mirror of
https://github.com/slackhq/nebula.git
synced 2026-11-16 20:56:52 +01:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
16538f5e44 |
No files matched your search
@@ -263,20 +263,6 @@ try {
|
|||||||
}
|
}
|
||||||
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
Write-Host "OK: WSL peer -> windows lighthouse over v6"
|
||||||
|
|
||||||
# The NlMtu check above proves the value was written, not that windows honors it. A payload this size only
|
|
||||||
# crosses the tunnel as fragments cut at NlMtu on the way out of the adapter. Left at the adapter default it
|
|
||||||
# reaches nebula whole, overflows the udp.MTU (9001) write buffer and is dropped, so the ping never answers.
|
|
||||||
# Anything smaller would ride out as one oversized datagram and survive on IP fragmentation of the underlay.
|
|
||||||
$BigPayload = 9000
|
|
||||||
foreach ($target in @(@{ Family = 'v4'; Ip = $Ip2 }, @{ Family = 'v6'; Ip = $Ip6_2 })) {
|
|
||||||
Wait-Until -TimeoutSec 30 -What "$($target.Family) ping with a $BigPayload byte payload from windows lighthouse to WSL peer ($($target.Ip))" -Predicate {
|
|
||||||
if ($peerProc.HasExited) { throw "peer exited (code $($peerProc.ExitCode)) before the large $($target.Family) ping succeeded" }
|
|
||||||
$null = & ping.exe -n 1 -w 1000 -l $BigPayload $target.Ip
|
|
||||||
$LASTEXITCODE -eq 0
|
|
||||||
}
|
|
||||||
Write-Host "OK: windows lighthouse -> WSL peer, $BigPayload byte $($target.Family) payload"
|
|
||||||
}
|
|
||||||
|
|
||||||
Write-Host ''
|
Write-Host ''
|
||||||
Write-Host 'All smoke checks passed.'
|
Write-Host 'All smoke checks passed.'
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -242,14 +242,11 @@ test-cov-html:
|
|||||||
go test -coverprofile=coverage.out
|
go test -coverprofile=coverage.out
|
||||||
go tool cover -html=coverage.out
|
go tool cover -html=coverage.out
|
||||||
|
|
||||||
# The package builds only compile. The final line links an android binary so a linker-only failure
|
|
||||||
# cannot pass CI.
|
|
||||||
build-test-mobile:
|
build-test-mobile:
|
||||||
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
GOARCH=amd64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||||
GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
GOARCH=arm64 GOOS=ios go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||||
GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
GOARCH=amd64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||||
GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
GOARCH=arm64 GOOS=android go build $(shell go list ./... | grep -v '/cmd/\|/examples/')
|
||||||
GOARCH=arm64 GOOS=android go build -o /dev/null ${NEBULA_CMD_PATH}
|
|
||||||
|
|
||||||
bench:
|
bench:
|
||||||
go test -bench=.
|
go test -bench=.
|
||||||
|
|||||||
@@ -5,7 +5,6 @@ go 1.26.0
|
|||||||
require (
|
require (
|
||||||
dario.cat/mergo v1.0.2
|
dario.cat/mergo v1.0.2
|
||||||
filippo.io/bigmod v0.1.0
|
filippo.io/bigmod v0.1.0
|
||||||
github.com/DefinedNet/netlink v1.3.2-dn.1
|
|
||||||
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
|
||||||
github.com/armon/go-radix v1.0.0
|
github.com/armon/go-radix v1.0.0
|
||||||
github.com/flynn/noise v1.1.0
|
github.com/flynn/noise v1.1.0
|
||||||
@@ -21,6 +20,7 @@ require (
|
|||||||
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
|
github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
|
||||||
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
|
github.com/stefanberger/go-pkcs11uri v0.0.0-20230803200340-78284954bff6
|
||||||
github.com/stretchr/testify v1.12.1
|
github.com/stretchr/testify v1.12.1
|
||||||
|
github.com/vishvananda/netlink v1.3.1
|
||||||
go.uber.org/goleak v1.3.0
|
go.uber.org/goleak v1.3.0
|
||||||
go.yaml.in/yaml/v3 v3.0.5
|
go.yaml.in/yaml/v3 v3.0.5
|
||||||
golang.org/x/crypto v0.57.0
|
golang.org/x/crypto v0.57.0
|
||||||
|
|||||||
@@ -3,8 +3,6 @@ dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
|
|||||||
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
|
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
|
||||||
filippo.io/bigmod v0.1.0 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
|
filippo.io/bigmod v0.1.0 h1:UNzDk7y9ADKST+axd9skUpBQeW7fG2KrTZyOE4uGQy8=
|
||||||
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
|
filippo.io/bigmod v0.1.0/go.mod h1:OjOXDNlClLblvXdwgFFOQFJEocLhhtai8vGLy0JCZlI=
|
||||||
github.com/DefinedNet/netlink v1.3.2-dn.1 h1:Md2PsUE1Xuy1Zxs/Bm6356n1kt5bq2HspXlPJ6pEspg=
|
|
||||||
github.com/DefinedNet/netlink v1.3.2-dn.1/go.mod h1:o4YSn8Jw7zoDcYXDmV77TRd4eS5sSLuE+vu2zAN67C8=
|
|
||||||
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||||
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
|
||||||
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
|
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
|
||||||
@@ -140,6 +138,8 @@ github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81P
|
|||||||
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
|
||||||
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
||||||
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
||||||
|
github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW6bV0=
|
||||||
|
github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
|
||||||
github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
|
github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
|
||||||
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
|
||||||
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
|
||||||
@@ -195,6 +195,8 @@ golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7w
|
|||||||
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||||
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||||
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
golang.org/x/sys v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||||
|
golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||||
|
golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||||
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
||||||
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||||
|
|||||||
+58
@@ -6,6 +6,7 @@ import (
|
|||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
|
"net"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"slices"
|
"slices"
|
||||||
"sync"
|
"sync"
|
||||||
@@ -17,6 +18,7 @@ import (
|
|||||||
"github.com/slackhq/nebula/cert"
|
"github.com/slackhq/nebula/cert"
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/header"
|
"github.com/slackhq/nebula/header"
|
||||||
|
"github.com/slackhq/nebula/logging"
|
||||||
)
|
)
|
||||||
|
|
||||||
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
|
const defaultPromoteEvery = 1000 // Count of packets sent before we try moving a tunnel to a preferred underlay ip address
|
||||||
@@ -928,3 +930,59 @@ func (i *HostInfo) logger(l *slog.Logger) *slog.Logger {
|
|||||||
|
|
||||||
return li
|
return li
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Utility functions
|
||||||
|
|
||||||
|
func localAddrs(l *slog.Logger, allowList *LocalAllowList) []netip.Addr {
|
||||||
|
//FIXME: This function is pretty garbage
|
||||||
|
var finalAddrs []netip.Addr
|
||||||
|
ifaces, _ := net.Interfaces()
|
||||||
|
for _, i := range ifaces {
|
||||||
|
allow := allowList.AllowName(i.Name)
|
||||||
|
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||||
|
l.Log(context.Background(), logging.LevelTrace, "localAllowList.AllowName",
|
||||||
|
"interfaceName", i.Name,
|
||||||
|
"allow", allow,
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
if !allow {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
addrs, _ := i.Addrs()
|
||||||
|
for _, rawAddr := range addrs {
|
||||||
|
var addr netip.Addr
|
||||||
|
switch v := rawAddr.(type) {
|
||||||
|
case *net.IPNet:
|
||||||
|
//continue
|
||||||
|
addr, _ = netip.AddrFromSlice(v.IP)
|
||||||
|
case *net.IPAddr:
|
||||||
|
addr, _ = netip.AddrFromSlice(v.IP)
|
||||||
|
}
|
||||||
|
|
||||||
|
if !addr.IsValid() {
|
||||||
|
if l.Enabled(context.Background(), slog.LevelDebug) {
|
||||||
|
l.Debug("addr was invalid", "localAddr", rawAddr)
|
||||||
|
}
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
addr = addr.Unmap()
|
||||||
|
|
||||||
|
if addr.IsLoopback() == false && addr.IsLinkLocalUnicast() == false {
|
||||||
|
isAllowed := allowList.Allow(addr)
|
||||||
|
if l.Enabled(context.Background(), logging.LevelTrace) {
|
||||||
|
l.Log(context.Background(), logging.LevelTrace, "localAllowList.Allow",
|
||||||
|
"localAddr", addr,
|
||||||
|
"allowed", isAllowed,
|
||||||
|
)
|
||||||
|
}
|
||||||
|
if !isAllowed {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
finalAddrs = append(finalAddrs, addr)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return finalAddrs
|
||||||
|
}
|
||||||
+13
-3
@@ -45,7 +45,8 @@ func setTransportChecksum4(packet []byte) {
|
|||||||
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
if ihl < ipv4.HeaderLen || end < ihl || end > len(packet) {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
// do not attempt to set checksums for fragments
|
// The checksum covers the whole datagram, which a fragment (MF set or a
|
||||||
|
// non-zero offset) does not carry.
|
||||||
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
if binary.BigEndian.Uint16(packet[6:8])&0x3fff != 0 {
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
@@ -67,7 +68,10 @@ func setTransportChecksum6(packet []byte) {
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// we must find the transport header in order to write a checksum
|
// The checksum covers the whole datagram, which a fragment does not carry.
|
||||||
|
// An unknown extension header hides where the transport header starts. A
|
||||||
|
// chain longer than the walk's budget ends it early, at an offset that was
|
||||||
|
// never checked against the packet.
|
||||||
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
proto, offset, _, anyFragment, err := IPv6FindUpperProtocol(packet[:end])
|
||||||
if err != nil || anyFragment || offset >= end {
|
if err != nil || anyFragment || offset >= end {
|
||||||
return
|
return
|
||||||
@@ -105,7 +109,8 @@ func transportExtent(transport []byte, proto uint8) ([]byte, bool) {
|
|||||||
// writeTransportChecksum stores the checksum of transport, taken over the
|
// writeTransportChecksum stores the checksum of transport, taken over the
|
||||||
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
// pseudo-header sum csum, in the header's checksum field. A UDP checksum that
|
||||||
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
// computes to zero goes on the wire as 0xffff: zero means no checksum was
|
||||||
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200 section 8.1).
|
// computed (RFC 768), and over IPv6 the checksum is mandatory (RFC 8200
|
||||||
|
// section 8.1).
|
||||||
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
||||||
var at, minLen int
|
var at, minLen int
|
||||||
switch proto {
|
switch proto {
|
||||||
@@ -128,6 +133,11 @@ func writeTransportChecksum(transport []byte, proto uint8, csum uint32) {
|
|||||||
binary.BigEndian.PutUint16(transport[at:], sum)
|
binary.BigEndian.PutUint16(transport[at:], sum)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// fold reduces a pseudo-header sum to the 16 bit seed Checksum takes. Carrying
|
||||||
|
// the high half back into the low half is what keeps the reduction lossless, so
|
||||||
|
// the seed sums exactly as the wider value would; 0xffff is its fixed point.
