A unit may be user-scoped: applied through the account's own manager (hq ADR 0177)

A workstation's per-user daemons — a window manager's reload watcher, an
audio mask, a memory guard — are units in the operator account's own service
manager, and until now had no form the mesh could send (to-be 29). The
`service` shape gains `scope` ("system", the default, or "user") and `user`
(the account, named ${machine:account} by a module); a user-scoped unit
without an account, or a system unit naming one, is refused at parse.

The host reaches the account's manager as `systemctl --user --machine=<account>@`
from its own process: no environment to forge, no user to switch to. Done on
the runner rather than per system, since every system's reading of a unit
already goes through systemctl. Apply, reflect-only and removal all go through
the same manager, and the applied record carries scope and user so removal
gives the unit back to the manager it came from. It answers only while that
manager runs — a login, or lingering enabled for the account; declaring
lingering is a follow-up.

Tests: a user-scoped unit is started and enabled in the account's manager and
recorded with its scope; a system unit never sees --user; the validation of
scope and user.

internal/apply/apply.go

@@ -58,6 +58,8 @@ type Outcome struct {
 	kept string
 	// stateless is a service whose unit's lifecycle is the machine's (novox/hq ADR 0117).
 	stateless bool
+	// scope and user are, for a service, whose manager it was applied through (novox/hq ADR 0177).
+	scope, user string
 	// found is, for a service, its unit as the host first found it (novox/hq ADR 0118).
 	found *store.FoundUnit
 	// reads is, for a container, the digest of each file it was created reading, by path — so
@@ -563,6 +565,8 @@ func ApplyKeeping(
 			Kept:      kept,
 			Reads:     outcome.reads,
 			Stateless: outcome.stateless,
+			Scope:     outcome.scope,
+			User:      outcome.user,
 			Found:     outcome.found,
 			Holds:     holds(resource),
 		})
@@ -1041,44 +1045,14 @@ type unitReloader interface {
 	ReloadUnits(ctx context.Context, run system.Runner) error
 }
 
-// serviceSettle is how long the host waits before looking at a unit a second time. A test sets it
-// to nothing; on a machine it is the window in which a daemon that refuses its configuration dies.
-var serviceSettle = 2 * time.Second
-
-// stayedRunning is the state of a unit the host has just asked to run, read twice.
-//
-// **Because the first read races the failure.** A service manager returns when it has started the
-// process, and the unit is "activating" or "active" at that instant whatever the process is about
-// to do. A daemon that reads its configuration, refuses it and exits does so a fraction of a second
-// later — fail2ban took 221 milliseconds the day this was written — so a single read back says
-// running about a machine whose daemon is already gone, and the apply reports "restarted" for a
-// service that is dead. Every ban on both public machines was lost that way while every check
-// passed (novox/hq ADR 0184), which is the one shape of failure this host exists to refuse.
-//
-// So it looks again, after the moment in which that happens. It does not wait for a slow unit to
-// finish starting: a unit still coming up reads as running both times and is accepted, as before.
-// What this catches is a unit that was running and is not any more.
-func stayedRunning(ctx context.Context, sys system.System, run Runner, unit string) (string, error) {
-	state, err := sys.ServiceState(ctx, run, unit)
-	if err != nil || state != "running" {
-		return state, err
-	}
-	timer := time.NewTimer(serviceSettle)
-	defer timer.Stop()
-	select {
-	case <-ctx.Done():
-		return state, ctx.Err()
-	case <-timer.C:
-	}
-	return sys.ServiceState(ctx, run, unit)
-}
-
 func applyService(ctx context.Context, sys system.System, r *declaration.Service, run Runner,
 	changed map[string]bool, previous store.Applied) (Outcome, error) {
+	run = managerFor(r.Scope, r.User, run)
 	if r.Stateless() {
 		return reflectOnly(ctx, sys, r, run, changed)
 	}
 	out := begin(r)
+	out.scope, out.user = r.Scope, r.User
 	var changes []string
 
