mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 06:06:52 +01:00
Compare commits
57
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
92c67a52b2 | ||
|
|
0f767ce529 | ||
|
|
9a5bdb508e | ||
|
|
48ba879198 | ||
|
|
fb2c153dfa | ||
|
|
f552cebc51 | ||
|
|
b04d71d96a | ||
|
|
cacfa8fac4 | ||
|
|
8a4bd8b10f | ||
|
|
b426843f88 | ||
|
|
cda3710d5a | ||
|
|
c26871fe08 | ||
|
|
7daacc6a48 | ||
|
|
428dad94b3 | ||
|
|
5bf666dd90 | ||
|
|
49207da077 | ||
|
|
bbc49669b7 | ||
|
|
915495d5f4 | ||
|
|
a203d044bb | ||
|
|
316bf87780 | ||
|
|
1a0ac25db0 | ||
|
|
42597dda7d | ||
|
|
afbdc87ed9 | ||
|
|
94372f4f51 | ||
|
|
42280f04ce | ||
|
|
11c1917387 | ||
|
|
5ba7aff4b3 | ||
|
|
8a2de9b1b5 | ||
|
|
a8c52f5c13 | ||
|
|
13af8dd6f3 | ||
|
|
5bb0622192 | ||
|
|
f3705cbb67 | ||
|
|
94be454f4f | ||
|
|
5f26c1a7e5 | ||
|
|
d47c8c71f1 | ||
|
|
f57539a163 | ||
|
|
8d8ae0f744 | ||
|
|
f9b0853476 | ||
|
|
d5062dacf0 | ||
|
|
7cfa47d569 | ||
|
|
e20569ce51 | ||
|
|
9651ffdb0d | ||
|
|
3a45c01656 | ||
|
|
019cc46a7f | ||
|
|
cf3f315cd3 | ||
|
|
3fc627e08d | ||
|
|
abff1a4555 | ||
|
|
227134a1d5 | ||
|
|
232bacfdd0 | ||
|
|
4e1ef9cd73 | ||
|
|
614e0ea3aa | ||
|
|
2999fc0b6a | ||
|
|
f474b534e1 | ||
|
|
0dc8a28d1f | ||
|
|
89178f45ba | ||
|
|
6a72e1c304 | ||
|
|
e50f8128f4 |
No files matched your search
@@ -0,0 +1,2 @@
|
||||
# Goldens are compared byte for byte, so they must come out of git the way they went in.
|
||||
*.golden -text
|
||||
Executable
+142
@@ -0,0 +1,142 @@
|
||||
#!/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 -
|
||||
@@ -14,7 +14,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -83,7 +83,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
# GitHub holds ARNs, not credentials, and ARNs outlive a rotation
|
||||
|
||||
@@ -34,7 +34,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -66,7 +66,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: add hashicorp source
|
||||
@@ -92,13 +92,13 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
# WSL2 + Ubuntu so the smoke can run a real linux peer with its own
|
||||
# netns. iputils-ping is needed for the in-WSL ping check. WSL1 has no
|
||||
# real kernel and would lack /dev/net/tun, so we have to force WSL2.
|
||||
- uses: Vampire/setup-wsl@v3
|
||||
- uses: Vampire/setup-wsl@v7
|
||||
with:
|
||||
distribution: Ubuntu-24.04
|
||||
additional-packages: iputils-ping iproute2
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Smoke Docker
|
||||
@@ -51,7 +51,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: build
|
||||
|
||||
@@ -51,15 +51,19 @@ wsl -d $Distro -- bash -c "rm -rf $WslDir && mkdir -p $WslDir" | Out-Null
|
||||
$DevName = 'nebula-smoke'
|
||||
$Ip1 = '192.168.241.1'
|
||||
$Ip2 = '192.168.241.2'
|
||||
# Dual stack on purpose: a v4-only overlay never exercises the v6 side of tun.mtu.
|
||||
$Ip6_1 = 'fd42:4242:241::1'
|
||||
$Ip6_2 = 'fd42:4242:241::2'
|
||||
$Mtu = 1300
|
||||
$Port = 4242
|
||||
|
||||
& $NebulaCert ca -name 'smoke-ca' -out-crt "$WorkDir\ca.crt" -out-key "$WorkDir\ca.key"
|
||||
if ($LASTEXITCODE -ne 0) { throw "nebula-cert ca failed (exit $LASTEXITCODE)" }
|
||||
|
||||
& $NebulaCert sign -name 'lighthouse' -networks "$Ip1/24" -ca-crt "$WorkDir\ca.crt" -ca-key "$WorkDir\ca.key" -out-crt "$WorkDir\lighthouse.crt" -out-key "$WorkDir\lighthouse.key"
|
||||
& $NebulaCert sign -name 'lighthouse' -networks "$Ip1/24,$Ip6_1/64" -ca-crt "$WorkDir\ca.crt" -ca-key "$WorkDir\ca.key" -out-crt "$WorkDir\lighthouse.crt" -out-key "$WorkDir\lighthouse.key"
|
||||
if ($LASTEXITCODE -ne 0) { throw "nebula-cert sign lighthouse failed (exit $LASTEXITCODE)" }
|
||||
|
||||
& $NebulaCert sign -name 'peer' -networks "$Ip2/24" -ca-crt "$WorkDir\ca.crt" -ca-key "$WorkDir\ca.key" -out-crt "$WorkDir\peer.crt" -out-key "$WorkDir\peer.key"
|
||||
& $NebulaCert sign -name 'peer' -networks "$Ip2/24,$Ip6_2/64" -ca-crt "$WorkDir\ca.crt" -ca-key "$WorkDir\ca.key" -out-crt "$WorkDir\peer.crt" -out-key "$WorkDir\peer.key"
|
||||
if ($LASTEXITCODE -ne 0) { throw "nebula-cert sign peer failed (exit $LASTEXITCODE)" }
|
||||
|
||||
# Windows lighthouse config.
|
||||
@@ -82,7 +86,7 @@ tun:
|
||||
drop_local_broadcast: false
|
||||
drop_multicast: false
|
||||
tx_queue: 500
|
||||
mtu: 1300
|
||||
mtu: $Mtu
|
||||
network_category: private
|
||||
logging:
|
||||
level: info
|
||||
@@ -126,7 +130,7 @@ tun:
|
||||
drop_local_broadcast: false
|
||||
drop_multicast: false
|
||||
tx_queue: 500
|
||||
mtu: 1300
|
||||
mtu: $Mtu
|
||||
logging:
|
||||
level: info
|
||||
format: text
|
||||
@@ -169,7 +173,7 @@ Write-Host '=== WSL diagnostic ==='
|
||||
wsl --version 2>&1 | Out-Host
|
||||
wsl --list --verbose 2>&1 | Out-Host
|
||||
wsl -d $Distro -u root -- uname -a | Out-Host
|
||||
wsl -d $Distro -u root -- bash -c "modprobe tun 2>&1 || true; mkdir -p /dev/net; [ -c /dev/net/tun ] || mknod /dev/net/tun c 10 200; chmod 600 /dev/net/tun; ls -l /dev/net/tun"
|
||||
wsl -d $Distro -u root -- bash -c "modprobe tun 2>&1 || true; mkdir -p /dev/net; [ -c /dev/net/tun ] || mknod /dev/net/tun c 10 200; chmod 600 /dev/net/tun; { echo 0 > /proc/sys/net/ipv6/conf/all/disable_ipv6; echo 0 > /proc/sys/net/ipv6/conf/default/disable_ipv6; } 2>/dev/null || true; ls -l /dev/net/tun"
|
||||
if ($LASTEXITCODE -ne 0) { throw "failed to prepare /dev/net/tun in WSL (TUN support missing?)" }
|
||||
|
||||
# Deliberately no New-NetFirewallRule calls here -- nebula's windows_bypass_wdf
|
||||
@@ -214,6 +218,16 @@ try {
|
||||
}
|
||||
Write-Host "OK: $DevName NetworkCategory=Private"
|
||||
|
||||
# v6 silently kept the adapter default of 65535 while v4 was correct.
|
||||
foreach ($family in @('IPv4', 'IPv6')) {
|
||||
Wait-Until -TimeoutSec 30 -What "$DevName $family NlMtu=$Mtu" -Predicate {
|
||||
if ($lhProc.HasExited) { throw "lighthouse exited (code $($lhProc.ExitCode)) before $family mtu was set" }
|
||||
$rows = @(Get-NetIPInterface -InterfaceAlias $DevName -AddressFamily $family -ErrorAction SilentlyContinue)
|
||||
$rows.Count -gt 0 -and -not ($rows | Where-Object { $_.NlMtu -ne $Mtu })
|
||||
}
|
||||
Write-Host "OK: $DevName $family NlMtu=$Mtu"
|
||||
}
|
||||
|
||||
Wait-Until -TimeoutSec 30 -What "WSL nebula1 with $Ip2" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before tun was ready" }
|
||||
$r = wsl -d $Distro -u root -- bash -c "ip -o addr show nebula1 2>/dev/null | grep -q 'inet $Ip2' && echo yes"
|
||||
@@ -221,6 +235,13 @@ try {
|
||||
}
|
||||
Write-Host "OK: WSL nebula1 has $Ip2"
|
||||
|
||||
Wait-Until -TimeoutSec 30 -What "WSL nebula1 with $Ip6_2" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the v6 address was up" }
|
||||
$r = wsl -d $Distro -u root -- bash -c "ip -o addr show nebula1 2>/dev/null | grep -q 'inet6 $Ip6_2' && echo yes"
|
||||
("$r").Trim() -eq 'yes'
|
||||
}
|
||||
Write-Host "OK: WSL nebula1 has $Ip6_2"
|
||||
|
||||
Wait-Until -TimeoutSec 30 -What "ping from WSL peer to windows lighthouse ($Ip1)" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before ping succeeded" }
|
||||
$r = wsl -d $Distro -u root -- bash -c "ping -c1 -W1 $Ip1 >/dev/null 2>&1 && echo OK"
|
||||
@@ -234,6 +255,28 @@ try {
|
||||
}
|
||||
Write-Host "OK: windows lighthouse -> WSL peer"
|
||||
|
||||
# Otherwise the v6 networks only prove the interface exists, not that it forwards.
|
||||
Wait-Until -TimeoutSec 30 -What "v6 ping from WSL peer to windows lighthouse ($Ip6_1)" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the v6 ping succeeded" }
|
||||
$r = wsl -d $Distro -u root -- bash -c "ping -6 -c1 -W1 $Ip6_1 >/dev/null 2>&1 && echo OK"
|
||||
("$r").Trim() -eq 'OK'
|
||||
}
|
||||
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
||||
|
||||
# The NlMtu check above proves the value was written, not that windows honors it. A payload this size only
|
||||
# crosses the tunnel as fragments cut at NlMtu on the way out of the adapter. Left at the adapter default it
|
||||
# reaches nebula whole, overflows the udp.MTU (9001) write buffer and is dropped, so the ping never answers.
|
||||
# Anything smaller would ride out as one oversized datagram and survive on IP fragmentation of the underlay.
|
||||
$BigPayload = 9000
|
||||
foreach ($target in @(@{ Family = 'v4'; Ip = $Ip2 }, @{ Family = 'v6'; Ip = $Ip6_2 })) {
|
||||
Wait-Until -TimeoutSec 30 -What "$($target.Family) ping with a $BigPayload byte payload from windows lighthouse to WSL peer ($($target.Ip))" -Predicate {
|
||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the large $($target.Family) ping succeeded" }
|
||||
$null = & ping.exe -n 1 -w 1000 -l $BigPayload $target.Ip
|
||||
$LASTEXITCODE -eq 0
|
||||
}
|
||||
Write-Host "OK: windows lighthouse -> WSL peer, $BigPayload byte $($target.Family) payload"
|
||||
}
|
||||
|
||||
Write-Host ''
|
||||
Write-Host 'All smoke checks passed.'
|
||||
}
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Install goimports
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
- name: golangci-lint
|
||||
uses: golangci/golangci-lint-action@v9
|
||||
with:
|
||||
version: v2.12
|
||||
version: v2.14
|
||||
|
||||
test:
|
||||
name: Test ${{ matrix.name }}
|
||||
@@ -87,7 +87,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Build
|
||||
@@ -132,7 +132,7 @@ jobs:
|
||||
|
||||
- uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version: '1.26'
|
||||
go-version: '1.27'
|
||||
check-latest: true
|
||||
|
||||
- name: Build ${{ matrix.name }}
|
||||
|
||||
+33
-1
@@ -7,6 +7,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
|
||||
- A control socket that provides access to all of the ssh debug server's commands along with support
|
||||
for running `nebula ctl <command>` as a client from the CLI.
|
||||
|
||||
### Removed
|
||||
|
||||
- The SSH debug server's `start-cpu-profile`, `stop-cpu-profile`, `save-heap-profile`, `save-mutex-profile`, and
|
||||
`mutex-profile-fraction` commands, and `sshd.sandbox_dir`, which is now ignored if set.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Signing a v2 certificate with an empty name, a name longer than 253 bytes, or an empty group now fails.
|
||||
These certificates were signed successfully but could not be loaded.
|
||||
- `create-tunnel -address <ip:port>` panicked on a nil RemoteList and, over the ssh debug server, took nebula
|
||||
down with it. A hostinfo returned by StartHandshake had no RemoteList until the handshake loop's first
|
||||
pass attached one, and `create-tunnel -address` set the remote before that. The list is now attached when
|
||||
the handshake starts, so a pending hostinfo never exists without one.
|
||||
|
||||
## [1.11.1] - 2026-08-21
|
||||
|
||||
See the [v1.11.1](https://github.com/slackhq/nebula/milestone/30?closed=1) milestone for a complete list of changes.
|
||||
|
||||
### Changed
|
||||
|
||||
- IPv6 packets whose next header is a protocol Nebula does not parse (SCTP, GRE, IP-in-IP, etc.) are now
|
||||
@@ -15,11 +38,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
their true protocol, so only a `proto: any` rule allows them. If you carry one of these protocols over the
|
||||
overlay, confirm a `proto: any` rule covers it before upgrading, it may have been passing only through this
|
||||
bypass. (#1840)
|
||||
- Drop the dependency on `github.com/cyberdelia/go-metrics-graphite`, which has been unmaintained for over ten
|
||||
years, by inlining the small amount of code Nebula used. (#1832)
|
||||
|
||||
### Fixed
|
||||
|
||||
- The ICMPv6 type was read from the wrong byte when classifying IPv6 packets, so the echo identifier used
|
||||
for conntrack was never picked up. (#1840)
|
||||
- Enforce outbound message counter limits so a tunnel is rehandshaked before the counter can wrap, preventing
|
||||
nonce reuse. This is unreachable in practice, but is enforced as a defense-in-depth measure. (#1841)
|
||||
- Prevent `nebula-cert ca` from running out of memory on 32bit systems when generating encrypted private keys. (#1834)
|
||||
- Tolerate `ErrDumpInterrupted` when listing tun addresses on Linux, so a transient interrupted netlink dump
|
||||
no longer aborts startup. (#1835)
|
||||
|
||||
## [1.11.0] - 2026-07-23
|
||||
|
||||
@@ -884,7 +914,9 @@ created.)
|
||||
|
||||
- Initial public release.
|
||||
|
||||
[Unreleased]: https://github.com/slackhq/nebula/compare/v1.10.3...HEAD
|
||||
[Unreleased]: https://github.com/slackhq/nebula/compare/v1.11.1...HEAD
|
||||
[1.11.1]: https://github.com/slackhq/nebula/releases/tag/v1.11.1
|
||||
[1.11.0]: https://github.com/slackhq/nebula/releases/tag/v1.11.0
|
||||
[1.10.3]: https://github.com/slackhq/nebula/releases/tag/v1.10.3
|
||||
[1.10.2]: https://github.com/slackhq/nebula/releases/tag/v1.10.2
|
||||
[1.10.1]: https://github.com/slackhq/nebula/releases/tag/v1.10.1
|
||||
|
||||
@@ -242,11 +242,14 @@ test-cov-html:
|
||||
go test -coverprofile=coverage.out
|
||||
go tool cover -html=coverage.out
|
||||
|
||||
# The package builds only compile. The final line links an android binary so a linker-only failure
|
||||
# cannot pass CI.
|
||||
build-test-mobile:
|
||||
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||
GOARCH=arm64 GOOS=android go build -o /dev/null ${NEBULA_CMD_PATH}
|
||||
|
||||
bench:
|
||||
go test -bench=.
|
||||
|
||||
@@ -79,13 +79,7 @@ func (b *Bits) clearRange(startPos, count uint64) uint64 {
|
||||
// handle the potential partial word before pos becomes u64 aligned
|
||||
word := pos >> 6
|
||||
bit := pos & 63
|
||||
take := uint64(64) - bit
|
||||
if take > remaining {
|
||||
take = remaining
|
||||
}
|
||||
if take > b.length-pos {
|
||||
take = b.length - pos
|
||||
}
|
||||
take := min(min(uint64(64)-bit, remaining), b.length-pos)
|
||||
var mask uint64
|
||||
if take == 64 {
|
||||
mask = math.MaxUint64
|
||||
@@ -189,10 +183,7 @@ func (b *Bits) Update(l *slog.Logger, i uint64) bool {
|
||||
func (b *Bits) updateSlow(l *slog.Logger, i uint64) bool {
|
||||
// If i is a jump, adjust the window, record lost, update current, and return true
|
||||
if i > b.current {
|
||||
end := i
|
||||
if end > b.current+b.length {
|
||||
end = b.current + b.length
|
||||
}
|
||||
end := min(i, b.current+b.length)
|
||||
count := end - b.current
|
||||
startPos := (b.current + 1) & b.lengthMask
|
||||
|
||||
|
||||
+10
-1
@@ -389,7 +389,16 @@ func (c *certificateV2) fromTBSCertificate(t *TBSCertificate) error {
|
||||
}
|
||||
|
||||
func (c *certificateV2) validate() error {
|
||||
// Empty names are allowed
|
||||
// Mirror the name and group rules in unmarshalDetails so signing fails instead of producing an unparseable certificate
|
||||
if c.details.name == "" || len(c.details.name) > MaxNameLength {
|
||||
return NewErrInvalidCertificateProperties("name must be between 1 and %d bytes", MaxNameLength)
|
||||
}
|
||||
|
||||
for _, group := range c.details.groups {
|
||||
if group == "" {
|
||||
return NewErrInvalidCertificateProperties("groups may not be empty")
|
||||
}
|
||||
}
|
||||
|
||||
if len(c.publicKey) == 0 {
|
||||
return ErrInvalidPublicKey
|
||||
|
||||
+46
-1
@@ -6,6 +6,7 @@ import (
|
||||
"crypto/elliptic"
|
||||
"crypto/rand"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -120,7 +121,7 @@ func TestCertificate_SignP256_AlwaysNormalized(t *testing.T) {
|
||||
pub := elliptic.Marshal(elliptic.P256(), priv.PublicKey.X, priv.PublicKey.Y)
|
||||
rawPriv := priv.D.FillBytes(make([]byte, 32))
|
||||
|
||||
for i := 0; i < 1000; i++ {
|
||||
for i := range 1000 {
|
||||
if i&1 == 1 {
|
||||
tbs.Version = Version1
|
||||
} else {
|
||||
@@ -135,3 +136,47 @@ func TestCertificate_SignP256_AlwaysNormalized(t *testing.T) {
|
||||
assert.True(t, normie)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCertificateV2_SignRejectsUnparseable(t *testing.T) {
|
||||
_, priv, err := ed25519.GenerateKey(rand.Reader)
|
||||
require.NoError(t, err)
|
||||
var invalid *ErrInvalidCertificateProperties
|
||||
|
||||
newTBS := func() TBSCertificate {
|
||||
return TBSCertificate{
|
||||
Version: Version2,
|
||||
Name: "testing",
|
||||
Networks: []netip.Prefix{mustParsePrefixUnmapped("10.1.1.1/24")},
|
||||
Groups: []string{"test-group1"},
|
||||
NotBefore: time.Now().Add(-time.Minute),
|
||||
NotAfter: time.Now().Add(time.Minute),
|
||||
PublicKey: []byte("1234567890abcedfghij1234567890ab"),
|
||||
Curve: Curve_CURVE25519,
|
||||
IsCA: true,
|
||||
}
|
||||
}
|
||||
|
||||
tbs := newTBS()
|
||||
tbs.Name = strings.Repeat("a", MaxNameLength)
|
||||
c, err := tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.NoError(t, err)
|
||||
b, err := c.Marshal()
|
||||
require.NoError(t, err)
|
||||
_, err = unmarshalCertificateV2(b, nil, Curve_CURVE25519)
|
||||
require.NoError(t, err)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Name = strings.Repeat("a", MaxNameLength+1)
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Name = ""
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
|
||||
tbs = newTBS()
|
||||
tbs.Groups = []string{"test-group1", ""}
|
||||
_, err = tbs.Sign(nil, Curve_CURVE25519, priv)
|
||||
require.ErrorAs(t, err, &invalid)
|
||||
}
|
||||
@@ -0,0 +1,420 @@
|
||||
package ctl
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"os"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
)
|
||||
|
||||
// Word is the argument that selects the control client instead of the daemon.
|
||||
const Word = "ctl"
|
||||
|
||||
// Subcommand handles the one bare word a daemon binary accepts before its flags. `nebula
|
||||
// ctl <command>` runs the client. Any other first argument that is not a flag is a
|
||||
// mistyped subcommand, reported with a usage line: the daemon's flag parser would ignore
|
||||
// the stray word and start nebula, so `nebula clt` would bring up a second daemon
|
||||
// instead of reporting a typo. It returns the exit code and true when the process is
|
||||
// done, and false when argv is the daemon's to parse. Both daemon binaries, cmd/nebula
|
||||
// and cmd/nebula-service, call it before anything else, so each has a nebula ctl and
|
||||
// neither has the hazard. A word that follows the daemon's flags instead is Trailing's.
|
||||
func Subcommand(argv []string) (code int, done bool) {
|
||||
if len(argv) < 2 || strings.HasPrefix(argv[1], "-") {
|
||||
return 0, false
|
||||
}
|
||||
|
||||
if argv[1] == Word {
|
||||
return Run(argv[2:]), true
|
||||
}
|
||||
|
||||
return unknownCommand(argv[1]), true
|
||||
}
|
||||
|
||||
// Trailing handles the words the daemon's flag parser leaves unparsed: flag.Parse stops
|
||||
// at the first argument that is not a flag and hands the rest back. rest is flag.Args()
|
||||
// after the daemon has parsed, and configPath is the config the daemon's -config named,
|
||||
// "" when it did not. Both daemon binaries call it right after flag.Parse, so that
|
||||
// `nebula -config x ctl identity` runs the client and `nebula -config x clt` reports a
|
||||
// typo, as Subcommand does for a word at the front of the line; a daemon that ignored
|
||||
// the words would start in their place.
|
||||
//
|
||||
// A leading ctl word runs the client on what follows, with the daemon's -config carried
|
||||
// over: an operator who typed it meant the daemon running on that config, and the client
|
||||
// derives the same socket from it. Any other word is a mistake, reported as Subcommand
|
||||
// reports one.
|
||||
func Trailing(rest []string, configPath string) (code int, done bool) {
|
||||
if len(rest) == 0 {
|
||||
return 0, false
|
||||
}
|
||||
|
||||
if rest[0] != Word {
|
||||
return unknownCommand(rest[0]), true
|
||||
}
|
||||
|
||||
args := rest[1:]
|
||||
if configPath != "" {
|
||||
// First, so a -config on the ctl side of the line still wins: Parse applies
|
||||
// flags in order and the last value set is the one read.
|
||||
args = append([]string{"-" + commands.FlagConfig, configPath}, args...)
|
||||
}
|
||||
|
||||
return Run(args), true
|
||||
}
|
||||
|
||||
// unknownCommand reports a bare word that is neither a flag nor ctl, with the one usage
|
||||
// line that says what the two forms of the command line are.
|
||||
func unknownCommand(word string) int {
|
||||
fmt.Fprintf(os.Stderr, "nebula: unknown command %q\n\n", word)
|
||||
fmt.Fprintf(os.Stderr, "Run nebula with flags to start it, or `nebula %s <command>` to control one that is already running.\n", Word)
|
||||
return 1
|
||||
}
|
||||
|
||||
// Run implements `nebula ctl <command> [args]`
|
||||
//
|
||||
// args is everything after the `ctl` word.
|
||||
func Run(args []string) int {
|
||||
fs := flag.NewFlagSet("nebula ctl", flag.ContinueOnError)
|
||||
fs.SetOutput(os.Stderr)
|
||||
|
||||
configPath := fs.String(commands.FlagConfig, "", "Path to the config of the running nebula, used to locate its control socket")
|
||||
socketPath := fs.String(commands.FlagSocket, "", "Path to the control socket, instead of the one the config implies")
|
||||
fs.Usage = func() {
|
||||
fmt.Fprintf(os.Stderr, "Usage: nebula ctl [flags] <command> [command flags]\n\n")
|
||||
fmt.Fprintf(os.Stderr, "Inspects and controls a nebula already running on this machine.\n")
|
||||
fmt.Fprintf(os.Stderr, "Run it as the user who ran nebula, or as a member of the group %s names.\n\n", localapi.CtlGroupKey)
|
||||
fmt.Fprintf(os.Stderr, "Flags, which may come before or after the command:\n")
|
||||
fs.PrintDefaults()
|
||||
fmt.Fprintf(os.Stderr, "\nRun `nebula ctl help` for the available commands.\n")
|
||||
}
|
||||
|
||||
own, cmdArgs := splitLine(fs, args)
|
||||
if err := fs.Parse(own); err != nil {
|
||||
// fs has already printed the usage, or the problem. Asking for help is not a
|
||||
// failure, and a script that chains on `nebula ctl -h` should not see one.
|
||||
if errors.Is(err, flag.ErrHelp) {
|
||||
return 0
|
||||
}
|
||||
return 1
|
||||
}
|
||||
|
||||
if len(cmdArgs) == 0 {
|
||||
cmdArgs = []string{"help"}
|
||||
}
|
||||
|
||||
path, err := resolveSocket(*socketPath, *configPath)
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "%s\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
client := &localapi.Client{Path: path}
|
||||
|
||||
// Ask the daemon what it serves before parsing anything. The flags belong to the
|
||||
// command, which lives over there, so this is what lets the CLI keep its usual shape
|
||||
// while the wire protocol stays a named-parameter API rather than a shipped argv.
|
||||
schema, err := client.Describe()
|
||||
if err != nil {
|
||||
// A daemon that answered was reached, and what it said, or that it could not be
|
||||
// read, is the whole message.
|
||||
var refused *localapi.DaemonError
|
||||
var unread *localapi.ReplyError
|
||||
if errors.As(err, &refused) || errors.As(err, &unread) {
|
||||
fmt.Fprintf(os.Stderr, "nebula: %s\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
// Otherwise the operating system said why, and it is passed on as it came: a
|
||||
// permission denied or a missing socket says more about what to do than a
|
||||
// guess at the operator's setup would.
|
||||
fmt.Fprintf(os.Stderr, "nebula: could not reach the control socket at %s: %s\n", path, err)
|
||||
return 1
|
||||
}
|
||||
|
||||
req, printedHelp, err := parseCommand(schema, cmdArgs)
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "%s\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
if printedHelp {
|
||||
return 0
|
||||
}
|
||||
|
||||
res, err := client.Invoke(string(req.name), req.Params, req.Args, wireFormat(req.Format))
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "nebula: %s\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
out := output(res, req.Format)
|
||||
if out != "" {
|
||||
fmt.Fprint(os.Stdout, out)
|
||||
if !strings.HasSuffix(out, "\n") {
|
||||
fmt.Fprintln(os.Stdout)
|
||||
}
|
||||
}
|
||||
|
||||
// Error set is the one failure signal, whether the request never ran or the command
|
||||
// ran and refused. A refusal asked for in JSON has already gone to stdout as the
|
||||
// {ok, reason} object, and is not said again on stderr; the exit status carries it.
|
||||
if res.Error == "" {
|
||||
return 0
|
||||
}
|
||||
|
||||
if len(res.Result) == 0 && len(res.Text) == 0 {
|
||||
msg := res.Error
|
||||
if !strings.HasSuffix(msg, "\n") {
|
||||
msg += "\n"
|
||||
}
|
||||
fmt.Fprint(os.Stderr, msg)
|
||||
}
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
// output renders what the daemon answered for the format the line asked for. A text
|
||||
// request is answered in Text with the bytes the command wrote, printed as they are; a
|
||||
// JSON request is answered in Result with the value itself, printed as it came, since a
|
||||
// value that happens to be a string is still JSON to the script reading it. Indentation
|
||||
// is the client's business: whitespace does not survive a JSON envelope, and the daemon
|
||||
// has no reason to care how its answer is laid out. The bytes are re-indented rather
|
||||
// than decoded and encoded again, which would sort the keys and round the numbers.
|
||||
func output(res *localapi.Response, format commands.Format) string {
|
||||
switch format {
|
||||
case commands.FormatJSON:
|
||||
return string(res.Result)
|
||||
case commands.FormatPrettyJSON:
|
||||
var buf bytes.Buffer
|
||||
if err := json.Indent(&buf, res.Result, "", " "); err != nil {
|
||||
return string(res.Result)
|
||||
}
|
||||
return buf.String()
|
||||
default:
|
||||
return string(res.Text)
|
||||
}
|
||||
}
|
||||
|
||||
// ctlRequest is one parsed nebula ctl command line: the command's name, which only the
|
||||
// daemon can resolve, and the line as every surface parses it. The Request's Command is
|
||||
// nil here, since the CLI holds a schema rather than the command, and its Format is
|
||||
// FormatUnset when the line named none, which to nebula ctl means text: its default
|
||||
// differs from the API's.
|
||||
type ctlRequest struct {
|
||||
name commands.Name
|
||||
commands.Request
|
||||
}
|
||||
|
||||
// wireFormat is what a request asks the daemon for. Pretty is the client's business,
|
||||
// since whitespace does not survive a JSON envelope, so it travels as json. No
|
||||
// preference is text, nebula ctl's default: a person gets the human rendering wherever
|
||||
// one exists.
|
||||
func wireFormat(f commands.Format) string {
|
||||
switch f {
|
||||
case commands.FormatJSON, commands.FormatPrettyJSON:
|
||||
return "json"
|
||||
default:
|
||||
return "text"
|
||||
}
|
||||
}
|
||||
|
||||
// parseCommand turns the user's command line into a ctlRequest, using the schema the
|
||||
// daemon supplied. The line is parsed with the same rules the daemon applies to an ssh
|
||||
// line, through ParseArgs, and ParseLine reads what was set into the Request to send, so
|
||||
// a line means the same on both.
|
||||
//
|
||||
// printedHelp reports that help was written for the command instead, and there is
|
||||
// nothing to send.
|
||||
func parseCommand(schema []commands.CommandSchema, argv []string) (req ctlRequest, printedHelp bool, err error) {
|
||||
name := commands.Name(argv[0])
|
||||
|
||||
var found *commands.CommandSchema
|
||||
for i := range schema {
|
||||
if schema[i].Name == name {
|
||||
found = &schema[i]
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
if found == nil {
|
||||
// Let the daemon answer. It knows whether this is a typo or a command it holds
|
||||
// back, and its message for the second case is better than anything guessable
|
||||
// from the schema alone.
|
||||
return ctlRequest{name: name, Request: commands.Request{Args: argv[1:]}}, false, nil
|
||||
}
|
||||
|
||||
// The flag package's own report is a bare message followed by a usage dump in a layout
|
||||
// that does not match WriteCommandHelp, so it is silenced and the error is reported
|
||||
// once, below, with a pointer at the help this command actually prints.
|
||||
fs := flag.NewFlagSet(string(name), flag.ContinueOnError)
|
||||
fs.SetOutput(io.Discard)
|
||||
|
||||
for _, f := range found.Flags {
|
||||
if f.Bool {
|
||||
fs.Bool(f.Name, f.Default == "true", f.Usage)
|
||||
continue
|
||||
}
|
||||
fs.String(f.Name, f.Default, f.Usage)
|
||||
}
|
||||
|
||||
operands, err := commands.ParseArgs(fs, argv[1:])
|
||||
if err != nil {
|
||||
if errors.Is(err, flag.ErrHelp) {
|
||||
// The same rendering the daemon uses for `help <command>`, so -h and help agree.
|
||||
_ = commands.WriteCommandHelp(*found, os.Stdout)
|
||||
return ctlRequest{}, true, nil
|
||||
}
|
||||
|
||||
// Say what flag did: an unknown flag, a missing value and a malformed value are
|
||||
// different mistakes, and "does not take" would be wrong for two of them.
|
||||
return ctlRequest{}, false, fmt.Errorf("nebula: %s: %s (see 'nebula ctl %s -h')", name, err, name)
|
||||
}
|
||||
|
||||
// Only what the user actually set travels. A parameter left alone is the daemon's
|
||||
// default to apply, not the client's to assert, and the presentation flags are the
|
||||
// client's to interpret, never sent.
|
||||
//
|
||||
// Where the command has no human form the daemon says so, and only once the command
|
||||
// has run: a refusal ("No vpn address was provided") always has a human form, so
|
||||
// telling the user to pass -json before finding out whether the command would even
|
||||
// accept the line sends them to fix the wrong thing. That is why the schema does not
|
||||
// say which commands have a human form: nothing should decide on it before running.
|
||||
return ctlRequest{name: name, Request: commands.ParseLine(fs, operands)}, false, nil
|
||||
}
|
||||
|
||||
// splitLine divides a nebula ctl line into the client's own flags, for fs to parse, and
|
||||
// the command line to send, which begins with the command word. The client's flags may
|
||||
// come before the command or after it: `nebula ctl -config x identity` and
|
||||
// `nebula ctl identity -config x` mean the same, so an operator who has typed a command
|
||||
// and then remembers which daemon they meant does not have to retype the line.
|
||||
//
|
||||
// Before the command word every flag is the client's, whatever it is, so an unknown one
|
||||
// is reported by fs, and -h is the client's usage. After it only the
|
||||
// flags fs defines are lifted out, and only those: the command's own flags are unknown
|
||||
// here, since they come from the daemon the line has yet to name, and -h after the
|
||||
// command asks for that command's help. Which command flags take a value is unknown too,
|
||||
// so the client's names are reserved in the commands package and no command can give
|
||||
// one a value that would be lifted from here. A "--" before the command is consumed, as
|
||||
// fs.Parse would have; one after it belongs to the command line and ends the lifting,
|
||||
// so an operand spelled like a client flag can still be passed.
|
||||
func splitLine(fs *flag.FlagSet, args []string) (own, cmd []string) {
|
||||
seenCommand := false
|
||||
for i := 0; i < len(args); i++ {
|
||||
a := args[i]
|
||||
|
||||
if a == "--" {
|
||||
if seenCommand {
|
||||
return own, append(cmd, args[i:]...)
|
||||
}
|
||||
seenCommand = true
|
||||
continue
|
||||
}
|
||||
|
||||
if !seenCommand {
|
||||
if len(a) < 2 || a[0] != '-' {
|
||||
seenCommand = true
|
||||
cmd = append(cmd, a)
|
||||
continue
|
||||
}
|
||||
|
||||
own = append(own, a)
|
||||
if f, hasValue := commands.LookupArg(fs, a); f != nil && !hasValue && !commands.IsBoolFlag(f) && i+1 < len(args) {
|
||||
i++
|
||||
own = append(own, args[i])
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
if len(a) >= 2 && a[0] == '-' {
|
||||
// The same reading of the argument ParseArgs makes, so a word this lifts as a
|
||||
// client flag's value is one the daemon's parser would have read the same way.
|
||||
if f, hasValue := commands.LookupArg(fs, a); f != nil {
|
||||
own = append(own, a)
|
||||
if !hasValue && !commands.IsBoolFlag(f) && i+1 < len(args) {
|
||||
i++
|
||||
own = append(own, args[i])
|
||||
}
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
cmd = append(cmd, a)
|
||||
}
|
||||
|
||||
return own, cmd
|
||||
}
|
||||
|
||||
// resolveSocket decides which socket to talk to. It never searches: the answer is the
|
||||
// socket the operator named, or the one the config implies, and nothing else.
|
||||
//
|
||||
// An explicit flag wins. Otherwise the config is read, the one the operator named or the
|
||||
// one found next to the executable, and the path is the socket that config implies: its
|
||||
// local_api.control.socket if set, else the same derivation the daemon applies.
|
||||
func resolveSocket(socketFlag, configFlag string) (string, error) {
|
||||
if socketFlag != "" {
|
||||
return socketFlag, nil
|
||||
}
|
||||
|
||||
return pathFromConfig(configFlag)
|
||||
}
|
||||
|
||||
// pathFromConfig returns the socket path the daemon would be serving: the one
|
||||
// local_api.control.socket names in the config, so an operator who moved the socket does
|
||||
// not have to repeat themselves on every invocation, else the default.
|
||||
//
|
||||
// A config the operator did not name is a guess: config.DefaultPath looks next to the
|
||||
// executable, and a package that installs a default config there while systemd starts
|
||||
// the daemon with another will make it the wrong guess. It is still the only answer
|
||||
// that involves no searching. A guess that cannot be read is not an error, it is no
|
||||
// guess: a member of the socket's group cannot read a root daemon's config, and is
|
||||
// answered by the default path, where the daemon serves unless that config moved it.
|
||||
// A config the operator named is theirs to make readable.
|
||||
func pathFromConfig(configFlag string) (string, error) {
|
||||
return socketFromConfigFile(configFlag, configFlag != "")
|
||||
}
|
||||
|
||||
func socketFromConfigFile(configPath string, named bool) (string, error) {
|
||||
if !named {
|
||||
p, err := config.DefaultPath()
|
||||
if err != nil {
|
||||
return localapi.DefaultSocketPath, nil
|
||||
}
|
||||
configPath = p
|
||||
}
|
||||
|
||||
// The config is loaded only to find the socket path. Loading logs lines that belong
|
||||
// to the daemon, not to someone running a read only command, and mixing them into
|
||||
// the CLI's output would corrupt a -json result, so they are discarded.
|
||||
c := config.NewC(slog.New(slog.DiscardHandler))
|
||||
if err := c.Load(configPath); err != nil {
|
||||
if !named {
|
||||
return localapi.DefaultSocketPath, nil
|
||||
}
|
||||
// The operating system's error, as it came: permission denied on a root daemon's
|
||||
// config says what to do.
|
||||
return "", fmt.Errorf("nebula: could not read %s: %w", configPath, err)
|
||||
}
|
||||
|
||||
// A daemon running this config serves no socket; dialing the path would only say
|
||||
// that nothing is there.
|
||||
if !localapi.ControlEnabled(c) {
|
||||
return "", fmt.Errorf("nebula: the control socket is disabled in %s by %s", configPath, localapi.CtlEnabledKey)
|
||||
}
|
||||
|
||||
// The same call the daemon makes, so the two agree on the path and on what makes a
|
||||
// path unusable.
|
||||
p, err := localapi.SocketPathFromConfig(c)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("nebula: %w", err)
|
||||
}
|
||||
|
||||
return p, nil
|
||||
}
|
||||
@@ -0,0 +1,294 @@
|
||||
package ctl
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"flag"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestResolveSocketReportsAnUnreadableConfig: an operator who named a config must hear
|
||||
// that it could not be read, rather than have the command steered anywhere else.
|
||||
func TestResolveSocketReportsAnUnreadableConfig(t *testing.T) {
|
||||
missing := filepath.Join(t.TempDir(), "typo.yml")
|
||||
|
||||
_, err := resolveSocket("", missing)
|
||||
require.Error(t, err)
|
||||
assert.Contains(t, err.Error(), missing)
|
||||
}
|
||||
|
||||
// TestResolveSocketGuessedConfigNeedNotBeReadable: a config nobody named is a guess, and
|
||||
// one that cannot be read, a root daemon's config read by a member of the socket's
|
||||
// group, means the default path rather than an error.
|
||||
func TestResolveSocketGuessedConfigNeedNotBeReadable(t *testing.T) {
|
||||
missing := filepath.Join(t.TempDir(), "config.yml")
|
||||
|
||||
p, err := socketFromConfigFile(missing, false)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, localapi.DefaultSocketPath, p)
|
||||
|
||||
_, err = socketFromConfigFile(missing, true)
|
||||
require.ErrorContains(t, err, missing)
|
||||
}
|
||||
|
||||
// nowhereSocket is a socket name nothing listens on, spelled the way the platform
|
||||
// requires: a full pipe name on windows, an absolute path elsewhere.
|
||||
var nowhereSocket = map[bool]string{true: `\\.\pipe\nebula-nowhere`, false: "/nowhere/ctl.sock"}[runtime.GOOS == "windows"]
|
||||
|
||||
// namedSocketConfig is a config that names nowhereSocket as the control socket. Single
|
||||
// quotes keep a pipe name's backslashes literal in YAML.
|
||||
var namedSocketConfig = "local_api:\n control:\n socket: '" + nowhereSocket + "'\n"
|
||||
|
||||
// TestResolveSocketTrustsANamedConfig: a config the operator named yields the socket it
|
||||
// implies even when nothing is listening there, so a dial failure names that socket.
|
||||
func TestResolveSocketTrustsANamedConfig(t *testing.T) {
|
||||
cfg := filepath.Join(t.TempDir(), "config.yml")
|
||||
require.NoError(t, os.WriteFile(cfg, []byte(namedSocketConfig), 0600))
|
||||
|
||||
p, err := resolveSocket("", cfg)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, nowhereSocket, p)
|
||||
}
|
||||
|
||||
// TestResolveSocketSaysTheSocketIsDisabled: a config that turns the control socket off
|
||||
// is answered with that, not with a dial to a path nothing serves. -socket still wins.
|
||||
func TestResolveSocketSaysTheSocketIsDisabled(t *testing.T) {
|
||||
cfg := filepath.Join(t.TempDir(), "config.yml")
|
||||
require.NoError(t, os.WriteFile(cfg, []byte("local_api:\n control:\n enabled: false\n"), 0600))
|
||||
|
||||
_, err := resolveSocket("", cfg)
|
||||
require.ErrorContains(t, err, "the control socket is disabled in "+cfg+" by local_api.control.enabled")
|
||||
|
||||
p, err := resolveSocket("/explicit.sock", cfg)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "/explicit.sock", p)
|
||||
}
|
||||
|
||||
// TestResolveSocketUsesTheDefaultWithoutAnOverride: a config that does not name the
|
||||
// socket means the default path, the same one the daemon serves with that config, and
|
||||
// no config at all means the default too, since that is where a daemon started without
|
||||
// an override serves. Nothing is searched for.
|
||||
func TestResolveSocketUsesTheDefaultWithoutAnOverride(t *testing.T) {
|
||||
cfg := filepath.Join(t.TempDir(), "config.yml")
|
||||
require.NoError(t, os.WriteFile(cfg, []byte("static_host_map: {}\n"), 0600))
|
||||
|
||||
p, err := resolveSocket("", cfg)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, localapi.DefaultSocketPath, p)
|
||||
|
||||
// The test binary has no config next to it.
|
||||
p, err = resolveSocket("", "")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, localapi.DefaultSocketPath, p)
|
||||
}
|
||||
|
||||
func TestResolveSocketFlagWins(t *testing.T) {
|
||||
p, err := resolveSocket("/explicit.sock", "/does/not/matter.yml")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "/explicit.sock", p)
|
||||
}
|
||||
|
||||
// TestParseCommandReportsWhatFlagSaid covers the three ways a flag line goes wrong, which
|
||||
// are different mistakes: an unknown flag, a valid flag with a missing value, and a
|
||||
// valid flag with a value it cannot parse.
|
||||
func TestParseCommandReportsWhatFlagSaid(t *testing.T) {
|
||||
schema := []commands.CommandSchema{{
|
||||
Name: "change-remote",
|
||||
Flags: []commands.FlagSchema{
|
||||
{Name: "address"},
|
||||
{Name: "by-index", Bool: true},
|
||||
},
|
||||
}}
|
||||
|
||||
cases := map[string]struct {
|
||||
argv []string
|
||||
want string
|
||||
}{
|
||||
"missing value": {[]string{"change-remote", "-address"}, "flag needs an argument: -address"},
|
||||
"bad bool": {[]string{"change-remote", "-by-index=maybe"}, "invalid boolean value \"maybe\" for -by-index"},
|
||||
"unknown flag": {[]string{"change-remote", "-nope"}, "flag provided but not defined: -nope"},
|
||||
}
|
||||
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
_, _, err := parseCommand(schema, tc.argv)
|
||||
require.Error(t, err)
|
||||
require.ErrorContains(t, err, "nebula: change-remote: "+tc.want)
|
||||
require.ErrorContains(t, err, "see 'nebula ctl change-remote -h'")
|
||||
assert.NotContains(t, err.Error(), "does not take")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestParseCommandOffPresentationFlagIsNoPreference: the daemon treats -json=false as
|
||||
// no preference, so nebula ctl must too, or the same line renders differently on the
|
||||
// two surfaces. Only a true value asks for JSON, and -pretty implies it.
|
||||
func TestParseCommandOffPresentationFlagIsNoPreference(t *testing.T) {
|
||||
schema := []commands.CommandSchema{{
|
||||
Name: "device-info",
|
||||
Flags: []commands.FlagSchema{
|
||||
{Name: commands.FlagJSON, Bool: true, Default: "false"},
|
||||
{Name: commands.FlagPretty, Bool: true, Default: "false"},
|
||||
},
|
||||
}}
|
||||
|
||||
for _, tc := range []struct {
|
||||
argv []string
|
||||
want commands.Format
|
||||
wire string
|
||||
}{
|
||||
{[]string{"device-info"}, commands.FormatUnset, "text"},
|
||||
{[]string{"device-info", "-json=false"}, commands.FormatUnset, "text"},
|
||||
{[]string{"device-info", "-json"}, commands.FormatJSON, "json"},
|
||||
{[]string{"device-info", "-pretty"}, commands.FormatPrettyJSON, "json"},
|
||||
} {
|
||||
t.Run(strings.Join(tc.argv[1:], " "), func(t *testing.T) {
|
||||
req, printedHelp, err := parseCommand(schema, tc.argv)
|
||||
require.NoError(t, err)
|
||||
assert.False(t, printedHelp)
|
||||
assert.Equal(t, tc.want, req.Format)
|
||||
assert.Equal(t, tc.wire, wireFormat(req.Format))
|
||||
assert.Nil(t, req.Params, "presentation flags are never sent as parameters")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestParseCommandReadsTheLineAsTheDaemonDoes: nebula ctl parses the line with the same
|
||||
// rules as the daemon, so an operand after "--" reaches the command on both and a
|
||||
// negative number before it is the flag it would be at an ssh prompt.
|
||||
func TestParseCommandReadsTheLineAsTheDaemonDoes(t *testing.T) {
|
||||
schema := []commands.CommandSchema{{Name: "set"}}
|
||||
|
||||
req, printedHelp, err := parseCommand(schema, []string{"set", "--", "-1"})
|
||||
require.NoError(t, err)
|
||||
assert.False(t, printedHelp)
|
||||
assert.Equal(t, commands.Name("set"), req.name)
|
||||
assert.Nil(t, req.Params)
|
||||
assert.Equal(t, []string{"-1"}, req.Args)
|
||||
|
||||
_, _, err = parseCommand(schema, []string{"set", "-1"})
|
||||
require.ErrorContains(t, err, "flag provided but not defined: -1")
|
||||
}
|
||||
|
||||
// TestOutputRendersForTheFormatAsked: what the daemon answered is read by the format the
|
||||
// line asked for, never by sniffing the bytes. A text answer is the command's rendering,
|
||||
// printed as it came; a JSON answer whose value is a string stays quoted, since to the
|
||||
// script reading it that string is the JSON.
|
||||
func TestOutputRendersForTheFormatAsked(t *testing.T) {
|
||||
text := &localapi.Response{Text: []byte("Log level is: info\n")}
|
||||
assert.Equal(t, "Log level is: info\n", output(text, commands.FormatUnset))
|
||||
assert.Equal(t, "Log level is: info\n", output(text, commands.FormatText))
|
||||
|
||||
str := &localapi.Response{Result: json.RawMessage(`"some string"`)}
|
||||
assert.Equal(t, `"some string"`, output(str, commands.FormatJSON))
|
||||
assert.Equal(t, `"some string"`, output(str, commands.FormatPrettyJSON))
|
||||
|
||||
// Keys stay in the order the daemon wrote them and a uint64 past 2^53 is not rounded,
|
||||
// which decoding into `any` and encoding again would do.
|
||||
obj := &localapi.Response{Result: json.RawMessage(`{"z":18446744073709551615,"a":{"y":[1,2],"b":true}}`)}
|
||||
//nolint:testifylint // the layout is what is under test, which JSONEq would not see
|
||||
assert.Equal(t, `{"z":18446744073709551615,"a":{"y":[1,2],"b":true}}`, output(obj, commands.FormatJSON))
|
||||
//nolint:testifylint // as above
|
||||
assert.Equal(t, "{\n \"z\": 18446744073709551615,\n \"a\": {\n \"y\": [\n 1,\n 2\n ],\n \"b\": true\n }\n}", output(obj, commands.FormatPrettyJSON))
|
||||
|
||||
bad := &localapi.Response{Result: json.RawMessage(`{"a":`)}
|
||||
assert.Equal(t, `{"a":`, output(bad, commands.FormatPrettyJSON), "what cannot be indented is printed as it came")
|
||||
|
||||
none := &localapi.Response{}
|
||||
assert.Empty(t, output(none, commands.FormatJSON))
|
||||
assert.Empty(t, output(none, commands.FormatUnset))
|
||||
}
|
||||
|
||||
// TestSplitLineLiftsOwnFlagsFromAnywhere: -config and -socket are the client's wherever
|
||||
// they appear, before the command or after it, in either spelling, so the two orders
|
||||
// mean the same line. Everything else after the command word stays in order for the
|
||||
// command's own parse, including flags and operands that happen to look like values.
|
||||
func TestSplitLineLiftsOwnFlagsFromAnywhere(t *testing.T) {
|
||||
newFS := func() *flag.FlagSet {
|
||||
fs := flag.NewFlagSet("nebula ctl", flag.ContinueOnError)
|
||||
fs.String(commands.FlagConfig, "", "")
|
||||
fs.String(commands.FlagSocket, "", "")
|
||||
return fs
|
||||
}
|
||||
|
||||
for _, tc := range []struct {
|
||||
args []string
|
||||
wantOwn []string
|
||||
wantCmd []string
|
||||
}{
|
||||
{nil, nil, nil},
|
||||
{[]string{"identity"}, nil, []string{"identity"}},
|
||||
{[]string{"-config", "x", "identity"}, []string{"-config", "x"}, []string{"identity"}},
|
||||
{[]string{"identity", "-config", "x"}, []string{"-config", "x"}, []string{"identity"}},
|
||||
{[]string{"identity", "-config=x"}, []string{"-config=x"}, []string{"identity"}},
|
||||
{[]string{"identity", "--socket", "s"}, []string{"--socket", "s"}, []string{"identity"}},
|
||||
{[]string{"-socket", "s", "identity", "-config", "x"}, []string{"-socket", "s", "-config", "x"}, []string{"identity"}},
|
||||
// The command's flags and operands are left where they are, around the lifted ones.
|
||||
{[]string{"print-tunnel", "10.0.0.1", "-config", "x", "-json"}, []string{"-config", "x"}, []string{"print-tunnel", "10.0.0.1", "-json"}},
|
||||
{[]string{"change-remote", "-address", "1.2.3.4:5", "-socket", "s", "10.0.0.1"}, []string{"-socket", "s"}, []string{"change-remote", "-address", "1.2.3.4:5", "10.0.0.1"}},
|
||||
// -h before the command is the client's usage; after it, the command's help.
|
||||
{[]string{"-h"}, []string{"-h"}, nil},
|
||||
{[]string{"identity", "-h"}, nil, []string{"identity", "-h"}},
|
||||
// An unknown flag before the command is the client's to report, and does not
|
||||
// swallow the command word as its value.
|
||||
{[]string{"-nope", "identity"}, []string{"-nope"}, []string{"identity"}},
|
||||
// A -config with nothing after it is left for fs.Parse to report.
|
||||
{[]string{"identity", "-config"}, []string{"-config"}, []string{"identity"}},
|
||||
// "--" before the command is consumed, as fs.Parse consumed it; after the command
|
||||
// it belongs to the line and ends the lifting.
|
||||
{[]string{"--", "identity", "-config", "x"}, []string{"-config", "x"}, []string{"identity"}},
|
||||
{[]string{"identity", "--", "-config", "x"}, nil, []string{"identity", "--", "-config", "x"}},
|
||||
} {
|
||||
t.Run(strings.Join(tc.args, " "), func(t *testing.T) {
|
||||
own, cmd := splitLine(newFS(), tc.args)
|
||||
assert.Equal(t, tc.wantOwn, own)
|
||||
assert.Equal(t, tc.wantCmd, cmd)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestTrailingHandlesWordsAfterTheDaemonsFlags: what flag.Parse leaves behind is never
|
||||
// a daemon to start. A leading ctl runs the client on the rest, with the daemon's
|
||||
// -config carried over; anything else is a mistyped subcommand. Only -h is run here,
|
||||
// since the client's help needs no daemon: it proves the words reach Run and that a
|
||||
// carried -config is accepted by it.
|
||||
func TestTrailingHandlesWordsAfterTheDaemonsFlags(t *testing.T) {
|
||||
code, done := Trailing(nil, "")
|
||||
assert.False(t, done)
|
||||
assert.Equal(t, 0, code)
|
||||
|
||||
code, done = Trailing([]string{"clt"}, "")
|
||||
assert.True(t, done)
|
||||
assert.Equal(t, 1, code)
|
||||
|
||||
code, done = Trailing([]string{Word, "-h"}, "")
|
||||
assert.True(t, done)
|
||||
assert.Equal(t, 0, code)
|
||||
|
||||
code, done = Trailing([]string{Word, "-h"}, "/etc/nebula/config.yml")
|
||||
assert.True(t, done)
|
||||
assert.Equal(t, 0, code)
|
||||
}
|
||||
|
||||
// TestSubcommandOnlyReadsTheFirstWord: a flag first means the line is the daemon's to
|
||||
// parse, and whatever follows the flags is Trailing's to judge.
|
||||
func TestSubcommandOnlyReadsTheFirstWord(t *testing.T) {
|
||||
_, done := Subcommand([]string{"nebula", "-config", "x", Word})
|
||||
assert.False(t, done)
|
||||
|
||||
code, done := Subcommand([]string{"nebula", "clt"})
|
||||
assert.True(t, done)
|
||||
assert.Equal(t, 1, code)
|
||||
|
||||
code, done = Subcommand([]string{"nebula", Word, "-h"})
|
||||
assert.True(t, done)
|
||||
assert.Equal(t, 0, code)
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
//go:build !windows
|
||||
|
||||
package ctl
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestResolveSocketDiagnosesAnOverlongOverride: the CLI applies the daemon's own rule to
|
||||
// the override, so it says what the daemon's log says rather than dialing a path the
|
||||
// kernel would truncate and reporting the generic failure. The rule is sun_path's, which
|
||||
// a named pipe does not have, so this is a unix test.
|
||||
func TestResolveSocketDiagnosesAnOverlongOverride(t *testing.T) {
|
||||
cfg := filepath.Join(t.TempDir(), "config.yml")
|
||||
long := "/" + strings.Repeat("x", 120)
|
||||
require.NoError(t, os.WriteFile(cfg, []byte("local_api:\n control:\n socket: "+long+"\n"), 0600))
|
||||
|
||||
_, err := resolveSocket("", cfg)
|
||||
require.Error(t, err)
|
||||
require.ErrorContains(t, err, "too long for this platform")
|
||||
assert.ErrorContains(t, err, localapi.CtlSocketKey)
|
||||
}
|
||||
|
||||
// TestResolveSocketRefusesARelativeOverride: the CLI applies the daemon's rule here too,
|
||||
// so a relative path in the config is reported as the daemon's log reports it rather
|
||||
// than resolved against wherever nebula ctl happened to be run from.
|
||||
func TestResolveSocketRefusesARelativeOverride(t *testing.T) {
|
||||
cfg := filepath.Join(t.TempDir(), "config.yml")
|
||||
require.NoError(t, os.WriteFile(cfg, []byte("local_api:\n control:\n socket: run/ctl.sock\n"), 0600))
|
||||
|
||||
_, err := resolveSocket("", cfg)
|
||||
require.Error(t, err)
|
||||
require.ErrorContains(t, err, "must be an absolute path")
|
||||
assert.ErrorContains(t, err, localapi.CtlSocketKey)
|
||||
}
|
||||
@@ -151,7 +151,7 @@ func ca(args []string, out io.Writer, errOut io.Writer, pr PasswordReader) error
|
||||
|
||||
var groups []string
|
||||
if *cf.groups != "" {
|
||||
for _, rg := range strings.Split(*cf.groups, ",") {
|
||||
for rg := range strings.SplitSeq(*cf.groups, ",") {
|
||||
g := strings.TrimSpace(rg)
|
||||
if g != "" {
|
||||
groups = append(groups, g)
|
||||
@@ -171,7 +171,7 @@ func ca(args []string, out io.Writer, errOut io.Writer, pr PasswordReader) error
|
||||
}
|
||||
|
||||
if *cf.networks != "" {
|
||||
for _, rs := range strings.Split(*cf.networks, ",") {
|
||||
for rs := range strings.SplitSeq(*cf.networks, ",") {
|
||||
rs := strings.Trim(rs, " ")
|
||||
if rs != "" {
|
||||
n, err := netip.ParsePrefix(rs)
|
||||
@@ -193,7 +193,7 @@ func ca(args []string, out io.Writer, errOut io.Writer, pr PasswordReader) error
|
||||
}
|
||||
|
||||
if *cf.unsafeNetworks != "" {
|
||||
for _, rs := range strings.Split(*cf.unsafeNetworks, ",") {
|
||||
for rs := range strings.SplitSeq(*cf.unsafeNetworks, ",") {
|
||||
rs := strings.Trim(rs, " ")
|
||||
if rs != "" {
|
||||
n, err := netip.ParsePrefix(rs)
|
||||
@@ -221,7 +221,7 @@ func ca(args []string, out io.Writer, errOut io.Writer, pr PasswordReader) error
|
||||
if !isP11 && *cf.encryption {
|
||||
passphrase = []byte(os.Getenv("NEBULA_CA_PASSPHRASE"))
|
||||
if len(passphrase) == 0 {
|
||||
for i := 0; i < 5; i++ {
|
||||
for range 5 {
|
||||
errOut.Write([]byte("Enter passphrase: "))
|
||||
passphrase, err = pr.ReadPassword()
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build !windows
|
||||
// +build !windows
|
||||
|
||||
package main
|
||||
|
||||
|
||||
@@ -146,7 +146,7 @@ func signCert(args []string, out io.Writer, errOut io.Writer, pr PasswordReader)
|
||||
passphrase = []byte(os.Getenv("NEBULA_CA_PASSPHRASE"))
|
||||
if len(passphrase) == 0 {
|
||||
// ask for a passphrase until we get one
|
||||
for i := 0; i < 5; i++ {
|
||||
for range 5 {
|
||||
errOut.Write([]byte("Enter passphrase: "))
|
||||
passphrase, err = pr.ReadPassword()
|
||||
|
||||
@@ -203,7 +203,7 @@ func signCert(args []string, out io.Writer, errOut io.Writer, pr PasswordReader)
|
||||
}
|
||||
|
||||
if *sf.networks != "" {
|
||||
for _, rs := range strings.Split(*sf.networks, ",") {
|
||||
for rs := range strings.SplitSeq(*sf.networks, ",") {
|
||||
rs := strings.Trim(rs, " ")
|
||||
if rs != "" {
|
||||
n, err := netip.ParsePrefix(rs)
|
||||
@@ -228,7 +228,7 @@ func signCert(args []string, out io.Writer, errOut io.Writer, pr PasswordReader)
|
||||
}
|
||||
|
||||
if *sf.unsafeNetworks != "" {
|
||||
for _, rs := range strings.Split(*sf.unsafeNetworks, ",") {
|
||||
for rs := range strings.SplitSeq(*sf.unsafeNetworks, ",") {
|
||||
rs := strings.Trim(rs, " ")
|
||||
if rs != "" {
|
||||
n, err := netip.ParsePrefix(rs)
|
||||
@@ -247,7 +247,7 @@ func signCert(args []string, out io.Writer, errOut io.Writer, pr PasswordReader)
|
||||
|
||||
var groups []string
|
||||
if *sf.groups != "" {
|
||||
for _, rg := range strings.Split(*sf.groups, ",") {
|
||||
for rg := range strings.SplitSeq(*sf.groups, ",") {
|
||||
g := strings.TrimSpace(rg)
|
||||
if g != "" {
|
||||
groups = append(groups, g)
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build !windows
|
||||
// +build !windows
|
||||
|
||||
package main
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build !windows
|
||||
// +build !windows
|
||||
|
||||
package main
|
||||
|
||||
|
||||
@@ -8,7 +8,9 @@ import (
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula"
|
||||
"github.com/slackhq/nebula/cmd/internal/ctl"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
@@ -32,6 +34,11 @@ func init() {
|
||||
}
|
||||
|
||||
func main() {
|
||||
// commands are either `nebula ctl ...` or `nebula -<flag> ...`
|
||||
if code, done := ctl.Subcommand(os.Args); done {
|
||||
os.Exit(code)
|
||||
}
|
||||
|
||||
serviceFlag := flag.String("service", "", "Control the system service.")