|
||||||
|
// Every term of that sum comes from a 16 bit field, so it stays far below the
|
||||||
|
// width at which the accumulator would wrap.
|
||||||
func fold(csum uint32) uint16 {
|
func fold(csum uint32) uint16 {
|
||||||
for csum > 0xffff {
|
for csum > 0xffff {
|
||||||
csum = (csum >> 16) + (csum & 0xffff)
|
csum = (csum >> 16) + (csum & 0xffff)
|
||||||
|
|||||||
+16
-13
@@ -345,11 +345,14 @@ func ipv6CreateRejectTCPPacket(packet []byte, out []byte, offset int) []byte {
|
|||||||
return out
|
return out
|
||||||
}
|
}
|
||||||
|
|
||||||
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the offset it begins at, and whether the packet is a non-first fragment.
|
// IPv6FindUpperProtocol walks the ipv6 extension header chain and returns the upper layer protocol, the
|
||||||
// Only the RFC 8200 and IANA extension headers below are walked.
|
// offset it begins at, and whether the packet is a non-first fragment. Only the RFC 8200 and IANA extension
|
||||||
// Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental 253/254, and real upper layer protocols like SCTP or GRE, is terminal.
|
// headers below are walked. Everything else, including Mobility (135), HIP (139), Shim6 (140), experimental
|
||||||
// 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.
|
// 253/254, and real upper layer protocols like SCTP or GRE, is terminal. Walking those as extension headers
|
||||||
// Returns ErrIPv6CouldNotFindPayload if packet is smaller than an ipv6 header, or the chain is truncated, or if more than 8 extension headers are present.
|
// is a firewall bypass, so they fail closed. 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 before a
|
||||||
|
// terminal protocol is reached.
|
||||||
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 {
|
||||||
@@ -362,14 +365,14 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
|||||||
switch nextHeader {
|
switch nextHeader {
|
||||||
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
case 0, 43, 60: // Hop-by-Hop, Routing, Destination
|
||||||
if len(packet) < offset+2 {
|
if len(packet) < offset+2 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
}
|
}
|
||||||
nextHeader = packet[offset]
|
nextHeader = packet[offset]
|
||||||
offset += (int(packet[offset+1]) + 1) << 3
|
offset += (int(packet[offset+1]) + 1) << 3
|
||||||
|
|
||||||
case 44: // Fragment
|
case 44: // Fragment
|
||||||
if len(packet) < offset+8 {
|
if len(packet) < offset+8 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, 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
|
||||||
@@ -381,21 +384,21 @@ func IPv6FindUpperProtocol(packet []byte) (nextHeader uint8, offset int, isFragm
|
|||||||
|
|
||||||
case 51: // AH
|
case 51: // AH
|
||||||
if len(packet) < offset+2 {
|
if len(packet) < offset+2 {
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
}
|
}
|
||||||
nextHeader = packet[offset]
|
nextHeader = packet[offset]
|
||||||
offset += (int(packet[offset+1]) + 2) << 2
|
offset += (int(packet[offset+1]) + 2) << 2
|
||||||
|
|
||||||
default:
|
default:
|
||||||
|
// A prior extension header can declare a length that advances offset past the packet. The terminal
|
||||||
|
// protocol's header isn't actually here, so treat the chain as truncated rather than classifying it.
|
||||||
if offset > len(packet) {
|
if offset > len(packet) {
|
||||||
// A prior extension header can declare a length that advances offset past the packet, reject this.
|
return nextHeader, offset, isFragment, anyFragment, ErrIPv6CouldNotFindPayload
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
|
||||||
}
|
}
|
||||||
return nextHeader, offset, isFragment, anyFragment, nil //success!
|
return nextHeader, offset, isFragment, anyFragment, nil
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// Fail closed
|
return nextHeader, offset, isFragment, anyFragment, nil
|
||||||
return 0, 0, false, false, ErrIPv6CouldNotFindPayload
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
func CreateICMPEchoResponse(packet, out []byte) []byte {
|
||||||
|
|||||||
+5
-17
@@ -529,17 +529,6 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
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
|
|
||||||
|
|
||||||
// 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
|
|
||||||
// from the attacker's bytes there.
|
|
||||||
var budgetChain []byte
|
|
||||||
for range 7 {
|
|
||||||
budgetChain = append(budgetChain, extToHbH...)
|
|
||||||
}
|
|
||||||
budgetChain = append(budgetChain, extToTCP...)
|
|
||||||
budgetChain = append(budgetChain, transport...)
|
|
||||||
|
|
||||||
tests := []struct {
|
tests := []struct {
|
||||||
name string
|
name string
|
||||||
@@ -560,10 +549,9 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
{"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},
|
||||||
{"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, ipv6.HeaderLen, 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", 60, []byte{132, 255, 0, 0, 0, 0, 0, 0}, 132, ipv6.HeaderLen + 2048, false, false, ErrIPv6CouldNotFindPayload},
|
||||||
{"budget exhausted fails closed", 0, budgetChain, 0, 0, false, false, ErrIPv6CouldNotFindPayload},
|
|
||||||
}
|
}
|
||||||
|
|
||||||
for _, tt := range tests {
|
for _, tt := range tests {
|
||||||
@@ -571,10 +559,10 @@ func Test_IPv6FindUpperProtocol(t *testing.T) {
|
|||||||
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
packet := makeIPv6Packet(src, dst, tt.nextHeader, tt.payload)
|
||||||
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
proto, offset, isFragment, anyFragment, err := IPv6FindUpperProtocol(packet)
|
||||||
if tt.wantErr != nil {
|
if tt.wantErr != nil {
|
||||||
require.ErrorIs(t, err, tt.wantErr)
|
assert.ErrorIs(t, err, tt.wantErr)
|
||||||
} else {
|
return
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
}
|
||||||
|
require.NoError(t, err)
|
||||||
assert.Equal(t, tt.wantProto, proto)
|
assert.Equal(t, tt.wantProto, proto)
|
||||||
assert.Equal(t, tt.wantOffset, offset)
|
assert.Equal(t, tt.wantOffset, offset)
|
||||||
assert.Equal(t, tt.wantFragment, isFragment)
|
assert.Equal(t, tt.wantFragment, isFragment)
|
||||||
|
|||||||
+1
-28
@@ -19,7 +19,6 @@ import (
|
|||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/header"
|
"github.com/slackhq/nebula/header"
|
||||||
"github.com/slackhq/nebula/logging"
|
"github.com/slackhq/nebula/logging"
|
||||||
"github.com/slackhq/nebula/nicfinder"
|
|
||||||
"github.com/slackhq/nebula/udp"
|
"github.com/slackhq/nebula/udp"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
)
|
)
|
||||||
@@ -43,10 +42,6 @@ type LightHouse struct {
|
|||||||
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
// addresses rather than whatever this machine's NICs happen to be. Set it before Start.
|
||||||
localAddrsFn func(*LocalAllowList) []netip.Addr
|
localAddrsFn func(*LocalAllowList) []netip.Addr
|
||||||
|
|
||||||
// lastLocalAddrsErr is the previous localAddrsFn failure. Enumeration runs on every update, so an
|
|
||||||
// unchanged failure is demoted to Debug rather than warning every lighthouse.interval forever.
|
|
||||||
lastLocalAddrsErr atomic.Pointer[string]
|
|
||||||
|
|
||||||
// Local cache of answers from light houses
|
// Local cache of answers from light houses
|
||||||
// map of vpn addr to answers
|
// map of vpn addr to answers
|
||||||
addrMap map[netip.Addr]*RemoteList
|
addrMap map[netip.Addr]*RemoteList
|
||||||
@@ -120,9 +115,7 @@ func NewLightHouseFromConfig(ctx context.Context, l *slog.Logger, c *config.C, c
|
|||||||
l: l,
|
l: l,
|
||||||
}
|
}
|
||||||
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
h.localAddrsFn = func(al *LocalAllowList) []netip.Addr {
|
||||||
addrs, err := nicfinder.Find(ctx, h.l, al)
|
return localAddrs(h.l, al)
|
||||||
h.logLocalAddrsErr(err)
|
|
||||||
return addrs
|
|
||||||
}
|
}
|
||||||
|
|
||||||
lighthouses := make([]netip.Addr, 0)
|
lighthouses := make([]netip.Addr, 0)
|
||||||
@@ -923,26 +916,6 @@ func (lh *LightHouse) TriggerUpdate() {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// logLocalAddrsErr reports a localAddrs failure at Warn the first time it is seen and at Debug while
|
|
||||||
// it persists unchanged, so a permanent failure does not warn on every update forever.
|
|
||||||
func (lh *LightHouse) logLocalAddrsErr(err error) {
|
|
||||||
if err == nil {
|
|
||||||
lh.lastLocalAddrsErr.Store(nil)
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
msg := err.Error()
|
|
||||||
prev := lh.lastLocalAddrsErr.Swap(&msg)
|
|
||||||
if prev != nil && *prev == msg {
|
|
||||||
if lh.l.Enabled(context.Background(), slog.LevelDebug) {
|
|
||||||
lh.l.Debug("Failed to collect local addresses to advertise", "error", err)
|
|
||||||
}
|
|
||||||
return
|
|
||||||
}
|
|
||||||
|
|
||||||
lh.l.Warn("Failed to collect local addresses to advertise", "error", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
func (lh *LightHouse) SendUpdate() {
|
func (lh *LightHouse) SendUpdate() {
|
||||||
var v4 []*V4AddrPort
|
var v4 []*V4AddrPort
|
||||||
var v6 []*V6AddrPort
|
var v6 []*V6AddrPort
|
||||||
|
|||||||
@@ -1,9 +1,7 @@
|
|||||||
package nebula
|
package nebula
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"bytes"
|
|
||||||
"encoding/binary"
|
"encoding/binary"
|
||||||
"errors"
|
|
||||||
"fmt"
|
"fmt"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"testing"
|
"testing"
|
||||||
@@ -766,32 +764,3 @@ func TestLighthouse_DeletesWork(t *testing.T) {
|
|||||||
out = lh.Query(testHost)
|
out = lh.Query(testHost)
|
||||||
assert.Nil(t, out)
|
assert.Nil(t, out)
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestLightHouse_logLocalAddrsErr(t *testing.T) {
|
|
||||||
out := &bytes.Buffer{}
|
|
||||||
lh := &LightHouse{l: test.NewLoggerWithOutput(out)}
|
|
||||||
|
|
||||||
// The first sighting of a failure warns.
