error) {
return f.inner.Stat(ctx, key)
}
// Delete delegates unchanged.
func (f *Storer) Delete(ctx context.Context, key string) error {
return f.inner.Delete(ctx, key)
}
// List delegates unchanged.
func (f *Storer) List(ctx context.Context, prefix string) ([]string, error) {
return f.inner.List(ctx, prefix)
}
// ListStream delegates unchanged.
func (f *Storer) ListStream(
ctx context.Context, prefix string,
) <-chan storage.ObjectInfo {
return f.inner.ListStream(ctx, prefix)
}
// Info delegates unchanged.
func (f *Storer) Info() storage.Info {
return f.inner.Info()
}
func (f *Storer) putAction(key string) PutAction {
if f.OnPut == nil {
return PutNormal
}
return f.OnPut(key)
}
// injectPut handles the non-normal write dispositions. It reports
// whether it handled the write and, if so, with what error.
func (f *Storer) injectPut(key string, data io.Reader) (bool, error) {
switch f.putAction(key) {
case PutFail:
// Consume part of the stream so the failure lands mid-transfer,
// the way a dropped connection would, then error without
// storing anything.
_, _ = io.CopyN(io.Discard, data, midStreamBytes)
return true, fmt.Errorf("%w for %q", ErrInjectedUpload, key)
case PutSwallow:
// A lying backend still drains the request body, then keeps
// nothing.
_, _ = io.Copy(io.Discard, data)
return true, nil
case PutNormal:
return false, nil
default:
return false, nil
}
}
internal/storage/file.go
+79 -54
View File
@@ -46,31 +46,18 @@ func (f *FileStorer) SetFilesystem(fs afero.Fs) {
// storage base path.
const storageDirPerm = 0o755
// tempSuffix marks a partially written object. writeAtomic streams into a
// temp file carrying this suffix and only renames it onto the real key once
// the whole object is on disk, so an interrupted write can never leave a
// truncated object at the key a later run would Stat and trust as a complete
// blob. List and ListStream skip these files, so a leftover from an
// interrupted write is never listed or trusted as a blob; it is otherwise
// harmless and is overwritten when the same key is written again.
const tempSuffix = ".partial"
// Put stores data at the specified key.
func (f *FileStorer) Put(_ context.Context, key string, data io.Reader) error {
path := f.fullPath(key)
// Create parent directories
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
file, err := f.fs.Create(path)
if err != nil {
return fmt.Errorf("creating file: %w", err)
}
defer func() { _ = file.Close() }()
_, err = io.Copy(file, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
return nil
return f.writeAtomic(key, data, nil)
}
// PutWithProgress stores data with progress reporting.
@@ -78,35 +65,7 @@ func (f *FileStorer) PutWithProgress(
_ context.Context, key string, data io.Reader,
_ int64, progress ProgressCallback,
) error {
path := f.fullPath(key)
// Create parent directories
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
file, err := f.fs.Create(path)
if err != nil {
return fmt.Errorf("creating file: %w", err)
}
defer func() { _ = file.Close() }()
// Wrap with progress tracking
pw := &progressWriter{
writer: file,
callback: progress,
}
_, err = io.Copy(pw, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
return nil
return f.writeAtomic(key, data, progress)
}
// Get retrieves data from the specified key.
@@ -188,7 +147,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
default:
}
if !info.IsDir() {
if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
// Convert back to key (relative path from basePath)
relPath, err := filepath.Rel(f.basePath, path)
if err != nil {
@@ -245,7 +204,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return nil //nolint:nilerr // continue walking despite errors
}
if !info.IsDir() {
if !info.IsDir() && !strings.HasSuffix(info.Name(), tempSuffix) {
relPath, err := filepath.Rel(f.basePath, path)
if err != nil {
ch <- ObjectInfo{Err: fmt.Errorf("computing relative path: %w", err)}
@@ -275,6 +234,72 @@ func (f *FileStorer) Info() Info {
}
}
// writeAtomic streams data into a temp file in the destination directory,
// fsyncs it, and renames it onto the final key. The key therefore appears
// only once the whole object has been durably written; a failure part-way
// leaves a temp file (removed here on the failing path) rather than a
// truncated object at the key.
func (f *FileStorer) writeAtomic(
key string, data io.Reader, progress ProgressCallback,
) error {
path := f.fullPath(key)
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
tmp, err := afero.TempFile(f.fs, dir, filepath.Base(path)+"-*"+tempSuffix)
if err != nil {
return fmt.Errorf("creating temp file: %w", err)
}
tmpPath := tmp.Name()
// Remove the temp file unless the rename below claims it. On the success
// path renamed is true, so the deferred Close and Remove are harmless
// no-ops on a name that no longer exists.
renamed := false
defer func() {
_ = tmp.Close()
if !renamed {
_ = f.fs.Remove(tmpPath)
}
}()
var w io.Writer = tmp
if progress != nil {
w = &progressWriter{writer: tmp, callback: progress}
}
_, err = io.Copy(w, data)
if err != nil {
return fmt.Errorf("writing file: %w", err)
}
err = tmp.Sync()
if err != nil {
return fmt.Errorf("syncing temp file: %w", err)
}
err = tmp.Close()
if err != nil {
return fmt.Errorf("closing temp file: %w", err)
}
err = f.fs.Rename(tmpPath, path)
if err != nil {
return fmt.Errorf("renaming temp file: %w", err)
}
renamed = true
return nil
}
// fullPath returns the full filesystem path for a key.
func (f *FileStorer) fullPath(key string) string {
return filepath.Join(f.basePath, key)
internal/storage/file_atomic_test.go
+119
View File
@@ -0,0 +1,119 @@
package storage_test
import (
"context"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// errStreamInterrupted stands in for an upload cut off mid-stream.
var errStreamInterrupted = errors.New("connection reset mid-upload")
// failingReader yields its data once, then fails.
type failingReader struct {
data []byte
done bool
}
func (r *failingReader) Read(p []byte) (int, error) {
if r.done {
return 0, errStreamInterrupted
}
n := copy(p, r.data)
r.done = true
return n, nil
}
// TestFileStorer_InterruptedWriteLeavesNoTrustedObject checks that a write
// cut off mid-stream leaves nothing at the destination key, so a later run
// cannot Stat a truncated object and trust it as a complete blob.
func TestFileStorer_InterruptedWriteLeavesNoTrustedObject(t *testing.T) {
t.Parallel()
f, err := storage.NewFileStorer(t.TempDir())
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
ctx := context.Background()
key := "blobs/aa/bb/aabbccddeeff"
err = f.PutWithProgress(ctx, key, &failingReader{data: []byte("partial")}, 4096, nil)
if err == nil {
t.Fatal("expected the interrupted write to fail, got nil")
}
_, err = f.Stat(ctx, key)
if !errors.Is(err, storage.ErrNotFound) {
t.Fatalf("expected key absent after interrupted write, got Stat err %v", err)
}
keys, err := f.List(ctx, "blobs/")
if err != nil {
t.Fatalf("List: %v", err)
}
if len(keys) != 0 {
t.Fatalf("expected no keys listed after interrupted write, got %v", keys)
}
}
// TestFileStorer_ListSkipsPartialFiles checks that a leftover temp file (the
// storage layer names them with a ".partial" suffix) is never surfaced as a
// key by List or ListStream.
func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
t.Parallel()
base := t.TempDir()
f, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
ctx := context.Background()
realKey := "blobs/aa/bb/aabbccddeeff"
err = f.Put(ctx, realKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
// A stray temp file, as an interrupted write would leave behind.
leftover := filepath.Join(base, "blobs/aa/bb/aabbccddeeff-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
keys, err := f.List(ctx, "blobs/")
if err != nil {
t.Fatalf("List: %v", err)
}
if len(keys) != 1 || keys[0] != realKey {
t.Fatalf("List should return only the real key, got %v", keys)
}
var streamed []string
for obj := range f.ListStream(ctx, "blobs/") {
if obj.Err != nil {
t.Fatalf("ListStream: %v", obj.Err)
}
streamed = append(streamed, obj.Key)
}
if len(streamed) != 1 || streamed[0] != realKey {
t.Fatalf("ListStream should return only the real key, got %v", streamed)
}
}
internal/storage/file_backend_test.go
+27
View File
@@ -0,0 +1,27 @@
package storage_test
import (
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// newFileStorer builds a file:// backend rooted at a fresh temp directory.
//
//nolint:ireturn // conformance runs against the Storer interface by design
func newFileStorer(t *testing.T) storage.Storer {
t.Helper()
s, err := storage.NewFileStorer(t.TempDir())
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
return s
}
// TestFileStorer runs the shared Storer contract against the file:// backend.
func TestFileStorer(t *testing.T) {
t.Parallel()
runStorerConformance(t, newFileStorer)
}
internal/storage/module.go
+3 -2
View File
@@ -111,10 +111,11 @@ func storerFromParsedS3URL(parsed *URL, cfg *config.Config) (Storer, error) {
func storerFromLegacyS3Config(cfg *config.Config) (Storer, error) {
endpoint := cfg.S3.Endpoint
// Ensure protocol is present
// Ensure protocol is present. Absent an explicit use_ssl, default to TLS;
// plain HTTP only when use_ssl is written as false.
if !strings.HasPrefix(endpoint, "http://") &&
!strings.HasPrefix(endpoint, "https://") {
if cfg.S3.UseSSL {
if cfg.S3.UseSSL == nil || *cfg.S3.UseSSL {
endpoint = "https://" + endpoint
} else {
endpoint = "http://" + endpoint
internal/storage/module_test.go
+61
View File
@@ -0,0 +1,61 @@
package storage_test
import (
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/storage"
)
// legacyS3Config returns a minimal s3.* (no storage_url) configuration with a
// scheme-less endpoint. useSSL mirrors the config file: nil means the key is
// omitted, a pointer means it was written explicitly.
func legacyS3Config(useSSL *bool) *config.Config {
return &config.Config{
S3: config.S3Config{
Endpoint: "s3.example.com",
Bucket: "bucket",
AccessKeyID: "key",
SecretAccessKey: "secret",
Region: "us-east-1",
UseSSL: useSSL,
},
}
}
// endpointScheme builds the storer from cfg and returns the scheme its
// resolved endpoint carries (Info().Location is "endpoint/bucket").
func endpointScheme(t *testing.T, cfg *config.Config) string {
t.Helper()
storer, err := storage.NewStorer(cfg)
if err != nil {
t.Fatalf("NewStorer: %v", err)
}
location := storer.Info().Location
switch {
case strings.HasPrefix(location, "https://"):
return "https"
case strings.HasPrefix(location, "http://"):
return "http"
default:
t.Fatalf("endpoint has no http(s) scheme: %q", location)
return ""
}
}
func TestLegacyS3SchemelessEndpointDefaultsToTLS(t *testing.T) {
t.Parallel()
if got := endpointScheme(t, legacyS3Config(nil)); got != "https" {
t.Errorf("use_ssl omitted: got %q scheme, want https", got)
}
no := false
if got := endpointScheme(t, legacyS3Config(&no)); got != "http" {
t.Errorf("use_ssl: false: got %q scheme, want http", got)
}
}
internal/storage/rclone_test.go
+58
View File
@@ -0,0 +1,58 @@
package storage_test
import (
"context"
"errors"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// The rclone backend is a thin adapter over the rclone library: it turns a
// (remote, path) pair into rclone's "remote:path" string, hands it to
// rclone, and maps rclone's own results back to the Storer interface. What
// can be tested in-process, without a configured remote or network, is that
// adapter layer — how the arguments are shaped and how construction errors
// are reported. The data-plane operations (Put/Get/List/Delete) are rclone's
// own, exercised against a real provider (drive, s3-via-rclone, ...), which
// needs a configured remote with credentials and network access and so is
// out of reach of a unit test. The shared Storer conformance suite therefore
// runs against the in-process file and s3 backends; the rclone backend
// inherits that contract once a remote is configured.
//
// These tests use rclone's ":local:" on-the-fly backend, which addresses the
// local filesystem directly without any configured remote, so construction
// runs entirely in-process.
// TestNewRcloneStorerConstruction checks that a valid remote constructs a
// backend and that Info() reports the shaped "remote:path" location.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestNewRcloneStorerConstruction(t *testing.T) {
dir := t.TempDir()
s, err := storage.NewRcloneStorer(context.Background(), ":local", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
// Info().Location is the "remote:path" string the adapter builds from
// its two arguments, so asserting it confirms the argument shaping.
want := ":local:" + dir
if got := s.Info().Location; got != want {
t.Errorf("Info().Location = %q, want %q", got, want)
}
}
// TestNewRcloneStorerUnknownRemote checks that a remote that is not in the
// rclone config fails construction with the ErrRemoteNotFound sentinel,
// rather than silently returning a backend pointed nowhere.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestNewRcloneStorerUnknownRemote(t *testing.T) {
_, err := storage.NewRcloneStorer(
context.Background(), "vaultik-no-such-remote", "path")
if !errors.Is(err, storage.ErrRemoteNotFound) {
t.Errorf("NewRcloneStorer error = %v, want ErrRemoteNotFound", err)
}
}
internal/storage/s3_test.go
+36 -14
View File
@@ -13,18 +13,23 @@ import (
"sneak.berlin/go/vaultik/internal/storage"
)
// TestS3StorerMissingKeyMapsToErrNotFound verifies that the s3 backend reports
// a missing object as storage.ErrNotFound, matching the file and rclone
// backends and the Storer contract. Without the mapping, Get and Stat leak the
// raw SDK error and errors.Is(err, storage.ErrNotFound) is false.
// s3TestBucket is the bucket created for each in-process S3 server.
const s3TestBucket = "test-bucket"
// newS3Storer builds an s3:// backend backed by a fresh in-process
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
// over httptest) that internal/s3 and the not-found regression test use,
// so no new mock or dependency is introduced. Each call gets its own
// server, bucket, and client, so the conformance suite's per-section
// instances stay isolated.
//
//nolint:paralleltest // shares an in-process S3 server via t.Cleanup
func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
const bucket = "test-bucket"
//nolint:ireturn // conformance runs against the Storer interface by design
func newS3Storer(t *testing.T) storage.Storer {
t.Helper()
backend := s3mem.New()
err := backend.CreateBucket(bucket)
err := backend.CreateBucket(s3TestBucket)
if err != nil {
t.Fatalf("create bucket: %v", err)
}
@@ -32,11 +37,9 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
srv := httptest.NewServer(gofakes3.New(backend).Server())
t.Cleanup(srv.Close)
ctx := context.Background()
client, err := s3.NewClient(ctx, s3.Config{
client, err := s3.NewClient(context.Background(), s3.Config{
Endpoint: srv.URL,
Bucket: bucket,
Bucket: s3TestBucket,
AccessKeyID: "test",
SecretAccessKey: "test",
Region: "us-east-1",
@@ -45,9 +48,28 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
t.Fatalf("new client: %v", err)
}
storer := storage.NewS3Storer(client)
return storage.NewS3Storer(client)
}
_, err = storer.Get(ctx, "does-not-exist")
// TestS3Storer runs the shared Storer contract against the s3:// backend,
// so it is held to the same round-trip, list, delete, and not-found
// behaviour as the file:// backend.
func TestS3Storer(t *testing.T) {
t.Parallel()
runStorerConformance(t, newS3Storer)
}
// TestS3StorerMissingKeyMapsToErrNotFound pins the specific contract that a
// missing object surfaces as storage.ErrNotFound rather than the raw AWS SDK
// error. Without the mapping, errors.Is(err, storage.ErrNotFound) is false on
// s3 and callers would branch differently per backend.
func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
t.Parallel()
storer := newS3Storer(t)
ctx := context.Background()
_, err := storer.Get(ctx, "does-not-exist")
if !errors.Is(err, storage.ErrNotFound) {
t.Errorf("Get on missing key: got %v, want ErrNotFound", err)
}
internal/storage/url.go
+70 -15
View File
@@ -4,6 +4,7 @@ import (
"errors"
"fmt"
"net/url"
"slices"
"strings"
)
@@ -23,6 +24,10 @@ var (
ErrUnsupportedScheme = errors.New(
"unsupported URL scheme: must start with s3://, file://, or rclone://")
ErrUnsupportedStorage = errors.New("unsupported storage scheme")
ErrURLCredentials = errors.New(
"storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead")
ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
)
// URL represents a parsed storage URL.
@@ -59,11 +64,28 @@ func ParseStorageURL(rawURL string) (*URL, error) {
}, nil
}
// Handle s3:// URLs
if strings.HasPrefix(rawURL, "s3://") {
return parseS3URL(rawURL)
}
if strings.HasPrefix(rawURL, "rclone://") {
return parseRcloneURL(rawURL)
}
return nil, ErrUnsupportedScheme
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo and any query parameter other than endpoint, region and
// ssl, so a credential-bearing URL is never stored or echoed.
func parseS3URL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL)
if err != nil {
return nil, fmt.Errorf("invalid URL: %w", err)
return nil, wrapParseError(err)
}
if u.User != nil {
return nil, ErrURLCredentials
}
bucket := u.Host
@@ -71,30 +93,34 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrMissingBucket
}
prefix := strings.TrimPrefix(u.Path, "/")
query := u.Query()
useSSL := true
if query.Get("ssl") == "false" {
useSSL = false
err = rejectUnknownParams(query, "endpoint", "region", "ssl")
if err != nil {
return nil, err
}
return &URL{
Scheme: schemeS3,
Bucket: bucket,
Prefix: prefix,
Prefix: strings.TrimPrefix(u.Path, "/"),
Endpoint: query.Get("endpoint"),
Region: query.Get("region"),
UseSSL: useSSL,
UseSSL: query.Get("ssl") != "false",
}, nil
}
// Handle rclone:// URLs
if strings.HasPrefix(rawURL, "rclone://") {
// parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
// query parameters, so credentials in the userinfo and any parameter at
// all are rejected rather than silently ignored.
func parseRcloneURL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL)
if err != nil {
return nil, fmt.Errorf("invalid URL: %w", err)
return nil, wrapParseError(err)
}
if u.User != nil {
return nil, ErrURLCredentials
}
remote := u.Host
@@ -102,16 +128,45 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrMissingRemote
}
path := strings.TrimPrefix(u.Path, "/")
err = rejectUnknownParams(u.Query())
if err != nil {
return nil, err
}
return &URL{
Scheme: schemeRclone,
Prefix: path,
Prefix: strings.TrimPrefix(u.Path, "/"),
RcloneRemote: remote,
}, nil
}
return nil, ErrUnsupportedScheme
// rejectUnknownParams returns an error naming the first query parameter
// not in allowed. The parameter's name is included (so a misspelt
// endpoint= is caught), but never its value, which could be a secret,
// and never the whole URL.
func rejectUnknownParams(query url.Values, allowed ...string) error {
for name := range query {
if !slices.Contains(allowed, name) {
return fmt.Errorf(
"%w: %q; put credentials in s3.access_key_id and "+
"s3.secret_access_key, not the URL",
ErrURLUnknownParam, name)
}
}
return nil
}
// wrapParseError wraps only the inner cause of a url.Parse failure. The
// *url.Error that url.Parse returns embeds the raw URL in its message, so
// wrapping it directly would echo a credential-bearing URL into logs.
func wrapParseError(err error) error {
var uerr *url.Error
if errors.As(err, &uerr) {
return fmt.Errorf("invalid URL: %w", uerr.Err)
}
return fmt.Errorf("invalid URL: %w", err)
}
// String returns a human-readable representation of the storage URL.
internal/storage/url_parse_test.go
+208
View File
@@ -0,0 +1,208 @@
package storage_test
import (
"errors"
"reflect"
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
)
// TestParseStorageURLValid checks that each supported scheme parses into
// the expected fields, since those fields decide which backend is built.
func TestParseStorageURLValid(t *testing.T) {
t.Parallel()
const bucket = "mybucket"
cases := []struct {
name string
raw string
want *storage.URL
}{
{
name: "file absolute path",
raw: "file:///var/backups/vaultik",
want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
},
{
name: "s3 bucket and prefix, ssl defaults on",
raw: "s3://mybucket/backups/host",
want: &storage.URL{
Scheme: "s3", Bucket: bucket,
Prefix: "backups/host", UseSSL: true,
},
},
{
name: "s3 bucket only",
raw: "s3://mybucket",
want: &storage.URL{Scheme: "s3", Bucket: bucket, UseSSL: true},
},
{
name: "s3 with endpoint, region, ssl off",
raw: "s3://mybucket?endpoint=minio.example.com&region=us-west-2&ssl=false",
want: &storage.URL{
Scheme: "s3", Bucket: bucket,
Endpoint: "minio.example.com", Region: "us-west-2", UseSSL: false,
},
},
{
name: "rclone remote and path",
raw: "rclone://gdrive/backups/host",
want: &storage.URL{
Scheme: "rclone", RcloneRemote: "gdrive", Prefix: "backups/host",
},
},
{
name: "rclone remote only",
raw: "rclone://gdrive",
want: &storage.URL{Scheme: "rclone", RcloneRemote: "gdrive"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
got, err := storage.ParseStorageURL(tc.raw)
if err != nil {
t.Fatalf("ParseStorageURL(%q) returned error: %v", tc.raw, err)
}
if !reflect.DeepEqual(got, tc.want) {
t.Errorf("ParseStorageURL(%q) = %+v, want %+v", tc.raw, got, tc.want)
}
})
}
}
// TestParseStorageURLErrors checks that empty, missing, and unknown-scheme
// inputs fail with the documented sentinel errors instead of parsing to a
// wrong destination.
func TestParseStorageURLErrors(t *testing.T) {
t.Parallel()
cases := []struct {
name string
raw string
wantErr error
}{
{"empty url", "", storage.ErrEmptyStorageURL},
{"file empty path", "file://", storage.ErrEmptyFilePath},
{"s3 missing bucket", "s3://", storage.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
{"rclone missing remote", "rclone://", storage.ErrMissingRemote},
{"unknown scheme", "gs://bucket/x", storage.ErrUnsupportedScheme},
{"no scheme", "/local/path", storage.ErrUnsupportedScheme},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, tc.wantErr) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, tc.wantErr)
}
})
}
}
// TestParseStorageURLRejectsCredentials checks that a URL carrying
// credentials in its userinfo or in an unknown query parameter is
// rejected, and that the error never echoes the secret-bearing URL back
// into logs or output.
func TestParseStorageURLRejectsCredentials(t *testing.T) {
t.Parallel()
// Split so the literals never form a "user:pass@" URL pattern that
// tooling would flag as a real hardcoded credential.
const (
key = "AKIAKEY"
secret = "topsecret"
)
cases := []struct {
name string
raw string
wantErr error
secrets []string // must not appear in the error message
}{
{
name: "s3 userinfo",
raw: "s3://" + key + ":" + secret + "@mybucket/prefix",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret, "mybucket"},
},
{
name: "s3 unknown query param",
raw: "s3://mybucket?access_key=" + key + "&secret=" + secret,
wantErr: storage.ErrURLUnknownParam,
secrets: []string{key, secret},
},
{
name: "s3 misspelt endpoint",
raw: "s3://mybucket?endpiont=minio.example.com",
wantErr: storage.ErrURLUnknownParam,
secrets: nil,
},
{
name: "rclone userinfo",
raw: "rclone://user:" + secret + "@gdrive/backups",
wantErr: storage.ErrURLCredentials,
secrets: []string{secret},
},
{
name: "rclone query param",
raw: "rclone://gdrive/backups?token=" + secret,
wantErr: storage.ErrURLUnknownParam,
secrets: []string{secret},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, tc.wantErr) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, tc.wantErr)
}
// The rejection must name the proper config keys so the
// operator knows where credentials belong.
for _, key := range []string{"s3.access_key_id", "s3.secret_access_key"} {
if !strings.Contains(err.Error(), key) {
t.Errorf("error %q does not name %q", err.Error(), key)
}
}
for _, secret := range tc.secrets {
if strings.Contains(err.Error(), secret) {
t.Errorf("error message leaked %q: %v", secret, err.Error())
}
}
})
}
}
// TestParseStorageURLParseFailureHidesURL checks that when url.Parse
// itself fails, the wrapped error carries only the inner cause, not the
// *url.Error whose text embeds the raw (possibly credential-bearing) URL.
func TestParseStorageURLParseFailureHidesURL(t *testing.T) {
t.Parallel()
const raw = "s3://mybucket/%zz"
_, err := storage.ParseStorageURL(raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", raw)
}
if strings.Contains(err.Error(), "mybucket") {
t.Errorf("error message echoed the raw URL: %v", err.Error())
}
}
internal/types/types.go
+7 -50
View File
@@ -1,7 +1,7 @@
// Package types provides custom types for better type safety across the
// vaultik codebase. Using distinct types for IDs, hashes, paths, and
// credentials prevents accidental mixing of semantically different values
// that happen to share the same underlying type.
// vaultik codebase. Using distinct types for IDs, hashes, and paths prevents
// accidental mixing of semantically different values that happen to share the
// same underlying type.
package types //nolint:revive,nolintlint // rename decision tracked in #76
import (
@@ -146,8 +146,10 @@ type SnapshotID string
// Used for content-addressing and deduplication of file chunks.
type ChunkHash string
// BlobHash is the SHA256 hash of a blob's compressed and encrypted content.
// This is used as the filename in S3 storage for content-addressed retrieval.
// BlobHash is hex(SHA256(SHA256(uncompressed blob contents))), computed before
// compression and encryption (see blobgen.DoubleSHA256 and
// docs/REPOSTRUCTURE.md). It is used as the filename in S3 storage for
// content-addressed retrieval.
type BlobHash string
// FilePath represents an absolute path to a file or directory.
