mirror of
https://github.com/Twigpine/node.git
synced 2026-11-09 05:20:05 -10:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 beardthelion
|
ad0fdd57c9 |
No files matched your search
+10
-56
@@ -24,26 +24,11 @@ DATABASE_URL=postgresql://gitlawb:changeme@localhost:5432/gitlawb
|
||||
# ── Database pool & startup resilience ────────────────────────────────────
|
||||
# Maximum connections in the PostgreSQL pool. A cap, not a floor —
|
||||
# connections open lazily. Size against the DB server's max_connections,
|
||||
# remembering admin tooling opens its own pool.
|
||||
# remembering admin tooling opens its own pool. Each concurrent write pins one
|
||||
# connection for its whole duration (the connection-affine advisory lock), so the
|
||||
# node REJECTS at boot any value below GITLAWB_MAX_CONCURRENT_GIT_PUSHES + 8
|
||||
# headroom — keep this comfortably above that (default 48 for pushes 32).
|
||||
GITLAWB_DB_MAX_CONNECTIONS=48
|
||||
# Maximum connections in the DEDICATED advisory-lock pool, separate from the
|
||||
# pool above. Every in-flight repo write pins one connection here for its whole
|
||||
# duration, so this is a hard ceiling on simultaneous writes node-wide: size it
|
||||
# to expected peak concurrent writers, not small. Keeping it separate is what
|
||||
# stops a push burst from starving ordinary request handlers. Budget
|
||||
# (GITLAWB_DB_MAX_CONNECTIONS + this) per node against the server's
|
||||
# max_connections, times node count, plus admin tooling.
|
||||
GITLAWB_DB_LOCK_POOL_MAX_CONNECTIONS=40
|
||||
# Upper bound, in seconds, on any object-storage transfer that runs while a
|
||||
# per-repo write lock is HELD (the archive download inside acquire_write and the
|
||||
# upload inside release). These were free before the lock's connection was
|
||||
# pinned to the guard; now an unbounded stall holds a lock-pool slot, and enough
|
||||
# stalls deny every write on the node. The bound applies PER SPAN and there are
|
||||
# two (the acquire-side refresh, which covers the existence check and download
|
||||
# together, and the release-side upload), so worst-case slot occupancy is about
|
||||
# twice this value plus the git work between them. Read it together with the pool
|
||||
# size above and with GITLAWB_GIT_SERVICE_TIMEOUT_SECS.
|
||||
GITLAWB_LOCK_HELD_TRANSFER_TIMEOUT_SECS=300
|
||||
# Seconds a request waits for a pool connection before failing with 503.
|
||||
GITLAWB_DB_ACQUIRE_TIMEOUT_SECS=5
|
||||
# Upper bound on each startup connect+migrate attempt, in seconds. Keep it
|
||||
@@ -109,14 +94,9 @@ GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false
|
||||
|
||||
# Require the authenticated pusher to be the repo owner on git-receive-pack.
|
||||
# A valid did:key signature is authentication, not authorization: anyone can
|
||||
# mint a key, derive its DID and sign, so with this off every signed caller may
|
||||
# push to every repository, private ones included. On by default.
|
||||
#
|
||||
# Set to false only for a rolling upgrade whose pushers are not yet the repo
|
||||
# owner. Note that delegated and CI keys count as non-owners: UCAN git/push is
|
||||
# verified but not yet honored for authorization, so they cannot push while this
|
||||
# is on. See docs/RUN-A-NODE.md.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH=true
|
||||
# sign as their own DID. When true, pushes from a non-owner DID are rejected.
|
||||
# Keep false until the repo owner is ready for owner-only writes.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH=false
|
||||
|
||||
# Comma-separated libp2p multiaddrs.
|
||||
# Example: /ip4/1.2.3.4/udp/7546/quic-v1/p2p/12D3KooW...
|
||||
@@ -211,9 +191,8 @@ GITLAWB_MAX_CONCURRENT_READS_PER_CALLER=16
|
||||
# many WRITE-pool slots. This one is load-bearing for push availability, since
|
||||
# it is acquired before the global write permit: without it, one host minting
|
||||
# disposable did:key identities could open enough slow pushes to monopolize the
|
||||
# write pool and 503 every other source (the push rate limiter caps arrival
|
||||
# rate, not in-flight concurrency, and owner enforcement can be turned off for
|
||||
# a rolling upgrade).
|
||||
# write pool and 503 every other source (owner enforcement defaults off, and
|
||||
# the push rate limiter caps arrival rate, not in-flight concurrency).
|
||||
# Keyed on the resolved source IP, never the DID, so a DID farm does not defeat
|
||||
# them; keying granularity follows GITLAWB_TRUSTED_PROXY like the read cap above.
|
||||
|
||||
@@ -234,26 +213,10 @@ GITLAWB_MAX_CONCURRENT_IPFS_WALKS=32
|
||||
# per-caller caps via GITLAWB_TRUSTED_PROXY; reject-before-insert bounded map).
|
||||
# Default 4.
|
||||
GITLAWB_IPFS_WALK_PER_SOURCE=4
|
||||
# Max legacy (NULL-provenance) repos probed per single /ipfs request, bounding the
|
||||
# scan-fallback fan-out (git cat-file per candidate repo) for an anonymous caller. A
|
||||
# truncated scan sheds a retryable 503, never a false 404. Default 256.
|
||||
GITLAWB_IPFS_MAX_LEGACY_PROBES=256
|
||||
# Max repo ROWS one /ipfs request's legacy scan may read from the database. The probe
|
||||
# ceiling above only counts once a probe runs, and quarantined or private repos are
|
||||
# denied before that, so without this an all-denying inventory paged the whole repo
|
||||
# table for one anonymous request. A truncated scan sheds a retryable 503 carrying a
|
||||
# sealed `continuation` token; echo it as ?scan= to resume, so a holder buried past the
|
||||
# ceiling is reachable in ceil(repos / ceiling) + 1 requests. Raising this also raises
|
||||
# the per-caller /ipfs work allowance, since each page is charged to it. Lowering it
|
||||
# sharpens a coarse oracle: laddering to the end reveals the node's total repo count to
|
||||
# within one ceiling. Default 2048.
|
||||
GITLAWB_IPFS_MAX_LEGACY_SCAN_ROWS=2048
|
||||
# Max EXPENSIVE path-scope visibility walks per single /ipfs request (only a
|
||||
# blob in a path-scoped repo costs a full-history walk). Over-cap repos are
|
||||
# skipped without a verdict and the scan continues; if the object is then found
|
||||
# nowhere the request sheds a retryable 503 instead of a false 404. The effective
|
||||
# cap is the tighter of this value and the node's internal per-request ceiling of
|
||||
# 17, so values above 17 have no effect; lower values do tighten it. Default 64.
|
||||
# nowhere the request sheds a retryable 503 instead of a false 404. Default 64.
|
||||
GITLAWB_IPFS_MAX_REPOS_WALKED=64
|
||||
# Ceiling on repos one /ipfs request may VISIT past the visibility gate. Each
|
||||
# visit costs a repo acquire — on a Tigris cache miss a full archive download,
|
||||
@@ -274,15 +237,6 @@ GITLAWB_IPFS_MAX_REPO_VISITS=1024
|
||||
# Must be 1..=3153600000 (100 years): the node derives an Instant deadline from
|
||||
# this value, and a larger one cannot be represented. Default 600.
|
||||
GITLAWB_IPFS_REQUEST_BUDGET_SECS=600
|
||||
# Shorter budget (seconds) for the pre-walk CID resolve: the lookup that maps a
|
||||
# requested CID to its git oid(s), which runs while the scarce walk admission is
|
||||
# already held. A well-formed CID with no pin row does no probe and no walk work,
|
||||
# so without this a stalled lookup could hold a walk slot for the whole request
|
||||
# budget while nothing walked. The effective deadline is the lesser of this and
|
||||
# the remaining request budget; walk and probe work stay on the request budget,
|
||||
# so a slow but progressing scan is never shed by it.
|
||||
# Must be 1..=3153600000 (100 years). Default 10.
|
||||
GITLAWB_IPFS_RESOLVE_BUDGET_SECS=10
|
||||
# Max /ipfs/{cid} requests per client IP per hour (route flood brake, distinct
|
||||
# from the concurrency caps above). 0 disables. Default 600.
|
||||
GITLAWB_IPFS_RATE_LIMIT=600
|
||||
|
||||
@@ -296,35 +296,3 @@ jobs:
|
||||
|
||||
- name: Check gitlawb-core dependency allowlist
|
||||
run: bash scripts/check-gitlawb-core-deps.sh
|
||||
|
||||
# release-please only rewrites a crate's version when the line carries the
|
||||
# `# x-release-please-version` annotation AND the manifest is listed under
|
||||
# extra-files in release-please-config.json. Miss either half and the crate
|
||||
# is skipped silently at release time, freezing at its creation version:
|
||||
# icaptcha-client was added as a workspace member after the config was last
|
||||
# written and sat at 0.4.0 through four releases before anyone noticed.
|
||||
# Exhaustive-by-construction, like the allowlist gate above: the required set
|
||||
# is derived from `cargo metadata`, so a newly added crate reds CI whether or
|
||||
# not its author knew this gate existed.
|
||||
release-versioning:
|
||||
name: release versioning coverage
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
steps:
|
||||
- name: Check out repository
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
|
||||
with:
|
||||
toolchain: stable
|
||||
|
||||
- name: Cache cargo
|
||||
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
|
||||
with:
|
||||
key: release-versioning
|
||||
|
||||
- name: Check every workspace crate is release-managed
|
||||
run: bash scripts/check-release-versioning.sh
|
||||
+2
-4
@@ -31,9 +31,7 @@ crates/
|
||||
├── gitlawb-core/ crypto primitives (DID, CID, HTTP sigs, UCAN, ref certs)
|
||||
├── gitlawb-node/ axum HTTP server, git smart HTTP, P2P, GraphQL
|
||||
├── gl/ CLI — identity, repos, MCP server, Base L2 names
|
||||
├── git-remote-gitlawb/ git remote helper for gitlawb:// URLs
|
||||
├── gitlawb-attest/ provenance attestations for ref-update certificates
|
||||
└── icaptcha-client/ client for the iCaptcha proof-of-intelligence service
|
||||
└── git-remote-gitlawb/ git remote helper for gitlawb:// URLs
|
||||
docs/ Operator guides
|
||||
scripts/ Build helpers
|
||||
```
|
||||
@@ -108,7 +106,7 @@ cargo test -p gitlawb-node
|
||||
|
||||
- **TypeScript SDK** (`@gitlawb/sdk`) — client library for the HTTP API
|
||||
- **Python SDK** (`gitlawb`) — for ML/agent pipeline integration
|
||||
- **UCAN authorization** — add trusted issuer anchoring, capability checks, and authorization-aware revocation
|
||||
- **UCAN chain validation** — complete the auth middleware
|
||||
- **Filecoin storage tier** — wire up cold storage deals
|
||||
- **Documentation** — guides, tutorials, API examples
|
||||
- **Node operators** — run a public node and report issues
|
||||
|
||||
Generated
+9
-10
@@ -2630,7 +2630,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7ab67060fc6b8ef687992d439ca0fa36e7ed17e9a0b16b25b601e8757df720de"
|
||||
dependencies = [
|
||||
"data-encoding",
|
||||
"syn 1.0.109",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3002,7 +3002,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3427,7 +3427,6 @@ dependencies = [
|
||||
"sha2",
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"url",
|
||||
"uuid",
|
||||
"zeroize",
|
||||
]
|
||||
@@ -3543,9 +3542,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "h2"
|
||||
version = "0.4.18"
|
||||
version = "0.4.13"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "839c0e8a181239723652be9062bb56ca5bf5f64011f73b623f6f4fc59086a228"
|
||||
checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54"
|
||||
dependencies = [
|
||||
"atomic-waker",
|
||||
"bytes",
|
||||
@@ -3864,7 +3863,7 @@ dependencies = [
|
||||
"libc",
|
||||
"percent-encoding",
|
||||
"pin-project-lite",
|
||||
"socket2 0.5.10",
|
||||
"socket2 0.6.3",
|
||||
"tokio",
|
||||
"tower-service",
|
||||
"tracing",
|
||||
@@ -5432,7 +5431,7 @@ dependencies = [
|
||||
"quinn-udp",
|
||||
"rustc-hash",
|
||||
"rustls",
|
||||
"socket2 0.5.10",
|
||||
"socket2 0.6.3",
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"tracing",
|
||||
@@ -5469,7 +5468,7 @@ dependencies = [
|
||||
"cfg_aliases",
|
||||
"libc",
|
||||
"once_cell",
|
||||
"socket2 0.5.10",
|
||||
"socket2 0.6.3",
|
||||
"tracing",
|
||||
"windows-sys 0.52.0",
|
||||
]
|
||||
@@ -5901,7 +5900,7 @@ dependencies = [
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -6795,7 +6794,7 @@ dependencies = [
|
||||
"getrandom 0.4.2",
|
||||
"once_cell",
|
||||
"rustix",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
@@ -53,9 +53,6 @@ chrono = { version = "0.4", features = ["serde"] }
|
||||
uuid = { version = "1", features = ["v4"] }
|
||||
# http client
|
||||
reqwest = { version = "0.12", features = ["blocking", "json", "multipart", "rustls-tls"], default-features = false }
|
||||
# URL parsing (what reqwest::Url re-exports, so the shared redirect predicate can
|
||||
# take a parsed URL without pulling reqwest into gitlawb-core)
|
||||
url = "2"
|
||||
# HMAC
|
||||
hmac = "0.12"
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ The mission is simple: once code is pushed to the network, it should not disappe
|
||||
|
||||
## What is in this repository?
|
||||
|
||||
This is a Rust workspace with six crates:
|
||||
This is a Rust workspace with four crates:
|
||||
|
||||
| Crate | Purpose |
|
||||
|---|---|
|
||||
@@ -27,8 +27,6 @@ This is a Rust workspace with six crates:
|
||||
| `gl` | The Gitlawb CLI for identity, repos, issues, PRs, bounties, tasks, peers, node status, MCP, and setup flows. |
|
||||
| `git-remote-gitlawb` | Git remote helper for `gitlawb://` URLs, so normal `git clone`, `git fetch`, and `git push` can talk to Gitlawb nodes. |
|
||||
| `gitlawb-core` | Shared primitives: Ed25519 identities, `did:key`, CIDs, RFC 9421 HTTP signatures, certificates, and UCAN tokens. |
|
||||
| `gitlawb-attest` | Pluggable external provenance attestations for ref-update certificates. |
|
||||
| `icaptcha-client` | Client for the iCaptcha proof-of-intelligence flow used to protect spam-prone writes. |
|
||||
|
||||
---
|
||||
|
||||
@@ -56,7 +54,6 @@ Good today:
|
||||
- Bare git repository storage.
|
||||
- Git smart-HTTP clone/fetch/push.
|
||||
- RFC 9421-signed writes.
|
||||
- Repository and path-scoped visibility enforcement for repository and Git content reads, with 404-shaped repository denials.
|
||||
- DID identities.
|
||||
- `gl` CLI workflows.
|
||||
- libp2p peer discovery/gossip foundation.
|
||||
@@ -66,13 +63,11 @@ Good today:
|
||||
|
||||
Known limitations:
|
||||
|
||||
- Repository write authorization is not secure by default: `GITLAWB_ENFORCE_OWNER_PUSH` defaults to `false` for compatibility, so a valid HTTP Signature identifies a pusher but does not enforce owner-only pushes.
|
||||
- UCAN proof chains are validated when supplied, but UCAN capabilities are not consulted by write authorization and the root issuer is not independently trust-anchored. UCANs therefore do not yet grant scoped collaborator access.
|
||||
- Agent lifecycle revocation is not enforced by HTTP Signature authorization; do not rely on removing or revoking an agent record to block a compromised signer.
|
||||
- Read visibility is not a blanket data-classification boundary: task, IPFS-pin, and Arweave-anchor listings are not repository-gated; withheld path names can be visible to a root reader; and later visibility changes cannot retract content already announced or externally anchored.
|
||||
- Private repository read enforcement is not wired yet. Treat public nodes as public infrastructure unless you restrict access at your proxy/firewall.
|
||||
- UCAN chain validation and revocation are not complete.
|
||||
- Repository write authorization is not capability-complete yet; HTTP signatures prove identity, not full authorization policy.
|
||||
- Peer writes are signed by upgraded nodes, but strict signed-peer enforcement is opt-in during rolling upgrades.
|
||||
- Current GraphQL mutations require an authenticated signer, but there is no mutation-specific guardrail that prevents a future mutation from omitting that check.
|
||||
- Pull-request review comments do not yet have threaded line-level anchors, and merges do not enforce approval requirements.
|
||||
- GraphQL mutations need mutation-aware auth before becoming a public write surface.
|
||||
|
||||
See:
|
||||
|
||||
@@ -229,53 +224,6 @@ Notes:
|
||||
sends the bearer token **only** to your configured origin, never to a URL a
|
||||
node advertises, so a hostile node can't capture the key or redirect the solve.
|
||||
|
||||
### Fetching an object by CID
|
||||
|
||||
```bash
|
||||
gl ipfs list # CIDs this node has pinned
|
||||
gl ipfs get bafkrei... > object.bin # object bytes on stdout
|
||||
```
|
||||
|
||||
Objects that were pinned before the node started recording which repo they came
|
||||
from are found by scanning its repo inventory, and that scan stops at the
|
||||
per-request ceilings in the [Configuration](#configuration) table. A stopped scan
|
||||
answers 503 with a resume token instead of a false "not found", and `gl ipfs get`
|
||||
follows the token automatically: up to 8 resumes after the first request, so at
|
||||
most 9 calls to the node, waiting between attempts for as long as the node's
|
||||
`Retry-After` asks and never longer than 5 seconds.
|
||||
|
||||
The whole ladder runs under a 60 second wall-clock deadline. The deadline bounds
|
||||
the search, not the download: each attempt gets the time left on it to produce
|
||||
response headers, and once an object is found its bytes stream outside that
|
||||
deadline. They are not unbounded, though. The client's own 30 second HTTP timeout
|
||||
is a total request timeout, running from the start of a request until its body
|
||||
has finished, so a transfer still going 30 seconds after its request began is cut
|
||||
off. Waits between attempts never run past the deadline either, so a single run
|
||||
spends at most around 90 seconds on the network: the deadline plus the 30 second
|
||||
timeout covering the last attempt. Writing the object out sits outside both
|
||||
bounds, so piping into a reader that stops reading can hold the command open
|
||||
longer than that.
|
||||
|
||||
Two node-side brakes end a ladder early and are reported rather than retried
|
||||
around. A 429 is terminal, because the node's rate-limit window is an hour and
|
||||
that wait cannot be honored inside one invocation; a transient overload (a 503
|
||||
carrying no incomplete-scan code) is retried on the token already held, under the
|
||||
same cap, clamp and deadline. The per-IP fanout brake can also stop a ladder well
|
||||
short of the 9 calls, so automatic resumption is not a guarantee of reaching the
|
||||
object.
|
||||
|
||||
When a bound stops the ladder with a usable token in hand, the command prints the
|
||||
token and the invocation that continues from it before exiting nonzero:
|
||||
|
||||
```txt
|
||||
resume from where this stopped: gl ipfs get bafkrei... --scan <token>
|
||||
```
|
||||
|
||||
Run that to carry on from where the scan stopped. Re-running without `--scan`
|
||||
restarts at the first row, reproduces the same truncation and spends the node's
|
||||
per-IP budget again, so the token is the only thing that makes progress. Tokens
|
||||
are valid for an hour.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
@@ -361,7 +309,7 @@ POST /api/v1/peers/announce
|
||||
POST /api/v1/sync/notify
|
||||
```
|
||||
|
||||
When `GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false`, unsigned legacy peers are accepted on those two routes, but signed requests are verified when signature headers are present. Staged rollout relaxes who may announce, not who owns a peer row. An unsigned announce may register a previously unseen peer, and it may refresh an existing row whose `http_url` is unchanged, but changing an existing peer's `http_url` requires an RFC 9421 signature from that peer's own DID and is refused with 403 otherwise. An unsigned announce can only register a `did:key`, since that is the only method whose verifying key can be resolved and therefore the only kind of row anyone could ever correct through the signed path; any other DID is refused with 400. Once all live peers upgrade, operators can set:
|
||||
When `GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false`, unsigned legacy peers are accepted on those two routes, but signed requests are verified when signature headers are present. Once all live peers upgrade, operators can set:
|
||||
|
||||
```bash
|
||||
GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true
|
||||
@@ -392,8 +340,7 @@ Important node settings:
|
||||
| `GITLAWB_BOOTSTRAP_PEERS` | Comma-separated HTTP peer URLs. |
|
||||
| `GITLAWB_P2P_BOOTSTRAP` | Comma-separated libp2p multiaddrs. |
|
||||
| `GITLAWB_BOOTSTRAP_DISABLE_SEEDS` | Disable embedded seed peers for isolated dev/test networks. |
|
||||
| `GITLAWB_REQUIRE_SIGNED_PEER_WRITES` | Require signed peer announce/sync writes. Defaults to `false` during the staged rollout below. |
|
||||
| `GITLAWB_ENFORCE_OWNER_PUSH` | Require the authenticated pusher to be the repo owner on `git-receive-pack`. **Defaults to `true`.** A `did:key` signature is authentication, not authorization — anyone can mint a key and sign — so with this off every signed caller may push to every repository, private ones included. Delegated and CI keys count as non-owners: a UCAN `git/push` capability is verified but not yet honored for authorization, so they cannot push while this is on. Set `false` only for a rolling upgrade; see [`docs/RUN-A-NODE.md`](docs/RUN-A-NODE.md). |
|
||||
| `GITLAWB_REQUIRE_SIGNED_PEER_WRITES` | Require signed peer announce/sync writes. |
|
||||
| `GITLAWB_AUTO_SYNC` | Enable automatic sync from known peers. |
|
||||
| `GITLAWB_MAX_PACK_BYTES` | Max git pack body size for smart-HTTP routes. |
|
||||
| `GITLAWB_GIT_SERVICE_TIMEOUT_SECS` | Max seconds a served git upload-pack, receive-pack, or `info/refs` advertisement may run before it is aborted (504). Default 600. Also bounds the withheld-blob classification walk (on both the upload-pack serve and receive-pack replication paths) and the push-side pin-candidate discovery (`rev-list` / `cat-file`), each reaped via process-group teardown at the deadline. On the path-scoped upload-pack path the classification walk and the pack serve share ONE deadline, so this value bounds their combined duration rather than granting each stage a full budget: a walk that consumes it leaves the serve nothing and the clone gets a 504. Serving large path-scoped repos may therefore need a higher value than they did when each stage was budgeted separately. Accepted range is 1 to 3153600000 (100 years), since the node derives deadlines from this value and a larger one cannot be represented. |
|
||||
@@ -405,12 +352,9 @@ Important node settings:
|
||||
| `GITLAWB_REPO_LEASE_MAX_WAITERS` | Max pushes parked at once waiting for the same repo's write lease. Each waiter pins its buffered pack body, so this bounds that memory for a hot repo; past the cap the newest push sheds a 503 + Retry-After instead of queueing. Pushes to other repos are unaffected, and the lease holder is not counted. Default 8. |
|
||||
| `GITLAWB_MAX_CONCURRENT_IPFS_WALKS` | Max concurrent `GET /ipfs/{cid}` visibility walks across all callers (own pool, disjoint from the served-git pools); over-cap sheds 503. Default 32. |
|
||||
| `GITLAWB_IPFS_WALK_PER_SOURCE` | Max concurrent `/ipfs` walks a single source IP may hold. Default 4. |
|
||||
| `GITLAWB_IPFS_MAX_LEGACY_PROBES` | Max legacy (NULL-provenance) repos probed per `/ipfs/{cid}` request, bounding the scan-fallback fan-out. A truncated scan returns a retryable 503, not a false 404. Default 256. |
|
||||
| `GITLAWB_IPFS_MAX_LEGACY_SCAN_ROWS` | Max repo rows one `/ipfs/{cid}` request's legacy scan may read from the database. The probe ceiling above only starts counting once a probe runs, and quarantined or private repos are denied before that, so this is what bounds a scan over an inventory that denies the caller everywhere. A truncated scan sheds a retryable 503 carrying an opaque `continuation` token; echoing it as `?scan=` resumes the scan where it stopped. Every per-request ceiling on this path (rows, probes, visits, retained rule bytes) mints one, so each request advances the ladder by at least the rows it read and a holder buried past a ceiling is reached in a bounded number of requests, `ceil(repos / ceiling) + 1` when this row ceiling is the one that binds. No ceiling ever produces a 404. Every page is charged to the caller's `/ipfs` work allowance, so raising this raises that allowance too. Lowering it sharpens an oracle: because a truncation emits a token and a completed wrap does not, laddering to the end reveals the node's total repo count (private and quarantined included) to within one ceiling. Default 2048. |
|
||||
| `GITLAWB_IPFS_MAX_REPOS_WALKED` | Max expensive path-scope visibility walks a `/ipfs/{cid}` request may run per phase; over-cap repos are skipped and the scan continues, shedding a retryable 503 (not a false 404) if the object is then found nowhere. The effective cap is the tighter of this knob and the node's internal history-walk ceiling of 17 (`MAX_PIN_SOURCES + 1`), so a value above 17 has no effect while a value below it does tighten the cap. It is charged per phase: the provenance lookup and the legacy-scan fallback get separate equal budgets, so one request can run up to twice the cap in total. Default 64. |
|
||||
| `GITLAWB_IPFS_MAX_REPOS_WALKED` | Max expensive path-scope visibility walks per `/ipfs/{cid}` request; over-cap repos are skipped and the scan continues, shedding a retryable 503 (not a false 404) if the object is then found nowhere. Default 64. |
|
||||
| `GITLAWB_IPFS_MAX_REPO_VISITS` | Ceiling on repos one `/ipfs/{cid}` request may visit (acquire + probe) past the visibility gate. Also the worst-case per-request Tigris fetch count. On exhaustion the scan stops with a retryable 503. Default 1024. |
|
||||
| `GITLAWB_IPFS_REQUEST_BUDGET_SECS` | Absolute wall-clock budget for one admitted `/ipfs/{cid}` request's acquire+walk lifetime. Per-stage clamps bound the acquire and walk stages to the remaining budget, and no stage starts once it is exhausted; the scan then stops with a retryable 503. The object-type probe and content-read `cat-file` subprocesses are budget-checked before starting and each also run under their own deadline (the lesser of `GITLAWB_GIT_SERVICE_TIMEOUT_SECS` and the remaining budget), reaped via process-group teardown, so a hung `cat-file` cannot hold the request's walk slot past it. One hang path is still unbounded: the probe's object-store readability check is a plain filesystem sweep with nothing to reap, so a wedged filesystem can hold the slot past the deadline. Default 600. Accepted range is 1 to 3153600000 (100 years), since the node derives a deadline from this value and a larger one cannot be represented. |
|
||||
| `GITLAWB_IPFS_RESOLVE_BUDGET_SECS` | Shorter budget for the pre-walk CID resolve inside an admitted `/ipfs/{cid}` request: the lookup that maps the requested CID to its git oid(s), which runs while the scarce walk admission is already held. A well-formed CID with no pin row does no probe and no walk work, so without this it could hold a walk slot for the whole request budget while nothing walked, and enough such requests shed every real retrieval at admission. The effective deadline is the lesser of this and the remaining request budget, so a value above `GITLAWB_IPFS_REQUEST_BUDGET_SECS` degrades to the request budget. Only the resolve is on this clock; walk and probe work stay on the request budget, so a slow but progressing scan is never shed by it. Default 10. Accepted range is 1 to 3153600000 (100 years). |
|
||||
| `GITLAWB_IPFS_RATE_LIMIT` | Max `/ipfs/{cid}` requests per client IP per hour (route flood brake). 0 disables. Default 600. |
|
||||
| `GITLAWB_TIGRIS_BUCKET` | Optional S3/Tigris shared repo storage bucket. |
|
||||
| `GITLAWB_PINATA_JWT` | Optional Pinata/IPFS warm-storage pinning. |
|
||||
@@ -418,8 +362,6 @@ Important node settings:
|
||||
|
||||
Production note: change the default Postgres password before exposing a node publicly.
|
||||
|
||||
Legacy-pin window: releases before the CID-resolver work stored the provider CID (Kubo dag-pb / Pinata) as a pinned object's resolver key. The `/ipfs/{cid}` resolver now recomputes the raw-content CID from the object bytes and refuses to serve a key that does not match, so `GET /api/v1/ipfs/pins` can still advertise an unrepaired legacy CID that 404s. Such a row is repaired opportunistically the next time a push carries the object again (its key is rewritten to the raw CID, the old value kept in `legacy_provider_cid`), but git negotiation omits objects the node already has, so most legacy rows never re-enter a push delta. A deferred one-shot startup sweep, not this opportunistic path, is what fully retires the advertise-then-404 window. Rows whose object bytes are gone stay withheld.
|
||||
|
||||
---
|
||||
|
||||
## Optional node staking
|
||||
@@ -524,8 +466,8 @@ Short-term priorities:
|
||||
2. Add Docker and installer smoke tests.
|
||||
3. Improve operator docs and `gl doctor` checks.
|
||||
4. Harden peer writes and publish the signed-peer rollout plan.
|
||||
5. Close default-open write authorization and wire trusted UCAN delegation into repository permissions.
|
||||
6. Add threaded, line-level pull-request discussions and enforce approval requirements on merges.
|
||||
5. Implement repo write authorization: owner checks, protected branches, and UCAN capability checks.
|
||||
6. Implement private-read enforcement or remove private repo affordances until it exists.
|
||||
7. Add metrics for pushes, fetches, pack sizes, peer sync, failed auth, and webhooks.
|
||||
|
||||
Product direction:
|
||||
|
||||
+22
-32
@@ -28,11 +28,10 @@ We will acknowledge receipt within 48 hours and aim to release a fix within 14 d
|
||||
- Every git object is content-addressed via CIDv1 (SHA-256)
|
||||
- Tamper-evident by construction — a modified object changes its CID
|
||||
|
||||
**UCAN token validation**
|
||||
- Bootstrap UCAN tokens are issued at registration.
|
||||
- A supplied token's signature, audience, expiry, and proof-chain attenuation are validated.
|
||||
- Tokens use a signed JSON wire format with expiry.
|
||||
- Capability grants are not yet consulted by repository write authorization; see the limitations below.
|
||||
**UCAN capability tokens**
|
||||
- Bootstrap UCAN tokens issued at registration
|
||||
- Capability-scoped: `git:push`, `git:fetch`, `issue:create`, `pr:open`
|
||||
- JWT-format tokens with expiry
|
||||
|
||||
**Smart contracts (Base Sepolia testnet)**
|
||||
- `GitlawbDIDRegistry` — on-chain DID → document registry
|
||||
@@ -49,20 +48,21 @@ We will acknowledge receipt within 48 hours and aim to release a fix within 14 d
|
||||
|
||||
---
|
||||
|
||||
## Known Limitations
|
||||
## Known Limitations (Planned for v0.2)
|
||||
|
||||
These are documented limitations of the current live release. They should be prioritized without breaking existing nodes during rolling upgrades.
|
||||
These are **documented, accepted limitations** for the current live release and should be prioritized without breaking existing nodes during rolling upgrades.
|
||||
|
||||
### Repository write authorization defaults
|
||||
- `git-receive-pack` verifies HTTP Signatures, but `GITLAWB_ENFORCE_OWNER_PUSH` defaults to `false` for compatibility during rollout.
|
||||
- **Impact:** With the default setting, a valid signature authenticates the pusher but does not require that DID to be the repository owner.
|
||||
- **Mitigation:** Set `GITLAWB_ENFORCE_OWNER_PUSH=true` on nodes where owner-only pushes are required. Confirm that every legitimate pusher uses the owner DID before enabling it.
|
||||
### UCAN chain validation
|
||||
- The auth middleware verifies HTTP Signatures and token structure, but does not yet walk the full UCAN delegation chain.
|
||||
- **Impact:** A node cannot yet enforce fine-grained capability delegation. Currently, any registered agent with a valid HTTP Signature can push.
|
||||
- **Mitigation:** Keep write endpoints signed, treat public nodes as public infrastructure, and treat trust scores as soft rate-limiting signals rather than authorization.
|
||||
- **Fix target:** v0.2
|
||||
|
||||
### UCAN delegation and revocation
|
||||
- The middleware validates a supplied UCAN's complete proof chain, but a root token is accepted without an independently trusted issuer anchor. `Ucan::can` is not yet used by write handlers, so a UCAN does not grant scoped repository access.
|
||||
- Agent lifecycle revocation is not checked by HTTP Signature authorization. Removing or revoking an agent record does not itself block a compromised DID from authenticating.
|
||||
- **Impact:** Do not use UCANs for collaborator permissions or rely on agent-record revocation as a key-compromise response.
|
||||
- **Mitigation:** Keep sensitive deployments behind operational network controls and enable owner-only push enforcement where it fits the deployment until trusted delegation and authorization-aware revocation are implemented.
|
||||
### UCAN revocation
|
||||
- Issued UCAN tokens cannot be revoked before expiry.
|
||||
- **Impact:** If a keypair is compromised, the attacker retains access until the UCAN expires (default: 30 days).
|
||||
- **Mitigation:** Regenerate your identity (`gl identity new --force`) and re-register to issue a new UCAN. Until revocation/blocklisting is implemented, operators should remove compromised DIDs directly from their local database.
|
||||
- **Fix target:** v0.2
|
||||
|
||||
### git-receive-pack authentication
|
||||
- The `git-receive-pack` endpoint enforces HTTP Signature auth. Plain Git smart-HTTP clients do not generate those headers, so the `git-remote-gitlawb` helper is required for pushes.
|
||||
@@ -71,20 +71,10 @@ These are documented limitations of the current live release. They should be pri
|
||||
- **Fix target:** v0.2
|
||||
|
||||
### Private repository reads
|
||||
- Repository and path-scoped visibility checks are enforced for repository API and Git content reads. A denied whole-repository or root read returns the same 404 shape as a missing repository, so the denial does not reveal private-repository existence.
|
||||
- Sparse-clone support exposes withheld path globs to callers who may read the repository root. Do not put sensitive information in withheld path names.
|
||||
- `GET /api/v1/tasks`, `/api/v1/ipfs/pins`, and `/api/v1/arweave/anchors` are not repository-gated. Task records include a UCAN token; pin and anchor listings expose object and ref metadata.
|
||||
- Changing a repository's visibility controls future serving, but cannot retract ref metadata or configured external pins and anchors already announced while the repository was public. Do not push secrets to an announceable repository.
|
||||
- **Impact:** Visibility policies protect the repository and Git content routes they gate, not every metadata endpoint or previously published content.
|
||||
- **Remaining boundary:** This read control does not address the independent write-authorization and UCAN-delegation limitations described above.
|
||||
|
||||
### Pull-request review enforcement
|
||||
- Pull-request review comments are not yet threaded or line-anchored, and merges do not enforce required approvals.
|
||||
- **Impact:** Teams must use their own review policy or external controls for merge approval requirements.
|
||||
|
||||
### GraphQL mutation coverage
|
||||
- Existing GraphQL mutations require an authenticated signer, but a mutation-specific source-level guardrail has not yet been added for future mutations.
|
||||
- **Impact:** A new mutation could accidentally omit its signer check without an explicit test fence.
|
||||
- Repository records have an `is_public` field and the node exposes `GITLAWB_PUBLIC_READ`, but per-repository private-read enforcement is not wired in the current live release.
|
||||
- **Impact:** Do not store private repositories or secrets on public nodes.
|
||||
- **Mitigation:** Run isolated nodes for non-public data and restrict network access at the reverse proxy or firewall layer.
|
||||
- **Fix target:** v0.2
|
||||
|
||||
### Peer route hardening rollout
|
||||
- Peer announce and sync notification routes accept signed requests and verify DID matches when a signature is present.
|
||||
@@ -111,7 +101,7 @@ These are documented limitations of the current live release. They should be pri
|
||||
| Key storage | PKCS#8 PEM, 0600 permissions |
|
||||
| Content hashing | SHA-256 via CIDv1 |
|
||||
| HTTP Signatures | RFC 9421 (Ed25519 + SHA-256 Content-Digest) |
|
||||
| UCAN tokens | Signed JSON object (Ed25519 signature) |
|
||||
| UCAN tokens | JWT (Ed25519 signatures) |
|
||||
| On-chain | ECDSA secp256k1 (Base L2 / Ethereum) |
|
||||
|
||||
---
|
||||
@@ -119,7 +109,7 @@ These are documented limitations of the current live release. They should be pri
|
||||
## Threat Model
|
||||
|
||||
gitlawb is designed to be secure against:
|
||||
- **Unauthenticated writes** — HTTP Signature auth on protected write endpoints; see Known Limitations for owner and capability authorization gaps
|
||||
- **Unauthorized writes** — HTTP Signature auth on all write endpoints
|
||||
- **Tampered git objects** — CIDv1 content addressing detects modification
|
||||
- **Identity spoofing** — DIDs derived from public keys, unforgeable without the private key
|
||||
- **Centralized takedown** — no single point of control; data on IPFS + Arweave
|
||||
|
||||
@@ -11,7 +11,7 @@ name = "git-remote-gitlawb"
|
||||
path = "src/main.rs"
|
||||
|
||||
[dependencies]
|
||||
gitlawb-core = { path = "../gitlawb-core", features = ["redirect"] }
|
||||
gitlawb-core = { path = "../gitlawb-core" }
|
||||
anyhow = { workspace = true }
|
||||
reqwest = { workspace = true }
|
||||
tracing = { workspace = true }
|
||||
|
||||
@@ -199,7 +199,9 @@ fn handle_connect<R: Read>(
|
||||
other => bail!("unsupported git service: {other}"),
|
||||
}
|
||||
|
||||
let client = build_http_client()?;
|
||||
let client = reqwest::blocking::Client::builder()
|
||||
.timeout(std::time::Duration::from_secs(300))
|
||||
.build()?;
|
||||
|
||||
// ── Phase 1: ref advertisement (GET /info/refs?service=<service>) ─────────
|
||||
//
|
||||
@@ -318,58 +320,6 @@ fn handle_connect<R: Read>(
|
||||
)
|
||||
}
|
||||
|
||||
// ── HTTP client ───────────────────────────────────────────────────────────────
|
||||
|
||||
/// Total request timeout. A pack transfer can be large and slow, so this is far
|
||||
/// wider than the CLI's.
|
||||
const HTTP_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(300);
|
||||
|
||||
/// The one client both phases use, with the redirect policy the signing surfaces
|
||||
/// need.
|
||||
///
|
||||
/// Every request this client sends can carry RFC 9421 `Signature` and
|
||||
/// `Signature-Input` headers: a push signs from the first request, and a fetch of a
|
||||
/// private repo signs on the retry. reqwest strips only `Authorization`, `Cookie`,
|
||||
/// `Proxy-Authorization` and `WWW-Authenticate` across hosts, so under the default
|
||||
/// `Policy::limited(10)` those signature headers rode a 302 to whatever origin the
|
||||
/// node named, and on a 307/308 the pack body went with them. Scope the follow to the
|
||||
/// origin that issued the redirect AND to an identical request-target, which is the
|
||||
/// same predicate `gl` uses.
|
||||
fn build_http_client() -> Result<reqwest::blocking::Client> {
|
||||
Ok(reqwest::blocking::Client::builder()
|
||||
.timeout(HTTP_TIMEOUT)
|
||||
.redirect(reqwest::redirect::Policy::custom(same_origin_redirect))
|
||||
.build()?)
|
||||
}
|
||||
|
||||
/// Refuse any redirect that leaves the issuing origin or rewrites the request-target,
|
||||
/// and bound the chain.
|
||||
///
|
||||
/// Refusal is `stop`, not `error`: the 3xx comes back as an ordinary response and
|
||||
/// the caller reports it through the status path it already has.
|
||||
///
|
||||
/// `Policy::custom` replaces reqwest's built-in limit, so the chain bound is
|
||||
/// restated. It is not what makes the request finite (`HTTP_TIMEOUT` covers the whole
|
||||
/// chain); it is what keeps a node that redirects to itself from costing a request
|
||||
/// per round trip until that timeout. `>` and not `>=` because reqwest pushes the
|
||||
/// redirecting URL onto `previous` before consulting the policy, which is how
|
||||
/// `Policy::limited` reads the same counter.
|
||||
fn same_origin_redirect(attempt: reqwest::redirect::Attempt<'_>) -> reqwest::redirect::Action {
|
||||
let Some(previous) = attempt.previous().last() else {
|
||||
// Unreachable through reqwest, which pushes the redirecting URL first, but
|
||||
// the safe reading of "cannot prove same-origin" is to refuse.
|
||||
return attempt.stop();
|
||||
};
|
||||
if attempt.previous().len() > gitlawb_core::redirect::MAX_REDIRECTS {
|
||||
return attempt.stop();
|
||||
}
|
||||
if gitlawb_core::redirect::may_follow(previous, attempt.url()) {
|
||||
attempt.follow()
|
||||
} else {
|
||||
attempt.stop()
|
||||
}
|
||||
}
|
||||
|
||||
// ── Smart-protocol request builders ───────────────────────────────────────────
|
||||
|
||||
const USER_AGENT: &str = "git/2.0 git-remote-gitlawb/0.1.0";
|
||||
@@ -908,438 +858,6 @@ mod tests {
|
||||
String::from_utf8_lossy(&buf).into_owned()
|
||||
}
|
||||
|
||||
/// The signed headers must not survive a redirect off the node's origin, on
|
||||
/// EITHER phase.
|
||||
///
|
||||
/// This is the binary git runs for `clone`, `fetch` and `push`. It built its
|
||||
/// client with a timeout and nothing else, so it ran reqwest's default
|
||||
/// `Policy::limited(10)`, and reqwest's cross-host header stripping covers
|
||||
/// `Authorization`, `Cookie`, `Proxy-Authorization` and `WWW-Authenticate` only.
|
||||
/// `Signature` and `Signature-Input` came straight through. A push signs from the
|
||||
/// first request, so a hostile node answering 302 was handed a working credential,
|
||||
/// and a 307/308 would have taken the pack body along.
|
||||
///
|
||||
/// Two mockito servers are two ports on one host, which is the boundary this
|
||||
/// policy draws. The second server answers everything and expects nothing, with a
|
||||
/// second mock matching on the `signature` header also at zero, so a followed
|
||||
/// redirect fails whether or not the signature came with it. Phase 1 is driven
|
||||
/// with a 302 and Phase 2 with a 308, the status that would carry the body.
|
||||
///
|
||||
/// MUTATION (RED): drop the `.redirect(...)` line from `build_http_client`.
|
||||
#[test]
|
||||
fn signed_requests_do_not_follow_a_redirect_off_the_node_origin() {
|
||||
let kp = Keypair::generate();
|
||||
let client = build_http_client().unwrap();
|
||||
|
||||
let mut elsewhere = mockito::Server::new();
|
||||
let never = elsewhere
|
||||
.mock("GET", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_body("bytes from the redirect target")
|
||||
.expect(0)
|
||||
.create();
|
||||
let never_post = elsewhere
|
||||
.mock("POST", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create();
|
||||
let signature_seen_get = elsewhere
|
||||
.mock("GET", mockito::Matcher::Any)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create();
|
||||
let signature_seen_post = elsewhere
|
||||
.mock("POST", mockito::Matcher::Any)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create();
|
||||
|
||||
let mut node = mockito::Server::new();
|
||||
let repo_base = format!("{}/zOwner/myrepo", node.url());
|
||||
let bounce_get = node
|
||||
.mock("GET", mockito::Matcher::Regex(r"/info/refs".to_string()))
|
||||
.with_status(302)
|
||||
.with_header("location", &format!("{}/info/refs", elsewhere.url()))
|
||||
.expect(1)
|
||||
.create();
|
||||
let bounce_post = node
|
||||
.mock(
|
||||
"POST",
|
||||
mockito::Matcher::Regex(r"/git-receive-pack$".to_string()),
|
||||
)
|
||||
.with_status(308)
|
||||
.with_header("location", &format!("{}/git-receive-pack", elsewhere.url()))
|
||||
.expect(1)
|
||||
.create();
|
||||
|
||||
let refs_url = format!("{repo_base}/info/refs?service=git-receive-pack");
|
||||
let advertisement = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.unwrap();
|
||||
|
||||
let body = b"0009done\n".to_vec();
|
||||
let post_url = format!("{repo_base}/git-receive-pack");
|
||||
let pack_post =
|
||||
build_pack_post_request(&client, &post_url, "git-receive-pack", &body, Some(&kp))
|
||||
.body(body.clone())
|
||||
.send()
|
||||
.unwrap();
|
||||
|
||||
// The other origin first: it is the assertion that names the leak, and it must
|
||||
// be the one that speaks when a followed redirect makes every one of these
|
||||
// fail at once.
|
||||
never.assert();
|
||||
never_post.assert();
|
||||
signature_seen_get.assert();
|
||||
signature_seen_post.assert();
|
||||
bounce_get.assert();
|
||||
bounce_post.assert();
|
||||
|
||||
assert_eq!(
|
||||
advertisement.status(),
|
||||
302,
|
||||
"a refused redirect stops rather than errors, so the caller sees the 3xx"
|
||||
);
|
||||
assert!(
|
||||
!advertisement
|
||||
.text()
|
||||
.unwrap()
|
||||
.contains("bytes from the redirect target"),
|
||||
"the redirect target's bytes must never reach the caller"
|
||||
);
|
||||
assert_eq!(
|
||||
pack_post.status(),
|
||||
308,
|
||||
"the pack POST stops at the redirect too"
|
||||
);
|
||||
}
|
||||
|
||||
/// A same-origin hop that REWRITES the request-target is refused, even though the
|
||||
/// origin never changes.
|
||||
///
|
||||
/// The signature binds `@path` as the literal path-and-query the helper signed, and
|
||||
/// the node rebuilds it from the URI it received. An `info/refs` to `info/refs/`
|
||||
/// bounce therefore presents a signature over a target the node never saw, so a
|
||||
/// clone or push behind such a proxy 401s. Refusing the hop hands the caller the
|
||||
/// 3xx that names what happened instead.
|
||||
///
|
||||
/// The target mock expects zero hits and is asserted: mockito only checks
|
||||
/// `.expect(N)` when `.assert()` runs, so an unbound or unasserted mock passes
|
||||
/// vacuously.
|
||||
#[test]
|
||||
fn a_same_origin_path_changing_redirect_is_refused() {
|
||||
let kp = Keypair::generate();
|
||||
let client = build_http_client().unwrap();
|
||||
|
||||
let mut node = mockito::Server::new();
|
||||
let bounce = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs")
|
||||
.with_status(301)
|
||||
.with_header("location", "/zOwner/myrepo/info/refs/")
|
||||
.expect(1)
|
||||
.create();
|
||||
let target = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs/")
|
||||
.with_status(200)
|
||||
.with_body("bytes from the rewritten target")
|
||||
.expect(0)
|
||||
.create();
|
||||
|
||||
let refs_url = format!("{}/zOwner/myrepo/info/refs", node.url());
|
||||
let resp = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"a refused redirect stops rather than errors, so the caller sees the 3xx"
|
||||
);
|
||||
assert!(
|
||||
!resp
|
||||
.text()
|
||||
.unwrap()
|
||||
.contains("bytes from the rewritten target"),
|
||||
"the rewritten target's bytes must never reach the caller"
|
||||
);
|
||||
bounce.assert();
|
||||
target.assert();
|
||||
}
|
||||
|
||||
/// The other direction, and the only same-origin hop still followed: a redirect
|
||||
/// that re-issues the IDENTICAL request-target.
|
||||
///
|
||||
/// Without this the policy could be tightened to `Policy::none()` and nothing in
|
||||
/// this crate would notice. It is also the first executed coverage of the chain
|
||||
/// bound in `build_http_client`'s policy closure: the route answers 301 pointing at
|
||||
/// itself, so bounded it is hit once for the original request plus `MAX_REDIRECTS`
|
||||
/// follows and the call returns the 301 (a refused hop stops rather than errors).
|
||||
/// Unbounded it would spin until `HTTP_TIMEOUT`, costing the node a request per
|
||||
/// round trip. Its twin is `a_self_redirect_stops_at_the_chain_bound` in
|
||||
/// `crates/gl/src/http.rs`.
|
||||
#[test]
|
||||
fn an_identical_target_redirect_is_still_followed_up_to_the_chain_bound() {
|
||||
let kp = Keypair::generate();
|
||||
let client = build_http_client().unwrap();
|
||||
|
||||
let mut node = mockito::Server::new();
|
||||
let loop_route = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs")
|
||||
.with_status(301)
|
||||
.with_header("location", "/zOwner/myrepo/info/refs")
|
||||
.expect(gitlawb_core::redirect::MAX_REDIRECTS + 1)
|
||||
.create();
|
||||
|
||||
let refs_url = format!("{}/zOwner/myrepo/info/refs", node.url());
|
||||
let resp = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.expect("the bound must end the chain, not the timeout");
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"the chain ends by refusing the next hop, so the last 3xx is what comes back"
|
||||
);
|
||||
loop_route.assert();
|
||||
}
|
||||
|
||||
// ── the node's own verification, run over what the helper actually sent ──
|
||||
|
||||
/// What the verifying mock made of a request that reached it.
|
||||
///
|
||||
/// The empty slot (`None`) is its own state and means the mock was never hit at
|
||||
/// all, which is what the refusal test asserts. It must stay distinguishable from
|
||||
/// [`Verdict::WrongIdentity`], because "nobody verified anything" and "something
|
||||
/// verified against the wrong key" are opposite findings.
|
||||
///
|
||||
/// The payloads are read through `Debug` in the assertion messages and nowhere
|
||||
/// else, which the dead-code pass does not count; they carry the detail that makes
|
||||
/// a failure legible, so they stay.
|
||||
#[derive(Debug)]
|
||||
#[allow(dead_code)]
|
||||
enum Verdict {
|
||||
/// The chain accepted the signature AND the key it resolved is the test's DID.
|
||||
Accepted,
|
||||
/// The chain refused it. Carries the error so a failure reads as the actual
|
||||
/// rejection rather than a bare hit count.
|
||||
Rejected(String),
|
||||
/// The chain accepted a signature made by somebody else. A key resolved from
|
||||
/// the parsed `key_id` is read out of the artifact under verification, so an
|
||||
/// accept on it alone proves consistency, never authenticity.
|
||||
WrongIdentity { expected: String, got: String },
|
||||
}
|
||||
|
||||
/// The node's `require_signature` verification, over a request this crate did not
|
||||
/// necessarily build: parse the headers, recompute the content-digest from the
|
||||
/// body, rebuild the signing string over `@method`/`@path`/`content-digest`,
|
||||
/// Ed25519-verify. Returns the DID the signature resolved to, so a caller can pin
|
||||
/// the identity.
|
||||
///
|
||||
/// Its twin is the hand-copy in `crates/gl/src/http.rs`, which cannot import this
|
||||
/// module (this is a binary crate's test module). Keep the two textually identical
|
||||
/// apart from the mockito seam around them, so an edit to one is visibly an edit to
|
||||
/// both.
|
||||
///
|
||||
/// The production verifier both copies mirror is `crate::auth::require_signature` in
|
||||
/// `crates/gitlawb-node/src/auth/mod.rs`. This is a re-implementation, not a call, so
|
||||
/// an edit to that middleware has to land here too: otherwise the copies drift and
|
||||
/// this test keeps passing against a rule the node has stopped applying.
|
||||
///
|
||||
/// It asserts internally, which is deliberate but constrains its callers: inside
|
||||
/// `with_body_from_request` those assertions fire on the server thread and reach
|
||||
/// the client as a transport error, not as a recorded verdict. So the identity
|
||||
/// check lives in the caller as a [`Verdict`] variant, never as an assert in here.
|
||||
fn node_verifies(
|
||||
method: &str,
|
||||
path_and_query: &str,
|
||||
body: &[u8],
|
||||
sig_input: &str,
|
||||
sig_header: &str,
|
||||
content_digest: &str,
|
||||
) -> anyhow::Result<String> {
|
||||
use gitlawb_core::http_sig::{build_signing_string, compute_content_digest, HttpSignature};
|
||||
use gitlawb_core::identity::verify;
|
||||
use std::collections::HashMap;
|
||||
|
||||
let sig = HttpSignature::parse(sig_input, sig_header)?;
|
||||
sig.check_created()?;
|
||||
assert!(
|
||||
sig.missing_components().is_empty(),
|
||||
"signature must cover all required components"
|
||||
);
|
||||
assert_eq!(sig.alg, "ed25519");
|
||||
assert_eq!(
|
||||
content_digest,
|
||||
compute_content_digest(body),
|
||||
"content-digest must match the body"
|
||||
);
|
||||
let vk = sig.key_id.to_verifying_key()?;
|
||||
let mut values = HashMap::new();
|
||||
values.insert("@method".to_string(), method.to_uppercase());
|
||||
values.insert("@path".to_string(), path_and_query.to_string());
|
||||
values.insert("content-digest".to_string(), content_digest.to_string());
|
||||
let sig_params_value = sig_input.strip_prefix("sig1=").unwrap_or(sig_input);
|
||||
let components: Vec<&str> = sig.components.iter().map(String::as_str).collect();
|
||||
let signing_string = build_signing_string(&components, sig_params_value, &values)?;
|
||||
let sig_array: [u8; 64] = sig.signature_bytes.as_slice().try_into()?;
|
||||
verify(&vk, signing_string.as_bytes(), &sig_array)?;
|
||||
Ok(sig.key_id.to_string())
|
||||
}
|
||||
|
||||
/// Pull a header value off a received mockito request, or explain which one the
|
||||
/// helper failed to send.
|
||||
fn received_header(req: &mockito::Request, name: &str) -> String {
|
||||
req.header(name)
|
||||
.first()
|
||||
.unwrap_or_else(|| panic!("the helper sent no {name} header"))
|
||||
.to_str()
|
||||
.unwrap()
|
||||
.to_string()
|
||||
}
|
||||
|
||||
/// Run [`node_verifies`] over a GET that arrived at the mock and record what the
|
||||
/// node would have made of it, pinned to `expected_did`.
|
||||
fn record_get_verdict(
|
||||
req: &mockito::Request,
|
||||
expected_did: &str,
|
||||
slot: &std::sync::Arc<std::sync::Mutex<Option<Verdict>>>,
|
||||
) {
|
||||
let verdict = match node_verifies(
|
||||
"GET",
|
||||
req.path_and_query(),
|
||||
b"",
|
||||
&received_header(req, "signature-input"),
|
||||
&received_header(req, "signature"),
|
||||
&received_header(req, "content-digest"),
|
||||
) {
|
||||
Ok(did) if did == expected_did => Verdict::Accepted,
|
||||
Ok(did) => Verdict::WrongIdentity {
|
||||
expected: expected_did.to_string(),
|
||||
got: did,
|
||||
},
|
||||
Err(e) => Verdict::Rejected(e.to_string()),
|
||||
};
|
||||
*slot.lock().unwrap() = Some(verdict);
|
||||
}
|
||||
|
||||
/// The finding's repro, now a guard: a rewritten same-origin target must never
|
||||
/// receive the advertisement's signature, and the proof is the node's own
|
||||
/// verification, not a hit count.
|
||||
///
|
||||
/// Post-fix the hop is refused, so the slot stays empty. Pre-fix the hop is
|
||||
/// followed and the slot records the Ed25519 rejection of a signature made over
|
||||
/// `.../info/refs?service=git-upload-pack` and presented at `.../info/refs/...`,
|
||||
/// which is the 401 an operator behind such a proxy actually sees. The verdict is
|
||||
/// asserted first, so a failure speaks about verification rather than about
|
||||
/// reachability.
|
||||
///
|
||||
/// Its paired positive control is
|
||||
/// `a_direct_signed_advertisement_verifies_under_the_node_verifier`: without it, an
|
||||
/// empty slot would be satisfied just as well by a harness that can never record
|
||||
/// anything.
|
||||
#[test]
|
||||
fn a_rewritten_target_never_receives_the_signature() {
|
||||
let kp = Keypair::generate();
|
||||
let expected_did = kp.did().to_string();
|
||||
let client = build_http_client().unwrap();
|
||||
let slot = std::sync::Arc::new(std::sync::Mutex::new(None::<Verdict>));
|
||||
|
||||
let mut node = mockito::Server::new();
|
||||
let bounce = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs?service=git-upload-pack")
|
||||
.with_status(301)
|
||||
.with_header(
|
||||
"location",
|
||||
"/zOwner/myrepo/info/refs/?service=git-upload-pack",
|
||||
)
|
||||
.expect(1)
|
||||
.create();
|
||||
let recorder = slot.clone();
|
||||
let did_for_target = expected_did.clone();
|
||||
let target = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs/?service=git-upload-pack")
|
||||
.with_status(200)
|
||||
.with_body_from_request(move |req| {
|
||||
record_get_verdict(req, &did_for_target, &recorder);
|
||||
Vec::new()
|
||||
})
|
||||
.expect(0)
|
||||
.create();
|
||||
|
||||
let refs_url = format!(
|
||||
"{}/zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
node.url()
|
||||
);
|
||||
let resp = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.unwrap();
|
||||
|
||||
let verdict = slot.lock().unwrap().take();
|
||||
assert!(
|
||||
verdict.is_none(),
|
||||
"the node's own verifier must never see this request: the signature covers \
|
||||
/zOwner/myrepo/info/refs?service=git-upload-pack and the rewritten target \
|
||||
adds a trailing slash, so what arrives there is a stale request-target; \
|
||||
recorded verdict: {verdict:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"the caller sees the 3xx, not the rewritten target's answer"
|
||||
);
|
||||
bounce.assert();
|
||||
target.assert();
|
||||
}
|
||||
|
||||
/// The positive control for the test above, and the proof that the helper signs the
|
||||
/// query it sends.
|
||||
///
|
||||
/// A direct signed advertisement GET, no redirect anywhere, through the same
|
||||
/// verifying mock. The verdict must be `Accepted`, which is what makes the refusal
|
||||
/// test's empty slot attributable to the refusal rather than to a harness that
|
||||
/// cannot record. The advertisement URL carries `?service=`, so a helper that
|
||||
/// signed the bare path would land here as `Rejected`.
|
||||
#[test]
|
||||
fn a_direct_signed_advertisement_verifies_under_the_node_verifier() {
|
||||
let kp = Keypair::generate();
|
||||
let expected_did = kp.did().to_string();
|
||||
let client = build_http_client().unwrap();
|
||||
let slot = std::sync::Arc::new(std::sync::Mutex::new(None::<Verdict>));
|
||||
|
||||
let mut node = mockito::Server::new();
|
||||
let recorder = slot.clone();
|
||||
let did_for_target = expected_did.clone();
|
||||
let route = node
|
||||
.mock("GET", "/zOwner/myrepo/info/refs?service=git-upload-pack")
|
||||
.with_status(200)
|
||||
.with_body_from_request(move |req| {
|
||||
record_get_verdict(req, &did_for_target, &recorder);
|
||||
Vec::new()
|
||||
})
|
||||
.expect(1)
|
||||
.create();
|
||||
|
||||
let refs_url = format!(
|
||||
"{}/zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
node.url()
|
||||
);
|
||||
let resp = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
|
||||
let verdict = slot.lock().unwrap().take();
|
||||
assert!(
|
||||
matches!(verdict, Some(Verdict::Accepted)),
|
||||
"a direct signed advertisement must verify under the node's own chain and \
|
||||
resolve to {expected_did}, or the refusal test's empty slot proves \
|
||||
nothing; recorded verdict: {verdict:?}"
|
||||
);
|
||||
route.assert();
|
||||
}
|
||||
|
||||
/// The regression that round-1 missed: the Phase-2 `git-upload-pack` POST was
|
||||
/// left unsigned, so an owner's fetch of a private repo cleared the (now signed)
|
||||
/// advertisement and then 404'd on the pack POST. Drive BOTH request builders
|
||||
@@ -1619,13 +1137,49 @@ mod tests {
|
||||
/// to end (sign here, verify with the node's verifier), not reasoned.
|
||||
#[test]
|
||||
fn client_signature_verifies_under_node_verification_for_both_services() {
|
||||
use gitlawb_core::http_sig::{build_signing_string, compute_content_digest, HttpSignature};
|
||||
use gitlawb_core::identity::verify;
|
||||
use std::collections::HashMap;
|
||||
|
||||
let kp = Keypair::generate();
|
||||
let client = reqwest::blocking::Client::new();
|
||||
let body = b"0009done\n".to_vec();
|
||||
|
||||
// The verification chain is [`node_verifies`], the test-module helper the
|
||||
// redirect verdict tests share. Same primitives the node's require_signature
|
||||
// runs, over the request-target this crate transmits.
|
||||
// Re-implements the node's require_signature verification (auth/mod.rs):
|
||||
// parse headers, recompute content-digest from the body, rebuild the signing
|
||||
// string over @method/@path/content-digest, Ed25519-verify. Ok iff the node
|
||||
// would accept it.
|
||||
let node_verifies = |method: &str,
|
||||
path_and_query: &str,
|
||||
body: &[u8],
|
||||
sig_input: &str,
|
||||
sig_header: &str,
|
||||
content_digest: &str|
|
||||
-> anyhow::Result<()> {
|
||||
let sig = HttpSignature::parse(sig_input, sig_header)?;
|
||||
sig.check_created()?;
|
||||
assert!(
|
||||
sig.missing_components().is_empty(),
|
||||
"signature must cover all required components"
|
||||
);
|
||||
assert_eq!(sig.alg, "ed25519");
|
||||
assert_eq!(
|
||||
content_digest,
|
||||
compute_content_digest(body),
|
||||
"content-digest must match the body"
|
||||
);
|
||||
let vk = sig.key_id.to_verifying_key()?;
|
||||
let mut values = HashMap::new();
|
||||
values.insert("@method".to_string(), method.to_uppercase());
|
||||
values.insert("@path".to_string(), path_and_query.to_string());
|
||||
values.insert("content-digest".to_string(), content_digest.to_string());
|
||||
let sig_params_value = sig_input.strip_prefix("sig1=").unwrap_or(sig_input);
|
||||
let components: Vec<&str> = sig.components.iter().map(String::as_str).collect();
|
||||
let signing_string = build_signing_string(&components, sig_params_value, &values)?;
|
||||
let sig_array: [u8; 64] = sig.signature_bytes.as_slice().try_into()?;
|
||||
verify(&vk, signing_string.as_bytes(), &sig_array)?;
|
||||
Ok(())
|
||||
};
|
||||
// @path exactly as the node reconstructs it from the request it receives.
|
||||
let path_and_query = |req: &reqwest::blocking::Request| match req.url().query() {
|
||||
Some(q) => format!("{}?{}", req.url().path(), q),
|
||||
|
||||
@@ -162,28 +162,16 @@ fn start_shim(repo: PathBuf, mode: ShimMode) -> Shim {
|
||||
}
|
||||
}
|
||||
|
||||
/// `start_shim` makes the LISTENER non-blocking to poll its stop flag, and an
|
||||
/// accepted socket can inherit that flag.
|
||||
///
|
||||
/// Observed on Windows: Winsock hands back a socket carrying the listener's
|
||||
/// FIONBIO state and std's `accept` does not reset it. Expected on macOS and the
|
||||
/// BSDs for the same reason, since the accept4 man page describes inheritance as
|
||||
/// the canonical BSD behavior, though nothing in this repo's CI exercises that
|
||||
/// half. Linux is the exception, because std uses `accept4` there and it does
|
||||
/// not inherit file status flags (rust-lang/rust#67027).
|
||||
///
|
||||
/// Every read in `handle_conn` is a blocking read whose errors collapse to "peer
|
||||
/// closed", so an inherited WouldBlock would drop the connection with no
|
||||
/// response and abort the client mid-request. Normalize before reading; this
|
||||
/// also restores the read timeout, which a non-blocking socket silently makes
|
||||
/// meaningless.
