Group the HostInfo fields the packet paths touch

.github/backport.sh

@@ -1,142 +0,0 @@
-#!/usr/bin/env bash
-#
-# Backport a merged PR to a release branch.
-#
-# Cherry-picks the merge commit of a merged PR onto release-1.11 and opens a
-# backport PR, mirroring the shape of #1842.
-#
-# Usage: ./backport.sh <pr-number> [target-version] [--continue]
-#   pr-number       The merged PR to backport
-#   target-version  Release version to target (default: 1.11)
-#   --continue      Resume after resolving cherry-pick conflicts: assumes the
-#                   fixes are staged, runs `git cherry-pick --continue`, and
-#                   proceeds to push and open the backport PR.
-#
-# Requires: gh (authenticated), git, jq.
-
-set -euo pipefail
-
-PR_NUMBER=${1:?usage: backport.sh <pr-number> [target-version] [--continue]}
-shift
-CONTINUE=0
-TARGET_VERSION=""
-for arg in "$@"; do
-  case "$arg" in
-    --continue) CONTINUE=1 ;;
-    *) TARGET_VERSION=$arg ;;
-  esac
-done
-
-for cmd in gh git jq; do
-  command -v "$cmd" >/dev/null || { echo "error: $cmd is required" >&2; exit 1; }
-done
-
-# Pull the source PR's metadata. Refuse to backport a PR that never merged.
-pr_json=$(gh pr view "$PR_NUMBER" --json title,body,mergedAt,mergeCommit,milestone)
-PR_TITLE=$(jq -r '.title' <<<"$pr_json")
-PR_BODY=$(jq -r '.body' <<<"$pr_json")
-MERGE_SHA=$(jq -r '.mergeCommit.oid // empty' <<<"$pr_json")
-PR_MILESTONE=$(jq -r '.milestone.title // empty' <<<"$pr_json")
-
-if [ "$(jq -r '.mergedAt // empty' <<<"$pr_json")" = "" ] || [ -z "$MERGE_SHA" ]; then
-  echo "error: PR #${PR_NUMBER} is not merged (no merge commit to cherry-pick)" >&2
-  exit 1
-fi
-
-# Default the target to one minor below the PR's milestone: a PR landing in
-# v1.12.0 backports to release-1.11. An explicit target-version arg overrides.
-if [ -z "$TARGET_VERSION" ]; then
-  if [[ $PR_MILESTONE =~ ^v?([0-9]+)\.([0-9]+) ]]; then
-    TARGET_VERSION="${BASH_REMATCH[1]}.$(( BASH_REMATCH[2] - 1 ))"
-  else
-    echo "error: PR #${PR_NUMBER} has no v<major>.<minor>.* milestone to infer the target from." >&2
-    echo "Pass the target version explicitly, e.g. $0 ${PR_NUMBER} 1.11" >&2
-    exit 1
-  fi
-fi
-TARGET_BRANCH="release-${TARGET_VERSION}"
-
-# Slug from the PR title: lower-case, non-alphanumerics to dashes, trimmed.
-slug=$(printf '%s' "$PR_TITLE" \
-  | tr '[:upper:]' '[:lower:]' \
-  | sed -E 's/[^a-z0-9]+/-/g; s/^-+//; s/-+$//' \
-  | cut -c1-50 \
-  | sed -E 's/-+$//')
-BRANCH="backport-${TARGET_VERSION//./-}-${slug}"
-
-if [ "$CONTINUE" -eq 1 ]; then
-  # Resuming: the branch already exists and a cherry-pick is mid-conflict.
-  current=$(git rev-parse --abbrev-ref HEAD)
-  if [ "$current" != "$BRANCH" ]; then
-    echo "error: --continue expects to be on ${BRANCH}, but HEAD is ${current}" >&2