@@ -157,34 +159,6 @@ type FilePath string
// Used during restore to strip the source prefix from paths.
type SourcePath string
// AgeRecipient is an age public key used for encryption.
// Format: age1... (Bech32-encoded X25519 public key)
type AgeRecipient string
// AgeSecretKey is an age private key used for decryption.
// Format: AGE-SECRET-KEY-... (Bech32-encoded X25519 private key)
// This type should never be logged or serialized in plaintext.
type AgeSecretKey string
// S3Endpoint is the URL of an S3-compatible storage endpoint.
type S3Endpoint string
// BucketName is the name of an S3 bucket.
type BucketName string
// S3Prefix is the path prefix within an S3 bucket.
type S3Prefix string
// AWSRegion is an AWS region identifier (e.g., "us-east-1").
type AWSRegion string
// AWSAccessKeyID is an AWS access key ID for authentication.
type AWSAccessKeyID string
// AWSSecretAccessKey is an AWS secret access key for authentication.
// This type should never be logged or serialized in plaintext.
type AWSSecretAccessKey string
// Hostname identifies a host machine.
type Hostname string
@@ -206,24 +180,7 @@ func (h ChunkHash) String() string { return string(h) }
func (h BlobHash) String() string { return string(h) }
func (p FilePath) String() string { return string(p) }
func (p SourcePath) String() string { return string(p) }
func (r AgeRecipient) String() string { return string(r) }
func (e S3Endpoint) String() string { return string(e) }
func (b BucketName) String() string { return string(b) }
func (p S3Prefix) String() string { return string(p) }
func (r AWSRegion) String() string { return string(r) }
func (k AWSAccessKeyID) String() string { return string(k) }
func (h Hostname) String() string { return string(h) }
func (v Version) String() string { return string(v) }
func (r GitRevision) String() string { return string(r) }
func (p GlobPattern) String() string { return string(p) }
// Redacted String methods for sensitive types - prevents accidental logging
func (k AgeSecretKey) String() string { return "[REDACTED]" }
func (k AWSSecretAccessKey) String() string { return "[REDACTED]" }
// Raw returns the actual value for sensitive types when explicitly needed.
func (k AgeSecretKey) Raw() string { return string(k) }
// Raw returns the actual value for sensitive types when explicitly needed.
func (k AWSSecretAccessKey) Raw() string { return string(k) }
internal/types/types_test.go
+136
View File
@@ -0,0 +1,136 @@
package types_test
import (
"database/sql"
"database/sql/driver"
"fmt"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/types"
)
// scannableID is the shared behaviour of the UUID-backed id types. A pointer
// to FileID or BlobID satisfies it, so both are tested through one set of
// cases.
type scannableID interface {
driver.Valuer
sql.Scanner
fmt.Stringer
IsZero() bool
}
// idKind adapts one id type to the generic tests below.
type idKind struct {
name string
newZero func() scannableID
newRandom func() scannableID
parse func(string) (scannableID, error)
}
func idKinds() []idKind {
return []idKind{
{
name: "FileID",
newZero: func() scannableID { return &types.FileID{} },
newRandom: func() scannableID {
id := types.NewFileID()
return &id
},
parse: func(s string) (scannableID, error) {
id, err := types.ParseFileID(s)
return &id, err
},
},
{
name: "BlobID",
newZero: func() scannableID { return &types.BlobID{} },
newRandom: func() scannableID {
id := types.NewBlobID()
return &id
},
parse: func(s string) (scannableID, error) {
id, err := types.ParseBlobID(s)
return &id, err
},
},
}
}
// TestIDValueScan checks that Value then Scan round trips from both a string
// and a []byte, that a NULL scans to the zero id, and that a non-string type
// and malformed text are rejected.
func TestIDValueScan(t *testing.T) {
t.Parallel()
for _, k := range idKinds() {
t.Run(k.name, func(t *testing.T) {
t.Parallel()
orig := k.newRandom()
v, err := orig.Value()
require.NoError(t, err)
s, ok := v.(string)
require.True(t, ok, "Value must yield a string")
fromString := k.newZero()
require.NoError(t, fromString.Scan(s))
assert.Equal(t, orig.String(), fromString.String())
assert.False(t, fromString.IsZero())
fromBytes := k.newZero()
require.NoError(t, fromBytes.Scan([]byte(s)))
assert.Equal(t, orig.String(), fromBytes.String())
nulled := k.newRandom()
require.NoError(t, nulled.Scan(nil))
assert.True(t, nulled.IsZero(), "NULL scans to the zero id")
require.Error(t, k.newZero().Scan(42),
"a non-string type must be rejected")
assert.Error(t, k.newZero().Scan("not-a-uuid"),
"malformed text must be rejected")
})
}
}
// TestIDParse checks that the Parse function accepts a canonical id and
// rejects malformed text.
func TestIDParse(t *testing.T) {
t.Parallel()
for _, k := range idKinds() {
t.Run(k.name, func(t *testing.T) {
t.Parallel()
canonical := k.newRandom().String()
parsed, err := k.parse(canonical)
require.NoError(t, err)
assert.Equal(t, canonical, parsed.String())
_, err = k.parse("not-a-uuid")
assert.Error(t, err)
})
}
}
// TestIDIsZero checks IsZero on the zero and on a freshly generated id.
func TestIDIsZero(t *testing.T) {
t.Parallel()
for _, k := range idKinds() {
t.Run(k.name, func(t *testing.T) {
t.Parallel()
assert.True(t, k.newZero().IsZero())
assert.False(t, k.newRandom().IsZero())
})
}
}
internal/ui/ui.go
+22 -3
View File
@@ -23,7 +23,9 @@ import (
"fmt"
"io"
"os"
"strconv"
"time"
"unicode"
"github.com/dustin/go-humanize"
"golang.org/x/term"
@@ -225,17 +227,17 @@ func (w *Writer) Hex(s string) string {
short = s[:hexAbbrevLen] + "..."
}
return w.paint(ansiCyan, short)
return w.paint(ansiCyan, sanitize(short))
}
// Snapshot colorizes a snapshot ID (full, no abbreviation).
func (w *Writer) Snapshot(id string) string {
return w.paint(ansiCyan+ansiBold, id)
return w.paint(ansiCyan+ansiBold, sanitize(id))
}
// Path colorizes a filesystem path.
func (w *Writer) Path(p string) string {
return w.paint(ansiBlue, p)
return w.paint(ansiBlue, sanitize(p))
}
// Size colorizes a byte count using humanize.Bytes.
@@ -310,6 +312,23 @@ func (w *Writer) paint(color, s string) string {
return color + s + ansiReset
}
// sanitize returns s unchanged when every rune in it is printable, and a
// double-quoted, backslash-escaped form (\n, \x1b, …) otherwise. The
// string value formatters escape their argument through this before
// painting: identifiers, paths and symlink targets they render come from
// the snapshot database, which is not trusted, and escaping must happen
// before colour is applied — the painted result already contains the
// escape codes the raw text would otherwise be indistinguishable from.
func sanitize(s string) string {
for _, r := range s {
if !unicode.IsPrint(r) {
return strconv.Quote(s)
}
}
return s
}
// emit writes "<prefix> <body>\n" with the prefix painted in prefixColor
// and the body optionally painted in bodyColor (empty = no body color).
func (w *Writer) emit(prefixColor, prefix, bodyColor, format string, args []any) {
internal/ui/ui_escape_test.go
+32
View File
@@ -0,0 +1,32 @@
package ui_test
import (
"strings"
"testing"
)
// TestValueFormattersEscapeControlCharacters checks that a path carrying an
// ESC and a newline — the shape a symlink target read back from the
// snapshot database could take — is escaped before it reaches the output.
// Colour is off here, so the only way a control byte could appear is from
// the value itself.
func TestValueFormattersEscapeControlCharacters(t *testing.T) {
t.Parallel()
w, buf := newTestWriter(false)
w.Infof("restoring %s", w.Path("a\x1b[31mZAP\nb"))
out := buf.String()
if strings.ContainsRune(out, '\x1b') {
t.Fatalf("raw ESC from a value survived in output: %q", out)
}
if strings.Count(out, "\n") != 1 {
t.Fatalf("a newline in a value must be escaped, not emitted raw: %q", out)
}
if !strings.Contains(out, `\x1b`) {
t.Fatalf("expected the escaped form of ESC in output: %q", out)
}
}
internal/vaultik/blob_fetch.go
+40 -43
View File
@@ -2,35 +2,40 @@ package vaultik
import (
"context"
"crypto/sha256"
"encoding/hex"
"errors"
"fmt"
"io"
"time"
"filippo.io/age"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/log"
)
// errBlobHashMismatch is returned when a fetched blob's content hash does
// not match the expected double-SHA-256 hash.
var errBlobHashMismatch = errors.New("blob hash mismatch")
// errBlobNotFullyRead is returned when the verifying reader is closed
// before its plaintext reached EOF. The hash can only be checked once
// the whole stream has been read, so an early or short-read close must
// fail rather than silently skip verification.
var errBlobNotFullyRead = errors.New(
"blob closed before fully read; hash not verified")
// hashVerifyReader wraps a blobgen.Reader and verifies the double-SHA-256 hash
// of decrypted plaintext when Close is called. It reuses the hash that
// blobgen.Reader already computes internally via its TeeReader, avoiding
// redundant SHA-256 computation.
type hashVerifyReader struct {
reader *blobgen.Reader // underlying decrypted blob reader (has internal hasher)
limited io.Reader // reader bounded to the blob's recorded plaintext size
fetcher io.ReadCloser // raw fetched stream (closed on Close)
blobHash string // expected double-SHA-256 hex
done bool // EOF reached
}
func (h *hashVerifyReader) Read(p []byte) (int, error) {
n, err := h.reader.Read(p)
n, err := h.limited.Read(p)
if errors.Is(err, io.EOF) {
h.done = true
}
@@ -38,21 +43,22 @@ func (h *hashVerifyReader) Read(p []byte) (int, error) {
return n, err
}
// Close verifies the hash (if the stream was fully read) and closes underlying readers.
// Close closes the underlying readers and verifies the blob hash. The
// hash check cannot be skipped: closing before the plaintext reached
// EOF (a short read or an early close) is an error, so a caller can
// never obtain unverified blob bytes.
func (h *hashVerifyReader) Close() error {
readerErr := h.reader.Close()
fetcherErr := h.fetcher.Close()
if h.done {
firstHash := h.reader.Sum256()
secondHasher := sha256.New()
secondHasher.Write(firstHash)
if !h.done {
return errBlobNotFullyRead
}
actualHashHex := hex.EncodeToString(secondHasher.Sum(nil))
actualHashHex := hex.EncodeToString(blobgen.DoubleSHA256(h.reader.Sum256()))
if actualHashHex != h.blobHash {
return fmt.Errorf("%w: expected %s, got %s",
errBlobHashMismatch, h.blobHash[:16], actualHashHex[:16])
}
errBlobHashMismatch, shortHash(h.blobHash), shortHash(actualHashHex))
}
if readerErr != nil {
@@ -66,15 +72,22 @@ func (h *hashVerifyReader) Close() error {
// returns a streaming reader that computes the double-SHA-256 hash on the fly.
// The hash is verified when the returned reader is closed (after fully reading).
// This avoids buffering the entire blob in memory.
//
// maxPlaintextSize is the blob's uncompressed_size as recorded in the
// snapshot database. Decompression stops with blobgen.ErrOutputTooLarge
// once the plaintext exceeds it, so a tampered blob cannot expand without
// limit — using the recorded size, not the restoring host's
// blob_size_limit, since that config may differ from the backup host's.
func (v *Vaultik) FetchAndDecryptBlob(
ctx context.Context, blobHash string, expectedSize int64, identity age.Identity,
ctx context.Context, blobHash string, maxPlaintextSize int64,
identities ...age.Identity,
) (io.ReadCloser, error) {
rc, _, err := v.FetchBlob(ctx, blobHash, expectedSize)
rc, err := v.FetchBlob(ctx, blobHash)
if err != nil {
return nil, err
}
reader, err := blobgen.NewReader(rc, identity)
reader, err := blobgen.NewReader(rc, identities...)
if err != nil {
_ = rc.Close()
@@ -83,45 +96,29 @@ func (v *Vaultik) FetchAndDecryptBlob(
return &hashVerifyReader{
reader: reader,
limited: blobgen.LimitReader(reader, maxPlaintextSize),
fetcher: rc,
blobHash: blobHash,
}, nil
}
// FetchBlob downloads a blob and returns a reader for the encrypted data.
// Times the Storage.Get and Storage.Stat round-trips separately at
// debug level so we can see whether the size-only Stat (which is an
// extra request on every fetch) is hurting throughput.
func (v *Vaultik) FetchBlob(
ctx context.Context, blobHash string, expectedSize int64,
) (io.ReadCloser, int64, error) {
ctx context.Context, blobHash string,
) (io.ReadCloser, error) {
// blobHash reaches here from the snapshot database, which is not
// trusted. Reject a malformed hash before it is spliced into a storage
// path (blobHash[:2]/blobHash[2:4]) or a fetch is attempted.
if !isBlobHash(blobHash) {
return nil, fmt.Errorf("%w: %s", errInvalidBlobHash, shortHash(blobHash))
}
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blobHash[:2], blobHash[2:4], blobHash)
t0 := time.Now()
rc, err := v.Storage.Get(ctx, blobPath)
getDur := time.Since(t0)
if err != nil {
return nil, 0, fmt.Errorf("downloading blob %s: %w", blobHash[:16], err)
return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
}
t0 = time.Now()
info, err := v.Storage.Stat(ctx, blobPath)
statDur := time.Since(t0)
if err != nil {
_ = rc.Close()
return nil, 0, fmt.Errorf("stat blob %s: %w", blobHash[:16], err)
}
log.Debug("FetchBlob round-trips",
"hash", blobHash[:16],
"ms_storage_get", getDur.Milliseconds(),
"ms_storage_stat", statDur.Milliseconds(),
"expected_size", expectedSize,
"stat_size", info.Size,
)
return rc, info.Size, nil
return rc, nil
}
internal/vaultik/blob_fetch_bound_test.go
+50
View File
@@ -0,0 +1,50 @@
package vaultik_test
import (
"context"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestFetchAndDecryptBlobBoundsPlaintext feeds a small, highly
// compressible blob (256 KiB of zeros) whose decompressed size far exceeds
// the plaintext bound passed to FetchAndDecryptBlob. Decompression must
// stop with blobgen.ErrOutputTooLarge within the bound rather than
// expanding the whole blob into the restore cache.
func TestFetchAndDecryptBlobBoundsPlaintext(t *testing.T) {
t.Parallel()
identity, err := age.GenerateX25519Identity()
require.NoError(t, err)
plaintext := make([]byte, 256*1024)
encryptedData, correctHash := buildHashTestBlob(t, identity, plaintext)
mockStorage := NewMockStorer()
blobPath := "blobs/" + correctHash[:2] + "/" +
correctHash[2:4] + "/" + correctHash
mockStorage.mu.Lock()
mockStorage.data[blobPath] = encryptedData
mockStorage.mu.Unlock()
tv := vaultik.NewForTesting(mockStorage)
const maxPlaintext = 1024
rc, err := tv.FetchAndDecryptBlob(
context.Background(), correctHash, maxPlaintext, identity)
require.NoError(t, err)
n, copyErr := io.Copy(io.Discard, rc)
_ = rc.Close()
require.ErrorIs(t, copyErr, blobgen.ErrOutputTooLarge)
require.LessOrEqual(t, n, int64(maxPlaintext)+1,
"decompression must stop within the recorded plaintext bound")
}
internal/vaultik/blob_fetch_hash_test.go
+81 -4
View File
@@ -40,13 +40,13 @@ func buildHashTestBlob(
}
// Compute the double-SHA-256 hash of the plaintext (matches
// blobgen.Writer.Sum256).
// blobgen.Writer.ContentID).
firstHash := sha256.Sum256(plaintext)
secondHash := sha256.Sum256(firstHash[:])
correctHash := hex.EncodeToString(secondHash[:])
// Verify our hash matches what blobgen.Writer produces
writerHash := hex.EncodeToString(writer.Sum256())
writerHash := hex.EncodeToString(writer.ContentID())
if correctHash != writerHash {
t.Fatalf("hash computation mismatch: manual=%s, writer=%s",
correctHash, writerHash)
@@ -55,6 +55,35 @@ func buildHashTestBlob(
return encBuf.Bytes(), correctHash
}
// TestFetchBlobRejectsMalformedHash verifies FetchBlob refuses a blob hash
// that is not 64 lowercase hex characters before it builds a storage path
// or issues any request. The hash reaches FetchBlob from the snapshot
// database, which is not trusted, so a value such as one containing "/.."
// must never reach the store.
func TestFetchBlobRejectsMalformedHash(t *testing.T) {
t.Parallel()
mockStorage := NewMockStorer()
tv := vaultik.NewForTesting(mockStorage)
ctx := context.Background()
for _, bad := range []string{
"aa/../../../home/u/.profile",
"abc",
strings.Repeat("A", 64), // uppercase hex is not accepted
strings.Repeat("g", 64), // not hex
} {
_, err := tv.FetchBlob(ctx, bad)
if err == nil {
t.Fatalf("expected error for malformed hash %q, got nil", bad)
}
}
if calls := mockStorage.GetCalls(); len(calls) != 0 {
t.Fatalf("storage was accessed for a malformed hash: %v", calls)
}
}
// TestFetchAndDecryptBlobVerifiesHash verifies that FetchAndDecryptBlob checks
// the double-SHA-256 hash of the decrypted plaintext against the expected blob hash.
func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
@@ -84,7 +113,7 @@ func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
t.Parallel()
rc, err := tv.FetchAndDecryptBlob(
ctx, correctHash, int64(len(encryptedData)), identity)
ctx, correctHash, int64(len(plaintext)), identity)
if err != nil {
t.Fatalf("expected success, got error: %v", err)
}
@@ -116,7 +145,7 @@ func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
mockStorage.mu.Unlock()
rc, err := tv.FetchAndDecryptBlob(
ctx, fakeHash, int64(len(encryptedData)), identity)
ctx, fakeHash, int64(len(plaintext)), identity)
if err != nil {
t.Fatalf("unexpected error opening stream: %v", err)
}
@@ -133,3 +162,51 @@ func TestFetchAndDecryptBlobVerifiesHash(t *testing.T) {
}
})
}
// TestFetchAndDecryptBlobCloseBeforeEOFFails verifies the hash check
// cannot be skipped: a caller that reads only part of the blob and then
// closes gets an error rather than silently unverified bytes.
func TestFetchAndDecryptBlobCloseBeforeEOFFails(t *testing.T) {
t.Parallel()
identity, err := age.GenerateX25519Identity()
if err != nil {
t.Fatalf("generating identity: %v", err)
}
plaintext := []byte("hello world test data for blob hash verification")
encryptedData, correctHash := buildHashTestBlob(t, identity, plaintext)
mockStorage := NewMockStorer()
blobPath := "blobs/" + correctHash[:2] + "/" +
correctHash[2:4] + "/" + correctHash
mockStorage.mu.Lock()
mockStorage.data[blobPath] = encryptedData
mockStorage.mu.Unlock()
tv := vaultik.NewForTesting(mockStorage)
rc, err := tv.FetchAndDecryptBlob(
context.Background(), correctHash, int64(len(plaintext)), identity)
if err != nil {
t.Fatalf("unexpected error opening stream: %v", err)
}
// Read one byte, far short of the plaintext length, then close.
buf := make([]byte, 1)
_, err = rc.Read(buf)
if err != nil {
t.Fatalf("reading first byte: %v", err)
}
err = rc.Close()
if err == nil {
t.Fatal("expected error closing before EOF, got nil")
}
if !strings.Contains(err.Error(), "hash not verified") {
t.Fatalf("expected not-verified error, got: %v", err)
}
}
internal/vaultik/blobcache.go
+72 -14
View File
@@ -6,6 +6,7 @@ import (
"io"
"os"
"path/filepath"
"strings"
"sync"
)
@@ -13,6 +14,9 @@ import (
var (
errCacheKeyMissing = errors.New("key not in cache")
errCacheReadBeyondBlob = errors.New("read beyond blob size")
errCacheKeyHasSeparator = errors.New(
"cache key contains a path separator")
errCacheNegativeRead = errors.New("negative offset or length")
)
// blobCacheFileMode is the permission mode for cached blob files.
@@ -74,6 +78,11 @@ func newBlobDiskCache(maxBytes int64) (*blobDiskCache, error) {
// Put writes blob data to disk cache. Entries larger than maxBytes are
// silently skipped.
func (c *blobDiskCache) Put(key string, data []byte) error {
p, err := c.path(key)
if err != nil {
return err
}
entrySize := int64(len(data))
c.mu.Lock()
@@ -87,11 +96,12 @@ func (c *blobDiskCache) Put(key string, data []byte) error {
if e, ok := c.items[key]; ok {
c.unlink(e)
c.curBytes -= e.size
_ = os.Remove(c.path(key))
_ = os.Remove(p)
delete(c.items, key)
}
err := os.WriteFile(c.path(key), data, blobCacheFileMode)
err = os.WriteFile(p, data, blobCacheFileMode)
if err != nil {
return fmt.Errorf("writing blob to cache: %w", err)
}
@@ -119,19 +129,26 @@ func (c *blobDiskCache) Put(key string, data []byte) error {
// disk without buffering its entire plaintext (which may be tens of GB)
// in RAM.
func (c *blobDiskCache) PutFromReader(key string, r io.Reader) (int64, error) {
p, err := c.path(key)
if err != nil {
return 0, err
}
c.mu.Lock()
// Remove any prior entry first; we'll re-link after the file is
// written successfully.
if e, ok := c.items[key]; ok {
c.unlink(e)
c.curBytes -= e.size
_ = os.Remove(c.path(key))
_ = os.Remove(p)
delete(c.items, key)
}
c.mu.Unlock()
//nolint:gosec // G304: path() rejects keys with a separator
f, err := os.OpenFile(
c.path(key), os.O_CREATE|os.O_TRUNC|os.O_WRONLY, blobCacheFileMode)
p, os.O_CREATE|os.O_TRUNC|os.O_WRONLY, blobCacheFileMode)
if err != nil {
return 0, fmt.Errorf("creating cache file: %w", err)
}
@@ -140,13 +157,13 @@ func (c *blobDiskCache) PutFromReader(key string, r io.Reader) (int64, error) {
closeErr := f.Close()
if copyErr != nil {
_ = os.Remove(c.path(key))
_ = os.Remove(p)
return written, fmt.Errorf("streaming to cache file: %w", copyErr)
}
if closeErr != nil {
_ = os.Remove(c.path(key))
_ = os.Remove(p)
return written, fmt.Errorf("closing cache file: %w", closeErr)
}
@@ -158,7 +175,7 @@ func (c *blobDiskCache) PutFromReader(key string, r io.Reader) (int64, error) {
// floor — but the restore path passes math.MaxInt64 as maxBytes
// so this branch is effectively unreachable there.
if written > c.maxBytes {
_ = os.Remove(c.path(key))
_ = os.Remove(p)
return written, nil
}
@@ -181,6 +198,11 @@ func (c *blobDiskCache) PutFromReader(key string, r io.Reader) (int64, error) {
// Get reads a cached blob from disk. Returns data and true on hit.
func (c *blobDiskCache) Get(key string) ([]byte, bool) {
p, err := c.path(key)
if err != nil {
return nil, false
}
c.mu.Lock()
c.getCalls++
@@ -195,7 +217,8 @@ func (c *blobDiskCache) Get(key string) ([]byte, bool) {
c.pushFront(e)
c.mu.Unlock()
data, err := os.ReadFile(c.path(key))
//nolint:gosec // G304: path() rejects keys with a separator
data, err := os.ReadFile(p)
if err != nil {
c.mu.Lock()
if e2, ok2 := c.items[key]; ok2 && e2 == e {
@@ -213,6 +236,20 @@ func (c *blobDiskCache) Get(key string) ([]byte, bool) {
// ReadAt reads a slice of a cached blob without loading the entire blob into memory.
func (c *blobDiskCache) ReadAt(key string, offset, length int64) ([]byte, error) {
p, err := c.path(key)
if err != nil {
return nil, err
}
// offset and length come from a blob_chunks row read back from the
// destination. A negative value must be rejected outright; the upper
// bound is checked as length > size-offset (a subtraction) so a huge
// offset+length cannot overflow int64 and slip past the check.
if offset < 0 || length < 0 {
return nil, fmt.Errorf("%w: offset=%d length=%d",
errCacheNegativeRead, offset, length)
}
c.mu.Lock()
c.readAtCalls++
@@ -223,7 +260,7 @@ func (c *blobDiskCache) ReadAt(key string, offset, length int64) ([]byte, error)
return nil, fmt.Errorf("%w: %q", errCacheKeyMissing, key)
}
if offset+length > e.size {
if length > e.size-offset {
c.mu.Unlock()
return nil, fmt.Errorf("%w: offset=%d length=%d size=%d",
@@ -234,7 +271,7 @@ func (c *blobDiskCache) ReadAt(key string, offset, length int64) ([]byte, error)
c.pushFront(e)
c.mu.Unlock()
f, err := os.Open(c.path(key))
f, err := os.Open(p) //nolint:gosec // G304: path() rejects keys with a separator
if err != nil {
return nil, err
}
@@ -276,7 +313,13 @@ func (c *blobDiskCache) Delete(key string) {
c.unlink(e)
delete(c.items, key)
c.curBytes -= e.size
_ = os.Remove(c.path(key))
// The key is already in the map, so it passed path() when it was
// inserted; the error cannot occur here.
p, err := c.path(key)
if err == nil {
_ = os.Remove(p)
}
}
// Keys returns a snapshot of all cached keys. Safe for iteration without
@@ -347,8 +390,18 @@ func (c *blobDiskCache) Close() error {
return os.RemoveAll(c.dir)
}
func (c *blobDiskCache) path(key string) string {
return filepath.Join(c.dir, key)
// path returns the on-disk location of the cache file for key. The key is
// a blob hash read back from the destination and is not trusted: a value
// such as "aa/../../../home/u/.profile" would otherwise make filepath.Join
// escape the cache directory, so a key containing a path separator is
// refused rather than joined.
func (c *blobDiskCache) path(key string) (string, error) {
if strings.ContainsRune(key, '/') ||
strings.ContainsRune(key, filepath.Separator) {
return "", fmt.Errorf("%w: %q", errCacheKeyHasSeparator, key)
}
return filepath.Join(c.dir, key), nil
}
func (c *blobDiskCache) unlink(e *blobDiskCacheEntry) {
@@ -391,5 +444,10 @@ func (c *blobDiskCache) evictLRU() {
c.unlink(victim)
delete(c.items, victim.key)
c.curBytes -= victim.size
_ = os.Remove(c.path(victim.key))
// victim.key was validated by path() on insertion, so this cannot err.
p, err := c.path(victim.key)
if err == nil {
_ = os.Remove(p)
}
}
internal/vaultik/blobhash.go
+52
View File
@@ -0,0 +1,52 @@
package vaultik
import "errors"
// blobHashHexLen is the length of a blob hash written as lowercase hex: a
// SHA-256 digest is 32 bytes, so 64 characters. Remote snapshot keys are
// SHA-256 hashes too and share this exact form.
const blobHashHexLen = 64
// shortHashLen is how many leading characters of a hash appear in log and
// error text.
const shortHashLen = 16
// errInvalidBlobHash reports a value used as a blob hash that is not
// exactly 64 lowercase hex characters. Restore, verify and prune read
// these values back from the destination, which is not trusted, so each
// one is checked before it is used to build a path or drive a read.
var errInvalidBlobHash = errors.New(
"blob hash is not 64 lowercase hex characters")
// isBlobHash reports whether s is exactly 64 lowercase hex characters.
