mirror of
https://github.com/jcreek/CosmicClash.git
synced 2026-09-11 08:23:45 +00:00
520613aab0
WorkloadVerify (api.Service.WorkloadVerify) was permanently unwired: both
/v1/servers/{id}/register and /v1/servers/{id}/result always 503, because
the only design considered so far was verifying a Kubernetes-projected
service-account JWT (server/workload/jwt.go), which needs a live cluster's
TokenReview/JWKS endpoint to validate against safely -- something this
sandbox cannot do without guessing at a trust boundary.
The API layer doesn't actually require that specific mechanism. serverMutation
only compares WorkloadBinding.ServerID and .MatchID (server/api/service.go);
AdvanceServerRegistration only uses .MatchID/.ServerID/.AllocationID. Nothing
downstream needs Namespace/ServiceAcct/PodUID/GameServerUID populated.
This adds a self-contained alternative: a short-lived, HMAC-signed token the
control plane mints and verifies with a secret only it holds (server/workload/
signed_token.go), the same trust model domain.SessionStore already uses for
player sessions elsewhere in this codebase. It needs no cluster to verify --
signature + expiry is fully self-contained and unit-testable.
The design's soundness rests on the delivery channel, not the crypto: the
token is meant to reach the allocated GameServer via the same Agones
GameServerAllocation annotation channel allocation.go already uses for
match-id/allocation-id, readable only by that pod's own local SDK sidecar. A
caller presenting this token has already proven, via that channel, that it is
the pod Agones allocated. (Wiring the actual annotation delivery -- extending
agones.Client.Allocate and the supervisor's token source -- is a separate,
follow-up change; this commit lands the verification core it depends on.)
store.AllocationBindingStillValid adds defense-in-depth on top of signature
and expiry: it cross-checks the token's claims against the durable
allocations table (append-only, never leaves 'ALLOCATED'), so a validly-signed
token naming an allocation that was never recorded -- or a real allocation id
paired with a mismatched match/server -- is still rejected.
api.WorkloadVerifierFromSignedToken wires the two together and is now plugged
into cmd/control-plane (new --workload-secret / COSMIC_CLASH_WORKLOAD_SECRET
flag; a startup warning is logged if it's left unset, since the route then
stays 503 exactly as before) and cmd/testkit-api (fixed test secret, since
that binary is test-only already).
Verified: new unit tests in server/workload (signature tamper, wrong secret,
expiry boundary, malformed input) and a new Postgres integration suite in
server/api (real allocation row, real signed token, acceptance / unknown-
allocation rejection / mismatched-triple rejection / the previously-503
Service.WorkloadVerify field itself) -- both run clean with -race across
multiple passes against a live postgres:17-alpine container. Full
`go build ./... && go vet ./... && gofmt -l . && go test ./... -race` and
`go test -tags integration ./... -race` both clean.
127 lines
4.8 KiB
Go
127 lines
4.8 KiB
Go
package workload
|
|
|
|
import (
|
|
"crypto/hmac"
|
|
"crypto/sha256"
|
|
"crypto/subtle"
|
|
"encoding/base64"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"time"
|
|
)
|
|
|
|
// SignedWorkloadToken is a control-plane-issued bearer credential for the
|
|
// WorkloadVerify boundary (see multiplayer-next.md 8.10). It exists because
|
|
// the obvious approach -- verifying a Kubernetes-projected service-account
|
|
// JWT via TokenReview/JWKS (see jwt.go, ParseAndValidate) -- needs a live
|
|
// cluster to validate against and so cannot be built or tested here.
|
|
//
|
|
// This sidesteps that requirement entirely: the control plane signs its own
|
|
// short-lived token over (allocation_id, match_id, server_id, expiry) with a
|
|
// secret only it holds, exactly the way domain.SessionStore already mints
|
|
// player session tokens elsewhere in this codebase. It needs no Kubernetes
|
|
// trust boundary to verify -- HMAC signature plus expiry is self-contained.
|
|
//
|
|
// The delivery channel is what makes this safe despite not proving pod
|
|
// identity the way a Kubernetes-issued token would: the token is meant to be
|
|
// handed to the allocated GameServer via the same Agones GameServerAllocation
|
|
// annotation channel allocation.go already uses for match-id/allocation-id
|
|
// (see agones/allocation.go), which only the actually-allocated pod's local
|
|
// SDK sidecar can read. A caller who can present this token has already
|
|
// proven, via that channel, that it is the pod Agones allocated.
