tun: export GSOSplit() for external Device implementers
External implementers of tun.Device may support GSO, and may also be platform-agnostic, e.g. gVisor. Signed-off-by: Jordan Whited <jordan@tailscale.com>
This commit is contained in:
Jordan Whited
Jordan Whited
parent
2f5d148bcf
commit
60eeedfd62
4 changed files with 354 additions and 162 deletions
|
|
@ -9,6 +9,7 @@ import (
|
|||
"bytes"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"unsafe"
|
||||
|
||||
|
|
@ -16,14 +17,6 @@ import (
|
|||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
const tcpFlagsOffset = 13
|
||||
|
||||
const (
|
||||
tcpFlagFIN uint8 = 0x01
|
||||
tcpFlagPSH uint8 = 0x08
|
||||
tcpFlagACK uint8 = 0x10
|
||||
)
|
||||
|
||||
// virtioNetHdr is defined in the kernel in include/uapi/linux/virtio_net.h. The
|
||||
// kernel symbol is virtio_net_hdr.
|
||||
type virtioNetHdr struct {
|
||||
|
|
@ -35,6 +28,30 @@ type virtioNetHdr struct {
|
|||
csumOffset uint16
|
||||
}
|
||||
|
||||
func (v *virtioNetHdr) toGSOOptions() (GSOOptions, error) {
|
||||
var gsoType GSOType
|
||||
switch v.gsoType {
|
||||
case unix.VIRTIO_NET_HDR_GSO_NONE:
|
||||
gsoType = GSONone
|
||||
case unix.VIRTIO_NET_HDR_GSO_TCPV4:
|
||||
gsoType = GSOTCPv4
|
||||
case unix.VIRTIO_NET_HDR_GSO_TCPV6:
|
||||
gsoType = GSOTCPv6
|
||||
case unix.VIRTIO_NET_HDR_GSO_UDP_L4:
|
||||
gsoType = GSOUDPL4
|
||||
default:
|
||||
return GSOOptions{}, fmt.Errorf("unsupported virtio gsoType: %d", v.gsoType)
|
||||
}
|
||||
return GSOOptions{
|
||||
GSOType: gsoType,
|
||||
HdrLen: v.hdrLen,
|
||||
CsumStart: v.csumStart,
|
||||
CsumOffset: v.csumOffset,
|
||||
GSOSize: v.gsoSize,
|
||||
NeedsCsum: v.flags&unix.VIRTIO_NET_HDR_F_NEEDS_CSUM != 0,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (v *virtioNetHdr) decode(b []byte) error {
|
||||
if len(b) < virtioNetHdrLen {
|
||||
return io.ErrShortBuffer
|
||||
|
|
@ -510,9 +527,7 @@ const (
|
|||
)
|
||||
|
||||
const (
|
||||
ipv4SrcAddrOffset = 12
|
||||
ipv6SrcAddrOffset = 8
|
||||
maxUint16 = 1<<16 - 1
|
||||
maxUint16 = 1<<16 - 1
|
||||
)
|
||||
|
||||
type groResult int
|
||||
|
|
@ -894,100 +909,3 @@ func handleGRO(bufs [][]byte, offset int, tcpTable *tcpGROTable, udpTable *udpGR
|
|||
errUDP := applyUDPCoalesceAccounting(bufs, offset, udpTable)
|
||||
return errors.Join(errTCP, errUDP)
|
||||
}
|
||||
|
||||
// gsoSplit splits packets from in into outBuffs, writing the size of each
|
||||
// element into sizes. It returns the number of buffers populated, and/or an
|
||||
// error.
