Files
nebula/connection_state.go
T
Ryan Huber e4f659a207 tun: Share replay-window reservation credit across readers
Charge staged reservations to each tunnel instead of dividing a static share
of the window by routines. Several readers sending on one tunnel then share
its credit: the limit is half the peer replay window, assumed from
ReplayWindow, which must be a power of two of at least 8192 (checked at
compile time). The other half allows finite unreserved traffic (inline and
control sends, relay forwarding through SendVia) and network reordering;
unlimited bypass traffic or delay can still exceed it.

An outstanding-count cap alone would let a fast reader repeatedly send and
reacquire credit, overtaking a paused reader without bound. So once readers
overlap, spent credit is only recycled when every reservation has drained. A
sole ordered reader gets each completion refunded, since its later batches
cannot overtake its earlier ones. A reader that fails to acquire ends sole
ownership, so a busy owner cannot keep a larger waiter blocked forever. This
restores progress, not FIFO fairness. All transitions are a single CAS.

Waiting readers flush their own oldest batch before retrying and never hold a
partial acquisition: a failed multi-tunnel (relay) acquisition rolls back.
Credit is released only after the flush or an explicit drop. A read that alone
exceeds a tunnel's credit, such as a tiny-MSS superpacket, is sent segment by
segment, synchronously. Acquisition is per read, so pressure on one tunnel
also delays the other tunnels in the same read.

The combined staged transmit, receive and shared credit measured 15 to 25
Gbit/s over one tunnel with eight TCP streams between two 100 GbE hosts.

Tests model overtaking, ordered reuse, a blocked reader behind a busy owner,
and relay rollback with both window sizes, and run eight competing readers
plus unreserved control traffic on one tunnel, checking every packet is
accepted by the receiver's replay window in wire order.
2026-10-16 21:22:11 +00:00