-    exit 1
-  fi
-  echo "Resuming backport of #${PR_NUMBER} on ${BRANCH}"
-  # Conflicts assumed resolved and staged; core.editor=true keeps the commit message.
-  git -c core.editor=true cherry-pick --continue
-else
-  # A fresh run switches branches and cherry-picks, so tracked changes must be
-  # clean. Untracked files are fine, and --continue is exempt (its resolved
-  # conflicts are meant to be staged).
-  if [ -n "$(git status --porcelain --untracked-files=no)" ]; then
-    echo "error: working tree has uncommitted changes to tracked files; commit or stash them first." >&2
-    exit 1
-  fi
-
-  echo "Backporting #${PR_NUMBER} (${MERGE_SHA}) onto ${TARGET_BRANCH} as ${BRANCH}"
-
-  git fetch origin
-  git checkout -b "$BRANCH" "origin/${TARGET_BRANCH}"
-
-  # -m 1 handles a real merge commit; plain cherry-pick handles a squash merge.
-  if ! { git cherry-pick -x -m 1 "$MERGE_SHA" 2>/dev/null || git cherry-pick -x "$MERGE_SHA"; }; then
-    echo "error: ${MERGE_SHA} did not cherry-pick cleanly onto ${TARGET_BRANCH}." >&2
-    echo "Resolve the conflicts, 'git add' them, then re-run:" >&2
-    echo "  $0 ${PR_NUMBER} ${TARGET_VERSION} --continue" >&2
-    exit 1
-  fi
-fi
-
-title="backport v${TARGET_VERSION}: ${PR_TITLE}"
-body=$(printf 'Backport from #%s to release v%s\n\n---\n\n%s' \
-  "$PR_NUMBER" "$TARGET_VERSION" "$PR_BODY")
-
-# Highest open milestone matching v<version>.* (e.g. v1.11.1), if any.
-MILESTONE=$(gh api "repos/{owner}/{repo}/milestones?state=open" \
-  --jq ".[].title | select(startswith(\"v${TARGET_VERSION}.\"))" \
-  | sort -V | tail -n1)
-milestone_args=()
-if [ -n "$MILESTONE" ]; then
-  milestone_args=(--milestone "$MILESTONE")
-else
-  echo "warning: no open milestone matching v${TARGET_VERSION}.* found; PR will have no milestone" >&2
-fi
-
-echo
-echo "About to run:"
-printf '  git push -u --force-with-lease origin %q\n' "$BRANCH"
-printf '  gh pr create --base %q --head %q --title %q --body %q' \
-  "$TARGET_BRANCH" "$BRANCH" "$title" "$body"
-[ -n "$MILESTONE" ] && printf ' --milestone %q' "$MILESTONE"
-printf '\n'
-echo
-read -r -p "Open this pull request? [y/N] " reply
-case "$reply" in
-  [yY] | [yY][eE][sS]) ;;
-  *) echo "Aborted. The cherry-pick is on local branch ${BRANCH}; push it manually if desired."; exit 0 ;;
-esac
-
-git push -u --force-with-lease origin "$BRANCH"
-
-gh pr create \
-  --base "$TARGET_BRANCH" \
-  --head "$BRANCH" \
-  --title "$title" \
-  --body "$body" \
-  ${milestone_args[@]+"${milestone_args[@]}"}
-
-# The backport now exists, so drop the label that flagged this PR for one.
-gh pr edit "$PR_NUMBER" --remove-label needs-backport
-
-# Switch back to the original branch we were on before doing the backport
-git checkout -

