Use PacketBuffers, rather than VectorisedViews, in netstack.

PacketBuffers are analogous to Linux's sk_buff. They hold all information about
a packet, headers, and payload. This is important for:

* iptables to access various headers of packets
* Preventing the clutter of passing different net and link headers along with
  VectorisedViews to packet handling functions.

This change only affects the incoming packet path, and a future change will
change the outgoing path.

Benchmark               Regular         PacketBufferPtr  PacketBufferConcrete
--------------------------------------------------------------------------------
BM_Recvmsg             400.715MB/s      373.676MB/s      396.276MB/s
BM_Sendmsg             361.832MB/s      333.003MB/s      335.571MB/s
BM_Recvfrom            453.336MB/s      393.321MB/s      381.650MB/s
BM_Sendto              378.052MB/s      372.134MB/s      341.342MB/s
BM_SendmsgTCP/0/1k     353.711MB/s      316.216MB/s      322.747MB/s
BM_SendmsgTCP/0/2k     600.681MB/s      588.776MB/s      565.050MB/s
BM_SendmsgTCP/0/4k     995.301MB/s      888.808MB/s      941.888MB/s
BM_SendmsgTCP/0/8k     1.517GB/s        1.274GB/s        1.345GB/s
BM_SendmsgTCP/0/16k    1.872GB/s        1.586GB/s        1.698GB/s
BM_SendmsgTCP/0/32k    1.017GB/s        1.020GB/s        1.133GB/s
BM_SendmsgTCP/0/64k    475.626MB/s      584.587MB/s      627.027MB/s
BM_SendmsgTCP/0/128k   416.371MB/s      503.434MB/s      409.850MB/s
BM_SendmsgTCP/0/256k   323.449MB/s      449.599MB/s      388.852MB/s
BM_SendmsgTCP/0/512k   243.992MB/s      267.676MB/s      314.474MB/s
BM_SendmsgTCP/0/1M     95.138MB/s       95.874MB/s       95.417MB/s
BM_SendmsgTCP/0/2M     96.261MB/s       94.977MB/s       96.005MB/s
BM_SendmsgTCP/0/4M     96.512MB/s       95.978MB/s       95.370MB/s
BM_SendmsgTCP/0/8M     95.603MB/s       95.541MB/s       94.935MB/s
BM_SendmsgTCP/0/16M    94.598MB/s       94.696MB/s       94.521MB/s
BM_SendmsgTCP/0/32M    94.006MB/s       94.671MB/s       94.768MB/s
BM_SendmsgTCP/0/64M    94.133MB/s       94.333MB/s       94.746MB/s
BM_SendmsgTCP/0/128M   93.615MB/s       93.497MB/s       93.573MB/s
BM_SendmsgTCP/0/256M   93.241MB/s       95.100MB/s       93.272MB/s
BM_SendmsgTCP/1/1k     303.644MB/s      316.074MB/s      308.430MB/s
BM_SendmsgTCP/1/2k     537.093MB/s      584.962MB/s      529.020MB/s
BM_SendmsgTCP/1/4k     882.362MB/s      939.087MB/s      892.285MB/s
BM_SendmsgTCP/1/8k     1.272GB/s        1.394GB/s        1.296GB/s
BM_SendmsgTCP/1/16k    1.802GB/s        2.019GB/s        1.830GB/s
BM_SendmsgTCP/1/32k    2.084GB/s        2.173GB/s        2.156GB/s
BM_SendmsgTCP/1/64k    2.515GB/s        2.463GB/s        2.473GB/s
BM_SendmsgTCP/1/128k   2.811GB/s        3.004GB/s        2.946GB/s
BM_SendmsgTCP/1/256k   3.008GB/s        3.159GB/s        3.171GB/s
BM_SendmsgTCP/1/512k   2.980GB/s        3.150GB/s        3.126GB/s
BM_SendmsgTCP/1/1M     2.165GB/s        2.233GB/s        2.163GB/s
BM_SendmsgTCP/1/2M     2.370GB/s        2.219GB/s        2.453GB/s
BM_SendmsgTCP/1/4M     2.005GB/s        2.091GB/s        2.214GB/s
BM_SendmsgTCP/1/8M     2.111GB/s        2.013GB/s        2.109GB/s
BM_SendmsgTCP/1/16M    1.902GB/s        1.868GB/s        1.897GB/s
BM_SendmsgTCP/1/32M    1.655GB/s        1.665GB/s        1.635GB/s
BM_SendmsgTCP/1/64M    1.575GB/s        1.547GB/s        1.575GB/s
BM_SendmsgTCP/1/128M   1.524GB/s        1.584GB/s        1.580GB/s
BM_SendmsgTCP/1/256M   1.579GB/s        1.607GB/s        1.593GB/s