// Every real blob hash and remote snapshot key has this form.
//
// The check is a plain function, not a method on types.BlobHash: the
// packer stores "temp-placeholder-{uuid}" as the hash of an unfinished
// blob in the local index, so the type itself must keep accepting values
// that are not hashes.
func isBlobHash(s string) bool {
if len(s) != blobHashHexLen {
return false
}
for _, r := range s {
if (r < '0' || r > '9') && (r < 'a' || r > 'f') {
return false
}
}
return true
}
// shortHash returns the leading part of a hash for log and error text. It
// never panics: a string shorter than the prefix is returned whole. A hash
// read from the destination may be malformed, and formatting one for a
// message must not crash the command.
func shortHash(s string) string {
if len(s) <= shortHashLen {
return s
}
return s[:shortHashLen]
}
internal/vaultik/destination_validation_test.go
+262
View File
@@ -0,0 +1,262 @@
package vaultik //nolint:testpackage // drives unexported input validation
import (
"context"
"errors"
"io"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/types"
)
// These tests treat every hash, offset and length read back from the
// destination as hostile. A blob hash comes from the downloaded snapshot
// database or the store listing, neither of which is authenticated (see
// https://git.eeqj.de/sneak/vaultik/issues/155), so each is validated
// before it is used to build a path or size an allocation.
// TestBlobCacheRejectsKeyWithSeparator proves the arbitrary-file-write
// hole is closed: a blob hash that climbs out of the cache directory is
// refused and nothing is written outside it. This is the exact write the
// restore path performs, keyed by the hash from the snapshot database.
func TestBlobCacheRejectsKeyWithSeparator(t *testing.T) {
t.Parallel()
cache, err := newBlobDiskCache(1 << 20)
require.NoError(t, err)
defer func() { _ = cache.Close() }()
target := filepath.Join(t.TempDir(), "pwned")
// A hash whose relative form escapes the cache directory to target.
key, err := filepath.Rel(cache.dir, target)
require.NoError(t, err)
require.Contains(t, key, "..")
err = cache.Put(key, []byte("secret"))
require.ErrorIs(t, err, errCacheKeyHasSeparator)
_, err = cache.PutFromReader(key, strings.NewReader("secret"))
require.ErrorIs(t, err, errCacheKeyHasSeparator)
_, statErr := os.Stat(target)
require.Truef(t, os.IsNotExist(statErr),
"cache wrote outside its directory at %s", target)
}
// TestBuildBlobIndexesRejectsHostileHash proves restore refuses a snapshot
// database whose blob_hash escapes the cache directory. buildBlobIndexes is
// the first place restore reads these hashes back, and it fails there, before
// any blob is fetched or written, so a hash containing /../ cannot steer a
// later write outside the cache directory.
func TestBuildBlobIndexesRejectsHostileHash(t *testing.T) {
t.Parallel()
ctx := context.Background()
db, err := database.New(ctx, filepath.Join(t.TempDir(), "index.sqlite"))
require.NoError(t, err)
defer func() { _ = db.Close() }()
// A blob cache and a target file just outside it. The hostile hash is
// the relative path from the cache to that target, so an unguarded
// restore keyed by this hash would write there.
cache, err := newBlobDiskCache(1 << 20)
require.NoError(t, err)
defer func() { _ = cache.Close() }()
target := filepath.Join(t.TempDir(), "pwned")
hostile, err := filepath.Rel(cache.dir, target)
require.NoError(t, err)
require.Contains(t, hostile, "..")
repos := database.NewRepositories(db)
require.NoError(t, repos.Blobs.Create(ctx, nil, &database.Blob{
ID: types.NewBlobID(),
Hash: types.BlobHash(hostile),
CreatedTS: time.Now().UTC(),
}))
v := NewForTesting(nil)
v.SetContext(ctx)
_, _, err = v.buildBlobIndexes(repos)
require.ErrorIs(t, err, errInvalidBlobHash)
_, statErr := os.Stat(target)
require.Truef(t, os.IsNotExist(statErr),
"restore wrote outside the cache directory at %s", target)
}
// TestBlobCacheReadAtRejectsBadBounds proves a blob_chunks row cannot
// drive an out-of-range or negative read. offset/length reach ReadAt
// straight from the database.
func TestBlobCacheReadAtRejectsBadBounds(t *testing.T) {
t.Parallel()
cache, err := newBlobDiskCache(1 << 20)
require.NoError(t, err)
defer func() { _ = cache.Close() }()
require.NoError(t, cache.Put("blob", make([]byte, 100)))
_, err = cache.ReadAt("blob", -1, 10)
require.ErrorIs(t, err, errCacheNegativeRead)
_, err = cache.ReadAt("blob", 0, -1)
require.ErrorIs(t, err, errCacheNegativeRead)
// A length past the end is rejected via the subtraction bound, so a
// huge offset+length cannot overflow past the check.
_, err = cache.ReadAt("blob", 50, 60)
require.ErrorIs(t, err, errCacheReadBeyondBlob)
}
// TestListAllRemoteBlobsSkipsNonConformingName proves a bogus object name
// under blobs/ (here a three-character name) is skipped rather than
// entering the blob map, so prune's later hash[:2]/hash[2:4] path build
// cannot panic on it.
func TestListAllRemoteBlobsSkipsNonConformingName(t *testing.T) {
// Initialize the global logger before t.Parallel() so the write lands
// in the serial phase and cannot race other parallel tests reading it.
log.Initialize(log.Config{})
t.Parallel()
good := strings.Repeat("a", blobHashHexLen)
store := &stubLister{objects: []storage.ObjectInfo{
{Key: "blobs/" + good[:2] + "/" + good[2:4] + "/" + good, Size: 10},
{Key: "blobs/a/b/c", Size: 3},
}}
v := &Vaultik{Storage: store}
v.SetContext(context.Background())
blobs, err := v.listAllRemoteBlobs()
require.NoError(t, err)
require.Contains(t, blobs, good)
require.NotContains(t, blobs, "c")
require.Len(t, blobs, 1)
}
// TestVerifyManifestBlobsRejectsShortHash proves a manifest (which is not
// authenticated) with a short blob hash fails cleanly instead of panicking
// on blob.Hash[:2].
func TestVerifyManifestBlobsRejectsShortHash(t *testing.T) {
t.Parallel()
v := &Vaultik{Stdout: io.Discard}
manifest := &snapshot.Manifest{
Blobs: []snapshot.BlobInfo{{Hash: "abc", CompressedSize: 1}},
}
verified, missing, mismatched, missingSize, err :=
v.verifyManifestBlobs(manifest, &VerifyOptions{JSON: true})
require.ErrorIs(t, err, errInvalidBlobHash)
require.Zero(t, verified)
require.Zero(t, missing)
require.Zero(t, mismatched)
require.Zero(t, missingSize)
}
// TestVerifyBlobChunksRejectsNegativeLength proves a blob_chunks row with a
// negative length returns an error rather than reaching make([]byte,
// length) or streaming an untrusted size.
func TestVerifyBlobChunksRejectsNegativeLength(t *testing.T) {
t.Parallel()
ctx := context.Background()
db, err := database.New(ctx, filepath.Join(t.TempDir(), "index.sqlite"))
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
blobHash := strings.Repeat("b", blobHashHexLen)
blob := &database.Blob{
ID: types.NewBlobID(),
Hash: types.BlobHash(blobHash),
CreatedTS: time.Now().UTC(),
}
require.NoError(t, repos.Blobs.Create(ctx, nil, blob))
chunkHash := strings.Repeat("c", blobHashHexLen)
require.NoError(t, repos.Chunks.Create(ctx, nil,
&database.Chunk{ChunkHash: types.ChunkHash(chunkHash), Size: 1024}))
require.NoError(t, repos.BlobChunks.Create(ctx, nil, &database.BlobChunk{
BlobID: blob.ID,
ChunkHash: types.ChunkHash(chunkHash),
Offset: 0,
Length: -1,
}))
v := NewForTesting(nil)
_, err = v.verifyBlobChunks(db.Conn(), blobHash, strings.NewReader(""))
require.ErrorIs(t, err, errNegativeChunkLength)
}
// errStubUnused marks a stubLister method a test never exercises.
var errStubUnused = errors.New("stubLister method not used in test")
// stubLister is a storage.Storer whose ListStream yields a fixed set of
// objects; every other method is unused by the tests here.
type stubLister struct {
objects []storage.ObjectInfo
}
func (s *stubLister) ListStream(
_ context.Context, prefix string,
) <-chan storage.ObjectInfo {
ch := make(chan storage.ObjectInfo, len(s.objects))
for _, o := range s.objects {
if strings.HasPrefix(o.Key, prefix) {
ch <- o
}
}
close(ch)
return ch
}
func (s *stubLister) Put(_ context.Context, _ string, _ io.Reader) error {
return errStubUnused
}
func (s *stubLister) PutWithProgress(
_ context.Context, _ string, _ io.Reader, _ int64, _ storage.ProgressCallback,
) error {
return errStubUnused
}
func (s *stubLister) Get(_ context.Context, _ string) (io.ReadCloser, error) {
return nil, errStubUnused
}
func (s *stubLister) Stat(_ context.Context, _ string) (*storage.ObjectInfo, error) {
return nil, errStubUnused
}
func (s *stubLister) Delete(_ context.Context, _ string) error {
return errStubUnused
}
func (s *stubLister) List(_ context.Context, _ string) ([]string, error) {
return nil, errStubUnused
}
func (s *stubLister) Info() storage.Info {
return storage.Info{}
}
internal/vaultik/fault_injection_test.go
+647
View File
@@ -0,0 +1,647 @@
package vaultik_test
import (
"context"
"errors"
"io"
"os"
"path/filepath"
"strings"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// These tests cover the failure modes a backup tool must survive:
// interrupted uploads, an interrupted metadata export, corrupt and
// truncated reads, a full restore disk, and a backend that reports
// success while storing nothing. Faults are injected through the
// storage.Storer seam (internal/storage/faultstore), never by patching
// production code. Each test asserts on the observable end state — what
// is in the index, what is at the destination, what the user is told —
// not merely that an error was returned. See
// https://git.eeqj.de/sneak/vaultik/issues/72.
//
// Object-level write atomicity (no partial blob object left behind) is
// covered by the file:// backend's atomic-write work
// (https://git.eeqj.de/sneak/vaultik/issues/130) and is not re-tested
// here; these tests target the layers above the backend.
//
// The tests run serially, not with t.Parallel: each calls
// log.Initialize, which replaces the package-global logger, and a
// backup or restore running concurrently reads that same logger. Under
// -race the two collide. Running one at a time is the same choice
// prune_count_test.go already makes for the same reason.
const (
faultChunkSize = int64(64 * 1024)
faultMaxBlobSize = int64(256 * 1024)
)
// faultTestConfig returns the config shared by the fault-injection
// tests: a real recipient/secret keypair so blobs are genuinely
// encrypted, and a blob size limit the restore sweeper can divide.
func faultTestConfig() *config.Config {
return &config.Config{
AgeRecipients: []string{testAgePublicKey},
AgeSecretKey: testAgeSecretKey,
CompressionLevel: 3,
Hostname: testHostname,
BlobSizeLimit: config.Size(faultMaxBlobSize),
}
}
// writeFaultSourceTree writes a spread of file sizes that forces several
// chunks across more than one blob, so a fault landing on a single blob
// still leaves other data intact. Returns the expected content by path.
func writeFaultSourceTree(
t *testing.T, fs afero.Fs, dataDir string,
) map[string][]byte {
t.Helper()
files := map[string][]byte{
filepath.Join(dataDir, "small.txt"): []byte("hello vaultik"),
filepath.Join(dataDir, "a.bin"): bytesPattern("a-", int(faultChunkSize*3)),
filepath.Join(dataDir, "sub", "b.bin"): bytesPattern("b-", int(faultChunkSize*3)),
filepath.Join(dataDir, "sub", "c.bin"): bytesPattern("c-", int(faultChunkSize*2)),
}
for path, content := range files {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
return files
}
// newFaultScanner builds a scanner writing through the given storer.
func newFaultScanner(
fs afero.Fs, storer storage.Storer,
cfg *config.Config, repos *database.Repositories,
) *snapshot.Scanner {
return snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: faultChunkSize,
MaxBlobSize: faultMaxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
}
// newFaultSnapshotManager builds a snapshot manager writing through the
// given storer.
func newFaultSnapshotManager(
fs afero.Fs, storer storage.Storer,
cfg *config.Config, repos *database.Repositories,
) *snapshot.SnapshotManager {
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: storer,
Config: cfg,
})
sm.SetFilesystem(fs)
return sm
}
// fullFaultBackup runs a complete backup (create, scan, complete,
// export) through storer and returns the snapshot ID.
func fullFaultBackup(
ctx context.Context, t *testing.T, fs afero.Fs, storer storage.Storer,
cfg *config.Config, repos *database.Repositories,
dataDir, dbPath, name string,
) string {
t.Helper()
sm := newFaultSnapshotManager(fs, storer, cfg, repos)
scanner := newFaultScanner(fs, storer, cfg, repos)
id, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, name, "v", "g")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, id)
require.NoError(t, err)
require.NoError(t, sm.CompleteSnapshot(ctx, id))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, id))
return id
}
// newReaderVaultik builds a Vaultik that reads (restore/verify) through
// storer, with the given repositories (nil is fine for restore/verify,
// which read metadata from storage).
func newReaderVaultik(
ctx context.Context, cfg *config.Config, storer storage.Storer,
repos *database.Repositories, fs afero.Fs,
) *vaultik.Vaultik {
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Repositories: repos,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
// Scenario 3: a stored blob's bytes are flipped before restore reads
// them. Restore must fail loudly, and no file must be left on the
// restore target holding corrupt content.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestRestoreRejectsCorruptBlob(t *testing.T) {
assertRestoreRejectsDamagedBlob(t, faultstore.GetCorrupt, "corrupt")
}
// Scenario 4: a stored blob is truncated before restore reads it. Same
// contract as the corrupt case.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestRestoreRejectsTruncatedBlob(t *testing.T) {
assertRestoreRejectsDamagedBlob(t, faultstore.GetTruncate, "truncated")
}
// assertRestoreRejectsDamagedBlob backs up the source tree, then restores
// through a store that damages every blob read with the given fault, and
// asserts restore fails naming a blob and leaves no file on the target
// holding wrong bytes. Metadata reads are returned intact so the failure
// is isolated to the blob.
func assertRestoreRejectsDamagedBlob(
t *testing.T, fault faultstore.GetFault, name string,
) {
t.Helper()
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
testFiles := writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
id := fullFaultBackup(ctx, t, fs, inner, cfg, repos, dataDir, dbPath, name)
require.NoError(t, db.Close())
faultStore := faultstore.New(inner)
faultStore.OnGet = func(key string) faultstore.GetFault {
if strings.HasPrefix(key, "blobs/") {
return fault
}
return faultstore.GetNormal
}
v := newReaderVaultik(ctx, cfg, faultStore, nil, fs)
err = v.Restore(&vaultik.RestoreOptions{SnapshotID: id, TargetDir: restoreDir})
require.Error(t, err, "restore must fail on a damaged blob")
assert.Contains(t, err.Error(), "blob",
"error should name the blob that failed")
assertNoCorruptFiles(t, fs, restoreDir, testFiles)
}
// Scenario 6: the backend accepts blob uploads and reports success but
// stores nothing. verify --deep must catch it.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestDeepVerifyCatchesLyingBackend(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
// Blob uploads are swallowed; metadata uploads land, so verify can
// download the manifest and database and then discover the blobs are
// absent.
lying := faultstore.New(inner)
lying.OnPut = func(key string) faultstore.PutAction {
if strings.HasPrefix(key, "blobs/") {
return faultstore.PutSwallow
}
return faultstore.PutNormal
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
id := fullFaultBackup(ctx, t, fs, lying, cfg, repos, dataDir, dbPath, "lying")
require.NoError(t, db.Close())
// No blob objects were actually written.
blobKeys, err := inner.List(ctx, "blobs/")
require.NoError(t, err)
assert.Empty(t, blobKeys, "lying backend should have stored no blobs")
// Read back through the honest underlying store.
v := newReaderVaultik(ctx, cfg, inner, nil, fs)
err = v.VerifySnapshotWithOptions(id, &vaultik.VerifyOptions{Deep: true})
require.Error(t, err, "deep verify must catch a backend that stored nothing")
}
// Scenario 1a: a blob upload fails partway through. The interrupted run
// must not record the blob as uploaded, must not reference it from the
// snapshot, and must leave no blob object at the destination.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestInterruptedBlobUploadRecordsNoUploadedBlob(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
defer func() { _ = db.Close() }()
repos := database.NewRepositories(db)
// Every blob upload fails partway through. The scan must surface it.
fault := faultstore.New(inner)
fault.OnPut = func(key string) faultstore.PutAction {
if strings.HasPrefix(key, "blobs/") {
return faultstore.PutFail
}
return faultstore.PutNormal
}
sm := newFaultSnapshotManager(fs, fault, cfg, repos)
scanner := newFaultScanner(fs, fault, cfg, repos)
id, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "interrupted", "v", "g")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, id)
require.Error(t, err, "scan must fail when a blob upload fails")
// No blob may claim to be uploaded.
blobs, err := repos.Blobs.GetAll(ctx)
require.NoError(t, err)
for _, b := range blobs {
assert.Nilf(t, b.UploadedTS,
"blob %s marked uploaded after a failed upload", b.Hash)
}
// The snapshot may reference no blobs, and the destination holds none.
hashes, err := repos.Snapshots.GetBlobHashes(ctx, id)
require.NoError(t, err)
assert.Empty(t, hashes, "interrupted snapshot must reference no blobs")
blobKeys, err := inner.List(ctx, "blobs/")
require.NoError(t, err)
assert.Empty(t, blobKeys, "no blob object may survive at the destination")
}
// Scenario 1b: after an interrupted upload, a retry on the same local
// index must produce a restorable snapshot. The interrupted run leaves
// the blob's chunk rows in the index; the fix for
// https://git.eeqj.de/sneak/vaultik/issues/148 discards those un-uploaded
// blob rows at the start of the next scan and deduplicates only against
// chunks in a blob that was actually uploaded, so the retry re-chunks and
// re-uploads the affected data instead of silently referencing data that
// never reached storage.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupRetryAfterInterruptedUploadIsRestorable(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
testFiles := writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
// Attempt 1: every blob upload fails.
fault := faultstore.New(inner)
fault.OnPut = func(key string) faultstore.PutAction {
if strings.HasPrefix(key, "blobs/") {
return faultstore.PutFail
}
return faultstore.PutNormal
}
sm := newFaultSnapshotManager(fs, fault, cfg, repos)
scanner := newFaultScanner(fs, fault, cfg, repos)
id1, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "interrupted", "v", "g")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, id1)
require.Error(t, err)
// Retry on the same local index with a working backend.
id2 := fullFaultBackup(ctx, t, fs, inner, cfg, repos, dataDir, dbPath, "retry")
require.NoError(t, db.Close())
v := newReaderVaultik(ctx, cfg, inner, nil, fs)
require.NoError(t, v.Restore(&vaultik.RestoreOptions{
SnapshotID: id2,
TargetDir: restoreDir,
Verify: true,
}), "retry after an interrupted upload must produce a restorable snapshot")
assertRestoredTree(t, fs, restoreDir, testFiles)
}
// Scenario 2: the process dies during the metadata export, after the
// database is uploaded but before the manifest. The destination is left
// with blobs and a database but no manifest. verify and snapshot list
// must report the damage honestly rather than crashing or passing.
// Automatic detection and repair of this partial state on the next run
// is tracked in https://git.eeqj.de/sneak/vaultik/issues/177 and is not
// asserted here.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
// Back up and complete with a working backend.
sm := newFaultSnapshotManager(fs, inner, cfg, repos)
scanner := newFaultScanner(fs, inner, cfg, repos)
id, err := sm.CreateSnapshotWithName(ctx, cfg.Hostname, "export", "v", "g")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, id)
require.NoError(t, err)
require.NoError(t, sm.CompleteSnapshot(ctx, id))
// Export through a backend that fails only the manifest upload. The
// database uploads first and lands; the manifest does not.
fault := faultstore.New(inner)
fault.OnPut = func(key string) faultstore.PutAction {
if strings.HasSuffix(key, "manifest.json.zst") {
return faultstore.PutFail
}
return faultstore.PutNormal
}
smFault := newFaultSnapshotManager(fs, fault, cfg, repos)
err = smFault.ExportSnapshotMetadata(ctx, dbPath, id)
require.Error(t, err, "export must fail when the manifest upload fails")
// The destination is in the partial state the scenario describes.
key := snapshot.RemoteSnapshotKey(id)
_, err = inner.Stat(ctx, "metadata/"+key+"/db.zst.age")
require.NoError(t, err, "database should have been uploaded before the manifest")
_, err = inner.Stat(ctx, "metadata/"+key+"/manifest.json.zst")
require.ErrorIs(t, err, storage.ErrNotFound, "manifest upload should not have landed")
// verify must fail loudly for this snapshot, in both modes.
reader := newReaderVaultik(ctx, cfg, inner, repos, fs)
deepOpts := &vaultik.VerifyOptions{Deep: true}
require.Error(t, reader.VerifySnapshotWithOptions(id, deepOpts),
"deep verify must report the missing manifest")
shallowOpts := &vaultik.VerifyOptions{Deep: false}
require.Error(t, reader.VerifySnapshotWithOptions(id, shallowOpts),
"shallow verify must report the missing manifest")
// snapshot list must not crash on the partial snapshot.
require.NoError(t, reader.ListSnapshots(false),
"snapshot list must tolerate a partially-exported snapshot")
}
// Scenario 5: the restore target runs out of space mid-file. Restore
// must fail with an out-of-space error, and must not leave a truncated
// file at the target path presenting as a complete restore. Restore
// today writes each file straight to its final path and does not remove
// it when a write fails, so the truncated file survives; deleting it is
// tracked by https://git.eeqj.de/sneak/vaultik/issues/163. Skipped until
// that lands, so the destination assertion below is recorded rather than
// dropped.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestRestoreReportsDiskFull(t *testing.T) {
t.Skip("blocked on https://git.eeqj.de/sneak/vaultik/issues/163: " +
"a disk-full write leaves a truncated file at the target path " +
"instead of removing it")
log.Initialize(log.Config{})
osFS := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
testFiles := writeFaultSourceTree(t, osFS, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
id := fullFaultBackup(ctx, t, osFS, inner, cfg, repos, dataDir, dbPath, "diskfull")
require.NoError(t, db.Close())
// Restore onto a filesystem that allows only a few bytes of file
// content: enough to create files, far too little to hold them.
budget := int64(8)
quota := &quotaFS{Fs: osFS, remaining: &budget}
v := newReaderVaultik(ctx, cfg, inner, nil, quota)
err = v.Restore(&vaultik.RestoreOptions{SnapshotID: id, TargetDir: restoreDir})
require.Error(t, err, "restore must fail when the target disk is full")
assert.Contains(t, err.Error(), errNoSpace.Error(),
"restore error should surface the out-of-space cause")
// The failure must not leave a truncated file behind presenting as a
// complete restore: any file at the target must hold the original
// bytes, or be absent.
assertNoCorruptFiles(t, osFS, restoreDir, testFiles)
}
// assertRestoredTree byte-compares every restored file against the
// original.
func assertRestoredTree(
t *testing.T, fs afero.Fs, restoreDir string, testFiles map[string][]byte,
) {
t.Helper()
for origPath, expected := range testFiles {
restoredPath := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restoredPath)
require.NoErrorf(t, err, "restored file missing: %s", origPath)
require.Equalf(t, expected, got, "restored content mismatch for %s", origPath)
}
}
// errNoSpace is the out-of-space error quotaFS returns once its byte
// budget is exhausted, mirroring a real ENOSPC.
var errNoSpace = errors.New("no space left on device")
// quotaFS is an afero.Fs whose files may write only a fixed total number
// of content bytes before failing, simulating a full restore target. It
// wraps the interface so every method except Create delegates to the
// real filesystem; only file writes are capped.
type quotaFS struct {
afero.Fs
remaining *int64
}
//nolint:ireturn // afero.Fs.Create's signature requires returning afero.File.
func (q *quotaFS) Create(name string) (afero.File, error) {
f, err := q.Fs.Create(name)
if err != nil {
return nil, err
}
return &quotaFile{File: f, remaining: q.remaining}, nil
}
// quotaFile fails writes once the shared byte budget is exhausted.
type quotaFile struct {
afero.File
remaining *int64
}
func (q *quotaFile) Write(p []byte) (int, error) {
if *q.remaining <= 0 {
return 0, errNoSpace
}
allowed := min(int64(len(p)), *q.remaining)
n, err := q.File.Write(p[:allowed])
*q.remaining -= int64(n)
if err != nil {
return n, err
}
if int64(n) < int64(len(p)) {
return n, errNoSpace
}
return n, nil
}
// assertNoCorruptFiles fails if any file that made it to the restore
// target holds content that differs from the original: a failed restore
// may leave a file absent, but must never leave wrong bytes presenting
// as the real file.
func assertNoCorruptFiles(
t *testing.T, fs afero.Fs, restoreDir string, testFiles map[string][]byte,
) {
t.Helper()
for origPath, expected := range testFiles {
restoredPath := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restoredPath)
if err != nil {
if os.IsNotExist(err) {
continue
}
require.NoError(t, err)
}
assert.Equalf(t, expected, got,
"restored file %s holds corrupt content", origPath)
}
}
internal/vaultik/prune.go
+23 -9
View File
@@ -167,6 +167,12 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
// collectReferencedBlobs downloads all manifests and returns the set of
// referenced blob hashes.