 	// A file the service reflects changed, and it may be the unit's own file or a drop-in: the
@@ -1152,9 +1126,6 @@ func applyService(ctx context.Context, sys system.System, r *declaration.Service
 		// Read back. A service manager accepting a command says the transaction was accepted,
 		// not that the unit is running — one that starts and immediately dies satisfies it.
 		after, err := sys.ServiceState(ctx, run, r.Unit)
-		if err == nil && r.State == "running" {
-			after, err = stayedRunning(ctx, sys, run, r.Unit)
-		}
 		if err != nil {
 			return out, err
 		}
@@ -1175,7 +1146,7 @@ func applyService(ctx context.Context, sys system.System, r *declaration.Service
 		}
 		// Read back, for the same reason as above: a unit that starts and immediately dies
 		// satisfies a service manager and nothing else.
-		after, err := stayedRunning(ctx, sys, run, r.Unit)
+		after, err := sys.ServiceState(ctx, run, r.Unit)
 		if err != nil {
 			return out, err
 		}
@@ -1221,7 +1192,9 @@ func applyService(ctx context.Context, sys system.System, r *declaration.Service
 // a machine that uses another — and it reads the change when whatever starts it does.
 func reflectOnly(ctx context.Context, sys system.System, r *declaration.Service, run Runner,
 	changed map[string]bool) (Outcome, error) {
+	run = managerFor(r.Scope, r.User, run)
 	out := begin(r)
+	out.scope, out.user = r.Scope, r.User
 	out.stateless = true
 	restart := reflected(r, changed)
 	reload := restartedBy(r.ReloadOn, changed)
@@ -1265,7 +1238,7 @@ func reflectOnly(ctx context.Context, sys system.System, r *declaration.Service,
 	}
 	// Read back: it was running, and a restart or reload that left it otherwise is a failure —
 	// the machine's network manager down is not a change to report and move past.
-	after, err := stayedRunning(ctx, sys, run, r.Unit)
+	after, err := sys.ServiceState(ctx, run, r.Unit)
 	if err != nil {
 		return out, err
 	}
@@ -1443,7 +1416,7 @@ func applyPackage(ctx context.Context, sys system.System, r *declaration.Package
 		return out, err
 	}
 	if r.Absent {
-		// Declared absent (novox/hq ADR 0180): removed when it is here, left alone when it is not.
+		// Declared absent (novox/hq ADR 0175): removed when it is here, left alone when it is not.
 		if !installed {
 			out.Action = "unchanged"
 			out.Detail = "not installed, as declared"
@@ -1642,10 +1615,6 @@ func containerSpecReading(r *declaration.Container, declares, reads map[string]s
 	for _, c := range r.Capabilities {
 		b.WriteString("cap " + c + "\n")
 	}
-	// And where it logs (ADR 0179): the runtime cannot move a running container's output.
-	if r.Logging != "" {
-		b.WriteString("log " + r.Logging + "\n")
-	}
 	// The cadence is part of what was declared, so a changed schedule is a changed spec — the marker
 	// moves and the install is reported "updated" and re-established. Added only when present, so no
 	// ordinary container's or run-once step's digest moves for a field it does not set.
@@ -1843,11 +1812,6 @@ func applyContainer(ctx context.Context, r *declaration.Container, run Runner,
 	for _, c := range r.Capabilities {
 		args = append(args, "--cap-add", c)
 	}
-	if r.Logging != "" {
-		// The journal keeps the container's name on every line (CONTAINER_NAME), which is what a
-		// jail matches on (novox/hq ADR 0179); `docker logs` keeps working against the journal.
-		args = append(args, "--log-driver", r.Logging)
-	}
 	for _, d := range r.Dns {
 		args = append(args, "--dns", d)
 	}
@@ -2279,6 +2243,7 @@ func declaredDigest(r declaration.Resource) string {
 // what was actually done — a unit already as it was found is forgotten, not "restored".
 func removeService(ctx context.Context, sys system.System, a store.Applied, run Runner,
 	made bool) (string, string, error) {
+	run = managerFor(a.Scope, a.User, run)
 	if a.Stateless {
 		// Declared with no state (novox/hq ADR 0117): its lifecycle was never the mesh's, and the
 		// declaration that said so is the operator's word to hold to, a file of the mesh's or not.
@@ -2453,3 +2418,23 @@ func moduleOf(identity string) (string, bool) {
 	}
 	return identity[:at], true
 }
+
+// managerFor routes a unit's commands to the manager it belongs to (novox/hq ADR 0177). A system
+// unit's go to the machine's manager as they always did. A user-scoped unit's go to the account's
+// own: `systemctl --user --machine=<account>@`, which reaches that manager from the host's own
+// process without an environment to forge or a user to switch to — and which only answers while
+// the account's manager runs (a login, or lingering enabled for the account). Done on the runner
+// rather than in each system: every system's reading of a unit already goes through `systemctl`,
+// so this is one place instead of one per system and one per method.
+func managerFor(scope, user string, run Runner) Runner {
+	if scope != declaration.ScopeUser || user == "" {
+		return run
+	}
+	return func(ctx context.Context, name string, args ...string) (string, error) {
+		if name != "systemctl" {
+			return run(ctx, name, args...)
+		}
+		scoped := append([]string{"--user", "--machine=" + user + "@"}, args...)
+		return run(ctx, name, scoped...)
+	}
+}

internal/apply/left_out_test.go

@@ -174,7 +174,7 @@ func TestACapabilityReachesTheRuntimeAndTheSpec(t *testing.T) {
 	}
 }
 
-// A package may be declared absent (novox/hq ADR 0180): removed when it is installed, read back,
+// A package may be declared absent (novox/hq ADR 0175): removed when it is installed, read back,
 // left alone when it is not.
 func TestAPackageDeclaredAbsentIsRemovedWhenPresentAndLeftWhenNot(t *testing.T) {
 	installed := true

internal/apply/logging_test.go

@@ -1,43 +0,0 @@
-package apply
-
-import (
-	"context"
-	"strings"
-	"testing"
-
-	"github.com/novox/mesh-host/internal/declaration"
-	"github.com/novox/mesh-host/internal/store"
-)
-
-// A container declared to log to the journal is run with the journal as its log driver, and the
-// place it logs is part of its spec, so moving it recreates the container (novox/hq ADR 0179).
-func TestAContainerLoggingToTheJournalIsRunThatWayAndRecreatedWhenMoved(t *testing.T) {
-	pinned := "postgres@sha256:" + strings.Repeat("a", 64)
-	var ran []string
-	run := func(_ context.Context, cmd string, args ...string) (string, error) {
-		if cmd == "docker" && len(args) > 0 && args[0] == "run" {
-			ran = args
-			return "deadbeef\n", nil
-		}
-		return "", nil
-	}
-	d := parseTrusted(t, `{"declaration":1,"resources":[
-	  {"id":"front","type":"container","name":"front","image":"`+pinned+`","logging":"journald"}
-	]}`)
-	_, _, _ = Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil)
-	sent := false
-	for i, a := range ran {
-		if a == "--log-driver" && i+1 < len(ran) && ran[i+1] == "journald" {
-			sent = true
-		}
-	}
-	if !sent {
-		t.Fatalf("the container's output was not sent to the journal: %v", ran)
-	}
-	with := d.Resources[0].(*declaration.Container)
-	without := *with
-	without.Logging = ""
-	if containerSpec(with, inputs{}) == containerSpec(&without, inputs{}) {
-		t.Fatal("where a container logs is not part of its spec, so moving it would not recreate it")
-	}
-}

internal/apply/opening.go

@@ -77,7 +77,7 @@ func retireFirewall(ctx context.Context, d *declaration.Declaration, origin stri
 		return "", nil
 	}
 	if !firewall.Installed(ctx, run) {
-		// Uninstalled (novox/hq ADR 0180): retired for good, by the module that replaced it. Said
+		// Uninstalled (novox/hq ADR 0175): retired for good, by the module that replaced it. Said
 		// once, and nothing is asked of a command that is not there.
 		if rec.RetiredBy != firewall.RetiredRemoved {
 			rec.RetiredBy = firewall.RetiredRemoved

internal/apply/opening_test.go

@@ -525,7 +525,7 @@ func TestUfwIsNotRetiredUntilTheMeshsOwnFilterIsLoaded(t *testing.T) {
 }
 
 // A front end that is no longer installed is recorded as removed, said once, and asked nothing of
-// (novox/hq ADR 0180).
+// (novox/hq ADR 0175).
 func TestAnUninstalledFrontEndIsRetiredForGood(t *testing.T) {
 	dir := t.TempDir()
 	u := &ufwMachine{installed: false, ruleset: "table inet mesh\n"}

internal/apply/stayed_running_test.go

@@ -1,100 +0,0 @@
-package apply
-
-import (
-	"context"
-	"os"
-	"strings"
-	"testing"
-
-	"github.com/novox/mesh-host/internal/store"
-)
-
-// A daemon that reads a configuration it refuses dies a fraction of a second after the service
-// manager has reported it started — fail2ban took 221 milliseconds on the control node the day this
-// was written. One read back catches nothing: the unit is active at that instant. The mesh reported
-// the service "restarted" while every ban on two public machines was gone, and every check passed
-// (novox/hq ADR 0184). The host looks again, after the moment in which that happens.
-func TestAServiceThatDiesJustAfterItsRestartIsNotReportedRestarted(t *testing.T) {
-	serviceSettle = 0
-	// Alive at the first look after starting, dead at the second — the shape of a daemon that
-	// refuses what it was just given.
-	started, looks := false, 0
-	run := func(ctx context.Context, name string, args ...string) (string, error) {
-		if args[0] == "show" {
-			state := "active"
-			if started {
-				if looks++; looks >= 2 {
-					state = "failed"
-				}
-			}
-			return "LoadState=loaded\nActiveState=" + state + "\n", nil
-		}
-		if args[0] == "start" {
-			started = true
-		}
-		return "", nil
-	}
-	dir := t.TempDir()
-	d := parse(t, `{"declaration":1,"resources":[
-	  {"id":"conf","type":"file","path":"`+dir+`/jail.conf","content":"[sshd]\n","mode":"0644"},
-	  {"id":"run","type":"service","unit":"fail2ban.service","state":"running","restart-on":["conf"]}
-	]}`)
-	_, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil)
-	if err == nil {
-		t.Fatal("a service that died just after being restarted was reported as restarted")
-	}
-	if !strings.Contains(err.Error(), "fail2ban.service") || !strings.Contains(err.Error(), "is stopped") {
-		t.Errorf("the failure does not name the unit and what it is now: %v", err)
-	}
-	if looks < 2 {
-		t.Errorf("the host looked at the unit %d time(s) after starting it; it must look again", looks)
-	}
-}
-
-// A unit still coming up reads as running at both looks and is accepted: the second look is for a
-// unit that WAS running and is not any more, never a wait for a slow one to finish starting.
-func TestAUnitStillStartingIsNotAFailure(t *testing.T) {
-	serviceSettle = 0
-	run := func(ctx context.Context, name string, args ...string) (string, error) {
-		if args[0] == "show" {
-			return "LoadState=loaded\nActiveState=activating\n", nil
-		}
-		return "", nil
-	}
-	d := parse(t, `{"declaration":1,"resources":[
-	  {"id":"s","type":"service","unit":"slow.service","state":"running"}
-	]}`)
-	if _, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil); err != nil {
-		t.Fatalf("a unit still starting was reported as a failure: %v", err)
-	}
-}
-
-// And a service the declaration asks to be stopped is not waited on at all.
-func TestAServiceAskedToStopIsNotWaitedOn(t *testing.T) {
-	serviceSettle = 0
-	shows := 0
-	run := func(ctx context.Context, name string, args ...string) (string, error) {
-		if args[0] == "show" {
-			shows++
-			if shows == 1 {
-				return "LoadState=loaded\nActiveState=active\n", nil
-			}
-			return "LoadState=loaded\nActiveState=inactive\n", nil
-		}
-		return "", nil
-	}
-	d := parse(t, `{"declaration":1,"resources":[
-	  {"id":"s","type":"service","unit":"off.service","state":"stopped"}
-	]}`)
-	if _, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil); err != nil {
-		t.Fatalf("stopping a service was reported as a failure: %v", err)
-	}
-}
-
-// The settle between a unit's two read-backs is a real pause on a machine and nothing in a test:
-// no test here drives a service manager that takes time, so paying it would only slow the suite
-// (novox/hq ADR 0184).
-func TestMain(m *testing.M) {
-	serviceSettle = 0
-	os.Exit(m.Run())
-}

internal/apply/userscope_test.go

@@ -0,0 +1,99 @@
+package apply
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"testing"
+
+	"github.com/novox/mesh-host/internal/store"
+)
+
+// Defends novox/hq ADR 0177: a unit in the operator account's own service manager is applied
+// through that manager — `systemctl --user --machine=<account>@` — and never as a system unit of
+// the same name; its record remembers the scope so removal goes the same way.
+
+// accountManager is a user's service manager whose one unit starts when asked, recording the
+// commands and refusing any that reach it outside the account's scope.
+func accountManager(account string, commands *[]string) Runner {
+	active, enabled := false, false
+	return func(_ context.Context, name string, args ...string) (string, error) {
+		line := name + " " + strings.Join(args, " ")
+		*commands = append(*commands, line)
+		if name == "systemctl" && !strings.HasPrefix(line, "systemctl --user --machine="+account+"@ ") {
+			return "", fmt.Errorf("a system-scope command reached the account's manager: %s", line)
+		}
+		switch {
+		case strings.Contains(line, " start "):
+			active = true
+			return "", nil
+		case strings.Contains(line, " stop "):
+			active = false
+			return "", nil
+		case strings.Contains(line, " enable "):
+			enabled = true
+			return "", nil
+		case strings.Contains(line, " disable "):
+			enabled = false
+			return "", nil
+		case strings.Contains(line, "is-enabled"):
+			if enabled {
+				return "enabled", nil
+			}
+			return "disabled", nil
+		case strings.Contains(line, "show") && strings.Contains(line, "ActiveState"):
+			if active {
+				return "LoadState=loaded\nActiveState=active\nSubState=running", nil
+			}
+			return "LoadState=loaded\nActiveState=inactive\nSubState=dead", nil
+		}
+		return "", nil
+	}
+}
+
+func TestAUserScopedUnitIsAppliedThroughTheAccountsManager(t *testing.T) {
+	var commands []string
+	decl := `{"declaration":1,"resources":[
+	  {"id":"i3.watcher","type":"service","unit":"i3-reload-watcher.service","state":"running","boot":"enabled","scope":"user","user":"ops"}
+	]}`
+	report, known, err := Apply(context.Background(), archHost(t), parse(t, decl),
+		store.State{}, store.OriginDeclared, accountManager("ops", &commands), nil, nil)
+	if err != nil {
+		t.Fatalf("apply: %v\n%s", err, strings.Join(commands, "\n"))
+	}
+	if !report.Changed() {
+		t.Fatal("a unit that was stopped and is now running changed nothing")
+	}
+	var started, enabled bool
+	for _, c := range commands {
+		if c == "systemctl --user --machine=ops@ start i3-reload-watcher.service" {
+			started = true
+		}
+		if c == "systemctl --user --machine=ops@ enable i3-reload-watcher.service" {
+			enabled = true
+		}
+	}
+	if !started || !enabled {
+		t.Fatalf("the unit was not started and enabled in the account's manager:\n%s", strings.Join(commands, "\n"))
+	}
+	recorded, ok := known.At("service", "i3-reload-watcher.service")
+	if !ok || recorded.Scope != "user" || recorded.User != "ops" {
+		t.Fatalf("the record does not say whose manager the unit is in: %+v", recorded)
+	}
+}
+
+func TestASystemUnitIsUntouchedByTheScope(t *testing.T) {
+	var commands []string
+	decl := `{"declaration":1,"resources":[
+	  {"id":"x.daemon","type":"service","unit":"sshd.service","state":"running","boot":"enabled"}
+	]}`
+	if _, _, err := Apply(context.Background(), archHost(t), parse(t, decl),
+		store.State{}, store.OriginDeclared, unitIn(true, &commands), nil, nil); err != nil {
+		t.Fatal(err)
+	}
+	for _, c := range commands {
+		if strings.Contains(c, "--user") || strings.Contains(c, "--machine") {
+			t.Fatalf("a system unit was addressed to an account's manager: %s", c)
+		}
+	}
+}

internal/declaration/declaration.go

@@ -684,6 +684,16 @@ type Service struct {
 	// declaration that reports success and stops being true at the next power cut.
 	Boot string `json:"boot,omitempty"`
 
+	// Scope is whose service manager the unit belongs to: "system" (absent means system), or
+	// "user" — the operator account's own manager (novox/hq ADR 0177). A workstation's per-user
+	// daemons — a window manager's reload watcher, an audio mask, a memory guard — are units in
+	// that manager, and until this they had no form the mesh could send. A user-scoped unit names
+	// its User; the host talks to that account's manager and never starts a system unit by the
+	// same name.
+	Scope string `json:"scope,omitempty"`
+	// User is the account whose manager a user-scoped unit lives in. Required with scope "user",
+	// refused otherwise; a module names it ${machine:account} and never the person.
+	User string `json:"user,omitempty"`
 	// RestartOn names resources whose change means this service must be restarted.
 	//
 	// Because a running service does not re-read its configuration. Replace the file, find the
@@ -729,11 +739,33 @@ func (s *Service) Identity() string { return s.ID }
 func (s *Service) Kind() Type       { return TypeService }
 func (s *Service) Target() string   { return s.Unit }
 
+// ScopeSystem and ScopeUser are the two managers a unit may belong to (novox/hq ADR 0177).
+const (
+	ScopeSystem = "system"
+	ScopeUser   = "user"
+)
+
+// UserScoped is whether this unit lives in an account's own service manager.
+func (s *Service) UserScoped() bool { return s.Scope == ScopeUser }
+
 func (s *Service) validate(where string, _ bool) []string {
 	var problems []string
 	if s.Unit == "" {
 		problems = append(problems, where+": a service needs a unit")
 	}
+	switch s.Scope {
+	case "", ScopeSystem:
+		if s.User != "" {
+			problems = append(problems, where+": a system unit names no user; only a user-scoped unit does")
+		}
+	case ScopeUser:
+		if s.User == "" {
+			problems = append(problems, where+": a user-scoped unit names the account whose manager it lives in")
+		}
+	default:
+		problems = append(problems, fmt.Sprintf(
+			"%s: scope %q; a unit is in the \"system\" manager or the operator account's \"user\" one", where, s.Scope))
+	}
 	switch {
 	case s.State == "running" || s.State == "stopped":
 	case s.State != "":
@@ -870,7 +902,7 @@ type Package struct {
 	ID      string `json:"id"`
 	Type    Type   `json:"type"`
 	Package string `json:"package"`
-	// Absent declares that the package is NOT installed (novox/hq ADR 0180): the host removes it
+	// Absent declares that the package is NOT installed (novox/hq ADR 0175): the host removes it
 	// when it is, and leaves a machine that never had it alone. For the one case a module replaces
 	// software the machine was found with and the operator has decided it does not come back — the
 	// firewall front end a converged machine's filter module retired. Nothing to undo when the
@@ -952,14 +984,6 @@ type Container struct {
 	// container; a privileged container stays undeclarable.
 	Capabilities []string `json:"capabilities,omitempty"`
 
-	// Logging names where the runtime sends this container's output: "journald" sends it to the
-	// machine's journal, under the container's name, where what reads the machine's logs — its
-	// intrusion prevention first of all (novox/hq ADR 0179) — can read it the way it reads the
-	// machine's own services. Empty keeps the runtime's default, which is a file of the runtime's
-	// own that nothing but the runtime reads. Part of the spec: a container that logs elsewhere
-	// is a different container, and the runtime cannot change a running one's driver.
-	Logging string `json:"logging,omitempty"`
-
 	// Networks are networks this container also joins once created, by name — a found network a
 	// per-machine setting keeps for a taken container (novox/hq ADR 0163, rule 4), so a
 	// neighbour that resolves it there keeps resolving it until the neighbour is taken too.
@@ -1065,10 +1089,6 @@ func (c *Container) validate(where string, _ bool) []string {
 				"capability's name (CAP_NET_ADMIN or NET_ADMIN)")
 		}
 	}
-	if c.Logging != "" && c.Logging != "journald" {
-		problems = append(problems, where+": logging is "+strconv.Quote(c.Logging)+", and the only place a "+
-			"container's output can be sent besides the runtime's own file is \"journald\"")
-	}
 	for _, n := range c.Networks {
 		problems = append(problems, (&Network{Name: n}).validate(where+": networks", false)...)
 		if n == c.Network {

internal/declaration/declaration_test.go

@@ -524,24 +524,3 @@ func TestACapabilityIsNamedOrRefused(t *testing.T) {
 		}
 	}
 }
-
-// A container may send its output to the machine's journal, and nowhere else but the runtime's own
-// file (novox/hq ADR 0179): what reads the machine's logs then reads the container's too.
-func TestAContainerMayLogToTheJournalAndNowhereElse(t *testing.T) {
-	image := "postgres@sha256:" + strings.Repeat("a", 64)
-	d, err := Parse([]byte(`{"declaration":1,"resources":[
-	  {"id":"front","type":"container","name":"front","image":"` + image + `","logging":"journald"}
-	]}`))
-	if err != nil {
-		t.Fatal(err)
-	}
-	if got := d.Resources[0].(*Container).Logging; got != "journald" {
-		t.Fatalf("logging read as %q", got)
-	}
-	for _, bad := range []string{`"syslog"`, `"none"`, `"json-file"`} {
-		if _, err := Parse([]byte(`{"declaration":1,"resources":[
-		  {"id":"front","type":"container","name":"front","image":"` + image + `","logging":` + bad + `}]}`)); err == nil {
-			t.Errorf("%s was accepted as a place to log", bad)
-		}
-	}
-}

internal/declaration/userscope_test.go

@@ -0,0 +1,30 @@
+package declaration
+
+import (
+	"strings"
+	"testing"
+)
+
+// novox/hq ADR 0177: a unit is in the system manager or an account's own; a user-scoped one names
+// the account, a system one may not, and any other word is refused.
+func TestAUserScopedUnitNamesItsAccountAndASystemOneMayNot(t *testing.T) {
+	cases := []struct{ scope, user, wants string }{
+		{"user", "ops", ""},
+		{"", "", ""},
+		{"system", "", ""},
+		{"user", "", "names the account"},
+		{"", "ops", "names no user"},
+		{"session", "ops", "scope \"session\""},
+	}
+	for _, c := range cases {
+		s := &Service{ID: "m.u", Type: TypeService, Unit: "u.service", State: "running", Scope: c.scope, User: c.user}
+		problems := s.validate("m.u", false)
+		got := strings.Join(problems, "; ")
+		if c.wants == "" && len(problems) != 0 {
+			t.Fatalf("scope %q user %q refused: %s", c.scope, c.user, got)
+		}
+		if c.wants != "" && !strings.Contains(got, c.wants) {
+			t.Fatalf("scope %q user %q: wanted a refusal saying %q, got %q", c.scope, c.user, c.wants, got)
+		}
+	}
+}