PiperOrigin-RevId: 278940079

5 files changed, 22 insertions, 14 deletions

diff --git a/pkg/tcpip/transport/tcp/endpoint.go b/pkg/tcpip/transport/tcp/endpoint.go
index a1efd8d55..e31464c9b 100644
--- a/pkg/tcpip/transport/tcp/endpoint.go
+++ b/pkg/tcpip/transport/tcp/endpoint.go
@@ -2029,8 +2029,8 @@ func (e *endpoint) GetRemoteAddress() (tcpip.FullAddress, *tcpip.Error) {
 
 // HandlePacket is called by the stack when new packets arrive to this transport
 // endpoint.
-func (e *endpoint) HandlePacket(r *stack.Route, id stack.TransportEndpointID, vv buffer.VectorisedView) {
-	s := newSegment(r, id, vv)
+func (e *endpoint) HandlePacket(r *stack.Route, id stack.TransportEndpointID, pkt tcpip.PacketBuffer) {
+	s := newSegment(r, id, pkt)
 	if !s.parse() {
 		e.stack.Stats().MalformedRcvdPackets.Increment()
 		e.stack.Stats().TCP.InvalidSegmentsReceived.Increment()
@@ -2065,7 +2065,7 @@ func (e *endpoint) HandlePacket(r *stack.Route, id stack.TransportEndpointID, vv
 }
 
 // HandleControlPacket implements stack.TransportEndpoint.HandleControlPacket.
-func (e *endpoint) HandleControlPacket(id stack.TransportEndpointID, typ stack.ControlType, extra uint32, vv buffer.VectorisedView) {
+func (e *endpoint) HandleControlPacket(id stack.TransportEndpointID, typ stack.ControlType, extra uint32, pkt tcpip.PacketBuffer) {
 	switch typ {
 	case stack.ControlPacketTooBig:
 		e.sndBufMu.Lock()
diff --git a/pkg/tcpip/transport/tcp/forwarder.go b/pkg/tcpip/transport/tcp/forwarder.go
index 63666f0b3..4983bca81 100644
--- a/pkg/tcpip/transport/tcp/forwarder.go
+++ b/pkg/tcpip/transport/tcp/forwarder.go
@@ -18,7 +18,6 @@ import (
 	"sync"
 
 	"gvisor.dev/gvisor/pkg/tcpip"
-	"gvisor.dev/gvisor/pkg/tcpip/buffer"
 	"gvisor.dev/gvisor/pkg/tcpip/header"
 	"gvisor.dev/gvisor/pkg/tcpip/seqnum"
 	"gvisor.dev/gvisor/pkg/tcpip/stack"
@@ -63,8 +62,8 @@ func NewForwarder(s *stack.Stack, rcvWnd, maxInFlight int, handler func(*Forward
 //
 // This function is expected to be passed as an argument to the
 // stack.SetTransportProtocolHandler function.
-func (f *Forwarder) HandlePacket(r *stack.Route, id stack.TransportEndpointID, netHeader buffer.View, vv buffer.VectorisedView) bool {
-	s := newSegment(r, id, vv)
+func (f *Forwarder) HandlePacket(r *stack.Route, id stack.TransportEndpointID, pkt tcpip.PacketBuffer) bool {
+	s := newSegment(r, id, pkt)
 	defer s.decRef()
 
 	// We only care about well-formed SYN packets.
diff --git a/pkg/tcpip/transport/tcp/protocol.go b/pkg/tcpip/transport/tcp/protocol.go
index db40785d3..c4f1a84bb 100644
--- a/pkg/tcpip/transport/tcp/protocol.go
+++ b/pkg/tcpip/transport/tcp/protocol.go
@@ -126,8 +126,8 @@ func (*protocol) ParsePorts(v buffer.View) (src, dst uint16, err *tcpip.Error) {
 // a reset is sent in response to any incoming segment except another reset. In
 // particular, SYNs addressed to a non-existent connection are rejected by this
 // means."
-func (*protocol) HandleUnknownDestinationPacket(r *stack.Route, id stack.TransportEndpointID, netHeader buffer.View, vv buffer.VectorisedView) bool {
-	s := newSegment(r, id, vv)
+func (*protocol) HandleUnknownDestinationPacket(r *stack.Route, id stack.TransportEndpointID, pkt tcpip.PacketBuffer) bool {
+	s := newSegment(r, id, pkt)
 	defer s.decRef()
 
