tcp可靠性实现 抄了一堆东西 信息量太大了 看不过来

tcpip/stack/stack.go

@@ -6,7 +6,9 @@ import (
 	"netstack/sleep"
 	"netstack/tcpip"
 	"netstack/tcpip/buffer"
+	"netstack/tcpip/header"
 	"netstack/tcpip/ports"
+	"netstack/tcpip/seqnum"
 	"netstack/waiter"
 	"sync"
 	"time"
@@ -21,12 +23,22 @@ const (
 	resolutionAttempts = 3
 )
 
-// TODO 需要解读
-type TCPProbeFunc func(s TcpEndpointState)
+// TCPProbeFunc is the expected function type for a TCP probe function to be
+// passed to stack.AddTCPProbe.
+type TCPProbeFunc func(s TCPEndpointState)
 
-// TODO 需要解读
-type TcpEndpointState struct {
-	// TODO 需要添加
+// 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
 }
 
 // 传输层协议状态机 包含传输层协议以及默认处理方法
@@ -35,6 +47,207 @@ type transportProtocolState struct {
 	defaultHandler func(*Route, TransportEndpointID, buffer.VectorisedView) bool
 }
 
+// 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
+}
+
+// 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 seqnum.Size
+
+	// PendingBufSize is the size of the socket receive buffer.
+	PendingBufSize seqnum.Size
+}
+
+// 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
+
+	// 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
+}
+
+// TCPSACKInfo holds TCP SACK related information for a given TCP endpoint.
+type TCPSACKInfo struct {
+	// Blocks is the list of SACK block currently received by the
+	// TCP endpoint.
+	Blocks []header.SACKBlock
+}
+
+// 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
+
+	// 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
+}
+
 // Stack 是一个网络堆栈，具有所有支持的协议、NIC 和路由表。
 type Stack struct {
 	transportProtocols map[tcpip.TransportProtocolNumber]*transportProtocolState // 各种传输层协议