Compare commits

..
Author SHA1 Message Date
jschoubben ab74988f1c The filter constrains what arrives from outside, and names no network
The forward chain blocked everything passing through the machine and then allowed
the machine's own containers back by naming their address ranges: 172.16.0.0/12 and
192.168.128.0/17 fixed here, the rest recorded per machine by 0043. Every way of
keeping that list correct fails — a constant describes one machine, a recorded range
goes stale in silence and cannot tell a network the mesh made from one a predecessor
left behind, and generating it from the modules would put half the rule set on the
machine.

The mesh has no position on a container reaching outward: that is not a port opened
to anybody. So both chains are written around the links traffic arrives on. What did
not arrive from outside is accepted in one line; what did meets the declared rules.
The tunnel is named beside the outward links rather than treated as inside, or a port
nothing declares would be reachable from every machine in the mesh.

A machine that has not reported an outward link is sent no filter and keeps the one
it has, refused where a person reads it rather than as a rule set that will not load.

Removes the two constants, `node networks`, and the column behind it. novox/hq ADR
0140, superseding 0137 and 0139.
2026-09-28 23:49:14 +02:00
jschoubben 54812306be A machine says which networks it routes, and its filter forwards them
The derived filter denies forwarding by default and then allows the container
runtime's two default pools, named in this code with a comment saying a machine
configured otherwise needs to say so -- and no way to say it. So the filter was
right on a machine using the defaults and silently wrong on any other.

Measured today: flipping a workstation to the derived filter cut egress for five
of its container networks and for every network its test beds create, because
those come from ranges the defaults do not cover. Nothing reported a fault; the
guests just could not reach anything, while the machine reported it had applied
what it was told.

A node-level fact beside the public domain, because the machine routes them and
the module that loads the filter may be replaced. Added to the defaults, never
replacing them. Their guests also keep address and name service, without which a
network does not work at all, and the converge preview now says what a machine
routes instead of leaving it to a sentence about what it cannot preview.
2026-09-28 21:29:10 +02:00
mesh-admin ce9e20fbbc Merge pull request 'A push raises what a module hears, not only a start' (#132) from fix/a-push-raises-what-a-module-hears into main 2026-09-28 14:46:54 +00:00
16 changed files with 410 additions and 59 deletions
+23 -1
View File
@@ -309,7 +309,7 @@ func converge(ctx context.Context, open *stores, node string, yes bool, digest s
return "", err
}
derived := derivedFilter{rules: rules, foundation: with.Foundation, mesh: with.Mesh,
outward: plan.PublicDomain != ""}
outward: plan.PublicDomain != "", outwardLinks: with.OutwardLinks}
preview, saw := previewOf(node, reported, derived, plan, taken, filter, runs[filter])
preview += "\n\n preview " + saw
if !yes {
@@ -414,6 +414,18 @@ func previewOf(node string, reported inventory.Adoption, derived derivedFilter,
b.WriteString(" not previewed: traffic the machine routes that is not a published port " +
"(a tunnel, NAT in the found firewall) — the derived filter drops it unless a module " +
"declares it\n")
// Which links the filter constrains, said rather than left to the sentence above (novox/hq ADR
// 0140). Everything arriving anywhere else is this machine's own guest and keeps working — which
// is what a reader most wants to know, because the previous shape of this filter cut a machine's
// guests off at the flip without saying so, and that is how this was found.
if len(derived.outwardLinks) > 0 {
b.WriteString(fmt.Sprintf(" it filters what arrives on: %s, and on the private network "+
"— everything its own guests send keeps working\n",
strings.Join(derived.outwardLinks, ", ")))
} else {
b.WriteString(" it has reported no link facing outside, so no filter can be composed " +
"for it — the flip is refused until it reports one\n")
}
isTaken := map[string]bool{}
for _, m := range taken {
@@ -473,6 +485,10 @@ type derivedFilter struct {
// mesh is every address on the private network; outward says the machine faces outside.
mesh []string
outward bool
// outwardLinks is the links this machine reported as facing outside it (novox/hq ADR 0140).
// The filter constrains what arrives on them; everything arriving elsewhere is this machine's
// own guest and is not filtered.
outwardLinks []string
}
// closesOutside is what a narrowing from everywhere to the private network is called: it closes.
@@ -498,6 +514,12 @@ func (d derivedFilter) fate(r inventory.Reach) string {
return "stays open — the mesh's own, from anywhere"
}
}
// This machine's own guests ask it for an address and for names, and those two arrive here
// (novox/hq ADR 0140). Admitted by the link they arrive on, so a listener bound anywhere but an
// outward link keeps answering them.
