Compare commits

..
Author SHA1 Message Date
JackDoan 1519dbbf8e ipv6: tighten handling of fragments wrt extension headers 2026-09-29 13:20:22 -05:00
JackDoan d576827ade checkpt 2026-09-29 12:50:27 -05:00
13 changed files with 103 additions and 962 deletions

No files matched your search

+3
View File
@@ -457,6 +457,9 @@ firewall:
# Rules are comprised of a protocol, port, and one or more of host, group, or CIDR # Rules are comprised of a protocol, port, and one or more of host, group, or CIDR
# Logical evaluation is roughly: port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND (local cidr) # Logical evaluation is roughly: port AND proto AND (ca_sha OR ca_name) AND (host OR group OR groups OR cidr) AND (local cidr)
# - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available). # - port: Takes `0` or `any` as any, a single number `80`, a range `200-901`, or `fragment` to match second and further fragments of fragmented packets (since there is no port available).
# For IPv6, Nebula can't tell which protocol a second or further fragment belongs to. Any rule that allows them (port `any` or `fragment`,
# and every icmp rule, since icmp ignores ports) allows them for every protocol, not just the rule's. The first fragment, which carries
# the ports, is always checked against its real protocol and port, so this never opens a port the rules don't allow.
# proto: `any`, `tcp`, `udp`, or `icmp` # proto: `any`, `tcp`, `udp`, or `icmp`
# a port specification is ignored if proto is `icmp` # a port specification is ignored if proto is `icmp`
# host: `any` or a literal hostname, ie `test-host` # host: `any` or a literal hostname, ie `test-host`
+35 -4
View File
@@ -11,6 +11,8 @@ import (
// ErrIPv6CouldNotFindPayload is returned when the ipv6 extension header chain is truncated before a terminal // ErrIPv6CouldNotFindPayload is returned when the ipv6 extension header chain is truncated before a terminal
// upper layer protocol is reached. // upper layer protocol is reached.
var ErrIPv6CouldNotFindPayload = errors.New("could not find payload in ipv6 packet") var ErrIPv6CouldNotFindPayload = errors.New("could not find payload in ipv6 packet")
var ErrIPv6ExtensionHeaderAfterFragment = errors.New("extension header after fragment header in packet")
var ErrIPv6HopByHopHeadersMustBeFirst = errors.New("hop-by-hop header must be first extension header")
const ( const (
// MaxIPv4RejectPacketSize is the largest IPv4 reject packet: // MaxIPv4RejectPacketSize is the largest IPv4 reject packet:
@@ -28,6 +30,13 @@ const (
MaxRejectPacketSize = maxIPv6RejectPacketSize MaxRejectPacketSize = maxIPv6RejectPacketSize
IPv6HeaderHopByHop = 0
IPv6HeaderRouting = 43
IPv6HeaderFragment = 44
IPv6NoNextHeader = 59
IPv6HeaderDestination = 60
IPv6HeaderAuthentication = 51
IPProtocolICMP = 1 IPProtocolICMP = 1
IPProtocolICMPv6 = 58 IPProtocolICMPv6 = 58
IPProtocolTCP = 6 IPProtocolTCP = 6
@@ -350,6 +359,10 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal. // Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
// For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate. // For a non-first fragment the returned protocol is the fragmented protocol and offset points at the fragment header, there is no transport header to locate.
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present. // Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
// Returns ErrIPv6HopByHopHeadersMustBeFirst if a hop-by-hop header appears anywhere but directly after the ipv6 header (RFC 8200 section 4.1).
// Returns ErrIPv6ExtensionHeaderAfterFragment if any walked extension header, including a second fragment header, follows the fragment header of a
// first fragment. The upper layer header must then begin at byte 0 of the fragmentable part, beyond the reach of any non-first fragment,
// whose offset is at least 8, so overlapping fragments cannot rewrite the ports or protocol the firewall read from the first fragment.
func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) { func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragment bool, anyFragment bool, err error) {
const maxIPv6ExtHeaders = 8 const maxIPv6ExtHeaders = 8
if len(packet) < ipv6.HeaderLen { if len(packet) < ipv6.HeaderLen {
@@ -360,26 +373,44 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
for range maxIPv6ExtHeaders { for range maxIPv6ExtHeaders {
switch nextHeader { switch nextHeader {
case 0, 43, 60: // Hop-by-Hop, Routing, Destination case IPv6HeaderHopByHop, IPv6HeaderRouting, IPv6HeaderDestination:
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+2 { if len(packet) < offset+2 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload return 0, 0, false, false, ErrIPv6CouldNotFindPayload
} }
if nextHeader == IPv6HeaderHopByHop && offset != ipv6.HeaderLen {
//hop-by-hop must appear first, and only once, if it exists.
return 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst
}
nextHeader = packet[offset] nextHeader = packet[offset]
offset += (int(packet[offset+1]) + 1) << 3 offset += (int(packet[offset+1]) + 1) << 3
case 44: // Fragment case IPv6HeaderFragment:
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+8 { if len(packet) < offset+8 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload return 0, 0, false, false, ErrIPv6CouldNotFindPayload
} }
anyFragment = true anyFragment = true
// Non-first fragments carry no transport header, report the fragmented protocol and stop // Non-first fragments carry no transport header, report the fragmented protocol and stop.
// Per RFC 8200 section 4.5 the receiver only uses the offset zero fragment's next header, so the value
// returned here can't be verified.