|
||||
configPath := flag.String("config", "", "Path to either a file or directory to load configuration from")
|
||||
configTest := flag.Bool("test", false, "Test the config and print the end result. Non zero exit indicates a faulty config")
|
||||
@@ -40,6 +47,12 @@ func main() {
|
||||
|
||||
flag.Parse()
|
||||
|
||||
// A word after the daemon's flags is `ctl` in the other place an operator puts it,
|
||||
// or a mistyped subcommand, and either way not a daemon to start; see Trailing.
|
||||
if code, done := ctl.Trailing(flag.Args(), *configPath); done {
|
||||
os.Exit(code)
|
||||
}
|
||||
|
||||
if *printVersion {
|
||||
fmt.Printf("Version: %s\n", Build)
|
||||
os.Exit(0)
|
||||
@@ -85,9 +98,10 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -103,9 +117,17 @@ func main() {
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
ctl := localapi.Wire(ctrl.Context(), l, c, ctrl.Commands())
|
||||
|
||||
go ctrl.ShutdownBlock()
|
||||
|
||||
if err := ctrl.Wait(); err != nil {
|
||||
err := ctrl.Wait()
|
||||
|
||||
// os.Exit skips deferred calls, so the socket is removed here, before either exit
|
||||
// below, rather than left to a deferred Stop that would never run.
|
||||
ctl.Stop()
|
||||
|
||||
if err != nil {
|
||||
l.Error("Nebula stopped due to fatal error", "error", err)
|
||||
os.Exit(2)
|
||||
}
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"github.com/kardianos/service"
|
||||
"github.com/slackhq/nebula"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
@@ -17,6 +18,7 @@ type program struct {
|
||||
configPath *string
|
||||
build string
|
||||
control *nebula.Control
|
||||
ctl *localapi.Server
|
||||
}
|
||||
|
||||
func (p *program) Start(s service.Service) error {
|
||||
@@ -34,9 +36,10 @@ func (p *program) Start(s service.Service) error {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
return fmt.Errorf("failed to apply logging config: %s", err)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -49,10 +52,16 @@ func (p *program) Start(s service.Service) error {
|
||||
return err
|
||||
}
|
||||
|
||||
// Now that we're started, stand up the local control socket.
|
||||
p.ctl = localapi.Wire(p.control.Context(), l, c, p.control.Commands())
|
||||
|
||||
// Nebula can stop itself on a fatal packet reader error, make sure to log it if it happens.
|
||||
go func() {
|
||||
if err := p.control.Wait(); err != nil {
|
||||
logger.Error(fmt.Sprintf("Nebula stopped due to fatal error: %v", err))
|
||||
// os.Exit skips deferred calls and races the socket's own context watcher,
|
||||
// so the socket is removed here, as cmd/nebula does.
|
||||
p.ctl.Stop()
|
||||
os.Exit(2)
|
||||
}
|
||||
}()
|
||||
@@ -62,6 +71,11 @@ func (p *program) Start(s service.Service) error {
|
||||
|
||||
func (p *program) Stop(s service.Service) error {
|
||||
logger.Info("Nebula service stopping.")
|
||||
|
||||
if p.ctl != nil {
|
||||
p.ctl.Stop()
|
||||
}
|
||||
|
||||
if p.control == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
+24
-2
@@ -8,7 +8,9 @@ import (
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula"
|
||||
"github.com/slackhq/nebula/cmd/internal/ctl"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/localapi"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
@@ -32,6 +34,11 @@ func init() {
|
||||
}
|
||||
|
||||
func main() {
|
||||
// commands are either `nebula ctl ...` or `nebula -<flag> ...`
|
||||
if code, done := ctl.Subcommand(os.Args); done {
|
||||
os.Exit(code)
|
||||
}
|
||||
|
||||
configPath := flag.String("config", "", "Path to either a file or directory to load configuration from")
|
||||
configTest := flag.Bool("test", false, "Test the config and print the end result. Non zero exit indicates a faulty config")
|
||||
printVersion := flag.Bool("version", false, "Print version")
|
||||
@@ -39,6 +46,12 @@ func main() {
|
||||
|
||||
flag.Parse()
|
||||
|
||||
// A word after the daemon's flags is `ctl` in the other place an operator puts it,
|
||||
// or a mistyped subcommand, and either way not a daemon to start; see Trailing.
|
||||
if code, done := ctl.Trailing(flag.Args(), *configPath); done {
|
||||
os.Exit(code)
|
||||
}
|
||||
|
||||
if *printVersion {
|
||||
fmt.Printf("Version: %s\n", Build)
|
||||
os.Exit(0)
|
||||
@@ -71,9 +84,10 @@ func main() {
|
||||
fmt.Printf("failed to apply logging config: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := logging.ApplyConfig(l, c); err != nil {
|
||||
l.Error("Failed to reconfigure logger on reload", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -89,10 +103,18 @@ func main() {
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
ctl := localapi.Wire(ctrl.Context(), l, c, ctrl.Commands())
|
||||
|
||||
go ctrl.ShutdownBlock()
|
||||
notifyReady(l)
|
||||
|
||||
if err := ctrl.Wait(); err != nil {
|
||||
err := ctrl.Wait()
|
||||
|
||||
// os.Exit skips deferred calls, so the socket is removed here, before either exit
|
||||
// below, rather than left to a deferred Stop that would never run.
|
||||
ctl.Stop()
|
||||
|
||||
if err != nil {
|
||||
l.Error("Nebula stopped due to fatal error", "error", err)
|
||||
os.Exit(2)
|
||||
}
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build !linux
|
||||
// +build !linux
|
||||
|
||||
package main
|
||||
|
||||
|
||||
+624
@@ -0,0 +1,624 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"maps"
|
||||
"net/netip"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
// The commands nebula serves. attachCommands builds the one registry every surface
|
||||
// reads; the ssh debug server is a consumer of it, not its owner, which is why this
|
||||
// is not ssh.go. See the commands package for what a Command is.
|
||||
|
||||
type listHostMapFlags struct {
|
||||
ByIndex bool
|
||||
}
|
||||
|
||||
type printCertFlags struct {
|
||||
Raw bool
|
||||
}
|
||||
|
||||
type changeRemoteFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
type closeTunnelFlags struct {
|
||||
LocalOnly bool
|
||||
}
|
||||
|
||||
type createTunnelFlags struct {
|
||||
Address string
|
||||
}
|
||||
|
||||
// lighthouseInfo is one entry of list-lighthouse-addrmap.
|
||||
type lighthouseInfo struct {
|
||||
VpnAddr string `json:"vpnAddr"`
|
||||
Addrs *CacheMap `json:"addrs"`
|
||||
}
|
||||
|
||||
// deviceInfo is the result of device-info.
|
||||
type deviceInfo struct {
|
||||
Name string `json:"name"`
|
||||
Cidr []netip.Prefix `json:"cidr"`
|
||||
}
|
||||
|
||||
// certPEM is the result of print-cert -raw. The PEM form is a different thing to emit,
|
||||
// not a different formatting of the certificate, so it is its own shape.
|
||||
type certPEM struct {
|
||||
PEM string `json:"pem"`
|
||||
}
|
||||
|
||||
// Result shapes for print-relays. Field names are the JSON keys; changing them would
|
||||
// change the output.
|
||||
type relayFor struct {
|
||||
Error string `json:",omitempty"`
|
||||
Type string
|
||||
State string
|
||||
PeerAddr netip.Addr
|
||||
LocalIndex uint32
|
||||
RemoteIndex uint32
|
||||
RelayedThrough []netip.Addr
|
||||
}
|
||||
|
||||
type relayOutput struct {
|
||||
NebulaAddr netip.Addr
|
||||
RelayForAddrs []relayFor
|
||||
}
|
||||
|
||||
type relaysOutput struct {
|
||||
Relays []*relayOutput
|
||||
}
|
||||
|
||||
type versionInfo struct {
|
||||
Version string `json:"version"`
|
||||
}
|
||||
|
||||
type logLevelInfo struct {
|
||||
Level string `json:"level"`
|
||||
}
|
||||
|
||||
type logFormatInfo struct {
|
||||
Format string `json:"format"`
|
||||
}
|
||||
|
||||
// defineListHostMapFlags declares the flags list-hostmap and list-pending-hostmap share.
|
||||
func defineListHostMapFlags(fl *flag.FlagSet, s *listHostMapFlags) {
|
||||
fl.BoolVar(&s.ByIndex, "by-index", false, "gets all hosts in the hostmap from the index table")
|
||||
}
|
||||
|
||||
func attachCommands(l *slog.Logger, c *config.C, reg *commands.Registry, f *Interface) {
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.ListHostmap,
|
||||
ShortDescription: "List all known previously connected hosts",
|
||||
Text: commands.Typed(textListHostMap),
|
||||
}, defineListHostMapFlags, func(s *listHostMapFlags, a []string) (commands.Result, error) {
|
||||
return runListHostMap(f.hostMap, s)
|
||||
}))
|
||||
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.ListPendingHostmap,
|
||||
ShortDescription: "List all handshaking hosts",
|
||||
Text: commands.Typed(textListHostMap),
|
||||
}, defineListHostMapFlags, func(s *listHostMapFlags, a []string) (commands.Result, error) {
|
||||
return runListHostMap(f.handshakeManager, s)
|
||||
}))
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.ListLighthouseAddrmap,
|
||||
ShortDescription: "List all lighthouse map entries",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return runListLighthouseMap(f.lightHouse)
|
||||
},
|
||||
Text: commands.Typed(textListLighthouseMap),
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.Reload,
|
||||
ShortDescription: "Reloads configuration from disk, same as sending HUP to the process",
|
||||
// The line goes out before the reload: a reload that restarts the ssh server ends
|
||||
// the session that asked, and this is what it sees.
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return commands.Did("Reloading config"), nil
|
||||
},
|
||||
Then: func() commands.Result {
|
||||
return runReload(l, c)
|
||||
},
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.LogLevel,
|
||||
ShortDescription: "Gets or sets the current log level",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return runLogLevel(l, a)
|
||||
},
|
||||
Text: commands.Typed(textLogLevel),
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.LogFormat,
|
||||
ShortDescription: "Gets or sets the current log format",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return runLogFormat(l, a)
|
||||
},
|
||||
Text: commands.Typed(textLogFormat),
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.Version,
|
||||
ShortDescription: "Prints the currently running version of nebula",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return commands.Value(versionInfo{Version: f.version}), nil
|
||||
},
|
||||
Text: commands.Typed(textVersion),
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.DeviceInfo,
|
||||
ShortDescription: "Prints information about the network device.",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return commands.Value(runDeviceInfo(f)), nil
|
||||
},
|
||||
Text: commands.Typed(textDeviceInfo),
|
||||
})
|
||||
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.PrintCert,
|
||||
ShortDescription: "Prints the current certificate being used or the certificate for the provided vpn addr",
|
||||
Text: textPrintCert,
|
||||
}, func(fl *flag.FlagSet, s *printCertFlags) {
|
||||
fl.BoolVar(&s.Raw, "raw", false, "prints the PEM encoded certificate; with -json, an object holding it")
|
||||
}, func(s *printCertFlags, a []string) (commands.Result, error) {
|
||||
return runPrintCert(f, s, a)
|
||||
}))
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.PrintTunnel,
|
||||
ShortDescription: "Prints json details about a tunnel for the provided vpn addr",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return runPrintTunnel(f, a)
|
||||
},
|
||||
// No Text on purpose: nothing human readable exists yet, and shipping an interim
|
||||
// form would invite scripts against it. ssh defaults these to JSON; ctl asks.
|
||||
JSONOnly: true,
|
||||
})
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.PrintRelays,
|
||||
ShortDescription: "Prints json details about all relay info",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return commands.Value(runPrintRelays(f)), nil
|
||||
},
|
||||
// No Text on purpose; see print-tunnel.
|
||||
JSONOnly: true,
|
||||
})
|
||||
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.ChangeRemote,
|
||||
ShortDescription: "Changes the remote address used in the tunnel for the provided vpn addr",
|
||||
}, func(fl *flag.FlagSet, s *changeRemoteFlags) {
|
||||
fl.StringVar(&s.Address, "address", "", "The new remote address, ip:port")
|
||||
}, func(s *changeRemoteFlags, a []string) (commands.Result, error) {
|
||||
return runChangeRemote(f, s, a)
|
||||
}))
|
||||
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.CloseTunnel,
|
||||
ShortDescription: "Closes a tunnel for the provided vpn addr",
|
||||
}, func(fl *flag.FlagSet, s *closeTunnelFlags) {
|
||||
fl.BoolVar(&s.LocalOnly, "local-only", false, "Disables notifying the remote that the tunnel is shutting down")
|
||||
}, func(s *closeTunnelFlags, a []string) (commands.Result, error) {
|
||||
return runCloseTunnel(f, s, a)
|
||||
}))
|
||||
|
||||
reg.Register(commands.Flagged(&commands.Command{
|
||||
Name: commands.CreateTunnel,
|
||||
ShortDescription: "Creates a tunnel for the provided vpn address",
|
||||
Help: "The lighthouses will be queried for real addresses but you can provide one as well.",
|
||||
}, func(fl *flag.FlagSet, s *createTunnelFlags) {
|
||||
fl.StringVar(&s.Address, "address", "", "Optionally provide a real remote address, ip:port ")
|
||||
}, func(s *createTunnelFlags, a []string) (commands.Result, error) {
|
||||
return runCreateTunnel(f, s, a)
|
||||
}))
|
||||
|
||||
reg.Register(&commands.Command{
|
||||
Name: commands.QueryLighthouse,
|
||||
ShortDescription: "Query the lighthouses for the provided vpn address",
|
||||
Help: "This command is asynchronous. Only currently known udp addresses will be printed.",
|
||||
Run: func(fs any, a []string) (commands.Result, error) {
|
||||
return runQueryLighthouse(f, a)
|
||||
},
|
||||
// No Text on purpose; see print-tunnel.
|
||||
JSONOnly: true,
|
||||
})
|
||||
}
|
||||
|
||||
// runListHostMap computes the hostmap listing. Presentation is Render's job.
|
||||
func runListHostMap(hl controlHostLister, fs *listHostMapFlags) (commands.Result, error) {
|
||||
var hm []ControlHostInfo
|
||||
if fs.ByIndex {
|
||||
hm = listHostMapIndexes(hl)
|
||||
} else {
|
||||
hm = listHostMapHosts(hl)
|
||||
}
|
||||
|
||||
sort.Slice(hm, func(i, j int) bool {
|
||||
return hm[i].VpnAddrs[0].Compare(hm[j].VpnAddrs[0]) < 0
|
||||
})
|
||||
|
||||
return commands.Value(hm), nil
|
||||
}
|
||||
|
||||
// textListHostMap is the human rendering, shared by every surface.
|
||||
func textListHostMap(hm []ControlHostInfo, w io.Writer) error {
|
||||
for _, h := range hm {
|
||||
if _, err := fmt.Fprintf(w, "%s: %s\n", h.VpnAddrs, h.RemoteAddrs); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func runListLighthouseMap(lightHouse *LightHouse) (commands.Result, error) {
|
||||
lightHouse.RLock()
|
||||
addrMap := make([]lighthouseInfo, len(lightHouse.addrMap))
|
||||
x := 0
|
||||
for k, v := range lightHouse.addrMap {
|
||||
addrMap[x] = lighthouseInfo{
|
||||
VpnAddr: k.String(),
|
||||
Addrs: v.CopyCache(),
|
||||
}
|
||||
x++
|
||||
}
|
||||
lightHouse.RUnlock()
|
||||
|
||||
sort.Slice(addrMap, func(i, j int) bool {
|
||||
return strings.Compare(addrMap[i].VpnAddr, addrMap[j].VpnAddr) < 0
|
||||
})
|
||||
|
||||
return commands.Value(addrMap), nil
|
||||
}
|
||||
|
||||
func textListLighthouseMap(addrMap []lighthouseInfo, w io.Writer) error {
|
||||
for _, e := range addrMap {
|
||||
b, err := json.Marshal(e.Addrs)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := fmt.Fprintf(w, "%s: %s\n", e.VpnAddr, string(b)); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func textVersion(vi versionInfo, w io.Writer) error {
|
||||
_, err := fmt.Fprintf(w, "%s\n", vi.Version)
|
||||
return err
|
||||
}
|
||||
|
||||
// vpnAddrOperand parses the vpn address a command takes as its first operand. noun is
|
||||
// how the command's messages name it, "vpn address" or "vpn addr", which the output
|
||||
// golden pins per command. With no operand, or one that does not parse, ok is false and
|
||||
// res is the refusal to return.
|
||||
func vpnAddrOperand(a []string, noun string) (vpnAddr netip.Addr, res commands.Result, ok bool) {
|
||||
if len(a) == 0 {
|
||||
return netip.Addr{}, commands.Failed("No vpn address was provided"), false
|
||||
}
|
||||
|
||||
vpnAddr, err := netip.ParseAddr(a[0])
|
||||
if err != nil {
|
||||
return netip.Addr{}, commands.Failed("The provided %s could not be parsed: %s", noun, a[0]), false
|
||||
}
|
||||
|
||||
return vpnAddr, commands.Result{}, true
|
||||
}
|
||||
|
||||
// tunnelOperand is vpnAddrOperand followed by the lookup of the tunnel it names.
|
||||
func tunnelOperand(ifce *Interface, a []string, noun string) (*HostInfo, commands.Result, bool) {
|
||||
vpnAddr, res, ok := vpnAddrOperand(a, noun)
|
||||
if !ok {
|
||||
return nil, res, false
|
||||
}
|
||||
|
||||
hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if hostInfo == nil {
|
||||
return nil, commands.Failed("Could not find tunnel for %s: %v", noun, a[0]), false
|
||||
}
|
||||
|
||||
return hostInfo, commands.Result{}, true
|
||||
}
|
||||
|
||||
func runQueryLighthouse(ifce *Interface, a []string) (commands.Result, error) {
|
||||
vpnAddr, res, ok := vpnAddrOperand(a, "vpn address")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
|
||||
var cm *CacheMap
|
||||
rl := ifce.lightHouse.Query(vpnAddr)
|
||||
if rl != nil {
|
||||
cm = rl.CopyCache()
|
||||
}
|
||||
return commands.Value(cm), nil
|
||||
}
|
||||
|
||||
func runCloseTunnel(ifce *Interface, flags *closeTunnelFlags, a []string) (commands.Result, error) {
|
||||
hostInfo, res, ok := tunnelOperand(ifce, a, "vpn address")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
|
||||
if !flags.LocalOnly {
|
||||
ifce.send(
|
||||
header.CloseTunnel,
|
||||
0,
|
||||
hostInfo.ConnectionState,
|
||||
hostInfo,
|
||||
[]byte{},
|
||||
make([]byte, 12, 12),
|
||||
make([]byte, mtu),
|
||||
)
|
||||
}
|
||||
|
||||
ifce.closeTunnel(hostInfo)
|
||||
return commands.Did("Closed"), nil
|
||||
}
|
||||
|
||||
func runCreateTunnel(ifce *Interface, flags *createTunnelFlags, a []string) (commands.Result, error) {
|
||||
|
||||
vpnAddr, res, ok := vpnAddrOperand(a, "vpn address")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
|
||||
if hostInfo := ifce.hostMap.QueryVpnAddr(vpnAddr); hostInfo != nil {
|
||||
return commands.Failed("Tunnel already exists"), nil
|
||||
}
|
||||
|
||||
if hostInfo := ifce.handshakeManager.QueryVpnAddr(vpnAddr); hostInfo != nil {
|
||||
return commands.Failed("Tunnel already handshaking"), nil
|
||||
}
|
||||
|
||||
var addr netip.AddrPort
|
||||
if flags.Address != "" {
|
||||
var err error
|
||||
addr, err = netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return commands.Failed("Address could not be parsed"), nil
|
||||
}
|
||||
}
|
||||
|
||||
// Set the remote from the callback, which StartHandshake runs under the handshake manager lock
|
||||
// before the hostinfo reaches the handshake loop or the static-host trigger, so the address is
|
||||
// in the RemoteList before the first handshake is sent.
|
||||
ifce.handshakeManager.StartHandshake(vpnAddr, func(hh *HandshakeHostInfo) {
|
||||
if addr.IsValid() {
|
||||
hh.hostinfo.SetRemote(addr)
|
||||
}
|
||||
})
|
||||
|
||||
return commands.Did("Created"), nil
|
||||
}
|
||||
|
||||
func runChangeRemote(ifce *Interface, flags *changeRemoteFlags, a []string) (commands.Result, error) {
|
||||
|
||||
if len(a) == 0 {
|
||||
return commands.Failed("No vpn address was provided"), nil
|
||||
}
|
||||
|
||||
if flags.Address == "" {
|
||||
return commands.Failed("No address was provided"), nil
|
||||
}
|
||||
|
||||
addr, err := netip.ParseAddrPort(flags.Address)
|
||||
if err != nil {
|
||||
return commands.Failed("Address could not be parsed"), nil
|
||||
}
|
||||
|
||||
hostInfo, res, ok := tunnelOperand(ifce, a, "vpn address")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
|
||||
hostInfo.SetRemote(addr)
|
||||
return commands.Did("Changed"), nil
|
||||
}
|
||||
|
||||
func runLogLevel(l *slog.Logger, a []string) (commands.Result, error) {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetLevel() slog.Level
|
||||
SetLevel(slog.Level)
|
||||
})
|
||||
if !ok {
|
||||
return commands.Failed("Log level is not reconfigurable on this logger"), nil
|
||||
}
|
||||
|
||||
if len(a) > 0 {
|
||||
level, err := logging.ParseLevel(strings.ToLower(a[0]))
|
||||
if err != nil {
|
||||
return commands.Failed("Unknown log level %s. Possible log levels: trace, debug, info, warn, error", a), nil
|
||||
}
|
||||
|
||||
ctrl.SetLevel(level)
|
||||
}
|
||||
|
||||
return commands.Value(logLevelInfo{Level: logging.LevelName(ctrl.GetLevel())}), nil
|
||||
}
|
||||
|
||||
func textLogLevel(li logLevelInfo, w io.Writer) error {
|
||||
_, err := fmt.Fprintf(w, "Log level is: %s\n", li.Level)
|
||||
return err
|
||||
}
|
||||
|
||||
func runLogFormat(l *slog.Logger, a []string) (commands.Result, error) {
|
||||
ctrl, ok := l.Handler().(interface {
|
||||
GetFormat() string
|
||||
SetFormat(string) error
|
||||
})
|
||||
if !ok {
|
||||
return commands.Failed("Log format is not reconfigurable on this logger"), nil
|
||||
}
|
||||
|
||||
if len(a) > 0 {
|
||||
if err := ctrl.SetFormat(strings.ToLower(a[0])); err != nil {
|
||||
return commands.Failed("Unable to set log format: %s", err), nil
|
||||
}
|
||||
}
|
||||
|
||||
return commands.Value(logFormatInfo{Format: ctrl.GetFormat()}), nil
|
||||
}
|
||||
|
||||
func textLogFormat(fi logFormatInfo, w io.Writer) error {
|
||||
_, err := fmt.Fprintf(w, "Log format is: %s\n", fi.Format)
|
||||
return err
|
||||
}
|
||||
|
||||
func runPrintCert(ifce *Interface, args *printCertFlags, a []string) (commands.Result, error) {
|
||||
|
||||
c := ifce.pki.getCertState().GetDefaultCertificate()
|
||||
if len(a) > 0 {
|
||||
hostInfo, res, ok := tunnelOperand(ifce, a, "vpn addr")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
// A tunnel still handshaking, or one being torn down, has no certificate.
|
||||
cc := hostInfo.GetCert()
|
||||
if cc == nil {
|
||||
return commands.Failed("Could not find tunnel for vpn addr: %v", a[0]), nil
|
||||
}
|
||||
c = cc.Certificate
|
||||
}
|
||||
|
||||
if args.Raw {
|
||||
b, err := c.MarshalPEM()
|
||||
if err != nil {
|
||||
return commands.Failed("Unable to marshal the certificate: %s", err), nil
|
||||
}
|
||||
return commands.Value(certPEM{PEM: string(b)}), nil
|
||||
}
|
||||
|
||||
return commands.Value(c), nil
|
||||
}
|
||||
|
||||
// textPrintCert takes the value untyped: print-cert returns a certificate or, with -raw,
|
||||
// its PEM, and those are two things to emit rather than two renderings of one.
|
||||
func textPrintCert(v any, w io.Writer) error {
|
||||
switch c := v.(type) {
|
||||
case certPEM:
|
||||
_, err := io.WriteString(w, c.PEM)
|
||||
return err
|
||||
case cert.Certificate:
|
||||
_, err := io.WriteString(w, c.String()+"\n")
|
||||
return err
|
||||
default:
|
||||
return fmt.Errorf("expected a certificate, got %T", v)
|
||||
}
|
||||
}
|
||||
|
||||
func runPrintRelays(ifce *Interface) any {
|
||||
ifce.hostMap.RLock()
|
||||
relays := maps.Clone(ifce.hostMap.Relays)
|
||||
ifce.hostMap.RUnlock()
|
||||
|
||||
co := relaysOutput{}
|
||||
|
||||
for k, v := range relays {
|
||||
ro := relayOutput{NebulaAddr: v.vpnAddrs[0]}
|
||||
co.Relays = append(co.Relays, &ro)
|
||||
relayHI := ifce.hostMap.QueryVpnAddr(v.vpnAddrs[0])
|
||||
if relayHI == nil {
|
||||
ro.RelayForAddrs = append(ro.RelayForAddrs, relayFor{Error: "could not find hostinfo"})
|
||||
continue
|
||||
}
|
||||
for _, vpnAddr := range relayHI.relayState.CopyRelayForIps() {
|
||||
rf := relayFor{}
|
||||
r, ok := relayHI.relayState.GetRelayForByAddr(vpnAddr)
|
||||
if ok {
|
||||
t := ""
|
||||
switch r.Type {
|
||||
case ForwardingType:
|
||||
t = "forwarding"
|
||||
case TerminalType:
|
||||
t = "terminal"
|
||||
default:
|
||||
t = "unknown"
|
||||
}
|
||||
|
||||
st := ""
|
||||
switch r.State {
|
||||
case Requested:
|
||||
st = "requested"
|
||||
case Established:
|
||||
st = "established"
|
||||
default:
|
||||
st = "unknown"
|
||||
}
|
||||
|
||||
rf.LocalIndex = r.LocalIndex
|
||||
rf.RemoteIndex = r.RemoteIndex
|
||||
rf.PeerAddr = r.PeerAddr
|
||||
rf.Type = t
|
||||
rf.State = st
|
||||
if rf.LocalIndex != k {
|
||||
rf.Error = fmt.Sprintf("hostmap LocalIndex '%v' does not match RelayState LocalIndex", k)
|
||||
}
|
||||
}
|
||||
relayedHI := ifce.hostMap.QueryVpnAddr(vpnAddr)
|
||||
if relayedHI != nil {
|
||||
rf.RelayedThrough = append(rf.RelayedThrough, relayedHI.relayState.CopyRelayIps()...)
|
||||
}
|
||||
|
||||
ro.RelayForAddrs = append(ro.RelayForAddrs, rf)
|
||||
}
|
||||
}
|
||||
|
||||
return co
|
||||
}
|
||||
|
||||
func runPrintTunnel(ifce *Interface, a []string) (commands.Result, error) {
|
||||
hostInfo, res, ok := tunnelOperand(ifce, a, "vpn addr")
|
||||
if !ok {
|
||||
return res, nil
|
||||
}
|
||||
|
||||
return commands.Value(copyHostInfo(hostInfo, ifce.hostMap.GetPreferredRanges())), nil
|
||||
}
|
||||
|
||||
func runDeviceInfo(ifce *Interface) deviceInfo {
|
||||
d := deviceInfo{
|
||||
Name: ifce.inside.Name(),
|
||||
Cidr: make([]netip.Prefix, len(ifce.inside.Networks())),
|
||||
}
|
||||
copy(d.Cidr, ifce.inside.Networks())
|
||||
return d
|
||||
}
|
||||
|
||||
func textDeviceInfo(d deviceInfo, w io.Writer) error {
|
||||
_, err := fmt.Fprintf(w, "name=%v cidr=%v\n", d.Name, d.Cidr)
|
||||
return err
|
||||
}
|
||||
|
||||
// runReload reloads the config and reports how it went. A reload that failed is a
|
||||
// refusal, exit 1 over ssh; one that merely needs a restart is not.
|
||||
func runReload(l *slog.Logger, c *config.C) commands.Result {
|
||||
res := c.ReloadConfig()
|
||||
res.Log(l)
|
||||
if res.Err != nil || res.Failed {
|
||||
return commands.Failed("%s", res.String())
|
||||
}
|
||||
return commands.Did("%s", res.String())
|
||||
}
|
||||
@@ -0,0 +1,300 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// CommandFlags is called before help or command execution to parse command line flags.
|
||||
// It should return a flag.FlagSet instance and a pointer to the struct that will contain parsed flags
|
||||
//
|
||||
// Every call must build a fresh FlagSet and a fresh struct. Nothing may be shared between
|
||||
// calls: a command runs on more than one surface and on more than one goroutine.
|
||||
type CommandFlags func() (*flag.FlagSet, any)
|
||||
|
||||
// RunFunc computes a command's Result.
|
||||
//
|
||||
// fs is the pointer returned by Command.Flags, if there was one; -h, -help, -json and
|
||||
// -pretty are reserved and handled before Run is called. a is the operands: whatever
|
||||
// was not consumed as a flag. The Result is rendered by whichever surface asked: Value
|
||||
// for a command that reports, Did or Failed for one that acts, Nothing for one with
|
||||
// nothing to say. An error is for a failure of the command itself; a bad argument is
|
||||
// Failed, so the caller hears why in its own format.
|
||||
type RunFunc func(fs any, a []string) (Result, error)
|
||||
|
||||
// TextFunc renders a Result's Value for a person. See Typed for declaring one against
|
||||
// the type the command actually returns.
|
||||
type TextFunc func(v any, w io.Writer) error
|
||||
|
||||
type Command struct {
|
||||
Name Name
|
||||
ShortDescription string
|
||||
Help string
|
||||
|
||||
Flags CommandFlags
|
||||
|
||||
// Run produces the command's Result, leaving presentation to Render.
|
||||
Run RunFunc
|
||||
|
||||
// Text renders a Result's Value for a person. Both surfaces call it, so a command
|
||||
// reads the same over ssh as it does through the control socket. It never sees an
|
||||
// outcome: Render prints those itself, the same way for every command. Leaving it
|
||||
// nil declares that no human rendering of the Value exists yet, which JSONOnly says
|
||||
// up front; Render then refuses text rather than inventing an interim form for
|
||||
// people to script against.
|
||||
Text TextFunc
|
||||
|
||||
// JSONOnly declares that the command's Value has no human rendering yet, so a surface
|
||||
// whose default is text asks for JSON instead, and the schema says so to a client. It
|
||||
// is a statement that no such form exists, not a fallback. A refusal is still
|
||||
// rendered as a sentence, since that always has a human form.
|
||||
JSONOnly bool
|
||||
|
||||
// Then, when set, is the second half of a command that acts: Run says what is about
|
||||
// to happen and Then does it and says how it went, with its Result rendered after
|
||||
// Run's and deciding the outcome. A Run that refused is the outcome, and Then does
|
||||
// not run. It exists for a command whose action can cut off
|
||||
// its own reply: reload restarts the ssh server when the sshd keys changed, which
|
||||
// ends the session that asked, so Run's line has to be on the wire before the reload
|
||||
// begins. A surface that answers in one piece, the control socket, runs Then before
|
||||
// it answers and carries both.
|
||||
Then func() Result
|
||||
}
|
||||
|
||||
// Failure is the error a surface gets for a refusal the person has already been shown:
|
||||
// a Run that returned Failed, a command that is not there, a line that would not parse.
|
||||
// The message it rendered is the whole story, so the surface reports the failure, exit
|
||||
// status 1 over ssh, and does not log it.
|
||||
type Failure struct {
|
||||
Msg string
|
||||
}
|
||||
|
||||
func (f *Failure) Error() string {
|
||||
return f.Msg
|
||||
}
|
||||
|
||||
// commandFlags returns the FlagSet a command is driven through, on any surface: the
|
||||
// command's own flags, if it declares any, with the two presentation flags added. own
|
||||
// reports whether the command declared any of its own, which is what tells a caller
|
||||
// whether to say a parameter is unknown or that the command takes none at all.
|
||||
//
|
||||
// The presentation flags are defined here rather than by each command, because how a
|
||||
// result is displayed is not a property of the command that produced it. This is also
|
||||
// the one definition of them: the ssh line parses into it, nebula ctl parses its line
|
||||
// against the schema derived from it, and help renders from that schema. They are
|
||||
// command line flags only: a socket request chooses its rendering with the envelope's
|
||||
// format field, and Invoke refuses them as parameters.
|
||||
func commandFlags(c *Command) (fl *flag.FlagSet, fs any, own bool) {
|
||||
if c.Flags != nil {
|
||||
fl, fs = c.Flags()
|
||||
}
|
||||
own = fl != nil
|
||||
if fl == nil {
|
||||
fl = flag.NewFlagSet(string(c.Name), flag.ContinueOnError)
|
||||
}
|
||||
|
||||
addPresentationFlags(fl)
|
||||
|
||||
// What Parse prints after a bad flag, and for -h: the command's usage as help renders
|
||||
// it, so a line that went wrong is answered with the same text as `help <command>`.
|
||||
fl.Usage = func() { _ = WriteCommandHelp(schemaOf(c, fl), fl.Output()) }
|
||||
|
||||
return fl, fs, own
|
||||
}
|
||||
|
||||
// addPresentationFlags defines the two presentation flags on fl.
|
||||
func addPresentationFlags(fl *flag.FlagSet) {
|
||||
fl.Bool(FlagJSON, false, "outputs as json")
|
||||
fl.Bool(FlagPretty, false, "pretty prints json, assumes -json")
|
||||
}
|
||||
|
||||
// Flagged fills in c's Flags and Run as a pair: define declares the flags on a fresh F,
|
||||
// and run is handed that F. The struct the flags fill is the struct Run reads by
|
||||
// construction, so no Run has to assert the type it was given or decide what to do
|
||||
// when the assertion fails.
|
||||
func Flagged[F any](c *Command, define func(*flag.FlagSet, *F), run func(*F, []string) (Result, error)) *Command {
|
||||
c.Flags = func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := new(F)
|
||||
define(fl, s)
|
||||
return fl, s
|
||||
}
|
||||
c.Run = func(fs any, a []string) (Result, error) {
|
||||
s, ok := fs.(*F)
|
||||
if !ok {
|
||||
return Result{}, fmt.Errorf("%s was handed %T for its flags, not %T", c.Name, fs, s)
|
||||
}
|
||||
return run(s, a)
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// isPresentationFlag reports whether name is one of the two flags commandFlags adds.
|
||||
func isPresentationFlag(name string) bool {
|
||||
return name == FlagJSON || name == FlagPretty
|
||||
}
|
||||
|
||||
// execLine runs an ssh command line against c, reporting problems to w. The line is
|
||||
// parsed into the command's own FlagSet and Run reads it directly, so a flag.Value whose
|
||||
// String does not re-parse, flag.Func above all, arrives as the line said. Invoke fills
|
||||
// the same FlagSet through Set.
|
||||
func (r *Registry) execLine(c *Command, args []string, w Output) error {
|
||||
fl, fs, _ := commandFlags(c)
|
||||
|
||||
// Parse reports a bad flag to this writer, with the command's usage after it. -h,
|
||||
// -help and --help take the same path with nothing wrong: the usage is the whole
|
||||
// answer, and Parse says so with ErrHelp. A -h that is a flag's value or follows --
|
||||
// is read as the operand it is, since ParseArgs is the one reading of the line.
|
||||
fl.SetOutput(w.Err)
|
||||
operands, err := ParseArgs(fl, args)
|
||||
if err != nil {
|
||||
if errors.Is(err, flag.ErrHelp) {
|
||||
return nil
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
format := presentationFormat(fl)
|
||||
|
||||
// An error from Run is something the command could not do rather than a refusal it
|
||||
// chose, but the person at the prompt still hears it; the surface logs it too.
|
||||
res, err := c.Run(fs, operands)
|
||||
if err != nil {
|
||||
_, _ = fmt.Fprintln(w.Err, err.Error())
|
||||
return err
|
||||
}
|
||||
|
||||
// Run's reply goes out first, and then the action, if the command has one and Run
|
||||
// did not refuse, whose Result is the outcome. In JSON only the outcome travels:
|
||||
// the promise is for a person to read, and a program expects one document.
|
||||
if c.Then == nil || !res.OK || r.formatFor(c, res, format) == FormatText {
|
||||
if err := r.renderLine(c, res, format, w); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if c.Then != nil && res.OK {
|
||||
res = c.Then()
|
||||
if err := r.renderLine(c, res, format, w); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
if !res.OK {
|
||||
return &Failure{Msg: res.Reason}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// formatFor is the format a Result is rendered in. The line wins when it asked for one;
|
||||
// otherwise the surface that owns the registry decides, from the command and its
|
||||
// Result, so each surface can keep its own default.
|
||||
func (r *Registry) formatFor(c *Command, res Result, format Format) Format {
|
||||
if format == FormatUnset {
|
||||
return r.defaultFormatFor(c, res)
|
||||
}
|
||||
return format
|
||||
}
|
||||
|
||||
// renderLine writes one Result of a command line to w; see formatFor. An empty Result
|
||||
// writes nothing.
|
||||
func (r *Registry) renderLine(c *Command, res Result, format Format, w Output) error {
|
||||
if res.Empty() {
|
||||
return nil
|
||||
}
|
||||
|
||||
if err := Render(c, res, r.formatFor(c, res, format), w.Out); err != nil {
|
||||
if errors.Is(err, ErrNoTextRendering) {
|
||||
_, _ = fmt.Fprintln(w.Err, err.Error())
|
||||
}
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// ParseArgs parses args with fl and returns the operands.
|
||||
//
|
||||
// It differs from fl.Parse in two ways, and both surfaces parse through here so a line
|
||||
// means the same typed at an ssh prompt or to nebula ctl.
|
||||
//
|
||||
// Flags and operands may come in any order, which is the one way it differs from
|
||||
// fl.Parse. Parse stops at the first operand, so `print-tunnel 10.0.0.1 -json` would
|
||||
// reach the command with "-json" as a second operand and the flag silently dropped. Here
|
||||
// an operand ends nothing: parsing resumes after it, and only "--" ends the flags, with
|
||||
// everything after it an operand. What counts as a flag is Parse's rule: every argument
|
||||
// that starts with "-", a negative number included, so one that is meant as an operand
|
||||
// goes after "--".
|
||||
func ParseArgs(fl *flag.FlagSet, args []string) ([]string, error) {
|
||||
operands := make([]string, 0, len(args))
|
||||
|
||||
for len(args) > 0 {
|
||||
// Walk the flags the way Parse will, to the first argument it would not read as a
|
||||
// flag: an operand or the terminator. Everything before it is Parse's.
|
||||
end := len(args)
|
||||
for i := 0; i < len(args); {
|
||||
a := args[i]
|
||||
if a == "--" {
|
||||
if err := fl.Parse(args[:i]); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return append(operands, args[i+1:]...), nil
|
||||
}
|
||||
|
||||
if len(a) < 2 || a[0] != '-' {
|
||||
end = i
|
||||
break
|
||||
}
|
||||
|
||||
f, hasValue := LookupArg(fl, a)
|
||||
if f == nil {
|
||||
// An undefined flag: leave it for Parse to report.
|
||||
i++
|
||||
continue
|
||||
}
|
||||
|
||||
if hasValue || IsBoolFlag(f) {
|
||||
i++
|
||||
} else {
|
||||
// The flag's value is the next argument, whatever it looks like.
|
||||
i += 2
|
||||
}
|
||||
}
|
||||
|
||||
if err := fl.Parse(args[:end]); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if end == len(args) {
|
||||
break
|
||||
}
|
||||
|
||||
operands = append(operands, args[end])
|
||||
args = args[end+1:]
|
||||
}
|
||||
|
||||
return operands, nil
|
||||
}
|
||||
|
||||
// LookupArg reads arg the way Parse does: one or two leading dashes, the flag's name, and
|
||||
// an optional "=value". f is the flag of fl by that name, nil when fl has none, and
|
||||
// hasValue reports that the value came with the argument rather than in the one after it.
|
||||
// It is the one reading of an argument's shape: ParseArgs walks a line with it, and
|
||||
// nebula ctl lifts its own flags out of a line with it, so the two cannot disagree about
|
||||
// which word is a flag's value.
|
||||
func LookupArg(fl *flag.FlagSet, arg string) (f *flag.Flag, hasValue bool) {
|
||||
name := strings.TrimPrefix(strings.TrimPrefix(arg, "-"), "-")
|
||||
if eq := strings.IndexByte(name, '='); eq >= 0 {
|
||||
name, hasValue = name[:eq], true
|
||||
}
|
||||
return fl.Lookup(name), hasValue
|
||||
}
|
||||
|
||||
// IsBoolFlag reports whether f is satisfied by its presence alone and never reads the
|
||||
// argument after it as its value. The flag package marks these with an unexported
|
||||
// interface, which is the only way to tell.
|
||||
func IsBoolFlag(f *flag.Flag) bool {
|
||||
bf, ok := f.Value.(interface{ IsBoolFlag() bool })
|
||||
return ok && bf.IsBoolFlag()
|
||||
}
|
||||
@@ -0,0 +1,101 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"flag"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestParseArgsAllowsFlagsAfterOperands pins the one way ParseArgs departs from fl.Parse,
|
||||
// that a flag may follow an operand, and that it departs in no other: a negative number
|
||||
// is a flag, as Parse reads it, and goes after "--" when it is meant as an operand.
|
||||
func TestParseArgsAllowsFlagsAfterOperands(t *testing.T) {
|
||||
cases := map[string]struct {
|
||||
args []string
|
||||
wantOps []string
|
||||
wantN string
|
||||
wantV bool
|
||||
wantJSON bool
|
||||
wantErr string
|
||||
}{
|
||||
"flag after operand": {args: []string{"x", "-json"}, wantOps: []string{"x"}, wantJSON: true},
|
||||
"flags around": {args: []string{"-v", "x", "-n", "1", "y"}, wantOps: []string{"x", "y"}, wantV: true, wantN: "1"},
|
||||
"value after operand": {args: []string{"x", "-n", "-1"}, wantOps: []string{"x"}, wantN: "-1"},
|
||||
"equals value": {args: []string{"-n=-1", "x"}, wantOps: []string{"x"}, wantN: "-1"},
|
||||
"terminator after": {args: []string{"x", "--", "-json", "-1"}, wantOps: []string{"x", "-json", "-1"}},
|
||||
"terminator": {args: []string{"--", "-json"}, wantOps: []string{"-json"}},
|
||||
"defined numeric": {args: []string{"-2", "x"}, wantOps: []string{"x"}, wantV: true},
|
||||
"negative number": {args: []string{"-1"}, wantErr: "flag provided but not defined: -1"},
|
||||
"bad flag after": {args: []string{"x", "-nope"}, wantErr: "flag provided but not defined: -nope"},
|
||||
"undefined flag": {args: []string{"-nope", "x"}, wantErr: "flag provided but not defined: -nope"},
|
||||
"missing value": {args: []string{"-n"}, wantErr: "flag needs an argument: -n"},
|
||||
}
|
||||
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
fl := flag.NewFlagSet("t", flag.ContinueOnError)
|
||||
fl.SetOutput(&bytes.Buffer{})
|
||||
n := fl.String("n", "", "")
|
||||
v := fl.Bool("v", false, "")
|
||||
two := fl.Bool("2", false, "a flag that happens to be a number")
|
||||
asJSON := fl.Bool(FlagJSON, false, "")
|
||||
|
||||
ops, err := ParseArgs(fl, tc.args)
|
||||
if tc.wantErr != "" {
|
||||
require.ErrorContains(t, err, tc.wantErr)
|
||||
return
|
||||
}
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, tc.wantOps, ops)
|
||||
assert.Equal(t, tc.wantN, *n)
|
||||
assert.Equal(t, tc.wantV, *v || *two)
|
||||
assert.Equal(t, tc.wantJSON, *asJSON)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestDispatchFlagAfterOperand: the same through a registered command with no Flags of
|
||||
// its own, which only has the presentation flags to find.
|
||||
func TestDispatchFlagAfterOperand(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, testRegistry().DispatchArgs([]string{"served", "x", "-json"}, MergedOutput(out)))
|
||||
assert.Equal(t, "\"read x\"\n", out.String())
|
||||
}
|
||||
|
||||
// TestLookupArg pins the reading of an argument's shape that ParseArgs and nebula ctl
|
||||
// share.
|
||||
func TestLookupArg(t *testing.T) {
|
||||
fl := flag.NewFlagSet("t", flag.ContinueOnError)
|
||||
fl.String("n", "", "")
|
||||
fl.Bool("v", false, "")
|
||||
|
||||
for _, tc := range []struct {
|
||||
arg string
|
||||
name string
|
||||
hasValue bool
|
||||
}{
|
||||
{"-n", "n", false},
|
||||
{"--n", "n", false},
|
||||
{"-n=1", "n", true},
|
||||
{"--n=", "n", true},
|
||||
{"-v", "v", false},
|
||||
{"-nope", "", false},
|
||||
{"-1", "", false},
|
||||
} {
|
||||
f, hasValue := LookupArg(fl, tc.arg)
|
||||
if tc.name == "" {
|
||||
assert.Nil(t, f, tc.arg)
|
||||
} else {
|
||||
require.NotNil(t, f, tc.arg)
|
||||
assert.Equal(t, tc.name, f.Name, tc.arg)
|
||||
}
|
||||
assert.Equal(t, tc.hasValue, hasValue, tc.arg)
|
||||
}
|
||||
|
||||
assert.True(t, IsBoolFlag(fl.Lookup("v")))
|
||||
assert.False(t, IsBoolFlag(fl.Lookup("n")))
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
package commands
|
||||
|
||||
// Name identifies a command. Every command nebula serves is a constant here, so a
|
||||
// surface, a client and a test spell it the same way and are told at compile time when
|
||||
// they do not. It is a string rather than an integer so a test can register a throwaway
|
||||
// command without adding it here, and so the wire carries the name as the string it has
|
||||
// always been.
|
||||
type Name string
|
||||
|
||||
const (
|
||||
ChangeRemote Name = "change-remote"
|
||||
CloseTunnel Name = "close-tunnel"
|
||||
CreateTunnel Name = "create-tunnel"
|
||||
DeviceInfo Name = "device-info"
|
||||
Help Name = "help"
|
||||
ListHostmap Name = "list-hostmap"
|
||||
ListLighthouseAddrmap Name = "list-lighthouse-addrmap"
|
||||
ListPendingHostmap Name = "list-pending-hostmap"
|
||||
LogFormat Name = "log-format"
|
||||
LogLevel Name = "log-level"
|
||||
Logout Name = "logout"
|
||||
PrintCert Name = "print-cert"
|
||||
PrintRelays Name = "print-relays"
|
||||
PrintTunnel Name = "print-tunnel"
|
||||
QueryLighthouse Name = "query-lighthouse"
|
||||
Reload Name = "reload"
|
||||
Version Name = "version"
|
||||
)
|
||||
@@ -0,0 +1,428 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"cmp"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"maps"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/anmitsu/go-shlex"
|
||||
)
|
||||
|
||||
// Registry holds a set of commands.
|
||||
//
|
||||
// It is safe for concurrent use. Commands may be registered while surfaces are serving
|
||||
// from the registry: the ssh server clones it per session and the control socket filters
|
||||
// it per request, and either may overlap a Register.
|
||||
type Registry struct {
|
||||
mu sync.RWMutex
|
||||
commands map[Name]*Command
|
||||
|
||||
// full is set on a filtered registry and points at the registry it was filtered
|
||||
// from, so a command that's filtered can be reported as such.
|
||||
full *Registry
|
||||
|
||||
// reason explains, in the terms an operator cares about, why this registry withholds
|
||||
// a command they can name. It is supplied by whoever built the filter, because why a
|
||||
// surface declines a command is that surface's business, not the registry's.
|
||||
reason string
|
||||
|
||||
// DefaultFormat decides how a result is rendered when the command line named no
|
||||
// format. It sees the command and its Result, and applies to values and refusals
|
||||
// alike: the registry does not special-case either. The renderer is shared between
|
||||
// surfaces; what each asks for by default is not, so the surface that owns this
|
||||
// registry sets it. Nil means text.
|
||||
DefaultFormat func(c *Command, r Result) Format
|
||||
}
|
||||
|
||||
// defaultFormatFor resolves the surface's default for c's Result.
|
||||
func (r *Registry) defaultFormatFor(c *Command, res Result) Format {
|
||||
if r.DefaultFormat == nil {
|
||||
return FormatText
|
||||
}
|
||||
return r.DefaultFormat(c, res)
|
||||
}
|
||||
|
||||
// New returns an empty Registry with only `help` available.
|
||||
func New() *Registry {
|
||||
r := &Registry{commands: map[Name]*Command{}}
|
||||
r.registerHelp()
|
||||
return r
|
||||
}
|
||||
|
||||
func (r *Registry) registerHelp() {
|
||||
r.Register(&Command{
|
||||
Name: Help,
|
||||
ShortDescription: "prints available commands or help <command> for specific usage info",
|
||||
Run: func(a any, args []string) (Result, error) {
|
||||
if len(args) == 0 {
|
||||
return Value(r.Schema()), nil
|
||||
}
|
||||
|
||||
if c := r.Get(Name(args[0])); c != nil {
|
||||
return Value(r.schemaFor(c)), nil
|
||||
}
|
||||
|
||||
if err := r.unavailable(Name(args[0])); err != nil {
|
||||
return Failed("%s", err), nil
|
||||
}
|
||||
|
||||
return Failed("Command not available %s", args[0]), nil
|
||||
},
|
||||
Text: renderHelp,
|
||||
})
|
||||
}
|
||||
|
||||
// renderHelp is help's human rendering: the command list, or one command's usage.
|
||||
func renderHelp(v any, w io.Writer) error {
|
||||
switch h := v.(type) {
|
||||
case []CommandSchema:
|
||||
return writeCommandList(h, w)
|
||||
case CommandSchema:
|
||||
return WriteCommandHelp(h, w)
|
||||
default:
|
||||
return fmt.Errorf("expected a command schema, got %T", v)
|
||||
}
|
||||
}
|
||||
|
||||
func writeCommandList(cmds []CommandSchema, w io.Writer) error {
|
||||
if _, err := io.WriteString(w, "Available commands:\n"); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// In the order the schema came, which is the display order; see Registry.All.
|
||||
lines := make([]string, 0, len(cmds))
|
||||
for _, c := range cmds {
|
||||
lines = append(lines, fmt.Sprintf("%s - %s", c.Name, c.Short))
|
||||
}
|
||||
|
||||
_, err := io.WriteString(w, strings.Join(lines, "\n")+"\n\n")
|
||||
return err
|
||||
}
|
||||
|
||||
// WriteCommandHelp renders one command's usage. It is the single rendering of a
|
||||
// CommandSchema for a person: the daemon uses it for `help <command>` on both surfaces,
|
||||
// and a client that already holds the schema uses it for `-h`, so the two cannot drift.
|
||||
func WriteCommandHelp(c CommandSchema, w io.Writer) error {
|
||||
if _, err := fmt.Fprintf(w, "%s - %s\n", c.Name, c.Short); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if c.Help != "" {
|
||||
if _, err := fmt.Fprintf(w, " %s\n", c.Help); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
// Same layout as flag.PrintDefaults, including its habit of leaving out a default
|
||||
// that is the zero value.
|
||||
for _, f := range c.Flags {
|
||||
kind := ""
|
||||
if !f.Bool {
|
||||
kind = " string"
|
||||
}
|
||||
def := ""
|
||||
if f.Default != "" && f.Default != "false" {
|
||||
def = fmt.Sprintf(" (default %s)", f.Default)
|
||||
}
|
||||
if _, err := fmt.Fprintf(w, " -%s%s\n \t%s%s\n", f.Name, kind, f.Usage, def); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// Register adds a command that can be run by a user.
|
||||
//
|
||||
// It panics if the command declares a reserved flag. That is a programming error, and
|
||||
// surfacing it here, at startup, is better than at the moment an operator first types
|
||||
// the command.
|
||||
func (r *Registry) Register(c *Command) {
|
||||
if c.Run == nil {
|
||||
panic(fmt.Sprintf("commands: %s has no Run", c.Name))
|
||||
}
|
||||
|
||||
if c.Flags != nil {
|
||||
if fl, _ := c.Flags(); fl != nil {
|
||||
for _, name := range reservedFlags {
|
||||
if fl.Lookup(name) != nil {
|
||||
panic(fmt.Sprintf("commands: %s declares reserved flag -%s", c.Name, name))
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
r.insert(c)
|
||||
}
|
||||
|
||||
// insert adds c without the reserved flag check, for commands that have already passed
|
||||
// it on another registry.
|
||||
func (r *Registry) insert(c *Command) {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
r.commands[c.Name] = c
|
||||
}
|
||||
|
||||
// Get returns the command registered under name, or nil if there is no such command.
|
||||
func (r *Registry) Get(name Name) *Command {
|
||||
r.mu.RLock()
|
||||
defer r.mu.RUnlock()
|
||||
return r.commands[name]
|
||||
}
|
||||
|
||||
// Match returns the names of every command starting with prefix, sorted, as strings for
|
||||
// a prompt to complete and print.
|
||||
func (r *Registry) Match(prefix string) []string {
|
||||
cmds := make([]string, 0)
|
||||
r.mu.RLock()
|
||||
for n := range r.commands {
|
||||
if strings.HasPrefix(string(n), prefix) {
|
||||
cmds = append(cmds, string(n))
|
||||
}
|
||||
}
|
||||
r.mu.RUnlock()
|
||||
slices.Sort(cmds)
|
||||
return cmds
|
||||
}
|
||||
|
||||
// All returns every registered command sorted by name, which is the order help lists
|
||||
// them and the schema describes them.
|
||||
func (r *Registry) All() []*Command {
|
||||
r.mu.RLock()
|
||||
defer r.mu.RUnlock()
|
||||
|
||||
cmds := slices.Collect(maps.Values(r.commands))
|
||||
slices.SortFunc(cmds, func(a, b *Command) int { return cmp.Compare(a.Name, b.Name) })
|
||||
return cmds
|
||||
}
|
||||
|
||||
// Clone returns a copy holding the same commands.
|
||||
//
|
||||
// help is re-registered on the copy rather than carried over, because the source's help
|
||||
// is bound to the source and would list its commands, not the copy's, once a caller
|
||||
// registers something on the copy.
|
||||
func (r *Registry) Clone() *Registry {
|
||||
r.mu.RLock()
|
||||
out := &Registry{
|
||||
commands: maps.Clone(r.commands),
|
||||
full: r.full,
|
||||
reason: r.reason,
|
||||
DefaultFormat: r.DefaultFormat,
|
||||
}
|
||||
r.mu.RUnlock()
|
||||
|
||||
out.registerHelp()
|
||||
return out
|
||||
}
|
||||
|
||||
// Filter returns a filtered copy of the registry.
|
||||
//
|
||||
// Keep should return true for commands that should be included in the copy.
|
||||
//
|
||||
// reason says, to an operator who names a command the copy left out, why this surface
|
||||
// does not serve it; "" leaves the registry to say only that it does not.
|
||||
func (r *Registry) Filter(keep func(*Command) bool, reason string) *Registry {
|
||||
out := &Registry{commands: map[Name]*Command{}, full: r, reason: reason, DefaultFormat: r.DefaultFormat}
|
||||
|
||||
for _, cmd := range r.All() {
|
||||
if keep(cmd) {
|
||||
out.insert(cmd)
|
||||
}
|
||||
}
|
||||
|
||||
// Bind help to the filtered set so it only advertises what this surface serves.
|
||||
out.registerHelp()
|
||||
return out
|
||||
}
|
||||
|
||||
// Dispatch parses a command line and runs it, reporting problems to w. The error is for
|
||||
// the caller to log, not to show; see RunFunc and Failure.
|
||||
func (r *Registry) Dispatch(line string, w Output) error {
|
||||
// A line shlex cannot split, an unbalanced quote. Reported on Err so the output
|
||||
// stream stays parseable.
|
||||
args, err := shlex.Split(line, true)
|
||||
if err != nil {
|
||||
msg := "could not parse the command line: " + err.Error()
|
||||
if _, err := fmt.Fprintln(w.Err, msg); err != nil {
|
||||
return err
|
||||
}
|
||||
return &Failure{Msg: msg}
|
||||
}
|
||||
|
||||
return r.DispatchArgs(args, w)
|
||||
}
|
||||
|
||||
// DispatchArgs runs an already tokenized command line. The error is as for Dispatch.
|
||||
//
|
||||
// An empty line and an unknown command both end up running `help`, the first with the
|
||||
// arguments help itself would take; `<command> -h` is answered by the command's own
|
||||
// FlagSet, with the same rendering, in execLine.
|
||||
func (r *Registry) DispatchArgs(args []string, w Output) error {
|
||||
if len(args) == 0 {
|
||||
args = []string{"help"}
|
||||
}
|
||||
|
||||
c := r.Get(Name(args[0]))
|
||||
if c == nil {
|
||||
if err := r.unavailable(Name(args[0])); err != nil {
|
||||
// Saying why, rather than "did not understand", keeps the rule legible and
|
||||
// points at a surface that will actually run the command.
|
||||
_, _ = fmt.Fprintln(w.Err, err)
|
||||
return err
|
||||
}
|
||||
|
||||
// Only the first word was looked up, so only it is named.
|
||||
msg := fmt.Sprintf("did not understand: %s", args[0])
|
||||
if _, err := fmt.Fprintln(w.Out, msg); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if err := r.DispatchArgs([]string{"help"}, w); err != nil {
|
||||
return err
|
||||
}
|
||||
return &Failure{Msg: msg}
|
||||
}
|
||||
|
||||
return r.execLine(c, args[1:], w)
|
||||
}
|
||||
|
||||
// unavailable explains why name cannot be run here when this registry was filtered from
|
||||
// one that holds it: the command exists, and this surface withholds it, for the reason
|
||||
// whoever built the filter gave. It is nil when name is simply unknown, so the two cases
|
||||
// read differently to an operator.
|
||||
func (r *Registry) unavailable(name Name) error {
|
||||
if r.full == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
c := r.full.Get(name)
|
||||
if c == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
reason := r.reason
|
||||
if reason == "" {
|
||||
reason = "this surface does not serve it"
|
||||
}
|
||||
|
||||
return fmt.Errorf("%s is not available on this surface: %s", c.Name, reason)
|
||||
}
|
||||
|
||||
// Resolve returns the command registered under name, or says why there is none: the
|
||||
// filter's reason for one this surface withholds, or unknown for a name that does not
|
||||
// exist.
