mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-17 00:06:52 +01:00
Compare commits
20
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b3a252e64d | ||
|
|
13658b74a0 | ||
|
|
22cdb0739a | ||
|
|
45e449a591 | ||
|
|
a36ce25af4 | ||
|
|
2e5adfddc6 | ||
|
|
31f3d6435e | ||
|
|
8f9a631f6e | ||
|
|
8a2de9b1b5 | ||
|
|
a8c52f5c13 | ||
|
|
13af8dd6f3 | ||
|
|
5bb0622192 | ||
|
|
f3705cbb67 | ||
|
|
94be454f4f | ||
|
|
5f26c1a7e5 | ||
|
|
d47c8c71f1 | ||
|
|
f57539a163 | ||
|
|
8d8ae0f744 | ||
|
|
f9b0853476 | ||
|
|
d5062dacf0 |
No files matched your search
@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Fixed
|
||||
|
||||
- `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.
|
||||
|
||||
@@ -174,10 +174,8 @@ 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)
|
||||
|
||||
@@ -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{}{}
|
||||
|
||||
@@ -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"
|
||||
@@ -147,6 +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)
|
||||
|
||||
|
||||
@@ -0,0 +1,131 @@
|
||||
# Post-quantum handshake transport compared with QUIC
|
||||
|
||||
Status: analysis, 2026-10-14. Compares the fragment transport in
|
||||
[pq-handshake.md](pq-handshake.md) with how QUIC makes its handshake reliable. TLS is out of
|
||||
scope; only the transport mechanics are compared.
|
||||
|
||||
## Summary
|
||||
|
||||
QUIC's handshake reliability is closed-loop: the receiver acknowledges, and the sender
|
||||
repairs exactly what is missing. Ours is open-loop: repair symbols are sent up front, and a
|
||||
timer sends fresh symbols. At handshake sizes (K <= 15) a QUIC-style acknowledgement
|
||||
shrinks to a 16-bit bitmap, and with an MDS code to a single count. So the real comparison
|
||||
is forward error correction versus acknowledgements, not QUIC versus us.
|
||||
|
||||
FEC is the right core. One piece of feedback is worth adding, initiator to responder and for
|
||||
msg2 only (see [Worth taking from QUIC](#worth-taking-from-quic)).
|
||||
|
||||
## What QUIC does
|
||||
|
||||
- **Messages as a stream.** Handshake bytes travel as `CRYPTO` frames (offset and length)
|
||||
and are reassembled in order. Initial and Handshake packets each have their own packet
|
||||
number space.
|
||||
- **Immediate acknowledgements.** Receivers must acknowledge Initial and Handshake packets
|
||||
without delay. ACK frames list ranges of received packet numbers.
|
||||
- **Loss detection** (RFC 9002). A packet is lost once 3 later packets are acknowledged, or
|
||||
after 9/8 of the round-trip time. Lost bytes are resent in new packets.
|
||||
- **Probe timeout (PTO).** If a whole flight vanishes, a probe timer fires. Before any RTT
|
||||
sample it starts at about 1 s (333 ms initial RTT plus 4x its variance) and doubles each
|
||||
time. Both endpoints run it.
|
||||
- **Amplification limit and anti-deadlock.** The server may send at most 3x what it
|
||||
received until the client's address is validated. The client must keep probing so a
|
||||
server stuck at that limit cannot deadlock.
|
||||
- **Retry.** A stateless round trip to validate the address. `NEW_TOKEN` lets later
|
||||
connections skip it.
|
||||
- **Congestion control from the first packet.** The initial window is 10 packets of 1200
|
||||
bytes.
|
||||
|
||||
## Side by side
|
||||
|
||||
| | QUIC | pq-handshake |
|
||||
|---|---|---|
|
||||
| Receiver feedback | ACK ranges, sent immediately | None; the next handshake message is the only acknowledgement |
|
||||
| Partial loss | +1 to 2 RTT (ACK, detect, resend) | 0 RTT while at most m symbols are lost |
|
||||
| Total loss | PTO: about 1 s, then doubling | Next PQ tick: 300 ms, then 1 s (alternating), or 100/300/600 ms (sticky) |
|
||||
| Spurious retransmit | Wasted bytes | Still useful: fresh repair indexes add to what the receiver holds |
|
||||
| Reassembly | Every byte offset, in order | Any K of up to 256 symbols |
|
||||
| Who retransmits | Both sides on their own timers | Initiator on a timer; the responder resends msg2 only when a repeat msg1 arrives (rate limited) |
|
||||
| State from the first packet | Server buffers and acknowledges partial flights | Capped pre-authentication table that never acknowledges |
|
||||
| Address validation | Retry, 1 RTT | Cookie under load, 1 RTT |
|
||||
|
||||
From the [simulation results](pq-handshake.md#simulation-results): phase 2 at 5% random
|
||||
loss with no FEC completes on the first attempt 39.8% of the time. Under
|
||||
acknowledgement-based recovery roughly 60% of handshakes would pay at least one extra round
|
||||
trip. With FEC, 0.4% wait for a retry. Spending bandwidth to save round trips is the stated
|
||||
design preference, and open-loop recovery delivers it.
|
||||
|
||||
## Where the designs already agree
|
||||
|
||||
- **1200-byte floor and the 3x amplification budget**, both taken directly from QUIC.
|
||||
- **Cookie and Retry.** Both cost one round trip and both can be forged by an on-path
|
||||
attacker. QUIC's Retry integrity tag uses a fixed, published key.
|
||||
- **On-path injection.** QUIC's Initial keys are derived from the client's connection ID,
|
||||
which an observer can read, so QUIC accepts the same handshake-blocking injection
|
||||
weakness documented for our symbols in
|
||||
[Injected symbols](pq-handshake.md#injected-symbols).
|
||||
- **Phase 2 msg3 confirmation.** Resending msg3 until any authenticated packet arrives,
|
||||
with a `Test` from the responder on completion, is QUIC's handshake confirmation and
|
||||
`HANDSHAKE_DONE`.
|
||||
|
||||
## Worth taking from QUIC
|
||||
|
||||
### 1. A msg2 progress probe from the initiator
|
||||
|
||||
This is the main gap. Today, recovering a partially lost msg2 means the initiator resends a
|
||||
full msg1 attempt; the responder decodes it, matches it in the answered-msg1 cache, and
|
||||
resends msg2. In phase 2 that is about 12 fragments (~13 KB) uploaded just to act as an
|
||||
acknowledgement, and recovery waits for the 300 ms or 1 s tick.
|
||||
|
||||
- The initiator already knows the responder's index: msg2 fragments carry it as `FragID`
|
||||
(`sendFragmentedResponse` passes `hostinfo.localIndexId`).
|
||||
- A one-packet probe, "msg2: have n of K", sent to that index would recover in about one
|
||||
round trip. The responder finds it the way phase 2 plans to find msg3.
|
||||
- Timing comes for free: msg1 send to first msg2 fragment is an RTT sample. Probe at
|
||||
roughly RTT/8 plus the repair delay after the first msg2 fragment if decoding has not
|
||||
completed.
|
||||
- Forging a probe needs the 32-bit responder index, so only an on-path attacker can, and
|
||||
the existing 3x budget bounds the reply.
|
||||
- If no msg2 fragment arrived at all, the initiator keeps today's msg1 resend. That is the
|
||||
same tail-loss case QUIC's PTO covers.
|
||||
|
||||
The reverse direction, the responder reporting progress on msg1, should not be added. It
|
||||
needs per-entry timers on the pre-authentication path, which is exactly the state QUIC
|
||||
servers carry and the reason QUIC needs Retry.
|
||||
|
||||
### 2. Buffer early data in phase 2
|
||||
|
||||
QUIC stacks hold a few packets they cannot decrypt yet. The phase 2 plan drops data that
|
||||
reaches the responder before msg3 decodes. Because repair fragments trail by
|
||||
`handshakes.pq.repair_delay` (10 ms), losing one msg3 data fragment drops about 10 ms of
|
||||
the initiator's first data while the repair is in flight. A small queue on the pending
|
||||
responder entry, replayed once msg3 verifies, avoids this.
|
||||
|
||||
### 3. Burst size across remotes
|
||||
|
||||
QUIC handshakes on a single path. `handleOutbound` sends the same `now` and `later` sets to
|
||||
every known remote and to relays (`StartRelays`).
|
||||
|
||||
- Phase 1 is fine.
|
||||
- In phase 2, four remotes means about 48 packets (~54 KB) leaving one uplink at once,
|
||||
every PQ tick, about 4x QUIC's initial window.
|
||||
- The Gilbert-Elliott simulation treats each path independently, so it does not capture
|
||||
this self-inflicted burst on a constrained uplink such as cellular.
|
||||
- Options: send the full FEC set only to the most likely remote and a reduced set to the
|
||||
others, or interleave packets across remotes.
|
||||
|
||||
## Not worth taking
|
||||
|
||||
- **Packet numbers, ACK ranges, an RTT estimator, loss thresholds, congestion control.**
|
||||
QUIC pays for this machinery because it also serves a data transport. Nebula carries
|
||||
packets and leaves reliability to the overlay's own transports. Building it only for
|
||||
handshakes of at most 15 fragments buys nothing a symbol count cannot.
|
||||
- **Offset-based reassembly.** It gives up the any-K-of-256 property and makes spurious
|
||||
retransmits wasteful again.
|
||||
- **An RTT-adaptive retry timer.** Low value. The fixed 100 ms linear schedule already fires
|
||||
sooner than QUIC's 1 s first PTO, and a spurious resend costs bandwidth, not correctness.
|
||||
|
||||
## Conclusion
|
||||
|
||||
Keep FEC as the core and add the msg2 progress probe. That gets QUIC's roughly one round
|
||||
trip tail recovery without pre-authentication state, and cuts phase 2's retry cost on the
|
||||
uplink by about 10x. Items 2 and 3 are phase 2 concerns; item 1 also helps phase 1.
|
||||
@@ -0,0 +1,348 @@
|
||||
# Post-quantum handshakes
|
||||
|
||||
Status: draft. Decisions below were made on 2026-10-13; open items are listed at the end.
|
||||
Phase 1 is implemented (see [Implementation](#implementation-phase-1)).
|
||||
|
||||
## Goals
|
||||
|
||||
1. **Confidentiality against harvest-now-decrypt-later.** Traffic recorded today must stay
|
||||
secret after a cryptographically relevant quantum computer exists. This needs a
|
||||
post-quantum key exchange now.
|
||||
2. **Post-quantum authentication, later.** Needs certificates whose CA signature and host
|
||||
keys are post-quantum. This requires reissuing certificates, so it ships second.
|
||||
3. **Never rely on IP fragmentation.** ML-KEM and ML-DSA do not fit in one packet, so the
|
||||
handshake must carry messages larger than the path MTU itself.
|
||||
|
||||
Non-goals: identity hiding beyond what IX offers today, and signatures at handshake time.
|
||||
The only signature in the system stays the CA signature inside the certificate.
|
||||
|
||||
## Primitives and sizes
|
||||
|
||||
| Primitive | Size |
|
||||
|---|---|
|
||||
| ML-KEM-1024 encapsulation key | 1568 B |
|
||||
| ML-KEM-1024 ciphertext | 1568 B |
|
||||
| ML-DSA-87 public key / signature | 2592 B / 4627 B |
|
||||
| Today's IX msg1 / msg2 (v2 cert, 151 B) | 252 B / 287 B |
|
||||
|
||||
`crypto/mlkem` is available in Go 1.26 (the current `go.mod`); `crypto/mldsa` arrives in
|
||||
Go 1.27 and is only needed for phase 2.
|
||||
|
||||
## Phase 1: ephemeral ML-KEM on today's certificates
|
||||
|
||||
A new handshake subtype, `ix_psk2_mlkem1024` (2), IX-shaped (2 messages; the responder
|
||||
completes on msg1 as today), using the flynn/noise `psk2` modifier. The Noise protocol name
|
||||
becomes `Noise_IXpsk2_...`, which separates it from the classical subtype.
|
||||
|
||||
- **msg1**: the initiator generates a fresh ML-KEM-1024 key pair and places the
|
||||
encapsulation key in `NebulaHandshakeDetails.KEMKey` (field 9). msg1's payload is mixed
|
||||
into the Noise transcript, so it cannot be stripped or replaced without msg2 failing.
|
||||
With the psk modifier Noise also mixes `e` into the cipher key, so msg1's static key and
|
||||
payload are encrypted, though only under a key derived from the public ephemeral.
|
||||
- **Responder**: after `ReadMessage(msg1)` it encapsulates to that key, obtaining
|
||||
`(ct, ss)`, and calls `HandshakeState.SetPresharedKey(psk)` before writing msg2, with
|
||||
`psk = HKDF-Extract(SHA-256, salt = "nebula ix_psk2_mlkem1024 v1", ikm = ss || ct)`.
|
||||
The ciphertext is bound in because, unlike the encapsulation key, it is not part of the
|
||||
Noise transcript.
|
||||
- **msg2** on the wire is `ct || noise_msg2`. The ciphertext travels outside the Noise
|
||||
message because the initiator needs `ss` before processing msg2's `psk` token. Any change
|
||||
to `ct` yields a different `ss` (ML-KEM implicit rejection) and the handshake fails.
|
||||
|
||||
Transport keys depend on both the X25519 DH outputs and the ML-KEM shared secret.
|
||||
Authentication is unchanged and classical. With a minimal v2 certificate msg1 and msg2 are
|
||||
about 1.84 KB each, so each travels as 2 data and 2 repair fragments of about 936 bytes.
|
||||
A KEM key on the classical subtype, or a missing or malformed one on this subtype, is a fatal
|
||||
protocol error; a forged ciphertext only fails that packet.
|
||||
|
||||
## Phase 2: pqIX hybrid with certificate v3
|
||||
|
||||
Certificate v3 is hybrid: the classical static key and CA signature plus a static
|
||||
ML-KEM-1024 key and an ML-DSA-87 CA signature. Host authentication is by KEM rather than by
|
||||
signature, following PQNoise's pqIX, while keeping the classical DH tokens:
|
||||
|
||||
- **msg1** (I to R): `e, s`, ephemeral ML-KEM key, initiator cert.
|
||||
- **msg2** (R to I): `e, s`, ciphertext to I's ephemeral KEM key, ciphertext to I's static
|
||||
KEM key, responder cert.
|
||||
- **msg3** (I to R): ciphertext to R's static KEM key, plus first data. R authenticates I
|
||||
when msg3 decrypts; I authenticates R implicitly when R's first reply decrypts.
|
||||
|
||||
msg3 is about 1.6 KB, 2 data and 2 repair fragments, and adds no new message types:
|
||||
|
||||
- **Responder.** After sending msg2 the responder keeps a pending Machine, found by its
|
||||
local index like the initiator's today; this is the multi-message responder support the
|
||||
manager lacks now. A repeat msg1 maps to it through the answered-msg1 cache and gets msg2
|
||||
resent with fresh symbols, exactly as in phase 1. Until msg3 verifies, data for that
|
||||
index is dropped silently: it must not draw a RecvError, which would tear down the
|
||||
initiator's new tunnel. On completing it sends an empty `Test`/`TestReply` under the
|
||||
new keys, so the initiator hears back even when there is no traffic.
|
||||
- **Initiator.** Writing msg3 yields the transport keys, so the hostinfo moves to the main
|
||||
hostmap and data flows at once, readable only by the real responder. The handshake entry
|
||||
stays behind in a confirming state: each retry tick resends msg3 with fresh symbols until
|
||||
any packet from the responder decrypts on the new tunnel, and if that never happens
|
||||
within the handshake timeout the tunnel is torn down. Losing msg3 costs the data sent
|
||||
behind it, which the overlay's own transport retransmits.
|
||||
- msg3's fragments use the responder's index as RemoteIndex and land on the responder's
|
||||
pending entry, so they never enter the pre-authentication table.
|
||||
|
||||
The initiator never caches the responder's certificate, so every handshake has three
|
||||
messages and carries both full certificates. With ML-DSA-87:
|
||||
|
||||
| Message | Size | Data fragments (k) |
|
||||
|---|---|---|
|
||||
| msg1 | ~8.2 KB | 8 |
|
||||
| msg2 | ~9.8 KB | 9 |
|
||||
| msg3 | ~1.6 KB | 2 |
|
||||
|
||||
flynn/noise cannot mix multiple KEM secrets into the chaining key, so phase 2 needs a
|
||||
KEM-aware Noise symmetric state written in this repository. Both subtypes coexist.
|
||||
|
||||
Cryptographic review of the hybrid composition will be done by in-house cryptographers.
|
||||
|
||||
## Fragment transport
|
||||
|
||||
### Requirements
|
||||
|
||||
- No IP fragmentation: every datagram's UDP payload is at most 1232 bytes **after** relay
|
||||
wrapping (16 B header + 16 B tag), the IPv6 minimum MTU budget also used by DNS Flag Day
|
||||
2020 and Solana's Turbine.
|
||||
- Every fragment of a handshake uses the same 5-tuple.
|
||||
- Bounded pre-authentication state, bounded amplification, selective loss recovery,
|
||||
tolerance of reordering and duplication, and a strictly validated, fuzzable parser.
|
||||
|
||||
### Wire format
|
||||
|
||||
Every packet of a fragmented handshake subtype is:
|
||||
|
||||
```
|
||||
Nebula header (16) Version | Type=Handshake | Subtype | Reserved=0 | RemoteIndex | Counter
|
||||
Fragment header (8) FragID u32 | MsgLen u16 | Index u8 | Flags u8
|
||||
Cookie (16) only when Flags has 0x01
|
||||
Symbol SymbolSize bytes
|
||||
```
|
||||
|
||||
- `Counter` is the Noise message number (1, 2, 3). `RemoteIndex` is 0 for msg1, as today.
|
||||
- `FragID` is the sender's local index (random, non-zero).
|
||||
- `MsgLen` is the length of the whole message. Both ends derive the layout from it:
|
||||
`K = ceil(MsgLen / 1160)`, `SymbolSize = ceil(MsgLen / K)`. Every symbol has the same
|
||||
size. Room for a cookie is always reserved, so a packet is at most
|
||||
16 + 8 + 16 + 1160 = 1200 bytes with or without one.
|
||||
- `Index < K` is a data symbol (a slice of the message, the last one zero padded);
|
||||
`Index >= K` is a repair symbol.
|
||||
- `Flags` bit 0x01 means a cookie follows the fragment header. Other bits must be zero.
|
||||
|
||||
A cookie reply, sent by a responder under load, is a bare 32 byte packet:
|
||||
|
||||
```
|
||||
Nebula header (16) Version | Type=Handshake | Subtype | Reserved=0 | RemoteIndex=FragID | Counter=0
|
||||
Cookie (16)
|
||||
```
|
||||
|
||||
It names the initiator's FragID, so the initiator finds its attempt the same way it finds
|
||||
msg2.
|
||||
|
||||
### Forward error correction
|
||||
|
||||
Messages are protected with a systematic Reed-Solomon code over GF(2^8), implemented in
|
||||
`handshake/fec`:
|
||||
|
||||
- The repair rows form a Cauchy matrix, `coefficient(row, col) = 1 / (row XOR col)` with
|
||||
`row >= K > col`, so every square submatrix is invertible and **any K distinct symbols
|
||||
reconstruct the message**. Naive identity-over-Vandermonde constructions are not MDS
|
||||
(the PAR1 flaw and the 1997 Plank tutorial erratum).
|
||||
- A repair row depends only on its index, so repair symbols are generated on demand and
|
||||
their indexes never need to be agreed in advance. Up to 256 symbols exist per message.
|
||||
- Known-answer vectors in `fec_test.go` pin the encoding and were cross-checked against an
|
||||
independent implementation; changing them is a wire format change.
|
||||
- Cost for a 9.8 KB message (k=9): about 13 µs for three repair symbols, about 19 µs to
|
||||
decode with three data symbols missing.
|
||||
|
||||
**The sender chooses m**, the number of repair symbols per attempt. The receiver only needs
|
||||
any K symbols, so this is policy and can change without a protocol change. The starting
|
||||
rule is `m = max(2, ceil(K/3))`.
|
||||
|
||||
**Retries send fresh symbols.** Attempt 0 sends indexes `0 .. K+m-1`; each retry sends
|
||||
the next `K+m` unused indexes. The receiver merges all distinct symbols across attempts,
|
||||
so no received fragment is wasted. Indexes are a deterministic function of the message,
|
||||
so retransmits stay idempotent: the responder caches msg2 itself and regenerates any
|
||||
symbol.
|
||||
|
||||
**Repair symbols trail the data.** Data symbols go out back to back; repair symbols follow
|
||||
after a short delay, so a queue tail-drop at the end of the data run does not also take the
|
||||
repair. In simulation this lifts small messages substantially (k=2 at 10% loss, burst 8:
|
||||
91.4% to 98.2% first-attempt success). Pacing every fragment was also evaluated; it gains
|
||||
about 5 more points for k=7..9 on bursty paths, which is not worth the extra machinery,
|
||||
and the retry with fresh symbols covers the remainder.
|
||||
|
||||
### Receiver rules
|
||||
|
||||
Implemented in `handshake/fragment` (`Sender`, `Assembly`, and the capped `Table`).
|
||||
|
||||
- Fragments are stored individually as they arrive and charged against a memory cap.
|
||||
Nothing is allocated from a claimed size alone (FragmentSmack, game-engine "fragment
|
||||
bombs").
|
||||
- `MsgLen` must be identical for every fragment of a `FragID`; a mismatch drops the whole
|
||||
entry. msg1 is capped at `MsgLen <= 16384` (K <= 15).
|
||||
- The decoder keeps at most K distinct symbols, so an entry never exceeds about MsgLen bytes
|
||||
however many repair symbols arrive.
|
||||
- When K symbols are present the message is decoded and handed to the handshake `Machine`
|
||||
as a synthetic `[header | message]`. The Machine never sees fragments.
|
||||
- A completed entry is forgotten immediately. A late duplicate fragment starts a new entry
|
||||
and, once enough arrive, reconstructs the same message again; the handshake layer's
|
||||
duplicate detection recognises it.
|
||||
- If Noise rejects a decoded message, the entry is discarded and the next attempt
|
||||
supplies fresh symbols. (Possible refinement: keep a few spare symbols so an injected
|
||||
bad symbol can be identified by re-encoding instead of waiting for a retry.)
|
||||
- Pre-authentication msg1 entries live in a table keyed by (source address or relay index,
|
||||
FragID) with a total memory cap, per-source quotas (/32 for IPv4, /64 for IPv6), a
|
||||
sliding TTL of about 2 s refreshed by progress, and random eviction under pressure.
|
||||
msg2 and msg3 reassembly attaches to the existing pending handshake found by RemoteIndex.
|
||||
|
||||
### Retransmission and amplification
|
||||
|
||||
- Only timers cause transmission. Reactive resends (the responder resending its cached
|
||||
msg2 when a duplicate msg1 completes) are rate limited to one per handshake per retry
|
||||
interval, to avoid TFTP's Sorcerer's Apprentice amplification.
|
||||
- Duplicate msg1 detection compares the decoded message to the cached one **before**
|
||||
running Noise or certificate verification.
|
||||
- Before an address is validated, a responder sends at most 3x the bytes it received from
|
||||
it (QUIC's rule). Normal handshakes sit near 1.1-1.2x.
|
||||
- In phase 2 the initiator retransmits msg3 until any authenticated packet arrives from
|
||||
the responder; the responder sends a small confirmation on completion and holds tunnel
|
||||
traffic until msg3 verifies.
|
||||
|
||||
### Denial of service
|
||||
|
||||
The responder can no longer complete statelessly on msg1, since msg1 arrives in pieces.
|
||||
Defenses are the capped table above plus a **cookie under load**, in the style of
|
||||
WireGuard's mac2, QUIC Retry and the SCTP state cookie:
|
||||
|
||||
- Once the msg1 table is at least half full (by bytes or by entries), every msg1 fragment
|
||||
must carry a valid cookie. One without is answered with a cookie reply and leaves no
|
||||
state. Fragments that already belong to an entry need one too, so an attacker cannot
|
||||
hold old entries open.
|
||||
- A cookie is `HMAC-SHA256(secret, source address and port, relay channel, FragID)`
|
||||
truncated to 16 bytes. The secret rotates every 2 minutes and the previous one is still
|
||||
accepted, so a cookie is good for 2 to 4 minutes.
|
||||
- Replies are never larger than the packet that prompted them (no amplification) and are
|
||||
rate limited as a whole (a burst of 256, then 1000 per second), so spoofed floods cannot
|
||||
turn the responder into a reflector.
|
||||
- The initiator attaches the cookie to its PQ attempt, so every later packet carries it,
|
||||
and immediately resends fresh symbols to the address the reply came from, at most once
|
||||
per retry interval. Under load a PQ handshake costs one extra round trip, which in
|
||||
practice still beats the classical attempt on the next retry tick.
|
||||
- An attacker on the path can forge a cookie reply; the bogus cookie is simply rejected
|
||||
and answered with a real one.
|
||||
|
||||
A CA-keyed pre-filter MAC was considered and rejected: networks commonly trust many CAs.
|
||||
|
||||
#### Injected symbols
|
||||
|
||||
The decoder keeps the first K distinct symbols it sees, so one forged symbol in those K
|
||||
spoils that attempt's decode; Noise rejects the result and the next attempt brings fresh
|
||||
symbols. Forging one needs the attempt's FragID or index, which are random 32 bit values,
|
||||
and for msg1 the initiator's exact address and port too, so in practice only an attacker
|
||||
who sees the traffic can do it. An attacker who can also drop packets gains nothing new.
|
||||
One who can only inject, and races a forged symbol into every attempt, can stop a PQ
|
||||
handshake where it could not stop a classical one, since classical msg2s are tried one
|
||||
packet at a time. Keeping spare symbols to find a consistent subset only raises the number
|
||||
of forgeries needed per attempt, and authenticating symbols is impossible for msg1, which
|
||||
travels before any key exists. So the decoder deliberately does neither. A non-sticky
|
||||
initiator still gets a classical tunnel from its next attempt; a sticky one, by design,
|
||||
does not downgrade.
|
||||
|
||||
## Rollout
|
||||
|
||||
- Separate settings for initiating and accepting PQ handshakes, both off by default:
|
||||
`handshakes.pq.initiate`, `handshakes.pq.accept`. `handshakes.pq.repair_delay` (default
|
||||
10ms) sets how long repair fragments trail the data fragments.
|
||||
- `handshakes.pq.require` makes every handshake PQ: it implies `initiate` and `accept`,
|
||||
never offers a classical attempt, and drops classical msg1s.
|
||||
- Old nodes silently drop unknown subtypes, so discovery is speculative: an initiator with
|
||||
`initiate` enabled alternates PQ and classical attempts on successive timer retries,
|
||||
keeping both pending, and the first to complete wins. A path nothing has been sent over
|
||||
yet gets the PQ attempt first: an early resend triggered by a lighthouse reply is PQ, and
|
||||
a relay that comes up pushes the PQ attempt through at once, counting as the PQ turn.
|
||||
Without that, relays set up during the first attempt handed every relayed handshake to
|
||||
the classical retry (seen on real hosts: 11 of 11). Once a msg2 fragment or cookie reply
|
||||
arrives for the PQ attempt the peer evidently speaks PQ, and classical stops getting
|
||||
turns.
|
||||
- All `handshakes.pq` settings reload without a restart. Handshakes in flight carry on;
|
||||
the new settings apply to the next attempt and the next packet.
|
||||
- `handshakes.pq.sticky` (default off): once a peer has completed a PQ handshake, never fall
|
||||
back to classical for it again during this process lifetime. This resists active
|
||||
downgrade after first contact.
|
||||
- No lighthouse capability advertisement.
|
||||
|
||||
## Simulation results
|
||||
|
||||
Gilbert-Elliott channel (bad state drops everything), losses expressed as average rate and
|
||||
mean burst length in packets. First-attempt success for the whole handshake with
|
||||
`m = max(2, ceil(K/3))` and repair delayed 16 packet slots, compared with no FEC:
|
||||
|
||||
| Handshake | Loss | Burst 1 | Burst 2 | Burst 4 | Burst 8 |
|
||||
|---|---|---|---|---|---|
|
||||
| phase 1 (2, 2) no FEC | 5% | 81.4% | 85.6% | 87.9% | 89.0% |
|
||||
| phase 1 (2, 2) FEC | 5% | 99.9% | 99.4% | 99.3% | 98.6% |
|
||||
| phase 1 (2, 2) FEC | 10% | 99.3% | 97.5% | 97.4% | 96.3% |
|
||||
| phase 2 (8, 9, 2) no FEC | 5% | 37.8% | 56.0% | 69.3% | 77.1% |
|
||||
| phase 2 (8, 9, 2) FEC | 5% | 99.6% | 93.7% | 89.9% | 88.4% |
|
||||
| phase 2 (8, 9, 2) FEC | 10% | 95.3% | 83.5% | 77.9% | 76.7% |
|
||||
|
||||
With fresh repair symbols, phase 2 completes within two attempts at least 99.1% of the time
|
||||
in every scenario above, and within three at least 99.98%.
|
||||
|
||||
The simulators and their outputs are in [pq-handshake-sim](pq-handshake-sim/README.md),
|
||||
including a comparison with classical handshakes and a model of time to a working tunnel
|
||||
under Nebula's retry schedule.
|
||||
|
||||
## Prior art
|
||||
|
||||
- **WireGuard / Rosenpass**: fit every message in one packet; cookies and biscuits for
|
||||
statelessness. Not possible at our sizes.
|
||||
- **IKEv2**: RFC 7383 fragments only after keys exist, with each fragment authenticated;
|
||||
RFC 9242/9370 move PQ key exchange into intermediate exchanges for that reason.
|
||||
- **QUIC / DTLS 1.3**: offset-based reassembly with ACKs; QUIC's 3x amplification limit and
|
||||
1200-byte floor.
|
||||
- **Solana Turbine**: Reed-Solomon over 1232-byte UDP packets through untrusted relays;
|
||||
moved to Merkle-authenticated shreds after unauthenticated repair symbols enabled
|
||||
poisoning.
|
||||
- **kcp-go, UDPspeeder, CM256**: RS FEC over UDP; parity must scale up for small groups.
|
||||
- **gQUIC FEC (removed)**: FEC does not pay for bulk transfer under bursty loss; it does
|
||||
for short, latency-critical transfers such as handshakes.
|
||||
- **TFTP, NFS duplicate request cache, memcached UDP, IP reassembly bugs**: retransmit
|
||||
storms, ID-wrap misassembly, reflection amplification, and allocation from claimed sizes.
|
||||
|
||||
## Implementation (phase 1)
|
||||
|
||||
- `handshake`: the `ix_psk2_mlkem1024` subtype (`patterns.go`, `kem.go`), the `KEMKey`
|
||||
payload field, and the psk2 plumbing in `Machine`.
|
||||
- `handshake/fec`, `handshake/fragment`: the code and the fragment transport.
|
||||
- `handshake_manager_pq.go` and the manager:
|
||||
- **Initiator.** Attempts alternate PQ and classical, starting with PQ (sticky peers get
|
||||
only PQ). The PQ attempt has its own local index registered alongside the classical
|
||||
one; whichever response completes first wins, and the other index is released
|
||||
(`settleIndex`). A timed out or deleted pending handshake releases both.
|
||||
- **Responder.** msg1 fragments go into the capped pre-authentication table. A decoded
|
||||
msg1 is looked up by hash among recently answered ones before any Noise, KEM or
|
||||
certificate work: the trailing repair fragments of an attempt rebuild a msg1 its data
|
||||
fragments already completed, and a retrying initiator offers fresh symbols for the
|
||||
same msg1. A repeat goes straight to the cached-response resend, which offers fresh
|
||||
msg2 symbols, is rate limited to one per retry interval and is held to the 3x
|
||||
amplification budget.
|
||||
- **Relays** carry fragments unchanged; repair fragments trail via a timer.
|
||||
- The pre-authentication table is capped at 4 MiB, 1024 entries, 4 per source (IPv4 /32,
|
||||
IPv6 /64, or relay channel), 16 KiB messages and a 3 s idle timeout. Cookies are
|
||||
demanded from half full.
|
||||
- Tests: Noise-level KEM tests, codec and fragment tests and fuzzers, manager unit tests
|
||||
for the response budget and rate limit, and e2e tests for a clean handshake, loss of
|
||||
data fragments in both directions, fallback to a peer that does not accept PQ, a lost
|
||||
msg2 recovered by fresh symbols, sticky mode under an attacker dropping PQ packets,
|
||||
relays, index cleanup on completion, fallback and timeout, and a responder flooded from
|
||||
spoofed sources demanding and accepting a cookie. Unit tests cover cookie binding and
|
||||
rotation, the never-amplify rule, the initiator's rate limited resend, and reload. ML-KEM and HKDF also
|
||||
pass under `GOEXPERIMENT=boringcrypto` and `GODEBUG=fips140=on`.
|
||||
|
||||
## Open items
|
||||
|
||||
None for phase 1. Phase 2 needs certificate v3, the KEM-aware Noise symmetric state, and
|
||||
the msg3 design above.
|
||||
@@ -0,0 +1,476 @@
|
||||
//go:build e2e_testing
|
||||
|
||||
package e2e
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/cert_test"
|
||||
"github.com/slackhq/nebula/e2e/router"
|
||||
"github.com/slackhq/nebula/handshake/fragment"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func pqRequire() m {
|
||||
return m{"handshakes": m{"pq": m{"require": true, "repair_delay": "0s"}}}
|
||||
}
|
||||
|
||||
func pqConfig(initiate, accept, sticky bool) m {
|
||||
return m{"handshakes": m{"pq": m{
|
||||
"initiate": initiate,
|
||||
"accept": accept,
|
||||
"sticky": sticky,
|
||||
"repair_delay": "0s",
|
||||
}}}
|
||||
}
|
||||
|
||||
// handshakeOf returns the handshake header p carries, looking inside relay
|
||||
// wrapping, plus the fragment header when the handshake is fragmented.
|
||||
func handshakeOf(p *udp.Packet) (*header.H, *fragment.Header) {
|
||||
b := p.Data
|
||||
h := &header.H{}
|
||||
if h.Parse(b) != nil {
|
||||
return nil, nil
|
||||
}
|
||||
if h.Type == header.Message && h.Subtype == header.MessageRelay {
|
||||
// Relays authenticate but do not encrypt the inner packet.
|
||||
b = b[header.Len:]
|
||||
if h.Parse(b) != nil {
|
||||
return nil, nil
|
||||
}
|
||||
}
|
||||
if h.Type != header.Handshake {
|
||||
return nil, nil
|
||||
}
|
||||
if !header.IsFragmented(h.Subtype) {
|
||||
return h, nil
|
||||
}
|
||||
// A relayed packet still has the relay's AEAD tag on the end.
|
||||
for _, tag := range []int{0, 16} {
|
||||
if len(b) < header.Len+tag {
|
||||
break
|
||||
}
|
||||
if fh, _, err := fragment.Parse(b[header.Len : len(b)-tag]); err == nil {
|
||||
return h, &fh
|
||||
}
|
||||
}
|
||||
return h, nil
|
||||
}
|
||||
|
||||
// handshakeTally counts handshake packets by style as the router moves them.
|
||||
type handshakeTally struct {
|
||||
sync.Mutex
|
||||
pq, classical int
|
||||
maxPQLen int
|
||||
}
|
||||
|
||||
func (ht *handshakeTally) observe(p *udp.Packet) {
|
||||
h, _ := handshakeOf(p)
|
||||
if h == nil {
|
||||
return
|
||||
}
|
||||
ht.Lock()
|
||||
defer ht.Unlock()
|
||||
if h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
||||
ht.pq++
|
||||
ht.maxPQLen = max(ht.maxPQLen, len(p.Data))
|
||||
} else {
|
||||
ht.classical++
|
||||
}
|
||||
}
|
||||
|
||||
// isTunnelData reports whether p is ordinary tunnel traffic headed for to,
|
||||
// directly or as the last hop of a relay.
|
||||
func isTunnelData(p *udp.Packet, receiver, to *nebula.Control) bool {
|
||||
h := &header.H{}
|
||||
if receiver != to || h.Parse(p.Data) != nil || h.Type != header.Message {
|
||||
return false
|
||||
}
|
||||
if h.Subtype == header.MessageRelay {
|
||||
if h.Parse(p.Data[header.Len:]) != nil {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return h.Type == header.Message && h.Subtype == header.MessageNone
|
||||
}
|
||||
|
||||
func newPQPair(t *testing.T, mine, theirs m) (myControl, theirControl *nebula.Control, myVpn, theirVpn []netip.Prefix, myUdp, theirUdp netip.AddrPort, r *router.R) {
|
||||
t.Helper()
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
myControl, myVpn, myUdp, _ = newSimpleServer(cert.Version2, ca, caKey, "me", "10.128.0.1/24", mine)
|
||||
theirControl, theirVpn, theirUdp, _ = newSimpleServer(cert.Version2, ca, caKey, "them", "10.128.0.2/24", theirs)
|
||||
myControl.InjectLightHouseAddr(theirVpn[0].Addr(), theirUdp)
|
||||
r = router.NewR(t, myControl, theirControl)
|
||||
myControl.Start()
|
||||
theirControl.Start()
|
||||
return
|
||||
}
|
||||
|
||||
func TestPQHandshake(t *testing.T) {
|
||||
t.Parallel()
|
||||
// They only accept, which is all a PQ initiator needs.