if (r.Protocol == "udp" && (r.Port == 53 || r.Port == 67)) || (r.Protocol == "tcp" && r.Port == 53) {
return "stays open — this machine's own guests asking it for an address and for names"
}
for _, rule := range d.rules {
if rule.Port != r.Port || rule.Protocol != r.Protocol {
continue
+3
View File
@@ -148,6 +148,9 @@ func usage() {
node public-domain <name> the domain it composes its routed names under
node public-domain <name> <d> ...set it to d
node public-domain <name> --clear ...it faces the outside no longer
node networks <name> the networks it routes for what it hosts
node networks <name> <cidr>... ...set them; its filter forwards these too
node networks <name> --clear ...only the container runtime's own
token issue --node <name> a one-time right to join, for an existing record
token issue --new <name> create the record and issue for it
token issue ... --adopted ...for a machine in use, which joins adopted
+12
View File
@@ -66,6 +66,18 @@ func nodeCommand(ctx context.Context, args []string) error {
// because the damage is already done by the time it prints.
return publicDomain(ctx, inv, args[1:])
case "networks":
// Removed by novox/hq ADR 0140, which superseded the record that added it. The filter no
// longer names any network: it constrains what arrives from outside the machine and says
// nothing about what did not, so there is no list to keep. Answered rather than met with
// "unknown command", because this was the documented way to stop a flip cutting a machine's
// containers off and somebody will reasonably still type it.
return errors.New("`node networks` is gone (novox/hq ADR 0140). The filter constrains what " +
"arrives from outside this machine and says nothing about traffic that did not, so no " +
"network is named anywhere and nothing needs to be said to keep a machine's own " +
"containers reaching outward. The machine reports which of its links face outside; see " +
"`node show <name>`")
case "account":
// The operator's login on this machine (novox/hq to-be 29): what a home-scoped file is
// owned by and which account `ssh <node>` uses. Reports with no argument; sets with one;
+8 -2
View File
@@ -640,13 +640,19 @@ func renderingFor(ctx context.Context, open *stores, node string,
if err != nil {
return catalogue.Rendering{}, inventory.Node{}, err
}
// Which of this machine's links face outside, which is what the derived filter is written
// around (novox/hq ADR 0140). Reported by the machine, never set.
outwardLinks, err := inv.OutwardLinksOf(ctx, node)
if err != nil {
return catalogue.Rendering{}, inventory.Node{}, err
}
return catalogue.Rendering{
BusMembership: memberships[node],
Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
Certificate: certificate, Authority: authority, Mesh: private, Names: names,
Machines: machines,
Suffix: overlay.Suffix(), MeshRange: meshRange, Accounts: accounts, Foundation: foundation,
Kept: kept, Adopted: record.Adopted,
Suffix: overlay.Suffix(), MeshRange: meshRange, TunnelInterface: overlay.Interface, Accounts: accounts, Foundation: foundation,
Kept: kept, Adopted: record.Adopted, OutwardLinks: outwardLinks,
Given: given, Taken: taken, Seats: seats, ArtifactStore: artifactStore, Built: built,
BusUsers: busUsers,
}, record, nil
+17 -9
View File
@@ -59,7 +59,11 @@ func anchorRendering(adopted bool) Rendering {
Values: map[string]any{ExposeSetting: map[string]any{"5000": FromEverywhere}}}}},
Mesh: []string{"10.42.0.1"},
Foundation: []int{5671},
Adopted: adopted,
// What the machine reported faces outside, which every rule in the filter is written
// around (novox/hq ADR 0140).
OutwardLinks: []string{"eth0"},
TunnelInterface: "mesh0",
Adopted: adopted,
// Genesis takes the foundation's modules.
Taken: map[string]bool{"postgres": true, "lavinmq": true},
}
@@ -575,11 +579,13 @@ func TestAGivenMachineSideReachesTheFilterTheOpeningAndTheConsumer(t *testing.T)
}
r := Resolution{Node: "anchor", Modules: []Manifest{forge}}
with := Rendering{
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, given)},
Given: map[string]map[int]int{"forge": given},
Mesh: []string{"10.77.0.1"},
Adopted: true,
Taken: map[string]bool{"forge": true},
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, given)},
Given: map[string]map[int]int{"forge": given},
Mesh: []string{"10.77.0.1"},
Adopted: true,
OutwardLinks: []string{"eth0"},
TunnelInterface: "mesh0",
Taken: map[string]bool{"forge": true},
}
// What the runtime is handed: the machine's own port on the outside, the container's within.
@@ -660,9 +666,11 @@ func TestALongFormPortIsOpenedWhereTheManifestPublishesIt(t *testing.T) {
forge := aForge()
r := Resolution{Node: "anchor", Modules: []Manifest{forge}}
composed, err := r.Compose(Rendering{
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, nil)},
Mesh: []string{"10.77.0.1"},
Adopted: true,
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, nil)},
Mesh: []string{"10.77.0.1"},
Adopted: true,
OutwardLinks: []string{"eth0"},
TunnelInterface: "mesh0",
})
if err != nil {
t.Fatal(err)
+36 -1
View File
@@ -124,6 +124,16 @@ type Rendering struct {
// nothing on this node keeps them, or the mesh has no operator key.
Kept *KeptExport
// OutwardLinks is the links this machine reported as facing outside it, which the filter is
// written around (novox/hq ADR 0140). Empty means the machine has not said, and the mesh
// composes no filter for it rather than writing a rule around a link with no name.
OutwardLinks []string
// TunnelInterface is the interface the mesh's private network runs on, named here rather than
// imported because the overlay package rests on this one. Traffic arriving on it is the mesh's,
// not this machine's own guest, so the filter admits it only by a rule.
