summaryrefslogtreecommitdiffhomepage
path: root/pkg/tcpip/transport/raw/endpoint.go
blob: 0a1e1fbb32073e49827cdefc38b444158d6e9999 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
// Copyright 2019 The gVisor Authors.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

// Package raw provides the implementation of raw sockets (see raw(7)). Raw
// sockets allow applications to:
//
//   * manually write and inspect transport layer headers and payloads
//   * receive all traffic of a given transport protocol (e.g. ICMP or UDP)
//   * optionally write and inspect network layer headers of packets
//
// Raw sockets don't have any notion of ports, and incoming packets are
// demultiplexed solely by protocol number. Thus, a raw UDP endpoint will
// receive every UDP packet received by netstack. bind(2) and connect(2) can be
// used to filter incoming packets by source and destination.
package raw

import (
	"fmt"

	"gvisor.dev/gvisor/pkg/sync"
	"gvisor.dev/gvisor/pkg/tcpip"
	"gvisor.dev/gvisor/pkg/tcpip/buffer"
	"gvisor.dev/gvisor/pkg/tcpip/header"
	"gvisor.dev/gvisor/pkg/tcpip/stack"
	"gvisor.dev/gvisor/pkg/waiter"
)

// +stateify savable
type rawPacket struct {
	rawPacketEntry
	// data holds the actual packet data, including any headers and
	// payload.
	data buffer.VectorisedView `state:".(buffer.VectorisedView)"`
	// timestampNS is the unix time at which the packet was received.
	timestampNS int64
	// senderAddr is the network address of the sender.
	senderAddr tcpip.FullAddress
}

// endpoint is the raw socket implementation of tcpip.Endpoint. It is legal to
// have goroutines make concurrent calls into the endpoint.
//
// Lock order:
//   endpoint.mu
//     endpoint.rcvMu
//
// +stateify savable
type endpoint struct {
	stack.TransportEndpointInfo
	// The following fields are initialized at creation time and are
	// immutable.
	stack       *stack.Stack `state:"manual"`
	waiterQueue *waiter.Queue
	associated  bool
	hdrIncluded bool

	// The following fields are used to manage the receive queue and are
	// protected by rcvMu.
	rcvMu         sync.Mutex `state:"nosave"`
	rcvList       rawPacketList
	rcvBufSize    int
	rcvBufSizeMax int `state:".(int)"`
	rcvClosed     bool

	// The following fields are protected by mu.
	mu            sync.RWMutex `state:"nosave"`
	sndBufSize    int
	sndBufSizeMax int
	closed        bool
	connected     bool
	bound         bool
	// route is the route to a remote network endpoint. It is set via
	// Connect(), and is valid only when conneted is true.
	route stack.Route                  `state:"manual"`
	stats tcpip.TransportEndpointStats `state:"nosave"`
	// linger is used for SO_LINGER socket option.
	linger tcpip.LingerOption

	// owner is used to get uid and gid of the packet.
	owner tcpip.PacketOwner

	// ops is used to get socket level options.
	ops tcpip.SocketOptions
}

// NewEndpoint returns a raw  endpoint for the given protocols.
func NewEndpoint(stack *stack.Stack, netProto tcpip.NetworkProtocolNumber, transProto tcpip.TransportProtocolNumber, waiterQueue *waiter.Queue) (tcpip.Endpoint, *tcpip.Error) {
	return newEndpoint(stack, netProto, transProto, waiterQueue, true /* associated */)
}

func newEndpoint(s *stack.Stack, netProto tcpip.NetworkProtocolNumber, transProto tcpip.TransportProtocolNumber, waiterQueue *waiter.Queue, associated bool) (tcpip.Endpoint, *tcpip.Error) {
	if netProto != header.IPv4ProtocolNumber && netProto != header.IPv6ProtocolNumber {
		return nil, tcpip.ErrUnknownProtocol
	}

	e := &endpoint{
		stack: s,
		TransportEndpointInfo: stack.TransportEndpointInfo{
			NetProto:   netProto,
			TransProto: transProto,
		},
		waiterQueue:   waiterQueue,
		rcvBufSizeMax: 32 * 1024,
		sndBufSizeMax: 32 * 1024,
		associated:    associated,
		hdrIncluded:   !associated,
	}

	// Override with stack defaults.
	var ss stack.SendBufferSizeOption
	if err := s.Option(&ss); err == nil {
		e.sndBufSizeMax = ss.Default
	}

	var rs stack.ReceiveBufferSizeOption
	if err := s.Option(&rs); err == nil {
		e.rcvBufSizeMax = rs.Default
	}