.github/workflows/release.yml

@@ -73,11 +73,8 @@ jobs:
   build-darwin:
     name: Build Universal Darwin
     env:
-      HAS_SIGNING_CREDS: ${{ secrets.APPLE_SIGNING_ROLE_ARN != '' }}
+      HAS_SIGNING_CREDS: ${{ secrets.AC_USERNAME != '' }}
     runs-on: macos-latest
-    permissions:
-      id-token: write
-      contents: read
     steps:
       - uses: actions/checkout@v7
 
@@ -86,68 +83,17 @@ jobs:
           go-version: '1.26'
           check-latest: true
 
-      # GitHub holds ARNs, not credentials, and ARNs outlive a rotation
-      - name: Configure AWS credentials
-        if: env.HAS_SIGNING_CREDS == 'true'
-        uses: aws-actions/configure-aws-credentials@v6
-        with:
-          role-to-assume: ${{ secrets.APPLE_SIGNING_ROLE_ARN }}
-          aws-region: us-east-2
-
-      # parse-json-secrets unpacks into SIGNING_* and ASC_*, masked on the way in
-      - name: Fetch signing credentials
-        if: env.HAS_SIGNING_CREDS == 'true'
-        uses: aws-actions/aws-secretsmanager-get-secrets@v3
-        with:
-          parse-json-secrets: true
-          secret-ids: |
-            SIGNING,${{ secrets.APPLE_SIGNING_DEVELOPER_ID_ARN }}
-            ASC,${{ secrets.APPLE_NOTARY_KEY_ARN }}
-
       - name: Import certificates
         if: env.HAS_SIGNING_CREDS == 'true'
         uses: Apple-Actions/import-codesign-certs@v7
         with:
-          p12-file-base64: ${{ env.SIGNING_P12_BASE64 }}
-          p12-password: ${{ env.SIGNING_PASSWORD }}
-
-      # The action imports but does not check the chain validates, which is how a p12
-      # missing its intermediate reaches a failing codesign
-      - name: Check the identity is usable
-        if: env.HAS_SIGNING_CREDS == 'true'
-        run: |
-          : "${SIGNING_IDENTITY_SHA1:?empty, so the secret has no identity_sha1}"
-          identities=$(security find-identity -v -p codesigning signing_temp.keychain)
-          case "$identities" in
-          *"$SIGNING_IDENTITY_SHA1"*) ;;
-          *) printf '%s\n' "$identities" >&2; exit 1 ;;
-          esac
-
-      # notarytool wants the key as a file
-      - name: Write the App Store Connect key
-        if: env.HAS_SIGNING_CREDS == 'true'
-        run: |
-          mkdir -p ~/private_keys
-          chmod 700 ~/private_keys
-          key_path="$HOME/private_keys/AuthKey_${ASC_KEY_ID}.p8"
-          (umask 077; printf '%s\n' "$ASC_PRIVATE_KEY" > "$key_path")
-          echo "ASC_P8=$key_path" >> "$GITHUB_ENV"
-
-      - name: Drop the credentials from the environment
-        if: env.HAS_SIGNING_CREDS == 'true'
-        run: |
-          # The action's own inventory, so a new field in a secret is covered
-          python3 -c '
-          import json, os
-          raw = os.environ.get("SECRETS_LIST_CLEAN_UP")
-          if raw is None and os.environ.get("SIGNING_P12_BASE64"):
-              raise SystemExit("SECRETS_LIST_CLEAN_UP is gone, fetched secrets are not being scrubbed")
-          keep = {"SIGNING_IDENTITY_SHA1", "ASC_KEY_ID", "ASC_ISSUER_ID"}
-          names = [n for n in json.loads(raw or "[]") if n not in keep]
-          print("\n".join(f"{n}=" for n in dict.fromkeys(names)))
-          ' >> "$GITHUB_ENV"
+          p12-file-base64: ${{ secrets.APPLE_DEVELOPER_CERTIFICATE_P12_BASE64 }}
+          p12-password: ${{ secrets.APPLE_DEVELOPER_CERTIFICATE_PASSWORD }}
 
       - name: Build, sign, and notarize
+        env:
+          AC_USERNAME: ${{ secrets.AC_USERNAME }}
+          AC_PASSWORD: ${{ secrets.AC_PASSWORD }}
         run: |
           rm -rf release
           mkdir release
@@ -156,34 +102,17 @@ jobs:
           lipo -create -output ./release/nebula ./build/darwin-amd64/nebula ./build/darwin-arm64/nebula
           lipo -create -output ./release/nebula-cert ./build/darwin-amd64/nebula-cert ./build/darwin-arm64/nebula-cert
 
-          # Unset in a fork, which has no credentials to sign with
-          if [ -n "$SIGNING_IDENTITY_SHA1" ]; then
-            codesign -s "$SIGNING_IDENTITY_SHA1" -f -v --timestamp --options=runtime -i "net.defined.nebula" ./release/nebula
-            codesign -s "$SIGNING_IDENTITY_SHA1" -f -v --timestamp --options=runtime -i "net.defined.nebula-cert" ./release/nebula-cert
+          if [ -n "$AC_USERNAME" ]; then
+            codesign -s "10BC1FDDEB6CE753550156C0669109FAC49E4D1E" -f -v --timestamp --options=runtime -i "net.defined.nebula" ./release/nebula
+            codesign -s "10BC1FDDEB6CE753550156C0669109FAC49E4D1E" -f -v --timestamp --options=runtime -i "net.defined.nebula-cert" ./release/nebula-cert
           fi
 
           zip -j release/nebula-darwin.zip release/nebula-cert release/nebula
 
-          if [ -n "$ASC_P8" ]; then
-            xcrun notarytool submit ./release/nebula-darwin.zip --key "$ASC_P8" --key-id "$ASC_KEY_ID" --issuer "$ASC_ISSUER_ID" --wait
+          if [ -n "$AC_USERNAME" ]; then
+            xcrun notarytool submit ./release/nebula-darwin.zip --team-id "576H3XS7FP" --apple-id "$AC_USERNAME" --password "$AC_PASSWORD" --wait
           fi
 