TunnelInterface string
// Foundation is the ports the mesh itself needs reachable on every machine, which no module
// declares because the foundation is not a module (novox/hq 04-ISSUES/051 and 052). The broker
// is the one that matters: a machine dials it to enrol, and a firewall derived only from
@@ -345,7 +355,21 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
if err != nil {
return nil, err
}
filtering := AsNftables(rules, with.Mesh, r.PublicDomain != "", with.Foundation)
// **A machine that has not said which links face outside is sent no filter** (novox/hq ADR
// 0140). The whole chain is written around those links: with none, the rule that lets this
// machine's own guests keep working would name an empty set, which nftables refuses, and a rule
// set that does not load is a machine filtering nothing while its unit reports success. Refused
// here, where a person reads it, rather than on the machine — and the machine keeps the filter
// it already has.
if filters := r.filtersHere(); filters != "" && len(with.OutwardLinks) == 0 {
return nil, fmt.Errorf(
"%s cannot be sent a filter: it has not reported which of its links face outside, and "+
"every rule in the chain is written around them. It reports that on each apply; "+
"`node show %s` says whether it has. Until then %s is not sent, and the machine "+
"keeps the filter it has", r.Node, r.Node, filters)
}
filtering := AsNftables(rules, with.Mesh, r.PublicDomain != "", with.Foundation,
with.OutwardLinks, with.TunnelInterface)
var out []map[string]any
for _, m := range r.Modules {
@@ -852,6 +876,17 @@ func mapping(written string) (outer, inner int, address string, ok bool) {
return outer, inner, strings.Join(parts[:len(parts)-2], ":"), true
}
// filtersHere is the module on this node that loads the machine's packet filter, or empty when none
// does. Named rather than counted: a refusal that says which module is one step from acted on.
func (r Resolution) filtersHere() string {
for _, m := range r.Modules {
if m.Filtering != nil {
return m.Module
}
}
return ""
}
// Rules is the rule set this node's filter is derived from: every module's listens, what was
// computed for this machine, and each module's per-node exposure. The same answer whether the node
// is adopted or converged — the one loads it as a filter, the other declares it as openings.
+58 -21
View File
@@ -230,7 +230,23 @@ const SSHPort = 22
// It is a floor for the same reason ssh is. A machine nobody can reach is a machine nobody can
// repair; a machine the mesh cannot reach is a machine the mesh cannot manage. Neither is a thing
// any module asks for, and neither may be derived away.
func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) string {
func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int,
outwardLinks []string, tunnel string) string {
// The links that are not this machine's own: the ones facing outside, and the mesh's tunnel.
// Traffic arriving on any of them is admitted only by a rule below; traffic arriving anywhere
// else is this machine's own guest and is not something the mesh has a position on.
//
// The tunnel is named here deliberately. Treating it as "not outside" would make a port nothing
// declares reachable from every machine in the mesh, which is the derivation abandoned.
quoted := make([]string, 0, len(outwardLinks)+1)
for _, link := range outwardLinks {
quoted = append(quoted, fmt.Sprintf("%q", link))
}
if tunnel != "" {
quoted = append(quoted, fmt.Sprintf("%q", tunnel))
}
inward := strings.Join(quoted, ", ")
var b strings.Builder
b.WriteString("# Computed by the mesh from what is assigned to this node.\n")
b.WriteString("# Edits are lost on the next declaration; change a module's listens instead.\n\n")
@@ -252,6 +268,22 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
b.WriteString("\t\ticmp type echo-request accept\n")
b.WriteString("\t\ticmpv6 type { echo-request, nd-neighbor-solicit, nd-neighbor-advert, nd-router-advert } accept\n")
// **What this machine's own guests must be able to ask it** (novox/hq ADR 0140). A guest gets
// its address and its names from this machine, over the link it is on, and those two questions
// arrive at the input chain like any other. Denied, the guest never gets an address and never
// resolves a name — which is not "a closed port" but a network that does not work at all, and it
// is this machine's own guest asking.
//
// Asked for by the link it arrives on rather than by the address it comes from, for the reason
// the forward chain below no longer names an address: a range describes one machine and goes
// stale in silence. Anything arriving from outside, or over the tunnel, is not a guest of this
// machine and asks through a port somebody declared, like everything else.
if len(inward) > 0 {
b.WriteString("\t\t# this machine's own guests asking it for an address and for names\n")
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } udp dport { 53, 67 } accept\n", inward))
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } tcp dport 53 accept\n", inward))
}
// **ssh, always, and not because a module asked.**
//
// Every other line in this chain is derived from what is assigned here, which is the whole
@@ -361,19 +393,36 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
// about the ports most worth protecting. Rehearsed on three machines: loading these rules
// refused a port on the host and left a published container port reachable (novox/hq issue 047).
//
// The way through is the one the system being replaced already used: deny by default here, and
// then explicitly allow the runtime's own networks, so containers keep working while everything
// else has to be asked for.
// **What it constrains is traffic arriving from OUTSIDE this machine, and nothing else**
// (novox/hq ADR 0140).