if packet[offset+2] != 0 || packet[offset+3]&0xf8 != 0 { if packet[offset+2] != 0 || packet[offset+3]&0xf8 != 0 {
return packet[offset], offset, true, anyFragment, nil return packet[offset], offset, true, anyFragment, nil
} }
nextHeader = packet[offset] nextHeader = packet[offset]
offset += 8 offset += 8
case 51: // AH case IPv6HeaderAuthentication: // AH
if anyFragment {
return 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment
}
if len(packet) < offset+2 { if len(packet) < offset+2 {
return 0, 0, false, false, ErrIPv6CouldNotFindPayload return 0, 0, false, false, ErrIPv6CouldNotFindPayload
} }
+28 -11
View File
@@ -522,21 +522,29 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
dst := net.ParseIP("fd00::2") dst := net.ParseIP("fd00::2")
// 8 byte extension/transport stand-ins, first byte is the next header, second is the length field // 8 byte extension/transport stand-ins, first byte is the next header, second is the length field
extToTCP := []byte{6, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = TCP extToTCP := []byte{6, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = TCP
extToUDP := []byte{17, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = UDP extToUDP := []byte{17, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = UDP
extToRouting := []byte{43, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Routing extToRouting := []byte{43, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Routing
ahToUDP := []byte{17, 0, 0, 0, 0, 0, 0, 0} // AH len 0 -> (0+2)<<2 = 8 bytes, next = UDP ahToUDP := []byte{17, 0, 0, 0, 0, 0, 0, 0} // AH len 0 -> (0+2)<<2 = 8 bytes, next = UDP
firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP firstFragToUDP := []byte{17, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = UDP
nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP nonFirstFrag := []byte{17, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = UDP
transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports transport := []byte{0, 80, 1, 187, 0, 0, 0, 0} // stand-in bytes, IPv6FindUpperProtocol never reads ports
extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop extToHbH := []byte{0, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Hop-by-Hop
extToDst := []byte{60, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Destination
extToFrag := []byte{44, 0, 0, 0, 0, 0, 0, 0} // len 0 -> 8 bytes, next = Fragment
firstFragToDst := []byte{60, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = Destination
firstFragToAH := []byte{51, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = AH
firstFragToFrag := []byte{44, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = Fragment
firstFragToESP := []byte{50, 0, 0, 1, 0, 0, 0, 1} // frag offset 0, M=1, next = ESP
atomicFragToDst := []byte{60, 0, 0, 0, 0, 0, 0, 1} // frag offset 0, M=0, next = Destination
nonFirstFragToDst := []byte{60, 0, 0, 9, 0, 0, 0, 1} // frag offset non-zero, next = Destination
// 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the // 8 walked headers spend the budget before the 9th slot's terminal is ever classified. This is the
// report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports // report 4040546 shape: without failing closed the walk hands back offset 104, and a caller reads ports
// from the attacker's bytes there. // from the attacker's bytes there. Destination is the header that may legally repeat.
var budgetChain []byte var budgetChain []byte
for range 7 { for range 7 {
budgetChain = append(budgetChain, extToHbH...) budgetChain = append(budgetChain, extToDst...)
} }
budgetChain = append(budgetChain, extToTCP...) budgetChain = append(budgetChain, extToTCP...)
budgetChain = append(budgetChain, transport...) budgetChain = append(budgetChain, transport...)
@@ -559,11 +567,20 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
{"ah then udp", 51, append(ahToUDP, transport...), 17, ipv6.HeaderLen + 8, false, false, nil}, {"ah then udp", 51, append(ahToUDP, transport...), 17, ipv6.HeaderLen + 8, false, false, nil},
{"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil}, {"first fragment walks to transport", 44, append(firstFragToUDP, transport...), 17, ipv6.HeaderLen + 8, false, true, nil},
{"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil}, {"non-first fragment stops", 44, append(nonFirstFrag, transport...), 17, ipv6.HeaderLen, true, true, nil},
{"non-first fragment reports its claimed protocol", 44, append(nonFirstFragToDst, transport...), 60, ipv6.HeaderLen, true, true, nil},
{"routing then first fragment", 43, append(append(extToFrag, firstFragToUDP...), transport...), 17, ipv6.HeaderLen + 16, false, true, nil},
{"first fragment of a non-transport protocol is terminal", 44, append(firstFragToESP, transport...), 50, ipv6.HeaderLen + 8, false, true, nil},
{"destination after first fragment", 44, append(append(firstFragToDst, extToTCP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"ah after first fragment", 44, append(append(firstFragToAH, ahToUDP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"fragment after first fragment", 44, append(append(firstFragToFrag, nonFirstFrag...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"destination after atomic fragment", 44, append(append(atomicFragToDst, extToTCP...), transport...), 0, 0, false, false, ErrIPv6ExtensionHeaderAfterFragment},
{"hop-by-hop after destination", 60, append(append(extToHbH, extToTCP...), transport...), 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst},
{"hop-by-hop twice", 0, append(append(extToHbH, extToTCP...), transport...), 0, 0, false, false, ErrIPv6HopByHopHeadersMustBeFirst},
{"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP {"unknown protocol is terminal", 132, transport, 132, ipv6.HeaderLen, false, false, nil}, // SCTP
{"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload}, {"truncated extension header", 0, nil, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
// Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP // Destination Options with a declared length (255+1)*8 = 2048 that runs past the 48 byte buffer, next = SCTP
{"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload}, {"extension length past buffer", 0, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload}, {"budget exhausted fails closed", 60, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
} }
for _, tt := range tests { for _, tt := range tests {
+20
View File
@@ -710,6 +710,26 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload) require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload)
} }
// Test_newPacket_v6ExtHeaderAfterFragment rejects a first fragment whose transport header sits behind another extension
// header. The ports would then start 8 or more bytes into the fragmentable part, where a non-first fragment, filtered
// only as `port: fragment`, could overlap them on a receiver that splices overlapping fragments.
func Test_newPacket_v6ExtHeaderAfterFragment(t *testing.T) {
p := &firewall.ParsedPacket{}
pkt := make([]byte, 60)
pkt[0] = 0x60 // version 6
pkt[6] = byte(layers.IPProtocolIPv6Fragment) // NextHeader -> Fragment
pkt[7] = 64 // hop limit
pkt[40] = byte(layers.IPProtocolIPv6Destination) // Fragment NextHeader -> Destination Options
pkt[43] = 0x01 // offset 0, M=1: a first fragment
pkt[48] = byte(iputil.IPProtocolTCP) // Destination Options NextHeader -> TCP
pkt[49] = 0 // HdrExtLen 0 -> 8 bytes, TCP begins at 56
binary.BigEndian.PutUint16(pkt[58:60], 443) // TCP dst port, reachable by a fragment at offset 8
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6ExtensionHeaderAfterFragment)
require.ErrorIs(t, newPacket(pkt, false, p), iputil.ErrIPv6ExtensionHeaderAfterFragment)
}
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized // Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
// Next Header as if it were an ipv6 extension header. A real upper layer protocol Nebula doesn't // Next Header as if it were an ipv6 extension header. A real upper layer protocol Nebula doesn't
// dissect (SCTP here) is not walkable, so applying the (len+1)*8 formula marched into the SCTP // dissect (SCTP here) is not walkable, so applying the (len+1)*8 formula marched into the SCTP
-62
View File
@@ -435,65 +435,3 @@ func testPP(pkt []byte) *firewall.ParsedPacket {
} }
return pp return pp
} }
// fakeTunBatchWriter records each WriteBatch call and each plain Write separately.