|
||||
func (r *Registry) Resolve(name Name) (*Command, error) {
|
||||
if c := r.Get(name); c != nil {
|
||||
return c, nil
|
||||
}
|
||||
|
||||
if err := r.unavailable(name); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("unknown command %q", name)
|
||||
}
|
||||
|
||||
// setParams sets each named parameter on fl, in the order of names, and stops at the
|
||||
// first that is unknown or does not parse. own says whether the command declared flags
|
||||
// of its own, which decides between "takes no parameters" and "has no parameter".
|
||||
//
|
||||
// The presentation flags are on fl, since commandFlags put them there, but they are not
|
||||
// parameters: a request has one place to choose its rendering, the envelope's format
|
||||
// field, and a client that sends them here is told where that is rather than having a
|
||||
// second, weaker way to say the same thing.
|
||||
func setParams(fl *flag.FlagSet, name string, names []string, params map[string]string, own bool) error {
|
||||
for _, k := range names {
|
||||
if isPresentationFlag(k) {
|
||||
return fmt.Errorf("%s is a command line flag, not a parameter; choose the rendering with the request's format field", k)
|
||||
}
|
||||
|
||||
f := fl.Lookup(k)
|
||||
if f == nil {
|
||||
if !own {
|
||||
return fmt.Errorf("%s takes no parameters", name)
|
||||
}
|
||||
return fmt.Errorf("%s has no parameter %q", name, k)
|
||||
}
|
||||
|
||||
v := params[k]
|
||||
if err := fl.Set(k, v); err != nil {
|
||||
if IsBoolFlag(f) {
|
||||
// The flag package's own words for this are "parse error".
|
||||
return fmt.Errorf("%s: expected a boolean, got %q", k, v)
|
||||
}
|
||||
return fmt.Errorf("%s: %w", k, err)
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// Schema describes every command in the registry, so a client can offer them without
|
||||
// having been built against this daemon.
|
||||
func (r *Registry) Schema() []CommandSchema {
|
||||
all := r.All()
|
||||
out := make([]CommandSchema, 0, len(all))
|
||||
for _, c := range all {
|
||||
out = append(out, r.schemaFor(c))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// schemaFor describes one command. It is the one derivation, for the whole schema and
|
||||
// for `help <command>` alike.
|
||||
func (r *Registry) schemaFor(c *Command) CommandSchema {
|
||||
fl, _, _ := commandFlags(c)
|
||||
return schemaOf(c, fl)
|
||||
}
|
||||
|
||||
// schemaOf describes c as driven through fl, the FlagSet commandFlags built for it. The
|
||||
// presentation flags are included because a command line client parses its line
|
||||
// against this and help renders from it; they are listed after the command's own,
|
||||
// which is where readers expect them. Invoke refuses them as parameters.
|
||||
func schemaOf(c *Command, fl *flag.FlagSet) CommandSchema {
|
||||
cs := CommandSchema{Name: c.Name, Short: c.ShortDescription, Help: c.Help}
|
||||
|
||||
var own, shared []FlagSchema
|
||||
fl.VisitAll(func(f *flag.Flag) {
|
||||
fs := FlagSchema{
|
||||
Name: f.Name,
|
||||
Bool: IsBoolFlag(f),
|
||||
Default: f.DefValue,
|
||||
Usage: f.Usage,
|
||||
}
|
||||
if isPresentationFlag(f.Name) {
|
||||
shared = append(shared, fs)
|
||||
return
|
||||
}
|
||||
own = append(own, fs)
|
||||
})
|
||||
cs.Flags = append(own, shared...)
|
||||
|
||||
return cs
|
||||
}
|
||||
|
||||
// CommandSchema describes one command well enough for a client to offer it.
|
||||
type CommandSchema struct {
|
||||
Name Name `json:"name"`
|
||||
Short string `json:"short,omitempty"`
|
||||
Help string `json:"help,omitempty"`
|
||||
Flags []FlagSchema `json:"flags,omitempty"`
|
||||
}
|
||||
|
||||
// FlagSchema describes one of a command's named parameters.
|
||||
type FlagSchema struct {
|
||||
Name string `json:"name"`
|
||||
|
||||
// Bool reports a parameter that takes no value, which is what tells a command line
|
||||
// client whether `-pretty` swallows the word after it.
|
||||
Bool bool `json:"bool,omitempty"`
|
||||
|
||||
Default string `json:"default,omitempty"`
|
||||
Usage string `json:"usage,omitempty"`
|
||||
}
|
||||
@@ -0,0 +1,420 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"flag"
|
||||
"io"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// notWithheld is a stand in for a surface's own policy, which the registry knows nothing
|
||||
// of; see Command.Identity for the one the info API applies.
|
||||
func notWithheld(c *Command) bool { return c.Name != "withheld" }
|
||||
|
||||
const testReason = "this surface does not run commands that write"
|
||||
|
||||
// textLine is a Text renderer for test commands whose result is one string.
|
||||
func textLine(v any, w io.Writer) error {
|
||||
_, err := io.WriteString(w, v.(string)+"\n")
|
||||
return err
|
||||
}
|
||||
|
||||
func testRegistry() *Registry {
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "served",
|
||||
ShortDescription: "a command this surface serves",
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
return Value("read " + strings.Join(a, ",")), nil
|
||||
},
|
||||
Text: textLine,
|
||||
})
|
||||
r.Register(&Command{
|
||||
Name: "withheld",
|
||||
ShortDescription: "a command this surface withholds",
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
return Value("wrote"), nil
|
||||
},
|
||||
Text: textLine,
|
||||
})
|
||||
return r
|
||||
}
|
||||
|
||||
// TestFilterKeepsWhatKeepSays: the copy holds the commands keep accepted, and help.
|
||||
func TestFilterKeepsWhatKeepSays(t *testing.T) {
|
||||
ro := testRegistry().Filter(notWithheld, testReason)
|
||||
|
||||
names := make([]string, 0)
|
||||
for _, c := range ro.All() {
|
||||
names = append(names, string(c.Name))
|
||||
}
|
||||
|
||||
assert.ElementsMatch(t, []string{"help", "served"}, names)
|
||||
}
|
||||
|
||||
// TestRefusesWithheldByName covers a client that knows a command exists and asks for it
|
||||
// anyway. The filter lives on the serving side, so the answer must not depend on what
|
||||
// the client was told was available.
|
||||
func TestRefusesWithheldByName(t *testing.T) {
|
||||
out, errOut := &bytes.Buffer{}, &bytes.Buffer{}
|
||||
w := Output{Out: out, Err: errOut}
|
||||
|
||||
err := testRegistry().Filter(notWithheld, testReason).DispatchArgs([]string{"withheld"}, w)
|
||||
|
||||
require.Error(t, err)
|
||||
assert.Contains(t, err.Error(), "withheld is not available on this surface")
|
||||
assert.Empty(t, out.String(), "a withheld command must produce no output")
|
||||
assert.Contains(t, errOut.String(), "withheld is not available on this surface")
|
||||
assert.Contains(t, errOut.String(), testReason,
|
||||
"the registry should render the explanation the filter supplied, not one of its own")
|
||||
}
|
||||
|
||||
// TestWithheldIsNotReportedAsUnknown keeps the two cases distinct: an operator who
|
||||
// mistypes and one who asked for a real command should not get the same answer.
|
||||
func TestWithheldIsNotReportedAsUnknown(t *testing.T) {
|
||||
out, errOut := &bytes.Buffer{}, &bytes.Buffer{}
|
||||
err := testRegistry().Filter(notWithheld, testReason).DispatchArgs([]string{"no-such-command"}, Output{Out: out, Err: errOut})
|
||||
|
||||
var f *Failure
|
||||
require.ErrorAs(t, err, &f, "an unknown command is a failure to the surface")
|
||||
assert.Contains(t, out.String(), "did not understand: no-such-command")
|
||||
}
|
||||
|
||||
// paramRegistry holds one command with a bool flag and a duration flag, and reports what
|
||||
// the command saw when it ran.
|
||||
func paramRegistry(t *testing.T) (*Registry, *[]paramsSeen) {
|
||||
t.Helper()
|
||||
|
||||
var seen []paramsSeen
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "set",
|
||||
ShortDescription: "sets things",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := paramsSeen{}
|
||||
fl.BoolVar(&s.Verbose, "verbose", false, "say more")
|
||||
fl.DurationVar(&s.Wait, "wait", 0, "how long")
|
||||
return fl, &s
|
||||
},
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
seen = append(seen, *fs.(*paramsSeen))
|
||||
return Value("ok"), nil
|
||||
},
|
||||
})
|
||||
|
||||
return r, &seen
|
||||
}
|
||||
|
||||
type paramsSeen struct {
|
||||
Verbose bool
|
||||
Wait time.Duration
|
||||
}
|
||||
|
||||
// TestInvokeReportsParametersInNameOrder: parameters arrive as an unordered object, so
|
||||
// with two bad ones the error must not depend on map iteration. Name order decides.
|
||||
func TestInvokeReportsParametersInNameOrder(t *testing.T) {
|
||||
r, _ := paramRegistry(t)
|
||||
|
||||
cases := map[string]struct {
|
||||
params map[string]string
|
||||
want string
|
||||
}{
|
||||
"two unknown": {map[string]string{"zed": "1", "alpha": "1"}, `set has no parameter "alpha"`},
|
||||
"unknown before bad bool": {map[string]string{"aaa": "1", "verbose": "maybe"}, `set has no parameter "aaa"`},
|
||||
"bad bool before unknown": {map[string]string{"verbose": "maybe", "zzz": "1"}, `verbose: expected a boolean, got "maybe"`},
|
||||
"bad value before bad bool": {map[string]string{"wait": "soon", "verbose": "maybe"}, `verbose: expected a boolean`},
|
||||
}
|
||||
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
// Enough runs that a map-order dependence would show.
|
||||
for i := 0; i < 50; i++ {
|
||||
_, err := Invoke(Request{Command: r.Get("set"), Params: tc.params})
|
||||
require.Error(t, err)
|
||||
assert.ErrorContains(t, err, tc.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestInvokeWithABadParameterSetsNothing: a request with any bad parameter must not run
|
||||
// the command, and must leave nothing behind for the next request to see. The good
|
||||
// parameter sorts before the bad one, so a one-pass Invoke would have applied it.
|
||||
func TestInvokeWithABadParameterSetsNothing(t *testing.T) {
|
||||
r, seen := paramRegistry(t)
|
||||
|
||||
_, err := Invoke(Request{Command: r.Get("set"), Params: map[string]string{"verbose": "true", "wait": "soon"}})
|
||||
require.ErrorContains(t, err, "wait:")
|
||||
assert.Empty(t, *seen, "the command must not run with a partial parameter set")
|
||||
|
||||
v, err := Invoke(Request{Command: r.Get("set")})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "ok", v.Value)
|
||||
require.Len(t, *seen, 1)
|
||||
assert.Equal(t, paramsSeen{}, (*seen)[0], "nothing from the failed request carried over")
|
||||
|
||||
_, err = Invoke(Request{Command: r.Get("set"), Params: map[string]string{"verbose": "true", "wait": "2s"}})
|
||||
require.NoError(t, err)
|
||||
require.Len(t, *seen, 2)
|
||||
assert.Equal(t, paramsSeen{Verbose: true, Wait: 2 * time.Second}, (*seen)[1])
|
||||
}
|
||||
|
||||
func TestHelpListsOnlyServedCommands(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, testRegistry().Filter(notWithheld, testReason).DispatchArgs(nil, MergedOutput(out)))
|
||||
|
||||
assert.Contains(t, out.String(), "served")
|
||||
assert.NotContains(t, out.String(), "withheld")
|
||||
}
|
||||
|
||||
// TestDispatchReportsUnparseableLine pins that a line shlex rejects says so on Err rather
|
||||
// than coming back silent, so an operator with an unbalanced quote learns the quote is the
|
||||
// problem instead of assuming the command is broken.
|
||||
func TestDispatchReportsUnparseableLine(t *testing.T) {
|
||||
out, errOut := &bytes.Buffer{}, &bytes.Buffer{}
|
||||
testRegistry().Dispatch(`served "unterminated`, Output{Out: out, Err: errOut})
|
||||
assert.Empty(t, out.String())
|
||||
assert.Contains(t, errOut.String(), "could not parse the command line")
|
||||
}
|
||||
|
||||
// TestRegisterRejectsReservedFlags: a command that declares a reserved flag is refused
|
||||
// at Register rather than when an operator first runs it; see reservedFlags.
|
||||
func TestRegisterRejectsReservedFlags(t *testing.T) {
|
||||
for _, name := range []string{"json", "pretty", "h", "help", "config", "socket"} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
r := New()
|
||||
assert.PanicsWithValue(t, "commands: clash declares reserved flag -"+name, func() {
|
||||
r.Register(&Command{
|
||||
Name: "clash",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("clash", flag.ContinueOnError)
|
||||
fl.Bool(name, false, "")
|
||||
return fl, nil
|
||||
},
|
||||
Run: func(fs any, a []string) (Result, error) { return Nothing(), nil },
|
||||
})
|
||||
})
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestRegistryIsSafeForConcurrentUse runs the operations the surfaces perform, filtering
|
||||
// and cloning per request or session, against a stream of registrations. It exists to
|
||||
// be run under the race detector: the map underneath is not goroutine safe.
|
||||
func TestRegistryIsSafeForConcurrentUse(t *testing.T) {
|
||||
r := testRegistry()
|
||||
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 8; i++ {
|
||||
wg.Add(1)
|
||||
go func(i int) {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 50; j++ {
|
||||
r.Register(&Command{
|
||||
Name: Name("late-" + strings.Repeat("a", i) + "-" + strings.Repeat("b", j)),
|
||||
ShortDescription: "registered after the surfaces started",
|
||||
Run: func(fs any, a []string) (Result, error) { return Nothing(), nil },
|
||||
})
|
||||
}
|
||||
}(i)
|
||||
}
|
||||
|
||||
for i := 0; i < 8; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 50; j++ {
|
||||
f := r.Filter(notWithheld, testReason)
|
||||
_ = f.Get("served")
|
||||
_ = f.Schema()
|
||||
_ = r.Clone().Match("late-")
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
wg.Wait()
|
||||
|
||||
f := r.Filter(notWithheld, testReason)
|
||||
assert.Len(t, f.Match("late-"), 8*50, "every late registration is visible once the writers finish")
|
||||
}
|
||||
|
||||
// TestCloneHelpSeesCloneCommands: the ssh session registers logout on its clone, and
|
||||
// the source does not learn of it. Help on the clone answers for the clone, and -h on a
|
||||
// command prints what `help <name>` does, on a clone as on the source: both render
|
||||
// through WriteCommandHelp, and Clone rebinds help to the copy.
|
||||
func TestCloneHelpSeesCloneCommands(t *testing.T) {
|
||||
r := testRegistry()
|
||||
c := r.Clone()
|
||||
c.Register(&Command{
|
||||
Name: Logout,
|
||||
ShortDescription: "ends the session",
|
||||
Run: func(fs any, a []string) (Result, error) { return Nothing(), nil },
|
||||
})
|
||||
assert.Nil(t, r.Get(Logout), "the source is not affected")
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, c.DispatchArgs([]string{"help"}, MergedOutput(out)))
|
||||
assert.Contains(t, out.String(), "logout")
|
||||
|
||||
for _, name := range []string{"logout", "served"} {
|
||||
flag := &bytes.Buffer{}
|
||||
c.Dispatch(name+" -h", MergedOutput(flag))
|
||||
cmd := &bytes.Buffer{}
|
||||
c.Dispatch("help "+name, MergedOutput(cmd))
|
||||
assert.Equal(t, cmd.String(), flag.String(), name)
|
||||
assert.Contains(t, flag.String(), name+" - ", name)
|
||||
}
|
||||
}
|
||||
|
||||
// TestThenRunsAfterTheReply pins the order Then exists for: Run's line is on the writer
|
||||
// before the action begins, Then's Result follows it, and Then's outcome is the
|
||||
// command's.
|
||||
func TestThenRunsAfterTheReply(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
seen := "never ran"
|
||||
outcome := Did("acted")
|
||||
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "act",
|
||||
ShortDescription: "replies, then acts",
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
return Did("about to act"), nil
|
||||
},
|
||||
Then: func() Result {
|
||||
seen = out.String()
|
||||
return outcome
|
||||
},
|
||||
})
|
||||
|
||||
require.NoError(t, r.DispatchArgs([]string{"act"}, MergedOutput(out)))
|
||||
assert.Equal(t, "about to act\n", seen, "the line was written before the action")
|
||||
assert.Equal(t, "about to act\nacted\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
outcome = Failed("could not act")
|
||||
var f *Failure
|
||||
require.ErrorAs(t, r.DispatchArgs([]string{"act"}, MergedOutput(out)), &f)
|
||||
assert.Equal(t, "about to act\ncould not act\n", out.String())
|
||||
|
||||
// In JSON only the outcome travels: one document for the program that asked.
|
||||
out.Reset()
|
||||
require.ErrorAs(t, r.DispatchArgs([]string{"act", "-json"}, MergedOutput(out)), &f)
|
||||
assert.JSONEq(t, `{"ok":false,"reason":"could not act"}`, out.String())
|
||||
|
||||
// A Run that refused is the outcome; the action does not happen.
|
||||
ran := false
|
||||
r.Register(&Command{
|
||||
Name: "refuse",
|
||||
ShortDescription: "refuses, so never acts",
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
return Failed("not like that"), nil
|
||||
},
|
||||
Then: func() Result {
|
||||
ran = true
|
||||
return Did("acted anyway")
|
||||
},
|
||||
})
|
||||
out.Reset()
|
||||
require.ErrorAs(t, r.DispatchArgs([]string{"refuse"}, MergedOutput(out)), &f)
|
||||
assert.Equal(t, "not like that\n", out.String())
|
||||
assert.False(t, ran)
|
||||
out.Reset()
|
||||
require.ErrorAs(t, r.DispatchArgs([]string{"refuse", "-json"}, MergedOutput(out)), &f)
|
||||
assert.JSONEq(t, `{"ok":false,"reason":"not like that"}`, out.String())
|
||||
assert.False(t, ran)
|
||||
}
|
||||
|
||||
// TestWriteCommandHelpIsTheOneRendering pins the layout both `help <command>` on the
|
||||
// daemon and `-h` in the client print, so the two cannot drift apart again.
|
||||
func TestWriteCommandHelpIsTheOneRendering(t *testing.T) {
|
||||
cs := CommandSchema{
|
||||
Name: "change-remote",
|
||||
Short: "changes a remote",
|
||||
Help: "Give it an address.",
|
||||
Flags: []FlagSchema{
|
||||
{Name: "address", Usage: "the new remote", Default: "1.2.3.4:4242"},
|
||||
{Name: "by-index", Bool: true, Usage: "match by index"},
|
||||
{Name: "json", Bool: true, Usage: "outputs as json"},
|
||||
},
|
||||
}
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, WriteCommandHelp(cs, out))
|
||||
|
||||
assert.Equal(t, "change-remote - changes a remote\n"+
|
||||
" Give it an address.\n"+
|
||||
" -address string\n \tthe new remote (default 1.2.3.4:4242)\n"+
|
||||
" -by-index\n \tmatch by index\n"+
|
||||
" -json\n \toutputs as json\n", out.String())
|
||||
}
|
||||
|
||||
// addrFlags is the flag struct of a test command that takes -address.
|
||||
type addrFlags struct{ Address string }
|
||||
|
||||
// TestHelpFlagIsReadWhereParseReadsIt: -h asks for help only where the line's parser
|
||||
// reads it as a flag. As a flag's value or after -- it reaches the command as the
|
||||
// operand it is, and help is rendered by the same function `help <command>` uses.
|
||||
func TestHelpFlagIsReadWhereParseReadsIt(t *testing.T) {
|
||||
var seen []string
|
||||
r := New()
|
||||
r.Register(Flagged(&Command{Name: "x", ShortDescription: "takes an address"},
|
||||
func(fl *flag.FlagSet, s *addrFlags) { fl.StringVar(&s.Address, "address", "", "an address") },
|
||||
func(s *addrFlags, a []string) (Result, error) {
|
||||
seen = append(seen, s.Address+"|"+strings.Join(a, ","))
|
||||
return Nothing(), nil
|
||||
}))
|
||||
|
||||
for _, line := range []string{"x -h", "x -help", "x --help", "x 10.0.0.1 -h", "x -address=1 -h"} {
|
||||
out := &bytes.Buffer{}
|
||||
r.Dispatch(line, MergedOutput(out))
|
||||
assert.Contains(t, out.String(), "x - takes an address\n", line)
|
||||
assert.Contains(t, out.String(), "-address string", line)
|
||||
}
|
||||
assert.Empty(t, seen, "asking for help must not run the command")
|
||||
|
||||
for _, line := range []string{"x -address -h", "x -- -h"} {
|
||||
out := &bytes.Buffer{}
|
||||
r.Dispatch(line, MergedOutput(out))
|
||||
assert.Empty(t, out.String(), line)
|
||||
}
|
||||
assert.Equal(t, []string{"-h|", "|-h"}, seen)
|
||||
}
|
||||
|
||||
// TestBadFlagIsAnsweredWithTheCommandsHelp: a flag the command does not have is reported
|
||||
// on the error stream followed by the command's usage, in the rendering help uses.
|
||||
func TestBadFlagIsAnsweredWithTheCommandsHelp(t *testing.T) {
|
||||
out, errOut := &bytes.Buffer{}, &bytes.Buffer{}
|
||||
r := New()
|
||||
r.Register(&Command{Name: "x", ShortDescription: "has no flags", Run: func(fs any, a []string) (Result, error) { return Nothing(), nil }})
|
||||
|
||||
require.Error(t, r.DispatchArgs([]string{"x", "-nope"}, Output{Out: out, Err: errOut}))
|
||||
assert.Empty(t, out.String())
|
||||
assert.Equal(t, "flag provided but not defined: -nope\nx - has no flags\n -json\n \toutputs as json\n -pretty\n \tpretty prints json, assumes -json\n", errOut.String())
|
||||
}
|
||||
|
||||
// TestRunErrorIsShown: an error Run returns reaches the person at the prompt on the
|
||||
// error stream, as well as the surface that logs it.
|
||||
func TestRunErrorIsShown(t *testing.T) {
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "broken",
|
||||
ShortDescription: "cannot do what it is asked",
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
return Result{}, errors.New("no certificate is loaded")
|
||||
},
|
||||
})
|
||||
|
||||
out, errOut := &bytes.Buffer{}, &bytes.Buffer{}
|
||||
require.EqualError(t, r.DispatchArgs([]string{"broken"}, Output{Out: out, Err: errOut}), "no certificate is loaded")
|
||||
assert.Empty(t, out.String())
|
||||
assert.Equal(t, "no certificate is loaded\n", errOut.String())
|
||||
}
|
||||
@@ -0,0 +1,179 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
)
|
||||
|
||||
// ErrNoTextRendering is returned by Render when a command's Value has no human rendering
|
||||
// and text was asked for anyway. A command declares this by leaving Text nil and saying
|
||||
// so with JSONOnly; it is not a fallback situation but a statement that no such form
|
||||
// exists yet, so nobody builds a script around an interim one. Each surface's default
|
||||
// policy avoids ever asking.
|
||||
var ErrNoTextRendering = errors.New("no human readable output yet; pass -json or -pretty")
|
||||
|
||||
// Format is how a result should be presented.
|
||||
type Format int
|
||||
|
||||
const (
|
||||
// FormatUnset is a request that expressed no preference. A surface resolves it with
|
||||
// its own default before rendering; Render itself treats it as FormatText.
|
||||
FormatUnset Format = iota
|
||||
|
||||
// FormatText renders for a person. It is what an operator gets by default on every
|
||||
// surface with a human at the other end.
|
||||
FormatText
|
||||
|
||||
// FormatJSON renders the result as compact JSON.
|
||||
FormatJSON
|
||||
|
||||
// FormatPrettyJSON renders the result as indented JSON.
|
||||
FormatPrettyJSON
|
||||
)
|
||||
|
||||
// Flag names for the two presentation flags. They are offered on every command rather
|
||||
// than declared by each one, because how a result is displayed is not a property of the
|
||||
// command that produced it.
|
||||
const (
|
||||
FlagJSON = "json"
|
||||
FlagPretty = "pretty"
|
||||
)
|
||||
|
||||
// Flag names nebula ctl takes for itself, anywhere on its line, to say which daemon to
|
||||
// talk to; see reservedFlags.
|
||||
const (
|
||||
FlagConfig = "config"
|
||||
FlagSocket = "socket"
|
||||
)
|
||||
|
||||
// reservedFlags are handled before a command's Run is called, so a command may not
|
||||
// declare them itself. -h and -help are intercepted as a request for usage; -json and
|
||||
// -pretty are added to every command's FlagSet by commandFlags, on every surface, so a
|
||||
// command that defined either would make that definition panic with "flag redefined"
|
||||
// on whichever goroutine ran the command; and -config and -socket are nebula ctl's own,
|
||||
// taken off the line before the client knows which command it names, so a command
|
||||
// that declared either would never receive it there.
|
||||
var reservedFlags = []string{"h", "help", FlagJSON, FlagPretty, FlagConfig, FlagSocket}
|
||||
|
||||
// Render writes r in the requested format. Every surface calls it, so a hostmap looks
|
||||
// the same over ssh as it does through the control socket, and a change to either
|
||||
// rendering happens once.
|
||||
func Render(c *Command, r Result, f Format, w io.Writer) error {
|
||||
switch f {
|
||||
case FormatJSON:
|
||||
return renderJSON(r.Payload(), w, false)
|
||||
|
||||
case FormatPrettyJSON:
|
||||
return renderJSON(r.Payload(), w, true)
|
||||
|
||||
default:
|
||||
// An outcome reads the same for every command: its reason, as a sentence. Only a
|
||||
// Value needs the command's own rendering, so Text never sees anything else.
|
||||
if r.Value == nil {
|
||||
_, err := io.WriteString(w, r.Reason+"\n")
|
||||
return err
|
||||
}
|
||||
|
||||
if c != nil && c.Text != nil {
|
||||
return c.Text(r.Value, w)
|
||||
}
|
||||
|
||||
name := "this command"
|
||||
if c != nil {
|
||||
name = string(c.Name)
|
||||
}
|
||||
return fmt.Errorf("%s has %w", name, ErrNoTextRendering)
|
||||
}
|
||||
}
|
||||
|
||||
func renderJSON(v any, w io.Writer, indent bool) error {
|
||||
enc := json.NewEncoder(w)
|
||||
if indent {
|
||||
enc.SetIndent("", " ")
|
||||
}
|
||||
|
||||
return enc.Encode(v)
|
||||
}
|
||||
|
||||
// Result is what every Run returns: whether the command worked, a sentence saying so,
|
||||
// and, for a command that reports rather than acts, the value it produced.
|
||||
//
|
||||
// Value and Reason are alternatives. A command that reports returns Value(v), and the
|
||||
// surfaces render v, as JSON or through the command's Text. A command that acts, or any
|
||||
// command refusing its arguments, returns Did or Failed, and the surfaces render the
|
||||
// Outcome: its Reason is the sentence these commands have always printed. Nothing is for
|
||||
// a command with nothing to say.
|
||||
//
|
||||
// The envelope itself never reaches a caller. Payload is what JSON carries, and Render
|
||||
// hands Text only the Value, so a command's renderer sees the one type it returns on
|
||||
// success and is never asked to recognise an Outcome.
|
||||
type Result struct {
|
||||
Outcome
|
||||
Value any
|
||||
}
|
||||
|
||||
// Outcome is the part of a Result that says whether the command worked and, in words a
|
||||
// caller can show someone, why. It is what a program receives from a command that acts
|
||||
// rather than reports: closing a tunnel, changing a remote, reloading config.
|
||||
//
|
||||
// One shape serves all of them. Designing a payload per outcome would be work without a
|
||||
// reader. Reason is set either way, so a success says what it did rather than leaving
|
||||
// the caller to infer it from a bare true.
|
||||
type Outcome struct {
|
||||
OK bool `json:"ok"`
|
||||
Reason string `json:"reason"`
|
||||
}
|
||||
|
||||
// Value is the Result of a command that reports: v is what it has to show, and it must
|
||||
// marshal to JSON.
|
||||
func Value(v any) Result {
|
||||
return Result{Outcome: Outcome{OK: true}, Value: v}
|
||||
}
|
||||
|
||||
// Failed is a convenience for the common "it did not work, here is why" case.
|
||||
func Failed(format string, args ...any) Result {
|
||||
return Result{Outcome: Outcome{Reason: fmt.Sprintf(format, args...)}}
|
||||
}
|
||||
|
||||
// Did is a convenience for the common "it worked, here is what happened" case.
|
||||
func Did(format string, args ...any) Result {
|
||||
return Result{Outcome: Outcome{OK: true, Reason: fmt.Sprintf(format, args...)}}
|
||||
}
|
||||
|
||||
// Nothing is the Result of a command with nothing to say: it did its work, and the
|
||||
// surface sends an empty, successful reply without rendering anything.
|
||||
func Nothing() Result {
|
||||
return Result{Outcome: Outcome{OK: true}}
|
||||
}
|
||||
|
||||
// Empty reports a Result with nothing to render: no Value and no Reason. The zero Result
|
||||
// counts, so a Run that returns Result{} says nothing rather than failing silently.
|
||||
func (r Result) Empty() bool {
|
||||
return r.Value == nil && r.Reason == ""
|
||||
}
|
||||
|
||||
// Payload is what a program receives: the Value when there is one, otherwise the
|
||||
// Outcome. No surface sends the envelope itself, so print-tunnel -json emits the tunnel
|
||||
// and close-tunnel -json emits {ok, reason}.
|
||||
func (r Result) Payload() any {
|
||||
if r.Value != nil {
|
||||
return r.Value
|
||||
}
|
||||
return r.Outcome
|
||||
}
|
||||
|
||||
// Typed adapts a renderer for one result type to the TextFunc a Command declares. The
|
||||
// value Render passes is the command's own, see Result, so all that is left is to name
|
||||
// its type once here instead of asserting it at the top of every renderer. A renderer
|
||||
// paired with a command that returns something else fails here, saying what arrived.
|
||||
func Typed[T any](render func(T, io.Writer) error) TextFunc {
|
||||
return func(v any, w io.Writer) error {
|
||||
t, ok := v.(T)
|
||||
if !ok {
|
||||
return fmt.Errorf("expected %T, got %T", t, v)
|
||||
}
|
||||
return render(t, w)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,105 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"io"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestRenderPrintsAnOutcomeWithoutText: a command that acts declares no Text. Its
|
||||
// outcome renders as the reason, the same for every command, and as {ok, reason} in
|
||||
// JSON, which is the shape these commands have always emitted.
|
||||
func TestRenderPrintsAnOutcomeWithoutText(t *testing.T) {
|
||||
c := &Command{Name: "act"}
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, Render(c, Did("Closed"), FormatText, out))
|
||||
assert.Equal(t, "Closed\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
require.NoError(t, Render(c, Failed("No vpn address was provided"), FormatText, out))
|
||||
assert.Equal(t, "No vpn address was provided\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
require.NoError(t, Render(c, Failed("nope"), FormatJSON, out))
|
||||
assert.JSONEq(t, `{"ok":false,"reason":"nope"}`, out.String())
|
||||
}
|
||||
|
||||
// TestRenderHandsTextOnlyTheValue pins the guarantee Result exists for: a command's
|
||||
// renderer sees the type it returns on success and never the envelope or an outcome, so
|
||||
// a report command that refuses its arguments needs nothing in its Text to cope.
|
||||
func TestRenderHandsTextOnlyTheValue(t *testing.T) {
|
||||
var got any
|
||||
c := &Command{
|
||||
Name: "report",
|
||||
Text: func(v any, w io.Writer) error {
|
||||
got = v
|
||||
_, err := io.WriteString(w, "rendered\n")
|
||||
return err
|
||||
},
|
||||
}
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, Render(c, Value("data"), FormatText, out))
|
||||
assert.Equal(t, "data", got)
|
||||
assert.Equal(t, "rendered\n", out.String())
|
||||
|
||||
got, out = nil, &bytes.Buffer{}
|
||||
require.NoError(t, Render(c, Failed("refused"), FormatText, out))
|
||||
assert.Nil(t, got, "Text must not be called for an outcome")
|
||||
assert.Equal(t, "refused\n", out.String())
|
||||
|
||||
out.Reset()
|
||||
require.NoError(t, Render(c, Value("data"), FormatJSON, out))
|
||||
assert.JSONEq(t, `"data"`, out.String(), "JSON carries the value, never the envelope")
|
||||
}
|
||||
|
||||
// TestRenderRefusesTextForAValueWithoutText: leaving Text nil is a statement that no
|
||||
// human form of the value exists yet, and asking for one is an error that says so.
|
||||
func TestRenderRefusesTextForAValueWithoutText(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
err := Render(&Command{Name: "print-tunnel"}, Value(map[string]int{"index": 7}), FormatText, out)
|
||||
require.ErrorIs(t, err, ErrNoTextRendering)
|
||||
require.ErrorContains(t, err, "print-tunnel has no human readable output yet")
|
||||
assert.Empty(t, out.String())
|
||||
}
|
||||
|
||||
// TestTypedNamesTheTypeOnce: Typed replaces the assertion at the top of every renderer.
|
||||
// The right type reaches the renderer; the wrong one is reported, naming both.
|
||||
func TestTypedNamesTheTypeOnce(t *testing.T) {
|
||||
type info struct{ Name string }
|
||||
render := Typed(func(i info, w io.Writer) error {
|
||||
_, err := io.WriteString(w, i.Name+"\n")
|
||||
return err
|
||||
})
|
||||
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, render(info{Name: "tun0"}, out))
|
||||
assert.Equal(t, "tun0\n", out.String())
|
||||
|
||||
err := render("not an info", out)
|
||||
require.Error(t, err)
|
||||
assert.ErrorContains(t, err, "expected commands.info, got string")
|
||||
}
|
||||
|
||||
// TestResultShapes pins what each constructor means to a surface: Empty is the one that
|
||||
// renders nothing, Payload is what a program receives, and OK is set wherever a reason
|
||||
// or value says the command worked.
|
||||
func TestResultShapes(t *testing.T) {
|
||||
assert.True(t, Nothing().Empty())
|
||||
assert.True(t, Result{}.Empty(), "the zero Result says nothing rather than failing silently")
|
||||
assert.False(t, Did("done").Empty())
|
||||
assert.False(t, Failed("no").Empty())
|
||||
assert.False(t, Value("x").Empty())
|
||||
|
||||
assert.True(t, Value("x").OK)
|
||||
assert.True(t, Did("done").OK)
|
||||
assert.False(t, Failed("no").OK)
|
||||
|
||||
assert.Equal(t, "x", Value("x").Payload())
|
||||
assert.Equal(t, Outcome{OK: true, Reason: "done"}, Did("done").Payload())
|
||||
assert.Equal(t, Outcome{Reason: "no"}, Failed("no").Payload())
|
||||
}
|
||||
@@ -0,0 +1,119 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"flag"
|
||||
"maps"
|
||||
"slices"
|
||||
)
|
||||
|
||||
// Request is one command to run, as every surface hands it to Invoke: the command, its
|
||||
// options by name in the form their flags parse, its operands, and the rendering the
|
||||
// line asked for, if any.
|
||||
//
|
||||
// nebula ctl builds one with ParseLine and it travels as a JSON object to the control
|
||||
// socket. An ssh line never becomes one: it is parsed straight into the command's own
|
||||
// FlagSet; see execLine.
|
||||
type Request struct {
|
||||
// Command is the command to run, resolved by the surface at its edge. See
|
||||
// Registry.Resolve for the one that tells an unknown name from a withheld one.
|
||||
Command *Command
|
||||
|
||||
// Params carries the options the line set, by flag name, each in the form its flag
|
||||
// parses from. An option left alone is absent, so the command's default applies.
|
||||
Params map[string]string
|
||||
|
||||
// Args carries the operands: whatever the line did not consume as a flag.
|
||||
Args []string
|
||||
|
||||
// Format is the rendering the line asked for with -json or -pretty, or FormatUnset
|
||||
// when it expressed no preference. It is ParseLine's reading of the line for the
|
||||
// client that sends the Request; Invoke does not read it, since the surface that
|
||||
// runs a Request renders with the format it agreed with its caller.
|
||||
Format Format
|
||||
}
|
||||
|
||||
// ParseLine reads a FlagSet that ParseArgs has filled, and the operands it returned,
|
||||
// into a Request to send over the wire. Command is left for the caller to set.
|
||||
//
|
||||
// Every flag the line set other than the presentation flags travels by name, as its
|
||||
// flag's String, which is what the daemon's Set parses. That round trip is exact for
|
||||
// the bool and string flags a client builds from the schema; it is the client's to make,
|
||||
// and the ssh path does not make it, since it runs the FlagSet it parsed.
|
||||
func ParseLine(fl *flag.FlagSet, operands []string) Request {
|
||||
req := Request{Args: operands, Format: presentationFormat(fl)}
|
||||
|
||||
fl.Visit(func(f *flag.Flag) {
|
||||
if isPresentationFlag(f.Name) {
|
||||
return
|
||||
}
|
||||
if req.Params == nil {
|
||||
req.Params = map[string]string{}
|
||||
}
|
||||
req.Params[f.Name] = f.Value.String()
|
||||
})
|
||||
|
||||
return req
|
||||
}
|
||||
|
||||
// presentationFormat is the one reading of -json and -pretty from a parsed line, so a
|
||||
// line means the same on every surface: only a flag set to true asks for JSON, since one
|
||||
// set to false expresses no preference, and -pretty implies -json. FormatUnset means the
|
||||
// line expressed no preference and the surface's own default applies.
|
||||
func presentationFormat(fl *flag.FlagSet) Format {
|
||||
var asJSON, pretty bool
|
||||
fl.Visit(func(f *flag.Flag) {
|
||||
switch f.Name {
|
||||
case FlagJSON:
|
||||
asJSON = flagIsTrue(f)
|
||||
case FlagPretty:
|
||||
pretty = flagIsTrue(f)
|
||||
}
|
||||
})
|
||||
|
||||
switch {
|
||||
case pretty:
|
||||
return FormatPrettyJSON
|
||||
case asJSON:
|
||||
return FormatJSON
|
||||
default:
|
||||
return FormatUnset
|
||||
}
|
||||
}
|
||||
|
||||
// flagIsTrue reports whether a bool flag was set to true. The flag package's bool value
|
||||
// is a flag.Getter whose Get returns the bool, so this never falls back to parsing text.
|
||||
func flagIsTrue(f *flag.Flag) bool {
|
||||
g, ok := f.Value.(flag.Getter)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
b, _ := g.Get().(bool)
|
||||
return b
|
||||
}
|
||||
|
||||
// Invoke runs one Request and returns the command's Result, unrendered.
|
||||
//
|
||||
// The parameters are applied by flag name, in name order: a request from the wire is a
|
||||
// JSON object with no order of its own, and which of two bad parameters is reported must
|
||||
// not change from one request to the next. An unknown parameter is an error rather than
|
||||
// something quietly ignored, because a caller that misspells one deserves to hear about
|
||||
// it instead of getting a default. A bad parameter means Run is never called, and the
|
||||
// FlagSet is fresh for this call, so nothing set before it is seen by anyone.
|
||||
//
|
||||
// Nothing here writes anywhere and nothing here renders. What a surface does with the
|
||||
// Result, marshal its Payload or run the command's own text rendering through Render,
|
||||
// is the surface's decision, and keeping that out of here is what lets a caller tell a
|
||||
// refusal from a success after the text has been produced. The presentation flags are
|
||||
// not parameters: a Request says how it wants rendering in Format, and sending them as
|
||||
// parameters is refused rather than read as a preference.
|
||||
func Invoke(req Request) (Result, error) {
|
||||
c := req.Command
|
||||
names := slices.Sorted(maps.Keys(req.Params))
|
||||
|
||||
fl, fs, own := commandFlags(c)
|
||||
if err := setParams(fl, string(c.Name), names, req.Params, own); err != nil {
|
||||
return Result{}, err
|
||||
}
|
||||
|
||||
return c.Run(fs, req.Args)
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package commands
|
||||
|
||||
import (
|
||||
"flag"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func lineFlags() *flag.FlagSet {
|
||||
fl := flag.NewFlagSet("set", flag.ContinueOnError)
|
||||
fl.Bool("verbose", false, "")
|
||||
fl.Duration("wait", 0, "")
|
||||
fl.String("label", "none", "")
|
||||
fl.Bool(FlagJSON, false, "")
|
||||
fl.Bool(FlagPretty, false, "")
|
||||
return fl
|
||||
}
|
||||
|
||||
// TestParseLineReadsThePresentationFlagsOnce: presentationFormat is the one reading of
|
||||
// -json and -pretty, for every surface, and ParseLine carries its answer. A flag set to
|
||||
// false expresses no preference, and neither flag ever travels as a parameter.
|
||||
func TestParseLineReadsThePresentationFlagsOnce(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
args []string
|
||||
want Format
|
||||
}{
|
||||
{nil, FormatUnset},
|
||||
{[]string{"-json=false"}, FormatUnset},
|
||||
{[]string{"-pretty=false"}, FormatUnset},
|
||||
{[]string{"-json"}, FormatJSON},
|
||||
{[]string{"-pretty"}, FormatPrettyJSON},
|
||||
{[]string{"-pretty", "-json=false"}, FormatPrettyJSON},
|
||||
} {
|
||||
fl := lineFlags()
|
||||
operands, err := ParseArgs(fl, tc.args)
|
||||
require.NoError(t, err)
|
||||
|
||||
req := ParseLine(fl, operands)
|
||||
assert.Equal(t, tc.want, req.Format, "%v", tc.args)
|
||||
assert.Nil(t, req.Params, "%v: presentation flags are not parameters", tc.args)
|
||||
}
|
||||
}
|
||||
|
||||
// TestParseLineCarriesWhatWasSetInParseableForm: only the flags the line set travel,
|
||||
// each as the string its flag parses from, so the daemon's Invoke can apply them to a
|
||||
// fresh FlagSet and get the same values back. Operands come through untouched, those
|
||||
// after "--" included.
|
||||
func TestParseLineCarriesWhatWasSetInParseableForm(t *testing.T) {
|
||||
fl := lineFlags()
|
||||
operands, err := ParseArgs(fl, []string{"-verbose", "-wait", "2s", "x", "--", "-1"})
|
||||
require.NoError(t, err)
|
||||
|
||||
req := ParseLine(fl, operands)
|
||||
assert.Equal(t, map[string]string{"verbose": "true", "wait": "2s"}, req.Params, "label was left alone and must be absent")
|
||||
assert.Equal(t, []string{"x", "-1"}, req.Args)
|
||||
assert.Equal(t, FormatUnset, req.Format)
|
||||
|
||||
// The round trip a client makes: what ParseLine produced is what Invoke applies.
|
||||
r, seen := paramRegistry(t)
|
||||
req.Command = r.Get("set")
|
||||
_, err = Invoke(req)
|
||||
require.NoError(t, err)
|
||||
require.Len(t, *seen, 1)
|
||||
assert.Equal(t, paramsSeen{Verbose: true, Wait: 2 * time.Second}, (*seen)[0])
|
||||
}
|
||||
|
||||
// TestResolveTellsUnknownFromWithheld: the two cases read differently to an operator,
|
||||
// and Resolve is the edge that decides which one a name from the wire is.
|
||||
func TestResolveTellsUnknownFromWithheld(t *testing.T) {
|
||||
r := testRegistry().Filter(notWithheld, testReason)
|
||||
|
||||
c, err := r.Resolve("served")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, Name("served"), c.Name)
|
||||
|
||||
_, err = r.Resolve("withheld")
|
||||
require.ErrorContains(t, err, "withheld is not available on this surface")
|
||||
|
||||
_, err = r.Resolve("no-such-command")
|
||||
require.ErrorContains(t, err, `unknown command "no-such-command"`)
|
||||
}
|
||||
|
||||
// TestLineRunsTheFlagSetItParsed: the ssh path hands Run the FlagSet the line was parsed
|
||||
// into, with no trip through a Request. A flag.Func has no String worth re-parsing, so a
|
||||
// round trip would hand Run an empty value and no error; the line's value must arrive.
|
||||
func TestLineRunsTheFlagSetItParsed(t *testing.T) {
|
||||
var seen []string
|
||||
r := New()
|
||||
r.Register(&Command{
|
||||
Name: "mode",
|
||||
Flags: func() (*flag.FlagSet, any) {
|
||||
fl := flag.NewFlagSet("", flag.ContinueOnError)
|
||||
s := new(string)
|
||||
fl.Func("mode", "the mode", func(v string) error {
|
||||
*s = "set:" + v
|
||||
return nil
|
||||
})
|
||||
return fl, s
|
||||
},
|
||||
Run: func(fs any, a []string) (Result, error) {
|
||||
seen = append(seen, *fs.(*string))
|
||||
return Value("ok"), nil
|
||||
},
|
||||
})
|
||||
|
||||
var out, errw strings.Builder
|
||||
r.Dispatch("mode -json -mode fast", Output{Out: &out, Err: &errw})
|
||||
require.Equal(t, []string{"set:fast"}, seen)
|
||||
assert.Empty(t, errw.String())
|
||||
assert.Equal(t, "\"ok\"\n", out.String(), "-json was read from the same FlagSet")
|
||||
}
|
||||
@@ -0,0 +1,23 @@
|
||||
package commands
|
||||
|
||||
import "io"
|
||||
|
||||
// Output is where a command line surface's text goes.
|
||||
//
|
||||
// Out and Err are distinct so a command's primary output can stay machine readable on
|
||||
// a surface that separates the two. The ssh surface points both at the same channel and
|
||||
// sees a single merged stream. The local
|
||||
// control socket does not use one at all: it invokes by named parameter and carries the
|
||||
// returned value, so there is no stream for a command to write to.
|
||||
type Output struct {
|
||||
// Out receives what a command produces.
|
||||
Out io.Writer
|
||||
|
||||
// Err receives usage text, refusals and errors.
|
||||
Err io.Writer
|
||||
}
|
||||
|
||||
// MergedOutput sends output and errors to the same writer.
|
||||
func MergedOutput(w io.Writer) Output {
|
||||
return Output{Out: w, Err: w}
|
||||
}
|
||||
@@ -0,0 +1,111 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// TestLogFormatRefusalIsShown: a format the logger does not know is a refusal the user
|
||||
// sees, rather than a bare error, which over ssh was silence.
|
||||
func TestLogFormatRefusalIsShown(t *testing.T) {
|
||||
l := logging.NewLogger(io.Discard)
|
||||
|
||||
res, err := runLogFormat(l, []string{"bogus"})
|
||||
require.NoError(t, err)
|
||||
assert.False(t, res.OK)
|
||||
assert.Equal(t, "Unable to set log format: unknown log format `bogus`. possible formats: [text json]", res.Reason)
|
||||
|
||||
res, err = runLogFormat(l, []string{"JSON"})
|
||||
require.NoError(t, err)
|
||||
out := &bytes.Buffer{}
|
||||
require.NoError(t, commands.Typed(textLogFormat)(res.Value, out))
|
||||
assert.Equal(t, "Log format is: json\n", out.String())
|
||||
}
|
||||
|
||||
// TestPrintRelaysReportsErrorsAsText: the Error field was an error value, which encodes
|
||||
// as {} and lost the message. It is the message now, and absent when there is none.
|
||||
func TestPrintRelaysReportsErrorsAsText(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
hm := newHostMap(l)
|
||||
relay := netip.MustParseAddr("10.0.0.1")
|
||||
peer := netip.MustParseAddr("10.0.0.2")
|
||||
|
||||
// A relay host that is in Relays but not in Hosts, so its hostinfo cannot be found.
|
||||
hm.Relays[1] = &HostInfo{vpnAddrs: []netip.Addr{relay}}
|
||||
ifce := &Interface{hostMap: hm}
|
||||
|
||||
marshal := func() string {
|
||||
b, err := json.Marshal(runPrintRelays(ifce))
|
||||
require.NoError(t, err)
|
||||
return string(b)
|
||||
}
|
||||
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Error":"could not find hostinfo","Type":"","State":"","PeerAddr":"","LocalIndex":0,"RemoteIndex":0,"RelayedThrough":null}]}]}`, marshal())
|
||||
|
||||
// The same relay host, found, relaying for a peer whose index matches: no Error key.
|
||||
hi := hm.Relays[1]
|
||||
r := &Relay{Type: ForwardingType, State: Established, PeerAddr: peer, LocalIndex: 1, RemoteIndex: 2}
|
||||
hi.relayState = RelayState{
|
||||
relayForByAddr: map[netip.Addr]*Relay{peer: r},
|
||||
relayForByIdx: map[uint32]*Relay{r.LocalIndex: r},
|
||||
}
|
||||
hm.Hosts[relay] = hi
|
||||
assert.JSONEq(t, `{"Relays":[{"NebulaAddr":"10.0.0.1","RelayForAddrs":[{"Type":"forwarding","State":"established","PeerAddr":"10.0.0.2","LocalIndex":1,"RemoteIndex":2,"RelayedThrough":null}]}]}`, marshal())
|
||||
|
||||
// And an index mismatch names it.
|
||||
hm.Relays[7] = hi
|
||||
delete(hm.Relays, 1)
|
||||
assert.Contains(t, marshal(), `"Error":"hostmap LocalIndex '7' does not match RelayState LocalIndex"`)
|
||||
}
|
||||
|
||||
// tunnelFixture is an Interface with our own certificate loaded, one peer behind an
|
||||
// established tunnel and one still handshaking, which has no certificate yet.
|
||||
func tunnelFixture(t *testing.T) *Interface {
|
||||
t.Helper()
|
||||
|
||||
l := test.NewLogger()
|
||||
me := netip.MustParseAddr("10.0.0.1")
|
||||
peer := netip.MustParsePrefix("10.0.0.2/24")
|
||||
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
peerCert, _, _, _ := cert_test.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey, "peer", time.Time{}, time.Time{},
|
||||
[]netip.Prefix{peer}, nil, []string{"web", "db"})
|
||||
|
||||
hm := newHostMap(l)
|
||||
hm.Hosts[peer.Addr()] = &HostInfo{
|
||||
vpnAddrs: []netip.Addr{peer.Addr()},
|
||||
ConnectionState: &ConnectionState{peerCert: &cert.CachedCertificate{Certificate: peerCert}},
|
||||
}
|
||||
hm.Hosts[netip.MustParseAddr("10.0.0.3")] = &HostInfo{
|
||||
vpnAddrs: []netip.Addr{netip.MustParseAddr("10.0.0.3")},
|
||||
ConnectionState: &ConnectionState{},
|
||||
}
|
||||
|
||||
return &Interface{pki: newTestPKI(t, "me", []netip.Addr{me}), hostMap: hm}
|
||||
}
|
||||
|
||||
// TestPrintCertOfATunnelWithoutACertificate: a tunnel still handshaking, or one being
|
||||
// torn down, has no certificate, and print-cert refuses rather than panicking.
|
||||
func TestPrintCertOfATunnelWithoutACertificate(t *testing.T) {
|
||||
f := tunnelFixture(t)
|
||||
|
||||
r, err := runPrintCert(f, &printCertFlags{}, []string{"10.0.0.3"})
|
||||
require.NoError(t, err)
|
||||
assert.False(t, r.OK)
|
||||
assert.Equal(t, "Could not find tunnel for vpn addr: 10.0.0.3", r.Reason)
|
||||
|
||||
r, err = runPrintCert(f, &printCertFlags{}, []string{"10.0.0.2"})
|
||||
require.NoError(t, err)
|
||||
assert.True(t, r.OK, "a tunnel with a certificate is printed")
|
||||
}
|
||||
+72
-33
@@ -5,6 +5,7 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"maps"
|
||||
"math"
|
||||
"os"
|
||||
"os/signal"
|
||||
@@ -25,9 +26,17 @@ type C struct {
|
||||
files []string
|
||||
Settings map[string]any
|
||||
oldSettings map[string]any
|
||||
callbacks []func(*C)
|
||||
callbacks []func(*C, *Reload)
|
||||
l *slog.Logger
|
||||
reloadLock sync.Mutex
|
||||
|
||||
// Set by the first reload that needs a restart and never cleared. Guarded by reloadLock
|
||||
needsRestart bool
|
||||
|
||||
// callbackLock guards callbacks. Registration is not confined to startup: CatchHUP is
|
||||
// running from inside Main, and anything wired up after Main returns registers while
|
||||
// a HUP could already be reloading, so append and iteration have to be serialized.
|
||||
callbackLock sync.Mutex
|
||||
}
|
||||
|
||||
func NewC(l *slog.Logger) *C {
|
||||
@@ -71,16 +80,45 @@ func (c *C) LoadString(raw string) error {
|
||||
// RegisterReloadCallback stores a function to be called when a config reload is triggered. The functions registered
|
||||
// here should decide if they need to make a change to the current process before making the change. HasChanged can be
|
||||
// used to help decide if a change is necessary.
