mirror of
https://github.com/slackhq/nebula.git
synced 2024-11-14 20:05:53 +08:00
d604270966
This change fixes all of the known data races that `make smoke-docker-race` finds, except for one.
Most of these races are around the handshake phase for a hostinfo, so we add a RWLock to the hostinfo and Lock during each of the handshake stages.
Some of the other races are around consistently using `atomic` around the `messageCounter` field. To make this harder to mess up, I have renamed the field to `atomicMessageCounter` (I also removed the unnecessary extra pointer deference as we can just point directly to the struct field).
The last remaining data race is around reading `ConnectionInfo.ready`, which is a boolean that is only written to once when the handshake has finished. Due to it being in the hot path for packets and the rare case that this could actually be an issue, holding off on fixing that one for now.
here is the results of `make smoke-docker-race`:
before:
lighthouse1: Found 2 data race(s)
host2: Found 36 data race(s)
host3: Found 17 data race(s)
host4: Found 31 data race(s)
after:
host2: Found 1 data race(s)
host4: Found 1 data race(s)
Fixes: #147
Fixes: #226
Fixes: #283
Fixes: #316
75 lines
2 KiB
Go
75 lines
2 KiB
Go
package nebula
|
|
|
|
import (
|
|
"crypto/rand"
|
|
"encoding/json"
|
|
"sync"
|
|
"sync/atomic"
|
|
|
|
"github.com/flynn/noise"
|
|
"github.com/slackhq/nebula/cert"
|
|
)
|
|
|
|
const ReplayWindow = 1024
|
|
|
|
type ConnectionState struct {
|
|
eKey *NebulaCipherState
|
|
dKey *NebulaCipherState
|
|
H *noise.HandshakeState
|
|
certState *CertState
|
|
peerCert *cert.NebulaCertificate
|
|
initiator bool
|
|
atomicMessageCounter uint64
|
|
window *Bits
|
|
queueLock sync.Mutex
|
|
writeLock sync.Mutex
|
|
ready bool
|
|
}
|
|
|
|
func (f *Interface) newConnectionState(initiator bool, pattern noise.HandshakePattern, psk []byte, pskStage int) *ConnectionState {
|
|
cs := noise.NewCipherSuite(noise.DH25519, noise.CipherAESGCM, noise.HashSHA256)
|
|
if f.cipher == "chachapoly" {
|
|
cs = noise.NewCipherSuite(noise.DH25519, noise.CipherChaChaPoly, noise.HashSHA256)
|
|
}
|
|
|
|
curCertState := f.certState
|
|
static := noise.DHKey{Private: curCertState.privateKey, Public: curCertState.publicKey}
|
|
|
|
b := NewBits(ReplayWindow)
|
|
// Clear out bit 0, we never transmit it and we don't want it showing as packet loss
|
|
b.Update(0)
|
|
|
|
hs, err := noise.NewHandshakeState(noise.Config{
|
|
CipherSuite: cs,
|
|
Random: rand.Reader,
|
|
Pattern: pattern,
|
|
Initiator: initiator,
|
|
StaticKeypair: static,
|
|
PresharedKey: psk,
|
|
PresharedKeyPlacement: pskStage,
|
|
})
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
|
|
// The queue and ready params prevent a counter race that would happen when
|
|
// sending stored packets and simultaneously accepting new traffic.
|
|
ci := &ConnectionState{
|
|
H: hs,
|
|
initiator: initiator,
|
|
window: b,
|
|
ready: false,
|
|
certState: curCertState,
|
|
}
|
|
|
|
return ci
|
|
}
|
|
|
|
func (cs *ConnectionState) MarshalJSON() ([]byte, error) {
|
|
return json.Marshal(m{
|
|
"certificate": cs.peerCert,
|
|
"initiator": cs.initiator,
|
|
"message_counter": atomic.LoadUint64(&cs.atomicMessageCounter),
|
|
"ready": cs.ready,
|
|
})
|
|
}
|