contrib/internal/httptrace: store client ip in span tags (#1328)

contrib/internal/httptrace/httptrace.go

@@ -10,14 +10,37 @@ package httptrace
 import (
 	"context"
 	"fmt"
+	"net"
 	"net/http"
+	"os"
 	"strconv"
+	"strings"
+
+	"inet.af/netaddr"
 
 	"gopkg.in/DataDog/dd-trace-go.v1/ddtrace"
 	"gopkg.in/DataDog/dd-trace-go.v1/ddtrace/ext"
 	"gopkg.in/DataDog/dd-trace-go.v1/ddtrace/tracer"
 )
 
+var (
+	ipv6SpecialNetworks = []*netaddr.IPPrefix{
+		ippref("fec0::/10"), // site local
+	}
+	defaultIPHeaders = []string{
+		"x-forwarded-for",
+		"x-real-ip",
+		"x-client-ip",
+		"x-forwarded",
+		"x-cluster-client-ip",
+		"forwarded-for",
+		"forwarded",
+		"via",
+		"true-client-ip",
+	}
+	clientIPHeader = os.Getenv("DD_TRACE_CLIENT_IP_HEADER")
+)
+
 // StartRequestSpan starts an HTTP request span with the standard list of HTTP request span tags (http.method, http.url,
 // http.useragent). Any further span start option can be added with opts.
 func StartRequestSpan(r *http.Request, opts ...ddtrace.StartSpanOption) (tracer.Span, context.Context) {
@@ -34,6 +57,9 @@ func StartRequestSpan(r *http.Request, opts ...ddtrace.StartSpanOption) (tracer.
 			tracer.Tag("http.host", r.Host),
 		}, opts...)
 	}
+	if ip := getClientIP(r); ip.IsValid() {
+		opts = append(opts, tracer.Tag(ext.HTTPClientIP, ip.String()))
+	}
 	if spanctx, err := tracer.Extract(tracer.HTTPHeadersCarrier(r.Header)); err == nil {
 		opts = append(opts, tracer.ChildOf(spanctx))
 	}
@@ -55,3 +81,70 @@ func FinishRequestSpan(s tracer.Span, status int, opts ...tracer.FinishOption) {
 	}
 	s.Finish(opts...)
 }
+
+// ippref returns the IP network from an IP address string s. If not possible, it returns nil.
+func ippref(s string) *netaddr.IPPrefix {
+	if prefix, err := netaddr.ParseIPPrefix(s); err == nil {
+		return &prefix
+	}
+	return nil
+}
+
+// getClientIP attempts to find the client IP address in the given request r.
+func getClientIP(r *http.Request) netaddr.IP {
+	ipHeaders := defaultIPHeaders
+	if len(clientIPHeader) > 0 {
+		ipHeaders = []string{clientIPHeader}
+	}
+	check := func(s string) netaddr.IP {
+		for _, ipstr := range strings.Split(s, ",") {
+			ip := parseIP(strings.TrimSpace(ipstr))
+			if !ip.IsValid() {
+				continue
+			}
+			if isGlobal(ip) {
+				return ip
+			}
+		}
+		return netaddr.IP{}
+	}
+	for _, hdr := range ipHeaders {
+		if v := r.Header.Get(hdr); v != "" {
+			if ip := check(v); ip.IsValid() {
+				return ip
+			}
+		}
+	}
+	if remoteIP := parseIP(r.RemoteAddr); remoteIP.IsValid() && isGlobal(remoteIP) {
+		return remoteIP
+	}
+	return netaddr.IP{}
+}
+
+func parseIP(s string) netaddr.IP {
+	if ip, err := netaddr.ParseIP(s); err == nil {
+		return ip
+	}
+	if h, _, err := net.SplitHostPort(s); err == nil {
+		if ip, err := netaddr.ParseIP(h); err == nil {
+			return ip
+		}
+	}
+	return netaddr.IP{}
+}
+
+func isGlobal(ip netaddr.IP) bool {
+	// IsPrivate also checks for ipv6 ULA.
+	// We care to check for these addresses are not considered public, hence not global.
+	// See https://www.rfc-editor.org/rfc/rfc4193.txt for more details.
+	isGlobal := !ip.IsPrivate() && !ip.IsLoopback() && !ip.IsLinkLocalUnicast()
+	if !isGlobal || !ip.Is6() {
+		return isGlobal
+	}
+	for _, n := range ipv6SpecialNetworks {
+		if n.Contains(ip) {
+			return false
+		}
+	}
+	return isGlobal
+}

contrib/internal/httptrace/httptrace_test.go

@@ -6,10 +6,13 @@
 package httptrace
 
 import (
+	"math/rand"
 	"net/http"
 	"net/http/httptest"
 	"testing"
 