-      - name: Drop the signing key
-        if: always() && env.HAS_SIGNING_CREDS == 'true'
-        run: |
-          # Locked, not deleted: import-codesign-certs deletes it in its own post
-          # step and fails the job if it is already gone. Locked is unusable.
-          security lock-keychain signing_temp.keychain || true
-          rm -f "$ASC_P8"
-          # Nothing later in this job needs AWS
-          python3 -c '
-          import json, os
-          names = json.loads(os.environ.get("SECRETS_LIST_CLEAN_UP") or "[]")
-          names += ["ASC_P8", "SIGNING_IDENTITY_SHA1", "ASC_KEY_ID", "ASC_ISSUER_ID",
-                    "AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_SESSION_TOKEN"]
-          print("\n".join(f"{n}=" for n in dict.fromkeys(names)))
-          ' >> "$GITHUB_ENV"
-
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
         with:

connection_manager.go

@@ -105,11 +105,12 @@ func (cm *connectionManager) getInactivityTimeout() time.Duration {
 }
 
 func (cm *connectionManager) In(h *HostInfo) {
-	h.in.Store(true)
+	h.markIn()
 }
 
-func (cm *connectionManager) Out(h *HostInfo) {
-	h.out.Store(true)
+// Out records outbound traffic and reports whether the local network changed since this tunnel last sent.
+func (cm *connectionManager) Out(h *HostInfo) bool {
+	return h.markOut(cm.intf.rebindEpoch.Load())
 }
 
 func (cm *connectionManager) RelayUsed(localIndex uint32) {
@@ -128,8 +129,7 @@ func (cm *connectionManager) RelayUsed(localIndex uint32) {
 // getAndResetTrafficCheck returns if there was any inbound or outbound traffic within the last tick and
 // resets the state for this local index
 func (cm *connectionManager) getAndResetTrafficCheck(h *HostInfo, now time.Time) (bool, bool) {
-	in := h.in.Swap(false)
-	out := h.out.Swap(false)
+	in, out := h.takeTraffic()
 	if in || out {
 		h.lastUsed = now
 	}
@@ -340,7 +340,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 				"tunnelCheck", m{"state": "alive", "method": "passive"},
 			)
 		}
-		hostinfo.pendingDeletion.Store(false)
+		hostinfo.setPendingDeletion(false)
 
 		if mainHostInfo {
 			decision = tryRehandshake
@@ -363,7 +363,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 		return decision, hostinfo, primary
 	}
 
-	if hostinfo.pendingDeletion.Load() {
+	if hostinfo.isPendingDeletion() {
 		// We have already sent a test packet and nothing was returned, this hostinfo is dead
 		hostinfo.logger(cm.l).Info("Tunnel status",
 			"tunnelCheck", m{"state": "dead", "method": "active"},
@@ -414,7 +414,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
 		}
 	}
 
-	hostinfo.pendingDeletion.Store(true)
+	hostinfo.setPendingDeletion(true)
 	cm.trafficTimer.Add(hostinfo.localIndexId, cm.pendingDeletionInterval)
 	return decision, hostinfo, nil
 }

connection_manager_test.go

@@ -86,25 +86,25 @@ func Test_NewConnectionManagerTest(t *testing.T) {
 	// We saw traffic out to vpnIp
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
-	assert.True(t, hostinfo.out.Load())
-	assert.True(t, hostinfo.in.Load())
+	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
 
 	// Do a traffic check tick, should not be pending deletion but should not have any in/out packets recorded
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 
 	// Do another traffic check tick, this host should be pending deletion now
 	nc.Out(hostinfo)
-	assert.True(t, hostinfo.out.Load())
+	assert.True(t, hostinfo.sentSinceCheck())
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.True(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.True(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
@@ -168,33 +168,33 @@ func Test_NewConnectionManagerTest2(t *testing.T) {
 	// We saw traffic out to vpnIp
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.True(t, hostinfo.in.Load())
-	assert.True(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.pendingDeletion.Load())
+	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
+	assert.True(t, hostinfo.sentSinceCheck())
+	assert.False(t, hostinfo.isPendingDeletion())
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 
 	// Do a traffic check tick, should not be pending deletion but should not have any in/out packets recorded
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 
 	// Do another traffic check tick, this host should be pending deletion now
 	nc.Out(hostinfo)
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.True(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.True(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
 	// We saw traffic, should no longer be pending deletion
 	nc.In(hostinfo)
 	nc.doTrafficCheck(hostinfo.localIndexId, p, nb, out, time.Now())
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 }
@@ -253,31 +253,31 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
 	// Do a traffic check tick, in and out should be cleared but should not be pending deletion
 	nc.Out(hostinfo)
 	nc.In(hostinfo)
-	assert.True(t, hostinfo.out.Load())
-	assert.True(t, hostinfo.in.Load())
+	assert.True(t, hostinfo.sentSinceCheck())
+	assert.True(t, (hostinfo.state.Load()&stateIn != 0))
 