|
||||
fn normalize_accepted_stream(stream: &TcpStream) {
|
||||
fn handle_conn(stream: TcpStream, repo: &Path, mode: ShimMode, posts: &AtomicUsize) {
|
||||
// `start_shim` makes the LISTENER non-blocking to poll its stop flag. On
|
||||
// Windows the accepted socket inherits that (Winsock FIONBIO inheritance;
|
||||
// std's `accept` does not reset it), on unix it does not. Every read below
|
||||
// is a blocking read whose errors collapse to "peer closed", so an inherited
|
||||
// WouldBlock would drop the connection with no response and abort the client
|
||||
// mid-request. Normalize before reading; this also restores the read timeout
|
||||
// on the next line, which a non-blocking socket silently makes meaningless.
|
||||
stream.set_nonblocking(false).ok();
|
||||
stream.set_read_timeout(Some(Duration::from_secs(30))).ok();
|
||||
}
|
||||
|
||||
fn handle_conn(stream: TcpStream, repo: &Path, mode: ShimMode, posts: &AtomicUsize) {
|
||||
normalize_accepted_stream(&stream);
|
||||
let mut reader = BufReader::new(stream);
|
||||
|
||||
// Request line.
|
||||
@@ -769,160 +757,26 @@ fn build_divergent_repos(shared_commits: usize) -> Repos {
|
||||
}
|
||||
}
|
||||
|
||||
/// `normalize_accepted_stream` must leave the socket in blocking mode.
|
||||
///
|
||||
/// This asserts the helper's postconditions directly: no client, no request, and
|
||||
/// no race over whether bytes arrive before the shim reads them. It removes the
|
||||
/// byte-arrival race entirely, which is what the end-to-end test cannot do. It is
|
||||
/// not literally deterministic, and the paragraph below says exactly what is left.
|
||||
///
|
||||
/// The read timeout has a getter, so it is checked exactly. Blocking mode does
|
||||
/// not: std exposes none, and Winsock has no FIONBIO getter at all (`ioctlsocket`
|
||||
/// documents FIONBIO with no output type, so it is set-only), so that half has to
|
||||
/// be observed through behavior: a blocking socket with no data pending parks its
|
||||
/// reader, a non-blocking one returns `WouldBlock` at once.
|
||||
///
|
||||
/// The reader owns the very socket the helper normalized. Do not reintroduce a
|
||||
/// `try_clone` here: on Windows that mints a new descriptor through
|
||||
/// `WSADuplicateSocketW` rather than duplicating a handle, and whether FIONBIO
|
||||
/// state follows the new descriptor is a question this test would then depend on
|
||||
/// and could not answer. Owning the original removes the question.
|
||||
///
|
||||
/// The `Started` handshake is load-bearing and must not be removed. It SHRINKS
|
||||
/// the vacuity window; it does not close it. Read that literally, because the
|
||||
/// looser version of this sentence is the mistake this whole test exists to
|
||||
/// correct. Without the handshake the window includes thread spawn itself, which
|
||||
/// is unbounded and can be very slow on a loaded runner. With it, spawn is out of
|
||||
/// the window entirely and what remains is the cross-thread round trip: the
|
||||
/// signal, the read call, its `WouldBlock` return, the channel send, and this
|
||||
/// thread waking from `recv_timeout`.
|
||||
///
|
||||
/// So the residual false-green path is a reader descheduled anywhere along that
|
||||
/// round trip for more than 250ms, notably between its own `Started` send and its
|
||||
/// `read`. That path is real and this comment does not claim otherwise. What the
|
||||
/// design does buy is that the guard cannot flake RED, and that no arrangement of
|
||||
/// bytes on the wire can fool it, only the scheduler. Measured 50 of 50 RED under
|
||||
/// a mutation deleting the normalization, at full-suite parallelism; that bounds
|
||||
/// the false-green rate, it does not make it zero.
|
||||
///
|
||||
/// Teardown order is a constraint, not a preference: the peer close must come
|
||||
/// AFTER the timeout assertion. Closing first unblocks the parked read, the
|
||||
/// outcome arrives, and the assertion fails even when the helper is correct.
|
||||
#[test]
|
||||
fn normalize_accepted_stream_leaves_the_socket_blocking() {
|
||||
enum Probe {
|
||||
Started,
|
||||
Outcome(std::io::Result<usize>),
|
||||
}
|
||||
|
||||
let listener = TcpListener::bind("127.0.0.1:0").unwrap();
|
||||
let addr = listener.local_addr().unwrap();
|
||||
let client = TcpStream::connect(addr).unwrap();
|
||||
let (accepted, _) = listener.accept().unwrap();
|
||||
|
||||
// The state Windows hands the shim. Forced here so the property is checked
|
||||
// on every platform rather than only where the OS supplies it.
|
||||
accepted.set_nonblocking(true).unwrap();
|
||||
normalize_accepted_stream(&accepted);
|
||||
|
||||
// The helper's other postcondition, and the one std lets us check exactly.
|
||||
// Without this, deleting the timeout leaves every test here green while a
|
||||
// stalled peer parks the shim's only accept-loop thread forever.
|
||||
assert_eq!(
|
||||
accepted.read_timeout().unwrap(),
|
||||
Some(Duration::from_secs(30)),
|
||||
"normalize_accepted_stream must restore the read timeout, not only blocking mode"
|
||||
);
|
||||
|
||||
let (tx, rx) = std::sync::mpsc::channel();
|
||||
// Move, never clone: see the try_clone note above.
|
||||
let mut reader = accepted;
|
||||
let probe = std::thread::spawn(move || {
|
||||
let mut buf = [0u8; 1];
|
||||
tx.send(Probe::Started).unwrap();
|
||||
let outcome = reader.read(&mut buf);
|
||||
let _ = tx.send(Probe::Outcome(outcome));
|
||||
});
|
||||
|
||||
// Bounded, not `recv()`. A bare recv here turns "the reader never ran" into a
|
||||
// hung test binary rather than a failing test, and cargo test has no per-test
|
||||
// timeout to rescue it. The bound is far above any real scheduling delay, so
|
||||
// hitting it is a genuine defect report, never a flake.
|
||||
match rx
|
||||
.recv_timeout(Duration::from_secs(30))
|
||||
.expect("reader thread never signalled Started (died, or never scheduled)")
|
||||
{
|
||||
Probe::Started => {}
|
||||
Probe::Outcome(_) => panic!("reader reported an outcome before its Started signal"),
|
||||
}
|
||||
|
||||
match rx.recv_timeout(Duration::from_millis(250)) {
|
||||
// The read is still parked, which is what blocking mode means.
|
||||
Err(std::sync::mpsc::RecvTimeoutError::Timeout) => {}
|
||||
Err(std::sync::mpsc::RecvTimeoutError::Disconnected) => {
|
||||
panic!("the reader thread exited instead of parking in its read")
|
||||
}
|
||||
Ok(Probe::Started) => panic!("received a second Started signal"),
|
||||
Ok(Probe::Outcome(outcome)) => {
|
||||
assert_eq!(
|
||||
outcome.as_ref().err().map(std::io::Error::kind),
|
||||
Some(std::io::ErrorKind::WouldBlock),
|
||||
"the read returned instead of parking, but not with WouldBlock \
|
||||
({outcome:?}); that is a different failure than the one this test \
|
||||
guards, so do not read it as a non-blocking socket"
|
||||
);
|
||||
panic!(
|
||||
"accepted socket is still non-blocking after \
|
||||
normalize_accepted_stream: the read returned WouldBlock \
|
||||
immediately instead of parking"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Only now: EOF unblocks the parked read so the thread can be joined. Bounded
|
||||
// for the same reason as the handshake wait above; the socket's own 30s read
|
||||
// timeout is the other backstop, and it is asserted rather than assumed.
|
||||
drop(client);
|
||||
match rx
|
||||
.recv_timeout(Duration::from_secs(60))
|
||||
.expect("reader did not return after the peer closed")
|
||||
{
|
||||
Probe::Outcome(outcome) => assert_eq!(
|
||||
outcome.ok(),
|
||||
Some(0),
|
||||
"expected EOF once the peer closed, not payload"
|
||||
),
|
||||
Probe::Started => panic!("received a second Started signal"),
|
||||
}
|
||||
probe.join().unwrap();
|
||||
}
|
||||
|
||||
/// The shim must answer a connection that arrives in non-blocking mode.
|
||||
///
|
||||
/// End-to-end realism check through the real `handle_conn` request path. The
|
||||
/// deterministic guarantee lives in
|
||||
/// `normalize_accepted_stream_leaves_the_socket_blocking`, which asserts the
|
||||
/// helper's postcondition with no client at all; see `normalize_accepted_stream`
|
||||
/// for why an accepted socket can arrive non-blocking in the first place. The
|
||||
/// shim reads with `read_line(..).unwrap_or(0)`, which collapses `WouldBlock`
|
||||
/// into "peer closed" and returns WITHOUT writing a response, aborting the
|
||||
/// client mid-request.
|
||||
/// `start_shim` sets the LISTENER non-blocking so the accept loop can poll the
|
||||
/// stop flag. On unix the socket handed back by `accept()` is blocking, so that
|
||||
/// is invisible; on Windows, Winsock has the accepted socket inherit the
|
||||
/// listener's FIONBIO state and std does not reset it (`accept` is a bare
|
||||
/// `c::accept`), so every accepted connection is non-blocking there. The shim
|
||||
/// reads with `read_line(..).unwrap_or(0)`, which collapses `WouldBlock` into
|
||||
/// "peer closed" and returns WITHOUT writing a response, aborting the client
|
||||
/// mid-request. Because the shim accepts as soon as the handshake completes,
|
||||
/// strictly before the request bytes arrive, that window is open on every
|
||||
/// connection and closes only because the accept poll usually lags the client.
|
||||
///
|
||||
/// This test is BEST EFFORT and known to be nondeterministic. Its handshake
|
||||
/// fires after `accept()` but before `handle_conn` runs, so it narrows the
|
||||
/// accept-before-request window without closing it: the request bytes can
|
||||
/// already be buffered by the time the shim reads, and the read then succeeds
|
||||
/// even with the normalization removed. Against a deleted
|
||||
/// `set_nonblocking(false)` it caught the defect in 39, 43, and 47 of 50 across
|
||||
/// three full-suite samples. The spread is the point: it is a sampled tendency,
|
||||
/// not a property, so do not quote a percentage off it. Running it alone on an
|
||||
/// idle machine flattered it to 48 of 50; the full-suite numbers are the honest
|
||||
/// ones, because that is how it ships.
|
||||
///
|
||||
/// It is still the only coverage for the helper's CALL SITE. The deterministic
|
||||
/// probe calls `normalize_accepted_stream` directly, so deleting the call from
|
||||
/// `handle_conn` leaves that probe green (0 of 50 in both samples) and only this
|
||||
/// test notices, at 45 and 46 of 50.
|
||||
/// Force the Windows shape explicitly so this is checked on every platform
|
||||
/// rather than only the one that exhibits it. The accept-before-request
|
||||
/// interleaving is the losing one, so it is established by a handshake rather
|
||||
/// than a sleep: a timing-based version cannot flake RED, but it CAN flake
|
||||
/// GREEN on a loaded runner (bytes already buffered, so the read succeeds even
|
||||
/// while non-blocking), which would make this guard vacuous exactly where it
|
||||
/// is supposed to bite.
|
||||
#[test]
|
||||
fn shim_answers_a_connection_that_arrives_non_blocking() {
|
||||
let repos = build_divergent_repos(1);
|
||||
@@ -944,9 +798,8 @@ fn shim_answers_a_connection_that_arrives_non_blocking() {
|
||||
Err(e) => panic!("accept failed: {e}"),
|
||||
}
|
||||
};
|
||||
// What Windows hands the shim, and what macOS is expected to. On Linux
|
||||
// this is the only way to reach that state, so forcing it is what makes
|
||||
// the assertions below run on every platform.
|
||||
// What Windows hands the shim. On unix this is the only way to reach
|
||||
// that state, so the assertion below is load-bearing here too.
|
||||
stream.set_nonblocking(true).unwrap();
|
||||
accepted_tx.send(()).unwrap();
|
||||
handle_conn(stream, &repo, ShimMode::Normal, &posts);
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
//! by exact match.
|
||||
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD as B64U, Engine};
|
||||
use ed25519_dalek::{Signature, Signer, SigningKey, VerifyingKey};
|
||||
use ed25519_dalek::{Signature, Signer, SigningKey, Verifier, VerifyingKey};
|
||||
use serde::{de::DeserializeOwned, Deserialize, Serialize};
|
||||
|
||||
use crate::error::{Error, Result};
|
||||
@@ -111,7 +111,7 @@ impl Attestation {
|
||||
.try_into()
|
||||
.map_err(|_| Error::Signature("signature must be 64 bytes".to_string()))?;
|
||||
let sig = Signature::from_bytes(&sig_bytes);
|
||||
vk.verify_strict(&bytes, &sig)
|
||||
vk.verify(&bytes, &sig)
|
||||
.map_err(|e| Error::Signature(format!("ed25519: {e}")))?;
|
||||
|
||||
Ok(vk)
|
||||
@@ -554,39 +554,4 @@ mod tests {
|
||||
let err = tampered.verify_signature(cert_hash).unwrap_err();
|
||||
assert!(matches!(err, Error::Signature(_)));
|
||||
}
|
||||
|
||||
/// Regression guard for strict verification: a signature forged under a
|
||||
/// weak (small-order) public key satisfies the verification equation
|
||||
/// but must be rejected. The identity point is such a key: with R the
|
||||
/// identity and S = 0, [S]B - [k]A is the identity for any message.
|
||||
#[test]
|
||||
fn verify_rejects_weak_key_signature() {
|
||||
let mut weak_key_bytes = [0u8; 32];
|
||||
weak_key_bytes[0] = 1; // compressed identity point (y = 1, x = 0)
|
||||
let weak_vk = VerifyingKey::from_bytes(&weak_key_bytes).unwrap();
|
||||
assert!(weak_vk.is_weak(), "identity point must be a weak key");
|
||||
|
||||
let cert_hash = sample_cert_hash();
|
||||
let mut forged = [0u8; 64];
|
||||
forged[0] = 1; // R = identity point, S = 0
|
||||
let forged_sig = B64U.encode(forged);
|
||||
|
||||
// Build an attestation with the weak key as signer and the forged
|
||||
// signature. The weak-key check happens at verify time.
|
||||
let mut att = dummy_attestation(&SigningKey::generate(&mut OsRng), cert_hash);
|
||||
let mut buf = Vec::with_capacity(ED25519_MULTICODEC.len() + 32);
|
||||
buf.extend_from_slice(&ED25519_MULTICODEC);
|
||||
buf.extend_from_slice(&weak_key_bytes);
|
||||
att.signer = format!(
|
||||
"did:key:{}",
|
||||
multibase::encode(multibase::Base::Base58Btc, &buf)
|
||||
);
|
||||
att.sig = forged_sig;
|
||||
|
||||
let err = att.verify_signature(cert_hash).unwrap_err();
|
||||
assert!(
|
||||
matches!(err, Error::Signature(_)),
|
||||
"signature under a weak (small-order) public key must be rejected"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -22,7 +22,6 @@ multihash-codetable = { workspace = true }
|
||||
cid = { workspace = true }
|
||||
chrono = { workspace = true }
|
||||
uuid = { workspace = true }
|
||||
url = { workspace = true, optional = true }
|
||||
zeroize = { version = "1", features = ["derive"] }
|
||||
pkcs8 = { version = "0.10", features = ["pem", "std"] }
|
||||
curve25519-dalek = "4"
|
||||
@@ -31,9 +30,3 @@ chacha20poly1305 = "0.10"
|
||||
|
||||
[dev-dependencies]
|
||||
tokio = { workspace = true }
|
||||
# Not optional here: the redirect matrix must run under a bare
|
||||
# `cargo test -p gitlawb-core`, with no feature selected.
|
||||
url = { workspace = true }
|
||||
|
||||
[features]
|
||||
redirect = ["dep:url"]
|
||||
@@ -6,8 +6,6 @@
|
||||
//! The schema is frozen at v1. All fields are mandatory for forward compatibility.
|
||||
//! Nodes that receive a certificate with an unknown version MUST reject it.
|
||||
|
||||
use std::collections::HashSet;
|
||||
|
||||
use chrono::{DateTime, Utc};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use uuid::Uuid;
|
||||
@@ -137,14 +135,10 @@ impl RefUpdateCert {
|
||||
|
||||
/// Check if this certificate satisfies a threshold of valid signatures
|
||||
/// from the provided set of authorized maintainer DIDs.
|
||||
///
|
||||
/// Counts distinct signer DIDs, not signature entries: a repeated
|
||||
/// signature from the same maintainer counts once.
|
||||
pub fn satisfies_threshold(&self, maintainers: &[Did], threshold: usize) -> Result<bool> {
|
||||
let valid = self.verify_all()?;
|
||||
let distinct_signers: HashSet<&Did> =
|
||||
valid.iter().filter(|d| maintainers.contains(d)).collect();
|
||||
Ok(distinct_signers.len() >= threshold)
|
||||
let count = valid.iter().filter(|d| maintainers.contains(d)).count();
|
||||
Ok(count >= threshold)
|
||||
}
|
||||
|
||||
/// Validate the certificate structure (not signatures).
|
||||
@@ -350,33 +344,6 @@ mod tests {
|
||||
assert!(!cert.satisfies_threshold(&maintainers, 1).unwrap());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn satisfies_threshold_rejects_duplicated_signature() {
|
||||
let kp1 = Keypair::generate();
|
||||
let kp2 = Keypair::generate();
|
||||
let kp3 = Keypair::generate();
|
||||
let repo_did = kp1.did();
|
||||
|
||||
let mut cert = RefUpdateCert::new(
|
||||
repo_did,
|
||||
"refs/heads/main".to_string(),
|
||||
dummy_hash('0'),
|
||||
dummy_hash('a'),
|
||||
1,
|
||||
&kp1,
|
||||
)
|
||||
.unwrap();
|
||||
// Copy-paste the only real signature onto the certificate a second
|
||||
// time. Same signer, same valid signature, still one real signer.
|
||||
let dup = cert.signatures[0].clone();
|
||||
cert.signatures.push(dup);
|
||||
|
||||
let maintainers = vec![kp1.did(), kp2.did(), kp3.did()];
|
||||
// Two signature entries but a single distinct signer must not
|
||||
// satisfy a 2-of-3 threshold.
|
||||
assert!(!cert.satisfies_threshold(&maintainers, 2).unwrap());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn threshold_zero_is_always_satisfied() {
|
||||
let kp = Keypair::generate();
|
||||
|
||||
@@ -64,19 +64,6 @@ impl Cid {
|
||||
}
|
||||
}
|
||||
|
||||
/// True when `s` parses as a CIDv1 with the raw codec — the exact shape
|
||||
/// [`Cid::from_git_object_bytes`] produces and the `/ipfs` resolver looks up.
|
||||
/// A legacy provider CID (Kubo dag-pb, Pinata CIDv0) parses to a different
|
||||
/// version or codec and returns `false`, marking it an opportunistic-repair
|
||||
/// candidate. Decidable from the string alone (no object bytes), so the pin path
|
||||
/// can gate the byte-read/recompute cost on it and leave non-legacy rows at the
|
||||
/// existing DB-only skip cost. An unparseable string is non-canonical (`false`).
|
||||
pub fn is_raw_cidv1(s: &str) -> bool {
|
||||
s.parse::<CidGeneric<64>>()
|
||||
.map(|c| c.version() == cid::Version::V1 && c.codec() == RAW)
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
impl fmt::Display for Cid {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
write!(f, "{}", self.0)
|
||||
@@ -190,38 +177,6 @@ mod tests {
|
||||
assert!(result.is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn is_raw_cidv1_classifies_codec_from_string() {
|
||||
// The canonical resolver key: CIDv1 + raw codec → not a repair candidate.
|
||||
let raw = Cid::from_git_object_bytes(b"blob 5\0hello");
|
||||
assert!(
|
||||
is_raw_cidv1(raw.as_str()),
|
||||
"from_git_object_bytes output is CIDv1/raw"
|
||||
);
|
||||
|
||||
// A CIDv0 (Pinata dag-pb legacy shape) → repair candidate.
|
||||
assert!(
|
||||
!is_raw_cidv1("QmYwAPJzv5CZsnA625s3Xf2nemtYgPpHdWEz79ojWnPbdG"),
|
||||
"a CIDv0 dag-pb value is a legacy-repair candidate"
|
||||
);
|
||||
|
||||
// A CIDv1 with the dag-pb codec (the Kubo above-block-size root) over the
|
||||
// same multihash → still a repair candidate (codec, not just version).
|
||||
let parsed = raw.as_str().parse::<CidGeneric<64>>().unwrap();
|
||||
const DAG_PB: u64 = 0x70;
|
||||
let dagpb = CidGeneric::<64>::new_v1(DAG_PB, *parsed.hash()).to_string();
|
||||
assert!(
|
||||
!is_raw_cidv1(&dagpb),
|
||||
"a CIDv1 dag-pb value is a legacy-repair candidate"
|
||||
);
|
||||
|
||||
// Garbage is non-canonical.
|
||||
assert!(
|
||||
!is_raw_cidv1("not-a-cid"),
|
||||
"an unparseable string is non-canonical"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sha256_hex_of_empty_input_is_well_known() {
|
||||
// SHA-256("") is a fixed constant; verifies the hasher is wired correctly.
|
||||
|
||||
@@ -80,19 +80,6 @@ impl Did {
|
||||
)));
|
||||
}
|
||||
|
||||
// Refuse an oversized id before decoding. base58 decoding is quadratic
|
||||
// in its input, and both callers of this function take the string from
|
||||
// an untrusted request: the unauthenticated peer-announce gate, and the
|
||||
// HTTP-signature keyid. An ed25519 did:key method-id is a fixed 48
|
||||
// characters, so this bound is slack rather than a behavior change, and
|
||||
// it has to sit ahead of the decode to be worth anything.
|
||||
const MAX_METHOD_ID_LEN: usize = 64;
|
||||
if self.method_id().len() > MAX_METHOD_ID_LEN {
|
||||
return Err(Error::InvalidDid(
|
||||
"did:key method-specific id too long".to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
let (_, bytes) =
|
||||
multibase::decode(self.method_id()).map_err(|e| Error::InvalidDid(e.to_string()))?;
|
||||
|
||||
@@ -321,52 +308,4 @@ mod tests {
|
||||
assert_eq!(Did::web("example.com").method_id(), "example.com");
|
||||
assert_eq!(Did::gitlawb("z6MkSomeKey").method_id(), "z6MkSomeKey");
|
||||
}
|
||||
|
||||
/// An oversized method-specific id is refused on its length, before the
|
||||
/// base58 decode runs.
|
||||
///
|
||||
/// base58 decoding is quadratic in the input, and `to_verifying_key` is
|
||||
/// reached from two places that take an attacker-supplied string: the
|
||||
/// unauthenticated peer-announce gate, and the HTTP-signature keyid. A
|
||||
/// 64k-character DID measured 8s through the router without this guard
|
||||
/// against 4.6ms with it, on a tokio worker with no spawn_blocking, so a
|
||||
/// single caller could buy CPU-seconds by the thousand.
|
||||
///
|
||||
/// Asserting the MESSAGE is what makes this load-bearing: an oversized id
|
||||
/// errors either way, so a test that only checked `is_err()` would pass
|
||||
/// with the guard removed, having merely paid the cost it exists to avoid.
|
||||
#[test]
|
||||
fn to_verifying_key_rejects_an_oversized_method_id_before_decoding() {
|
||||
let oversized = format!("did:key:z{}", "z".repeat(64_000));
|
||||
let did: Did = oversized.parse().expect("method is still `key`");
|
||||
|
||||
let start = std::time::Instant::now();
|
||||
let err = did.to_verifying_key().expect_err("must be refused");
|
||||
let elapsed = start.elapsed();
|
||||
|
||||
assert!(
|
||||
err.to_string().contains("too long"),
|
||||
"must be refused on length, not after the decode: {err}"
|
||||
);
|
||||
assert!(
|
||||
elapsed < std::time::Duration::from_secs(1),
|
||||
"refusal must not pay the quadratic decode: took {elapsed:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The bound must not reject a real key. Every `did:key` this project
|
||||
/// mints is a fixed 48 characters, so the limit is slack, not a behavior
|
||||
/// change.
|
||||
#[test]
|
||||
fn to_verifying_key_still_accepts_a_real_did_key() {
|
||||
use ed25519_dalek::SigningKey;
|
||||
let signing = SigningKey::from_bytes(&[7u8; 32]);
|
||||
let did = Did::from_verifying_key(&signing.verifying_key());
|
||||
assert_eq!(
|
||||
did.method_id().len(),
|
||||
48,
|
||||
"did:key method-id is fixed-width"
|
||||
);
|
||||
did.to_verifying_key().expect("a real did:key must resolve");
|
||||
}
|
||||
}
|
||||
@@ -78,9 +78,10 @@ impl Keypair {
|
||||
|
||||
/// Verify an Ed25519 signature.
|
||||
pub fn verify(verifying_key: &VerifyingKey, msg: &[u8], sig_bytes: &[u8; 64]) -> Result<()> {
|
||||
use ed25519_dalek::Verifier;
|
||||
let sig = Signature::from_bytes(sig_bytes);
|
||||
verifying_key
|
||||
.verify_strict(msg, &sig)
|
||||
.verify(msg, &sig)
|
||||
.map_err(|_| Error::SignatureInvalid)
|
||||
}
|
||||
|
||||
@@ -208,28 +209,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn verify_rejects_weak_key_signature() {
|
||||
// Regression guard for strict verification: a signature forged under a
|
||||
// weak (small-order) public key satisfies the verification equation
|
||||
// but must be rejected. The identity point is such a key: with R the
|
||||
// identity and S = 0, [S]B - [k]A is the identity for any message.
|
||||
let mut weak_key_bytes = [0u8; 32];
|
||||
weak_key_bytes[0] = 1; // compressed identity point (y = 1, x = 0)
|
||||
let weak_vk = VerifyingKey::from_bytes(&weak_key_bytes).unwrap();
|
||||
assert!(weak_vk.is_weak(), "identity point must be a weak key");
|
||||
|
||||
let msg = b"forged message";
|
||||
let mut forged = [0u8; 64];
|
||||
forged[0] = 1; // R = identity point, S = 0
|
||||
|
||||
let result = verify(&weak_vk, msg, &forged);
|
||||
assert!(
|
||||
result.is_err(),
|
||||
"signature under a weak (small-order) public key must be rejected"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn signed_payload_round_trip() {
|
||||
let kp = Keypair::generate();
|
||||
|
||||
@@ -5,16 +5,7 @@ pub mod encrypt;
|
||||
pub mod error;
|
||||
pub mod http_sig;
|
||||
pub mod identity;
|
||||
// `url` is the one dependency here that drags a tail (idna, then the icu
|
||||
// crates), and gitlawb-core is allowlisted to stay embeddable. Every client that
|
||||
// needs this predicate already parses URLs, so they opt in and nothing else
|
||||
// pays. `test` is in the cfg so `cargo test -p gitlawb-core` still compiles and
|
||||
// runs the matrix below with no feature selected; without it the tests would
|
||||
// silently not run, which is the failure this module exists to prevent.
|
||||
#[cfg(any(feature = "redirect", test))]
|
||||
pub mod redirect;
|
||||
pub mod sanitize;
|
||||
pub mod scan_token;
|
||||
pub mod ucan;
|
||||
|
||||
pub use error::Error;
|
||||
|
||||
@@ -1,241 +0,0 @@
|
||||
//! Redirect policy shared by every gitlawb HTTP client that signs its requests.
|
||||
//!
|
||||
//! Both `gl` (async) and `git-remote-gitlawb` (blocking) attach RFC 9421
|
||||
//! `Signature` and `Signature-Input` headers, and reqwest strips only
|
||||
//! `Authorization`, `Cookie`, `Proxy-Authorization` and `WWW-Authenticate` when a
|
||||
//! redirect crosses hosts. A signature would survive that hop, and it binds
|
||||
//! `@method`, `@path` and `content-digest` with no authority component, so a node
|
||||
//! answering 302 could hand a working credential to a host of its choosing and read
|
||||
//! as the caller anywhere until the clock-skew window closes. On a 307/308 the
|
||||
//! request body goes along with it, which for the remote helper is the pack.
|
||||
//!
|
||||
//! That same missing authority component is why the predicate also pins the
|
||||
//! request-target: `@path` is signed as the client sent it and verified as the node
|
||||
//! received it, so a same-origin hop that rewrites the path or the query (a
|
||||
//! trailing-slash or query normalization) makes the signature cover a target the
|
||||
//! node never saw and the read 401s. Only a hop that re-issues the identical target,
|
||||
//! an http-to-https upgrade being the one that matters in practice, is followed.
|
||||
//!
|
||||
//! The decision lives here rather than in either client because the two used to
|
||||
//! disagree: `gl` was scoped to the origin while the remote helper, the binary that
|
||||
//! actually runs `git clone gitlawb://`, still ran reqwest's default and followed
|
||||
//! anywhere. One predicate is what keeps a future third client from repeating that.
|
||||
//!
|
||||
//! The type is `url::Url`, which is what `reqwest::Url` re-exports, so both clients
|
||||
//! pass their attempt URLs straight in.
|
||||
|
||||
/// Longest redirect chain followed. `reqwest::redirect::Policy::custom` replaces
|
||||
/// reqwest's built-in limit, so the bound has to be restated by every client that
|
||||
/// installs a custom policy; the value is reqwest's own default.
|
||||
///
|
||||
/// This counts FOLLOWS, matching `Policy::limited`: reqwest pushes the redirecting
|
||||
/// URL onto `previous` before consulting the policy, and `Limit(max)` refuses once
|
||||
/// `previous.len() > max`, so a caller comparing against this constant must use `>`
|
||||
/// too or it permits one hop fewer than it says.
|
||||
pub const MAX_REDIRECTS: usize = 10;
|
||||
|
||||
/// Follow a redirect only when it stays on the origin that issued it AND re-issues
|
||||
/// the identical request-target.
|
||||
///
|
||||
/// `Policy::none()` would have been the simpler answer, but one same-origin redirect
|
||||
/// shape is legitimate here: a node fronted by a proxy that upgrades http to https,
|
||||
/// or otherwise re-issues the same path and query, so the policy is scoped rather
|
||||
/// than switched off.
|
||||
///
|
||||
/// Path and query must match exactly, and that is the request-target clause rather
|
||||
/// than an origin one. `@path` is signed as the client sent it and verified as the
|
||||
/// node received it, so a hop that rewrites either half leaves a signature covering
|
||||
/// a target nobody asked for and the node answers 401. Refusing the hop turns a
|
||||
/// confusing 401 into the 3xx that names what actually happened. One policy covers
|
||||
/// signed and unsigned callers alike, for the same reason the predicate is shared:
|
||||
/// two rules would drift.
|
||||
///
|
||||
/// The clause pins `@path`, and only `@path`. A gitlawb signature also covers
|
||||
/// `@method` and `content-digest`, and both of those are still open on a followed
|
||||
/// hop: on a 301, 302 or 303, reqwest 0.12.28 delegates to tower-http's
|
||||
/// `FollowRedirect`, which rewrites a POST to a GET and empties the body
|
||||
/// (tower-http-0.6.8 `src/follow_redirect/mod.rs:273-285`), while its
|
||||
/// `drop_payload_headers` removes only `Content-Type`, `Content-Length`,
|
||||
/// `Content-Encoding` and `Transfer-Encoding`. So `Signature`, `Signature-Input` and
|
||||
/// `Content-Digest` ride along on a request that no longer has the method or the body
|
||||
/// they were computed over. Only 307 and 308 preserve both. This predicate returning
|
||||
/// true therefore makes a GET-shaped hop safe to replay against the node's verifier
|
||||
/// and says nothing about a bodied one: a signed write must not rely on it alone.
|
||||
///
|
||||
/// `Url::query` is `None` for `/a` and `Some("")` for `/a?`, and those are two
|
||||
/// different request-targets on the node side too, so the comparison is strict and
|
||||
/// needs no special case.
|
||||
///
|
||||
/// Host and port must match exactly. Port is compared as `Url::port`, which is
|
||||
/// `None` for a scheme's default port, so http -> https on the same host compares
|
||||
/// equal while http -> http on a different port does not. A downgrade from https to
|
||||
/// http is refused as well: the target is the same host, but the signature would go
|
||||
/// out in cleartext, which is the same credential leak by a slower route.
|
||||
///
|
||||
/// Host comparison rides on `url`'s parse-time normalization (lowercasing and IDN
|
||||
/// -> punycode), so the spellings an attacker reaches for do not open a gap. That
|
||||
/// is a property of the parsed `Url`, not of this function, which is why the test
|
||||
/// matrix pins it: a move to raw string comparison would silently lose it.
|
||||
pub fn may_follow(previous: &url::Url, next: &url::Url) -> bool {
|
||||
let same_origin = next.host_str() == previous.host_str() && next.port() == previous.port();
|
||||
let same_target = next.path() == previous.path() && next.query() == previous.query();
|
||||
let downgraded = previous.scheme() == "https" && next.scheme() != "https";
|
||||
same_origin && same_target && !downgraded
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// Every branch of the decision, both ways, plus the spellings that would slip
|
||||
/// past a comparison less careful than `Url`'s own normalization.
|
||||
#[test]
|
||||
fn may_follow_covers_each_origin_branch() {
|
||||
let url = |s: &str| url::Url::parse(s).unwrap();
|
||||
let cases: &[(&str, &str, bool, &str)] = &[
|
||||
(
|
||||
"http://node.example/a",
|
||||
"http://node.example/b",
|
||||
false,
|
||||
"same origin but the path changed: @path is signed as sent and verified as received",
|
||||
),
|
||||
(
|
||||
"http://node.example/a",
|
||||
"https://node.example/a",
|
||||
true,
|
||||
"http to https on one host with an identical request-target: both ports are \
|
||||
the scheme default, so the proxy upgrade is still followed",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://node.example/a/",
|
||||
false,
|
||||
"trailing-slash normalization changes the request-target, so it is refused",
|
||||
),
|
||||
(
|
||||
"https://node.example:8443/a",
|
||||
"https://node.example:8443/a",
|
||||
true,
|
||||
"same explicit port",
|
||||
),
|
||||
(
|
||||
"http://node.example/a",
|
||||
"http://attacker.example/a",
|
||||
false,
|
||||
"different host",
|
||||
),
|
||||
(
|
||||
"http://node.example/a",
|
||||
"http://node.example:8080/a",
|
||||
false,
|
||||
"same host, different port",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"http://node.example/a",
|
||||
false,
|
||||
"https downgraded to cleartext on the same host",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"http://node.example:443/a",
|
||||
false,
|
||||
"a downgrade dressed up as the https port",
|
||||
),
|
||||
// The rows below pass today because `Url::parse` normalizes the host, not
|
||||
// because anything here compares case-insensitively or decodes IDN. They
|
||||
// are the variants an attacker reaches for, so they are pinned: swapping
|
||||
// this predicate for a raw string comparison must break the suite.
|
||||
// Each of these pairs an IDENTICAL path on both sides, deliberately. The
|
||||
// request-target clause below would make every one of them false on the
|
||||
// path alone, and a row that is false for two reasons has stopped pinning
|
||||
// either. With the paths equal, the host or port comparison is the only
|
||||
// thing left that can decide them.
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://NODE.EXAMPLE/a",
|
||||
true,
|
||||
"same host in a different case: parse lowercases it",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://node.example./a",
|
||||
false,
|
||||
"a trailing dot is a different host to url, so the redirect is refused",
|
||||
),
|
||||
(
|
||||
"https://exämple.test/a",
|
||||
"https://xn--exmple-cua.test/a",
|
||||
true,
|
||||
"unicode host and its punycode spelling are one host after parse",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://user:[email protected]/a",
|
||||
true,
|
||||
"userinfo is not part of the origin: same host, still followed",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://[email protected]/a",
|
||||
false,
|
||||
"the node's name smuggled into userinfo: the host is the attacker's",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://attacker.example/a#node.example",
|
||||
false,
|
||||
"the node's name pushed into the fragment: the host is the attacker's",
|
||||
),
|
||||
// The request-target clause, both directions. `@path` is the only thing a
|
||||
// gitlawb signature binds the request to, so a hop that rewrites it hands
|
||||
// the node a signature over a target it never received.
|
||||
(
|
||||
"https://node.example/a?x=1",
|
||||
"https://node.example/a?x=1",
|
||||
true,
|
||||
"identical request-target: the same-origin hop that is still followed",
|
||||
),
|
||||
(
|
||||
"https://node.example/a?x=1",
|
||||
"https://node.example/a?x=2",
|
||||
false,
|
||||
"same path but a different query: the request-target covers the query too",
|
||||
),
|
||||
(
|
||||
"https://node.example/a",
|
||||
"https://node.example/a?x=1",
|
||||
false,
|
||||
"a query added where there was none",
|
||||
),
|
||||
(
|
||||
"http://node.example/a",
|
||||
"http://node.example/a?",
|
||||
false,
|
||||
"an empty query added where there was none: a missing query and an empty \
|
||||
one are different request-targets",
|
||||
),
|
||||
(
|
||||
"https://node.example/a?x=1",
|
||||
"https://node.example/a",
|
||||
false,
|
||||
"the query dropped where there was one: the comparison is symmetric, and \
|
||||
nothing else in the matrix pins that direction",
|
||||
),
|
||||
(
|
||||
"https://node.example/a#x",
|
||||
"https://node.example/a#y",
|
||||
true,
|
||||
"a fragment-only difference is still followed: a fragment never reaches \
|
||||
the wire, so it is no part of the request-target the node verifies",
|
||||
),
|
||||
];
|
||||
for (previous, next, expected, why) in cases {
|
||||
assert_eq!(
|
||||
may_follow(&url(previous), &url(next)),
|
||||
*expected,
|
||||
"{previous} -> {next} ({why})"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,499 +0,0 @@
|
||||
//! Sealed continuation token for the node's bounded legacy CID scan (INV-13).
|
||||
//!
|
||||
//! The `/ipfs/{cid}` resolver's legacy scan stops at a row ceiling and sheds a
|
||||
//! retryable 503. To let a holder buried past that ceiling still be reached, the
|
||||
//! shed carries the scan position so the caller can echo it back and resume. The
|
||||
//! whole point of the design is that the node keeps NO server-side scan state: the
|
||||
//! position rides in the caller's token.
|
||||
//!
|
||||
//! That makes the token an EMITTED continuation derived from a FETCHED row, and on
|
||||
//! a scan that served nothing every fetched row is by construction a private or
|
||||
//! quarantined repo the caller may not read. The row's `created_at` leaks its
|
||||
//! creation time and its `id` carries the owner's DID, so both halves are withheld
|
||||
//! fields and the token must be CONFIDENTIAL, not merely tamper-evident:
|
||||
//!
|
||||
//! * AEAD-sealed (XChaCha20-Poly1305), never base64-of-plaintext and never
|
||||
//! signed plaintext. Integrity is not confidentiality.
|
||||
//! * A fresh `OsRng` nonce on EVERY seal. Under a stream cipher a repeated nonce
|
||||
//! means repeated keystream, and an attacker who can force the node to seal a
|
||||
//! position whose plaintext they know XORs two tokens and recovers a withheld
|
||||
//! row's fields in full, strictly worse than emitting plaintext.
|
||||
//! * FIXED-WIDTH plaintext. AEAD ciphertext is plaintext-length plus the tag, and
|
||||
//! every field of a scan position varies in length, so a variable encoding would
|
||||
//! make token LENGTH a side channel for the sealed row (a short name under a
|
||||
//! short owner vs a long one) and for the candidate oid's width (40 hex on a
|
||||
//! sha1 repo, 64 on a sha256 one). Every token this module mints is byte-identical
|
||||
//! in length. Each field is padded to its own separate width, which is a per-field
|
||||
//! constant and so still leaks nothing about a given row or candidate.
|
||||
//! * The canonical CID as associated data, so a token minted while scanning for
|
||||
//! one CID does not authenticate when replayed against another.
|
||||
//!
|
||||
//! Every failure to open (wrong key, tampered bytes, wrong CID, expired, malformed)
|
||||
//! returns the same `None`. The caller treats that as "no token" and starts at the
|
||||
//! front, so no failure class is distinguishable and the token is no oracle.
|
||||
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD as B64URL, Engine};
|
||||
use chacha20poly1305::{
|
||||
aead::{Aead, KeyInit, OsRng, Payload},
|
||||
XChaCha20Poly1305, XNonce,
|
||||
};
|
||||
use rand::RngCore;
|
||||
|
||||
/// Keyset position of the last row a truncated scan fetched.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct ScanPosition {
|
||||
/// The row's raw stored `created_at` text, the first half of the keyset cursor.
|
||||
pub created_at_key: String,
|
||||
/// The row's `id`, the tiebreaking half of the keyset cursor.
|
||||
pub id: String,
|
||||
/// The oid hex of the CANDIDATE this position resumes. One CID can map to several
|
||||
/// git oids, so a bare row cursor names a row without naming whose walk it belongs
|
||||
/// to. The candidate is named by IDENTITY rather than by position in the candidate
|
||||
/// list: that list is ordered by hex and mutates between rungs, so an index would
|
||||
/// name a different candidate the moment anything is pinned or unpinned.
|
||||
pub sha256_hex: String,
|
||||
}
|
||||
|
||||
/// Plaintext version byte, so a future layout change is a clean open-failure
|
||||
/// (treated as absent) rather than a misparse.
|
||||
///
|
||||
/// Bumped to 2 when the two halves stopped sharing one width (see [`ID_WIDTH`]), and
|
||||
/// to 3 when the position gained the candidate oid it resumes (see [`OID_WIDTH`]).
|
||||
/// A token minted under an earlier layout is a different length and a different
|
||||
/// framing, so it opens to `None` and the caller restarts at the front, which is the
|
||||
/// safe direction: a misparse would resume at a fabricated row and skip coverage.
|
||||
const VERSION: u8 = 3;
|
||||
|
||||
/// Byte width the `created_at` half is padded to. Every value stored here is a
|
||||
/// serialized timestamp, about 30 bytes, so 64 is roomy for the field's whole domain.
|
||||
/// It is deliberately NOT widened to match [`ID_WIDTH`]: padding both halves to the id
|
||||
/// width would nearly double every token for a field that can never use the space.
|
||||
const CREATED_WIDTH: usize = 64;
|
||||
|
||||
/// Byte width the `id` half is padded to.
|
||||
///
|
||||
/// The bound is set by the WRITERS, not by what a typical id happens to look like.
|
||||
/// `upsert_mirror_repo` builds `repos.id` as `{owner}/{name}`, and the slug validators
|
||||
/// in the node's `repo_store` admit an owner of up to 255 bytes and a name of up to
|
||||
/// 100, so 356 bytes is reachable through the ordinary write path and repo names are
|
||||
/// peer-controllable. 384 clears that with margin.
|
||||
///
|
||||
/// Under-sizing this is not a cosmetic bug. A row at a truncation boundary whose id
|
||||
/// exceeds the width fails the seal, the handler sheds a 503 with no continuation, and
|
||||
/// a tokenless shed is byte-identical to the wrapped-scan response whose contract is
|
||||
/// "the absence of a token means the ladder is over". The boundary row is deterministic
|
||||
/// for a stable inventory, so every retry reproduces it and every row past it becomes
|
||||
/// permanently unreachable. Anything past the width still fails loudly rather than
|
||||
/// silently truncating a cursor into one that resumes at the wrong row.
|
||||
const ID_WIDTH: usize = 384;
|
||||
|
||||
/// Byte width the candidate oid half is padded to.
|
||||
///
|
||||
/// Git mints exactly two oid widths and this field carries BOTH. A production repo is
|
||||
/// created by `store::init_bare` with `git init --bare --object-format=sha1`, so its
|
||||
/// oids are 40 hex; only the sha256 test fixtures mint 64. The field is therefore
|
||||
/// length-prefixed like the two row halves rather than a bare fixed 64: a 64-only
|
||||
/// field would fail every seal on a real deployment, and a failed seal sheds a
|
||||
/// tokenless 503 that is byte-identical to "your ladder is over".
|
||||
///
|
||||
/// The padding to 64 is what keeps the WIDTH off the wire. Without it a 40-hex token
|
||||
/// is 24 bytes shorter than a 64-hex one, and token length would say which object
|
||||
/// format the holder's repo uses.
|
||||
const OID_WIDTH: usize = 64;
|
||||
|
||||
/// `version | created_len:u16 | created[CREATED_WIDTH] | id_len:u16 | id[ID_WIDTH] | oid_len:u16 | oid[OID_WIDTH] | expires:i64`
|
||||
const PLAINTEXT_LEN: usize = 1 + 2 + CREATED_WIDTH + 2 + ID_WIDTH + 2 + OID_WIDTH + 8;
|
||||
|
||||
/// Nonce width for XChaCha20-Poly1305.
|
||||
const NONCE_LEN: usize = 24;
|
||||
|
||||
/// A fresh random 32-byte sealing key from the OS CSPRNG.
|
||||
pub fn new_key() -> [u8; 32] {
|
||||
let mut key = [0u8; 32];
|
||||
OsRng.fill_bytes(&mut key);
|
||||
key
|
||||
}
|
||||
|
||||
// The two halves below are deliberately separate and adjacent. The framing pair owns
|
||||
// "every token is the same length"; the AEAD pair owns "the contents are confidential
|
||||
// and CID-bound". Keeping them apart is what lets each property be exercised (and
|
||||
// broken) without disturbing the other.
|
||||
|
||||
/// Encode a position into the FIXED-WIDTH plaintext:
|
||||
/// `version | created_len:u16 | created[CREATED_WIDTH] | id_len:u16 | id[ID_WIDTH] | oid_len:u16 | oid[OID_WIDTH] | expires:i64`
|
||||
///
|
||||
/// The padding is the point. AEAD ciphertext is plaintext-length plus the tag, and every
|
||||
/// field of a scan position varies in length, so a length-prefixed encoding with no
|
||||
/// padding would make token LENGTH a side channel for the sealed row and for the
|
||||
/// candidate's object format. Each field is padded to its OWN fixed width, which keeps
|
||||
/// every minted token the same length while letting the id half carry the range the
|
||||
/// write path actually admits.
|
||||
fn encode_position(pos: &ScanPosition, expires_at_unix: i64) -> anyhow::Result<Vec<u8>> {
|
||||
let mut out = vec![0u8; PLAINTEXT_LEN];
|
||||
out[0] = VERSION;
|
||||
let mut at = 1;
|
||||
for (field, width) in [
|
||||
(pos.created_at_key.as_bytes(), CREATED_WIDTH),
|
||||
(pos.id.as_bytes(), ID_WIDTH),
|
||||
(pos.sha256_hex.as_bytes(), OID_WIDTH),
|
||||
] {
|
||||
if field.len() > width {
|
||||
// Loud rather than truncating: a clipped cursor resumes at the wrong row and
|
||||
// silently skips coverage, which is the availability half of the bug this
|
||||
// token exists to fix.
|
||||
anyhow::bail!(
|
||||
"scan token field is {} bytes, over the {width}-byte fixed width",
|
||||
field.len()
|
||||
);
|
||||
}
|
||||
out[at..at + 2].copy_from_slice(&(field.len() as u16).to_le_bytes());
|
||||
at += 2;
|
||||
out[at..at + field.len()].copy_from_slice(field);
|
||||
at += width;
|
||||
}
|
||||
out[at..at + 8].copy_from_slice(&expires_at_unix.to_le_bytes());
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Decode what [`encode_position`] wrote. `None` on any structural mismatch.
|
||||
fn decode_position(bytes: &[u8]) -> Option<(ScanPosition, i64)> {
|
||||
if bytes.len() != PLAINTEXT_LEN || bytes[0] != VERSION {
|
||||
return None;
|
||||
}
|
||||
let mut at = 1;
|
||||
let mut fields = [const { String::new() }; 3];
|
||||
for (slot, width) in fields.iter_mut().zip([CREATED_WIDTH, ID_WIDTH, OID_WIDTH]) {
|
||||
let len = u16::from_le_bytes([bytes[at], bytes[at + 1]]) as usize;
|
||||
at += 2;
|
||||
if len > width {
|
||||
return None;
|
||||
}
|
||||
*slot = String::from_utf8(bytes[at..at + len].to_vec()).ok()?;
|
||||
at += width;
|
||||
}
|
||||
let expires_at = i64::from_le_bytes(bytes[at..at + 8].try_into().ok()?);
|
||||
let [created_at_key, id, sha256_hex] = fields;
|
||||
// A zero-length candidate is a third state the encoder never mints. The front-of-table
|
||||
// sentinel is empty ROW halves with a real oid, so an empty oid would hand the resume
|
||||
// path a candidate that names nothing; refuse it like every other malformed frame.
|
||||
if sha256_hex.is_empty() {
|
||||
return None;
|
||||
}
|
||||
Some((
|
||||
ScanPosition {
|
||||
created_at_key,
|
||||
id,
|
||||
sha256_hex,
|
||||
},
|
||||
expires_at,
|
||||
))
|
||||
}
|
||||
|
||||
/// AEAD-seal `plaintext` under `key`, bound to `cid`, framed as `nonce || ciphertext`.
|
||||
fn seal_bytes(key: &[u8; 32], cid: &str, plaintext: &[u8]) -> anyhow::Result<Vec<u8>> {
|
||||
let cipher = XChaCha20Poly1305::new_from_slice(key)
|
||||
.map_err(|e| anyhow::anyhow!("scan token key: {e}"))?;
|
||||
// A FRESH nonce per seal, from the OS CSPRNG. Under a stream cipher a repeated nonce
|
||||
// repeats the keystream, and two tokens sealed under one nonce XOR to the difference
|
||||
// of their plaintexts, which recovers a withheld row in full when the attacker can
|
||||
// force one of the two positions. This draw is the property the whole confidentiality
|
||||
// claim rests on.
|
||||
let mut nonce = [0u8; NONCE_LEN];
|
||||
OsRng.fill_bytes(&mut nonce);
|
||||
let sealed = cipher
|
||||
.encrypt(
|
||||
XNonce::from_slice(&nonce),
|
||||
Payload {
|
||||
msg: plaintext,
|
||||
// The canonical CID as associated data: a token minted while scanning for
|
||||
// one CID does not authenticate against another, so it cannot be replayed
|
||||
// to seed a different scan.
|
||||
aad: cid.as_bytes(),
|
||||
},
|
||||
)
|
||||
.map_err(|e| anyhow::anyhow!("scan token seal: {e}"))?;
|
||||
let mut out = Vec::with_capacity(NONCE_LEN + sealed.len());
|
||||
out.extend_from_slice(&nonce);
|
||||
out.extend_from_slice(&sealed);
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Open what [`seal_bytes`] framed. `None` on any failure, including a wrong `cid`.
|
||||
fn open_bytes(key: &[u8; 32], cid: &str, raw: &[u8]) -> Option<Vec<u8>> {
|
||||
if raw.len() <= NONCE_LEN + 16 {
|
||||
return None;
|
||||
}
|
||||
let (nonce, sealed) = raw.split_at(NONCE_LEN);
|
||||
let cipher = XChaCha20Poly1305::new_from_slice(key).ok()?;
|
||||
cipher
|
||||
.decrypt(
|
||||
XNonce::from_slice(nonce),
|
||||
Payload {
|
||||
msg: sealed,
|
||||
aad: cid.as_bytes(),
|
||||
},
|
||||
)
|
||||
.ok()
|
||||
}
|
||||
|
||||
/// Seal `pos` under `key`, bound to `cid`, expiring at `expires_at_unix`.
|
||||
///
|
||||
/// Returns the base64url (no pad) token. Errors only when a field exceeds
|
||||
/// its own fixed width ([`CREATED_WIDTH`], [`ID_WIDTH`], [`OID_WIDTH`]) or the AEAD
|
||||
/// itself fails, never silently truncates.
|
||||
pub fn seal_scan_token(
|
||||
key: &[u8; 32],
|
||||
cid: &str,
|
||||
pos: &ScanPosition,
|
||||
expires_at_unix: i64,
|
||||
) -> anyhow::Result<String> {
|
||||
let plaintext = encode_position(pos, expires_at_unix)?;
|
||||
Ok(B64URL.encode(seal_bytes(key, cid, &plaintext)?))
|
||||
}
|
||||
|
||||
/// Open a token minted by [`seal_scan_token`] under the same key and CID.
|
||||
///
|
||||
/// `None` for every failure class alike (wrong key, tampered, foreign CID, expired,
|
||||
/// malformed, wrong version), so the caller can treat all of them as "absent" without
|
||||
/// leaking which one occurred.
|
||||
pub fn open_scan_token(
|
||||
key: &[u8; 32],
|
||||
cid: &str,
|
||||
token: &str,
|
||||
now_unix: i64,
|
||||
) -> Option<ScanPosition> {
|
||||
let raw = B64URL.decode(token).ok()?;
|
||||
let plaintext = open_bytes(key, cid, &raw)?;
|
||||
let (pos, expires_at) = decode_position(&plaintext)?;
|
||||
if now_unix >= expires_at {
|
||||
return None;
|
||||
}
|
||||
Some(pos)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// A production-shaped candidate: `git init --bare --object-format=sha1`, so 40 hex.
|
||||
const OID_40: &str = "a1b2c3d4e5f60718293a4b5c6d7e8f9012345678";
|
||||
/// A test-fixture-shaped candidate: the sha256 repos the suite creates mint 64 hex.
|
||||
const OID_64: &str = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef";
|
||||
|
||||
fn pos(created: &str, id: &str) -> ScanPosition {
|
||||
pos_for(created, id, OID_40)
|
||||
}
|
||||
|
||||
fn pos_for(created: &str, id: &str, sha256_hex: &str) -> ScanPosition {
|
||||
ScanPosition {
|
||||
created_at_key: created.to_string(),
|
||||
id: id.to_string(),
|
||||
sha256_hex: sha256_hex.to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Seal a hand-built plaintext through the AEAD half, so a test can frame bytes the
|
||||
/// encoder would never mint (an old version byte, a zero-length oid) and still exercise
|
||||
/// the real open path.
|
||||
fn seal_raw(key: &[u8; 32], cid: &str, plaintext: &[u8]) -> String {
|
||||
B64URL.encode(seal_bytes(key, cid, plaintext).unwrap())
|
||||
}
|
||||
|
||||
/// Byte offset of the oid length prefix inside the plaintext, derived from the widths
|
||||
/// rather than hardcoded so a width change moves it with the layout.
|
||||
const OID_LEN_AT: usize = 1 + 2 + CREATED_WIDTH + 2 + ID_WIDTH;
|
||||
|
||||
/// Scenario 1: both of git's oid widths round trip. The 40-hex case is the PRODUCTION
|
||||
/// shape (`git init --bare --object-format=sha1`), and an all-64 fixture suite would
|
||||
/// never exercise it, which is exactly how a fixed-64 field would ship broken.
|
||||
#[test]
|
||||
fn round_trips_at_both_oid_widths() {
|
||||
let key = new_key();
|
||||
for hex in [OID_40, OID_64] {
|
||||
let p = pos_for("2020-01-01T00:00:03+00:00", "z6MkOwner/private-repo", hex);
|
||||
let t =
|
||||
seal_scan_token(&key, "bafkcid", &p, 1 << 40).expect("both oid widths must seal");
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &t, 0),
|
||||
Some(p),
|
||||
"a {}-hex candidate must open to the identical position",
|
||||
hex.len()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Scenario 2: a token framed under the OLD version opens to `None`, never a misparse.
|
||||
/// Both legs matter: the version-2 plaintext was a different LENGTH, and a future
|
||||
/// same-length layout would only be caught by the version byte itself.
|
||||
#[test]
|
||||
fn a_prior_layout_version_opens_to_none() {
|
||||
let key = new_key();
|
||||
|
||||
// The version-2 layout verbatim: no oid field, so 461 bytes.
|
||||
let mut old = vec![0u8; 1 + 2 + CREATED_WIDTH + 2 + ID_WIDTH + 8];
|
||||
old[0] = 2;
|
||||
assert_eq!(old.len(), 461, "the version-2 plaintext was 461 bytes");
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &seal_raw(&key, "bafkcid", &old), 0),
|
||||
None,
|
||||
"a version-2 token must open to None so the caller restarts at the front"
|
||||
);
|
||||
|
||||
// Same length, stale version byte: only the version check can refuse this one.
|
||||
let mut stamped = encode_position(
|
||||
&pos("2020-01-01T00:00:03+00:00", "z6MkOwner/private-repo"),
|
||||
1 << 40,
|
||||
)
|
||||
.unwrap();
|
||||
stamped[0] = VERSION - 1;
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &seal_raw(&key, "bafkcid", &stamped), 0),
|
||||
None,
|
||||
"a stale version byte must open to None even at the current width"
|
||||
);
|
||||
}
|
||||
|
||||
/// Scenario 3: token length is invariant across candidate VALUE and candidate WIDTH.
|
||||
/// The padding is what keeps the oid width off the wire: without it a 40-hex token is
|
||||
/// 24 bytes shorter than a 64-hex one and the length says which repo format the
|
||||
/// holder uses.
|
||||
#[test]
|
||||
fn token_length_is_invariant_across_oid_widths() {
|
||||
let key = new_key();
|
||||
let created = "2020-01-01T00:00:00+00:00";
|
||||
let id = "z6MkOwner/private-repo";
|
||||
let short =
|
||||
seal_scan_token(&key, "bafkcid", &pos_for(created, id, OID_40), 1 << 40).unwrap();
|
||||
let long =
|
||||
seal_scan_token(&key, "bafkcid", &pos_for(created, id, OID_64), 1 << 40).unwrap();
|
||||
assert_eq!(
|
||||
short.len(),
|
||||
long.len(),
|
||||
"a 40-hex and a 64-hex candidate must mint tokens of identical length, or the \
|
||||
oid width is a side channel"
|
||||
);
|
||||
|
||||
// The absolute width, pinned by execution rather than by arithmetic on paper. The
|
||||
// gl client's mock fixtures hardcode this number (`TOKEN_LEN` in
|
||||
// crates/gl/src/ipfs_cmd.rs), and nothing in that crate seals a real token, so this
|
||||
// assertion is the only executable check that the two agree.
|
||||
assert_eq!(
|
||||
short.len(),
|
||||
756,
|
||||
"24 nonce + {PLAINTEXT_LEN} plaintext + 16 tag, base64url no pad"
|
||||
);
|
||||
}
|
||||
|
||||
/// Scenario 4: the front-of-table sentinel. Empty row halves with a REAL candidate
|
||||
/// round trip, which is what lets a seal say "this candidate, no row cursor yet".
|
||||
#[test]
|
||||
fn empty_row_fields_round_trip_with_a_real_candidate() {
|
||||
let key = new_key();
|
||||
let p = pos_for("", "", OID_40);
|
||||
let t =
|
||||
seal_scan_token(&key, "bafkcid", &p, 1 << 40).expect("the front sentinel must seal");
|
||||
assert_eq!(open_scan_token(&key, "bafkcid", &t, 0), Some(p));
|
||||
}
|
||||
|
||||
/// Scenario 6, third leg: a zero-length oid is a distinguishable third state that the
|
||||
/// encoder never mints, and accepting it would hand the sentinel machinery a candidate
|
||||
/// naming nothing. The decode path refuses it.
|
||||
#[test]
|
||||
fn a_zero_length_candidate_opens_to_none() {
|
||||
let key = new_key();
|
||||
let mut plaintext = encode_position(
|
||||
&pos("2020-01-01T00:00:03+00:00", "z6MkOwner/private-repo"),
|
||||
1 << 40,
|
||||
)
|
||||
.unwrap();
|
||||
plaintext[OID_LEN_AT..OID_LEN_AT + 2].copy_from_slice(&0u16.to_le_bytes());
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &seal_raw(&key, "bafkcid", &plaintext), 0),
|
||||
None,
|
||||
"a zero-length candidate must open to None, not to a position naming nothing"
|
||||
);
|
||||
}
|
||||
|
||||
/// Scenario 6, second leg: an oid past the 64-byte width fails the seal loudly rather
|
||||
/// than being clipped into a hex that names a different candidate.
|
||||
#[test]
|
||||
fn an_oid_over_the_fixed_width_fails_loudly() {
|
||||
let key = new_key();
|
||||
let p = pos_for(
|
||||
"2020-01-01T00:00:03+00:00",
|
||||
"z6MkOwner/private-repo",
|
||||
&"a".repeat(OID_WIDTH + 1),
|
||||
);
|
||||
assert!(
|
||||
seal_scan_token(&key, "bafkcid", &p, 1 << 40).is_err(),
|
||||
"an over-wide candidate must fail the seal, never be truncated into a hex that \
|
||||
resumes the wrong candidate"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_trips_under_the_same_key_and_cid() {
|
||||
let key = new_key();
|
||||
let p = pos("2020-01-01T00:00:03+00:00", "z6MkOwner/private-repo");
|
||||
let t = seal_scan_token(&key, "bafkcid", &p, 1 << 40).unwrap();
|
||||
assert_eq!(open_scan_token(&key, "bafkcid", &t, 0), Some(p));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn every_failure_class_opens_to_none() {
|
||||
let key = new_key();
|
||||
let other = new_key();
|
||||
let p = pos("2020-01-01T00:00:03+00:00", "z6MkOwner/private-repo");
|
||||
let t = seal_scan_token(&key, "bafkcid", &p, 1 << 40).unwrap();
|
||||
|
||||
assert_eq!(open_scan_token(&other, "bafkcid", &t, 0), None, "wrong key");
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkOTHER", &t, 0),
|
||||
None,
|
||||
"foreign CID"
|
||||
);
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &t, 1 << 41),
|
||||
None,
|
||||
"expired"
|
||||
);
|
||||
assert_eq!(open_scan_token(&key, "bafkcid", "!!not b64", 0), None);
|
||||
assert_eq!(open_scan_token(&key, "bafkcid", "", 0), None);
|
||||
let mut flipped: Vec<u8> = t.bytes().collect();
|
||||
let last = flipped.len() - 1;
|
||||
flipped[last] = if flipped[last] == b'A' { b'B' } else { b'A' };
|
||||
assert_eq!(
|
||||
open_scan_token(&key, "bafkcid", &String::from_utf8(flipped).unwrap(), 0),
|
||||
None,
|
||||
"tampered"
|
||||
);
|
||||
}
|
||||
|
||||
/// The id half must clear the LARGEST repo id the node's own write path admits,
|
||||
/// not merely a typical one. `upsert_mirror_repo` builds `repos.id` as
|
||||
/// `{owner}/{name}`, and the slug validators in `repo_store` admit 255 bytes of
|
||||
/// owner and 100 of name, so 356 is reachable. A width under that turns the
|
||||
/// boundary row into a seal failure, which sheds a tokenless 503 that is
|
||||
/// byte-identical to "your ladder is over" and strands every row past it forever.
|
||||
#[test]
|
||||
fn round_trips_a_repo_id_at_the_write_paths_maximum() {
|
||||
let key = new_key();
|
||||
let id = format!("{}/{}", "o".repeat(255), "n".repeat(100));
|
||||
assert_eq!(id.len(), 356, "255 owner + '/' + 100 name");
|
||||
let p = pos("2020-01-01T00:00:03+00:00", &id);
|
||||
let t = seal_scan_token(&key, "bafkcid", &p, 1 << 40)
|
||||
.expect("a repo id the write path admits must seal, never fail the width");
|
||||
assert_eq!(open_scan_token(&key, "bafkcid", &t, 0), Some(p));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_field_over_the_fixed_width_fails_loudly() {
|
||||
let key = new_key();
|
||||
let p = pos("2020-01-01T00:00:03+00:00", &"x".repeat(ID_WIDTH + 1));
|
||||
assert!(
|
||||
seal_scan_token(&key, "bafkcid", &p, 1 << 40).is_err(),
|
||||
"an over-wide field must fail the seal, never be truncated into a cursor \
|
||||
that resumes at the wrong row"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -26,61 +26,14 @@ pub async fn list_anchors(
|
||||
Query(q): Query<ListAnchorsQuery>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let limit = q.limit.min(200);
|
||||
// Bare `?` so connection-class sqlx failures downcast to `AppError::Db` and
|
||||
// map to 503 `db_unavailable` (not 500 via `.map_err(AppError::Internal)`) (#251).
|
||||
let anchors = state
|
||||
.db
|
||||
.list_arweave_anchors(q.repo.as_deref(), limit)
|
||||
.await?;
|
||||
.await
|
||||
.map_err(crate::error::AppError::Internal)?;
|
||||
|
||||
Ok(Json(serde_json::json!({
|
||||
"anchors": anchors,
|
||||
"count": anchors.len(),
|
||||
})))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod closed_pool_tests {
|
||||
use super::*;
|
||||
use axum::http::{Request, StatusCode};
|
||||
use axum::Router;
|
||||
use serde_json::Value;
|
||||
use sqlx::PgPool;
|
||||
use tower::ServiceExt;
|
||||
|
||||
/// #251: a closed pool on /api/v1/arweave/anchors must be 503 db_unavailable.
|
||||
#[sqlx::test]
|
||||
async fn list_anchors_closed_pool_returns_503_db_unavailable(pool: PgPool) {
|
||||
let state = crate::test_support::test_state(pool.clone()).await;
|
||||
pool.close().await;
|
||||
|
||||
let resp = Router::new()
|
||||
.route("/api/v1/arweave/anchors", axum::routing::get(list_anchors))
|
||||
.with_state(state)
|
||||
.oneshot(
|
||||
Request::builder()
|
||||
.uri("/api/v1/arweave/anchors")
|
||||
.body(axum::body::Body::empty())
|
||||
.unwrap(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"closed-pool outage must be retryable 503, not 500"
|
||||
);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.expect("read body");
|
||||
let v: Value = serde_json::from_slice(&bytes).expect("json body");
|
||||
assert_eq!(
|
||||
v,
|
||||
serde_json::json!({
|
||||
"error": crate::error::DB_UNAVAILABLE_CODE,
|
||||
"message": crate::error::DB_UNAVAILABLE_MESSAGE,
|
||||
})
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1440,8 +1440,7 @@ mod ref_updates_feed_tests {
|
||||
|
||||
// A DB error in the gate fails closed as 500, not swallowed into an empty 200 (the
|
||||
// regression the old get_repo().ok().flatten() allowed). Inject by dropping a
|
||||
// column get_repo selects so its query errors. Also pin the anonymous body to
|
||||
// the exact opaque object (#226).
|
||||
// column get_repo selects so its query errors.
|
||||
#[sqlx::test]
|
||||
async fn repo_events_db_error_fails_closed_500(pool: PgPool) {
|
||||
let state = test_state(pool.clone()).await;
|
||||
@@ -1464,18 +1463,6 @@ mod ref_updates_feed_tests {
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
"a DB error must fail closed (500), never serve an empty 200"
|
||||
);
|
||||
let body = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.expect("read body");
|
||||
let body = String::from_utf8_lossy(&body);
|
||||
let v: serde_json::Value = serde_json::from_str(&body).expect("json body");
|
||||
assert_eq!(
|
||||
v,
|
||||
serde_json::json!({
|
||||
"error": "db_error",
|
||||
"message": crate::error::DB_ERROR_MESSAGE,
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
// Symmetric to the gate DB-error test: a DB error in the CERT fetch (after the gate
|
||||
|
||||
+618
-7578
File diff suppressed because it is too large.