158 lines
5.5 KiB
Go

package nebula
import (
"encoding/json"
"fmt"
"log/slog"
"sync"
"sync/atomic"
"github.com/slackhq/nebula/cert"
"github.com/slackhq/nebula/handshake"
"github.com/slackhq/nebula/header"
"github.com/slackhq/nebula/noiseutil"
)
const (
// ReplayWindow is the build-time receive window and the assumed peer window
// for TX reservation credit. Use a power of two; peers must match or have a
// larger receive window. The bitmap costs ReplayWindow/8 bytes per tunnel.
ReplayWindow = 8192
// RehandshakeAfterMessages rolls keys inside the AES-GCM data-volume margin (~2^-36 advantage at 64KB frames).
RehandshakeAfterMessages = uint64(1) << 34
// RejectAfterMessages is the nonce ceiling enforced by noiseutil; a tunnel here is deleted locally, not notified.
RejectAfterMessages = noiseutil.RejectAfterMessages
)
// RehandshakeAfterMessages must stay below RejectAfterMessages so tunnels roll before the hard send stop.
const _ = RejectAfterMessages - RehandshakeAfterMessages
// sessionEpoch hands out a receiver-local ordinal to every ConnectionState at creation. The RX
// staging sort (overlay/batch) orders packets by (epoch, message counter). A re-handshake never
// rekeys an existing tunnel; it brings up a new hostinfo and ConnectionState with a counter space
// starting near zero, while the old tunnel keeps decrypting until torn down. During that cutover
// one flush batch can hold packets from both tunnels, and the epoch keeps the old tunnel's
// packets sorted first.
var sessionEpoch atomic.Uint64
type ConnectionState struct {
eKey noiseutil.CipherState
dKey noiseutil.CipherState
myCert cert.Certificate
peerCert *cert.CachedCertificate
initiator bool
messageCounter atomic.Uint64
txBudget txBudget
window *Bits
decryptLock sync.Mutex
writeLock sync.Mutex
// epoch is this session's sessionEpoch ordinal. Immutable after creation.
epoch uint64
}
// newConnectionStateFromResult builds a fully-populated ConnectionState from a
// completed handshake.Result. It seeds messageCounter and the replay window so
// that the post-handshake message indices already used on the wire don't count
// as missed traffic in the data plane.
func newConnectionStateFromResult(r *handshake.Result) (*ConnectionState, error) {
// Refuse a MessageIndex too big for the replay window: it can only be a bug, and would spin the seed loop below.
if r.MessageIndex >= ReplayWindow {
return nil, fmt.Errorf("handshake message index %d exceeds replay window", r.MessageIndex)
}
ci := &ConnectionState{
myCert: r.MyCert,
initiator: r.Initiator,
peerCert: r.RemoteCert,
eKey: noiseutil.NewCipherState(r.EKey, r.Cipher),
dKey: noiseutil.NewCipherState(r.DKey, r.Cipher),
window: NewBits(ReplayWindow),
epoch: sessionEpoch.Add(1),
}
ci.messageCounter.Add(r.MessageIndex)
for i := uint64(1); i <= r.MessageIndex; i++ {
ci.window.Update(nil, i)
}
return ci, nil
}
func (cs *ConnectionState) MarshalJSON() ([]byte, error) {
return json.Marshal(m{
"certificate": cs.peerCert,
"initiator": cs.initiator,
"message_counter": cs.messageCounter.Load(),
})
}
// NextMessageCounter reserves the next 1-based counter; RejectAfterMessages is the first we refuse, pinned to not wrap.
func (cs *ConnectionState) NextMessageCounter() (uint64, bool) {
c := cs.messageCounter.Add(1)
if c >= RejectAfterMessages {
cs.messageCounter.Store(RejectAfterMessages)
return c, false
}
return c, true
}
func (cs *ConnectionState) Curve() cert.Curve {
return cs.myCert.Curve()
}
func (cs *ConnectionState) Decrypt(l *slog.Logger, messageCounter uint64, packet []byte, nb []byte) ([]byte, error) {
cs.decryptLock.Lock()
result := cs.window.Check(l, messageCounter)
cs.decryptLock.Unlock()
if !result {
return nil, ErrAlreadySeen
}
out, err := cs.decryptPacket(messageCounter, packet, nb)
if err != nil {
return nil, err
}
cs.decryptLock.Lock()
result = cs.window.Update(l, messageCounter)
cs.decryptLock.Unlock()
if !result {
return nil, ErrAlreadySeen
}
return out, nil
}
// decryptPacket authenticates and decrypts packet in place, leaving the replay window to the caller.
func (cs *ConnectionState) decryptPacket(messageCounter uint64, packet, nb []byte) ([]byte, error) {
return cs.dKey.DecryptDanger(packet[header.Len:header.Len], packet[:header.Len], packet[header.Len:], messageCounter, nb)
}
func (cs *ConnectionState) VerifyRelay(l *slog.Logger, messageCounter uint64, packet []byte, nb []byte) error {
cs.decryptLock.Lock()
result := cs.window.Check(l, messageCounter)
cs.decryptLock.Unlock()
if !result {
return ErrAlreadySeen
}
// The entire body is sent as AD, not encrypted.
// The packet consists of a 16-byte parsed Nebula header, Associated Data-protected payload, and a trailing 16-byte AEAD signature value.
// The packet is guaranteed to be at least 16 bytes at this point, b/c it got past the h.Parse() call above. If it's
// otherwise malformed (meaning, there is no trailing 16 byte AEAD value), then this will result in at worst a 0-length slice
// which will gracefully fail in the DecryptDanger call.
signedPayload := packet[:len(packet)-cs.dKey.Overhead()]
signatureValue := packet[len(packet)-cs.dKey.Overhead():]
_, err := cs.dKey.DecryptDanger(nil, signedPayload, signatureValue, messageCounter, nb)
if err != nil {
return err
}
cs.decryptLock.Lock()
result = cs.window.Update(l, messageCounter)
cs.decryptLock.Unlock()
if !result {
return ErrAlreadySeen
}
return nil
}