//
// Every manifest must be read successfully. A manifest that cannot be
// downloaded or decoded means its snapshot's blobs are unknown, so
// treating them as unreferenced would let prune delete data a snapshot
// still needs. Rather than risk that silent loss, any failure returns an
// error naming the remote key and prune deletes nothing.
func (v *Vaultik) collectReferencedBlobs() (map[string]bool, error) {
log.Info("Listing remote snapshots")
// IDs returned by listUniqueSnapshotIDs are remote keys (hashed
@@ -179,27 +185,22 @@ func (v *Vaultik) collectReferencedBlobs() (map[string]bool, error) {
log.Info("Found manifests in remote storage", "count", len(remoteKeys))
allBlobsReferenced := make(map[string]bool)
manifestCount := 0
for _, remoteKey := range remoteKeys {
log.Debug("Processing manifest", "remote_key", remoteKey)
manifest, err := v.downloadManifestByKey(remoteKey)
if err != nil {
log.Error("Failed to download manifest", "remote_key", remoteKey, "error", err)
continue
return nil, fmt.Errorf("reading manifest %s: %w", remoteKey, err)
}
for _, blob := range manifest.Blobs {
allBlobsReferenced[blob.Hash] = true
}
manifestCount++
}
log.Info("Processed manifests",
"count", manifestCount, "unique_blobs_referenced", len(allBlobsReferenced))
"count", len(remoteKeys), "unique_blobs_referenced", len(allBlobsReferenced))
return allBlobsReferenced, nil
}
@@ -246,9 +247,22 @@ func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
}
parts := strings.Split(object.Key, "/")
if len(parts) == blobKeyParts && parts[0] == "blobs" {
allBlobs[parts[3]] = object.Size
if len(parts) != blobKeyParts || parts[0] != "blobs" {
continue
}
// The object name is read from the destination store and is not
// trusted. A name that is not a blob hash (e.g. a short or
// non-hex string) would panic the later hash[:2]/hash[2:4] path
// build, so skip it with a warning rather than delete it.
if !isBlobHash(parts[3]) {
log.Warn("Skipping non-conforming object under blobs/",
"key", object.Key)
continue
}
allBlobs[parts[3]] = object.Size
}
log.Info("Found blobs in storage", "count", len(allBlobs))
internal/vaultik/prune_count_test.go
+79
View File
@@ -0,0 +1,79 @@
package vaultik //nolint:testpackage // exercises unexported count helpers
import (
"context"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
)
// TestTableCountForReportSurfacesReadFailure is the regression guard for
// the discarded-error bug: getTableCount for a table its query cannot
// resolve must not silently become 0. A count that could not be read is
// reported as unknown, which a reader can tell apart from an empty table.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestTableCountForReportSurfacesReadFailure(t *testing.T) {
log.Initialize(log.Config{})
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
v := &Vaultik{DB: db}
v.SetContext(ctx)
// A table present in the schema reads as a real count.
blobs := v.tableCountForReport("blobs")
require.NotNil(t, blobs, "an existing table must read as a real count")
assert.Equal(t, int64(0), *blobs)
// A syntactically valid name the sanitizer accepts but whose table
// the query cannot resolve is the exact shape #96 describes: a
// would-be loud failure that used to be discarded into a 0.
_, err = v.getTableCount("snapshots_missing")
require.Error(t, err, "a query against a nonexistent table must fail")
missing := v.tableCountForReport("snapshots_missing")
assert.Nil(t, missing, "a failed read is unknown, not a count")
// The rendered count for a failed read must say unknown, never 0.
assert.Equal(t, countUnknown, countText(missing))
assert.NotEqual(t, "0", countText(missing))
}
// TestCountTextDistinguishesEmptyFromUnknown pins the distinction the
// output has to preserve: 0 means the table was empty, "unknown" means
// the count could not be read.
func TestCountTextDistinguishesEmptyFromUnknown(t *testing.T) {
t.Parallel()
zero := int64(0)
seven := int64(7)
assert.Equal(t, "0", countText(&zero))
assert.Equal(t, "7", countText(&seven))
assert.Equal(t, countUnknown, countText(nil))
}
// TestCountDiffUnknownWhenEitherSideUnknown checks that a delta computed
// from an unreadable count is itself unknown rather than a plausible
// number.
func TestCountDiffUnknownWhenEitherSideUnknown(t *testing.T) {
t.Parallel()
before := int64(10)
after := int64(3)
require.NotNil(t, countDiff(&before, &after))
assert.Equal(t, int64(7), *countDiff(&before, &after))
assert.Nil(t, countDiff(nil, &after), "unknown before yields unknown delta")
assert.Nil(t, countDiff(&before, nil), "unknown after yields unknown delta")
assert.Nil(t, countDiff(nil, nil))
}
internal/vaultik/prune_manifest_safety_test.go
+47
View File
@@ -0,0 +1,47 @@
package vaultik_test
import (
"bytes"
"context"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestPruneBlobs_UnreadableManifestDeletesNothing is the regression guard
// for issue #157: prune identifies referenced blobs by reading every
// snapshot's manifest, and a manifest it cannot decode used to be logged
// and skipped. Blobs referenced only by that snapshot then looked
// unreferenced and were deleted, with a zero exit — silent backup loss,
// made worse by `snapshot create --prune` running unattended with force.
//
// The single blob here is referenced only by the snapshot whose manifest
// is corrupt, so the old behaviour would delete it and succeed. Prune
// must instead delete nothing and return an error.
func TestPruneBlobs_UnreadableManifestDeletesNothing(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
ctx := context.Background()
blobKey := "blobs/" + testBlobHashA[:2] + "/" + testBlobHashA[2:4] +
"/" + testBlobHashA
require.NoError(t, env.store.Put(ctx, blobKey,
bytes.NewReader([]byte("blob-bytes"))))
// A manifest at the path prune reads, but with contents it cannot
// decode.
require.NoError(t, env.store.Put(ctx,
"metadata/corruptkey/manifest.json.zst",
bytes.NewReader([]byte("not a valid manifest"))))
err := env.v.PruneBlobs(&vaultik.PruneOptions{Force: true})
require.Error(t, err, "prune must fail when a manifest cannot be read")
assert.True(t, env.store.hasKey(blobKey),
"no blob may be deleted when a manifest is unreadable")
}
internal/vaultik/purge_local_remote_consistency_test.go
+146
View File
@@ -0,0 +1,146 @@
package vaultik_test
import (
"bytes"
"context"
"database/sql"
"strings"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// setupConsistencyTest builds a Vaultik whose local database and mock
// remote both hold the given snapshots. Remote metadata is stored under
// the production layout, metadata/<RemoteSnapshotKey(id)>/manifest.json.zst.
// It returns the instance and the mock so a test can inspect the remote.
func setupConsistencyTest(
t *testing.T, snapshotIDs []string,
) (*vaultik.Vaultik, *MockStorer) {
t.Helper()
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
for _, id := range snapshotIDs {
parts := strings.Split(id, "_")
startedAt, err := time.Parse(time.RFC3339, parts[len(parts)-1])
require.NoError(t, err, "parsing timestamp from snapshot ID %q", id)
completedAt := startedAt.Add(5 * time.Minute)
snap := &database.Snapshot{
ID: types.SnapshotID(id),
Hostname: testHostname,
VaultikVersion: testLabel,
StartedAt: startedAt,
CompletedAt: &completedAt,
}
err = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return repos.Snapshots.Create(ctx, tx, snap)
})
require.NoError(t, err, "creating snapshot %s", id)
metadataKey := "metadata/" + snapshot.RemoteSnapshotKey(id) +
"/manifest.json.zst"
err = mockStorage.Put(ctx, metadataKey, strings.NewReader("stub"))
require.NoError(t, err)
}
v := &vaultik.Vaultik{
Storage: mockStorage,
Repositories: repos,
DB: db,
Stdout: &bytes.Buffer{},
Stderr: &bytes.Buffer{},
Stdin: &bytes.Buffer{},
}
v.SetContext(ctx)
return v, mockStorage
}
func remoteHasSnapshot(t *testing.T, m *MockStorer, id string) bool {
t.Helper()
prefix := "metadata/" + snapshot.RemoteSnapshotKey(id) + "/"
keys, err := m.List(context.Background(), prefix)
require.NoError(t, err)
return len(keys) > 0
}
// TestPurgeKeepsRemotelyBackedLocalRows guards against issue #160
// (https://git.eeqj.de/sneak/vaultik/issues/160): purge reconciles local
// rows against the remote first, and that step compared human snapshot IDs
// against the hashed remote directory names, which never match — so it
// deleted every local record and the purge itself then removed nothing.
//
// With every snapshot still present remotely and nothing old enough to
// purge, all local rows must survive the reconcile untouched.
func TestPurgeKeepsRemotelyBackedLocalRows(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ids := []string{snapHomeT0, snapHomeT1, snapSystemT0}
v, _ := setupConsistencyTest(t, ids)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
// 100 years: nothing is old enough to delete, so the reconcile
// is the only thing that touches the rows.
OlderThan: "36500d",
Force: true,
})
require.NoError(t, err)
remaining := listRemainingSnapshots(t, v)
assert.Len(t, remaining, len(ids),
"remotely-backed local rows must survive the reconcile")
assert.Contains(t, remaining, snapHomeT0)
assert.Contains(t, remaining, snapHomeT1)
assert.Contains(t, remaining, snapSystemT0)
}
// TestPurgeRemovesLocalAndRemoteTogether proves the two halves stay
// consistent: a purged snapshot is gone both locally and remotely, while a
// retained one keeps both. Before the fix, the reconcile dropped every
// local row yet the remote metadata was left in place.
func TestPurgeRemovesLocalAndRemoteTogether(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ids := []string{snapHomeT0, snapHomeT1, snapSystemT0}
v, mock := setupConsistencyTest(t, ids)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.NoError(t, err)
// Keep latest per name: newest home and the lone system are kept.
remaining := listRemainingSnapshots(t, v)
assert.ElementsMatch(t, []string{snapHomeT1, snapSystemT0}, remaining)
// Local and remote agree: the older home snapshot is gone from both,
// the retained ones are present in both.
assert.False(t, remoteHasSnapshot(t, mock, snapHomeT0),
"purged snapshot must also be removed remotely")
assert.True(t, remoteHasSnapshot(t, mock, snapHomeT1),
"retained snapshot must remain remotely")
assert.True(t, remoteHasSnapshot(t, mock, snapSystemT0),
"retained snapshot must remain remotely")
}
internal/vaultik/purge_per_name_test.go
+6 -2
View File
@@ -12,6 +12,7 @@ import (
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -60,8 +61,11 @@ func setupPurgeTest(t *testing.T, snapshotIDs []string) *vaultik.Vaultik {
})
require.NoError(t, err, "creating snapshot %s", id)
// Create remote metadata stub so syncWithRemote keeps it
metadataKey := "metadata/" + id + "/manifest.json.zst"
// Create the remote metadata stub under the production layout so
// syncWithRemote keeps the local row. Production stores metadata
// under the hashed remote key, not the human snapshot ID.
metadataKey := "metadata/" + snapshot.RemoteSnapshotKey(id) +
"/manifest.json.zst"
err = mockStorage.Put(ctx, metadataKey, strings.NewReader("stub"))
require.NoError(t, err)
}
internal/vaultik/restore.go
+368 -97
View File
@@ -1,7 +1,6 @@
package vaultik
import (
"bytes"
"context"
"crypto/sha256"
"encoding/hex"
@@ -11,6 +10,7 @@ import (
"math"
"os"
"path/filepath"
"strings"
"time"
"filippo.io/age"
@@ -29,19 +29,47 @@ var (
errDecryptionKeyRequired = errors.New(
"decryption key required for restore\n\n" +
"Set the VAULTIK_AGE_SECRET_KEY environment variable to your " +
"age private key:\n" +
" export VAULTIK_AGE_SECRET_KEY='AGE-SECRET-KEY-...'")
"age private key file:\n" +
" export VAULTIK_AGE_SECRET_KEY=\"$(cat vaultik_backup_private_key.txt)\"")
// errInvalidAgeSecretKey is returned when the configured key does not
// parse as any age identity. It names the source but never the value,
// which is secret, so the message is safe to print and log.
errInvalidAgeSecretKey = errors.New(
"configured age secret key holds no usable age identity")
errBlobMissingFromIndex = errors.New("blob hash missing from blob index")
errChunkNotInAnyBlob = errors.New("chunk not found in any blob")
errBlobIDNotInHashIndex = errors.New("blob id missing from hash index")
errShortChunkRead = errors.New("short read")
errRestorePathEscapesTarget = errors.New(
"refusing to restore path outside the target directory")
errTrailingRestoreData = errors.New(
"restored file has trailing data after its last chunk")
errRestoreIncomplete = errors.New(
"restore loop ended with files still pending")
errSnapshotDBMismatch = errors.New(
"decrypted database is not the requested snapshot")
// errEmptySnapshotDB is returned when the decrypted metadata database has
// zero length, which happens when the object was truncated or replaced
// with an empty payload. Rejected before any schema is built on it.
errEmptySnapshotDB = errors.New("decrypted snapshot database is empty")
)
// snapshotDBFilename is the name the decrypted snapshot database is
// written under inside its private temp directory.
const snapshotDBFilename = "snapshot.db"
// restoreDirMode is the permission mode for directories created while
// restoring (parent directories and the target root; restored
// directories themselves get their stored mode).
const restoreDirMode = 0o755
// restoreFileMode is the restrictive mode a regular file is created with
// during restore. Content is written while the file holds this mode; the
// stored mode is applied only after the file is fully written and closed,
// so a file whose stored mode is restrictive is never briefly readable by
// other local users while its content is being written.
const restoreFileMode = 0o600
// sweepIntervalDivisor sets the sweeper threshold to one N-th of the
// configured blob size limit.
const sweepIntervalDivisor = 100
@@ -77,7 +105,7 @@ type RestoreResult struct {
func (v *Vaultik) Restore(opts *RestoreOptions) error {
startTime := time.Now()
identity, err := v.prepareRestoreIdentity()
identities, err := v.restoreIdentities()
if err != nil {
return err
}
@@ -91,7 +119,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
// Step 1: Download and decrypt the snapshot metadata database
log.Info("Downloading snapshot metadata...")
tempDB, err := v.downloadSnapshotDB(opts.SnapshotID, identity)
tempDB, tempDir, err := v.downloadSnapshotDB(opts.SnapshotID, identities)
if err != nil {
return fmt.Errorf("downloading snapshot database: %w", err)
}
@@ -101,10 +129,11 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
if err != nil {
log.Debug("Failed to close temp database", "error", err)
}
// Clean up temp file
err = v.Fs.Remove(tempDB.Path())
// Remove the whole private directory, so the decrypted database
// and any SQLite side files it produced are gone on every path.
err = v.Fs.RemoveAll(tempDir)
if err != nil {
log.Debug("Failed to remove temp database", "error", err)
log.Debug("Failed to remove temp database directory", "error", err)
}
}()
@@ -139,7 +168,7 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
}
// Step 5: Restore files
result, err := v.restoreAllFiles(files, repos, opts, identity, chunkToBlobMap)
result, err := v.restoreAllFiles(files, repos, opts, identities, chunkToBlobMap)
if err != nil {
return err
}
@@ -200,21 +229,28 @@ func (v *Vaultik) finishRestore(
return nil
}
// prepareRestoreIdentity validates that an age secret key is configured
// and parses it.
//
//nolint:ireturn // age.Identity is the decryption abstraction by design
func (v *Vaultik) prepareRestoreIdentity() (age.Identity, error) {
// restoreIdentities parses the configured age secret key once into every
// identity it contains. The value may be a single key line or a whole
// age-keygen file with several identities; all of them are returned so
// blobgen (via age.Decrypt) can read a blob encrypted to any of their
// recipients. This is the first step of both restore and deep verify, so
// a missing or unparseable key fails before anything is downloaded. The
// error names the configuration source but never the key value.
func (v *Vaultik) restoreIdentities() ([]age.Identity, error) {
if v.Config.AgeSecretKey == "" {
return nil, errDecryptionKeyRequired
}
identity, err := age.ParseX25519Identity(v.Config.AgeSecretKey)
// age.ParseIdentities skips comment and blank lines and rejects a
// malformed key. Its error can quote the offending line, so it is not
// wrapped here — that would leak the secret into the message.
identities, err := age.ParseIdentities(strings.NewReader(v.Config.AgeSecretKey))
if err != nil {
return nil, fmt.Errorf("parsing age secret key: %w", err)
return nil, fmt.Errorf("%w (source: %s)",
errInvalidAgeSecretKey, v.Config.AgeSecretKeySourceName())
}
return identity, nil
return identities, nil
}
// restoreAllFiles processes files in blob-locality order: drain every
@@ -227,7 +263,7 @@ func (v *Vaultik) restoreAllFiles(
files []*database.File,
repos *database.Repositories,
opts *RestoreOptions,
identity age.Identity,
identities []age.Identity,
chunkToBlobMap map[string]*database.BlobChunk,
) (*RestoreResult, error) {
result := &RestoreResult{}
@@ -281,7 +317,7 @@ func (v *Vaultik) restoreAllFiles(
ctx: v.ctx,
repos: repos,
opts: opts,
identity: identity,
identities: identities,
chunkToBlobMap: chunkToBlobMap,
blobByHash: blobByHash,
blobIDToHash: blobIDToHash,
@@ -357,6 +393,13 @@ func (v *Vaultik) runRestoreLoop(
totalBytesExpected, startTime, &lastStatusTime)
}
// The loop above stops as soon as nothing is ready and nothing more
// can be downloaded. If files still remain, they were abandoned
// rather than restored; fail loudly instead of reporting success.
if plan.hasPending() {
return errRestoreIncomplete
}
return nil
}
@@ -371,20 +414,26 @@ func (v *Vaultik) runRestoreLoop(
func (s *restoreSession) downloadNextBlobSet(plan *restorePlan) (bool, error) {
s.sweeper.sweep()
next := plan.pickNextDownload()
if next.IsZero() {
next, ok := plan.pickNextDownload()
if !ok {
return false, nil
}
for _, hash := range plan.blobsNeeded(next) {
blob, ok := s.blobByHash[hash]
if !ok {
return false, fmt.Errorf("%w: %s", errBlobMissingFromIndex, hash[:16])
// Stop between blobs on cancel so an interrupt ends the download
// phase promptly rather than fetching the rest of the set.
if s.ctx.Err() != nil {
return false, s.ctx.Err()
}
err := s.downloadBlobToCache(hash, blob.CompressedSize)
blob, ok := s.blobByHash[hash]
if !ok {
return false, fmt.Errorf("%w: %s", errBlobMissingFromIndex, shortHash(hash))
}
err := s.downloadBlobToCache(hash, blob.CompressedSize, blob.UncompressedSize)
if err != nil {
return false, fmt.Errorf("downloading blob %s: %w", hash[:16], err)
return false, fmt.Errorf("downloading blob %s: %w", shortHash(hash), err)
}
s.result.BlobsDownloaded++
@@ -428,6 +477,16 @@ func (v *Vaultik) buildBlobIndexes(
blobByHash := make(map[string]*database.Blob, len(blobsByID))
for id, blob := range blobsByID {
hash := blob.Hash.String()
// The snapshot database is untrusted. A hash that is not 64
// lowercase hex characters could steer a later fetch to a path
// outside the cache directory, so reject it here, before any
// blob is downloaded.
if !isBlobHash(hash) {
return nil, nil, fmt.Errorf(
"%w: %s", errInvalidBlobHash, shortHash(hash))
}
blobIDToHash[id] = hash
blobByHash[hash] = blob
}
@@ -577,80 +636,145 @@ func (v *Vaultik) handleRestoreVerification(
}
// downloadSnapshotDB downloads and decrypts the snapshot metadata
// database. The snapshotID is the human ID; we hash it to the remote
// key for the storage path.
// database. The identifier is resolved to the snapshot's remote key: a
// human ID is hashed, and a remote key (or its abbreviation, as printed
// for a remote-only snapshot) is used as-is, so a host with no local
// index can restore the snapshots it can only see on the store.
func (v *Vaultik) downloadSnapshotDB(
snapshotID string, identity age.Identity,
) (*database.DB, error) {
snapshotID string, identities []age.Identity,
) (*database.DB, string, error) {
remoteKey, err := v.resolveSnapshotRemoteKey(snapshotID)
if err != nil {
return nil, "", err
}
// Download encrypted database from storage
dbKey := fmt.Sprintf("metadata/%s/db.zst.age",
snapshot.RemoteSnapshotKey(snapshotID))
dbKey := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
reader, err := v.Storage.Get(v.ctx, dbKey)
if err != nil {
return nil, fmt.Errorf("downloading %s: %w", dbKey, err)
return nil, "", fmt.Errorf("downloading %s: %w", dbKey, err)
}
defer func() { _ = reader.Close() }()
// Read all data
encryptedData, err := io.ReadAll(reader)
// Decrypt and decompress straight from the storage stream, then stream
// the plaintext to a temp file. Neither the encrypted bytes nor the
// decrypted database is ever held whole in memory; a snapshot database
// can be large.
blobReader, err := blobgen.NewReader(reader, identities...)
if err != nil {
return nil, fmt.Errorf("reading encrypted data: %w", err)
}
log.Debug("Downloaded encrypted database",
"size", ubytes(int64(len(encryptedData))))
// Decrypt and decompress using blobgen.Reader
blobReader, err := blobgen.NewReader(bytes.NewReader(encryptedData), identity)
if err != nil {
return nil, fmt.Errorf("creating decryption reader: %w", err)
return nil, "", fmt.Errorf("creating decryption reader: %w", err)
}
defer func() { _ = blobReader.Close() }()
// Read the binary SQLite database
dbData, err := io.ReadAll(blobReader)
db, tempDir, err := v.materializeSnapshotDB(blobReader)
if err != nil {
return nil, fmt.Errorf("decrypting and decompressing: %w", err)
return nil, "", err
}
log.Debug("Decrypted database", "size", ubytes(int64(len(dbData))))
// Create a temporary database file and write the binary SQLite data directly
tempFile, err := afero.TempFile(v.Fs, "", "vaultik-restore-*.db")
// Confirm the decrypted database really is the snapshot named by
// remoteKey before any files are read from it. On mismatch, close the
// database and remove its private directory so nothing is left behind.
err = v.verifySnapshotDBIdentity(db, snapshotID, remoteKey)
if err != nil {
return nil, fmt.Errorf("creating temp file: %w", err)
_ = db.Close()
_ = v.Fs.RemoveAll(tempDir)
return nil, "", err
}
tempPath := tempFile.Name()
// Write the binary SQLite database directly
_, err = tempFile.Write(dbData)
if err != nil {
_ = tempFile.Close()
_ = v.Fs.Remove(tempPath)
return nil, fmt.Errorf("writing database file: %w", err)
return db, tempDir, nil
}
err = tempFile.Close()
if err != nil {
_ = v.Fs.Remove(tempPath)
// verifySnapshotDBIdentity confirms the decrypted metadata database really
// is the snapshot named by remoteKey. age decryption proves the database
// is readable, not that the object served at
// metadata/<remoteKey>/db.zst.age is the snapshot that was requested: an
// attacker who swaps in another valid db.zst.age (which needs no key
// material) would otherwise redirect restore and deep verify to a
// different snapshot's contents. The exported per-snapshot database holds
// exactly one snapshot row, and a snapshot's remote key is derived from
// that row's ID, so the database is the requested one exactly when its
// sole snapshot hashes back to remoteKey. Comparing the requested
// identifier directly would not do: it may be a remote-key prefix a
// recovery host uses in place of a human snapshot ID it cannot know.
func (v *Vaultik) verifySnapshotDBIdentity(
db *database.DB, requested, remoteKey string,
) error {
repos := database.NewRepositories(db)
return nil, fmt.Errorf("closing temp file: %w", err)
snap, err := repos.Snapshots.GetOnlySnapshot(v.ctx)
if err != nil {
return fmt.Errorf("checking identity of database for %s: %w", requested, err)
}
log.Debug("Created restore database", "path", tempPath)
// Open the database
db, err := database.New(v.ctx, tempPath)
if err != nil {
return nil, fmt.Errorf("opening restore database: %w", err)
if snapshot.RemoteSnapshotKey(snap.ID.String()) != remoteKey {
return fmt.Errorf("%w: requested %s but the database is snapshot %s",
errSnapshotDBMismatch, requested, snap.ID)
}
return db, nil
return nil
}
// materializeSnapshotDB streams the decrypted snapshot database into a
// fresh private (0700) temp directory and opens the file read-only. The
// database is copied through an io.Copy buffer rather than read whole into
// memory. On any failure it removes the directory before returning, so no
// decrypted metadata is left on disk when the copy is interrupted or the
// payload is damaged. On success the returned directory is the caller's to
// remove.
func (v *Vaultik) materializeSnapshotDB(
dbReader io.Reader,
) (*database.DB, string, error) {
tempDir, err := afero.TempDir(v.Fs, "", "vaultik-restore-")
if err != nil {
return nil, "", fmt.Errorf("creating temp directory: %w", err)
}
success := false
defer func() {
if !success {
_ = v.Fs.RemoveAll(tempDir)
}
}()
dbPath := filepath.Join(tempDir, snapshotDBFilename)
dbFile, err := v.Fs.OpenFile(
dbPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, restoreFileMode)
if err != nil {
return nil, "", fmt.Errorf("creating database file: %w", err)
}
written, copyErr := io.Copy(dbFile, dbReader)
closeErr := dbFile.Close()
if copyErr != nil {
return nil, "", fmt.Errorf("writing database file: %w", copyErr)
}
if closeErr != nil {
return nil, "", fmt.Errorf("closing database file: %w", closeErr)
}
log.Debug("Created restore database", "path", dbPath, "size", ubytes(written))
// Reject an empty database before OpenReadOnly builds a schema on it.
if written == 0 {
return nil, "", errEmptySnapshotDB
}
db, err := database.OpenReadOnly(v.ctx, dbPath)
if err != nil {
return nil, "", fmt.Errorf("opening restore database: %w", err)
}
success = true
return db, tempDir, nil
}
// getFilesToRestore returns the list of files to restore based on path filters
@@ -739,7 +863,7 @@ type restoreSession struct {
ctx context.Context //nolint:containedctx // per-restore state by design
repos *database.Repositories
opts *RestoreOptions
identity age.Identity
identities []age.Identity
chunkToBlobMap map[string]*database.BlobChunk
blobByHash map[string]*database.Blob
blobIDToHash map[string]string
@@ -755,13 +879,85 @@ type restoreSession struct {
runningAsRoot bool
}
// containedRestorePath resolves rel — a path read from the snapshot
// database — to its location under targetDir and confirms the write will
// stay inside the target.