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while
|
||||
func (c *C) RegisterReloadCallback(f func(*C)) {
|
||||
// These functions should return quickly or spawn their own go routine if they will take a while.
|
||||
// Use r to report anything that failed or needs a restart to apply.
|
||||
func (c *C) RegisterReloadCallback(f func(c *C, r *Reload)) {
|
||||
c.callbackLock.Lock()
|
||||
defer c.callbackLock.Unlock()
|
||||
c.callbacks = append(c.callbacks, f)
|
||||
}
|
||||
|
||||
// reloadCallbacks returns a snapshot of the registered callbacks. Reloads iterate the
|
||||
// snapshot rather than the live slice, so a registration from another goroutine cannot
|
||||
// race the loop; a callback registered while a reload is in progress runs from the next
|
||||
// reload on. callbackLock is not held during the calls themselves, so a callback that
|
||||
// registers another callback does not deadlock.
|
||||
func (c *C) reloadCallbacks() []func(*C, *Reload) {
|
||||
c.callbackLock.Lock()
|
||||
defer c.callbackLock.Unlock()
|
||||
return append(make([]func(*C, *Reload), 0, len(c.callbacks)), c.callbacks...)
|
||||
}
|
||||
|
||||
// InitialLoad returns true if this is the first load of the config, and ReloadConfig has not been called yet.
|
||||
func (c *C) InitialLoad() bool {
|
||||
return c.oldSettings == nil
|
||||
}
|
||||
|
||||
// Render returns keys and their values as yaml, for a subsystem to remember what it applied. Empty means they couldn't
|
||||
// be rendered and should never match.
|
||||
func (c *C) Render(keys ...string) string {
|
||||
m := make(map[string]any, len(keys))
|
||||
for _, k := range keys {
|
||||
m[k] = c.Get(k)
|
||||
}
|
||||
b, err := yaml.Marshal(m)
|
||||
if err != nil {
|
||||
c.l.Debug("Failed to render config", "keys", keys, "error", err)
|
||||
return ""
|
||||
}
|
||||
return string(b)
|
||||
}
|
||||
|
||||
// HasChanged checks if the underlying structure of the provided key has changed after a config reload. The value of
|
||||
// k in both the old and new settings will be serialized, the result of the string comparison is returned.
|
||||
// If k is an empty string the entire config is tested.
|
||||
@@ -143,54 +181,55 @@ func (c *C) CatchHUP(ctx context.Context) {
|
||||
return
|
||||
case <-ch:
|
||||
c.l.Info("Caught HUP, reloading config")
|
||||
c.ReloadConfig()
|
||||
c.ReloadConfig().Log(c.l)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
func (c *C) ReloadConfig() {
|
||||
// ReloadConfig reloads the config from the path provided to Load and runs every registered callback. A config that
|
||||
// fails to load is logged here, like any other failure, and the result carries the error for the summary.
|
||||
func (c *C) ReloadConfig() ReloadResult {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
for k, v := range c.Settings {
|
||||
c.oldSettings[k] = v
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.Load(c.path); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "config_path", c.path, "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
}
|
||||
|
||||
err := c.Load(c.path)
|
||||
if err != nil {
|
||||
c.l.Error("Error occurred while reloading config",
|
||||
"config_path", c.path,
|
||||
"error", err,
|
||||
)
|
||||
return
|
||||
}
|
||||
|
||||
for _, v := range c.callbacks {
|
||||
v(c)
|
||||
}
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
func (c *C) ReloadConfigString(raw string) error {
|
||||
// ReloadConfigString is ReloadConfig for a config held in memory rather than on disk.
|
||||
func (c *C) ReloadConfigString(raw string) ReloadResult {
|
||||
c.reloadLock.Lock()
|
||||
defer c.reloadLock.Unlock()
|
||||
|
||||
c.oldSettings = make(map[string]any)
|
||||
for k, v := range c.Settings {
|
||||
c.oldSettings[k] = v
|
||||
maps.Copy(c.oldSettings, c.Settings)
|
||||
|
||||
if err := c.LoadString(raw); err != nil {
|
||||
c.l.Error("Error occurred while reloading config", "error", err)
|
||||
return ReloadResult{Err: err, RestartRequired: c.needsRestart}
|
||||
}
|
||||
|
||||
err := c.LoadString(raw)
|
||||
if err != nil {
|
||||
return err
|
||||
return c.runCallbacks()
|
||||
}
|
||||
|
||||
func (c *C) runCallbacks() ReloadResult {
|
||||
r := &Reload{c: c}
|
||||
for _, v := range c.reloadCallbacks() {
|
||||
v(c, r)
|
||||
}
|
||||
|
||||
for _, v := range c.callbacks {
|
||||
v(c)
|
||||
if r.restart {
|
||||
c.needsRestart = true
|
||||
}
|
||||
|
||||
return nil
|
||||
return ReloadResult{Failed: r.failed, RestartRequired: c.needsRestart, RestartKeys: r.keys}
|
||||
}
|
||||
|
||||
// GetString will get the string for k or return the default d if not found or invalid
|
||||
@@ -216,7 +255,7 @@ func (c *C) GetStringSlice(k string, d []string) []string {
|
||||
}
|
||||
|
||||
v := make([]string, len(rv))
|
||||
for i := 0; i < len(v); i++ {
|
||||
for i := range v {
|
||||
v[i] = fmt.Sprintf("%v", rv[i])
|
||||
}
|
||||
|
||||
@@ -310,8 +349,8 @@ func (c *C) IsSet(k string) bool {
|
||||
}
|
||||
|
||||
func (c *C) get(k string, v any) any {
|
||||
parts := strings.Split(k, ".")
|
||||
for _, p := range parts {
|
||||
parts := strings.SplitSeq(k, ".")
|
||||
for p := range parts {
|
||||
m, ok := v.(map[string]any)
|
||||
if !ok {
|
||||
return nil
|
||||
@@ -394,7 +433,7 @@ func (c *C) parse() error {
|
||||
var nm map[string]any
|
||||
err = yaml.Unmarshal(b, &nm)
|
||||
if err != nil {
|
||||
return err
|
||||
return fmt.Errorf("%s: %w", path, err)
|
||||
}
|
||||
|
||||
// We need to use WithAppendSlice so that firewall rules in separate
|
||||
|
||||
+41
-2
@@ -3,6 +3,7 @@ package config
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -19,7 +20,7 @@ func TestConfig_Load(t *testing.T) {
|
||||
// invalid yaml
|
||||
c := NewC(l)
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte(" invalid yaml"), 0644)
|
||||
require.EqualError(t, c.Load(dir), "yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
require.EqualError(t, c.Load(dir), filepath.Join(dir, "01.yaml")+": yaml: unmarshal errors:\n line 1: cannot unmarshal !!str `invalid...` into map[string]interface {}")
|
||||
|
||||
// simple multi config merge
|
||||
c = NewC(l)
|
||||
@@ -129,7 +130,7 @@ func TestConfig_ReloadConfig(t *testing.T) {
|
||||
|
||||
os.WriteFile(filepath.Join(dir, "01.yaml"), []byte("outer:\n inner: ho"), 0644)
|
||||
|
||||
c.RegisterReloadCallback(func(c *C) {
|
||||
c.RegisterReloadCallback(func(c *C, _ *Reload) {
|
||||
done <- true
|
||||
})
|
||||
|
||||
@@ -220,3 +221,41 @@ firewall:
|
||||
}
|
||||
assert.Equal(t, expected, m)
|
||||
}
|
||||
|
||||
// TestRegisterReloadCallbackDuringReload: registration is not confined to startup. The
|
||||
// HUP handler runs from inside nebula.Main, and anything wired after Main returns
|
||||
// registers while a reload may already be iterating the callbacks. Under -race this is
|
||||
// the data race on the slice; without it, it checks a callback registered mid-reload is
|
||||
// picked up by the next one.
|
||||
func TestRegisterReloadCallbackDuringReload(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := NewC(l)
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
|
||||
var wg sync.WaitGroup
|
||||
wg.Add(2)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for i := 0; i < 200; i++ {
|
||||
c.RegisterReloadCallback(func(*C, *Reload) {})
|
||||
}
|
||||
}()
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for i := 0; i < 200; i++ {
|
||||
assert.NoError(t, c.ReloadConfigString("a: 1").Err)
|
||||
}
|
||||
}()
|
||||
wg.Wait()
|
||||
|
||||
// A callback that registers another callback must not deadlock, and the new one
|
||||
// runs from the following reload on.
|
||||
var ran int
|
||||
c.RegisterReloadCallback(func(c *C, _ *Reload) {
|
||||
c.RegisterReloadCallback(func(*C, *Reload) { ran++ })
|
||||
})
|
||||
require.NoError(t, c.ReloadConfigString("a: 1").Err)
|
||||
assert.Equal(t, 0, ran, "registered during this reload, so not run by it")
|
||||
require.NoError(t, c.ReloadConfigString("a: 1").Err)
|
||||
assert.Equal(t, 1, ran, "and run by the next")
|
||||
}
|
||||
@@ -0,0 +1,98 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"slices"
|
||||
)
|
||||
|
||||
// ReloadResult describes how a reload went. Problems are logged where they happen, Log writes a one line summary.
|
||||
type ReloadResult struct {
|
||||
// Err is set when the new config could not be read or parsed, no callbacks ran
|
||||
Err error
|
||||
// Failed is true when a callback could not apply part of the new config
|
||||
Failed bool
|
||||
// RestartRequired is true once any reload has needed a restart, and stays true until the process restarts
|
||||
RestartRequired bool
|
||||
// RestartKeys are the keys this reload changed that only apply on a restart
|
||||
RestartKeys []string
|
||||
}
|
||||
|
||||
// Summary returns a one line summary of the reload and the level to log it at.
|
||||
func (r ReloadResult) Summary() (slog.Level, string) {
|
||||
switch {
|
||||
case r.Err != nil && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"
|
||||
case r.Err != nil:
|
||||
return slog.LevelError, "Config reload failed, the new config did not load"
|
||||
case r.Failed && r.RestartRequired:
|
||||
return slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"
|
||||
case r.Failed:
|
||||
return slog.LevelError, "Config reload completed with errors, review the logs"
|
||||
case r.RestartRequired:
|
||||
return slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"
|
||||
default:
|
||||
return slog.LevelInfo, "Config reload complete"
|
||||
}
|
||||
}
|
||||
|
||||
// String is the summary with Err and RestartKeys included, for output other than the log.
|
||||
func (r ReloadResult) String() string {
|
||||
_, msg := r.Summary()
|
||||
if r.Err != nil {
|
||||
msg = fmt.Sprintf("%s: %v", msg, r.Err)
|
||||
}
|
||||
if len(r.RestartKeys) > 0 {
|
||||
msg = fmt.Sprintf("%s, keys %v", msg, r.RestartKeys)
|
||||
}
|
||||
return msg
|
||||
}
|
||||
|
||||
// Log writes Summary to l.
|
||||
func (r ReloadResult) Log(l *slog.Logger) {
|
||||
level, msg := r.Summary()
|
||||
if len(r.RestartKeys) > 0 {
|
||||
l.Log(context.Background(), level, msg, "keys", r.RestartKeys)
|
||||
return
|
||||
}
|
||||
l.Log(context.Background(), level, msg)
|
||||
}
|
||||
|
||||
// Reload is passed to each reload callback to report how applying the new config went.
|
||||
type Reload struct {
|
||||
c *C
|
||||
failed bool
|
||||
restart bool
|
||||
// Changed keys that only apply on a restart, from every callback
|
||||
keys []string
|
||||
}
|
||||
|
||||
// Failed marks the reload as failed, the caller logs why. Safe to call on a nil Reload, which is what the initial load
|
||||
// passes.
|
||||
func (r *Reload) Failed() {
|
||||
if r != nil {
|
||||
r.failed = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequired marks the reload as needing a restart, the caller logs why. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequired() {
|
||||
if r != nil {
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
|
||||
// RestartRequiredIfChanged marks the reload as needing a restart if any of keys changed, and adds them to RestartKeys.
|
||||
// Use it for keys that are only read at startup. Safe to call on a nil Reload.
|
||||
func (r *Reload) RestartRequiredIfChanged(keys ...string) {
|
||||
if r == nil {
|
||||
return
|
||||
}
|
||||
for _, k := range keys {
|
||||
if r.c.HasChanged(k) && !slices.Contains(r.keys, k) {
|
||||
r.keys = append(r.keys, k)
|
||||
r.restart = true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,108 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"log/slog"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestReloadConfigString(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
fail := false
|
||||
ran := 0
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) {
|
||||
ran++
|
||||
if fail {
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 2"))
|
||||
fail = true
|
||||
assert.Equal(t, ReloadResult{Failed: true}, c.ReloadConfigString("a: 3"))
|
||||
assert.Equal(t, 2, ran)
|
||||
|
||||
// A config that fails to load runs no callbacks and returns the error
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, 2, ran)
|
||||
assert.Equal(t, 3, c.GetInt("a", 0))
|
||||
}
|
||||
|
||||
func TestReloadRestartRequiredLatches(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
// Nothing that needs a restart changed
|
||||
assert.Equal(t, ReloadResult{}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
|
||||
// The restart sticks through a reload with no changes, reverting the key and a config that fails to load. Only the
|
||||
// reload that changed the key lists it
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 2\nb: 1\nc: 1"))
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true, RestartKeys: []string{"a"}}, c.ReloadConfigString("a: 1\nb: 1\nc: 1"))
|
||||
|
||||
res := c.ReloadConfigString("a: [")
|
||||
require.Error(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A key reported by more than one callback is listed once
|
||||
func TestReloadRestartKeysDeduped(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1\nb: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a") })
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequiredIfChanged("a", "b") })
|
||||
|
||||
assert.Equal(t, []string{"a", "b"}, c.ReloadConfigString("a: 2\nb: 2").RestartKeys)
|
||||
}
|
||||
|
||||
// A callback can require a restart without a key changing, a file the config points at may have
|
||||
func TestReloadRestartRequiredWithoutAChange(t *testing.T) {
|
||||
c := NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("a: 1"))
|
||||
c.RegisterReloadCallback(func(c *C, r *Reload) { r.RestartRequired() })
|
||||
|
||||
assert.Equal(t, ReloadResult{RestartRequired: true}, c.ReloadConfigString("a: 1"))
|
||||
}
|
||||
|
||||
func TestReloadResultSummary(t *testing.T) {
|
||||
cases := []struct {
|
||||
res ReloadResult
|
||||
level slog.Level
|
||||
msg string
|
||||
}{
|
||||
{ReloadResult{}, slog.LevelInfo, "Config reload complete"},
|
||||
{ReloadResult{RestartRequired: true}, slog.LevelWarn, "Config reload was completed but requires a restart to fully apply"},
|
||||
{ReloadResult{Failed: true}, slog.LevelError, "Config reload completed with errors, review the logs"},
|
||||
{ReloadResult{Failed: true, RestartRequired: true}, slog.LevelError, "Config reload completed with errors and requires a restart to fully apply, review the logs"},
|
||||
{ReloadResult{Err: errors.New("bad yaml")}, slog.LevelError, "Config reload failed, the new config did not load"},
|
||||
{ReloadResult{Err: errors.New("bad yaml"), RestartRequired: true}, slog.LevelError, "Config reload failed, the new config did not load and a restart is still required"},
|
||||
}
|
||||
for _, tc := range cases {
|
||||
level, msg := tc.res.Summary()
|
||||
assert.Equal(t, tc.level, level, tc.msg)
|
||||
assert.Equal(t, tc.msg, msg)
|
||||
}
|
||||
|
||||
res := ReloadResult{RestartRequired: true, RestartKeys: []string{"a", "b"}}
|
||||
assert.Equal(t, "Config reload was completed but requires a restart to fully apply, keys [a b]", res.String())
|
||||
|
||||
// String includes the error
|
||||
assert.Equal(t, "Config reload failed, the new config did not load: bad yaml", ReloadResult{Err: errors.New("bad yaml")}.String())
|
||||
}
|
||||
|
||||
// The initial load passes a nil Reload
|
||||
func TestReloadNilIsSafe(t *testing.T) {
|
||||
var r *Reload
|
||||
r.Failed()
|
||||
r.RestartRequired()
|
||||
r.RestartRequiredIfChanged("a")
|
||||
}
|
||||
+7
-33
@@ -57,7 +57,8 @@ func newConnectionManagerFromConfig(l *slog.Logger, c *config.C, hm *HostMap, p
|
||||
}
|
||||
|
||||
cm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("timers.connection_alive_interval", "timers.pending_deletion_interval")
|
||||
cm.reload(c, false)
|
||||
})
|
||||
|
||||
@@ -174,10 +175,8 @@ func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte
|
||||
|
||||
switch decision {
|
||||
case deleteTunnel:
|
||||
if cm.hostMap.DeleteHostInfo(hostinfo) {
|
||||
// Only clearing the lighthouse cache if this is the last hostinfo for this vpn ip in the hostmap
|
||||
cm.intf.lightHouse.DeleteVpnAddrs(hostinfo.vpnAddrs)
|
||||
}
|
||||
// Local delete only, clearing the lighthouse cache if this was the last hostinfo for the vpn addr
|
||||
cm.intf.closeTunnel(hostinfo)
|
||||
|
||||
case closeTunnel:
|
||||
cm.intf.sendCloseTunnel(hostinfo)
|
||||
@@ -197,27 +196,6 @@ func (cm *connectionManager) doTrafficCheck(localIndex uint32, p, nb, out []byte
|
||||
}
|
||||
|
||||
cm.resetRelayTrafficCheck(hostinfo)
|
||||
cm.maintainLanes(localIndex, decision, hostinfo, now, nb, out)
|
||||
}
|
||||
|
||||
// maintainLanes piggybacks multiport lane probing on the per-tunnel traffic
|
||||
// tick. This tick is the right place for it precisely because lanes are
|
||||
// demand-driven: a tunnel only lands here when it has traffic, which is the
|
||||
// same condition that raises lane demand.
|
||||
//
|
||||
// makeTrafficDecision returns a nil hostinfo on some keep-alive paths, so
|
||||
// re-resolve the index in that case.
|
||||
func (cm *connectionManager) maintainLanes(localIndex uint32, decision trafficDecision, hostinfo *HostInfo, now time.Time, nb, out []byte) {
|
||||
if decision == deleteTunnel || decision == closeTunnel {
|
||||
return
|
||||
}
|
||||
if hostinfo == nil {
|
||||
hostinfo = cm.hostMap.QueryIndex(localIndex)
|
||||
if hostinfo == nil {
|
||||
return
|
||||
}
|
||||
}
|
||||
cm.intf.probeLanes(hostinfo, now, nb, out)
|
||||
}
|
||||
|
||||
func (cm *connectionManager) resetRelayTrafficCheck(hostinfo *HostInfo) {
|
||||
@@ -350,10 +328,7 @@ func (cm *connectionManager) makeTrafficDecision(localIndex uint32, now time.Tim
|
||||
return closeTunnel, hostinfo, nil
|
||||
}
|
||||
|
||||
// The highest counter across the base session and its lanes: the lanes carry
|
||||
// the data, so the base counter alone would sit near zero while a lane runs
|
||||
// its keys past the nonce ceiling.
|
||||
if hostinfo.maxMessageCounter() >= RejectAfterMessages {
|
||||
if hostinfo.ConnectionState != nil && hostinfo.ConnectionState.messageCounter.Load() >= RejectAfterMessages {
|
||||
// Send path can't encrypt a CloseTunnel notify, so just delete locally; the peer recovers via recv_error.
|
||||
hostinfo.logger(cm.l).Error("Dropping tunnel, message counter is exhausted")
|
||||
return deleteTunnel, hostinfo, nil
|
||||
@@ -461,7 +436,6 @@ func (cm *connectionManager) isInactive(hostinfo *HostInfo, now time.Time) (time
|
||||
return 0, false
|
||||
}
|
||||
|
||||
// Lane traffic is this hostinfo's traffic, so lastUsed already covers it.
|
||||
inactiveDuration := now.Sub(hostinfo.lastUsed)
|
||||
if inactiveDuration < cm.getInactivityTimeout() {
|
||||
// It's not considered inactive
|
||||
@@ -485,7 +459,7 @@ func (cm *connectionManager) shouldSwapPrimary(current *HostInfo) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
if current.maxMessageCounter() >= RehandshakeAfterMessages {
|
||||
if current.ConnectionState.messageCounter.Load() >= RehandshakeAfterMessages {
|
||||
// This tunnel is being rolled for counter exhaustion, never swap back onto its spent key.
|
||||
return false
|
||||
}
|
||||
@@ -589,7 +563,7 @@ func (cm *connectionManager) tryRehandshake(hostinfo *HostInfo) {
|
||||
cm.intf.handshakeManager.StartHandshake(hostinfo.vpnAddrs[0], nil)
|
||||
return
|
||||
}
|
||||
if hostinfo.maxMessageCounter() >= RehandshakeAfterMessages {
|
||||
if hostinfo.ConnectionState.messageCounter.Load() >= RehandshakeAfterMessages {
|
||||
cm.l.Info("Re-handshaking with remote",
|
||||
"vpnAddrs", hostinfo.vpnAddrs,
|
||||
"reason", "message counter rehandshake threshold reached",
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/overlay/overlaytest"
|
||||
@@ -21,6 +22,8 @@ func newTestLighthouse() *LightHouse {
|
||||
l: test.NewLogger(),
|
||||
addrMap: map[netip.Addr]*RemoteList{},
|
||||
queryChan: make(chan netip.Addr, 10),
|
||||
// Nothing drains queryChan here, so an 11th query is dropped.
|
||||
queryDropped: metrics.NilCounter{},
|
||||
}
|
||||
lighthouses := []netip.Addr{}
|
||||
staticList := map[netip.Addr]struct{}{}
|
||||
|
||||
+1
-63
@@ -1,12 +1,9 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"crypto/hkdf"
|
||||
"crypto/sha256"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"strconv"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
|
||||
@@ -29,15 +26,12 @@ const (
|
||||
// RehandshakeAfterMessages must stay below RejectAfterMessages so tunnels roll before the hard send stop.
|
||||
const _ = RejectAfterMessages - RehandshakeAfterMessages
|
||||
|
||||
// sessionEpoch hands out a receiver-local ordinal to every tunnel at creation. The RX
|
||||
// sessionEpoch hands out a receiver-local ordinal to every ConnectionState at creation. The RX
|
||||
// staging sort (overlay/batch) orders packets by (epoch, message counter). A re-handshake never
|
||||
// rekeys an existing tunnel; it brings up a new hostinfo and ConnectionState with a counter space
|
||||
// starting near zero, while the old tunnel keeps decrypting until torn down. During that cutover
|
||||
// one flush batch can hold packets from both tunnels, and the epoch keeps the old tunnel's
|
||||
// packets sorted first.
|
||||
//
|
||||
// It is drawn once per tunnel, by the base session: a tunnel's multiport lane sessions copy it
|
||||
// rather than draw their own.
|
||||
var sessionEpoch atomic.Uint64
|
||||
|
||||
type ConnectionState struct {
|
||||
@@ -80,53 +74,6 @@ func newConnectionStateFromResult(r *handshake.Result) (*ConnectionState, error)
|
||||
return ci, nil
|
||||
}
|
||||
|
||||
// newLaneConnectionState derives multiport lane s's session from the base
|
||||
// tunnel's material. Each key is an HKDF expansion of the base tunnel's matching
|
||||
// key, labelled with the lane index, so the pair stays matched with no extra
|
||||
// negotiation: Noise leaves our send key equal to the peer's receive key, and
|
||||
// expanding both with the same label preserves that.
|
||||
//
|
||||
// The lane gets its own counter and replay window starting from zero. No
|
||||
// handshake messages were spent on it, so unlike the base session there is
|
||||
// nothing to seed. The epoch is the tunnel's, not the lane's; see sessionEpoch.
|
||||
func newLaneConnectionState(m *laneMaterial, lane uint8) (*ConnectionState, error) {
|
||||
if lane == 0 {
|
||||
return nil, fmt.Errorf("lane 0 is the base session")
|
||||
}
|
||||
|
||||
eKey, err := deriveLaneKey(m.eKey, lane)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
dKey, err := deriveLaneKey(m.dKey, lane)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return &ConnectionState{
|
||||
myCert: m.myCert,
|
||||
initiator: m.initiator,
|
||||
peerCert: m.peerCert,
|
||||
eKey: noiseutil.NewCipherStateFromKey(eKey, m.cipher),
|
||||
dKey: noiseutil.NewCipherStateFromKey(dKey, m.cipher),
|
||||
window: NewBits(ReplayWindow),
|
||||
epoch: m.epoch,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// deriveLaneKey expands a base tunnel key into the key for one lane.
|
||||
func deriveLaneKey(base [32]byte, lane uint8) ([32]byte, error) {
|
||||
var out [32]byte
|
||||
// The base key is already unique to this tunnel and direction, so the lane
|
||||
// index is the only thing that needs to vary; no salt is required.
|
||||
k, err := hkdf.Key(sha256.New, base[:], nil, laneKeyInfo+" "+strconv.Itoa(int(lane)), len(out))
|
||||
if err != nil {
|
||||
return out, err
|
||||
}
|
||||
copy(out[:], k)
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func (cs *ConnectionState) MarshalJSON() ([]byte, error) {
|
||||
return json.Marshal(m{
|
||||
"certificate": cs.peerCert,
|
||||
@@ -171,15 +118,6 @@ func (cs *ConnectionState) Decrypt(l *slog.Logger, messageCounter uint64, packet
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// noteSeen records a counter that some other session for the same keys already
|
||||
// accepted, so a packet doesn't become replayable just because the session that
|
||||
// decrypted it was thrown away. See laneSet.installSession, its only caller.
|
||||
func (cs *ConnectionState) noteSeen(l *slog.Logger, messageCounter uint64) {
|
||||
cs.decryptLock.Lock()
|
||||
cs.window.Update(l, messageCounter)
|
||||
cs.decryptLock.Unlock()
|
||||
}
|
||||
|
||||
func (cs *ConnectionState) VerifyRelay(l *slog.Logger, messageCounter uint64, packet []byte, nb []byte) error {
|
||||
cs.decryptLock.Lock()
|
||||
result := cs.window.Check(l, messageCounter)
|
||||
|
||||
+120
-3
@@ -2,6 +2,8 @@ package nebula
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"strconv"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -11,6 +13,7 @@ import (
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -58,7 +61,6 @@ func runTestHandshake(t *testing.T) (initR, respR *handshake.Result) {
|
||||
cert.Version2, initCreds, verifier,
|
||||
func() (uint32, error) { return 1000, nil },
|
||||
true, header.HandshakeIXPSK0,
|
||||
nil,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
|
||||
@@ -66,7 +68,6 @@ func runTestHandshake(t *testing.T) (initR, respR *handshake.Result) {
|
||||
cert.Version2, respCreds, verifier,
|
||||
func() (uint32, error) { return 2000, nil },
|
||||
false, header.HandshakeIXPSK0,
|
||||
nil,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
|
||||
@@ -99,7 +100,7 @@ func TestConnectionState_NextMessageCounter(t *testing.T) {
|
||||
assert.Equal(t, RejectAfterMessages, cs.messageCounter.Load())
|
||||
|
||||
// Continued send attempts stay refused and the counter never wraps
|
||||
for i := 0; i < 10; i++ {
|
||||
for range 10 {
|
||||
_, ok = cs.NextMessageCounter()
|
||||
assert.False(t, ok)
|
||||
}
|
||||
@@ -149,6 +150,122 @@ func TestSendNoMetricsCloseTunnelKeepsRebindEpoch(t *testing.T) {
|
||||
assert.True(t, hostinfo.markOut(1), "a CloseTunnel send must not consume the rebind epoch")
|
||||
}
|
||||
|
||||
// capturingConn is a udp.Conn that records every WriteTo.
|
||||
type capturingConn struct {
|
||||
udp.NoopConn
|
||||
writes [][]byte
|
||||
addrs []netip.AddrPort
|
||||
}
|
||||
|
||||
func (c *capturingConn) WriteTo(b []byte, addr netip.AddrPort) error {
|
||||
c.writes = append(c.writes, append([]byte(nil), b...))
|
||||
c.addrs = append(c.addrs, addr)
|
||||
return nil
|
||||
}
|
||||
|
||||
// TestSendNoMetricsViaRelay sends through a relay from the mtu sized buffer the cached packet flush uses. Payloads up
|
||||
// to overlay.MaxMTU go out intact, anything bigger is dropped rather than outgrowing the buffer, which once panicked.
|
||||
func TestSendNoMetricsViaRelay(t *testing.T) {
|
||||
tests := []struct {
|
||||
n int
|
||||
sent bool
|
||||
}{
|
||||
{0, true},
|
||||
{1300, true},
|
||||
{overlay.MaxMTU, true},
|
||||
{overlay.MaxMTU + 1, false}, // too big for the relay's tag
|
||||
{mtu - 47, false}, // too big for the inner tag, this panicked
|
||||
{9000, false}, // a full packet at tun.mtu 9000
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(strconv.Itoa(tt.n), func(t *testing.T) {
|
||||
// One tunnel to the target, carried end to end, and one to the relay that wraps it
|
||||
targetInit, targetResp := runTestHandshake(t)
|
||||
relayInit, relayResp := runTestHandshake(t)
|
||||
ci, err := newConnectionStateFromResult(targetInit)
|
||||
require.NoError(t, err)
|
||||
relayCI, err := newConnectionStateFromResult(relayInit)
|
||||
require.NoError(t, err)
|
||||
|
||||
targetAddr := netip.MustParseAddr("10.0.0.2")
|
||||
relayAddr := netip.MustParseAddr("10.0.0.3")
|
||||
relayRemote := netip.MustParseAddrPort("192.0.2.1:4242")
|
||||
|
||||
relay := &Relay{Type: TerminalType, State: Established, LocalIndex: 5, RemoteIndex: 6, PeerAddr: targetAddr}
|
||||
relayHI := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{relayAddr},
|
||||
ConnectionState: relayCI,
|
||||
relayState: RelayState{
|
||||
relayForByAddr: map[netip.Addr]*Relay{targetAddr: relay},
|
||||
relayForByIdx: map[uint32]*Relay{relay.LocalIndex: relay},
|
||||
},
|
||||
}
|
||||
relayHI.remote.Store(&relayRemote)
|
||||
|
||||
// No remote of its own, so the send has to go via the relay
|
||||
hostinfo := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{targetAddr},
|
||||
ConnectionState: ci,
|
||||
remoteIndexId: 7,
|
||||
relayState: RelayState{
|
||||
relays: []netip.Addr{relayAddr},
|
||||
relayForByAddr: map[netip.Addr]*Relay{},
|
||||
relayForByIdx: map[uint32]*Relay{},
|
||||
},
|
||||
}
|
||||
|
||||
l := test.NewLogger()
|
||||
hm := newHostMap(l)
|
||||
hm.Hosts[relayAddr] = relayHI
|
||||
conn := &capturingConn{}
|
||||
f := &Interface{
|
||||
l: l,
|
||||
hostMap: hm,
|
||||
messageMetrics: &MessageMetrics{txExhausted: metrics.NewCounter()},
|
||||
writers: []udp.Conn{conn},
|
||||
}
|
||||
f.connectionManager = &connectionManager{intf: f, relayUsed: map[uint32]struct{}{}, relayUsedLock: &sync.RWMutex{}}
|
||||
|
||||
payload := make([]byte, tt.n)
|
||||
for i := range payload {
|
||||
payload[i] = byte(i)
|
||||
}
|
||||
counter := ci.messageCounter.Load()
|
||||
f.sendNoMetrics(header.Message, 0, ci, hostinfo, netip.AddrPort{}, payload, make([]byte, 12), make([]byte, mtu), 0)
|
||||
|
||||
if !tt.sent {
|
||||
assert.Empty(t, conn.writes)
|
||||
assert.Equal(t, counter, ci.messageCounter.Load(), "a dropped packet must not spend a counter")
|
||||
return
|
||||
}
|
||||
require.Len(t, conn.writes, 1)
|
||||
assert.Equal(t, relayRemote, conn.addrs[0])
|
||||
pkt := conn.writes[0]
|
||||
|
||||
// The relay authenticates the whole packet under its own header
|
||||
outer := &header.H{}
|
||||
require.NoError(t, outer.Parse(pkt))
|
||||
assert.Equal(t, header.MessageRelay, outer.Subtype)
|
||||
assert.Equal(t, relay.RemoteIndex, outer.RemoteIndex)
|
||||
relayPeer, err := newConnectionStateFromResult(relayResp)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, relayPeer.VerifyRelay(l, outer.MessageCounter, pkt, make([]byte, 12)))
|
||||
|
||||
// Inside it, the target decrypts the end to end packet back to the payload
|
||||
inner := pkt[header.Len : len(pkt)-relayPeer.dKey.Overhead()]
|
||||
h := &header.H{}
|
||||
require.NoError(t, h.Parse(inner))
|
||||
assert.Equal(t, header.Message, h.Type)
|
||||
assert.Equal(t, hostinfo.remoteIndexId, h.RemoteIndex)
|
||||
targetPeer, err := newConnectionStateFromResult(targetResp)
|
||||
require.NoError(t, err)
|
||||
got, err := targetPeer.Decrypt(l, h.MessageCounter, inner, make([]byte, 12))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, payload, got)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewConnectionStateFromResult(t *testing.T) {
|
||||
initR, respR := runTestHandshake(t)
|
||||
|
||||
|
||||
+11
-42
@@ -11,6 +11,7 @@ import (
|
||||
"syscall"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
)
|
||||
@@ -47,6 +48,7 @@ type Control struct {
|
||||
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
commands *commands.Registry
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
sshStart func()
|
||||
@@ -67,16 +69,6 @@ type ControlHostInfo struct {
|
||||
CurrentRemote netip.AddrPort `json:"currentRemote"`
|
||||
CurrentRelaysToMe []netip.Addr `json:"currentRelaysToMe"`
|
||||
CurrentRelaysThroughMe []netip.Addr `json:"currentRelaysThroughMe"`
|
||||
Lanes []ControlLane `json:"lanes,omitempty"`
|
||||
}
|
||||
|
||||
// ControlLane reports one multiport lane of a tunnel. Only lanes we may send on
|
||||
// are listed; receive-only lanes have no state worth showing.
|
||||
type ControlLane struct {
|
||||
Index uint8 `json:"index"`
|
||||
Up bool `json:"up"`
|
||||
Remote netip.AddrPort `json:"remote,omitempty"`
|
||||
MessageCounter uint64 `json:"messageCounter"`
|
||||
}
|
||||
|
||||
// Start actually runs nebula, this is a nonblocking call.
|
||||
@@ -212,15 +204,10 @@ func (c *Control) RebindUDPServer() {
|
||||
return
|
||||
}
|
||||
|
||||
// Every socket needs rebinding, not just the base: with multiport each one is bound to its own lane port, and
|
||||
// even without it the surplus SO_REUSEPORT sockets stay pinned to the interface we came up on otherwise.
|
||||
//
|
||||
// A failure here means we are likely still pinned to the interface we came up on, so the rest of this is
|
||||
// unlikely to help. Say so instead of silently carrying on as if we rebound.
|
||||
for i, w := range c.f.writers {
|
||||
if err := w.Rebind(); err != nil {
|
||||
c.l.Error("Failed to rebind udp socket", "error", err, "writer", i)
|
||||
}
|
||||
if err := c.f.outside.Rebind(); err != nil {
|
||||
c.l.Error("Failed to rebind udp socket", "error", err)
|
||||
}
|
||||
|
||||
// Trigger a lighthouse update, useful for mobile clients that should have an update interval of 0
|
||||
@@ -387,6 +374,13 @@ func (c *Control) CloseAllTunnels(excludeLighthouses bool) (closed int) {
|
||||
return
|
||||
}
|
||||
|
||||
// Commands returns the registry the daemon's surfaces serve from. It is the live
|
||||
// registry, not a copy: a command registered on it is served to every ssh session that
|
||||
// starts afterwards. Clone it to run commands without that reach.
|
||||
func (c *Control) Commands() *commands.Registry {
|
||||
return c.commands
|
||||
}
|
||||
|
||||
func (c *Control) Device() overlay.Device {
|
||||
return c.f.inside
|
||||
}
|
||||
@@ -400,7 +394,6 @@ func copyHostInfo(h *HostInfo, preferredRanges []netip.Prefix) ControlHostInfo {
|
||||
CurrentRelaysToMe: h.relayState.CopyRelayIps(),
|
||||
CurrentRelaysThroughMe: h.relayState.CopyRelayForIps(),
|
||||
CurrentRemote: h.GetRemote(),
|
||||
Lanes: copyLanes(h),
|
||||
}
|
||||
|
||||
for i, a := range h.vpnAddrs {
|
||||
@@ -418,30 +411,6 @@ func copyHostInfo(h *HostInfo, preferredRanges []netip.Prefix) ControlHostInfo {
|
||||
return chi
|
||||
}
|
||||
|
||||
// copyLanes snapshots the sendable multiport lanes of a tunnel, or nil when it
|
||||
// has none. txAddr is the lane's gate as well as its destination, so a nil load
|
||||
// is exactly "this lane is down and its routine is riding the base tunnel".
|
||||
func copyLanes(h *HostInfo) []ControlLane {
|
||||
ls := h.lanes
|
||||
if ls == nil || ls.txLanes < 2 {
|
||||
return nil
|
||||
}
|
||||
|
||||
lanes := make([]ControlLane, 0, ls.txLanes-1)
|
||||
for s := 1; s < ls.txLanes; s++ {
|
||||
l := ControlLane{Index: uint8(s)}
|
||||
if addr := ls.txAddr[s].Load(); addr != nil {
|
||||
l.Up = true
|
||||
l.Remote = *addr
|
||||
}
|
||||
if cs := ls.sessions[s].Load(); cs != nil {
|
||||
l.MessageCounter = cs.messageCounter.Load()
|
||||
}
|
||||
lanes = append(lanes, l)
|
||||
}
|
||||
return lanes
|
||||
}
|
||||
|
||||
func listHostMapHosts(hl controlHostLister) []ControlHostInfo {
|
||||
hosts := make([]ControlHostInfo, 0)
|
||||
pr := hl.GetPreferredRanges()
|
||||
|
||||
@@ -151,9 +151,9 @@ func (c *fakeConn) WriteTo(_ []byte, _ netip.AddrPort) error { return nil }
|
||||
func (c *fakeConn) WriteBatch(bufs [][]byte, _ []netip.AddrPort) (int, error) {
|
||||
return len(bufs), nil
|
||||
}
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
func (c *fakeConn) ReloadConfig(_ *config.C, _ *config.Reload) {}
|
||||
func (c *fakeConn) SupportsMultipleReaders() bool { return true }
|
||||
func (c *fakeConn) Close() error { c.closed = true; return nil }
|
||||
|
||||
type multiqueueDevice struct {
|
||||
*fakeDevice
|
||||
@@ -247,7 +247,7 @@ func TestControl_ConcurrentStopAndStart(t *testing.T) {
|
||||
c, _, _ := newReadyControl(t)
|
||||
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 2; i++ {
|
||||
for range 2 {
|
||||
wg.Go(func() { c.Stop() })
|
||||
}
|
||||
wg.Go(func() { _ = c.Start() })
|
||||
|
||||
+1
-1
@@ -105,7 +105,7 @@ func TestControl_GetHostInfoByVpnIp(t *testing.T) {
|
||||
}
|
||||
|
||||
// Make sure we don't have any unexpected fields
|
||||
assertFields(t, []string{"VpnAddrs", "LocalIndex", "RemoteIndex", "RemoteAddrs", "Cert", "MessageCounter", "CurrentRemote", "CurrentRelaysToMe", "CurrentRelaysThroughMe", "Lanes"}, thi)
|
||||
assertFields(t, []string{"VpnAddrs", "LocalIndex", "RemoteIndex", "RemoteAddrs", "Cert", "MessageCounter", "CurrentRemote", "CurrentRelaysToMe", "CurrentRelaysThroughMe"}, thi)
|
||||
assert.Equal(t, &expectedInfo, thi)
|
||||
test.AssertDeepCopyEqual(t, &expectedInfo, thi)
|
||||
|
||||
|
||||
@@ -1,526 +0,0 @@
|
||||
# Multiport lanes
|
||||
|
||||
Status: experimental. Linux only. Off unless `multiport.ports` is set.
|
||||
|
||||
## The problem
|
||||
|
||||
A nebula tunnel is one UDP 4-tuple. Everything between the two hosts that makes
|
||||
a decision per flow makes it once, for the whole tunnel:
|
||||
|
||||
- **ECMP / LAG** hashes the 4-tuple and picks one path. A tunnel gets one path's
|
||||
worth of bandwidth no matter how many exist.
|
||||
- **NIC RSS** hashes the 4-tuple to one receive queue, so one CPU takes every
|
||||
interrupt for the tunnel and receive is capped by a single core.
|
||||
- **Per-flow policers and shapers** see one flow and rate-limit it as one.
|
||||
- **Cloud per-flow bandwidth caps** are the hard version of that. AWS EC2 meters
|
||||
each 5-tuple separately and caps a single flow well below what the instance can
|
||||
do in aggregate -- on the order of 5 Gbps for a single flow within a VPC (more
|
||||
inside a cluster placement group, or with ENA Express; check the current EC2
|
||||
network-limits docs for exact numbers) on instances whose aggregate allowance
|
||||
is many times that. Other providers do the same. Nothing about the path is
|
||||
saturated when this fires, and no amount of retuning changes it: the hypervisor
|
||||
is metering *the flow*, so the only way to get more is to be more than one
|
||||
flow.
|
||||
|
||||
Running `routines: N` does not help. Those N sockets share one port through
|
||||
`SO_REUSEPORT`, and the group is keyed on the exact `(addr, port)` pair, so the
|
||||
kernel's reuseport hash is the *only* thing spreading the work -- every hash
|
||||
outside this host still sees a single flow.
|
||||
|
||||
Multiport gives one tunnel several underlay 4-tuples, so all of those per-flow
|
||||
decisions get made several times, independently. A tunnel with N lanes is N
|
||||
flows to everything counting flows: N ECMP hashes, N receive queues, N of the
|
||||
cloud provider's per-flow buckets.
|
||||
|
||||
There is a second bottleneck, and it is inside this host rather than out on the
|
||||
network: in FIPS 140 mode the AES-GCM implementation refuses to seal twice under
|
||||
the same nonce, which forces every encrypt on a session to be serialized behind
|
||||
one mutex. `routines: N` does not help there either. Because each lane is a
|
||||
separate session, multiport splits that mutex as well -- see
|
||||
[The FIPS 140 encrypt lock](#the-fips-140-encrypt-lock).
|
||||
|
||||
## What a lane is
|
||||
|
||||
A lane is **not** a second tunnel. It is an extra session on the same
|
||||
`HostInfo`.
|
||||
|
||||
Noise leaves both sides with `A.eKey == B.dKey` and `A.dKey == B.eKey`. Expanding
|
||||
both keys through HKDF-SHA256 with the same per-lane label preserves that
|
||||
equality, so both sides land on a matched key pair having exchanged nothing:
|
||||
|
||||
```
|
||||
lane s send key = HKDF(base eKey, info: "nebula multiport lane v1 <s>")
|
||||
lane s recv key = HKDF(base dKey, info: "nebula multiport lane v1 <s>")
|
||||
```
|
||||
|
||||
(`connection_state.go:deriveLaneKey`. The base key is already unique per tunnel
|
||||
and per direction, so the lane index is the only thing that needs to vary and no
|
||||
salt is required.)
|
||||
|
||||
Consequences worth stating plainly:
|
||||
|
||||
- A lane costs **no handshake** and has no half-established state.
|
||||
- A lane dies exactly when its base tunnel dies. There is no independent
|
||||
lifetime to reason about, no second teardown path.
|
||||
- Each lane is a **full** session: its own message counter, its own replay
|
||||
window, its own cipher states, its own encrypt lock. Flows on different paths
|
||||
never contend for shared replay state, which is what makes reordering across
|
||||
lanes harmless, and under FIPS 140 the separate encrypt locks are what let one
|
||||
tunnel encrypt on more than one core.
|
||||
- Rolling the base tunnel replaces every lane key, because lanes are derived
|
||||
from it. `maxMessageCounter` therefore reports the max across the base and all
|
||||
lane counters, so rehandshake and exhaustion thresholds see the real data
|
||||
volume rather than the base session's small share.
|
||||
|
||||
Which lane a packet belongs to travels in the nebula header, in the low 8 bits
|
||||
of what used to be `Reserved` (see `header/header.go`). It is part of the AEAD's
|
||||
associated data, so a lane index cannot be altered in flight -- a packet
|
||||
decrypts on the lane it claims or not at all.
|
||||
|
||||
**Lane 0 is the base tunnel itself**: `HostInfo.ConnectionState`, the base port,
|
||||
the peer's real remote address. It is not a special case reserved for control
|
||||
traffic; it carries its share of data flows like any other lane.
|
||||
|
||||
## Socket layout
|
||||
|
||||
`routines` is **per port**. Each of `multiport.ports` consecutive ports gets its
|
||||
own full group of `routines` sockets sharing it through `SO_REUSEPORT`, so total
|
||||
sockets = total routines = total tun queues = `routines * multiport.ports`.
|
||||
|
||||
```
|
||||
routines: 2, multiport.ports: 3, listen.port: 4242
|
||||
|
||||
port 4242 port 4243 port 4244
|
||||
(lane 0/base) (lane 1) (lane 2)
|
||||
+-------------+ +-------------+ +-------------+
|
||||
writers[] | 0 | 1 | | 2 | 3 | | 4 | 5 |
|
||||
+-------------+ +-------------+ +-------------+
|
||||
routine 0 1 0 1 0 1
|
||||
```
|
||||
|
||||
Sockets are laid out **port-major**: `writers[s*routinesPerPort + r]` is the
|
||||
r'th socket on port `listen.port+s`. So:
|
||||
|
||||
```go
|
||||
laneSock(q, s) = s*routinesPerPort + q%routinesPerPort // inside.go
|
||||
egressSock(q) = laneSock(q, 0) // base traffic
|
||||
```
|
||||
|
||||
Two properties fall out of this, and the rest of the design depends on both:
|
||||
|
||||
1. **Every routine owns exactly one socket.** `listenIn` blocks in `recvmmsg`
|
||||
and everything downstream of it -- the batcher, the conntrack cache, the
|
||||
`txQueue` -- is single-owner and lock-free. More sockets than routines would
|
||||
need epoll or locks.
|
||||
2. **Every routine has a sibling socket at the same group position on every
|
||||
port.** So socket selection is a pure function of `(queue, lane)` with no
|
||||
borrowing and no shared state, and each port's traffic spreads across its
|
||||
whole group rather than funnelling into one socket.
|
||||
|
||||
The second property is why `routines` is per port rather than a total to divide
|
||||
up. With one socket per port, each port would be served by a single core -- worst
|
||||
of all the base port, which carries every handshake, every lighthouse and punch
|
||||
packet, every peer without multiport, and every tunnel whose lanes are down.
|
||||
|
||||
## Negotiation
|
||||
|
||||
Multiport capability rides the existing handshake payload as two new protobuf
|
||||
fields (`handshake/payload.go`): `InitiatorLanes` field 9 and `ResponderLanes`
|
||||
field 10, each a `LaneDetails{PortCount, BasePort, TxLanes}`.
|
||||
|
||||
- `PortCount` / `BasePort` -- the contiguous port range the sender bound, so the
|
||||
peer knows where to aim its lanes.
|
||||
- `TxLanes` -- how many lanes the sender may send on, so the peer knows how many
|
||||
lane sessions it must be prepared to receive on.
|
||||
|
||||
Both are `nil` when multiport is off, which keeps the encoded payload
|
||||
**byte-identical** to a vanilla one. A peer that has never heard of lanes skips
|
||||
unknown fields as protobuf requires, and gets a plain tunnel.
|
||||
|
||||
From the result, `newLaneSet` computes:
|
||||
|
||||
```go
|
||||
sessions = min(max(myLanes, peerTxLanes), 256) // we must be able to RECEIVE all of theirs
|
||||
txLanes = min(myLanes, peerPortCount, sessions) // we may only SEND on ports they bound
|
||||
```
|
||||
|
||||
Sizing RX by the peer's count and TX by our own is what lets asymmetric hosts
|
||||
work: a 4-port laptop talking to a 32-port server sends on 4 lanes and receives
|
||||
on 32.
|
||||
|
||||
### Port pairing
|
||||
|
||||
Lane `s` targets `peerBasePort + ((s + portOffset) % peerPortCount)`.
|
||||
|
||||
`portOffset` is a per-pair FNV hash of the sorted vpn-address pair. Without it,
|
||||
every small peer would aim its few lanes at a big peer's first few ports and
|
||||
concentrate that peer's receive work on a couple of sockets.
|
||||
|
||||
The rotation has to cancel, though, or the two directions of one flow would take
|
||||
unrelated 4-tuples and neither side's traffic would arrive through the conntrack
|
||||
or NAT entry the other's probe opened. So both sides hash the *same* sorted pair
|
||||
and the higher-addressed side **negates** the result. When the port counts match,
|
||||
the two rotations cancel exactly: our lane `s`'s 4-tuple is the reverse of the
|
||||
peer's lane `s`. `laneBias` does the matching rotation on the flow hash for the
|
||||
same reason.
|
||||
|
||||
That pairing only exists when our lane indices map one-to-one onto the peer's
|
||||
ports, which is exactly the `txLanes == peerPortCount` test `newLaneSet` applies
|
||||
before setting `laneBias`. If we send on 4 lanes and the peer bound 8 ports, four
|
||||
of its ports have no lane of ours pointing at them, and no choice of rotation can
|
||||
make our lane `s` and its lane `s` be each other's reverse. So in that case
|
||||
`laneBias` stays 0 and each side hashes the flow to a lane on its own. The flow
|
||||
still works and is still spread; the two directions simply take two unrelated
|
||||
4-tuples instead of one 4-tuple and its exact reverse, and each direction depends
|
||||
on its own lane's probe having opened its own conntrack or NAT entry.
|
||||
|
||||
## Bringing a lane up
|
||||
|
||||
Receiving on a lane needs no permission: the keys are derivable the moment the
|
||||
base handshake completes. **Sending** on one needs proof the new 4-tuple actually
|
||||
works, because nothing else would notice a middlebox quietly dropping it. So:
|
||||
|
||||
```
|
||||
lane down --probe (Test/LaneProbe on lane s, from port base+s to peer's lane port)-->
|
||||
<--ack (Test/LaneProbeAck, on the BASE tunnel)--
|
||||
lane up
|
||||
```
|
||||
|
||||
- The probe is encrypted with **the lane's own session**, so an ack proves the
|
||||
whole lane end to end: our source port reached the peer, its reply reached us,
|
||||
and the keys we derived match the ones it derived.
|
||||
- The ack rides the **base tunnel** on purpose. A probe proves the peer's lane
|
||||
works in *its* send direction; answering on our own lane `s` would make the
|
||||
result depend on a second path that can be broken independently.
|
||||
- The ack echoes the header's lane, not the payload's, so a peer cannot get us to
|
||||
vouch for a lane it did not probe.
|
||||
- A generation byte in the probe is echoed in the ack, so a late ack cannot
|
||||
promote a lane on the strength of a superseded probe.
|
||||
|
||||
`txAddr[s]` is a single `atomic.Pointer[netip.AddrPort]` that is *both* the TX
|
||||
gate and the destination, so a data-plane routine that loads non-nil has
|
||||
everything it needs in one atomic read and there is no window where one is set
|
||||
and the other is not.
|
||||
|
||||
Probing is driven by the connection manager's per-tunnel traffic tick
|
||||
(`maintainLanes` -> `probeLanes`), which only fires for a tunnel with traffic --
|
||||
the same condition that makes a lane worth having. Timers:
|
||||
|
||||
| timer | value |
|
||||
|---|---|
|
||||
| probe timeout | 2s (shorter than the 5s tick on purpose) |
|
||||
| keepalive | 30s |
|
||||
| retry backoff | 5s, doubling to 60s |
|
||||
| max failure count | 8 |
|
||||
|
||||
Traffic on a lane is not evidence the lane works -- that is the whole reason
|
||||
lanes need probing -- so a lane that silently breaks is only caught by the
|
||||
keepalive.
|
||||
|
||||
Every lane starts out **demanded**, so the first traffic tick probes all of them
|
||||
at once. This matters more than it looks: see "flow pinning" below. A lane that
|
||||
is down also raises demand from the TX path each time a flow wants it, so a
|
||||
lane that keeps failing is retried only while something still wants it, and an
|
||||
idle tunnel costs nothing.
|
||||
|
||||
A lane aims **only** at its own port. There is no fallback to the peer's base
|
||||
port when the lane port doesn't answer: a lane sharing the base port's
|
||||
destination would gain only a source port of its own while costing the peer the
|
||||
receive spread that is the entire point. A lane that can't reach its port stays
|
||||
down and its flows ride the base tunnel.
|
||||
|
||||
## Flow -> lane -> routine: keeping a flow consistent
|
||||
|
||||
This is the part that took the most iterations to get right, so it's worth
|
||||
spelling out why it is shaped the way it is.
|
||||
|
||||
### The kernel's tun queue feedback loop
|
||||
|
||||
On Linux, a multiqueue tun device does not simply hash a flow to a queue. It
|
||||
also *learns*: `tun_flow_update` records "this flow was last seen on queue *q*"
|
||||
from the packets **we write in**, and `tun_automq_select_queue` prefers what it
|
||||
learned over the hash for as long as the flow stays busy.
|
||||
|
||||
We write an inbound packet to the tun queue with the same index as the UDP
|
||||
routine that received it (`batchers[rxc.q]`). So the queue a flow's *outbound*
|
||||
packets arrive on is decided by the socket its *inbound* packets landed on, at
|
||||
the far end, one RTT ago.
|
||||
|
||||
### Why the lane comes from the flow, not the routine
|
||||
|
||||
The obvious design -- routine `q` sends on lane `q` -- deadlocks against that
|
||||
feedback loop:
|
||||
|
||||
1. A tunnel comes up. All lanes are down, so all traffic goes out lane 0.
|
||||
2. The peer receives it all on socket 0 and writes it all to tun queue 0.
|
||||
3. Both kernels now believe every flow belongs on queue 0.
|
||||
4. Every flow is read by routine 0, so every flow picks lane 0.
|
||||
5. Go to 2. The tunnel is pinned to lane 0 for as long as its flows stay busy.
|
||||
|
||||
So the lane comes from **the flow's own 5-tuple**, not from the routine index:
|
||||
|
||||
```go
|
||||
s = (laneFlowHash(fwPacket) + laneBias) % txLanes // lanes.go:txLaneForFlow
|
||||
```
|
||||
|
||||
This makes lane spread completely independent of how the kernel steers tun
|
||||
queues. It also gives the properties you actually want from a flow's point of
|
||||
view:
|
||||
|
||||
- **A flow stays on one lane for its life.** The hash is a pure function of the
|
||||
5-tuple, so there is no per-packet lane hopping and therefore no reordering
|
||||
introduced by multiport.
|
||||
- **One lane's replay window sees one stable set of flows.**
|
||||
- **Both directions of a flow pick partner lanes.** `laneFlowHash` orders the two
|
||||
endpoints before hashing, so it returns the same value from either end, and
|
||||
`laneBias` lines the two sides' choices up. The two directions are exact
|
||||
reverse 4-tuples, which is what NAT and stateful firewalls need.
|
||||
|
||||
`newLaneSet` demanding every lane up front is the other half of this. Lanes have
|
||||
to be up *before* the flows are: a flow that starts while the lanes are still
|
||||
down gets its queue pinned by step 2 above and can stay there for its whole
|
||||
life. Eager demand costs one probe per lane on any tunnel that has traffic, and
|
||||
nothing at all on one that doesn't.
|
||||
|
||||
### The full path
|
||||
|
||||
```
|
||||
outbound inbound (at the peer)
|
||||
-------- ---------------------
|
||||
inside flow
|
||||
| kernel tun hash, or the queue it
|
||||
| learned from our last write
|
||||
v
|
||||
tun queue q -> routine q
|
||||
|
|
||||
| s = laneFlowHash(flow) % txLanes lane s arrives on port base+s
|
||||
v |
|
||||
lane s session | SO_REUSEPORT hash of the
|
||||
| | 4-tuple picks one socket
|
||||
| writers[laneSock(q,s)] v
|
||||
v routine q' (owner of that socket)
|
||||
port base+s -------------------------> |
|
||||
v
|
||||
tun queue q' (teaches the kernel
|
||||
flow -> q')
|
||||
```
|
||||
|
||||
Note that RX is entirely socket-agnostic: the lane comes from the header byte,
|
||||
not from the port the packet arrived on, and roaming is skipped for `lane != 0`
|
||||
(a lane's source address is a per-lane 4-tuple, not the tunnel's remote -- letting
|
||||
it roam the hostinfo would point every non-lane packet at a lane port). So a
|
||||
lane packet may legitimately arrive on any socket, which is what makes the
|
||||
reuseport spread within a port safe.
|
||||
|
||||
### Ordering and locking
|
||||
|
||||
Several routines can write to one socket, since the routines whose lane
|
||||
arithmetic lands on the same index share it. Linux's `batchWriter` serializes
|
||||
`sendmmsg` with a mutex. Per-flow wire order still holds regardless: a flow is
|
||||
hashed onto one lane and read by one routine, so nothing else is writing that
|
||||
flow.
|
||||
|
||||
Each routine holds one `txQueue` with one shared arena (~1.16 MB) and builds a
|
||||
`SendBatch` per lane lazily, on the first packet that picks it, so a routine that
|
||||
never sends on a lane never pays for one.
|
||||
|
||||
### The FIPS 140 encrypt lock
|
||||
|
||||
In FIPS 140 mode -- a `boringcrypto` build, or `GODEBUG=fips140=on` -- nebula
|
||||
uses `noiseutil.CipherAESGCMFIPS140` instead of the plain AES-GCM cipher. That
|
||||
cipher is the TLS 1.3 GCM (`GCMWithXORCounterNonce`), which **panics** if it is
|
||||
asked to seal with a counter that is not strictly greater than the last one. That
|
||||
check is the point: it is the nonce-reuse protection FIPS 140 requires, and
|
||||
`noiseutil`'s startup self-test refuses to run if the check has gone missing.
|
||||
|
||||
The check means encrypts on one session cannot overlap, so
|
||||
`noiseutil.EncryptLockNeeded` is true and every send path takes that session's
|
||||
`ConnectionState.writeLock`:
|
||||
|
||||
```go
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Lock()
|
||||
}
|
||||
c := ci.messageCounter.Add(1)
|
||||
out = header.EncodeLane(scratch, ..., c, lane)
|
||||
out, encErr := ci.eKey.EncryptDanger(out, out, seg, c, nb)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Unlock()
|
||||
}
|
||||
```
|
||||
|
||||
The lock has to cover the seal and not just the counter increment. Reserving
|
||||
counters atomically is easy; the requirement is that the seals *arrive at the
|
||||
AEAD in counter order*, and only holding the lock across both gives that.
|
||||
|
||||
So under FIPS 140 the encrypt cost of a tunnel is pinned to one core. `routines:
|
||||
N` gives N readers, but every one of them that has a packet for the same peer
|
||||
queues on the same mutex, and with TSO/USO the lock is taken and released once
|
||||
per segment -- up to ~45 times for a single superpacket
|
||||
(`sendInsideEncrypt`). Receive is not affected: `extractFIPSAEAD` deliberately
|
||||
pulls the inner FIPS AEAD out of the `crypto/tls` wrapper because that inner
|
||||
implementation is safe to `Open` concurrently, and `decryptLock` is only ever
|
||||
held around the replay-window check and update.
|
||||
|
||||
Lanes split the lock because a lane is a separate `ConnectionState`: its own
|
||||
`writeLock`, its own message counter, its own nonce sequence. A peer we send to
|
||||
on `txLanes` lanes has `txLanes` independent encrypt locks, so encrypt for that
|
||||
one tunnel can run on that many cores at once.
|
||||
|
||||
The flow hash is what makes this work rather than merely legal. A flow maps to
|
||||
one lane, so all of a flow's packets take one lock in counter order -- exactly
|
||||
what the FIPS AEAD demands -- while different flows to the same peer land on
|
||||
different locks. Contention is divided, not eliminated: any routine may send on
|
||||
any lane, so two routines whose flows hash to the same lane still serialize
|
||||
against each other.
|
||||
|
||||
Two caveats. This is only a FIPS 140 benefit -- in a normal build
|
||||
`EncryptLockNeeded` is false, encrypt is lock-free, and lanes buy path and queue
|
||||
spread only. And it is not unilateral: `txLanes` is bounded by the peer's port
|
||||
count, so a peer that binds one port leaves us back on one encrypt lock however
|
||||
many ports we bound ourselves.
|
||||
|
||||
## Falling back to the old behavior
|
||||
|
||||
Multiport degrades rather than failing, at every level. This is deliberate:
|
||||
managed deployments can't be hard-errored on config they don't control.
|
||||
|
||||
### Whole-node: back to one port
|
||||
|
||||
Any of these turns multiport off, logs why, and leaves a node that binds one
|
||||
port with `routines` `SO_REUSEPORT` sockets -- bit-for-bit the pre-multiport
|
||||
configuration:
|
||||
|
||||
| condition | log |
|
||||
|---|---|
|
||||
| `multiport.enabled: false` | - |
|
||||
| `multiport.ports` unset, 0, or 1 | `multiport disabled: set multiport.ports > 1 ...` |
|
||||
| `listen.port + ports - 1 > 65535` | `multiport disabled: would bind ports beyond 65535` |
|
||||
| platform can't run multiple UDP readers | `multiport disabled: this platform does not support multiple udp readers` |
|
||||
| that capability couldn't be probed | `multiport disabled: could not probe udp reader support` |
|
||||
|
||||
`multiport.ports` is also clamped to 256 (the lane header limit) and to
|
||||
`maxRoutines / routines`, with a warning, rather than being rejected.
|
||||
|
||||
With a dynamic `listen.port: 0`, the first socket binds dynamically and the
|
||||
range is claimed above it; a partially-occupied range re-rolls with a fresh
|
||||
dynamic port up to 6 times.
|
||||
|
||||
`laneSock` collapses to the identity when multiport is off, so the send path is
|
||||
unchanged: a routine writes to its own socket and no lane batches are built at
|
||||
all.
|
||||
|
||||
### Per-tunnel: back to a single session
|
||||
|
||||
`newLaneSet` returns `nil`, and the tunnel is an ordinary one, when:
|
||||
|
||||
- the peer advertised no port count (vanilla peer, or multiport off there), or
|
||||
- `sessions < 2`, i.e. neither side offers a lane.
|
||||
|
||||
`txLanes` can also land at 1 -- we bound ports but the peer bound only one -- in
|
||||
which case the set exists for RX but we never send on a lane.
|
||||
|
||||
### Per-packet: back to the base tunnel
|
||||
|
||||
`txLaneForFlow` returns a nil session and the packet rides the base tunnel,
|
||||
decided per packet with no state to unwind:
|
||||
|
||||
- the flow hashed onto lane 0 (its fair share of flows);
|
||||
- the lane it hashed onto has never come up;
|
||||
- the lane was **demoted** -- a probe or keepalive went unanswered. Fallback is
|
||||
immediate, on the very next packet, and the miss re-raises demand so the lane
|
||||
is re-probed;
|
||||
- the tunnel is **relayed** -- lanes are direct-only, so `probeLanes` drops them
|
||||
all when there is no direct path and rebuilds when one returns;
|
||||
- the peer **roamed** -- a new NAT mapping has no derivable relationship to the
|
||||
old lane ports, so every lane is torn down and re-probed from a clean backoff.
|
||||
Standing demand is deliberately kept across a reset, so the lanes that were
|
||||
actually carrying data come back first.
|
||||
|
||||
### Always on the base tunnel
|
||||
|
||||
Handshakes, lighthouse traffic, punching, relay carriers, close packets, rejects,
|
||||
and lane probe *acks* all use the base session and a socket on the base port
|
||||
(`egressSock`). Base traffic must keep the base source port or a vanilla peer
|
||||
would see the tunnel's address move and roam-thrash.
|
||||
|
||||
`recv_error` is the one deliberate exception: it replies from the socket the
|
||||
offending packet arrived on, because a lane peer's spoof guard compares our
|
||||
source address against that lane's remote and would discard a reply from the
|
||||
base port.
|
||||
|
||||
### Wire compatibility
|
||||
|
||||
- A vanilla sender emits lane 0 in a field it thinks is reserved, and lane 0 is
|
||||
the base tunnel, so it reads correctly with no version check.
|
||||
- We always send the upper 8 reserved bits as zero.
|
||||
- A lane index above what this tunnel has (a stale lane from a rolled tunnel, or
|
||||
a peer sending above what it advertised) is dropped **silently** -- a
|
||||
`recv_error` would tear down a perfectly good base tunnel on the strength of
|
||||
one odd packet.
|
||||
- Lane ciphertext wrapped in a relay carrier is refused before the session
|
||||
lookup, so a junk relay packet can't make us derive a session.
|
||||
|
||||
## Security notes
|
||||
|
||||
- The lane index is in the AEAD's associated data, so it is authenticated, not
|
||||
just carried.
|
||||
- On RX, a lane session derived for an unrecognized lane is **not installed**
|
||||
until the packet actually decrypts. Anyone who can spoof this tunnel's local
|
||||
index can name any lane; installing on sight would let them make us hold a
|
||||
replay window and two cipher states per lane, per tunnel, for lanes they never
|
||||
send on.
|
||||
- Two routines racing on a lane's first packet each derive a session. The loser's
|
||||
is dropped, and its replay-window entry for the packet it just accepted is
|
||||
handed to the winner (`installSession`) -- the keys are identical, so it is the
|
||||
same window in every respect that matters.
|
||||
|
||||
## Configuration
|
||||
|
||||
```yaml
|
||||
routines: 8 # PER PORT under multiport; total workers = routines * ports
|
||||
multiport:
|
||||
enabled: true # default true, but inert without ports
|
||||
ports: 4 # consecutive ports from listen.port; must be > 1, no default
|
||||
lanes: 0 # 0 = one per bound port; lower to send on a subset
|
||||
```
|
||||
|
||||
`multiport.ports` has no default on purpose: under these semantics a default
|
||||
would silently multiply the worker count. Nothing here is reloadable.
|
||||
|
||||
Both sides need a port range, and the range
|
||||
`[listen.port, listen.port+ports-1]` must be open in both directions. Opening
|
||||
only the base port is the common failure and gives you exactly one working lane
|
||||
-- the one whose rotation happens to land on the base port.
|
||||
|
||||
## Observability
|
||||
|
||||
```
|
||||
nebula-ssh> print-tunnel -vpn-addr <peer>
|
||||
```
|
||||
|
||||
`lanes[]` gives per-lane `up`, `remote` and `messageCounter`, which is the fastest
|
||||
way to tell "no lanes negotiated" (key absent) from "lanes up but traffic on one"
|
||||
(counters).
|
||||
|
||||
Metrics, registered only when multiport is running so they don't sit at zero on
|
||||
nodes without it:
|
||||
|
||||
- `multiport.lanes.up` -- lanes currently carrying traffic
|
||||
- `multiport.lanes.tunnels` -- tunnels with any lanes
|
||||
|
||||
Both are counted by walking the hostmap rather than kept at promotion/demotion,
|
||||
because a counter would drift upward forever: a tunnel torn down with its lanes
|
||||
up never demotes them.