	// Unassociated endpoints are write-only and users call Write() with IP
	// headers included. Because they're write-only, We don't need to
	// register with the stack.
	if !associated {
		e.rcvBufSizeMax = 0
		e.waiterQueue = nil
		return e, nil
	}

	if err := e.stack.RegisterRawTransportEndpoint(e.RegisterNICID, e.NetProto, e.TransProto, e); err != nil {
		return nil, err
	}

	return e, nil
}

// Abort implements stack.TransportEndpoint.Abort.
func (e *endpoint) Abort() {
	e.Close()
}

// Close implements tcpip.Endpoint.Close.
func (e *endpoint) Close() {
	e.mu.Lock()
	defer e.mu.Unlock()

	if e.closed || !e.associated {
		return
	}

	e.stack.UnregisterRawTransportEndpoint(e.RegisterNICID, e.NetProto, e.TransProto, e)

	e.rcvMu.Lock()
	defer e.rcvMu.Unlock()

	// Clear the receive list.
	e.rcvClosed = true
	e.rcvBufSize = 0
	for !e.rcvList.Empty() {
		e.rcvList.Remove(e.rcvList.Front())
	}

	if e.connected {
		e.route.Release()
		e.connected = false
	}

	e.closed = true

	e.waiterQueue.Notify(waiter.EventHUp | waiter.EventErr | waiter.EventIn | waiter.EventOut)
}

// ModerateRecvBuf implements tcpip.Endpoint.ModerateRecvBuf.
func (e *endpoint) ModerateRecvBuf(copied int) {}

func (e *endpoint) SetOwner(owner tcpip.PacketOwner) {
	e.owner = owner
}

// Read implements tcpip.Endpoint.Read.
func (e *endpoint) Read(addr *tcpip.FullAddress) (buffer.View, tcpip.ControlMessages, *tcpip.Error) {
	e.rcvMu.Lock()

	// If there's no data to read, return that read would block or that the
	// endpoint is closed.
	if e.rcvList.Empty() {
		err := tcpip.ErrWouldBlock
		if e.rcvClosed {
			e.stats.ReadErrors.ReadClosed.Increment()
			err = tcpip.ErrClosedForReceive
		}
		e.rcvMu.Unlock()
		return buffer.View{}, tcpip.ControlMessages{}, err
	}

	pkt := e.rcvList.Front()
	e.rcvList.Remove(pkt)
	e.rcvBufSize -= pkt.data.Size()

	e.rcvMu.Unlock()

	if addr != nil {
		*addr = pkt.senderAddr
	}

	return pkt.data.ToView(), tcpip.ControlMessages{HasTimestamp: true, Timestamp: pkt.timestampNS}, nil
}

// Write implements tcpip.Endpoint.Write.
func (e *endpoint) Write(p tcpip.Payloader, opts tcpip.WriteOptions) (int64, <-chan struct{}, *tcpip.Error) {
	// We can create, but not write to, unassociated IPv6 endpoints.
	if !e.associated && e.TransportEndpointInfo.NetProto == header.IPv6ProtocolNumber {
		return 0, nil, tcpip.ErrInvalidOptionValue
	}

	n, ch, err := e.write(p, opts)
	switch err {
	case nil:
		e.stats.PacketsSent.Increment()
	case tcpip.ErrMessageTooLong, tcpip.ErrInvalidOptionValue:
		e.stats.WriteErrors.InvalidArgs.Increment()
	case tcpip.ErrClosedForSend:
		e.stats.WriteErrors.WriteClosed.Increment()
	case tcpip.ErrInvalidEndpointState:
		e.stats.WriteErrors.InvalidEndpointState.Increment()
	case tcpip.ErrNoLinkAddress:
		e.stats.SendErrors.NoLinkAddr.Increment()
	case tcpip.ErrNoRoute, tcpip.ErrBroadcastDisabled, tcpip.ErrNetworkUnreachable:
		// Errors indicating any problem with IP routing of the packet.
		e.stats.SendErrors.NoRoute.Increment()
	default:
		// For all other errors when writing to the network layer.
		e.stats.SendErrors.SendToNetworkFailed.Increment()
	}
	return n, ch, err
}

func (e *endpoint) write(p tcpip.Payloader, opts tcpip.WriteOptions) (int64, <-chan struct{}, *tcpip.Error) {
	// MSG_MORE is unimplemented. This also means that MSG_EOR is a no-op.
	if opts.More {
		return 0, nil, tcpip.ErrInvalidOptionValue
	}

	e.mu.RLock()

	if e.closed {
		e.mu.RUnlock()
		return 0, nil, tcpip.ErrInvalidEndpointState
	}

	payloadBytes, err := p.FullPayload()
	if err != nil {
		e.mu.RUnlock()
		return 0, nil, err
	}

