Fix audit findings: lock architecture, security, deployment hardening

Close all 14 findings from the codebase audit (1 high, 5 medium, 8 low):

- Locking: replace the global API and workspace mutexes with per-instance
  and per-user keyed locks (new internal/api/locks.go) so a slow restore,
  upgrade or transfer no longer blocks unrelated users or instances; move
  Docker I/O out of the build queue and invalidate concurrent image-index
  observations with a generation counter; serialize instance deletion
  behind in-flight creation.
- Security: equalize login timing for unknown usernames, periodically
  purge expired sessions/refresh tokens/lock rows, URL-encode orphan IDs
  in the frontend, upgrade vitest 3.x->5.x to clear 3 npm audit
  vulnerabilities (2 critical RCE).
- Deployment: add a -healthcheck mode probing /healthz (used by Dockerfile
  HEALTHCHECK and compose), make ADMIN_PASSWORD optional in compose with
  removal guidance after first start, exclude test scripts from the image,
  and cap panel resources (cpus: 2, pids_limit: 512).
- Reliability: check rows.Err() on admin listing loops, surface intent
  polling errors without sticking, disable close during in-flight create.

Verified: go build/vet, full go test -race -count=1 ./..., frontend
tsc build + 32 tests, npm audit 0, compose config, real-container
healthcheck.
This commit is contained in:
2026-10-13 20:59:28 +08:00
parent 85332bbc56
commit 66abb76318
33 changed files with 1065 additions and 540 deletions
+15 -12
View File
@@ -63,20 +63,23 @@ func (a *API) config(w http.ResponseWriter, r *http.Request, i store.Instance, a
}
}
}
a.mu.Lock()
locked := true
inst := a.instanceLocks.Acquire(i.ID)
locked := inst
defer func() {
if locked {
a.mu.Unlock()
if locked != nil {
locked.Release()
}
}()
if r.Method != http.MethodGet && a.workspaceReaders[i.ID] > 0 {
fail(w, 409, "instance files busy; retry later")
return
}
if r.Method != http.MethodGet {
workspaceMu.Lock()
defer workspaceMu.Unlock()
a.readersMu.Lock()
readers := a.workspaceReaders[i.ID]
a.readersMu.Unlock()
if readers > 0 {
fail(w, 409, "instance files busy; retry later")
return
}
user := a.userLocks.Acquire(i.UID)
defer user.Release()
}
current, e := a.s.GetInstance(i.ID)
if e != nil || current.UID != i.UID {
@@ -266,8 +269,8 @@ func (a *API) config(w http.ResponseWriter, r *http.Request, i store.Instance, a
fail(w, 400, "invalid backup")
return
}
a.mu.Unlock()
locked = false
locked.Release()
locked = nil
http.ServeContent(w, r, id+".dshbak", st.ModTime(), f)
return
}