|
|
||||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
|
||||||
assert.Contains(t, out.String(), "level=WARN")
|
|
||||||
assert.Contains(t, out.String(), "permission denied")
|
|
||||||
|
|
||||||
// Repeating unchanged does not warn again, which is what keeps a permanent failure from warning
|
|
||||||
// on every lighthouse.interval for the life of the process.
|
|
||||||
out.Reset()
|
|
||||||
lh.logLocalAddrsErr(errors.New("permission denied"))
|
|
||||||
assert.NotContains(t, out.String(), "level=WARN")
|
|
||||||
|
|
||||||
// A different failure is a new event and warns.
|
|
||||||
out.Reset()
|
|
||||||
lh.logLocalAddrsErr(errors.New("something else"))
|
|
||||||
assert.Contains(t, out.String(), "level=WARN")
|
|
||||||
assert.Contains(t, out.String(), "something else")
|
|
||||||
|
|
||||||
// Recovering resets, so the same failure returning later warns again.
|
|
||||||
out.Reset()
|
|
||||||
lh.logLocalAddrsErr(nil)
|
|
||||||
assert.Empty(t, out.String())
|
|
||||||
lh.logLocalAddrsErr(errors.New("something else"))
|
|
||||||
assert.Contains(t, out.String(), "level=WARN")
|
|
||||||
}
|
|
||||||
@@ -32,12 +32,9 @@ const _ = noiseutil.RejectHeadroom - 4*maxRoutines
|
|||||||
|
|
||||||
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
|
func Main(c *config.C, configTest bool, buildVersion string, l *slog.Logger, deviceFactory overlay.DeviceFactory) (retcon *Control, reterr error) {
|
||||||
ctx, cancel := context.WithCancel(context.Background())
|
ctx, cancel := context.WithCancel(context.Background())
|
||||||
// The goroutines started below stop only when this context does, and only a caller holding the
|
// Automatically cancel the context if Main returns an error, to signal all created goroutines to quit.
|
||||||
// Control can arrange that. Cancel whenever we are not handing one back, which covers an error
|
|
||||||
// and a config test alike: a config test used to leave the lighthouse query worker, and a
|
|
||||||
// hostname resolver per dns named static host, running for the life of the process.
|
|
||||||
defer func() {
|
defer func() {
|
||||||
if retcon == nil {
|
if reterr != nil {
|
||||||
cancel()
|
cancel()
|
||||||
}
|
}
|
||||||
}()
|
}()
|
||||||
|
|||||||
@@ -1,21 +1,12 @@
|
|||||||
package nebula
|
package nebula
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"fmt"
|
|
||||||
"net/netip"
|
|
||||||
"os"
|
|
||||||
"path/filepath"
|
|
||||||
"testing"
|
"testing"
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/cert"
|
|
||||||
cert_test "github.com/slackhq/nebula/cert_test"
|
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/test"
|
"github.com/slackhq/nebula/test"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
"github.com/stretchr/testify/assert"
|
"github.com/stretchr/testify/assert"
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
"go.uber.org/goleak"
|
|
||||||
)
|
)
|
||||||
|
|
||||||
func TestParseCpuAffinity(t *testing.T) {
|
func TestParseCpuAffinity(t *testing.T) {
|
||||||
@@ -58,68 +49,3 @@ func TestParseCpuAffinity(t *testing.T) {
|
|||||||
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
assert.Nil(t, parseCpuAffinity(newConfig([]any{1 << 20}), l, 1))
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// TestMain_ConfigTestReleasesItsGoroutines pins the rule that Main only leaves goroutines running
|
|
||||||
// when it hands back a Control to stop them with.
|
|
||||||
//
|
|
||||||
// A config test gets no Control, so anything it started had nothing to stop it: the lighthouse
|
|
||||||
// query worker, and a hostname resolver per dns named static host, ran for the life of the
|
|
||||||
// process. That matters to every embedder that validates a config in process rather than by
|
|
||||||
// exec'ing, dnclient and the apple clients included, because they do it on each config load and
|
|
||||||
// the leak accumulates.
|
|
||||||
func TestMain_ConfigTestReleasesItsGoroutines(t *testing.T) {
|
|
||||||
defer goleak.VerifyNone(t, goleak.IgnoreCurrent())
|
|
||||||
|
|
||||||
l := test.NewLogger()
|
|
||||||
dir := t.TempDir()
|
|
||||||
|
|
||||||
before := time.Now().Add(-time.Hour)
|
|
||||||
after := time.Now().Add(time.Hour)
|
|
||||||
ca, _, caKey, caPEM := cert_test.NewTestCaCert(cert.Version2, cert.Curve_CURVE25519, before, after, nil, nil, nil)
|
|
||||||
networks := []netip.Prefix{netip.MustParsePrefix("10.0.0.1/24")}
|
|
||||||
_, _, keyPEM, certPEM := cert_test.NewTestCert(
|
|
||||||
cert.Version2, cert.Curve_CURVE25519, ca, caKey, "config-test", before, after, networks, nil, nil)
|
|
||||||
|
|
||||||
caPath := filepath.Join(dir, "ca.pem")
|
|
||||||
certPath := filepath.Join(dir, "cert.pem")
|
|
||||||
keyPath := filepath.Join(dir, "key.pem")
|
|
||||||
require.NoError(t, os.WriteFile(caPath, caPEM, 0o600))
|
|
||||||
require.NoError(t, os.WriteFile(certPath, certPEM, 0o600))
|
|
||||||
require.NoError(t, os.WriteFile(keyPath, keyPEM, 0o600))
|
|
||||||
|
|
||||||
// A static host by address, not by name: the query worker is the goroutine under test and a
|
|
||||||
// hostname would drag a real dns lookup into a unit test.
|
|
||||||
configBody := fmt.Sprintf(`
|
|
||||||
pki:
|
|
||||||
ca: %s
|
|
||||||
cert: %s
|
|
||||||
key: %s
|
|
||||||
static_host_map:
|
|
||||||
"10.0.0.2": ["192.0.2.1:4242"]
|
|
||||||
lighthouse:
|
|
||||||
hosts:
|
|
||||||
- "10.0.0.2"
|
|
||||||
listen:
|
|
||||||
host: 127.0.0.1
|
|
||||||
port: 0
|
|
||||||
tun:
|
|
||||||
disabled: true
|
|
||||||
firewall:
|
|
||||||
outbound:
|
|
||||||
- port: any
|
|
||||||
proto: any
|
|
||||||
host: any
|
|
||||||
inbound:
|
|
||||||
- port: any
|
|
||||||
proto: any
|
|
||||||
host: any
|
|
||||||
`, caPath, certPath, keyPath)
|
|
||||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "config.yml"), []byte(configBody), 0o600))
|
|
||||||
|
|
||||||
c := config.NewC(l)
|
|
||||||
require.NoError(t, c.Load(dir))
|
|
||||||
|
|
||||||
ctrl, err := Main(c, true, "config-test", l, nil)
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Nil(t, ctrl, "a config test hands back nothing to stop, so it must stop itself")
|
|
||||||
}
|
|
||||||
@@ -1,39 +0,0 @@
|
|||||||
//go:build !android
|
|
||||||
|
|
||||||
package nicfinder
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
|
||||||
"log/slog"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
)
|
|
||||||
|
|
||||||
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
|
|
||||||
ifaces, err := net.Interfaces()
|
|
||||||
if err != nil {
|
|
||||||
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
var out []netip.Addr
|
|
||||||
var errs []error
|
|
||||||
|
|
||||||
for _, i := range ifaces {
|
|
||||||
if !allowName(ctx, l, filter, i.Name) {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
addrs, err := i.Addrs()
|
|
||||||
if err != nil {
|
|
||||||
errs = append(errs, fmt.Errorf("failed to get addresses for %s: %w", i.Name, err))
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
for _, rawAddr := range addrs {
|
|
||||||
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
|
|
||||||
out = append(out, addr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return out, errors.Join(errs...)
|
|
||||||
}
|
|
||||||
@@ -1,104 +0,0 @@
|
|||||||
//go:build android
|
|
||||||
|
|
||||||
package nicfinder
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"errors"
|
|
||||||
"fmt"
|
|
||||||
"log/slog"
|
|
||||||
"net/netip"
|
|
||||||
"os"
|
|
||||||
|
|
||||||
"github.com/DefinedNet/netlink"
|
|
||||||
"github.com/DefinedNet/netlink/nl"
|
|
||||||
"golang.org/x/sys/unix"
|
|
||||||
)
|
|
||||||
|
|
||||||
// Android denies bind() on netlink route sockets and RTM_GETLINK, so net.Interfaces fails with EACCES.
|
|
||||||
// Enumerate with an RTM_GETADDR dump on an unbound socket instead.
|
|
||||||
|
|
||||||
// localInterfaces returns every interface that has an address, with its addresses. It lists
|
|
||||||
// addresses over a netlink socket that is never bound and names each index with SIOCGIFNAME, the
|
|
||||||
// same operations Bionic's getifaddrs uses for app UIDs, which the sandbox permits.
|
|
||||||
func localAddrs(ctx context.Context, l *slog.Logger, filter Filter) ([]netip.Addr, error) {
|
|
||||||
var errs []error
|
|
||||||
addrs, err := netlinkAddrList()
|
|
||||||
if err != nil {
|
|
||||||
if !errors.Is(err, netlink.ErrDumpInterrupted) {
|
|
||||||
return nil, fmt.Errorf("failed to enumerate local interfaces: %w", err)
|
|
||||||
}
|
|
||||||
// The address table kept changing under the dump and netlink gave up retrying. What it
|
|
||||||
// returned is still worth advertising.
|
|
||||||
errs = append(errs, fmt.Errorf("local addresses may be incomplete: %w", err))
|
|
||||||
}
|
|
||||||
|
|
||||||
// Any socket will do for SIOCGIFNAME.
|
|
||||||
sfd, err := unix.Socket(unix.AF_INET, unix.SOCK_DGRAM|unix.SOCK_CLOEXEC, 0)
|
|
||||||
if err != nil {
|
|
||||||
return nil, os.NewSyscallError("socket", err)
|
|
||||||
}
|
|
||||||
defer unix.Close(sfd)
|
|
||||||
|
|
||||||
var out []netip.Addr
|
|
||||||
nameAllowed := make(map[int]bool) // by interface index, once named
|
|
||||||
for _, a := range addrs {
|
|
||||||
allow, named := nameAllowed[a.LinkIndex]
|
|
||||||
if (named && !allow) || a.IPNet == nil {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
addr, ok := allowedAddr(ctx, l, filter, a.IPNet)
|
|
||||||
if !ok {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
if !named {
|
|
||||||
name, err := interfaceNameByIndex(sfd, a.LinkIndex)
|
|
||||||
// ENODEV means the interface went away after the dump. Any other failure is reported
|
|
||||||
// and the interface skipped, so the rest are still returned.
