mirror of
https://github.com/slackhq/nebula.git
synced 2026-08-15 20:47:04 +02:00
aacb4e2334
Multi-disciplinary correctness review of the batched tun / GSO-GRO / sendmmsg rework. Each fix has a regression test; the merged tree builds on linux/darwin/openbsd/windows/freebsd/netbsd, vets clean, passes the unit and e2e suites, and is -race clean. Critical: - C1 zero-length inner UDP datagram no longer panics the process (remote DoS): the UDP coalescer routes payLen==0 to passthrough instead of seeding a GSO slot, and WriteGSO skips empty payload iovecs as defense in depth. - C2 segmenter no longer corrupts inner headers when gsoSize < headerLen: the L3+L4 header is snapshotted once and each segment stamped from the copy, replacing the destructive overlapping in-place slide (SegmentTCP + SegmentUDP). High: - H1 applyOuterECN updates the IPv4 header checksum (RFC 1624 incremental) when folding outer CE into the inner ToS, so passthrough packets are no longer dropped by the peer stack. - H2 the GRO reject path caps the borrowed RX segment ([:n:n]) so a reject can no longer overrun into the next coalesced segment's Nebula header. Note: oversized ICMPv6 rejects that need >16B beyond the segment are now refused rather than sent under GRO (safe; see TOFIX.md for the scratch-buffer follow-up). - H3 WriteBatch falls back to per-packet WriteTo for a chunk when writeSockaddr fails, so one bad-family destination costs only its own packet, not the batch. - H4 UserDevice.Readers returns N distinct queue wrappers with private buffers (sharing the pipes) so concurrent readers no longer race/overwrite borrowed packet bytes. - H5 Poll.Close / Offload.Close no longer null t.fd (matching master's tunFile.Close), removing the data race with a concurrent readOne load. Medium/Low: - M1 the UDP GSO 127-segment gate moved from kernel >=5.5 to >=6.9 (the real UDP_MAX_SEGMENTS 64->128 threshold), avoiding EINVAL + per-packet fallback on 5.5-6.8 kernels. - M2 NewMultiQueueReader replays the offload mask newTun actually negotiated instead of the TSO-only mask, so adding a queue no longer disables USO device-wide; the advertised USO capability derives from the same mask. - M3 the shutdown eventfd is closed in pollQueueSet.Close / offloadQueueSet.Close (double-close guarded), fixing the per-lifecycle fd leak. - M4 dual-stack ECN selects the cmsg by address family, not socket family: RX parseRecvCmsg reads both IP_TOS and IPV6_TCLASS; TX writeEntryCmsg stamps IP_TOS for v4/v4-mapped dests and IPV6_TCLASS for v6 (on-host verified). - L1 newPoll no longer closes the fd on failure (matching newOffload), removing the double-close on QueueSet.Add error.
122 lines
3.1 KiB
Go
122 lines
3.1 KiB
Go
package overlay
|
|
|
|
import (
|
|
"io"
|
|
"log/slog"
|
|
"net/netip"
|
|
|
|
"github.com/slackhq/nebula/config"
|
|
"github.com/slackhq/nebula/overlay/tio"
|
|
"github.com/slackhq/nebula/routing"
|
|
)
|
|
|
|
func NewUserDeviceFromConfig(c *config.C, l *slog.Logger, vpnNetworks []netip.Prefix, routines int) (Device, error) {
|
|
return NewUserDevice(vpnNetworks)
|
|
}
|
|
|
|
func NewUserDevice(vpnNetworks []netip.Prefix) (Device, error) {
|
|
// these pipes guarantee each write/read will match 1:1
|
|
or, ow := io.Pipe()
|
|
ir, iw := io.Pipe()
|
|
return &UserDevice{
|
|
vpnNetworks: vpnNetworks,
|
|
outboundReader: or,
|
|
outboundWriter: ow,
|
|
inboundReader: ir,
|
|
inboundWriter: iw,
|
|
numReaders: 1,
|
|
}, nil
|
|
}
|
|
|
|
type UserDevice struct {
|
|
vpnNetworks []netip.Prefix
|
|
numReaders int
|
|
|
|
outboundReader *io.PipeReader
|
|
outboundWriter *io.PipeWriter
|
|
|
|
inboundReader *io.PipeReader
|
|
inboundWriter *io.PipeWriter
|
|
}
|
|
|
|
// userDeviceQueue is a single tio.Queue over a UserDevice's shared pipes.
|
|
// One is handed to each tun read goroutine by Readers(). All queues delegate
|
|
// reads to the same outboundReader and writes to the same inboundWriter (the
|
|
// io.Pipe serializes concurrent callers), but every queue owns a private
|
|
// readBuf/batchRet so the borrowed Packet.Bytes slice one goroutine returns is
|
|
// never clobbered by another goroutine's concurrent Read.
|
|
type userDeviceQueue struct {
|
|
outboundReader *io.PipeReader
|
|
inboundWriter *io.PipeWriter
|
|
|
|
readBuf []byte
|
|
batchRet [1]tio.Packet
|
|
}
|
|
|
|
func (q *userDeviceQueue) Read() ([]tio.Packet, error) {
|
|
n, err := q.outboundReader.Read(q.readBuf)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
q.batchRet[0] = tio.Packet{Bytes: q.readBuf[:n]}
|
|
return q.batchRet[:], nil
|
|
}
|
|
|
|
func (q *userDeviceQueue) Write(p []byte) (int, error) {
|
|
return q.inboundWriter.Write(p)
|
|
}
|
|
|
|
// Close is a no-op: the shared pipes are owned by the UserDevice and torn
|
|
// down by UserDevice.Close, so an individual queue must not close them out
|
|
// from under its siblings.
|
|
func (q *userDeviceQueue) Close() error {
|
|
return nil
|
|
}
|
|
|
|
func (d *UserDevice) Activate() error {
|
|
return nil
|
|
}
|
|
|
|
func (d *UserDevice) Networks() []netip.Prefix { return d.vpnNetworks }
|
|
func (d *UserDevice) Name() string { return "faketun0" }
|
|
func (d *UserDevice) RoutesFor(ip netip.Addr) routing.Gateways {
|
|
return routing.Gateways{routing.NewGateway(ip, 1)}
|
|
}
|
|
|
|
func (d *UserDevice) SupportsMultiqueue() bool {
|
|
return true
|
|
}
|
|
|
|
func (d *UserDevice) NewMultiQueueReader() error {
|
|
d.numReaders++
|
|
return nil
|
|
}
|
|
|
|
func (d *UserDevice) Readers() []tio.Queue {
|
|
out := make([]tio.Queue, d.numReaders)
|
|
for i := range d.numReaders {
|
|
// Each queue shares the underlying pipes but owns its own scratch
|
|
// buffer so concurrent Reads across queues never alias.
|
|
out[i] = &userDeviceQueue{
|
|
outboundReader: d.outboundReader,
|
|
inboundWriter: d.inboundWriter,
|
|
readBuf: make([]byte, defaultBatchBufSize),
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
func (d *UserDevice) Pipe() (*io.PipeReader, *io.PipeWriter) {
|
|
return d.inboundReader, d.outboundWriter
|
|
}
|
|
|
|
func (d *UserDevice) Write(p []byte) (n int, err error) {
|
|
return d.inboundWriter.Write(p)
|
|
}
|
|
|
|
func (d *UserDevice) Close() error {
|
|
d.inboundWriter.Close()
|
|
d.outboundWriter.Close()
|
|
return nil
|
|
}
|