 	now := time.Now()
 	decision, _, _ := nc.makeTrafficDecision(hostinfo.localIndexId, now)
 	assert.Equal(t, tryRehandshake, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*5))
 	assert.Equal(t, doNothing, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 
 	// Do another traffic check tick, should still not be pending deletion
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Second*10))
 	assert.Equal(t, doNothing, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 
@@ -285,9 +285,9 @@ func Test_NewConnectionManager_DisconnectInactive(t *testing.T) {
 	decision, _, _ = nc.makeTrafficDecision(hostinfo.localIndexId, now.Add(time.Minute*10))
 	assert.Equal(t, closeTunnel, decision)
 	assert.Equal(t, now, hostinfo.lastUsed)
-	assert.False(t, hostinfo.pendingDeletion.Load())
-	assert.False(t, hostinfo.out.Load())
-	assert.False(t, hostinfo.in.Load())
+	assert.False(t, hostinfo.isPendingDeletion())
+	assert.False(t, hostinfo.sentSinceCheck())
+	assert.False(t, (hostinfo.state.Load()&stateIn != 0))
 	assert.Contains(t, nc.hostMap.Indexes, hostinfo.localIndexId)
 	assert.Contains(t, nc.hostMap.Hosts, hostinfo.vpnAddrs[0])
 }

control.go

@@ -212,7 +212,7 @@ func (c *Control) RebindUDPServer() {
 	c.f.lightHouse.SendUpdate()
 
 	// Let the main interface know that we rebound so that underlying tunnels know to trigger punches from their remotes
-	c.f.rebindCount++
+	c.f.rebindEpoch.Add(1)
 }
 
 // ListHostmapHosts returns details about the actual or pending (handshaking) hostmap by vpn ip

e2e/router/router.go

@@ -6,13 +6,11 @@ package router
 import (
 	"context"
 	"fmt"
-	"maps"
 	"net/netip"
 	"os"
 	"path/filepath"
 	"reflect"
 	"regexp"
-	"slices"
 	"sort"
 	"sync"
 	"sync/atomic"
@@ -24,6 +22,7 @@ import (
 	"github.com/slackhq/nebula"
 	"github.com/slackhq/nebula/header"
 	"github.com/slackhq/nebula/udp"
+	"golang.org/x/exp/maps"
 )
 
 // outNatKey is the (from, to) pair used by outNat. Comparable struct, so it works as a map key without the
@@ -375,7 +374,7 @@ func (r *R) RenderHostmaps(title string, controls ...*nebula.Control) {
 }
 
 func (r *R) renderHostmaps(title string) {
-	c := slices.AppendSeq(make([]*nebula.Control, 0, len(r.controls)), maps.Values(r.controls))
+	c := maps.Values(r.controls)
 	sort.SliceStable(c, func(i, j int) bool {
 		return c[i].GetVpnAddrs()[0].Compare(c[j].GetVpnAddrs()[0]) > 0
 	})

go.mod

@@ -16,15 +16,16 @@ require (
 	github.com/miekg/dns v1.1.72
 	github.com/miekg/pkcs11 v1.1.2
 	github.com/nbrownus/go-metrics-prometheus v0.0.0-20210712211119-974a6260965f
-	github.com/prometheus/client_golang v1.24.1
+	github.com/prometheus/client_golang v1.23.2
 	github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475
 	github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
 	github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
 	github.com/stretchr/testify v1.11.1
 	github.com/vishvananda/netlink v1.3.1
 	go.uber.org/goleak v1.3.0
-	go.yaml.in/yaml/v3 v3.0.5
+	go.yaml.in/yaml/v3 v3.0.4
 	golang.org/x/crypto v0.54.0
+	golang.org/x/exp v0.0.0-20230725093048-515e97ebf090
 	golang.org/x/net v0.57.0
 	golang.org/x/sync v0.22.0
 	golang.org/x/sys v0.47.0
@@ -45,9 +46,10 @@ require (
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
-	github.com/prometheus/common v0.70.1 // indirect
-	github.com/prometheus/procfs v0.21.1 // indirect
+	github.com/prometheus/common v0.66.1 // indirect
+	github.com/prometheus/procfs v0.16.1 // indirect
 	github.com/vishvananda/netns v0.0.5 // indirect
+	go.yaml.in/yaml/v2 v2.4.2 // indirect
 	golang.org/x/mod v0.36.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
 	golang.org/x/tools v0.45.0 // indirect