type fakeTunBatchWriter struct {
writes [][]byte
batches [][][]byte
}
func (w *fakeTunBatchWriter) Write(p []byte) (int, error) {
w.writes = append(w.writes, bytes.Clone(p))
return len(p), nil
}
func (w *fakeTunBatchWriter) WriteBatch(pkts [][]byte) error {
var b [][]byte
for _, p := range pkts {
b = append(b, bytes.Clone(p))
}
w.batches = append(w.batches, b)
return nil
}
// TestPassthroughUsesWriteBatch pins that a writer implementing tio.BatchWriter gets the whole
// passthrough lane in one WriteBatch per Flush, in order, and no plain Writes; an empty Flush
// makes no call.
func TestPassthroughUsesWriteBatch(t *testing.T) {
w := &fakeTunBatchWriter{}
m := newTestMultiCoalescer(t, w)
k := &keySeq{epoch: 1}
var want [][]byte
for i := range 5 {
icmp := make([]byte, 28)
icmp[0] = 0x45
icmp[3] = 28
icmp[9] = 1
icmp[20] = byte(i)
want = append(want, icmp)
if err := m.Commit(icmp, k.next(), testPP(icmp)); err != nil {
t.Fatal(err)
}
}
if err := m.Flush(); err != nil {
t.Fatal(err)
}
if err := m.Flush(); err != nil {
t.Fatal(err)
}
if len(w.writes) != 0 {
t.Fatalf("got %d plain Writes, want 0", len(w.writes))
}
if len(w.batches) != 1 {
t.Fatalf("got %d WriteBatch calls, want 1", len(w.batches))
}
for i, p := range w.batches[0] {
if !bytes.Equal(p, want[i]) {
t.Fatalf("packet %d: got % x, want % x", i, p, want[i])
}
}
if len(w.batches[0]) != len(want) {
t.Fatalf("got %d packets, want %d", len(w.batches[0]), len(want))
}
}
+6 -17
View File
@@ -2,23 +2,18 @@ package batch
import ( import (
"io" "io"
"github.com/slackhq/nebula/overlay/tio"
) )
// Passthrough is MultiCoalescer's verbatim lane: no coalescing, packets are written at Flush in the // Passthrough is MultiCoalescer's verbatim lane: no batching, packets are written at Flush in the
// order enqueued, in one WriteBatch when out implements tio.BatchWriter. // order enqueued.
type Passthrough struct { type Passthrough struct {
out io.Writer out io.Writer
bw tio.BatchWriter // nil: Flush writes one packet per Write
slots [][]byte slots [][]byte
} }
func NewPassthrough(w io.Writer) *Passthrough { func NewPassthrough(w io.Writer) *Passthrough {
bw, _ := w.(tio.BatchWriter)
return &Passthrough{ return &Passthrough{
out: w, out: w,
bw: bw,
slots: make([][]byte, 0, 128), slots: make([][]byte, 0, 128),
} }
} }
@@ -31,16 +26,10 @@ func (p *Passthrough) enqueue(pkt []byte) error {
func (p *Passthrough) Flush() error { func (p *Passthrough) Flush() error {
var firstErr error var firstErr error
if p.bw != nil { for _, s := range p.slots {
if len(p.slots) > 0 { _, err := p.out.Write(s)
firstErr = p.bw.WriteBatch(p.slots) if err != nil && firstErr == nil {
} firstErr = err
} else {
for _, s := range p.slots {
_, err := p.out.Write(s)
if err != nil && firstErr == nil {
firstErr = err
}
} }
} }
clear(p.slots) clear(p.slots)
+2 -17
View File
@@ -15,13 +15,9 @@ type singleQueue struct {
// NewSingleQueue wraps a one-datagram-per-Read ReadWriteCloser (a legacy tun device) into a Queue. // NewSingleQueue wraps a one-datagram-per-Read ReadWriteCloser (a legacy tun device) into a Queue.
// bufSize is the per-queue read scratch size and must be at least the largest datagram the source can return. // bufSize is the per-queue read scratch size and must be at least the largest datagram the source can return.
// Close closes rwc. The Queue implements BatchWriter when rwc does. // Close closes rwc.
func NewSingleQueue(rwc io.ReadWriteCloser, bufSize int) Queue { func NewSingleQueue(rwc io.ReadWriteCloser, bufSize int) Queue {
q := &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)} return &singleQueue{rw: rwc, closer: rwc, buf: make([]byte, bufSize)}
if bw, ok := rwc.(BatchWriter); ok {
return &batchSingleQueue{singleQueue: q, bw: bw}
}
return q
} }
// NewSingleQueueNoClose is NewSingleQueue for a source owned by someone else, // NewSingleQueueNoClose is NewSingleQueue for a source owned by someone else,
@@ -51,14 +47,3 @@ func (q *singleQueue) Close() error {
} }
return q.closer.Close() return q.closer.Close()
} }
// batchSingleQueue is a singleQueue whose source also implements BatchWriter.
// It is a separate type so a plain singleQueue never advertises WriteBatch.
type batchSingleQueue struct {
*singleQueue
bw BatchWriter
}
func (q *batchSingleQueue) WriteBatch(pkts [][]byte) error {
return q.bw.WriteBatch(pkts)
}
-11
View File
@@ -145,14 +145,3 @@ func SupportsGSO(w io.Writer, want GSOProto) (GSOWriter, bool) {
return gw, false return gw, false
} }
} }
// BatchWriter is implemented by Queues that can emit several already-segmented packets in one call.
// Backends without a batched write do not implement it and callers loop over Write.
//
// pkts are borrowed: WriteBatch must not retain them past its return.
// A returned error doesn't say which packets were delivered, so callers must not retry the batch.