|
||||
myControl, theirControl, myVpn, theirVpn, myUdp, theirUdp, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Zero(t, tally.classical, "no classical handshake should be needed")
|
||||
assert.GreaterOrEqual(t, tally.pq, 4, "both messages travel as several fragments")
|
||||
assert.LessOrEqual(t, tally.maxPQLen, fragment.MaxPacketLen)
|
||||
|
||||
assertHostInfoPair(t, myUdp, theirUdp, myVpn, theirVpn, myControl, theirControl)
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
assert.Empty(t, myControl.ListHostmapIndexes(true), "no pending index may outlive the handshake")
|
||||
assert.Empty(t, theirControl.ListHostmapIndexes(true))
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQHandshakeLoss drops data fragments of both messages; the repair
|
||||
// fragments must carry the handshake without a retry.
|
||||
func TestPQHandshakeLoss(t *testing.T) {
|
||||
t.Parallel()
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
dropped := 0
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
if h, fh := handshakeOf(p); fh != nil {
|
||||
// Every data fragment of msg1, and the first of msg2.
|
||||
if (h.MessageCounter == 1 && int(fh.Index) < 2) || (h.MessageCounter == 2 && fh.Index == 0) {
|
||||
dropped++
|
||||
return router.Drop
|
||||
}
|
||||
}
|
||||
tally.observe(p)
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Equal(t, 3, dropped)
|
||||
assert.Zero(t, tally.classical, "the first attempt should succeed from repair fragments")
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQFallback has a peer that does not accept PQ handshakes. The initiator's
|
||||
// next attempt is classical and the tunnel comes up anyway.
|
||||
func TestPQFallback(t *testing.T) {
|
||||
t.Parallel()
|
||||
myControl, theirControl, myVpn, theirVpn, myUdp, theirUdp, r := newPQPair(t, pqConfig(true, true, false), nil)
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Positive(t, tally.pq, "a PQ attempt comes first")
|
||||
assert.Positive(t, tally.classical, "then a classical one")
|
||||
|
||||
assertHostInfoPair(t, myUdp, theirUdp, myVpn, theirVpn, myControl, theirControl)
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
assert.Empty(t, myControl.ListHostmapIndexes(true), "the losing PQ attempt's index must be released")
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQResendFreshSymbols loses the responder's whole first msg2. The
|
||||
// initiator's next PQ attempt offers fresh msg1 symbols, the responder
|
||||
// recognises the repeat and resends msg2 with symbols it has not sent before.
|
||||
func TestPQResendFreshSymbols(t *testing.T) {
|
||||
t.Parallel()
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
var firstMsg2, freshMsg2, freshMsg1 int
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(10*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
h, fh := handshakeOf(p)
|
||||
switch {
|
||||
case h != nil && fh == nil:
|
||||
// Keep the classical fallback out of the way.
|
||||
return router.Drop
|
||||
case fh != nil && h.MessageCounter == 2 && fh.Index < 4:
|
||||
firstMsg2++
|
||||
return router.Drop
|
||||
case fh != nil && h.MessageCounter == 2:
|
||||
freshMsg2++
|
||||
case fh != nil && h.MessageCounter == 1 && fh.Index >= 4:
|
||||
freshMsg1++
|
||||
}
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Equal(t, 4, firstMsg2, "the first msg2 is 2 data and 2 repair fragments")
|
||||
assert.Positive(t, freshMsg1, "the retry offers fresh msg1 symbols")
|
||||
assert.Positive(t, freshMsg2, "the resend offers fresh msg2 symbols")
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQSticky checks a sticky initiator never offers a classical handshake to a
|
||||
// peer it has already completed a PQ handshake with.
|
||||
func TestPQSticky(t *testing.T) {
|
||||
t.Parallel()
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqConfig(true, true, true), pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
theirControl.GetFromTun(true)
|
||||
|
||||
t.Log("Rehandshake while an attacker drops every PQ packet")
|
||||
var tally handshakeTally
|
||||
myControl.ReHandshake(theirVpn[0].Addr())
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
if h, _ := handshakeOf(p); h != nil && h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
||||
return router.Drop
|
||||
}
|
||||
return router.KeepRouting
|
||||
})
|
||||
assert.Positive(t, tally.pq, "PQ attempts keep being made")
|
||||
assert.Zero(t, tally.classical, "sticky must never fall back")
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
func TestPQRelays(t *testing.T) {
|
||||
t.Parallel()
|
||||
ca, _, caKey, _ := cert_test.NewTestCaCert(cert.Version1, cert.Curve_CURVE25519, time.Now(), time.Now().Add(10*time.Minute), nil, nil, []string{})
|
||||
useRelays := pqConfig(true, true, false)
|
||||
useRelays["relay"] = m{"use_relays": true}
|
||||
amRelay := pqConfig(true, true, false)
|
||||
amRelay["relay"] = m{"am_relay": true}
|
||||
myControl, myVpnIpNet, _, _ := newSimpleServer(cert.Version1, ca, caKey, "me ", "10.128.0.1/24", useRelays)
|
||||
relayControl, relayVpnIpNet, relayUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "relay ", "10.128.0.128/24", amRelay)
|
||||
theirControl, theirVpnIpNet, theirUdpAddr, _ := newSimpleServer(cert.Version1, ca, caKey, "them ", "10.128.0.2/24", useRelays)
|
||||
|
||||
myControl.InjectLightHouseAddr(relayVpnIpNet[0].Addr(), relayUdpAddr)
|
||||
myControl.InjectRelays(theirVpnIpNet[0].Addr(), []netip.Addr{relayVpnIpNet[0].Addr()})
|
||||
relayControl.InjectLightHouseAddr(theirVpnIpNet[0].Addr(), theirUdpAddr)
|
||||
|
||||
r := router.NewR(t, myControl, relayControl, theirControl)
|
||||
defer r.RenderFlow()
|
||||
|
||||
myControl.Start()
|
||||
relayControl.Start()
|
||||
theirControl.Start()
|
||||
|
||||
var tally handshakeTally
|
||||
var relayedPQ, relayedClassical int
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpnIpNet[0].Addr(), 80, myVpnIpNet[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(10*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
outer := &header.H{}
|
||||
if outer.Parse(p.Data) == nil && outer.Type == header.Message && outer.Subtype == header.MessageRelay {
|
||||
if h, fh := handshakeOf(p); h != nil && fh != nil {
|
||||
relayedPQ++
|
||||
assert.LessOrEqual(t, len(p.Data), fragment.MaxPacketLen+32, "a relayed fragment fits the IPv6 minimum MTU")
|
||||
} else if h != nil {
|
||||
relayedClassical++
|
||||
}
|
||||
}
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpnIpNet[0].Addr(), theirVpnIpNet[0].Addr(), 80, 80)
|
||||
assert.Positive(t, relayedPQ, "the end to end handshake is PQ through the relay")
|
||||
assert.Zero(t, relayedClassical, "the relay coming up carries the PQ attempt, not the classical retry")
|
||||
r.RenderHostmaps("Final hostmaps", myControl, relayControl, theirControl)
|
||||
|
||||
myControl.Stop()
|
||||
relayControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQTimeoutReleasesIndexes lets a handshake with both a PQ and a classical
|
||||
// attempt pending time out, and checks neither index is left behind.
|
||||
func TestPQTimeoutReleasesIndexes(t *testing.T) {
|
||||
t.Parallel()
|
||||
mine := pqConfig(true, true, false)
|
||||
mine["handshakes"].(m)["retries"] = 2
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, mine, pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
r.RouteForAllExitFuncOrTimeout(1500*time.Millisecond, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
return router.Drop
|
||||
})
|
||||
|
||||
assert.Positive(t, tally.pq)
|
||||
assert.Positive(t, tally.classical)
|
||||
assert.Nil(t, myControl.GetHostInfoByVpnAddr(theirVpn[0].Addr(), true), "the handshake should have timed out")
|
||||
assert.Empty(t, myControl.ListHostmapIndexes(true))
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQCookieUnderLoad floods the responder with msg1 fragments from spoofed
|
||||
// sources until it demands cookies, then checks a real initiator picks up the
|
||||
// cookie and still completes a PQ handshake.
|
||||
func TestPQCookieUnderLoad(t *testing.T) {
|
||||
t.Parallel()
|
||||
myControl, theirControl, myVpn, theirVpn, _, theirUdp, r := newPQPair(t, pqConfig(true, true, false), pqConfig(false, true, false))
|
||||
defer r.RenderFlow()
|
||||
|
||||
// Half of the 1024 entry table is the cookie threshold. Stopping exactly there
|
||||
// keeps them from answering the spoofed sources, which the router cannot reach.
|
||||
t.Log("Flood them with the first fragment of msg1s nobody will finish")
|
||||
for i := range 512 {
|
||||
from := netip.AddrPortFrom(netip.AddrFrom4([4]byte{198, 18, byte(i >> 8), byte(i)}), 4242)
|
||||
s, err := fragment.NewSender(make([]byte, 2000), header.HandshakeIXPSK2MLKEM1024, 0, 1, uint32(i+1))
|
||||
require.NoError(t, err)
|
||||
pkts, _, err := s.Attempt(0)
|
||||
require.NoError(t, err)
|
||||
theirControl.InjectUDPPacket(&udp.Packet{From: from, To: theirUdp, Data: pkts[0]})
|
||||
}
|
||||
|
||||
var tally handshakeTally
|
||||
var cookieReplies, msg2, withCookie int
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
if h, fh := handshakeOf(p); h != nil && h.Subtype == header.HandshakeIXPSK2MLKEM1024 {
|
||||
switch {
|
||||
case h.MessageCounter == 0:
|
||||
cookieReplies++
|
||||
case h.MessageCounter == 2:
|
||||
msg2++
|
||||
case fh != nil && fh.HasCookie():
|
||||
withCookie++
|
||||
}
|
||||
}
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Positive(t, cookieReplies, "a loaded responder asks for a cookie")
|
||||
assert.Positive(t, withCookie, "the initiator resends with it")
|
||||
assert.Positive(t, msg2, "and the handshake completes post-quantum")
|
||||
assert.Zero(t, tally.classical, "the cookie round trip beats the classical fallback")
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
}
|
||||
|
||||
// TestPQRequire checks require mode never handshakes classically, in either
|
||||
// direction.
|
||||
func TestPQRequire(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
t.Run("initiator", func(t *testing.T) {
|
||||
// They neither speak PQ nor require it; we never fall back.
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqRequire(), nil)
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
return router.KeepRouting
|
||||
})
|
||||
assert.Positive(t, tally.pq)
|
||||
assert.Zero(t, tally.classical)
|
||||
assert.Nil(t, theirControl.GetHostInfoByVpnAddr(myVpn[0].Addr(), false), "no tunnel without PQ")
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
})
|
||||
|
||||
t.Run("responder", func(t *testing.T) {
|
||||
// We only speak classical; they refuse it.
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, nil, pqRequire())
|
||||
defer r.RenderFlow()
|
||||
|
||||
var answers int
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
r.RouteForAllExitFuncOrTimeout(time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
if h, _ := handshakeOf(p); h != nil && h.MessageCounter == 2 {
|
||||
answers++
|
||||
}
|
||||
return router.KeepRouting
|
||||
})
|
||||
assert.Zero(t, answers, "a classical msg1 gets no answer")
|
||||
assert.Nil(t, theirControl.GetHostInfoByVpnAddr(myVpn[0].Addr(), false))
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
})
|
||||
|
||||
t.Run("both", func(t *testing.T) {
|
||||
myControl, theirControl, myVpn, theirVpn, _, _, r := newPQPair(t, pqRequire(), pqRequire())
|
||||
defer r.RenderFlow()
|
||||
|
||||
var tally handshakeTally
|
||||
myControl.InjectTunPacket(BuildTunUDPPacket(theirVpn[0].Addr(), 80, myVpn[0].Addr(), 80, []byte("Hi from me")))
|
||||
require.True(t, r.RouteForAllExitFuncOrTimeout(5*time.Second, func(p *udp.Packet, receiver *nebula.Control) router.ExitType {
|
||||
tally.observe(p)
|
||||
if isTunnelData(p, receiver, theirControl) {
|
||||
return router.RouteAndExit
|
||||
}
|
||||
return router.KeepRouting
|
||||
}), "tunnel never came up")
|
||||
assertUdpPacket(t, []byte("Hi from me"), theirControl.GetFromTun(true), myVpn[0].Addr(), theirVpn[0].Addr(), 80, 80)
|
||||
assert.Zero(t, tally.classical)
|
||||
assertTunnel(t, myVpn[0].Addr(), theirVpn[0].Addr(), myControl, theirControl, r)
|
||||
|
||||
myControl.Stop()
|
||||
theirControl.Stop()
|
||||
})
|
||||
}
|
||||
+26
-7
@@ -135,12 +135,12 @@ 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
|
||||
# Configure socket buffers for the udp side (outside), leave unset to use the system defaults. Values will be doubled by the kernel
|
||||
# Linux only. 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.
|
||||
@@ -262,9 +262,10 @@ tun:
|
||||
drop_local_broadcast: false
|
||||
# Toggles forwarding of multicast packets
|
||||
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
|
||||
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
|
||||
mtu: 1300
|
||||
|
||||
# the use_offloads setting controls if Nebula will attempt to enable GSO and GRO for the tun device. Linux only, not reloadable.
|
||||
@@ -410,13 +411,31 @@ logging:
|
||||
#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.
|
||||
#query_buffer: 1024
|
||||
|
||||
# trigger_buffer is the size of the buffer channel for quickly sending handshakes
|
||||
# after receiving the response for lighthouse queries
|
||||
#trigger_buffer: 64
|
||||
|
||||
# pq enables handshakes that mix an ephemeral ML-KEM-1024 key exchange into the session keys, protecting
|
||||
# recorded traffic against a future quantum computer. Authentication is unchanged. These handshakes are too
|
||||
# large for one packet and travel as fragments with forward error correction.
|
||||
#pq:
|
||||
# initiate starts post-quantum handshakes. Attempts alternate between post-quantum and classical until one is
|
||||
# answered, so peers that do not support them still connect.
|
||||
#initiate: false
|
||||
# accept answers post-quantum handshakes from peers.
|
||||
#accept: false
|
||||
# require makes every handshake post-quantum: it implies initiate and accept, never offers a classical handshake
|
||||
# and refuses classical handshakes from peers. Only enable it once every host can speak post-quantum handshakes.
|
||||
#require: false
|
||||
# sticky never falls back to a classical handshake with a peer that has completed a post-quantum one since
|
||||
# nebula started, which defeats an attacker who drops post-quantum handshakes to force a downgrade.
|
||||
#sticky: false
|
||||
# repair_delay is how long the forward error correction fragments trail the rest of a handshake message.
|
||||
#repair_delay: 10ms
|
||||
|
||||
# Tunnel manager settings
|
||||
#tunnels:
|
||||
# drop_inactive controls whether inactive tunnels are maintained or dropped after the inactive_timeout period has
|
||||
|
||||
+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")
|
||||
}
|
||||
@@ -35,7 +35,9 @@ func NewCredential(
|
||||
}
|
||||
|
||||
// buildHandshakeState creates a noise.HandshakeState from this credential.
|
||||
func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.HandshakePattern) (*noise.HandshakeState, error) {
|
||||
// pskPlacement selects the noise psk modifier; 0 means none. A psk for
|
||||
// placements 2 and up is supplied later with SetPresharedKey.
|
||||
func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.HandshakePattern, pskPlacement int) (*noise.HandshakeState, error) {
|
||||
return noise.NewHandshakeState(noise.Config{
|
||||
CipherSuite: hc.cipherSuite,
|
||||
Random: rand.Reader,
|
||||
@@ -43,7 +45,7 @@ func (hc *Credential) buildHandshakeState(initiator bool, pattern noise.Handshak
|
||||
Initiator: initiator,
|
||||
StaticKeypair: noise.DHKey{Private: hc.privateKey, Public: hc.Cert.PublicKey()},
|
||||
PresharedKey: []byte{},
|
||||
PresharedKeyPlacement: 0,
|
||||
PresharedKeyPlacement: pskPlacement,
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,216 @@
|
||||
// Package fec implements the systematic Reed-Solomon erasure code used to carry
|
||||
// handshake messages that do not fit in a single UDP packet.
|
||||
//
|
||||
// A message is split into K equally sized data symbols (the last one zero
|
||||
// padded). Symbol indexes 0..K-1 are the data symbols themselves; indexes
|
||||
// K..MaxSymbols-1 are repair symbols. Any K distinct symbols reconstruct the
|
||||
// message. Repair symbols are generated on demand, so a sender can emit fresh
|
||||
// ones on every retransmit and a receiver can merge everything it has seen.
|
||||
package fec
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
// MaxSymbols is the number of distinct symbols, data and repair together, one
|
||||
// message can be encoded into. It is bounded by the size of GF(2^8).
|
||||
const MaxSymbols = 256
|
||||
|
||||
var (
|
||||
ErrInvalidLayout = errors.New("invalid fec layout")
|
||||
ErrIndexRange = errors.New("symbol index out of range")
|
||||
ErrSymbolSize = errors.New("symbol has the wrong size")
|
||||
ErrNotEnough = errors.New("not enough symbols to decode")
|
||||
ErrCorrupt = errors.New("decoded message has non-zero padding")
|
||||
)
|
||||
|
||||
// Layout describes how a message is split into symbols. Both ends derive it
|
||||
// from the message length alone, so it never has to be sent.
|
||||
type Layout struct {
|
||||
MsgLen int // length of the message in bytes
|
||||
K int // number of data symbols
|
||||
SymbolSize int // size of every symbol, data and repair
|
||||
}
|
||||
|
||||
// NewLayout returns the layout for a message of msgLen bytes carried in symbols
|
||||
// of at most maxSymbolSize bytes. Symbols are balanced, so padding is always
|
||||
// less than K bytes.
|
||||
func NewLayout(msgLen, maxSymbolSize int) (Layout, error) {
|
||||
if msgLen <= 0 || maxSymbolSize <= 0 {
|
||||
return Layout{}, ErrInvalidLayout
|
||||
}
|
||||
k := (msgLen + maxSymbolSize - 1) / maxSymbolSize
|
||||
if k >= MaxSymbols {
|
||||
return Layout{}, fmt.Errorf("%w: %d data symbols", ErrInvalidLayout, k)
|
||||
}
|
||||
return Layout{
|
||||
MsgLen: msgLen,
|
||||
K: k,
|
||||
SymbolSize: (msgLen + k - 1) / k,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Encoder produces symbols for one message.
|
||||
type Encoder struct {
|
||||
layout Layout
|
||||
data [][]byte
|
||||
}
|
||||
|
||||
// NewEncoder copies msg into padded data symbols.
|
||||
func NewEncoder(msg []byte, maxSymbolSize int) (*Encoder, error) {
|
||||
l, err := NewLayout(len(msg), maxSymbolSize)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
buf := make([]byte, l.K*l.SymbolSize)
|
||||
copy(buf, msg)
|
||||
data := make([][]byte, l.K)
|
||||
for i := range data {
|
||||
data[i] = buf[i*l.SymbolSize : (i+1)*l.SymbolSize]
|
||||
}
|
||||
return &Encoder{layout: l, data: data}, nil
|
||||
}
|
||||
|
||||
func (e *Encoder) Layout() Layout {
|
||||
return e.layout
|
||||
}
|
||||
|
||||
// Symbol appends the symbol with the given index to dst and returns the result.
|
||||
func (e *Encoder) Symbol(dst []byte, index int) ([]byte, error) {
|
||||
if index < 0 || index >= MaxSymbols {
|
||||
return nil, ErrIndexRange
|
||||
}
|
||||
if index < e.layout.K {
|
||||
return append(dst, e.data[index]...), nil
|
||||
}
|
||||
|
||||
start := len(dst)
|
||||
dst = append(dst, make([]byte, e.layout.SymbolSize)...)
|
||||
out := dst[start:]
|
||||
for col, d := range e.data {
|
||||
mulAdd(out, d, coefficient(index, col))
|
||||
}
|
||||
return dst, nil
|
||||
}
|
||||
|
||||
// Decoder collects symbols for one message until it can reconstruct it.
|
||||
// It stores at most K symbols, so its memory is bounded by the layout no matter
|
||||
// how many symbols arrive.
|
||||
type Decoder struct {
|
||||
layout Layout
|
||||
have [MaxSymbols]bool
|
||||
syms map[int][]byte
|
||||
}
|
||||
|
||||
// NewDecoder returns a decoder for a message of msgLen bytes that was encoded
|
||||
// with the same maxSymbolSize.
|
||||
func NewDecoder(msgLen, maxSymbolSize int) (*Decoder, error) {
|
||||
l, err := NewLayout(msgLen, maxSymbolSize)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Decoder{layout: l, syms: make(map[int][]byte, l.K)}, nil
|
||||
}
|
||||
|
||||
func (d *Decoder) Layout() Layout {
|
||||
return d.layout
|
||||
}
|
||||
|
||||
// Stored returns the number of symbols held.
|
||||
func (d *Decoder) Stored() int {
|
||||
return len(d.syms)
|
||||
}
|
||||
|
||||
// Has reports whether the symbol with the given index is held.
|
||||
func (d *Decoder) Has(index int) bool {
|
||||
return index >= 0 && index < MaxSymbols && d.have[index]
|
||||
}
|
||||
|
||||
// Ready reports whether enough symbols have arrived to decode.
|
||||
func (d *Decoder) Ready() bool {
|
||||
return len(d.syms) >= d.layout.K
|
||||
}
|
||||
|
||||
// Add stores a copy of the symbol. Duplicates, and anything beyond the first K
|
||||
// distinct symbols, are ignored. It returns whether the decoder is ready.
|
||||
func (d *Decoder) Add(index int, sym []byte) (bool, error) {
|
||||
if index < 0 || index >= MaxSymbols {
|
||||
return d.Ready(), ErrIndexRange
|
||||
}
|
||||
if len(sym) != d.layout.SymbolSize {
|
||||
return d.Ready(), ErrSymbolSize
|
||||
}
|
||||
if d.have[index] || d.Ready() {
|
||||
return d.Ready(), nil
|
||||
}
|
||||
d.have[index] = true
|
||||
d.syms[index] = append([]byte(nil), sym...)
|
||||
return d.Ready(), nil
|
||||
}
|
||||
|
||||
// Decode reconstructs the message from the stored symbols.
|
||||
func (d *Decoder) Decode() ([]byte, error) {
|
||||
if !d.Ready() {
|
||||
return nil, ErrNotEnough
|
||||
}
|
||||
l := d.layout
|
||||
|
||||
out := make([]byte, l.K*l.SymbolSize)
|
||||
var missing, repair []int
|
||||
for i := range l.K {
|
||||
if s, ok := d.syms[i]; ok {
|
||||
copy(out[i*l.SymbolSize:], s)
|
||||
} else {
|
||||
missing = append(missing, i)
|
||||
}
|
||||
}
|
||||
|
||||
if len(missing) > 0 {
|
||||
for i := l.K; i < MaxSymbols && len(repair) < len(missing); i++ {
|
||||
if d.have[i] {
|
||||
repair = append(repair, i)
|
||||
}
|
||||
}
|
||||
if len(repair) < len(missing) {
|
||||
return nil, ErrNotEnough
|
||||
}
|
||||
|
||||
// Each repair symbol r satisfies r = sum_col coefficient(r, col) * data[col].
|
||||
// Move the known data columns to the left hand side, leaving a square
|
||||
// Cauchy system in the missing columns.
|
||||
rhs := make([][]byte, len(repair))
|
||||
m := make([][]byte, len(repair))
|
||||
for ri, row := range repair {
|
||||
rhs[ri] = append([]byte(nil), d.syms[row]...)
|
||||
m[ri] = make([]byte, len(missing))
|
||||
mi := 0
|
||||
for col := range l.K {
|
||||
if mi < len(missing) && missing[mi] == col {
|
||||
m[ri][mi] = coefficient(row, col)
|
||||
mi++
|
||||
continue
|
||||
}
|
||||
mulAdd(rhs[ri], out[col*l.SymbolSize:(col+1)*l.SymbolSize], coefficient(row, col))
|
||||
}
|
||||
}
|
||||
if !invert(m) {
|
||||
// Unreachable for a Cauchy matrix; kept so a broken invariant fails loudly.
|
||||
return nil, errors.New("fec: singular decode matrix")
|
||||
}
|
||||
for mi, col := range missing {
|
||||
dst := out[col*l.SymbolSize : (col+1)*l.SymbolSize]
|
||||
for ri := range repair {
|
||||
mulAdd(dst, rhs[ri], m[mi][ri])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for _, b := range out[l.MsgLen:] {
|
||||
if b != 0 {
|
||||
return nil, ErrCorrupt
|
||||
}
|
||||
}
|
||||
return out[:l.MsgLen], nil
|
||||
}
|
||||
@@ -0,0 +1,318 @@
|
||||
package fec
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"math/rand/v2"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// slowMul is carry-less multiplication reduced by gfPoly, used to check the tables.
|
||||
func slowMul(a, b byte) byte {
|
||||
var p int
|
||||
x, y := int(a), int(b)
|
||||
for y > 0 {
|
||||
if y&1 != 0 {
|
||||
p ^= x
|
||||
}
|
||||
x <<= 1
|
||||
if x&0x100 != 0 {
|
||||
x ^= gfPoly
|
||||
}
|
||||
y >>= 1
|
||||
}
|
||||
return byte(p)
|
||||
}
|
||||
|
||||
func TestGF(t *testing.T) {
|
||||
for a := range 256 {
|
||||
for b := range 256 {
|
||||
require.Equal(t, slowMul(byte(a), byte(b)), gfMul(byte(a), byte(b)), "%d*%d", a, b)
|
||||
}
|
||||
if a != 0 {
|
||||
require.Equal(t, byte(1), gfMul(byte(a), gfInv(byte(a))), "inv(%d)", a)
|
||||
}
|
||||
}
|
||||
|
||||
src := make([]byte, 256)
|
||||
for i := range src {
|
||||
src[i] = byte(i)
|
||||
}
|
||||
for c := range 256 {
|
||||
dst := make([]byte, 256)
|
||||
mulAdd(dst, src, byte(c))
|
||||
for i := range src {
|
||||
require.Equal(t, gfMul(byte(c), src[i]), dst[i])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestLayout(t *testing.T) {
|
||||
for msgLen := 1; msgLen <= 20000; msgLen++ {
|
||||
l, err := NewLayout(msgLen, 1176)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, (msgLen+1175)/1176, l.K)
|
||||
require.LessOrEqual(t, l.SymbolSize, 1176)
|
||||
require.GreaterOrEqual(t, l.K*l.SymbolSize, msgLen)
|
||||
require.Less(t, l.K*l.SymbolSize-msgLen, l.K, "padding must be less than one byte per symbol")
|
||||
}
|
||||
|
||||
l, err := NewLayout(65535, 1176)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 56, l.K)
|
||||
|
||||
_, err = NewLayout(0, 1176)
|
||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
||||
_, err = NewLayout(100, 0)
|
||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
||||
_, err = NewLayout(256, 1)
|
||||
require.ErrorIs(t, err, ErrInvalidLayout)
|
||||
_, err = NewLayout(255, 1)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
func randMsg(r *rand.Rand, n int) []byte {
|
||||
b := make([]byte, n)
|
||||
for i := range b {
|
||||
b[i] = byte(r.Uint32())
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
func decodeWith(t *testing.T, enc *Encoder, msgLen, maxSym int, indexes []int) []byte {
|
||||
t.Helper()
|
||||
dec, err := NewDecoder(msgLen, maxSym)
|
||||
require.NoError(t, err)
|
||||
for _, idx := range indexes {
|
||||
sym, err := enc.Symbol(nil, idx)
|
||||
require.NoError(t, err)
|
||||
_, err = dec.Add(idx, sym)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
require.True(t, dec.Ready())
|
||||
out, err := dec.Decode()
|
||||
require.NoError(t, err)
|
||||
return out
|
||||
}
|
||||
|
||||
// TestExhaustiveSubsets decodes every k-subset of the first k+m symbols for
|
||||
// small codes, which checks the MDS property directly.
|
||||
func TestExhaustiveSubsets(t *testing.T) {
|
||||
r := rand.New(rand.NewPCG(1, 2))
|
||||
const maxSym = 16
|
||||
for k := 1; k <= 10; k++ {
|
||||
for m := 1; m <= 5; m++ {
|
||||
msgLen := (k-1)*maxSym + 1 + r.IntN(maxSym)
|
||||
msg := randMsg(r, msgLen)
|
||||
enc, err := NewEncoder(msg, maxSym)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, k, enc.Layout().K)
|
||||
|
||||
n := k + m
|
||||
for mask := 0; mask < 1<<n; mask++ {
|
||||
var idx []int
|
||||
for i := range n {
|
||||
if mask&(1<<i) != 0 {
|
||||
idx = append(idx, i)
|
||||
}
|
||||
}
|
||||
if len(idx) != k {
|
||||
continue
|
||||
}
|
||||
require.Equal(t, msg, decodeWith(t, enc, msgLen, maxSym, idx), "k=%d m=%d idx=%v", k, m, idx)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestRandomHighIndexes draws symbols from the whole index space, the shape
|
||||
// retransmits produce once fresh repair symbols are in play.
|
||||
func TestRandomHighIndexes(t *testing.T) {
|
||||
r := rand.New(rand.NewPCG(3, 4))
|
||||
for range 2000 {
|
||||
msgLen := 1 + r.IntN(65535)
|
||||
msg := randMsg(r, msgLen)
|
||||
enc, err := NewEncoder(msg, 1176)
|
||||
require.NoError(t, err)
|
||||
k := enc.Layout().K
|
||||
|
||||
idx := r.Perm(MaxSymbols)[:k]
|
||||
require.Equal(t, msg, decodeWith(t, enc, msgLen, 1176, idx), "k=%d idx=%v", k, idx)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDecoderBounds(t *testing.T) {
|
||||
r := rand.New(rand.NewPCG(5, 6))
|
||||
msg := randMsg(r, 3000)
|
||||
enc, err := NewEncoder(msg, 1176)
|
||||
require.NoError(t, err)
|
||||
l := enc.Layout()
|
||||
require.Equal(t, 3, l.K)
|
||||
require.Equal(t, 1000, l.SymbolSize)
|
||||
|
||||
dec, err := NewDecoder(3000, 1176)
|
||||
require.NoError(t, err)
|
||||
|
||||
_, err = dec.Decode()
|
||||
require.ErrorIs(t, err, ErrNotEnough)
|
||||
|
||||
_, err = dec.Add(-1, make([]byte, 1000))
|
||||
require.ErrorIs(t, err, ErrIndexRange)
|
||||
_, err = dec.Add(MaxSymbols, make([]byte, 1000))
|
||||
require.ErrorIs(t, err, ErrIndexRange)
|
||||
_, err = dec.Add(0, make([]byte, 999))
|
||||
require.ErrorIs(t, err, ErrSymbolSize)
|
||||
|
||||
s5, _ := enc.Symbol(nil, 5)
|
||||
ready, err := dec.Add(5, s5)
|
||||
require.NoError(t, err)
|
||||
require.False(t, ready)
|
||||
|
||||
// A duplicate index is ignored, even with different contents.
|
||||
ready, err = dec.Add(5, make([]byte, 1000))
|
||||
require.NoError(t, err)
|
||||
require.False(t, ready)
|
||||
|
||||
s0, _ := enc.Symbol(nil, 0)
|
||||
s9, _ := enc.Symbol(nil, 9)
|
||||
_, err = dec.Add(0, s0)
|
||||
require.NoError(t, err)
|
||||
ready, err = dec.Add(9, s9)
|
||||
require.NoError(t, err)
|
||||
require.True(t, ready)
|
||||
|
||||
// Symbols beyond K are not stored.
|
||||
ready, err = dec.Add(1, make([]byte, 1000))
|
||||
require.NoError(t, err)
|
||||
require.True(t, ready)
|
||||
require.Len(t, dec.syms, 3)
|
||||
|
||||
out, err := dec.Decode()
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, msg, out)
|
||||
}
|
||||
|
||||
func TestCorruptPadding(t *testing.T) {
|
||||
// 3001 bytes in 3 symbols of 1001 leaves 2 bytes of padding in the last one.
|
||||
dec, err := NewDecoder(3001, 1176)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, 1001, dec.Layout().SymbolSize)
|
||||
|
||||
last := make([]byte, 1001)
|
||||
last[1000] = 1
|
||||
for i, s := range [][]byte{make([]byte, 1001), make([]byte, 1001), last} {
|
||||
_, err = dec.Add(i, s)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
_, err = dec.Decode()
|
||||
require.ErrorIs(t, err, ErrCorrupt)
|
||||
}
|
||||
|
||||
// TestKnownAnswer pins the encoding. Both ends of a handshake must produce
|
||||
// identical repair symbols, so any change here is a wire format change.
|
||||
func TestKnownAnswer(t *testing.T) {
|
||||
msg := make([]byte, 3000)
|
||||
for i := range msg {
|
||||
msg[i] = byte(i*7 + 3)
|
||||
}
|
||||
enc, err := NewEncoder(msg, 1176)
|
||||
require.NoError(t, err)
|
||||
|
||||
// Cross-checked against an independent bit-serial GF(2^8) implementation.
|
||||
want := map[int]string{
|
||||
3: "52124f58276ec6338d3b3f4eed273bc7cabfe4f0f467928962b046ad1b348f50",
|
||||
4: "a50928b04738981985a7d4a17ffaf8d7e30014ca64fc53c99800ffb61aec4aa7",
|
||||
5: "ada4c95a7facbc542aaef584e6f0d081b7b0d0eed69ded03b57d0753a119cfc9",
|
||||
255: "839066cdf94f963b223fb1c1c1360f698c14f6349b25653ff5b521791a4021b1",
|
||||
}
|
||||
for idx, h := range want {
|
||||
sym, err := enc.Symbol(nil, idx)
|
||||
require.NoError(t, err)
|
||||
sum := sha256.Sum256(sym)
|
||||
assert.Equal(t, h, hex.EncodeToString(sum[:]), "symbol %d", idx)
|
||||
}
|
||||
}
|
||||
|
||||
func FuzzRoundTrip(f *testing.F) {
|
||||
f.Add([]byte("hello"), uint16(2), uint64(0))
|
||||
f.Add(make([]byte, 9000), uint16(1176), uint64(7))
|
||||
f.Fuzz(func(t *testing.T, msg []byte, maxSym uint16, seed uint64) {
|
||||
if len(msg) == 0 || maxSym == 0 {
|
||||
return
|
||||
}
|
||||
enc, err := NewEncoder(msg, int(maxSym))
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
r := rand.New(rand.NewPCG(seed, seed))
|
||||
idx := r.Perm(MaxSymbols)[:enc.Layout().K]
|
||||
require.Equal(t, msg, decodeWith(t, enc, len(msg), int(maxSym), idx))
|
||||
})
|
||||
}
|
||||
|
||||
// FuzzDecoder feeds arbitrary symbols to a decoder; it must never panic and
|
||||
// must either fail or return a message of the declared length.
|
||||
func FuzzDecoder(f *testing.F) {
|
||||
f.Add(uint16(3000), []byte{0, 5, 9, 200}, []byte("some symbol bytes"))
|
||||
f.Fuzz(func(t *testing.T, msgLen uint16, indexes []byte, fill []byte) {
|
||||
dec, err := NewDecoder(int(msgLen), 1176)
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
size := dec.Layout().SymbolSize
|
||||
for i, idx := range indexes {
|
||||
sym := make([]byte, size)
|
||||
for j := range sym {
|
||||
if len(fill) > 0 {
|
||||
sym[j] = fill[(i+j)%len(fill)]
|
||||
}
|
||||
}
|
||||
if _, err := dec.Add(int(idx), sym); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
out, err := dec.Decode()
|
||||
if err == nil {
|
||||
require.Len(t, out, int(msgLen))
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// BenchmarkRepair and BenchmarkDecode use a v3-sized msg2 (~9.8KB, k=9) with
|
||||
// three repair symbols, decoding with three data symbols missing.
|
||||
func BenchmarkRepair(b *testing.B) {
|
||||
msg := randMsg(rand.New(rand.NewPCG(7, 8)), 9800)
|
||||
enc, err := NewEncoder(msg, 1176)
|
||||
require.NoError(b, err)
|
||||
buf := make([]byte, 0, 1176)
|
||||
b.SetBytes(int64(len(msg)))
|
||||
for b.Loop() {
|
||||
for idx := 9; idx < 12; idx++ {
|
||||
buf, _ = enc.Symbol(buf[:0], idx)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkDecode(b *testing.B) {
|
||||
msg := randMsg(rand.New(rand.NewPCG(7, 8)), 9800)
|
||||
enc, err := NewEncoder(msg, 1176)
|
||||
require.NoError(b, err)
|
||||
idx := []int{0, 1, 2, 3, 5, 6, 9, 10, 11}
|
||||
syms := make([][]byte, len(idx))
|
||||
for i, x := range idx {
|
||||
syms[i], _ = enc.Symbol(nil, x)
|
||||
}
|
||||
b.SetBytes(int64(len(msg)))
|
||||
for b.Loop() {
|
||||
dec, _ := NewDecoder(len(msg), 1176)
|
||||
for i, x := range idx {
|
||||
_, _ = dec.Add(x, syms[i])
|
||||
}
|
||||
if _, err := dec.Decode(); err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package fec
|
||||
|
||||
// Arithmetic over GF(2^8) with the reducing polynomial x^8+x^4+x^3+x^2+1 (0x11d).