+	"inet.af/netaddr"
+
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -27,3 +30,201 @@ func TestStartRequestSpan(t *testing.T) {
 	require.Len(t, spans, 1)
 	assert.Equal(t, "example.com", spans[0].Tag("http.host"))
 }
+
+type IPTestCase struct {
+	name           string
+	remoteAddr     string
+	headers        map[string]string
+	expectedIP     netaddr.IP
+	clientIPHeader string
+}
+
+func genIPTestCases() []IPTestCase {
+	ipv4Global := randGlobalIPv4().String()
+	ipv6Global := randGlobalIPv6().String()
+	ipv4Private := randPrivateIPv4().String()
+	ipv6Private := randPrivateIPv6().String()
+	tcs := []IPTestCase{}
+	// Simple ipv4 test cases over all headers
+	for _, header := range defaultIPHeaders {
+		tcs = append(tcs, IPTestCase{
+			name:       "ipv4-global." + header,
+			headers:    map[string]string{header: ipv4Global},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		})
+		tcs = append(tcs, IPTestCase{
+			name:       "ipv4-private." + header,
+			headers:    map[string]string{header: ipv4Private},
+			expectedIP: netaddr.IP{},
+		})
+	}
+	// Simple ipv6 test cases over all headers
+	for _, header := range defaultIPHeaders {
+		tcs = append(tcs, IPTestCase{
+			name:       "ipv6-global." + header,
+			headers:    map[string]string{header: ipv6Global},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		})
+		tcs = append(tcs, IPTestCase{
+			name:       "ipv6-private." + header,
+			headers:    map[string]string{header: ipv6Private},
+			expectedIP: netaddr.IP{},
+		})
+	}
+	// private and global in same header
+	tcs = append([]IPTestCase{
+		{
+			name:       "ipv4-private+global",
+			headers:    map[string]string{"x-forwarded-for": ipv4Private + "," + ipv4Global},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		},
+		{
+			name:       "ipv4-global+private",
+			headers:    map[string]string{"x-forwarded-for": ipv4Global + "," + ipv4Private},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		},
+		{
+			name:       "ipv6-private+global",
+			headers:    map[string]string{"x-forwarded-for": ipv6Private + "," + ipv6Global},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		},
+		{
+			name:       "ipv6-global+private",
+			headers:    map[string]string{"x-forwarded-for": ipv6Global + "," + ipv6Private},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		},
+	}, tcs...)
+	// Invalid IPs (or a mix of valid/invalid over a single or multiple headers)
+	tcs = append([]IPTestCase{
+		{
+			name:       "invalid-ipv4",
+			headers:    map[string]string{"x-forwarded-for": "127..0.0.1"},
+			expectedIP: netaddr.IP{},
+		},
+		{
+			name:       "invalid-ipv4-recover",
+			headers:    map[string]string{"x-forwarded-for": "127..0.0.1, " + ipv4Global},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		},
+		{
+			name:       "invalid-ipv4-recover-multi-header-1",
+			headers:    map[string]string{"x-forwarded-for": "127..0.0.1", "forwarded-for": ipv4Global},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		},
+		{
+			name:       "invalid-ipv4-recover-multi-header-2",
+			headers:    map[string]string{"forwarded-for": ipv4Global, "x-forwarded-for": "127..0.0.1"},
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+		},
+		{
+			name:       "invalid-ipv6",
+			headers:    map[string]string{"x-forwarded-for": "2001:0db8:2001:zzzz::"},
+			expectedIP: netaddr.IP{},
+		},
+		{
+			name:       "invalid-ipv6-recover",
+			headers:    map[string]string{"x-forwarded-for": "2001:0db8:2001:zzzz::, " + ipv6Global},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		},
+		{
+			name:       "invalid-ipv6-recover-multi-header-1",
+			headers:    map[string]string{"x-forwarded-for": "2001:0db8:2001:zzzz::", "forwarded-for": ipv6Global},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		},
+		{
+			name:       "invalid-ipv6-recover-multi-header-2",
+			headers:    map[string]string{"forwarded-for": ipv6Global, "x-forwarded-for": "2001:0db8:2001:zzzz::"},
+			expectedIP: netaddr.MustParseIP(ipv6Global),
+		},
+	}, tcs...)
+	tcs = append([]IPTestCase{
+		{
+			name:       "no-headers",
+			expectedIP: netaddr.IP{},
+		},
+		{
+			name:       "header-case",
+			expectedIP: netaddr.MustParseIP(ipv4Global),
+			headers:    map[string]string{"X-fOrWaRdEd-FoR": ipv4Global},
+		},
+		{
+			name:           "user-header",
+			expectedIP:     netaddr.MustParseIP(ipv4Global),
+			headers:        map[string]string{"x-forwarded-for": ipv6Global, "custom-header": ipv4Global},
+			clientIPHeader: "custom-header",
+		},
+		{
+			name:           "user-header-not-found",
+			expectedIP:     netaddr.IP{},
+			headers:        map[string]string{"x-forwarded-for": ipv4Global},
+			clientIPHeader: "custom-header",
+		},
+	}, tcs...)
+
+	return tcs
+}
+
+func TestIPHeaders(t *testing.T) {
+	// Make sure to restore the real value of clientIPHeader at the end of the test
+	defer func(s string) { clientIPHeader = s }(clientIPHeader)
+	for _, tc := range genIPTestCases() {
+		t.Run(tc.name, func(t *testing.T) {
+			header := http.Header{}
+			for k, v := range tc.headers {
+				header.Add(k, v)
+			}
+			r := http.Request{Header: header, RemoteAddr: tc.remoteAddr}
+			clientIPHeader = tc.clientIPHeader
+			require.Equal(t, tc.expectedIP.String(), getClientIP(&r).String())
+		})
+	}
+}
+
+func randIPv4() netaddr.IP {
+	return netaddr.IPv4(uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()))
+}
+
+func randIPv6() netaddr.IP {
+	return netaddr.IPv6Raw([16]byte{
+		uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()),
+		uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()),
+		uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()),
+		uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()), uint8(rand.Uint32()),
+	})
+}
+
+func randGlobalIPv4() netaddr.IP {
+	for {
+		ip := randIPv4()
+		if isGlobal(ip) {
+			return ip
+		}
+	}
+}
+
+func randGlobalIPv6() netaddr.IP {
+	for {
+		ip := randIPv6()
+		if isGlobal(ip) {
+			return ip
+		}
+	}
+}
+
+func randPrivateIPv4() netaddr.IP {
+	for {
+		ip := randIPv4()
+		if !isGlobal(ip) && ip.IsPrivate() {
+			return ip
+		}
+	}
+}
+
+func randPrivateIPv6() netaddr.IP {
+	for {
+		ip := randIPv6()
+		if !isGlobal(ip) && ip.IsPrivate() {
+			return ip
+		}
+	}
+}