// Safe for concurrent use, like Write.
type BatchWriter interface {
io.Writer
WriteBatch(pkts [][]byte) error
}
+8 -175
View File
@@ -8,7 +8,6 @@ import (
"log/slog" "log/slog"
"net/netip" "net/netip"
"os" "os"
"sync"
"sync/atomic" "sync/atomic"
"syscall" "syscall"
"unsafe" "unsafe"
@@ -34,35 +33,6 @@ type tun struct {
// and routes for it. NEPacketTunnelProvider on darwin does this. // and routes for it. NEPacketTunnelProvider on darwin does this.
hostOwned bool hostOwned bool
l *slog.Logger l *slog.Logger
// noSendmsgX is set once sendmsg_x is refused; WriteBatch then writes one packet at a time.
noSendmsgX atomic.Bool
batchMu sync.Mutex
batch tunBatch
}
// tunWriteBatch is how many packets one sendmsg_x call may carry.
const tunWriteBatch = 64
// tunBatch is WriteBatch's scratch, guarded by tun.batchMu. The kernel reads every entry in place.
type tunBatch struct {
heads [tunWriteBatch][4]byte
iovs [tunWriteBatch][2]unix.Iovec
hdrs [tunWriteBatch]msghdrX
pkts [tunWriteBatch][]byte
}
// msghdrX mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h).
// Keep in sync with msghdrX in udp/udp_darwin.go.
type msghdrX struct {
Name *byte
Namelen uint32
Iov *unix.Iovec
Iovlen int32
Control *byte
Controllen uint32
Flags int32
Datalen uint64
} }
type ifReq struct { type ifReq struct {
@@ -645,12 +615,16 @@ func (t *tun) Write(from []byte) (int, error) {
return 0, syscall.EIO return 0, syscall.EIO
} }
ipVer := from[0] >> 4
var head [4]byte var head [4]byte
af, err := tunAF(from) switch ipVer {
if err != nil { case 4:
return 0, err head[3] = syscall.AF_INET
case 6:
head[3] = syscall.AF_INET6
default:
return 0, fmt.Errorf("unable to determine IP version from packet")
} }
head[3] = af
// Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack. // Grab rc as a local so the compiler can devirtualize the call and keep the closure on the stack.
rc, err := t.f.SyscallConn() rc, err := t.f.SyscallConn()
@@ -683,147 +657,6 @@ func (t *tun) Write(from []byte) (int, error) {
return n - 4, nil return n - 4, nil
} }
// tunAF returns the utun address-family prefix byte for an IP packet.
func tunAF(pkt []byte) (byte, error) {
switch pkt[0] >> 4 {
case 4:
return syscall.AF_INET, nil
case 6:
return syscall.AF_INET6, nil
default:
return 0, fmt.Errorf("unable to determine IP version from packet")
}
}
// WriteBatch writes pkts to the utun device with sendmsg_x, xnu's private batched sendmsg, up to
// tunWriteBatch packets per syscall. The kernel still hands each packet to utun on its own, so this
// saves syscalls, not per-packet kernel work. Safe for concurrent use.
//
// An empty packet or one with no IP version is skipped and reported, as Write would. Any other
// error from sendmsg_x means the kernel took an unknown prefix of that call and dropped the rest, so
// it is reported rather than retried, which could deliver packets twice.
//
// Under mbuf exhaustion, sendmsg_x silently drops packets that writev would have delivered: the
// kernel counts each packet as sent once it is copied in, and when a later allocation fails it
// frees that prefix unsent and returns its length as a short count, which is indistinguishable
// from a real one.
func (t *tun) WriteBatch(pkts [][]byte) error {
if t.noSendmsgX.Load() {
return t.writeEach(pkts)
}
t.batchMu.Lock()
defer t.batchMu.Unlock()
b := &t.batch
var firstErr error
for len(pkts) > 0 {
n := 0
for len(pkts) > 0 && n < tunWriteBatch {
p := pkts[0]
pkts = pkts[1:]
var af byte
err := error(syscall.EIO)
if len(p) > 0 {
af, err = tunAF(p)
}
if err != nil {
if firstErr == nil {
firstErr = err
}
continue
}
b.heads[n] = [4]byte{3: af}
b.iovs[n] = [2]unix.Iovec{
{Base: &b.heads[n][0], Len: 4},
{Base: &p[0], Len: uint64(len(p))},
}
b.hdrs[n] = msghdrX{Iov: &b.iovs[n][0], Iovlen: 2}
b.pkts[n] = p
n++
}
if n == 0 {
continue
}
for off := 0; off < n; {
sent, err := t.sendmsgX(off, n)
switch {
case err == nil && sent > 0:
// The kernel stops early without an error on a packet larger than the socket's send
// buffer, or when sending a later packet fails with ENOBUFS; resend the remainder.
off += sent
case err == nil:
if werr := t.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
firstErr = werr
}
off = n
case err == unix.EMSGSIZE:
// Only the first packet being larger than the socket's send buffer fails the whole call,
// before the kernel takes any; Write reports that one and the rest go out in the next call.
if werr := t.writeEach(b.pkts[off : off+1]); werr != nil && firstErr == nil {
firstErr = werr
}
off++
case err == unix.ENOSYS || err == unix.EPERM || err == unix.EOPNOTSUPP:
// sendmsg_x is private API: fall back to writev if a kernel or sandbox refuses it.
if t.noSendmsgX.CompareAndSwap(false, true) {
t.l.Warn("sendmsg_x unavailable on the tun device, writing one packet per syscall", "error", err)
}
if werr := t.writeEach(b.pkts[off:n]); werr != nil && firstErr == nil {
firstErr = werr
}
clear(b.iovs[:n])
clear(b.pkts[:n])
if werr := t.writeEach(pkts); werr != nil && firstErr == nil {
firstErr = werr
}
return firstErr
default:
if firstErr == nil {
firstErr = err
}
off = n
}
}
clear(b.iovs[:n])
clear(b.pkts[:n])
}
return firstErr
}
// sendmsgX hands entries off through n-1 of t.batch to sendmsg_x and returns how many the kernel took.
func (t *tun) sendmsgX(off, n int) (int, error) {
rc, err := t.f.SyscallConn()
if err != nil {
return 0, err
}
var sent uintptr
var errno syscall.Errno
err = rc.Write(func(fd uintptr) bool {
sent, _, errno = unix.Syscall6(unix.SYS_SENDMSG_X, fd, uintptr(unsafe.Pointer(&t.batch.hdrs[off])), uintptr(n-off), 0, 0, 0)
// sendmsg_x reports EAGAIN only when it took nothing; a partial batch returns its count.
return !errno.Temporary()
})
if err != nil {
return 0, err
}
if errno != 0 {
return 0, errno
}
return int(sent), nil
}
// writeEach writes pkts one at a time with Write.
func (t *tun) writeEach(pkts [][]byte) error {
var firstErr error
for _, p := range pkts {
if _, err := t.Write(p); err != nil && firstErr == nil {
firstErr = err
}
}
return firstErr
}
func (t *tun) Networks() []netip.Prefix { func (t *tun) Networks() []netip.Prefix {
return t.vpnNetworks return t.vpnNetworks
} }
-153
View File
@@ -1,153 +0,0 @@
//go:build !ios && !e2e_testing
package overlay
import (
"bytes"
"os"
"syscall"
"testing"
"github.com/slackhq/nebula/test"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// newSocketpairTun returns a tun writing to one end of a connected AF_UNIX datagram socketpair, which
// takes sendmsg_x the way a utun control socket does, and the other end's fd for reading back.