|
||||
func gsoSplit(in []byte, hdr virtioNetHdr, outBuffs [][]byte, sizes []int, outOffset int, isV6 bool) (int, error) {
|
||||
iphLen := int(hdr.csumStart)
|
||||
srcAddrOffset := ipv6SrcAddrOffset
|
||||
addrLen := 16
|
||||
if !isV6 {
|
||||
in[10], in[11] = 0, 0 // clear ipv4 header checksum
|
||||
srcAddrOffset = ipv4SrcAddrOffset
|
||||
addrLen = 4
|
||||
}
|
||||
transportCsumAt := int(hdr.csumStart + hdr.csumOffset)
|
||||
in[transportCsumAt], in[transportCsumAt+1] = 0, 0 // clear tcp/udp checksum
|
||||
var firstTCPSeqNum uint32
|
||||
var protocol uint8
|
||||
if hdr.gsoType == unix.VIRTIO_NET_HDR_GSO_TCPV4 || hdr.gsoType == unix.VIRTIO_NET_HDR_GSO_TCPV6 {
|
||||
protocol = unix.IPPROTO_TCP
|
||||
firstTCPSeqNum = binary.BigEndian.Uint32(in[hdr.csumStart+4:])
|
||||
} else {
|
||||
protocol = unix.IPPROTO_UDP
|
||||
}
|
||||
nextSegmentDataAt := int(hdr.hdrLen)
|
||||
i := 0
|
||||
for ; nextSegmentDataAt < len(in); i++ {
|
||||
if i == len(outBuffs) {
|
||||
return i - 1, ErrTooManySegments
|
||||
}
|
||||
nextSegmentEnd := nextSegmentDataAt + int(hdr.gsoSize)
|
||||
if nextSegmentEnd > len(in) {
|
||||
nextSegmentEnd = len(in)
|
||||
}
|
||||
segmentDataLen := nextSegmentEnd - nextSegmentDataAt
|
||||
totalLen := int(hdr.hdrLen) + segmentDataLen
|
||||
sizes[i] = totalLen
|
||||
out := outBuffs[i][outOffset:]
|
||||
|
||||
copy(out, in[:iphLen])
|
||||
if !isV6 {
|
||||
// For IPv4 we are responsible for incrementing the ID field,
|
||||
// updating the total len field, and recalculating the header
|
||||
// checksum.
|
||||
if i > 0 {
|
||||
id := binary.BigEndian.Uint16(out[4:])
|
||||
id += uint16(i)
|
||||
binary.BigEndian.PutUint16(out[4:], id)
|
||||
}
|
||||
binary.BigEndian.PutUint16(out[2:], uint16(totalLen))
|
||||
ipv4CSum := ^checksum(out[:iphLen], 0)
|
||||
binary.BigEndian.PutUint16(out[10:], ipv4CSum)
|
||||
} else {
|
||||
// For IPv6 we are responsible for updating the payload length field.
|
||||
binary.BigEndian.PutUint16(out[4:], uint16(totalLen-iphLen))
|
||||
}
|
||||
|
||||
// copy transport header
|
||||
copy(out[hdr.csumStart:hdr.hdrLen], in[hdr.csumStart:hdr.hdrLen])
|
||||
|
||||
if protocol == unix.IPPROTO_TCP {
|
||||
// set TCP seq and adjust TCP flags
|
||||
tcpSeq := firstTCPSeqNum + uint32(hdr.gsoSize*uint16(i))
|
||||
binary.BigEndian.PutUint32(out[hdr.csumStart+4:], tcpSeq)
|
||||
if nextSegmentEnd != len(in) {
|
||||
// FIN and PSH should only be set on last segment
|
||||
clearFlags := tcpFlagFIN | tcpFlagPSH
|
||||
out[hdr.csumStart+tcpFlagsOffset] &^= clearFlags
|
||||
}
|
||||
} else {
|
||||
// set UDP header len
|
||||
binary.BigEndian.PutUint16(out[hdr.csumStart+4:], uint16(segmentDataLen)+(hdr.hdrLen-hdr.csumStart))
|
||||
}
|
||||
|
||||
// payload
|
||||
copy(out[hdr.hdrLen:], in[nextSegmentDataAt:nextSegmentEnd])
|
||||
|
||||
// transport checksum
|
||||
transportHeaderLen := int(hdr.hdrLen - hdr.csumStart)
|
||||
lenForPseudo := uint16(transportHeaderLen + segmentDataLen)
|
||||
transportCSum := pseudoHeaderChecksum(protocol, in[srcAddrOffset:srcAddrOffset+addrLen], in[srcAddrOffset+addrLen:srcAddrOffset+addrLen*2], lenForPseudo)
|
||||
transportCSum = ^checksum(out[hdr.csumStart:totalLen], transportCSum)
|
||||
binary.BigEndian.PutUint16(out[hdr.csumStart+hdr.csumOffset:], transportCSum)
|
||||
|
||||
nextSegmentDataAt += int(hdr.gsoSize)
|
||||
}
|
||||
return i, nil
|
||||
}
|
||||
|
||||
func gsoNoneChecksum(in []byte, cSumStart, cSumOffset uint16) error {
|
||||
cSumAt := cSumStart + cSumOffset
|
||||
// The initial value at the checksum offset should be summed with the
|
||||
// checksum we compute. This is typically the pseudo-header checksum.
|
||||
initial := binary.BigEndian.Uint16(in[cSumAt:])
|
||||
in[cSumAt], in[cSumAt+1] = 0, 0
|
||||
binary.BigEndian.PutUint16(in[cSumAt:], ^checksum(in[cSumStart:], initial))
|
||||
return nil
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue