Merge pull request 'A container may log to the journal (hq ADR 0179)' (#73) from feat/the-intrusion-seat-serves-its-verbs into main

A jail reads a log; a container's output went to a file of the runtime's own under a path that
changes on recreate, so no jail could read a container's service. logging: journald runs the
container with the journal as its driver, named in the spec so moving it recreates it; any other
place is refused.

internal/apply/apply.go

@@ -1407,6 +1407,25 @@ func applyPackage(ctx context.Context, sys system.System, r *declaration.Package
 	if err != nil {
 		return out, err
 	}
+	if r.Absent {
+		// 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"
+			return out, nil
+		}
+		if err := sys.RemovePackage(ctx, run, r.Package); err != nil {
+			return out, fmt.Errorf("removing %s: %w", r.Package, err)
+		}
+		if still, err := sys.PackageInstalled(ctx, run, r.Package); err != nil {
+			return out, err
+		} else if still {
+			return out, fmt.Errorf("%s was removed without error and the package database still has it", r.Package)
+		}
+		out.Action = "removed"
+		out.Detail = "declared absent; its configuration is left where the package manager leaves it"
+		return out, nil
+	}
 	if installed {
 		out.Action = "unchanged"
 		out.Detail = "already installed"
@@ -1588,6 +1607,10 @@ 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.
@@ -1785,6 +1808,11 @@ 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)
 	}

internal/apply/left_out_test.go

@@ -173,3 +173,42 @@ func TestACapabilityReachesTheRuntimeAndTheSpec(t *testing.T) {
 		t.Fatal("a capability is not part of the container's spec")
 	}
 }
+
+// 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
+	var ran []string
+	run := func(_ context.Context, name string, args ...string) (string, error) {
+		ran = append(ran, name+" "+strings.Join(args, " "))
+		if name != "pacman" {
+			return "", nil
+		}
+		switch args[0] {
+		case "-Q":
+			if args[1] == "pacman" || installed {
+				return args[1] + " 1.0\n", nil
+			}
+			return "", errors.New("package not found")
+		case "-R":
+			installed = false
+		}
+		return "", nil
+	}
+	d := parseTrusted(t, `{"declaration":1,"resources":[{"id":"front-end","type":"package","package":"ufw","absent":true}]}`)
+	report, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if report.Outcomes[0].Action != "removed" || !strings.Contains(strings.Join(ran, "\n"), "pacman -R --noconfirm ufw") {
+		t.Fatalf("an installed package declared absent was not removed: %+v\n%v", report.Outcomes[0], ran)
+	}
+	ran = nil
+	report, _, err = Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if report.Outcomes[0].Action != "unchanged" || strings.Contains(strings.Join(ran, "\n"), "-R") {
+		t.Fatalf("a package already absent was touched: %+v\n%v", report.Outcomes[0], ran)
+	}
+}

internal/apply/logging_test.go

@@ -0,0 +1,43 @@
+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

@@ -76,6 +76,16 @@ func retireFirewall(ctx context.Context, d *declaration.Declaration, origin stri
 	if origin != store.OriginDeclared || d.Adoption != nil || rec == nil || rec.Kind != string(firewall.UFW) || !rec.WasActive {
 		return "", nil
 	}
+	if !firewall.Installed(ctx, run) {
+		// 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
+			log("  the found firewall (ufw) is no longer installed; the mesh's filter is what filters this machine")
+			return "removed: ufw is no longer installed; the mesh's filter is what filters this machine", nil
+		}
+		return "", nil
+	}
 	active := firewall.Active(ctx, run)
 	if !active && !(rec.Forward != nil && !rec.DisabledByMesh) {
 		// Inactive, and either the mesh's doing already or nobody's recorded here: said as found,

internal/apply/opening_test.go

@@ -8,6 +8,7 @@ import (
 	"path/filepath"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/novox/mesh-host/internal/declaration"
 	"github.com/novox/mesh-host/internal/store"
@@ -522,3 +523,33 @@ func TestUfwIsNotRetiredUntilTheMeshsOwnFilterIsLoaded(t *testing.T) {
 		t.Errorf("ufw was not retired once the mesh's filter was loaded: active %v, %+v", u.active, state.Firewall)
 	}
 }
+
+// A front end that is no longer installed is recorded as removed, said once, and asked nothing of
+// (novox/hq ADR 0175).
+func TestAnUninstalledFrontEndIsRetiredForGood(t *testing.T) {
+	dir := t.TempDir()
+	u := &ufwMachine{installed: false, ruleset: "table inet mesh\n"}
+	known := store.State{Firewall: &store.FoundFirewall{Kind: "ufw", WasActive: true, DisabledByMesh: true,
+		RetiredBy: "mesh", FoundAt: time.Now()}}
+	converged := parse(t, `{"declaration":1,"resources":[`+withConf(dir)+`]}`)
+	report, state, err := applyWith(t, converged, known, u.run)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if state.Firewall.RetiredBy != "removed" || !strings.Contains(report.Firewall, "no longer installed") {
+		t.Fatalf("record %+v, said %q", state.Firewall, report.Firewall)
+	}
+	u.asked = nil
+	report, _, err = applyWith(t, converged, state, u.run)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if report.Firewall != "" {
+		t.Errorf("said again: %q", report.Firewall)
+	}
+	for _, a := range u.asked {
+		if strings.HasPrefix(a, "ufw") && a != "ufw status" {
+			t.Errorf("asked something of a front end that is not there: %v", u.asked)
+		}
+	}
+}

internal/declaration/declaration.go

@@ -870,6 +870,12 @@ 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 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
+	// declaration drops it: the host does not install what a declaration stopped saying is absent.
+	Absent bool `json:"absent,omitempty"`
 }
 
 func (p *Package) Identity() string { return p.ID }
@@ -946,6 +952,14 @@ 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.
@@ -1051,6 +1065,10 @@ 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

@@ -524,3 +524,24 @@ 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/firewall/filters.go

@@ -319,8 +319,17 @@ func Active(ctx context.Context, run Runner) bool {
 	return err == nil && statusActive(out)
 }
 
+// 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 0175), not one that is silent.
+func Installed(ctx context.Context, run Runner) bool {
+	_, err := run(ctx, "ufw", "status")
+	return !missing(err)
+}
+
 // Retirements of a found firewall, as the host records them.
 const (
 	RetiredByMesh  = "mesh"
 	RetiredFoundSo = "found-inactive"
+	// RetiredRemoved is a front end uninstalled by the module that replaced it (ADR 0175).
+	RetiredRemoved = "removed"
 )

internal/system/alpine.go

@@ -46,6 +46,11 @@ func (a alpine) PackageInstalled(ctx context.Context, run Runner, name string) (
 	return strings.TrimSpace(out) != "", nil
 }
 
+func (alpine) RemovePackage(ctx context.Context, run Runner, name string) error {
+	_, err := run(ctx, "apk", "del", name)
+	return err
+}
+
 func (alpine) InstallPackage(ctx context.Context, run Runner, name string) error {
 	_, err := run(ctx, "apk", "add", "--no-cache", name)
 	return err

internal/system/android.go

@@ -65,6 +65,10 @@ func (a android) InstallPackage(context.Context, Runner, string) error {
 	return fmt.Errorf("%w: package", ErrUnsupported)
 }
 
+func (a android) RemovePackage(context.Context, Runner, string) error {
+	return fmt.Errorf("%w: package", ErrUnsupported)
+}
+
 func (a android) ServiceState(context.Context, Runner, string) (string, error) {
 	return "", fmt.Errorf("%w: service (init is not reachable without root)", ErrUnsupported)
 }

internal/system/arch.go

@@ -39,6 +39,14 @@ func (a arch) PackageInstalled(ctx context.Context, run Runner, name string) (bo
 	return true, nil
 }
 
+// RemovePackage removes one package and nothing it depends on: `-R`, not `-Rs`, because what else
+// relied on a dependency is not this declaration's to know. pacman keeps a configuration file the
+// operator changed as `.pacsave`, which is what "never flushed" comes to once the front end is gone.
+func (arch) RemovePackage(ctx context.Context, run Runner, name string) error {
+	_, err := run(ctx, "pacman", "-R", "--noconfirm", name)
+	return err
+}
+
 func (arch) InstallPackage(ctx context.Context, run Runner, name string) error {
 	out, err := run(ctx, "pacman", "-S", "--noconfirm", "--needed", name)
 	if err == nil {

internal/system/system.go

@@ -51,6 +51,9 @@ 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 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
 	// "stopped" — reporting absence as satisfaction is the fault this host exists to prevent.