//go:build linux package host import ( "bytes" "context" "encoding/json" "github.com/carlosframework/platform/internal/instancectl" "net/http" "net/http/httptest" "os" "path/filepath" "testing" "github.com/carlosframework/platform/internal/cgroup" "github.com/carlosframework/platform/internal/hostbox" "github.com/carlosframework/platform/internal/hostguard" ) func TestPlan11Rev4JournalRefusesForeignContainment(t *testing.T) { oldRoot, oldInspect := claimContainmentAgentRoot, claimContainmentInspect t.Cleanup(func() { claimContainmentAgentRoot, claimContainmentInspect = oldRoot, oldInspect }) claimContainmentAgentRoot = func(context.Context) (string, error) { return "/sys/fs/cgroup/system.slice/carlos-edge.service", nil } claimContainmentInspect = func(p string) (hostbox.LaunchGroup, error) { return hostbox.LaunchGroup{RelativePath: p, Device: 1, Inode: 2}, nil } for _, op := range []string{"create", "prelaunch", "reserve"} { for _, path := range []string{"system.slice/ssh.service", "system.slice/carlos-edge.service/carlos-exec@other.example", "derived"} { t.Run(op+"/"+path, func(t *testing.T) { f := newRecoveryFixture(t) f.recordPrelaunch = false c := f.controller("boot-1", "controller-1", 4101, "start-1") admitted := c.admit(t, f) target := recoveryTuple(admitted, c.local) target.Op = admitted.Claim.Op.ID positive := path == "derived" && op != "reserve" if path == "derived" { path = filepath.Join("system.slice/carlos-edge.service", cgroup.ExecName(claimContainmentName(target))) } service, err := hostbox.NewJournalService(f.journal) if err != nil { t.Fatal(err) } root := ClaimRootHTTP{Journals: service} root.Reconcile.Box, root.Reconcile.Enrollment = target.Box, target.Enrollment root.Stop.Coordinator.Evidence = f.claims client, _ := hostbox.RemoteJournals(func(ctx context.Context, q hostbox.JournalRequest) (hostbox.JournalResponse, error) { raw, _ := json.Marshal(q) w := httptest.NewRecorder() root.serveJournal(w, httptest.NewRequest(http.MethodPost, "/claim/journal", bytes.NewReader(raw)), f.peer) if w.Code != http.StatusOK { return hostbox.JournalResponse{V: 1, ID: q.ID, Error: "refused"}, nil } var out hostbox.JournalResponse err := json.Unmarshal(w.Body.Bytes(), &out) return out, err }) in := hostbox.LaunchInventory{Target: target, ControllerPID: f.peer.PID, ProcessStart: f.peer.ProcessStart, NoState: true, Groups: []hostbox.LaunchGroup{{RelativePath: path, Device: 1, Inode: 2}}} switch op { case "create": err = client.Create(t.Context(), in) case "prelaunch": err = client.Prelaunch(t.Context(), in) case "reserve": if err = f.journal.Prelaunch(t.Context(), in); err != nil { t.Fatal(err) } err = client.Reserve(t.Context(), hostbox.LaunchReservation{ID: "x", Role: "main", InvocationID: "x", Inputs: "inputs", Target: target, Group: hostbox.LaunchGroup{RelativePath: path + "/role-x", Device: 1, Inode: 3, InvocationID: "x"}, Executable: hostbox.LaunchFile{Device: 1, Inode: 4}}) } if positive { if err != nil { t.Fatalf("valid root intake refused: %v", err) } return } if err == nil { t.Fatal("root accepted unrelated containment or parentless reservation") } }) } } } func TestPlan11Rev4RecoveryRefusesForgedPersistedGroups(t *testing.T) { for _, settled := range []bool{false, true} { t.Run(map[bool]string{false: "pending", true: "settled"}[settled], func(t *testing.T) { root, proc := t.TempDir(), t.TempDir() if err := os.MkdirAll(filepath.Join(proc, "sys/kernel/random"), 0700); err != nil { t.Fatal(err) } if err := os.WriteFile(filepath.Join(proc, "sys/kernel/random/boot_id"), []byte("new-boot"), 0600); err != nil { t.Fatal(err) } target := hostguard.FenceTarget{Host: "shop.example", Incarnation: "inc", Stamp: 1, Session: 1, Box: "box", Enrollment: "enroll", BootID: "old-boot", ControllerID: "controller", FenceID: "fence"} j := &rebootJournalFixture{j: hostbox.StopKernelJournal{V: 1, Target: target, ControllerPID: 42, ProcessStart: "42", Settled: settled, Cgroups: []hostbox.StopCgroupIdentity{{RelativePath: "system.slice/ssh.service", Device: 1, Inode: 2}}}} k := LinuxStopKernel{AgentCgroup: func(context.Context) (string, error) { return "/sys/fs/cgroup/system.slice/carlos-edge.service", nil }, Journal: j, CgroupRoot: root, ProcRoot: proc, ManagedRoots: map[string]string{"data": t.TempDir()}} _, _, err := k.recoverAfterReboot(t.Context(), target, StopInventory{Complete: true}, j.j, "new-boot", j) if err == nil { t.Fatal("recovery accepted unrelated persisted containment") } }) } } func TestPlan11Rev4ContainmentCapturesOnlyDerivedParent(t *testing.T) { target := hostguard.FenceTarget{Host: "shop.example", Incarnation: "inc", Stamp: 1, Session: 1, Box: "box", Enrollment: "enroll", BootID: "boot", ControllerID: "controller"} parentPath, err := claimContainmentParent("/sys/fs/cgroup/system.slice/carlos-edge.service", target) if err != nil { t.Fatal(err) } parent := hostbox.LaunchGroup{RelativePath: parentPath, Device: 1, Inode: 2} child := hostbox.LaunchGroup{RelativePath: parentPath + "/role-one", Device: 1, Inode: 3, InvocationID: "one"} oldRoot, oldInspect := claimContainmentAgentRoot, claimContainmentInspect t.Cleanup(func() { claimContainmentAgentRoot, claimContainmentInspect = oldRoot, oldInspect }) claimContainmentAgentRoot = func(context.Context) (string, error) { return "/sys/fs/cgroup/system.slice/carlos-edge.service", nil } claimContainmentInspect = func(p string) (hostbox.LaunchGroup, error) { if p == parent.RelativePath { return parent, nil } if p == child.RelativePath { g := child g.InvocationID = "" return g, nil } t.Fatalf("root tried to capture foreign containment: %s", p) return hostbox.LaunchGroup{}, nil } j, err := hostbox.OpenLaunchJournal(filepath.Join(t.TempDir(), "launch.db")) if err != nil { t.Fatal(err) } defer j.Close() in := hostbox.LaunchInventory{Target: target, ControllerPID: 42, ProcessStart: "42", NoState: true, Groups: []hostbox.LaunchGroup{parent}} for _, op := range []string{"create", "prelaunch"} { if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: op, Launch: in}, j); err != nil { t.Fatal(err) } for _, foreign := range []string{"system.slice/ssh.service", "system.slice/carlos-edge.service/carlos-exec@other.example"} { forged := in forged.Groups = []hostbox.LaunchGroup{{RelativePath: foreign, Device: 1, Inode: 2}} if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: op, Launch: forged}, j); err == nil { t.Fatal("foreign containment accepted with a valid capture provider") } } forged := in forged.Groups = append([]hostbox.LaunchGroup{}, in.Groups...) forged.Groups[0].Inode++ if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: op, Launch: forged}, j); err == nil { t.Fatal("forged kernel identity accepted") } } if err := j.Prelaunch(t.Context(), in); err != nil { t.Fatal(err) } r := hostbox.LaunchReservation{ID: "one", Role: "main", InvocationID: "one", Inputs: "inputs", Target: target, Parent: parent, Group: child, Executable: hostbox.LaunchFile{Device: 1, Inode: 4}} intended := r intended.Group.Device = 0 intended.Group.Inode = 0 if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: "intend", Reservation: intended}, j); err != nil { t.Fatal(err) } if err := j.IntendRole(t.Context(), intended); err != nil { t.Fatal(err) } if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: "reserve", Reservation: r}, j); err != nil { t.Fatal(err) } parentless := r parentless.Parent = hostbox.LaunchGroup{} if err := validateClaimJournalContainment(t.Context(), hostbox.JournalRequest{Op: "reserve", Reservation: parentless}, j); err == nil { t.Fatal("parentless reservation accepted") } if err := j.Reserve(t.Context(), r); err != nil { t.Fatal(err) } in, err = j.Read(t.Context(), target) if err != nil { t.Fatal(err) } in.Reservations = append(in.Reservations, hostbox.LaunchReservation{Target: target, State: hostbox.UnitIntended, Group: hostbox.LaunchGroup{RelativePath: instancectl.ClaimUnitControlGroup(target.Host)}}) if err := validateClaimContainment(in, parentPath); err != nil { t.Fatal("root's exact isolated unit rejected", err) } } type containmentCountingUnits struct { *launchUnits calls int } func (u *containmentCountingUnits) Gone(ctx context.Context, host, inv