// sndbuf is the writer's send buffer, which caps the largest datagram it accepts.
func newSocketpairTun(t *testing.T, sndbuf int) (*tun, int) {
t.Helper()
fds, err := unix.Socketpair(unix.AF_UNIX, unix.SOCK_DGRAM, 0)
require.NoError(t, err)
require.NoError(t, unix.SetsockoptInt(fds[0], unix.SOL_SOCKET, unix.SO_SNDBUF, sndbuf))
require.NoError(t, unix.SetsockoptInt(fds[1], unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
// A dropped datagram fails the read-back instead of hanging it.
require.NoError(t, unix.SetsockoptTimeval(fds[1], unix.SOL_SOCKET, unix.SO_RCVTIMEO, &unix.Timeval{Sec: 2}))
require.NoError(t, unix.SetNonblock(fds[0], true))
f := os.NewFile(uintptr(fds[0]), "socketpair")
t.Cleanup(func() {
_ = f.Close()
_ = unix.Close(fds[1])
})
return &tun{f: f, l: test.NewLogger()}, fds[1]
}
// testTunPkt returns packet i of size bytes, alternating IPv4 and IPv6, and the datagram the utun
// device should receive for it.
func testTunPkt(i, size int) (pkt, wire []byte) {
pkt = make([]byte, size)
pkt[0] = 0x45
af := byte(syscall.AF_INET)
if i%2 == 1 {
pkt[0] = 0x60
af = syscall.AF_INET6
}
pkt[1] = byte(i)
pkt[2] = byte(i >> 8)
return pkt, append([]byte{0, 0, 0, af}, pkt...)
}
// readTunBack asserts r receives exactly want, in order.
func readTunBack(t *testing.T, r int, want [][]byte) {
t.Helper()
buf := make([]byte, 4096)
for i, w := range want {
n, _, err := unix.Recvfrom(r, buf, 0)
require.NoError(t, err, "datagram %d", i)
if !bytes.Equal(w, buf[:n]) {
t.Fatalf("datagram %d: got % x, want % x", i, buf[:n], w)
}
}
_, _, err := unix.Recvfrom(r, buf, unix.MSG_DONTWAIT)
assert.ErrorIs(t, err, unix.EAGAIN, "extra datagrams delivered")
}
// forEachTunWritePath runs fn once over sendmsg_x and once over the per-packet writev fallback.
func forEachTunWritePath(t *testing.T, fn func(t *testing.T, fallback bool)) {
for _, fallback := range []bool{false, true} {
name := "sendmsg_x"
if fallback {
name = "writev"
}
t.Run(name, func(t *testing.T) { fn(t, fallback) })
}
}
// TestTunWriteBatch pins that WriteBatch delivers every packet whole, in order and behind the right
// utun AF prefix, across several sendmsg_x calls, and returns nil.
func TestTunWriteBatch(t *testing.T) {
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
tn, r := newSocketpairTun(t, 1<<20)
tn.noSendmsgX.Store(fallback)
var pkts, want [][]byte
for i := range 3*tunWriteBatch + 5 {
p, w := testTunPkt(i, 60+i)
pkts = append(pkts, p)
want = append(want, w)
}
require.NoError(t, tn.WriteBatch(pkts))
assert.Equal(t, fallback, tn.noSendmsgX.Load())
readTunBack(t, r, want)
})
}
// TestTunWriteBatchSkipsInvalid pins that an empty packet or one with no IP version is skipped
// without shifting the packets after it, and that the first such error is the one reported.
func TestTunWriteBatchSkipsInvalid(t *testing.T) {
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
tn, r := newSocketpairTun(t, 1<<20)
tn.noSendmsgX.Store(fallback)
var pkts, want [][]byte
for i := range 20 {
p, w := testTunPkt(i, 60)
pkts = append(pkts, p)
want = append(want, w)
}
pkts = append(pkts[:10], append([][]byte{{0x10, 1, 2}, {}}, pkts[10:]...)...)
err := tn.WriteBatch(pkts)
assert.ErrorContains(t, err, "IP version")
readTunBack(t, r, want)
})
}
// TestTunWriteBatchOversize pins that a packet larger than the socket's send buffer drops only
// itself and is reported, whether sendmsg_x reaches it mid-call (a short count) or first (EMSGSIZE
// for the whole call). The send buffer is 1024 bytes and the oversize packet 2000.
func TestTunWriteBatchOversize(t *testing.T) {
for _, tc := range []struct {
name string
at int
}{
{"mid-call", tunWriteBatch + 6},
{"first-in-call", tunWriteBatch},
} {
t.Run(tc.name, func(t *testing.T) {
forEachTunWritePath(t, func(t *testing.T, fallback bool) {
tn, r := newSocketpairTun(t, 1024)
tn.noSendmsgX.Store(fallback)
var pkts, want [][]byte
for i := range 2*tunWriteBatch + 10 {
size := 100
if i == tc.at {
size = 2000
}
p, w := testTunPkt(i, size)
pkts = append(pkts, p)
if i != tc.at {
want = append(want, w)
}
}
err := tn.WriteBatch(pkts)
assert.ErrorIs(t, err, unix.EMSGSIZE)
assert.Equal(t, fallback, tn.noSendmsgX.Load())
readTunBack(t, r, want)
})
})
}
}
+1 -125
View File
@@ -180,122 +180,11 @@ func NewUDPStatsEmitter(udpConns []Conn) func() {
return func() {} return func() {}
} }
// recvBatch is how many datagrams one recvmsg_x call may return.
const recvBatch = 64
// msghdrX mirrors xnu's struct msghdr_x (bsd/sys/socket_private.h). recvmsg_x reports each
// datagram's length in Datalen rather than in its return value.