go.sum

@@ -70,14 +70,15 @@ github.com/kardianos/service v1.3.0 h1:/LGy+xPP2TM+GLTiCZ2di7cy0Jd/qrawlTUfqKYFd
 github.com/kardianos/service v1.3.0/go.mod h1:E4V9ufUuY82F7Ztlu1eN9VXWIQxg8NoLQlmFe0MtrXc=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
-github.com/klauspost/compress v1.19.1 h1:VsB4HPswih7mmZ8WleSFQ75c/Ui1M4trX5oAsJnhSlk=
-github.com/klauspost/compress v1.19.1/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
+github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/konsorten/go-windows-terminal-sequences v1.0.3/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
@@ -107,8 +108,8 @@ github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXP
 github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
 github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M=
 github.com/prometheus/client_golang v1.11.0/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0=
-github.com/prometheus/client_golang v1.24.1 h1:JnJkREXzWxUdCuPFpIWZiPispT9xVV59uiuyR2bPlnU=
-github.com/prometheus/client_golang v1.24.1/go.mod h1:F+oSRECHg4sse5ucfYpYDeIv/hu68Zo0uoHKetWnzcE=
+github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
+github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
 github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
 github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.2.0/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
@@ -117,16 +118,18 @@ github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvM
 github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
 github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc=
-github.com/prometheus/common v0.70.1 h1:1HvjP4D5oL3t8RsPlwxA9onvvStjtIHYE5XuuwOi/PY=
-github.com/prometheus/common v0.70.1/go.mod h1:VdFUQDMZK3VLkurFUVhia6uys/0suUp86TJz5qbJRhc=
+github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9ZoGs=
+github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
 github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
 github.com/prometheus/procfs v0.1.3/go.mod h1:lV6e/gmhEcM9IjHGsFOCxxuZ+z1YqCvr4OA4YeYWdaU=
 github.com/prometheus/procfs v0.6.0/go.mod h1:cz+aTbrPOrUb4q7XlbU9ygM+/jj0fzG6c1xBZuNvfVA=
-github.com/prometheus/procfs v0.21.1 h1:GljZCt+zSTS+NZq88cyQ1LjZ+RCHp3uVuabBWA5+OJI=
-github.com/prometheus/procfs v0.21.1/go.mod h1:aB55Cww9pdSJVHk0hUf0inxWyyjPogFIjmHKYgMKmtY=
+github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
+github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
 github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475 h1:N/ElC8H3+5XpJzTSTfLsJV/mx9Q9g7kxmchpfZyxgzM=
 github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475/go.mod h1:bCqnVzQkZxMG4s8nGwiZ5l3QUCyqpo9Y+/ZMZ9VjZe4=
+github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
+github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
 github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
 github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
 github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
@@ -150,10 +153,10 @@ github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9de
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
-go.yaml.in/yaml/v2 v2.4.4 h1:tuyd0P+2Ont/d6e2rl3be67goVK4R6deVxCUX5vyPaQ=
-go.yaml.in/yaml/v2 v2.4.4/go.mod h1:gMZqIpDtDqOfM0uNfy0SkpRhvUryYH0Z6wdMYcacYXQ=
-go.yaml.in/yaml/v3 v3.0.5 h1:N6y/pJk8buWs9NY5ERU2HSMfm+IuD/OtfdAnq6kESPw=
-go.yaml.in/yaml/v3 v3.0.5/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
+go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
+go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
+go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
+go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
@@ -161,6 +164,8 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
 golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
 golang.org/x/crypto v0.54.0 h1:YLIA59K4fiNzHzjnZt2tUJQjQtUWfWbeHBqKtk3eScw=
 golang.org/x/crypto v0.54.0/go.mod h1:KWL8ny2AZdGR2cWmzeHrp2azQPGogOv+HeQaVEXC2dk=
+golang.org/x/exp v0.0.0-20230725093048-515e97ebf090 h1:Di6/M8l0O2lCLc6VVRWhgCiApHV8MnQurBnFSHsQtNY=
+golang.org/x/exp v0.0.0-20230725093048-515e97ebf090/go.mod h1:FXUEEKJgO7OQYeo8N01OfiKP8RXMtf6e8aTskBGqWdc=
 golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
 golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=

hostmap.go

@@ -238,18 +238,30 @@ const (
 )
 