Load diff
File diff suppressed because it is too large.
Load diff
@@ -208,15 +208,11 @@ mod authz_guard {
|
||||
(issues, "create_issue", "authorize_repo_read("),
|
||||
(bounties, "create_bounty", "authorize_repo_read("),
|
||||
(repos, "fork_repo", "authorize_repo_read("),
|
||||
// get_by_cid resolves each candidate (provenance path + legacy scan) through
|
||||
// the shared `gate_and_serve`; the gate markers themselves are asserted
|
||||
// below. This row proves the delegation is real, so the gate is actually
|
||||
// reached rather than dead code. The delegated gate still calls
|
||||
// `visibility_check` directly and never `authorize_repo_read`, so it keeps
|
||||
// the property the pre-merge marker enforced: no fuzzy re-resolve.
|
||||
(ipfs, "get_by_cid", "gate_and_serve("),
|
||||
// Sibling read surfaces: gate private-repo metadata on read visibility
|
||||
// (public repos stay anonymous; private repos 404).
|
||||
// get_by_cid gates each iterated repo row directly via visibility_check
|
||||
// (KTD2a: it must NOT route through authorize_repo_read's fuzzy re-resolve).
|
||||
(ipfs, "get_by_cid", "visibility_check("),
|
||||
// #94 sibling read surfaces: gate private-repo metadata on read
|
||||
// visibility (public repos stay anonymous; private repos 404).
|
||||
(replicas, "list_replicas", "authorize_repo_read("),
|
||||
(protect, "list_protected_branches", "authorize_repo_read("),
|
||||
(labels, "list_labels", "authorize_repo_read("),
|
||||
@@ -254,22 +250,6 @@ mod authz_guard {
|
||||
"visibility::require_owner must use did_matches for DID-safe owner matching"
|
||||
);
|
||||
|
||||
// The CID read surface (#173) enforces its gate inside the shared
|
||||
// `gate_and_serve`, which BOTH the provenance path and the legacy scan call, so
|
||||
// the markers must live there (the get_by_cid row above only proves delegation).
|
||||
// The repo's own "/" visibility check (KTD2a — never authorize_repo_read's fuzzy
|
||||
// re-resolve) and the quarantine hard-drop BEFORE visibility (INV-11) are both
|
||||
// load-bearing: removing either re-opens a leak on the provenance path.
|
||||
let gate_body = fn_body(ipfs, "gate_and_serve");
|
||||
assert!(
|
||||
gate_body.contains("visibility_check("),
|
||||
"gate_and_serve must gate the CID read surface via visibility_check (KTD2a)"
|
||||
);
|
||||
assert!(
|
||||
gate_body.contains("if quarantined"),
|
||||
"gate_and_serve must hard-drop a quarantined repo before the visibility gate (INV-11)"
|
||||
);
|
||||
|
||||
for (src, func, marker) in rows {
|
||||
let body = fn_body(src, func);
|
||||
assert!(
|
||||
|
||||
@@ -17,39 +17,9 @@ use gitlawb_core::did::Did;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::auth::AuthenticatedDid;
|
||||
use crate::db::{PeerWriteAuthority, PeerWriteDenied};
|
||||
use crate::error::{AppError, Result};
|
||||
use crate::state::AppState;
|
||||
|
||||
/// Map an `upsert_peer` failure onto its response class.
|
||||
///
|
||||
/// The boundary's denials arrive inside an anyhow chain, so they are downcast
|
||||
/// back out the way `From<anyhow::Error> for AppError` already recovers sqlx
|
||||
/// errors. Without this a refusal renders as a 500, which is the mis-rendered
|
||||
/// denial this gate exists to avoid. An authority refusal is 403; naming a DID
|
||||
/// method that can never authenticate, or a DID whose verifying key cannot be
|
||||
/// resolved, is a fact about the input's form, so both are the 400 validation
|
||||
/// class, and the unresolvable one carries its own code so it reads the same to
|
||||
/// a client as the auth middleware's answer for an unresolvable keyid. The match
|
||||
/// stays exhaustive with no wildcard: the compile error a new denial causes here
|
||||
/// is what finds every mapping site.
|
||||
fn peer_write_error(err: anyhow::Error) -> AppError {
|
||||
match err.downcast::<PeerWriteDenied>() {
|
||||
Ok(denied) => match &denied {
|
||||
PeerWriteDenied::UnsupportedDidMethod { .. } => {
|
||||
AppError::BadRequest(denied.to_string())
|
||||
}
|
||||
PeerWriteDenied::UnresolvableDid { .. } => {
|
||||
AppError::UnresolvableDid(denied.to_string())
|
||||
}
|
||||
PeerWriteDenied::UnprovenRepoint { .. } | PeerWriteDenied::ProofDidMismatch { .. } => {
|
||||
AppError::Forbidden(denied.to_string())
|
||||
}
|
||||
},
|
||||
Err(other) => AppError::from(other),
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct AnnounceRequest {
|
||||
/// The DID of the announcing node
|
||||
@@ -217,30 +187,18 @@ pub async fn announce(
|
||||
.did
|
||||
.parse()
|
||||
.map_err(|e: gitlawb_core::Error| AppError::BadRequest(e.to_string()))?;
|
||||
// The extension's DID is cryptographically derived, never body-supplied:
|
||||
// auth/mod.rs resolves the verifying key FROM the keyid DID itself, so what
|
||||
// is carried through to the upsert boundary below is a proof, not a claim.
|
||||
let proven_did: Option<String> = if let Some(Extension(auth)) = auth {
|
||||
// 403, not 400: this caller proved control of some DID and spent that
|
||||
// proof on a different DID's row, which is a refusal of authority over
|
||||
// the targeted row: the same denial as an unsigned repoint, and two
|
||||
// callers denied for the same reason must not get different response
|
||||
// classes. The 400 class stays for input-form failures: a malformed
|
||||
// DID, a non-public URL, a self-announce, and a DID method that can
|
||||
// never authenticate.
|
||||
if let Some(Extension(auth)) = auth {
|
||||
if auth.0 != announced_did.to_string() {
|
||||
return Err(AppError::Forbidden(
|
||||
return Err(AppError::BadRequest(
|
||||
"Signature keyid must match announced DID".into(),
|
||||
));
|
||||
}
|
||||
Some(auth.0)
|
||||
} else {
|
||||
tracing::warn!(
|
||||
did = %announced_did,
|
||||
"accepted unsigned peer announce; set GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true after all peers upgrade"
|
||||
);
|
||||
None
|
||||
};
|
||||
}
|
||||
|
||||
// Validate the URL is a public http(s) endpoint. The announce route is
|
||||
// reachable unauthenticated (until all peers sign), so without this an
|
||||
@@ -270,20 +228,7 @@ pub async fn announce(
|
||||
));
|
||||
}
|
||||
|
||||
// The authority declaration, not a re-statement of the check above: the
|
||||
// boundary carries the proven DID and re-checks it against the row itself,
|
||||
// so the keyid comparison above is an early rejection rather than the only
|
||||
// gate. The other writer (the bootstrap announce-back in main.rs) never
|
||||
// reaches this handler at all.
|
||||
let authority = match proven_did.as_deref() {
|
||||
Some(did) => PeerWriteAuthority::Proven(did),
|
||||
None => PeerWriteAuthority::Unproven,
|
||||
};
|
||||
state
|
||||
.db
|
||||
.upsert_peer(&req.did, &req.http_url, authority)
|
||||
.await
|
||||
.map_err(peer_write_error)?;
|
||||
state.db.upsert_peer(&req.did, &req.http_url).await?;
|
||||
|
||||
tracing::info!(did = %req.did, url = %req.http_url, "peer announced");
|
||||
|
||||
@@ -498,15 +443,21 @@ pub async fn ping_peer(
|
||||
.find(|p| p.did == did)
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("peer {did} not found")))?;
|
||||
|
||||
// Use DB-aware readiness rather than process liveness: `/health` stays 200
|
||||
// during a mid-life database outage, while `/ready` reports 503. A 404-only
|
||||
// fallback keeps pre-readiness peers compatible. The shared helper also
|
||||
// preserves the no-redirect SSRF guard on peer-controlled URLs.
|
||||
let ok = crate::ping_peer_readiness(&state.http_client, &peer.http_url).await;
|
||||
// Async ping
|
||||
let url = format!("{}/health", peer.http_url.trim_end_matches('/'));
|
||||
// Use the shared no-redirect client: bare `reqwest::get` follows redirects,
|
||||
// so a peer could answer with `302 -> http://127.0.0.1/` and turn the ping
|
||||
// into an SSRF probe.
|
||||
let ok = state
|
||||
.http_client
|
||||
.get(&url)
|
||||
.send()
|
||||
.await
|
||||
.map(|r| r.status().is_success())
|
||||
.unwrap_or(false);
|
||||
|
||||
let _ = state.db.mark_peer_ping(&did, ok).await;
|
||||
|
||||
// This anonymous diagnostic endpoint is intentionally read-only. The
|
||||
// periodic gossip loop owns the persisted federation-reachability gate and
|
||||
// requires consecutive failures before marking a peer unreachable.
|
||||
Ok(Json(serde_json::json!({
|
||||
"did": did,
|
||||
"http_url": peer.http_url,
|
||||
@@ -613,7 +564,7 @@ mod tests {
|
||||
use axum::body::Body;
|
||||
use axum::extract::ConnectInfo;
|
||||
use axum::http::{header, Method, Request, StatusCode};
|
||||
use axum::routing::{get, post};
|
||||
use axum::routing::post;
|
||||
use axum::{middleware, Extension, Router};
|
||||
use gitlawb_core::http_sig::sign_request;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
@@ -819,84 +770,12 @@ mod tests {
|
||||
let did = Keypair::generate().did().to_string();
|
||||
state
|
||||
.db
|
||||
.upsert_peer(
|
||||
&did,
|
||||
"https://peer.example.com",
|
||||
crate::db::PeerWriteAuthority::Unproven,
|
||||
)
|
||||
.upsert_peer(&did, "https://peer.example.com")
|
||||
.await
|
||||
.unwrap();
|
||||
did
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn manual_ping_uses_readiness_without_mutating_federation_gate(pool: PgPool) {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(503)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let mut state = test_state(pool.clone()).await;
|
||||
state.http_client =
|
||||
Arc::new(crate::build_http_client().expect("production HTTP client should build"));
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
sqlx::query(
|
||||
"INSERT INTO peers (did, http_url, last_seen, last_ping_ok, announced_at)
|
||||
VALUES ($1, $2, $3, TRUE, $3)",
|
||||
)
|
||||
.bind(&did)
|
||||
.bind(server.url())
|
||||
.bind(now)
|
||||
.execute(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let response = Router::new()
|
||||
.route("/api/v1/peers/{did}/ping", get(super::ping_peer))
|
||||
.with_state(state.clone())
|
||||
.oneshot(
|
||||
Request::builder()
|
||||
.method(Method::GET)
|
||||
.uri(format!("/api/v1/peers/{did}/ping"))
|
||||
.body(Body::empty())
|
||||
.unwrap(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(response.status(), StatusCode::OK);
|
||||
let body = axum::body::to_bytes(response.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let json: serde_json::Value = serde_json::from_slice(&body).unwrap();
|
||||
assert_eq!(json["reachable"], false);
|
||||
ready.assert_async().await;
|
||||
health.assert_async().await;
|
||||
|
||||
let peer = state
|
||||
.db
|
||||
.list_peers()
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.find(|peer| peer.did == did)
|
||||
.unwrap();
|
||||
assert!(
|
||||
peer.last_ping_ok,
|
||||
"an anonymous manual sample must not rewrite the federation gate"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_unsigned_flood_is_throttled(pool: PgPool) {
|
||||
// notify still accepts an unsigned known-peer notification (rolling-upgrade
|
||||
@@ -1276,57 +1155,6 @@ mod tests {
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
}
|
||||
|
||||
/// U1 (#273). An unsigned announce must not repoint an existing peer's row.
|
||||
///
|
||||
/// Kills the unconditional `ON CONFLICT(did) DO UPDATE SET http_url = $2` in
|
||||
/// `Db::upsert_peer`. The failure message carries BOTH observed values,
|
||||
/// because the gate is the observed rewrite (2xx AND the attacker URL
|
||||
/// stored), not merely a failing assertion: a 429 from the peer-write brake,
|
||||
/// a fixture URL `is_public_http_url` rejects, or a DB error would all read
|
||||
/// as "assertion failed" while proving nothing about this defect.
|
||||
#[sqlx::test]
|
||||
async fn unsigned_announce_cannot_repoint_an_existing_peer(pool: PgPool) {
|
||||
const HONEST: &str = "https://honest-peer.example.com";
|
||||
const ATTACKER: &str = "https://attacker.example.com";
|
||||
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
state
|
||||
.db
|
||||
.upsert_peer(&did, HONEST, crate::db::PeerWriteAuthority::Unproven)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let stored_url = |peers: Vec<crate::db::PeerRecord>| {
|
||||
peers.into_iter().find(|p| p.did == did).map(|p| p.http_url)
|
||||
};
|
||||
assert_eq!(
|
||||
stored_url(state.db.list_peers().await.unwrap()).as_deref(),
|
||||
Some(HONEST),
|
||||
"seed did not take; the case below would pass vacuously"
|
||||
);
|
||||
|
||||
// Clone before build_router consumes state, so the row can be read back.
|
||||
let db = state.db.clone();
|
||||
let body = format!(r#"{{"did":"{did}","http_url":"{ATTACKER}"}}"#);
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&body,
|
||||
"203.0.113.77:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
let status = resp.status();
|
||||
let stored = stored_url(db.list_peers().await.unwrap())
|
||||
.expect("peer row vanished; neither the allowed nor the denied outcome");
|
||||
|
||||
assert_eq!(
|
||||
stored, HONEST,
|
||||
"unsigned announce repointed an existing peer (observed status {status}, stored http_url {stored})"
|
||||
);
|
||||
}
|
||||
|
||||
// Build a request carrying a REAL RFC 9421 signature (not just an injected
|
||||
// extension), so it passes require_signature on the full production router.
|
||||
fn real_signed_trigger(peer: &str) -> Request<Body> {
|
||||
@@ -1437,607 +1265,4 @@ mod tests {
|
||||
"a 429 on a sync route must not say 'push': {s:?}"
|
||||
);
|
||||
}
|
||||
|
||||
// ── #273: the announce authority contract ─────────────────────────────────
|
||||
//
|
||||
// U4 drives the handler mounted alone, because signed_request_as injects an
|
||||
// AuthenticatedDid extension without a real signature and require_signature
|
||||
// would reject that on the full router. U5 then proves the same properties
|
||||
// through build_router with REAL RFC 9421 signatures, where a signature can
|
||||
// be pointed at a row it does not own.
|
||||
|
||||
const OWNER_URL: &str = "https://owner-peer.example.com";
|
||||
const MOVED_URL: &str = "https://moved-peer.example.com";
|
||||
const HIJACK_URL: &str = "https://hijacker.example.com";
|
||||
const WEB_DID: &str = "did:web:squatter.example.com";
|
||||
const KEYID_MISMATCH: &str = "Signature keyid must match announced DID";
|
||||
|
||||
/// Every column a consumer sees, so a case that claims "unchanged" compares
|
||||
/// the whole row rather than the one field it happened to think of.
|
||||
type PeerSnapshot = (String, String, Option<String>, bool, String);
|
||||
|
||||
async fn snapshot(db: &crate::db::Db, did: &str) -> Option<PeerSnapshot> {
|
||||
db.list_peers()
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.find(|p| p.did == did)
|
||||
.map(|p| {
|
||||
(
|
||||
p.did,
|
||||
p.http_url,
|
||||
p.last_seen,
|
||||
p.last_ping_ok,
|
||||
p.announced_at,
|
||||
)
|
||||
})
|
||||
}
|
||||
|
||||
/// Seed a peer row that has EARNED reachability, asserting the seed took,
|
||||
/// so no case below can pass vacuously against a row that was never written
|
||||
/// or against a flag that was already false. Without the granted ping a
|
||||
/// "must be unreachable after this" assertion compares false to false and
|
||||
/// stays green with the production code that clears the flag removed.
|
||||
async fn seed_peer_row(state: &AppState, did: &str, url: &str) -> PeerSnapshot {
|
||||
state
|
||||
.db
|
||||
.upsert_peer(did, url, crate::db::PeerWriteAuthority::Unproven)
|
||||
.await
|
||||
.expect("seed");
|
||||
state.db.mark_peer_ping(did, true).await.expect("seed ping");
|
||||
let seeded = snapshot(&state.db, did).await.expect("seed did not take");
|
||||
assert_eq!(seeded.1, url, "seed did not take");
|
||||
assert!(
|
||||
seeded.3,
|
||||
"the seeded row must start reachable, or a later unreachable assertion is vacuous"
|
||||
);
|
||||
seeded
|
||||
}
|
||||
|
||||
/// Status, error code, and message together, so a denial is asserted by its
|
||||
/// exact class and stated reason rather than by "not 2xx".
|
||||
async fn status_and_error(resp: axum::response::Response) -> (StatusCode, String, String) {
|
||||
let status = resp.status();
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let v: serde_json::Value = serde_json::from_slice(&bytes).unwrap_or_else(|_| {
|
||||
panic!(
|
||||
"error body must be JSON: {}",
|
||||
String::from_utf8_lossy(&bytes)
|
||||
)
|
||||
});
|
||||
let field = |k: &str| v[k].as_str().unwrap_or_default().to_string();
|
||||
(status, field("error"), field("message"))
|
||||
}
|
||||
|
||||
fn announce_body(did: &str, url: &str) -> String {
|
||||
format!(r#"{{"did":"{did}","http_url":"{url}"}}"#)
|
||||
}
|
||||
|
||||
fn announce_only(state: AppState) -> Router {
|
||||
Router::new()
|
||||
.route("/api/v1/peers/announce", post(super::announce))
|
||||
.with_state(state)
|
||||
}
|
||||
|
||||
fn announce_as(did: &str, body: &str) -> Request<Body> {
|
||||
signed_request_as(
|
||||
did,
|
||||
Method::POST,
|
||||
"/api/v1/peers/announce",
|
||||
Body::from(body.to_string()),
|
||||
)
|
||||
}
|
||||
|
||||
/// U4 scenario 1, and the first test the keyid branch has ever had: a caller
|
||||
/// who proved control of one DID must not announce another's. Kills
|
||||
/// neutralizing the handler's keyid comparison, and kills demoting this
|
||||
/// denial back to the 400 validation class where the unsigned repoint below
|
||||
/// is a 403 for the same reason.
|
||||
#[sqlx::test]
|
||||
async fn announce_keyid_mismatch_is_a_403_denial(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let victim = Keypair::generate().did().to_string();
|
||||
let hijacker = Keypair::generate().did().to_string();
|
||||
let before = seed_peer_row(&state, &victim, OWNER_URL).await;
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(announce_as(&hijacker, &announce_body(&victim, HIJACK_URL)))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::FORBIDDEN,
|
||||
"a proof spent on another DID's row is an authority refusal: {message}"
|
||||
);
|
||||
assert_eq!(code, "forbidden", "denial body must name the 403 class");
|
||||
assert!(
|
||||
message.contains(KEYID_MISMATCH),
|
||||
"the denial must name the keyid mismatch, got {message:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
snapshot(&state.db, &victim).await.expect("row vanished"),
|
||||
before,
|
||||
"the stored row must be byte-identical after a refused announce"
|
||||
);
|
||||
}
|
||||
|
||||
/// U4 scenario 2: the allowed signed case. A caller whose keyid IS the row
|
||||
/// repoints it. Kills a gate that refuses proven writes too.
|
||||
#[sqlx::test]
|
||||
async fn announce_with_matching_keyid_repoints_its_own_row(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let owner = Keypair::generate().did().to_string();
|
||||
seed_peer_row(&state, &owner, OWNER_URL).await;
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(announce_as(&owner, &announce_body(&owner, MOVED_URL)))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
let after = snapshot(&state.db, &owner).await.expect("row vanished");
|
||||
assert_eq!(after.1, MOVED_URL, "a proven repoint must land");
|
||||
}
|
||||
|
||||
/// U4 scenario 3: an unsigned caller cannot move an existing row, and the
|
||||
/// refusal renders as a 403 with its reason, never as a 500 or as success.
|
||||
#[sqlx::test]
|
||||
async fn announce_unsigned_repoint_is_a_403_denial(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let victim = Keypair::generate().did().to_string();
|
||||
let before = seed_peer_row(&state, &victim, OWNER_URL).await;
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(&victim, HIJACK_URL),
|
||||
"203.0.113.90:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::FORBIDDEN,
|
||||
"an unproven repoint is an authority refusal: {message}"
|
||||
);
|
||||
assert_eq!(code, "forbidden", "denial body must name the 403 class");
|
||||
assert!(
|
||||
message.contains("unproven announce cannot change an existing peer"),
|
||||
"the denial must name the repoint refusal, got {message:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
snapshot(&state.db, &victim).await.expect("row vanished"),
|
||||
before,
|
||||
"the stored row must be byte-identical after a refused repoint"
|
||||
);
|
||||
}
|
||||
|
||||
/// U4 scenarios 4 and 5, the allowed unsigned class: discovery of an unseen
|
||||
/// did:key still inserts, and an honest peer re-announcing the IDENTICAL URL
|
||||
/// still refreshes liveness. The URL is reused byte for byte because the
|
||||
/// comparison is exact, so a trailing slash would make this pass as a
|
||||
/// repoint rejection instead. Kills a gate widened until it breaks
|
||||
/// discovery or honest re-announces.
|
||||
#[sqlx::test]
|
||||
async fn announce_unsigned_insert_and_identical_url_reannounce_are_accepted(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let body = announce_body(&did, OWNER_URL);
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&body,
|
||||
"203.0.113.91:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::OK, "discovery must stay open");
|
||||
let before = snapshot(&state.db, &did).await.expect("row not inserted");
|
||||
assert_eq!(before.1, OWNER_URL);
|
||||
assert!(!before.3, "a never-probed peer inserts unreachable");
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&body,
|
||||
"203.0.113.92:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"an identical-URL re-announce is a liveness signal, not a repoint"
|
||||
);
|
||||
let after = snapshot(&state.db, &did).await.expect("row vanished");
|
||||
assert_eq!(after.1, OWNER_URL, "URL untouched");
|
||||
assert_eq!(after.3, before.3, "reachability untouched");
|
||||
assert_eq!(after.4, before.4, "announced_at untouched");
|
||||
let parse = |s: &Option<String>| {
|
||||
chrono::DateTime::parse_from_rfc3339(s.as_deref().expect("last_seen is set")).unwrap()
|
||||
};
|
||||
assert!(
|
||||
parse(&after.2) > parse(&before.2),
|
||||
"a same-URL re-announce must advance last_seen"
|
||||
);
|
||||
}
|
||||
|
||||
/// U4 scenario 6 (R8): a DID method that can never authenticate is refused
|
||||
/// in the 400 validation class, with nothing written. This one IS about the
|
||||
/// input's form, not the caller's authority, which is why it is not a 403.
|
||||
#[sqlx::test]
|
||||
async fn announce_of_a_did_web_is_a_400_validation_failure(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(WEB_DID, OWNER_URL),
|
||||
"203.0.113.93:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::BAD_REQUEST,
|
||||
"an unsupported DID method is a validation failure: {message}"
|
||||
);
|
||||
assert_eq!(code, "bad_request");
|
||||
assert!(
|
||||
message.contains("methodNotSupported"),
|
||||
"the rejection must carry the methodNotSupported shape, got {message:?}"
|
||||
);
|
||||
assert!(
|
||||
snapshot(&state.db, WEB_DID).await.is_none(),
|
||||
"a rejected announce must leave no row behind"
|
||||
);
|
||||
}
|
||||
|
||||
/// The sibling of the case above, and the one it must not swallow: the
|
||||
/// method IS did:key, so methodNotSupported would be a false statement
|
||||
/// about the input. The value is the W3C secp256k1 did:key test vector,
|
||||
/// which decodes cleanly and is simply not an ed25519 key. Still the 400
|
||||
/// validation class, still nothing written.
|
||||
#[sqlx::test]
|
||||
async fn announce_of_an_unresolvable_did_key_is_a_400_with_the_cause(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let did = "did:key:zQ3shokFTS3brHcDQrn82RUDfCZESWL1ZdCEJwekUDPQiYBme";
|
||||
|
||||
let resp = announce_only(state.clone())
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(did, OWNER_URL),
|
||||
"203.0.113.99:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::BAD_REQUEST,
|
||||
"an unresolvable did:key is a validation failure: {message}"
|
||||
);
|
||||
assert_eq!(
|
||||
code, "unresolvable_did",
|
||||
"the code must name the cause, the same way the signed path does for a keyid it \
|
||||
cannot resolve; a client distinguishing this from the other 400s on this route \
|
||||
must not have to substring-match the message: {message:?}"
|
||||
);
|
||||
assert!(
|
||||
message.contains("cannot resolve DID"),
|
||||
"the rejection must report resolution, not method support, got {message:?}"
|
||||
);
|
||||
assert!(
|
||||
snapshot(&state.db, did).await.is_none(),
|
||||
"a rejected announce must leave no row behind"
|
||||
);
|
||||
}
|
||||
|
||||
// ── U5: the same matrix through the production router, real signatures ────
|
||||
|
||||
/// An announce carrying a REAL RFC 9421 signature, signed AS `kp` while the
|
||||
/// body names whatever DID the caller chooses. That split is the point: it
|
||||
/// is what lets a valid signature be pointed at a row it does not own,
|
||||
/// which is the RUSTSEC-2022-0009 shape.
|
||||
fn real_signed_announce(kp: &Keypair, body: &str, peer: &str) -> Request<Body> {
|
||||
let path = "/api/v1/peers/announce";
|
||||
let s = sign_request(kp, "POST", path, body.as_bytes());
|
||||
let mut req = Request::builder()
|
||||
.method(Method::POST)
|
||||
.uri(path)
|
||||
.header(header::CONTENT_TYPE, "application/json")
|
||||
.header("content-digest", s.content_digest)
|
||||
.header("signature-input", s.signature_input)
|
||||
.header("signature", s.signature)
|
||||
.body(Body::from(body.to_string()))
|
||||
.unwrap();
|
||||
req.extensions_mut()
|
||||
.insert(ConnectInfo(peer.parse::<SocketAddr>().unwrap()));
|
||||
req
|
||||
}
|
||||
|
||||
/// U5 scenario 1: the lowest-privilege caller there is, fully
|
||||
/// unauthenticated, still seeds an unseen did:key row through the whole
|
||||
/// production stack.
|
||||
#[sqlx::test]
|
||||
async fn router_unsigned_announce_inserts_an_unseen_did(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(&did, OWNER_URL),
|
||||
"203.0.113.94:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
let row = snapshot(&db, &did).await.expect("row not inserted");
|
||||
assert_eq!(row.1, OWNER_URL);
|
||||
}
|
||||
|
||||
/// U5 scenario 2: the defect this change closes, driven end to end. An
|
||||
/// unsigned repoint is refused with its reason and the row does not move.
|
||||
/// Kills reverting the unproven arm to an unconditional DO UPDATE.
|
||||
#[sqlx::test]
|
||||
async fn router_unsigned_announce_cannot_repoint_an_existing_row(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let victim = Keypair::generate().did().to_string();
|
||||
let before = seed_peer_row(&state, &victim, OWNER_URL).await;
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(&victim, HIJACK_URL),
|
||||
"203.0.113.95:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// The row assertion leads: the property is that the row does not move.
|
||||
// A response-class regression is a second, separate failure below.
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
snapshot(&db, &victim).await.expect("row vanished"),
|
||||
before,
|
||||
"the stored row must be byte-identical after a refused unsigned repoint \
|
||||
(observed status {status})"
|
||||
);
|
||||
assert_eq!(status, StatusCode::FORBIDDEN, "observed body: {message}");
|
||||
assert_eq!(code, "forbidden");
|
||||
}
|
||||
|
||||
/// U5 scenario 3: the allowed signed case through the real verification
|
||||
/// middleware. The row was seeded under this keypair's own did:key, so the
|
||||
/// signature names the row it moves.
|
||||
#[sqlx::test]
|
||||
async fn router_signature_from_the_rows_own_did_repoints_it(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let owner = Keypair::generate();
|
||||
let owner_did = owner.did().to_string();
|
||||
seed_peer_row(&state, &owner_did, OWNER_URL).await;
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(real_signed_announce(
|
||||
&owner,
|
||||
&announce_body(&owner_did, MOVED_URL),
|
||||
"203.0.113.96:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"a real signature from the row's own DID must be admitted"
|
||||
);
|
||||
let row = snapshot(&db, &owner_did).await.expect("row vanished");
|
||||
assert_eq!(row.1, MOVED_URL, "a proven repoint must land");
|
||||
assert!(
|
||||
!row.3,
|
||||
"a repointed peer must re-earn reachability even when the repoint is signed"
|
||||
);
|
||||
}
|
||||
|
||||
/// U5 scenario 4, the RUSTSEC-2022-0009 shape: a signature that verifies
|
||||
/// perfectly, spent on a row it does not own. The key must be bound to the
|
||||
/// ROW, not to anything the request carries. The assertion names the keyid
|
||||
/// denial specifically, because the boundary's own DID comparison would
|
||||
/// also refuse this write, so a status-only assertion would stay green with
|
||||
/// the handler branch neutralized.
|
||||
#[sqlx::test]
|
||||
async fn router_signature_from_another_did_cannot_repoint_this_row(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let victim = Keypair::generate().did().to_string();
|
||||
let hijacker = Keypair::generate();
|
||||
let before = seed_peer_row(&state, &victim, OWNER_URL).await;
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(real_signed_announce(
|
||||
&hijacker,
|
||||
&announce_body(&victim, HIJACK_URL),
|
||||
"203.0.113.97:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::FORBIDDEN,
|
||||
"a valid signature over another DID's row must be refused: {message}"
|
||||
);
|
||||
assert_eq!(code, "forbidden");
|
||||
assert!(
|
||||
message.contains(KEYID_MISMATCH),
|
||||
"the denial must name the keyid mismatch, got {message:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
snapshot(&db, &victim).await.expect("row vanished"),
|
||||
before,
|
||||
"the stored row must be byte-identical after a mismatched signature"
|
||||
);
|
||||
}
|
||||
|
||||
/// U5 scenario 5: an honest unsigned peer re-announcing the identical URL
|
||||
/// through the full stack refreshes last_seen and moves nothing else. The
|
||||
/// seeded string is reused byte for byte, since the comparison is exact.
|
||||
#[sqlx::test]
|
||||
async fn router_unsigned_identical_url_reannounce_refreshes_last_seen(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let before = seed_peer_row(&state, &did, OWNER_URL).await;
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(&did, OWNER_URL),
|
||||
"203.0.113.98:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
let after = snapshot(&db, &did).await.expect("row vanished");
|
||||
assert_eq!(after.1, OWNER_URL, "URL untouched");
|
||||
assert_eq!(after.3, before.3, "reachability untouched");
|
||||
assert_eq!(after.4, before.4, "announced_at untouched");
|
||||
let parse = |s: &Option<String>| {
|
||||
chrono::DateTime::parse_from_rfc3339(s.as_deref().expect("last_seen is set")).unwrap()
|
||||
};
|
||||
assert!(
|
||||
parse(&after.2) > parse(&before.2),
|
||||
"a same-URL re-announce must advance last_seen"
|
||||
);
|
||||
}
|
||||
|
||||
/// U5 scenario 6 (R8) through the full stack: a did:web announce is refused
|
||||
/// in the validation class and writes nothing. Such a row could never be
|
||||
/// corrected by anyone, since only a did:key can ever satisfy the proven
|
||||
/// path. Kills neutralizing the method gate on the unproven arm.
|
||||
#[sqlx::test]
|
||||
async fn router_unsigned_announce_of_a_did_web_is_refused(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let db = state.db.clone();
|
||||
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(WEB_DID, OWNER_URL),
|
||||
"203.0.113.99:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let (status, code, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::BAD_REQUEST,
|
||||
"an unsupported DID method must be refused: {message}"
|
||||
);
|
||||
assert_eq!(code, "bad_request");
|
||||
assert!(
|
||||
message.contains("methodNotSupported"),
|
||||
"the rejection must carry the methodNotSupported shape, got {message:?}"
|
||||
);
|
||||
assert!(
|
||||
snapshot(&db, WEB_DID).await.is_none(),
|
||||
"a rejected announce must leave no row behind"
|
||||
);
|
||||
}
|
||||
|
||||
/// U5, flag-on mode: with require_signed_peer_writes the write group moves
|
||||
/// under add_auth_layers, so the unsigned caller dies at the auth layer with
|
||||
/// a 401 instead of reaching the handler's 403. The authority rules
|
||||
/// themselves do not change: a signature over another DID's row is still
|
||||
/// refused, and the row's own key still moves it. The flag is applied BEFORE
|
||||
/// build_router, which reads it at build time.
|
||||
#[sqlx::test]
|
||||
async fn announce_authority_matrix_in_signed_writes_mode(pool: PgPool) {
|
||||
let mut state = test_state(pool).await;
|
||||
require_signed_peer_writes(&mut state);
|
||||
let owner = Keypair::generate();
|
||||
let owner_did = owner.did().to_string();
|
||||
let hijacker = Keypair::generate();
|
||||
let before = seed_peer_row(&state, &owner_did, OWNER_URL).await;
|
||||
let db = state.db.clone();
|
||||
let router = crate::server::build_router(state);
|
||||
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce_body(&owner_did, HIJACK_URL),
|
||||
"203.0.113.100:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::UNAUTHORIZED,
|
||||
"with the flag on, an unsigned announce dies at the auth layer"
|
||||
);
|
||||
assert_eq!(
|
||||
snapshot(&db, &owner_did).await.expect("row vanished"),
|
||||
before,
|
||||
"the row must be byte-identical after the 401"
|
||||
);
|
||||
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(real_signed_announce(
|
||||
&hijacker,
|
||||
&announce_body(&owner_did, HIJACK_URL),
|
||||
"203.0.113.101:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
let (status, _, message) = status_and_error(resp).await;
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::FORBIDDEN,
|
||||
"a signature over another DID's row is still refused: {message}"
|
||||
);
|
||||
assert!(message.contains(KEYID_MISMATCH), "got {message:?}");
|
||||
assert_eq!(
|
||||
snapshot(&db, &owner_did).await.expect("row vanished"),
|
||||
before,
|
||||
"the row must be byte-identical after the mismatched signature"
|
||||
);
|
||||
|
||||
let resp = router
|
||||
.oneshot(real_signed_announce(
|
||||
&owner,
|
||||
&announce_body(&owner_did, MOVED_URL),
|
||||
"203.0.113.102:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"the row's own key still moves it with the flag on"
|
||||
);
|
||||
assert_eq!(
|
||||
snapshot(&db, &owner_did).await.expect("row vanished").1,
|
||||
MOVED_URL
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -213,7 +213,7 @@ pub async fn merge_pr(
|
||||
.repo_store
|
||||
.acquire_write(&record.owner_did, &record.name)
|
||||
.await
|
||||
.map_err(|e| crate::api::repos::acquire_write_app_error(&e, &name))?;
|
||||
.map_err(|e| AppError::Git(e.to_string()))?;
|
||||
let disk_path = guard.path().to_path_buf();
|
||||
let merger_did = auth.0;
|
||||
let merge_result = store::merge_branch(
|
||||
@@ -225,10 +225,7 @@ pub async fn merge_pr(
|
||||
);
|
||||
|
||||
// Always release the advisory lock — even on error; upload to Tigris only on success.
|
||||
// Short-circuit on a refused publish before the PR is marked merged and
|
||||
// before the webhook fires. Both are irreversible announcements of a merge
|
||||
// commit that only exists on this node's disk.
|
||||
guard.release(merge_result.is_ok()).await.into_result()?;
|
||||
guard.release(merge_result.is_ok()).await;
|
||||
|
||||
let merge_sha = merge_result.map_err(|e| AppError::Git(e.to_string()))?;
|
||||
|
||||
@@ -427,105 +424,3 @@ pub async fn list_comments(
|
||||
let comments = state.db.list_pr_comments(&pr.id).await?;
|
||||
Ok(Json(serde_json::json!({ "comments": comments })))
|
||||
}
|
||||
|
||||
/// #173 F1 follow-up: merge holds no admission permit, so an exhausted write-lock
|
||||
/// pool must shed 503 + Retry-After.
|
||||
#[cfg(test)]
|
||||
mod lock_pool_shed_tests {
|
||||
use super::*;
|
||||
use axum::response::IntoResponse;
|
||||
use sqlx::PgPool;
|
||||
|
||||
fn seed_repo(owner_did: &str, name: &str) -> crate::db::RepoRecord {
|
||||
let now = Utc::now();
|
||||
crate::db::RepoRecord {
|
||||
id: Uuid::new_v4().to_string(),
|
||||
name: name.to_string(),
|
||||
owner_did: owner_did.to_string(),
|
||||
description: None,
|
||||
is_public: true,
|
||||
default_branch: "main".to_string(),
|
||||
created_at: now,
|
||||
updated_at: now,
|
||||
disk_path: format!("/tmp/{name}"),
|
||||
forked_from: None,
|
||||
machine_id: None,
|
||||
}
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn merge_pr_lock_pool_exhaustion_sheds_503_not_500(pool: PgPool) {
|
||||
let owner = "did:key:zMERGELOCKPOOLOWNERAAAAAAAAAAAAAAAAAAAAA";
|
||||
let mut state = crate::test_support::test_state(pool.clone()).await;
|
||||
state.repo_store = crate::git::repo_store::RepoStore::new(
|
||||
std::path::PathBuf::from("/tmp/gitlawb-pulls-lockpool"),
|
||||
None,
|
||||
crate::git::repo_store::build_lock_pool(&pool, 1, std::time::Duration::from_secs(1)),
|
||||
std::time::Duration::from_secs(300),
|
||||
);
|
||||
|
||||
let repo = seed_repo(owner, "lp-merge");
|
||||
let repo_id = repo.id.clone();
|
||||
state.db.create_repo(&repo).await.expect("seed repo");
|
||||
let now = Utc::now().to_rfc3339();
|
||||
state
|
||||
.db
|
||||
.create_pr(&PullRequest {
|
||||
id: Uuid::new_v4().to_string(),
|
||||
repo_id: repo_id.clone(),
|
||||
number: 1,
|
||||
title: "lp".to_string(),
|
||||
body: None,
|
||||
author_did: owner.to_string(),
|
||||
source_branch: "feature".to_string(),
|
||||
target_branch: "main".to_string(),
|
||||
status: "open".to_string(),
|
||||
merged_by_did: None,
|
||||
merged_at: None,
|
||||
created_at: now.clone(),
|
||||
updated_at: now,
|
||||
})
|
||||
.await
|
||||
.expect("seed open PR");
|
||||
|
||||
let held = state
|
||||
.repo_store
|
||||
.acquire_write(owner, "other-repo")
|
||||
.await
|
||||
.expect("the first write takes the only lock-pool connection");
|
||||
|
||||
let shed = merge_pr(
|
||||
State(state.clone()),
|
||||
Extension(AuthenticatedDid(owner.to_string())),
|
||||
Path((owner.to_string(), "lp-merge".to_string(), 1)),
|
||||
)
|
||||
.await;
|
||||
let err = shed.expect_err("an exhausted lock pool must fail the call");
|
||||
let resp = err.into_response();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"merge_pr: an exhausted write-lock pool must shed 503, not a 500 git error"
|
||||
);
|
||||
assert_eq!(
|
||||
resp.headers()
|
||||
.get("retry-after")
|
||||
.map(|v| v.to_str().unwrap()),
|
||||
Some("1"),
|
||||
"merge_pr: a capacity shed must tell the client when to retry"
|
||||
);
|
||||
|
||||
let _ = held.release(false).await;
|
||||
let admitted = merge_pr(
|
||||
State(state.clone()),
|
||||
Extension(AuthenticatedDid(owner.to_string())),
|
||||
Path((owner.to_string(), "lp-merge".to_string(), 1)),
|
||||
)
|
||||
.await;
|
||||
assert!(
|
||||
!matches!(admitted, Err(AppError::Overloaded(_))),
|
||||
"with the lock pool free, merge_pr must not be shed as capacity; got {:?}",
|
||||
admitted.err()
|
||||
);
|
||||
}
|
||||
}
|
||||
+107
-1562
File diff suppressed because it is too large.
Load diff
@@ -490,7 +490,6 @@ mod tests {
|
||||
use clap::Parser;
|
||||
|
||||
let keypair = Keypair::generate();
|
||||
let scan_token_key = crate::state::AppState::derive_scan_token_key(&keypair);
|
||||
let (ref_tx, _) = tokio::sync::broadcast::channel(1);
|
||||
let (task_tx, _) = tokio::sync::broadcast::channel(1);
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
@@ -517,17 +516,6 @@ mod tests {
|
||||
rate_limiter: RateLimiter::new(100, Duration::from_secs(60)),
|
||||
create_ip_rate_limiter: RateLimiter::new(1000, Duration::from_secs(3600)),
|
||||
push_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
close_issue_rate_limiter: RateLimiter::new(120, Duration::from_secs(3600)),
|
||||
ipfs_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
ipfs_work_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
ipfs_max_history_walks: crate::api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST,
|
||||
ipfs_max_legacy_probes: crate::api::ipfs::MAX_LEGACY_PROBES_PER_REQUEST,
|
||||
ipfs_legacy_scan_page_rows: crate::api::ipfs::LEGACY_SCAN_PAGE_ROWS,
|
||||
ipfs_max_legacy_scan_rows: crate::api::ipfs::MAX_LEGACY_SCAN_ROWS_PER_REQUEST,
|
||||
ipfs_max_legacy_scan_rule_bytes:
|
||||
crate::api::ipfs::MAX_LEGACY_SCAN_RULE_BYTES_PER_REQUEST,
|
||||
ipfs_scan_token_key: Arc::new(scan_token_key),
|
||||
ipfs_max_served_object_bytes: crate::api::ipfs::MAX_SERVED_OBJECT_BYTES,
|
||||
push_limiter_trust: crate::rate_limit::TrustedProxy::None,
|
||||
sync_trigger_rate_limiter: RateLimiter::new(60, Duration::from_secs(3600)),
|
||||
peer_write_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
@@ -546,6 +534,7 @@ mod tests {
|
||||
git_ipfs_walk_semaphore: Arc::new(tokio::sync::Semaphore::new(64)),
|
||||
git_ipfs_walk_per_caller:
|
||||
crate::rate_limit::PerCallerConcurrency::with_default_max_keys(16),
|
||||
ipfs_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
git_bin: "git".to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
use clap::Parser;
|
||||
use std::path::PathBuf;
|
||||
|
||||
/// Upper bound on `git_service_timeout_secs`, `ipfs_request_budget_secs`, and
|
||||
/// `ipfs_resolve_budget_secs`, in seconds (100 years).
|
||||
/// Upper bound on `git_service_timeout_secs` and `ipfs_request_budget_secs`, in seconds
|
||||
/// (100 years).
|
||||
///
|
||||
/// Three consumers now, so a future tightening moves all of them. `ipfs_request_budget_secs`
|
||||
/// and `ipfs_resolve_budget_secs` derive only the `Instant` addition in `get_by_cid`, not the
|
||||
/// lease-steal multiply below, but they share this ceiling because the defect class and the
|
||||
/// "set it very large to disable" contract are the same.
|
||||
/// Two consumers now, so a future tightening moves both. `ipfs_request_budget_secs`
|
||||
/// derives only the `Instant` addition in `get_by_cid`, not the lease-steal multiply
|
||||
/// below, but it shares this ceiling because the defect class and the "set it very large
|
||||
/// to disable" contract are the same.
|
||||
///
|
||||
/// The knob is not just stored, it is arithmetic input: the write path derives the
|
||||
/// per-repo lease steal bound from it (`* 2 + 60`), and #174 routed it into
|
||||
@@ -78,26 +78,10 @@ pub struct Config {
|
||||
|
||||
/// Require the authenticated pusher to be the repo owner on `git-receive-pack`.
|
||||
/// Authentication (a valid did:key signature) is not authorization on its own:
|
||||
/// any party can mint a did:key and sign as it, so with this off every signed
|
||||
/// caller may push to every repository, private ones included. On by default.
|
||||
///
|
||||
/// Turn it off only for a rolling upgrade whose pushers are not yet the repo
|
||||
/// owner. Both `GITLAWB_ENFORCE_OWNER_PUSH=false` and `--enforce-owner-push
|
||||
/// false` disable it, and the bare `--enforce-owner-push` form still means
|
||||
/// `true`.
|
||||
///
|
||||
/// The value-taking action is what makes the CLI form parse at all: as a
|
||||
/// presence-only flag, `--enforce-owner-push false` is an "unexpected argument"
|
||||
/// error. The env form resolved correctly either way, so it is the CLI escape
|
||||
/// hatch this buys, not the environment one.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_ENFORCE_OWNER_PUSH",
|
||||
action = clap::ArgAction::Set,
|
||||
num_args = 0..=1,
|
||||
default_value_t = true,
|
||||
default_missing_value = "true"
|
||||
)]
|
||||
/// any party can sign as their own DID. When true, pushes whose authenticated
|
||||
/// DID is not the repo owner are rejected. Keep false during rolling upgrades;
|
||||
/// flip it on once owners are ready for owner-only writes.
|
||||
#[arg(long, env = "GITLAWB_ENFORCE_OWNER_PUSH", default_value_t = false)]
|
||||
pub enforce_owner_push: bool,
|
||||
|
||||
/// URL of local IPFS/Kubo node HTTP API (e.g. http://127.0.0.1:5001)
|
||||
@@ -252,9 +236,11 @@ pub struct Config {
|
||||
|
||||
/// Maximum connections in the PostgreSQL pool. This is a cap, not a floor
|
||||
/// (connections open lazily). Size against the database server's
|
||||
/// max_connections, remembering admin tooling opens its own pool. Writes pin
|
||||
/// the dedicated lock pool, not this one; this pool still needs enough headroom
|
||||
/// for ordinary request handlers and metadata paths (`DB_POOL_APP_HEADROOM`).
|
||||
/// max_connections, remembering admin tooling opens its own pool. Each
|
||||
/// concurrent write pins one pooled connection for its whole duration (the
|
||||
/// advisory lock in `repo_store::acquire_write` is connection-affine), so this
|
||||
/// must exceed `max_concurrent_git_pushes` by `DB_POOL_APP_HEADROOM` or slow
|
||||
/// pushes starve every other DB path — enforced by `Config::validate`.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_MAX_CONNECTIONS",
|
||||
@@ -263,46 +249,6 @@ pub struct Config {
|
||||
)]
|
||||
pub db_max_connections: u32,
|
||||
|
||||
/// Maximum connections in the dedicated advisory-lock pool, which is separate
|
||||
/// from the main pool above.
|
||||
///
|
||||
/// Size this against the expected peak number of concurrent distinct-repo
|
||||
/// writers, NOT small. Every in-flight repo write pins one connection here for
|
||||
/// its whole duration (the write, its metadata tail, and the bounded archive
|
||||
/// upload), so this value is a hard ceiling on simultaneous writes node-wide.
|
||||
/// Keeping it separate from GITLAWB_DB_MAX_CONNECTIONS is what stops a push
|
||||
/// burst from starving ordinary request handlers; the cost is that
|
||||
/// (main pool + lock pool) must fit inside the database server's
|
||||
/// max_connections, times the number of nodes, plus admin tooling.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_LOCK_POOL_MAX_CONNECTIONS",
|
||||
default_value_t = 40,
|
||||
value_parser = clap::value_parser!(u32).range(1..)
|
||||
)]
|
||||
pub db_lock_pool_max_connections: u32,
|
||||
|
||||
/// Upper bound, in seconds, on any single object-storage transfer that runs
|
||||
/// while the per-repo advisory lock is HELD.
|
||||
///
|
||||
/// Two bounded spans exist, and the bound applies per span. The acquire-side
|
||||
/// refresh in `acquire_write` covers the existence HEAD and the download
|
||||
/// together under ONE budget (it runs after the lock is taken and before the
|
||||
/// guard is constructed), and the archive upload in `release` gets its own.
|
||||
/// Worst-case slot occupancy is therefore about twice this value plus the git
|
||||
/// work between them, not one times this value. Both used to be free, because the lock's
|
||||
/// connection was returned to the pool immediately; now that a write guard
|
||||
/// pins a lock-pool connection for its whole lifetime, an unbounded transfer
|
||||
/// holds that slot, and enough stalled transfers deny every write on the node.
|
||||
/// This is the bound that keeps a stall from becoming an outage.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_LOCK_HELD_TRANSFER_TIMEOUT_SECS",
|
||||
default_value_t = 300,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub lock_held_transfer_timeout_secs: u64,
|
||||
|
||||
/// Maximum time a request waits for a pool connection before failing with
|
||||
/// 503, in seconds. Bounds queueing when the database is slow or down.
|
||||
#[arg(
|
||||
@@ -395,16 +341,6 @@ pub struct Config {
|
||||
/// Default: 32. Must be between 1 and 1_048_576 (the ceiling keeps the value
|
||||
/// under tokio's `Semaphore` permit limit so an oversized value is a clean CLI
|
||||
/// error rather than a boot-time panic).
|
||||
///
|
||||
/// CONNECTION BUDGET. A push holds a Postgres connection from the node's separate
|
||||
/// advisory-lock pool (`GITLAWB_DB_LOCK_POOL_MAX_CONNECTIONS`, default 40) for
|
||||
/// the whole receive-pack. That pool must be at least this value plus
|
||||
/// `DB_LOCK_POOL_NON_PUSH_HEADROOM` so admitted pushes and non-push mutations
|
||||
/// can each pin a lock-pool connection for their whole duration. Size BOTH
|
||||
/// pools against the database server's `max_connections`: the main pool
|
||||
/// (`GITLAWB_DB_MAX_CONNECTIONS`, default 48) serves ordinary handlers, and the
|
||||
/// lock pool serves writes. Raising this knob does not raise the lock pool;
|
||||
/// set `GITLAWB_DB_LOCK_POOL_MAX_CONNECTIONS` explicitly.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_MAX_CONCURRENT_GIT_PUSHES",
|
||||
@@ -516,54 +452,6 @@ pub struct Config {
|
||||
)]
|
||||
pub ipfs_walk_per_source: usize,
|
||||
|
||||
/// Per-request ceiling on the number of legacy (NULL-provenance) repos the
|
||||
/// `/ipfs/{cid}` resolver's scan fallback will PROBE (`acquire` + `git cat-file
|
||||
/// -t`) before giving up. The provenance path targets its recorded sources; the
|
||||
/// legacy scan, absent this bound, fans one anonymous request out to O(repos)
|
||||
/// subprocess spawns and cold-cache fetches for a CID enumerable from the public
|
||||
/// pins index. A truncated scan surfaces as a retryable 503, never a false 404.
|
||||
/// Wired into `AppState::ipfs_max_legacy_probes` at construction. This knob does
|
||||
/// not govern the history-walk ceiling; see `ipfs_max_repos_walked` for that.
|
||||
/// Must be between 1 and 1_048_576. Default: 256.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_IPFS_MAX_LEGACY_PROBES",
|
||||
default_value_t = crate::api::ipfs::MAX_LEGACY_PROBES_PER_REQUEST as usize,
|
||||
value_parser = clap::builder::RangedU64ValueParser::<usize>::new().range(1..=1_048_576)
|
||||
)]
|
||||
pub ipfs_max_legacy_probes: usize,
|
||||
|
||||
/// Per-request ceiling on how many repo ROWS the `/ipfs/{cid}` resolver's legacy
|
||||
/// scan may fetch from the database. The probe ceiling above only starts counting
|
||||
/// once a probe runs, and the two denial classes that dominate a hostile inventory
|
||||
/// (quarantine, and a root-scope visibility deny) return before a probe or a visit
|
||||
/// is spent, so without this an all-denying node paged its ENTIRE repo table for one
|
||||
/// anonymous request while holding a scarce walk permit.
|
||||
///
|
||||
/// Reach bound: a holder buried past the ceiling is servable in
|
||||
/// `ceil(repos / ceiling) + 1` token-echoing retries. A truncated scan sheds a
|
||||
/// retryable 503 carrying a sealed continuation token; the caller echoes it as
|
||||
/// `?scan=` and the scan resumes where it stopped. No server-side scan state.
|
||||
///
|
||||
/// Floor coupling: raising this knob raises every caller's per-window `/ipfs` work
|
||||
/// allowance whenever the route limit sits below the derived floor, because the
|
||||
/// floor must fit one full deep scan's page toll (see `AppState::ipfs_work_budget`).
|
||||
///
|
||||
/// Tuning DOWN trade: token presence is a coarse inventory-size oracle. A ceiling
|
||||
/// truncation emits a token and a wrapped scan does not, so laddering to the
|
||||
/// `scan-wrapped` taint tells an anonymous caller the node's total repo count,
|
||||
/// private and quarantined included, to within one ceiling. Tolled and coarse at
|
||||
/// the 2048 default; it sharpens as the ceiling is lowered.
|
||||
///
|
||||
/// Must be between 1 and 1_048_576. Default: 2048.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_IPFS_MAX_LEGACY_SCAN_ROWS",
|
||||
default_value_t = crate::api::ipfs::MAX_LEGACY_SCAN_ROWS_PER_REQUEST,
|
||||
value_parser = clap::builder::RangedU64ValueParser::<usize>::new().range(1..=1_048_576)
|
||||
)]
|
||||
pub ipfs_max_legacy_scan_rows: usize,
|
||||
|
||||
/// Upper bound on the number of EXPENSIVE visibility walks
|
||||
/// (`allowed_blob_set_for_caller_bounded`, a full-history git walk in a
|
||||
/// blocking thread) a single `/ipfs/{cid}` request may run. Only a blob in a
|
||||
@@ -575,22 +463,6 @@ pub struct Config {
|
||||
/// sheds a retryable 503 + Retry-After rather than misreport existing content
|
||||
/// absent with a 404. The handler still short-circuits the moment it serves.
|
||||
/// Must be between 1 and 1_048_576. Default: 64.
|
||||
///
|
||||
/// The effective ceiling is the TIGHTER of this knob and the node's internal
|
||||
/// history-walk ceiling, `MAX_PIN_SOURCES + 1` = 17 (see
|
||||
/// `api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST` and the `min()` that combines the
|
||||
/// two in the resolver). Setting this above 17 changes nothing, because the
|
||||
/// internal ceiling already binds. Setting it below 17 does lower the cap: the
|
||||
/// constant side of the `min()` is what keeps a request from being truncated
|
||||
/// before its whole bounded provenance source set has been tried, so an operator
|
||||
/// who goes under it is choosing a tighter cap that can 503 a provenanced
|
||||
/// request, which is allowed.
|
||||
///
|
||||
/// That combined cap is charged PER PHASE, not per request: the provenance phase and
|
||||
/// the legacy-scan fallback each get their own equal budget, so one request can run
|
||||
/// up to twice it in total (see `MAX_HISTORY_WALKS_PER_REQUEST`, which explains why
|
||||
/// the split is what keeps the fallback from inheriting a provenance phase's spent
|
||||
/// remainder).
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_IPFS_MAX_REPOS_WALKED",
|
||||
@@ -659,86 +531,14 @@ pub struct Config {
|
||||
)]
|
||||
pub ipfs_request_budget_secs: u64,
|
||||
|
||||
/// Budget for the PRE-WALK CID resolve inside `get_by_cid`, in seconds: the
|
||||
/// `oids_for_cid` lookup that maps the requested CID to its git oid(s), which runs
|
||||
/// while the scarce walk admission (the global pool permit plus the per-source
|
||||
/// sub-permit) is already held.
|
||||
///
|
||||
/// It exists because that one await decides whether the request does any admitted
|
||||
/// work at all. A syntactically valid CID with no `pinned_cids` row runs zero probes
|
||||
/// and zero walks, so under a stalled or saturated pool it would otherwise occupy a
|
||||
/// walk slot for the whole `ipfs_request_budget_secs` window (600s by default) while
|
||||
/// nothing is walking, and enough distinct source keys doing that reject every real
|
||||
/// `/ipfs` retrieval at admission. The other repair, resolving the CID before taking
|
||||
/// admission, was rejected: admission stays FIRST so an anonymous flood sheds before
|
||||
/// touching the database at all, and moving the read ahead of it would let arbitrarily
|
||||
/// many unadmitted permissionless callers stack concurrent DB queries.
|
||||
///
|
||||
/// The effective deadline is the lesser of this and the remaining request budget, so a
|
||||
/// value larger than `ipfs_request_budget_secs` degrades to the request budget rather
|
||||
/// than extending it. Only the resolve is on this clock; every later stage stays on the
|
||||
/// full request budget, because from the second oid candidate on those run after real
|
||||
/// probe and walk work and a short deadline anchored at admission would shed a
|
||||
/// legitimately slow but progressing scan.
|
||||
///
|
||||
/// Must be positive, and no larger than `GIT_SERVICE_TIMEOUT_SECS_MAX`, for the same
|
||||
/// representability reason as the request budget above: `get_by_cid` derives the
|
||||
/// resolve deadline as `Instant::now() + Duration::from_secs(this)`, and that addition
|
||||
/// panics on overflow in release builds too. Default: 10s.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_IPFS_RESOLVE_BUDGET_SECS",
|
||||
default_value_t = 10,
|
||||
value_parser = clap::value_parser!(u64).range(1..=GIT_SERVICE_TIMEOUT_SECS_MAX)
|
||||
)]
|
||||
pub ipfs_resolve_budget_secs: u64,
|
||||
|
||||
/// Per-client-IP rate limit for `GET /ipfs/{cid}`, in requests per hour. The
|
||||
/// route is publicly reachable (`optional_signature`) and each request can drive
|
||||
/// a full-history git walk, so it carries a per-IP flood brake in addition to the
|
||||
/// concurrency cap above (a rate limit bounds request *rate*, the semaphore
|
||||
/// bounds concurrent slow holds — different axes). Keyed on the resolved client
|
||||
/// IP via `GITLAWB_TRUSTED_PROXY`. `0` disables. Default: 600.
|
||||
///
|
||||
/// This is the pure once-per-request ROUTE brake. The resolver's internal
|
||||
/// per-probe/per-walk WORK budget is a SEPARATE bucket whose capacity is DERIVED
|
||||
/// from this value (`AppState::ipfs_work_budget`), not a knob of its own; `0` here
|
||||
/// disables that derived bucket too.
|
||||
#[arg(long, env = "GITLAWB_IPFS_RATE_LIMIT", default_value_t = 600)]
|
||||
pub ipfs_rate_limit: usize,
|
||||
|
||||
/// Rows the legacy provider-CID repair sweep reads per batch (U4, #173).
|
||||
///
|
||||
/// The sweep walks every `pinned_cids` row on the node once, repairing rows that
|
||||
/// releases before this branch keyed on a PROVIDER CID (Kubo dag-pb / Pinata CIDv0)
|
||||
/// instead of the raw-content resolver key. This bounds one batch, so the sweep can
|
||||
/// never turn into a single unbounded table scan competing with request traffic.
|
||||
/// Conservative on purpose: paired with the inter-batch delay below the default is
|
||||
/// ~64 rows per minute, which finishes a large pin set in hours of idle background
|
||||
/// work rather than one expensive burst. Must be between 1 and 100_000.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_PIN_REPAIR_SWEEP_BATCH",
|
||||
default_value_t = 64,
|
||||
value_parser = clap::builder::RangedU64ValueParser::<i64>::new().range(1..=100_000)
|
||||
)]
|
||||
pub pin_repair_sweep_batch: i64,
|
||||
|
||||
/// Seconds the legacy provider-CID repair sweep sleeps between batches (U4, #173).
|
||||
///
|
||||
/// Each batch costs an indexed range scan plus, for the legacy rows in it, a
|
||||
/// `git cat-file` per row. The delay is what keeps that off the DB's and the disk's
|
||||
/// critical path: the sweep is repairing rows that have been unresolvable since the
|
||||
/// upgrade, so finishing slowly is fine and finishing fast at the cost of live
|
||||
/// traffic is not. `0` disables the pause (test and one-off operational use only).
|
||||
/// Must be between 0 and 86_400.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_PIN_REPAIR_SWEEP_DELAY_SECS",
|
||||
default_value_t = 60,
|
||||
value_parser = clap::builder::RangedU64ValueParser::<u64>::new().range(0..=86_400)
|
||||
)]
|
||||
pub pin_repair_sweep_delay_secs: u64,
|
||||
}
|
||||
|
||||
impl Config {
|
||||
@@ -762,37 +562,25 @@ impl Config {
|
||||
/// the pool must clear the concurrent-write cap by at least this margin.
|
||||
pub const DB_POOL_APP_HEADROOM: u32 = 8;
|
||||
|
||||
/// Lock-pool slots reserved for non-push `acquire_write` callers (issue create,
|
||||
/// close, merge) so a saturated push budget cannot turn ordinary mutations into
|
||||
/// lock-pool exhaustion on unrelated repositories.
|
||||
pub const DB_LOCK_POOL_NON_PUSH_HEADROOM: u32 = 8;
|
||||
|
||||
/// Cross-field boot validation. Single-field ranges are enforced by clap; this
|
||||
/// catches combinations that ship a denial-of-service under otherwise-valid
|
||||
/// values. Call once at startup and fail fast on `Err`.
|
||||
pub fn validate(&self) -> Result<(), String> {
|
||||
// Concurrent git writes pin the dedicated lock pool for their whole
|
||||
// duration (connection-affine advisory lock in acquire_write). The main
|
||||
// pool no longer carries that occupancy.
|
||||
let lock_floor = self
|
||||
.max_concurrent_git_pushes
|
||||
.saturating_add(Self::DB_LOCK_POOL_NON_PUSH_HEADROOM as usize);
|
||||
if (self.db_lock_pool_max_connections as usize) < lock_floor {
|
||||
// A write pins one pooled connection for its whole duration (the
|
||||
// connection-affine advisory lock in repo_store::acquire_write), and
|
||||
// concurrent writes are capped at max_concurrent_git_pushes. If the pool
|
||||
// does not exceed that cap by DB_POOL_APP_HEADROOM, a burst of slow pushes
|
||||
// drains every connection and every other DB path 503s. (#174 F1)
|
||||
let floor = (self.max_concurrent_git_pushes as u64) + (Self::DB_POOL_APP_HEADROOM as u64);
|
||||
if (self.db_max_connections as u64) < floor {
|
||||
return Err(format!(
|
||||
"GITLAWB_DB_LOCK_POOL_MAX_CONNECTIONS ({}) must be at least \
|
||||
max_concurrent_git_pushes ({}) plus {} for non-push mutations \
|
||||
that share the lock pool",
|
||||
self.db_lock_pool_max_connections,
|
||||
"GITLAWB_DB_MAX_CONNECTIONS ({}) must be at least max_concurrent_git_pushes ({}) \
|
||||
+ {} headroom = {}: each concurrent write pins one pooled connection for its whole \
|
||||
duration, so a smaller pool lets a burst of slow pushes starve every other DB path.",
|
||||
self.db_max_connections,
|
||||
self.max_concurrent_git_pushes,
|
||||
Self::DB_LOCK_POOL_NON_PUSH_HEADROOM
|
||||
));
|
||||
}
|
||||
let main_floor = Self::DB_POOL_APP_HEADROOM as u64;
|
||||
if (self.db_max_connections as u64) < main_floor {
|
||||
return Err(format!(
|
||||
"GITLAWB_DB_MAX_CONNECTIONS ({}) must be at least {} for non-git \
|
||||
database paths",
|
||||
self.db_max_connections, main_floor
|
||||
Self::DB_POOL_APP_HEADROOM,
|
||||
floor
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
@@ -803,25 +591,6 @@ impl Config {
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn lock_pool_size_defaults_to_40_and_rejects_zero() {
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node"]).db_lock_pool_max_connections,
|
||||
40
|
||||
);
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--db-lock-pool-max-connections", "8"])
|
||||
.db_lock_pool_max_connections,
|
||||
8
|
||||
);
|
||||
// A zero-sized lock pool would deny every write, so clap must reject it
|
||||
// rather than let a node boot into a state where no repo can be written.