// Keep in sync with msghdrX in overlay/tun_darwin.go.
type msghdrX struct {
Name *byte
Namelen uint32
Iov *unix.Iovec
Iovlen int32
Control *byte
Controllen uint32
Flags int32
Datalen uint64
}
// ListenOut drains the socket with recvmsg_x, darwin's private batched recvmsg, so one syscall reads
// up to recvBatch datagrams instead of one. Sends stay on sendto: xnu batches sendmsg_x through
// the stack only on connected sockets, and on this unconnected one it loops sendit per message.
func (u *StdConn) ListenOut(r EncReader, flush func()) error { func (u *StdConn) ListenOut(r EncReader, flush func()) error {
rc, err := u.UDPConn.SyscallConn()
if err != nil {
return err
}
bufs := make([][]byte, recvBatch)
names := make([]unix.RawSockaddrInet6, recvBatch)
iovs := make([]unix.Iovec, recvBatch)
hdrs := make([]msghdrX, recvBatch)
for i := range hdrs {
bufs[i] = make([]byte, MTU)
iovs[i].Base = &bufs[i][0]
iovs[i].SetLen(MTU)
hdrs[i].Iov = &iovs[i]
hdrs[i].Iovlen = 1
hdrs[i].Name = (*byte)(unsafe.Pointer(&names[i]))
}
for {
var n int
var errno syscall.Errno
err := rc.Read(func(fd uintptr) bool {
for i := range hdrs {
hdrs[i].Namelen = unix.SizeofSockaddrInet6
hdrs[i].Flags = 0
hdrs[i].Datalen = 0
}
r0, _, e := unix.Syscall6(unix.SYS_RECVMSG_X, fd, uintptr(unsafe.Pointer(&hdrs[0])), recvBatch, 0, 0, 0)
if e == unix.EAGAIN {
return false
}
n, errno = int(r0), e
return true
})
if err != nil {
if errors.Is(err, net.ErrClosed) {
return err
}
u.l.Error("unexpected udp socket receive error", "error", err)
continue
}
if errno == unix.ENOSYS || errno == unix.EPERM || errno == unix.EOPNOTSUPP {
// recvmsg_x is private, so a kernel or sandbox (such as an iOS extension's) may refuse it.
u.l.Warn("recvmsg_x unavailable, reading one datagram per syscall", "error", errno)
return u.listenOutSingle(r, flush)
}
if errno != 0 {
if errno != unix.EINTR {
u.l.Error("unexpected udp socket receive error", "error", errno)
}
continue
}
if err := checkMsghdrX(hdrs, names, n); err != nil {
// The batch was read through a layout the kernel no longer writes, so none of it is trustworthy.
u.l.Warn("recvmsg_x returned an unexpected header, reading one datagram per syscall", "error", err)
return u.listenOutSingle(r, flush)
}
for i := 0; i < n; i++ {
addr, ok := sockaddrToAddrPort(&names[i])
if !ok {
continue
}
l := int(hdrs[i].Datalen)
r(addr, bufs[i][:l:l])
}
flush()
}
}
// checkMsghdrX rejects a recvmsg_x result that intact msghdr_x entries can't produce, which is how a change
// to xnu's private struct layout would show up.
func checkMsghdrX(hdrs []msghdrX, names []unix.RawSockaddrInet6, n int) error {
if n > len(hdrs) {
return fmt.Errorf("returned %d datagrams for %d headers", n, len(hdrs))
}
for i := range n {
if hdrs[i].Datalen > MTU {
return fmt.Errorf("datagram %d is %d bytes, past the %d byte buffer", i, hdrs[i].Datalen, MTU)
}
switch {
case names[i].Family == unix.AF_INET && hdrs[i].Namelen == unix.SizeofSockaddrInet4:
case names[i].Family == unix.AF_INET6 && hdrs[i].Namelen == unix.SizeofSockaddrInet6:
default:
return fmt.Errorf("datagram %d has address family %d with length %d", i, names[i].Family, hdrs[i].Namelen)
}
}
return nil
}
// listenOutSingle reads one datagram per recvfrom and flushes after each, for when recvmsg_x is refused or misbehaves.
func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
buffer := make([]byte, MTU) buffer := make([]byte, MTU)
for { for {
// Just read one packet at a time
n, rua, err := u.ReadFromUDPAddrPort(buffer) n, rua, err := u.ReadFromUDPAddrPort(buffer)
if err != nil { if err != nil {
if errors.Is(err, net.ErrClosed) { if errors.Is(err, net.ErrClosed) {
@@ -310,19 +199,6 @@ func (u *StdConn) listenOutSingle(r EncReader, flush func()) error {
} }
} }
func sockaddrToAddrPort(sa *unix.RawSockaddrInet6) (netip.AddrPort, bool) {
switch sa.Family {
case unix.AF_INET:
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:])
return netip.AddrPortFrom(netip.AddrFrom4(sa4.Addr), port), true
case unix.AF_INET6:
port := binary.BigEndian.Uint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:])
return netip.AddrPortFrom(netip.AddrFrom16(sa.Addr).Unmap(), port), true
}
return netip.AddrPort{}, false
}
func (u *StdConn) SupportsMultipleReaders() bool { func (u *StdConn) SupportsMultipleReaders() bool {
return false return false
} }
-85
View File
@@ -1,85 +0,0 @@
//go:build !e2e_testing
package udp
import (
"log/slog"
"net"
"net/netip"
"sync"
"sync/atomic"
"testing"
)
// BenchmarkListenOut measures the receive path on loopback: senders flood datagrams sized like a full tunnel
// packet, and each op is one datagram delivered to the reader. There are enough senders that the reader, not the
// senders, sets the pace. flushes/pkt is 1 when every receive is its own syscall and falls as receives batch. The
// senders share the machine, so ns/op is only comparable between runs on the same host.
func BenchmarkListenOut(b *testing.B) {
for _, tc := range []struct{ name, listen string }{
{"v4", "127.0.0.1"},
{"v6", "::1"},
} {
b.Run(tc.name, func(b *testing.B) {
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
if err != nil {
b.Fatal(err)
}
la, err := c.LocalAddr()
if err != nil {
b.Fatal(err)
}
const size, senders = 1300, 4
txs := make([]net.Conn, senders)
for i := range txs {
if txs[i], err = net.Dial("udp", la.String()); err != nil {
b.Fatal(err)
}
defer txs[i].Close()
}
target := int64(b.N)
var got, flushes atomic.Int64
reached := make(chan struct{})
done := make(chan struct{})
go func() {
_ = c.ListenOut(func(netip.AddrPort, []byte) {
if got.Add(1) == target {
close(reached)
}
}, func() { flushes.Add(1) })
close(done)
}()
// Writes fail with ENOBUFS while the send queue is full; the flood only has to keep the receiver busy.