internal/firewall/filters.go

@@ -179,18 +179,27 @@ func legacyFilters(rules, tool string, ufwActive bool) []Filter {
 			}
 		}
 	}
-	// A chain of refusals is a ban list when every refusal names the sources it refuses and the
-	// chain accepts nothing — the same rule the nftables side applies, and no more.
-	//
-	// **The policy of the chains that jump to it says nothing about what it is.** An earlier cut
-	// required every path into the chain to come from a built-in whose policy accepts, and the
-	// mesh's own intrusion prevention then read as a foreign rule set on the home server: its ban
-	// chain hangs off the container runtime's user chain as well as INPUT, and that machine's
-	// forward policy is DROP because the runtime set it. The machine reported "NOT the mesh alone"
-	// about a chain the mesh had just written (novox/hq ADR 0186). The policy is already classified
-	// where it belongs — as the runtime's — so requiring it here counted it twice.
+	var entered func(chain string, seen map[string]bool) bool
+	entered = func(chain string, seen map[string]bool) bool {
+		if seen[chain] || accepting[chain] || len(jumpedFrom[chain]) == 0 {
+			return false
+		}
+		seen[chain] = true
+		for _, from := range jumpedFrom[chain] {
+			if p, builtIn := policy[from]; builtIn {
+				if p != "ACCEPT" {
+					return false
+				}
+				continue
+			}
+			if !entered(from, seen) {
+				return false
+			}
+		}
+		return true
+	}
 	ban := func(chain, line string) bool {
-		return bansSources(line) && !accepting[chain] && len(jumpedFrom[chain]) > 0
+		return bansSources(line) && entered(chain, map[string]bool{})
 	}
 	type seen struct {
 		owner string
@@ -311,7 +320,7 @@ func Active(ctx context.Context, run Runner) bool {
 }
 
 // Installed says whether ufw is on this machine at all: a command that is not there is a front end
-// that was uninstalled (novox/hq ADR 0180), not one that is silent.
+// that was uninstalled (novox/hq ADR 0175), not one that is silent.
 func Installed(ctx context.Context, run Runner) bool {
 	_, err := run(ctx, "ufw", "status")
 	return !missing(err)
@@ -321,6 +330,6 @@ func Installed(ctx context.Context, run Runner) bool {
 const (
 	RetiredByMesh  = "mesh"
 	RetiredFoundSo = "found-inactive"
-	// RetiredRemoved is a front end uninstalled by the module that replaced it (ADR 0180).
+	// RetiredRemoved is a front end uninstalled by the module that replaced it (ADR 0175).
 	RetiredRemoved = "removed"
 )

internal/firewall/neighbour_ban_test.go

@@ -1,60 +0,0 @@
-package firewall
-
-import (
-	"os"
-	"testing"
-)
-
-// The mesh's own ban list is a ban wherever it hangs (novox/hq ADR 0186).
-//
-// Captured from the home server after the intrusion prevention had banned four addresses: its ban
-// chain is jumped to from INPUT, whose policy accepts, and from the container runtime's user chain,
-// which hangs off a FORWARD the runtime set to DROP. Requiring every path to come from an accepting
-// built-in made the machine report "NOT the mesh alone" about a chain the mesh had just written.
-func TestTheMeshsOwnBanChainIsABanBehindADroppingForward(t *testing.T) {
-	legacy, err := os.ReadFile("testdata/home-server-bans-S.txt")
-	if err != nil {
-		t.Fatal(err)
-	}
-	filters := Filters("", map[string]string{"iptables-legacy": string(legacy)}, false)
-
-	var ban, other []string
-	for _, f := range filters {
-		switch f.Owner {
-		case OwnerBan:
-			ban = append(ban, f.Where)
-		case OwnerOther:
-			other = append(other, f.Where)
-		}
-	}
-	if len(other) > 0 {
-		t.Errorf("the machine reports %v as rule sets the mesh did not write", other)
-	}
-	found := false
-	for _, w := range ban {
-		if w == "chain f2b-route-proxy (iptables-legacy)" {
-			found = true
-		}
-	}
-	if !found {
-		t.Errorf("the intrusion prevention's own chain was not read as a ban; bans were %v", ban)
-	}
-	if !Alone(filters) {
-		t.Error("a machine filtered by the mesh and its own bans does not read as the mesh alone")
-	}
-}
-
-// A chain that accepts anything is doing more than banning, and is still not a ban — which is what
-// keeps a predecessor's allow-and-drop chain classified as something the operator must look at.
-func TestAChainThatAcceptsIsNotABan(t *testing.T) {
-	rules := "-P INPUT ACCEPT\n" +
-		"-A INPUT -j HAL-MESH-ONLY\n" +
-		"-N HAL-MESH-ONLY\n" +
-		"-A HAL-MESH-ONLY -s 10.0.0.0/8 -j ACCEPT\n" +
-		"-A HAL-MESH-ONLY -s 203.0.113.7/32 -j DROP\n"
-	for _, f := range Filters("", map[string]string{"iptables-legacy": rules}, false) {
-		if f.Where == "chain HAL-MESH-ONLY (iptables-legacy)" && f.Owner != OwnerOther {
-			t.Errorf("a chain that accepts was classified as %s", f.Owner)
-		}
-	}
-}