//
// It used to deny everything here and then allow the machine's own containers back by naming
// the address ranges they sit on — two ranges fixed in this file and the rest recorded per
// machine. Every way of keeping that list correct failed. A constant describes one machine. A
// recorded range goes stale in silence and cannot tell a network the mesh made from one a
// predecessor left behind. Generating it from the modules would have put half this rule set on
// the machine.
//
// The list should not exist, because the mesh has no position on a container reaching outward:
// that is not a port opened to anybody. So traffic that did not arrive from outside is accepted
// in one line, and what did arrive from outside is allowed only where a rule below admits it.
//
// The tunnel is not "not outside". Accepting everything off it would make a port nothing
// declares reachable from any machine in the mesh, which is the derivation abandoned — so it is
// named here beside the outward links, and traffic arriving on it meets the rules below like
// anything else.
b.WriteString("\tchain forward {\n")
b.WriteString("\t\ttype filter hook forward priority filter; policy drop;\n")
b.WriteString("\t\tct state established,related accept\n")
b.WriteString("\t\tct state invalid drop\n")
b.WriteString("\n")
// What the container runtime created. Without these, denying by default stops every container
// on the machine — which is exactly the failure the absent chain was avoiding, avoided properly.
for _, network := range runtimeNetworks {
b.WriteString(fmt.Sprintf("\t\t# %s\n", network.why))
b.WriteString(fmt.Sprintf("\t\tip saddr %s accept\n", network.cidr))
// Only when there is a link to name. An empty set is a line nftables refuses, and a rule set
// that does not load is a machine filtering nothing while its unit reports success — so the
// chain denies rather than renders nonsense. Composing a declaration for a machine that has
// named none is refused upstream, so this is a floor and not a path anything travels.
if inward != "" {
b.WriteString("\t\t# this machine's own guests reaching outward: not a port opened to anybody\n")
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } accept\n", inward))
}
if len(rules) > 0 {
@@ -430,18 +479,6 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
return b.String()
}
// runtimeNetworks are the container runtime's own networks, which must keep working when the
// forward chain denies by default.
//
// Taken from what the system being replaced allows, which has been carrying this machine's traffic
// for months: the runtime's bridge range and the range its compose files are given. A machine whose
// runtime is configured with something else needs this to say so — which is a thing the mesh cannot
// derive and a reason this list is named here rather than computed.
var runtimeNetworks = []struct{ cidr, why string }{
{"172.16.0.0/12", "the container runtime's bridge networks"},
{"192.168.128.0/17", "the networks its compose files are given"},
}
// byFamily splits addresses into the two nftables understands separately.
//
// `ip saddr` and `ip6 saddr` are different matches, and one set holding both families is a syntax
@@ -19,7 +19,7 @@ func TestTheBrokersPortIsOpenedThoughNoModuleDeclaresIt(t *testing.T) {
// A machine on the private network, with one ordinary module rule, and nothing that mentions
// the broker — which is every machine.
rules := []Rule{{Port: 8080, From: FromMesh, Because: []string{"some-module"}}}
out := AsNftables(rules, []string{"10.42.0.1"}, false, []int{brokerPort})
out := AsNftables(rules, []string{"10.42.0.1"}, false, []int{brokerPort}, nil, "mesh0")
if !strings.Contains(out, "tcp dport 5671 accept") {
t.Fatalf("the broker's port is not opened, so no machine could enrol:\n%s", out)
@@ -48,7 +48,7 @@ func TestTheBrokersPortIsOpenedThoughNoModuleDeclaresIt(t *testing.T) {
// And a mesh that was never told about a broker still gets a ruleset, rather than an empty one or
// a panic. A control plane in that state cannot issue tokens either, which is where it surfaces.
func TestNoBrokerMeansNoFoundationRuleRatherThanNoRuleset(t *testing.T) {
out := AsNftables(nil, []string{"10.42.0.1"}, false, nil)
out := AsNftables(nil, []string{"10.42.0.1"}, false, nil, nil, "mesh0")
if !strings.Contains(out, "table inet mesh") {
t.Fatalf("no ruleset at all:\n%s", out)
}
+123 -21
View File
@@ -79,7 +79,7 @@ func TestTwoModulesWantingOnePortAreBothNamed(t *testing.T) {
t.Fatalf("a module that wanted this port open is not named: %+v", rules[0])
}
// The consequence, which is the reason this matters: removing web must not read as closing 443.
nft := AsNftables(rules, nil, false, nil)
nft := AsNftables(rules, nil, false, nil, nil, "mesh0")
if !strings.Contains(nft, "web") || !strings.Contains(nft, "board") {
t.Fatalf("the rendered rule set does not name both sources:\n%s", nft)
}
@@ -107,7 +107,7 @@ func TestAPortOpenToEveryoneIsNotAlsoRestrictedToTheMesh(t *testing.T) {
func TestWhatNoModuleDeclaredIsClosed(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
}}, nil), []string{"198.51.100.2"}, false, nil)
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
// Naming the chain, not just the policy: the forward chain drops too, and an assertion on
// "policy drop" alone passes while the input chain accepts everything. It did, once, here.
