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, 229 insertions, 1 deletions

diff --git a/conn/bind_std_test.go b/conn/bind_std_test.go
index 1e46776..34a3c9a 100644
--- a/conn/bind_std_test.go
+++ b/conn/bind_std_test.go
@@ -1,6 +1,12 @@
 package conn
 
-import "testing"
+import (
+	"encoding/binary"
+	"net"
+	"testing"
+
+	"golang.org/x/net/ipv6"
+)
 
 func TestStdNetBindReceiveFuncAfterClose(t *testing.T) {
 	bind := NewStdNetBind().(*StdNetBind)
@@ -20,3 +26,225 @@ func TestStdNetBindReceiveFuncAfterClose(t *testing.T) {
 		fn(bufs, sizes, eps)
 	}
 }
+
+func mockSetGSOSize(control *[]byte, gsoSize uint16) {
+	*control = (*control)[:cap(*control)]
+	binary.LittleEndian.PutUint16(*control, gsoSize)
+}
+
+func Test_coalesceMessages(t *testing.T) {
+	cases := []struct {
+		name     string
+		buffs    [][]byte
+		wantLens []int
+		wantGSO  []int
+	}{
+		{
+			name: "one message no coalesce",
+			buffs: [][]byte{
+				make([]byte, 1, 1),
+			},
+			wantLens: []int{1},
+			wantGSO:  []int{0},
+		},
+		{
+			name: "two messages equal len coalesce",
+			buffs: [][]byte{
+				make([]byte, 1, 2),
+				make([]byte, 1, 1),
+			},
+			wantLens: []int{2},
+			wantGSO:  []int{1},
+		},
+		{
+			name: "two messages unequal len coalesce",
+			buffs: [][]byte{
+				make([]byte, 2, 3),
+				make([]byte, 1, 1),
+			},
+			wantLens: []int{3},
+			wantGSO:  []int{2},
+		},
+		{
+			name: "three messages second unequal len coalesce",
+			buffs: [][]byte{
+				make([]byte, 2, 3),
+				make([]byte, 1, 1),
+				make([]byte, 2, 2),
+			},
+			wantLens: []int{3, 2},
+			wantGSO:  []int{2, 0},
+		},
+		{
+			name: "three messages limited cap coalesce",
+			buffs: [][]byte{
+				make([]byte, 2, 4),
+				make([]byte, 2, 2),
+				make([]byte, 2, 2),
+			},
+			wantLens: []int{4, 2},
+			wantGSO:  []int{2, 0},
+		},
+	}
+
+	for _, tt := range cases {
+		t.Run(tt.name, func(t *testing.T) {
+			addr := &net.UDPAddr{
+				IP:   net.ParseIP("127.0.0.1").To4(),
+				Port: 1,
+			}
+			msgs := make([]ipv6.Message, len(tt.buffs))
+			for i := range msgs {
+				msgs[i].Buffers = make([][]byte, 1)
+				msgs[i].OOB = make([]byte, 0, 2)
+			}
+			got := coalesceMessages(addr, &StdNetEndpoint{AddrPort: addr.AddrPort()}, tt.buffs, msgs, mockSetGSOSize)
+			if got != len(tt.wantLens) {
+				t.Fatalf("got len %d want: %d", got, len(tt.wantLens))
+			}
+			for i := 0; i < got; i++ {
+				if msgs[i].Addr != addr {
+					t.Errorf("msgs[%d].Addr != passed addr", i)
+				}
+				gotLen := len(msgs[i].Buffers[0])
+				if gotLen != tt.wantLens[i] {
+					t.Errorf("len(msgs[%d].Buffers[0]) %d != %d", i, gotLen, tt.wantLens[i])
+				}
+				gotGSO, err := mockGetGSOSize(msgs[i].OOB)
+				if err != nil {
+					t.Fatalf("msgs[%d] getGSOSize err: %v", i, err)
+				}
+				if gotGSO != tt.wantGSO[i] {
+					t.Errorf("msgs[%d] gsoSize %d != %d", i, gotGSO, tt.wantGSO[i])
+				}
+			}
+		})
+	}
+}
+
+func mockGetGSOSize(control []byte) (int, error) {
+	if len(control) < 2 {
+		return 0, nil
+	}
+	return int(binary.LittleEndian.Uint16(control)), nil
+}
+
+func Test_splitCoalescedMessages(t *testing.T) {
+	newMsg := func(n, gso int) ipv6.Message {
+		msg := ipv6.Message{
+			Buffers: [][]byte{make([]byte, 1<<16-1)},
+			N:       n,
+			OOB:     make([]byte, 2),
+		}
+		binary.LittleEndian.PutUint16(msg.OOB, uint16(gso))
+		if gso > 0 {
+			msg.NN = 2
+		}
+		return msg
+	}
+
+	cases := []struct {
+		name        string
+		msgs        []ipv6.Message
+		firstMsgAt  int
+		wantNumEval int
+		wantMsgLens []int
+		wantErr     bool
+	}{
+		{
+			name: "second last split last empty",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(3, 1),
+				newMsg(0, 0),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 3,
+			wantMsgLens: []int{1, 1, 1, 0},
+			wantErr:     false,
+		},
+		{
+			name: "second last no split last empty",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(1, 0),
+				newMsg(0, 0),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 1,
+			wantMsgLens: []int{1, 0, 0, 0},
+			wantErr:     false,
+		},
+		{
+			name: "second last no split last no split",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(1, 0),
+				newMsg(1, 0),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 2,
+			wantMsgLens: []int{1, 1, 0, 0},
+			wantErr:     false,
+		},
+		{
+			name: "second last no split last split",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(1, 0),
+				newMsg(3, 1),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 4,
+			wantMsgLens: []int{1, 1, 1, 1},
+			wantErr:     false,
+		},
+		{
+			name: "second last split last split",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(2, 1),
+				newMsg(2, 1),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 4,
+			wantMsgLens: []int{1, 1, 1, 1},
+			wantErr:     false,
+		},
+		{
+			name: "second last no split last split overflow",
+			msgs: []ipv6.Message{
+				newMsg(0, 0),
+				newMsg(0, 0),
+				newMsg(1, 0),
+				newMsg(4, 1),
+			},
+			firstMsgAt:  2,
+			wantNumEval: 4,
+			wantMsgLens: []int{1, 1, 1, 1},
+			wantErr:     true,
+		},
+	}
+
+	for _, tt := range cases {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := splitCoalescedMessages(tt.msgs, 2, mockGetGSOSize)
+			if err != nil && !tt.wantErr {
+				t.Fatalf("err: %v", err)
+			}
+			if got != tt.wantNumEval {
+				t.Fatalf("got to eval: %d want: %d", got, tt.wantNumEval)
+			}
+			for i, msg := range tt.msgs {
+				if msg.N != tt.wantMsgLens[i] {
+					t.Fatalf("msg[%d].N: %d want: %d", i, msg.N, tt.wantMsgLens[i])
+				}
+			}
+		})
+	}
+}