|
|
||||||
if err != nil && !errors.Is(err, unix.ENODEV) {
|
|
||||||
errs = append(errs, fmt.Errorf("failed to resolve name of interface %d: %w", a.LinkIndex, err))
|
|
||||||
}
|
|
||||||
allow = err == nil && allowName(ctx, l, filter, name)
|
|
||||||
nameAllowed[a.LinkIndex] = allow
|
|
||||||
}
|
|
||||||
if allow {
|
|
||||||
out = append(out, addr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return out, errors.Join(errs...)
|
|
||||||
}
|
|
||||||
|
|
||||||
// netlinkAddrList is netlink.AddrList over a socket that is never bound. The kernel autobinds it
|
|
||||||
// on the first send, which the sandbox permits.
|
|
||||||
func netlinkAddrList() ([]netlink.Addr, error) {
|
|
||||||
fd, err := unix.Socket(unix.AF_NETLINK, unix.SOCK_RAW|unix.SOCK_CLOEXEC, unix.NETLINK_ROUTE)
|
|
||||||
if err != nil {
|
|
||||||
return nil, os.NewSyscallError("socket", err)
|
|
||||||
}
|
|
||||||
s, err := nl.NewNetlinkSocketFromFd(fd)
|
|
||||||
if err != nil {
|
|
||||||
unix.Close(fd)
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
h := netlink.NewHandleFromSockets(
|
|
||||||
map[int]*nl.SocketHandle{unix.NETLINK_ROUTE: {Socket: s}},
|
|
||||||
netlink.HandleOptions{RetryInterrupted: true},
|
|
||||||
)
|
|
||||||
defer h.Close()
|
|
||||||
if err := h.SetSocketTimeout(netlink.GetSocketTimeout()); err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
return h.AddrList(nil, netlink.FAMILY_ALL)
|
|
||||||
}
|
|
||||||
|
|
||||||
// interfaceNameByIndex resolves an interface index with SIOCGIFNAME.
|
|
||||||
func interfaceNameByIndex(fd int, index int) (string, error) {
|
|
||||||
var ifr unix.Ifreq
|
|
||||||
ifr.SetUint32(uint32(index)) // ifr_ifindex is in the ifr_ifru union
|
|
||||||
if err := unix.IoctlIfreq(fd, unix.SIOCGIFNAME, &ifr); err != nil {
|
|
||||||
return "", err
|
|
||||||
}
|
|
||||||
return ifr.Name(), nil
|
|
||||||
}
|
|
||||||
@@ -1,59 +0,0 @@
|
|||||||
package nicfinder
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"log/slog"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/logging"
|
|
||||||
)
|
|
||||||
|
|
||||||
// Filter decides which interfaces, by name, and which of their addresses Find returns.
|
|
||||||
type Filter interface {
|
|
||||||
AllowName(string) bool
|
|
||||||
Allow(netip.Addr) bool
|
|
||||||
}
|
|
||||||
|
|
||||||
// Find returns the addresses of this host's network interfaces that allowList accepts, with
|
|
||||||
// loopback and link-local addresses left out. When only some interfaces could be read it returns
|
|
||||||
// their addresses alongside an error for the rest. allowList must not be nil; it is called as
|
|
||||||
// given, so a nil pointer of a type whose methods accept a nil receiver is fine.
|
|
||||||
func Find(ctx context.Context, l *slog.Logger, allowList Filter) ([]netip.Addr, error) {
|
|
||||||
return localAddrs(ctx, l, allowList)
|
|
||||||
}
|
|
||||||
|
|
||||||
// allowName asks filter about an interface name and traces the answer.
|
|
||||||
func allowName(ctx context.Context, l *slog.Logger, filter Filter, name string) bool {
|
|
||||||
allow := filter.AllowName(name)
|
|
||||||
if l.Enabled(ctx, logging.LevelTrace) {
|
|
||||||
l.Log(ctx, logging.LevelTrace, "localAllowList.AllowName", "interfaceName", name, "allow", allow)
|
|
||||||
}
|
|
||||||
return allow
|
|
||||||
}
|
|
||||||
|
|
||||||
// allowedAddr converts one address a platform reports and says whether to advertise it: it must
|
|
||||||
// be a *net.IPNet or *net.IPAddr carrying an IP, not be loopback or link-local, and be accepted by
|
|
||||||
// filter, whose answer is traced. IPv4 comes back unmapped.
|
|
||||||
func allowedAddr(ctx context.Context, l *slog.Logger, filter Filter, rawAddr net.Addr) (netip.Addr, bool) {
|
|
||||||
var ip net.IP
|
|
||||||
switch v := rawAddr.(type) {
|
|
||||||
case *net.IPNet:
|
|
||||||
ip = v.IP
|
|
||||||
case *net.IPAddr:
|
|
||||||
ip = v.IP
|
|
||||||
}
|
|
||||||
addr, ok := netip.AddrFromSlice(ip)
|
|
||||||
if !ok {
|
|
||||||
return netip.Addr{}, false
|
|
||||||
}
|
|
||||||
addr = addr.Unmap()
|
|
||||||
if addr.IsLoopback() || addr.IsLinkLocalUnicast() {
|
|
||||||
return netip.Addr{}, false
|
|
||||||
}
|
|
||||||
isAllowed := filter.Allow(addr)
|
|
||||||
if l.Enabled(ctx, logging.LevelTrace) {
|
|
||||||
l.Log(ctx, logging.LevelTrace, "localAllowList.Allow", "localAddr", addr, "allowed", isAllowed)
|
|
||||||
}
|
|
||||||
return addr, isAllowed
|
|
||||||
}
|
|
||||||
@@ -1,117 +0,0 @@
|
|||||||
package nicfinder
|
|
||||||
|
|
||||||
import (
|
|
||||||
"context"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
"regexp"
|
|
||||||
"testing"
|
|
||||||
|
|
||||||
"github.com/slackhq/nebula/test"
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
)
|
|
||||||
|
|
||||||
type allowAll struct{}
|
|
||||||
|
|
||||||
func (allowAll) Allow(netip.Addr) bool { return true }
|
|
||||||
func (allowAll) AllowName(string) bool { return true }
|
|
||||||
|
|
||||||
type testAllowList struct {
|
|
||||||
bannedName *regexp.Regexp
|
|
||||||
bannedAddr netip.Addr
|
|
||||||
}
|
|
||||||
|
|
||||||
func (l *testAllowList) Allow(addr netip.Addr) bool {
|
|
||||||
return addr != l.bannedAddr
|
|
||||||
}
|
|
||||||
|
|
||||||
func (l *testAllowList) AllowName(n string) bool {
|
|
||||||
return !l.bannedName.MatchString(n)
|
|
||||||
}
|
|
||||||
|
|
||||||
func newTestAllowList(bannedName string) *testAllowList {
|
|
||||||
return &testAllowList{
|
|
||||||
bannedName: regexp.MustCompile(bannedName),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
func TestAllowedAddr(t *testing.T) {
|
|
||||||
ctx, l := context.Background(), test.NewLogger()
|
|
||||||
allowed := func(filter Filter, addrs []net.Addr) []netip.Addr {
|
|
||||||
var out []netip.Addr
|
|
||||||
for _, rawAddr := range addrs {
|
|
||||||
if addr, ok := allowedAddr(ctx, l, filter, rawAddr); ok {
|
|
||||||
out = append(out, addr)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return out
|
|
||||||
}
|
|
||||||
addrs := []net.Addr{
|
|
||||||
&net.IPNet{IP: net.ParseIP("127.0.0.1"), Mask: net.CIDRMask(8, 32)},
|
|
||||||
&net.IPNet{IP: net.ParseIP("::1"), Mask: net.CIDRMask(128, 128)},
|
|
||||||
&net.IPNet{IP: net.ParseIP("10.0.0.5"), Mask: net.CIDRMask(24, 32)},
|
|
||||||
&net.IPNet{IP: net.ParseIP("169.254.10.10"), Mask: net.CIDRMask(16, 32)},
|
|
||||||
&net.IPNet{IP: net.ParseIP("fe80::1"), Mask: net.CIDRMask(64, 128)},
|
|
||||||
&net.IPAddr{IP: net.ParseIP("fd00::5")},
|
|
||||||
&net.IPNet{},
|
|
||||||
otherAddr{},
|
|
||||||
nil,
|
|
||||||
}
|
|
||||||
|
|
||||||
// Loopback, link local and anything without an IP are dropped, and IPv4 comes back unmapped
|
|
||||||
// even though net.ParseIP hands over a 16 byte slice.
|
|
||||||
assert.Equal(t, []netip.Addr{
|
|
||||||
netip.MustParseAddr("10.0.0.5"),
|
|
||||||
netip.MustParseAddr("fd00::5"),
|
|
||||||
}, allowed(allowAll{}, addrs))
|
|
||||||
|
|
||||||
// The filter sees the unmapped form and can drop a single address.
|
|
||||||
al := newTestAllowList("none")
|
|
||||||
al.bannedAddr = netip.MustParseAddr("10.0.0.5")
|
|
||||||
assert.Equal(t, []netip.Addr{netip.MustParseAddr("fd00::5")}, allowed(al, addrs))
|
|
||||||
}
|
|
||||||
|
|
||||||
// otherAddr is a net.Addr that is neither *net.IPNet nor *net.IPAddr. netlink.Addr is one such
|
|
||||||
// type: it satisfies net.Addr through an embedded *net.IPNet, and passing it directly once
|
|
||||||
// silently produced no addresses.
|
|
||||||
type otherAddr struct{}
|
|
||||||
|
|
||||||
func (otherAddr) Network() string { return "other" }
|
|
||||||
func (otherAddr) String() string { return "other" }
|
|
||||||
|
|
||||||
// hostFilter counts AllowName calls and can reject every name or every address.
|
|
||||||
type hostFilter struct {
|
|
||||||
rejectNames bool
|
|
||||||
rejectAddrs bool
|
|
||||||
asked map[string]int
|
|
||||||
}
|
|
||||||
|
|
||||||
func (f *hostFilter) Allow(netip.Addr) bool { return !f.rejectAddrs }
|
|
||||||
func (f *hostFilter) AllowName(name string) bool {
|
|
||||||
f.asked[name]++
|
|
||||||
return !f.rejectNames
|
|
||||||
}
|
|
||||||
|
|
||||||
// Runs this platform's localAddrs against the host and checks it honors the whole filter.
|
|
||||||
func TestLocalAddrsAppliesFilter(t *testing.T) {
|
|
||||||
ctx, l := context.Background(), test.NewLogger()
|
|
||||||
|
|
||||||
f := &hostFilter{asked: map[string]int{}}
|
|
||||||
all, err := localAddrs(ctx, l, f)
|
|
||||||
if len(f.asked) == 0 {
|
|
||||||
t.Skipf("no interfaces to enumerate here: %v", err)
|
|
||||||
}
|
|
||||||
for name, n := range f.asked {
|
|
||||||
assert.Equal(t, 1, n, "AllowName asked %d times for %s", n, name)
|
|
||||||
}
|
|
||||||
// Loopback and link-local never come back, whatever the filter says.
|
|
||||||
for _, addr := range all {
|
|
||||||
assert.False(t, addr.IsLoopback() || addr.IsLinkLocalUnicast(), "%s", addr)
|
|
||||||
}
|
|
||||||
|
|
||||||
none, _ := localAddrs(ctx, l, &hostFilter{rejectNames: true, asked: map[string]int{}})
|
|
||||||
assert.Empty(t, none, "addresses got past a filter that rejects every interface name")
|
|
||||||
|
|
||||||
none, _ = localAddrs(ctx, l, &hostFilter{rejectAddrs: true, asked: map[string]int{}})
|
|
||||||
assert.Empty(t, none, "addresses got past a filter that rejects every address")
|
|
||||||
}
|
|
||||||
+10
-73
@@ -2,14 +2,13 @@ package noiseutil
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bytes"
|
"bytes"
|
||||||
|
"crypto/aes"
|
||||||
"crypto/cipher"
|
"crypto/cipher"
|
||||||
"crypto/fips140"
|
"crypto/fips140"
|
||||||
"encoding/binary"
|
"encoding/binary"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"reflect"
|
|
||||||
"runtime"
|
"runtime"
|
||||||
"unsafe"
|
|
||||||
|
|
||||||
// unsafe needed for go:linkname
|
// unsafe needed for go:linkname
|
||||||
_ "crypto/tls"
|
_ "crypto/tls"
|
||||||
@@ -18,16 +17,6 @@ import (
|
|||||||
"github.com/flynn/noise"
|
"github.com/flynn/noise"
|
||||||
)
|
)
|
||||||
|
|
||||||
// TODO: Use NewGCMWithCounterNonce or NewGCMForQUIC once available:
|
|
||||||
// - https://github.com/golang/go/issues/73110
|
|
||||||
// - https://github.com/golang/go/issues/79219
|
|
||||||
// Using tls.aeadAESGCMTLS13 gives us the TLS 1.3 GCM, which also verifies
|
|
||||||
// that the nonce is strictly increasing. This works for both boringcrypto
|
|
||||||
// and fips140.
|
|
||||||
//
|
|
||||||
//go:linkname aeadAESGCMTLS13 crypto/tls.aeadAESGCMTLS13
|
|
||||||
func aeadAESGCMTLS13(key, noncePrefix []byte) cipher.AEAD
|
|
||||||
|
|
||||||
type cipherFn struct {
|
type cipherFn struct {
|
||||||
fn func([32]byte) noise.Cipher
|
fn func([32]byte) noise.Cipher
|
||||||
name string
|
name string
|
||||||
@@ -43,8 +32,14 @@ var CipherAESGCMFIPS140 noise.CipherFunc = cipherFn{cipherAESGCMFIPS140, "AESGCM
|
|||||||
var emptyNonce = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
|
var emptyNonce = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}
|
||||||
|
|
||||||
func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
||||||
gcm := aeadAESGCMTLS13(k[:], emptyNonce)
|
c, err := aes.NewCipher(k[:])
|
||||||
gcm = extractFIPSAEAD(gcm)
|
if err != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
|
gcm, err := cipher.NewGCMWithCounterNonce(c)
|
||||||
|
if err != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
return &aeadGCMFIPS140Cipher{
|
return &aeadGCMFIPS140Cipher{
|
||||||
AEAD: gcm,
|
AEAD: gcm,
|
||||||
}
|
}
|
||||||
@@ -52,57 +47,6 @@ func cipherAESGCMFIPS140(k [32]byte) noise.Cipher {
|
|||||||
|
|
||||||
type aeadGCMFIPS140Cipher struct {
|
type aeadGCMFIPS140Cipher struct {
|
||||||
cipher.AEAD
|
cipher.AEAD
|
||||||
ready bool
|
|
||||||
}
|
|
||||||
|
|
||||||
// Extract the internal FIPS GCM implementation from the tls wrapper. The TLS
|
|
||||||
// wrapper is not thread safe around Open, so instead of locking around it we
|
|
||||||
// can grab the internal implementation that is thread safe. This is the FIPS
|
|
||||||
// module implementation: `crypto/internal/fips140/aes/gcm.GCMWithXORCounterNonce`
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/internal/fips140/aes/gcm/gcm_nonces.go#L212-L287
|
|
||||||
//
|
|
||||||
// The wrapper is struct `crypto/tls.xorNonceAEAD` , with field `aead`:
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/blob/go1.26.4/src/crypto/tls/cipher_suites.go#L482-L487
|
|
||||||
//
|
|
||||||
// This can be cleaned up once these FIPS implementations are exposed directly:
|
|
||||||
//
|
|
||||||
// - https://github.com/golang/go/issues/73110
|
|
||||||
func extractFIPSAEAD(xorNonceAEAD cipher.AEAD) cipher.AEAD {
|
|
||||||
r := reflect.ValueOf(xorNonceAEAD)
|
|
||||||
v := r.Elem().FieldByName("aead")
|
|
||||||
if !v.IsValid() {
|
|
||||||
// The internal crypto/tls.xorNonceAEAD struct no longer has an `aead`
|
|
||||||
// field. This can only happen on a Go version this code was not built
|
|
||||||
// against; the package init() self-test guards against ever reaching
|
|
||||||
// this at runtime, so this is a defensive fail-fast.
|
|
||||||
panic(fmt.Sprintf("noiseutil: could not extract FIPS AEAD from %T on %s: no `aead` field (incompatible Go version)", xorNonceAEAD, runtime.Version()))
|
|
||||||
}
|
|
||||||
v2 := reflect.NewAt(v.Type(), unsafe.Pointer(v.UnsafeAddr())).Elem()
|
|
||||||
aead, ok := v2.Interface().(cipher.AEAD)
|
|
||||||
if !ok {
|
|
||||||
panic(fmt.Sprintf("noiseutil: extracted FIPS `aead` field is %s, not a cipher.AEAD, on %s (incompatible Go version)", v2.Type(), runtime.Version()))
|
|
||||||
}
|
|
||||||
return aead
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) init(nonce []byte) {
|
|
||||||
// GCMWithXORCounterNonce expects that the first call to Seal
|
|
||||||
// is with a counter of `0`, this is how it extracts the nonce mask.
|
|
||||||
// We can clean this up in the future when NewGCMWithCounterNonce or
|
|
||||||
// NewGCMForQUIC are available:
|
|
||||||
if !bytes.Equal(emptyNonce, nonce) {
|
|
||||||
c.AEAD.Seal([]byte{}, emptyNonce, []byte{}, []byte{})
|
|
||||||
}
|
|
||||||
c.ready = true
|
|
||||||
}
|
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
|
||||||
if !c.ready {
|
|
||||||
c.init(nonce)
|
|
||||||
}
|
|
||||||
return c.AEAD.Seal(dst, nonce, plaintext, additionalData)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Encrypt(out []byte, n uint64, ad, plaintext []byte) []byte {
|
func (c *aeadGCMFIPS140Cipher) Encrypt(out []byte, n uint64, ad, plaintext []byte) []byte {
|
||||||
@@ -133,15 +77,8 @@ func (c *aeadGCMFIPS140Cipher) DecryptDanger(out, ad, ciphertext []byte, n uint6
|
|||||||
return c.Open(out, nb, ciphertext, ad)
|
return c.Open(out, nb, ciphertext, ad)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *aeadGCMFIPS140Cipher) Overhead() int {
|
|
||||||
if c == nil {
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
return c.AEAD.Overhead()
|
|
||||||
}
|
|
||||||
|
|
||||||
func aeadGCMFIPS140CipherNonce(n uint64) []byte {
|
func aeadGCMFIPS140CipherNonce(n uint64) []byte {
|
||||||
// GCMWithXORCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
// GCMWithCounterNonce uses a 4 byte static prefix and an 8 byte nonce
|
||||||
var nonce [12]byte
|
var nonce [12]byte
|
||||||
binary.BigEndian.PutUint64(nonce[4:], n)
|
binary.BigEndian.PutUint64(nonce[4:], n)
|
||||||
return nonce[:]
|
return nonce[:]
|
||||||
|
|||||||
+1
-1
@@ -354,7 +354,7 @@ func parseV6(data []byte, incoming bool, fp *firewall.ParsedPacket) error {
|
|||||||
// and cannot drift into misreading an unknown protocol (SCTP, GRE, etc.) as a forged transport.
|
// and cannot drift into misreading an unknown protocol (SCTP, GRE, etc.) as a forged transport.
|
||||||
proto, offset, isFragment, anyFragment, err := iputil.IPv6FindUpperProtocol(data)
|
proto, offset, isFragment, anyFragment, err := iputil.IPv6FindUpperProtocol(data)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return ErrIPv6PacketTooShort
|
||||||
}
|
}
|
||||||
|
|
||||||
fp.Protocol = proto
|
fp.Protocol = proto
|
||||||
|
|||||||
+7
-7
@@ -117,7 +117,7 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
err = newPacket(buffer.Bytes(), true, p)
|
err = newPacket(buffer.Bytes(), true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// A v6 packet with a hop-by-hop extension
|
// A v6 packet with a hop-by-hop extension
|
||||||
// ICMPv6 Payload (Echo Request)
|
// ICMPv6 Payload (Echo Request)
|
||||||
@@ -151,12 +151,12 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
// A full IPv6 header and 1 byte in the first extension, but missing
|
// A full IPv6 header and 1 byte in the first extension, but missing
|
||||||
// the length byte.
|
// the length byte.