|
||||
|
||||
Logs worth grepping: `multiport enabled` and `multiport routines` at startup, the
|
||||
`lanes` attr on handshake completion (`tx`, `sessions`, `peerBasePort`,
|
||||
`peerPorts`, `portOffset`), and `Multiport lane up` / `Multiport lane demoted`,
|
||||
both of which name the `udpAddr` involved.
|
||||
|
||||
## Known gaps
|
||||
|
||||
- No `readOutsidePackets`-level test for the RX lane drop paths.
|
||||
- No multiport coverage in the e2e suite.
|
||||
- `routines * ports > 256` fails at startup from the kernel's tun queue limit
|
||||
rather than being clamped with a warning.
|
||||
+2
-1
@@ -69,9 +69,10 @@ func newDnsServerFromConfig(ctx context.Context, l *slog.Logger, pki *PKI, hostM
|
||||
ds.mux = dns.NewServeMux()
|
||||
ds.mux.HandleFunc(".", ds.handleDnsRequest)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
if err := ds.reload(c, false); err != nil {
|
||||
ds.l.Error("Failed to reload DNS responder from config", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
|
||||
@@ -0,0 +1,169 @@
|
||||
//go:build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/commands"
|
||||
"github.com/slackhq/nebula/sshd"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// volatile lists everything in command output that legitimately differs between runs.
|
||||
// Each run mints fresh certificates and indexes, so these are replaced with a marker
|
||||
// before comparison. Keep the list short: anything added here is something the golden
|
||||
// stops guarding.
|
||||
var volatile = []struct {
|
||||
re *regexp.Regexp
|
||||
with string
|
||||
}{
|
||||
{regexp.MustCompile(`[0-9a-f]{40,}`), "<hex>"}, // fingerprints, keys, signatures
|
||||
{regexp.MustCompile(`\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:\d{2})`), "<time>"}, // RFC 3339
|
||||
{regexp.MustCompile(`\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}(?:\.\d+)? [+-]\d{4} \w+`), "<time>"}, // time.Time.String()
|
||||
{regexp.MustCompile(`(?s)(-----BEGIN [A-Z ]+-----\n).*?(\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // print-cert -raw
|
||||
{regexp.MustCompile(`(-----BEGIN [A-Z ]+-----\\n).*?(\\n-----END [A-Z ]+-----)`), "${1}<pem>${2}"}, // the same, inside a JSON string
|
||||
{regexp.MustCompile(`"(localIndex|remoteIndex|messageCounter)":\d+`), `"$1":<n>`},
|
||||
{regexp.MustCompile(`(?m)^(\s*"?(?:LocalIndex|RemoteIndex|localIndex|remoteIndex|messageCounter)"?:?\s*)\d+`), "${1}<n>"}, // and the -pretty form
|
||||
}
|
||||
|
||||
func normalise(s string) string {
|
||||
for _, v := range volatile {
|
||||
s = v.re.ReplaceAllString(s, v.with)
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// outputCase is one command line to run through the ssh dispatch path.
|
||||
type outputCase struct {
|
||||
name string
|
||||
args []string
|
||||
}
|
||||
|
||||
// TestCommandOutput pins the bytes every command produces, in every format, through the
|
||||
// ssh dispatch path. It is the safety net for moving rendering out of the commands: a
|
||||
// change here is a change someone at an ssh prompt would see. Regenerate with:
|
||||
//
|
||||
// go test -tags e2e_testing ./e2e -run TestCommandOutput -update
|
||||
func TestCommandOutput(t *testing.T) {
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(
|
||||
cert.Version1, cert.Curve_CURVE25519,
|
||||
time.Now(), time.Now().Add(10*time.Minute),
|
||||
nil, nil, []string{},
|
||||
)
|
||||
|
||||
control, _, _, _ := newSimpleServer(cert.Version1, ca, caKey, "output-golden", "10.222.0.1/24", nil)
|
||||
control.Start()
|
||||
t.Cleanup(func() { control.Stop() })
|
||||
|
||||
// As an ssh session does: a clone of the daemon's registry with logout added, which
|
||||
// help on the clone lists and describes. There is no session to end here.
|
||||
reg := control.Commands().Clone()
|
||||
reg.Register(sshd.LogoutCommand(func() {}))
|
||||
// Dispatch with ssh's default-format policy, so the no-flag column records what an
|
||||
// operator at an ssh prompt sees.
|
||||
reg.DefaultFormat = sshd.DefaultFormat
|
||||
|
||||
// run dispatches as the ssh exec path does and returns the output and the error, which
|
||||
// over ssh is exit status 1.
|
||||
run := func(args ...string) (string, error) {
|
||||
buf := &bytes.Buffer{}
|
||||
err := reg.DispatchArgs(args, commands.MergedOutput(buf))
|
||||
return buf.String(), err
|
||||
}
|
||||
|
||||
// Seed a pending tunnel so the listing and per-address commands have something to show.
|
||||
seed, err := run("create-tunnel", "10.222.0.9")
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, "Created\n", seed, "seeding a tunnel should succeed before anything else is recorded")
|
||||
|
||||
cases := []outputCase{
|
||||
{"version", nil},
|
||||
{"device-info", nil},
|
||||
{"list-hostmap", nil},
|
||||
{"list-hostmap", []string{"-by-index"}},
|
||||
{"list-pending-hostmap", nil},
|
||||
{"list-pending-hostmap", []string{"-by-index"}},
|
||||
{"list-lighthouse-addrmap", nil},
|
||||
{"print-cert", nil},
|
||||
{"print-cert", []string{"-raw"}},
|
||||
{"print-cert", []string{"10.222.0.9"}},
|
||||
// A flag after the operand is still a flag, on both surfaces.
|
||||
{"print-cert", []string{"10.222.0.9", "-json"}},
|
||||
{"print-cert", []string{"10.222.0.250"}},
|
||||
{"print-cert", []string{"not-an-address"}},
|
||||
{"print-tunnel", nil},
|
||||
{"print-tunnel", []string{"10.222.0.9"}},
|
||||
{"print-tunnel", []string{"10.222.0.250"}},
|
||||
{"print-relays", nil},
|
||||
{"query-lighthouse", nil},
|
||||
{"query-lighthouse", []string{"10.222.0.9"}},
|
||||
{"query-lighthouse", []string{"not-an-address"}},
|
||||
// The test logger cannot change level or format, so these cases record the
|
||||
// refusal each command prints on it, not a successful change.
|
||||
{"log-level", nil},
|
||||
{"log-level", []string{"debug"}},
|
||||
{"log-level", []string{"bogus"}},
|
||||
{"log-level", []string{"info"}},
|
||||
{"log-format", nil},
|
||||
{"log-format", []string{"json"}},
|
||||
{"log-format", []string{"text"}},
|
||||
{"change-remote", nil},
|
||||
{"change-remote", []string{"10.222.0.9"}},
|
||||
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.9"}},
|
||||
{"change-remote", []string{"-address", "10.94.0.10:4242", "10.222.0.250"}},
|
||||
{"create-tunnel", nil},
|
||||
{"create-tunnel", []string{"10.222.0.9"}},
|
||||
// A fresh address, so this exercises the handshake start with a remote attached
|
||||
// rather than the "already handshaking" path above.
|
||||
{"create-tunnel", []string{"-address", "10.94.0.10:4242", "10.222.0.10"}},
|
||||
{"create-tunnel", []string{"not-an-address"}},
|
||||
{"close-tunnel", nil},
|
||||
{"close-tunnel", []string{"10.222.0.250"}},
|
||||
{"close-tunnel", []string{"not-an-address"}},
|
||||
{"help", nil},
|
||||
{"help", []string{"print-cert"}},
|
||||
{"help", []string{"logout"}},
|
||||
{"logout", []string{"-h"}},
|
||||
{"not-a-command", []string{"10.222.0.9"}},
|
||||
// reload is last so that whatever a reload does to the daemon cannot leak into an
|
||||
// earlier case. In this harness it fails: the config was loaded from a string and
|
||||
// has no path to re-read, which is what the recorded result says.
|
||||
{"reload", nil},
|
||||
}
|
||||
|
||||
got := &strings.Builder{}
|
||||
for _, c := range cases {
|
||||
for _, fmtFlags := range [][]string{nil, {"-json"}, {"-pretty"}} {
|
||||
args := append([]string{c.name}, fmtFlags...)
|
||||
args = append(args, c.args...)
|
||||
|
||||
fmt.Fprintf(got, "$ %s\n", strings.Join(args, " "))
|
||||
out, err := run(args...)
|
||||
out = normalise(out)
|
||||
got.WriteString(out)
|
||||
// Output that does not end in a newline is recorded as such, the way diff marks
|
||||
// it, so the golden sees that byte too and the next prompt still starts a line.
|
||||
if out != "" && !strings.HasSuffix(out, "\n") {
|
||||
got.WriteString("\\ No newline at end of output\n")
|
||||
}
|
||||
// A failed command is recorded as the exit status an ssh caller sees, so the
|
||||
// golden pins which outcomes count as failures.
|
||||
if err != nil {
|
||||
got.WriteString("exit status 1\n")
|
||||
}
|
||||
got.WriteString("\n")
|
||||
}
|
||||
}
|
||||
|
||||
test.Golden(t, filepath.Join("testdata", "commands_output.golden"), got.String())
|
||||
}
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
@@ -1514,7 +1513,7 @@ func TestLighthouseUpdateOnReload(t *testing.T) {
|
||||
// Reload the config. The lighthouse.hosts change triggers TriggerUpdate,
|
||||
// which wakes the update worker. It calls SendUpdate, initiating a
|
||||
// handshake to the new lighthouse and caching the HostUpdateNotification.
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)))
|
||||
require.NoError(t, myConfig.ReloadConfigString(string(newCfg)).Err)
|
||||
|
||||
// Route until the lighthouse receives the HostUpdateNotification.
|
||||
// This covers: handshake stage 1, stage 2, then the cached update.
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package router
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package router
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
|
||||
Vendored
+1110
File diff suppressed because it is too large.
Load diff
+2
-3
@@ -1,5 +1,4 @@
|
||||
//go:build e2e_testing
|
||||
// +build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
@@ -130,7 +129,7 @@ func TestCertUpgrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v2-only config")
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
@@ -223,7 +222,7 @@ func TestCertDowngrade(t *testing.T) {
|
||||
}
|
||||
|
||||
r.Logf("reload new v1-only config")
|
||||
err = myC.ReloadConfigString(string(cb))
|
||||
err = myC.ReloadConfigString(string(cb)).Err
|
||||
assert.NoError(t, err)
|
||||
r.Log("yay, spin until their sees it")
|
||||
waitStart := time.Now()
|
||||
|
||||
+49
-64
@@ -8,6 +8,7 @@ pki:
|
||||
cert: /etc/nebula/host.crt
|
||||
key: /etc/nebula/host.key
|
||||
# blocklist is a list of certificate fingerprints that we will refuse to talk to
|
||||
# Entries are the hex fingerprints shown by `nebula-cert print`, an invalid entry fails startup and reload.
|
||||
#blocklist:
|
||||
# - c99d4e650533b92061b09918e838a5a0a6aaee21eed1d12fd937682865936c72
|
||||
# disconnect_invalid is a toggle to force a client to be disconnected if the certificate is expired or invalid.
|
||||
@@ -43,7 +44,7 @@ static_host_map:
|
||||
|
||||
lighthouse:
|
||||
# am_lighthouse is used to enable lighthouse functionality for a node. This should ONLY be true on nodes
|
||||
# you have configured to be lighthouses in your network
|
||||
# you have configured to be lighthouses in your network. Not reloadable.
|
||||
am_lighthouse: false
|
||||
# serve_dns optionally starts a dns listener that responds to various queries and can even be
|
||||
# delegated to for resolution
|
||||
@@ -126,8 +127,9 @@ lighthouse:
|
||||
# Port Nebula will be listening on. The default here is 4242. For a lighthouse node, the port should be defined,
|
||||
# however using port 0 will dynamically assign a port and is recommended for roaming nodes.
|
||||
listen:
|
||||
# To listen on only ipv4, use "0.0.0.0"
|
||||
# To listen on only ipv4, use "0.0.0.0". Not reloadable.
|
||||
host: "::"
|
||||
# Not reloadable.
|
||||
port: 4242
|
||||
# Sets the max number of packets to pull from the kernel for each syscall (under systems that support recvmmsg)
|
||||
# default is 64, does not support reload
|
||||
@@ -135,12 +137,13 @@ listen:
|
||||
# superpacket, so the receive scratch is batch * 64KiB per listening socket (~4MiB per routine at the
|
||||
# default of 64). Lower this to trade peak per-syscall throughput for memory on constrained hosts.
|
||||
#batch: 64
|
||||
# Linux only. Reloadable, but removing a value leaves the socket at the old size until Nebula restarts.
|
||||
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||
# Default is net.core.rmem_default and net.core.wmem_default (/proc/sys/net/core/rmem_default and /proc/sys/net/core/rmem_default)
|
||||
# Maximum is limited by memory in the system, SO_RCVBUFFORCE and SO_SNDBUFFORCE is used to avoid having to raise the system wide
|
||||
# max, net.core.rmem_max and net.core.wmem_max
|
||||
#read_buffer: 10485760
|
||||
#write_buffer: 10485760
|
||||
read_buffer: 3412512
|
||||
write_buffer: 3412512
|
||||
|
||||
# On Windows only
|
||||
# When true, Nebula installs a WFP (Windows Filtering Platform) PERMIT filter scoped to UDP at the listener port.
|
||||
@@ -179,54 +182,9 @@ listen:
|
||||
# Currently, this defaults to 1 which means we have 1 tun queue reader and 1
|
||||
# UDP queue reader. Setting this above one will set IFF_MULTI_QUEUE on the tun
|
||||
# device and SO_REUSEPORT on the UDP socket to allow multiple queues.
|
||||
# With multiport enabled this is the number of routines *per port*, so the total
|
||||
# is routines * multiport.ports.
|
||||
# This option is only supported on Linux.
|
||||
# This option is only supported on Linux. Not reloadable.
|
||||
#routines: 1
|
||||
|
||||
# EXPERIMENTAL: multiport lanes give each pair of hosts multiple underlay UDP
|
||||
# flows so overlay traffic is no longer bottlenecked by a single 5-tuple
|
||||
# (one ECMP path, one NIC RSS queue, one per-flow policer). Instead of every
|
||||
# socket sharing listen.port, multiport.ports consecutive ports are bound and
|
||||
# each gets its own group of `routines` sockets sharing it via SO_REUSEPORT, so
|
||||
# no port (the base port above all, which carries every handshake and every
|
||||
# vanilla peer) depends on a single core. One extra tunnel ("lane") per port is
|
||||
# negotiated with capable peers: lane i handshakes from local port listen.port+i
|
||||
# to the peer's advertised base+((i + pair_offset) mod peer_ports), where
|
||||
# pair_offset is a per-pair hash that spreads many small peers across a big
|
||||
# peer's whole port range.
|
||||
# Each lane is a full Noise session with its own
|
||||
# keys, nonce counter and replay window, so flows taking different paths
|
||||
# never fight over shared replay state.
|
||||
#
|
||||
# Peers negotiate lanes in the handshake; vanilla peers get a single normal
|
||||
# tunnel. All control traffic (handshakes, lighthouse, punching, relays) and
|
||||
# the data fallback stay on the base tunnel/port. Lanes are built lazily: a
|
||||
# lane is only established once a routine actually has traffic for that peer
|
||||
# and no lane to carry it, so a peer you exchange a trickle with costs one
|
||||
# tunnel regardless of how many routines are configured. Established lanes
|
||||
# are kept alive with their own keepalives, and traffic falls back to the base
|
||||
# tunnel while a lane is down or not yet up.
|
||||
#
|
||||
# Requirements: multiport.ports > 1, Linux, and the port range
|
||||
# [listen.port, listen.port+multiport.ports-1] reachable through firewalls on
|
||||
# both sides. A lane whose port is unreachable stays down and its traffic rides
|
||||
# the base tunnel. With listen.port 0 the base port is dynamic and the next
|
||||
# ports-1 ports above it are claimed. Degrades to a single port when the
|
||||
# requirements don't hold. Not reloadable.
|
||||
#multiport:
|
||||
#enabled: true
|
||||
# How many consecutive UDP ports to bind, starting at listen.port. Must be
|
||||
# greater than 1 for multiport to do anything; there is no default, since
|
||||
# each port costs a full set of `routines` threads and sockets. Capped at 256
|
||||
# (the lane header limit). 4-8 is plenty to escape a single ECMP path.
|
||||
#ports: 0
|
||||
# How many lanes to run, counting the base tunnel as lane 0. 0 (default)
|
||||
# means one per bound port. Lowering this sends on a subset of the range,
|
||||
# which bounds how many extra tunnels each peer pair maintains (useful on a
|
||||
# big server with many peers); the ports are bound and read either way.
|
||||
#lanes: 0
|
||||
|
||||
punchy:
|
||||
# Continues to punch inbound/outbound at a regular interval to avoid expiration of firewall nat mappings
|
||||
# This setting is reloadable.
|
||||
@@ -248,6 +206,7 @@ punchy:
|
||||
|
||||
# Cipher allows you to choose between the available ciphers for your network. Options are chachapoly or aes
|
||||
# IMPORTANT: this value must be identical on ALL NODES/LIGHTHOUSES. We do not/will not support use of different ciphers simultaneously!
|
||||
# Not reloadable.
|
||||
#cipher: aes
|
||||
|
||||
# Preferred ranges is used to define a hint about the local network ranges, which speeds up discovering the fastest
|
||||
@@ -274,12 +233,26 @@ punchy:
|
||||
# Trusted SSH CA public keys. These are the public keys of the CAs that are allowed to sign SSH keys for access.
|
||||
#trusted_cas:
|
||||
#- "ssh public key string"
|
||||
# sandbox_dir restricts file paths for profiling commands (start-cpu-profile, save-heap-profile,
|
||||
# save-mutex-profile) to the specified directory. Relative paths will be resolved within this directory,
|
||||
# and absolute paths outside of it will be rejected. Default is $TMP/nebula-debug.
|
||||
# The directory is NOT automatically created.
|
||||
# Overriding this to "" is the same as "/" and will allow overwriting any path on the host.
|
||||
#sandbox_dir: /var/tmp/nebula-debug
|
||||
|
||||
# Local APIs allow accessing running nebula state.
|
||||
#local_api:
|
||||
# There are two types of sockets available: a control socket intended for use on the
|
||||
# local machine, primarily for debugging, and an info socket intended to make
|
||||
# nebula's internal state available to other consumers.
|
||||
#
|
||||
# The control socket is made available by default, and can be accessed via
|
||||
# `nebula ctl <command>`. It defaults to /var/run/nebula/ctl.sock on Linux, macOS and
|
||||
# the BSDs; on Windows it is a named pipe under \\.\pipe\ProtectedPrefix\Administrators.
|
||||
#control:
|
||||
# Set to false to turn the control socket off. Reloadable.
|
||||
#enabled: true
|
||||
# The absolute path where the control socket should live, or a full pipe name on
|
||||
# Windows. The last directory is created if missing, and must be owned by root or by
|
||||
# the user running nebula. It must not be writable by anyone else.
|
||||
#socket: /var/run/nebula/ctl.sock
|
||||
# A group (or account/group/SID on Windows) that should be allowed to access the
|
||||
# socket.
|
||||
#group: nebula
|
||||
|
||||
# EXPERIMENTAL: relay support for networks that can't establish direct connections.
|
||||
relay:
|
||||
@@ -298,18 +271,25 @@ relay:
|
||||
# Configure the private interface. Note: addr is baked into the nebula certificate
|
||||
tun:
|
||||
# When tun is disabled, a lighthouse can be started without a local tun interface (and therefore without root)
|
||||
# Not reloadable.
|
||||
disabled: false
|
||||
# Name of the device. If not set, a default will be chosen by the OS.
|
||||
# For macOS: if set, must be in the form `utun[0-9]+`.
|
||||
# For NetBSD: Required to be set, must be in the form `tun[0-9]+`
|
||||
# For OpenBSD and NetBSD: if set, must be in the form `tun[0-9]+`, otherwise the first free one is used.
|
||||
# Not reloadable.
|
||||
dev: nebula1
|
||||
# Toggles forwarding of local broadcast packets, the address of which depends on the ip/mask encoded in pki.cert
|
||||
# Not reloadable.
|
||||
drop_local_broadcast: false
|
||||
# Toggles forwarding of multicast packets
|
||||
# Toggles forwarding of multicast packets. Not reloadable.
|
||||
drop_multicast: false
|
||||
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 500
|
||||
tx_queue: 500
|
||||
# Sets the transmit queue length, if you notice lots of transmit drops on the tun it may help to raise this number. Default is 5000
|
||||
# Not reloadable.
|
||||
tx_queue: 5000
|
||||
# Default MTU for every packet, safe setting is (and the default) 1300 for internet based traffic
|
||||
# Anything above 8937, here or on a route below, is capped to 8937 with a warning
|
||||
# Reloadable on Linux only. Where the tun is handed to nebula by a host app (iOS, Android, macOS network extensions)
|
||||
# the host app owns the MTU.
|
||||
mtu: 1300
|
||||
|
||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||
@@ -371,6 +351,9 @@ tun:
|
||||
# `mtu`: will default to tun mtu if this option is not specified
|
||||
# `metric`: will default to 0 if this option is not specified
|
||||
# `install`: will default to true, controls whether this route is installed in the systems routing table.
|
||||
# On macOS, a route whose destination another interface already routes, like the local network, is installed once
|
||||
# that route is removed. One deleted by hand stays deleted until nebula reloads or restarts, or until another
|
||||
# interface routes its destination and lets it go.
|
||||
# This setting is reloadable.
|
||||
unsafe_routes:
|
||||
#- route: 172.16.1.0/24
|
||||
@@ -402,7 +385,7 @@ tun:
|
||||
#use_system_route_table: false
|
||||
# Buffer size for reading routes updates. 0 means default system buffer size. (/proc/sys/net/core/rmem_default).
|
||||
# If using massive routes updates, for example BGP, you may need to increase this value to avoid packet loss.
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max
|
||||
# SO_RCVBUFFORCE is used to avoid having to raise the system wide max. Not reloadable.
|
||||
#use_system_route_table_buffer_size: 0
|
||||
|
||||
# Configure logging level
|
||||
@@ -452,14 +435,16 @@ logging:
|
||||
# Handshakes are sent to all known addresses at each interval with a linear backoff,
|
||||
# Wait try_interval after the 1st attempt, 2 * try_interval after the 2nd, etc, until the handshake is older than timeout
|
||||
# A 100ms interval with the default 10 retries will give a handshake 5.5 seconds to resolve before timing out
|
||||
# Not reloadable.
|
||||
#try_interval: 100ms
|
||||
#retries: 20
|
||||
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses
|
||||
#query_buffer: 64
|
||||
# query_buffer is the size of the buffer channel for querying lighthouses, drops are recorded in the lighthouse.query.dropped metric.
|
||||
# Not reloadable.
|
||||
#query_buffer: 1024
|
||||
|
||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||
# after receiving the response for lighthouse queries
|
||||
# after receiving the response for lighthouse queries. Not reloadable.
|
||||
#trigger_buffer: 64
|
||||
|
||||
# Tunnel manager settings
|
||||
|
||||
+21
-3
@@ -66,6 +66,9 @@ type Firewall struct {
|
||||
rules string
|
||||
rulesVersion uint16
|
||||
|
||||
// source is the rendered firewall config this firewall was built from, the cert networks are kept above
|
||||
source string
|
||||
|
||||
defaultLocalCIDRAny bool
|
||||
incomingMetrics firewallMetrics
|
||||
outgoingMetrics firewallMetrics
|
||||
@@ -203,11 +206,25 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
panic("No certificate available to reconfigure the firewall")
|
||||
}
|
||||
|
||||
tcpTimeout := c.GetDuration("firewall.conntrack.tcp_timeout", time.Minute*12)
|
||||
udpTimeout := c.GetDuration("firewall.conntrack.udp_timeout", time.Minute*3)
|
||||
defaultTimeout := c.GetDuration("firewall.conntrack.default_timeout", time.Minute*10)
|
||||
|
||||
if tcpTimeout <= 0 {
|
||||
return nil, fmt.Errorf("firewall.conntrack.tcp_timeout must be greater than 0, got: %s", tcpTimeout)
|
||||
}
|
||||
if udpTimeout <= 0 {
|
||||
return nil, fmt.Errorf("firewall.conntrack.udp_timeout must be greater than 0, got: %s", udpTimeout)
|
||||
}
|
||||
if defaultTimeout <= 0 {
|
||||
return nil, fmt.Errorf("firewall.conntrack.default_timeout must be greater than 0, got: %s", defaultTimeout)
|
||||
}
|
||||
|
||||
fw := NewFirewall(
|
||||
l,
|
||||
c.GetDuration("firewall.conntrack.tcp_timeout", time.Minute*12),
|
||||
c.GetDuration("firewall.conntrack.udp_timeout", time.Minute*3),
|
||||
c.GetDuration("firewall.conntrack.default_timeout", time.Minute*10),
|
||||
tcpTimeout,
|
||||
udpTimeout,
|
||||
defaultTimeout,
|
||||
certificate,
|
||||
//TODO: max_connections
|
||||
)
|
||||
@@ -246,6 +263,7 @@ func NewFirewallFromConfig(l *slog.Logger, cs *CertState, c *config.C) (*Firewal
|
||||
return nil, err
|
||||
}
|
||||
|
||||
fw.source = c.Render("firewall")
|
||||
return fw, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ func newFixedTicker(t *testing.T, l *slog.Logger, cacheLen int) *ConntrackCacheT
|
||||
l: l,
|
||||
cache: make(ConntrackCache, cacheLen),
|
||||
}
|
||||
for i := 0; i < cacheLen; i++ {
|
||||
for i := range cacheLen {
|
||||
c.cache[Packet{LocalPort: uint16(i) + 1}] = struct{}{}
|
||||
}
|
||||
c.cacheTick.Store(1) // cacheV starts at 0, so Get() takes the reset path
|
||||
|
||||
@@ -58,6 +58,31 @@ func TestNewFirewall(t *testing.T) {
|
||||
assert.Equal(t, 3602, conntrack.TimerWheel.wheelLen)
|
||||
}
|
||||
|
||||
func TestNewFirewall_ZeroOrNegativeTimeout(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := &dummyCert{}
|
||||
cs := &CertState{v2Cert: c, initiatingVersion: cert.Version2}
|
||||
|
||||
cases := map[string]string{
|
||||
"tcp_timeout zero": "firewall:\n conntrack:\n tcp_timeout: 0s\n",
|
||||
"tcp_timeout negative": "firewall:\n conntrack:\n tcp_timeout: -5s\n",
|
||||
"udp_timeout zero": "firewall:\n conntrack:\n udp_timeout: 0s\n",
|
||||
"udp_timeout negative": "firewall:\n conntrack:\n udp_timeout: -5s\n",
|
||||
"default_timeout zero": "firewall:\n conntrack:\n default_timeout: 0s\n",
|
||||
"default_timeout negative": "firewall:\n conntrack:\n default_timeout: -5s\n",
|
||||
}
|
||||
|
||||
for name, cfgStr := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(cfgStr))
|
||||
_, err := NewFirewallFromConfig(l, cs, cfg)
|
||||
require.Error(t, err, "expected error for non-positive timeout duration")
|
||||
assert.ErrorContains(t, err, "must be greater than 0")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestFirewall_AddRule(t *testing.T) {
|
||||
ob := &bytes.Buffer{}
|
||||
l := test.NewLoggerWithOutput(ob)
|
||||
|
||||
@@ -1,39 +1,39 @@
|
||||
module github.com/slackhq/nebula
|
||||
|
||||
go 1.26.0
|
||||
go 1.27.2
|
||||
|
||||
require (
|
||||
dario.cat/mergo v1.0.2
|
||||
filippo.io/bigmod v0.1.0
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1
|
||||
github.com/Microsoft/go-winio v0.6.2
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
||||
github.com/armon/go-radix v1.0.0
|
||||
github.com/flynn/noise v1.1.0
|
||||
github.com/gaissmai/bart v0.28.0
|
||||
github.com/gaissmai/bart v0.29.0
|
||||
github.com/gogo/protobuf v1.3.2
|
||||
github.com/google/gopacket v1.1.19
|
||||
github.com/kardianos/service v1.3.0
|
||||
github.com/miekg/dns v1.1.72
|
||||
github.com/miekg/dns v1.1.73
|
||||
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/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 v1.12.0
|
||||
github.com/vishvananda/netlink v1.3.1
|
||||
github.com/stretchr/testify v1.12.1
|
||||
go.uber.org/goleak v1.3.0
|
||||
go.yaml.in/yaml/v3 v3.0.5
|
||||
golang.org/x/crypto v0.54.0
|
||||
golang.org/x/net v0.57.0
|
||||
golang.org/x/sync v0.22.0
|
||||
golang.org/x/sys v0.47.0
|
||||
golang.org/x/term v0.45.0
|
||||
golang.org/x/crypto v0.57.0
|
||||
golang.org/x/net v0.59.0
|
||||
golang.org/x/sync v0.23.0
|
||||
golang.org/x/sys v0.48.0
|
||||
golang.org/x/term v0.46.0
|
||||
golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2
|
||||
golang.zx2c4.com/wireguard v0.0.0-20230325221338-052af4a8072b
|
||||
golang.zx2c4.com/wireguard/windows v1.0.1
|
||||
google.golang.org/protobuf v1.36.11
|
||||
google.golang.org/protobuf v1.36.12
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980
|
||||
)
|
||||
|
||||
require (
|
||||
@@ -45,7 +45,6 @@ require (
|
||||
github.com/prometheus/common v0.70.1 // indirect
|
||||
github.com/prometheus/procfs v0.21.1 // indirect
|
||||
github.com/vishvananda/netns v0.0.5 // 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
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc // indirect
|
||||
golang.org/x/time v0.15.0 // indirect
|
||||
)
|
||||
@@ -3,6 +3,10 @@ dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
|
||||
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
|
||||
filippo.io/bigmod v0.1.0 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
|
||||
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1 h1:Md2PsUE1Xuy1Zxs/Bm6356n1kt5bq2HspXlPJ6pEspg=
|
||||
github.com/DefinedNet/netlink v1.3.2-dn.1/go.mod h1:o4YSn8Jw7zoDcYXDmV77TRd4eS5sSLuE+vu2zAN67C8=
|
||||
github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
|
||||
github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
|
||||
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
|
||||
@@ -10,8 +14,6 @@ github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRF
|
||||
github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
|
||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
|
||||
github.com/armon/go-radix v1.0.0 h1:F4z6KzEeeQIMeLFa97iZU6vupzoecKdU5TX24SNppXI=
|
||||
github.com/armon/go-radix v1.0.0/go.mod h1:ufUuZ+zHj4x4TnLV4JWEpy2hxWSpsRywHrMgIH9cCH8=
|
||||
github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
|
||||
github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
|
||||
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
|
||||
@@ -23,8 +25,8 @@ github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
|
||||
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
github.com/flynn/noise v1.1.0 h1:KjPQoQCEFdZDiP03phOvGi11+SVVhBG2wOWAorLsstg=
|
||||
github.com/flynn/noise v1.1.0/go.mod h1:xbMo+0i6+IGbYdJhF31t2eR1BIU0CYc12+BNAKwUTag=
|
||||
github.com/gaissmai/bart v0.28.0 h1:89yZLo8NmyqD0RYgJ3QO9HhqqGGw+oWhf90cZm69Lko=
|
||||
github.com/gaissmai/bart v0.28.0/go.mod h1:GREWQfTLRWz/c5FTOsIw+KkscuFkIV5t8Rp7Nd1Td5c=
|
||||
github.com/gaissmai/bart v0.29.0 h1:wO6HGE8g9YE0Wm0bCpYxwRzfQ4+fbJKOhL64e5ACGCI=
|
||||
github.com/gaissmai/bart v0.29.0/go.mod h1:GREWQfTLRWz/c5FTOsIw+KkscuFkIV5t8Rp7Nd1Td5c=
|
||||
github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
|
||||
github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
|
||||
github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
|
||||
@@ -81,8 +83,8 @@ github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
|
||||
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
|
||||
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
|
||||
github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
|
||||
github.com/miekg/dns v1.1.72 h1:vhmr+TF2A3tuoGNkLDFK9zi36F2LS+hKTRW0Uf8kbzI=
|
||||
github.com/miekg/dns v1.1.72/go.mod h1:+EuEPhdHOsfk6Wk5TT2CzssZdqkmFhf8r+aVyDEToIs=
|
||||
github.com/miekg/dns v1.1.73 h1:uhT8nJxmTrPJYClxVxTCX+CVn6qnzSiybRk72Z6DgrE=
|
||||
github.com/miekg/dns v1.1.73/go.mod h1:RW2Obtfd5NZHvOFe3zYG0W8koWOQtAzyHaLo8vASBuQ=
|
||||
github.com/miekg/pkcs11 v1.1.2 h1:/VxmeAX5qU6Q3EwafypogwWbYryHFmF2RpkJmw3m4MQ=
|
||||
github.com/miekg/pkcs11 v1.1.2/go.mod h1:XsNlhZGX73bx86s2hdc/FuaLm2CPZJemRLMA+WTFxgs=
|
||||
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
|
||||
@@ -136,10 +138,8 @@ github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXf
|
||||
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
|
||||
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
|
||||
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
||||
github.com/stretchr/testify v1.12.0 h1:K6Mr6jO9JICuend/5xzTM03ydSV3vdNRYAdPSukj8uI=
|
||||
github.com/stretchr/testify v1.12.0/go.mod h1:bOYBZb5qJ00vPzWfIqBUZPaxK8jWiXc6d3ErP4Ca9Gw=
|
||||
github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW6bV0=
|
||||
github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
|
||||
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
||||
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
||||
github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
|
||||
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
||||
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
||||
@@ -155,14 +155,14 @@ golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACk
|
||||
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
|
||||
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
|
||||
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/crypto v0.57.0 h1:3ZVCjf8Ggz7zneR/EHRVx68Ctf+2pmIMP2UFhh9cC6M=
|
||||
golang.org/x/crypto v0.57.0/go.mod h1:Fdz0i5U6CoizGwLda9DttjSk6qlZo25zYNtR+ycvuZA=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc h1:TS73t7x3KarrNd5qAipmspBDS1rkMcgVG/fS1aRb4Rc=
|
||||
golang.org/x/exp v0.0.0-20250711185948-6ae5c78190dc/go.mod h1:A+z0yzpGtvnG90cToK5n2tu8UJVP2XUATh+r+sfOOOc=
|
||||
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=
|
||||
golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
||||
golang.org/x/mod v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
|
||||
golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
|
||||
golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
@@ -173,8 +173,8 @@ golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLL
|
||||
golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
|
||||
golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
|
||||
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
|
||||
golang.org/x/net v0.57.0 h1:K5+3DljvIuDG9/Jv9rvyMywYNFCQ9RSUY6OOTTkT+tE=
|
||||
golang.org/x/net v0.57.0/go.mod h1:KpXc8iv+r3XplLAG/f7Jsf9RPszJzdR0f58q9vGOuEU=
|
||||
golang.org/x/net v0.59.0 h1:5zfYln+w5XCxwrnMMJPufRgNoXEaGxl0wo5GqPXyues=
|
||||
golang.org/x/net v0.59.0/go.mod h1:2DA/G1UfVbCpQPeWTmMPGY7Cs2PkBkwu743bVX5PIVg=
|
||||
golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
|
||||
golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
@@ -182,8 +182,8 @@ golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJ
|
||||
golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=
|
||||
golang.org/x/sync v0.22.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
|
||||
golang.org/x/sync v0.23.0 h1:KameEIfc1IkluZyXWLn39Wd4tURc6GbCiISGiZm2bQk=
|
||||
golang.org/x/sync v0.23.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0=
|
||||
golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
@@ -197,25 +197,21 @@ golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7w
|
||||
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
|
||||
golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
|
||||
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
||||
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||
golang.org/x/term v0.45.0 h1:NwWyBmoJCbfTHpxrWoZ9C6/VxOf7ic219I8xZZFdrf0=
|
||||
golang.org/x/term v0.45.0/go.mod h1:9aqxs0blBcrm/n0L9QW0aRVD+ktan8ssZromtqJC43w=
|
||||
golang.org/x/term v0.46.0 h1:3+OXuTbaKDgwk8jTi3aSLHRlmWqHEUDUtxnbFigO4YE=
|
||||
golang.org/x/term v0.46.0/go.mod h1:+K02xbkittuwc0Am4abfA3Fc+XRGXkvBXNO88NCXPoc=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
|
||||
golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
|
||||
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
|
||||
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
|
||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
||||
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
|
||||
golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
|
||||
golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
|
||||
golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
|
||||
golang.org/x/tools v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=
|
||||
golang.org/x/tools v0.45.0/go.mod h1:LuUGqqaXcXMEFEruIVJVm5mgDD8vww/z/SR1gQ4uE/0=
|
||||
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
@@ -234,8 +230,8 @@ google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miE
|
||||
google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
|
||||
google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
|
||||
google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
|
||||
google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
|
||||
google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
|
||||
google.golang.org/protobuf v1.36.12 h1:pJOKDDOyeXErUroCihFAd5LQuwXBSpVnKGrj5o/fwxc=
|
||||
google.golang.org/protobuf v1.36.12/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
|
||||
gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
|
||||
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
||||
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
||||
@@ -249,5 +245,5 @@ gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
|
||||
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe h1:fre4i6mv4iBuz5lCMOzHD1rH1ljqHWSICFmZRbbgp3g=
|
||||
gvisor.dev/gvisor v0.0.0-20240423190808-9d7a357edefe/go.mod h1:sxc3Uvk/vHcd3tj7/DHVBoR5wvWT/MmRq2pj7HRJnwU=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980 h1:ribyrTYQ/QYeUIs8x8bVLYwGyepa7RnHLqJzegT5YYk=
|
||||
gvisor.dev/gvisor v0.0.0-20261014193016-04d31b385980/go.mod h1:pK/dapF5Bf3KGW7/kd5CI5IC4lYh9FMFY1qETAIGLXk=
|
||||
+18
-5
@@ -31,6 +31,7 @@ package nebula
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"strconv"
|
||||
@@ -51,17 +52,29 @@ type graphiteConfigExport struct {
|
||||
Percentiles []float64 // Percentiles to export from timers and histograms
|
||||
}
|
||||
|
||||
// graphiteTimeout bounds one submission, the connect and the write together. An export is a few KB, a host that can't
|
||||
// take that in this long isn't going to.
|
||||
const graphiteTimeout = 30 * time.Second
|
||||
|
||||
// graphiteOnce performs a single submission to Graphite, returning a non-nil
|
||||
// error on failed connections.
|
||||
func graphiteOnce(c graphiteConfigExport) error {
|
||||
// error if it could not connect or write all of it within timeout. It gives up
|
||||
// as soon as ctx is done.
|
||||
func graphiteOnce(ctx context.Context, c graphiteConfigExport, timeout time.Duration) error {
|
||||
now := time.Now().Unix()
|
||||
du := float64(c.DurationUnit)
|
||||
flushSeconds := float64(c.FlushInterval) / float64(time.Second)
|
||||
conn, err := net.DialTCP("tcp", nil, c.Addr)
|
||||
deadline := time.Now().Add(timeout)
|
||||
d := net.Dialer{Deadline: deadline}
|
||||
conn, err := d.DialContext(ctx, "tcp", c.Addr.String())
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer conn.Close()
|
||||
if err := conn.SetDeadline(deadline); err != nil {
|
||||
return err
|
||||
}
|
||||
stop := context.AfterFunc(ctx, func() { _ = conn.Close() })
|
||||
defer stop()
|
||||
w := bufio.NewWriter(conn)
|
||||
c.Registry.Each(func(name string, i any) {
|
||||
switch metric := i.(type) {
|
||||
@@ -111,7 +124,7 @@ func graphiteOnce(c graphiteConfigExport) error {
|
||||
fmt.Fprintf(w, "%s.%s.fifteen-minute %.2f %d\n", c.Prefix, name, t.Rate15(), now)
|
||||
fmt.Fprintf(w, "%s.%s.mean-rate %.2f %d\n", c.Prefix, name, t.RateMean(), now)
|
||||
}
|
||||
w.Flush()
|
||||
})
|
||||
return nil
|
||||
// A failed write sticks, so this reports the first one
|
||||
return w.Flush()
|
||||
}
|
||||
@@ -0,0 +1,315 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// graphiteHost accepts connections and hands each one to the test
|
||||
type graphiteHost struct {
|
||||
ln net.Listener
|
||||
conns chan net.Conn
|
||||
|
||||
mu sync.Mutex
|
||||
closed bool
|
||||
open []net.Conn
|
||||
}
|
||||
|
||||
// newGraphiteHost accepts connections for the test. A non-zero window shrinks each connection's receive buffer, so a
|
||||
// sender that is not read from blocks after a little whatever the host's TCP tuning. Only for tests that need a stall,
|
||||
// a small window makes reading very slow on Linux.
|
||||
func newGraphiteHost(t *testing.T, window int) *graphiteHost {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
h := &graphiteHost{ln: ln, conns: make(chan net.Conn, 8)}
|
||||
done := make(chan struct{})
|
||||
t.Cleanup(func() {
|
||||
_ = ln.Close()
|
||||
h.mu.Lock()
|
||||
h.closed = true
|
||||
for _, c := range h.open {
|
||||
_ = c.Close()
|
||||
}
|
||||
h.mu.Unlock()
|
||||
close(done)
|
||||
})
|
||||
go func() {
|
||||
for {
|
||||
c, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
h.mu.Lock()
|
||||
if h.closed {
|
||||
h.mu.Unlock()
|
||||
_ = c.Close()
|
||||
return
|
||||
}
|
||||
h.open = append(h.open, c)
|
||||
h.mu.Unlock()
|
||||
if tc, ok := c.(*net.TCPConn); ok && window > 0 {
|
||||
_ = tc.SetReadBuffer(window)
|
||||
}
|
||||
select {
|
||||
case h.conns <- c:
|
||||
case <-done:
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
return h
|
||||
}
|
||||
|
||||
func (h *graphiteHost) addr(t *testing.T) *net.TCPAddr {
|
||||
a, err := net.ResolveTCPAddr("tcp", h.ln.Addr().String())
|
||||
require.NoError(t, err)
|
||||
return a
|
||||
}
|
||||
|
||||
// readExport reads what one send wrote, bounded so a send that never finishes fails the test rather than hanging it
|
||||
func readExport(t *testing.T, c net.Conn) []byte {
|
||||
t.Helper()
|
||||
require.NoError(t, c.SetReadDeadline(time.Now().Add(10*time.Second)))
|
||||
b, err := io.ReadAll(c)
|
||||
require.NoError(t, err)
|
||||
return b
|
||||
}
|
||||
|
||||
func (h *graphiteHost) next(t *testing.T, wait time.Duration) net.Conn {
|
||||
t.Helper()
|
||||
select {
|
||||
case c := <-h.conns:
|
||||
return c
|
||||
case <-time.After(wait):
|
||||
t.Fatal("no connection")
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// lockedBuffer is a log destination a test can read while the code under test writes to it from another goroutine
|
||||
type lockedBuffer struct {
|
||||
mu sync.Mutex
|
||||
buf bytes.Buffer
|
||||
}
|
||||
|
||||
func (b *lockedBuffer) Write(p []byte) (int, error) {
|
||||
b.mu.Lock()
|
||||
defer b.mu.Unlock()
|
||||
return b.buf.Write(p)
|
||||
}
|
||||
|
||||
func (b *lockedBuffer) String() string {
|
||||
b.mu.Lock()
|
||||
defer b.mu.Unlock()
|
||||
return b.buf.String()
|
||||
}
|
||||
|
||||
func testGraphiteConfig(addr *net.TCPAddr, r metrics.Registry) graphiteConfigExport {
|
||||
return graphiteConfigExport{Addr: addr, Registry: r, FlushInterval: time.Second, DurationUnit: time.Nanosecond, Prefix: "nebula"}
|
||||
}
|
||||
|
||||
// Enough metrics that one export overflows the socket buffers on any platform, so a send to a host that stops
|
||||
// reading blocks
|
||||
func bigGraphiteRegistry(r metrics.Registry, t *testing.T) {
|
||||
for i := range 200000 {
|
||||
name := fmt.Sprintf("big.gauge.%d", i)
|
||||
metrics.GetOrRegisterGauge(name, r).Update(int64(i))
|
||||
t.Cleanup(func() { r.Unregister(name) })
|
||||
}
|
||||
}
|
||||
|
||||
func TestGraphiteOnce_sends(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
metrics.GetOrRegisterGauge("g", r).Update(7)
|
||||
metrics.GetOrRegisterCounter("c", r).Inc(3)
|
||||
h := newGraphiteHost(t, 0)
|
||||
|
||||
require.NoError(t, graphiteOnce(t.Context(), testGraphiteConfig(h.addr(t), r), time.Minute))
|
||||
b := readExport(t, h.next(t, 5*time.Second))
|
||||
assert.Contains(t, string(b), "nebula.g.value 7 ")
|
||||
assert.Contains(t, string(b), "nebula.c.count 3 ")
|
||||
assert.Contains(t, string(b), "nebula.c.count_ps 3.00 ")
|
||||
}
|
||||
|
||||
// A host that accepts and never reads is given up on, and the failed write is reported
|
||||
func TestGraphiteOnce_stalledHostTimesOut(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
done := make(chan error, 1)
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(t.Context(), cfg, 300*time.Millisecond) }()
|
||||
h.next(t, 5*time.Second) // accepted, never read
|
||||
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("the send did not give up on a host that stopped reading")
|
||||
}
|
||||
}
|
||||
|
||||
// The timeout covers the whole send, a host that keeps reading but too slowly is still given up on
|
||||
func TestGraphiteOnce_timeoutCoversTheWholeSend(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 0)
|
||||
done := make(chan error, 1)
|
||||
start := time.Now()
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(t.Context(), cfg, 500*time.Millisecond) }()
|
||||
c := h.next(t, 5*time.Second)
|
||||
stopReading := make(chan struct{})
|
||||
defer close(stopReading)
|
||||
// 32KB every 10ms keeps every write well inside the timeout, the whole export takes seconds
|
||||
go func() {
|
||||
buf := make([]byte, 32<<10)
|
||||
for {
|
||||
select {
|
||||
case <-stopReading:
|
||||
return
|
||||
case <-time.After(10 * time.Millisecond):
|
||||
}
|
||||
if _, err := c.Read(buf); err != nil {
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
assert.Less(t, time.Since(start), 5*time.Second)
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("a host that kept reading slowly held the send past its timeout")
|
||||
}
|
||||
}
|
||||
|
||||
func TestGraphiteOnce_cancelledCtxDoesNotConnect(t *testing.T) {
|
||||
h := newGraphiteHost(t, 0)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
cancel()
|
||||
require.Error(t, graphiteOnce(ctx, testGraphiteConfig(h.addr(t), metrics.NewRegistry()), time.Minute))
|
||||
select {
|
||||
case <-h.conns:
|
||||
t.Fatal("connected on a cancelled ctx")
|
||||
case <-time.After(200 * time.Millisecond):
|
||||
}
|
||||
}
|
||||
|
||||
// A stop or reload abandons a stuck send rather than waiting out its timeout
|
||||
func TestGraphiteOnce_cancelAbandonsSend(t *testing.T) {
|
||||
r := metrics.NewRegistry()
|
||||
bigGraphiteRegistry(r, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
done := make(chan error, 1)
|
||||
cfg := testGraphiteConfig(h.addr(t), r)
|
||||
go func() { done <- graphiteOnce(ctx, cfg, time.Minute) }()
|
||||
h.next(t, 5*time.Second)
|
||||
select {
|
||||
case err := <-done:
|
||||
t.Fatalf("the send should be stuck on a host that is not reading, it ended with %v", err)
|
||||
case <-time.After(200 * time.Millisecond):
|
||||
}
|
||||
|
||||
cancel()
|
||||
select {
|
||||
case err := <-done:
|
||||
require.Error(t, err)
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("the send is still stuck after its ctx was cancelled")
|
||||
}
|
||||
}
|
||||
|
||||
// buildRuntime hands graphite the configured prefix and interval
|
||||
func TestStatsServer_graphiteExportUsesConfig(t *testing.T) {
|
||||
const name = "graphite.wiring.test"
|
||||
metrics.GetOrRegisterCounter(name, nil).Inc(8)
|
||||
t.Cleanup(func() { metrics.DefaultRegistry.Unregister(name) })
|
||||
h := newGraphiteHost(t, 0)
|
||||
s, c := newTestStatsServer(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "4s", "prefix": "pfx", "host": h.ln.Addr().String()})
|
||||
cfg, err := loadStatsConfig(c)
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), cfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
b := readExport(t, h.next(t, 5*time.Second))
|
||||
assert.Contains(t, string(b), "pfx."+name+".count 8 ")
|
||||
assert.Contains(t, string(b), "pfx."+name+".count_ps 2.00 ")
|
||||
}
|
||||
|
||||
func TestStatsServer_graphiteFailureIsLogged(t *testing.T) {
|
||||
logs := &lockedBuffer{}
|
||||
s, c := newTestStatsServer(t)
|
||||
s.l = test.NewLoggerWithOutput(logs)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
cfg, err := loadStatsConfig(c)
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), cfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
assert.Contains(t, logs.String(), "Graphite export failed")
|
||||
}
|
||||
|
||||
// Stop abandons the running export, so it goes through Start rather than handing buildRuntime a ctx, and a stop is
|
||||
// not logged as a failure
|
||||
func TestStatsServer_stopAbandonsGraphiteSend(t *testing.T) {
|
||||
bigGraphiteRegistry(metrics.DefaultRegistry, t)
|
||||
h := newGraphiteHost(t, 4096)
|
||||
logs := &lockedBuffer{}
|
||||
s, c := newTestStatsServer(t)
|
||||
s.l = test.NewLoggerWithOutput(logs)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "50ms", "host": h.ln.Addr().String()})
|
||||
require.NoError(t, s.reload(c, true))
|
||||
|
||||
started := make(chan struct{})
|
||||
go func() {
|
||||
s.Start()
|
||||
close(started)
|
||||
}()
|
||||
stuck := h.next(t, 30*time.Second)
|
||||
s.Stop()
|
||||
select {
|
||||
case <-started:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Start did not return after Stop")
|
||||
}
|
||||
|
||||
// A closed sender resets the connection once it sees this, one still sending just buffers it. Either way the
|
||||
// read below doesn't have to drain the export through the small window to find out
|
||||
_, err := stuck.Write([]byte("x"))
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, stuck.SetReadDeadline(time.Now().Add(10*time.Second)))
|
||||
n, err := io.Copy(io.Discard, stuck)
|
||||
var ne net.Error
|
||||
if errors.As(err, &ne) && ne.Timeout() {
|
||||
t.Fatalf("the send kept the connection after Stop, read %d bytes", n)
|
||||
}
|
||||
assert.Less(t, n, int64(1<<20), "the send kept going after Stop")
|
||||
// The capture loop logs on its own goroutine after Start has returned, give it the chance
|
||||
assert.Never(t, func() bool { return strings.Contains(logs.String(), "Graphite export failed") }, 500*time.Millisecond, 10*time.Millisecond, "a stop is not a failure")
|
||||
}
|
||||
@@ -26,18 +26,4 @@ message NebulaHandshakeDetails {
|
||||
uint32 CertVersion = 8;
|
||||
// reserved for WIP multiport
|
||||
reserved 6, 7;
|
||||
// Multiport lane negotiation. Absent on hosts without multiport enabled;
|
||||
// vanilla nebula treats 9 and 10 as unknown fields and skips them.
|
||||
LaneDetails InitiatorLanes = 9;
|
||||
LaneDetails ResponderLanes = 10;
|
||||
}
|
||||
|
||||
// LaneDetails advertises a host's multiport lane capability. On a base
|
||||
// handshake LaneIndex is 0 and PortCount/BasePort describe the sender's
|
||||
// consecutively bound UDP ports. On a lane handshake the initiator sets
|
||||
// LaneIndex to its (nonzero) lane number.
|
||||
message LaneDetails {
|
||||
uint32 PortCount = 1;
|
||||
uint32 BasePort = 2;
|
||||
uint32 LaneIndex = 3;
|
||||
}
|
||||
@@ -71,7 +71,6 @@ func newTestMachine(
|
||||
cs.version, cs.getCredential,
|
||||
verifier, func() (uint32, error) { return localIndex, nil },
|
||||
initiator, header.HandshakeIXPSK0,
|
||||
nil,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
return m
|
||||
|
||||
+1
-34
@@ -39,14 +39,6 @@ type Result struct {
|
||||
HandshakeTime uint64
|
||||
MessageIndex uint64 // number of messages exchanged during the handshake
|
||||
Initiator bool
|
||||
|
||||
// Multiport lane negotiation, from the peer's LaneDetails. All zero when
|
||||
// the peer did not advertise (vanilla peer or multiport disabled).
|
||||
// PeerTxLanes is how many lanes the peer may send on, which is how many lane
|
||||
// sessions we need in order to receive everything it sends.
|
||||
PeerPortCount uint32
|
||||
PeerBasePort uint32
|
||||
PeerTxLanes uint32
|
||||
}
|
||||
|
||||
// Machine drives a Noise handshake through N messages. It handles Noise
|
||||
@@ -69,7 +61,6 @@ type Machine struct {
|
||||
verifier CertVerifier
|
||||
result *Result
|
||||
msgs []msgFlags
|
||||
lanes *LaneDetails // our multiport advert; nil emits a vanilla payload
|
||||
myVersion cert.Version
|
||||
subtype header.MessageSubType
|
||||
indexAllocated bool
|
||||
@@ -82,8 +73,6 @@ type Machine struct {
|
||||
// the noise pattern and the per-message content layout. The credential for
|
||||
// `version` is fetched via getCred and used to seed the noise.HandshakeState.
|
||||
// IndexAllocator is called lazily when the first outgoing payload is built.
|
||||
// lanes, when non-nil, is emitted as this side's multiport advert on every
|
||||
// payload-bearing message; nil produces byte-identical vanilla payloads.
|
||||
func NewMachine(
|
||||
version cert.Version,
|
||||
getCred GetCredentialFunc,
|
||||
@@ -91,7 +80,6 @@ func NewMachine(
|
||||
allocIndex IndexAllocator,
|
||||
initiator bool,
|
||||
subtype header.MessageSubType,
|
||||
lanes *LaneDetails,
|
||||
) (*Machine, error) {
|
||||
info, err := subtypeInfoFor(subtype)
|
||||
if err != nil {
|
||||
@@ -115,7 +103,6 @@ func NewMachine(
|
||||
getCred: getCred,
|
||||
allocIndex: allocIndex,
|
||||
verifier: verifier,
|
||||
lanes: lanes,
|
||||
myVersion: version,
|
||||
result: &Result{
|
||||
Initiator: initiator,
|
||||
@@ -311,8 +298,7 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||
}
|
||||
|
||||
// Assert the payload contains exactly what we expect
|
||||
hasPayloadData := payload.InitiatorIndex != 0 || payload.ResponderIndex != 0 || payload.Time != 0 ||
|
||||
payload.InitiatorLanes != nil || payload.ResponderLanes != nil
|
||||
hasPayloadData := payload.InitiatorIndex != 0 || payload.ResponderIndex != 0 || payload.Time != 0
|
||||
if hasPayloadData != flags.expectsPayload {
|
||||
m.failed = true
|
||||
return ErrUnexpectedContent
|
||||
@@ -341,23 +327,6 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||
m.result.RemoteIndex = remoteIndex
|
||||
m.result.HandshakeTime = payload.Time
|
||||
m.payloadSet = true
|
||||
|
||||
// Multiport advert from the peer's side of the exchange. Out-of-range
|
||||
// values mean a peer we can't pair lanes with; ignore the advert
|
||||
// rather than failing the handshake — the tunnel itself is fine, it
|
||||
// just won't get lanes. Semantic policing (port-count caps, lane
|
||||
// clamping) belongs to the handshake manager.
|
||||
var peerLanes *LaneDetails
|
||||
if m.result.Initiator {
|
||||
peerLanes = payload.ResponderLanes
|
||||
} else {
|
||||
peerLanes = payload.InitiatorLanes
|
||||
}
|
||||
if peerLanes != nil && peerLanes.BasePort <= 0xffff && peerLanes.PortCount <= 0xffff && peerLanes.TxLanes <= 0xffff {
|
||||
m.result.PeerPortCount = peerLanes.PortCount
|
||||
m.result.PeerBasePort = peerLanes.BasePort
|
||||
m.result.PeerTxLanes = peerLanes.TxLanes
|
||||
}
|
||||
}
|
||||
|
||||
// Process certificate
|
||||
@@ -428,11 +397,9 @@ func (m *Machine) marshalOutgoing(flags msgFlags) ([]byte, error) {
|
||||
|
||||
if m.result.Initiator {
|
||||
p.InitiatorIndex = m.result.LocalIndex
|
||||
p.InitiatorLanes = m.lanes
|
||||
} else {
|
||||
p.ResponderIndex = m.result.LocalIndex
|
||||
p.InitiatorIndex = m.result.RemoteIndex
|
||||
p.ResponderLanes = m.lanes
|
||||
}
|
||||
p.Time = uint64(time.Now().UnixNano())
|
||||
}
|
||||
|
||||
@@ -1,111 +0,0 @@
|
||||
package handshake
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/cert"
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// newTestLaneMachine is newTestMachine with a lane advert attached.
|
||||
func newTestLaneMachine(
|
||||
t *testing.T,
|
||||
cs *testCertState,
|
||||
verifier CertVerifier,
|
||||
initiator bool,
|
||||
localIndex uint32,
|
||||
lanes *LaneDetails,
|
||||
) *Machine {
|
||||
t.Helper()
|
||||
m, err := NewMachine(
|
||||
cs.version, cs.getCredential,
|
||||
verifier, func() (uint32, error) { return localIndex, nil },
|
||||
initiator, header.HandshakeIXPSK0,
|
||||
lanes,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
return m
|
||||
}
|
||||
|
||||
func doFullLaneHandshake(t *testing.T, initLanes, respLanes *LaneDetails) (initR, respR *Result) {
|
||||
t.Helper()
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(
|
||||
cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil,
|
||||
)
|
||||
caPool := ct.NewTestCAPool(ca)
|
||||
v := testVerifier(caPool)
|
||||
|
||||
initCS := newTestCertState(t, ca, caKey, "initiator", []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")})
|
||||
respCS := newTestCertState(t, ca, caKey, "responder", []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")})
|
||||
|
||||
initM := newTestLaneMachine(t, initCS, v, true, 1000, initLanes)
|
||||
respM := newTestLaneMachine(t, respCS, v, false, 2000, respLanes)
|
||||
|
||||
msg1, err := initM.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
resp, respR, err := respM.ProcessPacket(nil, msg1)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, respR)
|
||||
|
||||
_, initR, err = initM.ProcessPacket(nil, resp)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, initR)
|
||||
return initR, respR
|
||||
}
|
||||
|
||||
func TestMachineLaneAdvertBothSides(t *testing.T) {
|
||||
initR, respR := doFullLaneHandshake(t,
|
||||
&LaneDetails{PortCount: 8, BasePort: 4242, TxLanes: 8},
|
||||
&LaneDetails{PortCount: 4, BasePort: 5353, TxLanes: 3},
|
||||
)
|
||||
|
||||
// Each side's Result carries the peer's advert.
|
||||
assert.Equal(t, uint32(4), initR.PeerPortCount)
|
||||
assert.Equal(t, uint32(5353), initR.PeerBasePort)
|
||||
assert.Equal(t, uint32(3), initR.PeerTxLanes)
|
||||
|
||||
assert.Equal(t, uint32(8), respR.PeerPortCount)
|
||||
assert.Equal(t, uint32(4242), respR.PeerBasePort)
|
||||
assert.Equal(t, uint32(8), respR.PeerTxLanes)
|
||||
}
|
||||
|
||||
func TestMachineLaneAdvertAsymmetric(t *testing.T) {
|
||||
// Vanilla initiator, multiport responder and vice versa: the nil side
|
||||
// yields all-zero peer fields on the other end.