internal/firewall/testdata/home-server-bans-S.txt

@@ -1,147 +0,0 @@
--P INPUT ACCEPT
--P FORWARD DROP
--P OUTPUT ACCEPT
--N DOCKER
--N DOCKER-BRIDGE
--N DOCKER-CT
--N DOCKER-FORWARD
--N DOCKER-INTERNAL
--N DOCKER-USER
--N f2b-route-proxy
--N ufw-after-forward
--N ufw-after-input
--N ufw-after-logging-forward
--N ufw-after-logging-input
--N ufw-after-logging-output
--N ufw-after-output
--N ufw-before-forward
--N ufw-before-input
--N ufw-before-logging-forward
--N ufw-before-logging-input
--N ufw-before-logging-output
--N ufw-before-output
--N ufw-reject-forward
--N ufw-reject-input
--N ufw-reject-output
--N ufw-track-forward
--N ufw-track-input
--N ufw-track-output
--A INPUT -p tcp -j f2b-route-proxy
--A INPUT -j ufw-before-logging-input
--A INPUT -j ufw-before-input
--A INPUT -j ufw-after-input
--A INPUT -j ufw-after-logging-input
--A INPUT -j ufw-reject-input
--A INPUT -j ufw-track-input
--A FORWARD -j DOCKER-USER
--A FORWARD -j DOCKER-FORWARD
--A FORWARD -j ufw-before-logging-forward
--A FORWARD -j ufw-before-forward
--A FORWARD -j ufw-after-forward
--A FORWARD -j ufw-after-logging-forward
--A FORWARD -j ufw-reject-forward
--A FORWARD -j ufw-track-forward
--A OUTPUT -j ufw-before-logging-output
--A OUTPUT -j ufw-before-output
--A OUTPUT -j ufw-after-output
--A OUTPUT -j ufw-after-logging-output
--A OUTPUT -j ufw-reject-output
--A OUTPUT -j ufw-track-output
--A DOCKER -d 172.17.0.18/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8686 -j ACCEPT
--A DOCKER -d 172.17.0.14/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8989 -j ACCEPT
--A DOCKER -d 172.17.0.15/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 7878 -j ACCEPT
--A DOCKER -d 172.17.0.5/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 9117 -j ACCEPT
--A DOCKER -d 172.17.0.13/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 6789 -j ACCEPT
--A DOCKER -d 172.19.0.2/32 ! -i br-32062158f584 -o br-32062158f584 -p tcp -m tcp --dport 8080 -j ACCEPT
--A DOCKER -d 172.17.0.2/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 5432 -j ACCEPT
--A DOCKER -d 172.27.0.2/32 ! -i br-0910a98c6158 -o br-0910a98c6158 -p tcp -m tcp --dport 5678 -j ACCEPT
--A DOCKER -d 172.17.0.21/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 3579 -j ACCEPT
--A DOCKER -d 172.17.0.19/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8181 -j ACCEPT
--A DOCKER -d 172.17.0.17/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8787 -j ACCEPT
--A DOCKER -d 172.17.0.16/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 6767 -j ACCEPT
--A DOCKER -d 172.17.0.12/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 3000 -j ACCEPT
--A DOCKER -d 172.17.0.11/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 80 -j ACCEPT
--A DOCKER -d 172.17.0.10/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 9443 -j ACCEPT
--A DOCKER -d 172.17.0.10/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 9000 -j ACCEPT
--A DOCKER -d 172.17.0.9/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 3000 -j ACCEPT
--A DOCKER -d 172.17.0.7/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 1880 -j ACCEPT
--A DOCKER -d 172.28.0.2/32 ! -i br-b11461b5b028 -o br-b11461b5b028 -p tcp -m tcp --dport 80 -j ACCEPT
--A DOCKER -d 172.23.0.14/32 ! -i br-66ffa5c1cba5 -o br-66ffa5c1cba5 -p tcp -m tcp --dport 6543 -j ACCEPT
--A DOCKER -d 172.23.0.14/32 ! -i br-66ffa5c1cba5 -o br-66ffa5c1cba5 -p tcp -m tcp --dport 5432 -j ACCEPT
--A DOCKER -d 172.23.0.5/32 ! -i br-66ffa5c1cba5 -o br-66ffa5c1cba5 -p tcp -m tcp --dport 8000 -j ACCEPT
--A DOCKER -d 172.26.0.3/32 ! -i br-b0fec361ccaa -o br-b0fec361ccaa -p tcp -m tcp --dport 6167 -j ACCEPT
--A DOCKER -d 172.26.0.2/32 ! -i br-b0fec361ccaa -o br-b0fec361ccaa -p tcp -m tcp --dport 80 -j ACCEPT
--A DOCKER -d 172.17.0.8/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8000 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p udp -m udp --dport 10001 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8880 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8843 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8443 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8080 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 6789 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p udp -m udp --dport 5514 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p udp -m udp --dport 3478 -j ACCEPT
--A DOCKER -d 172.17.0.6/32 ! -i docker0 -o docker0 -p udp -m udp --dport 1900 -j ACCEPT
--A DOCKER -d 172.25.0.3/32 ! -i br-b98821f7dc38 -o br-b98821f7dc38 -p tcp -m tcp --dport 8000 -j ACCEPT
--A DOCKER -d 172.18.0.3/32 ! -i br-442a0bfc65f8 -o br-442a0bfc65f8 -p tcp -m tcp --dport 1433 -j ACCEPT
--A DOCKER -d 172.20.0.3/32 ! -i br-afa37ac8b33d -o br-afa37ac8b33d -p tcp -m tcp --dport 8081 -j ACCEPT
--A DOCKER -d 172.20.0.3/32 ! -i br-afa37ac8b33d -o br-afa37ac8b33d -p tcp -m tcp --dport 1883 -j ACCEPT
--A DOCKER -d 172.17.0.4/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 8086 -j ACCEPT
--A DOCKER -d 172.21.0.2/32 ! -i br-df15d8e19ec7 -o br-df15d8e19ec7 -p tcp -m tcp --dport 6379 -j ACCEPT
--A DOCKER -d 172.30.0.3/32 ! -i br-521eab9a3a5e -o br-521eab9a3a5e -p tcp -m tcp --dport 8283 -j ACCEPT
--A DOCKER -d 172.17.0.3/32 ! -i docker0 -o docker0 -p tcp -m tcp --dport 3000 -j ACCEPT
--A DOCKER ! -i br-32062158f584 -o br-32062158f584 -j DROP
--A DOCKER ! -i docker0 -o docker0 -j DROP
--A DOCKER ! -i br-521eab9a3a5e -o br-521eab9a3a5e -j DROP
--A DOCKER ! -i br-df15d8e19ec7 -o br-df15d8e19ec7 -j DROP
--A DOCKER ! -i br-afa37ac8b33d -o br-afa37ac8b33d -j DROP
--A DOCKER ! -i br-442a0bfc65f8 -o br-442a0bfc65f8 -j DROP
--A DOCKER ! -i br-b98821f7dc38 -o br-b98821f7dc38 -j DROP
--A DOCKER ! -i br-b0fec361ccaa -o br-b0fec361ccaa -j DROP
--A DOCKER ! -i br-66ffa5c1cba5 -o br-66ffa5c1cba5 -j DROP
--A DOCKER ! -i br-b11461b5b028 -o br-b11461b5b028 -j DROP
--A DOCKER ! -i br-2df4e541b877 -o br-2df4e541b877 -j DROP
--A DOCKER ! -i br-0910a98c6158 -o br-0910a98c6158 -j DROP
--A DOCKER-BRIDGE -o br-32062158f584 -j DOCKER
--A DOCKER-BRIDGE -o docker0 -j DOCKER
--A DOCKER-BRIDGE -o br-521eab9a3a5e -j DOCKER
--A DOCKER-BRIDGE -o br-df15d8e19ec7 -j DOCKER
--A DOCKER-BRIDGE -o br-afa37ac8b33d -j DOCKER
--A DOCKER-BRIDGE -o br-442a0bfc65f8 -j DOCKER
--A DOCKER-BRIDGE -o br-b98821f7dc38 -j DOCKER
--A DOCKER-BRIDGE -o br-b0fec361ccaa -j DOCKER
--A DOCKER-BRIDGE -o br-66ffa5c1cba5 -j DOCKER
--A DOCKER-BRIDGE -o br-b11461b5b028 -j DOCKER
--A DOCKER-BRIDGE -o br-2df4e541b877 -j DOCKER
--A DOCKER-BRIDGE -o br-0910a98c6158 -j DOCKER
--A DOCKER-CT -o br-32062158f584 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o docker0 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-521eab9a3a5e -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-df15d8e19ec7 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-afa37ac8b33d -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-442a0bfc65f8 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-b98821f7dc38 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-b0fec361ccaa -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-66ffa5c1cba5 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-b11461b5b028 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-2df4e541b877 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-CT -o br-0910a98c6158 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-FORWARD -j DOCKER-CT
--A DOCKER-FORWARD -j DOCKER-INTERNAL
--A DOCKER-FORWARD -j DOCKER-BRIDGE
--A DOCKER-FORWARD -i br-32062158f584 -j ACCEPT
--A DOCKER-FORWARD -i docker0 -j ACCEPT
--A DOCKER-FORWARD -i br-521eab9a3a5e -j ACCEPT
--A DOCKER-FORWARD -i br-df15d8e19ec7 -j ACCEPT
--A DOCKER-FORWARD -i br-afa37ac8b33d -j ACCEPT
--A DOCKER-FORWARD -i br-442a0bfc65f8 -j ACCEPT
--A DOCKER-FORWARD -i br-b98821f7dc38 -j ACCEPT
--A DOCKER-FORWARD -i br-b0fec361ccaa -j ACCEPT
--A DOCKER-FORWARD -i br-66ffa5c1cba5 -j ACCEPT
--A DOCKER-FORWARD -i br-b11461b5b028 -j ACCEPT
--A DOCKER-FORWARD -i br-2df4e541b877 -j ACCEPT
--A DOCKER-FORWARD -i br-0910a98c6158 -j ACCEPT
--A DOCKER-USER -p tcp -j f2b-route-proxy
--A f2b-route-proxy -s 13.70.107.184/32 -j REJECT --reject-with icmp-port-unreachable
--A f2b-route-proxy -s 45.138.12.51/32 -j REJECT --reject-with icmp-port-unreachable
--A f2b-route-proxy -s 20.214.191.94/32 -j REJECT --reject-with icmp-port-unreachable
--A f2b-route-proxy -j RETURN