if !strings.Contains(nft, "type filter hook input priority filter; policy drop;") {
@@ -134,7 +134,7 @@ func TestWhatNoModuleDeclaredIsClosed(t *testing.T) {
// `flush ruleset` would do the first and not the second: it empties every table on the machine,
// including the ones the container runtime writes for its bridges.
func TestReloadingReplacesOnlyTheMeshsOwnRules(t *testing.T) {
nft := AsNftables(nil, nil, false, nil)
nft := AsNftables(nil, nil, false, nil, nil, "mesh0")
if strings.Contains(nft, "flush ruleset") {
t.Fatalf("loading the rule set empties every table on the machine:\n%s", nft)
}
@@ -160,22 +160,122 @@ func TestReloadingReplacesOnlyTheMeshsOwnRules(t *testing.T) {
// So the chain exists and denies by default, and the runtime's own networks are allowed explicitly
// — which is how the system being replaced has been doing it on these machines for months.
func TestWhatIsForwardedIsGovernedToo(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil)
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "hook forward priority filter; policy drop") {
t.Fatalf("forwarded traffic is not governed, so container ports are open:\n%s", nft)
}
}
// And containers keep working, which is the whole reason the chain was left out before.
func TestTheRuntimesOwnNetworksKeepWorking(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil)
for _, network := range []string{"172.16.0.0/12", "192.168.128.0/17"} {
if !strings.Contains(nft, "ip saddr "+network+" accept") {
t.Fatalf("%s is not allowed, so denying by default stops every container:\n%s", network, nft)
// And this machine's own guests keep working, which is the whole reason the chain was left out
// before — by not being mentioned (novox/hq ADR 0140).
//
// It used to be done by naming the address ranges they sit on: two fixed here and the rest recorded
// per machine. That list broke a workstation's containers at a flip and could not be made correct,
// because a range describes one machine and cannot tell a network the mesh made from one a
// predecessor left behind. What replaced it is a single line about the links traffic arrives on.
func TestThisMachinesOwnGuestsKeepWorkingWithoutBeingNamed(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
if !strings.Contains(nft, `iifname != { "eth0", "mesh0" } accept`) {
t.Fatalf("what did not arrive from outside is not accepted, so this machine's own guests "+
"reach nothing:\n%s", nft)
}
}
// No address of a machine's own networks appears anywhere in a rendered filter.
//
// This is the assertion that fails against the previous behaviour, and it is why it is written on
// the text rather than on an outcome: the two ranges were a constant in this file, so nothing but
// reading the output catches one creeping back in.
func TestNoNetworkOfTheMachinesOwnIsNamed(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
for _, gone := range []string{"172.16.0.0/12", "192.168.128.0/17", "saddr 192.168", "saddr 172."} {
if strings.Contains(nft, gone) {
t.Fatalf("%q is named, and a range describes one machine and goes stale in silence:\n%s",
gone, nft)
}
}
}
// **The tunnel is constrained, not treated as inside.**
//
// Accepting everything arriving over the private network would make a port nothing declares
// reachable from every machine in the mesh — the derivation abandoned, and a rule that reads as a
// restriction while restricting nothing. So the tunnel is named beside the outward links, and
// traffic arriving on it meets the declared rules like anything else.
func TestTheTunnelIsConstrainedLikeAnOutwardLink(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
line := `iifname != { "eth0", "mesh0" } accept`
if !strings.Contains(nft, line) {
t.Fatalf("the tunnel is not constrained, so an undeclared port is reachable from any "+
"machine in the mesh:\n%s", nft)
}
}
// A machine with two links facing outside has both constrained. Asserted on the one line, because a
// rule covering one and not the other would leave a machine filtering half of what reaches it.
func TestEveryOutwardLinkIsConstrained(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0", "wlan0"}, "mesh0")
if !strings.Contains(nft, `iifname != { "eth0", "wlan0", "mesh0" } accept`) {
t.Fatalf("not every outward link is constrained:\n%s", nft)
}
}
// A guest asks its host for an address and for names, and those two arrive at the input chain. Asked
// for by the link they arrive on, so a resolver bound anywhere but an outward link keeps answering.
func TestGuestsMayAskTheirHostForAnAddressAndNames(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
for _, want := range []string{
`iifname != { "eth0", "mesh0" } udp dport { 53, 67 } accept`,
`iifname != { "eth0", "mesh0" } tcp dport 53 accept`,
} {
if !strings.Contains(nft, want) {
t.Fatalf("a guest cannot ask its host for an address or a name, which is not a closed "+
"port but a network that does not work:\n%s", nft)
}
}
}
// With no link named at all the chain denies rather than rendering an empty set, which nftables
// refuses — and a rule set that does not load is a machine filtering nothing while its unit reports
// success. Composing a declaration for such a machine is refused upstream; this is the floor.
func TestNoLinkNamedRendersNoCatchAllRatherThanAnEmptySet(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, nil, "")
if strings.Contains(nft, "{ }") || strings.Contains(nft, "iifname != {}") {
t.Fatalf("an empty set is rendered, which nftables refuses:\n%s", nft)
}
if !strings.Contains(nft, "hook forward priority filter; policy drop") {
t.Fatalf("the forward chain does not deny:\n%s", nft)
}
}
// A machine that has not said which links face outside is sent no filter, and the refusal names the
// module that would have loaded it so the reader knows what is being withheld.