|
||||
initR, respR := doFullLaneHandshake(t, nil, &LaneDetails{PortCount: 4, BasePort: 5353})
|
||||
assert.Equal(t, uint32(4), initR.PeerPortCount)
|
||||
assert.Equal(t, uint32(0), respR.PeerPortCount)
|
||||
assert.Equal(t, uint32(0), respR.PeerBasePort)
|
||||
|
||||
initR, respR = doFullLaneHandshake(t, &LaneDetails{PortCount: 8, BasePort: 4242}, nil)
|
||||
assert.Equal(t, uint32(0), initR.PeerPortCount)
|
||||
assert.Equal(t, uint32(8), respR.PeerPortCount)
|
||||
}
|
||||
|
||||
func TestMachineLaneAdvertOutOfRangeIgnored(t *testing.T) {
|
||||
// A BasePort that can't be a real UDP port is ignored, not fatal.
|
||||
initR, respR := doFullLaneHandshake(t,
|
||||
&LaneDetails{PortCount: 8, BasePort: 70000, TxLanes: 8},
|
||||
&LaneDetails{PortCount: 4, BasePort: 5353, TxLanes: 4},
|
||||
)
|
||||
assert.Equal(t, uint32(0), respR.PeerPortCount)
|
||||
assert.Equal(t, uint32(0), respR.PeerBasePort)
|
||||
assert.Equal(t, uint32(0), respR.PeerTxLanes)
|
||||
// The sane side still negotiates.
|
||||
assert.Equal(t, uint32(4), initR.PeerPortCount)
|
||||
|
||||
// An out-of-range TxLanes drops the whole advert the same way: a lane index
|
||||
// that does not fit the header is as unusable as an impossible port.
|
||||
initR, respR = doFullLaneHandshake(t,
|
||||
&LaneDetails{PortCount: 8, BasePort: 4242, TxLanes: 0x10000},
|
||||
&LaneDetails{PortCount: 4, BasePort: 5353, TxLanes: 4},
|
||||
)
|
||||
assert.Equal(t, uint32(0), respR.PeerPortCount)
|
||||
assert.Equal(t, uint32(4), initR.PeerPortCount)
|
||||
}
|
||||
@@ -444,7 +444,6 @@ func TestMachineThreeMessagePattern(t *testing.T) {
|
||||
initCS.getCredential, v,
|
||||
func() (uint32, error) { return 1000, nil },
|
||||
true, header.HandshakeXXPSK0,
|
||||
nil,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
|
||||
@@ -453,7 +452,6 @@ func TestMachineThreeMessagePattern(t *testing.T) {
|
||||
respCS.getCredential, v,
|
||||
func() (uint32, error) { return 2000, nil },
|
||||
false, header.HandshakeXXPSK0,
|
||||
nil,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
|
||||
|
||||
+5
-120
@@ -20,40 +20,15 @@ type Payload struct {
|
||||
ResponderIndex uint32
|
||||
Time uint64
|
||||
CertVersion uint32
|
||||
|
||||
// Multiport lane negotiation; nil when the sender has multiport disabled
|
||||
// (which keeps the encoded payload byte-identical to a vanilla one).
|
||||
InitiatorLanes *LaneDetails
|
||||
ResponderLanes *LaneDetails
|
||||
}
|
||||
|
||||
// LaneDetails advertises multiport lane capability: the contiguous UDP port
|
||||
// range the sender bound, and how many lanes it may send on. The receiver needs
|
||||
// PortCount/BasePort to aim its own lanes and TxLanes to know how many lane
|
||||
// sessions to derive for receiving.
|
||||
type LaneDetails struct {
|
||||
PortCount uint32
|
||||
BasePort uint32
|
||||
TxLanes uint32
|
||||
}
|
||||
|
||||
// Proto field numbers for NebulaHandshakeDetails
|
||||
const (
|
||||
fieldCert = 1 // bytes
|
||||
fieldInitiatorIndex = 2 // uint32
|
||||
fieldResponderIndex = 3 // uint32
|
||||
fieldTime = 5 // uint64
|
||||
fieldCertVersion = 8 // uint32
|
||||
fieldInitiatorLanes = 9 // LaneDetails
|
||||
fieldResponderLanes = 10 // LaneDetails
|
||||
)
|
||||
|
||||
// Proto field numbers for LaneDetails.
|
||||
// Field 3 was a per-lane handshake index and is permanently reserved.
|
||||
const (
|
||||
fieldLanePortCount = 1 // uint32
|
||||
fieldLaneBasePort = 2 // uint32
|
||||
fieldLaneTxLanes = 4 // uint32
|
||||
fieldCert = 1 // bytes
|
||||
fieldInitiatorIndex = 2 // uint32
|
||||
fieldResponderIndex = 3 // uint32
|
||||
fieldTime = 5 // uint64
|
||||
fieldCertVersion = 8 // uint32
|
||||
)
|
||||
|
||||
// MarshalPayload encodes a handshake payload in protobuf wire format compatible
|
||||
@@ -82,16 +57,6 @@ func MarshalPayload(out []byte, p Payload) []byte {
|
||||
details = protowire.AppendTag(details, fieldCertVersion, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, uint64(p.CertVersion))
|
||||
}
|
||||
// Emitted last to keep the encoding in ascending field-number order, which
|
||||
// is what protoc-gen-go would produce for the same message.
|
||||
if p.InitiatorLanes != nil {
|
||||
details = protowire.AppendTag(details, fieldInitiatorLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, p.InitiatorLanes.marshal(nil))
|
||||
}
|
||||
if p.ResponderLanes != nil {
|
||||
details = protowire.AppendTag(details, fieldResponderLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, p.ResponderLanes.marshal(nil))
|
||||
}
|
||||
|
||||
out = protowire.AppendTag(out, 1, protowire.BytesType)
|
||||
out = protowire.AppendBytes(out, details)
|
||||
@@ -99,20 +64,6 @@ func MarshalPayload(out []byte, p Payload) []byte {
|
||||
return out
|
||||
}
|
||||
|
||||
// marshal appends the LaneDetails submessage fields to out. All fields are
|
||||
// emitted unconditionally: a LaneDetails is only present at all when multiport
|
||||
// is negotiating, and explicit zeros keep the parser's presence semantics
|
||||
// trivial.
|
||||
func (d *LaneDetails) marshal(out []byte) []byte {
|
||||
out = protowire.AppendTag(out, fieldLanePortCount, protowire.VarintType)
|
||||
out = protowire.AppendVarint(out, uint64(d.PortCount))
|
||||
out = protowire.AppendTag(out, fieldLaneBasePort, protowire.VarintType)
|
||||
out = protowire.AppendVarint(out, uint64(d.BasePort))
|
||||
out = protowire.AppendTag(out, fieldLaneTxLanes, protowire.VarintType)
|
||||
out = protowire.AppendVarint(out, uint64(d.TxLanes))
|
||||
return out
|
||||
}
|
||||
|
||||
// UnmarshalPayload decodes a protobuf-encoded NebulaHandshake message.
|
||||
func UnmarshalPayload(b []byte) (Payload, error) {
|
||||
var p Payload
|
||||
@@ -210,72 +161,6 @@ func unmarshalPayloadDetails(p *Payload, b []byte) error {
|
||||
}
|
||||
p.CertVersion = uint32(v)
|
||||
b = b[n:]
|
||||
case fieldInitiatorLanes:
|
||||
if typ != protowire.BytesType {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
v, n := protowire.ConsumeBytes(b)
|
||||
if n < 0 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
p.InitiatorLanes = new(LaneDetails)
|
||||
if err := unmarshalLaneDetails(p.InitiatorLanes, v); err != nil {
|
||||
return err
|
||||
}
|
||||
b = b[n:]
|
||||
case fieldResponderLanes:
|
||||
if typ != protowire.BytesType {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
v, n := protowire.ConsumeBytes(b)
|
||||
if n < 0 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
p.ResponderLanes = new(LaneDetails)
|
||||
if err := unmarshalLaneDetails(p.ResponderLanes, v); err != nil {
|
||||
return err
|
||||
}
|
||||
b = b[n:]
|
||||
default:
|
||||
n := protowire.ConsumeFieldValue(num, typ, b)
|
||||
if n < 0 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
b = b[n:]
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func unmarshalLaneDetails(d *LaneDetails, b []byte) error {
|
||||
for len(b) > 0 {
|
||||
num, typ, n := protowire.ConsumeTag(b)
|
||||
if n < 0 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
b = b[n:]
|
||||
|
||||
// Same contract as the details parser: known fields hard-fail on a
|
||||
// wire-type mismatch, unknown fields are skipped, repeated singular
|
||||
// fields follow proto3 last-wins.
|
||||
switch num {
|
||||
case fieldLanePortCount, fieldLaneBasePort, fieldLaneTxLanes:
|
||||
if typ != protowire.VarintType {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
v, n := protowire.ConsumeVarint(b)
|
||||
if n < 0 || v > math.MaxUint32 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
switch num {
|
||||
case fieldLanePortCount:
|
||||
d.PortCount = uint32(v)
|
||||
case fieldLaneBasePort:
|
||||
d.BasePort = uint32(v)
|
||||
case fieldLaneTxLanes:
|
||||
d.TxLanes = uint32(v)
|
||||
}
|
||||
b = b[n:]
|
||||
default:
|
||||
n := protowire.ConsumeFieldValue(num, typ, b)
|
||||
if n < 0 {
|
||||
|
||||
+12
-138
@@ -117,134 +117,23 @@ func TestPayloadUnknownFields(t *testing.T) {
|
||||
assert.Equal(t, uint32(88), got.ResponderIndex)
|
||||
})
|
||||
|
||||
t.Run("unknown field inside LaneDetails is skipped", func(t *testing.T) {
|
||||
var lane []byte
|
||||
lane = protowire.AppendTag(lane, fieldLanePortCount, protowire.VarintType)
|
||||
lane = protowire.AppendVarint(lane, 4)
|
||||
lane = protowire.AppendTag(lane, 50, protowire.VarintType) // unknown subfield
|
||||
lane = protowire.AppendVarint(lane, 9999)
|
||||
lane = protowire.AppendTag(lane, fieldLaneBasePort, protowire.VarintType)
|
||||
lane = protowire.AppendVarint(lane, 4242)
|
||||
|
||||
t.Run("reserved fields 6 and 7 are skipped", func(t *testing.T) {
|
||||
// Fields 6 and 7 are reserved in the proto definition
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldInitiatorIndex, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, 100)
|
||||
details = protowire.AppendTag(details, fieldInitiatorLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, lane)
|
||||
details = protowire.AppendTag(details, 6, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, 1)
|
||||
details = protowire.AppendTag(details, 7, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, 2)
|
||||
|
||||
got, err := UnmarshalPayload(wrapDetails(details))
|
||||
var data []byte
|
||||
data = protowire.AppendTag(data, 1, protowire.BytesType)
|
||||
data = protowire.AppendBytes(data, details)
|
||||
|
||||
got, err := UnmarshalPayload(data)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, uint32(100), got.InitiatorIndex)
|
||||
require.NotNil(t, got.InitiatorLanes)
|
||||
assert.Equal(t, uint32(4), got.InitiatorLanes.PortCount)
|
||||
assert.Equal(t, uint32(4242), got.InitiatorLanes.BasePort)
|
||||
})
|
||||
}
|
||||
|
||||
func TestPayloadLaneDetails(t *testing.T) {
|
||||
t.Run("round trip both sides", func(t *testing.T) {
|
||||
data := MarshalPayload(nil, Payload{
|
||||
InitiatorIndex: 12345,
|
||||
Time: 999,
|
||||
InitiatorLanes: &LaneDetails{PortCount: 8, BasePort: 4242, TxLanes: 3},
|
||||
ResponderLanes: &LaneDetails{PortCount: 4, BasePort: 5353},
|
||||
})
|
||||
|
||||
got, err := UnmarshalPayload(data)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, got.InitiatorLanes)
|
||||
assert.Equal(t, LaneDetails{PortCount: 8, BasePort: 4242, TxLanes: 3}, *got.InitiatorLanes)
|
||||
require.NotNil(t, got.ResponderLanes)
|
||||
assert.Equal(t, LaneDetails{PortCount: 4, BasePort: 5353}, *got.ResponderLanes)
|
||||
})
|
||||
|
||||
t.Run("zero-valued LaneDetails survives the round trip", func(t *testing.T) {
|
||||
// Presence is what negotiation keys on; an all-zero advert must not
|
||||
// decay to nil.
|
||||
data := MarshalPayload(nil, Payload{
|
||||
InitiatorIndex: 1,
|
||||
InitiatorLanes: &LaneDetails{},
|
||||
})
|
||||
got, err := UnmarshalPayload(data)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, got.InitiatorLanes)
|
||||
assert.Equal(t, LaneDetails{}, *got.InitiatorLanes)
|
||||
assert.Nil(t, got.ResponderLanes)
|
||||
})
|
||||
|
||||
t.Run("nil lanes marshal byte-identical to a vanilla payload", func(t *testing.T) {
|
||||
p := Payload{
|
||||
Cert: []byte("cert"),
|
||||
CertVersion: 2,
|
||||
InitiatorIndex: 100,
|
||||
Time: 999,
|
||||
}
|
||||
// The vanilla encoding of the same fields, built by hand in field order.
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldCert, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, p.Cert)
|
||||
details = protowire.AppendTag(details, fieldInitiatorIndex, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, uint64(p.InitiatorIndex))
|
||||
details = protowire.AppendTag(details, fieldTime, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, p.Time)
|
||||
details = protowire.AppendTag(details, fieldCertVersion, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, uint64(p.CertVersion))
|
||||
|
||||
assert.Equal(t, wrapDetails(details), MarshalPayload(nil, p))
|
||||
})
|
||||
|
||||
t.Run("lane field with wrong wire type rejected", func(t *testing.T) {
|
||||
for _, field := range []protowire.Number{fieldInitiatorLanes, fieldResponderLanes} {
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, field, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, 1)
|
||||
_, err := UnmarshalPayload(wrapDetails(details))
|
||||
assert.Error(t, err)
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("lane subfield with wrong wire type rejected", func(t *testing.T) {
|
||||
var lane []byte
|
||||
lane = protowire.AppendTag(lane, fieldLanePortCount, protowire.BytesType)
|
||||
lane = protowire.AppendBytes(lane, []byte{1, 2, 3})
|
||||
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldInitiatorLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, lane)
|
||||
_, err := UnmarshalPayload(wrapDetails(details))
|
||||
assert.Error(t, err)
|
||||
})
|
||||
|
||||
t.Run("truncated LaneDetails submessage rejected", func(t *testing.T) {
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldInitiatorLanes, protowire.BytesType)
|
||||
details = append(details, 0x0a, 0x01, 0x02) // length 10, only 2 bytes
|
||||
_, err := UnmarshalPayload(wrapDetails(details))
|
||||
assert.Error(t, err)
|
||||
})
|
||||
|
||||
t.Run("truncated varint inside LaneDetails rejected", func(t *testing.T) {
|
||||
var lane []byte
|
||||
lane = protowire.AppendTag(lane, fieldLaneBasePort, protowire.VarintType)
|
||||
lane = append(lane, 0x80) // incomplete varint
|
||||
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldResponderLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, lane)
|
||||
_, err := UnmarshalPayload(wrapDetails(details))
|
||||
assert.Error(t, err)
|
||||
})
|
||||
|
||||
t.Run("lane subfield varint overflow rejected", func(t *testing.T) {
|
||||
var lane []byte
|
||||
lane = protowire.AppendTag(lane, fieldLaneTxLanes, protowire.VarintType)
|
||||
lane = protowire.AppendVarint(lane, math.MaxUint32+1)
|
||||
|
||||
var details []byte
|
||||
details = protowire.AppendTag(details, fieldInitiatorLanes, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, lane)
|
||||
_, err := UnmarshalPayload(wrapDetails(details))
|
||||
assert.Error(t, err)
|
||||
})
|
||||
}
|
||||
|
||||
@@ -439,12 +328,6 @@ func FuzzPayload(f *testing.F) {
|
||||
Time: 3,
|
||||
CertVersion: 2,
|
||||
}))
|
||||
f.Add(MarshalPayload(nil, Payload{
|
||||
InitiatorIndex: 1,
|
||||
Time: 3,
|
||||
InitiatorLanes: &LaneDetails{PortCount: 8, BasePort: 4242, TxLanes: 2},
|
||||
ResponderLanes: &LaneDetails{PortCount: 4, BasePort: 5353},
|
||||
}))
|
||||
f.Add([]byte{})
|
||||
f.Add([]byte{0xff})
|
||||
|
||||
@@ -474,14 +357,5 @@ func payloadsEqual(a, b Payload) bool {
|
||||
a.InitiatorIndex == b.InitiatorIndex &&
|
||||
a.ResponderIndex == b.ResponderIndex &&
|
||||
a.Time == b.Time &&
|
||||
a.CertVersion == b.CertVersion &&
|
||||
laneDetailsEqual(a.InitiatorLanes, b.InitiatorLanes) &&
|
||||
laneDetailsEqual(a.ResponderLanes, b.ResponderLanes)
|
||||
}
|
||||
|
||||
func laneDetailsEqual(a, b *LaneDetails) bool {
|
||||
if a == nil || b == nil {
|
||||
return a == b
|
||||
}
|
||||
return *a == *b
|
||||
a.CertVersion == b.CertVersion
|
||||
}
|
||||
+46
-95
@@ -50,34 +50,28 @@ type HandshakeConfig struct {
|
||||
retries int64
|
||||
triggerBuffer int
|
||||
|
||||
// Multiport lane parameters; laneCount == 0 means multiport is disabled.
|
||||
// laneCount includes implicit lane 0 (the base tunnel), so lanes
|
||||
// 1..laneCount-1 may carry traffic. lanePortCount/laneBasePort describe our
|
||||
// own bound port range and are advertised in every handshake payload.
|
||||
laneCount int
|
||||
lanePortCount uint16
|
||||
laneBasePort uint16
|
||||
|
||||
messageMetrics *MessageMetrics
|
||||
}
|
||||
|
||||
type HandshakeManager struct {
|
||||
// Mutex for interacting with the vpnIps and indexes maps
|
||||
// Mutex for interacting with the vpnIps and indexes maps.
|
||||
// Lock order is hostmap, then this lock, then the lighthouse, then a RemoteList.
|
||||
sync.RWMutex
|
||||
|
||||
vpnIps map[netip.Addr]*HandshakeHostInfo
|
||||
indexes map[uint32]*HandshakeHostInfo
|
||||
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
mainHostMap *HostMap
|
||||
lightHouse *LightHouse
|
||||
outside udp.Conn
|
||||
config HandshakeConfig
|
||||
OutboundHandshakeTimer *LockingTimerWheel[netip.Addr]
|
||||
messageMetrics *MessageMetrics
|
||||
metricInitiated metrics.Counter
|
||||
metricTimedOut metrics.Counter
|
||||
metricRejectedBlocklisted metrics.Counter
|
||||
f *Interface
|
||||
l *slog.Logger
|
||||
|
||||
// can be used to trigger outbound handshake for the given vpnIp
|
||||
trigger chan netip.Addr
|
||||
@@ -125,18 +119,19 @@ func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, s
|
||||
|
||||
func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *LightHouse, outside udp.Conn, config HandshakeConfig) *HandshakeManager {
|
||||
return &HandshakeManager{
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
l: l,
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
lightHouse: lightHouse,
|
||||
outside: outside,
|
||||
config: config,
|
||||
trigger: make(chan netip.Addr, config.triggerBuffer),
|
||||
OutboundHandshakeTimer: NewLockingTimerWheel[netip.Addr](config.tryInterval, hsTimeout(config.retries, config.tryInterval)),
|
||||
messageMetrics: config.messageMetrics,
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
metricRejectedBlocklisted: metrics.GetOrRegisterCounter("handshake_manager.rejected.blocklisted", nil),
|
||||
l: l,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -267,14 +262,6 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
||||
}
|
||||
|
||||
// Get a remotes object if we don't already have one.
|
||||
// This is mainly to protect us as this should never be the case
|
||||
// NB ^ This comment doesn't jive. It's how the thing gets initialized.
|
||||
// It's the common path. Should it update every time, in case a future LH query/queries give us more info?
|
||||
if hostinfo.remotes == nil {
|
||||
hostinfo.remotes = hm.lightHouse.QueryCache([]netip.Addr{vpnIp})
|
||||
}
|
||||
|
||||
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
|
||||
remotesHaveChanged := !slices.Equal(remotes, hh.lastRemotes)
|
||||
|
||||
@@ -379,6 +366,9 @@ func (hm *HandshakeManager) StartHandshake(vpnAddr netip.Addr, cacheCb func(*Han
|
||||
hostinfo := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
HandshakePacket: make(map[uint8][]byte, 0),
|
||||
// Attached here so a pending hostinfo never exists without one: SetRemote dereferences
|
||||
// it, and create-tunnel -address can reach SetRemote before the handshake loop runs.
|
||||
remotes: hm.lightHouse.QueryCache([]netip.Addr{vpnAddr}),
|
||||
relayState: RelayState{
|
||||
relays: nil,
|
||||
relayForByAddr: map[netip.Addr]*Relay{},
|
||||
@@ -543,9 +533,6 @@ func (hm *HandshakeManager) DeleteHostInfo(hostinfo *HostInfo) {
|
||||
|
||||
func (hm *HandshakeManager) unlockedDeleteHostInfo(hostinfo *HostInfo) {
|
||||
for _, addr := range hostinfo.vpnAddrs {
|
||||
// Only delete the pending entry if it is actually ours: an
|
||||
// unconditional delete could evict a concurrently pending handshake for
|
||||
// the same address.
|
||||
if cur, ok := hm.vpnIps[addr]; ok && cur.hostinfo == hostinfo {
|
||||
delete(hm.vpnIps, addr)
|
||||
}
|
||||
@@ -683,7 +670,6 @@ func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
v, cs.GetCredential,
|
||||
hm.certVerifier(), func() (uint32, error) { return hm.allocateIndex(hh) },
|
||||
true, header.HandshakeIXPSK0,
|
||||
hm.laneAdvert(),
|
||||
)
|
||||
if err != nil {
|
||||
hm.f.l.Error("Failed to create handshake machine",
|
||||
@@ -707,35 +693,6 @@ func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
return true
|
||||
}
|
||||
|
||||
// laneAdvert returns our multiport advert for a handshake payload, or nil
|
||||
// when multiport is disabled (which keeps the payload byte-identical to
|
||||
// vanilla).
|
||||
func (hm *HandshakeManager) laneAdvert() *handshake.LaneDetails {
|
||||
if hm.config.laneCount == 0 {
|
||||
return nil
|
||||
}
|
||||
return &handshake.LaneDetails{
|
||||
PortCount: uint32(hm.config.lanePortCount),
|
||||
BasePort: uint32(hm.config.laneBasePort),
|
||||
TxLanes: uint32(hm.config.laneCount),
|
||||
}
|
||||
}
|
||||
|
||||
// maybeAllocLanes sets up the multiport lanes for a just-completed tunnel. Must
|
||||
// run before the hostinfo becomes visible in the hostmap: the data plane reads
|
||||
// hostinfo.lanes without synchronizing on it. The sessions themselves are derived
|
||||
// later, on the first packet that needs each one.
|
||||
func (hm *HandshakeManager) maybeAllocLanes(hostinfo *HostInfo, result *handshake.Result) {
|
||||
if hm.config.laneCount == 0 || result.PeerPortCount == 0 {
|
||||
return
|
||||
}
|
||||
if len(hm.f.myVpnAddrs) == 0 || len(hostinfo.vpnAddrs) == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
hostinfo.lanes = newLaneSet(result, hm.config.laneCount, hostinfo.ConnectionState.epoch, hm.f.myVpnAddrs[0], hostinfo.vpnAddrs[0])
|
||||
}
|
||||
|
||||
// beginHandshake handles an incoming handshake packet that doesn't match any
|
||||
// existing pending handshake. It creates a new responder Machine and processes
|
||||
// the first message.
|
||||
@@ -754,7 +711,6 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
v, cs.GetCredential,
|
||||
hm.certVerifier(), func() (uint32, error) { return generateIndex(f.l) },
|
||||
false, header.HandshakeIXPSK0,
|
||||
hm.laneAdvert(),
|
||||
)
|
||||
if err != nil {
|
||||
f.l.Error("Failed to create handshake machine", "from", via, "error", err)
|
||||
@@ -763,7 +719,12 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
f.l.Error("Failed to process handshake packet", "from", via, "error", err)
|
||||
level := slog.LevelError
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
level = slog.LevelDebug
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
f.l.Log(context.Background(), level, "Failed to process handshake packet", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
@@ -811,10 +772,6 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
},
|
||||
}
|
||||
|
||||
// Lanes are allocated before the log line so it can report what was actually
|
||||
// negotiated, and must in any case be in place before CheckAndComplete below.
|
||||
hm.maybeAllocLanes(hostinfo, result)
|
||||
|
||||
msg := "Handshake message received"
|
||||
if !anyVpnAddrsInCommon {
|
||||
msg = "Handshake message received, but no vpnNetworks in common."
|
||||
@@ -829,7 +786,6 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
"initiatorIndex", result.RemoteIndex,
|
||||
"responderIndex", result.LocalIndex,
|
||||
"handshake", m{"stage": uint64(machine.MessageIndex()), "style": header.SubTypeName(header.Handshake, machine.Subtype())},
|
||||
laneLogAttr(hm.config.laneCount, hostinfo.lanes),
|
||||
)
|
||||
|
||||
// packet aliases the listener's incoming buffer, so this copy must stay.
|
||||
@@ -900,6 +856,9 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
|
||||
response, result, err := machine.ProcessPacket(nil, packet)
|
||||
if err != nil {
|
||||
if errors.Is(err, cert.ErrBlockListed) {
|
||||
hm.metricRejectedBlocklisted.Inc(1)
|
||||
}
|
||||
// Recoverable errors are routine noise, log at Debug. Fatal errors get a Warn.
|
||||
if machine.Failed() {
|
||||
f.l.Warn("Failed to process handshake packet, abandoning",
|
||||
@@ -993,25 +952,18 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
|
||||
hm.DeleteHostInfo(hostinfo)
|
||||
hm.StartHandshake(hostinfo.vpnAddrs[0], func(newHH *HandshakeHostInfo) {
|
||||
newHH.hostinfo.remotes = hostinfo.remotes
|
||||
newHH.hostinfo.remotes.BlockRemote(via)
|
||||
newHH.packetStore = hh.packetStore
|
||||
hh.packetStore = []*cachedPacket{}
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
f.sendCloseTunnel(hostinfo)
|
||||
})
|
||||
// sendCloseTunnel may take the hostmap lock, so it must not run under the handshake
|
||||
// manager lock that StartHandshake holds around the callback.
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
f.sendCloseTunnel(hostinfo)
|
||||
return
|
||||
}
|
||||
|
||||
duration := time.Since(hh.startTime).Nanoseconds()
|
||||
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
hostinfo.buildNetworks(f.myVpnNetworksTable, remoteCert.Certificate)
|
||||
|
||||
// Lanes are allocated before the log line so it can report what was actually
|
||||
// negotiated, and must in any case be in place before Complete below.
|
||||
hm.maybeAllocLanes(hostinfo, result)
|
||||
|
||||
msg := "Handshake message received"
|
||||
if !anyVpnAddrsInCommon {
|
||||
msg = "Handshake message received, but no vpnNetworks in common."
|
||||
@@ -1028,9 +980,11 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
"handshake", m{"stage": uint64(machine.MessageIndex()), "style": header.SubTypeName(header.Handshake, machine.Subtype())},
|
||||
"durationNs", duration,
|
||||
"sentCachedPackets", len(hh.packetStore),
|
||||
laneLogAttr(hm.config.laneCount, hostinfo.lanes),
|
||||
)
|
||||
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
hostinfo.buildNetworks(f.myVpnNetworksTable, remoteCert.Certificate)
|
||||
|
||||
hm.Complete(hostinfo, f)
|
||||
|
||||
if len(hh.packetStore) > 0 {
|
||||
@@ -1139,10 +1093,7 @@ func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hos
|
||||
|
||||
if !via.IsRelayed {
|
||||
fields := append(logFields, "from", via)
|
||||
// Reply from the socket the handshake arrived on so the initiator sees
|
||||
// the source port it targeted. Identical to f.outside under vanilla
|
||||
// config (all writers share one port); required for multiport lanes.
|
||||
err := f.writers[via.SockIdx].WriteTo(msg, via.UdpAddr)
|
||||
err := f.outside.WriteTo(msg, via.UdpAddr)
|
||||
if err != nil {
|
||||
f.l.Error("Failed to send handshake message", append(fields, "error", err)...)
|
||||
} else {
|
||||
|
||||
+156
-2
@@ -1,16 +1,22 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
ct "github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func Test_NewHandshakeManagerVpnIp(t *testing.T) {
|
||||
@@ -42,8 +48,6 @@ func Test_NewHandshakeManagerVpnIp(t *testing.T) {
|
||||
i2 := blah.StartHandshake(ip, nil)
|
||||
assert.Same(t, i, i2)
|
||||
|
||||
i.remotes = NewRemoteList([]netip.Addr{}, nil)
|
||||
|
||||
// Adding something to pending should not affect the main hostmap
|
||||
assert.Empty(t, mainHM.Hosts)
|
||||
|
||||
@@ -235,3 +239,153 @@ func TestHandleIncomingDispatch(t *testing.T) {
|
||||
assert.Empty(t, hm.indexes, "orphan stage-2 must not create state")
|
||||
})
|
||||
}
|
||||
|
||||
func TestBlocklistedHandshakeLogLevelAndCounter(t *testing.T) {
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil)
|
||||
pool := ct.NewTestCAPool(ca)
|
||||
|
||||
newCredential := func(name, network string) (cert.Certificate, *handshake.Credential) {
|
||||
c, _, rawKey, _ := ct.NewTestCert(cert.Version2, cert.Curve_CURVE25519, ca, caKey,
|
||||
name, ca.NotBefore(), ca.NotAfter(), []netip.Prefix{netip.MustParsePrefix(network)}, nil, nil)
|
||||
privateKey, _, _, err := cert.UnmarshalPrivateKeyFromPEM(rawKey)
|
||||
require.NoError(t, err)
|
||||
certBytes, err := c.MarshalForHandshakes()
|
||||
require.NoError(t, err)
|
||||
cipherSuite := noise.NewCipherSuite(noise.DH25519, noise.CipherChaChaPoly, noise.HashSHA256)
|
||||
return c, handshake.NewCredential(c, certBytes, privateKey, cipherSuite)
|
||||
}
|
||||
|
||||
initiatorCert, initiatorCredential := newCredential("initiator", "10.0.0.1/24")
|
||||
responderCert, responderCredential := newCredential("responder", "10.0.0.2/24")
|
||||
fingerprint, err := initiatorCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(fingerprint)
|
||||
|
||||
initiator, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return initiatorCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return pool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 1, nil }, true, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
packet, err := initiator.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
handler := &capturingHandler{}
|
||||
logger := slog.New(handler)
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{initiatingVersion: cert.Version2, v2Credential: responderCredential})
|
||||
pki.caPool.Store(pool)
|
||||
hm := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
hm.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
hm.f = &Interface{pki: pki, l: logger}
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("198.51.100.7:4242")}
|
||||
|
||||
hm.beginHandshake(via, packet, nil)
|
||||
entry := findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelDebug, entry.Level)
|
||||
require.ErrorIs(t, entry.Attrs["error"].(error), cert.ErrBlockListed)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
handler.entries = nil
|
||||
hm.beginHandshake(via, nil, nil)
|
||||
entry = findEntry(t, handler.entries, "Failed to process handshake packet")
|
||||
assert.Equal(t, slog.LevelError, entry.Level)
|
||||
assert.Equal(t, int64(1), hm.metricRejectedBlocklisted.Count())
|
||||
|
||||
// The initiator sees the same rejection in continueHandshake, after a
|
||||
// responder has accepted its first packet and sent a valid reply.
|
||||
cleanPool := ct.NewTestCAPool(ca)
|
||||
responder, err := handshake.NewMachine(cert.Version2,
|
||||
func(cert.Version) *handshake.Credential { return responderCredential },
|
||||
func(c cert.Certificate) (*cert.CachedCertificate, error) {
|
||||
return cleanPool.VerifyCertificate(time.Now(), c)
|
||||
},
|
||||
func() (uint32, error) { return 2, nil }, false, header.HandshakeIXPSK0)
|
||||
require.NoError(t, err)
|
||||
response, _, err := responder.ProcessPacket(nil, packet)
|
||||
require.NoError(t, err)
|
||||
|
||||
responderFingerprint, err := responderCert.Fingerprint()
|
||||
require.NoError(t, err)
|
||||
pool.BlocklistFingerprint(responderFingerprint)
|
||||
|
||||
initiatingHM := NewHandshakeManager(logger, nil, nil, nil, defaultHandshakeConfig)
|
||||
initiatingHM.metricRejectedBlocklisted = metrics.NewCounter()
|
||||
initiatingHM.f = &Interface{l: logger}
|
||||
hh := &HandshakeHostInfo{
|
||||
machine: initiator,
|
||||
hostinfo: &HostInfo{localIndexId: 1, vpnAddrs: []netip.Addr{netip.MustParseAddr("10.0.0.2")}},
|
||||
}
|
||||
initiatingHM.indexes[1] = hh
|
||||
via.IsRelayed = true // skip the remote allow list before certificate validation
|
||||
initiatingHM.continueHandshake(via, hh, response)
|
||||
assert.Equal(t, int64(1), initiatingHM.metricRejectedBlocklisted.Count())
|
||||
}
|
||||
|
||||
// Test_PendingHandshakeHasRemotes covers create-tunnel -address: a pending hostinfo must already
|
||||
// carry its RemoteList when StartHandshake runs its callback, so SetRemote there, before the
|
||||
// handshake loop has run, is safe and the address becomes one the handshake is sent to.
|
||||
func Test_PendingHandshakeHasRemotes(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
mainHM := newHostMap(l)
|
||||
preferredRanges := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&preferredRanges)
|
||||
|
||||
hm := NewHandshakeManager(l, mainHM, newTestLighthouse(), &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
|
||||
vpnIp := netip.MustParseAddr("172.1.1.2")
|
||||
remote := netip.MustParseAddrPort("192.168.1.9:4242")
|
||||
|
||||
hi := hm.StartHandshake(vpnIp, func(hh *HandshakeHostInfo) {
|
||||
require.NotNil(t, hh.hostinfo.remotes, "a pending handshake must never be without its RemoteList")
|
||||
hh.hostinfo.SetRemote(remote)
|
||||
})
|
||||
assert.Contains(t, hi.remotes.CopyAddrs(preferredRanges), remote, "the handshake must be sent to the supplied remote")
|
||||
assert.Equal(t, remote, hi.GetRemote())
|
||||
|
||||
// A RemoteList keeps one learned address per host, so a second remote replaces the
|
||||
// first — the same behaviour change-remote has on an established tunnel.
|
||||
other := netip.MustParseAddrPort("192.168.1.10:4242")
|
||||
hi.SetRemote(other)
|
||||
assert.Equal(t, []netip.AddrPort{other}, hi.remotes.CopyAddrs(preferredRanges))
|
||||
assert.Equal(t, other, hi.GetRemote())
|
||||
}
|
||||
|
||||
// newRemotesRaceFixture builds a handshake manager with an established tunnel to vpnAddr whose
|
||||
// RemoteList is the lighthouse's cached list, the state every teardown-during-handshake race starts from.
|
||||
func newRemotesRaceFixture(t *testing.T, vpnAddr netip.Addr) (*HandshakeManager, *Interface, *HostInfo) {
|
||||
t.Helper()
|
||||
l := test.NewLogger()
|
||||
mainHM := newHostMap(l)
|
||||
preferredRanges := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&preferredRanges)
|
||||
|
||||
lh := newTestLighthouse()
|
||||
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
|
||||
hm.f = f
|
||||
|
||||
established := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{vpnAddr},
|
||||
localIndexId: 1,
|
||||
remoteIndexId: 101,
|
||||
remotes: lh.QueryCache([]netip.Addr{vpnAddr}),
|
||||
HandshakePacket: map[uint8][]byte{},
|
||||
}
|
||||
mainHM.Lock()
|
||||
mainHM.unlockedAddHostInfo(established, f)
|
||||
mainHM.Unlock()
|
||||
|
||||
return hm, f, established
|
||||
}
|
||||
|
||||
// With no handshake pending, tearing down the last tunnel still evicts the list.
|
||||
func Test_CloseTunnelEvictsWithoutPendingHandshake(t *testing.T) {
|
||||
vpnAddr := netip.MustParseAddr("172.1.1.2")
|
||||
_, f, established := newRemotesRaceFixture(t, vpnAddr)
|
||||
|
||||
f.closeTunnel(established)
|
||||
assert.NotContains(t, f.hostMap.Hosts, vpnAddr)
|
||||
assert.NotContains(t, f.lightHouse.addrMap, vpnAddr)
|
||||
}
|
||||
+20
-51
@@ -8,34 +8,27 @@ import (
|
||||
)
|
||||
|
||||
//Version 1 header:
|
||||
// 0 31
|
||||
// |------------------------------------------------------------------------------------|
|
||||
// | Version (uint4) | Type (uint4) | Subtype (uint8) | Reserved (uint8) | Lane (uint8) | 32
|
||||
// |------------------------------------------------------------------------------------|
|
||||
// | Remote index (uint32) | 64
|
||||
// |------------------------------------------------------------------------------------|
|
||||
// | Message counter | 96
|
||||
// | (uint64) | 128
|
||||
// |------------------------------------------------------------------------------------|
|
||||
// | payload... |
|
||||
//
|
||||
// Lane is the multiport lane index, carved out of the low 8 bits of what was a
|
||||
// single Reserved (uint16) before multiport. Lane 0 is the base tunnel, which is
|
||||
// what every sender that does not know about lanes emits and what every non-lane
|
||||
// packet — handshakes, lighthouse, relays, close — carries, so the field is
|
||||
// compatible in both directions with a peer that has never heard of it. The
|
||||
// remaining 8 bits stay reserved and are always sent as zero. The H struct still
|
||||
// holds the pair as one Reserved field; use H.Lane and EncodeLane to reach the
|
||||
// low byte.
|
||||
//
|
||||
// Lane is part of the AEAD's associated data, so a lane index cannot be altered
|
||||
// in flight: a packet decrypts on the lane it claims or not at all.
|
||||
// 0 31
|
||||
// |-----------------------------------------------------------------------|
|
||||
// | Version (uint4) | Type (uint4) | Subtype (uint8) | Reserved (uint16) | 32
|
||||
// |-----------------------------------------------------------------------|
|
||||
// | Remote index (uint32) | 64
|
||||
// |-----------------------------------------------------------------------|
|
||||
// | Message counter | 96
|
||||
// | (uint64) | 128
|
||||
// |-----------------------------------------------------------------------|
|
||||
// | payload... |
|
||||
|
||||
type m = map[string]any
|
||||
|
||||
const (
|
||||
Version uint8 = 1
|
||||
Len = 16
|
||||
|
||||
// MaxOverhead is the most a payload grows on its way to the underlay.
|
||||
// A relayed packet has two headers and two AEAD tags, one for the inner tunnel and another for the relay tunnel.
|
||||
// Every supported cipher (today) has a 16 byte tag.
|
||||
MaxOverhead = 2 * (Len + 16)
|
||||
)
|
||||
|
||||
type MessageType uint8
|
||||
@@ -69,18 +62,8 @@ const (
|
||||
const (
|
||||
TestRequest MessageSubType = 0
|
||||
TestReply MessageSubType = 1
|
||||
// LaneProbe is sent on a multiport lane to prove the lane's 5-tuple is
|
||||
// usable; LaneProbeAck answers it on the base tunnel.
|
||||
LaneProbe MessageSubType = 2
|
||||
LaneProbeAck MessageSubType = 3
|
||||
)
|
||||
|
||||
// MaxLane is the largest lane index the header can carry.
|
||||
const MaxLane = 0xff
|
||||
|
||||
// laneMask covers the bits of Reserved that hold the lane index.
|
||||
const laneMask uint16 = 0x00ff
|
||||
|
||||
const (
|
||||
HandshakeIXPSK0 MessageSubType = 0
|
||||
HandshakeXXPSK0 MessageSubType = 1
|
||||
@@ -89,10 +72,8 @@ const (
|
||||
var ErrHeaderTooShort = errors.New("header is too short")
|
||||
|
||||
var subTypeTestMap = map[MessageSubType]string{
|
||||
TestRequest: "testRequest",
|
||||
TestReply: "testReply",
|
||||
LaneProbe: "laneProbe",
|
||||
LaneProbeAck: "laneProbeAck",
|
||||
TestRequest: "testRequest",
|
||||
TestReply: "testReply",
|
||||
}
|
||||
|
||||
var subTypeNoneMap = map[MessageSubType]string{0: "none"}
|
||||
@@ -124,16 +105,10 @@ type H struct {
|
||||
// Encode uses the provided byte array to encode the provided header values into.
|
||||
// Byte array must be capped higher than HeaderLen or this will panic
|
||||
func Encode(b []byte, v uint8, t MessageType, st MessageSubType, ri uint32, c uint64) []byte {
|
||||
return EncodeLane(b, v, t, st, ri, c, 0)
|
||||
}
|
||||
|
||||
// EncodeLane is Encode with an explicit multiport lane index, which is carried
|
||||
// in the low 8 bits of Reserved.
|
||||
func EncodeLane(b []byte, v uint8, t MessageType, st MessageSubType, ri uint32, c uint64, lane uint8) []byte {
|
||||
b = b[:Len]
|
||||
b[0] = v<<4 | byte(t&0x0f)
|
||||
b[1] = byte(st)
|
||||
binary.BigEndian.PutUint16(b[2:4], uint16(lane))
|
||||
binary.BigEndian.PutUint16(b[2:4], 0)
|
||||
binary.BigEndian.PutUint32(b[4:8], ri)
|
||||
binary.BigEndian.PutUint64(b[8:16], c)
|
||||
return b
|
||||
@@ -166,13 +141,7 @@ func (h *H) Encode(b []byte) ([]byte, error) {
|
||||
return nil, errors.New("nil header")
|
||||
}
|
||||
|
||||
return EncodeLane(b, h.Version, h.Type, h.Subtype, h.RemoteIndex, h.MessageCounter, h.Lane()), nil
|
||||
}
|
||||
|
||||
// Lane returns the multiport lane index carried in Reserved. Lane 0 is the base
|
||||
// tunnel, which is what any sender that does not know about lanes will report.
|
||||
func (h *H) Lane() uint8 {
|
||||
return uint8(h.Reserved & laneMask)
|
||||
return Encode(b, h.Version, h.Type, h.Subtype, h.RemoteIndex, h.MessageCounter), nil
|
||||
}
|
||||
|
||||
// Parse is a helper function to parses given bytes into new Header struct
|
||||
@@ -232,7 +201,7 @@ func IsValidSubType(t MessageType, s MessageSubType) bool {
|
||||
case Handshake:
|
||||
return s == HandshakeIXPSK0
|
||||
case Test:
|
||||
return s == TestReply || s == TestRequest || s == LaneProbe || s == LaneProbeAck
|
||||
return s == TestReply || s == TestRequest
|
||||
case Control, CloseTunnel, RecvError, LightHouse:
|
||||
return s == 0
|
||||
default:
|
||||
|
||||
+1
-25
@@ -52,28 +52,6 @@ func TestParse(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestEncodeLane(t *testing.T) {
|
||||
b := EncodeLane(make([]byte, Len), Version, Message, MessageNone, 10, 9, 3)
|
||||
assert.Equal(t, []byte{0x11, 0x0, 0x0, 0x3}, b[:4])
|
||||
|
||||
h := &H{}
|
||||
require.NoError(t, h.Parse(b))
|
||||
assert.Equal(t, uint16(3), h.Reserved)
|
||||
assert.Equal(t, uint8(3), h.Lane())
|
||||
|
||||
// Encode is EncodeLane on the base tunnel, and the H method round trips the lane.
|
||||
assert.Equal(t,
|
||||
EncodeLane(make([]byte, Len), Version, Message, MessageNone, 10, 9, 0),
|
||||
Encode(make([]byte, Len), Version, Message, MessageNone, 10, 9))
|
||||
|
||||
rt, err := h.Encode(make([]byte, Len))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, b, rt)
|
||||
|
||||
// Only the low 8 bits of Reserved are the lane.
|
||||
assert.Equal(t, uint8(0x2a), (&H{Reserved: 0xff2a}).Lane())
|
||||
}
|
||||
|
||||
func TestTypeName(t *testing.T) {
|
||||
assert.Equal(t, "test", TypeName(Test))
|
||||
assert.Equal(t, "test", (&H{Type: Test}).TypeName())
|
||||
@@ -149,9 +127,7 @@ func TestIsValidSubType(t *testing.T) {
|
||||
|
||||
assert.True(t, IsValidSubType(Test, TestRequest))
|
||||
assert.True(t, IsValidSubType(Test, TestReply))
|
||||
assert.True(t, IsValidSubType(Test, LaneProbe))
|
||||
assert.True(t, IsValidSubType(Test, LaneProbeAck))
|
||||
assert.False(t, IsValidSubType(Test, 4))
|
||||
assert.False(t, IsValidSubType(Test, 2))
|
||||
|
||||
// These types only ever carry subtype 0.
|
||||
for _, mt := range []MessageType{Control, CloseTunnel, RecvError, LightHouse} {
|
||||
|
||||
+7
-76
@@ -6,7 +6,6 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/netip"
|
||||
"slices"
|
||||
"sync"
|
||||
@@ -18,7 +17,6 @@ import (
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
)
|
||||
|
||||
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
|
||||
@@ -278,11 +276,6 @@ type HostInfo struct {
|
||||
// This value will be behind against actual tunnel utilization in the hot path.
|
||||
// This should only be used by the ConnectionManagers ticker routine.
|
||||
lastUsed time.Time
|
||||
|
||||
// lanes holds this tunnel's multiport lane sessions. Allocated when the
|
||||
// handshake completes if both sides advertised multiport, nil otherwise.
|
||||
// Immutable once the hostinfo is published to the data plane.
|
||||
lanes *laneSet
|
||||
}
|
||||
|
||||
type ViaSender struct {
|
||||
@@ -290,11 +283,6 @@ type ViaSender struct {
|
||||
relayHI *HostInfo // relayHI is the host info object of the relay
|
||||
relay *Relay // relay contains the rest of the relay information, including the PeerIP of the host trying to communicate with us.
|
||||
IsRelayed bool // IsRelayed is true if the packet was sent through a relay
|
||||
|
||||
// SockIdx is the local socket (Interface.writers index) the packet
|
||||
// arrived on. Replies that must originate from the same 4-tuple egress
|
||||
// f.writers[SockIdx].
|
||||
SockIdx int
|
||||
}
|
||||
|
||||
func (v ViaSender) String() string {
|
||||
@@ -328,9 +316,9 @@ type cachedPacketMetrics struct {
|
||||
func NewHostMapFromConfig(l *slog.Logger, c *config.C) *HostMap {
|
||||
hm := newHostMap(l)
|
||||
|
||||
hm.reload(c, true)
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
hm.reload(c, false)
|
||||
hm.reload(c, true, nil)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
hm.reload(c, false, r)
|
||||
})
|
||||
|
||||
l.Info("Main HostMap created", "preferredRanges", hm.GetPreferredRanges())
|
||||
@@ -349,7 +337,8 @@ func newHostMap(l *slog.Logger) *HostMap {
|
||||
}
|
||||
}
|
||||
|
||||
func (hm *HostMap) reload(c *config.C, initial bool) {
|
||||
// r is nil on the initial load
|
||||
func (hm *HostMap) reload(c *config.C, initial bool, r *config.Reload) {
|
||||
if initial || c.HasChanged("preferred_ranges") {
|
||||
var preferredRanges []netip.Prefix
|
||||
rawPreferredRanges := c.GetStringSlice("preferred_ranges", []string{})
|
||||
@@ -360,8 +349,9 @@ func (hm *HostMap) reload(c *config.C, initial bool) {
|
||||
if err != nil {
|
||||
hm.l.Warn("Failed to parse preferred ranges, ignoring",
|
||||
"error", err,
|
||||
"range", rawPreferredRanges,
|
||||
"range", rawPreferredRange,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -484,9 +474,6 @@ func (hm *HostMap) unlockedMakePrimary(hostinfo *HostInfo) bool {
|
||||
// any tunnel to the peer), which the caller uses to decide whether to clear learned lighthouse
|
||||
// state and disestablish relays.
|
||||
func (hm *HostMap) unlockedDeleteHostInfo(hostinfo *HostInfo) bool {
|
||||
// Lane sessions hang off this hostinfo, so deleting it takes them with it
|
||||
// and there is nothing extra to unwind here.
|
||||
|
||||
// Remove this hostinfo from each of its address lists. The lists are independent, so a
|
||||
// sibling is never promoted to an address it does not own and no other list is touched.
|
||||
final := true
|
||||
@@ -943,59 +930,3 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
|
||||
|
||||
return li
|
||||
}
|
||||
|
||||
// Utility functions
|
||||
|
||||
func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
|
||||
//FIXME: This function is pretty garbage
|
||||
var finalAddrs []netip.Addr
|
||||
ifaces, _ := net.Interfaces()
|
||||
for _, i := range ifaces {
|
||||
allow := allowList.AllowName(i.Name)
|
||||
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||
l.Log(context.Background(), logging.LevelTrace, "localAllowList.AllowName",
|
||||
"interfaceName", i.Name,
|
||||
"allow", allow,
|
||||
)
|
||||
}
|
||||
|
||||
if !allow {
|
||||
continue
|
||||
}
|
||||
addrs, _ := i.Addrs()
|
||||
for _, rawAddr := range addrs {
|
||||
var addr netip.Addr
|
||||
switch v := rawAddr.(type) {
|
||||
case *net.IPNet:
|
||||
//continue
|
||||
addr, _ = netip.AddrFromSlice(v.IP)
|
||||
case *net.IPAddr:
|
||||
addr, _ = netip.AddrFromSlice(v.IP)
|
||||
}
|
||||
|
||||
if !addr.IsValid() {
|
||||
if l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
l.Debug("addr was invalid", "localAddr", rawAddr)
|
||||
}
|
||||
continue
|
||||
}
|
||||
addr = addr.Unmap()
|
||||
|
||||
if addr.IsLoopback() == false && addr.IsLinkLocalUnicast() == false {
|
||||
isAllowed := allowList.Allow(addr)
|
||||
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||
l.Log(context.Background(), logging.LevelTrace, "localAllowList.Allow",
|
||||
"localAddr", addr,
|
||||
"allowed", isAllowed,
|
||||
)
|
||||
}
|
||||
if !isAllowed {
|
||||
continue
|
||||
}
|
||||
|
||||
finalAddrs = append(finalAddrs, addr)
|
||||
}
|
||||
}
|
||||
}
|
||||
return finalAddrs
|
||||
}
|
||||
@@ -447,3 +447,16 @@ func TestHostInfo_markOutOnly(t *testing.T) {
|
||||
assert.True(t, h.markOut(6), "a relayed send must not consume the epoch edge")
|
||||
assert.False(t, h.markOut(6))
|
||||
}
|
||||
|
||||
// A preferred range that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestHostMap_reloadBadPreferredRangeFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("preferred_ranges: [10.0.0.0/8]\n"))
|
||||
hm := NewHostMapFromConfig(l, c)
|
||||
|
||||
res := c.ReloadConfigString("preferred_ranges: [10.0.0.0/8, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/8")}, hm.GetPreferredRanges())
|
||||
}
|
||||
@@ -10,12 +10,14 @@ import (
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/iputil"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
)
|
||||
|
||||
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, tx *txQueue, rejectBuf []byte, q int, localCache firewall.ConntrackCache) {
|
||||
func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.ParsedPacket, nb []byte, sendBatch *batch.SendBatch, rejectBuf []byte, q int, localCache firewall.ConntrackCache) {
|
||||
// borrowed: pkt.Bytes is owned by the originating tio.Queue and is
|
||||
// only valid until the next Read on that queue. Every consumer below
|
||||
// (parse, self-forward, handshake cache, sendInsideMessage) reads it
|
||||
@@ -110,7 +112,7 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
|
||||
|
||||
dropReason := f.firewall.Drop(fwPacket.Packet, false, hostinfo, f.pki.GetCAPool(), localCache)
|
||||
if dropReason == nil {
|
||||
f.sendInsideMessage(hostinfo, pkt, &fwPacket.Packet, nb, tx)
|
||||
f.sendInsideMessage(hostinfo, pkt, nb, sendBatch)
|
||||
} else {
|
||||
f.rejectInside(packet, rejectBuf, q)
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
@@ -122,13 +124,13 @@ func (f *Interface) consumeInsidePacket(pkt tio.Packet, fwPacket *firewall.Parse
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) sendInsideEncrypt(hostinfo *HostInfo, ci *ConnectionState, lane uint8, seg, scratch, nb []byte) []byte {
|
||||
func (f *Interface) sendInsideEncrypt(hostinfo *HostInfo, ci *ConnectionState, seg, scratch, nb []byte) []byte {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Lock()
|
||||
}
|
||||
c := ci.messageCounter.Add(1)
|
||||
|
||||
out := header.EncodeLane(scratch, header.Version, header.Message, 0, hostinfo.remoteIndexId, c, lane)
|
||||
out := header.Encode(scratch, header.Version, header.Message, 0, hostinfo.remoteIndexId, c)
|
||||
|
||||
out, encErr := ci.eKey.EncryptDanger(out, out, seg, c, nb)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
@@ -153,19 +155,12 @@ func (f *Interface) sendInsideEncrypt(hostinfo *HostInfo, ci *ConnectionState, l
|
||||
// kernel-supplied superpacket bytes never get written into a separate
|
||||
// scratch arena: SegmentSuperpacket builds each segment's plaintext in
|
||||
// segScratch[:segLen] in turn, and we encrypt directly into a fresh SendBatch slot.
|
||||
//
|
||||
// When this flow has a usable multiport lane to this peer, the direct path swaps
|
||||
// to that lane's session and socket below. Relay and base traffic stays on
|
||||
// tx.base (socket 0).
|
||||
func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, fwPacket *firewall.Packet, nb []byte, tx *txQueue) {
|
||||
func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, nb []byte, sendBatch *batch.SendBatch) {
|
||||
ci := hostinfo.ConnectionState
|
||||
if ci.eKey == nil {
|
||||
return
|
||||
}
|
||||
|
||||
// Base and relay traffic stays on socket 0; the direct path may swap to tx.lane below.
|
||||
sendBatch := tx.base
|
||||
|
||||
// One traffic-out mark covers every segment of the superpacket; doing it
|
||||
// per segment in sendInsideEncrypt paid an atomic store up to ~45 extra
|
||||
// times per TSO packet, inside writeLock under boring crypto.
|
||||
@@ -204,10 +199,10 @@ func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, fwPack
|
||||
}
|
||||
|
||||
err = tio.SegmentSuperpacket(pkt, func(seg []byte) error {
|
||||
//relay header + header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305) + relay tag
|
||||
scratch := sendBatch.Reserve(header.Len + header.Len + len(seg) + 16 + 16)
|
||||
//relay header + header + plaintext + AEAD tag + relay tag
|
||||
scratch := sendBatch.Reserve(len(seg) + header.MaxOverhead)
|
||||
|
||||
innerPacket := f.sendInsideEncrypt(hostinfo, ci, 0, seg, scratch[header.Len:], nb)
|
||||
innerPacket := f.sendInsideEncrypt(hostinfo, ci, seg, scratch[header.Len:], nb)
|
||||
if innerPacket == nil {
|
||||
return nil
|
||||
}
|
||||
@@ -228,28 +223,11 @@ func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, fwPack
|
||||
return
|
||||
}
|
||||
|
||||
// Direct path: prefer this flow's multiport lane once it is proven usable.
|
||||
// txLaneForFlow hands back the lane's session and destination together, so
|
||||
// there is no window where one is set and the other is not, and a demotion
|
||||
// drops us back onto the base tunnel on the very next packet.
|
||||
//
|
||||
// A miss is also how a lane gets re-probed after a demotion: txLane raises
|
||||
// demand, which the connection manager's next tick on this tunnel picks up.
|
||||
// Until the lane is up the traffic rides the base tunnel, the same fallback
|
||||
// a demoted lane uses.
|
||||
lane := uint8(0)
|
||||
if s, lci, laneRemote := hostinfo.lanes.txLaneForFlow(fwPacket); lci != nil {
|
||||
lane = uint8(s)
|
||||
ci = lci
|
||||
remote = laneRemote
|
||||
sendBatch = tx.laneBatch(f, s)
|
||||
}
|
||||
|
||||
err := tio.SegmentSuperpacket(pkt, func(seg []byte) error {
|
||||
// header + plaintext + AEAD tag (16 bytes for both AES-GCM and ChaCha20-Poly1305)
|
||||
scratch := sendBatch.Reserve(header.Len + len(seg) + 16)
|
||||
|
||||
out := f.sendInsideEncrypt(hostinfo, ci, lane, seg, scratch, nb)
|
||||
out := f.sendInsideEncrypt(hostinfo, ci, seg, scratch, nb)
|
||||
if out == nil {
|
||||
return nil
|
||||
}
|
||||
@@ -538,61 +516,39 @@ func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, noc
|
||||
return
|
||||
}
|
||||
|
||||
err = f.writers[f.egressSock(q)].WriteTo(toSend, via.GetRemote())
|
||||
err = f.writers[q].WriteTo(toSend, via.GetRemote())
|
||||
if err != nil {
|
||||
via.logger(f.l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpRelayTxErrLimiter); ok {
|
||||
via.logger(l).Info("Failed to WriteTo in sendVia", "error", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// egressSock picks the socket a tunnel packet leaves from.
|
||||
//
|
||||
// Everything that is not lane data plane leaves from the base port: handshakes, keepalives, close packets, rejects and
|
||||
// relay carriers all belong to the base tunnel's 4-tuple, which is the only one a peer's spoof/roam checks and a
|
||||
// vanilla peer's expectations know about. Lane data goes through laneSock instead and never comes here.
|
||||
//
|
||||
// Which socket on the base port doesn't matter — they share an address, so they produce identical packets — so keep to
|
||||
// this routine's own share of the group and leave the rest of it uncontended. Without multiport that is q itself, since
|
||||
// every socket is on the base port.
|
||||
func (f *Interface) egressSock(q int) int {
|
||||
return f.laneSock(q, 0)
|
||||
}
|
||||
|
||||
// laneSock returns the index in writers of a socket bound to lane s's port, for a
|
||||
// routine that reads queue q.
|
||||
//
|
||||
// Under multiport the sockets are laid out port-major — writers[s*routinesPerPort
|
||||
// + r] is the r'th socket on port listen.port+s — so every routine has a sibling
|
||||
// socket on every port and the arithmetic is a lane index away. Routines pick the
|
||||
// sibling matching their own position in their group, which spreads the writers
|
||||
// for one port over that port's whole group rather than funnelling them onto its
|
||||
// first socket. It is a pure function of (q, s), so a flow always leaves from the
|
||||
// same socket and cannot reorder itself across two of them.
|
||||
//
|
||||
// Without multiport there is one port and every socket is on it, so any lane
|
||||
// resolves to q's own socket.
|
||||
func (f *Interface) laneSock(q, s int) int {
|
||||
if !f.multiport {
|
||||
return q
|
||||
}
|
||||
return s*f.routinesPerPort + q%f.routinesPerPort
|
||||
}
|
||||
|
||||
func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType, ci *ConnectionState, hostinfo *HostInfo, remote netip.AddrPort, p, nb, out []byte, q int) {
|
||||
if ci.eKey == nil {
|
||||
return
|
||||
}
|
||||
q = f.egressSock(q)
|
||||
useRelay := !remote.IsValid() && !hostinfo.GetRemote().IsValid()
|
||||
fullOut := out
|
||||
|
||||
// The encrypt appends to out in place and a relayed packet is then wrapped in place,
|
||||
// so out has to fit the whole packet up front or the encrypt reallocates out from under SendVia.