internal/store/store.go

@@ -82,6 +82,10 @@ type Applied struct {
 	// 0117) — kept here because removal happens once the declaration that said so is gone, and a
 	// service removed as if it had a state is stopped: the machine's network manager, for one.
 	Stateless bool `json:"stateless,omitempty"`
+	// Scope and User are, for a service in an account's own manager (novox/hq ADR 0177), which
+	// manager — so removal gives the unit back through the same one it was applied through.
+	Scope string `json:"scope,omitempty"`
+	User  string `json:"user,omitempty"`
 
 	// Found is, for a service, the state its unit was in when this host first applied it — before
 	// the mesh started, stopped, enabled or disabled anything. Removal gives that back and nothing

internal/system/system.go

@@ -52,7 +52,7 @@ type System interface {
 	PackageInstalled(ctx context.Context, run Runner, name string) (bool, error)
 	InstallPackage(ctx context.Context, run Runner, name string) error
 	// RemovePackage uninstalls one package, leaving its dependencies and anything the operator
-	// changed in its configuration where the package manager leaves them (novox/hq ADR 0180).
+	// changed in its configuration where the package manager leaves them (novox/hq ADR 0175).
 	RemovePackage(ctx context.Context, run Runner, name string) error
 
 	// ServiceState is "running" or "stopped". A unit that does not exist is an error, never