func TestAMachineThatNamedNoOutwardLinkIsSentNoFilter(t *testing.T) {
r := Resolution{Node: "anchor", Modules: []Manifest{
{Module: "nftables", Filtering: &Filtering{Into: "/etc/mesh/filter.nft"}},
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
}}
_, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}, TunnelInterface: "mesh0"})
if err == nil {
t.Fatal("a machine that named no outward link was sent a filter written around none")
}
for _, want := range []string{"anchor", "nftables", "face outside"} {
if !strings.Contains(err.Error(), want) {
t.Fatalf("the refusal does not say %q: %v", want, err)
}
}
}
// And a machine that names none but loads no filter is not refused: there is nothing to write.
func TestAMachineWithNoFilterModuleIsNotRefused(t *testing.T) {
r := Resolution{Node: "anchor", Modules: []Manifest{
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
}}
if _, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}}); err != nil {
t.Fatalf("a machine that loads no filter was refused one: %v", err)
}
}
// A published port is matched by what the client asked for, not by where the packet ends up.
//
// The runtime rewrites the destination before this chain sees it, so a rule naming the published
@@ -183,7 +283,7 @@ func TestTheRuntimesOwnNetworksKeepWorking(t *testing.T) {
func TestAPublishedPortIsMatchedByWhatWasAskedFor(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "web", Listens: []Listening{{Port: 8080, From: FromEverywhere}}},
}}, nil), []string{"198.51.100.2"}, false, nil)
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "ct original proto-dst 8080 accept") {
t.Fatalf("the forwarded rule does not match the port a client asked for:\n%s", nft)
}
@@ -193,7 +293,7 @@ func TestAPublishedPortIsMatchedByWhatWasAskedFor(t *testing.T) {
func TestAMeshScopedPortIsMeshScopedWhenForwarded(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
}}, nil), []string{"198.51.100.2"}, false, nil)
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "ip saddr { 198.51.100.2 } ct original proto-dst 5432 accept") {
t.Fatalf("a mesh-only port is reachable from anywhere once forwarded:\n%s", nft)
}
@@ -203,7 +303,7 @@ func TestAMeshScopedPortIsMeshScopedWhenForwarded(t *testing.T) {
func TestFromTheMeshIsTheNodesTheMeshKnows(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
}}, nil), []string{"198.51.100.2", "198.51.100.3"}, false, nil)
}}, nil), []string{"198.51.100.2", "198.51.100.3"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "ip saddr { 198.51.100.2, 198.51.100.3 } tcp dport 5432 accept") {
t.Fatalf("a mesh-scoped port was not restricted to the mesh's addresses:\n%s", nft)
}
@@ -213,7 +313,7 @@ func TestFromTheMeshIsTheNodesTheMeshKnows(t *testing.T) {
func TestAMeshPortOnANodeWithNoMeshIsClosedAndSaysSo(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
}}, nil), nil, false, nil)
}}, nil), nil, false, nil, nil, "mesh0")
if strings.Contains(nft, "dport 5432 accept") {
t.Fatalf("a port meant for the mesh was opened to everything:\n%s", nft)
}
@@ -226,7 +326,7 @@ func TestAMeshPortOnANodeWithNoMeshIsClosedAndSaysSo(t *testing.T) {
func TestAMachineScopedPortIsNotOpened(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "cache", Listens: []Listening{{Port: 6379, From: FromMachine}}},
}}, nil), []string{"198.51.100.2"}, false, nil)
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
if strings.Contains(nft, "dport 6379 accept") {
t.Fatalf("a port for this machine only was opened to the network:\n%s", nft)
}
@@ -238,7 +338,8 @@ func TestTheModuleAskingForTheRuleSetGetsEveryModulesPorts(t *testing.T) {
{Module: "firewall", Filtering: &Filtering{Into: "/etc/mesh/filter.nft"}},
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
}}
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}})
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"},
OutwardLinks: []string{"eth0"}, TunnelInterface: "mesh0"})
if err != nil {
t.Fatalf("declaration: %v", err)
}
@@ -268,7 +369,7 @@ func TestAskingForTheRuleSetWithNowhereToPutItIsRefused(t *testing.T) {
func TestAMeshOnBothAddressFamiliesRendersBoth(t *testing.T) {
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
}}, nil), []string{"198.51.100.2", "2001:db8::2"}, false, nil)
}}, nil), []string{"198.51.100.2", "2001:db8::2"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "ip saddr { 198.51.100.2 } tcp dport 5432 accept") {
t.Fatalf("the machines with v4 addresses were dropped:\n%s", nft)
}
@@ -296,7 +397,8 @@ func TestWhatTheMeshComputesIsAppliedBeforeWhatTheModuleDeclared(t *testing.T) {
"restart-on": []any{"filtering"}},
},
}}}
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}})
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"},
OutwardLinks: []string{"eth0"}, TunnelInterface: "mesh0"})
if err != nil {
t.Fatalf("declaration: %v", err)
}
@@ -672,7 +774,7 @@ func TestExposureRefusesAPortNotListenedOnAndABadSource(t *testing.T) {
// loading the rules lives on conntrack until it drops, and then the machine is reached from a
// rescue console (novox/hq issue 047).