|
||||||
err = newPacket(buffer.Bytes()[:41], true, p)
|
err = newPacket(buffer.Bytes()[:41], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// A full IPv6 header plus 1 full extension, but only 1 byte of the
|
// A full IPv6 header plus 1 full extension, but only 1 byte of the
|
||||||
// next layer, missing length byte
|
// next layer, missing length byte
|
||||||
err = newPacket(buffer.Bytes()[:49], true, p)
|
err = newPacket(buffer.Bytes()[:49], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
err = nil
|
err = nil
|
||||||
|
|
||||||
// A good ICMP packet
|
// A good ICMP packet
|
||||||
@@ -354,12 +354,12 @@ func Test_newPacket_v6(t *testing.T) {
|
|||||||
|
|
||||||
// Ensure buffer bounds checking during processing, a truncated AH header can't reach the payload
|
// Ensure buffer bounds checking during processing, a truncated AH header can't reach the payload
|
||||||
err = newPacket(b[:41], true, p)
|
err = newPacket(b[:41], true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
|
|
||||||
// Invalid AH header
|
// Invalid AH header
|
||||||
b = buffer.Bytes()
|
b = buffer.Bytes()
|
||||||
err = newPacket(b, true, p)
|
err = newPacket(b, true, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
func Test_newPacket_ipv6Fragment(t *testing.T) {
|
func Test_newPacket_ipv6Fragment(t *testing.T) {
|
||||||
@@ -466,7 +466,7 @@ func Test_newPacket_ipv6Fragment(t *testing.T) {
|
|||||||
|
|
||||||
// Too short of a fragment packet
|
// Too short of a fragment packet
|
||||||
err = newPacket(secondFrag[:len(secondFrag)-10], false, p)
|
err = newPacket(secondFrag[:len(secondFrag)-10], false, p)
|
||||||
require.ErrorIs(t, err, iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, err, ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
func BenchmarkParseV6(b *testing.B) {
|
func BenchmarkParseV6(b *testing.B) {
|
||||||
@@ -707,7 +707,7 @@ func Test_newPacket_v6ExtHeaderPastBuffer(t *testing.T) {
|
|||||||
pkt[40] = byte(layers.IPProtocolSCTP) // Dest Options next header = SCTP
|
pkt[40] = byte(layers.IPProtocolSCTP) // Dest Options next header = SCTP
|
||||||
pkt[41] = 255 // declared length (255+1)*8 = 2048, past the 48 byte buffer
|
pkt[41] = 255 // declared length (255+1)*8 = 2048, past the 48 byte buffer
|
||||||
|
|
||||||
require.ErrorIs(t, newPacket(pkt, true, p), iputil.ErrIPv6CouldNotFindPayload)
|
require.ErrorIs(t, newPacket(pkt, true, p), ErrIPv6PacketTooShort)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
// Test_newPacket_v6ExtHeaderConfusion is a regression test for parseV6 walking any unrecognized
|
||||||
|
|||||||
@@ -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))
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -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
@@ -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)
|
|
||||||
}
|
|
||||||
@@ -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
|
|
||||||
}
|
|
||||||
+12
-305
@@ -8,7 +8,6 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"os"
|
"os"
|
||||||
"sync"
|
|
||||||
"sync/atomic"
|
"sync/atomic"
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
@@ -30,39 +29,7 @@ type tun struct {
|
|||||||
Routes atomic.Pointer[[]Route]
|
Routes atomic.Pointer[[]Route]
|
||||||
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
routeTree atomic.Pointer[bart.Table[routing.Gateways]]
|
||||||
linkAddr *netroute.LinkAddr
|
linkAddr *netroute.LinkAddr
|
||||||
// hostOwned means the fd arrived from the OS, which has already configured addressing, mtu
|
l *slog.Logger
|
||||||
// and routes for it. NEPacketTunnelProvider on darwin does this.
|
|
||||||
hostOwned bool
|
|
||||||
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 {
|
||||||
@@ -182,48 +149,8 @@ func (t *tun) deviceBytes() (o [16]byte) {
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
// newTunFromFd adopts a utun the host already created and configured, which is how a darwin
|
func newTunFromFd(_ *config.C, _ *slog.Logger, _ int, _ []netip.Prefix) (*tun, error) {
|
||||||
// network extension is handed its device. Everything about moving packets is shared with newTun,
|
return nil, fmt.Errorf("newTunFromFd not supported in Darwin")
|
||||||
// only the setup differs: the host owns addressing and routing here.
|
|
||||||
func newTunFromFd(c *config.C, l *slog.Logger, deviceFd int, vpnNetworks []netip.Prefix) (*tun, error) {
|
|
||||||
if err := unix.SetNonblock(deviceFd, true); err != nil {
|
|
||||||
// We own the fd from the moment it is handed to us
|
|
||||||
_ = unix.Close(deviceFd)
|
|
||||||
return nil, fmt.Errorf("failed to set the tun fd to non-blocking mode: %w", err)
|
|
||||||
}
|
|
||||||
|
|
||||||
file := os.NewFile(uintptr(deviceFd), "/dev/tun")
|
|
||||||
t := &tun{
|
|
||||||
f: file,
|
|
||||||
Device: utunNameFromFd(deviceFd),
|
|
||||||
vpnNetworks: vpnNetworks,
|
|
||||||
DefaultMTU: c.GetInt("tun.mtu", DefaultMTU),
|
|
||||||
hostOwned: true,
|
|
||||||
l: l,
|
|
||||||
}
|
|
||||||
|
|
||||||
if err := t.reload(c, true); err != nil {
|
|
||||||
_ = file.Close()
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
c.RegisterReloadCallback(func(c *config.C) {
|
|
||||||
if err := t.reload(c, false); err != nil {
|
|
||||||
util.LogWithContextIfNeeded("failed to reload tun device", err, t.l)
|
|
||||||
}
|
|
||||||
})
|
|
||||||
|
|
||||||
return t, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// utunNameFromFd asks the socket what interface it is, for logs. A blank name is not worth
|
|
||||||
// failing a tunnel over, so an error just leaves it empty.
|
|
||||||
func utunNameFromFd(fd int) string {
|
|
||||||
name, err := unix.GetsockoptString(fd, unix.AF_SYS_CONTROL, _UTUN_OPT_IFNAME)
|
|
||||||
if err != nil {
|
|
||||||
return ""
|
|
||||||
}
|
|
||||||
return name
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) Close() error {
|
func (t *tun) Close() error {
|
||||||
@@ -234,12 +161,6 @@ func (t *tun) Close() error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) Activate() error {
|
func (t *tun) Activate() error {
|
||||||
// The host handed us a configured device. Its addresses, mtu and routes come from the network
|
|
||||||
// settings it applied, and a sandboxed extension cannot change them anyway.
|
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
devName := t.deviceBytes()
|
devName := t.deviceBytes()
|
||||||
|
|
||||||
s, err := unix.Socket(
|
s, err := unix.Socket(
|
||||||
@@ -453,11 +374,6 @@ func getLinkAddr(name string) (*netroute.LinkAddr, error) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) addRoutes(logErrors bool) error {
|
func (t *tun) addRoutes(logErrors bool) error {
|
||||||
// The route tree is still ours, the system routing table is not
|
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
routes := *t.Routes.Load()
|
routes := *t.Routes.Load()
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
@@ -487,10 +403,6 @@ func (t *tun) addRoutes(logErrors bool) error {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) removeRoutes(routes []Route) error {
|
func (t *tun) removeRoutes(routes []Route) error {
|
||||||
if t.hostOwned {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
for _, r := range routes {
|
for _, r := range routes {
|
||||||
if !r.Install {
|
if !r.Install {
|
||||||
continue
|
continue
|
||||||
@@ -637,74 +549,6 @@ func (t *tun) Read(to []byte) (int, error) {
|
|||||||
return n - 4, nil
|
return n - 4, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// tunReadBatch is the most packets one tunQueue.Read returns.
|
|
||||||
const tunReadBatch = 64
|
|
||||||
|
|
||||||
// tunReadArena is tunQueue's receive buffer. Draining stops once less than defaultBatchBufSize of it
|
|
||||||
// is left, so every readv has room for the largest packet utun can return at any device MTU.
|
|
||||||
const tunReadArena = 4 * defaultBatchBufSize
|
|
||||||
|
|
||||||
// tunQueue is the darwin tun's Queue. Read drains every packet already queued on the utun, up to
|
|
||||||
// tunReadBatch, so the caller encrypts and sends them as one batch rather than one per wakeup.
|
|
||||||
type tunQueue struct {
|
|
||||||
t *tun
|
|
||||||
buf []byte
|
|
||||||
pkts [tunReadBatch]tio.Packet
|
|
||||||
}
|
|
||||||
|
|
||||||
// Read waits for the utun to become readable, then reads packets until it would block. An error after
|
|
||||||
// at least one packet is dropped in favor of returning those packets; a persistent one recurs on the
|
|
||||||
// next Read.
|
|
||||||
func (q *tunQueue) Read() ([]tio.Packet, error) {
|
|
||||||
rc, err := q.t.f.SyscallConn()
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
var head [4]byte
|
|
||||||
n, off := 0, 0
|
|
||||||
var callErr error
|
|
||||||
err = rc.Read(func(fd uintptr) bool {
|
|
||||||
for n < tunReadBatch && len(q.buf)-off >= defaultBatchBufSize {
|
|
||||||
iovecs := [2]unix.Iovec{
|
|
||||||
{Base: &head[0], Len: 4},
|
|
||||||
{Base: &q.buf[off], Len: uint64(len(q.buf) - off)},
|
|
||||||
}
|
|
||||||
l, e := tunReadv(int(fd), iovecs[:])
|
|
||||||
if e != nil {
|
|
||||||
if errno, ok := e.(syscall.Errno); ok && errno.Temporary() {
|
|
||||||
// Park on the poller only while there is nothing to hand back.
|
|
||||||
return n > 0
|
|
||||||
}
|
|
||||||
callErr = e
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
if l < 4 {
|
|
||||||
// A datagram too short to carry the AF prefix, or end of file; stop rather than spin on it.