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--db-lock-pool-max-connections", "0"])
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn git_service_timeout_defaults_to_600_and_rejects_zero() {
|
||||
assert_eq!(
|
||||
@@ -1002,35 +771,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// U4 (#173): the repair sweep's bounds are conservative by default and a batch of
|
||||
/// 0 (a sweep that walks nothing and never terminates) is a CLI error, not a
|
||||
/// runtime hang. The delay does accept 0, for tests and one-off operational runs.
|
||||
#[test]
|
||||
fn pin_repair_sweep_knobs_default_conservatively() {
|
||||
let c = Config::parse_from(["gitlawb-node"]);
|
||||
assert_eq!(c.pin_repair_sweep_batch, 64);
|
||||
assert_eq!(c.pin_repair_sweep_delay_secs, 60);
|
||||
|
||||
assert!(Config::try_parse_from(["gitlawb-node", "--pin-repair-sweep-batch", "0"]).is_err());
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--pin-repair-sweep-batch", "100001"]).is_err()
|
||||
);
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--pin-repair-sweep-batch", "8"])
|
||||
.pin_repair_sweep_batch,
|
||||
8
|
||||
);
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--pin-repair-sweep-delay-secs", "0"])
|
||||
.pin_repair_sweep_delay_secs,
|
||||
0
|
||||
);
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--pin-repair-sweep-delay-secs", "86401"])
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ipfs_walk_per_source_defaults_and_rejects_out_of_range() {
|
||||
assert_eq!(Config::parse_from(["gitlawb-node"]).ipfs_walk_per_source, 4);
|
||||
@@ -1046,195 +786,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// The legacy-probe budget and the expensive-walk cap are SEPARATE knobs with
|
||||
/// different defaults. They were one field until the probe budget and the walk cap
|
||||
/// were split apart, so assert both defaults here: a future collapse back into one
|
||||
/// field silently gives one of the two the other's default.
|
||||
#[test]
|
||||
fn ipfs_probe_and_walk_knobs_default_apart_and_reject_out_of_range() {
|
||||
let default = Config::parse_from(["gitlawb-node"]);
|
||||
assert_eq!(default.ipfs_max_legacy_probes, 256, "legacy-probe budget");
|
||||
assert_eq!(default.ipfs_max_repos_walked, 64, "expensive-walk cap");
|
||||
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--ipfs-max-legacy-probes", "8"])
|
||||
.ipfs_max_legacy_probes,
|
||||
8
|
||||
);
|
||||
// 0 would probe no repos (serve nothing); clap must reject it.
|
||||
assert!(Config::try_parse_from(["gitlawb-node", "--ipfs-max-legacy-probes", "0"]).is_err());
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--ipfs-max-legacy-probes", "1048577"])
|
||||
.is_err()
|
||||
);
|
||||
assert!(Config::try_parse_from(["gitlawb-node", "--ipfs-max-repos-walked", "0"]).is_err());
|
||||
}
|
||||
|
||||
/// The `GITLAWB_IPFS_MAX_LEGACY_PROBES` knob must actually reach the legacy-probe
|
||||
/// budget it advertises: production seeds `ipfs_max_legacy_probes` from this helper,
|
||||
/// so the knob is a no-op unless the helper reflects it. RED while the helper returns
|
||||
/// the hardcoded `MAX_LEGACY_PROBES_PER_REQUEST` (256 regardless of the knob), GREEN
|
||||
/// once it reads the knob.
|
||||
#[test]
|
||||
fn ipfs_max_legacy_probes_wires_the_legacy_probe_budget() {
|
||||
use crate::state::AppState;
|
||||
// Knob set to 1 → a one-probe legacy budget.
|
||||
let one = Config::parse_from(["gitlawb-node", "--ipfs-max-legacy-probes", "1"]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_legacy_probe_budget(&one),
|
||||
1,
|
||||
"the knob must control the legacy-probe budget, not be ignored"
|
||||
);
|
||||
// Unset knob preserves the shipped 256-probe behaviour.
|
||||
let default = Config::parse_from(["gitlawb-node"]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_legacy_probe_budget(&default),
|
||||
256,
|
||||
"the default knob keeps the shipped 256-probe budget"
|
||||
);
|
||||
assert_eq!(
|
||||
AppState::ipfs_legacy_probe_budget(&default),
|
||||
crate::api::ipfs::MAX_LEGACY_PROBES_PER_REQUEST,
|
||||
"the default budget equals the constant it replaced"
|
||||
);
|
||||
// Ceiling guard: the knob never governs the history-walk ceiling, which must
|
||||
// stay at MAX_PIN_SOURCES + 1 or a provenanced full source set false-503s.
|
||||
assert!(
|
||||
crate::api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST > crate::db::MAX_PIN_SOURCES as u32,
|
||||
"the history-walk ceiling is independent of the repos-walked knob"
|
||||
);
|
||||
}
|
||||
|
||||
/// The `/ipfs` work-budget capacity is DERIVED from the route limit (R6, KTD6), with
|
||||
/// a hard floor of one complete COMBINED resolution per window: the provenance
|
||||
/// phase's walk term plus a full legacy search (the effective
|
||||
/// `ipfs_max_legacy_probes` plus the row ceiling's page toll). This guards the
|
||||
/// derived default so a single default-config deep search never self-throttles
|
||||
/// mid-scan and recreates the F6 admit-then-429 for a legitimate caller. A
|
||||
/// `RateLimiter` sized to the derived budget must admit the whole budget back to
|
||||
/// back.
|
||||
#[test]
|
||||
fn ipfs_work_budget_derives_from_route_limit_and_clears_the_probe_floor() {
|
||||
use crate::state::AppState;
|
||||
|
||||
// Default config: derived work budget = max(route 600, probe budget 256) = 600,
|
||||
// comfortably above the 256-probe floor.
|
||||
let default = Config::parse_from(["gitlawb-node"]);
|
||||
let budget = AppState::ipfs_work_budget(&default);
|
||||
assert_eq!(budget, 600, "default derives max(route 600, probe 256)");
|
||||
assert!(
|
||||
budget >= AppState::ipfs_legacy_probe_budget(&default) as usize,
|
||||
"the work budget must clear one full legacy search per window"
|
||||
);
|
||||
|
||||
// Tight route limit (1): the floor lifts the work budget to one complete
|
||||
// COMBINED resolution, the 256-probe budget PLUS the page toll a 2048-row
|
||||
// ceiling costs at 128 rows per page (16) PLUS the provenance phase's walk term
|
||||
// min(17, 64) = 17, so 289, NOT down to 1. The provenance walks come off the
|
||||
// same bucket before the fallback runs, so a floor without that term hands the
|
||||
// legacy search a bucket the provenance phase already spent from. This case
|
||||
// also carries the walk term's ABOVE-constant direction: the repos-walked knob
|
||||
// is at its default 64, so `MAX_HISTORY_WALKS_PER_REQUEST` (17) is what binds.
|
||||
let tight = Config::parse_from(["gitlawb-node", "--ipfs-rate-limit", "1"]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_work_budget(&tight),
|
||||
289,
|
||||
"a tight route limit is floored at probes + pages + walks \
|
||||
(256 + 16 + min(17, 64) = 17), not clamped to 1"
|
||||
);
|
||||
|
||||
// The walk term's BELOW-constant direction: a repos-walked knob under the
|
||||
// history-walk constant is what the resolver's own `walk_cap` min() selects, so
|
||||
// it is what the floor must carry too. 256 + 16 + min(17, 3) = 275.
|
||||
let narrow_walk = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--ipfs-rate-limit",
|
||||
"1",
|
||||
"--ipfs-max-repos-walked",
|
||||
"3",
|
||||
]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_work_budget(&narrow_walk),
|
||||
275,
|
||||
"the walk term takes min(17, repos-walked 3) = 3, the resolver's own \
|
||||
walk_cap, so the floor is 256 + 16 + 3"
|
||||
);
|
||||
|
||||
// Raised probe budget lifts the floor with it (the work budget tracks the
|
||||
// effective probe budget, not the constant). The walk cap here is a SECOND
|
||||
// below-constant proof at a different pair of values: min(17, 7) = 7, and the
|
||||
// probe knob is raised at the same time so a floor that folded the two terms
|
||||
// together (they were one field before the split) reads visibly wrong rather
|
||||
// than plausibly right.
|
||||
let raised = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--ipfs-rate-limit",
|
||||
"10",
|
||||
"--ipfs-max-legacy-probes",
|
||||
"1000",
|
||||
"--ipfs-max-repos-walked",
|
||||
"7",
|
||||
]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_work_budget(&raised),
|
||||
1023,
|
||||
"the floor tracks the operator-raised legacy-probe budget (1000) plus the \
|
||||
default row ceiling's page toll (16) plus the walk term min(17, 7) = 7"
|
||||
);
|
||||
|
||||
// The scan-rows knob is coupled to the floor too, and this EXECUTES the coupling
|
||||
// rather than describing it: every page the ceiling permits is charged to the
|
||||
// caller's work bucket, so a raised ceiling that did not lift the floor would
|
||||
// 429 an honest caller part-way down their own token ladder. 4096 rows at 128
|
||||
// rows per page is 32 pages, so the floor is 256 + 32 + the default walk term
|
||||
// of 17.
|
||||
let wide_scan = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--ipfs-rate-limit",
|
||||
"10",
|
||||
"--ipfs-max-legacy-scan-rows",
|
||||
"4096",
|
||||
]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_work_budget(&wide_scan),
|
||||
305,
|
||||
"raising the row ceiling must raise the work floor by the pages it buys \
|
||||
(256 probes + 4096/128 = 32 pages + min(17, 64) = 17 walks), or a full \
|
||||
deep scan self-throttles"
|
||||
);
|
||||
|
||||
// 0 route limit disables the derived bucket too (a 0-capacity limiter admits all).
|
||||
let disabled = Config::parse_from(["gitlawb-node", "--ipfs-rate-limit", "0"]);
|
||||
assert_eq!(
|
||||
AppState::ipfs_work_budget(&disabled),
|
||||
0,
|
||||
"route limit 0 disables the derived work bucket alongside the route brake"
|
||||
);
|
||||
|
||||
// Behavioral floor: a limiter sized to the derived (tight-route) budget admits
|
||||
// a whole combined resolution's worth of charges back to back for one source,
|
||||
// then sheds the next.
|
||||
let budget = AppState::ipfs_work_budget(&tight);
|
||||
let limiter =
|
||||
crate::rate_limit::RateLimiter::new(budget, std::time::Duration::from_secs(3600));
|
||||
let rt = tokio::runtime::Builder::new_current_thread()
|
||||
.enable_all()
|
||||
.build()
|
||||
.unwrap();
|
||||
rt.block_on(async {
|
||||
for i in 0..budget {
|
||||
assert!(
|
||||
limiter.check("1.2.3.4").await,
|
||||
"charge {i} of one full combined resolution must be admitted (no mid-scan throttle)"
|
||||
);
|
||||
}
|
||||
assert!(
|
||||
!limiter.check("1.2.3.4").await,
|
||||
"the probe past the derived budget is shed"
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ipfs_max_repos_walked_defaults_and_rejects_out_of_range() {
|
||||
assert_eq!(
|
||||
@@ -1289,52 +840,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ipfs_resolve_budget_secs_defaults_to_10_and_rejects_zero() {
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node"]).ipfs_resolve_budget_secs,
|
||||
10
|
||||
);
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--ipfs-resolve-budget-secs", "3"])
|
||||
.ipfs_resolve_budget_secs,
|
||||
3
|
||||
);
|
||||
// 0 would shed every /ipfs request at the pre-walk resolve (unconditional
|
||||
// 503); clap must reject it.
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--ipfs-resolve-budget-secs", "0"]).is_err()
|
||||
);
|
||||
// The ceiling is shared with the request budget: at the max it parses and the
|
||||
// derived deadline is still representable, past it clap rejects.
|
||||
let at_max = Config::try_parse_from([
|
||||
"gitlawb-node",
|
||||
"--ipfs-resolve-budget-secs",
|
||||
&GIT_SERVICE_TIMEOUT_SECS_MAX.to_string(),
|
||||
])
|
||||
.expect("the documented maximum must parse");
|
||||
assert_eq!(
|
||||
at_max.ipfs_resolve_budget_secs,
|
||||
GIT_SERVICE_TIMEOUT_SECS_MAX
|
||||
);
|
||||
assert!(std::time::Instant::now()
|
||||
.checked_add(std::time::Duration::from_secs(
|
||||
at_max.ipfs_resolve_budget_secs
|
||||
))
|
||||
.is_some());
|
||||
for over in [GIT_SERVICE_TIMEOUT_SECS_MAX + 1, u64::MAX] {
|
||||
assert!(
|
||||
Config::try_parse_from([
|
||||
"gitlawb-node",
|
||||
"--ipfs-resolve-budget-secs",
|
||||
&over.to_string(),
|
||||
])
|
||||
.is_err(),
|
||||
"{over} is past the representable ceiling and must be rejected at parse time"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// #174 (RED-before/GREEN-after): the upper bound is what keeps the deadline derived
|
||||
/// from this knob in range. `get_by_cid` builds the request budget as
|
||||
/// `Instant::now() + Duration::from_secs(this)` (api/ipfs.rs), and that addition is an
|
||||
@@ -1431,108 +936,41 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// #174 F1: concurrent git writes pin the dedicated lock pool, not the main
|
||||
/// pool. `validate()` must reject an under-sized lock pool at boot.
|
||||
/// #174 F1: a connection-affine write lock pins a pooled connection per
|
||||
/// concurrent write, so the pool must clear `max_concurrent_git_pushes` by
|
||||
/// `DB_POOL_APP_HEADROOM` or a push burst starves every other DB path.
|
||||
/// `validate()` must reject an under-sized pool at boot.
|
||||
#[test]
|
||||
fn db_pool_must_clear_the_git_push_cap() {
|
||||
// Shipped defaults validate (lock pool 40 >= pushes 32 + non-push headroom 8).
|
||||
// Shipped defaults validate (48 >= 32 + 8).
|
||||
Config::parse_from(["gitlawb-node"])
|
||||
.validate()
|
||||
.expect("default config must validate");
|
||||
|
||||
// An under-sized lock pool relative to the push cap is rejected.
|
||||
let under_lock = Config::parse_from([
|
||||
// An under-sized pool relative to the push cap is rejected (20 < 32 + 8).
|
||||
let under = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--db-lock-pool-max-connections",
|
||||
"16",
|
||||
"--db-max-connections",
|
||||
"20",
|
||||
"--max-concurrent-git-pushes",
|
||||
"32",
|
||||
]);
|
||||
assert!(
|
||||
under_lock.validate().is_err(),
|
||||
"db_lock_pool_max_connections below max_concurrent_git_pushes + headroom must be rejected"
|
||||
under.validate().is_err(),
|
||||
"db_max_connections 20 below max_concurrent_git_pushes 32 + headroom must be rejected"
|
||||
);
|
||||
|
||||
// Exactly at the push cap without non-push headroom is rejected.
|
||||
let push_only = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--db-lock-pool-max-connections",
|
||||
"32",
|
||||
"--max-concurrent-git-pushes",
|
||||
"32",
|
||||
]);
|
||||
assert!(
|
||||
push_only.validate().is_err(),
|
||||
"db_lock_pool_max_connections equal to max_concurrent_git_pushes must be rejected"
|
||||
);
|
||||
|
||||
// Main pool can be smaller than pushes + headroom when the lock pool carries writes.
|
||||
let split = Config::parse_from([
|
||||
// Exactly at the floor validates (40 == 32 + 8).
|
||||
let at_floor = Config::parse_from([
|
||||
"gitlawb-node",
|
||||
"--db-max-connections",
|
||||
"16",
|
||||
"--db-lock-pool-max-connections",
|
||||
"40",
|
||||
"--max-concurrent-git-pushes",
|
||||
"32",
|
||||
]);
|
||||
assert!(
|
||||
split.validate().is_ok(),
|
||||
"a small main pool with a large lock pool must validate"
|
||||
);
|
||||
|
||||
// Main pool still needs the app headroom floor.
|
||||
let under_main = Config::parse_from(["gitlawb-node", "--db-max-connections", "4"]);
|
||||
assert!(
|
||||
under_main.validate().is_err(),
|
||||
"db_max_connections below DB_POOL_APP_HEADROOM must be rejected"
|
||||
);
|
||||
}
|
||||
|
||||
/// The DECLARED default, read off the parser rather than out of a parse.
|
||||
///
|
||||
/// `Config::parse_from` consults the process environment, so on a host that
|
||||
/// exports `GITLAWB_ENFORCE_OWNER_PUSH=false` a parse-based assertion says
|
||||
/// nothing about what this crate declares — it reports the operator's setting.
|
||||
/// Asserting the declaration is the env-independent form, and it is the one that
|
||||
/// actually fails if someone flips `default_value_t` back.
|
||||
#[test]
|
||||
fn enforce_owner_push_is_declared_true_independent_of_the_environment() {
|
||||
use clap::CommandFactory;
|
||||
let cmd = Config::command();
|
||||
let arg = cmd
|
||||
.get_arguments()
|
||||
.find(|a| a.get_id() == "enforce_owner_push")
|
||||
.expect("the argument must exist");
|
||||
assert_eq!(
|
||||
arg.get_default_values(),
|
||||
["true"],
|
||||
"owner-only push must be the declared default; a node started with no \
|
||||
configuration cannot accept a push from a self-minted key"
|
||||
);
|
||||
}
|
||||
|
||||
/// The flip must not strand an operator mid-upgrade.
|
||||
///
|
||||
/// Turning the gate on is a breaking change for any deployment whose pushers are
|
||||
/// not yet the repo owner, so the escape hatch has to keep working. As a
|
||||
/// presence-only flag `--enforce-owner-push false` is not "false", it is an
|
||||
/// "unexpected argument" error; the value-taking action is what makes that form
|
||||
/// parse.
|
||||
///
|
||||
/// This pins the CLI form only. The environment form resolved to `false` under
|
||||
/// the presence-only declaration too, so it is not what this change fixed, and it
|
||||
/// is not exercised here because the process environment is global and these
|
||||
/// tests run in parallel.
|
||||
#[test]
|
||||
fn enforce_owner_push_stays_disableable_for_rolling_upgrades() {
|
||||
assert!(
|
||||
!Config::parse_from(["gitlawb-node", "--enforce-owner-push", "false"])
|
||||
.enforce_owner_push,
|
||||
"operators must still be able to opt out during a rolling upgrade"
|
||||
);
|
||||
assert!(
|
||||
Config::parse_from(["gitlawb-node", "--enforce-owner-push", "true"]).enforce_owner_push
|
||||
at_floor.validate().is_ok(),
|
||||
"db_max_connections at the floor (pushes + headroom) must validate"
|
||||
);
|
||||
}
|
||||
}
|
||||
+67
-2379
File diff suppressed because it is too large.
Load diff
@@ -35,31 +35,12 @@ pub enum AppError {
|
||||
#[error("invalid request: {0}")]
|
||||
BadRequest(String),
|
||||
|
||||
/// A DID was well-formed enough to carry to a resolver but no verifying key
|
||||
/// could be derived from it. Its own code rather than plain `bad_request`
|
||||
/// because the auth middleware already answers `unresolvable_did` for the
|
||||
/// same failure on a request's keyid, and a client should not have to
|
||||
/// substring-match a message to tell this apart from the other validation
|
||||
/// failures on the same route.
|
||||
#[error("unresolvable did: {0}")]
|
||||
UnresolvableDid(String),
|
||||
|
||||
#[error("too many requests: {0}")]
|
||||
TooManyRequests(String),
|
||||
|
||||
#[error("incomplete: {0}")]
|
||||
Incomplete(String),
|
||||
|
||||
/// A bounded search that could not complete. `continuation`, when present, is the
|
||||
/// sealed scan position the caller echoes as `?scan=` to resume where the search
|
||||
/// stopped (#173 round 13, F2). It is AEAD-sealed at the mint site, never plaintext:
|
||||
/// the row it names is by construction one the caller was denied (INV-13).
|
||||
#[error("search incomplete: {message}")]
|
||||
SearchIncomplete {
|
||||
message: String,
|
||||
continuation: Option<String>,
|
||||
},
|
||||
|
||||
#[error("git error: {0}")]
|
||||
Git(String),
|
||||
|
||||
@@ -69,15 +50,6 @@ pub enum AppError {
|
||||
#[error("server overloaded: {0}")]
|
||||
Overloaded(String),
|
||||
|
||||
#[error("repository is busy")]
|
||||
RepoBusy,
|
||||
|
||||
#[error("repository is temporarily unavailable")]
|
||||
RepoUnavailable,
|
||||
|
||||
#[error("repository write was fenced by a concurrent publish")]
|
||||
RepoWriteFenced,
|
||||
|
||||
#[error("database error: {0}")]
|
||||
Db(#[from] sqlx::Error),
|
||||
|
||||
@@ -91,14 +63,6 @@ pub enum AppError {
|
||||
pub const DB_UNAVAILABLE_CODE: &str = "db_unavailable";
|
||||
pub const DB_UNAVAILABLE_MESSAGE: &str = "database is temporarily unavailable";
|
||||
|
||||
/// Generic client-facing message for `AppError::Internal`. The real error is
|
||||
/// logged server-side; never put sqlx/anyhow detail in the HTTP body (#226).
|
||||
pub const INTERNAL_ERROR_MESSAGE: &str = "an internal error occurred";
|
||||
|
||||
/// Generic client-facing message for non-unavailable `AppError::Db`. Query /
|
||||
/// schema errors stay in logs; the HTTP body must not leak them (#226).
|
||||
pub const DB_ERROR_MESSAGE: &str = "a database error occurred";
|
||||
|
||||
/// Connection-level sqlx failures that mean the database is unreachable right
|
||||
/// now (retryable, 503), as opposed to server-reported query errors.
|
||||
fn db_unavailable(e: &sqlx::Error) -> bool {
|
||||
@@ -119,31 +83,7 @@ impl From<anyhow::Error> for AppError {
|
||||
fn from(err: anyhow::Error) -> Self {
|
||||
match err.downcast::<sqlx::Error>() {
|
||||
Ok(sql) => AppError::Db(sql),
|
||||
// Lock contention is transient and ordinary, so it must not land as a
|
||||
// 500. The internal message names the owner slug and repo, so the
|
||||
// variant carries nothing: the detail stays in the log at the raise
|
||||
// site and the client gets a fixed retryable body.
|
||||
Err(err) => match err.downcast::<crate::git::repo_store::LockPoolBusy>() {
|
||||
Ok(_) => AppError::Overloaded("git write locks at capacity, retry shortly".into()),
|
||||
Err(err) => match err.downcast::<crate::git::repo_store::RepoBusy>() {
|
||||
Ok(_) => AppError::RepoBusy,
|
||||
// Same reasoning one rung down: a refused under-lock refresh is a
|
||||
// transient storage condition, and its internal message names the
|
||||
// owner slug and repo, so the variant carries nothing.
|
||||
Err(err) => match err.downcast::<crate::git::repo_store::RepoUnavailable>() {
|
||||
Ok(_) => AppError::RepoUnavailable,
|
||||
// And one more rung: a publish the store refused twice is
|
||||
// transient in the same way, and the retry is the client's
|
||||
// to make. The variant carries nothing for the same reason
|
||||
// as the two above.
|
||||
Err(err) => match err.downcast::<crate::git::repo_store::RepoWriteFenced>()
|
||||
{
|
||||
Ok(_) => AppError::RepoWriteFenced,
|
||||
Err(err) => AppError::Internal(err),
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
Err(err) => AppError::Internal(err),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -195,51 +135,16 @@ impl IntoResponse for AppError {
|
||||
// IcaptchaProofRequired is handled above (it carries extra headers/fields).
|
||||
AppError::IcaptchaProofRequired { .. } => unreachable!("handled before this match"),
|
||||
AppError::BadRequest(msg) => (StatusCode::BAD_REQUEST, "bad_request", msg.clone()),
|
||||
AppError::UnresolvableDid(msg) => {
|
||||
(StatusCode::BAD_REQUEST, "unresolvable_did", msg.clone())
|
||||
}
|
||||
AppError::TooManyRequests(msg) => {
|
||||
(StatusCode::TOO_MANY_REQUESTS, "rate_limited", msg.clone())
|
||||
}
|
||||
AppError::Incomplete(msg) => {
|
||||
(StatusCode::UNPROCESSABLE_ENTITY, "incomplete", msg.clone())
|
||||
}
|
||||
// A bounded search that could not complete (the CID resolver hit its
|
||||
// legacy-probe or walk ceiling), distinct from the 404 that asserts a
|
||||
// definitive not-found: absence was NOT proven, so the caller should
|
||||
// retry rather than treat it as gone (#173, F2). 503, retryable.
|
||||
AppError::SearchIncomplete { message, .. } => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"search_incomplete",
|
||||
message.clone(),
|
||||
),
|
||||
AppError::Git(msg) => (StatusCode::INTERNAL_SERVER_ERROR, "git_error", msg.clone()),
|
||||
// 504, distinct from the 500 git_error and from the read-gate's 404 /
|
||||
// the auth 401, so the client can tell a deadline from a failure.
|
||||
AppError::Timeout(msg) => (StatusCode::GATEWAY_TIMEOUT, "git_timeout", msg.clone()),
|
||||
// 503 with a FIXED body: the caller should retry, and must not be told
|
||||
// which repo is contended or for how long.
|
||||
AppError::RepoBusy => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"repo_busy",
|
||||
"repository is busy — retry".into(),
|
||||
),
|
||||
// 503 with a FIXED body for the same reason: the caller should retry, and
|
||||
// must not be told which repo could not be refreshed or why.
|
||||
AppError::RepoUnavailable => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"repo_unavailable",
|
||||
"repository is temporarily unavailable, retry".into(),
|
||||
),
|
||||
// 503 with a FIXED body again, and its own code: the caller should
|
||||
// retry, but the condition is not contention, so a client that
|
||||
// distinguishes them should be able to. The body must not say which
|
||||
// repo lost its publish or to whom.
|
||||
AppError::RepoWriteFenced => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"repo_write_fenced",
|
||||
"repository changed underneath this write, retry".into(),
|
||||
),
|
||||
AppError::Db(e) if db_unavailable(e) => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
DB_UNAVAILABLE_CODE,
|
||||
@@ -251,61 +156,24 @@ impl IntoResponse for AppError {
|
||||
AppError::Overloaded(msg) => {
|
||||
(StatusCode::SERVICE_UNAVAILABLE, "overloaded", msg.clone())
|
||||
}
|
||||
// Opaque body + server log: bare `?` on sqlx paths becomes `AppError::Db`
|
||||
// via `From`, so this arm (not `Internal`) is the common leak for open
|
||||
// routes like GET /api/v1/repos and GET /api/v1/peers (#226).
|
||||
AppError::Db(e) => {
|
||||
tracing::error!(error = %e, "database error");
|
||||
(
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
"db_error",
|
||||
DB_ERROR_MESSAGE.into(),
|
||||
)
|
||||
}
|
||||
// Opaque body: handlers that map with `.map_err(AppError::Internal)`
|
||||
// (e.g. GET /ipfs/{cid}) land here; other DB failures usually hit `Db`.
|
||||
// Log `{e:#}` so context-wrapped anyhow chains keep the leaf cause
|
||||
// (Display alone is only the outermost layer; see api/repos.rs).
|
||||
AppError::Internal(e) => {
|
||||
tracing::error!(error = %format!("{e:#}"), "internal error");
|
||||
(
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
"internal_error",
|
||||
INTERNAL_ERROR_MESSAGE.into(),
|
||||
)
|
||||
}
|
||||
AppError::Db(e) => (StatusCode::INTERNAL_SERVER_ERROR, "db_error", e.to_string()),
|
||||
AppError::Internal(e) => (
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
"internal_error",
|
||||
e.to_string(),
|
||||
),
|
||||
};
|
||||
|
||||
let mut body = json!({
|
||||
let body = Json(json!({
|
||||
"error": code,
|
||||
"message": message,
|
||||
});
|
||||
// A truncated CID search may carry the sealed position the caller echoes as
|
||||
// `?scan=` to resume. Rendered as a third body field, present only when the
|
||||
// shed actually left something to resume: a wrapped scan and a throttled
|
||||
// request both omit it, and its ABSENCE is what tells a caller the ladder is
|
||||
// over. It is opaque ciphertext; see `gitlawb_core::scan_token`.
|
||||
if let AppError::SearchIncomplete {
|
||||
continuation: Some(token),
|
||||
..
|
||||
} = &self
|
||||
{
|
||||
body["continuation"] = json!(token);
|
||||
}
|
||||
}));
|
||||
|
||||
let mut resp = (status, Json(body)).into_response();
|
||||
// Both retryable 503s advertise when to retry: Overloaded (capacity shed) and
|
||||
// SearchIncomplete (a bounded CID search cut short by a cap — retry may complete
|
||||
// it). They ride the shared tail above for body/status, so the header is attached
|
||||
// here rather than in bespoke early returns, keeping each variant handled once.
|
||||
if matches!(
|
||||
self,
|
||||
AppError::Overloaded(_)
|
||||
| AppError::SearchIncomplete { .. }
|
||||
| AppError::RepoBusy
|
||||
| AppError::RepoUnavailable
|
||||
| AppError::RepoWriteFenced
|
||||
) {
|
||||
let mut resp = (status, body).into_response();
|
||||
// Overloaded advertises when to retry. It rides the shared tail above for
|
||||
// its body/status, so the header is attached here rather than in a bespoke
|
||||
// early return — keeping the variant handled in exactly one place.
|
||||
if matches!(self, AppError::Overloaded(_)) {
|
||||
resp.headers_mut().insert(
|
||||
axum::http::header::RETRY_AFTER,
|
||||
axum::http::HeaderValue::from_static("1"),
|
||||
@@ -343,110 +211,4 @@ mod tests {
|
||||
"1"
|
||||
);
|
||||
}
|
||||
|
||||
/// #226: raw sqlx/DB detail must never appear in the Internal 500 body.
|
||||
#[tokio::test]
|
||||
async fn internal_error_body_is_opaque() {
|
||||
use serde_json::{json, Value};
|
||||
|
||||
let leak = "error returned from database: relation \"repos\" does not exist";
|
||||
let resp = AppError::Internal(anyhow::anyhow!("{leak}")).into_response();
|
||||
assert_eq!(resp.status(), StatusCode::INTERNAL_SERVER_ERROR);
|
||||
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.expect("read body");
|
||||
let v: Value = serde_json::from_slice(&bytes).expect("json body");
|
||||
// Exact object: a new `detail` field with different sensitive text must
|
||||
// also fail, not only a repeat of the original error string.
|
||||
assert_eq!(
|
||||
v,
|
||||
json!({
|
||||
"error": "internal_error",
|
||||
"message": INTERNAL_ERROR_MESSAGE,
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
/// #226: `AppError::Db` query errors (the common `?` path) must also be opaque.
|
||||
#[tokio::test]
|
||||
async fn db_error_body_is_opaque() {
|
||||
use serde_json::{json, Value};
|
||||
|
||||
let resp = AppError::Db(sqlx::Error::Protocol(
|
||||
"error returned from database: column \"is_public\" does not exist".into(),
|
||||
))
|
||||
.into_response();
|
||||
assert_eq!(resp.status(), StatusCode::INTERNAL_SERVER_ERROR);
|
||||
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.expect("read body");
|
||||
let v: Value = serde_json::from_slice(&bytes).expect("json body");
|
||||
assert_eq!(
|
||||
v,
|
||||
json!({
|
||||
"error": "db_error",
|
||||
"message": DB_ERROR_MESSAGE,
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
/// Connection-level failures must stay 503 `db_unavailable`, not collapse
|
||||
/// into the opaque 500 `db_error` arm if `db_unavailable` loses a variant.
|
||||
#[tokio::test]
|
||||
async fn db_pool_timeout_stays_503_unavailable() {
|
||||
use serde_json::{json, Value};
|
||||
|
||||
let resp = AppError::Db(sqlx::Error::PoolTimedOut).into_response();
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.expect("read body");
|
||||
let v: Value = serde_json::from_slice(&bytes).expect("json body");
|
||||
assert_eq!(
|
||||
v,
|
||||
json!({
|
||||
"error": DB_UNAVAILABLE_CODE,
|
||||
"message": DB_UNAVAILABLE_MESSAGE,
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
/// #251: bare `?` on anyhow-wrapped sqlx relies on this downcast so a
|
||||
/// closed pool becomes 503 `db_unavailable`, not 500 `internal_error`.
|
||||
#[test]
|
||||
fn pool_closed_via_anyhow_from_is_503_db_unavailable() {
|
||||
let err: AppError = anyhow::Error::from(sqlx::Error::PoolClosed).into();
|
||||
let resp = err.into_response();
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lock_pool_busy_via_anyhow_from_is_503_overloaded() {
|
||||
let err: AppError = anyhow::Error::new(crate::git::repo_store::LockPoolBusy).into();
|
||||
let resp = err.into_response();
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
assert_eq!(
|
||||
resp.headers().get("retry-after").unwrap().to_str().unwrap(),
|
||||
"1"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn repo_busy_unavailable_and_fenced_advertise_retry_after() {
|
||||
for err in [
|
||||
AppError::RepoBusy,
|
||||
AppError::RepoUnavailable,
|
||||
AppError::RepoWriteFenced,
|
||||
] {
|
||||
let resp = err.into_response();
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
assert_eq!(
|
||||
resp.headers().get("retry-after").unwrap().to_str().unwrap(),
|
||||
"1"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -61,27 +61,6 @@ pub fn create_issue(repo_path: &Path, issue_id: &str, json: &str) -> Result<()>
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Remove a single issue ref while the write guard still holds the advisory lock,
|
||||
/// after a definite publish refusal. Best-effort: a failed delete leaves a
|
||||
/// local-only orphan, which is still better than telling the client to retry into a
|
||||
/// duplicate id. Not used on `UploadUnknowable`, where the PUT may still land.
|
||||
pub fn delete_issue_ref(
|
||||
git_bin: &str,
|
||||
repo_path: &Path,
|
||||
issue_id: &str,
|
||||
deadline: std::time::Instant,
|
||||
) -> Result<()> {
|
||||
let ref_name = format!("refs/gitlawb/issues/{issue_id}");
|
||||
crate::git::visibility_pack::run_bounded_git(
|
||||
git_bin,
|
||||
&["update-ref", "-d", &ref_name],
|
||||
repo_path,
|
||||
b"",
|
||||
deadline,
|
||||
)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// List all issue refs and return their JSON content.
|
||||
pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
|
||||
// List all refs under refs/gitlawb/issues/
|
||||
@@ -299,27 +278,6 @@ mod tests {
|
||||
assert!(result.unwrap_err().to_string().contains("ambiguous"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn delete_issue_ref_removes_a_created_ref() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
init_repo(&dir);
|
||||
let full_id = "eee88888-0000-0000-0000-000000000000";
|
||||
create_issue(
|
||||
dir.path(),
|
||||
full_id,
|
||||
r#"{"id":"eee88888-0000-0000-0000-000000000000","status":"open"}"#,
|
||||
)
|
||||
.unwrap();
|
||||
delete_issue_ref(
|
||||
"git",
|
||||
dir.path(),
|
||||
full_id,
|
||||
std::time::Instant::now() + std::time::Duration::from_secs(30),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(resolve_issue_id(dir.path(), full_id).unwrap(), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_close_issue_via_prefix() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -14,13 +14,13 @@ use tokio::process::Command;
|
||||
/// the work they admitted, so admission is released only when that work is truly
|
||||
/// done — not the instant the handler future drops on a client disconnect.
|
||||
///
|
||||
/// A drop-only wrapper: nothing here inspects what it holds. The handler MOVEs its
|
||||
/// permits in and keeps no copy (a retained copy would drop early and release admission
|
||||
/// the moment the future is dropped, defeating the guard). It is threaded into
|
||||
/// `drive_git_child`, whose [`KillGroupOnDrop`] moves it into the detached reaper on
|
||||
/// disconnect, so both permits drop only after the process group is confirmed reaped
|
||||
/// (`kill(-pgid,0)==ESRCH`) rather than while the group is still alive holding PIDs past
|
||||
/// the concurrency cap (#174 P1-a, plain-spawn residual).
|
||||
/// A move-only wrapper: no methods beyond construction and `Drop`. The handler
|
||||
/// MOVEs its permits in and keeps no copy (a retained copy would drop early and
|
||||
/// release admission the moment the future is dropped, defeating the guard). It is
|
||||
/// threaded into `drive_git_child`, whose [`KillGroupOnDrop`] moves it into the
|
||||
/// detached reaper on disconnect, so both permits drop only after the process group
|
||||
/// is confirmed reaped (`kill(-pgid,0)==ESRCH`) rather than while the group is still
|
||||
/// alive holding PIDs past the concurrency cap (#174 P1-a, plain-spawn residual).
|
||||
///
|
||||
/// The `be0cdd6` path-scoped upload-pack walk already applies this discipline by
|
||||
/// moving its permits into the `spawn_blocking`; this generalizes it to the plain
|
||||
@@ -33,8 +33,6 @@ pub struct AdmissionGuard {
|
||||
// 'static` so the guard can move into the detached reaper task.
|
||||
_global: Option<Box<dyn Send + 'static>>,
|
||||
_caller: Option<Box<dyn Send + 'static>>,
|
||||
// Any further work-scoped hold that must outlive the process group; see `with_hold`.
|
||||
_hold: Option<Box<dyn Send + 'static>>,
|
||||
// Per-repo write lease (#174 U2/F3), `Some` ONLY on the receive-pack write path
|
||||
// (via [`with_lease`](Self::with_lease)); `None` on every read path and every
|
||||
// non-receive-pack write path. It rides this guard into `KillGroupOnDrop`'s detached
|
||||
@@ -56,26 +54,10 @@ impl AdmissionGuard {
|
||||
Self {
|
||||
_global: Some(Box::new(global)),
|
||||
_caller: caller.map(|c| Box::new(c) as Box<dyn Send + 'static>),
|
||||
_hold: None,
|
||||
_lease: None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Attach a further hold that must not be released until the process group is
|
||||
/// reaped, and ride it through the same seam as the permits.
|
||||
///
|
||||
/// The push handler uses this for the repo WRITE LOCK (#173 F2). Its
|
||||
/// `guard.release(..)` line is only reached if `receive_pack` returns, so on a client
|
||||
/// disconnect the lock used to be freed by the dropped future while the detached
|
||||
/// reaper was still giving the group its SIGTERM grace, admitting a second
|
||||
/// `receive-pack` on the same repo. Carrying the lock here holds it until the group
|
||||
/// is ESRCH-confirmed gone, which is the same invariant the timeout path already
|
||||
/// keeps ("a caller releasing a write lock can't race them", `reap_group_on_timeout`).
|
||||
pub fn with_hold(mut self, hold: impl Send + 'static) -> Self {
|
||||
self._hold = Some(Box::new(hold));
|
||||
self
|
||||
}
|
||||
|
||||
/// Attach the per-repo write lease (#174 U2/F3). Called ONLY on the receive-pack
|
||||
/// write path, so the lease rides the disconnect reaper; read paths never call this.
|
||||
pub fn with_lease(mut self, lease: crate::state::RepoWriteLease) -> Self {
|
||||
@@ -110,7 +92,7 @@ pub async fn info_refs(
|
||||
.arg("--stateless-rpc")
|
||||
.arg("--advertise-refs")
|
||||
.arg(repo_path);
|
||||
// No request body: advertise-refs does not read stdin.
|
||||
// No request body — advertise-refs does not read stdin.
|
||||
let (stdout, admission) =
|
||||
drive_git_child(command, Bytes::new(), timeout, "advertise-refs", admission).await?;
|
||||
// Single-stage op: the advertisement's group is reaped by now; release admission
|
||||
@@ -677,15 +659,14 @@ pub async fn build_filtered_pack(
|
||||
command
|
||||
.args(["pack-objects", "--stdout"])
|
||||
.current_dir(repo_path);
|
||||
let (out, admission) = drive_git_child(
|
||||
drive_git_child(
|
||||
command,
|
||||
Bytes::from(data),
|
||||
deadline.saturating_duration_since(Instant::now()),
|
||||
"pack-objects",
|
||||
admission,
|
||||
)
|
||||
.await?;
|
||||
Ok((out, admission))
|
||||
.await
|
||||
}
|
||||
|
||||
/// Serve a clone/fetch with the withheld blobs removed from the response pack.
|
||||
@@ -1899,143 +1880,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
// #174 U1 (R2, KTD3, RED-before/GREEN-after): the path-scoped filtered-pack serve
|
||||
// must hold read + per-caller admission until its pack-objects process group is
|
||||
// reaped on a client disconnect, exactly as the plain upload_pack path does. Before
|
||||
// the fix build_filtered_pack took no AdmissionGuard and the handler's `_hold`
|
||||
// permits dropped the instant the request future was dropped, so disconnect-spam on
|
||||
// a path-scoped repo could hold PIDs past the concurrency cap while the permits were
|
||||
// already free (#174 P1-a, on the filtered path the plain path had already closed).
|
||||
//
|
||||
// A real AdmissionGuard built from two owned semaphore permits rides
|
||||
// rev-list -> pack-objects. We drive the future until pack-objects has forked its
|
||||
// grandchild (the streaming pack-writer stand-in), assert the permits are still held
|
||||
// mid-serve, then DROP the future (client disconnect) and assert the permits are
|
||||
// released only AFTER the group is ESRCH-confirmed gone — never while it is alive.
|
||||
// Goes RED if the guard is not threaded into the pack-objects stage (it would then
|
||||
// drop after rev-list, freeing the permits mid-serve or on the bare future drop).
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn filtered_pack_holds_admission_until_group_reaped_on_disconnect() {
|
||||
use std::sync::Arc;
|
||||
use tokio::sync::Semaphore;
|
||||
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// rev-list returns one oid fast; pack-objects forks a grandchild (the streaming
|
||||
// writer stand-in), records leader+grandchild pids, then hangs so the future
|
||||
// parks mid-serve with the guard owned by the pack-objects KillGroupOnDrop. The
|
||||
// grandchild inherits (holds open) the stdout pipe, so drive_git_child's
|
||||
// read_to_end blocks and the future stays pending until we drop it.
|
||||
let body = format!(
|
||||
"#!/bin/sh\ncase \"$1\" in\n rev-list) echo deadbeefdeadbeefdeadbeefdeadbeefdeadbeef ;;\n pack-objects) sleep 300 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nwait ;;\n *) exit 1 ;;\nesac\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
let withheld = HashSet::new();
|
||||
|
||||
// Retry the fake-git spawn race like the sibling disconnect test; each attempt
|
||||
// gets a FRESH semaphore so a dropped losing attempt can't skew the winning
|
||||
// attempt's permit accounting. Keep the winning attempt's future PENDING so the
|
||||
// drop below exercises the client-disconnect teardown.
|
||||
let (fut, sem, leader, grandchild) = {
|
||||
let mut attempt = 0u64;
|
||||
loop {
|
||||
attempt += 1;
|
||||
let _ = std::fs::remove_file(&pidfile);
|
||||
// Semaphore(4): two owned permits model the handler's global-read +
|
||||
// per-caller admission, leaving 2 available while the op is in flight.
|
||||
let sem = Arc::new(Semaphore::new(4));
|
||||
let g = sem.clone().try_acquire_owned().unwrap();
|
||||
let c = sem.clone().try_acquire_owned().unwrap();
|
||||
let admission = AdmissionGuard::new(g, Some(c));
|
||||
let mut fut = Box::pin(build_filtered_pack(
|
||||
git_bin.to_str().unwrap(),
|
||||
tmp.path(),
|
||||
&withheld,
|
||||
Duration::from_secs(60),
|
||||
Some(admission),
|
||||
));
|
||||
// Advance the future a slice at a time until the fake records its pids
|
||||
// (i.e. pack-objects is running). `Ok(_)` means the future returned
|
||||
// before the pidfile appeared (spawn error / early exit); stop polling
|
||||
// then, since re-polling a completed future panics.
|
||||
let mut pids = None;
|
||||
for _ in 0..500 {
|
||||
let finished = tokio::time::timeout(Duration::from_millis(10), &mut fut)
|
||||
.await
|
||||
.is_ok();
|
||||
if let Some(p) = read_two_pids(&pidfile) {
|
||||
pids = Some(p);
|
||||
break;
|
||||
}
|
||||
if finished {
|
||||
break;
|
||||
}
|
||||
}
|
||||
match pids {
|
||||
Some((l, gch)) => break (fut, sem, l, gch),
|
||||
None => {
|
||||
// Transient spawn miss: drop the still-armed future so its guard
|
||||
// reaps anything that spawned (and returns the permits), then
|
||||
// back off before retrying.
|
||||
drop(fut);
|
||||
assert!(
|
||||
attempt < FAKE_GIT_RETRY_ATTEMPTS,
|
||||
"fake git failed to reach the pack-objects stage after \
|
||||
{FAKE_GIT_RETRY_ATTEMPTS} attempts (persistent failure, \
|
||||
not a transient parallel-runner miss)"
|
||||
);
|
||||
tokio::time::sleep(Duration::from_millis(
|
||||
FAKE_GIT_BACKOFF_STEP_MS * attempt,
|
||||
))
|
||||
.await;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
let _cleanup = ReapOnPanic(vec![leader, grandchild]);
|
||||
assert!(alive(grandchild), "grandchild must be running mid-serve");
|
||||
|
||||
// Mid-serve: the pack-objects stage owns the guard, so the two permits are still
|
||||
// held. A build that dropped the guard after rev-list (unthreaded pack-objects
|
||||
// stage) would have freed them here.
|
||||
assert_eq!(
|
||||
sem.available_permits(),
|
||||
2,
|
||||
"admission permits must be held while the filtered serve is in flight"
|
||||
);
|
||||
|
||||
// Client disconnect: drop the request future. The pack-objects KillGroupOnDrop
|
||||
// must tear the group down AND hold the permits until the group is
|
||||
// ESRCH-confirmed gone, releasing them only then.
|
||||
drop(fut);
|
||||
|
||||
let mut released_while_alive = false;
|
||||
let mut released_after_reap = false;
|
||||
for _ in 0..500 {
|
||||
let released = sem.available_permits() == 4;
|
||||
let group_alive = alive(grandchild);
|
||||
if released && group_alive {
|
||||
released_while_alive = true;
|
||||
}
|
||||
if released && !group_alive {
|
||||
released_after_reap = true;
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
assert!(
|
||||
!released_while_alive,
|
||||
"admission permits were released while the git group was still alive — the \
|
||||
path-scoped concurrency-cap bypass (#174 P1-a) is open"
|
||||
);
|
||||
assert!(
|
||||
released_after_reap,
|
||||
"admission permits must be released once the group is reaped on disconnect"
|
||||
);
|
||||
}
|
||||
|
||||
// ── F1: filtered-serve admission threaded through both pack stages ──────
|
||||
//
|
||||
// The handler-level disconnect regression lives in api/repos.rs
|
||||
|
||||
@@ -431,9 +431,7 @@ fn batch_check_probe(
|
||||
/// never on any English `fatal:` wording (KTD-4): a genuinely-absent object is the only
|
||||
/// `Ok(None)` (404) path. A probe that could not honestly examine the store is a
|
||||
/// [`ProbeError`], split by object-store readability into `Transient` (retryable 503)
|
||||
/// and `Deterministic` (terminal 500) so the serve path can shed the right status. The
|
||||
/// deadline itself arrives as a `Transient` fault, so the handler marks the search
|
||||
/// truncated rather than reporting a false not-found (#173 round-10 R1/KTD2).
|
||||
/// and `Deterministic` (terminal 500) so the serve path can shed the right status.
|
||||
pub fn object_type_bounded(
|
||||
git_bin: &str,
|
||||
repo_path: &Path,
|
||||
@@ -601,63 +599,6 @@ pub(crate) fn object_store_readable_store_wide(repo_path: &Path) -> bool {
|
||||
object_store_readable(repo_path, "")
|
||||
}
|
||||
|
||||
/// Bounded `git cat-file -s` size read for the `GET /ipfs/{cid}` serve path (#173
|
||||
/// round-10, R1/KTD2): reads the object size WITHOUT its content (so an oversized object
|
||||
/// is rejected before it is buffered, #173 F6), under
|
||||
/// [`run_bounded_git`](crate::git::visibility_pack::run_bounded_git) so a wedged size
|
||||
/// read is reaped at `deadline` instead of pinning the held /ipfs walk admission.
|
||||
/// `Ok(n)` on success, and otherwise a [`ProbeError`] in the same vocabulary the type and
|
||||
/// content stages use: a reaped child is `Transient` (retryable), and every other failure
|
||||
/// goes through [`classify_store_fault`], so it is `Transient` when the object store is
|
||||
/// not readable and `Deterministic` when it is.
|
||||
///
|
||||
/// There is deliberately NO absence value (#173 round 12). This returned
|
||||
/// `Ok(None)` for every non-timeout failure, which `gate_and_serve` reads as a verified
|
||||
/// absence and does not taint the search for, so a corrupt object, an unreadable pack, or
|
||||
/// a failed spawn handed an authorized caller a definitive 404 instead of the retryable
|
||||
/// 503 tail. Absence is also not this stage's question: the caller has already had a
|
||||
/// `Present` verdict from [`object_type_bounded`], so an object that cannot be sized here
|
||||
/// is a fault, not a not-found, and the one honest exception (a concurrent gc between the
|
||||
/// two stages) is classified by store readability like any other. Making the absence
|
||||
/// unrepresentable is what keeps the next caller from reintroducing the swallow.
|
||||
///
|
||||
/// Takes the shared `deadline` rather than its own timeout so a caller that pairs this
|
||||
/// size check with a later read spends ONE budget across the pair, not one per stage.
|
||||
pub fn object_size_bounded(
|
||||
git_bin: &str,
|
||||
repo_path: &Path,
|
||||
sha256_hex: &str,
|
||||
deadline: std::time::Instant,
|
||||
) -> std::result::Result<u64, ProbeError> {
|
||||
match crate::git::visibility_pack::run_bounded_git(
|
||||
git_bin,
|
||||
&["cat-file", "-s", sha256_hex],
|
||||
repo_path,
|
||||
b"",
|
||||
deadline,
|
||||
) {
|
||||
Ok(out) => {
|
||||
let text = String::from_utf8_lossy(&out);
|
||||
text.trim().parse::<u64>().map_err(|e| {
|
||||
// git exited 0 but did not print a size: the store answered something
|
||||
// this code cannot read, which is a fault and never an absence.
|
||||
classify_store_fault(
|
||||
repo_path,
|
||||
sha256_hex,
|
||||
anyhow::anyhow!("unparseable `cat-file -s` output {:?}: {e}", text.trim()),
|
||||
)
|
||||
})
|
||||
}
|
||||
// The watchdog reaped the child at `deadline`; retryable whatever the store looks
|
||||
// like, so it is routed before readability gets a say (same rule as the content
|
||||
// stage in `read_object_bounded`).
|
||||
Err(e) if e.is::<crate::git::smart_http::GitServiceTimeout>() => {
|
||||
Err(ProbeError::Transient(e))
|
||||
}
|
||||
Err(e) => Err(classify_store_fault(repo_path, sha256_hex, e)),
|
||||
}
|
||||
}
|
||||
|
||||
/// Bounded, reaped variant of [`read_object_content`] for the async `/ipfs` serve
|
||||
/// path (#174 F3). Same teardown guarantees as [`object_type_bounded`].
|
||||
pub fn read_object_content_bounded(
|
||||
@@ -870,7 +811,6 @@ pub fn merge_branch(
|
||||
}
|
||||
|
||||
/// Resolve a repo disk path: {repos_dir}/{owner_slug}/{repo_name}.git
|
||||
#[allow(dead_code)] // exercised from test_support and state tests; production uses validated_repo_disk_path
|
||||
pub fn repo_disk_path(repos_dir: &Path, owner_did: &str, repo_name: &str) -> PathBuf {
|
||||
// Sanitize the DID for use as a directory name
|
||||
let owner_slug = owner_did.replace([':', '/'], "_");
|
||||
@@ -926,92 +866,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// #173 round-10 (KTD2): `object_type_bounded` reaps a wedged `cat-file` child at its
|
||||
/// deadline instead of blocking on it to natural exit, so a hung probe cannot pin the
|
||||
/// /ipfs walk admission the owning task holds. A fake `git` records its pid and sleeps
|
||||
/// far past the 1s deadline; the `run_bounded_git` watchdog (SIGTERM -> grace ->
|
||||
/// SIGKILL of the process group) must kill it well before that natural exit, and the
|
||||
/// call must surface `GitServiceTimeout`. REVERT PROOF (RED): swap the twin's
|
||||
/// `run_bounded_git` for the bare `Command::output()` and the wedged child stays alive
|
||||
/// past the deadline — the mid-flight liveness poll below reads it still running.
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn object_type_bounded_reaps_wedged_child_at_deadline() {
|
||||
use std::time::Duration;
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("catfile.pid");
|
||||
// `cat-file` records its own pid then sleeps 8s (>> the 1s deadline) so the probe
|
||||
// is genuinely wedged; the watchdog is what must end it.
|
||||
let body = format!(
|
||||
"#!/bin/sh\n\
|
||||
case \"$1\" in\n\
|
||||
cat-file) echo $$ > \"{}\"; sleep 8 ;;\n\
|
||||
*) : ;;\n\
|
||||
esac\n\
|
||||
exit 0\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_path = tmp.path().join("fakegit");
|
||||
std::fs::write(&git_path, &body).unwrap();
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
let mut perm = std::fs::metadata(&git_path).unwrap().permissions();
|
||||
perm.set_mode(0o755);
|
||||
std::fs::set_permissions(&git_path, perm).unwrap();
|
||||
}
|
||||
let repo = tmp.path().to_path_buf();
|
||||
let git = git_path.to_str().unwrap().to_string();
|
||||
|
||||
let alive = |pid: i32| unsafe { libc::kill(pid, 0) == 0 };
|
||||
|
||||
// The bounded probe blocks until the watchdog tears the child down, so run it on
|
||||
// a worker thread and poll for the reap from here.
|
||||
let handle = std::thread::spawn(move || {
|
||||
let deadline = std::time::Instant::now() + Duration::from_secs(1);
|
||||
super::object_type_bounded(&git, &repo, "deadbeef", deadline)
|
||||
});
|
||||
|
||||
let mut pid = None;
|
||||
for _ in 0..500 {
|
||||
if let Some(p) = std::fs::read_to_string(&pidfile)
|
||||
.ok()
|
||||
.and_then(|s| s.trim().parse::<i32>().ok())
|
||||
{
|
||||
pid = Some(p);
|
||||
break;
|
||||
}
|
||||
std::thread::sleep(Duration::from_millis(10));
|
||||
}
|
||||
let pid = pid.expect("the fake cat-file must have spawned and recorded its pid");
|
||||
|
||||
// Past the 1s deadline + SIGTERM grace but well before the 8s natural exit: the
|
||||
// watchdog must already have reaped the wedged group. A bare, unbounded read would
|
||||
// leave it running here — the load-bearing RED.
|
||||
std::thread::sleep(Duration::from_secs(3));
|
||||
let reaped = !alive(pid);
|
||||
// Defensive reap so a RED run leaks no orphan.
|
||||
unsafe {
|
||||
libc::kill(pid, libc::SIGKILL);
|
||||
}
|
||||
assert!(
|
||||
reaped,
|
||||
"object_type_bounded must reap the wedged cat-file child at the deadline, \
|
||||
not leave it running to its natural exit"
|
||||
);
|
||||
|
||||
let res = handle.join().expect("probe thread joins");
|
||||
let err = res.expect_err("a deadline overrun must be an error, not a value");
|
||||
// A reaped deadline is a retryable fault, not a verdict about the object, so it
|
||||
// must arrive as Transient (-> 503) carrying GitServiceTimeout.
|
||||
let super::ProbeError::Transient(inner) = &err else {
|
||||
panic!("a deadline overrun must be a Transient probe fault, got: {err:?}");
|
||||
};
|
||||
assert!(
|
||||
inner.is::<crate::git::smart_http::GitServiceTimeout>(),
|
||||
"a deadline overrun must surface GitServiceTimeout, got: {inner:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// #174 F5 (RED-before/GREEN-after): a packed object whose pack/idx is unreadable
|
||||
/// makes `git cat-file -t` emit "could not get object info" — byte-identical to a
|
||||
/// genuine miss. `object_type_bounded` must report absence ONLY when the object
|
||||
@@ -1517,134 +1371,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// #173 round 12 (jatmn): the SIZE probe must use the same absence-versus-fault
|
||||
/// vocabulary the type probe does. It mapped every non-timeout failure to `Ok(None)`,
|
||||
/// which `gate_and_serve` reads as a verified absence and does not taint, so a
|
||||
/// corrupt object, an unreadable pack, or a failed spawn ended the search cleanly and
|
||||
/// handed an authorized caller a definitive 404 instead of the retryable 503 tail.
|
||||
///
|
||||
/// A corrupt loose object is the same fixture the type stage uses for this, and it is
|
||||
/// the honest case: the object EXISTS, the type probe says so, and only the size read
|
||||
/// fails. RED before the change (`Ok(None)`).
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn object_size_bounded_corrupt_loose_object_is_fault_not_absence() {
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
let td = tempfile::TempDir::new().unwrap();
|
||||
let work = td.path().join("sizecorrupt");
|
||||
std::fs::create_dir_all(&work).unwrap();
|
||||
let g = |args: &[&str]| {
|
||||
assert!(
|
||||
Command::new("git")
|
||||
.args(args)
|
||||
.current_dir(&work)
|
||||
.status()
|
||||
.unwrap()
|
||||
.success(),
|
||||
"git {args:?}"
|
||||
);
|
||||
};
|
||||
g(&["init", "-q", "--object-format=sha256", "."]);
|
||||
g(&["config", "user.email", "t@t"]);
|
||||
g(&["config", "user.name", "t"]);
|
||||
std::fs::write(work.join("f.txt"), b"loose object content\n").unwrap();
|
||||
g(&["add", "f.txt"]);
|
||||
g(&["commit", "-qm", "c1"]);
|
||||
let blob = String::from_utf8(
|
||||
Command::new("git")
|
||||
.args(["rev-parse", "HEAD:f.txt"])
|
||||
.current_dir(&work)
|
||||
.output()
|
||||
.unwrap()
|
||||
.stdout,
|
||||
)
|
||||
.unwrap()
|
||||
.trim()
|
||||
.to_string();
|
||||
|
||||
let deadline = std::time::Instant::now() + std::time::Duration::from_secs(10);
|
||||
// Healthy first: the probe reads the real size, so the fault case below is not
|
||||
// passing for the trivial reason that this fixture never worked.
|
||||
let healthy = super::object_size_bounded("git", &work, &blob, deadline);
|
||||
assert!(
|
||||
matches!(healthy, Ok(n) if n > 0),
|
||||
"a readable object reports its size; got {healthy:?}"
|
||||
);
|
||||
|
||||
let obj = work.join(".git/objects").join(&blob[0..2]).join(&blob[2..]);
|
||||
let mut perms = std::fs::metadata(&obj).unwrap().permissions();
|
||||
perms.set_mode(0o644);
|
||||
std::fs::set_permissions(&obj, perms).unwrap();
|
||||
std::fs::write(&obj, b"garbage not a zlib stream").unwrap();
|
||||
|
||||
let res = super::object_size_bounded("git", &work, &blob, deadline);
|
||||
assert!(
|
||||
res.is_err(),
|
||||
"a corrupt object must surface as a probe fault, never as an absence the \
|
||||
resolver renders as a clean 404; got {res:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// #173 round 12 (jatmn), the transient arm: a store this process cannot read is the
|
||||
/// retryable case, so the size probe classifies it `Transient` exactly as the type
|
||||
/// probe does. Distinguishing the two arms is the whole point of routing through
|
||||
/// `classify_store_fault` rather than returning one undifferentiated error.