 	if !s.parse() || !s.csumValid {
diff --git a/pkg/tcpip/transport/tcp/segment.go b/pkg/tcpip/transport/tcp/segment.go
index c4a89525e..1c10da5ca 100644
--- a/pkg/tcpip/transport/tcp/segment.go
+++ b/pkg/tcpip/transport/tcp/segment.go
@@ -18,6 +18,7 @@ import (
 	"sync/atomic"
 	"time"
 
+	"gvisor.dev/gvisor/pkg/tcpip"
 	"gvisor.dev/gvisor/pkg/tcpip/buffer"
 	"gvisor.dev/gvisor/pkg/tcpip/header"
 	"gvisor.dev/gvisor/pkg/tcpip/seqnum"
@@ -60,13 +61,13 @@ type segment struct {
 	xmitTime time.Time `state:".(unixTime)"`
 }
 
-func newSegment(r *stack.Route, id stack.TransportEndpointID, vv buffer.VectorisedView) *segment {
+func newSegment(r *stack.Route, id stack.TransportEndpointID, pkt tcpip.PacketBuffer) *segment {
 	s := &segment{
 		refCnt: 1,
 		id:     id,
 		route:  r.Clone(),
 	}
-	s.data = vv.Clone(s.views[:])
+	s.data = pkt.Data.Clone(s.views[:])
 	s.rcvdTime = time.Now()
 	return s
 }
diff --git a/pkg/tcpip/transport/tcp/testing/context/context.go b/pkg/tcpip/transport/tcp/testing/context/context.go
index ef823e4ae..4854e719d 100644
--- a/pkg/tcpip/transport/tcp/testing/context/context.go
+++ b/pkg/tcpip/transport/tcp/testing/context/context.go
@@ -302,7 +302,9 @@ func (c *Context) SendICMPPacket(typ header.ICMPv4Type, code uint8, p1, p2 []byt
 	copy(icmp[header.ICMPv4PayloadOffset:], p2)
 
 	// Inject packet.
-	c.linkEP.Inject(ipv4.ProtocolNumber, buf.ToVectorisedView())
+	c.linkEP.InjectInbound(ipv4.ProtocolNumber, tcpip.PacketBuffer{
+		Data: buf.ToVectorisedView(),
+	})
 }
 
 // BuildSegment builds a TCP segment based on the given Headers and payload.
@@ -350,13 +352,17 @@ func (c *Context) BuildSegment(payload []byte, h *Headers) buffer.VectorisedView
 // SendSegment sends a TCP segment that has already been built and written to a
 // buffer.VectorisedView.
 func (c *Context) SendSegment(s buffer.VectorisedView) {
-	c.linkEP.Inject(ipv4.ProtocolNumber, s)
+	c.linkEP.InjectInbound(ipv4.ProtocolNumber, tcpip.PacketBuffer{
+		Data: s,
+	})
 }
 
 // SendPacket builds and sends a TCP segment(with the provided payload & TCP
 // headers) in an IPv4 packet via the link layer endpoint.
 func (c *Context) SendPacket(payload []byte, h *Headers) {
-	c.linkEP.Inject(ipv4.ProtocolNumber, c.BuildSegment(payload, h))
+	c.linkEP.InjectInbound(ipv4.ProtocolNumber, tcpip.PacketBuffer{
+		Data: c.BuildSegment(payload, h),
+	})
 }
 
 // SendAck sends an ACK packet.
@@ -518,7 +524,9 @@ func (c *Context) SendV6Packet(payload []byte, h *Headers) {
 	t.SetChecksum(^t.CalculateChecksum(xsum))
 
 	// Inject packet.
-	c.linkEP.Inject(ipv6.ProtocolNumber, buf.ToVectorisedView())
+	c.linkEP.InjectInbound(ipv6.ProtocolNumber, tcpip.PacketBuffer{
+		Data: buf.ToVectorisedView(),
+	})
 }
 
 // CreateConnected creates a connected TCP endpoint.