|
||||
// Addition is XOR. Multiplication uses log/exp tables; the exp table is doubled so
|
||||
// the sum of two logs never needs reducing mod 255.
|
||||
|
||||
const gfPoly = 0x11d
|
||||
|
||||
var (
|
||||
gfExp [510]byte
|
||||
gfLog [256]byte
|
||||
)
|
||||
|
||||
func init() {
|
||||
x := 1
|
||||
for i := range 255 {
|
||||
gfExp[i] = byte(x)
|
||||
gfExp[i+255] = byte(x)
|
||||
gfLog[x] = byte(i)
|
||||
x <<= 1
|
||||
if x&0x100 != 0 {
|
||||
x ^= gfPoly
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func gfMul(a, b byte) byte {
|
||||
if a == 0 || b == 0 {
|
||||
return 0
|
||||
}
|
||||
return gfExp[int(gfLog[a])+int(gfLog[b])]
|
||||
}
|
||||
|
||||
// gfInv returns the multiplicative inverse of a. a must be non-zero.
|
||||
func gfInv(a byte) byte {
|
||||
return gfExp[255-int(gfLog[a])]
|
||||
}
|
||||
|
||||
// mulAdd computes dst ^= c*src element-wise. dst must be at least as long as src.
|
||||
func mulAdd(dst, src []byte, c byte) {
|
||||
switch c {
|
||||
case 0:
|
||||
return
|
||||
case 1:
|
||||
for i, s := range src {
|
||||
dst[i] ^= s
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
var t [256]byte
|
||||
lc := int(gfLog[c])
|
||||
for s := 1; s < 256; s++ {
|
||||
t[s] = gfExp[int(gfLog[s])+lc]
|
||||
}
|
||||
for i, s := range src {
|
||||
dst[i] ^= t[s]
|
||||
}
|
||||
}
|
||||
|
||||
// coefficient returns the generator matrix entry for repair symbol index row and
|
||||
// data symbol index col. Repair rows are a Cauchy matrix 1/(x_row + y_col) with
|
||||
// x_row = row and y_col = col: rows are always >= k and columns < k so the two
|
||||
// sets are disjoint, which makes every square submatrix invertible and the
|
||||
// systematic code [I; C] MDS. A row depends only on its index, never on how many
|
||||
// repair symbols exist, so new repair symbols can be generated at any time.
|
||||
func coefficient(row, col int) byte {
|
||||
return gfInv(byte(row) ^ byte(col))
|
||||
}
|
||||
|
||||
// invert inverts the n x n matrix m in place with Gauss-Jordan elimination.
|
||||
// It returns false if m is singular.
|
||||
func invert(m [][]byte) bool {
|
||||
n := len(m)
|
||||
inv := make([][]byte, n)
|
||||
for i := range inv {
|
||||
inv[i] = make([]byte, n)
|
||||
inv[i][i] = 1
|
||||
}
|
||||
|
||||
for col := range n {
|
||||
pivot := -1
|
||||
for r := col; r < n; r++ {
|
||||
if m[r][col] != 0 {
|
||||
pivot = r
|
||||
break
|
||||
}
|
||||
}
|
||||
if pivot < 0 {
|
||||
return false
|
||||
}
|
||||
m[col], m[pivot] = m[pivot], m[col]
|
||||
inv[col], inv[pivot] = inv[pivot], inv[col]
|
||||
|
||||
scale := gfInv(m[col][col])
|
||||
for c := range n {
|
||||
m[col][c] = gfMul(m[col][c], scale)
|
||||
inv[col][c] = gfMul(inv[col][c], scale)
|
||||
}
|
||||
|
||||
for r := 0; r < n; r++ {
|
||||
if r == col || m[r][col] == 0 {
|
||||
continue
|
||||
}
|
||||
f := m[r][col]
|
||||
for c := range n {
|
||||
m[r][c] ^= gfMul(f, m[col][c])
|
||||
inv[r][c] ^= gfMul(f, inv[col][c])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
copy(m, inv)
|
||||
return true
|
||||
}
|
||||
@@ -0,0 +1,67 @@
|
||||
package fragment
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/slackhq/nebula/handshake/fec"
|
||||
"github.com/slackhq/nebula/header"
|
||||
)
|
||||
|
||||
// ErrMismatch is returned when a fragment disagrees with the message it claims to
|
||||
// belong to. The caller should discard the whole assembly.
|
||||
var ErrMismatch = errors.New("fragment does not match its message")
|
||||
|
||||
// Assembly collects the fragments of one incoming message. Its memory is bounded
|
||||
// by the message length: at most K symbols are kept however many arrive.
|
||||
//
|
||||
// An Assembly is not safe for concurrent use.
|
||||
type Assembly struct {
|
||||
fragID uint32
|
||||
msgLen uint16
|
||||
dec *fec.Decoder
|
||||
received int
|
||||
}
|
||||
|
||||
// NewAssembly starts an assembly for the message described by h. The fragment
|
||||
// itself still has to be passed to Add.
|
||||
func NewAssembly(h Header) (*Assembly, error) {
|
||||
dec, err := fec.NewDecoder(int(h.MsgLen), MaxSymbolSize)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Assembly{fragID: h.FragID, msgLen: h.MsgLen, dec: dec}, nil
|
||||
}
|
||||
|
||||
// Add records a fragment parsed by Parse. It returns true once enough symbols
|
||||
// are held to call Decode.
|
||||
func (a *Assembly) Add(h Header, sym []byte) (bool, error) {
|
||||
if h.FragID != a.fragID || h.MsgLen != a.msgLen {
|
||||
return a.dec.Ready(), ErrMismatch
|
||||
}
|
||||
a.received += header.Len + HeaderLen + len(sym)
|
||||
return a.dec.Add(int(h.Index), sym)
|
||||
}
|
||||
|
||||
// wouldStore returns how many bytes Add would retain for this fragment.
|
||||
func (a *Assembly) wouldStore(h Header, sym []byte) int {
|
||||
if h.FragID != a.fragID || h.MsgLen != a.msgLen || a.dec.Ready() || a.dec.Has(int(h.Index)) {
|
||||
return 0
|
||||
}
|
||||
return len(sym)
|
||||
}
|
||||
|
||||
// Decode reconstructs the message. It requires Add to have reported ready.
|
||||
func (a *Assembly) Decode() ([]byte, error) {
|
||||
return a.dec.Decode()
|
||||
}
|
||||
|
||||
// Stored returns the number of symbol bytes held.
|
||||
func (a *Assembly) Stored() int {
|
||||
return a.dec.Stored() * a.dec.Layout().SymbolSize
|
||||
}
|
||||
|
||||
// Received returns the number of packet bytes received for this message,
|
||||
// duplicates included. It is the basis for the amplification budget.
|
||||
func (a *Assembly) Received() int {
|
||||
return a.received
|
||||
}
|
||||
@@ -0,0 +1,515 @@
|
||||
package fragment
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"math/rand/v2"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
const testSubtype = header.MessageSubType(9)
|
||||
|
||||
type testKey struct {
|
||||
src string
|
||||
fragID uint32
|
||||
}
|
||||
|
||||
func randMsg(r *rand.Rand, n int) []byte {
|
||||
b := make([]byte, n)
|
||||
for i := range b {
|
||||
b[i] = byte(r.Uint32())
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
func testConfig() TableConfig {
|
||||
return TableConfig{
|
||||
MaxBytes: 1 << 20,
|
||||
MaxEntries: 64,
|
||||
MaxPerSource: 4,
|
||||
MaxMsgLen: 16384,
|
||||
TTL: 2 * time.Second,
|
||||
}
|
||||
}
|
||||
|
||||
// checkInvariants verifies the table's bookkeeping against its contents.
|
||||
func checkInvariants[K, S comparable](t *testing.T, tb *Table[K, S]) {
|
||||
t.Helper()
|
||||
tb.mu.Lock()
|
||||
defer tb.mu.Unlock()
|
||||
|
||||
require.Len(t, tb.order, len(tb.entries))
|
||||
require.LessOrEqual(t, len(tb.entries), tb.cfg.MaxEntries)
|
||||
bytes := 0
|
||||
perSource := map[S]int{}
|
||||
for i, key := range tb.order {
|
||||
e, ok := tb.entries[key]
|
||||
require.True(t, ok)
|
||||
require.Equal(t, i, e.pos)
|
||||
bytes += e.a.Stored()
|
||||
perSource[e.source]++
|
||||
}
|
||||
require.Equal(t, bytes, tb.bytes)
|
||||
require.LessOrEqual(t, tb.bytes, tb.cfg.MaxBytes)
|
||||
require.Equal(t, perSource, tb.perSource)
|
||||
for _, n := range perSource {
|
||||
require.LessOrEqual(t, n, tb.cfg.MaxPerSource)
|
||||
}
|
||||
}
|
||||
|
||||
func parse(t *testing.T, p []byte) (header.H, Header, []byte) {
|
||||
t.Helper()
|
||||
var nh header.H
|
||||
require.NoError(t, nh.Parse(p))
|
||||
h, sym, err := Parse(p[header.Len:])
|
||||
require.NoError(t, err)
|
||||
return nh, h, sym
|
||||
}
|
||||
|
||||
func TestParse(t *testing.T) {
|
||||
h := Header{FragID: 0xdeadbeef, MsgLen: 3000, Index: 7}
|
||||
b := h.Encode(nil)
|
||||
require.Len(t, b, HeaderLen)
|
||||
b = append(b, make([]byte, 1000)...)
|
||||
|
||||
got, sym, err := Parse(b)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, h, got)
|
||||
assert.Len(t, sym, 1000)
|
||||
|
||||
_, _, err = Parse(b[:HeaderLen-1])
|
||||
require.ErrorIs(t, err, ErrShortFragment)
|
||||
_, _, err = Parse(b[:len(b)-1])
|
||||
require.ErrorIs(t, err, ErrSymbolSize)
|
||||
_, _, err = Parse(append(b, 0))
|
||||
require.ErrorIs(t, err, ErrSymbolSize)
|
||||
|
||||
bad := Header{FragID: 0, MsgLen: 3000}.Encode(nil)
|
||||
_, _, err = Parse(append(bad, make([]byte, 1000)...))
|
||||
require.ErrorIs(t, err, ErrFragID)
|
||||
|
||||
bad = Header{FragID: 1, MsgLen: 0}.Encode(nil)
|
||||
_, _, err = Parse(bad)
|
||||
require.ErrorIs(t, err, ErrMsgLen)
|
||||
|
||||
bad = Header{FragID: 1, MsgLen: 3000, Flags: 0x02}.Encode(nil)
|
||||
_, _, err = Parse(append(bad, make([]byte, 1000)...))
|
||||
require.ErrorIs(t, err, ErrFlags)
|
||||
|
||||
t.Run("cookie", func(t *testing.T) {
|
||||
h := Header{FragID: 7, MsgLen: 3000, Index: 4, Flags: FlagCookie}
|
||||
for i := range h.Cookie {
|
||||
h.Cookie[i] = byte(i + 1)
|
||||
}
|
||||
b := h.Encode(nil)
|
||||
require.Len(t, b, HeaderLen+CookieLen)
|
||||
b = append(b, make([]byte, 1000)...)
|
||||
|
||||
got, sym, err := Parse(b)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, h, got)
|
||||
assert.True(t, got.HasCookie())
|
||||
assert.Len(t, sym, 1000)
|
||||
|
||||
_, _, err = Parse(b[:HeaderLen+CookieLen-1])
|
||||
require.ErrorIs(t, err, ErrNoCookie)
|
||||
})
|
||||
}
|
||||
|
||||
func TestDefaultRepair(t *testing.T) {
|
||||
for k, want := range map[int]int{1: 2, 2: 2, 6: 2, 7: 3, 9: 3, 10: 4, 14: 5} {
|
||||
assert.Equal(t, want, DefaultRepair(k), "k=%d", k)
|
||||
}
|
||||
}
|
||||
|
||||
func TestSender(t *testing.T) {
|
||||
_, err := NewSender(nil, testSubtype, 0, 1, 1)
|
||||
require.ErrorIs(t, err, ErrMsgLen)
|
||||
_, err = NewSender(make([]byte, 65536), testSubtype, 0, 1, 1)
|
||||
require.ErrorIs(t, err, ErrMsgLen)
|
||||
_, err = NewSender(make([]byte, 10), testSubtype, 0, 1, 0)
|
||||
require.ErrorIs(t, err, ErrFragID)
|
||||
|
||||
msg := randMsg(rand.New(rand.NewPCG(1, 1)), 9800)
|
||||
s, err := NewSender(msg, testSubtype, 77, 2, 1234)
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, 9, s.Layout().K)
|
||||
|
||||
indexes := func(ps [][]byte) []int {
|
||||
var out []int
|
||||
for _, p := range ps {
|
||||
require.LessOrEqual(t, len(p), MaxPacketLen)
|
||||
nh, h, _ := parse(t, p)
|
||||
assert.Equal(t, header.Handshake, nh.Type)
|
||||
assert.Equal(t, testSubtype, nh.Subtype)
|
||||
assert.Equal(t, uint32(77), nh.RemoteIndex)
|
||||
assert.Equal(t, uint64(2), nh.MessageCounter)
|
||||
assert.Equal(t, uint32(1234), h.FragID)
|
||||
assert.Equal(t, uint16(9800), h.MsgLen)
|
||||
out = append(out, int(h.Index))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
now, later, err := s.Attempt(3)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []int{0, 1, 2, 3, 4, 5, 6, 7, 8}, indexes(now))
|
||||
assert.Equal(t, []int{9, 10, 11}, indexes(later))
|
||||
|
||||
// A retry offers only indexes the receiver has not seen.
|
||||
now, later, err = s.Attempt(3)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []int{12, 13, 14, 15, 16, 17, 18, 19, 20}, indexes(now))
|
||||
assert.Equal(t, []int{21, 22, 23}, indexes(later))
|
||||
|
||||
// A sender rebuilt from the same message resumes where it was told to.
|
||||
s2, err := NewSender(msg, testSubtype, 77, 2, 1234)
|
||||
require.NoError(t, err)
|
||||
s2.SetNext(s.Next())
|
||||
now2, _, err := s2.Attempt(0)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []int{24, 25, 26, 27, 28, 29, 30, 31, 32}, indexes(now2))
|
||||
s2.SetNext(-1)
|
||||
assert.Equal(t, 255, s2.Next())
|
||||
|
||||
// A cookie rides on every later packet, which still fits MaxPacketLen even
|
||||
// with a full size symbol.
|
||||
full, err := NewSender(make([]byte, 2*MaxSymbolSize), testSubtype, 0, 1, 9)
|
||||
require.NoError(t, err)
|
||||
full.SetCookie(Cookie{1, 2, 3})
|
||||
pkts, _, err := full.Attempt(1)
|
||||
require.NoError(t, err)
|
||||
for _, p := range pkts {
|
||||
assert.Len(t, p, MaxPacketLen)
|
||||
_, h, _ := parse(t, p)
|
||||
assert.True(t, h.HasCookie())
|
||||
assert.Equal(t, Cookie{1, 2, 3}, h.Cookie)
|
||||
}
|
||||
|
||||
// Indexes wrap once the space is used up.
|
||||
for range 19 {
|
||||
_, _, err = s.Attempt(3)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
now, _, err = s.Attempt(3)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []int{252, 253, 254, 255, 0, 1, 2, 3, 4}, indexes(now))
|
||||
}
|
||||
|
||||
// TestLossy runs whole messages through heavy loss, reordering and duplication,
|
||||
// merging across attempts, and checks the table ends empty.
|
||||
func TestLossy(t *testing.T) {
|
||||
r := rand.New(rand.NewPCG(2, 2))
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
now := time.Unix(1000, 0)
|
||||
|
||||
for i := range 300 {
|
||||
msg := randMsg(r, 1+r.IntN(16384))
|
||||
fragID := uint32(i + 1)
|
||||
s, err := NewSender(msg, testSubtype, 0, 1, fragID)
|
||||
require.NoError(t, err)
|
||||
|
||||
var got *Result
|
||||
for attempt := 0; got == nil; attempt++ {
|
||||
require.Less(t, attempt, 20, "message never completed")
|
||||
a, b, err := s.Attempt(DefaultRepair(s.Layout().K))
|
||||
require.NoError(t, err)
|
||||
var pkts [][]byte
|
||||
for _, p := range append(a, b...) {
|
||||
if r.Float64() < 0.3 {
|
||||
continue
|
||||
}
|
||||
pkts = append(pkts, p)
|
||||
if r.Float64() < 0.2 {
|
||||
pkts = append(pkts, p)
|
||||
}
|
||||
}
|
||||
r.Shuffle(len(pkts), func(i, j int) { pkts[i], pkts[j] = pkts[j], pkts[i] })
|
||||
|
||||
for _, p := range pkts {
|
||||
_, h, sym := parse(t, p)
|
||||
res, err := tb.Add(testKey{"a", h.FragID}, "a", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
if res != nil {
|
||||
// The table keeps no memory of completed messages, so a late
|
||||
// duplicate can complete one again; the handshake layer
|
||||
// recognises the repeat.
|
||||
require.True(t, bytes.Equal(msg, res.Msg))
|
||||
got = res
|
||||
}
|
||||
checkInvariants(t, tb)
|
||||
}
|
||||
now = now.Add(100 * time.Millisecond)
|
||||
}
|
||||
require.Positive(t, got.Received)
|
||||
// Late fragments of a completed message start a fresh entry; drop it.
|
||||
tb.Expire(now.Add(time.Hour))
|
||||
}
|
||||
assert.Zero(t, tb.Len())
|
||||
assert.Zero(t, tb.Bytes())
|
||||
}
|
||||
|
||||
// TestConcurrent spreads each message's fragments across goroutines, as
|
||||
// multiple UDP reader routines would.
|
||||
func TestConcurrent(t *testing.T) {
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
now := time.Unix(1000, 0)
|
||||
r := rand.New(rand.NewPCG(3, 3))
|
||||
|
||||
const msgs = 50
|
||||
want := make(map[uint32][]byte, msgs)
|
||||
var pkts [][]byte
|
||||
for id := uint32(1); id <= msgs; id++ {
|
||||
msg := randMsg(r, 1+r.IntN(16384))
|
||||
want[id] = msg
|
||||
s, err := NewSender(msg, testSubtype, 0, 1, id)
|
||||
require.NoError(t, err)
|
||||
a, b, err := s.Attempt(DefaultRepair(s.Layout().K))
|
||||
require.NoError(t, err)
|
||||
pkts = append(pkts, a...)
|
||||
pkts = append(pkts, b...)
|
||||
}
|
||||
r.Shuffle(len(pkts), func(i, j int) { pkts[i], pkts[j] = pkts[j], pkts[i] })
|
||||
|
||||
var mu sync.Mutex
|
||||
done := map[uint32]bool{}
|
||||
var wg sync.WaitGroup
|
||||
for w := range 8 {
|
||||
wg.Go(func() {
|
||||
for i := w; i < len(pkts); i += 8 {
|
||||
h, sym, err := Parse(pkts[i][16:])
|
||||
if err != nil {
|
||||
t.Error(err)
|
||||
return
|
||||
}
|
||||
src := string(rune('a' + h.FragID))
|
||||
res, err := tb.Add(testKey{src, h.FragID}, src, now, h, sym)
|
||||
if err != nil {
|
||||
t.Error(err)
|
||||
return
|
||||
}
|
||||
if res != nil {
|
||||
if !bytes.Equal(want[h.FragID], res.Msg) {
|
||||
t.Errorf("message %d decoded wrong", h.FragID)
|
||||
}
|
||||
mu.Lock()
|
||||
done[h.FragID] = true
|
||||
mu.Unlock()
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
wg.Wait()
|
||||
assert.Len(t, done, msgs)
|
||||
checkInvariants(t, tb)
|
||||
}
|
||||
|
||||
func firstFragment(t *testing.T, msgLen int, fragID uint32) (Header, []byte) {
|
||||
t.Helper()
|
||||
s, err := NewSender(make([]byte, msgLen), testSubtype, 0, 1, fragID)
|
||||
require.NoError(t, err)
|
||||
now, _, err := s.Attempt(0)
|
||||
require.NoError(t, err)
|
||||
_, h, sym := parse(t, now[0])
|
||||
return h, sym
|
||||
}
|
||||
|
||||
func TestTableLimits(t *testing.T) {
|
||||
now := time.Unix(1000, 0)
|
||||
|
||||
t.Run("max message length", func(t *testing.T) {
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
h, sym := firstFragment(t, 16385, 1)
|
||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.ErrorIs(t, err, ErrTooLarge)
|
||||
assert.Zero(t, tb.Len())
|
||||
})
|
||||
|
||||
t.Run("per source quota", func(t *testing.T) {
|
||||
cfg := testConfig()
|
||||
cfg.MaxPerSource = 2
|
||||
tb := NewTable[testKey, string](cfg)
|
||||
for id := uint32(1); id <= 3; id++ {
|
||||
h, sym := firstFragment(t, 5000, id)
|
||||
_, err := tb.Add(testKey{"a", id}, "a", now, h, sym)
|
||||
if id <= 2 {
|
||||
require.NoError(t, err)
|
||||
} else {
|
||||
require.ErrorIs(t, err, ErrSourceQuota)
|
||||
}
|
||||
}
|
||||
h, sym := firstFragment(t, 5000, 4)
|
||||
_, err := tb.Add(testKey{"b", 4}, "b", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 3, tb.Len())
|
||||
checkInvariants(t, tb)
|
||||
})
|
||||
|
||||
t.Run("max entries evicts", func(t *testing.T) {
|
||||
cfg := testConfig()
|
||||
cfg.MaxEntries = 4
|
||||
tb := NewTable[testKey, string](cfg)
|
||||
for id := uint32(1); id <= 10; id++ {
|
||||
h, sym := firstFragment(t, 5000, id)
|
||||
src := string(rune('a' + id))
|
||||
_, err := tb.Add(testKey{src, id}, src, now, h, sym)
|
||||
require.NoError(t, err)
|
||||
checkInvariants(t, tb)
|
||||
}
|
||||
assert.Equal(t, 4, tb.Len())
|
||||
})
|
||||
|
||||
t.Run("max bytes evicts others", func(t *testing.T) {
|
||||
cfg := testConfig()
|
||||
cfg.MaxBytes = 3 * 1000
|
||||
tb := NewTable[testKey, string](cfg)
|
||||
for id := uint32(1); id <= 10; id++ {
|
||||
h, sym := firstFragment(t, 5000, id) // 5 symbols of 1000
|
||||
src := string(rune('a' + id))
|
||||
_, err := tb.Add(testKey{src, id}, src, now, h, sym)
|
||||
require.NoError(t, err)
|
||||
checkInvariants(t, tb)
|
||||
}
|
||||
assert.Equal(t, 3000, tb.Bytes())
|
||||
})
|
||||
|
||||
t.Run("no room removes new entry", func(t *testing.T) {
|
||||
cfg := testConfig()
|
||||
cfg.MaxBytes = 500
|
||||
tb := NewTable[testKey, string](cfg)
|
||||
h, sym := firstFragment(t, 5000, 1)
|
||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.ErrorIs(t, err, ErrNoRoom)
|
||||
assert.Zero(t, tb.Len())
|
||||
checkInvariants(t, tb)
|
||||
})
|
||||
|
||||
t.Run("duplicates are not charged", func(t *testing.T) {
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
h, sym := firstFragment(t, 5000, 1)
|
||||
for range 5 {
|
||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
assert.Equal(t, 1000, tb.Bytes())
|
||||
})
|
||||
|
||||
t.Run("mismatch drops the entry", func(t *testing.T) {
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
h, sym := firstFragment(t, 5000, 1)
|
||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
|
||||
h2, sym2 := firstFragment(t, 6000, 1)
|
||||
_, err = tb.Add(testKey{"a", 1}, "a", now, h2, sym2)
|
||||
require.ErrorIs(t, err, ErrMismatch)
|
||||
assert.Zero(t, tb.Len())
|
||||
assert.Zero(t, tb.Bytes())
|
||||
checkInvariants(t, tb)
|
||||
})
|
||||
|
||||
t.Run("load", func(t *testing.T) {
|
||||
cfg := testConfig()
|
||||
cfg.MaxEntries = 4
|
||||
cfg.MaxBytes = 10000
|
||||
tb := NewTable[testKey, string](cfg)
|
||||
assert.Zero(t, tb.Load())
|
||||
h, sym := firstFragment(t, 5000, 1)
|
||||
_, err := tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
assert.InDelta(t, 0.25, tb.Load(), 0.001, "one of four entries")
|
||||
h, sym = firstFragment(t, 5000, 2)
|
||||
_, err = tb.Add(testKey{"b", 2}, "b", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
assert.InDelta(t, 0.5, tb.Load(), 0.001)
|
||||
})
|
||||
|
||||
t.Run("ttl", func(t *testing.T) {
|
||||
tb := NewTable[testKey, string](testConfig())
|
||||
s, err := NewSender(make([]byte, 5000), testSubtype, 0, 1, 1)
|
||||
require.NoError(t, err)
|
||||
pkts, _, err := s.Attempt(0)
|
||||
require.NoError(t, err)
|
||||
|
||||
_, h, sym := parse(t, pkts[0])
|
||||
_, err = tb.Add(testKey{"a", 1}, "a", now, h, sym)
|
||||
require.NoError(t, err)
|
||||
|
||||
// Activity within the TTL keeps the entry and slides its deadline.
|
||||
_, h, sym = parse(t, pkts[1])
|
||||
_, err = tb.Add(testKey{"a", 1}, "a", now.Add(1500*time.Millisecond), h, sym)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 2000, tb.Bytes())
|
||||
|
||||
tb.Expire(now.Add(3 * time.Second))
|
||||
assert.Equal(t, 1, tb.Len())
|
||||
|
||||
// A stale entry is restarted rather than merged.
|
||||
_, h, sym = parse(t, pkts[2])
|
||||
_, err = tb.Add(testKey{"a", 1}, "a", now.Add(10*time.Second), h, sym)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 1000, tb.Bytes())
|
||||
|
||||
tb.Expire(now.Add(time.Minute))
|
||||
assert.Zero(t, tb.Len())
|
||||
checkInvariants(t, tb)
|
||||
})
|
||||
}
|
||||
|
||||
func FuzzParse(f *testing.F) {
|
||||
f.Add(append(Header{FragID: 1, MsgLen: 3000}.Encode(nil), make([]byte, 1000)...))
|
||||
f.Add([]byte{0, 0, 0, 1, 0, 1, 0, 0, 7})
|
||||
f.Fuzz(func(t *testing.T, b []byte) {
|
||||
h, sym, err := Parse(b)
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
require.Equal(t, b, append(h.Encode(nil), sym...))
|
||||
l, err := h.Layout()
|
||||
require.NoError(t, err)
|
||||
require.LessOrEqual(t, l.SymbolSize, MaxSymbolSize)
|
||||
})
|
||||
}
|
||||
|
||||
// FuzzTable drives a small table with arbitrary fragments and checks its
|
||||
// bookkeeping after every step.
|
||||
func FuzzTable(f *testing.F) {
|
||||
f.Add([]byte{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12})
|
||||
f.Fuzz(func(t *testing.T, ops []byte) {
|
||||
tb := NewTable[testKey, string](TableConfig{
|
||||
MaxBytes: 4000,
|
||||
MaxEntries: 3,
|
||||
MaxPerSource: 2,
|
||||
MaxMsgLen: 6000,
|
||||
TTL: time.Second,
|
||||
})
|
||||
now := time.Unix(0, 0)
|
||||
for len(ops) >= 4 {
|
||||
src := string(rune('a' + ops[0]%4))
|
||||
fragID := uint32(ops[1]%5) + 1
|
||||
msgLen := uint16(ops[2])*32 + 1
|
||||
index := ops[3]
|
||||
ops = ops[4:]
|
||||
|
||||
h := Header{FragID: fragID, MsgLen: msgLen, Index: index}
|
||||
l, err := h.Layout()
|
||||
require.NoError(t, err)
|
||||
sym := make([]byte, l.SymbolSize)
|
||||
if index%7 == 0 {
|
||||
now = now.Add(600 * time.Millisecond)
|
||||
tb.Expire(now)
|
||||
}
|
||||
res, err := tb.Add(testKey{src, fragID}, src, now, h, sym)
|
||||
if res != nil {
|
||||
require.NoError(t, err)
|
||||
require.Len(t, res.Msg, int(msgLen))
|
||||
}
|
||||
checkInvariants(t, tb)
|
||||
}
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,118 @@
|
||||
package fragment
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"math"
|
||||
|
||||
"github.com/slackhq/nebula/handshake/fec"
|
||||
"github.com/slackhq/nebula/header"
|
||||
)
|
||||
|
||||
// DefaultRepair is the starting number of repair symbols per attempt for a
|
||||
// message of k data symbols. Small messages get proportionally more repair.
|
||||
func DefaultRepair(k int) int {
|
||||
return max(2, (k+2)/3)
|
||||
}
|
||||
|
||||
// Sender produces the fragment packets of one outgoing handshake message.
|
||||
//
|
||||
// The first attempt sends the K data symbols followed by repair symbols. Every
|
||||
// later attempt sends symbols with indexes the receiver has not been offered yet,
|
||||
// so whatever it already holds still counts toward K. Symbols are a deterministic
|
||||
// function of the message, which keeps retransmits idempotent. Once all
|
||||
// fec.MaxSymbols indexes are used the sequence wraps and repeats.
|
||||
//
|
||||
// A Sender is not safe for concurrent use.
|
||||
type Sender struct {
|
||||
enc *fec.Encoder
|
||||
subtype header.MessageSubType
|
||||
remoteIndex uint32
|
||||
counter uint64
|
||||
fragID uint32
|
||||
next int
|
||||
cookie *Cookie
|
||||
}
|
||||
|
||||
// NewSender prepares msg for sending. subtype, remoteIndex and counter fill the
|
||||
// Nebula header of every fragment; fragID is the sender's local index.
|
||||
func NewSender(msg []byte, subtype header.MessageSubType, remoteIndex uint32, counter uint64, fragID uint32) (*Sender, error) {
|
||||
if len(msg) == 0 || len(msg) > math.MaxUint16 {
|
||||
return nil, ErrMsgLen
|
||||
}
|
||||
if fragID == 0 {
|
||||
return nil, ErrFragID
|
||||
}
|
||||
enc, err := fec.NewEncoder(msg, MaxSymbolSize)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Sender{
|
||||
enc: enc,
|
||||
subtype: subtype,
|
||||
remoteIndex: remoteIndex,
|
||||
counter: counter,
|
||||
fragID: fragID,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (s *Sender) Layout() fec.Layout {
|
||||
return s.enc.Layout()
|
||||
}
|
||||
|
||||
// SetNext sets the index the next attempt starts from, so a sender rebuilt from
|
||||
// a cached message can carry on offering fresh symbols.
|
||||
func (s *Sender) SetNext(index int) {
|
||||
s.next = ((index % fec.MaxSymbols) + fec.MaxSymbols) % fec.MaxSymbols
|
||||
}
|
||||
|
||||
// SetCookie attaches a cookie from a responder under load to every later packet.
|
||||
func (s *Sender) SetCookie(c Cookie) {
|
||||
s.cookie = &c
|
||||
}
|
||||
|
||||
// Next returns the index the next attempt starts from.
|
||||
func (s *Sender) Next() int {
|
||||
return s.next
|
||||
}
|
||||
|
||||
// Attempt returns the packets for one transmission attempt carrying K+repair
|
||||
// symbols. now should be sent immediately and later after the repair delay, so
|
||||
// a tail drop at the end of the first burst does not also take the repair.
|
||||
func (s *Sender) Attempt(repair int) (now, later [][]byte, err error) {
|
||||
if repair < 0 {
|
||||
return nil, nil, errors.New("negative repair count")
|
||||
}
|
||||
k := s.enc.Layout().K
|
||||
now = make([][]byte, 0, k)
|
||||
later = make([][]byte, 0, repair)
|
||||
for i := range k + repair {
|
||||
p, err := s.packet(s.next)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
s.next = (s.next + 1) % fec.MaxSymbols
|
||||
if i < k {
|
||||
now = append(now, p)
|
||||
} else {
|
||||
later = append(later, p)
|
||||
}
|
||||
}
|
||||
return now, later, nil
|
||||
}
|
||||
|
||||
func (s *Sender) packet(index int) ([]byte, error) {
|
||||
l := s.enc.Layout()
|
||||
p := make([]byte, header.Len, header.Len+HeaderLen+CookieLen+l.SymbolSize)
|
||||
header.Encode(p, header.Version, header.Handshake, s.subtype, s.remoteIndex, s.counter)
|
||||
h := Header{
|
||||
FragID: s.fragID,
|
||||
MsgLen: uint16(l.MsgLen),
|
||||
Index: uint8(index),
|
||||
}
|
||||
if s.cookie != nil {
|
||||
h.Flags |= FlagCookie
|
||||
h.Cookie = *s.cookie
|
||||
}
|
||||
p = h.Encode(p)
|
||||
return s.enc.Symbol(p, index)
|
||||
}
|
||||
@@ -0,0 +1,220 @@
|
||||
package fragment
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"math/rand/v2"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
var (
|
||||
ErrTooLarge = errors.New("fragmented message exceeds the size limit")
|
||||
ErrSourceQuota = errors.New("source has too many messages in progress")
|
||||
ErrNoRoom = errors.New("no room for fragment")
|
||||
)
|
||||
|
||||
// TableConfig bounds a Table.
|
||||
type TableConfig struct {
|
||||
MaxBytes int // symbol bytes held across all entries
|
||||
MaxEntries int // messages in progress across all sources
|
||||
MaxPerSource int // messages in progress per source
|
||||
MaxMsgLen int // largest message accepted
|
||||
TTL time.Duration // an entry idle this long is dropped
|
||||
}
|
||||
|
||||
// Table reassembles messages from senders that have not authenticated yet, the
|
||||
// responder's view of msg1. Every resource is capped. When a cap is hit a
|
||||
// random entry is evicted; random eviction is harder to aim than LRU, which a
|
||||
// flood can use to flush specific entries.
|
||||
//
|
||||
// K identifies one message, typically the source plus FragID. S identifies the
|
||||
// source for quotas, typically the address masked to /32 or /64.
|
||||
//
|
||||
// A Table is safe for concurrent use.
|
||||
type Table[K, S comparable] struct {
|
||||
mu sync.Mutex
|
||||
cfg TableConfig
|
||||
entries map[K]*tableEntry[K, S]
|
||||
order []K
|
||||
perSource map[S]int
|
||||
bytes int
|
||||
}
|
||||
|
||||
type tableEntry[K, S comparable] struct {
|
||||
a *Assembly
|
||||
source S
|
||||
lastSeen time.Time
|
||||
pos int
|
||||
}
|
||||
|
||||
func NewTable[K, S comparable](cfg TableConfig) *Table[K, S] {
|
||||
return &Table[K, S]{
|
||||
cfg: cfg,
|
||||
entries: make(map[K]*tableEntry[K, S]),
|
||||
perSource: make(map[S]int),
|
||||
}
|
||||
}
|
||||
|
||||
// Result describes a completed message.
|
||||
type Result struct {
|
||||
Msg []byte // the decoded message
|
||||
Received int // packet bytes received for it, for the amplification budget
|
||||
}
|
||||
|
||||
// Add records a fragment parsed by Parse. When the message is complete its entry
|
||||
// is removed and the result returned; otherwise the result is nil. A decode
|
||||
// error means the message is lost and must be retransmitted.
|
||||
func (t *Table[K, S]) Add(key K, source S, now time.Time, h Header, sym []byte) (*Result, error) {
|
||||
if int(h.MsgLen) > t.cfg.MaxMsgLen {
|
||||
return nil, ErrTooLarge
|
||||
}
|
||||
|
||||
t.mu.Lock()
|
||||
e, ok := t.entries[key]
|
||||
if ok && now.Sub(e.lastSeen) > t.cfg.TTL {
|
||||
t.remove(key, e)
|
||||
ok = false
|
||||
}
|
||||
if !ok {
|
||||
var err error
|
||||
e, err = t.insert(key, source, h)
|
||||
if err != nil {
|
||||
t.mu.Unlock()
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
e.lastSeen = now
|
||||
|
||||
if !t.makeRoom(key, e.a.wouldStore(h, sym)) {
|
||||
if e.a.Stored() == 0 {
|
||||
t.remove(key, e)
|
||||
}
|
||||
t.mu.Unlock()
|
||||
return nil, ErrNoRoom
|
||||
}
|
||||
|
||||
before := e.a.Stored()
|
||||
ready, err := e.a.Add(h, sym)
|
||||
t.bytes += e.a.Stored() - before
|
||||
if err != nil || !ready {
|
||||
if errors.Is(err, ErrMismatch) || (err != nil && e.a.Stored() == 0) {
|
||||
t.remove(key, e)
|
||||
}
|
||||
t.mu.Unlock()
|
||||
return nil, err
|
||||
}
|
||||
|
||||
t.remove(key, e)
|
||||
t.mu.Unlock()
|
||||
|
||||
msg, err := e.a.Decode()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Result{Msg: msg, Received: e.a.Received()}, nil
|
||||
}
|
||||
|
||||
// Expire drops every entry idle for longer than the TTL.