stop := make(chan struct{})
var sent sync.WaitGroup
for _, tx := range txs {
sent.Go(func() {
payload := make([]byte, size)
for {
select {
case <-stop:
return
default:
_, _ = tx.Write(payload)
}
}
})
}
b.SetBytes(size)
b.ResetTimer()
<-reached
b.StopTimer()
close(stop)
sent.Wait()
if err := c.Close(); err != nil {
b.Fatal(err)
}
<-done
b.ReportMetric(float64(flushes.Load())/float64(got.Load()), "flushes/pkt")
})
}
}
-302
View File
@@ -1,302 +0,0 @@
//go:build !e2e_testing
package udp
import (
"bytes"
"fmt"
"log/slog"
"net"
"net/netip"
"sync"
"syscall"
"testing"
"time"
"unsafe"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
)
// A burst larger than recvBatch arrives whole, with each datagram's own bytes and source address, and
// flush runs once per recvmsg_x batch rather than once per datagram.
func TestListenOutBatchesBurst(t *testing.T) {
for _, tc := range []struct{ name, listen string }{
{"v4", "127.0.0.1"},
{"v6", "::1"},
} {
t.Run(tc.name, func(t *testing.T) {
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.AddrPortFrom(netip.MustParseAddr(tc.listen), 0)})
require.NoError(t, err)
la, err := c.LocalAddr()
require.NoError(t, err)
tx, err := net.Dial("udp", la.String())
require.NoError(t, err)
defer tx.Close()
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
const total = recvBatch*3 + 7
var mu sync.Mutex
var got []string
var froms []netip.AddrPort
flushes := 0
// Queued before the reader starts, so recvmsg_x sees full batches.
for i := 0; i < total; i++ {
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
require.NoError(t, err)
}
done := make(chan struct{})
go func() {
_ = c.ListenOut(func(addr netip.AddrPort, payload []byte) {
mu.Lock()
got = append(got, string(payload))
froms = append(froms, addr)
mu.Unlock()
}, func() {
mu.Lock()
flushes++
mu.Unlock()
})
close(done)
}()
require.Eventually(t, func() bool {
mu.Lock()
defer mu.Unlock()
return len(got) == total
}, 5*time.Second, 10*time.Millisecond)
require.NoError(t, c.Close())
<-done
for i, p := range got {
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
assert.Equal(t, txAddr, froms[i])
}
assert.Equal(t, (total+recvBatch-1)/recvBatch, flushes)
})
}
}
// msghdrX round-trips through xnu's recvmsg_x on a loopback socket, v4 and v6. The kernel reads Name, Namelen,
// Iov and Iovlen from each entry and writes Namelen, Flags and Datalen back, so a field at the wrong offset or a
// wrong stride between entries shows up as a wrong length, sender, or payload.
// TestListenOutSingleFallback pins the path ListenOut takes when the kernel refuses recvmsg_x.
func TestListenOutSingleFallback(t *testing.T) {
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
require.NoError(t, err)
la, err := c.LocalAddr()
require.NoError(t, err)
tx, err := net.Dial("udp", la.String())
require.NoError(t, err)
defer tx.Close()
txAddr := netip.MustParseAddrPort(tx.LocalAddr().String())
const total = 5
for i := 0; i < total; i++ {
_, err := tx.Write([]byte(fmt.Sprintf("pkt-%03d", i)))
require.NoError(t, err)
}
var mu sync.Mutex
var got []string
flushes := 0
done := make(chan struct{})
go func() {
_ = c.(*StdConn).listenOutSingle(func(addr netip.AddrPort, payload []byte) {
assert.Equal(t, txAddr, addr)
mu.Lock()
got = append(got, string(payload))
mu.Unlock()
}, func() {
mu.Lock()
flushes++
mu.Unlock()
})
close(done)
}()
require.Eventually(t, func() bool {
mu.Lock()
defer mu.Unlock()
return len(got) == total
}, 5*time.Second, 10*time.Millisecond)
require.NoError(t, c.Close())
<-done
for i, p := range got {
assert.Equal(t, fmt.Sprintf("pkt-%03d", i), p)
}
assert.Equal(t, total, flushes)
}
func TestCheckMsghdrX(t *testing.T) {
valid := func() ([]msghdrX, []unix.RawSockaddrInet6) {
hdrs := make([]msghdrX, 2)
names := make([]unix.RawSockaddrInet6, 2)
hdrs[0].Namelen, hdrs[0].Datalen = unix.SizeofSockaddrInet4, 1
names[0].Family = unix.AF_INET
hdrs[1].Namelen, hdrs[1].Datalen = unix.SizeofSockaddrInet6, MTU
names[1].Family = unix.AF_INET6
return hdrs, names
}
hdrs, names := valid()
require.NoError(t, checkMsghdrX(hdrs, names, 2))
require.NoError(t, checkMsghdrX(hdrs, names, 0))
for _, tc := range []struct {
name string
n int
mutate func([]msghdrX, []unix.RawSockaddrInet6)
}{
{"count past headers", 3, func([]msghdrX, []unix.RawSockaddrInet6) {}},
{"datalen past buffer", 2, func(h []msghdrX, _ []unix.RawSockaddrInet6) { h[1].Datalen = MTU + 1 }},
{"unknown family", 2, func(_ []msghdrX, a []unix.RawSockaddrInet6) { a[0].Family = unix.AF_UNIX }},
{"family and length disagree", 2, func(h []msghdrX, _ []unix.RawSockaddrInet6) { h[0].Namelen = unix.SizeofSockaddrInet6 }},
} {
t.Run(tc.name, func(t *testing.T) {
hdrs, names := valid()
tc.mutate(hdrs, names)
assert.Error(t, checkMsghdrX(hdrs, names, tc.n))
})
}
}
func TestMsghdrXKernelRoundTrip(t *testing.T) {
for _, v6 := range []bool{false, true} {
t.Run(fmt.Sprintf("v6=%v", v6), func(t *testing.T) {
// Loopback delivery goes through the dlil input thread, so the settle gives all three time to
// queue and come back from one call, which is what exercises the stride.
