conn, device: use UDP GSO and GRO on Linux

StdNetBind probes for UDP GSO and GRO support at runtime. UDP GSO is
dependent on checksum offload support on the egress netdev. UDP GSO
will be disabled in the event sendmmsg() returns EIO, which is a strong
signal that the egress netdev does not support checksum offload.

The iperf3 results below demonstrate the effect of this commit between
two Linux computers with i5-12400 CPUs. There is roughly ~13us of round
trip latency between them.

The first result is from commit 052af4a without UDP GSO or GRO.

Starting Test: protocol: TCP, 1 streams, 131072 byte blocks
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-10.00  sec  9.85 GBytes  8.46 Gbits/sec  1139   3.01 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
Test Complete. Summary Results:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  9.85 GBytes  8.46 Gbits/sec  1139  sender
[  5]   0.00-10.04  sec  9.85 GBytes  8.42 Gbits/sec        receiver

The second result is with UDP GSO and GRO.

Starting Test: protocol: TCP, 1 streams, 131072 byte blocks
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-10.00  sec  12.3 GBytes  10.6 Gbits/sec  232   3.15 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
Test Complete. Summary Results:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  12.3 GBytes  10.6 Gbits/sec  232   sender
[  5]   0.00-10.04  sec  12.3 GBytes  10.6 Gbits/sec        receiver

Reviewed-by: Adrian Dewhurst <adrian@tailscale.com>
Signed-off-by: Jordan Whited <jordan@tailscale.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

