diff --git a/client/internal/dns/host_windows.go b/client/internal/dns/host_windows.go index 4f6ece532..39f4e8182 100644 --- a/client/internal/dns/host_windows.go +++ b/client/internal/dns/host_windows.go @@ -32,9 +32,15 @@ var ( ) const ( - dnsPolicyConfigMatchPath = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig\NetBird-Match` + // nrptKeyPrefix starts the name of every NRPT rule key this client creates. + // Older versions used different layouts under the same prefix: a single + // unsuffixed key, then one key per domain, now one key per batch of domains. + nrptKeyPrefix = "NetBird-Match" + + dnsPolicyConfigRoot = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig` + dnsPolicyConfigMatchPath = dnsPolicyConfigRoot + `\` + nrptKeyPrefix gpoDnsPolicyRoot = `SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig` - gpoDnsPolicyConfigMatchPath = gpoDnsPolicyRoot + `\NetBird-Match` + gpoDnsPolicyConfigMatchPath = gpoDnsPolicyRoot + `\` + nrptKeyPrefix dnsPolicyConfigVersionKey = "Version" dnsPolicyConfigVersionValue = 2 @@ -73,7 +79,6 @@ type registryConfigurator struct { guid string routingAll bool gpo bool - nrptEntryCount int origNameservers []netip.Addr } @@ -306,14 +311,9 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager } if len(matchDomains) != 0 { - count, err := r.addDNSMatchPolicy(matchDomains, config.ServerIP) - // Update count even on error to ensure cleanup covers partially created rules - r.nrptEntryCount = count - if err != nil { + if err := r.addDNSMatchPolicy(matchDomains, config.ServerIP); err != nil { return fmt.Errorf("add dns match policy: %w", err) } - } else { - r.nrptEntryCount = 0 } r.updateState(stateManager) @@ -329,9 +329,8 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager func (r *registryConfigurator) updateState(stateManager *statemanager.Manager) { if err := stateManager.UpdateState(&ShutdownState{ - Guid: r.guid, - GPO: r.gpo, - NRPTEntryCount: r.nrptEntryCount, + Guid: r.guid, + GPO: r.gpo, }); err != nil { log.Errorf("failed to update shutdown state: %s", err) } @@ -346,7 +345,7 @@ func (r *registryConfigurator) addDNSSetupForAll(ip netip.Addr) error { return nil } -func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) (int, error) { +func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) error { // if the gpo key is present, we need to put our DNS settings there, otherwise our config might be ignored // see https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-gpnrpt/8cc31cb9-20cb-4140-9e85-3e08703b4745 @@ -363,19 +362,17 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, ruleIndex) if err := r.configureDNSPolicy(localPath, batchDomains, ip); err != nil { - return ruleIndex, fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err) + return fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err) } - // Increment immediately so the caller's cleanup path knows about this rule - ruleIndex++ - if r.gpo { if err := r.configureDNSPolicy(gpoPath, batchDomains, ip); err != nil { - return ruleIndex, fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex-1, err) + return fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex, err) } } - log.Debugf("added NRPT rule %d with %d domains", ruleIndex-1, len(batchDomains)) + log.Debugf("added NRPT rule %d with %d domains", ruleIndex, len(batchDomains)) + ruleIndex++ } if r.gpo { @@ -385,7 +382,7 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr } log.Infof("added %d NRPT rules for %d domains", ruleIndex, len(domains)) - return ruleIndex, nil + return nil } func (r *registryConfigurator) configureDNSPolicy(policyPath string, domains []string, ip netip.Addr) error { @@ -518,28 +515,28 @@ func (r *registryConfigurator) restoreHostDNS() error { return nil } +// removeDNSMatchPolicies deletes every NRPT rule this client may have created, +// from the local and the GPO policy store. The rules are found by enumerating +// the registry, the only authoritative record of what was written. Cleanup must +// not depend on a rule count: the in-memory one is scoped to a single +// registryConfigurator and the persisted one is deleted