diff options
Diffstat (limited to 'pkg/tcpip/stack/stack.go')
| -rw-r--r-- | pkg/tcpip/stack/stack.go | 313 |
1 files changed, 6 insertions, 307 deletions
diff --git a/pkg/tcpip/stack/stack.go b/pkg/tcpip/stack/stack.go index 931a97ddc..436392f23 100644 --- a/pkg/tcpip/stack/stack.go +++ b/pkg/tcpip/stack/stack.go @@ -35,7 +35,6 @@ import ( "gvisor.dev/gvisor/pkg/tcpip/buffer" "gvisor.dev/gvisor/pkg/tcpip/header" "gvisor.dev/gvisor/pkg/tcpip/ports" - "gvisor.dev/gvisor/pkg/tcpip/seqnum" "gvisor.dev/gvisor/pkg/waiter" ) @@ -56,306 +55,6 @@ type transportProtocolState struct { defaultHandler func(id TransportEndpointID, pkt *PacketBuffer) bool } -// TCPProbeFunc is the expected function type for a TCP probe function to be -// passed to stack.AddTCPProbe. -type TCPProbeFunc func(s TCPEndpointState) - -// TCPCubicState is used to hold a copy of the internal cubic state when the -// TCPProbeFunc is invoked. -type TCPCubicState struct { - WLastMax float64 - WMax float64 - T time.Time - TimeSinceLastCongestion time.Duration - C float64 - K float64 - Beta float64 - WC float64 - WEst float64 -} - -// TCPRACKState is used to hold a copy of the internal RACK state when the -// TCPProbeFunc is invoked. -type TCPRACKState struct { - XmitTime time.Time - EndSequence seqnum.Value - FACK seqnum.Value - RTT time.Duration - Reord bool - DSACKSeen bool - ReoWnd time.Duration - ReoWndIncr uint8 - ReoWndPersist int8 - RTTSeq seqnum.Value -} - -// TCPEndpointID is the unique 4 tuple that identifies a given endpoint. -type TCPEndpointID struct { - // LocalPort is the local port associated with the endpoint. - LocalPort uint16 - - // LocalAddress is the local [network layer] address associated with - // the endpoint. - LocalAddress tcpip.Address - - // RemotePort is the remote port associated with the endpoint. - RemotePort uint16 - - // RemoteAddress it the remote [network layer] address associated with - // the endpoint. - RemoteAddress tcpip.Address -} - -// TCPFastRecoveryState holds a copy of the internal fast recovery state of a -// TCP endpoint. -type TCPFastRecoveryState struct { - // Active if true indicates the endpoint is in fast recovery. - Active bool - - // First is the first unacknowledged sequence number being recovered. - First seqnum.Value - - // Last is the 'recover' sequence number that indicates the point at - // which we should exit recovery barring any timeouts etc. - Last seqnum.Value - - // MaxCwnd is the maximum value we are permitted to grow the congestion - // window during recovery. This is set at the time we enter recovery. - MaxCwnd int - - // HighRxt is the highest sequence number which has been retransmitted - // during the current loss recovery phase. - // See: RFC 6675 Section 2 for details. - HighRxt seqnum.Value - - // RescueRxt is the highest sequence number which has been - // optimistically retransmitted to prevent stalling of the ACK clock - // when there is loss at the end of the window and no new data is - // available for transmission. - // See: RFC 6675 Section 2 for details. - RescueRxt seqnum.Value -} - -// TCPReceiverState holds a copy of the internal state of the receiver for -// a given TCP endpoint. -type TCPReceiverState struct { - // RcvNxt is the TCP variable RCV.NXT. - RcvNxt seqnum.Value - - // RcvAcc is the TCP variable RCV.ACC. - RcvAcc seqnum.Value - - // RcvWndScale is the window scaling to use for inbound segments. - RcvWndScale uint8 - - // PendingBufUsed is the number of bytes pending in the receive - // queue. - PendingBufUsed int -} - -// TCPSenderState holds a copy of the internal state of the sender for -// a given TCP Endpoint. -type TCPSenderState struct { - // LastSendTime is the time at which we sent the last segment. - LastSendTime time.Time - - // DupAckCount is the number of Duplicate ACK's received. - DupAckCount int - - // SndCwnd is the size of the sending congestion window in packets. - SndCwnd int - - // Ssthresh is the slow start threshold in packets. - Ssthresh int - - // SndCAAckCount is the number of packets consumed in congestion - // avoidance mode. - SndCAAckCount int - - // Outstanding is the number of packets in flight. - Outstanding int - - // SackedOut is the number of packets which have been selectively acked. - SackedOut int - - // SndWnd is the send window size in bytes. - SndWnd seqnum.Size - - // SndUna is the next unacknowledged sequence number. - SndUna seqnum.Value - - // SndNxt is the sequence number of the next segment to be sent. - SndNxt seqnum.Value - - // RTTMeasureSeqNum is the sequence number being used for the latest RTT - // measurement. - RTTMeasureSeqNum seqnum.Value - - // RTTMeasureTime is the time when the RTTMeasureSeqNum was sent. - RTTMeasureTime time.Time - - // Closed indicates that the caller has closed the endpoint for sending. - Closed bool - - // SRTT is the smoothed round-trip time as defined in section 2 of - // RFC 6298. - SRTT time.Duration - - // RTO is the retransmit timeout as defined in section of 2 of RFC 6298. - RTO time.Duration - - // RTTVar is the round-trip time variation as defined in section 2 of - // RFC 6298. - RTTVar time.Duration - - // SRTTInited if true indicates take a valid RTT measurement has been - // completed. - SRTTInited bool - - // MaxPayloadSize is the maximum size of the payload of a given segment. - // It is initialized on demand. - MaxPayloadSize int - - // SndWndScale is the number of bits to shift left when reading the send - // window size from a segment. - SndWndScale uint8 - - // MaxSentAck is the highest acknowledgement number sent till now. - MaxSentAck seqnum.Value - - // FastRecovery holds the fast recovery state for the endpoint. - FastRecovery TCPFastRecoveryState - - // Cubic holds the state related to CUBIC congestion control. - Cubic TCPCubicState - - // RACKState holds the state related to RACK loss detection algorithm. - RACKState TCPRACKState -} - -// TCPSACKInfo holds TCP SACK related information for a given TCP endpoint. -type TCPSACKInfo struct { - // Blocks is the list of SACK Blocks that identify the out of order segments - // held by a given TCP endpoint. - Blocks []header.SACKBlock - - // ReceivedBlocks are the SACK blocks received by this endpoint - // from the peer endpoint. - ReceivedBlocks []header.SACKBlock - - // MaxSACKED is the highest sequence number that has been SACKED - // by the peer. - MaxSACKED seqnum.Value -} - -// RcvBufAutoTuneParams holds state related to TCP receive buffer auto-tuning. -type RcvBufAutoTuneParams struct { - // MeasureTime is the time at which the current measurement - // was started. - MeasureTime time.Time - - // CopiedBytes is the number of bytes copied to user space since - // this measure began. - CopiedBytes int - - // PrevCopiedBytes is the number of bytes copied to userspace in - // the previous RTT period. - PrevCopiedBytes int - - // RcvBufSize is the auto tuned receive buffer size. - RcvBufSize int - - // RTT is the smoothed RTT as measured by observing the time between - // when a byte is first acknowledged and the receipt of data that is at - // least one window beyond the sequence number that was acknowledged. - RTT time.Duration - - // RTTVar is the "round-trip time variation" as defined in section 2 - // of RFC6298. - RTTVar time.Duration - - // RTTMeasureSeqNumber is the highest acceptable sequence number at the - // time this RTT measurement period began. - RTTMeasureSeqNumber seqnum.Value - - // RTTMeasureTime is the absolute time at which the current RTT - // measurement period began. - RTTMeasureTime time.Time - - // Disabled is true if an explicit receive buffer is set for the - // endpoint. - Disabled bool -} - -// TCPEndpointState is a copy of the internal state of a TCP endpoint. -type TCPEndpointState struct { - // ID is a copy of the TransportEndpointID for the endpoint. - ID TCPEndpointID - - // SegTime denotes the absolute time when this segment was received. - SegTime time.Time - - // RcvBufSize is the size of the receive socket buffer for the endpoint. - RcvBufSize int - - // RcvBufUsed is the amount of bytes actually held in the receive socket - // buffer for the endpoint. - RcvBufUsed int - - // RcvBufAutoTuneParams is used to hold state variables to compute - // the auto tuned receive buffer size. - RcvAutoParams RcvBufAutoTuneParams - - // RcvClosed if true, indicates the endpoint has been closed for reading. - RcvClosed bool - - // SendTSOk is used to indicate when the TS Option has been negotiated. - // When sendTSOk is true every non-RST segment should carry a TS as per - // RFC7323#section-1.1. - SendTSOk bool - - // RecentTS is the timestamp that should be sent in the TSEcr field of - // the timestamp for future segments sent by the endpoint. This field is - // updated if required when a new segment is received by this endpoint. - RecentTS uint32 - - // TSOffset is a randomized offset added to the value of the TSVal field - // in the timestamp option. - TSOffset uint32 - - // SACKPermitted is set to true if the peer sends the TCPSACKPermitted - // option in the SYN/SYN-ACK. - SACKPermitted bool - - // SACK holds TCP SACK related information for this endpoint. - SACK TCPSACKInfo - - // SndBufSize is the size of the socket send buffer. - SndBufSize int - - // SndBufUsed is the number of bytes held in the socket send buffer. - SndBufUsed int - - // SndClosed indicates that the endpoint has been closed for sends. - SndClosed bool - - // SndBufInQueue is the number of bytes in the send queue. - SndBufInQueue seqnum.Size - - // PacketTooBigCount is used to notify the main protocol routine how - // many times a "packet too big" control packet is received. - PacketTooBigCount int - - // SndMTU is the smallest MTU seen in the control packets received. - SndMTU int - - // Receiver holds variables related to the TCP receiver for the endpoint. - Receiver TCPReceiverState - - // Sender holds state related to the TCP Sender for the endpoint. - Sender TCPSenderState -} - // ResumableEndpoint is an endpoint that needs to be resumed after restore. type ResumableEndpoint interface { // Resume resumes an endpoint after restore. This can be used to restart @@ -455,7 +154,7 @@ type Stack struct { // receiveBufferSize holds the min/default/max receive buffer sizes for // endpoints other than TCP. - receiveBufferSize ReceiveBufferSizeOption + receiveBufferSize tcpip.ReceiveBufferSizeOption // tcpInvalidRateLimit is the maximal rate for sending duplicate // acknowledgements in response to incoming TCP packets that are for an existing @@ -623,7 +322,7 @@ func (*TransportEndpointInfo) IsEndpointInfo() {} func New(opts Options) *Stack { clock := opts.Clock if clock == nil { - clock = &tcpip.StdClock{} + clock = tcpip.NewStdClock() } if opts.UniqueID == nil { @@ -669,7 +368,7 @@ func New(opts Options) *Stack { Default: DefaultBufferSize, Max: DefaultMaxBufferSize, }, - receiveBufferSize: ReceiveBufferSizeOption{ + receiveBufferSize: tcpip.ReceiveBufferSizeOption{ Min: MinBufferSize, Default: DefaultBufferSize, Max: DefaultMaxBufferSize, @@ -1344,7 +1043,7 @@ func (s *Stack) FindRoute(id tcpip.NICID, localAddr, remoteAddr tcpip.Address, n s.mu.RLock() defer s.mu.RUnlock() - isLinkLocal := header.IsV6LinkLocalAddress(remoteAddr) || header.IsV6LinkLocalMulticastAddress(remoteAddr) + isLinkLocal := header.IsV6LinkLocalUnicastAddress(remoteAddr) || header.IsV6LinkLocalMulticastAddress(remoteAddr) isLocalBroadcast := remoteAddr == header.IPv4Broadcast isMulticast := header.IsV4MulticastAddress(remoteAddr) || header.IsV6MulticastAddress(remoteAddr) isLoopback := header.IsV4LoopbackAddress(remoteAddr) || header.IsV6LoopbackAddress(remoteAddr) @@ -1381,7 +1080,7 @@ func (s *Stack) FindRoute(id tcpip.NICID, localAddr, remoteAddr tcpip.Address, n return nil, &tcpip.ErrNetworkUnreachable{} } - canForward := s.Forwarding(netProto) && !header.IsV6LinkLocalAddress(localAddr) && !isLinkLocal + canForward := s.Forwarding(netProto) && !header.IsV6LinkLocalUnicastAddress(localAddr) && !isLinkLocal // Find a route to the remote with the route table. var chosenRoute tcpip.Route @@ -1874,7 +1573,7 @@ func (s *Stack) WritePacketToRemote(nicID tcpip.NICID, remote tcpip.LinkAddress, ReserveHeaderBytes: int(nic.MaxHeaderLength()), Data: payload, }) - return nic.WritePacketToRemote(remote, nil, netProto, pkt) + return nic.WritePacketToRemote(remote, netProto, pkt) } // NetworkProtocolInstance returns the protocol instance in the stack for the |