conn, device, tun: implement vectorized I/O on Linux

Implement TCP offloading via TSO and GRO for the Linux tun.Device, which
is made possible by virtio extensions in the kernel's TUN driver.

Delete conn.LinuxSocketEndpoint in favor of a collapsed conn.StdNetBind.
conn.StdNetBind makes use of recvmmsg() and sendmmsg() on Linux. All
platforms now fall under conn.StdNetBind, except for Windows, which
remains in conn.WinRingBind, which still needs to be adjusted to handle
multiple packets.

Also refactor sticky sockets support to eventually be applicable on
platforms other than just Linux. However Linux remains the sole platform
that fully implements it for now.

Co-authored-by: James Tucker <james@tailscale.com>
Signed-off-by: James Tucker <james@tailscale.com>
Signed-off-by: Jordan Whited <jordan@tailscale.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

1 files changed, 42 insertions, 0 deletions

diff --git a/tun/checksum.go b/tun/checksum.go
new file mode 100644
index 0000000..f4f8471
--- /dev/null
+++ b/tun/checksum.go
@@ -0,0 +1,42 @@
+package tun
+
+import "encoding/binary"
+
+// TODO: Explore SIMD and/or other assembly optimizations.
+func checksumNoFold(b []byte, initial uint64) uint64 {
+	ac := initial
+	i := 0
+	n := len(b)
+	for n >= 4 {
+		ac += uint64(binary.BigEndian.Uint32(b[i : i+4]))
+		n -= 4
+		i += 4
+	}
+	for n >= 2 {
+		ac += uint64(binary.BigEndian.Uint16(b[i : i+2]))
+		n -= 2
+		i += 2
+	}
+	if n == 1 {
+		ac += uint64(b[i]) << 8
+	}
+	return ac
+}
+
+func checksum(b []byte, initial uint64) uint16 {
+	ac := checksumNoFold(b, initial)
+	ac = (ac >> 16) + (ac & 0xffff)
+	ac = (ac >> 16) + (ac & 0xffff)
+	ac = (ac >> 16) + (ac & 0xffff)
+	ac = (ac >> 16) + (ac & 0xffff)
+	return uint16(ac)
+}
+
+func pseudoHeaderChecksumNoFold(protocol uint8, srcAddr, dstAddr []byte, totalLen uint16) uint64 {
+	sum := checksumNoFold(srcAddr, 0)
+	sum = checksumNoFold(dstAddr, sum)
+	sum = checksumNoFold([]byte{0, protocol}, sum)
+	tmp := make([]byte, 2)
+	binary.BigEndian.PutUint16(tmp, totalLen)
+	return checksumNoFold(tmp, sum)
+}