	// If this is an unassociated socket and callee provided a nonzero
	// destination address, route using that address.
	if e.hdrIncluded {
		ip := header.IPv4(payloadBytes)
		if !ip.IsValid(len(payloadBytes)) {
			e.mu.RUnlock()
			return 0, nil, tcpip.ErrInvalidOptionValue
		}
		dstAddr := ip.DestinationAddress()
		// Update dstAddr with the address in the IP header, unless
		// opts.To is set (e.g. if sendto specifies a specific
		// address).
		if dstAddr != tcpip.Address([]byte{0, 0, 0, 0}) && opts.To == nil {
			opts.To = &tcpip.FullAddress{
				NIC:  0,       // NIC is unset.
				Addr: dstAddr, // The address from the payload.
				Port: 0,       // There are no ports here.
			}
		}
	}

	// Did the user caller provide a destination? If not, use the connected
	// destination.
	if opts.To == nil {
		// If the user doesn't specify a destination, they should have
		// connected to another address.
		if !e.connected {
			e.mu.RUnlock()
			return 0, nil, tcpip.ErrDestinationRequired
		}

		if e.route.IsResolutionRequired() {
			savedRoute := &e.route
			// Promote lock to exclusive if using a shared route,
			// given that it may need to change in finishWrite.
			e.mu.RUnlock()
			e.mu.Lock()

			// Make sure that the route didn't change during the
			// time we didn't hold the lock.
			if !e.connected || savedRoute != &e.route {
				e.mu.Unlock()
				return 0, nil, tcpip.ErrInvalidEndpointState
			}

			n, ch, err := e.finishWrite(payloadBytes, savedRoute)
			e.mu.Unlock()
			return n, ch, err
		}

		n, ch, err := e.finishWrite(payloadBytes, &e.route)
		e.mu.RUnlock()
		return n, ch, err
	}

	// The caller provided a destination. Reject destination address if it
	// goes through a different NIC than the endpoint was bound to.
	nic := opts.To.NIC
	if e.bound && nic != 0 && nic != e.BindNICID {
		e.mu.RUnlock()
		return 0, nil, tcpip.ErrNoRoute
	}

	// Find the route to the destination. If BindAddress is 0,
	// FindRoute will choose an appropriate source address.
	route, err := e.stack.FindRoute(nic, e.BindAddr, opts.To.Addr, e.NetProto, false)
	if err != nil {
		e.mu.RUnlock()
		return 0, nil, err
	}

	n, ch, err := e.finishWrite(payloadBytes, &route)
	route.Release()
	e.mu.RUnlock()
	return n, ch, err
}

// finishWrite writes the payload to a route. It resolves the route if
// necessary. It's really just a helper to make defer unnecessary in Write.
func (e *endpoint) finishWrite(payloadBytes []byte, route *stack.Route) (int64, <-chan struct{}, *tcpip.Error) {
	// We may need to resolve the route (match a link layer address to the
	// network address). If that requires blocking (e.g. to use ARP),
	// return a channel on which the caller can wait.
	if route.IsResolutionRequired() {
		if ch, err := route.Resolve(nil); err != nil {
			if err == tcpip.ErrWouldBlock {
				return 0, ch, tcpip.ErrNoLinkAddress
			}
			return 0, nil, err
		}
	}

	if e.hdrIncluded {
		pkt := stack.NewPacketBuffer(stack.PacketBufferOptions{
			Data: buffer.View(payloadBytes).ToVectorisedView(),
		})
		if err := route.WriteHeaderIncludedPacket(pkt); err != nil {
			return 0, nil, err
		}
	} else {
		pkt := stack.NewPacketBuffer(stack.PacketBufferOptions{
			ReserveHeaderBytes: int(route.MaxHeaderLength()),
			Data:               buffer.View(payloadBytes).ToVectorisedView(),
		})
		pkt.Owner = e.owner
		if err := route.WritePacket(nil /* gso */, stack.NetworkHeaderParams{
			Protocol: e.TransProto,
			TTL:      route.DefaultTTL(),
			TOS:      stack.DefaultTOS,
		}, pkt); err != nil {
			return 0, nil, err
		}
	}

	return int64(len(payloadBytes)), nil, nil
}

// Peek implements tcpip.Endpoint.Peek.
func (e *endpoint) Peek([][]byte) (int64, tcpip.ControlMessages, *tcpip.Error) {
	return 0, tcpip.ControlMessages{}, nil
}

// Disconnect implements tcpip.Endpoint.Disconnect.
func (*endpoint) Disconnect() *tcpip.Error {
	return tcpip.ErrNotSupported
}

// Connect implements tcpip.Endpoint.Connect.
func (e *endpoint) Connect(addr tcpip.FullAddress) *tcpip.Error {
	e.mu.Lock()
	defer e.mu.Unlock()

	if e.closed {
		return tcpip.ErrInvalidEndpointState
	}

	nic := addr.NIC
	if e.bound {
		if e.BindNICID == 0 {
			// If we're bound, but not to a specific NIC, the NIC
			// in addr will be used. Nothing to do here.
		} else if addr.NIC == 0 {
			// If we're bound to a specific NIC, but addr doesn't
			// specify a NIC, use the bound NIC.
			nic = e.BindNICID
		} else if addr.NIC != e.BindNICID {
			// We're bound and addr specifies a NIC. They must be
			// the same.
			return tcpip.ErrInvalidEndpointState
		}
	}

	// Find a route to the destination.
	route, err := e.stack.FindRoute(nic, tcpip.Address(""), addr.Addr, e.NetProto, false)
	if err != nil {
		return err
	}
	defer route.Release()

	if e.associated {
		// Re-register the endpoint with the appropriate NIC.
		if err := e.stack.RegisterRawTransportEndpoint(addr.NIC, e.NetProto, e.TransProto, e); err != nil {
			return err
		}
		e.stack.UnregisterRawTransportEndpoint(e.RegisterNICID, e.NetProto, e.TransProto, e)
		e.RegisterNICID = nic
	}

	// Save the route we've connected via.
	e.route = route.Clone()
	e.connected = true

	return nil
}

// Shutdown implements tcpip.Endpoint.Shutdown. It's a noop for raw sockets.
func (e *endpoint) Shutdown(flags tcpip.ShutdownFlags) *tcpip.Error {
	e.mu.Lock()
	defer e.mu.Unlock()

	if !e.connected {
		return tcpip.ErrNotConnected
	}
	return nil
}

// Listen implements tcpip.Endpoint.Listen.
func (*endpoint) Listen(backlog int) *tcpip.Error {
	return tcpip.ErrNotSupported
}

// Accept implements tcpip.Endpoint.Accept.
func (*endpoint) Accept(*tcpip.FullAddress) (tcpip.Endpoint, *waiter.Queue, *tcpip.Error) {
	return nil, nil, tcpip.ErrNotSupported
}

// Bind implements tcpip.Endpoint.Bind.
func (e *endpoint) Bind(addr tcpip.FullAddress) *tcpip.Error {
	e.mu.Lock()
	defer e.mu.Unlock()

	// If a local address was specified, verify that it's valid.
	if len(addr.Addr) != 0 && e.stack.CheckLocalAddress(addr.NIC, e.NetProto, addr.Addr) == 0 {
		return tcpip.ErrBadLocalAddress
	}

	if e.associated {
		// Re-register the endpoint with the appropriate NIC.
		if err := e.stack.RegisterRawTransportEndpoint(addr.NIC, e.NetProto, e.TransProto, e); err != nil {
			return err
		}
		e.stack.UnregisterRawTransportEndpoint(e.RegisterNICID, e.NetProto, e.TransProto, e)
		e.RegisterNICID = addr.NIC
		e.BindNICID = addr.NIC
	}

	e.BindAddr = addr.Addr
	e.bound = true

	return nil
}

// GetLocalAddress implements tcpip.Endpoint.GetLocalAddress.
func (*endpoint) GetLocalAddress() (tcpip.FullAddress, *tcpip.Error) {
	return tcpip.FullAddress{}, tcpip.ErrNotSupported
}

// GetRemoteAddress implements tcpip.Endpoint.GetRemoteAddress.
func (*endpoint) GetRemoteAddress() (tcpip.FullAddress, *tcpip.Error) {
	// Even a connected socket doesn't return a remote address.
	return tcpip.FullAddress{}, tcpip.ErrNotConnected
}

// Readiness implements tcpip.Endpoint.Readiness.
func (e *endpoint) Readiness(mask waiter.EventMask) waiter.EventMask {
	// The endpoint is always writable.
	result := waiter.EventOut & mask

	// Determine whether the endpoint is readable.
	if (mask & waiter.EventIn) != 0 {
		e.rcvMu.Lock()
		if !e.rcvList.Empty() || e.rcvClosed {
			result |= waiter.EventIn
		}
		e.rcvMu.Unlock()
	}

	return result
}

// SetSockOpt implements tcpip.Endpoint.SetSockOpt.
func (e *endpoint) SetSockOpt(opt tcpip.SettableSocketOption) *tcpip.Error {
	switch v := opt.(type) {
	case *tcpip.SocketDetachFilterOption:
		return nil

	case *tcpip.LingerOption:
		e.mu.Lock()
		e.linger = *v
		e.mu.Unlock()
		return nil

	default:
		return tcpip.ErrUnknownProtocolOption
	}
}

// SetSockOptBool implements tcpip.Endpoint.SetSockOptBool.
func (e *endpoint) SetSockOptBool(opt tcpip.SockOptBool, v bool) *tcpip.Error {
	switch opt {
	case tcpip.IPHdrIncludedOption:
		e.mu.Lock()
		e.hdrIncluded = v
		e.mu.Unlock()
		return nil
	}
	return tcpip.ErrUnknownProtocolOption
}

// SetSockOptInt implements tcpip.Endpoint.SetSockOptInt.
func (e *endpoint) SetSockOptInt(opt tcpip.SockOptInt, v int) *tcpip.Error {
	switch opt {
	case tcpip.SendBufferSizeOption:
		// Make sure the send buffer size is within the min and max
		// allowed.
		var ss stack.SendBufferSizeOption
		if err := e.stack.Option(&ss); err != nil {
			panic(fmt.Sprintf("s.Option(%#v) = %s", ss, err))
		}
		if v > ss.Max {
			v = ss.Max
		}
		if v < ss.Min {
			v = ss.Min
		}
		e.mu.Lock()
		e.sndBufSizeMax = v
		e.mu.Unlock()
		return nil

	case tcpip.ReceiveBufferSizeOption:
		// Make sure the receive buffer size is within the min and max
		// allowed.
		var rs stack.ReceiveBufferSizeOption
		if err := e.stack.Option(&rs); err != nil {
			panic(fmt.Sprintf("s.Option(%#v) = %s", rs, err))
		}
		if v > rs.Max {
			v = rs.Max
		}
		if v < rs.Min {
			v = rs.Min
		}
		e.rcvMu.Lock()
		e.rcvBufSizeMax = v
		e.rcvMu.Unlock()
		return nil

	default:
		return tcpip.ErrUnknownProtocolOption
	}
}

// GetSockOpt implements tcpip.Endpoint.GetSockOpt.
func (e *endpoint) GetSockOpt(opt tcpip.GettableSocketOption) *tcpip.Error {
	switch o := opt.(type) {
	case *tcpip.LingerOption:
		e.mu.Lock()
		*o = e.linger
		e.mu.Unlock()
		return nil

	default:
		return tcpip.ErrUnknownProtocolOption
	}
}

// GetSockOptBool implements tcpip.Endpoint.GetSockOptBool.
func (e *endpoint) GetSockOptBool(opt tcpip.SockOptBool) (bool, *tcpip.Error) {
	switch opt {
	case tcpip.KeepaliveEnabledOption, tcpip.AcceptConnOption:
		return false, nil

	case tcpip.IPHdrIncludedOption:
		e.mu.Lock()
		v := e.hdrIncluded
		e.mu.Unlock()
		return v, nil

	default:
		return false, tcpip.ErrUnknownProtocolOption
	}
}

// GetSockOptInt implements tcpip.Endpoint.GetSockOptInt.
func (e *endpoint) GetSockOptInt(opt tcpip.SockOptInt) (int, *tcpip.Error) {
	switch opt {
	case tcpip.ReceiveQueueSizeOption:
		v := 0
		e.rcvMu.Lock()
		if !e.rcvList.Empty() {
			p := e.rcvList.Front()
			v = p.data.Size()
		}
		e.rcvMu.Unlock()
		return v, nil

	case tcpip.SendBufferSizeOption:
		e.mu.Lock()
		v := e.sndBufSizeMax
		e.mu.Unlock()
		return v, nil

	case tcpip.ReceiveBufferSizeOption:
		e.rcvMu.Lock()
		v := e.rcvBufSizeMax
		e.rcvMu.Unlock()
		return v, nil

	default:
		return -1, tcpip.ErrUnknownProtocolOption
	}
}

// HandlePacket implements stack.RawTransportEndpoint.HandlePacket.
func (e *endpoint) HandlePacket(pkt *stack.PacketBuffer) {
	e.rcvMu.Lock()