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn object_size_bounded_unreadable_store_is_transient() {
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
let td = tempfile::TempDir::new().unwrap();
|
||||
let work = td.path().join("sizeunreadable");
|
||||
std::fs::create_dir_all(&work).unwrap();
|
||||
let g = |args: &[&str]| {
|
||||
assert!(
|
||||
Command::new("git")
|
||||
.args(args)
|
||||
.current_dir(&work)
|
||||
.status()
|
||||
.unwrap()
|
||||
.success(),
|
||||
"git {args:?}"
|
||||
);
|
||||
};
|
||||
g(&["init", "-q", "--object-format=sha256", "."]);
|
||||
g(&["config", "user.email", "t@t"]);
|
||||
g(&["config", "user.name", "t"]);
|
||||
std::fs::write(work.join("f.txt"), b"loose object content\n").unwrap();
|
||||
g(&["add", "f.txt"]);
|
||||
g(&["commit", "-qm", "c1"]);
|
||||
let blob = String::from_utf8(
|
||||
Command::new("git")
|
||||
.args(["rev-parse", "HEAD:f.txt"])
|
||||
.current_dir(&work)
|
||||
.output()
|
||||
.unwrap()
|
||||
.stdout,
|
||||
)
|
||||
.unwrap()
|
||||
.trim()
|
||||
.to_string();
|
||||
|
||||
// Make this oid's loose fan-out unreadable: git fails, and the store cannot
|
||||
// certify absence, so the fault is retryable rather than terminal.
|
||||
let fanout = work.join(".git/objects").join(&blob[0..2]);
|
||||
let mut perms = std::fs::metadata(&fanout).unwrap().permissions();
|
||||
perms.set_mode(0o000);
|
||||
std::fs::set_permissions(&fanout, perms).unwrap();
|
||||
|
||||
let deadline = std::time::Instant::now() + std::time::Duration::from_secs(10);
|
||||
let res = super::object_size_bounded("git", &work, &blob, deadline);
|
||||
|
||||
let mut restore = std::fs::metadata(&fanout).unwrap().permissions();
|
||||
restore.set_mode(0o755);
|
||||
std::fs::set_permissions(&fanout, restore).unwrap();
|
||||
|
||||
assert!(
|
||||
matches!(res, Err(super::ProbeError::Transient(_))),
|
||||
"an unreadable object store is the retryable arm; got {res:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// #174 F5/U4: a corrupt LOOSE object makes `git cat-file --batch-check` print
|
||||
/// `<oid> missing` on stdout (exit 0) yet emit `error:` diagnostics on stderr. The
|
||||
/// clean-`missing` absence path must NOT fire here — the `error:` line disqualifies
|
||||
|
||||
@@ -5,41 +5,12 @@
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::atomic::AtomicBool;
|
||||
use std::sync::{Arc, Mutex, OnceLock};
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use aws_sdk_s3::Client as S3Client;
|
||||
use tracing::{debug, info};
|
||||
|
||||
/// The precondition an upload is fenced on.
|
||||
///
|
||||
/// Object storage is the only place a fence can hold. Dropping the future of an
|
||||
/// in-flight PUT does not cancel the request the server is already processing,
|
||||
/// so no amount of local locking stops an abandoned writer's bytes from landing
|
||||
/// after a successor has published. A conditional PUT the store itself refuses
|
||||
/// is what actually stops it.
|
||||
#[derive(Clone, Debug)]
|
||||
pub enum UploadPrecondition {
|
||||
/// Publish only if the stored object is still the generation we observed.
|
||||
IfMatch(String),
|
||||
/// Publish only if nothing is stored under the key yet.
|
||||
IfAbsent,
|
||||
/// No fence. Last writer wins.
|
||||
Unconditional,
|
||||
}
|
||||
|
||||
/// Why an upload failed, split so a caller can tell "someone else already
|
||||
/// published this key" (expected, and dropping our bytes is the correct
|
||||
/// outcome) from a real storage failure.
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum UploadError {
|
||||
#[error("upload precondition lost (HTTP {status})")]
|
||||
PreconditionLost { status: u16 },
|
||||
#[error(transparent)]
|
||||
Other(#[from] anyhow::Error),
|
||||
}
|
||||
|
||||
/// Wrapper around the S3 client with the configured bucket.
|
||||
#[derive(Clone)]
|
||||
pub struct TigrisClient {
|
||||
@@ -60,29 +31,21 @@ impl TigrisClient {
|
||||
})
|
||||
}
|
||||
|
||||
/// Build a client pointed at an arbitrary endpoint, for tests.
|
||||
///
|
||||
/// The production constructor reads the endpoint and credentials from the
|
||||
/// environment, which a test cannot steer without mutating process-global
|
||||
/// state. This takes both explicitly so a test can aim the client at a
|
||||
/// closed port and get a prompt transport error out of `exists()`.
|
||||
///
|
||||
/// `RetryConfig::disabled()` is load-bearing, not tidiness: the SDK's default
|
||||
/// policy retries a connection refusal with backoff, which turns each failing
|
||||
/// call into seconds of waiting.
|
||||
/// Test-only constructor with an explicit S3 endpoint, region, and static
|
||||
/// credentials — no env-var reads, so parallel tests cannot race each other's
|
||||
/// `AWS_*` environment the way the env-based `new` would. Lets a test point
|
||||
/// the client at a non-routable endpoint to exercise acquire-stall paths.
|
||||
#[cfg(test)]
|
||||
pub fn for_testing_with_endpoint(bucket: &str, endpoint: &str) -> Self {
|
||||
use aws_sdk_s3::config::{retry::RetryConfig, Credentials, Region};
|
||||
|
||||
let config = aws_sdk_s3::config::Config::builder()
|
||||
.endpoint_url(endpoint)
|
||||
.credentials_provider(Credentials::new("test", "test", None, None, "test"))
|
||||
.region(Region::new("auto"))
|
||||
.retry_config(RetryConfig::disabled())
|
||||
.behavior_version_latest()
|
||||
.build();
|
||||
pub(crate) async fn for_testing_with_endpoint(bucket: &str, endpoint_url: &str) -> Self {
|
||||
let creds = aws_sdk_s3::config::Credentials::new("test", "test", None, None, "test");
|
||||
let config = aws_config::defaults(aws_config::BehaviorVersion::latest())
|
||||
.endpoint_url(endpoint_url)
|
||||
.region(aws_config::Region::new("auto"))
|
||||
.credentials_provider(creds)
|
||||
.load()
|
||||
.await;
|
||||
Self {
|
||||
s3: S3Client::from_conf(config),
|
||||
s3: S3Client::new(&config),
|
||||
bucket: bucket.to_string(),
|
||||
}
|
||||
}
|
||||
@@ -114,47 +77,8 @@ impl TigrisClient {
|
||||
}
|
||||
}
|
||||
|
||||
/// Read the ETag of a repo archive, or `None` when nothing is stored under
|
||||
/// the key. The ETag identifies the generation a later conditional upload
|
||||
/// can fence itself on.
|
||||
///
|
||||
/// Separate from `exists` rather than folded into it: `exists` has callers
|
||||
/// that only want the boolean, and widening its return type would churn
|
||||
/// every one of them for no benefit.
|
||||
pub async fn head_etag(&self, owner_slug: &str, repo_name: &str) -> Result<Option<String>> {
|
||||
let key = Self::repo_key(owner_slug, repo_name);
|
||||
match self
|
||||
.s3
|
||||
.head_object()
|
||||
.bucket(&self.bucket)
|
||||
.key(&key)
|
||||
.send()
|
||||
.await
|
||||
{
|
||||
Ok(out) => Ok(Some(
|
||||
out.e_tag()
|
||||
.context(format!("tigris HEAD {key}: hit carried no ETag"))?
|
||||
.to_string(),
|
||||
)),
|
||||
Err(e) => {
|
||||
if e.as_service_error().is_some_and(|e| e.is_not_found()) {
|
||||
Ok(None)
|
||||
} else {
|
||||
Err(anyhow::anyhow!("tigris HEAD {key}: {e}"))
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Upload a local bare repo directory to Tigris as a tar.zst archive,
|
||||
/// fenced by `precondition`.
|
||||
pub async fn upload(
|
||||
&self,
|
||||
owner_slug: &str,
|
||||
repo_name: &str,
|
||||
local_path: &Path,
|
||||
precondition: UploadPrecondition,
|
||||
) -> std::result::Result<(), UploadError> {
|
||||
/// Upload a local bare repo directory to Tigris as a tar.zst archive.
|
||||
pub async fn upload(&self, owner_slug: &str, repo_name: &str, local_path: &Path) -> Result<()> {
|
||||
let key = Self::repo_key(owner_slug, repo_name);
|
||||
debug!(key = %key, path = %local_path.display(), "uploading repo to tigris");
|
||||
|
||||
@@ -169,57 +93,15 @@ impl TigrisClient {
|
||||
|
||||
let body = aws_sdk_s3::primitives::ByteStream::from(archive_bytes);
|
||||
|
||||
let mut req = self
|
||||
.s3
|
||||
self.s3
|
||||
.put_object()
|
||||
.bucket(&self.bucket)
|
||||
.key(&key)
|
||||
.body(body)
|
||||
.content_type("application/zstd");
|
||||
match &precondition {
|
||||
UploadPrecondition::IfMatch(etag) => req = req.if_match(etag),
|
||||
UploadPrecondition::IfAbsent => req = req.if_none_match("*"),
|
||||
UploadPrecondition::Unconditional => {}
|
||||
}
|
||||
|
||||
if let Err(e) = req.send().await {
|
||||
// `PutObjectError` models no PreconditionFailed variant (its arms are
|
||||
// EncryptionTypeMismatch, InvalidRequest, InvalidWriteOffset,
|
||||
// TooManyParts, Unhandled), so a refused precondition arrives as
|
||||
// `Unhandled` and matching the enum would classify it as a generic
|
||||
// failure. The raw HTTP status off the response is the only place the
|
||||
// answer actually lives.
|
||||
//
|
||||
// Read it via `raw_response()`, not a `ServiceError`-only match: the
|
||||
// SDK exposes the raw response for BOTH `ServiceError` and
|
||||
// `ResponseError`, and a refused conditional PUT whose error body the
|
||||
// SDK cannot parse (malformed XML, premature close) surfaces as
|
||||
// `ResponseError`. Matching only `ServiceError` would classify that
|
||||
// unparsable 409/412 as a generic failure, and `RepoWriteGuard::release`
|
||||
// would log-and-succeed instead of taking the supersede retry,
|
||||
// acknowledging a write that was definitively not published.
|
||||
let status = e.raw_response().map(|raw| raw.status().as_u16());
|
||||
// 412 is always a lost precondition. 409 is one only when we asked
|
||||
// for create-only, which is how S3-compatible stores report "the key
|
||||
// already exists". Everything else, 404 included, is a real failure:
|
||||
// archive keys are never deleted (`delete` has no callers), so a 404
|
||||
// here means something permanent like a missing bucket or a
|
||||
// misrouted endpoint, and reporting that as a lost precondition
|
||||
// would tell a caller to expect a successor that does not exist.
|
||||
let lost = match status {
|
||||
Some(412) => true,
|
||||
Some(409) => matches!(precondition, UploadPrecondition::IfAbsent),
|
||||
_ => false,
|
||||
};
|
||||
if lost {
|
||||
return Err(UploadError::PreconditionLost {
|
||||
status: status.expect("a lost precondition came from a status"),
|
||||
});
|
||||
}
|
||||
return Err(UploadError::Other(
|
||||
anyhow::Error::new(e).context(format!("tigris PUT {key}")),
|
||||
));
|
||||
}
|
||||
.content_type("application/zstd")
|
||||
.send()
|
||||
.await
|
||||
.context(format!("tigris PUT {key}"))?;
|
||||
|
||||
info!(key = %key, "uploaded repo to tigris");
|
||||
Ok(())
|
||||
@@ -230,32 +112,10 @@ impl TigrisClient {
|
||||
&self,
|
||||
owner_slug: &str,
|
||||
repo_name: &str,
|
||||
local_path: &super::repo_store::ValidatedRepoDiskPath,
|
||||
swap_authority: Option<Arc<AtomicBool>>,
|
||||
local_path: &Path,
|
||||
) -> Result<()> {
|
||||
self.download_to(owner_slug, repo_name, local_path, true, swap_authority)
|
||||
.await
|
||||
.map(|_| ())
|
||||
}
|
||||
|
||||
/// Download a repo archive from Tigris and extract it, returning the
|
||||
/// directory that was populated.
|
||||
///
|
||||
/// `publish` controls whether the extract is swapped into `target` in place
|
||||
/// (the live-path mutation used by writes; returns `target`) or unpacked
|
||||
/// into a fresh temp directory under `target`'s parent (a non-mutating
|
||||
/// snapshot read; returns the temp dir, which the caller owns and cleans
|
||||
/// up). The snapshot form never touches the live repo path.
|
||||
pub async fn download_to(
|
||||
&self,
|
||||
owner_slug: &str,
|
||||
repo_name: &str,
|
||||
target: &super::repo_store::ValidatedRepoDiskPath,
|
||||
publish: bool,
|
||||
swap_authority: Option<Arc<AtomicBool>>,
|
||||
) -> Result<DownloadExtract> {
|
||||
let key = Self::repo_key(owner_slug, repo_name);
|
||||
debug!(key = %key, path = %target.as_path().display(), "downloading repo from tigris");
|
||||
debug!(key = %key, path = %local_path.display(), "downloading repo from tigris");
|
||||
|
||||
let resp = self
|
||||
.s3
|
||||
@@ -273,62 +133,21 @@ impl TigrisClient {
|
||||
.context("reading tigris response body")?
|
||||
.into_bytes();
|
||||
|
||||
// The snapshot temp dir is decided HERE, in the async layer, before the
|
||||
// extraction runs. Cleanup ownership moves into the blocking task so a
|
||||
// cancelled async future cannot drop it while extraction is still running.
|
||||
let snapshot_tmp = if publish {
|
||||
None
|
||||
} else {
|
||||
let parent = target.parent().context("snapshot path has no parent")?;
|
||||
std::fs::create_dir_all(parent).context("creating parent dir")?;
|
||||
let file_name = target
|
||||
.file_name()
|
||||
.context("snapshot path has no file name")?
|
||||
.to_string_lossy();
|
||||
Some(parent.join(format!(
|
||||
".{file_name}.tmp-snapshot.{}",
|
||||
uuid::Uuid::new_v4()
|
||||
)))
|
||||
};
|
||||
|
||||
// Extract tar.zst to a directory.
|
||||
let extracted = tokio::task::spawn_blocking({
|
||||
let target = target.clone();
|
||||
let snapshot_tmp = snapshot_tmp.clone();
|
||||
move || -> Result<DownloadExtract> {
|
||||
let result = (|| -> Result<DownloadExtract> {
|
||||
if publish {
|
||||
decompress_repo(&data, &target, swap_authority.as_ref())?;
|
||||
return Ok(DownloadExtract::Published(()));
|
||||
}
|
||||
// Non-mutating snapshot: unpack into the temp dir decided above.
|
||||
// The live repo path is never touched.
|
||||
let tmp_dir = snapshot_tmp.expect("snapshot path was decided above");
|
||||
std::fs::create_dir_all(&tmp_dir).context("creating temp extract dir")?;
|
||||
let unpack = (|| -> Result<()> {
|
||||
let decoder = zstd::stream::Decoder::new(&data[..])?;
|
||||
let mut archive = tar::Archive::new(decoder);
|
||||
archive.unpack(&tmp_dir).context("unpacking tar.zst")?;
|
||||
Ok(())
|
||||
})();
|
||||
if let Err(e) = unpack {
|
||||
let _ = std::fs::remove_dir_all(&tmp_dir);
|
||||
return Err(e);
|
||||
}
|
||||
Ok(DownloadExtract::Snapshot(TempSnapshotDir { path: tmp_dir }))
|
||||
})();
|
||||
result
|
||||
}
|
||||
// Extract tar.zst to local path
|
||||
tokio::task::spawn_blocking({
|
||||
let local_path = local_path.to_path_buf();
|
||||
move || decompress_repo(&data, &local_path)
|
||||
})
|
||||
.await
|
||||
.context("extract task panicked")?
|
||||
.context("extracting repo")?;
|
||||
|
||||
info!(key = %key, path = %target.as_path().display(), "downloaded repo from tigris");
|
||||
Ok(extracted)
|
||||
info!(key = %key, path = %local_path.display(), "downloaded repo from tigris");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Delete a repo archive from Tigris.
|
||||
#[allow(dead_code)]
|
||||
pub async fn delete(&self, owner_slug: &str, repo_name: &str) -> Result<()> {
|
||||
let key = Self::repo_key(owner_slug, repo_name);
|
||||
self.s3
|
||||
@@ -361,7 +180,7 @@ fn compress_repo(repo_path: &Path) -> Result<Vec<u8>> {
|
||||
/// `decompress_repo`. Concurrent extractions unpack into isolated temp dirs in
|
||||
/// parallel, but the final `remove_dir_all` + `rename` must not interleave for
|
||||
/// the same `local_path`, or they race to a nondeterministic overwrite/failure.
|
||||
pub(crate) fn publish_lock(local_path: &Path) -> Arc<Mutex<()>> {
|
||||
fn publish_lock(local_path: &Path) -> Arc<Mutex<()>> {
|
||||
// KNOWN LIMITATION: this map is never evicted — one (PathBuf, Arc<Mutex>)
|
||||
// entry accrues per distinct repo path for the process lifetime. Bounded by
|
||||
// the number of repos a node hosts, so it's negligible for normal use, but
|
||||
@@ -374,35 +193,6 @@ pub(crate) fn publish_lock(local_path: &Path) -> Arc<Mutex<()>> {
|
||||
.clone()
|
||||
}
|
||||
|
||||
/// Owns a snapshot temp dir from extraction through handoff to [`RepoSnapshot`].
|
||||
/// Dropped when the `spawn_blocking` join result is abandoned, so cancellation
|
||||
/// before the outer future resumes still removes the directory.
|
||||
pub(crate) struct TempSnapshotDir {
|
||||
path: PathBuf,
|
||||
}
|
||||
|
||||
impl TempSnapshotDir {
|
||||
pub(crate) fn into_repo_snapshot(self) -> super::repo_store::RepoSnapshot {
|
||||
let path = self.path.clone();
|
||||
std::mem::forget(self);
|
||||
super::repo_store::RepoSnapshot::from_owned_path(path)
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for TempSnapshotDir {
|
||||
fn drop(&mut self) {
|
||||
let _ = std::fs::remove_dir_all(&self.path);
|
||||
}
|
||||
}
|
||||
|
||||
/// What [`TigrisClient::download_to`] produced.
|
||||
pub enum DownloadExtract {
|
||||
/// Published into the validated live repo path.
|
||||
Published(()),
|
||||
/// Unpacked into a throwaway temp dir that cleans up on drop until adopted.
|
||||
Snapshot(TempSnapshotDir),
|
||||
}
|
||||
|
||||
/// Decompress a tar.zst byte vector into a local directory.
|
||||
///
|
||||
/// Extraction is atomic with respect to `local_path`: the archive is unpacked
|
||||
@@ -410,16 +200,11 @@ pub enum DownloadExtract {
|
||||
/// fully succeeds. A corrupt or truncated archive therefore can never clobber a
|
||||
/// good existing copy at `local_path` — on failure we discard the temp dir and
|
||||
/// leave `local_path` exactly as it was.
|
||||
fn decompress_repo(
|
||||
data: &[u8],
|
||||
local_path: &super::repo_store::ValidatedRepoDiskPath,
|
||||
swap_authority: Option<&Arc<AtomicBool>>,
|
||||
) -> Result<()> {
|
||||
let live = local_path.as_path();
|
||||
let parent = live.parent().context("repo path has no parent")?;
|
||||
fn decompress_repo(data: &[u8], local_path: &Path) -> Result<()> {
|
||||
let parent = local_path.parent().context("repo path has no parent")?;
|
||||
std::fs::create_dir_all(parent).context("creating parent dir")?;
|
||||
|
||||
let file_name = live
|
||||
let file_name = local_path
|
||||
.file_name()
|
||||
.context("repo path has no file name")?
|
||||
.to_string_lossy();
|
||||
@@ -444,218 +229,17 @@ fn decompress_repo(
|
||||
return Err(e);
|
||||
}
|
||||
|
||||
// Swap through the validated-path helper so CodeQL sees the barrier before the
|
||||
// remove/rename sink (`rust/path-injection`).
|
||||
super::repo_store::swap_extracted_into_validated_repo(local_path, &tmp_dir, swap_authority)?;
|
||||
// Swap the freshly-extracted repo into place. rename within the same parent
|
||||
// is effectively atomic, but most platforms refuse to rename onto a
|
||||
// non-empty dir, so remove the old copy first. Serialize this per repo path:
|
||||
// concurrent extractions unpack into isolated temp dirs, but their swaps
|
||||
// must not interleave or they race to a nondeterministic overwrite/failure.
|
||||
let lock = publish_lock(local_path);
|
||||
let _publish = lock.lock().expect("publish lock poisoned");
|
||||
if local_path.exists() {
|
||||
std::fs::remove_dir_all(local_path).context("removing stale repo dir")?;
|
||||
}
|
||||
std::fs::rename(&tmp_dir, local_path).context("swapping extracted repo into place")?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use aws_sdk_s3::primitives::ByteStream;
|
||||
use futures::FutureExt;
|
||||
|
||||
/// The envs the probe needs, all of them, or it does not run.
|
||||
///
|
||||
/// `AWS_ENDPOINT_URL_S3` is included on purpose: without it the SDK resolves
|
||||
/// to real AWS S3, and a probe that passed there would say nothing about
|
||||
/// Tigris.
|
||||
fn probe_env() -> Option<String> {
|
||||
if std::env::var("GITLAWB_TIGRIS_PROBE").ok().as_deref() != Some("1") {
|
||||
return None;
|
||||
}
|
||||
for name in [
|
||||
"AWS_ACCESS_KEY_ID",
|
||||
"AWS_SECRET_ACCESS_KEY",
|
||||
"AWS_ENDPOINT_URL_S3",
|
||||
] {
|
||||
if std::env::var(name).is_err() {
|
||||
eprintln!("tigris conditional-write probe: {name} is unset, skipping");
|
||||
return None;
|
||||
}
|
||||
}
|
||||
match std::env::var("GITLAWB_TIGRIS_BUCKET") {
|
||||
Ok(b) if !b.is_empty() => Some(b),
|
||||
_ => {
|
||||
eprintln!(
|
||||
"tigris conditional-write probe: GITLAWB_TIGRIS_BUCKET is unset, skipping"
|
||||
);
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// One conditional PUT, reported as the status that REFUSED it, or `None`
|
||||
/// when the store accepted the write.
|
||||
///
|
||||
/// Accepted is the interesting answer here, not an error: it means the
|
||||
/// endpoint ignored the header we fenced on.
|
||||
async fn conditional_put(
|
||||
s3: &S3Client,
|
||||
bucket: &str,
|
||||
key: &str,
|
||||
body: &'static [u8],
|
||||
if_match: Option<&str>,
|
||||
if_none_match: Option<&str>,
|
||||
) -> Result<Option<u16>, String> {
|
||||
let mut req = s3
|
||||
.put_object()
|
||||
.bucket(bucket)
|
||||
.key(key)
|
||||
.body(ByteStream::from_static(body));
|
||||
if let Some(v) = if_match {
|
||||
req = req.if_match(v);
|
||||
}
|
||||
if let Some(v) = if_none_match {
|
||||
req = req.if_none_match(v);
|
||||
}
|
||||
match req.send().await {
|
||||
Ok(_) => Ok(None),
|
||||
Err(e) => match e.raw_response() {
|
||||
// Same raw-response rule as `upload`: a refused conditional PUT
|
||||
// whose body the SDK cannot parse surfaces as `ResponseError`, and
|
||||
// the status has to come off the raw response for both variants.
|
||||
// Without it, an unparsable 409/412 would report "no HTTP
|
||||
// response" here and skip the supersede retry.
|
||||
Some(raw) => Ok(Some(raw.status().as_u16())),
|
||||
None => Err(format!("conditional PUT {key}: no HTTP response: {e}")),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/// The probe body, written to RETURN its failures rather than panic on
|
||||
/// them, so the caller's cleanup is reached on every arm.
|
||||
async fn conditional_write_probe(s3: &S3Client, bucket: &str, key: &str) -> Result<(), String> {
|
||||
// 1. A plain PUT under a throwaway key.
|
||||
let seeded = s3
|
||||
.put_object()
|
||||
.bucket(bucket)
|
||||
.key(key)
|
||||
.body(ByteStream::from_static(b"probe-one"))
|
||||
.send()
|
||||
.await
|
||||
.map_err(|e| format!("seeding PUT {key}: {e}"))?;
|
||||
|
||||
// 2. Its ETag, which is the generation the next arm fences against.
|
||||
let etag = seeded
|
||||
.e_tag()
|
||||
.ok_or_else(|| format!("seeding PUT {key} returned no ETag"))?
|
||||
.to_string();
|
||||
|
||||
// 3. A deliberately wrong If-Match. A store honoring it answers 412.
|
||||
let wrong = format!("\"{}\"", "0".repeat(32));
|
||||
if etag.trim_matches('"') == wrong.trim_matches('"') {
|
||||
return Err(format!(
|
||||
"the seeded ETag {etag} collides with the deliberately wrong one, \
|
||||
so this arm would prove nothing"
|
||||
));
|
||||
}
|
||||
match conditional_put(s3, bucket, key, b"probe-two", Some(&wrong), None).await? {
|
||||
Some(412) => {}
|
||||
Some(status) => {
|
||||
return Err(format!(
|
||||
"a stale If-Match must be refused with 412, the endpoint answered {status}"
|
||||
))
|
||||
}
|
||||
None => {
|
||||
return Err(
|
||||
"a stale If-Match was ACCEPTED: this endpoint does not honor If-Match, so \
|
||||
the release fence cannot hold here"
|
||||
.to_string(),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
// 4. If-None-Match `*` over the object that now exists. This arm matters
|
||||
// MORE than the one above. An ignored If-Match eventually surfaces as
|
||||
// odd behavior, because a stale writer overwrites and someone notices
|
||||
// the lost tree. An ignored If-None-Match just returns 200, so a publish
|
||||
// that should have been fenced lands with no error anywhere: the silent
|
||||
// no-op the bucket-type caveat on this test describes.
|
||||
match conditional_put(s3, bucket, key, b"probe-three", None, Some("*")).await? {
|
||||
// Either status is a pass, and the asymmetry with the If-Match arm
|
||||
// above mirrors `upload`'s classifier exactly: 412 is always a lost
|
||||
// precondition, and 409 is one too when we asked for create-only.
|
||||
// AWS documents 409 for a create-only conflict racing a delete, so a
|
||||
// store answering it is enforcing the precondition and we already
|
||||
// handle it. Pinning 412 alone here would fail the probe against a
|
||||
// backend that is behaving correctly, which sends whoever runs it
|
||||
// chasing a fault that is not there.
|
||||
Some(412) | Some(409) => {}
|
||||
Some(status) => {
|
||||
return Err(format!(
|
||||
"create-only over an existing object must be refused with 412 or 409, \
|
||||
the endpoint answered {status}"
|
||||
))
|
||||
}
|
||||
None => {
|
||||
return Err(
|
||||
"If-None-Match * was ACCEPTED over an existing object: this endpoint does \
|
||||
not honor create-only, so a fenced publish lands silently"
|
||||
.to_string(),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Probe the REAL Tigris endpoint for the conditional-write semantics the
|
||||
/// release fence depends on.
|
||||
///
|
||||
/// UNTIL THIS IS RUN AGAINST REAL CREDENTIALS, the fence is verified against
|
||||
/// vendor documentation and an in-process mock, not against the backend it
|
||||
/// runs on. The mock implements the semantics we believe Tigris has; it
|
||||
/// cannot tell us whether Tigris actually has them.
|
||||
///
|
||||
/// The bucket matters, not just the endpoint. Tigris documents conditional
|
||||
/// operations as supported on Single-region and Multi-region buckets only.
|
||||
/// Global and Dual-region buckets are eventually consistent, and a
|
||||
/// conditional PUT evaluated against a stale replica would make the fence a
|
||||
/// silent no-op rather than an error. So point `GITLAWB_TIGRIS_BUCKET` at a
|
||||
/// throwaway bucket of the SAME type production uses.
|
||||
///
|
||||
/// Ignored by default and additionally gated on `GITLAWB_TIGRIS_PROBE=1`,
|
||||
/// because it writes to a real bucket and costs real requests. Run with:
|
||||
/// `GITLAWB_TIGRIS_PROBE=1 cargo test -p gitlawb-node --bin gitlawb-node
|
||||
/// tigris_honors_conditional_writes -- --ignored --nocapture`
|
||||
#[tokio::test]
|
||||
#[ignore = "writes to a real Tigris bucket; needs GITLAWB_TIGRIS_PROBE=1 plus credentials"]
|
||||
async fn tigris_honors_conditional_writes() {
|
||||
let Some(bucket) = probe_env() else {
|
||||
eprintln!(
|
||||
"tigris conditional-write probe: skipped. Set GITLAWB_TIGRIS_PROBE=1, \
|
||||
GITLAWB_TIGRIS_BUCKET, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and \
|
||||
AWS_ENDPOINT_URL_S3 to run it."
|
||||
);
|
||||
return;
|
||||
};
|
||||
|
||||
let config = aws_config::load_defaults(aws_config::BehaviorVersion::latest()).await;
|
||||
let s3 = S3Client::new(&config);
|
||||
// A fresh key per run, so a probe that somehow orphaned an object on an
|
||||
// earlier run cannot change what this one observes.
|
||||
let key = format!("probe/conditional-write-{}.bin", uuid::Uuid::new_v4());
|
||||
|
||||
// CLEANUP MUST RUN ON EVERY ARM, and a failing assertion is precisely
|
||||
// the case this probe exists to catch, so the delete cannot sit after
|
||||
// the checks. The body returns its failures rather than panicking, and
|
||||
// `catch_unwind` covers the panic an SDK call could still raise; either
|
||||
// way the delete below is reached before the verdict is re-raised.
|
||||
let outcome = std::panic::AssertUnwindSafe(conditional_write_probe(&s3, &bucket, &key))
|
||||
.catch_unwind()
|
||||
.await;
|
||||
|
||||
if let Err(e) = s3.delete_object().bucket(&bucket).key(&key).send().await {
|
||||
eprintln!("tigris conditional-write probe: cleanup of {key} failed: {e}");
|
||||
}
|
||||
|
||||
match outcome {
|
||||
Ok(Ok(())) => {}
|
||||
Ok(Err(msg)) => panic!("tigris conditional-write probe: {msg}"),
|
||||
Err(payload) => std::panic::resume_unwind(payload),
|
||||
}
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large.
Load diff
+20
-2458
File diff suppressed because it is too large.
Load diff
+61
-497
@@ -31,7 +31,6 @@ use axum::response::IntoResponse;
|
||||
use axum::routing::get;
|
||||
use axum::{Json, Router};
|
||||
use clap::Parser;
|
||||
use std::collections::HashSet;
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::sync::Arc;
|
||||
use tokio::net::TcpListener;
|
||||
@@ -90,7 +89,6 @@ async fn main() -> Result<()> {
|
||||
|
||||
// Load or generate the node's identity keypair
|
||||
let keypair = load_or_create_keypair(&config)?;
|
||||
let scan_token_key = AppState::derive_scan_token_key(&keypair);
|
||||
let node_did = keypair.did();
|
||||
|
||||
// One-time metrics init. Must run before any handler that calls into
|
||||
@@ -288,20 +286,8 @@ async fn main() -> Result<()> {
|
||||
None
|
||||
};
|
||||
|
||||
// Advisory-lock connections come from their own pool: a write guard pins one
|
||||
// for its whole lifetime, and sharing the application pool would let a push
|
||||
// burst starve ordinary request handlers.
|
||||
let lock_pool = db::Db::lock_pool(
|
||||
&config.database_url,
|
||||
config.db_lock_pool_max_connections,
|
||||
std::time::Duration::from_secs(config.db_acquire_timeout_secs),
|
||||
)?;
|
||||
let repo_store = git::repo_store::RepoStore::new(
|
||||
config.repos_dir.clone(),
|
||||
tigris,
|
||||
lock_pool,
|
||||
std::time::Duration::from_secs(config.lock_held_transfer_timeout_secs),
|
||||
);
|
||||
let repo_store =
|
||||
git::repo_store::RepoStore::new(config.repos_dir.clone(), tigris, db.pool().clone());
|
||||
|
||||
// Per-DID limiter for the creation endpoints. Keyed on the authenticated
|
||||
// DID (attacker-varied), so bound its key set to cap memory.
|
||||
@@ -346,23 +332,6 @@ async fn main() -> Result<()> {
|
||||
tracing::warn!("GITLAWB_PUSH_RATE_LIMIT=0 — per-IP push rate limiting disabled");
|
||||
}
|
||||
|
||||
// close_issue drives a full archive download for non-owner author pre-checks.
|
||||
// Keep it on its own bucket so it cannot drain the receive-pack limit.
|
||||
let close_issue_limit = std::env::var("GITLAWB_CLOSE_ISSUE_RATE_LIMIT")
|
||||
.ok()
|
||||
.and_then(|v| v.trim().parse::<usize>().ok())
|
||||
.unwrap_or(120);
|
||||
let close_issue_rate_limiter = rate_limit::RateLimiter::new_bounded(
|
||||
close_issue_limit,
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
);
|
||||
if close_issue_limit == 0 {
|
||||
tracing::warn!(
|
||||
"GITLAWB_CLOSE_ISSUE_RATE_LIMIT=0 — per-IP close_issue rate limiting disabled"
|
||||
);
|
||||
}
|
||||
|
||||
// Which forwarded header the edge is trusted to set. Default None (trust
|
||||
// nothing, key on the socket peer). Fly nodes set GITLAWB_TRUSTED_PROXY=fly;
|
||||
// a node behind Caddy/NGINX sets it to x-forwarded-for.
|
||||
@@ -412,14 +381,6 @@ async fn main() -> Result<()> {
|
||||
rate_limiter,
|
||||
create_ip_rate_limiter,
|
||||
push_rate_limiter,
|
||||
close_issue_rate_limiter,
|
||||
ipfs_max_history_walks: crate::api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST,
|
||||
ipfs_max_legacy_probes: AppState::ipfs_legacy_probe_budget(&config),
|
||||
ipfs_legacy_scan_page_rows: crate::api::ipfs::LEGACY_SCAN_PAGE_ROWS,
|
||||
ipfs_max_legacy_scan_rows: AppState::ipfs_legacy_scan_row_budget(&config),
|
||||
ipfs_max_legacy_scan_rule_bytes: crate::api::ipfs::MAX_LEGACY_SCAN_RULE_BYTES_PER_REQUEST,
|
||||
ipfs_scan_token_key: Arc::new(scan_token_key),
|
||||
ipfs_max_served_object_bytes: crate::api::ipfs::MAX_SERVED_OBJECT_BYTES,
|
||||
push_limiter_trust,
|
||||
sync_trigger_rate_limiter,
|
||||
peer_write_rate_limiter,
|
||||
@@ -494,11 +455,6 @@ async fn main() -> Result<()> {
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
),
|
||||
ipfs_work_rate_limiter: rate_limit::RateLimiter::new_bounded(
|
||||
AppState::ipfs_work_budget(&config),
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
),
|
||||
git_bin: "git".to_string(),
|
||||
};
|
||||
if config.ipfs_rate_limit == 0 {
|
||||
@@ -540,7 +496,7 @@ async fn main() -> Result<()> {
|
||||
loop {
|
||||
tokio::select! {
|
||||
_ = tokio::time::sleep(std::time::Duration::from_secs(300)) => {
|
||||
sweep_state.sweep_rate_limiters().await;
|
||||
sweep_rate_limiters(&sweep_state).await;
|
||||
let now = std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.map(|d| d.as_secs() as i64)
|
||||
@@ -559,8 +515,6 @@ async fn main() -> Result<()> {
|
||||
});
|
||||
}
|
||||
|
||||
let _legacy_cid_sweep = spawn_legacy_cid_sweep(&state, &config);
|
||||
|
||||
let router = server::build_router(state.clone());
|
||||
// Re-register the socket bound at startup — same fd, so there was never a
|
||||
// moment with the port closed between the degraded and full servers.
|
||||
@@ -852,8 +806,8 @@ fn build_degraded_router(node_did: String, db_startup: Arc<DbStartupStatus>) ->
|
||||
db_startup,
|
||||
};
|
||||
// Everything answers 503 with the same body — including /health and
|
||||
// /ready, so peer readiness probes and uptime monitors correctly see a
|
||||
// node that cannot serve traffic.
|
||||
// /ready, so peer pings (which treat any 2xx /health as alive) and
|
||||
// uptime monitors correctly see a node that cannot serve traffic.
|
||||
// `/` additionally carries the node identity for probing peers.
|
||||
Router::new()
|
||||
.route("/", get(degraded_node_info))
|
||||
@@ -985,7 +939,7 @@ async fn gossip_task(
|
||||
}
|
||||
|
||||
// Reuse the shared no-redirect client for every gossip outbound call (the
|
||||
// bootstrap announce POST and the periodic peer /ready ping). Peer URLs are
|
||||
// bootstrap announce POST and the periodic peer /health ping). Peer URLs are
|
||||
// attacker-influenceable, so a 3xx to a private address must not be followed.
|
||||
// Do NOT fall back to reqwest::Client::new(): its default follows redirects
|
||||
// and would reintroduce the SSRF closed here (#93).
|
||||
@@ -1040,33 +994,8 @@ async fn gossip_task(
|
||||
json.get("node_url").and_then(|v| v.as_str()),
|
||||
) {
|
||||
if !their_url.is_empty() {
|
||||
// Unproven, unconditionally: their_did and
|
||||
// their_url come straight out of the contacted
|
||||
// peer's JSON response body, with no signature
|
||||
// and no proof the claimed DID belongs to the
|
||||
// peer we reached. This path therefore seeds
|
||||
// new peers and can never repoint an existing
|
||||
// row. The upsert's result is matched rather
|
||||
// than discarded, because "bootstrap peer
|
||||
// added" printed over a refused write is a
|
||||
// denial rendering as success. Non-fatal to the
|
||||
// loop either way.
|
||||
match state
|
||||
.db
|
||||
.upsert_peer(
|
||||
their_did,
|
||||
their_url,
|
||||
db::PeerWriteAuthority::Unproven,
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => {
|
||||
tracing::info!(did = %their_did, url = %their_url, "bootstrap peer added")
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!(did = %their_did, url = %their_url, err = %e, "bootstrap peer announce-back rejected")
|
||||
}
|
||||
}
|
||||
let _ = state.db.upsert_peer(their_did, their_url).await;
|
||||
tracing::info!(did = %their_did, url = %their_url, "bootstrap peer added");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1081,8 +1010,6 @@ async fn gossip_task(
|
||||
|
||||
// Periodic ping every 5 minutes — exit on shutdown.
|
||||
let mut interval = tokio::time::interval(std::time::Duration::from_secs(300));
|
||||
interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Delay);
|
||||
let mut failed_once: HashSet<String> = HashSet::new();
|
||||
loop {
|
||||
tokio::select! {
|
||||
_ = interval.tick() => {
|
||||
@@ -1090,13 +1017,10 @@ async fn gossip_task(
|
||||
Ok(p) => p,
|
||||
Err(_) => continue,
|
||||
};
|
||||
gossip_ping_round(
|
||||
state.db.as_ref(),
|
||||
client.as_ref(),
|
||||
&mut failed_once,
|
||||
peers,
|
||||
)
|
||||
.await;
|
||||
for peer in peers {
|
||||
let ok = ping_peer_health(&client, &peer.http_url).await;
|
||||
let _ = state.db.mark_peer_ping(&peer.did, ok).await;
|
||||
}
|
||||
}
|
||||
_ = shutdown_rx.changed() => {
|
||||
if *shutdown_rx.borrow() {
|
||||
@@ -1124,7 +1048,6 @@ mod rate_limiter_sweep_tests {
|
||||
state.rate_limiter = RateLimiter::new(10, window);
|
||||
state.create_ip_rate_limiter = RateLimiter::new(10, window);
|
||||
state.push_rate_limiter = RateLimiter::new(10, window);
|
||||
state.close_issue_rate_limiter = RateLimiter::new(10, window);
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(10, window);
|
||||
state.peer_write_rate_limiter = RateLimiter::new(10, window);
|
||||
state.ipfs_rate_limiter = RateLimiter::new(10, window);
|
||||
@@ -1134,7 +1057,6 @@ mod rate_limiter_sweep_tests {
|
||||
s.rate_limiter.clone(),
|
||||
s.create_ip_rate_limiter.clone(),
|
||||
s.push_rate_limiter.clone(),
|
||||
s.close_issue_rate_limiter.clone(),
|
||||
s.sync_trigger_rate_limiter.clone(),
|
||||
s.peer_write_rate_limiter.clone(),
|
||||
s.ipfs_rate_limiter.clone(),
|
||||
@@ -1146,7 +1068,7 @@ mod rate_limiter_sweep_tests {
|
||||
}
|
||||
|
||||
tokio::time::sleep(window * 3).await;
|
||||
state.sweep_rate_limiters().await;
|
||||
super::sweep_rate_limiters(&state).await;
|
||||
|
||||
for (i, l) in limiters(&state).into_iter().enumerate() {
|
||||
assert_eq!(l.tracked_keys().await, 0, "limiter {i} was not swept");
|
||||
@@ -1154,65 +1076,19 @@ mod rate_limiter_sweep_tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// it.
|
||||
fn spawn_legacy_cid_sweep(state: &AppState, config: &Config) -> tokio::task::JoinHandle<()> {
|
||||
let db = state.db.clone();
|
||||
let repos_dir = config.repos_dir.clone();
|
||||
let git_bin = state.git_bin.clone();
|
||||
let git_timeout = std::time::Duration::from_secs(config.git_service_timeout_secs);
|
||||
let batch = config.pin_repair_sweep_batch;
|
||||
let delay = std::time::Duration::from_secs(config.pin_repair_sweep_delay_secs);
|
||||
let mut shutdown_rx = state.subscribe_shutdown();
|
||||
tokio::spawn(async move {
|
||||
tokio::select! {
|
||||
_ = ipfs_pin::run_sweep_rearmed(
|
||||
&repos_dir, &git_bin, git_timeout, batch, delay,
|
||||
ipfs_pin::SWEEP_REARM_DELAY, &db,
|
||||
) => {}
|
||||
_ = shutdown_rx.changed() => {}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
async fn gossip_ping_round(
|
||||
db: &Db,
|
||||
client: &reqwest::Client,
|
||||
failed_once: &mut HashSet<String>,
|
||||
peers: Vec<db::PeerRecord>,
|
||||
) {
|
||||
{
|
||||
let current_dids: HashSet<&str> = peers.iter().map(|peer| peer.did.as_str()).collect();
|
||||
failed_once.retain(|did| current_dids.contains(did.as_str()));
|
||||
}
|
||||
for peer in peers {
|
||||
let ok = ping_peer_readiness(client, &peer.http_url).await;
|
||||
match peer_ping_db_update(failed_once, &peer.did, ok) {
|
||||
Some(reachable) => {
|
||||
if let Err(error) = db.mark_peer_ping(&peer.did, reachable).await {
|
||||
warn!(did = %peer.did, err = %error, "failed to persist peer readiness");
|
||||
}
|
||||
}
|
||||
None => warn!(
|
||||
did = %peer.did,
|
||||
"peer readiness probe failed once; preserving previous federation status"
|
||||
),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Decide whether one readiness sample should update the persisted federation
|
||||
/// gate. A success is authoritative immediately. A failure must repeat on the
|
||||
/// next gossip tick before it can mark a peer unreachable, so one transient
|
||||
/// database hiccup does not hide the peer's repositories for five minutes.
|
||||
fn peer_ping_db_update(failed_once: &mut HashSet<String>, did: &str, ready: bool) -> Option<bool> {
|
||||
if ready {
|
||||
failed_once.remove(did);
|
||||
Some(true)
|
||||
} else if failed_once.insert(did.to_owned()) {
|
||||
None
|
||||
} else {
|
||||
Some(false)
|
||||
}
|
||||
/// Evict expired entries from every per-key rate limiter on the state.
|
||||
///
|
||||
/// Named and driven off `AppState` so the periodic sweeper stays in step with
|
||||
/// the limiters the router actually mounts: adding a limiter field and
|
||||
/// forgetting it here leaves its keys pinned until the map hits `max_keys` and
|
||||
/// the inline capacity sweep runs (the `/ipfs` limiter was missed this way).
|
||||
async fn sweep_rate_limiters(state: &AppState) {
|
||||
state.rate_limiter.cleanup().await;
|
||||
state.create_ip_rate_limiter.cleanup().await;
|
||||
state.push_rate_limiter.cleanup().await;
|
||||
state.sync_trigger_rate_limiter.cleanup().await;
|
||||
state.peer_write_rate_limiter.cleanup().await;
|
||||
state.ipfs_rate_limiter.cleanup().await;
|
||||
}
|
||||
|
||||
/// Build the shared node HTTP client used for every outbound fan-out (sync
|
||||
@@ -1225,96 +1101,26 @@ fn peer_ping_db_update(failed_once: &mut HashSet<String>, did: &str, ready: bool
|
||||
/// runs, not a hand-rolled equivalent.
|
||||
fn build_http_client() -> reqwest::Result<reqwest::Client> {
|
||||
reqwest::Client::builder()
|
||||
.timeout(OUTBOUND_HTTP_TIMEOUT)
|
||||
.timeout(std::time::Duration::from_secs(10))
|
||||
.redirect(reqwest::redirect::Policy::none())
|
||||
.build()
|
||||
}
|
||||
|
||||
const OUTBOUND_HTTP_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
|
||||
|
||||
/// Ping a peer's DB-aware `/ready` endpoint and report whether it answered 2xx.
|
||||
///
|
||||
/// A 404 falls back to `/health` for compatibility with nodes released before
|
||||
/// `/ready` existed. Other readiness failures, including 503 during a database
|
||||
/// outage, fail closed and must not use the liveness-only endpoint. The complete
|
||||
/// `/ready`-then-`/health` probe shares one timeout budget.
|
||||
/// Ping a peer's `/health` endpoint and report whether it answered 2xx.
|
||||
///
|
||||
/// Takes the client by reference so callers supply the shared, no-redirect
|
||||
/// `state.http_client`. Peer URLs are attacker-influenceable, so a `3xx` to a
|
||||
/// private address must not be followed. Do NOT call this with a bare
|
||||
/// `reqwest::Client::new()`: its default follows redirects and would
|
||||
/// reintroduce the SSRF this guards against (#93).
|
||||
pub(crate) async fn ping_peer_readiness(client: &reqwest::Client, http_url: &str) -> bool {
|
||||
ping_peer_readiness_with_timeout(client, http_url, OUTBOUND_HTTP_TIMEOUT).await
|
||||
}
|
||||
|
||||
async fn ping_peer_readiness_with_timeout(
|
||||
client: &reqwest::Client,
|
||||
http_url: &str,
|
||||
timeout: std::time::Duration,
|
||||
) -> bool {
|
||||
let base_url = http_url.trim_end_matches('/');
|
||||
let result = tokio::time::timeout(timeout, async {
|
||||
let readiness = client.get(format!("{base_url}/ready")).send().await;
|
||||
|
||||
match readiness {
|
||||
Ok(response) if response.status().is_success() => true,
|
||||
Ok(response) if response.status() == reqwest::StatusCode::NOT_FOUND => {
|
||||
info!(
|
||||
peer_url = %http_url,
|
||||
"peer has no readiness endpoint; falling back to legacy health probe"
|
||||
);
|
||||
match client.get(format!("{base_url}/health")).send().await {
|
||||
Ok(response) if response.status().is_success() => true,
|
||||
Ok(response) => {
|
||||
warn!(
|
||||
peer_url = %http_url,
|
||||
status = %response.status(),
|
||||
"legacy peer health probe reported unhealthy"
|
||||
);
|
||||
false
|
||||
}
|
||||
Err(error) => {
|
||||
warn!(
|
||||
peer_url = %http_url,
|
||||
err = %error,
|
||||
"legacy peer health probe failed"
|
||||
);
|
||||
false
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(response) => {
|
||||
warn!(
|
||||
peer_url = %http_url,
|
||||
status = %response.status(),
|
||||
"peer readiness probe reported unready"
|
||||
);
|
||||
false
|
||||
}
|
||||
Err(error) => {
|
||||
warn!(
|
||||
peer_url = %http_url,
|
||||
err = %error,
|
||||
"peer readiness probe failed"
|
||||
);
|
||||
false
|
||||
}
|
||||
}
|
||||
})
|
||||
.await;
|
||||
|
||||
match result {
|
||||
Ok(ready) => ready,
|
||||
Err(_) => {
|
||||
warn!(
|
||||
peer_url = %http_url,
|
||||
timeout_ms = timeout.as_millis(),
|
||||
"peer readiness probe timed out"
|
||||
);
|
||||
false
|
||||
}
|
||||
}
|
||||
async fn ping_peer_health(client: &reqwest::Client, http_url: &str) -> bool {
|
||||
let url = format!("{}/health", http_url.trim_end_matches('/'));
|
||||
client
|
||||
.get(&url)
|
||||
.send()
|
||||
.await
|
||||
.map(|r| r.status().is_success())
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
fn load_or_create_keypair(config: &Config) -> Result<Keypair> {
|
||||
@@ -1352,130 +1158,20 @@ fn load_or_create_keypair(config: &Config) -> Result<Keypair> {
|
||||
|
||||
#[cfg(test)]
|
||||
mod gossip_ssrf_tests {
|
||||
use super::{
|
||||
gossip_ping_round, peer_ping_db_update, ping_peer_readiness,
|
||||
ping_peer_readiness_with_timeout,
|
||||
};
|
||||
use axum::{http::StatusCode, routing::get, Router};
|
||||
use sqlx::PgPool;
|
||||
use std::collections::HashSet;
|
||||
use std::sync::atomic::{AtomicUsize, Ordering};
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
use super::ping_peer_health;
|
||||
|
||||
// Build the client exactly as production does (super::build_http_client) so
|
||||
// these tests bind the redirect guarantee to the real shared client the
|
||||
// node runs. A regression that makes build_http_client follow redirects
|
||||
// fails ping_peer_readiness_does_not_follow_redirect.
|
||||
// fails ping_peer_health_does_not_follow_redirect.
|
||||
fn production_http_client() -> reqwest::Client {
|
||||
super::build_http_client().expect("failed to build production http client")
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn peer_ping_requires_two_failures_before_marking_unreachable() {
|
||||
let mut failed_once = HashSet::new();
|
||||
let did = "did:key:z6MkPeer";
|
||||
|
||||
assert_eq!(
|
||||
peer_ping_db_update(&mut failed_once, did, false),
|
||||
None,
|
||||
"one transient failure must preserve the persisted federation gate"
|
||||
);
|
||||
assert_eq!(
|
||||
peer_ping_db_update(&mut failed_once, did, false),
|
||||
Some(false),
|
||||
"a sustained failure must mark the peer unreachable"
|
||||
);
|
||||
assert_eq!(
|
||||
peer_ping_db_update(&mut failed_once, did, true),
|
||||
Some(true),
|
||||
"a success must restore reachability immediately"
|
||||
);
|
||||
assert_eq!(
|
||||
peer_ping_db_update(&mut failed_once, did, false),
|
||||
None,
|
||||
"a success must reset the consecutive-failure state"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn gossip_ping_round_requires_two_failures_before_persisting_unreachable(pool: PgPool) {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(503)
|
||||
.expect(2)
|
||||
.create_async()
|
||||
.await;
|
||||
let state = crate::test_support::test_state(pool.clone()).await;
|
||||
let did = "did:key:z6MkGossipHysteresis";
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
sqlx::query(
|
||||
"INSERT INTO peers (did, http_url, last_seen, last_ping_ok, announced_at)
|
||||
VALUES ($1, $2, $3, TRUE, $3)",
|
||||
)
|
||||
.bind(did)
|
||||
.bind(server.url())
|
||||
.bind(now)
|
||||
.execute(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let mut failed_once = HashSet::from(["did:key:z6MkRemovedPeer".to_owned()]);
|
||||
gossip_ping_round(
|
||||
state.db.as_ref(),
|
||||
&production_http_client(),
|
||||
&mut failed_once,
|
||||
state.db.list_peers().await.unwrap(),
|
||||
)
|
||||
.await;
|
||||
assert!(
|
||||
!failed_once.contains("did:key:z6MkRemovedPeer"),
|
||||
"failure tracking must prune peers outside the current snapshot"
|
||||
);
|
||||
assert!(
|
||||
failed_once.contains(did),
|
||||
"the first failed sample must be retained for the next round"
|
||||
);
|
||||
assert!(
|
||||
state
|
||||
.db
|
||||
.list_peers()
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.find(|peer| peer.did == did)
|
||||
.unwrap()
|
||||
.last_ping_ok,
|
||||
"one transient failure must preserve the persisted federation gate"
|
||||
);
|
||||
|
||||
gossip_ping_round(
|
||||
state.db.as_ref(),
|
||||
&production_http_client(),
|
||||
&mut failed_once,
|
||||
state.db.list_peers().await.unwrap(),
|
||||
)
|
||||
.await;
|
||||
assert!(
|
||||
!state
|
||||
.db
|
||||
.list_peers()
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.find(|peer| peer.did == did)
|
||||
.unwrap()
|
||||
.last_ping_ok,
|
||||
"two consecutive failed rounds must persist the peer as unreachable"
|
||||
);
|
||||
ready.assert_async().await;
|
||||
}
|
||||
|
||||
// A peer answering `/ready` with a 302 toward an internal address must not
|
||||
// A peer answering `/health` with a 302 toward an internal address must not
|
||||
// be followed: the redirect target must never be requested (#93).
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_does_not_follow_redirect() {
|
||||
async fn ping_peer_health_does_not_follow_redirect() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let internal = server
|
||||
.mock("GET", "/internal-metadata")
|
||||
@@ -1483,154 +1179,6 @@ mod gossip_ssrf_tests {
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
let _ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(302)
|
||||
.with_header("location", &format!("{}/internal-metadata", server.url()))
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_readiness(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(!ok, "a 302 must not count as a healthy peer");
|
||||
// expect(0) is enforced only at assert time; this fails if the redirect
|
||||
// was followed to the internal target.
|
||||
internal.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_reports_success_on_200() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(200)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_readiness(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(ok, "a 200 /ready must count as a ready peer");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_ignores_liveness_only_health() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
let ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(503)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_readiness(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(!ok, "a peer with an unavailable database must not be ready");
|
||||
health.assert_async().await;
|
||||
ready.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_falls_back_for_legacy_peer() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(404)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(200)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_readiness(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(
|
||||
ok,
|
||||
"a legacy peer with a healthy /health must remain reachable"
|
||||
);
|
||||
ready.assert_async().await;
|
||||
health.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_legacy_fallback_shares_deadline() {
|
||||
let health_requests = Arc::new(AtomicUsize::new(0));
|
||||
let health_requests_for_route = Arc::clone(&health_requests);
|
||||
let app = Router::new()
|
||||
.route(
|
||||
"/ready",
|
||||
get(|| async {
|
||||
tokio::time::sleep(Duration::from_millis(100)).await;
|
||||
StatusCode::NOT_FOUND
|
||||
}),
|
||||
)
|
||||
.route(
|
||||
"/health",
|
||||
get(move || {
|
||||
let health_requests = Arc::clone(&health_requests_for_route);
|
||||
async move {
|
||||
health_requests.fetch_add(1, Ordering::Relaxed);
|
||||
tokio::time::sleep(Duration::from_millis(300)).await;
|
||||
StatusCode::OK
|
||||
}
|
||||
}),
|
||||
);
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
|
||||
.await
|
||||
.expect("failed to bind delayed legacy peer");
|
||||
let peer_url = format!(
|
||||
"http://{}",
|
||||
listener
|
||||
.local_addr()
|
||||
.expect("delayed legacy peer has no local address")
|
||||
);
|
||||
let server = tokio::spawn(async move {
|
||||
axum::serve(listener, app)
|
||||
.await
|
||||
.expect("delayed legacy peer failed");
|
||||
});
|
||||
|
||||
let ok = ping_peer_readiness_with_timeout(
|
||||
&production_http_client(),
|
||||
&peer_url,
|
||||
// Each response arrives within 350 ms, but the two serial requests
|
||||
// cannot both finish within one 350 ms probe budget.
|
||||
Duration::from_millis(350),
|
||||
)
|
||||
.await;
|
||||
|
||||
assert!(!ok, "the fallback must not start a fresh timeout budget");
|
||||
assert_eq!(
|
||||
health_requests.load(Ordering::Relaxed),
|
||||
1,
|
||||
"the delayed 404 should reach the legacy fallback"
|
||||
);
|
||||
server.abort();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_legacy_fallback_does_not_follow_redirect() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let internal = server
|
||||
.mock("GET", "/internal-metadata")
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
let _ready = server
|
||||
.mock("GET", "/ready")
|
||||
.with_status(404)
|
||||
.create_async()
|
||||
.await;
|
||||
let _health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(302)
|
||||
@@ -1638,17 +1186,33 @@ mod gossip_ssrf_tests {
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_readiness(&production_http_client(), &server.url()).await;
|
||||
let ok = ping_peer_health(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(!ok, "the legacy fallback must not follow redirects");
|
||||
assert!(!ok, "a 302 must not count as a healthy peer");
|
||||
// expect(0) is enforced only at assert time; this fails if the redirect
|
||||
// was followed to the internal target.
|
||||
internal.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_health_reports_success_on_200() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(200)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_health(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(ok, "a 200 /health must count as a healthy peer");
|
||||
}
|
||||
|
||||
// A transport error (nothing listening) must map to unhealthy, never a
|
||||
// spurious healthy — the .unwrap_or(false) arm.
|
||||
#[tokio::test]
|
||||
async fn ping_peer_readiness_reports_unready_on_connection_error() {
|
||||
let ok = ping_peer_readiness(&production_http_client(), "http://127.0.0.1:1").await;
|
||||
assert!(!ok, "a connection error must count as an unready peer");
|
||||
async fn ping_peer_health_reports_unhealthy_on_connection_error() {
|
||||
let ok = ping_peer_health(&production_http_client(), "http://127.0.0.1:1").await;
|
||||
assert!(!ok, "a connection error must count as an unhealthy peer");
|
||||
}
|
||||
}
|
||||
@@ -76,87 +76,42 @@ pub async fn pin_object(
|
||||
/// still needed to read each object's bytes, and `git_bin` names the binary those
|
||||
/// reads run: the production caller passes the literal `"git"`, and a test passes a
|
||||
/// fake so the loop's own bound can be driven with a git that never answers.
|
||||
/// `git_timeout` is the per-object read bound, the same value and the same role it has
|
||||
/// in the twin: it bounds both the pin read and the skip branch's opportunistic repair.
|
||||
/// Objects already recorded with a `pinata_cid` are skipped, and `repo_id` records the
|
||||
/// pin's provenance (#173). Returns `(sha_hex, provider_cid)` pairs for each newly
|
||||
/// pinned object: the provider CID is the Pinata gateway CID (used for branch->CID
|
||||
/// recording and ref-update gossip), NOT the raw resolver-key CID stored in
|
||||
/// `pinned_cids.cid`.
|
||||
/// Objects already recorded with a `pinata_cid` are skipped. Returns
|
||||
/// `(sha_hex, cid)` pairs for each newly pinned object.
|
||||
///
|
||||
/// # What `batch_budget` does and does not bound
|
||||
///
|
||||
/// The loop runs under a `pin_semaphore` permit and that pool defers rather than
|
||||
/// sheds, so the hold has to be bounded by something other than the pusher's object
|
||||
/// count. Three things here are:
|
||||
/// count. Two things here are:
|
||||
///
|
||||
/// - this loop's own wall-clock: the deadline is taken once at loop start and
|
||||
/// checked at the top of every iteration, so no object's work begins with less
|
||||
/// than the read floor left. It is a gate, not a hard ceiling, since a started
|
||||
/// iteration still runs to completion;
|
||||
/// - the git read: `store::read_object_bounded` runs under `spawn_blocking` against the
|
||||
/// earlier of the ABSOLUTE batch deadline (not the loop-top remainder, which the
|
||||
/// `has_pinata_cid` round-trip sitting between the two would push past it) and this
|
||||
/// object's own `git_timeout`, with SIGTERM-then-SIGKILL process-group teardown, so a
|
||||
/// hung `git cat-file` costs this batch one `git_timeout` plus one watchdog teardown
|
||||
/// instead of holding the permit for the child's whole lifetime and blocking a runtime
|
||||
/// worker while it does;
|
||||
/// - the DB round-trips: every DB operation reachable from inside the region is
|
||||
/// bounded by the same absolute deadline through `crate::ipfs_pin::db_bounded`,
|
||||
/// including the two inside `repair_legacy_provider_cid`, which this loop body's own
|
||||
/// call sites do not show. `retry_db_record` is wrapped as a whole so its ladder
|
||||
/// cannot multiply one remainder, and the durability writes (the post-upload
|
||||
/// `record_pinata_cid` and source record, the skip branch's source record, and both
|
||||
/// incomplete markers) take the floored remainder `max(remaining, DB_RECORD_GRACE)`
|
||||
/// so a spent budget delays the permit release rather than dropping a write. That
|
||||
/// floor matters more here than on the twin: `pinned.push` is unconditional, so a
|
||||
/// dropped record would leave `api::repos` advertising a CID the resolver 404s. A
|
||||
/// bound is not a rollback, and what an elapsed bound MEANS is a property of the
|
||||
/// operation, so each site maps that arm from the shape of the call it wrapped. Both
|
||||
/// source-record sites wrap `record_pin_source`, an explicit transaction whose
|
||||
/// `tx.commit()` a cancelled future never reaches, so a timeout there definitely did
|
||||
/// not land and both write the incomplete marker exactly as the definite-error arm
|
||||
/// does. `record_pinata_cid` is a single autocommit upsert, so ITS timeout is a
|
||||
/// genuine unknown outcome and is never treated as a failed write. See
|
||||
/// `crate::ipfs_pin::BoundedDbError::Elapsed`.
|
||||
/// ABSOLUTE batch deadline (not the loop-top remainder, which the `has_pinata_cid`
|
||||
/// round-trip sitting between the two would push past it), with SIGTERM-then-SIGKILL
|
||||
/// process-group teardown, so a hung `git cat-file` costs this batch its remaining
|
||||
/// budget plus one watchdog teardown instead of holding the permit for the child's
|
||||
/// whole lifetime and blocking a runtime worker while it does.
|
||||
///
|
||||
/// So the LOOP's hold is bounded by roughly `batch_budget`, plus one watchdog
|
||||
/// teardown, one upload (the shared client's whole-request timeout bounds the
|
||||
/// upload; `pin_object` takes no per-request override), and the record graces one
|
||||
/// iteration can chain. `db_record_deadline` re-floors from `Instant::now()` at EVERY
|
||||
/// call, so the graces inside a single iteration add up rather than sharing one floor:
|
||||
/// the worst case here is the add path at `deadline + 6s` (`record_pinata_cid`, then
|
||||
/// `record_pin_source`, then its incomplete marker), against the skip branch's
|
||||
/// `deadline + 4s`. It does NOT stack per object, because the next iteration's first
|
||||
/// statement is `batch_budget_gate`, which breaks the batch, so the overrun is one
|
||||
/// iteration's worth however many objects the push carried. Against the 120s
|
||||
/// `PIN_BATCH_BUDGET` that is roughly a 5% overrun for the batch, not an unbounded
|
||||
/// hold. The PERMIT's hold is NOT bounded by any of this, and that stays out of
|
||||
/// scope: `api::repos` acquires the permit (repos.rs ~2688) and only then re-derives
|
||||
/// the object list with `pinata_object_list_for_refs` (~2697), BEFORE this function is
|
||||
/// entered, and that walk carries no aggregate deadline. What is bounded is this
|
||||
/// loop's own hold, not the permit's total hold and not the semaphore's worst-case
|
||||
/// queue.
|
||||
/// teardown and one upload (the shared client's whole-request timeout bounds the
|
||||
/// upload; `pin_object` takes no per-request override). The PERMIT's hold is NOT
|
||||
/// bounded by any of this: `api::repos` acquires the permit and then re-derives the
|
||||
/// object list with `pinata_object_list_for_refs` BEFORE this function is entered,
|
||||
/// and that walk carries no aggregate deadline. The DB round-trips
|
||||
/// (`has_pinata_cid`, `record_pinata_cid`) are untimed inside the budgeted region
|
||||
/// too.
|
||||
///
|
||||
/// The twin in `ipfs_pin.rs` is at parity with this loop on everything that bounds or
|
||||
/// repairs an object: the shared budget gate, the read bounded by the earlier of the
|
||||
/// batch deadline and `git_timeout`, the skip branch's opportunistic legacy
|
||||
/// provider-CID repair, and the DB bound above, which is the SAME helper and the same
|
||||
/// floor on both sides rather than a copy. Change them in lockstep: the
|
||||
/// skip-if-pinned check, the provenance and source recording, the fault arms, and the
|
||||
/// budget handling.