ddtrace/ext/tags.go

@@ -36,6 +36,9 @@ const (
 	// HTTPUserAgent is the user agent header value of the HTTP request.
 	HTTPUserAgent = "http.useragent"
 
+	// HTTPClientIP sets the HTTP client IP tag.
+	HTTPClientIP = "http.client_ip"
+
 	// SpanName is a pseudo-key for setting a span's operation name by means of
 	// a tag. It is mostly here to facilitate vendor-agnostic frameworks like Opentracing
 	// and OpenCensus.

go.mod

@@ -105,6 +105,7 @@ require (
 	gorm.io/driver/postgres v1.0.0
 	gorm.io/driver/sqlserver v1.0.4
 	gorm.io/gorm v1.20.6
+	inet.af/netaddr v0.0.0-20211027220019-c74959edd3b6
 	k8s.io/apimachinery v0.17.0
 	k8s.io/client-go v0.17.0
 )

go.sum

@@ -140,6 +140,7 @@ github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cu
 github.com/docker/spdystream v0.0.0-20160310174837-449fdfce4d96/go.mod h1:Qh8CwZgvJUkLughtfhJv5dyTYa91l1fOUCrgjqmcifM=
 github.com/dustin/go-humanize v1.0.0 h1:VSnTsYCnlFHaM2/igO1h6X3HA71jcobQuxemgkq4zYo=
 github.com/dustin/go-humanize v1.0.0/go.mod h1:HtrtbFcZ19U5GC7JDqmcUSB87Iq5E25KnS6fMYU6eOk=
+github.com/dvyukov/go-fuzz v0.0.0-20210103155950-6a8e9d1f2415/go.mod h1:11Gm+ccJnvAhCNLlf5+cS9KjtbaD5I5zaZpFMsTHWTw=
 github.com/eapache/go-resiliency v1.1.0 h1:1NtRmCAqadE2FN4ZcN6g90TP3uk8cg9rn9eNK2197aU=
 github.com/eapache/go-resiliency v1.1.0/go.mod h1:kFI+JgMyC7bLPUVY133qvEBtVayf5mFgVsvEsIPBvNs=
 github.com/eapache/go-xerial-snappy v0.0.0-20180814174437-776d5712da21 h1:YEetp8/yCZMuEPMUDHG0CW/brkkEp8mzqk2+ODEitlw=
@@ -793,6 +794,10 @@ go.uber.org/tools v0.0.0-20190618225709-2cfd321de3ee/go.mod h1:vJERXedbb3MVM5f9E
 go.uber.org/zap v1.9.1/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.13.0/go.mod h1:zwrFLgMcdUuIBviXEYEH1YKNaOBnKXsx2IPda5bBwHM=
+go4.org/intern v0.0.0-20211027215823-ae77deb06f29 h1:UXLjNohABv4S58tHmeuIZDO6e3mHpW2Dx33gaNt03LE=
+go4.org/intern v0.0.0-20211027215823-ae77deb06f29/go.mod h1:cS2ma+47FKrLPdXFpr7CuxiTW3eyJbWew4qx0qtQWDA=
+go4.org/unsafe/assume-no-moving-gc v0.0.0-20211027215541-db492cf91b37 h1:Tx9kY6yUkLge/pFG7IEMwDZy6CS2ajFc9TvQdPCW0uA=
+go4.org/unsafe/assume-no-moving-gc v0.0.0-20211027215541-db492cf91b37/go.mod h1:FftLjUGFEDu5k8lt0ddY+HcrH/qU/0qk+H8j9/nTl3E=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20180910181607-0e37d006457b/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20181029021203-45a5f77698d3/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
@@ -966,6 +971,7 @@ golang.org/x/sys v0.0.0-20200905004654-be1d3432aa8f/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210112080510-489259a85091/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210119212857-b64e53b001e4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210514084401-e8d321eab015/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -1049,8 +1055,9 @@ golang.org/x/tools v0.0.0-20200515010526-7d3b6ebf133d/go.mod h1:EkVYQZoAsY45+roY
 golang.org/x/tools v0.0.0-20200527183253-8e7acdbce89d/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
-golang.org/x/tools v0.0.0-20210106214847-113979e3529a h1:CB3a9Nez8M13wwlr/E2YtwoU+qYHKfC+JrDa45RXXoQ=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
+golang.org/x/tools v0.1.0 h1:po9/4sTYwZU9lPhi1tOrb4hCv3qrhiQ77LZfGa2OjwY=
+golang.org/x/tools v0.1.0/go.mod h1:xkSsbof2nBLbhDlRMhhhyNLN/zl3eTqcnHD5viDpcZ0=
 golang.org/x/xerrors v0.0.0-20190410155217-1f06c39b4373/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20190513163551-3ee3066db522/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -1185,6 +1192,8 @@ honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt
 honnef.co/go/tools v0.0.1-2020.1.3/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
 honnef.co/go/tools v0.0.1-2020.1.4 h1:UoveltGrhghAA7ePc+e+QYDHXrBps2PqFZiHkGR/xK8=
 honnef.co/go/tools v0.0.1-2020.1.4/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
+inet.af/netaddr v0.0.0-20211027220019-c74959edd3b6 h1:acCzuUSQ79tGsM/O50VRFySfMm19IoMKL+sZztZkCxw=
+inet.af/netaddr v0.0.0-20211027220019-c74959edd3b6/go.mod h1:y3MGhcFMlh0KZPMuXXow8mpjxxAk3yoDNsp4cQz54i8=
 k8s.io/api v0.17.0 h1:H9d/lw+VkZKEVIUc8F3wgiQ+FUXTTr21M87jXLU7yqM=
 k8s.io/api v0.17.0/go.mod h1:npsyOePkeP0CPwyGfXDHxvypiYMJxBWAMpQxCaJ4ZxI=
 k8s.io/apimachinery v0.17.0 h1:xRBnuie9rXcPxUkDizUsGvPf1cnlZCFu210op7J7LJo=