|
||||
func (t *Table[K, S]) Expire(now time.Time) {
|
||||
t.mu.Lock()
|
||||
defer t.mu.Unlock()
|
||||
for i := 0; i < len(t.order); {
|
||||
key := t.order[i]
|
||||
e := t.entries[key]
|
||||
if now.Sub(e.lastSeen) > t.cfg.TTL {
|
||||
// remove swaps the last entry into position i, so look at i again.
|
||||
t.remove(key, e)
|
||||
continue
|
||||
}
|
||||
i++
|
||||
}
|
||||
}
|
||||
|
||||
// Len returns the number of messages in progress.
|
||||
func (t *Table[K, S]) Len() int {
|
||||
t.mu.Lock()
|
||||
defer t.mu.Unlock()
|
||||
return len(t.entries)
|
||||
}
|
||||
|
||||
// Load returns how full the table is, from 0 to 1, by whichever of its byte and
|
||||
// entry limits is closer.
|
||||
func (t *Table[K, S]) Load() float64 {
|
||||
t.mu.Lock()
|
||||
defer t.mu.Unlock()
|
||||
return max(float64(t.bytes)/float64(t.cfg.MaxBytes), float64(len(t.entries))/float64(t.cfg.MaxEntries))
|
||||
}
|
||||
|
||||
// Bytes returns the number of symbol bytes held.
|
||||
func (t *Table[K, S]) Bytes() int {
|
||||
t.mu.Lock()
|
||||
defer t.mu.Unlock()
|
||||
return t.bytes
|
||||
}
|
||||
|
||||
func (t *Table[K, S]) insert(key K, source S, h Header) (*tableEntry[K, S], error) {
|
||||
if t.perSource[source] >= t.cfg.MaxPerSource {
|
||||
return nil, ErrSourceQuota
|
||||
}
|
||||
a, err := NewAssembly(h)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
for len(t.entries) >= t.cfg.MaxEntries {
|
||||
if !t.evictRandom(nil) {
|
||||
return nil, ErrNoRoom
|
||||
}
|
||||
}
|
||||
|
||||
e := &tableEntry[K, S]{a: a, source: source, pos: len(t.order)}
|
||||
t.entries[key] = e
|
||||
t.order = append(t.order, key)
|
||||
t.perSource[source]++
|
||||
return e, nil
|
||||
}
|
||||
|
||||
// makeRoom evicts random entries other than keep until n more bytes fit.
|
||||
func (t *Table[K, S]) makeRoom(keep K, n int) bool {
|
||||
for t.bytes+n > t.cfg.MaxBytes {
|
||||
if !t.evictRandom(&keep) {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (t *Table[K, S]) evictRandom(keep *K) bool {
|
||||
candidates := len(t.order)
|
||||
if keep != nil {
|
||||
if _, ok := t.entries[*keep]; ok {
|
||||
candidates--
|
||||
}
|
||||
}
|
||||
if candidates <= 0 {
|
||||
return false
|
||||
}
|
||||
for {
|
||||
key := t.order[rand.IntN(len(t.order))]
|
||||
if keep != nil && key == *keep {
|
||||
continue
|
||||
}
|
||||
t.remove(key, t.entries[key])
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
func (t *Table[K, S]) remove(key K, e *tableEntry[K, S]) {
|
||||
last := len(t.order) - 1
|
||||
moved := t.order[last]
|
||||
t.order[e.pos] = moved
|
||||
t.entries[moved].pos = e.pos
|
||||
t.order = t.order[:last]
|
||||
delete(t.entries, key)
|
||||
|
||||
t.bytes -= e.a.Stored()
|
||||
if t.perSource[e.source] <= 1 {
|
||||
delete(t.perSource, e.source)
|
||||
} else {
|
||||
t.perSource[e.source]--
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,121 @@
|
||||
// Package fragment carries handshake messages that do not fit in one UDP
|
||||
// packet. A message is Reed-Solomon coded into equally sized symbols (see
|
||||
// handshake/fec) and each symbol travels in its own packet:
|
||||
//
|
||||
// Nebula header (16) | Fragment header (8) | [cookie (16)] | symbol
|
||||
//
|
||||
// The fragment header is FragID u32 | MsgLen u16 | Index u8 | Flags u8, all big
|
||||
// endian. Both ends derive the symbol layout from MsgLen, so any MsgLen-derived
|
||||
// value never has to be sent. FlagCookie marks a cookie a responder under load
|
||||
// asked for; room for it is always reserved, so a fragment never outgrows
|
||||
// MaxPacketLen.
|
||||
package fragment
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
|
||||
"github.com/slackhq/nebula/handshake/fec"
|
||||
"github.com/slackhq/nebula/header"
|
||||
)
|
||||
|
||||
const (
|
||||
// HeaderLen is the size of the fragment header that follows the Nebula header.
|
||||
HeaderLen = 8
|
||||
|
||||
// CookieLen is the size of the cookie a fragment carries when FlagCookie is set.
|
||||
CookieLen = 16
|
||||
|
||||
// FlagCookie marks a fragment that carries a cookie after its header.
|
||||
FlagCookie uint8 = 0x01
|
||||
|
||||
// MaxPacketLen bounds every fragment packet, Nebula header included. A relayed
|
||||
// fragment gains a 16 byte header and a 16 byte tag, which lands exactly on
|
||||
// the 1232 byte UDP payload available on an IPv6 minimum MTU path.
|
||||
MaxPacketLen = 1200
|
||||
|
||||
// MaxSymbolSize is the largest symbol that fits in MaxPacketLen alongside a cookie.
|
||||
MaxSymbolSize = MaxPacketLen - header.Len - HeaderLen - CookieLen
|
||||
)
|
||||
|
||||
var (
|
||||
ErrShortFragment = errors.New("fragment is too short")
|
||||
ErrFragID = errors.New("fragment has a zero FragID")
|
||||
ErrMsgLen = errors.New("fragment has a zero MsgLen")
|
||||
ErrFlags = errors.New("fragment has reserved flags set")
|
||||
ErrNoCookie = errors.New("fragment is too short for its cookie")
|
||||
ErrSymbolSize = errors.New("fragment symbol size does not match its MsgLen")
|
||||
)
|
||||
|
||||
// Cookie proves a sender received a responder's reply at its address.
|
||||
type Cookie [CookieLen]byte
|
||||
|
||||
// Header is the fragment header.
|
||||
type Header struct {
|
||||
FragID uint32 // the sender's local index for this handshake, never zero
|
||||
MsgLen uint16 // length of the whole message
|
||||
Index uint8 // symbol index, data below K and repair from K
|
||||
Flags uint8 // FlagCookie, other bits reserved and zero
|
||||
Cookie Cookie // valid when Flags has FlagCookie
|
||||
}
|
||||
|
||||
func (h Header) HasCookie() bool {
|
||||
return h.Flags&FlagCookie != 0
|
||||
}
|
||||
|
||||
// Encode appends the header, and its cookie if it has one, to b.
|
||||
func (h Header) Encode(b []byte) []byte {
|
||||
b = binary.BigEndian.AppendUint32(b, h.FragID)
|
||||
b = binary.BigEndian.AppendUint16(b, h.MsgLen)
|
||||
b = append(b, h.Index, h.Flags)
|
||||
if h.HasCookie() {
|
||||
b = append(b, h.Cookie[:]...)
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
// Layout returns the symbol layout the header's MsgLen implies.
|
||||
func (h Header) Layout() (fec.Layout, error) {
|
||||
return fec.NewLayout(int(h.MsgLen), MaxSymbolSize)
|
||||
}
|
||||
|
||||
// Parse validates the bytes following the Nebula header and splits them into
|
||||
// the fragment header and the symbol. The symbol aliases b.
|
||||
func Parse(b []byte) (Header, []byte, error) {
|
||||
if len(b) < HeaderLen {
|
||||
return Header{}, nil, ErrShortFragment
|
||||
}
|
||||
h := Header{
|
||||
FragID: binary.BigEndian.Uint32(b[0:4]),
|
||||
MsgLen: binary.BigEndian.Uint16(b[4:6]),
|
||||
Index: b[6],
|
||||
Flags: b[7],
|
||||
}
|
||||
if h.FragID == 0 {
|
||||
return Header{}, nil, ErrFragID
|
||||
}
|
||||
if h.MsgLen == 0 {
|
||||
return Header{}, nil, ErrMsgLen
|
||||
}
|
||||
if h.Flags&^FlagCookie != 0 {
|
||||
return Header{}, nil, ErrFlags
|
||||
}
|
||||
b = b[HeaderLen:]
|
||||
if h.HasCookie() {
|
||||
if len(b) < CookieLen {
|
||||
return Header{}, nil, ErrNoCookie
|
||||
}
|
||||
copy(h.Cookie[:], b)
|
||||
b = b[CookieLen:]
|
||||
}
|
||||
|
||||
l, err := h.Layout()
|
||||
if err != nil {
|
||||
return Header{}, nil, err
|
||||
}
|
||||
sym := b
|
||||
if len(sym) != l.SymbolSize {
|
||||
return Header{}, nil, ErrSymbolSize
|
||||
}
|
||||
return h, sym, nil
|
||||
}
|
||||
@@ -24,6 +24,9 @@ message NebulaHandshakeDetails {
|
||||
uint64 Cookie = 4 [deprecated = true];
|
||||
uint64 Time = 5;
|
||||
uint32 CertVersion = 8;
|
||||
// KEMKey is the initiator's ephemeral ML-KEM-1024 encapsulation key. It is
|
||||
// only present in msg1 of the ix_psk2_mlkem1024 subtype.
|
||||
bytes KEMKey = 9;
|
||||
// reserved for WIP multiport
|
||||
reserved 6, 7;
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
package handshake
|
||||
|
||||
import (
|
||||
"crypto/hkdf"
|
||||
"crypto/mlkem"
|
||||
"crypto/sha256"
|
||||
"errors"
|
||||
"fmt"
|
||||
)
|
||||
|
||||
// kemPSKSalt separates the psk derivation from any other use of the secret.
|
||||
const kemPSKSalt = "nebula ix_psk2_mlkem1024 v1"
|
||||
|
||||
var ErrInvalidKEMKey = errors.New("peer sent an invalid ML-KEM encapsulation key")
|
||||
|
||||
// kemPSK derives the noise psk from an ML-KEM shared secret. The ciphertext is
|
||||
// bound in because, unlike the encapsulation key, it travels outside the noise
|
||||
// transcript.
|
||||
func kemPSK(sharedKey, ciphertext []byte) ([]byte, error) {
|
||||
secret := make([]byte, 0, len(sharedKey)+len(ciphertext))
|
||||
secret = append(secret, sharedKey...)
|
||||
secret = append(secret, ciphertext...)
|
||||
return hkdf.Extract(sha256.New, secret, []byte(kemPSKSalt))
|
||||
}
|
||||
|
||||
// kemEncapsulate is the responder half: encapsulate to the initiator's key,
|
||||
// install the psk, and remember the ciphertext to prefix the response with.
|
||||
func (m *Machine) kemEncapsulate(encapsulationKey []byte) error {
|
||||
ek, err := mlkem.NewEncapsulationKey1024(encapsulationKey)
|
||||
if err != nil {
|
||||
return fmt.Errorf("%w: %w", ErrInvalidKEMKey, err)
|
||||
}
|
||||
sharedKey, ct := ek.Encapsulate()
|
||||
psk, err := kemPSK(sharedKey, ct)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if err := m.hs.SetPresharedKey(psk); err != nil {
|
||||
return err
|
||||
}
|
||||
m.kemCiphertext = ct
|
||||
return nil
|
||||
}
|
||||
|
||||
// kemDecapsulate is the initiator half: recover the shared secret from the
|
||||
// ciphertext prefixing the response and install the psk. It returns the rest of
|
||||
// the message, which is the noise message.
|
||||
func (m *Machine) kemDecapsulate(msg []byte) ([]byte, error) {
|
||||
if len(msg) < mlkem.CiphertextSize1024 {
|
||||
return nil, ErrPacketTooShort
|
||||
}
|
||||
if m.kemKey == nil {
|
||||
return nil, errors.New("no ML-KEM decapsulation key for this handshake")
|
||||
}
|
||||
ct := msg[:mlkem.CiphertextSize1024]
|
||||
sharedKey, err := m.kemKey.Decapsulate(ct)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
psk, err := kemPSK(sharedKey, ct)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if err := m.hs.SetPresharedKey(psk); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return msg[mlkem.CiphertextSize1024:], nil
|
||||
}
|
||||
@@ -0,0 +1,208 @@
|
||||
package handshake
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"crypto/mlkem"
|
||||
"net/netip"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/flynn/noise"
|
||||
"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"
|
||||
)
|
||||
|
||||
func newKEMMachine(t *testing.T, cs *testCertState, v CertVerifier, initiator bool, index uint32) *Machine {
|
||||
t.Helper()
|
||||
m, err := NewMachine(
|
||||
cs.version, cs.getCredential, v,
|
||||
func() (uint32, error) { return index, nil },
|
||||
initiator, header.HandshakeIXPSK2MLKEM1024,
|
||||
)
|
||||
require.NoError(t, err)
|
||||
return m
|
||||
}
|
||||
|
||||
type kemFixture struct {
|
||||
initCS, respCS *testCertState
|
||||
v CertVerifier
|
||||
}
|
||||
|
||||
func newKEMFixture(t *testing.T, cipher noise.CipherFunc) kemFixture {
|
||||
ca, _, caKey, _ := ct.NewTestCaCert(
|
||||
cert.Version2, cert.Curve_CURVE25519, time.Time{}, time.Time{}, nil, nil, nil,
|
||||
)
|
||||
return kemFixture{
|
||||
initCS: newTestCertStateWithCipher(t, ca, caKey, "initiator", []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}, cipher),
|
||||
respCS: newTestCertStateWithCipher(t, ca, caKey, "responder", []netip.Prefix{netip.MustParsePrefix("10.0.0.2/24")}, cipher),
|
||||
v: testVerifier(ct.NewTestCAPool(ca)),
|
||||
}
|
||||
}
|
||||
|
||||
func requireKeysMatch(t *testing.T, a, b *Result) {
|
||||
t.Helper()
|
||||
c, err := a.EKey.Encrypt(nil, nil, []byte("hello"))
|
||||
require.NoError(t, err)
|
||||
p, err := b.DKey.Decrypt(nil, nil, c)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []byte("hello"), p)
|
||||
|
||||
c, err = b.EKey.Encrypt(nil, nil, []byte("world"))
|
||||
require.NoError(t, err)
|
||||
p, err = a.DKey.Decrypt(nil, nil, c)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, []byte("world"), p)
|
||||
}
|
||||
|
||||
func TestKEMHandshake(t *testing.T) {
|
||||
for _, cipher := range []noise.CipherFunc{noise.CipherChaChaPoly, noise.CipherAESGCM} {
|
||||
t.Run(cipher.CipherName(), func(t *testing.T) {
|
||||
f := newKEMFixture(t, cipher)
|
||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
|
||||
msg1, err := initM.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, header.HandshakeIXPSK2MLKEM1024, header.MessageSubType(msg1[1]))
|
||||
assert.Greater(t, len(msg1), header.Len+mlkem.EncapsulationKeySize1024)
|
||||
|
||||
msg2, respR, err := respM.ProcessPacket(nil, msg1)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, respR)
|
||||
assert.Greater(t, len(msg2), header.Len+mlkem.CiphertextSize1024)
|
||||
|
||||
_, initR, err := initM.ProcessPacket(nil, msg2)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, initR)
|
||||
|
||||
assert.Equal(t, "responder", initR.RemoteCert.Certificate.Name())
|
||||
assert.Equal(t, "initiator", respR.RemoteCert.Certificate.Name())
|
||||
assert.Equal(t, uint32(2000), initR.RemoteIndex)
|
||||
assert.Equal(t, uint32(1000), respR.RemoteIndex)
|
||||
requireKeysMatch(t, initR, respR)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestKEMSecretMatters checks the ML-KEM secret really reaches the transport
|
||||
// keys: an initiator holding a different decapsulation key cannot complete even
|
||||
// though every DH input is genuine.
|
||||
func TestKEMSecretMatters(t *testing.T) {
|
||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
|
||||
msg1, err := initM.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
msg2, _, err := respM.ProcessPacket(nil, msg1)
|
||||
require.NoError(t, err)
|
||||
|
||||
other, err := mlkem.GenerateKey1024()
|
||||
require.NoError(t, err)
|
||||
initM.kemKey = other
|
||||
|
||||
_, res, err := initM.ProcessPacket(nil, msg2)
|
||||
require.Error(t, err)
|
||||
assert.Nil(t, res)
|
||||
}
|
||||
|
||||
func TestKEMTamperedCiphertext(t *testing.T) {
|
||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
||||
respM := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
|
||||
msg1, err := initM.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
msg2, respR, err := respM.ProcessPacket(nil, msg1)
|
||||
require.NoError(t, err)
|
||||
|
||||
t.Run("truncated", func(t *testing.T) {
|
||||
_, res, err := initM.ProcessPacket(nil, msg2[:header.Len+mlkem.CiphertextSize1024-1])
|
||||
require.ErrorIs(t, err, ErrPacketTooShort)
|
||||
assert.Nil(t, res)
|
||||
assert.False(t, initM.Failed())
|
||||
})
|
||||
|
||||
t.Run("flipped ciphertext bit", func(t *testing.T) {
|
||||
bad := bytes.Clone(msg2)
|
||||
bad[header.Len+10] ^= 1
|
||||
_, res, err := initM.ProcessPacket(nil, bad)
|
||||
require.Error(t, err)
|
||||
assert.Nil(t, res)
|
||||
assert.False(t, initM.Failed(), "a forged ciphertext must not kill the handshake")
|
||||
})
|
||||
|
||||
t.Run("genuine response still completes", func(t *testing.T) {
|
||||
_, initR, err := initM.ProcessPacket(nil, msg2)
|
||||
require.NoError(t, err)
|
||||
require.NotNil(t, initR)
|
||||
requireKeysMatch(t, initR, respR)
|
||||
})
|
||||
}
|
||||
|
||||
// TestKEMBadMsg1 drives processPayload by hand. With the psk modifier msg1's
|
||||
// payload is encrypted under a key derived from the public ephemeral, so a
|
||||
// forged payload would need re-encrypting; the parsing rules are what matter.
|
||||
func TestKEMBadMsg1(t *testing.T) {
|
||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
||||
msg1Flags := subtypeInfos[header.HandshakeIXPSK2MLKEM1024].msgs[0]
|
||||
cert := f.initCS.creds[cert.Version2]
|
||||
payload := func(kemKey []byte) []byte {
|
||||
return MarshalPayload(nil, Payload{
|
||||
Cert: cert.Bytes,
|
||||
CertVersion: uint32(cert.Cert.Version()),
|
||||
InitiatorIndex: 1000,
|
||||
Time: 1,
|
||||
KEMKey: kemKey,
|
||||
})
|
||||
}
|
||||
dk, err := mlkem.GenerateKey1024()
|
||||
require.NoError(t, err)
|
||||
|
||||
t.Run("missing KEM key", func(t *testing.T) {
|
||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
err := m.processPayload(payload(nil), msg1Flags)
|
||||
require.ErrorIs(t, err, ErrUnexpectedContent)
|
||||
assert.True(t, m.Failed())
|
||||
})
|
||||
|
||||
t.Run("invalid KEM key", func(t *testing.T) {
|
||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
// Coefficients of 0xfff exceed the modulus, which ML-KEM must reject.
|
||||
bad := bytes.Repeat([]byte{0xff}, mlkem.EncapsulationKeySize1024)
|
||||
err := m.kemEncapsulate(bad)
|
||||
require.ErrorIs(t, err, ErrInvalidKEMKey)
|
||||
err = m.kemEncapsulate(bad[:100])
|
||||
require.ErrorIs(t, err, ErrInvalidKEMKey)
|
||||
})
|
||||
|
||||
t.Run("valid KEM key", func(t *testing.T) {
|
||||
m := newKEMMachine(t, f.respCS, f.v, false, 2000)
|
||||
require.NoError(t, m.kemEncapsulate(dk.EncapsulationKey().Bytes()))
|
||||
assert.Len(t, m.kemCiphertext, mlkem.CiphertextSize1024)
|
||||
})
|
||||
|
||||
t.Run("KEM key on the classical subtype", func(t *testing.T) {
|
||||
m := newTestMachine(t, f.respCS, f.v, false, 2000)
|
||||
classical := subtypeInfos[header.HandshakeIXPSK0].msgs[0]
|
||||
err := m.processPayload(payload(dk.EncapsulationKey().Bytes()), classical)
|
||||
require.ErrorIs(t, err, ErrUnexpectedContent)
|
||||
assert.True(t, m.Failed())
|
||||
})
|
||||
}
|
||||
|
||||
// TestKEMDistinctFromClassical makes sure the two subtypes cannot be mixed: a
|
||||
// classical responder cannot answer a KEM initiator.
|
||||
func TestKEMDistinctFromClassical(t *testing.T) {
|
||||
f := newKEMFixture(t, noise.CipherChaChaPoly)
|
||||
initM := newKEMMachine(t, f.initCS, f.v, true, 1000)
|
||||
respM := newTestMachine(t, f.respCS, f.v, false, 2000)
|
||||
|
||||
msg1, err := initM.Initiate(nil)
|
||||
require.NoError(t, err)
|
||||
_, _, err = respM.ProcessPacket(nil, msg1)
|
||||
require.ErrorIs(t, err, ErrSubtypeMismatch)
|
||||
}
|
||||
+54
-5
@@ -2,6 +2,8 @@ package handshake
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"crypto/mlkem"
|
||||
"errors"
|
||||
"fmt"
|
||||
"slices"
|
||||
"time"
|
||||
@@ -67,6 +69,9 @@ type Machine struct {
|
||||
remoteCertSet bool
|
||||
payloadSet bool
|
||||
failed bool
|
||||
|
||||
kemKey *mlkem.DecapsulationKey1024 // initiator's ephemeral ML-KEM key, until completion
|
||||
kemCiphertext []byte // responder's ciphertext to prefix its response with
|
||||
}
|
||||
|
||||
// NewMachine creates a handshake state machine. The subtype determines both
|
||||
@@ -91,7 +96,7 @@ func NewMachine(
|
||||
return nil, fmt.Errorf("%w: %v", ErrNoCredential, version)
|
||||
}
|
||||
|
||||
hs, err := cred.buildHandshakeState(initiator, info.pattern)
|
||||
hs, err := cred.buildHandshakeState(initiator, info.pattern, info.pskPlacement)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("build noise state: %w", err)
|
||||
}
|
||||
@@ -137,7 +142,8 @@ func (m *Machine) requireComplete() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// myMsgFlags returns the flags for the current outgoing message.
|
||||
// myMsgFlags returns the flags for the current outgoing message, which are
|
||||
// also the flags of the next incoming message before it is read.
|
||||
func (m *Machine) myMsgFlags() msgFlags {
|
||||
idx := m.hs.MessageIndex()
|
||||
if idx < len(m.msgs) {
|
||||
@@ -225,7 +231,18 @@ func (m *Machine) ProcessPacket(out, packet []byte) ([]byte, *Result, error) {
|
||||
// noise returns (cs1, cs2) where cs1 is the initiator->responder cipher.
|
||||
// For 3-message patterns where a responder finishes by reading the final
|
||||
// message, this ordering would be wrong; revisit when XX/pqIX lands.
|
||||
msg, eKey, dKey, err := m.hs.ReadMessage(nil, packet[header.Len:])
|
||||
noiseMsg := packet[header.Len:]
|
||||
if m.myMsgFlags().kemCiphertext {
|
||||
var err error
|
||||
// Installing a psk derived from a forged ciphertext is harmless: ReadMessage
|
||||
// then fails without advancing, and the next packet installs its own.
|
||||
noiseMsg, err = m.kemDecapsulate(noiseMsg)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
}
|
||||
|
||||
msg, eKey, dKey, err := m.hs.ReadMessage(nil, noiseMsg)
|
||||
if err != nil {
|
||||
// Noise ReadMessage failed. The noise library checkpoints and rolls back
|
||||
// on failure, so the Machine is still alive. The caller can retry with
|
||||
@@ -276,6 +293,8 @@ func (m *Machine) ProcessPacket(out, packet []byte) ([]byte, *Result, error) {
|
||||
}
|
||||
|
||||
func (m *Machine) completed(eKey, dKey *noise.CipherState) *Result {
|
||||
m.kemKey = nil
|
||||
m.kemCiphertext = nil
|
||||
m.result.EKey = eKey
|
||||
m.result.DKey = dKey
|
||||
m.result.MessageIndex = uint64(m.hs.MessageIndex())
|
||||
@@ -284,7 +303,7 @@ func (m *Machine) completed(eKey, dKey *noise.CipherState) *Result {
|
||||
|
||||
func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||
if len(msg) == 0 {
|
||||
if flags.expectsPayload || flags.expectsCert {
|
||||
if flags.expectsPayload || flags.expectsCert || flags.kemKey {
|
||||
m.failed = true
|
||||
return ErrMissingContent
|
||||
}
|
||||
@@ -310,6 +329,12 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||
return ErrUnexpectedContent
|
||||
}
|
||||
|
||||
hasKEMKey := len(payload.KEMKey) > 0
|
||||
if hasKEMKey != flags.kemKey {
|
||||
m.failed = true
|
||||
return ErrUnexpectedContent
|
||||
}
|
||||
|
||||
// Process payload
|
||||
if flags.expectsPayload {
|
||||
var remoteIndex uint32
|
||||
@@ -336,6 +361,13 @@ func (m *Machine) processPayload(msg []byte, flags msgFlags) error {
|
||||
}
|
||||
}
|
||||
|
||||
if flags.kemKey {
|
||||
if err := m.kemEncapsulate(payload.KEMKey); err != nil {
|
||||
m.failed = true
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -380,11 +412,21 @@ func (m *Machine) validateCert(payload Payload) error {
|
||||
}
|
||||
|
||||
func (m *Machine) marshalOutgoing(flags msgFlags) ([]byte, error) {
|
||||
if !flags.expectsPayload && !flags.expectsCert {
|
||||
if !flags.expectsPayload && !flags.expectsCert && !flags.kemKey {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
var p Payload
|
||||
if flags.kemKey {
|
||||
if m.kemKey == nil {
|
||||
dk, err := mlkem.GenerateKey1024()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("generate ML-KEM key: %w", err)
|
||||
}
|
||||
m.kemKey = dk
|
||||
}
|
||||
p.KEMKey = m.kemKey.EncapsulationKey().Bytes()
|
||||
}
|
||||
if flags.expectsPayload {
|
||||
if !m.indexAllocated {
|
||||
index, err := m.allocIndex()
|
||||
@@ -436,6 +478,13 @@ func (m *Machine) buildResponse(out []byte) ([]byte, *noise.CipherState, *noise.
|
||||
uint64(m.hs.MessageIndex()+1),
|
||||
)
|
||||
|
||||
if flags.kemCiphertext {
|
||||
if m.kemCiphertext == nil {
|
||||
return nil, nil, nil, errors.New("no ML-KEM ciphertext to send")
|
||||
}
|
||||
out = append(out, m.kemCiphertext...)
|
||||
}
|
||||
|
||||
// noise.WriteMessage appends the encrypted handshake message to out,
|
||||
// reusing capacity when present.
|
||||
//
|
||||
|
||||
+21
-2
@@ -11,13 +11,16 @@ import (
|
||||
type msgFlags struct {
|
||||
expectsPayload bool // message carries indexes and time
|
||||
expectsCert bool // message carries the certificate
|
||||
kemKey bool // payload carries an ML-KEM encapsulation key
|
||||
kemCiphertext bool // message is prefixed with the ML-KEM ciphertext for the peer's key
|
||||
}
|
||||
|
||||
// subtypeInfo bundles the noise pattern with the per-message flags for a
|
||||
// given handshake subtype.
|
||||
type subtypeInfo struct {
|
||||
pattern noise.HandshakePattern
|
||||
msgs []msgFlags
|
||||
pattern noise.HandshakePattern
|
||||
pskPlacement int // noise psk modifier position, 0 means no psk token
|
||||
msgs []msgFlags
|
||||
}
|
||||
|
||||
// subtypeInfos defines the noise pattern and message content layout for each
|
||||
@@ -32,6 +35,22 @@ var subtypeInfos = map[header.MessageSubType]subtypeInfo{
|
||||
},
|
||||
},
|
||||
|
||||
// IX with an ephemeral ML-KEM-1024 exchange:
|
||||
// msg1 (I->R): payload + cert + encapsulation key
|
||||
// msg2 (R->I): ciphertext || noise(payload + cert)
|
||||
// The responder encapsulates after reading msg1 and mixes the shared secret in
|
||||
// through the psk2 token at the end of msg2. The ciphertext travels outside the
|
||||
// noise message because the initiator needs the secret before it can process
|
||||
// that token.
|
||||
header.HandshakeIXPSK2MLKEM1024: {
|
||||
pattern: noise.HandshakeIX,
|
||||
pskPlacement: 2,
|
||||
msgs: []msgFlags{
|
||||
{expectsPayload: true, expectsCert: true, kemKey: true},
|
||||
{expectsPayload: true, expectsCert: true, kemCiphertext: true},
|
||||
},
|
||||
},
|
||||
|
||||
// XX: 3 messages
|
||||
// msg1 (I->R): payload only
|
||||
// msg2 (R->I): payload + cert
|
||||
|
||||
@@ -20,6 +20,7 @@ type Payload struct {
|
||||
ResponderIndex uint32
|
||||
Time uint64
|
||||
CertVersion uint32
|
||||
KEMKey []byte // ML-KEM encapsulation key, only in subtypes that carry one
|
||||
}
|
||||
|
||||
// Proto field numbers for NebulaHandshakeDetails
|
||||
@@ -29,6 +30,7 @@ const (
|
||||
fieldResponderIndex = 3 // uint32
|
||||
fieldTime = 5 // uint64
|
||||
fieldCertVersion = 8 // uint32
|
||||
fieldKEMKey = 9 // bytes
|
||||
)
|
||||
|
||||
// MarshalPayload encodes a handshake payload in protobuf wire format compatible
|
||||
@@ -57,6 +59,10 @@ func MarshalPayload(out []byte, p Payload) []byte {
|
||||
details = protowire.AppendTag(details, fieldCertVersion, protowire.VarintType)
|
||||
details = protowire.AppendVarint(details, uint64(p.CertVersion))
|
||||
}
|
||||
if len(p.KEMKey) > 0 {
|
||||
details = protowire.AppendTag(details, fieldKEMKey, protowire.BytesType)
|
||||
details = protowire.AppendBytes(details, p.KEMKey)
|
||||
}
|
||||
|
||||
out = protowire.AppendTag(out, 1, protowire.BytesType)
|
||||
out = protowire.AppendBytes(out, details)
|
||||
@@ -161,6 +167,16 @@ func unmarshalPayloadDetails(p *Payload, b []byte) error {
|
||||
}
|
||||
p.CertVersion = uint32(v)
|
||||
b = b[n:]
|
||||
case fieldKEMKey:
|
||||
if typ != protowire.BytesType {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
v, n := protowire.ConsumeBytes(b)
|
||||
if n < 0 {
|
||||
return errInvalidHandshakeDetails
|
||||
}
|
||||
p.KEMKey = append([]byte(nil), v...)
|
||||
b = b[n:]
|
||||
default:
|
||||
n := protowire.ConsumeFieldValue(num, typ, b)
|
||||
if n < 0 {
|
||||
|
||||
+160
-58
@@ -10,12 +10,15 @@ import (
|
||||
"net/netip"
|
||||
"slices"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/cert"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/handshake/fragment"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/ratelimit"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
)
|
||||
|
||||
@@ -49,12 +52,14 @@ type HandshakeConfig struct {
|
||||
tryInterval time.Duration
|
||||
retries int64
|
||||
triggerBuffer int
|
||||
pq pqHandshakeConfig
|
||||
|
||||
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
|
||||
@@ -73,6 +78,18 @@ type HandshakeManager struct {
|
||||
|
||||
// can be used to trigger outbound handshake for the given vpnIp
|
||||
trigger chan netip.Addr
|
||||
|
||||
// pq holds the post-quantum settings, which change on reload.
|
||||
pq atomic.Pointer[pqHandshakeConfig]
|
||||
// pqTable reassembles post-quantum msg1s from senders that have not authenticated yet.
|
||||
pqTable *fragment.Table[pqFragKey, pqFragSource]
|
||||
// pqPeers holds vpn addresses that completed a post-quantum handshake, for sticky mode.
|
||||
pqPeers sync.Map
|
||||
// pqAnswered recognises repeats of post-quantum msg1s already answered.
|
||||
pqAnswered *pqAnswered
|
||||
// pqCookies and pqCookieLimiter serve cookies while pqTable is under load.
|
||||
pqCookies *pqCookies
|
||||
pqCookieLimiter *ratelimit.Limiter
|
||||
}
|
||||
|
||||
type HandshakeHostInfo struct {
|
||||
@@ -88,6 +105,8 @@ type HandshakeHostInfo struct {
|
||||
|
||||
hostinfo *HostInfo
|
||||
machine *handshake.Machine // The handshake state machine, set during stage 0 (initiator) or beginHandshake (responder multi-message)
|
||||
pq *pqAttempt // The initiator's post-quantum attempt, pending alongside the classical one
|
||||
lastPQ bool // Whether the latest attempt was post-quantum
|
||||
}
|
||||
|
||||
func (hh *HandshakeHostInfo) cachePacket(l *slog.Logger, t header.MessageType, st header.MessageSubType, packet []byte, f packetCallback, m *cachedPacketMetrics) {
|
||||
@@ -116,7 +135,7 @@ 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{
|
||||
hm := &HandshakeManager{
|
||||
vpnIps: map[netip.Addr]*HandshakeHostInfo{},
|
||||
indexes: map[uint32]*HandshakeHostInfo{},
|
||||
mainHostMap: mainHostMap,
|
||||
@@ -129,7 +148,16 @@ func NewHandshakeManager(l *slog.Logger, mainHostMap *HostMap, lightHouse *Light
|
||||
metricInitiated: metrics.GetOrRegisterCounter("handshake_manager.initiated", nil),
|
||||
metricTimedOut: metrics.GetOrRegisterCounter("handshake_manager.timed_out", nil),
|
||||
l: l,
|
||||
pqTable: fragment.NewTable[pqFragKey, pqFragSource](pqTableConfig),
|
||||
pqAnswered: newPQAnswered(hsTimeout(config.retries, config.tryInterval)),
|
||||
}
|
||||
pq := config.pq
|
||||
hm.pq.Store(&pq)
|
||||
hm.pqCookies = newPQCookies(time.Now())
|
||||
// Cookie replies are tiny, but a flood of spoofed fragments must not turn
|
||||
// into a flood of replies.
|
||||
hm.pqCookieLimiter, _ = ratelimit.New(256, time.Millisecond)
|
||||
return hm
|
||||
}
|
||||
|
||||
func (hm *HandshakeManager) Run(ctx context.Context) {
|
||||
@@ -144,6 +172,8 @@ func (hm *HandshakeManager) Run(ctx context.Context) {
|
||||
hm.handleOutbound(vpnIP, true)
|
||||
case now := <-clockSource.C:
|
||||
hm.NextOutboundHandshakeTimerTick(now)
|
||||
hm.pqTable.Expire(now)
|
||||
hm.pqAnswered.expire(now)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -153,7 +183,7 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
||||
// don't yet support) are dropped here rather than silently routed through
|
||||
// the IX path. Add a case when introducing a new pattern.
|
||||
switch h.Subtype {
|
||||
case header.HandshakeIXPSK0:
|
||||
case header.HandshakeIXPSK0, pqSubtype:
|
||||
// supported
|
||||
default:
|
||||
hm.l.Debug("dropping handshake with unsupported subtype",
|
||||
@@ -169,6 +199,11 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
||||
}
|
||||
}
|
||||
|
||||
if header.IsFragmented(h.Subtype) {
|
||||
hm.handleFragment(via, packet, h)
|
||||
return
|
||||
}
|
||||
|
||||
// First message of a new handshake. The wire format requires RemoteIndex
|
||||
// to be zero here (the initiator has no responder index to fill in yet),
|
||||
// and generateIndex never allocates 0, so any non-zero RemoteIndex on a
|
||||
@@ -180,7 +215,11 @@ func (hm *HandshakeManager) HandleIncoming(via ViaSender, packet []byte, h *head
|
||||
"from", via, "remoteIndex", h.RemoteIndex)
|
||||
return
|
||||
}
|
||||
hm.beginHandshake(via, packet, h)
|
||||
if hm.pqConfig().require {
|
||||
hm.l.Debug("dropping classical handshake, post-quantum handshakes are required", "from", via)
|
||||
return
|
||||
}
|
||||
hm.beginHandshake(via, packet, h, 0)
|
||||
return
|
||||
}
|
||||
|
||||
@@ -229,6 +268,9 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
"style": header.SubTypeName(header.Handshake, hh.machine.Subtype()),
|
||||
})
|
||||
}
|
||||
if hh.pq != nil {
|
||||
fields = append(fields, "pqInitiatorIndex", hh.pq.index)
|
||||
}
|
||||
hh.hostinfo.logger(hm.l).Info("Handshake timed out", fields...)