|
||||
///
|
||||
/// The RETURNED PAIRS are the one deliberate divergence, and it is not drift. This side
|
||||
/// pushes a pin whose DB record exhausted its retries, because this return is a real
|
||||
/// input: `api::repos` builds the sha-to-cid `cid_map` from it, which drives
|
||||
/// `upsert_branch_cid` and the p2p `publish_ref_update` gossip CID. The twin's return is
|
||||
/// log-only, so it omits a record-failed pin rather than logging a pin the resolver
|
||||
/// cannot serve. Moving this side to match would need that consumer moved first.
|
||||
// Ten arguments, over clippy's threshold: the three the budget and the git seam add
|
||||
// (`git_bin`, `git_timeout`, `batch_budget`) plus #173's `repo_id` are what put the read
|
||||
// under test injection and under a deadline, and grouping them into a struct would only
|
||||
// move the same values behind a name the twin in `ipfs_pin.rs` does not use. Same allow
|
||||
// as the sibling call sites in `api::repos`.
|
||||
/// The twin in `ipfs_pin.rs` shares the budget gate and the bounded read with this
|
||||
/// loop, so both are at parity again. Change them in lockstep: the skip-if-pinned
|
||||
/// check, the fault arms, the returned pairs, and the budget handling.
|
||||
// Eight arguments, one over clippy's threshold: the two the budget adds (`git_bin`,
|
||||
// `batch_budget`) are what put the read under test injection and under a deadline, and
|
||||
// grouping them into a struct would only move the same values behind a name the twin in
|
||||
// `ipfs_pin.rs` does not use. Same allow as the sibling call sites in `api::repos`.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
pub async fn pin_new_objects(
|
||||
client: &reqwest::Client,
|
||||
@@ -164,10 +119,8 @@ pub async fn pin_new_objects(
|
||||
jwt: &str,
|
||||
repo_path: &std::path::Path,
|
||||
git_bin: &str,
|
||||
git_timeout: Duration,
|
||||
object_list: Vec<String>,
|
||||
db: &crate::db::Db,
|
||||
repo_id: &str,
|
||||
batch_budget: Duration,
|
||||
) -> Vec<(String, String)> {
|
||||
if jwt.is_empty() {
|
||||
@@ -191,124 +144,8 @@ pub async fn pin_new_objects(
|
||||
break;
|
||||
}
|
||||
|
||||
// Every DB call from here to the end of the iteration is bounded by the
|
||||
// ABSOLUTE batch deadline (F3, #173), through the same `db_bounded` helper the
|
||||
// ipfs_pin twin routes through: this loop runs under the same global pin permit
|
||||
// and a bare await parked it for the whole stall. The elapsed arm is mapped per
|
||||
// site below, never as a blanket "existing error arm": a timeout cancels the
|
||||
// client future but not the statement Postgres is running, so it reports an
|
||||
// UNKNOWN outcome, not a failed write.
|
||||
match crate::ipfs_pin::db_bounded(deadline, db.has_pinata_cid(&sha)).await {
|
||||
Ok(true) => {
|
||||
// Backfill NULL first-pinner provenance from a known source, in lockstep
|
||||
// with the ipfs_pin skip branch: a pinata-only node otherwise leaves
|
||||
// pre-provenance rows' `pinned_cids.repo_id` NULL forever (grok P2-D). The
|
||||
// resolver still finds the object via the pin_repo_sources union below, so
|
||||
// this is a consistency backfill, not a correctness fix.
|
||||
//
|
||||
// Elapsed here is free to skip: the read costs nothing when it lands late,
|
||||
// and the backfill's own `AND repo_id IS NULL` guard makes a late-landing
|
||||
// write idempotent.
|
||||
match crate::ipfs_pin::db_bounded(deadline, db.provenance_for_oid(&sha)).await {
|
||||
Ok(None) => {
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
deadline,
|
||||
db.backfill_pin_provenance(&sha, repo_id),
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to backfill pin provenance");
|
||||
}
|
||||
}
|
||||
Ok(Some(_)) => {}
|
||||
Err(e) => {
|
||||
tracing::warn!(sha = %sha, err = %e, "DB error reading pin provenance");
|
||||
}
|
||||
}
|
||||
// F1 (#173 round 8): record this repo as an additional source for the
|
||||
// already-pinned object (mirrors the ipfs_pin skip-branch insert) so the
|
||||
// resolver can serve a shared object from any pin-path source. U3 (#173):
|
||||
// retried through the SHARED helper (this was a bare call, so a single
|
||||
// transient error dropped the source outright) and, on exhaustion, marked
|
||||
// durably so the resolver keeps the bounded scan fallback for the object.
|
||||
// The retry ladder is bounded AS A WHOLE, not per attempt: three stalls
|
||||
// plus their backoff otherwise multiply one remainder by three. Floored at
|
||||
// DB_RECORD_GRACE because this is a durability write.
|
||||
match crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
crate::ipfs_pin::retry_db_record(|| db.record_pin_source(&sha, repo_id)),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => {}
|
||||
// Elapsed here is a DEFINITE non-write, in lockstep with the twin,
|
||||
// and for a reason that comes from the operation rather than the
|
||||
// timeout: `record_pin_source` is an explicit transaction whose
|
||||
// `tx.commit()` a cancelled future never reaches, so no COMMIT is
|
||||
// sent and the row cannot have landed. Mark the set incomplete
|
||||
// exactly as the definite-error arm does; an incomplete-and-unmarked
|
||||
// set is read as COMPLETE and 404s a copy this repo would serve. The
|
||||
// marker's cost is bounded (the fallback scan is capped at
|
||||
// `ipfs_max_legacy_probes` and charges the per-IP work rate limiter
|
||||
// per probe). The arm stays separate only so the warn tells an
|
||||
// operator a stalled batch from a scattered per-object failure.
|
||||
Err(e @ crate::ipfs_pin::BoundedDbError::Elapsed) => {
|
||||
tracing::warn!(
|
||||
sha = %sha,
|
||||
err = %e,
|
||||
"pin source record did not complete inside the batch deadline; \
|
||||
a cancelled multi-statement transaction never commits, so the \
|
||||
source is definitely missing and the set is marked incomplete"
|
||||
);
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
db.mark_pin_sources_incomplete(&sha, repo_id),
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to mark pin sources incomplete");
|
||||
}
|
||||
}
|
||||
// The retries are spent on REAL errors, so this repo is definitely NOT
|
||||
// in the source set and the set is known incomplete. Floored for the
|
||||
// same reason the record above is: a spent budget must not drop the
|
||||
// compensation. The marker write is a single autocommit statement, so
|
||||
// ITS own elapsed arm is a genuine unknown outcome; nothing branches
|
||||
// on it, which is why warn-only is right there.
|
||||
Err(e) => {
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to record pin source");
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
db.mark_pin_sources_incomplete(&sha, repo_id),
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to mark pin sources incomplete");
|
||||
}
|
||||
}
|
||||
}
|
||||
// R8 (#173 round 10), in lockstep with the ipfs_pin skip branch:
|
||||
// opportunistically repair a legacy provider-CID row (Kubo dag-pb /
|
||||
// Pinata) to the raw-content resolver key on this re-push. Cost-gated on
|
||||
// the stored key's codec, so a non-legacy row reads no bytes. Warn-only:
|
||||
// a failure leaves the row as-is for a later re-push or the deferred
|
||||
// one-shot sweep.
|
||||
// Clamped to the batch deadline, in lockstep with the ipfs_pin twin: this
|
||||
// runs with the pin permit held, so an unclamped `git_timeout` would let
|
||||
// one wedged read hold a global pin slot for 600s against a 120s budget.
|
||||
if let Err(e) = crate::ipfs_pin::repair_legacy_provider_cid(
|
||||
repo_path,
|
||||
git_bin,
|
||||
std::cmp::min(deadline, std::time::Instant::now() + git_timeout),
|
||||
&sha,
|
||||
db,
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to repair legacy provider CID");
|
||||
}
|
||||
continue;
|
||||
}
|
||||
match db.has_pinata_cid(&sha).await {
|
||||
Ok(true) => continue,
|
||||
Ok(false) => {}
|
||||
Err(e) => {
|
||||
tracing::warn!(sha = %sha, err = %e, "DB error checking pinata_cid");
|
||||
@@ -326,16 +163,7 @@ pub async fn pin_new_objects(
|
||||
// between the two, so `Instant::now() + budget_left` would land past `deadline` by
|
||||
// however long the DB took, and under a saturated pool that is the dominant term.
|
||||
// A slow DB check must not push the read's own bound out.
|
||||
//
|
||||
// Bounded by the EARLIER of the batch deadline (#174) and this object's own
|
||||
// `git_timeout` (#173), the same pair the ipfs_pin twin uses. Both bounds are
|
||||
// load-bearing and neither implies the other: the batch deadline alone would let
|
||||
// ONE wedged `cat-file` hold the pin permit for the whole budget, while
|
||||
// `git_timeout` alone would let a batch of merely-slow reads run past the budget.
|
||||
// As on the twin, at SHIPPED DEFAULTS the batch deadline is the arm that binds
|
||||
// (600s git timeout against a 120s budget); the `git_timeout` arm is for an
|
||||
// operator who tightens that knob below the remaining budget.
|
||||
let read_deadline = std::cmp::min(deadline, std::time::Instant::now() + git_timeout);
|
||||
let read_deadline = deadline;
|
||||
let read_path = repo_path.to_path_buf();
|
||||
let read_sha = sha.clone();
|
||||
let read_git = git_bin.to_string();
|
||||
@@ -396,86 +224,9 @@ pub async fn pin_new_objects(
|
||||
|
||||
match pin_object(client, upload_url, jwt, &sha, &data).await {
|
||||
Ok(cid) if !cid.is_empty() => {
|
||||
// The resolver key (`pinned_cids.cid`) must be the locally-computed
|
||||
// raw-content CID, never the provider CID: Pinata wraps the bytes in
|
||||
// dag-pb/UnixFS, so its returned CID does not hash the raw content and
|
||||
// must not become an alias `/ipfs/{cid}` serves raw git bytes for (#173).
|
||||
let raw_cid = gitlawb_core::cid::Cid::from_git_object_bytes(&data).to_string();
|
||||
// U3 (#173): both records go through the shared retry helper, at parity
|
||||
// with the ipfs_pin twin. These were bare calls, so one transient DB error
|
||||
// permanently dropped a pin source.
|
||||
//
|
||||
// Both bounds here are FLOORED at DB_RECORD_GRACE (F3, #173). The upload
|
||||
// runs under the shared client's own ceiling, so a successful one can
|
||||
// return with ~0 of the batch budget left, and an unfloored bound would
|
||||
// fail a write that today completes in milliseconds. That costs more on
|
||||
// this side than on the twin: `pinned.push` below is UNCONDITIONAL, so
|
||||
// `api/repos.rs` builds its `cid_map` from the pair either way and drives
|
||||
// `upsert_branch_cid` plus the p2p `publish_ref_update` gossip from it. A
|
||||
// dropped record therefore makes the node ADVERTISE a CID whose `/ipfs`
|
||||
// read 404s. If the floored bound still fires, THIS site's outcome really
|
||||
// is unknown, and unlike the source record below that is a property of
|
||||
// the operation: `record_pinata_cid` is a single autocommit upsert, so
|
||||
// the statement Postgres already started can still land after the client
|
||||
// future is cancelled. The warn names the arm through the error's own
|
||||
// Display and the site keeps its existing behavior: the pair is still
|
||||
// returned, and the row may or may not exist.
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
crate::ipfs_pin::retry_db_record(|| {
|
||||
db.record_pinata_cid(&sha, &raw_cid, &cid, Some(repo_id))
|
||||
}),
|
||||
)
|
||||
.await
|
||||
{
|
||||
if let Err(e) = db.record_pinata_cid(&sha, &cid).await {
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to record pinata_cid in DB");
|
||||
}
|
||||
// F1 (#173 round 8): also record the first pinner in pin_repo_sources.
|
||||
// U3: an exhausted retry marks the set incomplete so the resolver keeps
|
||||
// the scan fallback rather than 404ing a copy it could serve.
|
||||
match crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
crate::ipfs_pin::retry_db_record(|| db.record_pin_source(&sha, repo_id)),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => {}
|
||||
// Same rule as the skip branch above, and the same reason: this
|
||||
// wraps `record_pin_source`, an explicit transaction, so a timed-out
|
||||
// call definitely never committed and the source is definitely
|
||||
// missing. Mark the set incomplete rather than leaving it incomplete
|
||||
// and unmarked. Note the contrast with `record_pinata_cid` a few
|
||||
// lines up: that one is a single autocommit statement, so its
|
||||
// timeout genuinely is an unknown outcome and it is warn-only.
|
||||
Err(e @ crate::ipfs_pin::BoundedDbError::Elapsed) => {
|
||||
tracing::warn!(
|
||||
sha = %sha,
|
||||
err = %e,
|
||||
"pin source record did not complete inside the batch deadline; \
|
||||
a cancelled multi-statement transaction never commits, so the \
|
||||
source is definitely missing and the set is marked incomplete"
|
||||
);
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
db.mark_pin_sources_incomplete(&sha, repo_id),
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to mark pin sources incomplete");
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to record pin source");
|
||||
if let Err(e) = crate::ipfs_pin::db_bounded(
|
||||
crate::ipfs_pin::db_record_deadline(deadline),
|
||||
db.mark_pin_sources_incomplete(&sha, repo_id),
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::warn!(sha = %sha, err = %e, "failed to mark pin sources incomplete");
|
||||
}
|
||||
}
|
||||
}
|
||||
pinned.push((sha, cid));
|
||||
}
|
||||
Ok(_) => {}
|
||||
@@ -682,10 +433,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_millis(5500),
|
||||
),
|
||||
)
|
||||
@@ -773,10 +522,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
fake.to_str().unwrap(),
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(2),
|
||||
),
|
||||
)
|
||||
@@ -827,66 +574,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// U3 scenario 5 (#173): the read is bounded by the EARLIER of the batch deadline and
|
||||
/// this object's own `git_timeout`, the same pair the ipfs_pin twin uses. The batch
|
||||
/// budget here is generous (60s) so the budget gate cannot be what ends the call: only
|
||||
/// the 1s `git_timeout` can. A wedged `git cat-file` that traps SIGTERM and sleeps 30s
|
||||
/// must therefore be reaped in the `git_timeout` order and the call must return, rather
|
||||
/// than holding the pin permit for the whole budget.
|
||||
///
|
||||
/// RED with `let read_deadline = deadline;` (the pre-U3 bare batch deadline): the read
|
||||
/// waits out the wedged child, the call runs ~30s, and the outer 20s timeout fires.
|
||||
#[cfg(unix)]
|
||||
#[sqlx::test]
|
||||
async fn pin_new_objects_bounds_the_read_by_git_timeout_not_the_batch_budget(
|
||||
pool: sqlx::PgPool,
|
||||
) {
|
||||
let db = crate::db::Db::for_testing(pool);
|
||||
db.run_migrations().await.expect("migrations");
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let repo_path = tmp.path().join("git-timeout.git");
|
||||
let oids = seed_loose_blobs(&repo_path, 1);
|
||||
let fake = tmp.path().join("hanging-git");
|
||||
write_script(&fake, "#!/bin/sh\ntrap '' TERM\necho $$ > pid\nsleep 30\n");
|
||||
|
||||
let (_logs, _guard) = capture_logs();
|
||||
let client = reqwest::Client::new();
|
||||
let started = std::time::Instant::now();
|
||||
let pinned = tokio::time::timeout(
|
||||
Duration::from_secs(20),
|
||||
pin_new_objects(
|
||||
&client,
|
||||
"http://127.0.0.1:9",
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
fake.to_str().unwrap(),
|
||||
// The bound under test.
|
||||
Duration::from_secs(1),
|
||||
oids,
|
||||
&db,
|
||||
"repo-git-timeout",
|
||||
// Generous, so a call that ends on time ended on `git_timeout`.
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
.await
|
||||
.expect(
|
||||
"the read must be bounded by git_timeout, not by the batch budget: a wedged git \
|
||||
cannot hold the pin permit for the whole 60s budget",
|
||||
);
|
||||
let elapsed = started.elapsed();
|
||||
|
||||
assert!(
|
||||
pinned.is_empty(),
|
||||
"a git that never answers cannot produce a pinned object: {pinned:?}"
|
||||
);
|
||||
assert!(
|
||||
elapsed < Duration::from_secs(15),
|
||||
"elapsed {elapsed:?} must stay in the git_timeout order (1s plus one watchdog \
|
||||
teardown), not the 60s batch budget"
|
||||
);
|
||||
}
|
||||
|
||||
/// A `git_bin` wrapper that records every invocation's arguments and then execs the
|
||||
/// real git, so a test can tell which objects the loop actually attempted. The returned
|
||||
/// pin list cannot: it is empty both when the loop broke after one object and when it
|
||||
@@ -963,10 +650,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
&git_bin,
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
@@ -1037,10 +722,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
&git_bin,
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
@@ -1088,10 +771,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(60),
|
||||
oids.clone(),
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
@@ -1117,10 +798,8 @@ mod tests {
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
@@ -1170,10 +849,8 @@ mod tests {
|
||||
"",
|
||||
&repo_path,
|
||||
fake.to_str().unwrap(),
|
||||
Duration::from_secs(60),
|
||||
oids,
|
||||
&db,
|
||||
"repo-merge-test",
|
||||
Duration::from_secs(60),
|
||||
),
|
||||
)
|
||||
@@ -1188,406 +865,6 @@ mod tests {
|
||||
assert_eq!(requests.load(std::sync::atomic::Ordering::SeqCst), 0);
|
||||
}
|
||||
|
||||
// ── Stalled-DB bound (F3, #173) ───────────────────────────────────────
|
||||
//
|
||||
// `api/repos.rs` acquires the GLOBAL `pin_semaphore` for the Pinata
|
||||
// replication task and holds it across this whole function, the same permit
|
||||
// the IPFS lane takes. `batch_budget_gate` only gates BETWEEN objects and the
|
||||
// git read is already clamped, so a bare DB await in the region parked that
|
||||
// permit for as long as the query was stuck. The tests below drive the stall
|
||||
// with a `LOCK TABLE .. IN ACCESS EXCLUSIVE MODE` held on a dedicated pooled
|
||||
// connection, the same technique the ipfs_pin twin's stall tests use, and copy
|
||||
// their tolerances (a 1.5s budget, an `elapsed < 3s` assertion, a 10s outer
|
||||
// wrap). The budget is above `PIN_READ_FLOOR` on purpose: below it
|
||||
// `batch_budget_gate` breaks the batch as the loop body's FIRST statement, so a
|
||||
// ~1s budget would never reach a DB call and the test would pass with the bound
|
||||
// deleted.
|
||||
// ---------------------------------------------------------------------
|
||||
|
||||
/// Take an `ACCESS EXCLUSIVE` lock on `table` on a dedicated pooled connection.
|
||||
/// Every SELECT needs `ACCESS SHARE`, which conflicts, so the next statement
|
||||
/// touching the table blocks at lock acquisition regardless of row count.
|
||||
/// Copied from `ipfs_pin.rs`'s test mod rather than shared, since test mods are
|
||||
/// private, the same way `seed_loose_blobs` and `capture_logs` are.
|
||||
async fn lock_table(
|
||||
pool: &sqlx::PgPool,
|
||||
table: &str,
|
||||
) -> sqlx::pool::PoolConnection<sqlx::Postgres> {
|
||||
let mut conn = pool.acquire().await.unwrap();
|
||||
sqlx::raw_sql(&format!(
|
||||
"BEGIN; LOCK TABLE {table} IN ACCESS EXCLUSIVE MODE;"
|
||||
))
|
||||
.execute(&mut *conn)
|
||||
.await
|
||||
.unwrap();
|
||||
conn
|
||||
}
|
||||
|
||||
async fn rollback(conn: &mut sqlx::pool::PoolConnection<sqlx::Postgres>) {
|
||||
sqlx::raw_sql("ROLLBACK")
|
||||
.execute(&mut **conn)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
/// Scenario 3: the FIRST DB call in this lane's budgeted region
|
||||
/// (`has_pinata_cid`) stalls. With the batch deadline bounding it the loop
|
||||
/// abandons the object, the budget gate then breaks the batch, and the call
|
||||
/// returns at ~budget having uploaded nothing. Pre-fix the bare await blocks for
|
||||
/// the lock's whole lifetime, holding the caller's global pin permit with it.
|
||||
///
|
||||
/// The upload mock is at `.expect(0)`: a stalled pinned-status check must never
|
||||
/// fall through to an upload, since that would re-send bytes Pinata may already
|
||||
/// hold and, worse, return a CID this node then advertises.
|
||||
#[sqlx::test]
|
||||
async fn pinata_pin_new_objects_stalled_db_returns_by_budget(pool: sqlx::PgPool) {
|
||||
let db = crate::db::Db::for_testing(pool.clone());
|
||||
db.run_migrations().await.expect("migrations");
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let repo_path = tmp.path().join("pinata_stalled.git");
|
||||
let oids = seed_loose_blobs(&repo_path, 1);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let upload = server
|
||||
.mock("POST", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_body(r#"{"data":{"cid":"QmShouldNotHappen"}}"#)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
// Install a log capture even though nothing here asserts on it: `tracing`
|
||||
// caches a callsite's interest globally the first time it is hit, and a hit
|
||||
// from a thread with no subscriber caches it as never-interested for the whole
|
||||
// binary, which silently blinds the sibling tests that DO assert on the batch
|
||||
// deadline warn.
|
||||
let (_logs, _log_guard) = capture_logs();
|
||||
|
||||
let mut lock = lock_table(&pool, "pinned_cids").await;
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
let started = std::time::Instant::now();
|
||||
let pinned = tokio::time::timeout(
|
||||
Duration::from_secs(10),
|
||||
pin_new_objects(
|
||||
&client,
|
||||
&server.url(),
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(30),
|
||||
oids,
|
||||
&db,
|
||||
"repo-pinata-stalled",
|
||||
Duration::from_millis(1500),
|
||||
),
|
||||
)
|
||||
.await
|
||||
.expect(
|
||||
"a stalled DB must cost the batch its budget, not the lock's lifetime: the \
|
||||
bare await hangs past this wrap",
|
||||
);
|
||||
let elapsed = started.elapsed();
|
||||
|
||||
assert!(
|
||||
pinned.is_empty(),
|
||||
"a stalled pinata-status check cannot produce a pinned object: {pinned:?}"
|
||||
);
|
||||
assert!(
|
||||
elapsed < Duration::from_secs(3),
|
||||
"the batch deadline must end the call at ~budget (1.5s); got {elapsed:?}"
|
||||
);
|
||||
upload.assert_async().await;
|
||||
|
||||
rollback(&mut lock).await;
|
||||
}
|
||||
|
||||
/// The Pinata half of the timed-out source record, driven rather than argued: the
|
||||
/// twin's `pin_new_objects_skip_branch_stalled_record_returns_by_budget` covers the
|
||||
/// Kubo lane and this covers the site that has to change in lockstep with it.
|
||||
///
|
||||
/// The object already has a `pinata_cid`, so the loop takes the skip branch and
|
||||
/// tries to record this repo as an additional source; `pin_repo_sources` is locked
|
||||
/// for the whole run, so that insert stalls inside `retry_db_record` and the whole
|
||||
/// ladder elapses against one floored remainder. Two properties:
|
||||
///
|
||||
/// - the call still returns promptly, at the record floor rather than the lock's
|
||||
/// lifetime;
|
||||
/// - on the TIMEOUT arm the incomplete marker IS written. `record_pin_source` is an
|
||||
/// explicit transaction, so the cancelled future never reaches `tx.commit()`, no
|
||||
/// COMMIT is ever sent, and the source definitely did not land. Withholding the
|
||||
/// marker there would leave the set incomplete AND unmarked, which the resolver
|
||||
/// reads as complete and 404s a copy this repo would serve.
|
||||
///
|
||||
/// `pinned_cids` is deliberately NOT locked, so the marker write itself is free to
|
||||
/// land and the assertion below is about the branch, not about lock contention.
|
||||
#[sqlx::test]
|
||||
async fn pinata_skip_branch_stalled_record_marks_incomplete(pool: sqlx::PgPool) {
|
||||
let db = crate::db::Db::for_testing(pool.clone());
|
||||
db.run_migrations().await.expect("migrations");
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let repo_path = tmp.path().join("pinata_skip_stalled.git");
|
||||
let oids = seed_loose_blobs(&repo_path, 1);
|
||||
let sha = oids[0].clone();
|
||||
// Seed the object as already Pinata-pinned, by a DIFFERENT repo, so the skip
|
||||
// branch is taken and the source record below is a genuine additional-source
|
||||
// insert rather than a no-op on the conflict. The resolver key is a canonical
|
||||
// raw CIDv1 so the opportunistic legacy repair takes its cost gate and reads no
|
||||
// bytes.
|
||||
let raw_cid =
|
||||
gitlawb_core::cid::Cid::from_git_object_bytes(b"pinata skip seed").to_string();
|
||||
db.record_pinata_cid(&sha, &raw_cid, "QmSeedProviderCid", Some("repo-seed"))
|
||||
.await
|
||||
.unwrap();
|
||||
db.record_pin_source(&sha, "repo-seed").await.unwrap();
|
||||
let requests = std::sync::Arc::new(std::sync::atomic::AtomicUsize::new(0));
|
||||
let endpoint = delaying_pinata_endpoint(
|
||||
vec![Duration::from_millis(0)],
|
||||
std::sync::Arc::clone(&requests),
|
||||
)
|
||||
.await;
|
||||
// Install a log capture even though nothing here asserts on it: `tracing`
|
||||
// caches a callsite's interest globally the first time it is hit, and a hit
|
||||
// from a thread with no subscriber caches it as never-interested for the whole
|
||||
// binary, which silently blinds the sibling tests that DO assert on the batch
|
||||
// deadline warn.
|
||||
let (_logs, _log_guard) = capture_logs();
|
||||
|
||||
let mut lock = lock_table(&pool, "pin_repo_sources").await;
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
let started = std::time::Instant::now();
|
||||
let pinned = tokio::time::timeout(
|
||||
Duration::from_secs(15),
|
||||
pin_new_objects(
|
||||
&client,
|
||||
&endpoint,
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(30),
|
||||
oids,
|
||||
&db,
|
||||
"repo-pinata-skip-stalled",
|
||||
Duration::from_millis(1500),
|
||||
),
|
||||
)
|
||||
.await
|
||||
.expect(
|
||||
"the wrapped retry ladder must fit inside one floored remainder: the bare \
|
||||
retry_db_record hangs past this wrap",
|
||||
);
|
||||
let elapsed = started.elapsed();
|
||||
|
||||
assert!(
|
||||
pinned.is_empty(),
|
||||
"an already-pinned object is skipped, never re-uploaded: {pinned:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
requests.load(std::sync::atomic::Ordering::SeqCst),
|
||||
0,
|
||||
"the skip branch must not reach the upload at all"
|
||||
);
|
||||
assert!(
|
||||
elapsed < Duration::from_secs(5),
|
||||
"the record's floored remainder must end the call promptly; got {elapsed:?}"
|
||||
);
|
||||
|
||||
rollback(&mut lock).await;
|
||||
drop(lock);
|
||||
|
||||
assert!(
|
||||
db.pin_sources_incomplete(&sha).await.unwrap(),
|
||||
"a TIMED-OUT `record_pin_source` definitively did not land: it is an explicit \
|
||||
multi-statement transaction, and the cancelled future never reaches \
|
||||
`tx.commit()`, so no COMMIT is ever sent and the row cannot exist. The set is \
|
||||
therefore incomplete, and leaving it UNMARKED is the exact state the marker \
|
||||
exists to prevent: the resolver reads a non-empty below-cap set as complete \
|
||||
and 404s a copy this repo would serve"
|
||||
);
|
||||
}
|
||||
|
||||
/// Scenario 8, the Pinata half of the durability floor. `batch_budget_gate` only
|
||||
/// guarantees `PIN_READ_FLOOR` before an object STARTS and the upload runs under
|
||||
/// the shared client's own ceiling, so a successful upload can return with ~0 of
|
||||
/// the batch budget left. Without the floor the post-upload `record_pinata_cid`
|
||||
/// would then be failed by a spent deadline, and this lane's `pinned.push` is
|
||||
/// UNCONDITIONAL: `api/repos.rs` builds `cid_map` from the return and drives
|
||||
/// `upsert_branch_cid` plus the p2p `publish_ref_update` gossip from it, so a
|
||||
/// dropped record makes the node advertise a CID whose `/ipfs` read 404s.
|
||||
///
|
||||
/// Fixture: a 2s budget, a 1.7s upload, and `pinned_cids` locked from 500ms (well
|
||||
/// after `has_pinata_cid` has read it, and still well before the upload returns)
|
||||
/// until 2.4s. The record therefore starts at ~1.72s with ~280ms of budget left
|
||||
/// and needs ~680ms of lock wait to land, which only the `DB_RECORD_GRACE` floor
|
||||
/// buys it.
|
||||
///
|
||||
/// The lock time is a MARGIN, not a boundary: taking it at 100ms left
|
||||
/// `has_pinata_cid` racing it on a loaded box, and losing that race makes the read
|
||||
/// block, time out, and break the batch, which fails on `pinned.len() == 1` for a
|
||||
/// reason that has nothing to do with the floor. Any time between the
|
||||
/// `has_pinata_cid` round trip and the upload's 1.7s return proves the same thing.
|
||||
#[sqlx::test]
|
||||
async fn pinata_pin_add_with_spent_budget_still_records_cid(pool: sqlx::PgPool) {
|
||||
let db = crate::db::Db::for_testing(pool.clone());
|
||||
db.run_migrations().await.expect("migrations");
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let repo_path = tmp.path().join("pinata_spent_budget.git");
|
||||
let oids = seed_loose_blobs(&repo_path, 1);
|
||||
let sha = oids[0].clone();
|
||||
let requests = std::sync::Arc::new(std::sync::atomic::AtomicUsize::new(0));
|
||||
let endpoint = delaying_pinata_endpoint(
|
||||
vec![Duration::from_millis(1700)],
|
||||
std::sync::Arc::clone(&requests),
|
||||
)
|
||||
.await;
|
||||
// Install a log capture even though nothing here asserts on it: `tracing`
|
||||
// caches a callsite's interest globally the first time it is hit, and a hit
|
||||
// from a thread with no subscriber caches it as never-interested for the whole
|
||||
// binary, which silently blinds the sibling tests that DO assert on the batch
|
||||
// deadline warn.
|
||||
let (_logs, _log_guard) = capture_logs();
|
||||
|
||||
let lock_pool = pool.clone();
|
||||
let locker = async move {
|
||||
tokio::time::sleep(Duration::from_millis(500)).await;
|
||||
let mut conn = lock_table(&lock_pool, "pinned_cids").await;
|
||||
tokio::time::sleep(Duration::from_millis(1900)).await;
|
||||
rollback(&mut conn).await;
|
||||
};
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
let pin = tokio::time::timeout(
|
||||
Duration::from_secs(20),
|
||||
pin_new_objects(
|
||||
&client,
|
||||
&endpoint,
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(30),
|
||||
oids.clone(),
|
||||
&db,
|
||||
"repo-pinata-spent-budget",
|
||||
Duration::from_millis(2000),
|
||||
),
|
||||
);
|
||||
let (pinned, ()) = tokio::join!(pin, locker);
|
||||
let pinned = pinned.expect("the floored record must land well inside this wrap");
|
||||
|
||||
assert_eq!(
|
||||
requests.load(std::sync::atomic::Ordering::SeqCst),
|
||||
1,
|
||||
"the fixture only proves anything if the upload actually ran"
|
||||
);
|
||||
assert!(
|
||||
db.has_pinata_cid(&sha).await.unwrap(),
|
||||
"a successful upload whose batch deadline is spent must still land its \
|
||||
pinned_cids row: this lane pushes the pair unconditionally, so a dropped \
|
||||
record makes api/repos.rs advertise a CID the resolver cannot serve"
|
||||
);
|
||||
assert_eq!(
|
||||
pinned.len(),
|
||||
1,
|
||||
"the uploaded pin must still be returned: {pinned:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The POST-UPLOAD source record's timeout arm, the one site of the three that
|
||||
/// nothing else executes. The skip-branch twin above and the ipfs_pin lane cover
|
||||
/// the other two; this arm sits after a SUCCESSFUL `pin_object`, so no skip-branch
|
||||
/// fixture can reach it.
|
||||
///
|
||||
/// Why it has to write the marker at all: `record_pin_source` is an explicit
|
||||
/// transaction ending in `tx.commit()`, and a cancelled future never gets there, so
|
||||
/// no COMMIT is sent and the row definitely does not exist. The set is therefore
|
||||
/// incomplete, and leaving it unmarked is the state the marker exists to prevent.
|
||||
///
|
||||
/// Fixture: the object is NOT seeded as Pinata-pinned, so `has_pinata_cid` is false
|
||||
/// and the run takes the upload path. The mock answers the upload at once, then
|
||||
/// `pin_repo_sources` is held under `ACCESS EXCLUSIVE` for the whole run, so the
|
||||
/// post-upload `record_pin_source` blocks and elapses against its floored bound at
|
||||
/// ~2s. `pinned_cids` is deliberately left UNLOCKED, so both `record_pinata_cid`
|
||||
/// and the marker write itself are free to land and the assertion is about the arm
|
||||
/// rather than about my own lock.
|
||||
///
|
||||
/// The upload assertion is what keeps this from being vacuous: without it the test
|
||||
/// would pass just as well if the run never reached the post-upload path at all.
|
||||
#[sqlx::test]
|
||||
async fn pinata_post_upload_stalled_record_marks_incomplete(pool: sqlx::PgPool) {
|
||||
let db = crate::db::Db::for_testing(pool.clone());
|
||||
db.run_migrations().await.expect("migrations");
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let repo_path = tmp.path().join("pinata_post_upload.git");
|
||||
let oids = seed_loose_blobs(&repo_path, 1);
|
||||
let sha = oids[0].clone();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let upload = server
|
||||
.mock("POST", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_body(r#"{"data":{"cid":"QmPostUploadProviderCid"}}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
// Install a log capture even though nothing here asserts on it: `tracing`
|
||||
// caches a callsite's interest globally the first time it is hit, and a hit
|
||||
// from a thread with no subscriber caches it as never-interested for the whole
|
||||
// binary, which silently blinds the sibling tests that DO assert on the batch
|
||||
// deadline warn.
|
||||
let (_logs, _log_guard) = capture_logs();
|
||||
|
||||
let mut lock = lock_table(&pool, "pin_repo_sources").await;
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
let started = std::time::Instant::now();
|
||||
let pinned = tokio::time::timeout(
|
||||
Duration::from_secs(20),
|
||||
pin_new_objects(
|
||||
&client,
|
||||
&server.url(),
|
||||
"test-jwt",
|
||||
&repo_path,
|
||||
"git",
|
||||
Duration::from_secs(30),
|
||||
oids,
|
||||
&db,
|
||||
"repo-pinata-post-upload",
|
||||
Duration::from_millis(1500),
|
||||
),
|
||||
)
|
||||
.await
|
||||
.expect(
|
||||
"the wrapped retry ladder must fit inside one floored remainder: the bare \
|
||||
retry_db_record hangs past this wrap",
|
||||
);
|
||||
let elapsed = started.elapsed();
|
||||
|
||||
rollback(&mut lock).await;
|
||||
drop(lock);
|
||||
|
||||
upload.assert_async().await;
|
||||
assert_eq!(
|
||||
pinned.len(),
|
||||
1,
|
||||
"the upload succeeded, so this lane still returns the pair: {pinned:?}"
|
||||
);
|
||||
assert!(
|
||||
elapsed < Duration::from_secs(8),
|
||||
"the record's floored remainder must end the call promptly, never at the \
|
||||
lock's lifetime; got {elapsed:?}"
|
||||
);
|
||||
assert!(
|
||||
db.pin_sources_incomplete(&sha).await.unwrap(),
|
||||
"the POST-UPLOAD arm must mark the source set incomplete when its record \
|
||||
times out: `record_pin_source` is an explicit transaction whose cancelled \
|
||||
future never reaches `tx.commit()`, so the row definitely did not land, and \
|
||||
an incomplete-and-unmarked set is read as complete and 404s a copy this \
|
||||
repo would serve"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_pin_skipped_when_jwt_empty() {
|
||||
let client = reqwest::Client::new();
|
||||
|
||||
@@ -121,26 +121,11 @@ impl RateLimiter {
|
||||
true
|
||||
}
|
||||
|
||||
/// Non-consuming check: is this key ALREADY at its limit for the current window?
|
||||
/// Unlike [`check`], it records nothing and never inserts a new key — used to shed
|
||||
/// expensive preparatory work (e.g. the `/ipfs/{cid}` legacy scan's O(repos) DB
|
||||
/// preload) BEFORE it runs, without perturbing the per-unit budget the consuming
|
||||
/// `check` maintains (#173, F3). An unknown key or a disabled limiter is not
|
||||
/// throttled. Prunes the key's expired timestamps as a side effect (keeps state
|
||||
/// tidy) but adds none, so it cannot itself fill or grow the map.
|
||||
pub(crate) async fn is_throttled(&self, key: &str) -> bool {
|
||||
if self.max_requests == 0 {
|
||||
return false;
|
||||
}
|
||||
let now = Instant::now();
|
||||
let mut state = self.state.lock().await;
|
||||
if let Some(window) = state.get_mut(key) {
|
||||
window
|
||||
.timestamps
|
||||
.retain(|t| now.duration_since(*t) < self.window);
|
||||
return window.timestamps.len() >= self.max_requests;
|
||||
}
|
||||
false
|
||||
/// Number of keys currently tracked. Tests use it to observe what a sweep
|
||||
/// reclaimed; there is no production reader.
|
||||
#[cfg(test)]
|
||||
pub async fn tracked_keys(&self) -> usize {
|
||||
self.state.lock().await.len()
|
||||
}
|
||||
|
||||
pub async fn cleanup(&self) {
|
||||
@@ -152,14 +137,6 @@ impl RateLimiter {
|
||||
!w.timestamps.is_empty()
|
||||
});
|
||||
}
|
||||
|
||||
/// Number of distinct keys currently tracked. Test-only introspection so a
|
||||
/// cross-module test can assert that a sweep actually evicted expired entries
|
||||
/// and observe what it reclaimed. There is no production reader.
|
||||
#[cfg(test)]
|
||||
pub(crate) async fn tracked_keys(&self) -> usize {
|
||||
self.state.lock().await.len()
|
||||
}
|
||||
}
|
||||
|
||||
/// Per-source concurrency cap derived from the write-pool size: one resolved client
|
||||
|
||||
@@ -8,19 +8,6 @@ use crate::git::repo_store::RepoStore;
|
||||
use crate::p2p::P2pHandle;
|
||||
use crate::rate_limit::RateLimiter;
|
||||
|
||||
/// HKDF salt for [`AppState::derive_scan_token_key`]. A constant, not a secret: HKDF's
|
||||
/// salt is a domain qualifier, and the confidentiality of the derived key rests entirely
|
||||
/// on the node's private seed being the input keying material.
|
||||
const SCAN_TOKEN_KEY_SALT: &[u8] = b"gitlawb/hkdf-salt/ipfs-scan-token";
|
||||
|
||||
/// HKDF `info` for [`AppState::derive_scan_token_key`]: the domain separation AND the
|
||||
/// rotation handle in one string. Nothing else in the node derives from this label, so
|
||||
/// the token key is unrelated to the signing key it shares an input with; bumping the
|
||||
/// trailing version rotates every node's token key on its next boot, which invalidates
|
||||
/// outstanding continuations (they simply fail to open and the caller restarts at the
|
||||
/// front) and needs no migration, no config, and no change to this function.
|
||||
const SCAN_TOKEN_KEY_INFO: &[u8] = b"gitlawb/ipfs-scan-token/v1";
|
||||
|
||||
#[derive(Clone, Debug)]
|
||||
pub struct RefUpdateBroadcast {
|
||||
pub repo: String,
|
||||
@@ -79,102 +66,6 @@ pub struct AppState {
|
||||
/// brake a push flood from a DID farm (one throwaway DID per repo), so the
|
||||
/// push path throttles on the resolved client IP instead.
|
||||
pub push_rate_limiter: RateLimiter,
|
||||
/// Per-client-IP rate limiter for `close_issue`'s pre-lock snapshot path.
|
||||
/// Distinct from `push_rate_limiter` so a flood of close attempts cannot
|
||||
/// drain the receive-pack budget for the same source IP.
|
||||
pub close_issue_rate_limiter: RateLimiter,
|
||||
/// Per-client-IP ROUTE brake for `GET /ipfs/{cid}`: charged ONCE per request by the
|
||||
/// `rate_limit_by_ip` middleware (server.rs), never inside the handler. It bounds
|
||||
/// request RATE (the "requests per hour" contract of `GITLAWB_IPFS_RATE_LIMIT`) on
|
||||
/// the non-farmable source IP, so an anonymous flood of the public route is capped.
|
||||
/// The per-probe/per-walk WORK accounting the resolver does WITHIN a request draws
|
||||
/// from the SEPARATE `ipfs_work_rate_limiter` below — the two cannot share one bucket
|
||||
/// or a single request that spends a route token and then its own probe token off the
|
||||
/// same bucket is admitted at the route and falsely shed mid-request (#173 round-10,
|
||||
/// R6). Keyed by `push_limiter_trust`.
|
||||
pub ipfs_rate_limiter: RateLimiter,
|
||||
/// Per-client-IP WORK-budget limiter for the `GET /ipfs/{cid}` resolver's internal
|
||||
/// fan-out: charged per legacy (NULL-provenance) PROBE (`acquire` + `cat-file`) and
|
||||
/// per provenance-path WALK, and peeked non-consuming before the O(repos) legacy
|
||||
/// preload. A legacy CID from the public pins index otherwise lets one request drive
|
||||
/// O(repos) subprocess spawns and cold Tigris fetches, and repeat requests amplify
|
||||
/// that across requests with zero limiter contact (INV-10, F3). Charging the work to
|
||||
/// the non-farmable source IP bounds it. A bucket DISTINCT from the route brake above:
|
||||
/// one request legitimately spends many work tokens (a full legacy scan is up to
|
||||
/// `ipfs_max_legacy_probes` probes), so it must not double as the once-per-request
|
||||
/// route bucket. Capacity is DERIVED from the route limit (`AppState::ipfs_work_budget`,
|
||||
/// no separate operator knob), floored at the legacy-probe budget so a single default-
|
||||
/// config deep search never self-throttles mid-scan. Keyed by `push_limiter_trust`.
|
||||
pub ipfs_work_rate_limiter: RateLimiter,
|
||||
/// Per-request ceiling on full-history reachability walks the CID resolver
|
||||
/// may spawn (default `api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST`). A field,
|
||||
/// not a bare const, so tests can shrink it to exercise the cap cheaply;
|
||||
/// production keeps the const default.
|
||||
pub ipfs_max_history_walks: u32,
|
||||
/// Per-request ceiling on legacy (NULL-provenance) repo probes in the CID
|
||||
/// resolver's scan fallback (default `api::ipfs::MAX_LEGACY_PROBES_PER_REQUEST`).
|
||||
/// Bounds the anonymous `acquire` + `cat-file` fan-out across the node (#173,
|
||||
/// INV-10); a field for the same test-seam reason as `ipfs_max_history_walks`.
|
||||
pub ipfs_max_legacy_probes: u32,
|
||||
/// How many repo rows the CID resolver's legacy scan pulls per keyset page
|
||||
/// (default `api::ipfs::LEGACY_SCAN_PAGE_ROWS`). Bounds the DATABASE-facing half
|
||||
/// of the same fan-out `ipfs_max_legacy_probes` bounds on the probe side: without
|
||||
/// it the scan materialized every repo row and every matching visibility rule
|
||||
/// before spending a single probe (#173, INV-10). A field for the same test-seam
|
||||
/// reason as the sibling caps.
|
||||
pub ipfs_legacy_scan_page_rows: usize,
|
||||
/// Per-request ceiling on how many repo ROWS the CID resolver's legacy scan may
|
||||
/// fetch (default `api::ipfs::MAX_LEGACY_SCAN_ROWS_PER_REQUEST`, operator-tunable via
|
||||
/// `GITLAWB_IPFS_MAX_LEGACY_SCAN_ROWS`). `ipfs_max_legacy_probes` bounds the PROBE
|
||||
/// fan-out but only starts counting once a probe runs, and quarantine plus a
|
||||
/// root-scope visibility deny both return before a probe or a visit is spent, so an
|
||||
/// all-denying inventory paged the whole repo table at zero probes (#173 round 13, F2).
|
||||
/// Truncating here sheds a retryable 503 carrying a sealed continuation token.
|
||||
pub ipfs_max_legacy_scan_rows: usize,
|
||||
/// Per-request ceiling on the BYTES of visibility rules the CID resolver's legacy
|
||||
/// scan may retain (default `api::ipfs::MAX_LEGACY_SCAN_RULE_BYTES_PER_REQUEST`). The
|
||||
/// row ceiling above bounds the row count but not the memory each row drags in: the
|
||||
/// pager keeps every fetched page's rules for the whole request, and neither the
|
||||
/// number of rules per repo nor the length of a rule's reader list is capped, so a
|
||||
/// rule COUNT would be the wrong unit. Enforced by the rules QUERY
|
||||
/// (`Db::list_visibility_rules_for_repos_bounded`) rather than by a sum taken once the
|
||||
/// page has landed, so the oversized page is never materialized at all. Deliberately
|
||||
/// NOT an operator knob (it is a
|
||||
/// memory guard, not a reach tradeoff); a field only for the same test-seam reason as
|
||||
/// the sibling caps.
|
||||
pub ipfs_max_legacy_scan_rule_bytes: usize,
|
||||
/// Key sealing the legacy scan's continuation tokens (INV-13), derived from the
|
||||
/// node's persistent identity by [`AppState::derive_scan_token_key`].
|
||||
///
|
||||
/// The token is minted from a FETCHED row on a scan that served nothing, so by
|
||||
/// construction that row is a private or quarantined repo the caller may not read:
|
||||
/// its `created_at` and its `id` (which carries the owner's DID) are withheld
|
||||
/// fields. The token is therefore AEAD-SEALED, never signed plaintext and never
|
||||
/// base64-of-plaintext, since integrity is not confidentiality.
|
||||
///
|
||||
/// DERIVED, not random per boot. This reverses an earlier revision of this design,
|
||||
/// which argued that derivation "would make old tokens valid across restarts for no
|
||||
/// benefit and tie a throwaway transport secret to a long-lived signing key." Both
|
||||
/// halves were wrong. Surviving a restart IS the benefit: the token is the ONLY way
|
||||
/// a caller resumes a ladder, an unopenable one is treated as absent, and a caller
|
||||
/// treated as absent silently restarts at the front of the scan. A node whose
|
||||
/// inventory needs several ladder steps and which deploys more often than a caller
|
||||
/// can climb therefore keeps that caller from ever reaching a holder, which
|
||||
/// contradicts the reach bound the README states. And the tie to the signing key is
|
||||
/// what the HKDF domain separation removes: the derived key is a one-way function of
|
||||
/// the seed under an `info` string nothing else uses, so it is not the signing key
|
||||
/// and cannot be worked back into one.
|
||||
///
|
||||
/// Persisting a random key instead would need a schema change for a value the node
|
||||
/// already has on disk, so derivation is also the smaller mechanism. Rotation is a
|
||||
/// bump of the version in [`SCAN_TOKEN_KEY_INFO`].
|
||||
pub ipfs_scan_token_key: Arc<[u8; 32]>,
|
||||
/// Hard ceiling on the byte size of an object `GET /ipfs/{cid}` will buffer and
|
||||
/// serve (default `api::ipfs::MAX_SERVED_OBJECT_BYTES`). The serve reads via a
|
||||
/// blocking `git cat-file` and buffers the whole object; without a bound a large
|
||||
/// public blob could exhaust memory or block a runtime worker (#173, F6, INV-10).
|
||||
/// A field for the same test-seam reason as the sibling caps.
|
||||
pub ipfs_max_served_object_bytes: u64,
|
||||
/// Which forwarded header (if any) the edge is trusted to set, for
|
||||
/// resolving the push limiter's client-IP key. See `GITLAWB_TRUSTED_PROXY`.
|
||||
/// Node-wide; also keys the two peer-sync limiters below.
|
||||
@@ -323,6 +214,13 @@ pub struct AppState {
|
||||
/// (`with_default_max_keys`, reject-before-insert) so a source-key farm cannot grow
|
||||
/// it (INV-15).
|
||||
pub git_ipfs_walk_per_caller: crate::rate_limit::PerCallerConcurrency,
|
||||
/// Per-client-IP rate limiter for `GET /ipfs/{cid}`. The route is publicly
|
||||
/// reachable and each request can drive a full-history git walk, so it carries a
|
||||
/// per-IP flood brake in addition to the concurrency cap above — a rate limit
|
||||
/// bounds request *rate*, the semaphore bounds concurrent slow holds (different
|
||||
/// axes). Keyed on the resolved client IP via `push_limiter_trust`. Layered on the
|
||||
/// `/ipfs` route via `rate_limit_by_ip`.
|
||||
pub ipfs_rate_limiter: RateLimiter,
|
||||
/// The `git` executable the served-git withheld-blob walk spawns. Production is
|
||||
/// `"git"` (resolved via PATH); injectable so a fake `git` can drive the walk's
|
||||
/// process-group teardown in handler tests without mutating the process-global
|
||||
@@ -337,22 +235,6 @@ impl AppState {
|
||||
self.shutdown_tx.subscribe()
|
||||
}
|
||||
|
||||
/// Sweep expired entries from every per-IP/DID rate limiter. Driven by the
|
||||
/// periodic cleanup task so a bounded limiter's key map sheds stale entries
|
||||
/// instead of sitting near its cap until an inline capacity sweep reclaims
|
||||
/// them. Every limiter on the state is swept here; adding a new limiter means
|
||||
/// adding it to this list.
|
||||
pub(crate) async fn sweep_rate_limiters(&self) {
|
||||
self.rate_limiter.cleanup().await;
|
||||
self.create_ip_rate_limiter.cleanup().await;
|
||||
self.push_rate_limiter.cleanup().await;
|
||||
self.close_issue_rate_limiter.cleanup().await;
|
||||
self.ipfs_rate_limiter.cleanup().await;
|
||||
self.ipfs_work_rate_limiter.cleanup().await;
|
||||
self.sync_trigger_rate_limiter.cleanup().await;
|
||||
self.peer_write_rate_limiter.cleanup().await;
|
||||
}
|
||||
|
||||
/// Trigger graceful shutdown. Idempotent — calling more than once
|
||||
/// has no effect. Returns `true` if this call was the one that
|
||||
/// flipped the signal.
|
||||
@@ -373,130 +255,6 @@ impl AppState {
|
||||
pub fn is_shutting_down(&self) -> bool {
|
||||
*self.shutdown_tx.borrow()
|
||||
}
|
||||
|
||||
/// Legacy-probe budget wired from the `GITLAWB_IPFS_MAX_LEGACY_PROBES` operator
|
||||
/// knob. The knob seeds `ipfs_max_legacy_probes` at construction so it controls the
|
||||
/// per-request legacy (NULL-provenance) probe fan-out it advertises. It deliberately
|
||||
/// does NOT feed the history-walk ceiling: that is governed by
|
||||
/// `ipfs_max_repos_walked` under a `MAX_PIN_SOURCES + 1` floor, because a value
|
||||
/// below the floor truncates a provenanced request with a full source set into a
|
||||
/// false 503. The knob is `usize`, the field `u32`; the range cap (1_048_576) keeps
|
||||
/// the cast lossless.
|
||||
pub(crate) fn ipfs_legacy_probe_budget(config: &crate::config::Config) -> u32 {
|
||||
config.ipfs_max_legacy_probes as u32
|
||||
}
|
||||
|
||||
/// Legacy-scan ROW budget wired from the `GITLAWB_IPFS_MAX_LEGACY_SCAN_ROWS` knob,
|
||||
/// the same helper shape as the probe budget above so the knob cannot become a
|
||||
/// silent no-op if a struct literal drifts back to the bare constant.
|
||||
pub(crate) fn ipfs_legacy_scan_row_budget(config: &crate::config::Config) -> usize {
|
||||
config.ipfs_max_legacy_scan_rows
|
||||
}
|
||||
|
||||
/// The key sealing legacy-scan continuation tokens (INV-13), DERIVED from the node's
|
||||
/// persistent identity rather than minted per boot.
|
||||
///
|
||||
/// HKDF-SHA256 over the node's Ed25519 seed, the same key material
|
||||
/// `load_or_create_keypair` reads back from its PKCS#8 PEM on every boot, so the
|
||||
/// derived key is byte-identical after a restart or a rolling deploy.
|
||||
///
|
||||
/// Two properties the derivation has to carry, both load-bearing:
|
||||
///
|
||||
/// * DOMAIN SEPARATION. The `info` string below is unique to this use, so the
|
||||
/// derived key is not the signing seed and is not any other secret derived from
|
||||
/// it. HKDF is one-way, so a leaked token key yields nothing about the signing
|
||||
/// key and cannot be turned against a signature.
|
||||
/// * A VERSION component, carried in the same `info` string
|
||||
/// ([`SCAN_TOKEN_KEY_INFO`]) alongside a fixed [`SCAN_TOKEN_KEY_SALT`]. Bumping
|
||||
/// the version rotates every token key on the next boot without touching the
|
||||
/// identity, the token format, or any caller, so rotation is a constant change
|
||||
/// rather than a fork of this derivation.
|
||||
pub(crate) fn derive_scan_token_key(keypair: &Keypair) -> [u8; 32] {
|
||||
use hmac::{Hmac, Mac};
|
||||
type HmacSha256 = Hmac<sha2::Sha256>;
|
||||
|
||||
let seed = keypair.to_seed();
|
||||
// HKDF-Extract: PRK = HMAC(salt, ikm).
|
||||
let mut extract =
|
||||
HmacSha256::new_from_slice(SCAN_TOKEN_KEY_SALT).expect("HMAC takes a key of any size");
|
||||
extract.update(seed.as_slice());
|
||||
let prk = extract.finalize().into_bytes();
|
||||
// HKDF-Expand, one block: T(1) = HMAC(PRK, info || 0x01). One 32-byte output
|
||||
// needs exactly one block of SHA-256, so there is no counter loop to get wrong.
|
||||
let mut expand =
|
||||
HmacSha256::new_from_slice(prk.as_slice()).expect("HMAC takes a key of any size");
|
||||
expand.update(SCAN_TOKEN_KEY_INFO);
|
||||
expand.update(&[0x01]);
|
||||
expand.finalize().into_bytes().into()
|
||||
}
|
||||
|
||||
/// Work-budget capacity for [`ipfs_work_rate_limiter`](Self#structfield.ipfs_work_rate_limiter)
|
||||
/// (R6, KTD6), DERIVED from the route limit rather than a new operator knob. The route
|
||||
/// limiter (`ipfs_rate_limiter`) charges once per request; this separate bucket absorbs
|
||||
/// the resolver's per-probe/per-walk work charges so both the route "requests per hour"
|
||||
/// contract and the amplification bound hold. Floor: at least one complete COMBINED
|
||||
/// resolution per window, the provenance phase's walks plus a full legacy search
|
||||
/// (probes plus page tolls), so a single default-config resolution cannot
|
||||
/// self-throttle part-way and recreate the admit-then-429 for a legitimate caller.
|
||||
/// `GITLAWB_IPFS_RATE_LIMIT=0`
|
||||
/// disables the route brake and this derived bucket alike (a 0-capacity limiter admits
|
||||
/// everything).
|
||||
///
|
||||
/// The floor carries a WALK term (#173 round 15, F2). The provenance visibility walk
|
||||
/// in `gate_and_serve` debits this SAME bucket (its `!legacy_scan` charge), once per
|
||||
/// path-scoped source, before the legacy fallback runs at all, and the walk cap is
|
||||
/// charged per phase. A floor counting only the search therefore under-sizes the
|
||||
/// window by up to that cap exactly when the floor binds (a route limit set below
|
||||
/// it): the provenance phase spends from the budget the floor reserved for the
|
||||
/// search, the fallback 429s short of its configured reach, and the retry re-pays the
|
||||
/// same provenance charges. The term is
|
||||
/// `min(MAX_HISTORY_WALKS_PER_REQUEST, ipfs_max_repos_walked)` because that is what
|
||||
/// the resolver's own `walk_cap` in `gate_and_serve` evaluates to. The two
|
||||
/// expressions are separate, not one shared value: this one reads the CONSTANT
|
||||
/// `crate::api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST`, while `walk_cap` reads the
|
||||
/// `AppState` seam `state.ipfs_max_history_walks`. They agree only because every
|
||||
/// construction seeds that seam from that constant: the production one in `main.rs`,
|
||||
/// and the two test ones in `auth`'s test module and `test_support`. Nothing
|
||||
/// mechanically ties the two expressions beyond this comment and its counterpart at
|
||||
/// `walk_cap` (no shared helper, no type, no assertion outside the one fixture that
|
||||
/// pins the seam as a precondition), so the two `min()`s have to be moved together
|
||||
/// by hand, and a construction that seeded the seam from anything else would size
|
||||
/// the floor for a cap the resolver does not enforce. It reads the
|
||||
/// CONSTANT and the CONFIG knob for the same reason the page term below reads the
|
||||
/// constant page size: `ipfs_max_history_walks` is an `AppState` test seam, and
|
||||
/// sizing a production floor from a seam would inflate the budget by whatever a test
|
||||
/// chose.
|
||||
///
|
||||
/// The PROBE term is the LEGACY-PROBE knob, not `ipfs_max_repos_walked`. Those were
|
||||
/// one field before the walk cap and the probe budget were split apart, and sizing
|
||||
/// the probe term off the walk cap would silently read 64 instead of 256. That is a
|
||||
/// statement about which knob sizes the PROBE term; it is not a claim that the walk
|
||||
/// cap has no place in the floor, since the walk term above is added to this one
|
||||
/// rather than substituted for it.
|
||||
///
|
||||
/// The floor also carries the scan's PAGE toll (#173 round 13, F2): every page the
|
||||
/// legacy scan buys is charged to this same bucket, so a deep scan spends
|
||||
/// `ceil(ipfs_max_legacy_scan_rows / LEGACY_SCAN_PAGE_ROWS)` tokens on pages on top
|
||||
/// of its probes. Leaving those out would 429 an honest caller part-way down their
|
||||
/// own continuation-token ladder, which is the F6 admit-then-429 shape in a new
|
||||
/// place. The page term uses the CONSTANT page size, not `AppState`'s field: the
|
||||
/// field is a test seam that shrinks pages to make paging observable, and sizing a
|
||||
/// production floor from it would inflate the budget by whatever a test chose.
|
||||
pub(crate) fn ipfs_work_budget(config: &crate::config::Config) -> usize {
|
||||
if config.ipfs_rate_limit == 0 {
|
||||
return 0;
|
||||
}
|
||||
let pages = config
|
||||
.ipfs_max_legacy_scan_rows
|
||||
.div_ceil(crate::api::ipfs::LEGACY_SCAN_PAGE_ROWS);
|
||||
let walks = std::cmp::min(
|
||||
crate::api::ipfs::MAX_HISTORY_WALKS_PER_REQUEST as usize,
|
||||
config.ipfs_max_repos_walked,
|
||||
);
|
||||
config
|
||||
.ipfs_rate_limit
|
||||
.max(config.ipfs_max_legacy_probes + pages + walks)
|
||||
}
|
||||
}
|
||||
|
||||
/// Bounds the OUTSTANDING post-push encryption-task set by per-repo coalescing
|
||||
@@ -1468,80 +1226,3 @@ mod repo_write_lease_tests {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod scan_token_key_tests {
|
||||
use super::AppState;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
use gitlawb_core::scan_token::{open_scan_token, seal_scan_token, ScanPosition};
|
||||
|
||||
const CID: &str = "bafkreiscantokenkeyfixtureaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
|
||||
|
||||
fn pos() -> ScanPosition {
|
||||
ScanPosition {
|
||||
created_at_key: "2020-01-01T12:00:00+00:00".to_string(),
|
||||
id: "did:key:z6MkScanTokenOwner/repo".to_string(),
|
||||
// 40 hex: the production shape, since the node's own repos are sha1.
|
||||
sha256_hex: "a1b2c3d4e5f60718293a4b5c6d7e8f9012345678".to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
/// The RESTART case. A token minted before a restart must still open after it, or a
|
||||
/// caller laddering a deep inventory is silently returned to the front of the scan on
|
||||
/// every rolling deploy and can never reach a holder buried past one window.
|
||||
///
|
||||
/// The second key is derived from the identity RELOADED THROUGH ITS ON-DISK PEM,
|
||||
/// which is exactly what `load_or_create_keypair` does on boot, so this exercises the
|
||||
/// real restart path rather than a clone of the in-memory keypair.
|
||||
#[test]
|
||||
fn scan_token_key_survives_a_restart_of_the_same_identity() {
|
||||
let kp = Keypair::generate();
|
||||
let pem = kp.to_pem().expect("the identity serializes");
|
||||
let reloaded = Keypair::from_pem(&pem).expect("the identity reloads");
|
||||
|
||||
let before = AppState::derive_scan_token_key(&kp);
|
||||
let after = AppState::derive_scan_token_key(&reloaded);
|
||||
|
||||
let token = seal_scan_token(&before, CID, &pos(), i64::MAX - 1).expect("seal");
|
||||
assert_eq!(
|
||||
open_scan_token(&after, CID, &token, 0),
|
||||
Some(pos()),
|
||||
"a continuation minted before a restart must open after it: the node's \
|
||||
identity is the same, so the derived sealing key must be too"
|
||||
);
|
||||
}
|
||||
|
||||
/// The must-not: a DIFFERENT node identity must derive a DIFFERENT key, so a token is
|
||||
/// no more portable between nodes than it was when the key was random per boot.
|
||||
#[test]
|
||||
fn scan_token_key_does_not_open_under_a_different_identity() {
|
||||
let mine = Keypair::generate();
|
||||
let theirs = Keypair::generate();
|
||||
|
||||
let token = seal_scan_token(
|
||||
&AppState::derive_scan_token_key(&mine),
|
||||
CID,
|
||||
&pos(),
|
||||
i64::MAX - 1,
|
||||
)
|
||||
.expect("seal");
|
||||
assert_eq!(
|
||||
open_scan_token(&AppState::derive_scan_token_key(&theirs), CID, &token, 0),
|
||||
None,
|
||||
"a continuation sealed by one node must not open under another node's identity"
|
||||
);
|
||||
}
|
||||
|
||||
/// Domain separation, executed rather than asserted in prose: the derived token key
|
||||
/// must not be the signing seed itself. Compromising a token key must not hand an
|
||||
/// attacker the material that signs.
|
||||
#[test]
|
||||
fn scan_token_key_is_not_the_signing_seed() {
|
||||
let kp = Keypair::generate();
|
||||
assert_ne!(
|
||||
AppState::derive_scan_token_key(&kp),
|
||||
*kp.to_seed(),
|
||||
"the token key must be a DERIVED secret, never the Ed25519 signing seed"
|
||||
);
|
||||
}
|
||||
}
|
||||
+29
-11176
File diff suppressed because it is too large.