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
end := off + l - 4
|
|
||||||
q.pkts[n] = tio.Packet{Bytes: q.buf[off:end:end]}
|
|
||||||
n++
|
|
||||||
off = end
|
|
||||||
}
|
|
||||||
return true
|
|
||||||
})
|
|
||||||
if n > 0 {
|
|
||||||
return q.pkts[:n], nil
|
|
||||||
}
|
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
return nil, callErr
|
|
||||||
}
|
|
||||||
|
|
||||||
func (q *tunQueue) Write(p []byte) (int, error) { return q.t.Write(p) }
|
|
||||||
|
|
||||||
func (q *tunQueue) WriteBatch(pkts [][]byte) error { return q.t.WriteBatch(pkts) }
|
|
||||||
|
|
||||||
func (q *tunQueue) Close() error { return q.t.Close() }
|
|
||||||
|
|
||||||
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
|
// Write pushes one IP packet onto the utun device. Safe for concurrent use:
|
||||||
// the AF prefix and iovecs are per-call stack state, and the fd write itself
|
// the AF prefix and iovecs are per-call stack state, and the fd write itself
|
||||||
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
|
// serializes on the runtime's fd mutex (see the Queue contract in tio.go).
|
||||||
@@ -713,12 +557,16 @@ 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()
|
||||||
@@ -751,147 +599,6 @@ 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
|
||||||
}
|
}
|
||||||
@@ -901,5 +608,5 @@ func (t *tun) Name() string {
|
|||||||
}
|
}
|
||||||
|
|
||||||
func (t *tun) Queues(int) ([]tio.Queue, error) {
|
func (t *tun) Queues(int) ([]tio.Queue, error) {
|
||||||
return []tio.Queue{&tunQueue{t: t, buf: make([]byte, tunReadArena)}}, nil
|
return []tio.Queue{tio.NewSingleQueue(t, defaultBatchBufSize)}, nil
|
||||||
}
|
}
|
||||||
@@ -1,201 +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)
|
|
||||||
})
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestTunQueueReadDrains pins that Read hands back every queued packet, AF prefix stripped and in
|
|
||||||
// order, capped at tunReadBatch per call, and doesn't wait for more once the queue is empty.
|
|
||||||
func TestTunQueueReadDrains(t *testing.T) {
|
|
||||||
tn, w := newSocketpairTun(t, 1<<20)
|
|
||||||
// An AF_UNIX datagram send is bounded by the receiver's buffer, here the tun's end.
|
|
||||||
rc, err := tn.f.SyscallConn()
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.NoError(t, rc.Control(func(fd uintptr) {
|
|
||||||
require.NoError(t, unix.SetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_RCVBUF, 1<<20))
|
|
||||||
}))
|
|
||||||
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
|
|
||||||
total := tunReadBatch + 3
|
|
||||||
var want [][]byte
|
|
||||||
for i := range total {
|
|
||||||
pkt, wire := testTunPkt(i, 60+i)
|
|
||||||
_, err := unix.Write(w, wire)
|
|
||||||
require.NoError(t, err)
|
|
||||||
want = append(want, pkt)
|
|
||||||
}
|
|
||||||
|
|
||||||
var got [][]byte
|
|
||||||
for _, size := range []int{tunReadBatch, 3} {
|
|
||||||
pkts, err := q.Read()
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Len(t, pkts, size)
|
|
||||||
for _, p := range pkts {
|
|
||||||
got = append(got, p.Clone().Bytes)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
assert.Equal(t, want, got)
|
|
||||||
}
|
|
||||||
|
|
||||||
// TestTunQueueReadClipsPackets pins that each returned packet's capacity ends at its own bytes, so
|
|
||||||
// appending to one can't overwrite the next.
|
|
||||||
func TestTunQueueReadClipsPackets(t *testing.T) {
|
|
||||||
tn, w := newSocketpairTun(t, 1<<20)
|
|
||||||
q := &tunQueue{t: tn, buf: make([]byte, tunReadArena)}
|
|
||||||
for i := range 2 {
|
|
||||||
_, wire := testTunPkt(i, 100)
|
|
||||||
_, err := unix.Write(w, wire)
|
|
||||||
require.NoError(t, err)
|
|
||||||
}
|
|
||||||
pkts, err := q.Read()
|
|
||||||
require.NoError(t, err)
|
|
||||||
require.Len(t, pkts, 2)
|
|
||||||
assert.Equal(t, len(pkts[0].Bytes), cap(pkts[0].Bytes))
|
|
||||||
}
|
|
||||||
@@ -15,12 +15,12 @@ import (
|
|||||||
"time"
|
"time"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
|
|
||||||
"github.com/DefinedNet/netlink"
|
|
||||||
"github.com/gaissmai/bart"
|
"github.com/gaissmai/bart"
|
||||||
"github.com/slackhq/nebula/config"
|
"github.com/slackhq/nebula/config"
|
||||||
"github.com/slackhq/nebula/overlay/tio"
|
"github.com/slackhq/nebula/overlay/tio"
|
||||||
"github.com/slackhq/nebula/routing"
|
"github.com/slackhq/nebula/routing"
|
||||||
"github.com/slackhq/nebula/util"
|
"github.com/slackhq/nebula/util"
|
||||||
|
"github.com/vishvananda/netlink"
|
||||||
"golang.org/x/sys/unix"
|
"golang.org/x/sys/unix"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
+6
-276
@@ -10,7 +10,6 @@ import (
|
|||||||
"log/slog"
|
"log/slog"
|
||||||
"net"
|
"net"
|
||||||
"net/netip"
|
"net/netip"
|
||||||
"sync/atomic"
|
|
||||||
"syscall"
|
"syscall"
|
||||||
"unsafe"
|
"unsafe"
|
||||||
|
|
||||||
@@ -23,9 +22,6 @@ type StdConn struct {
|
|||||||
isV4 bool
|
isV4 bool
|
||||||
sysFd uintptr
|
sysFd uintptr
|
||||||
l *slog.Logger
|
l *slog.Logger
|
||||||
|
|
||||||
noSendmsgX atomic.Bool
|
|
||||||
sb *sendScratch
|
|
||||||
}
|
}
|
||||||
|
|
||||||
var _ Conn = &StdConn{}
|
var _ Conn = &StdConn{}
|
||||||
@@ -143,138 +139,11 @@ func (u *StdConn) WriteTo(b []byte, ap netip.AddrPort) error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// sendBatch is how many datagrams one sendmsg_x call may carry.
|
|
||||||
const sendBatch = 64
|
|
||||||
|
|
||||||
// sendScratch is WriteBatch's scratch. The kernel reads every entry in place.
|
|
||||||
type sendScratch struct {
|
|
||||||
names [sendBatch]unix.RawSockaddrInet6
|
|
||||||
iovs [sendBatch]unix.Iovec
|
|
||||||
hdrs [sendBatch]msghdrX
|
|
||||||
// idx maps each entry back to its index in WriteBatch's bufs.
|
|
||||||
idx [sendBatch]int
|
|
||||||
}
|
|
||||||
|
|
||||||
// WriteBatch sends bufs with sendmsg_x, darwin's private batched sendmsg, so one syscall carries up to
|
|
||||||
// sendBatch datagrams. On this unconnected socket xnu still runs each message through sendit, so the
|
|
||||||
// saving is the syscall crossings, not the per-send policy checks.
|
|
||||||
//
|
|
||||||
// xnu's per-message loop stops at the first message that fails. For the errors in sentNothing it reports
|
|
||||||
// how many went out; for any other it returns only the errno, with the messages before it already sent.
|
|
||||||
// Each call therefore carries one run of datagrams to the same destination: a destination the kernel
|
|
||||||
// refuses fails on its first datagram, so a failed call costs that run and nothing else, and no datagram
|
|
||||||
// is ever resent after the kernel may have taken it.
|
|
||||||
//
|
|
||||||
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
|
||||||
// silently drops the rest of a burst (linux blocks instead). Poll for
|
|
||||||
// writability on EAGAIN before giving up on the remainder.
|
|
||||||
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
func (u *StdConn) WriteBatch(bufs [][]byte, addrs []netip.AddrPort) (int, error) {
|
||||||
if u.noSendmsgX.Load() {
|
// An un-sendable destination costs its own packet, never the ones behind it in the batch.
|
||||||
return u.writeEach(bufs, addrs), nil
|
// TODO: WriteTo maps EWOULDBLOCK to an error, so a full send buffer
|
||||||
}
|
// silently drops the rest of a burst (linux blocks instead). Poll for
|
||||||
if u.sb == nil {
|
// writability on EAGAIN before giving up on the remainder.
|
||||||
u.sb = new(sendScratch)
|
|
||||||
}
|
|
||||||
b := u.sb
|
|
||||||
written := 0
|
|
||||||
for i := 0; i < len(bufs); {
|
|
||||||
n := 0
|
|
||||||
for ; i < len(bufs) && n < sendBatch; i++ {
|
|
||||||
namelen, err := u.putSockaddr(&b.names[n], addrs[i])
|
|
||||||
if err != nil {
|
|
||||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
b.iovs[n] = unix.Iovec{}
|
|
||||||
if len(bufs[i]) > 0 {
|
|
||||||
b.iovs[n].Base = &bufs[i][0]
|
|
||||||
b.iovs[n].SetLen(len(bufs[i]))
|
|
||||||
}
|
|
||||||
b.hdrs[n] = msghdrX{Name: (*byte)(unsafe.Pointer(&b.names[n])), Namelen: namelen, Iov: &b.iovs[n], Iovlen: 1}
|
|
||||||
b.idx[n] = i
|
|
||||||
n++
|
|
||||||
}
|
|
||||||
|
|
||||||
for off := 0; off < n; {
|
|
||||||
dst := addrs[b.idx[off]]
|
|
||||||
end := off + 1
|
|
||||||
for end < n && addrs[b.idx[end]] == dst {
|
|
||||||
end++
|
|
||||||
}
|
|
||||||
sent, errno := u.sendmsgX(off, end)
|
|
||||||
switch {
|
|
||||||
case errno == 0 && sent > 0:
|
|
||||||
written += sent
|
|
||||||
off += sent
|
|
||||||
continue
|
|
||||||
case sentNothing(errno):
|
|
||||||
// The datagram at off failed on its own account. sendto delivers or reports it, as without
|
|
||||||
// batching, and the rest of the run goes back to sendmsg_x.
|
|
||||||
j := b.idx[off]
|
|
||||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
|
||||||
off++
|
|
||||||
continue
|
|
||||||
case errno == 0:
|
|
||||||
case errno == unix.ENOSYS || errno == unix.EOPNOTSUPP:
|
|
||||||
u.fallBack(errno)
|
|
||||||
case errno == unix.EPERM || errno == unix.EINVAL:
|
|
||||||
// Either can refuse one destination, but a datagram that sendto delivers was refused by
|
|
||||||
// sendmsg_x itself, as a sandbox or an older kernel would.
|
|
||||||
j := b.idx[off]
|
|
||||||
if u.writeEach(bufs[j:j+1], addrs[j:j+1]) == 0 {
|
|
||||||
off = end
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
written++
|
|
||||||
off++
|
|
||||||
u.fallBack(errno)
|
|
||||||
default:
|
|
||||||
u.l.Debug("failed to write packets in batch", "udpAddr", dst, "packets", end-off, "error", errno)
|
|
||||||
off = end
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
// The kernel took nothing from this call, so the rest can go out one datagram at a time.
|
|
||||||
for _, j := range b.idx[off:n] {
|
|
||||||
written += u.writeEach(bufs[j:j+1], addrs[j:j+1])
|
|
||||||
}
|
|
||||||
off = n
|
|
||||||
if u.noSendmsgX.Load() {
|
|
||||||
clear(b.iovs[:n])
|
|
||||||
return written + u.writeEach(bufs[i:], addrs[i:]), nil
|
|
||||||
}
|
|
||||||
}
|
|
||||||
clear(b.iovs[:n])
|
|
||||||
}
|
|
||||||
return written, nil
|
|
||||||
}
|
|
||||||
|
|
||||||
// sendmsgX hands entries off through end-1 of u.sb to sendmsg_x and returns how many the kernel took.
|
|
||||||
// The socket is non-blocking, so a full send buffer returns EAGAIN rather than waiting.