|
||||
// We cap the MTU of tun devices and routes we create ourselves, so only a host that set a bigger MTU than we allow gets here.
|
||||
need := header.Len + len(p) + ci.eKey.Overhead()
|
||||
if useRelay {
|
||||
if len(out) < header.Len {
|
||||
// out always has a capacity of mtu, but not always a length greater than the header.Len.
|
||||
// Grow it to make sure the next operation works.
|
||||
out = out[:header.Len]
|
||||
// The relay tunnel runs the same cipher, and adds its own header and tag
|
||||
need += header.Len + ci.eKey.Overhead()
|
||||
}
|
||||
if cap(out) < need {
|
||||
if l, ok := logging.RateLimited(f.l, f.txOversizeLimiter); ok {
|
||||
hostinfo.logger(l).Error("Dropping outbound packet, out buffer not large enough", "outCap", cap(out), "payloadLen", len(p), "relayed", useRelay)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
fullOut := out
|
||||
if useRelay {
|
||||
// Save a header's worth of data at the front of the 'out' buffer.
|
||||
out = out[header.Len:]
|
||||
out = out[header.Len:header.Len]
|
||||
}
|
||||
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
@@ -639,18 +595,22 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
if remote.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, remote)
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", remote,
|
||||
)
|
||||
}
|
||||
}
|
||||
} else if hr := hostinfo.GetRemote(); hr.IsValid() {
|
||||
err = f.writers[q].WriteTo(out, hr)
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
hostinfo.logger(l).Error("Failed to write outgoing packet",
|
||||
"error", err,
|
||||
"udpAddr", hr,
|
||||
)
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Try to send via a relay
|
||||
|
||||
+107
-194
@@ -24,6 +24,7 @@ import (
|
||||
"github.com/slackhq/nebula/overlay"
|
||||
"github.com/slackhq/nebula/overlay/batch"
|
||||
"github.com/slackhq/nebula/overlay/tio"
|
||||
"github.com/slackhq/nebula/ratelimit"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
@@ -43,22 +44,10 @@ type InterfaceConfig struct {
|
||||
DropLocalBroadcast bool
|
||||
DropMulticast bool
|
||||
routines int
|
||||
// Multiport means the sockets are spread over a range of ports
|
||||
// (listen.port+slot) rather than all sharing listen.port, and that lane
|
||||
// tunnels are negotiated with capable peers.
|
||||
Multiport bool
|
||||
// RoutinesPerPort is how many sockets share each port under multiport, and so
|
||||
// the stride between port slots in writers: writers[s*RoutinesPerPort+r] is
|
||||
// the r'th socket bound to listen.port+s. It is `routines` as configured,
|
||||
// while routines above is that times the number of ports.
|
||||
RoutinesPerPort int
|
||||
// LaneCount is the number of lanes counting the base tunnel as lane 0
|
||||
// (multiport.lanes, clamped to the number of ports bound).
|
||||
LaneCount int
|
||||
MessageMetrics *MessageMetrics
|
||||
version string
|
||||
relayManager *relayManager
|
||||
punchy *Punchy
|
||||
MessageMetrics *MessageMetrics
|
||||
version string
|
||||
relayManager *relayManager
|
||||
punchy *Punchy
|
||||
|
||||
tryPromoteEvery uint32
|
||||
reQueryEvery uint32
|
||||
@@ -99,9 +88,6 @@ type Interface struct {
|
||||
dropLocalBroadcast bool
|
||||
dropMulticast bool
|
||||
routines int
|
||||
multiport bool
|
||||
routinesPerPort int
|
||||
laneCount int
|
||||
disconnectInvalid atomic.Bool
|
||||
closed atomic.Bool
|
||||
// cpuAffinity, when non-empty, names the CPUs each TUN reader goroutine
|
||||
@@ -138,6 +124,12 @@ type Interface struct {
|
||||
// reused (every udp.Conn ListenOut guarantees that ordering).
|
||||
batchers []*batch.MultiCoalescer
|
||||
wg sync.WaitGroup
|
||||
// readers covers just the listenIn and listenOut goroutines, wg also holds the construction token Close releases
|
||||
readers sync.WaitGroup
|
||||
|
||||
udpTxErrLimiter *ratelimit.Limiter // udp direct transmit error log limiter
|
||||
udpRelayTxErrLimiter *ratelimit.Limiter // udp relay transmit error log limiter
|
||||
txOversizeLimiter *ratelimit.Limiter // oversized outbound packet drop log limiter
|
||||
|
||||
// fatalErr holds the first unexpected reader error that caused shutdown.
|
||||
// nil means "no fatal error" (yet)
|
||||
@@ -213,6 +205,19 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
return nil, errors.New("no connection manager")
|
||||
}
|
||||
|
||||
udpTxErrLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
udpRelayTxErrLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
txOversizeLimiter, err := ratelimit.New(1, time.Second)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if c.routines <= 1 {
|
||||
c.PinThreads = false //pinning is not useful unless there's more than one tun reader
|
||||
}
|
||||
@@ -232,9 +237,6 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
dropLocalBroadcast: c.DropLocalBroadcast,
|
||||
dropMulticast: c.DropMulticast,
|
||||
routines: c.routines,
|
||||
multiport: c.Multiport,
|
||||
routinesPerPort: max(c.RoutinesPerPort, 1),
|
||||
laneCount: c.LaneCount,
|
||||
version: c.version,
|
||||
writers: make([]udp.Conn, c.routines),
|
||||
batchers: make([]*batch.MultiCoalescer, c.routines),
|
||||
@@ -248,6 +250,9 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
|
||||
conntrackCacheTimeout: c.ConntrackCacheTimeout,
|
||||
cpuAffinity: c.CpuAffinity,
|
||||
pinThreads: c.PinThreads,
|
||||
udpTxErrLimiter: udpTxErrLimiter,
|
||||
udpRelayTxErrLimiter: udpRelayTxErrLimiter,
|
||||
txOversizeLimiter: txOversizeLimiter,
|
||||
|
||||
metricHandshakes: metrics.GetOrRegisterHistogram("handshakes", nil, metrics.NewExpDecaySample(1028, 0.015)),
|
||||
metricTxDropped: metrics.GetOrRegisterCounter("udp.tx.dropped", nil),
|
||||
@@ -294,10 +299,7 @@ func (f *Interface) activate() error {
|
||||
"fips140Enforced", fips140.Enforced(),
|
||||
)
|
||||
|
||||
// Under multiport each socket has exactly one reader on its own port, so
|
||||
// the shared-port multi-reader capability is irrelevant (and main.go
|
||||
// already hard-errored on unsupported platforms).
|
||||
if f.routines > 1 && !f.multiport && !f.outside.SupportsMultipleReaders() {
|
||||
if f.routines > 1 && !f.outside.SupportsMultipleReaders() {
|
||||
f.routines = 1
|
||||
f.l.Warn("multiple udp readers are not supported on this platform, falling back to a single routine")
|
||||
}
|
||||
@@ -310,11 +312,6 @@ func (f *Interface) activate() error {
|
||||
return err
|
||||
}
|
||||
if len(queues) < f.routines {
|
||||
if f.multiport {
|
||||
// The lane sockets are already bound one-per-routine; shrinking
|
||||
// the routine count would leave bound ports with no reader.
|
||||
return fmt.Errorf("multiport requires %d tun queues, device provided %d", f.routines, len(queues))
|
||||
}
|
||||
// TODO: this clamp is only safe because it is unreachable when the
|
||||
// udp side has multiple readers (linux Queues opens exactly n or
|
||||
// errors; every other platform already clamped routines to 1 above).
|
||||
@@ -346,14 +343,18 @@ func (f *Interface) activate() error {
|
||||
func (f *Interface) run() {
|
||||
// Launch n queues to read packets from udp
|
||||
for i := 0; i < f.routines; i++ {
|
||||
f.readers.Add(1)
|
||||
f.wg.Go(func() {
|
||||
defer f.readers.Done()
|
||||
f.listenOut(i)
|
||||
})
|
||||
}
|
||||
|
||||
// Launch n queues to read packets from tun dev
|
||||
for i := 0; i < f.routines; i++ {
|
||||
f.readers.Add(1)
|
||||
f.wg.Go(func() {
|
||||
defer f.readers.Done()
|
||||
f.listenIn(f.queues[i], i)
|
||||
})
|
||||
}
|
||||
@@ -415,7 +416,7 @@ func (f *Interface) listenOut(i int) {
|
||||
rxc := newRxContext(f, i)
|
||||
|
||||
listener := func(fromUdpAddr netip.AddrPort, payload []byte) {
|
||||
f.readOutsidePackets(ViaSender{UdpAddr: fromUdpAddr, SockIdx: i}, payload, rxc)
|
||||
f.readOutsidePackets(ViaSender{UdpAddr: fromUdpAddr}, payload, rxc)
|
||||
}
|
||||
|
||||
flusher := func() {
|
||||
@@ -457,114 +458,6 @@ func (f *Interface) pinThisThread(i int) {
|
||||
}
|
||||
}
|
||||
|
||||
// txQueue is the per-routine TX state owned by one listenIn goroutine.
|
||||
//
|
||||
// base carries base-session data, relay carriers, and everything on a tunnel
|
||||
// without lanes. It goes out a socket on the base port — egressSock's pick — since
|
||||
// base traffic must keep the base source port or a vanilla peer would see it move
|
||||
// and roam-thrash. lane[s] goes out a socket on listen.port+s and carries traffic
|
||||
// encrypted with lane s's session; lane[0] is base, and the rest are built on the
|
||||
// first packet that picks them, since a routine that never sends on a lane should
|
||||
// not hold a batch for it. Both come from laneSock, so a routine writes to its own
|
||||
// share of each port's socket group.
|
||||
//
|
||||
// Which lane a packet rides comes from its own flow hash, not from this
|
||||
// routine's index. That is deliberate. Which routine reads a flow is the
|
||||
// kernel's decision: it hashes the flow to a tun queue, but it also *learns*
|
||||
// the queue we write that flow's inbound packets to, and prefers what it
|
||||
// learned. So if the lane followed the routine, a peer whose lanes were still
|
||||
// down — every peer, for the first moments of a tunnel — would write all of its
|
||||
// inbound traffic to queue 0, teaching both kernels to steer every flow to
|
||||
// queue 0, and every tunnel would collapse onto lane 0 and stay there for as
|
||||
// long as its flows kept busy. Hashing here makes lane spread independent of
|
||||
// tun steering entirely.
|
||||
//
|
||||
// Every batch borrows arena, so a routine holding a batch per lane still costs
|
||||
// one slab. The arena is reset by flush once every batch over it is drained.
|
||||
//
|
||||
// Several routines can still write to one socket — the sockets on a port are
|
||||
// shared by the routines whose lane arithmetic lands on them — which the underlay
|
||||
// serializes (see batchWriter). Per-flow wire order still holds: a flow is hashed
|
||||
// onto one lane and read by one routine, so nothing else is writing it.
|
||||
type txQueue struct {
|
||||
// q is the queue this state belongs to, which laneSock needs to resolve a lane
|
||||
// to one of its port's sockets.
|
||||
q int
|
||||
base *batch.SendBatch
|
||||
lane []*batch.SendBatch
|
||||
arena *batch.Arena
|
||||
|
||||
// live is every batch built so far, in build order, so base is first: see
|
||||
// flush. Kept as its own slice because lane is mostly nil holes and both
|
||||
// full and flush walk this per read batch.
|
||||
live []txBatch
|
||||
}
|
||||
|
||||
// txBatch is a live batch and the index in writers of the socket it flushes to.
|
||||
type txBatch struct {
|
||||
sb *batch.SendBatch
|
||||
sock int
|
||||
}
|
||||
|
||||
func (f *Interface) newTxQueue(q int) *txQueue {
|
||||
baseSock := f.egressSock(q)
|
||||
arena := batch.NewArena(batch.SendBatchCap * (udp.MTU + 32))
|
||||
base := batch.NewSendBatchSharedArena(f.writers[baseSock], batch.SendBatchCap, arena)
|
||||
|
||||
tx := &txQueue{
|
||||
q: q,
|
||||
base: base,
|
||||
arena: arena,
|
||||
live: []txBatch{{sb: base, sock: baseSock}},
|
||||
}
|
||||
if f.multiport && f.laneCount > 1 {
|
||||
tx.lane = make([]*batch.SendBatch, f.laneCount)
|
||||
tx.lane[0] = base
|
||||
}
|
||||
return tx
|
||||
}
|
||||
|
||||
// laneBatch returns the batch for lane s, building it the first time this
|
||||
// routine sends on that lane. Lanes this queue doesn't cover fall back to base,
|
||||
// which is also lane 0's batch.
|
||||
func (tx *txQueue) laneBatch(f *Interface, s int) *batch.SendBatch {
|
||||
if s <= 0 || s >= len(tx.lane) {
|
||||
return tx.base
|
||||
}
|
||||
sb := tx.lane[s]
|
||||
if sb == nil {
|
||||
sock := f.laneSock(tx.q, s)
|
||||
sb = batch.NewSendBatchSharedArena(f.writers[sock], batch.SendBatchCap, tx.arena)
|
||||
tx.lane[s] = sb
|
||||
tx.live = append(tx.live, txBatch{sb: sb, sock: sock})
|
||||
}
|
||||
return sb
|
||||
}
|
||||
|
||||
// full reports a full sendmmsg worth of work queued across every lane, rather
|
||||
// than on any one of them: the arena is shared, so it is the total that bounds
|
||||
// how much is outstanding.
|
||||
func (tx *txQueue) full() bool {
|
||||
n := 0
|
||||
for _, b := range tx.live {
|
||||
n += b.sb.Len()
|
||||
}
|
||||
return n >= batch.SendBatchCap
|
||||
}
|
||||
|
||||
// flush drains base before the lanes so that when a flow moves from the base
|
||||
// session onto a freshly promoted lane mid-window, its packets still leave this
|
||||
// host in encryption order. Resetting the shared arena is this queue's job,
|
||||
// since no single batch's Flush can know the others are done with it.
|
||||
func (tx *txQueue) flush(f *Interface) {
|
||||
for _, b := range tx.live {
|
||||
if b.sb.Len() > 0 {
|
||||
f.flushSendBatch(b.sb, b.sock)
|
||||
}
|
||||
}
|
||||
tx.arena.Reset()
|
||||
}
|
||||
|
||||
func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
|
||||
// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
|
||||
@@ -573,7 +466,8 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
}
|
||||
|
||||
rejectBuf := make([]byte, mtu)
|
||||
tx := f.newTxQueue(i)
|
||||
arenaSize := batch.SendBatchCap * (udp.MTU + 32)
|
||||
sb := batch.NewSendBatch(f.writers[i], batch.SendBatchCap, arenaSize)
|
||||
fwPacket := &firewall.ParsedPacket{}
|
||||
nb := make([]byte, 12, 12)
|
||||
|
||||
@@ -591,15 +485,15 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
|
||||
}
|
||||
|
||||
for _, pkt := range pkts {
|
||||
f.consumeInsidePacket(pkt, fwPacket, nb, tx, rejectBuf, i, conntrackCache.Get())
|
||||
f.consumeInsidePacket(pkt, fwPacket, nb, sb, rejectBuf, i, conntrackCache.Get())
|
||||
// Flush incrementally once a full sendmmsg batch has
|
||||
// accumulated so the first packets of a deep read drain
|
||||
// hit the wire while the rest are still being encrypted.
|
||||
if tx.full() {
|
||||
tx.flush(f)
|
||||
if sb.Len() >= batch.SendBatchCap {
|
||||
f.flushSendBatch(sb, i)
|
||||
}
|
||||
}
|
||||
tx.flush(f)
|
||||
f.flushSendBatch(sb, i)
|
||||
}
|
||||
|
||||
f.l.Debug("overlay reader is done", "reader", i)
|
||||
@@ -621,10 +515,11 @@ func (f *Interface) flushSendBatch(sb *batch.SendBatch, q int) {
|
||||
|
||||
func (f *Interface) RegisterConfigChangeCallbacks(c *config.C) {
|
||||
c.RegisterReloadCallback(f.reloadFirewall)
|
||||
c.RegisterReloadCallback(f.reloadSendRecvError)
|
||||
c.RegisterReloadCallback(f.reloadAcceptRecvError)
|
||||
c.RegisterReloadCallback(f.reloadDisconnectInvalid)
|
||||
c.RegisterReloadCallback(f.reloadMisc)
|
||||
for _, reload := range []func(*config.C){
|
||||
f.reloadSendRecvError, f.reloadAcceptRecvError, f.reloadDisconnectInvalid, f.reloadMisc,
|
||||
} {
|
||||
c.RegisterReloadCallback(func(c *config.C, _ *config.Reload) { reload(c) })
|
||||
}
|
||||
|
||||
for _, udpConn := range f.writers {
|
||||
c.RegisterReloadCallback(udpConn.ReloadConfig)
|
||||
@@ -641,18 +536,19 @@ func (f *Interface) reloadDisconnectInvalid(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) reloadFirewall(c *config.C) {
|
||||
func (f *Interface) reloadFirewall(c *config.C, r *config.Reload) {
|
||||
cs := f.pki.getCertState()
|
||||
curCert := cs.getCertificate(cert.Version2)
|
||||
if curCert == nil {
|
||||
curCert = cs.getCertificate(cert.Version1)
|
||||
}
|
||||
|
||||
// The firewall builds its routableNetworks set from the certificate's UnsafeNetworks at construction.
|
||||
// Check to see if that set has changed, and if so, rebuild the firewall.
|
||||
certUnsafeChanged := curCert != nil && !slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks)
|
||||
|
||||
if !c.HasChanged("firewall") && !certUnsafeChanged {
|
||||
// Compare with what the running firewall was built from, not the last config, so a firewall that failed to build
|
||||
// is tried again. The cert is the one this reload brought, PKI registers its reload callback before this one
|
||||
src := c.Render("firewall")
|
||||
if src != "" && src == f.firewall.source && curCert != nil &&
|
||||
slices.Equal(curCert.Networks(), f.firewall.assignedNetworks) &&
|
||||
slices.Equal(curCert.UnsafeNetworks(), f.firewall.unsafeNetworks) {
|
||||
f.l.Debug("No firewall config change detected")
|
||||
return
|
||||
}
|
||||
@@ -660,6 +556,7 @@ func (f *Interface) reloadFirewall(c *config.C) {
|
||||
fw, err := NewFirewallFromConfig(f.l, cs, c)
|
||||
if err != nil {
|
||||
f.l.Error("Error while creating firewall during reload", "error", err)
|
||||
r.Failed()
|
||||
return
|
||||
}
|
||||
|
||||
@@ -757,33 +654,19 @@ func (f *Interface) reloadMisc(c *config.C) {
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
|
||||
ticker := time.NewTicker(i)
|
||||
defer ticker.Stop()
|
||||
|
||||
// statsEmitter updates the interface's gauges, the stats server runs it on its capture loop.
|
||||
func (f *Interface) statsEmitter() func() {
|
||||
udpStats := udp.NewUDPStatsEmitter(f.writers)
|
||||
|
||||
certExpirationGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
|
||||
certInitiatingVersion := metrics.GetOrRegisterGauge("certificate.initiating_version", nil)
|
||||
certMaxVersion := metrics.GetOrRegisterGauge("certificate.max_version", nil)
|
||||
|
||||
// Registered only when we run multiport, so these don't sit at zero on a node
|
||||
// that was never going to have a lane and read as a broken feature.
|
||||
var lanesUpGauge, laneTunnelsGauge metrics.Gauge
|
||||
if f.multiport && f.laneCount > 1 {
|
||||
lanesUpGauge = metrics.GetOrRegisterGauge("multiport.lanes.up", nil)
|
||||
laneTunnelsGauge = metrics.GetOrRegisterGauge("multiport.lanes.tunnels", nil)
|
||||
}
|
||||
|
||||
emit := func() {
|
||||
return func() {
|
||||
f.firewall.EmitStats()
|
||||
f.handshakeManager.EmitStats()
|
||||
udpStats()
|
||||
|
||||
if lanesUpGauge != nil {
|
||||
f.emitLaneStats(lanesUpGauge, laneTunnelsGauge)
|
||||
}
|
||||
|
||||
certState := f.pki.getCertState()
|
||||
defaultCrt := certState.GetDefaultCertificate()
|
||||
certExpirationGauge.Update(int64(defaultCrt.NotAfter().Sub(time.Now()) / time.Second))
|
||||
@@ -796,19 +679,6 @@ func (f *Interface) emitStats(ctx context.Context, i time.Duration) {
|
||||
certMaxVersion.Update(int64(certState.v1Cert.Version()))
|
||||
}
|
||||
}
|
||||
|
||||
// Prime gauges so a Prometheus scrape that lands before the first tick
|
||||
// sees real values instead of the zero defaults (issue #907).
|
||||
emit()
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-ticker.C:
|
||||
emit()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (f *Interface) GetHostInfo(vpnIp netip.Addr) *HostInfo {
|
||||
@@ -819,6 +689,14 @@ func (f *Interface) GetCertState() *CertState {
|
||||
return f.pki.getCertState()
|
||||
}
|
||||
|
||||
// shutdowner is a udp.Conn or overlay.Device whose readers can be woken without releasing their fds
|
||||
type shutdowner interface {
|
||||
Shutdown() error
|
||||
}
|
||||
|
||||
// readerShutdownTimeout bounds how long Close waits on woken readers before releasing their fds anyway
|
||||
const readerShutdownTimeout = 5 * time.Second
|
||||
|
||||
// Close releases the interface's resources: the udp sockets and the tun device.
|
||||
// It is idempotent and safe to call at any point in the lifecycle, including on an interface that never activated,
|
||||
// calls after the first return nil without doing anything.
|
||||
@@ -828,20 +706,55 @@ func (f *Interface) Close() error {
|
||||
}
|
||||
|
||||
var errs []error
|
||||
|
||||
// Release the udp readers
|
||||
for i, u := range f.writers {
|
||||
err := u.Close()
|
||||
if err != nil {
|
||||
closeUdp := func(i int, u udp.Conn) {
|
||||
if err := u.Close(); err != nil {
|
||||
f.l.Error("Error while closing udp socket", "error", err, "writer", i)
|
||||
errs = append(errs, err)
|
||||
}
|
||||
}
|
||||
closeTun := func() {
|
||||
if err := f.inside.Close(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
}
|
||||
|
||||
// Release the tun device (closing the tun also closes all readers)
|
||||
closeErr := f.inside.Close()
|
||||
if closeErr != nil {
|
||||
errs = append(errs, closeErr)
|
||||
// Wake every reader before releasing any fd, one that loops back into a syscall on a reused fd number never wakes.
|
||||
// Anything without Shutdown is closed right away, as before.
|
||||
var deferred []func()
|
||||
for i, u := range f.writers {
|
||||
if s, ok := u.(shutdowner); ok {
|
||||
if err := s.Shutdown(); err != nil {
|
||||
f.l.Error("Error while shutting down udp socket", "error", err, "writer", i)
|
||||
errs = append(errs, err)
|
||||
}
|
||||
deferred = append(deferred, func() { closeUdp(i, u) })
|
||||
} else {
|
||||
closeUdp(i, u)
|
||||
}
|
||||
}
|
||||
if s, ok := f.inside.(shutdowner); ok {
|
||||
if err := s.Shutdown(); err != nil {
|
||||
errs = append(errs, err)
|
||||
}
|
||||
deferred = append(deferred, closeTun)
|
||||
} else {
|
||||
closeTun()
|
||||
}
|
||||
|
||||
if len(deferred) > 0 {
|
||||
readersDone := make(chan struct{})
|
||||
go func() {
|
||||
f.readers.Wait()
|
||||
close(readersDone)
|
||||
}()
|
||||
select {
|
||||
case <-readersDone:
|
||||
case <-time.After(readerShutdownTimeout):
|
||||
f.l.Warn("Readers did not stop, closing their fds anyway", "timeout", readerShutdownTimeout)
|
||||
}
|
||||
for _, closeFn := range deferred {
|
||||
closeFn()
|
||||
}
|
||||
}
|
||||
|
||||
// Release the construction token so waiters know the resources are gone
|
||||
|
||||
+5
-14
@@ -3,7 +3,6 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -18,11 +17,8 @@ import (
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// Test_emitStats_primesGauges covers issue #907: a Prometheus scrape that
|
||||
// landed before the first ticker fire used to read 0 for the cert gauges.
|
||||
// emitStats now primes the gauges before entering the ticker loop. We assert
|
||||
// the gauge is zero before the first call and non-zero after.
|
||||
func Test_emitStats_primesGauges(t *testing.T) {
|
||||
// Priming before the first tick (issue #907) is Start's job, see TestStatsServer_Start_primes.
|
||||
func Test_statsEmitter_setsGauges(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.UnregisterAll()
|
||||
|
||||
l := test.NewLogger()
|
||||
@@ -56,17 +52,12 @@ func Test_emitStats_primesGauges(t *testing.T) {
|
||||
ifce.pki.cs.Store(cs)
|
||||
|
||||
ttlGauge := metrics.GetOrRegisterGauge("certificate.ttl_seconds", nil)
|
||||
require.Zero(t, ttlGauge.Value(), "gauge should be zero before emitStats runs")
|
||||
require.Zero(t, ttlGauge.Value(), "gauge should be zero before the emitter runs")
|
||||
|
||||
// Pre-cancel the context so emitStats returns after priming the gauges
|
||||
// without ever reading from ticker.C. The one hour interval is just a
|
||||
// belt-and-suspenders, the test does not expect the ticker to fire.
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
cancel()
|
||||
ifce.emitStats(ctx, time.Hour)
|
||||
ifce.statsEmitter()()
|
||||
|
||||
ttl := ttlGauge.Value()
|
||||
assert.Positive(t, ttl, "ttl gauge should be primed by emitStats before its first tick")
|
||||
assert.Positive(t, ttl, "ttl gauge should be set by one run of the emitter")
|
||||
assert.LessOrEqual(t, ttl, int64(3600))
|
||||
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.initiating_version", nil).Value())
|
||||
assert.Equal(t, int64(cert.Version1), metrics.GetOrRegisterGauge("certificate.max_version", nil).Value())
|
||||
|
||||
+81
-4
@@ -65,10 +65,10 @@ func TestReloadFirewall_CertUnsafeNetworksChanged(t *testing.T) {
|
||||
pki.cs.Store(&CertState{v2Cert: c2, initiatingVersion: cert.Version2})
|
||||
|
||||
// Reload with the same YAML so HasChanged("firewall") reports false.
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
require.False(t, cfg.HasChanged("firewall"))
|
||||
|
||||
f.reloadFirewall(cfg)
|
||||
f.reloadFirewall(cfg, nil)
|
||||
|
||||
assert.NotSame(t, fw, f.firewall, "firewall pointer should have been replaced")
|
||||
assert.Equal(t, newUnsafe, f.firewall.unsafeNetworks)
|
||||
@@ -113,8 +113,85 @@ func TestReloadFirewall_NoChange(t *testing.T) {
|
||||
l: l,
|
||||
}
|
||||
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML))
|
||||
f.reloadFirewall(cfg)
|
||||
require.NoError(t, cfg.ReloadConfigString(rawYAML).Err)
|
||||
f.reloadFirewall(cfg, nil)
|
||||
|
||||
assert.Same(t, fw, f.firewall, "firewall should not have been replaced")
|
||||
}
|
||||
|
||||
// Rules that don't parse keep the old firewall, and the reload says it could not apply them
|
||||
func TestReloadFirewall_BadRulesFailTheReload(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}}, initiatingVersion: cert.Version2})
|
||||
|
||||
rules := func(proto string) string {
|
||||
return "firewall:\n outbound:\n - port: any\n proto: any\n host: any\n inbound:\n - port: any\n proto: " + proto + "\n host: any\n"
|
||||
}
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(rules("any")))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
|
||||
// The running firewall still isn't built from what the config asks for, so the same reload fails again
|
||||
for range 2 {
|
||||
res := cfg.ReloadConfigString(rules("nope"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Same(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
res := cfg.ReloadConfigString(rules("tcp"))
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.NotSame(t, fw, f.firewall)
|
||||
}
|
||||
|
||||
// Every input the firewall is built from rebuilds it when it changes, and nothing else does
|
||||
func TestReloadFirewall_RebuildsOnAnyInput(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
||||
base := "firewall:\n inbound:\n - port: any\n proto: any\n host: any\n"
|
||||
setup := func() (*config.C, *Interface, *PKI) {
|
||||
pki := &PKI{}
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks}, initiatingVersion: cert.Version2})
|
||||
cfg := config.NewC(l)
|
||||
require.NoError(t, cfg.LoadString(base))
|
||||
fw, err := NewFirewallFromConfig(l, pki.getCertState(), cfg)
|
||||
require.NoError(t, err)
|
||||
f := &Interface{pki: pki, firewall: fw, l: l}
|
||||
cfg.RegisterReloadCallback(f.reloadFirewall)
|
||||
return cfg, f, pki
|
||||
}
|
||||
setCert := func(pki *PKI, networks, unsafe []netip.Prefix) {
|
||||
pki.cs.Store(&CertState{v2Cert: &dummyCert{version: cert.Version2, networks: networks, unsafeNetworks: unsafe}, initiatingVersion: cert.Version2})
|
||||
}
|
||||
|
||||
cases := map[string]struct {
|
||||
cfg string
|
||||
cert func(*PKI)
|
||||
want bool
|
||||
}{
|
||||
"nothing": {base + "punchy:\n punch: true\n", nil, false},
|
||||
"rules": {base + " outbound:\n - port: any\n proto: any\n host: any\n", nil, true},
|
||||
"inbound_action": {base + " inbound_action: reject\n", nil, true},
|
||||
"conntrack": {base + " conntrack:\n tcp_timeout: 1m\n", nil, true},
|
||||
"networks": {base, func(p *PKI) { setCert(p, []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")}, nil) }, true},
|
||||
"unsafe_networks": {base, func(p *PKI) { setCert(p, networks, []netip.Prefix{netip.MustParsePrefix("192.168.0.0/24")}) }, true},
|
||||
}
|
||||
for name, tc := range cases {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
cfg, f, pki := setup()
|
||||
old := f.firewall
|
||||
if tc.cert != nil {
|
||||
tc.cert(pki)
|
||||
}
|
||||
res := cfg.ReloadConfigString(tc.cfg)
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.Failed)
|
||||
assert.Equal(t, tc.want, f.firewall != old)
|
||||
})
|
||||
}
|
||||
}
|
||||
+3
-13
@@ -45,8 +45,7 @@ func setTransportChecksum4(packet []byte) {
|
||||
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
||||
return
|
||||
}
|
||||
// The checksum covers the whole datagram, which a fragment (MF set or a
|
||||
// non-zero offset) does not carry.
|
||||
// do not attempt to set checksums for fragments
|
||||
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
||||
return
|
||||
}
|
||||
@@ -68,10 +67,7 @@ func setTransportChecksum6(packet []byte) {
|
||||
return
|
||||
}
|
||||
|
||||
// The checksum covers the whole datagram, which a fragment does not carry.
|
||||
// An unknown extension header hides where the transport header starts. A
|
||||
// chain longer than the walk's budget ends it early, at an offset that was
|
||||
// never checked against the packet.
|
||||
// we must find the transport header in order to write a checksum
|
||||
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
||||
if err != nil || anyFragment || offset >= end {
|
||||
return
|
||||
@@ -109,8 +105,7 @@ func transportExtent(transport []byte, proto uint8) ([]byte, bool) {
|
||||
// writeTransportChecksum stores the checksum of transport, taken over the
|
||||
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
||||
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200
|
||||
// section 8.1).
|
||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200 section 8.1).
|
||||
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||
var at, minLen int
|
||||
switch proto {
|
||||
@@ -133,11 +128,6 @@ func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||
binary.BigEndian.PutUint16(transport[at:], sum)
|
||||
}
|
||||
|
||||
// fold reduces a pseudo-header sum to the 16 bit seed Checksum takes. Carrying
|
||||
// the high half back into the low half is what keeps the reduction lossless, so
|
||||
// the seed sums exactly as the wider value would; 0xffff is its fixed point.
|
||||
// Every term of that sum comes from a 16 bit field, so it stays far below the
|
||||
// width at which the accumulator would wrap.
|
||||
func fold(csum uint32) uint16 {
|
||||
for csum > 0xffff {
|
||||
csum = (csum >> 16) + (csum & 0xffff)
|
||||
|
||||
+13
-16
@@ -345,14 +345,11 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
|
||||
return out
|
||||
}
|
||||
|
||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the
|
||||
// offset it begins at, and whether the packet is a non-first fragment. Only the RFC 8200 and IANA extension
|
||||
// headers below are walked. Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental
|
||||
// 253/254, and real upper layer protocols like SCTP or GRE, is terminal. Walking those as extension headers
|
||||
// is a firewall bypass, so they fail closed. For a non-first fragment the returned protocol is the fragmented
|
||||
// protocol and offset points at the fragment header, there is no transport header to locate. Returns
|
||||
// ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header or the chain is truncated before a
|
||||
// terminal protocol is reached.
|
||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the offset it begins at, and whether the packet is a non-first fragment.
|
||||
// Only the RFC 8200 and IANA extension headers below are walked.
|
||||
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
|
||||
// For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate.
|
||||
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
|
||||
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
|
||||
const maxIPv6ExtHeaders = 8
|
||||
if len(packet) < ipv6.HeaderLen {
|
||||
@@ -365,14 +362,14 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
||||
switch nextHeader {
|
||||
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
||||
if len(packet) < offset+2 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
nextHeader = packet[offset]
|
||||
offset += (int(packet[offset+1]) + 1) << 3
|
||||
|
||||
case 44: // Fragment
|
||||
if len(packet) < offset+8 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
anyFragment = true
|
||||
// Non-first fragments carry no transport header, report the fragmented protocol and stop
|
||||
@@ -384,21 +381,21 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
||||
|
||||
case 51: // AH
|
||||
if len(packet) < offset+2 {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
nextHeader = packet[offset]
|
||||
offset += (int(packet[offset+1]) + 2) << 2
|
||||
|
||||
default:
|
||||
// A prior extension header can declare a length that advances offset past the packet. The terminal
|
||||
// protocol's header isn't actually here, so treat the chain as truncated rather than classifying it.
|
||||
if offset > len(packet) {
|
||||
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||
// A prior extension header can declare a length that advances offset past the packet, reject this.
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
return nextHeader, offset, isFragment, anyFragment, nil
|
||||
return nextHeader, offset, isFragment, anyFragment, nil //success!
|
||||
}
|
||||
}
|
||||
return nextHeader, offset, isFragment, anyFragment, nil
|
||||
// Fail closed
|
||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
||||
}
|
||||
|
||||
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
||||
|
||||
+17
-5
@@ -529,6 +529,17 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP
|
||||
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
|
||||
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
|
||||
extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop
|
||||
|
||||
// 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the
|
||||
// report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports
|
||||
// from the attacker's bytes there.
|
||||
var budgetChain []byte
|
||||
for range 7 {
|
||||
budgetChain = append(budgetChain, extToHbH...)
|
||||
}
|
||||
budgetChain = append(budgetChain, extToTCP...)
|
||||
budgetChain = append(budgetChain, transport...)
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
@@ -549,9 +560,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
|
||||
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
|
||||
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
|
||||
{"truncated extension header", 0, nil, 0, ipv6.HeaderLen, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
|
||||
{"extension length past buffer", 60, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 132, ipv6.HeaderLen + 2048, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
@@ -559,10 +571,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
||||
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
||||
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
||||
if tt.wantErr != nil {
|
||||
assert.ErrorIs(t, err, tt.wantErr)
|
||||
return
|
||||
require.ErrorIs(t, err, tt.wantErr)
|
||||
} else {
|
||||
require.NoError(t, err)
|
||||
}
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, tt.wantProto, proto)
|
||||
assert.Equal(t, tt.wantOffset, offset)
|
||||
assert.Equal(t, tt.wantFragment, isFragment)
|
||||
|
||||
@@ -1,721 +0,0 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"hash/fnv"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/firewall"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/noiseutil"
|
||||
)
|
||||
|
||||
// Multiport lanes give one tunnel several underlay 5-tuples, so its traffic
|
||||
// spreads over ECMP paths, NIC receive queues and per-flow policers instead of
|
||||
// funnelling through a single flow. Each inside flow picks a lane by hashing its
|
||||
// own 5-tuple, so the spread doesn't depend on how a kernel steers tun queues
|
||||
// (see txQueue).
|
||||
//
|
||||
// A lane is not a second tunnel: it is an extra session on the same HostInfo.
|
||||
// Noise leaves us with A.eKey == B.dKey, so both sides expand the same two keys
|
||||
// with the same per-lane label and land on a matched pair without exchanging
|
||||
// anything. A lane therefore costs no handshake, has no half-established state,
|
||||
// and dies exactly when its base tunnel does. Which lane a packet belongs to
|
||||
// travels in the nebula header, inside the AEAD's associated data.
|
||||
//
|
||||
// Lane 0 is the base tunnel itself: HostInfo.ConnectionState, the base port, and
|
||||
// the peer's real remote address, and it carries its share of flows like any
|
||||
// other. Lane s > 0 egresses a socket on listen.port+s (see laneSock) toward the
|
||||
// peer's advertised port range. Receiving on a lane
|
||||
// needs no permission — the keys are derivable the moment the base handshake
|
||||
// completes — but sending on one needs proof the new 5-tuple actually works,
|
||||
// since nothing else would notice a middlebox quietly dropping it. So a lane
|
||||
// stays down until a probe on it is acked, and falls back to the base tunnel the
|
||||
// moment it stops being acked.
|
||||
//
|
||||
// Both directions are pay-per-use. A lane session is derived on the first packet
|
||||
// that needs it, because how many lanes exist is partly the peer's call: it
|
||||
// advertises how many it sends on, and we have to be able to receive all of
|
||||
// them. Deriving them all up front would let a peer advertising the maximum cost
|
||||
// us a replay window and two cipher states per lane, per tunnel, for lanes it
|
||||
// may never send on.
|
||||
|
||||
const (
|
||||
// laneKeyInfo is the HKDF label prefix for lane key expansion. Changing it
|
||||
// means older builds derive different keys and drop our lane traffic; the
|
||||
// base tunnel would keep working, so the failure would be a silent loss of
|
||||
// lanes rather than of connectivity.
|
||||
laneKeyInfo = "nebula multiport lane v1"
|
||||
|
||||
// laneRetryBase and laneRetryMax bound the backoff between probes of a lane
|
||||
// that will not come up, so a peer whose lane ports are firewalled costs one
|
||||
// packet a minute rather than one per traffic tick.
|
||||
laneRetryBase = 5 * time.Second
|
||||
laneRetryMax = 60 * time.Second
|
||||
|
||||
// laneMaxFails caps the failure counter; the backoff saturates well before.
|
||||
laneMaxFails = 8
|
||||
|
||||
// laneProbeTimeout is how long a probe may go unacked before it counts as a
|
||||
// failure. It is shorter than the connection manager's check interval on
|
||||
// purpose: an outstanding probe is judged on the next tick either way, and a
|
||||
// longer timeout would only delay that by a whole tick.
|
||||
laneProbeTimeout = 2 * time.Second
|
||||
|
||||
// laneKeepalive is how often a lane that is up re-proves its path. Traffic
|
||||
// on a lane is not evidence the lane works — that is the whole reason lanes
|
||||
// need probing — so a lane that silently breaks is only caught here.
|
||||
laneKeepalive = 30 * time.Second
|
||||
)
|
||||
|
||||
// laneSet holds a peer's lane sessions and the state deciding which lanes may
|
||||
// carry traffic. It is built when the base handshake completes and never
|
||||
// resized, so the slices and their lengths are immutable; mu guards the fields
|
||||
// under it, and sessions/txAddr/demand are atomics read by the data plane
|
||||
// without it.
|
||||
type laneSet struct {
|
||||
// sessions[s] holds lane s's session once something has needed it, and nil
|
||||
// until then. sessions[0] is never populated: lane 0 is the base tunnel's own
|
||||
// ConnectionState. The length is immutable, so the data plane bounds-checks
|
||||
// and loads with no locking.
|
||||
sessions []atomic.Pointer[ConnectionState]
|
||||
|
||||
// material is what a lane session is derived from, kept because sessions are
|
||||
// derived lazily and the handshake result is long gone by then.
|
||||
material laneMaterial
|
||||
|
||||
// txAddr[s] holds lane s's remote address while the lane is proven usable
|
||||
// and nil otherwise. This single atomic is both the TX gate and the
|
||||
// destination, so a routine that loads non-nil has everything it needs.
|
||||
// Sized txLanes: lanes above that never send.
|
||||
txAddr []atomic.Pointer[netip.AddrPort]
|
||||
|
||||
// demand[s] is raised at creation, and again by the TX path whenever a flow
|
||||
// hashes onto lane s while it is down. Probing is demand-driven, so a peer we
|
||||
// never send to costs nothing beyond its base tunnel no matter how many lanes
|
||||
// are configured, and a lane that keeps failing is only retried while
|
||||
// something still wants it. Sized txLanes.
|
||||
demand []atomic.Bool
|
||||
|
||||
// txLanes is how many lanes we may send on — our lane count clamped to the
|
||||
// ports the peer bound — and so the modulus a flow's hash is reduced by.
|
||||
// Lanes from txLanes up can only receive, which is how a peer with more
|
||||
// routines than us still spreads its own traffic.
|
||||
// Immutable, and the length of every TX-side slice here.
|
||||
txLanes int
|
||||
|
||||
mu sync.Mutex
|
||||
|
||||
// peerPortCount and peerBasePort are the peer's advertised port range and
|
||||
// portOffset is this pair's rotation within it: lane s targets
|
||||
// peerBasePort + ((s + portOffset) % peerPortCount).
|
||||
peerPortCount uint16
|
||||
peerBasePort uint16
|
||||
portOffset uint16
|
||||
|
||||
// laneBias rotates the flow hash before it picks a lane, so the two sides of
|
||||
// a flow land on lanes that are each other's partner rather than at
|
||||
// independent points in the range. See newLaneSet.
|
||||
laneBias uint16
|
||||
|
||||
// peerAddr is the address the current lane targets were built from. The
|
||||
// peer's lane ports have no derivable relationship to a new NAT mapping, so
|
||||
// a roam invalidates every lane rather than moving it.
|
||||
peerAddr netip.Addr
|
||||
|
||||
// probe[s] is lane s's probe and backoff state. Sized txLanes.
|
||||
probe []laneProbeState
|
||||
}
|
||||
|
||||
// laneMaterial is everything a lane session is derived from. The two base keys
|
||||
// are the same secret the base tunnel's own cipher states already hold — the
|
||||
// noiseutil.CipherState interface just doesn't hand them back, so a lane set
|
||||
// keeps its own copy rather than a reference to the session.
|
||||
type laneMaterial struct {
|
||||
eKey, dKey [32]byte
|
||||
cipher noise.CipherFunc
|
||||
myCert cert.Certificate
|
||||
peerCert *cert.CachedCertificate
|
||||
initiator bool
|
||||
epoch uint64
|
||||
}
|
||||
|
||||
type laneProbeState struct {
|
||||
// gen is the generation of the last probe sent, echoed in the ack so a late
|
||||
// ack cannot promote a lane on the strength of a superseded probe.
|
||||
gen uint8
|
||||
|
||||
// fails is the consecutive failure count driving retryAt.
|
||||
fails uint8
|
||||
|
||||
// sentAt is when the outstanding probe went out, zero when none is pending.
|
||||
sentAt time.Time
|
||||
|
||||
// target is where the outstanding probe went, promoted to txAddr on ack. It
|
||||
// outlives the probe, which is what lets a demotion log the address that
|
||||
// stopped answering.
|
||||
target netip.AddrPort
|
||||
|
||||
// lastAck is when the lane was last confirmed usable, driving the keepalive.
|
||||
lastAck time.Time
|
||||
|
||||
// retryAt is the earliest we may probe this lane again.
|
||||
retryAt time.Time
|
||||
}
|
||||
|
||||
// newLaneSet sets up the lanes for a freshly completed base handshake. It
|
||||
// returns nil when the pair has no lane beyond the base tunnel, which is the
|
||||
// normal answer for a peer running without multiport. No session is derived
|
||||
// here; each is derived on the first packet that needs it.
|
||||
//
|
||||
// epoch is the base session's, which every lane session will share.
|
||||
func newLaneSet(r *handshake.Result, myLanes int, epoch uint64, myAddr, peerAddr netip.Addr) *laneSet {
|
||||
// PeerPortCount and PeerBasePort are already bounded to uint16 by the
|
||||
// handshake payload parser. A zero port count is a peer that did not
|
||||
// advertise multiport at all, so there is no lane to be had in either
|
||||
// direction.
|
||||
peerPorts := uint16(r.PeerPortCount)
|
||||
if peerPorts == 0 {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Sessions have to cover both directions: we send on our lanes and receive
|
||||
// on the peer's, and one derived session serves both ends of a lane index.
|
||||
// Only the session table is sized by the peer's advertised count; the TX-side
|
||||
// state is sized by what we will actually send on.
|
||||
n := min(max(myLanes, int(r.PeerTxLanes)), header.MaxLane+1)
|
||||
if n < 2 {
|
||||
return nil
|
||||
}
|
||||
txLanes := min(myLanes, int(peerPorts), n)
|
||||
|
||||
offset := lanePortOffset(myAddr, peerAddr, peerPorts)
|
||||
|
||||
// A flow picks its lane from a hash both sides compute identically, so with
|
||||
// the ranges lined up the two directions of a flow would pick the same lane
|
||||
// index — and lane s targets the peer's lane (s + portOffset), not lane s. The
|
||||
// high-addressed side rotates its choice by the low side's offset, which is
|
||||
// its own negated, so the two directions land on partner lanes and their
|
||||
// 4-tuples are exact reverses: each side's traffic then arrives through the
|
||||
// conntrack entry the other's probe opened. With mismatched ranges there are
|
||||
// no partner lanes to find, so don't pretend: hash straight.
|
||||
bias := uint16(0)
|
||||
if txLanes == int(peerPorts) && peerAddr.Less(myAddr) {
|
||||
bias = (peerPorts - offset) % peerPorts
|
||||
}
|
||||
|
||||
ls := &laneSet{
|
||||
sessions: make([]atomic.Pointer[ConnectionState], n),
|
||||
material: laneMaterial{
|
||||
eKey: r.EKey.UnsafeKey(),
|
||||
dKey: r.DKey.UnsafeKey(),
|
||||
cipher: r.Cipher,
|
||||
myCert: r.MyCert,
|
||||
peerCert: r.RemoteCert,
|
||||
initiator: r.Initiator,
|
||||
epoch: epoch,
|
||||
},
|
||||
txAddr: make([]atomic.Pointer[netip.AddrPort], txLanes),
|
||||
demand: make([]atomic.Bool, txLanes),
|
||||
probe: make([]laneProbeState, txLanes),
|
||||
txLanes: txLanes,
|
||||
peerPortCount: peerPorts,
|
||||
peerBasePort: uint16(r.PeerBasePort),
|
||||
portOffset: offset,
|
||||
laneBias: bias,
|
||||
}
|
||||
|
||||
// Every lane starts out demanded, so the first traffic tick on this tunnel
|
||||
// probes all of them at once instead of waiting for a flow to hash onto each.
|
||||
// Lanes have to be up *before* the flows are, not after: the peer writes a
|
||||
// flow's inbound packets to the tun queue matching the socket they arrived on,
|
||||
// and the kernel remembers that for as long as the flow stays busy. A flow that
|
||||
// starts while the lanes are still down therefore gets pinned to queue 0 on
|
||||
// both hosts for its whole life. This costs one probe per lane on any tunnel
|
||||
// with traffic; an idle tunnel is never ticked, so it still costs nothing.
|
||||
for s := 1; s < txLanes; s++ {
|
||||
ls.demand[s].Store(true)
|
||||
}
|
||||
return ls
|
||||
}
|
||||
|
||||
// laneLogAttr summarizes what a tunnel negotiated, for the handshake log lines.
|
||||
// It is an empty attr, which slog drops, on a node not running multiport. A peer
|
||||
// that negotiated no lanes still logs, with zeros: "we offered and got nothing"
|
||||
// is exactly what you want to see when you expected lanes and have none.
|
||||
func laneLogAttr(myLanes int, ls *laneSet) slog.Attr {
|
||||
if myLanes == 0 {
|
||||
return slog.Attr{}
|
||||
}
|
||||
if ls == nil {
|
||||
return slog.Any("lanes", m{"tx": 0, "sessions": 0})
|
||||
}
|
||||
// Every field read here is immutable once the set is built.
|
||||
return slog.Any("lanes", m{
|
||||
"tx": ls.txLanes,
|
||||
"sessions": len(ls.sessions),
|
||||
"peerBasePort": ls.peerBasePort,
|
||||
"peerPorts": ls.peerPortCount,
|
||||
"portOffset": ls.portOffset,
|
||||
})
|
||||
}
|
||||
|
||||
// emitLaneStats reports how many lanes are carrying traffic and how many tunnels
|
||||
// have any. Both are counted by walking the hostmap, because a counter kept at
|
||||
// promotion and demotion would drift upward forever: a tunnel torn down while its
|
||||
// lanes are up never demotes them. Only a node running multiport pays for the
|
||||
// walk.
|
||||
func (f *Interface) emitLaneStats(up, tunnels metrics.Gauge) {
|
||||
var nUp, nTunnels int64
|
||||
f.hostMap.ForEachIndex(func(hostinfo *HostInfo) {
|
||||
ls := hostinfo.lanes
|
||||
if ls == nil {
|
||||
return
|
||||
}
|
||||
nTunnels++
|
||||
for s := 1; s < ls.txLanes; s++ {
|
||||
if ls.txAddr[s].Load() != nil {
|
||||
nUp++
|
||||
}
|
||||
}
|
||||
})
|
||||
up.Update(nUp)
|
||||
tunnels.Update(nTunnels)
|
||||
}
|
||||
|
||||
// lanePortOffset returns the rotation applied to this pair's lane target ports,
|
||||
// in [0, peerPortCount). Without it every low-routine peer would aim its few
|
||||
// lanes at a big peer's first few ports, concentrating the big peer's receive
|
||||
// work on a couple of sockets; the hash spreads pairs across the whole range.
|
||||
//
|
||||
// Both sides hash the same sorted vpn-address pair and the higher address
|
||||
// negates the result, so when port counts match the two sides' rotations
|
||||
// cancel: our lane s's 4-tuple stays the reverse of the peer's lane s, and each
|
||||
// side's probe opens the conntrack entry the other's arrives through. (The one
|
||||
// lane a nonzero rotation lands on the peer's base port has no partner lane, so
|
||||
// behind a port-restricted NAT it is the one lane that may never come up.)
|
||||
func lanePortOffset(myAddr, peerAddr netip.Addr, peerPortCount uint16) uint16 {
|
||||
if peerPortCount == 0 {
|
||||
return 0
|
||||
}
|
||||
lo, hi := myAddr, peerAddr
|
||||
if hi.Less(lo) {
|
||||
lo, hi = hi, lo
|
||||
}
|
||||
h := fnv.New32a()
|
||||
b := lo.As16()
|
||||
h.Write(b[:])
|
||||
b = hi.As16()
|
||||
h.Write(b[:])
|
||||
o := uint16(h.Sum32() % uint32(peerPortCount))
|
||||
if myAddr == hi {
|
||||
o = (peerPortCount - o) % peerPortCount
|
||||
}
|
||||
return o
|
||||
}
|
||||
|
||||
// laneSession returns the session to decrypt a lane s packet with, deriving one
|
||||
// if this is the first packet to claim that lane. A nil session with no error
|
||||
// means this tunnel has no lane s at all.
|
||||
//
|
||||
// cached reports whether the session was already in the table. A fresh one is
|
||||
// deliberately left out of it: anyone who can spoof this tunnel's local index
|
||||
// can name any lane, and installing on sight would let them make us hold a
|
||||
// replay window and two cipher states per lane without authenticating anything.
|
||||
// The caller must install with installSession once the packet decrypts, which is
|
||||
// the first moment the lane is known to be real, and must use the session
|
||||
// installSession hands back from then on.
|
||||
func (i *HostInfo) laneSession(s uint8) (ci *ConnectionState, cached bool, err error) {
|
||||
ls := i.lanes
|
||||
if ls == nil || s == 0 || int(s) >= len(ls.sessions) {
|
||||
return nil, false, nil
|
||||
}
|
||||
|
||||
if cs := ls.sessions[s].Load(); cs != nil {
|
||||
return cs, true, nil
|
||||
}
|
||||
|
||||
cs, err := newLaneConnectionState(&ls.material, s)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
return cs, false, nil
|
||||
}
|
||||
|
||||
// installSession publishes a session derived by laneSession, so the next packet
|
||||
// on the lane doesn't have to derive it again, and returns the session that is
|
||||
// now installed. cs must have already decrypted the packet at messageCounter.
|
||||
//
|
||||
// Two routines can race on a lane's first packet and derive a session each, and
|
||||
// only one of them can be installed. Every session derived for a lane holds the
|
||||
// same key, so a second one that ever encrypted would restart the message
|
||||
// counter and repeat nonces under it. Returning the winner solves this.
|
||||
func (ls *laneSet) installSession(l *slog.Logger, s uint8, cs *ConnectionState, messageCounter uint64) *ConnectionState {
|
||||
if ls.sessions[s].CompareAndSwap(nil, cs) {
|
||||
return cs
|
||||
}
|
||||
|
||||
winner := ls.sessions[s].Load()
|
||||
winner.noteSeen(l, messageCounter)
|
||||
return winner
|
||||
}
|
||||
|
||||
// session returns lane s's session for our own use, deriving and installing it
|
||||
// if it doesn't exist yet. Unlike the RX path this needs no proof the lane is
|
||||
// real: we only ask for lanes we chose to send on. s must be a lane this set
|
||||
// covers.
|
||||
func (ls *laneSet) session(s int) (*ConnectionState, error) {
|
||||
if cs := ls.sessions[s].Load(); cs != nil {
|
||||
return cs, nil
|
||||
}
|
||||
|
||||
cs, err := newLaneConnectionState(&ls.material, uint8(s))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if !ls.sessions[s].CompareAndSwap(nil, cs) {
|
||||
return ls.sessions[s].Load(), nil
|
||||
}
|
||||
return cs, nil
|
||||
}
|
||||
|
||||
// maxMessageCounter returns the highest counter across the base session and
|
||||
// every lane session. Data rides the lanes, so the base counter alone would
|
||||
// never reach the rehandshake or exhaustion thresholds and the lane keys would
|
||||
// be used past their data-volume margin. Rolling the base tunnel replaces the
|
||||
// lane keys with it, since lanes are derived from it.
|
||||
func (i *HostInfo) maxMessageCounter() uint64 {
|
||||
if i.ConnectionState == nil {
|
||||
return 0
|
||||
}
|
||||
c := i.ConnectionState.messageCounter.Load()
|
||||
if ls := i.lanes; ls != nil {
|
||||
for s := range ls.sessions {
|
||||
cs := ls.sessions[s].Load()
|
||||
if cs == nil {
|
||||
// Never derived, so it has never sent anything either.
|
||||
continue
|
||||
}
|
||||
if lc := cs.messageCounter.Load(); lc > c {
|
||||
c = lc
|
||||
}
|
||||
}
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// txLane returns the session and destination for lane s, or a nil session when
|
||||
// the lane is down and the caller must use the base tunnel. A miss raises
|
||||
// demand, which is what gets a down lane probed again, so we pay for a lane
|
||||
// exactly where real traffic wanted one. Callers on the data plane come through
|
||||
// txLaneForFlow.
|
||||
func (ls *laneSet) txLane(s int) (*ConnectionState, netip.AddrPort) {
|
||||
if ls == nil || s <= 0 || s >= ls.txLanes {
|
||||
return nil, netip.AddrPort{}
|
||||
}
|
||||
|
||||
if addr := ls.txAddr[s].Load(); addr != nil {
|
||||
// The lane is only up because a probe was acked on it, and that probe
|
||||
// derived the session, so this load cannot miss. Fall back rather than
|
||||
// derive here anyway: this is the hot path and a nil is not worth an HKDF.
|
||||
if cs := ls.sessions[s].Load(); cs != nil {
|
||||
return cs, *addr
|
||||
}
|
||||
return nil, netip.AddrPort{}
|
||||
}
|
||||
|
||||
// Load-guarded so the common case of a lane that will not come up is a
|
||||
// plain read and cannot ping-pong the cache line these flags share.
|
||||
if !ls.demand[s].Load() {
|
||||
ls.demand[s].Store(true)
|
||||
}
|
||||
return nil, netip.AddrPort{}
|
||||
}
|
||||
|
||||
// txLaneForFlow picks the lane a flow rides and returns it with its session and
|
||||
// destination, or lane 0 and a nil session when the flow belongs on the base
|
||||
// tunnel — either because the hash landed on lane 0 or because the lane it
|
||||
// landed on is down.
|
||||
//
|
||||
// The lane comes from the flow rather than from the sending routine so that lane
|
||||
// use doesn't depend on how the kernel steers tun queues; see txQueue. It is a
|
||||
// pure function of the 5-tuple, so a flow stays on one lane for its life: no
|
||||
// per-packet reordering, and one lane's replay window sees one set of flows.
|
||||
func (ls *laneSet) txLaneForFlow(p *firewall.Packet) (int, *ConnectionState, netip.AddrPort) {
|
||||
if ls == nil || ls.txLanes < 2 {
|
||||
return 0, nil, netip.AddrPort{}
|
||||
}
|
||||
|
||||
s := int((laneFlowHash(p) + uint32(ls.laneBias)) % uint32(ls.txLanes))
|
||||
if s == 0 {
|
||||
// Lane 0 is the base tunnel, and a full share of flows belongs on it.
|
||||
return 0, nil, netip.AddrPort{}
|
||||
}
|
||||
|
||||
cs, addr := ls.txLane(s)
|
||||
return s, cs, addr
|
||||
}
|
||||
|
||||
// laneFlowHash hashes a 5-tuple to the same value from either end of the flow,
|
||||
// which is what lets both peers pick partner lanes for it (see laneBias). FNV-1a
|
||||
// by hand rather than through hash/fnv: this runs per packet, and the interface
|
||||
// there would escape the addresses to the heap.
|
||||
func laneFlowHash(p *firewall.Packet) uint32 {
|
||||
// Order the two endpoints so the direction of travel cannot change the hash.
|
||||
aAddr, aPort := p.LocalAddr, p.LocalPort
|
||||
bAddr, bPort := p.RemoteAddr, p.RemotePort
|
||||
if bAddr.Less(aAddr) || (aAddr == bAddr && bPort < aPort) {
|
||||
aAddr, aPort, bAddr, bPort = bAddr, bPort, aAddr, aPort
|
||||
}
|
||||
|
||||
const prime = 16777619
|
||||
h := uint32(2166136261)
|
||||
x, y := aAddr.As16(), bAddr.As16()
|
||||
for i := range x {
|
||||
h = (h ^ uint32(x[i])) * prime
|
||||
h = (h ^ uint32(y[i])) * prime
|
||||
}
|
||||
for _, b := range [5]byte{byte(aPort >> 8), byte(aPort), byte(bPort >> 8), byte(bPort), p.Protocol} {
|
||||
h = (h ^ uint32(b)) * prime
|
||||
}
|
||||
return h
|
||||
}
|
||||
|
||||
// laneTargetPortLocked returns the peer port lane s aims at. Only meaningful
|
||||
// when peerPortCount is nonzero, which txLanes > 0 guarantees.
|
||||
func (ls *laneSet) laneTargetPortLocked(s int) uint16 {
|
||||
return ls.peerBasePort + uint16((s+int(ls.portOffset))%int(ls.peerPortCount))
|
||||
}
|
||||
|
||||
// laneTargetLocked returns where lane s's probes go: the peer port this lane is
|
||||
// paired with, on the peer's current direct address.
|
||||
//
|
||||
// A lane only ever aims at its own port. There is no fallback to the peer's base
|
||||
// port when the lane port doesn't answer — a lane sharing the base port's
|
||||
// destination gains only a source port of its own, while costing the peer the
|
||||
// receive spread that is the whole point, so a lane that can't reach its port
|
||||
// stays down and its traffic rides the base tunnel.