//
// age decryption proves a snapshot is readable, not that it is honest, so
// every stored path is treated as hostile. rel is rejected unless
// filepath.IsLocal accepts it once the leading separator is stripped:
// stored paths are absolute and the join to targetDir drops that
// separator, so "/etc/passwd" is judged as the relative "etc/passwd" it
// becomes on disk. This bars "..", absolute, and empty paths.
//
// A stored symlink whose target points outside the tree is still honest
// (and restored verbatim), but a later entry must not be written through
// it. Each existing ancestor directory below the target is therefore
// Lstat'ed and a symlink among them is refused. The leaf itself is not
// traversed: honest snapshots restore symlinks at leaf positions, and the
// unique-path constraint keeps a leaf from being both a symlink and a
// regular file. The target directory itself may be a symlink; only
// components below it are checked.
func containedRestorePath(fs afero.Fs, targetDir, rel string) (string, error) {
local := strings.TrimPrefix(rel, string(filepath.Separator))
if !filepath.IsLocal(local) {
return "", fmt.Errorf("%w: %s", errRestorePathEscapesTarget, rel)
}
local = filepath.Clean(local)
targetPath := filepath.Join(targetDir, local)
relDir := filepath.Dir(local)
if relDir == "." {
return targetPath, nil
}
current := targetDir
for component := range strings.SplitSeq(relDir, string(filepath.Separator)) {
current = filepath.Join(current, component)
info, err := lstatIfPossible(fs, current)
if err != nil {
if os.IsNotExist(err) {
continue
}
return "", fmt.Errorf("checking restore path %s: %w", current, err)
}
if info.Mode()&os.ModeSymlink != 0 {
return "", fmt.Errorf("%w: %s descends through symlink %s",
errRestorePathEscapesTarget, rel, current)
}
}
return targetPath, nil
}
// lstatIfPossible performs a symlink-aware stat when the filesystem
// supports it. afero.OsFs does; MemMapFs, which has no symlinks, reports
// that Lstat was not used and its result never carries ModeSymlink.
func lstatIfPossible(fs afero.Fs, name string) (os.FileInfo, error) {
if lstater, ok := fs.(afero.Lstater); ok {
info, _, err := lstater.LstatIfPossible(name)
return info, err
}
return fs.Stat(name)
}
// restoreFile dispatches to the right per-kind restorer.
func (s *restoreSession) restoreFile(file *database.File) error {
targetPath := filepath.Join(s.opts.TargetDir, file.Path.String())
targetPath, err := containedRestorePath(
s.v.Fs, s.opts.TargetDir, file.Path.String())
if err != nil {
return err
}
parentDir := filepath.Dir(targetPath)
err := s.v.Fs.MkdirAll(parentDir, restoreDirMode)
err = s.v.Fs.MkdirAll(parentDir, restoreDirMode)
if err != nil {
return fmt.Errorf("creating parent directory: %w", err)
}
@@ -809,6 +1005,13 @@ func (s *restoreSession) restoreDirectory(
return fmt.Errorf("creating directory: %w", err)
}
// MkdirAll applies the process umask, so chmod to the exact stored
// mode. A failure here is non-fatal.
err = s.v.Fs.Chmod(targetPath, os.FileMode(file.Mode))
if err != nil {
log.Debug("Failed to set permissions", "path", targetPath, "error", err)
}
s.applyFileMetadata(file, targetPath)
s.result.FilesRestored++
@@ -816,25 +1019,22 @@ func (s *restoreSession) restoreDirectory(
return nil
}
// applyFileMetadata applies stored permissions, ownership (when running
// as root on a real filesystem), and mtime to a restored path. Failures
// are logged at debug level and do not abort the restore.
// applyFileMetadata applies ownership (when running as root on a real
// filesystem) and mtime to a restored path. Permission mode is applied
// separately by each caller, with different failure handling, so it is
// not touched here. Failures are logged at debug level and do not abort
// the restore.
func (s *restoreSession) applyFileMetadata(file *database.File, targetPath string) {
err := s.v.Fs.Chmod(targetPath, os.FileMode(file.Mode))
if err != nil {
log.Debug("Failed to set permissions", "path", targetPath, "error", err)
}
if s.runningAsRoot {
if _, ok := s.v.Fs.(*afero.OsFs); ok {
err = os.Chown(targetPath, int(file.UID), int(file.GID))
err := os.Chown(targetPath, int(file.UID), int(file.GID))
if err != nil {
log.Debug("Failed to set ownership", "path", targetPath, "error", err)
}
}
}
err = s.v.Fs.Chtimes(targetPath, file.MTime, file.MTime)
err := s.v.Fs.Chtimes(targetPath, file.MTime, file.MTime)
if err != nil {
log.Debug("Failed to set mtime", "path", targetPath, "error", err)
}
@@ -868,17 +1068,30 @@ func (s *restoreSession) restoreRegularFile(
t0 = time.Now()
outFile, err := s.v.Fs.Create(targetPath)
// Remove any existing entry, then create the file with a restrictive
// mode via O_EXCL. The stored mode is applied only after the content
// is written and the file closed, so a file whose stored mode is
// restrictive is never briefly readable by other local users while
// its content is written. Removing first (rather than failing on a
// leftover file) matches the documented behaviour that re-running
// restore overwrites partial output.
_ = s.v.Fs.Remove(targetPath)
outFile, err := s.v.Fs.OpenFile(
targetPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, restoreFileMode)
createDur := time.Since(t0)
if err != nil {
return fmt.Errorf("creating output file: %w", err)
}
defer func() { _ = outFile.Close() }()
bytesWritten, timings, err := s.writeFileChunks(outFile, fileChunks)
if err != nil {
// Do not leave a partial file behind.
_ = outFile.Close()
s.removePartialRestore(targetPath)
return err
}
@@ -896,9 +1109,12 @@ func (s *restoreSession) restoreRegularFile(
err = outFile.Close()
if err != nil {
s.removePartialRestore(targetPath)
return fmt.Errorf("closing output file: %w", err)
}
s.applyRestoredFileMode(file, targetPath)
s.applyFileMetadata(file, targetPath)
s.result.FilesRestored++
@@ -909,6 +1125,31 @@ func (s *restoreSession) restoreRegularFile(
return nil
}
// applyRestoredFileMode applies the stored permission bits to a
// just-written regular file (created with restoreFileMode). A failure is
// a user-visible warning, not a fatal error: the file's content is
// intact and it remains at the restrictive create-time mode, so the
// restore is not aborted or discarded over it.
func (s *restoreSession) applyRestoredFileMode(
file *database.File, targetPath string,
) {
err := s.v.Fs.Chmod(targetPath, os.FileMode(file.Mode))
if err != nil {
s.v.UI.Warningf("Failed to set mode %s on %s: %v",
os.FileMode(file.Mode).Perm(), s.v.UI.Path(targetPath), err)
}
}
// removePartialRestore deletes a restore output file whose write did not
// complete, so a failed restore never leaves a partial file behind.
func (s *restoreSession) removePartialRestore(targetPath string) {
err := s.v.Fs.Remove(targetPath)
if err != nil {
log.Debug("Failed to remove partial restore file",
"path", targetPath, "error", err)
}
}
// writeFileChunks streams each of the file's chunks from the blob disk
// cache into outFile, crediting restored bytes to the sweeper as it
// goes. Returns the bytes written plus per-phase timing accumulators.
@@ -921,6 +1162,12 @@ func (s *restoreSession) writeFileChunks(
)
for _, fc := range fileChunks {
// Stop between chunks on cancel so an interrupt does not keep
// writing a large file after the operation has been told to stop.
if s.ctx.Err() != nil {
return bytesWritten, timings, s.ctx.Err()
}
chunkHashStr := fc.ChunkHash.String()
blobChunk, ok := s.chunkToBlobMap[chunkHashStr]
@@ -973,12 +1220,12 @@ func (s *restoreSession) writeFileChunks(
// size, which is what makes multi-GB blobs tractable on machines with
// less RAM than the blob.
func (s *restoreSession) downloadBlobToCache(
blobHash string, expectedSize int64,
blobHash string, compressedSize, uncompressedSize int64,
) error {
start := time.Now()
t0 := time.Now()
rc, err := s.v.FetchAndDecryptBlob(s.ctx, blobHash, expectedSize, s.identity)
rc, err := s.v.FetchAndDecryptBlob(s.ctx, blobHash, uncompressedSize, s.identities...)
fetchSetupDur := time.Since(t0)
if err != nil {
@@ -990,17 +1237,25 @@ func (s *restoreSession) downloadBlobToCache(
streamDur := time.Since(t0)
closeErr := rc.Close()
// closeErr carries the blob's hash-verification result (a mismatch,
// or the stream not being fully read). On any failure, drop the
// cache entry so a blob that failed verification is never read back
// as if it were valid.
if copyErr != nil {
s.blobCache.Delete(blobHash)
return copyErr
}
if closeErr != nil {
s.blobCache.Delete(blobHash)
return closeErr
}
log.Debug("Streamed blob into disk cache",
"hash", blobHash[:16],
"compressed_bytes", expectedSize,
"compressed_bytes", compressedSize,
"plaintext_bytes", written,
"ms_total", time.Since(start).Milliseconds(),
"ms_fetch_setup", fetchSetupDur.Milliseconds(),
@@ -1057,17 +1312,22 @@ func (v *Vaultik) verifyRestoredFiles(
return ctx.Err()
}
targetPath := filepath.Join(targetDir, file.Path.String())
targetPath, err := containedRestorePath(v.Fs, targetDir, file.Path.String())
if err == nil {
var bytesVerified int64
bytesVerified, err = v.verifyFile(ctx, repos, file, targetPath)
if err == nil {
result.FilesVerified++
result.BytesVerified += bytesVerified
}
}
bytesVerified, err := v.verifyFile(ctx, repos, file, targetPath)
if err != nil {
log.Error("File verification failed", "path", file.Path, "error", err)
result.FilesFailed++
result.FailedFiles = append(result.FailedFiles, file.Path.String())
} else {
result.FilesVerified++
result.BytesVerified += bytesVerified
}
bytesProcessed += file.Size
@@ -1157,6 +1417,17 @@ func (v *Vaultik) verifyFile(
bytesVerified += int64(n)
}
// The stored chunks account for the whole file, so the reader must
// be at EOF now. Trailing bytes past the last chunk are corruption
// the per-chunk loop cannot see.
extra := make([]byte, 1)
n, err := f.Read(extra)
if n != 0 || !errors.Is(err, io.EOF) {
return bytesVerified, fmt.Errorf("%w: file longer than its %d chunk(s)",
errTrailingRestoreData, len(fileChunks))
}
log.Debug("File verified",
"path", file.Path, "bytes", bytesVerified, "chunks", len(fileChunks))
internal/vaultik/restore_another_machine_test.go
+167
View File
@@ -0,0 +1,167 @@
package vaultik_test
import (
"bytes"
"context"
"io"
"path/filepath"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestRestoreOnAnotherMachine proves the disaster-recovery path: a host
// that has only the vaultik binary, the age secret key, and the storage
// credentials — no local index, a different hostname, and no
// age_recipients configured — can list, restore, and verify a snapshot
// straight from the destination store.
//
// The backup half writes a snapshot with one index and hostname. The
// restore half throws that index away entirely: a fresh, empty index and
// a config that shares nothing with the original but the storage location
// and the secret key. If restore or verify needed the original local
// index — or the human snapshot ID that only that index holds — this test
// could not run, because the recovery host can know neither.
func TestRestoreOnAnotherMachine(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024)
maxBlobSize := int64(512 * 1024)
sourceFiles := writeRecoverySourceTree(t, fs, dataDir, chunkSize)
ctx := context.Background()
// Backup host: one index, hostname test-host, age_recipients set.
// runFileStorageBackup closes the index before returning, so nothing
// below can lean on it.
_, storer, originalID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
// Recovery host: a fresh empty index, a different hostname, and no
// age_recipients — only the secret key and the same storage location.
recovery, stdout := newRecoveryHost(ctx, t, fs, storer)
// The recovery index really is empty. This is the assertion that makes
// the test a guard against restore quietly depending on the original
// index: if it did, an empty index would make restore fail.
localSnaps, err := recovery.Repositories.Snapshots.ListRecent(ctx, 100)
require.NoError(t, err)
require.Empty(t, localSnaps, "recovery host must start with no local index")
// List: the snapshot shows up as remote-only, identified by its remote
// key, with no recoverable human ID.
require.NoError(t, recovery.ListSnapshots(true))
rows := decodeListJSON(t, stdout.String())
require.Len(t, rows, 1)
remote := rows[0]
assert.False(t, remote.LocallyTracked, "snapshot must be remote-only here")
assert.Empty(t, remote.ID, "the human ID is unknown to the recovery host")
require.Len(t, remote.RemoteKey, 64)
assert.Equal(t, snapshot.RemoteSnapshotKey(originalID), remote.RemoteKey,
"the listed key is the hashed snapshot ID")
// Restore driven by the abbreviated identifier the table prints (the
// first 12 hex of the remote key), then deep-verify from the store
// keyed by the full remote key. Both are what a recovery host can know.
require.NoError(t, recovery.Restore(&vaultik.RestoreOptions{
SnapshotID: remote.RemoteKey[:12],
TargetDir: restoreDir,
Verify: true,
}))
require.NoError(t, recovery.RunDeepVerify(
remote.RemoteKey, &vaultik.VerifyOptions{Deep: true}))
assertRestoredTreeMatches(t, fs, restoreDir, sourceFiles)
}
// writeRecoverySourceTree writes a small source tree spanning several
// chunks (so restore reassembles real multi-chunk files) and returns the
// content keyed by absolute path.
func writeRecoverySourceTree(
t *testing.T, fs afero.Fs, dataDir string, chunkSize int64,
) map[string][]byte {
t.Helper()
sourceFiles := map[string][]byte{
filepath.Join(dataDir, "notes.txt"): []byte("recover me"),
filepath.Join(dataDir, "sub", "big.bin"): bytesPattern("big-", int(chunkSize*3)),
filepath.Join(dataDir, "sub", "small.bin"): bytesPattern("small-", 128),
}
for path, content := range sourceFiles {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
return sourceFiles
}
// newRecoveryHost builds the Vaultik a replacement machine would run: an
// empty in-memory index, a hostname different from the backup host, no
// age_recipients, and only the secret key plus the shared storer. It
// returns the instance and the buffer its stdout is wired to.
func newRecoveryHost(
ctx context.Context, t *testing.T, fs afero.Fs, storer storage.Storer,
) (*vaultik.Vaultik, *bytes.Buffer) {
t.Helper()
recoveryDB, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = recoveryDB.Close() })
stdout := &bytes.Buffer{}
recovery := &vaultik.Vaultik{
Config: &config.Config{
AgeSecretKey: testAgeSecretKey,
Hostname: "recovery-host",
},
Storage: storer,
Fs: fs,
Repositories: database.NewRepositories(recoveryDB),
DB: recoveryDB,
Stdout: stdout,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
recovery.SetContext(ctx)
return recovery, stdout
}
// assertRestoredTreeMatches byte-compares every restored file against its
// source content.
func assertRestoredTreeMatches(
t *testing.T, fs afero.Fs, restoreDir string, sourceFiles map[string][]byte,
) {
t.Helper()
for origPath, expected := range sourceFiles {
restored := filepath.Join(restoreDir, origPath)
got, err := afero.ReadFile(fs, restored)
require.NoErrorf(t, err, "restored file missing: %s", restored)
require.Truef(t, bytes.Equal(got, expected),
"byte mismatch for %s", origPath)
}
}
internal/vaultik/restore_containment_test.go
+175
View File
@@ -0,0 +1,175 @@
package vaultik //nolint:testpackage // drives unexported restore internals
import (
"context"
"io"
"os"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/ui"
)
// These tests exercise the path-containment guard that keeps restore from
// writing outside its target directory. age decryption proves only that a
// snapshot is readable, not that its recorded paths are honest, so restore
// treats every stored path as hostile: a compromised backed-up host could
// forge a snapshot that decrypts cleanly, and restore usually runs as root.
//
// They drive restoreAllFiles directly (rather than the full Restore, which
// downloads and decrypts the metadata database from storage) so a snapshot
// database with adversarial rows can be handed to the restore loop without
// the surrounding blob/storage machinery. Directory and symlink entries
// carry no chunks, so no blobs are needed.
// containmentDirMode marks a File row as a directory for the restore loop.
const containmentDirMode = uint32(os.ModeDir | 0o755)
// newContainmentVaultik builds the minimal Vaultik needed to run
// restoreAllFiles against fs.
func newContainmentVaultik(ctx context.Context, fs afero.Fs) *Vaultik {
v := &Vaultik{
Config: &config.Config{
BlobSizeLimit: config.Size(10 * 1024 * 1024),
},
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
// makeFiles inserts the given rows into a fresh in-memory snapshot database
// and returns them (with IDs assigned) plus the repositories.
func makeFiles(
ctx context.Context, t *testing.T, rows []*database.File,
) ([]*database.File, *database.Repositories) {
t.Helper()
db, err := database.New(ctx, filepath.Join(t.TempDir(), "index.sqlite"))
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
for _, f := range rows {
require.NoError(t, repos.Files.Create(ctx, nil, f))
}
return rows, repos
}
func TestRestoreRejectsPathTraversal(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tests := []struct {
name string
// rows are inserted in order; the escape entry is restored after
// any entry it depends on (the symlink case needs its link first).
rows func(outsideDir string) []*database.File
// escaped is the path, outside the target, that must not appear.
escaped func(tempDir, outsideDir string) string
}{
{
name: "relative dotdot",
rows: func(_ string) []*database.File {
return []*database.File{{
Path: "../escaped-relative",
Mode: containmentDirMode,
}}
},
escaped: func(tempDir, _ string) string {
return filepath.Join(tempDir, "escaped-relative")
},
},
{
name: "absolute with dotdot",
rows: func(_ string) []*database.File {
return []*database.File{{
Path: "/a/../../escaped-absolute",
Mode: containmentDirMode,
}}
},
escaped: func(tempDir, _ string) string {
return filepath.Join(tempDir, "escaped-absolute")
},
},
{
name: "child through symlink",
rows: func(outsideDir string) []*database.File {
return []*database.File{
// Restored first: an in-target symlink pointing out.
{Path: "linkdir", LinkTarget: types.FilePath(outsideDir)},
// Restored second: a child written through that link.
{Path: "linkdir/child", Mode: containmentDirMode},
}
},
escaped: func(_, outsideDir string) string {
return filepath.Join(outsideDir, "child")
},
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
fs := afero.NewOsFs()
tempDir := t.TempDir()
targetDir := filepath.Join(tempDir, "target")
outsideDir := filepath.Join(tempDir, "outside")
require.NoError(t, fs.MkdirAll(outsideDir, 0o755))
rows, repos := makeFiles(ctx, t, tc.rows(outsideDir))
v := newContainmentVaultik(ctx, fs)
_, err := v.restoreAllFiles(rows, repos,
&RestoreOptions{TargetDir: targetDir}, nil, nil)
require.ErrorIs(t, err, errRestorePathEscapesTarget)
escaped := tc.escaped(tempDir, outsideDir)
_, statErr := os.Lstat(escaped)
require.Truef(t, os.IsNotExist(statErr),
"restore wrote outside the target at %s", escaped)
})
}
}
// TestRestoreAllowsSymlinkPointingOutsideTree confirms the guard does not
// over-block: an honest snapshot may contain a symlink whose target lies
// outside the restored tree, and it must still be restored verbatim.
func TestRestoreAllowsSymlinkPointingOutsideTree(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
fs := afero.NewOsFs()
tempDir := t.TempDir()
targetDir := filepath.Join(tempDir, "target")
linkTarget := filepath.Join(tempDir, "outside", "data")
rows, repos := makeFiles(ctx, t, []*database.File{
{Path: "goodlink", LinkTarget: types.FilePath(linkTarget), MTime: time.Unix(0, 0)},
})
v := newContainmentVaultik(ctx, fs)
_, err := v.restoreAllFiles(rows, repos,
&RestoreOptions{TargetDir: targetDir}, nil, nil)
require.NoError(t, err)
got, err := os.Readlink(filepath.Join(targetDir, "goodlink"))
require.NoError(t, err)
require.Equal(t, linkTarget, got)
}
internal/vaultik/restore_identity_test.go
+108
View File
@@ -0,0 +1,108 @@
package vaultik //nolint:testpackage // exercises unexported restoreIdentities
import (
"bytes"
"io"
"testing"
"filippo.io/age"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/config"
)
// encryptBlobTo returns a blobgen blob of plaintext encrypted to exactly
// one recipient, so a decryptor succeeds only if it holds that recipient's
// identity.
func encryptBlobTo(t *testing.T, recipient string, plaintext []byte) []byte {
t.Helper()
var buf bytes.Buffer
writer, err := blobgen.NewWriter(&buf, 1, []string{recipient})
require.NoError(t, err)
_, err = writer.Write(plaintext)
require.NoError(t, err)
require.NoError(t, writer.Close())
return buf.Bytes()
}
// decryptBlobWith reads a blob back through the identities and returns its
// plaintext.
func decryptBlobWith(t *testing.T, blob []byte, identities []age.Identity) []byte {
t.Helper()
reader, err := blobgen.NewReader(bytes.NewReader(blob), identities...)
require.NoError(t, err)
plaintext, err := io.ReadAll(reader)
require.NoError(t, err)
require.NoError(t, reader.Close())
return plaintext
}
// TestRestoreIdentitiesAcceptsEveryIdentity proves a key file holding two
// identities yields both, so a blob encrypted only to the second
// recipient — the one the previous single-identity parse dropped — still
// decrypts.
func TestRestoreIdentitiesAcceptsEveryIdentity(t *testing.T) {
t.Parallel()
first, err := age.GenerateX25519Identity()
require.NoError(t, err)
second, err := age.GenerateX25519Identity()
require.NoError(t, err)
// A whole age-keygen-style file: comment lines plus two identity lines.
keyFile := "# public key: " + first.Recipient().String() + "\n" +
first.String() + "\n" +
"# public key: " + second.Recipient().String() + "\n" +
second.String() + "\n"
v := &Vaultik{Config: &config.Config{AgeSecretKey: keyFile}}
identities, err := v.restoreIdentities()
require.NoError(t, err)
require.Len(t, identities, 2)
plaintext := []byte("payload encrypted only to the second identity")
blob := encryptBlobTo(t, second.Recipient().String(), plaintext)
require.Equal(t, plaintext, decryptBlobWith(t, blob, identities))
}
// TestRestoreIdentitiesAcceptsTrailingNewline mirrors a YAML
// age_secret_key value that carries a trailing newline: it must still
// parse to its one identity and decrypt a blob encrypted to it.
func TestRestoreIdentitiesAcceptsTrailingNewline(t *testing.T) {
t.Parallel()
id, err := age.GenerateX25519Identity()
require.NoError(t, err)
v := &Vaultik{Config: &config.Config{AgeSecretKey: id.String() + "\n"}}
identities, err := v.restoreIdentities()
require.NoError(t, err)
require.Len(t, identities, 1)
plaintext := []byte("value with a trailing newline")
blob := encryptBlobTo(t, id.Recipient().String(), plaintext)
require.Equal(t, plaintext, decryptBlobWith(t, blob, identities))
}
// TestRestoreIdentitiesMissingKey reports the dedicated missing-key error
// rather than a parse failure, so the user is told to set the key.
func TestRestoreIdentitiesMissingKey(t *testing.T) {
t.Parallel()
v := &Vaultik{Config: &config.Config{}}
_, err := v.restoreIdentities()
require.ErrorIs(t, err, errDecryptionKeyRequired)
}
internal/vaultik/restore_interrupt_test.go
+159
View File
@@ -0,0 +1,159 @@
package vaultik //nolint:testpackage // sets ctx/cancel and inspects scratch files
import (
"context"
"io"
"path/filepath"
"strings"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
)
// blockingBlobStorer wraps a Storer and blocks the first blob download
// until its context is cancelled, so a test can catch a restore while it
// is mid-download. Metadata reads pass straight through, so the restore
// reaches the blob-download phase — having already written its decrypted
// scratch files — before it blocks.
type blockingBlobStorer struct {
storage.Storer
once sync.Once
entered chan struct{}
}
func newBlockingBlobStorer(inner storage.Storer) *blockingBlobStorer {
return &blockingBlobStorer{Storer: inner, entered: make(chan struct{})}
}
func (b *blockingBlobStorer) Get(
ctx context.Context, key string,
) (io.ReadCloser, error) {
if strings.HasPrefix(key, "blobs/") {
b.once.Do(func() { close(b.entered) })
<-ctx.Done()
return nil, ctx.Err()
}
return b.Storer.Get(ctx, key)
}
// TestRestoreCleansTempDirOnInterrupt drives a restore through the stop
// path (v.StartOperation, which is what the fx OnStop hook uses) instead
// of calling Restore directly, catches it mid-download, and asserts that
// stopping waits for the operation to unwind and removes its decrypted
// scratch files — the blob cache and the temporary snapshot database —
// from the temp directory. Without the wait a SIGINT exits the process
// before those defers run, leaving decrypted data on disk (issue #159).