	// Drop the packet if our buffer is currently full or if this is an unassociated
	// endpoint (i.e endpoint created  w/ IPPROTO_RAW). Such endpoints are send only
	// See: https://man7.org/linux/man-pages/man7/raw.7.html
	//
	//    An IPPROTO_RAW socket is send only.  If you really want to receive
	//    all IP packets, use a packet(7) socket with the ETH_P_IP protocol.
	//    Note that packet sockets don't reassemble IP fragments, unlike raw
	//    sockets.
	if e.rcvClosed || !e.associated {
		e.rcvMu.Unlock()
		e.stack.Stats().DroppedPackets.Increment()
		e.stats.ReceiveErrors.ClosedReceiver.Increment()
		return
	}

	if e.rcvBufSize >= e.rcvBufSizeMax {
		e.rcvMu.Unlock()
		e.stack.Stats().DroppedPackets.Increment()
		e.stats.ReceiveErrors.ReceiveBufferOverflow.Increment()
		return
	}

	remoteAddr := pkt.Network().SourceAddress()

	if e.bound {
		// If bound to a NIC, only accept data for that NIC.
		if e.BindNICID != 0 && e.BindNICID != pkt.NICID {
			e.rcvMu.Unlock()
			return
		}
		// If bound to an address, only accept data for that address.
		if e.BindAddr != "" && e.BindAddr != remoteAddr {
			e.rcvMu.Unlock()
			return
		}
	}

	// If connected, only accept packets from the remote address we
	// connected to.
	if e.connected && e.route.RemoteAddress != remoteAddr {
		e.rcvMu.Unlock()
		return
	}

	wasEmpty := e.rcvBufSize == 0

	// Push new packet into receive list and increment the buffer size.
	packet := &rawPacket{
		senderAddr: tcpip.FullAddress{
			NIC:  pkt.NICID,
			Addr: remoteAddr,
		},
	}

	// Raw IPv4 endpoints return the IP header, but IPv6 endpoints do not.
	// We copy headers' underlying bytes because pkt.*Header may point to
	// the middle of a slice, and another struct may point to the "outer"
	// slice. Save/restore doesn't support overlapping slices and will fail.
	var combinedVV buffer.VectorisedView
	if e.TransportEndpointInfo.NetProto == header.IPv4ProtocolNumber {
		network, transport := pkt.NetworkHeader().View(), pkt.TransportHeader().View()
		headers := make(buffer.View, 0, len(network)+len(transport))
		headers = append(headers, network...)
		headers = append(headers, transport...)
		combinedVV = headers.ToVectorisedView()
	} else {
		combinedVV = append(buffer.View(nil), pkt.TransportHeader().View()...).ToVectorisedView()
	}
	combinedVV.Append(pkt.Data)
	packet.data = combinedVV
	packet.timestampNS = e.stack.Clock().NowNanoseconds()

	e.rcvList.PushBack(packet)
	e.rcvBufSize += packet.data.Size()
	e.rcvMu.Unlock()
	e.stats.PacketsReceived.Increment()
	// Notify waiters that there's data to be read.
	if wasEmpty {
		e.waiterQueue.Notify(waiter.EventIn)
	}
}

// State implements socket.Socket.State.
func (e *endpoint) State() uint32 {
	return 0
}

// Info returns a copy of the endpoint info.
func (e *endpoint) Info() tcpip.EndpointInfo {
	e.mu.RLock()
	// Make a copy of the endpoint info.
	ret := e.TransportEndpointInfo
	e.mu.RUnlock()
	return &ret
}

// Stats returns a pointer to the endpoint stats.
func (e *endpoint) Stats() tcpip.EndpointStats {
	return &e.stats
}

// Wait implements stack.TransportEndpoint.Wait.
func (*endpoint) Wait() {}

// LastError implements tcpip.Endpoint.LastError.
func (*endpoint) LastError() *tcpip.Error {
	return nil
}

// SocketOptions implements tcpip.Endpoint.SocketOptions.
func (e *endpoint) SocketOptions() *tcpip.SocketOptions {
	return &e.ops
}