func TestSSHIsOpenFromTheMeshEvenWhenNothingIsAssigned(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2", "198.51.100.3"}, false, nil)
nft := AsNftables(nil, []string{"198.51.100.2", "198.51.100.3"}, false, nil, nil, "mesh0")
if !strings.Contains(nft, "ip saddr { 198.51.100.2, 198.51.100.3 } tcp dport 22 accept") {
t.Fatalf("ssh is not open to the mesh, so a machine can lock everyone out:\n%s", nft)
}
@@ -685,7 +787,7 @@ func TestSSHIsOpenFromTheMeshEvenWhenNothingIsAssigned(t *testing.T) {
// And from outside as well, on a machine that faces outward — because that is the way in when the
// private network is the thing that broke.
func TestSSHIsOpenFromOutsideOnAMachineThatFacesIt(t *testing.T) {
nft := AsNftables(nil, []string{"198.51.100.2"}, true, nil)
nft := AsNftables(nil, []string{"198.51.100.2"}, true, nil, nil, "mesh0")
if !strings.Contains(nft, "\t\ttcp dport 22 accept") {
t.Fatalf("a machine reachable from outside does not answer ssh there:\n%s", nft)
}
@@ -697,7 +799,7 @@ func TestSSHIsOpenFromOutsideOnAMachineThatFacesIt(t *testing.T) {
// to narrow the rule to, so narrowing it shuts the port entirely — on the first machine anybody
// adopts, reached over the network, closed by the act of adopting it.
func TestSSHIsNeverLeftWithoutARule(t *testing.T) {
nft := AsNftables(nil, nil, false, nil)
nft := AsNftables(nil, nil, false, nil, nil, "mesh0")
if !strings.Contains(nft, "tcp dport 22 accept") {
t.Fatalf("a machine with no mesh addresses has no ssh rule, so adopting it locks it:\n%s", nft)
}
+1 -1
View File
@@ -12,5 +12,5 @@ func TestPrintRehearsalRuleset(t *testing.T) {
rules := mustFilter(t, Resolution{Modules: []Manifest{
{Module: "pub", Listens: []Listening{{Port: 8099, From: FromMesh, Why: "the thing it serves"}}},
}}, nil)
t.Log("\n" + AsNftables(rules, []string{"192.0.2.20"}, true, nil))
t.Log("\n" + AsNftables(rules, []string{"192.0.2.20"}, true, nil, nil, "mesh0"))
}
@@ -0,0 +1,19 @@
-- The networks a machine routes for what it hosts, beyond the container runtime's own defaults.
--
-- novox/hq ADR 0137. The derived packet filter denies forwarding by default and then allows the
-- container runtime's two default pools, named in the controller's code with a comment saying that
-- a machine configured otherwise "needs this to say so" — and no way to say it. So the filter was
-- correct only on a machine whose runtime used the defaults, and silently wrong on any other.
--
-- Measured on 2026-09-28: flipping a workstation to the derived filter cut egress for five of its
-- container networks and for every network its test beds create, because those are allocated from
-- ranges the two defaults do not cover. Nothing reported a fault; the containers simply could not
-- reach anything.
--
-- A node-level fact, beside the node's public domain and for the same reason: it is a property of
-- the machine, not of whichever module happens to load the filter today. Swapping that module must
-- not lose it.
--
-- Null for a machine that routes nothing but the runtime's defaults, which is the ordinary case and
-- what every machine held before this column existed.
alter table node add column routed_networks jsonb;
@@ -0,0 +1,26 @@
-- Which of a machine's links face outside it, replacing the networks it was told to say it routes.
--
-- novox/hq ADR 0140, superseding 0137 and 0139. The derived filter blocked everything passing
-- through a machine and then allowed the machine's own containers back by naming the address ranges
-- they sit on: two ranges fixed in the controller's source, the rest recorded by 0043's column.
--
-- Every route to a correct list fails. A constant describes one machine. A recorded range goes stale
-- in silence, and cannot tell a network the mesh made from one a predecessor left behind — measured
-- on the control-node, where six ranges fall outside the constants and two of the six belong to
-- services the mesh does not run. Generating the list from the modules put half the rule set on the
-- machine.
--
-- The list should not exist, because the mesh has no position on a container reaching outward: that
-- is not a port opened to anybody. The filter constrains what arrives from OUTSIDE the machine and
-- says nothing about what did not, which needs one fact instead of a list — which links "outside"
-- arrives on.
--
-- Reported by the machine on every apply, never recorded by hand, so it cannot go stale. Null for a
-- machine that has not reported yet; the mesh composes no filter for such a machine and leaves the
-- one it has, because a rule written around a link with no name is a rule set that does not load.
alter table node add column outward_links jsonb;
-- What 0043 recorded is not migrated into it. The ranges answered a question that no longer exists,
-- and every machine that named one keeps working without it: the traffic those ranges allowed is now
-- allowed by not having arrived from outside.
alter table node drop column routed_networks;
+55
View File
@@ -518,6 +518,61 @@ func (i *Inventory) PublicDomainOf(ctx context.Context, name string) (string, er
return *domain, nil
}
// RecordOutwardLinks keeps the links a machine reported as facing outside it.