|
||||
hm.metricTimedOut.Inc(1)
|
||||
hm.DeleteHostInfo(hostinfo)
|
||||
@@ -238,33 +280,45 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
// Increment the counter to increase our delay, linear backoff
|
||||
hh.counter++
|
||||
|
||||
// Check if we have a handshake packet to transmit yet
|
||||
if !hh.ready {
|
||||
if !hm.buildStage0Packet(hh) {
|
||||
// Pick this attempt's style and make sure its first message exists. A PQ
|
||||
// attempt sends msg1 as fragments: now goes out immediately, later after the
|
||||
// repair delay, and every attempt offers fresh repair symbols.
|
||||
var now, later [][]byte
|
||||
var machine *handshake.Machine
|
||||
hh.lastPQ = hm.usePQ(hh, vpnIp, lighthouseTriggered)
|
||||
if hh.lastPQ {
|
||||
if hh.pq == nil && !hm.buildPQAttempt(hh) {
|
||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
||||
return
|
||||
}
|
||||
var err error
|
||||
now, later, err = hh.pq.sender.Attempt(fragment.DefaultRepair(hh.pq.sender.Layout().K))
|
||||
if err != nil {
|
||||
hostinfo.logger(hm.l).Error("Failed to fragment handshake", "error", err)
|
||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
||||
return
|
||||
}
|
||||
machine = hh.pq.machine
|
||||
} else {
|
||||
if !hh.ready {
|
||||
if !hm.buildStage0Packet(hh) {
|
||||
hm.OutboundHandshakeTimer.Add(vpnIp, hm.config.tryInterval*time.Duration(hh.counter))
|
||||
return
|
||||
}
|
||||
}
|
||||
// TODO: this hardcodes "always retransmit stage 0", which is correct for
|
||||
// IX (the initiator only ever sends one packet, msg1) but wrong the
|
||||
// moment a 3+ message pattern lands. The retry loop should resend the
|
||||
// most recent outgoing message, not always stage 0. That implies
|
||||
// HandshakeHostInfo tracking a single "currentOutbound" packet (bytes +
|
||||
// header metadata) that gets replaced as the handshake progresses,
|
||||
// instead of indexing into HandshakePacket.
|
||||
now = [][]byte{hostinfo.HandshakePacket[handshakePacketStage0]}
|
||||
machine = hh.machine
|
||||
}
|
||||
|
||||
// TODO: this hardcodes "always retransmit stage 0", which is correct for
|
||||
// IX (the initiator only ever sends one packet, msg1) but wrong the
|
||||
// moment a 3+ message pattern lands. The retry loop should resend the
|
||||
// most recent outgoing message, not always stage 0. That implies
|
||||
// HandshakeHostInfo tracking a single "currentOutbound" packet (bytes +
|
||||
// header metadata) that gets replaced as the handshake progresses,
|
||||
// instead of indexing into HandshakePacket.
|
||||
stage0 := hostinfo.HandshakePacket[handshakePacketStage0]
|
||||
hsFields := m{
|
||||
"stage": uint64(hh.machine.MessageIndex()),
|
||||
"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})
|
||||
"stage": uint64(machine.MessageIndex()),
|
||||
"style": header.SubTypeName(header.Handshake, machine.Subtype()),
|
||||
}
|
||||
|
||||
remotes := hostinfo.remotes.CopyAddrs(hm.mainHostMap.GetPreferredRanges())
|
||||
@@ -292,8 +346,10 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
// Send the handshake to all known ips, stage 2 takes care of assigning the hostinfo.remote based on the first to reply
|
||||
var sentTo []netip.AddrPort
|
||||
hostinfo.remotes.ForEach(hm.mainHostMap.GetPreferredRanges(), func(addr netip.AddrPort, _ bool) {
|
||||
hm.messageMetrics.Tx(header.Handshake, hh.machine.Subtype(), 1)
|
||||
err := hm.outside.WriteTo(stage0, addr)
|
||||
hm.messageMetrics.Tx(header.Handshake, machine.Subtype(), int64(len(now)+len(later)))
|
||||
err := hm.sendFragmented(now, later, func(p []byte) error {
|
||||
return hm.outside.WriteTo(p, addr)
|
||||
})
|
||||
if err != nil {
|
||||
// These repeat every attempt, so match the success log below and only shout when the remotes changed
|
||||
level := slog.LevelDebug
|
||||
@@ -329,7 +385,7 @@ func (hm *HandshakeManager) handleOutbound(vpnIp netip.Addr, lighthouseTriggered
|
||||
)
|
||||
}
|
||||
|
||||
hm.f.relayManager.StartRelays(hm.f, vpnIp, hh, stage0)
|
||||
hm.f.relayManager.StartRelays(hm.f, vpnIp, hh, now, later)
|
||||
|
||||
// If a lighthouse triggered this attempt then we are still in the timer wheel and do not need to re-add
|
||||
if !lighthouseTriggered {
|
||||
@@ -371,6 +427,9 @@ 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{},
|
||||
@@ -536,6 +595,10 @@ func (hm *HandshakeManager) DeleteHostInfo(hostinfo *HostInfo) {
|
||||
func (hm *HandshakeManager) unlockedDeleteHostInfo(hostinfo *HostInfo) {
|
||||
for _, addr := range hostinfo.vpnAddrs {
|
||||
if cur, ok := hm.vpnIps[addr]; ok && cur.hostinfo == hostinfo {
|
||||
// A PQ attempt holds its own index alongside the hostinfo's.
|
||||
if idx := cur.pqIndex(); idx != 0 && hm.indexes[idx] == cur {
|
||||
delete(hm.indexes, idx)
|
||||
}
|
||||
delete(hm.vpnIps, addr)
|
||||
}
|
||||
}
|
||||
@@ -646,9 +709,8 @@ func hsTimeout(tries int64, interval time.Duration) time.Duration {
|
||||
return time.Duration(tries / 2 * ((2 * int64(interval)) + (tries-1)*int64(interval)))
|
||||
}
|
||||
|
||||
// buildStage0Packet creates the initial handshake packet for the initiator.
|
||||
func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
cs := hm.f.pki.getCertState()
|
||||
// initiatingVersion picks the certificate version to initiate a handshake with.
|
||||
func (hm *HandshakeManager) initiatingVersion(hh *HandshakeHostInfo, cs *CertState) cert.Version {
|
||||
v := cs.DefaultVersion()
|
||||
if hh.initiatingVersionOverride != cert.VersionPre1 {
|
||||
v = hh.initiatingVersionOverride
|
||||
@@ -660,6 +722,13 @@ func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
}
|
||||
}
|
||||
}
|
||||
return v
|
||||
}
|
||||
|
||||
// buildStage0Packet creates the initial handshake packet for the initiator.
|
||||
func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
cs := hm.f.pki.getCertState()
|
||||
v := hm.initiatingVersion(hh, cs)
|
||||
|
||||
cred := cs.GetCredential(v)
|
||||
if cred == nil {
|
||||
@@ -698,7 +767,10 @@ func (hm *HandshakeManager) buildStage0Packet(hh *HandshakeHostInfo) bool {
|
||||
// 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.
|
||||
func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *header.H) {
|
||||
//
|
||||
// received is the number of bytes a fragmented msg1 arrived in, which bounds the
|
||||
// response sent back before the address is validated; 0 for unfragmented ones.
|
||||
func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *header.H, received int) {
|
||||
f := hm.f
|
||||
cs := f.pki.getCertState()
|
||||
|
||||
@@ -712,7 +784,7 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
machine, err := handshake.NewMachine(
|
||||
v, cs.GetCredential,
|
||||
hm.certVerifier(), func() (uint32, error) { return generateIndex(f.l) },
|
||||
false, header.HandshakeIXPSK0,
|
||||
false, h.Subtype,
|
||||
)
|
||||
if err != nil {
|
||||
f.l.Error("Failed to create handshake machine", "from", via, "error", err)
|
||||
@@ -802,11 +874,15 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
|
||||
existing, err := hm.CheckAndComplete(hostinfo, handshakePacketStage0, f)
|
||||
if err != nil {
|
||||
hm.handleCheckAndCompleteError(err, existing, hostinfo, via)
|
||||
hm.handleCheckAndCompleteError(err, existing, hostinfo, via, machine.Subtype(), received)
|
||||
return
|
||||
}
|
||||
|
||||
hm.sendHandshakeResponse(via, response, hostinfo, false)
|
||||
hm.sendHandshakeResponse(via, response, hostinfo, false, received)
|
||||
if header.IsFragmented(machine.Subtype()) {
|
||||
hm.pqAnswered.add(packet[header.Len:], hostinfo, time.Now())
|
||||
}
|
||||
hm.notePQPeer(machine.Subtype(), vpnAddrs)
|
||||
hostinfo.remotes.RefreshFromHandshake(vpnAddrs)
|
||||
|
||||
// Don't wait for UpdateWorker
|
||||
@@ -817,23 +893,32 @@ func (hm *HandshakeManager) beginHandshake(via ViaSender, packet []byte, h *head
|
||||
|
||||
// continueHandshake feeds an incoming packet to an existing pending handshake Machine.
|
||||
func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostInfo, packet []byte) {
|
||||
f := hm.f
|
||||
|
||||
hh.Lock()
|
||||
defer hh.Unlock()
|
||||
|
||||
// Re-verify hh is still tracked. Between queryIndex returning and us taking
|
||||
// hh.Lock, handleOutbound may have timed out and deleted it. Once we hold
|
||||
// hh.Lock no other deleter can race our index: handleOutbound also takes
|
||||
// hh.Lock first, and handleRecvError targets a main-hostmap entry with a
|
||||
// different localIndexId.
|
||||
hm.RLock()
|
||||
cur, ok := hm.indexes[hh.hostinfo.localIndexId]
|
||||
hm.RUnlock()
|
||||
if !ok || cur != hh {
|
||||
if !hm.stillPending(hh, hh.hostinfo.localIndexId) {
|
||||
return
|
||||
}
|
||||
hm.processResponse(via, hh, hh.machine, packet)
|
||||
}
|
||||
|
||||
// stillPending re-verifies hh is still tracked under index. Between queryIndex
|
||||
// returning and the caller taking hh.Lock, handleOutbound may have timed out and
|
||||
// deleted it. Once hh.Lock is held no other deleter can race the index:
|
||||
// handleOutbound also takes hh.Lock first, and handleRecvError targets a
|
||||
// main-hostmap entry with a different localIndexId. The caller must hold hh.Lock.
|
||||
func (hm *HandshakeManager) stillPending(hh *HandshakeHostInfo, index uint32) bool {
|
||||
hm.RLock()
|
||||
defer hm.RUnlock()
|
||||
cur, ok := hm.indexes[index]
|
||||
return ok && cur == hh
|
||||
}
|
||||
|
||||
// processResponse runs a responder's message through one of the initiator's
|
||||
// pending attempts and completes the tunnel when the handshake finishes. The
|
||||
// caller must hold hh.Lock.
|
||||
func (hm *HandshakeManager) processResponse(via ViaSender, hh *HandshakeHostInfo, machine *handshake.Machine, packet []byte) {
|
||||
f := hm.f
|
||||
hostinfo := hh.hostinfo
|
||||
if !via.IsRelayed {
|
||||
if !f.lightHouse.GetRemoteAllowList().AllowAll(hostinfo.vpnAddrs, via.UdpAddr.Addr()) {
|
||||
@@ -843,7 +928,6 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
}
|
||||
}
|
||||
|
||||
machine := hh.machine
|
||||
if machine == nil {
|
||||
f.l.Error("No handshake machine available for continuation",
|
||||
"vpnAddrs", hostinfo.vpnAddrs, "from", via)
|
||||
@@ -866,7 +950,7 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
}
|
||||
|
||||
if response != nil {
|
||||
hm.sendHandshakeResponse(via, response, hostinfo, false)
|
||||
hm.sendHandshakeResponse(via, response, hostinfo, false, 0)
|
||||
}
|
||||
|
||||
if result == nil {
|
||||
@@ -946,13 +1030,14 @@ 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
|
||||
}
|
||||
|
||||
@@ -978,7 +1063,10 @@ func (hm *HandshakeManager) continueHandshake(via ViaSender, hh *HandshakeHostIn
|
||||
hostinfo.vpnAddrs = vpnAddrs
|
||||
hostinfo.buildNetworks(f.myVpnNetworksTable, remoteCert.Certificate)
|
||||
|
||||
// The classical and PQ attempts each hold an index; keep the one that won.
|
||||
hm.settleIndex(hh, result.LocalIndex)
|
||||
hm.Complete(hostinfo, f)
|
||||
hm.notePQPeer(machine.Subtype(), vpnAddrs)
|
||||
|
||||
if len(hh.packetStore) > 0 {
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
@@ -1057,20 +1145,23 @@ func (hm *HandshakeManager) validatePeerCert(via ViaSender, remoteCert *cert.Cac
|
||||
// cached is true when msg is a stored response being retransmitted because
|
||||
// the peer's stage-1 retransmit landed (the ErrAlreadySeen path); false on a
|
||||
// fresh response.
|
||||
func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool) {
|
||||
//
|
||||
// received is the number of bytes a fragmented msg1 arrived in; it bounds what a
|
||||
// fragmented response may send back. It is ignored for unfragmented subtypes.
|
||||
func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool, received int) {
|
||||
if msg == nil {
|
||||
return
|
||||
}
|
||||
|
||||
f := hm.f
|
||||
f.messageMetrics.Tx(header.Handshake, header.MessageSubType(msg[1]), 1)
|
||||
subtype := header.MessageSubType(msg[1])
|
||||
|
||||
// Common log fields. peerCert may be nil during intermediate
|
||||
// multi-message flows (handshake hasn't completed yet); skip the cert
|
||||
// block if so.
|
||||
logFields := []any{
|
||||
"vpnAddrs", hostinfo.vpnAddrs,
|
||||
"handshake", m{"stage": uint64(2), "style": header.SubTypeName(header.Handshake, header.HandshakeIXPSK0)},
|
||||
"handshake", m{"stage": uint64(2), "style": header.SubTypeName(header.Handshake, subtype)},
|
||||
"cached", cached,
|
||||
"initiatorIndex", hostinfo.remoteIndexId,
|
||||
"responderIndex", hostinfo.localIndexId,
|
||||
@@ -1084,6 +1175,17 @@ func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hos
|
||||
)
|
||||
}
|
||||
|
||||
if header.IsFragmented(subtype) {
|
||||
fields := append(logFields, "from", via)
|
||||
if err := hm.sendFragmentedResponse(via, msg, hostinfo, cached, received); err != nil {
|
||||
f.l.Debug("Did not send handshake message", append(fields, "error", err)...)
|
||||
} else {
|
||||
f.l.Info("Handshake message sent", fields...)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
f.messageMetrics.Tx(header.Handshake, subtype, 1)
|
||||
if !via.IsRelayed {
|
||||
fields := append(logFields, "from", via)
|
||||
err := f.outside.WriteTo(msg, via.UdpAddr)
|
||||
@@ -1110,10 +1212,10 @@ func (hm *HandshakeManager) sendHandshakeResponse(via ViaSender, msg []byte, hos
|
||||
// This only fires from the responder-side beginHandshake path, after the
|
||||
// peer cert has been validated and ConnectionState populated, so peerCert
|
||||
// is always non-nil for the cases that log it.
|
||||
func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hostinfo *HostInfo, via ViaSender) {
|
||||
func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hostinfo *HostInfo, via ViaSender, subtype header.MessageSubType, received int) {
|
||||
f := hm.f
|
||||
peerCert := hostinfo.ConnectionState.peerCert
|
||||
hsFields := m{"stage": uint64(1), "style": header.SubTypeName(header.Handshake, header.HandshakeIXPSK0)}
|
||||
hsFields := m{"stage": uint64(1), "style": header.SubTypeName(header.Handshake, subtype)}
|
||||
|
||||
switch err {
|
||||
case ErrAlreadySeen:
|
||||
@@ -1124,7 +1226,7 @@ func (hm *HandshakeManager) handleCheckAndCompleteError(err error, existing, hos
|
||||
// ephemeral keys; a freshly-built one would have different keys and break
|
||||
// the tunnel even though both sides "completed" the handshake.
|
||||
if msg := existing.HandshakePacket[handshakePacketStage2]; msg != nil {
|
||||
hm.sendHandshakeResponse(via, msg, existing, true)
|
||||
hm.sendHandshakeResponse(via, msg, existing, true, received)
|
||||
}
|
||||
|
||||
case ErrExistingHostInfo:
|
||||
|
||||
@@ -0,0 +1,699 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/hmac"
|
||||
"crypto/rand"
|
||||
"crypto/sha256"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/handshake"
|
||||
"github.com/slackhq/nebula/handshake/fragment"
|
||||
"github.com/slackhq/nebula/header"
|
||||
)
|
||||
|
||||
const (
|
||||
// pqSubtype is the post-quantum handshake this node speaks.
|
||||
pqSubtype = header.HandshakeIXPSK2MLKEM1024
|
||||
|
||||
// DefaultPQRepairDelay is how long repair fragments trail the data fragments.
|
||||
DefaultPQRepairDelay = 10 * time.Millisecond
|
||||
|
||||
// pqAmplification bounds what a responder sends in reply to an unvalidated
|
||||
// address, as a multiple of what it received from it.
|
||||
pqAmplification = 3
|
||||
)
|
||||
|
||||
// pqTableConfig bounds the responder's reassembly of msg1 fragments from senders
|
||||
// that have not authenticated yet.
|
||||
var pqTableConfig = fragment.TableConfig{
|
||||
MaxBytes: 4 << 20,
|
||||
MaxEntries: 1024,
|
||||
MaxPerSource: 4,
|
||||
MaxMsgLen: 16384,
|
||||
TTL: 3 * time.Second,
|
||||
}
|
||||
|
||||
type pqHandshakeConfig struct {
|
||||
initiate bool // start PQ handshakes
|
||||
accept bool // answer PQ handshakes
|
||||
require bool // only PQ handshakes, in either direction
|
||||
sticky bool // never fall back to classical for a peer that completed PQ
|
||||
repairDelay time.Duration // delay between data and repair fragments
|
||||
}
|
||||
|
||||
func pqHandshakeConfigFrom(c *config.C) pqHandshakeConfig {
|
||||
cfg := pqHandshakeConfig{
|
||||
initiate: c.GetBool("handshakes.pq.initiate", false),
|
||||
accept: c.GetBool("handshakes.pq.accept", false),
|
||||
require: c.GetBool("handshakes.pq.require", false),
|
||||
sticky: c.GetBool("handshakes.pq.sticky", false),
|
||||
repairDelay: c.GetDuration("handshakes.pq.repair_delay", DefaultPQRepairDelay),
|
||||
}
|
||||
if cfg.require {
|
||||
cfg.initiate = true
|
||||
cfg.accept = true
|
||||
}
|
||||
return cfg
|
||||
}
|
||||
|
||||
// pqConfig returns the post-quantum settings in effect.
|
||||
func (hm *HandshakeManager) pqConfig() *pqHandshakeConfig {
|
||||
return hm.pq.Load()
|
||||
}
|
||||
|
||||
// reloadPQ applies changed post-quantum settings. Handshakes already in flight
|
||||
// keep going; the new settings apply to the next attempt and packet.
|
||||
func (hm *HandshakeManager) reloadPQ(c *config.C) {
|
||||
if !c.HasChanged("handshakes.pq") {
|
||||
return
|
||||
}
|
||||
old := hm.pqConfig()
|
||||
cfg := pqHandshakeConfigFrom(c)
|
||||
hm.pq.Store(&cfg)
|
||||
hm.l.Info("Post-quantum handshake settings changed",
|
||||
"initiate", cfg.initiate, "oldInitiate", old.initiate,
|
||||
"accept", cfg.accept, "oldAccept", old.accept,
|
||||
"require", cfg.require, "oldRequire", old.require,
|
||||
"sticky", cfg.sticky, "oldSticky", old.sticky,
|
||||
"repairDelay", cfg.repairDelay, "oldRepairDelay", old.repairDelay,
|
||||
)
|
||||
}
|
||||
|
||||
// pqAttempt is the initiator's post-quantum attempt for a pending handshake. It
|
||||
// lives alongside the classical attempt in HandshakeHostInfo and has its own
|
||||
// local index, so whichever answer arrives first wins.
|
||||
type pqAttempt struct {
|
||||
machine *handshake.Machine
|
||||
index uint32
|
||||
sender *fragment.Sender
|
||||
msg2 *fragment.Assembly
|
||||
cookieResendAt time.Time // last resend prompted by a cookie reply
|
||||
heard bool // a msg2 fragment or cookie reply arrived, so the peer speaks PQ
|
||||
}
|
||||
|
||||
// pqFragKey identifies one msg1 being reassembled.
|
||||
type pqFragKey struct {
|
||||
addr netip.AddrPort
|
||||
relay uint32
|
||||
fragID uint32
|
||||
}
|
||||
|
||||
// pqFragSource groups msg1 reassemblies for the per-source quota: an IPv4 /32,
|
||||
// an IPv6 /64, or one relay channel.
|
||||
type pqFragSource struct {
|
||||
prefix netip.Prefix
|
||||
relay uint32
|
||||
}
|
||||
|
||||
func pqFragKeyFor(via ViaSender, fragID uint32) (pqFragKey, pqFragSource) {
|
||||
if via.IsRelayed {
|
||||
return pqFragKey{relay: via.relay.LocalIndex, fragID: fragID},
|
||||
pqFragSource{relay: via.relay.LocalIndex}
|
||||
}
|
||||
addr := via.UdpAddr.Addr().Unmap()
|
||||
bits := 64
|
||||
if addr.Is4() {
|
||||
bits = 32
|
||||
}
|
||||
prefix, _ := addr.Prefix(bits)
|
||||
return pqFragKey{addr: via.UdpAddr, fragID: fragID}, pqFragSource{prefix: prefix}
|
||||
}
|
||||
|
||||
// reassembled rebuilds the packet the handshake Machine expects from the header
|
||||
// of a fragment and the decoded message.
|
||||
func reassembled(h *header.H, msg []byte) []byte {
|
||||
p := make([]byte, header.Len, header.Len+len(msg))
|
||||
header.Encode(p, header.Version, header.Handshake, h.Subtype, h.RemoteIndex, h.MessageCounter)
|
||||
return append(p, msg...)
|
||||
}
|
||||
|
||||
// usePQ decides whether this outbound attempt is post-quantum. A peer that does
|
||||
// not speak PQ silently drops it, so timer retries alternate between PQ and
|
||||
// classical, starting with PQ. An attempt triggered early by a lighthouse reply
|
||||
// is sending to addresses nothing has been sent to yet, and a new path gets the
|
||||
// PQ attempt first. With require, or for a peer that completed a PQ handshake
|
||||
// when sticky is on, every attempt is PQ. Once anything has come back for the PQ
|
||||
// attempt the peer evidently speaks PQ, and a classical attempt would only race
|
||||
// it, so classical stops getting turns.
|
||||
func (hm *HandshakeManager) usePQ(hh *HandshakeHostInfo, vpnIp netip.Addr, triggered bool) bool {
|
||||
cfg := hm.pqConfig()
|
||||
switch {
|
||||
case !cfg.initiate:
|
||||
return false
|
||||
case cfg.require:
|
||||
return true
|
||||
case hh.pq != nil && hh.pq.heard:
|
||||
return true
|
||||
case cfg.sticky:
|
||||
if _, ok := hm.pqPeers.Load(vpnIp); ok {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return hh.counter <= 1 || triggered || !hh.lastPQ
|
||||
}
|
||||
|
||||
// relayEstablished pushes the pending handshake with target through a relay that
|
||||
// just came up, rather than leaving it for the next retry. Nothing has gone over
|
||||
// the relay yet, so like any new path it gets the PQ attempt first, which then
|
||||
// counts as the PQ turn: the next retry is classical, as if it had been sent on
|
||||
// schedule. Without this, relays coming up while the first attempt is in flight
|
||||
// handed every relayed handshake to the classical retry.
|
||||
func (hm *HandshakeManager) relayEstablished(target netip.Addr, relayHI *HostInfo, relay *Relay) {
|
||||
hh := hm.queryVpnIp(target)
|
||||
if hh == nil {
|
||||
return
|
||||
}
|
||||
hh.Lock()
|
||||
defer hh.Unlock()
|
||||
if hm.queryVpnIp(target) != hh {
|
||||
return
|
||||
}
|
||||
|
||||
var now, later [][]byte
|
||||
switch {
|
||||
case hh.pq != nil:
|
||||
var err error
|
||||
now, later, err = hh.pq.sender.Attempt(fragment.DefaultRepair(hh.pq.sender.Layout().K))
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
hh.lastPQ = true
|
||||
case hh.ready:
|
||||
now = [][]byte{hh.hostinfo.HandshakePacket[handshakePacketStage0]}
|
||||
default:
|
||||
return
|
||||
}
|
||||
|
||||
f := hm.f
|
||||
hh.hostinfo.logger(hm.l).Info("Send handshake via new relay", "relay", relayHI.vpnAddrs[0])
|
||||
_ = hm.sendFragmented(now, later, func(p []byte) error {
|
||||
f.SendVia(relayHI, relay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
||||
return nil
|
||||
})
|
||||
}
|
||||
|
||||
// buildPQAttempt creates the initiator's PQ Machine and msg1 sender.
|
||||
func (hm *HandshakeManager) buildPQAttempt(hh *HandshakeHostInfo) bool {
|
||||
cs := hm.f.pki.getCertState()
|
||||
v := hm.initiatingVersion(hh, cs)
|
||||
if cs.GetCredential(v) == nil {
|
||||
hm.f.l.Error("Unable to handshake with host because no certificate is available",
|
||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "certVersion", v)
|
||||
return false
|
||||
}
|
||||
|
||||
pq := &pqAttempt{}
|
||||
machine, err := handshake.NewMachine(
|
||||
v, cs.GetCredential,
|
||||
hm.certVerifier(), func() (uint32, error) { return hm.allocatePQIndex(hh, pq) },
|
||||
true, pqSubtype,
|
||||
)
|
||||
if err != nil {
|
||||
hm.f.l.Error("Failed to create handshake machine",
|
||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
||||
return false
|
||||
}
|
||||
|
||||
msg, err := machine.Initiate(nil)
|
||||
if err != nil {
|
||||
hm.f.l.Error("Failed to initiate handshake",
|
||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
||||
hm.releasePQIndex(hh, pq)
|
||||
return false
|
||||
}
|
||||
|
||||
sender, err := fragment.NewSender(msg[header.Len:], pqSubtype, 0, 1, pq.index)
|
||||
if err != nil {
|
||||
hm.f.l.Error("Failed to fragment handshake",
|
||||
"vpnAddrs", hh.hostinfo.vpnAddrs, "error", err)
|
||||
hm.releasePQIndex(hh, pq)
|
||||
return false
|
||||
}
|
||||
|
||||
pq.machine = machine
|
||||
pq.sender = sender
|
||||
hh.pq = pq
|
||||
return true
|
||||
}
|
||||
|
||||
// allocatePQIndex registers a local index for the PQ attempt. Unlike
|
||||
// allocateIndex it leaves hostinfo.localIndexId alone; that is settled when one
|
||||
// of the attempts completes.
|
||||
func (hm *HandshakeManager) allocatePQIndex(hh *HandshakeHostInfo, pq *pqAttempt) (uint32, error) {
|
||||
hm.mainHostMap.RLock()
|
||||
defer hm.mainHostMap.RUnlock()
|
||||
hm.Lock()
|
||||
defer hm.Unlock()
|
||||
|
||||
for range 32 {
|
||||
index, err := generateIndex(hm.l)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
_, inPending := hm.indexes[index]
|
||||
_, inMain := hm.mainHostMap.Indexes[index]
|
||||
|
||||
if !inMain && !inPending {
|
||||
pq.index = index
|
||||
hm.indexes[index] = hh
|
||||
return index, nil
|
||||
}
|
||||
}
|
||||
|
||||
return 0, errors.New("failed to generate unique localIndexId")
|
||||
}
|
||||
|
||||
func (hm *HandshakeManager) releasePQIndex(hh *HandshakeHostInfo, pq *pqAttempt) {
|
||||
hm.Lock()
|
||||
defer hm.Unlock()
|
||||
if pq.index != 0 && hm.indexes[pq.index] == hh {
|
||||
delete(hm.indexes, pq.index)
|
||||
}
|
||||
}
|
||||
|
||||
// settleIndex makes winner the hostinfo's local index and releases the index of
|
||||
// the attempt that lost.
|
||||
func (hm *HandshakeManager) settleIndex(hh *HandshakeHostInfo, winner uint32) {
|
||||
hm.Lock()
|
||||
defer hm.Unlock()
|
||||
for _, idx := range []uint32{hh.hostinfo.localIndexId, hh.pqIndex()} {
|
||||
if idx != 0 && idx != winner && hm.indexes[idx] == hh {
|
||||
delete(hm.indexes, idx)
|
||||
}
|
||||
}
|
||||
hh.hostinfo.localIndexId = winner
|
||||
}
|
||||
|
||||
func (hh *HandshakeHostInfo) pqIndex() uint32 {
|
||||
if hh.pq == nil {
|
||||
return 0
|
||||
}
|
||||
return hh.pq.index
|
||||
}
|
||||
|
||||
// handleFragment routes one fragment of a PQ handshake message.
|
||||
func (hm *HandshakeManager) handleFragment(via ViaSender, packet []byte, h *header.H) {
|
||||
if h.MessageCounter == pqCookieCounter {
|
||||
hm.handleCookie(via, packet, h)
|
||||
return
|
||||
}
|
||||
|
||||
fh, sym, err := fragment.Parse(packet[header.Len:])
|
||||
if err != nil {
|
||||
hm.l.Debug("dropping malformed handshake fragment", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
|
||||
switch h.MessageCounter {
|
||||
case 1:
|
||||
if !hm.pqConfig().accept {
|
||||
hm.l.Debug("dropping post-quantum handshake, not accepting them", "from", via)
|
||||
return
|
||||
}
|
||||
if h.RemoteIndex != 0 {
|
||||
hm.l.Debug("dropping stage-1 handshake with non-zero RemoteIndex",
|
||||
"from", via, "remoteIndex", h.RemoteIndex)
|
||||
return
|
||||
}
|
||||
now := time.Now()
|
||||
key, src := pqFragKeyFor(via, fh.FragID)
|
||||
if hm.pqTable.Load() >= pqCookieLoad && !(fh.HasCookie() && hm.pqCookies.valid(key, fh.Cookie, now)) {
|
||||
hm.sendCookie(via, fh, key, len(packet), now)
|
||||
return
|
||||
}
|
||||
res, err := hm.pqTable.Add(key, src, now, fh, sym)
|
||||
if err != nil {
|
||||
hm.l.Debug("dropping handshake fragment", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
if res == nil {
|
||||
return
|
||||
}
|
||||
if existing := hm.pqAnswered.lookup(res.Msg, time.Now()); existing != nil {
|
||||
// Already answered: resend, rate limited, with fresh symbols.
|
||||
if msg := existing.HandshakePacket[handshakePacketStage2]; msg != nil {
|
||||
hm.sendHandshakeResponse(via, msg, existing, true, res.Received)
|
||||
}
|
||||
return
|
||||
}
|
||||
hm.beginHandshake(via, reassembled(h, res.Msg), h, res.Received)
|
||||
|
||||
case 2:
|
||||
if hh := hm.queryIndex(h.RemoteIndex); hh != nil {
|
||||
hm.continuePQ(via, hh, h, fh, sym)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// continuePQ collects msg2 fragments for the initiator's PQ attempt.
|
||||
func (hm *HandshakeManager) continuePQ(via ViaSender, hh *HandshakeHostInfo, h *header.H, fh fragment.Header, sym []byte) {
|
||||
hh.Lock()
|
||||
defer hh.Unlock()
|
||||
|
||||
pq := hh.pq
|
||||
if pq == nil || pq.index != h.RemoteIndex || !hm.stillPending(hh, pq.index) {
|
||||
return
|
||||
}
|
||||
pq.heard = true
|
||||
|
||||
if pq.msg2 == nil {
|
||||
a, err := fragment.NewAssembly(fh)
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
pq.msg2 = a
|
||||
}
|
||||
ready, err := pq.msg2.Add(fh, sym)
|
||||
if errors.Is(err, fragment.ErrMismatch) {
|
||||
// The responder's FragID and MsgLen never change, so this is a stray or a
|
||||
// forgery. Start over from this fragment rather than wedge.
|
||||
pq.msg2 = nil
|
||||
return
|
||||
}
|
||||
if err != nil || !ready {
|
||||
return
|
||||
}
|
||||
|
||||
msg, err := pq.msg2.Decode()
|
||||
pq.msg2 = nil
|
||||
if err != nil {
|
||||
hm.l.Debug("failed to decode handshake fragments", "from", via, "error", err)
|
||||
return
|
||||
}
|
||||
hm.processResponse(via, hh, pq.machine, reassembled(h, msg))
|
||||
}
|
||||
|
||||
// sendFragmented sends packets to a peer: now immediately and later after the
|
||||
// repair delay. It returns the first error from the immediate sends; errors from
|
||||
// delayed sends are only logged.
|
||||
func (hm *HandshakeManager) sendFragmented(now, later [][]byte, send func([]byte) error) error {
|
||||
var first error
|
||||
for _, p := range now {
|
||||
if err := send(p); err != nil && first == nil {
|
||||
first = err
|
||||
}
|
||||
}
|
||||
sendLater := func() {
|
||||
for _, p := range later {
|
||||
if err := send(p); err != nil {
|
||||
hm.l.Debug("Failed to send handshake repair fragment", "error", err)
|
||||
}
|
||||
}
|
||||
}
|
||||
delay := hm.pqConfig().repairDelay
|
||||
switch {
|
||||
case len(later) == 0:
|
||||
case delay <= 0:
|
||||
sendLater()
|
||||
default:
|
||||
time.AfterFunc(delay, sendLater)
|
||||
}
|
||||
return first
|
||||
}
|
||||
|
||||
// sendFragmentedResponse sends the responder's msg2 as fragments. A resend of a
|
||||
// cached response (cached) offers fresh symbols and is rate limited to one per
|
||||
// retry interval. received is how many bytes the triggering msg1 took, which
|
||||
// bounds what may be sent back before the address is validated.
|
||||
func (hm *HandshakeManager) sendFragmentedResponse(via ViaSender, msg []byte, hostinfo *HostInfo, cached bool, received int) error {
|
||||
now := time.Now()
|
||||
if cached {
|
||||
last := hostinfo.handshakeResendAt.Load()
|
||||
if now.UnixNano()-last < int64(hm.config.tryInterval) ||
|
||||
!hostinfo.handshakeResendAt.CompareAndSwap(last, now.UnixNano()) {
|
||||
return errors.New("handshake response resend rate limited")
|
||||
}
|
||||
} else {
|
||||
hostinfo.handshakeResendAt.Store(now.UnixNano())
|
||||
}
|
||||
|
||||
var h header.H
|
||||
if err := h.Parse(msg); err != nil {
|
||||
return err
|
||||
}
|
||||
s, err := fragment.NewSender(msg[header.Len:], h.Subtype, h.RemoteIndex, h.MessageCounter, hostinfo.localIndexId)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
l := s.Layout()
|
||||
repair := fragment.DefaultRepair(l.K)
|
||||
if received > 0 {
|
||||
pktLen := header.Len + fragment.HeaderLen + l.SymbolSize
|
||||
budget := pqAmplification * received / pktLen
|
||||
if budget < l.K {
|
||||
return errors.New("handshake response exceeds the amplification budget")
|
||||
}
|
||||
repair = min(repair, budget-l.K)
|
||||
}
|
||||
|
||||
n := uint32(l.K + repair)
|
||||
s.SetNext(int(hostinfo.handshakeNextSymbol.Add(n) - n))
|
||||
pkts, later, err := s.Attempt(repair)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
if via.IsRelayed {
|
||||
if via.relay == nil {
|
||||
return errors.New("both addr and via.relay are nil")
|
||||
}
|
||||
// We received a valid handshake on this relay, so make sure the relay
|
||||
// state reflects that, in case it had been marked Disestablished.
|
||||
hostinfo.relayState.InsertRelayTo(via.relayHI.vpnAddrs[0])
|
||||
via.relayHI.relayState.UpdateRelayForByIdxState(via.relay.LocalIndex, Established)
|
||||
}
|
||||
hm.f.messageMetrics.Tx(header.Handshake, h.Subtype, int64(len(pkts)+len(later)))
|
||||
return hm.sendFragmented(pkts, later, hm.sendTo(via))
|
||||
}
|
||||
|
||||
// notePQPeer remembers peers that completed a PQ handshake, for sticky mode.