|
||||
func (ls *laneSet) laneTargetLocked(s int, addr netip.Addr) netip.AddrPort {
|
||||
return netip.AddrPortFrom(addr, ls.laneTargetPortLocked(s))
|
||||
}
|
||||
|
||||
// laneRetryDelay is the backoff after fails consecutive probe failures.
|
||||
func laneRetryDelay(fails uint8) time.Duration {
|
||||
d := laneRetryBase << min(fails, 4)
|
||||
if d > laneRetryMax {
|
||||
d = laneRetryMax
|
||||
}
|
||||
return d
|
||||
}
|
||||
|
||||
// noteAck records an acked probe for lane s, promoting the lane if it was down.
|
||||
// gen must match the outstanding probe. Reports the target the lane came up on,
|
||||
// and whether this ack is what promoted it.
|
||||
func (ls *laneSet) noteAck(s int, gen uint8, now time.Time) (netip.AddrPort, bool) {
|
||||
if s <= 0 || s >= len(ls.probe) {
|
||||
return netip.AddrPort{}, false
|
||||
}
|
||||
|
||||
ls.mu.Lock()
|
||||
defer ls.mu.Unlock()
|
||||
|
||||
p := &ls.probe[s]
|
||||
if p.sentAt.IsZero() || p.gen != gen {
|
||||
// No probe outstanding, or an ack for a probe we have already given up
|
||||
// on. Either way it says nothing about the lane's current path.
|
||||
return netip.AddrPort{}, false
|
||||
}
|
||||
|
||||
p.sentAt = time.Time{}
|
||||
p.lastAck = now
|
||||
p.fails = 0
|
||||
p.retryAt = time.Time{}
|
||||
|
||||
target := p.target
|
||||
if ls.txAddr[s].Load() != nil {
|
||||
// Keepalive for a lane already up.
|
||||
return target, false
|
||||
}
|
||||
|
||||
ls.txAddr[s].Store(&target)
|
||||
return target, true
|
||||
}
|
||||
|
||||
// probeLanes runs one lane maintenance pass for a peer: it demotes lanes whose
|
||||
// probe went unanswered, re-proves lanes that have been up a while without one,
|
||||
// and probes down lanes the data plane asked for. Driven by the connection
|
||||
// manager's per-tunnel traffic tick, which only fires for a live tunnel — the
|
||||
// same condition that produces lane demand in the first place.
|
||||
func (f *Interface) probeLanes(hostinfo *HostInfo, now time.Time, nb, out []byte) {
|
||||
ls := hostinfo.lanes
|
||||
if ls == nil || ls.txLanes < 2 {
|
||||
return
|
||||
}
|
||||
|
||||
remote := hostinfo.GetRemote()
|
||||
|
||||
ls.mu.Lock()
|
||||
defer ls.mu.Unlock()
|
||||
|
||||
if !remote.IsValid() {
|
||||
// Relayed, or otherwise without a direct path. Lanes are direct-only,
|
||||
// so drop them all; a later tick rebuilds if a direct path returns.
|
||||
ls.resetLocked()
|
||||
return
|
||||
}
|
||||
|
||||
if ls.peerAddr != remote.Addr() {
|
||||
if ls.peerAddr.IsValid() {
|
||||
// A roam is a new path, not a failure: forget the lanes built on
|
||||
// the old one and let demand re-probe from a clean backoff. On the
|
||||
// first pass there is nothing built yet, so just record the address.
|
||||
ls.resetLocked()
|
||||
}
|
||||
ls.peerAddr = remote.Addr()
|
||||
}
|
||||
|
||||
for s := 1; s < ls.txLanes; s++ {
|
||||
p := &ls.probe[s]
|
||||
up := ls.txAddr[s].Load() != nil
|
||||
|
||||
if !p.sentAt.IsZero() {
|
||||
if now.Sub(p.sentAt) < laneProbeTimeout {
|
||||
continue
|
||||
}
|
||||
|
||||
// An aged-out probe is a failure whether it was bringing the lane
|
||||
// up or keeping it up.
|
||||
p.sentAt = time.Time{}
|
||||
p.fails = min(p.fails+1, laneMaxFails)
|
||||
p.retryAt = now.Add(laneRetryDelay(p.fails))
|
||||
if up {
|
||||
ls.txAddr[s].Store(nil)
|
||||
hostinfo.logger(f.l).Info("Multiport lane demoted, probe unanswered", "lane", s, "udpAddr", p.target)
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
if up {
|
||||
if now.Sub(p.lastAck) < laneKeepalive {
|
||||
continue
|
||||
}
|
||||
} else if now.Before(p.retryAt) || !ls.demand[s].Swap(false) {
|
||||
continue
|
||||
}
|
||||
|
||||
p.gen++
|
||||
p.target = ls.laneTargetLocked(s, remote.Addr())
|
||||
if f.sendLaneProbe(hostinfo, s, p.gen, p.target, nb, out) {
|
||||
p.sentAt = now
|
||||
} else {
|
||||
p.fails = min(p.fails+1, laneMaxFails)
|
||||
p.retryAt = now.Add(laneRetryDelay(p.fails))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// resetLocked takes every lane down and clears its probe state, without
|
||||
// counting it as a failure.
|
||||
//
|
||||
// Demand is deliberately left standing: it records that a routine has real
|
||||
// traffic for this peer, which a roam or a relay detour does not change. Keeping
|
||||
// it re-probes the lanes that were actually carrying data as soon as a path
|
||||
// exists again, while a lane whose routine has gone quiet stays down.
|
||||
func (ls *laneSet) resetLocked() {
|
||||
for s := 1; s < len(ls.probe); s++ {
|
||||
ls.txAddr[s].Store(nil)
|
||||
ls.probe[s] = laneProbeState{}
|
||||
}
|
||||
}
|
||||
|
||||
// sendLaneProbe sends a probe on lane s to addr from a socket on lane s's port.
|
||||
// The probe is an ordinary Test packet encrypted with the lane's session, so an
|
||||
// ack proves the whole lane: our source port reached the peer, its reply reached
|
||||
// us, and the keys we derived for this lane match the ones it derived. Reports
|
||||
// whether the probe made it onto the wire.
|
||||
//
|
||||
// It goes out the first socket on the port, since the connection manager runs
|
||||
// this and has no queue of its own; every socket on the port has the same address,
|
||||
// so the probe proves the path for whichever one the data plane picks.
|
||||
func (f *Interface) sendLaneProbe(hostinfo *HostInfo, s int, gen uint8, addr netip.AddrPort, nb, out []byte) bool {
|
||||
// The first probe on a lane is what derives its session.
|
||||
ci, err := hostinfo.lanes.session(s)
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to derive multiport lane session", "error", err, "lane", s)
|
||||
return false
|
||||
}
|
||||
if ci == nil || ci.eKey == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Lock()
|
||||
}
|
||||
c, ok := ci.NextMessageCounter()
|
||||
if !ok {
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Unlock()
|
||||
}
|
||||
f.dropExhausted(hostinfo, c, "Dropping multiport lane probe, lane message counter is exhausted")
|
||||
return false
|
||||
}
|
||||
|
||||
b := header.EncodeLane(out[:0], header.Version, header.Test, header.LaneProbe, hostinfo.remoteIndexId, c, uint8(s))
|
||||
b, err = ci.eKey.EncryptDanger(b, b, []byte{uint8(s), gen}, c, nb)
|
||||
if noiseutil.EncryptLockNeeded {
|
||||
ci.writeLock.Unlock()
|
||||
}
|
||||
if err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to encrypt multiport lane probe", "error", err, "lane", s)
|
||||
return false
|
||||
}
|
||||
|
||||
f.messageMetrics.Tx(header.Test, header.LaneProbe, 1)
|
||||
if err := f.writers[f.laneSock(0, s)].WriteTo(b, addr); err != nil {
|
||||
hostinfo.logger(f.l).Error("Failed to send multiport lane probe", "error", err, "lane", s, "udpAddr", addr)
|
||||
return false
|
||||
}
|
||||
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("Multiport lane probe sent", "lane", s, "gen", gen, "udpAddr", addr)
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// handleLaneProbe answers a peer's lane probe. The ack rides the base tunnel on
|
||||
// purpose: a probe proves the peer's lane s works in its send direction, and
|
||||
// answering on our own lane s would make the result depend on a second path
|
||||
// that may be broken independently.
|
||||
func (f *Interface) handleLaneProbe(hostinfo *HostInfo, lane uint8, payload []byte, rxc *rxContext) {
|
||||
if lane == 0 || len(payload) < 2 {
|
||||
return
|
||||
}
|
||||
|
||||
// Echo the header's lane rather than the payload's, so a peer cannot get us
|
||||
// to vouch for a lane it did not actually probe.
|
||||
f.send(header.Test, header.LaneProbeAck, hostinfo.ConnectionState, hostinfo,
|
||||
[]byte{lane, payload[1]}, rxc.nb, rxc.scratch[:0])
|
||||
}
|
||||
|
||||
// handleLaneProbeAck promotes the lane a peer just acked.
|
||||
func (f *Interface) handleLaneProbeAck(hostinfo *HostInfo, payload []byte) {
|
||||
ls := hostinfo.lanes
|
||||
if ls == nil || len(payload) < 2 {
|
||||
return
|
||||
}
|
||||
|
||||
// The target is worth logging next to the demotion that names the same
|
||||
// address, so a flapping lane can be read off the logs.
|
||||
if target, promoted := ls.noteAck(int(payload[0]), payload[1], time.Now()); promoted {
|
||||
hostinfo.logger(f.l).Info("Multiport lane up", "lane", payload[0], "udpAddr", target)
|
||||
}
|
||||
}
|
||||
-1061
File diff suppressed because it is too large.
Load diff
+81
-11
@@ -15,10 +15,12 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/logging"
|
||||
"github.com/slackhq/nebula/nicfinder"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
@@ -34,12 +36,18 @@ type LightHouse struct {
|
||||
|
||||
myVpnNetworks []netip.Prefix
|
||||
myVpnNetworksTable *bart.Lite
|
||||
punchy *Punchy
|
||||
// myVpnAddrsTable contains our overlay host addrs, as opposed to the overlay networks
|
||||
myVpnAddrsTable *bart.Lite
|
||||
punchy *Punchy
|
||||
|
||||
// localAddrsFn enumerates the underlay addresses we advertise. It is a field so tests can supply simulated
|
||||
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
||||
localAddrsFn func(*LocalAllowList) []netip.Addr
|
||||
|
||||
// lastLocalAddrsErr is the previous localAddrsFn failure. Enumeration runs on every update, so an
|
||||
// unchanged failure is demoted to Debug rather than warning every lighthouse.interval forever.
|
||||
lastLocalAddrsErr atomic.Pointer[string]
|
||||
|
||||
// Local cache of answers from light houses
|
||||
// map of vpn addr to answers
|
||||
addrMap map[netip.Addr]*RemoteList
|
||||
@@ -74,6 +82,8 @@ type LightHouse struct {
|
||||
|
||||
updateTrigger chan struct{}
|
||||
queryChan chan netip.Addr
|
||||
// queryDropped counts queries QueryServer dropped because queryChan was full.
|
||||
queryDropped metrics.Counter
|
||||
|
||||
calculatedRemotes atomic.Pointer[bart.Table[[]*calculatedRemote]] // Maps VpnAddr to []*calculatedRemote
|
||||
|
||||
@@ -104,15 +114,19 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
amLighthouse: amLighthouse,
|
||||
myVpnNetworks: cs.myVpnNetworks,
|
||||
myVpnNetworksTable: cs.myVpnNetworksTable,
|
||||
myVpnAddrsTable: cs.myVpnAddrsTable,
|
||||
addrMap: make(map[netip.Addr]*RemoteList),
|
||||
nebulaPort: nebulaPort,
|
||||
punchy: p,
|
||||
updateTrigger: make(chan struct{}, 1),
|
||||
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 64)),
|
||||
queryChan: make(chan netip.Addr, c.GetUint32("handshakes.query_buffer", 1024)),
|
||||
queryDropped: metrics.GetOrRegisterCounter("lighthouse.query.dropped", nil),
|
||||
l: l,
|
||||
}
|
||||
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
||||
return localAddrs(h.l, al)
|
||||
addrs, err := nicfinder.Find(ctx, h.l, al)
|
||||
h.logLocalAddrsErr(err)
|
||||
return addrs
|
||||
}
|
||||
|
||||
lighthouses := make([]netip.Addr, 0)
|
||||
@@ -124,18 +138,21 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
h.metrics = newLighthouseMetrics()
|
||||
}
|
||||
|
||||
err := h.reload(c, true)
|
||||
err := h.reload(c, true, nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := h.reload(c, false)
|
||||
c.RegisterReloadCallback(func(c *config.C, r *config.Reload) {
|
||||
r.RestartRequiredIfChanged("lighthouse.am_lighthouse", "listen.port", "handshakes.query_buffer", "stats.lighthouse_metrics")
|
||||
err := h.reload(c, false, r)
|
||||
switch v := err.(type) {
|
||||
case *util.ContextualError:
|
||||
v.Log(l)
|
||||
r.Failed()
|
||||
case error:
|
||||
l.Error("failed to reload lighthouse", "error", err)
|
||||
r.Failed()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -176,7 +193,8 @@ func (lh *LightHouse) GetUpdateInterval() int64 {
|
||||
return lh.interval.Load()
|
||||
}
|
||||
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
// r is nil on the initial load
|
||||
func (lh *LightHouse) reload(c *config.C, initial bool, r *config.Reload) error {
|
||||
if initial || c.HasChanged("lighthouse.advertise_addrs") {
|
||||
rawAdvAddrs := c.GetStringSlice("lighthouse.advertise_addrs", []string{})
|
||||
advAddrs := make([]netip.AddrPort, 0)
|
||||
@@ -211,6 +229,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
"addr", rawAddr,
|
||||
"entry", i+1,
|
||||
)
|
||||
r.Failed()
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -345,7 +364,13 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
}
|
||||
}
|
||||
|
||||
if initial || c.HasChanged("relay.relays") {
|
||||
// am_relay decides whether relay.relays applies to us at all
|
||||
if initial || c.HasChanged("relay.relays") || c.HasChanged("relay.am_relay") {
|
||||
var before []netip.Addr
|
||||
if !initial {
|
||||
before = lh.GetRelaysForMe()
|
||||
}
|
||||
|
||||
switch c.GetBool("relay.am_relay", false) {
|
||||
case true:
|
||||
// Relays aren't allowed to specify other relays
|
||||
@@ -363,6 +388,7 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
"relay", v,
|
||||
"error", err,
|
||||
)
|
||||
r.Failed()
|
||||
} else {
|
||||
lh.l.Info("Read relay from config", "relay", v)
|
||||
relaysForMe = append(relaysForMe, configRIP)
|
||||
@@ -370,6 +396,11 @@ func (lh *LightHouse) reload(c *config.C, initial bool) error {
|
||||
}
|
||||
lh.relaysForMe.Store(&relaysForMe)
|
||||
}
|
||||
|
||||
// Tell the lighthouses now rather than at the next interval, but only when what we advertise changed
|
||||
if !initial && !slices.Equal(before, lh.GetRelaysForMe()) {
|
||||
lh.TriggerUpdate()
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
@@ -502,14 +533,19 @@ func (lh *LightHouse) Query(vpnAddr netip.Addr) *RemoteList {
|
||||
return nil
|
||||
}
|
||||
|
||||
// QueryServer is asynchronous so no reply should be expected
|
||||
// QueryServer is asynchronous and non-blocking, no reply should be expected.
|
||||
// If the query channel is full, the query is dropped.
|
||||
func (lh *LightHouse) QueryServer(vpnAddr netip.Addr) {
|
||||
// Don't put lighthouse addrs in the query channel because we can't query lighthouses about lighthouses
|
||||
if lh.amLighthouse || lh.IsLighthouseAddr(vpnAddr) {
|
||||
return
|
||||
}
|
||||
|
||||
lh.queryChan <- vpnAddr
|
||||
select {
|
||||
case lh.queryChan <- vpnAddr:
|
||||
default:
|
||||
lh.queryDropped.Inc(1)
|
||||
}
|
||||
}
|
||||
|
||||
func (lh *LightHouse) QueryCache(vpnAddrs []netip.Addr) *RemoteList {
|
||||
@@ -913,6 +949,26 @@ func (lh *LightHouse) TriggerUpdate() {
|
||||
}
|
||||
}
|
||||
|
||||
// logLocalAddrsErr reports a localAddrs failure at Warn the first time it is seen and at Debug while
|
||||
// it persists unchanged, so a permanent failure does not warn on every update forever.
|
||||
func (lh *LightHouse) logLocalAddrsErr(err error) {
|
||||
if err == nil {
|
||||
lh.lastLocalAddrsErr.Store(nil)
|
||||
return
|
||||
}
|
||||
|
||||
msg := err.Error()
|
||||
prev := lh.lastLocalAddrsErr.Swap(&msg)
|
||||
if prev != nil && *prev == msg {
|
||||
if lh.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
lh.l.Debug("Failed to collect local addresses to advertise", "error", err)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
lh.l.Warn("Failed to collect local addresses to advertise", "error", err)
|
||||
}
|
||||
|
||||
func (lh *LightHouse) SendUpdate() {
|
||||
var v4 []*V4AddrPort
|
||||
var v6 []*V6AddrPort
|
||||
@@ -1158,6 +1214,17 @@ func (lhh *LightHouseHandler) handleHostQuery(n *NebulaMeta, fromVpnAddrs []neti
|
||||
return
|
||||
}
|
||||
|
||||
// Don't respond to requests for us.
|
||||
if lhh.lh.myVpnAddrsTable.Contains(queryVpnAddr) {
|
||||
if lhh.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
lhh.l.Debug("Ignoring HostQuery for one of my own addresses",
|
||||
"fromVpnAddrs", fromVpnAddrs,
|
||||
"queryVpnAddr", queryVpnAddr,
|
||||
)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
found, ln, err := lhh.lh.queryAndPrepMessage(queryVpnAddr, func(c *cache) (int, error) {
|
||||
n = lhh.resetMeta()
|
||||
n.Type = NebulaMeta_HostQueryReply
|
||||
@@ -1194,10 +1261,13 @@ func (lhh *LightHouseHandler) handleHostQuery(n *NebulaMeta, fromVpnAddrs []neti
|
||||
// sendHostPunchNotification signals the other side to punch some zero byte udp packets
|
||||
func (lhh *LightHouseHandler) sendHostPunchNotification(n *NebulaMeta, fromVpnAddrs []netip.Addr, punchNotifDest netip.Addr, w EncWriter) {
|
||||
whereToPunch := fromVpnAddrs[0]
|
||||
// Resolve the target before taking the querier's RemoteList lock below. GetHostInfo takes the
|
||||
// hostmap lock, and the hostmap is taken before the lighthouse, which is taken before a
|
||||
// RemoteList, so looking it up inside the callback would deadlock.
|
||||
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
|
||||
found, ln, err := lhh.lh.queryAndPrepMessage(whereToPunch, func(c *cache) (int, error) {
|
||||
n = lhh.resetMeta()
|
||||
n.Type = NebulaMeta_HostPunchNotification
|
||||
targetHI := lhh.lh.ifce.GetHostInfo(punchNotifDest)
|
||||
var useVersion cert.Version
|
||||
if targetHI == nil {
|
||||
useVersion = lhh.lh.ifce.GetCertState().initiatingVersion
|
||||
|
||||
+368
-64
@@ -1,16 +1,21 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/gaissmai/bart"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"go.yaml.in/yaml/v3"
|
||||
@@ -27,15 +32,27 @@ func TestOldIPv4Only(t *testing.T) {
|
||||
assert.Equal(t, binary.BigEndian.Uint32(bp[:]), m.GetAddr())
|
||||
}
|
||||
|
||||
func testCertState(networks ...netip.Prefix) *CertState {
|
||||
cs := &CertState{
|
||||
myVpnNetworks: networks,
|
||||
myVpnNetworksTable: new(bart.Lite),
|
||||
myVpnAddrs: make([]netip.Addr, 0, len(networks)),
|
||||
myVpnAddrsTable: new(bart.Lite),
|
||||
}
|
||||
|
||||
for _, n := range networks {
|
||||
cs.myVpnNetworksTable.Insert(n)
|
||||
cs.myVpnAddrs = append(cs.myVpnAddrs, n.Addr())
|
||||
cs.myVpnAddrsTable.Insert(netip.PrefixFrom(n.Addr(), n.Addr().BitLen()))
|
||||
}
|
||||
|
||||
return cs
|
||||
}
|
||||
|
||||
func Test_lhStaticMapping(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/16")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
lh1 := "10.128.0.2"
|
||||
|
||||
c := config.NewC(l)
|
||||
@@ -55,12 +72,7 @@ func Test_lhStaticMapping(t *testing.T) {
|
||||
func TestReloadLighthouseInterval(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/16")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
lh1 := "10.128.0.2"
|
||||
|
||||
c := config.NewC(l)
|
||||
@@ -75,27 +87,22 @@ func TestReloadLighthouseInterval(t *testing.T) {
|
||||
lh.ifce = &mockEncWriter{}
|
||||
|
||||
// The first one routine is kicked off by main.go currently, lets make sure that one dies
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5"))
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 5").Err)
|
||||
assert.Equal(t, int64(5), lh.interval.Load())
|
||||
|
||||
// Subsequent calls are killed off by the LightHouse.Reload function
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10"))
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 10").Err)
|
||||
assert.Equal(t, int64(10), lh.interval.Load())
|
||||
|
||||
// If this completes then nothing is stealing our reload routine
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11"))
|
||||
require.NoError(t, c.ReloadConfigString("lighthouse:\n interval: 11").Err)
|
||||
assert.Equal(t, int64(11), lh.interval.Load())
|
||||
}
|
||||
|
||||
func BenchmarkLighthouseHandleRequest(b *testing.B) {
|
||||
l := test.NewLogger()
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/0")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
|
||||
c := config.NewC(l)
|
||||
lh, err := NewLightHouseFromConfig(b.Context(), l, c, cs, nil, nil)
|
||||
@@ -195,12 +202,7 @@ func TestLighthouse_Memory(t *testing.T) {
|
||||
c.Settings["listen"] = map[string]any{"port": 4242}
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
lh.ifce = &mockEncWriter{}
|
||||
require.NoError(t, err)
|
||||
@@ -280,12 +282,7 @@ func TestLighthouse_reload(t *testing.T) {
|
||||
c.Settings["listen"] = map[string]any{"port": 4242}
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
@@ -299,7 +296,7 @@ func TestLighthouse_reload(t *testing.T) {
|
||||
require.NoError(t, err)
|
||||
c.ReloadConfigString(string(rc))
|
||||
|
||||
err = lh.reload(c, false)
|
||||
err = lh.reload(c, false, nil)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
@@ -315,12 +312,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
@@ -342,7 +334,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err := yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
rl := lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -358,7 +350,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -366,7 +358,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.1.1.1:4242")}, rl.CopyAddrs([]netip.Prefix{}))
|
||||
|
||||
// Reload with the same config. An unchanged entry must not duplicate.
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -381,7 +373,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
// Add a second host alongside the first. Both should be present, neither duplicated.
|
||||
nc = map[string]any{
|
||||
@@ -392,7 +384,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
rl = lh.Query(staticHost)
|
||||
require.NotNil(t, rl)
|
||||
@@ -414,7 +406,7 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
}
|
||||
rc, err = yaml.Marshal(nc)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)))
|
||||
require.NoError(t, c.ReloadConfigString(string(rc)).Err)
|
||||
|
||||
_, isStatic := lh.GetStaticHostList()[staticHost]
|
||||
assert.False(t, isStatic)
|
||||
@@ -429,7 +421,9 @@ func TestLighthouse_reloadStaticHostMap(t *testing.T) {
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("3.3.3.3:4242")}, rl.CopyAddrs([]netip.Prefix{}))
|
||||
}
|
||||
|
||||
func newLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, lhh *LightHouseHandler) testLhReply {
|
||||
// sendLHHostRequest delivers a HostQuery to lhh and hands back the writer that
|
||||
// captured what it emitted. Pass a nil filter to see every message.
|
||||
func sendLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, lhh *LightHouseHandler, filter *NebulaMeta_MessageType) *testEncWriter {
|
||||
req := &NebulaMeta{
|
||||
Type: NebulaMeta_HostQuery,
|
||||
Details: &NebulaMetaDetails{},
|
||||
@@ -447,12 +441,59 @@ func newLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, l
|
||||
panic(err)
|
||||
}
|
||||
|
||||
filter := NebulaMeta_HostQueryReply
|
||||
w := &testEncWriter{
|
||||
metaFilter: &filter,
|
||||
}
|
||||
w := &testEncWriter{metaFilter: filter}
|
||||
lhh.HandleRequest(fromAddr, []netip.Addr{myVpnIp}, b, w)
|
||||
return w.lastReply
|
||||
return w
|
||||
}
|
||||
|
||||
func newLHHostRequest(fromAddr netip.AddrPort, myVpnIp, queryVpnIp netip.Addr, lhh *LightHouseHandler) testLhReply {
|
||||
filter := NebulaMeta_HostQueryReply
|
||||
return sendLHHostRequest(fromAddr, myVpnIp, queryVpnIp, lhh, &filter).lastReply
|
||||
}
|
||||
|
||||
func TestLighthouse_IgnoresHostQueryForItself(t *testing.T) {
|
||||
// Validate that we don't answer host queries for our own address.
|
||||
l := test.NewLogger()
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
myVpnIp := myVpnNet.Addr()
|
||||
|
||||
c := config.NewC(l)
|
||||
c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
|
||||
c.Settings["listen"] = map[string]any{"port": 4242}
|
||||
// Add a static_host_map entry for ourselves, so our address
|
||||
// is in the addrMap.
|
||||
c.Settings["static_host_map"] = map[string]any{
|
||||
myVpnIp.String(): []any{"192.168.100.1:4242"},
|
||||
}
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
|
||||
require.NoError(t, err)
|
||||
lh.ifce = &mockEncWriter{}
|
||||
lhh := lh.NewRequestHandler()
|
||||
|
||||
peerVpnIp := netip.MustParseAddr("10.128.0.2")
|
||||
peerUdpAddr := netip.MustParseAddrPort("10.0.0.2:4242")
|
||||
otherVpnIp := netip.MustParseAddr("10.128.0.3")
|
||||
otherUdpAddr := netip.MustParseAddrPort("10.0.0.3:4242")
|
||||
|
||||
newLHHostUpdate(peerUdpAddr, peerVpnIp, []netip.AddrPort{peerUdpAddr}, lhh)
|
||||
newLHHostUpdate(otherUdpAddr, otherVpnIp, []netip.AddrPort{otherUdpAddr}, lhh)
|
||||
|
||||
// Control: a query about a real peer is still answered, and still ends with
|
||||
// the punch notification aimed at the host that was asked about.
|
||||
w := sendLHHostRequest(peerUdpAddr, peerVpnIp, otherVpnIp, lhh, nil)
|
||||
require.NotNil(t, w.lastReply.msg)
|
||||
assert.Equal(t, NebulaMeta_HostPunchNotification, w.lastReply.msg.Type)
|
||||
assert.Equal(t, otherVpnIp, w.lastReply.vpnIp)
|
||||
|
||||
// Now validate that we don't send to ourselves.
|
||||
found, _, err := lh.queryAndPrepMessage(myVpnIp, func(*cache) (int, error) { return 0, nil })
|
||||
require.NoError(t, err)
|
||||
require.True(t, found, "the lighthouse should hold a cache entry for its own address")
|
||||
|
||||
w = sendLHHostRequest(peerUdpAddr, peerVpnIp, myVpnIp, lhh, nil)
|
||||
assert.Nil(t, w.lastReply.msg, "a query about our own address must produce no reply and no punch notification")
|
||||
}
|
||||
|
||||
func newLHHostUpdate(fromAddr netip.AddrPort, vpnIp netip.Addr, addrs []netip.AddrPort, lhh *LightHouseHandler) {
|
||||
@@ -642,12 +683,7 @@ func TestLighthouse_Dont_Delete_Static_Hosts(t *testing.T) {
|
||||
}
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
lh.ifce = &mockEncWriter{}
|
||||
@@ -708,12 +744,7 @@ func TestLighthouse_DeletesWork(t *testing.T) {
|
||||
}
|
||||
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
nt := new(bart.Lite)
|
||||
nt.Insert(myVpnNet)
|
||||
cs := &CertState{
|
||||
myVpnNetworks: []netip.Prefix{myVpnNet},
|
||||
myVpnNetworksTable: nt,
|
||||
}
|
||||
cs := testCertState(myVpnNet)
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
lh.ifce = &mockEncWriter{}
|
||||
@@ -738,3 +769,276 @@ func TestLighthouse_DeletesWork(t *testing.T) {
|
||||
out = lh.Query(testHost)
|
||||
assert.Nil(t, out)
|
||||
}
|
||||
|
||||
func TestLightHouse_logLocalAddrsErr(t *testing.T) {
|
||||
out := &bytes.Buffer{}
|
||||
lh := &LightHouse{l: test.NewLoggerWithOutput(out)}
|
||||
|
||||
// The first sighting of a failure warns.
|
||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
assert.Contains(t, out.String(), "permission denied")
|
||||
|
||||
// Repeating unchanged does not warn again, which is what keeps a permanent failure from warning
|
||||
// on every lighthouse.interval for the life of the process.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
||||
assert.NotContains(t, out.String(), "level=WARN")
|
||||
|
||||
// A different failure is a new event and warns.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(errors.New("something else"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
assert.Contains(t, out.String(), "something else")
|
||||
|
||||
// Recovering resets, so the same failure returning later warns again.
|
||||
out.Reset()
|
||||
lh.logLocalAddrsErr(nil)
|
||||
assert.Empty(t, out.String())
|
||||
lh.logLocalAddrsErr(errors.New("something else"))
|
||||
assert.Contains(t, out.String(), "level=WARN")
|
||||
}
|
||||
|
||||
// heldEncWriter holds the query worker in its first GetHostInfo until release closes.
|
||||
type heldEncWriter struct {
|
||||
mockEncWriter
|
||||
once sync.Once
|
||||
held chan struct{}
|
||||
release chan struct{}
|
||||
}
|
||||
|
||||
func (w *heldEncWriter) GetHostInfo(netip.Addr) *HostInfo {
|
||||
w.once.Do(func() { close(w.held) })
|
||||
<-w.release
|
||||
return nil
|
||||
}
|
||||
|
||||
// QueryServer never waits on the query worker, since the packet readers call it and nothing drains the channel at
|
||||
// shutdown; a query that finds the channel full is dropped and counted. The worker is held on its first query so the
|
||||
// channel fills.
|
||||
func TestLighthouse_QueryServerDoesNotBlock(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
cs := testCertState(netip.MustParsePrefix("10.128.0.1/16"))
|
||||
lh1 := "10.128.0.2"
|
||||
c := config.NewC(l)
|
||||
c.Settings["lighthouse"] = map[string]any{"hosts": []any{lh1}}
|
||||
c.Settings["static_host_map"] = map[string]any{lh1: []any{"1.1.1.1:4242"}}
|
||||
c.Settings["handshakes"] = map[string]any{"query_buffer": 1}
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, cs, nil, nil)
|
||||
require.NoError(t, err)
|
||||
w := &heldEncWriter{held: make(chan struct{}), release: make(chan struct{})}
|
||||
lh.ifce = w
|
||||
t.Cleanup(func() { close(w.release) })
|
||||
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.10"))
|
||||
select {
|
||||
case <-w.held:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("the query worker never took the first query")
|
||||
}
|
||||
dropped := lh.queryDropped.Count()
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.11"))
|
||||
lh.QueryServer(netip.MustParseAddr("10.128.0.12"))
|
||||
close(done)
|
||||
}()
|
||||
select {
|
||||
case <-done:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("QueryServer blocked on a full query channel")
|
||||
}
|
||||
assert.EqualValues(t, 1, lh.queryDropped.Count()-dropped)
|
||||
}
|
||||
|
||||
// hostmapEncWriter answers GetHostInfo from a real hostmap, the way Interface does.
|
||||
type hostmapEncWriter struct {
|
||||
mockEncWriter
|
||||
hm *HostMap
|
||||
}
|
||||
|
||||
func (w *hostmapEncWriter) GetHostInfo(a netip.Addr) *HostInfo { return w.hm.QueryVpnAddr(a) }
|
||||
func (w *hostmapEncWriter) GetCertState() *CertState {
|
||||
return &CertState{initiatingVersion: cert.Version1}
|
||||
}
|
||||
|
||||
// A lighthouse runs four paths that each hold one lock while waiting for the next: CheckAndComplete
|
||||
// holds the hostmap and takes the handshake manager, StartHandshake holds the handshake manager and
|
||||
// takes the lighthouse, a host update holds the lighthouse and takes the sender's RemoteList, and a
|
||||
// punch notification holds the querier's RemoteList while it resolves the target. If that last step
|
||||
// reaches the hostmap under the RemoteList lock, the four deadlock. Drive them all at once.
|
||||
func TestLighthouse_PunchNotificationDoesNotCloseLockCycle(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
myVpnNet := netip.MustParsePrefix("10.128.0.1/24")
|
||||
|
||||
c := config.NewC(l)
|
||||
c.Settings["lighthouse"] = map[string]any{"am_lighthouse": true}
|
||||
c.Settings["listen"] = map[string]any{"port": 4242}
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(myVpnNet), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
mainHM := newHostMap(l)
|
||||
pr := []netip.Prefix{}
|
||||
mainHM.preferredRanges.Store(&pr)
|
||||
lh.ifce = &hostmapEncWriter{hm: mainHM}
|
||||
|
||||
hm := NewHandshakeManager(l, mainHM, lh, &udp.NoopConn{}, defaultHandshakeConfig)
|
||||
f := &Interface{hostMap: mainHM, lightHouse: lh, handshakeManager: hm, l: l}
|
||||
hm.f = f
|
||||
|
||||
peer := netip.MustParseAddr("10.128.0.2")
|
||||
peerUdp := netip.MustParseAddrPort("10.0.0.2:4242")
|
||||
target := netip.MustParseAddr("10.128.0.3")
|
||||
targetUdp := netip.MustParseAddrPort("10.0.0.3:4242")
|
||||
outbound := netip.MustParseAddr("10.128.0.4")
|
||||
inbound := netip.MustParseAddr("10.128.0.5")
|
||||
|
||||
seed := lh.NewRequestHandler()
|
||||
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, seed)
|
||||
newLHHostUpdate(targetUdp, target, []netip.AddrPort{targetUdp}, seed)
|
||||
|
||||
stop := make(chan struct{})
|
||||
var wg sync.WaitGroup
|
||||
loop := func(body func()) {
|
||||
defer wg.Done()
|
||||
for {
|
||||
select {
|
||||
case <-stop:
|
||||
return
|
||||
default:
|
||||
body()
|
||||
}
|
||||
}
|
||||
}
|
||||
wg.Add(4)
|
||||
|
||||
// Outbound handshakes keep starting and being dropped.
|
||||
go loop(func() {
|
||||
hm.DeleteHostInfo(hm.StartHandshake(outbound, nil))
|
||||
})
|
||||
|
||||
// Inbound handshakes keep completing and being torn down.
|
||||
var idx uint32
|
||||
go loop(func() {
|
||||
idx++
|
||||
hi := &HostInfo{
|
||||
vpnAddrs: []netip.Addr{inbound},
|
||||
localIndexId: idx,
|
||||
remoteIndexId: idx,
|
||||
remotes: lh.QueryCache([]netip.Addr{inbound}),
|
||||
HandshakePacket: map[uint8][]byte{handshakePacketStage0: {byte(idx)}},
|
||||
}
|
||||
if _, err := hm.CheckAndComplete(hi, handshakePacketStage0, f); err == nil {
|
||||
mainHM.DeleteHostInfo(hi)
|
||||
}
|
||||
})
|
||||
|
||||
// The peer keeps sending host updates.
|
||||
updates := lh.NewRequestHandler()
|
||||
go loop(func() {
|
||||
newLHHostUpdate(peerUdp, peer, []netip.AddrPort{peerUdp}, updates)
|
||||
})
|
||||
|
||||
// The same peer keeps querying for the target, which ends in a punch notification.
|
||||
queries := lh.NewRequestHandler()
|
||||
go loop(func() {
|
||||
sendLHHostRequest(peerUdp, peer, target, queries, nil)
|
||||
})
|
||||
|
||||
time.Sleep(time.Second)
|
||||
close(stop)
|
||||
done := make(chan struct{})
|
||||
go func() { wg.Wait(); close(done) }()
|
||||
select {
|
||||
case <-done:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("deadlock: the lighthouse paths never finished after stop was signalled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadRelaysTriggersUpdate(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\n"
|
||||
require.NoError(t, c.LoadString(base+"relay:\n relays: [10.128.0.5]\n"))
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6]\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
// The config changed but what we advertise did not, a bad entry is skipped
|
||||
require.NoError(t, c.ReloadConfigString(base+"relay:\n relays: [10.128.0.6, nope]\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.6")}, lh.GetRelaysForMe())
|
||||
assert.Empty(t, lh.updateTrigger)
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadAmRelayAlone(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\nlisten:\n port: 4242\nrelay:\n relays: [10.128.0.5]\n"
|
||||
require.NoError(t, c.LoadString(base+" am_relay: false\n"))
|
||||
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
|
||||
// Relays aren't allowed to have relays, flipping am_relay alone must drop them and tell the lighthouses
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: true\n").Err)
|
||||
assert.Empty(t, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n").Err)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
}
|
||||
|
||||
func TestLighthouse_reloadRestartRequired(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
base := "lighthouse:\n am_lighthouse: true\n"
|
||||
require.NoError(t, c.LoadString(base+"listen:\n port: 4242\n"))
|
||||
|
||||
_, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString(base + "listen:\n port: 4242\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.False(t, res.RestartRequired)
|
||||
res = c.ReloadConfigString(base + "listen:\n port: 4243\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.RestartRequired)
|
||||
}
|
||||
|
||||
// A relay that doesn't parse is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadBadRelayFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nrelay:\n relays: [10.128.0.2, nope]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.2")}, lh.GetRelaysForMe())
|
||||
}
|
||||
|
||||
// An advertise_addrs entry inside our own network is skipped and the rest are used, the reload says one was skipped
|
||||
func TestLighthouse_reloadAdvertiseAddrInNetworkFails(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString("listen:\n port: 4242\n"))
|
||||
lh, err := NewLightHouseFromConfig(t.Context(), l, c, testCertState(netip.MustParsePrefix("10.128.0.1/24")), nil, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
res := c.ReloadConfigString("listen:\n port: 4242\nlighthouse:\n advertise_addrs: [\"1.2.3.4:4242\", \"10.128.0.5:4242\"]\n")
|
||||
require.NoError(t, res.Err)
|
||||
assert.True(t, res.Failed)
|
||||
assert.Equal(t, []netip.AddrPort{netip.MustParseAddrPort("1.2.3.4:4242")}, lh.GetAdvertiseAddrs())
|
||||
}
|
||||
@@ -0,0 +1,79 @@
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
)
|
||||
|
||||
// Access is who may reach a socket beyond the account nebula runs as: the node's mode,
|
||||
// and the group that shares the socket when the config names one.
|
||||
//
|
||||
// It is the dockerd model (-G): the operator names a group, nebula hands the socket to
|
||||
// it, and who is in the group is managed outside nebula. On unix the mode is the
|
||||
// socket node's and the group becomes its owning group; on windows the group is an
|
||||
// entry in the pipe's security descriptor and the mode means nothing to a pipe.
|
||||
type Access struct {
|
||||
Mode os.FileMode
|
||||
Group Group
|
||||
}
|
||||
|
||||
// Group is a group named in the config, resolved to what the platform checks. The zero
|
||||
// Group is none.
|
||||
type Group struct {
|
||||
// Name is what the config said.
|
||||
Name string
|
||||
|
||||
// ID is the platform's identifier for it: a gid on unix, a SID on windows.
|
||||
ID string
|
||||
}
|
||||
|
||||
const (
|
||||
// ownerOnlyMode is a socket's mode when no group shares it: the account nebula runs
|
||||
// as, and nobody else.
|
||||
ownerOnlyMode os.FileMode = 0600
|
||||
|
||||
// groupSocketMode is the mode a socket takes when a group shares it and the config
|
||||
// names no other: the account nebula runs as and the group, and nobody else.
|
||||
groupSocketMode os.FileMode = 0660
|
||||
)
|
||||
|
||||
// errReopenForAccess is returned by applyAccess on a platform whose access control is
|
||||
// fixed when the endpoint is created, so a change means creating it again.
|
||||
var errReopenForAccess = errors.New("access is fixed at listen time")
|
||||
|
||||
// ownerOnly is the control socket's access when no group is configured. The mode
|
||||
// itself is not configurable there; what an operator can choose is a group,
|
||||
// CtlGroupKey, which makes it groupSocketMode.
|
||||
func ownerOnly() Access { return Access{Mode: ownerOnlyMode} }
|
||||
|
||||
// shared reports whether a group shares the socket.
|
||||
func (a Access) shared() bool { return a.Group.ID != "" }
|
||||
|
||||
// String renders the access for a log line.
|
||||
func (a Access) String() string {
|
||||
if !a.shared() {
|
||||
return modeString(a.Mode)
|
||||
}
|
||||
return fmt.Sprintf("%s group %s (%s)", modeString(a.Mode), a.Group.Name, a.Group.ID)
|
||||
}
|
||||
|
||||
// groupFromConfig reads the group a key names, the zero Group when it names none. The
|
||||
// name is resolved here, when the config is read, so a group that does not exist is a
|
||||
// config error reported with the key rather than a bind that fails later.
|
||||
func groupFromConfig(c interface{ GetString(string, string) string }, key string) (Group, error) {
|
||||
name := c.GetString(key, "")
|
||||
if name == "" {
|
||||
return Group{}, nil
|
||||
}
|
||||
|
||||
id, err := lookupGroupID(name)
|
||||
if err != nil {
|
||||
return Group{}, fmt.Errorf("%s: %w", key, err)
|
||||
}
|
||||
return Group{Name: name, ID: id}, nil
|
||||
}
|
||||
|
||||
func modeString(m os.FileMode) string {
|
||||
return fmt.Sprintf("%04o", m)
|
||||
}
|
||||
@@ -0,0 +1,176 @@
|
||||
//go:build !windows
|
||||
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"os/user"
|
||||
"strconv"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// ownGroup returns a group this process may hand a socket to: its own effective group,
|
||||
// by name and by gid, which is the one chown accepts from an unprivileged user.
|
||||
func ownGroup(t *testing.T) (name, gid string) {
|
||||
t.Helper()
|
||||
gid = strconv.Itoa(os.Getegid())
|
||||
g, err := user.LookupGroupId(gid)
|
||||
require.NoError(t, err)
|
||||
return g.Name, gid
|
||||
}
|
||||
|
||||
func socketGroup(t *testing.T, path string) uint32 {
|
||||
t.Helper()
|
||||
fi, err := os.Lstat(path)
|
||||
require.NoError(t, err)
|
||||
st, ok := fi.Sys().(*syscall.Stat_t)
|
||||
require.True(t, ok)
|
||||
return uint32(st.Gid)
|
||||
}
|
||||
|
||||
// TestLookupGroupID: a group is named as the host names it or by its gid; a gid the
|
||||
// host does not list is accepted as chown would accept it, and a name it does not list
|
||||
// is a mistake to report.
|
||||
func TestLookupGroupID(t *testing.T) {
|
||||
name, gid := ownGroup(t)
|
||||
|
||||
got, err := lookupGroupID(name)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, gid, got)
|
||||
|
||||
got, err = lookupGroupID(gid)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, gid, got)
|
||||
|
||||
got, err = lookupGroupID("4000000000")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "4000000000", got)
|
||||
|
||||
_, err = lookupGroupID("no-such-group-nebula-test")
|
||||
require.ErrorContains(t, err, "does not exist")
|
||||
}
|
||||
|
||||
// TestControlAccessFromConfig: no group is the owner-only socket; a group is 0660 with
|
||||
// that group; a group the host does not know is a config error naming the key.
|
||||
func TestControlAccessFromConfig(t *testing.T) {
|
||||
name, gid := ownGroup(t)
|
||||
load := func(body string) (Access, error) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString(body))
|
||||
return controlAccessFrom(c)
|
||||
}
|
||||
|
||||
acc, err := load("local_api: {}\n")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, ownerOnly(), acc)
|
||||
|
||||
acc, err = load("local_api:\n control:\n group: " + name + "\n")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, os.FileMode(0660), acc.Mode)
|
||||
assert.Equal(t, name, acc.Group.Name)
|
||||
assert.Equal(t, gid, acc.Group.ID)
|
||||
|
||||
_, err = load("local_api:\n control:\n group: no-such-group-nebula-test\n")
|
||||
require.ErrorContains(t, err, CtlGroupKey)
|
||||
assert.ErrorContains(t, err, "does not exist")
|
||||
}
|
||||
|
||||
// TestControlSocketIsHandedToTheGroup: the socket is created with the group's gid and
|
||||
// 0660, whatever the umask, and a reload that takes the group away tightens the socket
|
||||
// in place, without moving it.
|
||||
func TestControlSocketIsHandedToTheGroup(t *testing.T) {
|
||||
old := unix.Umask(0077)
|
||||
defer unix.Umask(old)
|
||||
|
||||
name, gid := ownGroup(t)
|
||||
want, err := strconv.ParseUint(gid, 10, 32)
|
||||
require.NoError(t, err)
|
||||
|
||||
s := NewServer(test.NewLogger(), basicRegistry())
|
||||
path := testSocket(t)
|
||||
require.NoError(t, s.Rebind(context.Background(), path, Access{Mode: 0660, Group: Group{Name: name, ID: gid}}))
|
||||
defer s.Stop()
|
||||
|
||||
fi, err := os.Lstat(path)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, os.FileMode(0660), fi.Mode().Perm())
|
||||
assert.Equal(t, uint32(want), socketGroup(t, path))
|
||||
|
||||
require.NoError(t, s.Rebind(context.Background(), path, ownerOnly()))
|
||||
fi, err = os.Lstat(path)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, os.FileMode(0600), fi.Mode().Perm())
|
||||
assert.Equal(t, path, s.Path())
|
||||
|
||||
_, err = (&Client{Path: path}).Describe()
|
||||
require.NoError(t, err, "the same listener is still serving")
|
||||
}
|
||||
|
||||
// TestControlSocketWithAGroupTrustsTheKernel: with a group sharing the socket, the
|
||||
// kernel's check on connect is the access control and the daemon's peer check stands
|
||||
// aside, so a connection the peer check alone would refuse is served. Without a group
|
||||
// the same connection is refused; see TestPeerCheckRefusesAnotherUser.
|
||||
func TestControlSocketWithAGroupTrustsTheKernel(t *testing.T) {
|
||||
if !peerCheckSupported {
|
||||
t.Skip("no peer credentials on this platform")
|
||||
}
|
||||
name, gid := ownGroup(t)
|
||||
|
||||
me := currentUID()
|
||||
asUID(t, me+1)
|
||||
s := NewServer(test.NewLogger(), basicRegistry())
|
||||
asUID(t, me)
|
||||
|
||||
path := testSocket(t)
|
||||
require.NoError(t, s.Rebind(context.Background(), path, Access{Mode: 0660, Group: Group{Name: name, ID: gid}}))
|
||||
defer s.Stop()
|
||||
|
||||
_, err := (&Client{Path: path}).Describe()
|
||||
require.NoError(t, err, "the socket's group admitted us; the peer check must not refuse")
|
||||
|
||||
// Taking the group away on a reload puts the peer check back.
|
||||
require.NoError(t, s.Rebind(context.Background(), path, ownerOnly()))
|
||||
_, err = (&Client{Path: path}).Describe()
|
||||
require.ErrorContains(t, err, "not permitted")
|
||||
}
|
||||
|
||||
// TestRemovingTheGroupHandsTheSocketBack: a reload that drops the group key leaves the
|
||||
// mode the operator set but returns the socket to the daemon's own group, so the old
|
||||
// group's members are no longer admitted. The socket is first handed to a group this
|
||||
// process belongs to other than its own, which not every host offers.
|
||||
func TestRemovingTheGroupHandsTheSocketBack(t *testing.T) {
|
||||
own := os.Getegid()
|
||||
groups, err := os.Getgroups()
|
||||
require.NoError(t, err)
|
||||
other := -1
|
||||
for _, g := range groups {
|
||||
if g != own {
|
||||
other = g
|
||||
break
|
||||
}
|
||||
}
|
||||
if other < 0 {
|
||||
t.Skip("this process belongs to no group but its own")
|
||||
}
|
||||
gid := strconv.Itoa(other)
|
||||
|
||||
s := NewServer(test.NewLogger(), basicRegistry())
|
||||
path := testSocket(t)
|
||||
require.NoError(t, s.Rebind(context.Background(), path, Access{Mode: 0660, Group: Group{Name: gid, ID: gid}}))
|
||||
defer s.Stop()
|
||||
assert.Equal(t, uint32(other), socketGroup(t, path))
|
||||
|
||||
require.NoError(t, s.Rebind(context.Background(), path, Access{Mode: 0660}))
|
||||
assert.Equal(t, uint32(own), socketGroup(t, path), "the daemon's own group again")
|
||||
fi, err := os.Lstat(path)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, os.FileMode(0660), fi.Mode().Perm(), "the mode is the operator's")
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
//go:build windows
|
||||
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/windows"
|
||||
)
|
||||
|
||||
// TestLookupGroupIDOnWindows: an account name resolves to its SID, a SID written out
|
||||
// is accepted as it is, and an account the host does not know is reported.
|
||||
func TestLookupGroupIDOnWindows(t *testing.T) {
|
||||
users, err := windows.CreateWellKnownSid(windows.WinBuiltinUsersSid)
|
||||
require.NoError(t, err)
|
||||
|
||||
got, err := lookupGroupID("Users")
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, users.String(), got)
|
||||
|
||||
got, err = lookupGroupID(users.String())
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, users.String(), got)
|
||||
|
||||
_, err = lookupGroupID("no-such-account-nebula-test")
|
||||
require.ErrorContains(t, err, "does not exist")
|
||||
}
|
||||
|
||||
// TestSDDLAdmitsTheGroup: the descriptor is the owner, SYSTEM and Administrators with
|
||||
// full access, plus the group with what a client needs and nothing generic, so a
|
||||
// member cannot create an instance of the pipe; see pipeClientAccess.
|
||||
func TestSDDLAdmitsTheGroup(t *testing.T) {
|
||||
sddl, err := sddlFor(ownerOnly())
|
||||
require.NoError(t, err)
|
||||
assert.NotContains(t, sddl, "S-1-5-32-545")
|
||||
|
||||
sddl, err = sddlFor(Access{Mode: groupSocketMode, Group: Group{Name: "Users", ID: "S-1-5-32-545"}})
|
||||
require.NoError(t, err)
|
||||
assert.Contains(t, sddl, "(A;;GA;;;SY)(A;;GA;;;BA)(A;;0x120083;;;S-1-5-32-545)")
|
||||
assert.Zero(t, pipeClientAccess&windows.FILE_APPEND_DATA, "FILE_APPEND_DATA is FILE_CREATE_PIPE_INSTANCE on a pipe")
|
||||
assert.Zero(t, pipeClientAccess&(windows.GENERIC_READ|windows.GENERIC_WRITE|windows.GENERIC_ALL))
|
||||
}
|
||||
@@ -0,0 +1,163 @@
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/commands"
|
||||
)
|
||||
|
||||
// DialTimeout bounds the connect to a socket that exists but is not being served.
|
||||
const DialTimeout = 5 * time.Second
|
||||
|
||||
// ResponseTimeout bounds the exchange once connected: sending the request and waiting
|
||||
// for the daemon's answer. The daemon drops a client that is slow to send in 10s and one
|
||||
// that is slow to read in 30s, so this is the other side of the same bargain, with room
|
||||
// for the slowest command (a hostmap dump on a large network) before a stalled daemon is
|
||||
// given up on. Client.Timeout overrides it.
|
||||
const ResponseTimeout = 60 * time.Second
|
||||
|
||||
// MaxResponseBytes bounds what a client will read back. A response carries one command's
|
||||
// output, and a hostmap dump on a large network is the realistic worst case.
|
||||
const MaxResponseBytes = 64 << 20
|
||||
|
||||
// Client talks to a nebula listening at Path.
|
||||
type Client struct {
|
||||
Path string
|
||||
|
||||
// Timeout bounds the request and response once connected. Zero means
|
||||
// ResponseTimeout.
|
||||
Timeout time.Duration
|
||||
}
|
||||
|
||||
// ReplyError is an answer the client could not read: the daemon was reached and wrote
|
||||
// something back, but not a response this client understands. The daemon is not
|
||||
// nebula, or not a version this client speaks to.
|
||||
type ReplyError struct {
|
||||
Err error
|
||||
}
|
||||
|
||||
func (e *ReplyError) Error() string { return "the daemon's reply could not be read: " + e.Err.Error() }
|
||||
func (e *ReplyError) Unwrap() error { return e.Err }
|
||||
|
||||
// DaemonError is a refusal the daemon answered with: the connection worked, the request
|
||||
// was read, and the daemon said no. It is told apart from a failure to reach the daemon
|
||||
// so that a client does not send its user after a socket path, or a sudo, when the daemon
|
||||
// was right there and answered. A protocol version the daemon does not speak, a socket at
|
||||
// its connection limit and a peer the daemon will not serve all arrive as one of these.
|
||||
type DaemonError struct {
|
||||
Msg string
|
||||
}
|
||||
|
||||
func (e *DaemonError) Error() string { return e.Msg }
|
||||
|
||||
// Describe asks the daemon which commands it serves and what parameters they take, so a
|
||||
// client can offer them without having been built against this daemon.
|
||||
func (c *Client) Describe() ([]commands.CommandSchema, error) {
|
||||
res, err := c.do(&Request{Version: ProtocolVersion, Describe: true})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if res.Error != "" {
|
||||
return nil, &DaemonError{Msg: res.Error}
|
||||
}
|
||||
|
||||
schema := []commands.CommandSchema{}
|
||||
if err := json.Unmarshal(res.Result, &schema); err != nil {
|
||||
return nil, &ReplyError{Err: fmt.Errorf("could not parse the command schema: %w", err)}
|
||||
}
|
||||
|
||||
return schema, nil
|
||||
}
|
||||
|
||||
// Invoke runs one command and returns what the daemon said. params are the command's
|
||||
// options by name, as the strings a command line parsed them from; a program speaking
|
||||
// the protocol directly may send JSON's own types instead, see Request.Params. An empty
|
||||
// format asks for JSON, which is the API's default; "text" asks the daemon to apply the
|
||||
// command's own human rendering.
|
||||
func (c *Client) Invoke(command string, params map[string]string, args []string, format string) (*Response, error) {
|
||||
var wire map[string]any
|
||||
if len(params) > 0 {
|
||||
wire = make(map[string]any, len(params))
|
||||
for k, v := range params {
|
||||
wire[k] = v
|
||||
}
|
||||
}
|
||||
|
||||
return c.do(&Request{
|
||||
Version: ProtocolVersion,
|
||||
Command: command,
|
||||
Params: wire,
|
||||
Args: args,
|
||||
Format: format,
|
||||
})
|
||||
}
|
||||
|
||||
// do sends one request and reads the one response.
|
||||
//
|
||||
// Nothing is checked about the socket before the connect: its mode is the kernel's to
|
||||
// enforce, and a socket that is not ours to connect to is refused there with a
|
||||
// permission error, which the caller turns into advice.
|
||||
func (c *Client) do(req *Request) (*Response, error) {
|
||||
conn, err := dial(c.Path, DialTimeout)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer conn.Close()
|
||||
|
||||
// Without this a daemon that accepts and then stalls, blocked inside a command or
|
||||
// stopped with SIGSTOP, hangs the client for good, and a script wrapping it never
|
||||
// completes. One deadline covers the write and the read: the answer is due within
|
||||
// the budget, however the time is spent.
|
||||
timeout := c.Timeout
|
||||
if timeout <= 0 {
|
||||
timeout = ResponseTimeout
|
||||
}
|
||||
_ = conn.SetDeadline(time.Now().Add(timeout))
|
||||
|
||||
// If we get a write error, save that fact but then look for a response from the server.
|
||||
// Some error conditions manifest as the server accepting our connection, writing an
|
||||
// error, and then closing the connection. Our write races against that close.
|
||||
writeErr := error(nil)
|
||||
if err := writeFrame(conn, req); err != nil {
|
||||
writeErr = fmt.Errorf("could not send request: %w", err)
|
||||
}
|
||||
|
||||
res, err := readResponse(conn)
|
||||
if err != nil {
|
||||
// Something answered and it was not a response: the daemon was reached, and
|
||||
// that is the message even when it hung up before the request was written,
|
||||
// which a daemon that is not nebula is likely to do.
|
||||
var fe *frameError
|
||||
if errors.As(err, &fe) {
|
||||
return nil, &ReplyError{Err: err}
|
||||
}
|
||||
if writeErr != nil {
|
||||
return nil, writeErr
|
||||
}
|
||||
var ne net.Error
|
||||
if errors.As(err, &ne) && ne.Timeout() {
|
||||
return nil, fmt.Errorf("the daemon did not answer within %s", timeout)
|
||||
}
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return res, nil
|
||||
}
|
||||
|
||||
func readResponse(conn net.Conn) (*Response, error) {
|
||||
res := &Response{}
|
||||
if err := readFrame(conn, MaxResponseBytes, "response", res, false); err != nil {
|
||||
if errors.Is(err, io.EOF) {
|
||||
return nil, errors.New("the daemon closed the connection without answering")
|
||||
}
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return res, nil
|
||||
}
|
||||
@@ -0,0 +1,39 @@
|
||||
//go:build !windows
|
||||
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"os/user"
|
||||
"strconv"
|
||||
)
|
||||
|
||||
// lookupGroupID resolves a group's name, or a numeric gid, to the gid as a string. A
|
||||
// gid that the group database does not list is accepted as chown would accept it: the
|
||||
// operator may be naming a group the host will learn about later, or one that only a
|
||||
// directory service knows.
|
||||
func lookupGroupID(name string) (string, error) {
|
||||
if g, err := user.LookupGroup(name); err == nil {
|
||||
return g.Gid, nil
|
||||
}
|
||||
|
||||
if _, err := strconv.ParseUint(name, 10, 32); err == nil {
|
||||
return name, nil
|
||||
}
|
||||
|
||||
return "", fmt.Errorf("group %q does not exist on this host", name)
|
||||
}
|
||||
|
||||
// gidFor returns the gid the socket is owned by under acc: the configured group's, or
|
||||
// the daemon's own effective group when none is configured.
|
||||
func gidFor(acc Access) (int, error) {
|
||||
if !acc.shared() {
|
||||
return os.Getegid(), nil
|
||||
}
|
||||
gid, err := strconv.ParseUint(acc.Group.ID, 10, 32)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("group %q resolved to %q, which is not a gid", acc.Group.Name, acc.Group.ID)
|
||||
}
|
||||
return int(gid), nil
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
//go:build windows
|
||||
|
||||
package localapi
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/sys/windows"
|
||||
)
|
||||
|
||||
// lookupGroupID resolves an account name, local or domain qualified, or a SID written
|
||||
// out, to the SID as a string, which is how the pipe's security descriptor names it.
|
||||
// Any account the host can resolve is accepted, as docker accepts any SID for its -G: a
|
||||
// group is the natural thing to name, but the descriptor does not care.
|
||||
func lookupGroupID(name string) (string, error) {
|
||||
if strings.HasPrefix(strings.ToUpper(name), "S-1-") {
|
||||
sid, err := windows.StringToSid(name)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("%q is not a SID: %w", name, err)
|
||||
}
|
||||
return sid.String(), nil
|
||||
}
|
||||
|
||||
sid, _, _, err := windows.LookupSID("", name)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("account %q does not exist on this host: %w", name, err)
|
||||
}
|
||||
return sid.String(), nil
|
||||
}
|
||||
Loaded 100 of 229 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user