//
// A reported fact, not a setting (novox/hq ADR 0140). It replaces the networks a machine used to be
// told to say it routes: the filter blocked everything passing through and then allowed the machine's
// own containers back by naming their address ranges, and every way of keeping that list correct
// failed — a constant describes one machine, and a recorded range goes stale in silence. The filter
// now constrains what arrives from outside and says nothing about what did not, and the one thing it
// needs is which links "outside" arrives on. The machine reads that from its own routing table on
// every apply, so it cannot go stale and nobody types it.
//
// An empty list clears it, which is what a machine with no route off itself reports. The mesh then
// composes no filter for that machine at all.
func (i *Inventory) RecordOutwardLinks(ctx context.Context, id string, links []string) error {
var kept []string
for _, name := range links {
if name = strings.TrimSpace(name); name != "" {
kept = append(kept, name)
}
}
if len(kept) == 0 {
_, err := i.store.Pool().Exec(ctx,
`update node set outward_links = null where id = $1`, id)
return err
}
body, err := json.Marshal(kept)
if err != nil {
return err
}
_, err = i.store.Pool().Exec(ctx,
`update node set outward_links = $2 where id = $1`, id, string(body))
return err
}
// OutwardLinksOf is the links a machine reported as facing outside it, empty when it has reported
// none — which is a machine the mesh composes no filter for.
func (i *Inventory) OutwardLinksOf(ctx context.Context, name string) ([]string, error) {
var body []byte
err := i.store.Pool().QueryRow(ctx,
`select outward_links from node where name = $1`, name).Scan(&body)
if errors.Is(err, pgx.ErrNoRows) {
return nil, fmt.Errorf("%w: %s", ErrNoSuchNode, name)
}
if err != nil {
return nil, err
}
if len(body) == 0 {
return nil, nil
}
var links []string
if err := json.Unmarshal(body, &links); err != nil {
return nil, fmt.Errorf("the outward links recorded for %s are not a list: %w", name, err)
}
return links, nil
}
// RecordOverlayKey keeps the public half a node generated.
func (i *Inventory) RecordOverlayKey(ctx context.Context, node, key string) error {
if strings.TrimSpace(key) == "" {
+11
View File
@@ -301,6 +301,17 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err err
return false, err
}
}
// Which of its links face outside (novox/hq ADR 0140), whenever it says so. Recorded on every
// report that carries it, adopted or converged, because the filter the mesh composes is written
// around it — and never cleared by a report that carries none, which is every bare word that the
// node is there. A machine whose routing table it could not read reports nothing rather than
// guessing, and keeps whatever it last said; a machine with genuinely no route off itself is one
// the mesh composes no filter for at all.
if len(report.Outward) > 0 {
if err := e.Inventory.RecordOutwardLinks(ctx, node.ID, report.Outward); err != nil {
return false, err
}
}
// What it says about the tunnel it carried (novox/hq ADR 0105), whenever it says it.
if report.Tunnel != nil {
if err := e.Inventory.RecordCarriedTunnel(ctx, node.ID, inventory.Carried{
+14
View File
@@ -170,6 +170,20 @@ type Report struct {
// Firewall is the firewall found on the machine — "ufw" or "none" — and empty on a node that
// was never asked, which is every converged one.
Firewall string `json:"firewall,omitempty"`
// Outward is the links on this machine that face outside it — the ones carrying a default route
// (novox/hq ADR 0140). Every node reports it, adopted or converged, because the filter the mesh
// composes for it is written around these and nothing else.
//
// **It replaces a list of addresses.** The filter used to block everything passing through the
// machine and then allow the machine's own containers back by naming the ranges they sit on. A
// range describes one machine and goes stale in silence; the link carrying the default route is
// read afresh on every report and does not change when a module is added or removed.
//
// Empty means the machine has not said. The mesh composes no filter for such a machine and
// leaves the one it has: a rule written around a link with no name is a rule set that does not
// load, and that is a machine filtering nothing while its unit reports success.
Outward []string `json:"outward,omitempty"`
// Reachable is what can be reached on the machine now: every listening socket and every
// published container port. Only an adopted node reports it; it is what converging previews.
Reachable []Reach `json:"reachable,omitempty"`
+2 -1
View File
@@ -346,7 +346,8 @@ func (s *Server) reported(ctx context.Context, m Control) {
// whenever it arrives, which is the behaviour the mesh has had all along.
func staleAgainst(report Report) string {
if report.Rekey != nil || report.Tunnel != nil || len(report.Held) > 0 ||
report.Firewall != "" || len(report.Reachable) > 0 || len(report.Carried) > 0 {
report.Firewall != "" || len(report.Reachable) > 0 || len(report.Carried) > 0 ||
len(report.Outward) > 0 {
return ""
}
return report.Declared