|
||||
func (hm *HandshakeManager) notePQPeer(subtype header.MessageSubType, vpnAddrs []netip.Addr) {
|
||||
if !hm.pqConfig().sticky || subtype != pqSubtype {
|
||||
return
|
||||
}
|
||||
for _, a := range vpnAddrs {
|
||||
hm.pqPeers.Store(a, struct{}{})
|
||||
}
|
||||
if hm.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hm.l.Debug("Remembering post-quantum peer", "vpnAddrs", vpnAddrs)
|
||||
}
|
||||
}
|
||||
|
||||
// pqAnswered remembers the msg1s a responder recently answered, keyed by hash,
|
||||
// so a repeat is recognised before any noise, KEM or certificate work. Repeats
|
||||
// are routine: the trailing repair fragments of an attempt rebuild a msg1 that
|
||||
// its data fragments already completed, and a retrying initiator offers fresh
|
||||
// symbols for the same msg1. Entries only exist for completed handshakes, which
|
||||
// need a valid certificate, and live as long as an initiator keeps retrying.
|
||||
type pqAnswered struct {
|
||||
sync.Mutex
|
||||
ttl time.Duration
|
||||
entries map[[sha256.Size]byte]pqAnsweredEntry
|
||||
}
|
||||
|
||||
type pqAnsweredEntry struct {
|
||||
hostinfo *HostInfo
|
||||
at time.Time
|
||||
}
|
||||
|
||||
const pqAnsweredMax = 4096
|
||||
|
||||
func newPQAnswered(ttl time.Duration) *pqAnswered {
|
||||
return &pqAnswered{ttl: ttl, entries: map[[sha256.Size]byte]pqAnsweredEntry{}}
|
||||
}
|
||||
|
||||
func (a *pqAnswered) add(msg1 []byte, hostinfo *HostInfo, now time.Time) {
|
||||
a.Lock()
|
||||
defer a.Unlock()
|
||||
if len(a.entries) >= pqAnsweredMax {
|
||||
for k := range a.entries {
|
||||
delete(a.entries, k)
|
||||
break
|
||||
}
|
||||
}
|
||||
a.entries[sha256.Sum256(msg1)] = pqAnsweredEntry{hostinfo: hostinfo, at: now}
|
||||
}
|
||||
|
||||
func (a *pqAnswered) lookup(msg1 []byte, now time.Time) *HostInfo {
|
||||
a.Lock()
|
||||
defer a.Unlock()
|
||||
e, ok := a.entries[sha256.Sum256(msg1)]
|
||||
if !ok || now.Sub(e.at) > a.ttl {
|
||||
return nil
|
||||
}
|
||||
return e.hostinfo
|
||||
}
|
||||
|
||||
func (a *pqAnswered) expire(now time.Time) {
|
||||
a.Lock()
|
||||
defer a.Unlock()
|
||||
for k, e := range a.entries {
|
||||
if now.Sub(e.at) > a.ttl {
|
||||
delete(a.entries, k)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A responder whose msg1 table is under load stops keeping state for senders
|
||||
// that have not shown they receive at their address. It answers a fragment
|
||||
// without a valid cookie with a cookie reply and keeps nothing; the initiator
|
||||
// resends with the cookie attached. This is WireGuard's under-load cookie, QUIC's
|
||||
// Retry and SCTP's state cookie: one extra round trip, only while under attack.
|
||||
const (
|
||||
// pqCookieLoad is the table load above which msg1 fragments need a cookie.
|
||||
pqCookieLoad = 0.5
|
||||
|
||||
// pqCookieCounter marks a cookie reply in the header's message counter.
|
||||
// Handshake messages count from 1.
|
||||
pqCookieCounter = 0
|
||||
|
||||
// pqCookieRotate is how often the cookie secret changes. A cookie stays
|
||||
// valid for between one and two rotations.
|
||||
pqCookieRotate = 2 * time.Minute
|
||||
|
||||
pqCookieReplyLen = header.Len + fragment.CookieLen
|
||||
)
|
||||
|
||||
// pqCookies mints and checks cookies: an HMAC over the sender's address (or relay
|
||||
// channel) and FragID under a rotating secret, with the previous secret still
|
||||
// accepted.
|
||||
type pqCookies struct {
|
||||
sync.Mutex
|
||||
secrets [2][32]byte
|
||||
rotatedAt time.Time
|
||||
}
|
||||
|
||||
func newPQCookies(now time.Time) *pqCookies {
|
||||
c := &pqCookies{rotatedAt: now}
|
||||
_, _ = rand.Read(c.secrets[0][:])
|
||||
_, _ = rand.Read(c.secrets[1][:])
|
||||
return c
|
||||
}
|
||||
|
||||
func (c *pqCookies) rotate(now time.Time) {
|
||||
if now.Sub(c.rotatedAt) < pqCookieRotate {
|
||||
return
|
||||
}
|
||||
c.secrets[1] = c.secrets[0]
|
||||
_, _ = rand.Read(c.secrets[0][:])
|
||||
c.rotatedAt = now
|
||||
}
|
||||
|
||||
func cookieMAC(secret []byte, key pqFragKey) fragment.Cookie {
|
||||
mac := hmac.New(sha256.New, secret)
|
||||
addr := key.addr.Addr().As16()
|
||||
mac.Write(addr[:])
|
||||
var b [10]byte
|
||||
binary.BigEndian.PutUint16(b[0:], key.addr.Port())
|
||||
binary.BigEndian.PutUint32(b[2:], key.relay)
|
||||
binary.BigEndian.PutUint32(b[6:], key.fragID)
|
||||
mac.Write(b[:])
|
||||
var c fragment.Cookie
|
||||
copy(c[:], mac.Sum(nil))
|
||||
return c
|
||||
}
|
||||
|
||||
func (c *pqCookies) make(key pqFragKey, now time.Time) fragment.Cookie {
|
||||
c.Lock()
|
||||
defer c.Unlock()
|
||||
c.rotate(now)
|
||||
return cookieMAC(c.secrets[0][:], key)
|
||||
}
|
||||
|
||||
func (c *pqCookies) valid(key pqFragKey, cookie fragment.Cookie, now time.Time) bool {
|
||||
c.Lock()
|
||||
defer c.Unlock()
|
||||
c.rotate(now)
|
||||
for _, s := range c.secrets {
|
||||
want := cookieMAC(s[:], key)
|
||||
if hmac.Equal(want[:], cookie[:]) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// sendCookie answers a msg1 fragment that arrived without a valid cookie while
|
||||
// under load. The reply is never larger than what triggered it, and replies are
|
||||
// rate limited as a whole.
|
||||
func (hm *HandshakeManager) sendCookie(via ViaSender, fh fragment.Header, key pqFragKey, received int, now time.Time) {
|
||||
if received < pqCookieReplyLen {
|
||||
return
|
||||
}
|
||||
if _, ok := hm.pqCookieLimiter.Allow(); !ok {
|
||||
return
|
||||
}
|
||||
c := hm.pqCookies.make(key, now)
|
||||
reply := make([]byte, header.Len, pqCookieReplyLen)
|
||||
header.Encode(reply, header.Version, header.Handshake, pqSubtype, fh.FragID, pqCookieCounter)
|
||||
reply = append(reply, c[:]...)
|
||||
hm.f.messageMetrics.Tx(header.Handshake, pqSubtype, 1)
|
||||
if err := hm.sendTo(via)(reply); err != nil {
|
||||
hm.l.Debug("Failed to send handshake cookie", "to", via, "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
// handleCookie attaches a responder's cookie to the PQ attempt it names and
|
||||
// resends right away, at most once per retry interval, rather than waiting for
|
||||
// the next attempt.
|
||||
func (hm *HandshakeManager) handleCookie(via ViaSender, packet []byte, h *header.H) {
|
||||
if len(packet) != pqCookieReplyLen {
|
||||
return
|
||||
}
|
||||
hh := hm.queryIndex(h.RemoteIndex)
|
||||
if hh == nil {
|
||||
return
|
||||
}
|
||||
hh.Lock()
|
||||
defer hh.Unlock()
|
||||
|
||||
pq := hh.pq
|
||||
if pq == nil || pq.index != h.RemoteIndex || !hm.stillPending(hh, pq.index) {
|
||||
return
|
||||
}
|
||||
var c fragment.Cookie
|
||||
copy(c[:], packet[header.Len:])
|
||||
pq.sender.SetCookie(c)
|
||||
pq.heard = true
|
||||
|
||||
now := time.Now()
|
||||
if now.Sub(pq.cookieResendAt) < hm.config.tryInterval {
|
||||
return
|
||||
}
|
||||
pq.cookieResendAt = now
|
||||
pkts, later, err := pq.sender.Attempt(fragment.DefaultRepair(pq.sender.Layout().K))
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
hm.messageMetrics.Tx(header.Handshake, pqSubtype, int64(len(pkts)+len(later)))
|
||||
if err := hm.sendFragmented(pkts, later, hm.sendTo(via)); err != nil {
|
||||
hm.l.Debug("Failed to resend handshake with cookie", "to", via, "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
// sendTo returns a function sending a packet back the way via came: directly, or
|
||||
// through the relay it arrived on.
|
||||
func (hm *HandshakeManager) sendTo(via ViaSender) func([]byte) error {
|
||||
f := hm.f
|
||||
if !via.IsRelayed {
|
||||
return func(p []byte) error {
|
||||
return f.outside.WriteTo(p, via.UdpAddr)
|
||||
}
|
||||
}
|
||||
return func(p []byte) error {
|
||||
if via.relay == nil {
|
||||
return errors.New("both addr and via.relay are nil")
|
||||
}
|
||||
f.SendVia(via.relayHI, via.relay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
||||
return nil
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,398 @@
|
||||
package nebula
|
||||
|
||||
import (
|
||||
"math/rand/v2"
|
||||
"net/netip"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/handshake/fragment"
|
||||
"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"
|
||||
)
|
||||
|
||||
// recordingConn captures what is written to it.
|
||||
type recordingConn struct {
|
||||
udp.NoopConn
|
||||
sync.Mutex
|
||||
sent [][]byte
|
||||
}
|
||||
|
||||
func (c *recordingConn) WriteTo(b []byte, _ netip.AddrPort) error {
|
||||
c.Lock()
|
||||
defer c.Unlock()
|
||||
c.sent = append(c.sent, append([]byte(nil), b...))
|
||||
return nil
|
||||
}
|
||||
|
||||
func (c *recordingConn) take() [][]byte {
|
||||
c.Lock()
|
||||
defer c.Unlock()
|
||||
s := c.sent
|
||||
c.sent = nil
|
||||
return s
|
||||
}
|
||||
|
||||
func newPQTestManager(t *testing.T) (*HandshakeManager, *recordingConn) {
|
||||
l := test.NewLogger()
|
||||
conn := &recordingConn{}
|
||||
cfg := defaultHandshakeConfig
|
||||
cfg.pq = pqHandshakeConfig{initiate: true, accept: true}
|
||||
hm := NewHandshakeManager(l, newHostMap(l), newTestLighthouse(), conn, cfg)
|
||||
hm.f = &Interface{
|
||||
handshakeManager: hm,
|
||||
outside: conn,
|
||||
messageMetrics: newMessageMetricsOnlyRecvError(),
|
||||
l: l,
|
||||
}
|
||||
return hm, conn
|
||||
}
|
||||
|
||||
// fragmentIndexes checks every packet is a fragment of the expected response and
|
||||
// returns their symbol indexes.
|
||||
func fragmentIndexes(t *testing.T, pkts [][]byte, fragID, remoteIndex uint32) []int {
|
||||
t.Helper()
|
||||
var out []int
|
||||
for _, p := range pkts {
|
||||
require.LessOrEqual(t, len(p), fragment.MaxPacketLen)
|
||||
var h header.H
|
||||
require.NoError(t, h.Parse(p))
|
||||
assert.Equal(t, pqSubtype, h.Subtype)
|
||||
assert.Equal(t, remoteIndex, h.RemoteIndex)
|
||||
assert.Equal(t, uint64(2), h.MessageCounter)
|
||||
fh, _, err := fragment.Parse(p[header.Len:])
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, fragID, fh.FragID)
|
||||
out = append(out, int(fh.Index))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func TestSendFragmentedResponse(t *testing.T) {
|
||||
hm, conn := newPQTestManager(t)
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
||||
hostinfo := &HostInfo{localIndexId: 77}
|
||||
|
||||
// A 2000 byte message is 2 symbols of 1000, so packets of 1024 bytes.
|
||||
msg := make([]byte, header.Len, header.Len+2000)
|
||||
header.Encode(msg, header.Version, header.Handshake, pqSubtype, 5, 2)
|
||||
r := rand.New(rand.NewPCG(1, 1))
|
||||
for range 2000 {
|
||||
msg = append(msg, byte(r.Uint32()))
|
||||
}
|
||||
const pktLen = header.Len + fragment.HeaderLen + 1000
|
||||
|
||||
t.Run("first send", func(t *testing.T) {
|
||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, false, 0))
|
||||
assert.Equal(t, []int{0, 1, 2, 3}, fragmentIndexes(t, conn.take(), 77, 5))
|
||||
})
|
||||
|
||||
t.Run("resends are rate limited", func(t *testing.T) {
|
||||
require.Error(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, 10*pktLen))
|
||||
assert.Empty(t, conn.take())
|
||||
})
|
||||
|
||||
allowResend := func() {
|
||||
hostinfo.handshakeResendAt.Store(time.Now().Add(-time.Second).UnixNano())
|
||||
}
|
||||
|
||||
t.Run("resend offers fresh symbols", func(t *testing.T) {
|
||||
allowResend()
|
||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, 10*pktLen))
|
||||
assert.Equal(t, []int{4, 5, 6, 7}, fragmentIndexes(t, conn.take(), 77, 5))
|
||||
})
|
||||
|
||||
t.Run("amplification budget trims repair", func(t *testing.T) {
|
||||
allowResend()
|
||||
// 3x of a little over one packet allows 3 packets: both data and 1 repair.
|
||||
require.NoError(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, pktLen+10))
|
||||
assert.Equal(t, []int{8, 9, 10}, fragmentIndexes(t, conn.take(), 77, 5))
|
||||
})
|
||||
|
||||
t.Run("amplification budget below the data refuses", func(t *testing.T) {
|
||||
allowResend()
|
||||
require.Error(t, hm.sendFragmentedResponse(via, msg, hostinfo, true, pktLen/2))
|
||||
assert.Empty(t, conn.take())
|
||||
})
|
||||
}
|
||||
|
||||
func TestPQAnswered(t *testing.T) {
|
||||
now := time.Unix(1000, 0)
|
||||
a := newPQAnswered(5 * time.Second)
|
||||
hi := &HostInfo{}
|
||||
|
||||
assert.Nil(t, a.lookup([]byte("msg1"), now))
|
||||
a.add([]byte("msg1"), hi, now)
|
||||
assert.Same(t, hi, a.lookup([]byte("msg1"), now.Add(time.Second)))
|
||||
assert.Nil(t, a.lookup([]byte("other"), now))
|
||||
assert.Nil(t, a.lookup([]byte("msg1"), now.Add(6*time.Second)), "stale entries are not answered")
|
||||
|
||||
a.expire(now.Add(6 * time.Second))
|
||||
assert.Empty(t, a.entries)
|
||||
|
||||
for i := range pqAnsweredMax + 10 {
|
||||
a.add([]byte{byte(i), byte(i >> 8)}, hi, now)
|
||||
}
|
||||
assert.Len(t, a.entries, pqAnsweredMax)
|
||||
}
|
||||
|
||||
func TestPQFragKeyFor(t *testing.T) {
|
||||
k1, s1 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}, 9)
|
||||
k2, s2 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4243")}, 9)
|
||||
assert.NotEqual(t, k1, k2, "different ports are different messages")
|
||||
assert.Equal(t, s1, s2, "but share an IPv4 /32 quota")
|
||||
|
||||
_, s3 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[2001:db8::1]:1")}, 9)
|
||||
_, s4 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[2001:db8::ffff]:1")}, 9)
|
||||
assert.Equal(t, s3, s4, "an IPv6 /64 shares a quota")
|
||||
|
||||
_, s5 := pqFragKeyFor(ViaSender{UdpAddr: netip.MustParseAddrPort("[::ffff:192.0.2.1]:1")}, 9)
|
||||
assert.Equal(t, s1, s5, "v4-mapped addresses count as IPv4")
|
||||
}
|
||||
|
||||
func TestPQCookies(t *testing.T) {
|
||||
now := time.Unix(1000, 0)
|
||||
c := newPQCookies(now)
|
||||
key := pqFragKey{addr: netip.MustParseAddrPort("192.0.2.1:4242"), fragID: 9}
|
||||
|
||||
cookie := c.make(key, now)
|
||||
assert.True(t, c.valid(key, cookie, now))
|
||||
|
||||
for _, other := range []pqFragKey{
|
||||
{addr: netip.MustParseAddrPort("192.0.2.2:4242"), fragID: 9},
|
||||
{addr: netip.MustParseAddrPort("192.0.2.1:4243"), fragID: 9},
|
||||
{addr: netip.MustParseAddrPort("192.0.2.1:4242"), fragID: 10},
|
||||
{addr: netip.MustParseAddrPort("192.0.2.1:4242"), relay: 1, fragID: 9},
|
||||
} {
|
||||
assert.False(t, c.valid(other, cookie, now), "%+v", other)
|
||||
}
|
||||
|
||||
now = now.Add(pqCookieRotate)
|
||||
assert.True(t, c.valid(key, cookie, now), "the previous secret is still accepted")
|
||||
assert.NotEqual(t, cookie, c.make(key, now), "new cookies come from the new secret")
|
||||
|
||||
now = now.Add(pqCookieRotate)
|
||||
assert.False(t, c.valid(key, cookie, now), "two rotations retire a cookie")
|
||||
}
|
||||
|
||||
// pqMsg1Fragment builds the first fragment of a msg1, optionally with a cookie.
|
||||
func pqMsg1Fragment(t *testing.T, fragID uint32, cookie *fragment.Cookie) ([]byte, *header.H) {
|
||||
t.Helper()
|
||||
s, err := fragment.NewSender(make([]byte, 2000), pqSubtype, 0, 1, fragID)
|
||||
require.NoError(t, err)
|
||||
if cookie != nil {
|
||||
s.SetCookie(*cookie)
|
||||
}
|
||||
pkts, _, err := s.Attempt(0)
|
||||
require.NoError(t, err)
|
||||
var h header.H
|
||||
require.NoError(t, h.Parse(pkts[0]))
|
||||
return pkts[0], &h
|
||||
}
|
||||
|
||||
// fillPQTable puts the responder's msg1 table at the cookie threshold.
|
||||
func fillPQTable(t *testing.T, hm *HandshakeManager) {
|
||||
t.Helper()
|
||||
now := time.Now()
|
||||
for i := 0; hm.pqTable.Load() < pqCookieLoad; i++ {
|
||||
p, _ := pqMsg1Fragment(t, uint32(i+1), nil)
|
||||
fh, sym, err := fragment.Parse(p[header.Len:])
|
||||
require.NoError(t, err)
|
||||
addr := netip.AddrPortFrom(netip.AddrFrom4([4]byte{198, 18, byte(i >> 8), byte(i)}), 4242)
|
||||
key, src := pqFragKeyFor(ViaSender{UdpAddr: addr}, fh.FragID)
|
||||
_, err = hm.pqTable.Add(key, src, now, fh, sym)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPQCookieUnderLoad(t *testing.T) {
|
||||
hm, conn := newPQTestManager(t)
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
||||
|
||||
t.Run("no cookie needed below the threshold", func(t *testing.T) {
|
||||
p, h := pqMsg1Fragment(t, 5000, nil)
|
||||
before := hm.pqTable.Len()
|
||||
hm.handleFragment(via, p, h)
|
||||
assert.Empty(t, conn.take())
|
||||
assert.Equal(t, before+1, hm.pqTable.Len())
|
||||
})
|
||||
|
||||
fillPQTable(t, hm)
|
||||
|
||||
var cookie fragment.Cookie
|
||||
t.Run("a fragment without a cookie gets one and leaves no state", func(t *testing.T) {
|
||||
p, h := pqMsg1Fragment(t, 7, nil)
|
||||
before := hm.pqTable.Len()
|
||||
hm.handleFragment(via, p, h)
|
||||
assert.Equal(t, before, hm.pqTable.Len())
|
||||
|
||||
sent := conn.take()
|
||||
require.Len(t, sent, 1)
|
||||
reply := sent[0]
|
||||
require.Len(t, reply, pqCookieReplyLen)
|
||||
var rh header.H
|
||||
require.NoError(t, rh.Parse(reply))
|
||||
assert.Equal(t, header.Handshake, rh.Type)
|
||||
assert.Equal(t, pqSubtype, rh.Subtype)
|
||||
assert.Equal(t, uint32(7), rh.RemoteIndex, "the reply names the initiator's FragID")
|
||||
assert.Equal(t, uint64(pqCookieCounter), rh.MessageCounter)
|
||||
copy(cookie[:], reply[header.Len:])
|
||||
})
|
||||
|
||||
t.Run("a forged cookie gets a fresh one", func(t *testing.T) {
|
||||
bad := cookie
|
||||
bad[0] ^= 1
|
||||
p, h := pqMsg1Fragment(t, 7, &bad)
|
||||
before := hm.pqTable.Len()
|
||||
hm.handleFragment(via, p, h)
|
||||
assert.Equal(t, before, hm.pqTable.Len())
|
||||
assert.Len(t, conn.take(), 1)
|
||||
})
|
||||
|
||||
t.Run("the cookie gets the fragment in", func(t *testing.T) {
|
||||
p, h := pqMsg1Fragment(t, 7, &cookie)
|
||||
before := hm.pqTable.Len()
|
||||
hm.handleFragment(via, p, h)
|
||||
assert.Equal(t, before+1, hm.pqTable.Len())
|
||||
assert.Empty(t, conn.take())
|
||||
})
|
||||
|
||||
t.Run("a cookie is bound to its address", func(t *testing.T) {
|
||||
p, h := pqMsg1Fragment(t, 7, &cookie)
|
||||
hm.handleFragment(ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.99:4242")}, p, h)
|
||||
assert.Len(t, conn.take(), 1, "another address gets its own cookie instead")
|
||||
})
|
||||
|
||||
t.Run("a reply never outgrows what prompted it", func(t *testing.T) {
|
||||
p, h := pqMsg1Fragment(t, 8, nil)
|
||||
hm.sendCookie(via, fragment.Header{FragID: 8}, pqFragKey{}, pqCookieReplyLen-1, time.Now())
|
||||
assert.Empty(t, conn.take())
|
||||
hm.handleFragment(via, p, h)
|
||||
assert.Len(t, conn.take(), 1)
|
||||
})
|
||||
}
|
||||
|
||||
func TestPQHandleCookie(t *testing.T) {
|
||||
hm, conn := newPQTestManager(t)
|
||||
via := ViaSender{UdpAddr: netip.MustParseAddrPort("192.0.2.1:4242")}
|
||||
|
||||
s, err := fragment.NewSender(make([]byte, 2000), pqSubtype, 0, 1, 99)
|
||||
require.NoError(t, err)
|
||||
_, _, err = s.Attempt(2)
|
||||
require.NoError(t, err)
|
||||
hh := &HandshakeHostInfo{hostinfo: &HostInfo{}, pq: &pqAttempt{index: 99, sender: s}}
|
||||
hm.indexes[99] = hh
|
||||
|
||||
reply := make([]byte, header.Len, pqCookieReplyLen)
|
||||
header.Encode(reply, header.Version, header.Handshake, pqSubtype, 99, pqCookieCounter)
|
||||
reply = append(reply, bytes16(0xab)...)
|
||||
var h header.H
|
||||
require.NoError(t, h.Parse(reply))
|
||||
|
||||
hm.handleFragment(via, reply, &h)
|
||||
assert.True(t, hh.pq.heard, "a cookie reply shows the peer speaks PQ")
|
||||
sent := conn.take()
|
||||
require.Len(t, sent, 4, "an immediate resend of fresh symbols")
|
||||
for i, p := range sent {
|
||||
fh, _, err := fragment.Parse(p[header.Len:])
|
||||
require.NoError(t, err)
|
||||
assert.True(t, fh.HasCookie())
|
||||
assert.Equal(t, fragment.Cookie(bytes16(0xab)), fh.Cookie)
|
||||
assert.Equal(t, uint8(4+i), fh.Index)
|
||||
}
|
||||
|
||||
hm.handleFragment(via, reply, &h)
|
||||
assert.Empty(t, conn.take(), "immediate resends are rate limited")
|
||||
|
||||
t.Run("replies for other indexes are ignored", func(t *testing.T) {
|
||||
other := append([]byte(nil), reply...)
|
||||
header.Encode(other, header.Version, header.Handshake, pqSubtype, 98, pqCookieCounter)
|
||||
var oh header.H
|
||||
require.NoError(t, oh.Parse(other))
|
||||
hh.pq.cookieResendAt = time.Time{}
|
||||
hm.handleFragment(via, other, &oh)
|
||||
assert.Empty(t, conn.take())
|
||||
})
|
||||
}
|
||||
|
||||
func bytes16(b byte) []byte {
|
||||
out := make([]byte, 16)
|
||||
for i := range out {
|
||||
out[i] = b
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func TestReloadPQ(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
require.NoError(t, c.LoadString(`handshakes: {pq: {initiate: false}}`))
|
||||
cfg := defaultHandshakeConfig
|
||||
cfg.pq = pqHandshakeConfigFrom(c)
|
||||
hm := NewHandshakeManager(l, newHostMap(l), newTestLighthouse(), &udp.NoopConn{}, cfg)
|
||||
c.RegisterReloadCallback(hm.reloadPQ)
|
||||
|
||||
assert.Equal(t, pqHandshakeConfig{repairDelay: DefaultPQRepairDelay}, *hm.pqConfig())
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`handshakes: {pq: {initiate: true, accept: true, sticky: true, repair_delay: 25ms}}`))
|
||||
assert.Equal(t, pqHandshakeConfig{initiate: true, accept: true, sticky: true, repairDelay: 25 * time.Millisecond}, *hm.pqConfig())
|
||||
|
||||
before := hm.pqConfig()
|
||||
require.NoError(t, c.ReloadConfigString(`handshakes: {try_interval: 1s, pq: {initiate: true, accept: true, sticky: true, repair_delay: 25ms}}`))
|
||||
assert.Same(t, before, hm.pqConfig(), "an unrelated change leaves the settings alone")
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`handshakes: {}`))
|
||||
assert.Equal(t, pqHandshakeConfig{repairDelay: DefaultPQRepairDelay}, *hm.pqConfig(), "removing the section restores the defaults")
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(`handshakes: {pq: {require: true}}`))
|
||||
assert.Equal(t, pqHandshakeConfig{initiate: true, accept: true, require: true, repairDelay: DefaultPQRepairDelay}, *hm.pqConfig(), "require implies initiate and accept")
|
||||
}
|
||||
|
||||
func TestUsePQ(t *testing.T) {
|
||||
hm, _ := newPQTestManager(t)
|
||||
peer := netip.MustParseAddr("10.1.0.1")
|
||||
set := func(cfg pqHandshakeConfig) { hm.pq.Store(&cfg) }
|
||||
|
||||
// attempts plays a run of attempts, given whether each was triggered early,
|
||||
// and returns which were PQ.
|
||||
attempts := func(triggered ...bool) []bool {
|
||||
hh := &HandshakeHostInfo{}
|
||||
var out []bool
|
||||
for _, tr := range triggered {
|
||||
hh.counter++
|
||||
hh.lastPQ = hm.usePQ(hh, peer, tr)
|
||||
out = append(out, hh.lastPQ)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
set(pqHandshakeConfig{})
|
||||
assert.Equal(t, []bool{false, false, false}, attempts(false, false, false), "off")
|
||||
|
||||
set(pqHandshakeConfig{initiate: true})
|
||||
assert.Equal(t, []bool{true, false, true, false}, attempts(false, false, false, false), "timer retries alternate, PQ first")
|
||||
assert.Equal(t, []bool{true, true, false, true, false}, attempts(false, true, false, true, false), "an early trigger is a new path, which gets PQ first")
|
||||
assert.Equal(t, []bool{true, true, false}, attempts(true, true, false), "a triggered first attempt is PQ")
|
||||
|
||||
t.Run("hearing back stops the classical turns", func(t *testing.T) {
|
||||
hh := &HandshakeHostInfo{pq: &pqAttempt{}}
|
||||
hh.counter, hh.lastPQ = 1, true
|
||||
hh.counter++
|
||||
assert.False(t, hm.usePQ(hh, peer, false), "unheard, the classical attempt gets its turn")
|
||||
hh.pq.heard = true
|
||||
assert.True(t, hm.usePQ(hh, peer, false))
|
||||
})
|
||||
|
||||
set(pqHandshakeConfig{initiate: true, accept: true, require: true})
|
||||
assert.Equal(t, []bool{true, true, true, true}, attempts(false, false, true, false), "require never offers classical")
|
||||
|
||||
set(pqHandshakeConfig{initiate: true, sticky: true})
|
||||
assert.Equal(t, []bool{true, false}, attempts(false, false), "sticky alternates until the peer has done PQ")
|
||||
hm.notePQPeer(pqSubtype, []netip.Addr{peer})
|
||||
assert.Equal(t, []bool{true, true, true}, attempts(false, false, false), "then only PQ")
|
||||
}
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"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 +43,6 @@ 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 +234,70 @@ func TestHandleIncomingDispatch(t *testing.T) {
|
||||
assert.Empty(t, hm.indexes, "orphan stage-2 must not create state")
|
||||
})
|
||||
}
|
||||
|
||||
// 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)
|
||||
}
|
||||
+19
-2
@@ -24,6 +24,11 @@ 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
|
||||
@@ -62,8 +67,19 @@ const (
|
||||
const (
|
||||
HandshakeIXPSK0 MessageSubType = 0
|
||||
HandshakeXXPSK0 MessageSubType = 1
|
||||
|
||||
// HandshakeIXPSK2MLKEM1024 is IX with an ephemeral ML-KEM-1024 exchange mixed
|
||||
// in through the psk2 slot. Its messages exceed the MTU and travel as
|
||||
// fragments (see handshake/fragment).
|
||||
HandshakeIXPSK2MLKEM1024 MessageSubType = 2
|
||||
)
|
||||
|
||||
// IsFragmented reports whether handshake messages of this subtype travel as
|
||||
// fragments.
|
||||
func IsFragmented(st MessageSubType) bool {
|
||||
return st == HandshakeIXPSK2MLKEM1024
|
||||
}
|
||||
|
||||
var ErrHeaderTooShort = errors.New("header is too short")
|
||||
|
||||
var subTypeTestMap = map[MessageSubType]string{
|
||||
@@ -83,7 +99,8 @@ var subTypeMap = map[MessageType]*map[MessageSubType]string{
|
||||
Test: &subTypeTestMap,
|
||||
CloseTunnel: &subTypeNoneMap,
|
||||
Handshake: {
|
||||
HandshakeIXPSK0: "ix_psk0",
|
||||
HandshakeIXPSK0: "ix_psk0",
|
||||
HandshakeIXPSK2MLKEM1024: "ix_psk2_mlkem1024",
|
||||
},
|
||||
Control: &subTypeNoneMap,
|
||||
}
|
||||
@@ -194,7 +211,7 @@ func IsValidSubType(t MessageType, s MessageSubType) bool {
|
||||
case Message:
|
||||
return s == MessageNone || s == MessageRelay
|
||||
case Handshake:
|
||||
return s == HandshakeIXPSK0
|
||||
return s == HandshakeIXPSK0 || s == HandshakeIXPSK2MLKEM1024
|
||||
case Test:
|
||||
return s == TestReply || s == TestRequest
|
||||
case Control, CloseTunnel, RecvError, LightHouse:
|
||||
|
||||
@@ -96,7 +96,8 @@ func TestTypeMap(t *testing.T) {
|
||||
Test: &subTypeTestMap,
|
||||
CloseTunnel: &subTypeNoneMap,
|
||||
Handshake: {
|
||||
HandshakeIXPSK0: "ix_psk0",
|
||||
HandshakeIXPSK0: "ix_psk0",
|
||||
HandshakeIXPSK2MLKEM1024: "ix_psk2_mlkem1024",
|
||||
},
|
||||
Control: &subTypeNoneMap,
|
||||
}, subTypeMap)
|
||||
@@ -122,6 +123,7 @@ func TestIsValidSubType(t *testing.T) {
|
||||
assert.False(t, IsValidSubType(Message, 2))
|
||||
|
||||
assert.True(t, IsValidSubType(Handshake, HandshakeIXPSK0))
|
||||
assert.True(t, IsValidSubType(Handshake, HandshakeIXPSK2MLKEM1024))
|
||||
// HandshakeXXPSK0 is defined but not a wire-valid subtype.
|
||||
assert.False(t, IsValidSubType(Handshake, HandshakeXXPSK0))
|
||||
|
||||
|
||||
@@ -260,6 +260,11 @@ type HostInfo struct {
|
||||
// We need these to avoid replayed handshake packets creating new hostinfos which causes churn
|
||||
HandshakePacket map[uint8][]byte
|
||||
|
||||
// A responder resending a fragmented handshake response offers symbols it has
|
||||
// not sent before, at most once per retry interval.
|
||||
handshakeResendAt atomic.Int64 // unix nanos of the last send
|
||||
handshakeNextSymbol atomic.Uint32 // next fragment symbol index to offer
|
||||
|
||||
// nextLHQuery is the earliest we can ask the lighthouse for new information.
|
||||
// This is used to limit lighthouse re-queries in chatty clients
|
||||
nextLHQuery atomic.Int64
|
||||
|
||||
@@ -10,6 +10,7 @@ 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"
|
||||
@@ -198,8 +199,8 @@ func (f *Interface) sendInsideMessage(hostinfo *HostInfo, pkt tio.Packet, nb []b
|
||||
}
|
||||
|
||||
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, seg, scratch[header.Len:], nb)
|
||||
if innerPacket == nil {
|
||||
@@ -517,7 +518,9 @@ func (f *Interface) SendVia(via *HostInfo, relay *Relay, ad, nb, out []byte, noc
|
||||
|
||||
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)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -526,16 +529,26 @@ func (f *Interface) sendNoMetrics(t header.MessageType, st header.MessageSubType
|
||||
return
|
||||
}
|
||||
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 {
|
||||
@@ -582,18 +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
|
||||
|
||||
+24
-18
@@ -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"
|
||||
)
|
||||
|
||||
@@ -124,6 +125,10 @@ type Interface struct {
|
||||
batchers []*batch.MultiCoalescer
|
||||
wg 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)
|
||||
fatalErr atomic.Pointer[error]
|
||||
@@ -198,6 +203,19 @@ 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
|
||||
}
|
||||
@@ -230,6 +248,9 @@ 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),
|
||||
@@ -624,17 +645,15 @@ 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)
|
||||
|
||||
emit := func() {
|
||||
return func() {
|
||||
f.firewall.EmitStats()
|
||||
f.handshakeManager.EmitStats()
|
||||
udpStats()
|
||||
@@ -651,19 +670,6 @@ 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 {
|
||||
|
||||
+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())
|
||||
|
||||
+28
-5
@@ -15,6 +15,7 @@ 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"
|
||||
@@ -81,6 +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
|
||||
|
||||
@@ -116,7 +119,8 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
||||
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 {
|
||||
@@ -355,7 +359,13 @@ 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
|
||||
@@ -380,6 +390,11 @@ 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
|
||||
@@ -512,14 +527,19 @@ 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 {
|
||||
@@ -1235,10 +1255,13 @@ 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
|
||||
|
||||
@@ -6,13 +6,16 @@ import (
|
||||
"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"
|
||||
@@ -795,3 +798,202 @@ func TestLightHouse_logLocalAddrsErr(t *testing.T) {
|
||||
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"))
|
||||
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"))
|
||||
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"))
|
||||
assert.Empty(t, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
<-lh.updateTrigger
|
||||
|
||||
require.NoError(t, c.ReloadConfigString(base+" am_relay: false\n"))
|
||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("10.128.0.5")}, lh.GetRelaysForMe())
|
||||
require.Len(t, lh.updateTrigger, 1)
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
package logging
|
||||
|
||||
import "log/slog"
|
||||
|
||||
// RateLimiter is what RateLimited needs from a rate limiter, such as a *ratelimit.Limiter.
|
||||
// Allow reports whether this call may proceed, and how many calls were denied since the last one that did.
|
||||
type RateLimiter interface {
|
||||
Allow() (denied uint64, ok bool)
|
||||
}
|
||||
|
||||
// RateLimited checks lim before anything is built.
|
||||
// When allowed it returns l, with a "suppressed" count attached if lim denied calls since its last allowed one.
|
||||
// A nil lim allows everything.