Load diff
@@ -437,31 +437,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
// #135 T1: a Mode-B rule on `/secret/**` must DENY the withheld directory's
|
||||
// OWN path `/secret` (the `path == prefix` arm), not just strict descendants —
|
||||
// otherwise get_by_cid's tree gate would serve the /secret tree object and leak
|
||||
// its children. Pins parity with get_tree, which denies the /secret path.
|
||||
#[test]
|
||||
fn subtree_rule_denies_the_withheld_directory_itself() {
|
||||
let reader = "did:key:z6MkReader";
|
||||
let rules = [rule("/secret/**", VisibilityMode::B, &[reader])];
|
||||
assert_eq!(
|
||||
visibility_check(&rules, true, OWNER, None, "/secret"),
|
||||
Decision::Deny,
|
||||
"anon denied at the withheld directory's OWN path /secret"
|
||||
);
|
||||
assert_eq!(
|
||||
visibility_check(&rules, true, OWNER, None, "/public"),
|
||||
Decision::Allow,
|
||||
"anon allowed at a sibling path outside the withheld subtree"
|
||||
);
|
||||
assert_eq!(
|
||||
visibility_check(&rules, true, OWNER, Some(reader), "/secret"),
|
||||
Decision::Allow,
|
||||
"listed reader allowed at the withheld directory (caller-aware)"
|
||||
);
|
||||
}
|
||||
|
||||
// #153 regression: cross-method DID must still be denied even when the
|
||||
// trailing segment collides with a bare owner key.
|
||||
#[test]
|
||||
|
||||
@@ -29,7 +29,6 @@ fn inv22_concurrency_gates_present_and_not_bypassed() {
|
||||
let repos = src("api/repos.rs");
|
||||
let smart_http = src("git/smart_http.rs");
|
||||
let vis = src("git/visibility_pack.rs");
|
||||
let ipfs = src("api/ipfs.rs");
|
||||
|
||||
// U1 / P1-a: run_bounded_git stands the watchdog down only after confirming the
|
||||
// child actually terminated (WNOWAIT), not on the raw stdout-drain EOF — otherwise
|
||||
@@ -69,57 +68,6 @@ fn inv22_concurrency_gates_present_and_not_bypassed() {
|
||||
withheld_recipients_gated, which acquires git_encrypt_semaphore"
|
||||
);
|
||||
|
||||
// U1 / R2 (#173 round-10): the path-scoped filtered-pack serve must thread the
|
||||
// caller's AdmissionGuard through BOTH git stages so read + per-caller admission is
|
||||
// held until the pack-objects group is reaped on disconnect, closing the cap bypass
|
||||
// the plain upload_pack path already fixed. Two load-bearing markers: rev-list hands
|
||||
// the disarmed guard back (its tuple return type), and build_filtered_pack forwards
|
||||
// that guard into the pack-objects stage (the `admission` arg after the
|
||||
// "pack-objects" label). Reverting either — dropping the guard between stages, or
|
||||
// passing `None` to pack-objects — trips this.
|
||||
assert!(
|
||||
smart_http.contains("Result<(Vec<String>, Option<AdmissionGuard>)>")
|
||||
&& smart_http.contains("\"pack-objects\",\n admission,"),
|
||||
"U1/R2 gate missing: build_filtered_pack must thread the AdmissionGuard through \
|
||||
rev-list -> pack-objects so the permits are held until the pack-objects group \
|
||||
is reaped on disconnect (the path-scoped half of #174 P1-a)"
|
||||
);
|
||||
|
||||
// U2 / R1: a cancelled or timed-out `GET /ipfs/{cid}` must release admission only
|
||||
// after the blocking work it admitted has finished, not the instant the handler
|
||||
// future drops (the /ipfs half of #174 P1-a). The mechanism is the shared
|
||||
// `Arc<WalkAdmission>`: both walk permits are moved into it once per request and a
|
||||
// clone rides every `spawn_blocking`, so the permits release when the LAST holder
|
||||
// drops. Reverting to handler-local permits trips this; the per-site clones are
|
||||
// bound separately by `inv22_ipfs_walk_admission_reaches_every_blocking_site`.
|
||||
//
|
||||
// This previously required the permits to be owned by a detached `tokio::spawn`
|
||||
// running the whole pipeline. That closed the same bypass but kept an abandoned
|
||||
// request's full legacy scan running against a held slot, so the merge of #173 and
|
||||
// #174 kept the Arc and dropped the detached task.
|
||||
assert!(
|
||||
ipfs.contains("struct WalkAdmission")
|
||||
&& ipfs.contains("let admission = std::sync::Arc::new(WalkAdmission {"),
|
||||
"U2/R1 gate missing: get_by_cid must move both /ipfs admission permits into a \
|
||||
shared Arc<WalkAdmission> whose clones ride the blocking work, so admission is \
|
||||
released only once that work completes (the /ipfs half of #174 P1-a)"
|
||||
);
|
||||
|
||||
// U2 / KTD2 (#173 round-10): the probe/read children on the /ipfs path must be the
|
||||
// duration-bounded twins (process-group teardown via run_bounded_git), not the bare
|
||||
// `store::object_type` / `read_object_content` (or an unbounded `cat-file -s`) a tokio
|
||||
// timeout cannot cancel — otherwise a wedged cat-file lingers and pins the held
|
||||
// admission past the deadline. Reverting any twin call site back to a bare read trips
|
||||
// this.
|
||||
assert!(
|
||||
ipfs.contains("object_type_bounded(")
|
||||
&& ipfs.contains("object_size_bounded(")
|
||||
&& ipfs.contains("read_object_content_bounded("),
|
||||
"U2/KTD2 gate missing: the /ipfs probe+read must call the run_bounded_git-backed \
|
||||
*_bounded twins so a wedged cat-file is reaped at the deadline, not left to pin \
|
||||
the held /ipfs walk admission"
|
||||
);
|
||||
|
||||
// P1-e non-bypass tripwire: the bounded recipients walk is spawn_blocking'd nowhere
|
||||
// but inside withheld_recipients_gated. A second call site (count > 1) is a new
|
||||
// detached git walk that skips the admission gate — exactly the class U5 closed.
|
||||
@@ -147,12 +95,8 @@ fn inv22_concurrency_gates_present_and_not_bypassed() {
|
||||
// recovery copies are absent until an unrelated later push. Scan only the
|
||||
// production half of the file — the u5 tests in its `mod tests` also name the
|
||||
// drain call, and matching them would make this check vacuous.
|
||||
// Split at the TEST MODULE, not at the first `#[cfg(test)]`. api/repos.rs carries
|
||||
// test-only items (the drain fault seam, the task entry point) ABOVE the production
|
||||
// code these gates scan for, so splitting on the attribute truncated the production
|
||||
// half above every line being checked and the gate went vacuously blind.
|
||||
let repos_production = repos
|
||||
.split("\nmod tests {")
|
||||
.split("#[cfg(test)]")
|
||||
.next()
|
||||
.expect("split always yields a first chunk");
|
||||
assert!(
|
||||
@@ -225,8 +169,7 @@ fn f4_release_keeps_conn_owned_until_unlock_resolves() {
|
||||
let repo_store = src("git/repo_store.rs");
|
||||
|
||||
let rel_start = repo_store
|
||||
.find("pub async fn release(self")
|
||||
.or_else(|| repo_store.find("pub async fn release(mut self"))
|
||||
.find("pub async fn release(mut self")
|
||||
.expect("F4 gate: repo_store.rs no longer defines RepoWriteGuard::release");
|
||||
let rel_end = repo_store[rel_start..]
|
||||
.find("impl Drop for RepoWriteGuard")
|
||||
@@ -258,10 +201,10 @@ fn f4_release_keeps_conn_owned_until_unlock_resolves() {
|
||||
);
|
||||
}
|
||||
|
||||
/// F6/KTD-5 (IPFS metadata queries deadline-wrapped): `get_by_cid` acquires
|
||||
/// the scarce walk permits (RAII, held for the whole request) BEFORE its metadata
|
||||
/// queries, and the per-repo loop's first budget gate runs only later. So
|
||||
/// both `list_repos_page_for_scan` and `list_visibility_rules_for_repos` must be clamped to the
|
||||
/// F6/KTD-5 (initial IPFS metadata queries deadline-wrapped): `get_by_cid` acquires
|
||||
/// the scarce walk permits (RAII, held for the whole request) BEFORE its two initial
|
||||
/// metadata queries, and the per-repo loop's first budget gate runs only later. So
|
||||
/// both `list_all_repos` and `list_visibility_rules_for_repos` must be clamped to the
|
||||
/// remaining request budget — otherwise a query blocked in Postgres pins the walk slot
|
||||
/// for the whole stall, past the budget. This scans the PRODUCTION half of `api/ipfs.rs`
|
||||
/// (the `mod tests` half names the same calls in its own harness and would make the
|
||||
@@ -271,44 +214,31 @@ fn f4_release_keeps_conn_owned_until_unlock_resolves() {
|
||||
#[test]
|
||||
fn f6_ipfs_metadata_queries_are_deadline_wrapped() {
|
||||
let ipfs = src("api/ipfs.rs");
|
||||
// Split at the TEST MODULE, not at the first `#[cfg(test)]`: the handler carries
|
||||
// in-line `#[cfg(test)]` query counters, so splitting on the attribute cut the
|
||||
// production half off above the calls this guard exists to check and the scan went
|
||||
// vacuously quiet (found 0 of each rather than failing on a missing wrapper).
|
||||
let production = ipfs
|
||||
.split("\nmod tests {")
|
||||
.split("#[cfg(test)]")
|
||||
.next()
|
||||
.expect("split always yields a first chunk");
|
||||
|
||||
// EVERY occurrence must be wrapped, not just the first. The handler now reaches
|
||||
// these queries from two places (the provenance fast path, one repo at a time, and
|
||||
// the legacy scan's preload), and an exact-count check would have to be relaxed
|
||||
// every time a call site is added, which is how a guard quietly stops covering the
|
||||
// site that matters. Requiring all of them scales with the code instead.
|
||||
for call in [
|
||||
".list_repos_page_for_scan(",
|
||||
".list_visibility_rules_for_repos(",
|
||||
".get_repo_by_id(",
|
||||
".is_repo_quarantined(",
|
||||
] {
|
||||
let occurrences = production.matches(call).count();
|
||||
for call in [".list_all_repos()", ".list_visibility_rules_for_repos("] {
|
||||
assert_eq!(
|
||||
production.matches(call).count(),
|
||||
1,
|
||||
"F6 guard stale: `{call}` must appear exactly once in the production half \
|
||||
of api/ipfs.rs (the deadline-wrapped handler call) — update this guard"
|
||||
);
|
||||
let idx = production
|
||||
.find(call)
|
||||
.unwrap_or_else(|| panic!("F6 gate: api/ipfs.rs no longer calls `{call}`"));
|
||||
// The wrapper opens a few lines above the call (match tokio::time::timeout( ...
|
||||
// remaining budget ..., <query> )); a 240-char lookback covers it without
|
||||
// reaching the previous statement.
|
||||
let window = &production[idx.saturating_sub(240)..idx];
|
||||
assert!(
|
||||
occurrences >= 1,
|
||||
"F6 guard stale: api/ipfs.rs no longer calls `{call}` — update this guard"
|
||||
window.contains("tokio::time::timeout("),
|
||||
"F6 gate missing: `{call}` must be wrapped in tokio::time::timeout(...) \
|
||||
clamped to the remaining request budget. An unwrapped await pins the held \
|
||||
walk permit for the whole DB stall, past GITLAWB_IPFS_REQUEST_BUDGET_SECS."
|
||||
);
|
||||
for (n, (idx, _)) in production.match_indices(call).enumerate() {
|
||||
// The wrapper opens a few lines above the call (match tokio::time::timeout(
|
||||
// ... remaining budget ..., <query> )); a 240-char lookback covers it
|
||||
// without reaching the previous statement.
|
||||
let window = &production[idx.saturating_sub(240)..idx];
|
||||
assert!(
|
||||
window.contains("tokio::time::timeout("),
|
||||
"F6 gate missing: occurrence {n} of `{call}` (of {occurrences}) is not \
|
||||
wrapped in tokio::time::timeout(...) clamped to the remaining request \
|
||||
budget. An unwrapped await pins the held walk permit for the whole DB \
|
||||
stall, past GITLAWB_IPFS_REQUEST_BUDGET_SECS."
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -331,12 +261,8 @@ fn f6_ipfs_metadata_queries_are_deadline_wrapped() {
|
||||
#[test]
|
||||
fn f2_pinata_enqueues_refs_not_retained_object_lists() {
|
||||
let repos = src("api/repos.rs");
|
||||
// Split at the TEST MODULE, not at the first `#[cfg(test)]`. api/repos.rs carries
|
||||
// test-only items (the drain fault seam, the task entry point) ABOVE the production
|
||||
// code these gates scan for, so splitting on the attribute truncated the production
|
||||
// half above every line being checked and the gate went vacuously blind.
|
||||
let production = repos
|
||||
.split("\nmod tests {")
|
||||
.split("#[cfg(test)]")
|
||||
.next()
|
||||
.expect("split always yields a first chunk");
|
||||
|
||||
@@ -395,12 +321,8 @@ fn f2_pinata_enqueues_refs_not_retained_object_lists() {
|
||||
fn f3_second_writer_leased_until_reap() {
|
||||
let repos = src("api/repos.rs");
|
||||
let smart_http = src("git/smart_http.rs");
|
||||
// Split at the TEST MODULE, not at the first `#[cfg(test)]`. api/repos.rs carries
|
||||
// test-only items (the drain fault seam, the task entry point) ABOVE the production
|
||||
// code these gates scan for, so splitting on the attribute truncated the production
|
||||
// half above every line being checked and the gate went vacuously blind.
|
||||
let repos_production = repos
|
||||
.split("\nmod tests {")
|
||||
.split("#[cfg(test)]")
|
||||
.next()
|
||||
.expect("split always yields a first chunk");
|
||||
|
||||
@@ -450,7 +372,7 @@ fn f3_second_writer_leased_until_reap() {
|
||||
/// exists: it binds all three sites, and any blocking site added to this loop
|
||||
/// later, without reversing that deliberate independence.
|
||||
///
|
||||
/// MUTATION (RED): delete any one `Arc::clone(ctx.admission)` binding, or drop the
|
||||
/// MUTATION (RED): delete any one `Arc::clone(&admission)` binding, or drop the
|
||||
/// clone from inside its closure, and the count falls below three.
|
||||
#[test]
|
||||
fn inv22_ipfs_walk_admission_reaches_every_blocking_site() {
|
||||
@@ -464,10 +386,7 @@ fn inv22_ipfs_walk_admission_reaches_every_blocking_site() {
|
||||
);
|
||||
|
||||
// Every blocking site in the scan takes its own clone...
|
||||
// `Arc::clone(ctx.admission)` in the gate, `Arc::clone(&admission)` if a site is
|
||||
// ever added back in the handler body itself; count both spellings.
|
||||
let clones = ipfs.matches("Arc::clone(ctx.admission)").count()
|
||||
+ ipfs.matches("Arc::clone(&admission)").count();
|
||||
let clones = ipfs.matches("Arc::clone(&admission)").count();
|
||||
assert!(
|
||||
clones >= 3,
|
||||
"U1 gate bypassed: expected an admission clone for each of the three \
|
||||
@@ -524,12 +443,8 @@ fn inv22_ipfs_walk_admission_reaches_every_blocking_site() {
|
||||
fn inv22_replication_tail_spawns_at_the_durability_boundary() {
|
||||
let repos = src("api/repos.rs");
|
||||
// Production half only — the tests below name these identifiers too.
|
||||
// Split at the TEST MODULE, not at the first `#[cfg(test)]`. api/repos.rs carries
|
||||
// test-only items (the drain fault seam, the task entry point) ABOVE the production
|
||||
// code these gates scan for, so splitting on the attribute truncated the production
|
||||
// half above every line being checked and the gate went vacuously blind.
|
||||
let production = repos
|
||||
.split("\nmod tests {")
|
||||
.split("#[cfg(test)]")
|
||||
.next()
|
||||
.expect("split always yields a first chunk");
|
||||
|
||||
@@ -545,7 +460,7 @@ fn inv22_replication_tail_spawns_at_the_durability_boundary() {
|
||||
.find("tokio::spawn(post_receive_replication_tail(")
|
||||
.expect("U5 gate missing: the replication tail must be spawned by git_receive_pack");
|
||||
let release = production
|
||||
.find(".release(push_succeeded)")
|
||||
.find("guard.release(push_succeeded)")
|
||||
.expect("U5 gate stale: release must consume the same success flag as the tail gate");
|
||||
let touch = production
|
||||
.find("state.db.touch_repo(")
|
||||
|
||||
@@ -11,7 +11,7 @@ name = "gl"
|
||||
path = "src/main.rs"
|
||||
|
||||
[dependencies]
|
||||
gitlawb-core = { path = "../gitlawb-core", features = ["redirect"] }
|
||||
gitlawb-core = { path = "../gitlawb-core" }
|
||||
icaptcha-client = { path = "../icaptcha-client" }
|
||||
base64 = { workspace = true }
|
||||
tokio = { workspace = true }
|
||||
|
||||
+8
-259
@@ -12,58 +12,9 @@ use serde::Deserialize;
|
||||
use std::path::Path;
|
||||
use std::process::Command;
|
||||
|
||||
use crate::http::{sanitize_node_msg, NodeClient};
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
/// Report why one candidate blob could not be recovered, in the register of the
|
||||
/// recovery loop's other warnings.
|
||||
///
|
||||
/// Both halves are gateway-supplied text on their way to a terminal: the oid comes
|
||||
/// out of a manifest fetched from a caller-chosen Arweave gateway, and a transport
|
||||
/// error carries the URL the same manifest chose. So the whole line is defanged and
|
||||
/// length-capped, like every other node/gateway string this crate prints.
|
||||
///
|
||||
/// Under `cfg(test)` the line is also mirrored into a per-thread buffer, so a test
|
||||
/// can assert the loop actually says what it skipped rather than only that it
|
||||
/// returned nothing.
|
||||
fn warn_skip(oid: &str, why: &str) {
|
||||
emit_warning(&format!(
|
||||
"warning: could not fetch encrypted blob {oid}: {why}; skipping"
|
||||
));
|
||||
}
|
||||
|
||||
/// The same report for a manifest rather than a blob. The manifest is one step
|
||||
/// earlier in the same recovery: losing it silently means every blob it would have
|
||||
/// named is missing with no reason given anywhere.
|
||||
fn warn_skip_manifest(id: &str, why: &str) {
|
||||
emit_warning(&format!(
|
||||
"warning: could not fetch blob manifest {id}: {why}; skipping"
|
||||
));
|
||||
}
|
||||
|
||||
/// Sanitize a warning and write it, once.
|
||||
///
|
||||
/// The write goes to [`warn_sink`], which is stderr in a normal build and the tests'
|
||||
/// per-thread mirror under `cfg(test)`. That indirection is the point: the mirror
|
||||
/// used to sit BESIDE an `eprintln!`, so deleting the user-visible write left every
|
||||
/// assertion on the mirror green and the shipped behaviour could be removed with the
|
||||
/// tests unchanged. There is one write now, and the tests observe it.
|
||||
fn emit_warning(line: &str) {
|
||||
use std::io::Write;
|
||||
let line = sanitize_node_msg(line);
|
||||
let _ = writeln!(warn_sink(), "{line}");
|
||||
}
|
||||
|
||||
#[cfg(not(test))]
|
||||
fn warn_sink() -> impl std::io::Write {
|
||||
std::io::stderr()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
fn warn_sink() -> impl std::io::Write {
|
||||
tests::WarnMirror
|
||||
}
|
||||
|
||||
#[derive(Args)]
|
||||
pub struct CloneArgs {
|
||||
/// Repo to clone: gitlawb://<owner_did>/<name> or <owner>/<name>.
|
||||
@@ -361,25 +312,10 @@ async fn recover_encrypted_blobs(
|
||||
.await
|
||||
{
|
||||
Ok(r) if r.status().is_success() => r,
|
||||
// The node path has the same silent exit the gateway path had: a 403, a
|
||||
// 404, or a dead connection all reached the caller as "blob not
|
||||
// recoverable" with no reason attached. One unreachable blob still must
|
||||
// not end the recovery of the rest, so it warns and moves on.
|
||||
Ok(r) => {
|
||||
warn_skip(oid, &format!("node returned {}", r.status()));
|
||||
continue;
|
||||
}
|
||||
Err(e) => {
|
||||
warn_skip(oid, &format!("node request failed: {e}"));
|
||||
continue;
|
||||
}
|
||||
_ => continue,
|
||||
};
|
||||
let envelope = match env_resp.bytes().await {
|
||||
Ok(b) => b,
|
||||
Err(e) => {
|
||||
warn_skip(oid, &format!("reading the envelope failed: {e}"));
|
||||
continue;
|
||||
}
|
||||
let Ok(envelope) = env_resp.bytes().await else {
|
||||
continue;
|
||||
};
|
||||
let plaintext = match open_blob(&envelope, keypair) {
|
||||
Ok(p) => p,
|
||||
@@ -706,14 +642,7 @@ async fn recover_from_arweave(
|
||||
for r in refs {
|
||||
let m = match client.get(format!("{ag}/{}", r.id)).send().await {
|
||||
Ok(resp) if resp.status().is_success() => resp,
|
||||
Ok(resp) => {
|
||||
warn_skip_manifest(&r.id, &format!("gateway returned {}", resp.status()));
|
||||
continue;
|
||||
}
|
||||
Err(e) => {
|
||||
warn_skip_manifest(&r.id, &format!("gateway request failed: {e}"));
|
||||
continue;
|
||||
}
|
||||
_ => continue,
|
||||
};
|
||||
if let Ok(parsed) = m.json::<Manifest>().await {
|
||||
manifests.push((parsed, r.height));
|
||||
@@ -755,31 +684,10 @@ async fn recover_from_arweave(
|
||||
}
|
||||
let env_resp = match client.get(format!("{ig}/ipfs/{cid}")).send().await {
|
||||
Ok(r) if r.status().is_success() => r,
|
||||
// Every other outcome used to leave through a bare `continue`, so a
|
||||
// gateway that answered 503, 404, or nothing at all was reported to the
|
||||
// caller as "blob not recoverable" with no reason attached. This is the
|
||||
// second in-repo client of GET /ipfs/{cid} and it has no resume ladder,
|
||||
// so saying what happened is all the recourse there is. It still skips to
|
||||
// the next candidate either way: one unreachable blob must not end the
|
||||
// recovery of the rest.
|
||||
Ok(r) => {
|
||||
warn_skip(&oid, &format!("gateway returned {}", r.status()));
|
||||
continue;
|
||||
}
|
||||
Err(e) => {
|
||||
warn_skip(&oid, &format!("gateway request failed: {e}"));
|
||||
continue;
|
||||
}
|
||||
_ => continue,
|
||||
};
|
||||
// A body that dies part-way through is the same mid-read failure the capped
|
||||
// read exists to stop rendering as silence, and it sits INSIDE the loop whose
|
||||
// status arms were already fixed.
|
||||
let envelope = match env_resp.bytes().await {
|
||||
Ok(b) => b,
|
||||
Err(e) => {
|
||||
warn_skip(&oid, &format!("reading the envelope failed: {e}"));
|
||||
continue;
|
||||
}
|
||||
let Ok(envelope) = env_resp.bytes().await else {
|
||||
continue;
|
||||
};
|
||||
// open_blob succeeds only if this caller is a recipient: this is the
|
||||
// authorization gate (no node, no DID check needed).
|
||||
@@ -893,42 +801,9 @@ pub async fn run(args: CloneArgs) -> Result<()> {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::cell::RefCell;
|
||||
use std::process::Command;
|
||||
use tempfile::TempDir;
|
||||
|
||||
thread_local! {
|
||||
/// Test-visible copy of the stderr warnings `warn_skip` emits.
|
||||
/// `#[tokio::test]` runs the future on the test's own thread, so a
|
||||
/// thread-local is enough.
|
||||
static WARNINGS: RefCell<String> = const { RefCell::new(String::new()) };
|
||||
}
|
||||
|
||||
/// The `cfg(test)` warning sink. `emit_warning` writes here instead of to
|
||||
/// stderr, so the assertions below observe the shipped write rather than a copy
|
||||
/// made beside it: delete that write and they go red.
|
||||
pub(super) struct WarnMirror;
|
||||
|
||||
impl std::io::Write for WarnMirror {
|
||||
fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
|
||||
let text = String::from_utf8_lossy(buf).into_owned();
|
||||
WARNINGS.with(|w| w.borrow_mut().push_str(&text));
|
||||
Ok(buf.len())
|
||||
}
|
||||
|
||||
fn flush(&mut self) -> std::io::Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
fn reset_warnings() {
|
||||
WARNINGS.with(|w| w.borrow_mut().clear());
|
||||
}
|
||||
|
||||
fn warnings() -> String {
|
||||
WARNINGS.with(|w| w.borrow().clone())
|
||||
}
|
||||
|
||||
fn g(args: &[&str], dir: &Path) {
|
||||
assert!(Command::new("git")
|
||||
.args(args)
|
||||
@@ -1380,132 +1255,6 @@ mod tests {
|
||||
assert_eq!(a.get("o1").map(String::as_str), Some("cidTS"));
|
||||
}
|
||||
|
||||
/// A gateway that refuses one blob must SAY so, and must not take the rest of the
|
||||
/// recovery down with it.
|
||||
///
|
||||
/// The IPFS fetch used to leave through a bare `_ => continue` on every
|
||||
/// non-success, so a 503 (the truncation status a tuned node makes more likely),
|
||||
/// a 404, and a dead connection all reached the caller as the same silent "blob
|
||||
/// not recoverable". Two withheld blobs here: the gateway answers 503 for the
|
||||
/// first and serves the second. The recovered path proves the loop continued; the
|
||||
/// warning proves the skip was reported and names both the object and the status.
|
||||
#[tokio::test]
|
||||
async fn recover_from_arweave_reports_a_refusing_gateway_and_continues() {
|
||||
use gitlawb_core::encrypt::seal_blob;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
|
||||
reset_warnings();
|
||||
let (td, url) = bare_remote(&[
|
||||
("public/a.txt", b"pub\n"),
|
||||
("secret/b.txt", b"SECRET B\n"),
|
||||
("secret/c.txt", b"SECRET C\n"),
|
||||
]);
|
||||
let dest = td.path().join("dest");
|
||||
let bare = url.strip_prefix("file://").unwrap();
|
||||
assert!(Command::new("git")
|
||||
.args(["-C", bare, "config", "uploadpack.allowFilter", "true"])
|
||||
.status()
|
||||
.unwrap()
|
||||
.success());
|
||||
setup_partial_clone(&dest, &url, &["/secret/**".to_string()], &[], None).unwrap();
|
||||
|
||||
let oid_of = |path: &str| {
|
||||
let out = Command::new("git")
|
||||
.args([
|
||||
"-C",
|
||||
dest.to_str().unwrap(),
|
||||
"rev-parse",
|
||||
&format!("HEAD:{path}"),
|
||||
])
|
||||
.output()
|
||||
.unwrap();
|
||||
String::from_utf8_lossy(&out.stdout).trim().to_string()
|
||||
};
|
||||
let refused_oid = oid_of("secret/b.txt");
|
||||
let served_oid = oid_of("secret/c.txt");
|
||||
|
||||
// Origin death, so recovery has to go through the gateways.
|
||||
std::fs::remove_dir_all(bare).unwrap();
|
||||
|
||||
let reader = Keypair::generate();
|
||||
let envelope = seal_blob(b"SECRET C\n", &[reader.verifying_key()]).unwrap();
|
||||
|
||||
let refused_cid = "cidrefused";
|
||||
let served_cid = "cidserved";
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _gql = server
|
||||
.mock("POST", "/graphql")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"data":{"transactions":{"edges":[{"node":{"id":"TX1"}}]}}}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let manifest_body = serde_json::json!({
|
||||
"timestamp": "2026-06-11T00:00:00Z",
|
||||
"blobs": [
|
||||
{ "oid": refused_oid, "cid": refused_cid },
|
||||
{ "oid": served_oid, "cid": served_cid },
|
||||
],
|
||||
})
|
||||
.to_string();
|
||||
let _tx = server
|
||||
.mock("GET", "/TX1")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(manifest_body)
|
||||
.create_async()
|
||||
.await;
|
||||
let refusal = server
|
||||
.mock("GET", format!("/ipfs/{refused_cid}").as_str())
|
||||
.with_status(503)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"error":"search_incomplete","message":"scan truncated"}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let ok = server
|
||||
.mock("GET", format!("/ipfs/{served_cid}").as_str())
|
||||
.with_status(200)
|
||||
.with_body(envelope)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let paths = recover_from_arweave(
|
||||
&server.url(),
|
||||
&server.url(),
|
||||
"alice",
|
||||
"myrepo",
|
||||
&dest,
|
||||
&reader,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
refusal.assert_async().await;
|
||||
ok.assert_async().await;
|
||||
assert_eq!(
|
||||
paths,
|
||||
vec!["secret/c.txt".to_string()],
|
||||
"a refused candidate must not stop the loop reaching the next one"
|
||||
);
|
||||
|
||||
let warnings = warnings();
|
||||
assert!(
|
||||
warnings.contains(&refused_oid),
|
||||
"the skip must name the object it could not fetch, got: {warnings}"
|
||||
);
|
||||
assert!(
|
||||
warnings.contains("503"),
|
||||
"the skip must name the gateway's status rather than failing silently, \
|
||||
got: {warnings}"
|
||||
);
|
||||
assert!(
|
||||
!warnings.contains(&served_oid),
|
||||
"the blob that was served must not be reported as skipped, got: {warnings}"
|
||||
);
|
||||
}
|
||||
|
||||
/// Read-path end-to-end over a mocked Arweave + IPFS gateway: discover the
|
||||
/// manifest via GraphQL, fetch it, fetch the envelope, decrypt with the
|
||||
/// caller's key, and install the previously-withheld blob.
|
||||
|
||||
+1
-682
@@ -15,47 +15,6 @@ use icaptcha_client::IcaptchaCfg;
|
||||
/// (absorbs proof expiry / first-seen replay).
|
||||
const MAX_ICAPTCHA_RETRIES: usize = 2;
|
||||
|
||||
/// Total request timeout: from the start of connecting through the end of the
|
||||
/// response body, so it bounds a slow download and not just a slow handshake.
|
||||
const TOTAL_REQUEST_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(30);
|
||||
|
||||
/// Follow a redirect only when it stays on the origin that issued it AND re-issues the
|
||||
/// identical request-target, and only for as long as the chain bound allows.
|
||||
///
|
||||
/// The decision itself is [`gitlawb_core::redirect::may_follow`], shared with
|
||||
/// `git-remote-gitlawb` so the two signing clients cannot drift apart on it. Refusal
|
||||
/// is `stop`, not `error`: the 3xx comes back as an ordinary response and each caller
|
||||
/// reports it through the status path it already has.
|
||||
///
|
||||
/// `Policy::custom` replaces reqwest's built-in limit, so the chain bound is restated
|
||||
/// here. Same-origin redirects can cycle, and this is what stops a node answering 302
|
||||
/// to itself from being followed indefinitely. It is not what makes the request
|
||||
/// finite: `.timeout(...)` on the same builder is a TOTAL request timeout covering the
|
||||
/// whole chain, so without this bound the worst case is a 30 second spin, not an
|
||||
/// endless one. The bound is what keeps that spin from costing the node a request per
|
||||
/// round trip for the full 30 seconds.
|
||||
///
|
||||
/// `>` and not `>=`: reqwest pushes the redirecting URL onto `previous` before
|
||||
/// consulting the policy, so on the first redirect `previous.len()` is already 1, and
|
||||
/// `>=` would permit `MAX_REDIRECTS - 1` follows. `Policy::limited(max)` refuses at
|
||||
/// `previous.len() > max`, and matching it is the point of reusing its value.
|
||||
fn same_origin_redirect(attempt: reqwest::redirect::Attempt<'_>) -> reqwest::redirect::Action {
|
||||
let Some(previous) = attempt.previous().last() else {
|
||||
// No previous URL to compare against. Unreachable through reqwest, which
|
||||
// pushes the redirecting URL before consulting the policy, but the safe
|
||||
// reading of "cannot prove same-origin" is to refuse.
|
||||
return attempt.stop();
|
||||
};
|
||||
if attempt.previous().len() > gitlawb_core::redirect::MAX_REDIRECTS {
|
||||
return attempt.stop();
|
||||
}
|
||||
if gitlawb_core::redirect::may_follow(previous, attempt.url()) {
|
||||
attempt.follow()
|
||||
} else {
|
||||
attempt.stop()
|
||||
}
|
||||
}
|
||||
|
||||
pub struct NodeClient {
|
||||
inner: reqwest::Client,
|
||||
pub node_url: String,
|
||||
@@ -64,20 +23,8 @@ pub struct NodeClient {
|
||||
|
||||
impl NodeClient {
|
||||
pub fn new(node_url: impl Into<String>, keypair: Option<Keypair>) -> Self {
|
||||
Self::with_timeout(node_url, keypair, TOTAL_REQUEST_TIMEOUT)
|
||||
}
|
||||
|
||||
/// `new` with the total request timeout as a parameter, so a test can drive the
|
||||
/// timeout's behaviour without waiting out the shipped value. `new` supplies the
|
||||
/// shipped one, which is what makes the scaled-down test cover the real client.
|
||||
fn with_timeout(
|
||||
node_url: impl Into<String>,
|
||||
keypair: Option<Keypair>,
|
||||
timeout: std::time::Duration,
|
||||
) -> Self {
|
||||
let inner = reqwest::Client::builder()
|
||||
.timeout(timeout)
|
||||
.redirect(reqwest::redirect::Policy::custom(same_origin_redirect))
|
||||
.timeout(std::time::Duration::from_secs(30))
|
||||
.user_agent(format!("gl/{} gitlawb-cli", env!("CARGO_PKG_VERSION")))
|
||||
.build()
|
||||
.expect("failed to build HTTP client");
|
||||
@@ -256,79 +203,6 @@ async fn obtain_proof(cfg: IcaptchaCfg) -> Result<String> {
|
||||
.context("iCaptcha solver task panicked")?
|
||||
}
|
||||
|
||||
/// What a capped body read produced. `text` is the bytes that arrived; the two flags
|
||||
/// say why the read stopped where it did, which a caller that CLASSIFIES on the body
|
||||
/// cannot work out from the text alone.
|
||||
pub(crate) struct CappedBody {
|
||||
/// The bytes read, lossily decoded.
|
||||
pub(crate) text: String,
|
||||
/// The cap cut the body short.
|
||||
pub(crate) truncated: bool,
|
||||
/// A chunk read FAILED part-way through, so the body is not merely short, it is
|
||||
/// unfinished and the node may have had more to say.
|
||||
pub(crate) read_failed: bool,
|
||||
}
|
||||
|
||||
/// Read at most `cap` bytes of a response body. Bounds the allocation from a
|
||||
/// hostile or broken node returning a huge error body — the display is capped
|
||||
/// separately, but the read itself must not be unbounded (INV-6, read half).
|
||||
///
|
||||
/// `truncated` reports whether the cap cut the body short. A caller that CLASSIFIES
|
||||
/// on the body needs it: a cut body fails JSON parse, and a parse failure is
|
||||
/// indistinguishable from a node that sent no code at all, so without this flag an
|
||||
/// oversized body silently picks a different arm.
|
||||
///
|
||||
/// `read_failed` reports the other way a body can end early. A mid-body read error
|
||||
/// used to leave through the same exit as a clean end of stream, so a 500 whose body
|
||||
/// died in transit surfaced as an empty message and the caller was told
|
||||
/// `node returned 500: ` with nothing after the colon. That is a report of what the
|
||||
/// node said, and the node never got to say it.
|
||||
pub(crate) async fn read_body_capped(mut resp: reqwest::Response, cap: usize) -> CappedBody {
|
||||
let mut buf: Vec<u8> = Vec::new();
|
||||
let mut truncated = false;
|
||||
let mut read_failed = false;
|
||||
while buf.len() < cap {
|
||||
match resp.chunk().await {
|
||||
Ok(Some(chunk)) => {
|
||||
let take = (cap - buf.len()).min(chunk.len());
|
||||
buf.extend_from_slice(&chunk[..take]);
|
||||
if take < chunk.len() {
|
||||
truncated = true;
|
||||
break; // hit the cap mid-chunk
|
||||
}
|
||||
}
|
||||
Ok(None) => break, // clean end of body
|
||||
Err(_) => {
|
||||
read_failed = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
// A body that lands exactly on the cap may or may not have more behind it;
|
||||
// report it as cut, since the classification that follows cannot tell either.
|
||||
if buf.len() >= cap {
|
||||
truncated = true;
|
||||
}
|
||||
CappedBody {
|
||||
text: String::from_utf8_lossy(&buf).into_owned(),
|
||||
truncated,
|
||||
read_failed,
|
||||
}
|
||||
}
|
||||
|
||||
/// Strip terminal-dangerous characters from (and cap the length of) a
|
||||
/// node-supplied error string before surfacing it. The node a caller talks to
|
||||
/// could be hostile and embed escape sequences in its error body; those must not
|
||||
/// reach the terminal verbatim (INV-6). We drop the C0/C1 control bytes (which
|
||||
/// defangs ANSI/OSC escapes) AND the Unicode bidi/format controls (which
|
||||
/// `char::is_control` does not cover — they can reorder the displayed line).
|
||||
pub(crate) fn sanitize_node_msg(s: &str) -> String {
|
||||
s.chars()
|
||||
.filter(|c| !c.is_control() && !gitlawb_core::sanitize::is_bidi_format(*c))
|
||||
.take(200)
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -713,559 +587,4 @@ mod tests {
|
||||
ic.challenge.assert();
|
||||
ic.answer.assert();
|
||||
}
|
||||
|
||||
// ── redirect policy ─────────────────────────────────────────────────
|
||||
|
||||
/// The signed headers must not survive a redirect off the node's origin.
|
||||
///
|
||||
/// reqwest strips only `Authorization`, `Cookie`, `Proxy-Authorization` and
|
||||
/// `WWW-Authenticate` across hosts, so `Signature` and `Signature-Input` used to
|
||||
/// ride a 302 straight to whatever origin the node named. The signature binds
|
||||
/// `@method`, `@path` and `content-digest` and nothing about the authority, so the
|
||||
/// receiving host holds a credential that reads path-scoped objects as the caller
|
||||
/// at any node until the clock-skew window closes.
|
||||
///
|
||||
/// Two mockito servers are two ports on one host, which is exactly the boundary
|
||||
/// this policy draws (and the one reqwest's own header stripping draws). The
|
||||
/// second server answers everything and expects nothing: a followed redirect
|
||||
/// fails the expectation whether or not the signature came with it. MUTATION
|
||||
/// (RED): drop the `.redirect(...)` line and the second server is hit.
|
||||
#[tokio::test]
|
||||
async fn cross_origin_redirect_is_not_followed() {
|
||||
let mut elsewhere = Server::new_async().await;
|
||||
let never = elsewhere
|
||||
.mock("GET", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_body("bytes from the redirect target")
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
let signature_seen = elsewhere
|
||||
.mock("GET", mockito::Matcher::Any)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let mut node = Server::new_async().await;
|
||||
let bounce = node
|
||||
.mock("GET", "/api/v1/thing")
|
||||
.with_status(302)
|
||||
.with_header("location", &format!("{}/api/v1/thing", elsewhere.url()))
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(test_keypair()));
|
||||
let resp = client.get_signed("/api/v1/thing").await.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
302,
|
||||
"a refused redirect stops rather than errors, so the caller sees the 3xx \
|
||||
and reports it through the status path it already has"
|
||||
);
|
||||
let body = resp.text().await.unwrap();
|
||||
assert!(
|
||||
!body.contains("bytes from the redirect target"),
|
||||
"the redirect target's bytes must never reach the caller, got: {body}"
|
||||
);
|
||||
bounce.assert_async().await;
|
||||
never.assert_async().await;
|
||||
signature_seen.assert_async().await;
|
||||
}
|
||||
|
||||
/// A node redirecting to itself is same-origin, so the origin predicate follows it
|
||||
/// every time and only the chain bound ends the loop. Deleting the bound left the
|
||||
/// whole suite green, because nothing here had ever built a cycle.
|
||||
///
|
||||
/// It has a second job now. A redirect back to the identical path and query is the
|
||||
/// only same-origin hop the predicate still follows, so the eleven hits below are
|
||||
/// also this crate's executed proof that such a hop IS followed. The old positive
|
||||
/// fixture drove a trailing-slash rewrite, which the request-target rule refuses,
|
||||
/// and an http-to-https upgrade cannot be mocked over mockito's plain http.
|
||||
///
|
||||
/// The route answers 301 pointing back at itself. Bounded, the handler is hit
|
||||
/// once for the original request plus `MAX_REDIRECTS` follows and the call returns
|
||||
/// the 301 (a refused redirect stops rather than errors). Unbounded, it runs until
|
||||
/// the client's total request timeout cuts it off, which is a 30 second spin at the
|
||||
/// shipped value and a request per round trip for the node.
|
||||
///
|
||||
/// MUTATION (RED): delete the `previous().len()` check.
|
||||
#[tokio::test]
|
||||
async fn a_self_redirect_stops_at_the_chain_bound() {
|
||||
let mut node = Server::new_async().await;
|
||||
let hits = std::sync::Arc::new(std::sync::atomic::AtomicUsize::new(0));
|
||||
let h = hits.clone();
|
||||
let loop_route = node
|
||||
.mock("GET", "/api/v1/loop")
|
||||
.with_status(301)
|
||||
.with_header("location", "/api/v1/loop")
|
||||
.with_body_from_request(move |_req| {
|
||||
h.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
|
||||
Vec::new()
|
||||
})
|
||||
.expect_at_least(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::with_timeout(
|
||||
node.url(),
|
||||
Some(test_keypair()),
|
||||
std::time::Duration::from_secs(5),
|
||||
);
|
||||
let resp = client
|
||||
.get_signed("/api/v1/loop")
|
||||
.await
|
||||
.expect("the bound must end the chain, not the timeout");
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"the chain ends by refusing the next hop, so the last 3xx is what comes back"
|
||||
);
|
||||
assert_eq!(
|
||||
hits.load(std::sync::atomic::Ordering::SeqCst),
|
||||
gitlawb_core::redirect::MAX_REDIRECTS + 1,
|
||||
"one original request plus MAX_REDIRECTS follows, matching what \
|
||||
Policy::limited(MAX_REDIRECTS) would have permitted"
|
||||
);
|
||||
loop_route.assert_async().await;
|
||||
}
|
||||
|
||||
/// A same-origin hop that REWRITES the request-target is refused, even though the
|
||||
/// origin never changes.
|
||||
///
|
||||
/// The signature binds `@path` as the literal path-and-query the client signed, and
|
||||
/// the node rebuilds it from the URI it received. A `/api/v1/thing` to
|
||||
/// `/api/v1/thing/` bounce therefore presents a signature over a target the node
|
||||
/// never saw, and every signed read behind such a proxy 401s. Refusing the hop
|
||||
/// hands the caller the 3xx that names what happened instead.
|
||||
///
|
||||
/// The target mock expects zero hits and is asserted: mockito only checks
|
||||
/// `.expect(N)` when `.assert()` runs, so an unbound or unasserted mock passes
|
||||
/// vacuously.
|
||||
#[tokio::test]
|
||||
async fn same_origin_path_changing_redirect_is_refused() {
|
||||
let mut node = Server::new_async().await;
|
||||
let bounce = node
|
||||
.mock("GET", "/api/v1/thing")
|
||||
.with_status(301)
|
||||
.with_header("location", "/api/v1/thing/")
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let target = node
|
||||
.mock("GET", "/api/v1/thing/")
|
||||
.with_status(200)
|
||||
.with_body("bytes from the rewritten target")
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(test_keypair()));
|
||||
let resp = client.get_signed("/api/v1/thing").await.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"a refused redirect stops rather than errors, so the caller sees the 3xx \
|
||||
and reports it through the status path it already has"
|
||||
);
|
||||
let body = resp.text().await.unwrap();
|
||||
assert!(
|
||||
!body.contains("bytes from the rewritten target"),
|
||||
"the rewritten target's bytes must never reach the caller, got: {body}"
|
||||
);
|
||||
bounce.assert_async().await;
|
||||
target.assert_async().await;
|
||||
}
|
||||
|
||||
// ── the node's own verification, run over what the client actually sent ──
|
||||
|
||||
/// What the verifying mock made of a request that reached it.
|
||||
///
|
||||
/// The empty slot (`None`) is its own state and means the mock was never hit at
|
||||
/// all, which is what the refusal test asserts. It must stay distinguishable from
|
||||
/// [`Verdict::WrongIdentity`], because "nobody verified anything" and "something
|
||||
/// verified against the wrong key" are opposite findings.
|
||||
///
|
||||
/// The payloads are read through `Debug` in the assertion messages and nowhere
|
||||
/// else, which the dead-code pass does not count; they carry the detail that makes
|
||||
/// a failure legible, so they stay.
|
||||
#[derive(Debug)]
|
||||
#[allow(dead_code)]
|
||||
enum Verdict {
|
||||
/// The chain accepted the signature AND the key it resolved is the test's DID.
|
||||
Accepted,
|
||||
/// The chain refused it. Carries the error so a failure reads as the actual
|
||||
/// rejection rather than a bare hit count.
|
||||
Rejected(String),
|
||||
/// The chain accepted a signature made by somebody else. A key resolved from
|
||||
/// the parsed `key_id` is read out of the artifact under verification, so an
|
||||
/// accept on it alone proves consistency, never authenticity.
|
||||
WrongIdentity { expected: String, got: String },
|
||||
}
|
||||
|
||||
/// The node's `require_signature` verification, over a request this crate did not
|
||||
/// build: parse the headers, recompute the content-digest from the body, rebuild
|
||||
/// the signing string over `@method`/`@path`/`content-digest`, Ed25519-verify.
|
||||
/// Returns the DID the signature resolved to, so a caller can pin the identity.
|
||||
///
|
||||
/// A hand-copy of its twin in `crates/git-remote-gitlawb/src/main.rs`, which gl
|
||||
/// cannot import (`git-remote-gitlawb` is a binary crate and this is its test
|
||||
/// module). Keep the two textually identical apart from the mockito seam around
|
||||
/// them, so an edit to one is visibly an edit to both.
|
||||
///
|
||||
/// The production verifier both copies mirror is `crate::auth::require_signature` in
|
||||
/// `crates/gitlawb-node/src/auth/mod.rs`. This is a re-implementation, not a call, so
|
||||
/// an edit to that middleware has to land here too: otherwise the copies drift and
|
||||
/// this test keeps passing against a rule the node has stopped applying.
|
||||
///
|
||||
/// It asserts internally, which is deliberate but constrains its callers: inside
|
||||
/// `with_body_from_request` those assertions fire on the server thread and reach
|
||||
/// the client as a transport error, not as a recorded verdict. So the identity
|
||||
/// check lives in the caller as a [`Verdict`] variant, never as an assert in here.
|
||||
fn node_verifies(
|
||||
method: &str,
|
||||
path_and_query: &str,
|
||||
body: &[u8],
|
||||
sig_input: &str,
|
||||
sig_header: &str,
|
||||
content_digest: &str,
|
||||
) -> anyhow::Result<String> {
|
||||
use gitlawb_core::http_sig::{build_signing_string, compute_content_digest, HttpSignature};
|
||||
use gitlawb_core::identity::verify;
|
||||
use std::collections::HashMap;
|
||||
|
||||
let sig = HttpSignature::parse(sig_input, sig_header)?;
|
||||
sig.check_created()?;
|
||||
assert!(
|
||||
sig.missing_components().is_empty(),
|
||||
"signature must cover all required components"
|
||||
);
|
||||
assert_eq!(sig.alg, "ed25519");
|
||||
assert_eq!(
|
||||
content_digest,
|
||||
compute_content_digest(body),
|
||||
"content-digest must match the body"
|
||||
);
|
||||
let vk = sig.key_id.to_verifying_key()?;
|
||||
let mut values = HashMap::new();
|
||||
values.insert("@method".to_string(), method.to_uppercase());
|
||||
values.insert("@path".to_string(), path_and_query.to_string());
|
||||
values.insert("content-digest".to_string(), content_digest.to_string());
|
||||
let sig_params_value = sig_input.strip_prefix("sig1=").unwrap_or(sig_input);
|
||||
let components: Vec<&str> = sig.components.iter().map(String::as_str).collect();
|
||||
let signing_string = build_signing_string(&components, sig_params_value, &values)?;
|
||||
let sig_array: [u8; 64] = sig.signature_bytes.as_slice().try_into()?;
|
||||
verify(&vk, signing_string.as_bytes(), &sig_array)?;
|
||||
Ok(sig.key_id.to_string())
|
||||
}
|
||||
|
||||
/// Pull a header value off a received mockito request, or explain which one the
|
||||
/// client failed to send.
|
||||
fn received_header(req: &mockito::Request, name: &str) -> String {
|
||||
req.header(name)
|
||||
.first()
|
||||
.unwrap_or_else(|| panic!("the client sent no {name} header"))
|
||||
.to_str()
|
||||
.unwrap()
|
||||
.to_string()
|
||||
}
|
||||
|
||||
/// Run [`node_verifies`] over a GET that arrived at the mock and record what the
|
||||
/// node would have made of it, pinned to `expected_did`.
|
||||
fn record_get_verdict(
|
||||
req: &mockito::Request,
|
||||
expected_did: &str,
|
||||
slot: &std::sync::Arc<std::sync::Mutex<Option<Verdict>>>,
|
||||
) {
|
||||
let verdict = match node_verifies(
|
||||
"GET",
|
||||
req.path_and_query(),
|
||||
b"",
|
||||
&received_header(req, "signature-input"),
|
||||
&received_header(req, "signature"),
|
||||
&received_header(req, "content-digest"),
|
||||
) {
|
||||
Ok(did) if did == expected_did => Verdict::Accepted,
|
||||
Ok(did) => Verdict::WrongIdentity {
|
||||
expected: expected_did.to_string(),
|
||||
got: did,
|
||||
},
|
||||
Err(e) => Verdict::Rejected(e.to_string()),
|
||||
};
|
||||
*slot.lock().unwrap() = Some(verdict);
|
||||
}
|
||||
|
||||
/// The finding's repro, now a guard: a rewritten same-origin target must never
|
||||
/// receive the signature, and the proof is the node's own verification, not a hit
|
||||
/// count.
|
||||
///
|
||||
/// The target mock runs the full `require_signature` chain over the request it
|
||||
/// receives. Post-fix the hop is refused, so the slot stays empty. Pre-fix the hop
|
||||
/// is followed and the slot records the Ed25519 rejection of a signature made over
|
||||
/// `/api/v1/thing` and presented at `/api/v1/thing/`, which is the 401 an operator
|
||||
/// behind such a proxy actually sees. The verdict is asserted first, so a failure
|
||||
/// speaks about verification rather than about reachability.
|
||||
///
|
||||
/// Its paired positive control is
|
||||
/// `a_direct_signed_get_verifies_under_the_node_verifier`: without it, an empty
|
||||
/// slot would be satisfied just as well by a harness that can never record
|
||||
/// anything.
|
||||
#[tokio::test]
|
||||
async fn a_rewritten_target_never_receives_the_signature() {
|
||||
let kp = test_keypair();
|
||||
let expected_did = kp.did().to_string();
|
||||
let slot = std::sync::Arc::new(std::sync::Mutex::new(None::<Verdict>));
|
||||
|
||||
let mut node = Server::new_async().await;
|
||||
let bounce = node
|
||||
.mock("GET", "/api/v1/thing")
|
||||
.with_status(301)
|
||||
.with_header("location", "/api/v1/thing/")
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let recorder = slot.clone();
|
||||
let did_for_target = expected_did.clone();
|
||||
let target = node
|
||||
.mock("GET", "/api/v1/thing/")
|
||||
.with_status(200)
|
||||
.with_body_from_request(move |req| {
|
||||
record_get_verdict(req, &did_for_target, &recorder);
|
||||
Vec::new()
|
||||
})
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(kp));
|
||||
let resp = client.get_signed("/api/v1/thing").await.unwrap();
|
||||
|
||||
let verdict = slot.lock().unwrap().take();
|
||||
assert!(
|
||||
verdict.is_none(),
|
||||
"the node's own verifier must never see this request: the signature covers \
|
||||
/api/v1/thing and the rewritten target is /api/v1/thing/, so what arrives \
|
||||
there is a stale request-target; recorded verdict: {verdict:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
301,
|
||||
"the caller sees the 3xx, not the rewritten target's answer"
|
||||
);
|
||||
bounce.assert_async().await;
|
||||
target.assert_async().await;
|
||||
}
|
||||
|
||||
/// The positive control for the test above, and the proof that the client signs
|
||||
/// the query it sends.
|
||||
///
|
||||
/// A direct signed GET, no redirect anywhere, through the same verifying mock. The
|
||||
/// verdict must be `Accepted`, which is what makes the refusal test's empty slot
|
||||
/// attributable to the refusal rather than to a harness that cannot record. The
|
||||
/// path carries a query, so a client that signed the bare path would land here as
|
||||
/// `Rejected`.
|
||||
#[tokio::test]
|
||||
async fn a_direct_signed_get_verifies_under_the_node_verifier() {
|
||||
let kp = test_keypair();
|
||||
let expected_did = kp.did().to_string();
|
||||
let slot = std::sync::Arc::new(std::sync::Mutex::new(None::<Verdict>));
|
||||
|
||||
let mut node = Server::new_async().await;
|
||||
let recorder = slot.clone();
|
||||
let did_for_target = expected_did.clone();
|
||||
let route = node
|
||||
.mock("GET", "/api/v1/thing?x=1")
|
||||
.with_status(200)
|
||||
.with_body_from_request(move |req| {
|
||||
record_get_verdict(req, &did_for_target, &recorder);
|
||||
Vec::new()
|
||||
})
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(kp));
|
||||
let resp = client.get_signed("/api/v1/thing?x=1").await.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
|
||||
let verdict = slot.lock().unwrap().take();
|
||||
assert!(
|
||||
matches!(verdict, Some(Verdict::Accepted)),
|
||||
"a direct signed GET must verify under the node's own chain and resolve to \
|
||||
{expected_did}, or the refusal test's empty slot proves nothing; recorded \
|
||||
verdict: {verdict:?}"
|
||||
);
|
||||
route.assert_async().await;
|
||||
}
|
||||
|
||||
// ── read_body_capped ────────────────────────────────────────────────
|
||||
|
||||
/// A body whose read FAILS mid-stream must be distinguishable from a body that
|
||||
/// ended. Both used to leave through the same `_ => break`, so a 500 whose body
|
||||
/// died in transit produced an empty message and the caller was told
|
||||
/// `node returned 500: ` with nothing after the colon.
|
||||
///
|
||||
/// The fixture is a raw listener that promises 64 bytes in `Content-Length`,
|
||||
/// writes 5, and closes. mockito cannot express that: it always completes the
|
||||
/// response it advertises. MUTATION (RED): restore the single `_ => break` arm
|
||||
/// (or hard-code `read_failed: false`) and the flag reads false.
|
||||
#[tokio::test]
|
||||
async fn read_body_capped_flags_a_mid_body_read_failure() {
|
||||
let addr = spawn_short_body_listener().await;
|
||||
let resp = reqwest::get(format!("http://{addr}/truncated"))
|
||||
.await
|
||||
.expect("headers arrive before the body is cut");
|
||||
let body = read_body_capped(resp, 8192).await;
|
||||
|
||||
assert!(
|
||||
body.read_failed,
|
||||
"a body cut off mid-stream must be reported as a failed read, not as a \
|
||||
body that ended: got {:?}",
|
||||
body.text
|
||||
);
|
||||
assert!(
|
||||
!body.truncated,
|
||||
"the cap did not cut this one; 5 bytes are nowhere near 8 KiB"
|
||||
);
|
||||
}
|
||||
|
||||
/// The must-not half: a body that ends cleanly must NOT be flagged, or the flag
|
||||
/// means nothing and every terminal starts claiming the node went quiet.
|
||||
#[tokio::test]
|
||||
async fn read_body_capped_does_not_flag_a_clean_body() {
|
||||
let mut server = Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/ok")
|
||||
.with_status(500)
|
||||
.with_body("node said this")
|
||||
.create_async()
|
||||
.await;
|
||||
let resp = reqwest::get(format!("{}/ok", server.url())).await.unwrap();
|
||||
let body = read_body_capped(resp, 8192).await;
|
||||
|
||||
assert_eq!(body.text, "node said this");
|
||||
assert!(!body.read_failed, "a complete body is not a failed read");
|
||||
assert!(!body.truncated, "a complete body is not a truncated one");
|
||||
}
|
||||
|
||||
/// Answer one request with headers promising more body than gets written, then
|
||||
/// close the connection. Returns the listener's address.
|
||||
async fn spawn_short_body_listener() -> std::net::SocketAddr {
|
||||
use tokio::io::{AsyncReadExt, AsyncWriteExt};
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let addr = listener.local_addr().unwrap();
|
||||
tokio::spawn(async move {
|
||||
let (mut sock, _) = listener.accept().await.unwrap();
|
||||
let mut scratch = [0u8; 1024];
|
||||
let _ = sock.read(&mut scratch).await;
|
||||
let _ = sock
|
||||
.write_all(b"HTTP/1.1 500 Internal Server Error\r\nContent-Length: 64\r\n\r\nshort")
|
||||
.await;
|
||||
let _ = sock.flush().await;
|
||||
// Drop closes the socket with 59 of the promised bytes never sent.
|
||||
});
|
||||
addr
|
||||
}
|
||||
|
||||
// ── total request timeout ───────────────────────────────────────────
|
||||
|
||||
/// The client's timeout is a TOTAL request timeout, so it bounds a download and
|
||||
/// not just the handshake. `gl ipfs get`'s documentation leans on exactly that:
|
||||
/// the wall-clock deadline covers the search and deliberately stops at the
|
||||
/// response headers, and this timeout is the only thing left bounding the body.
|
||||
///
|
||||
/// Driven at 250ms through `with_timeout`, the seam `new` itself calls with
|
||||
/// `TOTAL_REQUEST_TIMEOUT`, because a test at the shipped 30s has no place in this
|
||||
/// suite. What that costs is the value; what it proves is the SHAPE, which is the
|
||||
/// part in doubt: that the deadline keeps running once the headers have landed. A
|
||||
/// timeout that covered only the handshake would let this request hang until the
|
||||
/// listener gives up.
|
||||
#[tokio::test]
|
||||
async fn total_timeout_cuts_off_a_body_that_outruns_it() {
|
||||
use tokio::io::{AsyncReadExt, AsyncWriteExt};
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let addr = listener.local_addr().unwrap();
|
||||
tokio::spawn(async move {
|
||||
let (mut sock, _) = listener.accept().await.unwrap();
|
||||
let mut scratch = [0u8; 1024];
|
||||
let _ = sock.read(&mut scratch).await;
|
||||
// Headers land immediately, then the body stalls indefinitely.
|
||||
let _ = sock
|
||||
.write_all(b"HTTP/1.1 200 OK\r\nContent-Length: 1024\r\n\r\nfirst")
|
||||
.await;
|
||||
let _ = sock.flush().await;
|
||||
tokio::time::sleep(std::time::Duration::from_secs(30)).await;
|
||||
});
|
||||
|
||||
let client = NodeClient::with_timeout(
|
||||
format!("http://{addr}"),
|
||||
None,
|
||||
std::time::Duration::from_millis(250),
|
||||
);
|
||||
let started = std::time::Instant::now();
|
||||
let resp = client.get("/slow").await.expect("headers arrive promptly");
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
200,
|
||||
"the stall is in the body, not the status"
|
||||
);
|
||||
let err = resp
|
||||
.bytes()
|
||||
.await
|
||||
.expect_err("a body still arriving past the total timeout must be cut off");
|
||||
let elapsed = started.elapsed();
|
||||
|
||||
assert!(
|
||||
err.is_timeout(),
|
||||
"the body read must end in a timeout, got: {err}"
|
||||
);
|
||||
assert!(
|
||||
elapsed < std::time::Duration::from_secs(5),
|
||||
"the timeout must fire on its own schedule, not wait out the listener; \
|
||||
took {elapsed:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn shipped_client_uses_the_documented_total_timeout() {
|
||||
// The scaled-down test above proves the shape at 250ms. This pins the value
|
||||
// `new` actually ships, so the two together cover the documented behaviour.
|
||||
assert_eq!(TOTAL_REQUEST_TIMEOUT, std::time::Duration::from_secs(30));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_strips_controls_bidi_and_caps_length() {
|
||||
// C0 (ESC/BEL) and the Cf bidi override (U+202E) are both removed; the
|
||||
// printable text survives. (Note: a stripped ESC leaves any following
|
||||
// "[31m" as inert literal text — that is the point, so the input here
|
||||
// avoids that residue to keep the expectation unambiguous.)
|
||||
let out = sanitize_node_msg("a\u{1b}\u{07}b\u{202e}c");
|
||||
assert!(
|
||||
!out.chars().any(|c| c.is_control()),
|
||||
"control char leaked: {out:?}"
|
||||
);
|
||||
assert!(
|
||||
!out.contains('\u{202e}'),
|
||||
"RLO bidi override leaked: {out:?}"
|
||||
);
|
||||
assert_eq!(out, "abc");
|
||||
// Length is capped at 200 chars regardless of input size.
|
||||
let long = "x".repeat(250);
|
||||
assert_eq!(sanitize_node_msg(&long).chars().count(), 200);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_preserves_legitimate_and_rtl_text() {
|
||||
// Must not over-strip: a plain word, a genuine RTL SCRIPT letter (Arabic
|
||||
// U+0627, category Lo — NOT a format char), and ZWJ (U+200D, a legitimate
|
||||
// Cf char, e.g. emoji sequences) all survive. Guards the shared predicate
|
||||
// against being widened into a blanket Cf stripper.
|
||||
let out = sanitize_node_msg("ok \u{0627}\u{200D}b");
|
||||
assert_eq!(out, "ok \u{0627}\u{200D}b");
|
||||
}
|
||||
}
|
||||
+22
-2111
File diff suppressed because it is too large.