string) error { u.calls++ return u.launchUnits.Gone(ctx, host, inv) } func TestPlan11Rev4RecoveryValidatesWholeInventoryBeforeEffects(t *testing.T) { for _, kind := range []string{"unrelated-parent", "foreign-unit", "settled-foreign-unit", "parentless-role"} { t.Run(kind, func(t *testing.T) { f := newLaunchFixture(t, servingOp()) in, err := f.journal.Read(t.Context(), f.target) if err != nil { t.Fatal(err) } if kind == "unrelated-parent" { in.Groups[0].RelativePath = "system.slice/ssh.service" } j, err := hostbox.OpenLaunchJournal(filepath.Join(t.TempDir(), "forged.db")) if err != nil { t.Fatal(err) } defer j.Close() if err = j.Create(t.Context(), in); err != nil { t.Fatal(err) } r := *f.req.Reservation if kind == "foreign-unit" || kind == "settled-foreign-unit" { r.Group.RelativePath = instancectl.ClaimUnitControlGroup("other.example") } if err = j.IntendUnit(t.Context(), r); err != nil { t.Fatal(err) } if kind == "settled-foreign-unit" { if err = j.SettleUnit(t.Context(), f.target, r.ID); err != nil { t.Fatal(err) } } if kind == "parentless-role" { role := hostbox.LaunchReservation{ID: "role", Role: "writer", InvocationID: "role", Inputs: "inputs", Target: f.target, Group: hostbox.LaunchGroup{RelativePath: in.Groups[0].RelativePath + "/role-x", Device: 1, Inode: 7, InvocationID: "role"}, Executable: hostbox.LaunchFile{Device: 1, Inode: 8}} if err = j.Reserve(t.Context(), role); err != nil { t.Fatal(err) } } units := &containmentCountingUnits{launchUnits: f.units} innerCalls := 0 k := claimUnitStopKernel{Journal: j, Units: units, Inner: recoveryKernelFunc(func(context.Context, hostguard.FenceTarget, StopInventory) (StopKernelEvidence, DrainAcknowledgement, error) { innerCalls++ return StopKernelEvidence{}, DrainAcknowledgement{}, nil })} if _, _, err = k.RecoverStopped(t.Context(), f.target, StopInventory{}); err == nil { t.Fatal("forged persisted inventory accepted") } if units.calls != 0 || innerCalls != 0 { t.Fatalf("privileged recovery reached before validation: Gone=%d inner=%d", units.calls, innerCalls) } }) } } func TestPlan11Rev4LaunchAndStopRefuseForgedContainmentBeforeEffects(t *testing.T) { for _, op := range []string{hostbox.RoleLaunchStart, hostbox.RoleLaunchStop} { t.Run(op, func(t *testing.T) { f := newLaunchFixture(t, servingOp()) in, err := f.journal.Read(t.Context(), f.target) if err != nil { t.Fatal(err) } in.Groups[0].RelativePath = "system.slice/ssh.service" j, err := hostbox.OpenLaunchJournal(filepath.Join(t.TempDir(), "forged.db")) if err != nil { t.Fatal(err) } defer j.Close() if err = j.Create(t.Context(), in); err != nil { t.Fatal(err) } f.root.Journal = j units := &containmentCountingUnits{launchUnits: f.units} // The reserved-launch extension is supplied by the original fixture. f.root.Units = units q := f.req if op == hostbox.RoleLaunchStop { q = hostbox.RoleLaunchRequest{V: hostbox.RoleLaunchV, Op: op, Reservation: f.req.Reservation} } if _, err = f.root.Serve(t.Context(), f.peer, q); err == nil { t.Fatal("forged launch inventory accepted") } starts, stops := f.units.counts() if starts != 0 || stops != 0 || units.calls != 0 { t.Fatalf("privileged actions before validation: starts=%d stops=%d gone=%d", starts, stops, units.calls) } }) } } func TestPlan11Rev4StopCannotTombstoneForeignUnit(t *testing.T) { f := newLaunchFixture(t, servingOp()) units := &containmentCountingUnits{launchUnits: f.units} f.root.Units = units r := *f.req.Reservation r.ID = "foreign-stop" r.Group.RelativePath = instancectl.ClaimUnitControlGroup("other.example") if _, err := f.root.Serve(t.Context(), f.peer, hostbox.RoleLaunchRequest{V: hostbox.RoleLaunchV, Op: hostbox.RoleLaunchStop, Reservation: &r}); err == nil { t.Fatal("foreign stop request accepted") } in, err := f.journal.Read(t.Context(), f.target) if err != nil { t.Fatal(err) } starts, stops := f.units.counts() if len(in.Reservations) != 0 || starts != 0 || stops != 0 || units.calls != 0 { t.Fatalf("foreign stop changed state: reservations=%d starts=%d stops=%d gone=%d", len(in.Reservations), starts, stops, units.calls) } }