got := recvmsgXRoundTrip(t, v6, []int{1, 300, 1400}, 4, 50*time.Millisecond)
assert.Equal(t, 3, got, "largest batch from one recvmsg_x call")
})
}
}
// Any burst, of any datagram lengths up to the kernel's maxdgram, into any number of headers, comes back in order
// with every entry's fields intact, and headers past the returned count untouched.
func FuzzMsghdrXKernelRoundTrip(f *testing.F) {
f.Add(false, uint8(3), []byte{0, 1, 1, 44, 5, 120})
f.Add(true, uint8(0), []byte{0, 0, 0x23, 0x29}) // one empty datagram, then one at MTU
f.Add(false, uint8(1), []byte{0x23, 0x2a, 0x24, 0x00, 0}) // past MTU: cut to MTU, no MSG_TRUNC
f.Add(true, uint8(recvBatch-1), bytes.Repeat([]byte{0x05, 0xdc}, recvBatch))
f.Fuzz(func(t *testing.T, v6 bool, spare uint8, sizes []byte) {
// Two bytes per datagram, big-endian, folded into [0, maxdgram].
var lens []int
for i := 0; i+1 < len(sizes) && len(lens) < recvBatch; i += 2 {
lens = append(lens, (int(sizes[i])<<8|int(sizes[i+1]))%(maxDgram+1))
}
if len(lens) == 0 {
return
}
recvmsgXRoundTrip(t, v6, lens, 1+int(spare)%recvBatch, time.Millisecond)
})
}
// maxDgram is darwin's default net.inet.udp.maxdgram, the largest datagram a loopback sender may write.
const maxDgram = 9216
// recvmsgXRoundTrip sends one datagram per entry of lens to a fresh loopback socket, drains them with recvmsg_x
// into nh headers, and checks every field the kernel writes. Neighboring datagrams differ in sender, length and
// fill byte, so no field can pass by reading a neighbor's value. It returns the largest batch one call returned.
func recvmsgXRoundTrip(t *testing.T, v6 bool, lens []int, nh int, settle time.Duration) int {
t.Helper()
network, lo := "udp4", netip.MustParseAddr("127.0.0.1")
if v6 {
network, lo = "udp6", netip.IPv6Loopback()
}
rx, err := net.ListenUDP(network, net.UDPAddrFromAddrPort(netip.AddrPortFrom(lo, 0)))
require.NoError(t, err)
defer rx.Close()
txs := make([]*net.UDPConn, 3)
for i := range txs {
txs[i], err = net.DialUDP(network, nil, rx.LocalAddr().(*net.UDPAddr))
require.NoError(t, err)
defer txs[i].Close()
}
senders := make([]netip.AddrPort, len(lens))
for i, l := range lens {
tx := txs[i%len(txs)]
senders[i] = tx.LocalAddr().(*net.UDPAddr).AddrPort()
_, err := tx.Write(bytes.Repeat([]byte{byte(i + 1)}, l))
require.NoError(t, err)
}
time.Sleep(settle)
// Namelen goes in as the v6 size on both families, so the v4 size coming back proves the kernel wrote it.
const sentinel = 0xa5a5a5a5a5a5a5a5
wantNamelen := uint32(unix.SizeofSockaddrInet4)
if v6 {
wantNamelen = unix.SizeofSockaddrInet6
}
bufs := make([][]byte, nh)
names := make([]unix.RawSockaddrInet6, nh)
iovs := make([]unix.Iovec, nh)
hdrs := make([]msghdrX, nh)
for i := range hdrs {
bufs[i] = make([]byte, MTU)
iovs[i].Base = &bufs[i][0]
iovs[i].SetLen(MTU)
}
// A datagram dropped on loopback would otherwise block rc.Read forever.
require.NoError(t, rx.SetReadDeadline(time.Now().Add(5*time.Second)))
rc, err := rx.SyscallConn()
require.NoError(t, err)
largest := 0
for next := 0; next < len(lens); {
for i := range hdrs {
clear(bufs[i])
hdrs[i] = msghdrX{
Name: (*byte)(unsafe.Pointer(&names[i])),
Namelen: unix.SizeofSockaddrInet6,
Iov: &iovs[i],
Iovlen: 1,
Flags: -1,
Datalen: sentinel,
}
}
var n int
var errno syscall.Errno
require.NoError(t, rc.Read(func(fd uintptr) bool {
r0, _, e := unix.Syscall6(unix.SYS_RECVMSG_X, fd, uintptr(unsafe.Pointer(&hdrs[0])), uintptr(nh), 0, 0, 0)
n, errno = int(r0), e
return e != unix.EAGAIN
}), "received %d of %d datagrams", next, len(lens))
require.Zero(t, errno)
require.Positive(t, n)
require.LessOrEqual(t, n, min(nh, len(lens)-next))
largest = max(largest, n)
require.NoError(t, checkMsghdrX(hdrs[:nh], names[:nh], n), "ListenOut would fall back on this batch")
for i := range n {
d := next + i
h := &hdrs[i]
want := min(lens[d], MTU)
require.EqualValues(t, want, h.Datalen, "datagram %d Datalen", d)
require.Equal(t, wantNamelen, h.Namelen, "datagram %d Namelen", d)
from, ok := sockaddrToAddrPort(&names[i])
require.True(t, ok, "datagram %d family %d", d, names[i].Family)
require.Equal(t, senders[d], from, "datagram %d sender", d)
// Flags goes in as -1 and must come back 0. xnu's list receive (soreceive_m_list) never sets
// MSG_TRUNC, so a datagram past MTU arrives silently cut to MTU, as recvfrom through net.UDPConn does.
require.Zero(t, h.Flags, "datagram %d Flags", d)
require.Equal(t, bytes.Repeat([]byte{byte(d + 1)}, want), bufs[i][:want], "datagram %d payload", d)
if want < MTU {
require.Zero(t, bufs[i][want], "datagram %d wrote past Datalen", d)
}
}
for i := n; i < nh; i++ {
require.EqualValues(t, uint64(sentinel), hdrs[i].Datalen, "spare header %d Datalen", i)
require.EqualValues(t, unix.SizeofSockaddrInet6, hdrs[i].Namelen, "spare header %d Namelen", i)
}
next += n
}
return largest
}