|
||||
//
|
||||
// if l, ok := logging.RateLimited(f.l, f.udpTxErrLimiter); ok {
|
||||
// hostinfo.logger(l).Error("Failed to write outgoing packet", "error", err)
|
||||
// }
|
||||
func RateLimited(l *slog.Logger, lim RateLimiter) (*slog.Logger, bool) {
|
||||
if lim == nil {
|
||||
return l, true
|
||||
}
|
||||
|
||||
denied, ok := lim.Allow()
|
||||
if !ok {
|
||||
return nil, false
|
||||
}
|
||||
if denied > 0 {
|
||||
return l.With("suppressed", denied), true
|
||||
}
|
||||
return l, true
|
||||
}
|
||||
@@ -0,0 +1,106 @@
|
||||
package logging
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/slackhq/nebula/ratelimit"
|
||||
)
|
||||
|
||||
type fakeLimiter struct {
|
||||
denied uint64
|
||||
ok bool
|
||||
}
|
||||
|
||||
func (f fakeLimiter) Allow() (uint64, bool) { return f.denied, f.ok }
|
||||
|
||||
func TestRateLimited(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
base := NewLogger(&buf)
|
||||
|
||||
if l, ok := RateLimited(base, fakeLimiter{ok: false}); ok || l != nil {
|
||||
t.Fatalf("denied call: ok=%v logger=%v", ok, l)
|
||||
}
|
||||
|
||||
if l, ok := RateLimited(base, fakeLimiter{ok: true}); !ok || l != base {
|
||||
t.Fatal("nothing denied should hand back the same logger")
|
||||
}
|
||||
|
||||
if l, ok := RateLimited(base, nil); !ok || l != base {
|
||||
t.Fatal("a nil limiter should allow with the same logger")
|
||||
}
|
||||
|
||||
l, ok := RateLimited(base, fakeLimiter{denied: 7, ok: true})
|
||||
if !ok {
|
||||
t.Fatal("allowed call denied")
|
||||
}
|
||||
l.Info("hello", "k", "v")
|
||||
if !strings.Contains(buf.String(), "suppressed=7") {
|
||||
t.Fatalf("want suppressed=7, got %q", buf.String())
|
||||
}
|
||||
}
|
||||
|
||||
// The benchmarks compare a log line through slog directly against the same line behind RateLimited: logged with
|
||||
// nothing denied, denied, and logged after denials.
|
||||
|
||||
var (
|
||||
benchErr = errors.New("sendto: no buffer space available")
|
||||
benchAddr = netip.MustParseAddrPort("192.0.2.1:4242")
|
||||
)
|
||||
|
||||
func benchLogger() *slog.Logger {
|
||||
return NewLogger(io.Discard).With("localIndex", 1234, "remoteIndex", 5678)
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedBaseline(b *testing.B) {
|
||||
lg := benchLogger()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
lg.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedAllowed(b *testing.B) {
|
||||
lg, lim := benchLogger(), mustLimiter(b, 1, 0)
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedDenied(b *testing.B) {
|
||||
lg, lim := benchLogger(), mustLimiter(b, 1, time.Hour)
|
||||
lim.Allow()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkRateLimitedAfterDenied(b *testing.B) {
|
||||
lg, lim := benchLogger(), fakeLimiter{denied: 5, ok: true}
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
if l, ok := RateLimited(lg, lim); ok {
|
||||
l.Error("Failed to write outgoing packet", "error", benchErr, "udpAddr", benchAddr)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func mustLimiter(b *testing.B, burst int, every time.Duration) *ratelimit.Limiter {
|
||||
l, err := ratelimit.New(burst, every)
|
||||
if err != nil {
|
||||
b.Fatal(err)
|
||||
}
|
||||
return l
|
||||
}
|
||||
@@ -232,9 +232,11 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
retries: int64(c.GetInt("handshakes.retries", DefaultHandshakeRetries)),
|
||||
triggerBuffer: c.GetInt("handshakes.trigger_buffer", DefaultHandshakeTriggerBuffer),
|
||||
messageMetrics: messageMetrics,
|
||||
pq: pqHandshakeConfigFrom(c),
|
||||
}
|
||||
|
||||
handshakeManager := NewHandshakeManager(l, hostMap, lightHouse, udpConns[0], handshakeConfig)
|
||||
c.RegisterReloadCallback(handshakeManager.reloadPQ)
|
||||
lightHouse.handshakeTrigger = handshakeManager.trigger
|
||||
|
||||
ds, err := newDnsServerFromConfig(ctx, l, pki, hostMap, c)
|
||||
@@ -300,6 +302,7 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
}
|
||||
|
||||
var ifce *Interface
|
||||
var emitStats func()
|
||||
if !configTest {
|
||||
ifce, err = NewInterface(ctx, ifConfig)
|
||||
if err != nil {
|
||||
@@ -318,9 +321,12 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
go handshakeManager.Run(ctx)
|
||||
|
||||
punchy.Start(ctx, ifce, hostMap, lightHouse)
|
||||
|
||||
// On the stats server's loop, so the gauges follow the interval it accepted
|
||||
emitStats = ifce.statsEmitter()
|
||||
}
|
||||
|
||||
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest)
|
||||
stats, err := newStatsServerFromConfig(ctx, l, c, buildVersion, configTest, emitStats)
|
||||
if err != nil {
|
||||
return nil, util.ContextualizeIfNeeded("Failed to start stats emitter", err)
|
||||
}
|
||||
@@ -329,8 +335,6 @@ func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, dev
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
go ifce.emitStats(ctx, c.GetDuration("stats.interval", time.Second*10))
|
||||
|
||||
attachCommands(l, c, ssh, ifce)
|
||||
|
||||
networkChanges := udp.NewNetworkChangeMonitor(ctx, l, c)
|
||||
|
||||
+10
-7
@@ -160,9 +160,7 @@ func (f *Interface) readOutsidePackets(via ViaSender, packet []byte, rxc *rxCont
|
||||
case header.TestReply:
|
||||
// No-op, useful for the Roaming and connectionManager side-effects above
|
||||
case header.TestRequest:
|
||||
const maxCipherOverhead = 16 //todo we use this too often, needs a real importable const
|
||||
const maxOverhead = header.Len + header.Len + maxCipherOverhead + maxCipherOverhead
|
||||
if maxOverhead+len(out) > len(rxc.scratch) {
|
||||
if header.MaxOverhead+len(out) > len(rxc.scratch) {
|
||||
// A reply that cannot fit in scratch is dropped no matter the log level.
|
||||
if f.l.Enabled(context.Background(), slog.LevelDebug) {
|
||||
hostinfo.logger(f.l).Debug("dropping oversized test request", "payloadLen", len(out), "from", via)
|
||||
@@ -263,11 +261,16 @@ func (f *Interface) handleOutsideRelayPacket(hostinfo *HostInfo, via ViaSender,
|
||||
|
||||
// closeTunnel closes a tunnel locally, it does not send a closeTunnel packet to the remote
|
||||
func (f *Interface) closeTunnel(hostInfo *HostInfo) {
|
||||
final := f.hostMap.DeleteHostInfo(hostInfo)
|
||||
if final {
|
||||
// We no longer have any tunnels with this vpn addr, clear learned lighthouse state to lower memory usage
|
||||
f.lightHouse.DeleteVpnAddrs(hostInfo.vpnAddrs)
|
||||
// Hold the hostmap lock across both the delete and the lighthouse eviction,
|
||||
// to avoid a race with handshake completion.
|
||||
f.hostMap.Lock()
|
||||
defer f.hostMap.Unlock()
|
||||
if !f.hostMap.unlockedDeleteHostInfo(hostInfo) {
|
||||
return
|
||||
}
|
||||
|
||||
// We no longer have any tunnels with this vpn addr, clear learned lighthouse state to lower memory usage
|
||||
f.lightHouse.DeleteVpnAddrs(hostInfo.vpnAddrs)
|
||||
}
|
||||
|
||||
// sendCloseTunnel is a helper function to send a proper close tunnel packet to a remote
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
|
||||
"golang.org/x/sys/windows"
|
||||
"golang.org/x/sys/windows/registry"
|
||||
)
|
||||
|
||||
var tcpipInterfaceKeys = []string{
|
||||
`SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`,
|
||||
`SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`,
|
||||
}
|
||||
|
||||
// disableDNSRegistration prevents publishing overlay addresses in the host's
|
||||
// DNS records, where clients outside the overlay cannot reach them.
|
||||
// Failures are non-fatal so registry access cannot prevent tunnel creation.
|
||||
func disableDNSRegistration(l *slog.Logger, guid windows.GUID) {
|
||||
id := guid.String()
|
||||
for _, base := range tcpipInterfaceKeys {
|
||||
path := base + `\` + id
|
||||
if err := setDNSRegistrationValues(path); err != nil {
|
||||
l.Warn("Failed to disable DNS registration on the tun adapter", "error", err, "key", path)
|
||||
continue
|
||||
}
|
||||
l.Debug("Disabled DNS registration on the tun adapter", "key", path)
|
||||
}
|
||||
}
|
||||
|
||||
func setDNSRegistrationValues(path string) error {
|
||||
// The stack may not have created the adapter's interface key yet.
|
||||
k, _, err := registry.CreateKey(registry.LOCAL_MACHINE, path, registry.SET_VALUE)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open HKLM\\%s: %w", path, err)
|
||||
}
|
||||
defer k.Close()
|
||||
|
||||
// Neither RegistrationEnabled nor DisableDynamicUpdate alone reliably
|
||||
// prevents registration, so all three settings are required.
|
||||
values := []struct {
|
||||
name string
|
||||
data uint32
|
||||
}{
|
||||
{"RegistrationEnabled", 0},
|
||||
{"DisableDynamicUpdate", 1},
|
||||
{"MaxNumberOfAddressesToRegister", 0},
|
||||
}
|
||||
for _, v := range values {
|
||||
if err := k.SetDWordValue(v.name, v.data); err != nil {
|
||||
return fmt.Errorf("set %s: %w", v.name, err)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
+28
-4
@@ -50,7 +50,13 @@ func (r Route) String() string {
|
||||
|
||||
func makeRouteTree(l *slog.Logger, routes []Route, allowMTU bool) (*bart.Table[routing.Gateways], error) {
|
||||
routeTree := new(bart.Table[routing.Gateways])
|
||||
seen := make(map[netip.Prefix]bool, len(routes))
|
||||
for _, r := range routes {
|
||||
if seen[r.Cidr] {
|
||||
l.Warn("route is listed more than once, only the last entry's via is used", "route", r)
|
||||
}
|
||||
seen[r.Cidr] = true
|
||||
|
||||
if !allowMTU && r.MTU > 0 {
|
||||
l.Warn("route MTU is not supported on this platform",
|
||||
"goos", runtime.GOOS,
|
||||
@@ -98,7 +104,11 @@ func parseRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
mtu, ok := rMtu.(int)
|
||||
if !ok {
|
||||
mtu, err = strconv.Atoi(rMtu.(string))
|
||||
s, ok := rMtu.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, rMtu)
|
||||
}
|
||||
mtu, err = strconv.Atoi(s)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
@@ -174,7 +184,11 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
if rMtu, ok := m["mtu"]; ok {
|
||||
mtu, ok = rMtu.(int)
|
||||
if !ok {
|
||||
mtu, err = strconv.Atoi(rMtu.(string))
|
||||
s, ok := rMtu.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, rMtu)
|
||||
}
|
||||
mtu, err = strconv.Atoi(s)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.mtu in tun.unsafe_routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
@@ -192,10 +206,15 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
metric, ok := rMetric.(int)
|
||||
if !ok {
|
||||
_, err = strconv.ParseInt(rMetric.(string), 10, 32)
|
||||
s, ok := rMetric.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, rMetric)
|
||||
}
|
||||
n, err := strconv.ParseInt(s, 10, 32)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry %v.metric in tun.unsafe_routes is not an integer: %v", i+1, err)
|
||||
}
|
||||
metric = int(n)
|
||||
}
|
||||
|
||||
if metric < 0 || metric > math.MaxInt32 {
|
||||
@@ -248,10 +267,15 @@ func parseUnsafeRoutes(c *config.C, networks []netip.Prefix) ([]Route, error) {
|
||||
|
||||
gatewayWeight, ok := rGatewayWeight.(int)
|
||||
if !ok {
|
||||
_, err = strconv.ParseInt(rGatewayWeight.(string), 10, 32)
|
||||
s, ok := rGatewayWeight.(string)
|
||||
if !ok {
|
||||
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
|
||||
}
|
||||
w, err := strconv.ParseInt(s, 10, 32)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("entry .weight in tun.unsafe_routes[%v].via[%v] is not an integer", i+1, ig+1)
|
||||
}
|
||||
gatewayWeight = int(w)
|
||||
}
|
||||
|
||||
if gatewayWeight < 1 || gatewayWeight > math.MaxInt32 {
|
||||
|
||||
@@ -1,13 +1,17 @@
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -402,3 +406,115 @@ func Test_makeMultipathUnsafeRouteTree(t *testing.T) {
|
||||
routing.CalculateBucketsForGateways(expectedGateways)
|
||||
assert.ElementsMatch(t, expectedGateways, r)
|
||||
}
|
||||
|
||||
func Test_getMTU(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
|
||||
// unset
|
||||
assert.Equal(t, DefaultMTU, getMTU(l, c))
|
||||
|
||||
// the largest a relayed packet can carry in one underlay buffer
|
||||
require.Equal(t, udp.MTU, MaxMTU+header.MaxOverhead)
|
||||
c.Settings["tun"] = map[string]any{"mtu": MaxMTU}
|
||||
assert.Equal(t, MaxMTU, getMTU(l, c))
|
||||
|
||||
// too big is capped
|
||||
c.Settings["tun"] = map[string]any{"mtu": 9000}
|
||||
assert.Equal(t, MaxMTU, getMTU(l, c))
|
||||
}
|
||||
|
||||
func Test_getAllRoutesFromConfigCapsMTU(t *testing.T) {
|
||||
l := test.NewLogger()
|
||||
c := config.NewC(l)
|
||||
c.Settings["tun"] = map[string]any{
|
||||
"routes": []any{
|
||||
map[string]any{"mtu": "9000", "route": "10.0.0.0/29"},
|
||||
map[string]any{"mtu": "1300", "route": "10.0.0.8/29"},
|
||||
},
|
||||
"unsafe_routes": []any{
|
||||
map[string]any{"via": "127.0.0.1", "mtu": "9000", "route": "1.0.0.0/29"},
|
||||
},
|
||||
}
|
||||
|
||||
changed, routes, err := getAllRoutesFromConfig(l, c, []netip.Prefix{netip.MustParsePrefix("10.0.0.0/24")}, true)
|
||||
require.NoError(t, err)
|
||||
assert.True(t, changed)
|
||||
|
||||
mtus := map[string]int{}
|
||||
for _, r := range routes {
|
||||
mtus[r.Cidr.String()] = r.MTU
|
||||
}
|
||||
assert.Equal(t, map[string]int{"10.0.0.0/29": MaxMTU, "10.0.0.8/29": 1300, "1.0.0.0/29": MaxMTU}, mtus)
|
||||
}
|
||||
|
||||
// The route tree keeps one entry per CIDR, so a CIDR listed twice only routes by the last one. Say so instead of
|
||||
// letting the earlier via, or on Windows the earlier metric, quietly lose
|
||||
func Test_makeRouteTree_WarnsOnDuplicate(t *testing.T) {
|
||||
buf := &bytes.Buffer{}
|
||||
l := test.NewLoggerWithOutput(buf)
|
||||
via := func(s string) routing.Gateways {
|
||||
return routing.Gateways{routing.NewGateway(netip.MustParseAddr(s), 1)}
|
||||
}
|
||||
cidr := netip.MustParsePrefix("10.251.1.0/24")
|
||||
|
||||
_, err := makeRouteTree(l, []Route{
|
||||
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
|
||||
{Cidr: netip.MustParsePrefix("10.251.2.0/24"), Via: via("10.250.0.2"), Install: true},
|
||||
}, false)
|
||||
require.NoError(t, err)
|
||||
assert.Empty(t, buf.String())
|
||||
|
||||
tree, err := makeRouteTree(l, []Route{
|
||||
{Cidr: cidr, Via: via("10.250.0.2"), Install: true, Metric: 100},
|
||||
{Cidr: cidr, Via: via("10.250.0.3"), Install: true, Metric: 200},
|
||||
}, false)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 1, strings.Count(buf.String(), "route is listed more than once, only the last entry's via is used"))
|
||||
gw, ok := tree.Lookup(netip.MustParseAddr("10.251.1.1"))
|
||||
require.True(t, ok)
|
||||
assert.Equal(t, netip.MustParseAddr("10.250.0.3"), gw[0].Addr(), "the last entry wins")
|
||||
}
|
||||
|
||||
// A quoted metric or weight is a number written as a string, it means that number. Anything else is an error, not a
|
||||
// panic
|
||||
func Test_parseUnsafeRoutes_QuotedNumbers(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
n := netip.MustParsePrefix("10.0.0.1/24")
|
||||
route := func(metric, weight any) {
|
||||
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{
|
||||
"route": "1.0.0.0/8",
|
||||
"metric": metric,
|
||||
"via": []any{map[string]any{"gateway": "10.0.0.2", "weight": weight}},
|
||||
}}}
|
||||
}
|
||||
|
||||
route("100", "5")
|
||||
routes, err := parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.NoError(t, err)
|
||||
require.Len(t, routes, 1)
|
||||
assert.Equal(t, 100, routes[0].Metric)
|
||||
assert.Equal(t, "{addr: 10.0.0.2, weight: 5}", routes[0].Via[0].String())
|
||||
|
||||
route(1.5, 1)
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.metric in tun.unsafe_routes is not an integer: 1.5")
|
||||
|
||||
route(1, true)
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry .weight in tun.unsafe_routes[1].via[1] is not an integer")
|
||||
}
|
||||
|
||||
// An mtu that is neither a number nor a quoted one is an error, not a panic
|
||||
func Test_parseRoutes_MTUNotANumber(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
n := netip.MustParsePrefix("10.0.0.1/24")
|
||||
|
||||
c.Settings["tun"] = map[string]any{"routes": []any{map[string]any{"route": "1.0.0.0/8", "mtu": 1500.5}}}
|
||||
_, err := parseRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.mtu in tun.routes is not an integer: 1500.5")
|
||||
|
||||
c.Settings["tun"] = map[string]any{"unsafe_routes": []any{map[string]any{"route": "1.0.0.0/8", "via": "10.0.0.2", "mtu": 1500.5}}}
|
||||
_, err = parseUnsafeRoutes(c, []netip.Prefix{n})
|
||||
require.EqualError(t, err, "entry 1.mtu in tun.unsafe_routes is not an integer: 1500.5")
|
||||
}
|
||||
+24
-2
@@ -7,11 +7,27 @@ import (
|
||||
"net/netip"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/header"
|
||||
"github.com/slackhq/nebula/udp"
|
||||
"github.com/slackhq/nebula/util"
|
||||
)
|
||||
|
||||
const DefaultMTU = 1300
|
||||
|
||||
// MaxMTU is the largest tun.mtu, or route mtu, the underlay can carry.
|
||||
// Every underlay buffer is udp.MTU bytes, and a relayed packet adds header.MaxOverhead to its plaintext.
|
||||
const MaxMTU = udp.MTU - header.MaxOverhead
|
||||
|
||||
// getMTU reads tun.mtu, capping a value too big for the underlay to carry.
|
||||
func getMTU(l *slog.Logger, c *config.C) int {
|
||||
mtu := c.GetInt("tun.mtu", DefaultMTU)
|
||||
if mtu > MaxMTU {
|
||||
l.Warn("tun.mtu is too big for the underlay to carry, capping it", "mtu", mtu, "maxMTU", MaxMTU)
|
||||
return MaxMTU
|
||||
}
|
||||
return mtu
|
||||
}
|
||||
|
||||
type NameError struct {
|
||||
Name string
|
||||
Underlying error
|
||||
@@ -27,7 +43,7 @@ type DeviceFactory func(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix,
|
||||
func NewDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
|
||||
switch {
|
||||
case c.GetBool("tun.disabled", false):
|
||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 500), c.GetBool("stats.message_metrics", false), l)
|
||||
tun := newDisabledTun(vpnNetworks, c.GetInt("tun.tx_queue", 5000), c.GetBool("stats.message_metrics", false), l)
|
||||
return tun, nil
|
||||
|
||||
default:
|
||||
@@ -41,7 +57,7 @@ func NewFdDeviceFromConfig(fd *int) DeviceFactory {
|
||||
}
|
||||
}
|
||||
|
||||
func getAllRoutesFromConfig(c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
|
||||
func getAllRoutesFromConfig(l *slog.Logger, c *config.C, vpnNetworks []netip.Prefix, initial bool) (bool, []Route, error) {
|
||||
if !initial && !c.HasChanged("tun.routes") && !c.HasChanged("tun.unsafe_routes") {
|
||||
return false, nil, nil
|
||||
}
|
||||
@@ -57,6 +73,12 @@ func getAllRoutesFromConfig(c *config.C, vpnNetworks []netip.Prefix, initial boo
|
||||
}
|
||||
|
||||
routes = append(routes, unsafeRoutes...)
|
||||
for i, r := range routes {
|
||||
if r.MTU > MaxMTU {
|
||||
l.Warn("route mtu is too big for the underlay to carry, capping it", "route", r.Cidr, "mtu", r.MTU, "maxMTU", MaxMTU)
|
||||
routes[i].MTU = MaxMTU
|
||||
}
|
||||
}
|
||||
return true, routes, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -68,7 +68,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -126,7 +126,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
f: os.NewFile(uintptr(fd), ""),
|
||||
Device: name,
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
DefaultMTU: getMTU(l, c),
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -167,7 +167,7 @@ func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip
|
||||
f: file,
|
||||
Device: utunNameFromFd(deviceFd),
|
||||
vpnNetworks: vpnNetworks,
|
||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
DefaultMTU: getMTU(l, c),
|
||||
hostOwned: true,
|
||||
l: l,
|
||||
}
|
||||
@@ -350,7 +350,7 @@ func (t *tun) activate6(network netip.Prefix) error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -370,7 +370,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
t := &tun{
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
MTU: getMTU(l, c),
|
||||
l: l,
|
||||
fd: fd,
|
||||
shutdownR: shutdownR,
|
||||
@@ -510,7 +510,7 @@ func (t *tun) setMTU() error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
+1
-1
@@ -68,7 +68,7 @@ func (t *tun) Activate() error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
+13
-4
@@ -221,7 +221,7 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
|
||||
vnetHdr: vnetHdr,
|
||||
offloadFlags: offloadFlags,
|
||||
vpnNetworks: vpnNetworks,
|
||||
TXQueueLen: c.GetInt("tun.tx_queue", 500),
|
||||
TXQueueLen: c.GetInt("tun.tx_queue", 5000),
|
||||
useSystemRoutes: c.GetBool("tun.use_system_route_table", false),
|
||||
useSystemRoutesBufferSize: c.GetInt("tun.use_system_route_table_buffer_size", 0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
@@ -244,7 +244,7 @@ func newTunGeneric(c *config.C, l *slog.Logger, fd int, vnetHdr bool, offloadFla
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
routeChange, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
routeChange, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -253,6 +253,15 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Only the mtu changed. The routes are the same, parse them again so the ones without their own mtu pick up the
|
||||
// new default. Without this an mtu change would remove them all
|
||||
if !routeChange {
|
||||
_, routes, err = getAllRoutesFromConfig(t.l, c, t.vpnNetworks, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
routeTree, err := makeRouteTree(t.l, routes, true)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -267,14 +276,14 @@ func (t *tun) reload(c *config.C, initial bool) error {
|
||||
|
||||
oldDefaultMTU := t.DefaultMTU
|
||||
oldMaxMTU := t.MaxMTU
|
||||
newDefaultMTU := c.GetInt("tun.mtu", DefaultMTU)
|
||||
newDefaultMTU := getMTU(t.l, c)
|
||||
newMaxMTU := newDefaultMTU
|
||||
for i, r := range routes {
|
||||
if r.MTU == 0 {
|
||||
routes[i].MTU = newDefaultMTU
|
||||
}
|
||||
|
||||
if r.MTU > t.MaxMTU {
|
||||
if r.MTU > newMaxMTU {
|
||||
newMaxMTU = r.MTU
|
||||
}
|
||||
}
|
||||
|
||||
@@ -99,7 +99,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
fd: fd,
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
MTU: getMTU(l, c),
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -340,7 +340,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -90,7 +90,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*t
|
||||
fd: fd,
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
MTU: getMTU(l, c),
|
||||
l: l,
|
||||
}
|
||||
|
||||
@@ -319,7 +319,7 @@ func (t *tun) doIoctlByName(ctl uintptr, value uint32) error {
|
||||
}
|
||||
|
||||
func (t *tun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
//go:build !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"net/netip"
|
||||
"testing"
|
||||
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/slackhq/nebula/routing"
|
||||
"github.com/slackhq/nebula/test"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// Only tun.mtu changes. The system calls fail without a real device, what matters is the routes nebula keeps
|
||||
func TestReloadMTUOnlyKeepsRoutes(t *testing.T) {
|
||||
routes := " unsafe_routes:\n - route: 192.168.100.0/24\n via: 10.1.0.1\n"
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n"+routes))
|
||||
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true))
|
||||
|
||||
require.NoError(t, c.ReloadConfigString("tun:\n mtu: 1400\n"+routes))
|
||||
_ = tn.reload(c, false)
|
||||
|
||||
got := *tn.Routes.Load()
|
||||
require.Len(t, got, 1)
|
||||
assert.Equal(t, netip.MustParsePrefix("192.168.100.0/24"), got[0].Cidr)
|
||||
assert.Equal(t, 1400, got[0].MTU)
|
||||
assert.Equal(t, 1400, tn.DefaultMTU)
|
||||
}
|
||||
|
||||
// The device mtu has to fit the largest route mtu, wherever it sits in the list
|
||||
func TestReloadMaxMTUIsTheLargestRoute(t *testing.T) {
|
||||
c := config.NewC(test.NewLogger())
|
||||
require.NoError(t, c.LoadString("tun:\n mtu: 1300\n unsafe_routes:\n"+
|
||||
" - route: 192.168.100.0/24\n via: 10.1.0.1\n mtu: 1500\n"+
|
||||
" - route: 192.168.101.0/24\n via: 10.1.0.1\n mtu: 1400\n"))
|
||||
|
||||
tn := &tun{
|
||||
l: test.NewLogger(),
|
||||
vpnNetworks: []netip.Prefix{netip.MustParsePrefix("10.1.0.2/24")},
|
||||
ioctlFd: ^uintptr(0),
|
||||
routesFromSystem: map[netip.Prefix]routing.Gateways{},
|
||||
}
|
||||
require.NoError(t, tn.reload(c, true))
|
||||
assert.Equal(t, 1500, tn.MaxMTU)
|
||||
assert.Equal(t, 1300, tn.DefaultMTU)
|
||||
}
|
||||
@@ -31,7 +31,7 @@ type TestTun struct {
|
||||
}
|
||||
|
||||
func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*TestTun, error) {
|
||||
_, routes, err := getAllRoutesFromConfig(c, vpnNetworks, true)
|
||||
_, routes, err := getAllRoutesFromConfig(l, c, vpnNetworks, true)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
+80
-6
@@ -4,6 +4,7 @@ package overlay
|
||||
|
||||
import (
|
||||
"crypto"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/netip"
|
||||
@@ -75,7 +76,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
t := &winTun{
|
||||
Device: deviceName,
|
||||
vpnNetworks: vpnNetworks,
|
||||
MTU: c.GetInt("tun.mtu", DefaultMTU),
|
||||
MTU: getMTU(l, c),
|
||||
guid: *guid,
|
||||
networkCategory: cat,
|
||||
setCategory: setCat,
|
||||
@@ -104,6 +105,9 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
}
|
||||
t.tun = tunDevice.(*wintun.NativeTun)
|
||||
|
||||
// Disable registration before Activate assigns addresses and triggers it.
|
||||
disableDNSRegistration(l, *guid)
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
err := t.reload(c, false)
|
||||
if err != nil {
|
||||
@@ -115,7 +119,7 @@ func newTun(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, _ bool) (*w
|
||||
}
|
||||
|
||||
func (t *winTun) reload(c *config.C, initial bool) error {
|
||||
change, routes, err := getAllRoutesFromConfig(c, t.vpnNetworks, initial)
|
||||
change, routes, err := getAllRoutesFromConfig(t.l, c, t.vpnNetworks, initial)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -135,7 +139,7 @@ func (t *winTun) reload(c *config.C, initial bool) error {
|
||||
|
||||
if !initial {
|
||||
// Remove first, if the system removes a wanted route hopefully it will be re-added next
|
||||
err := t.removeRoutes(findRemovedRoutes(routes, *oldRoutes))
|
||||
err := t.removeRoutes(findRemovedSystemRoutes(routes, *oldRoutes))
|
||||
if err != nil {
|
||||
util.LogWithContextIfNeeded("Failed to remove routes", err, t.l)
|
||||
}
|
||||
@@ -184,17 +188,27 @@ func (t *winTun) addRoutes(logErrors bool) error {
|
||||
foundDefault4 := false
|
||||
carriesV6 := slices.ContainsFunc(t.vpnNetworks, func(p netip.Prefix) bool { return p.Addr().Is6() })
|
||||
|
||||
for _, r := range routes {
|
||||
// A CIDR listed twice routes by its last entry, install only that one or each reload would flip between them. The
|
||||
// same rule as systemRoutes
|
||||
last := make(map[netip.Prefix]int, len(routes))
|
||||
for i, r := range routes {
|
||||
last[r.Cidr] = i
|
||||
}
|
||||
|
||||
for i, r := range routes {
|
||||
if len(r.Via) == 0 || !r.Install {
|
||||
// We don't allow route MTUs so only install routes with a via
|
||||
continue
|
||||
}
|
||||
if last[r.Cidr] != i {
|
||||
continue
|
||||
}
|
||||
|
||||
// A v6 unsafe_route is legal under a v4-only cert; uninstalled ones put nothing on the adapter.
|
||||
carriesV6 = carriesV6 || r.Cidr.Addr().Is6()
|
||||
|
||||
// Add our unsafe route as an on-link route to the nebula tun device.
|
||||
err := luid.AddRoute(r.Cidr, unspecifiedNextHop(r.Cidr), uint32(r.Metric))
|
||||
result, err := addRoute(luid, r)
|
||||
if err != nil {
|
||||
retErr := util.NewContextualError("Failed to add route", map[string]any{"route": r}, err)
|
||||
if logErrors {
|
||||
@@ -204,7 +218,12 @@ func (t *winTun) addRoutes(logErrors bool) error {
|
||||
return retErr
|
||||
}
|
||||
} else {
|
||||
t.l.Info("Added route", "route", r)
|
||||
switch result {
|
||||
case routeAdded:
|
||||
t.l.Info("Added route", "route", r)
|
||||
case routeMetricUpdated:
|
||||
t.l.Info("Updated route metric", "route", r)
|
||||
}
|
||||
}
|
||||
|
||||
if !foundDefault4 {
|
||||
@@ -316,6 +335,61 @@ func (t *winTun) Close() error {
|
||||
return t.tun.Close()
|
||||
}
|
||||
|
||||
// systemRoutes maps each CIDR to the route that puts it in the system table. A CIDR's last entry decides, including
|
||||
// one that says not to install it
|
||||
func systemRoutes(routes []Route) map[netip.Prefix]Route {
|
||||
out := make(map[netip.Prefix]Route, len(routes))
|
||||
for _, r := range routes {
|
||||
if len(r.Via) > 0 && r.Install {
|
||||
out[r.Cidr] = r
|
||||
} else {
|
||||
delete(out, r.Cidr)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// findRemovedSystemRoutes is the routes to delete from the system table. Windows deletes by destination and next hop,
|
||||
// so only a CIDR nothing installs anymore goes, a changed metric is set on the route in place by addRoute
|
||||
func findRemovedSystemRoutes(newRoutes, oldRoutes []Route) []Route {
|
||||
keep := systemRoutes(newRoutes)
|
||||
var removed []Route
|
||||
for _, r := range systemRoutes(oldRoutes) {
|
||||
if _, ok := keep[r.Cidr]; !ok {
|
||||
removed = append(removed, r)
|
||||
}
|
||||
}
|
||||
return removed
|
||||
}
|
||||
|
||||
type routeResult int
|
||||
|
||||
const (
|
||||
routeAdded routeResult = iota
|
||||
routeMetricUpdated
|
||||
routeAlreadyInstalled
|
||||
)
|
||||
|
||||
// addRoute installs r on the interface. A reload re-adds every route to catch any the system dropped, and Windows
|
||||
// refuses one it has with the same destination and next hop whatever its metric. One that is there with another
|
||||
// metric, ours from before a metric change or someone else's, is brought to ours in place
|
||||
func addRoute(luid winipcfg.LUID, r Route) (routeResult, error) {
|
||||
nextHop := unspecifiedNextHop(r.Cidr)
|
||||
err := luid.AddRoute(r.Cidr, nextHop, uint32(r.Metric))
|
||||
if !errors.Is(err, windows.ERROR_OBJECT_ALREADY_EXISTS) {
|
||||
return routeAdded, err
|
||||
}
|
||||
row, err := luid.Route(r.Cidr, nextHop)
|
||||
if err != nil {
|
||||
return routeAlreadyInstalled, err
|
||||
}
|
||||
if row.Metric != uint32(r.Metric) {
|
||||
row.Metric = uint32(r.Metric)
|
||||
return routeMetricUpdated, row.Set()
|
||||
}
|
||||
return routeAlreadyInstalled, nil
|
||||
}
|
||||
|
||||
func unspecifiedNextHop(p netip.Prefix) netip.Addr {
|
||||
if p.Addr().Is4() {
|
||||
return netip.IPv4Unspecified()
|
||||
|
||||
@@ -0,0 +1,168 @@
|
||||
//go:build windows && !e2e_testing
|
||||
|
||||
package overlay
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"net/netip"
|
||||
"strings"
|
||||
"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/windows"
|
||||
"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
|
||||
)
|
||||
|
||||
type routeTest struct {
|
||||
c *config.C
|
||||
tun *winTun
|
||||
luid winipcfg.LUID
|
||||
log *bytes.Buffer
|
||||
}
|
||||
|
||||
// newRouteTest makes a wintun device of its own, before installing tun.unsafe_routes from cfg
|
||||
func newRouteTest(t *testing.T, cfg string) *routeTest {
|
||||
t.Helper()
|
||||
if !windows.GetCurrentProcessToken().IsElevated() {
|
||||
t.Skip("creating a wintun device needs an elevated process")
|
||||
}
|
||||
if err := checkWinTunExists(); err != nil {
|
||||
t.Skipf("wintun.dll is not where nebula looks for it: %v", err)
|
||||
}
|
||||
rt := &routeTest{log: &bytes.Buffer{}}
|
||||
l := test.NewLoggerWithOutput(rt.log)
|
||||
rt.c = config.NewC(l)
|
||||
require.NoError(t, rt.c.LoadString(cfg))
|
||||
var err error
|
||||
rt.tun, err = newTun(rt.c, l, []netip.Prefix{netip.MustParsePrefix("10.250.0.1/24")}, false)
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = rt.tun.Close() })
|
||||
rt.luid = winipcfg.LUID(rt.tun.tun.LUID())
|
||||
return rt
|
||||
}
|
||||
|
||||
func (rt *routeTest) metric(t *testing.T, cidr string) uint32 {
|
||||
t.Helper()
|
||||
p := netip.MustParsePrefix(cidr)
|
||||
row, err := rt.luid.Route(p, unspecifiedNextHop(p))
|
||||
require.NoError(t, err)
|
||||
return row.Metric
|
||||
}
|
||||
|
||||
func unsafeRoutes(routes ...string) string {
|
||||
var b strings.Builder
|
||||
b.WriteString("tun:\n dev: nebroutetest\n unsafe_routes:\n")
|
||||
// cidr[@metric][!], the ! for install: false
|
||||
for _, r := range routes {
|
||||
r, noInstall := strings.CutSuffix(r, "!")
|
||||
cidr, metric, _ := strings.Cut(r, "@")
|
||||
fmt.Fprintf(&b, " - route: %s\n via: 10.250.0.2\n", cidr)
|
||||
if metric != "" {
|
||||
fmt.Fprintf(&b, " metric: %s\n", metric)
|
||||
}
|
||||
if noInstall {
|
||||
b.WriteString(" install: false\n")
|
||||
}
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// A reload that adds a route re-adds the ones already installed, Windows refusing those as already there isn't a failure
|
||||
func TestWinTun_ReloadKeepsInstalledRoutes(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a, b)))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
rt.metric(t, a)
|
||||
rt.metric(t, b)
|
||||
})
|
||||
}
|
||||
|
||||
// Windows calls a route the same by destination and next hop, so a changed metric is set on the installed route in
|
||||
// place rather than deleted and added, which would leave a moment with no route
|
||||
func TestWinTun_ReloadMetricChangeApplies(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
require.Equal(t, uint32(100), rt.metric(t, a))
|
||||
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
})
|
||||
}
|
||||
|
||||
// A route someone else put on the device with another metric is brought to ours, at startup too
|
||||
func TestWinTun_ForeignRouteGetsOurMetric(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
p := netip.MustParsePrefix(a)
|
||||
require.NoError(t, rt.luid.AddRoute(p, unspecifiedNextHop(p), 50))
|
||||
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
assert.Equal(t, uint32(100), rt.metric(t, a))
|
||||
assert.Contains(t, rt.log.String(), "level=INFO msg=\"Updated route metric\"")
|
||||
})
|
||||
}
|
||||
|
||||
// A CIDR listed twice is installed once, by its last entry, and reloads leave it there instead of flipping between the
|
||||
// two metrics
|
||||
func TestWinTun_DuplicateCidrInstallsTheLastEntry(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@100", a+"@200", b)))
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
assert.NotContains(t, rt.log.String(), "Updated route metric")
|
||||
assert.NotContains(t, rt.log.String(), "Failed to add route")
|
||||
})
|
||||
}
|
||||
|
||||
// Dropping the duplicate that wasn't installed leaves the installed route alone. Windows deletes by destination and
|
||||
// next hop, deleting the dropped one would take the live route with it
|
||||
func TestWinTun_DroppingAnUninstalledDuplicateKeepsTheRoute(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100", a+"@200"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
|
||||
require.NoError(t, rt.c.ReloadConfigString(unsafeRoutes(a+"@200")))
|
||||
assert.NotContains(t, rt.log.String(), "Removed route")
|
||||
assert.Equal(t, uint32(200), rt.metric(t, a))
|
||||
})
|
||||
}
|
||||
|
||||
// A reload ends where a fresh start with the same config would, a CIDR whose last entry says not to install it is
|
||||
// removed
|
||||
func TestWinTun_ReloadMatchesAFreshStart(t *testing.T) {
|
||||
forFamilies(t, func(t *testing.T, a, b string) {
|
||||
cidr := netip.MustParsePrefix(a)
|
||||
routes := unsafeRoutes(a+"@100", a+"@100!")