 type HostInfo struct {
+	// The first cache line is everything the packet paths touch. Grouping them here means a send or receive
+	// pulls in one line instead of two, which is what the layout looked like when state lived at the end.
+
 	remote          atomic.Pointer[netip.AddrPort]
-	remotes         *RemoteList
-	promoteCounter  atomic.Uint32
 	ConnectionState *ConnectionState
-	remoteIndexId   uint32
-	localIndexId    uint32
+
+	// state holds everything the hot paths need to touch per packet, in one word: whether we have seen traffic
+	// each way since the connection manager last looked, whether it has given up on us, and the
+	// Interface.rebindEpoch this tunnel last sent under. Keeping the epoch here means it survives the traffic
+	// bits being cleared, so a tunnel that has not sent since a rebind still notices when it does.
+	state atomic.Uint32
+
+	promoteCounter atomic.Uint32
+	remoteIndexId  uint32
+	localIndexId   uint32
+	remotes        *RemoteList
 
 	// vpnAddrs is a list of vpn addresses assigned to this host that are within our own vpn networks
 	// The host may have other vpn addresses that are outside our
 	// vpn networks but were removed because they are not usable
 	vpnAddrs []netip.Addr
 
+	// Everything below is off the packet path: handshakes, relays, roaming and the connection manager.
+
 	// networks is a combination of specific vpn addresses (not prefixes!) and full unsafe networks assigned to this host.
 	networks   *bart.Table[NetworkType]
 	relayState RelayState
@@ -262,11 +274,6 @@ type HostInfo struct {
 	// This is used to limit lighthouse re-queries in chatty clients
 	nextLHQuery atomic.Int64
 
-	// lastRebindCount is the other side of Interface.rebindCount, if these values don't match then we need to ask LH
-	// for a punch from the remote end of this tunnel. The goal being to prime their conntrack for our traffic just like
-	// with a handshake
-	lastRebindCount int8
-
 	// lastHandshakeTime records the time the remote side told us about at the stage when the handshake was completed locally
 	// Stage 1 packet will contain it if I am a responder, stage 2 packet if I am an initiator
 	// This is used to avoid an attack where a handshake packet is replayed after some time
@@ -275,9 +282,6 @@ type HostInfo struct {
 	lastRoam       time.Time
 	lastRoamRemote netip.AddrPort
 
-	//TODO: in, out, and others might benefit from being an atomic.Int32. We could collapse connectionManager pendingDeletion, relayUsed, and in/out into this 1 thing
-	in, out, pendingDeletion atomic.Bool
-
 	// lastUsed tracks the last time ConnectionManager checked the tunnel and it was in use.
 	// This value will be behind against actual tunnel utilization in the hot path.
 	// This should only be used by the ConnectionManagers ticker routine.
@@ -658,7 +662,7 @@ func (hm *HostMap) unlockedAddHostInfo(hostinfo *HostInfo, f *Interface) {
 	hm.Indexes[hostinfo.localIndexId] = hostinfo
 	hm.RemoteIndexes[hostinfo.remoteIndexId] = hostinfo
 
-	hostinfo.out.Store(true)
+	hostinfo.markOut(f.rebindEpoch.Load())
 	if f.connectionManager != nil { // f.connectionManager is only nil in some unit tests
 		f.connectionManager.trafficTimer.Add(hostinfo.localIndexId, f.connectionManager.checkInterval)
 	}
@@ -759,6 +763,64 @@ func (i *HostInfo) TryPromoteBest(preferredRanges []netip.Prefix, ifce *Interfac
 	}
 }
 