Load diff
+12
-406
@@ -7,7 +7,7 @@ use clap::{Args, Subcommand};
|
||||
use serde_json::Value;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::{read_body_capped, sanitize_node_msg, NodeClient};
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
#[derive(Args)]
|
||||
@@ -97,74 +97,6 @@ async fn cmd_list(node: String) -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// The warning text for a local peer-add reply, or `None` when the node
|
||||
/// accepted it.
|
||||
///
|
||||
/// Split out so the refusal path is assertable. The node now answers 403 when
|
||||
/// an unproven caller tries to repoint an existing peer's `http_url`, so a
|
||||
/// reply that arrived and refused must not reach the success line.
|
||||
fn local_add_refusal(status: reqwest::StatusCode, body: &Value) -> Option<String> {
|
||||
if status.is_success() {
|
||||
return None;
|
||||
}
|
||||
// The message is the node's, not ours, so it is defanged before it reaches
|
||||
// the terminal. Only the message: the status and the prose are ours.
|
||||
let msg = sanitize_node_msg(body["message"].as_str().unwrap_or("unknown error"));
|
||||
Some(format!(
|
||||
"warning: local peer list not updated ({status}): {msg}"
|
||||
))
|
||||
}
|
||||
|
||||
/// The error text for a remote announce reply, or `None` when the peer accepted
|
||||
/// it.
|
||||
///
|
||||
/// Split out so the ordering is assertable: the status has to reach the caller
|
||||
/// even when the body does not parse. That case is reachable rather than
|
||||
/// theoretical, because the read above is capped, so a peer answering with a
|
||||
/// body past the cap leaves truncated JSON behind, and `peer_url` is whatever
|
||||
/// the caller passed, so a non-JSON error page is just as easy. Parsing first
|
||||
/// and failing on the parse would swallow the status the user needs.
|
||||
fn remote_announce_failure(status: reqwest::StatusCode, raw: &str) -> Option<String> {
|
||||
if status.is_success() {
|
||||
return None;
|
||||
}
|
||||
// Falls back to the body itself when there is no `message` field, which is
|
||||
// what a truncated or non-JSON reply leaves. Sanitized either way: it is the
|
||||
// peer's text and it is headed for the terminal.
|
||||
let parsed: Value = serde_json::from_str(raw).unwrap_or(Value::Null);
|
||||
let msg = sanitize_node_msg(parsed["message"].as_str().unwrap_or(raw));
|
||||
Some(format!("announce failed ({status}): {msg}"))
|
||||
}
|
||||
|
||||
/// Which line the local peer-add prints, and whether it is a warning.
|
||||
///
|
||||
/// Split out because the SELECTION is what the fix is: `local_add_refusal` was
|
||||
/// already unit-tested six ways, and replacing this whole match with an
|
||||
/// unconditional "Added to local peer list." still left 312 tests green. The
|
||||
/// helper was pinned; the wiring was not, which is the shape
|
||||
/// `unit-test-on-helper-does-not-prove-handler-wiring` names. With the choice
|
||||
/// extracted, the call site is a two-line dispatch carrying no logic.
|
||||
fn local_add_report(status: reqwest::StatusCode, body: &Value) -> (bool, String) {
|
||||
match local_add_refusal(status, body) {
|
||||
Some(warning) => (true, warning),
|
||||
None => (false, " Added to local peer list.".to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
/// The block printed after a peer accepts our announce. Split out so the
|
||||
/// defanging is assertable: the DID and URL are the remote peer's own strings,
|
||||
/// and `peer_url` is caller-chosen, so this is the least trusted body the
|
||||
/// command handles. Only the display is sanitized; the values sent on to our
|
||||
/// local node stay verbatim, since that is data rather than terminal output and
|
||||
/// the node runs its own validation on them.
|
||||
fn announced_peer_summary(their_did: &str, their_url: &str, peer_count: u64) -> String {
|
||||
format!(
|
||||
"Announced to peer node:\n DID: {}\n URL: {}\n Their peers: {peer_count}\n",
|
||||
sanitize_node_msg(their_did),
|
||||
sanitize_node_msg(their_url),
|
||||
)
|
||||
}
|
||||
|
||||
async fn cmd_add(peer_url: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let keypair = load_keypair_from_dir(dir.as_deref())?;
|
||||
let my_did = keypair.did().to_string();
|
||||
@@ -195,26 +127,21 @@ async fn cmd_add(peer_url: String, node: String, dir: Option<PathBuf>) -> Result
|
||||
.await
|
||||
.context("failed to connect to peer")?;
|
||||
let status = resp.status();
|
||||
// `peer_url` is fully caller-chosen, so this body is the least trusted one
|
||||
// in the command: bound the read, and defang the message before it reaches
|
||||
// the terminal through the error return. An announce reply is a DID, a URL
|
||||
// and a count, so 8 KiB is well past what the shape needs.
|
||||
let raw = read_body_capped(resp, 8 * 1024).await.text;
|
||||
let result: Value = resp.json().await.context("invalid JSON response")?;
|
||||
|
||||
if let Some(failure) = remote_announce_failure(status, &raw) {
|
||||
anyhow::bail!("{failure}");
|
||||
if !status.is_success() {
|
||||
let msg = result["message"].as_str().unwrap_or("unknown error");
|
||||
anyhow::bail!("announce failed ({status}): {msg}");
|
||||
}
|
||||
|
||||
let result: Value = serde_json::from_str(&raw).context("invalid JSON response")?;
|
||||
|
||||
let their_did = result["node_did"].as_str().unwrap_or("?");
|
||||
let their_url = result["node_url"].as_str().unwrap_or("?");
|
||||
let peer_count = result["peer_count"].as_u64().unwrap_or(0);
|
||||
|
||||
print!(
|
||||
"{}",
|
||||
announced_peer_summary(their_did, their_url, peer_count)
|
||||
);
|
||||
println!("Announced to peer node:");
|
||||
println!(" DID: {their_did}");
|
||||
println!(" URL: {their_url}");
|
||||
println!(" Their peers: {peer_count}");
|
||||
|
||||
// Also add their info to our local node's peer list
|
||||
// (the peer's /announce response includes their did + url)
|
||||
@@ -223,31 +150,9 @@ async fn cmd_add(peer_url: String, node: String, dir: Option<PathBuf>) -> Result
|
||||
"did": their_did,
|
||||
"http_url": their_url,
|
||||
}))?;
|
||||
// This requires the local node to be running, so a transport failure
|
||||
// stays a warning rather than failing the command. A reply that
|
||||
// ARRIVED and refused is different: the announce route answers 403
|
||||
// when an unproven caller tries to repoint an existing peer, and
|
||||
// printing the success line over that reports a completed add that
|
||||
// never happened. Same status handling as the remote announce above,
|
||||
// except best effort.
|
||||
match local_client.post("/api/v1/peers/announce", &add_body).await {
|
||||
Ok(resp) => {
|
||||
let status = resp.status();
|
||||
// Same bound as the remote announce above: a compromised local
|
||||
// node (or a MITM on plain http) must not force an unbounded
|
||||
// read. A body that does not parse stays `Null`, which still
|
||||
// routes a non-success status to the warning.
|
||||
let raw = read_body_capped(resp, 8 * 1024).await.text;
|
||||
let result: Value = serde_json::from_str(&raw).unwrap_or(Value::Null);
|
||||
let (is_warning, line) = local_add_report(status, &result);
|
||||
if is_warning {
|
||||
eprintln!("{line}");
|
||||
} else {
|
||||
println!("{line}");
|
||||
}
|
||||
}
|
||||
Err(e) => eprintln!("warning: local peer list not updated: {e}"),
|
||||
}
|
||||
// This requires the local node to be running; ignore errors here
|
||||
let _ = local_client.post("/api/v1/peers/announce", &add_body).await;
|
||||
println!(" Added to local peer list.");
|
||||
}
|
||||
|
||||
Ok(())
|
||||
@@ -305,302 +210,3 @@ async fn cmd_resolve(did: String, node: String) -> Result<()> {
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::{
|
||||
announced_peer_summary, cmd_add, local_add_refusal, local_add_report,
|
||||
remote_announce_failure,
|
||||
};
|
||||
use reqwest::StatusCode;
|
||||
use serde_json::json;
|
||||
|
||||
/// The node's 403 for repointing an existing peer must surface, not print
|
||||
/// as a completed add. Without the status check the command prints "Added
|
||||
/// to local peer list." over a refusal.
|
||||
///
|
||||
/// The fixture body is the real wire shape, not an invented one: the
|
||||
/// message is the Display of `PeerWriteDenied::UnprovenRepoint`, declared
|
||||
/// in `crates/gitlawb-node/src/db/mod.rs`. The executable detector for a
|
||||
/// wording change is the node-side pin
|
||||
/// `announce_unsigned_repoint_is_a_403_denial` in
|
||||
/// `crates/gitlawb-node/src/api/peers.rs`, which asserts this same
|
||||
/// substring against a response driven through the real router, so
|
||||
/// rewording the Display turns that test red and the grep for the old
|
||||
/// phrase lands here.
|
||||
///
|
||||
/// The assertion bites rather than echoing its own input because the
|
||||
/// substring is reachable only through the helper's `body["message"]`
|
||||
/// extraction; the fixture's `error` field carries a different string, so
|
||||
/// reading `body["error"]` instead fails this test.
|
||||
#[test]
|
||||
fn a_refused_local_add_warns_with_the_node_reason() {
|
||||
let warning = local_add_refusal(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({
|
||||
"error": "forbidden",
|
||||
"message": "unproven announce cannot change an existing peer's http_url: did:key:z6MkuMqUm4i228K9qXidJ57zqSWAcQLgrcbMxB8RKVLuqitj"
|
||||
}),
|
||||
)
|
||||
.expect("a refusal must not render as success");
|
||||
|
||||
assert!(warning.contains("403"), "must name the status: {warning}");
|
||||
assert!(
|
||||
warning.contains("unproven announce cannot change an existing peer"),
|
||||
"must carry the node's own reason: {warning}"
|
||||
);
|
||||
}
|
||||
|
||||
/// A refusal with no message body still warns rather than passing silently.
|
||||
#[test]
|
||||
fn a_refusal_without_a_message_still_warns() {
|
||||
let warning = local_add_refusal(StatusCode::BAD_REQUEST, &serde_json::Value::Null)
|
||||
.expect("a refusal must not render as success");
|
||||
assert!(warning.contains("400"), "must name the status: {warning}");
|
||||
}
|
||||
|
||||
/// The accepted case stays quiet, so the success line still prints.
|
||||
#[test]
|
||||
fn an_accepted_local_add_produces_no_warning() {
|
||||
assert!(local_add_refusal(StatusCode::OK, &json!({ "peer_count": 3 })).is_none());
|
||||
}
|
||||
|
||||
/// The warning is printed straight to a terminal, so a node-supplied message
|
||||
/// carrying an OSC title-rewrite plus a C0 escape must reach it defanged.
|
||||
#[test]
|
||||
fn a_refusal_message_cannot_carry_terminal_escapes() {
|
||||
let warning = local_add_refusal(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({ "message": "\u{1b}]2;pwned\u{7}legit-looking text" }),
|
||||
)
|
||||
.expect("a refusal must not render as success");
|
||||
|
||||
assert!(
|
||||
!warning.chars().any(|c| c.is_control()),
|
||||
"control char leaked to the terminal: {warning:?}"
|
||||
);
|
||||
assert!(
|
||||
warning.contains("legit-looking text"),
|
||||
"printable text dropped: {warning:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// Bidi format chars are not `char::is_control`, yet they reorder the
|
||||
/// displayed line, so a refusal must not carry them either.
|
||||
#[test]
|
||||
fn a_refusal_message_cannot_carry_bidi_overrides() {
|
||||
let warning = local_add_refusal(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({ "message": "peer \u{202e}refused\u{202c} here" }),
|
||||
)
|
||||
.expect("a refusal must not render as success");
|
||||
|
||||
assert!(
|
||||
!warning.chars().any(gitlawb_core::sanitize::is_bidi_format),
|
||||
"bidi format char leaked to the terminal: {warning:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// A hostile node must not be able to dump an arbitrary amount of text into
|
||||
/// the user's scrollback through the warning line.
|
||||
#[test]
|
||||
fn a_refusal_message_is_length_bounded() {
|
||||
let warning = local_add_refusal(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({ "message": "x".repeat(5000) }),
|
||||
)
|
||||
.expect("a refusal must not render as success");
|
||||
|
||||
assert!(
|
||||
warning.chars().count() < 500,
|
||||
"warning not bounded: {} chars",
|
||||
warning.chars().count()
|
||||
);
|
||||
}
|
||||
|
||||
/// The status is the part the user can act on, so it must survive a body
|
||||
/// that does not parse. The read is capped, so a peer answering past the cap
|
||||
/// leaves exactly this: a valid status and truncated JSON.
|
||||
#[test]
|
||||
fn a_remote_announce_failure_keeps_the_status_when_the_body_does_not_parse() {
|
||||
let truncated = r#"{"error":"service_unavailable","message":"backend is do"#;
|
||||
let failure = remote_announce_failure(StatusCode::SERVICE_UNAVAILABLE, truncated)
|
||||
.expect("a non-success status must produce a failure");
|
||||
|
||||
assert!(
|
||||
failure.contains("503"),
|
||||
"the status must survive an unparseable body: {failure:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// A parseable error body still reports the peer's own message.
|
||||
#[test]
|
||||
fn a_remote_announce_failure_carries_the_peers_message() {
|
||||
let failure = remote_announce_failure(
|
||||
StatusCode::FORBIDDEN,
|
||||
r#"{"error":"forbidden","message":"unproven announce cannot change an existing peer"}"#,
|
||||
)
|
||||
.expect("a non-success status must produce a failure");
|
||||
|
||||
assert!(
|
||||
failure.contains("403")
|
||||
&& failure.contains("unproven announce cannot change an existing peer"),
|
||||
"status and reason must both survive: {failure:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The fallback path prints the raw body, so it is defanged like every other
|
||||
/// peer-supplied string headed for the terminal.
|
||||
#[test]
|
||||
fn a_remote_announce_failure_defangs_an_unparseable_body() {
|
||||
let failure = remote_announce_failure(
|
||||
StatusCode::BAD_GATEWAY,
|
||||
"\u{1b}]2;pwned\u{7}<html>gateway error</html>",
|
||||
)
|
||||
.expect("a non-success status must produce a failure");
|
||||
|
||||
assert!(
|
||||
!failure.chars().any(|c| c.is_control()),
|
||||
"control char leaked to the terminal: {failure:?}"
|
||||
);
|
||||
assert!(failure.contains("502"), "status dropped: {failure:?}");
|
||||
assert!(
|
||||
failure.contains("gateway error"),
|
||||
"the body is all the user gets when there is no message field: {failure:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The unit tests above bind the helper. This one binds the CALL SITE: the
|
||||
/// failure check has to run before the parse, or a body past the read cap
|
||||
/// turns a 503 into "invalid JSON response" and the status the user needs is
|
||||
/// gone. Reordering the two statements in `cmd_add` compiles and passes every
|
||||
/// other test in this file, so only driving the command catches it.
|
||||
#[tokio::test]
|
||||
async fn a_peer_failure_past_the_read_cap_still_reports_its_status() {
|
||||
let mut peer = mockito::Server::new_async().await;
|
||||
let mut local = mockito::Server::new_async().await;
|
||||
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let _local_info = local
|
||||
.mock("GET", "/")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"public_url":"https://me.example"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
// Valid JSON, but past the 8 KiB read cap, so what survives the read is
|
||||
// truncated and unparseable. This is the shape the cap itself creates.
|
||||
let oversized = format!(r#"{{"message":"{}"}}"#, "x".repeat(16 * 1024));
|
||||
let _peer_refusal = peer
|
||||
.mock("POST", "/api/v1/peers/announce")
|
||||
.with_status(503)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(oversized)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_add(peer.url(), local.url(), Some(dir.path().to_path_buf()))
|
||||
.await
|
||||
.expect_err("a 503 from the peer must fail the command");
|
||||
|
||||
let rendered = format!("{err:#}");
|
||||
assert!(
|
||||
rendered.contains("503"),
|
||||
"the status must survive a body past the read cap: {rendered:?}"
|
||||
);
|
||||
assert!(
|
||||
!rendered.contains("invalid JSON response"),
|
||||
"the parse failure must not stand in for the status: {rendered:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// An accepted announce produces no error, so the caller proceeds to parse.
|
||||
#[test]
|
||||
fn an_accepted_remote_announce_produces_no_failure() {
|
||||
assert!(remote_announce_failure(StatusCode::OK, r#"{"peer_count":3}"#).is_none());
|
||||
}
|
||||
|
||||
/// The selection, not the helper. A refusal must never yield the success
|
||||
/// line, and the success line must never carry the warning prefix. This is
|
||||
/// what stayed green when the entire match was replaced with an
|
||||
/// unconditional "Added to local peer list."
|
||||
#[test]
|
||||
fn a_local_add_refusal_never_selects_the_success_line() {
|
||||
let (is_warning, line) = local_add_report(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({ "message": "unproven announce cannot change an existing peer's http_url: did:key:zAbc" }),
|
||||
);
|
||||
|
||||
assert!(is_warning, "a 403 must select the warning stream: {line:?}");
|
||||
assert!(
|
||||
!line.contains("Added to local peer list"),
|
||||
"a refusal rendered as the success line: {line:?}"
|
||||
);
|
||||
assert!(
|
||||
line.contains("unproven announce cannot change an existing peer"),
|
||||
"the node's reason must reach the user: {line:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The other direction, so the fix cannot be satisfied by always warning.
|
||||
#[test]
|
||||
fn an_accepted_local_add_selects_the_success_line() {
|
||||
let (is_warning, line) = local_add_report(StatusCode::OK, &json!({ "peer_count": 3 }));
|
||||
|
||||
assert!(!is_warning, "a 200 must not select the warning stream");
|
||||
assert!(
|
||||
line.contains("Added to local peer list"),
|
||||
"the success line must still print: {line:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The accepted-announce block prints the remote peer's own DID and URL, so
|
||||
/// a hostile peer answering 200 must not get escapes onto the terminal that
|
||||
/// way either. The refusal path is not the only sink in this command.
|
||||
#[test]
|
||||
fn an_accepted_announce_summary_cannot_carry_terminal_escapes() {
|
||||
let summary = announced_peer_summary(
|
||||
"did:key:z6Mk\u{1b}]2;pwned\u{7}abc",
|
||||
"https://peer.example\u{202e}moc.live//:sptth",
|
||||
3,
|
||||
);
|
||||
|
||||
assert!(
|
||||
!summary.chars().any(|c| c.is_control() && c != '\n'),
|
||||
"control char leaked to the terminal: {summary:?}"
|
||||
);
|
||||
assert!(
|
||||
!summary.chars().any(gitlawb_core::sanitize::is_bidi_format),
|
||||
"bidi format char leaked to the terminal: {summary:?}"
|
||||
);
|
||||
assert!(
|
||||
summary.contains("did:key:z6Mk") && summary.contains("Their peers: 3"),
|
||||
"printable content dropped: {summary:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// The counterweight to the stripping tests: a legitimate message with RTL
|
||||
/// script letters and a ZWJ must survive intact, so the sanitizer is not
|
||||
/// proven by over-stripping.
|
||||
#[test]
|
||||
fn a_legitimate_refusal_message_survives_intact() {
|
||||
let warning = local_add_refusal(
|
||||
StatusCode::FORBIDDEN,
|
||||
&json!({ "message": "peer refused \u{0627}\u{200D}b" }),
|
||||
)
|
||||
.expect("a refusal must not render as success");
|
||||
|
||||
assert!(
|
||||
warning.contains("peer refused \u{0627}\u{200D}b"),
|
||||
"legitimate text mangled: {warning:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
+67
-3
@@ -2,7 +2,7 @@ use anyhow::{Context, Result};
|
||||
use clap::{Args, Subcommand};
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::{read_body_capped, sanitize_node_msg, NodeClient};
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
#[derive(Args)]
|
||||
@@ -46,7 +46,7 @@ pub async fn run(args: SyncArgs) -> Result<()> {
|
||||
if !status.is_success() {
|
||||
// Bound the read: a hostile or broken node must not force an
|
||||
// unbounded allocation just to surface a denial (INV-6, read half).
|
||||
let raw = read_body_capped(resp, 8 * 1024).await.text;
|
||||
let raw = read_body_capped(resp, 8 * 1024).await;
|
||||
let msg = serde_json::from_str::<serde_json::Value>(&raw)
|
||||
.ok()
|
||||
.and_then(|v| {
|
||||
@@ -104,6 +104,39 @@ fn trigger_counts(resp: &serde_json::Value) -> (u64, u64) {
|
||||
)
|
||||
}
|
||||
|
||||
/// Read at most `cap` bytes of a response body. Bounds the allocation from a
|
||||
/// hostile or broken node returning a huge error body — the display is capped
|
||||
/// separately, but the read itself must not be unbounded (INV-6, read half).
|
||||
async fn read_body_capped(mut resp: reqwest::Response, cap: usize) -> String {
|
||||
let mut buf: Vec<u8> = Vec::new();
|
||||
while buf.len() < cap {
|
||||
match resp.chunk().await {
|
||||
Ok(Some(chunk)) => {
|
||||
let take = (cap - buf.len()).min(chunk.len());
|
||||
buf.extend_from_slice(&chunk[..take]);
|
||||
if take < chunk.len() {
|
||||
break; // hit the cap mid-chunk
|
||||
}
|
||||
}
|
||||
_ => break, // end of body or read error — return what we have
|
||||
}
|
||||
}
|
||||
String::from_utf8_lossy(&buf).into_owned()
|
||||
}
|
||||
|
||||
/// Strip terminal-dangerous characters from (and cap the length of) a
|
||||
/// node-supplied error string before surfacing it. The node a caller talks to
|
||||
/// could be hostile and embed escape sequences in its error body; those must not
|
||||
/// reach the terminal verbatim (INV-6). We drop the C0/C1 control bytes (which
|
||||
/// defangs ANSI/OSC escapes) AND the Unicode bidi/format controls (which
|
||||
/// `char::is_control` does not cover — they can reorder the displayed line).
|
||||
fn sanitize_node_msg(s: &str) -> String {
|
||||
s.chars()
|
||||
.filter(|c| !c.is_control() && !gitlawb_core::sanitize::is_bidi_format(*c))
|
||||
.take(200)
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -227,6 +260,37 @@ mod tests {
|
||||
run(args).await.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_strips_controls_bidi_and_caps_length() {
|
||||
// C0 (ESC/BEL) and the Cf bidi override (U+202E) are both removed; the
|
||||
// printable text survives. (Note: a stripped ESC leaves any following
|
||||
// "[31m" as inert literal text — that is the point, so the input here
|
||||
// avoids that residue to keep the expectation unambiguous.)
|
||||
let out = sanitize_node_msg("a\u{1b}\u{07}b\u{202e}c");
|
||||
assert!(
|
||||
!out.chars().any(|c| c.is_control()),
|
||||
"control char leaked: {out:?}"
|
||||
);
|
||||
assert!(
|
||||
!out.contains('\u{202e}'),
|
||||
"RLO bidi override leaked: {out:?}"
|
||||
);
|
||||
assert_eq!(out, "abc");
|
||||
// Length is capped at 200 chars regardless of input size.
|
||||
let long = "x".repeat(250);
|
||||
assert_eq!(sanitize_node_msg(&long).chars().count(), 200);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_preserves_legitimate_and_rtl_text() {
|
||||
// Must not over-strip: a plain word, a genuine RTL SCRIPT letter (Arabic
|
||||
// U+0627, category Lo — NOT a format char), and ZWJ (U+200D, a legitimate
|
||||
// Cf char, e.g. emoji sequences) all survive. Guards the shared predicate
|
||||
// against being widened into a blanket Cf stripper.
|
||||
let out = sanitize_node_msg("ok \u{0627}\u{200D}b");
|
||||
assert_eq!(out, "ok \u{0627}\u{200D}b");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_handles_oversized_error_body_without_unbounded_output() {
|
||||
// A hostile/broken node returns a 2 MB error body. The command must still
|
||||
@@ -261,7 +325,7 @@ mod tests {
|
||||
.create_async()
|
||||
.await;
|
||||
let resp = reqwest::get(format!("{}/big", server.url())).await.unwrap();
|
||||
let out = read_body_capped(resp, 8192).await.text;
|
||||
let out = read_body_capped(resp, 8192).await;
|
||||
assert!(out.len() <= 8192, "read not bounded: {} bytes", out.len());
|
||||
assert!(!out.is_empty(), "expected some body");
|
||||
}
|
||||
|
||||
+14
-334
@@ -1,11 +1,11 @@
|
||||
//! `gl whoami` — print current identity and optional node registration info.
|
||||
|
||||
use anyhow::{bail, Result};
|
||||
use anyhow::Result;
|
||||
use clap::Args;
|
||||
use serde_json::{json, Value};
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::{read_body_capped, sanitize_node_msg, NodeClient};
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
#[derive(Args)]
|
||||
@@ -22,10 +22,6 @@ pub struct WhoamiArgs {
|
||||
}
|
||||
|
||||
pub async fn run(args: WhoamiArgs) -> Result<()> {
|
||||
run_to_writer(args, &mut std::io::stdout()).await
|
||||
}
|
||||
|
||||
pub(crate) async fn run_to_writer(args: WhoamiArgs, w: &mut impl std::io::Write) -> Result<()> {
|
||||
let keypair = load_keypair_from_dir(args.dir.as_deref())?;
|
||||
let did = keypair.did().to_string();
|
||||
let short = did.split(':').next_back().unwrap_or(&did).to_string();
|
||||
@@ -45,7 +41,7 @@ pub(crate) async fn run_to_writer(args: WhoamiArgs, w: &mut impl std::io::Write)
|
||||
if let Some(caps) = info["capabilities"].as_array() {
|
||||
capabilities = caps
|
||||
.iter()
|
||||
.filter_map(|c| c.as_str().map(sanitize_node_msg))
|
||||
.filter_map(|c| c.as_str().map(String::from))
|
||||
.collect();
|
||||
}
|
||||
// Try to get repo count
|
||||
@@ -55,35 +51,11 @@ pub(crate) async fn run_to_writer(args: WhoamiArgs, w: &mut impl std::io::Write)
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(resp) if resp.status().as_u16() == 404 => {
|
||||
Ok(_) => {
|
||||
registered = Some(false);
|
||||
}
|
||||
Ok(resp) => {
|
||||
let status = resp.status();
|
||||
let raw = read_body_capped(resp, 8 * 1024).await.text;
|
||||
let msg = serde_json::from_str::<Value>(&raw)
|
||||
.ok()
|
||||
.and_then(|v| {
|
||||
let non_empty = |m: Option<&Value>| {
|
||||
m.and_then(|m| m.as_str())
|
||||
.map(String::from)
|
||||
.filter(|s| !s.is_empty())
|
||||
};
|
||||
non_empty(v.get("message")).or_else(|| non_empty(v.get("error")))
|
||||
})
|
||||
.unwrap_or(raw);
|
||||
bail!(
|
||||
"agent lookup failed ({status}): {}",
|
||||
sanitize_node_msg(&msg)
|
||||
);
|
||||
}
|
||||
Err(e) => {
|
||||
let detail: String = e
|
||||
.chain()
|
||||
.map(|e| sanitize_node_msg(&e.to_string()))
|
||||
.collect::<Vec<_>>()
|
||||
.join(": ");
|
||||
bail!("agent lookup failed: {detail}");
|
||||
Err(_) => {
|
||||
registered = Some(false);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -105,21 +77,21 @@ pub(crate) async fn run_to_writer(args: WhoamiArgs, w: &mut impl std::io::Write)
|
||||
if let Some(rc) = repo_count {
|
||||
out["repos"] = json!(rc);
|
||||
}
|
||||
writeln!(w, "{}", serde_json::to_string_pretty(&out)?)?;
|
||||
println!("{}", serde_json::to_string_pretty(&out)?);
|
||||
} else {
|
||||
writeln!(w, "DID: {did}")?;
|
||||
writeln!(w, "Short: {short}")?;
|
||||
println!("DID: {did}");
|
||||
println!("Short: {short}");
|
||||
if let Some(reg) = registered {
|
||||
writeln!(w, "Registered: {}", if reg { "yes" } else { "no" })?;
|
||||
println!("Registered: {}", if reg { "yes" } else { "no" });
|
||||
}
|
||||
if let Some(ts) = trust_score {
|
||||
writeln!(w, "Trust: {ts:.2}")?;
|
||||
println!("Trust: {ts:.2}");
|
||||
}
|
||||
if !capabilities.is_empty() {
|
||||
writeln!(w, "Caps: {}", capabilities.join(", "))?;
|
||||
println!("Caps: {}", capabilities.join(", "));
|
||||
}
|
||||
if let Some(rc) = repo_count {
|
||||
writeln!(w, "Repos: {rc}")?;
|
||||
println!("Repos: {rc}");
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
@@ -220,236 +192,7 @@ mod tests {
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let mut out = Vec::new();
|
||||
run_to_writer(args, &mut out).await.unwrap();
|
||||
let out = String::from_utf8(out).unwrap();
|
||||
assert!(out.contains("Registered: no"), "unexpected output: {out}");
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: true,
|
||||
};
|
||||
let mut out = Vec::new();
|
||||
run_to_writer(args, &mut out).await.unwrap();
|
||||
let out = String::from_utf8(out).unwrap();
|
||||
assert!(
|
||||
out.contains("\"registered\": false"),
|
||||
"unexpected output: {out}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_with_node_forbidden() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"forbidden"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(msg.contains("403"), "expected 403 error, got: {msg}");
|
||||
assert!(
|
||||
msg.contains("forbidden"),
|
||||
"expected 'forbidden' in error, got: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_with_node_server_error() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(500)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"internal error"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(msg.contains("500"), "expected 500 error, got: {msg}");
|
||||
assert!(
|
||||
msg.contains("internal error"),
|
||||
"expected 'internal error' in error, got: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_server_error_unusable_message_uses_error() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(500)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"","error":"boom"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(
|
||||
msg.contains("boom"),
|
||||
"expected 'boom' from error field, got: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_with_node_transport_error() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
|
||||
let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
|
||||
let node = format!("http://{}", listener.local_addr().unwrap());
|
||||
drop(listener);
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(node),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(
|
||||
msg.contains("agent lookup failed"),
|
||||
"expected transport error, got: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_transport_sanitizes_control_chars_in_node_url() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
|
||||
let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
|
||||
let port = listener.local_addr().unwrap().port();
|
||||
drop(listener);
|
||||
|
||||
let node = format!("http://127.0.0.1:{port}/\u{1b}]0;PWNED\u{7} \u{202e}gnitirw");
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(node),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(
|
||||
msg.contains("agent lookup failed"),
|
||||
"expected transport error, got: {msg}"
|
||||
);
|
||||
assert!(!msg.contains('\u{1b}'), "ESC leaked into output: {msg:?}");
|
||||
assert!(!msg.contains('\u{7}'), "BEL leaked into output: {msg:?}");
|
||||
assert!(!msg.contains('\u{202e}'), "RLO leaked into output: {msg:?}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_server_error_body_display_bounded() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(502)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body("x".repeat(100_000))
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(
|
||||
msg.contains("502"),
|
||||
"expected 502 error with bounded body, got: {msg}"
|
||||
);
|
||||
let display = format!("{err}");
|
||||
assert!(
|
||||
display.len() < 1000,
|
||||
"error message too long ({} bytes) — body was not capped",
|
||||
display.len()
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_server_error_sanitizes_controls() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(500)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body("{\"message\":\"\\u001b[31mowned\\u0007\\u202eevil\"}")
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
let msg = format!("{err:?}");
|
||||
assert!(
|
||||
msg.contains("owned"),
|
||||
"expected sanitized error body, got: {msg}"
|
||||
);
|
||||
assert!(!msg.contains('\u{1b}'), "ESC control char leaked: {msg}");
|
||||
assert!(!msg.contains('\u{07}'), "BEL control char leaked: {msg}");
|
||||
assert!(!msg.contains('\u{202e}'), "RTL override leaked: {msg}");
|
||||
run(args).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
@@ -487,67 +230,4 @@ mod tests {
|
||||
};
|
||||
run(args).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_whoami_sanitizes_hostile_capabilities() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
let did = kp.did().to_string();
|
||||
let short = did.split(':').next_back().unwrap().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _agent = server
|
||||
.mock("GET", format!("/api/v1/agents/{did}").as_str())
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
"{\"trust_score\":0.5,\"capabilities\":[\"\\u001b]0;PWNED\\u0007repo:write\",\"\\u202egnitirw-tfel\"]}",
|
||||
)
|
||||
.create_async()
|
||||
.await;
|
||||
let _repos = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(format!(r"^/api/v1/repos\?owner={short}")),
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body("[]")
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
// Human mode: no control bytes or bidi overrides reach the terminal
|
||||
let mut buf = Vec::new();
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: false,
|
||||
};
|
||||
run_to_writer(args, &mut buf).await.unwrap();
|
||||
let out = String::from_utf8(buf).unwrap();
|
||||
assert!(!out.contains('\u{1b}'), "ESC leaked in human mode: {out:?}");
|
||||
assert!(!out.contains('\u{07}'), "BEL leaked in human mode: {out:?}");
|
||||
assert!(
|
||||
!out.contains('\u{202e}'),
|
||||
"RLO leaked in human mode: {out:?}"
|
||||
);
|
||||
assert!(out.contains("repo:write"), "benign text missing: {out:?}");
|
||||
assert!(out.contains("tfel"), "reversed text missing: {out:?}");
|
||||
|
||||
// JSON mode: serde escapes C0 but passes bidi — ensure no U+202E
|
||||
let mut buf = Vec::new();
|
||||
let args = WhoamiArgs {
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
node: Some(server.url()),
|
||||
json: true,
|
||||
};
|
||||
run_to_writer(args, &mut buf).await.unwrap();
|
||||
let out = String::from_utf8(buf).unwrap();
|
||||
assert!(
|
||||
!out.contains('\u{202e}'),
|
||||
"RLO leaked in JSON mode: {out:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -44,10 +44,6 @@ services:
|
||||
GITLAWB_BOOTSTRAP_PEERS: ${GITLAWB_BOOTSTRAP_PEERS:-}
|
||||
GITLAWB_BOOTSTRAP_DISABLE_SEEDS: ${GITLAWB_BOOTSTRAP_DISABLE_SEEDS:-false}
|
||||
GITLAWB_REQUIRE_SIGNED_PEER_WRITES: ${GITLAWB_REQUIRE_SIGNED_PEER_WRITES:-false}
|
||||
# Owner-only push. The default matches the node's own, so the container path
|
||||
# behaves like a source build; forwarding it is what makes the documented
|
||||
# rolling-upgrade opt-out reachable for an operator running compose.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH: ${GITLAWB_ENFORCE_OWNER_PUSH:-true}
|
||||
GITLAWB_P2P_BOOTSTRAP: ${GITLAWB_P2P_BOOTSTRAP:-}
|
||||
GITLAWB_PUBLIC_READ: ${GITLAWB_PUBLIC_READ:-true}
|
||||
GITLAWB_MAX_PACK_BYTES: ${GITLAWB_MAX_PACK_BYTES:-2147483648}
|
||||
|
||||
@@ -38,8 +38,8 @@ Owner focus: node reliability.
|
||||
|
||||
Owner focus: protocol/auth.
|
||||
|
||||
- Close default-open repo write authorization and wire trusted UCAN delegation into repository permissions.
|
||||
- Close the remaining visibility gaps: restrict or document task, pin, and anchor metadata routes, and publish an irreversible-publication policy.
|
||||
- Implement repo write authorization: repo owner checks, protected branches, UCAN capability checks, and clear delegation semantics.
|
||||
- Implement private-read enforcement or remove private-repo affordances until it exists.
|
||||
- Add UCAN revocation or blocklisting, with an emergency compromised-key runbook.
|
||||
- Add mutation-aware GraphQL auth before GraphQL becomes a public write API surface.
|
||||
- Harden peer registration and outbound peer calls against SSRF and peer-list poisoning.
|
||||
|
||||
@@ -3,11 +3,6 @@
|
||||
Date: 2026-05-28
|
||||
Repo state inspected: `main` tracking `origin/main`, starting at `b12c6bc feat: per-DID rate limiting on creation endpoints (10/hour) (#13)`.
|
||||
|
||||
> **Historical snapshot.** This audit describes the repository at the commit above. Its
|
||||
> statements about incomplete UCAN chain validation and absent per-repository read
|
||||
> enforcement have been superseded; see [`SECURITY.md`](../SECURITY.md) for the current
|
||||
> security posture.
|
||||
|
||||
## Commands run
|
||||
|
||||
```sh
|
||||
@@ -93,7 +88,7 @@ Fixed or staged in this pass:
|
||||
Live-network blockers to prioritize:
|
||||
|
||||
- GraphQL POST is still open for compatibility; GraphQL mutations should get mutation-aware auth before it becomes a public write API surface.
|
||||
- Push authorization is still not capability-complete. A valid DID signature is authentication, not authorization. Owner checks are now enforced on every branch, protected or not (`GITLAWB_ENFORCE_OWNER_PUSH`, on by default); what remains is that a UCAN `git/push` capability is not yet honored, so a delegated or CI key cannot push.
|
||||
- Push authorization is still not capability-complete. A valid DID signature is authentication, not authorization; unprotected repo branches do not yet enforce owner/UCAN capability checks.
|
||||
- UCAN chain validation is incomplete and UCAN revocation/blocklisting is not implemented as an operator feature.
|
||||
- Private repository reads are not enforced. `is_public` and `GITLAWB_PUBLIC_READ` exist, but per-repository private-read behavior is not wired.
|
||||
- Peer URLs are self-asserted by DIDs. Signatures prove control of the DID key when present, not ownership/safety of the announced URL.
|
||||
|
||||
+20
-35
@@ -141,43 +141,31 @@ During the cooldown your node still earns rewards if it keeps heartbeating.
|
||||
|
||||
---
|
||||
|
||||
## Owner-only push
|
||||
## Hardening: owner-only push
|
||||
|
||||
The node requires the authenticated pusher to be the repo owner on **every**
|
||||
branch. A push whose authenticated DID is not the repo owner is rejected with
|
||||
HTTP 403 before any ref update is applied. The owner is matched in both the full
|
||||
`did:key:z6Mk…` form and its bare `z6Mk…` suffix.
|
||||
By default the node authenticates every `git-receive-pack` push (a valid RFC 9421
|
||||
`did:key` signature) but does **not** check that the pusher owns the repo, except
|
||||
on branches that are explicitly protected. Because `did:key` is self-certifying,
|
||||
any party can generate a key, derive its DID, sign, and push to an unprotected
|
||||
branch — authentication is not authorization.
|
||||
|
||||
This is on by default, and the default is the point. The node authenticates every
|
||||
`git-receive-pack` push with a valid RFC 9421 `did:key` signature, but `did:key`
|
||||
is self-certifying: any party can generate a key, derive its DID and sign.
|
||||
Authentication is not authorization, so without this gate every signed caller can
|
||||
push to every repository — private ones included — on any branch that is not
|
||||
explicitly protected.
|
||||
|
||||
### Turning it off
|
||||
To require the authenticated pusher to be the repo owner on **every** branch, set:
|
||||
|
||||
```bash
|
||||
GITLAWB_ENFORCE_OWNER_PUSH=false
|
||||
GITLAWB_ENFORCE_OWNER_PUSH=true
|
||||
```
|
||||
|
||||
Both the environment variable and `--enforce-owner-push false` disable it; the
|
||||
bare `--enforce-owner-push` flag still means `true`.
|
||||
|
||||
Do this only for a rolling upgrade whose pushers are not yet the repo owner, and
|
||||
treat it as temporary: while it is off, your node accepts a push to any repository
|
||||
from anyone who can generate a keypair.
|
||||
|
||||
### Caution: delegated and CI keys are non-owners
|
||||
|
||||
Push authorization is owner-only today. A UCAN `git/push` capability is verified
|
||||
but **not yet honored for authorization**, so a delegated key cannot push while
|
||||
this gate is on, even when it holds a valid capability for the repo.
|
||||
|
||||
If your automation pushes under its own DID rather than the owner's, it will start
|
||||
getting 403s. Either have it push as the owner, or set
|
||||
`GITLAWB_ENFORCE_OWNER_PUSH=false` until scoped collaborator / UCAN-delegated push
|
||||
rights land — that work is what removes this trade-off.
|
||||
- **Default `false`** — preserves current behavior so live nodes are unaffected by
|
||||
an upgrade. Turn it on once you're ready for owner-only writes.
|
||||
- **When `true`** — a push whose authenticated DID is not the repo owner is
|
||||
rejected (HTTP 403) before any ref update is applied. The owner is matched in
|
||||
both the full `did:key:z6Mk…` form and its bare `z6Mk…` suffix.
|
||||
- **Caution: this blocks every non-owner pusher, including your own delegated and
|
||||
CI agents.** Push authorization is owner-only today — a UCAN `git/push`
|
||||
capability is verified but not yet honored for authorization, so delegated keys
|
||||
cannot push while this is on. Don't enable it until every identity that pushes
|
||||
to your repos is the owner, or you'll lock out your own automation. Scoped
|
||||
collaborator / UCAN-delegated push rights are a planned follow-up.
|
||||
|
||||
---
|
||||
|
||||
@@ -189,8 +177,7 @@ rights land — that work is what removes this trade-off.
|
||||
| Missed heartbeats | After 3 days without one, you're excluded from rewards until you beat again |
|
||||
| Operator key | Dedicated wallet, small ETH balance, not your main treasury |
|
||||
| Monitoring | Watch `lastHeartbeat` on-chain; alert if > 22h since last beat |
|
||||
| Public URL | Must resolve and serve `/health` for liveness and DB-aware `/ready` for peer readiness |
|
||||
| Rolling upgrade (advisory-lock algorithm) | The SHA-256 advisory-lock key swap (replacing `DefaultHasher`) re-keys every repo in the first release that carries it. During a shared-Postgres rolling upgrade, old nodes compute a different `i64` key than new nodes for the same repo, so PostgreSQL treats them as independent locks and cross-machine write-exclusion is lost. **Drain in-flight writes** or cut over through a **single node** before bringing new-binary nodes online. |
|
||||
| Public URL | Must resolve and serve `/health` — peers will ping it |
|
||||
|
||||
---
|
||||
|
||||
@@ -200,8 +187,6 @@ rights land — that work is what removes this trade-off.
|
||||
|
||||
**Node refuses to start with "strict-mode operator check failed"** — either `gl node register` first, or unset `GITLAWB_OPERATOR_STRICT_MODE`.
|
||||
|
||||
**Node refuses to start with "GITLAWB_DB_MAX_CONNECTIONS (20) must be at least max_concurrent_git_pushes (32) + 8 headroom"**: raise `GITLAWB_DB_MAX_CONNECTIONS` to at least the push cap plus 8 (40 with the default cap of 32; 48 is the shipped default and the recommended value), or lower `GITLAWB_MAX_CONCURRENT_GIT_PUSHES`. This bites a node upgraded in place that still sets the old pool size of 20. The check is deliberate: each concurrent push pins one pooled connection for its whole receive-pack, so a pool that does not clear the push cap lets a burst of slow pushes starve every other database path.
|
||||
|
||||
**Rewards are 0 after a week** — run `gl node onchain-status`. If `currentlyActive: false`, check your heartbeat loop (node logs for `operator heartbeat sent`).
|
||||
|
||||
**Want to rotate operator wallet** — requires unstake → re-register with new wallet. No in-place rotation in v1.
|
||||
|
||||
+11
-60
@@ -91,39 +91,13 @@ User-data only runs at first boot, so upgrades go through SSM:
|
||||
$(terraform output -raw upgrade_command)
|
||||
```
|
||||
|
||||
This reinstalls the rendered `/opt/gitlawb/compose.yaml`, then runs
|
||||
`docker compose pull && docker compose up -d` on the instance.
|
||||
|
||||
**Run `terraform apply` before the upgrade command.** The command is an SSM
|
||||
document managed by Terraform, and it embeds the compose file rendered from your
|
||||
current variables. An instance that has not had a fresh `apply` still holds the
|
||||
previous document and will reinstall the previous compose file.
|
||||
This runs `docker compose pull && docker compose up -d` on the instance.
|
||||
|
||||
- With `image_tag = "latest"` (default) that picks up the newest release.
|
||||
- With a **pinned tag**, set `image_tag` in `terraform.tfvars` and `apply` — the
|
||||
rendered compose carries it, so the upgrade installs the right version.
|
||||
- **`compose.yaml` is Terraform-owned and is overwritten on every upgrade.**
|
||||
Per-instance settings belong in `/opt/gitlawb/.env`, which is never touched.
|
||||
- **The upgrade reconciles the service set, not just the image.** The rendering is
|
||||
conditional — `postgres` exists only when `db_host` is empty, `caddy` only when
|
||||
`domain_name` is set — and the command runs `--remove-orphans`. So setting
|
||||
`use_rds`, or clearing `domain_name`, and then upgrading will **stop and remove**
|
||||
the local postgres or the TLS terminator. That is the intended outcome of those
|
||||
variables, but it happens on the upgrade rather than on `apply`. Data survives
|
||||
either way: both bind-mount under `/mnt/data`.
|
||||
|
||||
### Why the upgrade rewrites the compose file
|
||||
|
||||
`aws_instance` deliberately ignores `user_data` drift, so an instance keeps the
|
||||
compose file it was created with. Compose passes only the variables named in a
|
||||
service's `environment:` block into the container, so **a node setting added to
|
||||
the template never reaches an existing instance** — writing it to
|
||||
`/opt/gitlawb/.env` and restarting leaves the node on its built-in default, with
|
||||
no error to indicate it. `pull && up -d` alone cannot fix that, because the file
|
||||
on disk is the authoritative one.
|
||||
|
||||
Reinstalling the rendering first makes the upgrade a real migration. It is
|
||||
idempotent: on an already-current instance it writes identical bytes.
|
||||
- With a **pinned tag**, first edit the tag in `/opt/gitlawb/compose.yaml` on
|
||||
the instance (via SSM session), then run the upgrade command — and keep
|
||||
`image_tag` in terraform.tfvars in sync so a future instance replacement
|
||||
boots the same version.
|
||||
|
||||
Replace the instance itself (OS/AMI/instance-type changes) with
|
||||
`terraform apply -replace=aws_instance.node` — the data volume reattaches and
|
||||
@@ -131,24 +105,12 @@ Replace the instance itself (OS/AMI/instance-type changes) with
|
||||
|
||||
## Changing configuration
|
||||
|
||||
`terraform apply` alone never changes a running instance: user-data runs once and
|
||||
the instance ignores `user_data` drift. How a change rolls out depends on which
|
||||
of the two files carries it.
|
||||
|
||||
**Rendered into `compose.yaml`** — `image_tag`, `gitlawb_port`, `metrics_port`,
|
||||
`domain_name`, `db_host`, the `icaptcha_*` values. `apply`, then run
|
||||
`upgrade_command`: it installs the new rendering and restarts.
|
||||
|
||||
```sh
|
||||
terraform apply
|
||||
$(terraform output -raw upgrade_command)
|
||||
```
|
||||
|
||||
**Written into `/opt/gitlawb/.env` at first boot** — `public_url`,
|
||||
`bootstrap_peers`, `auto_sync`, `max_pack_bytes`, and the integration secrets.
|
||||
Editing these in `terraform.tfvars` does **not** reach a running instance, because
|
||||
nothing rewrites `.env` after the first boot. Either edit `/opt/gitlawb/.env` on
|
||||
the instance and `docker compose up -d`, or replace it:
|
||||
User-data only runs at first boot, and the instance ignores `user_data` drift
|
||||
(`ignore_changes`), so editing terraform.tfvars values that feed the bootstrap
|
||||
(`bootstrap_peers`, `public_url`, integrations, `image_tag`) does **not**
|
||||
affect a running instance on `terraform apply`. To roll out such changes,
|
||||
either edit `/opt/gitlawb/.env` on the instance (SSM session, then
|
||||
`docker compose up -d`), or replace the instance:
|
||||
|
||||
```sh
|
||||
terraform apply -replace=aws_instance.node
|
||||
@@ -156,17 +118,6 @@ terraform apply -replace=aws_instance.node
|
||||
|
||||
The data volume reattaches; repos, postgres data, and the identity key survive.
|
||||
|
||||
**A node setting the installed `compose.yaml` does not already name** —
|
||||
`GITLAWB_ENFORCE_OWNER_PUSH` on an instance created before it was added, for
|
||||
example. Editing `.env` is **not enough**: compose only passes through the
|
||||
variables its `environment:` block lists, so the value is read from `.env` and
|
||||
then dropped. Run `apply` plus `upgrade_command` first, which installs a compose
|
||||
file that names the key; after that, `.env` governs it like any other.
|
||||
|
||||
That last case is the one worth remembering: `.env` reaches the container only for
|
||||
keys the *installed* compose interpolates, and the upgrade is what makes a newly
|
||||
added key one of them.
|
||||
|
||||
## Remote state (optional)
|
||||
|
||||
Local state is the default. To move state to S3: create a versioned bucket,
|
||||
|
||||
@@ -72,9 +72,6 @@ services:
|
||||
GITLAWB_BOOTSTRAP_PEERS: $${GITLAWB_BOOTSTRAP_PEERS}
|
||||
GITLAWB_AUTO_SYNC: $${GITLAWB_AUTO_SYNC}
|
||||
GITLAWB_MAX_PACK_BYTES: $${GITLAWB_MAX_PACK_BYTES}
|
||||
# Owner-only push. Matches the node's own default; forwarding it is what makes
|
||||
# the documented rolling-upgrade opt-out reachable on the container path.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH: $${GITLAWB_ENFORCE_OWNER_PUSH:-true}
|
||||
# On-chain PoS (optional — empty unless set in terraform.tfvars)
|
||||
GITLAWB_CHAIN_RPC_URL: $${GITLAWB_CHAIN_RPC_URL}
|
||||
GITLAWB_CONTRACT_NODE_STAKING: $${GITLAWB_CONTRACT_NODE_STAKING}
|
||||
|
||||
+7
-62
@@ -350,16 +350,10 @@ resource "aws_instance" "node" {
|
||||
# ami: new AL2023 releases shouldn't churn the instance; replace
|
||||
# deliberately for OS upgrades.
|
||||
# user_data: only runs at first boot, so re-rendering it on a live
|
||||
# instance is a pointless stop/start. How a config change reaches a running
|
||||
# instance depends on which file carries it:
|
||||
# - rendered into compose.yaml (image_tag, ports, domain_name, db_host,
|
||||
# icaptcha_*): `terraform apply` then `upgrade_command`, which
|
||||
# reinstalls the rendering and restarts.
|
||||
# - written into /opt/gitlawb/.env at first boot (public_url,
|
||||
# bootstrap_peers, integrations): nothing rewrites .env afterwards, so
|
||||
# these need an edit on the instance or
|
||||
# `terraform apply -replace=aws_instance.node`.
|
||||
# See README "Changing configuration".
|
||||
# instance is a pointless stop/start. Config changes that feed user-data
|
||||
# (bootstrap peers, integrations, image tag) require a deliberate
|
||||
# `terraform apply -replace=aws_instance.node` — see README "Changing
|
||||
# configuration".
|
||||
ignore_changes = [ami, user_data]
|
||||
}
|
||||
}
|
||||
@@ -443,62 +437,13 @@ resource "aws_ssm_document" "upgrade" {
|
||||
|
||||
content = jsonencode({
|
||||
schemaVersion = "2.2"
|
||||
description = "Reinstall the rendered compose file, pull the latest image, and restart"
|
||||
description = "Pull the latest gitlawb node image and restart the compose stack"
|
||||
mainSteps = [{
|
||||
action = "aws:runShellScript"
|
||||
name = "upgrade"
|
||||
inputs = {
|
||||
# Reinstall the CURRENT rendering before restarting.
|
||||
#
|
||||
# `aws_instance` ignores user_data drift, so an instance created before a
|
||||
# template change keeps the compose file it was born with. Compose passes
|
||||
# only the variables named in its `environment:` block into the container,
|
||||
# so a node setting added to the template never reaches an existing
|
||||
# instance — the operator writes it to /opt/gitlawb/.env, restarts, and the
|
||||
# node silently keeps the built-in default. `docker compose pull && up -d`
|
||||
# cannot fix that: the authoritative file is the one on disk.
|
||||
#
|
||||
# Idempotent: writing the same bytes and restarting is a no-op. This does
|
||||
# overwrite hand-edits to compose.yaml, which is intended — the file is
|
||||
# Terraform-owned; per-instance settings belong in /opt/gitlawb/.env.
|
||||
#
|
||||
# One shell step, under flock, writing through mktemp. Two overlapping
|
||||
# executions — a double run, a retry while the first is still pulling, two
|
||||
# operators — otherwise share one fixed temp path: the second truncates the
|
||||
# file the first is about to install, and once the first renames, the
|
||||
# second's open descriptor keeps writing into the live compose.yaml inode.
|
||||
# Both outcomes stay valid YAML, so the `up -d --remove-orphans` on the next
|
||||
# line accepts a blended or truncated service set and deletes whatever fell
|
||||
# off — on a live node, the local postgres or the TLS terminator. The lock
|
||||
# also covers pull and up, so a second run cannot restart against a file the
|
||||
# first is mid-install.
|
||||
runCommand = [<<-UPGRADE
|
||||
set -euo pipefail
|
||||
install -d -m 0755 /opt/gitlawb
|
||||
|
||||
exec 9>/opt/gitlawb/.upgrade.lock
|
||||
if ! flock -n 9; then
|
||||
echo "another upgrade is already running on this instance" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
tmp="$(mktemp /opt/gitlawb/compose.yaml.XXXXXX)"
|
||||
trap 'rm -f "$tmp"' EXIT
|
||||
# base64 rather than a nested heredoc: the rendered compose contains
|
||||
# `$${VAR}` passthroughs that must reach the file unexpanded, and a
|
||||
# heredoc inside an indented Terraform heredoc depends on the dedent
|
||||
# landing the delimiter at column 0. Decoding a single line has neither
|
||||
# failure mode, and no delimiter can collide with the content.
|
||||
echo '${base64encode(local.compose_yaml)}' | base64 -d > "$tmp"
|
||||
chmod 0644 "$tmp"
|
||||
mv "$tmp" /opt/gitlawb/compose.yaml
|
||||
trap - EXIT
|
||||
|
||||
cd /opt/gitlawb
|
||||
docker compose pull
|
||||
docker compose up -d --remove-orphans
|
||||
docker image prune -f
|
||||
UPGRADE
|
||||
runCommand = [
|
||||
"cd /opt/gitlawb && docker compose pull && docker compose up -d --remove-orphans && docker image prune -f"
|
||||
]
|
||||
}
|
||||
}]
|
||||
|
||||
@@ -19,11 +19,6 @@ class Config {
|
||||
var operatorPrivateKey: String = ""
|
||||
var tigrisBucket: String = ""
|
||||
var autoSync: Bool = false
|
||||
/// Owner-only push. Persisted as a setting rather than read from a hand-edited
|
||||
/// `.env`, because `writeEnvFile()` regenerates that file on every start and
|
||||
/// would discard the edit. Matches the node's own default; set false only for a
|
||||
/// rolling upgrade whose pushers are not yet the repo owner.
|
||||
var enforceOwnerPush: Bool = true
|
||||
var repoPathString: String = ""
|
||||
|
||||
// MARK: - Paths
|
||||
@@ -81,7 +76,6 @@ class Config {
|
||||
"operatorPrivateKey": operatorPrivateKey,
|
||||
"tigrisBucket": tigrisBucket,
|
||||
"autoSync": autoSync,
|
||||
"enforceOwnerPush": enforceOwnerPush,
|
||||
"repoPath": repoPathString,
|
||||
]
|
||||
|
||||
@@ -111,7 +105,6 @@ class Config {
|
||||
operatorPrivateKey = dict["operatorPrivateKey"] as? String ?? operatorPrivateKey
|
||||
tigrisBucket = dict["tigrisBucket"] as? String ?? tigrisBucket
|
||||
autoSync = dict["autoSync"] as? Bool ?? autoSync
|
||||
enforceOwnerPush = dict["enforceOwnerPush"] as? Bool ?? enforceOwnerPush
|
||||
repoPathString = dict["repoPath"] as? String ?? repoPathString
|
||||
}
|
||||
|
||||
@@ -128,7 +121,6 @@ class Config {
|
||||
lines.append("GITLAWB_PORT=\(httpPort)")
|
||||
lines.append("GITLAWB_P2P_PORT=\(p2pPort)")
|
||||
lines.append("GITLAWB_AUTO_SYNC=\(autoSync)")
|
||||
lines.append("GITLAWB_ENFORCE_OWNER_PUSH=\(enforceOwnerPush)")
|
||||
|
||||
if !chainRpcURL.isEmpty {
|
||||
lines.append("GITLAWB_CHAIN_RPC_URL=\(chainRpcURL)")
|
||||
|
||||
@@ -294,10 +294,6 @@ services:
|
||||
GITLAWB_HOST: 0.0.0.0
|
||||
GITLAWB_PUBLIC_URL: ${GITLAWB_PUBLIC_URL:-http://localhost:7545}
|
||||
GITLAWB_P2P_PORT: 7546
|
||||
# Owner-only push. Must match the bundled Resources/docker-compose.yml: this
|
||||
# generated file — not the bundled resource — is what a packaged app runs, so
|
||||
# omitting it here leaves the documented opt-out unreachable for those users.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH: ${GITLAWB_ENFORCE_OWNER_PUSH:-true}
|
||||
GITLAWB_CHAIN_RPC_URL: ${GITLAWB_CHAIN_RPC_URL:-}
|
||||
GITLAWB_CONTRACT_NODE_STAKING: ${GITLAWB_CONTRACT_NODE_STAKING:-}
|
||||
GITLAWB_OPERATOR_PRIVATE_KEY: ${GITLAWB_OPERATOR_PRIVATE_KEY:-}
|
||||
|
||||
@@ -33,9 +33,6 @@ services:
|
||||
GITLAWB_PORT: ${GITLAWB_PORT:-7545}
|
||||
GITLAWB_PUBLIC_URL: ${GITLAWB_PUBLIC_URL:-http://localhost:7545}
|
||||
GITLAWB_P2P_PORT: ${GITLAWB_P2P_PORT:-7546}
|
||||
# Owner-only push. Matches the node's own default; forwarding it is what makes
|
||||
# the documented rolling-upgrade opt-out reachable on the container path.
|
||||
GITLAWB_ENFORCE_OWNER_PUSH: ${GITLAWB_ENFORCE_OWNER_PUSH:-true}
|
||||
# Sync
|
||||
GITLAWB_AUTO_SYNC: ${GITLAWB_AUTO_SYNC:-false}
|
||||
# On-chain PoS (optional — leave unset for local/dev)
|
||||
|
||||
@@ -28,7 +28,6 @@ struct SettingsView: View {
|
||||
@State private var operatorPrivateKey: String = Config.shared.operatorPrivateKey
|
||||
@State private var tigrisBucket: String = Config.shared.tigrisBucket
|
||||
@State private var autoSync: Bool = Config.shared.autoSync
|
||||
@State private var enforceOwnerPush: Bool = Config.shared.enforceOwnerPush
|
||||
|
||||
var body: some View {
|
||||
VStack(alignment: .leading, spacing: 12) {
|
||||
@@ -54,15 +53,6 @@ struct SettingsView: View {
|
||||
.font(.caption)
|
||||
.foregroundColor(.secondary)
|
||||
}
|
||||
VStack(alignment: .leading, spacing: 2) {
|
||||
Toggle("Require repo owner to push", isOn: $enforceOwnerPush)
|
||||
Text("A signature proves who is pushing, not that they own the repo. "
|
||||
+ "Turn this off only during a rolling upgrade whose pushers are "
|
||||
+ "not yet the owner — while off, anyone who can sign may push to "
|
||||
+ "any repo on this node.")
|
||||
.font(.caption)
|
||||
.foregroundColor(.secondary)
|
||||
}
|
||||
|
||||
Divider()
|
||||
|
||||
@@ -106,7 +96,6 @@ struct SettingsView: View {
|
||||
Config.shared.operatorPrivateKey = operatorPrivateKey
|
||||
Config.shared.tigrisBucket = tigrisBucket
|
||||
Config.shared.autoSync = autoSync
|
||||
Config.shared.enforceOwnerPush = enforceOwnerPush
|
||||
|
||||
Config.shared.persist()
|
||||
Config.shared.writeEnvFile()
|
||||
|
||||
@@ -12,8 +12,7 @@
|
||||
{ "type": "generic", "path": "crates/gitlawb-node/Cargo.toml" },
|
||||
{ "type": "generic", "path": "crates/gl/Cargo.toml" },
|
||||
{ "type": "generic", "path": "crates/git-remote-gitlawb/Cargo.toml" },
|
||||
{ "type": "generic", "path": "crates/gitlawb-attest/Cargo.toml" },
|
||||
{ "type": "generic", "path": "crates/icaptcha-client/Cargo.toml" }
|
||||
{ "type": "generic", "path": "crates/gitlawb-attest/Cargo.toml" }
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,117 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Release-versioning coverage gate for the workspace crates.
|
||||
#
|
||||
# release-please owns every crate's version. It rewrites a version line only
|
||||
# when BOTH halves hold: the line carries an `# x-release-please-version`
|
||||
# annotation, and the crate's manifest is listed under `extra-files` in
|
||||
# release-please-config.json. A crate missing either half is silently skipped
|
||||
# at release time and freezes at whatever version it was created with, which
|
||||
# is exactly what happened to icaptcha-client (added as a workspace member
|
||||
# after the config was last written, so it sat at 0.4.0 while the rest of the
|
||||
# workspace walked to 0.7.1 across four releases).
|
||||
#
|
||||
# Exhaustive-by-construction: the required set is DERIVED from the workspace
|
||||
# member list via `cargo metadata`, never from a hand-maintained list here. A
|
||||
# newly added crate reds CI whether or not anyone remembered this gate exists,
|
||||
# which is the property a hand list cannot have.
|
||||
#
|
||||
# Hard-fail directions, all three release-silent:
|
||||
# 1. a workspace member absent from extra-files
|
||||
# 2. a workspace member whose version line lacks the annotation
|
||||
# 3. an extra-files entry pointing at a manifest that no longer exists
|
||||
#
|
||||
# Runnable from anywhere in the repo.
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(git rev-parse --show-toplevel)"
|
||||
CONFIG="$ROOT/release-please-config.json"
|
||||
|
||||
if [ ! -f "$CONFIG" ]; then
|
||||
echo "ERROR: release-please config not found at $CONFIG" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Resolving can refresh Cargo.lock as a side effect, so snapshot and restore it:
|
||||
# this check must never leave the working tree dirty when run locally. Same
|
||||
# reasoning as scripts/check-gitlawb-core-deps.sh.
|
||||
lock_backup="$(mktemp)"
|
||||
cp "$ROOT/Cargo.lock" "$lock_backup"
|
||||
restore_lock() { cp "$lock_backup" "$ROOT/Cargo.lock"; rm -f "$lock_backup"; }
|
||||
trap restore_lock EXIT
|
||||
|
||||
# Workspace members as repo-relative manifest paths, one per line. This is the
|
||||
# derived required set: whatever cargo considers a member must be release-managed.
|
||||
members="$(
|
||||
cargo metadata --no-deps --format-version 1 --manifest-path "$ROOT/Cargo.toml" \
|
||||
| jq -r '.packages[].manifest_path' \
|
||||
| sed "s#^$ROOT/##" \
|
||||
| sort -u
|
||||
)"
|
||||
|
||||
# Manifest paths release-please is configured to rewrite.
|
||||
listed="$(jq -r '.packages["."]["extra-files"][] | .path' "$CONFIG" | sort -u)"
|
||||
|
||||
unlisted="$(comm -23 <(printf '%s\n' "$members") <(printf '%s\n' "$listed"))"
|
||||
orphaned="$(comm -13 <(printf '%s\n' "$members") <(printf '%s\n' "$listed"))"
|
||||
|
||||
# Second half of the invariant: being listed does nothing without the marker,
|
||||
# because the generic updater keys on the annotation to find the line.
|
||||
#
|
||||
# Scoped to the [package] table on purpose. A manifest-wide match is satisfied by
|
||||
# an annotated `version` under any other table, so a crate could leave the version
|
||||
# cargo actually reads unannotated, pass this gate, and still freeze at release
|
||||
# time while release-please rewrote the decoy line instead.
|
||||
unmarked=""
|
||||
while IFS= read -r manifest; do
|
||||
[ -n "$manifest" ] || continue
|
||||
if ! awk '
|
||||
/^[[:space:]]*\[/ { in_package = ($0 ~ /^[[:space:]]*\[package\][[:space:]]*$/); next }
|
||||
in_package && /^version = ".*" # x-release-please-version/ { found = 1 }
|
||||
END { exit(found ? 0 : 1) }
|
||||
' "$ROOT/$manifest"; then
|
||||
unmarked="$unmarked$manifest"$'\n'
|
||||
fi
|
||||
done <<< "$members"
|
||||
|
||||
failed=0
|
||||
|
||||
if [ -n "$unlisted" ]; then
|
||||
{
|
||||
echo "ERROR: workspace members missing from extra-files in release-please-config.json:"
|
||||
printf ' %s\n' $unlisted
|
||||
echo
|
||||
echo "release-please will never bump these crates, so they freeze at their"
|
||||
echo "current version while the rest of the workspace moves. Add each one as"
|
||||
echo ' { "type": "generic", "path": "<manifest path>" }'
|
||||
} >&2
|
||||
failed=1
|
||||
fi
|
||||
|
||||
if [ -n "$unmarked" ]; then
|
||||
{
|
||||
echo "ERROR: workspace members whose version line lacks the release-please annotation:"
|
||||
printf ' %s\n' $unmarked
|
||||
echo
|
||||
echo 'The generic updater finds the line by its trailing `# x-release-please-version`'
|
||||
echo "comment. Without it the crate is listed but never rewritten."
|
||||
} >&2
|
||||
failed=1
|
||||
fi
|
||||
|
||||
if [ -n "$orphaned" ]; then
|
||||
{
|
||||
echo "ERROR: extra-files entries pointing at manifests that are not workspace members:"
|
||||
printf ' %s\n' $orphaned
|
||||
echo
|
||||
echo "release-please fails the release when an extra-file path does not exist."
|
||||
echo "Drop the stale entry, or restore the crate to the workspace."
|
||||
} >&2
|
||||
failed=1
|
||||
fi
|
||||
|
||||
if [ "$failed" -ne 0 ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "release versioning coverage: OK ($(printf '%s\n' "$members" | wc -l | tr -d ' ') workspace members, all annotated and listed)."
|
||||
Reference in new issue
Block a user