fix: verify signed assignment rosters

This commit is contained in:
Josh Creek
2026-09-01 09:53:45 +01:00
parent 55e07648cf
commit 8b5b5333c6
4 changed files with 32 additions and 8 deletions
+3 -2
View File
@@ -58,8 +58,9 @@ product policy are in [`docs/MATCHMAKING.md`](docs/MATCHMAKING.md).
fencing; `server/agones` now submits and validates namespaced
`GameServerAllocation` responses, including dynamic address/port data;
`server/allocator` now requires provider allocation reconciliation into the
durable registry before returning an endpoint; signed roster publication and
live Agones integration remain.
durable registry before returning an endpoint; durable roster publication
now verifies canonical join-authorisation signatures before exposing player
rows; live Agones integration remains.
- [ ] **IN PROGRESS:** Run the Go control plane against PostgreSQL/Redis with
independently runnable API, matcher, allocator and maintenance roles. The
`cmd/control-plane` API role now opens PostgreSQL, applies migrations, wires
+1 -1
View File
@@ -1214,7 +1214,7 @@ the local/CI/community transport, not a silent production fallback.
| 8.28 `[D:8.6,8.27]` | **IN PROGRESS.** Supervisor separates explicit process-ready from Agones Ready and never scrapes stdout; allocated mode refuses to mark Ready without a configured readiness probe | `server/supervisor/` tests prove Ready follows the probe and direct mode remains functional; `server_control.gd`, `agones_sdk.gd` and process-level smokes prove loopback `/ready`, `/health`, bearer-protected `/drain`, sidecar-shaped Health/Ready calls and drain admission fencing; detached-container and Health-reclaim integration remain |
| 8.29 `[D:8.26,8.27]` | **IN PROGRESS.** Supervisor discovers and validates the Agones endpoint, propagates the actual dynamic `--port`, and exports `SDR_LISTEN_PORT`/`SDR_IP` only for Hosted-SDR while preserving an isolated ENet path | `server/supervisor/` tests cover invalid address/port rejection, dynamic port argument/env propagation and SDR-vs-ENet separation; real Agones dynamic/passthrough mapping, POP/cert/firewall/NAT and multi-match fixture remain |
| 8.30 `[D:8.18,8.26,8.28,8.29]` | **IN PROGRESS.** Pure Go allocator filters Ready servers by region/build/protocol/transport, atomically claims one with idempotent allocation replay, and now owns the assignment-publication boundary; PostgreSQL adds durable GameServer registration and compatible `SKIP LOCKED` claims with request-digest fencing; `server/agones` submits and validates namespaced `GameServerAllocation` responses and dynamic endpoints; `server/allocator` reconciles provider success into durable state before exposing the endpoint | `server/domain/allocator.go`, `server/store/allocator_sql.go`, `server/agones/allocation.go`, `server/allocator/service.go`, `server/migrations/0004_allocator_registry.sql` and tests cover deterministic compatible selection, exhaustion, conflicting/identical allocation replay, unknown allocations, SQL claim ordering, invalid input, provider error/malformed response/IPv6 endpoint handling, durable-reconciliation failure isolation and assignment replay/conflict; `TestPostgreSQLAllocatorClaimReplayAndCapacityFence` now covers live registration/selection/replay/conflict/no-capacity when the disposable database gate is run; signed roster metadata, bounded cross-replica retry and live integration remain |
| 8.31 `[D:8.9,8.30]` | **IN PROGRESS.** Pure Go assignment gate requires Allocated state, exact allocation ID/match/server/region/build/protocol/transport compatibility, non-empty hosted endpoint and verified manifest signature before exposure; allocator publication cannot expose Ready state | `server/domain/assignment.go` and `allocator.go` plus adversarial fixtures cover early-connect, tampered signature/manifest, wrong compatibility, empty endpoint, unknown allocation and post-publication mutation rejection; Agones metadata watch, hosted-address registration, production signer and client-ticket publication remain |
| 8.31 `[D:8.9,8.30]` | **IN PROGRESS.** Pure Go assignment gate requires Allocated state, exact allocation ID/match/server/region/build/protocol/transport compatibility, non-empty hosted endpoint and verified manifest signature before exposure; allocator publication cannot expose Ready state; durable roster persistence now verifies each canonical join-authorisation signature before publishing player rows | `server/domain/assignment.go`, `allocator.go`, `store/assignment_sql.go` plus adversarial fixtures cover early-connect, tampered signature/manifest, wrong compatibility, empty endpoint, unknown allocation, forged roster signature, valid signature and post-publication mutation rejection; Agones metadata watch, hosted-address registration, production signer and client-ticket publication remain |
| 8.32 `[D:8.2,8.26,8.30]` | **IN PROGRESS.** Provider-neutral FleetAutoscaler baseline preserves a two-process Ready buffer, caps warm capacity, and leaves Allocated scale-down independent of the Ready floor; Fleet image references remain digest-pinned for current/rollback pre-pull | `deploy/k8s/base/fleet-autoscaler.yaml` and manifest tests cover Fleet ownership, Buffer policy and floor/cap invariants; regional on-demand node pools/failure domains, pre-pull rollout, warm-allocation p95/p99 and N+1 certification remain |
| 8.33 `[D:8.26,8.32]` | **IN PROGRESS.** Fleet scheduling now requires on-demand capacity and spreads Ready processes across zones with skew 1; the autoscaler preserves the two-process Ready floor | `deploy/k8s/base/fleet.yaml` and manifest tests reject interruptible placement and single-zone concentration structurally; regional node pools, forced node-loss testing and measured N+1 headroom remain |
| 8.34 `[D:8.28,8.29]` | Native x86_64 benchmark of boot-to-process-ready and assignment-ready, p99 CPU/RSS/network and 60 Hz ticks; limits/node cap with 30% headroom | Measurements replace old estimates and certify density with no tick backlog |
+12 -4
View File
@@ -132,16 +132,16 @@ func SaveAssignments(ctx context.Context, db *sql.DB, assignments []DurableAssig
// SaveVerifiedAssignmentRoster converts the backend-verified signed roster to
// player-scoped rows. It rechecks the claims at this persistence boundary so a
// caller cannot accidentally publish a token for another match or slot.