on every clean +// disconnect, and a rule left behind keeps resolving names over an interface +// that is gone, until reboot discards the volatile key. func (r *registryConfigurator) removeDNSMatchPolicies() error { var merr *multierror.Error - // Try to remove the base entries (for backward compatibility) - if err := removeRegistryKeyFromDNSPolicyConfig(dnsPolicyConfigMatchPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove local base entry: %w", err)) - } - - if err := removeRegistryKeyFromDNSPolicyConfig(gpoDnsPolicyConfigMatchPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove GPO base entry: %w", err)) - } - - for i := 0; i < r.nrptEntryCount; i++ { - localPath := fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i) - gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, i) - - if err := removeRegistryKeyFromDNSPolicyConfig(localPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove local entry %d: %w", i, err)) + for _, root := range []string{dnsPolicyConfigRoot, gpoDnsPolicyRoot} { + names, err := listNRPTRuleKeys(root) + if err != nil { + merr = multierror.Append(merr, fmt.Errorf("list rule keys under %s: %w", root, err)) + continue } - if err := removeRegistryKeyFromDNSPolicyConfig(gpoPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove GPO entry %d: %w", i, err)) + for _, name := range names { + path := root + `\` + name + if err := removeRegistryKeyFromDNSPolicyConfig(path); err != nil { + merr = multierror.Append(merr, fmt.Errorf("remove entry %s: %w", path, err)) + } } } @@ -554,6 +551,33 @@ func (r *registryConfigurator) restoreUncleanShutdownDNS() error { return r.restoreHostDNS() } +// listNRPTRuleKeys returns the names of our NRPT rule keys under a policy store +// root. A root that cannot be opened holds nothing to clean up: the GPO store is +// absent on a machine without DNS Client policy. +func listNRPTRuleKeys(root string) ([]string, error) { + k, err := registry.OpenKey(registry.LOCAL_MACHINE, root, registry.ENUMERATE_SUB_KEYS) + if err != nil { + log.Debugf("failed to open HKEY_LOCAL_MACHINE\\%s: %v", root, err) + return nil, nil + } + defer closer(k) + + names, err := k.ReadSubKeyNames(-1) + if err != nil { + return nil, fmt.Errorf("read subkey names: %w", err) + } + + var ruleKeys []string + for _, name := range names { + // registry key names are case insensitive + if strings.HasPrefix(strings.ToLower(name), strings.ToLower(nrptKeyPrefix)) { + ruleKeys = append(ruleKeys, name) + } + } + + return ruleKeys, nil +} + func removeRegistryKeyFromDNSPolicyConfig(regKeyPath string) error { k, err := registry.OpenKey(registry.LOCAL_MACHINE, regKeyPath, registry.QUERY_VALUE) if err != nil { diff --git a/client/internal/dns/host_windows_test.go b/client/internal/dns/host_windows_test.go index 3cd2b1bd5..4683f20f9 100644 --- a/client/internal/dns/host_windows_test.go +++ b/client/internal/dns/host_windows_test.go @@ -25,7 +25,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { // Create a test interface registry key so updateSearchDomains doesn't fail testGUID := "{12345678-1234-1234-1234-123456789ABC}" - interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID + interfacePath := interfaceConfigPath + `\` + testGUID testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE) require.NoError(t, err, "Should create test interface registry key") testKey.Close() @@ -56,7 +56,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { require.NoError(t, err) // Verify 3 NRPT rules exist - assert.Equal(t, 3, cfg.nrptEntryCount, "Should create 3 NRPT rules for 125 domains") + assert.Equal(t, 3, countNRPTRuleKeys(t), "Should create 3 NRPT rules for 125 domains") for i := 0; i < 3; i++ { exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i)) require.NoError(t, err) @@ -81,7 +81,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { require.NoError(t, err) // Verify first 2 NRPT rules exist - assert.Equal(t, 2, cfg.nrptEntryCount, "Should create 2 NRPT rules for 75 domains") + assert.Equal(t, 2, countNRPTRuleKeys(t), "Should create 2 NRPT rules for 75 domains") for i := 0; i < 2; i++ { exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i)) require.NoError(t, err) @@ -106,9 +106,65 @@ func registryKeyExists(path string) (bool, error) { return true, nil } +// TestNRPTCleanupWithoutRuleCount verifies that rules written by a previous run +// are removed by a configurator that has no record of how many there are: an +// unclean exit loses the in-memory count and a clean disconnect deletes the +// persisted one, so cleanup cannot depend on either. +func TestNRPTCleanupWithoutRuleCount(t *testing.T) { + if testing.Short() { + t.Skip("skipping registry integration test in short mode") + } + + defer cleanupRegistryKeys(t) + cleanupRegistryKeys(t) + + testIP := netip.MustParseAddr("100.64.0.1") + + // 75 domains produce two indexed rules, as the current layout does + domains := make([]string, 75) + for i := range domains { + domains[i] = fmt.Sprintf(".domain%d.com", i+1) + } + + previousRun := ®istryConfigurator{} + require.NoError(t, previousRun.addDNSMatchPolicy(domains, testIP)) + + // the unsuffixed key an older version would have written + require.NoError(t, previousRun.configureDNSPolicy(dnsPolicyConfigMatchPath, []string{".legacy.example.com"}, testIP)) + + // a policy owned by someone else, which cleanup must not touch + foreignPath := dnsPolicyConfigRoot + `\DnsPolicyConfigTestForeign` + foreignKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, foreignPath, registry.SET_VALUE) + require.NoError(t, err, "Should create foreign policy key") + foreignKey.Close() + defer func() { + _ = registry.DeleteKey(registry.LOCAL_MACHINE, foreignPath) + }() + + require.Equal(t, 3, countNRPTRuleKeys(t), "Should have two indexed rules and the legacy one") + + // a configurator that never applied a DNS config, as one built after a + // restart or from a shutdown state without a count is + freshRun := ®istryConfigurator{} + require.NoError(t, freshRun.removeDNSMatchPolicies()) + + assert.Equal(t, 0, countNRPTRuleKeys(t), "Should remove every rule left by the previous run") + + exists, err := registryKeyExists(foreignPath) + require.NoError(t, err) + assert.True(t, exists, "Should not remove a policy that is not ours") +} + +func countNRPTRuleKeys(t *testing.T) int { + t.Helper() + + names, err := listNRPTRuleKeys(dnsPolicyConfigRoot) + require.NoError(t, err, "Should list NRPT rule keys") + return len(names) +} + func cleanupRegistryKeys(*testing.T) { - // Clean up more entries to account for batching tests with many domains - cfg := ®istryConfigurator{nrptEntryCount: 20} + cfg := ®istryConfigurator{} _ = cfg.removeDNSMatchPolicies() } @@ -125,7 +181,7 @@ func TestNRPTDomainBatching(t *testing.T) { // Create a test interface registry key so updateSearchDomains doesn't fail testGUID := "{12345678-1234-1234-1234-123456789ABC}" - interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID + interfacePath := interfaceConfigPath + `\` + testGUID testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE) require.NoError(t, err, "Should create test interface registry key") testKey.Close() @@ -193,7 +249,7 @@ func TestNRPTDomainBatching(t *testing.T) { require.NoError(t, err) // Verify that exactly expectedRuleCount rules were created - assert.Equal(t, tc.expectedRuleCount, cfg.nrptEntryCount, + assert.Equal(t, tc.expectedRuleCount, countNRPTRuleKeys(t), "Should create %d NRPT rules for %d domains", tc.expectedRuleCount, tc.domainCount) // Verify all expected rules exist diff --git a/client/internal/dns/unclean_shutdown_windows.go b/client/internal/dns/unclean_shutdown_windows.go index 24a9eca50..ab0b2cc63 100644 --- a/client/internal/dns/unclean_shutdown_windows.go +++ b/client/internal/dns/unclean_shutdown_windows.go @@ -5,9 +5,8 @@ import ( ) type ShutdownState struct { - Guid string - GPO bool - NRPTEntryCount int + Guid string + GPO bool } func (s *ShutdownState) Name() string { @@ -16,9 +15,8 @@ func (s *ShutdownState) Name() string { func (s *ShutdownState) Cleanup() error { manager := ®istryConfigurator{ - guid: s.Guid, - gpo: s.GPO, - nrptEntryCount: s.NRPTEntryCount, + guid: s.Guid, + gpo: s.GPO, } if err := manager.restoreUncleanShutdownDNS(); err != nil {