|
|
type SignedWorkloadToken struct {
|
|
AllocationID string `json:"a"`
|
|
MatchID string `json:"m"`
|
|
ServerID string `json:"s"`
|
|
ExpiresAt time.Time `json:"e"`
|
|
}
|
|
|
|
var (
|
|
ErrEmptyWorkloadSecret = errors.New("workload token signing secret is empty")
|
|
ErrMalformedToken = errors.New("malformed signed workload token")
|
|
ErrTokenSignature = errors.New("signed workload token signature mismatch")
|
|
ErrTokenExpired = errors.New("signed workload token expired")
|
|
ErrTokenClaims = errors.New("signed workload token missing required claims")
|
|
)
|
|
|
|
// IssueSignedWorkloadToken produces a compact "payload.signature" token
|
|
// binding the three identifiers the API layer actually checks (see
|
|
// api.Service's WorkloadVerify call site: it only compares ServerID and
|
|
// MatchID on the returned domain.WorkloadBinding). now must be non-zero and
|
|
// ttl must be positive so a token is never silently issued already-expired.
|
|
func IssueSignedWorkloadToken(secret []byte, allocationID, matchID, serverID string, now time.Time, ttl time.Duration) (string, error) {
|
|
if len(secret) == 0 {
|
|
return "", ErrEmptyWorkloadSecret
|
|
}
|
|
if allocationID == "" || matchID == "" || serverID == "" {
|
|
return "", ErrTokenClaims
|
|
}
|
|
if now.IsZero() || ttl <= 0 {
|
|
return "", fmt.Errorf("issue signed workload token: now and ttl must be valid")
|
|
}
|
|
claims := SignedWorkloadToken{
|
|
AllocationID: allocationID,
|
|
MatchID: matchID,
|
|
ServerID: serverID,
|
|
ExpiresAt: now.Add(ttl).UTC(),
|
|
}
|
|
payload, err := json.Marshal(claims)
|
|
if err != nil {
|
|
return "", fmt.Errorf("marshal signed workload token: %w", err)
|
|
}
|
|
payloadEnc := base64.RawURLEncoding.EncodeToString(payload)
|
|
mac := hmac.New(sha256.New, secret)
|
|
mac.Write([]byte(payloadEnc))
|
|
sigEnc := base64.RawURLEncoding.EncodeToString(mac.Sum(nil))
|
|
return payloadEnc + "." + sigEnc, nil
|
|
}
|
|
|
|
// ParseSignedWorkloadToken verifies the signature in constant time, checks
|
|
// expiry against now, and returns the claims. It never trusts the payload
|
|
// before the signature is verified.
|
|
func ParseSignedWorkloadToken(secret []byte, token string, now time.Time) (SignedWorkloadToken, error) {
|
|
if len(secret) == 0 {
|
|
return SignedWorkloadToken{}, ErrEmptyWorkloadSecret
|
|
}
|
|
dot := -1
|
|
for i := 0; i < len(token); i++ {
|
|
if token[i] == '.' {
|
|
dot = i
|
|
break
|
|
}
|
|
}
|
|
if dot <= 0 || dot == len(token)-1 {
|
|
return SignedWorkloadToken{}, ErrMalformedToken
|
|
}
|
|
payloadEnc, sigEnc := token[:dot], token[dot+1:]
|
|
mac := hmac.New(sha256.New, secret)
|
|
mac.Write([]byte(payloadEnc))
|
|
expectedSig := mac.Sum(nil)
|
|
gotSig, err := base64.RawURLEncoding.DecodeString(sigEnc)
|
|
if err != nil {
|
|
return SignedWorkloadToken{}, ErrMalformedToken
|
|
}
|
|
if subtle.ConstantTimeCompare(expectedSig, gotSig) != 1 {
|
|
return SignedWorkloadToken{}, ErrTokenSignature
|
|
}
|
|
payload, err := base64.RawURLEncoding.DecodeString(payloadEnc)
|
|
if err != nil {
|
|
return SignedWorkloadToken{}, ErrMalformedToken
|
|
}
|
|
var claims SignedWorkloadToken
|
|
if err := json.Unmarshal(payload, &claims); err != nil {
|
|
return SignedWorkloadToken{}, ErrMalformedToken
|
|
}
|
|
if claims.AllocationID == "" || claims.MatchID == "" || claims.ServerID == "" || claims.ExpiresAt.IsZero() {
|
|
return SignedWorkloadToken{}, ErrTokenClaims
|
|
}
|
|
if now.IsZero() {
|
|
return SignedWorkloadToken{}, fmt.Errorf("parse signed workload token: now must be valid")
|
|
}
|
|
if !now.Before(claims.ExpiresAt) {
|
|
return SignedWorkloadToken{}, ErrTokenExpired
|
|
}
|
|
return claims, nil
|
|
}
|