//
// Not parallel: it points TMPDIR at a private directory (via t.Setenv)
// so it can assert on exactly the scratch files this restore created.
func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
root := t.TempDir()
dataDir := filepath.Join(root, "source")
storeDir := filepath.Join(root, "remote")
restoreDir := filepath.Join(root, "restored")
dbPath := filepath.Join(root, "index.sqlite")
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
buildLocalityFixture(t, fs, dataDir)
cfg, storer, snapshotID := setupLocalityBackup(
context.Background(), t, fs, dataDir, storeDir, dbPath)
// Point the "" temp paths (the blob cache directory and the
// snapshot-database directory) at a private directory so the test can
// assert on exactly the scratch this restore creates.
scratch := filepath.Join(root, "scratch")
require.NoError(t, fs.MkdirAll(scratch, 0o755))
t.Setenv("TMPDIR", scratch)
gate := newBlockingBlobStorer(storer)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
v := &Vaultik{
Config: cfg,
Storage: gate,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
ctx: ctx,
cancel: cancel,
}
var (
opReturned atomic.Bool
restoreErr error
)
stop := v.StartOperation(func() {
defer opReturned.Store(true)
restoreErr = v.Restore(&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
})
})
// Wait until the restore is blocked mid-download; its decrypted
// scratch files exist by now.
select {
case <-gate.entered:
case <-time.After(30 * time.Second):
t.Fatal("restore never reached the blob-download phase")
}
require.NotEmpty(t, scratchEntries(t, scratch),
"expected decrypted scratch files to exist mid-restore")
// Stop the operation the way the fx OnStop hook does.
stopCtx, stopCancel := context.WithTimeout(
context.Background(), 30*time.Second)
defer stopCancel()
require.True(t, stop(stopCtx),
"stop timed out; the operation goroutine did not return")
// stop returns only once the operation goroutine has returned, so its
// cleanup defers have run by the time we read these.
require.True(t, opReturned.Load(),
"stop returned before the operation goroutine finished")
require.ErrorIs(t, restoreErr, context.Canceled)
require.Empty(t, scratchEntries(t, scratch),
"decrypted scratch files remained after the interrupt")
}
// scratchEntries returns the vaultik blob-cache and snapshot-database
// scratch entries currently present in dir.
func scratchEntries(t *testing.T, dir string) []string {
t.Helper()
var matches []string
for _, pattern := range []string{
"vaultik-blobcache-*", "vaultik-restore-*",
} {
found, err := filepath.Glob(filepath.Join(dir, pattern))
require.NoError(t, err)
matches = append(matches, found...)
}
return matches
}
internal/vaultik/restore_malformed_key_test.go
+44
View File
@@ -0,0 +1,44 @@
package vaultik_test
import (
"context"
"io"
"testing"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestRestoreRejectsMalformedKeyBeforeDownload verifies that a malformed
// age secret key stops restore at the parse step: nothing is fetched from
// the store, and the error does not echo the key value (which is secret).
func TestRestoreRejectsMalformedKeyBeforeDownload(t *testing.T) {
t.Parallel()
const malformed = "this-is-not-a-valid-age-key"
mock := NewMockStorer()
v := &vaultik.Vaultik{
Config: &config.Config{AgeSecretKey: malformed},
Storage: mock,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(context.Background())
err := v.Restore(&vaultik.RestoreOptions{
SnapshotID: "any-snapshot",
TargetDir: t.TempDir(),
})
require.Error(t, err)
require.NotContains(t, err.Error(), malformed,
"error must not echo the key value")
require.Contains(t, err.Error(), "age_secret_key",
"error should name the configuration source")
require.Empty(t, mock.GetCalls(),
"a malformed key must fail before anything is fetched")
}
internal/vaultik/restore_perms_test.go
+306
View File
@@ -0,0 +1,306 @@
package vaultik //nolint:testpackage // drives restore through unexported session
import (
"bytes"
"context"
"errors"
"io"
"os"
"path/filepath"
"strings"
"sync"
"syscall"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
)
// errSpyWrite is the injected write failure used to exercise the
// partial-file cleanup path.
var errSpyWrite = errors.New("injected write failure")
// modeSpyFs wraps a real filesystem so restore tests can observe and
// perturb the single output file whose path contains watch. It records
// the on-disk permission bits seen at the moment content is first
// written (the window during which another local user could read it),
// and can inject a write failure or append trailing bytes on close.
type modeSpyFs struct {
afero.Fs
watch string
mu sync.Mutex
writeModes []os.FileMode
failWrite bool
trailing int
}
//nolint:ireturn // afero.Fs.OpenFile is defined to return the interface
func (m *modeSpyFs) OpenFile(
name string, flag int, perm os.FileMode,
) (afero.File, error) {
f, err := m.Fs.OpenFile(name, flag, perm)
if err != nil || !strings.Contains(name, m.watch) {
return f, err
}
return &modeSpyFile{File: f, fs: m, path: name}, nil
}
type modeSpyFile struct {
afero.File
fs *modeSpyFs
path string
written bool
}
func (f *modeSpyFile) Write(p []byte) (int, error) {
if !f.written {
f.written = true
info, err := f.fs.Stat(f.path)
if err == nil {
f.fs.mu.Lock()
f.fs.writeModes = append(f.fs.writeModes, info.Mode().Perm())
f.fs.mu.Unlock()
}
}
if f.fs.failWrite {
return 0, errSpyWrite
}
return f.File.Write(p)
}
func (f *modeSpyFile) Close() error {
if f.fs.trailing > 0 {
_, _ = f.File.Write(bytes.Repeat([]byte{'x'}, f.fs.trailing))
}
return f.File.Close()
}
// backupOneFile writes a single source file with the given mode and
// backs it up into a fresh file storer, returning everything a restore
// needs. The index database is closed before returning so the restore
// half runs from the exported metadata and remote bytes only.
func backupOneFile(
ctx context.Context, t *testing.T, fs afero.Fs, tempDir, name string,
content []byte, mode os.FileMode,
) (*config.Config, *storage.FileStorer, string, string) {
t.Helper()
dataDir := filepath.Join(tempDir, "src")
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
srcPath := filepath.Join(dataDir, name)
require.NoError(t, afero.WriteFile(fs, srcPath, content, mode))
require.NoError(t, fs.Chmod(srcPath, mode))
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
cfg := &config.Config{
AgeRecipients: []string{
"age1ezrjmfpwsc95svdg0y54mums3zevgzu0x0ecq2f7tp8a05gl0sjq9q9wjg",
},
AgeSecretKey: "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GXVEDMZFTVVF7PPHKU" +
"T68TXSFPK7APHXA2QS2NJA5",
CompressionLevel: 3,
Hostname: "test-host",
BlobSizeLimit: config.Size(5 * 1024 * 1024),
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: storer,
Config: cfg,
})
sm.SetFilesystem(fs)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: 4 * 1024 * 1024,
MaxBlobSize: 5 * 1024 * 1024,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
snapshotID, err := sm.CreateSnapshotWithName(
ctx, cfg.Hostname, "perms", "test-version", "test-git")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, snapshotID)
require.NoError(t, err)
require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
require.NoError(t, db.Close())
return cfg, storer, snapshotID, srcPath
}
// restoredPathFor returns where backupOneFile's source lands under a
// restore target: restore recreates each file at its original absolute
// path beneath TargetDir.
func restoredPathFor(restoreDir, srcPath string) string {
return filepath.Join(restoreDir, srcPath)
}
// withUmask022 forces the process umask to 022 for the duration of a
// test, so the difference between a 0600 create and a default create is
// observable. Restored serially (no t.Parallel) so it does not race
// other tests.
func withUmask022(t *testing.T) {
t.Helper()
old := syscall.Umask(0o022)
t.Cleanup(func() { syscall.Umask(old) })
}
// TestRestoreCreatesFileNeverWiderThanStoredMode checks that a file with
// a restrictive stored mode (0600) is never observable with a wider mode
// while its content is being written, and ends at its stored mode.
//
//nolint:paralleltest // sets the process umask; must run serially
func TestRestoreCreatesFileNeverWiderThanStoredMode(t *testing.T) {
log.Initialize(log.Config{})
withUmask022(t)
fs := afero.NewOsFs()
tempDir := t.TempDir()
ctx := context.Background()
content := randomBytes(t, 4096)
cfg, storer, snapshotID, srcPath := backupOneFile(
ctx, t, fs, tempDir, "secret.bin", content, 0o600)
restoreDir := filepath.Join(tempDir, "restored")
spy := &modeSpyFs{Fs: fs, watch: "secret.bin"}
v := newRestoreVaultik(ctx, cfg, storer, spy)
require.NoError(t, v.Restore(&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
}))
spy.mu.Lock()
observed := append([]os.FileMode(nil), spy.writeModes...)
spy.mu.Unlock()
require.NotEmpty(t, observed,
"spy never saw the output file being written")
for _, m := range observed {
assert.Equalf(t, os.FileMode(0o600), m,
"file was observable at mode %o during write; must be 0600", m)
}
// The stored mode is applied after the content is written.
info, err := fs.Stat(restoredPathFor(restoreDir, srcPath))
require.NoError(t, err)
assert.Equal(t, os.FileMode(0o600), info.Mode().Perm())
got, err := afero.ReadFile(fs, restoredPathFor(restoreDir, srcPath))
require.NoError(t, err)
require.True(t, bytes.Equal(got, content))
}
// TestRestoreRemovesPartialFileOnWriteFailure checks that a file whose
// content write fails is not left behind.
//
//nolint:paralleltest // sets the process umask; must run serially
func TestRestoreRemovesPartialFileOnWriteFailure(t *testing.T) {
log.Initialize(log.Config{})
withUmask022(t)
fs := afero.NewOsFs()
tempDir := t.TempDir()
ctx := context.Background()
cfg, storer, snapshotID, srcPath := backupOneFile(
ctx, t, fs, tempDir, "doomed.bin", randomBytes(t, 4096), 0o600)
restoreDir := filepath.Join(tempDir, "restored")
spy := &modeSpyFs{Fs: fs, watch: "doomed.bin", failWrite: true}
v := newRestoreVaultik(ctx, cfg, storer, spy)
err := v.Restore(&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
})
require.Error(t, err, "restore should fail when the write fails")
exists, err := afero.Exists(fs, restoredPathFor(restoreDir, srcPath))
require.NoError(t, err)
assert.False(t, exists, "partial file must be removed after a failed write")
}
// TestVerifyRejectsTrailingBytes checks that --verify fails a restored
// file that has bytes past its last chunk.
//
//nolint:paralleltest // sets the process umask; must run serially
func TestVerifyRejectsTrailingBytes(t *testing.T) {
log.Initialize(log.Config{})
withUmask022(t)
fs := afero.NewOsFs()
tempDir := t.TempDir()
ctx := context.Background()
cfg, storer, snapshotID, _ := backupOneFile(
ctx, t, fs, tempDir, "padded.bin", randomBytes(t, 4096), 0o600)
restoreDir := filepath.Join(tempDir, "restored")
// Append one byte to the file as it is written, so its content still
// matches the stored chunks but it is one byte too long.
spy := &modeSpyFs{Fs: fs, watch: "padded.bin", trailing: 1}
v := newRestoreVaultik(ctx, cfg, storer, spy)
err := v.Restore(&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
Verify: true,
})
require.Error(t, err, "verify should fail on a file with trailing bytes")
assert.ErrorIs(t, err, errFilesFailedVerify)
}
// newRestoreVaultik builds a Vaultik wired for a restore-only test.
func newRestoreVaultik(
ctx context.Context, cfg *config.Config, storer storage.Storer, fs afero.Fs,
) *Vaultik {
v := &Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
internal/vaultik/restore_plan.go
+8 -4
View File
@@ -171,10 +171,13 @@ func (p *restorePlan) finishFile(fileID types.FileID) {
// downloaded next, after which it — together with any other pending
// files whose blob sets become empty — moves to the ready queue.
//
// The zero FileID return means nothing is pending.
func (p *restorePlan) pickNextDownload() types.FileID {
// The second return value is false when no file needs a download, so a
// genuine file carrying the nil UUID is picked rather than mistaken for
// "nothing left".
func (p *restorePlan) pickNextDownload() (types.FileID, bool) {
var best types.FileID
found := false
bestCount := math.MaxInt
var bestID string
@@ -188,14 +191,15 @@ func (p *restorePlan) pickNextDownload() types.FileID {
}
idStr := id.String()
if n < bestCount || (n == bestCount && (best.IsZero() || idStr < bestID)) {
if !found || n < bestCount || (n == bestCount && idStr < bestID) {
best = id
found = true
bestCount = n
bestID = idStr
}
}
return best
return best, found
}
// blobsNeeded returns the uncached blob hashes for fileID in any order.
internal/vaultik/restore_plan_test.go
+88
View File
@@ -0,0 +1,88 @@
package vaultik //nolint:testpackage // inspects unexported restore plan internals
import (
"context"
"math"
"testing"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/types"
)
// TestPickNextDownloadReturnsNilUUIDFile proves a genuine pending file
// carrying the nil UUID is picked for download rather than mistaken for
// "nothing left" — the bug that could abandon every remaining file.
func TestPickNextDownloadReturnsNilUUIDFile(t *testing.T) {
t.Parallel()
var nilID types.FileID // zero value is the nil UUID
plan := &restorePlan{
fileBlobs: map[types.FileID]map[string]struct{}{
nilID: {"blobhash": {}},
},
}
id, ok := plan.pickNextDownload()
require.True(t, ok,
"pickNextDownload treated a pending nil-UUID file as nothing to do")
require.True(t, id.IsZero(), "expected the nil-UUID file to be picked")
}
// TestPickNextDownloadEmptyPlan confirms the second return value is false
// only when no file needs a download.
func TestPickNextDownloadEmptyPlan(t *testing.T) {
t.Parallel()
plan := &restorePlan{
fileBlobs: map[types.FileID]map[string]struct{}{},
}
_, ok := plan.pickNextDownload()
require.False(t, ok, "pickNextDownload reported work on an empty plan")
}
// TestRunRestoreLoopFailsOnAbandonedFiles proves the loop returns an
// error rather than silent success when files remain pending after it
// can make no further progress.
func TestRunRestoreLoopFailsOnAbandonedFiles(t *testing.T) {
t.Parallel()
ctx := context.Background()
db, err := database.NewTestDB()
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
cache, err := newBlobDiskCache(math.MaxInt64)
require.NoError(t, err)
t.Cleanup(func() { _ = cache.Close() })
v := &Vaultik{ctx: ctx}
session := &restoreSession{
v: v,
ctx: ctx,
repos: repos,
sweeper: newRestoreSweeper(ctx, repos, cache, 1),
result: &RestoreResult{},
}
// A file that is still pending but whose uncached-blob set is empty
// and which was never queued as ready: the loop can neither restore
// nor download it. This is the abandonment the guard must catch.
var stuck types.FileID
plan := &restorePlan{
fileBlobs: map[types.FileID]map[string]struct{}{stuck: {}},
blobFiles: map[string]map[types.FileID]struct{}{},
cached: map[string]struct{}{},
}
err = v.runRestoreLoop(session, plan, map[types.FileID]*database.File{}, 0)
require.ErrorIs(t, err, errRestoreIncomplete)
}
internal/vaultik/restore_snapshot_identity_test.go
+251
View File
@@ -0,0 +1,251 @@
package vaultik_test
import (
"context"
"io"
"path/filepath"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestRestoreAndDeepVerifyRejectSwappedDatabase proves that swapping two
// snapshots' encrypted databases on the store is caught. age decryption
// alone proves only that a database is readable; without an identity check
// restore would happily write the wrong snapshot's files and deep verify
// would report success. After the swap, restore and deep verify of A both
// fail, and the error names the snapshot the database actually holds (B).
func TestRestoreAndDeepVerifyRejectSwappedDatabase(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
ctx := context.Background()
// Two snapshots with different content, backed up into one shared
// store. Different names give them different remote keys, so their
// metadata directories are distinct and can be tampered with alone.
dataA := filepath.Join(tempDir, "srcA")
require.NoError(t, fs.MkdirAll(dataA, 0o755))
require.NoError(t, afero.WriteFile(fs, filepath.Join(dataA, "a.bin"),
bytesPattern("alpha-", int(chunkSize*2)), 0o644))
dataB := filepath.Join(tempDir, "srcB")
require.NoError(t, fs.MkdirAll(dataB, 0o755))
require.NoError(t, afero.WriteFile(fs, filepath.Join(dataB, "b.bin"),
bytesPattern("beta-", int(chunkSize*2)), 0o644))
idA := backupNamedSnapshotToStore(ctx, t, fs, dataA, storer,
filepath.Join(tempDir, "idxA.sqlite"), "alpha")
idB := backupNamedSnapshotToStore(ctx, t, fs, dataB, storer,
filepath.Join(tempDir, "idxB.sqlite"), "beta")
require.NotEqual(t, idA, idB)
keyA := snapshot.RemoteSnapshotKey(idA)
keyB := snapshot.RemoteSnapshotKey(idB)
require.NotEqual(t, keyA, keyB)
// Baseline: each snapshot verifies against its own intact metadata.
require.NoError(t, newStoreClient(ctx, t, fs, storer).RunDeepVerify(
idA, &vaultik.VerifyOptions{Deep: true}))
require.NoError(t, newStoreClient(ctx, t, fs, storer).RunDeepVerify(
idB, &vaultik.VerifyOptions{Deep: true}))
// Swap the two snapshots' encrypted databases on the store.
swapStoreFiles(t, fs,
filepath.Join(storeDir, "metadata", keyA, "db.zst.age"),
filepath.Join(storeDir, "metadata", keyB, "db.zst.age"))
// Restore of A now decrypts B's database; the identity check must
// reject it and name the snapshot it actually found.
restoreErr := newStoreClient(ctx, t, fs, storer).Restore(&vaultik.RestoreOptions{
SnapshotID: idA,
TargetDir: filepath.Join(tempDir, "restoreA"),
})
require.Error(t, restoreErr)
require.ErrorContains(t, restoreErr, idB)
// Deep verify of A must reject the swapped database for the same reason.
verifyErr := newStoreClient(ctx, t, fs, storer).RunDeepVerify(
idA, &vaultik.VerifyOptions{Deep: true})
require.Error(t, verifyErr)
require.ErrorContains(t, verifyErr, idB)
}
// TestDeepVerifyRejectsSwappedDatabaseWithEmptyManifest covers the case the
// issue calls out: swapping in a database whose blob set is empty and
// pairing it with an equally empty manifest. The manifest then agrees with
// the database, so every blob-level check passes and deep verify used to
// report success with zero blobs verified. The identity check rejects it
// before any blob check runs.
func TestDeepVerifyRejectsSwappedDatabaseWithEmptyManifest(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
ctx := context.Background()
// Snapshot A: real content, so its manifest lists blobs.
dataA := filepath.Join(tempDir, "srcA")
require.NoError(t, fs.MkdirAll(dataA, 0o755))
require.NoError(t, afero.WriteFile(fs, filepath.Join(dataA, "a.bin"),
bytesPattern("alpha-", int(chunkSize*2)), 0o644))
idA := backupNamedSnapshotToStore(ctx, t, fs, dataA, storer,
filepath.Join(tempDir, "idxA.sqlite"), "alpha")
// Snapshot C: a single empty file, so it references no blobs and its
// manifest is empty. This is the database/manifest pair an attacker
// would swap in to make the blob checks vacuously pass.
dataC := filepath.Join(tempDir, "srcC")
require.NoError(t, fs.MkdirAll(dataC, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataC, "empty.bin"), []byte{}, 0o644))
idC := backupNamedSnapshotToStore(ctx, t, fs, dataC, storer,
filepath.Join(tempDir, "idxC.sqlite"), "charlie")
keyA := snapshot.RemoteSnapshotKey(idA)
keyC := snapshot.RemoteSnapshotKey(idC)
// Replace A's database and manifest with C's empty pair.
copyStoreFile(t, fs,
filepath.Join(storeDir, "metadata", keyC, "db.zst.age"),
filepath.Join(storeDir, "metadata", keyA, "db.zst.age"))
copyStoreFile(t, fs,
filepath.Join(storeDir, "metadata", keyC, "manifest.json.zst"),
filepath.Join(storeDir, "metadata", keyA, "manifest.json.zst"))
verifyErr := newStoreClient(ctx, t, fs, storer).RunDeepVerify(
idA, &vaultik.VerifyOptions{Deep: true})
require.Error(t, verifyErr)
require.ErrorContains(t, verifyErr, idC)
}
// backupNamedSnapshotToStore backs up dataDir into the shared storer under
// the given snapshot name and returns the human snapshot ID. Two snapshots
// backed up under different names get different remote keys, so their
// metadata directories on the store are distinct.
func backupNamedSnapshotToStore(
ctx context.Context, t *testing.T, fs afero.Fs,
dataDir string, storer storage.Storer, dbPath, name string,
) string {
t.Helper()
const (
chunkSize = int64(64 * 1024)
maxBlobSize = int64(512 * 1024)
)
cfg := &config.Config{
AgeRecipients: []string{testAgePublicKey},
AgeSecretKey: testAgeSecretKey,
CompressionLevel: 3,
Hostname: testHostname,
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
sm := snapshot.NewSnapshotManager(snapshot.SnapshotManagerParams{
Repos: repos,
Storage: storer,
Config: cfg,
})
sm.SetFilesystem(fs)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
Storage: storer,
ChunkSize: chunkSize,
MaxBlobSize: maxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
})
snapshotID, err := sm.CreateSnapshotWithName(
ctx, cfg.Hostname, name, "test-version", "test-git")
require.NoError(t, err)
_, err = scanner.Scan(ctx, dataDir, snapshotID)
require.NoError(t, err)
require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
require.NoError(t, db.Close())
return snapshotID
}
// newStoreClient builds a Vaultik that reads only from the store: the
// secret key, the storer, and a filesystem, with no local index. This is
// what restore and deep verify need.
func newStoreClient(
ctx context.Context, t *testing.T, fs afero.Fs, storer storage.Storer,
) *vaultik.Vaultik {
t.Helper()
v := &vaultik.Vaultik{
Config: &config.Config{
AgeSecretKey: testAgeSecretKey,
Hostname: testHostname,
},
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
// swapStoreFiles exchanges the contents of two files on the store.
func swapStoreFiles(t *testing.T, fs afero.Fs, a, b string) {
t.Helper()
dataA, err := afero.ReadFile(fs, a)
require.NoError(t, err)
dataB, err := afero.ReadFile(fs, b)
require.NoError(t, err)
require.NoError(t, afero.WriteFile(fs, a, dataB, 0o644))
require.NoError(t, afero.WriteFile(fs, b, dataA, 0o644))
}
// copyStoreFile overwrites dst with the contents of src on the store.