func SaveVerifiedAssignmentRoster(ctx context.Context, db *sql.DB, assignment domain.Assignment, roster []domain.SignedJoinAuthorisation) error {
if assignment.Allocation.State != domain.ServerAllocated || len(roster) == 0 {
func SaveVerifiedAssignmentRoster(ctx context.Context, db *sql.DB, assignment domain.Assignment, roster []domain.SignedJoinAuthorisation, verify func([]byte, []byte) bool) error {
if assignment.Allocation.State != domain.ServerAllocated || len(roster) == 0 || verify == nil {
return fmt.Errorf("invalid verified assignment roster")
}
digest := domain.ManifestDigest(assignment.Manifest)
rows := make([]DurableAssignment, 0, len(roster))
for _, signed := range roster {
auth := signed.Authorisation
if len(signed.Signature) == 0 || auth.MatchID != assignment.Allocation.MatchID || auth.ServerID != assignment.Allocation.ServerID || auth.Protocol != strconv.Itoa(assignment.Allocation.Protocol) || auth.PlayerID == "" || auth.Slot < 0 || auth.Slot > 5 || auth.ExpiresAt.IsZero() {
return fmt.Errorf("invalid signed assignment roster")
if err := validateSignedRosterEntry(assignment, signed, verify); err != nil {
return err
}
envelope, err := json.Marshal(signed)
if err != nil {
@@ -159,6 +159,14 @@ func SaveVerifiedAssignmentRoster(ctx context.Context, db *sql.DB, assignment do
return SaveAssignments(ctx, db, rows)
}
func validateSignedRosterEntry(assignment domain.Assignment, signed domain.SignedJoinAuthorisation, verify func([]byte, []byte) bool) error {
auth := signed.Authorisation
if len(signed.Signature) == 0 || verify == nil || !verify(domain.JoinAuthorisationBytes(auth), signed.Signature) || auth.MatchID != assignment.Allocation.MatchID || auth.ServerID != assignment.Allocation.ServerID || auth.Protocol != strconv.Itoa(assignment.Allocation.Protocol) || auth.PlayerID == "" || auth.Slot < 0 || auth.Slot > 5 || auth.ExpiresAt.IsZero() {
return fmt.Errorf("invalid signed assignment roster")
}
return nil
}
func GetAssignment(ctx context.Context, db *sql.DB, playerID, matchID string, now time.Time) (DurableAssignment, error) {
if db == nil || playerID == "" || matchID == "" || now.IsZero() {
return DurableAssignment{}, fmt.Errorf("invalid assignment recovery arguments")
+16 -1
View File
@@ -39,7 +39,22 @@ func TestAssignmentStoreRejectsInvalidBatches(t *testing.T) {
if err := SaveAssignments(nil, nil, []DurableAssignment{{MatchID: "match-1", PlayerID: "player-1"}}); err == nil {
t.Fatal("invalid assignment batch accepted")
}
if err := SaveVerifiedAssignmentRoster(nil, nil, domain.Assignment{}, nil); err == nil {
if err := SaveVerifiedAssignmentRoster(nil, nil, domain.Assignment{}, nil, nil); err == nil {
t.Fatal("empty verified roster accepted")
}
}
func TestSignedRosterRequiresCryptographicVerification(t *testing.T) {
now := time.Unix(1000, 0)
assignment := domain.Assignment{Allocation: domain.Allocation{AllocationID: "allocation-1", MatchID: "match-1", ServerID: "server-1", Region: "EU", Build: "build-1", Protocol: 1, Transport: "enet", State: domain.ServerAllocated}, Manifest: domain.AllocationManifest{AllocationID: "allocation-1", MatchID: "match-1", ServerID: "server-1", Region: "EU", Build: "build-1", Protocol: 1, Transport: "enet", RosterDigest: "roster-1"}, Endpoint: "127.0.0.1:7777"}
auth := domain.JoinAuthorisation{MatchID: "match-1", ServerID: "server-1", PlayerID: "player-1", SteamID: "steam-1", Slot: 0, Team: 0, Protocol: "1", Generation: 1, ExpiresAt: now.Add(time.Minute)}
signed := domain.SignedJoinAuthorisation{Authorisation: auth, Signature: []byte("signature")}
if err := validateSignedRosterEntry(assignment, signed, func([]byte, []byte) bool { return false }); err == nil {
t.Fatal("forged signature accepted")
}
if err := validateSignedRosterEntry(assignment, signed, func(message, signature []byte) bool {
return string(message) == string(domain.JoinAuthorisationBytes(auth)) && string(signature) == "signature"
}); err != nil {
t.Fatalf("valid signature rejected: %v", err)
}
}