1 files changed, 159 insertions, 0 deletions

diff --git a/conn/control_linux.go b/conn/control_linux.go
new file mode 100644
index 0000000..44a94e6
--- /dev/null
+++ b/conn/control_linux.go
@@ -0,0 +1,159 @@
+//go:build linux && !android
+
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2017-2023 WireGuard LLC. All Rights Reserved.
+ */
+
+package conn
+
+import (
+	"fmt"
+	"net/netip"
+	"unsafe"
+
+	"golang.org/x/sys/unix"
+)
+
+func (e *StdNetEndpoint) SrcIP() netip.Addr {
+	switch len(e.src) {
+	case unix.CmsgSpace(unix.SizeofInet4Pktinfo):
+		info := (*unix.Inet4Pktinfo)(unsafe.Pointer(&e.src[unix.CmsgLen(0)]))
+		return netip.AddrFrom4(info.Spec_dst)
+	case unix.CmsgSpace(unix.SizeofInet6Pktinfo):
+		info := (*unix.Inet6Pktinfo)(unsafe.Pointer(&e.src[unix.CmsgLen(0)]))
+		// TODO: set zone. in order to do so we need to check if the address is
+		// link local, and if it is perform a syscall to turn the ifindex into a
+		// zone string because netip uses string zones.
+		return netip.AddrFrom16(info.Addr)
+	}
+	return netip.Addr{}
+}
+
+func (e *StdNetEndpoint) SrcIfidx() int32 {
+	switch len(e.src) {
+	case unix.CmsgSpace(unix.SizeofInet4Pktinfo):
+		info := (*unix.Inet4Pktinfo)(unsafe.Pointer(&e.src[unix.CmsgLen(0)]))
+		return info.Ifindex
+	case unix.CmsgSpace(unix.SizeofInet6Pktinfo):
+		info := (*unix.Inet6Pktinfo)(unsafe.Pointer(&e.src[unix.CmsgLen(0)]))
+		return int32(info.Ifindex)
+	}
+	return 0
+}
+
+func (e *StdNetEndpoint) SrcToString() string {
+	return e.SrcIP().String()
+}
+
+// getSrcFromControl parses the control for PKTINFO and if found updates ep with
+// the source information found.
+func getSrcFromControl(control []byte, ep *StdNetEndpoint) {
+	ep.ClearSrc()
+
+	var (
+		hdr  unix.Cmsghdr
+		data []byte
+		rem  []byte = control
+		err  error
+	)
+
+	for len(rem) > unix.SizeofCmsghdr {
+		hdr, data, rem, err = unix.ParseOneSocketControlMessage(rem)
+		if err != nil {
+			return
+		}
+
+		if hdr.Level == unix.IPPROTO_IP &&
+			hdr.Type == unix.IP_PKTINFO {
+
+			if ep.src == nil || cap(ep.src) < unix.CmsgSpace(unix.SizeofInet4Pktinfo) {
+				ep.src = make([]byte, 0, unix.CmsgSpace(unix.SizeofInet4Pktinfo))
+			}
+			ep.src = ep.src[:unix.CmsgSpace(unix.SizeofInet4Pktinfo)]
+
+			hdrBuf := unsafe.Slice((*byte)(unsafe.Pointer(&hdr)), unix.SizeofCmsghdr)
+			copy(ep.src, hdrBuf)
+			copy(ep.src[unix.CmsgLen(0):], data)
+			return
+		}
+
+		if hdr.Level == unix.IPPROTO_IPV6 &&
+			hdr.Type == unix.IPV6_PKTINFO {
+
+			if ep.src == nil || cap(ep.src) < unix.CmsgSpace(unix.SizeofInet6Pktinfo) {
+				ep.src = make([]byte, 0, unix.CmsgSpace(unix.SizeofInet6Pktinfo))
+			}
+
+			ep.src = ep.src[:unix.CmsgSpace(unix.SizeofInet6Pktinfo)]
+
+			hdrBuf := unsafe.Slice((*byte)(unsafe.Pointer(&hdr)), unix.SizeofCmsghdr)
+			copy(ep.src, hdrBuf)
+			copy(ep.src[unix.CmsgLen(0):], data)
+			return
+		}
+	}
+}
+
+// setSrcControl sets an IP{V6}_PKTINFO in control based on the source address
+// and source ifindex found in ep. control's len will be set to 0 in the event
+// that ep is a default value.
+func setSrcControl(control *[]byte, ep *StdNetEndpoint) {
+	if cap(*control) < len(ep.src) {
+		return
+	}
+	*control = (*control)[:0]
+	*control = append(*control, ep.src...)
+}
+
+const (
+	sizeOfGSOData = 2
+)
+
+// getGSOSize parses control for UDP_GRO and if found returns its GSO size data.
+func getGSOSize(control []byte) (int, error) {
+	var (
+		hdr  unix.Cmsghdr
+		data []byte
+		rem  = control
+		err  error
+	)
+
+	for len(rem) > unix.SizeofCmsghdr {
+		hdr, data, rem, err = unix.ParseOneSocketControlMessage(rem)
+		if err != nil {
+			return 0, fmt.Errorf("error parsing socket control message: %w", err)
+		}
+		if hdr.Level == unix.SOL_UDP && hdr.Type == unix.UDP_GRO && len(data) >= sizeOfGSOData {
+			var gso uint16
+			copy(unsafe.Slice((*byte)(unsafe.Pointer(&gso)), sizeOfGSOData), data[:sizeOfGSOData])
+			return int(gso), nil
+		}
+	}
+	return 0, nil
+}
+
+// setGSOSize sets a UDP_SEGMENT in control based on gsoSize. It leaves existing
+// data in control untouched.
+func setGSOSize(control *[]byte, gsoSize uint16) {
+	existingLen := len(*control)
+	avail := cap(*control) - existingLen
+	space := unix.CmsgSpace(sizeOfGSOData)
+	if avail < space {
+		return
+	}
+	*control = (*control)[:cap(*control)]
+	gsoControl := (*control)[existingLen:]
+	hdr := (*unix.Cmsghdr)(unsafe.Pointer(&(gsoControl)[0]))
+	hdr.Level = unix.SOL_UDP
+	hdr.Type = unix.UDP_SEGMENT
+	hdr.SetLen(unix.CmsgLen(sizeOfGSOData))
+	copy((gsoControl)[unix.SizeofCmsghdr:], unsafe.Slice((*byte)(unsafe.Pointer(&gsoSize)), sizeOfGSOData))
+	*control = (*control)[:existingLen+space]
+}
+
+// controlSize returns the recommended buffer size for pooling sticky and UDP
+// offloading control data.
+var controlSize = unix.CmsgSpace(unix.SizeofInet6Pktinfo) + unix.CmsgSpace(sizeOfGSOData)
+
+const StdNetSupportsStickySockets = true