func copyStoreFile(t *testing.T, fs afero.Fs, src, dst string) {
t.Helper()
data, err := afero.ReadFile(fs, src)
require.NoError(t, err)
require.NoError(t, afero.WriteFile(fs, dst, data, 0o644))
}
internal/vaultik/restore_snapshotdb_test.go
+108
View File
@@ -0,0 +1,108 @@
package vaultik //nolint:testpackage // inspects unexported snapshot-db materialization
import (
"bytes"
"context"
"os"
"path/filepath"
"testing"
"filippo.io/age"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/database"
)
// genuineSnapshotDBBytes returns the on-disk bytes of a real snapshot
// database (the full schema applied).
func genuineSnapshotDBBytes(t *testing.T) []byte {
t.Helper()
path := filepath.Join(t.TempDir(), "snapshot.db")
db, err := database.New(context.Background(), path)
require.NoError(t, err)
require.NoError(t, db.Close())
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled temp path
require.NoError(t, err)
return data
}
// TestMaterializeSnapshotDBPrivateDir proves the decrypted database lands
// in a private (0700) directory and opens read-only.
func TestMaterializeSnapshotDBPrivateDir(t *testing.T) {
dbData := genuineSnapshotDBBytes(t)
t.Setenv("TMPDIR", t.TempDir())
v := &Vaultik{ctx: context.Background(), Fs: afero.NewOsFs()}
db, dir, err := v.materializeSnapshotDB(bytes.NewReader(dbData))
require.NoError(t, err)
t.Cleanup(func() {
_ = db.Close()
_ = os.RemoveAll(dir)
})
info, err := os.Stat(dir)
require.NoError(t, err)
require.Equal(t, os.FileMode(0o700), info.Mode().Perm(),
"snapshot database directory must not be world-readable")
_, err = db.Conn().ExecContext(context.Background(),
"CREATE TABLE probe_readonly (x)")
require.Error(t, err, "materialized snapshot database must be read-only")
}
// TestMaterializeSnapshotDBRejectsCompleteEmptyStream proves the written == 0
// guard rejects a genuinely empty but complete metadata object: a real age
// header, nonce, and final tag encrypting zero plaintext bytes. The truncation
// case is stopped earlier by the reader (io.ErrUnexpectedEOF) and never reaches
// this branch, so it needs its own input. This complete stream decrypts to zero
// bytes with a clean EOF, passes the reader, and must be refused as empty rather
// than accepted as a valid zero-table database. Reverting the guard lets the
// empty file open as a fresh schema and the test fails.
func TestMaterializeSnapshotDBRejectsCompleteEmptyStream(t *testing.T) {
identity, err := age.GenerateX25519Identity()
require.NoError(t, err)
var stream bytes.Buffer
w, err := age.Encrypt(&stream, identity.Recipient())
require.NoError(t, err)
require.NoError(t, w.Close())
blobReader, err := blobgen.NewReader(bytes.NewReader(stream.Bytes()), identity)
require.NoError(t, err)
t.Cleanup(func() { _ = blobReader.Close() })
t.Setenv("TMPDIR", t.TempDir())
v := &Vaultik{ctx: context.Background(), Fs: afero.NewOsFs()}
_, _, err = v.materializeSnapshotDB(blobReader)
require.ErrorIs(t, err, errEmptySnapshotDB)
}
// TestMaterializeSnapshotDBRemovesDirOnOpenFailure proves a failed open
// leaves no temp directory behind.
func TestMaterializeSnapshotDBRemovesDirOnOpenFailure(t *testing.T) {
base := t.TempDir()
t.Setenv("TMPDIR", base)
v := &Vaultik{ctx: context.Background(), Fs: afero.NewOsFs()}
_, _, err := v.materializeSnapshotDB(
bytes.NewReader([]byte("this is not a sqlite database")))
require.Error(t, err)
entries, rerr := os.ReadDir(base)
require.NoError(t, rerr)
require.Empty(t, entries, "temp directory left behind after open failure")
}
internal/vaultik/restore_truncated_db_test.go
+85
View File
@@ -0,0 +1,85 @@
package vaultik_test
import (
"bytes"
"context"
"io"
"path/filepath"
"testing"
"filippo.io/age"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestRestoreRejectsTruncatedMetadataDB backs up a real tree, then replaces
// the snapshot's db.zst.age with a stream cut right after the age header and
// its 16-byte nonce. age.Decrypt still accepts such an object and the zstd
// decoder turns the truncated read into a clean EOF, so before the fix restore
// built a fresh empty schema and reported success. Restore must now fail with
// io.ErrUnexpectedEOF, the error the reader raises for a truncated object.
// Asserting that specific error pins the reader fix: without it the truncation
// yields an empty database, which the identity check rejects for an unrelated
// reason, and this test would pass anyway.
func TestRestoreRejectsTruncatedMetadataDB(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024)
maxBlobSize := int64(512 * 1024)
setupE2ESourceTree(t, fs, dataDir, chunkSize)
ctx := context.Background()
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
// Encrypting empty plaintext to the snapshot recipient yields
// header + nonce(16) + a single 16-byte final chunk tag. Dropping the
// trailing tag leaves exactly the age header plus its nonce — the
// truncation an attacker can write over metadata without any key.
recipient, err := age.ParseX25519Recipient(testAgePublicKey)
require.NoError(t, err)
var full bytes.Buffer
w, err := age.Encrypt(&full, recipient)
require.NoError(t, err)
require.NoError(t, w.Close())
truncated := full.Bytes()[:full.Len()-16]
dbKeyPath := filepath.Join(storeDir, "metadata",
snapshot.RemoteSnapshotKey(snapshotID), "db.zst.age")
require.NoError(t, afero.WriteFile(fs, dbKeyPath, truncated, 0o644))
restoreVaultik := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
restoreVaultik.SetContext(ctx)
err = restoreVaultik.Restore(&vaultik.RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
Verify: true,
})
require.ErrorIs(t, err, io.ErrUnexpectedEOF)
}
internal/vaultik/shallow_verify_test.go
+191
View File
@@ -0,0 +1,191 @@
package vaultik_test
import (
"bytes"
"context"
"encoding/json"
"io"
"os"
"path/filepath"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestShallowVerifyDetectsWrongBlobSize backs up a real snapshot, runs
// shallow verify (which passes and reports exactly the blobs it checked),
// then grows one stored blob so its size no longer matches the manifest.
// Shallow verify must then fail, count the grown blob as a size mismatch,
// and drop it from the verified count rather than continuing to report it
// as checked.
func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
// Enough data to span several blobs, so the mismatch count and the
// dropped verified count are both meaningful.
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"),
bytesPattern("shallow-", int(maxBlobSize*4)), 0o644))
ctx := context.Background()
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
newVerifier := func(out io.Writer) *vaultik.Vaultik {
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: out,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
var out bytes.Buffer
require.NoError(t,
newVerifier(&out).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{JSON: true}),
"shallow verify should pass on a healthy snapshot")
healthy := decodeVerifyResult(t, out.Bytes())
require.Equal(t, "ok", healthy.Status)
require.Positive(t, healthy.BlobCount)
require.Equal(t, healthy.BlobCount, healthy.Verified,
"shallow verify must report exactly the blobs it checked")
require.Zero(t, healthy.Mismatched)
// Grow one stored blob so its size no longer matches the manifest.
growOneBlob(t, fs, filepath.Join(storeDir, "blobs"))
out.Reset()
err := newVerifier(&out).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{JSON: true})
require.Error(t, err,
"shallow verify must fail when a blob's stored size differs from the manifest")
bad := decodeVerifyResult(t, out.Bytes())
require.Equal(t, "failed", bad.Status)
require.Equal(t, 1, bad.Mismatched)
require.Equal(t, healthy.BlobCount-1, bad.Verified,
"the wrong-sized blob must not be counted as verified")
}
// TestShallowVerifyDetectsMissingDatabase backs up a real snapshot,
// confirms shallow verify passes, then deletes the snapshot's encrypted
// database. Shallow verify must fail: a snapshot without its database is
// not restorable, even when every blob is present.
func TestShallowVerifyDetectsMissingDatabase(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"),
bytesPattern("shallow-db-", int(maxBlobSize*2)), 0o644))
ctx := context.Background()
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
newVerifier := func() *vaultik.Vaultik {
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
require.NoError(t,
newVerifier().VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{}),
"shallow verify should pass on a healthy snapshot")
// The database lives under the hashed remote key, not the human ID.
dbObject := filepath.Join(storeDir, "metadata",
snapshot.RemoteSnapshotKey(snapshotID), "db.zst.age")
require.NoError(t, os.Remove(dbObject))
require.Error(t,
newVerifier().VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{}),
"shallow verify must fail when db.zst.age is absent")
}
// growOneBlob appends bytes to the first blob file found under blobsDir,
// changing its on-disk size so it no longer matches the manifest.
func growOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {
t.Helper()
var blobPath string
err := afero.Walk(fs, blobsDir,
func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
if blobPath == "" && !info.IsDir() {
blobPath = path
}
return nil
})
require.NoError(t, err)
require.NotEmpty(t, blobPath, "expected at least one blob on disk")
data, err := afero.ReadFile(fs, blobPath)
require.NoError(t, err)
data = append(data, []byte("extra")...)
require.NoError(t, afero.WriteFile(fs, blobPath, data, 0o644))
}
func decodeVerifyResult(t *testing.T, b []byte) vaultik.VerifyResult {
t.Helper()
var result vaultik.VerifyResult
require.NoError(t, json.Unmarshal(b, &result))
return result
}
internal/vaultik/snapshot.go
+229 -87
View File
@@ -8,6 +8,7 @@ import (
"path/filepath"
"regexp"
"sort"
"strconv"
"strings"
"time"
@@ -19,7 +20,6 @@ import (
var (
errSnapshotNotInConfig = errors.New("snapshot not found in config")
errNoSnapshotsInConfig = errors.New("no snapshots configured")
errBlobsMissing = errors.New("blobs are missing")
errSnapshotVerifyFailed = errors.New("verification failed")
errRemoveAllNeedsForce = errors.New("--all requires --force")
errInvalidTableName = errors.New("invalid table name")
@@ -55,8 +55,8 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return err
}
// Clean up incomplete snapshots FIRST, before any scanning
// This is critical for data safety - see CleanupIncompleteSnapshots for details
// Clean up incomplete snapshots FIRST, before any scanning.
// This is critical for data safety; PruneDatabase below does it.
hostname := v.Config.Hostname
if hostname == "" {
hostname, _ = os.Hostname()
@@ -669,9 +669,24 @@ func (v *Vaultik) VerifySnapshotWithOptions(
v.printVerifyHeader(snapshotID, opts)
// Download and parse manifest. The caller supplies a human
// snapshot ID; we hash it to address remote storage.
manifest, err := v.downloadManifestByKey(snapshot.RemoteSnapshotKey(snapshotID))
// Resolve the identifier to the snapshot's remote key. A human ID is
// hashed; a remote key (or its abbreviation, as printed for a
// remote-only snapshot) is used as-is, so a host with no local index
// can verify a snapshot it can only see on the store. The key is kept
// so we can also check for the snapshot's encrypted database below.
remoteKey, err := v.resolveSnapshotRemoteKey(snapshotID)
if err != nil {
if opts.JSON {
result.Status = verifyStatusFailed
result.ErrorMessage = fmt.Sprintf("resolving snapshot identifier: %v", err)
return v.outputVerifyJSON(result)
}
return fmt.Errorf("resolving snapshot identifier: %w", err)
}
manifest, err := v.downloadManifestByKey(remoteKey)
if err != nil {
if opts.JSON {
result.Status = verifyStatusFailed
@@ -701,14 +716,34 @@ func (v *Vaultik) VerifySnapshotWithOptions(
v.printlnStdout()
// Check each blob exists
v.stdoutf("Checking blob existence...\n")
// Check each blob is present with the size the manifest records.
v.stdoutf("Checking blob presence and sizes...\n")
}
result.Verified, result.Missing, result.MissingSize =
v.verifyManifestBlobsExist(manifest, opts)
// A snapshot is only restorable if its encrypted database is present
// alongside the blobs. Shallow verify checks that the object exists; it
// does not decrypt it (that is deep verify's job).
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
return v.formatVerifyResult(result, manifest, opts)
_, dbErr := v.Storage.Stat(v.ctx, dbPath)
if dbErr != nil {
result.DatabaseMissing = true
}
result.Verified, result.Missing, result.Mismatched, result.MissingSize, err =
v.verifyManifestBlobs(manifest, opts)
if err != nil {
if opts.JSON {
result.Status = verifyStatusFailed
result.ErrorMessage = fmt.Sprintf("verifying manifest blobs: %v", err)
return v.outputVerifyJSON(result)
}
return fmt.Errorf("verifying manifest blobs: %w", err)
}
return v.formatVerifyResult(result, opts)
}
// printVerifyHeader prints the snapshot ID and parsed timestamp for
@@ -733,25 +768,34 @@ func (v *Vaultik) printVerifyHeader(snapshotID string, opts *VerifyOptions) {
}
}
// verifyManifestBlobsExist checks that each blob in the manifest exists
// in storage, returning the verified count, missing count, and total
// missing bytes.
func (v *Vaultik) verifyManifestBlobsExist(
// verifyManifestBlobs checks that each blob in the manifest is present in
// storage with the size the manifest records, returning the counts of
// blobs that were present with the right size, absent, and present but the
// wrong size, plus the total bytes of the absent blobs. It does not read
// blob contents; deep verification (RunDeepVerify) does that. The size
// comparison matches the deep path (see verifyBlobExistenceFromDB).
func (v *Vaultik) verifyManifestBlobs(
manifest *snapshot.Manifest, opts *VerifyOptions,
) (int, int, int64) {
) (int, int, int, int64, error) {
var (
verified, missing int
verified, missing, mismatched int
missingSize int64
)
for _, blob := range manifest.Blobs {
// The manifest is unauthenticated, so its blob hashes are checked
// before being spliced into a storage path.
if !isBlobHash(blob.Hash) {
return 0, 0, 0, 0, fmt.Errorf("%w: %s",
errInvalidBlobHash, shortHash(blob.Hash))
}
blobPath := fmt.Sprintf("blobs/%s/%s/%s",
blob.Hash[:2], blob.Hash[2:4], blob.Hash)
// Shallow: check existence only (deep verification is handled
// by RunDeepVerify).
_, err := v.Storage.Stat(v.ctx, blobPath)
if err != nil {
stat, err := v.Storage.Stat(v.ctx, blobPath)
switch {
case err != nil:
if !opts.JSON {
v.stdoutf(" Missing: %s (%s)\n",
blob.Hash, ubytes(blob.CompressedSize))
@@ -759,23 +803,32 @@ func (v *Vaultik) verifyManifestBlobsExist(
missing++
missingSize += blob.CompressedSize
} else {
case stat.Size != blob.CompressedSize:
if !opts.JSON {
v.stdoutf(" Wrong size: %s (store has %s, manifest lists %s)\n",
blob.Hash, ubytes(stat.Size), ubytes(blob.CompressedSize))
}
mismatched++
default:
verified++
}
}
return verified, missing, missingSize
return verified, missing, mismatched, missingSize, nil
}
// formatVerifyResult outputs the final verification results as JSON or
// human-readable text.
func (v *Vaultik) formatVerifyResult(
result *VerifyResult, manifest *snapshot.Manifest, opts *VerifyOptions,
result *VerifyResult, opts *VerifyOptions,
) error {
failure := shallowVerifyFailure(result)
if opts.JSON {
if result.Missing > 0 {
if failure != "" {
result.Status = verifyStatusFailed
result.ErrorMessage = fmt.Sprintf("%d blobs are missing", result.Missing)
result.ErrorMessage = failure
} else {
result.Status = "ok"
}
@@ -784,29 +837,57 @@ func (v *Vaultik) formatVerifyResult(
}
v.stdoutf("\nVerification complete:\n")
v.stdoutf(" Verified: %d blobs (%s)\n", result.Verified,
ubytes(manifest.TotalCompressedSize-result.MissingSize))
v.stdoutf(" Present with listed size: %d blobs\n", result.Verified)
if result.Missing > 0 {
v.stdoutf(" Missing: %d blobs (%s)\n",
result.Missing, ubytes(result.MissingSize))
} else {
v.stdoutf(" Missing: 0 blobs\n")
}
if result.Mismatched > 0 {
v.stdoutf(" Wrong size: %d blobs\n", result.Mismatched)
}
if result.DatabaseMissing {
v.stdoutf(" Encrypted database: missing\n")
}
v.stdoutf(" Status: ")
if result.Missing > 0 {
v.stdoutf("FAILED - %d blobs are missing\n", result.Missing)
if failure != "" {
v.stdoutf("FAILED - %s\n", failure)
return fmt.Errorf("%d %w", result.Missing, errBlobsMissing)
return fmt.Errorf("%w: %s", errSnapshotVerifyFailed, failure)
}
v.stdoutf("OK - All blobs verified\n")
// Report only what was actually checked: presence and size, not contents.
v.stdoutf("OK - all %d blobs listed in the manifest are present with the "+
"listed size; contents not checked (use --deep)\n", result.Verified)
return nil
}
// shallowVerifyFailure returns a human-readable description of everything
// that failed shallow verification, or the empty string if it passed.
func shallowVerifyFailure(result *VerifyResult) string {
var parts []string
if result.Missing > 0 {
parts = append(parts, fmt.Sprintf("%d blobs are missing", result.Missing))
}
if result.Mismatched > 0 {
parts = append(parts,
fmt.Sprintf("%d blobs have the wrong size", result.Mismatched))
}
if result.DatabaseMissing {
parts = append(parts, "the encrypted database is missing")
}
return strings.Join(parts, "; ")
}
// outputVerifyJSON outputs the verification result as JSON
func (v *Vaultik) outputVerifyJSON(result *VerifyResult) error {
encoder := json.NewEncoder(v.Stdout)
@@ -932,29 +1013,23 @@ func (v *Vaultik) downloadManifestByKey(remoteKey string) (*snapshot.Manifest, e
func (v *Vaultik) syncWithRemote() error {
log.Info("Syncing with remote snapshots")
// Get all remote snapshot IDs
remoteSnapshots := make(map[string]bool)
objectCh := v.Storage.ListStream(v.ctx, "metadata/")
for object := range objectCh {
if object.Err != nil {
return fmt.Errorf("listing remote snapshots: %w", object.Err)
// Remote metadata lives under metadata/<remote-key>/, where the
// directory name is snapshot.RemoteSnapshotKey(id), not the human
// snapshot ID. Compare each local row's hashed key against that set
// so a row still backed by remote metadata is kept. Comparing human
// IDs against the hashed directory names matches nothing and deletes
// every local snapshot record (issue #160).
remoteKeys, err := v.listAllRemoteSnapshotKeys()
if err != nil {
return fmt.Errorf("listing remote snapshots: %w", err)
}
// Extract snapshot ID from paths like metadata/hostname-20240115-143052Z/
parts := strings.Split(object.Key, "/")
if len(parts) >= minSnapshotIDParts &&
parts[0] == metadataDirName && parts[1] != "" {
// Skip macOS resource fork files (._*) and other hidden files
if strings.HasPrefix(parts[1], ".") {
continue
remoteKeySet := make(map[string]bool, len(remoteKeys))
for _, k := range remoteKeys {
remoteKeySet[k] = true
}
remoteSnapshots[parts[1]] = true
}
}
log.Debug("Found remote snapshots", "count", len(remoteSnapshots))
log.Debug("Found remote snapshots", "count", len(remoteKeySet))
// Get all local snapshots (use a high limit to get all)
localSnapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
@@ -962,12 +1037,12 @@ func (v *Vaultik) syncWithRemote() error {
return fmt.Errorf("listing local snapshots: %w", err)
}
// Remove local snapshots that don't exist remotely
// Remove local snapshots whose metadata is absent from the remote.
removedCount := 0
for _, snap := range localSnapshots {
snapshotIDStr := snap.ID.String()
if !remoteSnapshots[snapshotIDStr] {
if !remoteKeySet[snapshot.RemoteSnapshotKey(snapshotIDStr)] {
log.Info("Removing local snapshot not found in remote",
"snapshot_id", snap.ID)
@@ -1255,23 +1330,38 @@ func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
}
parts := strings.Split(object.Key, "/")
if len(parts) >= minSnapshotIDParts &&
parts[0] == metadataDirName && parts[1] != "" {
if len(parts) < minSnapshotIDParts ||
parts[0] != metadataDirName || parts[1] == "" {
continue
}
// Skip macOS resource fork files (._*) and other hidden files
if strings.HasPrefix(parts[1], ".") {
continue
}
if strings.HasSuffix(object.Key, "/") ||
strings.Contains(object.Key, "/manifest.json.zst") {
if !strings.HasSuffix(object.Key, "/") &&
!strings.Contains(object.Key, "/manifest.json.zst") {
continue
}
key := parts[1]
// A remote snapshot key is a SHA-256 hash: 64 lowercase hex
// characters. The listing comes from the untrusted destination,
// so accept a key only in that form.
if !isBlobHash(key) {
log.Warn("Skipping non-conforming key under metadata/",
"key", object.Key)
continue
}
if !seen[key] {
seen[key] = true
keys = append(keys, key)
}
}
}
}
return keys, nil
}
@@ -1540,12 +1630,17 @@ func (v *Vaultik) outputRemoveJSON(result *RemoveResult) error {
return encoder.Encode(result)
}
// PruneResult contains statistics about the prune operation
// PruneResult contains statistics about the prune operation.
// SnapshotsDeleted counts snapshots actually deleted. FilesDeleted,
// ChunksDeleted, and BlobsDeleted are derived from before/after row
// counts of the local index; each is nil when a count could not be read,
// so an unreadable count is reported as unknown rather than silently
// as 0.
type PruneResult struct {
SnapshotsDeleted int64
FilesDeleted int64
ChunksDeleted int64
BlobsDeleted int64
FilesDeleted *int64
ChunksDeleted *int64
BlobsDeleted *int64
}
// PruneDatabase removes incomplete snapshots and orphaned files, chunks,
@@ -1560,7 +1655,7 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
result := &PruneResult{}
// Snapshot counts before deletion of incompletes.
snapshotCountBefore, _ := v.getTableCount("snapshots")
snapshotCountBefore := v.tableCountForReport("snapshots")
// First, delete any incomplete snapshots
incompleteSnapshots, err := v.Repositories.Snapshots.GetIncompleteSnapshots(v.ctx)
@@ -1575,9 +1670,9 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
}
// Get counts before cleanup for reporting
fileCountBefore, _ := v.getTableCount("files")
chunkCountBefore, _ := v.getTableCount("chunks")
blobCountBefore, _ := v.getTableCount("blobs")
fileCountBefore := v.tableCountForReport("files")
chunkCountBefore := v.tableCountForReport("chunks")
blobCountBefore := v.tableCountForReport("blobs")
// Run the cleanup
err = v.SnapshotManager.CleanupOrphanedData(v.ctx)
@@ -1586,36 +1681,83 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
}
// Get counts after cleanup
fileCountAfter, _ := v.getTableCount("files")
chunkCountAfter, _ := v.getTableCount("chunks")
blobCountAfter, _ := v.getTableCount("blobs")
fileCountAfter := v.tableCountForReport("files")
chunkCountAfter := v.tableCountForReport("chunks")
blobCountAfter := v.tableCountForReport("blobs")
result.FilesDeleted = fileCountBefore - fileCountAfter
result.ChunksDeleted = chunkCountBefore - chunkCountAfter
result.BlobsDeleted = blobCountBefore - blobCountAfter
result.FilesDeleted = countDiff(fileCountBefore, fileCountAfter)
result.ChunksDeleted = countDiff(chunkCountBefore, chunkCountAfter)
result.BlobsDeleted = countDiff(blobCountBefore, blobCountAfter)
log.Info("Local database prune complete",
"incomplete_snapshots", result.SnapshotsDeleted,
"orphaned_files", result.FilesDeleted,
"orphaned_chunks", result.ChunksDeleted,
"orphaned_blobs", result.BlobsDeleted,
"orphaned_files", countText(result.FilesDeleted),
"orphaned_chunks", countText(result.ChunksDeleted),
"orphaned_blobs", countText(result.BlobsDeleted),
)
snapshotCountAfter := snapshotCountBefore - result.SnapshotsDeleted
// Snapshots remaining after removing the incomplete ones; unknown if
// the pre-prune snapshot count could not be read.
snapshotsRemain := countDiff(snapshotCountBefore, &result.SnapshotsDeleted)
v.UI.Completef("Pruned local index database.")
v.UI.Detailf("Incomplete snapshots: %d removed (%d remain).",
result.SnapshotsDeleted, snapshotCountAfter)
v.UI.Detailf("Orphaned files: %d removed (%d remain).",
result.FilesDeleted, fileCountAfter)
v.UI.Detailf("Orphaned chunks: %d removed (%d remain).",
result.ChunksDeleted, chunkCountAfter)
v.UI.Detailf("Orphaned blobs: %d removed (%d remain).",
result.BlobsDeleted, blobCountAfter)
v.UI.Detailf("Incomplete snapshots: %s removed (%s remain).",
countText(&result.SnapshotsDeleted), countText(snapshotsRemain))
v.UI.Detailf("Orphaned files: %s removed (%s remain).",
countText(result.FilesDeleted), countText(fileCountAfter))
v.UI.Detailf("Orphaned chunks: %s removed (%s remain).",
countText(result.ChunksDeleted), countText(chunkCountAfter))
v.UI.Detailf("Orphaned blobs: %s removed (%s remain).",
countText(result.BlobsDeleted), countText(blobCountAfter))
return result, nil
}
// countUnknown is what a count reads as when its query could not be run,
// distinct from "0", which means the table really was empty.
const countUnknown = "unknown"
// tableCountForReport returns the row count of a table for the prune
// summary, or nil if the count could not be read. A read failure is
// logged at warn — visible even under --json, which routes warnings to
// stderr — and then rendered as unknown rather than silently becoming 0,
// so a broken query is a visible failure instead of a plausible wrong
// number.
func (v *Vaultik) tableCountForReport(tableName string) *int64 {
count, err := v.getTableCount(tableName)
if err != nil {
log.Warn("could not read table row count for prune summary",
"table", tableName, "error", err)
return nil
}
return &count
}
// countDiff returns before-after, or nil if either count is unknown so
// that an unreadable count does not collapse into a plausible delta.
func countDiff(before, after *int64) *int64 {
if before == nil || after == nil {
return nil
}
diff := *before - *after
return &diff
}
// countText renders a count that may be unknown: nil (the read failed)
// becomes "unknown", never "0", so a reader can tell an empty table from
// one that could not be queried.
func countText(count *int64) string {
if count == nil {
return countUnknown
}
return strconv.FormatInt(*count, 10)
}
// validTableNameRe matches table names containing only lowercase
// alphanumeric characters and underscores.
var validTableNameRe = regexp.MustCompile(`^[a-z0-9_]+$`)
internal/vaultik/snapshot_identifier.go
+87
View File
@@ -0,0 +1,87 @@
package vaultik
import (
"errors"
"fmt"
"strings"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// remoteKeyHexLen is the length of a full remote snapshot key: a SHA256
// digest rendered as lowercase hex.
const remoteKeyHexLen = 64
// Sentinel errors for resolving a snapshot identifier against the store.
var (
errSnapshotKeyNotFound = errors.New(
"no snapshot on the destination store matches this identifier")
errSnapshotKeyAmbiguous = errors.New(
"identifier matches more than one snapshot on the destination store")
)
// resolveSnapshotRemoteKey turns a snapshot identifier supplied on the
// command line into the remote key that names the snapshot's metadata
// directory on the destination store. Every remote path a restore or
// verify reads is built from that key.