|
||||
|
||||
fresh := newRouteTest(t, routes)
|
||||
require.NoError(t, fresh.tun.Activate())
|
||||
_, err := fresh.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||
require.Error(t, err, "a fresh start installed it")
|
||||
require.NoError(t, fresh.tun.Close())
|
||||
|
||||
rt := newRouteTest(t, unsafeRoutes(a+"@100"))
|
||||
require.NoError(t, rt.tun.Activate())
|
||||
require.NoError(t, rt.c.ReloadConfigString(routes))
|
||||
_, err = rt.luid.Route(cidr, unspecifiedNextHop(cidr))
|
||||
assert.Error(t, err, "the reload left it installed")
|
||||
})
|
||||
}
|
||||
|
||||
// forFamilies runs f with two unsafe_routes CIDRs of each address family, the tun's own network stays IPv4
|
||||
func forFamilies(t *testing.T, f func(t *testing.T, a, b string)) {
|
||||
t.Run("ipv4", func(t *testing.T) { f(t, "10.251.1.0/24", "10.251.2.0/24") })
|
||||
t.Run("ipv6", func(t *testing.T) { f(t, "fd00:251:1::/64", "fd00:251:2::/64") })
|
||||
}
|
||||
@@ -0,0 +1,91 @@
|
||||
package ratelimit
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"math"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Limiter is a token bucket: `burst` calls are allowed at once, then one more per `every`.
|
||||
// It counts the calls it denies and hands that count to the next allowed call.
|
||||
//
|
||||
// The budget belongs to the Limiter instance.
|
||||
// Every Allow that returns true spends from it, whatever the caller then does.
|
||||
//
|
||||
// Time follows Go's monotonic clock.
|
||||
//
|
||||
// Create one Limiter for each thing you want to limit,
|
||||
// sharing one between unrelated events lets the noisy one starve the quiet one.
|
||||
//
|
||||
// Check Allow before doing the work being limited, so a denied call stays cheap:
|
||||
//
|
||||
// if denied, ok := probeLimiter.Allow(); ok {
|
||||
// sendProbe()
|
||||
// probesDenied.Inc(int64(denied))
|
||||
// }
|
||||
//
|
||||
// For log lines use logging.RateLimited, which attaches the denied count to the logger as "suppressed".
|
||||
type Limiter struct {
|
||||
every int64
|
||||
slack int64
|
||||
tat atomic.Int64
|
||||
denied atomic.Uint64
|
||||
}
|
||||
|
||||
// maxSpan bounds `burst` * `every` to half of int64, leaving the other half for process uptime so the bucket
|
||||
// math can't overflow.
|
||||
const maxSpan = math.MaxInt64 / 2
|
||||
|
||||
// New returns a Limiter allowing `burst` calls at once and one more per `every`.
|
||||
// A `burst` under 1 is 1, and an `every` of 0 or less never limits.
|
||||
// It returns an error if `burst` * `every` is over about 146 years.
|
||||
func New(burst int, every time.Duration) (*Limiter, error) {
|
||||
l := &Limiter{}
|
||||
if every > 0 {
|
||||
burst = max(burst, 1)
|
||||
if int64(burst) > maxSpan/int64(every) {
|
||||
return nil, fmt.Errorf("ratelimit: burst %d * every %v is too long", burst, every)
|
||||
}
|
||||
l.every = int64(every)
|
||||
l.slack = int64(burst-1) * l.every
|
||||
}
|
||||
return l, nil
|
||||
}
|
||||
|
||||
var monoStart = time.Now()
|
||||
|
||||
func monoNow() int64 { return int64(time.Since(monoStart)) }
|
||||
|
||||
// Allow reports whether this call is allowed.
|
||||
// If a token is available it spends it and returns the calls denied since the last allowed one, and true.
|
||||
// Otherwise it returns 0 and false, and counts the denial.
|
||||
// A nil Limiter allows everything.
|
||||
func (l *Limiter) Allow() (uint64, bool) {
|
||||
if l == nil {
|
||||
return 0, true
|
||||
}
|
||||
return l.allow(monoNow())
|
||||
}
|
||||
|
||||
// allow is Allow at a given monotonic time.
|
||||
func (l *Limiter) allow(now int64) (uint64, bool) {
|
||||
// Concurrent Allow calls read the clock before racing for the bucket, so one can see a time another already spent
|
||||
// past and be denied. An unlimited Limiter must never deny, so it skips the bucket.
|
||||
if l.every == 0 {
|
||||
return 0, true
|
||||
}
|
||||
|
||||
for {
|
||||
tat := l.tat.Load()
|
||||
next := max(tat, now)
|
||||
if next-now > l.slack {
|
||||
l.denied.Add(1)
|
||||
return 0, false
|
||||
}
|
||||
|
||||
if l.tat.CompareAndSwap(tat, next+l.every) {
|
||||
return l.denied.Swap(0), true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,264 @@
|
||||
package ratelimit
|
||||
|
||||
import (
|
||||
"math"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func mustLimiter(t testing.TB, burst int, every time.Duration) *Limiter {
|
||||
t.Helper()
|
||||
l, err := New(burst, every)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return l
|
||||
}
|
||||
|
||||
func TestLimiterBurstAndRefill(t *testing.T) {
|
||||
l, now := mustLimiter(t, 3, time.Second), int64(0)
|
||||
|
||||
for i := 0; i < 3; i++ {
|
||||
if n, ok := l.allow(now); !ok || n != 0 {
|
||||
t.Fatalf("burst line %d: ok=%v denied=%d", i, ok, n)
|
||||
}
|
||||
}
|
||||
for i := 0; i < 5; i++ {
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatalf("line %d past the burst logged", i)
|
||||
}
|
||||
}
|
||||
|
||||
now += int64(time.Second)
|
||||
if n, ok := l.allow(now); !ok || n != 5 {
|
||||
t.Fatalf("after one refill: ok=%v denied=%d, want true 5", ok, n)
|
||||
}
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatal("one refill earned more than one line")
|
||||
}
|
||||
|
||||
// A long quiet spell refills to burst, not past it, and the count reported above does not carry over.
|
||||
now += int64(time.Hour)
|
||||
for i, want := range []uint64{1, 0, 0} {
|
||||
if n, ok := l.allow(now); !ok || n != want {
|
||||
t.Fatalf("refilled line %d: ok=%v denied=%d, want true %d", i, ok, n, want)
|
||||
}
|
||||
}
|
||||
if _, ok := l.allow(now); ok {
|
||||
t.Fatal("bucket refilled past burst")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterBounds(t *testing.T) {
|
||||
for _, every := range []time.Duration{0, -time.Second} {
|
||||
l := mustLimiter(t, 1, every)
|
||||
for i := 0; i < 100; i++ {
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatalf("every=%v limited line %d", every, i)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
l := mustLimiter(t, 0, time.Second)
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatal("burst 0 should allow one line")
|
||||
}
|
||||
if _, ok := l.allow(0); ok {
|
||||
t.Fatal("burst 0 should allow only one line")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterOverflow(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
burst int
|
||||
every time.Duration
|
||||
}{
|
||||
{math.MaxInt, time.Second},
|
||||
{1, math.MaxInt64},
|
||||
{2, maxSpan/2 + 1},
|
||||
} {
|
||||
if _, err := New(c.burst, c.every); err == nil {
|
||||
t.Fatalf("burst %d every %d should not fit", c.burst, c.every)
|
||||
}
|
||||
}
|
||||
|
||||
l := mustLimiter(t, 2, maxSpan/2)
|
||||
for i := 0; i < 2; i++ {
|
||||
if _, ok := l.allow(0); !ok {
|
||||
t.Fatalf("the largest span should allow its burst, denied call %d", i)
|
||||
}
|
||||
}
|
||||
if _, ok := l.allow(0); ok {
|
||||
t.Fatal("the largest span allowed past its burst")
|
||||
}
|
||||
}
|
||||
|
||||
// Concurrent callers read the clock at slightly different times, which must not limit a Limiter that never limits.
|
||||
func TestLimiterUnlimitedConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 1, 0)
|
||||
|
||||
var denied atomic.Int64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 10000; j++ {
|
||||
if _, ok := l.Allow(); !ok {
|
||||
denied.Add(1)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if got := denied.Load(); got != 0 {
|
||||
t.Fatalf("denied %d lines", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterNil(t *testing.T) {
|
||||
var l *Limiter
|
||||
for i := 0; i < 10; i++ {
|
||||
if _, ok := l.Allow(); !ok {
|
||||
t.Fatal("nil limiter limited")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimiterConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 10, time.Hour)
|
||||
|
||||
var allowed atomic.Int64
|
||||
var reported atomic.Uint64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 1000; j++ {
|
||||
if n, ok := l.allow(0); ok {
|
||||
allowed.Add(1)
|
||||
reported.Add(n)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if got := allowed.Load(); got != 10 {
|
||||
t.Fatalf("allowed %d lines, want the burst of 10", got)
|
||||
}
|
||||
// An allowed call that lands after some denials reports them, so the rest are still pending.
|
||||
if got := reported.Load() + l.denied.Load(); got != 16*1000-10 {
|
||||
t.Fatalf("denied %d, want %d", got, 16*1000-10)
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowAllowed(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Nanosecond)
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
l.tat.Store(0)
|
||||
l.Allow()
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowDenied(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Hour)
|
||||
l.Allow()
|
||||
b.ReportAllocs()
|
||||
for i := 0; i < b.N; i++ {
|
||||
l.Allow()
|
||||
}
|
||||
}
|
||||
|
||||
func BenchmarkAllowDeniedParallel(b *testing.B) {
|
||||
l := mustLimiter(b, 1, time.Hour)
|
||||
l.Allow()
|
||||
b.ReportAllocs()
|
||||
b.RunParallel(func(pb *testing.PB) {
|
||||
for pb.Next() {
|
||||
l.Allow()
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// FuzzLimiter checks the bucket against its exact definition over arbitrary call timings.
|
||||
// A call is denied if and only if some allowed call a would leave too many calls for the time since a:
|
||||
// (allowed calls since a, plus this one) * every > burst * every + (now - a).
|
||||
// Every denied call must also be reported exactly once, by a later allowed call or still pending.
|
||||
func FuzzLimiter(f *testing.F) {
|
||||
f.Add(uint8(3), uint16(1000), []byte{0, 0, 0, 0, 16, 0, 0, 200, 1, 1, 1, 15, 17, 0})
|
||||
f.Add(uint8(1), uint16(1), []byte{0, 16, 15, 16, 0, 255, 0, 0})
|
||||
f.Fuzz(func(t *testing.T, burst uint8, everyUs uint16, steps []byte) {
|
||||
if len(steps) > 512 {
|
||||
steps = steps[:512]
|
||||
}
|
||||
b := int64(burst%16) + 1
|
||||
every := int64(everyUs%1000+1) * int64(time.Microsecond)
|
||||
l := mustLimiter(t, int(b), time.Duration(every))
|
||||
|
||||
var now int64
|
||||
var allowedAt []int64
|
||||
var denied, reported uint64
|
||||
for _, s := range steps {
|
||||
// Each step advances by a sixteenth of every, so timings land on and around the refill.
|
||||
now += int64(s) * every / 16
|
||||
|
||||
over := false
|
||||
for i, a := range allowedAt {
|
||||
if int64(len(allowedAt)-i+1)*every > b*every+now-a {
|
||||
over = true
|
||||
break
|
||||
}
|
||||
}
|
||||
|
||||
n, ok := l.allow(now)
|
||||
if ok == over {
|
||||
t.Fatalf("at %d with %d allowed before: ok=%v, the definition says %v", now, len(allowedAt), ok, !over)
|
||||
}
|
||||
if !ok {
|
||||
denied++
|
||||
continue
|
||||
}
|
||||
reported += n
|
||||
allowedAt = append(allowedAt, now)
|
||||
}
|
||||
|
||||
if got := reported + l.denied.Load(); got != denied {
|
||||
t.Fatalf("reported %d denied calls, made %d", got, denied)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// Concurrent callers on the real clock must account for every denied call exactly once.
|
||||
func TestLimiterDeniedConservedConcurrent(t *testing.T) {
|
||||
l := mustLimiter(t, 4, time.Microsecond)
|
||||
|
||||
var denied, reported atomic.Uint64
|
||||
var wg sync.WaitGroup
|
||||
for i := 0; i < 16; i++ {
|
||||
wg.Add(1)
|
||||
go func() {
|
||||
defer wg.Done()
|
||||
for j := 0; j < 20000; j++ {
|
||||
if n, ok := l.Allow(); ok {
|
||||
reported.Add(n)
|
||||
} else {
|
||||
denied.Add(1)
|
||||
}
|
||||
}
|
||||
}()
|
||||
}
|
||||
wg.Wait()
|
||||
|
||||
if denied.Load() == 0 {
|
||||
t.Fatal("nothing was denied, the test proves nothing")
|
||||
}
|
||||
if got := reported.Load() + l.denied.Load(); got != denied.Load() {
|
||||
t.Fatalf("reported %d denied calls, made %d", got, denied.Load())
|
||||
}
|
||||
}
|
||||
+9
-3
@@ -57,8 +57,9 @@ func (rm *relayManager) GetUseRelays() bool {
|
||||
// StartRelays drives the relay-establishment side of an outbound handshake attempt.
|
||||
// For each candidate relay it either kicks off a handshake to the relay, sends a CreateRelayRequest, retransmits
|
||||
// one that may have been lost, or, once the relay is Established, forwards the in-progress
|
||||
// stage 0 handshake packet for vpnIp through it.
|
||||
func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *HandshakeHostInfo, stage0 []byte) {
|
||||
// stage 0 handshake packets for vpnIp through it: now immediately and later after the
|
||||
// handshake repair delay.
|
||||
func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *HandshakeHostInfo, now, later [][]byte) {
|
||||
hostinfo := hh.hostinfo
|
||||
if !rm.GetUseRelays() || len(hostinfo.remotes.relays) == 0 {
|
||||
hh.lastRelays = nil
|
||||
@@ -161,7 +162,10 @@ func (rm *relayManager) StartRelays(f *Interface, vpnIp netip.Addr, hh *Handshak
|
||||
switch existingRelay.State {
|
||||
case Established:
|
||||
hl.Log(context.Background(), level, "Send handshake via relay", "relay", relay.String())
|
||||
f.SendVia(relayHostInfo, existingRelay, stage0, make([]byte, 12), make([]byte, mtu), false, 0)
|
||||
_ = f.handshakeManager.sendFragmented(now, later, func(p []byte) error {
|
||||
f.SendVia(relayHostInfo, existingRelay, p, make([]byte, 12), make([]byte, mtu), false, 0)
|
||||
return nil
|
||||
})
|
||||
case Disestablished:
|
||||
// Mark this relay as 'requested'
|
||||
relayHostInfo.relayState.UpdateRelayForByIpState(vpnIp, Requested)
|
||||
@@ -360,6 +364,8 @@ func (rm *relayManager) handleCreateRelayResponse(v cert.Version, h *HostInfo, f
|
||||
}
|
||||
// Do I need to complete the relays now?
|
||||
if relay.Type == TerminalType {
|
||||
// The relay I asked for is up; a handshake waiting on it can go now.
|
||||
f.handshakeManager.relayEstablished(relay.PeerAddr, h, relay)
|
||||
return
|
||||
}
|
||||
// I'm the middle man. Let the initiator know that the I've established the relay they requested.
|
||||
|
||||
@@ -50,7 +50,7 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
rm := newRM(&buf)
|
||||
hh := newHH()
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
assert.Equal(t, []netip.Addr{vpnIp}, hh.lastRelays, "lastRelays should record the relay set we just attempted")
|
||||
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info level on first attempt")
|
||||
})
|
||||
@@ -59,10 +59,10 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
rm := newRM(&buf)
|
||||
hh := newHH()
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
first := append([]netip.Addr(nil), hh.lastRelays...)
|
||||
buf.Reset()
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
assert.Equal(t, first, hh.lastRelays)
|
||||
assert.Contains(t, buf.String(), "level=DEBUG "+msg, "expected Debug level on identical retry")
|
||||
assert.NotContains(t, buf.String(), "level=INFO "+msg, "Info should not fire on identical retry")
|
||||
@@ -72,13 +72,13 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
rm := newRM(&buf)
|
||||
hh := newHH()
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
buf.Reset()
|
||||
|
||||
// The lighthouse handed us a new set this round.
|
||||
hh.hostinfo.remotes.relays = []netip.Addr{vpnIp, otherRelay}
|
||||
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
assert.Equal(t, []netip.Addr{vpnIp, otherRelay}, hh.lastRelays)
|
||||
assert.Contains(t, buf.String(), "level=INFO "+msg, "expected Info when the relay list changes")
|
||||
})
|
||||
@@ -90,7 +90,7 @@ func TestStartRelaysLogDedupe(t *testing.T) {
|
||||
hh := newHH()
|
||||
hh.lastRelays = []netip.Addr{vpnIp}
|
||||
|
||||
rm.StartRelays(f, vpnIp, hh, nil)
|
||||
rm.StartRelays(f, vpnIp, hh, nil, nil)
|
||||
assert.Nil(t, hh.lastRelays, "with relays disabled lastRelays should be cleared")
|
||||
assert.NotContains(t, buf.String(), msg, "should not log when we shortcut out")
|
||||
})
|
||||
|
||||
@@ -684,10 +684,14 @@ func sshCreateTunnel(ifce *Interface, fs any, a []string, w sshd.StringWriter) e
|
||||
}
|
||||
}
|
||||
|
||||
hostInfo = ifce.handshakeManager.StartHandshake(vpnAddr, nil)
|
||||
if addr.IsValid() {
|
||||
hostInfo.SetRemote(addr)
|
||||
}
|
||||
// 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 w.WriteLine("Created")
|
||||
}
|
||||
|
||||
@@ -38,6 +38,11 @@ type statsServer struct {
|
||||
runMu sync.Mutex
|
||||
runCfg *statsConfig
|
||||
run *statsRuntime // non-nil while a runtime is live
|
||||
// Closed when the last runtime's capture loop has returned. Stop waits on it so nothing captures once it returns,
|
||||
// and a reload's new runtime never overlaps the old one, go-metrics keeps its GC capture state in unguarded globals
|
||||
loopDone chan struct{}
|
||||
// See newStatsServerFromConfig, never changes after it
|
||||
emitStats func()
|
||||
}
|
||||
|
||||
// statsRuntime is the live state owned by a single Start invocation. Start
|
||||
@@ -82,12 +87,16 @@ type promConfig struct {
|
||||
//
|
||||
// Start is safe to call unconditionally: it no-ops when stats are disabled.
|
||||
// The returned pointer is always non-nil, even on error.
|
||||
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool) (*statsServer, error) {
|
||||
//
|
||||
// emitStats, if set, updates metrics on every capture, ahead of the exporters so each export sees what it just set. It
|
||||
// is fixed here, before the reload callback exists, so every runtime has it.
|
||||
func newStatsServerFromConfig(ctx context.Context, l *slog.Logger, c *config.C, buildVersion string, configTest bool, emitStats func()) (*statsServer, error) {
|
||||
s := &statsServer{
|
||||
l: l,
|
||||
ctx: ctx,
|
||||
buildVersion: buildVersion,
|
||||
configTest: configTest,
|
||||
emitStats: emitStats,
|
||||
}
|
||||
|
||||
c.RegisterReloadCallback(func(c *config.C) {
|
||||
@@ -120,7 +129,6 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
|
||||
s.runMu.Lock()
|
||||
sameCfg := s.runCfg != nil && *s.runCfg == newCfg
|
||||
s.runCfg = &newCfg
|
||||
running := s.run != nil
|
||||
s.runMu.Unlock()
|
||||
|
||||
s.enabled.Store(enabled)
|
||||
@@ -129,9 +137,8 @@ func (s *statsServer) reload(c *config.C, initial bool) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
if running {
|
||||
s.Stop()
|
||||
}
|
||||
// Even with nothing running, a runtime whose listener failed can still be finishing its last pass
|
||||
s.Stop()
|
||||
if enabled && !s.configTest {
|
||||
go s.Start()
|
||||
}
|
||||
@@ -153,13 +160,19 @@ func (s *statsServer) Start() {
|
||||
return
|
||||
}
|
||||
cfg := *s.runCfg
|
||||
captureFns, listener := s.buildRuntime(cfg)
|
||||
runCtx, cancel := context.WithCancel(s.ctx)
|
||||
captureFns, listener := s.buildRuntime(runCtx, cfg)
|
||||
rt := &statsRuntime{cancel: cancel, listener: listener}
|
||||
s.run = rt
|
||||
done := make(chan struct{})
|
||||
s.loopDone = done
|
||||
s.runMu.Unlock()
|
||||
|
||||
go captureStatsLoop(runCtx, cfg.interval, captureFns)
|
||||
// Prime before serving, so a scrape that lands before the first tick sees real values instead of zeros (issue #907)
|
||||
for _, fn := range captureFns {
|
||||
fn()
|
||||
}
|
||||
go captureStatsLoop(runCtx, cfg.interval, captureFns, done)
|
||||
|
||||
cleanExit := true
|
||||
if listener == nil {
|
||||
@@ -218,26 +231,32 @@ func (s *statsServer) serveListener(listener *http.Server) bool {
|
||||
|
||||
// Stop tears down the active runtime, if any. Idempotent.
|
||||
func (s *statsServer) Stop() {
|
||||
// Held until the last pass is done, a Start that slipped in after s.run cleared would capture alongside it
|
||||
s.runMu.Lock()
|
||||
defer s.runMu.Unlock()
|
||||
rt := s.run
|
||||
s.run = nil
|
||||
s.runMu.Unlock()
|
||||
if rt == nil {
|
||||
return
|
||||
}
|
||||
rt.cancel()
|
||||
if rt.listener != nil {
|
||||
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
if err := rt.listener.Shutdown(shutdownCtx); err != nil {
|
||||
s.l.Warn("Failed to shut down prometheus stats listener", "error", err)
|
||||
if rt != nil {
|
||||
rt.cancel()
|
||||
if rt.listener != nil {
|
||||
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||||
if err := rt.listener.Shutdown(shutdownCtx); err != nil {
|
||||
s.l.Warn("Failed to shut down prometheus stats listener", "error", err)
|
||||
}
|
||||
cancel()
|
||||
}
|
||||
cancel()
|
||||
}
|
||||
// Nothing captures once Stop returns. The last runtime is cancelled by now, whoever cleared it, so this is at most
|
||||
// the pass it was in. Nothing in a pass takes runMu
|
||||
if s.loopDone != nil {
|
||||
<-s.loopDone
|
||||
}
|
||||
}
|
||||
|
||||
// buildRuntime produces the capture functions and, for prometheus, an un-served
|
||||
// http.Server from cfg. cfg has already been validated by loadStatsConfig.
|
||||
func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
// A graphite send in progress is abandoned when ctx is done.
|
||||
func (s *statsServer) buildRuntime(ctx context.Context, cfg statsConfig) ([]func(), *http.Server) {
|
||||
// rcrowley/go-metrics guards these registrations with a private sync.Once,
|
||||
// so subsequent reloads are no-ops.
|
||||
metrics.RegisterDebugGCStats(metrics.DefaultRegistry)
|
||||
@@ -247,6 +266,9 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
func() { metrics.CaptureDebugGCStatsOnce(metrics.DefaultRegistry) },
|
||||
func() { metrics.CaptureRuntimeMemStatsOnce(metrics.DefaultRegistry) },
|
||||
}
|
||||
if s.emitStats != nil {
|
||||
captureFns = append(captureFns, s.emitStats)
|
||||
}
|
||||
|
||||
switch cfg.typ {
|
||||
case "graphite":
|
||||
@@ -262,7 +284,7 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
Percentiles: []float64{0.5, 0.75, 0.95, 0.99, 0.999},
|
||||
}
|
||||
captureFns = append(captureFns, func() {
|
||||
if err := graphiteOnce(gcfg); err != nil {
|
||||
if err := graphiteOnce(ctx, gcfg, graphiteTimeout); err != nil && ctx.Err() == nil {
|
||||
s.l.Error("Graphite export failed", "error", err)
|
||||
}
|
||||
})
|
||||
@@ -309,8 +331,10 @@ func (s *statsServer) buildRuntime(cfg statsConfig) ([]func(), *http.Server) {
|
||||
return captureFns, nil
|
||||
}
|
||||
|
||||
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled.
|
||||
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func()) {
|
||||
// captureStatsLoop runs each fn on every tick of d until ctx is cancelled, then
|
||||
// closes done.
|
||||
func captureStatsLoop(ctx context.Context, d time.Duration, fns []func(), done chan struct{}) {
|
||||
defer close(done)
|
||||
t := time.NewTicker(d)
|
||||
defer t.Stop()
|
||||
for {
|
||||
|
||||
+294
-29
@@ -2,13 +2,18 @@ package nebula
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strconv"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/rcrowley/go-metrics"
|
||||
"github.com/slackhq/nebula/config"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
@@ -110,15 +115,14 @@ func TestStatsServer_reload_initial_prometheus(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestStatsServer_Start_graphite_blocksUntilStop(t *testing.T) {
|
||||
sink := newGraphiteSink(t)
|
||||
defer sink.Close()
|
||||
h := newGraphiteHost(t, 0)
|
||||
|
||||
s, c := newTestStatsServer(t)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "graphite",
|
||||
"interval": "1s",
|
||||
"protocol": "tcp",
|
||||
"host": sink.Addr(),
|
||||
"host": h.ln.Addr().String(),
|
||||
"prefix": "test",
|
||||
})
|
||||
require.NoError(t, s.reload(c, true))
|
||||
@@ -371,35 +375,19 @@ func waitForListening(t *testing.T, addr string) {
|
||||
})
|
||||
}
|
||||
|
||||
// graphiteSink is a minimal TCP accept-and-discard server so graphiteOnce
|
||||
// calls in tests don't spam error logs or wedge on connection refused.
|
||||
type graphiteSink struct {
|
||||
ln net.Listener
|
||||
}
|
||||
|
||||
func newGraphiteSink(t *testing.T) *graphiteSink {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
g := &graphiteSink{ln: ln}
|
||||
go func() {
|
||||
for {
|
||||
conn, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
go func(c net.Conn) {
|
||||
_, _ = io.Copy(io.Discard, c)
|
||||
_ = c.Close()
|
||||
}(conn)
|
||||
// stopAtCleanup returns the ctx to build *s with, and stops it when the test ends. Cancelling first turns away a Start
|
||||
// a reload spawned that hasn't run yet, then Stop waits out the last pass, so nothing captures into the next test
|
||||
func stopAtCleanup(t *testing.T, s **statsServer) context.Context {
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
t.Cleanup(func() {
|
||||
cancel()
|
||||
if *s != nil {
|
||||
(*s).Stop()
|
||||
}
|
||||
}()
|
||||
return g
|
||||
})
|
||||
return ctx
|
||||
}
|
||||
|
||||
func (g *graphiteSink) Addr() string { return g.ln.Addr().String() }
|
||||
func (g *graphiteSink) Close() { _ = g.ln.Close() }
|
||||
|
||||
func freeTCPPort(t *testing.T) string {
|
||||
t.Helper()
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
@@ -408,3 +396,280 @@ func freeTCPPort(t *testing.T) string {
|
||||
require.NoError(t, ln.Close())
|
||||
return strconv.Itoa(port)
|
||||
}
|
||||
|
||||
// Each export has to see what emitStats set in the same pass
|
||||
func TestStatsServer_emitStatsRunsBeforeExport(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("emitter.order.test")
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "prometheus",
|
||||
"interval": "1s",
|
||||
"listen": "127.0.0.1:0",
|
||||
"path": "/metrics",
|
||||
})
|
||||
gauge := metrics.GetOrRegisterGauge("emitter.order.test", nil)
|
||||
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, srv := s.buildRuntime(t.Context(), *s.runCfg)
|
||||
s.runMu.Unlock()
|
||||
require.NotNil(t, srv)
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
|
||||
rec := httptest.NewRecorder()
|
||||
srv.Handler.ServeHTTP(rec, httptest.NewRequest("GET", "/metrics", nil))
|
||||
assert.Contains(t, rec.Body.String(), "emitter_order_test 42")
|
||||
}
|
||||
|
||||
// A scrape that lands the moment the listener is up already sees what emitStats set (issue #907)
|
||||
func TestStatsServer_Start_primesBeforeServing(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("prime.before.serving")
|
||||
|
||||
port := freeTCPPort(t)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{
|
||||
"type": "prometheus",
|
||||
"interval": "1h",
|
||||
"listen": "127.0.0.1:" + port,
|
||||
"path": "/metrics",
|
||||
})
|
||||
gauge := metrics.GetOrRegisterGauge("prime.before.serving", nil)
|
||||
// The pause would let a listener that came up before the prime serve the zero value
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
time.Sleep(200 * time.Millisecond)
|
||||
gauge.Update(42)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
waitForListening(t, "127.0.0.1:"+port)
|
||||
|
||||
resp, err := http.Get("http://127.0.0.1:" + port + "/metrics")
|
||||
require.NoError(t, err)
|
||||
defer resp.Body.Close()
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
require.NoError(t, err)
|
||||
assert.Contains(t, string(body), "prime_before_serving 42")
|
||||
}
|
||||
|
||||
// Start captures once before the first tick, the interval here is an hour
|
||||
func TestStatsServer_Start_primes(t *testing.T) {
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer ln.Close()
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
|
||||
primed := make(chan struct{}, 1)
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err = newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
select {
|
||||
case primed <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-primed:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("nothing was captured before the first tick")
|
||||
}
|
||||
}
|
||||
|
||||
// Graphite has to ship what emitStats set in the same pass, not the pass before
|
||||
func TestStatsServer_emitStatsRunsBeforeGraphiteExport(t *testing.T) {
|
||||
defer metrics.DefaultRegistry.Unregister("emitter.graphite.test")
|
||||
|
||||
ln, err := net.Listen("tcp", "127.0.0.1:0")
|
||||
require.NoError(t, err)
|
||||
defer ln.Close()
|
||||
received := make(chan string, 1)
|
||||
go func() {
|
||||
conn, err := ln.Accept()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
defer conn.Close()
|
||||
b, _ := io.ReadAll(conn)
|
||||
received <- string(b)
|
||||
}()
|
||||
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": ln.Addr().String()})
|
||||
gauge := metrics.GetOrRegisterGauge("emitter.graphite.test", nil)
|
||||
s, err := newStatsServerFromConfig(t.Context(), l, c, "", false, func() { gauge.Update(42) })
|
||||
require.NoError(t, err)
|
||||
|
||||
s.runMu.Lock()
|
||||
fns, _ := s.buildRuntime(t.Context(), *s.runCfg)
|
||||
s.runMu.Unlock()
|
||||
for _, fn := range fns {
|
||||
fn()
|
||||
}
|
||||
|
||||
select {
|
||||
case body := <-received:
|
||||
assert.Contains(t, body, ".emitter.graphite.test.value 42 ")
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("graphite sent nothing")
|
||||
}
|
||||
}
|
||||
|
||||
// stats.interval reloads, and the runtime a reload starts still has emitStats
|
||||
func TestStatsServer_reloadMovesTheInterval(t *testing.T) {
|
||||
var passes atomic.Int64
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
// Nothing listens here, each export fails at once
|
||||
host := "127.0.0.1:" + freeTCPPort(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() { passes.Add(1) })
|
||||
require.NoError(t, err)
|
||||
go s.Start()
|
||||
waitFor(t, func() bool { return passes.Load() == 1 })
|
||||
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "20ms", "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
waitFor(t, func() bool { return passes.Load() >= 6 })
|
||||
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
// The reload's Stop waited out the 20ms loop. The new runtime's prime may land either side of this read, it is the
|
||||
// only pass left to come
|
||||
stopped := passes.Load()
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
assert.LessOrEqual(t, passes.Load()-stopped, int64(1), "the 20ms loop kept running after the reload")
|
||||
}
|
||||
|
||||
// A reload's new runtime never captures while the old one is still in a pass, go-metrics keeps its GC capture state
|
||||
// in unguarded globals
|
||||
func TestStatsServer_reloadWaitsForTheLastPass(t *testing.T) {
|
||||
var active, most atomic.Int64
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
host := "127.0.0.1:" + freeTCPPort(t)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "10ms", "host": host})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
n := active.Add(1)
|
||||
for {
|
||||
m := most.Load()
|
||||
if n <= m || most.CompareAndSwap(m, n) {
|
||||
break
|
||||
}
|
||||
}
|
||||
// Long enough that a reload almost always lands mid pass
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
active.Add(-1)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
go s.Start()
|
||||
|
||||
for i := range 6 {
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": fmt.Sprintf("%dms", 11-i%2), "host": host})
|
||||
require.NoError(t, s.reload(c, false))
|
||||
time.Sleep(30 * time.Millisecond)
|
||||
}
|
||||
assert.Equal(t, int64(1), most.Load())
|
||||
}
|
||||
|
||||
// Nothing captures once Stop returns, a pass in progress is waited out
|
||||
func TestStatsServer_Stop_waitsForThePass(t *testing.T) {
|
||||
var inPass atomic.Bool
|
||||
entered := make(chan struct{}, 1)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
inPass.Store(true)
|
||||
select {
|
||||
case entered <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
time.Sleep(100 * time.Millisecond)
|
||||
inPass.Store(false)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-entered:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("never captured")
|
||||
}
|
||||
s.Stop()
|
||||
assert.False(t, inPass.Load(), "Stop returned with a pass still running")
|
||||
}
|
||||
|
||||
// A Start that arrives while Stop waits out the last pass doesn't capture alongside it
|
||||
func TestStatsServer_Start_duringStopWaitsForThePass(t *testing.T) {
|
||||
var active, most atomic.Int64
|
||||
entered := make(chan struct{}, 1)
|
||||
l := slog.New(slog.DiscardHandler)
|
||||
c := config.NewC(l)
|
||||
setStatsConfig(c, map[string]any{"type": "graphite", "interval": "1h", "host": "127.0.0.1:" + freeTCPPort(t)})
|
||||
var s *statsServer
|
||||
ctx := stopAtCleanup(t, &s)
|
||||
s, err := newStatsServerFromConfig(ctx, l, c, "", false, func() {
|
||||
n := active.Add(1)
|
||||
for {
|
||||
m := most.Load()
|
||||
if n <= m || most.CompareAndSwap(m, n) {
|
||||
break
|
||||
}
|
||||
}
|
||||
select {
|
||||
case entered <- struct{}{}:
|
||||
default:
|
||||
}
|
||||
time.Sleep(200 * time.Millisecond)
|
||||
active.Add(-1)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
|
||||
go s.Start()
|
||||
select {
|
||||
case <-entered:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("never captured")
|
||||
}
|
||||
stopped := make(chan struct{})
|
||||
go func() {
|
||||
s.Stop()
|
||||
close(stopped)
|
||||
}()
|
||||
// Stop holds runMu for its whole wait, the next Start has to arrive after it took it
|
||||
waitFor(t, func() bool {
|
||||
if s.runMu.TryLock() {
|
||||
s.runMu.Unlock()
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
go s.Start()
|
||||
select {
|
||||
case <-stopped:
|
||||
case <-time.After(5 * time.Second):
|
||||
t.Fatal("Stop did not return")
|
||||
}
|
||||
waitFor(t, func() bool { return len(entered) == 1 })
|
||||
assert.Equal(t, int64(1), most.Load(), "a Start captured alongside the pass Stop was waiting out")
|
||||
}
|
||||
@@ -30,7 +30,7 @@ func procyield(cycles uint32)
|
||||
|
||||
const (
|
||||
packetsPerRing = 1024
|
||||
// Caps tun.mtu at MTU-32 direct, MTU-64 relayed, unenforced anywhere else. 17.6MB page locked per socket.
|
||||
// Fits a relayed packet at overlay.MaxMTU, which tun.mtu and route mtus are capped to. 17.6MB page locked per socket.
|
||||
bytesPerPacket = MTU
|
||||
receiveSpins = 15
|
||||
)
|
||||
|
||||
Reference in new issue
Block a user