+// Bits within HostInfo.state. Everything above stateEpochShift is the rebind epoch.
+const (
+	stateIn uint32 = 1 << iota
+	stateOut
+	statePendingDeletion
+
+	stateFlags      = stateIn | stateOut | statePendingDeletion
+	stateEpochShift = 3
+)
+
+// markIn records inbound traffic. Reading first keeps the cache line shared on the common path, where the bit
+// is already set.
+func (i *HostInfo) markIn() {
+	if i.state.Load()&stateIn == 0 {
+		i.state.Or(stateIn)
+	}
+}
+
+// markOut records that we sent on this tunnel under the given rebind epoch. It reports whether the epoch moved
+// since our last send, which means the local network changed and we want the far side to punch at us again.
+// The common path is a single load that matches and returns.
+func (i *HostInfo) markOut(epoch uint32) bool {
+	e := epoch << stateEpochShift
+	for {
+		old := i.state.Load()
+		if old&stateOut != 0 && old&^stateFlags == e {
+			return false
+		}
+
+		if i.state.CompareAndSwap(old, old&stateFlags|stateOut|e) {
+			return old&^stateFlags != e
+		}
+	}
+}
+
+// sentSinceCheck reports whether anything has been sent since the connection manager last looked.
+func (i *HostInfo) sentSinceCheck() bool {
+	return i.state.Load()&stateOut != 0
+}
+
+// takeTraffic clears both traffic bits, leaving the epoch alone, and reports what they were.
+func (i *HostInfo) takeTraffic() (in bool, out bool) {
+	old := i.state.And(^(stateIn | stateOut))
+	return old&stateIn != 0, old&stateOut != 0
+}
+
+func (i *HostInfo) setPendingDeletion(v bool) {
+	if v {
+		i.state.Or(statePendingDeletion)
+	} else {
+		i.state.And(^statePendingDeletion)
+	}
+}
+
+func (i *HostInfo) isPendingDeletion() bool {
+	return i.state.Load()&statePendingDeletion != 0
+}
+
 func (i *HostInfo) GetCert() *cert.CachedCertificate {
 	if i.ConnectionState != nil {
 		return i.ConnectionState.peerCert

inside.go

@@ -365,17 +365,12 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
 
 	//l.WithField("trace", string(debug.Stack())).Error("out Header ", &Header{Version, t, st, 0, hostinfo.remoteIndexId, c}, p)
 	out = header.Encode(out, header.Version, t, st, hostinfo.remoteIndexId, c)
-	f.connectionManager.Out(hostinfo)
-
-	// Query our LH if we haven't since the last time we've been rebound, this will cause the remote to punch against
-	// all our addrs and enable a faster roaming.
-	if t != header.CloseTunnel && hostinfo.lastRebindCount != f.rebindCount {
-		//NOTE: there is an update hole if a tunnel isn't used and exactly 256 rebinds occur before the tunnel is
-		// finally used again. This tunnel would eventually be torn down and recreated if this action didn't help.
+	// We rebound since this tunnel last sent, so the local network moved. Ask the lighthouse to have the far side
+	// punch at where we are now, which primes their conntrack the same way a handshake would.
+	if f.connectionManager.Out(hostinfo) && t != header.CloseTunnel {
 		f.lightHouse.QueryServer(hostinfo.vpnAddrs[0])
-		hostinfo.lastRebindCount = f.rebindCount
 		if f.l.Enabled(context.Background(), slog.LevelDebug) {
-			f.l.Debug("Lighthouse update triggered for punch due to rebind counter",
+			f.l.Debug("Lighthouse update triggered for punch due to rebind epoch",
 				"vpnAddrs", hostinfo.vpnAddrs,
 			)
 		}

interface.go

@@ -82,8 +82,10 @@ type Interface struct {
 	sendRecvErrorConfig   recvErrorConfig
 	acceptRecvErrorConfig recvErrorConfig
 
-	// rebindCount is used to decide if an active tunnel should trigger a punch notification through a lighthouse
-	rebindCount int8
+	// rebindEpoch bumps every time the udp listener is rebound, which means the local network moved. Tunnels
+	// compare it against their own copy to decide they need a punch from the far side. Read on every send, only
+	// written on a rebind, so the cache line stays shared across the routines.
+	rebindEpoch atomic.Uint32
 	version     string
 
 	conntrackCacheTimeout time.Duration

overlay/tun_linux.go

@@ -5,7 +5,6 @@ package overlay
 
 import (
 	"encoding/binary"
-	"errors"
 	"fmt"
 	"io"
 	"log/slog"
@@ -484,16 +483,7 @@ func (t *tun) addIPs(link netlink.Link) error {
 	//iterate over remainder, remove whoever shouldn't be there
 	al, err := netlink.AddrList(link, netlink.FAMILY_ALL)
 	if err != nil {
-		//RTM_GETADDR dumps the whole system, so any concurrent address change
-		//interrupts it - including the kernel's async tentative->preferred
-		//flip of an IPv6 address the AddrReplace calls above just added,
-		//which makes this a race against our own setup. Partial results are
-		//still returned; the worst case is a stale address surviving until
-		//the next config reload, which beats failing startup over it.
-		if !errors.Is(err, netlink.ErrDumpInterrupted) {
-			return fmt.Errorf("failed to get tun address list: %s", err)
-		}
-		t.l.Warn("tun address list dump was interrupted, stale addresses may remain")
+		return fmt.Errorf("failed to get tun address list: %s", err)
 	}
 
 	for i := range al {