//
// Two forms are accepted, matching the two things a host can know:
//
// - A human snapshot ID (hostname_name_timestamp), which a host holding
// the local index has. It is hashed to its remote key; the store is
// not consulted.
// - A remote key, or the leading part of one, which is all a host with
// no local index can know — it is exactly what `snapshot list` prints
// for a remote-only snapshot (see formatRemoteOnlyID). It is resolved
// against the destination store's metadata listing; an identifier that
// matches no snapshot, or more than one, is an error.
//
// The two are told apart by shape: a remote key is lowercase hex, and a
// human snapshot ID never is (it carries a hostname, underscores, and an
// RFC3339 timestamp).
func (v *Vaultik) resolveSnapshotRemoteKey(identifier string) (string, error) {
if !isRemoteKeyOrPrefix(identifier) {
return snapshot.RemoteSnapshotKey(identifier), nil
}
keys, err := v.listAllRemoteSnapshotKeys()
if err != nil {
return "", fmt.Errorf(
"listing destination store to resolve %q: %w", identifier, err)
}
var matches []string
for _, key := range keys {
if strings.HasPrefix(key, identifier) {
matches = append(matches, key)
}
}
switch len(matches) {
case 1:
return matches[0], nil
case 0:
return "", fmt.Errorf("%w: %s", errSnapshotKeyNotFound, identifier)
default:
return "", fmt.Errorf("%w: %s (%d matches)",
errSnapshotKeyAmbiguous, identifier, len(matches))
}
}
// isRemoteKeyOrPrefix reports whether s is a full remote key or the
// leading part of one: 1 to 64 lowercase hex characters. A human snapshot
// ID is never all hex, so this shape test is enough to tell the two apart.
func isRemoteKeyOrPrefix(s string) bool {
if s == "" || len(s) > remoteKeyHexLen {
return false
}
for _, r := range s {
if (r < '0' || r > '9') && (r < 'a' || r > 'f') {
return false
}
}
return true
}
internal/vaultik/vaultik.go
+34 -28
View File
@@ -5,7 +5,6 @@ package vaultik
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"os"
@@ -13,7 +12,6 @@ import (
"github.com/spf13/afero"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/crypto"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/globals"
"sneak.berlin/go/vaultik/internal/snapshot"
@@ -21,12 +19,6 @@ import (
"sneak.berlin/go/vaultik/internal/ui"
)
// Sentinel errors for misconfigured encryption settings.
var (
errNoAgeRecipients = errors.New("no age recipients configured")
errNoAgeSecretKey = errors.New("no age secret key configured")
)
// Vaultik contains all dependencies needed for vaultik operations
type Vaultik struct {
Globals *globals.Globals
@@ -136,31 +128,45 @@ func (v *Vaultik) Cancel() {
v.cancel()
}
// StartOperation runs fn in its own goroutine and returns a stop
// function. fn is the command being run (a restore, verify, prune, and
// so on); it observes cancellation through the Vaultik context and
// removes its decrypted scratch files (the blob cache and the temporary
// snapshot database) from the temp directory as it unwinds.
//
// Calling stop cancels the Vaultik context and then blocks until fn has
// returned — so that unwinding, and the cleanup it does, completes
// before the caller proceeds — or until the passed context is done,
// whichever comes first. It reports whether fn returned before that
// deadline. A signal-driven shutdown must call stop before the process
// exits; otherwise the process can exit mid-operation and leave
// decrypted data behind.
func (v *Vaultik) StartOperation(fn func()) func(context.Context) bool {
done := make(chan struct{})
go func() {
defer close(done)
fn()
}()
return func(ctx context.Context) bool {
v.Cancel()
select {
case <-done:
return true
case <-ctx.Done():
return false
}
}
}
// CanDecrypt returns true if this Vaultik instance has decryption capabilities
func (v *Vaultik) CanDecrypt() bool {
return v.Config.AgeSecretKey != ""
}
// GetEncryptor creates a new Encryptor instance based on the configured age recipients
// Returns an error if no recipients are configured
func (v *Vaultik) GetEncryptor() (*crypto.Encryptor, error) {
if len(v.Config.AgeRecipients) == 0 {
return nil, errNoAgeRecipients
}
return crypto.NewEncryptor(v.Config.AgeRecipients)
}
// GetDecryptor creates a new Decryptor instance based on the configured age secret key
// Returns an error if no secret key is configured
func (v *Vaultik) GetDecryptor() (*crypto.Decryptor, error) {
if v.Config.AgeSecretKey == "" {
return nil, errNoAgeSecretKey
}
return crypto.NewDecryptor(v.Config.AgeSecretKey)
}
// GetFilesystem returns the filesystem instance used by Vaultik
//
//nolint:ireturn // afero.Fs is the filesystem abstraction by design
internal/vaultik/verify.go
+181 -121
View File
@@ -6,15 +6,15 @@ import (
"encoding/hex"
"errors"
"fmt"
"hash"
"io"
"os"
"path/filepath"
"time"
"github.com/klauspost/compress/zstd"
"filippo.io/age"
// Blank import registers the pure-Go sqlite driver for database/sql.
_ "modernc.org/sqlite"
"sneak.berlin/go/vaultik/internal/blobgen"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
)
@@ -26,9 +26,12 @@ var (
"VAULTIK_AGE_SECRET_KEY not set; required for deep verification")
errChunksOutOfOrder = errors.New("chunks out of order")
errChunkHashMismatch = errors.New("chunk hash mismatch")
errNegativeChunkLength = errors.New("chunk length is negative")
errTrailingBlobData = errors.New(
"blob has unexpected trailing bytes not covered by chunk list")
errManifestExtraBlob = errors.New("manifest contains blob not in database")
errManifestMissingBlob = errors.New(
"manifest omits blob present in database")
errBlobSizeMismatch = errors.New("blob size mismatch")
)
@@ -53,6 +56,11 @@ type VerifyResult struct {
Verified int `json:"verified"`
Missing int `json:"missing"`
MissingSize int64 `json:"missing_size,omitempty"`
Mismatched int `json:"mismatched,omitempty"`
// DatabaseMissing is set by shallow verify when the snapshot's
// encrypted database (metadata/<key>/db.zst.age) is absent, which
// makes the snapshot unrestorable regardless of the blobs.
DatabaseMissing bool `json:"database_missing,omitempty"`
ErrorMessage string `json:"error,omitempty"`
}
@@ -86,13 +94,21 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
errSecretKeyRequired.Error(), errSecretKeyRequired)
}
// Parse the age secret key once, the same way restore does, and reuse
// the identities for the database and every blob.
identities, err := v.restoreIdentities()
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
log.Info("Starting snapshot verification", "snapshot_id", snapshotID, "mode", "deep")
if !opts.JSON {
v.stdoutf("Deep verification of snapshot: %s\n\n", snapshotID)
}
manifest, tempDB, dbBlobs, err := v.loadVerificationData(snapshotID, opts, result)
manifest, tempDB, dbBlobs, err := v.loadVerificationData(
snapshotID, opts, result, identities)
if err != nil {
return err
}
@@ -112,7 +128,8 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
result.TotalSize = totalSize
err = v.runVerificationSteps(manifest, dbBlobs, tempDB, opts, result, totalSize)
err = v.runVerificationSteps(
manifest, dbBlobs, tempDB, opts, result, totalSize, identities)
if err != nil {
return err
}
@@ -137,9 +154,17 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
// loadVerificationData downloads manifest, database, and blob list for verification
func (v *Vaultik) loadVerificationData(
snapshotID string, opts *VerifyOptions, result *VerifyResult,
identities []age.Identity,
) (*snapshot.Manifest, *tempDB, []snapshot.BlobInfo, error) {
// All remote paths use the hashed key derived from the human ID.
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
// Resolve the identifier to the snapshot's remote key. A human ID is
// hashed; a remote key (or its abbreviation, as printed for a
// remote-only snapshot) is used as-is, so a host with no local index
// can verify a snapshot it can only see on the store.
remoteKey, err := v.resolveSnapshotRemoteKey(snapshotID)
if err != nil {
return nil, nil, nil, v.deepVerifyFailure(result, opts,
fmt.Sprintf("resolving snapshot identifier: %v", err), err)
}
// Download manifest. downloadManifestByKey is the single reader for
// remote manifests; see its doc comment.
@@ -166,27 +191,13 @@ func (v *Vaultik) loadVerificationData(
v.stdoutf("Downloading and decrypting database...\n")
}
// Download and decrypt database
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
log.Info("Downloading encrypted database", "path", dbPath)
dbReader, err := v.Storage.Get(v.ctx, dbPath)
tdb, err := v.downloadVerifiedSnapshotDB(
snapshotID, remoteKey, opts, result, identities)
if err != nil {
return nil, nil, nil, v.deepVerifyFailure(result, opts,
fmt.Sprintf("failed to download database: %v", err),
fmt.Errorf("failed to download database: %w", err))
return nil, nil, nil, err
}
defer func() { _ = dbReader.Close() }()
tdb, err := v.decryptAndLoadDatabase(dbReader)
if err != nil {
return nil, nil, nil, v.deepVerifyFailure(result, opts,
fmt.Sprintf("failed to decrypt database: %v", err),
fmt.Errorf("failed to decrypt database: %w", err))
}
dbBlobs, err := v.getBlobsFromDatabase(snapshotID, tdb.DB)
dbBlobs, err := v.getBlobsFromDatabase(tdb.db.Conn())
if err != nil {
_ = tdb.Close()
@@ -212,6 +223,45 @@ func (v *Vaultik) loadVerificationData(
return manifest, tdb, dbBlobs, nil
}
// downloadVerifiedSnapshotDB downloads and decrypts the snapshot metadata
// database and confirms it really is the snapshot named by remoteKey
// before any of its rows are trusted (see verifySnapshotDBIdentity). On
// any failure it records the failure in result and returns the error the
// caller should propagate; the temp database is closed on a rejected
// identity so nothing is left on disk.
func (v *Vaultik) downloadVerifiedSnapshotDB(
snapshotID, remoteKey string, opts *VerifyOptions, result *VerifyResult,
identities []age.Identity,
) (*tempDB, error) {
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
log.Info("Downloading encrypted database", "path", dbPath)
dbReader, err := v.Storage.Get(v.ctx, dbPath)
if err != nil {
return nil, v.deepVerifyFailure(result, opts,
fmt.Sprintf("failed to download database: %v", err),
fmt.Errorf("failed to download database: %w", err))
}
defer func() { _ = dbReader.Close() }()
tdb, err := v.decryptAndLoadDatabase(dbReader, identities)
if err != nil {
return nil, v.deepVerifyFailure(result, opts,
fmt.Sprintf("failed to decrypt database: %v", err),
fmt.Errorf("failed to decrypt database: %w", err))
}
err = v.verifySnapshotDBIdentity(tdb.db, snapshotID, remoteKey)
if err != nil {
_ = tdb.Close()
return nil, v.deepVerifyFailure(result, opts, err.Error(), err)
}
return tdb, nil
}
// runVerificationSteps executes manifest verification, blob existence
// check, and deep content verification.
func (v *Vaultik) runVerificationSteps(
@@ -221,6 +271,7 @@ func (v *Vaultik) runVerificationSteps(
opts *VerifyOptions,
result *VerifyResult,
totalSize int64,
identities []age.Identity,
) error {
if !opts.JSON {
v.stdoutf("Verifying manifest against database...\n")
@@ -247,7 +298,7 @@ func (v *Vaultik) runVerificationSteps(
len(dbBlobs), ubytes(totalSize))
}
err = v.performDeepVerificationFromDB(dbBlobs, tdb.DB, opts)
err = v.performDeepVerificationFromDB(dbBlobs, tdb.db.Conn(), opts, identities)
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
@@ -255,127 +306,123 @@ func (v *Vaultik) runVerificationSteps(
return nil
}
// tempDB wraps sql.DB with cleanup
// tempDB is the downloaded snapshot database opened read-only for deep
// verify, held in a private temp directory removed in full on Close.
type tempDB struct {
*sql.DB
tempPath string
db *database.DB
tempDir string
}
func (t *tempDB) Close() error {
err := t.DB.Close()
_ = os.Remove(t.tempPath)
err := t.db.Close()
// Remove the whole private directory so the decrypted database and
// any SQLite side files are gone on every path.
_ = os.RemoveAll(t.tempDir)
return err
}
// decryptAndLoadDatabase decrypts and loads the binary SQLite database
// from the encrypted stream.
func (v *Vaultik) decryptAndLoadDatabase(reader io.ReadCloser) (*tempDB, error) {
// Get decryptor
decryptor, err := v.GetDecryptor()
// from the encrypted stream. It reads through the same blobgen reader restore
// uses, streaming the decrypted, decompressed database to a temp file.
func (v *Vaultik) decryptAndLoadDatabase(
reader io.ReadCloser, identities []age.Identity,
) (*tempDB, error) {
// Decrypt and decompress through the shared blobgen reader.
blobReader, err := blobgen.NewReader(reader, identities...)
if err != nil {
return nil, fmt.Errorf("failed to get decryptor: %w", err)
return nil, fmt.Errorf("failed to create decryption reader: %w", err)
}
// Decrypt the stream
decryptedReader, err := decryptor.DecryptStream(reader)
defer func() { _ = blobReader.Close() }()
// Materialize the decrypted database inside a private (0700) temp
// directory so it is never world-readable, and remove the whole
// directory on any failure below.
tempDir, err := os.MkdirTemp("", "vaultik-verify-")
if err != nil {
return nil, fmt.Errorf("failed to decrypt database: %w", err)
return nil, fmt.Errorf("failed to create temp directory: %w", err)
}
// Decompress the binary database
decompressor, err := zstd.NewReader(decryptedReader)
if err != nil {
return nil, fmt.Errorf("failed to create decompressor: %w", err)
}
defer decompressor.Close()
success := false
// Create temporary file for the database
tempFile, err := os.CreateTemp("", "vaultik-verify-*.db")
defer func() {
if !success {
_ = os.RemoveAll(tempDir)
}
}()
dbPath := filepath.Join(tempDir, snapshotDBFilename)
//nolint:gosec // G304: dbPath is our MkdirTemp dir plus a constant filename
tempFile, err := os.OpenFile(
dbPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, restoreFileMode)
if err != nil {
return nil, fmt.Errorf("failed to create temp file: %w", err)
}
tempPath := tempFile.Name()
// Stream decompress directly to file
log.Info("Decompressing database...")
written, err := io.Copy(tempFile, decompressor)
written, err := io.Copy(tempFile, blobReader)
if err != nil {
_ = tempFile.Close()
_ = os.Remove(tempPath)
return nil, fmt.Errorf("failed to decompress database: %w", err)
}
_ = tempFile.Close()
err = tempFile.Close()
if err != nil {
return nil, fmt.Errorf("failed to close temp database file: %w", err)
}
log.Info("Database decompressed", "size", ubytes(written))
// Open the database
db, err := sql.Open("sqlite", tempPath)
db, err := database.OpenReadOnly(v.ctx, dbPath)
if err != nil {
_ = os.Remove(tempPath)
return nil, fmt.Errorf("failed to open database: %w", err)
}
return &tempDB{
DB: db,
tempPath: tempPath,
}, nil
success = true
return &tempDB{db: db, tempDir: tempDir}, nil
}
// verifyBlob downloads and verifies a single blob
func (v *Vaultik) verifyBlob(blobInfo snapshot.BlobInfo, db *sql.DB) error {
func (v *Vaultik) verifyBlob(
blobInfo snapshot.BlobInfo, db *sql.DB, identities []age.Identity,
) error {
// Download blob using shared fetch method
reader, _, err := v.FetchBlob(v.ctx, blobInfo.Hash, blobInfo.CompressedSize)
reader, err := v.FetchBlob(v.ctx, blobInfo.Hash)
if err != nil {
return fmt.Errorf("failed to download: %w", err)
}
defer func() { _ = reader.Close() }()
// Get decryptor
decryptor, err := v.GetDecryptor()
// Decrypt and decompress through the shared blobgen reader, which hashes
// the plaintext as it is read. A blob's hash — its remote name — is the
// double SHA-256 of that plaintext (see blobgen.DoubleSHA256), not of the
// encrypted bytes.
blobReader, err := blobgen.NewReader(reader, identities...)
if err != nil {
return fmt.Errorf("failed to get decryptor: %w", err)
return fmt.Errorf("failed to create blob reader: %w", err)
}
// Decrypt blob
decryptedReader, err := decryptor.DecryptStream(reader)
if err != nil {
return fmt.Errorf("failed to decrypt: %w", err)
}
defer func() { _ = blobReader.Close() }()
// Decompress blob
decompressor, err := zstd.NewReader(decryptedReader)
if err != nil {
return fmt.Errorf("failed to decompress: %w", err)
}
defer decompressor.Close()
// A blob's hash — its remote name — is the double SHA256 of its
// decompressed plaintext (see blobgen.Writer.Sum256), not of the
// encrypted bytes. Hash the plaintext as chunk verification streams
// it, then compare on completion.
plaintextHasher := sha256.New()
hashedStream := io.TeeReader(decompressor, plaintextHasher)
chunkCount, err := v.verifyBlobChunks(db, blobInfo.Hash, hashedStream)
chunkCount, err := v.verifyBlobChunks(db, blobInfo.Hash, blobReader)
if err != nil {
return err
}
err = v.verifyBlobFinalIntegrity(hashedStream, plaintextHasher, blobInfo.Hash)
err = v.verifyBlobFinalIntegrity(blobReader, blobInfo.Hash)
if err != nil {
return err
}
log.Info("Blob verified",
"hash", blobInfo.Hash[:16]+"...",
"hash", shortHash(blobInfo.Hash)+"...",
"chunks", chunkCount,
"size", ubytes(blobInfo.CompressedSize),
)
@@ -441,21 +488,24 @@ func (v *Vaultik) verifyBlobChunks(
totalRead = offset
}
// Read chunk data
chunkData := make([]byte, length)
// length comes from an untrusted blob_chunks row: reject a
// negative value, and hash by streaming exactly length bytes
// rather than allocating a database-supplied size up front.
if length < 0 {
return 0, fmt.Errorf("%w: offset %d length %d",
errNegativeChunkLength, offset, length)
}
_, err = io.ReadFull(decompressor, chunkData)
hasher := sha256.New()
n, err := io.CopyN(hasher, decompressor, length)
if err != nil {
return 0, fmt.Errorf("failed to read chunk at offset %d: %w", offset, err)
}
totalRead += length
totalRead += n
// Verify chunk hash
hasher := sha256.New()
hasher.Write(chunkData)
calculatedHash := hex.EncodeToString(hasher.Sum(nil))
if calculatedHash != chunkHash {
return 0, fmt.Errorf("%w at offset %d: calculated %s, expected %s",
errChunkHashMismatch, offset, calculatedHash, chunkHash)
@@ -475,11 +525,12 @@ func (v *Vaultik) verifyBlobChunks(
// verifyBlobFinalIntegrity checks that no trailing data exists in the
// decompressed stream and that the blob hash matches the expected value.
func (v *Vaultik) verifyBlobFinalIntegrity(
plaintext io.Reader, plaintextHasher hash.Hash, expectedHash string,
blobReader *blobgen.Reader, expectedHash string,
) error {
// Verify no remaining data in blob - if the chunk list is accurate,
// the blob should be fully consumed.
remaining, err := io.Copy(io.Discard, plaintext)
// the blob should be fully consumed. Draining to EOF also completes the
// reader's plaintext hash.
remaining, err := io.Copy(io.Discard, blobReader)
if err != nil {
return fmt.Errorf("failed to check for remaining blob data: %w", err)
}
@@ -488,10 +539,9 @@ func (v *Vaultik) verifyBlobFinalIntegrity(
return fmt.Errorf("%w: %d bytes", errTrailingBlobData, remaining)
}
// The blob hash is the double SHA256 of its plaintext content.
firstHash := plaintextHasher.Sum(nil)
secondHash := sha256.Sum256(firstHash)
calculatedBlobHash := hex.EncodeToString(secondHash[:])
// The blob hash is the double SHA-256 of its plaintext content.
calculatedBlobHash := hex.EncodeToString(
blobgen.DoubleSHA256(blobReader.Sum256()))
if calculatedBlobHash != expectedHash {
return fmt.Errorf("%w: calculated %s, expected %s",
@@ -501,19 +551,21 @@ func (v *Vaultik) verifyBlobFinalIntegrity(
return nil
}
// getBlobsFromDatabase gets all blobs for the snapshot from the database
func (v *Vaultik) getBlobsFromDatabase(
snapshotID string, db *sql.DB,
) ([]snapshot.BlobInfo, error) {
// getBlobsFromDatabase gets all blobs for the snapshot from the database.
//
// The exported per-snapshot database holds exactly one snapshot's data
// (see cleanSnapshotDB), so every row in snapshot_blobs belongs to it.
// We select them directly rather than filtering by the human snapshot ID,
// which a host restoring from the store alone does not have.
func (v *Vaultik) getBlobsFromDatabase(db *sql.DB) ([]snapshot.BlobInfo, error) {
query := `
SELECT b.blob_hash, b.compressed_size
FROM snapshot_blobs sb
JOIN blobs b ON sb.blob_hash = b.blob_hash
WHERE sb.snapshot_id = ?
ORDER BY b.blob_hash
`
rows, err := db.QueryContext(v.ctx, query, snapshotID)
rows, err := db.QueryContext(v.ctx, query)
if err != nil {
return nil, fmt.Errorf("failed to query snapshot blobs: %w", err)
}
@@ -566,16 +618,11 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
manifestBlobMap[blob.Hash] = blob.CompressedSize
}
// Check counts match
if len(dbBlobMap) != len(manifestBlobMap) {
log.Warn("Manifest blob count mismatch",
"database_blobs", len(dbBlobMap),
"manifest_blobs", len(manifestBlobMap),
)
// This is a warning, not an error - database is authoritative
}
// Check each manifest blob exists in database with correct size
// The manifest is the only blob list prune consults, so it must match
// the database exactly. A blob in the manifest but not the database
// points at a corrupt manifest; a blob in the database but omitted
// from the manifest would be pruned away while this snapshot still
// needs it. Either divergence fails verification.
for hash, manifestSize := range manifestBlobMap {
dbSize, exists := dbBlobMap[hash]
if !exists {
@@ -589,6 +636,12 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
}
}
for hash := range dbBlobMap {
if _, exists := manifestBlobMap[hash]; !exists {
return fmt.Errorf("%w: %s", errManifestMissingBlob, hash)
}
}
log.Info("✓ Manifest verified against database",
"manifest_blobs", len(manifestBlobMap),
"database_blobs", len(dbBlobMap),
@@ -602,6 +655,12 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
for i, blob := range blobs {
// The hash is read from the snapshot database, which is not
// trusted; check it before it is spliced into a storage path.
if !isBlobHash(blob.Hash) {
return fmt.Errorf("%w: %s", errInvalidBlobHash, shortHash(blob.Hash))
}
// Construct blob path
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
@@ -638,6 +697,7 @@ func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
// each blob using the database as source.
func (v *Vaultik) performDeepVerificationFromDB(
blobs []snapshot.BlobInfo, db *sql.DB, opts *VerifyOptions,
identities []age.Identity,
) error {
// Calculate total bytes for ETA
var totalBytesExpected int64
@@ -655,7 +715,7 @@ func (v *Vaultik) performDeepVerificationFromDB(
for i, blobInfo := range blobs {
// Verify individual blob
err := v.verifyBlob(blobInfo, db)
err := v.verifyBlob(blobInfo, db, identities)
if err != nil {
return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
}

Some files were not shown because too many files have changed in this diff Show More