|
|
||||||
func (u *StdConn) sendmsgX(off, end int) (int, syscall.Errno) {
|
|
||||||
for {
|
|
||||||
r0, _, errno := unix.Syscall6(unix.SYS_SENDMSG_X, u.sysFd, uintptr(unsafe.Pointer(&u.sb.hdrs[off])), uintptr(end-off), 0, 0, 0)
|
|
||||||
if errno == unix.EINTR {
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
return int(r0), errno
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// sentNothing reports whether sendmsg_x failing with errno means no datagram went out: once any has, xnu
|
|
||||||
// turns these errors into a short count instead.
|
|
||||||
func sentNothing(errno syscall.Errno) bool {
|
|
||||||
return errno == unix.EWOULDBLOCK || errno == unix.ENOBUFS || errno == unix.EMSGSIZE
|
|
||||||
}
|
|
||||||
|
|
||||||
// fallBack switches WriteBatch to one sendto per datagram for the life of the socket.
|
|
||||||
func (u *StdConn) fallBack(errno syscall.Errno) {
|
|
||||||
if u.noSendmsgX.CompareAndSwap(false, true) {
|
|
||||||
u.l.Warn("sendmsg_x unavailable, sending one datagram per syscall", "error", errno)
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// writeEach sends bufs one at a time with WriteTo and returns how many were written.
|
|
||||||
func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
|
||||||
written := 0
|
written := 0
|
||||||
for i, b := range bufs {
|
for i, b := range bufs {
|
||||||
if err := u.WriteTo(b, addrs[i]); err == nil {
|
if err := u.WriteTo(b, addrs[i]); err == nil {
|
||||||
@@ -283,23 +152,7 @@ func (u *StdConn) writeEach(bufs [][]byte, addrs []netip.AddrPort) int {
|
|||||||
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
u.l.Debug("failed to write packet in batch", "udpAddr", addrs[i], "error", err)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return written
|
return written, nil
|
||||||
}
|
|
||||||
|
|
||||||
// putSockaddr writes ap into sa in the socket's address family, as WriteTo would, and returns its length.
|
|
||||||
func (u *StdConn) putSockaddr(sa *unix.RawSockaddrInet6, ap netip.AddrPort) (uint32, error) {
|
|
||||||
if u.isV4 {
|
|
||||||
if ap.Addr().Is6() {
|
|
||||||
return 0, ErrInvalidIPv6RemoteForSocket
|
|
||||||
}
|
|
||||||
sa4 := (*unix.RawSockaddrInet4)(unsafe.Pointer(sa))
|
|
||||||
*sa4 = unix.RawSockaddrInet4{Family: unix.AF_INET, Addr: ap.Addr().As4()}
|
|
||||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa4.Port))[:], ap.Port())
|
|
||||||
return unix.SizeofSockaddrInet4, nil
|
|
||||||
}
|
|
||||||
*sa = unix.RawSockaddrInet6{Family: unix.AF_INET6, Addr: ap.Addr().As16()}
|
|
||||||
binary.BigEndian.PutUint16((*[2]byte)(unsafe.Pointer(&sa.Port))[:], ap.Port())
|
|
||||||
return unix.SizeofSockaddrInet6, nil
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
func (u *StdConn) LocalAddr() (netip.AddrPort, error) {
|
||||||
@@ -327,121 +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.
|
|
||||||
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) {
|
||||||
@@ -456,19 +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
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -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")
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@@ -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
|
|
||||||
}
|
|
||||||
@@ -1,150 +0,0 @@
|
|||||||
//go:build !e2e_testing
|
|
||||||
|
|
||||||
package udp
|
|
||||||
|
|
||||||
import (
|
|
||||||
"fmt"
|
|
||||||
"log/slog"
|
|
||||||
"net"
|
|
||||||
"net/netip"
|
|
||||||
"testing"
|
|
||||||
"time"
|
|
||||||
|
|
||||||
"github.com/stretchr/testify/assert"
|
|
||||||
"github.com/stretchr/testify/require"
|
|
||||||
)
|
|
||||||
|
|
||||||
// recvAll reads n datagrams from pc, or fails the test after a second without one.
|
|
||||||
func recvAll(t *testing.T, pc net.PacketConn, n int) []string {
|
|
||||||
t.Helper()
|
|
||||||
var got []string
|
|
||||||
buf := make([]byte, 64)
|
|
||||||
for len(got) < n {
|
|
||||||
require.NoError(t, pc.SetReadDeadline(time.Now().Add(time.Second)))
|
|
||||||
l, _, err := pc.ReadFrom(buf)
|
|
||||||
require.NoError(t, err, "after %d of %d datagrams", len(got), n)
|
|
||||||
got = append(got, string(buf[:l]))
|
|
||||||
}
|
|
||||||
return got
|
|
||||||
}
|
|
||||||
|
|
||||||
// A batch longer than sendBatch reaches each peer whole and in order through sendmsg_x, without falling
|
|
||||||
// back to sendto: a run to one peer that spans two calls, then datagrams alternating between peers.
|
|
||||||
func TestWriteBatchSendsEachToItsPeer(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)
|
|
||||||
defer c.Close()
|
|
||||||
|
|
||||||
var peers [2]net.PacketConn
|
|
||||||
var dsts [2]netip.AddrPort
|
|
||||||
for i := range peers {
|
|
||||||
peers[i], err = net.ListenPacket("udp", net.JoinHostPort(tc.listen, "0"))
|
|
||||||
require.NoError(t, err)
|
|
||||||
defer peers[i].Close()
|
|
||||||
dsts[i] = netip.MustParseAddrPort(peers[i].LocalAddr().String())
|
|
||||||
}
|
|
||||||
|
|
||||||
const total = sendBatch*2 + 5
|
|
||||||
bufs := make([][]byte, total)
|
|
||||||
addrs := make([]netip.AddrPort, total)
|
|
||||||
var want [2][]string
|
|
||||||
for i := range bufs {
|
|
||||||
bufs[i] = fmt.Appendf(nil, "pkt-%03d", i)
|
|
||||||
p := i % 2
|
|
||||||
if i < sendBatch+6 {
|
|
||||||
p = 0
|
|
||||||
}
|
|
||||||
addrs[i] = dsts[p]
|
|
||||||
want[p] = append(want[p], string(bufs[i]))
|
|
||||||
}
|
|
||||||
|
|
||||||
n, err := c.WriteBatch(bufs, addrs)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, total, n)
|
|
||||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
|
||||||
for i := range peers {
|
|
||||||
assert.Equal(t, want[i], recvAll(t, peers[i], len(want[i])))
|
|
||||||
}
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Destinations that can't be sent to cost only their own packets: an IPv6 peer on an IPv4 socket is
|
|
||||||
// skipped before the call, and a broadcast address without SO_BROADCAST is refused by the kernel
|
|
||||||
// mid-batch. Neither stops the packets around it, delivers any twice, or turns sendmsg_x off.
|
|
||||||
func TestWriteBatchSkipsUnsendableDestinations(t *testing.T) {
|
|
||||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
|
||||||
require.NoError(t, err)
|
|
||||||
defer c.Close()
|
|
||||||
|
|
||||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
|
||||||
require.NoError(t, err)
|
|
||||||
defer peer.Close()
|
|
||||||
good := netip.MustParseAddrPort(peer.LocalAddr().String())
|
|
||||||
bcast := netip.AddrPortFrom(netip.MustParseAddr("255.255.255.255"), good.Port())
|
|
||||||
v6 := netip.MustParseAddrPort("[::1]:4242")
|
|
||||||
|
|
||||||
addrs := []netip.AddrPort{good, bcast, bcast, good, v6, good, bcast}
|
|
||||||
bufs := make([][]byte, len(addrs))
|
|
||||||
for i := range bufs {
|
|
||||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
|
||||||
}
|
|
||||||
|
|
||||||
n, err := c.WriteBatch(bufs, addrs)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, 3, n)
|
|
||||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
|
||||||
assert.Equal(t, []string{"pkt-0", "pkt-3", "pkt-5"}, recvAll(t, peer, 3))
|
|
||||||
require.NoError(t, peer.SetReadDeadline(time.Now().Add(100*time.Millisecond)))
|
|
||||||
_, _, err = peer.ReadFrom(make([]byte, 64))
|
|
||||||
assert.Error(t, err, "a datagram arrived twice")
|
|
||||||
}
|
|
||||||
|
|
||||||
// A datagram the kernel refuses as its own fault (EMSGSIZE here, as ENOBUFS would be under a full
|
|
||||||
// interface queue) costs only itself, whether it fails after others in the same call (a short count) or
|
|
||||||
// first (the errno alone): the rest of its run still arrives, in order, and sendmsg_x stays on.
|
|
||||||
func TestWriteBatchLosesOnlyTheFailedDatagram(t *testing.T) {
|
|
||||||
for _, tc := range []struct {
|
|
||||||
name string
|
|
||||||
big int
|
|
||||||
}{
|
|
||||||
{"mid-call", 2},
|
|
||||||
{"first", 0},
|
|
||||||
} {
|
|
||||||
t.Run(tc.name, func(t *testing.T) {
|
|
||||||
c, err := NewListener(slog.New(slog.DiscardHandler), Settings{Listen: netip.MustParseAddrPort("127.0.0.1:0")})
|
|
||||||
require.NoError(t, err)
|
|
||||||
defer c.Close()
|
|
||||||
|
|
||||||
peer, err := net.ListenPacket("udp", "127.0.0.1:0")
|
|
||||||
require.NoError(t, err)
|
|
||||||
defer peer.Close()
|
|
||||||
dst := netip.MustParseAddrPort(peer.LocalAddr().String())
|
|
||||||
|
|
||||||
bufs := make([][]byte, 5)
|
|
||||||
addrs := make([]netip.AddrPort, len(bufs))
|
|
||||||
var want []string
|
|
||||||
for i := range bufs {
|
|
||||||
addrs[i] = dst
|
|
||||||
if i == tc.big {
|
|
||||||
// Past the 65535-byte IP datagram limit, so the kernel can only refuse it.
|
|
||||||
bufs[i] = make([]byte, 70000)
|
|
||||||
continue
|
|
||||||
}
|
|
||||||
bufs[i] = fmt.Appendf(nil, "pkt-%d", i)
|
|
||||||
want = append(want, string(bufs[i]))
|
|
||||||
}
|
|
||||||
|
|
||||||
n, err := c.WriteBatch(bufs, addrs)
|
|
||||||
require.NoError(t, err)
|
|
||||||
assert.Equal(t, len(want), n)
|
|
||||||
assert.False(t, c.(*StdConn).noSendmsgX.Load(), "fell back to sendto")
|
|
||||||
assert.Equal(t, want, recvAll(t, peer, len(want)))
|
|
||||||
})
|
|
||||||
}
|
|
||||||
}
|
|
||||||
Reference in new issue
Block a user