ResiLien/nebula
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix most known data races (#396)

Browse Source 
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
This commit is contained in:
Wade Simmons
2021-03-05 21:18:33 -05:00
committed by GitHub
parent 29c5f31f90
commit d604270966
10 changed files with 97 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
inside.go
View File

@ -103,16 +103,21 @@ func (f *Interface) getOrHandshake(vpnIp uint32) *HostInfo {
// If we have already created the handshake packet, we don't want to call the function at all.
if !hostinfo.HandshakeReady {
ixHandshakeStage0(f, vpnIp, hostinfo)
// FIXME: Maybe make XX selectable, but probably not since psk makes it nearly pointless for us.
//xx_handshakeStage0(f, ip, hostinfo)
hostinfo.Lock()
defer hostinfo.Unlock()
// If this is a static host, we don't need to wait for the HostQueryReply
// We can trigger the handshake right now
if _, ok := f.lightHouse.staticList[vpnIp]; ok {
select {
case f.handshakeManager.trigger <- vpnIp:
default:
if !hostinfo.HandshakeReady {
ixHandshakeStage0(f, vpnIp, hostinfo)
// FIXME: Maybe make XX selectable, but probably not since psk makes it nearly pointless for us.
//xx_handshakeStage0(f, ip, hostinfo)
// If this is a static host, we don't need to wait for the HostQueryReply
// We can trigger the handshake right now
if _, ok := f.lightHouse.staticList[vpnIp]; ok {
select {
case f.handshakeManager.trigger <- vpnIp:
default:
}
}
}
}
@ -139,8 +144,8 @@ func (f *Interface) sendMessageNow(t NebulaMessageType, st NebulaMessageSubType,
return
}
f.sendNoMetrics(message, st, hostInfo.ConnectionState, hostInfo, hostInfo.remote, p, nb, out, 0)
if f.lightHouse != nil && *hostInfo.ConnectionState.messageCounter%5000 == 0 {
messageCounter := f.sendNoMetrics(message, st, hostInfo.ConnectionState, hostInfo, hostInfo.remote, p, nb, out, 0)
if f.lightHouse != nil && messageCounter%5000 == 0 {
f.lightHouse.Query(fp.RemoteIP, f)
}
}
@ -223,7 +228,7 @@ func (f *Interface) sendNoMetrics(t NebulaMessageType, st NebulaMessageSubType,
var err error
//TODO: enable if we do more than 1 tun queue
//ci.writeLock.Lock()
c := atomic.AddUint64(ci.messageCounter, 1)
c := atomic.AddUint64(&ci.atomicMessageCounter, 1)
//l.WithField("trace", string(debug.Stack())).Error("out Header ", &Header{Version, t, st, 0, hostinfo.remoteIndexId, c}, p)
out = HeaderEncode(out, Version, uint8(t), uint8(st), hostinfo.remoteIndexId, c)
@ -247,7 +252,7 @@ func (f *Interface) sendNoMetrics(t NebulaMessageType, st NebulaMessageSubType,
if err != nil {
hostinfo.logger().WithError(err).
WithField("udpAddr", remote).WithField("counter", c).
WithField("attemptedCounter", ci.messageCounter).
WithField("attemptedCounter", c).
Error("Failed to encrypt outgoing packet")
return c
}